diff options
Diffstat (limited to 'tools')
444 files changed, 31512 insertions, 4548 deletions
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index f8129c624b070..f7ddd73a8c0fa 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -198,6 +198,15 @@ struct kvm_arm_copy_mte_tags { __u64 reserved[2]; }; +/* + * Counter/Timer offset structure. Describe the virtual/physical offset. + * To be used with KVM_ARM_SET_COUNTER_OFFSET. + */ +struct kvm_arm_counter_offset { + __u64 counter_offset; + __u64 reserved; +}; + #define KVM_ARM_TAGS_TO_GUEST 0 #define KVM_ARM_TAGS_FROM_GUEST 1 @@ -372,6 +381,10 @@ enum { #endif }; +/* Device Control API on vm fd */ +#define KVM_ARM_VM_SMCCC_CTRL 0 +#define KVM_ARM_VM_SMCCC_FILTER 0 + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 @@ -411,6 +424,8 @@ enum { #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 +#define KVM_ARM_VCPU_TIMER_IRQ_HVTIMER 2 +#define KVM_ARM_VCPU_TIMER_IRQ_HPTIMER 3 #define KVM_ARM_VCPU_PVTIME_CTRL 2 #define KVM_ARM_VCPU_PVTIME_IPA 0 @@ -469,6 +484,27 @@ enum { /* run->fail_entry.hardware_entry_failure_reason codes. */ #define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED (1ULL << 0) +enum kvm_smccc_filter_action { + KVM_SMCCC_FILTER_HANDLE = 0, + KVM_SMCCC_FILTER_DENY, + KVM_SMCCC_FILTER_FWD_TO_USER, + +#ifdef __KERNEL__ + NR_SMCCC_FILTER_ACTIONS +#endif +}; + +struct kvm_smccc_filter { + __u32 base; + __u32 nr_functions; + __u8 action; + __u8 pad[15]; +}; + +/* arm64-specific KVM_EXIT_HYPERCALL flags */ +#define KVM_HYPERCALL_EXIT_SMC (1U << 0) +#define KVM_HYPERCALL_EXIT_16BIT (1U << 1) + #endif #endif /* __ARM_KVM_H__ */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index b89005819cd55..cb8ca46213bed 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -97,7 +97,7 @@ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ +/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ #define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ @@ -226,10 +226,9 @@ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ -#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ -#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ -#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ -#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 2) /* Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 3) /* Intel Virtual Processor ID */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ @@ -307,14 +306,21 @@ #define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* "" SGX EDECCSSA user leaf function */ #define X86_FEATURE_CALL_DEPTH (11*32+19) /* "" Call depth tracking for RSB stuffing */ #define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ +#define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ +#define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ #define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */ +#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* "" Intel Architectural PerfMon Extension */ +#define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ +#define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ +#define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ #define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ #define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ #define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ +#define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ @@ -331,6 +337,7 @@ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ +#define X86_FEATURE_AMD_PSFD (13*32+28) /* "" Predictive Store Forwarding Disable */ #define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ #define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ @@ -363,6 +370,7 @@ #define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ #define X86_FEATURE_X2AVIC (15*32+18) /* Virtual x2apic */ #define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */ +#define X86_FEATURE_VNMI (15*32+25) /* Virtual NMI */ #define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ @@ -427,6 +435,13 @@ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ +#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */ +#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */ +#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* "" Null Selector Clears Base */ +#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ +#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* "" SMM_CTL MSR is not present */ + /* * BUG word(s) */ @@ -467,5 +482,6 @@ #define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ #define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 5dfa4fb76f4b2..fafe9be7a6f4f 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -75,6 +75,12 @@ # define DISABLE_CALL_DEPTH_TRACKING (1 << (X86_FEATURE_CALL_DEPTH & 31)) #endif +#ifdef CONFIG_ADDRESS_MASKING +# define DISABLE_LAM 0 +#else +# define DISABLE_LAM (1 << (X86_FEATURE_LAM & 31)) +#endif + #ifdef CONFIG_INTEL_IOMMU_SVM # define DISABLE_ENQCMD 0 #else @@ -115,7 +121,7 @@ #define DISABLED_MASK10 0 #define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \ DISABLE_CALL_DEPTH_TRACKING) -#define DISABLED_MASK12 0 +#define DISABLED_MASK12 (DISABLE_LAM) #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index ad35355ee43ea..3aedae61af4fc 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -206,6 +206,8 @@ /* Abbreviated from Intel SDM name IA32_INTEGRITY_CAPABILITIES */ #define MSR_INTEGRITY_CAPS 0x000002d9 +#define MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT 2 +#define MSR_INTEGRITY_CAPS_ARRAY_BIST BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT) #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT 4 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT) diff --git a/tools/arch/x86/include/asm/nops.h b/tools/arch/x86/include/asm/nops.h index c5573eaa5bb98..1c1b7550fa550 100644 --- a/tools/arch/x86/include/asm/nops.h +++ b/tools/arch/x86/include/asm/nops.h @@ -34,6 +34,8 @@ #define BYTES_NOP7 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00 #define BYTES_NOP8 0x3e,BYTES_NOP7 +#define ASM_NOP_MAX 8 + #else /* @@ -47,6 +49,9 @@ * 6: osp nopl 0x00(%eax,%eax,1) * 7: nopl 0x00000000(%eax) * 8: nopl 0x00000000(%eax,%eax,1) + * 9: cs nopl 0x00000000(%eax,%eax,1) + * 10: osp cs nopl 0x00000000(%eax,%eax,1) + * 11: osp osp cs nopl 0x00000000(%eax,%eax,1) */ #define BYTES_NOP1 0x90 #define BYTES_NOP2 0x66,BYTES_NOP1 @@ -56,6 +61,15 @@ #define BYTES_NOP6 0x66,BYTES_NOP5 #define BYTES_NOP7 0x0f,0x1f,0x80,0x00,0x00,0x00,0x00 #define BYTES_NOP8 0x0f,0x1f,0x84,0x00,0x00,0x00,0x00,0x00 +#define BYTES_NOP9 0x2e,BYTES_NOP8 +#define BYTES_NOP10 0x66,BYTES_NOP9 +#define BYTES_NOP11 0x66,BYTES_NOP10 + +#define ASM_NOP9 _ASM_BYTES(BYTES_NOP9) +#define ASM_NOP10 _ASM_BYTES(BYTES_NOP10) +#define ASM_NOP11 _ASM_BYTES(BYTES_NOP11) + +#define ASM_NOP_MAX 11 #endif /* CONFIG_64BIT */ @@ -68,8 +82,6 @@ #define ASM_NOP7 _ASM_BYTES(BYTES_NOP7) #define ASM_NOP8 _ASM_BYTES(BYTES_NOP8) -#define ASM_NOP_MAX 8 - #ifndef __ASSEMBLY__ extern const unsigned char * const x86_nops[]; #endif diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 7f467fe05d42e..1a6a1f9879496 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -559,4 +559,7 @@ struct kvm_pmu_event_filter { #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ +/* x86-specific KVM_EXIT_HYPERCALL flags. */ +#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) + #endif /* _ASM_X86_KVM_H */ diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h index 500b96e71f186..e8d7ebbca1a4d 100644 --- a/tools/arch/x86/include/uapi/asm/prctl.h +++ b/tools/arch/x86/include/uapi/asm/prctl.h @@ -16,8 +16,16 @@ #define ARCH_GET_XCOMP_GUEST_PERM 0x1024 #define ARCH_REQ_XCOMP_GUEST_PERM 0x1025 +#define ARCH_XCOMP_TILECFG 17 +#define ARCH_XCOMP_TILEDATA 18 + #define ARCH_MAP_VDSO_X32 0x2001 #define ARCH_MAP_VDSO_32 0x2002 #define ARCH_MAP_VDSO_64 0x2003 +#define ARCH_GET_UNTAG_MASK 0x4001 +#define ARCH_ENABLE_TAGGED_ADDR 0x4002 +#define ARCH_GET_MAX_TAG_BITS 0x4003 +#define ARCH_FORCE_TAGGED_SVA 0x4004 + #endif /* _ASM_X86_PRCTL_H */ diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h index b8ddfc4c4ab04..bc48a4dabe5db 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_32.h +++ b/tools/arch/x86/include/uapi/asm/unistd_32.h @@ -2,6 +2,9 @@ #ifndef __NR_fork #define __NR_fork 2 #endif +#ifndef __NR_execve +#define __NR_execve 11 +#endif #ifndef __NR_getppid #define __NR_getppid 64 #endif diff --git a/tools/arch/x86/kcpuid/.gitignore b/tools/arch/x86/kcpuid/.gitignore new file mode 100644 index 0000000000000..1b8541bc8dd06 --- /dev/null +++ b/tools/arch/x86/kcpuid/.gitignore @@ -0,0 +1 @@ +kcpuid diff --git a/tools/arch/x86/kcpuid/kcpuid.c b/tools/arch/x86/kcpuid/kcpuid.c index 416f5b35dd8f4..24b7d017ec2c1 100644 --- a/tools/arch/x86/kcpuid/kcpuid.c +++ b/tools/arch/x86/kcpuid/kcpuid.c @@ -517,15 +517,16 @@ static void show_range(struct cpuid_range *range) static inline struct cpuid_func *index_to_func(u32 index) { struct cpuid_range *range; + u32 func_idx; range = (index & 0x80000000) ? leafs_ext : leafs_basic; - index &= 0x7FFFFFFF; + func_idx = index & 0xffff; - if (((index & 0xFFFF) + 1) > (u32)range->nr) { + if ((func_idx + 1) > (u32)range->nr) { printf("ERR: invalid input index (0x%x)\n", index); return NULL; } - return &range->funcs[index]; + return &range->funcs[func_idx]; } static void show_info(void) diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index a91ac666f7582..d055b82d22ccd 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -10,13 +10,6 @@ .section .noinstr.text, "ax" /* - * We build a jump to memcpy_orig by default which gets NOPped out on - * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which - * have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs - * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. - */ - -/* * memcpy - Copy a memory block. * * Input: @@ -26,17 +19,21 @@ * * Output: * rax original destination + * + * The FSRM alternative should be done inline (avoiding the call and + * the disgusting return handling), but that would require some help + * from the compiler for better calling conventions. + * + * The 'rep movsb' itself is small enough to replace the call, but the + * two register moves blow up the code. And one of them is "needed" + * only for the return value that is the same as the source input, + * which the compiler could/should do much better anyway. */ SYM_TYPED_FUNC_START(__memcpy) - ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp memcpy_erms", X86_FEATURE_ERMS + ALTERNATIVE "jmp memcpy_orig", "", X86_FEATURE_FSRM movq %rdi, %rax movq %rdx, %rcx - shrq $3, %rcx - andl $7, %edx - rep movsq - movl %edx, %ecx rep movsb RET SYM_FUNC_END(__memcpy) @@ -45,17 +42,6 @@ EXPORT_SYMBOL(__memcpy) SYM_FUNC_ALIAS(memcpy, __memcpy) EXPORT_SYMBOL(memcpy) -/* - * memcpy_erms() - enhanced fast string memcpy. This is faster and - * simpler than memcpy. Use memcpy_erms when possible. - */ -SYM_FUNC_START_LOCAL(memcpy_erms) - movq %rdi, %rax - movq %rdx, %rcx - rep movsb - RET -SYM_FUNC_END(memcpy_erms) - SYM_FUNC_START_LOCAL(memcpy_orig) movq %rdi, %rax diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index 6143b1a6fa2ca..7c59a704c4584 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -18,27 +18,22 @@ * rdx count (bytes) * * rax original destination + * + * The FSRS alternative should be done inline (avoiding the call and + * the disgusting return handling), but that would require some help + * from the compiler for better calling conventions. + * + * The 'rep stosb' itself is small enough to replace the call, but all + * the register moves blow up the code. And two of them are "needed" + * only for the return value that is the same as the source input, + * which the compiler could/should do much better anyway. */ SYM_FUNC_START(__memset) - /* - * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended - * to use it when possible. If not available, use fast string instructions. - * - * Otherwise, use original memset function. - */ - ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp memset_erms", X86_FEATURE_ERMS + ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS movq %rdi,%r9 + movb %sil,%al movq %rdx,%rcx - andl $7,%edx - shrq $3,%rcx - /* expand byte value */ - movzbl %sil,%esi - movabs $0x0101010101010101,%rax - imulq %rsi,%rax - rep stosq - movl %edx,%ecx rep stosb movq %r9,%rax RET @@ -48,26 +43,6 @@ EXPORT_SYMBOL(__memset) SYM_FUNC_ALIAS(memset, __memset) EXPORT_SYMBOL(memset) -/* - * ISO C memset - set a memory block to a byte value. This function uses - * enhanced rep stosb to override the fast string function. - * The code is simpler and shorter than the fast string function as well. - * - * rdi destination - * rsi value (char) - * rdx count (bytes) - * - * rax original destination - */ -SYM_FUNC_START_LOCAL(memset_erms) - movq %rdi,%r9 - movb %sil,%al - movq %rdx,%rcx - rep stosb - movq %r9,%rax - RET -SYM_FUNC_END(memset_erms) - SYM_FUNC_START_LOCAL(memset_orig) movq %rdi,%r10 diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 11250c4734fe8..3b7ba037af95d 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -28,7 +28,7 @@ MAP COMMANDS | **bpftool** **map** { **show** | **list** } [*MAP*] | **bpftool** **map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* \ | **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] \ -| [**dev** *NAME*] +| [**offload_dev** *NAME*] | **bpftool** **map dump** *MAP* | **bpftool** **map update** *MAP* [**key** *DATA*] [**value** *VALUE*] [*UPDATE_FLAGS*] | **bpftool** **map lookup** *MAP* [**key** *DATA*] @@ -73,7 +73,7 @@ DESCRIPTION maps. On such kernels bpftool will automatically emit this information as well. - **bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] [**dev** *NAME*] + **bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] [**offload_dev** *NAME*] Create a new map with given parameters and pin it to *bpffs* as *FILE*. @@ -86,8 +86,8 @@ DESCRIPTION kernel needs it to collect metadata related to the inner maps that the new map will work with. - Keyword **dev** expects a network interface name, and is used - to request hardware offload for the map. + Keyword **offload_dev** expects a network interface name, + and is used to request hardware offload for the map. **bpftool map dump** *MAP* Dump all entries in a given *MAP*. In case of **name**, diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 9443c524bb763..dcae81bd27ed2 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -31,7 +31,7 @@ PROG COMMANDS | **bpftool** **prog dump xlated** *PROG* [{ **file** *FILE* | [**opcodes**] [**linum**] [**visual**] }] | **bpftool** **prog dump jited** *PROG* [{ **file** *FILE* | [**opcodes**] [**linum**] }] | **bpftool** **prog pin** *PROG* *FILE* -| **bpftool** **prog** { **load** | **loadall** } *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] +| **bpftool** **prog** { **load** | **loadall** } *OBJ* *PATH* [**type** *TYPE*] [**map** { **idx** *IDX* | **name** *NAME* } *MAP*] [{ **offload_dev** | **xdpmeta_dev** } *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] | **bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog tracelog** @@ -129,7 +129,7 @@ DESCRIPTION contain a dot character ('.'), which is reserved for future extensions of *bpffs*. - **bpftool prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] + **bpftool prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** { **idx** *IDX* | **name** *NAME* } *MAP*] [{ **offload_dev** | **xdpmeta_dev** } *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] Load bpf program(s) from binary *OBJ* and pin as *PATH*. **bpftool prog load** pins only the first program from the *OBJ* as *PATH*. **bpftool prog loadall** pins all programs @@ -143,8 +143,11 @@ DESCRIPTION to be replaced in the ELF file counting from 0, while *NAME* allows to replace a map by name. *MAP* specifies the map to use, referring to it by **id** or through a **pinned** file. - If **dev** *NAME* is specified program will be loaded onto - given networking device (offload). + If **offload_dev** *NAME* is specified program will be loaded + onto given networking device (offload). + If **xdpmeta_dev** *NAME* is specified program will become + device-bound without offloading, this facilitates access + to XDP metadata. Optional **pinmaps** argument can be provided to pin all maps under *MAP_DIR* directory. diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index e7234d1a53068..085bf18f3659a 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -278,7 +278,7 @@ _bpftool() _bpftool_get_prog_tags return 0 ;; - dev) + dev|offload_dev|xdpmeta_dev) _sysfs_get_netdevs return 0 ;; @@ -508,7 +508,8 @@ _bpftool() ;; *) COMPREPLY=( $( compgen -W "map" -- "$cur" ) ) - _bpftool_once_attr 'type dev pinmaps autoattach' + _bpftool_once_attr 'type pinmaps autoattach' + _bpftool_one_of_list 'offload_dev xdpmeta_dev' return 0 ;; esac @@ -733,7 +734,7 @@ _bpftool() esac ;; *) - _bpftool_once_attr 'type key value entries name flags dev' + _bpftool_once_attr 'type key value entries name flags offload_dev' if _bpftool_search_list 'array_of_maps' 'hash_of_maps'; then _bpftool_once_attr 'inner_map' fi diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 1360c82ae732f..cc6e6aae2447d 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -68,7 +68,7 @@ void p_info(const char *fmt, ...) va_end(ap); } -static bool is_bpffs(char *path) +static bool is_bpffs(const char *path) { struct statfs st_fs; @@ -244,13 +244,16 @@ int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type) return fd; } -int mount_bpffs_for_pin(const char *name) +int mount_bpffs_for_pin(const char *name, bool is_dir) { char err_str[ERR_MAX_LEN]; char *file; char *dir; int err = 0; + if (is_dir && is_bpffs(name)) + return err; + file = malloc(strlen(name) + 1); if (!file) { p_err("mem alloc failed"); @@ -286,7 +289,7 @@ int do_pin_fd(int fd, const char *name) { int err; - err = mount_bpffs_for_pin(name); + err = mount_bpffs_for_pin(name, false); if (err) return err; diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index da16e6a27cccd..0675d6a464138 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -167,12 +167,12 @@ static int get_vendor_id(int ifindex) return strtol(buf, NULL, 0); } -static int read_procfs(const char *path) +static long read_procfs(const char *path) { char *endptr, *line = NULL; size_t len = 0; FILE *fd; - int res; + long res; fd = fopen(path, "r"); if (!fd) @@ -194,7 +194,7 @@ static int read_procfs(const char *path) static void probe_unprivileged_disabled(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -216,14 +216,14 @@ static void probe_unprivileged_disabled(void) printf("Unable to retrieve required privileges for bpf() syscall\n"); break; default: - printf("bpf() syscall restriction has unknown value %d\n", res); + printf("bpf() syscall restriction has unknown value %ld\n", res); } } } static void probe_jit_enable(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -245,7 +245,7 @@ static void probe_jit_enable(void) printf("Unable to retrieve JIT-compiler status\n"); break; default: - printf("JIT-compiler status has unknown value %d\n", + printf("JIT-compiler status has unknown value %ld\n", res); } } @@ -253,7 +253,7 @@ static void probe_jit_enable(void) static void probe_jit_harden(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -275,7 +275,7 @@ static void probe_jit_harden(void) printf("Unable to retrieve JIT hardening status\n"); break; default: - printf("JIT hardening status has unknown value %d\n", + printf("JIT hardening status has unknown value %ld\n", res); } } @@ -283,7 +283,7 @@ static void probe_jit_harden(void) static void probe_jit_kallsyms(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -302,14 +302,14 @@ static void probe_jit_kallsyms(void) printf("Unable to retrieve JIT kallsyms export status\n"); break; default: - printf("JIT kallsyms exports status has unknown value %d\n", res); + printf("JIT kallsyms exports status has unknown value %ld\n", res); } } } static void probe_jit_limit(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -322,7 +322,7 @@ static void probe_jit_limit(void) printf("Unable to retrieve global memory limit for JIT compiler for unprivileged users\n"); break; default: - printf("Global memory limit for JIT compiler for unprivileged users is %d bytes\n", res); + printf("Global memory limit for JIT compiler for unprivileged users is %ld bytes\n", res); } } } diff --git a/tools/bpf/bpftool/iter.c b/tools/bpf/bpftool/iter.c index 9a1d2365a2974..6b0e5202ca7a9 100644 --- a/tools/bpf/bpftool/iter.c +++ b/tools/bpf/bpftool/iter.c @@ -76,7 +76,7 @@ static int do_pin(int argc, char **argv) goto close_obj; } - err = mount_bpffs_for_pin(path); + err = mount_bpffs_for_pin(path, false); if (err) goto close_link; diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index d98dbc50cf4c6..2d786072ed0d0 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -195,6 +195,8 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) show_link_attach_type_json(info->tracing.attach_type, json_wtr); + jsonw_uint_field(json_wtr, "target_obj_id", info->tracing.target_obj_id); + jsonw_uint_field(json_wtr, "target_btf_id", info->tracing.target_btf_id); break; case BPF_LINK_TYPE_CGROUP: jsonw_lluint_field(json_wtr, "cgroup_id", @@ -212,7 +214,10 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) case BPF_LINK_TYPE_NETFILTER: netfilter_dump_json(info, json_wtr); break; - + case BPF_LINK_TYPE_STRUCT_OPS: + jsonw_uint_field(json_wtr, "map_id", + info->struct_ops.map_id); + break; default: break; } @@ -245,7 +250,10 @@ static void show_link_header_plain(struct bpf_link_info *info) else printf("type %u ", info->type); - printf("prog %u ", info->prog_id); + if (info->type == BPF_LINK_TYPE_STRUCT_OPS) + printf("map %u ", info->struct_ops.map_id); + else + printf("prog %u ", info->prog_id); } static void show_link_attach_type_plain(__u32 attach_type) @@ -369,6 +377,10 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) printf("\n\tprog_type %u ", prog_info.type); show_link_attach_type_plain(info->tracing.attach_type); + if (info->tracing.target_obj_id || info->tracing.target_btf_id) + printf("\n\ttarget_obj_id %u target_btf_id %u ", + info->tracing.target_obj_id, + info->tracing.target_btf_id); break; case BPF_LINK_TYPE_CGROUP: printf("\n\tcgroup_id %zu ", (size_t)info->cgroup.cgroup_id); diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index a49534d7eafa9..b8bb08d10dec9 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -142,7 +142,7 @@ const char *get_fd_type_name(enum bpf_obj_type type); char *get_fdinfo(int fd, const char *key); int open_obj_pinned(const char *path, bool quiet); int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type); -int mount_bpffs_for_pin(const char *name); +int mount_bpffs_for_pin(const char *name, bool is_dir); int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(int *, char ***)); int do_pin_fd(int fd, const char *name); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index aaeb8939e1376..f98f7bbea2b15 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -139,6 +139,9 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, print_hex_data_json(key, info->key_size); jsonw_name(json_wtr, "value"); print_hex_data_json(value, info->value_size); + if (map_is_map_of_maps(info->type)) + jsonw_uint_field(json_wtr, "inner_map_id", + *(unsigned int *)value); if (btf) { struct btf_dumper d = { .btf = btf, @@ -259,8 +262,13 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, } if (info->value_size) { - printf("value:%c", break_names ? '\n' : ' '); - fprint_hex(stdout, value, info->value_size, " "); + if (map_is_map_of_maps(info->type)) { + printf("inner_map_id:%c", break_names ? '\n' : ' '); + printf("%u ", *(unsigned int *)value); + } else { + printf("value:%c", break_names ? '\n' : ' '); + fprint_hex(stdout, value, info->value_size, " "); + } } printf("\n"); @@ -1279,6 +1287,11 @@ static int do_create(int argc, char **argv) "flags")) goto exit; } else if (is_prefix(*argv, "dev")) { + p_info("Warning: 'bpftool map create [...] dev <ifname>' syntax is deprecated.\n" + "Going further, please use 'offload_dev <ifname>' to request hardware offload for the map."); + goto offload_dev; + } else if (is_prefix(*argv, "offload_dev")) { +offload_dev: NEXT_ARG(); if (attr.map_ifindex) { @@ -1423,7 +1436,7 @@ static int do_help(int argc, char **argv) "Usage: %1$s %2$s { show | list } [MAP]\n" " %1$s %2$s create FILE type TYPE key KEY_SIZE value VALUE_SIZE \\\n" " entries MAX_ENTRIES name NAME [flags FLAGS] \\\n" - " [inner_map MAP] [dev NAME]\n" + " [inner_map MAP] [offload_dev NAME]\n" " %1$s %2$s dump MAP\n" " %1$s %2$s update MAP [key DATA] [value VALUE] [UPDATE_FLAGS]\n" " %1$s %2$s lookup MAP [key DATA]\n" diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 91b6075b2db32..8443a149dd17f 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -1517,12 +1517,13 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) struct bpf_program *prog = NULL, *pos; unsigned int old_map_fds = 0; const char *pinmaps = NULL; + __u32 xdpmeta_ifindex = 0; + __u32 offload_ifindex = 0; bool auto_attach = false; struct bpf_object *obj; struct bpf_map *map; const char *pinfile; unsigned int i, j; - __u32 ifindex = 0; const char *file; int idx, err; @@ -1614,17 +1615,46 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) map_replace[old_map_fds].fd = fd; old_map_fds++; } else if (is_prefix(*argv, "dev")) { + p_info("Warning: 'bpftool prog load [...] dev <ifname>' syntax is deprecated.\n" + "Going further, please use 'offload_dev <ifname>' to offload program to device.\n" + "For applications using XDP hints only, use 'xdpmeta_dev <ifname>'."); + goto offload_dev; + } else if (is_prefix(*argv, "offload_dev")) { +offload_dev: NEXT_ARG(); - if (ifindex) { - p_err("offload device already specified"); + if (offload_ifindex) { + p_err("offload_dev already specified"); + goto err_free_reuse_maps; + } else if (xdpmeta_ifindex) { + p_err("xdpmeta_dev and offload_dev are mutually exclusive"); + goto err_free_reuse_maps; + } + if (!REQ_ARGS(1)) + goto err_free_reuse_maps; + + offload_ifindex = if_nametoindex(*argv); + if (!offload_ifindex) { + p_err("unrecognized netdevice '%s': %s", + *argv, strerror(errno)); + goto err_free_reuse_maps; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "xdpmeta_dev")) { + NEXT_ARG(); + + if (xdpmeta_ifindex) { + p_err("xdpmeta_dev already specified"); + goto err_free_reuse_maps; + } else if (offload_ifindex) { + p_err("xdpmeta_dev and offload_dev are mutually exclusive"); goto err_free_reuse_maps; } if (!REQ_ARGS(1)) goto err_free_reuse_maps; - ifindex = if_nametoindex(*argv); - if (!ifindex) { + xdpmeta_ifindex = if_nametoindex(*argv); + if (!xdpmeta_ifindex) { p_err("unrecognized netdevice '%s': %s", *argv, strerror(errno)); goto err_free_reuse_maps; @@ -1671,7 +1701,12 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; } - bpf_program__set_ifindex(pos, ifindex); + if (prog_type == BPF_PROG_TYPE_XDP && xdpmeta_ifindex) { + bpf_program__set_flags(pos, BPF_F_XDP_DEV_BOUND_ONLY); + bpf_program__set_ifindex(pos, xdpmeta_ifindex); + } else { + bpf_program__set_ifindex(pos, offload_ifindex); + } if (bpf_program__type(pos) != prog_type) bpf_program__set_type(pos, prog_type); bpf_program__set_expected_attach_type(pos, expected_attach_type); @@ -1709,7 +1744,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) idx = 0; bpf_object__for_each_map(map, obj) { if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY) - bpf_map__set_ifindex(map, ifindex); + bpf_map__set_ifindex(map, offload_ifindex); if (j < old_map_fds && idx == map_replace[j].idx) { err = bpf_map__reuse_fd(map, map_replace[j++].fd); @@ -1739,7 +1774,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; } - err = mount_bpffs_for_pin(pinfile); + err = mount_bpffs_for_pin(pinfile, !first_prog_only); if (err) goto err_close_obj; @@ -2416,7 +2451,7 @@ static int do_help(int argc, char **argv) " %1$s %2$s dump jited PROG [{ file FILE | [opcodes] [linum] }]\n" " %1$s %2$s pin PROG FILE\n" " %1$s %2$s { load | loadall } OBJ PATH \\\n" - " [type TYPE] [dev NAME] \\\n" + " [type TYPE] [{ offload_dev | xdpmeta_dev } NAME] \\\n" " [map { idx IDX | name NAME } MAP]\\\n" " [pinmaps MAP_DIR]\n" " [autoattach]\n" diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c index 57c3da70aa31a..3ebc9fe91e0e1 100644 --- a/tools/bpf/bpftool/struct_ops.c +++ b/tools/bpf/bpftool/struct_ops.c @@ -509,7 +509,7 @@ static int do_register(int argc, char **argv) if (argc == 1) linkdir = GET_ARG(); - if (linkdir && mount_bpffs_for_pin(linkdir)) { + if (linkdir && mount_bpffs_for_pin(linkdir, true)) { p_err("can't mount bpffs for pinning"); return -1; } diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index ac548a7baa73e..4b8079f294f65 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -67,7 +67,7 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OU LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null) LIBELF_LIBS := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf) -HOSTCFLAGS += -g \ +HOSTCFLAGS_resolve_btfids += -g \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ -I$(LIBBPF_INCLUDE) \ @@ -76,7 +76,7 @@ HOSTCFLAGS += -g \ LIBS = $(LIBELF_LIBS) -lz -export srctree OUTPUT HOSTCFLAGS Q HOSTCC HOSTLD HOSTAR +export srctree OUTPUT HOSTCFLAGS_resolve_btfids Q HOSTCC HOSTLD HOSTAR include $(srctree)/tools/build/Makefile.include $(BINARY_IN): fixdep FORCE prepare | $(OUTPUT) diff --git a/tools/gpio/lsgpio.c b/tools/gpio/lsgpio.c index c61d061247e17..52a0be45410c9 100644 --- a/tools/gpio/lsgpio.c +++ b/tools/gpio/lsgpio.c @@ -94,7 +94,7 @@ static void print_attributes(struct gpio_v2_line_info *info) for (i = 0; i < info->num_attrs; i++) { if (info->attrs[i].id == GPIO_V2_LINE_ATTR_ID_DEBOUNCE) fprintf(stdout, ", debounce_period=%dusec", - info->attrs[0].debounce_period_us); + info->attrs[i].debounce_period_us); } } diff --git a/tools/include/asm/alternative.h b/tools/include/asm/alternative.h index b54bd860dff6f..7ce02a2237325 100644 --- a/tools/include/asm/alternative.h +++ b/tools/include/asm/alternative.h @@ -4,7 +4,6 @@ /* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */ -#define altinstruction_entry # -#define ALTERNATIVE_2 # +#define ALTERNATIVE # #endif diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index cef3b1c25335a..51ac441a37c3e 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -21,19 +21,6 @@ */ #define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) (0x10 + (cpu * 2)) -/* CoreSight trace ID is currently the bottom 7 bits of the value */ -#define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) - -/* - * perf record will set the legacy meta data values as unused initially. - * This allows perf report to manage the decoders created when dynamic - * allocation in operation. - */ -#define CORESIGHT_TRACE_ID_UNUSED_FLAG BIT(31) - -/* Value to set for unused trace ID values */ -#define CORESIGHT_TRACE_ID_UNUSED_VAL 0x7F - /* * Below are the definition of bit offsets for perf option, and works as * arbitrary values for all ETM versions. diff --git a/tools/include/nolibc/Makefile b/tools/include/nolibc/Makefile index 9839feafd38a1..64d67b080744e 100644 --- a/tools/include/nolibc/Makefile +++ b/tools/include/nolibc/Makefile @@ -25,8 +25,23 @@ endif nolibc_arch := $(patsubst arm64,aarch64,$(ARCH)) arch_file := arch-$(nolibc_arch).h -all_files := ctype.h errno.h nolibc.h signal.h stackprotector.h std.h stdint.h \ - stdio.h stdlib.h string.h sys.h time.h types.h unistd.h +all_files := \ + compiler.h \ + ctype.h \ + errno.h \ + nolibc.h \ + signal.h \ + stackprotector.h \ + std.h \ + stdint.h \ + stdlib.h \ + string.h \ + sys.h \ + time.h \ + types.h \ + unistd.h \ + stdio.h \ + # install all headers needed to support a bare-metal compiler all: headers diff --git a/tools/include/nolibc/arch-aarch64.h b/tools/include/nolibc/arch-aarch64.h index 383baddef7019..11f294a406b7c 100644 --- a/tools/include/nolibc/arch-aarch64.h +++ b/tools/include/nolibc/arch-aarch64.h @@ -7,6 +7,8 @@ #ifndef _NOLIBC_ARCH_AARCH64_H #define _NOLIBC_ARCH_AARCH64_H +#include "compiler.h" + /* The struct returned by the newfstatat() syscall. Differs slightly from the * x86_64's stat one by field ordering, so be careful. */ @@ -173,27 +175,30 @@ char **environ __attribute__((weak)); const unsigned long *_auxv __attribute__((weak)); /* startup code */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( - "ldr x0, [sp]\n" // argc (x0) was in the stack - "add x1, sp, 8\n" // argv (x1) = sp - "lsl x2, x0, 3\n" // envp (x2) = 8*argc ... - "add x2, x2, 8\n" // + 8 (skip null) - "add x2, x2, x1\n" // + argv - "adrp x3, environ\n" // x3 = &environ (high bits) - "str x2, [x3, #:lo12:environ]\n" // store envp into environ - "mov x4, x2\n" // search for auxv (follows NULL after last env) +#ifdef _NOLIBC_STACKPROTECTOR + "bl __stack_chk_init\n" /* initialize stack protector */ +#endif + "ldr x0, [sp]\n" /* argc (x0) was in the stack */ + "add x1, sp, 8\n" /* argv (x1) = sp */ + "lsl x2, x0, 3\n" /* envp (x2) = 8*argc ... */ + "add x2, x2, 8\n" /* + 8 (skip null) */ + "add x2, x2, x1\n" /* + argv */ + "adrp x3, environ\n" /* x3 = &environ (high bits) */ + "str x2, [x3, #:lo12:environ]\n" /* store envp into environ */ + "mov x4, x2\n" /* search for auxv (follows NULL after last env) */ "0:\n" - "ldr x5, [x4], 8\n" // x5 = *x4; x4 += 8 - "cbnz x5, 0b\n" // and stop at NULL after last env - "adrp x3, _auxv\n" // x3 = &_auxv (high bits) - "str x4, [x3, #:lo12:_auxv]\n" // store x4 into _auxv - "and sp, x1, -16\n" // sp must be 16-byte aligned in the callee - "bl main\n" // main() returns the status code, we'll exit with it. - "mov x8, 93\n" // NR_exit == 93 + "ldr x5, [x4], 8\n" /* x5 = *x4; x4 += 8 */ + "cbnz x5, 0b\n" /* and stop at NULL after last env */ + "adrp x3, _auxv\n" /* x3 = &_auxv (high bits) */ + "str x4, [x3, #:lo12:_auxv]\n" /* store x4 into _auxv */ + "and sp, x1, -16\n" /* sp must be 16-byte aligned in the callee */ + "bl main\n" /* main() returns the status code, we'll exit with it. */ + "mov x8, 93\n" /* NR_exit == 93 */ "svc #0\n" ); __builtin_unreachable(); } -#endif // _NOLIBC_ARCH_AARCH64_H +#endif /* _NOLIBC_ARCH_AARCH64_H */ diff --git a/tools/include/nolibc/arch-arm.h b/tools/include/nolibc/arch-arm.h index 42499f23e73c5..ca4c669874973 100644 --- a/tools/include/nolibc/arch-arm.h +++ b/tools/include/nolibc/arch-arm.h @@ -7,6 +7,8 @@ #ifndef _NOLIBC_ARCH_ARM_H #define _NOLIBC_ARCH_ARM_H +#include "compiler.h" + /* The struct returned by the stat() syscall, 32-bit only, the syscall returns * exactly 56 bytes (stops before the unused array). In big endian, the format * differs as devices are returned as short only. @@ -196,41 +198,67 @@ struct sys_stat_struct { _arg1; \ }) +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + register long _arg2 __asm__ ("r1") = (long)(arg2); \ + register long _arg3 __asm__ ("r2") = (long)(arg3); \ + register long _arg4 __asm__ ("r3") = (long)(arg4); \ + register long _arg5 __asm__ ("r4") = (long)(arg5); \ + register long _arg6 __asm__ ("r5") = (long)(arg6); \ + \ + __asm__ volatile ( \ + _NOLIBC_THUMB_SET_R7 \ + "svc #0\n" \ + _NOLIBC_THUMB_RESTORE_R7 \ + : "=r"(_arg1), "=r" (_num) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_arg6), "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + + char **environ __attribute__((weak)); const unsigned long *_auxv __attribute__((weak)); /* startup code */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( - "pop {%r0}\n" // argc was in the stack - "mov %r1, %sp\n" // argv = sp +#ifdef _NOLIBC_STACKPROTECTOR + "bl __stack_chk_init\n" /* initialize stack protector */ +#endif + "pop {%r0}\n" /* argc was in the stack */ + "mov %r1, %sp\n" /* argv = sp */ - "add %r2, %r0, $1\n" // envp = (argc + 1) ... - "lsl %r2, %r2, $2\n" // * 4 ... - "add %r2, %r2, %r1\n" // + argv - "ldr %r3, 1f\n" // r3 = &environ (see below) - "str %r2, [r3]\n" // store envp into environ + "add %r2, %r0, $1\n" /* envp = (argc + 1) ... */ + "lsl %r2, %r2, $2\n" /* * 4 ... */ + "add %r2, %r2, %r1\n" /* + argv */ + "ldr %r3, 1f\n" /* r3 = &environ (see below) */ + "str %r2, [r3]\n" /* store envp into environ */ - "mov r4, r2\n" // search for auxv (follows NULL after last env) + "mov r4, r2\n" /* search for auxv (follows NULL after last env) */ "0:\n" - "mov r5, r4\n" // r5 = r4 - "add r4, r4, #4\n" // r4 += 4 - "ldr r5,[r5]\n" // r5 = *r5 = *(r4-4) - "cmp r5, #0\n" // and stop at NULL after last env + "mov r5, r4\n" /* r5 = r4 */ + "add r4, r4, #4\n" /* r4 += 4 */ + "ldr r5,[r5]\n" /* r5 = *r5 = *(r4-4) */ + "cmp r5, #0\n" /* and stop at NULL after last env */ "bne 0b\n" - "ldr %r3, 2f\n" // r3 = &_auxv (low bits) - "str r4, [r3]\n" // store r4 into _auxv + "ldr %r3, 2f\n" /* r3 = &_auxv (low bits) */ + "str r4, [r3]\n" /* store r4 into _auxv */ - "mov %r3, $8\n" // AAPCS : sp must be 8-byte aligned in the - "neg %r3, %r3\n" // callee, and bl doesn't push (lr=pc) - "and %r3, %r3, %r1\n" // so we do sp = r1(=sp) & r3(=-8); - "mov %sp, %r3\n" // + "mov %r3, $8\n" /* AAPCS : sp must be 8-byte aligned in the */ + "neg %r3, %r3\n" /* callee, and bl doesn't push (lr=pc) */ + "and %r3, %r3, %r1\n" /* so we do sp = r1(=sp) & r3(=-8); */ + "mov %sp, %r3\n" - "bl main\n" // main() returns the status code, we'll exit with it. - "movs r7, $1\n" // NR_exit == 1 + "bl main\n" /* main() returns the status code, we'll exit with it. */ + "movs r7, $1\n" /* NR_exit == 1 */ "svc $0x00\n" - ".align 2\n" // below are the pointers to a few variables + ".align 2\n" /* below are the pointers to a few variables */ "1:\n" ".word environ\n" "2:\n" @@ -239,4 +267,4 @@ void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) __builtin_unreachable(); } -#endif // _NOLIBC_ARCH_ARM_H +#endif /* _NOLIBC_ARCH_ARM_H */ diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h index 2d98d78fd3f3a..3d672d925e9e2 100644 --- a/tools/include/nolibc/arch-i386.h +++ b/tools/include/nolibc/arch-i386.h @@ -7,6 +7,8 @@ #ifndef _NOLIBC_ARCH_I386_H #define _NOLIBC_ARCH_I386_H +#include "compiler.h" + /* The struct returned by the stat() syscall, 32-bit only, the syscall returns * exactly 56 bytes (stops before the unused array). */ @@ -181,8 +183,6 @@ struct sys_stat_struct { char **environ __attribute__((weak)); const unsigned long *_auxv __attribute__((weak)); -#define __ARCH_SUPPORTS_STACK_PROTECTOR - /* startup code */ /* * i386 System V ABI mandates: @@ -190,35 +190,35 @@ const unsigned long *_auxv __attribute__((weak)); * 2) The deepest stack frame should be set to zero * */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"),no_stack_protector)) _start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( -#ifdef NOLIBC_STACKPROTECTOR - "call __stack_chk_init\n" // initialize stack protector +#ifdef _NOLIBC_STACKPROTECTOR + "call __stack_chk_init\n" /* initialize stack protector */ #endif - "pop %eax\n" // argc (first arg, %eax) - "mov %esp, %ebx\n" // argv[] (second arg, %ebx) - "lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx) - "mov %ecx, environ\n" // save environ - "xor %ebp, %ebp\n" // zero the stack frame - "mov %ecx, %edx\n" // search for auxv (follows NULL after last env) + "pop %eax\n" /* argc (first arg, %eax) */ + "mov %esp, %ebx\n" /* argv[] (second arg, %ebx) */ + "lea 4(%ebx,%eax,4),%ecx\n" /* then a NULL then envp (third arg, %ecx) */ + "mov %ecx, environ\n" /* save environ */ + "xor %ebp, %ebp\n" /* zero the stack frame */ + "mov %ecx, %edx\n" /* search for auxv (follows NULL after last env) */ "0:\n" - "add $4, %edx\n" // search for auxv using edx, it follows the - "cmp -4(%edx), %ebp\n" // ... NULL after last env (ebp is zero here) + "add $4, %edx\n" /* search for auxv using edx, it follows the */ + "cmp -4(%edx), %ebp\n" /* ... NULL after last env (ebp is zero here) */ "jnz 0b\n" - "mov %edx, _auxv\n" // save it into _auxv - "and $-16, %esp\n" // x86 ABI : esp must be 16-byte aligned before - "sub $4, %esp\n" // the call instruction (args are aligned) - "push %ecx\n" // push all registers on the stack so that we - "push %ebx\n" // support both regparm and plain stack modes + "mov %edx, _auxv\n" /* save it into _auxv */ + "and $-16, %esp\n" /* x86 ABI : esp must be 16-byte aligned before */ + "sub $4, %esp\n" /* the call instruction (args are aligned) */ + "push %ecx\n" /* push all registers on the stack so that we */ + "push %ebx\n" /* support both regparm and plain stack modes */ "push %eax\n" - "call main\n" // main() returns the status code in %eax - "mov %eax, %ebx\n" // retrieve exit code (32-bit int) - "movl $1, %eax\n" // NR_exit == 1 - "int $0x80\n" // exit now - "hlt\n" // ensure it does not + "call main\n" /* main() returns the status code in %eax */ + "mov %eax, %ebx\n" /* retrieve exit code (32-bit int) */ + "movl $1, %eax\n" /* NR_exit == 1 */ + "int $0x80\n" /* exit now */ + "hlt\n" /* ensure it does not */ ); __builtin_unreachable(); } -#endif // _NOLIBC_ARCH_I386_H +#endif /* _NOLIBC_ARCH_I386_H */ diff --git a/tools/include/nolibc/arch-loongarch.h b/tools/include/nolibc/arch-loongarch.h index 029ee3cd6bafa..ad3f266e70930 100644 --- a/tools/include/nolibc/arch-loongarch.h +++ b/tools/include/nolibc/arch-loongarch.h @@ -7,6 +7,8 @@ #ifndef _NOLIBC_ARCH_LOONGARCH_H #define _NOLIBC_ARCH_LOONGARCH_H +#include "compiler.h" + /* Syscalls for LoongArch : * - stack is 16-byte aligned * - syscall number is passed in a7 @@ -158,7 +160,7 @@ const unsigned long *_auxv __attribute__((weak)); #define LONG_ADDI "addi.w" #define LONG_SLL "slli.w" #define LONG_BSTRINS "bstrins.w" -#else // __loongarch_grlen == 64 +#else /* __loongarch_grlen == 64 */ #define LONGLOG "3" #define SZREG "8" #define REG_L "ld.d" @@ -170,31 +172,34 @@ const unsigned long *_auxv __attribute__((weak)); #endif /* startup code */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( - REG_L " $a0, $sp, 0\n" // argc (a0) was in the stack - LONG_ADDI " $a1, $sp, "SZREG"\n" // argv (a1) = sp + SZREG - LONG_SLL " $a2, $a0, "LONGLOG"\n" // envp (a2) = SZREG*argc ... - LONG_ADDI " $a2, $a2, "SZREG"\n" // + SZREG (skip null) - LONG_ADD " $a2, $a2, $a1\n" // + argv - - "move $a3, $a2\n" // iterate a3 over envp to find auxv (after NULL) - "0:\n" // do { - REG_L " $a4, $a3, 0\n" // a4 = *a3; - LONG_ADDI " $a3, $a3, "SZREG"\n" // a3 += sizeof(void*); - "bne $a4, $zero, 0b\n" // } while (a4); - "la.pcrel $a4, _auxv\n" // a4 = &_auxv - LONG_S " $a3, $a4, 0\n" // store a3 into _auxv - - "la.pcrel $a3, environ\n" // a3 = &environ - LONG_S " $a2, $a3, 0\n" // store envp(a2) into environ - LONG_BSTRINS " $sp, $zero, 3, 0\n" // sp must be 16-byte aligned - "bl main\n" // main() returns the status code, we'll exit with it. - "li.w $a7, 93\n" // NR_exit == 93 +#ifdef _NOLIBC_STACKPROTECTOR + "bl __stack_chk_init\n" /* initialize stack protector */ +#endif + REG_L " $a0, $sp, 0\n" /* argc (a0) was in the stack */ + LONG_ADDI " $a1, $sp, "SZREG"\n" /* argv (a1) = sp + SZREG */ + LONG_SLL " $a2, $a0, "LONGLOG"\n" /* envp (a2) = SZREG*argc ... */ + LONG_ADDI " $a2, $a2, "SZREG"\n" /* + SZREG (skip null) */ + LONG_ADD " $a2, $a2, $a1\n" /* + argv */ + + "move $a3, $a2\n" /* iterate a3 over envp to find auxv (after NULL) */ + "0:\n" /* do { */ + REG_L " $a4, $a3, 0\n" /* a4 = *a3; */ + LONG_ADDI " $a3, $a3, "SZREG"\n" /* a3 += sizeof(void*); */ + "bne $a4, $zero, 0b\n" /* } while (a4); */ + "la.pcrel $a4, _auxv\n" /* a4 = &_auxv */ + LONG_S " $a3, $a4, 0\n" /* store a3 into _auxv */ + + "la.pcrel $a3, environ\n" /* a3 = &environ */ + LONG_S " $a2, $a3, 0\n" /* store envp(a2) into environ */ + LONG_BSTRINS " $sp, $zero, 3, 0\n" /* sp must be 16-byte aligned */ + "bl main\n" /* main() returns the status code, we'll exit with it. */ + "li.w $a7, 93\n" /* NR_exit == 93 */ "syscall 0\n" ); __builtin_unreachable(); } -#endif // _NOLIBC_ARCH_LOONGARCH_H +#endif /* _NOLIBC_ARCH_LOONGARCH_H */ diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h index bf83432d23ed3..db24e0837a39b 100644 --- a/tools/include/nolibc/arch-mips.h +++ b/tools/include/nolibc/arch-mips.h @@ -7,6 +7,8 @@ #ifndef _NOLIBC_ARCH_MIPS_H #define _NOLIBC_ARCH_MIPS_H +#include "compiler.h" + /* The struct returned by the stat() syscall. 88 bytes are returned by the * syscall. */ @@ -180,45 +182,49 @@ char **environ __attribute__((weak)); const unsigned long *_auxv __attribute__((weak)); /* startup code, note that it's called __start on MIPS */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector __start(void) { __asm__ volatile ( - //".set nomips16\n" + /*".set nomips16\n"*/ ".set push\n" ".set noreorder\n" ".option pic0\n" - //".ent __start\n" - //"__start:\n" - "lw $a0,($sp)\n" // argc was in the stack - "addiu $a1, $sp, 4\n" // argv = sp + 4 - "sll $a2, $a0, 2\n" // a2 = argc * 4 - "add $a2, $a2, $a1\n" // envp = argv + 4*argc ... - "addiu $a2, $a2, 4\n" // ... + 4 - "lui $a3, %hi(environ)\n" // load environ into a3 (hi) - "addiu $a3, %lo(environ)\n" // load environ into a3 (lo) - "sw $a2,($a3)\n" // store envp(a2) into environ - - "move $t0, $a2\n" // iterate t0 over envp, look for NULL - "0:" // do { - "lw $a3, ($t0)\n" // a3=*(t0); - "bne $a3, $0, 0b\n" // } while (a3); - "addiu $t0, $t0, 4\n" // delayed slot: t0+=4; - "lui $a3, %hi(_auxv)\n" // load _auxv into a3 (hi) - "addiu $a3, %lo(_auxv)\n" // load _auxv into a3 (lo) - "sw $t0, ($a3)\n" // store t0 into _auxv +#ifdef _NOLIBC_STACKPROTECTOR + "jal __stack_chk_init\n" /* initialize stack protector */ + "nop\n" /* delayed slot */ +#endif + /*".ent __start\n"*/ + /*"__start:\n"*/ + "lw $a0,($sp)\n" /* argc was in the stack */ + "addiu $a1, $sp, 4\n" /* argv = sp + 4 */ + "sll $a2, $a0, 2\n" /* a2 = argc * 4 */ + "add $a2, $a2, $a1\n" /* envp = argv + 4*argc ... */ + "addiu $a2, $a2, 4\n" /* ... + 4 */ + "lui $a3, %hi(environ)\n" /* load environ into a3 (hi) */ + "addiu $a3, %lo(environ)\n" /* load environ into a3 (lo) */ + "sw $a2,($a3)\n" /* store envp(a2) into environ */ + + "move $t0, $a2\n" /* iterate t0 over envp, look for NULL */ + "0:" /* do { */ + "lw $a3, ($t0)\n" /* a3=*(t0); */ + "bne $a3, $0, 0b\n" /* } while (a3); */ + "addiu $t0, $t0, 4\n" /* delayed slot: t0+=4; */ + "lui $a3, %hi(_auxv)\n" /* load _auxv into a3 (hi) */ + "addiu $a3, %lo(_auxv)\n" /* load _auxv into a3 (lo) */ + "sw $t0, ($a3)\n" /* store t0 into _auxv */ "li $t0, -8\n" - "and $sp, $sp, $t0\n" // sp must be 8-byte aligned - "addiu $sp,$sp,-16\n" // the callee expects to save a0..a3 there! - "jal main\n" // main() returns the status code, we'll exit with it. - "nop\n" // delayed slot - "move $a0, $v0\n" // retrieve 32-bit exit code from v0 - "li $v0, 4001\n" // NR_exit == 4001 + "and $sp, $sp, $t0\n" /* sp must be 8-byte aligned */ + "addiu $sp,$sp,-16\n" /* the callee expects to save a0..a3 there! */ + "jal main\n" /* main() returns the status code, we'll exit with it. */ + "nop\n" /* delayed slot */ + "move $a0, $v0\n" /* retrieve 32-bit exit code from v0 */ + "li $v0, 4001\n" /* NR_exit == 4001 */ "syscall\n" - //".end __start\n" + /*".end __start\n"*/ ".set pop\n" ); __builtin_unreachable(); } -#endif // _NOLIBC_ARCH_MIPS_H +#endif /* _NOLIBC_ARCH_MIPS_H */ diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h index e197fcb10ac00..a2e8564e66d6a 100644 --- a/tools/include/nolibc/arch-riscv.h +++ b/tools/include/nolibc/arch-riscv.h @@ -7,6 +7,8 @@ #ifndef _NOLIBC_ARCH_RISCV_H #define _NOLIBC_ARCH_RISCV_H +#include "compiler.h" + struct sys_stat_struct { unsigned long st_dev; /* Device. */ unsigned long st_ino; /* File serial number. */ @@ -33,9 +35,13 @@ struct sys_stat_struct { #if __riscv_xlen == 64 #define PTRLOG "3" #define SZREG "8" +#define REG_L "ld" +#define REG_S "sd" #elif __riscv_xlen == 32 #define PTRLOG "2" #define SZREG "4" +#define REG_L "lw" +#define REG_S "sw" #endif /* Syscalls for RISCV : @@ -174,35 +180,38 @@ char **environ __attribute__((weak)); const unsigned long *_auxv __attribute__((weak)); /* startup code */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( ".option push\n" ".option norelax\n" "lla gp, __global_pointer$\n" ".option pop\n" - "lw a0, 0(sp)\n" // argc (a0) was in the stack - "add a1, sp, "SZREG"\n" // argv (a1) = sp - "slli a2, a0, "PTRLOG"\n" // envp (a2) = SZREG*argc ... - "add a2, a2, "SZREG"\n" // + SZREG (skip null) - "add a2,a2,a1\n" // + argv - - "add a3, a2, zero\n" // iterate a3 over envp to find auxv (after NULL) - "0:\n" // do { - "ld a4, 0(a3)\n" // a4 = *a3; - "add a3, a3, "SZREG"\n" // a3 += sizeof(void*); - "bne a4, zero, 0b\n" // } while (a4); - "lui a4, %hi(_auxv)\n" // a4 = &_auxv (high bits) - "sd a3, %lo(_auxv)(a4)\n" // store a3 into _auxv - - "lui a3, %hi(environ)\n" // a3 = &environ (high bits) - "sd a2,%lo(environ)(a3)\n" // store envp(a2) into environ - "andi sp,a1,-16\n" // sp must be 16-byte aligned - "call main\n" // main() returns the status code, we'll exit with it. - "li a7, 93\n" // NR_exit == 93 +#ifdef _NOLIBC_STACKPROTECTOR + "call __stack_chk_init\n" /* initialize stack protector */ +#endif + REG_L" a0, 0(sp)\n" /* argc (a0) was in the stack */ + "add a1, sp, "SZREG"\n" /* argv (a1) = sp */ + "slli a2, a0, "PTRLOG"\n" /* envp (a2) = SZREG*argc ... */ + "add a2, a2, "SZREG"\n" /* + SZREG (skip null) */ + "add a2,a2,a1\n" /* + argv */ + + "add a3, a2, zero\n" /* iterate a3 over envp to find auxv (after NULL) */ + "0:\n" /* do { */ + REG_L" a4, 0(a3)\n" /* a4 = *a3; */ + "add a3, a3, "SZREG"\n" /* a3 += sizeof(void*); */ + "bne a4, zero, 0b\n" /* } while (a4); */ + "lui a4, %hi(_auxv)\n" /* a4 = &_auxv (high bits) */ + REG_S" a3, %lo(_auxv)(a4)\n" /* store a3 into _auxv */ + + "lui a3, %hi(environ)\n" /* a3 = &environ (high bits) */ + REG_S" a2,%lo(environ)(a3)\n"/* store envp(a2) into environ */ + "andi sp,a1,-16\n" /* sp must be 16-byte aligned */ + "call main\n" /* main() returns the status code, we'll exit with it. */ + "li a7, 93\n" /* NR_exit == 93 */ "ecall\n" ); __builtin_unreachable(); } -#endif // _NOLIBC_ARCH_RISCV_H +#endif /* _NOLIBC_ARCH_RISCV_H */ diff --git a/tools/include/nolibc/arch-s390.h b/tools/include/nolibc/arch-s390.h index 6b0e54ed543dd..516dff5bff8bc 100644 --- a/tools/include/nolibc/arch-s390.h +++ b/tools/include/nolibc/arch-s390.h @@ -5,8 +5,11 @@ #ifndef _NOLIBC_ARCH_S390_H #define _NOLIBC_ARCH_S390_H +#include <asm/signal.h> #include <asm/unistd.h> +#include "compiler.h" + /* The struct returned by the stat() syscall, equivalent to stat64(). The * syscall returns 116 bytes and stops in the middle of __unused. */ @@ -163,7 +166,7 @@ char **environ __attribute__((weak)); const unsigned long *_auxv __attribute__((weak)); /* startup code */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( "lg %r2,0(%r15)\n" /* argument count */ @@ -223,4 +226,12 @@ void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd, return (void *)my_syscall1(__NR_mmap, &args); } #define sys_mmap sys_mmap -#endif // _NOLIBC_ARCH_S390_H + +static __attribute__((unused)) +pid_t sys_fork(void) +{ + return my_syscall5(__NR_clone, 0, SIGCHLD, 0, 0, 0); +} +#define sys_fork sys_fork + +#endif /* _NOLIBC_ARCH_S390_H */ diff --git a/tools/include/nolibc/arch-x86_64.h b/tools/include/nolibc/arch-x86_64.h index f7f2a11d4c3b0..6fc4d83927429 100644 --- a/tools/include/nolibc/arch-x86_64.h +++ b/tools/include/nolibc/arch-x86_64.h @@ -7,6 +7,8 @@ #ifndef _NOLIBC_ARCH_X86_64_H #define _NOLIBC_ARCH_X86_64_H +#include "compiler.h" + /* The struct returned by the stat() syscall, equivalent to stat64(). The * syscall returns 116 bytes and stops in the middle of __unused. */ @@ -181,8 +183,6 @@ struct sys_stat_struct { char **environ __attribute__((weak)); const unsigned long *_auxv __attribute__((weak)); -#define __ARCH_SUPPORTS_STACK_PROTECTOR - /* startup code */ /* * x86-64 System V ABI mandates: @@ -190,31 +190,31 @@ const unsigned long *_auxv __attribute__((weak)); * 2) The deepest stack frame should be zero (the %rbp). * */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( -#ifdef NOLIBC_STACKPROTECTOR - "call __stack_chk_init\n" // initialize stack protector +#ifdef _NOLIBC_STACKPROTECTOR + "call __stack_chk_init\n" /* initialize stack protector */ #endif - "pop %rdi\n" // argc (first arg, %rdi) - "mov %rsp, %rsi\n" // argv[] (second arg, %rsi) - "lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx) - "mov %rdx, environ\n" // save environ - "xor %ebp, %ebp\n" // zero the stack frame - "mov %rdx, %rax\n" // search for auxv (follows NULL after last env) + "pop %rdi\n" /* argc (first arg, %rdi) */ + "mov %rsp, %rsi\n" /* argv[] (second arg, %rsi) */ + "lea 8(%rsi,%rdi,8),%rdx\n" /* then a NULL then envp (third arg, %rdx) */ + "mov %rdx, environ\n" /* save environ */ + "xor %ebp, %ebp\n" /* zero the stack frame */ + "mov %rdx, %rax\n" /* search for auxv (follows NULL after last env) */ "0:\n" - "add $8, %rax\n" // search for auxv using rax, it follows the - "cmp -8(%rax), %rbp\n" // ... NULL after last env (rbp is zero here) + "add $8, %rax\n" /* search for auxv using rax, it follows the */ + "cmp -8(%rax), %rbp\n" /* ... NULL after last env (rbp is zero here) */ "jnz 0b\n" - "mov %rax, _auxv\n" // save it into _auxv - "and $-16, %rsp\n" // x86 ABI : esp must be 16-byte aligned before call - "call main\n" // main() returns the status code, we'll exit with it. - "mov %eax, %edi\n" // retrieve exit code (32 bit) - "mov $60, %eax\n" // NR_exit == 60 - "syscall\n" // really exit - "hlt\n" // ensure it does not return + "mov %rax, _auxv\n" /* save it into _auxv */ + "and $-16, %rsp\n" /* x86 ABI : esp must be 16-byte aligned before call */ + "call main\n" /* main() returns the status code, we'll exit with it. */ + "mov %eax, %edi\n" /* retrieve exit code (32 bit) */ + "mov $60, %eax\n" /* NR_exit == 60 */ + "syscall\n" /* really exit */ + "hlt\n" /* ensure it does not return */ ); __builtin_unreachable(); } -#endif // _NOLIBC_ARCH_X86_64_H +#endif /* _NOLIBC_ARCH_X86_64_H */ diff --git a/tools/include/nolibc/arch.h b/tools/include/nolibc/arch.h index 2d5386a8d6aac..82b43935650f4 100644 --- a/tools/include/nolibc/arch.h +++ b/tools/include/nolibc/arch.h @@ -7,7 +7,7 @@ * the syscall declarations and the _start code definition. This is the only * global part. On all architectures the kernel puts everything in the stack * before jumping to _start just above us, without any return address (_start - * is not a function but an entry pint). So at the stack pointer we find argc. + * is not a function but an entry point). So at the stack pointer we find argc. * Then argv[] begins, and ends at the first NULL. Then we have envp which * starts and ends with a NULL as well. So envp=argv+argc+1. */ diff --git a/tools/include/nolibc/compiler.h b/tools/include/nolibc/compiler.h new file mode 100644 index 0000000000000..beddc3665d690 --- /dev/null +++ b/tools/include/nolibc/compiler.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * NOLIBC compiler support header + * Copyright (C) 2023 Thomas Weißschuh <linux@weissschuh.net> + */ +#ifndef _NOLIBC_COMPILER_H +#define _NOLIBC_COMPILER_H + +#if defined(__SSP__) || defined(__SSP_STRONG__) || defined(__SSP_ALL__) || defined(__SSP_EXPLICIT__) + +#define _NOLIBC_STACKPROTECTOR + +#endif /* defined(__SSP__) ... */ + +#if defined(__has_attribute) +# if __has_attribute(no_stack_protector) +# define __no_stack_protector __attribute__((no_stack_protector)) +# else +# define __no_stack_protector __attribute__((__optimize__("-fno-stack-protector"))) +# endif +#else +# define __no_stack_protector __attribute__((__optimize__("-fno-stack-protector"))) +#endif /* defined(__has_attribute) */ + +#endif /* _NOLIBC_COMPILER_H */ diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h index 04739a6293c48..05a228a6ee782 100644 --- a/tools/include/nolibc/nolibc.h +++ b/tools/include/nolibc/nolibc.h @@ -99,11 +99,11 @@ #include "sys.h" #include "ctype.h" #include "signal.h" +#include "unistd.h" #include "stdio.h" #include "stdlib.h" #include "string.h" #include "time.h" -#include "unistd.h" #include "stackprotector.h" /* Used by programs to avoid std includes */ diff --git a/tools/include/nolibc/stackprotector.h b/tools/include/nolibc/stackprotector.h index d119cbbbc256f..88f7b2d098ff7 100644 --- a/tools/include/nolibc/stackprotector.h +++ b/tools/include/nolibc/stackprotector.h @@ -7,13 +7,9 @@ #ifndef _NOLIBC_STACKPROTECTOR_H #define _NOLIBC_STACKPROTECTOR_H -#include "arch.h" +#include "compiler.h" -#if defined(NOLIBC_STACKPROTECTOR) - -#if !defined(__ARCH_SUPPORTS_STACK_PROTECTOR) -#error "nolibc does not support stack protectors on this arch" -#endif +#if defined(_NOLIBC_STACKPROTECTOR) #include "sys.h" #include "stdlib.h" @@ -41,13 +37,14 @@ void __stack_chk_fail_local(void) __attribute__((weak,section(".data.nolibc_stack_chk"))) uintptr_t __stack_chk_guard; -__attribute__((weak,no_stack_protector,section(".text.nolibc_stack_chk"))) +__attribute__((weak,section(".text.nolibc_stack_chk"))) __no_stack_protector void __stack_chk_init(void) { my_syscall3(__NR_getrandom, &__stack_chk_guard, sizeof(__stack_chk_guard), 0); - /* a bit more randomness in case getrandom() fails */ - __stack_chk_guard ^= (uintptr_t) &__stack_chk_guard; + /* a bit more randomness in case getrandom() fails, ensure the guard is never 0 */ + if (__stack_chk_guard != (uintptr_t) &__stack_chk_guard) + __stack_chk_guard ^= (uintptr_t) &__stack_chk_guard; } -#endif // defined(NOLIBC_STACKPROTECTOR) +#endif /* defined(_NOLIBC_STACKPROTECTOR) */ -#endif // _NOLIBC_STACKPROTECTOR_H +#endif /* _NOLIBC_STACKPROTECTOR_H */ diff --git a/tools/include/nolibc/stdint.h b/tools/include/nolibc/stdint.h index c1ce4f5e06034..4b282435a59a6 100644 --- a/tools/include/nolibc/stdint.h +++ b/tools/include/nolibc/stdint.h @@ -36,8 +36,8 @@ typedef ssize_t int_fast16_t; typedef size_t uint_fast16_t; typedef ssize_t int_fast32_t; typedef size_t uint_fast32_t; -typedef ssize_t int_fast64_t; -typedef size_t uint_fast64_t; +typedef int64_t int_fast64_t; +typedef uint64_t uint_fast64_t; typedef int64_t intmax_t; typedef uint64_t uintmax_t; @@ -84,16 +84,30 @@ typedef uint64_t uintmax_t; #define INT_FAST8_MIN INT8_MIN #define INT_FAST16_MIN INTPTR_MIN #define INT_FAST32_MIN INTPTR_MIN -#define INT_FAST64_MIN INTPTR_MIN +#define INT_FAST64_MIN INT64_MIN #define INT_FAST8_MAX INT8_MAX #define INT_FAST16_MAX INTPTR_MAX #define INT_FAST32_MAX INTPTR_MAX -#define INT_FAST64_MAX INTPTR_MAX +#define INT_FAST64_MAX INT64_MAX #define UINT_FAST8_MAX UINT8_MAX #define UINT_FAST16_MAX SIZE_MAX #define UINT_FAST32_MAX SIZE_MAX -#define UINT_FAST64_MAX SIZE_MAX +#define UINT_FAST64_MAX UINT64_MAX + +#ifndef INT_MIN +#define INT_MIN (-__INT_MAX__ - 1) +#endif +#ifndef INT_MAX +#define INT_MAX __INT_MAX__ +#endif + +#ifndef LONG_MIN +#define LONG_MIN (-__LONG_MAX__ - 1) +#endif +#ifndef LONG_MAX +#define LONG_MAX __LONG_MAX__ +#endif #endif /* _NOLIBC_STDINT_H */ diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h index 6cbbb52836a00..0eef91daf2898 100644 --- a/tools/include/nolibc/stdio.h +++ b/tools/include/nolibc/stdio.h @@ -21,17 +21,75 @@ #define EOF (-1) #endif -/* just define FILE as a non-empty type */ +/* just define FILE as a non-empty type. The value of the pointer gives + * the FD: FILE=~fd for fd>=0 or NULL for fd<0. This way positive FILE + * are immediately identified as abnormal entries (i.e. possible copies + * of valid pointers to something else). + */ typedef struct FILE { char dummy[1]; } FILE; -/* We define the 3 common stdio files as constant invalid pointers that - * are easily recognized. - */ -static __attribute__((unused)) FILE* const stdin = (FILE*)-3; -static __attribute__((unused)) FILE* const stdout = (FILE*)-2; -static __attribute__((unused)) FILE* const stderr = (FILE*)-1; +static __attribute__((unused)) FILE* const stdin = (FILE*)(intptr_t)~STDIN_FILENO; +static __attribute__((unused)) FILE* const stdout = (FILE*)(intptr_t)~STDOUT_FILENO; +static __attribute__((unused)) FILE* const stderr = (FILE*)(intptr_t)~STDERR_FILENO; + +/* provides a FILE* equivalent of fd. The mode is ignored. */ +static __attribute__((unused)) +FILE *fdopen(int fd, const char *mode __attribute__((unused))) +{ + if (fd < 0) { + SET_ERRNO(EBADF); + return NULL; + } + return (FILE*)(intptr_t)~fd; +} + +/* provides the fd of stream. */ +static __attribute__((unused)) +int fileno(FILE *stream) +{ + intptr_t i = (intptr_t)stream; + + if (i >= 0) { + SET_ERRNO(EBADF); + return -1; + } + return ~i; +} + +/* flush a stream. */ +static __attribute__((unused)) +int fflush(FILE *stream) +{ + intptr_t i = (intptr_t)stream; + + /* NULL is valid here. */ + if (i > 0) { + SET_ERRNO(EBADF); + return -1; + } + + /* Don't do anything, nolibc does not support buffering. */ + return 0; +} + +/* flush a stream. */ +static __attribute__((unused)) +int fclose(FILE *stream) +{ + intptr_t i = (intptr_t)stream; + + if (i >= 0) { + SET_ERRNO(EBADF); + return -1; + } + + if (close(~i)) + return EOF; + + return 0; +} /* getc(), fgetc(), getchar() */ @@ -41,14 +99,8 @@ static __attribute__((unused)) int fgetc(FILE* stream) { unsigned char ch; - int fd; - if (stream < stdin || stream > stderr) - return EOF; - - fd = 3 + (long)stream; - - if (read(fd, &ch, 1) <= 0) + if (read(fileno(stream), &ch, 1) <= 0) return EOF; return ch; } @@ -68,14 +120,8 @@ static __attribute__((unused)) int fputc(int c, FILE* stream) { unsigned char ch = c; - int fd; - - if (stream < stdin || stream > stderr) - return EOF; - - fd = 3 + (long)stream; - if (write(fd, &ch, 1) <= 0) + if (write(fileno(stream), &ch, 1) <= 0) return EOF; return ch; } @@ -96,12 +142,7 @@ static __attribute__((unused)) int _fwrite(const void *buf, size_t size, FILE *stream) { ssize_t ret; - int fd; - - if (stream < stdin || stream > stderr) - return EOF; - - fd = 3 + (long)stream; + int fd = fileno(stream); while (size) { ret = write(fd, buf, size); diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h index 894c955d027e4..902162f80337d 100644 --- a/tools/include/nolibc/stdlib.h +++ b/tools/include/nolibc/stdlib.h @@ -102,7 +102,7 @@ char *_getenv(const char *name, char **environ) return NULL; } -static inline __attribute__((unused,always_inline)) +static __inline__ __attribute__((unused,always_inline)) char *getenv(const char *name) { extern char **environ; @@ -231,7 +231,7 @@ int utoh_r(unsigned long in, char *buffer) /* converts unsigned long <in> to an hex string using the static itoa_buffer * and returns the pointer to that string. */ -static inline __attribute__((unused)) +static __inline__ __attribute__((unused)) char *utoh(unsigned long in) { utoh_r(in, itoa_buffer); @@ -293,7 +293,7 @@ int itoa_r(long in, char *buffer) /* for historical compatibility, same as above but returns the pointer to the * buffer. */ -static inline __attribute__((unused)) +static __inline__ __attribute__((unused)) char *ltoa_r(long in, char *buffer) { itoa_r(in, buffer); @@ -303,7 +303,7 @@ char *ltoa_r(long in, char *buffer) /* converts long integer <in> to a string using the static itoa_buffer and * returns the pointer to that string. */ -static inline __attribute__((unused)) +static __inline__ __attribute__((unused)) char *itoa(long in) { itoa_r(in, itoa_buffer); @@ -313,7 +313,7 @@ char *itoa(long in) /* converts long integer <in> to a string using the static itoa_buffer and * returns the pointer to that string. Same as above, for compatibility. */ -static inline __attribute__((unused)) +static __inline__ __attribute__((unused)) char *ltoa(long in) { itoa_r(in, itoa_buffer); @@ -323,7 +323,7 @@ char *ltoa(long in) /* converts unsigned long integer <in> to a string using the static itoa_buffer * and returns the pointer to that string. */ -static inline __attribute__((unused)) +static __inline__ __attribute__((unused)) char *utoa(unsigned long in) { utoa_r(in, itoa_buffer); @@ -367,7 +367,7 @@ int u64toh_r(uint64_t in, char *buffer) /* converts uint64_t <in> to an hex string using the static itoa_buffer and * returns the pointer to that string. */ -static inline __attribute__((unused)) +static __inline__ __attribute__((unused)) char *u64toh(uint64_t in) { u64toh_r(in, itoa_buffer); @@ -429,7 +429,7 @@ int i64toa_r(int64_t in, char *buffer) /* converts int64_t <in> to a string using the static itoa_buffer and returns * the pointer to that string. */ -static inline __attribute__((unused)) +static __inline__ __attribute__((unused)) char *i64toa(int64_t in) { i64toa_r(in, itoa_buffer); @@ -439,7 +439,7 @@ char *i64toa(int64_t in) /* converts uint64_t <in> to a string using the static itoa_buffer and returns * the pointer to that string. */ -static inline __attribute__((unused)) +static __inline__ __attribute__((unused)) char *u64toa(uint64_t in) { u64toa_r(in, itoa_buffer); diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h index fffdaf6ff4673..0c2e06c7c4772 100644 --- a/tools/include/nolibc/string.h +++ b/tools/include/nolibc/string.h @@ -90,7 +90,7 @@ void *memset(void *dst, int b, size_t len) while (len--) { /* prevent gcc from recognizing memset() here */ - asm volatile(""); + __asm__ volatile(""); *(p++) = b; } return dst; @@ -139,7 +139,7 @@ size_t strlen(const char *str) size_t len; for (len = 0; str[len]; len++) - asm(""); + __asm__(""); return len; } diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index 5d624dc63a424..856249a118901 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -12,15 +12,17 @@ /* system includes */ #include <asm/unistd.h> -#include <asm/signal.h> // for SIGCHLD +#include <asm/signal.h> /* for SIGCHLD */ #include <asm/ioctls.h> #include <asm/mman.h> #include <linux/fs.h> #include <linux/loop.h> #include <linux/time.h> #include <linux/auxvec.h> -#include <linux/fcntl.h> // for O_* and AT_* -#include <linux/stat.h> // for statx() +#include <linux/fcntl.h> /* for O_* and AT_* */ +#include <linux/stat.h> /* for statx() */ +#include <linux/reboot.h> /* for LINUX_REBOOT_* */ +#include <linux/prctl.h> #include "arch.h" #include "errno.h" @@ -322,7 +324,7 @@ static __attribute__((noreturn,unused)) void sys_exit(int status) { my_syscall1(__NR_exit, status & 255); - while(1); // shut the "noreturn" warnings. + while(1); /* shut the "noreturn" warnings. */ } static __attribute__((noreturn,unused)) @@ -336,6 +338,7 @@ void exit(int status) * pid_t fork(void); */ +#ifndef sys_fork static __attribute__((unused)) pid_t sys_fork(void) { @@ -351,6 +354,7 @@ pid_t sys_fork(void) #error Neither __NR_clone nor __NR_fork defined, cannot implement sys_fork() #endif } +#endif static __attribute__((unused)) pid_t fork(void) @@ -858,7 +862,7 @@ int open(const char *path, int flags, ...) va_list args; va_start(args, flags); - mode = va_arg(args, mode_t); + mode = va_arg(args, int); va_end(args); } @@ -873,6 +877,32 @@ int open(const char *path, int flags, ...) /* + * int prctl(int option, unsigned long arg2, unsigned long arg3, + * unsigned long arg4, unsigned long arg5); + */ + +static __attribute__((unused)) +int sys_prctl(int option, unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5) +{ + return my_syscall5(__NR_prctl, option, arg2, arg3, arg4, arg5); +} + +static __attribute__((unused)) +int prctl(int option, unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5) +{ + int ret = sys_prctl(option, arg2, arg3, arg4, arg5); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* * int pivot_root(const char *new, const char *old); */ @@ -909,7 +939,7 @@ int sys_poll(struct pollfd *fds, int nfds, int timeout) t.tv_sec = timeout / 1000; t.tv_nsec = (timeout % 1000) * 1000000; } - return my_syscall4(__NR_ppoll, fds, nfds, (timeout >= 0) ? &t : NULL, NULL); + return my_syscall5(__NR_ppoll, fds, nfds, (timeout >= 0) ? &t : NULL, NULL, 0); #elif defined(__NR_poll) return my_syscall3(__NR_poll, fds, nfds, timeout); #else @@ -1131,23 +1161,26 @@ int sys_stat(const char *path, struct stat *buf) long ret; ret = sys_statx(AT_FDCWD, path, AT_NO_AUTOMOUNT, STATX_BASIC_STATS, &statx); - buf->st_dev = ((statx.stx_dev_minor & 0xff) - | (statx.stx_dev_major << 8) - | ((statx.stx_dev_minor & ~0xff) << 12)); - buf->st_ino = statx.stx_ino; - buf->st_mode = statx.stx_mode; - buf->st_nlink = statx.stx_nlink; - buf->st_uid = statx.stx_uid; - buf->st_gid = statx.stx_gid; - buf->st_rdev = ((statx.stx_rdev_minor & 0xff) - | (statx.stx_rdev_major << 8) - | ((statx.stx_rdev_minor & ~0xff) << 12)); - buf->st_size = statx.stx_size; - buf->st_blksize = statx.stx_blksize; - buf->st_blocks = statx.stx_blocks; - buf->st_atime = statx.stx_atime.tv_sec; - buf->st_mtime = statx.stx_mtime.tv_sec; - buf->st_ctime = statx.stx_ctime.tv_sec; + buf->st_dev = ((statx.stx_dev_minor & 0xff) + | (statx.stx_dev_major << 8) + | ((statx.stx_dev_minor & ~0xff) << 12)); + buf->st_ino = statx.stx_ino; + buf->st_mode = statx.stx_mode; + buf->st_nlink = statx.stx_nlink; + buf->st_uid = statx.stx_uid; + buf->st_gid = statx.stx_gid; + buf->st_rdev = ((statx.stx_rdev_minor & 0xff) + | (statx.stx_rdev_major << 8) + | ((statx.stx_rdev_minor & ~0xff) << 12)); + buf->st_size = statx.stx_size; + buf->st_blksize = statx.stx_blksize; + buf->st_blocks = statx.stx_blocks; + buf->st_atim.tv_sec = statx.stx_atime.tv_sec; + buf->st_atim.tv_nsec = statx.stx_atime.tv_nsec; + buf->st_mtim.tv_sec = statx.stx_mtime.tv_sec; + buf->st_mtim.tv_nsec = statx.stx_mtime.tv_nsec; + buf->st_ctim.tv_sec = statx.stx_ctime.tv_sec; + buf->st_ctim.tv_nsec = statx.stx_ctime.tv_nsec; return ret; } #else @@ -1165,19 +1198,22 @@ int sys_stat(const char *path, struct stat *buf) #else #error Neither __NR_newfstatat nor __NR_stat defined, cannot implement sys_stat() #endif - buf->st_dev = stat.st_dev; - buf->st_ino = stat.st_ino; - buf->st_mode = stat.st_mode; - buf->st_nlink = stat.st_nlink; - buf->st_uid = stat.st_uid; - buf->st_gid = stat.st_gid; - buf->st_rdev = stat.st_rdev; - buf->st_size = stat.st_size; - buf->st_blksize = stat.st_blksize; - buf->st_blocks = stat.st_blocks; - buf->st_atime = stat.st_atime; - buf->st_mtime = stat.st_mtime; - buf->st_ctime = stat.st_ctime; + buf->st_dev = stat.st_dev; + buf->st_ino = stat.st_ino; + buf->st_mode = stat.st_mode; + buf->st_nlink = stat.st_nlink; + buf->st_uid = stat.st_uid; + buf->st_gid = stat.st_gid; + buf->st_rdev = stat.st_rdev; + buf->st_size = stat.st_size; + buf->st_blksize = stat.st_blksize; + buf->st_blocks = stat.st_blocks; + buf->st_atim.tv_sec = stat.st_atime; + buf->st_atim.tv_nsec = stat.st_atime_nsec; + buf->st_mtim.tv_sec = stat.st_mtime; + buf->st_mtim.tv_nsec = stat.st_mtime_nsec; + buf->st_ctim.tv_sec = stat.st_ctime; + buf->st_ctim.tv_nsec = stat.st_ctime_nsec; return ret; } #endif @@ -1365,6 +1401,29 @@ ssize_t write(int fd, const void *buf, size_t count) return ret; } + +/* + * int memfd_create(const char *name, unsigned int flags); + */ + +static __attribute__((unused)) +int sys_memfd_create(const char *name, unsigned int flags) +{ + return my_syscall2(__NR_memfd_create, name, flags); +} + +static __attribute__((unused)) +int memfd_create(const char *name, unsigned int flags) +{ + ssize_t ret = sys_memfd_create(name, flags); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + /* make sure to include all global symbols */ #include "nolibc.h" diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h index aedd7d9e3f644..f96e28bff4bac 100644 --- a/tools/include/nolibc/types.h +++ b/tools/include/nolibc/types.h @@ -86,14 +86,6 @@ #define SEEK_CUR 1 #define SEEK_END 2 -/* cmd for reboot() */ -#define LINUX_REBOOT_MAGIC1 0xfee1dead -#define LINUX_REBOOT_MAGIC2 0x28121969 -#define LINUX_REBOOT_CMD_HALT 0xcdef0123 -#define LINUX_REBOOT_CMD_POWER_OFF 0x4321fedc -#define LINUX_REBOOT_CMD_RESTART 0x01234567 -#define LINUX_REBOOT_CMD_SW_SUSPEND 0xd000fce2 - /* Macros used on waitpid()'s return status */ #define WEXITSTATUS(status) (((status) & 0xff00) >> 8) #define WIFEXITED(status) (((status) & 0x7f) == 0) @@ -206,9 +198,9 @@ struct stat { off_t st_size; /* total size, in bytes */ blksize_t st_blksize; /* blocksize for file system I/O */ blkcnt_t st_blocks; /* number of 512B blocks allocated */ - time_t st_atime; /* time of last access */ - time_t st_mtime; /* time of last modification */ - time_t st_ctime; /* time of last status change */ + union { time_t st_atime; struct timespec st_atim; }; /* time of last access */ + union { time_t st_mtime; struct timespec st_mtim; }; /* time of last modification */ + union { time_t st_ctime; struct timespec st_ctim; }; /* time of last status change */ }; /* WARNING, it only deals with the 4096 first majors and 256 first minors */ diff --git a/tools/include/nolibc/unistd.h b/tools/include/nolibc/unistd.h index ac7d53d986cd1..0e832e10a0b27 100644 --- a/tools/include/nolibc/unistd.h +++ b/tools/include/nolibc/unistd.h @@ -56,6 +56,21 @@ int tcsetpgrp(int fd, pid_t pid) return ioctl(fd, TIOCSPGRP, &pid); } +#define _syscall(N, ...) \ +({ \ + long _ret = my_syscall##N(__VA_ARGS__); \ + if (_ret < 0) { \ + SET_ERRNO(-_ret); \ + _ret = -1; \ + } \ + _ret; \ +}) + +#define _syscall_narg(...) __syscall_narg(__VA_ARGS__, 6, 5, 4, 3, 2, 1, 0) +#define __syscall_narg(_0, _1, _2, _3, _4, _5, _6, N, ...) N +#define _syscall_n(N, ...) _syscall(N, __VA_ARGS__) +#define syscall(...) _syscall_n(_syscall_narg(__VA_ARGS__), ##__VA_ARGS__) + /* make sure to include all global symbols */ #include "nolibc.h" diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h index 8756df13be508..54d9c8bf7c55f 100644 --- a/tools/include/uapi/asm-generic/socket.h +++ b/tools/include/uapi/asm-generic/socket.h @@ -121,6 +121,9 @@ #define SO_RCVMARK 75 +#define SO_PASSPIDFD 76 +#define SO_PEERPIDFD 77 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 642808520d922..a87bbbbca2d48 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -972,6 +972,19 @@ extern "C" { #define DRM_IOCTL_GET_STATS DRM_IOR( 0x06, struct drm_stats) #define DRM_IOCTL_SET_VERSION DRM_IOWR(0x07, struct drm_set_version) #define DRM_IOCTL_MODESET_CTL DRM_IOW(0x08, struct drm_modeset_ctl) +/** + * DRM_IOCTL_GEM_CLOSE - Close a GEM handle. + * + * GEM handles are not reference-counted by the kernel. User-space is + * responsible for managing their lifetime. For example, if user-space imports + * the same memory object twice on the same DRM file description, the same GEM + * handle is returned by both imports, and user-space needs to ensure + * &DRM_IOCTL_GEM_CLOSE is performed once only. The same situation can happen + * when a memory object is allocated, then exported and imported again on the + * same DRM file description. The &DRM_IOCTL_MODE_GETFB2 IOCTL is an exception + * and always returns fresh new GEM handles even if an existing GEM handle + * already refers to the same memory object before the IOCTL is performed. + */ #define DRM_IOCTL_GEM_CLOSE DRM_IOW (0x09, struct drm_gem_close) #define DRM_IOCTL_GEM_FLINK DRM_IOWR(0x0a, struct drm_gem_flink) #define DRM_IOCTL_GEM_OPEN DRM_IOWR(0x0b, struct drm_gem_open) @@ -1012,7 +1025,37 @@ extern "C" { #define DRM_IOCTL_UNLOCK DRM_IOW( 0x2b, struct drm_lock) #define DRM_IOCTL_FINISH DRM_IOW( 0x2c, struct drm_lock) +/** + * DRM_IOCTL_PRIME_HANDLE_TO_FD - Convert a GEM handle to a DMA-BUF FD. + * + * User-space sets &drm_prime_handle.handle with the GEM handle to export and + * &drm_prime_handle.flags, and gets back a DMA-BUF file descriptor in + * &drm_prime_handle.fd. + * + * The export can fail for any driver-specific reason, e.g. because export is + * not supported for this specific GEM handle (but might be for others). + * + * Support for exporting DMA-BUFs is advertised via &DRM_PRIME_CAP_EXPORT. + */ #define DRM_IOCTL_PRIME_HANDLE_TO_FD DRM_IOWR(0x2d, struct drm_prime_handle) +/** + * DRM_IOCTL_PRIME_FD_TO_HANDLE - Convert a DMA-BUF FD to a GEM handle. + * + * User-space sets &drm_prime_handle.fd with a DMA-BUF file descriptor to + * import, and gets back a GEM handle in &drm_prime_handle.handle. + * &drm_prime_handle.flags is unused. + * + * If an existing GEM handle refers to the memory object backing the DMA-BUF, + * that GEM handle is returned. Therefore user-space which needs to handle + * arbitrary DMA-BUFs must have a user-space lookup data structure to manually + * reference-count duplicated GEM handles. For more information see + * &DRM_IOCTL_GEM_CLOSE. + * + * The import can fail for any driver-specific reason, e.g. because import is + * only supported for DMA-BUFs allocated on this DRM device. + * + * Support for importing DMA-BUFs is advertised via &DRM_PRIME_CAP_IMPORT. + */ #define DRM_IOCTL_PRIME_FD_TO_HANDLE DRM_IOWR(0x2e, struct drm_prime_handle) #define DRM_IOCTL_AGP_ACQUIRE DRM_IO( 0x30) @@ -1104,8 +1147,13 @@ extern "C" { * struct as the output. * * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles - * will be filled with GEM buffer handles. Planes are valid until one has a - * zero handle -- this can be used to compute the number of planes. + * will be filled with GEM buffer handles. Fresh new GEM handles are always + * returned, even if another GEM handle referring to the same memory object + * already exists on the DRM file description. The caller is responsible for + * removing the new handles, e.g. via the &DRM_IOCTL_GEM_CLOSE IOCTL. The same + * new handle will be returned for multiple planes in case they use the same + * memory object. Planes are valid until one has a zero handle -- this can be + * used to compute the number of planes. * * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid * until one has a zero &drm_mode_fb_cmd2.pitches. @@ -1113,6 +1161,11 @@ extern "C" { * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier. + * + * To obtain DMA-BUF FDs for each plane without leaking GEM handles, user-space + * can export each handle via &DRM_IOCTL_PRIME_HANDLE_TO_FD, then immediately + * close each unique handle via &DRM_IOCTL_GEM_CLOSE, making sure to not + * double-close handles which are specified multiple times in the array. */ #define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 8df261c5ab9b1..dba7c5a5b25e9 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -2491,7 +2491,7 @@ struct i915_context_param_engines { #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */ #define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __attribute__((packed)); #define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \ @@ -2676,6 +2676,10 @@ enum drm_i915_oa_format { I915_OAR_FORMAT_A32u40_A4u32_B8_C8, I915_OA_FORMAT_A24u40_A14u32_B8_C8, + /* MTL OAM */ + I915_OAM_FORMAT_MPEC8u64_B8_C8, + I915_OAM_FORMAT_MPEC8u32_B8_C8, + I915_OA_FORMAT_MAX /* non-ABI */ }; @@ -2758,6 +2762,25 @@ enum drm_i915_perf_property_id { */ DRM_I915_PERF_PROP_POLL_OA_PERIOD, + /** + * Multiple engines may be mapped to the same OA unit. The OA unit is + * identified by class:instance of any engine mapped to it. + * + * This parameter specifies the engine class and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_CLASS, + + /** + * This parameter specifies the engine instance and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_CLASS. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE, + DRM_I915_PERF_PROP_MAX /* non-ABI */ }; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1bb11a6ee6676..60a9d59beeabb 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1035,6 +1035,7 @@ enum bpf_attach_type { BPF_TRACE_KPROBE_MULTI, BPF_LSM_CGROUP, BPF_STRUCT_OPS, + BPF_NETFILTER, __MAX_BPF_ATTACH_TYPE }; @@ -1272,6 +1273,9 @@ enum { /* Create a map that will be registered/unregesitered by the backed bpf_link */ BPF_F_LINK = (1U << 13), + +/* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ + BPF_F_PATH_FD = (1U << 14), }; /* Flags for BPF_PROG_QUERY. */ @@ -1420,6 +1424,13 @@ union bpf_attr { __aligned_u64 pathname; __u32 bpf_fd; __u32 file_flags; + /* Same as dirfd in openat() syscall; see openat(2) + * manpage for details of path FD and pathname semantics; + * path_fd should accompanied by BPF_F_PATH_FD flag set in + * file_flags field, otherwise it should be set to zero; + * if BPF_F_PATH_FD flag is not set, AT_FDCWD is assumed. + */ + __s32 path_fd; }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ @@ -3167,6 +3178,10 @@ union bpf_attr { * **BPF_FIB_LOOKUP_DIRECT** * Do a direct table lookup vs full lookup using FIB * rules. + * **BPF_FIB_LOOKUP_TBID** + * Used with BPF_FIB_LOOKUP_DIRECT. + * Use the routing table ID present in *params*->tbid + * for the fib lookup. * **BPF_FIB_LOOKUP_OUTPUT** * Perform lookup from an egress perspective (default is * ingress). @@ -6821,6 +6836,7 @@ enum { BPF_FIB_LOOKUP_DIRECT = (1U << 0), BPF_FIB_LOOKUP_OUTPUT = (1U << 1), BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), + BPF_FIB_LOOKUP_TBID = (1U << 3), }; enum { @@ -6881,9 +6897,19 @@ struct bpf_fib_lookup { __u32 ipv6_dst[4]; /* in6_addr; network order */ }; - /* output */ - __be16 h_vlan_proto; - __be16 h_vlan_TCI; + union { + struct { + /* output */ + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + }; + /* input: when accompanied with the + * 'BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID` flags, a + * specific routing table to use for the fib lookup. + */ + __u32 tbid; + }; + __u8 smac[6]; /* ETH_ALEN */ __u8 dmac[6]; /* ETH_ALEN */ }; diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h index af2a44c08683d..a429381e7ca50 100644 --- a/tools/include/uapi/linux/const.h +++ b/tools/include/uapi/linux/const.h @@ -28,7 +28,7 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) -#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) +#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index 07a4cb149305b..e682ab628dfa6 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -162,6 +162,8 @@ struct in_addr { #define MCAST_MSFILTER 48 #define IP_MULTICAST_ALL 49 #define IP_UNICAST_IF 50 +#define IP_LOCAL_PORT_RANGE 51 +#define IP_PROTOCOL 52 #define MCAST_EXCLUDE 0 #define MCAST_INCLUDE 1 diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 4003a166328cc..737318b1c1d9a 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -341,8 +341,13 @@ struct kvm_run { __u64 nr; __u64 args[6]; __u64 ret; - __u32 longmode; - __u32 pad; + + union { +#ifndef __KERNEL__ + __u32 longmode; +#endif + __u64 flags; + }; } hypercall; /* KVM_EXIT_TPR_ACCESS */ struct { @@ -1184,6 +1189,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225 #define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226 +#define KVM_CAP_COUNTER_OFFSET 227 #ifdef KVM_CAP_IRQ_ROUTING @@ -1543,6 +1549,8 @@ struct kvm_s390_ucas_mapping { #define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) #define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3) #define KVM_ARM_MTE_COPY_TAGS _IOR(KVMIO, 0xb4, struct kvm_arm_copy_mte_tags) +/* Available with KVM_CAP_COUNTER_OFFSET */ +#define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO, 0xb5, struct kvm_arm_counter_offset) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 759b3f53e53f0..f23d9a16507f6 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -290,6 +290,8 @@ struct prctl_mm_map { #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 +#define PR_GET_AUXV 0x41555856 + #define PR_SET_MEMORY_MERGE 67 #define PR_GET_MEMORY_MERGE 68 #endif /* _LINUX_PRCTL_H */ diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index de6810e94abed..0aa955aa82463 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -429,9 +429,14 @@ struct snd_pcm_sw_params { snd_pcm_uframes_t avail_min; /* min avail frames for wakeup */ snd_pcm_uframes_t xfer_align; /* obsolete: xfer size need to be a multiple */ snd_pcm_uframes_t start_threshold; /* min hw_avail frames for automatic start */ - snd_pcm_uframes_t stop_threshold; /* min avail frames for automatic stop */ - snd_pcm_uframes_t silence_threshold; /* min distance from noise for silence filling */ - snd_pcm_uframes_t silence_size; /* silence block size */ + /* + * The following two thresholds alleviate playback buffer underruns; when + * hw_avail drops below the threshold, the respective action is triggered: + */ + snd_pcm_uframes_t stop_threshold; /* - stop playback */ + snd_pcm_uframes_t silence_threshold; /* - pre-fill buffer with silence */ + snd_pcm_uframes_t silence_size; /* max size of silence pre-fill; when >= boundary, + * fill played area with silence immediately */ snd_pcm_uframes_t boundary; /* pointers wrap point */ unsigned int proto; /* protocol version */ unsigned int tstamp_type; /* timestamp type (req. proto >= 2.0.12) */ @@ -570,7 +575,8 @@ struct __snd_pcm_mmap_status64 { struct __snd_pcm_mmap_control64 { __pad_before_uframe __pad1; snd_pcm_uframes_t appl_ptr; /* RW: appl ptr (0...boundary-1) */ - __pad_before_uframe __pad2; + __pad_before_uframe __pad2; // This should be __pad_after_uframe, but binary + // backwards compatibility constraints prevent a fix. __pad_before_uframe __pad3; snd_pcm_uframes_t avail_min; /* RW: min available frames for wakeup */ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 128ac723c4ea2..ed86b37d80243 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -572,20 +572,30 @@ int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *co (void *)keys, (void *)values, count, opts); } -int bpf_obj_pin(int fd, const char *pathname) +int bpf_obj_pin_opts(int fd, const char *pathname, const struct bpf_obj_pin_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, file_flags); + const size_t attr_sz = offsetofend(union bpf_attr, path_fd); union bpf_attr attr; int ret; + if (!OPTS_VALID(opts, bpf_obj_pin_opts)) + return libbpf_err(-EINVAL); + memset(&attr, 0, attr_sz); + attr.path_fd = OPTS_GET(opts, path_fd, 0); attr.pathname = ptr_to_u64((void *)pathname); + attr.file_flags = OPTS_GET(opts, file_flags, 0); attr.bpf_fd = fd; ret = sys_bpf(BPF_OBJ_PIN, &attr, attr_sz); return libbpf_err_errno(ret); } +int bpf_obj_pin(int fd, const char *pathname) +{ + return bpf_obj_pin_opts(fd, pathname, NULL); +} + int bpf_obj_get(const char *pathname) { return bpf_obj_get_opts(pathname, NULL); @@ -593,7 +603,7 @@ int bpf_obj_get(const char *pathname) int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, file_flags); + const size_t attr_sz = offsetofend(union bpf_attr, path_fd); union bpf_attr attr; int fd; @@ -601,6 +611,7 @@ int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts) return libbpf_err(-EINVAL); memset(&attr, 0, attr_sz); + attr.path_fd = OPTS_GET(opts, path_fd, 0); attr.pathname = ptr_to_u64((void *)pathname); attr.file_flags = OPTS_GET(opts, file_flags, 0); diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index a2c091389b186..9aa0ee4737546 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -284,16 +284,30 @@ LIBBPF_API int bpf_map_update_batch(int fd, const void *keys, const void *values __u32 *count, const struct bpf_map_batch_opts *opts); -struct bpf_obj_get_opts { +struct bpf_obj_pin_opts { size_t sz; /* size of this struct for forward/backward compatibility */ __u32 file_flags; + int path_fd; size_t :0; }; -#define bpf_obj_get_opts__last_field file_flags +#define bpf_obj_pin_opts__last_field path_fd LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); +LIBBPF_API int bpf_obj_pin_opts(int fd, const char *pathname, + const struct bpf_obj_pin_opts *opts); + +struct bpf_obj_get_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + + __u32 file_flags; + int path_fd; + + size_t :0; +}; +#define bpf_obj_get_opts__last_field path_fd + LIBBPF_API int bpf_obj_get(const char *pathname); LIBBPF_API int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts); diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 929a3baca8ef3..bbab9ad9dc5a7 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -77,16 +77,21 @@ /* * Helper macros to manipulate data structures */ -#ifndef offsetof -#define offsetof(TYPE, MEMBER) ((unsigned long)&((TYPE *)0)->MEMBER) -#endif -#ifndef container_of + +/* offsetof() definition that uses __builtin_offset() might not preserve field + * offset CO-RE relocation properly, so force-redefine offsetof() using + * old-school approach which works with CO-RE correctly + */ +#undef offsetof +#define offsetof(type, member) ((unsigned long)&((type *)0)->member) + +/* redefined container_of() to ensure we use the above offsetof() macro */ +#undef container_of #define container_of(ptr, type, member) \ ({ \ void *__mptr = (void *)(ptr); \ ((type *)(__mptr - offsetof(type, member))); \ }) -#endif /* * Compiler (optimization) barrier. diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index 6fb3d0f9af17e..be076a4041ab1 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -351,6 +351,7 @@ struct pt_regs___arm64 { * https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-cc.adoc#risc-v-calling-conventions */ +/* riscv provides struct user_regs_struct instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) #define __PT_PARM1_REG a0 #define __PT_PARM2_REG a1 @@ -383,7 +384,7 @@ struct pt_regs___arm64 { * https://raw.githubusercontent.com/wiki/foss-for-synopsys-dwc-arc-processors/toolchain/files/ARCv2_ABI.pdf */ -/* arc provides struct user_pt_regs instead of struct pt_regs to userspace */ +/* arc provides struct user_regs_struct instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) #define __PT_PARM1_REG scratch.r0 #define __PT_PARM2_REG scratch.r1 diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 0a2c079244b6e..8484b563b53d0 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1064,7 +1064,7 @@ static struct btf *btf_parse_raw(const char *path, struct btf *base_btf) int err = 0; long sz; - f = fopen(path, "rb"); + f = fopen(path, "rbe"); if (!f) { err = -errno; goto err_out; diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 580985ee55458..4d9f30bf7f014 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -2250,9 +2250,25 @@ static int btf_dump_type_data_check_overflow(struct btf_dump *d, const struct btf_type *t, __u32 id, const void *data, - __u8 bits_offset) + __u8 bits_offset, + __u8 bit_sz) { - __s64 size = btf__resolve_size(d->btf, id); + __s64 size; + + if (bit_sz) { + /* bits_offset is at most 7. bit_sz is at most 128. */ + __u8 nr_bytes = (bits_offset + bit_sz + 7) / 8; + + /* When bit_sz is non zero, it is called from + * btf_dump_struct_data() where it only cares about + * negative error value. + * Return nr_bytes in success case to make it + * consistent as the regular integer case below. + */ + return data + nr_bytes > d->typed_dump->data_end ? -E2BIG : nr_bytes; + } + + size = btf__resolve_size(d->btf, id); if (size < 0 || size >= INT_MAX) { pr_warn("unexpected size [%zu] for id [%u]\n", @@ -2407,7 +2423,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d, { int size, err = 0; - size = btf_dump_type_data_check_overflow(d, t, id, data, bits_offset); + size = btf_dump_type_data_check_overflow(d, t, id, data, bits_offset, bit_sz); if (size < 0) return size; err = btf_dump_type_data_check_zero(d, t, id, data, bits_offset, bit_sz); diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index 83e8e3bfd8ff3..cf3323fd47b88 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -703,17 +703,17 @@ static void emit_relo_kfunc_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo /* obtain fd in BPF_REG_9 */ emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7)); emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32)); - /* jump to fd_array store if fd denotes module BTF */ - emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 2)); - /* set the default value for off */ - emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0)); - /* skip BTF fd store for vmlinux BTF */ - emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4)); /* load fd_array slot pointer */ emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, blob_fd_array_off(gen, btf_fd_idx))); - /* store BTF fd in slot */ + /* store BTF fd in slot, 0 for vmlinux */ emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_9, 0)); + /* jump to insn[insn_idx].off store if fd denotes module BTF */ + emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 2)); + /* set the default value for off */ + emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0)); + /* skip BTF fd store for vmlinux BTF */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 1)); /* store index into insn[insn_idx].off */ emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), btf_fd_idx)); log: diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ad1ec893b41b2..214f828ece6bf 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -117,6 +117,7 @@ static const char * const attach_type_name[] = { [BPF_PERF_EVENT] = "perf_event", [BPF_TRACE_KPROBE_MULTI] = "trace_kprobe_multi", [BPF_STRUCT_OPS] = "struct_ops", + [BPF_NETFILTER] = "netfilter", }; static const char * const link_type_name[] = { @@ -1500,16 +1501,36 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) return map; } -static size_t bpf_map_mmap_sz(const struct bpf_map *map) +static size_t bpf_map_mmap_sz(unsigned int value_sz, unsigned int max_entries) { - long page_sz = sysconf(_SC_PAGE_SIZE); + const long page_sz = sysconf(_SC_PAGE_SIZE); size_t map_sz; - map_sz = (size_t)roundup(map->def.value_size, 8) * map->def.max_entries; + map_sz = (size_t)roundup(value_sz, 8) * max_entries; map_sz = roundup(map_sz, page_sz); return map_sz; } +static int bpf_map_mmap_resize(struct bpf_map *map, size_t old_sz, size_t new_sz) +{ + void *mmaped; + + if (!map->mmaped) + return -EINVAL; + + if (old_sz == new_sz) + return 0; + + mmaped = mmap(NULL, new_sz, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (mmaped == MAP_FAILED) + return -errno; + + memcpy(mmaped, map->mmaped, min(old_sz, new_sz)); + munmap(map->mmaped, old_sz); + map->mmaped = mmaped; + return 0; +} + static char *internal_map_name(struct bpf_object *obj, const char *real_name) { char map_name[BPF_OBJ_NAME_LEN], *p; @@ -1608,6 +1629,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, { struct bpf_map_def *def; struct bpf_map *map; + size_t mmap_sz; int err; map = bpf_object__add_map(obj); @@ -1642,7 +1664,8 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n", map->name, map->sec_idx, map->sec_offset, def->map_flags); - map->mmaped = mmap(NULL, bpf_map_mmap_sz(map), PROT_READ | PROT_WRITE, + mmap_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries); + map->mmaped = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); if (map->mmaped == MAP_FAILED) { err = -errno; @@ -4329,7 +4352,7 @@ static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info) snprintf(file, sizeof(file), "/proc/%d/fdinfo/%d", getpid(), fd); memset(info, 0, sizeof(*info)); - fp = fopen(file, "r"); + fp = fopen(file, "re"); if (!fp) { err = -errno; pr_warn("failed to open %s: %d. No procfs support?\n", file, @@ -4392,18 +4415,17 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) if (!new_name) return libbpf_err(-errno); - new_fd = open("/", O_RDONLY | O_CLOEXEC); + /* + * Like dup(), but make sure new FD is >= 3 and has O_CLOEXEC set. + * This is similar to what we do in ensure_good_fd(), but without + * closing original FD. + */ + new_fd = fcntl(fd, F_DUPFD_CLOEXEC, 3); if (new_fd < 0) { err = -errno; goto err_free_new_name; } - new_fd = dup3(fd, new_fd, O_CLOEXEC); - if (new_fd < 0) { - err = -errno; - goto err_close_new_fd; - } - err = zclose(map->fd); if (err) { err = -errno; @@ -7433,7 +7455,7 @@ int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *ctx) int ret, err = 0; FILE *f; - f = fopen("/proc/kallsyms", "r"); + f = fopen("/proc/kallsyms", "re"); if (!f) { err = -errno; pr_warn("failed to open /proc/kallsyms: %d\n", err); @@ -8294,7 +8316,10 @@ static void bpf_map__destroy(struct bpf_map *map) map->init_slots_sz = 0; if (map->mmaped) { - munmap(map->mmaped, bpf_map_mmap_sz(map)); + size_t mmap_sz; + + mmap_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries); + munmap(map->mmaped, mmap_sz); map->mmaped = NULL; } @@ -8712,7 +8737,7 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("struct_ops+", STRUCT_OPS, 0, SEC_NONE), SEC_DEF("struct_ops.s+", STRUCT_OPS, 0, SEC_SLEEPABLE), SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE), - SEC_DEF("netfilter", NETFILTER, 0, SEC_NONE), + SEC_DEF("netfilter", NETFILTER, BPF_NETFILTER, SEC_NONE), }; static size_t custom_sec_def_cnt; @@ -9412,10 +9437,103 @@ __u32 bpf_map__value_size(const struct bpf_map *map) return map->def.value_size; } +static int map_btf_datasec_resize(struct bpf_map *map, __u32 size) +{ + struct btf *btf; + struct btf_type *datasec_type, *var_type; + struct btf_var_secinfo *var; + const struct btf_type *array_type; + const struct btf_array *array; + int vlen, element_sz, new_array_id; + __u32 nr_elements; + + /* check btf existence */ + btf = bpf_object__btf(map->obj); + if (!btf) + return -ENOENT; + + /* verify map is datasec */ + datasec_type = btf_type_by_id(btf, bpf_map__btf_value_type_id(map)); + if (!btf_is_datasec(datasec_type)) { + pr_warn("map '%s': cannot be resized, map value type is not a datasec\n", + bpf_map__name(map)); + return -EINVAL; + } + + /* verify datasec has at least one var */ + vlen = btf_vlen(datasec_type); + if (vlen == 0) { + pr_warn("map '%s': cannot be resized, map value datasec is empty\n", + bpf_map__name(map)); + return -EINVAL; + } + + /* verify last var in the datasec is an array */ + var = &btf_var_secinfos(datasec_type)[vlen - 1]; + var_type = btf_type_by_id(btf, var->type); + array_type = skip_mods_and_typedefs(btf, var_type->type, NULL); + if (!btf_is_array(array_type)) { + pr_warn("map '%s': cannot be resized, last var must be an array\n", + bpf_map__name(map)); + return -EINVAL; + } + + /* verify request size aligns with array */ + array = btf_array(array_type); + element_sz = btf__resolve_size(btf, array->type); + if (element_sz <= 0 || (size - var->offset) % element_sz != 0) { + pr_warn("map '%s': cannot be resized, element size (%d) doesn't align with new total size (%u)\n", + bpf_map__name(map), element_sz, size); + return -EINVAL; + } + + /* create a new array based on the existing array, but with new length */ + nr_elements = (size - var->offset) / element_sz; + new_array_id = btf__add_array(btf, array->index_type, array->type, nr_elements); + if (new_array_id < 0) + return new_array_id; + + /* adding a new btf type invalidates existing pointers to btf objects, + * so refresh pointers before proceeding + */ + datasec_type = btf_type_by_id(btf, map->btf_value_type_id); + var = &btf_var_secinfos(datasec_type)[vlen - 1]; + var_type = btf_type_by_id(btf, var->type); + + /* finally update btf info */ + datasec_type->size = size; + var->size = size - var->offset; + var_type->type = new_array_id; + + return 0; +} + int bpf_map__set_value_size(struct bpf_map *map, __u32 size) { if (map->fd >= 0) return libbpf_err(-EBUSY); + + if (map->mmaped) { + int err; + size_t mmap_old_sz, mmap_new_sz; + + mmap_old_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries); + mmap_new_sz = bpf_map_mmap_sz(size, map->def.max_entries); + err = bpf_map_mmap_resize(map, mmap_old_sz, mmap_new_sz); + if (err) { + pr_warn("map '%s': failed to resize memory-mapped region: %d\n", + bpf_map__name(map), err); + return err; + } + err = map_btf_datasec_resize(map, size); + if (err && err != -ENOENT) { + pr_warn("map '%s': failed to adjust resized BTF, clearing BTF key/value info: %d\n", + bpf_map__name(map), err); + map->btf_value_type_id = 0; + map->btf_key_type_id = 0; + } + } + map->def.value_size = size; return 0; } @@ -9441,7 +9559,7 @@ int bpf_map__set_initial_value(struct bpf_map *map, return 0; } -const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize) +void *bpf_map__initial_value(struct bpf_map *map, size_t *psize) { if (!map->mmaped) return NULL; @@ -9957,7 +10075,7 @@ static int parse_uint_from_file(const char *file, const char *fmt) int err, ret; FILE *f; - f = fopen(file, "r"); + f = fopen(file, "re"); if (!f) { err = -errno; pr_debug("failed to open '%s': %s\n", file, @@ -12693,7 +12811,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s) for (i = 0; i < s->map_cnt; i++) { struct bpf_map *map = *s->maps[i].map; - size_t mmap_sz = bpf_map_mmap_sz(map); + size_t mmap_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries); int prot, map_fd = bpf_map__fd(map); void **mmaped = s->maps[i].mmaped; @@ -12720,8 +12838,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s) * as per normal clean up procedure, so we don't need to worry * about it from skeleton's clean up perspective. */ - *mmaped = mmap(map->mmaped, mmap_sz, prot, - MAP_SHARED | MAP_FIXED, map_fd, 0); + *mmaped = mmap(map->mmaped, mmap_sz, prot, MAP_SHARED | MAP_FIXED, map_fd, 0); if (*mmaped == MAP_FAILED) { err = -errno; *mmaped = NULL; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 0b7362397ea34..754da73c643b2 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -869,8 +869,22 @@ LIBBPF_API int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node); /* get/set map key size */ LIBBPF_API __u32 bpf_map__key_size(const struct bpf_map *map); LIBBPF_API int bpf_map__set_key_size(struct bpf_map *map, __u32 size); -/* get/set map value size */ +/* get map value size */ LIBBPF_API __u32 bpf_map__value_size(const struct bpf_map *map); +/** + * @brief **bpf_map__set_value_size()** sets map value size. + * @param map the BPF map instance + * @return 0, on success; negative error, otherwise + * + * There is a special case for maps with associated memory-mapped regions, like + * the global data section maps (bss, data, rodata). When this function is used + * on such a map, the mapped region is resized. Afterward, an attempt is made to + * adjust the corresponding BTF info. This attempt is best-effort and can only + * succeed if the last variable of the data section map is an array. The array + * BTF type is replaced by a new BTF array type with a different length. + * Any previously existing pointers returned from bpf_map__initial_value() or + * corresponding data section skeleton pointer must be reinitialized. + */ LIBBPF_API int bpf_map__set_value_size(struct bpf_map *map, __u32 size); /* get map key/value BTF type IDs */ LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map); @@ -884,7 +898,7 @@ LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra); LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size); -LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); +LIBBPF_API void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); /** * @brief **bpf_map__is_internal()** tells the caller whether or not the diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index a5aa3a383d694..7521a2fb76264 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -391,3 +391,8 @@ LIBBPF_1.2.0 { bpf_map_get_info_by_fd; bpf_prog_get_info_by_fd; } LIBBPF_1.1.0; + +LIBBPF_1.3.0 { + global: + bpf_obj_pin_opts; +} LIBBPF_1.2.0; diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 6065f408a59c1..9c4db90b92b6b 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -38,7 +38,7 @@ static __u32 get_ubuntu_kernel_version(void) if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) != 0) return 0; - f = fopen(ubuntu_kver_file, "r"); + f = fopen(ubuntu_kver_file, "re"); if (!f) return 0; @@ -180,7 +180,9 @@ static int probe_prog_load(enum bpf_prog_type prog_type, case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SYSCTL: + break; case BPF_PROG_TYPE_NETFILTER: + opts.expected_attach_type = BPF_NETFILTER; break; default: return -EOPNOTSUPP; diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h index 1fd2eeac5cfc1..290411ddb39e9 100644 --- a/tools/lib/bpf/libbpf_version.h +++ b/tools/lib/bpf/libbpf_version.h @@ -4,6 +4,6 @@ #define __LIBBPF_VERSION_H #define LIBBPF_MAJOR_VERSION 1 -#define LIBBPF_MINOR_VERSION 2 +#define LIBBPF_MINOR_VERSION 3 #endif /* __LIBBPF_VERSION_H */ diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c index 086eef355ab3d..f1a141555f084 100644 --- a/tools/lib/bpf/usdt.c +++ b/tools/lib/bpf/usdt.c @@ -466,7 +466,7 @@ static int parse_vma_segs(int pid, const char *lib_path, struct elf_seg **segs, proceed: sprintf(line, "/proc/%d/maps", pid); - f = fopen(line, "r"); + f = fopen(line, "re"); if (!f) { err = -errno; pr_warn("usdt: failed to open '%s' to get base addr of '%s': %d\n", @@ -954,8 +954,7 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct spec_map_fd = bpf_map__fd(man->specs_map); ip_map_fd = bpf_map__fd(man->ip_to_spec_id_map); - /* TODO: perform path resolution similar to uprobe's */ - fd = open(path, O_RDONLY); + fd = open(path, O_RDONLY | O_CLOEXEC); if (fd < 0) { err = -errno; pr_warn("usdt: failed to open ELF binary '%s': %d\n", path, err); diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h index 41b9b942504d3..8e9147358a281 100644 --- a/tools/lib/subcmd/parse-options.h +++ b/tools/lib/subcmd/parse-options.h @@ -6,10 +6,6 @@ #include <stdbool.h> #include <stdint.h> -#ifndef NORETURN -#define NORETURN __attribute__((__noreturn__)) -#endif - enum parse_opt_type { /* special types */ OPTION_END, @@ -183,9 +179,9 @@ extern int parse_options_subcommand(int argc, const char **argv, const char *const subcommands[], const char *usagestr[], int flags); -extern NORETURN void usage_with_options(const char * const *usagestr, +extern __noreturn void usage_with_options(const char * const *usagestr, const struct option *options); -extern NORETURN __attribute__((format(printf,3,4))) +extern __noreturn __attribute__((format(printf,3,4))) void usage_with_options_msg(const char * const *usagestr, const struct option *options, const char *fmt, ...); diff --git a/tools/lib/subcmd/subcmd-util.h b/tools/lib/subcmd/subcmd-util.h index b2aec04fce8f6..dfac76e35ac73 100644 --- a/tools/lib/subcmd/subcmd-util.h +++ b/tools/lib/subcmd/subcmd-util.h @@ -5,8 +5,7 @@ #include <stdarg.h> #include <stdlib.h> #include <stdio.h> - -#define NORETURN __attribute__((__noreturn__)) +#include <linux/compiler.h> static inline void report(const char *prefix, const char *err, va_list params) { @@ -15,7 +14,7 @@ static inline void report(const char *prefix, const char *err, va_list params) fprintf(stderr, " %s%s\n", prefix, msg); } -static NORETURN inline void die(const char *err, ...) +static __noreturn inline void die(const char *err, ...) { va_list params; diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile new file mode 100644 index 0000000000000..d664b36deb5b5 --- /dev/null +++ b/tools/net/ynl/Makefile @@ -0,0 +1,19 @@ +# SPDX-License-Identifier: GPL-2.0 + +SUBDIRS = lib generated samples + +all: $(SUBDIRS) + +$(SUBDIRS): + @if [ -f "$@/Makefile" ] ; then \ + $(MAKE) -C $@ ; \ + fi + +clean hardclean: + @for dir in $(SUBDIRS) ; do \ + if [ -f "$$dir/Makefile" ] ; then \ + $(MAKE) -C $$dir $@; \ + fi \ + done + +.PHONY: clean all $(SUBDIRS) diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps new file mode 100644 index 0000000000000..f842bc66b9672 --- /dev/null +++ b/tools/net/ynl/Makefile.deps @@ -0,0 +1,20 @@ +# SPDX-License-Identifier: GPL-2.0 + +# Try to include uAPI headers from the kernel uapi/ path. +# Most code under tools/ requires the respective kernel uAPI headers +# to be copied to tools/include. The duplication is annoying. +# All the family headers should be self-contained. We avoid the copying +# by selectively including just the uAPI header of the family directly +# from the kernel sources. + +UAPI_PATH:=../../../../include/uapi/ + +# scripts/headers_install.sh strips "_UAPI" from header guards so we +# need the explicit -D matching what's in /usr, to avoid multiple definitions. + +get_hdr_inc=-D$(1) -include $(UAPI_PATH)/linux/$(2) + +CFLAGS_devlink:=$(call get_hdr_inc,_LINUX_DEVLINK_H_,devlink.h) +CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) +CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h) +CFLAGS_netdev:=$(call get_hdr_inc,_LINUX_NETDEV_H,netdev.h) diff --git a/tools/net/ynl/generated/Makefile b/tools/net/ynl/generated/Makefile new file mode 100644 index 0000000000000..f8817d2e56e41 --- /dev/null +++ b/tools/net/ynl/generated/Makefile @@ -0,0 +1,50 @@ +# SPDX-License-Identifier: GPL-2.0 + +CC=gcc +CFLAGS=-std=gnu11 -O2 -W -Wall -Wextra -Wno-unused-parameter -Wshadow \ + -I../lib/ -idirafter $(UAPI_PATH) +ifeq ("$(DEBUG)","1") + CFLAGS += -g -fsanitize=address -fsanitize=leak -static-libasan +endif + +include ../Makefile.deps + +YNL_GEN_ARG_ethtool:=--user-header linux/ethtool_netlink.h \ + --exclude-op stats-get + +TOOL:=../ynl-gen-c.py + +GENS:=ethtool devlink handshake fou netdev +SRCS=$(patsubst %,%-user.c,${GENS}) +HDRS=$(patsubst %,%-user.h,${GENS}) +OBJS=$(patsubst %,%-user.o,${GENS}) + +all: protos.a $(HDRS) $(SRCS) $(KHDRS) $(KSRCS) $(UAPI) regen + +protos.a: $(OBJS) + @echo -e "\tAR $@" + @ar rcs $@ $(OBJS) + +%-user.h: ../../../../Documentation/netlink/specs/%.yaml $(TOOL) + @echo -e "\tGEN $@" + @$(TOOL) --mode user --header --spec $< $(YNL_GEN_ARG_$*) > $@ + +%-user.c: ../../../../Documentation/netlink/specs/%.yaml $(TOOL) + @echo -e "\tGEN $@" + @$(TOOL) --mode user --source --spec $< $(YNL_GEN_ARG_$*) > $@ + +%-user.o: %-user.c %-user.h + @echo -e "\tCC $@" + @$(COMPILE.c) $(CFLAGS_$*) -o $@ $< + +clean: + rm -f *.o + +hardclean: clean + rm -f *.c *.h *.a + +regen: + @../ynl-regen.sh + +.PHONY: all clean hardclean regen +.DEFAULT_GOAL: all diff --git a/tools/net/ynl/generated/devlink-user.c b/tools/net/ynl/generated/devlink-user.c new file mode 100644 index 0000000000000..939bd45feacad --- /dev/null +++ b/tools/net/ynl/generated/devlink-user.c @@ -0,0 +1,721 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/devlink.yaml */ +/* YNL-GEN user source */ + +#include <stdlib.h> +#include <string.h> +#include "devlink-user.h" +#include "ynl.h" +#include <linux/devlink.h> + +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> + +/* Enums */ +static const char * const devlink_op_strmap[] = { + [3] = "get", + [DEVLINK_CMD_INFO_GET] = "info-get", +}; + +const char *devlink_op_str(int op) +{ + if (op < 0 || op >= (int)MNL_ARRAY_SIZE(devlink_op_strmap)) + return NULL; + return devlink_op_strmap[op]; +} + +/* Policies */ +struct ynl_policy_attr devlink_dl_info_version_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_INFO_VERSION_NAME] = { .name = "info-version-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_INFO_VERSION_VALUE] = { .name = "info-version-value", .type = YNL_PT_NUL_STR, }, +}; + +struct ynl_policy_nest devlink_dl_info_version_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_info_version_policy, +}; + +struct ynl_policy_attr devlink_dl_reload_stats_entry_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_RELOAD_STATS_LIMIT] = { .name = "reload-stats-limit", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_RELOAD_STATS_VALUE] = { .name = "reload-stats-value", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest devlink_dl_reload_stats_entry_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_reload_stats_entry_policy, +}; + +struct ynl_policy_attr devlink_dl_reload_act_stats_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_RELOAD_STATS_ENTRY] = { .name = "reload-stats-entry", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_entry_nest, }, +}; + +struct ynl_policy_nest devlink_dl_reload_act_stats_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_reload_act_stats_policy, +}; + +struct ynl_policy_attr devlink_dl_reload_act_info_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_RELOAD_ACTION] = { .name = "reload-action", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_RELOAD_ACTION_STATS] = { .name = "reload-action-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_stats_nest, }, +}; + +struct ynl_policy_nest devlink_dl_reload_act_info_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_reload_act_info_policy, +}; + +struct ynl_policy_attr devlink_dl_reload_stats_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_RELOAD_ACTION_INFO] = { .name = "reload-action-info", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_info_nest, }, +}; + +struct ynl_policy_nest devlink_dl_reload_stats_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_reload_stats_policy, +}; + +struct ynl_policy_attr devlink_dl_dev_stats_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_RELOAD_STATS] = { .name = "reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, }, + [DEVLINK_ATTR_REMOTE_RELOAD_STATS] = { .name = "remote-reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, }, +}; + +struct ynl_policy_nest devlink_dl_dev_stats_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dev_stats_policy, +}; + +struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .name = "bus-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_DEV_NAME] = { .name = "dev-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_PORT_INDEX] = { .name = "port-index", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_INFO_DRIVER_NAME] = { .name = "info-driver-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_INFO_SERIAL_NUMBER] = { .name = "info-serial-number", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_INFO_VERSION_FIXED] = { .name = "info-version-fixed", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, }, + [DEVLINK_ATTR_INFO_VERSION_RUNNING] = { .name = "info-version-running", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, }, + [DEVLINK_ATTR_INFO_VERSION_STORED] = { .name = "info-version-stored", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, }, + [DEVLINK_ATTR_INFO_VERSION_NAME] = { .name = "info-version-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_INFO_VERSION_VALUE] = { .name = "info-version-value", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_RELOAD_FAILED] = { .name = "reload-failed", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_RELOAD_ACTION] = { .name = "reload-action", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_DEV_STATS] = { .name = "dev-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_dev_stats_nest, }, + [DEVLINK_ATTR_RELOAD_STATS] = { .name = "reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, }, + [DEVLINK_ATTR_RELOAD_STATS_ENTRY] = { .name = "reload-stats-entry", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_entry_nest, }, + [DEVLINK_ATTR_RELOAD_STATS_LIMIT] = { .name = "reload-stats-limit", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_RELOAD_STATS_VALUE] = { .name = "reload-stats-value", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_REMOTE_RELOAD_STATS] = { .name = "remote-reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, }, + [DEVLINK_ATTR_RELOAD_ACTION_INFO] = { .name = "reload-action-info", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_info_nest, }, + [DEVLINK_ATTR_RELOAD_ACTION_STATS] = { .name = "reload-action-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_stats_nest, }, +}; + +struct ynl_policy_nest devlink_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_policy, +}; + +/* Common nested types */ +void devlink_dl_info_version_free(struct devlink_dl_info_version *obj) +{ + free(obj->info_version_name); + free(obj->info_version_value); +} + +int devlink_dl_info_version_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_info_version *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_INFO_VERSION_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.info_version_name_len = len; + dst->info_version_name = malloc(len + 1); + memcpy(dst->info_version_name, mnl_attr_get_str(attr), len); + dst->info_version_name[len] = 0; + } else if (type == DEVLINK_ATTR_INFO_VERSION_VALUE) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.info_version_value_len = len; + dst->info_version_value = malloc(len + 1); + memcpy(dst->info_version_value, mnl_attr_get_str(attr), len); + dst->info_version_value[len] = 0; + } + } + + return 0; +} + +void +devlink_dl_reload_stats_entry_free(struct devlink_dl_reload_stats_entry *obj) +{ +} + +int devlink_dl_reload_stats_entry_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_reload_stats_entry *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_RELOAD_STATS_LIMIT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.reload_stats_limit = 1; + dst->reload_stats_limit = mnl_attr_get_u8(attr); + } else if (type == DEVLINK_ATTR_RELOAD_STATS_VALUE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.reload_stats_value = 1; + dst->reload_stats_value = mnl_attr_get_u32(attr); + } + } + + return 0; +} + +void devlink_dl_reload_act_stats_free(struct devlink_dl_reload_act_stats *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_reload_stats_entry; i++) + devlink_dl_reload_stats_entry_free(&obj->reload_stats_entry[i]); + free(obj->reload_stats_entry); +} + +int devlink_dl_reload_act_stats_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_reload_act_stats *dst = yarg->data; + unsigned int n_reload_stats_entry = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->reload_stats_entry) + return ynl_error_parse(yarg, "attribute already present (dl-reload-act-stats.reload-stats-entry)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_RELOAD_STATS_ENTRY) { + n_reload_stats_entry++; + } + } + + if (n_reload_stats_entry) { + dst->reload_stats_entry = calloc(n_reload_stats_entry, sizeof(*dst->reload_stats_entry)); + dst->n_reload_stats_entry = n_reload_stats_entry; + i = 0; + parg.rsp_policy = &devlink_dl_reload_stats_entry_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RELOAD_STATS_ENTRY) { + parg.data = &dst->reload_stats_entry[i]; + if (devlink_dl_reload_stats_entry_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void devlink_dl_reload_act_info_free(struct devlink_dl_reload_act_info *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_reload_action_stats; i++) + devlink_dl_reload_act_stats_free(&obj->reload_action_stats[i]); + free(obj->reload_action_stats); +} + +int devlink_dl_reload_act_info_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_reload_act_info *dst = yarg->data; + unsigned int n_reload_action_stats = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->reload_action_stats) + return ynl_error_parse(yarg, "attribute already present (dl-reload-act-info.reload-action-stats)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_RELOAD_ACTION) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.reload_action = 1; + dst->reload_action = mnl_attr_get_u8(attr); + } else if (type == DEVLINK_ATTR_RELOAD_ACTION_STATS) { + n_reload_action_stats++; + } + } + + if (n_reload_action_stats) { + dst->reload_action_stats = calloc(n_reload_action_stats, sizeof(*dst->reload_action_stats)); + dst->n_reload_action_stats = n_reload_action_stats; + i = 0; + parg.rsp_policy = &devlink_dl_reload_act_stats_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RELOAD_ACTION_STATS) { + parg.data = &dst->reload_action_stats[i]; + if (devlink_dl_reload_act_stats_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void devlink_dl_reload_stats_free(struct devlink_dl_reload_stats *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_reload_action_info; i++) + devlink_dl_reload_act_info_free(&obj->reload_action_info[i]); + free(obj->reload_action_info); +} + +int devlink_dl_reload_stats_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_reload_stats *dst = yarg->data; + unsigned int n_reload_action_info = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->reload_action_info) + return ynl_error_parse(yarg, "attribute already present (dl-reload-stats.reload-action-info)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_RELOAD_ACTION_INFO) { + n_reload_action_info++; + } + } + + if (n_reload_action_info) { + dst->reload_action_info = calloc(n_reload_action_info, sizeof(*dst->reload_action_info)); + dst->n_reload_action_info = n_reload_action_info; + i = 0; + parg.rsp_policy = &devlink_dl_reload_act_info_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RELOAD_ACTION_INFO) { + parg.data = &dst->reload_action_info[i]; + if (devlink_dl_reload_act_info_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void devlink_dl_dev_stats_free(struct devlink_dl_dev_stats *obj) +{ + devlink_dl_reload_stats_free(&obj->reload_stats); + devlink_dl_reload_stats_free(&obj->remote_reload_stats); +} + +int devlink_dl_dev_stats_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dev_stats *dst = yarg->data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + parg.ys = yarg->ys; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_RELOAD_STATS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.reload_stats = 1; + + parg.rsp_policy = &devlink_dl_reload_stats_nest; + parg.data = &dst->reload_stats; + if (devlink_dl_reload_stats_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == DEVLINK_ATTR_REMOTE_RELOAD_STATS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.remote_reload_stats = 1; + + parg.rsp_policy = &devlink_dl_reload_stats_nest; + parg.data = &dst->remote_reload_stats; + if (devlink_dl_reload_stats_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return 0; +} + +/* ============== DEVLINK_CMD_GET ============== */ +/* DEVLINK_CMD_GET - do */ +void devlink_get_req_free(struct devlink_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_get_rsp_free(struct devlink_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + devlink_dl_dev_stats_free(&rsp->dev_stats); + free(rsp); +} + +int devlink_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct devlink_get_rsp *dst; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_RELOAD_FAILED) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.reload_failed = 1; + dst->reload_failed = mnl_attr_get_u8(attr); + } else if (type == DEVLINK_ATTR_RELOAD_ACTION) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.reload_action = 1; + dst->reload_action = mnl_attr_get_u8(attr); + } else if (type == DEVLINK_ATTR_DEV_STATS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dev_stats = 1; + + parg.rsp_policy = &devlink_dl_dev_stats_nest; + parg.data = &dst->dev_stats; + if (devlink_dl_dev_stats_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return MNL_CB_OK; +} + +struct devlink_get_rsp * +devlink_get(struct ynl_sock *ys, struct devlink_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_get_rsp_parse; + yrs.rsp_cmd = 3; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_GET - dump */ +void devlink_get_list_free(struct devlink_get_list *rsp) +{ + struct devlink_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + devlink_dl_dev_stats_free(&rsp->obj.dev_stats); + free(rsp); + } +} + +struct devlink_get_list *devlink_get_dump(struct ynl_sock *ys) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_get_list); + yds.cb = devlink_get_rsp_parse; + yds.rsp_cmd = 3; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_GET, 1); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_INFO_GET ============== */ +/* DEVLINK_CMD_INFO_GET - do */ +void devlink_info_get_req_free(struct devlink_info_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_info_get_rsp_free(struct devlink_info_get_rsp *rsp) +{ + unsigned int i; + + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp->info_driver_name); + free(rsp->info_serial_number); + for (i = 0; i < rsp->n_info_version_fixed; i++) + devlink_dl_info_version_free(&rsp->info_version_fixed[i]); + free(rsp->info_version_fixed); + for (i = 0; i < rsp->n_info_version_running; i++) + devlink_dl_info_version_free(&rsp->info_version_running[i]); + free(rsp->info_version_running); + for (i = 0; i < rsp->n_info_version_stored; i++) + devlink_dl_info_version_free(&rsp->info_version_stored[i]); + free(rsp->info_version_stored); + free(rsp); +} + +int devlink_info_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + unsigned int n_info_version_running = 0; + unsigned int n_info_version_stored = 0; + unsigned int n_info_version_fixed = 0; + struct ynl_parse_arg *yarg = data; + struct devlink_info_get_rsp *dst; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + dst = yarg->data; + parg.ys = yarg->ys; + + if (dst->info_version_fixed) + return ynl_error_parse(yarg, "attribute already present (devlink.info-version-fixed)"); + if (dst->info_version_running) + return ynl_error_parse(yarg, "attribute already present (devlink.info-version-running)"); + if (dst->info_version_stored) + return ynl_error_parse(yarg, "attribute already present (devlink.info-version-stored)"); + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_INFO_DRIVER_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.info_driver_name_len = len; + dst->info_driver_name = malloc(len + 1); + memcpy(dst->info_driver_name, mnl_attr_get_str(attr), len); + dst->info_driver_name[len] = 0; + } else if (type == DEVLINK_ATTR_INFO_SERIAL_NUMBER) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.info_serial_number_len = len; + dst->info_serial_number = malloc(len + 1); + memcpy(dst->info_serial_number, mnl_attr_get_str(attr), len); + dst->info_serial_number[len] = 0; + } else if (type == DEVLINK_ATTR_INFO_VERSION_FIXED) { + n_info_version_fixed++; + } else if (type == DEVLINK_ATTR_INFO_VERSION_RUNNING) { + n_info_version_running++; + } else if (type == DEVLINK_ATTR_INFO_VERSION_STORED) { + n_info_version_stored++; + } + } + + if (n_info_version_fixed) { + dst->info_version_fixed = calloc(n_info_version_fixed, sizeof(*dst->info_version_fixed)); + dst->n_info_version_fixed = n_info_version_fixed; + i = 0; + parg.rsp_policy = &devlink_dl_info_version_nest; + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_INFO_VERSION_FIXED) { + parg.data = &dst->info_version_fixed[i]; + if (devlink_dl_info_version_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + if (n_info_version_running) { + dst->info_version_running = calloc(n_info_version_running, sizeof(*dst->info_version_running)); + dst->n_info_version_running = n_info_version_running; + i = 0; + parg.rsp_policy = &devlink_dl_info_version_nest; + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_INFO_VERSION_RUNNING) { + parg.data = &dst->info_version_running[i]; + if (devlink_dl_info_version_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + if (n_info_version_stored) { + dst->info_version_stored = calloc(n_info_version_stored, sizeof(*dst->info_version_stored)); + dst->n_info_version_stored = n_info_version_stored; + i = 0; + parg.rsp_policy = &devlink_dl_info_version_nest; + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_INFO_VERSION_STORED) { + parg.data = &dst->info_version_stored[i]; + if (devlink_dl_info_version_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return MNL_CB_OK; +} + +struct devlink_info_get_rsp * +devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_info_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_INFO_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_info_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_INFO_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_info_get_rsp_free(rsp); + return NULL; +} + +const struct ynl_family ynl_devlink_family = { + .name = "devlink", +}; diff --git a/tools/net/ynl/generated/devlink-user.h b/tools/net/ynl/generated/devlink-user.h new file mode 100644 index 0000000000000..a008b99b6e241 --- /dev/null +++ b/tools/net/ynl/generated/devlink-user.h @@ -0,0 +1,210 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/devlink.yaml */ +/* YNL-GEN user header */ + +#ifndef _LINUX_DEVLINK_GEN_H +#define _LINUX_DEVLINK_GEN_H + +#include <stdlib.h> +#include <string.h> +#include <linux/types.h> +#include <linux/devlink.h> + +struct ynl_sock; + +extern const struct ynl_family ynl_devlink_family; + +/* Enums */ +const char *devlink_op_str(int op); + +/* Common nested types */ +struct devlink_dl_info_version { + struct { + __u32 info_version_name_len; + __u32 info_version_value_len; + } _present; + + char *info_version_name; + char *info_version_value; +}; + +struct devlink_dl_reload_stats_entry { + struct { + __u32 reload_stats_limit:1; + __u32 reload_stats_value:1; + } _present; + + __u8 reload_stats_limit; + __u32 reload_stats_value; +}; + +struct devlink_dl_reload_act_stats { + unsigned int n_reload_stats_entry; + struct devlink_dl_reload_stats_entry *reload_stats_entry; +}; + +struct devlink_dl_reload_act_info { + struct { + __u32 reload_action:1; + } _present; + + __u8 reload_action; + unsigned int n_reload_action_stats; + struct devlink_dl_reload_act_stats *reload_action_stats; +}; + +struct devlink_dl_reload_stats { + unsigned int n_reload_action_info; + struct devlink_dl_reload_act_info *reload_action_info; +}; + +struct devlink_dl_dev_stats { + struct { + __u32 reload_stats:1; + __u32 remote_reload_stats:1; + } _present; + + struct devlink_dl_reload_stats reload_stats; + struct devlink_dl_reload_stats remote_reload_stats; +}; + +/* ============== DEVLINK_CMD_GET ============== */ +/* DEVLINK_CMD_GET - do */ +struct devlink_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_get_req *devlink_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_get_req)); +} +void devlink_get_req_free(struct devlink_get_req *req); + +static inline void +devlink_get_req_set_bus_name(struct devlink_get_req *req, const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_get_req_set_dev_name(struct devlink_get_req *req, const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 reload_failed:1; + __u32 reload_action:1; + __u32 dev_stats:1; + } _present; + + char *bus_name; + char *dev_name; + __u8 reload_failed; + __u8 reload_action; + struct devlink_dl_dev_stats dev_stats; +}; + +void devlink_get_rsp_free(struct devlink_get_rsp *rsp); + +/* + * Get devlink instances. + */ +struct devlink_get_rsp * +devlink_get(struct ynl_sock *ys, struct devlink_get_req *req); + +/* DEVLINK_CMD_GET - dump */ +struct devlink_get_list { + struct devlink_get_list *next; + struct devlink_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_get_list_free(struct devlink_get_list *rsp); + +struct devlink_get_list *devlink_get_dump(struct ynl_sock *ys); + +/* ============== DEVLINK_CMD_INFO_GET ============== */ +/* DEVLINK_CMD_INFO_GET - do */ +struct devlink_info_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_info_get_req *devlink_info_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_info_get_req)); +} +void devlink_info_get_req_free(struct devlink_info_get_req *req); + +static inline void +devlink_info_get_req_set_bus_name(struct devlink_info_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_info_get_req_set_dev_name(struct devlink_info_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_info_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 info_driver_name_len; + __u32 info_serial_number_len; + } _present; + + char *bus_name; + char *dev_name; + char *info_driver_name; + char *info_serial_number; + unsigned int n_info_version_fixed; + struct devlink_dl_info_version *info_version_fixed; + unsigned int n_info_version_running; + struct devlink_dl_info_version *info_version_running; + unsigned int n_info_version_stored; + struct devlink_dl_info_version *info_version_stored; +}; + +void devlink_info_get_rsp_free(struct devlink_info_get_rsp *rsp); + +/* + * Get device information, like driver name, hardware and firmware versions etc. + */ +struct devlink_info_get_rsp * +devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req); + +#endif /* _LINUX_DEVLINK_GEN_H */ diff --git a/tools/net/ynl/generated/ethtool-user.c b/tools/net/ynl/generated/ethtool-user.c new file mode 100644 index 0000000000000..74b883a14958f --- /dev/null +++ b/tools/net/ynl/generated/ethtool-user.c @@ -0,0 +1,6353 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/ethtool.yaml */ +/* YNL-GEN user source */ +/* YNL-ARG --user-header linux/ethtool_netlink.h --exclude-op stats-get */ + +#include <stdlib.h> +#include <string.h> +#include "ethtool-user.h" +#include "ynl.h" +#include <linux/ethtool.h> + +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> + +#include "linux/ethtool_netlink.h" + +/* Enums */ +static const char * const ethtool_op_strmap[] = { + [ETHTOOL_MSG_STRSET_GET] = "strset-get", + [ETHTOOL_MSG_LINKINFO_GET] = "linkinfo-get", + [3] = "linkinfo-ntf", + [ETHTOOL_MSG_LINKMODES_GET] = "linkmodes-get", + [5] = "linkmodes-ntf", + [ETHTOOL_MSG_LINKSTATE_GET] = "linkstate-get", + [ETHTOOL_MSG_DEBUG_GET] = "debug-get", + [8] = "debug-ntf", + [ETHTOOL_MSG_WOL_GET] = "wol-get", + [10] = "wol-ntf", + [ETHTOOL_MSG_FEATURES_GET] = "features-get", + [ETHTOOL_MSG_FEATURES_SET] = "features-set", + [13] = "features-ntf", + [14] = "privflags-get", + [15] = "privflags-ntf", + [16] = "rings-get", + [17] = "rings-ntf", + [18] = "channels-get", + [19] = "channels-ntf", + [20] = "coalesce-get", + [21] = "coalesce-ntf", + [22] = "pause-get", + [23] = "pause-ntf", + [24] = "eee-get", + [25] = "eee-ntf", + [26] = "tsinfo-get", + [27] = "cable-test-ntf", + [28] = "cable-test-tdr-ntf", + [29] = "tunnel-info-get", + [30] = "fec-get", + [31] = "fec-ntf", + [32] = "module-eeprom-get", + [34] = "phc-vclocks-get", + [35] = "module-get", + [36] = "module-ntf", + [37] = "pse-get", + [ETHTOOL_MSG_RSS_GET] = "rss-get", + [ETHTOOL_MSG_PLCA_GET_CFG] = "plca-get-cfg", + [40] = "plca-get-status", + [41] = "plca-ntf", + [ETHTOOL_MSG_MM_GET] = "mm-get", + [43] = "mm-ntf", +}; + +const char *ethtool_op_str(int op) +{ + if (op < 0 || op >= (int)MNL_ARRAY_SIZE(ethtool_op_strmap)) + return NULL; + return ethtool_op_strmap[op]; +} + +static const char * const ethtool_udp_tunnel_type_strmap[] = { + [0] = "vxlan", + [1] = "geneve", + [2] = "vxlan-gpe", +}; + +const char *ethtool_udp_tunnel_type_str(int value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(ethtool_udp_tunnel_type_strmap)) + return NULL; + return ethtool_udp_tunnel_type_strmap[value]; +} + +static const char * const ethtool_stringset_strmap[] = { +}; + +const char *ethtool_stringset_str(enum ethtool_stringset value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(ethtool_stringset_strmap)) + return NULL; + return ethtool_stringset_strmap[value]; +} + +/* Policies */ +struct ynl_policy_attr ethtool_header_policy[ETHTOOL_A_HEADER_MAX + 1] = { + [ETHTOOL_A_HEADER_DEV_INDEX] = { .name = "dev-index", .type = YNL_PT_U32, }, + [ETHTOOL_A_HEADER_DEV_NAME] = { .name = "dev-name", .type = YNL_PT_NUL_STR, }, + [ETHTOOL_A_HEADER_FLAGS] = { .name = "flags", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest ethtool_header_nest = { + .max_attr = ETHTOOL_A_HEADER_MAX, + .table = ethtool_header_policy, +}; + +struct ynl_policy_attr ethtool_pause_stat_policy[ETHTOOL_A_PAUSE_STAT_MAX + 1] = { + [ETHTOOL_A_PAUSE_STAT_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, }, + [ETHTOOL_A_PAUSE_STAT_TX_FRAMES] = { .name = "tx-frames", .type = YNL_PT_U64, }, + [ETHTOOL_A_PAUSE_STAT_RX_FRAMES] = { .name = "rx-frames", .type = YNL_PT_U64, }, +}; + +struct ynl_policy_nest ethtool_pause_stat_nest = { + .max_attr = ETHTOOL_A_PAUSE_STAT_MAX, + .table = ethtool_pause_stat_policy, +}; + +struct ynl_policy_attr ethtool_cable_test_tdr_cfg_policy[ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX + 1] = { + [ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST] = { .name = "first", .type = YNL_PT_U32, }, + [ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST] = { .name = "last", .type = YNL_PT_U32, }, + [ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP] = { .name = "step", .type = YNL_PT_U32, }, + [ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR] = { .name = "pair", .type = YNL_PT_U8, }, +}; + +struct ynl_policy_nest ethtool_cable_test_tdr_cfg_nest = { + .max_attr = ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX, + .table = ethtool_cable_test_tdr_cfg_policy, +}; + +struct ynl_policy_attr ethtool_fec_stat_policy[ETHTOOL_A_FEC_STAT_MAX + 1] = { + [ETHTOOL_A_FEC_STAT_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, }, + [ETHTOOL_A_FEC_STAT_CORRECTED] = { .name = "corrected", .type = YNL_PT_BINARY,}, + [ETHTOOL_A_FEC_STAT_UNCORR] = { .name = "uncorr", .type = YNL_PT_BINARY,}, + [ETHTOOL_A_FEC_STAT_CORR_BITS] = { .name = "corr-bits", .type = YNL_PT_BINARY,}, +}; + +struct ynl_policy_nest ethtool_fec_stat_nest = { + .max_attr = ETHTOOL_A_FEC_STAT_MAX, + .table = ethtool_fec_stat_policy, +}; + +struct ynl_policy_attr ethtool_mm_stat_policy[ETHTOOL_A_MM_STAT_MAX + 1] = { + [ETHTOOL_A_MM_STAT_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, }, + [ETHTOOL_A_MM_STAT_REASSEMBLY_ERRORS] = { .name = "reassembly-errors", .type = YNL_PT_U64, }, + [ETHTOOL_A_MM_STAT_SMD_ERRORS] = { .name = "smd-errors", .type = YNL_PT_U64, }, + [ETHTOOL_A_MM_STAT_REASSEMBLY_OK] = { .name = "reassembly-ok", .type = YNL_PT_U64, }, + [ETHTOOL_A_MM_STAT_RX_FRAG_COUNT] = { .name = "rx-frag-count", .type = YNL_PT_U64, }, + [ETHTOOL_A_MM_STAT_TX_FRAG_COUNT] = { .name = "tx-frag-count", .type = YNL_PT_U64, }, + [ETHTOOL_A_MM_STAT_HOLD_COUNT] = { .name = "hold-count", .type = YNL_PT_U64, }, +}; + +struct ynl_policy_nest ethtool_mm_stat_nest = { + .max_attr = ETHTOOL_A_MM_STAT_MAX, + .table = ethtool_mm_stat_policy, +}; + +struct ynl_policy_attr ethtool_cable_result_policy[ETHTOOL_A_CABLE_RESULT_MAX + 1] = { + [ETHTOOL_A_CABLE_RESULT_PAIR] = { .name = "pair", .type = YNL_PT_U8, }, + [ETHTOOL_A_CABLE_RESULT_CODE] = { .name = "code", .type = YNL_PT_U8, }, +}; + +struct ynl_policy_nest ethtool_cable_result_nest = { + .max_attr = ETHTOOL_A_CABLE_RESULT_MAX, + .table = ethtool_cable_result_policy, +}; + +struct ynl_policy_attr ethtool_cable_fault_length_policy[ETHTOOL_A_CABLE_FAULT_LENGTH_MAX + 1] = { + [ETHTOOL_A_CABLE_FAULT_LENGTH_PAIR] = { .name = "pair", .type = YNL_PT_U8, }, + [ETHTOOL_A_CABLE_FAULT_LENGTH_CM] = { .name = "cm", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest ethtool_cable_fault_length_nest = { + .max_attr = ETHTOOL_A_CABLE_FAULT_LENGTH_MAX, + .table = ethtool_cable_fault_length_policy, +}; + +struct ynl_policy_attr ethtool_bitset_bit_policy[ETHTOOL_A_BITSET_BIT_MAX + 1] = { + [ETHTOOL_A_BITSET_BIT_INDEX] = { .name = "index", .type = YNL_PT_U32, }, + [ETHTOOL_A_BITSET_BIT_NAME] = { .name = "name", .type = YNL_PT_NUL_STR, }, + [ETHTOOL_A_BITSET_BIT_VALUE] = { .name = "value", .type = YNL_PT_FLAG, }, +}; + +struct ynl_policy_nest ethtool_bitset_bit_nest = { + .max_attr = ETHTOOL_A_BITSET_BIT_MAX, + .table = ethtool_bitset_bit_policy, +}; + +struct ynl_policy_attr ethtool_tunnel_udp_entry_policy[ETHTOOL_A_TUNNEL_UDP_ENTRY_MAX + 1] = { + [ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT] = { .name = "port", .type = YNL_PT_U16, }, + [ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE] = { .name = "type", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest ethtool_tunnel_udp_entry_nest = { + .max_attr = ETHTOOL_A_TUNNEL_UDP_ENTRY_MAX, + .table = ethtool_tunnel_udp_entry_policy, +}; + +struct ynl_policy_attr ethtool_string_policy[ETHTOOL_A_STRING_MAX + 1] = { + [ETHTOOL_A_STRING_INDEX] = { .name = "index", .type = YNL_PT_U32, }, + [ETHTOOL_A_STRING_VALUE] = { .name = "value", .type = YNL_PT_NUL_STR, }, +}; + +struct ynl_policy_nest ethtool_string_nest = { + .max_attr = ETHTOOL_A_STRING_MAX, + .table = ethtool_string_policy, +}; + +struct ynl_policy_attr ethtool_cable_nest_policy[ETHTOOL_A_CABLE_NEST_MAX + 1] = { + [ETHTOOL_A_CABLE_NEST_RESULT] = { .name = "result", .type = YNL_PT_NEST, .nest = ðtool_cable_result_nest, }, + [ETHTOOL_A_CABLE_NEST_FAULT_LENGTH] = { .name = "fault-length", .type = YNL_PT_NEST, .nest = ðtool_cable_fault_length_nest, }, +}; + +struct ynl_policy_nest ethtool_cable_nest_nest = { + .max_attr = ETHTOOL_A_CABLE_NEST_MAX, + .table = ethtool_cable_nest_policy, +}; + +struct ynl_policy_attr ethtool_bitset_bits_policy[ETHTOOL_A_BITSET_BITS_MAX + 1] = { + [ETHTOOL_A_BITSET_BITS_BIT] = { .name = "bit", .type = YNL_PT_NEST, .nest = ðtool_bitset_bit_nest, }, +}; + +struct ynl_policy_nest ethtool_bitset_bits_nest = { + .max_attr = ETHTOOL_A_BITSET_BITS_MAX, + .table = ethtool_bitset_bits_policy, +}; + +struct ynl_policy_attr ethtool_strings_policy[ETHTOOL_A_STRINGS_MAX + 1] = { + [ETHTOOL_A_STRINGS_STRING] = { .name = "string", .type = YNL_PT_NEST, .nest = ðtool_string_nest, }, +}; + +struct ynl_policy_nest ethtool_strings_nest = { + .max_attr = ETHTOOL_A_STRINGS_MAX, + .table = ethtool_strings_policy, +}; + +struct ynl_policy_attr ethtool_bitset_policy[ETHTOOL_A_BITSET_MAX + 1] = { + [ETHTOOL_A_BITSET_NOMASK] = { .name = "nomask", .type = YNL_PT_FLAG, }, + [ETHTOOL_A_BITSET_SIZE] = { .name = "size", .type = YNL_PT_U32, }, + [ETHTOOL_A_BITSET_BITS] = { .name = "bits", .type = YNL_PT_NEST, .nest = ðtool_bitset_bits_nest, }, +}; + +struct ynl_policy_nest ethtool_bitset_nest = { + .max_attr = ETHTOOL_A_BITSET_MAX, + .table = ethtool_bitset_policy, +}; + +struct ynl_policy_attr ethtool_stringset_policy[ETHTOOL_A_STRINGSET_MAX + 1] = { + [ETHTOOL_A_STRINGSET_ID] = { .name = "id", .type = YNL_PT_U32, }, + [ETHTOOL_A_STRINGSET_COUNT] = { .name = "count", .type = YNL_PT_U32, }, + [ETHTOOL_A_STRINGSET_STRINGS] = { .name = "strings", .type = YNL_PT_NEST, .nest = ðtool_strings_nest, }, +}; + +struct ynl_policy_nest ethtool_stringset_nest = { + .max_attr = ETHTOOL_A_STRINGSET_MAX, + .table = ethtool_stringset_policy, +}; + +struct ynl_policy_attr ethtool_tunnel_udp_table_policy[ETHTOOL_A_TUNNEL_UDP_TABLE_MAX + 1] = { + [ETHTOOL_A_TUNNEL_UDP_TABLE_SIZE] = { .name = "size", .type = YNL_PT_U32, }, + [ETHTOOL_A_TUNNEL_UDP_TABLE_TYPES] = { .name = "types", .type = YNL_PT_NEST, .nest = ðtool_bitset_nest, }, + [ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY] = { .name = "entry", .type = YNL_PT_NEST, .nest = ðtool_tunnel_udp_entry_nest, }, +}; + +struct ynl_policy_nest ethtool_tunnel_udp_table_nest = { + .max_attr = ETHTOOL_A_TUNNEL_UDP_TABLE_MAX, + .table = ethtool_tunnel_udp_table_policy, +}; + +struct ynl_policy_attr ethtool_stringsets_policy[ETHTOOL_A_STRINGSETS_MAX + 1] = { + [ETHTOOL_A_STRINGSETS_STRINGSET] = { .name = "stringset", .type = YNL_PT_NEST, .nest = ðtool_stringset_nest, }, +}; + +struct ynl_policy_nest ethtool_stringsets_nest = { + .max_attr = ETHTOOL_A_STRINGSETS_MAX, + .table = ethtool_stringsets_policy, +}; + +struct ynl_policy_attr ethtool_tunnel_udp_policy[ETHTOOL_A_TUNNEL_UDP_MAX + 1] = { + [ETHTOOL_A_TUNNEL_UDP_TABLE] = { .name = "table", .type = YNL_PT_NEST, .nest = ðtool_tunnel_udp_table_nest, }, +}; + +struct ynl_policy_nest ethtool_tunnel_udp_nest = { + .max_attr = ETHTOOL_A_TUNNEL_UDP_MAX, + .table = ethtool_tunnel_udp_policy, +}; + +struct ynl_policy_attr ethtool_strset_policy[ETHTOOL_A_STRSET_MAX + 1] = { + [ETHTOOL_A_STRSET_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_STRSET_STRINGSETS] = { .name = "stringsets", .type = YNL_PT_NEST, .nest = ðtool_stringsets_nest, }, + [ETHTOOL_A_STRSET_COUNTS_ONLY] = { .name = "counts-only", .type = YNL_PT_FLAG, }, +}; + +struct ynl_policy_nest ethtool_strset_nest = { + .max_attr = ETHTOOL_A_STRSET_MAX, + .table = ethtool_strset_policy, +}; + +struct ynl_policy_attr ethtool_linkinfo_policy[ETHTOOL_A_LINKINFO_MAX + 1] = { + [ETHTOOL_A_LINKINFO_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_LINKINFO_PORT] = { .name = "port", .type = YNL_PT_U8, }, + [ETHTOOL_A_LINKINFO_PHYADDR] = { .name = "phyaddr", .type = YNL_PT_U8, }, + [ETHTOOL_A_LINKINFO_TP_MDIX] = { .name = "tp-mdix", .type = YNL_PT_U8, }, + [ETHTOOL_A_LINKINFO_TP_MDIX_CTRL] = { .name = "tp-mdix-ctrl", .type = YNL_PT_U8, }, + [ETHTOOL_A_LINKINFO_TRANSCEIVER] = { .name = "transceiver", .type = YNL_PT_U8, }, +}; + +struct ynl_policy_nest ethtool_linkinfo_nest = { + .max_attr = ETHTOOL_A_LINKINFO_MAX, + .table = ethtool_linkinfo_policy, +}; + +struct ynl_policy_attr ethtool_linkmodes_policy[ETHTOOL_A_LINKMODES_MAX + 1] = { + [ETHTOOL_A_LINKMODES_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_LINKMODES_AUTONEG] = { .name = "autoneg", .type = YNL_PT_U8, }, + [ETHTOOL_A_LINKMODES_OURS] = { .name = "ours", .type = YNL_PT_NEST, .nest = ðtool_bitset_nest, }, + [ETHTOOL_A_LINKMODES_PEER] = { .name = "peer", .type = YNL_PT_NEST, .nest = ðtool_bitset_nest, }, + [ETHTOOL_A_LINKMODES_SPEED] = { .name = "speed", .type = YNL_PT_U32, }, + [ETHTOOL_A_LINKMODES_DUPLEX] = { .name = "duplex", .type = YNL_PT_U8, }, + [ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG] = { .name = "master-slave-cfg", .type = YNL_PT_U8, }, + [ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE] = { .name = "master-slave-state", .type = YNL_PT_U8, }, + [ETHTOOL_A_LINKMODES_LANES] = { .name = "lanes", .type = YNL_PT_U32, }, + [ETHTOOL_A_LINKMODES_RATE_MATCHING] = { .name = "rate-matching", .type = YNL_PT_U8, }, +}; + +struct ynl_policy_nest ethtool_linkmodes_nest = { + .max_attr = ETHTOOL_A_LINKMODES_MAX, + .table = ethtool_linkmodes_policy, +}; + +struct ynl_policy_attr ethtool_linkstate_policy[ETHTOOL_A_LINKSTATE_MAX + 1] = { + [ETHTOOL_A_LINKSTATE_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_LINKSTATE_LINK] = { .name = "link", .type = YNL_PT_U8, }, + [ETHTOOL_A_LINKSTATE_SQI] = { .name = "sqi", .type = YNL_PT_U32, }, + [ETHTOOL_A_LINKSTATE_SQI_MAX] = { .name = "sqi-max", .type = YNL_PT_U32, }, + [ETHTOOL_A_LINKSTATE_EXT_STATE] = { .name = "ext-state", .type = YNL_PT_U8, }, + [ETHTOOL_A_LINKSTATE_EXT_SUBSTATE] = { .name = "ext-substate", .type = YNL_PT_U8, }, + [ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT] = { .name = "ext-down-cnt", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest ethtool_linkstate_nest = { + .max_attr = ETHTOOL_A_LINKSTATE_MAX, + .table = ethtool_linkstate_policy, +}; + +struct ynl_policy_attr ethtool_debug_policy[ETHTOOL_A_DEBUG_MAX + 1] = { + [ETHTOOL_A_DEBUG_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_DEBUG_MSGMASK] = { .name = "msgmask", .type = YNL_PT_NEST, .nest = ðtool_bitset_nest, }, +}; + +struct ynl_policy_nest ethtool_debug_nest = { + .max_attr = ETHTOOL_A_DEBUG_MAX, + .table = ethtool_debug_policy, +}; + +struct ynl_policy_attr ethtool_wol_policy[ETHTOOL_A_WOL_MAX + 1] = { + [ETHTOOL_A_WOL_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_WOL_MODES] = { .name = "modes", .type = YNL_PT_NEST, .nest = ðtool_bitset_nest, }, + [ETHTOOL_A_WOL_SOPASS] = { .name = "sopass", .type = YNL_PT_BINARY,}, +}; + +struct ynl_policy_nest ethtool_wol_nest = { + .max_attr = ETHTOOL_A_WOL_MAX, + .table = ethtool_wol_policy, +}; + +struct ynl_policy_attr ethtool_features_policy[ETHTOOL_A_FEATURES_MAX + 1] = { + [ETHTOOL_A_FEATURES_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_FEATURES_HW] = { .name = "hw", .type = YNL_PT_NEST, .nest = ðtool_bitset_nest, }, + [ETHTOOL_A_FEATURES_WANTED] = { .name = "wanted", .type = YNL_PT_NEST, .nest = ðtool_bitset_nest, }, + [ETHTOOL_A_FEATURES_ACTIVE] = { .name = "active", .type = YNL_PT_NEST, .nest = ðtool_bitset_nest, }, + [ETHTOOL_A_FEATURES_NOCHANGE] = { .name = "nochange", .type = YNL_PT_NEST, .nest = ðtool_bitset_nest, }, +}; + +struct ynl_policy_nest ethtool_features_nest = { + .max_attr = ETHTOOL_A_FEATURES_MAX, + .table = ethtool_features_policy, +}; + +struct ynl_policy_attr ethtool_privflags_policy[ETHTOOL_A_PRIVFLAGS_MAX + 1] = { + [ETHTOOL_A_PRIVFLAGS_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_PRIVFLAGS_FLAGS] = { .name = "flags", .type = YNL_PT_NEST, .nest = ðtool_bitset_nest, }, +}; + +struct ynl_policy_nest ethtool_privflags_nest = { + .max_attr = ETHTOOL_A_PRIVFLAGS_MAX, + .table = ethtool_privflags_policy, +}; + +struct ynl_policy_attr ethtool_rings_policy[ETHTOOL_A_RINGS_MAX + 1] = { + [ETHTOOL_A_RINGS_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_RINGS_RX_MAX] = { .name = "rx-max", .type = YNL_PT_U32, }, + [ETHTOOL_A_RINGS_RX_MINI_MAX] = { .name = "rx-mini-max", .type = YNL_PT_U32, }, + [ETHTOOL_A_RINGS_RX_JUMBO_MAX] = { .name = "rx-jumbo-max", .type = YNL_PT_U32, }, + [ETHTOOL_A_RINGS_TX_MAX] = { .name = "tx-max", .type = YNL_PT_U32, }, + [ETHTOOL_A_RINGS_RX] = { .name = "rx", .type = YNL_PT_U32, }, + [ETHTOOL_A_RINGS_RX_MINI] = { .name = "rx-mini", .type = YNL_PT_U32, }, + [ETHTOOL_A_RINGS_RX_JUMBO] = { .name = "rx-jumbo", .type = YNL_PT_U32, }, + [ETHTOOL_A_RINGS_TX] = { .name = "tx", .type = YNL_PT_U32, }, + [ETHTOOL_A_RINGS_RX_BUF_LEN] = { .name = "rx-buf-len", .type = YNL_PT_U32, }, + [ETHTOOL_A_RINGS_TCP_DATA_SPLIT] = { .name = "tcp-data-split", .type = YNL_PT_U8, }, + [ETHTOOL_A_RINGS_CQE_SIZE] = { .name = "cqe-size", .type = YNL_PT_U32, }, + [ETHTOOL_A_RINGS_TX_PUSH] = { .name = "tx-push", .type = YNL_PT_U8, }, + [ETHTOOL_A_RINGS_RX_PUSH] = { .name = "rx-push", .type = YNL_PT_U8, }, + [ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN] = { .name = "tx-push-buf-len", .type = YNL_PT_U32, }, + [ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX] = { .name = "tx-push-buf-len-max", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest ethtool_rings_nest = { + .max_attr = ETHTOOL_A_RINGS_MAX, + .table = ethtool_rings_policy, +}; + +struct ynl_policy_attr ethtool_channels_policy[ETHTOOL_A_CHANNELS_MAX + 1] = { + [ETHTOOL_A_CHANNELS_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_CHANNELS_RX_MAX] = { .name = "rx-max", .type = YNL_PT_U32, }, + [ETHTOOL_A_CHANNELS_TX_MAX] = { .name = "tx-max", .type = YNL_PT_U32, }, + [ETHTOOL_A_CHANNELS_OTHER_MAX] = { .name = "other-max", .type = YNL_PT_U32, }, + [ETHTOOL_A_CHANNELS_COMBINED_MAX] = { .name = "combined-max", .type = YNL_PT_U32, }, + [ETHTOOL_A_CHANNELS_RX_COUNT] = { .name = "rx-count", .type = YNL_PT_U32, }, + [ETHTOOL_A_CHANNELS_TX_COUNT] = { .name = "tx-count", .type = YNL_PT_U32, }, + [ETHTOOL_A_CHANNELS_OTHER_COUNT] = { .name = "other-count", .type = YNL_PT_U32, }, + [ETHTOOL_A_CHANNELS_COMBINED_COUNT] = { .name = "combined-count", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest ethtool_channels_nest = { + .max_attr = ETHTOOL_A_CHANNELS_MAX, + .table = ethtool_channels_policy, +}; + +struct ynl_policy_attr ethtool_coalesce_policy[ETHTOOL_A_COALESCE_MAX + 1] = { + [ETHTOOL_A_COALESCE_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_COALESCE_RX_USECS] = { .name = "rx-usecs", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_RX_MAX_FRAMES] = { .name = "rx-max-frames", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_RX_USECS_IRQ] = { .name = "rx-usecs-irq", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ] = { .name = "rx-max-frames-irq", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_TX_USECS] = { .name = "tx-usecs", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_TX_MAX_FRAMES] = { .name = "tx-max-frames", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_TX_USECS_IRQ] = { .name = "tx-usecs-irq", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ] = { .name = "tx-max-frames-irq", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_STATS_BLOCK_USECS] = { .name = "stats-block-usecs", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX] = { .name = "use-adaptive-rx", .type = YNL_PT_U8, }, + [ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX] = { .name = "use-adaptive-tx", .type = YNL_PT_U8, }, + [ETHTOOL_A_COALESCE_PKT_RATE_LOW] = { .name = "pkt-rate-low", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_RX_USECS_LOW] = { .name = "rx-usecs-low", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW] = { .name = "rx-max-frames-low", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_TX_USECS_LOW] = { .name = "tx-usecs-low", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW] = { .name = "tx-max-frames-low", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_PKT_RATE_HIGH] = { .name = "pkt-rate-high", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_RX_USECS_HIGH] = { .name = "rx-usecs-high", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH] = { .name = "rx-max-frames-high", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_TX_USECS_HIGH] = { .name = "tx-usecs-high", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH] = { .name = "tx-max-frames-high", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL] = { .name = "rate-sample-interval", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_USE_CQE_MODE_TX] = { .name = "use-cqe-mode-tx", .type = YNL_PT_U8, }, + [ETHTOOL_A_COALESCE_USE_CQE_MODE_RX] = { .name = "use-cqe-mode-rx", .type = YNL_PT_U8, }, + [ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES] = { .name = "tx-aggr-max-bytes", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES] = { .name = "tx-aggr-max-frames", .type = YNL_PT_U32, }, + [ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS] = { .name = "tx-aggr-time-usecs", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest ethtool_coalesce_nest = { + .max_attr = ETHTOOL_A_COALESCE_MAX, + .table = ethtool_coalesce_policy, +}; + +struct ynl_policy_attr ethtool_pause_policy[ETHTOOL_A_PAUSE_MAX + 1] = { + [ETHTOOL_A_PAUSE_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_PAUSE_AUTONEG] = { .name = "autoneg", .type = YNL_PT_U8, }, + [ETHTOOL_A_PAUSE_RX] = { .name = "rx", .type = YNL_PT_U8, }, + [ETHTOOL_A_PAUSE_TX] = { .name = "tx", .type = YNL_PT_U8, }, + [ETHTOOL_A_PAUSE_STATS] = { .name = "stats", .type = YNL_PT_NEST, .nest = ðtool_pause_stat_nest, }, + [ETHTOOL_A_PAUSE_STATS_SRC] = { .name = "stats-src", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest ethtool_pause_nest = { + .max_attr = ETHTOOL_A_PAUSE_MAX, + .table = ethtool_pause_policy, +}; + +struct ynl_policy_attr ethtool_eee_policy[ETHTOOL_A_EEE_MAX + 1] = { + [ETHTOOL_A_EEE_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_EEE_MODES_OURS] = { .name = "modes-ours", .type = YNL_PT_NEST, .nest = ðtool_bitset_nest, }, + [ETHTOOL_A_EEE_MODES_PEER] = { .name = "modes-peer", .type = YNL_PT_NEST, .nest = ðtool_bitset_nest, }, + [ETHTOOL_A_EEE_ACTIVE] = { .name = "active", .type = YNL_PT_U8, }, + [ETHTOOL_A_EEE_ENABLED] = { .name = "enabled", .type = YNL_PT_U8, }, + [ETHTOOL_A_EEE_TX_LPI_ENABLED] = { .name = "tx-lpi-enabled", .type = YNL_PT_U8, }, + [ETHTOOL_A_EEE_TX_LPI_TIMER] = { .name = "tx-lpi-timer", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest ethtool_eee_nest = { + .max_attr = ETHTOOL_A_EEE_MAX, + .table = ethtool_eee_policy, +}; + +struct ynl_policy_attr ethtool_tsinfo_policy[ETHTOOL_A_TSINFO_MAX + 1] = { + [ETHTOOL_A_TSINFO_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_TSINFO_TIMESTAMPING] = { .name = "timestamping", .type = YNL_PT_NEST, .nest = ðtool_bitset_nest, }, + [ETHTOOL_A_TSINFO_TX_TYPES] = { .name = "tx-types", .type = YNL_PT_NEST, .nest = ðtool_bitset_nest, }, + [ETHTOOL_A_TSINFO_RX_FILTERS] = { .name = "rx-filters", .type = YNL_PT_NEST, .nest = ðtool_bitset_nest, }, + [ETHTOOL_A_TSINFO_PHC_INDEX] = { .name = "phc-index", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest ethtool_tsinfo_nest = { + .max_attr = ETHTOOL_A_TSINFO_MAX, + .table = ethtool_tsinfo_policy, +}; + +struct ynl_policy_attr ethtool_cable_test_policy[ETHTOOL_A_CABLE_TEST_MAX + 1] = { + [ETHTOOL_A_CABLE_TEST_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, +}; + +struct ynl_policy_nest ethtool_cable_test_nest = { + .max_attr = ETHTOOL_A_CABLE_TEST_MAX, + .table = ethtool_cable_test_policy, +}; + +struct ynl_policy_attr ethtool_cable_test_ntf_policy[ETHTOOL_A_CABLE_TEST_NTF_MAX + 1] = { + [ETHTOOL_A_CABLE_TEST_NTF_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_CABLE_TEST_NTF_STATUS] = { .name = "status", .type = YNL_PT_U8, }, + [ETHTOOL_A_CABLE_TEST_NTF_NEST] = { .name = "nest", .type = YNL_PT_NEST, .nest = ðtool_cable_nest_nest, }, +}; + +struct ynl_policy_nest ethtool_cable_test_ntf_nest = { + .max_attr = ETHTOOL_A_CABLE_TEST_NTF_MAX, + .table = ethtool_cable_test_ntf_policy, +}; + +struct ynl_policy_attr ethtool_cable_test_tdr_policy[ETHTOOL_A_CABLE_TEST_TDR_MAX + 1] = { + [ETHTOOL_A_CABLE_TEST_TDR_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_CABLE_TEST_TDR_CFG] = { .name = "cfg", .type = YNL_PT_NEST, .nest = ðtool_cable_test_tdr_cfg_nest, }, +}; + +struct ynl_policy_nest ethtool_cable_test_tdr_nest = { + .max_attr = ETHTOOL_A_CABLE_TEST_TDR_MAX, + .table = ethtool_cable_test_tdr_policy, +}; + +struct ynl_policy_attr ethtool_cable_test_tdr_ntf_policy[ETHTOOL_A_CABLE_TEST_TDR_NTF_MAX + 1] = { + [ETHTOOL_A_CABLE_TEST_TDR_NTF_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_CABLE_TEST_TDR_NTF_STATUS] = { .name = "status", .type = YNL_PT_U8, }, + [ETHTOOL_A_CABLE_TEST_TDR_NTF_NEST] = { .name = "nest", .type = YNL_PT_NEST, .nest = ðtool_cable_nest_nest, }, +}; + +struct ynl_policy_nest ethtool_cable_test_tdr_ntf_nest = { + .max_attr = ETHTOOL_A_CABLE_TEST_TDR_NTF_MAX, + .table = ethtool_cable_test_tdr_ntf_policy, +}; + +struct ynl_policy_attr ethtool_tunnel_info_policy[ETHTOOL_A_TUNNEL_INFO_MAX + 1] = { + [ETHTOOL_A_TUNNEL_INFO_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_TUNNEL_INFO_UDP_PORTS] = { .name = "udp-ports", .type = YNL_PT_NEST, .nest = ðtool_tunnel_udp_nest, }, +}; + +struct ynl_policy_nest ethtool_tunnel_info_nest = { + .max_attr = ETHTOOL_A_TUNNEL_INFO_MAX, + .table = ethtool_tunnel_info_policy, +}; + +struct ynl_policy_attr ethtool_fec_policy[ETHTOOL_A_FEC_MAX + 1] = { + [ETHTOOL_A_FEC_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_FEC_MODES] = { .name = "modes", .type = YNL_PT_NEST, .nest = ðtool_bitset_nest, }, + [ETHTOOL_A_FEC_AUTO] = { .name = "auto", .type = YNL_PT_U8, }, + [ETHTOOL_A_FEC_ACTIVE] = { .name = "active", .type = YNL_PT_U32, }, + [ETHTOOL_A_FEC_STATS] = { .name = "stats", .type = YNL_PT_NEST, .nest = ðtool_fec_stat_nest, }, +}; + +struct ynl_policy_nest ethtool_fec_nest = { + .max_attr = ETHTOOL_A_FEC_MAX, + .table = ethtool_fec_policy, +}; + +struct ynl_policy_attr ethtool_module_eeprom_policy[ETHTOOL_A_MODULE_EEPROM_MAX + 1] = { + [ETHTOOL_A_MODULE_EEPROM_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_MODULE_EEPROM_OFFSET] = { .name = "offset", .type = YNL_PT_U32, }, + [ETHTOOL_A_MODULE_EEPROM_LENGTH] = { .name = "length", .type = YNL_PT_U32, }, + [ETHTOOL_A_MODULE_EEPROM_PAGE] = { .name = "page", .type = YNL_PT_U8, }, + [ETHTOOL_A_MODULE_EEPROM_BANK] = { .name = "bank", .type = YNL_PT_U8, }, + [ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS] = { .name = "i2c-address", .type = YNL_PT_U8, }, + [ETHTOOL_A_MODULE_EEPROM_DATA] = { .name = "data", .type = YNL_PT_BINARY,}, +}; + +struct ynl_policy_nest ethtool_module_eeprom_nest = { + .max_attr = ETHTOOL_A_MODULE_EEPROM_MAX, + .table = ethtool_module_eeprom_policy, +}; + +struct ynl_policy_attr ethtool_phc_vclocks_policy[ETHTOOL_A_PHC_VCLOCKS_MAX + 1] = { + [ETHTOOL_A_PHC_VCLOCKS_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_PHC_VCLOCKS_NUM] = { .name = "num", .type = YNL_PT_U32, }, + [ETHTOOL_A_PHC_VCLOCKS_INDEX] = { .name = "index", .type = YNL_PT_BINARY,}, +}; + +struct ynl_policy_nest ethtool_phc_vclocks_nest = { + .max_attr = ETHTOOL_A_PHC_VCLOCKS_MAX, + .table = ethtool_phc_vclocks_policy, +}; + +struct ynl_policy_attr ethtool_module_policy[ETHTOOL_A_MODULE_MAX + 1] = { + [ETHTOOL_A_MODULE_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_MODULE_POWER_MODE_POLICY] = { .name = "power-mode-policy", .type = YNL_PT_U8, }, + [ETHTOOL_A_MODULE_POWER_MODE] = { .name = "power-mode", .type = YNL_PT_U8, }, +}; + +struct ynl_policy_nest ethtool_module_nest = { + .max_attr = ETHTOOL_A_MODULE_MAX, + .table = ethtool_module_policy, +}; + +struct ynl_policy_attr ethtool_pse_policy[ETHTOOL_A_PSE_MAX + 1] = { + [ETHTOOL_A_PSE_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_PODL_PSE_ADMIN_STATE] = { .name = "admin-state", .type = YNL_PT_U32, }, + [ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] = { .name = "admin-control", .type = YNL_PT_U32, }, + [ETHTOOL_A_PODL_PSE_PW_D_STATUS] = { .name = "pw-d-status", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest ethtool_pse_nest = { + .max_attr = ETHTOOL_A_PSE_MAX, + .table = ethtool_pse_policy, +}; + +struct ynl_policy_attr ethtool_rss_policy[ETHTOOL_A_RSS_MAX + 1] = { + [ETHTOOL_A_RSS_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_RSS_CONTEXT] = { .name = "context", .type = YNL_PT_U32, }, + [ETHTOOL_A_RSS_HFUNC] = { .name = "hfunc", .type = YNL_PT_U32, }, + [ETHTOOL_A_RSS_INDIR] = { .name = "indir", .type = YNL_PT_BINARY,}, + [ETHTOOL_A_RSS_HKEY] = { .name = "hkey", .type = YNL_PT_BINARY,}, +}; + +struct ynl_policy_nest ethtool_rss_nest = { + .max_attr = ETHTOOL_A_RSS_MAX, + .table = ethtool_rss_policy, +}; + +struct ynl_policy_attr ethtool_plca_policy[ETHTOOL_A_PLCA_MAX + 1] = { + [ETHTOOL_A_PLCA_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_PLCA_VERSION] = { .name = "version", .type = YNL_PT_U16, }, + [ETHTOOL_A_PLCA_ENABLED] = { .name = "enabled", .type = YNL_PT_U8, }, + [ETHTOOL_A_PLCA_STATUS] = { .name = "status", .type = YNL_PT_U8, }, + [ETHTOOL_A_PLCA_NODE_CNT] = { .name = "node-cnt", .type = YNL_PT_U32, }, + [ETHTOOL_A_PLCA_NODE_ID] = { .name = "node-id", .type = YNL_PT_U32, }, + [ETHTOOL_A_PLCA_TO_TMR] = { .name = "to-tmr", .type = YNL_PT_U32, }, + [ETHTOOL_A_PLCA_BURST_CNT] = { .name = "burst-cnt", .type = YNL_PT_U32, }, + [ETHTOOL_A_PLCA_BURST_TMR] = { .name = "burst-tmr", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest ethtool_plca_nest = { + .max_attr = ETHTOOL_A_PLCA_MAX, + .table = ethtool_plca_policy, +}; + +struct ynl_policy_attr ethtool_mm_policy[ETHTOOL_A_MM_MAX + 1] = { + [ETHTOOL_A_MM_HEADER] = { .name = "header", .type = YNL_PT_NEST, .nest = ðtool_header_nest, }, + [ETHTOOL_A_MM_PMAC_ENABLED] = { .name = "pmac-enabled", .type = YNL_PT_U8, }, + [ETHTOOL_A_MM_TX_ENABLED] = { .name = "tx-enabled", .type = YNL_PT_U8, }, + [ETHTOOL_A_MM_TX_ACTIVE] = { .name = "tx-active", .type = YNL_PT_U8, }, + [ETHTOOL_A_MM_TX_MIN_FRAG_SIZE] = { .name = "tx-min-frag-size", .type = YNL_PT_U32, }, + [ETHTOOL_A_MM_RX_MIN_FRAG_SIZE] = { .name = "rx-min-frag-size", .type = YNL_PT_U32, }, + [ETHTOOL_A_MM_VERIFY_ENABLED] = { .name = "verify-enabled", .type = YNL_PT_U8, }, + [ETHTOOL_A_MM_VERIFY_STATUS] = { .name = "verify-status", .type = YNL_PT_U8, }, + [ETHTOOL_A_MM_VERIFY_TIME] = { .name = "verify-time", .type = YNL_PT_U32, }, + [ETHTOOL_A_MM_MAX_VERIFY_TIME] = { .name = "max-verify-time", .type = YNL_PT_U32, }, + [ETHTOOL_A_MM_STATS] = { .name = "stats", .type = YNL_PT_NEST, .nest = ðtool_mm_stat_nest, }, +}; + +struct ynl_policy_nest ethtool_mm_nest = { + .max_attr = ETHTOOL_A_MM_MAX, + .table = ethtool_mm_policy, +}; + +/* Common nested types */ +void ethtool_header_free(struct ethtool_header *obj) +{ + free(obj->dev_name); +} + +int ethtool_header_put(struct nlmsghdr *nlh, unsigned int attr_type, + struct ethtool_header *obj) +{ + struct nlattr *nest; + + nest = mnl_attr_nest_start(nlh, attr_type); + if (obj->_present.dev_index) + mnl_attr_put_u32(nlh, ETHTOOL_A_HEADER_DEV_INDEX, obj->dev_index); + if (obj->_present.dev_name_len) + mnl_attr_put_strz(nlh, ETHTOOL_A_HEADER_DEV_NAME, obj->dev_name); + if (obj->_present.flags) + mnl_attr_put_u32(nlh, ETHTOOL_A_HEADER_FLAGS, obj->flags); + mnl_attr_nest_end(nlh, nest); + + return 0; +} + +int ethtool_header_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_header *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_HEADER_DEV_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dev_index = 1; + dst->dev_index = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_HEADER_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == ETHTOOL_A_HEADER_FLAGS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.flags = 1; + dst->flags = mnl_attr_get_u32(attr); + } + } + + return 0; +} + +void ethtool_pause_stat_free(struct ethtool_pause_stat *obj) +{ +} + +int ethtool_pause_stat_put(struct nlmsghdr *nlh, unsigned int attr_type, + struct ethtool_pause_stat *obj) +{ + struct nlattr *nest; + + nest = mnl_attr_nest_start(nlh, attr_type); + if (obj->_present.tx_frames) + mnl_attr_put_u64(nlh, ETHTOOL_A_PAUSE_STAT_TX_FRAMES, obj->tx_frames); + if (obj->_present.rx_frames) + mnl_attr_put_u64(nlh, ETHTOOL_A_PAUSE_STAT_RX_FRAMES, obj->rx_frames); + mnl_attr_nest_end(nlh, nest); + + return 0; +} + +int ethtool_pause_stat_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_pause_stat *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_PAUSE_STAT_TX_FRAMES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_frames = 1; + dst->tx_frames = mnl_attr_get_u64(attr); + } else if (type == ETHTOOL_A_PAUSE_STAT_RX_FRAMES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_frames = 1; + dst->rx_frames = mnl_attr_get_u64(attr); + } + } + + return 0; +} + +void ethtool_cable_test_tdr_cfg_free(struct ethtool_cable_test_tdr_cfg *obj) +{ +} + +void ethtool_fec_stat_free(struct ethtool_fec_stat *obj) +{ + free(obj->corrected); + free(obj->uncorr); + free(obj->corr_bits); +} + +int ethtool_fec_stat_put(struct nlmsghdr *nlh, unsigned int attr_type, + struct ethtool_fec_stat *obj) +{ + struct nlattr *nest; + + nest = mnl_attr_nest_start(nlh, attr_type); + if (obj->_present.corrected_len) + mnl_attr_put(nlh, ETHTOOL_A_FEC_STAT_CORRECTED, obj->_present.corrected_len, obj->corrected); + if (obj->_present.uncorr_len) + mnl_attr_put(nlh, ETHTOOL_A_FEC_STAT_UNCORR, obj->_present.uncorr_len, obj->uncorr); + if (obj->_present.corr_bits_len) + mnl_attr_put(nlh, ETHTOOL_A_FEC_STAT_CORR_BITS, obj->_present.corr_bits_len, obj->corr_bits); + mnl_attr_nest_end(nlh, nest); + + return 0; +} + +int ethtool_fec_stat_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_fec_stat *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_FEC_STAT_CORRECTED) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.corrected_len = len; + dst->corrected = malloc(len); + memcpy(dst->corrected, mnl_attr_get_payload(attr), len); + } else if (type == ETHTOOL_A_FEC_STAT_UNCORR) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.uncorr_len = len; + dst->uncorr = malloc(len); + memcpy(dst->uncorr, mnl_attr_get_payload(attr), len); + } else if (type == ETHTOOL_A_FEC_STAT_CORR_BITS) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.corr_bits_len = len; + dst->corr_bits = malloc(len); + memcpy(dst->corr_bits, mnl_attr_get_payload(attr), len); + } + } + + return 0; +} + +void ethtool_mm_stat_free(struct ethtool_mm_stat *obj) +{ +} + +int ethtool_mm_stat_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_mm_stat *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_MM_STAT_REASSEMBLY_ERRORS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.reassembly_errors = 1; + dst->reassembly_errors = mnl_attr_get_u64(attr); + } else if (type == ETHTOOL_A_MM_STAT_SMD_ERRORS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.smd_errors = 1; + dst->smd_errors = mnl_attr_get_u64(attr); + } else if (type == ETHTOOL_A_MM_STAT_REASSEMBLY_OK) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.reassembly_ok = 1; + dst->reassembly_ok = mnl_attr_get_u64(attr); + } else if (type == ETHTOOL_A_MM_STAT_RX_FRAG_COUNT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_frag_count = 1; + dst->rx_frag_count = mnl_attr_get_u64(attr); + } else if (type == ETHTOOL_A_MM_STAT_TX_FRAG_COUNT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_frag_count = 1; + dst->tx_frag_count = mnl_attr_get_u64(attr); + } else if (type == ETHTOOL_A_MM_STAT_HOLD_COUNT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.hold_count = 1; + dst->hold_count = mnl_attr_get_u64(attr); + } + } + + return 0; +} + +void ethtool_cable_result_free(struct ethtool_cable_result *obj) +{ +} + +int ethtool_cable_result_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_cable_result *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_CABLE_RESULT_PAIR) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.pair = 1; + dst->pair = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_CABLE_RESULT_CODE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.code = 1; + dst->code = mnl_attr_get_u8(attr); + } + } + + return 0; +} + +void ethtool_cable_fault_length_free(struct ethtool_cable_fault_length *obj) +{ +} + +int ethtool_cable_fault_length_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_cable_fault_length *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_CABLE_FAULT_LENGTH_PAIR) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.pair = 1; + dst->pair = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_CABLE_FAULT_LENGTH_CM) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.cm = 1; + dst->cm = mnl_attr_get_u32(attr); + } + } + + return 0; +} + +void ethtool_bitset_bit_free(struct ethtool_bitset_bit *obj) +{ + free(obj->name); +} + +int ethtool_bitset_bit_put(struct nlmsghdr *nlh, unsigned int attr_type, + struct ethtool_bitset_bit *obj) +{ + struct nlattr *nest; + + nest = mnl_attr_nest_start(nlh, attr_type); + if (obj->_present.index) + mnl_attr_put_u32(nlh, ETHTOOL_A_BITSET_BIT_INDEX, obj->index); + if (obj->_present.name_len) + mnl_attr_put_strz(nlh, ETHTOOL_A_BITSET_BIT_NAME, obj->name); + if (obj->_present.value) + mnl_attr_put(nlh, ETHTOOL_A_BITSET_BIT_VALUE, 0, NULL); + mnl_attr_nest_end(nlh, nest); + + return 0; +} + +int ethtool_bitset_bit_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_bitset_bit *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_BITSET_BIT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.index = 1; + dst->index = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_BITSET_BIT_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.name_len = len; + dst->name = malloc(len + 1); + memcpy(dst->name, mnl_attr_get_str(attr), len); + dst->name[len] = 0; + } else if (type == ETHTOOL_A_BITSET_BIT_VALUE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.value = 1; + } + } + + return 0; +} + +void ethtool_tunnel_udp_entry_free(struct ethtool_tunnel_udp_entry *obj) +{ +} + +int ethtool_tunnel_udp_entry_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_tunnel_udp_entry *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port = 1; + dst->port = mnl_attr_get_u16(attr); + } else if (type == ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.type = 1; + dst->type = mnl_attr_get_u32(attr); + } + } + + return 0; +} + +void ethtool_string_free(struct ethtool_string *obj) +{ + free(obj->value); +} + +int ethtool_string_put(struct nlmsghdr *nlh, unsigned int attr_type, + struct ethtool_string *obj) +{ + struct nlattr *nest; + + nest = mnl_attr_nest_start(nlh, attr_type); + if (obj->_present.index) + mnl_attr_put_u32(nlh, ETHTOOL_A_STRING_INDEX, obj->index); + if (obj->_present.value_len) + mnl_attr_put_strz(nlh, ETHTOOL_A_STRING_VALUE, obj->value); + mnl_attr_nest_end(nlh, nest); + + return 0; +} + +int ethtool_string_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_string *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_STRING_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.index = 1; + dst->index = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_STRING_VALUE) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.value_len = len; + dst->value = malloc(len + 1); + memcpy(dst->value, mnl_attr_get_str(attr), len); + dst->value[len] = 0; + } + } + + return 0; +} + +void ethtool_cable_nest_free(struct ethtool_cable_nest *obj) +{ + ethtool_cable_result_free(&obj->result); + ethtool_cable_fault_length_free(&obj->fault_length); +} + +int ethtool_cable_nest_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_cable_nest *dst = yarg->data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + parg.ys = yarg->ys; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_CABLE_NEST_RESULT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.result = 1; + + parg.rsp_policy = ðtool_cable_result_nest; + parg.data = &dst->result; + if (ethtool_cable_result_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_CABLE_NEST_FAULT_LENGTH) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.fault_length = 1; + + parg.rsp_policy = ðtool_cable_fault_length_nest; + parg.data = &dst->fault_length; + if (ethtool_cable_fault_length_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return 0; +} + +void ethtool_bitset_bits_free(struct ethtool_bitset_bits *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_bit; i++) + ethtool_bitset_bit_free(&obj->bit[i]); + free(obj->bit); +} + +int ethtool_bitset_bits_put(struct nlmsghdr *nlh, unsigned int attr_type, + struct ethtool_bitset_bits *obj) +{ + struct nlattr *nest; + + nest = mnl_attr_nest_start(nlh, attr_type); + for (unsigned int i = 0; i < obj->n_bit; i++) + ethtool_bitset_bit_put(nlh, ETHTOOL_A_BITSET_BITS_BIT, &obj->bit[i]); + mnl_attr_nest_end(nlh, nest); + + return 0; +} + +int ethtool_bitset_bits_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_bitset_bits *dst = yarg->data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + unsigned int n_bit = 0; + int i; + + parg.ys = yarg->ys; + + if (dst->bit) + return ynl_error_parse(yarg, "attribute already present (bitset-bits.bit)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_BITSET_BITS_BIT) { + n_bit++; + } + } + + if (n_bit) { + dst->bit = calloc(n_bit, sizeof(*dst->bit)); + dst->n_bit = n_bit; + i = 0; + parg.rsp_policy = ðtool_bitset_bit_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == ETHTOOL_A_BITSET_BITS_BIT) { + parg.data = &dst->bit[i]; + if (ethtool_bitset_bit_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void ethtool_strings_free(struct ethtool_strings *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_string; i++) + ethtool_string_free(&obj->string[i]); + free(obj->string); +} + +int ethtool_strings_put(struct nlmsghdr *nlh, unsigned int attr_type, + struct ethtool_strings *obj) +{ + struct nlattr *nest; + + nest = mnl_attr_nest_start(nlh, attr_type); + for (unsigned int i = 0; i < obj->n_string; i++) + ethtool_string_put(nlh, ETHTOOL_A_STRINGS_STRING, &obj->string[i]); + mnl_attr_nest_end(nlh, nest); + + return 0; +} + +int ethtool_strings_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_strings *dst = yarg->data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + unsigned int n_string = 0; + int i; + + parg.ys = yarg->ys; + + if (dst->string) + return ynl_error_parse(yarg, "attribute already present (strings.string)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_STRINGS_STRING) { + n_string++; + } + } + + if (n_string) { + dst->string = calloc(n_string, sizeof(*dst->string)); + dst->n_string = n_string; + i = 0; + parg.rsp_policy = ðtool_string_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == ETHTOOL_A_STRINGS_STRING) { + parg.data = &dst->string[i]; + if (ethtool_string_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void ethtool_bitset_free(struct ethtool_bitset *obj) +{ + ethtool_bitset_bits_free(&obj->bits); +} + +int ethtool_bitset_put(struct nlmsghdr *nlh, unsigned int attr_type, + struct ethtool_bitset *obj) +{ + struct nlattr *nest; + + nest = mnl_attr_nest_start(nlh, attr_type); + if (obj->_present.nomask) + mnl_attr_put(nlh, ETHTOOL_A_BITSET_NOMASK, 0, NULL); + if (obj->_present.size) + mnl_attr_put_u32(nlh, ETHTOOL_A_BITSET_SIZE, obj->size); + if (obj->_present.bits) + ethtool_bitset_bits_put(nlh, ETHTOOL_A_BITSET_BITS, &obj->bits); + mnl_attr_nest_end(nlh, nest); + + return 0; +} + +int ethtool_bitset_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_bitset *dst = yarg->data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + parg.ys = yarg->ys; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_BITSET_NOMASK) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.nomask = 1; + } else if (type == ETHTOOL_A_BITSET_SIZE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.size = 1; + dst->size = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_BITSET_BITS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.bits = 1; + + parg.rsp_policy = ðtool_bitset_bits_nest; + parg.data = &dst->bits; + if (ethtool_bitset_bits_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return 0; +} + +void ethtool_stringset_free(struct ethtool_stringset_ *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_strings; i++) + ethtool_strings_free(&obj->strings[i]); + free(obj->strings); +} + +int ethtool_stringset_put(struct nlmsghdr *nlh, unsigned int attr_type, + struct ethtool_stringset_ *obj) +{ + struct nlattr *nest; + + nest = mnl_attr_nest_start(nlh, attr_type); + if (obj->_present.id) + mnl_attr_put_u32(nlh, ETHTOOL_A_STRINGSET_ID, obj->id); + if (obj->_present.count) + mnl_attr_put_u32(nlh, ETHTOOL_A_STRINGSET_COUNT, obj->count); + for (unsigned int i = 0; i < obj->n_strings; i++) + ethtool_strings_put(nlh, ETHTOOL_A_STRINGSET_STRINGS, &obj->strings[i]); + mnl_attr_nest_end(nlh, nest); + + return 0; +} + +int ethtool_stringset_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_stringset_ *dst = yarg->data; + unsigned int n_strings = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->strings) + return ynl_error_parse(yarg, "attribute already present (stringset.strings)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_STRINGSET_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.id = 1; + dst->id = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_STRINGSET_COUNT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.count = 1; + dst->count = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_STRINGSET_STRINGS) { + n_strings++; + } + } + + if (n_strings) { + dst->strings = calloc(n_strings, sizeof(*dst->strings)); + dst->n_strings = n_strings; + i = 0; + parg.rsp_policy = ðtool_strings_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == ETHTOOL_A_STRINGSET_STRINGS) { + parg.data = &dst->strings[i]; + if (ethtool_strings_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void ethtool_tunnel_udp_table_free(struct ethtool_tunnel_udp_table *obj) +{ + unsigned int i; + + ethtool_bitset_free(&obj->types); + for (i = 0; i < obj->n_entry; i++) + ethtool_tunnel_udp_entry_free(&obj->entry[i]); + free(obj->entry); +} + +int ethtool_tunnel_udp_table_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_tunnel_udp_table *dst = yarg->data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + unsigned int n_entry = 0; + int i; + + parg.ys = yarg->ys; + + if (dst->entry) + return ynl_error_parse(yarg, "attribute already present (tunnel-udp-table.entry)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_TUNNEL_UDP_TABLE_SIZE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.size = 1; + dst->size = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_TUNNEL_UDP_TABLE_TYPES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.types = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->types; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY) { + n_entry++; + } + } + + if (n_entry) { + dst->entry = calloc(n_entry, sizeof(*dst->entry)); + dst->n_entry = n_entry; + i = 0; + parg.rsp_policy = ðtool_tunnel_udp_entry_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY) { + parg.data = &dst->entry[i]; + if (ethtool_tunnel_udp_entry_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void ethtool_stringsets_free(struct ethtool_stringsets *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_stringset; i++) + ethtool_stringset_free(&obj->stringset[i]); + free(obj->stringset); +} + +int ethtool_stringsets_put(struct nlmsghdr *nlh, unsigned int attr_type, + struct ethtool_stringsets *obj) +{ + struct nlattr *nest; + + nest = mnl_attr_nest_start(nlh, attr_type); + for (unsigned int i = 0; i < obj->n_stringset; i++) + ethtool_stringset_put(nlh, ETHTOOL_A_STRINGSETS_STRINGSET, &obj->stringset[i]); + mnl_attr_nest_end(nlh, nest); + + return 0; +} + +int ethtool_stringsets_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_stringsets *dst = yarg->data; + unsigned int n_stringset = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->stringset) + return ynl_error_parse(yarg, "attribute already present (stringsets.stringset)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_STRINGSETS_STRINGSET) { + n_stringset++; + } + } + + if (n_stringset) { + dst->stringset = calloc(n_stringset, sizeof(*dst->stringset)); + dst->n_stringset = n_stringset; + i = 0; + parg.rsp_policy = ðtool_stringset_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == ETHTOOL_A_STRINGSETS_STRINGSET) { + parg.data = &dst->stringset[i]; + if (ethtool_stringset_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void ethtool_tunnel_udp_free(struct ethtool_tunnel_udp *obj) +{ + ethtool_tunnel_udp_table_free(&obj->table); +} + +int ethtool_tunnel_udp_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct ethtool_tunnel_udp *dst = yarg->data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + parg.ys = yarg->ys; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_TUNNEL_UDP_TABLE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.table = 1; + + parg.rsp_policy = ðtool_tunnel_udp_table_nest; + parg.data = &dst->table; + if (ethtool_tunnel_udp_table_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return 0; +} + +/* ============== ETHTOOL_MSG_STRSET_GET ============== */ +/* ETHTOOL_MSG_STRSET_GET - do */ +void ethtool_strset_get_req_free(struct ethtool_strset_get_req *req) +{ + ethtool_header_free(&req->header); + ethtool_stringsets_free(&req->stringsets); + free(req); +} + +void ethtool_strset_get_rsp_free(struct ethtool_strset_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + ethtool_stringsets_free(&rsp->stringsets); + free(rsp); +} + +int ethtool_strset_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_strset_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_STRSET_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_STRSET_STRINGSETS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.stringsets = 1; + + parg.rsp_policy = ðtool_stringsets_nest; + parg.data = &dst->stringsets; + if (ethtool_stringsets_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return MNL_CB_OK; +} + +struct ethtool_strset_get_rsp * +ethtool_strset_get(struct ynl_sock *ys, struct ethtool_strset_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_strset_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_STRSET_GET, 1); + ys->req_policy = ðtool_strset_nest; + yrs.yarg.rsp_policy = ðtool_strset_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_STRSET_HEADER, &req->header); + if (req->_present.stringsets) + ethtool_stringsets_put(nlh, ETHTOOL_A_STRSET_STRINGSETS, &req->stringsets); + if (req->_present.counts_only) + mnl_attr_put(nlh, ETHTOOL_A_STRSET_COUNTS_ONLY, 0, NULL); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_strset_get_rsp_parse; + yrs.rsp_cmd = ETHTOOL_MSG_STRSET_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_strset_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_STRSET_GET - dump */ +void ethtool_strset_get_list_free(struct ethtool_strset_get_list *rsp) +{ + struct ethtool_strset_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + ethtool_stringsets_free(&rsp->obj.stringsets); + free(rsp); + } +} + +struct ethtool_strset_get_list * +ethtool_strset_get_dump(struct ynl_sock *ys, + struct ethtool_strset_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_strset_get_list); + yds.cb = ethtool_strset_get_rsp_parse; + yds.rsp_cmd = ETHTOOL_MSG_STRSET_GET; + yds.rsp_policy = ðtool_strset_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_STRSET_GET, 1); + ys->req_policy = ðtool_strset_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_STRSET_HEADER, &req->header); + if (req->_present.stringsets) + ethtool_stringsets_put(nlh, ETHTOOL_A_STRSET_STRINGSETS, &req->stringsets); + if (req->_present.counts_only) + mnl_attr_put(nlh, ETHTOOL_A_STRSET_COUNTS_ONLY, 0, NULL); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_strset_get_list_free(yds.first); + return NULL; +} + +/* ============== ETHTOOL_MSG_LINKINFO_GET ============== */ +/* ETHTOOL_MSG_LINKINFO_GET - do */ +void ethtool_linkinfo_get_req_free(struct ethtool_linkinfo_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_linkinfo_get_rsp_free(struct ethtool_linkinfo_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + free(rsp); +} + +int ethtool_linkinfo_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_linkinfo_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_LINKINFO_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_LINKINFO_PORT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port = 1; + dst->port = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_LINKINFO_PHYADDR) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.phyaddr = 1; + dst->phyaddr = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_LINKINFO_TP_MDIX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tp_mdix = 1; + dst->tp_mdix = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_LINKINFO_TP_MDIX_CTRL) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tp_mdix_ctrl = 1; + dst->tp_mdix_ctrl = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_LINKINFO_TRANSCEIVER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.transceiver = 1; + dst->transceiver = mnl_attr_get_u8(attr); + } + } + + return MNL_CB_OK; +} + +struct ethtool_linkinfo_get_rsp * +ethtool_linkinfo_get(struct ynl_sock *ys, struct ethtool_linkinfo_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_linkinfo_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_LINKINFO_GET, 1); + ys->req_policy = ðtool_linkinfo_nest; + yrs.yarg.rsp_policy = ðtool_linkinfo_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_LINKINFO_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_linkinfo_get_rsp_parse; + yrs.rsp_cmd = ETHTOOL_MSG_LINKINFO_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_linkinfo_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_LINKINFO_GET - dump */ +void ethtool_linkinfo_get_list_free(struct ethtool_linkinfo_get_list *rsp) +{ + struct ethtool_linkinfo_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + free(rsp); + } +} + +struct ethtool_linkinfo_get_list * +ethtool_linkinfo_get_dump(struct ynl_sock *ys, + struct ethtool_linkinfo_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_linkinfo_get_list); + yds.cb = ethtool_linkinfo_get_rsp_parse; + yds.rsp_cmd = ETHTOOL_MSG_LINKINFO_GET; + yds.rsp_policy = ðtool_linkinfo_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_LINKINFO_GET, 1); + ys->req_policy = ðtool_linkinfo_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_LINKINFO_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_linkinfo_get_list_free(yds.first); + return NULL; +} + +/* ETHTOOL_MSG_LINKINFO_GET - notify */ +void ethtool_linkinfo_get_ntf_free(struct ethtool_linkinfo_get_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + free(rsp); +} + +/* ============== ETHTOOL_MSG_LINKINFO_SET ============== */ +/* ETHTOOL_MSG_LINKINFO_SET - do */ +void ethtool_linkinfo_set_req_free(struct ethtool_linkinfo_set_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +int ethtool_linkinfo_set(struct ynl_sock *ys, + struct ethtool_linkinfo_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_LINKINFO_SET, 1); + ys->req_policy = ðtool_linkinfo_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_LINKINFO_HEADER, &req->header); + if (req->_present.port) + mnl_attr_put_u8(nlh, ETHTOOL_A_LINKINFO_PORT, req->port); + if (req->_present.phyaddr) + mnl_attr_put_u8(nlh, ETHTOOL_A_LINKINFO_PHYADDR, req->phyaddr); + if (req->_present.tp_mdix) + mnl_attr_put_u8(nlh, ETHTOOL_A_LINKINFO_TP_MDIX, req->tp_mdix); + if (req->_present.tp_mdix_ctrl) + mnl_attr_put_u8(nlh, ETHTOOL_A_LINKINFO_TP_MDIX_CTRL, req->tp_mdix_ctrl); + if (req->_present.transceiver) + mnl_attr_put_u8(nlh, ETHTOOL_A_LINKINFO_TRANSCEIVER, req->transceiver); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== ETHTOOL_MSG_LINKMODES_GET ============== */ +/* ETHTOOL_MSG_LINKMODES_GET - do */ +void ethtool_linkmodes_get_req_free(struct ethtool_linkmodes_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_linkmodes_get_rsp_free(struct ethtool_linkmodes_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + ethtool_bitset_free(&rsp->ours); + ethtool_bitset_free(&rsp->peer); + free(rsp); +} + +int ethtool_linkmodes_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_linkmodes_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_LINKMODES_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_LINKMODES_AUTONEG) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.autoneg = 1; + dst->autoneg = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_LINKMODES_OURS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ours = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->ours; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_LINKMODES_PEER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.peer = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->peer; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_LINKMODES_SPEED) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.speed = 1; + dst->speed = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_LINKMODES_DUPLEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.duplex = 1; + dst->duplex = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.master_slave_cfg = 1; + dst->master_slave_cfg = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.master_slave_state = 1; + dst->master_slave_state = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_LINKMODES_LANES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.lanes = 1; + dst->lanes = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_LINKMODES_RATE_MATCHING) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rate_matching = 1; + dst->rate_matching = mnl_attr_get_u8(attr); + } + } + + return MNL_CB_OK; +} + +struct ethtool_linkmodes_get_rsp * +ethtool_linkmodes_get(struct ynl_sock *ys, + struct ethtool_linkmodes_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_linkmodes_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_LINKMODES_GET, 1); + ys->req_policy = ðtool_linkmodes_nest; + yrs.yarg.rsp_policy = ðtool_linkmodes_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_LINKMODES_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_linkmodes_get_rsp_parse; + yrs.rsp_cmd = ETHTOOL_MSG_LINKMODES_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_linkmodes_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_LINKMODES_GET - dump */ +void ethtool_linkmodes_get_list_free(struct ethtool_linkmodes_get_list *rsp) +{ + struct ethtool_linkmodes_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + ethtool_bitset_free(&rsp->obj.ours); + ethtool_bitset_free(&rsp->obj.peer); + free(rsp); + } +} + +struct ethtool_linkmodes_get_list * +ethtool_linkmodes_get_dump(struct ynl_sock *ys, + struct ethtool_linkmodes_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_linkmodes_get_list); + yds.cb = ethtool_linkmodes_get_rsp_parse; + yds.rsp_cmd = ETHTOOL_MSG_LINKMODES_GET; + yds.rsp_policy = ðtool_linkmodes_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_LINKMODES_GET, 1); + ys->req_policy = ðtool_linkmodes_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_LINKMODES_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_linkmodes_get_list_free(yds.first); + return NULL; +} + +/* ETHTOOL_MSG_LINKMODES_GET - notify */ +void ethtool_linkmodes_get_ntf_free(struct ethtool_linkmodes_get_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + ethtool_bitset_free(&rsp->obj.ours); + ethtool_bitset_free(&rsp->obj.peer); + free(rsp); +} + +/* ============== ETHTOOL_MSG_LINKMODES_SET ============== */ +/* ETHTOOL_MSG_LINKMODES_SET - do */ +void ethtool_linkmodes_set_req_free(struct ethtool_linkmodes_set_req *req) +{ + ethtool_header_free(&req->header); + ethtool_bitset_free(&req->ours); + ethtool_bitset_free(&req->peer); + free(req); +} + +int ethtool_linkmodes_set(struct ynl_sock *ys, + struct ethtool_linkmodes_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_LINKMODES_SET, 1); + ys->req_policy = ðtool_linkmodes_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_LINKMODES_HEADER, &req->header); + if (req->_present.autoneg) + mnl_attr_put_u8(nlh, ETHTOOL_A_LINKMODES_AUTONEG, req->autoneg); + if (req->_present.ours) + ethtool_bitset_put(nlh, ETHTOOL_A_LINKMODES_OURS, &req->ours); + if (req->_present.peer) + ethtool_bitset_put(nlh, ETHTOOL_A_LINKMODES_PEER, &req->peer); + if (req->_present.speed) + mnl_attr_put_u32(nlh, ETHTOOL_A_LINKMODES_SPEED, req->speed); + if (req->_present.duplex) + mnl_attr_put_u8(nlh, ETHTOOL_A_LINKMODES_DUPLEX, req->duplex); + if (req->_present.master_slave_cfg) + mnl_attr_put_u8(nlh, ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG, req->master_slave_cfg); + if (req->_present.master_slave_state) + mnl_attr_put_u8(nlh, ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE, req->master_slave_state); + if (req->_present.lanes) + mnl_attr_put_u32(nlh, ETHTOOL_A_LINKMODES_LANES, req->lanes); + if (req->_present.rate_matching) + mnl_attr_put_u8(nlh, ETHTOOL_A_LINKMODES_RATE_MATCHING, req->rate_matching); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== ETHTOOL_MSG_LINKSTATE_GET ============== */ +/* ETHTOOL_MSG_LINKSTATE_GET - do */ +void ethtool_linkstate_get_req_free(struct ethtool_linkstate_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_linkstate_get_rsp_free(struct ethtool_linkstate_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + free(rsp); +} + +int ethtool_linkstate_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_linkstate_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_LINKSTATE_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_LINKSTATE_LINK) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.link = 1; + dst->link = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_LINKSTATE_SQI) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sqi = 1; + dst->sqi = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_LINKSTATE_SQI_MAX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sqi_max = 1; + dst->sqi_max = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_LINKSTATE_EXT_STATE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ext_state = 1; + dst->ext_state = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_LINKSTATE_EXT_SUBSTATE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ext_substate = 1; + dst->ext_substate = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ext_down_cnt = 1; + dst->ext_down_cnt = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct ethtool_linkstate_get_rsp * +ethtool_linkstate_get(struct ynl_sock *ys, + struct ethtool_linkstate_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_linkstate_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_LINKSTATE_GET, 1); + ys->req_policy = ðtool_linkstate_nest; + yrs.yarg.rsp_policy = ðtool_linkstate_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_LINKSTATE_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_linkstate_get_rsp_parse; + yrs.rsp_cmd = ETHTOOL_MSG_LINKSTATE_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_linkstate_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_LINKSTATE_GET - dump */ +void ethtool_linkstate_get_list_free(struct ethtool_linkstate_get_list *rsp) +{ + struct ethtool_linkstate_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + free(rsp); + } +} + +struct ethtool_linkstate_get_list * +ethtool_linkstate_get_dump(struct ynl_sock *ys, + struct ethtool_linkstate_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_linkstate_get_list); + yds.cb = ethtool_linkstate_get_rsp_parse; + yds.rsp_cmd = ETHTOOL_MSG_LINKSTATE_GET; + yds.rsp_policy = ðtool_linkstate_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_LINKSTATE_GET, 1); + ys->req_policy = ðtool_linkstate_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_LINKSTATE_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_linkstate_get_list_free(yds.first); + return NULL; +} + +/* ============== ETHTOOL_MSG_DEBUG_GET ============== */ +/* ETHTOOL_MSG_DEBUG_GET - do */ +void ethtool_debug_get_req_free(struct ethtool_debug_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_debug_get_rsp_free(struct ethtool_debug_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + ethtool_bitset_free(&rsp->msgmask); + free(rsp); +} + +int ethtool_debug_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_debug_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_DEBUG_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_DEBUG_MSGMASK) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.msgmask = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->msgmask; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return MNL_CB_OK; +} + +struct ethtool_debug_get_rsp * +ethtool_debug_get(struct ynl_sock *ys, struct ethtool_debug_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_debug_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_DEBUG_GET, 1); + ys->req_policy = ðtool_debug_nest; + yrs.yarg.rsp_policy = ðtool_debug_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_DEBUG_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_debug_get_rsp_parse; + yrs.rsp_cmd = ETHTOOL_MSG_DEBUG_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_debug_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_DEBUG_GET - dump */ +void ethtool_debug_get_list_free(struct ethtool_debug_get_list *rsp) +{ + struct ethtool_debug_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + ethtool_bitset_free(&rsp->obj.msgmask); + free(rsp); + } +} + +struct ethtool_debug_get_list * +ethtool_debug_get_dump(struct ynl_sock *ys, + struct ethtool_debug_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_debug_get_list); + yds.cb = ethtool_debug_get_rsp_parse; + yds.rsp_cmd = ETHTOOL_MSG_DEBUG_GET; + yds.rsp_policy = ðtool_debug_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_DEBUG_GET, 1); + ys->req_policy = ðtool_debug_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_DEBUG_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_debug_get_list_free(yds.first); + return NULL; +} + +/* ETHTOOL_MSG_DEBUG_GET - notify */ +void ethtool_debug_get_ntf_free(struct ethtool_debug_get_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + ethtool_bitset_free(&rsp->obj.msgmask); + free(rsp); +} + +/* ============== ETHTOOL_MSG_DEBUG_SET ============== */ +/* ETHTOOL_MSG_DEBUG_SET - do */ +void ethtool_debug_set_req_free(struct ethtool_debug_set_req *req) +{ + ethtool_header_free(&req->header); + ethtool_bitset_free(&req->msgmask); + free(req); +} + +int ethtool_debug_set(struct ynl_sock *ys, struct ethtool_debug_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_DEBUG_SET, 1); + ys->req_policy = ðtool_debug_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_DEBUG_HEADER, &req->header); + if (req->_present.msgmask) + ethtool_bitset_put(nlh, ETHTOOL_A_DEBUG_MSGMASK, &req->msgmask); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== ETHTOOL_MSG_WOL_GET ============== */ +/* ETHTOOL_MSG_WOL_GET - do */ +void ethtool_wol_get_req_free(struct ethtool_wol_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_wol_get_rsp_free(struct ethtool_wol_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + ethtool_bitset_free(&rsp->modes); + free(rsp->sopass); + free(rsp); +} + +int ethtool_wol_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct ethtool_wol_get_rsp *dst; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_WOL_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_WOL_MODES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.modes = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->modes; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_WOL_SOPASS) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.sopass_len = len; + dst->sopass = malloc(len); + memcpy(dst->sopass, mnl_attr_get_payload(attr), len); + } + } + + return MNL_CB_OK; +} + +struct ethtool_wol_get_rsp * +ethtool_wol_get(struct ynl_sock *ys, struct ethtool_wol_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_wol_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_WOL_GET, 1); + ys->req_policy = ðtool_wol_nest; + yrs.yarg.rsp_policy = ðtool_wol_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_WOL_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_wol_get_rsp_parse; + yrs.rsp_cmd = ETHTOOL_MSG_WOL_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_wol_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_WOL_GET - dump */ +void ethtool_wol_get_list_free(struct ethtool_wol_get_list *rsp) +{ + struct ethtool_wol_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + ethtool_bitset_free(&rsp->obj.modes); + free(rsp->obj.sopass); + free(rsp); + } +} + +struct ethtool_wol_get_list * +ethtool_wol_get_dump(struct ynl_sock *ys, struct ethtool_wol_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_wol_get_list); + yds.cb = ethtool_wol_get_rsp_parse; + yds.rsp_cmd = ETHTOOL_MSG_WOL_GET; + yds.rsp_policy = ðtool_wol_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_WOL_GET, 1); + ys->req_policy = ðtool_wol_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_WOL_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_wol_get_list_free(yds.first); + return NULL; +} + +/* ETHTOOL_MSG_WOL_GET - notify */ +void ethtool_wol_get_ntf_free(struct ethtool_wol_get_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + ethtool_bitset_free(&rsp->obj.modes); + free(rsp->obj.sopass); + free(rsp); +} + +/* ============== ETHTOOL_MSG_WOL_SET ============== */ +/* ETHTOOL_MSG_WOL_SET - do */ +void ethtool_wol_set_req_free(struct ethtool_wol_set_req *req) +{ + ethtool_header_free(&req->header); + ethtool_bitset_free(&req->modes); + free(req->sopass); + free(req); +} + +int ethtool_wol_set(struct ynl_sock *ys, struct ethtool_wol_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_WOL_SET, 1); + ys->req_policy = ðtool_wol_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_WOL_HEADER, &req->header); + if (req->_present.modes) + ethtool_bitset_put(nlh, ETHTOOL_A_WOL_MODES, &req->modes); + if (req->_present.sopass_len) + mnl_attr_put(nlh, ETHTOOL_A_WOL_SOPASS, req->_present.sopass_len, req->sopass); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== ETHTOOL_MSG_FEATURES_GET ============== */ +/* ETHTOOL_MSG_FEATURES_GET - do */ +void ethtool_features_get_req_free(struct ethtool_features_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_features_get_rsp_free(struct ethtool_features_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + ethtool_bitset_free(&rsp->hw); + ethtool_bitset_free(&rsp->wanted); + ethtool_bitset_free(&rsp->active); + ethtool_bitset_free(&rsp->nochange); + free(rsp); +} + +int ethtool_features_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_features_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_FEATURES_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_FEATURES_HW) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.hw = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->hw; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_FEATURES_WANTED) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.wanted = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->wanted; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_FEATURES_ACTIVE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.active = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->active; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_FEATURES_NOCHANGE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.nochange = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->nochange; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return MNL_CB_OK; +} + +struct ethtool_features_get_rsp * +ethtool_features_get(struct ynl_sock *ys, struct ethtool_features_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_features_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_FEATURES_GET, 1); + ys->req_policy = ðtool_features_nest; + yrs.yarg.rsp_policy = ðtool_features_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_FEATURES_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_features_get_rsp_parse; + yrs.rsp_cmd = ETHTOOL_MSG_FEATURES_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_features_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_FEATURES_GET - dump */ +void ethtool_features_get_list_free(struct ethtool_features_get_list *rsp) +{ + struct ethtool_features_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + ethtool_bitset_free(&rsp->obj.hw); + ethtool_bitset_free(&rsp->obj.wanted); + ethtool_bitset_free(&rsp->obj.active); + ethtool_bitset_free(&rsp->obj.nochange); + free(rsp); + } +} + +struct ethtool_features_get_list * +ethtool_features_get_dump(struct ynl_sock *ys, + struct ethtool_features_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_features_get_list); + yds.cb = ethtool_features_get_rsp_parse; + yds.rsp_cmd = ETHTOOL_MSG_FEATURES_GET; + yds.rsp_policy = ðtool_features_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_FEATURES_GET, 1); + ys->req_policy = ðtool_features_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_FEATURES_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_features_get_list_free(yds.first); + return NULL; +} + +/* ETHTOOL_MSG_FEATURES_GET - notify */ +void ethtool_features_get_ntf_free(struct ethtool_features_get_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + ethtool_bitset_free(&rsp->obj.hw); + ethtool_bitset_free(&rsp->obj.wanted); + ethtool_bitset_free(&rsp->obj.active); + ethtool_bitset_free(&rsp->obj.nochange); + free(rsp); +} + +/* ============== ETHTOOL_MSG_FEATURES_SET ============== */ +/* ETHTOOL_MSG_FEATURES_SET - do */ +void ethtool_features_set_req_free(struct ethtool_features_set_req *req) +{ + ethtool_header_free(&req->header); + ethtool_bitset_free(&req->hw); + ethtool_bitset_free(&req->wanted); + ethtool_bitset_free(&req->active); + ethtool_bitset_free(&req->nochange); + free(req); +} + +void ethtool_features_set_rsp_free(struct ethtool_features_set_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + ethtool_bitset_free(&rsp->hw); + ethtool_bitset_free(&rsp->wanted); + ethtool_bitset_free(&rsp->active); + ethtool_bitset_free(&rsp->nochange); + free(rsp); +} + +int ethtool_features_set_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_features_set_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_FEATURES_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_FEATURES_HW) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.hw = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->hw; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_FEATURES_WANTED) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.wanted = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->wanted; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_FEATURES_ACTIVE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.active = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->active; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_FEATURES_NOCHANGE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.nochange = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->nochange; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return MNL_CB_OK; +} + +struct ethtool_features_set_rsp * +ethtool_features_set(struct ynl_sock *ys, struct ethtool_features_set_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_features_set_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_FEATURES_SET, 1); + ys->req_policy = ðtool_features_nest; + yrs.yarg.rsp_policy = ðtool_features_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_FEATURES_HEADER, &req->header); + if (req->_present.hw) + ethtool_bitset_put(nlh, ETHTOOL_A_FEATURES_HW, &req->hw); + if (req->_present.wanted) + ethtool_bitset_put(nlh, ETHTOOL_A_FEATURES_WANTED, &req->wanted); + if (req->_present.active) + ethtool_bitset_put(nlh, ETHTOOL_A_FEATURES_ACTIVE, &req->active); + if (req->_present.nochange) + ethtool_bitset_put(nlh, ETHTOOL_A_FEATURES_NOCHANGE, &req->nochange); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_features_set_rsp_parse; + yrs.rsp_cmd = ETHTOOL_MSG_FEATURES_SET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_features_set_rsp_free(rsp); + return NULL; +} + +/* ============== ETHTOOL_MSG_PRIVFLAGS_GET ============== */ +/* ETHTOOL_MSG_PRIVFLAGS_GET - do */ +void ethtool_privflags_get_req_free(struct ethtool_privflags_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_privflags_get_rsp_free(struct ethtool_privflags_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + ethtool_bitset_free(&rsp->flags); + free(rsp); +} + +int ethtool_privflags_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_privflags_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_PRIVFLAGS_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_PRIVFLAGS_FLAGS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.flags = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->flags; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return MNL_CB_OK; +} + +struct ethtool_privflags_get_rsp * +ethtool_privflags_get(struct ynl_sock *ys, + struct ethtool_privflags_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_privflags_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PRIVFLAGS_GET, 1); + ys->req_policy = ðtool_privflags_nest; + yrs.yarg.rsp_policy = ðtool_privflags_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_PRIVFLAGS_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_privflags_get_rsp_parse; + yrs.rsp_cmd = 14; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_privflags_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_PRIVFLAGS_GET - dump */ +void ethtool_privflags_get_list_free(struct ethtool_privflags_get_list *rsp) +{ + struct ethtool_privflags_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + ethtool_bitset_free(&rsp->obj.flags); + free(rsp); + } +} + +struct ethtool_privflags_get_list * +ethtool_privflags_get_dump(struct ynl_sock *ys, + struct ethtool_privflags_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_privflags_get_list); + yds.cb = ethtool_privflags_get_rsp_parse; + yds.rsp_cmd = 14; + yds.rsp_policy = ðtool_privflags_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_PRIVFLAGS_GET, 1); + ys->req_policy = ðtool_privflags_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_PRIVFLAGS_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_privflags_get_list_free(yds.first); + return NULL; +} + +/* ETHTOOL_MSG_PRIVFLAGS_GET - notify */ +void ethtool_privflags_get_ntf_free(struct ethtool_privflags_get_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + ethtool_bitset_free(&rsp->obj.flags); + free(rsp); +} + +/* ============== ETHTOOL_MSG_PRIVFLAGS_SET ============== */ +/* ETHTOOL_MSG_PRIVFLAGS_SET - do */ +void ethtool_privflags_set_req_free(struct ethtool_privflags_set_req *req) +{ + ethtool_header_free(&req->header); + ethtool_bitset_free(&req->flags); + free(req); +} + +int ethtool_privflags_set(struct ynl_sock *ys, + struct ethtool_privflags_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PRIVFLAGS_SET, 1); + ys->req_policy = ðtool_privflags_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_PRIVFLAGS_HEADER, &req->header); + if (req->_present.flags) + ethtool_bitset_put(nlh, ETHTOOL_A_PRIVFLAGS_FLAGS, &req->flags); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== ETHTOOL_MSG_RINGS_GET ============== */ +/* ETHTOOL_MSG_RINGS_GET - do */ +void ethtool_rings_get_req_free(struct ethtool_rings_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_rings_get_rsp_free(struct ethtool_rings_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + free(rsp); +} + +int ethtool_rings_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_rings_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_RINGS_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_RINGS_RX_MAX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_max = 1; + dst->rx_max = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_RINGS_RX_MINI_MAX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_mini_max = 1; + dst->rx_mini_max = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_RINGS_RX_JUMBO_MAX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_jumbo_max = 1; + dst->rx_jumbo_max = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_RINGS_TX_MAX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_max = 1; + dst->tx_max = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_RINGS_RX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx = 1; + dst->rx = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_RINGS_RX_MINI) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_mini = 1; + dst->rx_mini = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_RINGS_RX_JUMBO) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_jumbo = 1; + dst->rx_jumbo = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_RINGS_TX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx = 1; + dst->tx = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_RINGS_RX_BUF_LEN) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_buf_len = 1; + dst->rx_buf_len = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_RINGS_TCP_DATA_SPLIT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tcp_data_split = 1; + dst->tcp_data_split = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_RINGS_CQE_SIZE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.cqe_size = 1; + dst->cqe_size = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_RINGS_TX_PUSH) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_push = 1; + dst->tx_push = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_RINGS_RX_PUSH) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_push = 1; + dst->rx_push = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_push_buf_len = 1; + dst->tx_push_buf_len = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_push_buf_len_max = 1; + dst->tx_push_buf_len_max = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct ethtool_rings_get_rsp * +ethtool_rings_get(struct ynl_sock *ys, struct ethtool_rings_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_rings_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_RINGS_GET, 1); + ys->req_policy = ðtool_rings_nest; + yrs.yarg.rsp_policy = ðtool_rings_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_RINGS_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_rings_get_rsp_parse; + yrs.rsp_cmd = 16; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_rings_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_RINGS_GET - dump */ +void ethtool_rings_get_list_free(struct ethtool_rings_get_list *rsp) +{ + struct ethtool_rings_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + free(rsp); + } +} + +struct ethtool_rings_get_list * +ethtool_rings_get_dump(struct ynl_sock *ys, + struct ethtool_rings_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_rings_get_list); + yds.cb = ethtool_rings_get_rsp_parse; + yds.rsp_cmd = 16; + yds.rsp_policy = ðtool_rings_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_RINGS_GET, 1); + ys->req_policy = ðtool_rings_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_RINGS_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_rings_get_list_free(yds.first); + return NULL; +} + +/* ETHTOOL_MSG_RINGS_GET - notify */ +void ethtool_rings_get_ntf_free(struct ethtool_rings_get_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + free(rsp); +} + +/* ============== ETHTOOL_MSG_RINGS_SET ============== */ +/* ETHTOOL_MSG_RINGS_SET - do */ +void ethtool_rings_set_req_free(struct ethtool_rings_set_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +int ethtool_rings_set(struct ynl_sock *ys, struct ethtool_rings_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_RINGS_SET, 1); + ys->req_policy = ðtool_rings_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_RINGS_HEADER, &req->header); + if (req->_present.rx_max) + mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_RX_MAX, req->rx_max); + if (req->_present.rx_mini_max) + mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_RX_MINI_MAX, req->rx_mini_max); + if (req->_present.rx_jumbo_max) + mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_RX_JUMBO_MAX, req->rx_jumbo_max); + if (req->_present.tx_max) + mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_TX_MAX, req->tx_max); + if (req->_present.rx) + mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_RX, req->rx); + if (req->_present.rx_mini) + mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_RX_MINI, req->rx_mini); + if (req->_present.rx_jumbo) + mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_RX_JUMBO, req->rx_jumbo); + if (req->_present.tx) + mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_TX, req->tx); + if (req->_present.rx_buf_len) + mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_RX_BUF_LEN, req->rx_buf_len); + if (req->_present.tcp_data_split) + mnl_attr_put_u8(nlh, ETHTOOL_A_RINGS_TCP_DATA_SPLIT, req->tcp_data_split); + if (req->_present.cqe_size) + mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_CQE_SIZE, req->cqe_size); + if (req->_present.tx_push) + mnl_attr_put_u8(nlh, ETHTOOL_A_RINGS_TX_PUSH, req->tx_push); + if (req->_present.rx_push) + mnl_attr_put_u8(nlh, ETHTOOL_A_RINGS_RX_PUSH, req->rx_push); + if (req->_present.tx_push_buf_len) + mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN, req->tx_push_buf_len); + if (req->_present.tx_push_buf_len_max) + mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX, req->tx_push_buf_len_max); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== ETHTOOL_MSG_CHANNELS_GET ============== */ +/* ETHTOOL_MSG_CHANNELS_GET - do */ +void ethtool_channels_get_req_free(struct ethtool_channels_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_channels_get_rsp_free(struct ethtool_channels_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + free(rsp); +} + +int ethtool_channels_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_channels_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_CHANNELS_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_CHANNELS_RX_MAX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_max = 1; + dst->rx_max = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_CHANNELS_TX_MAX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_max = 1; + dst->tx_max = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_CHANNELS_OTHER_MAX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.other_max = 1; + dst->other_max = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_CHANNELS_COMBINED_MAX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.combined_max = 1; + dst->combined_max = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_CHANNELS_RX_COUNT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_count = 1; + dst->rx_count = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_CHANNELS_TX_COUNT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_count = 1; + dst->tx_count = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_CHANNELS_OTHER_COUNT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.other_count = 1; + dst->other_count = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_CHANNELS_COMBINED_COUNT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.combined_count = 1; + dst->combined_count = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct ethtool_channels_get_rsp * +ethtool_channels_get(struct ynl_sock *ys, struct ethtool_channels_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_channels_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_CHANNELS_GET, 1); + ys->req_policy = ðtool_channels_nest; + yrs.yarg.rsp_policy = ðtool_channels_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_CHANNELS_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_channels_get_rsp_parse; + yrs.rsp_cmd = 18; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_channels_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_CHANNELS_GET - dump */ +void ethtool_channels_get_list_free(struct ethtool_channels_get_list *rsp) +{ + struct ethtool_channels_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + free(rsp); + } +} + +struct ethtool_channels_get_list * +ethtool_channels_get_dump(struct ynl_sock *ys, + struct ethtool_channels_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_channels_get_list); + yds.cb = ethtool_channels_get_rsp_parse; + yds.rsp_cmd = 18; + yds.rsp_policy = ðtool_channels_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_CHANNELS_GET, 1); + ys->req_policy = ðtool_channels_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_CHANNELS_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_channels_get_list_free(yds.first); + return NULL; +} + +/* ETHTOOL_MSG_CHANNELS_GET - notify */ +void ethtool_channels_get_ntf_free(struct ethtool_channels_get_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + free(rsp); +} + +/* ============== ETHTOOL_MSG_CHANNELS_SET ============== */ +/* ETHTOOL_MSG_CHANNELS_SET - do */ +void ethtool_channels_set_req_free(struct ethtool_channels_set_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +int ethtool_channels_set(struct ynl_sock *ys, + struct ethtool_channels_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_CHANNELS_SET, 1); + ys->req_policy = ðtool_channels_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_CHANNELS_HEADER, &req->header); + if (req->_present.rx_max) + mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_RX_MAX, req->rx_max); + if (req->_present.tx_max) + mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_TX_MAX, req->tx_max); + if (req->_present.other_max) + mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_OTHER_MAX, req->other_max); + if (req->_present.combined_max) + mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_COMBINED_MAX, req->combined_max); + if (req->_present.rx_count) + mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_RX_COUNT, req->rx_count); + if (req->_present.tx_count) + mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_TX_COUNT, req->tx_count); + if (req->_present.other_count) + mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_OTHER_COUNT, req->other_count); + if (req->_present.combined_count) + mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_COMBINED_COUNT, req->combined_count); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== ETHTOOL_MSG_COALESCE_GET ============== */ +/* ETHTOOL_MSG_COALESCE_GET - do */ +void ethtool_coalesce_get_req_free(struct ethtool_coalesce_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_coalesce_get_rsp_free(struct ethtool_coalesce_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + free(rsp); +} + +int ethtool_coalesce_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_coalesce_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_COALESCE_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_COALESCE_RX_USECS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_usecs = 1; + dst->rx_usecs = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_RX_MAX_FRAMES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_max_frames = 1; + dst->rx_max_frames = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_RX_USECS_IRQ) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_usecs_irq = 1; + dst->rx_usecs_irq = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_max_frames_irq = 1; + dst->rx_max_frames_irq = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_TX_USECS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_usecs = 1; + dst->tx_usecs = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_TX_MAX_FRAMES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_max_frames = 1; + dst->tx_max_frames = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_TX_USECS_IRQ) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_usecs_irq = 1; + dst->tx_usecs_irq = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_max_frames_irq = 1; + dst->tx_max_frames_irq = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_STATS_BLOCK_USECS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.stats_block_usecs = 1; + dst->stats_block_usecs = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.use_adaptive_rx = 1; + dst->use_adaptive_rx = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.use_adaptive_tx = 1; + dst->use_adaptive_tx = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_COALESCE_PKT_RATE_LOW) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.pkt_rate_low = 1; + dst->pkt_rate_low = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_RX_USECS_LOW) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_usecs_low = 1; + dst->rx_usecs_low = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_max_frames_low = 1; + dst->rx_max_frames_low = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_TX_USECS_LOW) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_usecs_low = 1; + dst->tx_usecs_low = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_max_frames_low = 1; + dst->tx_max_frames_low = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_PKT_RATE_HIGH) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.pkt_rate_high = 1; + dst->pkt_rate_high = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_RX_USECS_HIGH) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_usecs_high = 1; + dst->rx_usecs_high = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_max_frames_high = 1; + dst->rx_max_frames_high = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_TX_USECS_HIGH) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_usecs_high = 1; + dst->tx_usecs_high = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_max_frames_high = 1; + dst->tx_max_frames_high = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rate_sample_interval = 1; + dst->rate_sample_interval = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_USE_CQE_MODE_TX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.use_cqe_mode_tx = 1; + dst->use_cqe_mode_tx = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_COALESCE_USE_CQE_MODE_RX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.use_cqe_mode_rx = 1; + dst->use_cqe_mode_rx = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_aggr_max_bytes = 1; + dst->tx_aggr_max_bytes = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_aggr_max_frames = 1; + dst->tx_aggr_max_frames = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_aggr_time_usecs = 1; + dst->tx_aggr_time_usecs = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct ethtool_coalesce_get_rsp * +ethtool_coalesce_get(struct ynl_sock *ys, struct ethtool_coalesce_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_coalesce_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_COALESCE_GET, 1); + ys->req_policy = ðtool_coalesce_nest; + yrs.yarg.rsp_policy = ðtool_coalesce_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_COALESCE_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_coalesce_get_rsp_parse; + yrs.rsp_cmd = 20; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_coalesce_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_COALESCE_GET - dump */ +void ethtool_coalesce_get_list_free(struct ethtool_coalesce_get_list *rsp) +{ + struct ethtool_coalesce_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + free(rsp); + } +} + +struct ethtool_coalesce_get_list * +ethtool_coalesce_get_dump(struct ynl_sock *ys, + struct ethtool_coalesce_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_coalesce_get_list); + yds.cb = ethtool_coalesce_get_rsp_parse; + yds.rsp_cmd = 20; + yds.rsp_policy = ðtool_coalesce_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_COALESCE_GET, 1); + ys->req_policy = ðtool_coalesce_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_COALESCE_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_coalesce_get_list_free(yds.first); + return NULL; +} + +/* ETHTOOL_MSG_COALESCE_GET - notify */ +void ethtool_coalesce_get_ntf_free(struct ethtool_coalesce_get_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + free(rsp); +} + +/* ============== ETHTOOL_MSG_COALESCE_SET ============== */ +/* ETHTOOL_MSG_COALESCE_SET - do */ +void ethtool_coalesce_set_req_free(struct ethtool_coalesce_set_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +int ethtool_coalesce_set(struct ynl_sock *ys, + struct ethtool_coalesce_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_COALESCE_SET, 1); + ys->req_policy = ðtool_coalesce_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_COALESCE_HEADER, &req->header); + if (req->_present.rx_usecs) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RX_USECS, req->rx_usecs); + if (req->_present.rx_max_frames) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RX_MAX_FRAMES, req->rx_max_frames); + if (req->_present.rx_usecs_irq) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RX_USECS_IRQ, req->rx_usecs_irq); + if (req->_present.rx_max_frames_irq) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ, req->rx_max_frames_irq); + if (req->_present.tx_usecs) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_USECS, req->tx_usecs); + if (req->_present.tx_max_frames) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_MAX_FRAMES, req->tx_max_frames); + if (req->_present.tx_usecs_irq) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_USECS_IRQ, req->tx_usecs_irq); + if (req->_present.tx_max_frames_irq) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ, req->tx_max_frames_irq); + if (req->_present.stats_block_usecs) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_STATS_BLOCK_USECS, req->stats_block_usecs); + if (req->_present.use_adaptive_rx) + mnl_attr_put_u8(nlh, ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX, req->use_adaptive_rx); + if (req->_present.use_adaptive_tx) + mnl_attr_put_u8(nlh, ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX, req->use_adaptive_tx); + if (req->_present.pkt_rate_low) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_PKT_RATE_LOW, req->pkt_rate_low); + if (req->_present.rx_usecs_low) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RX_USECS_LOW, req->rx_usecs_low); + if (req->_present.rx_max_frames_low) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW, req->rx_max_frames_low); + if (req->_present.tx_usecs_low) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_USECS_LOW, req->tx_usecs_low); + if (req->_present.tx_max_frames_low) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW, req->tx_max_frames_low); + if (req->_present.pkt_rate_high) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_PKT_RATE_HIGH, req->pkt_rate_high); + if (req->_present.rx_usecs_high) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RX_USECS_HIGH, req->rx_usecs_high); + if (req->_present.rx_max_frames_high) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH, req->rx_max_frames_high); + if (req->_present.tx_usecs_high) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_USECS_HIGH, req->tx_usecs_high); + if (req->_present.tx_max_frames_high) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH, req->tx_max_frames_high); + if (req->_present.rate_sample_interval) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL, req->rate_sample_interval); + if (req->_present.use_cqe_mode_tx) + mnl_attr_put_u8(nlh, ETHTOOL_A_COALESCE_USE_CQE_MODE_TX, req->use_cqe_mode_tx); + if (req->_present.use_cqe_mode_rx) + mnl_attr_put_u8(nlh, ETHTOOL_A_COALESCE_USE_CQE_MODE_RX, req->use_cqe_mode_rx); + if (req->_present.tx_aggr_max_bytes) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES, req->tx_aggr_max_bytes); + if (req->_present.tx_aggr_max_frames) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES, req->tx_aggr_max_frames); + if (req->_present.tx_aggr_time_usecs) + mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS, req->tx_aggr_time_usecs); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== ETHTOOL_MSG_PAUSE_GET ============== */ +/* ETHTOOL_MSG_PAUSE_GET - do */ +void ethtool_pause_get_req_free(struct ethtool_pause_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_pause_get_rsp_free(struct ethtool_pause_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + ethtool_pause_stat_free(&rsp->stats); + free(rsp); +} + +int ethtool_pause_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_pause_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_PAUSE_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_PAUSE_AUTONEG) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.autoneg = 1; + dst->autoneg = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_PAUSE_RX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx = 1; + dst->rx = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_PAUSE_TX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx = 1; + dst->tx = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_PAUSE_STATS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.stats = 1; + + parg.rsp_policy = ðtool_pause_stat_nest; + parg.data = &dst->stats; + if (ethtool_pause_stat_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_PAUSE_STATS_SRC) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.stats_src = 1; + dst->stats_src = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct ethtool_pause_get_rsp * +ethtool_pause_get(struct ynl_sock *ys, struct ethtool_pause_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_pause_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PAUSE_GET, 1); + ys->req_policy = ðtool_pause_nest; + yrs.yarg.rsp_policy = ðtool_pause_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_PAUSE_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_pause_get_rsp_parse; + yrs.rsp_cmd = 22; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_pause_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_PAUSE_GET - dump */ +void ethtool_pause_get_list_free(struct ethtool_pause_get_list *rsp) +{ + struct ethtool_pause_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + ethtool_pause_stat_free(&rsp->obj.stats); + free(rsp); + } +} + +struct ethtool_pause_get_list * +ethtool_pause_get_dump(struct ynl_sock *ys, + struct ethtool_pause_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_pause_get_list); + yds.cb = ethtool_pause_get_rsp_parse; + yds.rsp_cmd = 22; + yds.rsp_policy = ðtool_pause_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_PAUSE_GET, 1); + ys->req_policy = ðtool_pause_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_PAUSE_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_pause_get_list_free(yds.first); + return NULL; +} + +/* ETHTOOL_MSG_PAUSE_GET - notify */ +void ethtool_pause_get_ntf_free(struct ethtool_pause_get_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + ethtool_pause_stat_free(&rsp->obj.stats); + free(rsp); +} + +/* ============== ETHTOOL_MSG_PAUSE_SET ============== */ +/* ETHTOOL_MSG_PAUSE_SET - do */ +void ethtool_pause_set_req_free(struct ethtool_pause_set_req *req) +{ + ethtool_header_free(&req->header); + ethtool_pause_stat_free(&req->stats); + free(req); +} + +int ethtool_pause_set(struct ynl_sock *ys, struct ethtool_pause_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PAUSE_SET, 1); + ys->req_policy = ðtool_pause_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_PAUSE_HEADER, &req->header); + if (req->_present.autoneg) + mnl_attr_put_u8(nlh, ETHTOOL_A_PAUSE_AUTONEG, req->autoneg); + if (req->_present.rx) + mnl_attr_put_u8(nlh, ETHTOOL_A_PAUSE_RX, req->rx); + if (req->_present.tx) + mnl_attr_put_u8(nlh, ETHTOOL_A_PAUSE_TX, req->tx); + if (req->_present.stats) + ethtool_pause_stat_put(nlh, ETHTOOL_A_PAUSE_STATS, &req->stats); + if (req->_present.stats_src) + mnl_attr_put_u32(nlh, ETHTOOL_A_PAUSE_STATS_SRC, req->stats_src); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== ETHTOOL_MSG_EEE_GET ============== */ +/* ETHTOOL_MSG_EEE_GET - do */ +void ethtool_eee_get_req_free(struct ethtool_eee_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_eee_get_rsp_free(struct ethtool_eee_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + ethtool_bitset_free(&rsp->modes_ours); + ethtool_bitset_free(&rsp->modes_peer); + free(rsp); +} + +int ethtool_eee_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct ethtool_eee_get_rsp *dst; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_EEE_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_EEE_MODES_OURS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.modes_ours = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->modes_ours; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_EEE_MODES_PEER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.modes_peer = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->modes_peer; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_EEE_ACTIVE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.active = 1; + dst->active = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_EEE_ENABLED) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.enabled = 1; + dst->enabled = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_EEE_TX_LPI_ENABLED) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_lpi_enabled = 1; + dst->tx_lpi_enabled = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_EEE_TX_LPI_TIMER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_lpi_timer = 1; + dst->tx_lpi_timer = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct ethtool_eee_get_rsp * +ethtool_eee_get(struct ynl_sock *ys, struct ethtool_eee_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_eee_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_EEE_GET, 1); + ys->req_policy = ðtool_eee_nest; + yrs.yarg.rsp_policy = ðtool_eee_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_EEE_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_eee_get_rsp_parse; + yrs.rsp_cmd = 24; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_eee_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_EEE_GET - dump */ +void ethtool_eee_get_list_free(struct ethtool_eee_get_list *rsp) +{ + struct ethtool_eee_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + ethtool_bitset_free(&rsp->obj.modes_ours); + ethtool_bitset_free(&rsp->obj.modes_peer); + free(rsp); + } +} + +struct ethtool_eee_get_list * +ethtool_eee_get_dump(struct ynl_sock *ys, struct ethtool_eee_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_eee_get_list); + yds.cb = ethtool_eee_get_rsp_parse; + yds.rsp_cmd = 24; + yds.rsp_policy = ðtool_eee_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_EEE_GET, 1); + ys->req_policy = ðtool_eee_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_EEE_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_eee_get_list_free(yds.first); + return NULL; +} + +/* ETHTOOL_MSG_EEE_GET - notify */ +void ethtool_eee_get_ntf_free(struct ethtool_eee_get_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + ethtool_bitset_free(&rsp->obj.modes_ours); + ethtool_bitset_free(&rsp->obj.modes_peer); + free(rsp); +} + +/* ============== ETHTOOL_MSG_EEE_SET ============== */ +/* ETHTOOL_MSG_EEE_SET - do */ +void ethtool_eee_set_req_free(struct ethtool_eee_set_req *req) +{ + ethtool_header_free(&req->header); + ethtool_bitset_free(&req->modes_ours); + ethtool_bitset_free(&req->modes_peer); + free(req); +} + +int ethtool_eee_set(struct ynl_sock *ys, struct ethtool_eee_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_EEE_SET, 1); + ys->req_policy = ðtool_eee_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_EEE_HEADER, &req->header); + if (req->_present.modes_ours) + ethtool_bitset_put(nlh, ETHTOOL_A_EEE_MODES_OURS, &req->modes_ours); + if (req->_present.modes_peer) + ethtool_bitset_put(nlh, ETHTOOL_A_EEE_MODES_PEER, &req->modes_peer); + if (req->_present.active) + mnl_attr_put_u8(nlh, ETHTOOL_A_EEE_ACTIVE, req->active); + if (req->_present.enabled) + mnl_attr_put_u8(nlh, ETHTOOL_A_EEE_ENABLED, req->enabled); + if (req->_present.tx_lpi_enabled) + mnl_attr_put_u8(nlh, ETHTOOL_A_EEE_TX_LPI_ENABLED, req->tx_lpi_enabled); + if (req->_present.tx_lpi_timer) + mnl_attr_put_u32(nlh, ETHTOOL_A_EEE_TX_LPI_TIMER, req->tx_lpi_timer); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== ETHTOOL_MSG_TSINFO_GET ============== */ +/* ETHTOOL_MSG_TSINFO_GET - do */ +void ethtool_tsinfo_get_req_free(struct ethtool_tsinfo_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_tsinfo_get_rsp_free(struct ethtool_tsinfo_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + ethtool_bitset_free(&rsp->timestamping); + ethtool_bitset_free(&rsp->tx_types); + ethtool_bitset_free(&rsp->rx_filters); + free(rsp); +} + +int ethtool_tsinfo_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_tsinfo_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_TSINFO_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_TSINFO_TIMESTAMPING) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.timestamping = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->timestamping; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_TSINFO_TX_TYPES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_types = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->tx_types; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_TSINFO_RX_FILTERS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_filters = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->rx_filters; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_TSINFO_PHC_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.phc_index = 1; + dst->phc_index = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct ethtool_tsinfo_get_rsp * +ethtool_tsinfo_get(struct ynl_sock *ys, struct ethtool_tsinfo_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_tsinfo_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_TSINFO_GET, 1); + ys->req_policy = ðtool_tsinfo_nest; + yrs.yarg.rsp_policy = ðtool_tsinfo_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_TSINFO_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_tsinfo_get_rsp_parse; + yrs.rsp_cmd = 26; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_tsinfo_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_TSINFO_GET - dump */ +void ethtool_tsinfo_get_list_free(struct ethtool_tsinfo_get_list *rsp) +{ + struct ethtool_tsinfo_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + ethtool_bitset_free(&rsp->obj.timestamping); + ethtool_bitset_free(&rsp->obj.tx_types); + ethtool_bitset_free(&rsp->obj.rx_filters); + free(rsp); + } +} + +struct ethtool_tsinfo_get_list * +ethtool_tsinfo_get_dump(struct ynl_sock *ys, + struct ethtool_tsinfo_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_tsinfo_get_list); + yds.cb = ethtool_tsinfo_get_rsp_parse; + yds.rsp_cmd = 26; + yds.rsp_policy = ðtool_tsinfo_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_TSINFO_GET, 1); + ys->req_policy = ðtool_tsinfo_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_TSINFO_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_tsinfo_get_list_free(yds.first); + return NULL; +} + +/* ============== ETHTOOL_MSG_CABLE_TEST_ACT ============== */ +/* ETHTOOL_MSG_CABLE_TEST_ACT - do */ +void ethtool_cable_test_act_req_free(struct ethtool_cable_test_act_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +int ethtool_cable_test_act(struct ynl_sock *ys, + struct ethtool_cable_test_act_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_CABLE_TEST_ACT, 1); + ys->req_policy = ðtool_cable_test_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_CABLE_TEST_HEADER, &req->header); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== ETHTOOL_MSG_CABLE_TEST_TDR_ACT ============== */ +/* ETHTOOL_MSG_CABLE_TEST_TDR_ACT - do */ +void +ethtool_cable_test_tdr_act_req_free(struct ethtool_cable_test_tdr_act_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +int ethtool_cable_test_tdr_act(struct ynl_sock *ys, + struct ethtool_cable_test_tdr_act_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_CABLE_TEST_TDR_ACT, 1); + ys->req_policy = ðtool_cable_test_tdr_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_CABLE_TEST_TDR_HEADER, &req->header); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== ETHTOOL_MSG_TUNNEL_INFO_GET ============== */ +/* ETHTOOL_MSG_TUNNEL_INFO_GET - do */ +void ethtool_tunnel_info_get_req_free(struct ethtool_tunnel_info_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_tunnel_info_get_rsp_free(struct ethtool_tunnel_info_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + ethtool_tunnel_udp_free(&rsp->udp_ports); + free(rsp); +} + +int ethtool_tunnel_info_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_tunnel_info_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_TUNNEL_INFO_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_TUNNEL_INFO_UDP_PORTS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.udp_ports = 1; + + parg.rsp_policy = ðtool_tunnel_udp_nest; + parg.data = &dst->udp_ports; + if (ethtool_tunnel_udp_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return MNL_CB_OK; +} + +struct ethtool_tunnel_info_get_rsp * +ethtool_tunnel_info_get(struct ynl_sock *ys, + struct ethtool_tunnel_info_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_tunnel_info_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_TUNNEL_INFO_GET, 1); + ys->req_policy = ðtool_tunnel_info_nest; + yrs.yarg.rsp_policy = ðtool_tunnel_info_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_TUNNEL_INFO_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_tunnel_info_get_rsp_parse; + yrs.rsp_cmd = 29; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_tunnel_info_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_TUNNEL_INFO_GET - dump */ +void +ethtool_tunnel_info_get_list_free(struct ethtool_tunnel_info_get_list *rsp) +{ + struct ethtool_tunnel_info_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + ethtool_tunnel_udp_free(&rsp->obj.udp_ports); + free(rsp); + } +} + +struct ethtool_tunnel_info_get_list * +ethtool_tunnel_info_get_dump(struct ynl_sock *ys, + struct ethtool_tunnel_info_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_tunnel_info_get_list); + yds.cb = ethtool_tunnel_info_get_rsp_parse; + yds.rsp_cmd = 29; + yds.rsp_policy = ðtool_tunnel_info_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_TUNNEL_INFO_GET, 1); + ys->req_policy = ðtool_tunnel_info_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_TUNNEL_INFO_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_tunnel_info_get_list_free(yds.first); + return NULL; +} + +/* ============== ETHTOOL_MSG_FEC_GET ============== */ +/* ETHTOOL_MSG_FEC_GET - do */ +void ethtool_fec_get_req_free(struct ethtool_fec_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_fec_get_rsp_free(struct ethtool_fec_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + ethtool_bitset_free(&rsp->modes); + ethtool_fec_stat_free(&rsp->stats); + free(rsp); +} + +int ethtool_fec_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct ethtool_fec_get_rsp *dst; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_FEC_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_FEC_MODES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.modes = 1; + + parg.rsp_policy = ðtool_bitset_nest; + parg.data = &dst->modes; + if (ethtool_bitset_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_FEC_AUTO) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.auto_ = 1; + dst->auto_ = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_FEC_ACTIVE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.active = 1; + dst->active = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_FEC_STATS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.stats = 1; + + parg.rsp_policy = ðtool_fec_stat_nest; + parg.data = &dst->stats; + if (ethtool_fec_stat_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return MNL_CB_OK; +} + +struct ethtool_fec_get_rsp * +ethtool_fec_get(struct ynl_sock *ys, struct ethtool_fec_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_fec_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_FEC_GET, 1); + ys->req_policy = ðtool_fec_nest; + yrs.yarg.rsp_policy = ðtool_fec_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_FEC_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_fec_get_rsp_parse; + yrs.rsp_cmd = 30; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_fec_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_FEC_GET - dump */ +void ethtool_fec_get_list_free(struct ethtool_fec_get_list *rsp) +{ + struct ethtool_fec_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + ethtool_bitset_free(&rsp->obj.modes); + ethtool_fec_stat_free(&rsp->obj.stats); + free(rsp); + } +} + +struct ethtool_fec_get_list * +ethtool_fec_get_dump(struct ynl_sock *ys, struct ethtool_fec_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_fec_get_list); + yds.cb = ethtool_fec_get_rsp_parse; + yds.rsp_cmd = 30; + yds.rsp_policy = ðtool_fec_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_FEC_GET, 1); + ys->req_policy = ðtool_fec_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_FEC_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_fec_get_list_free(yds.first); + return NULL; +} + +/* ETHTOOL_MSG_FEC_GET - notify */ +void ethtool_fec_get_ntf_free(struct ethtool_fec_get_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + ethtool_bitset_free(&rsp->obj.modes); + ethtool_fec_stat_free(&rsp->obj.stats); + free(rsp); +} + +/* ============== ETHTOOL_MSG_FEC_SET ============== */ +/* ETHTOOL_MSG_FEC_SET - do */ +void ethtool_fec_set_req_free(struct ethtool_fec_set_req *req) +{ + ethtool_header_free(&req->header); + ethtool_bitset_free(&req->modes); + ethtool_fec_stat_free(&req->stats); + free(req); +} + +int ethtool_fec_set(struct ynl_sock *ys, struct ethtool_fec_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_FEC_SET, 1); + ys->req_policy = ðtool_fec_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_FEC_HEADER, &req->header); + if (req->_present.modes) + ethtool_bitset_put(nlh, ETHTOOL_A_FEC_MODES, &req->modes); + if (req->_present.auto_) + mnl_attr_put_u8(nlh, ETHTOOL_A_FEC_AUTO, req->auto_); + if (req->_present.active) + mnl_attr_put_u32(nlh, ETHTOOL_A_FEC_ACTIVE, req->active); + if (req->_present.stats) + ethtool_fec_stat_put(nlh, ETHTOOL_A_FEC_STATS, &req->stats); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== ETHTOOL_MSG_MODULE_EEPROM_GET ============== */ +/* ETHTOOL_MSG_MODULE_EEPROM_GET - do */ +void +ethtool_module_eeprom_get_req_free(struct ethtool_module_eeprom_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void +ethtool_module_eeprom_get_rsp_free(struct ethtool_module_eeprom_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + free(rsp->data); + free(rsp); +} + +int ethtool_module_eeprom_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_module_eeprom_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_MODULE_EEPROM_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_MODULE_EEPROM_OFFSET) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.offset = 1; + dst->offset = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_MODULE_EEPROM_LENGTH) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.length = 1; + dst->length = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_MODULE_EEPROM_PAGE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.page = 1; + dst->page = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_MODULE_EEPROM_BANK) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.bank = 1; + dst->bank = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.i2c_address = 1; + dst->i2c_address = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_MODULE_EEPROM_DATA) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.data_len = len; + dst->data = malloc(len); + memcpy(dst->data, mnl_attr_get_payload(attr), len); + } + } + + return MNL_CB_OK; +} + +struct ethtool_module_eeprom_get_rsp * +ethtool_module_eeprom_get(struct ynl_sock *ys, + struct ethtool_module_eeprom_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_module_eeprom_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_MODULE_EEPROM_GET, 1); + ys->req_policy = ðtool_module_eeprom_nest; + yrs.yarg.rsp_policy = ðtool_module_eeprom_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_MODULE_EEPROM_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_module_eeprom_get_rsp_parse; + yrs.rsp_cmd = 32; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_module_eeprom_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_MODULE_EEPROM_GET - dump */ +void +ethtool_module_eeprom_get_list_free(struct ethtool_module_eeprom_get_list *rsp) +{ + struct ethtool_module_eeprom_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + free(rsp->obj.data); + free(rsp); + } +} + +struct ethtool_module_eeprom_get_list * +ethtool_module_eeprom_get_dump(struct ynl_sock *ys, + struct ethtool_module_eeprom_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_module_eeprom_get_list); + yds.cb = ethtool_module_eeprom_get_rsp_parse; + yds.rsp_cmd = 32; + yds.rsp_policy = ðtool_module_eeprom_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_MODULE_EEPROM_GET, 1); + ys->req_policy = ðtool_module_eeprom_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_MODULE_EEPROM_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_module_eeprom_get_list_free(yds.first); + return NULL; +} + +/* ============== ETHTOOL_MSG_PHC_VCLOCKS_GET ============== */ +/* ETHTOOL_MSG_PHC_VCLOCKS_GET - do */ +void ethtool_phc_vclocks_get_req_free(struct ethtool_phc_vclocks_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_phc_vclocks_get_rsp_free(struct ethtool_phc_vclocks_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + free(rsp); +} + +int ethtool_phc_vclocks_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_phc_vclocks_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_PHC_VCLOCKS_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_PHC_VCLOCKS_NUM) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.num = 1; + dst->num = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct ethtool_phc_vclocks_get_rsp * +ethtool_phc_vclocks_get(struct ynl_sock *ys, + struct ethtool_phc_vclocks_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_phc_vclocks_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PHC_VCLOCKS_GET, 1); + ys->req_policy = ðtool_phc_vclocks_nest; + yrs.yarg.rsp_policy = ðtool_phc_vclocks_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_PHC_VCLOCKS_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_phc_vclocks_get_rsp_parse; + yrs.rsp_cmd = 34; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_phc_vclocks_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_PHC_VCLOCKS_GET - dump */ +void +ethtool_phc_vclocks_get_list_free(struct ethtool_phc_vclocks_get_list *rsp) +{ + struct ethtool_phc_vclocks_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + free(rsp); + } +} + +struct ethtool_phc_vclocks_get_list * +ethtool_phc_vclocks_get_dump(struct ynl_sock *ys, + struct ethtool_phc_vclocks_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_phc_vclocks_get_list); + yds.cb = ethtool_phc_vclocks_get_rsp_parse; + yds.rsp_cmd = 34; + yds.rsp_policy = ðtool_phc_vclocks_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_PHC_VCLOCKS_GET, 1); + ys->req_policy = ðtool_phc_vclocks_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_PHC_VCLOCKS_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_phc_vclocks_get_list_free(yds.first); + return NULL; +} + +/* ============== ETHTOOL_MSG_MODULE_GET ============== */ +/* ETHTOOL_MSG_MODULE_GET - do */ +void ethtool_module_get_req_free(struct ethtool_module_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_module_get_rsp_free(struct ethtool_module_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + free(rsp); +} + +int ethtool_module_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_module_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_MODULE_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_MODULE_POWER_MODE_POLICY) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.power_mode_policy = 1; + dst->power_mode_policy = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_MODULE_POWER_MODE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.power_mode = 1; + dst->power_mode = mnl_attr_get_u8(attr); + } + } + + return MNL_CB_OK; +} + +struct ethtool_module_get_rsp * +ethtool_module_get(struct ynl_sock *ys, struct ethtool_module_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_module_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_MODULE_GET, 1); + ys->req_policy = ðtool_module_nest; + yrs.yarg.rsp_policy = ðtool_module_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_MODULE_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_module_get_rsp_parse; + yrs.rsp_cmd = 35; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_module_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_MODULE_GET - dump */ +void ethtool_module_get_list_free(struct ethtool_module_get_list *rsp) +{ + struct ethtool_module_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + free(rsp); + } +} + +struct ethtool_module_get_list * +ethtool_module_get_dump(struct ynl_sock *ys, + struct ethtool_module_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_module_get_list); + yds.cb = ethtool_module_get_rsp_parse; + yds.rsp_cmd = 35; + yds.rsp_policy = ðtool_module_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_MODULE_GET, 1); + ys->req_policy = ðtool_module_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_MODULE_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_module_get_list_free(yds.first); + return NULL; +} + +/* ETHTOOL_MSG_MODULE_GET - notify */ +void ethtool_module_get_ntf_free(struct ethtool_module_get_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + free(rsp); +} + +/* ============== ETHTOOL_MSG_MODULE_SET ============== */ +/* ETHTOOL_MSG_MODULE_SET - do */ +void ethtool_module_set_req_free(struct ethtool_module_set_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +int ethtool_module_set(struct ynl_sock *ys, struct ethtool_module_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_MODULE_SET, 1); + ys->req_policy = ðtool_module_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_MODULE_HEADER, &req->header); + if (req->_present.power_mode_policy) + mnl_attr_put_u8(nlh, ETHTOOL_A_MODULE_POWER_MODE_POLICY, req->power_mode_policy); + if (req->_present.power_mode) + mnl_attr_put_u8(nlh, ETHTOOL_A_MODULE_POWER_MODE, req->power_mode); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== ETHTOOL_MSG_PSE_GET ============== */ +/* ETHTOOL_MSG_PSE_GET - do */ +void ethtool_pse_get_req_free(struct ethtool_pse_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_pse_get_rsp_free(struct ethtool_pse_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + free(rsp); +} + +int ethtool_pse_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct ethtool_pse_get_rsp *dst; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_PSE_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_PODL_PSE_ADMIN_STATE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.admin_state = 1; + dst->admin_state = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_PODL_PSE_ADMIN_CONTROL) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.admin_control = 1; + dst->admin_control = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_PODL_PSE_PW_D_STATUS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.pw_d_status = 1; + dst->pw_d_status = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct ethtool_pse_get_rsp * +ethtool_pse_get(struct ynl_sock *ys, struct ethtool_pse_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_pse_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PSE_GET, 1); + ys->req_policy = ðtool_pse_nest; + yrs.yarg.rsp_policy = ðtool_pse_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_PSE_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_pse_get_rsp_parse; + yrs.rsp_cmd = 37; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_pse_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_PSE_GET - dump */ +void ethtool_pse_get_list_free(struct ethtool_pse_get_list *rsp) +{ + struct ethtool_pse_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + free(rsp); + } +} + +struct ethtool_pse_get_list * +ethtool_pse_get_dump(struct ynl_sock *ys, struct ethtool_pse_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_pse_get_list); + yds.cb = ethtool_pse_get_rsp_parse; + yds.rsp_cmd = 37; + yds.rsp_policy = ðtool_pse_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_PSE_GET, 1); + ys->req_policy = ðtool_pse_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_PSE_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_pse_get_list_free(yds.first); + return NULL; +} + +/* ============== ETHTOOL_MSG_PSE_SET ============== */ +/* ETHTOOL_MSG_PSE_SET - do */ +void ethtool_pse_set_req_free(struct ethtool_pse_set_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +int ethtool_pse_set(struct ynl_sock *ys, struct ethtool_pse_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PSE_SET, 1); + ys->req_policy = ðtool_pse_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_PSE_HEADER, &req->header); + if (req->_present.admin_state) + mnl_attr_put_u32(nlh, ETHTOOL_A_PODL_PSE_ADMIN_STATE, req->admin_state); + if (req->_present.admin_control) + mnl_attr_put_u32(nlh, ETHTOOL_A_PODL_PSE_ADMIN_CONTROL, req->admin_control); + if (req->_present.pw_d_status) + mnl_attr_put_u32(nlh, ETHTOOL_A_PODL_PSE_PW_D_STATUS, req->pw_d_status); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== ETHTOOL_MSG_RSS_GET ============== */ +/* ETHTOOL_MSG_RSS_GET - do */ +void ethtool_rss_get_req_free(struct ethtool_rss_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_rss_get_rsp_free(struct ethtool_rss_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + free(rsp->indir); + free(rsp->hkey); + free(rsp); +} + +int ethtool_rss_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct ethtool_rss_get_rsp *dst; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_RSS_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_RSS_CONTEXT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.context = 1; + dst->context = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_RSS_HFUNC) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.hfunc = 1; + dst->hfunc = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_RSS_INDIR) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.indir_len = len; + dst->indir = malloc(len); + memcpy(dst->indir, mnl_attr_get_payload(attr), len); + } else if (type == ETHTOOL_A_RSS_HKEY) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.hkey_len = len; + dst->hkey = malloc(len); + memcpy(dst->hkey, mnl_attr_get_payload(attr), len); + } + } + + return MNL_CB_OK; +} + +struct ethtool_rss_get_rsp * +ethtool_rss_get(struct ynl_sock *ys, struct ethtool_rss_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_rss_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_RSS_GET, 1); + ys->req_policy = ðtool_rss_nest; + yrs.yarg.rsp_policy = ðtool_rss_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_RSS_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_rss_get_rsp_parse; + yrs.rsp_cmd = ETHTOOL_MSG_RSS_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_rss_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_RSS_GET - dump */ +void ethtool_rss_get_list_free(struct ethtool_rss_get_list *rsp) +{ + struct ethtool_rss_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + free(rsp->obj.indir); + free(rsp->obj.hkey); + free(rsp); + } +} + +struct ethtool_rss_get_list * +ethtool_rss_get_dump(struct ynl_sock *ys, struct ethtool_rss_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_rss_get_list); + yds.cb = ethtool_rss_get_rsp_parse; + yds.rsp_cmd = ETHTOOL_MSG_RSS_GET; + yds.rsp_policy = ðtool_rss_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_RSS_GET, 1); + ys->req_policy = ðtool_rss_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_RSS_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_rss_get_list_free(yds.first); + return NULL; +} + +/* ============== ETHTOOL_MSG_PLCA_GET_CFG ============== */ +/* ETHTOOL_MSG_PLCA_GET_CFG - do */ +void ethtool_plca_get_cfg_req_free(struct ethtool_plca_get_cfg_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_plca_get_cfg_rsp_free(struct ethtool_plca_get_cfg_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + free(rsp); +} + +int ethtool_plca_get_cfg_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_plca_get_cfg_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_PLCA_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_PLCA_VERSION) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.version = 1; + dst->version = mnl_attr_get_u16(attr); + } else if (type == ETHTOOL_A_PLCA_ENABLED) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.enabled = 1; + dst->enabled = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_PLCA_STATUS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.status = 1; + dst->status = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_PLCA_NODE_CNT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.node_cnt = 1; + dst->node_cnt = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_PLCA_NODE_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.node_id = 1; + dst->node_id = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_PLCA_TO_TMR) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.to_tmr = 1; + dst->to_tmr = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_PLCA_BURST_CNT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.burst_cnt = 1; + dst->burst_cnt = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_PLCA_BURST_TMR) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.burst_tmr = 1; + dst->burst_tmr = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct ethtool_plca_get_cfg_rsp * +ethtool_plca_get_cfg(struct ynl_sock *ys, struct ethtool_plca_get_cfg_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_plca_get_cfg_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PLCA_GET_CFG, 1); + ys->req_policy = ðtool_plca_nest; + yrs.yarg.rsp_policy = ðtool_plca_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_PLCA_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_plca_get_cfg_rsp_parse; + yrs.rsp_cmd = ETHTOOL_MSG_PLCA_GET_CFG; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_plca_get_cfg_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_PLCA_GET_CFG - dump */ +void ethtool_plca_get_cfg_list_free(struct ethtool_plca_get_cfg_list *rsp) +{ + struct ethtool_plca_get_cfg_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + free(rsp); + } +} + +struct ethtool_plca_get_cfg_list * +ethtool_plca_get_cfg_dump(struct ynl_sock *ys, + struct ethtool_plca_get_cfg_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_plca_get_cfg_list); + yds.cb = ethtool_plca_get_cfg_rsp_parse; + yds.rsp_cmd = ETHTOOL_MSG_PLCA_GET_CFG; + yds.rsp_policy = ðtool_plca_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_PLCA_GET_CFG, 1); + ys->req_policy = ðtool_plca_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_PLCA_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_plca_get_cfg_list_free(yds.first); + return NULL; +} + +/* ETHTOOL_MSG_PLCA_GET_CFG - notify */ +void ethtool_plca_get_cfg_ntf_free(struct ethtool_plca_get_cfg_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + free(rsp); +} + +/* ============== ETHTOOL_MSG_PLCA_SET_CFG ============== */ +/* ETHTOOL_MSG_PLCA_SET_CFG - do */ +void ethtool_plca_set_cfg_req_free(struct ethtool_plca_set_cfg_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +int ethtool_plca_set_cfg(struct ynl_sock *ys, + struct ethtool_plca_set_cfg_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PLCA_SET_CFG, 1); + ys->req_policy = ðtool_plca_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_PLCA_HEADER, &req->header); + if (req->_present.version) + mnl_attr_put_u16(nlh, ETHTOOL_A_PLCA_VERSION, req->version); + if (req->_present.enabled) + mnl_attr_put_u8(nlh, ETHTOOL_A_PLCA_ENABLED, req->enabled); + if (req->_present.status) + mnl_attr_put_u8(nlh, ETHTOOL_A_PLCA_STATUS, req->status); + if (req->_present.node_cnt) + mnl_attr_put_u32(nlh, ETHTOOL_A_PLCA_NODE_CNT, req->node_cnt); + if (req->_present.node_id) + mnl_attr_put_u32(nlh, ETHTOOL_A_PLCA_NODE_ID, req->node_id); + if (req->_present.to_tmr) + mnl_attr_put_u32(nlh, ETHTOOL_A_PLCA_TO_TMR, req->to_tmr); + if (req->_present.burst_cnt) + mnl_attr_put_u32(nlh, ETHTOOL_A_PLCA_BURST_CNT, req->burst_cnt); + if (req->_present.burst_tmr) + mnl_attr_put_u32(nlh, ETHTOOL_A_PLCA_BURST_TMR, req->burst_tmr); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== ETHTOOL_MSG_PLCA_GET_STATUS ============== */ +/* ETHTOOL_MSG_PLCA_GET_STATUS - do */ +void ethtool_plca_get_status_req_free(struct ethtool_plca_get_status_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_plca_get_status_rsp_free(struct ethtool_plca_get_status_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + free(rsp); +} + +int ethtool_plca_get_status_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_plca_get_status_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_PLCA_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_PLCA_VERSION) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.version = 1; + dst->version = mnl_attr_get_u16(attr); + } else if (type == ETHTOOL_A_PLCA_ENABLED) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.enabled = 1; + dst->enabled = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_PLCA_STATUS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.status = 1; + dst->status = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_PLCA_NODE_CNT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.node_cnt = 1; + dst->node_cnt = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_PLCA_NODE_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.node_id = 1; + dst->node_id = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_PLCA_TO_TMR) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.to_tmr = 1; + dst->to_tmr = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_PLCA_BURST_CNT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.burst_cnt = 1; + dst->burst_cnt = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_PLCA_BURST_TMR) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.burst_tmr = 1; + dst->burst_tmr = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct ethtool_plca_get_status_rsp * +ethtool_plca_get_status(struct ynl_sock *ys, + struct ethtool_plca_get_status_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_plca_get_status_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_PLCA_GET_STATUS, 1); + ys->req_policy = ðtool_plca_nest; + yrs.yarg.rsp_policy = ðtool_plca_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_PLCA_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_plca_get_status_rsp_parse; + yrs.rsp_cmd = 40; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_plca_get_status_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_PLCA_GET_STATUS - dump */ +void +ethtool_plca_get_status_list_free(struct ethtool_plca_get_status_list *rsp) +{ + struct ethtool_plca_get_status_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + free(rsp); + } +} + +struct ethtool_plca_get_status_list * +ethtool_plca_get_status_dump(struct ynl_sock *ys, + struct ethtool_plca_get_status_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_plca_get_status_list); + yds.cb = ethtool_plca_get_status_rsp_parse; + yds.rsp_cmd = 40; + yds.rsp_policy = ðtool_plca_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_PLCA_GET_STATUS, 1); + ys->req_policy = ðtool_plca_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_PLCA_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_plca_get_status_list_free(yds.first); + return NULL; +} + +/* ============== ETHTOOL_MSG_MM_GET ============== */ +/* ETHTOOL_MSG_MM_GET - do */ +void ethtool_mm_get_req_free(struct ethtool_mm_get_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +void ethtool_mm_get_rsp_free(struct ethtool_mm_get_rsp *rsp) +{ + ethtool_header_free(&rsp->header); + ethtool_mm_stat_free(&rsp->stats); + free(rsp); +} + +int ethtool_mm_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct ethtool_mm_get_rsp *dst; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_MM_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_MM_PMAC_ENABLED) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.pmac_enabled = 1; + dst->pmac_enabled = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_MM_TX_ENABLED) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_enabled = 1; + dst->tx_enabled = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_MM_TX_ACTIVE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_active = 1; + dst->tx_active = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_MM_TX_MIN_FRAG_SIZE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.tx_min_frag_size = 1; + dst->tx_min_frag_size = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_MM_RX_MIN_FRAG_SIZE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.rx_min_frag_size = 1; + dst->rx_min_frag_size = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_MM_VERIFY_ENABLED) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.verify_enabled = 1; + dst->verify_enabled = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_MM_VERIFY_TIME) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.verify_time = 1; + dst->verify_time = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_MM_MAX_VERIFY_TIME) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.max_verify_time = 1; + dst->max_verify_time = mnl_attr_get_u32(attr); + } else if (type == ETHTOOL_A_MM_STATS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.stats = 1; + + parg.rsp_policy = ðtool_mm_stat_nest; + parg.data = &dst->stats; + if (ethtool_mm_stat_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return MNL_CB_OK; +} + +struct ethtool_mm_get_rsp * +ethtool_mm_get(struct ynl_sock *ys, struct ethtool_mm_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct ethtool_mm_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_MM_GET, 1); + ys->req_policy = ðtool_mm_nest; + yrs.yarg.rsp_policy = ðtool_mm_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_MM_HEADER, &req->header); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = ethtool_mm_get_rsp_parse; + yrs.rsp_cmd = ETHTOOL_MSG_MM_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + ethtool_mm_get_rsp_free(rsp); + return NULL; +} + +/* ETHTOOL_MSG_MM_GET - dump */ +void ethtool_mm_get_list_free(struct ethtool_mm_get_list *rsp) +{ + struct ethtool_mm_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + ethtool_header_free(&rsp->obj.header); + ethtool_mm_stat_free(&rsp->obj.stats); + free(rsp); + } +} + +struct ethtool_mm_get_list * +ethtool_mm_get_dump(struct ynl_sock *ys, struct ethtool_mm_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct ethtool_mm_get_list); + yds.cb = ethtool_mm_get_rsp_parse; + yds.rsp_cmd = ETHTOOL_MSG_MM_GET; + yds.rsp_policy = ðtool_mm_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, ETHTOOL_MSG_MM_GET, 1); + ys->req_policy = ðtool_mm_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_MM_HEADER, &req->header); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + ethtool_mm_get_list_free(yds.first); + return NULL; +} + +/* ETHTOOL_MSG_MM_GET - notify */ +void ethtool_mm_get_ntf_free(struct ethtool_mm_get_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + ethtool_mm_stat_free(&rsp->obj.stats); + free(rsp); +} + +/* ============== ETHTOOL_MSG_MM_SET ============== */ +/* ETHTOOL_MSG_MM_SET - do */ +void ethtool_mm_set_req_free(struct ethtool_mm_set_req *req) +{ + ethtool_header_free(&req->header); + free(req); +} + +int ethtool_mm_set(struct ynl_sock *ys, struct ethtool_mm_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, ETHTOOL_MSG_MM_SET, 1); + ys->req_policy = ðtool_mm_nest; + + if (req->_present.header) + ethtool_header_put(nlh, ETHTOOL_A_MM_HEADER, &req->header); + if (req->_present.verify_enabled) + mnl_attr_put_u8(nlh, ETHTOOL_A_MM_VERIFY_ENABLED, req->verify_enabled); + if (req->_present.verify_time) + mnl_attr_put_u32(nlh, ETHTOOL_A_MM_VERIFY_TIME, req->verify_time); + if (req->_present.tx_enabled) + mnl_attr_put_u8(nlh, ETHTOOL_A_MM_TX_ENABLED, req->tx_enabled); + if (req->_present.pmac_enabled) + mnl_attr_put_u8(nlh, ETHTOOL_A_MM_PMAC_ENABLED, req->pmac_enabled); + if (req->_present.tx_min_frag_size) + mnl_attr_put_u32(nlh, ETHTOOL_A_MM_TX_MIN_FRAG_SIZE, req->tx_min_frag_size); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ETHTOOL_MSG_CABLE_TEST_NTF - event */ +int ethtool_cable_test_ntf_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ethtool_cable_test_ntf_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_CABLE_TEST_NTF_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_CABLE_TEST_NTF_STATUS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.status = 1; + dst->status = mnl_attr_get_u8(attr); + } + } + + return MNL_CB_OK; +} + +void ethtool_cable_test_ntf_free(struct ethtool_cable_test_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + free(rsp); +} + +/* ETHTOOL_MSG_CABLE_TEST_TDR_NTF - event */ +int ethtool_cable_test_tdr_ntf_rsp_parse(const struct nlmsghdr *nlh, + void *data) +{ + struct ethtool_cable_test_tdr_ntf_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == ETHTOOL_A_CABLE_TEST_TDR_NTF_HEADER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.header = 1; + + parg.rsp_policy = ðtool_header_nest; + parg.data = &dst->header; + if (ethtool_header_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == ETHTOOL_A_CABLE_TEST_TDR_NTF_STATUS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.status = 1; + dst->status = mnl_attr_get_u8(attr); + } else if (type == ETHTOOL_A_CABLE_TEST_TDR_NTF_NEST) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.nest = 1; + + parg.rsp_policy = ðtool_cable_nest_nest; + parg.data = &dst->nest; + if (ethtool_cable_nest_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return MNL_CB_OK; +} + +void ethtool_cable_test_tdr_ntf_free(struct ethtool_cable_test_tdr_ntf *rsp) +{ + ethtool_header_free(&rsp->obj.header); + ethtool_cable_nest_free(&rsp->obj.nest); + free(rsp); +} + +static const struct ynl_ntf_info ethtool_ntf_info[] = { + [ETHTOOL_MSG_LINKINFO_NTF] = { + .alloc_sz = sizeof(struct ethtool_linkinfo_get_ntf), + .cb = ethtool_linkinfo_get_rsp_parse, + .policy = ðtool_linkinfo_nest, + .free = (void *)ethtool_linkinfo_get_ntf_free, + }, + [ETHTOOL_MSG_LINKMODES_NTF] = { + .alloc_sz = sizeof(struct ethtool_linkmodes_get_ntf), + .cb = ethtool_linkmodes_get_rsp_parse, + .policy = ðtool_linkmodes_nest, + .free = (void *)ethtool_linkmodes_get_ntf_free, + }, + [ETHTOOL_MSG_DEBUG_NTF] = { + .alloc_sz = sizeof(struct ethtool_debug_get_ntf), + .cb = ethtool_debug_get_rsp_parse, + .policy = ðtool_debug_nest, + .free = (void *)ethtool_debug_get_ntf_free, + }, + [ETHTOOL_MSG_WOL_NTF] = { + .alloc_sz = sizeof(struct ethtool_wol_get_ntf), + .cb = ethtool_wol_get_rsp_parse, + .policy = ðtool_wol_nest, + .free = (void *)ethtool_wol_get_ntf_free, + }, + [ETHTOOL_MSG_FEATURES_NTF] = { + .alloc_sz = sizeof(struct ethtool_features_get_ntf), + .cb = ethtool_features_get_rsp_parse, + .policy = ðtool_features_nest, + .free = (void *)ethtool_features_get_ntf_free, + }, + [ETHTOOL_MSG_PRIVFLAGS_NTF] = { + .alloc_sz = sizeof(struct ethtool_privflags_get_ntf), + .cb = ethtool_privflags_get_rsp_parse, + .policy = ðtool_privflags_nest, + .free = (void *)ethtool_privflags_get_ntf_free, + }, + [ETHTOOL_MSG_RINGS_NTF] = { + .alloc_sz = sizeof(struct ethtool_rings_get_ntf), + .cb = ethtool_rings_get_rsp_parse, + .policy = ðtool_rings_nest, + .free = (void *)ethtool_rings_get_ntf_free, + }, + [ETHTOOL_MSG_CHANNELS_NTF] = { + .alloc_sz = sizeof(struct ethtool_channels_get_ntf), + .cb = ethtool_channels_get_rsp_parse, + .policy = ðtool_channels_nest, + .free = (void *)ethtool_channels_get_ntf_free, + }, + [ETHTOOL_MSG_COALESCE_NTF] = { + .alloc_sz = sizeof(struct ethtool_coalesce_get_ntf), + .cb = ethtool_coalesce_get_rsp_parse, + .policy = ðtool_coalesce_nest, + .free = (void *)ethtool_coalesce_get_ntf_free, + }, + [ETHTOOL_MSG_PAUSE_NTF] = { + .alloc_sz = sizeof(struct ethtool_pause_get_ntf), + .cb = ethtool_pause_get_rsp_parse, + .policy = ðtool_pause_nest, + .free = (void *)ethtool_pause_get_ntf_free, + }, + [ETHTOOL_MSG_EEE_NTF] = { + .alloc_sz = sizeof(struct ethtool_eee_get_ntf), + .cb = ethtool_eee_get_rsp_parse, + .policy = ðtool_eee_nest, + .free = (void *)ethtool_eee_get_ntf_free, + }, + [ETHTOOL_MSG_CABLE_TEST_NTF] = { + .alloc_sz = sizeof(struct ethtool_cable_test_ntf), + .cb = ethtool_cable_test_ntf_rsp_parse, + .policy = ðtool_cable_test_ntf_nest, + .free = (void *)ethtool_cable_test_ntf_free, + }, + [ETHTOOL_MSG_CABLE_TEST_TDR_NTF] = { + .alloc_sz = sizeof(struct ethtool_cable_test_tdr_ntf), + .cb = ethtool_cable_test_tdr_ntf_rsp_parse, + .policy = ðtool_cable_test_tdr_ntf_nest, + .free = (void *)ethtool_cable_test_tdr_ntf_free, + }, + [ETHTOOL_MSG_FEC_NTF] = { + .alloc_sz = sizeof(struct ethtool_fec_get_ntf), + .cb = ethtool_fec_get_rsp_parse, + .policy = ðtool_fec_nest, + .free = (void *)ethtool_fec_get_ntf_free, + }, + [ETHTOOL_MSG_MODULE_NTF] = { + .alloc_sz = sizeof(struct ethtool_module_get_ntf), + .cb = ethtool_module_get_rsp_parse, + .policy = ðtool_module_nest, + .free = (void *)ethtool_module_get_ntf_free, + }, + [ETHTOOL_MSG_PLCA_NTF] = { + .alloc_sz = sizeof(struct ethtool_plca_get_cfg_ntf), + .cb = ethtool_plca_get_cfg_rsp_parse, + .policy = ðtool_plca_nest, + .free = (void *)ethtool_plca_get_cfg_ntf_free, + }, + [ETHTOOL_MSG_MM_NTF] = { + .alloc_sz = sizeof(struct ethtool_mm_get_ntf), + .cb = ethtool_mm_get_rsp_parse, + .policy = ðtool_mm_nest, + .free = (void *)ethtool_mm_get_ntf_free, + }, +}; + +const struct ynl_family ynl_ethtool_family = { + .name = "ethtool", + .ntf_info = ethtool_ntf_info, + .ntf_info_size = MNL_ARRAY_SIZE(ethtool_ntf_info), +}; diff --git a/tools/net/ynl/generated/ethtool-user.h b/tools/net/ynl/generated/ethtool-user.h new file mode 100644 index 0000000000000..d7d4ba855f439 --- /dev/null +++ b/tools/net/ynl/generated/ethtool-user.h @@ -0,0 +1,5531 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/ethtool.yaml */ +/* YNL-GEN user header */ +/* YNL-ARG --user-header linux/ethtool_netlink.h --exclude-op stats-get */ + +#ifndef _LINUX_ETHTOOL_GEN_H +#define _LINUX_ETHTOOL_GEN_H + +#include <stdlib.h> +#include <string.h> +#include <linux/types.h> +#include <linux/ethtool.h> + +struct ynl_sock; + +extern const struct ynl_family ynl_ethtool_family; + +/* Enums */ +const char *ethtool_op_str(int op); +const char *ethtool_udp_tunnel_type_str(int value); +const char *ethtool_stringset_str(enum ethtool_stringset value); + +/* Common nested types */ +struct ethtool_header { + struct { + __u32 dev_index:1; + __u32 dev_name_len; + __u32 flags:1; + } _present; + + __u32 dev_index; + char *dev_name; + __u32 flags; +}; + +struct ethtool_pause_stat { + struct { + __u32 tx_frames:1; + __u32 rx_frames:1; + } _present; + + __u64 tx_frames; + __u64 rx_frames; +}; + +struct ethtool_cable_test_tdr_cfg { + struct { + __u32 first:1; + __u32 last:1; + __u32 step:1; + __u32 pair:1; + } _present; + + __u32 first; + __u32 last; + __u32 step; + __u8 pair; +}; + +struct ethtool_fec_stat { + struct { + __u32 corrected_len; + __u32 uncorr_len; + __u32 corr_bits_len; + } _present; + + void *corrected; + void *uncorr; + void *corr_bits; +}; + +struct ethtool_mm_stat { + struct { + __u32 reassembly_errors:1; + __u32 smd_errors:1; + __u32 reassembly_ok:1; + __u32 rx_frag_count:1; + __u32 tx_frag_count:1; + __u32 hold_count:1; + } _present; + + __u64 reassembly_errors; + __u64 smd_errors; + __u64 reassembly_ok; + __u64 rx_frag_count; + __u64 tx_frag_count; + __u64 hold_count; +}; + +struct ethtool_cable_result { + struct { + __u32 pair:1; + __u32 code:1; + } _present; + + __u8 pair; + __u8 code; +}; + +struct ethtool_cable_fault_length { + struct { + __u32 pair:1; + __u32 cm:1; + } _present; + + __u8 pair; + __u32 cm; +}; + +struct ethtool_bitset_bit { + struct { + __u32 index:1; + __u32 name_len; + __u32 value:1; + } _present; + + __u32 index; + char *name; +}; + +struct ethtool_tunnel_udp_entry { + struct { + __u32 port:1; + __u32 type:1; + } _present; + + __u16 port /* big-endian */; + __u32 type; +}; + +struct ethtool_string { + struct { + __u32 index:1; + __u32 value_len; + } _present; + + __u32 index; + char *value; +}; + +struct ethtool_cable_nest { + struct { + __u32 result:1; + __u32 fault_length:1; + } _present; + + struct ethtool_cable_result result; + struct ethtool_cable_fault_length fault_length; +}; + +struct ethtool_bitset_bits { + unsigned int n_bit; + struct ethtool_bitset_bit *bit; +}; + +struct ethtool_strings { + unsigned int n_string; + struct ethtool_string *string; +}; + +struct ethtool_bitset { + struct { + __u32 nomask:1; + __u32 size:1; + __u32 bits:1; + } _present; + + __u32 size; + struct ethtool_bitset_bits bits; +}; + +struct ethtool_stringset_ { + struct { + __u32 id:1; + __u32 count:1; + } _present; + + __u32 id; + __u32 count; + unsigned int n_strings; + struct ethtool_strings *strings; +}; + +struct ethtool_tunnel_udp_table { + struct { + __u32 size:1; + __u32 types:1; + } _present; + + __u32 size; + struct ethtool_bitset types; + unsigned int n_entry; + struct ethtool_tunnel_udp_entry *entry; +}; + +struct ethtool_stringsets { + unsigned int n_stringset; + struct ethtool_stringset_ *stringset; +}; + +struct ethtool_tunnel_udp { + struct { + __u32 table:1; + } _present; + + struct ethtool_tunnel_udp_table table; +}; + +/* ============== ETHTOOL_MSG_STRSET_GET ============== */ +/* ETHTOOL_MSG_STRSET_GET - do */ +struct ethtool_strset_get_req { + struct { + __u32 header:1; + __u32 stringsets:1; + __u32 counts_only:1; + } _present; + + struct ethtool_header header; + struct ethtool_stringsets stringsets; +}; + +static inline struct ethtool_strset_get_req *ethtool_strset_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_strset_get_req)); +} +void ethtool_strset_get_req_free(struct ethtool_strset_get_req *req); + +static inline void +ethtool_strset_get_req_set_header_dev_index(struct ethtool_strset_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_strset_get_req_set_header_dev_name(struct ethtool_strset_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_strset_get_req_set_header_flags(struct ethtool_strset_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +__ethtool_strset_get_req_set_stringsets_stringset(struct ethtool_strset_get_req *req, + struct ethtool_stringset_ *stringset, + unsigned int n_stringset) +{ + free(req->stringsets.stringset); + req->stringsets.stringset = stringset; + req->stringsets.n_stringset = n_stringset; +} +static inline void +ethtool_strset_get_req_set_counts_only(struct ethtool_strset_get_req *req) +{ + req->_present.counts_only = 1; +} + +struct ethtool_strset_get_rsp { + struct { + __u32 header:1; + __u32 stringsets:1; + } _present; + + struct ethtool_header header; + struct ethtool_stringsets stringsets; +}; + +void ethtool_strset_get_rsp_free(struct ethtool_strset_get_rsp *rsp); + +/* + * Get string set from the kernel. + */ +struct ethtool_strset_get_rsp * +ethtool_strset_get(struct ynl_sock *ys, struct ethtool_strset_get_req *req); + +/* ETHTOOL_MSG_STRSET_GET - dump */ +struct ethtool_strset_get_req_dump { + struct { + __u32 header:1; + __u32 stringsets:1; + __u32 counts_only:1; + } _present; + + struct ethtool_header header; + struct ethtool_stringsets stringsets; +}; + +static inline struct ethtool_strset_get_req_dump * +ethtool_strset_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_strset_get_req_dump)); +} +void ethtool_strset_get_req_dump_free(struct ethtool_strset_get_req_dump *req); + +static inline void +ethtool_strset_get_req_dump_set_header_dev_index(struct ethtool_strset_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_strset_get_req_dump_set_header_dev_name(struct ethtool_strset_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_strset_get_req_dump_set_header_flags(struct ethtool_strset_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +__ethtool_strset_get_req_dump_set_stringsets_stringset(struct ethtool_strset_get_req_dump *req, + struct ethtool_stringset_ *stringset, + unsigned int n_stringset) +{ + free(req->stringsets.stringset); + req->stringsets.stringset = stringset; + req->stringsets.n_stringset = n_stringset; +} +static inline void +ethtool_strset_get_req_dump_set_counts_only(struct ethtool_strset_get_req_dump *req) +{ + req->_present.counts_only = 1; +} + +struct ethtool_strset_get_list { + struct ethtool_strset_get_list *next; + struct ethtool_strset_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_strset_get_list_free(struct ethtool_strset_get_list *rsp); + +struct ethtool_strset_get_list * +ethtool_strset_get_dump(struct ynl_sock *ys, + struct ethtool_strset_get_req_dump *req); + +/* ============== ETHTOOL_MSG_LINKINFO_GET ============== */ +/* ETHTOOL_MSG_LINKINFO_GET - do */ +struct ethtool_linkinfo_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_linkinfo_get_req * +ethtool_linkinfo_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_linkinfo_get_req)); +} +void ethtool_linkinfo_get_req_free(struct ethtool_linkinfo_get_req *req); + +static inline void +ethtool_linkinfo_get_req_set_header_dev_index(struct ethtool_linkinfo_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_linkinfo_get_req_set_header_dev_name(struct ethtool_linkinfo_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_linkinfo_get_req_set_header_flags(struct ethtool_linkinfo_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_linkinfo_get_rsp { + struct { + __u32 header:1; + __u32 port:1; + __u32 phyaddr:1; + __u32 tp_mdix:1; + __u32 tp_mdix_ctrl:1; + __u32 transceiver:1; + } _present; + + struct ethtool_header header; + __u8 port; + __u8 phyaddr; + __u8 tp_mdix; + __u8 tp_mdix_ctrl; + __u8 transceiver; +}; + +void ethtool_linkinfo_get_rsp_free(struct ethtool_linkinfo_get_rsp *rsp); + +/* + * Get link info. + */ +struct ethtool_linkinfo_get_rsp * +ethtool_linkinfo_get(struct ynl_sock *ys, struct ethtool_linkinfo_get_req *req); + +/* ETHTOOL_MSG_LINKINFO_GET - dump */ +struct ethtool_linkinfo_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_linkinfo_get_req_dump * +ethtool_linkinfo_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_linkinfo_get_req_dump)); +} +void +ethtool_linkinfo_get_req_dump_free(struct ethtool_linkinfo_get_req_dump *req); + +static inline void +ethtool_linkinfo_get_req_dump_set_header_dev_index(struct ethtool_linkinfo_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_linkinfo_get_req_dump_set_header_dev_name(struct ethtool_linkinfo_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_linkinfo_get_req_dump_set_header_flags(struct ethtool_linkinfo_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_linkinfo_get_list { + struct ethtool_linkinfo_get_list *next; + struct ethtool_linkinfo_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_linkinfo_get_list_free(struct ethtool_linkinfo_get_list *rsp); + +struct ethtool_linkinfo_get_list * +ethtool_linkinfo_get_dump(struct ynl_sock *ys, + struct ethtool_linkinfo_get_req_dump *req); + +/* ETHTOOL_MSG_LINKINFO_GET - notify */ +struct ethtool_linkinfo_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_linkinfo_get_ntf *ntf); + struct ethtool_linkinfo_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_linkinfo_get_ntf_free(struct ethtool_linkinfo_get_ntf *rsp); + +/* ============== ETHTOOL_MSG_LINKINFO_SET ============== */ +/* ETHTOOL_MSG_LINKINFO_SET - do */ +struct ethtool_linkinfo_set_req { + struct { + __u32 header:1; + __u32 port:1; + __u32 phyaddr:1; + __u32 tp_mdix:1; + __u32 tp_mdix_ctrl:1; + __u32 transceiver:1; + } _present; + + struct ethtool_header header; + __u8 port; + __u8 phyaddr; + __u8 tp_mdix; + __u8 tp_mdix_ctrl; + __u8 transceiver; +}; + +static inline struct ethtool_linkinfo_set_req * +ethtool_linkinfo_set_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_linkinfo_set_req)); +} +void ethtool_linkinfo_set_req_free(struct ethtool_linkinfo_set_req *req); + +static inline void +ethtool_linkinfo_set_req_set_header_dev_index(struct ethtool_linkinfo_set_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_linkinfo_set_req_set_header_dev_name(struct ethtool_linkinfo_set_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_linkinfo_set_req_set_header_flags(struct ethtool_linkinfo_set_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +ethtool_linkinfo_set_req_set_port(struct ethtool_linkinfo_set_req *req, + __u8 port) +{ + req->_present.port = 1; + req->port = port; +} +static inline void +ethtool_linkinfo_set_req_set_phyaddr(struct ethtool_linkinfo_set_req *req, + __u8 phyaddr) +{ + req->_present.phyaddr = 1; + req->phyaddr = phyaddr; +} +static inline void +ethtool_linkinfo_set_req_set_tp_mdix(struct ethtool_linkinfo_set_req *req, + __u8 tp_mdix) +{ + req->_present.tp_mdix = 1; + req->tp_mdix = tp_mdix; +} +static inline void +ethtool_linkinfo_set_req_set_tp_mdix_ctrl(struct ethtool_linkinfo_set_req *req, + __u8 tp_mdix_ctrl) +{ + req->_present.tp_mdix_ctrl = 1; + req->tp_mdix_ctrl = tp_mdix_ctrl; +} +static inline void +ethtool_linkinfo_set_req_set_transceiver(struct ethtool_linkinfo_set_req *req, + __u8 transceiver) +{ + req->_present.transceiver = 1; + req->transceiver = transceiver; +} + +/* + * Set link info. + */ +int ethtool_linkinfo_set(struct ynl_sock *ys, + struct ethtool_linkinfo_set_req *req); + +/* ============== ETHTOOL_MSG_LINKMODES_GET ============== */ +/* ETHTOOL_MSG_LINKMODES_GET - do */ +struct ethtool_linkmodes_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_linkmodes_get_req * +ethtool_linkmodes_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_linkmodes_get_req)); +} +void ethtool_linkmodes_get_req_free(struct ethtool_linkmodes_get_req *req); + +static inline void +ethtool_linkmodes_get_req_set_header_dev_index(struct ethtool_linkmodes_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_linkmodes_get_req_set_header_dev_name(struct ethtool_linkmodes_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_linkmodes_get_req_set_header_flags(struct ethtool_linkmodes_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_linkmodes_get_rsp { + struct { + __u32 header:1; + __u32 autoneg:1; + __u32 ours:1; + __u32 peer:1; + __u32 speed:1; + __u32 duplex:1; + __u32 master_slave_cfg:1; + __u32 master_slave_state:1; + __u32 lanes:1; + __u32 rate_matching:1; + } _present; + + struct ethtool_header header; + __u8 autoneg; + struct ethtool_bitset ours; + struct ethtool_bitset peer; + __u32 speed; + __u8 duplex; + __u8 master_slave_cfg; + __u8 master_slave_state; + __u32 lanes; + __u8 rate_matching; +}; + +void ethtool_linkmodes_get_rsp_free(struct ethtool_linkmodes_get_rsp *rsp); + +/* + * Get link modes. + */ +struct ethtool_linkmodes_get_rsp * +ethtool_linkmodes_get(struct ynl_sock *ys, + struct ethtool_linkmodes_get_req *req); + +/* ETHTOOL_MSG_LINKMODES_GET - dump */ +struct ethtool_linkmodes_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_linkmodes_get_req_dump * +ethtool_linkmodes_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_linkmodes_get_req_dump)); +} +void +ethtool_linkmodes_get_req_dump_free(struct ethtool_linkmodes_get_req_dump *req); + +static inline void +ethtool_linkmodes_get_req_dump_set_header_dev_index(struct ethtool_linkmodes_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_linkmodes_get_req_dump_set_header_dev_name(struct ethtool_linkmodes_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_linkmodes_get_req_dump_set_header_flags(struct ethtool_linkmodes_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_linkmodes_get_list { + struct ethtool_linkmodes_get_list *next; + struct ethtool_linkmodes_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_linkmodes_get_list_free(struct ethtool_linkmodes_get_list *rsp); + +struct ethtool_linkmodes_get_list * +ethtool_linkmodes_get_dump(struct ynl_sock *ys, + struct ethtool_linkmodes_get_req_dump *req); + +/* ETHTOOL_MSG_LINKMODES_GET - notify */ +struct ethtool_linkmodes_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_linkmodes_get_ntf *ntf); + struct ethtool_linkmodes_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_linkmodes_get_ntf_free(struct ethtool_linkmodes_get_ntf *rsp); + +/* ============== ETHTOOL_MSG_LINKMODES_SET ============== */ +/* ETHTOOL_MSG_LINKMODES_SET - do */ +struct ethtool_linkmodes_set_req { + struct { + __u32 header:1; + __u32 autoneg:1; + __u32 ours:1; + __u32 peer:1; + __u32 speed:1; + __u32 duplex:1; + __u32 master_slave_cfg:1; + __u32 master_slave_state:1; + __u32 lanes:1; + __u32 rate_matching:1; + } _present; + + struct ethtool_header header; + __u8 autoneg; + struct ethtool_bitset ours; + struct ethtool_bitset peer; + __u32 speed; + __u8 duplex; + __u8 master_slave_cfg; + __u8 master_slave_state; + __u32 lanes; + __u8 rate_matching; +}; + +static inline struct ethtool_linkmodes_set_req * +ethtool_linkmodes_set_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_linkmodes_set_req)); +} +void ethtool_linkmodes_set_req_free(struct ethtool_linkmodes_set_req *req); + +static inline void +ethtool_linkmodes_set_req_set_header_dev_index(struct ethtool_linkmodes_set_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_linkmodes_set_req_set_header_dev_name(struct ethtool_linkmodes_set_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_linkmodes_set_req_set_header_flags(struct ethtool_linkmodes_set_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +ethtool_linkmodes_set_req_set_autoneg(struct ethtool_linkmodes_set_req *req, + __u8 autoneg) +{ + req->_present.autoneg = 1; + req->autoneg = autoneg; +} +static inline void +ethtool_linkmodes_set_req_set_ours_nomask(struct ethtool_linkmodes_set_req *req) +{ + req->_present.ours = 1; + req->ours._present.nomask = 1; +} +static inline void +ethtool_linkmodes_set_req_set_ours_size(struct ethtool_linkmodes_set_req *req, + __u32 size) +{ + req->_present.ours = 1; + req->ours._present.size = 1; + req->ours.size = size; +} +static inline void +__ethtool_linkmodes_set_req_set_ours_bits_bit(struct ethtool_linkmodes_set_req *req, + struct ethtool_bitset_bit *bit, + unsigned int n_bit) +{ + free(req->ours.bits.bit); + req->ours.bits.bit = bit; + req->ours.bits.n_bit = n_bit; +} +static inline void +ethtool_linkmodes_set_req_set_peer_nomask(struct ethtool_linkmodes_set_req *req) +{ + req->_present.peer = 1; + req->peer._present.nomask = 1; +} +static inline void +ethtool_linkmodes_set_req_set_peer_size(struct ethtool_linkmodes_set_req *req, + __u32 size) +{ + req->_present.peer = 1; + req->peer._present.size = 1; + req->peer.size = size; +} +static inline void +__ethtool_linkmodes_set_req_set_peer_bits_bit(struct ethtool_linkmodes_set_req *req, + struct ethtool_bitset_bit *bit, + unsigned int n_bit) +{ + free(req->peer.bits.bit); + req->peer.bits.bit = bit; + req->peer.bits.n_bit = n_bit; +} +static inline void +ethtool_linkmodes_set_req_set_speed(struct ethtool_linkmodes_set_req *req, + __u32 speed) +{ + req->_present.speed = 1; + req->speed = speed; +} +static inline void +ethtool_linkmodes_set_req_set_duplex(struct ethtool_linkmodes_set_req *req, + __u8 duplex) +{ + req->_present.duplex = 1; + req->duplex = duplex; +} +static inline void +ethtool_linkmodes_set_req_set_master_slave_cfg(struct ethtool_linkmodes_set_req *req, + __u8 master_slave_cfg) +{ + req->_present.master_slave_cfg = 1; + req->master_slave_cfg = master_slave_cfg; +} +static inline void +ethtool_linkmodes_set_req_set_master_slave_state(struct ethtool_linkmodes_set_req *req, + __u8 master_slave_state) +{ + req->_present.master_slave_state = 1; + req->master_slave_state = master_slave_state; +} +static inline void +ethtool_linkmodes_set_req_set_lanes(struct ethtool_linkmodes_set_req *req, + __u32 lanes) +{ + req->_present.lanes = 1; + req->lanes = lanes; +} +static inline void +ethtool_linkmodes_set_req_set_rate_matching(struct ethtool_linkmodes_set_req *req, + __u8 rate_matching) +{ + req->_present.rate_matching = 1; + req->rate_matching = rate_matching; +} + +/* + * Set link modes. + */ +int ethtool_linkmodes_set(struct ynl_sock *ys, + struct ethtool_linkmodes_set_req *req); + +/* ============== ETHTOOL_MSG_LINKSTATE_GET ============== */ +/* ETHTOOL_MSG_LINKSTATE_GET - do */ +struct ethtool_linkstate_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_linkstate_get_req * +ethtool_linkstate_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_linkstate_get_req)); +} +void ethtool_linkstate_get_req_free(struct ethtool_linkstate_get_req *req); + +static inline void +ethtool_linkstate_get_req_set_header_dev_index(struct ethtool_linkstate_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_linkstate_get_req_set_header_dev_name(struct ethtool_linkstate_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_linkstate_get_req_set_header_flags(struct ethtool_linkstate_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_linkstate_get_rsp { + struct { + __u32 header:1; + __u32 link:1; + __u32 sqi:1; + __u32 sqi_max:1; + __u32 ext_state:1; + __u32 ext_substate:1; + __u32 ext_down_cnt:1; + } _present; + + struct ethtool_header header; + __u8 link; + __u32 sqi; + __u32 sqi_max; + __u8 ext_state; + __u8 ext_substate; + __u32 ext_down_cnt; +}; + +void ethtool_linkstate_get_rsp_free(struct ethtool_linkstate_get_rsp *rsp); + +/* + * Get link state. + */ +struct ethtool_linkstate_get_rsp * +ethtool_linkstate_get(struct ynl_sock *ys, + struct ethtool_linkstate_get_req *req); + +/* ETHTOOL_MSG_LINKSTATE_GET - dump */ +struct ethtool_linkstate_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_linkstate_get_req_dump * +ethtool_linkstate_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_linkstate_get_req_dump)); +} +void +ethtool_linkstate_get_req_dump_free(struct ethtool_linkstate_get_req_dump *req); + +static inline void +ethtool_linkstate_get_req_dump_set_header_dev_index(struct ethtool_linkstate_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_linkstate_get_req_dump_set_header_dev_name(struct ethtool_linkstate_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_linkstate_get_req_dump_set_header_flags(struct ethtool_linkstate_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_linkstate_get_list { + struct ethtool_linkstate_get_list *next; + struct ethtool_linkstate_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_linkstate_get_list_free(struct ethtool_linkstate_get_list *rsp); + +struct ethtool_linkstate_get_list * +ethtool_linkstate_get_dump(struct ynl_sock *ys, + struct ethtool_linkstate_get_req_dump *req); + +/* ============== ETHTOOL_MSG_DEBUG_GET ============== */ +/* ETHTOOL_MSG_DEBUG_GET - do */ +struct ethtool_debug_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_debug_get_req *ethtool_debug_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_debug_get_req)); +} +void ethtool_debug_get_req_free(struct ethtool_debug_get_req *req); + +static inline void +ethtool_debug_get_req_set_header_dev_index(struct ethtool_debug_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_debug_get_req_set_header_dev_name(struct ethtool_debug_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_debug_get_req_set_header_flags(struct ethtool_debug_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_debug_get_rsp { + struct { + __u32 header:1; + __u32 msgmask:1; + } _present; + + struct ethtool_header header; + struct ethtool_bitset msgmask; +}; + +void ethtool_debug_get_rsp_free(struct ethtool_debug_get_rsp *rsp); + +/* + * Get debug message mask. + */ +struct ethtool_debug_get_rsp * +ethtool_debug_get(struct ynl_sock *ys, struct ethtool_debug_get_req *req); + +/* ETHTOOL_MSG_DEBUG_GET - dump */ +struct ethtool_debug_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_debug_get_req_dump * +ethtool_debug_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_debug_get_req_dump)); +} +void ethtool_debug_get_req_dump_free(struct ethtool_debug_get_req_dump *req); + +static inline void +ethtool_debug_get_req_dump_set_header_dev_index(struct ethtool_debug_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_debug_get_req_dump_set_header_dev_name(struct ethtool_debug_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_debug_get_req_dump_set_header_flags(struct ethtool_debug_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_debug_get_list { + struct ethtool_debug_get_list *next; + struct ethtool_debug_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_debug_get_list_free(struct ethtool_debug_get_list *rsp); + +struct ethtool_debug_get_list * +ethtool_debug_get_dump(struct ynl_sock *ys, + struct ethtool_debug_get_req_dump *req); + +/* ETHTOOL_MSG_DEBUG_GET - notify */ +struct ethtool_debug_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_debug_get_ntf *ntf); + struct ethtool_debug_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_debug_get_ntf_free(struct ethtool_debug_get_ntf *rsp); + +/* ============== ETHTOOL_MSG_DEBUG_SET ============== */ +/* ETHTOOL_MSG_DEBUG_SET - do */ +struct ethtool_debug_set_req { + struct { + __u32 header:1; + __u32 msgmask:1; + } _present; + + struct ethtool_header header; + struct ethtool_bitset msgmask; +}; + +static inline struct ethtool_debug_set_req *ethtool_debug_set_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_debug_set_req)); +} +void ethtool_debug_set_req_free(struct ethtool_debug_set_req *req); + +static inline void +ethtool_debug_set_req_set_header_dev_index(struct ethtool_debug_set_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_debug_set_req_set_header_dev_name(struct ethtool_debug_set_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_debug_set_req_set_header_flags(struct ethtool_debug_set_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +ethtool_debug_set_req_set_msgmask_nomask(struct ethtool_debug_set_req *req) +{ + req->_present.msgmask = 1; + req->msgmask._present.nomask = 1; +} +static inline void +ethtool_debug_set_req_set_msgmask_size(struct ethtool_debug_set_req *req, + __u32 size) +{ + req->_present.msgmask = 1; + req->msgmask._present.size = 1; + req->msgmask.size = size; +} +static inline void +__ethtool_debug_set_req_set_msgmask_bits_bit(struct ethtool_debug_set_req *req, + struct ethtool_bitset_bit *bit, + unsigned int n_bit) +{ + free(req->msgmask.bits.bit); + req->msgmask.bits.bit = bit; + req->msgmask.bits.n_bit = n_bit; +} + +/* + * Set debug message mask. + */ +int ethtool_debug_set(struct ynl_sock *ys, struct ethtool_debug_set_req *req); + +/* ============== ETHTOOL_MSG_WOL_GET ============== */ +/* ETHTOOL_MSG_WOL_GET - do */ +struct ethtool_wol_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_wol_get_req *ethtool_wol_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_wol_get_req)); +} +void ethtool_wol_get_req_free(struct ethtool_wol_get_req *req); + +static inline void +ethtool_wol_get_req_set_header_dev_index(struct ethtool_wol_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_wol_get_req_set_header_dev_name(struct ethtool_wol_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_wol_get_req_set_header_flags(struct ethtool_wol_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_wol_get_rsp { + struct { + __u32 header:1; + __u32 modes:1; + __u32 sopass_len; + } _present; + + struct ethtool_header header; + struct ethtool_bitset modes; + void *sopass; +}; + +void ethtool_wol_get_rsp_free(struct ethtool_wol_get_rsp *rsp); + +/* + * Get WOL params. + */ +struct ethtool_wol_get_rsp * +ethtool_wol_get(struct ynl_sock *ys, struct ethtool_wol_get_req *req); + +/* ETHTOOL_MSG_WOL_GET - dump */ +struct ethtool_wol_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_wol_get_req_dump * +ethtool_wol_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_wol_get_req_dump)); +} +void ethtool_wol_get_req_dump_free(struct ethtool_wol_get_req_dump *req); + +static inline void +ethtool_wol_get_req_dump_set_header_dev_index(struct ethtool_wol_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_wol_get_req_dump_set_header_dev_name(struct ethtool_wol_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_wol_get_req_dump_set_header_flags(struct ethtool_wol_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_wol_get_list { + struct ethtool_wol_get_list *next; + struct ethtool_wol_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_wol_get_list_free(struct ethtool_wol_get_list *rsp); + +struct ethtool_wol_get_list * +ethtool_wol_get_dump(struct ynl_sock *ys, struct ethtool_wol_get_req_dump *req); + +/* ETHTOOL_MSG_WOL_GET - notify */ +struct ethtool_wol_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_wol_get_ntf *ntf); + struct ethtool_wol_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_wol_get_ntf_free(struct ethtool_wol_get_ntf *rsp); + +/* ============== ETHTOOL_MSG_WOL_SET ============== */ +/* ETHTOOL_MSG_WOL_SET - do */ +struct ethtool_wol_set_req { + struct { + __u32 header:1; + __u32 modes:1; + __u32 sopass_len; + } _present; + + struct ethtool_header header; + struct ethtool_bitset modes; + void *sopass; +}; + +static inline struct ethtool_wol_set_req *ethtool_wol_set_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_wol_set_req)); +} +void ethtool_wol_set_req_free(struct ethtool_wol_set_req *req); + +static inline void +ethtool_wol_set_req_set_header_dev_index(struct ethtool_wol_set_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_wol_set_req_set_header_dev_name(struct ethtool_wol_set_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_wol_set_req_set_header_flags(struct ethtool_wol_set_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +ethtool_wol_set_req_set_modes_nomask(struct ethtool_wol_set_req *req) +{ + req->_present.modes = 1; + req->modes._present.nomask = 1; +} +static inline void +ethtool_wol_set_req_set_modes_size(struct ethtool_wol_set_req *req, __u32 size) +{ + req->_present.modes = 1; + req->modes._present.size = 1; + req->modes.size = size; +} +static inline void +__ethtool_wol_set_req_set_modes_bits_bit(struct ethtool_wol_set_req *req, + struct ethtool_bitset_bit *bit, + unsigned int n_bit) +{ + free(req->modes.bits.bit); + req->modes.bits.bit = bit; + req->modes.bits.n_bit = n_bit; +} +static inline void +ethtool_wol_set_req_set_sopass(struct ethtool_wol_set_req *req, + const void *sopass, size_t len) +{ + free(req->sopass); + req->sopass = malloc(req->_present.sopass_len); + memcpy(req->sopass, sopass, req->_present.sopass_len); +} + +/* + * Set WOL params. + */ +int ethtool_wol_set(struct ynl_sock *ys, struct ethtool_wol_set_req *req); + +/* ============== ETHTOOL_MSG_FEATURES_GET ============== */ +/* ETHTOOL_MSG_FEATURES_GET - do */ +struct ethtool_features_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_features_get_req * +ethtool_features_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_features_get_req)); +} +void ethtool_features_get_req_free(struct ethtool_features_get_req *req); + +static inline void +ethtool_features_get_req_set_header_dev_index(struct ethtool_features_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_features_get_req_set_header_dev_name(struct ethtool_features_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_features_get_req_set_header_flags(struct ethtool_features_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_features_get_rsp { + struct { + __u32 header:1; + __u32 hw:1; + __u32 wanted:1; + __u32 active:1; + __u32 nochange:1; + } _present; + + struct ethtool_header header; + struct ethtool_bitset hw; + struct ethtool_bitset wanted; + struct ethtool_bitset active; + struct ethtool_bitset nochange; +}; + +void ethtool_features_get_rsp_free(struct ethtool_features_get_rsp *rsp); + +/* + * Get features. + */ +struct ethtool_features_get_rsp * +ethtool_features_get(struct ynl_sock *ys, struct ethtool_features_get_req *req); + +/* ETHTOOL_MSG_FEATURES_GET - dump */ +struct ethtool_features_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_features_get_req_dump * +ethtool_features_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_features_get_req_dump)); +} +void +ethtool_features_get_req_dump_free(struct ethtool_features_get_req_dump *req); + +static inline void +ethtool_features_get_req_dump_set_header_dev_index(struct ethtool_features_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_features_get_req_dump_set_header_dev_name(struct ethtool_features_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_features_get_req_dump_set_header_flags(struct ethtool_features_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_features_get_list { + struct ethtool_features_get_list *next; + struct ethtool_features_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_features_get_list_free(struct ethtool_features_get_list *rsp); + +struct ethtool_features_get_list * +ethtool_features_get_dump(struct ynl_sock *ys, + struct ethtool_features_get_req_dump *req); + +/* ETHTOOL_MSG_FEATURES_GET - notify */ +struct ethtool_features_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_features_get_ntf *ntf); + struct ethtool_features_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_features_get_ntf_free(struct ethtool_features_get_ntf *rsp); + +/* ============== ETHTOOL_MSG_FEATURES_SET ============== */ +/* ETHTOOL_MSG_FEATURES_SET - do */ +struct ethtool_features_set_req { + struct { + __u32 header:1; + __u32 hw:1; + __u32 wanted:1; + __u32 active:1; + __u32 nochange:1; + } _present; + + struct ethtool_header header; + struct ethtool_bitset hw; + struct ethtool_bitset wanted; + struct ethtool_bitset active; + struct ethtool_bitset nochange; +}; + +static inline struct ethtool_features_set_req * +ethtool_features_set_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_features_set_req)); +} +void ethtool_features_set_req_free(struct ethtool_features_set_req *req); + +static inline void +ethtool_features_set_req_set_header_dev_index(struct ethtool_features_set_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_features_set_req_set_header_dev_name(struct ethtool_features_set_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_features_set_req_set_header_flags(struct ethtool_features_set_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +ethtool_features_set_req_set_hw_nomask(struct ethtool_features_set_req *req) +{ + req->_present.hw = 1; + req->hw._present.nomask = 1; +} +static inline void +ethtool_features_set_req_set_hw_size(struct ethtool_features_set_req *req, + __u32 size) +{ + req->_present.hw = 1; + req->hw._present.size = 1; + req->hw.size = size; +} +static inline void +__ethtool_features_set_req_set_hw_bits_bit(struct ethtool_features_set_req *req, + struct ethtool_bitset_bit *bit, + unsigned int n_bit) +{ + free(req->hw.bits.bit); + req->hw.bits.bit = bit; + req->hw.bits.n_bit = n_bit; +} +static inline void +ethtool_features_set_req_set_wanted_nomask(struct ethtool_features_set_req *req) +{ + req->_present.wanted = 1; + req->wanted._present.nomask = 1; +} +static inline void +ethtool_features_set_req_set_wanted_size(struct ethtool_features_set_req *req, + __u32 size) +{ + req->_present.wanted = 1; + req->wanted._present.size = 1; + req->wanted.size = size; +} +static inline void +__ethtool_features_set_req_set_wanted_bits_bit(struct ethtool_features_set_req *req, + struct ethtool_bitset_bit *bit, + unsigned int n_bit) +{ + free(req->wanted.bits.bit); + req->wanted.bits.bit = bit; + req->wanted.bits.n_bit = n_bit; +} +static inline void +ethtool_features_set_req_set_active_nomask(struct ethtool_features_set_req *req) +{ + req->_present.active = 1; + req->active._present.nomask = 1; +} +static inline void +ethtool_features_set_req_set_active_size(struct ethtool_features_set_req *req, + __u32 size) +{ + req->_present.active = 1; + req->active._present.size = 1; + req->active.size = size; +} +static inline void +__ethtool_features_set_req_set_active_bits_bit(struct ethtool_features_set_req *req, + struct ethtool_bitset_bit *bit, + unsigned int n_bit) +{ + free(req->active.bits.bit); + req->active.bits.bit = bit; + req->active.bits.n_bit = n_bit; +} +static inline void +ethtool_features_set_req_set_nochange_nomask(struct ethtool_features_set_req *req) +{ + req->_present.nochange = 1; + req->nochange._present.nomask = 1; +} +static inline void +ethtool_features_set_req_set_nochange_size(struct ethtool_features_set_req *req, + __u32 size) +{ + req->_present.nochange = 1; + req->nochange._present.size = 1; + req->nochange.size = size; +} +static inline void +__ethtool_features_set_req_set_nochange_bits_bit(struct ethtool_features_set_req *req, + struct ethtool_bitset_bit *bit, + unsigned int n_bit) +{ + free(req->nochange.bits.bit); + req->nochange.bits.bit = bit; + req->nochange.bits.n_bit = n_bit; +} + +struct ethtool_features_set_rsp { + struct { + __u32 header:1; + __u32 hw:1; + __u32 wanted:1; + __u32 active:1; + __u32 nochange:1; + } _present; + + struct ethtool_header header; + struct ethtool_bitset hw; + struct ethtool_bitset wanted; + struct ethtool_bitset active; + struct ethtool_bitset nochange; +}; + +void ethtool_features_set_rsp_free(struct ethtool_features_set_rsp *rsp); + +/* + * Set features. + */ +struct ethtool_features_set_rsp * +ethtool_features_set(struct ynl_sock *ys, struct ethtool_features_set_req *req); + +/* ============== ETHTOOL_MSG_PRIVFLAGS_GET ============== */ +/* ETHTOOL_MSG_PRIVFLAGS_GET - do */ +struct ethtool_privflags_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_privflags_get_req * +ethtool_privflags_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_privflags_get_req)); +} +void ethtool_privflags_get_req_free(struct ethtool_privflags_get_req *req); + +static inline void +ethtool_privflags_get_req_set_header_dev_index(struct ethtool_privflags_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_privflags_get_req_set_header_dev_name(struct ethtool_privflags_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_privflags_get_req_set_header_flags(struct ethtool_privflags_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_privflags_get_rsp { + struct { + __u32 header:1; + __u32 flags:1; + } _present; + + struct ethtool_header header; + struct ethtool_bitset flags; +}; + +void ethtool_privflags_get_rsp_free(struct ethtool_privflags_get_rsp *rsp); + +/* + * Get device private flags. + */ +struct ethtool_privflags_get_rsp * +ethtool_privflags_get(struct ynl_sock *ys, + struct ethtool_privflags_get_req *req); + +/* ETHTOOL_MSG_PRIVFLAGS_GET - dump */ +struct ethtool_privflags_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_privflags_get_req_dump * +ethtool_privflags_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_privflags_get_req_dump)); +} +void +ethtool_privflags_get_req_dump_free(struct ethtool_privflags_get_req_dump *req); + +static inline void +ethtool_privflags_get_req_dump_set_header_dev_index(struct ethtool_privflags_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_privflags_get_req_dump_set_header_dev_name(struct ethtool_privflags_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_privflags_get_req_dump_set_header_flags(struct ethtool_privflags_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_privflags_get_list { + struct ethtool_privflags_get_list *next; + struct ethtool_privflags_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_privflags_get_list_free(struct ethtool_privflags_get_list *rsp); + +struct ethtool_privflags_get_list * +ethtool_privflags_get_dump(struct ynl_sock *ys, + struct ethtool_privflags_get_req_dump *req); + +/* ETHTOOL_MSG_PRIVFLAGS_GET - notify */ +struct ethtool_privflags_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_privflags_get_ntf *ntf); + struct ethtool_privflags_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_privflags_get_ntf_free(struct ethtool_privflags_get_ntf *rsp); + +/* ============== ETHTOOL_MSG_PRIVFLAGS_SET ============== */ +/* ETHTOOL_MSG_PRIVFLAGS_SET - do */ +struct ethtool_privflags_set_req { + struct { + __u32 header:1; + __u32 flags:1; + } _present; + + struct ethtool_header header; + struct ethtool_bitset flags; +}; + +static inline struct ethtool_privflags_set_req * +ethtool_privflags_set_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_privflags_set_req)); +} +void ethtool_privflags_set_req_free(struct ethtool_privflags_set_req *req); + +static inline void +ethtool_privflags_set_req_set_header_dev_index(struct ethtool_privflags_set_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_privflags_set_req_set_header_dev_name(struct ethtool_privflags_set_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_privflags_set_req_set_header_flags(struct ethtool_privflags_set_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +ethtool_privflags_set_req_set_flags_nomask(struct ethtool_privflags_set_req *req) +{ + req->_present.flags = 1; + req->flags._present.nomask = 1; +} +static inline void +ethtool_privflags_set_req_set_flags_size(struct ethtool_privflags_set_req *req, + __u32 size) +{ + req->_present.flags = 1; + req->flags._present.size = 1; + req->flags.size = size; +} +static inline void +__ethtool_privflags_set_req_set_flags_bits_bit(struct ethtool_privflags_set_req *req, + struct ethtool_bitset_bit *bit, + unsigned int n_bit) +{ + free(req->flags.bits.bit); + req->flags.bits.bit = bit; + req->flags.bits.n_bit = n_bit; +} + +/* + * Set device private flags. + */ +int ethtool_privflags_set(struct ynl_sock *ys, + struct ethtool_privflags_set_req *req); + +/* ============== ETHTOOL_MSG_RINGS_GET ============== */ +/* ETHTOOL_MSG_RINGS_GET - do */ +struct ethtool_rings_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_rings_get_req *ethtool_rings_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_rings_get_req)); +} +void ethtool_rings_get_req_free(struct ethtool_rings_get_req *req); + +static inline void +ethtool_rings_get_req_set_header_dev_index(struct ethtool_rings_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_rings_get_req_set_header_dev_name(struct ethtool_rings_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_rings_get_req_set_header_flags(struct ethtool_rings_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_rings_get_rsp { + struct { + __u32 header:1; + __u32 rx_max:1; + __u32 rx_mini_max:1; + __u32 rx_jumbo_max:1; + __u32 tx_max:1; + __u32 rx:1; + __u32 rx_mini:1; + __u32 rx_jumbo:1; + __u32 tx:1; + __u32 rx_buf_len:1; + __u32 tcp_data_split:1; + __u32 cqe_size:1; + __u32 tx_push:1; + __u32 rx_push:1; + __u32 tx_push_buf_len:1; + __u32 tx_push_buf_len_max:1; + } _present; + + struct ethtool_header header; + __u32 rx_max; + __u32 rx_mini_max; + __u32 rx_jumbo_max; + __u32 tx_max; + __u32 rx; + __u32 rx_mini; + __u32 rx_jumbo; + __u32 tx; + __u32 rx_buf_len; + __u8 tcp_data_split; + __u32 cqe_size; + __u8 tx_push; + __u8 rx_push; + __u32 tx_push_buf_len; + __u32 tx_push_buf_len_max; +}; + +void ethtool_rings_get_rsp_free(struct ethtool_rings_get_rsp *rsp); + +/* + * Get ring params. + */ +struct ethtool_rings_get_rsp * +ethtool_rings_get(struct ynl_sock *ys, struct ethtool_rings_get_req *req); + +/* ETHTOOL_MSG_RINGS_GET - dump */ +struct ethtool_rings_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_rings_get_req_dump * +ethtool_rings_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_rings_get_req_dump)); +} +void ethtool_rings_get_req_dump_free(struct ethtool_rings_get_req_dump *req); + +static inline void +ethtool_rings_get_req_dump_set_header_dev_index(struct ethtool_rings_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_rings_get_req_dump_set_header_dev_name(struct ethtool_rings_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_rings_get_req_dump_set_header_flags(struct ethtool_rings_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_rings_get_list { + struct ethtool_rings_get_list *next; + struct ethtool_rings_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_rings_get_list_free(struct ethtool_rings_get_list *rsp); + +struct ethtool_rings_get_list * +ethtool_rings_get_dump(struct ynl_sock *ys, + struct ethtool_rings_get_req_dump *req); + +/* ETHTOOL_MSG_RINGS_GET - notify */ +struct ethtool_rings_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_rings_get_ntf *ntf); + struct ethtool_rings_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_rings_get_ntf_free(struct ethtool_rings_get_ntf *rsp); + +/* ============== ETHTOOL_MSG_RINGS_SET ============== */ +/* ETHTOOL_MSG_RINGS_SET - do */ +struct ethtool_rings_set_req { + struct { + __u32 header:1; + __u32 rx_max:1; + __u32 rx_mini_max:1; + __u32 rx_jumbo_max:1; + __u32 tx_max:1; + __u32 rx:1; + __u32 rx_mini:1; + __u32 rx_jumbo:1; + __u32 tx:1; + __u32 rx_buf_len:1; + __u32 tcp_data_split:1; + __u32 cqe_size:1; + __u32 tx_push:1; + __u32 rx_push:1; + __u32 tx_push_buf_len:1; + __u32 tx_push_buf_len_max:1; + } _present; + + struct ethtool_header header; + __u32 rx_max; + __u32 rx_mini_max; + __u32 rx_jumbo_max; + __u32 tx_max; + __u32 rx; + __u32 rx_mini; + __u32 rx_jumbo; + __u32 tx; + __u32 rx_buf_len; + __u8 tcp_data_split; + __u32 cqe_size; + __u8 tx_push; + __u8 rx_push; + __u32 tx_push_buf_len; + __u32 tx_push_buf_len_max; +}; + +static inline struct ethtool_rings_set_req *ethtool_rings_set_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_rings_set_req)); +} +void ethtool_rings_set_req_free(struct ethtool_rings_set_req *req); + +static inline void +ethtool_rings_set_req_set_header_dev_index(struct ethtool_rings_set_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_rings_set_req_set_header_dev_name(struct ethtool_rings_set_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_rings_set_req_set_header_flags(struct ethtool_rings_set_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +ethtool_rings_set_req_set_rx_max(struct ethtool_rings_set_req *req, + __u32 rx_max) +{ + req->_present.rx_max = 1; + req->rx_max = rx_max; +} +static inline void +ethtool_rings_set_req_set_rx_mini_max(struct ethtool_rings_set_req *req, + __u32 rx_mini_max) +{ + req->_present.rx_mini_max = 1; + req->rx_mini_max = rx_mini_max; +} +static inline void +ethtool_rings_set_req_set_rx_jumbo_max(struct ethtool_rings_set_req *req, + __u32 rx_jumbo_max) +{ + req->_present.rx_jumbo_max = 1; + req->rx_jumbo_max = rx_jumbo_max; +} +static inline void +ethtool_rings_set_req_set_tx_max(struct ethtool_rings_set_req *req, + __u32 tx_max) +{ + req->_present.tx_max = 1; + req->tx_max = tx_max; +} +static inline void +ethtool_rings_set_req_set_rx(struct ethtool_rings_set_req *req, __u32 rx) +{ + req->_present.rx = 1; + req->rx = rx; +} +static inline void +ethtool_rings_set_req_set_rx_mini(struct ethtool_rings_set_req *req, + __u32 rx_mini) +{ + req->_present.rx_mini = 1; + req->rx_mini = rx_mini; +} +static inline void +ethtool_rings_set_req_set_rx_jumbo(struct ethtool_rings_set_req *req, + __u32 rx_jumbo) +{ + req->_present.rx_jumbo = 1; + req->rx_jumbo = rx_jumbo; +} +static inline void +ethtool_rings_set_req_set_tx(struct ethtool_rings_set_req *req, __u32 tx) +{ + req->_present.tx = 1; + req->tx = tx; +} +static inline void +ethtool_rings_set_req_set_rx_buf_len(struct ethtool_rings_set_req *req, + __u32 rx_buf_len) +{ + req->_present.rx_buf_len = 1; + req->rx_buf_len = rx_buf_len; +} +static inline void +ethtool_rings_set_req_set_tcp_data_split(struct ethtool_rings_set_req *req, + __u8 tcp_data_split) +{ + req->_present.tcp_data_split = 1; + req->tcp_data_split = tcp_data_split; +} +static inline void +ethtool_rings_set_req_set_cqe_size(struct ethtool_rings_set_req *req, + __u32 cqe_size) +{ + req->_present.cqe_size = 1; + req->cqe_size = cqe_size; +} +static inline void +ethtool_rings_set_req_set_tx_push(struct ethtool_rings_set_req *req, + __u8 tx_push) +{ + req->_present.tx_push = 1; + req->tx_push = tx_push; +} +static inline void +ethtool_rings_set_req_set_rx_push(struct ethtool_rings_set_req *req, + __u8 rx_push) +{ + req->_present.rx_push = 1; + req->rx_push = rx_push; +} +static inline void +ethtool_rings_set_req_set_tx_push_buf_len(struct ethtool_rings_set_req *req, + __u32 tx_push_buf_len) +{ + req->_present.tx_push_buf_len = 1; + req->tx_push_buf_len = tx_push_buf_len; +} +static inline void +ethtool_rings_set_req_set_tx_push_buf_len_max(struct ethtool_rings_set_req *req, + __u32 tx_push_buf_len_max) +{ + req->_present.tx_push_buf_len_max = 1; + req->tx_push_buf_len_max = tx_push_buf_len_max; +} + +/* + * Set ring params. + */ +int ethtool_rings_set(struct ynl_sock *ys, struct ethtool_rings_set_req *req); + +/* ============== ETHTOOL_MSG_CHANNELS_GET ============== */ +/* ETHTOOL_MSG_CHANNELS_GET - do */ +struct ethtool_channels_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_channels_get_req * +ethtool_channels_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_channels_get_req)); +} +void ethtool_channels_get_req_free(struct ethtool_channels_get_req *req); + +static inline void +ethtool_channels_get_req_set_header_dev_index(struct ethtool_channels_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_channels_get_req_set_header_dev_name(struct ethtool_channels_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_channels_get_req_set_header_flags(struct ethtool_channels_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_channels_get_rsp { + struct { + __u32 header:1; + __u32 rx_max:1; + __u32 tx_max:1; + __u32 other_max:1; + __u32 combined_max:1; + __u32 rx_count:1; + __u32 tx_count:1; + __u32 other_count:1; + __u32 combined_count:1; + } _present; + + struct ethtool_header header; + __u32 rx_max; + __u32 tx_max; + __u32 other_max; + __u32 combined_max; + __u32 rx_count; + __u32 tx_count; + __u32 other_count; + __u32 combined_count; +}; + +void ethtool_channels_get_rsp_free(struct ethtool_channels_get_rsp *rsp); + +/* + * Get channel params. + */ +struct ethtool_channels_get_rsp * +ethtool_channels_get(struct ynl_sock *ys, struct ethtool_channels_get_req *req); + +/* ETHTOOL_MSG_CHANNELS_GET - dump */ +struct ethtool_channels_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_channels_get_req_dump * +ethtool_channels_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_channels_get_req_dump)); +} +void +ethtool_channels_get_req_dump_free(struct ethtool_channels_get_req_dump *req); + +static inline void +ethtool_channels_get_req_dump_set_header_dev_index(struct ethtool_channels_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_channels_get_req_dump_set_header_dev_name(struct ethtool_channels_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_channels_get_req_dump_set_header_flags(struct ethtool_channels_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_channels_get_list { + struct ethtool_channels_get_list *next; + struct ethtool_channels_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_channels_get_list_free(struct ethtool_channels_get_list *rsp); + +struct ethtool_channels_get_list * +ethtool_channels_get_dump(struct ynl_sock *ys, + struct ethtool_channels_get_req_dump *req); + +/* ETHTOOL_MSG_CHANNELS_GET - notify */ +struct ethtool_channels_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_channels_get_ntf *ntf); + struct ethtool_channels_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_channels_get_ntf_free(struct ethtool_channels_get_ntf *rsp); + +/* ============== ETHTOOL_MSG_CHANNELS_SET ============== */ +/* ETHTOOL_MSG_CHANNELS_SET - do */ +struct ethtool_channels_set_req { + struct { + __u32 header:1; + __u32 rx_max:1; + __u32 tx_max:1; + __u32 other_max:1; + __u32 combined_max:1; + __u32 rx_count:1; + __u32 tx_count:1; + __u32 other_count:1; + __u32 combined_count:1; + } _present; + + struct ethtool_header header; + __u32 rx_max; + __u32 tx_max; + __u32 other_max; + __u32 combined_max; + __u32 rx_count; + __u32 tx_count; + __u32 other_count; + __u32 combined_count; +}; + +static inline struct ethtool_channels_set_req * +ethtool_channels_set_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_channels_set_req)); +} +void ethtool_channels_set_req_free(struct ethtool_channels_set_req *req); + +static inline void +ethtool_channels_set_req_set_header_dev_index(struct ethtool_channels_set_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_channels_set_req_set_header_dev_name(struct ethtool_channels_set_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_channels_set_req_set_header_flags(struct ethtool_channels_set_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +ethtool_channels_set_req_set_rx_max(struct ethtool_channels_set_req *req, + __u32 rx_max) +{ + req->_present.rx_max = 1; + req->rx_max = rx_max; +} +static inline void +ethtool_channels_set_req_set_tx_max(struct ethtool_channels_set_req *req, + __u32 tx_max) +{ + req->_present.tx_max = 1; + req->tx_max = tx_max; +} +static inline void +ethtool_channels_set_req_set_other_max(struct ethtool_channels_set_req *req, + __u32 other_max) +{ + req->_present.other_max = 1; + req->other_max = other_max; +} +static inline void +ethtool_channels_set_req_set_combined_max(struct ethtool_channels_set_req *req, + __u32 combined_max) +{ + req->_present.combined_max = 1; + req->combined_max = combined_max; +} +static inline void +ethtool_channels_set_req_set_rx_count(struct ethtool_channels_set_req *req, + __u32 rx_count) +{ + req->_present.rx_count = 1; + req->rx_count = rx_count; +} +static inline void +ethtool_channels_set_req_set_tx_count(struct ethtool_channels_set_req *req, + __u32 tx_count) +{ + req->_present.tx_count = 1; + req->tx_count = tx_count; +} +static inline void +ethtool_channels_set_req_set_other_count(struct ethtool_channels_set_req *req, + __u32 other_count) +{ + req->_present.other_count = 1; + req->other_count = other_count; +} +static inline void +ethtool_channels_set_req_set_combined_count(struct ethtool_channels_set_req *req, + __u32 combined_count) +{ + req->_present.combined_count = 1; + req->combined_count = combined_count; +} + +/* + * Set channel params. + */ +int ethtool_channels_set(struct ynl_sock *ys, + struct ethtool_channels_set_req *req); + +/* ============== ETHTOOL_MSG_COALESCE_GET ============== */ +/* ETHTOOL_MSG_COALESCE_GET - do */ +struct ethtool_coalesce_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_coalesce_get_req * +ethtool_coalesce_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_coalesce_get_req)); +} +void ethtool_coalesce_get_req_free(struct ethtool_coalesce_get_req *req); + +static inline void +ethtool_coalesce_get_req_set_header_dev_index(struct ethtool_coalesce_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_coalesce_get_req_set_header_dev_name(struct ethtool_coalesce_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_coalesce_get_req_set_header_flags(struct ethtool_coalesce_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_coalesce_get_rsp { + struct { + __u32 header:1; + __u32 rx_usecs:1; + __u32 rx_max_frames:1; + __u32 rx_usecs_irq:1; + __u32 rx_max_frames_irq:1; + __u32 tx_usecs:1; + __u32 tx_max_frames:1; + __u32 tx_usecs_irq:1; + __u32 tx_max_frames_irq:1; + __u32 stats_block_usecs:1; + __u32 use_adaptive_rx:1; + __u32 use_adaptive_tx:1; + __u32 pkt_rate_low:1; + __u32 rx_usecs_low:1; + __u32 rx_max_frames_low:1; + __u32 tx_usecs_low:1; + __u32 tx_max_frames_low:1; + __u32 pkt_rate_high:1; + __u32 rx_usecs_high:1; + __u32 rx_max_frames_high:1; + __u32 tx_usecs_high:1; + __u32 tx_max_frames_high:1; + __u32 rate_sample_interval:1; + __u32 use_cqe_mode_tx:1; + __u32 use_cqe_mode_rx:1; + __u32 tx_aggr_max_bytes:1; + __u32 tx_aggr_max_frames:1; + __u32 tx_aggr_time_usecs:1; + } _present; + + struct ethtool_header header; + __u32 rx_usecs; + __u32 rx_max_frames; + __u32 rx_usecs_irq; + __u32 rx_max_frames_irq; + __u32 tx_usecs; + __u32 tx_max_frames; + __u32 tx_usecs_irq; + __u32 tx_max_frames_irq; + __u32 stats_block_usecs; + __u8 use_adaptive_rx; + __u8 use_adaptive_tx; + __u32 pkt_rate_low; + __u32 rx_usecs_low; + __u32 rx_max_frames_low; + __u32 tx_usecs_low; + __u32 tx_max_frames_low; + __u32 pkt_rate_high; + __u32 rx_usecs_high; + __u32 rx_max_frames_high; + __u32 tx_usecs_high; + __u32 tx_max_frames_high; + __u32 rate_sample_interval; + __u8 use_cqe_mode_tx; + __u8 use_cqe_mode_rx; + __u32 tx_aggr_max_bytes; + __u32 tx_aggr_max_frames; + __u32 tx_aggr_time_usecs; +}; + +void ethtool_coalesce_get_rsp_free(struct ethtool_coalesce_get_rsp *rsp); + +/* + * Get coalesce params. + */ +struct ethtool_coalesce_get_rsp * +ethtool_coalesce_get(struct ynl_sock *ys, struct ethtool_coalesce_get_req *req); + +/* ETHTOOL_MSG_COALESCE_GET - dump */ +struct ethtool_coalesce_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_coalesce_get_req_dump * +ethtool_coalesce_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_coalesce_get_req_dump)); +} +void +ethtool_coalesce_get_req_dump_free(struct ethtool_coalesce_get_req_dump *req); + +static inline void +ethtool_coalesce_get_req_dump_set_header_dev_index(struct ethtool_coalesce_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_coalesce_get_req_dump_set_header_dev_name(struct ethtool_coalesce_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_coalesce_get_req_dump_set_header_flags(struct ethtool_coalesce_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_coalesce_get_list { + struct ethtool_coalesce_get_list *next; + struct ethtool_coalesce_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_coalesce_get_list_free(struct ethtool_coalesce_get_list *rsp); + +struct ethtool_coalesce_get_list * +ethtool_coalesce_get_dump(struct ynl_sock *ys, + struct ethtool_coalesce_get_req_dump *req); + +/* ETHTOOL_MSG_COALESCE_GET - notify */ +struct ethtool_coalesce_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_coalesce_get_ntf *ntf); + struct ethtool_coalesce_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_coalesce_get_ntf_free(struct ethtool_coalesce_get_ntf *rsp); + +/* ============== ETHTOOL_MSG_COALESCE_SET ============== */ +/* ETHTOOL_MSG_COALESCE_SET - do */ +struct ethtool_coalesce_set_req { + struct { + __u32 header:1; + __u32 rx_usecs:1; + __u32 rx_max_frames:1; + __u32 rx_usecs_irq:1; + __u32 rx_max_frames_irq:1; + __u32 tx_usecs:1; + __u32 tx_max_frames:1; + __u32 tx_usecs_irq:1; + __u32 tx_max_frames_irq:1; + __u32 stats_block_usecs:1; + __u32 use_adaptive_rx:1; + __u32 use_adaptive_tx:1; + __u32 pkt_rate_low:1; + __u32 rx_usecs_low:1; + __u32 rx_max_frames_low:1; + __u32 tx_usecs_low:1; + __u32 tx_max_frames_low:1; + __u32 pkt_rate_high:1; + __u32 rx_usecs_high:1; + __u32 rx_max_frames_high:1; + __u32 tx_usecs_high:1; + __u32 tx_max_frames_high:1; + __u32 rate_sample_interval:1; + __u32 use_cqe_mode_tx:1; + __u32 use_cqe_mode_rx:1; + __u32 tx_aggr_max_bytes:1; + __u32 tx_aggr_max_frames:1; + __u32 tx_aggr_time_usecs:1; + } _present; + + struct ethtool_header header; + __u32 rx_usecs; + __u32 rx_max_frames; + __u32 rx_usecs_irq; + __u32 rx_max_frames_irq; + __u32 tx_usecs; + __u32 tx_max_frames; + __u32 tx_usecs_irq; + __u32 tx_max_frames_irq; + __u32 stats_block_usecs; + __u8 use_adaptive_rx; + __u8 use_adaptive_tx; + __u32 pkt_rate_low; + __u32 rx_usecs_low; + __u32 rx_max_frames_low; + __u32 tx_usecs_low; + __u32 tx_max_frames_low; + __u32 pkt_rate_high; + __u32 rx_usecs_high; + __u32 rx_max_frames_high; + __u32 tx_usecs_high; + __u32 tx_max_frames_high; + __u32 rate_sample_interval; + __u8 use_cqe_mode_tx; + __u8 use_cqe_mode_rx; + __u32 tx_aggr_max_bytes; + __u32 tx_aggr_max_frames; + __u32 tx_aggr_time_usecs; +}; + +static inline struct ethtool_coalesce_set_req * +ethtool_coalesce_set_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_coalesce_set_req)); +} +void ethtool_coalesce_set_req_free(struct ethtool_coalesce_set_req *req); + +static inline void +ethtool_coalesce_set_req_set_header_dev_index(struct ethtool_coalesce_set_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_coalesce_set_req_set_header_dev_name(struct ethtool_coalesce_set_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_coalesce_set_req_set_header_flags(struct ethtool_coalesce_set_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +ethtool_coalesce_set_req_set_rx_usecs(struct ethtool_coalesce_set_req *req, + __u32 rx_usecs) +{ + req->_present.rx_usecs = 1; + req->rx_usecs = rx_usecs; +} +static inline void +ethtool_coalesce_set_req_set_rx_max_frames(struct ethtool_coalesce_set_req *req, + __u32 rx_max_frames) +{ + req->_present.rx_max_frames = 1; + req->rx_max_frames = rx_max_frames; +} +static inline void +ethtool_coalesce_set_req_set_rx_usecs_irq(struct ethtool_coalesce_set_req *req, + __u32 rx_usecs_irq) +{ + req->_present.rx_usecs_irq = 1; + req->rx_usecs_irq = rx_usecs_irq; +} +static inline void +ethtool_coalesce_set_req_set_rx_max_frames_irq(struct ethtool_coalesce_set_req *req, + __u32 rx_max_frames_irq) +{ + req->_present.rx_max_frames_irq = 1; + req->rx_max_frames_irq = rx_max_frames_irq; +} +static inline void +ethtool_coalesce_set_req_set_tx_usecs(struct ethtool_coalesce_set_req *req, + __u32 tx_usecs) +{ + req->_present.tx_usecs = 1; + req->tx_usecs = tx_usecs; +} +static inline void +ethtool_coalesce_set_req_set_tx_max_frames(struct ethtool_coalesce_set_req *req, + __u32 tx_max_frames) +{ + req->_present.tx_max_frames = 1; + req->tx_max_frames = tx_max_frames; +} +static inline void +ethtool_coalesce_set_req_set_tx_usecs_irq(struct ethtool_coalesce_set_req *req, + __u32 tx_usecs_irq) +{ + req->_present.tx_usecs_irq = 1; + req->tx_usecs_irq = tx_usecs_irq; +} +static inline void +ethtool_coalesce_set_req_set_tx_max_frames_irq(struct ethtool_coalesce_set_req *req, + __u32 tx_max_frames_irq) +{ + req->_present.tx_max_frames_irq = 1; + req->tx_max_frames_irq = tx_max_frames_irq; +} +static inline void +ethtool_coalesce_set_req_set_stats_block_usecs(struct ethtool_coalesce_set_req *req, + __u32 stats_block_usecs) +{ + req->_present.stats_block_usecs = 1; + req->stats_block_usecs = stats_block_usecs; +} +static inline void +ethtool_coalesce_set_req_set_use_adaptive_rx(struct ethtool_coalesce_set_req *req, + __u8 use_adaptive_rx) +{ + req->_present.use_adaptive_rx = 1; + req->use_adaptive_rx = use_adaptive_rx; +} +static inline void +ethtool_coalesce_set_req_set_use_adaptive_tx(struct ethtool_coalesce_set_req *req, + __u8 use_adaptive_tx) +{ + req->_present.use_adaptive_tx = 1; + req->use_adaptive_tx = use_adaptive_tx; +} +static inline void +ethtool_coalesce_set_req_set_pkt_rate_low(struct ethtool_coalesce_set_req *req, + __u32 pkt_rate_low) +{ + req->_present.pkt_rate_low = 1; + req->pkt_rate_low = pkt_rate_low; +} +static inline void +ethtool_coalesce_set_req_set_rx_usecs_low(struct ethtool_coalesce_set_req *req, + __u32 rx_usecs_low) +{ + req->_present.rx_usecs_low = 1; + req->rx_usecs_low = rx_usecs_low; +} +static inline void +ethtool_coalesce_set_req_set_rx_max_frames_low(struct ethtool_coalesce_set_req *req, + __u32 rx_max_frames_low) +{ + req->_present.rx_max_frames_low = 1; + req->rx_max_frames_low = rx_max_frames_low; +} +static inline void +ethtool_coalesce_set_req_set_tx_usecs_low(struct ethtool_coalesce_set_req *req, + __u32 tx_usecs_low) +{ + req->_present.tx_usecs_low = 1; + req->tx_usecs_low = tx_usecs_low; +} +static inline void +ethtool_coalesce_set_req_set_tx_max_frames_low(struct ethtool_coalesce_set_req *req, + __u32 tx_max_frames_low) +{ + req->_present.tx_max_frames_low = 1; + req->tx_max_frames_low = tx_max_frames_low; +} +static inline void +ethtool_coalesce_set_req_set_pkt_rate_high(struct ethtool_coalesce_set_req *req, + __u32 pkt_rate_high) +{ + req->_present.pkt_rate_high = 1; + req->pkt_rate_high = pkt_rate_high; +} +static inline void +ethtool_coalesce_set_req_set_rx_usecs_high(struct ethtool_coalesce_set_req *req, + __u32 rx_usecs_high) +{ + req->_present.rx_usecs_high = 1; + req->rx_usecs_high = rx_usecs_high; +} +static inline void +ethtool_coalesce_set_req_set_rx_max_frames_high(struct ethtool_coalesce_set_req *req, + __u32 rx_max_frames_high) +{ + req->_present.rx_max_frames_high = 1; + req->rx_max_frames_high = rx_max_frames_high; +} +static inline void +ethtool_coalesce_set_req_set_tx_usecs_high(struct ethtool_coalesce_set_req *req, + __u32 tx_usecs_high) +{ + req->_present.tx_usecs_high = 1; + req->tx_usecs_high = tx_usecs_high; +} +static inline void +ethtool_coalesce_set_req_set_tx_max_frames_high(struct ethtool_coalesce_set_req *req, + __u32 tx_max_frames_high) +{ + req->_present.tx_max_frames_high = 1; + req->tx_max_frames_high = tx_max_frames_high; +} +static inline void +ethtool_coalesce_set_req_set_rate_sample_interval(struct ethtool_coalesce_set_req *req, + __u32 rate_sample_interval) +{ + req->_present.rate_sample_interval = 1; + req->rate_sample_interval = rate_sample_interval; +} +static inline void +ethtool_coalesce_set_req_set_use_cqe_mode_tx(struct ethtool_coalesce_set_req *req, + __u8 use_cqe_mode_tx) +{ + req->_present.use_cqe_mode_tx = 1; + req->use_cqe_mode_tx = use_cqe_mode_tx; +} +static inline void +ethtool_coalesce_set_req_set_use_cqe_mode_rx(struct ethtool_coalesce_set_req *req, + __u8 use_cqe_mode_rx) +{ + req->_present.use_cqe_mode_rx = 1; + req->use_cqe_mode_rx = use_cqe_mode_rx; +} +static inline void +ethtool_coalesce_set_req_set_tx_aggr_max_bytes(struct ethtool_coalesce_set_req *req, + __u32 tx_aggr_max_bytes) +{ + req->_present.tx_aggr_max_bytes = 1; + req->tx_aggr_max_bytes = tx_aggr_max_bytes; +} +static inline void +ethtool_coalesce_set_req_set_tx_aggr_max_frames(struct ethtool_coalesce_set_req *req, + __u32 tx_aggr_max_frames) +{ + req->_present.tx_aggr_max_frames = 1; + req->tx_aggr_max_frames = tx_aggr_max_frames; +} +static inline void +ethtool_coalesce_set_req_set_tx_aggr_time_usecs(struct ethtool_coalesce_set_req *req, + __u32 tx_aggr_time_usecs) +{ + req->_present.tx_aggr_time_usecs = 1; + req->tx_aggr_time_usecs = tx_aggr_time_usecs; +} + +/* + * Set coalesce params. + */ +int ethtool_coalesce_set(struct ynl_sock *ys, + struct ethtool_coalesce_set_req *req); + +/* ============== ETHTOOL_MSG_PAUSE_GET ============== */ +/* ETHTOOL_MSG_PAUSE_GET - do */ +struct ethtool_pause_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_pause_get_req *ethtool_pause_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_pause_get_req)); +} +void ethtool_pause_get_req_free(struct ethtool_pause_get_req *req); + +static inline void +ethtool_pause_get_req_set_header_dev_index(struct ethtool_pause_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_pause_get_req_set_header_dev_name(struct ethtool_pause_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_pause_get_req_set_header_flags(struct ethtool_pause_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_pause_get_rsp { + struct { + __u32 header:1; + __u32 autoneg:1; + __u32 rx:1; + __u32 tx:1; + __u32 stats:1; + __u32 stats_src:1; + } _present; + + struct ethtool_header header; + __u8 autoneg; + __u8 rx; + __u8 tx; + struct ethtool_pause_stat stats; + __u32 stats_src; +}; + +void ethtool_pause_get_rsp_free(struct ethtool_pause_get_rsp *rsp); + +/* + * Get pause params. + */ +struct ethtool_pause_get_rsp * +ethtool_pause_get(struct ynl_sock *ys, struct ethtool_pause_get_req *req); + +/* ETHTOOL_MSG_PAUSE_GET - dump */ +struct ethtool_pause_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_pause_get_req_dump * +ethtool_pause_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_pause_get_req_dump)); +} +void ethtool_pause_get_req_dump_free(struct ethtool_pause_get_req_dump *req); + +static inline void +ethtool_pause_get_req_dump_set_header_dev_index(struct ethtool_pause_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_pause_get_req_dump_set_header_dev_name(struct ethtool_pause_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_pause_get_req_dump_set_header_flags(struct ethtool_pause_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_pause_get_list { + struct ethtool_pause_get_list *next; + struct ethtool_pause_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_pause_get_list_free(struct ethtool_pause_get_list *rsp); + +struct ethtool_pause_get_list * +ethtool_pause_get_dump(struct ynl_sock *ys, + struct ethtool_pause_get_req_dump *req); + +/* ETHTOOL_MSG_PAUSE_GET - notify */ +struct ethtool_pause_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_pause_get_ntf *ntf); + struct ethtool_pause_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_pause_get_ntf_free(struct ethtool_pause_get_ntf *rsp); + +/* ============== ETHTOOL_MSG_PAUSE_SET ============== */ +/* ETHTOOL_MSG_PAUSE_SET - do */ +struct ethtool_pause_set_req { + struct { + __u32 header:1; + __u32 autoneg:1; + __u32 rx:1; + __u32 tx:1; + __u32 stats:1; + __u32 stats_src:1; + } _present; + + struct ethtool_header header; + __u8 autoneg; + __u8 rx; + __u8 tx; + struct ethtool_pause_stat stats; + __u32 stats_src; +}; + +static inline struct ethtool_pause_set_req *ethtool_pause_set_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_pause_set_req)); +} +void ethtool_pause_set_req_free(struct ethtool_pause_set_req *req); + +static inline void +ethtool_pause_set_req_set_header_dev_index(struct ethtool_pause_set_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_pause_set_req_set_header_dev_name(struct ethtool_pause_set_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_pause_set_req_set_header_flags(struct ethtool_pause_set_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +ethtool_pause_set_req_set_autoneg(struct ethtool_pause_set_req *req, + __u8 autoneg) +{ + req->_present.autoneg = 1; + req->autoneg = autoneg; +} +static inline void +ethtool_pause_set_req_set_rx(struct ethtool_pause_set_req *req, __u8 rx) +{ + req->_present.rx = 1; + req->rx = rx; +} +static inline void +ethtool_pause_set_req_set_tx(struct ethtool_pause_set_req *req, __u8 tx) +{ + req->_present.tx = 1; + req->tx = tx; +} +static inline void +ethtool_pause_set_req_set_stats_tx_frames(struct ethtool_pause_set_req *req, + __u64 tx_frames) +{ + req->_present.stats = 1; + req->stats._present.tx_frames = 1; + req->stats.tx_frames = tx_frames; +} +static inline void +ethtool_pause_set_req_set_stats_rx_frames(struct ethtool_pause_set_req *req, + __u64 rx_frames) +{ + req->_present.stats = 1; + req->stats._present.rx_frames = 1; + req->stats.rx_frames = rx_frames; +} +static inline void +ethtool_pause_set_req_set_stats_src(struct ethtool_pause_set_req *req, + __u32 stats_src) +{ + req->_present.stats_src = 1; + req->stats_src = stats_src; +} + +/* + * Set pause params. + */ +int ethtool_pause_set(struct ynl_sock *ys, struct ethtool_pause_set_req *req); + +/* ============== ETHTOOL_MSG_EEE_GET ============== */ +/* ETHTOOL_MSG_EEE_GET - do */ +struct ethtool_eee_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_eee_get_req *ethtool_eee_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_eee_get_req)); +} +void ethtool_eee_get_req_free(struct ethtool_eee_get_req *req); + +static inline void +ethtool_eee_get_req_set_header_dev_index(struct ethtool_eee_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_eee_get_req_set_header_dev_name(struct ethtool_eee_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_eee_get_req_set_header_flags(struct ethtool_eee_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_eee_get_rsp { + struct { + __u32 header:1; + __u32 modes_ours:1; + __u32 modes_peer:1; + __u32 active:1; + __u32 enabled:1; + __u32 tx_lpi_enabled:1; + __u32 tx_lpi_timer:1; + } _present; + + struct ethtool_header header; + struct ethtool_bitset modes_ours; + struct ethtool_bitset modes_peer; + __u8 active; + __u8 enabled; + __u8 tx_lpi_enabled; + __u32 tx_lpi_timer; +}; + +void ethtool_eee_get_rsp_free(struct ethtool_eee_get_rsp *rsp); + +/* + * Get eee params. + */ +struct ethtool_eee_get_rsp * +ethtool_eee_get(struct ynl_sock *ys, struct ethtool_eee_get_req *req); + +/* ETHTOOL_MSG_EEE_GET - dump */ +struct ethtool_eee_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_eee_get_req_dump * +ethtool_eee_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_eee_get_req_dump)); +} +void ethtool_eee_get_req_dump_free(struct ethtool_eee_get_req_dump *req); + +static inline void +ethtool_eee_get_req_dump_set_header_dev_index(struct ethtool_eee_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_eee_get_req_dump_set_header_dev_name(struct ethtool_eee_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_eee_get_req_dump_set_header_flags(struct ethtool_eee_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_eee_get_list { + struct ethtool_eee_get_list *next; + struct ethtool_eee_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_eee_get_list_free(struct ethtool_eee_get_list *rsp); + +struct ethtool_eee_get_list * +ethtool_eee_get_dump(struct ynl_sock *ys, struct ethtool_eee_get_req_dump *req); + +/* ETHTOOL_MSG_EEE_GET - notify */ +struct ethtool_eee_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_eee_get_ntf *ntf); + struct ethtool_eee_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_eee_get_ntf_free(struct ethtool_eee_get_ntf *rsp); + +/* ============== ETHTOOL_MSG_EEE_SET ============== */ +/* ETHTOOL_MSG_EEE_SET - do */ +struct ethtool_eee_set_req { + struct { + __u32 header:1; + __u32 modes_ours:1; + __u32 modes_peer:1; + __u32 active:1; + __u32 enabled:1; + __u32 tx_lpi_enabled:1; + __u32 tx_lpi_timer:1; + } _present; + + struct ethtool_header header; + struct ethtool_bitset modes_ours; + struct ethtool_bitset modes_peer; + __u8 active; + __u8 enabled; + __u8 tx_lpi_enabled; + __u32 tx_lpi_timer; +}; + +static inline struct ethtool_eee_set_req *ethtool_eee_set_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_eee_set_req)); +} +void ethtool_eee_set_req_free(struct ethtool_eee_set_req *req); + +static inline void +ethtool_eee_set_req_set_header_dev_index(struct ethtool_eee_set_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_eee_set_req_set_header_dev_name(struct ethtool_eee_set_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_eee_set_req_set_header_flags(struct ethtool_eee_set_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +ethtool_eee_set_req_set_modes_ours_nomask(struct ethtool_eee_set_req *req) +{ + req->_present.modes_ours = 1; + req->modes_ours._present.nomask = 1; +} +static inline void +ethtool_eee_set_req_set_modes_ours_size(struct ethtool_eee_set_req *req, + __u32 size) +{ + req->_present.modes_ours = 1; + req->modes_ours._present.size = 1; + req->modes_ours.size = size; +} +static inline void +__ethtool_eee_set_req_set_modes_ours_bits_bit(struct ethtool_eee_set_req *req, + struct ethtool_bitset_bit *bit, + unsigned int n_bit) +{ + free(req->modes_ours.bits.bit); + req->modes_ours.bits.bit = bit; + req->modes_ours.bits.n_bit = n_bit; +} +static inline void +ethtool_eee_set_req_set_modes_peer_nomask(struct ethtool_eee_set_req *req) +{ + req->_present.modes_peer = 1; + req->modes_peer._present.nomask = 1; +} +static inline void +ethtool_eee_set_req_set_modes_peer_size(struct ethtool_eee_set_req *req, + __u32 size) +{ + req->_present.modes_peer = 1; + req->modes_peer._present.size = 1; + req->modes_peer.size = size; +} +static inline void +__ethtool_eee_set_req_set_modes_peer_bits_bit(struct ethtool_eee_set_req *req, + struct ethtool_bitset_bit *bit, + unsigned int n_bit) +{ + free(req->modes_peer.bits.bit); + req->modes_peer.bits.bit = bit; + req->modes_peer.bits.n_bit = n_bit; +} +static inline void +ethtool_eee_set_req_set_active(struct ethtool_eee_set_req *req, __u8 active) +{ + req->_present.active = 1; + req->active = active; +} +static inline void +ethtool_eee_set_req_set_enabled(struct ethtool_eee_set_req *req, __u8 enabled) +{ + req->_present.enabled = 1; + req->enabled = enabled; +} +static inline void +ethtool_eee_set_req_set_tx_lpi_enabled(struct ethtool_eee_set_req *req, + __u8 tx_lpi_enabled) +{ + req->_present.tx_lpi_enabled = 1; + req->tx_lpi_enabled = tx_lpi_enabled; +} +static inline void +ethtool_eee_set_req_set_tx_lpi_timer(struct ethtool_eee_set_req *req, + __u32 tx_lpi_timer) +{ + req->_present.tx_lpi_timer = 1; + req->tx_lpi_timer = tx_lpi_timer; +} + +/* + * Set eee params. + */ +int ethtool_eee_set(struct ynl_sock *ys, struct ethtool_eee_set_req *req); + +/* ============== ETHTOOL_MSG_TSINFO_GET ============== */ +/* ETHTOOL_MSG_TSINFO_GET - do */ +struct ethtool_tsinfo_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_tsinfo_get_req *ethtool_tsinfo_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_tsinfo_get_req)); +} +void ethtool_tsinfo_get_req_free(struct ethtool_tsinfo_get_req *req); + +static inline void +ethtool_tsinfo_get_req_set_header_dev_index(struct ethtool_tsinfo_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_tsinfo_get_req_set_header_dev_name(struct ethtool_tsinfo_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_tsinfo_get_req_set_header_flags(struct ethtool_tsinfo_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_tsinfo_get_rsp { + struct { + __u32 header:1; + __u32 timestamping:1; + __u32 tx_types:1; + __u32 rx_filters:1; + __u32 phc_index:1; + } _present; + + struct ethtool_header header; + struct ethtool_bitset timestamping; + struct ethtool_bitset tx_types; + struct ethtool_bitset rx_filters; + __u32 phc_index; +}; + +void ethtool_tsinfo_get_rsp_free(struct ethtool_tsinfo_get_rsp *rsp); + +/* + * Get tsinfo params. + */ +struct ethtool_tsinfo_get_rsp * +ethtool_tsinfo_get(struct ynl_sock *ys, struct ethtool_tsinfo_get_req *req); + +/* ETHTOOL_MSG_TSINFO_GET - dump */ +struct ethtool_tsinfo_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_tsinfo_get_req_dump * +ethtool_tsinfo_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_tsinfo_get_req_dump)); +} +void ethtool_tsinfo_get_req_dump_free(struct ethtool_tsinfo_get_req_dump *req); + +static inline void +ethtool_tsinfo_get_req_dump_set_header_dev_index(struct ethtool_tsinfo_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_tsinfo_get_req_dump_set_header_dev_name(struct ethtool_tsinfo_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_tsinfo_get_req_dump_set_header_flags(struct ethtool_tsinfo_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_tsinfo_get_list { + struct ethtool_tsinfo_get_list *next; + struct ethtool_tsinfo_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_tsinfo_get_list_free(struct ethtool_tsinfo_get_list *rsp); + +struct ethtool_tsinfo_get_list * +ethtool_tsinfo_get_dump(struct ynl_sock *ys, + struct ethtool_tsinfo_get_req_dump *req); + +/* ============== ETHTOOL_MSG_CABLE_TEST_ACT ============== */ +/* ETHTOOL_MSG_CABLE_TEST_ACT - do */ +struct ethtool_cable_test_act_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_cable_test_act_req * +ethtool_cable_test_act_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_cable_test_act_req)); +} +void ethtool_cable_test_act_req_free(struct ethtool_cable_test_act_req *req); + +static inline void +ethtool_cable_test_act_req_set_header_dev_index(struct ethtool_cable_test_act_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_cable_test_act_req_set_header_dev_name(struct ethtool_cable_test_act_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_cable_test_act_req_set_header_flags(struct ethtool_cable_test_act_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +/* + * Cable test. + */ +int ethtool_cable_test_act(struct ynl_sock *ys, + struct ethtool_cable_test_act_req *req); + +/* ============== ETHTOOL_MSG_CABLE_TEST_TDR_ACT ============== */ +/* ETHTOOL_MSG_CABLE_TEST_TDR_ACT - do */ +struct ethtool_cable_test_tdr_act_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_cable_test_tdr_act_req * +ethtool_cable_test_tdr_act_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_cable_test_tdr_act_req)); +} +void +ethtool_cable_test_tdr_act_req_free(struct ethtool_cable_test_tdr_act_req *req); + +static inline void +ethtool_cable_test_tdr_act_req_set_header_dev_index(struct ethtool_cable_test_tdr_act_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_cable_test_tdr_act_req_set_header_dev_name(struct ethtool_cable_test_tdr_act_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_cable_test_tdr_act_req_set_header_flags(struct ethtool_cable_test_tdr_act_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +/* + * Cable test TDR. + */ +int ethtool_cable_test_tdr_act(struct ynl_sock *ys, + struct ethtool_cable_test_tdr_act_req *req); + +/* ============== ETHTOOL_MSG_TUNNEL_INFO_GET ============== */ +/* ETHTOOL_MSG_TUNNEL_INFO_GET - do */ +struct ethtool_tunnel_info_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_tunnel_info_get_req * +ethtool_tunnel_info_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_tunnel_info_get_req)); +} +void ethtool_tunnel_info_get_req_free(struct ethtool_tunnel_info_get_req *req); + +static inline void +ethtool_tunnel_info_get_req_set_header_dev_index(struct ethtool_tunnel_info_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_tunnel_info_get_req_set_header_dev_name(struct ethtool_tunnel_info_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_tunnel_info_get_req_set_header_flags(struct ethtool_tunnel_info_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_tunnel_info_get_rsp { + struct { + __u32 header:1; + __u32 udp_ports:1; + } _present; + + struct ethtool_header header; + struct ethtool_tunnel_udp udp_ports; +}; + +void ethtool_tunnel_info_get_rsp_free(struct ethtool_tunnel_info_get_rsp *rsp); + +/* + * Get tsinfo params. + */ +struct ethtool_tunnel_info_get_rsp * +ethtool_tunnel_info_get(struct ynl_sock *ys, + struct ethtool_tunnel_info_get_req *req); + +/* ETHTOOL_MSG_TUNNEL_INFO_GET - dump */ +struct ethtool_tunnel_info_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_tunnel_info_get_req_dump * +ethtool_tunnel_info_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_tunnel_info_get_req_dump)); +} +void +ethtool_tunnel_info_get_req_dump_free(struct ethtool_tunnel_info_get_req_dump *req); + +static inline void +ethtool_tunnel_info_get_req_dump_set_header_dev_index(struct ethtool_tunnel_info_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_tunnel_info_get_req_dump_set_header_dev_name(struct ethtool_tunnel_info_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_tunnel_info_get_req_dump_set_header_flags(struct ethtool_tunnel_info_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_tunnel_info_get_list { + struct ethtool_tunnel_info_get_list *next; + struct ethtool_tunnel_info_get_rsp obj __attribute__ ((aligned (8))); +}; + +void +ethtool_tunnel_info_get_list_free(struct ethtool_tunnel_info_get_list *rsp); + +struct ethtool_tunnel_info_get_list * +ethtool_tunnel_info_get_dump(struct ynl_sock *ys, + struct ethtool_tunnel_info_get_req_dump *req); + +/* ============== ETHTOOL_MSG_FEC_GET ============== */ +/* ETHTOOL_MSG_FEC_GET - do */ +struct ethtool_fec_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_fec_get_req *ethtool_fec_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_fec_get_req)); +} +void ethtool_fec_get_req_free(struct ethtool_fec_get_req *req); + +static inline void +ethtool_fec_get_req_set_header_dev_index(struct ethtool_fec_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_fec_get_req_set_header_dev_name(struct ethtool_fec_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_fec_get_req_set_header_flags(struct ethtool_fec_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_fec_get_rsp { + struct { + __u32 header:1; + __u32 modes:1; + __u32 auto_:1; + __u32 active:1; + __u32 stats:1; + } _present; + + struct ethtool_header header; + struct ethtool_bitset modes; + __u8 auto_; + __u32 active; + struct ethtool_fec_stat stats; +}; + +void ethtool_fec_get_rsp_free(struct ethtool_fec_get_rsp *rsp); + +/* + * Get FEC params. + */ +struct ethtool_fec_get_rsp * +ethtool_fec_get(struct ynl_sock *ys, struct ethtool_fec_get_req *req); + +/* ETHTOOL_MSG_FEC_GET - dump */ +struct ethtool_fec_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_fec_get_req_dump * +ethtool_fec_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_fec_get_req_dump)); +} +void ethtool_fec_get_req_dump_free(struct ethtool_fec_get_req_dump *req); + +static inline void +ethtool_fec_get_req_dump_set_header_dev_index(struct ethtool_fec_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_fec_get_req_dump_set_header_dev_name(struct ethtool_fec_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_fec_get_req_dump_set_header_flags(struct ethtool_fec_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_fec_get_list { + struct ethtool_fec_get_list *next; + struct ethtool_fec_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_fec_get_list_free(struct ethtool_fec_get_list *rsp); + +struct ethtool_fec_get_list * +ethtool_fec_get_dump(struct ynl_sock *ys, struct ethtool_fec_get_req_dump *req); + +/* ETHTOOL_MSG_FEC_GET - notify */ +struct ethtool_fec_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_fec_get_ntf *ntf); + struct ethtool_fec_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_fec_get_ntf_free(struct ethtool_fec_get_ntf *rsp); + +/* ============== ETHTOOL_MSG_FEC_SET ============== */ +/* ETHTOOL_MSG_FEC_SET - do */ +struct ethtool_fec_set_req { + struct { + __u32 header:1; + __u32 modes:1; + __u32 auto_:1; + __u32 active:1; + __u32 stats:1; + } _present; + + struct ethtool_header header; + struct ethtool_bitset modes; + __u8 auto_; + __u32 active; + struct ethtool_fec_stat stats; +}; + +static inline struct ethtool_fec_set_req *ethtool_fec_set_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_fec_set_req)); +} +void ethtool_fec_set_req_free(struct ethtool_fec_set_req *req); + +static inline void +ethtool_fec_set_req_set_header_dev_index(struct ethtool_fec_set_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_fec_set_req_set_header_dev_name(struct ethtool_fec_set_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_fec_set_req_set_header_flags(struct ethtool_fec_set_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +ethtool_fec_set_req_set_modes_nomask(struct ethtool_fec_set_req *req) +{ + req->_present.modes = 1; + req->modes._present.nomask = 1; +} +static inline void +ethtool_fec_set_req_set_modes_size(struct ethtool_fec_set_req *req, __u32 size) +{ + req->_present.modes = 1; + req->modes._present.size = 1; + req->modes.size = size; +} +static inline void +__ethtool_fec_set_req_set_modes_bits_bit(struct ethtool_fec_set_req *req, + struct ethtool_bitset_bit *bit, + unsigned int n_bit) +{ + free(req->modes.bits.bit); + req->modes.bits.bit = bit; + req->modes.bits.n_bit = n_bit; +} +static inline void +ethtool_fec_set_req_set_auto_(struct ethtool_fec_set_req *req, __u8 auto_) +{ + req->_present.auto_ = 1; + req->auto_ = auto_; +} +static inline void +ethtool_fec_set_req_set_active(struct ethtool_fec_set_req *req, __u32 active) +{ + req->_present.active = 1; + req->active = active; +} +static inline void +ethtool_fec_set_req_set_stats_corrected(struct ethtool_fec_set_req *req, + const void *corrected, size_t len) +{ + free(req->stats.corrected); + req->stats.corrected = malloc(req->stats._present.corrected_len); + memcpy(req->stats.corrected, corrected, req->stats._present.corrected_len); +} +static inline void +ethtool_fec_set_req_set_stats_uncorr(struct ethtool_fec_set_req *req, + const void *uncorr, size_t len) +{ + free(req->stats.uncorr); + req->stats.uncorr = malloc(req->stats._present.uncorr_len); + memcpy(req->stats.uncorr, uncorr, req->stats._present.uncorr_len); +} +static inline void +ethtool_fec_set_req_set_stats_corr_bits(struct ethtool_fec_set_req *req, + const void *corr_bits, size_t len) +{ + free(req->stats.corr_bits); + req->stats.corr_bits = malloc(req->stats._present.corr_bits_len); + memcpy(req->stats.corr_bits, corr_bits, req->stats._present.corr_bits_len); +} + +/* + * Set FEC params. + */ +int ethtool_fec_set(struct ynl_sock *ys, struct ethtool_fec_set_req *req); + +/* ============== ETHTOOL_MSG_MODULE_EEPROM_GET ============== */ +/* ETHTOOL_MSG_MODULE_EEPROM_GET - do */ +struct ethtool_module_eeprom_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_module_eeprom_get_req * +ethtool_module_eeprom_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_module_eeprom_get_req)); +} +void +ethtool_module_eeprom_get_req_free(struct ethtool_module_eeprom_get_req *req); + +static inline void +ethtool_module_eeprom_get_req_set_header_dev_index(struct ethtool_module_eeprom_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_module_eeprom_get_req_set_header_dev_name(struct ethtool_module_eeprom_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_module_eeprom_get_req_set_header_flags(struct ethtool_module_eeprom_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_module_eeprom_get_rsp { + struct { + __u32 header:1; + __u32 offset:1; + __u32 length:1; + __u32 page:1; + __u32 bank:1; + __u32 i2c_address:1; + __u32 data_len; + } _present; + + struct ethtool_header header; + __u32 offset; + __u32 length; + __u8 page; + __u8 bank; + __u8 i2c_address; + void *data; +}; + +void +ethtool_module_eeprom_get_rsp_free(struct ethtool_module_eeprom_get_rsp *rsp); + +/* + * Get module EEPROM params. + */ +struct ethtool_module_eeprom_get_rsp * +ethtool_module_eeprom_get(struct ynl_sock *ys, + struct ethtool_module_eeprom_get_req *req); + +/* ETHTOOL_MSG_MODULE_EEPROM_GET - dump */ +struct ethtool_module_eeprom_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_module_eeprom_get_req_dump * +ethtool_module_eeprom_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_module_eeprom_get_req_dump)); +} +void +ethtool_module_eeprom_get_req_dump_free(struct ethtool_module_eeprom_get_req_dump *req); + +static inline void +ethtool_module_eeprom_get_req_dump_set_header_dev_index(struct ethtool_module_eeprom_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_module_eeprom_get_req_dump_set_header_dev_name(struct ethtool_module_eeprom_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_module_eeprom_get_req_dump_set_header_flags(struct ethtool_module_eeprom_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_module_eeprom_get_list { + struct ethtool_module_eeprom_get_list *next; + struct ethtool_module_eeprom_get_rsp obj __attribute__ ((aligned (8))); +}; + +void +ethtool_module_eeprom_get_list_free(struct ethtool_module_eeprom_get_list *rsp); + +struct ethtool_module_eeprom_get_list * +ethtool_module_eeprom_get_dump(struct ynl_sock *ys, + struct ethtool_module_eeprom_get_req_dump *req); + +/* ============== ETHTOOL_MSG_PHC_VCLOCKS_GET ============== */ +/* ETHTOOL_MSG_PHC_VCLOCKS_GET - do */ +struct ethtool_phc_vclocks_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_phc_vclocks_get_req * +ethtool_phc_vclocks_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_phc_vclocks_get_req)); +} +void ethtool_phc_vclocks_get_req_free(struct ethtool_phc_vclocks_get_req *req); + +static inline void +ethtool_phc_vclocks_get_req_set_header_dev_index(struct ethtool_phc_vclocks_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_phc_vclocks_get_req_set_header_dev_name(struct ethtool_phc_vclocks_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_phc_vclocks_get_req_set_header_flags(struct ethtool_phc_vclocks_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_phc_vclocks_get_rsp { + struct { + __u32 header:1; + __u32 num:1; + } _present; + + struct ethtool_header header; + __u32 num; +}; + +void ethtool_phc_vclocks_get_rsp_free(struct ethtool_phc_vclocks_get_rsp *rsp); + +/* + * Get PHC VCLOCKs. + */ +struct ethtool_phc_vclocks_get_rsp * +ethtool_phc_vclocks_get(struct ynl_sock *ys, + struct ethtool_phc_vclocks_get_req *req); + +/* ETHTOOL_MSG_PHC_VCLOCKS_GET - dump */ +struct ethtool_phc_vclocks_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_phc_vclocks_get_req_dump * +ethtool_phc_vclocks_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_phc_vclocks_get_req_dump)); +} +void +ethtool_phc_vclocks_get_req_dump_free(struct ethtool_phc_vclocks_get_req_dump *req); + +static inline void +ethtool_phc_vclocks_get_req_dump_set_header_dev_index(struct ethtool_phc_vclocks_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_phc_vclocks_get_req_dump_set_header_dev_name(struct ethtool_phc_vclocks_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_phc_vclocks_get_req_dump_set_header_flags(struct ethtool_phc_vclocks_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_phc_vclocks_get_list { + struct ethtool_phc_vclocks_get_list *next; + struct ethtool_phc_vclocks_get_rsp obj __attribute__ ((aligned (8))); +}; + +void +ethtool_phc_vclocks_get_list_free(struct ethtool_phc_vclocks_get_list *rsp); + +struct ethtool_phc_vclocks_get_list * +ethtool_phc_vclocks_get_dump(struct ynl_sock *ys, + struct ethtool_phc_vclocks_get_req_dump *req); + +/* ============== ETHTOOL_MSG_MODULE_GET ============== */ +/* ETHTOOL_MSG_MODULE_GET - do */ +struct ethtool_module_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_module_get_req *ethtool_module_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_module_get_req)); +} +void ethtool_module_get_req_free(struct ethtool_module_get_req *req); + +static inline void +ethtool_module_get_req_set_header_dev_index(struct ethtool_module_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_module_get_req_set_header_dev_name(struct ethtool_module_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_module_get_req_set_header_flags(struct ethtool_module_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_module_get_rsp { + struct { + __u32 header:1; + __u32 power_mode_policy:1; + __u32 power_mode:1; + } _present; + + struct ethtool_header header; + __u8 power_mode_policy; + __u8 power_mode; +}; + +void ethtool_module_get_rsp_free(struct ethtool_module_get_rsp *rsp); + +/* + * Get module params. + */ +struct ethtool_module_get_rsp * +ethtool_module_get(struct ynl_sock *ys, struct ethtool_module_get_req *req); + +/* ETHTOOL_MSG_MODULE_GET - dump */ +struct ethtool_module_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_module_get_req_dump * +ethtool_module_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_module_get_req_dump)); +} +void ethtool_module_get_req_dump_free(struct ethtool_module_get_req_dump *req); + +static inline void +ethtool_module_get_req_dump_set_header_dev_index(struct ethtool_module_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_module_get_req_dump_set_header_dev_name(struct ethtool_module_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_module_get_req_dump_set_header_flags(struct ethtool_module_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_module_get_list { + struct ethtool_module_get_list *next; + struct ethtool_module_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_module_get_list_free(struct ethtool_module_get_list *rsp); + +struct ethtool_module_get_list * +ethtool_module_get_dump(struct ynl_sock *ys, + struct ethtool_module_get_req_dump *req); + +/* ETHTOOL_MSG_MODULE_GET - notify */ +struct ethtool_module_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_module_get_ntf *ntf); + struct ethtool_module_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_module_get_ntf_free(struct ethtool_module_get_ntf *rsp); + +/* ============== ETHTOOL_MSG_MODULE_SET ============== */ +/* ETHTOOL_MSG_MODULE_SET - do */ +struct ethtool_module_set_req { + struct { + __u32 header:1; + __u32 power_mode_policy:1; + __u32 power_mode:1; + } _present; + + struct ethtool_header header; + __u8 power_mode_policy; + __u8 power_mode; +}; + +static inline struct ethtool_module_set_req *ethtool_module_set_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_module_set_req)); +} +void ethtool_module_set_req_free(struct ethtool_module_set_req *req); + +static inline void +ethtool_module_set_req_set_header_dev_index(struct ethtool_module_set_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_module_set_req_set_header_dev_name(struct ethtool_module_set_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_module_set_req_set_header_flags(struct ethtool_module_set_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +ethtool_module_set_req_set_power_mode_policy(struct ethtool_module_set_req *req, + __u8 power_mode_policy) +{ + req->_present.power_mode_policy = 1; + req->power_mode_policy = power_mode_policy; +} +static inline void +ethtool_module_set_req_set_power_mode(struct ethtool_module_set_req *req, + __u8 power_mode) +{ + req->_present.power_mode = 1; + req->power_mode = power_mode; +} + +/* + * Set module params. + */ +int ethtool_module_set(struct ynl_sock *ys, struct ethtool_module_set_req *req); + +/* ============== ETHTOOL_MSG_PSE_GET ============== */ +/* ETHTOOL_MSG_PSE_GET - do */ +struct ethtool_pse_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_pse_get_req *ethtool_pse_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_pse_get_req)); +} +void ethtool_pse_get_req_free(struct ethtool_pse_get_req *req); + +static inline void +ethtool_pse_get_req_set_header_dev_index(struct ethtool_pse_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_pse_get_req_set_header_dev_name(struct ethtool_pse_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_pse_get_req_set_header_flags(struct ethtool_pse_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_pse_get_rsp { + struct { + __u32 header:1; + __u32 admin_state:1; + __u32 admin_control:1; + __u32 pw_d_status:1; + } _present; + + struct ethtool_header header; + __u32 admin_state; + __u32 admin_control; + __u32 pw_d_status; +}; + +void ethtool_pse_get_rsp_free(struct ethtool_pse_get_rsp *rsp); + +/* + * Get Power Sourcing Equipment params. + */ +struct ethtool_pse_get_rsp * +ethtool_pse_get(struct ynl_sock *ys, struct ethtool_pse_get_req *req); + +/* ETHTOOL_MSG_PSE_GET - dump */ +struct ethtool_pse_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_pse_get_req_dump * +ethtool_pse_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_pse_get_req_dump)); +} +void ethtool_pse_get_req_dump_free(struct ethtool_pse_get_req_dump *req); + +static inline void +ethtool_pse_get_req_dump_set_header_dev_index(struct ethtool_pse_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_pse_get_req_dump_set_header_dev_name(struct ethtool_pse_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_pse_get_req_dump_set_header_flags(struct ethtool_pse_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_pse_get_list { + struct ethtool_pse_get_list *next; + struct ethtool_pse_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_pse_get_list_free(struct ethtool_pse_get_list *rsp); + +struct ethtool_pse_get_list * +ethtool_pse_get_dump(struct ynl_sock *ys, struct ethtool_pse_get_req_dump *req); + +/* ============== ETHTOOL_MSG_PSE_SET ============== */ +/* ETHTOOL_MSG_PSE_SET - do */ +struct ethtool_pse_set_req { + struct { + __u32 header:1; + __u32 admin_state:1; + __u32 admin_control:1; + __u32 pw_d_status:1; + } _present; + + struct ethtool_header header; + __u32 admin_state; + __u32 admin_control; + __u32 pw_d_status; +}; + +static inline struct ethtool_pse_set_req *ethtool_pse_set_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_pse_set_req)); +} +void ethtool_pse_set_req_free(struct ethtool_pse_set_req *req); + +static inline void +ethtool_pse_set_req_set_header_dev_index(struct ethtool_pse_set_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_pse_set_req_set_header_dev_name(struct ethtool_pse_set_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_pse_set_req_set_header_flags(struct ethtool_pse_set_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +ethtool_pse_set_req_set_admin_state(struct ethtool_pse_set_req *req, + __u32 admin_state) +{ + req->_present.admin_state = 1; + req->admin_state = admin_state; +} +static inline void +ethtool_pse_set_req_set_admin_control(struct ethtool_pse_set_req *req, + __u32 admin_control) +{ + req->_present.admin_control = 1; + req->admin_control = admin_control; +} +static inline void +ethtool_pse_set_req_set_pw_d_status(struct ethtool_pse_set_req *req, + __u32 pw_d_status) +{ + req->_present.pw_d_status = 1; + req->pw_d_status = pw_d_status; +} + +/* + * Set Power Sourcing Equipment params. + */ +int ethtool_pse_set(struct ynl_sock *ys, struct ethtool_pse_set_req *req); + +/* ============== ETHTOOL_MSG_RSS_GET ============== */ +/* ETHTOOL_MSG_RSS_GET - do */ +struct ethtool_rss_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_rss_get_req *ethtool_rss_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_rss_get_req)); +} +void ethtool_rss_get_req_free(struct ethtool_rss_get_req *req); + +static inline void +ethtool_rss_get_req_set_header_dev_index(struct ethtool_rss_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_rss_get_req_set_header_dev_name(struct ethtool_rss_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_rss_get_req_set_header_flags(struct ethtool_rss_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_rss_get_rsp { + struct { + __u32 header:1; + __u32 context:1; + __u32 hfunc:1; + __u32 indir_len; + __u32 hkey_len; + } _present; + + struct ethtool_header header; + __u32 context; + __u32 hfunc; + void *indir; + void *hkey; +}; + +void ethtool_rss_get_rsp_free(struct ethtool_rss_get_rsp *rsp); + +/* + * Get RSS params. + */ +struct ethtool_rss_get_rsp * +ethtool_rss_get(struct ynl_sock *ys, struct ethtool_rss_get_req *req); + +/* ETHTOOL_MSG_RSS_GET - dump */ +struct ethtool_rss_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_rss_get_req_dump * +ethtool_rss_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_rss_get_req_dump)); +} +void ethtool_rss_get_req_dump_free(struct ethtool_rss_get_req_dump *req); + +static inline void +ethtool_rss_get_req_dump_set_header_dev_index(struct ethtool_rss_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_rss_get_req_dump_set_header_dev_name(struct ethtool_rss_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_rss_get_req_dump_set_header_flags(struct ethtool_rss_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_rss_get_list { + struct ethtool_rss_get_list *next; + struct ethtool_rss_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_rss_get_list_free(struct ethtool_rss_get_list *rsp); + +struct ethtool_rss_get_list * +ethtool_rss_get_dump(struct ynl_sock *ys, struct ethtool_rss_get_req_dump *req); + +/* ============== ETHTOOL_MSG_PLCA_GET_CFG ============== */ +/* ETHTOOL_MSG_PLCA_GET_CFG - do */ +struct ethtool_plca_get_cfg_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_plca_get_cfg_req * +ethtool_plca_get_cfg_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_plca_get_cfg_req)); +} +void ethtool_plca_get_cfg_req_free(struct ethtool_plca_get_cfg_req *req); + +static inline void +ethtool_plca_get_cfg_req_set_header_dev_index(struct ethtool_plca_get_cfg_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_plca_get_cfg_req_set_header_dev_name(struct ethtool_plca_get_cfg_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_plca_get_cfg_req_set_header_flags(struct ethtool_plca_get_cfg_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_plca_get_cfg_rsp { + struct { + __u32 header:1; + __u32 version:1; + __u32 enabled:1; + __u32 status:1; + __u32 node_cnt:1; + __u32 node_id:1; + __u32 to_tmr:1; + __u32 burst_cnt:1; + __u32 burst_tmr:1; + } _present; + + struct ethtool_header header; + __u16 version; + __u8 enabled; + __u8 status; + __u32 node_cnt; + __u32 node_id; + __u32 to_tmr; + __u32 burst_cnt; + __u32 burst_tmr; +}; + +void ethtool_plca_get_cfg_rsp_free(struct ethtool_plca_get_cfg_rsp *rsp); + +/* + * Get PLCA params. + */ +struct ethtool_plca_get_cfg_rsp * +ethtool_plca_get_cfg(struct ynl_sock *ys, struct ethtool_plca_get_cfg_req *req); + +/* ETHTOOL_MSG_PLCA_GET_CFG - dump */ +struct ethtool_plca_get_cfg_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_plca_get_cfg_req_dump * +ethtool_plca_get_cfg_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_plca_get_cfg_req_dump)); +} +void +ethtool_plca_get_cfg_req_dump_free(struct ethtool_plca_get_cfg_req_dump *req); + +static inline void +ethtool_plca_get_cfg_req_dump_set_header_dev_index(struct ethtool_plca_get_cfg_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_plca_get_cfg_req_dump_set_header_dev_name(struct ethtool_plca_get_cfg_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_plca_get_cfg_req_dump_set_header_flags(struct ethtool_plca_get_cfg_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_plca_get_cfg_list { + struct ethtool_plca_get_cfg_list *next; + struct ethtool_plca_get_cfg_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_plca_get_cfg_list_free(struct ethtool_plca_get_cfg_list *rsp); + +struct ethtool_plca_get_cfg_list * +ethtool_plca_get_cfg_dump(struct ynl_sock *ys, + struct ethtool_plca_get_cfg_req_dump *req); + +/* ETHTOOL_MSG_PLCA_GET_CFG - notify */ +struct ethtool_plca_get_cfg_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_plca_get_cfg_ntf *ntf); + struct ethtool_plca_get_cfg_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_plca_get_cfg_ntf_free(struct ethtool_plca_get_cfg_ntf *rsp); + +/* ============== ETHTOOL_MSG_PLCA_SET_CFG ============== */ +/* ETHTOOL_MSG_PLCA_SET_CFG - do */ +struct ethtool_plca_set_cfg_req { + struct { + __u32 header:1; + __u32 version:1; + __u32 enabled:1; + __u32 status:1; + __u32 node_cnt:1; + __u32 node_id:1; + __u32 to_tmr:1; + __u32 burst_cnt:1; + __u32 burst_tmr:1; + } _present; + + struct ethtool_header header; + __u16 version; + __u8 enabled; + __u8 status; + __u32 node_cnt; + __u32 node_id; + __u32 to_tmr; + __u32 burst_cnt; + __u32 burst_tmr; +}; + +static inline struct ethtool_plca_set_cfg_req * +ethtool_plca_set_cfg_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_plca_set_cfg_req)); +} +void ethtool_plca_set_cfg_req_free(struct ethtool_plca_set_cfg_req *req); + +static inline void +ethtool_plca_set_cfg_req_set_header_dev_index(struct ethtool_plca_set_cfg_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_plca_set_cfg_req_set_header_dev_name(struct ethtool_plca_set_cfg_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_plca_set_cfg_req_set_header_flags(struct ethtool_plca_set_cfg_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +ethtool_plca_set_cfg_req_set_version(struct ethtool_plca_set_cfg_req *req, + __u16 version) +{ + req->_present.version = 1; + req->version = version; +} +static inline void +ethtool_plca_set_cfg_req_set_enabled(struct ethtool_plca_set_cfg_req *req, + __u8 enabled) +{ + req->_present.enabled = 1; + req->enabled = enabled; +} +static inline void +ethtool_plca_set_cfg_req_set_status(struct ethtool_plca_set_cfg_req *req, + __u8 status) +{ + req->_present.status = 1; + req->status = status; +} +static inline void +ethtool_plca_set_cfg_req_set_node_cnt(struct ethtool_plca_set_cfg_req *req, + __u32 node_cnt) +{ + req->_present.node_cnt = 1; + req->node_cnt = node_cnt; +} +static inline void +ethtool_plca_set_cfg_req_set_node_id(struct ethtool_plca_set_cfg_req *req, + __u32 node_id) +{ + req->_present.node_id = 1; + req->node_id = node_id; +} +static inline void +ethtool_plca_set_cfg_req_set_to_tmr(struct ethtool_plca_set_cfg_req *req, + __u32 to_tmr) +{ + req->_present.to_tmr = 1; + req->to_tmr = to_tmr; +} +static inline void +ethtool_plca_set_cfg_req_set_burst_cnt(struct ethtool_plca_set_cfg_req *req, + __u32 burst_cnt) +{ + req->_present.burst_cnt = 1; + req->burst_cnt = burst_cnt; +} +static inline void +ethtool_plca_set_cfg_req_set_burst_tmr(struct ethtool_plca_set_cfg_req *req, + __u32 burst_tmr) +{ + req->_present.burst_tmr = 1; + req->burst_tmr = burst_tmr; +} + +/* + * Set PLCA params. + */ +int ethtool_plca_set_cfg(struct ynl_sock *ys, + struct ethtool_plca_set_cfg_req *req); + +/* ============== ETHTOOL_MSG_PLCA_GET_STATUS ============== */ +/* ETHTOOL_MSG_PLCA_GET_STATUS - do */ +struct ethtool_plca_get_status_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_plca_get_status_req * +ethtool_plca_get_status_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_plca_get_status_req)); +} +void ethtool_plca_get_status_req_free(struct ethtool_plca_get_status_req *req); + +static inline void +ethtool_plca_get_status_req_set_header_dev_index(struct ethtool_plca_get_status_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_plca_get_status_req_set_header_dev_name(struct ethtool_plca_get_status_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_plca_get_status_req_set_header_flags(struct ethtool_plca_get_status_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_plca_get_status_rsp { + struct { + __u32 header:1; + __u32 version:1; + __u32 enabled:1; + __u32 status:1; + __u32 node_cnt:1; + __u32 node_id:1; + __u32 to_tmr:1; + __u32 burst_cnt:1; + __u32 burst_tmr:1; + } _present; + + struct ethtool_header header; + __u16 version; + __u8 enabled; + __u8 status; + __u32 node_cnt; + __u32 node_id; + __u32 to_tmr; + __u32 burst_cnt; + __u32 burst_tmr; +}; + +void ethtool_plca_get_status_rsp_free(struct ethtool_plca_get_status_rsp *rsp); + +/* + * Get PLCA status params. + */ +struct ethtool_plca_get_status_rsp * +ethtool_plca_get_status(struct ynl_sock *ys, + struct ethtool_plca_get_status_req *req); + +/* ETHTOOL_MSG_PLCA_GET_STATUS - dump */ +struct ethtool_plca_get_status_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_plca_get_status_req_dump * +ethtool_plca_get_status_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_plca_get_status_req_dump)); +} +void +ethtool_plca_get_status_req_dump_free(struct ethtool_plca_get_status_req_dump *req); + +static inline void +ethtool_plca_get_status_req_dump_set_header_dev_index(struct ethtool_plca_get_status_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_plca_get_status_req_dump_set_header_dev_name(struct ethtool_plca_get_status_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_plca_get_status_req_dump_set_header_flags(struct ethtool_plca_get_status_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_plca_get_status_list { + struct ethtool_plca_get_status_list *next; + struct ethtool_plca_get_status_rsp obj __attribute__ ((aligned (8))); +}; + +void +ethtool_plca_get_status_list_free(struct ethtool_plca_get_status_list *rsp); + +struct ethtool_plca_get_status_list * +ethtool_plca_get_status_dump(struct ynl_sock *ys, + struct ethtool_plca_get_status_req_dump *req); + +/* ============== ETHTOOL_MSG_MM_GET ============== */ +/* ETHTOOL_MSG_MM_GET - do */ +struct ethtool_mm_get_req { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_mm_get_req *ethtool_mm_get_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_mm_get_req)); +} +void ethtool_mm_get_req_free(struct ethtool_mm_get_req *req); + +static inline void +ethtool_mm_get_req_set_header_dev_index(struct ethtool_mm_get_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_mm_get_req_set_header_dev_name(struct ethtool_mm_get_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_mm_get_req_set_header_flags(struct ethtool_mm_get_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_mm_get_rsp { + struct { + __u32 header:1; + __u32 pmac_enabled:1; + __u32 tx_enabled:1; + __u32 tx_active:1; + __u32 tx_min_frag_size:1; + __u32 rx_min_frag_size:1; + __u32 verify_enabled:1; + __u32 verify_time:1; + __u32 max_verify_time:1; + __u32 stats:1; + } _present; + + struct ethtool_header header; + __u8 pmac_enabled; + __u8 tx_enabled; + __u8 tx_active; + __u32 tx_min_frag_size; + __u32 rx_min_frag_size; + __u8 verify_enabled; + __u32 verify_time; + __u32 max_verify_time; + struct ethtool_mm_stat stats; +}; + +void ethtool_mm_get_rsp_free(struct ethtool_mm_get_rsp *rsp); + +/* + * Get MAC Merge configuration and state + */ +struct ethtool_mm_get_rsp * +ethtool_mm_get(struct ynl_sock *ys, struct ethtool_mm_get_req *req); + +/* ETHTOOL_MSG_MM_GET - dump */ +struct ethtool_mm_get_req_dump { + struct { + __u32 header:1; + } _present; + + struct ethtool_header header; +}; + +static inline struct ethtool_mm_get_req_dump * +ethtool_mm_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_mm_get_req_dump)); +} +void ethtool_mm_get_req_dump_free(struct ethtool_mm_get_req_dump *req); + +static inline void +ethtool_mm_get_req_dump_set_header_dev_index(struct ethtool_mm_get_req_dump *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_mm_get_req_dump_set_header_dev_name(struct ethtool_mm_get_req_dump *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_mm_get_req_dump_set_header_flags(struct ethtool_mm_get_req_dump *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} + +struct ethtool_mm_get_list { + struct ethtool_mm_get_list *next; + struct ethtool_mm_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_mm_get_list_free(struct ethtool_mm_get_list *rsp); + +struct ethtool_mm_get_list * +ethtool_mm_get_dump(struct ynl_sock *ys, struct ethtool_mm_get_req_dump *req); + +/* ETHTOOL_MSG_MM_GET - notify */ +struct ethtool_mm_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_mm_get_ntf *ntf); + struct ethtool_mm_get_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_mm_get_ntf_free(struct ethtool_mm_get_ntf *rsp); + +/* ============== ETHTOOL_MSG_MM_SET ============== */ +/* ETHTOOL_MSG_MM_SET - do */ +struct ethtool_mm_set_req { + struct { + __u32 header:1; + __u32 verify_enabled:1; + __u32 verify_time:1; + __u32 tx_enabled:1; + __u32 pmac_enabled:1; + __u32 tx_min_frag_size:1; + } _present; + + struct ethtool_header header; + __u8 verify_enabled; + __u32 verify_time; + __u8 tx_enabled; + __u8 pmac_enabled; + __u32 tx_min_frag_size; +}; + +static inline struct ethtool_mm_set_req *ethtool_mm_set_req_alloc(void) +{ + return calloc(1, sizeof(struct ethtool_mm_set_req)); +} +void ethtool_mm_set_req_free(struct ethtool_mm_set_req *req); + +static inline void +ethtool_mm_set_req_set_header_dev_index(struct ethtool_mm_set_req *req, + __u32 dev_index) +{ + req->_present.header = 1; + req->header._present.dev_index = 1; + req->header.dev_index = dev_index; +} +static inline void +ethtool_mm_set_req_set_header_dev_name(struct ethtool_mm_set_req *req, + const char *dev_name) +{ + free(req->header.dev_name); + req->header._present.dev_name_len = strlen(dev_name); + req->header.dev_name = malloc(req->header._present.dev_name_len + 1); + memcpy(req->header.dev_name, dev_name, req->header._present.dev_name_len); + req->header.dev_name[req->header._present.dev_name_len] = 0; +} +static inline void +ethtool_mm_set_req_set_header_flags(struct ethtool_mm_set_req *req, + __u32 flags) +{ + req->_present.header = 1; + req->header._present.flags = 1; + req->header.flags = flags; +} +static inline void +ethtool_mm_set_req_set_verify_enabled(struct ethtool_mm_set_req *req, + __u8 verify_enabled) +{ + req->_present.verify_enabled = 1; + req->verify_enabled = verify_enabled; +} +static inline void +ethtool_mm_set_req_set_verify_time(struct ethtool_mm_set_req *req, + __u32 verify_time) +{ + req->_present.verify_time = 1; + req->verify_time = verify_time; +} +static inline void +ethtool_mm_set_req_set_tx_enabled(struct ethtool_mm_set_req *req, + __u8 tx_enabled) +{ + req->_present.tx_enabled = 1; + req->tx_enabled = tx_enabled; +} +static inline void +ethtool_mm_set_req_set_pmac_enabled(struct ethtool_mm_set_req *req, + __u8 pmac_enabled) +{ + req->_present.pmac_enabled = 1; + req->pmac_enabled = pmac_enabled; +} +static inline void +ethtool_mm_set_req_set_tx_min_frag_size(struct ethtool_mm_set_req *req, + __u32 tx_min_frag_size) +{ + req->_present.tx_min_frag_size = 1; + req->tx_min_frag_size = tx_min_frag_size; +} + +/* + * Set MAC Merge configuration + */ +int ethtool_mm_set(struct ynl_sock *ys, struct ethtool_mm_set_req *req); + +/* ETHTOOL_MSG_CABLE_TEST_NTF - event */ +struct ethtool_cable_test_ntf_rsp { + struct { + __u32 header:1; + __u32 status:1; + } _present; + + struct ethtool_header header; + __u8 status; +}; + +struct ethtool_cable_test_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_cable_test_ntf *ntf); + struct ethtool_cable_test_ntf_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_cable_test_ntf_free(struct ethtool_cable_test_ntf *rsp); + +/* ETHTOOL_MSG_CABLE_TEST_TDR_NTF - event */ +struct ethtool_cable_test_tdr_ntf_rsp { + struct { + __u32 header:1; + __u32 status:1; + __u32 nest:1; + } _present; + + struct ethtool_header header; + __u8 status; + struct ethtool_cable_nest nest; +}; + +struct ethtool_cable_test_tdr_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ethtool_cable_test_tdr_ntf *ntf); + struct ethtool_cable_test_tdr_ntf_rsp obj __attribute__ ((aligned (8))); +}; + +void ethtool_cable_test_tdr_ntf_free(struct ethtool_cable_test_tdr_ntf *rsp); + +#endif /* _LINUX_ETHTOOL_GEN_H */ diff --git a/tools/net/ynl/generated/fou-user.c b/tools/net/ynl/generated/fou-user.c new file mode 100644 index 0000000000000..4271b5d43c586 --- /dev/null +++ b/tools/net/ynl/generated/fou-user.c @@ -0,0 +1,328 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/fou.yaml */ +/* YNL-GEN user source */ + +#include <stdlib.h> +#include <string.h> +#include "fou-user.h" +#include "ynl.h" +#include <linux/fou.h> + +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> + +/* Enums */ +static const char * const fou_op_strmap[] = { + [FOU_CMD_ADD] = "add", + [FOU_CMD_DEL] = "del", + [FOU_CMD_GET] = "get", +}; + +const char *fou_op_str(int op) +{ + if (op < 0 || op >= (int)MNL_ARRAY_SIZE(fou_op_strmap)) + return NULL; + return fou_op_strmap[op]; +} + +static const char * const fou_encap_type_strmap[] = { + [0] = "unspec", + [1] = "direct", + [2] = "gue", +}; + +const char *fou_encap_type_str(int value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(fou_encap_type_strmap)) + return NULL; + return fou_encap_type_strmap[value]; +} + +/* Policies */ +struct ynl_policy_attr fou_policy[FOU_ATTR_MAX + 1] = { + [FOU_ATTR_UNSPEC] = { .name = "unspec", .type = YNL_PT_REJECT, }, + [FOU_ATTR_PORT] = { .name = "port", .type = YNL_PT_U16, }, + [FOU_ATTR_AF] = { .name = "af", .type = YNL_PT_U8, }, + [FOU_ATTR_IPPROTO] = { .name = "ipproto", .type = YNL_PT_U8, }, + [FOU_ATTR_TYPE] = { .name = "type", .type = YNL_PT_U8, }, + [FOU_ATTR_REMCSUM_NOPARTIAL] = { .name = "remcsum_nopartial", .type = YNL_PT_FLAG, }, + [FOU_ATTR_LOCAL_V4] = { .name = "local_v4", .type = YNL_PT_U32, }, + [FOU_ATTR_LOCAL_V6] = { .name = "local_v6", .type = YNL_PT_BINARY,}, + [FOU_ATTR_PEER_V4] = { .name = "peer_v4", .type = YNL_PT_U32, }, + [FOU_ATTR_PEER_V6] = { .name = "peer_v6", .type = YNL_PT_BINARY,}, + [FOU_ATTR_PEER_PORT] = { .name = "peer_port", .type = YNL_PT_U16, }, + [FOU_ATTR_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest fou_nest = { + .max_attr = FOU_ATTR_MAX, + .table = fou_policy, +}; + +/* Common nested types */ +/* ============== FOU_CMD_ADD ============== */ +/* FOU_CMD_ADD - do */ +void fou_add_req_free(struct fou_add_req *req) +{ + free(req->local_v6); + free(req->peer_v6); + free(req); +} + +int fou_add(struct ynl_sock *ys, struct fou_add_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, FOU_CMD_ADD, 1); + ys->req_policy = &fou_nest; + + if (req->_present.port) + mnl_attr_put_u16(nlh, FOU_ATTR_PORT, req->port); + if (req->_present.ipproto) + mnl_attr_put_u8(nlh, FOU_ATTR_IPPROTO, req->ipproto); + if (req->_present.type) + mnl_attr_put_u8(nlh, FOU_ATTR_TYPE, req->type); + if (req->_present.remcsum_nopartial) + mnl_attr_put(nlh, FOU_ATTR_REMCSUM_NOPARTIAL, 0, NULL); + if (req->_present.local_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_LOCAL_V4, req->local_v4); + if (req->_present.peer_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_PEER_V4, req->peer_v4); + if (req->_present.local_v6_len) + mnl_attr_put(nlh, FOU_ATTR_LOCAL_V6, req->_present.local_v6_len, req->local_v6); + if (req->_present.peer_v6_len) + mnl_attr_put(nlh, FOU_ATTR_PEER_V6, req->_present.peer_v6_len, req->peer_v6); + if (req->_present.peer_port) + mnl_attr_put_u16(nlh, FOU_ATTR_PEER_PORT, req->peer_port); + if (req->_present.ifindex) + mnl_attr_put_u32(nlh, FOU_ATTR_IFINDEX, req->ifindex); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== FOU_CMD_DEL ============== */ +/* FOU_CMD_DEL - do */ +void fou_del_req_free(struct fou_del_req *req) +{ + free(req->local_v6); + free(req->peer_v6); + free(req); +} + +int fou_del(struct ynl_sock *ys, struct fou_del_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, FOU_CMD_DEL, 1); + ys->req_policy = &fou_nest; + + if (req->_present.af) + mnl_attr_put_u8(nlh, FOU_ATTR_AF, req->af); + if (req->_present.ifindex) + mnl_attr_put_u32(nlh, FOU_ATTR_IFINDEX, req->ifindex); + if (req->_present.port) + mnl_attr_put_u16(nlh, FOU_ATTR_PORT, req->port); + if (req->_present.peer_port) + mnl_attr_put_u16(nlh, FOU_ATTR_PEER_PORT, req->peer_port); + if (req->_present.local_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_LOCAL_V4, req->local_v4); + if (req->_present.peer_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_PEER_V4, req->peer_v4); + if (req->_present.local_v6_len) + mnl_attr_put(nlh, FOU_ATTR_LOCAL_V6, req->_present.local_v6_len, req->local_v6); + if (req->_present.peer_v6_len) + mnl_attr_put(nlh, FOU_ATTR_PEER_V6, req->_present.peer_v6_len, req->peer_v6); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== FOU_CMD_GET ============== */ +/* FOU_CMD_GET - do */ +void fou_get_req_free(struct fou_get_req *req) +{ + free(req->local_v6); + free(req->peer_v6); + free(req); +} + +void fou_get_rsp_free(struct fou_get_rsp *rsp) +{ + free(rsp->local_v6); + free(rsp->peer_v6); + free(rsp); +} + +int fou_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct fou_get_rsp *dst; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == FOU_ATTR_PORT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port = 1; + dst->port = mnl_attr_get_u16(attr); + } else if (type == FOU_ATTR_IPPROTO) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ipproto = 1; + dst->ipproto = mnl_attr_get_u8(attr); + } else if (type == FOU_ATTR_TYPE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.type = 1; + dst->type = mnl_attr_get_u8(attr); + } else if (type == FOU_ATTR_REMCSUM_NOPARTIAL) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.remcsum_nopartial = 1; + } else if (type == FOU_ATTR_LOCAL_V4) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.local_v4 = 1; + dst->local_v4 = mnl_attr_get_u32(attr); + } else if (type == FOU_ATTR_PEER_V4) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.peer_v4 = 1; + dst->peer_v4 = mnl_attr_get_u32(attr); + } else if (type == FOU_ATTR_LOCAL_V6) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.local_v6_len = len; + dst->local_v6 = malloc(len); + memcpy(dst->local_v6, mnl_attr_get_payload(attr), len); + } else if (type == FOU_ATTR_PEER_V6) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.peer_v6_len = len; + dst->peer_v6 = malloc(len); + memcpy(dst->peer_v6, mnl_attr_get_payload(attr), len); + } else if (type == FOU_ATTR_PEER_PORT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.peer_port = 1; + dst->peer_port = mnl_attr_get_u16(attr); + } else if (type == FOU_ATTR_IFINDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ifindex = 1; + dst->ifindex = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct fou_get_rsp *fou_get(struct ynl_sock *ys, struct fou_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct fou_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, FOU_CMD_GET, 1); + ys->req_policy = &fou_nest; + yrs.yarg.rsp_policy = &fou_nest; + + if (req->_present.af) + mnl_attr_put_u8(nlh, FOU_ATTR_AF, req->af); + if (req->_present.ifindex) + mnl_attr_put_u32(nlh, FOU_ATTR_IFINDEX, req->ifindex); + if (req->_present.port) + mnl_attr_put_u16(nlh, FOU_ATTR_PORT, req->port); + if (req->_present.peer_port) + mnl_attr_put_u16(nlh, FOU_ATTR_PEER_PORT, req->peer_port); + if (req->_present.local_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_LOCAL_V4, req->local_v4); + if (req->_present.peer_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_PEER_V4, req->peer_v4); + if (req->_present.local_v6_len) + mnl_attr_put(nlh, FOU_ATTR_LOCAL_V6, req->_present.local_v6_len, req->local_v6); + if (req->_present.peer_v6_len) + mnl_attr_put(nlh, FOU_ATTR_PEER_V6, req->_present.peer_v6_len, req->peer_v6); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = fou_get_rsp_parse; + yrs.rsp_cmd = FOU_CMD_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + fou_get_rsp_free(rsp); + return NULL; +} + +/* FOU_CMD_GET - dump */ +void fou_get_list_free(struct fou_get_list *rsp) +{ + struct fou_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.local_v6); + free(rsp->obj.peer_v6); + free(rsp); + } +} + +struct fou_get_list *fou_get_dump(struct ynl_sock *ys) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct fou_get_list); + yds.cb = fou_get_rsp_parse; + yds.rsp_cmd = FOU_CMD_GET; + yds.rsp_policy = &fou_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, FOU_CMD_GET, 1); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + fou_get_list_free(yds.first); + return NULL; +} + +const struct ynl_family ynl_fou_family = { + .name = "fou", +}; diff --git a/tools/net/ynl/generated/fou-user.h b/tools/net/ynl/generated/fou-user.h new file mode 100644 index 0000000000000..d8ab50579cd13 --- /dev/null +++ b/tools/net/ynl/generated/fou-user.h @@ -0,0 +1,337 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/fou.yaml */ +/* YNL-GEN user header */ + +#ifndef _LINUX_FOU_GEN_H +#define _LINUX_FOU_GEN_H + +#include <stdlib.h> +#include <string.h> +#include <linux/types.h> +#include <linux/fou.h> + +struct ynl_sock; + +extern const struct ynl_family ynl_fou_family; + +/* Enums */ +const char *fou_op_str(int op); +const char *fou_encap_type_str(int value); + +/* Common nested types */ +/* ============== FOU_CMD_ADD ============== */ +/* FOU_CMD_ADD - do */ +struct fou_add_req { + struct { + __u32 port:1; + __u32 ipproto:1; + __u32 type:1; + __u32 remcsum_nopartial:1; + __u32 local_v4:1; + __u32 peer_v4:1; + __u32 local_v6_len; + __u32 peer_v6_len; + __u32 peer_port:1; + __u32 ifindex:1; + } _present; + + __u16 port /* big-endian */; + __u8 ipproto; + __u8 type; + __u32 local_v4; + __u32 peer_v4; + void *local_v6; + void *peer_v6; + __u16 peer_port /* big-endian */; + __s32 ifindex; +}; + +static inline struct fou_add_req *fou_add_req_alloc(void) +{ + return calloc(1, sizeof(struct fou_add_req)); +} +void fou_add_req_free(struct fou_add_req *req); + +static inline void +fou_add_req_set_port(struct fou_add_req *req, __u16 port /* big-endian */) +{ + req->_present.port = 1; + req->port = port; +} +static inline void +fou_add_req_set_ipproto(struct fou_add_req *req, __u8 ipproto) +{ + req->_present.ipproto = 1; + req->ipproto = ipproto; +} +static inline void fou_add_req_set_type(struct fou_add_req *req, __u8 type) +{ + req->_present.type = 1; + req->type = type; +} +static inline void fou_add_req_set_remcsum_nopartial(struct fou_add_req *req) +{ + req->_present.remcsum_nopartial = 1; +} +static inline void +fou_add_req_set_local_v4(struct fou_add_req *req, __u32 local_v4) +{ + req->_present.local_v4 = 1; + req->local_v4 = local_v4; +} +static inline void +fou_add_req_set_peer_v4(struct fou_add_req *req, __u32 peer_v4) +{ + req->_present.peer_v4 = 1; + req->peer_v4 = peer_v4; +} +static inline void +fou_add_req_set_local_v6(struct fou_add_req *req, const void *local_v6, + size_t len) +{ + free(req->local_v6); + req->local_v6 = malloc(req->_present.local_v6_len); + memcpy(req->local_v6, local_v6, req->_present.local_v6_len); +} +static inline void +fou_add_req_set_peer_v6(struct fou_add_req *req, const void *peer_v6, + size_t len) +{ + free(req->peer_v6); + req->peer_v6 = malloc(req->_present.peer_v6_len); + memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len); +} +static inline void +fou_add_req_set_peer_port(struct fou_add_req *req, + __u16 peer_port /* big-endian */) +{ + req->_present.peer_port = 1; + req->peer_port = peer_port; +} +static inline void +fou_add_req_set_ifindex(struct fou_add_req *req, __s32 ifindex) +{ + req->_present.ifindex = 1; + req->ifindex = ifindex; +} + +/* + * Add port. + */ +int fou_add(struct ynl_sock *ys, struct fou_add_req *req); + +/* ============== FOU_CMD_DEL ============== */ +/* FOU_CMD_DEL - do */ +struct fou_del_req { + struct { + __u32 af:1; + __u32 ifindex:1; + __u32 port:1; + __u32 peer_port:1; + __u32 local_v4:1; + __u32 peer_v4:1; + __u32 local_v6_len; + __u32 peer_v6_len; + } _present; + + __u8 af; + __s32 ifindex; + __u16 port /* big-endian */; + __u16 peer_port /* big-endian */; + __u32 local_v4; + __u32 peer_v4; + void *local_v6; + void *peer_v6; +}; + +static inline struct fou_del_req *fou_del_req_alloc(void) +{ + return calloc(1, sizeof(struct fou_del_req)); +} +void fou_del_req_free(struct fou_del_req *req); + +static inline void fou_del_req_set_af(struct fou_del_req *req, __u8 af) +{ + req->_present.af = 1; + req->af = af; +} +static inline void +fou_del_req_set_ifindex(struct fou_del_req *req, __s32 ifindex) +{ + req->_present.ifindex = 1; + req->ifindex = ifindex; +} +static inline void +fou_del_req_set_port(struct fou_del_req *req, __u16 port /* big-endian */) +{ + req->_present.port = 1; + req->port = port; +} +static inline void +fou_del_req_set_peer_port(struct fou_del_req *req, + __u16 peer_port /* big-endian */) +{ + req->_present.peer_port = 1; + req->peer_port = peer_port; +} +static inline void +fou_del_req_set_local_v4(struct fou_del_req *req, __u32 local_v4) +{ + req->_present.local_v4 = 1; + req->local_v4 = local_v4; +} +static inline void +fou_del_req_set_peer_v4(struct fou_del_req *req, __u32 peer_v4) +{ + req->_present.peer_v4 = 1; + req->peer_v4 = peer_v4; +} +static inline void +fou_del_req_set_local_v6(struct fou_del_req *req, const void *local_v6, + size_t len) +{ + free(req->local_v6); + req->local_v6 = malloc(req->_present.local_v6_len); + memcpy(req->local_v6, local_v6, req->_present.local_v6_len); +} +static inline void +fou_del_req_set_peer_v6(struct fou_del_req *req, const void *peer_v6, + size_t len) +{ + free(req->peer_v6); + req->peer_v6 = malloc(req->_present.peer_v6_len); + memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len); +} + +/* + * Delete port. + */ +int fou_del(struct ynl_sock *ys, struct fou_del_req *req); + +/* ============== FOU_CMD_GET ============== */ +/* FOU_CMD_GET - do */ +struct fou_get_req { + struct { + __u32 af:1; + __u32 ifindex:1; + __u32 port:1; + __u32 peer_port:1; + __u32 local_v4:1; + __u32 peer_v4:1; + __u32 local_v6_len; + __u32 peer_v6_len; + } _present; + + __u8 af; + __s32 ifindex; + __u16 port /* big-endian */; + __u16 peer_port /* big-endian */; + __u32 local_v4; + __u32 peer_v4; + void *local_v6; + void *peer_v6; +}; + +static inline struct fou_get_req *fou_get_req_alloc(void) +{ + return calloc(1, sizeof(struct fou_get_req)); +} +void fou_get_req_free(struct fou_get_req *req); + +static inline void fou_get_req_set_af(struct fou_get_req *req, __u8 af) +{ + req->_present.af = 1; + req->af = af; +} +static inline void +fou_get_req_set_ifindex(struct fou_get_req *req, __s32 ifindex) +{ + req->_present.ifindex = 1; + req->ifindex = ifindex; +} +static inline void +fou_get_req_set_port(struct fou_get_req *req, __u16 port /* big-endian */) +{ + req->_present.port = 1; + req->port = port; +} +static inline void +fou_get_req_set_peer_port(struct fou_get_req *req, + __u16 peer_port /* big-endian */) +{ + req->_present.peer_port = 1; + req->peer_port = peer_port; +} +static inline void +fou_get_req_set_local_v4(struct fou_get_req *req, __u32 local_v4) +{ + req->_present.local_v4 = 1; + req->local_v4 = local_v4; +} +static inline void +fou_get_req_set_peer_v4(struct fou_get_req *req, __u32 peer_v4) +{ + req->_present.peer_v4 = 1; + req->peer_v4 = peer_v4; +} +static inline void +fou_get_req_set_local_v6(struct fou_get_req *req, const void *local_v6, + size_t len) +{ + free(req->local_v6); + req->local_v6 = malloc(req->_present.local_v6_len); + memcpy(req->local_v6, local_v6, req->_present.local_v6_len); +} +static inline void +fou_get_req_set_peer_v6(struct fou_get_req *req, const void *peer_v6, + size_t len) +{ + free(req->peer_v6); + req->peer_v6 = malloc(req->_present.peer_v6_len); + memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len); +} + +struct fou_get_rsp { + struct { + __u32 port:1; + __u32 ipproto:1; + __u32 type:1; + __u32 remcsum_nopartial:1; + __u32 local_v4:1; + __u32 peer_v4:1; + __u32 local_v6_len; + __u32 peer_v6_len; + __u32 peer_port:1; + __u32 ifindex:1; + } _present; + + __u16 port /* big-endian */; + __u8 ipproto; + __u8 type; + __u32 local_v4; + __u32 peer_v4; + void *local_v6; + void *peer_v6; + __u16 peer_port /* big-endian */; + __s32 ifindex; +}; + +void fou_get_rsp_free(struct fou_get_rsp *rsp); + +/* + * Get tunnel info. + */ +struct fou_get_rsp *fou_get(struct ynl_sock *ys, struct fou_get_req *req); + +/* FOU_CMD_GET - dump */ +struct fou_get_list { + struct fou_get_list *next; + struct fou_get_rsp obj __attribute__ ((aligned (8))); +}; + +void fou_get_list_free(struct fou_get_list *rsp); + +struct fou_get_list *fou_get_dump(struct ynl_sock *ys); + +#endif /* _LINUX_FOU_GEN_H */ diff --git a/tools/net/ynl/generated/handshake-user.c b/tools/net/ynl/generated/handshake-user.c new file mode 100644 index 0000000000000..7c67765daf902 --- /dev/null +++ b/tools/net/ynl/generated/handshake-user.c @@ -0,0 +1,331 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/handshake.yaml */ +/* YNL-GEN user source */ + +#include <stdlib.h> +#include <string.h> +#include "handshake-user.h" +#include "ynl.h" +#include <linux/handshake.h> + +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> + +/* Enums */ +static const char * const handshake_op_strmap[] = { + [HANDSHAKE_CMD_READY] = "ready", + [HANDSHAKE_CMD_ACCEPT] = "accept", + [HANDSHAKE_CMD_DONE] = "done", +}; + +const char *handshake_op_str(int op) +{ + if (op < 0 || op >= (int)MNL_ARRAY_SIZE(handshake_op_strmap)) + return NULL; + return handshake_op_strmap[op]; +} + +static const char * const handshake_handler_class_strmap[] = { + [0] = "none", + [1] = "tlshd", + [2] = "max", +}; + +const char *handshake_handler_class_str(enum handshake_handler_class value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(handshake_handler_class_strmap)) + return NULL; + return handshake_handler_class_strmap[value]; +} + +static const char * const handshake_msg_type_strmap[] = { + [0] = "unspec", + [1] = "clienthello", + [2] = "serverhello", +}; + +const char *handshake_msg_type_str(enum handshake_msg_type value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(handshake_msg_type_strmap)) + return NULL; + return handshake_msg_type_strmap[value]; +} + +static const char * const handshake_auth_strmap[] = { + [0] = "unspec", + [1] = "unauth", + [2] = "psk", + [3] = "x509", +}; + +const char *handshake_auth_str(enum handshake_auth value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(handshake_auth_strmap)) + return NULL; + return handshake_auth_strmap[value]; +} + +/* Policies */ +struct ynl_policy_attr handshake_x509_policy[HANDSHAKE_A_X509_MAX + 1] = { + [HANDSHAKE_A_X509_CERT] = { .name = "cert", .type = YNL_PT_U32, }, + [HANDSHAKE_A_X509_PRIVKEY] = { .name = "privkey", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest handshake_x509_nest = { + .max_attr = HANDSHAKE_A_X509_MAX, + .table = handshake_x509_policy, +}; + +struct ynl_policy_attr handshake_accept_policy[HANDSHAKE_A_ACCEPT_MAX + 1] = { + [HANDSHAKE_A_ACCEPT_SOCKFD] = { .name = "sockfd", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_HANDLER_CLASS] = { .name = "handler-class", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_MESSAGE_TYPE] = { .name = "message-type", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_TIMEOUT] = { .name = "timeout", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_AUTH_MODE] = { .name = "auth-mode", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_PEER_IDENTITY] = { .name = "peer-identity", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_CERTIFICATE] = { .name = "certificate", .type = YNL_PT_NEST, .nest = &handshake_x509_nest, }, + [HANDSHAKE_A_ACCEPT_PEERNAME] = { .name = "peername", .type = YNL_PT_NUL_STR, }, +}; + +struct ynl_policy_nest handshake_accept_nest = { + .max_attr = HANDSHAKE_A_ACCEPT_MAX, + .table = handshake_accept_policy, +}; + +struct ynl_policy_attr handshake_done_policy[HANDSHAKE_A_DONE_MAX + 1] = { + [HANDSHAKE_A_DONE_STATUS] = { .name = "status", .type = YNL_PT_U32, }, + [HANDSHAKE_A_DONE_SOCKFD] = { .name = "sockfd", .type = YNL_PT_U32, }, + [HANDSHAKE_A_DONE_REMOTE_AUTH] = { .name = "remote-auth", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest handshake_done_nest = { + .max_attr = HANDSHAKE_A_DONE_MAX, + .table = handshake_done_policy, +}; + +/* Common nested types */ +void handshake_x509_free(struct handshake_x509 *obj) +{ +} + +int handshake_x509_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct handshake_x509 *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == HANDSHAKE_A_X509_CERT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.cert = 1; + dst->cert = mnl_attr_get_u32(attr); + } else if (type == HANDSHAKE_A_X509_PRIVKEY) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.privkey = 1; + dst->privkey = mnl_attr_get_u32(attr); + } + } + + return 0; +} + +/* ============== HANDSHAKE_CMD_ACCEPT ============== */ +/* HANDSHAKE_CMD_ACCEPT - do */ +void handshake_accept_req_free(struct handshake_accept_req *req) +{ + free(req); +} + +void handshake_accept_rsp_free(struct handshake_accept_rsp *rsp) +{ + unsigned int i; + + free(rsp->peer_identity); + for (i = 0; i < rsp->n_certificate; i++) + handshake_x509_free(&rsp->certificate[i]); + free(rsp->certificate); + free(rsp->peername); + free(rsp); +} + +int handshake_accept_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct handshake_accept_rsp *dst; + unsigned int n_peer_identity = 0; + unsigned int n_certificate = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + dst = yarg->data; + parg.ys = yarg->ys; + + if (dst->certificate) + return ynl_error_parse(yarg, "attribute already present (accept.certificate)"); + if (dst->peer_identity) + return ynl_error_parse(yarg, "attribute already present (accept.peer-identity)"); + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == HANDSHAKE_A_ACCEPT_SOCKFD) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sockfd = 1; + dst->sockfd = mnl_attr_get_u32(attr); + } else if (type == HANDSHAKE_A_ACCEPT_MESSAGE_TYPE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.message_type = 1; + dst->message_type = mnl_attr_get_u32(attr); + } else if (type == HANDSHAKE_A_ACCEPT_TIMEOUT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.timeout = 1; + dst->timeout = mnl_attr_get_u32(attr); + } else if (type == HANDSHAKE_A_ACCEPT_AUTH_MODE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.auth_mode = 1; + dst->auth_mode = mnl_attr_get_u32(attr); + } else if (type == HANDSHAKE_A_ACCEPT_PEER_IDENTITY) { + n_peer_identity++; + } else if (type == HANDSHAKE_A_ACCEPT_CERTIFICATE) { + n_certificate++; + } else if (type == HANDSHAKE_A_ACCEPT_PEERNAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.peername_len = len; + dst->peername = malloc(len + 1); + memcpy(dst->peername, mnl_attr_get_str(attr), len); + dst->peername[len] = 0; + } + } + + if (n_certificate) { + dst->certificate = calloc(n_certificate, sizeof(*dst->certificate)); + dst->n_certificate = n_certificate; + i = 0; + parg.rsp_policy = &handshake_x509_nest; + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == HANDSHAKE_A_ACCEPT_CERTIFICATE) { + parg.data = &dst->certificate[i]; + if (handshake_x509_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + if (n_peer_identity) { + dst->peer_identity = calloc(n_peer_identity, sizeof(*dst->peer_identity)); + dst->n_peer_identity = n_peer_identity; + i = 0; + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == HANDSHAKE_A_ACCEPT_PEER_IDENTITY) { + dst->peer_identity[i] = mnl_attr_get_u32(attr); + i++; + } + } + } + + return MNL_CB_OK; +} + +struct handshake_accept_rsp * +handshake_accept(struct ynl_sock *ys, struct handshake_accept_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct handshake_accept_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, HANDSHAKE_CMD_ACCEPT, 1); + ys->req_policy = &handshake_accept_nest; + yrs.yarg.rsp_policy = &handshake_accept_nest; + + if (req->_present.handler_class) + mnl_attr_put_u32(nlh, HANDSHAKE_A_ACCEPT_HANDLER_CLASS, req->handler_class); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = handshake_accept_rsp_parse; + yrs.rsp_cmd = HANDSHAKE_CMD_ACCEPT; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + handshake_accept_rsp_free(rsp); + return NULL; +} + +/* HANDSHAKE_CMD_ACCEPT - notify */ +void handshake_accept_ntf_free(struct handshake_accept_ntf *rsp) +{ + unsigned int i; + + free(rsp->obj.peer_identity); + for (i = 0; i < rsp->obj.n_certificate; i++) + handshake_x509_free(&rsp->obj.certificate[i]); + free(rsp->obj.certificate); + free(rsp->obj.peername); + free(rsp); +} + +/* ============== HANDSHAKE_CMD_DONE ============== */ +/* HANDSHAKE_CMD_DONE - do */ +void handshake_done_req_free(struct handshake_done_req *req) +{ + free(req->remote_auth); + free(req); +} + +int handshake_done(struct ynl_sock *ys, struct handshake_done_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, HANDSHAKE_CMD_DONE, 1); + ys->req_policy = &handshake_done_nest; + + if (req->_present.status) + mnl_attr_put_u32(nlh, HANDSHAKE_A_DONE_STATUS, req->status); + if (req->_present.sockfd) + mnl_attr_put_u32(nlh, HANDSHAKE_A_DONE_SOCKFD, req->sockfd); + for (unsigned int i = 0; i < req->n_remote_auth; i++) + mnl_attr_put_u32(nlh, HANDSHAKE_A_DONE_REMOTE_AUTH, req->remote_auth[i]); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +static const struct ynl_ntf_info handshake_ntf_info[] = { + [HANDSHAKE_CMD_READY] = { + .alloc_sz = sizeof(struct handshake_accept_ntf), + .cb = handshake_accept_rsp_parse, + .policy = &handshake_accept_nest, + .free = (void *)handshake_accept_ntf_free, + }, +}; + +const struct ynl_family ynl_handshake_family = { + .name = "handshake", + .ntf_info = handshake_ntf_info, + .ntf_info_size = MNL_ARRAY_SIZE(handshake_ntf_info), +}; diff --git a/tools/net/ynl/generated/handshake-user.h b/tools/net/ynl/generated/handshake-user.h new file mode 100644 index 0000000000000..47646bb91cea6 --- /dev/null +++ b/tools/net/ynl/generated/handshake-user.h @@ -0,0 +1,145 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/handshake.yaml */ +/* YNL-GEN user header */ + +#ifndef _LINUX_HANDSHAKE_GEN_H +#define _LINUX_HANDSHAKE_GEN_H + +#include <stdlib.h> +#include <string.h> +#include <linux/types.h> +#include <linux/handshake.h> + +struct ynl_sock; + +extern const struct ynl_family ynl_handshake_family; + +/* Enums */ +const char *handshake_op_str(int op); +const char *handshake_handler_class_str(enum handshake_handler_class value); +const char *handshake_msg_type_str(enum handshake_msg_type value); +const char *handshake_auth_str(enum handshake_auth value); + +/* Common nested types */ +struct handshake_x509 { + struct { + __u32 cert:1; + __u32 privkey:1; + } _present; + + __u32 cert; + __u32 privkey; +}; + +/* ============== HANDSHAKE_CMD_ACCEPT ============== */ +/* HANDSHAKE_CMD_ACCEPT - do */ +struct handshake_accept_req { + struct { + __u32 handler_class:1; + } _present; + + enum handshake_handler_class handler_class; +}; + +static inline struct handshake_accept_req *handshake_accept_req_alloc(void) +{ + return calloc(1, sizeof(struct handshake_accept_req)); +} +void handshake_accept_req_free(struct handshake_accept_req *req); + +static inline void +handshake_accept_req_set_handler_class(struct handshake_accept_req *req, + enum handshake_handler_class handler_class) +{ + req->_present.handler_class = 1; + req->handler_class = handler_class; +} + +struct handshake_accept_rsp { + struct { + __u32 sockfd:1; + __u32 message_type:1; + __u32 timeout:1; + __u32 auth_mode:1; + __u32 peername_len; + } _present; + + __u32 sockfd; + enum handshake_msg_type message_type; + __u32 timeout; + enum handshake_auth auth_mode; + unsigned int n_peer_identity; + __u32 *peer_identity; + unsigned int n_certificate; + struct handshake_x509 *certificate; + char *peername; +}; + +void handshake_accept_rsp_free(struct handshake_accept_rsp *rsp); + +/* + * Handler retrieves next queued handshake request + */ +struct handshake_accept_rsp * +handshake_accept(struct ynl_sock *ys, struct handshake_accept_req *req); + +/* HANDSHAKE_CMD_ACCEPT - notify */ +struct handshake_accept_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct handshake_accept_ntf *ntf); + struct handshake_accept_rsp obj __attribute__ ((aligned (8))); +}; + +void handshake_accept_ntf_free(struct handshake_accept_ntf *rsp); + +/* ============== HANDSHAKE_CMD_DONE ============== */ +/* HANDSHAKE_CMD_DONE - do */ +struct handshake_done_req { + struct { + __u32 status:1; + __u32 sockfd:1; + } _present; + + __u32 status; + __u32 sockfd; + unsigned int n_remote_auth; + __u32 *remote_auth; +}; + +static inline struct handshake_done_req *handshake_done_req_alloc(void) +{ + return calloc(1, sizeof(struct handshake_done_req)); +} +void handshake_done_req_free(struct handshake_done_req *req); + +static inline void +handshake_done_req_set_status(struct handshake_done_req *req, __u32 status) +{ + req->_present.status = 1; + req->status = status; +} +static inline void +handshake_done_req_set_sockfd(struct handshake_done_req *req, __u32 sockfd) +{ + req->_present.sockfd = 1; + req->sockfd = sockfd; +} +static inline void +__handshake_done_req_set_remote_auth(struct handshake_done_req *req, + __u32 *remote_auth, + unsigned int n_remote_auth) +{ + free(req->remote_auth); + req->remote_auth = remote_auth; + req->n_remote_auth = n_remote_auth; +} + +/* + * Handler reports handshake completion + */ +int handshake_done(struct ynl_sock *ys, struct handshake_done_req *req); + +#endif /* _LINUX_HANDSHAKE_GEN_H */ diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c new file mode 100644 index 0000000000000..4eb8aefef0cd2 --- /dev/null +++ b/tools/net/ynl/generated/netdev-user.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN user source */ + +#include <stdlib.h> +#include <string.h> +#include "netdev-user.h" +#include "ynl.h" +#include <linux/netdev.h> + +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> + +/* Enums */ +static const char * const netdev_op_strmap[] = { + [NETDEV_CMD_DEV_GET] = "dev-get", + [NETDEV_CMD_DEV_ADD_NTF] = "dev-add-ntf", + [NETDEV_CMD_DEV_DEL_NTF] = "dev-del-ntf", + [NETDEV_CMD_DEV_CHANGE_NTF] = "dev-change-ntf", +}; + +const char *netdev_op_str(int op) +{ + if (op < 0 || op >= (int)MNL_ARRAY_SIZE(netdev_op_strmap)) + return NULL; + return netdev_op_strmap[op]; +} + +static const char * const netdev_xdp_act_strmap[] = { + [0] = "basic", + [1] = "redirect", + [2] = "ndo-xmit", + [3] = "xsk-zerocopy", + [4] = "hw-offload", + [5] = "rx-sg", + [6] = "ndo-xmit-sg", +}; + +const char *netdev_xdp_act_str(enum netdev_xdp_act value) +{ + value = ffs(value) - 1; + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(netdev_xdp_act_strmap)) + return NULL; + return netdev_xdp_act_strmap[value]; +} + +/* Policies */ +struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = { + [NETDEV_A_DEV_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, + [NETDEV_A_DEV_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, }, + [NETDEV_A_DEV_XDP_FEATURES] = { .name = "xdp-features", .type = YNL_PT_U64, }, +}; + +struct ynl_policy_nest netdev_dev_nest = { + .max_attr = NETDEV_A_DEV_MAX, + .table = netdev_dev_policy, +}; + +/* Common nested types */ +/* ============== NETDEV_CMD_DEV_GET ============== */ +/* NETDEV_CMD_DEV_GET - do */ +void netdev_dev_get_req_free(struct netdev_dev_get_req *req) +{ + free(req); +} + +void netdev_dev_get_rsp_free(struct netdev_dev_get_rsp *rsp) +{ + free(rsp); +} + +int netdev_dev_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct netdev_dev_get_rsp *dst; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == NETDEV_A_DEV_IFINDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ifindex = 1; + dst->ifindex = mnl_attr_get_u32(attr); + } else if (type == NETDEV_A_DEV_XDP_FEATURES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.xdp_features = 1; + dst->xdp_features = mnl_attr_get_u64(attr); + } + } + + return MNL_CB_OK; +} + +struct netdev_dev_get_rsp * +netdev_dev_get(struct ynl_sock *ys, struct netdev_dev_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct netdev_dev_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, NETDEV_CMD_DEV_GET, 1); + ys->req_policy = &netdev_dev_nest; + yrs.yarg.rsp_policy = &netdev_dev_nest; + + if (req->_present.ifindex) + mnl_attr_put_u32(nlh, NETDEV_A_DEV_IFINDEX, req->ifindex); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = netdev_dev_get_rsp_parse; + yrs.rsp_cmd = NETDEV_CMD_DEV_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + netdev_dev_get_rsp_free(rsp); + return NULL; +} + +/* NETDEV_CMD_DEV_GET - dump */ +void netdev_dev_get_list_free(struct netdev_dev_get_list *rsp) +{ + struct netdev_dev_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp); + } +} + +struct netdev_dev_get_list *netdev_dev_get_dump(struct ynl_sock *ys) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct netdev_dev_get_list); + yds.cb = netdev_dev_get_rsp_parse; + yds.rsp_cmd = NETDEV_CMD_DEV_GET; + yds.rsp_policy = &netdev_dev_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, NETDEV_CMD_DEV_GET, 1); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + netdev_dev_get_list_free(yds.first); + return NULL; +} + +/* NETDEV_CMD_DEV_GET - notify */ +void netdev_dev_get_ntf_free(struct netdev_dev_get_ntf *rsp) +{ + free(rsp); +} + +static const struct ynl_ntf_info netdev_ntf_info[] = { + [NETDEV_CMD_DEV_ADD_NTF] = { + .alloc_sz = sizeof(struct netdev_dev_get_ntf), + .cb = netdev_dev_get_rsp_parse, + .policy = &netdev_dev_nest, + .free = (void *)netdev_dev_get_ntf_free, + }, + [NETDEV_CMD_DEV_DEL_NTF] = { + .alloc_sz = sizeof(struct netdev_dev_get_ntf), + .cb = netdev_dev_get_rsp_parse, + .policy = &netdev_dev_nest, + .free = (void *)netdev_dev_get_ntf_free, + }, + [NETDEV_CMD_DEV_CHANGE_NTF] = { + .alloc_sz = sizeof(struct netdev_dev_get_ntf), + .cb = netdev_dev_get_rsp_parse, + .policy = &netdev_dev_nest, + .free = (void *)netdev_dev_get_ntf_free, + }, +}; + +const struct ynl_family ynl_netdev_family = { + .name = "netdev", + .ntf_info = netdev_ntf_info, + .ntf_info_size = MNL_ARRAY_SIZE(netdev_ntf_info), +}; diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h new file mode 100644 index 0000000000000..5554dc69bb9c8 --- /dev/null +++ b/tools/net/ynl/generated/netdev-user.h @@ -0,0 +1,85 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN user header */ + +#ifndef _LINUX_NETDEV_GEN_H +#define _LINUX_NETDEV_GEN_H + +#include <stdlib.h> +#include <string.h> +#include <linux/types.h> +#include <linux/netdev.h> + +struct ynl_sock; + +extern const struct ynl_family ynl_netdev_family; + +/* Enums */ +const char *netdev_op_str(int op); +const char *netdev_xdp_act_str(enum netdev_xdp_act value); + +/* Common nested types */ +/* ============== NETDEV_CMD_DEV_GET ============== */ +/* NETDEV_CMD_DEV_GET - do */ +struct netdev_dev_get_req { + struct { + __u32 ifindex:1; + } _present; + + __u32 ifindex; +}; + +static inline struct netdev_dev_get_req *netdev_dev_get_req_alloc(void) +{ + return calloc(1, sizeof(struct netdev_dev_get_req)); +} +void netdev_dev_get_req_free(struct netdev_dev_get_req *req); + +static inline void +netdev_dev_get_req_set_ifindex(struct netdev_dev_get_req *req, __u32 ifindex) +{ + req->_present.ifindex = 1; + req->ifindex = ifindex; +} + +struct netdev_dev_get_rsp { + struct { + __u32 ifindex:1; + __u32 xdp_features:1; + } _present; + + __u32 ifindex; + __u64 xdp_features; +}; + +void netdev_dev_get_rsp_free(struct netdev_dev_get_rsp *rsp); + +/* + * Get / dump information about a netdev. + */ +struct netdev_dev_get_rsp * +netdev_dev_get(struct ynl_sock *ys, struct netdev_dev_get_req *req); + +/* NETDEV_CMD_DEV_GET - dump */ +struct netdev_dev_get_list { + struct netdev_dev_get_list *next; + struct netdev_dev_get_rsp obj __attribute__ ((aligned (8))); +}; + +void netdev_dev_get_list_free(struct netdev_dev_get_list *rsp); + +struct netdev_dev_get_list *netdev_dev_get_dump(struct ynl_sock *ys); + +/* NETDEV_CMD_DEV_GET - notify */ +struct netdev_dev_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct netdev_dev_get_ntf *ntf); + struct netdev_dev_get_rsp obj __attribute__ ((aligned (8))); +}; + +void netdev_dev_get_ntf_free(struct netdev_dev_get_ntf *rsp); + +#endif /* _LINUX_NETDEV_GEN_H */ diff --git a/tools/net/ynl/lib/Makefile b/tools/net/ynl/lib/Makefile new file mode 100644 index 0000000000000..d2e50fd0a52dd --- /dev/null +++ b/tools/net/ynl/lib/Makefile @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 + +CC=gcc +CFLAGS=-std=gnu11 -O2 -W -Wall -Wextra -Wno-unused-parameter -Wshadow +ifeq ("$(DEBUG)","1") + CFLAGS += -g -fsanitize=address -fsanitize=leak -static-libasan +endif + +SRCS=$(wildcard *.c) +OBJS=$(patsubst %.c,%.o,${SRCS}) + +include $(wildcard *.d) + +all: ynl.a + +ynl.a: $(OBJS) + ar rcs $@ $(OBJS) +clean: + rm -f *.o *.d *~ + +hardclean: clean + rm -f *.a + +%.o: %.c + $(COMPILE.c) -MMD -c -o $@ $< + +.PHONY: all clean +.DEFAULT_GOAL=all diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/lib/nlspec.py index a0241add38392..0ff0d18666b2d 100644 --- a/tools/net/ynl/lib/nlspec.py +++ b/tools/net/ynl/lib/nlspec.py @@ -154,6 +154,9 @@ class SpecAttr(SpecElement): is_multi bool, attr may repeat multiple times struct_name string, name of struct definition sub_type string, name of sub type + len integer, optional byte length of binary types + display_hint string, hint to help choose format specifier + when displaying the value """ def __init__(self, family, attr_set, yaml, value): super().__init__(family, yaml) @@ -164,6 +167,8 @@ class SpecAttr(SpecElement): self.struct_name = yaml.get('struct') self.sub_type = yaml.get('sub-type') self.byte_order = yaml.get('byte-order') + self.len = yaml.get('len') + self.display_hint = yaml.get('display-hint') class SpecAttrSet(SpecElement): @@ -226,11 +231,20 @@ class SpecStructMember(SpecElement): Represents a single struct member attribute. Attributes: - type string, type of the member attribute + type string, type of the member attribute + byte_order string or None for native byte order + enum string, name of the enum definition + len integer, optional byte length of binary types + display_hint string, hint to help choose format specifier + when displaying the value """ def __init__(self, family, yaml): super().__init__(family, yaml) self.type = yaml['type'] + self.byte_order = yaml.get('byte-order') + self.enum = yaml.get('enum') + self.len = yaml.get('len') + self.display_hint = yaml.get('display-hint') class SpecStruct(SpecElement): @@ -320,16 +334,17 @@ class SpecFamily(SpecElement): Attributes: proto protocol type (e.g. genetlink) + msg_id_model enum-model for operations (unified, directional etc.) license spec license (loaded from an SPDX tag on the spec) attr_sets dict of attribute sets msgs dict of all messages (index by name) - msgs_by_value dict of all messages (indexed by name) ops dict of all valid requests / responses + ntfs dict of all async events consts dict of all constants/enums fixed_header string, optional name of family default fixed header struct """ - def __init__(self, spec_path, schema_path=None): + def __init__(self, spec_path, schema_path=None, exclude_ops=None): with open(spec_path, "r") as stream: prefix = '# SPDX-License-Identifier: ' first = stream.readline().strip() @@ -344,7 +359,10 @@ class SpecFamily(SpecElement): super().__init__(self, spec) + self._exclude_ops = exclude_ops if exclude_ops else [] + self.proto = self.yaml.get('protocol', 'genetlink') + self.msg_id_model = self.yaml['operations'].get('enum-model', 'unified') if schema_path is None: schema_path = os.path.dirname(os.path.dirname(spec_path)) + f'/{self.proto}.yaml' @@ -364,6 +382,7 @@ class SpecFamily(SpecElement): self.req_by_value = collections.OrderedDict() self.rsp_by_value = collections.OrderedDict() self.ops = collections.OrderedDict() + self.ntfs = collections.OrderedDict() self.consts = collections.OrderedDict() last_exception = None @@ -416,7 +435,7 @@ class SpecFamily(SpecElement): self.fixed_header = self.yaml['operations'].get('fixed-header') req_val = rsp_val = 1 for elem in self.yaml['operations']['list']: - if 'notify' in elem: + if 'notify' in elem or 'event' in elem: if 'value' in elem: rsp_val = elem['value'] req_val_next = req_val @@ -438,7 +457,17 @@ class SpecFamily(SpecElement): else: raise Exception("Can't parse directional ops") - op = self.new_operation(elem, req_val, rsp_val) + if req_val == req_val_next: + req_val = None + if rsp_val == rsp_val_next: + rsp_val = None + + skip = False + for exclude in self._exclude_ops: + skip |= bool(exclude.match(elem['name'])) + if not skip: + op = self.new_operation(elem, req_val, rsp_val) + req_val = req_val_next rsp_val = rsp_val_next @@ -469,10 +498,9 @@ class SpecFamily(SpecElement): attr_set = self.new_attr_set(elem) self.attr_sets[elem['name']] = attr_set - msg_id_model = self.yaml['operations'].get('enum-model', 'unified') - if msg_id_model == 'unified': + if self.msg_id_model == 'unified': self._dictify_ops_unified() - elif msg_id_model == 'directional': + elif self.msg_id_model == 'directional': self._dictify_ops_directional() for op in self.msgs.values(): @@ -482,3 +510,5 @@ class SpecFamily(SpecElement): self.rsp_by_value[op.rsp_value] = op if not op.is_async and 'attribute-set' in op: self.ops[op.name] = op + elif op.is_async: + self.ntfs[op.name] = op diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c new file mode 100644 index 0000000000000..514e0d69e7310 --- /dev/null +++ b/tools/net/ynl/lib/ynl.c @@ -0,0 +1,901 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +#include <errno.h> +#include <poll.h> +#include <string.h> +#include <stdlib.h> +#include <linux/types.h> + +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> + +#include "ynl.h" + +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(*arr)) + +#define __yerr_msg(yse, _msg...) \ + ({ \ + struct ynl_error *_yse = (yse); \ + \ + if (_yse) { \ + snprintf(_yse->msg, sizeof(_yse->msg) - 1, _msg); \ + _yse->msg[sizeof(_yse->msg) - 1] = 0; \ + } \ + }) + +#define __yerr_code(yse, _code...) \ + ({ \ + struct ynl_error *_yse = (yse); \ + \ + if (_yse) { \ + _yse->code = _code; \ + } \ + }) + +#define __yerr(yse, _code, _msg...) \ + ({ \ + __yerr_msg(yse, _msg); \ + __yerr_code(yse, _code); \ + }) + +#define __perr(yse, _msg) __yerr(yse, errno, _msg) + +#define yerr_msg(_ys, _msg...) __yerr_msg(&(_ys)->err, _msg) +#define yerr(_ys, _code, _msg...) __yerr(&(_ys)->err, _code, _msg) +#define perr(_ys, _msg) __yerr(&(_ys)->err, errno, _msg) + +/* -- Netlink boiler plate */ +static int +ynl_err_walk_report_one(struct ynl_policy_nest *policy, unsigned int type, + char *str, int str_sz, int *n) +{ + if (!policy) { + if (*n < str_sz) + *n += snprintf(str, str_sz, "!policy"); + return 1; + } + + if (type > policy->max_attr) { + if (*n < str_sz) + *n += snprintf(str, str_sz, "!oob"); + return 1; + } + + if (!policy->table[type].name) { + if (*n < str_sz) + *n += snprintf(str, str_sz, "!name"); + return 1; + } + + if (*n < str_sz) + *n += snprintf(str, str_sz - *n, + ".%s", policy->table[type].name); + return 0; +} + +static int +ynl_err_walk(struct ynl_sock *ys, void *start, void *end, unsigned int off, + struct ynl_policy_nest *policy, char *str, int str_sz, + struct ynl_policy_nest **nest_pol) +{ + unsigned int astart_off, aend_off; + const struct nlattr *attr; + unsigned int data_len; + unsigned int type; + bool found = false; + int n = 0; + + if (!policy) { + if (n < str_sz) + n += snprintf(str, str_sz, "!policy"); + return n; + } + + data_len = end - start; + + mnl_attr_for_each_payload(start, data_len) { + astart_off = (char *)attr - (char *)start; + aend_off = astart_off + mnl_attr_get_payload_len(attr); + if (aend_off <= off) + continue; + + found = true; + break; + } + if (!found) + return 0; + + off -= astart_off; + + type = mnl_attr_get_type(attr); + + if (ynl_err_walk_report_one(policy, type, str, str_sz, &n)) + return n; + + if (!off) { + if (nest_pol) + *nest_pol = policy->table[type].nest; + return n; + } + + if (!policy->table[type].nest) { + if (n < str_sz) + n += snprintf(str, str_sz, "!nest"); + return n; + } + + off -= sizeof(struct nlattr); + start = mnl_attr_get_payload(attr); + end = start + mnl_attr_get_payload_len(attr); + + return n + ynl_err_walk(ys, start, end, off, policy->table[type].nest, + &str[n], str_sz - n, nest_pol); +} + +#define NLMSGERR_ATTR_MISS_TYPE (NLMSGERR_ATTR_POLICY + 1) +#define NLMSGERR_ATTR_MISS_NEST (NLMSGERR_ATTR_POLICY + 2) +#define NLMSGERR_ATTR_MAX (NLMSGERR_ATTR_MAX + 2) + +static int +ynl_ext_ack_check(struct ynl_sock *ys, const struct nlmsghdr *nlh, + unsigned int hlen) +{ + const struct nlattr *tb[NLMSGERR_ATTR_MAX + 1] = {}; + char miss_attr[sizeof(ys->err.msg)]; + char bad_attr[sizeof(ys->err.msg)]; + const struct nlattr *attr; + const char *str = NULL; + + if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS)) + return MNL_CB_OK; + + mnl_attr_for_each(attr, nlh, hlen) { + unsigned int len, type; + + len = mnl_attr_get_payload_len(attr); + type = mnl_attr_get_type(attr); + + if (type > NLMSGERR_ATTR_MAX) + continue; + + tb[type] = attr; + + switch (type) { + case NLMSGERR_ATTR_OFFS: + case NLMSGERR_ATTR_MISS_TYPE: + case NLMSGERR_ATTR_MISS_NEST: + if (len != sizeof(__u32)) + return MNL_CB_ERROR; + break; + case NLMSGERR_ATTR_MSG: + str = mnl_attr_get_payload(attr); + if (str[len - 1]) + return MNL_CB_ERROR; + break; + default: + break; + } + } + + bad_attr[0] = '\0'; + miss_attr[0] = '\0'; + + if (tb[NLMSGERR_ATTR_OFFS]) { + unsigned int n, off; + void *start, *end; + + ys->err.attr_offs = mnl_attr_get_u32(tb[NLMSGERR_ATTR_OFFS]); + + n = snprintf(bad_attr, sizeof(bad_attr), "%sbad attribute: ", + str ? " (" : ""); + + start = mnl_nlmsg_get_payload_offset(ys->nlh, + sizeof(struct genlmsghdr)); + end = mnl_nlmsg_get_payload_tail(ys->nlh); + + off = ys->err.attr_offs; + off -= sizeof(struct nlmsghdr); + off -= sizeof(struct genlmsghdr); + + n += ynl_err_walk(ys, start, end, off, ys->req_policy, + &bad_attr[n], sizeof(bad_attr) - n, NULL); + + if (n >= sizeof(bad_attr)) + n = sizeof(bad_attr) - 1; + bad_attr[n] = '\0'; + } + if (tb[NLMSGERR_ATTR_MISS_TYPE]) { + struct ynl_policy_nest *nest_pol = NULL; + unsigned int n, off, type; + void *start, *end; + int n2; + + type = mnl_attr_get_u32(tb[NLMSGERR_ATTR_MISS_TYPE]); + + n = snprintf(miss_attr, sizeof(miss_attr), "%smissing attribute: ", + bad_attr[0] ? ", " : (str ? " (" : "")); + + start = mnl_nlmsg_get_payload_offset(ys->nlh, + sizeof(struct genlmsghdr)); + end = mnl_nlmsg_get_payload_tail(ys->nlh); + + nest_pol = ys->req_policy; + if (tb[NLMSGERR_ATTR_MISS_NEST]) { + off = mnl_attr_get_u32(tb[NLMSGERR_ATTR_MISS_NEST]); + off -= sizeof(struct nlmsghdr); + off -= sizeof(struct genlmsghdr); + + n += ynl_err_walk(ys, start, end, off, ys->req_policy, + &miss_attr[n], sizeof(miss_attr) - n, + &nest_pol); + } + + n2 = 0; + ynl_err_walk_report_one(nest_pol, type, &miss_attr[n], + sizeof(miss_attr) - n, &n2); + n += n2; + + if (n >= sizeof(miss_attr)) + n = sizeof(miss_attr) - 1; + miss_attr[n] = '\0'; + } + + /* Implicitly depend on ys->err.code already set */ + if (str) + yerr_msg(ys, "Kernel %s: '%s'%s%s%s", + ys->err.code ? "error" : "warning", + str, bad_attr, miss_attr, + bad_attr[0] || miss_attr[0] ? ")" : ""); + else if (bad_attr[0] || miss_attr[0]) + yerr_msg(ys, "Kernel %s: %s%s", + ys->err.code ? "error" : "warning", + bad_attr, miss_attr); + + return MNL_CB_OK; +} + +static int ynl_cb_error(const struct nlmsghdr *nlh, void *data) +{ + const struct nlmsgerr *err = mnl_nlmsg_get_payload(nlh); + struct ynl_parse_arg *yarg = data; + unsigned int hlen; + int code; + + code = err->error >= 0 ? err->error : -err->error; + yarg->ys->err.code = code; + errno = code; + + hlen = sizeof(*err); + if (!(nlh->nlmsg_flags & NLM_F_CAPPED)) + hlen += mnl_nlmsg_get_payload_len(&err->msg); + + ynl_ext_ack_check(yarg->ys, nlh, hlen); + + return code ? MNL_CB_ERROR : MNL_CB_STOP; +} + +static int ynl_cb_done(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + int err; + + err = *(int *)NLMSG_DATA(nlh); + if (err < 0) { + yarg->ys->err.code = -err; + errno = -err; + + ynl_ext_ack_check(yarg->ys, nlh, sizeof(int)); + + return MNL_CB_ERROR; + } + return MNL_CB_STOP; +} + +static int ynl_cb_noop(const struct nlmsghdr *nlh, void *data) +{ + return MNL_CB_OK; +} + +mnl_cb_t ynl_cb_array[NLMSG_MIN_TYPE] = { + [NLMSG_NOOP] = ynl_cb_noop, + [NLMSG_ERROR] = ynl_cb_error, + [NLMSG_DONE] = ynl_cb_done, + [NLMSG_OVERRUN] = ynl_cb_noop, +}; + +/* Attribute validation */ + +int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr) +{ + struct ynl_policy_attr *policy; + unsigned int type, len; + unsigned char *data; + + data = mnl_attr_get_payload(attr); + len = mnl_attr_get_payload_len(attr); + type = mnl_attr_get_type(attr); + if (type > yarg->rsp_policy->max_attr) { + yerr(yarg->ys, YNL_ERROR_INTERNAL, + "Internal error, validating unknown attribute"); + return -1; + } + + policy = &yarg->rsp_policy->table[type]; + + switch (policy->type) { + case YNL_PT_REJECT: + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Rejected attribute (%s)", policy->name); + return -1; + case YNL_PT_IGNORE: + break; + case YNL_PT_U8: + if (len == sizeof(__u8)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (u8 %s)", policy->name); + return -1; + case YNL_PT_U16: + if (len == sizeof(__u16)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (u16 %s)", policy->name); + return -1; + case YNL_PT_U32: + if (len == sizeof(__u32)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (u32 %s)", policy->name); + return -1; + case YNL_PT_U64: + if (len == sizeof(__u64)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (u64 %s)", policy->name); + return -1; + case YNL_PT_FLAG: + /* Let flags grow into real attrs, why not.. */ + break; + case YNL_PT_NEST: + if (!len || len >= sizeof(*attr)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (nest %s)", policy->name); + return -1; + case YNL_PT_BINARY: + if (!policy->len || len == policy->len) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (binary %s)", policy->name); + return -1; + case YNL_PT_NUL_STR: + if ((!policy->len || len <= policy->len) && !data[len - 1]) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (string %s)", policy->name); + return -1; + default: + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (unknown %s)", policy->name); + return -1; + } + + return 0; +} + +/* Generic code */ + +static void ynl_err_reset(struct ynl_sock *ys) +{ + ys->err.code = 0; + ys->err.attr_offs = 0; + ys->err.msg[0] = 0; +} + +struct nlmsghdr *ynl_msg_start(struct ynl_sock *ys, __u32 id, __u16 flags) +{ + struct nlmsghdr *nlh; + + ynl_err_reset(ys); + + nlh = ys->nlh = mnl_nlmsg_put_header(ys->tx_buf); + nlh->nlmsg_type = id; + nlh->nlmsg_flags = flags; + nlh->nlmsg_seq = ++ys->seq; + + return nlh; +} + +struct nlmsghdr * +ynl_gemsg_start(struct ynl_sock *ys, __u32 id, __u16 flags, + __u8 cmd, __u8 version) +{ + struct genlmsghdr gehdr; + struct nlmsghdr *nlh; + void *data; + + nlh = ynl_msg_start(ys, id, flags); + + memset(&gehdr, 0, sizeof(gehdr)); + gehdr.cmd = cmd; + gehdr.version = version; + + data = mnl_nlmsg_put_extra_header(nlh, sizeof(gehdr)); + memcpy(data, &gehdr, sizeof(gehdr)); + + return nlh; +} + +void ynl_msg_start_req(struct ynl_sock *ys, __u32 id) +{ + ynl_msg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK); +} + +void ynl_msg_start_dump(struct ynl_sock *ys, __u32 id) +{ + ynl_msg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP); +} + +struct nlmsghdr * +ynl_gemsg_start_req(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version) +{ + return ynl_gemsg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK, cmd, version); +} + +struct nlmsghdr * +ynl_gemsg_start_dump(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version) +{ + return ynl_gemsg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP, + cmd, version); +} + +int ynl_recv_ack(struct ynl_sock *ys, int ret) +{ + if (!ret) { + yerr(ys, YNL_ERROR_EXPECT_ACK, + "Expecting an ACK but nothing received"); + return -1; + } + + ret = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE); + if (ret < 0) { + perr(ys, "Socket receive failed"); + return ret; + } + return mnl_cb_run(ys->rx_buf, ret, ys->seq, ys->portid, + ynl_cb_null, ys); +} + +int ynl_cb_null(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + + yerr(yarg->ys, YNL_ERROR_UNEXPECT_MSG, + "Received a message when none were expected"); + + return MNL_CB_ERROR; +} + +/* Init/fini and genetlink boiler plate */ +static int +ynl_get_family_info_mcast(struct ynl_sock *ys, const struct nlattr *mcasts) +{ + const struct nlattr *entry, *attr; + unsigned int i; + + mnl_attr_for_each_nested(attr, mcasts) + ys->n_mcast_groups++; + + if (!ys->n_mcast_groups) + return 0; + + ys->mcast_groups = calloc(ys->n_mcast_groups, + sizeof(*ys->mcast_groups)); + if (!ys->mcast_groups) + return MNL_CB_ERROR; + + i = 0; + mnl_attr_for_each_nested(entry, mcasts) { + mnl_attr_for_each_nested(attr, entry) { + if (mnl_attr_get_type(attr) == CTRL_ATTR_MCAST_GRP_ID) + ys->mcast_groups[i].id = mnl_attr_get_u32(attr); + if (mnl_attr_get_type(attr) == CTRL_ATTR_MCAST_GRP_NAME) { + strncpy(ys->mcast_groups[i].name, + mnl_attr_get_str(attr), + GENL_NAMSIZ - 1); + ys->mcast_groups[i].name[GENL_NAMSIZ - 1] = 0; + } + } + } + + return 0; +} + +static int ynl_get_family_info_cb(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct ynl_sock *ys = yarg->ys; + const struct nlattr *attr; + bool found_id = true; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == CTRL_ATTR_MCAST_GROUPS) + if (ynl_get_family_info_mcast(ys, attr)) + return MNL_CB_ERROR; + + if (mnl_attr_get_type(attr) != CTRL_ATTR_FAMILY_ID) + continue; + + if (mnl_attr_get_payload_len(attr) != sizeof(__u16)) { + yerr(ys, YNL_ERROR_ATTR_INVALID, "Invalid family ID"); + return MNL_CB_ERROR; + } + + ys->family_id = mnl_attr_get_u16(attr); + found_id = true; + } + + if (!found_id) { + yerr(ys, YNL_ERROR_ATTR_MISSING, "Family ID missing"); + return MNL_CB_ERROR; + } + return MNL_CB_OK; +} + +static int ynl_sock_read_family(struct ynl_sock *ys, const char *family_name) +{ + struct ynl_parse_arg yarg = { .ys = ys, }; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, GENL_ID_CTRL, CTRL_CMD_GETFAMILY, 1); + mnl_attr_put_strz(nlh, CTRL_ATTR_FAMILY_NAME, family_name); + + err = mnl_socket_sendto(ys->sock, nlh, nlh->nlmsg_len); + if (err < 0) { + perr(ys, "failed to request socket family info"); + return err; + } + + err = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE); + if (err <= 0) { + perr(ys, "failed to receive the socket family info"); + return err; + } + err = mnl_cb_run2(ys->rx_buf, err, ys->seq, ys->portid, + ynl_get_family_info_cb, &yarg, + ynl_cb_array, ARRAY_SIZE(ynl_cb_array)); + if (err < 0) { + free(ys->mcast_groups); + perr(ys, "failed to receive the socket family info - no such family?"); + return err; + } + + return ynl_recv_ack(ys, err); +} + +struct ynl_sock * +ynl_sock_create(const struct ynl_family *yf, struct ynl_error *yse) +{ + struct ynl_sock *ys; + int one = 1; + + ys = malloc(sizeof(*ys) + 2 * MNL_SOCKET_BUFFER_SIZE); + if (!ys) + return NULL; + memset(ys, 0, sizeof(*ys)); + + ys->family = yf; + ys->tx_buf = &ys->raw_buf[0]; + ys->rx_buf = &ys->raw_buf[MNL_SOCKET_BUFFER_SIZE]; + ys->ntf_last_next = &ys->ntf_first; + + ys->sock = mnl_socket_open(NETLINK_GENERIC); + if (!ys->sock) { + __perr(yse, "failed to create a netlink socket"); + goto err_free_sock; + } + + if (mnl_socket_setsockopt(ys->sock, NETLINK_CAP_ACK, + &one, sizeof(one))) { + __perr(yse, "failed to enable netlink ACK"); + goto err_close_sock; + } + if (mnl_socket_setsockopt(ys->sock, NETLINK_EXT_ACK, + &one, sizeof(one))) { + __perr(yse, "failed to enable netlink ext ACK"); + goto err_close_sock; + } + + ys->seq = random(); + ys->portid = mnl_socket_get_portid(ys->sock); + + if (ynl_sock_read_family(ys, yf->name)) { + if (yse) + memcpy(yse, &ys->err, sizeof(*yse)); + goto err_close_sock; + } + + return ys; + +err_close_sock: + mnl_socket_close(ys->sock); +err_free_sock: + free(ys); + return NULL; +} + +void ynl_sock_destroy(struct ynl_sock *ys) +{ + struct ynl_ntf_base_type *ntf; + + mnl_socket_close(ys->sock); + while ((ntf = ynl_ntf_dequeue(ys))) + ynl_ntf_free(ntf); + free(ys->mcast_groups); + free(ys); +} + +/* YNL multicast handling */ + +void ynl_ntf_free(struct ynl_ntf_base_type *ntf) +{ + ntf->free(ntf); +} + +int ynl_subscribe(struct ynl_sock *ys, const char *grp_name) +{ + unsigned int i; + int err; + + for (i = 0; i < ys->n_mcast_groups; i++) + if (!strcmp(ys->mcast_groups[i].name, grp_name)) + break; + if (i == ys->n_mcast_groups) { + yerr(ys, ENOENT, "Multicast group '%s' not found", grp_name); + return -1; + } + + err = mnl_socket_setsockopt(ys->sock, NETLINK_ADD_MEMBERSHIP, + &ys->mcast_groups[i].id, + sizeof(ys->mcast_groups[i].id)); + if (err < 0) { + perr(ys, "Subscribing to multicast group failed"); + return -1; + } + + return 0; +} + +int ynl_socket_get_fd(struct ynl_sock *ys) +{ + return mnl_socket_get_fd(ys->sock); +} + +struct ynl_ntf_base_type *ynl_ntf_dequeue(struct ynl_sock *ys) +{ + struct ynl_ntf_base_type *ntf; + + if (!ynl_has_ntf(ys)) + return NULL; + + ntf = ys->ntf_first; + ys->ntf_first = ntf->next; + if (ys->ntf_last_next == &ntf->next) + ys->ntf_last_next = &ys->ntf_first; + + return ntf; +} + +static int ynl_ntf_parse(struct ynl_sock *ys, const struct nlmsghdr *nlh) +{ + struct ynl_parse_arg yarg = { .ys = ys, }; + const struct ynl_ntf_info *info; + struct ynl_ntf_base_type *rsp; + struct genlmsghdr *gehdr; + int ret; + + gehdr = mnl_nlmsg_get_payload(nlh); + if (gehdr->cmd >= ys->family->ntf_info_size) + return MNL_CB_ERROR; + info = &ys->family->ntf_info[gehdr->cmd]; + if (!info->cb) + return MNL_CB_ERROR; + + rsp = calloc(1, info->alloc_sz); + rsp->free = info->free; + yarg.data = rsp->data; + yarg.rsp_policy = info->policy; + + ret = info->cb(nlh, &yarg); + if (ret <= MNL_CB_STOP) + goto err_free; + + rsp->family = nlh->nlmsg_type; + rsp->cmd = gehdr->cmd; + + *ys->ntf_last_next = rsp; + ys->ntf_last_next = &rsp->next; + + return MNL_CB_OK; + +err_free: + info->free(rsp); + return MNL_CB_ERROR; +} + +static int ynl_ntf_trampoline(const struct nlmsghdr *nlh, void *data) +{ + return ynl_ntf_parse((struct ynl_sock *)data, nlh); +} + +int ynl_ntf_check(struct ynl_sock *ys) +{ + ssize_t len; + int err; + + do { + /* libmnl doesn't let us pass flags to the recv to make + * it non-blocking so we need to poll() or peek() :| + */ + struct pollfd pfd = { }; + + pfd.fd = mnl_socket_get_fd(ys->sock); + pfd.events = POLLIN; + err = poll(&pfd, 1, 1); + if (err < 1) + return err; + + len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, + MNL_SOCKET_BUFFER_SIZE); + if (len < 0) + return len; + + err = mnl_cb_run2(ys->rx_buf, len, ys->seq, ys->portid, + ynl_ntf_trampoline, ys, + ynl_cb_array, NLMSG_MIN_TYPE); + if (err < 0) + return err; + } while (err > 0); + + return 0; +} + +/* YNL specific helpers used by the auto-generated code */ + +struct ynl_dump_list_type *YNL_LIST_END = (void *)(0xb4d123); + +void ynl_error_unknown_notification(struct ynl_sock *ys, __u8 cmd) +{ + yerr(ys, YNL_ERROR_UNKNOWN_NTF, + "Unknown notification message type '%d'", cmd); +} + +int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg) +{ + yerr(yarg->ys, YNL_ERROR_INV_RESP, "Error parsing response: %s", msg); + return MNL_CB_ERROR; +} + +static int +ynl_check_alien(struct ynl_sock *ys, const struct nlmsghdr *nlh, __u32 rsp_cmd) +{ + struct genlmsghdr *gehdr; + + if (mnl_nlmsg_get_payload_len(nlh) < sizeof(*gehdr)) { + yerr(ys, YNL_ERROR_INV_RESP, + "Kernel responded with truncated message"); + return -1; + } + + gehdr = mnl_nlmsg_get_payload(nlh); + if (gehdr->cmd != rsp_cmd) + return ynl_ntf_parse(ys, nlh); + + return 0; +} + +static int ynl_req_trampoline(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_req_state *yrs = data; + int ret; + + ret = ynl_check_alien(yrs->yarg.ys, nlh, yrs->rsp_cmd); + if (ret) + return ret < 0 ? MNL_CB_ERROR : MNL_CB_OK; + + return yrs->cb(nlh, &yrs->yarg); +} + +int ynl_exec(struct ynl_sock *ys, struct nlmsghdr *req_nlh, + struct ynl_req_state *yrs) +{ + ssize_t len; + int err; + + err = mnl_socket_sendto(ys->sock, req_nlh, req_nlh->nlmsg_len); + if (err < 0) + return err; + + do { + len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, + MNL_SOCKET_BUFFER_SIZE); + if (len < 0) + return len; + + err = mnl_cb_run2(ys->rx_buf, len, ys->seq, ys->portid, + ynl_req_trampoline, yrs, + ynl_cb_array, NLMSG_MIN_TYPE); + if (err < 0) + return err; + } while (err > 0); + + return 0; +} + +static int ynl_dump_trampoline(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_dump_state *ds = data; + struct ynl_dump_list_type *obj; + struct ynl_parse_arg yarg = {}; + int ret; + + ret = ynl_check_alien(ds->ys, nlh, ds->rsp_cmd); + if (ret) + return ret < 0 ? MNL_CB_ERROR : MNL_CB_OK; + + obj = calloc(1, ds->alloc_sz); + if (!obj) + return MNL_CB_ERROR; + + if (!ds->first) + ds->first = obj; + if (ds->last) + ds->last->next = obj; + ds->last = obj; + + yarg.ys = ds->ys; + yarg.rsp_policy = ds->rsp_policy; + yarg.data = &obj->data; + + return ds->cb(nlh, &yarg); +} + +static void *ynl_dump_end(struct ynl_dump_state *ds) +{ + if (!ds->first) + return YNL_LIST_END; + + ds->last->next = YNL_LIST_END; + return ds->first; +} + +int ynl_exec_dump(struct ynl_sock *ys, struct nlmsghdr *req_nlh, + struct ynl_dump_state *yds) +{ + ssize_t len; + int err; + + err = mnl_socket_sendto(ys->sock, req_nlh, req_nlh->nlmsg_len); + if (err < 0) + return err; + + do { + len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, + MNL_SOCKET_BUFFER_SIZE); + if (len < 0) + goto err_close_list; + + err = mnl_cb_run2(ys->rx_buf, len, ys->seq, ys->portid, + ynl_dump_trampoline, yds, + ynl_cb_array, NLMSG_MIN_TYPE); + if (err < 0) + goto err_close_list; + } while (err > 0); + + yds->first = ynl_dump_end(yds); + return 0; + +err_close_list: + yds->first = ynl_dump_end(yds); + return -1; +} diff --git a/tools/net/ynl/lib/ynl.h b/tools/net/ynl/lib/ynl.h new file mode 100644 index 0000000000000..9eafa3552c167 --- /dev/null +++ b/tools/net/ynl/lib/ynl.h @@ -0,0 +1,237 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +#ifndef __YNL_C_H +#define __YNL_C_H 1 + +#include <stddef.h> +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> +#include <linux/types.h> + +struct mnl_socket; +struct nlmsghdr; + +/* + * User facing code + */ + +struct ynl_ntf_base_type; +struct ynl_ntf_info; +struct ynl_sock; + +enum ynl_error_code { + YNL_ERROR_NONE = 0, + __YNL_ERRNO_END = 4096, + YNL_ERROR_INTERNAL, + YNL_ERROR_EXPECT_ACK, + YNL_ERROR_EXPECT_MSG, + YNL_ERROR_UNEXPECT_MSG, + YNL_ERROR_ATTR_MISSING, + YNL_ERROR_ATTR_INVALID, + YNL_ERROR_UNKNOWN_NTF, + YNL_ERROR_INV_RESP, +}; + +/** + * struct ynl_error - error encountered by YNL + * @code: errno (low values) or YNL error code (enum ynl_error_code) + * @attr_offs: offset of bad attribute (for very advanced users) + * @msg: error message + * + * Error information for when YNL operations fail. + * Users should interact with the err member of struct ynl_sock directly. + * The main exception to that rule is ynl_sock_create(). + */ +struct ynl_error { + enum ynl_error_code code; + unsigned int attr_offs; + char msg[512]; +}; + +/** + * struct ynl_family - YNL family info + * Family description generated by codegen. Pass to ynl_sock_create(). + */ +struct ynl_family { +/* private: */ + const char *name; + const struct ynl_ntf_info *ntf_info; + unsigned int ntf_info_size; +}; + +/** + * struct ynl_sock - YNL wrapped netlink socket + * @err: YNL error descriptor, cleared on every request. + */ +struct ynl_sock { + struct ynl_error err; + +/* private: */ + const struct ynl_family *family; + struct mnl_socket *sock; + __u32 seq; + __u32 portid; + __u16 family_id; + + unsigned int n_mcast_groups; + struct { + unsigned int id; + char name[GENL_NAMSIZ]; + } *mcast_groups; + + struct ynl_ntf_base_type *ntf_first; + struct ynl_ntf_base_type **ntf_last_next; + + struct nlmsghdr *nlh; + struct ynl_policy_nest *req_policy; + unsigned char *tx_buf; + unsigned char *rx_buf; + unsigned char raw_buf[]; +}; + +struct ynl_sock * +ynl_sock_create(const struct ynl_family *yf, struct ynl_error *e); +void ynl_sock_destroy(struct ynl_sock *ys); + +#define ynl_dump_foreach(dump, iter) \ + for (typeof(dump->obj) *iter = &dump->obj; \ + !ynl_dump_obj_is_last(iter); \ + iter = ynl_dump_obj_next(iter)) + +int ynl_subscribe(struct ynl_sock *ys, const char *grp_name); +int ynl_socket_get_fd(struct ynl_sock *ys); +int ynl_ntf_check(struct ynl_sock *ys); + +/** + * ynl_has_ntf() - check if socket has *parsed* notifications + * @ys: active YNL socket + * + * Note that this does not take into account notifications sitting + * in netlink socket, just the notifications which have already been + * read and parsed (e.g. during a ynl_ntf_check() call). + */ +static inline bool ynl_has_ntf(struct ynl_sock *ys) +{ + return ys->ntf_last_next != &ys->ntf_first; +} +struct ynl_ntf_base_type *ynl_ntf_dequeue(struct ynl_sock *ys); + +void ynl_ntf_free(struct ynl_ntf_base_type *ntf); + +/* + * YNL internals / low level stuff + */ + +/* Generic mnl helper code */ + +enum ynl_policy_type { + YNL_PT_REJECT = 1, + YNL_PT_IGNORE, + YNL_PT_NEST, + YNL_PT_FLAG, + YNL_PT_BINARY, + YNL_PT_U8, + YNL_PT_U16, + YNL_PT_U32, + YNL_PT_U64, + YNL_PT_NUL_STR, +}; + +struct ynl_policy_attr { + enum ynl_policy_type type; + unsigned int len; + const char *name; + struct ynl_policy_nest *nest; +}; + +struct ynl_policy_nest { + unsigned int max_attr; + struct ynl_policy_attr *table; +}; + +struct ynl_parse_arg { + struct ynl_sock *ys; + struct ynl_policy_nest *rsp_policy; + void *data; +}; + +struct ynl_dump_list_type { + struct ynl_dump_list_type *next; + unsigned char data[] __attribute__ ((aligned (8))); +}; +extern struct ynl_dump_list_type *YNL_LIST_END; + +static inline bool ynl_dump_obj_is_last(void *obj) +{ + unsigned long uptr = (unsigned long)obj; + + uptr -= offsetof(struct ynl_dump_list_type, data); + return uptr == (unsigned long)YNL_LIST_END; +} + +static inline void *ynl_dump_obj_next(void *obj) +{ + unsigned long uptr = (unsigned long)obj; + struct ynl_dump_list_type *list; + + uptr -= offsetof(struct ynl_dump_list_type, data); + list = (void *)uptr; + uptr = (unsigned long)list->next; + uptr += offsetof(struct ynl_dump_list_type, data); + + return (void *)uptr; +} + +struct ynl_ntf_base_type { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ynl_ntf_base_type *ntf); + unsigned char data[] __attribute__ ((aligned (8))); +}; + +extern mnl_cb_t ynl_cb_array[NLMSG_MIN_TYPE]; + +struct nlmsghdr * +ynl_gemsg_start_req(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version); +struct nlmsghdr * +ynl_gemsg_start_dump(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version); + +int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr); + +int ynl_recv_ack(struct ynl_sock *ys, int ret); +int ynl_cb_null(const struct nlmsghdr *nlh, void *data); + +/* YNL specific helpers used by the auto-generated code */ + +struct ynl_req_state { + struct ynl_parse_arg yarg; + mnl_cb_t cb; + __u32 rsp_cmd; +}; + +struct ynl_dump_state { + struct ynl_sock *ys; + struct ynl_policy_nest *rsp_policy; + void *first; + struct ynl_dump_list_type *last; + size_t alloc_sz; + mnl_cb_t cb; + __u32 rsp_cmd; +}; + +struct ynl_ntf_info { + struct ynl_policy_nest *policy; + mnl_cb_t cb; + size_t alloc_sz; + void (*free)(struct ynl_ntf_base_type *ntf); +}; + +int ynl_exec(struct ynl_sock *ys, struct nlmsghdr *req_nlh, + struct ynl_req_state *yrs); +int ynl_exec_dump(struct ynl_sock *ys, struct nlmsghdr *req_nlh, + struct ynl_dump_state *yds); + +void ynl_error_unknown_notification(struct ynl_sock *ys, __u8 cmd); +int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg); + +#endif diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index aa77bcae4807e..1b3a36fbb1c37 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -1,11 +1,15 @@ # SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +from collections import namedtuple import functools import os import random import socket import struct +from struct import Struct import yaml +import ipaddress +import uuid from .nlspec import SpecFamily @@ -76,10 +80,17 @@ class NlError(Exception): class NlAttr: - type_formats = { 'u8' : ('B', 1), 's8' : ('b', 1), - 'u16': ('H', 2), 's16': ('h', 2), - 'u32': ('I', 4), 's32': ('i', 4), - 'u64': ('Q', 8), 's64': ('q', 8) } + ScalarFormat = namedtuple('ScalarFormat', ['native', 'big', 'little']) + type_formats = { + 'u8' : ScalarFormat(Struct('B'), Struct("B"), Struct("B")), + 's8' : ScalarFormat(Struct('b'), Struct("b"), Struct("b")), + 'u16': ScalarFormat(Struct('H'), Struct(">H"), Struct("<H")), + 's16': ScalarFormat(Struct('h'), Struct(">h"), Struct("<h")), + 'u32': ScalarFormat(Struct('I'), Struct(">I"), Struct("<I")), + 's32': ScalarFormat(Struct('i'), Struct(">i"), Struct("<i")), + 'u64': ScalarFormat(Struct('Q'), Struct(">Q"), Struct("<Q")), + 's64': ScalarFormat(Struct('q'), Struct(">q"), Struct("<q")) + } def __init__(self, raw, offset): self._len, self._type = struct.unpack("HH", raw[offset:offset + 4]) @@ -88,25 +99,31 @@ class NlAttr: self.full_len = (self.payload_len + 3) & ~3 self.raw = raw[offset + 4:offset + self.payload_len] - def format_byte_order(byte_order): + @classmethod + def get_format(cls, attr_type, byte_order=None): + format = cls.type_formats[attr_type] if byte_order: - return ">" if byte_order == "big-endian" else "<" - return "" - - def as_u8(self): - return struct.unpack("B", self.raw)[0] - - def as_u16(self, byte_order=None): - endian = NlAttr.format_byte_order(byte_order) - return struct.unpack(f"{endian}H", self.raw)[0] - - def as_u32(self, byte_order=None): - endian = NlAttr.format_byte_order(byte_order) - return struct.unpack(f"{endian}I", self.raw)[0] + return format.big if byte_order == "big-endian" \ + else format.little + return format.native + + @classmethod + def formatted_string(cls, raw, display_hint): + if display_hint == 'mac': + formatted = ':'.join('%02x' % b for b in raw) + elif display_hint == 'hex': + formatted = bytes.hex(raw, ' ') + elif display_hint in [ 'ipv4', 'ipv6' ]: + formatted = format(ipaddress.ip_address(raw)) + elif display_hint == 'uuid': + formatted = str(uuid.UUID(bytes=raw)) + else: + formatted = raw + return formatted - def as_u64(self, byte_order=None): - endian = NlAttr.format_byte_order(byte_order) - return struct.unpack(f"{endian}Q", self.raw)[0] + def as_scalar(self, attr_type, byte_order=None): + format = self.get_format(attr_type, byte_order) + return format.unpack(self.raw)[0] def as_strz(self): return self.raw.decode('ascii')[:-1] @@ -115,18 +132,24 @@ class NlAttr: return self.raw def as_c_array(self, type): - format, _ = self.type_formats[type] - return list({ x[0] for x in struct.iter_unpack(format, self.raw) }) + format = self.get_format(type) + return [ x[0] for x in format.iter_unpack(self.raw) ] def as_struct(self, members): value = dict() offset = 0 for m in members: # TODO: handle non-scalar members - format, size = self.type_formats[m.type] - decoded = struct.unpack_from(format, self.raw, offset) - offset += size - value[m.name] = decoded[0] + if m.type == 'binary': + decoded = self.raw[offset:offset+m['len']] + offset += m['len'] + elif m.type in NlAttr.type_formats: + format = self.get_format(m.type, m.byte_order) + [ decoded ] = format.unpack_from(self.raw, offset) + offset += format.size + if m.display_hint: + decoded = self.formatted_string(decoded, m.display_hint) + value[m.name] = decoded return value def __repr__(self): @@ -184,11 +207,11 @@ class NlMsg: if extack.type == Netlink.NLMSGERR_ATTR_MSG: self.extack['msg'] = extack.as_strz() elif extack.type == Netlink.NLMSGERR_ATTR_MISS_TYPE: - self.extack['miss-type'] = extack.as_u32() + self.extack['miss-type'] = extack.as_scalar('u32') elif extack.type == Netlink.NLMSGERR_ATTR_MISS_NEST: - self.extack['miss-nest'] = extack.as_u32() + self.extack['miss-nest'] = extack.as_scalar('u32') elif extack.type == Netlink.NLMSGERR_ATTR_OFFS: - self.extack['bad-attr-offs'] = extack.as_u32() + self.extack['bad-attr-offs'] = extack.as_scalar('u32') else: if 'unknown' not in self.extack: self.extack['unknown'] = [] @@ -272,11 +295,11 @@ def _genl_load_families(): fam = dict() for attr in gm.raw_attrs: if attr.type == Netlink.CTRL_ATTR_FAMILY_ID: - fam['id'] = attr.as_u16() + fam['id'] = attr.as_scalar('u16') elif attr.type == Netlink.CTRL_ATTR_FAMILY_NAME: fam['name'] = attr.as_strz() elif attr.type == Netlink.CTRL_ATTR_MAXATTR: - fam['maxattr'] = attr.as_u32() + fam['maxattr'] = attr.as_scalar('u32') elif attr.type == Netlink.CTRL_ATTR_MCAST_GROUPS: fam['mcast'] = dict() for entry in NlAttrs(attr.raw): @@ -286,7 +309,7 @@ def _genl_load_families(): if entry_attr.type == Netlink.CTRL_ATTR_MCAST_GRP_NAME: mcast_name = entry_attr.as_strz() elif entry_attr.type == Netlink.CTRL_ATTR_MCAST_GRP_ID: - mcast_id = entry_attr.as_u32() + mcast_id = entry_attr.as_scalar('u32') if mcast_name and mcast_id is not None: fam['mcast'][mcast_name] = mcast_id if 'name' in fam and 'id' in fam: @@ -304,9 +327,9 @@ class GenlMsg: self.fixed_header_attrs = dict() for m in fixed_header_members: - format, size = NlAttr.type_formats[m.type] - decoded = struct.unpack_from(format, nl_msg.raw, offset) - offset += size + format = NlAttr.get_format(m.type, m.byte_order) + decoded = format.unpack_from(nl_msg.raw, offset) + offset += format.size self.fixed_header_attrs[m.name] = decoded[0] self.raw = nl_msg.raw[offset:] @@ -381,21 +404,13 @@ class YnlFamily(SpecFamily): attr_payload += self._add_attr(attr['nested-attributes'], subname, subvalue) elif attr["type"] == 'flag': attr_payload = b'' - elif attr["type"] == 'u8': - attr_payload = struct.pack("B", int(value)) - elif attr["type"] == 'u16': - endian = NlAttr.format_byte_order(attr.byte_order) - attr_payload = struct.pack(f"{endian}H", int(value)) - elif attr["type"] == 'u32': - endian = NlAttr.format_byte_order(attr.byte_order) - attr_payload = struct.pack(f"{endian}I", int(value)) - elif attr["type"] == 'u64': - endian = NlAttr.format_byte_order(attr.byte_order) - attr_payload = struct.pack(f"{endian}Q", int(value)) elif attr["type"] == 'string': attr_payload = str(value).encode('ascii') + b'\x00' elif attr["type"] == 'binary': - attr_payload = value + attr_payload = bytes.fromhex(value) + elif attr['type'] in NlAttr.type_formats: + format = NlAttr.get_format(attr['type'], attr.byte_order) + attr_payload = format.pack(int(value)) else: raise Exception(f'Unknown type at {space} {name} {value} {attr["type"]}') @@ -419,11 +434,17 @@ class YnlFamily(SpecFamily): def _decode_binary(self, attr, attr_spec): if attr_spec.struct_name: - decoded = attr.as_struct(self.consts[attr_spec.struct_name]) + members = self.consts[attr_spec.struct_name] + decoded = attr.as_struct(members) + for m in members: + if m.enum: + self._decode_enum(decoded, m) elif attr_spec.sub_type: decoded = attr.as_c_array(attr_spec.sub_type) else: decoded = attr.as_bin() + if attr_spec.display_hint: + decoded = NlAttr.formatted_string(decoded, attr_spec.display_hint) return decoded def _decode(self, attrs, space): @@ -434,22 +455,16 @@ class YnlFamily(SpecFamily): if attr_spec["type"] == 'nest': subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes']) decoded = subdict - elif attr_spec['type'] == 'u8': - decoded = attr.as_u8() - elif attr_spec['type'] == 'u16': - decoded = attr.as_u16(attr_spec.byte_order) - elif attr_spec['type'] == 'u32': - decoded = attr.as_u32(attr_spec.byte_order) - elif attr_spec['type'] == 'u64': - decoded = attr.as_u64(attr_spec.byte_order) elif attr_spec["type"] == 'string': decoded = attr.as_strz() elif attr_spec["type"] == 'binary': decoded = self._decode_binary(attr, attr_spec) elif attr_spec["type"] == 'flag': decoded = True + elif attr_spec["type"] in NlAttr.type_formats: + decoded = attr.as_scalar(attr_spec['type'], attr_spec.byte_order) else: - raise Exception(f'Unknown {attr.type} {attr_spec["name"]} {attr_spec["type"]}') + raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}') if not attr_spec.is_multi: rsp[attr_spec['name']] = decoded @@ -554,9 +569,9 @@ class YnlFamily(SpecFamily): if op.fixed_header: fixed_header_members = self.consts[op.fixed_header].members for m in fixed_header_members: - value = vals.pop(m.name) - format, _ = NlAttr.type_formats[m.type] - msg += struct.pack(format, value) + value = vals.pop(m.name) if m.name in vals else 0 + format = NlAttr.get_format(m.type, m.byte_order) + msg += format.pack(value) for name, value in vals.items(): msg += self._add_attr(op.attr_set.name, name, value) msg = _genl_msg_finalize(msg) @@ -591,8 +606,9 @@ class YnlFamily(SpecFamily): print('Unexpected message: ' + repr(gm)) continue - rsp.append(self._decode(gm.raw_attrs, op.attr_set.name) - | gm.fixed_header_attrs) + rsp_msg = self._decode(gm.raw_attrs, op.attr_set.name) + rsp_msg.update(gm.fixed_header_attrs) + rsp.append(rsp_msg) if not rsp: return None diff --git a/tools/net/ynl/samples/.gitignore b/tools/net/ynl/samples/.gitignore new file mode 100644 index 0000000000000..2aae60c4829fd --- /dev/null +++ b/tools/net/ynl/samples/.gitignore @@ -0,0 +1,3 @@ +ethtool +devlink +netdev diff --git a/tools/net/ynl/samples/Makefile b/tools/net/ynl/samples/Makefile new file mode 100644 index 0000000000000..f2db8bb783095 --- /dev/null +++ b/tools/net/ynl/samples/Makefile @@ -0,0 +1,30 @@ +# SPDX-License-Identifier: GPL-2.0 + +include ../Makefile.deps + +CC=gcc +CFLAGS=-std=gnu11 -O2 -W -Wall -Wextra -Wno-unused-parameter -Wshadow \ + -I../lib/ -I../generated/ -idirafter $(UAPI_PATH) +ifeq ("$(DEBUG)","1") + CFLAGS += -g -fsanitize=address -fsanitize=leak -static-libasan +endif + +LDLIBS=-lmnl ../lib/ynl.a ../generated/protos.a + +SRCS=$(wildcard *.c) +BINS=$(patsubst %.c,%,${SRCS}) + +include $(wildcard *.d) + +all: $(BINS) + +$(BINS): ../lib/ynl.a ../generated/protos.a + +clean: + rm -f *.o *.d *~ + +hardclean: clean + rm -f $(BINS) + +.PHONY: all clean +.DEFAULT_GOAL=all diff --git a/tools/net/ynl/samples/devlink.c b/tools/net/ynl/samples/devlink.c new file mode 100644 index 0000000000000..d2611d7ebab45 --- /dev/null +++ b/tools/net/ynl/samples/devlink.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <string.h> + +#include <ynl.h> + +#include "devlink-user.h" + +int main(int argc, char **argv) +{ + struct devlink_get_list *devs; + struct ynl_sock *ys; + + ys = ynl_sock_create(&ynl_devlink_family, NULL); + if (!ys) + return 1; + + devs = devlink_get_dump(ys); + if (!devs) + goto err_close; + + ynl_dump_foreach(devs, d) { + struct devlink_info_get_req *info_req; + struct devlink_info_get_rsp *info_rsp; + + printf("%s/%s:\n", d->bus_name, d->dev_name); + + info_req = devlink_info_get_req_alloc(); + devlink_info_get_req_set_bus_name(info_req, d->bus_name); + devlink_info_get_req_set_dev_name(info_req, d->dev_name); + + info_rsp = devlink_info_get(ys, info_req); + devlink_info_get_req_free(info_req); + if (!info_rsp) + goto err_free_devs; + + if (info_rsp->_present.info_driver_name_len) + printf(" driver: %s\n", info_rsp->info_driver_name); + if (info_rsp->n_info_version_running) + printf(" running fw:\n"); + for (unsigned i = 0; i < info_rsp->n_info_version_running; i++) + printf(" %s: %s\n", + info_rsp->info_version_running[i].info_version_name, + info_rsp->info_version_running[i].info_version_value); + printf(" ...\n"); + devlink_info_get_rsp_free(info_rsp); + } + devlink_get_list_free(devs); + + ynl_sock_destroy(ys); + + return 0; + +err_free_devs: + devlink_get_list_free(devs); +err_close: + fprintf(stderr, "YNL: %s\n", ys->err.msg); + ynl_sock_destroy(ys); + return 2; +} diff --git a/tools/net/ynl/samples/ethtool.c b/tools/net/ynl/samples/ethtool.c new file mode 100644 index 0000000000000..a7ebbd1b98db8 --- /dev/null +++ b/tools/net/ynl/samples/ethtool.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <string.h> + +#include <ynl.h> + +#include <net/if.h> + +#include "ethtool-user.h" + +int main(int argc, char **argv) +{ + struct ethtool_channels_get_req_dump creq = {}; + struct ethtool_rings_get_req_dump rreq = {}; + struct ethtool_channels_get_list *channels; + struct ethtool_rings_get_list *rings; + struct ynl_sock *ys; + + ys = ynl_sock_create(&ynl_ethtool_family, NULL); + if (!ys) + return 1; + + creq._present.header = 1; /* ethtool needs an empty nest, sigh */ + channels = ethtool_channels_get_dump(ys, &creq); + if (!channels) + goto err_close; + + printf("Channels:\n"); + ynl_dump_foreach(channels, dev) { + printf(" %8s: ", dev->header.dev_name); + if (dev->_present.rx_count) + printf("rx %d ", dev->rx_count); + if (dev->_present.tx_count) + printf("tx %d ", dev->tx_count); + if (dev->_present.combined_count) + printf("combined %d ", dev->combined_count); + printf("\n"); + } + ethtool_channels_get_list_free(channels); + + rreq._present.header = 1; /* ethtool needs an empty nest.. */ + rings = ethtool_rings_get_dump(ys, &rreq); + if (!rings) + goto err_close; + + printf("Rings:\n"); + ynl_dump_foreach(rings, dev) { + printf(" %8s: ", dev->header.dev_name); + if (dev->_present.rx) + printf("rx %d ", dev->rx); + if (dev->_present.tx) + printf("tx %d ", dev->tx); + printf("\n"); + } + ethtool_rings_get_list_free(rings); + + ynl_sock_destroy(ys); + + return 0; + +err_close: + fprintf(stderr, "YNL (%d): %s\n", ys->err.code, ys->err.msg); + ynl_sock_destroy(ys); + return 2; +} diff --git a/tools/net/ynl/samples/netdev.c b/tools/net/ynl/samples/netdev.c new file mode 100644 index 0000000000000..d31268aa47c5d --- /dev/null +++ b/tools/net/ynl/samples/netdev.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <string.h> + +#include <ynl.h> + +#include <net/if.h> + +#include "netdev-user.h" + +/* netdev genetlink family code sample + * This sample shows off basics of the netdev family but also notification + * handling, hence the somewhat odd UI. We subscribe to notifications first + * then wait for ifc selection, so the socket may already accumulate + * notifications as we wait. This allows us to test that YNL can handle + * requests and notifications getting interleaved. + */ + +static void netdev_print_device(struct netdev_dev_get_rsp *d, unsigned int op) +{ + char ifname[IF_NAMESIZE]; + const char *name; + + if (!d->_present.ifindex) + return; + + name = if_indextoname(d->ifindex, ifname); + if (name) + printf("%8s", name); + printf("[%d]\t", d->ifindex); + + if (!d->_present.xdp_features) + return; + + printf("%llx:", d->xdp_features); + for (int i = 0; d->xdp_features > 1U << i; i++) { + if (d->xdp_features & (1U << i)) + printf(" %s", netdev_xdp_act_str(1 << i)); + } + + name = netdev_op_str(op); + if (name) + printf(" (ntf: %s)", name); + printf("\n"); +} + +int main(int argc, char **argv) +{ + struct netdev_dev_get_list *devs; + struct ynl_ntf_base_type *ntf; + struct ynl_error yerr; + struct ynl_sock *ys; + int ifindex = 0; + + if (argc > 1) + ifindex = strtol(argv[1], NULL, 0); + + ys = ynl_sock_create(&ynl_netdev_family, &yerr); + if (!ys) { + fprintf(stderr, "YNL: %s\n", yerr.msg); + return 1; + } + + if (ynl_subscribe(ys, "mgmt")) + goto err_close; + + printf("Select ifc ($ifindex; or 0 = dump; or -2 ntf check): "); + scanf("%d", &ifindex); + + if (ifindex > 0) { + struct netdev_dev_get_req *req; + struct netdev_dev_get_rsp *d; + + req = netdev_dev_get_req_alloc(); + netdev_dev_get_req_set_ifindex(req, ifindex); + + d = netdev_dev_get(ys, req); + netdev_dev_get_req_free(req); + if (!d) + goto err_close; + + netdev_print_device(d, 0); + netdev_dev_get_rsp_free(d); + } else if (!ifindex) { + devs = netdev_dev_get_dump(ys); + if (!devs) + goto err_close; + + ynl_dump_foreach(devs, d) + netdev_print_device(d, 0); + netdev_dev_get_list_free(devs); + } else if (ifindex == -2) { + ynl_ntf_check(ys); + } + while ((ntf = ynl_ntf_dequeue(ys))) { + netdev_print_device((struct netdev_dev_get_rsp *)&ntf->data, + ntf->cmd); + ynl_ntf_free(ntf); + } + + ynl_sock_destroy(ys); + return 0; + +err_close: + fprintf(stderr, "YNL: %s\n", ys->err.msg); + ynl_sock_destroy(ys); + return 2; +} diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index cc2f8c9453404..71c5e79e877f0 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -4,6 +4,7 @@ import argparse import collections import os +import re import yaml from lib import SpecFamily, SpecAttrSet, SpecAttr, SpecOperation, SpecEnumSet, SpecEnumEntry @@ -48,6 +49,11 @@ class Type(SpecAttr): else: self.nested_render_name = f"{family.name}_{c_lower(self.nested_attrs)}" + if self.nested_attrs in self.family.consts: + self.nested_struct_type = 'struct ' + self.nested_render_name + '_' + else: + self.nested_struct_type = 'struct ' + self.nested_render_name + self.c_name = c_lower(self.name) if self.c_name in _C_KW: self.c_name += '_' @@ -57,8 +63,11 @@ class Type(SpecAttr): delattr(self, "enum_name") def resolve(self): - self.enum_name = f"{self.attr_set.name_prefix}{self.name}" - self.enum_name = c_upper(self.enum_name) + if 'name-prefix' in self.attr: + enum_name = f"{self.attr['name-prefix']}{self.name}" + else: + enum_name = f"{self.attr_set.name_prefix}{self.name}" + self.enum_name = c_upper(enum_name) def is_multi_val(self): return None @@ -94,7 +103,10 @@ class Type(SpecAttr): def arg_member(self, ri): member = self._complex_member_type(ri) if member: - return [member + ' *' + self.c_name] + arg = [member + ' *' + self.c_name] + if self.presence_type() == 'count': + arg += ['unsigned int n_' + self.c_name] + return arg raise Exception(f"Struct member not implemented for class type {self.type}") def struct_member(self, ri): @@ -150,7 +162,7 @@ class Type(SpecAttr): init_lines = [init_lines] kw = 'if' if first else 'else if' - ri.cw.block_start(line=f"{kw} (mnl_attr_get_type(attr) == {self.enum_name})") + ri.cw.block_start(line=f"{kw} (type == {self.enum_name})") if local_vars: for local in local_vars: ri.cw.p(local) @@ -170,6 +182,7 @@ class Type(SpecAttr): for line in lines: ri.cw.p(line) ri.cw.block_end() + return True def _setter_lines(self, ri, member, presence): raise Exception(f"Setter not implemented for class type {self.type}") @@ -187,9 +200,12 @@ class Type(SpecAttr): code.append(presence + ' = 1;') code += self._setter_lines(ri, member, presence) - ri.cw.write_func('static inline void', - f"{op_prefix(ri, direction, deref=deref)}_set_{'_'.join(ref)}", - body=code, + func_name = f"{op_prefix(ri, direction, deref=deref)}_set_{'_'.join(ref)}" + free = bool([x for x in code if 'free(' in x]) + alloc = bool([x for x in code if 'alloc(' in x]) + if free and not alloc: + func_name = '__' + func_name + ri.cw.write_func('static inline void', func_name, body=code, args=[f'{type_name(ri, direction, deref=deref)} *{var}'] + self.arg_member(ri)) @@ -197,6 +213,12 @@ class TypeUnused(Type): def presence_type(self): return '' + def arg_member(self, ri): + return [] + + def _attr_get(self, ri, var): + return ['return MNL_CB_ERROR;'], None, None + def _attr_typol(self): return '.type = YNL_PT_REJECT, ' @@ -208,12 +230,24 @@ class TypePad(Type): def presence_type(self): return '' + def arg_member(self, ri): + return [] + def _attr_typol(self): - return '.type = YNL_PT_REJECT, ' + return '.type = YNL_PT_IGNORE, ' + + def attr_put(self, ri, var): + pass + + def attr_get(self, ri, var, first): + pass def attr_policy(self, cw): pass + def setter(self, ri, space, direction, deref=False, ref=None): + pass + class TypeScalar(Type): def __init__(self, family, attr_set, attr, value): @@ -239,7 +273,8 @@ class TypeScalar(Type): else: self.is_bitfield = False - if 'enum' in self.attr and not self.is_bitfield: + maybe_enum = not self.is_bitfield and 'enum' in self.attr + if maybe_enum and self.family.consts[self.attr['enum']].enum_name: self.type_name = f"enum {self.family.name}_{c_lower(self.attr['enum'])}" else: self.type_name = '__' + self.type @@ -265,8 +300,10 @@ class TypeScalar(Type): return f"NLA_POLICY_MIN({policy}, {self.checks['min']})" elif 'enum' in self.attr: enum = self.family.consts[self.attr['enum']] - cnt = len(enum['entries']) - return f"NLA_POLICY_MAX({policy}, {cnt - 1})" + low, high = enum.value_range() + if low == 0: + return f"NLA_POLICY_MAX({policy}, {high})" + return f"NLA_POLICY_RANGE({policy}, {low}, {high})" return super()._attr_policy(policy) def _attr_typol(self): @@ -395,7 +432,7 @@ class TypeBinary(Type): class TypeNest(Type): def _complex_member_type(self, ri): - return f"struct {self.nested_render_name}" + return self.nested_struct_type def free(self, ri, var, ref): ri.cw.p(f'{self.nested_render_name}_free(&{var}->{ref}{self.c_name});') @@ -411,7 +448,8 @@ class TypeNest(Type): f"{self.enum_name}, &{var}->{self.c_name})") def _attr_get(self, ri, var): - get_lines = [f"{self.nested_render_name}_parse(&parg, attr);"] + get_lines = [f"if ({self.nested_render_name}_parse(&parg, attr))", + "return MNL_CB_ERROR;"] init_lines = [f"parg.rsp_policy = &{self.nested_render_name}_nest;", f"parg.data = &{var}->{self.c_name};"] return get_lines, init_lines, None @@ -424,15 +462,27 @@ class TypeNest(Type): class TypeMultiAttr(Type): + def __init__(self, family, attr_set, attr, value, base_type): + super().__init__(family, attr_set, attr, value) + + self.base_type = base_type + def is_multi_val(self): return True def presence_type(self): return 'count' + def _mnl_type(self): + t = self.type + # mnl does not have a helper for signed types + if t[0] == 's': + t = 'u' + t[1:] + return t + def _complex_member_type(self, ri): if 'type' not in self.attr or self.attr['type'] == 'nest': - return f"struct {self.nested_render_name}" + return self.nested_struct_type elif self.attr['type'] in scalars: scalar_pfx = '__' if ri.ku_space == 'user' else '' return scalar_pfx + self.attr['type'] @@ -443,20 +493,42 @@ class TypeMultiAttr(Type): return 'type' not in self.attr or self.attr['type'] == 'nest' def free(self, ri, var, ref): - if 'type' not in self.attr or self.attr['type'] == 'nest': + if self.attr['type'] in scalars: + ri.cw.p(f"free({var}->{ref}{self.c_name});") + elif 'type' not in self.attr or self.attr['type'] == 'nest': ri.cw.p(f"for (i = 0; i < {var}->{ref}n_{self.c_name}; i++)") ri.cw.p(f'{self.nested_render_name}_free(&{var}->{ref}{self.c_name}[i]);') + ri.cw.p(f"free({var}->{ref}{self.c_name});") + else: + raise Exception(f"Free of MultiAttr sub-type {self.attr['type']} not supported yet") + + def _attr_policy(self, policy): + return self.base_type._attr_policy(policy) def _attr_typol(self): - if 'type' not in self.attr or self.attr['type'] == 'nest': - return f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, ' - elif self.attr['type'] in scalars: - return f".type = YNL_PT_U{self.attr['type'][1:]}, " - else: - raise Exception(f"Sub-type {self.attr['type']} not supported yet") + return self.base_type._attr_typol() def _attr_get(self, ri, var): - return f'{var}->n_{self.c_name}++;', None, None + return f'n_{self.c_name}++;', None, None + + def attr_put(self, ri, var): + if self.attr['type'] in scalars: + put_type = self._mnl_type() + ri.cw.p(f"for (unsigned int i = 0; i < {var}->n_{self.c_name}; i++)") + ri.cw.p(f"mnl_attr_put_{put_type}(nlh, {self.enum_name}, {var}->{self.c_name}[i]);") + elif 'type' not in self.attr or self.attr['type'] == 'nest': + ri.cw.p(f"for (unsigned int i = 0; i < {var}->n_{self.c_name}; i++)") + self._attr_put_line(ri, var, f"{self.nested_render_name}_put(nlh, " + + f"{self.enum_name}, &{var}->{self.c_name}[i])") + else: + raise Exception(f"Put of MultiAttr sub-type {self.attr['type']} not supported yet") + + def _setter_lines(self, ri, member, presence): + # For multi-attr we have a count, not presence, hack up the presence + presence = presence[:-(len('_present.') + len(self.c_name))] + "n_" + self.c_name + return [f"free({member});", + f"{member} = {self.c_name};", + f"{presence} = n_{self.c_name};"] class TypeArrayNest(Type): @@ -468,7 +540,7 @@ class TypeArrayNest(Type): def _complex_member_type(self, ri): if 'sub-type' not in self.attr or self.attr['sub-type'] == 'nest': - return f"struct {self.nested_render_name}" + return self.nested_struct_type elif self.attr['sub-type'] in scalars: scalar_pfx = '__' if ri.ku_space == 'user' else '' return scalar_pfx + self.attr['sub-type'] @@ -488,7 +560,7 @@ class TypeArrayNest(Type): class TypeNestTypeValue(Type): def _complex_member_type(self, ri): - return f"struct {self.nested_render_name}" + return self.nested_struct_type def _attr_typol(self): return f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, ' @@ -531,6 +603,8 @@ class Struct: else: self.render_name = f"{family.name}_{c_lower(space_name)}" self.struct_name = 'struct ' + self.render_name + if self.nested and space_name in family.consts: + self.struct_name += '_' self.ptr_name = self.struct_name + ' *' self.request = False @@ -591,7 +665,14 @@ class EnumEntry(SpecEnumEntry): class EnumSet(SpecEnumSet): def __init__(self, family, yaml): self.render_name = c_lower(family.name + '-' + yaml['name']) - self.enum_name = 'enum ' + self.render_name + + if 'enum-name' in yaml: + if yaml['enum-name']: + self.enum_name = 'enum ' + c_lower(yaml['enum-name']) + else: + self.enum_name = None + else: + self.enum_name = 'enum ' + self.render_name self.value_pfx = yaml.get('name-prefix', f"{family.name}-{yaml['name']}-") @@ -600,6 +681,15 @@ class EnumSet(SpecEnumSet): def new_entry(self, entry, prev_entry, value_start): return EnumEntry(self, entry, prev_entry, value_start) + def value_range(self): + low = min([x.value for x in self.entries.values()]) + high = max([x.value for x in self.entries.values()]) + + if high - low + 1 != len(self.entries): + raise Exception("Can't get value range for a noncontiguous enum") + + return low, high + class AttrSet(SpecAttrSet): def __init__(self, family, yaml): @@ -630,42 +720,44 @@ class AttrSet(SpecAttrSet): self.c_name = '' def new_attr(self, elem, value): - if 'multi-attr' in elem and elem['multi-attr']: - return TypeMultiAttr(self.family, self, elem, value) - elif elem['type'] in scalars: - return TypeScalar(self.family, self, elem, value) + if elem['type'] in scalars: + t = TypeScalar(self.family, self, elem, value) elif elem['type'] == 'unused': - return TypeUnused(self.family, self, elem, value) + t = TypeUnused(self.family, self, elem, value) elif elem['type'] == 'pad': - return TypePad(self.family, self, elem, value) + t = TypePad(self.family, self, elem, value) elif elem['type'] == 'flag': - return TypeFlag(self.family, self, elem, value) + t = TypeFlag(self.family, self, elem, value) elif elem['type'] == 'string': - return TypeString(self.family, self, elem, value) + t = TypeString(self.family, self, elem, value) elif elem['type'] == 'binary': - return TypeBinary(self.family, self, elem, value) + t = TypeBinary(self.family, self, elem, value) elif elem['type'] == 'nest': - return TypeNest(self.family, self, elem, value) + t = TypeNest(self.family, self, elem, value) elif elem['type'] == 'array-nest': - return TypeArrayNest(self.family, self, elem, value) + t = TypeArrayNest(self.family, self, elem, value) elif elem['type'] == 'nest-type-value': - return TypeNestTypeValue(self.family, self, elem, value) + t = TypeNestTypeValue(self.family, self, elem, value) else: raise Exception(f"No typed class for type {elem['type']}") + if 'multi-attr' in elem and elem['multi-attr']: + t = TypeMultiAttr(self.family, self, elem, value, t) + + return t + class Operation(SpecOperation): def __init__(self, family, yaml, req_value, rsp_value): super().__init__(family, yaml, req_value, rsp_value) - if req_value != rsp_value: - raise Exception("Directional messages not supported by codegen") - self.render_name = family.name + '_' + c_lower(self.name) self.dual_policy = ('do' in yaml and 'request' in yaml['do']) and \ ('dump' in yaml and 'request' in yaml['dump']) + self.has_ntf = False + # Added by resolve: self.enum_name = None delattr(self, "enum_name") @@ -678,16 +770,12 @@ class Operation(SpecOperation): else: self.enum_name = self.family.async_op_prefix + c_upper(self.name) - def add_notification(self, op): - if 'notify' not in self.yaml: - self.yaml['notify'] = dict() - self.yaml['notify']['reply'] = self.yaml['do']['reply'] - self.yaml['notify']['cmds'] = [] - self.yaml['notify']['cmds'].append(op) + def mark_has_ntf(self): + self.has_ntf = True class Family(SpecFamily): - def __init__(self, file_name): + def __init__(self, file_name, exclude_ops): # Added by resolve: self.c_name = None delattr(self, "c_name") @@ -702,7 +790,7 @@ class Family(SpecFamily): self.hooks = None delattr(self, "hooks") - super().__init__(file_name) + super().__init__(file_name, exclude_ops=exclude_ops) self.fam_key = c_upper(self.yaml.get('c-family-name', self.yaml["name"] + '_FAMILY_NAME')) self.ver_key = c_upper(self.yaml.get('c-version-name', self.yaml["name"] + '_FAMILY_VERSION')) @@ -745,14 +833,12 @@ class Family(SpecFamily): self.root_sets = dict() # dict space-name -> set('request', 'reply') self.pure_nested_structs = dict() - self.all_notify = dict() + self._mark_notify() self._mock_up_events() - self._dictify() self._load_root_sets() self._load_nested_sets() - self._load_all_notify() self._load_hooks() self.kernel_policy = self.yaml.get('kernel-policy', 'split') @@ -768,6 +854,11 @@ class Family(SpecFamily): def new_operation(self, elem, req_value, rsp_value): return Operation(self, elem, req_value, rsp_value) + def _mark_notify(self): + for op in self.msgs.values(): + if 'notify' in op: + self.ops[op['notify']].mark_has_ntf() + # Fake a 'do' equivalent of all events, so that we can render their response parsing def _mock_up_events(self): for op in self.yaml['operations']['list']: @@ -778,16 +869,8 @@ class Family(SpecFamily): } } - def _dictify(self): - ntf = [] - for msg in self.msgs.values(): - if 'notify' in msg: - ntf.append(msg) - for n in ntf: - self.ops[n['notify']].add_notification(n) - def _load_root_sets(self): - for op_name, op in self.ops.items(): + for op_name, op in self.msgs.items(): if 'attribute-set' not in op: continue @@ -798,6 +881,8 @@ class Family(SpecFamily): req_attrs.update(set(op[op_mode]['request']['attributes'])) if op_mode in op and 'reply' in op[op_mode]: rsp_attrs.update(set(op[op_mode]['reply']['attributes'])) + if 'event' in op: + rsp_attrs.update(set(op['event']['attributes'])) if op['attribute-set'] not in self.root_sets: self.root_sets[op['attribute-set']] = {'request': req_attrs, 'reply': rsp_attrs} @@ -806,33 +891,73 @@ class Family(SpecFamily): self.root_sets[op['attribute-set']]['reply'].update(rsp_attrs) def _load_nested_sets(self): + attr_set_queue = list(self.root_sets.keys()) + attr_set_seen = set(self.root_sets.keys()) + + while len(attr_set_queue): + a_set = attr_set_queue.pop(0) + for attr, spec in self.attr_sets[a_set].items(): + if 'nested-attributes' not in spec: + continue + + nested = spec['nested-attributes'] + if nested not in attr_set_seen: + attr_set_queue.append(nested) + attr_set_seen.add(nested) + + inherit = set() + if nested not in self.root_sets: + if nested not in self.pure_nested_structs: + self.pure_nested_structs[nested] = Struct(self, nested, inherited=inherit) + else: + raise Exception(f'Using attr set as root and nested not supported - {nested}') + + if 'type-value' in spec: + if nested in self.root_sets: + raise Exception("Inheriting members to a space used as root not supported") + inherit.update(set(spec['type-value'])) + elif spec['type'] == 'array-nest': + inherit.add('idx') + self.pure_nested_structs[nested].set_inherited(inherit) + for root_set, rs_members in self.root_sets.items(): for attr, spec in self.attr_sets[root_set].items(): if 'nested-attributes' in spec: - inherit = set() nested = spec['nested-attributes'] - if nested not in self.root_sets: - self.pure_nested_structs[nested] = Struct(self, nested, inherited=inherit) if attr in rs_members['request']: self.pure_nested_structs[nested].request = True if attr in rs_members['reply']: self.pure_nested_structs[nested].reply = True - if 'type-value' in spec: - if nested in self.root_sets: - raise Exception("Inheriting members to a space used as root not supported") - inherit.update(set(spec['type-value'])) - elif spec['type'] == 'array-nest': - inherit.add('idx') - self.pure_nested_structs[nested].set_inherited(inherit) - - def _load_all_notify(self): - for op_name, op in self.ops.items(): - if not op: - continue - - if 'notify' in op: - self.all_notify[op_name] = op['notify']['cmds'] + # Try to reorder according to dependencies + pns_key_list = list(self.pure_nested_structs.keys()) + pns_key_seen = set() + rounds = len(pns_key_list)**2 # it's basically bubble sort + for _ in range(rounds): + if len(pns_key_list) == 0: + break + name = pns_key_list.pop(0) + finished = True + for _, spec in self.attr_sets[name].items(): + if 'nested-attributes' in spec: + if spec['nested-attributes'] not in pns_key_seen: + # Dicts are sorted, this will make struct last + struct = self.pure_nested_structs.pop(name) + self.pure_nested_structs[name] = struct + finished = False + break + if finished: + pns_key_seen.add(name) + else: + pns_key_list.append(name) + # Propagate the request / reply + for attr_set, struct in reversed(self.pure_nested_structs.items()): + for _, spec in self.attr_sets[attr_set].items(): + if 'nested-attributes' in spec: + child = self.pure_nested_structs.get(spec['nested-attributes']) + if child: + child.request |= struct.request + child.reply |= struct.reply def _load_global_policy(self): global_set = set() @@ -874,33 +999,38 @@ class Family(SpecFamily): class RenderInfo: - def __init__(self, cw, family, ku_space, op, op_name, op_mode, attr_set=None): + def __init__(self, cw, family, ku_space, op, op_mode, attr_set=None): self.family = family self.nl = cw.nlib self.ku_space = ku_space - self.op = op - self.op_name = op_name self.op_mode = op_mode + self.op = op # 'do' and 'dump' response parsing is identical - if op_mode != 'do' and 'dump' in op and 'do' in op and 'reply' in op['do'] and \ - op["do"]["reply"] == op["dump"]["reply"]: - self.type_consistent = True - else: - self.type_consistent = op_mode == 'event' + self.type_consistent = True + if op_mode != 'do' and 'dump' in op and 'do' in op: + if ('reply' in op['do']) != ('reply' in op["dump"]): + self.type_consistent = False + elif 'reply' in op['do'] and op["do"]["reply"] != op["dump"]["reply"]: + self.type_consistent = False self.attr_set = attr_set if not self.attr_set: self.attr_set = op['attribute-set'] + self.type_name_conflict = False if op: - self.type_name = c_lower(op_name) + self.type_name = c_lower(op.name) else: self.type_name = c_lower(attr_set) + if attr_set in family.consts: + self.type_name_conflict = True self.cw = cw self.struct = dict() + if op_mode == 'notify': + op_mode = 'do' for op_dir in ['request', 'reply']: if op and op_dir in op[op_mode]: self.struct[op_dir] = Struct(family, self.attr_set, @@ -914,6 +1044,7 @@ class CodeWriter: self.nlib = nlib self._nl = False + self._block_end = False self._silent_block = False self._ind = 0 self._out = out_file @@ -923,9 +1054,17 @@ class CodeWriter: return line.startswith('if') or line.startswith('while') or line.startswith('for') def p(self, line, add_ind=0): + if self._block_end: + self._block_end = False + if line.startswith('else'): + line = '} ' + line + else: + self._out.write('\t' * self._ind + '}\n') + if self._nl: self._out.write('\n') self._nl = False + ind = self._ind if line[-1] == ':': ind -= 1 @@ -949,7 +1088,14 @@ class CodeWriter: if line and line[0] not in {';', ','}: line = ' ' + line self._ind -= 1 - self.p('}' + line) + self._nl = False + if not line: + # Delay printing closing bracket in case "else" comes next + if self._block_end: + self._out.write('\t' * (self._ind + 1) + '}\n') + self._block_end = True + else: + self.p('}' + line) def write_doc_line(self, doc, indent=True): words = doc.split() @@ -1068,7 +1214,40 @@ op_mode_to_wrapper = { } _C_KW = { - 'do' + 'auto', + 'bool', + 'break', + 'case', + 'char', + 'const', + 'continue', + 'default', + 'do', + 'double', + 'else', + 'enum', + 'extern', + 'float', + 'for', + 'goto', + 'if', + 'inline', + 'int', + 'long', + 'register', + 'return', + 'short', + 'signed', + 'sizeof', + 'static', + 'struct', + 'switch', + 'typedef', + 'union', + 'unsigned', + 'void', + 'volatile', + 'while' } @@ -1131,10 +1310,6 @@ def print_dump_prototype(ri): print_prototype(ri, "request") -def put_typol_fwd(cw, struct): - cw.p(f'extern struct ynl_policy_nest {struct.render_name}_nest;') - - def put_typol(cw, struct): type_max = struct.attr_set.max_name cw.block_start(line=f'struct ynl_policy_attr {struct.render_name}_policy[{type_max} + 1] =') @@ -1152,6 +1327,58 @@ def put_typol(cw, struct): cw.nl() +def _put_enum_to_str_helper(cw, render_name, map_name, arg_name, enum=None): + args = [f'int {arg_name}'] + if enum and not ('enum-name' in enum and not enum['enum-name']): + args = [f'enum {render_name} {arg_name}'] + cw.write_func_prot('const char *', f'{render_name}_str', args) + cw.block_start() + if enum and enum.type == 'flags': + cw.p(f'{arg_name} = ffs({arg_name}) - 1;') + cw.p(f'if ({arg_name} < 0 || {arg_name} >= (int)MNL_ARRAY_SIZE({map_name}))') + cw.p('return NULL;') + cw.p(f'return {map_name}[{arg_name}];') + cw.block_end() + cw.nl() + + +def put_op_name_fwd(family, cw): + cw.write_func_prot('const char *', f'{family.name}_op_str', ['int op'], suffix=';') + + +def put_op_name(family, cw): + map_name = f'{family.name}_op_strmap' + cw.block_start(line=f"static const char * const {map_name}[] =") + for op_name, op in family.msgs.items(): + if op.rsp_value: + if op.req_value == op.rsp_value: + cw.p(f'[{op.enum_name}] = "{op_name}",') + else: + cw.p(f'[{op.rsp_value}] = "{op_name}",') + cw.block_end(line=';') + cw.nl() + + _put_enum_to_str_helper(cw, family.name + '_op', map_name, 'op') + + +def put_enum_to_str_fwd(family, cw, enum): + args = [f'enum {enum.render_name} value'] + if 'enum-name' in enum and not enum['enum-name']: + args = ['int value'] + cw.write_func_prot('const char *', f'{enum.render_name}_str', args, suffix=';') + + +def put_enum_to_str(family, cw, enum): + map_name = f'{enum.render_name}_strmap' + cw.block_start(line=f"static const char * const {map_name}[] =") + for entry in enum.entries.values(): + cw.p(f'[{entry.value}] = "{entry.name}",') + cw.block_end(line=';') + cw.nl() + + _put_enum_to_str_helper(cw, enum.render_name, map_name, 'value', enum=enum) + + def put_req_nested(ri, struct): func_args = ['struct nlmsghdr *nlh', 'unsigned int attr_type', @@ -1196,6 +1423,11 @@ def _multi_parse(ri, struct, init_lines, local_vars): local_vars.append('struct ynl_parse_arg parg;') init_lines.append('parg.ys = yarg->ys;') + all_multi = array_nests | multi_attrs + + for anest in sorted(all_multi): + local_vars.append(f"unsigned int n_{struct[anest].c_name} = 0;") + ri.cw.block_start() ri.cw.write_func_lvar(local_vars) @@ -1206,13 +1438,21 @@ def _multi_parse(ri, struct, init_lines, local_vars): for arg in struct.inherited: ri.cw.p(f'dst->{arg} = {arg};') + for anest in sorted(all_multi): + aspec = struct[anest] + ri.cw.p(f"if (dst->{aspec.c_name})") + ri.cw.p(f'return ynl_error_parse(yarg, "attribute already present ({struct.attr_set.name}.{aspec.name})");') + ri.cw.nl() ri.cw.block_start(line=iter_line) + ri.cw.p('unsigned int type = mnl_attr_get_type(attr);') + ri.cw.nl() first = True for _, arg in struct.member_list(): - arg.attr_get(ri, 'dst', first=first) - first = False + good = arg.attr_get(ri, 'dst', first=first) + # First may be 'unused' or 'pad', ignore those + first &= not good ri.cw.block_end() ri.cw.nl() @@ -1220,8 +1460,9 @@ def _multi_parse(ri, struct, init_lines, local_vars): for anest in sorted(array_nests): aspec = struct[anest] - ri.cw.block_start(line=f"if (dst->n_{aspec.c_name})") - ri.cw.p(f"dst->{aspec.c_name} = calloc(dst->n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));") + ri.cw.block_start(line=f"if (n_{aspec.c_name})") + ri.cw.p(f"dst->{aspec.c_name} = calloc({aspec.c_name}, sizeof(*dst->{aspec.c_name}));") + ri.cw.p(f"dst->n_{aspec.c_name} = n_{aspec.c_name};") ri.cw.p('i = 0;') ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;") ri.cw.block_start(line=f"mnl_attr_for_each_nested(attr, attr_{aspec.c_name})") @@ -1235,8 +1476,9 @@ def _multi_parse(ri, struct, init_lines, local_vars): for anest in sorted(multi_attrs): aspec = struct[anest] - ri.cw.block_start(line=f"if (dst->n_{aspec.c_name})") - ri.cw.p(f"dst->{aspec.c_name} = calloc(dst->n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));") + ri.cw.block_start(line=f"if (n_{aspec.c_name})") + ri.cw.p(f"dst->{aspec.c_name} = calloc(n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));") + ri.cw.p(f"dst->n_{aspec.c_name} = n_{aspec.c_name};") ri.cw.p('i = 0;') if 'nested-attributes' in aspec: ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;") @@ -1304,13 +1546,13 @@ def print_req(ri): ret_err = '-1' direction = "request" local_vars = ['struct nlmsghdr *nlh;', - 'int len, err;'] + 'int err;'] if 'reply' in ri.op[ri.op_mode]: ret_ok = 'rsp' ret_err = 'NULL' local_vars += [f'{type_name(ri, rdir(direction))} *rsp;', - 'struct ynl_parse_arg yarg = { .ys = ys, };'] + 'struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };'] print_prototype(ri, direction, terminate=False) ri.cw.block_start() @@ -1320,41 +1562,39 @@ def print_req(ri): ri.cw.p(f"ys->req_policy = &{ri.struct['request'].render_name}_nest;") if 'reply' in ri.op[ri.op_mode]: - ri.cw.p(f"yarg.rsp_policy = &{ri.struct['reply'].render_name}_nest;") + ri.cw.p(f"yrs.yarg.rsp_policy = &{ri.struct['reply'].render_name}_nest;") ri.cw.nl() for _, attr in ri.struct["request"].member_list(): attr.attr_put(ri, "req") ri.cw.nl() - ri.cw.p('err = mnl_socket_sendto(ys->sock, nlh, nlh->nlmsg_len);') - ri.cw.p('if (err < 0)') - ri.cw.p(f"return {ret_err};") - ri.cw.nl() - ri.cw.p('len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE);') - ri.cw.p('if (len < 0)') - ri.cw.p(f"return {ret_err};") - ri.cw.nl() - + parse_arg = "NULL" if 'reply' in ri.op[ri.op_mode]: ri.cw.p('rsp = calloc(1, sizeof(*rsp));') - ri.cw.p('yarg.data = rsp;') + ri.cw.p('yrs.yarg.data = rsp;') + ri.cw.p(f"yrs.cb = {op_prefix(ri, 'reply')}_parse;") + if ri.op.value is not None: + ri.cw.p(f'yrs.rsp_cmd = {ri.op.enum_name};') + else: + ri.cw.p(f'yrs.rsp_cmd = {ri.op.rsp_value};') ri.cw.nl() - ri.cw.p(f"err = {ri.nl.parse_cb_run(op_prefix(ri, 'reply') + '_parse', '&yarg', False)};") - ri.cw.p('if (err < 0)') + parse_arg = '&yrs' + ri.cw.p(f"err = ynl_exec(ys, nlh, {parse_arg});") + ri.cw.p('if (err < 0)') + if 'reply' in ri.op[ri.op_mode]: ri.cw.p('goto err_free;') - ri.cw.nl() - - ri.cw.p('err = ynl_recv_ack(ys, err);') - ri.cw.p('if (err)') - ri.cw.p('goto err_free;') + else: + ri.cw.p('return -1;') ri.cw.nl() + ri.cw.p(f"return {ret_ok};") ri.cw.nl() - ri.cw.p('err_free:') if 'reply' in ri.op[ri.op_mode]: + ri.cw.p('err_free:') ri.cw.p(f"{call_free(ri, rdir(direction), 'rsp')}") - ri.cw.p(f"return {ret_err};") + ri.cw.p(f"return {ret_err};") + ri.cw.block_end() @@ -1364,7 +1604,7 @@ def print_dump(ri): ri.cw.block_start() local_vars = ['struct ynl_dump_state yds = {};', 'struct nlmsghdr *nlh;', - 'int len, err;'] + 'int err;'] for var in local_vars: ri.cw.p(f'{var}') @@ -1373,6 +1613,10 @@ def print_dump(ri): ri.cw.p('yds.ys = ys;') ri.cw.p(f"yds.alloc_sz = sizeof({type_name(ri, rdir(direction))});") ri.cw.p(f"yds.cb = {op_prefix(ri, 'reply', deref=True)}_parse;") + if ri.op.value is not None: + ri.cw.p(f'yds.rsp_cmd = {ri.op.enum_name};') + else: + ri.cw.p(f'yds.rsp_cmd = {ri.op.rsp_value};') ri.cw.p(f"yds.rsp_policy = &{ri.struct['reply'].render_name}_nest;") ri.cw.nl() ri.cw.p(f"nlh = ynl_gemsg_start_dump(ys, {ri.nl.get_family_id()}, {ri.op.enum_name}, 1);") @@ -1384,20 +1628,9 @@ def print_dump(ri): attr.attr_put(ri, "req") ri.cw.nl() - ri.cw.p('err = mnl_socket_sendto(ys->sock, nlh, nlh->nlmsg_len);') - ri.cw.p('if (err < 0)') - ri.cw.p('return NULL;') - ri.cw.nl() - - ri.cw.block_start(line='do') - ri.cw.p('len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE);') - ri.cw.p('if (len < 0)') - ri.cw.p('goto free_list;') - ri.cw.nl() - ri.cw.p(f"err = {ri.nl.parse_cb_run('ynl_dump_trampoline', '&yds', False, indent=2)};") + ri.cw.p('err = ynl_exec_dump(ys, nlh, &yds);') ri.cw.p('if (err < 0)') ri.cw.p('goto free_list;') - ri.cw.block_end(line='while (err > 0);') ri.cw.nl() ri.cw.p('return yds.first;') @@ -1418,14 +1651,27 @@ def free_arg_name(direction): return 'obj' +def print_alloc_wrapper(ri, direction): + name = op_prefix(ri, direction) + ri.cw.write_func_prot(f'static inline struct {name} *', f"{name}_alloc", [f"void"]) + ri.cw.block_start() + ri.cw.p(f'return calloc(1, sizeof(struct {name}));') + ri.cw.block_end() + + def print_free_prototype(ri, direction, suffix=';'): name = op_prefix(ri, direction) + struct_name = name + if ri.type_name_conflict: + struct_name += '_' arg = free_arg_name(direction) - ri.cw.write_func_prot('void', f"{name}_free", [f"struct {name} *{arg}"], suffix=suffix) + ri.cw.write_func_prot('void', f"{name}_free", [f"struct {struct_name} *{arg}"], suffix=suffix) def _print_type(ri, direction, struct): suffix = f'_{ri.type_name}{direction_to_suffix[direction]}' + if not direction and ri.type_name_conflict: + suffix += '_' if ri.op_mode == 'dump': suffix += '_dump' @@ -1465,6 +1711,7 @@ def print_type_full(ri, struct): def print_type_helpers(ri, direction, deref=False): print_free_prototype(ri, direction) + ri.cw.nl() if ri.ku_space == 'user' and direction == 'request': for _, attr in ri.struct[direction].member_list(): @@ -1473,6 +1720,7 @@ def print_type_helpers(ri, direction, deref=False): def print_req_type_helpers(ri): + print_alloc_wrapper(ri, "request") print_type_helpers(ri, "request") @@ -1496,6 +1744,12 @@ def print_req_type(ri): print_type(ri, "request") +def print_req_free(ri): + if 'request' not in ri.op[ri.op_mode]: + return + _free_type(ri, 'request', ri.struct['request']) + + def print_rsp_type(ri): if (ri.op_mode == 'do' or ri.op_mode == 'dump') and 'reply' in ri.op[ri.op_mode]: direction = 'reply' @@ -1513,6 +1767,7 @@ def print_wrapped_type(ri): elif ri.op_mode == 'notify' or ri.op_mode == 'event': ri.cw.p('__u16 family;') ri.cw.p('__u8 cmd;') + ri.cw.p('struct ynl_ntf_base_type *next;') ri.cw.p(f"void (*free)({type_name(ri, 'reply')} *ntf);") ri.cw.p(f"{type_name(ri, 'reply', deref=True)} obj __attribute__ ((aligned (8)));") ri.cw.block_end(line=';') @@ -1564,7 +1819,7 @@ def print_dump_type_free(ri): ri.cw.block_start() ri.cw.p(f"{sub_type} *next = rsp;") ri.cw.nl() - ri.cw.block_start(line='while (next)') + ri.cw.block_start(line='while ((void *)next != YNL_LIST_END)') _free_type_members_iter(ri, ri.struct['reply']) ri.cw.p('rsp = next;') ri.cw.p('next = rsp->next;') @@ -1587,70 +1842,6 @@ def print_ntf_type_free(ri): ri.cw.nl() -def print_ntf_parse_prototype(family, cw, suffix=';'): - cw.write_func_prot('struct ynl_ntf_base_type *', f"{family['name']}_ntf_parse", - ['struct ynl_sock *ys'], suffix=suffix) - - -def print_ntf_type_parse(family, cw, ku_mode): - print_ntf_parse_prototype(family, cw, suffix='') - cw.block_start() - cw.write_func_lvar(['struct genlmsghdr *genlh;', - 'struct nlmsghdr *nlh;', - 'struct ynl_parse_arg yarg = { .ys = ys, };', - 'struct ynl_ntf_base_type *rsp;', - 'int len, err;', - 'mnl_cb_t parse;']) - cw.p('len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE);') - cw.p('if (len < (ssize_t)(sizeof(*nlh) + sizeof(*genlh)))') - cw.p('return NULL;') - cw.nl() - cw.p('nlh = (struct nlmsghdr *)ys->rx_buf;') - cw.p('genlh = mnl_nlmsg_get_payload(nlh);') - cw.nl() - cw.block_start(line='switch (genlh->cmd)') - for ntf_op in sorted(family.all_notify.keys()): - op = family.ops[ntf_op] - ri = RenderInfo(cw, family, ku_mode, op, ntf_op, "notify") - for ntf in op['notify']['cmds']: - cw.p(f"case {ntf.enum_name}:") - cw.p(f"rsp = calloc(1, sizeof({type_name(ri, 'notify')}));") - cw.p(f"parse = {op_prefix(ri, 'reply', deref=True)}_parse;") - cw.p(f"yarg.rsp_policy = &{ri.struct['reply'].render_name}_nest;") - cw.p(f"rsp->free = (void *){op_prefix(ri, 'notify')}_free;") - cw.p('break;') - for op_name, op in family.ops.items(): - if 'event' not in op: - continue - ri = RenderInfo(cw, family, ku_mode, op, op_name, "event") - cw.p(f"case {op.enum_name}:") - cw.p(f"rsp = calloc(1, sizeof({type_name(ri, 'event')}));") - cw.p(f"parse = {op_prefix(ri, 'reply', deref=True)}_parse;") - cw.p(f"yarg.rsp_policy = &{ri.struct['reply'].render_name}_nest;") - cw.p(f"rsp->free = (void *){op_prefix(ri, 'notify')}_free;") - cw.p('break;') - cw.p('default:') - cw.p('ynl_error_unknown_notification(ys, genlh->cmd);') - cw.p('return NULL;') - cw.block_end() - cw.nl() - cw.p('yarg.data = rsp->data;') - cw.nl() - cw.p(f"err = {cw.nlib.parse_cb_run('parse', '&yarg', True)};") - cw.p('if (err < 0)') - cw.p('goto err_free;') - cw.nl() - cw.p('rsp->family = nlh->nlmsg_type;') - cw.p('rsp->cmd = genlh->cmd;') - cw.p('return rsp;') - cw.nl() - cw.p('err_free:') - cw.p('free(rsp);') - cw.p('return NULL;') - cw.block_end() - cw.nl() - - def print_req_policy_fwd(cw, struct, ri=None, terminate=True): if terminate and ri and kernel_can_gen_family_struct(struct.family): return @@ -2035,6 +2226,48 @@ def render_uapi(family, cw): cw.p(f'#endif /* {hdr_prot} */') +def _render_user_ntf_entry(ri, op): + ri.cw.block_start(line=f"[{op.enum_name}] = ") + ri.cw.p(f".alloc_sz\t= sizeof({type_name(ri, 'event')}),") + ri.cw.p(f".cb\t\t= {op_prefix(ri, 'reply', deref=True)}_parse,") + ri.cw.p(f".policy\t\t= &{ri.struct['reply'].render_name}_nest,") + ri.cw.p(f".free\t\t= (void *){op_prefix(ri, 'notify')}_free,") + ri.cw.block_end(line=',') + + +def render_user_family(family, cw, prototype): + symbol = f'const struct ynl_family ynl_{family.c_name}_family' + if prototype: + cw.p(f'extern {symbol};') + return + + if family.ntfs: + cw.block_start(line=f"static const struct ynl_ntf_info {family['name']}_ntf_info[] = ") + for ntf_op_name, ntf_op in family.ntfs.items(): + if 'notify' in ntf_op: + op = family.ops[ntf_op['notify']] + ri = RenderInfo(cw, family, "user", op, "notify") + elif 'event' in ntf_op: + ri = RenderInfo(cw, family, "user", ntf_op, "event") + else: + raise Exception('Invalid notification ' + ntf_op_name) + _render_user_ntf_entry(ri, ntf_op) + for op_name, op in family.ops.items(): + if 'event' not in op: + continue + ri = RenderInfo(cw, family, "user", op, "event") + _render_user_ntf_entry(ri, op) + cw.block_end(line=";") + cw.nl() + + cw.block_start(f'{symbol} = ') + cw.p(f'.name\t\t= "{family.name}",') + if family.ntfs: + cw.p(f".ntf_info\t= {family['name']}_ntf_info,") + cw.p(f".ntf_info_size\t= MNL_ARRAY_SIZE({family['name']}_ntf_info),") + cw.block_end(line=';') + + def find_kernel_root(full_path): sub_path = '' while True: @@ -2052,6 +2285,7 @@ def main(): parser.add_argument('--header', dest='header', action='store_true', default=None) parser.add_argument('--source', dest='header', action='store_false') parser.add_argument('--user-header', nargs='+', default=[]) + parser.add_argument('--exclude-op', action='append', default=[]) parser.add_argument('-o', dest='out_file', type=str) args = parser.parse_args() @@ -2060,8 +2294,10 @@ def main(): if args.header is None: parser.error("--header or --source is required") + exclude_ops = [re.compile(expr) for expr in args.exclude_op] + try: - parsed = Family(args.spec) + parsed = Family(args.spec, exclude_ops) if parsed.license != '((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)': print('Spec license:', parsed.license) print('License must be: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)') @@ -2071,6 +2307,13 @@ def main(): os.sys.exit(1) return + supported_models = ['unified'] + if args.mode == 'user': + supported_models += ['directional'] + if parsed.msg_id_model not in supported_models: + print(f'Message enum-model {parsed.msg_id_model} not supported for {args.mode} generation') + os.sys.exit(1) + cw = CodeWriter(BaseNlLib(), out_file) _, spec_kernel = find_kernel_root(args.spec) @@ -2081,6 +2324,11 @@ def main(): cw.p("/* Do not edit directly, auto-generated from: */") cw.p(f"/*\t{spec_kernel} */") cw.p(f"/* YNL-GEN {args.mode} {'header' if args.header else 'source'} */") + if args.exclude_op or args.user_header: + line = '' + line += ' --user-header '.join([''] + args.user_header) + line += ' --exclude-op '.join([''] + args.exclude_op) + cw.p(f'/* YNL-ARG{line} */') cw.nl() if args.mode == 'uapi': @@ -2101,7 +2349,16 @@ def main(): if args.out_file: cw.p(f'#include "{os.path.basename(args.out_file[:-2])}.h"') cw.nl() - headers = [parsed.uapi_header] + headers = ['uapi/' + parsed.uapi_header] + else: + cw.p('#include <stdlib.h>') + cw.p('#include <string.h>') + if args.header: + cw.p('#include <linux/types.h>') + else: + cw.p(f'#include "{parsed.name}-user.h"') + cw.p('#include "ynl.h"') + headers = [parsed.uapi_header] for definition in parsed['definitions']: if 'header' in definition: headers.append(definition['header']) @@ -2111,9 +2368,6 @@ def main(): if args.mode == "user": if not args.header: - cw.p("#include <stdlib.h>") - cw.p("#include <stdio.h>") - cw.p("#include <string.h>") cw.p("#include <libmnl/libmnl.h>") cw.p("#include <linux/genetlink.h>") cw.nl() @@ -2121,6 +2375,8 @@ def main(): cw.p(f'#include "{one}"') else: cw.p('struct ynl_sock;') + cw.nl() + render_user_family(parsed, cw, True) cw.nl() if args.mode == "kernel": @@ -2144,7 +2400,7 @@ def main(): if parsed.kernel_policy in {'per-op', 'split'}: for op_name, op in parsed.ops.items(): if 'do' in op and 'event' not in op: - ri = RenderInfo(cw, parsed, args.mode, op, op_name, "do") + ri = RenderInfo(cw, parsed, args.mode, op, "do") print_req_policy_fwd(cw, ri.struct['request'], ri=ri) cw.nl() @@ -2173,7 +2429,7 @@ def main(): for op_mode in ['do', 'dump']: if op_mode in op and 'request' in op[op_mode]: cw.p(f"/* {op.enum_name} - {op_mode} */") - ri = RenderInfo(cw, parsed, args.mode, op, op_name, op_mode) + ri = RenderInfo(cw, parsed, args.mode, op, op_mode) print_req_policy(cw, ri.struct['request'], ri=ri) cw.nl() @@ -2182,11 +2438,18 @@ def main(): print_kernel_family_struct_src(parsed, cw) if args.mode == "user": - has_ntf = False if args.header: + cw.p('/* Enums */') + put_op_name_fwd(parsed, cw) + + for name, const in parsed.consts.items(): + if isinstance(const, EnumSet): + put_enum_to_str_fwd(parsed, cw, const) + cw.nl() + cw.p('/* Common nested types */') - for attr_set, struct in sorted(parsed.pure_nested_structs.items()): - ri = RenderInfo(cw, parsed, args.mode, "", "", "", attr_set) + for attr_set, struct in parsed.pure_nested_structs.items(): + ri = RenderInfo(cw, parsed, args.mode, "", "", attr_set) print_type_full(ri, struct) for op_name, op in parsed.ops.items(): @@ -2194,7 +2457,7 @@ def main(): if 'do' in op and 'event' not in op: cw.p(f"/* {op.enum_name} - do */") - ri = RenderInfo(cw, parsed, args.mode, op, op_name, "do") + ri = RenderInfo(cw, parsed, args.mode, op, "do") print_req_type(ri) print_req_type_helpers(ri) cw.nl() @@ -2206,7 +2469,7 @@ def main(): if 'dump' in op: cw.p(f"/* {op.enum_name} - dump */") - ri = RenderInfo(cw, parsed, args.mode, op, op_name, 'dump') + ri = RenderInfo(cw, parsed, args.mode, op, 'dump') if 'request' in op['dump']: print_req_type(ri) print_req_type_helpers(ri) @@ -2216,39 +2479,41 @@ def main(): print_dump_prototype(ri) cw.nl() - if 'notify' in op: + if op.has_ntf: cw.p(f"/* {op.enum_name} - notify */") - ri = RenderInfo(cw, parsed, args.mode, op, op_name, 'notify') - has_ntf = True + ri = RenderInfo(cw, parsed, args.mode, op, 'notify') if not ri.type_consistent: - raise Exception('Only notifications with consistent types supported') + raise Exception(f'Only notifications with consistent types supported ({op.name})') print_wrapped_type(ri) + for op_name, op in parsed.ntfs.items(): if 'event' in op: - ri = RenderInfo(cw, parsed, args.mode, op, op_name, 'event') + ri = RenderInfo(cw, parsed, args.mode, op, 'event') cw.p(f"/* {op.enum_name} - event */") print_rsp_type(ri) cw.nl() print_wrapped_type(ri) - - if has_ntf: - cw.p('/* --------------- Common notification parsing --------------- */') - print_ntf_parse_prototype(parsed, cw) cw.nl() else: - cw.p('/* Policies */') - for name, _ in parsed.attr_sets.items(): - struct = Struct(parsed, name) - put_typol_fwd(cw, struct) + cw.p('/* Enums */') + put_op_name(parsed, cw) + + for name, const in parsed.consts.items(): + if isinstance(const, EnumSet): + put_enum_to_str(parsed, cw, const) cw.nl() - for name, _ in parsed.attr_sets.items(): + cw.p('/* Policies */') + for name in parsed.pure_nested_structs: + struct = Struct(parsed, name) + put_typol(cw, struct) + for name in parsed.root_sets: struct = Struct(parsed, name) put_typol(cw, struct) cw.p('/* Common nested types */') - for attr_set, struct in sorted(parsed.pure_nested_structs.items()): - ri = RenderInfo(cw, parsed, args.mode, "", "", "", attr_set) + for attr_set, struct in parsed.pure_nested_structs.items(): + ri = RenderInfo(cw, parsed, args.mode, "", "", attr_set) free_rsp_nested(ri, struct) if struct.request: @@ -2260,7 +2525,8 @@ def main(): cw.p(f"/* ============== {op.enum_name} ============== */") if 'do' in op and 'event' not in op: cw.p(f"/* {op.enum_name} - do */") - ri = RenderInfo(cw, parsed, args.mode, op, op_name, "do") + ri = RenderInfo(cw, parsed, args.mode, op, "do") + print_req_free(ri) print_rsp_free(ri) parse_rsp_msg(ri) print_req(ri) @@ -2268,34 +2534,31 @@ def main(): if 'dump' in op: cw.p(f"/* {op.enum_name} - dump */") - ri = RenderInfo(cw, parsed, args.mode, op, op_name, "dump") + ri = RenderInfo(cw, parsed, args.mode, op, "dump") if not ri.type_consistent: parse_rsp_msg(ri, deref=True) print_dump_type_free(ri) print_dump(ri) cw.nl() - if 'notify' in op: + if op.has_ntf: cw.p(f"/* {op.enum_name} - notify */") - ri = RenderInfo(cw, parsed, args.mode, op, op_name, 'notify') - has_ntf = True + ri = RenderInfo(cw, parsed, args.mode, op, 'notify') if not ri.type_consistent: - raise Exception('Only notifications with consistent types supported') + raise Exception(f'Only notifications with consistent types supported ({op.name})') print_ntf_type_free(ri) + for op_name, op in parsed.ntfs.items(): if 'event' in op: cw.p(f"/* {op.enum_name} - event */") - has_ntf = True - ri = RenderInfo(cw, parsed, args.mode, op, op_name, "do") + ri = RenderInfo(cw, parsed, args.mode, op, "do") parse_rsp_msg(ri) - ri = RenderInfo(cw, parsed, args.mode, op, op_name, "event") + ri = RenderInfo(cw, parsed, args.mode, op, "event") print_ntf_type_free(ri) - - if has_ntf: - cw.p('/* --------------- Common notification parsing --------------- */') - print_ntf_type_parse(parsed, cw, args.mode) + cw.nl() + render_user_family(parsed, cw, False) if args.header: cw.p(f'#endif /* {hdr_prot} */') diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh index 74f5de1c23994..8d4ca6a505826 100755 --- a/tools/net/ynl/ynl-regen.sh +++ b/tools/net/ynl/ynl-regen.sh @@ -14,11 +14,12 @@ done KDIR=$(dirname $(dirname $(dirname $(dirname $(realpath $0))))) -files=$(git grep --files-with-matches '^/\* YNL-GEN \(kernel\|uapi\)') +files=$(git grep --files-with-matches '^/\* YNL-GEN \(kernel\|uapi\|user\)') for f in $files; do # params: 0 1 2 3 # $YAML YNL-GEN kernel $mode params=( $(git grep -B1 -h '/\* YNL-GEN' $f | sed 's@/\*\(.*\)\*/@\1@') ) + args=$(sed -n 's@/\* YNL-ARG \(.*\) \*/@\1@p' $f) if [ $f -nt ${params[0]} -a -z "$force" ]; then echo -e "\tSKIP $f" @@ -26,5 +27,6 @@ for f in $files; do fi echo -e "\tGEN ${params[2]}\t$f" - $TOOL --mode ${params[2]} --${params[3]} --spec $KDIR/${params[0]} -o $f + $TOOL --mode ${params[2]} --${params[3]} --spec $KDIR/${params[0]} \ + $args -o $f done diff --git a/tools/objtool/Documentation/objtool.txt b/tools/objtool/Documentation/objtool.txt index 744db4218e7ac..fe39c2a8ef0db 100644 --- a/tools/objtool/Documentation/objtool.txt +++ b/tools/objtool/Documentation/objtool.txt @@ -244,6 +244,11 @@ To achieve the validation, objtool enforces the following rules: Objtool warnings ---------------- +NOTE: When requesting help with an objtool warning, please recreate with +OBJTOOL_VERBOSE=1 (e.g., "make OBJTOOL_VERBOSE=1") and send the full +output, including any disassembly or backtrace below the warning, to the +objtool maintainers. + For asm files, if you're getting an error which doesn't make sense, first make sure that the affected code follows the above rules. @@ -298,6 +303,11 @@ the objtool maintainers. If it's not actually in a callable function (e.g. kernel entry code), change ENDPROC to END. +3. file.o: warning: objtool: foo+0x48c: bar() is missing a __noreturn annotation + + The call from foo() to bar() doesn't return, but bar() is missing the + __noreturn annotation. NOTE: In addition to annotating the function + with __noreturn, please also add it to tools/objtool/noreturns.h. 4. file.o: warning: objtool: func(): can't find starting instruction or diff --git a/tools/objtool/arch/powerpc/include/arch/elf.h b/tools/objtool/arch/powerpc/include/arch/elf.h index 73f9ae172fe55..66814fa280240 100644 --- a/tools/objtool/arch/powerpc/include/arch/elf.h +++ b/tools/objtool/arch/powerpc/include/arch/elf.h @@ -1,10 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ - #ifndef _OBJTOOL_ARCH_ELF #define _OBJTOOL_ARCH_ELF -#define R_NONE R_PPC_NONE -#define R_ABS64 R_PPC64_ADDR64 -#define R_ABS32 R_PPC_ADDR32 +#define R_NONE R_PPC_NONE +#define R_ABS64 R_PPC64_ADDR64 +#define R_ABS32 R_PPC_ADDR32 +#define R_DATA32 R_PPC_REL32 +#define R_DATA64 R_PPC64_REL64 +#define R_TEXT32 R_PPC_REL32 +#define R_TEXT64 R_PPC64_REL32 #endif /* _OBJTOOL_ARCH_ELF */ diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 9ef024fd648c1..2e1caabecb185 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -84,7 +84,7 @@ bool arch_pc_relative_reloc(struct reloc *reloc) * All relocation types where P (the address of the target) * is included in the computation. */ - switch (reloc->type) { + switch (reloc_type(reloc)) { case R_X86_64_PC8: case R_X86_64_PC16: case R_X86_64_PC32: @@ -623,11 +623,11 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec if (!immr || strcmp(immr->sym->name, "pv_ops")) break; - idx = (immr->addend + 8) / sizeof(void *); + idx = (reloc_addend(immr) + 8) / sizeof(void *); func = disp->sym; if (disp->sym->type == STT_SECTION) - func = find_symbol_by_offset(disp->sym->sec, disp->addend); + func = find_symbol_by_offset(disp->sym->sec, reloc_addend(disp)); if (!func) { WARN("no func for pv_ops[]"); return -1; diff --git a/tools/objtool/arch/x86/include/arch/elf.h b/tools/objtool/arch/x86/include/arch/elf.h index ac14987cf6875..7131f7f51a4e8 100644 --- a/tools/objtool/arch/x86/include/arch/elf.h +++ b/tools/objtool/arch/x86/include/arch/elf.h @@ -1,8 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef _OBJTOOL_ARCH_ELF #define _OBJTOOL_ARCH_ELF -#define R_NONE R_X86_64_NONE -#define R_ABS64 R_X86_64_64 -#define R_ABS32 R_X86_64_32 +#define R_NONE R_X86_64_NONE +#define R_ABS32 R_X86_64_32 +#define R_ABS64 R_X86_64_64 +#define R_DATA32 R_X86_64_PC32 +#define R_DATA64 R_X86_64_PC32 +#define R_TEXT32 R_X86_64_PC32 +#define R_TEXT64 R_X86_64_PC32 #endif /* _OBJTOOL_ARCH_ELF */ diff --git a/tools/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c index 7c97b73912799..29e949579ede6 100644 --- a/tools/objtool/arch/x86/special.c +++ b/tools/objtool/arch/x86/special.c @@ -42,13 +42,7 @@ bool arch_support_alt_relocation(struct special_alt *special_alt, struct instruction *insn, struct reloc *reloc) { - /* - * The x86 alternatives code adjusts the offsets only when it - * encounters a branch instruction at the very beginning of the - * replacement group. - */ - return insn->offset == special_alt->new_off && - (insn->type == INSN_CALL || is_jump(insn)); + return true; } /* @@ -105,10 +99,10 @@ struct reloc *arch_find_switch_table(struct objtool_file *file, !text_reloc->sym->sec->rodata) return NULL; - table_offset = text_reloc->addend; + table_offset = reloc_addend(text_reloc); table_sec = text_reloc->sym->sec; - if (text_reloc->type == R_X86_64_PC32) + if (reloc_type(text_reloc) == R_X86_64_PC32) table_offset += 4; /* @@ -138,7 +132,7 @@ struct reloc *arch_find_switch_table(struct objtool_file *file, * indicates a rare GCC quirk/bug which can leave dead * code behind. */ - if (text_reloc->type == R_X86_64_PC32) + if (reloc_type(text_reloc) == R_X86_64_PC32) file->ignore_unreachables = true; return rodata_reloc; diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index 7c175198d09fc..5e21cfb7661d0 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -93,6 +93,7 @@ static const struct option check_options[] = { OPT_BOOLEAN(0, "no-unreachable", &opts.no_unreachable, "skip 'unreachable instruction' warnings"), OPT_BOOLEAN(0, "sec-address", &opts.sec_address, "print section addresses in warnings"), OPT_BOOLEAN(0, "stats", &opts.stats, "print statistics"), + OPT_BOOLEAN('v', "verbose", &opts.verbose, "verbose warnings"), OPT_END(), }; @@ -118,6 +119,10 @@ int cmd_parse_options(int argc, const char **argv, const char * const usage[]) parse_options(envc, envv, check_options, env_usage, 0); } + env = getenv("OBJTOOL_VERBOSE"); + if (env && !strcmp(env, "1")) + opts.verbose = true; + argc = parse_options(argc, argv, check_options, usage, 0); if (argc != 1) usage_with_options(usage, check_options); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 0fcf99c914000..8936a05f0e5ac 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -8,7 +8,6 @@ #include <inttypes.h> #include <sys/mman.h> -#include <arch/elf.h> #include <objtool/builtin.h> #include <objtool/cfi.h> #include <objtool/arch.h> @@ -33,6 +32,7 @@ static unsigned long nr_cfi, nr_cfi_reused, nr_cfi_cache; static struct cfi_init_state initial_func_cfi; static struct cfi_state init_cfi; static struct cfi_state func_cfi; +static struct cfi_state force_undefined_cfi; struct instruction *find_insn(struct objtool_file *file, struct section *sec, unsigned long offset) @@ -192,51 +192,11 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, struct instruction *insn; bool empty = true; - /* - * Unfortunately these have to be hard coded because the noreturn - * attribute isn't provided in ELF data. Keep 'em sorted. - */ +#define NORETURN(func) __stringify(func), static const char * const global_noreturns[] = { - "__invalid_creds", - "__module_put_and_kthread_exit", - "__reiserfs_panic", - "__stack_chk_fail", - "__ubsan_handle_builtin_unreachable", - "arch_call_rest_init", - "arch_cpu_idle_dead", - "btrfs_assertfail", - "cpu_bringup_and_idle", - "cpu_startup_entry", - "do_exit", - "do_group_exit", - "do_task_dead", - "ex_handler_msr_mce", - "fortify_panic", - "hlt_play_dead", - "hv_ghcb_terminate", - "kthread_complete_and_exit", - "kthread_exit", - "kunit_try_catch_throw", - "lbug_with_loc", - "machine_real_restart", - "make_task_dead", - "mpt_halt_firmware", - "nmi_panic_self_stop", - "panic", - "panic_smp_self_stop", - "rest_init", - "resume_play_dead", - "rewind_stack_and_make_dead", - "sev_es_terminate", - "snp_abort", - "start_kernel", - "stop_this_cpu", - "usercopy_abort", - "x86_64_start_kernel", - "x86_64_start_reservations", - "xen_cpu_bringup_again", - "xen_start_kernel", +#include "noreturns.h" }; +#undef NORETURN if (!func) return false; @@ -533,7 +493,7 @@ static int add_pv_ops(struct objtool_file *file, const char *symname) { struct symbol *sym, *func; unsigned long off, end; - struct reloc *rel; + struct reloc *reloc; int idx; sym = find_symbol_by_name(file->elf, symname); @@ -543,19 +503,20 @@ static int add_pv_ops(struct objtool_file *file, const char *symname) off = sym->offset; end = off + sym->len; for (;;) { - rel = find_reloc_by_dest_range(file->elf, sym->sec, off, end - off); - if (!rel) + reloc = find_reloc_by_dest_range(file->elf, sym->sec, off, end - off); + if (!reloc) break; - func = rel->sym; + func = reloc->sym; if (func->type == STT_SECTION) - func = find_symbol_by_offset(rel->sym->sec, rel->addend); + func = find_symbol_by_offset(reloc->sym->sec, + reloc_addend(reloc)); - idx = (rel->offset - sym->offset) / sizeof(unsigned long); + idx = (reloc_offset(reloc) - sym->offset) / sizeof(unsigned long); objtool_pv_add(file, idx, func); - off = rel->offset + 1; + off = reloc_offset(reloc) + 1; if (off > end) break; } @@ -620,35 +581,40 @@ static struct instruction *find_last_insn(struct objtool_file *file, */ static int add_dead_ends(struct objtool_file *file) { - struct section *sec; + struct section *rsec; struct reloc *reloc; struct instruction *insn; + s64 addend; /* * Check for manually annotated dead ends. */ - sec = find_section_by_name(file->elf, ".rela.discard.unreachable"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.unreachable"); + if (!rsec) goto reachable; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { + if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", sec->name); + WARN("unexpected relocation symbol type in %s", rsec->name); return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + + addend = reloc_addend(reloc); + + insn = find_insn(file, reloc->sym->sec, addend); if (insn) insn = prev_insn_same_sec(file, insn); - else if (reloc->addend == reloc->sym->sec->sh.sh_size) { + else if (addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find unreachable insn at %s+0x%" PRIx64, - reloc->sym->sec->name, reloc->addend); + reloc->sym->sec->name, addend); return -1; } } else { WARN("can't find unreachable insn at %s+0x%" PRIx64, - reloc->sym->sec->name, reloc->addend); + reloc->sym->sec->name, addend); return -1; } @@ -662,28 +628,32 @@ reachable: * GCC doesn't know the "ud2" is fatal, so it generates code as if it's * not a dead end. */ - sec = find_section_by_name(file->elf, ".rela.discard.reachable"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.reachable"); + if (!rsec) return 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { + if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", sec->name); + WARN("unexpected relocation symbol type in %s", rsec->name); return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + + addend = reloc_addend(reloc); + + insn = find_insn(file, reloc->sym->sec, addend); if (insn) insn = prev_insn_same_sec(file, insn); - else if (reloc->addend == reloc->sym->sec->sh.sh_size) { + else if (addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find reachable insn at %s+0x%" PRIx64, - reloc->sym->sec->name, reloc->addend); + reloc->sym->sec->name, addend); return -1; } } else { WARN("can't find reachable insn at %s+0x%" PRIx64, - reloc->sym->sec->name, reloc->addend); + reloc->sym->sec->name, addend); return -1; } @@ -695,8 +665,8 @@ reachable: static int create_static_call_sections(struct objtool_file *file) { - struct section *sec; struct static_call_site *site; + struct section *sec; struct instruction *insn; struct symbol *key_sym; char *key_name, *tmp; @@ -716,22 +686,21 @@ static int create_static_call_sections(struct objtool_file *file) list_for_each_entry(insn, &file->static_call_list, call_node) idx++; - sec = elf_create_section(file->elf, ".static_call_sites", SHF_WRITE, - sizeof(struct static_call_site), idx); + sec = elf_create_section_pair(file->elf, ".static_call_sites", + sizeof(*site), idx, idx * 2); if (!sec) return -1; + /* Allow modules to modify the low bits of static_call_site::key */ + sec->sh.sh_flags |= SHF_WRITE; + idx = 0; list_for_each_entry(insn, &file->static_call_list, call_node) { - site = (struct static_call_site *)sec->data->d_buf + idx; - memset(site, 0, sizeof(struct static_call_site)); - /* populate reloc for 'addr' */ - if (elf_add_reloc_to_insn(file->elf, sec, - idx * sizeof(struct static_call_site), - R_X86_64_PC32, - insn->sec, insn->offset)) + if (!elf_init_reloc_text_sym(file->elf, sec, + idx * sizeof(*site), idx * 2, + insn->sec, insn->offset)) return -1; /* find key symbol */ @@ -771,10 +740,10 @@ static int create_static_call_sections(struct objtool_file *file) free(key_name); /* populate reloc for 'key' */ - if (elf_add_reloc(file->elf, sec, - idx * sizeof(struct static_call_site) + 4, - R_X86_64_PC32, key_sym, - is_sibling_call(insn) * STATIC_CALL_SITE_TAIL)) + if (!elf_init_reloc_data_sym(file->elf, sec, + idx * sizeof(*site) + 4, + (idx * 2) + 1, key_sym, + is_sibling_call(insn) * STATIC_CALL_SITE_TAIL)) return -1; idx++; @@ -802,26 +771,18 @@ static int create_retpoline_sites_sections(struct objtool_file *file) if (!idx) return 0; - sec = elf_create_section(file->elf, ".retpoline_sites", 0, - sizeof(int), idx); - if (!sec) { - WARN("elf_create_section: .retpoline_sites"); + sec = elf_create_section_pair(file->elf, ".retpoline_sites", + sizeof(int), idx, idx); + if (!sec) return -1; - } idx = 0; list_for_each_entry(insn, &file->retpoline_call_list, call_node) { - int *site = (int *)sec->data->d_buf + idx; - *site = 0; - - if (elf_add_reloc_to_insn(file->elf, sec, - idx * sizeof(int), - R_X86_64_PC32, - insn->sec, insn->offset)) { - WARN("elf_add_reloc_to_insn: .retpoline_sites"); + if (!elf_init_reloc_text_sym(file->elf, sec, + idx * sizeof(int), idx, + insn->sec, insn->offset)) return -1; - } idx++; } @@ -848,26 +809,18 @@ static int create_return_sites_sections(struct objtool_file *file) if (!idx) return 0; - sec = elf_create_section(file->elf, ".return_sites", 0, - sizeof(int), idx); - if (!sec) { - WARN("elf_create_section: .return_sites"); + sec = elf_create_section_pair(file->elf, ".return_sites", + sizeof(int), idx, idx); + if (!sec) return -1; - } idx = 0; list_for_each_entry(insn, &file->return_thunk_list, call_node) { - int *site = (int *)sec->data->d_buf + idx; - *site = 0; - - if (elf_add_reloc_to_insn(file->elf, sec, - idx * sizeof(int), - R_X86_64_PC32, - insn->sec, insn->offset)) { - WARN("elf_add_reloc_to_insn: .return_sites"); + if (!elf_init_reloc_text_sym(file->elf, sec, + idx * sizeof(int), idx, + insn->sec, insn->offset)) return -1; - } idx++; } @@ -900,12 +853,10 @@ static int create_ibt_endbr_seal_sections(struct objtool_file *file) if (!idx) return 0; - sec = elf_create_section(file->elf, ".ibt_endbr_seal", 0, - sizeof(int), idx); - if (!sec) { - WARN("elf_create_section: .ibt_endbr_seal"); + sec = elf_create_section_pair(file->elf, ".ibt_endbr_seal", + sizeof(int), idx, idx); + if (!sec) return -1; - } idx = 0; list_for_each_entry(insn, &file->endbr_list, call_node) { @@ -920,13 +871,10 @@ static int create_ibt_endbr_seal_sections(struct objtool_file *file) !strcmp(sym->name, "cleanup_module"))) WARN("%s(): not an indirect call target", sym->name); - if (elf_add_reloc_to_insn(file->elf, sec, - idx * sizeof(int), - R_X86_64_PC32, - insn->sec, insn->offset)) { - WARN("elf_add_reloc_to_insn: .ibt_endbr_seal"); + if (!elf_init_reloc_text_sym(file->elf, sec, + idx * sizeof(int), idx, + insn->sec, insn->offset)) return -1; - } idx++; } @@ -938,7 +886,6 @@ static int create_cfi_sections(struct objtool_file *file) { struct section *sec; struct symbol *sym; - unsigned int *loc; int idx; sec = find_section_by_name(file->elf, ".cfi_sites"); @@ -959,7 +906,8 @@ static int create_cfi_sections(struct objtool_file *file) idx++; } - sec = elf_create_section(file->elf, ".cfi_sites", 0, sizeof(unsigned int), idx); + sec = elf_create_section_pair(file->elf, ".cfi_sites", + sizeof(unsigned int), idx, idx); if (!sec) return -1; @@ -971,13 +919,9 @@ static int create_cfi_sections(struct objtool_file *file) if (strncmp(sym->name, "__cfi_", 6)) continue; - loc = (unsigned int *)sec->data->d_buf + idx; - memset(loc, 0, sizeof(unsigned int)); - - if (elf_add_reloc_to_insn(file->elf, sec, - idx * sizeof(unsigned int), - R_X86_64_PC32, - sym->sec, sym->offset)) + if (!elf_init_reloc_text_sym(file->elf, sec, + idx * sizeof(unsigned int), idx, + sym->sec, sym->offset)) return -1; idx++; @@ -988,7 +932,7 @@ static int create_cfi_sections(struct objtool_file *file) static int create_mcount_loc_sections(struct objtool_file *file) { - int addrsize = elf_class_addrsize(file->elf); + size_t addr_size = elf_addr_size(file->elf); struct instruction *insn; struct section *sec; int idx; @@ -1007,25 +951,26 @@ static int create_mcount_loc_sections(struct objtool_file *file) list_for_each_entry(insn, &file->mcount_loc_list, call_node) idx++; - sec = elf_create_section(file->elf, "__mcount_loc", 0, addrsize, idx); + sec = elf_create_section_pair(file->elf, "__mcount_loc", addr_size, + idx, idx); if (!sec) return -1; - sec->sh.sh_addralign = addrsize; + sec->sh.sh_addralign = addr_size; idx = 0; list_for_each_entry(insn, &file->mcount_loc_list, call_node) { - void *loc; - loc = sec->data->d_buf + idx; - memset(loc, 0, addrsize); + struct reloc *reloc; - if (elf_add_reloc_to_insn(file->elf, sec, idx, - addrsize == sizeof(u64) ? R_ABS64 : R_ABS32, - insn->sec, insn->offset)) + reloc = elf_init_reloc_text_sym(file->elf, sec, idx * addr_size, idx, + insn->sec, insn->offset); + if (!reloc) return -1; - idx += addrsize; + set_reloc_type(file->elf, reloc, addr_size == 8 ? R_ABS64 : R_ABS32); + + idx++; } return 0; @@ -1035,7 +980,6 @@ static int create_direct_call_sections(struct objtool_file *file) { struct instruction *insn; struct section *sec; - unsigned int *loc; int idx; sec = find_section_by_name(file->elf, ".call_sites"); @@ -1052,20 +996,17 @@ static int create_direct_call_sections(struct objtool_file *file) list_for_each_entry(insn, &file->call_list, call_node) idx++; - sec = elf_create_section(file->elf, ".call_sites", 0, sizeof(unsigned int), idx); + sec = elf_create_section_pair(file->elf, ".call_sites", + sizeof(unsigned int), idx, idx); if (!sec) return -1; idx = 0; list_for_each_entry(insn, &file->call_list, call_node) { - loc = (unsigned int *)sec->data->d_buf + idx; - memset(loc, 0, sizeof(unsigned int)); - - if (elf_add_reloc_to_insn(file->elf, sec, - idx * sizeof(unsigned int), - R_X86_64_PC32, - insn->sec, insn->offset)) + if (!elf_init_reloc_text_sym(file->elf, sec, + idx * sizeof(unsigned int), idx, + insn->sec, insn->offset)) return -1; idx++; @@ -1080,28 +1021,29 @@ static int create_direct_call_sections(struct objtool_file *file) static void add_ignores(struct objtool_file *file) { struct instruction *insn; - struct section *sec; + struct section *rsec; struct symbol *func; struct reloc *reloc; - sec = find_section_by_name(file->elf, ".rela.discard.func_stack_frame_non_standard"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.func_stack_frame_non_standard"); + if (!rsec) return; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { switch (reloc->sym->type) { case STT_FUNC: func = reloc->sym; break; case STT_SECTION: - func = find_func_by_offset(reloc->sym->sec, reloc->addend); + func = find_func_by_offset(reloc->sym->sec, reloc_addend(reloc)); if (!func) continue; break; default: - WARN("unexpected relocation symbol type in %s: %d", sec->name, reloc->sym->type); + WARN("unexpected relocation symbol type in %s: %d", + rsec->name, reloc->sym->type); continue; } @@ -1320,21 +1262,21 @@ static void add_uaccess_safe(struct objtool_file *file) */ static int add_ignore_alternatives(struct objtool_file *file) { - struct section *sec; + struct section *rsec; struct reloc *reloc; struct instruction *insn; - sec = find_section_by_name(file->elf, ".rela.discard.ignore_alts"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.ignore_alts"); + if (!rsec) return 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", sec->name); + WARN("unexpected relocation symbol type in %s", rsec->name); return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!insn) { WARN("bad .discard.ignore_alts entry"); return -1; @@ -1421,10 +1363,8 @@ static void annotate_call_site(struct objtool_file *file, * noinstr text. */ if (opts.hack_noinstr && insn->sec->noinstr && sym->profiling_func) { - if (reloc) { - reloc->type = R_NONE; - elf_write_reloc(file->elf, reloc); - } + if (reloc) + set_reloc_type(file->elf, reloc, R_NONE); elf_write_insn(file->elf, insn->sec, insn->offset, insn->len, @@ -1450,10 +1390,8 @@ static void annotate_call_site(struct objtool_file *file, if (sibling) WARN_INSN(insn, "tail call to __fentry__ !?!?"); if (opts.mnop) { - if (reloc) { - reloc->type = R_NONE; - elf_write_reloc(file->elf, reloc); - } + if (reloc) + set_reloc_type(file->elf, reloc, R_NONE); elf_write_insn(file->elf, insn->sec, insn->offset, insn->len, @@ -1610,7 +1548,7 @@ static int add_jump_destinations(struct objtool_file *file) dest_off = arch_jump_destination(insn); } else if (reloc->sym->type == STT_SECTION) { dest_sec = reloc->sym->sec; - dest_off = arch_dest_reloc_offset(reloc->addend); + dest_off = arch_dest_reloc_offset(reloc_addend(reloc)); } else if (reloc->sym->retpoline_thunk) { add_retpoline_call(file, insn); continue; @@ -1627,7 +1565,7 @@ static int add_jump_destinations(struct objtool_file *file) } else if (reloc->sym->sec->idx) { dest_sec = reloc->sym->sec; dest_off = reloc->sym->sym.st_value + - arch_dest_reloc_offset(reloc->addend); + arch_dest_reloc_offset(reloc_addend(reloc)); } else { /* non-func asm code jumping to another file */ continue; @@ -1744,7 +1682,7 @@ static int add_call_destinations(struct objtool_file *file) } } else if (reloc->sym->type == STT_SECTION) { - dest_off = arch_dest_reloc_offset(reloc->addend); + dest_off = arch_dest_reloc_offset(reloc_addend(reloc)); dest = find_call_destination(reloc->sym->sec, dest_off); if (!dest) { WARN_INSN(insn, "can't find call dest symbol at %s+0x%lx", @@ -1932,10 +1870,8 @@ static int handle_jump_alt(struct objtool_file *file, if (opts.hack_jump_label && special_alt->key_addend & 2) { struct reloc *reloc = insn_reloc(file, orig_insn); - if (reloc) { - reloc->type = R_NONE; - elf_write_reloc(file->elf, reloc); - } + if (reloc) + set_reloc_type(file->elf, reloc, R_NONE); elf_write_insn(file->elf, orig_insn->sec, orig_insn->offset, orig_insn->len, arch_nop_insn(orig_insn->len)); @@ -2047,34 +1983,35 @@ out: } static int add_jump_table(struct objtool_file *file, struct instruction *insn, - struct reloc *table) + struct reloc *next_table) { - struct reloc *reloc = table; - struct instruction *dest_insn; - struct alternative *alt; struct symbol *pfunc = insn_func(insn)->pfunc; + struct reloc *table = insn_jump_table(insn); + struct instruction *dest_insn; unsigned int prev_offset = 0; + struct reloc *reloc = table; + struct alternative *alt; /* * Each @reloc is a switch table relocation which points to the target * instruction. */ - list_for_each_entry_from(reloc, &table->sec->reloc_list, list) { + for_each_reloc_from(table->sec, reloc) { /* Check for the end of the table: */ - if (reloc != table && reloc->jump_table_start) + if (reloc != table && reloc == next_table) break; /* Make sure the table entries are consecutive: */ - if (prev_offset && reloc->offset != prev_offset + 8) + if (prev_offset && reloc_offset(reloc) != prev_offset + 8) break; /* Detect function pointers from contiguous objects: */ if (reloc->sym->sec == pfunc->sec && - reloc->addend == pfunc->offset) + reloc_addend(reloc) == pfunc->offset) break; - dest_insn = find_insn(file, reloc->sym->sec, reloc->addend); + dest_insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!dest_insn) break; @@ -2091,7 +2028,7 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, alt->insn = dest_insn; alt->next = insn->alts; insn->alts = alt; - prev_offset = reloc->offset; + prev_offset = reloc_offset(reloc); } if (!prev_offset) { @@ -2135,7 +2072,7 @@ static struct reloc *find_jump_table(struct objtool_file *file, table_reloc = arch_find_switch_table(file, insn); if (!table_reloc) continue; - dest_insn = find_insn(file, table_reloc->sym->sec, table_reloc->addend); + dest_insn = find_insn(file, table_reloc->sym->sec, reloc_addend(table_reloc)); if (!dest_insn || !insn_func(dest_insn) || insn_func(dest_insn)->pfunc != func) continue; @@ -2177,29 +2114,39 @@ static void mark_func_jump_tables(struct objtool_file *file, continue; reloc = find_jump_table(file, func, insn); - if (reloc) { - reloc->jump_table_start = true; + if (reloc) insn->_jump_table = reloc; - } } } static int add_func_jump_tables(struct objtool_file *file, struct symbol *func) { - struct instruction *insn; - int ret; + struct instruction *insn, *insn_t1 = NULL, *insn_t2; + int ret = 0; func_for_each_insn(file, func, insn) { if (!insn_jump_table(insn)) continue; - ret = add_jump_table(file, insn, insn_jump_table(insn)); + if (!insn_t1) { + insn_t1 = insn; + continue; + } + + insn_t2 = insn; + + ret = add_jump_table(file, insn_t1, insn_jump_table(insn_t2)); if (ret) return ret; + + insn_t1 = insn_t2; } - return 0; + if (insn_t1) + ret = add_jump_table(file, insn_t1, NULL); + + return ret; } /* @@ -2240,7 +2187,7 @@ static void set_func_state(struct cfi_state *state) static int read_unwind_hints(struct objtool_file *file) { struct cfi_state cfi = init_cfi; - struct section *sec, *relocsec; + struct section *sec; struct unwind_hint *hint; struct instruction *insn; struct reloc *reloc; @@ -2250,8 +2197,7 @@ static int read_unwind_hints(struct objtool_file *file) if (!sec) return 0; - relocsec = sec->reloc; - if (!relocsec) { + if (!sec->rsec) { WARN("missing .rela.discard.unwind_hints section"); return -1; } @@ -2272,7 +2218,7 @@ static int read_unwind_hints(struct objtool_file *file) return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!insn) { WARN("can't find insn for unwind_hints[%d]", i); return -1; @@ -2280,6 +2226,11 @@ static int read_unwind_hints(struct objtool_file *file) insn->hint = true; + if (hint->type == UNWIND_HINT_TYPE_UNDEFINED) { + insn->cfi = &force_undefined_cfi; + continue; + } + if (hint->type == UNWIND_HINT_TYPE_SAVE) { insn->hint = false; insn->save = true; @@ -2326,16 +2277,17 @@ static int read_unwind_hints(struct objtool_file *file) static int read_noendbr_hints(struct objtool_file *file) { - struct section *sec; struct instruction *insn; + struct section *rsec; struct reloc *reloc; - sec = find_section_by_name(file->elf, ".rela.discard.noendbr"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.noendbr"); + if (!rsec) return 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { - insn = find_insn(file, reloc->sym->sec, reloc->sym->offset + reloc->addend); + for_each_reloc(rsec, reloc) { + insn = find_insn(file, reloc->sym->sec, + reloc->sym->offset + reloc_addend(reloc)); if (!insn) { WARN("bad .discard.noendbr entry"); return -1; @@ -2349,21 +2301,21 @@ static int read_noendbr_hints(struct objtool_file *file) static int read_retpoline_hints(struct objtool_file *file) { - struct section *sec; + struct section *rsec; struct instruction *insn; struct reloc *reloc; - sec = find_section_by_name(file->elf, ".rela.discard.retpoline_safe"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.retpoline_safe"); + if (!rsec) return 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", sec->name); + WARN("unexpected relocation symbol type in %s", rsec->name); return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!insn) { WARN("bad .discard.retpoline_safe entry"); return -1; @@ -2385,21 +2337,21 @@ static int read_retpoline_hints(struct objtool_file *file) static int read_instr_hints(struct objtool_file *file) { - struct section *sec; + struct section *rsec; struct instruction *insn; struct reloc *reloc; - sec = find_section_by_name(file->elf, ".rela.discard.instr_end"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.instr_end"); + if (!rsec) return 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", sec->name); + WARN("unexpected relocation symbol type in %s", rsec->name); return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!insn) { WARN("bad .discard.instr_end entry"); return -1; @@ -2408,17 +2360,17 @@ static int read_instr_hints(struct objtool_file *file) insn->instr--; } - sec = find_section_by_name(file->elf, ".rela.discard.instr_begin"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.instr_begin"); + if (!rsec) return 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", sec->name); + WARN("unexpected relocation symbol type in %s", rsec->name); return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!insn) { WARN("bad .discard.instr_begin entry"); return -1; @@ -2432,21 +2384,21 @@ static int read_instr_hints(struct objtool_file *file) static int read_validate_unret_hints(struct objtool_file *file) { - struct section *sec; + struct section *rsec; struct instruction *insn; struct reloc *reloc; - sec = find_section_by_name(file->elf, ".rela.discard.validate_unret"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.validate_unret"); + if (!rsec) return 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", sec->name); + WARN("unexpected relocation symbol type in %s", rsec->name); return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!insn) { WARN("bad .discard.instr_end entry"); return -1; @@ -2461,23 +2413,23 @@ static int read_validate_unret_hints(struct objtool_file *file) static int read_intra_function_calls(struct objtool_file *file) { struct instruction *insn; - struct section *sec; + struct section *rsec; struct reloc *reloc; - sec = find_section_by_name(file->elf, ".rela.discard.intra_function_calls"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.intra_function_calls"); + if (!rsec) return 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { unsigned long dest_off; if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", - sec->name); + rsec->name); return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!insn) { WARN("bad .discard.intra_function_call entry"); return -1; @@ -2833,6 +2785,10 @@ static int update_cfi_state(struct instruction *insn, struct cfi_reg *cfa = &cfi->cfa; struct cfi_reg *regs = cfi->regs; + /* ignore UNWIND_HINT_UNDEFINED regions */ + if (cfi->force_undefined) + return 0; + /* stack operations don't make sense with an undefined CFA */ if (cfa->base == CFI_UNDEFINED) { if (insn_func(insn)) { @@ -3369,15 +3325,15 @@ static inline bool func_uaccess_safe(struct symbol *func) static inline const char *call_dest_name(struct instruction *insn) { static char pvname[19]; - struct reloc *rel; + struct reloc *reloc; int idx; if (insn_call_dest(insn)) return insn_call_dest(insn)->name; - rel = insn_reloc(NULL, insn); - if (rel && !strcmp(rel->sym->name, "pv_ops")) { - idx = (rel->addend / sizeof(void *)); + reloc = insn_reloc(NULL, insn); + if (reloc && !strcmp(reloc->sym->name, "pv_ops")) { + idx = (reloc_addend(reloc) / sizeof(void *)); snprintf(pvname, sizeof(pvname), "pv_ops[%d]", idx); return pvname; } @@ -3388,14 +3344,14 @@ static inline const char *call_dest_name(struct instruction *insn) static bool pv_call_dest(struct objtool_file *file, struct instruction *insn) { struct symbol *target; - struct reloc *rel; + struct reloc *reloc; int idx; - rel = insn_reloc(file, insn); - if (!rel || strcmp(rel->sym->name, "pv_ops")) + reloc = insn_reloc(file, insn); + if (!reloc || strcmp(reloc->sym->name, "pv_ops")) return false; - idx = (arch_dest_reloc_offset(rel->addend) / sizeof(void *)); + idx = (arch_dest_reloc_offset(reloc_addend(reloc)) / sizeof(void *)); if (file->pv_ops[idx].clean) return true; @@ -3657,8 +3613,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, ret = validate_branch(file, func, alt->insn, state); if (ret) { - if (opts.backtrace) - BT_FUNC("(alt)", insn); + BT_INSN(insn, "(alt)"); return ret; } } @@ -3703,8 +3658,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, ret = validate_branch(file, func, insn->jump_dest, state); if (ret) { - if (opts.backtrace) - BT_FUNC("(branch)", insn); + BT_INSN(insn, "(branch)"); return ret; } } @@ -3802,8 +3756,8 @@ static int validate_unwind_hint(struct objtool_file *file, { if (insn->hint && !insn->visited && !insn->ignore) { int ret = validate_branch(file, insn_func(insn), insn, *state); - if (ret && opts.backtrace) - BT_FUNC("<=== (hint)", insn); + if (ret) + BT_INSN(insn, "<=== (hint)"); return ret; } @@ -3841,7 +3795,7 @@ static int validate_unwind_hints(struct objtool_file *file, struct section *sec) static int validate_unret(struct objtool_file *file, struct instruction *insn) { struct instruction *next, *dest; - int ret, warnings = 0; + int ret; for (;;) { next = next_insn_to_validate(file, insn); @@ -3861,8 +3815,7 @@ static int validate_unret(struct objtool_file *file, struct instruction *insn) ret = validate_unret(file, alt->insn); if (ret) { - if (opts.backtrace) - BT_FUNC("(alt)", insn); + BT_INSN(insn, "(alt)"); return ret; } } @@ -3888,10 +3841,8 @@ static int validate_unret(struct objtool_file *file, struct instruction *insn) } ret = validate_unret(file, insn->jump_dest); if (ret) { - if (opts.backtrace) { - BT_FUNC("(branch%s)", insn, - insn->type == INSN_JUMP_CONDITIONAL ? "-cond" : ""); - } + BT_INSN(insn, "(branch%s)", + insn->type == INSN_JUMP_CONDITIONAL ? "-cond" : ""); return ret; } @@ -3913,8 +3864,7 @@ static int validate_unret(struct objtool_file *file, struct instruction *insn) ret = validate_unret(file, dest); if (ret) { - if (opts.backtrace) - BT_FUNC("(call)", insn); + BT_INSN(insn, "(call)"); return ret; } /* @@ -3943,7 +3893,7 @@ static int validate_unret(struct objtool_file *file, struct instruction *insn) insn = next; } - return warnings; + return 0; } /* @@ -4178,7 +4128,6 @@ static int add_prefix_symbols(struct objtool_file *file) { struct section *sec; struct symbol *func; - int warnings = 0; for_each_sec(file, sec) { if (!(sec->sh.sh_flags & SHF_EXECINSTR)) @@ -4192,7 +4141,7 @@ static int add_prefix_symbols(struct objtool_file *file) } } - return warnings; + return 0; } static int validate_symbol(struct objtool_file *file, struct section *sec, @@ -4216,8 +4165,8 @@ static int validate_symbol(struct objtool_file *file, struct section *sec, state->uaccess = sym->uaccess_safe; ret = validate_branch(file, insn_func(insn), insn, *state); - if (ret && opts.backtrace) - BT_FUNC("<=== (sym)", insn); + if (ret) + BT_INSN(insn, "<=== (sym)"); return ret; } @@ -4333,8 +4282,8 @@ static int validate_ibt_insn(struct objtool_file *file, struct instruction *insn for (reloc = insn_reloc(file, insn); reloc; reloc = find_reloc_by_dest_range(file->elf, insn->sec, - reloc->offset + 1, - (insn->offset + insn->len) - (reloc->offset + 1))) { + reloc_offset(reloc) + 1, + (insn->offset + insn->len) - (reloc_offset(reloc) + 1))) { /* * static_call_update() references the trampoline, which @@ -4344,10 +4293,11 @@ static int validate_ibt_insn(struct objtool_file *file, struct instruction *insn continue; off = reloc->sym->offset; - if (reloc->type == R_X86_64_PC32 || reloc->type == R_X86_64_PLT32) - off += arch_dest_reloc_offset(reloc->addend); + if (reloc_type(reloc) == R_X86_64_PC32 || + reloc_type(reloc) == R_X86_64_PLT32) + off += arch_dest_reloc_offset(reloc_addend(reloc)); else - off += reloc->addend; + off += reloc_addend(reloc); dest = find_insn(file, reloc->sym->sec, off); if (!dest) @@ -4404,7 +4354,7 @@ static int validate_ibt_data_reloc(struct objtool_file *file, struct instruction *dest; dest = find_insn(file, reloc->sym->sec, - reloc->sym->offset + reloc->addend); + reloc->sym->offset + reloc_addend(reloc)); if (!dest) return 0; @@ -4417,7 +4367,7 @@ static int validate_ibt_data_reloc(struct objtool_file *file, return 0; WARN_FUNC("data relocation to !ENDBR: %s", - reloc->sec->base, reloc->offset, + reloc->sec->base, reloc_offset(reloc), offstr(dest->sec, dest->offset)); return 1; @@ -4444,7 +4394,7 @@ static int validate_ibt(struct objtool_file *file) if (sec->sh.sh_flags & SHF_EXECINSTR) continue; - if (!sec->reloc) + if (!sec->rsec) continue; /* @@ -4471,7 +4421,7 @@ static int validate_ibt(struct objtool_file *file) strstr(sec->name, "__patchable_function_entries")) continue; - list_for_each_entry(reloc, &sec->reloc->reloc_list, list) + for_each_reloc(sec->rsec, reloc) warnings += validate_ibt_data_reloc(file, reloc); } @@ -4511,9 +4461,40 @@ static int validate_sls(struct objtool_file *file) return warnings; } +static bool ignore_noreturn_call(struct instruction *insn) +{ + struct symbol *call_dest = insn_call_dest(insn); + + /* + * FIXME: hack, we need a real noreturn solution + * + * Problem is, exc_double_fault() may or may not return, depending on + * whether CONFIG_X86_ESPFIX64 is set. But objtool has no visibility + * to the kernel config. + * + * Other potential ways to fix it: + * + * - have compiler communicate __noreturn functions somehow + * - remove CONFIG_X86_ESPFIX64 + * - read the .config file + * - add a cmdline option + * - create a generic objtool annotation format (vs a bunch of custom + * formats) and annotate it + */ + if (!strcmp(call_dest->name, "exc_double_fault")) { + /* prevent further unreachable warnings for the caller */ + insn->sym->warned = 1; + return true; + } + + return false; +} + static int validate_reachable_instructions(struct objtool_file *file) { - struct instruction *insn; + struct instruction *insn, *prev_insn; + struct symbol *call_dest; + int warnings = 0; if (file->ignore_unreachables) return 0; @@ -4522,13 +4503,127 @@ static int validate_reachable_instructions(struct objtool_file *file) if (insn->visited || ignore_unreachable_insn(file, insn)) continue; + prev_insn = prev_insn_same_sec(file, insn); + if (prev_insn && prev_insn->dead_end) { + call_dest = insn_call_dest(prev_insn); + if (call_dest && !ignore_noreturn_call(prev_insn)) { + WARN_INSN(insn, "%s() is missing a __noreturn annotation", + call_dest->name); + warnings++; + continue; + } + } + WARN_INSN(insn, "unreachable instruction"); - return 1; + warnings++; + } + + return warnings; +} + +/* 'funcs' is a space-separated list of function names */ +static int disas_funcs(const char *funcs) +{ + const char *objdump_str, *cross_compile; + int size, ret; + char *cmd; + + cross_compile = getenv("CROSS_COMPILE"); + + objdump_str = "%sobjdump -wdr %s | gawk -M -v _funcs='%s' '" + "BEGIN { split(_funcs, funcs); }" + "/^$/ { func_match = 0; }" + "/<.*>:/ { " + "f = gensub(/.*<(.*)>:/, \"\\\\1\", 1);" + "for (i in funcs) {" + "if (funcs[i] == f) {" + "func_match = 1;" + "base = strtonum(\"0x\" $1);" + "break;" + "}" + "}" + "}" + "{" + "if (func_match) {" + "addr = strtonum(\"0x\" $1);" + "printf(\"%%04x \", addr - base);" + "print;" + "}" + "}' 1>&2"; + + /* fake snprintf() to calculate the size */ + size = snprintf(NULL, 0, objdump_str, cross_compile, objname, funcs) + 1; + if (size <= 0) { + WARN("objdump string size calculation failed"); + return -1; + } + + cmd = malloc(size); + + /* real snprintf() */ + snprintf(cmd, size, objdump_str, cross_compile, objname, funcs); + ret = system(cmd); + if (ret) { + WARN("disassembly failed: %d", ret); + return -1; } return 0; } +static int disas_warned_funcs(struct objtool_file *file) +{ + struct symbol *sym; + char *funcs = NULL, *tmp; + + for_each_sym(file, sym) { + if (sym->warned) { + if (!funcs) { + funcs = malloc(strlen(sym->name) + 1); + strcpy(funcs, sym->name); + } else { + tmp = malloc(strlen(funcs) + strlen(sym->name) + 2); + sprintf(tmp, "%s %s", funcs, sym->name); + free(funcs); + funcs = tmp; + } + } + } + + if (funcs) + disas_funcs(funcs); + + return 0; +} + +struct insn_chunk { + void *addr; + struct insn_chunk *next; +}; + +/* + * Reduce peak RSS usage by freeing insns memory before writing the ELF file, + * which can trigger more allocations for .debug_* sections whose data hasn't + * been read yet. + */ +static void free_insns(struct objtool_file *file) +{ + struct instruction *insn; + struct insn_chunk *chunks = NULL, *chunk; + + for_each_insn(file, insn) { + if (!insn->idx) { + chunk = malloc(sizeof(*chunk)); + chunk->addr = insn; + chunk->next = chunks; + chunks = chunk; + } + } + + for (chunk = chunks; chunk; chunk = chunk->next) + free(chunk->addr); +} + int check(struct objtool_file *file) { int ret, warnings = 0; @@ -4537,6 +4632,8 @@ int check(struct objtool_file *file) init_cfi_state(&init_cfi); init_cfi_state(&func_cfi); set_func_state(&func_cfi); + init_cfi_state(&force_undefined_cfi); + force_undefined_cfi.force_undefined = true; if (!cfi_hash_alloc(1UL << (file->elf->symbol_bits - 3))) goto out; @@ -4673,6 +4770,10 @@ int check(struct objtool_file *file) warnings += ret; } + free_insns(file); + + if (opts.verbose) + disas_warned_funcs(file); if (opts.stats) { printf("nr_insns_visited: %ld\n", nr_insns_visited); diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 500e92979a31c..d420b5d2e2b67 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -32,16 +32,52 @@ static inline u32 str_hash(const char *str) #define __elf_table(name) (elf->name##_hash) #define __elf_bits(name) (elf->name##_bits) -#define elf_hash_add(name, node, key) \ - hlist_add_head(node, &__elf_table(name)[hash_min(key, __elf_bits(name))]) +#define __elf_table_entry(name, key) \ + __elf_table(name)[hash_min(key, __elf_bits(name))] + +#define elf_hash_add(name, node, key) \ +({ \ + struct elf_hash_node *__node = node; \ + __node->next = __elf_table_entry(name, key); \ + __elf_table_entry(name, key) = __node; \ +}) + +static inline void __elf_hash_del(struct elf_hash_node *node, + struct elf_hash_node **head) +{ + struct elf_hash_node *cur, *prev; + + if (node == *head) { + *head = node->next; + return; + } + + for (prev = NULL, cur = *head; cur; prev = cur, cur = cur->next) { + if (cur == node) { + prev->next = cur->next; + break; + } + } +} -#define elf_hash_for_each_possible(name, obj, member, key) \ - hlist_for_each_entry(obj, &__elf_table(name)[hash_min(key, __elf_bits(name))], member) +#define elf_hash_del(name, node, key) \ + __elf_hash_del(node, &__elf_table_entry(name, key)) + +#define elf_list_entry(ptr, type, member) \ +({ \ + typeof(ptr) __ptr = (ptr); \ + __ptr ? container_of(__ptr, type, member) : NULL; \ +}) + +#define elf_hash_for_each_possible(name, obj, member, key) \ + for (obj = elf_list_entry(__elf_table_entry(name, key), typeof(*obj), member); \ + obj; \ + obj = elf_list_entry(obj->member.next, typeof(*(obj)), member)) #define elf_alloc_hash(name, size) \ ({ \ __elf_bits(name) = max(10, ilog2(size)); \ - __elf_table(name) = mmap(NULL, sizeof(struct hlist_head) << __elf_bits(name), \ + __elf_table(name) = mmap(NULL, sizeof(struct elf_hash_node *) << __elf_bits(name), \ PROT_READ|PROT_WRITE, \ MAP_PRIVATE|MAP_ANON, -1, 0); \ if (__elf_table(name) == (void *)-1L) { \ @@ -233,21 +269,22 @@ struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *se unsigned long offset, unsigned int len) { struct reloc *reloc, *r = NULL; + struct section *rsec; unsigned long o; - if (!sec->reloc) + rsec = sec->rsec; + if (!rsec) return NULL; - sec = sec->reloc; - for_offset_range(o, offset, offset + len) { elf_hash_for_each_possible(reloc, reloc, hash, - sec_offset_hash(sec, o)) { - if (reloc->sec != sec) + sec_offset_hash(rsec, o)) { + if (reloc->sec != rsec) continue; - if (reloc->offset >= offset && reloc->offset < offset + len) { - if (!r || reloc->offset < r->offset) + if (reloc_offset(reloc) >= offset && + reloc_offset(reloc) < offset + len) { + if (!r || reloc_offset(reloc) < reloc_offset(r)) r = reloc; } } @@ -263,6 +300,11 @@ struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, uns return find_reloc_by_dest_range(elf, sec, offset, 1); } +static bool is_dwarf_section(struct section *sec) +{ + return !strncmp(sec->name, ".debug_", 7); +} + static int read_sections(struct elf *elf) { Elf_Scn *s = NULL; @@ -293,7 +335,6 @@ static int read_sections(struct elf *elf) sec = &elf->section_data[i]; INIT_LIST_HEAD(&sec->symbol_list); - INIT_LIST_HEAD(&sec->reloc_list); s = elf_getscn(elf->elf, i); if (!s) { @@ -314,7 +355,7 @@ static int read_sections(struct elf *elf) return -1; } - if (sec->sh.sh_size != 0) { + if (sec->sh.sh_size != 0 && !is_dwarf_section(sec)) { sec->data = elf_getdata(s, NULL); if (!sec->data) { WARN_ELF("elf_getdata"); @@ -328,12 +369,12 @@ static int read_sections(struct elf *elf) } } - if (sec->sh.sh_flags & SHF_EXECINSTR) - elf->text_size += sec->sh.sh_size; - list_add_tail(&sec->list, &elf->sections); elf_hash_add(section, &sec->hash, sec->idx); elf_hash_add(section_name, &sec->name_hash, str_hash(sec->name)); + + if (is_reloc_sec(sec)) + elf->num_relocs += sec_num_entries(sec); } if (opts.stats) { @@ -356,7 +397,6 @@ static void elf_add_symbol(struct elf *elf, struct symbol *sym) struct rb_node *pnode; struct symbol *iter; - INIT_LIST_HEAD(&sym->reloc_list); INIT_LIST_HEAD(&sym->pv_target); sym->alias = sym; @@ -407,7 +447,7 @@ static int read_symbols(struct elf *elf) if (symtab_shndx) shndx_data = symtab_shndx->data; - symbols_nr = symtab->sh.sh_size / symtab->sh.sh_entsize; + symbols_nr = sec_num_entries(symtab); } else { /* * A missing symbol table is actually possible if it's an empty @@ -533,52 +573,17 @@ err: return -1; } -static struct section *elf_create_reloc_section(struct elf *elf, - struct section *base, - int reltype); - -int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, - unsigned int type, struct symbol *sym, s64 addend) -{ - struct reloc *reloc; - - if (!sec->reloc && !elf_create_reloc_section(elf, sec, SHT_RELA)) - return -1; - - reloc = malloc(sizeof(*reloc)); - if (!reloc) { - perror("malloc"); - return -1; - } - memset(reloc, 0, sizeof(*reloc)); - - reloc->sec = sec->reloc; - reloc->offset = offset; - reloc->type = type; - reloc->sym = sym; - reloc->addend = addend; - - list_add_tail(&reloc->sym_reloc_entry, &sym->reloc_list); - list_add_tail(&reloc->list, &sec->reloc->reloc_list); - elf_hash_add(reloc, &reloc->hash, reloc_hash(reloc)); - - sec->reloc->sh.sh_size += sec->reloc->sh.sh_entsize; - sec->reloc->changed = true; - - return 0; -} - /* - * Ensure that any reloc section containing references to @sym is marked - * changed such that it will get re-generated in elf_rebuild_reloc_sections() - * with the new symbol index. + * @sym's idx has changed. Update the relocs which reference it. */ -static void elf_dirty_reloc_sym(struct elf *elf, struct symbol *sym) +static int elf_update_sym_relocs(struct elf *elf, struct symbol *sym) { struct reloc *reloc; - list_for_each_entry(reloc, &sym->reloc_list, sym_reloc_entry) - reloc->sec->changed = true; + for (reloc = sym->relocs; reloc; reloc = reloc->sym_next_reloc) + set_reloc_sym(elf, reloc, reloc->sym->idx); + + return 0; } /* @@ -655,7 +660,7 @@ static int elf_update_symbol(struct elf *elf, struct section *symtab, symtab_data->d_align = 1; symtab_data->d_type = ELF_T_SYM; - symtab->changed = true; + mark_sec_changed(elf, symtab, true); symtab->truncate = true; if (t) { @@ -670,7 +675,7 @@ static int elf_update_symbol(struct elf *elf, struct section *symtab, shndx_data->d_align = sizeof(Elf32_Word); shndx_data->d_type = ELF_T_WORD; - symtab_shndx->changed = true; + mark_sec_changed(elf, symtab_shndx, true); symtab_shndx->truncate = true; } @@ -734,7 +739,7 @@ __elf_create_symbol(struct elf *elf, struct symbol *sym) return NULL; } - new_idx = symtab->sh.sh_size / symtab->sh.sh_entsize; + new_idx = sec_num_entries(symtab); if (GELF_ST_BIND(sym->sym.st_info) != STB_LOCAL) goto non_local; @@ -746,18 +751,19 @@ __elf_create_symbol(struct elf *elf, struct symbol *sym) first_non_local = symtab->sh.sh_info; old = find_symbol_by_index(elf, first_non_local); if (old) { - old->idx = new_idx; - hlist_del(&old->hash); - elf_hash_add(symbol, &old->hash, old->idx); - - elf_dirty_reloc_sym(elf, old); + elf_hash_del(symbol, &old->hash, old->idx); + elf_hash_add(symbol, &old->hash, new_idx); + old->idx = new_idx; if (elf_update_symbol(elf, symtab, symtab_shndx, old)) { WARN("elf_update_symbol move"); return NULL; } + if (elf_update_sym_relocs(elf, old)) + return NULL; + new_idx = first_non_local; } @@ -774,11 +780,11 @@ non_local: } symtab->sh.sh_size += symtab->sh.sh_entsize; - symtab->changed = true; + mark_sec_changed(elf, symtab, true); if (symtab_shndx) { symtab_shndx->sh.sh_size += sizeof(Elf32_Word); - symtab_shndx->changed = true; + mark_sec_changed(elf, symtab_shndx, true); } return sym; @@ -841,13 +847,57 @@ elf_create_prefix_symbol(struct elf *elf, struct symbol *orig, long size) return sym; } -int elf_add_reloc_to_insn(struct elf *elf, struct section *sec, - unsigned long offset, unsigned int type, - struct section *insn_sec, unsigned long insn_off) +static struct reloc *elf_init_reloc(struct elf *elf, struct section *rsec, + unsigned int reloc_idx, + unsigned long offset, struct symbol *sym, + s64 addend, unsigned int type) +{ + struct reloc *reloc, empty = { 0 }; + + if (reloc_idx >= sec_num_entries(rsec)) { + WARN("%s: bad reloc_idx %u for %s with %d relocs", + __func__, reloc_idx, rsec->name, sec_num_entries(rsec)); + return NULL; + } + + reloc = &rsec->relocs[reloc_idx]; + + if (memcmp(reloc, &empty, sizeof(empty))) { + WARN("%s: %s: reloc %d already initialized!", + __func__, rsec->name, reloc_idx); + return NULL; + } + + reloc->sec = rsec; + reloc->sym = sym; + + set_reloc_offset(elf, reloc, offset); + set_reloc_sym(elf, reloc, sym->idx); + set_reloc_type(elf, reloc, type); + set_reloc_addend(elf, reloc, addend); + + elf_hash_add(reloc, &reloc->hash, reloc_hash(reloc)); + reloc->sym_next_reloc = sym->relocs; + sym->relocs = reloc; + + return reloc; +} + +struct reloc *elf_init_reloc_text_sym(struct elf *elf, struct section *sec, + unsigned long offset, + unsigned int reloc_idx, + struct section *insn_sec, + unsigned long insn_off) { struct symbol *sym = insn_sec->sym; int addend = insn_off; + if (!(insn_sec->sh.sh_flags & SHF_EXECINSTR)) { + WARN("bad call to %s() for data symbol %s", + __func__, sym->name); + return NULL; + } + if (!sym) { /* * Due to how weak functions work, we must use section based @@ -857,108 +907,86 @@ int elf_add_reloc_to_insn(struct elf *elf, struct section *sec, */ sym = elf_create_section_symbol(elf, insn_sec); if (!sym) - return -1; + return NULL; insn_sec->sym = sym; } - return elf_add_reloc(elf, sec, offset, type, sym, addend); + return elf_init_reloc(elf, sec->rsec, reloc_idx, offset, sym, addend, + elf_text_rela_type(elf)); } -static int read_rel_reloc(struct section *sec, int i, struct reloc *reloc, unsigned int *symndx) +struct reloc *elf_init_reloc_data_sym(struct elf *elf, struct section *sec, + unsigned long offset, + unsigned int reloc_idx, + struct symbol *sym, + s64 addend) { - if (!gelf_getrel(sec->data, i, &reloc->rel)) { - WARN_ELF("gelf_getrel"); - return -1; + if (sym->sec && (sec->sh.sh_flags & SHF_EXECINSTR)) { + WARN("bad call to %s() for text symbol %s", + __func__, sym->name); + return NULL; } - reloc->type = GELF_R_TYPE(reloc->rel.r_info); - reloc->addend = 0; - reloc->offset = reloc->rel.r_offset; - *symndx = GELF_R_SYM(reloc->rel.r_info); - return 0; -} -static int read_rela_reloc(struct section *sec, int i, struct reloc *reloc, unsigned int *symndx) -{ - if (!gelf_getrela(sec->data, i, &reloc->rela)) { - WARN_ELF("gelf_getrela"); - return -1; - } - reloc->type = GELF_R_TYPE(reloc->rela.r_info); - reloc->addend = reloc->rela.r_addend; - reloc->offset = reloc->rela.r_offset; - *symndx = GELF_R_SYM(reloc->rela.r_info); - return 0; + return elf_init_reloc(elf, sec->rsec, reloc_idx, offset, sym, addend, + elf_data_rela_type(elf)); } static int read_relocs(struct elf *elf) { - unsigned long nr_reloc, max_reloc = 0, tot_reloc = 0; - struct section *sec; + unsigned long nr_reloc, max_reloc = 0; + struct section *rsec; struct reloc *reloc; unsigned int symndx; struct symbol *sym; int i; - if (!elf_alloc_hash(reloc, elf->text_size / 16)) + if (!elf_alloc_hash(reloc, elf->num_relocs)) return -1; - list_for_each_entry(sec, &elf->sections, list) { - if ((sec->sh.sh_type != SHT_RELA) && - (sec->sh.sh_type != SHT_REL)) + list_for_each_entry(rsec, &elf->sections, list) { + if (!is_reloc_sec(rsec)) continue; - sec->base = find_section_by_index(elf, sec->sh.sh_info); - if (!sec->base) { + rsec->base = find_section_by_index(elf, rsec->sh.sh_info); + if (!rsec->base) { WARN("can't find base section for reloc section %s", - sec->name); + rsec->name); return -1; } - sec->base->reloc = sec; + rsec->base->rsec = rsec; nr_reloc = 0; - sec->reloc_data = calloc(sec->sh.sh_size / sec->sh.sh_entsize, sizeof(*reloc)); - if (!sec->reloc_data) { + rsec->relocs = calloc(sec_num_entries(rsec), sizeof(*reloc)); + if (!rsec->relocs) { perror("calloc"); return -1; } - for (i = 0; i < sec->sh.sh_size / sec->sh.sh_entsize; i++) { - reloc = &sec->reloc_data[i]; - switch (sec->sh.sh_type) { - case SHT_REL: - if (read_rel_reloc(sec, i, reloc, &symndx)) - return -1; - break; - case SHT_RELA: - if (read_rela_reloc(sec, i, reloc, &symndx)) - return -1; - break; - default: return -1; - } + for (i = 0; i < sec_num_entries(rsec); i++) { + reloc = &rsec->relocs[i]; - reloc->sec = sec; - reloc->idx = i; + reloc->sec = rsec; + symndx = reloc_sym(reloc); reloc->sym = sym = find_symbol_by_index(elf, symndx); if (!reloc->sym) { WARN("can't find reloc entry symbol %d for %s", - symndx, sec->name); + symndx, rsec->name); return -1; } - list_add_tail(&reloc->sym_reloc_entry, &sym->reloc_list); - list_add_tail(&reloc->list, &sec->reloc_list); elf_hash_add(reloc, &reloc->hash, reloc_hash(reloc)); + reloc->sym_next_reloc = sym->relocs; + sym->relocs = reloc; nr_reloc++; } max_reloc = max(max_reloc, nr_reloc); - tot_reloc += nr_reloc; } if (opts.stats) { printf("max_reloc: %lu\n", max_reloc); - printf("tot_reloc: %lu\n", tot_reloc); + printf("num_relocs: %lu\n", elf->num_relocs); printf("reloc_bits: %d\n", elf->reloc_bits); } @@ -1053,13 +1081,14 @@ static int elf_add_string(struct elf *elf, struct section *strtab, char *str) len = strtab->sh.sh_size; strtab->sh.sh_size += data->d_size; - strtab->changed = true; + + mark_sec_changed(elf, strtab, true); return len; } struct section *elf_create_section(struct elf *elf, const char *name, - unsigned int sh_flags, size_t entsize, int nr) + size_t entsize, unsigned int nr) { struct section *sec, *shstrtab; size_t size = entsize * nr; @@ -1073,7 +1102,6 @@ struct section *elf_create_section(struct elf *elf, const char *name, memset(sec, 0, sizeof(*sec)); INIT_LIST_HEAD(&sec->symbol_list); - INIT_LIST_HEAD(&sec->reloc_list); s = elf_newscn(elf->elf); if (!s) { @@ -1088,7 +1116,6 @@ struct section *elf_create_section(struct elf *elf, const char *name, } sec->idx = elf_ndxscn(s); - sec->changed = true; sec->data = elf_newdata(s); if (!sec->data) { @@ -1117,7 +1144,7 @@ struct section *elf_create_section(struct elf *elf, const char *name, sec->sh.sh_entsize = entsize; sec->sh.sh_type = SHT_PROGBITS; sec->sh.sh_addralign = 1; - sec->sh.sh_flags = SHF_ALLOC | sh_flags; + sec->sh.sh_flags = SHF_ALLOC; /* Add section name to .shstrtab (or .strtab for Clang) */ shstrtab = find_section_by_name(elf, ".shstrtab"); @@ -1135,158 +1162,66 @@ struct section *elf_create_section(struct elf *elf, const char *name, elf_hash_add(section, &sec->hash, sec->idx); elf_hash_add(section_name, &sec->name_hash, str_hash(sec->name)); - elf->changed = true; + mark_sec_changed(elf, sec, true); return sec; } -static struct section *elf_create_rel_reloc_section(struct elf *elf, struct section *base) +static struct section *elf_create_rela_section(struct elf *elf, + struct section *sec, + unsigned int reloc_nr) { - char *relocname; - struct section *sec; + struct section *rsec; + char *rsec_name; - relocname = malloc(strlen(base->name) + strlen(".rel") + 1); - if (!relocname) { + rsec_name = malloc(strlen(sec->name) + strlen(".rela") + 1); + if (!rsec_name) { perror("malloc"); return NULL; } - strcpy(relocname, ".rel"); - strcat(relocname, base->name); + strcpy(rsec_name, ".rela"); + strcat(rsec_name, sec->name); - sec = elf_create_section(elf, relocname, 0, sizeof(GElf_Rel), 0); - free(relocname); - if (!sec) + rsec = elf_create_section(elf, rsec_name, elf_rela_size(elf), reloc_nr); + free(rsec_name); + if (!rsec) return NULL; - base->reloc = sec; - sec->base = base; + rsec->data->d_type = ELF_T_RELA; + rsec->sh.sh_type = SHT_RELA; + rsec->sh.sh_addralign = elf_addr_size(elf); + rsec->sh.sh_link = find_section_by_name(elf, ".symtab")->idx; + rsec->sh.sh_info = sec->idx; + rsec->sh.sh_flags = SHF_INFO_LINK; + + rsec->relocs = calloc(sec_num_entries(rsec), sizeof(struct reloc)); + if (!rsec->relocs) { + perror("calloc"); + return NULL; + } - sec->sh.sh_type = SHT_REL; - sec->sh.sh_addralign = 8; - sec->sh.sh_link = find_section_by_name(elf, ".symtab")->idx; - sec->sh.sh_info = base->idx; - sec->sh.sh_flags = SHF_INFO_LINK; + sec->rsec = rsec; + rsec->base = sec; - return sec; + return rsec; } -static struct section *elf_create_rela_reloc_section(struct elf *elf, struct section *base) +struct section *elf_create_section_pair(struct elf *elf, const char *name, + size_t entsize, unsigned int nr, + unsigned int reloc_nr) { - char *relocname; struct section *sec; - int addrsize = elf_class_addrsize(elf); - - relocname = malloc(strlen(base->name) + strlen(".rela") + 1); - if (!relocname) { - perror("malloc"); - return NULL; - } - strcpy(relocname, ".rela"); - strcat(relocname, base->name); - if (addrsize == sizeof(u32)) - sec = elf_create_section(elf, relocname, 0, sizeof(Elf32_Rela), 0); - else - sec = elf_create_section(elf, relocname, 0, sizeof(GElf_Rela), 0); - free(relocname); + sec = elf_create_section(elf, name, entsize, nr); if (!sec) return NULL; - base->reloc = sec; - sec->base = base; - - sec->sh.sh_type = SHT_RELA; - sec->sh.sh_addralign = addrsize; - sec->sh.sh_link = find_section_by_name(elf, ".symtab")->idx; - sec->sh.sh_info = base->idx; - sec->sh.sh_flags = SHF_INFO_LINK; + if (!elf_create_rela_section(elf, sec, reloc_nr)) + return NULL; return sec; } -static struct section *elf_create_reloc_section(struct elf *elf, - struct section *base, - int reltype) -{ - switch (reltype) { - case SHT_REL: return elf_create_rel_reloc_section(elf, base); - case SHT_RELA: return elf_create_rela_reloc_section(elf, base); - default: return NULL; - } -} - -static int elf_rebuild_rel_reloc_section(struct section *sec) -{ - struct reloc *reloc; - int idx = 0; - void *buf; - - /* Allocate a buffer for relocations */ - buf = malloc(sec->sh.sh_size); - if (!buf) { - perror("malloc"); - return -1; - } - - sec->data->d_buf = buf; - sec->data->d_size = sec->sh.sh_size; - sec->data->d_type = ELF_T_REL; - - idx = 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { - reloc->rel.r_offset = reloc->offset; - reloc->rel.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); - if (!gelf_update_rel(sec->data, idx, &reloc->rel)) { - WARN_ELF("gelf_update_rel"); - return -1; - } - idx++; - } - - return 0; -} - -static int elf_rebuild_rela_reloc_section(struct section *sec) -{ - struct reloc *reloc; - int idx = 0; - void *buf; - - /* Allocate a buffer for relocations with addends */ - buf = malloc(sec->sh.sh_size); - if (!buf) { - perror("malloc"); - return -1; - } - - sec->data->d_buf = buf; - sec->data->d_size = sec->sh.sh_size; - sec->data->d_type = ELF_T_RELA; - - idx = 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { - reloc->rela.r_offset = reloc->offset; - reloc->rela.r_addend = reloc->addend; - reloc->rela.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); - if (!gelf_update_rela(sec->data, idx, &reloc->rela)) { - WARN_ELF("gelf_update_rela"); - return -1; - } - idx++; - } - - return 0; -} - -static int elf_rebuild_reloc_section(struct elf *elf, struct section *sec) -{ - switch (sec->sh.sh_type) { - case SHT_REL: return elf_rebuild_rel_reloc_section(sec); - case SHT_RELA: return elf_rebuild_rela_reloc_section(sec); - default: return -1; - } -} - int elf_write_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int len, const char *insn) @@ -1299,37 +1234,8 @@ int elf_write_insn(struct elf *elf, struct section *sec, } memcpy(data->d_buf + offset, insn, len); - elf_flagdata(data, ELF_C_SET, ELF_F_DIRTY); - elf->changed = true; - - return 0; -} - -int elf_write_reloc(struct elf *elf, struct reloc *reloc) -{ - struct section *sec = reloc->sec; - - if (sec->sh.sh_type == SHT_REL) { - reloc->rel.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); - reloc->rel.r_offset = reloc->offset; - - if (!gelf_update_rel(sec->data, reloc->idx, &reloc->rel)) { - WARN_ELF("gelf_update_rel"); - return -1; - } - } else { - reloc->rela.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); - reloc->rela.r_addend = reloc->addend; - reloc->rela.r_offset = reloc->offset; - - if (!gelf_update_rela(sec->data, reloc->idx, &reloc->rela)) { - WARN_ELF("gelf_update_rela"); - return -1; - } - } - - elf->changed = true; + mark_sec_changed(elf, sec, true); return 0; } @@ -1401,25 +1307,20 @@ int elf_write(struct elf *elf) if (sec->truncate) elf_truncate_section(elf, sec); - if (sec->changed) { + if (sec_changed(sec)) { s = elf_getscn(elf->elf, sec->idx); if (!s) { WARN_ELF("elf_getscn"); return -1; } + + /* Note this also flags the section dirty */ if (!gelf_update_shdr(s, &sec->sh)) { WARN_ELF("gelf_update_shdr"); return -1; } - if (sec->base && - elf_rebuild_reloc_section(elf, sec)) { - WARN("elf_rebuild_reloc_section"); - return -1; - } - - sec->changed = false; - elf->changed = true; + mark_sec_changed(elf, sec, false); } } @@ -1439,30 +1340,14 @@ int elf_write(struct elf *elf) void elf_close(struct elf *elf) { - struct section *sec, *tmpsec; - struct symbol *sym, *tmpsym; - struct reloc *reloc, *tmpreloc; - if (elf->elf) elf_end(elf->elf); if (elf->fd > 0) close(elf->fd); - list_for_each_entry_safe(sec, tmpsec, &elf->sections, list) { - list_for_each_entry_safe(sym, tmpsym, &sec->symbol_list, list) { - list_del(&sym->list); - hash_del(&sym->hash); - } - list_for_each_entry_safe(reloc, tmpreloc, &sec->reloc_list, list) { - list_del(&reloc->list); - hash_del(&reloc->hash); - } - list_del(&sec->list); - free(sec->reloc_data); - } - - free(elf->symbol_data); - free(elf->section_data); - free(elf); + /* + * NOTE: All remaining allocations are leaked on purpose. Objtool is + * about to exit anyway. + */ } diff --git a/tools/objtool/include/objtool/builtin.h b/tools/objtool/include/objtool/builtin.h index 2a108e648b7a6..fcca6662c8b4b 100644 --- a/tools/objtool/include/objtool/builtin.h +++ b/tools/objtool/include/objtool/builtin.h @@ -37,6 +37,7 @@ struct opts { bool no_unreachable; bool sec_address; bool stats; + bool verbose; }; extern struct opts opts; diff --git a/tools/objtool/include/objtool/cfi.h b/tools/objtool/include/objtool/cfi.h index b1258e79a1b7e..c8a6bec4f6b91 100644 --- a/tools/objtool/include/objtool/cfi.h +++ b/tools/objtool/include/objtool/cfi.h @@ -36,6 +36,7 @@ struct cfi_state { bool drap; bool signal; bool end; + bool force_undefined; }; #endif /* _OBJTOOL_CFI_H */ diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index e1ca588eb69d1..c532d70864dc5 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -12,6 +12,7 @@ #include <linux/hashtable.h> #include <linux/rbtree.h> #include <linux/jhash.h> +#include <arch/elf.h> #ifdef LIBELF_USE_DEPRECATED # define elf_getshdrnum elf_getshnum @@ -25,28 +26,31 @@ #define ELF_C_READ_MMAP ELF_C_READ #endif +struct elf_hash_node { + struct elf_hash_node *next; +}; + struct section { struct list_head list; - struct hlist_node hash; - struct hlist_node name_hash; + struct elf_hash_node hash; + struct elf_hash_node name_hash; GElf_Shdr sh; struct rb_root_cached symbol_tree; struct list_head symbol_list; - struct list_head reloc_list; - struct section *base, *reloc; + struct section *base, *rsec; struct symbol *sym; Elf_Data *data; char *name; int idx; - bool changed, text, rodata, noinstr, init, truncate; - struct reloc *reloc_data; + bool _changed, text, rodata, noinstr, init, truncate; + struct reloc *relocs; }; struct symbol { struct list_head list; struct rb_node node; - struct hlist_node hash; - struct hlist_node name_hash; + struct elf_hash_node hash; + struct elf_hash_node name_hash; GElf_Sym sym; struct section *sec; char *name; @@ -61,37 +65,27 @@ struct symbol { u8 return_thunk : 1; u8 fentry : 1; u8 profiling_func : 1; + u8 warned : 1; struct list_head pv_target; - struct list_head reloc_list; + struct reloc *relocs; }; struct reloc { - struct list_head list; - struct hlist_node hash; - union { - GElf_Rela rela; - GElf_Rel rel; - }; + struct elf_hash_node hash; struct section *sec; struct symbol *sym; - struct list_head sym_reloc_entry; - unsigned long offset; - unsigned int type; - s64 addend; - int idx; - bool jump_table_start; + struct reloc *sym_next_reloc; }; -#define ELF_HASH_BITS 20 - struct elf { Elf *elf; GElf_Ehdr ehdr; int fd; bool changed; char *name; - unsigned int text_size, num_files; + unsigned int num_files; struct list_head sections; + unsigned long num_relocs; int symbol_bits; int symbol_name_bits; @@ -99,44 +93,54 @@ struct elf { int section_name_bits; int reloc_bits; - struct hlist_head *symbol_hash; - struct hlist_head *symbol_name_hash; - struct hlist_head *section_hash; - struct hlist_head *section_name_hash; - struct hlist_head *reloc_hash; + struct elf_hash_node **symbol_hash; + struct elf_hash_node **symbol_name_hash; + struct elf_hash_node **section_hash; + struct elf_hash_node **section_name_hash; + struct elf_hash_node **reloc_hash; struct section *section_data; struct symbol *symbol_data; }; -#define OFFSET_STRIDE_BITS 4 -#define OFFSET_STRIDE (1UL << OFFSET_STRIDE_BITS) -#define OFFSET_STRIDE_MASK (~(OFFSET_STRIDE - 1)) - -#define for_offset_range(_offset, _start, _end) \ - for (_offset = ((_start) & OFFSET_STRIDE_MASK); \ - _offset >= ((_start) & OFFSET_STRIDE_MASK) && \ - _offset <= ((_end) & OFFSET_STRIDE_MASK); \ - _offset += OFFSET_STRIDE) +struct elf *elf_open_read(const char *name, int flags); -static inline u32 sec_offset_hash(struct section *sec, unsigned long offset) -{ - u32 ol, oh, idx = sec->idx; +struct section *elf_create_section(struct elf *elf, const char *name, + size_t entsize, unsigned int nr); +struct section *elf_create_section_pair(struct elf *elf, const char *name, + size_t entsize, unsigned int nr, + unsigned int reloc_nr); - offset &= OFFSET_STRIDE_MASK; +struct symbol *elf_create_prefix_symbol(struct elf *elf, struct symbol *orig, long size); - ol = offset; - oh = (offset >> 16) >> 16; +struct reloc *elf_init_reloc_text_sym(struct elf *elf, struct section *sec, + unsigned long offset, + unsigned int reloc_idx, + struct section *insn_sec, + unsigned long insn_off); - __jhash_mix(ol, oh, idx); +struct reloc *elf_init_reloc_data_sym(struct elf *elf, struct section *sec, + unsigned long offset, + unsigned int reloc_idx, + struct symbol *sym, + s64 addend); - return ol; -} +int elf_write_insn(struct elf *elf, struct section *sec, + unsigned long offset, unsigned int len, + const char *insn); +int elf_write(struct elf *elf); +void elf_close(struct elf *elf); -static inline u32 reloc_hash(struct reloc *reloc) -{ - return sec_offset_hash(reloc->sec, reloc->offset); -} +struct section *find_section_by_name(const struct elf *elf, const char *name); +struct symbol *find_func_by_offset(struct section *sec, unsigned long offset); +struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset); +struct symbol *find_symbol_by_name(const struct elf *elf, const char *name); +struct symbol *find_symbol_containing(const struct section *sec, unsigned long offset); +int find_symbol_hole_containing(const struct section *sec, unsigned long offset); +struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, unsigned long offset); +struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *sec, + unsigned long offset, unsigned int len); +struct symbol *find_func_containing(struct section *sec, unsigned long offset); /* * Try to see if it's a whole archive (vmlinux.o or module). @@ -148,42 +152,147 @@ static inline bool has_multiple_files(struct elf *elf) return elf->num_files > 1; } -static inline int elf_class_addrsize(struct elf *elf) +static inline size_t elf_addr_size(struct elf *elf) { - if (elf->ehdr.e_ident[EI_CLASS] == ELFCLASS32) - return sizeof(u32); - else - return sizeof(u64); + return elf->ehdr.e_ident[EI_CLASS] == ELFCLASS32 ? 4 : 8; } -struct elf *elf_open_read(const char *name, int flags); -struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr); +static inline size_t elf_rela_size(struct elf *elf) +{ + return elf_addr_size(elf) == 4 ? sizeof(Elf32_Rela) : sizeof(Elf64_Rela); +} -struct symbol *elf_create_prefix_symbol(struct elf *elf, struct symbol *orig, long size); +static inline unsigned int elf_data_rela_type(struct elf *elf) +{ + return elf_addr_size(elf) == 4 ? R_DATA32 : R_DATA64; +} -int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, - unsigned int type, struct symbol *sym, s64 addend); -int elf_add_reloc_to_insn(struct elf *elf, struct section *sec, - unsigned long offset, unsigned int type, - struct section *insn_sec, unsigned long insn_off); +static inline unsigned int elf_text_rela_type(struct elf *elf) +{ + return elf_addr_size(elf) == 4 ? R_TEXT32 : R_TEXT64; +} -int elf_write_insn(struct elf *elf, struct section *sec, - unsigned long offset, unsigned int len, - const char *insn); -int elf_write_reloc(struct elf *elf, struct reloc *reloc); -int elf_write(struct elf *elf); -void elf_close(struct elf *elf); +static inline bool is_reloc_sec(struct section *sec) +{ + return sec->sh.sh_type == SHT_RELA || sec->sh.sh_type == SHT_REL; +} -struct section *find_section_by_name(const struct elf *elf, const char *name); -struct symbol *find_func_by_offset(struct section *sec, unsigned long offset); -struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset); -struct symbol *find_symbol_by_name(const struct elf *elf, const char *name); -struct symbol *find_symbol_containing(const struct section *sec, unsigned long offset); -int find_symbol_hole_containing(const struct section *sec, unsigned long offset); -struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, unsigned long offset); -struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *sec, - unsigned long offset, unsigned int len); -struct symbol *find_func_containing(struct section *sec, unsigned long offset); +static inline bool sec_changed(struct section *sec) +{ + return sec->_changed; +} + +static inline void mark_sec_changed(struct elf *elf, struct section *sec, + bool changed) +{ + sec->_changed = changed; + elf->changed |= changed; +} + +static inline unsigned int sec_num_entries(struct section *sec) +{ + return sec->sh.sh_size / sec->sh.sh_entsize; +} + +static inline unsigned int reloc_idx(struct reloc *reloc) +{ + return reloc - reloc->sec->relocs; +} + +static inline void *reloc_rel(struct reloc *reloc) +{ + struct section *rsec = reloc->sec; + + return rsec->data->d_buf + (reloc_idx(reloc) * rsec->sh.sh_entsize); +} + +static inline bool is_32bit_reloc(struct reloc *reloc) +{ + /* + * Elf32_Rel: 8 bytes + * Elf32_Rela: 12 bytes + * Elf64_Rel: 16 bytes + * Elf64_Rela: 24 bytes + */ + return reloc->sec->sh.sh_entsize < 16; +} + +#define __get_reloc_field(reloc, field) \ +({ \ + is_32bit_reloc(reloc) ? \ + ((Elf32_Rela *)reloc_rel(reloc))->field : \ + ((Elf64_Rela *)reloc_rel(reloc))->field; \ +}) + +#define __set_reloc_field(reloc, field, val) \ +({ \ + if (is_32bit_reloc(reloc)) \ + ((Elf32_Rela *)reloc_rel(reloc))->field = val; \ + else \ + ((Elf64_Rela *)reloc_rel(reloc))->field = val; \ +}) + +static inline u64 reloc_offset(struct reloc *reloc) +{ + return __get_reloc_field(reloc, r_offset); +} + +static inline void set_reloc_offset(struct elf *elf, struct reloc *reloc, u64 offset) +{ + __set_reloc_field(reloc, r_offset, offset); + mark_sec_changed(elf, reloc->sec, true); +} + +static inline s64 reloc_addend(struct reloc *reloc) +{ + return __get_reloc_field(reloc, r_addend); +} + +static inline void set_reloc_addend(struct elf *elf, struct reloc *reloc, s64 addend) +{ + __set_reloc_field(reloc, r_addend, addend); + mark_sec_changed(elf, reloc->sec, true); +} + + +static inline unsigned int reloc_sym(struct reloc *reloc) +{ + u64 info = __get_reloc_field(reloc, r_info); + + return is_32bit_reloc(reloc) ? + ELF32_R_SYM(info) : + ELF64_R_SYM(info); +} + +static inline unsigned int reloc_type(struct reloc *reloc) +{ + u64 info = __get_reloc_field(reloc, r_info); + + return is_32bit_reloc(reloc) ? + ELF32_R_TYPE(info) : + ELF64_R_TYPE(info); +} + +static inline void set_reloc_sym(struct elf *elf, struct reloc *reloc, unsigned int sym) +{ + u64 info = is_32bit_reloc(reloc) ? + ELF32_R_INFO(sym, reloc_type(reloc)) : + ELF64_R_INFO(sym, reloc_type(reloc)); + + __set_reloc_field(reloc, r_info, info); + + mark_sec_changed(elf, reloc->sec, true); +} +static inline void set_reloc_type(struct elf *elf, struct reloc *reloc, unsigned int type) +{ + u64 info = is_32bit_reloc(reloc) ? + ELF32_R_INFO(reloc_sym(reloc), type) : + ELF64_R_INFO(reloc_sym(reloc), type); + + __set_reloc_field(reloc, r_info, info); + + mark_sec_changed(elf, reloc->sec, true); +} #define for_each_sec(file, sec) \ list_for_each_entry(sec, &file->elf->sections, list) @@ -197,4 +306,44 @@ struct symbol *find_func_containing(struct section *sec, unsigned long offset); for_each_sec(file, __sec) \ sec_for_each_sym(__sec, sym) +#define for_each_reloc(rsec, reloc) \ + for (int __i = 0, __fake = 1; __fake; __fake = 0) \ + for (reloc = rsec->relocs; \ + __i < sec_num_entries(rsec); \ + __i++, reloc++) + +#define for_each_reloc_from(rsec, reloc) \ + for (int __i = reloc_idx(reloc); \ + __i < sec_num_entries(rsec); \ + __i++, reloc++) + +#define OFFSET_STRIDE_BITS 4 +#define OFFSET_STRIDE (1UL << OFFSET_STRIDE_BITS) +#define OFFSET_STRIDE_MASK (~(OFFSET_STRIDE - 1)) + +#define for_offset_range(_offset, _start, _end) \ + for (_offset = ((_start) & OFFSET_STRIDE_MASK); \ + _offset >= ((_start) & OFFSET_STRIDE_MASK) && \ + _offset <= ((_end) & OFFSET_STRIDE_MASK); \ + _offset += OFFSET_STRIDE) + +static inline u32 sec_offset_hash(struct section *sec, unsigned long offset) +{ + u32 ol, oh, idx = sec->idx; + + offset &= OFFSET_STRIDE_MASK; + + ol = offset; + oh = (offset >> 16) >> 16; + + __jhash_mix(ol, oh, idx); + + return ol; +} + +static inline u32 reloc_hash(struct reloc *reloc) +{ + return sec_offset_hash(reloc->sec, reloc_offset(reloc)); +} + #endif /* _OBJTOOL_ELF_H */ diff --git a/tools/objtool/include/objtool/warn.h b/tools/objtool/include/objtool/warn.h index b1c920dc9516c..ac04d3fe4dd9c 100644 --- a/tools/objtool/include/objtool/warn.h +++ b/tools/objtool/include/objtool/warn.h @@ -55,15 +55,22 @@ static inline char *offstr(struct section *sec, unsigned long offset) #define WARN_INSN(insn, format, ...) \ ({ \ - WARN_FUNC(format, insn->sec, insn->offset, ##__VA_ARGS__); \ + struct instruction *_insn = (insn); \ + if (!_insn->sym || !_insn->sym->warned) \ + WARN_FUNC(format, _insn->sec, _insn->offset, \ + ##__VA_ARGS__); \ + if (_insn->sym) \ + _insn->sym->warned = 1; \ }) -#define BT_FUNC(format, insn, ...) \ -({ \ - struct instruction *_insn = (insn); \ - char *_str = offstr(_insn->sec, _insn->offset); \ - WARN(" %s: " format, _str, ##__VA_ARGS__); \ - free(_str); \ +#define BT_INSN(insn, format, ...) \ +({ \ + if (opts.verbose || opts.backtrace) { \ + struct instruction *_insn = (insn); \ + char *_str = offstr(_insn->sec, _insn->offset); \ + WARN(" %s: " format, _str, ##__VA_ARGS__); \ + free(_str); \ + } \ }) #define WARN_ELF(format, ...) \ diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h new file mode 100644 index 0000000000000..e45c7cb1d5bcd --- /dev/null +++ b/tools/objtool/noreturns.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * This is a (sorted!) list of all known __noreturn functions in the kernel. + * It's needed for objtool to properly reverse-engineer the control flow graph. + * + * Yes, this is unfortunate. A better solution is in the works. + */ +NORETURN(__invalid_creds) +NORETURN(__kunit_abort) +NORETURN(__module_put_and_kthread_exit) +NORETURN(__reiserfs_panic) +NORETURN(__stack_chk_fail) +NORETURN(__ubsan_handle_builtin_unreachable) +NORETURN(arch_call_rest_init) +NORETURN(arch_cpu_idle_dead) +NORETURN(cpu_bringup_and_idle) +NORETURN(cpu_startup_entry) +NORETURN(do_exit) +NORETURN(do_group_exit) +NORETURN(do_task_dead) +NORETURN(ex_handler_msr_mce) +NORETURN(fortify_panic) +NORETURN(hlt_play_dead) +NORETURN(hv_ghcb_terminate) +NORETURN(kthread_complete_and_exit) +NORETURN(kthread_exit) +NORETURN(kunit_try_catch_throw) +NORETURN(machine_real_restart) +NORETURN(make_task_dead) +NORETURN(mpt_halt_firmware) +NORETURN(nmi_panic_self_stop) +NORETURN(panic) +NORETURN(panic_smp_self_stop) +NORETURN(rest_init) +NORETURN(rewind_stack_and_make_dead) +NORETURN(sev_es_terminate) +NORETURN(snp_abort) +NORETURN(start_kernel) +NORETURN(stop_this_cpu) +NORETURN(usercopy_abort) +NORETURN(x86_64_start_kernel) +NORETURN(x86_64_start_reservations) +NORETURN(xen_cpu_bringup_again) +NORETURN(xen_start_kernel) diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 48efd1e2f00d2..bae3439088671 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -118,8 +118,8 @@ static int write_orc_entry(struct elf *elf, struct section *orc_sec, orc->bp_offset = bswap_if_needed(elf, orc->bp_offset); /* populate reloc for ip */ - if (elf_add_reloc_to_insn(elf, ip_sec, idx * sizeof(int), R_X86_64_PC32, - insn_sec, insn_off)) + if (!elf_init_reloc_text_sym(elf, ip_sec, idx * sizeof(int), idx, + insn_sec, insn_off)) return -1; return 0; @@ -237,12 +237,12 @@ int orc_create(struct objtool_file *file) WARN("file already has .orc_unwind section, skipping"); return -1; } - orc_sec = elf_create_section(file->elf, ".orc_unwind", 0, + orc_sec = elf_create_section(file->elf, ".orc_unwind", sizeof(struct orc_entry), nr); if (!orc_sec) return -1; - sec = elf_create_section(file->elf, ".orc_unwind_ip", 0, sizeof(int), nr); + sec = elf_create_section_pair(file->elf, ".orc_unwind_ip", sizeof(int), nr, nr); if (!sec) return -1; diff --git a/tools/objtool/special.c b/tools/objtool/special.c index baa85c31526b3..91b1950f5bd8a 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -62,7 +62,7 @@ static void reloc_to_sec_off(struct reloc *reloc, struct section **sec, unsigned long *off) { *sec = reloc->sym->sec; - *off = reloc->sym->offset + reloc->addend; + *off = reloc->sym->offset + reloc_addend(reloc); } static int get_alt_entry(struct elf *elf, const struct special_entry *entry, @@ -126,7 +126,7 @@ static int get_alt_entry(struct elf *elf, const struct special_entry *entry, sec, offset + entry->key); return -1; } - alt->key_addend = key_reloc->addend; + alt->key_addend = reloc_addend(key_reloc); } return 0; diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 4884520f954f4..a794d9eca93d8 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -216,6 +216,12 @@ ifeq ($(call get-executable,$(BISON)),) dummy := $(error Error: $(BISON) is missing on this system, please install it) endif +ifeq ($(BUILD_BPF_SKEL),1) + ifeq ($(call get-executable,$(CLANG)),) + dummy := $(error $(CLANG) is missing on this system, please install it to be able to build with BUILD_BPF_SKEL=1) + endif +endif + ifneq ($(OUTPUT),) ifeq ($(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \>\= 371), 1) BISON_FILE_PREFIX_MAP := --file-prefix-map=$(OUTPUT)= @@ -921,6 +927,7 @@ ifndef NO_DEMANGLE EXTLIBS += -lstdc++ CFLAGS += -DHAVE_CXA_DEMANGLE_SUPPORT CXXFLAGS += -DHAVE_CXA_DEMANGLE_SUPPORT + $(call detected,CONFIG_CXX_DEMANGLE) endif ifdef BUILD_NONDISTRO ifeq ($(filter -liberty,$(EXTLIBS)),) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index a42a6a99c2bca..f48794816d82a 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -181,7 +181,6 @@ HOSTCC ?= gcc HOSTLD ?= ld HOSTAR ?= ar CLANG ?= clang -LLVM_STRIP ?= llvm-strip PKG_CONFIG = $(CROSS_COMPILE)pkg-config @@ -1057,15 +1056,33 @@ $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_ ifdef BUILD_BPF_SKEL BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool -BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) +# Get Clang's default includes on this system, as opposed to those seen by +# '-target bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +define get_sys_includes +$(shell $(1) $(2) -v -E - </dev/null 2>&1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') +endef + +ifneq ($(CROSS_COMPILE),) +CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) +endif + +CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) +BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) +TOOLS_UAPI_INCLUDE := -I$(srctree)/tools/include/uapi $(BPFTOOL): | $(SKEL_TMP_OUT) $(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \ OUTPUT=$(SKEL_TMP_OUT)/ bootstrap $(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) | $(SKEL_TMP_OUT) - $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) \ - -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ && $(LLVM_STRIP) -g $@ + $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \ + -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ $(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL) $(QUIET_GENSKEL)$(BPFTOOL) gen skeleton $< > $@ diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 77cb03e6ff875..9ca040bfb1aa7 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -78,9 +78,9 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, char path[PATH_MAX]; int err; u32 val; - u64 contextid = - evsel->core.attr.config & - (perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") | + u64 contextid = evsel->core.attr.config & + (perf_pmu__format_bits(&cs_etm_pmu->format, "contextid") | + perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") | perf_pmu__format_bits(&cs_etm_pmu->format, "contextid2")); if (!contextid) @@ -114,8 +114,7 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, * 0b00100 Maximum of 32-bit Context ID size. * All other values are reserved. */ - val = BMVAL(val, 5, 9); - if (!val || val != 0x4) { + if (BMVAL(val, 5, 9) != 0x4) { pr_err("%s: CONTEXTIDR_EL1 isn't supported, disable with %s/contextid1=0/\n", CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME); return -EINVAL; diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index 860a8b42b4b5b..a9623b128ece2 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -12,7 +12,7 @@ #include "arm-spe.h" #include "hisi-ptt.h" #include "../../../util/pmu.h" -#include "../cs-etm.h" +#include "../../../util/cs-etm.h" struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c index d730666ab95d2..80b9f6287fe2f 100644 --- a/tools/perf/arch/arm64/util/header.c +++ b/tools/perf/arch/arm64/util/header.c @@ -29,8 +29,8 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus) char path[PATH_MAX]; FILE *file; - scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR, - sysfs, cpus->map[cpu]); + scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR, + sysfs, RC_CHK_ACCESS(cpus)->map[cpu].cpu); file = fopen(path, "r"); if (!file) { diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c index fa143acb4c8d0..ef1ed645097c6 100644 --- a/tools/perf/arch/arm64/util/pmu.c +++ b/tools/perf/arch/arm64/util/pmu.c @@ -18,7 +18,7 @@ static struct perf_pmu *pmu__find_core_pmu(void) * The cpumap should cover all CPUs. Otherwise, some CPUs may * not support some events or have different event IDs. */ - if (pmu->cpus->nr != cpu__max_cpu().cpu) + if (RC_CHK_ACCESS(pmu->cpus)->nr != cpu__max_cpu().cpu) return NULL; return pmu; diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 799147658dee2..b68f47541169f 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -449,7 +449,7 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self -# 447 reserved for memfd_secret +447 common memfd_secret sys_memfd_secret sys_memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index 902e9ea9b99ed..93d3b8877baab 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -11,6 +11,7 @@ int test__intel_pt_pkt_decoder(struct test_suite *test, int subtest); int test__intel_pt_hybrid_compat(struct test_suite *test, int subtest); int test__bp_modify(struct test_suite *test, int subtest); int test__x86_sample_parsing(struct test_suite *test, int subtest); +int test__amd_ibs_via_core_pmu(struct test_suite *test, int subtest); extern struct test_suite *arch_tests[]; diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 6f4e8636c3bf7..fd02d81817186 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -5,3 +5,4 @@ perf-y += arch-tests.o perf-y += sample-parsing.o perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-test.o perf-$(CONFIG_X86_64) += bp-modify.o +perf-y += amd-ibs-via-core-pmu.o diff --git a/tools/perf/arch/x86/tests/amd-ibs-via-core-pmu.c b/tools/perf/arch/x86/tests/amd-ibs-via-core-pmu.c new file mode 100644 index 0000000000000..2902798ca5c1e --- /dev/null +++ b/tools/perf/arch/x86/tests/amd-ibs-via-core-pmu.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "arch-tests.h" +#include "linux/perf_event.h" +#include "tests/tests.h" +#include "pmu.h" +#include "pmus.h" +#include "../perf-sys.h" +#include "debug.h" + +#define NR_SUB_TESTS 5 + +static struct sub_tests { + int type; + unsigned long config; + bool valid; +} sub_tests[NR_SUB_TESTS] = { + { PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES, true }, + { PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS, false }, + { PERF_TYPE_RAW, 0x076, true }, + { PERF_TYPE_RAW, 0x0C1, true }, + { PERF_TYPE_RAW, 0x012, false }, +}; + +static int event_open(int type, unsigned long config) +{ + struct perf_event_attr attr; + + memset(&attr, 0, sizeof(struct perf_event_attr)); + attr.type = type; + attr.size = sizeof(struct perf_event_attr); + attr.config = config; + attr.disabled = 1; + attr.precise_ip = 1; + attr.sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID; + attr.sample_period = 100000; + + return sys_perf_event_open(&attr, -1, 0, -1, 0); +} + +int test__amd_ibs_via_core_pmu(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + struct perf_pmu *ibs_pmu; + int ret = TEST_OK; + int fd, i; + + if (list_empty(&pmus)) + perf_pmu__scan(NULL); + + ibs_pmu = perf_pmu__find("ibs_op"); + if (!ibs_pmu) + return TEST_SKIP; + + for (i = 0; i < NR_SUB_TESTS; i++) { + fd = event_open(sub_tests[i].type, sub_tests[i].config); + pr_debug("type: 0x%x, config: 0x%lx, fd: %d - ", sub_tests[i].type, + sub_tests[i].config, fd); + if ((sub_tests[i].valid && fd == -1) || + (!sub_tests[i].valid && fd > 0)) { + pr_debug("Fail\n"); + ret = TEST_FAIL; + } else { + pr_debug("Pass\n"); + } + + if (fd > 0) + close(fd); + } + + return ret; +} diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index aae6ea0fe52b7..b5c85ab8d92eb 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -22,6 +22,7 @@ struct test_suite suite__intel_pt = { DEFINE_SUITE("x86 bp modify", bp_modify); #endif DEFINE_SUITE("x86 Sample parsing", x86_sample_parsing); +DEFINE_SUITE("AMD IBS via core pmu", amd_ibs_via_core_pmu); struct test_suite *arch_tests[] = { #ifdef HAVE_DWARF_UNWIND_SUPPORT @@ -35,5 +36,6 @@ struct test_suite *arch_tests[] = { &suite__bp_modify, #endif &suite__x86_sample_parsing, + &suite__amd_ibs_via_core_pmu, NULL, }; diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h index 50ae8bd58296e..6188e19d31296 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h @@ -7,7 +7,3 @@ MEMCPY_FN(memcpy_orig, MEMCPY_FN(__memcpy, "x86-64-movsq", "movsq-based memcpy() in arch/x86/lib/memcpy_64.S") - -MEMCPY_FN(memcpy_erms, - "x86-64-movsb", - "movsb-based memcpy() in arch/x86/lib/memcpy_64.S") diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index 6eb45a2aa8db3..1b9fef7efcdcc 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -2,7 +2,7 @@ /* Various wrappers to make the kernel .S file build in user-space: */ -// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it +// memcpy_orig is being defined as SYM_L_LOCAL but we need it #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memcpy MEMCPY /* don't hide glibc's memcpy() */ diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h index dac6d2b7c39b2..247c72fdfb9d4 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h @@ -7,7 +7,3 @@ MEMSET_FN(memset_orig, MEMSET_FN(__memset, "x86-64-stosq", "movsq-based memset() in arch/x86/lib/memset_64.S") - -MEMSET_FN(memset_erms, - "x86-64-stosb", - "movsb-based memset() in arch/x86/lib/memset_64.S") diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S index 6f093c483842e..abd26c95f1aa0 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm.S +++ b/tools/perf/bench/mem-memset-x86-64-asm.S @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it +// memset_orig is being defined as SYM_L_LOCAL but we need it #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memset MEMSET /* don't hide glibc's memset() */ diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 810e3376c7d6c..f9906f52e4fa7 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -1175,7 +1175,7 @@ int cmd_ftrace(int argc, const char **argv) OPT_BOOLEAN('b', "use-bpf", &ftrace.target.use_bpf, "Use BPF to measure function latency"), #endif - OPT_BOOLEAN('n', "--use-nsec", &ftrace.use_nsec, + OPT_BOOLEAN('n', "use-nsec", &ftrace.use_nsec, "Use nano-second histogram"), OPT_PARENT(common_options), }; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 006f522d0e7f6..c57be48d65bb0 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3647,6 +3647,13 @@ static int process_stat_config_event(struct perf_session *session __maybe_unused union perf_event *event) { perf_event__read_stat_config(&stat_config, &event->stat_config); + + /* + * Aggregation modes are not used since post-processing scripts are + * supposed to take care of such requirements + */ + stat_config.aggr_mode = AGGR_NONE; + return 0; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index cc9fa48d636f0..b9ad32f21e575 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -667,6 +667,13 @@ static enum counter_recovery stat_handle_error(struct evsel *counter) evsel_list->core.threads->err_thread = -1; return COUNTER_RETRY; } + } else if (counter->skippable) { + if (verbose > 0) + ui__warning("skipping event %s that kernel failed to open .\n", + evsel__name(counter)); + counter->supported = false; + counter->errored = true; + return COUNTER_SKIP; } evsel__open_strerror(counter, &target, errno, msg, sizeof(msg)); @@ -1890,15 +1897,28 @@ static int add_default_attributes(void) * caused by exposing latent bugs. This is fixed properly in: * https://lore.kernel.org/lkml/bff481ba-e60a-763f-0aa0-3ee53302c480@linux.intel.com/ */ - if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid() && - metricgroup__parse_groups(evsel_list, "TopdownL1", - /*metric_no_group=*/false, - /*metric_no_merge=*/false, - /*metric_no_threshold=*/true, - stat_config.user_requested_cpu_list, - stat_config.system_wide, - &stat_config.metric_events) < 0) - return -1; + if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid()) { + struct evlist *metric_evlist = evlist__new(); + struct evsel *metric_evsel; + + if (!metric_evlist) + return -1; + + if (metricgroup__parse_groups(metric_evlist, "TopdownL1", + /*metric_no_group=*/false, + /*metric_no_merge=*/false, + /*metric_no_threshold=*/true, + stat_config.user_requested_cpu_list, + stat_config.system_wide, + &stat_config.metric_events) < 0) + return -1; + + evlist__for_each_entry(metric_evlist, metric_evsel) { + metric_evsel->skippable = true; + } + evlist__splice_list_tail(evsel_list, &metric_evlist->core.entries); + evlist__delete(metric_evlist); + } /* Platform specific attrs */ if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0) diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json index 75d80e70e5cd1..1f90475539423 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json @@ -133,6 +133,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -143,6 +144,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound_aux", "MetricThreshold": "tma_backend_bound_aux > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -153,6 +155,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -163,6 +166,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_base", "MetricThreshold": "tma_base > 0.6", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -182,6 +186,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -209,6 +214,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -255,6 +261,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -264,6 +271,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -291,6 +299,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -593,6 +602,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -611,6 +621,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -629,6 +640,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -729,6 +741,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group", "MetricName": "tma_resource_bound", "MetricThreshold": "tma_resource_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -739,6 +752,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -848,6 +862,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -858,6 +873,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -868,6 +884,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -919,6 +936,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1031,6 +1049,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1041,6 +1060,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1121,6 +1141,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1141,6 +1162,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2023,6 +2045,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2082,6 +2105,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2112,6 +2136,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2310,6 +2335,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json index 1a85d935c733c..0402adbf7d927 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json @@ -98,6 +98,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", "ScaleUnit": "100%" }, @@ -107,6 +108,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound_aux", "MetricThreshold": "tma_backend_bound_aux > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.", "ScaleUnit": "100%" }, @@ -116,6 +118,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%" }, @@ -125,6 +128,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_base", "MetricThreshold": "tma_base > 0.6", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -142,6 +146,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -166,6 +171,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -207,6 +213,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -215,6 +222,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -239,6 +247,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { @@ -499,6 +508,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -515,6 +525,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -531,6 +542,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "ScaleUnit": "100%" }, @@ -620,6 +632,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group", "MetricName": "tma_resource_bound", "MetricThreshold": "tma_resource_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count.", "ScaleUnit": "100%" }, @@ -629,6 +642,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index 51cf8560a8d38..f9e2316601e1e 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -170,6 +173,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -263,6 +267,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -272,6 +277,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -326,6 +332,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -335,6 +342,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -828,6 +836,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -858,6 +867,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -886,6 +896,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1048,6 +1059,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json index fb57c73824084..e9c46d336a8e0 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json @@ -97,6 +97,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -106,6 +107,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -116,6 +118,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -164,6 +167,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -248,6 +252,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -257,6 +262,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -311,6 +317,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -320,6 +327,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -795,6 +803,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -825,6 +834,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -853,6 +863,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1013,6 +1024,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index 65ec0c9e55d12..437b9867acb9f 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -170,6 +173,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -263,6 +267,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -272,6 +277,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -326,6 +332,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -335,6 +342,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -829,6 +837,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -869,6 +878,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -897,6 +907,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1079,6 +1090,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index 8f7dc72accd06..875c766222e36 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -354,6 +360,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1142,6 +1150,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1196,6 +1205,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1224,6 +1234,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1458,6 +1469,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index 2528418200bb8..9570a88d6d1c1 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -272,6 +278,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -281,6 +288,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -663,6 +671,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -693,6 +702,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -721,6 +731,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -874,6 +885,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index 11f152c346eb0..a522202cf6844 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -272,6 +278,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -281,6 +288,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -664,6 +672,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -704,6 +713,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -732,6 +742,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -905,6 +916,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json index f45ae3483df48..1a2154f28b7b5 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json @@ -115,6 +115,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -124,6 +125,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -141,6 +143,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -187,6 +190,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -288,6 +292,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -297,6 +302,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -369,6 +375,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -378,6 +385,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1111,6 +1119,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1164,6 +1173,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1191,6 +1201,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1360,6 +1371,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index 0f9b174dfc22a..1ef772b40e045 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -80,6 +80,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -89,6 +90,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -106,6 +108,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -152,6 +155,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -253,6 +257,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -262,6 +267,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -334,6 +340,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -343,6 +350,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1134,6 +1142,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1187,6 +1196,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1214,6 +1224,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1410,6 +1421,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json index 5247f69c13b64..11080ccffd514 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -299,6 +305,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -308,6 +315,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -724,6 +732,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -754,6 +763,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -782,6 +792,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -917,6 +928,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json index 89469b10fa304..65a46d659c0a2 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -299,6 +305,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -308,6 +315,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -725,6 +733,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -765,6 +774,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -793,6 +803,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -948,6 +959,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json index e8f4e5c01c9fb..66a6f657bd6f7 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -76,6 +76,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -85,6 +86,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -95,6 +97,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -114,6 +117,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -160,6 +164,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, @@ -169,6 +174,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -205,6 +211,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -214,6 +221,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -412,6 +420,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -422,6 +431,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -450,6 +460,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -487,6 +498,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json index 4a99fe515f4b0..4b8bc19392a44 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -76,6 +76,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -85,6 +86,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -95,6 +97,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -114,6 +117,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -160,6 +164,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, @@ -169,6 +174,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -205,6 +211,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -214,6 +221,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -411,6 +419,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -421,6 +430,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -449,6 +459,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -486,6 +497,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index 126300b7ae777..620fc5bd2217d 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -87,6 +87,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -96,6 +97,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -105,6 +107,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -151,6 +154,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -252,6 +256,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -261,6 +266,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -351,6 +357,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -369,6 +376,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%" }, @@ -1216,6 +1224,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1269,6 +1278,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1304,6 +1314,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1509,6 +1520,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index a6d212b349f5d..21ef6c9be8167 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -345,6 +351,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -363,6 +370,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1065,6 +1073,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1110,6 +1119,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1138,6 +1148,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1343,6 +1354,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index fa2f7f126a305..eb6f12c0343d5 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -354,6 +360,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1123,6 +1131,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1177,6 +1186,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1205,6 +1215,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1429,6 +1440,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json index 4c80d6be6cf1d..b442ed4acfbb4 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json @@ -109,6 +109,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -118,6 +119,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -135,6 +137,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -181,6 +184,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -282,6 +286,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -291,6 +296,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -363,6 +369,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1125,6 +1133,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1178,6 +1187,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1205,6 +1215,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1374,6 +1385,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index ca99b9cfe4ada..f57a8f2740257 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -52,7 +52,8 @@ _json_event_attributes = [ # Attributes that are in pmu_metric rather than pmu_event. _json_metric_attributes = [ 'metric_name', 'metric_group', 'metric_expr', 'metric_threshold', 'desc', - 'long_desc', 'unit', 'compat', 'aggr_mode', 'event_grouping' + 'long_desc', 'unit', 'compat', 'metricgroup_no_group', 'aggr_mode', + 'event_grouping' ] # Attributes that are bools or enum int values, encoded as '0', '1',... _json_enum_attributes = ['aggr_mode', 'deprecated', 'event_grouping', 'perpkg'] @@ -303,6 +304,7 @@ class JsonEvent: self.deprecated = jd.get('Deprecated') self.metric_name = jd.get('MetricName') self.metric_group = jd.get('MetricGroup') + self.metricgroup_no_group = jd.get('MetricgroupNoGroup') self.event_grouping = convert_metric_constraint(jd.get('MetricConstraint')) self.metric_expr = None if 'MetricExpr' in jd: diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index b7dff8f1021fd..80349685cf4d8 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -59,6 +59,7 @@ struct pmu_metric { const char *compat; const char *desc; const char *long_desc; + const char *metricgroup_no_group; enum aggr_mode_class aggr_mode; enum metric_event_groups event_grouping; }; diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index ccfef861e9315..e890c261ad269 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -152,7 +152,7 @@ def parse_version(version): # - expected values assignments class Test(object): def __init__(self, path, options): - parser = configparser.SafeConfigParser() + parser = configparser.ConfigParser() parser.read(path) log.warning("running '%s'" % path) @@ -247,7 +247,7 @@ class Test(object): return True def load_events(self, path, events): - parser_event = configparser.SafeConfigParser() + parser_event = configparser.ConfigParser() parser_event.read(path) # The event record section header contains 'event' word, @@ -261,7 +261,7 @@ class Test(object): # Read parent event if there's any if (':' in section): base = section[section.index(':') + 1:] - parser_base = configparser.SafeConfigParser() + parser_base = configparser.ConfigParser() parser_base.read(self.test_dir + '/' + base) base_items = parser_base.items('event') diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat index a21fb65bc012e..fccd8ec4d1b02 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -16,7 +16,7 @@ pinned=0 exclusive=0 exclude_user=0 exclude_kernel=0|1 -exclude_hv=0 +exclude_hv=0|1 exclude_idle=0 mmap=0 comm=0 diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default index d8ea6a88163fb..a1e2da0a9a6dd 100644 --- a/tools/perf/tests/attr/test-stat-default +++ b/tools/perf/tests/attr/test-stat-default @@ -40,7 +40,6 @@ fd=6 type=0 config=7 optional=1 - # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND [event7:base-stat] fd=7 @@ -89,79 +88,98 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1 index b656ab93c5bf9..1c52cb05c900d 100644 --- a/tools/perf/tests/attr/test-stat-detailed-1 +++ b/tools/perf/tests/attr/test-stat-detailed-1 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2 index 97625090a1c4c..7e961d24a885a 100644 --- a/tools/perf/tests/attr/test-stat-detailed-2 +++ b/tools/perf/tests/attr/test-stat-detailed-2 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 @@ -211,8 +230,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event24:base-stat] -fd=24 +[event29:base-stat] +fd=29 type=3 config=1 optional=1 @@ -221,8 +240,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event25:base-stat] -fd=25 +[event30:base-stat] +fd=30 type=3 config=65537 optional=1 @@ -231,8 +250,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event26:base-stat] -fd=26 +[event31:base-stat] +fd=31 type=3 config=3 optional=1 @@ -241,8 +260,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event27:base-stat] -fd=27 +[event32:base-stat] +fd=32 type=3 config=65539 optional=1 @@ -251,8 +270,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event28:base-stat] -fd=28 +[event33:base-stat] +fd=33 type=3 config=4 optional=1 @@ -261,8 +280,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event29:base-stat] -fd=29 +[event34:base-stat] +fd=34 type=3 config=65540 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3 index d555042e3fbfe..e50535f45977c 100644 --- a/tools/perf/tests/attr/test-stat-detailed-3 +++ b/tools/perf/tests/attr/test-stat-detailed-3 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 @@ -211,8 +230,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event24:base-stat] -fd=24 +[event29:base-stat] +fd=29 type=3 config=1 optional=1 @@ -221,8 +240,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event25:base-stat] -fd=25 +[event30:base-stat] +fd=30 type=3 config=65537 optional=1 @@ -231,8 +250,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event26:base-stat] -fd=26 +[event31:base-stat] +fd=31 type=3 config=3 optional=1 @@ -241,8 +260,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event27:base-stat] -fd=27 +[event32:base-stat] +fd=32 type=3 config=65539 optional=1 @@ -251,8 +270,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event28:base-stat] -fd=28 +[event33:base-stat] +fd=33 type=3 config=4 optional=1 @@ -261,8 +280,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event29:base-stat] -fd=29 +[event34:base-stat] +fd=34 type=3 config=65540 optional=1 @@ -271,8 +290,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event30:base-stat] -fd=30 +[event35:base-stat] +fd=35 type=3 config=512 optional=1 @@ -281,8 +300,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event31:base-stat] -fd=31 +[event36:base-stat] +fd=36 type=3 config=66048 optional=1 diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index cbf0e0c749066..733ead151c636 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -120,7 +120,8 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u p = "FOO/0"; ret = expr__parse(&val, ctx, p); - TEST_ASSERT_VAL("division by zero", ret == -1); + TEST_ASSERT_VAL("division by zero", ret == 0); + TEST_ASSERT_VAL("division by zero", isnan(val)); p = "BAR/"; ret = expr__parse(&val, ctx, p); diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 1185b79e62748..c05148ea400cb 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -38,6 +38,7 @@ static void load_runtime_stat(struct evlist *evlist, struct value *vals) evlist__alloc_aggr_stats(evlist, 1); evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); + evsel->supported = true; evsel->stats->aggr->counts.val = count; if (evsel__name_is(evsel, "duration_time")) update_stats(&walltime_nsecs_stats, count); diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh index 2c1d3f7049951..b154fbb15d544 100755 --- a/tools/perf/tests/shell/stat.sh +++ b/tools/perf/tests/shell/stat.sh @@ -28,6 +28,18 @@ test_stat_record_report() { echo "stat record and report test [Success]" } +test_stat_record_script() { + echo "stat record and script test" + if ! perf stat record -o - true | perf script -i - 2>&1 | \ + grep -E -q "CPU[[:space:]]+THREAD[[:space:]]+VAL[[:space:]]+ENA[[:space:]]+RUN[[:space:]]+TIME[[:space:]]+EVENT" + then + echo "stat record and script test [Failed]" + err=1 + return + fi + echo "stat record and script test [Success]" +} + test_stat_repeat_weak_groups() { echo "stat repeat weak groups test" if ! perf stat -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' \ @@ -93,6 +105,7 @@ test_topdown_weak_groups() { test_default_stat test_stat_record_report +test_stat_record_script test_stat_repeat_weak_groups test_topdown_groups test_topdown_weak_groups diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index 4ddb17cb83c5f..3a8b9bffa0225 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -506,6 +506,13 @@ test_sample() echo "perf record failed with --aux-sample" return 1 fi + # Check with event with PMU name + if perf_record_no_decode -o "${perfdatafile}" -e br_misp_retired.all_branches:u uname ; then + if ! perf_record_no_decode -o "${perfdatafile}" -e '{intel_pt//,br_misp_retired.all_branches/aux-sample-size=8192/}:u' uname ; then + echo "perf record failed with --aux-sample-size" + return 1 + fi + fi echo OK return 0 } diff --git a/tools/perf/tests/shell/test_java_symbol.sh b/tools/perf/tests/shell/test_java_symbol.sh index 90cea88119268..499539d1c4794 100755 --- a/tools/perf/tests/shell/test_java_symbol.sh +++ b/tools/perf/tests/shell/test_java_symbol.sh @@ -56,7 +56,7 @@ if [ $? -ne 0 ]; then exit 1 fi -if ! perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then +if ! DEBUGINFOD_URLS='' perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then echo "Fail to inject samples" exit 1 fi diff --git a/tools/perf/trace/beauty/arch_prctl.c b/tools/perf/trace/beauty/arch_prctl.c index fe022ca67e609..a211348d32044 100644 --- a/tools/perf/trace/beauty/arch_prctl.c +++ b/tools/perf/trace/beauty/arch_prctl.c @@ -12,10 +12,12 @@ static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_1, "ARCH_", x86_arch_prctl_codes_1_offset); static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_2, "ARCH_", x86_arch_prctl_codes_2_offset); +static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_3, "ARCH_", x86_arch_prctl_codes_3_offset); static struct strarray *x86_arch_prctl_codes[] = { &strarray__x86_arch_prctl_codes_1, &strarray__x86_arch_prctl_codes_2, + &strarray__x86_arch_prctl_codes_3, }; static DEFINE_STRARRAYS(x86_arch_prctl_codes); diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 13c3a237b9c93..3bef212a24d77 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -318,7 +318,6 @@ struct ucred { #define MSG_MORE 0x8000 /* Sender will send more */ #define MSG_WAITFORONE 0x10000 /* recvmmsg(): block until 1+ packets avail */ #define MSG_SENDPAGE_NOPOLICY 0x10000 /* sendpage() internal : do no apply policy */ -#define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */ #define MSG_BATCH 0x40000 /* sendmmsg(): more messages coming */ #define MSG_EOF MSG_FIN #define MSG_NO_SHARED_FRAGS 0x80000 /* sendpage() internal : page frags are not shared */ diff --git a/tools/perf/trace/beauty/msg_flags.c b/tools/perf/trace/beauty/msg_flags.c index ea68db08b8e71..aa9934020232e 100644 --- a/tools/perf/trace/beauty/msg_flags.c +++ b/tools/perf/trace/beauty/msg_flags.c @@ -8,8 +8,8 @@ #ifndef MSG_WAITFORONE #define MSG_WAITFORONE 0x10000 #endif -#ifndef MSG_SENDPAGE_NOTLAST -#define MSG_SENDPAGE_NOTLAST 0x20000 +#ifndef MSG_SPLICE_PAGES +#define MSG_SPLICE_PAGES 0x8000000 #endif #ifndef MSG_FASTOPEN #define MSG_FASTOPEN 0x20000000 @@ -50,7 +50,7 @@ static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size, P_MSG_FLAG(NOSIGNAL); P_MSG_FLAG(MORE); P_MSG_FLAG(WAITFORONE); - P_MSG_FLAG(SENDPAGE_NOTLAST); + P_MSG_FLAG(SPLICE_PAGES); P_MSG_FLAG(FASTOPEN); P_MSG_FLAG(CMSG_CLOEXEC); #undef P_MSG_FLAG diff --git a/tools/perf/trace/beauty/x86_arch_prctl.sh b/tools/perf/trace/beauty/x86_arch_prctl.sh index 57fa6aaffe700..fd5c740512c52 100755 --- a/tools/perf/trace/beauty/x86_arch_prctl.sh +++ b/tools/perf/trace/beauty/x86_arch_prctl.sh @@ -24,3 +24,4 @@ print_range () { print_range 1 0x1 0x1001 print_range 2 0x2 0x2001 +print_range 3 0x4 0x4001 diff --git a/tools/perf/util/Build b/tools/perf/util/Build index bd18fe5f27195..f9df1df1eec03 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -214,7 +214,7 @@ perf-$(CONFIG_ZSTD) += zstd.o perf-$(CONFIG_LIBCAP) += cap.o -perf-y += demangle-cxx.o +perf-$(CONFIG_CXX_DEMANGLE) += demangle-cxx.o perf-y += demangle-ocaml.o perf-y += demangle-java.o perf-y += demangle-rust.o diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c index f3918f290df50..ba807071d3c15 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -51,7 +51,7 @@ static u64 arm_spe_calc_ip(int index, u64 payload) * (bits [63:56]) is assigned as top-byte tag; so we only can * retrieve address value from bits [55:0]. * - * According to Documentation/arm64/memory.rst, if detects the + * According to Documentation/arch/arm64/memory.rst, if detects the * specific pattern in bits [55:52] of payload which falls in * the kernel space, should fixup the top byte and this allows * perf tool to parse DSO symbol for data address correctly. diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 8d3cfbb3cc65b..1d48226ae75d4 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -416,6 +416,8 @@ int contention_end(u64 *ctx) return 0; } +struct rq {}; + extern struct rq runqueues __ksym; struct rq___old { diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c index cffe493af1ed5..fb94f52806266 100644 --- a/tools/perf/util/bpf_skel/sample_filter.bpf.c +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -25,7 +25,7 @@ struct perf_sample_data___new { } __attribute__((preserve_access_index)); /* new kernel perf_mem_data_src definition */ -union perf_mem_data_src__new { +union perf_mem_data_src___new { __u64 val; struct { __u64 mem_op:5, /* type of opcode */ @@ -108,7 +108,7 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, if (entry->part == 7) return kctx->data->data_src.mem_blk; if (entry->part == 8) { - union perf_mem_data_src__new *data = (void *)&kctx->data->data_src; + union perf_mem_data_src___new *data = (void *)&kctx->data->data_src; if (bpf_core_field_exists(data->mem_hops)) return data->mem_hops; diff --git a/tools/perf/util/bpf_skel/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux.h index 449b1ea91fc48..c7ed51b0c1ef9 100644 --- a/tools/perf/util/bpf_skel/vmlinux.h +++ b/tools/perf/util/bpf_skel/vmlinux.h @@ -1,6 +1,7 @@ #ifndef __VMLINUX_H #define __VMLINUX_H +#include <linux/stddef.h> // for define __always_inline #include <linux/bpf.h> #include <linux/types.h> #include <linux/perf_event.h> diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 70cac0375b340..ecca40787ac9a 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -227,6 +227,19 @@ struct cs_etm_packet_queue { #define INFO_HEADER_SIZE (sizeof(((struct perf_record_auxtrace_info *)0)->type) + \ sizeof(((struct perf_record_auxtrace_info *)0)->reserved__)) +/* CoreSight trace ID is currently the bottom 7 bits of the value */ +#define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) + +/* + * perf record will set the legacy meta data values as unused initially. + * This allows perf report to manage the decoders created when dynamic + * allocation in operation. + */ +#define CORESIGHT_TRACE_ID_UNUSED_FLAG BIT(31) + +/* Value to set for unused trace ID values */ +#define CORESIGHT_TRACE_ID_UNUSED_VAL 0x7F + int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session); struct perf_event_attr *cs_etm_get_default_config(struct perf_pmu *pmu); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 356c07f03be6b..c2dbb5647e754 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -282,6 +282,7 @@ void evsel__init(struct evsel *evsel, evsel->bpf_fd = -1; INIT_LIST_HEAD(&evsel->config_terms); INIT_LIST_HEAD(&evsel->bpf_counter_list); + INIT_LIST_HEAD(&evsel->bpf_filters); perf_evsel__object.init(evsel); evsel->sample_size = __evsel__sample_size(attr->sample_type); evsel__calc_id_pos(evsel); @@ -290,6 +291,7 @@ void evsel__init(struct evsel *evsel, evsel->per_pkg_mask = NULL; evsel->collect_stat = false; evsel->pmu_name = NULL; + evsel->skippable = false; } struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx) @@ -828,26 +830,26 @@ bool evsel__name_is(struct evsel *evsel, const char *name) const char *evsel__group_pmu_name(const struct evsel *evsel) { - const struct evsel *leader; + struct evsel *leader = evsel__leader(evsel); + struct evsel *pos; - /* If the pmu_name is set use it. pmu_name isn't set for CPU and software events. */ - if (evsel->pmu_name) - return evsel->pmu_name; /* * Software events may be in a group with other uncore PMU events. Use - * the pmu_name of the group leader to avoid breaking the software event - * out of the group. + * the pmu_name of the first non-software event to avoid breaking the + * software event out of the group. * * Aux event leaders, like intel_pt, expect a group with events from * other PMUs, so substitute the AUX event's PMU in this case. */ - leader = evsel__leader(evsel); - if ((evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) && - leader->pmu_name) { - return leader->pmu_name; + if (evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) { + /* Starting with the leader, find the first event with a named PMU. */ + for_each_group_evsel(pos, leader) { + if (pos->pmu_name) + return pos->pmu_name; + } } - return "cpu"; + return evsel->pmu_name ?: "cpu"; } const char *evsel__metric_id(const struct evsel *evsel) @@ -1725,9 +1727,13 @@ static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread) return -1; fd = FD(leader, cpu_map_idx, thread); - BUG_ON(fd == -1); + BUG_ON(fd == -1 && !leader->skippable); - return fd; + /* + * When the leader has been skipped, return -2 to distinguish from no + * group leader case. + */ + return fd == -1 ? -2 : fd; } static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int thread_idx) @@ -2109,6 +2115,12 @@ retry_open: group_fd = get_group_fd(evsel, idx, thread); + if (group_fd == -2) { + pr_debug("broken group leader for %s\n", evsel->name); + err = -EINVAL; + goto out_close; + } + test_attr__ready(); /* Debug message used by test scripts */ diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d575390d80bc3..0f54f28a69c25 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -95,6 +95,7 @@ struct evsel { bool weak_group; bool bpf_counter; bool use_config_name; + bool skippable; int bpf_fd; struct bpf_object *bpf_obj; struct list_head config_terms; @@ -150,10 +151,8 @@ struct evsel { */ struct bpf_counter_ops *bpf_counter_ops; - union { - struct list_head bpf_counter_list; /* for perf-stat -b */ - struct list_head bpf_filters; /* for perf-record --filter */ - }; + struct list_head bpf_counter_list; /* for perf-stat -b */ + struct list_head bpf_filters; /* for perf-record --filter */ /* for perf-stat --use-bpf */ int bperf_leader_prog_fd; diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 250e444bf0325..4ce931cccb633 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -225,7 +225,11 @@ expr: NUMBER { if (fpclassify($3.val) == FP_ZERO) { pr_debug("division by zero\n"); - YYABORT; + assert($3.ids == NULL); + if (compute_ids) + ids__free($1.ids); + $$.val = NAN; + $$.ids = NULL; } else if (!compute_ids || (is_const($1.val) && is_const($3.val))) { assert($1.ids == NULL); assert($3.ids == NULL); diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index c566c68593026..5e9c657dd3f7a 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -1144,12 +1144,12 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm, struct metricgroup__add_metric_data *data = vdata; int ret = 0; - if (pm->metric_expr && - (match_metric(pm->metric_group, data->metric_name) || - match_metric(pm->metric_name, data->metric_name))) { + if (pm->metric_expr && match_pm_metric(pm, data->metric_name)) { + bool metric_no_group = data->metric_no_group || + match_metric(data->metric_name, pm->metricgroup_no_group); data->has_match = true; - ret = add_metric(data->list, pm, data->modifier, data->metric_no_group, + ret = add_metric(data->list, pm, data->modifier, metric_no_group, data->metric_no_threshold, data->user_requested_cpu_list, data->system_wide, /*root_metric=*/NULL, /*visited_metrics=*/NULL, table); @@ -1672,7 +1672,7 @@ static int metricgroup__topdown_max_level_callback(const struct pmu_metric *pm, { unsigned int *max_level = data; unsigned int level; - const char *p = strstr(pm->metric_group, "TopdownL"); + const char *p = strstr(pm->metric_group ?: "", "TopdownL"); if (!p || p[8] == '\0') return 0; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index d71019dcd6142..34ba840ae19a2 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2140,25 +2140,32 @@ static int evlist__cmp(void *state, const struct list_head *l, const struct list int *leader_idx = state; int lhs_leader_idx = *leader_idx, rhs_leader_idx = *leader_idx, ret; const char *lhs_pmu_name, *rhs_pmu_name; + bool lhs_has_group = false, rhs_has_group = false; /* * First sort by grouping/leader. Read the leader idx only if the evsel * is part of a group, as -1 indicates no group. */ - if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) + if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) { + lhs_has_group = true; lhs_leader_idx = lhs_core->leader->idx; - if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) + } + if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) { + rhs_has_group = true; rhs_leader_idx = rhs_core->leader->idx; + } if (lhs_leader_idx != rhs_leader_idx) return lhs_leader_idx - rhs_leader_idx; - /* Group by PMU. Groups can't span PMUs. */ - lhs_pmu_name = evsel__group_pmu_name(lhs); - rhs_pmu_name = evsel__group_pmu_name(rhs); - ret = strcmp(lhs_pmu_name, rhs_pmu_name); - if (ret) - return ret; + /* Group by PMU if there is a group. Groups can't span PMUs. */ + if (lhs_has_group && rhs_has_group) { + lhs_pmu_name = evsel__group_pmu_name(lhs); + rhs_pmu_name = evsel__group_pmu_name(rhs); + ret = strcmp(lhs_pmu_name, rhs_pmu_name); + if (ret) + return ret; + } /* Architecture specific sorting. */ return arch_evlist__cmp(lhs, rhs); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 73b2ff2ddf298..bf5a6c14dfcdb 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -431,7 +431,7 @@ static void print_metric_json(struct perf_stat_config *config __maybe_unused, struct outstate *os = ctx; FILE *out = os->fh; - fprintf(out, "\"metric-value\" : %f, ", val); + fprintf(out, "\"metric-value\" : \"%f\", ", val); fprintf(out, "\"metric-unit\" : \"%s\"", unit); if (!config->metric_only) fprintf(out, "}"); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index eeccab6751d7c..1566a206ba42c 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -403,12 +403,25 @@ static int prepare_metric(struct evsel **metric_events, if (!aggr) break; - /* - * If an event was scaled during stat gathering, reverse - * the scale before computing the metric. - */ - val = aggr->counts.val * (1.0 / metric_events[i]->scale); - source_count = evsel__source_count(metric_events[i]); + if (!metric_events[i]->supported) { + /* + * Not supported events will have a count of 0, + * which can be confusing in a + * metric. Explicitly set the value to NAN. Not + * counted events (enable time of 0) are read as + * 0. + */ + val = NAN; + source_count = 0; + } else { + /* + * If an event was scaled during stat gathering, + * reverse the scale before computing the + * metric. + */ + val = aggr->counts.val * (1.0 / metric_events[i]->scale); + source_count = evsel__source_count(metric_events[i]); + } } n = strdup(evsel__metric_id(metric_events[i])); if (!n) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index b2ed9cc522655..63882a4db5c74 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -31,6 +31,13 @@ #include <bfd.h> #endif +#if defined(HAVE_LIBBFD_SUPPORT) || defined(HAVE_CPLUS_DEMANGLE_SUPPORT) +#ifndef DMGL_PARAMS +#define DMGL_PARAMS (1 << 0) /* Include function args */ +#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ +#endif +#endif + #ifndef EM_AARCH64 #define EM_AARCH64 183 /* ARM 64 bit */ #endif @@ -271,6 +278,26 @@ static bool want_demangle(bool is_kernel_sym) return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle; } +/* + * Demangle C++ function signature, typically replaced by demangle-cxx.cpp + * version. + */ +__weak char *cxx_demangle_sym(const char *str __maybe_unused, bool params __maybe_unused, + bool modifiers __maybe_unused) +{ +#ifdef HAVE_LIBBFD_SUPPORT + int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); + + return bfd_demangle(NULL, str, flags); +#elif defined(HAVE_CPLUS_DEMANGLE_SUPPORT) + int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); + + return cplus_demangle(str, flags); +#else + return NULL; +#endif +} + static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) { char *demangled = NULL; diff --git a/tools/power/cpupower/lib/powercap.c b/tools/power/cpupower/lib/powercap.c index 0ce29ee4c2e46..a7a59c6bacda8 100644 --- a/tools/power/cpupower/lib/powercap.c +++ b/tools/power/cpupower/lib/powercap.c @@ -40,25 +40,34 @@ static int sysfs_get_enabled(char *path, int *mode) { int fd; char yes_no; + int ret = 0; *mode = 0; fd = open(path, O_RDONLY); - if (fd == -1) - return -1; + if (fd == -1) { + ret = -1; + goto out; + } if (read(fd, &yes_no, 1) != 1) { - close(fd); - return -1; + ret = -1; + goto out_close; } if (yes_no == '1') { *mode = 1; - return 0; + goto out_close; } else if (yes_no == '0') { - return 0; + goto out_close; + } else { + ret = -1; + goto out_close; } - return -1; +out_close: + close(fd); +out: + return ret; } int powercap_get_enabled(int *mode) diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c index e7d48cb563c0e..ae6af354a81db 100644 --- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c @@ -70,8 +70,8 @@ static int max_freq_mode; */ static unsigned long max_frequency; -static unsigned long long tsc_at_measure_start; -static unsigned long long tsc_at_measure_end; +static unsigned long long *tsc_at_measure_start; +static unsigned long long *tsc_at_measure_end; static unsigned long long *mperf_previous_count; static unsigned long long *aperf_previous_count; static unsigned long long *mperf_current_count; @@ -169,7 +169,7 @@ static int mperf_get_count_percent(unsigned int id, double *percent, aperf_diff = aperf_current_count[cpu] - aperf_previous_count[cpu]; if (max_freq_mode == MAX_FREQ_TSC_REF) { - tsc_diff = tsc_at_measure_end - tsc_at_measure_start; + tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; *percent = 100.0 * mperf_diff / tsc_diff; dprint("%s: TSC Ref - mperf_diff: %llu, tsc_diff: %llu\n", mperf_cstates[id].name, mperf_diff, tsc_diff); @@ -206,7 +206,7 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, if (max_freq_mode == MAX_FREQ_TSC_REF) { /* Calculate max_freq from TSC count */ - tsc_diff = tsc_at_measure_end - tsc_at_measure_start; + tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; time_diff = timespec_diff_us(time_start, time_end); max_frequency = tsc_diff / time_diff; } @@ -225,33 +225,27 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, static int mperf_start(void) { int cpu; - unsigned long long dbg; clock_gettime(CLOCK_REALTIME, &time_start); - mperf_get_tsc(&tsc_at_measure_start); - for (cpu = 0; cpu < cpu_count; cpu++) + for (cpu = 0; cpu < cpu_count; cpu++) { + mperf_get_tsc(&tsc_at_measure_start[cpu]); mperf_init_stats(cpu); + } - mperf_get_tsc(&dbg); - dprint("TSC diff: %llu\n", dbg - tsc_at_measure_start); return 0; } static int mperf_stop(void) { - unsigned long long dbg; int cpu; - for (cpu = 0; cpu < cpu_count; cpu++) + for (cpu = 0; cpu < cpu_count; cpu++) { mperf_measure_stats(cpu); + mperf_get_tsc(&tsc_at_measure_end[cpu]); + } - mperf_get_tsc(&tsc_at_measure_end); clock_gettime(CLOCK_REALTIME, &time_end); - - mperf_get_tsc(&dbg); - dprint("TSC diff: %llu\n", dbg - tsc_at_measure_end); - return 0; } @@ -353,7 +347,8 @@ struct cpuidle_monitor *mperf_register(void) aperf_previous_count = calloc(cpu_count, sizeof(unsigned long long)); mperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); aperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); - + tsc_at_measure_start = calloc(cpu_count, sizeof(unsigned long long)); + tsc_at_measure_end = calloc(cpu_count, sizeof(unsigned long long)); mperf_monitor.name_len = strlen(mperf_monitor.name); return &mperf_monitor; } @@ -364,6 +359,8 @@ void mperf_unregister(void) free(aperf_previous_count); free(mperf_current_count); free(aperf_current_count); + free(tsc_at_measure_start); + free(tsc_at_measure_end); free(is_valid); } diff --git a/tools/spi/spidev_test.c b/tools/spi/spidev_test.c index b0ca44c70e83e..9179942d7f15c 100644 --- a/tools/spi/spidev_test.c +++ b/tools/spi/spidev_test.c @@ -172,28 +172,37 @@ static void transfer(int fd, uint8_t const *tx, uint8_t const *rx, size_t len) static void print_usage(const char *prog) { - printf("Usage: %s [-DsbdlHOLC3vpNR24SI]\n", prog); - puts(" -D --device device to use (default /dev/spidev1.1)\n" - " -s --speed max speed (Hz)\n" - " -d --delay delay (usec)\n" - " -b --bpw bits per word\n" - " -i --input input data from a file (e.g. \"test.bin\")\n" - " -o --output output data to a file (e.g. \"results.bin\")\n" - " -l --loop loopback\n" - " -H --cpha clock phase\n" - " -O --cpol clock polarity\n" - " -L --lsb least significant bit first\n" - " -C --cs-high chip select active high\n" - " -3 --3wire SI/SO signals shared\n" - " -v --verbose Verbose (show tx buffer)\n" - " -p Send data (e.g. \"1234\\xde\\xad\")\n" - " -N --no-cs no chip select\n" - " -R --ready slave pulls low to pause\n" - " -2 --dual dual transfer\n" - " -4 --quad quad transfer\n" - " -8 --octal octal transfer\n" - " -S --size transfer size\n" - " -I --iter iterations\n"); + printf("Usage: %s [-2348CDFHILMNORSZbdilopsv]\n", prog); + puts("general device settings:\n" + " -D --device device to use (default /dev/spidev1.1)\n" + " -s --speed max speed (Hz)\n" + " -d --delay delay (usec)\n" + " -l --loop loopback\n" + "spi mode:\n" + " -H --cpha clock phase\n" + " -O --cpol clock polarity\n" + " -F --rx-cpha-flip flip CPHA on Rx only xfer\n" + "number of wires for transmission:\n" + " -2 --dual dual transfer\n" + " -4 --quad quad transfer\n" + " -8 --octal octal transfer\n" + " -3 --3wire SI/SO signals shared\n" + " -Z --3wire-hiz high impedance turnaround\n" + "data:\n" + " -i --input input data from a file (e.g. \"test.bin\")\n" + " -o --output output data to a file (e.g. \"results.bin\")\n" + " -p Send data (e.g. \"1234\\xde\\xad\")\n" + " -S --size transfer size\n" + " -I --iter iterations\n" + "additional parameters:\n" + " -b --bpw bits per word\n" + " -L --lsb least significant bit first\n" + " -C --cs-high chip select active high\n" + " -N --no-cs no chip select\n" + " -R --ready slave pulls low to pause\n" + " -M --mosi-idle-low leave mosi line low when idle\n" + "misc:\n" + " -v --verbose Verbose (show tx buffer)\n"); exit(1); } @@ -201,31 +210,34 @@ static void parse_opts(int argc, char *argv[]) { while (1) { static const struct option lopts[] = { - { "device", 1, 0, 'D' }, - { "speed", 1, 0, 's' }, - { "delay", 1, 0, 'd' }, - { "bpw", 1, 0, 'b' }, - { "input", 1, 0, 'i' }, - { "output", 1, 0, 'o' }, - { "loop", 0, 0, 'l' }, - { "cpha", 0, 0, 'H' }, - { "cpol", 0, 0, 'O' }, - { "lsb", 0, 0, 'L' }, - { "cs-high", 0, 0, 'C' }, - { "3wire", 0, 0, '3' }, - { "no-cs", 0, 0, 'N' }, - { "ready", 0, 0, 'R' }, - { "dual", 0, 0, '2' }, - { "verbose", 0, 0, 'v' }, - { "quad", 0, 0, '4' }, - { "octal", 0, 0, '8' }, - { "size", 1, 0, 'S' }, - { "iter", 1, 0, 'I' }, + { "device", 1, 0, 'D' }, + { "speed", 1, 0, 's' }, + { "delay", 1, 0, 'd' }, + { "loop", 0, 0, 'l' }, + { "cpha", 0, 0, 'H' }, + { "cpol", 0, 0, 'O' }, + { "rx-cpha-flip", 0, 0, 'F' }, + { "dual", 0, 0, '2' }, + { "quad", 0, 0, '4' }, + { "octal", 0, 0, '8' }, + { "3wire", 0, 0, '3' }, + { "3wire-hiz", 0, 0, 'Z' }, + { "input", 1, 0, 'i' }, + { "output", 1, 0, 'o' }, + { "size", 1, 0, 'S' }, + { "iter", 1, 0, 'I' }, + { "bpw", 1, 0, 'b' }, + { "lsb", 0, 0, 'L' }, + { "cs-high", 0, 0, 'C' }, + { "no-cs", 0, 0, 'N' }, + { "ready", 0, 0, 'R' }, + { "mosi-idle-low", 0, 0, 'M' }, + { "verbose", 0, 0, 'v' }, { NULL, 0, 0, 0 }, }; int c; - c = getopt_long(argc, argv, "D:s:d:b:i:o:lHOLC3NR248p:vS:I:", + c = getopt_long(argc, argv, "D:s:d:b:i:o:lHOLC3ZFMNR248p:vS:I:", lopts, NULL); if (c == -1) @@ -268,6 +280,15 @@ static void parse_opts(int argc, char *argv[]) case '3': mode |= SPI_3WIRE; break; + case 'Z': + mode |= SPI_3WIRE_HIZ; + break; + case 'F': + mode |= SPI_RX_CPHA_FLIP; + break; + case 'M': + mode |= SPI_MOSI_IDLE_LOW; + break; case 'N': mode |= SPI_NO_CS; break; diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index fba7bec96acd1..6f9347ade82cd 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -6,6 +6,7 @@ ldflags-y += --wrap=acpi_pci_find_root ldflags-y += --wrap=nvdimm_bus_register ldflags-y += --wrap=devm_cxl_port_enumerate_dports ldflags-y += --wrap=devm_cxl_setup_hdm +ldflags-y += --wrap=devm_cxl_enable_hdm ldflags-y += --wrap=devm_cxl_add_passthrough_decoder ldflags-y += --wrap=devm_cxl_enumerate_decoders ldflags-y += --wrap=cxl_await_media_ready diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index ba572d03c6875..34b48027b3def 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -1256,6 +1256,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) if (rc) return rc; + cxlds->media_ready = true; rc = cxl_dev_state_identify(cxlds); if (rc) return rc; diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index de3933a776fdb..2844165276440 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -149,6 +149,21 @@ struct cxl_hdm *__wrap_devm_cxl_setup_hdm(struct cxl_port *port, } EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_setup_hdm, CXL); +int __wrap_devm_cxl_enable_hdm(struct cxl_port *port, struct cxl_hdm *cxlhdm) +{ + int index, rc; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + + if (ops && ops->is_mock_port(port->uport)) + rc = 0; + else + rc = devm_cxl_enable_hdm(port, cxlhdm); + put_cxl_mock_ops(index); + + return rc; +} +EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_enable_hdm, CXL); + int __wrap_devm_cxl_add_passthrough_decoder(struct cxl_port *port) { int rc, index; diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config index f990cbb732500..0393940c706a6 100644 --- a/tools/testing/kunit/configs/all_tests.config +++ b/tools/testing/kunit/configs/all_tests.config @@ -9,6 +9,8 @@ CONFIG_KUNIT=y CONFIG_KUNIT_EXAMPLE_TEST=y CONFIG_KUNIT_ALL_TESTS=y +CONFIG_FORTIFY_SOURCE=y + CONFIG_IIO=y CONFIG_EXT4_FS=y diff --git a/tools/testing/kunit/configs/arch_uml.config b/tools/testing/kunit/configs/arch_uml.config index e824ce43b05a0..54ad8972681a2 100644 --- a/tools/testing/kunit/configs/arch_uml.config +++ b/tools/testing/kunit/configs/arch_uml.config @@ -3,3 +3,6 @@ # Enable virtio/pci, as a lot of tests require it. CONFIG_VIRTIO_UML=y CONFIG_UML_PCI_OVER_VIRTIO=y + +# Enable FORTIFY_SOURCE for wider checking. +CONFIG_FORTIFY_SOURCE=y diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index f01f941061296..7f648802caf6a 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -92,7 +92,7 @@ class LinuxSourceTreeOperations: if stderr: # likely only due to build warnings print(stderr.decode()) - def start(self, params: List[str], build_dir: str) -> subprocess.Popen[str]: + def start(self, params: List[str], build_dir: str) -> subprocess.Popen: raise RuntimeError('not implemented!') @@ -113,7 +113,7 @@ class LinuxSourceTreeOperationsQemu(LinuxSourceTreeOperations): kconfig.merge_in_entries(base_kunitconfig) return kconfig - def start(self, params: List[str], build_dir: str) -> subprocess.Popen[str]: + def start(self, params: List[str], build_dir: str) -> subprocess.Popen: kernel_path = os.path.join(build_dir, self._kernel_path) qemu_command = ['qemu-system-' + self._qemu_arch, '-nodefaults', @@ -142,7 +142,7 @@ class LinuxSourceTreeOperationsUml(LinuxSourceTreeOperations): kconfig.merge_in_entries(base_kunitconfig) return kconfig - def start(self, params: List[str], build_dir: str) -> subprocess.Popen[str]: + def start(self, params: List[str], build_dir: str) -> subprocess.Popen: """Runs the Linux UML binary. Must be named 'linux'.""" linux_bin = os.path.join(build_dir, 'linux') params.extend(['mem=1G', 'console=tty', 'kunit_shutdown=halt']) diff --git a/tools/testing/kunit/mypy.ini b/tools/testing/kunit/mypy.ini new file mode 100644 index 0000000000000..ddd288309efaa --- /dev/null +++ b/tools/testing/kunit/mypy.ini @@ -0,0 +1,6 @@ +[mypy] +strict = True + +# E.g. we can't write subprocess.Popen[str] until Python 3.9+. +# But kunit.py tries to support Python 3.7+, so let's disable it. +disable_error_code = type-arg diff --git a/tools/testing/kunit/run_checks.py b/tools/testing/kunit/run_checks.py index 8208c3b3135ef..c6d494ea33739 100755 --- a/tools/testing/kunit/run_checks.py +++ b/tools/testing/kunit/run_checks.py @@ -23,7 +23,7 @@ commands: Dict[str, Sequence[str]] = { 'kunit_tool_test.py': ['./kunit_tool_test.py'], 'kunit smoke test': ['./kunit.py', 'run', '--kunitconfig=lib/kunit', '--build_dir=kunit_run_checks'], 'pytype': ['/bin/sh', '-c', 'pytype *.py'], - 'mypy': ['mypy', '--strict', '--exclude', '_test.py$', '--exclude', 'qemu_configs/', '.'], + 'mypy': ['mypy', '--config-file', 'mypy.ini', '--exclude', '_test.py$', '--exclude', 'qemu_configs/', '.'], } # The user might not have mypy or pytype installed, skip them if so. diff --git a/tools/testing/memblock/tests/alloc_nid_api.c b/tools/testing/memblock/tests/alloc_nid_api.c index 49ef68cccd6f8..49bb416d34ffc 100644 --- a/tools/testing/memblock/tests/alloc_nid_api.c +++ b/tools/testing/memblock/tests/alloc_nid_api.c @@ -2494,6 +2494,35 @@ static int alloc_nid_numa_split_all_reserved_generic_check(void) return 0; } +/* + * A simple test that tries to allocate a memory region through the + * memblock_alloc_node() on a NUMA node with id `nid`. Expected to have the + * correct NUMA node set for the new region. + */ +static int alloc_node_on_correct_nid(void) +{ + int nid_req = 2; + void *allocated_ptr = NULL; +#ifdef CONFIG_NUMA + struct memblock_region *req_node = &memblock.memory.regions[nid_req]; +#endif + phys_addr_t size = SZ_512; + + PREFIX_PUSH(); + setup_numa_memblock(node_fractions); + + allocated_ptr = memblock_alloc_node(size, SMP_CACHE_BYTES, nid_req); + + ASSERT_NE(allocated_ptr, NULL); +#ifdef CONFIG_NUMA + ASSERT_EQ(nid_req, req_node->nid); +#endif + + test_pass_pop(); + + return 0; +} + /* Test case wrappers for NUMA tests */ static int alloc_nid_numa_simple_check(void) { @@ -2632,6 +2661,15 @@ static int alloc_nid_numa_split_all_reserved_check(void) return 0; } +static int alloc_node_numa_on_correct_nid(void) +{ + test_print("\tRunning %s...\n", __func__); + run_top_down(alloc_node_on_correct_nid); + run_bottom_up(alloc_node_on_correct_nid); + + return 0; +} + int __memblock_alloc_nid_numa_checks(void) { test_print("Running %s NUMA tests...\n", @@ -2652,6 +2690,8 @@ int __memblock_alloc_nid_numa_checks(void) alloc_nid_numa_reserved_full_merge_check(); alloc_nid_numa_split_all_reserved_check(); + alloc_node_numa_on_correct_nid(); + return 0; } diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index caf32a9b96089..7527f738b4a14 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \ - -fsanitize=undefined +CFLAGS += -I. -I../../include -I../../../lib -g -Og -Wall \ + -D_LGPL_SOURCE -fsanitize=address -fsanitize=undefined LDFLAGS += -fsanitize=address -fsanitize=undefined LDLIBS+= -lpthread -lurcu TARGETS = main idr-test multiorder xarray maple @@ -49,6 +49,7 @@ $(OFILES): Makefile *.h */*.h generated/map-shift.h generated/bit-length.h \ ../../../include/linux/xarray.h \ ../../../include/linux/maple_tree.h \ ../../../include/linux/radix-tree.h \ + ../../../lib/radix-tree.h \ ../../../include/linux/idr.h radix-tree.c: ../../../lib/radix-tree.c diff --git a/tools/testing/radix-tree/linux/init.h b/tools/testing/radix-tree/linux/init.h index 1bb0afc213099..81563c3dfce79 100644 --- a/tools/testing/radix-tree/linux/init.h +++ b/tools/testing/radix-tree/linux/init.h @@ -1 +1,2 @@ #define __init +#define __exit diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 9286d3baa12d6..03539d86cdf0f 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -14,6 +14,7 @@ #include "test.h" #include <stdlib.h> #include <time.h> +#include "linux/init.h" #define module_init(x) #define module_exit(x) @@ -22,7 +23,6 @@ #define dump_stack() assert(0) #include "../../../lib/maple_tree.c" -#undef CONFIG_DEBUG_MAPLE_TREE #include "../../../lib/test_maple_tree.c" #define RCU_RANGE_COUNT 1000 @@ -81,7 +81,7 @@ static void check_mas_alloc_node_count(struct ma_state *mas) * check_new_node() - Check the creation of new nodes and error path * verification. */ -static noinline void check_new_node(struct maple_tree *mt) +static noinline void __init check_new_node(struct maple_tree *mt) { struct maple_node *mn, *mn2, *mn3; @@ -455,7 +455,7 @@ static noinline void check_new_node(struct maple_tree *mt) /* * Check erasing including RCU. */ -static noinline void check_erase(struct maple_tree *mt, unsigned long index, +static noinline void __init check_erase(struct maple_tree *mt, unsigned long index, void *ptr) { MT_BUG_ON(mt, mtree_test_erase(mt, index) != ptr); @@ -465,24 +465,24 @@ static noinline void check_erase(struct maple_tree *mt, unsigned long index, #define erase_check_insert(mt, i) check_insert(mt, set[i], entry[i%2]) #define erase_check_erase(mt, i) check_erase(mt, set[i], entry[i%2]) -static noinline void check_erase_testset(struct maple_tree *mt) +static noinline void __init check_erase_testset(struct maple_tree *mt) { - unsigned long set[] = { 5015, 5014, 5017, 25, 1000, - 1001, 1002, 1003, 1005, 0, - 6003, 6002, 6008, 6012, 6015, - 7003, 7002, 7008, 7012, 7015, - 8003, 8002, 8008, 8012, 8015, - 9003, 9002, 9008, 9012, 9015, - 10003, 10002, 10008, 10012, 10015, - 11003, 11002, 11008, 11012, 11015, - 12003, 12002, 12008, 12012, 12015, - 13003, 13002, 13008, 13012, 13015, - 14003, 14002, 14008, 14012, 14015, - 15003, 15002, 15008, 15012, 15015, - }; - - - void *ptr = &set; + static const unsigned long set[] = { 5015, 5014, 5017, 25, 1000, + 1001, 1002, 1003, 1005, 0, + 6003, 6002, 6008, 6012, 6015, + 7003, 7002, 7008, 7012, 7015, + 8003, 8002, 8008, 8012, 8015, + 9003, 9002, 9008, 9012, 9015, + 10003, 10002, 10008, 10012, 10015, + 11003, 11002, 11008, 11012, 11015, + 12003, 12002, 12008, 12012, 12015, + 13003, 13002, 13008, 13012, 13015, + 14003, 14002, 14008, 14012, 14015, + 15003, 15002, 15008, 15012, 15015, + }; + + + void *ptr = &check_erase_testset; void *entry[2] = { ptr, mt }; void *root_node; @@ -739,7 +739,7 @@ static noinline void check_erase_testset(struct maple_tree *mt) int mas_ce2_over_count(struct ma_state *mas_start, struct ma_state *mas_end, void *s_entry, unsigned long s_min, void *e_entry, unsigned long e_max, - unsigned long *set, int i, bool null_entry) + const unsigned long *set, int i, bool null_entry) { int count = 0, span = 0; unsigned long retry = 0; @@ -969,8 +969,8 @@ retry: } #if defined(CONFIG_64BIT) -static noinline void check_erase2_testset(struct maple_tree *mt, - unsigned long *set, unsigned long size) +static noinline void __init check_erase2_testset(struct maple_tree *mt, + const unsigned long *set, unsigned long size) { int entry_count = 0; int check = 0; @@ -1054,7 +1054,7 @@ static noinline void check_erase2_testset(struct maple_tree *mt, if (entry_count) MT_BUG_ON(mt, !mt_height(mt)); #if check_erase2_debug > 1 - mt_dump(mt); + mt_dump(mt, mt_dump_hex); #endif #if check_erase2_debug pr_err("Done\n"); @@ -1085,7 +1085,7 @@ static noinline void check_erase2_testset(struct maple_tree *mt, mas_for_each(&mas, foo, ULONG_MAX) { if (xa_is_zero(foo)) { if (addr == mas.index) { - mt_dump(mas.tree); + mt_dump(mas.tree, mt_dump_hex); pr_err("retry failed %lu - %lu\n", mas.index, mas.last); MT_BUG_ON(mt, 1); @@ -1114,11 +1114,11 @@ static noinline void check_erase2_testset(struct maple_tree *mt, /* These tests were pulled from KVM tree modifications which failed. */ -static noinline void check_erase2_sets(struct maple_tree *mt) +static noinline void __init check_erase2_sets(struct maple_tree *mt) { void *entry; unsigned long start = 0; - unsigned long set[] = { + static const unsigned long set[] = { STORE, 140737488347136, 140737488351231, STORE, 140721266458624, 140737488351231, ERASE, 140721266458624, 140737488351231, @@ -1136,7 +1136,7 @@ ERASE, 140253902692352, 140253902864383, STORE, 140253902692352, 140253902696447, STORE, 140253902696448, 140253902864383, }; - unsigned long set2[] = { + static const unsigned long set2[] = { STORE, 140737488347136, 140737488351231, STORE, 140735933583360, 140737488351231, ERASE, 140735933583360, 140737488351231, @@ -1160,7 +1160,7 @@ STORE, 140277094813696, 140277094821887, STORE, 140277094821888, 140277094825983, STORE, 140735933906944, 140735933911039, }; - unsigned long set3[] = { + static const unsigned long set3[] = { STORE, 140737488347136, 140737488351231, STORE, 140735790264320, 140737488351231, ERASE, 140735790264320, 140737488351231, @@ -1203,7 +1203,7 @@ STORE, 47135835840512, 47135835885567, STORE, 47135835885568, 47135835893759, }; - unsigned long set4[] = { + static const unsigned long set4[] = { STORE, 140737488347136, 140737488351231, STORE, 140728251703296, 140737488351231, ERASE, 140728251703296, 140737488351231, @@ -1224,7 +1224,7 @@ ERASE, 47646523277312, 47646523445247, STORE, 47646523277312, 47646523400191, }; - unsigned long set5[] = { + static const unsigned long set5[] = { STORE, 140737488347136, 140737488351231, STORE, 140726874062848, 140737488351231, ERASE, 140726874062848, 140737488351231, @@ -1357,7 +1357,7 @@ STORE, 47884791619584, 47884791623679, STORE, 47884791623680, 47884791627775, }; - unsigned long set6[] = { + static const unsigned long set6[] = { STORE, 140737488347136, 140737488351231, STORE, 140722999021568, 140737488351231, ERASE, 140722999021568, 140737488351231, @@ -1489,7 +1489,7 @@ ERASE, 47430432014336, 47430432022527, STORE, 47430432014336, 47430432018431, STORE, 47430432018432, 47430432022527, }; - unsigned long set7[] = { + static const unsigned long set7[] = { STORE, 140737488347136, 140737488351231, STORE, 140729808330752, 140737488351231, ERASE, 140729808330752, 140737488351231, @@ -1621,7 +1621,7 @@ ERASE, 47439987130368, 47439987138559, STORE, 47439987130368, 47439987134463, STORE, 47439987134464, 47439987138559, }; - unsigned long set8[] = { + static const unsigned long set8[] = { STORE, 140737488347136, 140737488351231, STORE, 140722482974720, 140737488351231, ERASE, 140722482974720, 140737488351231, @@ -1754,7 +1754,7 @@ STORE, 47708488638464, 47708488642559, STORE, 47708488642560, 47708488646655, }; - unsigned long set9[] = { + static const unsigned long set9[] = { STORE, 140737488347136, 140737488351231, STORE, 140736427839488, 140737488351231, ERASE, 140736427839488, 140736427839488, @@ -5620,7 +5620,7 @@ ERASE, 47906195480576, 47906195480576, STORE, 94641242615808, 94641242750975, }; - unsigned long set10[] = { + static const unsigned long set10[] = { STORE, 140737488347136, 140737488351231, STORE, 140736427839488, 140737488351231, ERASE, 140736427839488, 140736427839488, @@ -9484,7 +9484,7 @@ STORE, 139726599680000, 139726599684095, ERASE, 47906195480576, 47906195480576, STORE, 94641242615808, 94641242750975, }; - unsigned long set11[] = { + static const unsigned long set11[] = { STORE, 140737488347136, 140737488351231, STORE, 140732658499584, 140737488351231, ERASE, 140732658499584, 140732658499584, @@ -9510,7 +9510,7 @@ STORE, 140732658565120, 140732658569215, STORE, 140732658552832, 140732658565119, }; - unsigned long set12[] = { /* contains 12 values. */ + static const unsigned long set12[] = { /* contains 12 values. */ STORE, 140737488347136, 140737488351231, STORE, 140732658499584, 140737488351231, ERASE, 140732658499584, 140732658499584, @@ -9537,7 +9537,7 @@ STORE, 140732658552832, 140732658565119, STORE, 140014592741375, 140014592741375, /* contrived */ STORE, 140014592733184, 140014592741376, /* creates first entry retry. */ }; - unsigned long set13[] = { + static const unsigned long set13[] = { STORE, 140373516247040, 140373516251135,/*: ffffa2e7b0e10d80 */ STORE, 140373516251136, 140373516255231,/*: ffffa2e7b1195d80 */ STORE, 140373516255232, 140373516443647,/*: ffffa2e7b0e109c0 */ @@ -9550,7 +9550,7 @@ STORE, 140373518684160, 140373518688254,/*: ffffa2e7b05fec00 */ STORE, 140373518688256, 140373518692351,/*: ffffa2e7bfbdcd80 */ STORE, 140373518692352, 140373518696447,/*: ffffa2e7b0749e40 */ }; - unsigned long set14[] = { + static const unsigned long set14[] = { STORE, 140737488347136, 140737488351231, STORE, 140731667996672, 140737488351231, SNULL, 140731668000767, 140737488351231, @@ -9834,7 +9834,7 @@ SNULL, 139826136543232, 139826136809471, STORE, 139826136809472, 139826136842239, STORE, 139826136543232, 139826136809471, }; - unsigned long set15[] = { + static const unsigned long set15[] = { STORE, 140737488347136, 140737488351231, STORE, 140722061451264, 140737488351231, SNULL, 140722061455359, 140737488351231, @@ -10119,7 +10119,7 @@ STORE, 139906808958976, 139906808991743, STORE, 139906808692736, 139906808958975, }; - unsigned long set16[] = { + static const unsigned long set16[] = { STORE, 94174808662016, 94174809321471, STORE, 94174811414528, 94174811426815, STORE, 94174811426816, 94174811430911, @@ -10330,7 +10330,7 @@ STORE, 139921865613312, 139921865617407, STORE, 139921865547776, 139921865564159, }; - unsigned long set17[] = { + static const unsigned long set17[] = { STORE, 94397057224704, 94397057646591, STORE, 94397057650688, 94397057691647, STORE, 94397057691648, 94397057695743, @@ -10392,7 +10392,7 @@ STORE, 140720477511680, 140720477646847, STORE, 140720478302208, 140720478314495, STORE, 140720478314496, 140720478318591, }; - unsigned long set18[] = { + static const unsigned long set18[] = { STORE, 140737488347136, 140737488351231, STORE, 140724953673728, 140737488351231, SNULL, 140724953677823, 140737488351231, @@ -10425,7 +10425,7 @@ STORE, 140222970597376, 140222970605567, ERASE, 140222970597376, 140222970605567, STORE, 140222970597376, 140222970605567, }; - unsigned long set19[] = { + static const unsigned long set19[] = { STORE, 140737488347136, 140737488351231, STORE, 140725182459904, 140737488351231, SNULL, 140725182463999, 140737488351231, @@ -10694,7 +10694,7 @@ STORE, 140656836775936, 140656836780031, STORE, 140656787476480, 140656791920639, ERASE, 140656774639616, 140656779083775, }; - unsigned long set20[] = { + static const unsigned long set20[] = { STORE, 140737488347136, 140737488351231, STORE, 140735952392192, 140737488351231, SNULL, 140735952396287, 140737488351231, @@ -10850,7 +10850,7 @@ STORE, 140590386819072, 140590386823167, STORE, 140590386823168, 140590386827263, SNULL, 140590376591359, 140590376595455, }; - unsigned long set21[] = { + static const unsigned long set21[] = { STORE, 93874710941696, 93874711363583, STORE, 93874711367680, 93874711408639, STORE, 93874711408640, 93874711412735, @@ -10920,7 +10920,7 @@ ERASE, 140708393312256, 140708393316351, ERASE, 140708393308160, 140708393312255, ERASE, 140708393291776, 140708393308159, }; - unsigned long set22[] = { + static const unsigned long set22[] = { STORE, 93951397134336, 93951397183487, STORE, 93951397183488, 93951397728255, STORE, 93951397728256, 93951397826559, @@ -11047,7 +11047,7 @@ STORE, 140551361253376, 140551361519615, ERASE, 140551361253376, 140551361519615, }; - unsigned long set23[] = { + static const unsigned long set23[] = { STORE, 94014447943680, 94014448156671, STORE, 94014450253824, 94014450257919, STORE, 94014450257920, 94014450266111, @@ -14371,7 +14371,7 @@ SNULL, 140175956627455, 140175985139711, STORE, 140175927242752, 140175956627455, STORE, 140175956627456, 140175985139711, }; - unsigned long set24[] = { + static const unsigned long set24[] = { STORE, 140737488347136, 140737488351231, STORE, 140735281639424, 140737488351231, SNULL, 140735281643519, 140737488351231, @@ -15533,7 +15533,7 @@ ERASE, 139635393024000, 139635401412607, ERASE, 139635384627200, 139635384631295, ERASE, 139635384631296, 139635393019903, }; - unsigned long set25[] = { + static const unsigned long set25[] = { STORE, 140737488347136, 140737488351231, STORE, 140737488343040, 140737488351231, STORE, 140722547441664, 140737488351231, @@ -22321,7 +22321,7 @@ STORE, 140249652703232, 140249682087935, STORE, 140249682087936, 140249710600191, }; - unsigned long set26[] = { + static const unsigned long set26[] = { STORE, 140737488347136, 140737488351231, STORE, 140729464770560, 140737488351231, SNULL, 140729464774655, 140737488351231, @@ -22345,7 +22345,7 @@ ERASE, 140109040951296, 140109040959487, STORE, 140109040955392, 140109040959487, ERASE, 140109040955392, 140109040959487, }; - unsigned long set27[] = { + static const unsigned long set27[] = { STORE, 140737488347136, 140737488351231, STORE, 140726128070656, 140737488351231, SNULL, 140726128074751, 140737488351231, @@ -22741,7 +22741,7 @@ STORE, 140415509696512, 140415535910911, ERASE, 140415537422336, 140415562588159, STORE, 140415482433536, 140415509696511, }; - unsigned long set28[] = { + static const unsigned long set28[] = { STORE, 140737488347136, 140737488351231, STORE, 140722475622400, 140737488351231, SNULL, 140722475626495, 140737488351231, @@ -22809,7 +22809,7 @@ STORE, 139918413348864, 139918413352959, ERASE, 139918413316096, 139918413344767, STORE, 93865848528896, 93865848664063, }; - unsigned long set29[] = { + static const unsigned long set29[] = { STORE, 140737488347136, 140737488351231, STORE, 140734467944448, 140737488351231, SNULL, 140734467948543, 140737488351231, @@ -23684,7 +23684,7 @@ ERASE, 140143079972864, 140143088361471, ERASE, 140143205793792, 140143205797887, ERASE, 140143205797888, 140143214186495, }; - unsigned long set30[] = { + static const unsigned long set30[] = { STORE, 140737488347136, 140737488351231, STORE, 140733436743680, 140737488351231, SNULL, 140733436747775, 140737488351231, @@ -24566,7 +24566,7 @@ ERASE, 140165225893888, 140165225897983, ERASE, 140165225897984, 140165234286591, ERASE, 140165058105344, 140165058109439, }; - unsigned long set31[] = { + static const unsigned long set31[] = { STORE, 140737488347136, 140737488351231, STORE, 140730890784768, 140737488351231, SNULL, 140730890788863, 140737488351231, @@ -25379,7 +25379,7 @@ ERASE, 140623906590720, 140623914979327, ERASE, 140622950277120, 140622950281215, ERASE, 140622950281216, 140622958669823, }; - unsigned long set32[] = { + static const unsigned long set32[] = { STORE, 140737488347136, 140737488351231, STORE, 140731244212224, 140737488351231, SNULL, 140731244216319, 140737488351231, @@ -26175,7 +26175,7 @@ ERASE, 140400417288192, 140400425676799, ERASE, 140400283066368, 140400283070463, ERASE, 140400283070464, 140400291459071, }; - unsigned long set33[] = { + static const unsigned long set33[] = { STORE, 140737488347136, 140737488351231, STORE, 140734562918400, 140737488351231, SNULL, 140734562922495, 140737488351231, @@ -26317,7 +26317,7 @@ STORE, 140582961786880, 140583003750399, ERASE, 140582961786880, 140583003750399, }; - unsigned long set34[] = { + static const unsigned long set34[] = { STORE, 140737488347136, 140737488351231, STORE, 140731327180800, 140737488351231, SNULL, 140731327184895, 140737488351231, @@ -27198,7 +27198,7 @@ ERASE, 140012522094592, 140012530483199, ERASE, 140012033142784, 140012033146879, ERASE, 140012033146880, 140012041535487, }; - unsigned long set35[] = { + static const unsigned long set35[] = { STORE, 140737488347136, 140737488351231, STORE, 140730536939520, 140737488351231, SNULL, 140730536943615, 140737488351231, @@ -27955,7 +27955,7 @@ ERASE, 140474471936000, 140474480324607, ERASE, 140474396430336, 140474396434431, ERASE, 140474396434432, 140474404823039, }; - unsigned long set36[] = { + static const unsigned long set36[] = { STORE, 140737488347136, 140737488351231, STORE, 140723893125120, 140737488351231, SNULL, 140723893129215, 140737488351231, @@ -28816,7 +28816,7 @@ ERASE, 140121890357248, 140121898745855, ERASE, 140121269587968, 140121269592063, ERASE, 140121269592064, 140121277980671, }; - unsigned long set37[] = { + static const unsigned long set37[] = { STORE, 140737488347136, 140737488351231, STORE, 140722404016128, 140737488351231, SNULL, 140722404020223, 140737488351231, @@ -28942,7 +28942,7 @@ STORE, 139759821246464, 139759888355327, ERASE, 139759821246464, 139759888355327, ERASE, 139759888355328, 139759955464191, }; - unsigned long set38[] = { + static const unsigned long set38[] = { STORE, 140737488347136, 140737488351231, STORE, 140730666221568, 140737488351231, SNULL, 140730666225663, 140737488351231, @@ -29752,7 +29752,7 @@ ERASE, 140613504712704, 140613504716799, ERASE, 140613504716800, 140613513105407, }; - unsigned long set39[] = { + static const unsigned long set39[] = { STORE, 140737488347136, 140737488351231, STORE, 140736271417344, 140737488351231, SNULL, 140736271421439, 140737488351231, @@ -30124,7 +30124,7 @@ STORE, 140325364428800, 140325372821503, STORE, 140325356036096, 140325364428799, SNULL, 140325364432895, 140325372821503, }; - unsigned long set40[] = { + static const unsigned long set40[] = { STORE, 140737488347136, 140737488351231, STORE, 140734309167104, 140737488351231, SNULL, 140734309171199, 140737488351231, @@ -30875,7 +30875,7 @@ ERASE, 140320289300480, 140320289304575, ERASE, 140320289304576, 140320297693183, ERASE, 140320163409920, 140320163414015, }; - unsigned long set41[] = { + static const unsigned long set41[] = { STORE, 140737488347136, 140737488351231, STORE, 140728157171712, 140737488351231, SNULL, 140728157175807, 140737488351231, @@ -31185,7 +31185,7 @@ STORE, 94376135090176, 94376135094271, STORE, 94376135094272, 94376135098367, SNULL, 94376135094272, 94377208836095, }; - unsigned long set42[] = { + static const unsigned long set42[] = { STORE, 314572800, 1388314623, STORE, 1462157312, 1462169599, STORE, 1462169600, 1462185983, @@ -33862,7 +33862,7 @@ SNULL, 3798999040, 3799101439, */ }; - unsigned long set43[] = { + static const unsigned long set43[] = { STORE, 140737488347136, 140737488351231, STORE, 140734187720704, 140737488351231, SNULL, 140734187724800, 140737488351231, @@ -34513,7 +34513,7 @@ static void *rcu_reader_rev(void *ptr) if (mas.index != r_start) { alt = xa_mk_value(index + i * 2 + 1 + RCU_RANGE_COUNT); - mt_dump(test->mt); + mt_dump(test->mt, mt_dump_dec); printk("Error: %lu-%lu %p != %lu-%lu %p %p line %d i %d\n", mas.index, mas.last, entry, r_start, r_end, expected, alt, @@ -34996,7 +34996,7 @@ void run_check_rcu_slowread(struct maple_tree *mt, struct rcu_test_struct *vals) MT_BUG_ON(mt, !vals->seen_entry3); MT_BUG_ON(mt, !vals->seen_both); } -static noinline void check_rcu_simulated(struct maple_tree *mt) +static noinline void __init check_rcu_simulated(struct maple_tree *mt) { unsigned long i, nr_entries = 1000; unsigned long target = 4320; @@ -35157,7 +35157,7 @@ static noinline void check_rcu_simulated(struct maple_tree *mt) rcu_unregister_thread(); } -static noinline void check_rcu_threaded(struct maple_tree *mt) +static noinline void __init check_rcu_threaded(struct maple_tree *mt) { unsigned long i, nr_entries = 1000; struct rcu_test_struct vals; @@ -35259,6 +35259,7 @@ static void mas_dfs_preorder(struct ma_state *mas) struct maple_enode *prev; unsigned char end, slot = 0; + unsigned long *pivots; if (mas->node == MAS_START) { mas_start(mas); @@ -35291,6 +35292,9 @@ walk_up: mas_ascend(mas); goto walk_up; } + pivots = ma_pivots(mte_to_node(prev), mte_node_type(prev)); + mas->max = mas_safe_pivot(mas, pivots, slot, mte_node_type(prev)); + mas->min = mas_safe_min(mas, pivots, slot); return; done: @@ -35366,7 +35370,7 @@ static void check_dfs_preorder(struct maple_tree *mt) /* End of depth first search tests */ /* Preallocation testing */ -static noinline void check_prealloc(struct maple_tree *mt) +static noinline void __init check_prealloc(struct maple_tree *mt) { unsigned long i, max = 100; unsigned long allocated; @@ -35494,7 +35498,7 @@ static noinline void check_prealloc(struct maple_tree *mt) /* End of preallocation testing */ /* Spanning writes, writes that span nodes and layers of the tree */ -static noinline void check_spanning_write(struct maple_tree *mt) +static noinline void __init check_spanning_write(struct maple_tree *mt) { unsigned long i, max = 5000; MA_STATE(mas, mt, 1200, 2380); @@ -35662,7 +35666,7 @@ static noinline void check_spanning_write(struct maple_tree *mt) /* End of spanning write testing */ /* Writes to a NULL area that are adjacent to other NULLs */ -static noinline void check_null_expand(struct maple_tree *mt) +static noinline void __init check_null_expand(struct maple_tree *mt) { unsigned long i, max = 100; unsigned char data_end; @@ -35723,7 +35727,7 @@ static noinline void check_null_expand(struct maple_tree *mt) /* End of NULL area expansions */ /* Checking for no memory is best done outside the kernel */ -static noinline void check_nomem(struct maple_tree *mt) +static noinline void __init check_nomem(struct maple_tree *mt) { MA_STATE(ms, mt, 1, 1); @@ -35758,7 +35762,7 @@ static noinline void check_nomem(struct maple_tree *mt) mtree_destroy(mt); } -static noinline void check_locky(struct maple_tree *mt) +static noinline void __init check_locky(struct maple_tree *mt) { MA_STATE(ms, mt, 2, 2); MA_STATE(reader, mt, 2, 2); @@ -35780,10 +35784,10 @@ void farmer_tests(void) struct maple_node *node; DEFINE_MTREE(tree); - mt_dump(&tree); + mt_dump(&tree, mt_dump_dec); tree.ma_root = xa_mk_value(0); - mt_dump(&tree); + mt_dump(&tree, mt_dump_dec); node = mt_alloc_one(GFP_KERNEL); node->parent = (void *)((unsigned long)(&tree) | 1); @@ -35793,7 +35797,7 @@ void farmer_tests(void) node->mr64.pivot[1] = 1; node->mr64.pivot[2] = 0; tree.ma_root = mt_mk_node(node, maple_leaf_64); - mt_dump(&tree); + mt_dump(&tree, mt_dump_dec); node->parent = ma_parent_ptr(node); ma_free_rcu(node); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 90a62cf750088..6b456c5ecec17 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -4,6 +4,7 @@ TARGETS += amd-pstate TARGETS += arm64 TARGETS += bpf TARGETS += breakpoints +TARGETS += cachestat TARGETS += capabilities TARGETS += cgroup TARGETS += clone3 @@ -144,10 +145,12 @@ ifneq ($(KBUILD_OUTPUT),) abs_objtree := $(realpath $(abs_objtree)) BUILD := $(abs_objtree)/kselftest KHDR_INCLUDES := -isystem ${abs_objtree}/usr/include + KHDR_DIR := ${abs_objtree}/usr/include else BUILD := $(CURDIR) abs_srctree := $(shell cd $(top_srcdir) && pwd) KHDR_INCLUDES := -isystem ${abs_srctree}/usr/include + KHDR_DIR := ${abs_srctree}/usr/include DEFAULT_INSTALL_HDR_PATH := 1 endif @@ -161,7 +164,7 @@ export KHDR_INCLUDES # all isn't the first target in the file. .DEFAULT_GOAL := all -all: +all: kernel_header_files @ret=1; \ for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ @@ -172,6 +175,23 @@ all: ret=$$((ret * $$?)); \ done; exit $$ret; +kernel_header_files: + @ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null; \ + if [ $$? -ne 0 ]; then \ + RED='\033[1;31m'; \ + NOCOLOR='\033[0m'; \ + echo; \ + echo -e "$${RED}error$${NOCOLOR}: missing kernel header files."; \ + echo "Please run this and try again:"; \ + echo; \ + echo " cd $(top_srcdir)"; \ + echo " make headers"; \ + echo; \ + exit 1; \ + fi + +.PHONY: kernel_header_files + run_tests: all @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile index 901949db80ade..5af9ba8a4645b 100644 --- a/tools/testing/selftests/alsa/Makefile +++ b/tools/testing/selftests/alsa/Makefile @@ -12,7 +12,7 @@ LDLIBS+=-lpthread OVERRIDE_TARGETS = 1 -TEST_GEN_PROGS := mixer-test pcm-test +TEST_GEN_PROGS := mixer-test pcm-test test-pcmtest-driver TEST_GEN_PROGS_EXTENDED := libatest.so diff --git a/tools/testing/selftests/alsa/pcm-test.c b/tools/testing/selftests/alsa/pcm-test.c index 3e390fe67eb93..b7eef32addb4a 100644 --- a/tools/testing/selftests/alsa/pcm-test.c +++ b/tools/testing/selftests/alsa/pcm-test.c @@ -381,7 +381,7 @@ __format: goto __close; } if (rrate != rate) { - snprintf(msg, sizeof(msg), "rate mismatch %ld != %ld", rate, rrate); + snprintf(msg, sizeof(msg), "rate mismatch %ld != %d", rate, rrate); goto __close; } rperiod_size = period_size; @@ -447,24 +447,24 @@ __format: frames = snd_pcm_writei(handle, samples, rate); if (frames < 0) { snprintf(msg, sizeof(msg), - "Write failed: expected %d, wrote %li", rate, frames); + "Write failed: expected %ld, wrote %li", rate, frames); goto __close; } if (frames < rate) { snprintf(msg, sizeof(msg), - "expected %d, wrote %li", rate, frames); + "expected %ld, wrote %li", rate, frames); goto __close; } } else { frames = snd_pcm_readi(handle, samples, rate); if (frames < 0) { snprintf(msg, sizeof(msg), - "expected %d, wrote %li", rate, frames); + "expected %ld, wrote %li", rate, frames); goto __close; } if (frames < rate) { snprintf(msg, sizeof(msg), - "expected %d, wrote %li", rate, frames); + "expected %ld, wrote %li", rate, frames); goto __close; } } diff --git a/tools/testing/selftests/alsa/test-pcmtest-driver.c b/tools/testing/selftests/alsa/test-pcmtest-driver.c new file mode 100644 index 0000000000000..71931b240a839 --- /dev/null +++ b/tools/testing/selftests/alsa/test-pcmtest-driver.c @@ -0,0 +1,333 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This is the test which covers PCM middle layer data transferring using + * the virtual pcm test driver (snd-pcmtest). + * + * Copyright 2023 Ivan Orlov <ivan.orlov0322@gmail.com> + */ +#include <string.h> +#include <alsa/asoundlib.h> +#include "../kselftest_harness.h" + +#define CH_NUM 4 + +struct pattern_buf { + char buf[1024]; + int len; +}; + +struct pattern_buf patterns[CH_NUM]; + +struct pcmtest_test_params { + unsigned long buffer_size; + unsigned long period_size; + unsigned long channels; + unsigned int rate; + snd_pcm_access_t access; + size_t sec_buf_len; + size_t sample_size; + int time; + snd_pcm_format_t format; +}; + +static int read_patterns(void) +{ + FILE *fp, *fpl; + int i; + char pf[64]; + char plf[64]; + + for (i = 0; i < CH_NUM; i++) { + sprintf(plf, "/sys/kernel/debug/pcmtest/fill_pattern%d_len", i); + fpl = fopen(plf, "r"); + if (!fpl) + return -1; + fscanf(fpl, "%u", &patterns[i].len); + fclose(fpl); + + sprintf(pf, "/sys/kernel/debug/pcmtest/fill_pattern%d", i); + fp = fopen(pf, "r"); + if (!fp) { + fclose(fpl); + return -1; + } + fread(patterns[i].buf, 1, patterns[i].len, fp); + fclose(fp); + } + + return 0; +} + +static int get_test_results(char *debug_name) +{ + int result; + FILE *f; + char fname[128]; + + sprintf(fname, "/sys/kernel/debug/pcmtest/%s", debug_name); + + f = fopen(fname, "r"); + if (!f) { + printf("Failed to open file\n"); + return -1; + } + fscanf(f, "%d", &result); + fclose(f); + + return result; +} + +static size_t get_sec_buf_len(unsigned int rate, unsigned long channels, snd_pcm_format_t format) +{ + return rate * channels * snd_pcm_format_physical_width(format) / 8; +} + +static int setup_handle(snd_pcm_t **handle, snd_pcm_sw_params_t *swparams, + snd_pcm_hw_params_t *hwparams, struct pcmtest_test_params *params, + int card, snd_pcm_stream_t stream) +{ + char pcm_name[32]; + int err; + + sprintf(pcm_name, "hw:%d,0,0", card); + err = snd_pcm_open(handle, pcm_name, stream, 0); + if (err < 0) + return err; + snd_pcm_hw_params_any(*handle, hwparams); + snd_pcm_hw_params_set_rate_resample(*handle, hwparams, 0); + snd_pcm_hw_params_set_access(*handle, hwparams, params->access); + snd_pcm_hw_params_set_format(*handle, hwparams, params->format); + snd_pcm_hw_params_set_channels(*handle, hwparams, params->channels); + snd_pcm_hw_params_set_rate_near(*handle, hwparams, ¶ms->rate, 0); + snd_pcm_hw_params_set_period_size_near(*handle, hwparams, ¶ms->period_size, 0); + snd_pcm_hw_params_set_buffer_size_near(*handle, hwparams, ¶ms->buffer_size); + snd_pcm_hw_params(*handle, hwparams); + snd_pcm_sw_params_current(*handle, swparams); + + snd_pcm_hw_params_set_rate_resample(*handle, hwparams, 0); + snd_pcm_sw_params_set_avail_min(*handle, swparams, params->period_size); + snd_pcm_hw_params_set_buffer_size_near(*handle, hwparams, ¶ms->buffer_size); + snd_pcm_hw_params_set_period_size_near(*handle, hwparams, ¶ms->period_size, 0); + snd_pcm_sw_params(*handle, swparams); + snd_pcm_hw_params(*handle, hwparams); + + return 0; +} + +FIXTURE(pcmtest) { + int card; + snd_pcm_sw_params_t *swparams; + snd_pcm_hw_params_t *hwparams; + struct pcmtest_test_params params; +}; + +FIXTURE_TEARDOWN(pcmtest) { +} + +FIXTURE_SETUP(pcmtest) { + char *card_name; + int err; + + if (geteuid()) + SKIP(exit(-1), "This test needs root to run!"); + + err = read_patterns(); + if (err) + SKIP(exit(-1), "Can't read patterns. Probably, module isn't loaded"); + + card_name = malloc(127); + ASSERT_NE(card_name, NULL); + self->params.buffer_size = 16384; + self->params.period_size = 4096; + self->params.channels = CH_NUM; + self->params.rate = 8000; + self->params.access = SND_PCM_ACCESS_RW_INTERLEAVED; + self->params.format = SND_PCM_FORMAT_S16_LE; + self->card = -1; + self->params.sample_size = snd_pcm_format_physical_width(self->params.format) / 8; + + self->params.sec_buf_len = get_sec_buf_len(self->params.rate, self->params.channels, + self->params.format); + self->params.time = 4; + + while (snd_card_next(&self->card) >= 0) { + if (self->card == -1) + break; + snd_card_get_name(self->card, &card_name); + if (!strcmp(card_name, "PCM-Test")) + break; + } + free(card_name); + ASSERT_NE(self->card, -1); +} + +/* + * Here we are trying to send the looped monotonically increasing sequence of bytes to the driver. + * If our data isn't corrupted, the driver will set the content of 'pc_test' debugfs file to '1' + */ +TEST_F(pcmtest, playback) { + snd_pcm_t *handle; + unsigned char *it; + size_t write_res; + int test_results; + int i, cur_ch, pos_in_ch; + void *samples; + struct pcmtest_test_params *params = &self->params; + + samples = calloc(self->params.sec_buf_len * self->params.time, 1); + ASSERT_NE(samples, NULL); + + snd_pcm_sw_params_alloca(&self->swparams); + snd_pcm_hw_params_alloca(&self->hwparams); + + ASSERT_EQ(setup_handle(&handle, self->swparams, self->hwparams, params, + self->card, SND_PCM_STREAM_PLAYBACK), 0); + snd_pcm_format_set_silence(params->format, samples, + params->rate * params->channels * params->time); + it = samples; + for (i = 0; i < self->params.sec_buf_len * params->time; i++) { + cur_ch = (i / params->sample_size) % CH_NUM; + pos_in_ch = i / params->sample_size / CH_NUM * params->sample_size + + (i % params->sample_size); + it[i] = patterns[cur_ch].buf[pos_in_ch % patterns[cur_ch].len]; + } + write_res = snd_pcm_writei(handle, samples, params->rate * params->time); + ASSERT_GE(write_res, 0); + + snd_pcm_close(handle); + free(samples); + test_results = get_test_results("pc_test"); + ASSERT_EQ(test_results, 1); +} + +/* + * Here we test that the virtual alsa driver returns looped and monotonically increasing sequence + * of bytes. In the interleaved mode the buffer will contain samples in the following order: + * C0, C1, C2, C3, C0, C1, ... + */ +TEST_F(pcmtest, capture) { + snd_pcm_t *handle; + unsigned char *it; + size_t read_res; + int i, cur_ch, pos_in_ch; + void *samples; + struct pcmtest_test_params *params = &self->params; + + samples = calloc(self->params.sec_buf_len * self->params.time, 1); + ASSERT_NE(samples, NULL); + + snd_pcm_sw_params_alloca(&self->swparams); + snd_pcm_hw_params_alloca(&self->hwparams); + + ASSERT_EQ(setup_handle(&handle, self->swparams, self->hwparams, + params, self->card, SND_PCM_STREAM_CAPTURE), 0); + snd_pcm_format_set_silence(params->format, samples, + params->rate * params->channels * params->time); + read_res = snd_pcm_readi(handle, samples, params->rate * params->time); + ASSERT_GE(read_res, 0); + snd_pcm_close(handle); + it = (unsigned char *)samples; + for (i = 0; i < self->params.sec_buf_len * self->params.time; i++) { + cur_ch = (i / params->sample_size) % CH_NUM; + pos_in_ch = i / params->sample_size / CH_NUM * params->sample_size + + (i % params->sample_size); + ASSERT_EQ(it[i], patterns[cur_ch].buf[pos_in_ch % patterns[cur_ch].len]); + } + free(samples); +} + +// Test capture in the non-interleaved access mode. The are buffers for each recorded channel +TEST_F(pcmtest, ni_capture) { + snd_pcm_t *handle; + struct pcmtest_test_params params = self->params; + char **chan_samples; + size_t i, j, read_res; + + chan_samples = calloc(CH_NUM, sizeof(*chan_samples)); + ASSERT_NE(chan_samples, NULL); + + snd_pcm_sw_params_alloca(&self->swparams); + snd_pcm_hw_params_alloca(&self->hwparams); + + params.access = SND_PCM_ACCESS_RW_NONINTERLEAVED; + + ASSERT_EQ(setup_handle(&handle, self->swparams, self->hwparams, + ¶ms, self->card, SND_PCM_STREAM_CAPTURE), 0); + + for (i = 0; i < CH_NUM; i++) + chan_samples[i] = calloc(params.sec_buf_len * params.time, 1); + + for (i = 0; i < 1; i++) { + read_res = snd_pcm_readn(handle, (void **)chan_samples, params.rate * params.time); + ASSERT_GE(read_res, 0); + } + snd_pcm_close(handle); + + for (i = 0; i < CH_NUM; i++) { + for (j = 0; j < params.rate * params.time; j++) + ASSERT_EQ(chan_samples[i][j], patterns[i].buf[j % patterns[i].len]); + free(chan_samples[i]); + } + free(chan_samples); +} + +TEST_F(pcmtest, ni_playback) { + snd_pcm_t *handle; + struct pcmtest_test_params params = self->params; + char **chan_samples; + size_t i, j, read_res; + int test_res; + + chan_samples = calloc(CH_NUM, sizeof(*chan_samples)); + ASSERT_NE(chan_samples, NULL); + + snd_pcm_sw_params_alloca(&self->swparams); + snd_pcm_hw_params_alloca(&self->hwparams); + + params.access = SND_PCM_ACCESS_RW_NONINTERLEAVED; + + ASSERT_EQ(setup_handle(&handle, self->swparams, self->hwparams, + ¶ms, self->card, SND_PCM_STREAM_PLAYBACK), 0); + + for (i = 0; i < CH_NUM; i++) { + chan_samples[i] = calloc(params.sec_buf_len * params.time, 1); + for (j = 0; j < params.sec_buf_len * params.time; j++) + chan_samples[i][j] = patterns[i].buf[j % patterns[i].len]; + } + + for (i = 0; i < 1; i++) { + read_res = snd_pcm_writen(handle, (void **)chan_samples, params.rate * params.time); + ASSERT_GE(read_res, 0); + } + + snd_pcm_close(handle); + test_res = get_test_results("pc_test"); + ASSERT_EQ(test_res, 1); + + for (i = 0; i < CH_NUM; i++) + free(chan_samples[i]); + free(chan_samples); +} + +/* + * Here we are testing the custom ioctl definition inside the virtual driver. If it triggers + * successfully, the driver sets the content of 'ioctl_test' debugfs file to '1'. + */ +TEST_F(pcmtest, reset_ioctl) { + snd_pcm_t *handle; + unsigned char *it; + int test_res; + struct pcmtest_test_params *params = &self->params; + + snd_pcm_sw_params_alloca(&self->swparams); + snd_pcm_hw_params_alloca(&self->hwparams); + + ASSERT_EQ(setup_handle(&handle, self->swparams, self->hwparams, params, + self->card, SND_PCM_STREAM_CAPTURE), 0); + snd_pcm_reset(handle); + test_res = get_test_results("ioctl_test"); + ASSERT_EQ(test_res, 1); + snd_pcm_close(handle); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index 93333a90bf3a7..d4ad813fed10f 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -39,6 +39,20 @@ static void cssc_sigill(void) asm volatile(".inst 0xdac01c00" : : : "x0"); } +static void mops_sigill(void) +{ + char dst[1], src[1]; + register char *dstp asm ("x0") = dst; + register char *srcp asm ("x1") = src; + register long size asm ("x2") = 1; + + /* CPYP [x0]!, [x1]!, x2! */ + asm volatile(".inst 0x1d010440" + : "+r" (dstp), "+r" (srcp), "+r" (size) + : + : "cc", "memory"); +} + static void rng_sigill(void) { asm volatile("mrs x0, S3_3_C2_C4_0" : : : "x0"); @@ -210,6 +224,14 @@ static const struct hwcap_data { .sigill_fn = cssc_sigill, }, { + .name = "MOPS", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_MOPS, + .cpuinfo = "mops", + .sigill_fn = mops_sigill, + .sigill_reliable = true, + }, + { .name = "RNG", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_RNG, diff --git a/tools/testing/selftests/arm64/abi/ptrace.c b/tools/testing/selftests/arm64/abi/ptrace.c index be952511af221..abe4d58d731df 100644 --- a/tools/testing/selftests/arm64/abi/ptrace.c +++ b/tools/testing/selftests/arm64/abi/ptrace.c @@ -20,7 +20,7 @@ #include "../../kselftest.h" -#define EXPECTED_TESTS 7 +#define EXPECTED_TESTS 11 #define MAX_TPIDRS 2 @@ -132,6 +132,34 @@ static void test_tpidr(pid_t child) } } +static void test_hw_debug(pid_t child, int type, const char *type_name) +{ + struct user_hwdebug_state state; + struct iovec iov; + int slots, arch, ret; + + iov.iov_len = sizeof(state); + iov.iov_base = &state; + + /* Should be able to read the values */ + ret = ptrace(PTRACE_GETREGSET, child, type, &iov); + ksft_test_result(ret == 0, "read_%s\n", type_name); + + if (ret == 0) { + /* Low 8 bits is the number of slots, next 4 bits the arch */ + slots = state.dbg_info & 0xff; + arch = (state.dbg_info >> 8) & 0xf; + + ksft_print_msg("%s version %d with %d slots\n", type_name, + arch, slots); + + /* Zero is not currently architecturally valid */ + ksft_test_result(arch, "%s_arch_set\n", type_name); + } else { + ksft_test_result_skip("%s_arch_set\n"); + } +} + static int do_child(void) { if (ptrace(PTRACE_TRACEME, -1, NULL, NULL)) @@ -207,6 +235,8 @@ static int do_parent(pid_t child) ksft_print_msg("Parent is %d, child is %d\n", getpid(), child); test_tpidr(child); + test_hw_debug(child, NT_ARM_HW_WATCH, "NT_ARM_HW_WATCH"); + test_hw_debug(child, NT_ARM_HW_BREAK, "NT_ARM_HW_BREAK"); ret = EXIT_SUCCESS; diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore index 8ab4c86837fdf..839e3a252629d 100644 --- a/tools/testing/selftests/arm64/signal/.gitignore +++ b/tools/testing/selftests/arm64/signal/.gitignore @@ -4,7 +4,7 @@ fake_sigreturn_* sme_* ssve_* sve_* -tpidr2_siginfo +tpidr2_* za_* zt_* !*.[ch] diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 40be8443949d4..0dc948db3a4a4 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -249,7 +249,8 @@ static void default_handler(int signum, siginfo_t *si, void *uc) fprintf(stderr, "-- Timeout !\n"); } else { fprintf(stderr, - "-- RX UNEXPECTED SIGNAL: %d\n", signum); + "-- RX UNEXPECTED SIGNAL: %d code %d address %p\n", + signum, si->si_code, si->si_addr); } default_result(current, 1); } diff --git a/tools/testing/selftests/arm64/signal/testcases/tpidr2_restore.c b/tools/testing/selftests/arm64/signal/testcases/tpidr2_restore.c new file mode 100644 index 0000000000000..f9a86c00c28c1 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/tpidr2_restore.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 ARM Limited + * + * Verify that the TPIDR2 register context in signal frames is restored. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/auxv.h> +#include <sys/prctl.h> +#include <unistd.h> +#include <asm/sigcontext.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +#define SYS_TPIDR2 "S3_3_C13_C0_5" + +static uint64_t get_tpidr2(void) +{ + uint64_t val; + + asm volatile ( + "mrs %0, " SYS_TPIDR2 "\n" + : "=r"(val) + : + : "cc"); + + return val; +} + +static void set_tpidr2(uint64_t val) +{ + asm volatile ( + "msr " SYS_TPIDR2 ", %0\n" + : + : "r"(val) + : "cc"); +} + + +static uint64_t initial_tpidr2; + +static bool save_tpidr2(struct tdescr *td) +{ + initial_tpidr2 = get_tpidr2(); + fprintf(stderr, "Initial TPIDR2: %lx\n", initial_tpidr2); + + return true; +} + +static int modify_tpidr2(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + uint64_t my_tpidr2 = get_tpidr2(); + + my_tpidr2++; + fprintf(stderr, "Setting TPIDR2 to %lx\n", my_tpidr2); + set_tpidr2(my_tpidr2); + + return 0; +} + +static void check_tpidr2(struct tdescr *td) +{ + uint64_t tpidr2 = get_tpidr2(); + + td->pass = tpidr2 == initial_tpidr2; + + if (td->pass) + fprintf(stderr, "TPIDR2 restored\n"); + else + fprintf(stderr, "TPIDR2 was %lx but is now %lx\n", + initial_tpidr2, tpidr2); +} + +struct tdescr tde = { + .name = "TPIDR2 restore", + .descr = "Validate that TPIDR2 is restored from the sigframe", + .feats_required = FEAT_SME, + .timeout = 3, + .sig_trig = SIGUSR1, + .init = save_tpidr2, + .run = modify_tpidr2, + .check_result = check_tpidr2, +}; diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64 index 0a6837f97c324..08adc805878bb 100644 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ b/tools/testing/selftests/bpf/DENYLIST.aarch64 @@ -1,33 +1,6 @@ -bloom_filter_map # libbpf: prog 'check_bloom': failed to attach: ERROR: strerror_r(-524)=22 -bpf_cookie/lsm -bpf_cookie/multi_kprobe_attach_api -bpf_cookie/multi_kprobe_link_api -bpf_cookie/trampoline -bpf_loop/check_callback_fn_stop # link unexpected error: -524 -bpf_loop/check_invalid_flags -bpf_loop/check_nested_calls -bpf_loop/check_non_constant_callback -bpf_loop/check_nr_loops -bpf_loop/check_null_callback_ctx -bpf_loop/check_stack -bpf_mod_race # bpf_mod_kfunc_race__attach unexpected error: -524 (errno 524) -bpf_tcp_ca/dctcp_fallback -btf_dump/btf_dump: var_data # find type id unexpected find type id: actual -2 < expected 0 -cgroup_hierarchical_stats # attach unexpected error: -524 (errno 524) -d_path/basic # setup attach failed: -524 -deny_namespace # attach unexpected error: -524 (errno 524) -fentry_fexit # fentry_attach unexpected error: -1 (errno 524) -fentry_test # fentry_attach unexpected error: -1 (errno 524) -fexit_sleep # fexit_attach fexit attach failed: -1 -fexit_stress # fexit attach unexpected fexit attach: actual -524 < expected 0 -fexit_test # fexit_attach unexpected error: -1 (errno 524) -get_func_args_test # get_func_args_test__attach unexpected error: -524 (errno 524) (trampoline) -get_func_ip_test # get_func_ip_test__attach unexpected error: -524 (errno 524) (trampoline) -htab_update/reenter_update -kfree_skb # attach fentry unexpected error: -524 (trampoline) -kfunc_call/subprog # extern (var ksym) 'bpf_prog_active': not found in kernel BTF -kfunc_call/subprog_lskel # skel unexpected error: -2 -kfunc_dynptr_param/dynptr_data_null # libbpf: prog 'dynptr_data_null': failed to attach: ERROR: strerror_r(-524)=22 +bpf_cookie/multi_kprobe_attach_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3 +bpf_cookie/multi_kprobe_link_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3 +fexit_sleep # The test never returns. The remaining tests cannot start. kprobe_multi_bench_attach # bpf_program__attach_kprobe_multi_opts unexpected error: -95 kprobe_multi_test/attach_api_addrs # bpf_program__attach_kprobe_multi_opts unexpected error: -95 kprobe_multi_test/attach_api_pattern # bpf_program__attach_kprobe_multi_opts unexpected error: -95 @@ -35,51 +8,5 @@ kprobe_multi_test/attach_api_syms # bpf_program__attach_kprobe_mu kprobe_multi_test/bench_attach # bpf_program__attach_kprobe_multi_opts unexpected error: -95 kprobe_multi_test/link_api_addrs # link_fd unexpected link_fd: actual -95 < expected 0 kprobe_multi_test/link_api_syms # link_fd unexpected link_fd: actual -95 < expected 0 -kprobe_multi_test/skel_api # kprobe_multi__attach unexpected error: -524 (errno 524) -ksyms_module/libbpf # 'bpf_testmod_ksym_percpu': not found in kernel BTF -ksyms_module/lskel # test_ksyms_module_lskel__open_and_load unexpected error: -2 -libbpf_get_fd_by_id_opts # test_libbpf_get_fd_by_id_opts__attach unexpected error: -524 (errno 524) -linked_list -lookup_key # test_lookup_key__attach unexpected error: -524 (errno 524) -lru_bug # lru_bug__attach unexpected error: -524 (errno 524) -modify_return # modify_return__attach failed unexpected error: -524 (errno 524) -module_attach # skel_attach skeleton attach failed: -524 -module_fentry_shadow # bpf_link_create unexpected bpf_link_create: actual -524 < expected 0 -mptcp/base # run_test mptcp unexpected error: -524 (errno 524) -netcnt # packets unexpected packets: actual 10001 != expected 10000 -rcu_read_lock # failed to attach: ERROR: strerror_r(-524)=22 -recursion # skel_attach unexpected error: -524 (errno 524) -ringbuf # skel_attach skeleton attachment failed: -1 -setget_sockopt # attach_cgroup unexpected error: -524 -sk_storage_tracing # test_sk_storage_tracing__attach unexpected error: -524 (errno 524) -skc_to_unix_sock # could not attach BPF object unexpected error: -524 (errno 524) -socket_cookie # prog_attach unexpected error: -524 -stacktrace_build_id # compare_stack_ips stackmap vs. stack_amap err -1 errno 2 -task_local_storage/exit_creds # skel_attach unexpected error: -524 (errno 524) -task_local_storage/recursion # skel_attach unexpected error: -524 (errno 524) -test_bprm_opts # attach attach failed: -524 -test_ima # attach attach failed: -524 -test_local_storage # attach lsm attach failed: -524 -test_lsm # test_lsm_first_attach unexpected error: -524 (errno 524) -test_overhead # attach_fentry unexpected error: -524 -timer # timer unexpected error: -524 (errno 524) -timer_crash # timer_crash__attach unexpected error: -524 (errno 524) -timer_mim # timer_mim unexpected error: -524 (errno 524) -trace_printk # trace_printk__attach unexpected error: -1 (errno 524) -trace_vprintk # trace_vprintk__attach unexpected error: -1 (errno 524) -tracing_struct # tracing_struct__attach unexpected error: -524 (errno 524) -trampoline_count # attach_prog unexpected error: -524 -unpriv_bpf_disabled # skel_attach unexpected error: -524 (errno 524) -user_ringbuf/test_user_ringbuf_post_misaligned # misaligned_skel unexpected error: -524 (errno 524) -user_ringbuf/test_user_ringbuf_post_producer_wrong_offset -user_ringbuf/test_user_ringbuf_post_larger_than_ringbuf_sz -user_ringbuf/test_user_ringbuf_basic # ringbuf_basic_skel unexpected error: -524 (errno 524) -user_ringbuf/test_user_ringbuf_sample_full_ring_buffer -user_ringbuf/test_user_ringbuf_post_alignment_autoadjust -user_ringbuf/test_user_ringbuf_overfill -user_ringbuf/test_user_ringbuf_discards_properly_ignored -user_ringbuf/test_user_ringbuf_loop -user_ringbuf/test_user_ringbuf_msg_protocol -user_ringbuf/test_user_ringbuf_blocking_reserve -verify_pkcs7_sig # test_verify_pkcs7_sig__attach unexpected error: -524 (errno 524) -vmlinux # skel_attach skeleton attach failed: -524 +kprobe_multi_test/skel_api # libbpf: failed to load BPF skeleton 'kprobe_multi': -3 +module_attach # prog 'kprobe_multi': failed to auto-attach: -95 diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x index c7463f3ec3c09..5061d9e24c164 100644 --- a/tools/testing/selftests/bpf/DENYLIST.s390x +++ b/tools/testing/selftests/bpf/DENYLIST.s390x @@ -26,3 +26,4 @@ user_ringbuf # failed to find kernel BTF type ID of verif_stats # trace_vprintk__open_and_load unexpected error: -9 (?) xdp_bonding # failed to auto-attach program 'trace_on_entry': -524 (trampoline) xdp_metadata # JIT does not support calling kernel function (kfunc) +test_task_under_cgroup # JIT does not support calling kernel function (kfunc) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index c49e5403ad0ed..538df8fb8c42b 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -88,8 +88,7 @@ TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \ xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \ xdp_features -TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read $(OUTPUT)/sign-file -TEST_GEN_FILES += liburandom_read.so +TEST_GEN_FILES += liburandom_read.so urandom_read sign-file # Emit succinct information message describing current building step # $1 - generic step name (e.g., CC, LINK, etc); @@ -197,7 +196,7 @@ $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_r $(OUTPUT)/sign-file: ../../../../scripts/sign-file.c $(call msg,SIGN-FILE,,$@) - $(Q)$(CC) $(shell $(HOSTPKG_CONFIG)--cflags libcrypto 2> /dev/null) \ + $(Q)$(CC) $(shell $(HOSTPKG_CONFIG) --cflags libcrypto 2> /dev/null) \ $< -o $@ \ $(shell $(HOSTPKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto) diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index d9c080ac17967..41fe5a82b88bc 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -17,7 +17,7 @@ struct env env = { .duration_sec = 5, .affinity = false, .quiet = false, - .consumer_cnt = 1, + .consumer_cnt = 0, .producer_cnt = 1, }; @@ -441,12 +441,14 @@ static void setup_timer() static void set_thread_affinity(pthread_t thread, int cpu) { cpu_set_t cpuset; + int err; CPU_ZERO(&cpuset); CPU_SET(cpu, &cpuset); - if (pthread_setaffinity_np(thread, sizeof(cpuset), &cpuset)) { + err = pthread_setaffinity_np(thread, sizeof(cpuset), &cpuset); + if (err) { fprintf(stderr, "setting affinity to CPU #%d failed: %d\n", - cpu, errno); + cpu, -err); exit(1); } } @@ -467,7 +469,7 @@ static int next_cpu(struct cpu_set *cpu_set) exit(1); } - return cpu_set->next_cpu++; + return cpu_set->next_cpu++ % env.nr_cpus; } static struct bench_state { @@ -605,7 +607,7 @@ static void setup_benchmark(void) bench->consumer_thread, (void *)(long)i); if (err) { fprintf(stderr, "failed to create consumer thread #%d: %d\n", - i, -errno); + i, -err); exit(1); } if (env.affinity) @@ -624,7 +626,7 @@ static void setup_benchmark(void) bench->producer_thread, (void *)(long)i); if (err) { fprintf(stderr, "failed to create producer thread #%d: %d\n", - i, -errno); + i, -err); exit(1); } if (env.affinity) @@ -657,6 +659,7 @@ static void collect_measurements(long delta_ns) { int main(int argc, char **argv) { + env.nr_cpus = get_nprocs(); parse_cmdline_args_init(argc, argv); if (env.list) { diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h index 402729c6a3ac5..7ff32be3d7300 100644 --- a/tools/testing/selftests/bpf/bench.h +++ b/tools/testing/selftests/bpf/bench.h @@ -27,6 +27,7 @@ struct env { bool quiet; int consumer_cnt; int producer_cnt; + int nr_cpus; struct cpu_set prod_cpus; struct cpu_set cons_cpus; }; diff --git a/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c b/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c index 7c8ccc1083138..e289dd1a14eef 100644 --- a/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c +++ b/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c @@ -107,9 +107,9 @@ const struct argp bench_bloom_map_argp = { static void validate(void) { - if (env.consumer_cnt != 1) { + if (env.consumer_cnt != 0) { fprintf(stderr, - "The bloom filter benchmarks do not support multi-consumer use\n"); + "The bloom filter benchmarks do not support consumer\n"); exit(1); } } @@ -421,18 +421,12 @@ static void measure(struct bench_res *res) last_false_hits = total_false_hits; } -static void *consumer(void *input) -{ - return NULL; -} - const struct bench bench_bloom_lookup = { .name = "bloom-lookup", .argp = &bench_bloom_map_argp, .validate = validate, .setup = bloom_lookup_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -444,7 +438,6 @@ const struct bench bench_bloom_update = { .validate = validate, .setup = bloom_update_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -456,7 +449,6 @@ const struct bench bench_bloom_false_positive = { .validate = validate, .setup = false_positive_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = false_hits_report_progress, .report_final = false_hits_report_final, @@ -468,7 +460,6 @@ const struct bench bench_hashmap_without_bloom = { .validate = validate, .setup = hashmap_no_bloom_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -480,7 +471,6 @@ const struct bench bench_hashmap_with_bloom = { .validate = validate, .setup = hashmap_with_bloom_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c index 75abe8137b6cf..ee1dc12c5e5e8 100644 --- a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c +++ b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c @@ -14,8 +14,8 @@ static struct ctx { static void validate(void) { - if (env.consumer_cnt != 1) { - fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer!\n"); exit(1); } } @@ -30,11 +30,6 @@ static void *producer(void *input) return NULL; } -static void *consumer(void *input) -{ - return NULL; -} - static void measure(struct bench_res *res) { } @@ -88,7 +83,6 @@ const struct bench bench_bpf_hashmap_full_update = { .validate = validate, .setup = setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = NULL, .report_final = hashmap_report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c index 8dbb02f75cffc..279ff1b8b5b23 100644 --- a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c +++ b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c @@ -113,8 +113,8 @@ const struct argp bench_hashmap_lookup_argp = { static void validate(void) { - if (env.consumer_cnt != 1) { - fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer!\n"); exit(1); } @@ -134,11 +134,6 @@ static void *producer(void *input) return NULL; } -static void *consumer(void *input) -{ - return NULL; -} - static void measure(struct bench_res *res) { } @@ -276,7 +271,6 @@ const struct bench bench_bpf_hashmap_lookup = { .validate = validate, .setup = setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = NULL, .report_final = hashmap_report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c b/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c index d8a0394e10b15..a705cfb2bccc8 100644 --- a/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c +++ b/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c @@ -47,8 +47,8 @@ const struct argp bench_bpf_loop_argp = { static void validate(void) { - if (env.consumer_cnt != 1) { - fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer!\n"); exit(1); } } @@ -62,11 +62,6 @@ static void *producer(void *input) return NULL; } -static void *consumer(void *input) -{ - return NULL; -} - static void measure(struct bench_res *res) { res->hits = atomic_swap(&ctx.skel->bss->hits, 0); @@ -99,7 +94,6 @@ const struct bench bench_bpf_loop = { .validate = validate, .setup = setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = ops_report_progress, .report_final = ops_report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_count.c b/tools/testing/selftests/bpf/benchs/bench_count.c index 078972ce208e6..ba89ed3936b7a 100644 --- a/tools/testing/selftests/bpf/benchs/bench_count.c +++ b/tools/testing/selftests/bpf/benchs/bench_count.c @@ -18,11 +18,6 @@ static void *count_global_producer(void *input) return NULL; } -static void *count_global_consumer(void *input) -{ - return NULL; -} - static void count_global_measure(struct bench_res *res) { struct count_global_ctx *ctx = &count_global_ctx; @@ -40,7 +35,7 @@ static void count_local_setup(void) { struct count_local_ctx *ctx = &count_local_ctx; - ctx->hits = calloc(env.consumer_cnt, sizeof(*ctx->hits)); + ctx->hits = calloc(env.producer_cnt, sizeof(*ctx->hits)); if (!ctx->hits) exit(1); } @@ -56,11 +51,6 @@ static void *count_local_producer(void *input) return NULL; } -static void *count_local_consumer(void *input) -{ - return NULL; -} - static void count_local_measure(struct bench_res *res) { struct count_local_ctx *ctx = &count_local_ctx; @@ -74,7 +64,6 @@ static void count_local_measure(struct bench_res *res) const struct bench bench_count_global = { .name = "count-global", .producer_thread = count_global_producer, - .consumer_thread = count_global_consumer, .measure = count_global_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -84,7 +73,6 @@ const struct bench bench_count_local = { .name = "count-local", .setup = count_local_setup, .producer_thread = count_local_producer, - .consumer_thread = count_local_consumer, .measure = count_local_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_local_storage.c b/tools/testing/selftests/bpf/benchs/bench_local_storage.c index d4b2817306d42..452499428ceb5 100644 --- a/tools/testing/selftests/bpf/benchs/bench_local_storage.c +++ b/tools/testing/selftests/bpf/benchs/bench_local_storage.c @@ -74,8 +74,8 @@ static void validate(void) fprintf(stderr, "benchmark doesn't support multi-producer!\n"); exit(1); } - if (env.consumer_cnt != 1) { - fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer!\n"); exit(1); } @@ -230,11 +230,6 @@ static inline void trigger_bpf_program(void) syscall(__NR_getpgid); } -static void *consumer(void *input) -{ - return NULL; -} - static void *producer(void *input) { while (true) @@ -259,7 +254,6 @@ const struct bench bench_local_storage_cache_seq_get = { .validate = validate, .setup = local_storage_cache_get_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = local_storage_report_progress, .report_final = local_storage_report_final, @@ -271,7 +265,6 @@ const struct bench bench_local_storage_cache_interleaved_get = { .validate = validate, .setup = local_storage_cache_get_interleaved_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = local_storage_report_progress, .report_final = local_storage_report_final, @@ -283,7 +276,6 @@ const struct bench bench_local_storage_cache_hashmap_control = { .validate = validate, .setup = hashmap_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = local_storage_report_progress, .report_final = local_storage_report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c b/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c index cff703f90e958..b36de42ee4d97 100644 --- a/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c +++ b/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c @@ -71,7 +71,7 @@ const struct argp bench_local_storage_create_argp = { static void validate(void) { - if (env.consumer_cnt > 1) { + if (env.consumer_cnt != 0) { fprintf(stderr, "local-storage-create benchmark does not need consumer\n"); exit(1); @@ -143,11 +143,6 @@ static void measure(struct bench_res *res) res->drops = atomic_swap(&skel->bss->kmalloc_cnts, 0); } -static void *consumer(void *input) -{ - return NULL; -} - static void *sk_producer(void *input) { struct thread *t = &threads[(long)(input)]; @@ -257,7 +252,6 @@ const struct bench bench_local_storage_create = { .validate = validate, .setup = setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = report_progress, .report_final = report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c b/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c index d5eb5587f2aa9..edf0b00418c1a 100644 --- a/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c +++ b/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c @@ -72,8 +72,8 @@ static void validate(void) fprintf(stderr, "benchmark doesn't support multi-producer!\n"); exit(1); } - if (env.consumer_cnt != 1) { - fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer!\n"); exit(1); } @@ -197,11 +197,6 @@ static void measure(struct bench_res *res) ctx.prev_kthread_stime = ticks; } -static void *consumer(void *input) -{ - return NULL; -} - static void *producer(void *input) { while (true) @@ -262,7 +257,6 @@ const struct bench bench_local_storage_tasks_trace = { .validate = validate, .setup = local_storage_tasks_trace_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = report_progress, .report_final = report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_rename.c b/tools/testing/selftests/bpf/benchs/bench_rename.c index 3c203b6d6a6ec..bf66893c7a338 100644 --- a/tools/testing/selftests/bpf/benchs/bench_rename.c +++ b/tools/testing/selftests/bpf/benchs/bench_rename.c @@ -17,8 +17,8 @@ static void validate(void) fprintf(stderr, "benchmark doesn't support multi-producer!\n"); exit(1); } - if (env.consumer_cnt != 1) { - fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer!\n"); exit(1); } } @@ -106,17 +106,11 @@ static void setup_fexit(void) attach_bpf(ctx.skel->progs.prog5); } -static void *consumer(void *input) -{ - return NULL; -} - const struct bench bench_rename_base = { .name = "rename-base", .validate = validate, .setup = setup_base, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -127,7 +121,6 @@ const struct bench bench_rename_kprobe = { .validate = validate, .setup = setup_kprobe, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -138,7 +131,6 @@ const struct bench bench_rename_kretprobe = { .validate = validate, .setup = setup_kretprobe, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -149,7 +141,6 @@ const struct bench bench_rename_rawtp = { .validate = validate, .setup = setup_rawtp, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -160,7 +151,6 @@ const struct bench bench_rename_fentry = { .validate = validate, .setup = setup_fentry, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -171,7 +161,6 @@ const struct bench bench_rename_fexit = { .validate = validate, .setup = setup_fexit, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c index fc91fdac4faa5..3ca14ad366071 100644 --- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c +++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c @@ -96,7 +96,7 @@ static inline void bufs_trigger_batch(void) static void bufs_validate(void) { if (env.consumer_cnt != 1) { - fprintf(stderr, "rb-libbpf benchmark doesn't support multi-consumer!\n"); + fprintf(stderr, "rb-libbpf benchmark needs one consumer!\n"); exit(1); } diff --git a/tools/testing/selftests/bpf/benchs/bench_strncmp.c b/tools/testing/selftests/bpf/benchs/bench_strncmp.c index d3fad2ba6916f..a5e1428fd7a0c 100644 --- a/tools/testing/selftests/bpf/benchs/bench_strncmp.c +++ b/tools/testing/selftests/bpf/benchs/bench_strncmp.c @@ -50,8 +50,8 @@ const struct argp bench_strncmp_argp = { static void strncmp_validate(void) { - if (env.consumer_cnt != 1) { - fprintf(stderr, "strncmp benchmark doesn't support multi-consumer!\n"); + if (env.consumer_cnt != 0) { + fprintf(stderr, "strncmp benchmark doesn't support consumer!\n"); exit(1); } } @@ -128,11 +128,6 @@ static void *strncmp_producer(void *ctx) return NULL; } -static void *strncmp_consumer(void *ctx) -{ - return NULL; -} - static void strncmp_measure(struct bench_res *res) { res->hits = atomic_swap(&ctx.skel->bss->hits, 0); @@ -144,7 +139,6 @@ const struct bench bench_strncmp_no_helper = { .validate = strncmp_validate, .setup = strncmp_no_helper_setup, .producer_thread = strncmp_producer, - .consumer_thread = strncmp_consumer, .measure = strncmp_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -156,7 +150,6 @@ const struct bench bench_strncmp_helper = { .validate = strncmp_validate, .setup = strncmp_helper_setup, .producer_thread = strncmp_producer, - .consumer_thread = strncmp_consumer, .measure = strncmp_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c index 0c481de2833d2..dbd362771d6ab 100644 --- a/tools/testing/selftests/bpf/benchs/bench_trigger.c +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -13,8 +13,8 @@ static struct counter base_hits; static void trigger_validate(void) { - if (env.consumer_cnt != 1) { - fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer!\n"); exit(1); } } @@ -103,11 +103,6 @@ static void trigger_fmodret_setup(void) attach_bpf(ctx.skel->progs.bench_trigger_fmodret); } -static void *trigger_consumer(void *input) -{ - return NULL; -} - /* make sure call is not inlined and not avoided by compiler, so __weak and * inline asm volatile in the body of the function * @@ -205,7 +200,6 @@ const struct bench bench_trig_base = { .name = "trig-base", .validate = trigger_validate, .producer_thread = trigger_base_producer, - .consumer_thread = trigger_consumer, .measure = trigger_base_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -216,7 +210,6 @@ const struct bench bench_trig_tp = { .validate = trigger_validate, .setup = trigger_tp_setup, .producer_thread = trigger_producer, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -227,7 +220,6 @@ const struct bench bench_trig_rawtp = { .validate = trigger_validate, .setup = trigger_rawtp_setup, .producer_thread = trigger_producer, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -238,7 +230,6 @@ const struct bench bench_trig_kprobe = { .validate = trigger_validate, .setup = trigger_kprobe_setup, .producer_thread = trigger_producer, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -249,7 +240,6 @@ const struct bench bench_trig_fentry = { .validate = trigger_validate, .setup = trigger_fentry_setup, .producer_thread = trigger_producer, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -260,7 +250,6 @@ const struct bench bench_trig_fentry_sleep = { .validate = trigger_validate, .setup = trigger_fentry_sleep_setup, .producer_thread = trigger_producer, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -271,7 +260,6 @@ const struct bench bench_trig_fmodret = { .validate = trigger_validate, .setup = trigger_fmodret_setup, .producer_thread = trigger_producer, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -281,7 +269,6 @@ const struct bench bench_trig_uprobe_base = { .name = "trig-uprobe-base", .setup = NULL, /* no uprobe/uretprobe is attached */ .producer_thread = uprobe_base_producer, - .consumer_thread = trigger_consumer, .measure = trigger_base_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -291,7 +278,6 @@ const struct bench bench_trig_uprobe_with_nop = { .name = "trig-uprobe-with-nop", .setup = uprobe_setup_with_nop, .producer_thread = uprobe_producer_with_nop, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -301,7 +287,6 @@ const struct bench bench_trig_uretprobe_with_nop = { .name = "trig-uretprobe-with-nop", .setup = uretprobe_setup_with_nop, .producer_thread = uprobe_producer_with_nop, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -311,7 +296,6 @@ const struct bench bench_trig_uprobe_without_nop = { .name = "trig-uprobe-without-nop", .setup = uprobe_setup_without_nop, .producer_thread = uprobe_producer_without_nop, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -321,7 +305,6 @@ const struct bench bench_trig_uretprobe_without_nop = { .name = "trig-uretprobe-without-nop", .setup = uretprobe_setup_without_nop, .producer_thread = uprobe_producer_without_nop, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, diff --git a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh index ada028aa90073..91e3567962ffb 100755 --- a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh +++ b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh @@ -4,46 +4,48 @@ source ./benchs/run_common.sh set -eufo pipefail +RUN_RB_BENCH="$RUN_BENCH -c1" + header "Single-producer, parallel producer" for b in rb-libbpf rb-custom pb-libbpf pb-custom; do - summarize $b "$($RUN_BENCH $b)" + summarize $b "$($RUN_RB_BENCH $b)" done header "Single-producer, parallel producer, sampled notification" for b in rb-libbpf rb-custom pb-libbpf pb-custom; do - summarize $b "$($RUN_BENCH --rb-sampled $b)" + summarize $b "$($RUN_RB_BENCH --rb-sampled $b)" done header "Single-producer, back-to-back mode" for b in rb-libbpf rb-custom pb-libbpf pb-custom; do - summarize $b "$($RUN_BENCH --rb-b2b $b)" - summarize $b-sampled "$($RUN_BENCH --rb-sampled --rb-b2b $b)" + summarize $b "$($RUN_RB_BENCH --rb-b2b $b)" + summarize $b-sampled "$($RUN_RB_BENCH --rb-sampled --rb-b2b $b)" done header "Ringbuf back-to-back, effect of sample rate" for b in 1 5 10 25 50 100 250 500 1000 2000 3000; do - summarize "rb-sampled-$b" "$($RUN_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b rb-custom)" + summarize "rb-sampled-$b" "$($RUN_RB_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b rb-custom)" done header "Perfbuf back-to-back, effect of sample rate" for b in 1 5 10 25 50 100 250 500 1000 2000 3000; do - summarize "pb-sampled-$b" "$($RUN_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b pb-custom)" + summarize "pb-sampled-$b" "$($RUN_RB_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b pb-custom)" done header "Ringbuf back-to-back, reserve+commit vs output" -summarize "reserve" "$($RUN_BENCH --rb-b2b rb-custom)" -summarize "output" "$($RUN_BENCH --rb-b2b --rb-use-output rb-custom)" +summarize "reserve" "$($RUN_RB_BENCH --rb-b2b rb-custom)" +summarize "output" "$($RUN_RB_BENCH --rb-b2b --rb-use-output rb-custom)" header "Ringbuf sampled, reserve+commit vs output" -summarize "reserve-sampled" "$($RUN_BENCH --rb-sampled rb-custom)" -summarize "output-sampled" "$($RUN_BENCH --rb-sampled --rb-use-output rb-custom)" +summarize "reserve-sampled" "$($RUN_RB_BENCH --rb-sampled rb-custom)" +summarize "output-sampled" "$($RUN_RB_BENCH --rb-sampled --rb-use-output rb-custom)" header "Single-producer, consumer/producer competing on the same CPU, low batch count" for b in rb-libbpf rb-custom pb-libbpf pb-custom; do - summarize $b "$($RUN_BENCH --rb-batch-cnt 1 --rb-sample-rate 1 --prod-affinity 0 --cons-affinity 0 $b)" + summarize $b "$($RUN_RB_BENCH --rb-batch-cnt 1 --rb-sample-rate 1 --prod-affinity 0 --cons-affinity 0 $b)" done header "Ringbuf, multi-producer contention" for b in 1 2 3 4 8 12 16 20 24 28 32 36 40 44 48 52; do - summarize "rb-libbpf nr_prod $b" "$($RUN_BENCH -p$b --rb-batch-cnt 50 rb-libbpf)" + summarize "rb-libbpf nr_prod $b" "$($RUN_RB_BENCH -p$b --rb-batch-cnt 50 rb-libbpf)" done diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h index 8c993ec8ceea6..642dda0e758ac 100644 --- a/tools/testing/selftests/bpf/bpf_kfuncs.h +++ b/tools/testing/selftests/bpf/bpf_kfuncs.h @@ -35,4 +35,10 @@ extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, __u32 offset, extern void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *ptr, __u32 offset, void *buffer, __u32 buffer__szk) __ksym; +extern int bpf_dynptr_adjust(const struct bpf_dynptr *ptr, __u32 start, __u32 end) __ksym; +extern bool bpf_dynptr_is_null(const struct bpf_dynptr *ptr) __ksym; +extern bool bpf_dynptr_is_rdonly(const struct bpf_dynptr *ptr) __ksym; +extern __u32 bpf_dynptr_size(const struct bpf_dynptr *ptr) __ksym; +extern int bpf_dynptr_clone(const struct bpf_dynptr *ptr, struct bpf_dynptr *clone__init) __ksym; + #endif diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 52785ba671e6c..aaf6ef1201c7b 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -9,6 +9,7 @@ #include <linux/sysfs.h> #include <linux/tracepoint.h> #include "bpf_testmod.h" +#include "bpf_testmod_kfunc.h" #define CREATE_TRACE_POINTS #include "bpf_testmod-events.h" @@ -190,8 +191,6 @@ noinline int bpf_testmod_fentry_test3(char a, int b, u64 c) return a + b + c; } -__diag_pop(); - int bpf_testmod_fentry_ok; noinline ssize_t @@ -272,6 +271,14 @@ bpf_testmod_test_write(struct file *file, struct kobject *kobj, EXPORT_SYMBOL(bpf_testmod_test_write); ALLOW_ERROR_INJECTION(bpf_testmod_test_write, ERRNO); +noinline int bpf_fentry_shadow_test(int a) +{ + return a + 2; +} +EXPORT_SYMBOL_GPL(bpf_fentry_shadow_test); + +__diag_pop(); + static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = { .attr = { .name = "bpf_testmod", .mode = 0666, }, .read = bpf_testmod_test_read, @@ -289,8 +296,171 @@ static const struct btf_kfunc_id_set bpf_testmod_common_kfunc_set = { .set = &bpf_testmod_common_kfunc_ids, }; +__bpf_kfunc u64 bpf_kfunc_call_test1(struct sock *sk, u32 a, u64 b, u32 c, u64 d) +{ + return a + b + c + d; +} + +__bpf_kfunc int bpf_kfunc_call_test2(struct sock *sk, u32 a, u32 b) +{ + return a + b; +} + +__bpf_kfunc struct sock *bpf_kfunc_call_test3(struct sock *sk) +{ + return sk; +} + +__bpf_kfunc long noinline bpf_kfunc_call_test4(signed char a, short b, int c, long d) +{ + /* Provoke the compiler to assume that the caller has sign-extended a, + * b and c on platforms where this is required (e.g. s390x). + */ + return (long)a + (long)b + (long)c + d; +} + +static struct prog_test_ref_kfunc prog_test_struct = { + .a = 42, + .b = 108, + .next = &prog_test_struct, + .cnt = REFCOUNT_INIT(1), +}; + +__bpf_kfunc struct prog_test_ref_kfunc * +bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) +{ + refcount_inc(&prog_test_struct.cnt); + return &prog_test_struct; +} + +__bpf_kfunc void bpf_kfunc_call_test_offset(struct prog_test_ref_kfunc *p) +{ + WARN_ON_ONCE(1); +} + +__bpf_kfunc struct prog_test_member * +bpf_kfunc_call_memb_acquire(void) +{ + WARN_ON_ONCE(1); + return NULL; +} + +__bpf_kfunc void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p) +{ + WARN_ON_ONCE(1); +} + +static int *__bpf_kfunc_call_test_get_mem(struct prog_test_ref_kfunc *p, const int size) +{ + if (size > 2 * sizeof(int)) + return NULL; + + return (int *)p; +} + +__bpf_kfunc int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, + const int rdwr_buf_size) +{ + return __bpf_kfunc_call_test_get_mem(p, rdwr_buf_size); +} + +__bpf_kfunc int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, + const int rdonly_buf_size) +{ + return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size); +} + +/* the next 2 ones can't be really used for testing expect to ensure + * that the verifier rejects the call. + * Acquire functions must return struct pointers, so these ones are + * failing. + */ +__bpf_kfunc int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, + const int rdonly_buf_size) +{ + return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size); +} + +__bpf_kfunc void bpf_kfunc_call_int_mem_release(int *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_mem_len_pass1(void *mem, int mem__sz) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) +{ + /* p != NULL, but p->cnt could be 0 */ +} + +__bpf_kfunc void bpf_kfunc_call_test_destructive(void) +{ +} + +__bpf_kfunc static u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) +{ + return arg; +} + BTF_SET8_START(bpf_testmod_check_kfunc_ids) BTF_ID_FLAGS(func, bpf_testmod_test_mod_kfunc) +BTF_ID_FLAGS(func, bpf_kfunc_call_test1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test2) +BTF_ID_FLAGS(func, bpf_kfunc_call_test3) +BTF_ID_FLAGS(func, bpf_kfunc_call_test4) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_pass1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail2) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_acquire, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_memb_acquire, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_memb1_release, KF_RELEASE) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_get_rdwr_mem, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_get_rdonly_mem, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_acq_rdonly_mem, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_int_mem_release, KF_RELEASE) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass_ctx) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass2) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail2) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail3) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_ref, KF_TRUSTED_ARGS | KF_RCU) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset) BTF_SET8_END(bpf_testmod_check_kfunc_ids) static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = { @@ -298,12 +468,6 @@ static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = { .set = &bpf_testmod_check_kfunc_ids, }; -noinline int bpf_fentry_shadow_test(int a) -{ - return a + 2; -} -EXPORT_SYMBOL_GPL(bpf_fentry_shadow_test); - extern int bpf_fentry_test1(int a); static int bpf_testmod_init(void) @@ -312,6 +476,8 @@ static int bpf_testmod_init(void) ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &bpf_testmod_common_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_testmod_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_testmod_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &bpf_testmod_kfunc_set); if (ret < 0) return ret; if (bpf_fentry_test1(0) < 0) diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h new file mode 100644 index 0000000000000..f5c5b1375c24d --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _BPF_TESTMOD_KFUNC_H +#define _BPF_TESTMOD_KFUNC_H + +#ifndef __KERNEL__ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#else +#define __ksym +struct prog_test_member1 { + int a; +}; + +struct prog_test_member { + struct prog_test_member1 m; + int c; +}; + +struct prog_test_ref_kfunc { + int a; + int b; + struct prog_test_member memb; + struct prog_test_ref_kfunc *next; + refcount_t cnt; +}; +#endif + +struct prog_test_pass1 { + int x0; + struct { + int x1; + struct { + int x2; + struct { + int x3; + }; + }; + }; +}; + +struct prog_test_pass2 { + int len; + short arr1[4]; + struct { + char arr2[4]; + unsigned long arr3[8]; + } x; +}; + +struct prog_test_fail1 { + void *p; + int x; +}; + +struct prog_test_fail2 { + int x8; + struct prog_test_pass1 x; +}; + +struct prog_test_fail3 { + int len; + char arr1[2]; + char arr2[]; +}; + +struct prog_test_ref_kfunc * +bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) __ksym; +void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; +void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) __ksym; + +void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; +int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym; +int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; +int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; +void bpf_kfunc_call_int_mem_release(int *p) __ksym; + +/* The bpf_kfunc_call_test_static_unused_arg is defined as static, + * but bpf program compilation needs to see it as global symbol. + */ +#ifndef __KERNEL__ +u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) __ksym; +#endif + +void bpf_testmod_test_mod_kfunc(int i) __ksym; + +__u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, + __u32 c, __u64 d) __ksym; +int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; +struct sock *bpf_kfunc_call_test3(struct sock *sk) __ksym; +long bpf_kfunc_call_test4(signed char a, short b, int c, long d) __ksym; + +void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) __ksym; +void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) __ksym; +void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) __ksym; +void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym; + +void bpf_kfunc_call_test_destructive(void) __ksym; + +void bpf_kfunc_call_test_offset(struct prog_test_ref_kfunc *p); +struct prog_test_member *bpf_kfunc_call_memb_acquire(void); +void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p); +void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p); +void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p); +void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p); +void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len); +#endif /* _BPF_TESTMOD_KFUNC_H */ diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 63cd4ab70171e..3b350bc313430 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -13,6 +13,9 @@ CONFIG_CGROUP_BPF=y CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_USER_API_HASH=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_BTF=y +CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DYNAMIC_FTRACE=y CONFIG_FPROBE=y CONFIG_FTRACE_SYSCALLS=y @@ -60,6 +63,7 @@ CONFIG_NET_SCH_INGRESS=y CONFIG_NET_SCHED=y CONFIG_NETDEVSIM=y CONFIG_NETFILTER=y +CONFIG_NETFILTER_ADVANCED=y CONFIG_NETFILTER_SYNPROXY=y CONFIG_NETFILTER_XT_CONNMARK=y CONFIG_NETFILTER_XT_MATCH_STATE=y diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 596caa1765820..a105c0cd008a4 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -427,3 +427,26 @@ void close_netns(struct nstoken *token) close(token->orig_netns_fd); free(token); } + +int get_socket_local_port(int sock_fd) +{ + struct sockaddr_storage addr; + socklen_t addrlen = sizeof(addr); + int err; + + err = getsockname(sock_fd, (struct sockaddr *)&addr, &addrlen); + if (err < 0) + return err; + + if (addr.ss_family == AF_INET) { + struct sockaddr_in *sin = (struct sockaddr_in *)&addr; + + return sin->sin_port; + } else if (addr.ss_family == AF_INET6) { + struct sockaddr_in6 *sin = (struct sockaddr_in6 *)&addr; + + return sin->sin6_port; + } + + return -1; +} diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index f882c691b7909..694185644da6b 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -56,6 +56,7 @@ int fastopen_connect(int server_fd, const char *data, unsigned int data_len, int make_sockaddr(int family, const char *addr_str, __u16 port, struct sockaddr_storage *addr, socklen_t *len); char *ping_command(int family); +int get_socket_local_port(int sock_fd); struct nstoken; /** diff --git a/tools/testing/selftests/bpf/prog_tests/arg_parsing.c b/tools/testing/selftests/bpf/prog_tests/arg_parsing.c index b17bfa0e0aacc..bb143de68875c 100644 --- a/tools/testing/selftests/bpf/prog_tests/arg_parsing.c +++ b/tools/testing/selftests/bpf/prog_tests/arg_parsing.c @@ -96,12 +96,80 @@ static void test_parse_test_list(void) goto error; ASSERT_OK(strcmp("*bpf_cookie*", set.tests[0].name), "test name"); ASSERT_OK(strcmp("*trace*", set.tests[0].subtests[0]), "subtest name"); + free_test_filter_set(&set); + + ASSERT_OK(parse_test_list("t/subtest1,t/subtest2", &set, true), + "parsing"); + if (!ASSERT_EQ(set.cnt, 1, "count of test filters")) + goto error; + if (!ASSERT_OK_PTR(set.tests, "test filters initialized")) + goto error; + if (!ASSERT_EQ(set.tests[0].subtest_cnt, 2, "subtest filters count")) + goto error; + ASSERT_OK(strcmp("t", set.tests[0].name), "test name"); + ASSERT_OK(strcmp("subtest1", set.tests[0].subtests[0]), "subtest name"); + ASSERT_OK(strcmp("subtest2", set.tests[0].subtests[1]), "subtest name"); error: free_test_filter_set(&set); } +static void test_parse_test_list_file(void) +{ + struct test_filter_set set; + char tmpfile[80]; + FILE *fp; + int fd; + + snprintf(tmpfile, sizeof(tmpfile), "/tmp/bpf_arg_parsing_test.XXXXXX"); + fd = mkstemp(tmpfile); + if (!ASSERT_GE(fd, 0, "create tmp")) + return; + + fp = fdopen(fd, "w"); + if (!ASSERT_NEQ(fp, NULL, "fdopen tmp")) { + close(fd); + goto out_remove; + } + + fprintf(fp, "# comment\n"); + fprintf(fp, " test_with_spaces \n"); + fprintf(fp, "testA/subtest # comment\n"); + fprintf(fp, "testB#comment with no space\n"); + fprintf(fp, "testB # duplicate\n"); + fprintf(fp, "testA/subtest # subtest duplicate\n"); + fprintf(fp, "testA/subtest2\n"); + fprintf(fp, "testC_no_eof_newline"); + fflush(fp); + + if (!ASSERT_OK(ferror(fp), "prepare tmp")) + goto out_fclose; + + init_test_filter_set(&set); + + ASSERT_OK(parse_test_list_file(tmpfile, &set, true), "parse file"); + + ASSERT_EQ(set.cnt, 4, "test count"); + ASSERT_OK(strcmp("test_with_spaces", set.tests[0].name), "test 0 name"); + ASSERT_EQ(set.tests[0].subtest_cnt, 0, "test 0 subtest count"); + ASSERT_OK(strcmp("testA", set.tests[1].name), "test 1 name"); + ASSERT_EQ(set.tests[1].subtest_cnt, 2, "test 1 subtest count"); + ASSERT_OK(strcmp("subtest", set.tests[1].subtests[0]), "test 1 subtest 0"); + ASSERT_OK(strcmp("subtest2", set.tests[1].subtests[1]), "test 1 subtest 1"); + ASSERT_OK(strcmp("testB", set.tests[2].name), "test 2 name"); + ASSERT_OK(strcmp("testC_no_eof_newline", set.tests[3].name), "test 3 name"); + + free_test_filter_set(&set); + +out_fclose: + fclose(fp); +out_remove: + remove(tmpfile); +} + void test_arg_parsing(void) { if (test__start_subtest("test_parse_test_list")) test_parse_test_list(); + if (test__start_subtest("test_parse_test_list_file")) + test_parse_test_list_file(); } diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c index a4d0cc9d3367e..fe2c502e5089a 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c @@ -11,6 +11,7 @@ #include "ksym_race.skel.h" #include "bpf_mod_race.skel.h" #include "kfunc_call_race.skel.h" +#include "testing_helpers.h" /* This test crafts a race between btf_try_get_module and do_init_module, and * checks whether btf_try_get_module handles the invocation for a well-formed @@ -44,35 +45,10 @@ enum bpf_test_state { static _Atomic enum bpf_test_state state = _TS_INVALID; -static int sys_finit_module(int fd, const char *param_values, int flags) -{ - return syscall(__NR_finit_module, fd, param_values, flags); -} - -static int sys_delete_module(const char *name, unsigned int flags) -{ - return syscall(__NR_delete_module, name, flags); -} - -static int load_module(const char *mod) -{ - int ret, fd; - - fd = open("bpf_testmod.ko", O_RDONLY); - if (fd < 0) - return fd; - - ret = sys_finit_module(fd, "", 0); - close(fd); - if (ret < 0) - return ret; - return 0; -} - static void *load_module_thread(void *p) { - if (!ASSERT_NEQ(load_module("bpf_testmod.ko"), 0, "load_module_thread must fail")) + if (!ASSERT_NEQ(load_bpf_testmod(false), 0, "load_module_thread must fail")) atomic_store(&state, TS_MODULE_LOAD); else atomic_store(&state, TS_MODULE_LOAD_FAIL); @@ -124,7 +100,7 @@ static void test_bpf_mod_race_config(const struct test_config *config) if (!ASSERT_NEQ(fault_addr, MAP_FAILED, "mmap for uffd registration")) return; - if (!ASSERT_OK(sys_delete_module("bpf_testmod", 0), "unload bpf_testmod")) + if (!ASSERT_OK(unload_bpf_testmod(false), "unload bpf_testmod")) goto end_mmap; skel = bpf_mod_race__open(); @@ -202,8 +178,8 @@ end_destroy: bpf_mod_race__destroy(skel); ASSERT_OK(kern_sync_rcu(), "kern_sync_rcu"); end_module: - sys_delete_module("bpf_testmod", 0); - ASSERT_OK(load_module("bpf_testmod.ko"), "restore bpf_testmod"); + unload_bpf_testmod(false); + ASSERT_OK(load_bpf_testmod(false), "restore bpf_testmod"); end_mmap: munmap(fault_addr, 4096); atomic_store(&state, _TS_INVALID); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c new file mode 100644 index 0000000000000..31f1e815f6719 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c @@ -0,0 +1,268 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#define _GNU_SOURCE +#include <test_progs.h> +#include <bpf/btf.h> +#include <fcntl.h> +#include <unistd.h> +#include <linux/unistd.h> +#include <linux/mount.h> +#include <sys/syscall.h> + +static inline int sys_fsopen(const char *fsname, unsigned flags) +{ + return syscall(__NR_fsopen, fsname, flags); +} + +static inline int sys_fsconfig(int fs_fd, unsigned cmd, const char *key, const void *val, int aux) +{ + return syscall(__NR_fsconfig, fs_fd, cmd, key, val, aux); +} + +static inline int sys_fsmount(int fs_fd, unsigned flags, unsigned ms_flags) +{ + return syscall(__NR_fsmount, fs_fd, flags, ms_flags); +} + +__attribute__((unused)) +static inline int sys_move_mount(int from_dfd, const char *from_path, + int to_dfd, const char *to_path, + unsigned int ms_flags) +{ + return syscall(__NR_move_mount, from_dfd, from_path, to_dfd, to_path, ms_flags); +} + +static void bpf_obj_pinning_detached(void) +{ + LIBBPF_OPTS(bpf_obj_pin_opts, pin_opts); + LIBBPF_OPTS(bpf_obj_get_opts, get_opts); + int fs_fd = -1, mnt_fd = -1; + int map_fd = -1, map_fd2 = -1; + int zero = 0, src_value, dst_value, err; + const char *map_name = "fsmount_map"; + + /* A bunch of below UAPI calls are constructed based on reading: + * https://brauner.io/2023/02/28/mounting-into-mount-namespaces.html + */ + + /* create VFS context */ + fs_fd = sys_fsopen("bpf", 0); + if (!ASSERT_GE(fs_fd, 0, "fs_fd")) + goto cleanup; + + /* instantiate FS object */ + err = sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); + if (!ASSERT_OK(err, "fs_create")) + goto cleanup; + + /* create O_PATH fd for detached mount */ + mnt_fd = sys_fsmount(fs_fd, 0, 0); + if (!ASSERT_GE(mnt_fd, 0, "mnt_fd")) + goto cleanup; + + /* If we wanted to expose detached mount in the file system, we'd do + * something like below. But the whole point is that we actually don't + * even have to expose BPF FS in the file system to be able to work + * (pin/get objects) with it. + * + * err = sys_move_mount(mnt_fd, "", -EBADF, mnt_path, MOVE_MOUNT_F_EMPTY_PATH); + * if (!ASSERT_OK(err, "move_mount")) + * goto cleanup; + */ + + /* create BPF map to pin */ + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, map_name, 4, 4, 1, NULL); + if (!ASSERT_GE(map_fd, 0, "map_fd")) + goto cleanup; + + /* pin BPF map into detached BPF FS through mnt_fd */ + pin_opts.file_flags = BPF_F_PATH_FD; + pin_opts.path_fd = mnt_fd; + err = bpf_obj_pin_opts(map_fd, map_name, &pin_opts); + if (!ASSERT_OK(err, "map_pin")) + goto cleanup; + + /* get BPF map from detached BPF FS through mnt_fd */ + get_opts.file_flags = BPF_F_PATH_FD; + get_opts.path_fd = mnt_fd; + map_fd2 = bpf_obj_get_opts(map_name, &get_opts); + if (!ASSERT_GE(map_fd2, 0, "map_get")) + goto cleanup; + + /* update map through one FD */ + src_value = 0xcafebeef; + err = bpf_map_update_elem(map_fd, &zero, &src_value, 0); + ASSERT_OK(err, "map_update"); + + /* check values written/read through different FDs do match */ + dst_value = 0; + err = bpf_map_lookup_elem(map_fd2, &zero, &dst_value); + ASSERT_OK(err, "map_lookup"); + ASSERT_EQ(dst_value, src_value, "map_value_eq1"); + ASSERT_EQ(dst_value, 0xcafebeef, "map_value_eq2"); + +cleanup: + if (map_fd >= 0) + ASSERT_OK(close(map_fd), "close_map_fd"); + if (map_fd2 >= 0) + ASSERT_OK(close(map_fd2), "close_map_fd2"); + if (fs_fd >= 0) + ASSERT_OK(close(fs_fd), "close_fs_fd"); + if (mnt_fd >= 0) + ASSERT_OK(close(mnt_fd), "close_mnt_fd"); +} + +enum path_kind +{ + PATH_STR_ABS, + PATH_STR_REL, + PATH_FD_REL, +}; + +static void validate_pin(int map_fd, const char *map_name, int src_value, + enum path_kind path_kind) +{ + LIBBPF_OPTS(bpf_obj_pin_opts, pin_opts); + char abs_path[PATH_MAX], old_cwd[PATH_MAX]; + const char *pin_path = NULL; + int zero = 0, dst_value, map_fd2, err; + + snprintf(abs_path, sizeof(abs_path), "/sys/fs/bpf/%s", map_name); + old_cwd[0] = '\0'; + + switch (path_kind) { + case PATH_STR_ABS: + /* absolute path */ + pin_path = abs_path; + break; + case PATH_STR_REL: + /* cwd + relative path */ + ASSERT_OK_PTR(getcwd(old_cwd, sizeof(old_cwd)), "getcwd"); + ASSERT_OK(chdir("/sys/fs/bpf"), "chdir"); + pin_path = map_name; + break; + case PATH_FD_REL: + /* dir fd + relative path */ + pin_opts.file_flags = BPF_F_PATH_FD; + pin_opts.path_fd = open("/sys/fs/bpf", O_PATH); + ASSERT_GE(pin_opts.path_fd, 0, "path_fd"); + pin_path = map_name; + break; + } + + /* pin BPF map using specified path definition */ + err = bpf_obj_pin_opts(map_fd, pin_path, &pin_opts); + ASSERT_OK(err, "obj_pin"); + + /* cleanup */ + if (pin_opts.path_fd >= 0) + close(pin_opts.path_fd); + if (old_cwd[0]) + ASSERT_OK(chdir(old_cwd), "restore_cwd"); + + map_fd2 = bpf_obj_get(abs_path); + if (!ASSERT_GE(map_fd2, 0, "map_get")) + goto cleanup; + + /* update map through one FD */ + err = bpf_map_update_elem(map_fd, &zero, &src_value, 0); + ASSERT_OK(err, "map_update"); + + /* check values written/read through different FDs do match */ + dst_value = 0; + err = bpf_map_lookup_elem(map_fd2, &zero, &dst_value); + ASSERT_OK(err, "map_lookup"); + ASSERT_EQ(dst_value, src_value, "map_value_eq"); +cleanup: + if (map_fd2 >= 0) + ASSERT_OK(close(map_fd2), "close_map_fd2"); + unlink(abs_path); +} + +static void validate_get(int map_fd, const char *map_name, int src_value, + enum path_kind path_kind) +{ + LIBBPF_OPTS(bpf_obj_get_opts, get_opts); + char abs_path[PATH_MAX], old_cwd[PATH_MAX]; + const char *pin_path = NULL; + int zero = 0, dst_value, map_fd2, err; + + snprintf(abs_path, sizeof(abs_path), "/sys/fs/bpf/%s", map_name); + /* pin BPF map using specified path definition */ + err = bpf_obj_pin(map_fd, abs_path); + if (!ASSERT_OK(err, "pin_map")) + return; + + old_cwd[0] = '\0'; + + switch (path_kind) { + case PATH_STR_ABS: + /* absolute path */ + pin_path = abs_path; + break; + case PATH_STR_REL: + /* cwd + relative path */ + ASSERT_OK_PTR(getcwd(old_cwd, sizeof(old_cwd)), "getcwd"); + ASSERT_OK(chdir("/sys/fs/bpf"), "chdir"); + pin_path = map_name; + break; + case PATH_FD_REL: + /* dir fd + relative path */ + get_opts.file_flags = BPF_F_PATH_FD; + get_opts.path_fd = open("/sys/fs/bpf", O_PATH); + ASSERT_GE(get_opts.path_fd, 0, "path_fd"); + pin_path = map_name; + break; + } + + map_fd2 = bpf_obj_get_opts(pin_path, &get_opts); + if (!ASSERT_GE(map_fd2, 0, "map_get")) + goto cleanup; + + /* cleanup */ + if (get_opts.path_fd >= 0) + close(get_opts.path_fd); + if (old_cwd[0]) + ASSERT_OK(chdir(old_cwd), "restore_cwd"); + + /* update map through one FD */ + err = bpf_map_update_elem(map_fd, &zero, &src_value, 0); + ASSERT_OK(err, "map_update"); + + /* check values written/read through different FDs do match */ + dst_value = 0; + err = bpf_map_lookup_elem(map_fd2, &zero, &dst_value); + ASSERT_OK(err, "map_lookup"); + ASSERT_EQ(dst_value, src_value, "map_value_eq"); +cleanup: + if (map_fd2 >= 0) + ASSERT_OK(close(map_fd2), "close_map_fd2"); + unlink(abs_path); +} + +static void bpf_obj_pinning_mounted(enum path_kind path_kind) +{ + const char *map_name = "mounted_map"; + int map_fd; + + /* create BPF map to pin */ + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, map_name, 4, 4, 1, NULL); + if (!ASSERT_GE(map_fd, 0, "map_fd")) + return; + + validate_pin(map_fd, map_name, 100 + (int)path_kind, path_kind); + validate_get(map_fd, map_name, 200 + (int)path_kind, path_kind); + ASSERT_OK(close(map_fd), "close_map_fd"); +} + +void test_bpf_obj_pinning() +{ + if (test__start_subtest("detached")) + bpf_obj_pinning_detached(); + if (test__start_subtest("mounted-str-abs")) + bpf_obj_pinning_mounted(PATH_STR_ABS); + if (test__start_subtest("mounted-str-rel")) + bpf_obj_pinning_mounted(PATH_STR_REL); + if (test__start_subtest("mounted-fd-rel")) + bpf_obj_pinning_mounted(PATH_FD_REL); +} diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 210d643fda6c7..4e0cdb5933188 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -3991,6 +3991,46 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid arg#1", }, { + .descr = "decl_tag test #18, decl_tag as the map key type", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_STRUCT_ENC(0, 2, 8), /* [2] */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_MEMBER_ENC(NAME_TBD, 1, 32), + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), /* [3] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0m1\0m2\0tag"), + .map_type = BPF_MAP_TYPE_HASH, + .map_name = "tag_type_check_btf", + .key_size = 8, + .value_size = 4, + .key_type_id = 3, + .value_type_id = 1, + .max_entries = 1, + .map_create_err = true, +}, +{ + .descr = "decl_tag test #19, decl_tag as the map value type", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_STRUCT_ENC(0, 2, 8), /* [2] */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_MEMBER_ENC(NAME_TBD, 1, 32), + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), /* [3] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0m1\0m2\0tag"), + .map_type = BPF_MAP_TYPE_HASH, + .map_name = "tag_type_check_btf", + .key_size = 4, + .value_size = 8, + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 1, + .map_create_err = true, +}, +{ .descr = "type_tag test #1", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c index 4d2fa99273d8e..2bb5773d6f993 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c @@ -25,6 +25,8 @@ static void test_setsockopt_set(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that sets EUNATCH, assert that * we actually get that error when we run setsockopt() */ @@ -59,6 +61,8 @@ static void test_setsockopt_set_and_get(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that sets EUNATCH, and one that gets the * previously set errno. Assert that we get the same errno back. */ @@ -100,6 +104,8 @@ static void test_setsockopt_default_zero(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that gets the previously set errno. * Assert that, without anything setting one, we get 0. */ @@ -134,6 +140,8 @@ static void test_setsockopt_default_zero_and_set(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that gets the previously set errno, and then * one that sets the errno to EUNATCH. Assert that the get does not * see EUNATCH set later, and does not prevent EUNATCH from being set. @@ -177,6 +185,8 @@ static void test_setsockopt_override(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that sets EUNATCH, then one that sets EISCONN, * and then one that gets the exported errno. Assert both the syscall * and the helper sees the last set errno. @@ -224,6 +234,8 @@ static void test_setsockopt_legacy_eperm(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that return a reject without setting errno * (legacy reject), and one that gets the errno. Assert that for * backward compatibility the syscall result in EPERM, and this @@ -268,6 +280,8 @@ static void test_setsockopt_legacy_no_override(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that sets EUNATCH, then one that return a reject * without setting errno, and then one that gets the exported errno. * Assert both the syscall and the helper's errno are unaffected by @@ -319,6 +333,8 @@ static void test_getsockopt_get(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach getsockopt that gets previously set errno. Assert that the * error from kernel is in both ctx_retval_value and retval_value. */ @@ -359,6 +375,8 @@ static void test_getsockopt_override(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach getsockopt that sets retval to -EISCONN. Assert that this * overrides the value from kernel. */ @@ -396,6 +414,8 @@ static void test_getsockopt_retval_sync(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach getsockopt that sets retval to -EISCONN, and one that clears * ctx retval. Assert that the clearing ctx retval is synced to helper * and clears any errors both from kernel and BPF.. diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c index 5338d2ea04603..2a9a30650350e 100644 --- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c +++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c @@ -183,7 +183,7 @@ cleanup: void serial_test_check_mtu(void) { - __u32 mtu_lo; + int mtu_lo; if (test__start_subtest("bpf_check_mtu XDP-attach")) test_check_mtu_xdp_attach(); diff --git a/tools/testing/selftests/bpf/prog_tests/cpumask.c b/tools/testing/selftests/bpf/prog_tests/cpumask.c index cdf4acc18e4c5..756ea8b590b6f 100644 --- a/tools/testing/selftests/bpf/prog_tests/cpumask.c +++ b/tools/testing/selftests/bpf/prog_tests/cpumask.c @@ -10,6 +10,7 @@ static const char * const cpumask_success_testcases[] = { "test_set_clear_cpu", "test_setall_clear_cpu", "test_first_firstzero_cpu", + "test_firstand_nocpu", "test_test_and_set_clear", "test_and_or_xor", "test_intersects_subset", @@ -70,5 +71,6 @@ void test_cpumask(void) verify_success(cpumask_success_testcases[i]); } + RUN_TESTS(cpumask_success); RUN_TESTS(cpumask_failure); } diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c index d176c34a7d2e4..7cfac53c0d58d 100644 --- a/tools/testing/selftests/bpf/prog_tests/dynptr.c +++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c @@ -20,6 +20,14 @@ static struct { {"test_ringbuf", SETUP_SYSCALL_SLEEP}, {"test_skb_readonly", SETUP_SKB_PROG}, {"test_dynptr_skb_data", SETUP_SKB_PROG}, + {"test_adjust", SETUP_SYSCALL_SLEEP}, + {"test_adjust_err", SETUP_SYSCALL_SLEEP}, + {"test_zero_size_dynptr", SETUP_SYSCALL_SLEEP}, + {"test_dynptr_is_null", SETUP_SYSCALL_SLEEP}, + {"test_dynptr_is_rdonly", SETUP_SKB_PROG}, + {"test_dynptr_clone", SETUP_SKB_PROG}, + {"test_dynptr_skb_no_buff", SETUP_SKB_PROG}, + {"test_dynptr_skb_strcmp", SETUP_SKB_PROG}, }; static void verify_success(const char *prog_name, enum test_setup_type setup_type) diff --git a/tools/testing/selftests/bpf/prog_tests/fib_lookup.c b/tools/testing/selftests/bpf/prog_tests/fib_lookup.c index a1e7121058118..2fd05649bad19 100644 --- a/tools/testing/selftests/bpf/prog_tests/fib_lookup.c +++ b/tools/testing/selftests/bpf/prog_tests/fib_lookup.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include <linux/rtnetlink.h> #include <sys/types.h> #include <net/if.h> @@ -15,14 +16,23 @@ #define IPV4_IFACE_ADDR "10.0.0.254" #define IPV4_NUD_FAILED_ADDR "10.0.0.1" #define IPV4_NUD_STALE_ADDR "10.0.0.2" +#define IPV4_TBID_ADDR "172.0.0.254" +#define IPV4_TBID_NET "172.0.0.0" +#define IPV4_TBID_DST "172.0.0.2" +#define IPV6_TBID_ADDR "fd00::FFFF" +#define IPV6_TBID_NET "fd00::" +#define IPV6_TBID_DST "fd00::2" #define DMAC "11:11:11:11:11:11" #define DMAC_INIT { 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, } +#define DMAC2 "01:01:01:01:01:01" +#define DMAC_INIT2 { 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, } struct fib_lookup_test { const char *desc; const char *daddr; int expected_ret; int lookup_flags; + __u32 tbid; __u8 dmac[6]; }; @@ -43,6 +53,22 @@ static const struct fib_lookup_test tests[] = { { .desc = "IPv4 skip neigh", .daddr = IPV4_NUD_FAILED_ADDR, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS, .lookup_flags = BPF_FIB_LOOKUP_SKIP_NEIGH, }, + { .desc = "IPv4 TBID lookup failure", + .daddr = IPV4_TBID_DST, .expected_ret = BPF_FIB_LKUP_RET_NOT_FWDED, + .lookup_flags = BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID, + .tbid = RT_TABLE_MAIN, }, + { .desc = "IPv4 TBID lookup success", + .daddr = IPV4_TBID_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS, + .lookup_flags = BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID, .tbid = 100, + .dmac = DMAC_INIT2, }, + { .desc = "IPv6 TBID lookup failure", + .daddr = IPV6_TBID_DST, .expected_ret = BPF_FIB_LKUP_RET_NOT_FWDED, + .lookup_flags = BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID, + .tbid = RT_TABLE_MAIN, }, + { .desc = "IPv6 TBID lookup success", + .daddr = IPV6_TBID_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS, + .lookup_flags = BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID, .tbid = 100, + .dmac = DMAC_INIT2, }, }; static int ifindex; @@ -53,6 +79,7 @@ static int setup_netns(void) SYS(fail, "ip link add veth1 type veth peer name veth2"); SYS(fail, "ip link set dev veth1 up"); + SYS(fail, "ip link set dev veth2 up"); err = write_sysctl("/proc/sys/net/ipv4/neigh/veth1/gc_stale_time", "900"); if (!ASSERT_OK(err, "write_sysctl(net.ipv4.neigh.veth1.gc_stale_time)")) @@ -70,6 +97,17 @@ static int setup_netns(void) SYS(fail, "ip neigh add %s dev veth1 nud failed", IPV4_NUD_FAILED_ADDR); SYS(fail, "ip neigh add %s dev veth1 lladdr %s nud stale", IPV4_NUD_STALE_ADDR, DMAC); + /* Setup for tbid lookup tests */ + SYS(fail, "ip addr add %s/24 dev veth2", IPV4_TBID_ADDR); + SYS(fail, "ip route del %s/24 dev veth2", IPV4_TBID_NET); + SYS(fail, "ip route add table 100 %s/24 dev veth2", IPV4_TBID_NET); + SYS(fail, "ip neigh add %s dev veth2 lladdr %s nud stale", IPV4_TBID_DST, DMAC2); + + SYS(fail, "ip addr add %s/64 dev veth2", IPV6_TBID_ADDR); + SYS(fail, "ip -6 route del %s/64 dev veth2", IPV6_TBID_NET); + SYS(fail, "ip -6 route add table 100 %s/64 dev veth2", IPV6_TBID_NET); + SYS(fail, "ip neigh add %s dev veth2 lladdr %s nud stale", IPV6_TBID_DST, DMAC2); + err = write_sysctl("/proc/sys/net/ipv4/conf/veth1/forwarding", "1"); if (!ASSERT_OK(err, "write_sysctl(net.ipv4.conf.veth1.forwarding)")) goto fail; @@ -83,7 +121,7 @@ fail: return -1; } -static int set_lookup_params(struct bpf_fib_lookup *params, const char *daddr) +static int set_lookup_params(struct bpf_fib_lookup *params, const struct fib_lookup_test *test) { int ret; @@ -91,8 +129,9 @@ static int set_lookup_params(struct bpf_fib_lookup *params, const char *daddr) params->l4_protocol = IPPROTO_TCP; params->ifindex = ifindex; + params->tbid = test->tbid; - if (inet_pton(AF_INET6, daddr, params->ipv6_dst) == 1) { + if (inet_pton(AF_INET6, test->daddr, params->ipv6_dst) == 1) { params->family = AF_INET6; ret = inet_pton(AF_INET6, IPV6_IFACE_ADDR, params->ipv6_src); if (!ASSERT_EQ(ret, 1, "inet_pton(IPV6_IFACE_ADDR)")) @@ -100,7 +139,7 @@ static int set_lookup_params(struct bpf_fib_lookup *params, const char *daddr) return 0; } - ret = inet_pton(AF_INET, daddr, ¶ms->ipv4_dst); + ret = inet_pton(AF_INET, test->daddr, ¶ms->ipv4_dst); if (!ASSERT_EQ(ret, 1, "convert IP[46] address")) return -1; params->family = AF_INET; @@ -154,13 +193,12 @@ void test_fib_lookup(void) fib_params = &skel->bss->fib_params; for (i = 0; i < ARRAY_SIZE(tests); i++) { - printf("Testing %s\n", tests[i].desc); + printf("Testing %s ", tests[i].desc); - if (set_lookup_params(fib_params, tests[i].daddr)) + if (set_lookup_params(fib_params, &tests[i])) continue; skel->bss->fib_lookup_ret = -1; - skel->bss->lookup_flags = BPF_FIB_LOOKUP_OUTPUT | - tests[i].lookup_flags; + skel->bss->lookup_flags = tests[i].lookup_flags; err = bpf_prog_test_run_opts(prog_fd, &run_opts); if (!ASSERT_OK(err, "bpf_prog_test_run_opts")) @@ -175,7 +213,14 @@ void test_fib_lookup(void) mac_str(expected, tests[i].dmac); mac_str(actual, fib_params->dmac); - printf("dmac expected %s actual %s\n", expected, actual); + printf("dmac expected %s actual %s ", expected, actual); + } + + // ensure tbid is zero'd out after fib lookup. + if (tests[i].lookup_flags & BPF_FIB_LOOKUP_DIRECT) { + if (!ASSERT_EQ(skel->bss->fib_params.tbid, 0, + "expected fib_params.tbid to be zero")) + goto fail; } } diff --git a/tools/testing/selftests/bpf/prog_tests/global_map_resize.c b/tools/testing/selftests/bpf/prog_tests/global_map_resize.c new file mode 100644 index 0000000000000..fd41425d2e5c3 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/global_map_resize.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include <errno.h> +#include <sys/syscall.h> +#include <unistd.h> +#include "test_global_map_resize.skel.h" +#include "test_progs.h" + +static void run_prog_bss_array_sum(void) +{ + (void)syscall(__NR_getpid); +} + +static void run_prog_data_array_sum(void) +{ + (void)syscall(__NR_getuid); +} + +static void global_map_resize_bss_subtest(void) +{ + int err; + struct test_global_map_resize *skel; + struct bpf_map *map; + const __u32 desired_sz = sizeof(skel->bss->sum) + sysconf(_SC_PAGE_SIZE) * 2; + size_t array_len, actual_sz; + + skel = test_global_map_resize__open(); + if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open")) + goto teardown; + + /* set some initial value before resizing. + * it is expected this non-zero value will be preserved + * while resizing. + */ + skel->bss->array[0] = 1; + + /* resize map value and verify the new size */ + map = skel->maps.bss; + err = bpf_map__set_value_size(map, desired_sz); + if (!ASSERT_OK(err, "bpf_map__set_value_size")) + goto teardown; + if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "resize")) + goto teardown; + + /* set the expected number of elements based on the resized array */ + array_len = (desired_sz - sizeof(skel->bss->sum)) / sizeof(skel->bss->array[0]); + if (!ASSERT_GT(array_len, 1, "array_len")) + goto teardown; + + skel->bss = bpf_map__initial_value(skel->maps.bss, &actual_sz); + if (!ASSERT_OK_PTR(skel->bss, "bpf_map__initial_value (ptr)")) + goto teardown; + if (!ASSERT_EQ(actual_sz, desired_sz, "bpf_map__initial_value (size)")) + goto teardown; + + /* fill the newly resized array with ones, + * skipping the first element which was previously set + */ + for (int i = 1; i < array_len; i++) + skel->bss->array[i] = 1; + + /* set global const values before loading */ + skel->rodata->pid = getpid(); + skel->rodata->bss_array_len = array_len; + skel->rodata->data_array_len = 1; + + err = test_global_map_resize__load(skel); + if (!ASSERT_OK(err, "test_global_map_resize__load")) + goto teardown; + err = test_global_map_resize__attach(skel); + if (!ASSERT_OK(err, "test_global_map_resize__attach")) + goto teardown; + + /* run the bpf program which will sum the contents of the array. + * since the array was filled with ones,verify the sum equals array_len + */ + run_prog_bss_array_sum(); + if (!ASSERT_EQ(skel->bss->sum, array_len, "sum")) + goto teardown; + +teardown: + test_global_map_resize__destroy(skel); +} + +static void global_map_resize_data_subtest(void) +{ + int err; + struct test_global_map_resize *skel; + struct bpf_map *map; + const __u32 desired_sz = sysconf(_SC_PAGE_SIZE) * 2; + size_t array_len, actual_sz; + + skel = test_global_map_resize__open(); + if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open")) + goto teardown; + + /* set some initial value before resizing. + * it is expected this non-zero value will be preserved + * while resizing. + */ + skel->data_custom->my_array[0] = 1; + + /* resize map value and verify the new size */ + map = skel->maps.data_custom; + err = bpf_map__set_value_size(map, desired_sz); + if (!ASSERT_OK(err, "bpf_map__set_value_size")) + goto teardown; + if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "resize")) + goto teardown; + + /* set the expected number of elements based on the resized array */ + array_len = (desired_sz - sizeof(skel->bss->sum)) / sizeof(skel->data_custom->my_array[0]); + if (!ASSERT_GT(array_len, 1, "array_len")) + goto teardown; + + skel->data_custom = bpf_map__initial_value(skel->maps.data_custom, &actual_sz); + if (!ASSERT_OK_PTR(skel->data_custom, "bpf_map__initial_value (ptr)")) + goto teardown; + if (!ASSERT_EQ(actual_sz, desired_sz, "bpf_map__initial_value (size)")) + goto teardown; + + /* fill the newly resized array with ones, + * skipping the first element which was previously set + */ + for (int i = 1; i < array_len; i++) + skel->data_custom->my_array[i] = 1; + + /* set global const values before loading */ + skel->rodata->pid = getpid(); + skel->rodata->bss_array_len = 1; + skel->rodata->data_array_len = array_len; + + err = test_global_map_resize__load(skel); + if (!ASSERT_OK(err, "test_global_map_resize__load")) + goto teardown; + err = test_global_map_resize__attach(skel); + if (!ASSERT_OK(err, "test_global_map_resize__attach")) + goto teardown; + + /* run the bpf program which will sum the contents of the array. + * since the array was filled with ones,verify the sum equals array_len + */ + run_prog_data_array_sum(); + if (!ASSERT_EQ(skel->bss->sum, array_len, "sum")) + goto teardown; + +teardown: + test_global_map_resize__destroy(skel); +} + +static void global_map_resize_invalid_subtest(void) +{ + int err; + struct test_global_map_resize *skel; + struct bpf_map *map; + __u32 element_sz, desired_sz; + + skel = test_global_map_resize__open(); + if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open")) + return; + + /* attempt to resize a global datasec map to size + * which does NOT align with array + */ + map = skel->maps.data_custom; + if (!ASSERT_NEQ(bpf_map__btf_value_type_id(map), 0, ".data.custom initial btf")) + goto teardown; + /* set desired size a fraction of element size beyond an aligned size */ + element_sz = sizeof(skel->data_custom->my_array[0]); + desired_sz = element_sz + element_sz / 2; + /* confirm desired size does NOT align with array */ + if (!ASSERT_NEQ(desired_sz % element_sz, 0, "my_array alignment")) + goto teardown; + err = bpf_map__set_value_size(map, desired_sz); + /* confirm resize is OK but BTF info is cleared */ + if (!ASSERT_OK(err, ".data.custom bpf_map__set_value_size") || + !ASSERT_EQ(bpf_map__btf_key_type_id(map), 0, ".data.custom clear btf key") || + !ASSERT_EQ(bpf_map__btf_value_type_id(map), 0, ".data.custom clear btf val")) + goto teardown; + + /* attempt to resize a global datasec map whose only var is NOT an array */ + map = skel->maps.data_non_array; + if (!ASSERT_NEQ(bpf_map__btf_value_type_id(map), 0, ".data.non_array initial btf")) + goto teardown; + /* set desired size to arbitrary value */ + desired_sz = 1024; + err = bpf_map__set_value_size(map, desired_sz); + /* confirm resize is OK but BTF info is cleared */ + if (!ASSERT_OK(err, ".data.non_array bpf_map__set_value_size") || + !ASSERT_EQ(bpf_map__btf_key_type_id(map), 0, ".data.non_array clear btf key") || + !ASSERT_EQ(bpf_map__btf_value_type_id(map), 0, ".data.non_array clear btf val")) + goto teardown; + + /* attempt to resize a global datasec map + * whose last var is NOT an array + */ + map = skel->maps.data_array_not_last; + if (!ASSERT_NEQ(bpf_map__btf_value_type_id(map), 0, ".data.array_not_last initial btf")) + goto teardown; + /* set desired size to a multiple of element size */ + element_sz = sizeof(skel->data_array_not_last->my_array_first[0]); + desired_sz = element_sz * 8; + /* confirm desired size aligns with array */ + if (!ASSERT_EQ(desired_sz % element_sz, 0, "my_array_first alignment")) + goto teardown; + err = bpf_map__set_value_size(map, desired_sz); + /* confirm resize is OK but BTF info is cleared */ + if (!ASSERT_OK(err, ".data.array_not_last bpf_map__set_value_size") || + !ASSERT_EQ(bpf_map__btf_key_type_id(map), 0, ".data.array_not_last clear btf key") || + !ASSERT_EQ(bpf_map__btf_value_type_id(map), 0, ".data.array_not_last clear btf val")) + goto teardown; + +teardown: + test_global_map_resize__destroy(skel); +} + +void test_global_map_resize(void) +{ + if (test__start_subtest("global_map_resize_bss")) + global_map_resize_bss_subtest(); + + if (test__start_subtest("global_map_resize_data")) + global_map_resize_data_subtest(); + + if (test__start_subtest("global_map_resize_invalid")) + global_map_resize_invalid_subtest(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c b/tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c new file mode 100644 index 0000000000000..9ab4cd1951087 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <test_progs.h> + +#include "inner_array_lookup.skel.h" + +void test_inner_array_lookup(void) +{ + int map1_fd, err; + int key = 3; + int val = 1; + struct inner_array_lookup *skel; + + skel = inner_array_lookup__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_load_skeleton")) + return; + + err = inner_array_lookup__attach(skel); + if (!ASSERT_OK(err, "skeleton_attach")) + goto cleanup; + + map1_fd = bpf_map__fd(skel->maps.inner_map1); + bpf_map_update_elem(map1_fd, &key, &val, 0); + + /* Probe should have set the element at index 3 to 2 */ + bpf_map_lookup_elem(map1_fd, &key, &val); + ASSERT_EQ(val, 2, "value_is_2"); + +cleanup: + inner_array_lookup__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c index 7fc01ff490db7..f53d658ed080b 100644 --- a/tools/testing/selftests/bpf/prog_tests/module_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c @@ -4,6 +4,7 @@ #include <test_progs.h> #include <stdbool.h> #include "test_module_attach.skel.h" +#include "testing_helpers.h" static int duration; @@ -32,11 +33,6 @@ static int trigger_module_test_writable(int *val) return 0; } -static int delete_module(const char *name, int flags) -{ - return syscall(__NR_delete_module, name, flags); -} - void test_module_attach(void) { const int READ_SZ = 456; @@ -93,21 +89,21 @@ void test_module_attach(void) if (!ASSERT_OK_PTR(link, "attach_fentry")) goto cleanup; - ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module"); + ASSERT_ERR(unload_bpf_testmod(false), "unload_bpf_testmod"); bpf_link__destroy(link); link = bpf_program__attach(skel->progs.handle_fexit); if (!ASSERT_OK_PTR(link, "attach_fexit")) goto cleanup; - ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module"); + ASSERT_ERR(unload_bpf_testmod(false), "unload_bpf_testmod"); bpf_link__destroy(link); link = bpf_program__attach(skel->progs.kprobe_multi); if (!ASSERT_OK_PTR(link, "attach_kprobe_multi")) goto cleanup; - ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module"); + ASSERT_ERR(unload_bpf_testmod(false), "unload_bpf_testmod"); bpf_link__destroy(link); cleanup: diff --git a/tools/testing/selftests/bpf/prog_tests/netcnt.c b/tools/testing/selftests/bpf/prog_tests/netcnt.c index d3915c58d0e17..c3333edd029f8 100644 --- a/tools/testing/selftests/bpf/prog_tests/netcnt.c +++ b/tools/testing/selftests/bpf/prog_tests/netcnt.c @@ -67,12 +67,12 @@ void serial_test_netcnt(void) } /* No packets should be lost */ - ASSERT_EQ(packets, 10000, "packets"); + ASSERT_GE(packets, 10000, "packets"); /* Let's check that bytes counter matches the number of packets * multiplied by the size of ipv6 ICMP packet. */ - ASSERT_EQ(bytes, packets * 104, "bytes"); + ASSERT_GE(bytes, packets * 104, "bytes"); err: if (cg_fd != -1) diff --git a/tools/testing/selftests/bpf/prog_tests/sock_destroy.c b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c new file mode 100644 index 0000000000000..b0583309a94e1 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c @@ -0,0 +1,221 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <bpf/bpf_endian.h> + +#include "sock_destroy_prog.skel.h" +#include "sock_destroy_prog_fail.skel.h" +#include "network_helpers.h" + +#define TEST_NS "sock_destroy_netns" + +static void start_iter_sockets(struct bpf_program *prog) +{ + struct bpf_link *link; + char buf[50] = {}; + int iter_fd, len; + + link = bpf_program__attach_iter(prog, NULL); + if (!ASSERT_OK_PTR(link, "attach_iter")) + return; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (!ASSERT_GE(iter_fd, 0, "create_iter")) + goto free_link; + + while ((len = read(iter_fd, buf, sizeof(buf))) > 0) + ; + ASSERT_GE(len, 0, "read"); + + close(iter_fd); + +free_link: + bpf_link__destroy(link); +} + +static void test_tcp_client(struct sock_destroy_prog *skel) +{ + int serv = -1, clien = -1, accept_serv = -1, n; + + serv = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); + if (!ASSERT_GE(serv, 0, "start_server")) + goto cleanup; + + clien = connect_to_fd(serv, 0); + if (!ASSERT_GE(clien, 0, "connect_to_fd")) + goto cleanup; + + accept_serv = accept(serv, NULL, NULL); + if (!ASSERT_GE(accept_serv, 0, "serv accept")) + goto cleanup; + + n = send(clien, "t", 1, 0); + if (!ASSERT_EQ(n, 1, "client send")) + goto cleanup; + + /* Run iterator program that destroys connected client sockets. */ + start_iter_sockets(skel->progs.iter_tcp6_client); + + n = send(clien, "t", 1, 0); + if (!ASSERT_LT(n, 0, "client_send on destroyed socket")) + goto cleanup; + ASSERT_EQ(errno, ECONNABORTED, "error code on destroyed socket"); + +cleanup: + if (clien != -1) + close(clien); + if (accept_serv != -1) + close(accept_serv); + if (serv != -1) + close(serv); +} + +static void test_tcp_server(struct sock_destroy_prog *skel) +{ + int serv = -1, clien = -1, accept_serv = -1, n, serv_port; + + serv = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); + if (!ASSERT_GE(serv, 0, "start_server")) + goto cleanup; + serv_port = get_socket_local_port(serv); + if (!ASSERT_GE(serv_port, 0, "get_sock_local_port")) + goto cleanup; + skel->bss->serv_port = (__be16) serv_port; + + clien = connect_to_fd(serv, 0); + if (!ASSERT_GE(clien, 0, "connect_to_fd")) + goto cleanup; + + accept_serv = accept(serv, NULL, NULL); + if (!ASSERT_GE(accept_serv, 0, "serv accept")) + goto cleanup; + + n = send(clien, "t", 1, 0); + if (!ASSERT_EQ(n, 1, "client send")) + goto cleanup; + + /* Run iterator program that destroys server sockets. */ + start_iter_sockets(skel->progs.iter_tcp6_server); + + n = send(clien, "t", 1, 0); + if (!ASSERT_LT(n, 0, "client_send on destroyed socket")) + goto cleanup; + ASSERT_EQ(errno, ECONNRESET, "error code on destroyed socket"); + +cleanup: + if (clien != -1) + close(clien); + if (accept_serv != -1) + close(accept_serv); + if (serv != -1) + close(serv); +} + +static void test_udp_client(struct sock_destroy_prog *skel) +{ + int serv = -1, clien = -1, n = 0; + + serv = start_server(AF_INET6, SOCK_DGRAM, NULL, 0, 0); + if (!ASSERT_GE(serv, 0, "start_server")) + goto cleanup; + + clien = connect_to_fd(serv, 0); + if (!ASSERT_GE(clien, 0, "connect_to_fd")) + goto cleanup; + + n = send(clien, "t", 1, 0); + if (!ASSERT_EQ(n, 1, "client send")) + goto cleanup; + + /* Run iterator program that destroys sockets. */ + start_iter_sockets(skel->progs.iter_udp6_client); + + n = send(clien, "t", 1, 0); + if (!ASSERT_LT(n, 0, "client_send on destroyed socket")) + goto cleanup; + /* UDP sockets have an overriding error code after they are disconnected, + * so we don't check for ECONNABORTED error code. + */ + +cleanup: + if (clien != -1) + close(clien); + if (serv != -1) + close(serv); +} + +static void test_udp_server(struct sock_destroy_prog *skel) +{ + int *listen_fds = NULL, n, i, serv_port; + unsigned int num_listens = 5; + char buf[1]; + + /* Start reuseport servers. */ + listen_fds = start_reuseport_server(AF_INET6, SOCK_DGRAM, + "::1", 0, 0, num_listens); + if (!ASSERT_OK_PTR(listen_fds, "start_reuseport_server")) + goto cleanup; + serv_port = get_socket_local_port(listen_fds[0]); + if (!ASSERT_GE(serv_port, 0, "get_sock_local_port")) + goto cleanup; + skel->bss->serv_port = (__be16) serv_port; + + /* Run iterator program that destroys server sockets. */ + start_iter_sockets(skel->progs.iter_udp6_server); + + for (i = 0; i < num_listens; ++i) { + n = read(listen_fds[i], buf, sizeof(buf)); + if (!ASSERT_EQ(n, -1, "read") || + !ASSERT_EQ(errno, ECONNABORTED, "error code on destroyed socket")) + break; + } + ASSERT_EQ(i, num_listens, "server socket"); + +cleanup: + free_fds(listen_fds, num_listens); +} + +void test_sock_destroy(void) +{ + struct sock_destroy_prog *skel; + struct nstoken *nstoken = NULL; + int cgroup_fd; + + skel = sock_destroy_prog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + cgroup_fd = test__join_cgroup("/sock_destroy"); + if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup")) + goto cleanup; + + skel->links.sock_connect = bpf_program__attach_cgroup( + skel->progs.sock_connect, cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.sock_connect, "prog_attach")) + goto cleanup; + + SYS(cleanup, "ip netns add %s", TEST_NS); + SYS(cleanup, "ip -net %s link set dev lo up", TEST_NS); + + nstoken = open_netns(TEST_NS); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto cleanup; + + if (test__start_subtest("tcp_client")) + test_tcp_client(skel); + if (test__start_subtest("tcp_server")) + test_tcp_server(skel); + if (test__start_subtest("udp_client")) + test_udp_client(skel); + if (test__start_subtest("udp_server")) + test_udp_server(skel); + + RUN_TESTS(sock_destroy_prog_fail); + +cleanup: + if (nstoken) + close_netns(nstoken); + SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null"); + if (cgroup_fd >= 0) + close(cgroup_fd); + sock_destroy_prog__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 0ce25a967481e..064cc5e8d9ade 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -2,6 +2,7 @@ // Copyright (c) 2020 Cloudflare #include <error.h> #include <netinet/tcp.h> +#include <sys/epoll.h> #include "test_progs.h" #include "test_skmsg_load_helpers.skel.h" @@ -9,8 +10,12 @@ #include "test_sockmap_invalid_update.skel.h" #include "test_sockmap_skb_verdict_attach.skel.h" #include "test_sockmap_progs_query.skel.h" +#include "test_sockmap_pass_prog.skel.h" +#include "test_sockmap_drop_prog.skel.h" #include "bpf_iter_sockmap.skel.h" +#include "sockmap_helpers.h" + #define TCP_REPAIR 19 /* TCP sock is under repair right now */ #define TCP_REPAIR_ON 1 @@ -350,6 +355,126 @@ out: test_sockmap_progs_query__destroy(skel); } +#define MAX_EVENTS 10 +static void test_sockmap_skb_verdict_shutdown(void) +{ + struct epoll_event ev, events[MAX_EVENTS]; + int n, err, map, verdict, s, c1, p1; + struct test_sockmap_pass_prog *skel; + int epollfd; + int zero = 0; + char b; + + skel = test_sockmap_pass_prog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + verdict = bpf_program__fd(skel->progs.prog_skb_verdict); + map = bpf_map__fd(skel->maps.sock_map_rx); + + err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out; + + s = socket_loopback(AF_INET, SOCK_STREAM); + if (s < 0) + goto out; + err = create_pair(s, AF_INET, SOCK_STREAM, &c1, &p1); + if (err < 0) + goto out; + + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (err < 0) + goto out_close; + + shutdown(p1, SHUT_WR); + + ev.events = EPOLLIN; + ev.data.fd = c1; + + epollfd = epoll_create1(0); + if (!ASSERT_GT(epollfd, -1, "epoll_create(0)")) + goto out_close; + err = epoll_ctl(epollfd, EPOLL_CTL_ADD, c1, &ev); + if (!ASSERT_OK(err, "epoll_ctl(EPOLL_CTL_ADD)")) + goto out_close; + err = epoll_wait(epollfd, events, MAX_EVENTS, -1); + if (!ASSERT_EQ(err, 1, "epoll_wait(fd)")) + goto out_close; + + n = recv(c1, &b, 1, SOCK_NONBLOCK); + ASSERT_EQ(n, 0, "recv_timeout(fin)"); +out_close: + close(c1); + close(p1); +out: + test_sockmap_pass_prog__destroy(skel); +} + +static void test_sockmap_skb_verdict_fionread(bool pass_prog) +{ + int expected, zero = 0, sent, recvd, avail; + int err, map, verdict, s, c0, c1, p0, p1; + struct test_sockmap_pass_prog *pass; + struct test_sockmap_drop_prog *drop; + char buf[256] = "0123456789"; + + if (pass_prog) { + pass = test_sockmap_pass_prog__open_and_load(); + if (!ASSERT_OK_PTR(pass, "open_and_load")) + return; + verdict = bpf_program__fd(pass->progs.prog_skb_verdict); + map = bpf_map__fd(pass->maps.sock_map_rx); + expected = sizeof(buf); + } else { + drop = test_sockmap_drop_prog__open_and_load(); + if (!ASSERT_OK_PTR(drop, "open_and_load")) + return; + verdict = bpf_program__fd(drop->progs.prog_skb_verdict); + map = bpf_map__fd(drop->maps.sock_map_rx); + /* On drop data is consumed immediately and copied_seq inc'd */ + expected = 0; + } + + + err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out; + + s = socket_loopback(AF_INET, SOCK_STREAM); + if (!ASSERT_GT(s, -1, "socket_loopback(s)")) + goto out; + err = create_socket_pairs(s, AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1); + if (!ASSERT_OK(err, "create_socket_pairs(s)")) + goto out; + + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(c1)")) + goto out_close; + + sent = xsend(p1, &buf, sizeof(buf), 0); + ASSERT_EQ(sent, sizeof(buf), "xsend(p0)"); + err = ioctl(c1, FIONREAD, &avail); + ASSERT_OK(err, "ioctl(FIONREAD) error"); + ASSERT_EQ(avail, expected, "ioctl(FIONREAD)"); + /* On DROP test there will be no data to read */ + if (pass_prog) { + recvd = recv_timeout(c1, &buf, sizeof(buf), SOCK_NONBLOCK, IO_TIMEOUT_SEC); + ASSERT_EQ(recvd, sizeof(buf), "recv_timeout(c0)"); + } + +out_close: + close(c0); + close(p0); + close(c1); + close(p1); +out: + if (pass_prog) + test_sockmap_pass_prog__destroy(pass); + else + test_sockmap_drop_prog__destroy(drop); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -384,4 +509,10 @@ void test_sockmap_basic(void) test_sockmap_progs_query(BPF_SK_SKB_STREAM_VERDICT); if (test__start_subtest("sockmap skb_verdict progs query")) test_sockmap_progs_query(BPF_SK_SKB_VERDICT); + if (test__start_subtest("sockmap skb_verdict shutdown")) + test_sockmap_skb_verdict_shutdown(); + if (test__start_subtest("sockmap skb_verdict fionread")) + test_sockmap_skb_verdict_fionread(true); + if (test__start_subtest("sockmap skb_verdict fionread on drop")) + test_sockmap_skb_verdict_fionread(false); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h new file mode 100644 index 0000000000000..d12665490a905 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h @@ -0,0 +1,390 @@ +#ifndef __SOCKMAP_HELPERS__ +#define __SOCKMAP_HELPERS__ + +#include <linux/vm_sockets.h> + +#define IO_TIMEOUT_SEC 30 +#define MAX_STRERR_LEN 256 +#define MAX_TEST_NAME 80 + +/* workaround for older vm_sockets.h */ +#ifndef VMADDR_CID_LOCAL +#define VMADDR_CID_LOCAL 1 +#endif + +#define __always_unused __attribute__((__unused__)) + +#define _FAIL(errnum, fmt...) \ + ({ \ + error_at_line(0, (errnum), __func__, __LINE__, fmt); \ + CHECK_FAIL(true); \ + }) +#define FAIL(fmt...) _FAIL(0, fmt) +#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) +#define FAIL_LIBBPF(err, msg) \ + ({ \ + char __buf[MAX_STRERR_LEN]; \ + libbpf_strerror((err), __buf, sizeof(__buf)); \ + FAIL("%s: %s", (msg), __buf); \ + }) + +/* Wrappers that fail the test on error and report it. */ + +#define xaccept_nonblock(fd, addr, len) \ + ({ \ + int __ret = \ + accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("accept"); \ + __ret; \ + }) + +#define xbind(fd, addr, len) \ + ({ \ + int __ret = bind((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("bind"); \ + __ret; \ + }) + +#define xclose(fd) \ + ({ \ + int __ret = close((fd)); \ + if (__ret == -1) \ + FAIL_ERRNO("close"); \ + __ret; \ + }) + +#define xconnect(fd, addr, len) \ + ({ \ + int __ret = connect((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("connect"); \ + __ret; \ + }) + +#define xgetsockname(fd, addr, len) \ + ({ \ + int __ret = getsockname((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockname"); \ + __ret; \ + }) + +#define xgetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = getsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockopt(" #name ")"); \ + __ret; \ + }) + +#define xlisten(fd, backlog) \ + ({ \ + int __ret = listen((fd), (backlog)); \ + if (__ret == -1) \ + FAIL_ERRNO("listen"); \ + __ret; \ + }) + +#define xsetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = setsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("setsockopt(" #name ")"); \ + __ret; \ + }) + +#define xsend(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = send((fd), (buf), (len), (flags)); \ + if (__ret == -1) \ + FAIL_ERRNO("send"); \ + __ret; \ + }) + +#define xrecv_nonblock(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ + IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("recv"); \ + __ret; \ + }) + +#define xsocket(family, sotype, flags) \ + ({ \ + int __ret = socket(family, sotype, flags); \ + if (__ret == -1) \ + FAIL_ERRNO("socket"); \ + __ret; \ + }) + +#define xbpf_map_delete_elem(fd, key) \ + ({ \ + int __ret = bpf_map_delete_elem((fd), (key)); \ + if (__ret < 0) \ + FAIL_ERRNO("map_delete"); \ + __ret; \ + }) + +#define xbpf_map_lookup_elem(fd, key, val) \ + ({ \ + int __ret = bpf_map_lookup_elem((fd), (key), (val)); \ + if (__ret < 0) \ + FAIL_ERRNO("map_lookup"); \ + __ret; \ + }) + +#define xbpf_map_update_elem(fd, key, val, flags) \ + ({ \ + int __ret = bpf_map_update_elem((fd), (key), (val), (flags)); \ + if (__ret < 0) \ + FAIL_ERRNO("map_update"); \ + __ret; \ + }) + +#define xbpf_prog_attach(prog, target, type, flags) \ + ({ \ + int __ret = \ + bpf_prog_attach((prog), (target), (type), (flags)); \ + if (__ret < 0) \ + FAIL_ERRNO("prog_attach(" #type ")"); \ + __ret; \ + }) + +#define xbpf_prog_detach2(prog, target, type) \ + ({ \ + int __ret = bpf_prog_detach2((prog), (target), (type)); \ + if (__ret < 0) \ + FAIL_ERRNO("prog_detach2(" #type ")"); \ + __ret; \ + }) + +#define xpthread_create(thread, attr, func, arg) \ + ({ \ + int __ret = pthread_create((thread), (attr), (func), (arg)); \ + errno = __ret; \ + if (__ret) \ + FAIL_ERRNO("pthread_create"); \ + __ret; \ + }) + +#define xpthread_join(thread, retval) \ + ({ \ + int __ret = pthread_join((thread), (retval)); \ + errno = __ret; \ + if (__ret) \ + FAIL_ERRNO("pthread_join"); \ + __ret; \ + }) + +static inline int poll_read(int fd, unsigned int timeout_sec) +{ + struct timeval timeout = { .tv_sec = timeout_sec }; + fd_set rfds; + int r; + + FD_ZERO(&rfds); + FD_SET(fd, &rfds); + + r = select(fd + 1, &rfds, NULL, NULL, &timeout); + if (r == 0) + errno = ETIME; + + return r == 1 ? 0 : -1; +} + +static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return accept(fd, addr, len); +} + +static inline int recv_timeout(int fd, void *buf, size_t len, int flags, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return recv(fd, buf, len, flags); +} + +static inline void init_addr_loopback4(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); + + addr4->sin_family = AF_INET; + addr4->sin_port = 0; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + *len = sizeof(*addr4); +} + +static inline void init_addr_loopback6(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); + + addr6->sin6_family = AF_INET6; + addr6->sin6_port = 0; + addr6->sin6_addr = in6addr_loopback; + *len = sizeof(*addr6); +} + +static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); + + addr->svm_family = AF_VSOCK; + addr->svm_port = VMADDR_PORT_ANY; + addr->svm_cid = VMADDR_CID_LOCAL; + *len = sizeof(*addr); +} + +static inline void init_addr_loopback(int family, struct sockaddr_storage *ss, + socklen_t *len) +{ + switch (family) { + case AF_INET: + init_addr_loopback4(ss, len); + return; + case AF_INET6: + init_addr_loopback6(ss, len); + return; + case AF_VSOCK: + init_addr_loopback_vsock(ss, len); + return; + default: + FAIL("unsupported address family %d", family); + } +} + +static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) +{ + return (struct sockaddr *)ss; +} + +static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2) +{ + u64 value; + u32 key; + int err; + + key = 0; + value = fd1; + err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); + if (err) + return err; + + key = 1; + value = fd2; + return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); +} + +static inline int create_pair(int s, int family, int sotype, int *c, int *p) +{ + struct sockaddr_storage addr; + socklen_t len; + int err = 0; + + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + return err; + + *c = xsocket(family, sotype, 0); + if (*c < 0) + return errno; + err = xconnect(*c, sockaddr(&addr), len); + if (err) { + err = errno; + goto close_cli0; + } + + *p = xaccept_nonblock(s, NULL, NULL); + if (*p < 0) { + err = errno; + goto close_cli0; + } + return err; +close_cli0: + close(*c); + return err; +} + +static inline int create_socket_pairs(int s, int family, int sotype, + int *c0, int *c1, int *p0, int *p1) +{ + int err; + + err = create_pair(s, family, sotype, c0, p0); + if (err) + return err; + + err = create_pair(s, family, sotype, c1, p1); + if (err) { + close(*c0); + close(*p0); + } + return err; +} + +static inline int enable_reuseport(int s, int progfd) +{ + int err, one = 1; + + err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); + if (err) + return -1; + err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, + sizeof(progfd)); + if (err) + return -1; + + return 0; +} + +static inline int socket_loopback_reuseport(int family, int sotype, int progfd) +{ + struct sockaddr_storage addr; + socklen_t len; + int err, s; + + init_addr_loopback(family, &addr, &len); + + s = xsocket(family, sotype, 0); + if (s == -1) + return -1; + + if (progfd >= 0) + enable_reuseport(s, progfd); + + err = xbind(s, sockaddr(&addr), len); + if (err) + goto close; + + if (sotype & SOCK_DGRAM) + return s; + + err = xlisten(s, SOMAXCONN); + if (err) + goto close; + + return s; +close: + xclose(s); + return -1; +} + +static inline int socket_loopback(int family, int sotype) +{ + return socket_loopback_reuseport(family, sotype, -1); +} + + +#endif // __SOCKMAP_HELPERS__ diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 141c1e5944ee3..b4f6f3a50ae58 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -20,11 +20,6 @@ #include <unistd.h> #include <linux/vm_sockets.h> -/* workaround for older vm_sockets.h */ -#ifndef VMADDR_CID_LOCAL -#define VMADDR_CID_LOCAL 1 -#endif - #include <bpf/bpf.h> #include <bpf/libbpf.h> @@ -32,315 +27,7 @@ #include "test_progs.h" #include "test_sockmap_listen.skel.h" -#define IO_TIMEOUT_SEC 30 -#define MAX_STRERR_LEN 256 -#define MAX_TEST_NAME 80 - -#define __always_unused __attribute__((__unused__)) - -#define _FAIL(errnum, fmt...) \ - ({ \ - error_at_line(0, (errnum), __func__, __LINE__, fmt); \ - CHECK_FAIL(true); \ - }) -#define FAIL(fmt...) _FAIL(0, fmt) -#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) -#define FAIL_LIBBPF(err, msg) \ - ({ \ - char __buf[MAX_STRERR_LEN]; \ - libbpf_strerror((err), __buf, sizeof(__buf)); \ - FAIL("%s: %s", (msg), __buf); \ - }) - -/* Wrappers that fail the test on error and report it. */ - -#define xaccept_nonblock(fd, addr, len) \ - ({ \ - int __ret = \ - accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("accept"); \ - __ret; \ - }) - -#define xbind(fd, addr, len) \ - ({ \ - int __ret = bind((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("bind"); \ - __ret; \ - }) - -#define xclose(fd) \ - ({ \ - int __ret = close((fd)); \ - if (__ret == -1) \ - FAIL_ERRNO("close"); \ - __ret; \ - }) - -#define xconnect(fd, addr, len) \ - ({ \ - int __ret = connect((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("connect"); \ - __ret; \ - }) - -#define xgetsockname(fd, addr, len) \ - ({ \ - int __ret = getsockname((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockname"); \ - __ret; \ - }) - -#define xgetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = getsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockopt(" #name ")"); \ - __ret; \ - }) - -#define xlisten(fd, backlog) \ - ({ \ - int __ret = listen((fd), (backlog)); \ - if (__ret == -1) \ - FAIL_ERRNO("listen"); \ - __ret; \ - }) - -#define xsetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = setsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("setsockopt(" #name ")"); \ - __ret; \ - }) - -#define xsend(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = send((fd), (buf), (len), (flags)); \ - if (__ret == -1) \ - FAIL_ERRNO("send"); \ - __ret; \ - }) - -#define xrecv_nonblock(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ - IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("recv"); \ - __ret; \ - }) - -#define xsocket(family, sotype, flags) \ - ({ \ - int __ret = socket(family, sotype, flags); \ - if (__ret == -1) \ - FAIL_ERRNO("socket"); \ - __ret; \ - }) - -#define xbpf_map_delete_elem(fd, key) \ - ({ \ - int __ret = bpf_map_delete_elem((fd), (key)); \ - if (__ret < 0) \ - FAIL_ERRNO("map_delete"); \ - __ret; \ - }) - -#define xbpf_map_lookup_elem(fd, key, val) \ - ({ \ - int __ret = bpf_map_lookup_elem((fd), (key), (val)); \ - if (__ret < 0) \ - FAIL_ERRNO("map_lookup"); \ - __ret; \ - }) - -#define xbpf_map_update_elem(fd, key, val, flags) \ - ({ \ - int __ret = bpf_map_update_elem((fd), (key), (val), (flags)); \ - if (__ret < 0) \ - FAIL_ERRNO("map_update"); \ - __ret; \ - }) - -#define xbpf_prog_attach(prog, target, type, flags) \ - ({ \ - int __ret = \ - bpf_prog_attach((prog), (target), (type), (flags)); \ - if (__ret < 0) \ - FAIL_ERRNO("prog_attach(" #type ")"); \ - __ret; \ - }) - -#define xbpf_prog_detach2(prog, target, type) \ - ({ \ - int __ret = bpf_prog_detach2((prog), (target), (type)); \ - if (__ret < 0) \ - FAIL_ERRNO("prog_detach2(" #type ")"); \ - __ret; \ - }) - -#define xpthread_create(thread, attr, func, arg) \ - ({ \ - int __ret = pthread_create((thread), (attr), (func), (arg)); \ - errno = __ret; \ - if (__ret) \ - FAIL_ERRNO("pthread_create"); \ - __ret; \ - }) - -#define xpthread_join(thread, retval) \ - ({ \ - int __ret = pthread_join((thread), (retval)); \ - errno = __ret; \ - if (__ret) \ - FAIL_ERRNO("pthread_join"); \ - __ret; \ - }) - -static int poll_read(int fd, unsigned int timeout_sec) -{ - struct timeval timeout = { .tv_sec = timeout_sec }; - fd_set rfds; - int r; - - FD_ZERO(&rfds); - FD_SET(fd, &rfds); - - r = select(fd + 1, &rfds, NULL, NULL, &timeout); - if (r == 0) - errno = ETIME; - - return r == 1 ? 0 : -1; -} - -static int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return accept(fd, addr, len); -} - -static int recv_timeout(int fd, void *buf, size_t len, int flags, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return recv(fd, buf, len, flags); -} - -static void init_addr_loopback4(struct sockaddr_storage *ss, socklen_t *len) -{ - struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); - - addr4->sin_family = AF_INET; - addr4->sin_port = 0; - addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); - *len = sizeof(*addr4); -} - -static void init_addr_loopback6(struct sockaddr_storage *ss, socklen_t *len) -{ - struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); - - addr6->sin6_family = AF_INET6; - addr6->sin6_port = 0; - addr6->sin6_addr = in6addr_loopback; - *len = sizeof(*addr6); -} - -static void init_addr_loopback_vsock(struct sockaddr_storage *ss, socklen_t *len) -{ - struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); - - addr->svm_family = AF_VSOCK; - addr->svm_port = VMADDR_PORT_ANY; - addr->svm_cid = VMADDR_CID_LOCAL; - *len = sizeof(*addr); -} - -static void init_addr_loopback(int family, struct sockaddr_storage *ss, - socklen_t *len) -{ - switch (family) { - case AF_INET: - init_addr_loopback4(ss, len); - return; - case AF_INET6: - init_addr_loopback6(ss, len); - return; - case AF_VSOCK: - init_addr_loopback_vsock(ss, len); - return; - default: - FAIL("unsupported address family %d", family); - } -} - -static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) -{ - return (struct sockaddr *)ss; -} - -static int enable_reuseport(int s, int progfd) -{ - int err, one = 1; - - err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); - if (err) - return -1; - err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, - sizeof(progfd)); - if (err) - return -1; - - return 0; -} - -static int socket_loopback_reuseport(int family, int sotype, int progfd) -{ - struct sockaddr_storage addr; - socklen_t len; - int err, s; - - init_addr_loopback(family, &addr, &len); - - s = xsocket(family, sotype, 0); - if (s == -1) - return -1; - - if (progfd >= 0) - enable_reuseport(s, progfd); - - err = xbind(s, sockaddr(&addr), len); - if (err) - goto close; - - if (sotype & SOCK_DGRAM) - return s; - - err = xlisten(s, SOMAXCONN); - if (err) - goto close; - - return s; -close: - xclose(s); - return -1; -} - -static int socket_loopback(int family, int sotype) -{ - return socket_loopback_reuseport(family, sotype, -1); -} +#include "sockmap_helpers.h" static void test_insert_invalid(struct test_sockmap_listen *skel __always_unused, int family, int sotype, int mapfd) @@ -984,31 +671,12 @@ static const char *redir_mode_str(enum redir_mode mode) } } -static int add_to_sockmap(int sock_mapfd, int fd1, int fd2) -{ - u64 value; - u32 key; - int err; - - key = 0; - value = fd1; - err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); - if (err) - return err; - - key = 1; - value = fd2; - return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); -} - static void redir_to_connected(int family, int sotype, int sock_mapfd, int verd_mapfd, enum redir_mode mode) { const char *log_prefix = redir_mode_str(mode); - struct sockaddr_storage addr; int s, c0, c1, p0, p1; unsigned int pass; - socklen_t len; int err, n; u32 key; char b; @@ -1019,36 +687,13 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (s < 0) return; - len = sizeof(addr); - err = xgetsockname(s, sockaddr(&addr), &len); + err = create_socket_pairs(s, family, sotype, &c0, &c1, &p0, &p1); if (err) goto close_srv; - c0 = xsocket(family, sotype, 0); - if (c0 < 0) - goto close_srv; - err = xconnect(c0, sockaddr(&addr), len); - if (err) - goto close_cli0; - - p0 = xaccept_nonblock(s, NULL, NULL); - if (p0 < 0) - goto close_cli0; - - c1 = xsocket(family, sotype, 0); - if (c1 < 0) - goto close_peer0; - err = xconnect(c1, sockaddr(&addr), len); - if (err) - goto close_cli1; - - p1 = xaccept_nonblock(s, NULL, NULL); - if (p1 < 0) - goto close_cli1; - err = add_to_sockmap(sock_mapfd, p0, p1); if (err) - goto close_peer1; + goto close; n = write(mode == REDIR_INGRESS ? c1 : p1, "a", 1); if (n < 0) @@ -1056,12 +701,12 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (n == 0) FAIL("%s: incomplete write", log_prefix); if (n < 1) - goto close_peer1; + goto close; key = SK_PASS; err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass); if (err) - goto close_peer1; + goto close; if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); n = recv_timeout(c0, &b, 1, 0, IO_TIMEOUT_SEC); @@ -1070,13 +715,10 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (n == 0) FAIL("%s: incomplete recv", log_prefix); -close_peer1: +close: xclose(p1); -close_cli1: xclose(c1); -close_peer0: xclose(p0); -close_cli0: xclose(c0); close_srv: xclose(s); diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt.c b/tools/testing/selftests/bpf/prog_tests/sockopt.c index aa4debf62fc6d..9e6a5e3ed4de5 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt.c @@ -5,10 +5,15 @@ static char bpf_log_buf[4096]; static bool verbose; +#ifndef PAGE_SIZE +#define PAGE_SIZE 4096 +#endif + enum sockopt_test_error { OK = 0, DENY_LOAD, DENY_ATTACH, + EOPNOTSUPP_GETSOCKOPT, EPERM_GETSOCKOPT, EFAULT_GETSOCKOPT, EPERM_SETSOCKOPT, @@ -273,10 +278,31 @@ static struct sockopt_test { .error = EFAULT_GETSOCKOPT, }, { - .descr = "getsockopt: deny arbitrary ctx->retval", + .descr = "getsockopt: ignore >PAGE_SIZE optlen", .insns = { - /* ctx->retval = 123 */ - BPF_MOV64_IMM(BPF_REG_0, 123), + /* write 0xFF to the first optval byte */ + + /* r6 = ctx->optval */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optval)), + /* r2 = ctx->optval */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + /* r6 = ctx->optval + 1 */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + + /* r7 = ctx->optval_end */ + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1, + offsetof(struct bpf_sockopt, optval_end)), + + /* if (ctx->optval + 1 <= ctx->optval_end) { */ + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1), + /* ctx->optval[0] = 0xF0 */ + BPF_ST_MEM(BPF_B, BPF_REG_2, 0, 0xFF), + /* } */ + + /* retval changes are ignored */ + /* ctx->retval = 5 */ + BPF_MOV64_IMM(BPF_REG_0, 5), BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, offsetof(struct bpf_sockopt, retval)), @@ -287,9 +313,11 @@ static struct sockopt_test { .attach_type = BPF_CGROUP_GETSOCKOPT, .expected_attach_type = BPF_CGROUP_GETSOCKOPT, - .get_optlen = 64, - - .error = EFAULT_GETSOCKOPT, + .get_level = 1234, + .get_optname = 5678, + .get_optval = {}, /* the changes are ignored */ + .get_optlen = PAGE_SIZE + 1, + .error = EOPNOTSUPP_GETSOCKOPT, }, { .descr = "getsockopt: support smaller ctx->optlen", @@ -649,6 +677,45 @@ static struct sockopt_test { .error = EFAULT_SETSOCKOPT, }, { + .descr = "setsockopt: ignore >PAGE_SIZE optlen", + .insns = { + /* write 0xFF to the first optval byte */ + + /* r6 = ctx->optval */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optval)), + /* r2 = ctx->optval */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + /* r6 = ctx->optval + 1 */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + + /* r7 = ctx->optval_end */ + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1, + offsetof(struct bpf_sockopt, optval_end)), + + /* if (ctx->optval + 1 <= ctx->optval_end) { */ + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1), + /* ctx->optval[0] = 0xF0 */ + BPF_ST_MEM(BPF_B, BPF_REG_2, 0, 0xF0), + /* } */ + + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .set_level = SOL_IP, + .set_optname = IP_TOS, + .set_optval = {}, + .set_optlen = PAGE_SIZE + 1, + + .get_level = SOL_IP, + .get_optname = IP_TOS, + .get_optval = {}, /* the changes are ignored */ + .get_optlen = 4, + }, + { .descr = "setsockopt: allow changing ctx->optlen within bounds", .insns = { /* r6 = ctx->optval */ @@ -906,6 +973,13 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) } if (test->set_optlen) { + if (test->set_optlen >= PAGE_SIZE) { + int num_pages = test->set_optlen / PAGE_SIZE; + int remainder = test->set_optlen % PAGE_SIZE; + + test->set_optlen = num_pages * sysconf(_SC_PAGESIZE) + remainder; + } + err = setsockopt(sock_fd, test->set_level, test->set_optname, test->set_optval, test->set_optlen); if (err) { @@ -921,7 +995,15 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) } if (test->get_optlen) { + if (test->get_optlen >= PAGE_SIZE) { + int num_pages = test->get_optlen / PAGE_SIZE; + int remainder = test->get_optlen % PAGE_SIZE; + + test->get_optlen = num_pages * sysconf(_SC_PAGESIZE) + remainder; + } + optval = malloc(test->get_optlen); + memset(optval, 0, test->get_optlen); socklen_t optlen = test->get_optlen; socklen_t expected_get_optlen = test->get_optlen_ret ?: test->get_optlen; @@ -929,6 +1011,8 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) err = getsockopt(sock_fd, test->get_level, test->get_optname, optval, &optlen); if (err) { + if (errno == EOPNOTSUPP && test->error == EOPNOTSUPP_GETSOCKOPT) + goto free_optval; if (errno == EPERM && test->error == EPERM_GETSOCKOPT) goto free_optval; if (errno == EFAULT && test->error == EFAULT_GETSOCKOPT) @@ -976,7 +1060,9 @@ void test_sockopt(void) return; for (i = 0; i < ARRAY_SIZE(tests); i++) { - test__start_subtest(tests[i].descr); + if (!test__start_subtest(tests[i].descr)) + continue; + ASSERT_OK(run_test(cgroup_fd, &tests[i]), tests[i].descr); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c index 60c17a8e27899..917f486db8264 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c @@ -2,6 +2,8 @@ #include <test_progs.h> #include "cgroup_helpers.h" +#include "sockopt_inherit.skel.h" + #define SOL_CUSTOM 0xdeadbeef #define CUSTOM_INHERIT1 0 #define CUSTOM_INHERIT2 1 @@ -132,58 +134,30 @@ static int start_server(void) return fd; } -static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title, - const char *prog_name) -{ - enum bpf_attach_type attach_type; - enum bpf_prog_type prog_type; - struct bpf_program *prog; - int err; - - err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); - if (err) { - log_err("Failed to deduct types for %s BPF program", prog_name); - return -1; - } - - prog = bpf_object__find_program_by_name(obj, prog_name); - if (!prog) { - log_err("Failed to find %s BPF program", prog_name); - return -1; - } - - err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, - attach_type, 0); - if (err) { - log_err("Failed to attach %s BPF program", prog_name); - return -1; - } - - return 0; -} - static void run_test(int cgroup_fd) { + struct bpf_link *link_getsockopt = NULL; + struct bpf_link *link_setsockopt = NULL; int server_fd = -1, client_fd; - struct bpf_object *obj; + struct sockopt_inherit *obj; void *server_err; pthread_t tid; int err; - obj = bpf_object__open_file("sockopt_inherit.bpf.o", NULL); - if (!ASSERT_OK_PTR(obj, "obj_open")) + obj = sockopt_inherit__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) return; - err = bpf_object__load(obj); - if (!ASSERT_OK(err, "obj_load")) - goto close_bpf_object; + obj->bss->page_size = sysconf(_SC_PAGESIZE); - err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt", "_getsockopt"); - if (!ASSERT_OK(err, "prog_attach _getsockopt")) + link_getsockopt = bpf_program__attach_cgroup(obj->progs._getsockopt, + cgroup_fd); + if (!ASSERT_OK_PTR(link_getsockopt, "cg-attach-getsockopt")) goto close_bpf_object; - err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt", "_setsockopt"); - if (!ASSERT_OK(err, "prog_attach _setsockopt")) + link_setsockopt = bpf_program__attach_cgroup(obj->progs._setsockopt, + cgroup_fd); + if (!ASSERT_OK_PTR(link_setsockopt, "cg-attach-setsockopt")) goto close_bpf_object; server_fd = start_server(); @@ -217,7 +191,10 @@ static void run_test(int cgroup_fd) close_server_fd: close(server_fd); close_bpf_object: - bpf_object__close(obj); + bpf_link__destroy(link_getsockopt); + bpf_link__destroy(link_setsockopt); + + sockopt_inherit__destroy(obj); } void test_sockopt_inherit(void) diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c index 7f5659349011b..759bbb6f8c5f7 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c @@ -2,61 +2,13 @@ #include <test_progs.h> #include "cgroup_helpers.h" -static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name) -{ - enum bpf_attach_type attach_type; - enum bpf_prog_type prog_type; - struct bpf_program *prog; - int err; - - err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); - if (err) { - log_err("Failed to deduct types for %s BPF program", title); - return -1; - } - - prog = bpf_object__find_program_by_name(obj, name); - if (!prog) { - log_err("Failed to find %s BPF program", name); - return -1; - } - - err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, - attach_type, BPF_F_ALLOW_MULTI); - if (err) { - log_err("Failed to attach %s BPF program", name); - return -1; - } - - return 0; -} +#include "sockopt_multi.skel.h" -static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name) -{ - enum bpf_attach_type attach_type; - enum bpf_prog_type prog_type; - struct bpf_program *prog; - int err; - - err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); - if (err) - return -1; - - prog = bpf_object__find_program_by_name(obj, name); - if (!prog) - return -1; - - err = bpf_prog_detach2(bpf_program__fd(prog), cgroup_fd, - attach_type); - if (err) - return -1; - - return 0; -} - -static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, +static int run_getsockopt_test(struct sockopt_multi *obj, int cg_parent, int cg_child, int sock_fd) { + struct bpf_link *link_parent = NULL; + struct bpf_link *link_child = NULL; socklen_t optlen; __u8 buf; int err; @@ -89,8 +41,9 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - child: 0x80 -> 0x90 */ - err = prog_attach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); - if (err) + link_child = bpf_program__attach_cgroup(obj->progs._getsockopt_child, + cg_child); + if (!ASSERT_OK_PTR(link_child, "cg-attach-getsockopt_child")) goto detach; buf = 0x00; @@ -113,8 +66,9 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - parent: 0x90 -> 0xA0 */ - err = prog_attach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent"); - if (err) + link_parent = bpf_program__attach_cgroup(obj->progs._getsockopt_parent, + cg_parent); + if (!ASSERT_OK_PTR(link_parent, "cg-attach-getsockopt_parent")) goto detach; buf = 0x00; @@ -157,11 +111,8 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - parent: unexpected 0x40, EPERM */ - err = prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); - if (err) { - log_err("Failed to detach child program"); - goto detach; - } + bpf_link__destroy(link_child); + link_child = NULL; buf = 0x00; optlen = 1; @@ -198,15 +149,17 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, } detach: - prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); - prog_detach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent"); + bpf_link__destroy(link_child); + bpf_link__destroy(link_parent); return err; } -static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, +static int run_setsockopt_test(struct sockopt_multi *obj, int cg_parent, int cg_child, int sock_fd) { + struct bpf_link *link_parent = NULL; + struct bpf_link *link_child = NULL; socklen_t optlen; __u8 buf; int err; @@ -236,8 +189,9 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, /* Attach child program and make sure it adds 0x10. */ - err = prog_attach(obj, cg_child, "cgroup/setsockopt", "_setsockopt"); - if (err) + link_child = bpf_program__attach_cgroup(obj->progs._setsockopt, + cg_child); + if (!ASSERT_OK_PTR(link_child, "cg-attach-setsockopt_child")) goto detach; buf = 0x80; @@ -263,8 +217,9 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, /* Attach parent program and make sure it adds another 0x10. */ - err = prog_attach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt"); - if (err) + link_parent = bpf_program__attach_cgroup(obj->progs._setsockopt, + cg_parent); + if (!ASSERT_OK_PTR(link_parent, "cg-attach-setsockopt_parent")) goto detach; buf = 0x80; @@ -289,8 +244,8 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, } detach: - prog_detach(obj, cg_child, "cgroup/setsockopt", "_setsockopt"); - prog_detach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt"); + bpf_link__destroy(link_child); + bpf_link__destroy(link_parent); return err; } @@ -298,9 +253,8 @@ detach: void test_sockopt_multi(void) { int cg_parent = -1, cg_child = -1; - struct bpf_object *obj = NULL; + struct sockopt_multi *obj = NULL; int sock_fd = -1; - int err = -1; cg_parent = test__join_cgroup("/parent"); if (!ASSERT_GE(cg_parent, 0, "join_cgroup /parent")) @@ -310,13 +264,11 @@ void test_sockopt_multi(void) if (!ASSERT_GE(cg_child, 0, "join_cgroup /parent/child")) goto out; - obj = bpf_object__open_file("sockopt_multi.bpf.o", NULL); - if (!ASSERT_OK_PTR(obj, "obj_load")) + obj = sockopt_multi__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) goto out; - err = bpf_object__load(obj); - if (!ASSERT_OK(err, "obj_load")) - goto out; + obj->bss->page_size = sysconf(_SC_PAGESIZE); sock_fd = socket(AF_INET, SOCK_STREAM, 0); if (!ASSERT_GE(sock_fd, 0, "socket")) @@ -327,7 +279,7 @@ void test_sockopt_multi(void) out: close(sock_fd); - bpf_object__close(obj); + sockopt_multi__destroy(obj); close(cg_child); close(cg_parent); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c index 6b53b3cb8dada..6b2d300e9fd40 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c @@ -42,6 +42,8 @@ void test_sockopt_qos_to_cc(void) if (!ASSERT_OK_PTR(skel, "skel")) goto done; + skel->bss->page_size = sysconf(_SC_PAGESIZE); + sock_fd = socket(AF_INET6, SOCK_STREAM, 0); if (!ASSERT_GE(sock_fd, 0, "v6 socket open")) goto done; diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index 4512dd808c335..05d0e07da3942 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -209,7 +209,7 @@ static int getsetsockopt(void) err, errno); goto err; } - ASSERT_EQ(optlen, 4, "Unexpected NETLINK_LIST_MEMBERSHIPS value"); + ASSERT_EQ(optlen, 8, "Unexpected NETLINK_LIST_MEMBERSHIPS value"); free(big_buf); close(fd); diff --git a/tools/testing/selftests/bpf/prog_tests/subprogs_extable.c b/tools/testing/selftests/bpf/prog_tests/subprogs_extable.c new file mode 100644 index 0000000000000..3afd9f775f685 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/subprogs_extable.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include "test_subprogs_extable.skel.h" + +void test_subprogs_extable(void) +{ + const int read_sz = 456; + struct test_subprogs_extable *skel; + int err; + + skel = test_subprogs_extable__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + return; + + err = test_subprogs_extable__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto cleanup; + + /* trigger tracepoint */ + ASSERT_OK(trigger_module_test_read(read_sz), "trigger_read"); + + ASSERT_NEQ(skel->bss->triggered, 0, "verify at least one program ran"); + + test_subprogs_extable__detach(skel); + +cleanup: + test_subprogs_extable__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c b/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c new file mode 100644 index 0000000000000..4224727fb3644 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Bytedance */ + +#include <sys/syscall.h> +#include <test_progs.h> +#include <cgroup_helpers.h> +#include "test_task_under_cgroup.skel.h" + +#define FOO "/foo" + +void test_task_under_cgroup(void) +{ + struct test_task_under_cgroup *skel; + int ret, foo; + pid_t pid; + + foo = test__join_cgroup(FOO); + if (!ASSERT_OK(foo < 0, "cgroup_join_foo")) + return; + + skel = test_task_under_cgroup__open(); + if (!ASSERT_OK_PTR(skel, "test_task_under_cgroup__open")) + goto cleanup; + + skel->rodata->local_pid = getpid(); + skel->bss->remote_pid = getpid(); + skel->rodata->cgid = get_cgroup_id(FOO); + + ret = test_task_under_cgroup__load(skel); + if (!ASSERT_OK(ret, "test_task_under_cgroup__load")) + goto cleanup; + + ret = test_task_under_cgroup__attach(skel); + if (!ASSERT_OK(ret, "test_task_under_cgroup__attach")) + goto cleanup; + + pid = fork(); + if (pid == 0) + exit(0); + + ret = (pid == -1); + if (ASSERT_OK(ret, "fork process")) + wait(NULL); + + test_task_under_cgroup__detach(skel); + + ASSERT_NEQ(skel->bss->remote_pid, skel->rodata->local_pid, + "test task_under_cgroup"); + +cleanup: + test_task_under_cgroup__destroy(skel); + close(foo); +} diff --git a/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c b/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c index 8383a99f610fd..0adf8d9475cb2 100644 --- a/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c +++ b/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c @@ -171,7 +171,11 @@ static void test_unpriv_bpf_disabled_negative(struct test_unpriv_bpf_disabled *s prog_insns, prog_insn_cnt, &load_opts), -EPERM, "prog_load_fails"); - for (i = BPF_MAP_TYPE_HASH; i <= BPF_MAP_TYPE_BLOOM_FILTER; i++) + /* some map types require particular correct parameters which could be + * sanity-checked before enforcing -EPERM, so only validate that + * the simple ARRAY and HASH maps are failing with -EPERM + */ + for (i = BPF_MAP_TYPE_HASH; i <= BPF_MAP_TYPE_ARRAY; i++) ASSERT_EQ(bpf_map_create(i, NULL, sizeof(int), sizeof(int), 1, NULL), -EPERM, "map_create_fails"); diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 2497716ee3790..070a13833c3f0 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -50,11 +50,13 @@ #include "verifier_regalloc.skel.h" #include "verifier_ringbuf.skel.h" #include "verifier_runtime_jit.skel.h" +#include "verifier_scalar_ids.skel.h" #include "verifier_search_pruning.skel.h" #include "verifier_sock.skel.h" #include "verifier_spill_fill.skel.h" #include "verifier_spin_lock.skel.h" #include "verifier_stack_ptr.skel.h" +#include "verifier_subprog_precision.skel.h" #include "verifier_subreg.skel.h" #include "verifier_uninit.skel.h" #include "verifier_unpriv.skel.h" @@ -149,11 +151,13 @@ void test_verifier_ref_tracking(void) { RUN(verifier_ref_tracking); } void test_verifier_regalloc(void) { RUN(verifier_regalloc); } void test_verifier_ringbuf(void) { RUN(verifier_ringbuf); } void test_verifier_runtime_jit(void) { RUN(verifier_runtime_jit); } +void test_verifier_scalar_ids(void) { RUN(verifier_scalar_ids); } void test_verifier_search_pruning(void) { RUN(verifier_search_pruning); } void test_verifier_sock(void) { RUN(verifier_sock); } void test_verifier_spill_fill(void) { RUN(verifier_spill_fill); } void test_verifier_spin_lock(void) { RUN(verifier_spin_lock); } void test_verifier_stack_ptr(void) { RUN(verifier_stack_ptr); } +void test_verifier_subprog_precision(void) { RUN(verifier_subprog_precision); } void test_verifier_subreg(void) { RUN(verifier_subreg); } void test_verifier_uninit(void) { RUN(verifier_uninit); } void test_verifier_unpriv(void) { RUN(verifier_unpriv); } diff --git a/tools/testing/selftests/bpf/prog_tests/vrf_socket_lookup.c b/tools/testing/selftests/bpf/prog_tests/vrf_socket_lookup.c new file mode 100644 index 0000000000000..2a5e207edad61 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/vrf_socket_lookup.c @@ -0,0 +1,312 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + +/* + * Topology: + * --------- + * NS0 namespace | NS1 namespace + * | + * +--------------+ | +--------------+ + * | veth01 |----------| veth10 | + * | 172.16.1.100 | | | 172.16.1.200 | + * | bpf | | +--------------+ + * +--------------+ | + * server(UDP/TCP) | + * +-------------------+ | + * | vrf1 | | + * | +--------------+ | | +--------------+ + * | | veth02 |----------| veth20 | + * | | 172.16.2.100 | | | | 172.16.2.200 | + * | | bpf | | | +--------------+ + * | +--------------+ | | + * | server(UDP/TCP) | | + * +-------------------+ | + * + * Test flow + * ----------- + * The tests verifies that socket lookup via TC is VRF aware: + * 1) Creates two veth pairs between NS0 and NS1: + * a) veth01 <-> veth10 outside the VRF + * b) veth02 <-> veth20 in the VRF + * 2) Attaches to veth01 and veth02 a program that calls: + * a) bpf_skc_lookup_tcp() with TCP and tcp_skc is true + * b) bpf_sk_lookup_tcp() with TCP and tcp_skc is false + * c) bpf_sk_lookup_udp() with UDP + * The program stores the lookup result in bss->lookup_status. + * 3) Creates a socket TCP/UDP server in/outside the VRF. + * 4) The test expects lookup_status to be: + * a) 0 from device in VRF to server outside VRF + * b) 0 from device outside VRF to server in VRF + * c) 1 from device in VRF to server in VRF + * d) 1 from device outside VRF to server outside VRF + */ + +#include <net/if.h> + +#include "test_progs.h" +#include "network_helpers.h" +#include "vrf_socket_lookup.skel.h" + +#define NS0 "vrf_socket_lookup_0" +#define NS1 "vrf_socket_lookup_1" + +#define IP4_ADDR_VETH01 "172.16.1.100" +#define IP4_ADDR_VETH10 "172.16.1.200" +#define IP4_ADDR_VETH02 "172.16.2.100" +#define IP4_ADDR_VETH20 "172.16.2.200" + +#define NON_VRF_PORT 5000 +#define IN_VRF_PORT 5001 + +#define TIMEOUT_MS 3000 + +static int make_socket(int sotype, const char *ip, int port, + struct sockaddr_storage *addr) +{ + int err, fd; + + err = make_sockaddr(AF_INET, ip, port, addr, NULL); + if (!ASSERT_OK(err, "make_address")) + return -1; + + fd = socket(AF_INET, sotype, 0); + if (!ASSERT_GE(fd, 0, "socket")) + return -1; + + if (!ASSERT_OK(settimeo(fd, TIMEOUT_MS), "settimeo")) + goto fail; + + return fd; +fail: + close(fd); + return -1; +} + +static int make_server(int sotype, const char *ip, int port, const char *ifname) +{ + int err, fd = -1; + + fd = start_server(AF_INET, sotype, ip, port, TIMEOUT_MS); + if (!ASSERT_GE(fd, 0, "start_server")) + return -1; + + if (ifname) { + err = setsockopt(fd, SOL_SOCKET, SO_BINDTODEVICE, + ifname, strlen(ifname) + 1); + if (!ASSERT_OK(err, "setsockopt(SO_BINDTODEVICE)")) + goto fail; + } + + return fd; +fail: + close(fd); + return -1; +} + +static int attach_progs(char *ifname, int tc_prog_fd, int xdp_prog_fd) +{ + LIBBPF_OPTS(bpf_tc_hook, hook, .attach_point = BPF_TC_INGRESS); + LIBBPF_OPTS(bpf_tc_opts, opts, .handle = 1, .priority = 1, + .prog_fd = tc_prog_fd); + int ret, ifindex; + + ifindex = if_nametoindex(ifname); + if (!ASSERT_NEQ(ifindex, 0, "if_nametoindex")) + return -1; + hook.ifindex = ifindex; + + ret = bpf_tc_hook_create(&hook); + if (!ASSERT_OK(ret, "bpf_tc_hook_create")) + return ret; + + ret = bpf_tc_attach(&hook, &opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) { + bpf_tc_hook_destroy(&hook); + return ret; + } + ret = bpf_xdp_attach(ifindex, xdp_prog_fd, 0, NULL); + if (!ASSERT_OK(ret, "bpf_xdp_attach")) { + bpf_tc_hook_destroy(&hook); + return ret; + } + + return 0; +} + +static void cleanup(void) +{ + SYS_NOFAIL("test -f /var/run/netns/" NS0 " && ip netns delete " + NS0); + SYS_NOFAIL("test -f /var/run/netns/" NS1 " && ip netns delete " + NS1); +} + +static int setup(struct vrf_socket_lookup *skel) +{ + int tc_prog_fd, xdp_prog_fd, ret = 0; + struct nstoken *nstoken = NULL; + + SYS(fail, "ip netns add " NS0); + SYS(fail, "ip netns add " NS1); + + /* NS0 <-> NS1 [veth01 <-> veth10] */ + SYS(fail, "ip link add veth01 netns " NS0 " type veth peer name veth10" + " netns " NS1); + SYS(fail, "ip -net " NS0 " addr add " IP4_ADDR_VETH01 "/24 dev veth01"); + SYS(fail, "ip -net " NS0 " link set dev veth01 up"); + SYS(fail, "ip -net " NS1 " addr add " IP4_ADDR_VETH10 "/24 dev veth10"); + SYS(fail, "ip -net " NS1 " link set dev veth10 up"); + + /* NS0 <-> NS1 [veth02 <-> veth20] */ + SYS(fail, "ip link add veth02 netns " NS0 " type veth peer name veth20" + " netns " NS1); + SYS(fail, "ip -net " NS0 " addr add " IP4_ADDR_VETH02 "/24 dev veth02"); + SYS(fail, "ip -net " NS0 " link set dev veth02 up"); + SYS(fail, "ip -net " NS1 " addr add " IP4_ADDR_VETH20 "/24 dev veth20"); + SYS(fail, "ip -net " NS1 " link set dev veth20 up"); + + /* veth02 -> vrf1 */ + SYS(fail, "ip -net " NS0 " link add vrf1 type vrf table 11"); + SYS(fail, "ip -net " NS0 " route add vrf vrf1 unreachable default" + " metric 4278198272"); + SYS(fail, "ip -net " NS0 " link set vrf1 alias vrf"); + SYS(fail, "ip -net " NS0 " link set vrf1 up"); + SYS(fail, "ip -net " NS0 " link set veth02 master vrf1"); + + /* Attach TC and XDP progs to veth devices in NS0 */ + nstoken = open_netns(NS0); + if (!ASSERT_OK_PTR(nstoken, "setns " NS0)) + goto fail; + tc_prog_fd = bpf_program__fd(skel->progs.tc_socket_lookup); + if (!ASSERT_GE(tc_prog_fd, 0, "bpf_program__tc_fd")) + goto fail; + xdp_prog_fd = bpf_program__fd(skel->progs.xdp_socket_lookup); + if (!ASSERT_GE(xdp_prog_fd, 0, "bpf_program__xdp_fd")) + goto fail; + + if (attach_progs("veth01", tc_prog_fd, xdp_prog_fd)) + goto fail; + + if (attach_progs("veth02", tc_prog_fd, xdp_prog_fd)) + goto fail; + + goto close; +fail: + ret = -1; +close: + if (nstoken) + close_netns(nstoken); + return ret; +} + +static int test_lookup(struct vrf_socket_lookup *skel, int sotype, + const char *ip, int port, bool test_xdp, bool tcp_skc, + int lookup_status_exp) +{ + static const char msg[] = "Hello Server"; + struct sockaddr_storage addr = {}; + int fd, ret = 0; + + fd = make_socket(sotype, ip, port, &addr); + if (fd < 0) + return -1; + + skel->bss->test_xdp = test_xdp; + skel->bss->tcp_skc = tcp_skc; + skel->bss->lookup_status = -1; + + if (sotype == SOCK_STREAM) + connect(fd, (void *)&addr, sizeof(struct sockaddr_in)); + else + sendto(fd, msg, sizeof(msg), 0, (void *)&addr, + sizeof(struct sockaddr_in)); + + if (!ASSERT_EQ(skel->bss->lookup_status, lookup_status_exp, + "lookup_status")) + goto fail; + + goto close; + +fail: + ret = -1; +close: + close(fd); + return ret; +} + +static void _test_vrf_socket_lookup(struct vrf_socket_lookup *skel, int sotype, + bool test_xdp, bool tcp_skc) +{ + int in_vrf_server = -1, non_vrf_server = -1; + struct nstoken *nstoken = NULL; + + nstoken = open_netns(NS0); + if (!ASSERT_OK_PTR(nstoken, "setns " NS0)) + goto done; + + /* Open sockets in and outside VRF */ + non_vrf_server = make_server(sotype, "0.0.0.0", NON_VRF_PORT, NULL); + if (!ASSERT_GE(non_vrf_server, 0, "make_server__outside_vrf_fd")) + goto done; + + in_vrf_server = make_server(sotype, "0.0.0.0", IN_VRF_PORT, "veth02"); + if (!ASSERT_GE(in_vrf_server, 0, "make_server__in_vrf_fd")) + goto done; + + /* Perform test from NS1 */ + close_netns(nstoken); + nstoken = open_netns(NS1); + if (!ASSERT_OK_PTR(nstoken, "setns " NS1)) + goto done; + + if (!ASSERT_OK(test_lookup(skel, sotype, IP4_ADDR_VETH02, NON_VRF_PORT, + test_xdp, tcp_skc, 0), "in_to_out")) + goto done; + if (!ASSERT_OK(test_lookup(skel, sotype, IP4_ADDR_VETH02, IN_VRF_PORT, + test_xdp, tcp_skc, 1), "in_to_in")) + goto done; + if (!ASSERT_OK(test_lookup(skel, sotype, IP4_ADDR_VETH01, NON_VRF_PORT, + test_xdp, tcp_skc, 1), "out_to_out")) + goto done; + if (!ASSERT_OK(test_lookup(skel, sotype, IP4_ADDR_VETH01, IN_VRF_PORT, + test_xdp, tcp_skc, 0), "out_to_in")) + goto done; + +done: + if (non_vrf_server >= 0) + close(non_vrf_server); + if (in_vrf_server >= 0) + close(in_vrf_server); + if (nstoken) + close_netns(nstoken); +} + +void test_vrf_socket_lookup(void) +{ + struct vrf_socket_lookup *skel; + + cleanup(); + + skel = vrf_socket_lookup__open_and_load(); + if (!ASSERT_OK_PTR(skel, "vrf_socket_lookup__open_and_load")) + return; + + if (!ASSERT_OK(setup(skel), "setup")) + goto done; + + if (test__start_subtest("tc_socket_lookup_tcp")) + _test_vrf_socket_lookup(skel, SOCK_STREAM, false, false); + if (test__start_subtest("tc_socket_lookup_tcp_skc")) + _test_vrf_socket_lookup(skel, SOCK_STREAM, false, false); + if (test__start_subtest("tc_socket_lookup_udp")) + _test_vrf_socket_lookup(skel, SOCK_STREAM, false, false); + if (test__start_subtest("xdp_socket_lookup_tcp")) + _test_vrf_socket_lookup(skel, SOCK_STREAM, true, false); + if (test__start_subtest("xdp_socket_lookup_tcp_skc")) + _test_vrf_socket_lookup(skel, SOCK_STREAM, true, false); + if (test__start_subtest("xdp_socket_lookup_udp")) + _test_vrf_socket_lookup(skel, SOCK_STREAM, true, false); + +done: + vrf_socket_lookup__destroy(skel); + cleanup(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c index d19f79048ff6f..c3b45745cbccd 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c @@ -18,6 +18,7 @@ #include <linux/if_bonding.h> #include <linux/limits.h> #include <linux/udp.h> +#include <uapi/linux/netdev.h> #include "xdp_dummy.skel.h" #include "xdp_redirect_multi_kern.skel.h" @@ -492,6 +493,123 @@ out: system("ip link del bond_nest2"); } +static void test_xdp_bonding_features(struct skeletons *skeletons) +{ + LIBBPF_OPTS(bpf_xdp_query_opts, query_opts); + int bond_idx, veth1_idx, err; + struct bpf_link *link = NULL; + + if (!ASSERT_OK(system("ip link add bond type bond"), "add bond")) + goto out; + + bond_idx = if_nametoindex("bond"); + if (!ASSERT_GE(bond_idx, 0, "if_nametoindex bond")) + goto out; + + /* query default xdp-feature for bond device */ + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK, + "bond query_opts.feature_flags")) + goto out; + + if (!ASSERT_OK(system("ip link add veth0 type veth peer name veth1"), + "add veth{0,1} pair")) + goto out; + + if (!ASSERT_OK(system("ip link add veth2 type veth peer name veth3"), + "add veth{2,3} pair")) + goto out; + + if (!ASSERT_OK(system("ip link set veth0 master bond"), + "add veth0 to master bond")) + goto out; + + /* xdp-feature for bond device should be obtained from the single slave + * device (veth0) + */ + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG, + "bond query_opts.feature_flags")) + goto out; + + veth1_idx = if_nametoindex("veth1"); + if (!ASSERT_GE(veth1_idx, 0, "if_nametoindex veth1")) + goto out; + + link = bpf_program__attach_xdp(skeletons->xdp_dummy->progs.xdp_dummy_prog, + veth1_idx); + if (!ASSERT_OK_PTR(link, "attach program to veth1")) + goto out; + + /* xdp-feature for veth0 are changed */ + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG | NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "bond query_opts.feature_flags")) + goto out; + + if (!ASSERT_OK(system("ip link set veth2 master bond"), + "add veth2 to master bond")) + goto out; + + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + /* xdp-feature for bond device should be set to the most restrict + * value obtained from attached slave devices (veth0 and veth2) + */ + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG, + "bond query_opts.feature_flags")) + goto out; + + if (!ASSERT_OK(system("ip link set veth2 nomaster"), + "del veth2 to master bond")) + goto out; + + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG | NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "bond query_opts.feature_flags")) + goto out; + + if (!ASSERT_OK(system("ip link set veth0 nomaster"), + "del veth0 to master bond")) + goto out; + + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK, + "bond query_opts.feature_flags"); +out: + bpf_link__destroy(link); + system("ip link del veth0"); + system("ip link del veth2"); + system("ip link del bond"); +} + static int libbpf_debug_print(enum libbpf_print_level level, const char *format, va_list args) { @@ -546,6 +664,9 @@ void serial_test_xdp_bonding(void) if (test__start_subtest("xdp_bonding_nested")) test_xdp_bonding_nested(&skeletons); + if (test__start_subtest("xdp_bonding_features")) + test_xdp_bonding_features(&skeletons); + for (i = 0; i < ARRAY_SIZE(bond_test_cases); i++) { struct bond_test_case *test_case = &bond_test_cases[i]; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c b/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c index 5ddcc46fd8868..521267818f4dd 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c @@ -59,9 +59,7 @@ int dump_ksym(struct bpf_iter__ksym *ctx) } else { BPF_SEQ_PRINTF(seq, "0x%llx %c %s ", value, type, iter->name); } - if (!iter->pos_arch_end || iter->pos_arch_end > iter->pos) - BPF_SEQ_PRINTF(seq, "CORE "); - else if (!iter->pos_mod_end || iter->pos_mod_end > iter->pos) + if (!iter->pos_mod_end || iter->pos_mod_end > iter->pos) BPF_SEQ_PRINTF(seq, "MOD "); else if (!iter->pos_ftrace_mod_end || iter->pos_ftrace_mod_end > iter->pos) BPF_SEQ_PRINTF(seq, "FTRACE_MOD "); diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h index d3c1217ba79ab..38a57a2e70dbe 100644 --- a/tools/testing/selftests/bpf/progs/bpf_misc.h +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -86,6 +86,10 @@ #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 +#ifndef __used +#define __used __attribute__((used)) +#endif + #if defined(__TARGET_ARCH_x86) #define SYSCALL_WRAPPER 1 #define SYS_PREFIX "__x64_" diff --git a/tools/testing/selftests/bpf/progs/cb_refs.c b/tools/testing/selftests/bpf/progs/cb_refs.c index 50f95ec611650..76d661b20e87d 100644 --- a/tools/testing/selftests/bpf/progs/cb_refs.c +++ b/tools/testing/selftests/bpf/progs/cb_refs.c @@ -2,6 +2,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct map_value { struct prog_test_ref_kfunc __kptr *ptr; @@ -14,9 +15,6 @@ struct { __uint(max_entries, 16); } array_map SEC(".maps"); -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; - static __noinline int cb1(void *map, void *key, void *value, void *ctx) { void *p = *(void **)ctx; diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c index b2a409e6382a4..932b8ecd4ae33 100644 --- a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c @@ -12,6 +12,7 @@ __u32 invocations = 0; __u32 assertion_error = 0; __u32 retval_value = 0; __u32 ctx_retval_value = 0; +__u32 page_size = 0; SEC("cgroup/getsockopt") int get_retval(struct bpf_sockopt *ctx) @@ -20,6 +21,10 @@ int get_retval(struct bpf_sockopt *ctx) ctx_retval_value = ctx->retval; __sync_fetch_and_add(&invocations, 1); + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } @@ -31,6 +36,10 @@ int set_eisconn(struct bpf_sockopt *ctx) if (bpf_set_retval(-EISCONN)) assertion_error = 1; + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } @@ -41,5 +50,9 @@ int clear_retval(struct bpf_sockopt *ctx) ctx->retval = 0; + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c index d6e5903e06ba0..b7fa8804e19de 100644 --- a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c @@ -11,6 +11,7 @@ __u32 invocations = 0; __u32 assertion_error = 0; __u32 retval_value = 0; +__u32 page_size = 0; SEC("cgroup/setsockopt") int get_retval(struct bpf_sockopt *ctx) @@ -18,6 +19,10 @@ int get_retval(struct bpf_sockopt *ctx) retval_value = bpf_get_retval(); __sync_fetch_and_add(&invocations, 1); + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } @@ -29,6 +34,10 @@ int set_eunatch(struct bpf_sockopt *ctx) if (bpf_set_retval(-EUNATCH)) assertion_error = 1; + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 0; } @@ -40,6 +49,10 @@ int set_eisconn(struct bpf_sockopt *ctx) if (bpf_set_retval(-EISCONN)) assertion_error = 1; + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 0; } @@ -48,5 +61,9 @@ int legacy_eperm(struct bpf_sockopt *ctx) { __sync_fetch_and_add(&invocations, 1); + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 0; } diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h index 0c5b785a93e45..b15c588ace15d 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_common.h +++ b/tools/testing/selftests/bpf/progs/cpumask_common.h @@ -28,6 +28,8 @@ void bpf_cpumask_release(struct bpf_cpumask *cpumask) __ksym; struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) __ksym; u32 bpf_cpumask_first(const struct cpumask *cpumask) __ksym; u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym; +u32 bpf_cpumask_first_and(const struct cpumask *src1, + const struct cpumask *src2) __ksym; void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym; void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym; bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask) __ksym; @@ -50,8 +52,8 @@ bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2) bool bpf_cpumask_empty(const struct cpumask *cpumask) __ksym; bool bpf_cpumask_full(const struct cpumask *cpumask) __ksym; void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym; -u32 bpf_cpumask_any(const struct cpumask *src) __ksym; -u32 bpf_cpumask_any_and(const struct cpumask *src1, const struct cpumask *src2) __ksym; +u32 bpf_cpumask_any_distribute(const struct cpumask *src) __ksym; +u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, const struct cpumask *src2) __ksym; void bpf_rcu_read_lock(void) __ksym; void bpf_rcu_read_unlock(void) __ksym; diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c index 2fcdd7f68ac7a..674a63424dee3 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_success.c +++ b/tools/testing/selftests/bpf/progs/cpumask_success.c @@ -5,6 +5,7 @@ #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" #include "cpumask_common.h" char _license[] SEC("license") = "GPL"; @@ -175,6 +176,38 @@ release_exit: } SEC("tp_btf/task_newtask") +int BPF_PROG(test_firstand_nocpu, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *mask1, *mask2; + u32 first; + + if (!is_test_task()) + return 0; + + mask1 = create_cpumask(); + if (!mask1) + return 0; + + mask2 = create_cpumask(); + if (!mask2) + goto release_exit; + + bpf_cpumask_set_cpu(0, mask1); + bpf_cpumask_set_cpu(1, mask2); + + first = bpf_cpumask_first_and(cast(mask1), cast(mask2)); + if (first <= 1) + err = 3; + +release_exit: + if (mask1) + bpf_cpumask_release(mask1); + if (mask2) + bpf_cpumask_release(mask2); + return 0; +} + +SEC("tp_btf/task_newtask") int BPF_PROG(test_test_and_set_clear, struct task_struct *task, u64 clone_flags) { struct bpf_cpumask *cpumask; @@ -311,13 +344,13 @@ int BPF_PROG(test_copy_any_anyand, struct task_struct *task, u64 clone_flags) bpf_cpumask_set_cpu(1, mask2); bpf_cpumask_or(dst1, cast(mask1), cast(mask2)); - cpu = bpf_cpumask_any(cast(mask1)); + cpu = bpf_cpumask_any_distribute(cast(mask1)); if (cpu != 0) { err = 6; goto release_exit; } - cpu = bpf_cpumask_any(cast(dst2)); + cpu = bpf_cpumask_any_distribute(cast(dst2)); if (cpu < nr_cpus) { err = 7; goto release_exit; @@ -329,13 +362,13 @@ int BPF_PROG(test_copy_any_anyand, struct task_struct *task, u64 clone_flags) goto release_exit; } - cpu = bpf_cpumask_any(cast(dst2)); + cpu = bpf_cpumask_any_distribute(cast(dst2)); if (cpu > 1) { err = 9; goto release_exit; } - cpu = bpf_cpumask_any_and(cast(mask1), cast(mask2)); + cpu = bpf_cpumask_any_and_distribute(cast(mask1), cast(mask2)); if (cpu < nr_cpus) { err = 10; goto release_exit; @@ -426,3 +459,26 @@ int BPF_PROG(test_global_mask_rcu, struct task_struct *task, u64 clone_flags) return 0; } + +SEC("tp_btf/task_newtask") +__success +int BPF_PROG(test_refcount_null_tracking, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *mask1, *mask2; + + mask1 = bpf_cpumask_create(); + mask2 = bpf_cpumask_create(); + + if (!mask1 || !mask2) + goto free_masks_return; + + bpf_cpumask_test_cpu(0, (const struct cpumask *)mask1); + bpf_cpumask_test_cpu(0, (const struct cpumask *)mask2); + +free_masks_return: + if (mask1) + bpf_cpumask_release(mask1); + if (mask2) + bpf_cpumask_release(mask2); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index 759eb5c245cd9..7ce7e827d5f01 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -3,6 +3,7 @@ #include <errno.h> #include <string.h> +#include <stdbool.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include <linux/if_ether.h> @@ -1378,3 +1379,310 @@ int invalid_slice_rdwr_rdonly(struct __sk_buff *skb) return 0; } + +/* bpf_dynptr_adjust can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_adjust_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_adjust(&ptr, 1, 2); + + return 0; +} + +/* bpf_dynptr_is_null can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_is_null_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_is_null(&ptr); + + return 0; +} + +/* bpf_dynptr_is_rdonly can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_is_rdonly_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_is_rdonly(&ptr); + + return 0; +} + +/* bpf_dynptr_size can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_size_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_size(&ptr); + + return 0; +} + +/* Only initialized dynptrs can be cloned */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int clone_invalid1(void *ctx) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + + /* this should fail */ + bpf_dynptr_clone(&ptr1, &ptr2); + + return 0; +} + +/* Can't overwrite an existing dynptr when cloning */ +SEC("?xdp") +__failure __msg("cannot overwrite referenced dynptr") +int clone_invalid2(struct xdp_md *xdp) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr clone; + + bpf_dynptr_from_xdp(xdp, 0, &ptr1); + + bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &clone); + + /* this should fail */ + bpf_dynptr_clone(&ptr1, &clone); + + bpf_ringbuf_submit_dynptr(&clone, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate its clones */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #3") +int clone_invalidate1(void *ctx) +{ + struct bpf_dynptr clone; + struct bpf_dynptr ptr; + char read_data[64]; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + + bpf_ringbuf_submit_dynptr(&ptr, 0); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &clone, 0, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate its parent */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #3") +int clone_invalidate2(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone; + char read_data[64]; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + + bpf_ringbuf_submit_dynptr(&clone, 0); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate its siblings */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #3") +int clone_invalidate3(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone1; + struct bpf_dynptr clone2; + char read_data[64]; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone1); + + bpf_dynptr_clone(&ptr, &clone2); + + bpf_ringbuf_submit_dynptr(&clone2, 0); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &clone1, 0, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate any data slices + * of its clones + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int clone_invalidate4(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone; + int *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + data = bpf_dynptr_data(&clone, 0, sizeof(val)); + if (!data) + return 0; + + bpf_ringbuf_submit_dynptr(&ptr, 0); + + /* this should fail */ + *data = 123; + + return 0; +} + +/* Invalidating a dynptr should invalidate any data slices + * of its parent + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int clone_invalidate5(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone; + int *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + data = bpf_dynptr_data(&ptr, 0, sizeof(val)); + if (!data) + return 0; + + bpf_dynptr_clone(&ptr, &clone); + + bpf_ringbuf_submit_dynptr(&clone, 0); + + /* this should fail */ + *data = 123; + + return 0; +} + +/* Invalidating a dynptr should invalidate any data slices + * of its sibling + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int clone_invalidate6(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone1; + struct bpf_dynptr clone2; + int *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone1); + + bpf_dynptr_clone(&ptr, &clone2); + + data = bpf_dynptr_data(&clone1, 0, sizeof(val)); + if (!data) + return 0; + + bpf_ringbuf_submit_dynptr(&clone2, 0); + + /* this should fail */ + *data = 123; + + return 0; +} + +/* A skb clone's data slices should be invalid anytime packet data changes */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int clone_skb_packet_data(struct __sk_buff *skb) +{ + char buffer[sizeof(__u32)] = {}; + struct bpf_dynptr clone; + struct bpf_dynptr ptr; + __u32 *data; + + bpf_dynptr_from_skb(skb, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + data = bpf_dynptr_slice_rdwr(&clone, 0, buffer, sizeof(buffer)); + if (!data) + return XDP_DROP; + + if (bpf_skb_pull_data(skb, skb->len)) + return SK_DROP; + + /* this should fail */ + *data = 123; + + return 0; +} + +/* A xdp clone's data slices should be invalid anytime packet data changes */ +SEC("?xdp") +__failure __msg("invalid mem access 'scalar'") +int clone_xdp_packet_data(struct xdp_md *xdp) +{ + char buffer[sizeof(__u32)] = {}; + struct bpf_dynptr clone; + struct bpf_dynptr ptr; + struct ethhdr *hdr; + __u32 *data; + + bpf_dynptr_from_xdp(xdp, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + data = bpf_dynptr_slice_rdwr(&clone, 0, buffer, sizeof(buffer)); + if (!data) + return XDP_DROP; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(*hdr))) + return XDP_DROP; + + /* this should fail */ + *data = 123; + + return 0; +} + +/* Buffers that are provided must be sufficiently long */ +SEC("?cgroup_skb/egress") +__failure __msg("memory, len pair leads to invalid memory access") +int test_dynptr_skb_small_buff(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + char buffer[8] = {}; + __u64 *data; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* This may return NULL. SKB may require a buffer */ + data = bpf_dynptr_slice(&ptr, 0, buffer, 9); + + return !!data; +} diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c index b2fa6c47ecc0b..5985920d162e7 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_success.c +++ b/tools/testing/selftests/bpf/progs/dynptr_success.c @@ -2,6 +2,7 @@ /* Copyright (c) 2022 Facebook */ #include <string.h> +#include <stdbool.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include "bpf_misc.h" @@ -207,3 +208,339 @@ int test_dynptr_skb_data(struct __sk_buff *skb) return 1; } + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_adjust(void *ctx) +{ + struct bpf_dynptr ptr; + __u32 bytes = 64; + __u32 off = 10; + __u32 trim = 15; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + err = bpf_ringbuf_reserve_dynptr(&ringbuf, bytes, 0, &ptr); + if (err) { + err = 1; + goto done; + } + + if (bpf_dynptr_size(&ptr) != bytes) { + err = 2; + goto done; + } + + /* Advance the dynptr by off */ + err = bpf_dynptr_adjust(&ptr, off, bpf_dynptr_size(&ptr)); + if (err) { + err = 3; + goto done; + } + + if (bpf_dynptr_size(&ptr) != bytes - off) { + err = 4; + goto done; + } + + /* Trim the dynptr */ + err = bpf_dynptr_adjust(&ptr, off, 15); + if (err) { + err = 5; + goto done; + } + + /* Check that the size was adjusted correctly */ + if (bpf_dynptr_size(&ptr) != trim - off) { + err = 6; + goto done; + } + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_adjust_err(void *ctx) +{ + char write_data[45] = "hello there, world!!"; + struct bpf_dynptr ptr; + __u32 size = 64; + __u32 off = 20; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr)) { + err = 1; + goto done; + } + + /* Check that start can't be greater than end */ + if (bpf_dynptr_adjust(&ptr, 5, 1) != -EINVAL) { + err = 2; + goto done; + } + + /* Check that start can't be greater than size */ + if (bpf_dynptr_adjust(&ptr, size + 1, size + 1) != -ERANGE) { + err = 3; + goto done; + } + + /* Check that end can't be greater than size */ + if (bpf_dynptr_adjust(&ptr, 0, size + 1) != -ERANGE) { + err = 4; + goto done; + } + + if (bpf_dynptr_adjust(&ptr, off, size)) { + err = 5; + goto done; + } + + /* Check that you can't write more bytes than available into the dynptr + * after you've adjusted it + */ + if (bpf_dynptr_write(&ptr, 0, &write_data, sizeof(write_data), 0) != -E2BIG) { + err = 6; + goto done; + } + + /* Check that even after adjusting, submitting/discarding + * a ringbuf dynptr works + */ + bpf_ringbuf_submit_dynptr(&ptr, 0); + return 0; + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_zero_size_dynptr(void *ctx) +{ + char write_data = 'x', read_data; + struct bpf_dynptr ptr; + __u32 size = 64; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr)) { + err = 1; + goto done; + } + + /* After this, the dynptr has a size of 0 */ + if (bpf_dynptr_adjust(&ptr, size, size)) { + err = 2; + goto done; + } + + /* Test that reading + writing non-zero bytes is not ok */ + if (bpf_dynptr_read(&read_data, sizeof(read_data), &ptr, 0, 0) != -E2BIG) { + err = 3; + goto done; + } + + if (bpf_dynptr_write(&ptr, 0, &write_data, sizeof(write_data), 0) != -E2BIG) { + err = 4; + goto done; + } + + /* Test that reading + writing 0 bytes from a 0-size dynptr is ok */ + if (bpf_dynptr_read(&read_data, 0, &ptr, 0, 0)) { + err = 5; + goto done; + } + + if (bpf_dynptr_write(&ptr, 0, &write_data, 0, 0)) { + err = 6; + goto done; + } + + err = 0; + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_dynptr_is_null(void *ctx) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + __u64 size = 4; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + /* Pass in invalid flags, get back an invalid dynptr */ + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 123, &ptr1) != -EINVAL) { + err = 1; + goto exit_early; + } + + /* Test that the invalid dynptr is null */ + if (!bpf_dynptr_is_null(&ptr1)) { + err = 2; + goto exit_early; + } + + /* Get a valid dynptr */ + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr2)) { + err = 3; + goto exit; + } + + /* Test that the valid dynptr is not null */ + if (bpf_dynptr_is_null(&ptr2)) { + err = 4; + goto exit; + } + +exit: + bpf_ringbuf_discard_dynptr(&ptr2, 0); +exit_early: + bpf_ringbuf_discard_dynptr(&ptr1, 0); + return 0; +} + +SEC("cgroup_skb/egress") +int test_dynptr_is_rdonly(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + struct bpf_dynptr ptr3; + + /* Pass in invalid flags, get back an invalid dynptr */ + if (bpf_dynptr_from_skb(skb, 123, &ptr1) != -EINVAL) { + err = 1; + return 0; + } + + /* Test that an invalid dynptr is_rdonly returns false */ + if (bpf_dynptr_is_rdonly(&ptr1)) { + err = 2; + return 0; + } + + /* Get a read-only dynptr */ + if (bpf_dynptr_from_skb(skb, 0, &ptr2)) { + err = 3; + return 0; + } + + /* Test that the dynptr is read-only */ + if (!bpf_dynptr_is_rdonly(&ptr2)) { + err = 4; + return 0; + } + + /* Get a read-writeable dynptr */ + if (bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr3)) { + err = 5; + goto done; + } + + /* Test that the dynptr is read-only */ + if (bpf_dynptr_is_rdonly(&ptr3)) { + err = 6; + goto done; + } + +done: + bpf_ringbuf_discard_dynptr(&ptr3, 0); + return 0; +} + +SEC("cgroup_skb/egress") +int test_dynptr_clone(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + __u32 off = 2, size; + + /* Get a dynptr */ + if (bpf_dynptr_from_skb(skb, 0, &ptr1)) { + err = 1; + return 0; + } + + if (bpf_dynptr_adjust(&ptr1, off, bpf_dynptr_size(&ptr1))) { + err = 2; + return 0; + } + + /* Clone the dynptr */ + if (bpf_dynptr_clone(&ptr1, &ptr2)) { + err = 3; + return 0; + } + + size = bpf_dynptr_size(&ptr1); + + /* Check that the clone has the same size and rd-only */ + if (bpf_dynptr_size(&ptr2) != size) { + err = 4; + return 0; + } + + if (bpf_dynptr_is_rdonly(&ptr2) != bpf_dynptr_is_rdonly(&ptr1)) { + err = 5; + return 0; + } + + /* Advance and trim the original dynptr */ + bpf_dynptr_adjust(&ptr1, 5, 5); + + /* Check that only original dynptr was affected, and the clone wasn't */ + if (bpf_dynptr_size(&ptr2) != size) { + err = 6; + return 0; + } + + return 0; +} + +SEC("?cgroup_skb/egress") +int test_dynptr_skb_no_buff(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + __u64 *data; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* This may return NULL. SKB may require a buffer */ + data = bpf_dynptr_slice(&ptr, 0, NULL, 1); + + return !!data; +} + +SEC("?cgroup_skb/egress") +int test_dynptr_skb_strcmp(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + char *data; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* This may return NULL. SKB may require a buffer */ + data = bpf_dynptr_slice(&ptr, 0, NULL, 10); + if (data) { + bpf_strncmp(data, 10, "foo"); + return 1; + } + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/inner_array_lookup.c b/tools/testing/selftests/bpf/progs/inner_array_lookup.c new file mode 100644 index 0000000000000..c2c8f2fa451dd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/inner_array_lookup.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct inner_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 5); + __type(key, int); + __type(value, int); +} inner_map1 SEC(".maps"); + +struct outer_map { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 3); + __type(key, int); + __array(values, struct inner_map); +} outer_map1 SEC(".maps") = { + .values = { + [2] = &inner_map1, + }, +}; + +SEC("raw_tp/sys_enter") +int handle__sys_enter(void *ctx) +{ + int outer_key = 2, inner_key = 3; + int *val; + void *map; + + map = bpf_map_lookup_elem(&outer_map1, &outer_key); + if (!map) + return 1; + + val = bpf_map_lookup_elem(map, &inner_key); + if (!val) + return 1; + + if (*val == 1) + *val = 2; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index be16143ae292f..6b9b3c56f009a 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -651,29 +651,25 @@ int iter_stack_array_loop(const void *ctx) return sum; } -#define ARR_SZ 16 - -static __noinline void fill(struct bpf_iter_num *it, int *arr, int mul) +static __noinline void fill(struct bpf_iter_num *it, int *arr, __u32 n, int mul) { - int *t; - __u64 i; + int *t, i; while ((t = bpf_iter_num_next(it))) { i = *t; - if (i >= ARR_SZ) + if (i >= n) break; arr[i] = i * mul; } } -static __noinline int sum(struct bpf_iter_num *it, int *arr) +static __noinline int sum(struct bpf_iter_num *it, int *arr, __u32 n) { - int *t, sum = 0;; - __u64 i; + int *t, i, sum = 0;; while ((t = bpf_iter_num_next(it))) { i = *t; - if (i >= ARR_SZ) + if (i >= n) break; sum += arr[i]; } @@ -685,7 +681,7 @@ SEC("raw_tp") __success int iter_pass_iter_ptr_to_subprog(const void *ctx) { - int arr1[ARR_SZ], arr2[ARR_SZ]; + int arr1[16], arr2[32]; struct bpf_iter_num it; int n, sum1, sum2; @@ -694,25 +690,25 @@ int iter_pass_iter_ptr_to_subprog(const void *ctx) /* fill arr1 */ n = ARRAY_SIZE(arr1); bpf_iter_num_new(&it, 0, n); - fill(&it, arr1, 2); + fill(&it, arr1, n, 2); bpf_iter_num_destroy(&it); /* fill arr2 */ n = ARRAY_SIZE(arr2); bpf_iter_num_new(&it, 0, n); - fill(&it, arr2, 10); + fill(&it, arr2, n, 10); bpf_iter_num_destroy(&it); /* sum arr1 */ n = ARRAY_SIZE(arr1); bpf_iter_num_new(&it, 0, n); - sum1 = sum(&it, arr1); + sum1 = sum(&it, arr1, n); bpf_iter_num_destroy(&it); /* sum arr2 */ n = ARRAY_SIZE(arr2); bpf_iter_num_new(&it, 0, n); - sum2 = sum(&it, arr2); + sum2 = sum(&it, arr2, n); bpf_iter_num_destroy(&it); bpf_printk("sum1=%d, sum2=%d", sum1, sum2); diff --git a/tools/testing/selftests/bpf/progs/jit_probe_mem.c b/tools/testing/selftests/bpf/progs/jit_probe_mem.c index 13f00ca2ed0a0..f9789e6682973 100644 --- a/tools/testing/selftests/bpf/progs/jit_probe_mem.c +++ b/tools/testing/selftests/bpf/progs/jit_probe_mem.c @@ -3,13 +3,11 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" static struct prog_test_ref_kfunc __kptr *v; long total_sum = -1; -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; - SEC("tc") int test_jit_probe_mem(struct __sk_buff *ctx) { diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c b/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c index 767472bc5a97b..7632d9ecb253b 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c @@ -1,8 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <vmlinux.h> #include <bpf/bpf_helpers.h> - -extern void bpf_kfunc_call_test_destructive(void) __ksym; +#include "../bpf_testmod/bpf_testmod_kfunc.h" SEC("tc") int kfunc_destructive_test(void) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c index b98313d391c66..4b0b7b79cdfb7 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c @@ -2,14 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> - -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; -extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; -extern int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym; -extern int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; -extern int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; -extern void bpf_kfunc_call_int_mem_release(int *p) __ksym; +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct syscall_test_args { __u8 data[16]; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_race.c b/tools/testing/selftests/bpf/progs/kfunc_call_race.c index 4e8fed75a4e09..d532af07decf9 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_race.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_race.c @@ -1,8 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <vmlinux.h> #include <bpf/bpf_helpers.h> - -extern void bpf_testmod_test_mod_kfunc(int i) __ksym; +#include "../bpf_testmod/bpf_testmod_kfunc.h" SEC("tc") int kfunc_call_fail(struct __sk_buff *ctx) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index 7daa8f5720b94..cf68d1e48a0f5 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -2,22 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> - -extern long bpf_kfunc_call_test4(signed char a, short b, int c, long d) __ksym; -extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; -extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, - __u32 c, __u64 d) __ksym; - -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; -extern void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) __ksym; -extern void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) __ksym; -extern void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) __ksym; -extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; -extern void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym; -extern int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym; -extern int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; -extern u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) __ksym; +#include "../bpf_testmod/bpf_testmod_kfunc.h" SEC("tc") int kfunc_call_test4(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c index c1fdecabeabfc..2380c75e74ce2 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c @@ -1,13 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ -#include <linux/bpf.h> -#include <bpf/bpf_helpers.h> -#include "bpf_tcp_helpers.h" +#include "../bpf_testmod/bpf_testmod_kfunc.h" extern const int bpf_prog_active __ksym; -extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, - __u32 c, __u64 d) __ksym; -extern struct sock *bpf_kfunc_call_test3(struct sock *sk) __ksym; int active_res = -1; int sk_state_res = -1; @@ -28,7 +23,7 @@ int __noinline f1(struct __sk_buff *skb) if (active) active_res = *active; - sk_state_res = bpf_kfunc_call_test3((struct sock *)sk)->sk_state; + sk_state_res = bpf_kfunc_call_test3((struct sock *)sk)->__sk_common.skc_state; return (__u32)bpf_kfunc_call_test1((struct sock *)sk, 1, 2, 3, 4); } diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash.c b/tools/testing/selftests/bpf/progs/local_kptr_stash.c index 0ef286da092bb..06838083079c1 100644 --- a/tools/testing/selftests/bpf/progs/local_kptr_stash.c +++ b/tools/testing/selftests/bpf/progs/local_kptr_stash.c @@ -5,7 +5,8 @@ #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_core_read.h> -#include "bpf_experimental.h" +#include "../bpf_experimental.h" +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct node_data { long key; @@ -32,8 +33,6 @@ struct map_value { */ struct node_data *just_here_because_btf_bug; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; - struct { __uint(type, BPF_MAP_TYPE_ARRAY); __type(key, int); diff --git a/tools/testing/selftests/bpf/progs/map_kptr.c b/tools/testing/selftests/bpf/progs/map_kptr.c index d7150041e5d15..da30f0d593648 100644 --- a/tools/testing/selftests/bpf/progs/map_kptr.c +++ b/tools/testing/selftests/bpf/progs/map_kptr.c @@ -2,6 +2,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct map_value { struct prog_test_ref_kfunc __kptr_untrusted *unref_ptr; @@ -114,10 +115,6 @@ DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, hash_map, hash_of_hash_maps); DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, hash_malloc_map, hash_of_hash_malloc_maps); DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, lru_hash_map, hash_of_lru_hash_maps); -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; -void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) __ksym; - #define WRITE_ONCE(x, val) ((*(volatile typeof(x) *) &(x)) = (val)) static void test_kptr_unref(struct map_value *v) diff --git a/tools/testing/selftests/bpf/progs/map_kptr_fail.c b/tools/testing/selftests/bpf/progs/map_kptr_fail.c index da8c724f839b7..450bb373b179f 100644 --- a/tools/testing/selftests/bpf/progs/map_kptr_fail.c +++ b/tools/testing/selftests/bpf/progs/map_kptr_fail.c @@ -4,6 +4,7 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_core_read.h> #include "bpf_misc.h" +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct map_value { char buf[8]; @@ -19,9 +20,6 @@ struct array_map { __uint(max_entries, 1); } array_map SEC(".maps"); -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; - SEC("?tc") __failure __msg("kptr access size must be BPF_DW") int size_not_bpf_dw(struct __sk_buff *ctx) diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr.c b/tools/testing/selftests/bpf/progs/refcounted_kptr.c index 1d348a225140d..a3da610b1e6b0 100644 --- a/tools/testing/selftests/bpf/progs/refcounted_kptr.c +++ b/tools/testing/selftests/bpf/progs/refcounted_kptr.c @@ -375,6 +375,8 @@ long rbtree_refcounted_node_ref_escapes(void *ctx) bpf_rbtree_add(&aroot, &n->node, less_a); m = bpf_refcount_acquire(n); bpf_spin_unlock(&alock); + if (!m) + return 2; m->key = 2; bpf_obj_drop(m); diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c index efcb308f80adf..0b09e5c915b15 100644 --- a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c +++ b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c @@ -29,7 +29,7 @@ static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b) } SEC("?tc") -__failure __msg("Unreleased reference id=3 alloc_insn=21") +__failure __msg("Unreleased reference id=4 alloc_insn=21") long rbtree_refcounted_node_ref_escapes(void *ctx) { struct node_acquire *n, *m; @@ -43,6 +43,8 @@ long rbtree_refcounted_node_ref_escapes(void *ctx) /* m becomes an owning ref but is never drop'd or added to a tree */ m = bpf_refcount_acquire(n); bpf_spin_unlock(&glock); + if (!m) + return 2; m->key = 2; return 0; diff --git a/tools/testing/selftests/bpf/progs/sock_destroy_prog.c b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c new file mode 100644 index 0000000000000..9e0bf7a54cec9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include "bpf_tracing_net.h" + +__be16 serv_port = 0; + +int bpf_sock_destroy(struct sock_common *sk) __ksym; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} tcp_conn_sockets SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} udp_conn_sockets SEC(".maps"); + +SEC("cgroup/connect6") +int sock_connect(struct bpf_sock_addr *ctx) +{ + __u64 sock_cookie = 0; + int key = 0; + __u32 keyc = 0; + + if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6) + return 1; + + sock_cookie = bpf_get_socket_cookie(ctx); + if (ctx->protocol == IPPROTO_TCP) + bpf_map_update_elem(&tcp_conn_sockets, &key, &sock_cookie, 0); + else if (ctx->protocol == IPPROTO_UDP) + bpf_map_update_elem(&udp_conn_sockets, &keyc, &sock_cookie, 0); + else + return 1; + + return 1; +} + +SEC("iter/tcp") +int iter_tcp6_client(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + __u64 sock_cookie = 0; + __u64 *val; + int key = 0; + + if (!sk_common) + return 0; + + if (sk_common->skc_family != AF_INET6) + return 0; + + sock_cookie = bpf_get_socket_cookie(sk_common); + val = bpf_map_lookup_elem(&tcp_conn_sockets, &key); + if (!val) + return 0; + /* Destroy connected client sockets. */ + if (sock_cookie == *val) + bpf_sock_destroy(sk_common); + + return 0; +} + +SEC("iter/tcp") +int iter_tcp6_server(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + const struct inet_connection_sock *icsk; + const struct inet_sock *inet; + struct tcp6_sock *tcp_sk; + __be16 srcp; + + if (!sk_common) + return 0; + + if (sk_common->skc_family != AF_INET6) + return 0; + + tcp_sk = bpf_skc_to_tcp6_sock(sk_common); + if (!tcp_sk) + return 0; + + icsk = &tcp_sk->tcp.inet_conn; + inet = &icsk->icsk_inet; + srcp = inet->inet_sport; + + /* Destroy server sockets. */ + if (srcp == serv_port) + bpf_sock_destroy(sk_common); + + return 0; +} + + +SEC("iter/udp") +int iter_udp6_client(struct bpf_iter__udp *ctx) +{ + struct udp_sock *udp_sk = ctx->udp_sk; + struct sock *sk = (struct sock *) udp_sk; + __u64 sock_cookie = 0, *val; + int key = 0; + + if (!sk) + return 0; + + sock_cookie = bpf_get_socket_cookie(sk); + val = bpf_map_lookup_elem(&udp_conn_sockets, &key); + if (!val) + return 0; + /* Destroy connected client sockets. */ + if (sock_cookie == *val) + bpf_sock_destroy((struct sock_common *)sk); + + return 0; +} + +SEC("iter/udp") +int iter_udp6_server(struct bpf_iter__udp *ctx) +{ + struct udp_sock *udp_sk = ctx->udp_sk; + struct sock *sk = (struct sock *) udp_sk; + struct inet_sock *inet; + __be16 srcp; + + if (!sk) + return 0; + + inet = &udp_sk->inet; + srcp = inet->inet_sport; + if (srcp == serv_port) + bpf_sock_destroy((struct sock_common *)sk); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c b/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c new file mode 100644 index 0000000000000..dd6850b58e259 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +int bpf_sock_destroy(struct sock_common *sk) __ksym; + +SEC("tp_btf/tcp_destroy_sock") +__failure __msg("calling kernel function bpf_sock_destroy is not allowed") +int BPF_PROG(trace_tcp_destroy_sock, struct sock *sk) +{ + /* should not load */ + bpf_sock_destroy((struct sock_common *)sk); + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c index 9fb241b972919..c8f59caa46394 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c @@ -9,6 +9,8 @@ char _license[] SEC("license") = "GPL"; #define CUSTOM_INHERIT2 1 #define CUSTOM_LISTENER 2 +__u32 page_size = 0; + struct sockopt_inherit { __u8 val; }; @@ -55,7 +57,7 @@ int _getsockopt(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_CUSTOM) - return 1; /* only interested in SOL_CUSTOM */ + goto out; /* only interested in SOL_CUSTOM */ if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -70,6 +72,12 @@ int _getsockopt(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } SEC("cgroup/setsockopt") @@ -80,7 +88,7 @@ int _setsockopt(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_CUSTOM) - return 1; /* only interested in SOL_CUSTOM */ + goto out; /* only interested in SOL_CUSTOM */ if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -93,4 +101,10 @@ int _setsockopt(struct bpf_sockopt *ctx) ctx->optlen = -1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c index 177a59069dae6..96f29fce050bc 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_multi.c +++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c @@ -5,6 +5,8 @@ char _license[] SEC("license") = "GPL"; +__u32 page_size = 0; + SEC("cgroup/getsockopt") int _getsockopt_child(struct bpf_sockopt *ctx) { @@ -12,7 +14,7 @@ int _getsockopt_child(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_IP || ctx->optname != IP_TOS) - return 1; + goto out; if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -26,6 +28,12 @@ int _getsockopt_child(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } SEC("cgroup/getsockopt") @@ -35,7 +43,7 @@ int _getsockopt_parent(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_IP || ctx->optname != IP_TOS) - return 1; + goto out; if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -49,6 +57,12 @@ int _getsockopt_parent(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } SEC("cgroup/setsockopt") @@ -58,7 +72,7 @@ int _setsockopt(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_IP || ctx->optname != IP_TOS) - return 1; + goto out; if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -67,4 +81,10 @@ int _setsockopt(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c index 1bce83b6e3a7b..dbe235ede7f38 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c +++ b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c @@ -9,6 +9,8 @@ char _license[] SEC("license") = "GPL"; +__u32 page_size = 0; + SEC("cgroup/setsockopt") int sockopt_qos_to_cc(struct bpf_sockopt *ctx) { @@ -19,7 +21,7 @@ int sockopt_qos_to_cc(struct bpf_sockopt *ctx) char cc_cubic[TCP_CA_NAME_MAX] = "cubic"; if (ctx->level != SOL_IPV6 || ctx->optname != IPV6_TCLASS) - return 1; + goto out; if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -36,4 +38,10 @@ int sockopt_qos_to_cc(struct bpf_sockopt *ctx) return 0; } return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index fe1df4cd206eb..cb990a7d3d458 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -37,7 +37,7 @@ int _getsockopt(struct bpf_sockopt *ctx) /* Bypass AF_NETLINK. */ sk = ctx->sk; if (sk && sk->family == AF_NETLINK) - return 1; + goto out; /* Make sure bpf_get_netns_cookie is callable. */ @@ -52,8 +52,7 @@ int _getsockopt(struct bpf_sockopt *ctx) * let next BPF program in the cgroup chain or kernel * handle it. */ - ctx->optlen = 0; /* bypass optval>PAGE_SIZE */ - return 1; + goto out; } if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) { @@ -61,7 +60,7 @@ int _getsockopt(struct bpf_sockopt *ctx) * let next BPF program in the cgroup chain or kernel * handle it. */ - return 1; + goto out; } if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) { @@ -69,7 +68,7 @@ int _getsockopt(struct bpf_sockopt *ctx) * let next BPF program in the cgroup chain or kernel * handle it. */ - return 1; + goto out; } if (ctx->level == SOL_TCP && ctx->optname == TCP_ZEROCOPY_RECEIVE) { @@ -85,7 +84,7 @@ int _getsockopt(struct bpf_sockopt *ctx) if (((struct tcp_zerocopy_receive *)optval)->address != 0) return 0; /* unexpected data */ - return 1; + goto out; } if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { @@ -129,6 +128,12 @@ int _getsockopt(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } SEC("cgroup/setsockopt") @@ -142,7 +147,7 @@ int _setsockopt(struct bpf_sockopt *ctx) /* Bypass AF_NETLINK. */ sk = ctx->sk; if (sk && sk->family == AF_NETLINK) - return 1; + goto out; /* Make sure bpf_get_netns_cookie is callable. */ @@ -224,4 +229,10 @@ int _setsockopt(struct bpf_sockopt *ctx) */ return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c index b85fc8c423ba7..17a9f59bf5f30 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func1.c +++ b/tools/testing/selftests/bpf/progs/test_global_func1.c @@ -10,6 +10,8 @@ static __attribute__ ((noinline)) int f0(int var, struct __sk_buff *skb) { + asm volatile (""); + return skb->len; } diff --git a/tools/testing/selftests/bpf/progs/test_global_map_resize.c b/tools/testing/selftests/bpf/progs/test_global_map_resize.c new file mode 100644 index 0000000000000..2588f23842462 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_map_resize.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +/* rodata section */ +const volatile pid_t pid; +const volatile size_t bss_array_len; +const volatile size_t data_array_len; + +/* bss section */ +int sum = 0; +int array[1]; + +/* custom data secton */ +int my_array[1] SEC(".data.custom"); + +/* custom data section which should NOT be resizable, + * since it contains a single var which is not an array + */ +int my_int SEC(".data.non_array"); + +/* custom data section which should NOT be resizable, + * since its last var is not an array + */ +int my_array_first[1] SEC(".data.array_not_last"); +int my_int_last SEC(".data.array_not_last"); + +SEC("tp/syscalls/sys_enter_getpid") +int bss_array_sum(void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + sum = 0; + + for (size_t i = 0; i < bss_array_len; ++i) + sum += array[i]; + + return 0; +} + +SEC("tp/syscalls/sys_enter_getuid") +int data_array_sum(void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + sum = 0; + + for (size_t i = 0; i < data_array_len; ++i) + sum += my_array[i]; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c index bbad3c2d9aa57..f75e531bf36fc 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c @@ -265,7 +265,10 @@ static __noinline bool sk_dst_port__load_word(struct bpf_sock *sk) static __noinline bool sk_dst_port__load_half(struct bpf_sock *sk) { - __u16 *half = (__u16 *)&sk->dst_port; + __u16 *half; + + asm volatile (""); + half = (__u16 *)&sk->dst_port; return half[0] == bpf_htons(0xcafe); } diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c b/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c new file mode 100644 index 0000000000000..29314805ce421 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c @@ -0,0 +1,32 @@ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_tx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_msg SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h index baf9ebc6d903f..99d2ea9fb658f 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h @@ -191,7 +191,7 @@ SEC("sockops") int bpf_sockmap(struct bpf_sock_ops *skops) { __u32 lport, rport; - int op, err, ret; + int op, ret; op = (int) skops->op; @@ -203,10 +203,10 @@ int bpf_sockmap(struct bpf_sock_ops *skops) if (lport == 10000) { ret = 1; #ifdef SOCKMAP - err = bpf_sock_map_update(skops, &sock_map, &ret, + bpf_sock_map_update(skops, &sock_map, &ret, BPF_NOEXIST); #else - err = bpf_sock_hash_update(skops, &sock_map, &ret, + bpf_sock_hash_update(skops, &sock_map, &ret, BPF_NOEXIST); #endif } @@ -218,10 +218,10 @@ int bpf_sockmap(struct bpf_sock_ops *skops) if (bpf_ntohl(rport) == 10001) { ret = 10; #ifdef SOCKMAP - err = bpf_sock_map_update(skops, &sock_map, &ret, + bpf_sock_map_update(skops, &sock_map, &ret, BPF_NOEXIST); #else - err = bpf_sock_hash_update(skops, &sock_map, &ret, + bpf_sock_hash_update(skops, &sock_map, &ret, BPF_NOEXIST); #endif } @@ -230,8 +230,6 @@ int bpf_sockmap(struct bpf_sock_ops *skops) break; } - __sink(err); - return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c b/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c new file mode 100644 index 0000000000000..1d86a717a290a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c @@ -0,0 +1,32 @@ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_tx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_msg SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_subprogs_extable.c b/tools/testing/selftests/bpf/progs/test_subprogs_extable.c new file mode 100644 index 0000000000000..e2a21fbd4e442 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subprogs_extable.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 8); + __type(key, __u32); + __type(value, __u64); +} test_array SEC(".maps"); + +unsigned int triggered; + +static __u64 test_cb(struct bpf_map *map, __u32 *key, __u64 *val, void *data) +{ + return 1; +} + +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret_subprogs, int arg, struct file *ret) +{ + *(volatile long *)ret; + *(volatile int *)&ret->f_mode; + bpf_for_each_map_elem(&test_array, test_cb, NULL, 0); + triggered++; + return 0; +} + +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret_subprogs2, int arg, struct file *ret) +{ + *(volatile long *)ret; + *(volatile int *)&ret->f_mode; + bpf_for_each_map_elem(&test_array, test_cb, NULL, 0); + triggered++; + return 0; +} + +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret_subprogs3, int arg, struct file *ret) +{ + *(volatile long *)ret; + *(volatile int *)&ret->f_mode; + bpf_for_each_map_elem(&test_array, test_cb, NULL, 0); + triggered++; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c new file mode 100644 index 0000000000000..56cdc0a553f08 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Bytedance */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +long bpf_task_under_cgroup(struct task_struct *task, struct cgroup *ancestor) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; +struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym; +void bpf_task_release(struct task_struct *p) __ksym; + +const volatile int local_pid; +const volatile __u64 cgid; +int remote_pid; + +SEC("tp_btf/task_newtask") +int BPF_PROG(handle__task_newtask, struct task_struct *task, u64 clone_flags) +{ + struct cgroup *cgrp = NULL; + struct task_struct *acquired; + + if (local_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + acquired = bpf_task_acquire(task); + if (!acquired) + return 0; + + if (local_pid == acquired->tgid) + goto out; + + cgrp = bpf_cgroup_from_id(cgid); + if (!cgrp) + goto out; + + if (bpf_task_under_cgroup(acquired, cgrp)) + remote_pid = acquired->tgid; + +out: + if (cgrp) + bpf_cgroup_release(cgrp); + bpf_task_release(acquired); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c index 25ee4a22e48d9..78c368e717972 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c @@ -2,6 +2,7 @@ /* Copyright (c) 2022 Meta */ #include <stddef.h> #include <string.h> +#include <stdbool.h> #include <linux/bpf.h> #include <linux/if_ether.h> #include <linux/if_packet.h> diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c new file mode 100644 index 0000000000000..13b29a7faa71a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c @@ -0,0 +1,659 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +/* Check that precision marks propagate through scalar IDs. + * Registers r{0,1,2} have the same scalar ID at the moment when r0 is + * marked to be precise, this mark is immediately propagated to r{1,2}. + */ +SEC("socket") +__success __log_level(2) +__msg("frame0: regs=r0,r1,r2 stack= before 4: (bf) r3 = r10") +__msg("frame0: regs=r0,r1,r2 stack= before 3: (bf) r2 = r0") +__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_same_state(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == r2.id */ + "r1 = r0;" + "r2 = r0;" + /* force r0 to be precise, this immediately marks r1 and r2 as + * precise as well because of shared IDs + */ + "r3 = r10;" + "r3 += r0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Same as precision_same_state, but mark propagates through state / + * parent state boundary. + */ +SEC("socket") +__success __log_level(2) +__msg("frame0: last_idx 6 first_idx 5 subseq_idx -1") +__msg("frame0: regs=r0,r1,r2 stack= before 5: (bf) r3 = r10") +__msg("frame0: parent state regs=r0,r1,r2 stack=:") +__msg("frame0: regs=r0,r1,r2 stack= before 4: (05) goto pc+0") +__msg("frame0: regs=r0,r1,r2 stack= before 3: (bf) r2 = r0") +__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__msg("frame0: parent state regs=r0 stack=:") +__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_cross_state(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == r2.id */ + "r1 = r0;" + "r2 = r0;" + /* force checkpoint */ + "goto +0;" + /* force r0 to be precise, this immediately marks r1 and r2 as + * precise as well because of shared IDs + */ + "r3 = r10;" + "r3 += r0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Same as precision_same_state, but break one of the + * links, note that r1 is absent from regs=... in __msg below. + */ +SEC("socket") +__success __log_level(2) +__msg("frame0: regs=r0,r2 stack= before 5: (bf) r3 = r10") +__msg("frame0: regs=r0,r2 stack= before 4: (b7) r1 = 0") +__msg("frame0: regs=r0,r2 stack= before 3: (bf) r2 = r0") +__msg("frame0: regs=r0 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_same_state_broken_link(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == r2.id */ + "r1 = r0;" + "r2 = r0;" + /* break link for r1, this is the only line that differs + * compared to the previous test + */ + "r1 = 0;" + /* force r0 to be precise, this immediately marks r1 and r2 as + * precise as well because of shared IDs + */ + "r3 = r10;" + "r3 += r0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Same as precision_same_state_broken_link, but with state / + * parent state boundary. + */ +SEC("socket") +__success __log_level(2) +__msg("frame0: regs=r0,r2 stack= before 6: (bf) r3 = r10") +__msg("frame0: regs=r0,r2 stack= before 5: (b7) r1 = 0") +__msg("frame0: parent state regs=r0,r2 stack=:") +__msg("frame0: regs=r0,r1,r2 stack= before 4: (05) goto pc+0") +__msg("frame0: regs=r0,r1,r2 stack= before 3: (bf) r2 = r0") +__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__msg("frame0: parent state regs=r0 stack=:") +__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_cross_state_broken_link(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == r2.id */ + "r1 = r0;" + "r2 = r0;" + /* force checkpoint, although link between r1 and r{0,2} is + * broken by the next statement current precision tracking + * algorithm can't react to it and propagates mark for r1 to + * the parent state. + */ + "goto +0;" + /* break link for r1, this is the only line that differs + * compared to precision_cross_state() + */ + "r1 = 0;" + /* force r0 to be precise, this immediately marks r1 and r2 as + * precise as well because of shared IDs + */ + "r3 = r10;" + "r3 += r0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Check that precision marks propagate through scalar IDs. + * Use the same scalar ID in multiple stack frames, check that + * precision information is propagated up the call stack. + */ +SEC("socket") +__success __log_level(2) +__msg("11: (0f) r2 += r1") +/* Current state */ +__msg("frame2: last_idx 11 first_idx 10 subseq_idx -1") +__msg("frame2: regs=r1 stack= before 10: (bf) r2 = r10") +__msg("frame2: parent state regs=r1 stack=") +/* frame1.r{6,7} are marked because mark_precise_scalar_ids() + * looks for all registers with frame2.r1.id in the current state + */ +__msg("frame1: parent state regs=r6,r7 stack=") +__msg("frame0: parent state regs=r6 stack=") +/* Parent state */ +__msg("frame2: last_idx 8 first_idx 8 subseq_idx 10") +__msg("frame2: regs=r1 stack= before 8: (85) call pc+1") +/* frame1.r1 is marked because of backtracking of call instruction */ +__msg("frame1: parent state regs=r1,r6,r7 stack=") +__msg("frame0: parent state regs=r6 stack=") +/* Parent state */ +__msg("frame1: last_idx 7 first_idx 6 subseq_idx 8") +__msg("frame1: regs=r1,r6,r7 stack= before 7: (bf) r7 = r1") +__msg("frame1: regs=r1,r6 stack= before 6: (bf) r6 = r1") +__msg("frame1: parent state regs=r1 stack=") +__msg("frame0: parent state regs=r6 stack=") +/* Parent state */ +__msg("frame1: last_idx 4 first_idx 4 subseq_idx 6") +__msg("frame1: regs=r1 stack= before 4: (85) call pc+1") +__msg("frame0: parent state regs=r1,r6 stack=") +/* Parent state */ +__msg("frame0: last_idx 3 first_idx 1 subseq_idx 4") +__msg("frame0: regs=r0,r1,r6 stack= before 3: (bf) r6 = r0") +__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_many_frames(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == r6.id */ + "r1 = r0;" + "r6 = r0;" + "call precision_many_frames__foo;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +static __naked __noinline __used +void precision_many_frames__foo(void) +{ + asm volatile ( + /* conflate one of the register numbers (r6) with outer frame, + * to verify that those are tracked independently + */ + "r6 = r1;" + "r7 = r1;" + "call precision_many_frames__bar;" + "exit" + ::: __clobber_all); +} + +static __naked __noinline __used +void precision_many_frames__bar(void) +{ + asm volatile ( + /* force r1 to be precise, this immediately marks: + * - bar frame r1 + * - foo frame r{1,6,7} + * - main frame r{1,6} + */ + "r2 = r10;" + "r2 += r1;" + "r0 = 0;" + "exit;" + ::: __clobber_all); +} + +/* Check that scalars with the same IDs are marked precise on stack as + * well as in registers. + */ +SEC("socket") +__success __log_level(2) +/* foo frame */ +__msg("frame1: regs=r1 stack=-8,-16 before 9: (bf) r2 = r10") +__msg("frame1: regs=r1 stack=-8,-16 before 8: (7b) *(u64 *)(r10 -16) = r1") +__msg("frame1: regs=r1 stack=-8 before 7: (7b) *(u64 *)(r10 -8) = r1") +__msg("frame1: regs=r1 stack= before 4: (85) call pc+2") +/* main frame */ +__msg("frame0: regs=r0,r1 stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r1") +__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_stack(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == fp[-8].id */ + "r1 = r0;" + "*(u64*)(r10 - 8) = r1;" + "call precision_stack__foo;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +static __naked __noinline __used +void precision_stack__foo(void) +{ + asm volatile ( + /* conflate one of the register numbers (r6) with outer frame, + * to verify that those are tracked independently + */ + "*(u64*)(r10 - 8) = r1;" + "*(u64*)(r10 - 16) = r1;" + /* force r1 to be precise, this immediately marks: + * - foo frame r1,fp{-8,-16} + * - main frame r1,fp{-8} + */ + "r2 = r10;" + "r2 += r1;" + "exit" + ::: __clobber_all); +} + +/* Use two separate scalar IDs to check that these are propagated + * independently. + */ +SEC("socket") +__success __log_level(2) +/* r{6,7} */ +__msg("11: (0f) r3 += r7") +__msg("frame0: regs=r6,r7 stack= before 10: (bf) r3 = r10") +/* ... skip some insns ... */ +__msg("frame0: regs=r6,r7 stack= before 3: (bf) r7 = r0") +__msg("frame0: regs=r0,r6 stack= before 2: (bf) r6 = r0") +/* r{8,9} */ +__msg("12: (0f) r3 += r9") +__msg("frame0: regs=r8,r9 stack= before 11: (0f) r3 += r7") +/* ... skip some insns ... */ +__msg("frame0: regs=r8,r9 stack= before 7: (bf) r9 = r0") +__msg("frame0: regs=r0,r8 stack= before 6: (bf) r8 = r0") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_two_ids(void) +{ + asm volatile ( + /* r6 = random number up to 0xff + * r6.id == r7.id + */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + "r6 = r0;" + "r7 = r0;" + /* same, but for r{8,9} */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + "r8 = r0;" + "r9 = r0;" + /* clear r0 id */ + "r0 = 0;" + /* force checkpoint */ + "goto +0;" + "r3 = r10;" + /* force r7 to be precise, this also marks r6 */ + "r3 += r7;" + /* force r9 to be precise, this also marks r8 */ + "r3 += r9;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Verify that check_ids() is used by regsafe() for scalars. + * + * r9 = ... some pointer with range X ... + * r6 = ... unbound scalar ID=a ... + * r7 = ... unbound scalar ID=b ... + * if (r6 > r7) goto +1 + * r7 = r6 + * if (r7 > X) goto exit + * r9 += r6 + * ... access memory using r9 ... + * + * The memory access is safe only if r7 is bounded, + * which is true for one branch and not true for another. + */ +SEC("socket") +__failure __msg("register with unbounded min value") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void check_ids_in_regsafe(void) +{ + asm volatile ( + /* Bump allocated stack */ + "r1 = 0;" + "*(u64*)(r10 - 8) = r1;" + /* r9 = pointer to stack */ + "r9 = r10;" + "r9 += -8;" + /* r7 = ktime_get_ns() */ + "call %[bpf_ktime_get_ns];" + "r7 = r0;" + /* r6 = ktime_get_ns() */ + "call %[bpf_ktime_get_ns];" + "r6 = r0;" + /* if r6 > r7 is an unpredictable jump */ + "if r6 > r7 goto l1_%=;" + "r7 = r6;" +"l1_%=:" + /* if r7 > 4 ...; transfers range to r6 on one execution path + * but does not transfer on another + */ + "if r7 > 4 goto l2_%=;" + /* Access memory at r9[r6], r6 is not always bounded */ + "r9 += r6;" + "r0 = *(u8*)(r9 + 0);" +"l2_%=:" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Similar to check_ids_in_regsafe. + * The l0 could be reached in two states: + * + * (1) r6{.id=A}, r7{.id=A}, r8{.id=B} + * (2) r6{.id=B}, r7{.id=A}, r8{.id=B} + * + * Where (2) is not safe, as "r7 > 4" check won't propagate range for it. + * This example would be considered safe without changes to + * mark_chain_precision() to track scalar values with equal IDs. + */ +SEC("socket") +__failure __msg("register with unbounded min value") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void check_ids_in_regsafe_2(void) +{ + asm volatile ( + /* Bump allocated stack */ + "r1 = 0;" + "*(u64*)(r10 - 8) = r1;" + /* r9 = pointer to stack */ + "r9 = r10;" + "r9 += -8;" + /* r8 = ktime_get_ns() */ + "call %[bpf_ktime_get_ns];" + "r8 = r0;" + /* r7 = ktime_get_ns() */ + "call %[bpf_ktime_get_ns];" + "r7 = r0;" + /* r6 = ktime_get_ns() */ + "call %[bpf_ktime_get_ns];" + "r6 = r0;" + /* scratch .id from r0 */ + "r0 = 0;" + /* if r6 > r7 is an unpredictable jump */ + "if r6 > r7 goto l1_%=;" + /* tie r6 and r7 .id */ + "r6 = r7;" +"l0_%=:" + /* if r7 > 4 exit(0) */ + "if r7 > 4 goto l2_%=;" + /* Access memory at r9[r6] */ + "r9 += r6;" + "r0 = *(u8*)(r9 + 0);" +"l2_%=:" + "r0 = 0;" + "exit;" +"l1_%=:" + /* tie r6 and r8 .id */ + "r6 = r8;" + "goto l0_%=;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Check that scalar IDs *are not* generated on register to register + * assignments if source register is a constant. + * + * If such IDs *are* generated the 'l1' below would be reached in + * two states: + * + * (1) r1{.id=A}, r2{.id=A} + * (2) r1{.id=C}, r2{.id=C} + * + * Thus forcing 'if r1 == r2' verification twice. + */ +SEC("socket") +__success __log_level(2) +__msg("11: (1d) if r3 == r4 goto pc+0") +__msg("frame 0: propagating r3,r4") +__msg("11: safe") +__msg("processed 15 insns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void no_scalar_id_for_const(void) +{ + asm volatile ( + "call %[bpf_ktime_get_ns];" + /* unpredictable jump */ + "if r0 > 7 goto l0_%=;" + /* possibly generate same scalar ids for r3 and r4 */ + "r1 = 0;" + "r1 = r1;" + "r3 = r1;" + "r4 = r1;" + "goto l1_%=;" +"l0_%=:" + /* possibly generate different scalar ids for r3 and r4 */ + "r1 = 0;" + "r2 = 0;" + "r3 = r1;" + "r4 = r2;" +"l1_%=:" + /* predictable jump, marks r3 and r4 precise */ + "if r3 == r4 goto +0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Same as no_scalar_id_for_const() but for 32-bit values */ +SEC("socket") +__success __log_level(2) +__msg("11: (1e) if w3 == w4 goto pc+0") +__msg("frame 0: propagating r3,r4") +__msg("11: safe") +__msg("processed 15 insns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void no_scalar_id_for_const32(void) +{ + asm volatile ( + "call %[bpf_ktime_get_ns];" + /* unpredictable jump */ + "if r0 > 7 goto l0_%=;" + /* possibly generate same scalar ids for r3 and r4 */ + "w1 = 0;" + "w1 = w1;" + "w3 = w1;" + "w4 = w1;" + "goto l1_%=;" +"l0_%=:" + /* possibly generate different scalar ids for r3 and r4 */ + "w1 = 0;" + "w2 = 0;" + "w3 = w1;" + "w4 = w2;" +"l1_%=:" + /* predictable jump, marks r1 and r2 precise */ + "if w3 == w4 goto +0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Check that unique scalar IDs are ignored when new verifier state is + * compared to cached verifier state. For this test: + * - cached state has no id on r1 + * - new state has a unique id on r1 + */ +SEC("socket") +__success __log_level(2) +__msg("6: (25) if r6 > 0x7 goto pc+1") +__msg("7: (57) r1 &= 255") +__msg("8: (bf) r2 = r10") +__msg("from 6 to 8: safe") +__msg("processed 12 insns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void ignore_unique_scalar_ids_cur(void) +{ + asm volatile ( + "call %[bpf_ktime_get_ns];" + "r6 = r0;" + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* r1.id == r0.id */ + "r1 = r0;" + /* make r1.id unique */ + "r0 = 0;" + "if r6 > 7 goto l0_%=;" + /* clear r1 id, but keep the range compatible */ + "r1 &= 0xff;" +"l0_%=:" + /* get here in two states: + * - first: r1 has no id (cached state) + * - second: r1 has a unique id (should be considered equivalent) + */ + "r2 = r10;" + "r2 += r1;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Check that unique scalar IDs are ignored when new verifier state is + * compared to cached verifier state. For this test: + * - cached state has a unique id on r1 + * - new state has no id on r1 + */ +SEC("socket") +__success __log_level(2) +__msg("6: (25) if r6 > 0x7 goto pc+1") +__msg("7: (05) goto pc+1") +__msg("9: (bf) r2 = r10") +__msg("9: safe") +__msg("processed 13 insns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void ignore_unique_scalar_ids_old(void) +{ + asm volatile ( + "call %[bpf_ktime_get_ns];" + "r6 = r0;" + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* r1.id == r0.id */ + "r1 = r0;" + /* make r1.id unique */ + "r0 = 0;" + "if r6 > 7 goto l1_%=;" + "goto l0_%=;" +"l1_%=:" + /* clear r1 id, but keep the range compatible */ + "r1 &= 0xff;" +"l0_%=:" + /* get here in two states: + * - first: r1 has a unique id (cached state) + * - second: r1 has no id (should be considered equivalent) + */ + "r2 = r10;" + "r2 += r1;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Check that two different scalar IDs in a verified state can't be + * mapped to the same scalar ID in current state. + */ +SEC("socket") +__success __log_level(2) +/* The exit instruction should be reachable from two states, + * use two matches and "processed .. insns" to ensure this. + */ +__msg("13: (95) exit") +__msg("13: (95) exit") +__msg("processed 18 insns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void two_old_ids_one_cur_id(void) +{ + asm volatile ( + /* Give unique scalar IDs to r{6,7} */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + "r6 = r0;" + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + "r7 = r0;" + "r0 = 0;" + /* Maybe make r{6,7} IDs identical */ + "if r6 > r7 goto l0_%=;" + "goto l1_%=;" +"l0_%=:" + "r6 = r7;" +"l1_%=:" + /* Mark r{6,7} precise. + * Get here in two states: + * - first: r6{.id=A}, r7{.id=B} (cached state) + * - second: r6{.id=A}, r7{.id=A} + * Currently we don't want to consider such states equivalent. + * Thus "exit;" would be verified twice. + */ + "r2 = r10;" + "r2 += r6;" + "r2 += r7;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c index 136e5530b72cf..6115520154e33 100644 --- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c +++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c @@ -371,4 +371,83 @@ __naked void and_then_at_fp_8(void) " ::: __clobber_all); } +SEC("xdp") +__description("32-bit spill of 64-bit reg should clear ID") +__failure __msg("math between ctx pointer and 4294967295 is not allowed") +__naked void spill_32bit_of_64bit_fail(void) +{ + asm volatile (" \ + r6 = r1; \ + /* Roll one bit to force the verifier to track both branches. */\ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x8; \ + /* Put a large number into r1. */ \ + r1 = 0xffffffff; \ + r1 <<= 32; \ + r1 += r0; \ + /* Assign an ID to r1. */ \ + r2 = r1; \ + /* 32-bit spill r1 to stack - should clear the ID! */\ + *(u32*)(r10 - 8) = r1; \ + /* 32-bit fill r2 from stack. */ \ + r2 = *(u32*)(r10 - 8); \ + /* Compare r2 with another register to trigger find_equal_scalars.\ + * Having one random bit is important here, otherwise the verifier cuts\ + * the corners. If the ID was mistakenly preserved on spill, this would\ + * cause the verifier to think that r1 is also equal to zero in one of\ + * the branches, and equal to eight on the other branch.\ + */ \ + r3 = 0; \ + if r2 != r3 goto l0_%=; \ +l0_%=: r1 >>= 32; \ + /* At this point, if the verifier thinks that r1 is 0, an out-of-bounds\ + * read will happen, because it actually contains 0xffffffff.\ + */ \ + r6 += r1; \ + r0 = *(u32*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("xdp") +__description("16-bit spill of 32-bit reg should clear ID") +__failure __msg("dereference of modified ctx ptr R6 off=65535 disallowed") +__naked void spill_16bit_of_32bit_fail(void) +{ + asm volatile (" \ + r6 = r1; \ + /* Roll one bit to force the verifier to track both branches. */\ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x8; \ + /* Put a large number into r1. */ \ + w1 = 0xffff0000; \ + r1 += r0; \ + /* Assign an ID to r1. */ \ + r2 = r1; \ + /* 16-bit spill r1 to stack - should clear the ID! */\ + *(u16*)(r10 - 8) = r1; \ + /* 16-bit fill r2 from stack. */ \ + r2 = *(u16*)(r10 - 8); \ + /* Compare r2 with another register to trigger find_equal_scalars.\ + * Having one random bit is important here, otherwise the verifier cuts\ + * the corners. If the ID was mistakenly preserved on spill, this would\ + * cause the verifier to think that r1 is also equal to zero in one of\ + * the branches, and equal to eight on the other branch.\ + */ \ + r3 = 0; \ + if r2 != r3 goto l0_%=; \ +l0_%=: r1 >>= 16; \ + /* At this point, if the verifier thinks that r1 is 0, an out-of-bounds\ + * read will happen, because it actually contains 0xffff.\ + */ \ + r6 += r1; \ + r0 = *(u32*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c new file mode 100644 index 0000000000000..db6b3143338b6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -0,0 +1,536 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <errno.h> +#include <string.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof(x[0])) + +int vals[] SEC(".data.vals") = {1, 2, 3, 4}; + +__naked __noinline __used +static unsigned long identity_subprog() +{ + /* the simplest *static* 64-bit identity function */ + asm volatile ( + "r0 = r1;" + "exit;" + ); +} + +__noinline __used +unsigned long global_identity_subprog(__u64 x) +{ + /* the simplest *global* 64-bit identity function */ + return x; +} + +__naked __noinline __used +static unsigned long callback_subprog() +{ + /* the simplest callback function */ + asm volatile ( + "r0 = 0;" + "exit;" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("7: (0f) r1 += r0") +__msg("mark_precise: frame0: regs=r0 stack= before 6: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r0 stack= before 5: (27) r0 *= 4") +__msg("mark_precise: frame0: regs=r0 stack= before 11: (95) exit") +__msg("mark_precise: frame1: regs=r0 stack= before 10: (bf) r0 = r1") +__msg("mark_precise: frame1: regs=r1 stack= before 4: (85) call pc+5") +__msg("mark_precise: frame0: regs=r1 stack= before 3: (bf) r1 = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int subprog_result_precise(void) +{ + asm volatile ( + "r6 = 3;" + /* pass r6 through r1 into subprog to get it back as r0; + * this whole chain will have to be marked as precise later + */ + "r1 = r6;" + "call identity_subprog;" + /* now use subprog's returned value (which is a + * r6 -> r1 -> r0 chain), as index into vals array, forcing + * all of that to be known precisely + */ + "r0 *= 4;" + "r1 = %[vals];" + /* here r0->r1->r6 chain is forced to be precise and has to be + * propagated back to the beginning, including through the + * subprog call + */ + "r1 += r0;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("9: (0f) r1 += r0") +__msg("mark_precise: frame0: last_idx 9 first_idx 0") +__msg("mark_precise: frame0: regs=r0 stack= before 8: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r0 stack= before 7: (27) r0 *= 4") +__msg("mark_precise: frame0: regs=r0 stack= before 5: (a5) if r0 < 0x4 goto pc+1") +__msg("mark_precise: frame0: regs=r0 stack= before 4: (85) call pc+7") +__naked int global_subprog_result_precise(void) +{ + asm volatile ( + "r6 = 3;" + /* pass r6 through r1 into subprog to get it back as r0; + * given global_identity_subprog is global, precision won't + * propagate all the way back to r6 + */ + "r1 = r6;" + "call global_identity_subprog;" + /* now use subprog's returned value (which is unknown now, so + * we need to clamp it), as index into vals array, forcing r0 + * to be marked precise (with no effect on r6, though) + */ + "if r0 < %[vals_arr_sz] goto 1f;" + "r0 = %[vals_arr_sz] - 1;" + "1:" + "r0 *= 4;" + "r1 = %[vals];" + /* here r0 is forced to be precise and has to be + * propagated back to the global subprog call, but it + * shouldn't go all the way to mark r6 as precise + */ + "r1 += r0;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals), + __imm_const(vals_arr_sz, ARRAY_SIZE(vals)) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("14: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 14 first_idx 10") +__msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (25) if r6 > 0x3 goto pc+4") +__msg("mark_precise: frame0: regs=r6 stack= before 10: (bf) r6 = r0") +__msg("mark_precise: frame0: parent state regs=r0 stack=:") +__msg("mark_precise: frame0: last_idx 18 first_idx 0") +__msg("mark_precise: frame0: regs=r0 stack= before 18: (95) exit") +__naked int callback_result_precise(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and use result; r0 shouldn't propagate back to + * callback_subprog + */ + "r1 = r6;" /* nr_loops */ + "r2 = %[callback_subprog];" /* callback_fn */ + "r3 = 0;" /* callback_ctx */ + "r4 = 0;" /* flags */ + "call %[bpf_loop];" + + "r6 = r0;" + "if r6 > 3 goto 1f;" + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the bpf_loop() call, but not beyond + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "1:" + "exit;" + : + : __imm_ptr(vals), + __imm_ptr(callback_subprog), + __imm(bpf_loop) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("7: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 7 first_idx 0") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 5: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 10: (bf) r0 = r1") +__msg("mark_precise: frame1: regs= stack= before 4: (85) call pc+5") +__msg("mark_precise: frame0: regs=r6 stack= before 3: (b7) r1 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_callee_saved_reg_precise(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call identity_subprog;" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("7: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 7 first_idx 0") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 5: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (85) call pc+5") +__msg("mark_precise: frame0: regs=r6 stack= before 3: (b7) r1 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_callee_saved_reg_precise_global(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call global_identity_subprog;" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("12: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 12 first_idx 10") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 10: (27) r6 *= 4") +__msg("mark_precise: frame0: parent state regs=r6 stack=:") +__msg("mark_precise: frame0: last_idx 16 first_idx 0") +__msg("mark_precise: frame0: regs=r6 stack= before 16: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0") +__msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop#181") +__msg("mark_precise: frame0: regs=r6 stack= before 8: (b7) r4 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 7: (b7) r3 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r2 = r8") +__msg("mark_precise: frame0: regs=r6 stack= before 5: (b7) r1 = 1") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +__naked int parent_callee_saved_reg_precise_with_callback(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 1;" /* nr_loops */ + "r2 = %[callback_subprog];" /* callback_fn */ + "r3 = 0;" /* callback_ctx */ + "r4 = 0;" /* flags */ + "call %[bpf_loop];" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) callback call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals), + __imm_ptr(callback_subprog), + __imm(bpf_loop) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("9: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 9 first_idx 6") +__msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: parent state regs= stack=-8:") +__msg("mark_precise: frame0: last_idx 13 first_idx 0") +__msg("mark_precise: frame0: regs= stack=-8 before 13: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 12: (bf) r0 = r1") +__msg("mark_precise: frame1: regs= stack= before 5: (85) call pc+6") +__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_stack_slot_precise(void) +{ + asm volatile ( + /* spill reg */ + "r6 = 3;" + "*(u64 *)(r10 - 8) = r6;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call identity_subprog;" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r6 = *(u64 *)(r10 - 8);" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("9: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 9 first_idx 6") +__msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: parent state regs= stack=-8:") +__msg("mark_precise: frame0: last_idx 5 first_idx 0") +__msg("mark_precise: frame0: regs= stack=-8 before 5: (85) call pc+6") +__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_stack_slot_precise_global(void) +{ + asm volatile ( + /* spill reg */ + "r6 = 3;" + "*(u64 *)(r10 - 8) = r6;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call global_identity_subprog;" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r6 = *(u64 *)(r10 - 8);" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("14: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 14 first_idx 11") +__msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: parent state regs= stack=-8:") +__msg("mark_precise: frame0: last_idx 18 first_idx 0") +__msg("mark_precise: frame0: regs= stack=-8 before 18: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0") +__msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181") +__msg("mark_precise: frame0: regs= stack=-8 before 9: (b7) r4 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 8: (b7) r3 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r2 = r8") +__msg("mark_precise: frame0: regs= stack=-8 before 6: (bf) r1 = r6") +__msg("mark_precise: frame0: regs= stack=-8 before 5: (7b) *(u64 *)(r10 -8) = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +__naked int parent_stack_slot_precise_with_callback(void) +{ + asm volatile ( + /* spill reg */ + "r6 = 3;" + "*(u64 *)(r10 - 8) = r6;" + + /* ensure we have callback frame in jump history */ + "r1 = r6;" /* nr_loops */ + "r2 = %[callback_subprog];" /* callback_fn */ + "r3 = 0;" /* callback_ctx */ + "r4 = 0;" /* flags */ + "call %[bpf_loop];" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r6 = *(u64 *)(r10 - 8);" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals), + __imm_ptr(callback_subprog), + __imm(bpf_loop) + : __clobber_common, "r6" + ); +} + +__noinline __used +static __u64 subprog_with_precise_arg(__u64 x) +{ + return vals[x]; /* x is forced to be precise */ +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("8: (0f) r2 += r1") +__msg("mark_precise: frame1: last_idx 8 first_idx 0") +__msg("mark_precise: frame1: regs=r1 stack= before 6: (18) r2 = ") +__msg("mark_precise: frame1: regs=r1 stack= before 5: (67) r1 <<= 2") +__msg("mark_precise: frame1: regs=r1 stack= before 2: (85) call pc+2") +__msg("mark_precise: frame0: regs=r1 stack= before 1: (bf) r1 = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 0: (b7) r6 = 3") +__naked int subprog_arg_precise(void) +{ + asm volatile ( + "r6 = 3;" + "r1 = r6;" + /* subprog_with_precise_arg expects its argument to be + * precise, so r1->r6 will be marked precise from inside the + * subprog + */ + "call subprog_with_precise_arg;" + "r0 += r6;" + "exit;" + : + : + : __clobber_common, "r6" + ); +} + +/* r1 is pointer to stack slot; + * r2 is a register to spill into that slot + * subprog also spills r2 into its own stack slot + */ +__naked __noinline __used +static __u64 subprog_spill_reg_precise(void) +{ + asm volatile ( + /* spill to parent stack */ + "*(u64 *)(r1 + 0) = r2;" + /* spill to subprog stack (we use -16 offset to avoid + * accidental confusion with parent's -8 stack slot in + * verifier log output) + */ + "*(u64 *)(r10 - 16) = r2;" + /* use both spills as return result to propagete precision everywhere */ + "r0 = *(u64 *)(r10 - 16);" + "r2 = *(u64 *)(r1 + 0);" + "r0 += r2;" + "exit;" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +/* precision backtracking can't currently handle stack access not through r10, + * so we won't be able to mark stack slot fp-8 as precise, and so will + * fallback to forcing all as precise + */ +__msg("mark_precise: frame0: falling back to forcing all scalars precise") +__naked int subprog_spill_into_parent_stack_slot_precise(void) +{ + asm volatile ( + "r6 = 1;" + + /* pass pointer to stack slot and r6 to subprog; + * r6 will be marked precise and spilled into fp-8 slot, which + * also should be marked precise + */ + "r1 = r10;" + "r1 += -8;" + "r2 = r6;" + "call subprog_spill_reg_precise;" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r7 = *(u64 *)(r10 - 8);" + + "r7 *= 4;" + "r1 = %[vals];" + /* here r7 is forced to be precise and has to be propagated + * back to the beginning, handling subprog call and logic + */ + "r1 += r7;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6", "r7" + ); +} + +__naked __noinline __used +static __u64 subprog_with_checkpoint(void) +{ + asm volatile ( + "r0 = 0;" + /* guaranteed checkpoint if BPF_F_TEST_STATE_FREQ is used */ + "goto +0;" + "exit;" + ); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/vrf_socket_lookup.c b/tools/testing/selftests/bpf/progs/vrf_socket_lookup.c new file mode 100644 index 0000000000000..bcfb6feb38c01 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/vrf_socket_lookup.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include <linux/ip.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/pkt_cls.h> +#include <stdbool.h> + +int lookup_status; +bool test_xdp; +bool tcp_skc; + +#define CUR_NS BPF_F_CURRENT_NETNS + +static void socket_lookup(void *ctx, void *data_end, void *data) +{ + struct ethhdr *eth = data; + struct bpf_sock_tuple *tp; + struct bpf_sock *sk; + struct iphdr *iph; + int tplen; + + if (eth + 1 > data_end) + return; + + if (eth->h_proto != bpf_htons(ETH_P_IP)) + return; + + iph = (struct iphdr *)(eth + 1); + if (iph + 1 > data_end) + return; + + tp = (struct bpf_sock_tuple *)&iph->saddr; + tplen = sizeof(tp->ipv4); + if ((void *)tp + tplen > data_end) + return; + + switch (iph->protocol) { + case IPPROTO_TCP: + if (tcp_skc) + sk = bpf_skc_lookup_tcp(ctx, tp, tplen, CUR_NS, 0); + else + sk = bpf_sk_lookup_tcp(ctx, tp, tplen, CUR_NS, 0); + break; + case IPPROTO_UDP: + sk = bpf_sk_lookup_udp(ctx, tp, tplen, CUR_NS, 0); + break; + default: + return; + } + + lookup_status = 0; + + if (sk) { + bpf_sk_release(sk); + lookup_status = 1; + } +} + +SEC("tc") +int tc_socket_lookup(struct __sk_buff *skb) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + + if (test_xdp) + return TC_ACT_UNSPEC; + + socket_lookup(skb, data_end, data); + return TC_ACT_UNSPEC; +} + +SEC("xdp") +int xdp_socket_lookup(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + + if (!test_xdp) + return XDP_PASS; + + socket_lookup(xdp, data_end, data); + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c index e1c787815e44b..b2dfd7066c6e4 100644 --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -77,7 +77,9 @@ int rx(struct xdp_md *ctx) } err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp); - if (err) + if (!err) + meta->xdp_timestamp = bpf_ktime_get_tai_ns(); + else meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */ err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index ea82921110daf..4d582cac2c09e 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -11,7 +11,6 @@ #include <signal.h> #include <string.h> #include <execinfo.h> /* backtrace */ -#include <linux/membarrier.h> #include <sys/sysinfo.h> /* get_nprocs */ #include <netinet/in.h> #include <sys/select.h> @@ -629,68 +628,6 @@ out: return err; } -static int finit_module(int fd, const char *param_values, int flags) -{ - return syscall(__NR_finit_module, fd, param_values, flags); -} - -static int delete_module(const char *name, int flags) -{ - return syscall(__NR_delete_module, name, flags); -} - -/* - * Trigger synchronize_rcu() in kernel. - */ -int kern_sync_rcu(void) -{ - return syscall(__NR_membarrier, MEMBARRIER_CMD_SHARED, 0, 0); -} - -static void unload_bpf_testmod(void) -{ - if (kern_sync_rcu()) - fprintf(env.stderr, "Failed to trigger kernel-side RCU sync!\n"); - if (delete_module("bpf_testmod", 0)) { - if (errno == ENOENT) { - if (verbose()) - fprintf(stdout, "bpf_testmod.ko is already unloaded.\n"); - return; - } - fprintf(env.stderr, "Failed to unload bpf_testmod.ko from kernel: %d\n", -errno); - return; - } - if (verbose()) - fprintf(stdout, "Successfully unloaded bpf_testmod.ko.\n"); -} - -static int load_bpf_testmod(void) -{ - int fd; - - /* ensure previous instance of the module is unloaded */ - unload_bpf_testmod(); - - if (verbose()) - fprintf(stdout, "Loading bpf_testmod.ko...\n"); - - fd = open("bpf_testmod.ko", O_RDONLY); - if (fd < 0) { - fprintf(env.stderr, "Can't find bpf_testmod.ko kernel module: %d\n", -errno); - return -ENOENT; - } - if (finit_module(fd, "", 0)) { - fprintf(env.stderr, "Failed to load bpf_testmod.ko into the kernel: %d\n", -errno); - close(fd); - return -EINVAL; - } - close(fd); - - if (verbose()) - fprintf(stdout, "Successfully loaded bpf_testmod.ko.\n"); - return 0; -} - /* extern declarations for test funcs */ #define DEFINE_TEST(name) \ extern void test_##name(void) __weak; \ @@ -714,7 +651,13 @@ static struct test_state test_states[ARRAY_SIZE(prog_test_defs)]; const char *argp_program_version = "test_progs 0.1"; const char *argp_program_bug_address = "<bpf@vger.kernel.org>"; -static const char argp_program_doc[] = "BPF selftests test runner"; +static const char argp_program_doc[] = +"BPF selftests test runner\v" +"Options accepting the NAMES parameter take either a comma-separated list\n" +"of test names, or a filename prefixed with @. The file contains one name\n" +"(or wildcard pattern) per line, and comments beginning with # are ignored.\n" +"\n" +"These options can be passed repeatedly to read multiple files.\n"; enum ARG_KEYS { ARG_TEST_NUM = 'n', @@ -797,6 +740,7 @@ extern int extra_prog_load_log_flags; static error_t parse_arg(int key, char *arg, struct argp_state *state) { struct test_env *env = state->input; + int err = 0; switch (key) { case ARG_TEST_NUM: { @@ -821,18 +765,28 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) } case ARG_TEST_NAME_GLOB_ALLOWLIST: case ARG_TEST_NAME: { - if (parse_test_list(arg, - &env->test_selector.whitelist, - key == ARG_TEST_NAME_GLOB_ALLOWLIST)) - return -ENOMEM; + if (arg[0] == '@') + err = parse_test_list_file(arg + 1, + &env->test_selector.whitelist, + key == ARG_TEST_NAME_GLOB_ALLOWLIST); + else + err = parse_test_list(arg, + &env->test_selector.whitelist, + key == ARG_TEST_NAME_GLOB_ALLOWLIST); + break; } case ARG_TEST_NAME_GLOB_DENYLIST: case ARG_TEST_NAME_BLACKLIST: { - if (parse_test_list(arg, - &env->test_selector.blacklist, - key == ARG_TEST_NAME_GLOB_DENYLIST)) - return -ENOMEM; + if (arg[0] == '@') + err = parse_test_list_file(arg + 1, + &env->test_selector.blacklist, + key == ARG_TEST_NAME_GLOB_DENYLIST); + else + err = parse_test_list(arg, + &env->test_selector.blacklist, + key == ARG_TEST_NAME_GLOB_DENYLIST); + break; } case ARG_VERIFIER_STATS: @@ -900,7 +854,7 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) default: return ARGP_ERR_UNKNOWN; } - return 0; + return err; } /* @@ -1703,9 +1657,14 @@ int main(int argc, char **argv) env.stderr = stderr; env.has_testmod = true; - if (!env.list_test_names && load_bpf_testmod()) { - fprintf(env.stderr, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n"); - env.has_testmod = false; + if (!env.list_test_names) { + /* ensure previous instance of the module is unloaded */ + unload_bpf_testmod(verbose()); + + if (load_bpf_testmod(verbose())) { + fprintf(env.stderr, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n"); + env.has_testmod = false; + } } /* initializing tests */ @@ -1802,7 +1761,7 @@ int main(int argc, char **argv) close(env.saved_netns_fd); out: if (!env.list_test_names && env.has_testmod) - unload_bpf_testmod(); + unload_bpf_testmod(verbose()); free_test_selector(&env.test_selector); free_test_selector(&env.subtest_selector); diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 0ed3134333d41..77bd492c60248 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -405,7 +405,6 @@ static inline void *u64_to_ptr(__u64 ptr) int bpf_find_map(const char *test, struct bpf_object *obj, const char *name); int compare_map_keys(int map1_fd, int map2_fd); int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len); -int kern_sync_rcu(void); int trigger_module_test_read(int read_sz); int trigger_module_test_write(int write_sz); int write_sysctl(const char *sysctl, const char *value); diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index e4657c5bc3f12..31f1c935cd07d 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -40,6 +40,7 @@ #include "bpf_util.h" #include "test_btf.h" #include "../../../include/linux/filter.h" +#include "testing_helpers.h" #ifndef ENOTSUPP #define ENOTSUPP 524 @@ -873,8 +874,140 @@ static int create_map_kptr(void) return fd; } +static void set_root(bool set) +{ + __u64 caps; + + if (set) { + if (cap_enable_effective(1ULL << CAP_SYS_ADMIN, &caps)) + perror("cap_disable_effective(CAP_SYS_ADMIN)"); + } else { + if (cap_disable_effective(1ULL << CAP_SYS_ADMIN, &caps)) + perror("cap_disable_effective(CAP_SYS_ADMIN)"); + } +} + +static __u64 ptr_to_u64(const void *ptr) +{ + return (uintptr_t) ptr; +} + +static struct btf *btf__load_testmod_btf(struct btf *vmlinux) +{ + struct bpf_btf_info info; + __u32 len = sizeof(info); + struct btf *btf = NULL; + char name[64]; + __u32 id = 0; + int err, fd; + + /* Iterate all loaded BTF objects and find bpf_testmod, + * we need SYS_ADMIN cap for that. + */ + set_root(true); + + while (true) { + err = bpf_btf_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + break; + perror("bpf_btf_get_next_id failed"); + break; + } + + fd = bpf_btf_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + perror("bpf_btf_get_fd_by_id failed"); + break; + } + + memset(&info, 0, sizeof(info)); + info.name_len = sizeof(name); + info.name = ptr_to_u64(name); + len = sizeof(info); + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + close(fd); + perror("bpf_obj_get_info_by_fd failed"); + break; + } + + if (strcmp("bpf_testmod", name)) { + close(fd); + continue; + } + + btf = btf__load_from_kernel_by_id_split(id, vmlinux); + if (!btf) { + close(fd); + break; + } + + /* We need the fd to stay open so it can be used in fd_array. + * The final cleanup call to btf__free will free btf object + * and close the file descriptor. + */ + btf__set_fd(btf, fd); + break; + } + + set_root(false); + return btf; +} + +static struct btf *testmod_btf; +static struct btf *vmlinux_btf; + +static void kfuncs_cleanup(void) +{ + btf__free(testmod_btf); + btf__free(vmlinux_btf); +} + +static void fixup_prog_kfuncs(struct bpf_insn *prog, int *fd_array, + struct kfunc_btf_id_pair *fixup_kfunc_btf_id) +{ + /* Patch in kfunc BTF IDs */ + while (fixup_kfunc_btf_id->kfunc) { + int btf_id = 0; + + /* try to find kfunc in kernel BTF */ + vmlinux_btf = vmlinux_btf ?: btf__load_vmlinux_btf(); + if (vmlinux_btf) { + btf_id = btf__find_by_name_kind(vmlinux_btf, + fixup_kfunc_btf_id->kfunc, + BTF_KIND_FUNC); + btf_id = btf_id < 0 ? 0 : btf_id; + } + + /* kfunc not found in kernel BTF, try bpf_testmod BTF */ + if (!btf_id) { + testmod_btf = testmod_btf ?: btf__load_testmod_btf(vmlinux_btf); + if (testmod_btf) { + btf_id = btf__find_by_name_kind(testmod_btf, + fixup_kfunc_btf_id->kfunc, + BTF_KIND_FUNC); + btf_id = btf_id < 0 ? 0 : btf_id; + if (btf_id) { + /* We put bpf_testmod module fd into fd_array + * and its index 1 into instruction 'off'. + */ + *fd_array = btf__fd(testmod_btf); + prog[fixup_kfunc_btf_id->insn_idx].off = 1; + } + } + } + + prog[fixup_kfunc_btf_id->insn_idx].imm = btf_id; + fixup_kfunc_btf_id++; + } +} + static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, - struct bpf_insn *prog, int *map_fds) + struct bpf_insn *prog, int *map_fds, int *fd_array) { int *fixup_map_hash_8b = test->fixup_map_hash_8b; int *fixup_map_hash_48b = test->fixup_map_hash_48b; @@ -899,7 +1032,6 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_ringbuf = test->fixup_map_ringbuf; int *fixup_map_timer = test->fixup_map_timer; int *fixup_map_kptr = test->fixup_map_kptr; - struct kfunc_btf_id_pair *fixup_kfunc_btf_id = test->fixup_kfunc_btf_id; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -1100,25 +1232,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, } while (*fixup_map_kptr); } - /* Patch in kfunc BTF IDs */ - if (fixup_kfunc_btf_id->kfunc) { - struct btf *btf; - int btf_id; - - do { - btf_id = 0; - btf = btf__load_vmlinux_btf(); - if (btf) { - btf_id = btf__find_by_name_kind(btf, - fixup_kfunc_btf_id->kfunc, - BTF_KIND_FUNC); - btf_id = btf_id < 0 ? 0 : btf_id; - } - btf__free(btf); - prog[fixup_kfunc_btf_id->insn_idx].imm = btf_id; - fixup_kfunc_btf_id++; - } while (fixup_kfunc_btf_id->kfunc); - } + fixup_prog_kfuncs(prog, fd_array, test->fixup_kfunc_btf_id); } struct libcap { @@ -1227,45 +1341,46 @@ static bool cmp_str_seq(const char *log, const char *exp) return true; } -static int get_xlated_program(int fd_prog, struct bpf_insn **buf, int *cnt) +static struct bpf_insn *get_xlated_program(int fd_prog, int *cnt) { + __u32 buf_element_size = sizeof(struct bpf_insn); struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); __u32 xlated_prog_len; - __u32 buf_element_size = sizeof(struct bpf_insn); + struct bpf_insn *buf; if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) { perror("bpf_prog_get_info_by_fd failed"); - return -1; + return NULL; } xlated_prog_len = info.xlated_prog_len; if (xlated_prog_len % buf_element_size) { printf("Program length %d is not multiple of %d\n", xlated_prog_len, buf_element_size); - return -1; + return NULL; } *cnt = xlated_prog_len / buf_element_size; - *buf = calloc(*cnt, buf_element_size); + buf = calloc(*cnt, buf_element_size); if (!buf) { perror("can't allocate xlated program buffer"); - return -ENOMEM; + return NULL; } bzero(&info, sizeof(info)); info.xlated_prog_len = xlated_prog_len; - info.xlated_prog_insns = (__u64)(unsigned long)*buf; + info.xlated_prog_insns = (__u64)(unsigned long)buf; if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) { perror("second bpf_prog_get_info_by_fd failed"); goto out_free_buf; } - return 0; + return buf; out_free_buf: - free(*buf); - return -1; + free(buf); + return NULL; } static bool is_null_insn(struct bpf_insn *insn) @@ -1398,7 +1513,8 @@ static bool check_xlated_program(struct bpf_test *test, int fd_prog) if (!check_expected && !check_unexpected) goto out; - if (get_xlated_program(fd_prog, &buf, &cnt)) { + buf = get_xlated_program(fd_prog, &cnt); + if (!buf) { printf("FAIL: can't get xlated program\n"); result = false; goto out; @@ -1445,6 +1561,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, int run_errs, run_successes; int map_fds[MAX_NR_MAPS]; const char *expected_err; + int fd_array[2] = { -1, -1 }; int saved_errno; int fixup_skips; __u32 pflags; @@ -1458,7 +1575,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, if (!prog_type) prog_type = BPF_PROG_TYPE_SOCKET_FILTER; fixup_skips = skips; - do_test_fixup(test, prog_type, prog, map_fds); + do_test_fixup(test, prog_type, prog, map_fds, &fd_array[1]); if (test->fill_insns) { prog = test->fill_insns; prog_len = test->prog_len; @@ -1492,6 +1609,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv, else opts.log_level = DEFAULT_LIBBPF_LOG_LEVEL; opts.prog_flags = pflags; + if (fd_array[1] != -1) + opts.fd_array = &fd_array[0]; if ((prog_type == BPF_PROG_TYPE_TRACING || prog_type == BPF_PROG_TYPE_LSM) && test->kfunc) { @@ -1684,6 +1803,12 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to) { int i, passes = 0, errors = 0; + /* ensure previous instance of the module is unloaded */ + unload_bpf_testmod(verbose); + + if (load_bpf_testmod(verbose)) + return EXIT_FAILURE; + for (i = from; i < to; i++) { struct bpf_test *test = &tests[i]; @@ -1711,6 +1836,9 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to) } } + unload_bpf_testmod(verbose); + kfuncs_cleanup(); + printf("Summary: %d PASSED, %d SKIPPED, %d FAILED\n", passes, skips, errors); return errors ? EXIT_FAILURE : EXIT_SUCCESS; diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh index 377fb157a57c5..c2ad50f26b636 100755 --- a/tools/testing/selftests/bpf/test_xsk.sh +++ b/tools/testing/selftests/bpf/test_xsk.sh @@ -68,9 +68,6 @@ # Run with verbose output: # sudo ./test_xsk.sh -v # -# Run and dump packet contents: -# sudo ./test_xsk.sh -D -# # Set up veth interfaces and leave them up so xskxceiver can be launched in a debugger: # sudo ./test_xsk.sh -d # @@ -81,11 +78,10 @@ ETH="" -while getopts "vDi:d" flag +while getopts "vi:d" flag do case "${flag}" in v) verbose=1;; - D) dump_pkts=1;; d) debug=1;; i) ETH=${OPTARG};; esac @@ -157,10 +153,6 @@ if [[ $verbose -eq 1 ]]; then ARGS+="-v " fi -if [[ $dump_pkts -eq 1 ]]; then - ARGS="-D " -fi - retval=$? test_status $retval "${TEST_NAME}" diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index 0b5e0829e5bee..8d994884c7b44 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) /* Copyright (C) 2019 Netronome Systems, Inc. */ /* Copyright (C) 2020 Facebook, Inc. */ +#include <ctype.h> #include <stdlib.h> #include <string.h> #include <errno.h> @@ -8,6 +9,7 @@ #include <bpf/libbpf.h> #include "test_progs.h" #include "testing_helpers.h" +#include <linux/membarrier.h> int parse_num_list(const char *s, bool **num_set, int *num_set_len) { @@ -70,92 +72,168 @@ int parse_num_list(const char *s, bool **num_set, int *num_set_len) return 0; } -int parse_test_list(const char *s, - struct test_filter_set *set, - bool is_glob_pattern) +static int do_insert_test(struct test_filter_set *set, + char *test_str, + char *subtest_str) { - char *input, *state = NULL, *next; - struct test_filter *tmp, *tests = NULL; - int i, j, cnt = 0; + struct test_filter *tmp, *test; + char **ctmp; + int i; - input = strdup(s); - if (!input) + for (i = 0; i < set->cnt; i++) { + test = &set->tests[i]; + + if (strcmp(test_str, test->name) == 0) { + free(test_str); + goto subtest; + } + } + + tmp = realloc(set->tests, sizeof(*test) * (set->cnt + 1)); + if (!tmp) return -ENOMEM; - while ((next = strtok_r(state ? NULL : input, ",", &state))) { - char *subtest_str = strchr(next, '/'); - char *pattern = NULL; - int glob_chars = 0; + set->tests = tmp; + test = &set->tests[set->cnt]; - tmp = realloc(tests, sizeof(*tests) * (cnt + 1)); - if (!tmp) - goto err; - tests = tmp; + test->name = test_str; + test->subtests = NULL; + test->subtest_cnt = 0; - tests[cnt].subtest_cnt = 0; - tests[cnt].subtests = NULL; + set->cnt++; - if (is_glob_pattern) { - pattern = "%s"; - } else { - pattern = "*%s*"; - glob_chars = 2; - } +subtest: + if (!subtest_str) + return 0; - if (subtest_str) { - char **tmp_subtests = NULL; - int subtest_cnt = tests[cnt].subtest_cnt; - - *subtest_str = '\0'; - subtest_str += 1; - tmp_subtests = realloc(tests[cnt].subtests, - sizeof(*tmp_subtests) * - (subtest_cnt + 1)); - if (!tmp_subtests) - goto err; - tests[cnt].subtests = tmp_subtests; - - tests[cnt].subtests[subtest_cnt] = - malloc(strlen(subtest_str) + glob_chars + 1); - if (!tests[cnt].subtests[subtest_cnt]) - goto err; - sprintf(tests[cnt].subtests[subtest_cnt], - pattern, - subtest_str); - - tests[cnt].subtest_cnt++; + for (i = 0; i < test->subtest_cnt; i++) { + if (strcmp(subtest_str, test->subtests[i]) == 0) { + free(subtest_str); + return 0; } + } - tests[cnt].name = malloc(strlen(next) + glob_chars + 1); - if (!tests[cnt].name) - goto err; - sprintf(tests[cnt].name, pattern, next); + ctmp = realloc(test->subtests, + sizeof(*test->subtests) * (test->subtest_cnt + 1)); + if (!ctmp) + return -ENOMEM; - cnt++; + test->subtests = ctmp; + test->subtests[test->subtest_cnt] = subtest_str; + + test->subtest_cnt++; + + return 0; +} + +static int insert_test(struct test_filter_set *set, + char *test_spec, + bool is_glob_pattern) +{ + char *pattern, *subtest_str, *ext_test_str, *ext_subtest_str = NULL; + int glob_chars = 0; + + if (is_glob_pattern) { + pattern = "%s"; + } else { + pattern = "*%s*"; + glob_chars = 2; } - tmp = realloc(set->tests, sizeof(*tests) * (cnt + set->cnt)); - if (!tmp) + subtest_str = strchr(test_spec, '/'); + if (subtest_str) { + *subtest_str = '\0'; + subtest_str += 1; + } + + ext_test_str = malloc(strlen(test_spec) + glob_chars + 1); + if (!ext_test_str) goto err; - memcpy(tmp + set->cnt, tests, sizeof(*tests) * cnt); - set->tests = tmp; - set->cnt += cnt; + sprintf(ext_test_str, pattern, test_spec); - free(tests); - free(input); - return 0; + if (subtest_str) { + ext_subtest_str = malloc(strlen(subtest_str) + glob_chars + 1); + if (!ext_subtest_str) + goto err; + + sprintf(ext_subtest_str, pattern, subtest_str); + } + + return do_insert_test(set, ext_test_str, ext_subtest_str); err: - for (i = 0; i < cnt; i++) { - for (j = 0; j < tests[i].subtest_cnt; j++) - free(tests[i].subtests[j]); + free(ext_test_str); + free(ext_subtest_str); + + return -ENOMEM; +} + +int parse_test_list_file(const char *path, + struct test_filter_set *set, + bool is_glob_pattern) +{ + char *buf = NULL, *capture_start, *capture_end, *scan_end; + size_t buflen = 0; + int err = 0; + FILE *f; + + f = fopen(path, "r"); + if (!f) { + err = -errno; + fprintf(stderr, "Failed to open '%s': %d\n", path, err); + return err; + } + + while (getline(&buf, &buflen, f) != -1) { + capture_start = buf; + + while (isspace(*capture_start)) + ++capture_start; + + capture_end = capture_start; + scan_end = capture_start; + + while (*scan_end && *scan_end != '#') { + if (!isspace(*scan_end)) + capture_end = scan_end; + + ++scan_end; + } + + if (capture_end == capture_start) + continue; + + *(++capture_end) = '\0'; + + err = insert_test(set, capture_start, is_glob_pattern); + if (err) + break; + } + + fclose(f); + return err; +} + +int parse_test_list(const char *s, + struct test_filter_set *set, + bool is_glob_pattern) +{ + char *input, *state = NULL, *test_spec; + int err = 0; + + input = strdup(s); + if (!input) + return -ENOMEM; - free(tests[i].name); + while ((test_spec = strtok_r(state ? NULL : input, ",", &state))) { + err = insert_test(set, test_spec, is_glob_pattern); + if (err) + break; } - free(tests); + free(input); - return -ENOMEM; + return err; } __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info) @@ -249,3 +327,63 @@ __u64 read_perf_max_sample_freq(void) fclose(f); return sample_freq; } + +static int finit_module(int fd, const char *param_values, int flags) +{ + return syscall(__NR_finit_module, fd, param_values, flags); +} + +static int delete_module(const char *name, int flags) +{ + return syscall(__NR_delete_module, name, flags); +} + +int unload_bpf_testmod(bool verbose) +{ + if (kern_sync_rcu()) + fprintf(stdout, "Failed to trigger kernel-side RCU sync!\n"); + if (delete_module("bpf_testmod", 0)) { + if (errno == ENOENT) { + if (verbose) + fprintf(stdout, "bpf_testmod.ko is already unloaded.\n"); + return -1; + } + fprintf(stdout, "Failed to unload bpf_testmod.ko from kernel: %d\n", -errno); + return -1; + } + if (verbose) + fprintf(stdout, "Successfully unloaded bpf_testmod.ko.\n"); + return 0; +} + +int load_bpf_testmod(bool verbose) +{ + int fd; + + if (verbose) + fprintf(stdout, "Loading bpf_testmod.ko...\n"); + + fd = open("bpf_testmod.ko", O_RDONLY); + if (fd < 0) { + fprintf(stdout, "Can't find bpf_testmod.ko kernel module: %d\n", -errno); + return -ENOENT; + } + if (finit_module(fd, "", 0)) { + fprintf(stdout, "Failed to load bpf_testmod.ko into the kernel: %d\n", -errno); + close(fd); + return -EINVAL; + } + close(fd); + + if (verbose) + fprintf(stdout, "Successfully loaded bpf_testmod.ko.\n"); + return 0; +} + +/* + * Trigger synchronize_rcu() in kernel. + */ +int kern_sync_rcu(void) +{ + return syscall(__NR_membarrier, MEMBARRIER_CMD_SHARED, 0, 0); +} diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h index eb8790f928e4c..5312323881b65 100644 --- a/tools/testing/selftests/bpf/testing_helpers.h +++ b/tools/testing/selftests/bpf/testing_helpers.h @@ -1,5 +1,9 @@ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ /* Copyright (C) 2020 Facebook, Inc. */ + +#ifndef __TESTING_HELPERS_H +#define __TESTING_HELPERS_H + #include <stdbool.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> @@ -20,5 +24,13 @@ struct test_filter_set; int parse_test_list(const char *s, struct test_filter_set *test_set, bool is_glob_pattern); +int parse_test_list_file(const char *path, + struct test_filter_set *test_set, + bool is_glob_pattern); __u64 read_perf_max_sample_freq(void); +int load_bpf_testmod(bool verbose); +int unload_bpf_testmod(bool verbose); +int kern_sync_rcu(void); + +#endif /* __TESTING_HELPERS_H */ diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c index 6c03a7d805f9d..99272bb890da8 100644 --- a/tools/testing/selftests/bpf/verifier/precise.c +++ b/tools/testing/selftests/bpf/verifier/precise.c @@ -38,25 +38,24 @@ .fixup_map_array_48b = { 1 }, .result = VERBOSE_ACCEPT, .errstr = - "26: (85) call bpf_probe_read_kernel#113\ - last_idx 26 first_idx 20\ - regs=4 stack=0 before 25\ - regs=4 stack=0 before 24\ - regs=4 stack=0 before 23\ - regs=4 stack=0 before 22\ - regs=4 stack=0 before 20\ - parent didn't have regs=4 stack=0 marks\ - last_idx 19 first_idx 10\ - regs=4 stack=0 before 19\ - regs=200 stack=0 before 18\ - regs=300 stack=0 before 17\ - regs=201 stack=0 before 15\ - regs=201 stack=0 before 14\ - regs=200 stack=0 before 13\ - regs=200 stack=0 before 12\ - regs=200 stack=0 before 11\ - regs=200 stack=0 before 10\ - parent already had regs=0 stack=0 marks", + "mark_precise: frame0: last_idx 26 first_idx 20\ + mark_precise: frame0: regs=r2 stack= before 25\ + mark_precise: frame0: regs=r2 stack= before 24\ + mark_precise: frame0: regs=r2 stack= before 23\ + mark_precise: frame0: regs=r2 stack= before 22\ + mark_precise: frame0: regs=r2 stack= before 20\ + mark_precise: frame0: parent state regs=r2 stack=:\ + mark_precise: frame0: last_idx 19 first_idx 10\ + mark_precise: frame0: regs=r2,r9 stack= before 19\ + mark_precise: frame0: regs=r9 stack= before 18\ + mark_precise: frame0: regs=r8,r9 stack= before 17\ + mark_precise: frame0: regs=r0,r9 stack= before 15\ + mark_precise: frame0: regs=r0,r9 stack= before 14\ + mark_precise: frame0: regs=r9 stack= before 13\ + mark_precise: frame0: regs=r9 stack= before 12\ + mark_precise: frame0: regs=r9 stack= before 11\ + mark_precise: frame0: regs=r9 stack= before 10\ + mark_precise: frame0: parent state regs= stack=:", }, { "precise: test 2", @@ -100,20 +99,20 @@ .flags = BPF_F_TEST_STATE_FREQ, .errstr = "26: (85) call bpf_probe_read_kernel#113\ - last_idx 26 first_idx 22\ - regs=4 stack=0 before 25\ - regs=4 stack=0 before 24\ - regs=4 stack=0 before 23\ - regs=4 stack=0 before 22\ - parent didn't have regs=4 stack=0 marks\ - last_idx 20 first_idx 20\ - regs=4 stack=0 before 20\ - parent didn't have regs=4 stack=0 marks\ - last_idx 19 first_idx 17\ - regs=4 stack=0 before 19\ - regs=200 stack=0 before 18\ - regs=300 stack=0 before 17\ - parent already had regs=0 stack=0 marks", + mark_precise: frame0: last_idx 26 first_idx 22\ + mark_precise: frame0: regs=r2 stack= before 25\ + mark_precise: frame0: regs=r2 stack= before 24\ + mark_precise: frame0: regs=r2 stack= before 23\ + mark_precise: frame0: regs=r2 stack= before 22\ + mark_precise: frame0: parent state regs=r2 stack=:\ + mark_precise: frame0: last_idx 20 first_idx 20\ + mark_precise: frame0: regs=r2,r9 stack= before 20\ + mark_precise: frame0: parent state regs=r2,r9 stack=:\ + mark_precise: frame0: last_idx 19 first_idx 17\ + mark_precise: frame0: regs=r2,r9 stack= before 19\ + mark_precise: frame0: regs=r9 stack= before 18\ + mark_precise: frame0: regs=r8,r9 stack= before 17\ + mark_precise: frame0: parent state regs= stack=:", }, { "precise: cross frame pruning", @@ -153,15 +152,16 @@ }, .prog_type = BPF_PROG_TYPE_XDP, .flags = BPF_F_TEST_STATE_FREQ, - .errstr = "5: (2d) if r4 > r0 goto pc+0\ - last_idx 5 first_idx 5\ - parent didn't have regs=10 stack=0 marks\ - last_idx 4 first_idx 2\ - regs=10 stack=0 before 4\ - regs=10 stack=0 before 3\ - regs=0 stack=1 before 2\ - last_idx 5 first_idx 5\ - parent didn't have regs=1 stack=0 marks", + .errstr = "mark_precise: frame0: last_idx 5 first_idx 5\ + mark_precise: frame0: parent state regs=r4 stack=:\ + mark_precise: frame0: last_idx 4 first_idx 2\ + mark_precise: frame0: regs=r4 stack= before 4\ + mark_precise: frame0: regs=r4 stack= before 3\ + mark_precise: frame0: regs= stack=-8 before 2\ + mark_precise: frame0: falling back to forcing all scalars precise\ + force_precise: frame0: forcing r0 to be precise\ + mark_precise: frame0: last_idx 5 first_idx 5\ + mark_precise: frame0: parent state regs= stack=:", .result = VERBOSE_ACCEPT, .retval = -1, }, @@ -179,16 +179,19 @@ }, .prog_type = BPF_PROG_TYPE_XDP, .flags = BPF_F_TEST_STATE_FREQ, - .errstr = "last_idx 6 first_idx 6\ - parent didn't have regs=10 stack=0 marks\ - last_idx 5 first_idx 3\ - regs=10 stack=0 before 5\ - regs=10 stack=0 before 4\ - regs=0 stack=1 before 3\ - last_idx 6 first_idx 6\ - parent didn't have regs=1 stack=0 marks\ - last_idx 5 first_idx 3\ - regs=1 stack=0 before 5", + .errstr = "mark_precise: frame0: last_idx 6 first_idx 6\ + mark_precise: frame0: parent state regs=r4 stack=:\ + mark_precise: frame0: last_idx 5 first_idx 3\ + mark_precise: frame0: regs=r4 stack= before 5\ + mark_precise: frame0: regs=r4 stack= before 4\ + mark_precise: frame0: regs= stack=-8 before 3\ + mark_precise: frame0: falling back to forcing all scalars precise\ + force_precise: frame0: forcing r0 to be precise\ + force_precise: frame0: forcing r0 to be precise\ + force_precise: frame0: forcing r0 to be precise\ + force_precise: frame0: forcing r0 to be precise\ + mark_precise: frame0: last_idx 6 first_idx 6\ + mark_precise: frame0: parent state regs= stack=:", .result = VERBOSE_ACCEPT, .retval = -1, }, @@ -217,3 +220,39 @@ .errstr = "invalid access to memory, mem_size=1 off=42 size=8", .result = REJECT, }, +{ + "precise: program doesn't prematurely prune branches", + .insns = { + BPF_ALU64_IMM(BPF_MOV, BPF_REG_6, 0x400), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_8, 0), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_9, 0x80000000), + BPF_ALU64_IMM(BPF_MOD, BPF_REG_6, 0x401), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), + BPF_JMP_REG(BPF_JLE, BPF_REG_6, BPF_REG_9, 2), + BPF_ALU64_IMM(BPF_MOD, BPF_REG_6, 1), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_9, 0), + BPF_JMP_REG(BPF_JLE, BPF_REG_6, BPF_REG_9, 1), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_6, 0), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), + BPF_LD_MAP_FD(BPF_REG_4, 0), + BPF_ALU64_REG(BPF_MOV, BPF_REG_1, BPF_REG_4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_6, 10), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_6, 8192), + BPF_ALU64_REG(BPF_MOV, BPF_REG_1, BPF_REG_0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_6), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_3, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 13 }, + .prog_type = BPF_PROG_TYPE_XDP, + .result = REJECT, + .errstr = "register with unbounded min value is not allowed", +}, diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index 1db7185181dab..655095810d4a1 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -141,6 +141,7 @@ static struct env { bool verbose; bool debug; bool quiet; + bool force_checkpoints; enum resfmt out_fmt; bool show_version; bool comparison_mode; @@ -209,6 +210,8 @@ static const struct argp_option opts[] = { { "log-level", 'l', "LEVEL", 0, "Verifier log level (default 0 for normal mode, 1 for verbose mode)" }, { "log-fixed", OPT_LOG_FIXED, NULL, 0, "Disable verifier log rotation" }, { "log-size", OPT_LOG_SIZE, "BYTES", 0, "Customize verifier log size (default to 16MB)" }, + { "test-states", 't', NULL, 0, + "Force frequent BPF verifier state checkpointing (set BPF_F_TEST_STATE_FREQ program flag)" }, { "quiet", 'q', NULL, 0, "Quiet mode" }, { "emit", 'e', "SPEC", 0, "Specify stats to be emitted" }, { "sort", 's', "SPEC", 0, "Specify sort order" }, @@ -284,6 +287,9 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) argp_usage(state); } break; + case 't': + env.force_checkpoints = true; + break; case 'C': env.comparison_mode = true; break; @@ -989,6 +995,9 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf /* increase chances of successful BPF object loading */ fixup_obj(obj, prog, base_filename); + if (env.force_checkpoints) + bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_STATE_FREQ); + err = bpf_object__load(obj); env.progs_processed++; diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 987cf0db5ebc8..613321eb84c19 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -27,6 +27,7 @@ #include <sys/mman.h> #include <net/if.h> #include <poll.h> +#include <time.h> #include "xdp_metadata.h" @@ -134,18 +135,52 @@ static void refill_rx(struct xsk *xsk, __u64 addr) } } -static void verify_xdp_metadata(void *data) +#define NANOSEC_PER_SEC 1000000000 /* 10^9 */ +static __u64 gettime(clockid_t clock_id) +{ + struct timespec t; + int res; + + /* See man clock_gettime(2) for type of clock_id's */ + res = clock_gettime(clock_id, &t); + + if (res < 0) + error(res, errno, "Error with clock_gettime()"); + + return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec; +} + +static void verify_xdp_metadata(void *data, clockid_t clock_id) { struct xdp_meta *meta; meta = data - sizeof(*meta); - printf("rx_timestamp: %llu\n", meta->rx_timestamp); if (meta->rx_hash_err < 0) printf("No rx_hash err=%d\n", meta->rx_hash_err); else printf("rx_hash: 0x%X with RSS type:0x%X\n", meta->rx_hash, meta->rx_hash_type); + + printf("rx_timestamp: %llu (sec:%0.4f)\n", meta->rx_timestamp, + (double)meta->rx_timestamp / NANOSEC_PER_SEC); + if (meta->rx_timestamp) { + __u64 usr_clock = gettime(clock_id); + __u64 xdp_clock = meta->xdp_timestamp; + __s64 delta_X = xdp_clock - meta->rx_timestamp; + __s64 delta_X2U = usr_clock - xdp_clock; + + printf("XDP RX-time: %llu (sec:%0.4f) delta sec:%0.4f (%0.3f usec)\n", + xdp_clock, (double)xdp_clock / NANOSEC_PER_SEC, + (double)delta_X / NANOSEC_PER_SEC, + (double)delta_X / 1000); + + printf("AF_XDP time: %llu (sec:%0.4f) delta sec:%0.4f (%0.3f usec)\n", + usr_clock, (double)usr_clock / NANOSEC_PER_SEC, + (double)delta_X2U / NANOSEC_PER_SEC, + (double)delta_X2U / 1000); + } + } static void verify_skb_metadata(int fd) @@ -193,7 +228,7 @@ static void verify_skb_metadata(int fd) printf("skb hwtstamp is not found!\n"); } -static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd) +static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t clock_id) { const struct xdp_desc *rx_desc; struct pollfd fds[rxq + 1]; @@ -243,7 +278,8 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd) addr = xsk_umem__add_offset_to_addr(rx_desc->addr); printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx\n", xsk, idx, rx_desc->addr, addr, comp_addr); - verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr)); + verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr), + clock_id); xsk_ring_cons__release(&xsk->rx, 1); refill_rx(xsk, comp_addr); } @@ -370,6 +406,7 @@ static void timestamping_enable(int fd, int val) int main(int argc, char *argv[]) { + clockid_t clock_id = CLOCK_TAI; int server_fd = -1; int ret; int i; @@ -443,7 +480,7 @@ int main(int argc, char *argv[]) error(1, -ret, "bpf_xdp_attach"); signal(SIGINT, handle_signal); - ret = verify_metadata(rx_xsk, rxq, server_fd); + ret = verify_metadata(rx_xsk, rxq, server_fd, clock_id); close(server_fd); cleanup(); if (ret) diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h index 0c4624dc6f2f7..938a729bd3072 100644 --- a/tools/testing/selftests/bpf/xdp_metadata.h +++ b/tools/testing/selftests/bpf/xdp_metadata.h @@ -11,6 +11,7 @@ struct xdp_meta { __u64 rx_timestamp; + __u64 xdp_timestamp; __u32 rx_hash; union { __u32 rx_hash_type; diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h index 04ed8b5447129..8da8d557768b4 100644 --- a/tools/testing/selftests/bpf/xsk.h +++ b/tools/testing/selftests/bpf/xsk.h @@ -134,6 +134,11 @@ static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, __u32 nb) __atomic_store_n(prod->producer, *prod->producer + nb, __ATOMIC_RELEASE); } +static inline void xsk_ring_prod__cancel(struct xsk_ring_prod *prod, __u32 nb) +{ + prod->cached_prod -= nb; +} + static inline __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __u32 *idx) { __u32 entries = xsk_cons_nb_avail(cons, nb); diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c index f144d0604ddf9..218d7f694e5cf 100644 --- a/tools/testing/selftests/bpf/xskxceiver.c +++ b/tools/testing/selftests/bpf/xskxceiver.c @@ -76,16 +76,13 @@ #include <asm/barrier.h> #include <linux/if_link.h> #include <linux/if_ether.h> -#include <linux/ip.h> #include <linux/mman.h> -#include <linux/udp.h> #include <arpa/inet.h> #include <net/if.h> #include <locale.h> #include <poll.h> #include <pthread.h> #include <signal.h> -#include <stdbool.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -94,10 +91,8 @@ #include <sys/socket.h> #include <sys/time.h> #include <sys/types.h> -#include <sys/queue.h> #include <time.h> #include <unistd.h> -#include <stdatomic.h> #include "xsk_xdp_progs.skel.h" #include "xsk.h" @@ -109,10 +104,6 @@ static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62"; static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61"; -static const char *IP1 = "192.168.100.162"; -static const char *IP2 = "192.168.100.161"; -static const u16 UDP_PORT1 = 2020; -static const u16 UDP_PORT2 = 2121; static void __exit_with_error(int error, const char *file, const char *func, int line) { @@ -147,112 +138,25 @@ static void report_failure(struct test_spec *test) test->fail = true; } -static void memset32_htonl(void *dest, u32 val, u32 size) -{ - u32 *ptr = (u32 *)dest; - int i; - - val = htonl(val); - - for (i = 0; i < (size & (~0x3)); i += 4) - ptr[i >> 2] = val; -} - -/* - * Fold a partial checksum - * This function code has been taken from - * Linux kernel include/asm-generic/checksum.h - */ -static __u16 csum_fold(__u32 csum) -{ - u32 sum = (__force u32)csum; - - sum = (sum & 0xffff) + (sum >> 16); - sum = (sum & 0xffff) + (sum >> 16); - return (__force __u16)~sum; -} - -/* - * This function code has been taken from - * Linux kernel lib/checksum.c - */ -static u32 from64to32(u64 x) -{ - /* add up 32-bit and 32-bit for 32+c bit */ - x = (x & 0xffffffff) + (x >> 32); - /* add up carry.. */ - x = (x & 0xffffffff) + (x >> 32); - return (u32)x; -} - -/* - * This function code has been taken from - * Linux kernel lib/checksum.c - */ -static __u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum) -{ - unsigned long long s = (__force u32)sum; - - s += (__force u32)saddr; - s += (__force u32)daddr; -#ifdef __BIG_ENDIAN__ - s += proto + len; -#else - s += (proto + len) << 8; -#endif - return (__force __u32)from64to32(s); -} - -/* - * This function has been taken from - * Linux kernel include/asm-generic/checksum.h +/* The payload is a word consisting of a packet sequence number in the upper + * 16-bits and a intra packet data sequence number in the lower 16 bits. So the 3rd packet's + * 5th word of data will contain the number (2<<16) | 4 as they are numbered from 0. */ -static __u16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum) -{ - return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum)); -} - -static u16 udp_csum(u32 saddr, u32 daddr, u32 len, u8 proto, u16 *udp_pkt) +static void write_payload(void *dest, u32 pkt_nb, u32 start, u32 size) { - u32 csum = 0; - u32 cnt = 0; - - /* udp hdr and data */ - for (; cnt < len; cnt += 2) - csum += udp_pkt[cnt >> 1]; + u32 *ptr = (u32 *)dest, i; - return csum_tcpudp_magic(saddr, daddr, len, proto, csum); + start /= sizeof(*ptr); + size /= sizeof(*ptr); + for (i = 0; i < size; i++) + ptr[i] = htonl(pkt_nb << 16 | (i + start)); } static void gen_eth_hdr(struct ifobject *ifobject, struct ethhdr *eth_hdr) { memcpy(eth_hdr->h_dest, ifobject->dst_mac, ETH_ALEN); memcpy(eth_hdr->h_source, ifobject->src_mac, ETH_ALEN); - eth_hdr->h_proto = htons(ETH_P_IP); -} - -static void gen_ip_hdr(struct ifobject *ifobject, struct iphdr *ip_hdr) -{ - ip_hdr->version = IP_PKT_VER; - ip_hdr->ihl = 0x5; - ip_hdr->tos = IP_PKT_TOS; - ip_hdr->tot_len = htons(IP_PKT_SIZE); - ip_hdr->id = 0; - ip_hdr->frag_off = 0; - ip_hdr->ttl = IPDEFTTL; - ip_hdr->protocol = IPPROTO_UDP; - ip_hdr->saddr = ifobject->src_ip; - ip_hdr->daddr = ifobject->dst_ip; - ip_hdr->check = 0; -} - -static void gen_udp_hdr(u32 payload, void *pkt, struct ifobject *ifobject, - struct udphdr *udp_hdr) -{ - udp_hdr->source = htons(ifobject->src_port); - udp_hdr->dest = htons(ifobject->dst_port); - udp_hdr->len = htons(UDP_PKT_SIZE); - memset32_htonl(pkt + PKT_HDR_SIZE, payload, UDP_PKT_DATA_SIZE); + eth_hdr->h_proto = htons(ETH_P_LOOPBACK); } static bool is_umem_valid(struct ifobject *ifobj) @@ -260,19 +164,18 @@ static bool is_umem_valid(struct ifobject *ifobj) return !!ifobj->umem->umem; } -static void gen_udp_csum(struct udphdr *udp_hdr, struct iphdr *ip_hdr) +static u32 mode_to_xdp_flags(enum test_mode mode) { - udp_hdr->check = 0; - udp_hdr->check = - udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE, IPPROTO_UDP, (u16 *)udp_hdr); + return (mode == TEST_MODE_SKB) ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE; } -static u32 mode_to_xdp_flags(enum test_mode mode) +static u64 umem_size(struct xsk_umem_info *umem) { - return (mode == TEST_MODE_SKB) ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE; + return umem->num_frames * umem->frame_size; } -static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size) +static int xsk_configure_umem(struct ifobject *ifobj, struct xsk_umem_info *umem, void *buffer, + u64 size) { struct xsk_umem_config cfg = { .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, @@ -292,9 +195,31 @@ static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size return ret; umem->buffer = buffer; + if (ifobj->shared_umem && ifobj->rx_on) { + umem->base_addr = umem_size(umem); + umem->next_buffer = umem_size(umem); + } + return 0; } +static u64 umem_alloc_buffer(struct xsk_umem_info *umem) +{ + u64 addr; + + addr = umem->next_buffer; + umem->next_buffer += umem->frame_size; + if (umem->next_buffer >= umem->base_addr + umem_size(umem)) + umem->next_buffer = umem->base_addr; + + return addr; +} + +static void umem_reset_alloc(struct xsk_umem_info *umem) +{ + umem->next_buffer = 0; +} + static void enable_busy_poll(struct xsk_socket_info *xsk) { int sock_opt; @@ -354,7 +279,7 @@ static bool ifobj_zc_avail(struct ifobject *ifobject) exit_with_error(ENOMEM); } umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; - ret = xsk_configure_umem(umem, bufs, umem_sz); + ret = xsk_configure_umem(ifobject, umem, bufs, umem_sz); if (ret) exit_with_error(-ret); @@ -380,7 +305,6 @@ out: static struct option long_options[] = { {"interface", required_argument, 0, 'i'}, {"busy-poll", no_argument, 0, 'b'}, - {"dump-pkts", no_argument, 0, 'D'}, {"verbose", no_argument, 0, 'v'}, {0, 0, 0, 0} }; @@ -391,7 +315,6 @@ static void usage(const char *prog) " Usage: %s [OPTIONS]\n" " Options:\n" " -i, --interface Use interface\n" - " -D, --dump-pkts Dump packets L2 - L5\n" " -v, --verbose Verbose output\n" " -b, --busy-poll Enable busy poll\n"; @@ -415,7 +338,7 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj opterr = 0; for (;;) { - c = getopt_long(argc, argv, "i:Dvb", long_options, &option_index); + c = getopt_long(argc, argv, "i:vb", long_options, &option_index); if (c == -1) break; @@ -437,9 +360,6 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj interface_nb++; break; - case 'D': - opt_pkt_dump = true; - break; case 'v': opt_verbose = true; break; @@ -482,9 +402,6 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, memset(ifobj->umem, 0, sizeof(*ifobj->umem)); ifobj->umem->num_frames = DEFAULT_UMEM_BUFFERS; ifobj->umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; - if (ifobj->shared_umem && ifobj->rx_on) - ifobj->umem->base_addr = DEFAULT_UMEM_BUFFERS * - XSK_UMEM__DEFAULT_FRAME_SIZE; for (j = 0; j < MAX_SOCKETS; j++) { memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j])); @@ -554,24 +471,24 @@ static void test_spec_set_xdp_prog(struct test_spec *test, struct bpf_program *x static void pkt_stream_reset(struct pkt_stream *pkt_stream) { if (pkt_stream) - pkt_stream->rx_pkt_nb = 0; + pkt_stream->current_pkt_nb = 0; } -static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb) +static struct pkt *pkt_stream_get_next_tx_pkt(struct pkt_stream *pkt_stream) { - if (pkt_nb >= pkt_stream->nb_pkts) + if (pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts) return NULL; - return &pkt_stream->pkts[pkt_nb]; + return &pkt_stream->pkts[pkt_stream->current_pkt_nb++]; } static struct pkt *pkt_stream_get_next_rx_pkt(struct pkt_stream *pkt_stream, u32 *pkts_sent) { - while (pkt_stream->rx_pkt_nb < pkt_stream->nb_pkts) { + while (pkt_stream->current_pkt_nb < pkt_stream->nb_pkts) { (*pkts_sent)++; - if (pkt_stream->pkts[pkt_stream->rx_pkt_nb].valid) - return &pkt_stream->pkts[pkt_stream->rx_pkt_nb++]; - pkt_stream->rx_pkt_nb++; + if (pkt_stream->pkts[pkt_stream->current_pkt_nb].valid) + return &pkt_stream->pkts[pkt_stream->current_pkt_nb++]; + pkt_stream->current_pkt_nb++; } return NULL; } @@ -616,9 +533,21 @@ static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts) return pkt_stream; } -static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr, u32 len) +static u32 ceil_u32(u32 a, u32 b) +{ + return (a + b - 1) / b; +} + +static u32 pkt_nb_frags(u32 frame_size, struct pkt *pkt) +{ + if (!pkt || !pkt->valid) + return 1; + return ceil_u32(pkt->len, frame_size); +} + +static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, int offset, u32 len) { - pkt->addr = addr + umem->base_addr; + pkt->offset = offset; pkt->len = len; if (len > umem->frame_size - XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 2 - umem->frame_headroom) pkt->valid = false; @@ -626,6 +555,11 @@ static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr, u32 l pkt->valid = true; } +static u32 pkt_get_buffer_len(struct xsk_umem_info *umem, u32 len) +{ + return ceil_u32(len, umem->frame_size) * umem->frame_size; +} + static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb_pkts, u32 pkt_len) { struct pkt_stream *pkt_stream; @@ -635,10 +569,13 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb if (!pkt_stream) exit_with_error(ENOMEM); + pkt_stream->nb_pkts = nb_pkts; + pkt_stream->max_pkt_len = pkt_len; for (i = 0; i < nb_pkts; i++) { - pkt_set(umem, &pkt_stream->pkts[i], (i % umem->num_frames) * umem->frame_size, - pkt_len); - pkt_stream->pkts[i].payload = i; + struct pkt *pkt = &pkt_stream->pkts[i]; + + pkt_set(umem, pkt, 0, pkt_len); + pkt->pkt_nb = i; } return pkt_stream; @@ -669,8 +606,7 @@ static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len, pkt_stream = pkt_stream_clone(umem, ifobj->pkt_stream); for (i = 1; i < ifobj->pkt_stream->nb_pkts; i += 2) - pkt_set(umem, &pkt_stream->pkts[i], - (i % umem->num_frames) * umem->frame_size + offset, pkt_len); + pkt_set(umem, &pkt_stream->pkts[i], offset, pkt_len); ifobj->pkt_stream = pkt_stream; } @@ -694,30 +630,31 @@ static void pkt_stream_receive_half(struct test_spec *test) pkt_stream->pkts[i].valid = false; } -static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb) +static u64 pkt_get_addr(struct pkt *pkt, struct xsk_umem_info *umem) { - struct pkt *pkt = pkt_stream_get_pkt(ifobject->pkt_stream, pkt_nb); - struct udphdr *udp_hdr; - struct ethhdr *eth_hdr; - struct iphdr *ip_hdr; - void *data; + if (!pkt->valid) + return pkt->offset; + return pkt->offset + umem_alloc_buffer(umem); +} - if (!pkt) - return NULL; - if (!pkt->valid || pkt->len < MIN_PKT_SIZE) - return pkt; +static void pkt_generate(struct ifobject *ifobject, u64 addr, u32 len, u32 pkt_nb, + u32 bytes_written) +{ + void *data = xsk_umem__get_data(ifobject->umem->buffer, addr); - data = xsk_umem__get_data(ifobject->umem->buffer, pkt->addr); - udp_hdr = (struct udphdr *)(data + sizeof(struct ethhdr) + sizeof(struct iphdr)); - ip_hdr = (struct iphdr *)(data + sizeof(struct ethhdr)); - eth_hdr = (struct ethhdr *)data; + if (len < MIN_PKT_SIZE) + return; - gen_udp_hdr(pkt_nb, data, ifobject, udp_hdr); - gen_ip_hdr(ifobject, ip_hdr); - gen_udp_csum(udp_hdr, ip_hdr); - gen_eth_hdr(ifobject, eth_hdr); + if (!bytes_written) { + gen_eth_hdr(ifobject, data); - return pkt; + len -= PKT_HDR_SIZE; + data += PKT_HDR_SIZE; + } else { + bytes_written -= PKT_HDR_SIZE; + } + + write_payload(data, pkt_nb, bytes_written, len); } static void __pkt_stream_generate_custom(struct ifobject *ifobj, @@ -731,10 +668,14 @@ static void __pkt_stream_generate_custom(struct ifobject *ifobj, exit_with_error(ENOMEM); for (i = 0; i < nb_pkts; i++) { - pkt_stream->pkts[i].addr = pkts[i].addr + ifobj->umem->base_addr; - pkt_stream->pkts[i].len = pkts[i].len; - pkt_stream->pkts[i].payload = i; - pkt_stream->pkts[i].valid = pkts[i].valid; + struct pkt *pkt = &pkt_stream->pkts[i]; + + pkt->offset = pkts[i].offset; + pkt->len = pkts[i].len; + pkt->pkt_nb = i; + pkt->valid = pkts[i].valid; + if (pkt->len > pkt_stream->max_pkt_len) + pkt_stream->max_pkt_len = pkt->len; } ifobj->pkt_stream = pkt_stream; @@ -746,53 +687,62 @@ static void pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, __pkt_stream_generate_custom(test->ifobj_rx, pkts, nb_pkts); } -static void pkt_dump(void *pkt, u32 len) -{ - char s[INET_ADDRSTRLEN]; - struct ethhdr *ethhdr; - struct udphdr *udphdr; - struct iphdr *iphdr; - u32 payload, i; - - ethhdr = pkt; - iphdr = pkt + sizeof(*ethhdr); - udphdr = pkt + sizeof(*ethhdr) + sizeof(*iphdr); - - /*extract L2 frame */ - fprintf(stdout, "DEBUG>> L2: dst mac: "); - for (i = 0; i < ETH_ALEN; i++) - fprintf(stdout, "%02X", ethhdr->h_dest[i]); - - fprintf(stdout, "\nDEBUG>> L2: src mac: "); - for (i = 0; i < ETH_ALEN; i++) - fprintf(stdout, "%02X", ethhdr->h_source[i]); - - /*extract L3 frame */ - fprintf(stdout, "\nDEBUG>> L3: ip_hdr->ihl: %02X\n", iphdr->ihl); - fprintf(stdout, "DEBUG>> L3: ip_hdr->saddr: %s\n", - inet_ntop(AF_INET, &iphdr->saddr, s, sizeof(s))); - fprintf(stdout, "DEBUG>> L3: ip_hdr->daddr: %s\n", - inet_ntop(AF_INET, &iphdr->daddr, s, sizeof(s))); - /*extract L4 frame */ - fprintf(stdout, "DEBUG>> L4: udp_hdr->src: %d\n", ntohs(udphdr->source)); - fprintf(stdout, "DEBUG>> L4: udp_hdr->dst: %d\n", ntohs(udphdr->dest)); - /*extract L5 frame */ - payload = ntohl(*((u32 *)(pkt + PKT_HDR_SIZE))); +static void pkt_print_data(u32 *data, u32 cnt) +{ + u32 i; + + for (i = 0; i < cnt; i++) { + u32 seqnum, pkt_nb; - fprintf(stdout, "DEBUG>> L5: payload: %d\n", payload); - fprintf(stdout, "---------------------------------------\n"); + seqnum = ntohl(*data) & 0xffff; + pkt_nb = ntohl(*data) >> 16; + fprintf(stdout, "%u:%u ", pkt_nb, seqnum); + data++; + } } -static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, u64 addr, - u64 pkt_stream_addr) +static void pkt_dump(void *pkt, u32 len, bool eth_header) +{ + struct ethhdr *ethhdr = pkt; + u32 i, *data; + + if (eth_header) { + /*extract L2 frame */ + fprintf(stdout, "DEBUG>> L2: dst mac: "); + for (i = 0; i < ETH_ALEN; i++) + fprintf(stdout, "%02X", ethhdr->h_dest[i]); + + fprintf(stdout, "\nDEBUG>> L2: src mac: "); + for (i = 0; i < ETH_ALEN; i++) + fprintf(stdout, "%02X", ethhdr->h_source[i]); + + data = pkt + PKT_HDR_SIZE; + } else { + data = pkt; + } + + /*extract L5 frame */ + fprintf(stdout, "\nDEBUG>> L5: seqnum: "); + pkt_print_data(data, PKT_DUMP_NB_TO_PRINT); + fprintf(stdout, "...."); + if (len > PKT_DUMP_NB_TO_PRINT * sizeof(u32)) { + fprintf(stdout, "\n.... "); + pkt_print_data(data + len / sizeof(u32) - PKT_DUMP_NB_TO_PRINT, + PKT_DUMP_NB_TO_PRINT); + } + fprintf(stdout, "\n---------------------------------------\n"); +} + +static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr) { u32 headroom = umem->unaligned_mode ? 0 : umem->frame_headroom; - u32 offset = addr % umem->frame_size, expected_offset = 0; + u32 offset = addr % umem->frame_size, expected_offset; + int pkt_offset = pkt->valid ? pkt->offset : 0; - if (!pkt_stream->use_addr_for_fill) - pkt_stream_addr = 0; + if (!umem->unaligned_mode) + pkt_offset = 0; - expected_offset += (pkt_stream_addr + headroom + XDP_PACKET_HEADROOM) % umem->frame_size; + expected_offset = (pkt_offset + headroom + XDP_PACKET_HEADROOM) % umem->frame_size; if (offset == expected_offset) return true; @@ -806,9 +756,9 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr) void *data = xsk_umem__get_data(buffer, addr); struct xdp_info *meta = data - sizeof(struct xdp_info); - if (meta->count != pkt->payload) { + if (meta->count != pkt->pkt_nb) { ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%d]\n", - __func__, pkt->payload, meta->count); + __func__, pkt->pkt_nb, meta->count); return false; } @@ -818,11 +768,11 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr) static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) { void *data = xsk_umem__get_data(buffer, addr); - struct iphdr *iphdr = (struct iphdr *)(data + sizeof(struct ethhdr)); + u32 seqnum, pkt_data; if (!pkt) { ksft_print_msg("[%s] too many packets received\n", __func__); - return false; + goto error; } if (len < MIN_PKT_SIZE || pkt->len < MIN_PKT_SIZE) { @@ -833,28 +783,23 @@ static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) if (pkt->len != len) { ksft_print_msg("[%s] expected length [%d], got length [%d]\n", __func__, pkt->len, len); - return false; + goto error; } - if (iphdr->version == IP_PKT_VER && iphdr->tos == IP_PKT_TOS) { - u32 seqnum = ntohl(*((u32 *)(data + PKT_HDR_SIZE))); - - if (opt_pkt_dump) - pkt_dump(data, PKT_SIZE); + pkt_data = ntohl(*((u32 *)(data + PKT_HDR_SIZE))); + seqnum = pkt_data >> 16; - if (pkt->payload != seqnum) { - ksft_print_msg("[%s] expected seqnum [%d], got seqnum [%d]\n", - __func__, pkt->payload, seqnum); - return false; - } - } else { - ksft_print_msg("Invalid frame received: "); - ksft_print_msg("[IP_PKT_VER: %02X], [IP_PKT_TOS: %02X]\n", iphdr->version, - iphdr->tos); - return false; + if (pkt->pkt_nb != seqnum) { + ksft_print_msg("[%s] expected seqnum [%d], got seqnum [%d]\n", + __func__, pkt->pkt_nb, seqnum); + goto error; } return true; + +error: + pkt_dump(data, len, true); + return false; } static void kick_tx(struct xsk_socket_info *xsk) @@ -976,7 +921,7 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) addr = xsk_umem__add_offset_to_addr(addr); if (!is_pkt_valid(pkt, umem->buffer, addr, desc->len) || - !is_offset_correct(umem, pkt_stream, addr, pkt->addr) || + !is_offset_correct(umem, pkt, addr) || (ifobj->use_metadata && !is_metadata_correct(pkt, umem->buffer, addr))) return TEST_FAILURE; @@ -992,8 +937,6 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) pthread_mutex_lock(&pacing_mutex); pkts_in_flight -= pkts_sent; - if (pkts_in_flight < umem->num_frames) - pthread_cond_signal(&pacing_cond); pthread_mutex_unlock(&pacing_mutex); pkts_sent = 0; } @@ -1001,14 +944,21 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) return TEST_PASS; } -static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb, struct pollfd *fds, - bool timeout) +static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeout) { struct xsk_socket_info *xsk = ifobject->xsk; + struct xsk_umem_info *umem = ifobject->umem; + u32 i, idx = 0, valid_pkts = 0, buffer_len; bool use_poll = ifobject->use_poll; - u32 i, idx = 0, valid_pkts = 0; int ret; + buffer_len = pkt_get_buffer_len(umem, ifobject->pkt_stream->max_pkt_len); + /* pkts_in_flight might be negative if many invalid packets are sent */ + if (pkts_in_flight >= (int)((umem_size(umem) - BATCH_SIZE * buffer_len) / buffer_len)) { + kick_tx(xsk); + return TEST_CONTINUE; + } + while (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) < BATCH_SIZE) { if (use_poll) { ret = poll(fds, 1, POLL_TMOUT); @@ -1034,25 +984,21 @@ static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb, struct pollfd *fd for (i = 0; i < BATCH_SIZE; i++) { struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i); - struct pkt *pkt = pkt_generate(ifobject, *pkt_nb); + struct pkt *pkt = pkt_stream_get_next_tx_pkt(ifobject->pkt_stream); if (!pkt) break; - tx_desc->addr = pkt->addr; + tx_desc->addr = pkt_get_addr(pkt, umem); tx_desc->len = pkt->len; - (*pkt_nb)++; - if (pkt->valid) + if (pkt->valid) { valid_pkts++; + pkt_generate(ifobject, tx_desc->addr, tx_desc->len, pkt->pkt_nb, 0); + } } pthread_mutex_lock(&pacing_mutex); pkts_in_flight += valid_pkts; - /* pkts_in_flight might be negative if many invalid packets are sent */ - if (pkts_in_flight >= (int)(ifobject->umem->num_frames - BATCH_SIZE)) { - kick_tx(xsk); - pthread_cond_wait(&pacing_cond, &pacing_mutex); - } pthread_mutex_unlock(&pacing_mutex); xsk_ring_prod__submit(&xsk->tx, i); @@ -1088,18 +1034,21 @@ static void wait_for_tx_completion(struct xsk_socket_info *xsk) static int send_pkts(struct test_spec *test, struct ifobject *ifobject) { + struct pkt_stream *pkt_stream = ifobject->pkt_stream; bool timeout = !is_umem_valid(test->ifobj_rx); struct pollfd fds = { }; - u32 pkt_cnt = 0, ret; + u32 ret; fds.fd = xsk_socket__fd(ifobject->xsk->xsk); fds.events = POLLOUT; - while (pkt_cnt < ifobject->pkt_stream->nb_pkts) { - ret = __send_pkts(ifobject, &pkt_cnt, &fds, timeout); + while (pkt_stream->current_pkt_nb < pkt_stream->nb_pkts) { + ret = __send_pkts(ifobject, &fds, timeout); + if (ret == TEST_CONTINUE && !test->fail) + continue; if ((ret || test->fail) && !timeout) return TEST_FAILURE; - else if (ret == TEST_PASS && timeout) + if (ret == TEST_PASS && timeout) return ret; } @@ -1249,11 +1198,14 @@ static void thread_common_ops_tx(struct test_spec *test, struct ifobject *ifobje ifobject->xsk = &ifobject->xsk_arr[0]; ifobject->xskmap = test->ifobj_rx->xskmap; memcpy(ifobject->umem, test->ifobj_rx->umem, sizeof(struct xsk_umem_info)); + ifobject->umem->base_addr = 0; } -static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream) +static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, + bool fill_up) { - u32 idx = 0, i, buffers_to_fill; + u32 rx_frame_size = umem->frame_size - XDP_PACKET_HEADROOM; + u32 idx = 0, filled = 0, buffers_to_fill, nb_pkts; int ret; if (umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS) @@ -1264,22 +1216,33 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream ret = xsk_ring_prod__reserve(&umem->fq, buffers_to_fill, &idx); if (ret != buffers_to_fill) exit_with_error(ENOSPC); - for (i = 0; i < buffers_to_fill; i++) { - u64 addr; - if (pkt_stream->use_addr_for_fill) { - struct pkt *pkt = pkt_stream_get_pkt(pkt_stream, i); + while (filled < buffers_to_fill) { + struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &nb_pkts); + u64 addr; + u32 i; + + for (i = 0; i < pkt_nb_frags(rx_frame_size, pkt); i++) { + if (!pkt) { + if (!fill_up) + break; + addr = filled * umem->frame_size + umem->base_addr; + } else if (pkt->offset >= 0) { + addr = pkt->offset % umem->frame_size + umem_alloc_buffer(umem); + } else { + addr = pkt->offset + umem_alloc_buffer(umem); + } - if (!pkt) + *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; + if (++filled >= buffers_to_fill) break; - addr = pkt->addr; - } else { - addr = i * umem->frame_size; } - - *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; } - xsk_ring_prod__submit(&umem->fq, i); + xsk_ring_prod__submit(&umem->fq, filled); + xsk_ring_prod__cancel(&umem->fq, buffers_to_fill - filled); + + pkt_stream_reset(pkt_stream); + umem_reset_alloc(umem); } static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) @@ -1300,12 +1263,10 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) if (bufs == MAP_FAILED) exit_with_error(errno); - ret = xsk_configure_umem(ifobject->umem, bufs, umem_sz); + ret = xsk_configure_umem(ifobject, ifobject->umem, bufs, umem_sz); if (ret) exit_with_error(-ret); - xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream); - xsk_configure_socket(test, ifobject, ifobject->umem, false); ifobject->xsk = &ifobject->xsk_arr[0]; @@ -1313,6 +1274,8 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) if (!ifobject->rx_on) return; + xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream, ifobject->use_fill_ring); + ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk); if (ret) exit_with_error(errno); @@ -1370,12 +1333,8 @@ static void *worker_testapp_validate_rx(void *arg) if (!err && ifobject->validation_func) err = ifobject->validation_func(ifobject); - if (err) { + if (err) report_failure(test); - pthread_mutex_lock(&pacing_mutex); - pthread_cond_signal(&pacing_cond); - pthread_mutex_unlock(&pacing_mutex); - } pthread_exit(NULL); } @@ -1402,11 +1361,20 @@ static void handler(int signum) pthread_exit(NULL); } -static bool xdp_prog_changed(struct test_spec *test, struct ifobject *ifobj) +static bool xdp_prog_changed_rx(struct test_spec *test) { + struct ifobject *ifobj = test->ifobj_rx; + return ifobj->xdp_prog != test->xdp_prog_rx || ifobj->mode != test->mode; } +static bool xdp_prog_changed_tx(struct test_spec *test) +{ + struct ifobject *ifobj = test->ifobj_tx; + + return ifobj->xdp_prog != test->xdp_prog_tx || ifobj->mode != test->mode; +} + static void xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_prog, struct bpf_map *xskmap, enum test_mode mode) { @@ -1433,13 +1401,13 @@ static void xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_pro static void xsk_attach_xdp_progs(struct test_spec *test, struct ifobject *ifobj_rx, struct ifobject *ifobj_tx) { - if (xdp_prog_changed(test, ifobj_rx)) + if (xdp_prog_changed_rx(test)) xsk_reattach_xdp(ifobj_rx, test->xdp_prog_rx, test->xskmap_rx, test->mode); if (!ifobj_tx || ifobj_tx->shared_umem) return; - if (xdp_prog_changed(test, ifobj_tx)) + if (xdp_prog_changed_tx(test)) xsk_reattach_xdp(ifobj_tx, test->xdp_prog_tx, test->xskmap_tx, test->mode); } @@ -1448,9 +1416,11 @@ static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *i { pthread_t t0, t1; - if (ifobj2) + if (ifobj2) { if (pthread_barrier_init(&barr, NULL, 2)) exit_with_error(errno); + pkt_stream_reset(ifobj2->pkt_stream); + } test->current_step++; pkt_stream_reset(ifobj1->pkt_stream); @@ -1493,6 +1463,12 @@ static int testapp_validate_traffic(struct test_spec *test) struct ifobject *ifobj_rx = test->ifobj_rx; struct ifobject *ifobj_tx = test->ifobj_tx; + if ((ifobj_rx->umem->unaligned_mode && !ifobj_rx->unaligned_supp) || + (ifobj_tx->umem->unaligned_mode && !ifobj_tx->unaligned_supp)) { + ksft_test_result_skip("No huge pages present.\n"); + return TEST_SKIP; + } + xsk_attach_xdp_progs(test, ifobj_rx, ifobj_tx); return __testapp_validate_traffic(test, ifobj_rx, ifobj_tx); } @@ -1502,16 +1478,18 @@ static int testapp_validate_traffic_single_thread(struct test_spec *test, struct return __testapp_validate_traffic(test, ifobj, NULL); } -static void testapp_teardown(struct test_spec *test) +static int testapp_teardown(struct test_spec *test) { int i; test_spec_set_name(test, "TEARDOWN"); for (i = 0; i < MAX_TEARDOWN_ITER; i++) { if (testapp_validate_traffic(test)) - return; + return TEST_FAILURE; test_spec_reset(test); } + + return TEST_PASS; } static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2) @@ -1526,20 +1504,23 @@ static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2) *ifobj2 = tmp_ifobj; } -static void testapp_bidi(struct test_spec *test) +static int testapp_bidi(struct test_spec *test) { + int res; + test_spec_set_name(test, "BIDIRECTIONAL"); test->ifobj_tx->rx_on = true; test->ifobj_rx->tx_on = true; test->total_steps = 2; if (testapp_validate_traffic(test)) - return; + return TEST_FAILURE; print_verbose("Switching Tx/Rx vectors\n"); swap_directions(&test->ifobj_rx, &test->ifobj_tx); - __testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx); + res = __testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx); swap_directions(&test->ifobj_rx, &test->ifobj_tx); + return res; } static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx) @@ -1556,160 +1537,139 @@ static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj exit_with_error(errno); } -static void testapp_bpf_res(struct test_spec *test) +static int testapp_bpf_res(struct test_spec *test) { test_spec_set_name(test, "BPF_RES"); test->total_steps = 2; test->nb_sockets = 2; if (testapp_validate_traffic(test)) - return; + return TEST_FAILURE; swap_xsk_resources(test->ifobj_tx, test->ifobj_rx); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_headroom(struct test_spec *test) +static int testapp_headroom(struct test_spec *test) { test_spec_set_name(test, "UMEM_HEADROOM"); test->ifobj_rx->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE; - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_stats_rx_dropped(struct test_spec *test) +static int testapp_stats_rx_dropped(struct test_spec *test) { test_spec_set_name(test, "STAT_RX_DROPPED"); + if (test->mode == TEST_MODE_ZC) { + ksft_test_result_skip("Can not run RX_DROPPED test for ZC mode\n"); + return TEST_SKIP; + } + pkt_stream_replace_half(test, MIN_PKT_SIZE * 4, 0); test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size - XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 3; pkt_stream_receive_half(test); test->ifobj_rx->validation_func = validate_rx_dropped; - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_stats_tx_invalid_descs(struct test_spec *test) +static int testapp_stats_tx_invalid_descs(struct test_spec *test) { test_spec_set_name(test, "STAT_TX_INVALID"); pkt_stream_replace_half(test, XSK_UMEM__INVALID_FRAME_SIZE, 0); test->ifobj_tx->validation_func = validate_tx_invalid_descs; - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_stats_rx_full(struct test_spec *test) +static int testapp_stats_rx_full(struct test_spec *test) { test_spec_set_name(test, "STAT_RX_FULL"); - pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, PKT_SIZE); + pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem, - DEFAULT_UMEM_BUFFERS, PKT_SIZE); - if (!test->ifobj_rx->pkt_stream) - exit_with_error(ENOMEM); + DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS; test->ifobj_rx->release_rx = false; test->ifobj_rx->validation_func = validate_rx_full; - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_stats_fill_empty(struct test_spec *test) +static int testapp_stats_fill_empty(struct test_spec *test) { test_spec_set_name(test, "STAT_RX_FILL_EMPTY"); - pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, PKT_SIZE); + pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem, - DEFAULT_UMEM_BUFFERS, PKT_SIZE); - if (!test->ifobj_rx->pkt_stream) - exit_with_error(ENOMEM); + DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); test->ifobj_rx->use_fill_ring = false; test->ifobj_rx->validation_func = validate_fill_empty; - testapp_validate_traffic(test); -} - -/* Simple test */ -static bool hugepages_present(struct ifobject *ifobject) -{ - size_t mmap_sz = 2 * ifobject->umem->num_frames * ifobject->umem->frame_size; - void *bufs; - - bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | MAP_HUGE_2MB, -1, 0); - if (bufs == MAP_FAILED) - return false; - - mmap_sz = ceil_u64(mmap_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE; - munmap(bufs, mmap_sz); - return true; + return testapp_validate_traffic(test); } -static bool testapp_unaligned(struct test_spec *test) +static int testapp_unaligned(struct test_spec *test) { - if (!hugepages_present(test->ifobj_tx)) { - ksft_test_result_skip("No 2M huge pages present.\n"); - return false; - } - test_spec_set_name(test, "UNALIGNED_MODE"); test->ifobj_tx->umem->unaligned_mode = true; test->ifobj_rx->umem->unaligned_mode = true; - /* Let half of the packets straddle a buffer boundrary */ - pkt_stream_replace_half(test, PKT_SIZE, -PKT_SIZE / 2); - test->ifobj_rx->pkt_stream->use_addr_for_fill = true; - testapp_validate_traffic(test); + /* Let half of the packets straddle a 4K buffer boundary */ + pkt_stream_replace_half(test, MIN_PKT_SIZE, -MIN_PKT_SIZE / 2); - return true; + return testapp_validate_traffic(test); } -static void testapp_single_pkt(struct test_spec *test) +static int testapp_single_pkt(struct test_spec *test) { - struct pkt pkts[] = {{0x1000, PKT_SIZE, 0, true}}; + struct pkt pkts[] = {{0, MIN_PKT_SIZE, 0, true}}; pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_invalid_desc(struct test_spec *test) +static int testapp_invalid_desc(struct test_spec *test) { - u64 umem_size = test->ifobj_tx->umem->num_frames * test->ifobj_tx->umem->frame_size; + struct xsk_umem_info *umem = test->ifobj_tx->umem; + u64 umem_size = umem->num_frames * umem->frame_size; struct pkt pkts[] = { /* Zero packet address allowed */ - {0, PKT_SIZE, 0, true}, + {0, MIN_PKT_SIZE, 0, true}, /* Allowed packet */ - {0x1000, PKT_SIZE, 0, true}, + {0, MIN_PKT_SIZE, 0, true}, /* Straddling the start of umem */ - {-2, PKT_SIZE, 0, false}, + {-2, MIN_PKT_SIZE, 0, false}, /* Packet too large */ - {0x2000, XSK_UMEM__INVALID_FRAME_SIZE, 0, false}, + {0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false}, /* Up to end of umem allowed */ - {umem_size - PKT_SIZE, PKT_SIZE, 0, true}, + {umem_size - MIN_PKT_SIZE - 2 * umem->frame_size, MIN_PKT_SIZE, 0, true}, /* After umem ends */ - {umem_size, PKT_SIZE, 0, false}, + {umem_size, MIN_PKT_SIZE, 0, false}, /* Straddle the end of umem */ - {umem_size - PKT_SIZE / 2, PKT_SIZE, 0, false}, - /* Straddle a page boundrary */ - {0x3000 - PKT_SIZE / 2, PKT_SIZE, 0, false}, - /* Straddle a 2K boundrary */ - {0x3800 - PKT_SIZE / 2, PKT_SIZE, 0, true}, + {umem_size - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false}, + /* Straddle a 4K boundary */ + {0x1000 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false}, + /* Straddle a 2K boundary */ + {0x800 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, true}, /* Valid packet for synch so that something is received */ - {0x4000, PKT_SIZE, 0, true}}; + {0, MIN_PKT_SIZE, 0, true}}; - if (test->ifobj_tx->umem->unaligned_mode) { - /* Crossing a page boundrary allowed */ + if (umem->unaligned_mode) { + /* Crossing a page boundary allowed */ pkts[7].valid = true; } - if (test->ifobj_tx->umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) { - /* Crossing a 2K frame size boundrary not allowed */ + if (umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) { + /* Crossing a 2K frame size boundary not allowed */ pkts[8].valid = false; } if (test->ifobj_tx->shared_umem) { - pkts[4].addr += umem_size; - pkts[5].addr += umem_size; - pkts[6].addr += umem_size; + pkts[4].offset += umem_size; + pkts[5].offset += umem_size; + pkts[6].offset += umem_size; } pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_xdp_drop(struct test_spec *test) +static int testapp_xdp_drop(struct test_spec *test) { struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; @@ -1719,10 +1679,10 @@ static void testapp_xdp_drop(struct test_spec *test) skel_rx->maps.xsk, skel_tx->maps.xsk); pkt_stream_receive_half(test); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_xdp_metadata_count(struct test_spec *test) +static int testapp_xdp_metadata_count(struct test_spec *test) { struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; @@ -1743,10 +1703,10 @@ static void testapp_xdp_metadata_count(struct test_spec *test) if (bpf_map_update_elem(bpf_map__fd(data_map), &key, &count, BPF_ANY)) exit_with_error(errno); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_poll_txq_tmout(struct test_spec *test) +static int testapp_poll_txq_tmout(struct test_spec *test) { test_spec_set_name(test, "POLL_TXQ_FULL"); @@ -1754,14 +1714,14 @@ static void testapp_poll_txq_tmout(struct test_spec *test) /* create invalid frame by set umem frame_size and pkt length equal to 2048 */ test->ifobj_tx->umem->frame_size = 2048; pkt_stream_replace(test, 2 * DEFAULT_PKT_CNT, 2048); - testapp_validate_traffic_single_thread(test, test->ifobj_tx); + return testapp_validate_traffic_single_thread(test, test->ifobj_tx); } -static void testapp_poll_rxq_tmout(struct test_spec *test) +static int testapp_poll_rxq_tmout(struct test_spec *test) { test_spec_set_name(test, "POLL_RXQ_EMPTY"); test->ifobj_rx->use_poll = true; - testapp_validate_traffic_single_thread(test, test->ifobj_rx); + return testapp_validate_traffic_single_thread(test, test->ifobj_rx); } static int xsk_load_xdp_programs(struct ifobject *ifobj) @@ -1778,25 +1738,30 @@ static void xsk_unload_xdp_programs(struct ifobject *ifobj) xsk_xdp_progs__destroy(ifobj->xdp_progs); } +/* Simple test */ +static bool hugepages_present(void) +{ + size_t mmap_sz = 2 * DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE; + void *bufs; + + bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, MAP_HUGE_2MB); + if (bufs == MAP_FAILED) + return false; + + mmap_sz = ceil_u64(mmap_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE; + munmap(bufs, mmap_sz); + return true; +} + static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac, - const char *dst_ip, const char *src_ip, const u16 dst_port, - const u16 src_port, thread_func_t func_ptr) + thread_func_t func_ptr) { - struct in_addr ip; int err; memcpy(ifobj->dst_mac, dst_mac, ETH_ALEN); memcpy(ifobj->src_mac, src_mac, ETH_ALEN); - inet_aton(dst_ip, &ip); - ifobj->dst_ip = ip.s_addr; - - inet_aton(src_ip, &ip); - ifobj->src_ip = ip.s_addr; - - ifobj->dst_port = dst_port; - ifobj->src_port = src_port; - ifobj->func_ptr = func_ptr; err = xsk_load_xdp_programs(ifobj); @@ -1804,94 +1769,87 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char * printf("Error loading XDP program\n"); exit_with_error(err); } + + if (hugepages_present()) + ifobj->unaligned_supp = true; } static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_type type) { + int ret = TEST_SKIP; + switch (type) { case TEST_TYPE_STATS_RX_DROPPED: - if (mode == TEST_MODE_ZC) { - ksft_test_result_skip("Can not run RX_DROPPED test for ZC mode\n"); - return; - } - testapp_stats_rx_dropped(test); + ret = testapp_stats_rx_dropped(test); break; case TEST_TYPE_STATS_TX_INVALID_DESCS: - testapp_stats_tx_invalid_descs(test); + ret = testapp_stats_tx_invalid_descs(test); break; case TEST_TYPE_STATS_RX_FULL: - testapp_stats_rx_full(test); + ret = testapp_stats_rx_full(test); break; case TEST_TYPE_STATS_FILL_EMPTY: - testapp_stats_fill_empty(test); + ret = testapp_stats_fill_empty(test); break; case TEST_TYPE_TEARDOWN: - testapp_teardown(test); + ret = testapp_teardown(test); break; case TEST_TYPE_BIDI: - testapp_bidi(test); + ret = testapp_bidi(test); break; case TEST_TYPE_BPF_RES: - testapp_bpf_res(test); + ret = testapp_bpf_res(test); break; case TEST_TYPE_RUN_TO_COMPLETION: test_spec_set_name(test, "RUN_TO_COMPLETION"); - testapp_validate_traffic(test); + ret = testapp_validate_traffic(test); break; case TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT: test_spec_set_name(test, "RUN_TO_COMPLETION_SINGLE_PKT"); - testapp_single_pkt(test); + ret = testapp_single_pkt(test); break; case TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME: test_spec_set_name(test, "RUN_TO_COMPLETION_2K_FRAME_SIZE"); test->ifobj_tx->umem->frame_size = 2048; test->ifobj_rx->umem->frame_size = 2048; - pkt_stream_replace(test, DEFAULT_PKT_CNT, PKT_SIZE); - testapp_validate_traffic(test); + pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE); + ret = testapp_validate_traffic(test); break; case TEST_TYPE_RX_POLL: test->ifobj_rx->use_poll = true; test_spec_set_name(test, "POLL_RX"); - testapp_validate_traffic(test); + ret = testapp_validate_traffic(test); break; case TEST_TYPE_TX_POLL: test->ifobj_tx->use_poll = true; test_spec_set_name(test, "POLL_TX"); - testapp_validate_traffic(test); + ret = testapp_validate_traffic(test); break; case TEST_TYPE_POLL_TXQ_TMOUT: - testapp_poll_txq_tmout(test); + ret = testapp_poll_txq_tmout(test); break; case TEST_TYPE_POLL_RXQ_TMOUT: - testapp_poll_rxq_tmout(test); + ret = testapp_poll_rxq_tmout(test); break; case TEST_TYPE_ALIGNED_INV_DESC: test_spec_set_name(test, "ALIGNED_INV_DESC"); - testapp_invalid_desc(test); + ret = testapp_invalid_desc(test); break; case TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME: test_spec_set_name(test, "ALIGNED_INV_DESC_2K_FRAME_SIZE"); test->ifobj_tx->umem->frame_size = 2048; test->ifobj_rx->umem->frame_size = 2048; - testapp_invalid_desc(test); + ret = testapp_invalid_desc(test); break; case TEST_TYPE_UNALIGNED_INV_DESC: - if (!hugepages_present(test->ifobj_tx)) { - ksft_test_result_skip("No 2M huge pages present.\n"); - return; - } test_spec_set_name(test, "UNALIGNED_INV_DESC"); test->ifobj_tx->umem->unaligned_mode = true; test->ifobj_rx->umem->unaligned_mode = true; - testapp_invalid_desc(test); + ret = testapp_invalid_desc(test); break; case TEST_TYPE_UNALIGNED_INV_DESC_4K1_FRAME: { u64 page_size, umem_size; - if (!hugepages_present(test->ifobj_tx)) { - ksft_test_result_skip("No 2M huge pages present.\n"); - return; - } test_spec_set_name(test, "UNALIGNED_INV_DESC_4K1_FRAME_SIZE"); /* Odd frame size so the UMEM doesn't end near a page boundary. */ test->ifobj_tx->umem->frame_size = 4001; @@ -1903,29 +1861,28 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_ */ page_size = sysconf(_SC_PAGESIZE); umem_size = test->ifobj_tx->umem->num_frames * test->ifobj_tx->umem->frame_size; - assert(umem_size % page_size > PKT_SIZE); - assert(umem_size % page_size < page_size - PKT_SIZE); - testapp_invalid_desc(test); + assert(umem_size % page_size > MIN_PKT_SIZE); + assert(umem_size % page_size < page_size - MIN_PKT_SIZE); + ret = testapp_invalid_desc(test); break; } case TEST_TYPE_UNALIGNED: - if (!testapp_unaligned(test)) - return; + ret = testapp_unaligned(test); break; case TEST_TYPE_HEADROOM: - testapp_headroom(test); + ret = testapp_headroom(test); break; case TEST_TYPE_XDP_DROP_HALF: - testapp_xdp_drop(test); + ret = testapp_xdp_drop(test); break; case TEST_TYPE_XDP_METADATA_COUNT: - testapp_xdp_metadata_count(test); + ret = testapp_xdp_metadata_count(test); break; default: break; } - if (!test->fail) + if (ret == TEST_PASS) ksft_test_result_pass("PASS: %s %s%s\n", mode_string(test), busy_poll_string(test), test->name); pkt_stream_restore_default(test); @@ -2030,14 +1987,12 @@ int main(int argc, char **argv) modes++; } - init_iface(ifobj_rx, MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, - worker_testapp_validate_rx); - init_iface(ifobj_tx, MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, - worker_testapp_validate_tx); + init_iface(ifobj_rx, MAC1, MAC2, worker_testapp_validate_rx); + init_iface(ifobj_tx, MAC2, MAC1, worker_testapp_validate_tx); test_spec_init(&test, ifobj_tx, ifobj_rx, 0); - tx_pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, PKT_SIZE); - rx_pkt_stream_default = pkt_stream_generate(ifobj_rx->umem, DEFAULT_PKT_CNT, PKT_SIZE); + tx_pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, MIN_PKT_SIZE); + rx_pkt_stream_default = pkt_stream_generate(ifobj_rx->umem, DEFAULT_PKT_CNT, MIN_PKT_SIZE); if (!tx_pkt_stream_default || !rx_pkt_stream_default) exit_with_error(ENOMEM); test.tx_pkt_stream_default = tx_pkt_stream_default; diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h index c535aeab2ca35..aaf27e0676406 100644 --- a/tools/testing/selftests/bpf/xskxceiver.h +++ b/tools/testing/selftests/bpf/xskxceiver.h @@ -30,22 +30,14 @@ #define TEST_PASS 0 #define TEST_FAILURE -1 #define TEST_CONTINUE 1 +#define TEST_SKIP 2 #define MAX_INTERFACES 2 #define MAX_INTERFACE_NAME_CHARS 16 #define MAX_SOCKETS 2 #define MAX_TEST_NAME_SIZE 32 #define MAX_TEARDOWN_ITER 10 -#define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \ - sizeof(struct udphdr)) -#define MIN_ETH_PKT_SIZE 64 -#define ETH_FCS_SIZE 4 -#define MIN_PKT_SIZE (MIN_ETH_PKT_SIZE - ETH_FCS_SIZE) -#define PKT_SIZE (MIN_PKT_SIZE) -#define IP_PKT_SIZE (PKT_SIZE - sizeof(struct ethhdr)) -#define IP_PKT_VER 0x4 -#define IP_PKT_TOS 0x9 -#define UDP_PKT_SIZE (IP_PKT_SIZE - sizeof(struct iphdr)) -#define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr)) +#define PKT_HDR_SIZE (sizeof(struct ethhdr) + 2) /* Just to align the data in the packet */ +#define MIN_PKT_SIZE 64 #define USLEEP_MAX 10000 #define SOCK_RECONF_CTR 10 #define BATCH_SIZE 64 @@ -57,6 +49,7 @@ #define UMEM_HEADROOM_TEST_SIZE 128 #define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1) #define HUGEPAGE_SIZE (2 * 1024 * 1024) +#define PKT_DUMP_NB_TO_PRINT 16 #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0) @@ -93,13 +86,13 @@ enum test_type { TEST_TYPE_MAX }; -static bool opt_pkt_dump; static bool opt_verbose; struct xsk_umem_info { struct xsk_ring_prod fq; struct xsk_ring_cons cq; struct xsk_umem *umem; + u64 next_buffer; u32 num_frames; u32 frame_headroom; void *buffer; @@ -118,17 +111,17 @@ struct xsk_socket_info { }; struct pkt { - u64 addr; + int offset; u32 len; - u32 payload; + u32 pkt_nb; bool valid; }; struct pkt_stream { u32 nb_pkts; - u32 rx_pkt_nb; + u32 current_pkt_nb; struct pkt *pkts; - bool use_addr_for_fill; + u32 max_pkt_len; }; struct ifobject; @@ -148,11 +141,7 @@ struct ifobject { struct bpf_program *xdp_prog; enum test_mode mode; int ifindex; - u32 dst_ip; - u32 src_ip; u32 bind_flags; - u16 src_port; - u16 dst_port; bool tx_on; bool rx_on; bool use_poll; @@ -161,6 +150,7 @@ struct ifobject { bool release_rx; bool shared_umem; bool use_metadata; + bool unaligned_supp; u8 dst_mac[ETH_ALEN]; u8 src_mac[ETH_ALEN]; }; @@ -184,7 +174,6 @@ struct test_spec { pthread_barrier_t barr; pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER; -pthread_cond_t pacing_cond = PTHREAD_COND_INITIALIZER; int pkts_in_flight; diff --git a/tools/testing/selftests/cachestat/.gitignore b/tools/testing/selftests/cachestat/.gitignore new file mode 100644 index 0000000000000..d6c30b43a4bb6 --- /dev/null +++ b/tools/testing/selftests/cachestat/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +test_cachestat diff --git a/tools/testing/selftests/cachestat/Makefile b/tools/testing/selftests/cachestat/Makefile new file mode 100644 index 0000000000000..fca73aaa7d141 --- /dev/null +++ b/tools/testing/selftests/cachestat/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0 +TEST_GEN_PROGS := test_cachestat + +CFLAGS += $(KHDR_INCLUDES) +CFLAGS += -Wall +CFLAGS += -lrt + +include ../lib.mk diff --git a/tools/testing/selftests/cachestat/test_cachestat.c b/tools/testing/selftests/cachestat/test_cachestat.c new file mode 100644 index 0000000000000..54d09b820ed4b --- /dev/null +++ b/tools/testing/selftests/cachestat/test_cachestat.c @@ -0,0 +1,269 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdbool.h> +#include <linux/kernel.h> +#include <linux/mman.h> +#include <sys/mman.h> +#include <sys/shm.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <string.h> +#include <fcntl.h> +#include <errno.h> + +#include "../kselftest.h" + +static const char * const dev_files[] = { + "/dev/zero", "/dev/null", "/dev/urandom", + "/proc/version", "/proc" +}; +static const int cachestat_nr = 451; + +void print_cachestat(struct cachestat *cs) +{ + ksft_print_msg( + "Using cachestat: Cached: %lu, Dirty: %lu, Writeback: %lu, Evicted: %lu, Recently Evicted: %lu\n", + cs->nr_cache, cs->nr_dirty, cs->nr_writeback, + cs->nr_evicted, cs->nr_recently_evicted); +} + +bool write_exactly(int fd, size_t filesize) +{ + int random_fd = open("/dev/urandom", O_RDONLY); + char *cursor, *data; + int remained; + bool ret; + + if (random_fd < 0) { + ksft_print_msg("Unable to access urandom.\n"); + ret = false; + goto out; + } + + data = malloc(filesize); + if (!data) { + ksft_print_msg("Unable to allocate data.\n"); + ret = false; + goto close_random_fd; + } + + remained = filesize; + cursor = data; + + while (remained) { + ssize_t read_len = read(random_fd, cursor, remained); + + if (read_len <= 0) { + ksft_print_msg("Unable to read from urandom.\n"); + ret = false; + goto out_free_data; + } + + remained -= read_len; + cursor += read_len; + } + + /* write random data to fd */ + remained = filesize; + cursor = data; + while (remained) { + ssize_t write_len = write(fd, cursor, remained); + + if (write_len <= 0) { + ksft_print_msg("Unable write random data to file.\n"); + ret = false; + goto out_free_data; + } + + remained -= write_len; + cursor += write_len; + } + + ret = true; +out_free_data: + free(data); +close_random_fd: + close(random_fd); +out: + return ret; +} + +/* + * Open/create the file at filename, (optionally) write random data to it + * (exactly num_pages), then test the cachestat syscall on this file. + * + * If test_fsync == true, fsync the file, then check the number of dirty + * pages. + */ +bool test_cachestat(const char *filename, bool write_random, bool create, + bool test_fsync, unsigned long num_pages, int open_flags, + mode_t open_mode) +{ + size_t PS = sysconf(_SC_PAGESIZE); + int filesize = num_pages * PS; + bool ret = true; + long syscall_ret; + struct cachestat cs; + struct cachestat_range cs_range = { 0, filesize }; + + int fd = open(filename, open_flags, open_mode); + + if (fd == -1) { + ksft_print_msg("Unable to create/open file.\n"); + ret = false; + goto out; + } else { + ksft_print_msg("Create/open %s\n", filename); + } + + if (write_random) { + if (!write_exactly(fd, filesize)) { + ksft_print_msg("Unable to access urandom.\n"); + ret = false; + goto out1; + } + } + + syscall_ret = syscall(cachestat_nr, fd, &cs_range, &cs, 0); + + ksft_print_msg("Cachestat call returned %ld\n", syscall_ret); + + if (syscall_ret) { + ksft_print_msg("Cachestat returned non-zero.\n"); + ret = false; + goto out1; + + } else { + print_cachestat(&cs); + + if (write_random) { + if (cs.nr_cache + cs.nr_evicted != num_pages) { + ksft_print_msg( + "Total number of cached and evicted pages is off.\n"); + ret = false; + } + } + } + + if (test_fsync) { + if (fsync(fd)) { + ksft_print_msg("fsync fails.\n"); + ret = false; + } else { + syscall_ret = syscall(cachestat_nr, fd, &cs_range, &cs, 0); + + ksft_print_msg("Cachestat call (after fsync) returned %ld\n", + syscall_ret); + + if (!syscall_ret) { + print_cachestat(&cs); + + if (cs.nr_dirty) { + ret = false; + ksft_print_msg( + "Number of dirty should be zero after fsync.\n"); + } + } else { + ksft_print_msg("Cachestat (after fsync) returned non-zero.\n"); + ret = false; + goto out1; + } + } + } + +out1: + close(fd); + + if (create) + remove(filename); +out: + return ret; +} + +bool test_cachestat_shmem(void) +{ + size_t PS = sysconf(_SC_PAGESIZE); + size_t filesize = PS * 512 * 2; /* 2 2MB huge pages */ + int syscall_ret; + size_t compute_len = PS * 512; + struct cachestat_range cs_range = { PS, compute_len }; + char *filename = "tmpshmcstat"; + struct cachestat cs; + bool ret = true; + unsigned long num_pages = compute_len / PS; + int fd = shm_open(filename, O_CREAT | O_RDWR, 0600); + + if (fd < 0) { + ksft_print_msg("Unable to create shmem file.\n"); + ret = false; + goto out; + } + + if (ftruncate(fd, filesize)) { + ksft_print_msg("Unable to truncate shmem file.\n"); + ret = false; + goto close_fd; + } + + if (!write_exactly(fd, filesize)) { + ksft_print_msg("Unable to write to shmem file.\n"); + ret = false; + goto close_fd; + } + + syscall_ret = syscall(cachestat_nr, fd, &cs_range, &cs, 0); + + if (syscall_ret) { + ksft_print_msg("Cachestat returned non-zero.\n"); + ret = false; + goto close_fd; + } else { + print_cachestat(&cs); + if (cs.nr_cache + cs.nr_evicted != num_pages) { + ksft_print_msg( + "Total number of cached and evicted pages is off.\n"); + ret = false; + } + } + +close_fd: + shm_unlink(filename); +out: + return ret; +} + +int main(void) +{ + int ret = 0; + + for (int i = 0; i < 5; i++) { + const char *dev_filename = dev_files[i]; + + if (test_cachestat(dev_filename, false, false, false, + 4, O_RDONLY, 0400)) + ksft_test_result_pass("cachestat works with %s\n", dev_filename); + else { + ksft_test_result_fail("cachestat fails with %s\n", dev_filename); + ret = 1; + } + } + + if (test_cachestat("tmpfilecachestat", true, true, + true, 4, O_CREAT | O_RDWR, 0400 | 0600)) + ksft_test_result_pass("cachestat works with a normal file\n"); + else { + ksft_test_result_fail("cachestat fails with normal file\n"); + ret = 1; + } + + if (test_cachestat_shmem()) + ksft_test_result_pass("cachestat works with a shmem file\n"); + else { + ksft_test_result_fail("cachestat fails with a shmem file\n"); + ret = 1; + } + + return ret; +} diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index f4f7c0aef702b..c7c9572003a8c 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -292,6 +292,7 @@ static int test_memcg_protection(const char *root, bool min) char *children[4] = {NULL}; const char *attribute = min ? "memory.min" : "memory.low"; long c[4]; + long current; int i, attempts; int fd; @@ -400,7 +401,8 @@ static int test_memcg_protection(const char *root, bool min) goto cleanup; } - if (!values_close(cg_read_long(parent[1], "memory.current"), MB(50), 3)) + current = min ? MB(50) : MB(30); + if (!values_close(cg_read_long(parent[1], "memory.current"), current, 3)) goto cleanup; if (!reclaim_until(children[0], MB(10))) @@ -987,7 +989,9 @@ static int tcp_client(const char *cgroup, unsigned short port) char servport[6]; int retries = 0x10; /* nice round number */ int sk, ret; + long allocated; + allocated = cg_read_long(cgroup, "memory.current"); snprintf(servport, sizeof(servport), "%hd", port); ret = getaddrinfo(server, servport, NULL, &ai); if (ret) @@ -1015,7 +1019,8 @@ static int tcp_client(const char *cgroup, unsigned short port) if (current < 0 || sock < 0) goto close_sk; - if (values_close(current, sock, 10)) { + /* exclude the memory not related to socket connection */ + if (values_close(current - allocated, sock, 10)) { ret = KSFT_PASS; break; } diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index e495f895a2cdd..e60cf4da8fb07 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -129,7 +129,7 @@ int main(int argc, char *argv[]) uid_t uid = getuid(); ksft_print_header(); - ksft_set_plan(18); + ksft_set_plan(19); test_clone3_supported(); /* Just a simple clone3() should return 0.*/ @@ -198,5 +198,8 @@ int main(int argc, char *argv[]) /* Do a clone3() in a new time namespace */ test_clone3(CLONE_NEWTIME, 0, 0, CLONE3_ARGS_NO_TEST); + /* Do a clone3() with exit signal (SIGCHLD) in flags */ + test_clone3(SIGCHLD, 0, -EINVAL, CLONE3_ARGS_NO_TEST); + ksft_finished(); } diff --git a/tools/testing/selftests/cpufreq/config b/tools/testing/selftests/cpufreq/config index 75e900793e8a9..ce5068f5a6a27 100644 --- a/tools/testing/selftests/cpufreq/config +++ b/tools/testing/selftests/cpufreq/config @@ -5,11 +5,3 @@ CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y -CONFIG_DEBUG_RT_MUTEXES=y -CONFIG_DEBUG_PLIST=y -CONFIG_DEBUG_SPINLOCK=y -CONFIG_DEBUG_MUTEXES=y -CONFIG_DEBUG_LOCK_ALLOC=y -CONFIG_PROVE_LOCKING=y -CONFIG_LOCKDEP=y -CONFIG_DEBUG_ATOMIC_SLEEP=y diff --git a/tools/testing/selftests/damon/config b/tools/testing/selftests/damon/config new file mode 100644 index 0000000000000..0daf38974eb03 --- /dev/null +++ b/tools/testing/selftests/damon/config @@ -0,0 +1,7 @@ +CONFIG_DAMON=y +CONFIG_DAMON_SYSFS=y +CONFIG_DAMON_DBGFS=y +CONFIG_DAMON_PADDR=y +CONFIG_DAMON_VADDR=y +CONFIG_DAMON_RECLAIM=y +CONFIG_DAMON_LRU_SORT=y diff --git a/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh b/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh index 5cdd22048ba70..862e947e17c7a 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh @@ -53,7 +53,6 @@ bond_test_enslave_type_change() # restore ARPHRD_ETHER type by enslaving such device ip link set dev "$devbond2" master "$devbond0" check_err $? "could not enslave $devbond2 to $devbond0" - ip link set dev "$devbond1" nomaster bond_check_flags "$devbond0" diff --git a/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh b/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh index 0cf9e47e32092..a5c2aec528985 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh @@ -16,10 +16,9 @@ # +----------------|--+ +--|-----------------+ # | | # +----------------|-------------------------|-----------------+ -# | SW | | | +# | SW $swp1 + + $swp2 | +# | | | | # | +--------------|-------------------------|---------------+ | -# | | $swp1 + + $swp2 | | -# | | | | | | # | | $swp1.10 + + $swp2.10 | | # | | | | # | | br0 | | diff --git a/tools/testing/selftests/drivers/net/mlxsw/extack.sh b/tools/testing/selftests/drivers/net/mlxsw/extack.sh index 7a0a99c1d22fd..6fd422d38fe8c 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/extack.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/extack.sh @@ -35,7 +35,9 @@ netdev_pre_up_test() { RET=0 - ip link add name br1 up type bridge vlan_filtering 0 mcast_snooping 0 + ip link add name br1 type bridge vlan_filtering 0 mcast_snooping 0 + ip link set dev br1 addrgenmode none + ip link set dev br1 up ip link add name vx1 up type vxlan id 1000 \ local 192.0.2.17 remote 192.0.2.18 \ dstport 4789 nolearning noudpcsum tos inherit ttl 100 @@ -46,7 +48,9 @@ netdev_pre_up_test() ip link set dev $swp1 master br1 check_err $? - ip link add name br2 up type bridge vlan_filtering 0 mcast_snooping 0 + ip link add name br2 type bridge vlan_filtering 0 mcast_snooping 0 + ip link set dev br2 addrgenmode none + ip link set dev br2 up ip link add name vx2 up type vxlan id 2000 \ local 192.0.2.17 remote 192.0.2.18 \ dstport 4789 nolearning noudpcsum tos inherit ttl 100 @@ -81,7 +85,9 @@ vxlan_vlan_add_test() { RET=0 - ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 0 + ip link add name br1 type bridge vlan_filtering 1 mcast_snooping 0 + ip link set dev br1 addrgenmode none + ip link set dev br1 up # Unsupported configuration: mlxsw demands VXLAN with "noudpcsum". ip link add name vx1 up type vxlan id 1000 \ @@ -117,7 +123,9 @@ vxlan_bridge_create_test() dstport 4789 tos inherit ttl 100 # Test with VLAN-aware bridge. - ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 0 + ip link add name br1 type bridge vlan_filtering 1 mcast_snooping 0 + ip link set dev br1 addrgenmode none + ip link set dev br1 up ip link set dev vx1 master br1 @@ -142,8 +150,12 @@ bridge_create_test() { RET=0 - ip link add name br1 up type bridge vlan_filtering 1 - ip link add name br2 up type bridge vlan_filtering 1 + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 addrgenmode none + ip link set dev br1 up + ip link add name br2 type bridge vlan_filtering 1 + ip link set dev br2 addrgenmode none + ip link set dev br2 up ip link set dev $swp1 master br1 check_err $? diff --git a/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh b/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh index df2b099668862..7d7f862c809cf 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh @@ -15,10 +15,9 @@ # +----------------|--+ +--|-----------------+ # | | # +----------------|-------------------------|-----------------+ -# | SW | | | +# | SW $swp1 + + $swp2 | +# | | | | # | +--------------|-------------------------|---------------+ | -# | | $swp1 + + $swp2 | | -# | | | | | | # | | $swp1.10 + + $swp2.10 | | # | | | | # | | br0 | | diff --git a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh index e00435753008a..e5589e2fca85a 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh @@ -165,6 +165,7 @@ mirror_gre_setup_prepare() simple_if_init $h3 ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 addrgenmode none ip link set dev br1 up ip link set dev $swp1 master br1 diff --git a/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh b/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh index f02d83e945767..fca0e1e642c63 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh @@ -83,7 +83,8 @@ h2_destroy() switch_create() { - ip link add name br0 type bridge mcast_snooping 0 + ip link add name br0 address $(mac_get $swp1) \ + type bridge mcast_snooping 0 ip link set dev br0 up ip link set dev $swp1 master br0 diff --git a/tools/testing/selftests/drivers/net/mlxsw/q_in_q_veto.sh b/tools/testing/selftests/drivers/net/mlxsw/q_in_q_veto.sh index 7edaed8eb86ac..00d55b0e98c11 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/q_in_q_veto.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/q_in_q_veto.sh @@ -48,6 +48,7 @@ create_vlan_upper_on_top_of_bridge() ip link add dev br0 type bridge vlan_filtering 1 \ vlan_protocol $bridge_proto vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev br0 up ip link set dev $swp1 master br0 @@ -88,6 +89,7 @@ create_8021ad_vlan_upper_on_top_bridge_port() ip link add dev br0 type bridge vlan_filtering 1 \ vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev $swp1 master br0 ip link set dev br0 up @@ -155,6 +157,7 @@ create_vlan_upper_on_top_front_panel_enslaved_to_8021ad_bridge() ip link add dev br0 type bridge vlan_filtering 1 \ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev br0 up ip link set dev $swp1 master br0 @@ -177,6 +180,7 @@ create_vlan_upper_on_top_lag_enslaved_to_8021ad_bridge() ip link add dev br0 type bridge vlan_filtering 1 \ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev br0 up ip link add name bond1 type bond mode 802.3ad @@ -203,6 +207,7 @@ enslave_front_panel_with_vlan_upper_to_8021ad_bridge() ip link add dev br0 type bridge vlan_filtering 1 \ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev br0 up ip link add name $swp1.100 link $swp1 type vlan id 100 @@ -225,6 +230,7 @@ enslave_lag_with_vlan_upper_to_8021ad_bridge() ip link add dev br0 type bridge vlan_filtering 1 \ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev br0 up ip link add name bond1 type bond mode 802.3ad @@ -252,6 +258,7 @@ add_ip_address_to_8021ad_bridge() ip link add dev br0 type bridge vlan_filtering 1 \ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev br0 up ip link set dev $swp1 master br0 @@ -273,6 +280,7 @@ switch_bridge_protocol_from_8021q_to_8021ad() ip link add dev br0 type bridge vlan_filtering 1 \ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev br0 up ip link set dev $swp1 master br0 diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh index 87c41f5727c9e..914c63d6318ae 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh @@ -65,6 +65,7 @@ h2_destroy() switch_create() { ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 addrgenmode none ip link set dev br1 up ip link set dev $swp1 master br1 ip link set dev $swp1 up diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh index 690d8daa71b49..fee74f215cec6 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh @@ -138,11 +138,15 @@ switch_create() vlan_create $swp3 111 vlan_create $swp3 222 - ip link add name br111 up type bridge vlan_filtering 0 + ip link add name br111 type bridge vlan_filtering 0 + ip link set dev br111 addrgenmode none + ip link set dev br111 up ip link set dev $swp1.111 master br111 ip link set dev $swp3.111 master br111 - ip link add name br222 up type bridge vlan_filtering 0 + ip link add name br222 type bridge vlan_filtering 0 + ip link set dev br222 addrgenmode none + ip link set dev br222 up ip link set dev $swp2.222 master br222 ip link set dev $swp3.222 master br222 diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh index c8e55fa916609..6d892de43fa80 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh @@ -135,11 +135,13 @@ switch_create() prio bands 8 priomap 7 7 7 7 7 7 7 7 ip link add name br1 type bridge vlan_filtering 0 + ip link set dev br1 addrgenmode none ip link set dev br1 up ip link set dev $swp1 master br1 ip link set dev $swp3 master br1 ip link add name br111 type bridge vlan_filtering 0 + ip link set dev br111 addrgenmode none ip link set dev br111 up ip link set dev $swp2.111 master br111 ip link set dev $swp3.111 master br111 diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/q_in_vni_veto.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/q_in_vni_veto.sh index f0443b1b05b9d..60753d46a2d4f 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/q_in_vni_veto.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/q_in_vni_veto.sh @@ -34,6 +34,7 @@ create_vxlan_on_top_of_8021ad_bridge() ip link add dev br0 type bridge vlan_filtering 1 vlan_protocol 802.1ad \ vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev br0 up ip link add name vx100 type vxlan id 1000 local 192.0.2.17 dstport \ diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh index 99a332b712f0f..4687b0a7dffbf 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh @@ -444,8 +444,12 @@ offload_indication_setup_create() { # Create a simple setup with two bridges, each with a VxLAN device # and one local port - ip link add name br0 up type bridge mcast_snooping 0 - ip link add name br1 up type bridge mcast_snooping 0 + ip link add name br0 type bridge mcast_snooping 0 + ip link set dev br0 addrgenmode none + ip link set dev br0 up + ip link add name br1 type bridge mcast_snooping 0 + ip link set dev br1 addrgenmode none + ip link set dev br1 up ip link set dev $swp1 master br0 ip link set dev $swp2 master br1 @@ -646,8 +650,12 @@ offload_indication_decap_route_test() RET=0 - ip link add name br0 up type bridge mcast_snooping 0 - ip link add name br1 up type bridge mcast_snooping 0 + ip link add name br0 type bridge mcast_snooping 0 + ip link set dev br0 addrgenmode none + ip link set dev br0 up + ip link add name br1 type bridge mcast_snooping 0 + ip link set dev br1 addrgenmode none + ip link set dev br1 up ip link set dev $swp1 master br0 ip link set dev $swp2 master br1 ip link set dev vxlan0 master br0 @@ -780,7 +788,9 @@ __offload_indication_join_vxlan_first() offload_indication_join_vxlan_first() { - ip link add dev br0 up type bridge mcast_snooping 0 + ip link add dev br0 type bridge mcast_snooping 0 + ip link set dev br0 addrgenmode none + ip link set dev br0 up ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 @@ -815,7 +825,9 @@ __offload_indication_join_vxlan_last() offload_indication_join_vxlan_last() { - ip link add dev br0 up type bridge mcast_snooping 0 + ip link add dev br0 type bridge mcast_snooping 0 + ip link set dev br0 addrgenmode none + ip link set dev br0 up ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 @@ -842,6 +854,7 @@ sanitization_vlan_aware_test() RET=0 ip link add dev br0 type bridge mcast_snooping 0 vlan_filtering 1 + ip link set dev br0 addrgenmode none ip link add name vxlan10 up master br0 type vxlan id 10 nolearning \ $UDPCSUM_FLAFS ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 @@ -915,8 +928,10 @@ offload_indication_vlan_aware_setup_create() { # Create a simple setup with two VxLAN devices and a single VLAN-aware # bridge - ip link add name br0 up type bridge mcast_snooping 0 vlan_filtering 1 \ + ip link add name br0 type bridge mcast_snooping 0 vlan_filtering 1 \ vlan_default_pvid 0 + ip link set dev br0 addrgenmode none + ip link set dev br0 up ip link set dev $swp1 master br0 @@ -1060,8 +1075,10 @@ offload_indication_vlan_aware_decap_route_test() offload_indication_vlan_aware_join_vxlan_first() { - ip link add dev br0 up type bridge mcast_snooping 0 \ + ip link add dev br0 type bridge mcast_snooping 0 \ vlan_filtering 1 vlan_default_pvid 1 + ip link set dev br0 addrgenmode none + ip link set dev br0 up ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 @@ -1073,8 +1090,10 @@ offload_indication_vlan_aware_join_vxlan_first() offload_indication_vlan_aware_join_vxlan_last() { - ip link add dev br0 up type bridge mcast_snooping 0 \ + ip link add dev br0 type bridge mcast_snooping 0 \ vlan_filtering 1 vlan_default_pvid 1 + ip link set dev br0 addrgenmode none + ip link set dev br0 up ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 @@ -1091,8 +1110,10 @@ offload_indication_vlan_aware_l3vni_test() RET=0 sysctl_set net.ipv6.conf.default.disable_ipv6 1 - ip link add dev br0 up type bridge mcast_snooping 0 \ + ip link add dev br0 type bridge mcast_snooping 0 \ vlan_filtering 1 vlan_default_pvid 0 + ip link set dev br0 addrgenmode none + ip link set dev br0 up ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index d6e106fbce11c..a1e955d2de4cc 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 all: -TEST_PROGS := ftracetest +TEST_PROGS_EXTENDED := ftracetest +TEST_PROGS := ftracetest-ktap TEST_FILES := test.d settings EXTRA_CLEAN := $(OUTPUT)/logs/* diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index c3311c8c40890..cb5f18c06593d 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -13,6 +13,7 @@ echo "Usage: ftracetest [options] [testcase(s)] [testcase-directory(s)]" echo " Options:" echo " -h|--help Show help message" echo " -k|--keep Keep passed test logs" +echo " -K|--ktap Output in KTAP format" echo " -v|--verbose Increase verbosity of test messages" echo " -vv Alias of -v -v (Show all results in stdout)" echo " -vvv Alias of -v -v -v (Show all commands immediately)" @@ -85,6 +86,10 @@ parse_opts() { # opts KEEP_LOG=1 shift 1 ;; + --ktap|-K) + KTAP=1 + shift 1 + ;; --verbose|-v|-vv|-vvv) if [ $VERBOSE -eq -1 ]; then usage "--console can not use with --verbose" @@ -178,6 +183,7 @@ TEST_DIR=$TOP_DIR/test.d TEST_CASES=`find_testcases $TEST_DIR` LOG_DIR=$TOP_DIR/logs/`date +%Y%m%d-%H%M%S`/ KEEP_LOG=0 +KTAP=0 DEBUG=0 VERBOSE=0 UNSUPPORTED_RESULT=0 @@ -229,7 +235,7 @@ prlog() { # messages newline= shift fi - printf "$*$newline" + [ "$KTAP" != "1" ] && printf "$*$newline" [ "$LOG_FILE" ] && printf "$*$newline" | strip_esc >> $LOG_FILE } catlog() { #file @@ -260,11 +266,11 @@ TOTAL_RESULT=0 INSTANCE= CASENO=0 +CASENAME= testcase() { # testfile CASENO=$((CASENO+1)) - desc=`grep "^#[ \t]*description:" $1 | cut -f2- -d:` - prlog -n "[$CASENO]$INSTANCE$desc" + CASENAME=`grep "^#[ \t]*description:" $1 | cut -f2- -d:` } checkreq() { # testfile @@ -277,40 +283,68 @@ test_on_instance() { # testfile grep -q "^#[ \t]*flags:.*instance" $1 } +ktaptest() { # result comment + if [ "$KTAP" != "1" ]; then + return + fi + + local result= + if [ "$1" = "1" ]; then + result="ok" + else + result="not ok" + fi + shift + + local comment=$* + if [ "$comment" != "" ]; then + comment="# $comment" + fi + + echo $result $CASENO $INSTANCE$CASENAME $comment +} + eval_result() { # sigval case $1 in $PASS) prlog " [${color_green}PASS${color_reset}]" + ktaptest 1 PASSED_CASES="$PASSED_CASES $CASENO" return 0 ;; $FAIL) prlog " [${color_red}FAIL${color_reset}]" + ktaptest 0 FAILED_CASES="$FAILED_CASES $CASENO" return 1 # this is a bug. ;; $UNRESOLVED) prlog " [${color_blue}UNRESOLVED${color_reset}]" + ktaptest 0 UNRESOLVED UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO" return $UNRESOLVED_RESULT # depends on use case ;; $UNTESTED) prlog " [${color_blue}UNTESTED${color_reset}]" + ktaptest 1 SKIP UNTESTED_CASES="$UNTESTED_CASES $CASENO" return 0 ;; $UNSUPPORTED) prlog " [${color_blue}UNSUPPORTED${color_reset}]" + ktaptest 1 SKIP UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO" return $UNSUPPORTED_RESULT # depends on use case ;; $XFAIL) prlog " [${color_green}XFAIL${color_reset}]" + ktaptest 1 XFAIL XFAILED_CASES="$XFAILED_CASES $CASENO" return 0 ;; *) prlog " [${color_blue}UNDEFINED${color_reset}]" + ktaptest 0 error UNDEFINED_CASES="$UNDEFINED_CASES $CASENO" return 1 # this must be a test bug ;; @@ -371,6 +405,7 @@ __run_test() { # testfile run_test() { # testfile local testname=`basename $1` testcase $1 + prlog -n "[$CASENO]$INSTANCE$CASENAME" if [ ! -z "$LOG_FILE" ] ; then local testlog=`mktemp $LOG_DIR/${CASENO}-${testname}-log.XXXXXX` else @@ -405,6 +440,17 @@ run_test() { # testfile # load in the helper functions . $TEST_DIR/functions +if [ "$KTAP" = "1" ]; then + echo "TAP version 13" + + casecount=`echo $TEST_CASES | wc -w` + for t in $TEST_CASES; do + test_on_instance $t || continue + casecount=$((casecount+1)) + done + echo "1..${casecount}" +fi + # Main loop for t in $TEST_CASES; do run_test $t @@ -439,6 +485,17 @@ prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w` prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w` prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w` +if [ "$KTAP" = "1" ]; then + echo -n "# Totals:" + echo -n " pass:"`echo $PASSED_CASES | wc -w` + echo -n " faii:"`echo $FAILED_CASES | wc -w` + echo -n " xfail:"`echo $XFAILED_CASES | wc -w` + echo -n " xpass:0" + echo -n " skip:"`echo $UNTESTED_CASES $UNSUPPORTED_CASES | wc -w` + echo -n " error:"`echo $UNRESOLVED_CASES $UNDEFINED_CASES | wc -w` + echo +fi + cleanup # if no error, return 0 diff --git a/tools/testing/selftests/ftrace/ftracetest-ktap b/tools/testing/selftests/ftrace/ftracetest-ktap new file mode 100755 index 0000000000000..b3284679ef3af --- /dev/null +++ b/tools/testing/selftests/ftrace/ftracetest-ktap @@ -0,0 +1,8 @@ +#!/bin/sh -e +# SPDX-License-Identifier: GPL-2.0-only +# +# ftracetest-ktap: Wrapper to integrate ftracetest with the kselftest runner +# +# Copyright (C) Arm Ltd., 2023 + +./ftracetest -K diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc index e2ff3bf4df80f..2de7c61d1ae30 100644 --- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc +++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc @@ -9,18 +9,33 @@ fail() { #msg exit_fail } -echo "Test event filter function name" +sample_events() { + echo > trace + echo 1 > events/kmem/kmem_cache_free/enable + echo 1 > tracing_on + ls > /dev/null + echo 0 > tracing_on + echo 0 > events/kmem/kmem_cache_free/enable +} + echo 0 > tracing_on echo 0 > events/enable + +echo "Get the most frequently calling function" +sample_events + +target_func=`cut -d: -f3 trace | sed 's/call_site=\([^+]*\)+0x.*/\1/' | sort | uniq -c | sort | tail -n 1 | sed 's/^[ 0-9]*//'` +if [ -z "$target_func" ]; then + exit_fail +fi echo > trace -echo 'call_site.function == exit_mmap' > events/kmem/kmem_cache_free/filter -echo 1 > events/kmem/kmem_cache_free/enable -echo 1 > tracing_on -ls > /dev/null -echo 0 > events/kmem/kmem_cache_free/enable -hitcnt=`grep kmem_cache_free trace| grep exit_mmap | wc -l` -misscnt=`grep kmem_cache_free trace| grep -v exit_mmap | wc -l` +echo "Test event filter function name" +echo "call_site.function == $target_func" > events/kmem/kmem_cache_free/filter +sample_events + +hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l` +misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l` if [ $hitcnt -eq 0 ]; then exit_fail @@ -30,20 +45,14 @@ if [ $misscnt -gt 0 ]; then exit_fail fi -address=`grep ' exit_mmap$' /proc/kallsyms | cut -d' ' -f1` +address=`grep " ${target_func}\$" /proc/kallsyms | cut -d' ' -f1` echo "Test event filter function address" -echo 0 > tracing_on -echo 0 > events/enable -echo > trace echo "call_site.function == 0x$address" > events/kmem/kmem_cache_free/filter -echo 1 > events/kmem/kmem_cache_free/enable -echo 1 > tracing_on -sleep 1 -echo 0 > events/kmem/kmem_cache_free/enable +sample_events -hitcnt=`grep kmem_cache_free trace| grep exit_mmap | wc -l` -misscnt=`grep kmem_cache_free trace| grep -v exit_mmap | wc -l` +hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l` +misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l` if [ $hitcnt -eq 0 ]; then exit_fail diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_opt_types.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_opt_types.tc new file mode 100644 index 0000000000000..9f5d99328086b --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_opt_types.tc @@ -0,0 +1,34 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-or-later +# Copyright (C) 2023 Akanksha J N, IBM corporation +# description: Register/unregister optimized probe +# requires: kprobe_events + +case `uname -m` in +x86_64) +;; +arm*) +;; +ppc*) +;; +*) + echo "Please implement other architecture here" + exit_unsupported +esac + +DEFAULT=$(cat /proc/sys/debug/kprobes-optimization) +echo 1 > /proc/sys/debug/kprobes-optimization +for i in `seq 0 255`; do + echo "p:testprobe $FUNCTION_FORK+${i}" > kprobe_events || continue + echo 1 > events/kprobes/enable || continue + (echo "forked") + PROBE=$(grep $FUNCTION_FORK /sys/kernel/debug/kprobes/list) + echo 0 > events/kprobes/enable + echo > kprobe_events + if echo $PROBE | grep -q OPTIMIZED; then + echo "$DEFAULT" > /proc/sys/debug/kprobes-optimization + exit_pass + fi +done +echo "$DEFAULT" > /proc/sys/debug/kprobes-optimization +exit_unresolved diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc new file mode 100644 index 0000000000000..d0cd91a930699 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc @@ -0,0 +1,24 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event trigger - test inter-event histogram trigger trace action with dynamic string param (legacy stack) +# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[] stack' >> synthetic_events":README + +fail() { #msg + echo $1 + exit_fail +} + +echo "Test create synthetic event with stack" + +# Test the old stacktrace keyword (for backward compatibility) +echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events +echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger +echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger +echo 1 > events/synthetic/wake_lat/enable +sleep 1 + +if ! grep -q "=>.*sched" trace; then + fail "Failed to create synthetic event with stack" +fi + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc index 755dbe94ccf4a..8f1cc9a86a060 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: event trigger - test inter-event histogram trigger trace action with dynamic string param -# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[]' >> synthetic_events":README +# requires: set_event synthetic_events events/sched/sched_process_exec/hist "can be any field, or the special string 'common_stacktrace'":README fail() { #msg echo $1 @@ -10,9 +10,8 @@ fail() { #msg echo "Test create synthetic event with stack" - echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events -echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger +echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=common_stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger echo 1 > events/synthetic/wake_lat/enable sleep 1 diff --git a/tools/testing/selftests/gpio/gpio-sim.sh b/tools/testing/selftests/gpio/gpio-sim.sh index 9f539d454ee4d..6fb66a687f173 100755 --- a/tools/testing/selftests/gpio/gpio-sim.sh +++ b/tools/testing/selftests/gpio/gpio-sim.sh @@ -152,9 +152,9 @@ sysfs_set_pull() { local PULL=$4 local DEVNAME=`configfs_dev_name $DEV` local CHIPNAME=`configfs_chip_name $DEV $BANK` - local SYSFSPATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio$OFFSET/pull" + local SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio$OFFSET/pull" - echo $PULL > $SYSFSPATH || fail "Unable to set line pull in sysfs" + echo $PULL > $SYSFS_PATH || fail "Unable to set line pull in sysfs" } # Load the gpio-sim module. This will pull in configfs if needed too. @@ -389,6 +389,9 @@ create_chip chip create_bank chip bank set_num_lines chip bank 8 enable_chip chip +DEVNAME=`configfs_dev_name chip` +CHIPNAME=`configfs_chip_name chip bank` +SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value" $BASE_DIR/gpio-mockup-cdev -b pull-up /dev/`configfs_chip_name chip bank` 0 test `cat $SYSFS_PATH` = "1" || fail "bias setting does not work" remove_chip chip diff --git a/tools/testing/selftests/hid/tests/test_wacom_generic.py b/tools/testing/selftests/hid/tests/test_wacom_generic.py index b1eb2bc787fc1..f92fe8e02c1bf 100644 --- a/tools/testing/selftests/hid/tests/test_wacom_generic.py +++ b/tools/testing/selftests/hid/tests/test_wacom_generic.py @@ -31,6 +31,7 @@ from enum import Enum from hidtools.hut import HUT from hidtools.hid import HidUnit from . import base +from . import test_multitouch import libevdev import pytest @@ -517,7 +518,7 @@ class BaseTest: for usage in get_report_usages(report): yield usage - def assertName(self, uhdev): + def assertName(self, uhdev, type): """ Assert that the name is as we expect. @@ -526,7 +527,7 @@ class BaseTest: this assertion from the base class to work properly. """ evdev = uhdev.get_evdev() - expected_name = uhdev.name + " Pen" + expected_name = uhdev.name + type if "wacom" not in expected_name.lower(): expected_name = "Wacom " + expected_name assert evdev.name == expected_name @@ -549,6 +550,12 @@ class BaseTest: usage_id("Generic Desktop", "Y"): PhysRange( PhysRange.CENTIMETER, 5, 150 ), + usage_id("Digitizers", "Width"): PhysRange( + PhysRange.CENTIMETER, 5, 150 + ), + usage_id("Digitizers", "Height"): PhysRange( + PhysRange.CENTIMETER, 5, 150 + ), usage_id("Digitizers", "X Tilt"): PhysRange(PhysRange.DEGREE, 90, 180), usage_id("Digitizers", "Y Tilt"): PhysRange(PhysRange.DEGREE, 90, 180), usage_id("Digitizers", "Twist"): PhysRange(PhysRange.DEGREE, 358, 360), @@ -603,7 +610,17 @@ class BaseTest: pass -class TestOpaqueTablet(BaseTest.TestTablet): +class PenTabletTest(BaseTest.TestTablet): + def assertName(self, uhdev): + super().assertName(uhdev, " Pen") + + +class TouchTabletTest(BaseTest.TestTablet): + def assertName(self, uhdev): + super().assertName(uhdev, " Finger") + + +class TestOpaqueTablet(PenTabletTest): def create_device(self): return OpaqueTablet() @@ -842,3 +859,64 @@ class TestPTHX60_Pen(TestOpaqueCTLTablet): libevdev.InputEvent(libevdev.EV_KEY.BTN_0, 0), ], ) + + +class TestDTH2452Tablet(test_multitouch.BaseTest.TestMultitouch, TouchTabletTest): + def create_device(self): + return test_multitouch.Digitizer( + "DTH 2452", + rdesc="05 0d 09 04 a1 01 85 0c 95 01 75 08 15 00 26 ff 00 81 03 09 54 81 02 09 22 a1 02 05 0d 95 01 75 01 25 01 09 42 81 02 81 03 09 47 81 02 95 05 81 03 09 51 26 ff 00 75 10 95 01 81 02 35 00 65 11 55 0e 05 01 09 30 26 a0 44 46 96 14 81 42 09 31 26 9a 26 46 95 0b 81 42 05 0d 75 08 95 01 15 00 09 48 26 5f 00 46 7c 14 81 02 09 49 25 35 46 7d 0b 81 02 45 00 65 00 55 00 c0 05 0d 09 22 a1 02 05 0d 95 01 75 01 25 01 09 42 81 02 81 03 09 47 81 02 95 05 81 03 09 51 26 ff 00 75 10 95 01 81 02 35 00 65 11 55 0e 05 01 09 30 26 a0 44 46 96 14 81 42 09 31 26 9a 26 46 95 0b 81 42 05 0d 75 08 95 01 15 00 09 48 26 5f 00 46 7c 14 81 02 09 49 25 35 46 7d 0b 81 02 45 00 65 00 55 00 c0 05 0d 09 22 a1 02 05 0d 95 01 75 01 25 01 09 42 81 02 81 03 09 47 81 02 95 05 81 03 09 51 26 ff 00 75 10 95 01 81 02 35 00 65 11 55 0e 05 01 09 30 26 a0 44 46 96 14 81 42 09 31 26 9a 26 46 95 0b 81 42 05 0d 75 08 95 01 15 00 09 48 26 5f 00 46 7c 14 81 02 09 49 25 35 46 7d 0b 81 02 45 00 65 00 55 00 c0 05 0d 09 22 a1 02 05 0d 95 01 75 01 25 01 09 42 81 02 81 03 09 47 81 02 95 05 81 03 09 51 26 ff 00 75 10 95 01 81 02 35 00 65 11 55 0e 05 01 09 30 26 a0 44 46 96 14 81 42 09 31 26 9a 26 46 95 0b 81 42 05 0d 75 08 95 01 15 00 09 48 26 5f 00 46 7c 14 81 02 09 49 25 35 46 7d 0b 81 02 45 00 65 00 55 00 c0 05 0d 09 22 a1 02 05 0d 95 01 75 01 25 01 09 42 81 02 81 03 09 47 81 02 95 05 81 03 09 51 26 ff 00 75 10 95 01 81 02 35 00 65 11 55 0e 05 01 09 30 26 a0 44 46 96 14 81 42 09 31 26 9a 26 46 95 0b 81 42 05 0d 75 08 95 01 15 00 09 48 26 5f 00 46 7c 14 81 02 09 49 25 35 46 7d 0b 81 02 45 00 65 00 55 00 c0 05 0d 27 ff ff 00 00 75 10 95 01 09 56 81 02 75 08 95 0e 81 03 09 55 26 ff 00 75 08 b1 02 85 0a 06 00 ff 09 c5 96 00 01 b1 02 c0 06 00 ff 09 01 a1 01 09 01 85 13 15 00 26 ff 00 75 08 95 3f 81 02 06 00 ff 09 01 15 00 26 ff 00 75 08 95 3f 91 02 c0", + input_info=(0x3, 0x056A, 0x0383), + ) + + def test_contact_id_0(self): + """ + Bring a finger in contact with the tablet, then hold it down and remove it. + + Ensure that even with contact ID = 0 which is usually given as an invalid + touch event by most tablets with the exception of a few, that given the + confidence bit is set to 1 it should process it as a valid touch to cover + the few tablets using contact ID = 0 as a valid touch value. + """ + uhdev = self.uhdev + evdev = uhdev.get_evdev() + + t0 = test_multitouch.Touch(0, 50, 100) + r = uhdev.event([t0]) + events = uhdev.next_sync_events() + self.debug_reports(r, uhdev, events) + + slot = self.get_slot(uhdev, t0, 0) + + assert libevdev.InputEvent(libevdev.EV_KEY.BTN_TOUCH, 1) in events + assert evdev.slots[slot][libevdev.EV_ABS.ABS_MT_TRACKING_ID] == 0 + assert evdev.slots[slot][libevdev.EV_ABS.ABS_MT_POSITION_X] == 50 + assert evdev.slots[slot][libevdev.EV_ABS.ABS_MT_POSITION_Y] == 100 + + t0.tipswitch = False + if uhdev.quirks is None or "VALID_IS_INRANGE" not in uhdev.quirks: + t0.inrange = False + r = uhdev.event([t0]) + events = uhdev.next_sync_events() + self.debug_reports(r, uhdev, events) + assert libevdev.InputEvent(libevdev.EV_KEY.BTN_TOUCH, 0) in events + assert evdev.slots[slot][libevdev.EV_ABS.ABS_MT_TRACKING_ID] == -1 + + def test_confidence_false(self): + """ + Bring a finger in contact with the tablet with confidence set to false. + + Ensure that the confidence bit being set to false should not result in a touch event. + """ + uhdev = self.uhdev + evdev = uhdev.get_evdev() + + t0 = test_multitouch.Touch(1, 50, 100) + t0.confidence = False + r = uhdev.event([t0]) + events = uhdev.next_sync_events() + self.debug_reports(r, uhdev, events) + + slot = self.get_slot(uhdev, t0, 0) + + assert not events
\ No newline at end of file diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index 294619ade49fe..1c952d1401d46 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -8,7 +8,8 @@ export logfile=/dev/stdout export per_test_logging= # Defaults for "settings" file fields: -# "timeout" how many seconds to let each test run before failing. +# "timeout" how many seconds to let each test run before running +# over our soft timeout limit. export kselftest_default_timeout=45 # There isn't a shell-agnostic way to find the path of a sourced file, @@ -90,6 +91,14 @@ run_one() done < "$settings" fi + # Command line timeout overrides the settings file + if [ -n "$kselftest_override_timeout" ]; then + kselftest_timeout="$kselftest_override_timeout" + echo "# overriding timeout to $kselftest_timeout" >> "$logfile" + else + echo "# timeout set to $kselftest_timeout" >> "$logfile" + fi + TEST_HDR_MSG="selftests: $DIR: $BASENAME_TEST" echo "# $TEST_HDR_MSG" if [ ! -e "$TEST" ]; then diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index d8bff2005dfc9..5fd49ad0c696f 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -249,7 +249,7 @@ /** * FIXTURE_SETUP() - Prepares the setup function for the fixture. - * *_metadata* is included so that EXPECT_* and ASSERT_* work correctly. + * *_metadata* is included so that EXPECT_*, ASSERT_* etc. work correctly. * * @fixture_name: fixture name * @@ -275,7 +275,7 @@ /** * FIXTURE_TEARDOWN() - * *_metadata* is included so that EXPECT_* and ASSERT_* work correctly. + * *_metadata* is included so that EXPECT_*, ASSERT_* etc. work correctly. * * @fixture_name: fixture name * @@ -388,7 +388,7 @@ if (setjmp(_metadata->env) == 0) { \ fixture_name##_setup(_metadata, &self, variant->data); \ /* Let setup failure terminate early. */ \ - if (!_metadata->passed) \ + if (!_metadata->passed || _metadata->skip) \ return; \ _metadata->setup_completed = true; \ fixture_name##_##test_name(_metadata, &self, variant->data); \ diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 7a5ff646e7e79..4761b768b773c 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -116,6 +116,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests TEST_GEN_PROGS_x86_64 += x86_64/amx_test TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test +TEST_GEN_PROGS_x86_64 += x86_64/recalc_apic_map_test TEST_GEN_PROGS_x86_64 += access_tracking_perf_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index d4e1f4af29d68..4f10055af2aa2 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -48,6 +48,34 @@ struct reg_sublist { __u64 rejects_set_n; }; +struct feature_id_reg { + __u64 reg; + __u64 id_reg; + __u64 feat_shift; + __u64 feat_min; +}; + +static struct feature_id_reg feat_id_regs[] = { + { + ARM64_SYS_REG(3, 0, 2, 0, 3), /* TCR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ + 0, + 1 + }, + { + ARM64_SYS_REG(3, 0, 10, 2, 2), /* PIRE0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ + 4, + 1 + }, + { + ARM64_SYS_REG(3, 0, 10, 2, 3), /* PIR_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ + 4, + 1 + } +}; + struct vcpu_config { char *name; struct reg_sublist sublists[]; @@ -68,7 +96,8 @@ static int vcpu_configs_n; #define for_each_missing_reg(i) \ for ((i) = 0; (i) < blessed_n; ++(i)) \ - if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i])) + if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i])) \ + if (check_supported_feat_reg(vcpu, blessed_reg[i])) #define for_each_new_reg(i) \ for_each_reg_filtered(i) \ @@ -132,6 +161,25 @@ static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg) return false; } +static bool check_supported_feat_reg(struct kvm_vcpu *vcpu, __u64 reg) +{ + int i, ret; + __u64 data, feat_val; + + for (i = 0; i < ARRAY_SIZE(feat_id_regs); i++) { + if (feat_id_regs[i].reg == reg) { + ret = __vcpu_get_reg(vcpu, feat_id_regs[i].id_reg, &data); + if (ret < 0) + return false; + + feat_val = ((data >> feat_id_regs[i].feat_shift) & 0xf); + return feat_val >= feat_id_regs[i].feat_min; + } + } + + return true; +} + static const char *str_with_index(const char *template, __u64 index) { char *str, *p; @@ -843,12 +891,15 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 0, 2, 0, 0), /* TTBR0_EL1 */ ARM64_SYS_REG(3, 0, 2, 0, 1), /* TTBR1_EL1 */ ARM64_SYS_REG(3, 0, 2, 0, 2), /* TCR_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 3), /* TCR2_EL1 */ ARM64_SYS_REG(3, 0, 5, 1, 0), /* AFSR0_EL1 */ ARM64_SYS_REG(3, 0, 5, 1, 1), /* AFSR1_EL1 */ ARM64_SYS_REG(3, 0, 5, 2, 0), /* ESR_EL1 */ ARM64_SYS_REG(3, 0, 6, 0, 0), /* FAR_EL1 */ ARM64_SYS_REG(3, 0, 7, 4, 0), /* PAR_EL1 */ ARM64_SYS_REG(3, 0, 10, 2, 0), /* MAIR_EL1 */ + ARM64_SYS_REG(3, 0, 10, 2, 2), /* PIRE0_EL1 */ + ARM64_SYS_REG(3, 0, 10, 2, 3), /* PIR_EL1 */ ARM64_SYS_REG(3, 0, 10, 3, 0), /* AMAIR_EL1 */ ARM64_SYS_REG(3, 0, 12, 0, 0), /* VBAR_EL1 */ ARM64_SYS_REG(3, 0, 12, 1, 1), /* DISR_EL1 */ diff --git a/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c b/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c new file mode 100644 index 0000000000000..4c416ebe7d66d --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test edge cases and race conditions in kvm_recalculate_apic_map(). + */ + +#include <sys/ioctl.h> +#include <pthread.h> +#include <time.h> + +#include "processor.h" +#include "test_util.h" +#include "kvm_util.h" +#include "apic.h" + +#define TIMEOUT 5 /* seconds */ + +#define LAPIC_DISABLED 0 +#define LAPIC_X2APIC (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE) +#define MAX_XAPIC_ID 0xff + +static void *race(void *arg) +{ + struct kvm_lapic_state lapic = {}; + struct kvm_vcpu *vcpu = arg; + + while (1) { + /* Trigger kvm_recalculate_apic_map(). */ + vcpu_ioctl(vcpu, KVM_SET_LAPIC, &lapic); + pthread_testcancel(); + } + + return NULL; +} + +int main(void) +{ + struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + struct kvm_vcpu *vcpuN; + struct kvm_vm *vm; + pthread_t thread; + time_t t; + int i; + + kvm_static_assert(KVM_MAX_VCPUS > MAX_XAPIC_ID); + + /* + * Create the max number of vCPUs supported by selftests so that KVM + * has decent amount of work to do when recalculating the map, i.e. to + * make the problematic window large enough to hit. + */ + vm = vm_create_with_vcpus(KVM_MAX_VCPUS, NULL, vcpus); + + /* + * Enable x2APIC on all vCPUs so that KVM doesn't bail from the recalc + * due to vCPUs having aliased xAPIC IDs (truncated to 8 bits). + */ + for (i = 0; i < KVM_MAX_VCPUS; i++) + vcpu_set_msr(vcpus[i], MSR_IA32_APICBASE, LAPIC_X2APIC); + + ASSERT_EQ(pthread_create(&thread, NULL, race, vcpus[0]), 0); + + vcpuN = vcpus[KVM_MAX_VCPUS - 1]; + for (t = time(NULL) + TIMEOUT; time(NULL) < t;) { + vcpu_set_msr(vcpuN, MSR_IA32_APICBASE, LAPIC_X2APIC); + vcpu_set_msr(vcpuN, MSR_IA32_APICBASE, LAPIC_DISABLED); + } + + ASSERT_EQ(pthread_cancel(thread), 0); + ASSERT_EQ(pthread_join(thread, NULL), 0); + + kvm_vm_free(vm); + + return 0; +} diff --git a/tools/testing/selftests/landlock/config b/tools/testing/selftests/landlock/config index 0f0a65287bacf..3dc9e438eab10 100644 --- a/tools/testing/selftests/landlock/config +++ b/tools/testing/selftests/landlock/config @@ -1,7 +1,10 @@ +CONFIG_CGROUPS=y +CONFIG_CGROUP_SCHED=y CONFIG_OVERLAY_FS=y -CONFIG_SECURITY_LANDLOCK=y -CONFIG_SECURITY_PATH=y +CONFIG_PROC_FS=y CONFIG_SECURITY=y +CONFIG_SECURITY_LANDLOCK=y CONFIG_SHMEM=y -CONFIG_TMPFS_XATTR=y +CONFIG_SYSFS=y CONFIG_TMPFS=y +CONFIG_TMPFS_XATTR=y diff --git a/tools/testing/selftests/landlock/config.um b/tools/testing/selftests/landlock/config.um new file mode 100644 index 0000000000000..40937c0395d6c --- /dev/null +++ b/tools/testing/selftests/landlock/config.um @@ -0,0 +1 @@ +CONFIG_HOSTFS=y diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index b6c4be3faf7a9..83d5655695126 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -10,6 +10,7 @@ #define _GNU_SOURCE #include <fcntl.h> #include <linux/landlock.h> +#include <linux/magic.h> #include <sched.h> #include <stdio.h> #include <string.h> @@ -19,6 +20,7 @@ #include <sys/sendfile.h> #include <sys/stat.h> #include <sys/sysmacros.h> +#include <sys/vfs.h> #include <unistd.h> #include "common.h" @@ -107,8 +109,10 @@ static bool fgrep(FILE *const inf, const char *const str) return false; } -static bool supports_overlayfs(void) +static bool supports_filesystem(const char *const filesystem) { + char str[32]; + int len; bool res; FILE *const inf = fopen("/proc/filesystems", "r"); @@ -119,11 +123,33 @@ static bool supports_overlayfs(void) if (!inf) return true; - res = fgrep(inf, "nodev\toverlay\n"); + /* filesystem can be null for bind mounts. */ + if (!filesystem) + return true; + + len = snprintf(str, sizeof(str), "nodev\t%s\n", filesystem); + if (len >= sizeof(str)) + /* Ignores too-long filesystem names. */ + return true; + + res = fgrep(inf, str); fclose(inf); return res; } +static bool cwd_matches_fs(unsigned int fs_magic) +{ + struct statfs statfs_buf; + + if (!fs_magic) + return true; + + if (statfs(".", &statfs_buf)) + return true; + + return statfs_buf.f_type == fs_magic; +} + static void mkdir_parents(struct __test_metadata *const _metadata, const char *const path) { @@ -206,7 +232,26 @@ out: return err; } -static void prepare_layout(struct __test_metadata *const _metadata) +struct mnt_opt { + const char *const source; + const char *const type; + const unsigned long flags; + const char *const data; +}; + +const struct mnt_opt mnt_tmp = { + .type = "tmpfs", + .data = "size=4m,mode=700", +}; + +static int mount_opt(const struct mnt_opt *const mnt, const char *const target) +{ + return mount(mnt->source ?: mnt->type, target, mnt->type, mnt->flags, + mnt->data); +} + +static void prepare_layout_opt(struct __test_metadata *const _metadata, + const struct mnt_opt *const mnt) { disable_caps(_metadata); umask(0077); @@ -217,12 +262,28 @@ static void prepare_layout(struct __test_metadata *const _metadata) * for tests relying on pivot_root(2) and move_mount(2). */ set_cap(_metadata, CAP_SYS_ADMIN); - ASSERT_EQ(0, unshare(CLONE_NEWNS)); - ASSERT_EQ(0, mount("tmp", TMP_DIR, "tmpfs", 0, "size=4m,mode=700")); + ASSERT_EQ(0, unshare(CLONE_NEWNS | CLONE_NEWCGROUP)); + ASSERT_EQ(0, mount_opt(mnt, TMP_DIR)) + { + TH_LOG("Failed to mount the %s filesystem: %s", mnt->type, + strerror(errno)); + /* + * FIXTURE_TEARDOWN() is not called when FIXTURE_SETUP() + * failed, so we need to explicitly do a minimal cleanup to + * avoid cascading errors with other tests that don't depend on + * the same filesystem. + */ + remove_path(TMP_DIR); + } ASSERT_EQ(0, mount(NULL, TMP_DIR, NULL, MS_PRIVATE | MS_REC, NULL)); clear_cap(_metadata, CAP_SYS_ADMIN); } +static void prepare_layout(struct __test_metadata *const _metadata) +{ + prepare_layout_opt(_metadata, &mnt_tmp); +} + static void cleanup_layout(struct __test_metadata *const _metadata) { set_cap(_metadata, CAP_SYS_ADMIN); @@ -231,6 +292,20 @@ static void cleanup_layout(struct __test_metadata *const _metadata) EXPECT_EQ(0, remove_path(TMP_DIR)); } +/* clang-format off */ +FIXTURE(layout0) {}; +/* clang-format on */ + +FIXTURE_SETUP(layout0) +{ + prepare_layout(_metadata); +} + +FIXTURE_TEARDOWN(layout0) +{ + cleanup_layout(_metadata); +} + static void create_layout1(struct __test_metadata *const _metadata) { create_file(_metadata, file1_s1d1); @@ -248,7 +323,7 @@ static void create_layout1(struct __test_metadata *const _metadata) create_file(_metadata, file1_s3d1); create_directory(_metadata, dir_s3d2); set_cap(_metadata, CAP_SYS_ADMIN); - ASSERT_EQ(0, mount("tmp", dir_s3d2, "tmpfs", 0, "size=4m,mode=700")); + ASSERT_EQ(0, mount_opt(&mnt_tmp, dir_s3d2)); clear_cap(_metadata, CAP_SYS_ADMIN); ASSERT_EQ(0, mkdir(dir_s3d3, 0700)); @@ -262,11 +337,13 @@ static void remove_layout1(struct __test_metadata *const _metadata) EXPECT_EQ(0, remove_path(file1_s1d3)); EXPECT_EQ(0, remove_path(file1_s1d2)); EXPECT_EQ(0, remove_path(file1_s1d1)); + EXPECT_EQ(0, remove_path(dir_s1d3)); EXPECT_EQ(0, remove_path(file2_s2d3)); EXPECT_EQ(0, remove_path(file1_s2d3)); EXPECT_EQ(0, remove_path(file1_s2d2)); EXPECT_EQ(0, remove_path(file1_s2d1)); + EXPECT_EQ(0, remove_path(dir_s2d2)); EXPECT_EQ(0, remove_path(file1_s3d1)); EXPECT_EQ(0, remove_path(dir_s3d3)); @@ -510,7 +587,7 @@ TEST_F_FORK(layout1, file_and_dir_access_rights) ASSERT_EQ(0, close(ruleset_fd)); } -TEST_F_FORK(layout1, unknown_access_rights) +TEST_F_FORK(layout0, unknown_access_rights) { __u64 access_mask; @@ -608,7 +685,7 @@ static void enforce_ruleset(struct __test_metadata *const _metadata, } } -TEST_F_FORK(layout1, proc_nsfs) +TEST_F_FORK(layout0, proc_nsfs) { const struct rule rules[] = { { @@ -657,11 +734,11 @@ TEST_F_FORK(layout1, proc_nsfs) ASSERT_EQ(0, close(path_beneath.parent_fd)); } -TEST_F_FORK(layout1, unpriv) +TEST_F_FORK(layout0, unpriv) { const struct rule rules[] = { { - .path = dir_s1d2, + .path = TMP_DIR, .access = ACCESS_RO, }, {}, @@ -1301,12 +1378,12 @@ TEST_F_FORK(layout1, inherit_superset) ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY)); } -TEST_F_FORK(layout1, max_layers) +TEST_F_FORK(layout0, max_layers) { int i, err; const struct rule rules[] = { { - .path = dir_s1d2, + .path = TMP_DIR, .access = ACCESS_RO, }, {}, @@ -4030,21 +4107,24 @@ static const char (*merge_sub_files[])[] = { * └── work */ -/* clang-format off */ -FIXTURE(layout2_overlay) {}; -/* clang-format on */ +FIXTURE(layout2_overlay) +{ + bool skip_test; +}; FIXTURE_SETUP(layout2_overlay) { - if (!supports_overlayfs()) - SKIP(return, "overlayfs is not supported"); + if (!supports_filesystem("overlay")) { + self->skip_test = true; + SKIP(return, "overlayfs is not supported (setup)"); + } prepare_layout(_metadata); create_directory(_metadata, LOWER_BASE); set_cap(_metadata, CAP_SYS_ADMIN); /* Creates tmpfs mount points to get deterministic overlayfs. */ - ASSERT_EQ(0, mount("tmp", LOWER_BASE, "tmpfs", 0, "size=4m,mode=700")); + ASSERT_EQ(0, mount_opt(&mnt_tmp, LOWER_BASE)); clear_cap(_metadata, CAP_SYS_ADMIN); create_file(_metadata, lower_fl1); create_file(_metadata, lower_dl1_fl2); @@ -4054,7 +4134,7 @@ FIXTURE_SETUP(layout2_overlay) create_directory(_metadata, UPPER_BASE); set_cap(_metadata, CAP_SYS_ADMIN); - ASSERT_EQ(0, mount("tmp", UPPER_BASE, "tmpfs", 0, "size=4m,mode=700")); + ASSERT_EQ(0, mount_opt(&mnt_tmp, UPPER_BASE)); clear_cap(_metadata, CAP_SYS_ADMIN); create_file(_metadata, upper_fu1); create_file(_metadata, upper_du1_fu2); @@ -4075,8 +4155,8 @@ FIXTURE_SETUP(layout2_overlay) FIXTURE_TEARDOWN(layout2_overlay) { - if (!supports_overlayfs()) - SKIP(return, "overlayfs is not supported"); + if (self->skip_test) + SKIP(return, "overlayfs is not supported (teardown)"); EXPECT_EQ(0, remove_path(lower_do1_fl3)); EXPECT_EQ(0, remove_path(lower_dl1_fl2)); @@ -4109,8 +4189,8 @@ FIXTURE_TEARDOWN(layout2_overlay) TEST_F_FORK(layout2_overlay, no_restriction) { - if (!supports_overlayfs()) - SKIP(return, "overlayfs is not supported"); + if (self->skip_test) + SKIP(return, "overlayfs is not supported (test)"); ASSERT_EQ(0, test_open(lower_fl1, O_RDONLY)); ASSERT_EQ(0, test_open(lower_dl1, O_RDONLY)); @@ -4275,8 +4355,8 @@ TEST_F_FORK(layout2_overlay, same_content_different_file) size_t i; const char *path_entry; - if (!supports_overlayfs()) - SKIP(return, "overlayfs is not supported"); + if (self->skip_test) + SKIP(return, "overlayfs is not supported (test)"); /* Sets rules on base directories (i.e. outside overlay scope). */ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer1_base); @@ -4423,4 +4503,261 @@ TEST_F_FORK(layout2_overlay, same_content_different_file) } } +FIXTURE(layout3_fs) +{ + bool has_created_dir; + bool has_created_file; + char *dir_path; + bool skip_test; +}; + +FIXTURE_VARIANT(layout3_fs) +{ + const struct mnt_opt mnt; + const char *const file_path; + unsigned int cwd_fs_magic; +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(layout3_fs, tmpfs) { + /* clang-format on */ + .mnt = mnt_tmp, + .file_path = file1_s1d1, +}; + +FIXTURE_VARIANT_ADD(layout3_fs, ramfs) { + .mnt = { + .type = "ramfs", + .data = "mode=700", + }, + .file_path = TMP_DIR "/dir/file", +}; + +FIXTURE_VARIANT_ADD(layout3_fs, cgroup2) { + .mnt = { + .type = "cgroup2", + }, + .file_path = TMP_DIR "/test/cgroup.procs", +}; + +FIXTURE_VARIANT_ADD(layout3_fs, proc) { + .mnt = { + .type = "proc", + }, + .file_path = TMP_DIR "/self/status", +}; + +FIXTURE_VARIANT_ADD(layout3_fs, sysfs) { + .mnt = { + .type = "sysfs", + }, + .file_path = TMP_DIR "/kernel/notes", +}; + +FIXTURE_VARIANT_ADD(layout3_fs, hostfs) { + .mnt = { + .source = TMP_DIR, + .flags = MS_BIND, + }, + .file_path = TMP_DIR "/dir/file", + .cwd_fs_magic = HOSTFS_SUPER_MAGIC, +}; + +FIXTURE_SETUP(layout3_fs) +{ + struct stat statbuf; + const char *slash; + size_t dir_len; + + if (!supports_filesystem(variant->mnt.type) || + !cwd_matches_fs(variant->cwd_fs_magic)) { + self->skip_test = true; + SKIP(return, "this filesystem is not supported (setup)"); + } + + slash = strrchr(variant->file_path, '/'); + ASSERT_NE(slash, NULL); + dir_len = (size_t)slash - (size_t)variant->file_path; + ASSERT_LT(0, dir_len); + self->dir_path = malloc(dir_len + 1); + self->dir_path[dir_len] = '\0'; + strncpy(self->dir_path, variant->file_path, dir_len); + + prepare_layout_opt(_metadata, &variant->mnt); + + /* Creates directory when required. */ + if (stat(self->dir_path, &statbuf)) { + set_cap(_metadata, CAP_DAC_OVERRIDE); + EXPECT_EQ(0, mkdir(self->dir_path, 0700)) + { + TH_LOG("Failed to create directory \"%s\": %s", + self->dir_path, strerror(errno)); + free(self->dir_path); + self->dir_path = NULL; + } + self->has_created_dir = true; + clear_cap(_metadata, CAP_DAC_OVERRIDE); + } + + /* Creates file when required. */ + if (stat(variant->file_path, &statbuf)) { + int fd; + + set_cap(_metadata, CAP_DAC_OVERRIDE); + fd = creat(variant->file_path, 0600); + EXPECT_LE(0, fd) + { + TH_LOG("Failed to create file \"%s\": %s", + variant->file_path, strerror(errno)); + } + EXPECT_EQ(0, close(fd)); + self->has_created_file = true; + clear_cap(_metadata, CAP_DAC_OVERRIDE); + } +} + +FIXTURE_TEARDOWN(layout3_fs) +{ + if (self->skip_test) + SKIP(return, "this filesystem is not supported (teardown)"); + + if (self->has_created_file) { + set_cap(_metadata, CAP_DAC_OVERRIDE); + /* + * Don't check for error because the file might already + * have been removed (cf. release_inode test). + */ + unlink(variant->file_path); + clear_cap(_metadata, CAP_DAC_OVERRIDE); + } + + if (self->has_created_dir) { + set_cap(_metadata, CAP_DAC_OVERRIDE); + /* + * Don't check for error because the directory might already + * have been removed (cf. release_inode test). + */ + rmdir(self->dir_path); + clear_cap(_metadata, CAP_DAC_OVERRIDE); + } + free(self->dir_path); + self->dir_path = NULL; + + cleanup_layout(_metadata); +} + +static void layer3_fs_tag_inode(struct __test_metadata *const _metadata, + FIXTURE_DATA(layout3_fs) * self, + const FIXTURE_VARIANT(layout3_fs) * variant, + const char *const rule_path) +{ + const struct rule layer1_allow_read_file[] = { + { + .path = rule_path, + .access = LANDLOCK_ACCESS_FS_READ_FILE, + }, + {}, + }; + const struct landlock_ruleset_attr layer2_deny_everything_attr = { + .handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE, + }; + const char *const dev_null_path = "/dev/null"; + int ruleset_fd; + + if (self->skip_test) + SKIP(return, "this filesystem is not supported (test)"); + + /* Checks without Landlock. */ + EXPECT_EQ(0, test_open(dev_null_path, O_RDONLY | O_CLOEXEC)); + EXPECT_EQ(0, test_open(variant->file_path, O_RDONLY | O_CLOEXEC)); + + ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE, + layer1_allow_read_file); + EXPECT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + EXPECT_EQ(0, close(ruleset_fd)); + + EXPECT_EQ(EACCES, test_open(dev_null_path, O_RDONLY | O_CLOEXEC)); + EXPECT_EQ(0, test_open(variant->file_path, O_RDONLY | O_CLOEXEC)); + + /* Forbids directory reading. */ + ruleset_fd = + landlock_create_ruleset(&layer2_deny_everything_attr, + sizeof(layer2_deny_everything_attr), 0); + EXPECT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + EXPECT_EQ(0, close(ruleset_fd)); + + /* Checks with Landlock and forbidden access. */ + EXPECT_EQ(EACCES, test_open(dev_null_path, O_RDONLY | O_CLOEXEC)); + EXPECT_EQ(EACCES, test_open(variant->file_path, O_RDONLY | O_CLOEXEC)); +} + +/* Matrix of tests to check file hierarchy evaluation. */ + +TEST_F_FORK(layout3_fs, tag_inode_dir_parent) +{ + /* The current directory must not be the root for this test. */ + layer3_fs_tag_inode(_metadata, self, variant, "."); +} + +TEST_F_FORK(layout3_fs, tag_inode_dir_mnt) +{ + layer3_fs_tag_inode(_metadata, self, variant, TMP_DIR); +} + +TEST_F_FORK(layout3_fs, tag_inode_dir_child) +{ + layer3_fs_tag_inode(_metadata, self, variant, self->dir_path); +} + +TEST_F_FORK(layout3_fs, tag_inode_file) +{ + layer3_fs_tag_inode(_metadata, self, variant, variant->file_path); +} + +/* Light version of layout1.release_inodes */ +TEST_F_FORK(layout3_fs, release_inodes) +{ + const struct rule layer1[] = { + { + .path = TMP_DIR, + .access = LANDLOCK_ACCESS_FS_READ_DIR, + }, + {}, + }; + int ruleset_fd; + + if (self->skip_test) + SKIP(return, "this filesystem is not supported (test)"); + + /* Clean up for the teardown to not fail. */ + if (self->has_created_file) + EXPECT_EQ(0, remove_path(variant->file_path)); + + if (self->has_created_dir) + /* Don't check for error because of cgroup specificities. */ + remove_path(self->dir_path); + + ruleset_fd = + create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_DIR, layer1); + ASSERT_LE(0, ruleset_fd); + + /* Unmount the filesystem while it is being used by a ruleset. */ + set_cap(_metadata, CAP_SYS_ADMIN); + ASSERT_EQ(0, umount(TMP_DIR)); + clear_cap(_metadata, CAP_SYS_ADMIN); + + /* Replaces with a new mount point to simplify FIXTURE_TEARDOWN. */ + set_cap(_metadata, CAP_SYS_ADMIN); + ASSERT_EQ(0, mount_opt(&mnt_tmp, TMP_DIR)); + clear_cap(_metadata, CAP_SYS_ADMIN); + + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); + + /* Checks that access to the new mount point is denied. */ + ASSERT_EQ(EACCES, test_open(TMP_DIR, O_RDONLY)); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 05400462c7799..d17854285f2b6 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -44,10 +44,26 @@ endif selfdir = $(realpath $(dir $(filter %/lib.mk,$(MAKEFILE_LIST)))) top_srcdir = $(selfdir)/../../.. -ifeq ($(KHDR_INCLUDES),) -KHDR_INCLUDES := -isystem $(top_srcdir)/usr/include +ifeq ("$(origin O)", "command line") + KBUILD_OUTPUT := $(O) endif +ifneq ($(KBUILD_OUTPUT),) + # Make's built-in functions such as $(abspath ...), $(realpath ...) cannot + # expand a shell special character '~'. We use a somewhat tedious way here. + abs_objtree := $(shell cd $(top_srcdir) && mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd) + $(if $(abs_objtree),, \ + $(error failed to create output directory "$(KBUILD_OUTPUT)")) + # $(realpath ...) resolves symlinks + abs_objtree := $(realpath $(abs_objtree)) + KHDR_DIR := ${abs_objtree}/usr/include +else + abs_srctree := $(shell cd $(top_srcdir) && pwd) + KHDR_DIR := ${abs_srctree}/usr/include +endif + +KHDR_INCLUDES := -isystem $(KHDR_DIR) + # The following are built by lib.mk common compile rules. # TEST_CUSTOM_PROGS should be used by tests that require # custom build rule and prevent common build rule use. @@ -58,7 +74,25 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) -all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) +all: kernel_header_files $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) \ + $(TEST_GEN_FILES) + +kernel_header_files: + @ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null; \ + if [ $$? -ne 0 ]; then \ + RED='\033[1;31m'; \ + NOCOLOR='\033[0m'; \ + echo; \ + echo -e "$${RED}error$${NOCOLOR}: missing kernel header files."; \ + echo "Please run this and try again:"; \ + echo; \ + echo " cd $(top_srcdir)"; \ + echo " make headers"; \ + echo; \ + exit 1; \ + fi + +.PHONY: kernel_header_files define RUN_TESTS BASE_DIR="$(selfdir)"; \ diff --git a/tools/testing/selftests/media_tests/video_device_test.c b/tools/testing/selftests/media_tests/video_device_test.c index 0f6aef2e25932..2c44e115f2f06 100644 --- a/tools/testing/selftests/media_tests/video_device_test.c +++ b/tools/testing/selftests/media_tests/video_device_test.c @@ -37,45 +37,58 @@ #include <time.h> #include <linux/videodev2.h> -int main(int argc, char **argv) +#define PRIORITY_MAX 4 + +int priority_test(int fd) { - int opt; - char video_dev[256]; - int count; - struct v4l2_tuner vtuner; - struct v4l2_capability vcap; + /* This test will try to update the priority associated with a file descriptor */ + + enum v4l2_priority old_priority, new_priority, priority_to_compare; int ret; - int fd; + int result = 0; - if (argc < 2) { - printf("Usage: %s [-d </dev/videoX>]\n", argv[0]); - exit(-1); + ret = ioctl(fd, VIDIOC_G_PRIORITY, &old_priority); + if (ret < 0) { + printf("Failed to get priority: %s\n", strerror(errno)); + return -1; + } + new_priority = (old_priority + 1) % PRIORITY_MAX; + ret = ioctl(fd, VIDIOC_S_PRIORITY, &new_priority); + if (ret < 0) { + printf("Failed to set priority: %s\n", strerror(errno)); + return -1; + } + ret = ioctl(fd, VIDIOC_G_PRIORITY, &priority_to_compare); + if (ret < 0) { + printf("Failed to get new priority: %s\n", strerror(errno)); + result = -1; + goto cleanup; + } + if (priority_to_compare != new_priority) { + printf("Priority wasn't set - test failed\n"); + result = -1; } - /* Process arguments */ - while ((opt = getopt(argc, argv, "d:")) != -1) { - switch (opt) { - case 'd': - strncpy(video_dev, optarg, sizeof(video_dev) - 1); - video_dev[sizeof(video_dev)-1] = '\0'; - break; - default: - printf("Usage: %s [-d </dev/videoX>]\n", argv[0]); - exit(-1); - } +cleanup: + ret = ioctl(fd, VIDIOC_S_PRIORITY, &old_priority); + if (ret < 0) { + printf("Failed to restore priority: %s\n", strerror(errno)); + return -1; } + return result; +} + +int loop_test(int fd) +{ + int count; + struct v4l2_tuner vtuner; + struct v4l2_capability vcap; + int ret; /* Generate random number of interations */ srand((unsigned int) time(NULL)); count = rand(); - /* Open Video device and keep it open */ - fd = open(video_dev, O_RDWR); - if (fd == -1) { - printf("Video Device open errno %s\n", strerror(errno)); - exit(-1); - } - printf("\nNote:\n" "While test is running, remove the device or unbind\n" "driver and ensure there are no use after free errors\n" @@ -98,4 +111,46 @@ int main(int argc, char **argv) sleep(10); count--; } + return 0; +} + +int main(int argc, char **argv) +{ + int opt; + char video_dev[256]; + int fd; + int test_result; + + if (argc < 2) { + printf("Usage: %s [-d </dev/videoX>]\n", argv[0]); + exit(-1); + } + + /* Process arguments */ + while ((opt = getopt(argc, argv, "d:")) != -1) { + switch (opt) { + case 'd': + strncpy(video_dev, optarg, sizeof(video_dev) - 1); + video_dev[sizeof(video_dev)-1] = '\0'; + break; + default: + printf("Usage: %s [-d </dev/videoX>]\n", argv[0]); + exit(-1); + } + } + + /* Open Video device and keep it open */ + fd = open(video_dev, O_RDWR); + if (fd == -1) { + printf("Video Device open errno %s\n", strerror(errno)); + exit(-1); + } + + test_result = priority_test(fd); + if (!test_result) + printf("Priority test - PASSED\n"); + else + printf("Priority test - FAILED\n"); + + loop_test(fd); } diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 8917455f4f516..7e2a982383c00 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -39,3 +39,6 @@ local_config.h local_config.mk ksm_functional_tests mdwe_test +gup_longterm +mkdirty +va_high_addr_switch diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 23af4633f0f4b..66d7c07dc1773 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -5,12 +5,15 @@ LOCAL_HDRS += $(selfdir)/mm/local_config.h $(top_srcdir)/mm/gup_test.h include local_config.mk +ifeq ($(ARCH),) + ifeq ($(CROSS_COMPILE),) uname_M := $(shell uname -m 2>/dev/null || echo not) else uname_M := $(shell echo $(CROSS_COMPILE) | grep -o '^[a-z0-9]\+') endif -MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') +ARCH ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') +endif # Without this, failed build products remain, with up-to-date timestamps, # thus tricking Make (and you!) into believing that All Is Well, in subsequent @@ -29,11 +32,12 @@ MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/p # LDLIBS. MAKEFLAGS += --no-builtin-rules -CFLAGS = -Wall -I $(top_srcdir) -I $(top_srcdir)/tools/include/uapi $(EXTRA_CFLAGS) $(KHDR_INCLUDES) +CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) LDLIBS = -lrt -lpthread TEST_GEN_PROGS = cow TEST_GEN_PROGS += compaction_test +TEST_GEN_PROGS += gup_longterm TEST_GEN_PROGS += gup_test TEST_GEN_PROGS += hmm-tests TEST_GEN_PROGS += hugetlb-madvise @@ -65,7 +69,7 @@ TEST_GEN_PROGS += ksm_tests TEST_GEN_PROGS += ksm_functional_tests TEST_GEN_PROGS += mdwe_test -ifeq ($(MACHINE),x86_64) +ifeq ($(ARCH),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_program.c -m32) CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_64bit_program.c) CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_program.c -no-pie) @@ -87,13 +91,13 @@ TEST_GEN_PROGS += $(BINARIES_64) endif else -ifneq (,$(findstring $(MACHINE),ppc64)) +ifneq (,$(findstring $(ARCH),ppc64)) TEST_GEN_PROGS += protection_keys endif endif -ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sparc64 x86_64)) +ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sparc64 x86_64)) TEST_GEN_PROGS += va_high_addr_switch TEST_GEN_PROGS += virtual_address_range TEST_GEN_PROGS += write_to_hugetlbfs @@ -112,7 +116,7 @@ $(TEST_GEN_PROGS): vm_util.c $(OUTPUT)/uffd-stress: uffd-common.c $(OUTPUT)/uffd-unit-tests: uffd-common.c -ifeq ($(MACHINE),x86_64) +ifeq ($(ARCH),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) @@ -164,6 +168,8 @@ endif # IOURING_EXTRA_LIBS may get set in local_config.mk, or it may be left empty. $(OUTPUT)/cow: LDLIBS += $(IOURING_EXTRA_LIBS) +$(OUTPUT)/gup_longterm: LDLIBS += $(IOURING_EXTRA_LIBS) + $(OUTPUT)/mlock-random-test $(OUTPUT)/memfd_secret: LDLIBS += -lcap $(OUTPUT)/ksm_tests: LDLIBS += -lnuma diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index dc9d6fe860285..7324ce5363c0c 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -14,8 +14,8 @@ #include <unistd.h> #include <errno.h> #include <fcntl.h> -#include <dirent.h> #include <assert.h> +#include <linux/mman.h> #include <sys/mman.h> #include <sys/ioctl.h> #include <sys/wait.h> @@ -30,13 +30,6 @@ #include "../kselftest.h" #include "vm_util.h" -#ifndef MADV_PAGEOUT -#define MADV_PAGEOUT 21 -#endif -#ifndef MADV_COLLAPSE -#define MADV_COLLAPSE 25 -#endif - static size_t pagesize; static int pagemap_fd; static size_t thpsize; @@ -70,31 +63,6 @@ static void detect_huge_zeropage(void) close(fd); } -static void detect_hugetlbsizes(void) -{ - DIR *dir = opendir("/sys/kernel/mm/hugepages/"); - - if (!dir) - return; - - while (nr_hugetlbsizes < ARRAY_SIZE(hugetlbsizes)) { - struct dirent *entry = readdir(dir); - size_t kb; - - if (!entry) - break; - if (entry->d_type != DT_DIR) - continue; - if (sscanf(entry->d_name, "hugepages-%zukB", &kb) != 1) - continue; - hugetlbsizes[nr_hugetlbsizes] = kb * 1024; - nr_hugetlbsizes++; - ksft_print_msg("[INFO] detected hugetlb size: %zu KiB\n", - kb); - } - closedir(dir); -} - static bool range_is_swapped(void *addr, size_t size) { for (; size; addr += pagesize, size -= pagesize) @@ -1717,7 +1685,8 @@ int main(int argc, char **argv) if (thpsize) ksft_print_msg("[INFO] detected THP size: %zu KiB\n", thpsize / 1024); - detect_hugetlbsizes(); + nr_hugetlbsizes = detect_hugetlb_page_sizes(hugetlbsizes, + ARRAY_SIZE(hugetlbsizes)); detect_huge_zeropage(); ksft_print_header(); diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c new file mode 100644 index 0000000000000..d33d3e68ffab8 --- /dev/null +++ b/tools/testing/selftests/mm/gup_longterm.c @@ -0,0 +1,459 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * GUP long-term page pinning tests. + * + * Copyright 2023, Red Hat, Inc. + * + * Author(s): David Hildenbrand <david@redhat.com> + */ +#define _GNU_SOURCE +#include <stdlib.h> +#include <string.h> +#include <stdbool.h> +#include <stdint.h> +#include <unistd.h> +#include <errno.h> +#include <fcntl.h> +#include <assert.h> +#include <sys/mman.h> +#include <sys/ioctl.h> +#include <sys/vfs.h> +#include <linux/magic.h> +#include <linux/memfd.h> + +#include "local_config.h" +#ifdef LOCAL_CONFIG_HAVE_LIBURING +#include <liburing.h> +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ + +#include "../../../../mm/gup_test.h" +#include "../kselftest.h" +#include "vm_util.h" + +static size_t pagesize; +static int nr_hugetlbsizes; +static size_t hugetlbsizes[10]; +static int gup_fd; + +static __fsword_t get_fs_type(int fd) +{ + struct statfs fs; + int ret; + + do { + ret = fstatfs(fd, &fs); + } while (ret && errno == EINTR); + + return ret ? 0 : fs.f_type; +} + +static bool fs_is_unknown(__fsword_t fs_type) +{ + /* + * We only support some filesystems in our tests when dealing with + * R/W long-term pinning. For these filesystems, we can be fairly sure + * whether they support it or not. + */ + switch (fs_type) { + case TMPFS_MAGIC: + case HUGETLBFS_MAGIC: + case BTRFS_SUPER_MAGIC: + case EXT4_SUPER_MAGIC: + case XFS_SUPER_MAGIC: + return false; + default: + return true; + } +} + +static bool fs_supports_writable_longterm_pinning(__fsword_t fs_type) +{ + assert(!fs_is_unknown(fs_type)); + switch (fs_type) { + case TMPFS_MAGIC: + case HUGETLBFS_MAGIC: + return true; + default: + return false; + } +} + +enum test_type { + TEST_TYPE_RO, + TEST_TYPE_RO_FAST, + TEST_TYPE_RW, + TEST_TYPE_RW_FAST, +#ifdef LOCAL_CONFIG_HAVE_LIBURING + TEST_TYPE_IOURING, +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ +}; + +static void do_test(int fd, size_t size, enum test_type type, bool shared) +{ + __fsword_t fs_type = get_fs_type(fd); + bool should_work; + char *mem; + int ret; + + if (ftruncate(fd, size)) { + ksft_test_result_fail("ftruncate() failed\n"); + return; + } + + if (fallocate(fd, 0, 0, size)) { + if (size == pagesize) + ksft_test_result_fail("fallocate() failed\n"); + else + ksft_test_result_skip("need more free huge pages\n"); + return; + } + + mem = mmap(NULL, size, PROT_READ | PROT_WRITE, + shared ? MAP_SHARED : MAP_PRIVATE, fd, 0); + if (mem == MAP_FAILED) { + if (size == pagesize || shared) + ksft_test_result_fail("mmap() failed\n"); + else + ksft_test_result_skip("need more free huge pages\n"); + return; + } + + /* + * Fault in the page writable such that GUP-fast can eventually pin + * it immediately. + */ + memset(mem, 0, size); + + switch (type) { + case TEST_TYPE_RO: + case TEST_TYPE_RO_FAST: + case TEST_TYPE_RW: + case TEST_TYPE_RW_FAST: { + struct pin_longterm_test args; + const bool fast = type == TEST_TYPE_RO_FAST || + type == TEST_TYPE_RW_FAST; + const bool rw = type == TEST_TYPE_RW || + type == TEST_TYPE_RW_FAST; + + if (gup_fd < 0) { + ksft_test_result_skip("gup_test not available\n"); + break; + } + + if (rw && shared && fs_is_unknown(fs_type)) { + ksft_test_result_skip("Unknown filesystem\n"); + return; + } + /* + * R/O pinning or pinning in a private mapping is always + * expected to work. Otherwise, we expect long-term R/W pinning + * to only succeed for special fielesystems. + */ + should_work = !shared || !rw || + fs_supports_writable_longterm_pinning(fs_type); + + args.addr = (__u64)(uintptr_t)mem; + args.size = size; + args.flags = fast ? PIN_LONGTERM_TEST_FLAG_USE_FAST : 0; + args.flags |= rw ? PIN_LONGTERM_TEST_FLAG_USE_WRITE : 0; + ret = ioctl(gup_fd, PIN_LONGTERM_TEST_START, &args); + if (ret && errno == EINVAL) { + ksft_test_result_skip("PIN_LONGTERM_TEST_START failed\n"); + break; + } else if (ret && errno == EFAULT) { + ksft_test_result(!should_work, "Should have failed\n"); + break; + } else if (ret) { + ksft_test_result_fail("PIN_LONGTERM_TEST_START failed\n"); + break; + } + + if (ioctl(gup_fd, PIN_LONGTERM_TEST_STOP)) + ksft_print_msg("[INFO] PIN_LONGTERM_TEST_STOP failed\n"); + + /* + * TODO: if the kernel ever supports long-term R/W pinning on + * some previously unsupported filesystems, we might want to + * perform some additional tests for possible data corruptions. + */ + ksft_test_result(should_work, "Should have worked\n"); + break; + } +#ifdef LOCAL_CONFIG_HAVE_LIBURING + case TEST_TYPE_IOURING: { + struct io_uring ring; + struct iovec iov; + + /* io_uring always pins pages writable. */ + if (shared && fs_is_unknown(fs_type)) { + ksft_test_result_skip("Unknown filesystem\n"); + return; + } + should_work = !shared || + fs_supports_writable_longterm_pinning(fs_type); + + /* Skip on errors, as we might just lack kernel support. */ + ret = io_uring_queue_init(1, &ring, 0); + if (ret < 0) { + ksft_test_result_skip("io_uring_queue_init() failed\n"); + break; + } + /* + * Register the range as a fixed buffer. This will FOLL_WRITE | + * FOLL_PIN | FOLL_LONGTERM the range. + */ + iov.iov_base = mem; + iov.iov_len = size; + ret = io_uring_register_buffers(&ring, &iov, 1); + /* Only new kernels return EFAULT. */ + if (ret && (errno == ENOSPC || errno == EOPNOTSUPP || + errno == EFAULT)) { + ksft_test_result(!should_work, "Should have failed\n"); + } else if (ret) { + /* + * We might just lack support or have insufficient + * MEMLOCK limits. + */ + ksft_test_result_skip("io_uring_register_buffers() failed\n"); + } else { + ksft_test_result(should_work, "Should have worked\n"); + io_uring_unregister_buffers(&ring); + } + + io_uring_queue_exit(&ring); + break; + } +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ + default: + assert(false); + } + + munmap(mem, size); +} + +typedef void (*test_fn)(int fd, size_t size); + +static void run_with_memfd(test_fn fn, const char *desc) +{ + int fd; + + ksft_print_msg("[RUN] %s ... with memfd\n", desc); + + fd = memfd_create("test", 0); + if (fd < 0) { + ksft_test_result_fail("memfd_create() failed\n"); + return; + } + + fn(fd, pagesize); + close(fd); +} + +static void run_with_tmpfile(test_fn fn, const char *desc) +{ + FILE *file; + int fd; + + ksft_print_msg("[RUN] %s ... with tmpfile\n", desc); + + file = tmpfile(); + if (!file) { + ksft_test_result_fail("tmpfile() failed\n"); + return; + } + + fd = fileno(file); + if (fd < 0) { + ksft_test_result_fail("fileno() failed\n"); + return; + } + + fn(fd, pagesize); + fclose(file); +} + +static void run_with_local_tmpfile(test_fn fn, const char *desc) +{ + char filename[] = __FILE__"_tmpfile_XXXXXX"; + int fd; + + ksft_print_msg("[RUN] %s ... with local tmpfile\n", desc); + + fd = mkstemp(filename); + if (fd < 0) { + ksft_test_result_fail("mkstemp() failed\n"); + return; + } + + if (unlink(filename)) { + ksft_test_result_fail("unlink() failed\n"); + goto close; + } + + fn(fd, pagesize); +close: + close(fd); +} + +static void run_with_memfd_hugetlb(test_fn fn, const char *desc, + size_t hugetlbsize) +{ + int flags = MFD_HUGETLB; + int fd; + + ksft_print_msg("[RUN] %s ... with memfd hugetlb (%zu kB)\n", desc, + hugetlbsize / 1024); + + flags |= __builtin_ctzll(hugetlbsize) << MFD_HUGE_SHIFT; + + fd = memfd_create("test", flags); + if (fd < 0) { + ksft_test_result_skip("memfd_create() failed\n"); + return; + } + + fn(fd, hugetlbsize); + close(fd); +} + +struct test_case { + const char *desc; + test_fn fn; +}; + +static void test_shared_rw_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RW, true); +} + +static void test_shared_rw_fast_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RW_FAST, true); +} + +static void test_shared_ro_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RO, true); +} + +static void test_shared_ro_fast_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RO_FAST, true); +} + +static void test_private_rw_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RW, false); +} + +static void test_private_rw_fast_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RW_FAST, false); +} + +static void test_private_ro_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RO, false); +} + +static void test_private_ro_fast_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RO_FAST, false); +} + +#ifdef LOCAL_CONFIG_HAVE_LIBURING +static void test_shared_iouring(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_IOURING, true); +} + +static void test_private_iouring(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_IOURING, false); +} +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ + +static const struct test_case test_cases[] = { + { + "R/W longterm GUP pin in MAP_SHARED file mapping", + test_shared_rw_pin, + }, + { + "R/W longterm GUP-fast pin in MAP_SHARED file mapping", + test_shared_rw_fast_pin, + }, + { + "R/O longterm GUP pin in MAP_SHARED file mapping", + test_shared_ro_pin, + }, + { + "R/O longterm GUP-fast pin in MAP_SHARED file mapping", + test_shared_ro_fast_pin, + }, + { + "R/W longterm GUP pin in MAP_PRIVATE file mapping", + test_private_rw_pin, + }, + { + "R/W longterm GUP-fast pin in MAP_PRIVATE file mapping", + test_private_rw_fast_pin, + }, + { + "R/O longterm GUP pin in MAP_PRIVATE file mapping", + test_private_ro_pin, + }, + { + "R/O longterm GUP-fast pin in MAP_PRIVATE file mapping", + test_private_ro_fast_pin, + }, +#ifdef LOCAL_CONFIG_HAVE_LIBURING + { + "io_uring fixed buffer with MAP_SHARED file mapping", + test_shared_iouring, + }, + { + "io_uring fixed buffer with MAP_PRIVATE file mapping", + test_private_iouring, + }, +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ +}; + +static void run_test_case(struct test_case const *test_case) +{ + int i; + + run_with_memfd(test_case->fn, test_case->desc); + run_with_tmpfile(test_case->fn, test_case->desc); + run_with_local_tmpfile(test_case->fn, test_case->desc); + for (i = 0; i < nr_hugetlbsizes; i++) + run_with_memfd_hugetlb(test_case->fn, test_case->desc, + hugetlbsizes[i]); +} + +static int tests_per_test_case(void) +{ + return 3 + nr_hugetlbsizes; +} + +int main(int argc, char **argv) +{ + int i, err; + + pagesize = getpagesize(); + nr_hugetlbsizes = detect_hugetlb_page_sizes(hugetlbsizes, + ARRAY_SIZE(hugetlbsizes)); + + ksft_print_header(); + ksft_set_plan(ARRAY_SIZE(test_cases) * tests_per_test_case()); + + gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) + run_test_case(&test_cases[i]); + + err = ksft_get_fail_cnt(); + if (err) + ksft_exit_fail_msg("%d out of %d tests failed\n", + err, ksft_test_num()); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/mm/hugepage-shm.c b/tools/testing/selftests/mm/hugepage-shm.c index e2527f32005b3..478bb1e989e9f 100644 --- a/tools/testing/selftests/mm/hugepage-shm.c +++ b/tools/testing/selftests/mm/hugepage-shm.c @@ -35,10 +35,6 @@ #include <sys/shm.h> #include <sys/mman.h> -#ifndef SHM_HUGETLB -#define SHM_HUGETLB 04000 -#endif - #define LENGTH (256UL*1024*1024) #define dprintf(x) printf(x) diff --git a/tools/testing/selftests/mm/hugepage-vmemmap.c b/tools/testing/selftests/mm/hugepage-vmemmap.c index 557bdbd4f87e8..5b354c209e936 100644 --- a/tools/testing/selftests/mm/hugepage-vmemmap.c +++ b/tools/testing/selftests/mm/hugepage-vmemmap.c @@ -13,10 +13,6 @@ #define MAP_LENGTH (2UL * 1024 * 1024) -#ifndef MAP_HUGETLB -#define MAP_HUGETLB 0x40000 /* arch specific */ -#endif - #define PAGE_SIZE 4096 #define PAGE_COMPOUND_HEAD (1UL << 15) diff --git a/tools/testing/selftests/mm/hugetlb-madvise.c b/tools/testing/selftests/mm/hugetlb-madvise.c index 28426e30d9bc2..d55322df4b736 100644 --- a/tools/testing/selftests/mm/hugetlb-madvise.c +++ b/tools/testing/selftests/mm/hugetlb-madvise.c @@ -65,11 +65,15 @@ void write_fault_pages(void *addr, unsigned long nr_pages) void read_fault_pages(void *addr, unsigned long nr_pages) { - unsigned long dummy = 0; + volatile unsigned long dummy = 0; unsigned long i; - for (i = 0; i < nr_pages; i++) + for (i = 0; i < nr_pages; i++) { dummy += *((unsigned long *)(addr + (i * huge_page_size))); + + /* Prevent the compiler from optimizing out the entire loop: */ + asm volatile("" : "+r" (dummy)); + } } int main(int argc, char **argv) diff --git a/tools/testing/selftests/mm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c index 97adc0f34f9c0..030667cb55337 100644 --- a/tools/testing/selftests/mm/khugepaged.c +++ b/tools/testing/selftests/mm/khugepaged.c @@ -11,6 +11,7 @@ #include <string.h> #include <unistd.h> +#include <linux/mman.h> #include <sys/mman.h> #include <sys/wait.h> #include <sys/types.h> @@ -22,16 +23,6 @@ #include "vm_util.h" -#ifndef MADV_PAGEOUT -#define MADV_PAGEOUT 21 -#endif -#ifndef MADV_POPULATE_READ -#define MADV_POPULATE_READ 22 -#endif -#ifndef MADV_COLLAPSE -#define MADV_COLLAPSE 25 -#endif - #define BASE_ADDR ((void *)(1UL << 30)) static unsigned long hpage_pmd_size; static unsigned long page_size; diff --git a/tools/testing/selftests/mm/madv_populate.c b/tools/testing/selftests/mm/madv_populate.c index 262eae6b58f23..60547245e479b 100644 --- a/tools/testing/selftests/mm/madv_populate.c +++ b/tools/testing/selftests/mm/madv_populate.c @@ -20,13 +20,6 @@ #include "../kselftest.h" #include "vm_util.h" -#ifndef MADV_POPULATE_READ -#define MADV_POPULATE_READ 22 -#endif /* MADV_POPULATE_READ */ -#ifndef MADV_POPULATE_WRITE -#define MADV_POPULATE_WRITE 23 -#endif /* MADV_POPULATE_WRITE */ - /* * For now, we're using 2 MiB of private anonymous memory for all tests. */ diff --git a/tools/testing/selftests/mm/map_fixed_noreplace.c b/tools/testing/selftests/mm/map_fixed_noreplace.c index eed44322d1a63..598159f3df1f2 100644 --- a/tools/testing/selftests/mm/map_fixed_noreplace.c +++ b/tools/testing/selftests/mm/map_fixed_noreplace.c @@ -13,10 +13,6 @@ #include <stdlib.h> #include <unistd.h> -#ifndef MAP_FIXED_NOREPLACE -#define MAP_FIXED_NOREPLACE 0x100000 -#endif - static void dump_maps(void) { char cmd[32]; diff --git a/tools/testing/selftests/mm/map_hugetlb.c b/tools/testing/selftests/mm/map_hugetlb.c index 312889edb84ab..193281560b61b 100644 --- a/tools/testing/selftests/mm/map_hugetlb.c +++ b/tools/testing/selftests/mm/map_hugetlb.c @@ -19,18 +19,6 @@ #define LENGTH (256UL*1024*1024) #define PROTECTION (PROT_READ | PROT_WRITE) -#ifndef MAP_HUGETLB -#define MAP_HUGETLB 0x40000 /* arch specific */ -#endif - -#ifndef MAP_HUGE_SHIFT -#define MAP_HUGE_SHIFT 26 -#endif - -#ifndef MAP_HUGE_MASK -#define MAP_HUGE_MASK 0x3f -#endif - /* Only ia64 requires this */ #ifdef __ia64__ #define ADDR (void *)(0x8000000000000000UL) diff --git a/tools/testing/selftests/mm/map_populate.c b/tools/testing/selftests/mm/map_populate.c index 6b8aeaa0bf7a5..240f2d9dae7a9 100644 --- a/tools/testing/selftests/mm/map_populate.c +++ b/tools/testing/selftests/mm/map_populate.c @@ -17,9 +17,7 @@ #include <string.h> #include <unistd.h> -#ifndef MMAP_SZ #define MMAP_SZ 4096 -#endif #define BUG_ON(condition, description) \ do { \ diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c index 1cec8425e3caa..379581567f272 100644 --- a/tools/testing/selftests/mm/migration.c +++ b/tools/testing/selftests/mm/migration.c @@ -95,12 +95,15 @@ int migrate(uint64_t *ptr, int n1, int n2) void *access_mem(void *ptr) { - uint64_t y = 0; + volatile uint64_t y = 0; volatile uint64_t *x = ptr; while (1) { pthread_testcancel(); y += *x; + + /* Prevent the compiler from optimizing out the writes to y: */ + asm volatile("" : "+r" (y)); } return NULL; diff --git a/tools/testing/selftests/mm/mlock-random-test.c b/tools/testing/selftests/mm/mlock-random-test.c index 782ea94dee2f2..1fba77df7f628 100644 --- a/tools/testing/selftests/mm/mlock-random-test.c +++ b/tools/testing/selftests/mm/mlock-random-test.c @@ -7,6 +7,7 @@ #include <sys/resource.h> #include <sys/capability.h> #include <sys/mman.h> +#include <linux/mman.h> #include <fcntl.h> #include <string.h> #include <sys/ipc.h> diff --git a/tools/testing/selftests/mm/mlock2-tests.c b/tools/testing/selftests/mm/mlock2-tests.c index 11b2301f3aa37..80cddc0de2061 100644 --- a/tools/testing/selftests/mm/mlock2-tests.c +++ b/tools/testing/selftests/mm/mlock2-tests.c @@ -50,7 +50,6 @@ static int get_vm_area(unsigned long addr, struct vm_boundaries *area) printf("cannot parse /proc/self/maps\n"); goto out; } - stop = '\0'; sscanf(line, "%lx", &start); sscanf(end_addr, "%lx", &end); diff --git a/tools/testing/selftests/mm/mlock2.h b/tools/testing/selftests/mm/mlock2.h index 2a6e76c226bc3..8e02991b313c8 100644 --- a/tools/testing/selftests/mm/mlock2.h +++ b/tools/testing/selftests/mm/mlock2.h @@ -4,14 +4,6 @@ #include <stdio.h> #include <stdlib.h> -#ifndef MLOCK_ONFAULT -#define MLOCK_ONFAULT 1 -#endif - -#ifndef MCL_ONFAULT -#define MCL_ONFAULT (MCL_FUTURE << 1) -#endif - static int mlock2_(void *start, size_t len, int flags) { #ifdef __NR_mlock2 diff --git a/tools/testing/selftests/mm/mrelease_test.c b/tools/testing/selftests/mm/mrelease_test.c index 37b6d33b9e845..dca21042b6792 100644 --- a/tools/testing/selftests/mm/mrelease_test.c +++ b/tools/testing/selftests/mm/mrelease_test.c @@ -9,18 +9,10 @@ #include <stdlib.h> #include <sys/wait.h> #include <unistd.h> +#include <asm-generic/unistd.h> #include "vm_util.h" - #include "../kselftest.h" -#ifndef __NR_pidfd_open -#define __NR_pidfd_open -1 -#endif - -#ifndef __NR_process_mrelease -#define __NR_process_mrelease -1 -#endif - #define MB(x) (x << 20) #define MAX_SIZE_MB 1024 diff --git a/tools/testing/selftests/mm/mremap_dontunmap.c b/tools/testing/selftests/mm/mremap_dontunmap.c index f01dc4a85b0be..ca2359835e751 100644 --- a/tools/testing/selftests/mm/mremap_dontunmap.c +++ b/tools/testing/selftests/mm/mremap_dontunmap.c @@ -15,10 +15,6 @@ #include "../kselftest.h" -#ifndef MREMAP_DONTUNMAP -#define MREMAP_DONTUNMAP 4 -#endif - unsigned long page_size; char *page_buffer; diff --git a/tools/testing/selftests/mm/on-fault-limit.c b/tools/testing/selftests/mm/on-fault-limit.c index 634d87dfb2a4e..b5888d613f34e 100644 --- a/tools/testing/selftests/mm/on-fault-limit.c +++ b/tools/testing/selftests/mm/on-fault-limit.c @@ -6,10 +6,6 @@ #include <sys/time.h> #include <sys/resource.h> -#ifndef MCL_ONFAULT -#define MCL_ONFAULT (MCL_FUTURE << 1) -#endif - static int test_limit(void) { int ret = 1; diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h index 1ebb586b2fbc2..ae5df26104e5f 100644 --- a/tools/testing/selftests/mm/pkey-powerpc.h +++ b/tools/testing/selftests/mm/pkey-powerpc.h @@ -3,9 +3,6 @@ #ifndef _PKEYS_POWERPC_H #define _PKEYS_POWERPC_H -#ifndef SYS_mprotect_key -# define SYS_mprotect_key 386 -#endif #ifndef SYS_pkey_alloc # define SYS_pkey_alloc 384 # define SYS_pkey_free 385 diff --git a/tools/testing/selftests/mm/pkey-x86.h b/tools/testing/selftests/mm/pkey-x86.h index 72c14cd3ddc74..814758e109c0b 100644 --- a/tools/testing/selftests/mm/pkey-x86.h +++ b/tools/testing/selftests/mm/pkey-x86.h @@ -5,29 +5,11 @@ #ifdef __i386__ -#ifndef SYS_mprotect_key -# define SYS_mprotect_key 380 -#endif - -#ifndef SYS_pkey_alloc -# define SYS_pkey_alloc 381 -# define SYS_pkey_free 382 -#endif - #define REG_IP_IDX REG_EIP #define si_pkey_offset 0x14 #else -#ifndef SYS_mprotect_key -# define SYS_mprotect_key 329 -#endif - -#ifndef SYS_pkey_alloc -# define SYS_pkey_alloc 330 -# define SYS_pkey_free 331 -#endif - #define REG_IP_IDX REG_RIP #define si_pkey_offset 0x20 @@ -132,7 +114,7 @@ int pkey_reg_xstate_offset(void) unsigned int ecx; unsigned int edx; int xstate_offset; - int xstate_size; + int xstate_size = 0; unsigned long XSTATE_CPUID = 0xd; int leaf; diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index 0381c34fdd565..48dc151f8fca8 100644 --- a/tools/testing/selftests/mm/protection_keys.c +++ b/tools/testing/selftests/mm/protection_keys.c @@ -294,15 +294,6 @@ void pkey_access_deny(int pkey) pkey_disable_set(pkey, PKEY_DISABLE_ACCESS); } -/* Failed address bound checks: */ -#ifndef SEGV_BNDERR -# define SEGV_BNDERR 3 -#endif - -#ifndef SEGV_PKUERR -# define SEGV_PKUERR 4 -#endif - static char *si_code_str(int si_code) { if (si_code == SEGV_MAPERR) @@ -476,7 +467,7 @@ int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, ptr, size, orig_prot, pkey); errno = 0; - sret = syscall(SYS_mprotect_key, ptr, size, orig_prot, pkey); + sret = syscall(__NR_pkey_mprotect, ptr, size, orig_prot, pkey); if (errno) { dprintf2("SYS_mprotect_key sret: %d\n", sret); dprintf2("SYS_mprotect_key prot: 0x%lx\n", orig_prot); @@ -1684,7 +1675,7 @@ void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) return; } - sret = syscall(SYS_mprotect_key, ptr, size, PROT_READ, pkey); + sret = syscall(__NR_pkey_mprotect, ptr, size, PROT_READ, pkey); pkey_assert(sret < 0); } diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 4893eb60d96d8..3f26f6e15b2a4 100644 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -24,7 +24,7 @@ separated by spaces: - mmap tests for mmap(2) - gup_test - tests for gup using gup_test interface + tests for gup - userfaultfd tests for userfaultfd(2) - compaction @@ -196,6 +196,8 @@ CATEGORY="gup_test" run_test ./gup_test -a # Dump pages 0, 19, and 4096, using pin_user_pages: CATEGORY="gup_test" run_test ./gup_test -ct -F 0x1 0 19 0x1000 +CATEGORY="gup_test" run_test ./gup_longterm + CATEGORY="userfaultfd" run_test ./uffd-unit-tests uffd_stress_bin=./uffd-stress CATEGORY="userfaultfd" run_test ${uffd_stress_bin} anon 20 16 @@ -242,18 +244,18 @@ if [ $VADDR64 -ne 0 ]; then if [ "$ARCH" == "$ARCH_ARM64" ]; then echo 6 > /proc/sys/vm/nr_hugepages fi - CATEGORY="hugevm" run_test ./va_high_addr_switch.sh + CATEGORY="hugevm" run_test bash ./va_high_addr_switch.sh if [ "$ARCH" == "$ARCH_ARM64" ]; then echo $prev_nr_hugepages > /proc/sys/vm/nr_hugepages fi fi # VADDR64 # vmalloc stability smoke test -CATEGORY="vmalloc" run_test ./test_vmalloc.sh smoke +CATEGORY="vmalloc" run_test bash ./test_vmalloc.sh smoke CATEGORY="mremap" run_test ./mremap_dontunmap -CATEGORY="hmm" run_test ./test_hmm.sh smoke +CATEGORY="hmm" run_test bash ./test_hmm.sh smoke # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index 61c6250adf93e..ba20d75040226 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -616,3 +616,62 @@ int copy_page(int ufd, unsigned long offset, bool wp) { return __copy_page(ufd, offset, false, wp); } + +int uffd_open_dev(unsigned int flags) +{ + int fd, uffd; + + fd = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC); + if (fd < 0) + return fd; + uffd = ioctl(fd, USERFAULTFD_IOC_NEW, flags); + close(fd); + + return uffd; +} + +int uffd_open_sys(unsigned int flags) +{ +#ifdef __NR_userfaultfd + return syscall(__NR_userfaultfd, flags); +#else + return -1; +#endif +} + +int uffd_open(unsigned int flags) +{ + int uffd = uffd_open_sys(flags); + + if (uffd < 0) + uffd = uffd_open_dev(flags); + + return uffd; +} + +int uffd_get_features(uint64_t *features) +{ + struct uffdio_api uffdio_api = { .api = UFFD_API, .features = 0 }; + /* + * This should by default work in most kernels; the feature list + * will be the same no matter what we pass in here. + */ + int fd = uffd_open(UFFD_USER_MODE_ONLY); + + if (fd < 0) + /* Maybe the kernel is older than user-only mode? */ + fd = uffd_open(0); + + if (fd < 0) + return fd; + + if (ioctl(fd, UFFDIO_API, &uffdio_api)) { + close(fd); + return -errno; + } + + *features = uffdio_api.features; + close(fd); + + return 0; +} diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index 6068f2346b860..197f5262fe0d1 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -110,6 +110,11 @@ int __copy_page(int ufd, unsigned long offset, bool retry, bool wp); int copy_page(int ufd, unsigned long offset, bool wp); void *uffd_poll_thread(void *arg); +int uffd_open_dev(unsigned int flags); +int uffd_open_sys(unsigned int flags); +int uffd_open(unsigned int flags); +int uffd_get_features(uint64_t *features); + #define TEST_ANON 1 #define TEST_HUGETLB 2 #define TEST_SHMEM 3 diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index f1ad9eef1c3ad..995ff13e74c78 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -88,16 +88,6 @@ static void uffd_stats_reset(struct uffd_args *args, unsigned long n_cpus) } } -static inline uint64_t uffd_minor_feature(void) -{ - if (test_type == TEST_HUGETLB && map_shared) - return UFFD_FEATURE_MINOR_HUGETLBFS; - else if (test_type == TEST_SHMEM) - return UFFD_FEATURE_MINOR_SHMEM; - else - return 0; -} - static void *locking_thread(void *arg) { unsigned long cpu = (unsigned long) arg; diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 269c86768a024..04d91f144d1cb 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -109,12 +109,11 @@ static void uffd_test_pass(void) ksft_inc_fail_cnt(); \ } while (0) -#define uffd_test_skip(...) do { \ - printf("skipped [reason: "); \ - printf(__VA_ARGS__); \ - printf("]\n"); \ - ksft_inc_xskip_cnt(); \ - } while (0) +static void uffd_test_skip(const char *message) +{ + printf("skipped [reason: %s]\n", message); + ksft_inc_xskip_cnt(); +} /* * Returns 1 if specific userfaultfd supported, 0 otherwise. Note, we'll @@ -1149,7 +1148,6 @@ int main(int argc, char *argv[]) uffd_test_case_t *test; mem_type_t *mem_type; uffd_test_args_t args; - char test_name[128]; const char *errmsg; int has_uffd, opt; int i, j; @@ -1192,10 +1190,8 @@ int main(int argc, char *argv[]) mem_type = &mem_types[j]; if (!(test->mem_targets & mem_type->mem_flag)) continue; - snprintf(test_name, sizeof(test_name), - "%s on %s", test->name, mem_type->name); - uffd_test_start(test_name); + uffd_test_start("%s on %s", test->name, mem_type->name); if (!uffd_feature_supported(test)) { uffd_test_skip("feature missing"); continue; diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 9b06a5034808b..558c9cd8901c5 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <string.h> #include <fcntl.h> +#include <dirent.h> #include <sys/ioctl.h> #include <linux/userfaultfd.h> #include <sys/syscall.h> @@ -198,6 +199,32 @@ unsigned long default_huge_page_size(void) return hps; } +int detect_hugetlb_page_sizes(size_t sizes[], int max) +{ + DIR *dir = opendir("/sys/kernel/mm/hugepages/"); + int count = 0; + + if (!dir) + return 0; + + while (count < max) { + struct dirent *entry = readdir(dir); + size_t kb; + + if (!entry) + break; + if (entry->d_type != DT_DIR) + continue; + if (sscanf(entry->d_name, "hugepages-%zukB", &kb) != 1) + continue; + sizes[count++] = kb * 1024; + ksft_print_msg("[INFO] detected hugetlb page size: %zu KiB\n", + kb); + } + closedir(dir); + return count; +} + /* If `ioctls' non-NULL, the allowed ioctls will be returned into the var */ int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor, uint64_t *ioctls) @@ -242,62 +269,3 @@ int uffd_unregister(int uffd, void *addr, uint64_t len) return ret; } - -int uffd_open_dev(unsigned int flags) -{ - int fd, uffd; - - fd = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC); - if (fd < 0) - return fd; - uffd = ioctl(fd, USERFAULTFD_IOC_NEW, flags); - close(fd); - - return uffd; -} - -int uffd_open_sys(unsigned int flags) -{ -#ifdef __NR_userfaultfd - return syscall(__NR_userfaultfd, flags); -#else - return -1; -#endif -} - -int uffd_open(unsigned int flags) -{ - int uffd = uffd_open_sys(flags); - - if (uffd < 0) - uffd = uffd_open_dev(flags); - - return uffd; -} - -int uffd_get_features(uint64_t *features) -{ - struct uffdio_api uffdio_api = { .api = UFFD_API, .features = 0 }; - /* - * This should by default work in most kernels; the feature list - * will be the same no matter what we pass in here. - */ - int fd = uffd_open(UFFD_USER_MODE_ONLY); - - if (fd < 0) - /* Maybe the kernel is older than user-only mode? */ - fd = uffd_open(0); - - if (fd < 0) - return fd; - - if (ioctl(fd, UFFDIO_API, &uffdio_api)) { - close(fd); - return -errno; - } - - *features = uffdio_api.features; - close(fd); - - return 0; -} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index b950bd16083ac..c7fa61f0dff8d 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -44,14 +44,11 @@ bool check_huge_file(void *addr, int nr_hpages, uint64_t hpage_size); bool check_huge_shmem(void *addr, int nr_hpages, uint64_t hpage_size); int64_t allocate_transhuge(void *ptr, int pagemap_fd); unsigned long default_huge_page_size(void); +int detect_hugetlb_page_sizes(size_t sizes[], int max); int uffd_register(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor); int uffd_unregister(int uffd, void *addr, uint64_t len); -int uffd_open_dev(unsigned int flags); -int uffd_open_sys(unsigned int flags); -int uffd_open(unsigned int flags); -int uffd_get_features(uint64_t *features); int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor, uint64_t *ioctls); diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 80f06aa620345..501854a89cc01 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -8,8 +8,10 @@ diag_uid fin_ack_lat gro hwtstamp_config +io_uring_zerocopy_tx ioam6_parser ip_defrag +ip_local_port_range ipsec ipv6_flowlabel ipv6_flowlabel_mgr @@ -26,6 +28,8 @@ reuseport_bpf_cpu reuseport_bpf_numa reuseport_dualstack rxtimestamp +sctp_hello +scm_pidfd sk_bind_sendto_listen sk_connect_zero_addr socket diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index c12df57d55396..7f3ab2a93ed61 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -84,6 +84,7 @@ TEST_GEN_FILES += ip_local_port_range TEST_GEN_FILES += bind_wildcard TEST_PROGS += test_vxlan_mdb.sh TEST_PROGS += test_bridge_neigh_suppress.sh +TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_FILES := settings diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 1e4b397cece66..221c387a7d7f6 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,3 +1,4 @@ -TEST_GEN_PROGS := diag_uid test_unix_oob unix_connect +CFLAGS += $(KHDR_INCLUDES) +TEST_GEN_PROGS := diag_uid test_unix_oob unix_connect scm_pidfd include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c new file mode 100644 index 0000000000000..a86222143d792 --- /dev/null +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -0,0 +1,430 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +#define _GNU_SOURCE +#include <error.h> +#include <limits.h> +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/socket.h> +#include <linux/socket.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> +#include <sys/un.h> +#include <sys/signal.h> +#include <sys/types.h> +#include <sys/wait.h> + +#include "../../kselftest_harness.h" + +#define clean_errno() (errno == 0 ? "None" : strerror(errno)) +#define log_err(MSG, ...) \ + fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", __FILE__, __LINE__, \ + clean_errno(), ##__VA_ARGS__) + +#ifndef SCM_PIDFD +#define SCM_PIDFD 0x04 +#endif + +static void child_die() +{ + exit(1); +} + +static int safe_int(const char *numstr, int *converted) +{ + char *err = NULL; + long sli; + + errno = 0; + sli = strtol(numstr, &err, 0); + if (errno == ERANGE && (sli == LONG_MAX || sli == LONG_MIN)) + return -ERANGE; + + if (errno != 0 && sli == 0) + return -EINVAL; + + if (err == numstr || *err != '\0') + return -EINVAL; + + if (sli > INT_MAX || sli < INT_MIN) + return -ERANGE; + + *converted = (int)sli; + return 0; +} + +static int char_left_gc(const char *buffer, size_t len) +{ + size_t i; + + for (i = 0; i < len; i++) { + if (buffer[i] == ' ' || buffer[i] == '\t') + continue; + + return i; + } + + return 0; +} + +static int char_right_gc(const char *buffer, size_t len) +{ + int i; + + for (i = len - 1; i >= 0; i--) { + if (buffer[i] == ' ' || buffer[i] == '\t' || + buffer[i] == '\n' || buffer[i] == '\0') + continue; + + return i + 1; + } + + return 0; +} + +static char *trim_whitespace_in_place(char *buffer) +{ + buffer += char_left_gc(buffer, strlen(buffer)); + buffer[char_right_gc(buffer, strlen(buffer))] = '\0'; + return buffer; +} + +/* borrowed (with all helpers) from pidfd/pidfd_open_test.c */ +static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen) +{ + int ret; + char path[512]; + FILE *f; + size_t n = 0; + pid_t result = -1; + char *line = NULL; + + snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", pidfd); + + f = fopen(path, "re"); + if (!f) + return -1; + + while (getline(&line, &n, f) != -1) { + char *numstr; + + if (strncmp(line, key, keylen)) + continue; + + numstr = trim_whitespace_in_place(line + 4); + ret = safe_int(numstr, &result); + if (ret < 0) + goto out; + + break; + } + +out: + free(line); + fclose(f); + return result; +} + +static int cmsg_check(int fd) +{ + struct msghdr msg = { 0 }; + struct cmsghdr *cmsg; + struct iovec iov; + struct ucred *ucred = NULL; + int data = 0; + char control[CMSG_SPACE(sizeof(struct ucred)) + + CMSG_SPACE(sizeof(int))] = { 0 }; + int *pidfd = NULL; + pid_t parent_pid; + int err; + + iov.iov_base = &data; + iov.iov_len = sizeof(data); + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + err = recvmsg(fd, &msg, 0); + if (err < 0) { + log_err("recvmsg"); + return 1; + } + + if (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) { + log_err("recvmsg: truncated"); + return 1; + } + + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL; + cmsg = CMSG_NXTHDR(&msg, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_PIDFD) { + if (cmsg->cmsg_len < sizeof(*pidfd)) { + log_err("CMSG parse: SCM_PIDFD wrong len"); + return 1; + } + + pidfd = (void *)CMSG_DATA(cmsg); + } + + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_CREDENTIALS) { + if (cmsg->cmsg_len < sizeof(*ucred)) { + log_err("CMSG parse: SCM_CREDENTIALS wrong len"); + return 1; + } + + ucred = (void *)CMSG_DATA(cmsg); + } + } + + /* send(pfd, "x", sizeof(char), 0) */ + if (data != 'x') { + log_err("recvmsg: data corruption"); + return 1; + } + + if (!pidfd) { + log_err("CMSG parse: SCM_PIDFD not found"); + return 1; + } + + if (!ucred) { + log_err("CMSG parse: SCM_CREDENTIALS not found"); + return 1; + } + + /* pidfd from SCM_PIDFD should point to the parent process PID */ + parent_pid = + get_pid_from_fdinfo_file(*pidfd, "Pid:", sizeof("Pid:") - 1); + if (parent_pid != getppid()) { + log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid()); + return 1; + } + + return 0; +} + +struct sock_addr { + char sock_name[32]; + struct sockaddr_un listen_addr; + socklen_t addrlen; +}; + +FIXTURE(scm_pidfd) +{ + int server; + pid_t client_pid; + int startup_pipe[2]; + struct sock_addr server_addr; + struct sock_addr *client_addr; +}; + +FIXTURE_VARIANT(scm_pidfd) +{ + int type; + bool abstract; +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, stream_pathname) +{ + .type = SOCK_STREAM, + .abstract = 0, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, stream_abstract) +{ + .type = SOCK_STREAM, + .abstract = 1, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, dgram_pathname) +{ + .type = SOCK_DGRAM, + .abstract = 0, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, dgram_abstract) +{ + .type = SOCK_DGRAM, + .abstract = 1, +}; + +FIXTURE_SETUP(scm_pidfd) +{ + self->client_addr = mmap(NULL, sizeof(*self->client_addr), PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(MAP_FAILED, self->client_addr); +} + +FIXTURE_TEARDOWN(scm_pidfd) +{ + close(self->server); + + kill(self->client_pid, SIGKILL); + waitpid(self->client_pid, NULL, 0); + + if (!variant->abstract) { + unlink(self->server_addr.sock_name); + unlink(self->client_addr->sock_name); + } +} + +static void fill_sockaddr(struct sock_addr *addr, bool abstract) +{ + char *sun_path_buf = (char *)&addr->listen_addr.sun_path; + + addr->listen_addr.sun_family = AF_UNIX; + addr->addrlen = offsetof(struct sockaddr_un, sun_path); + snprintf(addr->sock_name, sizeof(addr->sock_name), "scm_pidfd_%d", getpid()); + addr->addrlen += strlen(addr->sock_name); + if (abstract) { + *sun_path_buf = '\0'; + addr->addrlen++; + sun_path_buf++; + } else { + unlink(addr->sock_name); + } + memcpy(sun_path_buf, addr->sock_name, strlen(addr->sock_name)); +} + +static void client(FIXTURE_DATA(scm_pidfd) *self, + const FIXTURE_VARIANT(scm_pidfd) *variant) +{ + int err; + int cfd; + socklen_t len; + struct ucred peer_cred; + int peer_pidfd; + pid_t peer_pid; + int on = 0; + + cfd = socket(AF_UNIX, variant->type, 0); + if (cfd < 0) { + log_err("socket"); + child_die(); + } + + if (variant->type == SOCK_DGRAM) { + fill_sockaddr(self->client_addr, variant->abstract); + + if (bind(cfd, (struct sockaddr *)&self->client_addr->listen_addr, self->client_addr->addrlen)) { + log_err("bind"); + child_die(); + } + } + + if (connect(cfd, (struct sockaddr *)&self->server_addr.listen_addr, + self->server_addr.addrlen) != 0) { + log_err("connect"); + child_die(); + } + + on = 1; + if (setsockopt(cfd, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) { + log_err("Failed to set SO_PASSCRED"); + child_die(); + } + + if (setsockopt(cfd, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) { + log_err("Failed to set SO_PASSPIDFD"); + child_die(); + } + + close(self->startup_pipe[1]); + + if (cmsg_check(cfd)) { + log_err("cmsg_check failed"); + child_die(); + } + + /* skip further for SOCK_DGRAM as it's not applicable */ + if (variant->type == SOCK_DGRAM) + return; + + len = sizeof(peer_cred); + if (getsockopt(cfd, SOL_SOCKET, SO_PEERCRED, &peer_cred, &len)) { + log_err("Failed to get SO_PEERCRED"); + child_die(); + } + + len = sizeof(peer_pidfd); + if (getsockopt(cfd, SOL_SOCKET, SO_PEERPIDFD, &peer_pidfd, &len)) { + log_err("Failed to get SO_PEERPIDFD"); + child_die(); + } + + /* pid from SO_PEERCRED should point to the parent process PID */ + if (peer_cred.pid != getppid()) { + log_err("peer_cred.pid != getppid(): %d != %d", peer_cred.pid, getppid()); + child_die(); + } + + peer_pid = get_pid_from_fdinfo_file(peer_pidfd, + "Pid:", sizeof("Pid:") - 1); + if (peer_pid != peer_cred.pid) { + log_err("peer_pid != peer_cred.pid: %d != %d", peer_pid, peer_cred.pid); + child_die(); + } +} + +TEST_F(scm_pidfd, test) +{ + int err; + int pfd; + int child_status = 0; + + self->server = socket(AF_UNIX, variant->type, 0); + ASSERT_NE(-1, self->server); + + fill_sockaddr(&self->server_addr, variant->abstract); + + err = bind(self->server, (struct sockaddr *)&self->server_addr.listen_addr, self->server_addr.addrlen); + ASSERT_EQ(0, err); + + if (variant->type == SOCK_STREAM) { + err = listen(self->server, 1); + ASSERT_EQ(0, err); + } + + err = pipe(self->startup_pipe); + ASSERT_NE(-1, err); + + self->client_pid = fork(); + ASSERT_NE(-1, self->client_pid); + if (self->client_pid == 0) { + close(self->server); + close(self->startup_pipe[0]); + client(self, variant); + exit(0); + } + close(self->startup_pipe[1]); + + if (variant->type == SOCK_STREAM) { + pfd = accept(self->server, NULL, NULL); + ASSERT_NE(-1, pfd); + } else { + pfd = self->server; + } + + /* wait until the child arrives at checkpoint */ + read(self->startup_pipe[0], &err, sizeof(int)); + close(self->startup_pipe[0]); + + if (variant->type == SOCK_DGRAM) { + err = sendto(pfd, "x", sizeof(char), 0, (struct sockaddr *)&self->client_addr->listen_addr, self->client_addr->addrlen); + ASSERT_NE(-1, err); + } else { + err = send(pfd, "x", sizeof(char), 0); + ASSERT_NE(-1, err); + } + + close(pfd); + waitpid(self->client_pid, &child_status, 0); + ASSERT_EQ(0, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 21ca91473c095..d32a14ba069ac 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -92,6 +92,13 @@ NSC_CMD="ip netns exec ${NSC}" which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) +# Check if FIPS mode is enabled +if [ -f /proc/sys/crypto/fips_enabled ]; then + fips_enabled=`cat /proc/sys/crypto/fips_enabled` +else + fips_enabled=0 +fi + ################################################################################ # utilities @@ -585,6 +592,20 @@ ipv4_ping_novrf() done # + # out, but don't use gateway if peer is not on link + # + a=${NSB_IP} + log_start + run_cmd ping -c 1 -w 1 -r ${a} + log_test_addr ${a} $? 0 "ping out (don't route), peer on link" + + a=${NSB_LO_IP} + log_start + show_hint "Fails since peer is not on link" + run_cmd ping -c 1 -w 1 -r ${a} + log_test_addr ${a} $? 1 "ping out (don't route), peer not on link" + + # # in # for a in ${NSA_IP} ${NSA_LO_IP} @@ -1098,6 +1119,59 @@ test_ipv4_md5_vrf__global_server__bind_ifindex0() set_sysctl net.ipv4.tcp_l3mdev_accept="$old_tcp_l3mdev_accept" } +ipv4_tcp_dontroute() +{ + local syncookies=$1 + local nsa_syncookies + local nsb_syncookies + local a + + # + # Link local connection tests (SO_DONTROUTE). + # Connections should succeed only when the remote IP address is + # on link (doesn't need to be routed through a gateway). + # + + nsa_syncookies=$(ip netns exec "${NSA}" sysctl -n net.ipv4.tcp_syncookies) + nsb_syncookies=$(ip netns exec "${NSB}" sysctl -n net.ipv4.tcp_syncookies) + ip netns exec "${NSA}" sysctl -wq net.ipv4.tcp_syncookies=${syncookies} + ip netns exec "${NSB}" sysctl -wq net.ipv4.tcp_syncookies=${syncookies} + + # Test with eth1 address (on link). + + a=${NSB_IP} + log_start + do_run_cmd nettest -B -N "${NSA}" -O "${NSB}" -r ${a} --client-dontroute + log_test_addr ${a} $? 0 "SO_DONTROUTE client, syncookies=${syncookies}" + + a=${NSB_IP} + log_start + do_run_cmd nettest -B -N "${NSA}" -O "${NSB}" -r ${a} --server-dontroute + log_test_addr ${a} $? 0 "SO_DONTROUTE server, syncookies=${syncookies}" + + # Test with loopback address (routed). + # + # The client would use the eth1 address as source IP by default. + # Therefore, we need to use the -c option here, to force the use of the + # routed (loopback) address as source IP (so that the server will try + # to respond to a routed address and not a link local one). + + a=${NSB_LO_IP} + log_start + show_hint "Should fail 'Network is unreachable' since server is not on link" + do_run_cmd nettest -B -N "${NSA}" -O "${NSB}" -c "${NSA_LO_IP}" -r ${a} --client-dontroute + log_test_addr ${a} $? 1 "SO_DONTROUTE client, syncookies=${syncookies}" + + a=${NSB_LO_IP} + log_start + show_hint "Should timeout since server cannot respond (client is not on link)" + do_run_cmd nettest -B -N "${NSA}" -O "${NSB}" -c "${NSA_LO_IP}" -r ${a} --server-dontroute + log_test_addr ${a} $? 2 "SO_DONTROUTE server, syncookies=${syncookies}" + + ip netns exec "${NSB}" sysctl -wq net.ipv4.tcp_syncookies=${nsb_syncookies} + ip netns exec "${NSA}" sysctl -wq net.ipv4.tcp_syncookies=${nsa_syncookies} +} + ipv4_tcp_novrf() { local a @@ -1216,7 +1290,10 @@ ipv4_tcp_novrf() run_cmd nettest -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 1 "No server, device client, local conn" - ipv4_tcp_md5_novrf + [ "$fips_enabled" = "1" ] || ipv4_tcp_md5_novrf + + ipv4_tcp_dontroute 0 + ipv4_tcp_dontroute 2 } ipv4_tcp_vrf() @@ -1270,9 +1347,11 @@ ipv4_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection" # run MD5 tests - setup_vrf_dup - ipv4_tcp_md5 - cleanup_vrf_dup + if [ "$fips_enabled" = "0" ]; then + setup_vrf_dup + ipv4_tcp_md5 + cleanup_vrf_dup + fi # # enable VRF global server @@ -1585,6 +1664,23 @@ ipv4_udp_novrf() log_start run_cmd nettest -D -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 2 "No server, device client, local conn" + + # + # Link local connection tests (SO_DONTROUTE). + # Connections should succeed only when the remote IP address is + # on link (doesn't need to be routed through a gateway). + # + + a=${NSB_IP} + log_start + do_run_cmd nettest -B -D -N "${NSA}" -O "${NSB}" -r ${a} --client-dontroute + log_test_addr ${a} $? 0 "SO_DONTROUTE client" + + a=${NSB_LO_IP} + log_start + show_hint "Should fail 'Network is unreachable' since server is not on link" + do_run_cmd nettest -B -D -N "${NSA}" -O "${NSB}" -r ${a} --client-dontroute + log_test_addr ${a} $? 1 "SO_DONTROUTE client" } ipv4_udp_vrf() @@ -2772,7 +2868,7 @@ ipv6_tcp_novrf() log_test_addr ${a} $? 1 "No server, device client, local conn" done - ipv6_tcp_md5_novrf + [ "$fips_enabled" = "1" ] || ipv6_tcp_md5_novrf } ipv6_tcp_vrf() @@ -2842,9 +2938,11 @@ ipv6_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection" # run MD5 tests - setup_vrf_dup - ipv6_tcp_md5 - cleanup_vrf_dup + if [ "$fips_enabled" = "0" ]; then + setup_vrf_dup + ipv6_tcp_md5 + cleanup_vrf_dup + fi # # enable VRF global server diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index a47b26ab48f23..0f5e88c8f4ffe 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -2283,7 +2283,7 @@ EOF ################################################################################ # main -while getopts :t:pP46hv:w: o +while getopts :t:pP46hvw: o do case $o in t) TESTS=$OPTARG;; diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 7da8ec838c63a..35d89dfa6f11b 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -68,7 +68,7 @@ setup() cleanup() { $IP link del dev dummy0 &> /dev/null - ip netns del ns1 + ip netns del ns1 &> /dev/null ip netns del ns2 &> /dev/null } diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index a474c60fe3488..770efbe24f0d0 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -83,6 +83,8 @@ TEST_PROGS = bridge_igmp.sh \ tc_chains.sh \ tc_flower_router.sh \ tc_flower.sh \ + tc_flower_l2_miss.sh \ + tc_flower_cfm.sh \ tc_mpls_l2vpn.sh \ tc_police.sh \ tc_shblocks.sh \ diff --git a/tools/testing/selftests/net/forwarding/dual_vxlan_bridge.sh b/tools/testing/selftests/net/forwarding/dual_vxlan_bridge.sh index 5148d97a5df85..68ee92df3e07f 100755 --- a/tools/testing/selftests/net/forwarding/dual_vxlan_bridge.sh +++ b/tools/testing/selftests/net/forwarding/dual_vxlan_bridge.sh @@ -132,6 +132,7 @@ switch_create() #### BR1 #### ip link add name br1 type bridge vlan_filtering 1 \ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br1 addrgenmode none # Make sure the bridge uses the MAC address of the local port and not # that of the VxLAN's device. ip link set dev br1 address $(mac_get $swp1) diff --git a/tools/testing/selftests/net/forwarding/hw_stats_l3.sh b/tools/testing/selftests/net/forwarding/hw_stats_l3.sh index 432fe84698519..48584a51388fd 100755 --- a/tools/testing/selftests/net/forwarding/hw_stats_l3.sh +++ b/tools/testing/selftests/net/forwarding/hw_stats_l3.sh @@ -84,8 +84,9 @@ h2_destroy() router_rp1_200_create() { - ip link add name $rp1.200 up \ - link $rp1 addrgenmode eui64 type vlan id 200 + ip link add name $rp1.200 link $rp1 type vlan id 200 + ip link set dev $rp1.200 addrgenmode eui64 + ip link set dev $rp1.200 up ip address add dev $rp1.200 192.0.2.2/28 ip address add dev $rp1.200 2001:db8:1::2/64 ip stats set dev $rp1.200 l3_stats on @@ -256,9 +257,11 @@ reapply_config() router_rp1_200_destroy - ip link add name $rp1.200 link $rp1 addrgenmode none type vlan id 200 + ip link add name $rp1.200 link $rp1 type vlan id 200 + ip link set dev $rp1.200 addrgenmode none ip stats set dev $rp1.200 l3_stats on - ip link set dev $rp1.200 up addrgenmode eui64 + ip link set dev $rp1.200 addrgenmode eui64 + ip link set dev $rp1.200 up ip address add dev $rp1.200 192.0.2.2/28 ip address add dev $rp1.200 2001:db8:1::2/64 } diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh index 360ca133bead6..6c257ec03756f 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh @@ -98,6 +98,7 @@ switch_create() # Bridge between H1 and H2. ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 addrgenmode none ip link set dev br1 up ip link set dev $swp1 master br1 diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh index c5095da7f6bf8..04fd14b0a9b79 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh @@ -65,7 +65,8 @@ setup_prepare() vrf_prepare mirror_gre_topo_create - ip link add name br2 type bridge vlan_filtering 0 + ip link add name br2 address $(mac_get $swp3) \ + type bridge vlan_filtering 0 ip link set dev br2 up ip link set dev $swp3 master br2 @@ -93,12 +94,16 @@ cleanup() test_gretap() { + ip neigh replace 192.0.2.130 lladdr $(mac_get $h3) \ + nud permanent dev br2 full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap" full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap" } test_ip6gretap() { + ip neigh replace 2001:db8:2::2 lladdr $(mac_get $h3) \ + nud permanent dev br2 full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap" full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap" } diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh index 1b27f2b0f1960..f35313c76facd 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh @@ -35,7 +35,8 @@ setup_prepare() vrf_prepare mirror_gre_topo_create - ip link add name br2 type bridge vlan_filtering 0 + ip link add name br2 address $(mac_get $swp3) \ + type bridge vlan_filtering 0 ip link set dev br2 up vlan_create $swp3 555 diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh index 9ff22f28032dd..0cf4c47a46f9b 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh @@ -90,12 +90,16 @@ cleanup() test_gretap() { + ip neigh replace 192.0.2.130 lladdr $(mac_get $h3) \ + nud permanent dev br1 full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap" full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap" } test_ip6gretap() { + ip neigh replace 2001:db8:2::2 lladdr $(mac_get $h3) \ + nud permanent dev br1 full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap" full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap" } diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh index 91e431cd919e5..c53148b1dc636 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh @@ -140,7 +140,8 @@ switch_create() ip link set dev $swp3 up ip link set dev $swp4 up - ip link add name br1 type bridge vlan_filtering 1 + ip link add name br1 address $(mac_get $swp3) \ + type bridge vlan_filtering 1 team_create lag loadbalance $swp3 $swp4 ip link set dev lag master br1 diff --git a/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh b/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh index 04979e5962e7f..bb1adbb7b98a4 100644 --- a/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh +++ b/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh @@ -60,6 +60,7 @@ mirror_topo_switch_create() ip link set dev $swp3 up ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 addrgenmode none ip link set dev br1 up ip link set dev $swp1 master br1 diff --git a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh index 64fbd211d907b..af008fbf2725e 100755 --- a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh +++ b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh @@ -60,7 +60,9 @@ h2_destroy() switch_create() { - ip link add name br1 up type bridge vlan_filtering 1 + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 addrgenmode none + ip link set dev br1 up ip link set dev $swp1 master br1 ip link set dev $swp1 up ip link set dev $swp2 master br1 diff --git a/tools/testing/selftests/net/forwarding/q_in_vni.sh b/tools/testing/selftests/net/forwarding/q_in_vni.sh index 4c50c0234bce7..798b13525c028 100755 --- a/tools/testing/selftests/net/forwarding/q_in_vni.sh +++ b/tools/testing/selftests/net/forwarding/q_in_vni.sh @@ -137,6 +137,7 @@ switch_create() { ip link add name br1 type bridge vlan_filtering 1 vlan_protocol 802.1ad \ vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br1 addrgenmode none # Make sure the bridge uses the MAC address of the local port and not # that of the VxLAN's device. ip link set dev br1 address $(mac_get $swp1) diff --git a/tools/testing/selftests/net/forwarding/router_bridge.sh b/tools/testing/selftests/net/forwarding/router_bridge.sh index ebc596a272f7c..8ce0aed54ece3 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge.sh @@ -38,7 +38,8 @@ h2_destroy() router_create() { - ip link add name br1 type bridge vlan_filtering 1 + ip link add name br1 address $(mac_get $swp1) \ + type bridge vlan_filtering 1 ip link set dev br1 up ip link set dev $swp1 master br1 diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh index fa6a88c50750d..de2b2d5480dd2 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh @@ -1,6 +1,28 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# +------------------------+ +----------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1.555 | | + $h2 | +# | | 192.0.2.1/28 | | | 192.0.2.130/28 | +# | | 2001:db8:1::1/64 | | | 2001:db8:2::2/64 | +# | | | | | | +# | + $h1 | | | | +# +----|-------------------+ +--|-------------------+ +# | | +# +----|--------------------------------------------------|-------------------+ +# | SW | | | +# | +--|-------------------------------+ + $swp2 | +# | | + $swp1 | 192.0.2.129/28 | +# | | vid 555 | 2001:db8:2::1/64 | +# | | | | +# | | + BR1 (802.1q) | | +# | | vid 555 pvid untagged | | +# | | 192.0.2.2/28 | | +# | | 2001:db8:1::2/64 | | +# | +----------------------------------+ | +# +---------------------------------------------------------------------------+ + ALL_TESTS=" ping_ipv4 ping_ipv6 @@ -41,7 +63,7 @@ h2_destroy() router_create() { - ip link add name br1 type bridge vlan_filtering 1 + ip link add name br1 type bridge vlan_filtering 1 vlan_default_pvid 0 ip link set dev br1 up ip link set dev $swp1 master br1 diff --git a/tools/testing/selftests/net/forwarding/skbedit_priority.sh b/tools/testing/selftests/net/forwarding/skbedit_priority.sh index bde11dc27873c..3dd5fcbd3eaa4 100755 --- a/tools/testing/selftests/net/forwarding/skbedit_priority.sh +++ b/tools/testing/selftests/net/forwarding/skbedit_priority.sh @@ -54,7 +54,9 @@ h2_destroy() switch_create() { - ip link add name br1 up type bridge vlan_filtering 1 + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 addrgenmode none + ip link set dev br1 up ip link set dev $swp1 master br1 ip link set dev $swp1 up ip link set dev $swp2 master br1 diff --git a/tools/testing/selftests/net/forwarding/tc_flower_cfm.sh b/tools/testing/selftests/net/forwarding/tc_flower_cfm.sh new file mode 100755 index 0000000000000..3ca20df952ebf --- /dev/null +++ b/tools/testing/selftests/net/forwarding/tc_flower_cfm.sh @@ -0,0 +1,206 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS="match_cfm_opcode match_cfm_level match_cfm_level_and_opcode" +NUM_NETIFS=2 +source tc_common.sh +source lib.sh + +h1_create() +{ + simple_if_init $h1 +} + +h1_destroy() +{ + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 + tc qdisc add dev $h2 clsact +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + simple_if_fini $h2 +} + +u8_to_hex() +{ + local u8=$1; shift + + printf "%02x" $u8 +} + +generate_cfm_hdr() +{ + local mdl=$1; shift + local op=$1; shift + local flags=$1; shift + local tlv_offset=$1; shift + + local cfm_hdr=$(: + )"$(u8_to_hex $((mdl << 5))):"$( : MD level and Version + )"$(u8_to_hex $op):"$( : OpCode + )"$(u8_to_hex $flags):"$( : Flags + )"$(u8_to_hex $tlv_offset)"$( : TLV offset + ) + + echo $cfm_hdr +} + +match_cfm_opcode() +{ + local ethtype="89 02"; readonly ethtype + RET=0 + + tc filter add dev $h2 ingress protocol cfm pref 1 handle 101 \ + flower cfm op 47 action drop + tc filter add dev $h2 ingress protocol cfm pref 1 handle 102 \ + flower cfm op 43 action drop + + pkt="$ethtype $(generate_cfm_hdr 7 47 0 32)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + pkt="$ethtype $(generate_cfm_hdr 6 5 0 4)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Did not match on correct opcode" + + tc_check_packets "dev $h2 ingress" 102 0 + check_err $? "Matched on the wrong opcode" + + pkt="$ethtype $(generate_cfm_hdr 0 43 0 12)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Matched on the wrong opcode" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Did not match on correct opcode" + + tc filter del dev $h2 ingress protocol cfm pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol cfm pref 1 handle 102 flower + + log_test "CFM opcode match test" +} + +match_cfm_level() +{ + local ethtype="89 02"; readonly ethtype + RET=0 + + tc filter add dev $h2 ingress protocol cfm pref 1 handle 101 \ + flower cfm mdl 5 action drop + tc filter add dev $h2 ingress protocol cfm pref 1 handle 102 \ + flower cfm mdl 3 action drop + tc filter add dev $h2 ingress protocol cfm pref 1 handle 103 \ + flower cfm mdl 0 action drop + + pkt="$ethtype $(generate_cfm_hdr 5 42 0 12)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + pkt="$ethtype $(generate_cfm_hdr 6 1 0 70)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + pkt="$ethtype $(generate_cfm_hdr 0 1 0 70)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Did not match on correct level" + + tc_check_packets "dev $h2 ingress" 102 0 + check_err $? "Matched on the wrong level" + + tc_check_packets "dev $h2 ingress" 103 1 + check_err $? "Did not match on correct level" + + pkt="$ethtype $(generate_cfm_hdr 3 0 0 4)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Matched on the wrong level" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Did not match on correct level" + + tc_check_packets "dev $h2 ingress" 103 1 + check_err $? "Matched on the wrong level" + + tc filter del dev $h2 ingress protocol cfm pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol cfm pref 1 handle 102 flower + tc filter del dev $h2 ingress protocol cfm pref 1 handle 103 flower + + log_test "CFM level match test" +} + +match_cfm_level_and_opcode() +{ + local ethtype="89 02"; readonly ethtype + RET=0 + + tc filter add dev $h2 ingress protocol cfm pref 1 handle 101 \ + flower cfm mdl 5 op 41 action drop + tc filter add dev $h2 ingress protocol cfm pref 1 handle 102 \ + flower cfm mdl 7 op 42 action drop + + pkt="$ethtype $(generate_cfm_hdr 5 41 0 4)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + pkt="$ethtype $(generate_cfm_hdr 7 3 0 4)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + pkt="$ethtype $(generate_cfm_hdr 3 42 0 12)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Did not match on correct level and opcode" + + tc_check_packets "dev $h2 ingress" 102 0 + check_err $? "Matched on the wrong level and opcode" + + pkt="$ethtype $(generate_cfm_hdr 7 42 0 12)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Matched on the wrong level and opcode" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Did not match on correct level and opcode" + + tc filter del dev $h2 ingress protocol cfm pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol cfm pref 1 handle 102 flower + + log_test "CFM opcode and level match test" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + h2=${NETIFS[p2]} + h1mac=$(mac_get $h1) + h2mac=$(mac_get $h2) + + vrf_prepare + + h1_create + h2_create +} + +cleanup() +{ + pre_cleanup + + h2_destroy + h1_destroy + + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh new file mode 100755 index 0000000000000..e22c2d28b6ebf --- /dev/null +++ b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh @@ -0,0 +1,350 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +-----------------------+ +----------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# | | 2001:db8:1::1/64 | | 2001:db8:1::2/64 | | +# +----|------------------+ +------------------|---+ +# | | +# +----|-------------------------------------------------------------------|---+ +# | SW | | | +# | +-|-------------------------------------------------------------------|-+ | +# | | + $swp1 BR $swp2 + | | +# | +-----------------------------------------------------------------------+ | +# +----------------------------------------------------------------------------+ + +ALL_TESTS=" + test_l2_miss_unicast + test_l2_miss_multicast + test_l2_miss_ll_multicast + test_l2_miss_broadcast +" + +NUM_NETIFS=4 +source lib.sh +source tc_common.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 2001:db8:1::2/64 +} + +h2_destroy() +{ + simple_if_fini $h2 192.0.2.2/28 2001:db8:1::2/64 +} + +switch_create() +{ + ip link add name br1 up type bridge + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + tc qdisc add dev $swp2 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp2 clsact + + ip link set dev $swp2 down + ip link set dev $swp2 nomaster + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + ip link del dev br1 +} + +test_l2_miss_unicast() +{ + local dmac=00:01:02:03:04:05 + local dip=192.0.2.2 + local sip=192.0.2.1 + + RET=0 + + # Unknown unicast. + tc filter add dev $swp2 egress protocol ipv4 handle 101 pref 1 \ + flower indev $swp1 l2_miss 1 dst_mac $dmac src_ip $sip \ + dst_ip $dip action pass + # Known unicast. + tc filter add dev $swp2 egress protocol ipv4 handle 102 pref 1 \ + flower indev $swp1 l2_miss 0 dst_mac $dmac src_ip $sip \ + dst_ip $dip action pass + + # Before adding FDB entry. + $MZ $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Unknown unicast filter was not hit before adding FDB entry" + + tc_check_packets "dev $swp2 egress" 102 0 + check_err $? "Known unicast filter was hit before adding FDB entry" + + # Adding FDB entry. + bridge fdb replace $dmac dev $swp2 master static + + $MZ $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Unknown unicast filter was hit after adding FDB entry" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "Known unicast filter was not hit after adding FDB entry" + + # Deleting FDB entry. + bridge fdb del $dmac dev $swp2 master static + + $MZ $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 2 + check_err $? "Unknown unicast filter was not hit after deleting FDB entry" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "Known unicast filter was hit after deleting FDB entry" + + tc filter del dev $swp2 egress protocol ipv4 pref 1 handle 102 flower + tc filter del dev $swp2 egress protocol ipv4 pref 1 handle 101 flower + + log_test "L2 miss - Unicast" +} + +test_l2_miss_multicast_common() +{ + local proto=$1; shift + local sip=$1; shift + local dip=$1; shift + local mode=$1; shift + local name=$1; shift + + RET=0 + + # Unregistered multicast. + tc filter add dev $swp2 egress protocol $proto handle 101 pref 1 \ + flower indev $swp1 l2_miss 1 src_ip $sip dst_ip $dip \ + action pass + # Registered multicast. + tc filter add dev $swp2 egress protocol $proto handle 102 pref 1 \ + flower indev $swp1 l2_miss 0 src_ip $sip dst_ip $dip \ + action pass + + # Before adding MDB entry. + $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Unregistered multicast filter was not hit before adding MDB entry" + + tc_check_packets "dev $swp2 egress" 102 0 + check_err $? "Registered multicast filter was hit before adding MDB entry" + + # Adding MDB entry. + bridge mdb replace dev br1 port $swp2 grp $dip permanent + + $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Unregistered multicast filter was hit after adding MDB entry" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "Registered multicast filter was not hit after adding MDB entry" + + # Deleting MDB entry. + bridge mdb del dev br1 port $swp2 grp $dip + + $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 2 + check_err $? "Unregistered multicast filter was not hit after deleting MDB entry" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "Registered multicast filter was hit after deleting MDB entry" + + tc filter del dev $swp2 egress protocol $proto pref 1 handle 102 flower + tc filter del dev $swp2 egress protocol $proto pref 1 handle 101 flower + + log_test "L2 miss - Multicast ($name)" +} + +test_l2_miss_multicast_ipv4() +{ + local proto="ipv4" + local sip=192.0.2.1 + local dip=239.1.1.1 + local mode="-4" + local name="IPv4" + + test_l2_miss_multicast_common $proto $sip $dip $mode $name +} + +test_l2_miss_multicast_ipv6() +{ + local proto="ipv6" + local sip=2001:db8:1::1 + local dip=ff0e::1 + local mode="-6" + local name="IPv6" + + test_l2_miss_multicast_common $proto $sip $dip $mode $name +} + +test_l2_miss_multicast() +{ + # Configure $swp2 as a multicast router port so that it will forward + # both registered and unregistered multicast traffic. + bridge link set dev $swp2 mcast_router 2 + + # Forwarding according to MDB entries only takes place when the bridge + # detects that there is a valid querier in the network. Set the bridge + # as the querier and assign it a valid IPv6 link-local address to be + # used as the source address for MLD queries. + ip link set dev br1 type bridge mcast_querier 1 + ip -6 address add fe80::1/64 nodad dev br1 + # Wait the default Query Response Interval (10 seconds) for the bridge + # to determine that there are no other queriers in the network. + sleep 10 + + test_l2_miss_multicast_ipv4 + test_l2_miss_multicast_ipv6 + + ip -6 address del fe80::1/64 dev br1 + ip link set dev br1 type bridge mcast_querier 0 + bridge link set dev $swp2 mcast_router 1 +} + +test_l2_miss_multicast_common2() +{ + local name=$1; shift + local dmac=$1; shift + local dip=224.0.0.1 + local sip=192.0.2.1 + +} + +test_l2_miss_ll_multicast_common() +{ + local proto=$1; shift + local dmac=$1; shift + local sip=$1; shift + local dip=$1; shift + local mode=$1; shift + local name=$1; shift + + RET=0 + + tc filter add dev $swp2 egress protocol $proto handle 101 pref 1 \ + flower indev $swp1 l2_miss 1 dst_mac $dmac src_ip $sip \ + dst_ip $dip action pass + + $MZ $mode $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Filter was not hit" + + tc filter del dev $swp2 egress protocol $proto pref 1 handle 101 flower + + log_test "L2 miss - Link-local multicast ($name)" +} + +test_l2_miss_ll_multicast_ipv4() +{ + local proto=ipv4 + local dmac=01:00:5e:00:00:01 + local sip=192.0.2.1 + local dip=224.0.0.1 + local mode="-4" + local name="IPv4" + + test_l2_miss_ll_multicast_common $proto $dmac $sip $dip $mode $name +} + +test_l2_miss_ll_multicast_ipv6() +{ + local proto=ipv6 + local dmac=33:33:00:00:00:01 + local sip=2001:db8:1::1 + local dip=ff02::1 + local mode="-6" + local name="IPv6" + + test_l2_miss_ll_multicast_common $proto $dmac $sip $dip $mode $name +} + +test_l2_miss_ll_multicast() +{ + test_l2_miss_ll_multicast_ipv4 + test_l2_miss_ll_multicast_ipv6 +} + +test_l2_miss_broadcast() +{ + local dmac=ff:ff:ff:ff:ff:ff + local smac=00:01:02:03:04:05 + + RET=0 + + tc filter add dev $swp2 egress protocol all handle 101 pref 1 \ + flower l2_miss 1 dst_mac $dmac src_mac $smac \ + action pass + tc filter add dev $swp2 egress protocol all handle 102 pref 1 \ + flower l2_miss 0 dst_mac $dmac src_mac $smac \ + action pass + + $MZ $h1 -a $smac -b $dmac -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 0 + check_err $? "L2 miss filter was hit when should not" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "L2 no miss filter was not hit when should" + + tc filter del dev $swp2 egress protocol all pref 1 handle 102 flower + tc filter del dev $swp2 egress protocol all pref 1 handle 101 flower + + log_test "L2 miss - Broadcast" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 43a7236261261..7b936a9268594 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -9,7 +9,7 @@ TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq -TEST_FILES := settings +TEST_FILES := mptcp_lib.sh settings EXTRA_CLEAN := *.pcap diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index 38021a0dd5276..6032f9b23c4c2 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -1,3 +1,4 @@ +CONFIG_KALLSYMS=y CONFIG_MPTCP=y CONFIG_IPV6=y CONFIG_MPTCP_IPV6=y diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index ef628b16fe9b4..fa9e09ad97d99 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + sec=$(date +%s) rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) ns="ns1-$rndh" @@ -31,6 +33,8 @@ cleanup() ip netns del $ns } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" @@ -51,16 +55,20 @@ __chk_nr() { local command="$1" local expected=$2 - local msg nr + local msg="$3" + local skip="${4:-SKIP}" + local nr - shift 2 - msg=$* nr=$(eval $command) printf "%-50s" "$msg" if [ $nr != $expected ]; then - echo "[ fail ] expected $expected found $nr" - ret=$test_cnt + if [ $nr = "$skip" ] && ! mptcp_lib_expect_all_features; then + echo "[ skip ] Feature probably not supported" + else + echo "[ fail ] expected $expected found $nr" + ret=$test_cnt + fi else echo "[ ok ]" fi @@ -72,12 +80,12 @@ __chk_msk_nr() local condition=$1 shift 1 - __chk_nr "ss -inmHMN $ns | $condition" $* + __chk_nr "ss -inmHMN $ns | $condition" "$@" } chk_msk_nr() { - __chk_msk_nr "grep -c token:" $* + __chk_msk_nr "grep -c token:" "$@" } wait_msk_nr() @@ -115,37 +123,26 @@ wait_msk_nr() chk_msk_fallback_nr() { - __chk_msk_nr "grep -c fallback" $* + __chk_msk_nr "grep -c fallback" "$@" } chk_msk_remote_key_nr() { - __chk_msk_nr "grep -c remote_key" $* + __chk_msk_nr "grep -c remote_key" "$@" } __chk_listen() { local filter="$1" local expected=$2 + local msg="$3" - shift 2 - msg=$* - - nr=$(ss -N $ns -Ml "$filter" | grep -c LISTEN) - printf "%-50s" "$msg" - - if [ $nr != $expected ]; then - echo "[ fail ] expected $expected found $nr" - ret=$test_cnt - else - echo "[ ok ]" - fi + __chk_nr "ss -N $ns -Ml '$filter' | grep -c LISTEN" "$expected" "$msg" 0 } chk_msk_listen() { lport=$1 - local msg="check for listen socket" # destination port search should always return empty list __chk_listen "dport $lport" 0 "listen match for dport $lport" @@ -163,10 +160,9 @@ chk_msk_listen() chk_msk_inuse() { local expected=$1 + local msg="$2" local listen_nr - shift 1 - listen_nr=$(ss -N "${ns}" -Ml | grep -c LISTEN) expected=$((expected + listen_nr)) @@ -177,7 +173,7 @@ chk_msk_inuse() sleep 0.1 done - __chk_nr get_msk_inuse $expected $* + __chk_nr get_msk_inuse $expected "$msg" 0 } # $1: ns, $2: port diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index a43d3e2f59bbe..13561e5bc0cdb 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + time_start=$(date +%s) optstring="S:R:d:e:l:r:h4cm:f:tC" @@ -141,6 +143,9 @@ cleanup() done } +mptcp_lib_check_mptcp +mptcp_lib_check_kallsyms + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" @@ -691,6 +696,15 @@ run_test_transparent() return 0 fi + # IP(V6)_TRANSPARENT has been added after TOS support which came with + # the required infrastructure in MPTCP sockopt code. To support TOS, the + # following function has been exported (T). Not great but better than + # checking for a specific kernel version. + if ! mptcp_lib_kallsyms_has "T __ip_sock_set_tos$"; then + echo "INFO: ${msg} not supported by the kernel: SKIP" + return + fi + ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF" flush ruleset table inet mangle { @@ -763,6 +777,11 @@ run_tests_peekmode() run_tests_mptfo() { + if ! mptcp_lib_kallsyms_has "mptcp_fastopen_"; then + echo "INFO: TFO not supported by the kernel: SKIP" + return + fi + echo "INFO: with MPTFO start" ip netns exec "$ns1" sysctl -q net.ipv4.tcp_fastopen=2 ip netns exec "$ns2" sysctl -q net.ipv4.tcp_fastopen=1 @@ -783,9 +802,14 @@ run_tests_disconnect() local old_cin=$cin local old_sin=$sin + if ! mptcp_lib_kallsyms_has "mptcp_pm_data_reset$"; then + echo "INFO: Full disconnect not supported: SKIP" + return + fi + cat $cin $cin $cin > "$cin".disconnect - # force do_transfer to cope with the multiple tranmissions + # force do_transfer to cope with the multiple transmissions sin="$cin.disconnect" cin="$cin.disconnect" cin_disconnect="$old_cin" diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 26310c17b4c6b..e6c9d5451c5b5 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -10,6 +10,8 @@ # because it's invoked by variable name, see how the "tests" array is used #shellcheck disable=SC2317 +. "$(dirname "${0}")/mptcp_lib.sh" + ret=0 sin="" sinfail="" @@ -17,11 +19,14 @@ sout="" cin="" cinfail="" cinsent="" +tmpfile="" cout="" capout="" ns1="" ns2="" ksft_skip=4 +iptables="iptables" +ip6tables="ip6tables" timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) capture=0 @@ -34,6 +39,7 @@ evts_ns1="" evts_ns2="" evts_ns1_pid=0 evts_ns2_pid=0 +stats_dumped=0 declare -A all_tests declare -a only_tests_ids @@ -44,6 +50,10 @@ TEST_NAME="" nr_blank=40 export FAILING_LINKS="" +export test_linkfail=0 +export addr_nr_ns1=0 +export addr_nr_ns2=0 +export sflags="" # generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) || # (ip6 && (ip6[74] & 0xf0) == 0x30)'" @@ -79,7 +89,7 @@ init_partial() ip netns add $netns || exit $ksft_skip ip -net $netns link set lo up ip netns exec $netns sysctl -q net.mptcp.enabled=1 - ip netns exec $netns sysctl -q net.mptcp.pm_type=0 + ip netns exec $netns sysctl -q net.mptcp.pm_type=0 2>/dev/null || true ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0 ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0 if [ $checksum -eq 1 ]; then @@ -87,6 +97,7 @@ init_partial() fi done + stats_dumped=0 check_invert=0 validate_checksum=$checksum FAILING_LINKS="" @@ -136,12 +147,19 @@ cleanup_partial() check_tools() { + mptcp_lib_check_mptcp + mptcp_lib_check_kallsyms + if ! ip -Version &> /dev/null; then echo "SKIP: Could not run test without ip tool" exit $ksft_skip fi - if ! iptables -V &> /dev/null; then + # Use the legacy version if available to support old kernel versions + if iptables-legacy -V &> /dev/null; then + iptables="iptables-legacy" + ip6tables="ip6tables-legacy" + elif ! iptables -V &> /dev/null; then echo "SKIP: Could not run all tests without iptables tool" exit $ksft_skip fi @@ -175,10 +193,37 @@ cleanup() { rm -f "$cin" "$cout" "$sinfail" rm -f "$sin" "$sout" "$cinsent" "$cinfail" + rm -f "$tmpfile" rm -rf $evts_ns1 $evts_ns2 cleanup_partial } +# $1: msg +print_title() +{ + printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${1}" +} + +# [ $1: fail msg ] +mark_as_skipped() +{ + local msg="${1:-"Feature not supported"}" + + mptcp_lib_fail_if_expected_feature "${msg}" + + print_title "[ skip ] ${msg}" + printf "\n" +} + +# $@: condition +continue_if() +{ + if ! "${@}"; then + mark_as_skipped + return 1 + fi +} + skip_test() { if [ "${#only_tests_ids[@]}" -eq 0 ] && [ "${#only_tests_names[@]}" -eq 0 ]; then @@ -222,6 +267,19 @@ reset() return 0 } +# $1: test name ; $2: counter to check +reset_check_counter() +{ + reset "${1}" || return 1 + + local counter="${2}" + + if ! nstat -asz "${counter}" | grep -wq "${counter}"; then + mark_as_skipped "counter '${counter}' is not available" + return 1 + fi +} + # $1: test name reset_with_cookies() { @@ -241,17 +299,21 @@ reset_with_add_addr_timeout() reset "${1}" || return 1 - tables="iptables" + tables="${iptables}" if [ $ip -eq 6 ]; then - tables="ip6tables" + tables="${ip6tables}" fi ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 - ip netns exec $ns2 $tables -A OUTPUT -p tcp \ - -m tcp --tcp-option 30 \ - -m bpf --bytecode \ - "$CBPF_MPTCP_SUBOPTION_ADD_ADDR" \ - -j DROP + + if ! ip netns exec $ns2 $tables -A OUTPUT -p tcp \ + -m tcp --tcp-option 30 \ + -m bpf --bytecode \ + "$CBPF_MPTCP_SUBOPTION_ADD_ADDR" \ + -j DROP; then + mark_as_skipped "unable to set the 'add addr' rule" + return 1 + fi } # $1: test name @@ -295,22 +357,17 @@ reset_with_allow_join_id0() # tc action pedit offset 162 out of bounds # # Netfilter is used to mark packets with enough data. -reset_with_fail() +setup_fail_rules() { - reset "${1}" || return 1 - - ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=1 - ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=1 - check_invert=1 validate_checksum=1 - local i="$2" - local ip="${3:-4}" + local i="$1" + local ip="${2:-4}" local tables - tables="iptables" + tables="${iptables}" if [ $ip -eq 6 ]; then - tables="ip6tables" + tables="${ip6tables}" fi ip netns exec $ns2 $tables \ @@ -320,15 +377,32 @@ reset_with_fail() -p tcp \ -m length --length 150:9999 \ -m statistic --mode nth --packet 1 --every 99999 \ - -j MARK --set-mark 42 || exit 1 + -j MARK --set-mark 42 || return ${ksft_skip} - tc -n $ns2 qdisc add dev ns2eth$i clsact || exit 1 + tc -n $ns2 qdisc add dev ns2eth$i clsact || return ${ksft_skip} tc -n $ns2 filter add dev ns2eth$i egress \ protocol ip prio 1000 \ handle 42 fw \ action pedit munge offset 148 u8 invert \ pipe csum tcp \ - index 100 || exit 1 + index 100 || return ${ksft_skip} +} + +reset_with_fail() +{ + reset_check_counter "${1}" "MPTcpExtInfiniteMapTx" || return 1 + shift + + ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=1 + ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=1 + + local rc=0 + setup_fail_rules "${@}" || rc=$? + + if [ ${rc} -eq ${ksft_skip} ]; then + mark_as_skipped "unable to set the 'fail' rules" + return 1 + fi } reset_with_events() @@ -343,10 +417,32 @@ reset_with_events() evts_ns2_pid=$! } +reset_with_tcp_filter() +{ + reset "${1}" || return 1 + shift + + local ns="${!1}" + local src="${2}" + local target="${3}" + + if ! ip netns exec "${ns}" ${iptables} \ + -A INPUT \ + -s "${src}" \ + -p tcp \ + -j "${target}"; then + mark_as_skipped "unable to set the filter rules" + return 1 + fi +} + fail_test() { ret=1 failed_tests[${TEST_COUNT}]="${TEST_NAME}" + + [ "${stats_dumped}" = 0 ] && dump_stats + stats_dumped=1 } get_failed_tests_ids() @@ -383,9 +479,16 @@ check_transfer() fail_test return 1 fi - bytes="--bytes=${bytes}" + + # note: BusyBox's "cmp" command doesn't support --bytes + tmpfile=$(mktemp) + head --bytes="$bytes" "$in" > "$tmpfile" + mv "$tmpfile" "$in" + head --bytes="$bytes" "$out" > "$tmpfile" + mv "$tmpfile" "$out" + tmpfile="" fi - cmp -l "$in" "$out" ${bytes} | while read -r i a b; do + cmp -l "$in" "$out" | while read -r i a b; do local sum=$((0${a} + 0${b})) if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then echo "[ FAIL ] $what does not match (in, out):" @@ -454,11 +557,25 @@ wait_local_port_listen() done } -rm_addr_count() +# $1: ns ; $2: counter +get_counter() { - local ns=${1} + local ns="${1}" + local counter="${2}" + local count - ip netns exec ${ns} nstat -as | grep MPTcpExtRmAddr | awk '{print $2}' + count=$(ip netns exec ${ns} nstat -asz "${counter}" | awk 'NR==1 {next} {print $2}') + if [ -z "${count}" ]; then + mptcp_lib_fail_if_expected_feature "${counter} counter" + return 1 + fi + + echo "${count}" +} + +rm_addr_count() +{ + get_counter "${1}" "MPTcpExtRmAddr" } # $1: ns, $2: old rm_addr counter in $ns @@ -476,16 +593,36 @@ wait_rm_addr() done } +rm_sf_count() +{ + get_counter "${1}" "MPTcpExtRmSubflow" +} + +# $1: ns, $2: old rm_sf counter in $ns +wait_rm_sf() +{ + local ns="${1}" + local old_cnt="${2}" + local cnt + + local i + for i in $(seq 10); do + cnt=$(rm_sf_count ${ns}) + [ "$cnt" = "${old_cnt}" ] || break + sleep 0.1 + done +} + wait_mpj() { local ns="${1}" local cnt old_cnt - old_cnt=$(ip netns exec ${ns} nstat -as | grep MPJoinAckRx | awk '{print $2}') + old_cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") local i for i in $(seq 10); do - cnt=$(ip netns exec ${ns} nstat -as | grep MPJoinAckRx | awk '{print $2}') + cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") [ "$cnt" = "${old_cnt}" ] || break sleep 0.1 done @@ -685,144 +822,11 @@ pm_nl_check_endpoint() fi } -filter_tcp_from() -{ - local ns="${1}" - local src="${2}" - local target="${3}" - - ip netns exec "${ns}" iptables -A INPUT -s "${src}" -p tcp -j "${target}" -} - -do_transfer() +pm_nl_set_endpoint() { local listener_ns="$1" local connector_ns="$2" - local cl_proto="$3" - local srv_proto="$4" - local connect_addr="$5" - local test_link_fail="$6" - local addr_nr_ns1="$7" - local addr_nr_ns2="$8" - local speed="$9" - local sflags="${10}" - - local port=$((10000 + TEST_COUNT - 1)) - local cappid - local userspace_pm=0 - - :> "$cout" - :> "$sout" - :> "$capout" - - if [ $capture -eq 1 ]; then - local capuser - if [ -z $SUDO_USER ] ; then - capuser="" - else - capuser="-Z $SUDO_USER" - fi - - capfile=$(printf "mp_join-%02u-%s.pcap" "$TEST_COUNT" "${listener_ns}") - - echo "Capturing traffic for test $TEST_COUNT into $capfile" - ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 & - cappid=$! - - sleep 1 - fi - - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat -n - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat -n - - local extra_args - if [ $speed = "fast" ]; then - extra_args="-j" - elif [ $speed = "slow" ]; then - extra_args="-r 50" - elif [[ $speed = "speed_"* ]]; then - extra_args="-r ${speed:6}" - fi - - if [[ "${addr_nr_ns1}" = "userspace_"* ]]; then - userspace_pm=1 - addr_nr_ns1=${addr_nr_ns1:10} - fi - - local flags="subflow" - local extra_cl_args="" - local extra_srv_args="" - local trunc_size="" - if [[ "${addr_nr_ns2}" = "fastclose_"* ]]; then - if [ ${test_link_fail} -le 1 ]; then - echo "fastclose tests need test_link_fail argument" - fail_test - return 1 - fi - - # disconnect - trunc_size=${test_link_fail} - local side=${addr_nr_ns2:10} - - if [ ${side} = "client" ]; then - extra_cl_args="-f ${test_link_fail}" - extra_srv_args="-f -1" - elif [ ${side} = "server" ]; then - extra_srv_args="-f ${test_link_fail}" - extra_cl_args="-f -1" - else - echo "wrong/unknown fastclose spec ${side}" - fail_test - return 1 - fi - addr_nr_ns2=0 - elif [[ "${addr_nr_ns2}" = "userspace_"* ]]; then - userspace_pm=1 - addr_nr_ns2=${addr_nr_ns2:10} - elif [[ "${addr_nr_ns2}" = "fullmesh_"* ]]; then - flags="${flags},fullmesh" - addr_nr_ns2=${addr_nr_ns2:9} - fi - - extra_srv_args="$extra_args $extra_srv_args" - if [ "$test_link_fail" -gt 1 ];then - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - $extra_srv_args "::" < "$sinfail" > "$sout" & - else - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - $extra_srv_args "::" < "$sin" > "$sout" & - fi - local spid=$! - - wait_local_port_listen "${listener_ns}" "${port}" - - extra_cl_args="$extra_args $extra_cl_args" - if [ "$test_link_fail" -eq 0 ];then - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_cl_args $connect_addr < "$cin" > "$cout" & - elif [ "$test_link_fail" -eq 1 ] || [ "$test_link_fail" -eq 2 ];then - ( cat "$cinfail" ; sleep 2; link_failure $listener_ns ; cat "$cinfail" ) | \ - tee "$cinsent" | \ - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_cl_args $connect_addr > "$cout" & - else - tee "$cinsent" < "$cinfail" | \ - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_cl_args $connect_addr > "$cout" & - fi - local cpid=$! + local connect_addr="$3" # let the mptcp subflow be established in background before # do endpoint manipulation @@ -834,7 +838,6 @@ do_transfer() local counter=2 local add_nr_ns1=${addr_nr_ns1} local id=10 - local tk while [ $add_nr_ns1 -gt 0 ]; do local addr if is_v6 "${connect_addr}"; then @@ -842,16 +845,7 @@ do_transfer() else addr="10.0.$counter.1" fi - if [ $userspace_pm -eq 0 ]; then - pm_nl_add_endpoint $ns1 $addr flags signal - else - tk=$(grep "type:1," "$evts_ns1" | - sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q') - ip netns exec ${listener_ns} ./pm_nl_ctl ann $addr token $tk id $id - sleep 1 - ip netns exec ${listener_ns} ./pm_nl_ctl rem token $tk id $id - fi - + pm_nl_add_endpoint $ns1 $addr flags signal counter=$((counter + 1)) add_nr_ns1=$((add_nr_ns1 - 1)) id=$((id + 1)) @@ -896,7 +890,6 @@ do_transfer() local add_nr_ns2=${addr_nr_ns2} local counter=3 local id=20 - local tk da dp sp while [ $add_nr_ns2 -gt 0 ]; do local addr if is_v6 "${connect_addr}"; then @@ -904,20 +897,7 @@ do_transfer() else addr="10.0.$counter.2" fi - if [ $userspace_pm -eq 0 ]; then - pm_nl_add_endpoint $ns2 $addr flags $flags - else - tk=$(sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") - da=$(sed -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evts_ns2") - dp=$(sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") - ip netns exec ${connector_ns} ./pm_nl_ctl csf lip $addr lid $id \ - rip $da rport $dp token $tk - sleep 1 - sp=$(grep "type:10" "$evts_ns2" | - sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') - ip netns exec ${connector_ns} ./pm_nl_ctl dsf lip $addr lport $sp \ - rip $da rport $dp token $tk - fi + pm_nl_add_endpoint $ns2 $addr flags $flags counter=$((counter + 1)) add_nr_ns2=$((add_nr_ns2 - 1)) id=$((id + 1)) @@ -986,6 +966,126 @@ do_transfer() done done fi +} + +do_transfer() +{ + local listener_ns="$1" + local connector_ns="$2" + local cl_proto="$3" + local srv_proto="$4" + local connect_addr="$5" + local speed="$6" + + local port=$((10000 + TEST_COUNT - 1)) + local cappid + + :> "$cout" + :> "$sout" + :> "$capout" + + if [ $capture -eq 1 ]; then + local capuser + if [ -z $SUDO_USER ] ; then + capuser="" + else + capuser="-Z $SUDO_USER" + fi + + capfile=$(printf "mp_join-%02u-%s.pcap" "$TEST_COUNT" "${listener_ns}") + + echo "Capturing traffic for test $TEST_COUNT into $capfile" + ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 & + cappid=$! + + sleep 1 + fi + + NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ + nstat -n + NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ + nstat -n + + local extra_args + if [ $speed = "fast" ]; then + extra_args="-j" + elif [ $speed = "slow" ]; then + extra_args="-r 50" + elif [[ $speed = "speed_"* ]]; then + extra_args="-r ${speed:6}" + fi + + local flags="subflow" + local extra_cl_args="" + local extra_srv_args="" + local trunc_size="" + if [[ "${addr_nr_ns2}" = "fastclose_"* ]]; then + if [ ${test_linkfail} -le 1 ]; then + echo "fastclose tests need test_linkfail argument" + fail_test + return 1 + fi + + # disconnect + trunc_size=${test_linkfail} + local side=${addr_nr_ns2:10} + + if [ ${side} = "client" ]; then + extra_cl_args="-f ${test_linkfail}" + extra_srv_args="-f -1" + elif [ ${side} = "server" ]; then + extra_srv_args="-f ${test_linkfail}" + extra_cl_args="-f -1" + else + echo "wrong/unknown fastclose spec ${side}" + fail_test + return 1 + fi + addr_nr_ns2=0 + elif [[ "${addr_nr_ns2}" = "fullmesh_"* ]]; then + flags="${flags},fullmesh" + addr_nr_ns2=${addr_nr_ns2:9} + fi + + extra_srv_args="$extra_args $extra_srv_args" + if [ "$test_linkfail" -gt 1 ];then + timeout ${timeout_test} \ + ip netns exec ${listener_ns} \ + ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ + $extra_srv_args "::" < "$sinfail" > "$sout" & + else + timeout ${timeout_test} \ + ip netns exec ${listener_ns} \ + ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ + $extra_srv_args "::" < "$sin" > "$sout" & + fi + local spid=$! + + wait_local_port_listen "${listener_ns}" "${port}" + + extra_cl_args="$extra_args $extra_cl_args" + if [ "$test_linkfail" -eq 0 ];then + timeout ${timeout_test} \ + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr < "$cin" > "$cout" & + elif [ "$test_linkfail" -eq 1 ] || [ "$test_linkfail" -eq 2 ];then + ( cat "$cinfail" ; sleep 2; link_failure $listener_ns ; cat "$cinfail" ) | \ + tee "$cinsent" | \ + timeout ${timeout_test} \ + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr > "$cout" & + else + tee "$cinsent" < "$cinfail" | \ + timeout ${timeout_test} \ + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr > "$cout" & + fi + local cpid=$! + + pm_nl_set_endpoint $listener_ns $connector_ns $connect_addr wait $cpid local retc=$? @@ -1016,13 +1116,13 @@ do_transfer() return 1 fi - if [ "$test_link_fail" -gt 1 ];then + if [ "$test_linkfail" -gt 1 ];then check_transfer $sinfail $cout "file received by client" $trunc_size else check_transfer $sin $cout "file received by client" $trunc_size fi retc=$? - if [ "$test_link_fail" -eq 0 ];then + if [ "$test_linkfail" -eq 0 ];then check_transfer $cin $sout "file received by server" $trunc_size else check_transfer $cinsent $sout "file received by server" $trunc_size @@ -1055,11 +1155,7 @@ run_tests() local listener_ns="$1" local connector_ns="$2" local connect_addr="$3" - local test_linkfail="${4:-0}" - local addr_nr_ns1="${5:-0}" - local addr_nr_ns2="${6:-0}" - local speed="${7:-fast}" - local sflags="${8:-""}" + local speed="${4:-fast}" local size @@ -1103,8 +1199,7 @@ run_tests() make_file "$sinfail" "server" $size fi - do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} \ - ${test_linkfail} ${addr_nr_ns1} ${addr_nr_ns2} ${speed} ${sflags} + do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} ${speed} } dump_stats() @@ -1120,7 +1215,6 @@ chk_csum_nr() local csum_ns1=${1:-0} local csum_ns2=${2:-0} local count - local dump_stats local extra_msg="" local allow_multi_errors_ns1=0 local allow_multi_errors_ns2=0 @@ -1135,34 +1229,33 @@ chk_csum_nr() fi printf "%-${nr_blank}s %s" " " "sum" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns1} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns1" ]; then extra_msg="$extra_msg ns1=$count" fi - if { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } || { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then echo "[fail] got $count data checksum error[s] expected $csum_ns1" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - csum " - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns2} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns2" ]; then extra_msg="$extra_msg ns2=$count" fi - if { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } || { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then echo "[fail] got $count data checksum error[s] expected $csum_ns2" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats echo "$extra_msg" } @@ -1173,7 +1266,6 @@ chk_fail_nr() local fail_rx=$2 local ns_invert=${3:-""} local count - local dump_stats local ns_tx=$ns1 local ns_rx=$ns2 local extra_msg="" @@ -1196,37 +1288,35 @@ chk_fail_nr() fi printf "%-${nr_blank}s %s" " " "ftx" - count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPFailTx | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns_tx} "MPTcpExtMPFailTx") if [ "$count" != "$fail_tx" ]; then extra_msg="$extra_msg,tx=$count" fi - if { [ "$count" != "$fail_tx" ] && [ $allow_tx_lost -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != "$fail_tx" ] && [ $allow_tx_lost -eq 0 ]; } || { [ "$count" -gt "$fail_tx" ] && [ $allow_tx_lost -eq 1 ]; }; then echo "[fail] got $count MP_FAIL[s] TX expected $fail_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - failrx" - count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPFailRx | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns_rx} "MPTcpExtMPFailRx") if [ "$count" != "$fail_rx" ]; then extra_msg="$extra_msg,rx=$count" fi - if { [ "$count" != "$fail_rx" ] && [ $allow_rx_lost -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != "$fail_rx" ] && [ $allow_rx_lost -eq 0 ]; } || { [ "$count" -gt "$fail_rx" ] && [ $allow_rx_lost -eq 1 ]; }; then echo "[fail] got $count MP_FAIL[s] RX expected $fail_rx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats - echo "$extra_msg" } @@ -1236,7 +1326,6 @@ chk_fclose_nr() local fclose_rx=$2 local ns_invert=$3 local count - local dump_stats local ns_tx=$ns2 local ns_rx=$ns1 local extra_msg=" " @@ -1248,31 +1337,29 @@ chk_fclose_nr() fi printf "%-${nr_blank}s %s" " " "ctx" - count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPFastcloseTx | awk '{print $2}') - [ -z "$count" ] && count=0 - [ "$count" != "$fclose_tx" ] && extra_msg="$extra_msg,tx=$count" - if [ "$count" != "$fclose_tx" ]; then + count=$(get_counter ${ns_tx} "MPTcpExtMPFastcloseTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$fclose_tx" ]; then + extra_msg="$extra_msg,tx=$count" echo "[fail] got $count MP_FASTCLOSE[s] TX expected $fclose_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - fclzrx" - count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPFastcloseRx | awk '{print $2}') - [ -z "$count" ] && count=0 - [ "$count" != "$fclose_rx" ] && extra_msg="$extra_msg,rx=$count" - if [ "$count" != "$fclose_rx" ]; then + count=$(get_counter ${ns_rx} "MPTcpExtMPFastcloseRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$fclose_rx" ]; then + extra_msg="$extra_msg,rx=$count" echo "[fail] got $count MP_FASTCLOSE[s] RX expected $fclose_rx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats - echo "$extra_msg" } @@ -1282,7 +1369,6 @@ chk_rst_nr() local rst_rx=$2 local ns_invert=${3:-""} local count - local dump_stats local ns_tx=$ns1 local ns_rx=$ns2 local extra_msg="" @@ -1294,29 +1380,27 @@ chk_rst_nr() fi printf "%-${nr_blank}s %s" " " "rtx" - count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPRstTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ $count -lt $rst_tx ]; then + count=$(get_counter ${ns_tx} "MPTcpExtMPRstTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ $count -lt $rst_tx ]; then echo "[fail] got $count MP_RST[s] TX expected $rst_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - rstrx " - count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPRstRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" -lt "$rst_rx" ]; then + count=$(get_counter ${ns_rx} "MPTcpExtMPRstRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" -lt "$rst_rx" ]; then echo "[fail] got $count MP_RST[s] RX expected $rst_rx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats - echo "$extra_msg" } @@ -1325,31 +1409,28 @@ chk_infi_nr() local infi_tx=$1 local infi_rx=$2 local count - local dump_stats printf "%-${nr_blank}s %s" " " "itx" - count=$(ip netns exec $ns2 nstat -as | grep InfiniteMapTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$infi_tx" ]; then + count=$(get_counter ${ns2} "MPTcpExtInfiniteMapTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$infi_tx" ]; then echo "[fail] got $count infinite map[s] TX expected $infi_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - infirx" - count=$(ip netns exec $ns1 nstat -as | grep InfiniteMapRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$infi_rx" ]; then + count=$(get_counter ${ns1} "MPTcpExtInfiniteMapRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$infi_rx" ]; then echo "[fail] got $count infinite map[s] RX expected $infi_rx" fail_test - dump_stats=1 else echo "[ ok ]" fi - - [ "${dump_stats}" = 1 ] && dump_stats } chk_join_nr() @@ -1364,7 +1445,6 @@ chk_join_nr() local infi_nr=${8:-0} local corrupted_pkts=${9:-0} local count - local dump_stats local with_cookie local title="${TEST_NAME}" @@ -1373,21 +1453,22 @@ chk_join_nr() fi printf "%03u %-36s %s" "${TEST_COUNT}" "${title}" "syn" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn expected $syn_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - synack" with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies) - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinSynAckRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_ack_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtMPJoinSynAckRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_ack_nr" ]; then # simult connections exceeding the limit with cookie enabled could go up to # synack validation as the conn limit can be enforced reliably only after # the subflow creation @@ -1396,23 +1477,21 @@ chk_join_nr() else echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr" fail_test - dump_stats=1 fi else echo -n "[ ok ]" fi echo -n " - ack" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinAckRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$ack_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack expected $ack_nr" fail_test - dump_stats=1 else echo "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats if [ $validate_checksum -eq 1 ]; then chk_csum_nr $csum_ns1 $csum_ns2 chk_fail_nr $fail_nr $fail_nr @@ -1437,12 +1516,12 @@ chk_stale_nr() local recover_nr printf "%-${nr_blank}s %-18s" " " "stale" - stale_nr=$(ip netns exec $ns nstat -as | grep MPTcpExtSubflowStale | awk '{print $2}') - [ -z "$stale_nr" ] && stale_nr=0 - recover_nr=$(ip netns exec $ns nstat -as | grep MPTcpExtSubflowRecover | awk '{print $2}') - [ -z "$recover_nr" ] && recover_nr=0 - if [ $stale_nr -lt $stale_min ] || + stale_nr=$(get_counter ${ns} "MPTcpExtSubflowStale") + recover_nr=$(get_counter ${ns} "MPTcpExtSubflowRecover") + if [ -z "$stale_nr" ] || [ -z "$recover_nr" ]; then + echo "[skip]" + elif [ $stale_nr -lt $stale_min ] || { [ $stale_max -gt 0 ] && [ $stale_nr -gt $stale_max ]; } || [ $((stale_nr - recover_nr)) -ne $stale_delta ]; then echo "[fail] got $stale_nr stale[s] $recover_nr recover[s], " \ @@ -1472,117 +1551,142 @@ chk_add_nr() local mis_syn_nr=${7:-0} local mis_ack_nr=${8:-0} local count - local dump_stats local timeout timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) printf "%-${nr_blank}s %s" " " "add" - count=$(ip netns exec $ns2 nstat -as MPTcpExtAddAddr | grep MPTcpExtAddAddr | awk '{print $2}') - [ -z "$count" ] && count=0 - + count=$(get_counter ${ns2} "MPTcpExtAddAddr") + if [ -z "$count" ]; then + echo -n "[skip]" # if the test configured a short timeout tolerate greater then expected # add addrs options, due to retransmissions - if [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then + elif [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then echo "[fail] got $count ADD_ADDR[s] expected $add_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - echo " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtEchoAdd | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$echo_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtEchoAdd") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$echo_nr" ]; then echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi if [ $port_nr -gt 0 ]; then echo -n " - pt " - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtPortAdd | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$port_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtPortAdd") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$port_nr" ]; then echo "[fail] got $count ADD_ADDR[s] with a port-number expected $port_nr" fail_test - dump_stats=1 else echo "[ ok ]" fi printf "%-${nr_blank}s %s" " " "syn" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortSynRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinPortSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn with a different \ port-number expected $syn_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - synack" - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinPortSynAckRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_ack_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_ack_nr" ]; then echo "[fail] got $count JOIN[s] synack with a different \ port-number expected $syn_ack_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - ack" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortAckRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$ack_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinPortAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack with a different \ port-number expected $ack_nr" fail_test - dump_stats=1 else echo "[ ok ]" fi printf "%-${nr_blank}s %s" " " "syn" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortSynRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mis_syn_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMismatchPortSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$mis_syn_nr" ]; then echo "[fail] got $count JOIN[s] syn with a mismatched \ port-number expected $mis_syn_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - ack " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortAckRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mis_ack_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMismatchPortAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$mis_ack_nr" ]; then echo "[fail] got $count JOIN[s] ack with a mismatched \ port-number expected $mis_ack_nr" fail_test - dump_stats=1 else echo "[ ok ]" fi else echo "" fi +} + +chk_add_tx_nr() +{ + local add_tx_nr=$1 + local echo_tx_nr=$2 + local timeout + local count + + timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) + + printf "%-${nr_blank}s %s" " " "add TX" + count=$(get_counter ${ns1} "MPTcpExtAddAddrTx") + if [ -z "$count" ]; then + echo -n "[skip]" + # if the test configured a short timeout tolerate greater then expected + # add addrs options, due to retransmissions + elif [ "$count" != "$add_tx_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_tx_nr" ]; }; then + echo "[fail] got $count ADD_ADDR[s] TX, expected $add_tx_nr" + fail_test + else + echo -n "[ ok ]" + fi - [ "${dump_stats}" = 1 ] && dump_stats + echo -n " - echo TX " + count=$(get_counter ${ns2} "MPTcpExtEchoAddTx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$echo_tx_nr" ]; then + echo "[fail] got $count ADD_ADDR echo[s] TX, expected $echo_tx_nr" + fail_test + else + echo "[ ok ]" + fi } chk_rm_nr() @@ -1592,7 +1696,6 @@ chk_rm_nr() local invert local simult local count - local dump_stats local addr_ns=$ns1 local subflow_ns=$ns2 local extra_msg="" @@ -1614,82 +1717,89 @@ chk_rm_nr() fi printf "%-${nr_blank}s %s" " " "rm " - count=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmAddr | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$rm_addr_nr" ]; then + count=$(get_counter ${addr_ns} "MPTcpExtRmAddr") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$rm_addr_nr" ]; then echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - rmsf " - count=$(ip netns exec $subflow_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ -n "$simult" ]; then + count=$(get_counter ${subflow_ns} "MPTcpExtRmSubflow") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ -n "$simult" ]; then local cnt suffix - cnt=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') + cnt=$(get_counter ${addr_ns} "MPTcpExtRmSubflow") # in case of simult flush, the subflow removal count on each side is # unreliable - [ -z "$cnt" ] && cnt=0 count=$((count + cnt)) [ "$count" != "$rm_subflow_nr" ] && suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]" if [ $count -ge "$rm_subflow_nr" ] && \ [ "$count" -le "$((rm_subflow_nr *2 ))" ]; then - echo "[ ok ] $suffix" + echo -n "[ ok ] $suffix" else echo "[fail] got $count RM_SUBFLOW[s] expected in range [$rm_subflow_nr:$((rm_subflow_nr*2))]" fail_test - dump_stats=1 fi - return - fi - if [ "$count" != "$rm_subflow_nr" ]; then + elif [ "$count" != "$rm_subflow_nr" ]; then echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats - echo "$extra_msg" } +chk_rm_tx_nr() +{ + local rm_addr_tx_nr=$1 + + printf "%-${nr_blank}s %s" " " "rm TX " + count=$(get_counter ${ns2} "MPTcpExtRmAddrTx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$rm_addr_tx_nr" ]; then + echo "[fail] got $count RM_ADDR[s] expected $rm_addr_tx_nr" + fail_test + else + echo "[ ok ]" + fi +} + chk_prio_nr() { local mp_prio_nr_tx=$1 local mp_prio_nr_rx=$2 local count - local dump_stats printf "%-${nr_blank}s %s" " " "ptx" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mp_prio_nr_tx" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPPrioTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$mp_prio_nr_tx" ]; then echo "[fail] got $count MP_PRIO[s] TX expected $mp_prio_nr_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - prx " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mp_prio_nr_rx" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPPrioRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$mp_prio_nr_rx" ]; then echo "[fail] got $count MP_PRIO[s] RX expected $mp_prio_nr_rx" fail_test - dump_stats=1 else echo "[ ok ]" fi - - [ "${dump_stats}" = 1 ] && dump_stats } chk_subflow_nr() @@ -1721,37 +1831,31 @@ chk_subflow_nr() ss -N $ns1 -tOni ss -N $ns1 -tOni | grep token ip -n $ns1 mptcp endpoint - dump_stats fi } chk_mptcp_info() { - local nr_info=$1 - local info + local info1=$1 + local exp1=$2 + local info2=$3 + local exp2=$4 local cnt1 local cnt2 local dump_stats - if [[ $nr_info = "subflows_"* ]]; then - info="subflows" - nr_info=${nr_info:9} - else - echo "[fail] unsupported argument: $nr_info" - fail_test - return 1 - fi - - printf "%-${nr_blank}s %-30s" " " "mptcp_info $info=$nr_info" + printf "%-${nr_blank}s %-30s" " " "mptcp_info $info1:$info2=$exp1:$exp2" - cnt1=$(ss -N $ns1 -inmHM | grep "$info:" | - sed -n 's/.*\('"$info"':\)\([[:digit:]]*\).*$/\2/p;q') + cnt1=$(ss -N $ns1 -inmHM | grep "$info1:" | + sed -n 's/.*\('"$info1"':\)\([[:digit:]]*\).*$/\2/p;q') + cnt2=$(ss -N $ns2 -inmHM | grep "$info2:" | + sed -n 's/.*\('"$info2"':\)\([[:digit:]]*\).*$/\2/p;q') + # 'ss' only display active connections and counters that are not 0. [ -z "$cnt1" ] && cnt1=0 - cnt2=$(ss -N $ns2 -inmHM | grep "$info:" | - sed -n 's/.*\('"$info"':\)\([[:digit:]]*\).*$/\2/p;q') [ -z "$cnt2" ] && cnt2=0 - if [ "$cnt1" != "$nr_info" ] || [ "$cnt2" != "$nr_info" ]; then - echo "[fail] got $cnt1:$cnt2 $info expected $nr_info" + + if [ "$cnt1" != "$exp1" ] || [ "$cnt2" != "$exp2" ]; then + echo "[fail] got $cnt1:$cnt2 $info1:$info2 expected $exp1:$exp2" fail_test dump_stats=1 else @@ -1761,7 +1865,6 @@ chk_mptcp_info() if [ "$dump_stats" = 1 ]; then ss -N $ns1 -inmHM ss -N $ns2 -inmHM - dump_stats fi } @@ -1797,7 +1900,7 @@ wait_attempt_fail() while [ $time -lt $timeout_ms ]; do local cnt - cnt=$(ip netns exec $ns nstat -as TcpAttemptFails | grep TcpAttemptFails | awk '{print $2}') + cnt=$(get_counter ${ns} "TcpAttemptFails") [ "$cnt" = 1 ] && return 1 time=$((time + 100)) @@ -1885,41 +1988,41 @@ subflows_error_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 0 0 0 fi # multiple subflows, with subflow creation error - if reset "multi subflows, with failing subflow"; then + if reset_with_tcp_filter "multi subflows, with failing subflow" ns1 10.0.3.2 REJECT && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - filter_tcp_from $ns1 10.0.3.2 REJECT - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 fi # multiple subflows, with subflow timeout on MPJ - if reset "multi subflows, with subflow timeout"; then + if reset_with_tcp_filter "multi subflows, with subflow timeout" ns1 10.0.3.2 DROP && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - filter_tcp_from $ns1 10.0.3.2 DROP - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 fi # multiple subflows, check that the endpoint corresponding to # closed subflow (due to reset) is not reused if additional # subflows are added later - if reset "multi subflows, fair usage on close"; then + if reset_with_tcp_filter "multi subflows, fair usage on close" ns1 10.0.3.2 REJECT && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - filter_tcp_from $ns1 10.0.3.2 REJECT - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & + run_tests $ns1 $ns2 10.0.1.1 slow & # mpj subflow will be in TW after the reset wait_attempt_fail $ns2 @@ -1939,6 +2042,7 @@ signal_address_tests() pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 + chk_add_tx_nr 1 1 chk_add_nr 1 1 fi @@ -2017,12 +2121,19 @@ signal_address_tests() # the peer could possibly miss some addr notification, allow retransmission ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr 3 3 3 + run_tests $ns1 $ns2 10.0.1.1 slow - # the server will not signal the address terminating - # the MPC subflow - chk_add_nr 3 3 + # It is not directly linked to the commit introducing this + # symbol but for the parent one which is linked anyway. + if ! mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then + chk_join_nr 3 3 2 + chk_add_nr 4 4 + else + chk_join_nr 3 3 3 + # the server will not signal the address terminating + # the MPC subflow + chk_add_nr 3 3 + fi fi } @@ -2042,7 +2153,8 @@ link_failure_tests() pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow - run_tests $ns1 $ns2 10.0.1.1 1 + test_linkfail=1 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 chk_add_nr 1 1 chk_stale_nr $ns2 1 5 1 @@ -2057,7 +2169,8 @@ link_failure_tests() pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow - run_tests $ns1 $ns2 10.0.1.1 2 + test_linkfail=2 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 chk_add_nr 1 1 chk_stale_nr $ns2 1 -1 1 @@ -2070,9 +2183,9 @@ link_failure_tests() pm_nl_set_limits $ns1 0 2 pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal pm_nl_set_limits $ns2 1 2 - FAILING_LINKS="1" pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 1 + FAILING_LINKS="1" test_linkfail=1 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 chk_add_nr 1 1 chk_link_usage $ns2 ns2eth3 $cinsent 0 @@ -2086,8 +2199,8 @@ link_failure_tests() pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal pm_nl_set_limits $ns2 1 2 pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup - FAILING_LINKS="1 2" - run_tests $ns1 $ns2 10.0.1.1 1 + FAILING_LINKS="1 2" test_linkfail=1 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 chk_add_nr 1 1 chk_stale_nr $ns2 2 4 2 @@ -2102,8 +2215,8 @@ link_failure_tests() pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup - FAILING_LINKS="1 2" - run_tests $ns1 $ns2 10.0.1.1 2 + FAILING_LINKS="1 2" test_linkfail=2 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 chk_add_nr 1 1 chk_stale_nr $ns2 1 -1 2 @@ -2118,8 +2231,9 @@ add_addr_timeout_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 + chk_add_tx_nr 4 4 chk_add_nr 4 0 fi @@ -2128,7 +2242,7 @@ add_addr_timeout_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 1 1 1 chk_add_nr 4 0 fi @@ -2139,7 +2253,7 @@ add_addr_timeout_tests() pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_set_limits $ns2 2 2 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 speed_10 + run_tests $ns1 $ns2 10.0.1.1 speed_10 chk_join_nr 2 2 2 chk_add_nr 8 0 fi @@ -2150,7 +2264,7 @@ add_addr_timeout_tests() pm_nl_add_endpoint $ns1 10.0.12.1 flags signal pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_set_limits $ns2 2 2 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 speed_10 + run_tests $ns1 $ns2 10.0.1.1 speed_10 chk_join_nr 1 1 1 chk_add_nr 8 0 fi @@ -2163,8 +2277,10 @@ remove_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow + addr_nr_ns2=-1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 + chk_rm_tx_nr 1 chk_rm_nr 1 1 fi @@ -2174,7 +2290,8 @@ remove_tests() pm_nl_set_limits $ns2 0 2 pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -2 slow + addr_nr_ns2=-2 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 2 2 2 chk_rm_nr 2 2 fi @@ -2184,7 +2301,8 @@ remove_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow + addr_nr_ns1=-1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_add_nr 1 1 chk_rm_nr 1 1 invert @@ -2196,7 +2314,8 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_set_limits $ns2 1 2 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow + addr_nr_ns1=-1 addr_nr_ns2=-1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 2 2 2 chk_add_nr 1 1 chk_rm_nr 1 1 @@ -2209,7 +2328,8 @@ remove_tests() pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 speed_10 + addr_nr_ns1=-1 addr_nr_ns2=-2 \ + run_tests $ns1 $ns2 10.0.1.1 speed_10 chk_join_nr 3 3 3 chk_add_nr 1 1 chk_rm_nr 2 2 @@ -2222,7 +2342,8 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.4.1 flags signal pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -3 0 speed_10 + addr_nr_ns1=-3 \ + run_tests $ns1 $ns2 10.0.1.1 speed_10 chk_join_nr 3 3 3 chk_add_nr 3 3 chk_rm_nr 3 3 invert @@ -2235,7 +2356,8 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.14.1 flags signal pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -3 0 speed_10 + addr_nr_ns1=-3 \ + run_tests $ns1 $ns2 10.0.1.1 speed_10 chk_join_nr 1 1 1 chk_add_nr 3 3 chk_rm_nr 3 1 invert @@ -2248,7 +2370,8 @@ remove_tests() pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + addr_nr_ns1=-8 addr_nr_ns2=-8 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 3 3 3 chk_add_nr 1 1 chk_rm_nr 1 3 invert simult @@ -2261,9 +2384,16 @@ remove_tests() pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow id 150 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + addr_nr_ns1=-8 addr_nr_ns2=-8 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 3 3 3 - chk_rm_nr 0 3 simult + + if mptcp_lib_kversion_ge 5.18; then + chk_rm_tx_nr 0 + chk_rm_nr 0 3 simult + else + chk_rm_nr 3 3 + fi fi # addresses flush @@ -2273,7 +2403,8 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.4.1 flags signal pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + addr_nr_ns1=-8 addr_nr_ns2=-8 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 3 3 3 chk_add_nr 3 3 chk_rm_nr 3 3 invert simult @@ -2286,7 +2417,8 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.14.1 flags signal pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -8 0 slow + addr_nr_ns1=-8 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_add_nr 3 3 chk_rm_nr 3 1 invert @@ -2297,7 +2429,8 @@ remove_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -9 slow + addr_nr_ns2=-9 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_rm_nr 1 1 fi @@ -2307,7 +2440,8 @@ remove_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 -9 0 slow + addr_nr_ns1=-9 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_add_nr 1 1 chk_rm_nr 1 1 invert @@ -2320,7 +2454,8 @@ add_tests() if reset "add single subflow"; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 - run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow + addr_nr_ns2=1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 fi @@ -2328,7 +2463,8 @@ add_tests() if reset "add signal address"; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow + addr_nr_ns1=1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_add_nr 1 1 fi @@ -2337,7 +2473,8 @@ add_tests() if reset "add multiple subflows"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 - run_tests $ns1 $ns2 10.0.1.1 0 0 2 slow + addr_nr_ns2=2 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 2 2 2 fi @@ -2345,7 +2482,8 @@ add_tests() if reset "add multiple subflows IPv6"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 - run_tests $ns1 $ns2 dead:beef:1::1 0 0 2 slow + addr_nr_ns2=2 \ + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 2 2 2 fi @@ -2353,7 +2491,8 @@ add_tests() if reset "add multiple addresses IPv6"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 2 2 - run_tests $ns1 $ns2 dead:beef:1::1 0 2 0 slow + addr_nr_ns1=2 \ + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 2 2 2 chk_add_nr 2 2 fi @@ -2366,14 +2505,14 @@ ipv6_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 1 1 1 fi # add_address, unused IPv6 if reset "unused signal address IPv6"; then pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 0 0 0 chk_add_nr 1 1 fi @@ -2383,7 +2522,7 @@ ipv6_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 1 1 1 chk_add_nr 1 1 fi @@ -2393,7 +2532,8 @@ ipv6_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 dead:beef:1::1 0 -1 0 slow + addr_nr_ns1=-1 \ + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 1 1 1 chk_add_nr 1 1 chk_rm_nr 1 1 invert @@ -2405,7 +2545,8 @@ ipv6_tests() pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal pm_nl_set_limits $ns2 1 2 pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow - run_tests $ns1 $ns2 dead:beef:1::1 0 -1 -1 slow + addr_nr_ns1=-1 addr_nr_ns2=-1 \ + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 2 2 2 chk_add_nr 1 1 chk_rm_nr 1 1 @@ -2501,41 +2642,46 @@ v4mapped_tests() mixed_tests() { - if reset "IPv4 sockets do not use IPv6 addresses"; then + if reset "IPv4 sockets do not use IPv6 addresses" && + continue_if mptcp_lib_kversion_ge 6.3; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 0 0 0 fi # Need an IPv6 mptcp socket to allow subflows of both families - if reset "simult IPv4 and IPv6 subflows"; then + if reset "simult IPv4 and IPv6 subflows" && + continue_if mptcp_lib_kversion_ge 6.3; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns1 10.0.1.1 flags signal - run_tests $ns1 $ns2 dead:beef:2::1 0 0 0 slow + run_tests $ns1 $ns2 dead:beef:2::1 slow chk_join_nr 1 1 1 fi # cross families subflows will not be created even in fullmesh mode - if reset "simult IPv4 and IPv6 subflows, fullmesh 1x1"; then + if reset "simult IPv4 and IPv6 subflows, fullmesh 1x1" && + continue_if mptcp_lib_kversion_ge 6.3; then pm_nl_set_limits $ns1 0 4 pm_nl_set_limits $ns2 1 4 pm_nl_add_endpoint $ns2 dead:beef:2::2 flags subflow,fullmesh pm_nl_add_endpoint $ns1 10.0.1.1 flags signal - run_tests $ns1 $ns2 dead:beef:2::1 0 0 0 slow + run_tests $ns1 $ns2 dead:beef:2::1 slow chk_join_nr 1 1 1 fi # fullmesh still tries to create all the possibly subflows with # matching family - if reset "simult IPv4 and IPv6 subflows, fullmesh 2x2"; then + if reset "simult IPv4 and IPv6 subflows, fullmesh 2x2" && + continue_if mptcp_lib_kversion_ge 6.3; then pm_nl_set_limits $ns1 0 4 pm_nl_set_limits $ns2 2 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - run_tests $ns1 $ns2 dead:beef:1::1 0 0 fullmesh_1 slow + addr_nr_ns2=fullmesh_1 \ + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 4 4 4 fi } @@ -2543,63 +2689,75 @@ mixed_tests() backup_tests() { # single subflow, backup - if reset "single subflow, backup"; then + if reset "single subflow, backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup + sflags=nobackup \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_prio_nr 0 1 fi # single address, backup - if reset "single address, backup"; then + if reset "single address, backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + sflags=backup \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_add_nr 1 1 chk_prio_nr 1 1 fi # single address with port, backup - if reset "single address with port, backup"; then + if reset "single address with port, backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + sflags=backup \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_add_nr 1 1 chk_prio_nr 1 1 fi - if reset "mpc backup"; then + if reset "mpc backup" && + continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 0 0 0 chk_prio_nr 0 1 fi - if reset "mpc backup both sides"; then + if reset "mpc backup both sides" && + continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 0 0 0 chk_prio_nr 1 1 fi - if reset "mpc switch to backup"; then + if reset "mpc switch to backup" && + continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + sflags=backup \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 0 0 0 chk_prio_nr 0 1 fi - if reset "mpc switch to backup both sides"; then + if reset "mpc switch to backup both sides" && + continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + sflags=backup \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 0 0 0 chk_prio_nr 1 1 fi @@ -2622,38 +2780,41 @@ verify_listener_events() local family local saddr local sport + local name if [ $e_type = $LISTENER_CREATED ]; then - stdbuf -o0 -e0 printf "\t\t\t\t\t CREATE_LISTENER %s:%s"\ - $e_saddr $e_sport + name="LISTENER_CREATED" elif [ $e_type = $LISTENER_CLOSED ]; then - stdbuf -o0 -e0 printf "\t\t\t\t\t CLOSE_LISTENER %s:%s "\ - $e_saddr $e_sport + name="LISTENER_CLOSED" + else + name="$e_type" fi - type=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q') - family=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(family:\)\([[:digit:]]*\).*$/\2/p;q') - sport=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + printf "%-${nr_blank}s %s %s:%s " " " "$name" "$e_saddr" "$e_sport" + + if ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then + printf "[skip]: event not supported\n" + return + fi + + type=$(grep "type:$e_type," $evt | sed -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q') + family=$(grep "type:$e_type," $evt | sed -n 's/.*\(family:\)\([[:digit:]]*\).*$/\2/p;q') + sport=$(grep "type:$e_type," $evt | sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') if [ $family ] && [ $family = $AF_INET6 ]; then - saddr=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(saddr6:\)\([0-9a-f:.]*\).*$/\2/p;q') + saddr=$(grep "type:$e_type," $evt | sed -n 's/.*\(saddr6:\)\([0-9a-f:.]*\).*$/\2/p;q') else - saddr=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(saddr4:\)\([0-9.]*\).*$/\2/p;q') + saddr=$(grep "type:$e_type," $evt | sed -n 's/.*\(saddr4:\)\([0-9.]*\).*$/\2/p;q') fi if [ $type ] && [ $type = $e_type ] && [ $family ] && [ $family = $e_family ] && [ $saddr ] && [ $saddr = $e_saddr ] && [ $sport ] && [ $sport = $e_sport ]; then - stdbuf -o0 -e0 printf "[ ok ]\n" + echo "[ ok ]" return 0 fi fail_test - stdbuf -o0 -e0 printf "[fail]\n" + echo "[fail]" } add_addr_ports_tests() @@ -2685,7 +2846,8 @@ add_addr_ports_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow + addr_nr_ns1=-1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_add_nr 1 1 1 chk_rm_nr 1 1 invert @@ -2701,7 +2863,8 @@ add_addr_ports_tests() pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 pm_nl_set_limits $ns2 1 2 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow + addr_nr_ns1=-1 addr_nr_ns2=-1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 2 2 2 chk_add_nr 1 1 1 chk_rm_nr 1 1 @@ -2714,7 +2877,8 @@ add_addr_ports_tests() pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -8 -2 slow + addr_nr_ns1=-8 addr_nr_ns2=-2 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 3 3 3 chk_add_nr 1 1 chk_rm_nr 1 3 invert simult @@ -2916,7 +3080,8 @@ fullmesh_tests() pm_nl_set_limits $ns2 1 4 pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,fullmesh pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,fullmesh - run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow + addr_nr_ns1=1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 4 4 4 chk_add_nr 1 1 fi @@ -2928,7 +3093,8 @@ fullmesh_tests() pm_nl_set_limits $ns1 1 3 pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow + addr_nr_ns2=fullmesh_1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 3 3 3 chk_add_nr 1 1 fi @@ -2940,7 +3106,8 @@ fullmesh_tests() pm_nl_set_limits $ns1 2 5 pm_nl_set_limits $ns2 1 5 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow + addr_nr_ns2=fullmesh_2 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 5 5 5 chk_add_nr 1 1 fi @@ -2953,48 +3120,57 @@ fullmesh_tests() pm_nl_set_limits $ns1 2 4 pm_nl_set_limits $ns2 1 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow + addr_nr_ns2=fullmesh_2 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 4 4 4 chk_add_nr 1 1 fi # set fullmesh flag - if reset "set fullmesh flag test"; then + if reset "set fullmesh flag test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow pm_nl_set_limits $ns2 4 4 - run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow fullmesh + addr_nr_ns2=1 sflags=fullmesh \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 2 2 2 chk_rm_nr 0 1 fi # set nofullmesh flag - if reset "set nofullmesh flag test"; then + if reset "set nofullmesh flag test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow,fullmesh pm_nl_set_limits $ns2 4 4 - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow nofullmesh + addr_nr_ns2=fullmesh_1 sflags=nofullmesh \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 2 2 2 chk_rm_nr 0 1 fi # set backup,fullmesh flags - if reset "set backup,fullmesh flags test"; then + if reset "set backup,fullmesh flags test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow pm_nl_set_limits $ns2 4 4 - run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow backup,fullmesh + addr_nr_ns2=1 sflags=backup,fullmesh \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 2 2 2 chk_prio_nr 0 1 chk_rm_nr 0 1 fi # set nobackup,nofullmesh flags - if reset "set nobackup,nofullmesh flags test"; then + if reset "set nobackup,nofullmesh flags test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_set_limits $ns2 4 4 pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,backup,fullmesh - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup,nofullmesh + sflags=nobackup,nofullmesh \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 2 2 2 chk_prio_nr 0 1 chk_rm_nr 0 1 @@ -3003,15 +3179,17 @@ fullmesh_tests() fastclose_tests() { - if reset "fastclose test"; then - run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_client + if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then + test_linkfail=1024 addr_nr_ns2=fastclose_client \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 chk_fclose_nr 1 1 chk_rst_nr 1 1 invert fi - if reset "fastclose server test"; then - run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_server + if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then + test_linkfail=1024 addr_nr_ns2=fastclose_server \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 chk_fclose_nr 1 1 invert chk_rst_nr 1 1 @@ -3029,7 +3207,8 @@ fail_tests() { # single subflow if reset_with_fail "Infinite map" 1; then - run_tests $ns1 $ns2 10.0.1.1 128 + test_linkfail=128 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 +1 +0 1 0 1 "$(pedit_action_pkts)" chk_fail_nr 1 -1 invert fi @@ -3040,15 +3219,82 @@ fail_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 1024 + test_linkfail=1024 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 1 0 1 1 0 "$(pedit_action_pkts)" fi } +userspace_pm_add_addr() +{ + local addr=$1 + local id=$2 + local tk + + tk=$(grep "type:1," "$evts_ns1" | + sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q') + ip netns exec $ns1 ./pm_nl_ctl ann $addr token $tk id $id + sleep 1 +} + +userspace_pm_rm_sf_addr_ns1() +{ + local addr=$1 + local id=$2 + local tk sp da dp + + tk=$(grep "type:1," "$evts_ns1" | + sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q') + sp=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + da=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(daddr6:\)\([0-9a-f:.]*\).*$/\2/p;q') + dp=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q') + ip netns exec $ns1 ./pm_nl_ctl rem token $tk id $id + ip netns exec $ns1 ./pm_nl_ctl dsf lip "::ffff:$addr" \ + lport $sp rip $da rport $dp token $tk + wait_rm_addr $ns1 1 + wait_rm_sf $ns1 1 +} + +userspace_pm_add_sf() +{ + local addr=$1 + local id=$2 + local tk da dp + + tk=$(sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") + da=$(sed -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evts_ns2") + dp=$(sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") + ip netns exec $ns2 ./pm_nl_ctl csf lip $addr lid $id \ + rip $da rport $dp token $tk + sleep 1 +} + +userspace_pm_rm_sf_addr_ns2() +{ + local addr=$1 + local id=$2 + local tk da dp sp + + tk=$(sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") + da=$(sed -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evts_ns2") + dp=$(sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") + sp=$(grep "type:10" "$evts_ns2" | + sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + ip netns exec $ns2 ./pm_nl_ctl rem token $tk id $id + ip netns exec $ns2 ./pm_nl_ctl dsf lip $addr lport $sp \ + rip $da rport $dp token $tk + wait_rm_addr $ns2 1 + wait_rm_sf $ns2 1 +} + userspace_tests() { # userspace pm type prevents add_addr - if reset "userspace pm type prevents add_addr"; then + if reset "userspace pm type prevents add_addr" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 @@ -3059,7 +3305,8 @@ userspace_tests() fi # userspace pm type does not echo add_addr without daemon - if reset "userspace pm no echo w/o daemon"; then + if reset "userspace pm no echo w/o daemon" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 @@ -3070,7 +3317,8 @@ userspace_tests() fi # userspace pm type rejects join - if reset "userspace pm type rejects join"; then + if reset "userspace pm type rejects join" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 @@ -3080,7 +3328,8 @@ userspace_tests() fi # userspace pm type does not send join - if reset "userspace pm type does not send join"; then + if reset "userspace pm type does not send join" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 @@ -3090,62 +3339,87 @@ userspace_tests() fi # userspace pm type prevents mp_prio - if reset "userspace pm type prevents mp_prio"; then + if reset "userspace pm type prevents mp_prio" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + sflags=backup \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 0 chk_prio_nr 0 0 fi # userspace pm type prevents rm_addr - if reset "userspace pm type prevents rm_addr"; then + if reset "userspace pm type prevents rm_addr" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow + addr_nr_ns2=-1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 0 0 0 chk_rm_nr 0 0 fi # userspace pm add & remove address - if reset_with_events "userspace pm add & remove address"; then + if reset_with_events "userspace pm add & remove address" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 userspace_1 0 slow + run_tests $ns1 $ns2 10.0.1.1 speed_10 & + local tests_pid=$! + wait_mpj $ns1 + userspace_pm_add_addr 10.0.2.1 10 chk_join_nr 1 1 1 chk_add_nr 1 1 + chk_mptcp_info subflows 1 subflows 1 + chk_mptcp_info add_addr_signal 1 add_addr_accepted 1 + userspace_pm_rm_sf_addr_ns1 10.0.2.1 10 chk_rm_nr 1 1 invert + chk_mptcp_info subflows 0 subflows 0 kill_events_pids + wait $tests_pid fi # userspace pm create destroy subflow - if reset_with_events "userspace pm create destroy subflow"; then + if reset_with_events "userspace pm create destroy subflow" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 - run_tests $ns1 $ns2 10.0.1.1 0 0 userspace_1 slow + run_tests $ns1 $ns2 10.0.1.1 speed_10 & + local tests_pid=$! + wait_mpj $ns2 + userspace_pm_add_sf 10.0.3.2 20 chk_join_nr 1 1 1 - chk_rm_nr 0 1 + chk_mptcp_info subflows 1 subflows 1 + userspace_pm_rm_sf_addr_ns2 10.0.3.2 20 + chk_rm_nr 1 1 + chk_mptcp_info subflows 0 subflows 0 kill_events_pids + wait $tests_pid fi } endpoint_tests() { + # subflow_rebuild_header is needed to support the implicit flag # userspace pm type prevents add_addr - if reset "implicit EP"; then + if reset "implicit EP" && + mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 2 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow 2>/dev/null & + run_tests $ns1 $ns2 10.0.1.1 slow 2>/dev/null & wait_mpj $ns1 pm_nl_check_endpoint 1 "creation" \ $ns2 10.0.2.2 id 1 flags implicit + chk_mptcp_info subflows 1 subflows 1 + chk_mptcp_info add_addr_signal 1 add_addr_accepted 1 pm_nl_add_endpoint $ns2 10.0.2.2 id 33 pm_nl_check_endpoint 0 "ID change is prevented" \ @@ -3157,25 +3431,27 @@ endpoint_tests() kill_tests_wait fi - if reset "delete and re-add"; then + if reset "delete and re-add" && + mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 4 0 0 speed_20 2>/dev/null & + test_linkfail=4 \ + run_tests $ns1 $ns2 10.0.1.1 speed_20 2>/dev/null & wait_mpj $ns2 chk_subflow_nr needtitle "before delete" 2 - chk_mptcp_info subflows_1 + chk_mptcp_info subflows 1 subflows 1 pm_nl_del_endpoint $ns2 2 10.0.2.2 sleep 0.5 chk_subflow_nr "" "after delete" 1 - chk_mptcp_info subflows_0 + chk_mptcp_info subflows 0 subflows 0 pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow wait_mpj $ns2 chk_subflow_nr "" "after re-add" 2 - chk_mptcp_info subflows_1 + chk_mptcp_info subflows 1 subflows 1 kill_tests_wait fi } diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh new file mode 100644 index 0000000000000..f32045b23b893 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -0,0 +1,104 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 + +readonly KSFT_FAIL=1 +readonly KSFT_SKIP=4 + +# SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var can be set when validating all +# features using the last version of the kernel and the selftests to make sure +# a test is not being skipped by mistake. +mptcp_lib_expect_all_features() { + [ "${SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES:-}" = "1" ] +} + +# $1: msg +mptcp_lib_fail_if_expected_feature() { + if mptcp_lib_expect_all_features; then + echo "ERROR: missing feature: ${*}" + exit ${KSFT_FAIL} + fi + + return 1 +} + +# $1: file +mptcp_lib_has_file() { + local f="${1}" + + if [ -f "${f}" ]; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${f} file not found" +} + +mptcp_lib_check_mptcp() { + if ! mptcp_lib_has_file "/proc/sys/net/mptcp/enabled"; then + echo "SKIP: MPTCP support is not available" + exit ${KSFT_SKIP} + fi +} + +mptcp_lib_check_kallsyms() { + if ! mptcp_lib_has_file "/proc/kallsyms"; then + echo "SKIP: CONFIG_KALLSYMS is missing" + exit ${KSFT_SKIP} + fi +} + +# Internal: use mptcp_lib_kallsyms_has() instead +__mptcp_lib_kallsyms_has() { + local sym="${1}" + + mptcp_lib_check_kallsyms + + grep -q " ${sym}" /proc/kallsyms +} + +# $1: part of a symbol to look at, add '$' at the end for full name +mptcp_lib_kallsyms_has() { + local sym="${1}" + + if __mptcp_lib_kallsyms_has "${sym}"; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${sym} symbol not found" +} + +# $1: part of a symbol to look at, add '$' at the end for full name +mptcp_lib_kallsyms_doesnt_have() { + local sym="${1}" + + if ! __mptcp_lib_kallsyms_has "${sym}"; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${sym} symbol has been found" +} + +# !!!AVOID USING THIS!!! +# Features might not land in the expected version and features can be backported +# +# $1: kernel version, e.g. 6.3 +mptcp_lib_kversion_ge() { + local exp_maj="${1%.*}" + local exp_min="${1#*.}" + local v maj min + + # If the kernel has backported features, set this env var to 1: + if [ "${SELFTESTS_MPTCP_LIB_NO_KVERSION_CHECK:-}" = "1" ]; then + return 0 + fi + + v=$(uname -r | cut -d'.' -f1,2) + maj=${v%.*} + min=${v#*.} + + if [ "${maj}" -gt "${exp_maj}" ] || + { [ "${maj}" -eq "${exp_maj}" ] && [ "${min}" -ge "${exp_min}" ]; }; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "kernel version ${1} lower than ${v}" +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c index ae61f39556ca8..926b0be87c990 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -51,6 +51,11 @@ struct mptcp_info { __u8 mptcpi_local_addr_used; __u8 mptcpi_local_addr_max; __u8 mptcpi_csum_enabled; + __u32 mptcpi_retransmits; + __u64 mptcpi_bytes_retrans; + __u64 mptcpi_bytes_sent; + __u64 mptcpi_bytes_received; + __u64 mptcpi_bytes_acked; }; struct mptcp_subflow_data { @@ -81,12 +86,47 @@ struct mptcp_subflow_addrs { #define MPTCP_SUBFLOW_ADDRS 3 #endif +#ifndef MPTCP_FULL_INFO +struct mptcp_subflow_info { + __u32 id; + struct mptcp_subflow_addrs addrs; +}; + +struct mptcp_full_info { + __u32 size_tcpinfo_kernel; /* must be 0, set by kernel */ + __u32 size_tcpinfo_user; + __u32 size_sfinfo_kernel; /* must be 0, set by kernel */ + __u32 size_sfinfo_user; + __u32 num_subflows; /* must be 0, set by kernel (real subflow count) */ + __u32 size_arrays_user; /* max subflows that userspace is interested in; + * the buffers at subflow_info/tcp_info + * are respectively at least: + * size_arrays * size_sfinfo_user + * size_arrays * size_tcpinfo_user + * bytes wide + */ + __aligned_u64 subflow_info; + __aligned_u64 tcp_info; + struct mptcp_info mptcp_info; +}; + +#define MPTCP_FULL_INFO 4 +#endif + struct so_state { struct mptcp_info mi; + struct mptcp_info last_sample; + struct tcp_info tcp_info; + struct mptcp_subflow_addrs addrs; uint64_t mptcpi_rcv_delta; uint64_t tcpi_rcv_delta; + bool pkt_stats_avail; }; +#ifndef MIN +#define MIN(a, b) ((a) < (b) ? (a) : (b)) +#endif + static void die_perror(const char *msg) { perror(msg); @@ -318,8 +358,9 @@ static void do_getsockopt_mptcp_info(struct so_state *s, int fd, size_t w) if (ret < 0) die_perror("getsockopt MPTCP_INFO"); - assert(olen == sizeof(i)); + s->pkt_stats_avail = olen >= sizeof(i); + s->last_sample = i; if (s->mi.mptcpi_write_seq == 0) s->mi = i; @@ -349,13 +390,16 @@ static void do_getsockopt_tcp_info(struct so_state *s, int fd, size_t r, size_t xerror("getsockopt MPTCP_TCPINFO (tries %d, %m)"); assert(olen <= sizeof(ti)); - assert(ti.d.size_user == ti.d.size_kernel); - assert(ti.d.size_user == sizeof(struct tcp_info)); + assert(ti.d.size_kernel > 0); + assert(ti.d.size_user == + MIN(ti.d.size_kernel, sizeof(struct tcp_info))); assert(ti.d.num_subflows == 1); assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data)); olen -= sizeof(struct mptcp_subflow_data); - assert(olen == sizeof(struct tcp_info)); + assert(olen == ti.d.size_user); + + s->tcp_info = ti.ti[0]; if (ti.ti[0].tcpi_bytes_sent == w && ti.ti[0].tcpi_bytes_received == r) @@ -378,7 +422,7 @@ done: do_getsockopt_bogus_sf_data(fd, MPTCP_TCPINFO); } -static void do_getsockopt_subflow_addrs(int fd) +static void do_getsockopt_subflow_addrs(struct so_state *s, int fd) { struct sockaddr_storage remote, local; socklen_t olen, rlen, llen; @@ -401,13 +445,14 @@ static void do_getsockopt_subflow_addrs(int fd) die_perror("getsockopt MPTCP_SUBFLOW_ADDRS"); assert(olen <= sizeof(addrs)); - assert(addrs.d.size_user == addrs.d.size_kernel); - assert(addrs.d.size_user == sizeof(struct mptcp_subflow_addrs)); + assert(addrs.d.size_kernel > 0); + assert(addrs.d.size_user == + MIN(addrs.d.size_kernel, sizeof(struct mptcp_subflow_addrs))); assert(addrs.d.num_subflows == 1); assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data)); olen -= sizeof(struct mptcp_subflow_data); - assert(olen == sizeof(struct mptcp_subflow_addrs)); + assert(olen == addrs.d.size_user); llen = sizeof(local); ret = getsockname(fd, (struct sockaddr *)&local, &llen); @@ -425,6 +470,7 @@ static void do_getsockopt_subflow_addrs(int fd) assert(memcmp(&local, &addrs.addr[0].ss_local, sizeof(local)) == 0); assert(memcmp(&remote, &addrs.addr[0].ss_remote, sizeof(remote)) == 0); + s->addrs = addrs.addr[0]; memset(&addrs, 0, sizeof(addrs)); @@ -445,13 +491,70 @@ static void do_getsockopt_subflow_addrs(int fd) do_getsockopt_bogus_sf_data(fd, MPTCP_SUBFLOW_ADDRS); } +static void do_getsockopt_mptcp_full_info(struct so_state *s, int fd) +{ + size_t data_size = sizeof(struct mptcp_full_info); + struct mptcp_subflow_info sfinfo[2]; + struct tcp_info tcp_info[2]; + struct mptcp_full_info mfi; + socklen_t olen; + int ret; + + memset(&mfi, 0, data_size); + memset(tcp_info, 0, sizeof(tcp_info)); + memset(sfinfo, 0, sizeof(sfinfo)); + + mfi.size_tcpinfo_user = sizeof(struct tcp_info); + mfi.size_sfinfo_user = sizeof(struct mptcp_subflow_info); + mfi.size_arrays_user = 2; + mfi.subflow_info = (unsigned long)&sfinfo[0]; + mfi.tcp_info = (unsigned long)&tcp_info[0]; + olen = data_size; + + ret = getsockopt(fd, SOL_MPTCP, MPTCP_FULL_INFO, &mfi, &olen); + if (ret < 0) { + if (errno == EOPNOTSUPP) { + perror("MPTCP_FULL_INFO test skipped"); + return; + } + xerror("getsockopt MPTCP_FULL_INFO"); + } + + assert(olen <= data_size); + assert(mfi.size_tcpinfo_kernel > 0); + assert(mfi.size_tcpinfo_user == + MIN(mfi.size_tcpinfo_kernel, sizeof(struct tcp_info))); + assert(mfi.size_sfinfo_kernel > 0); + assert(mfi.size_sfinfo_user == + MIN(mfi.size_sfinfo_kernel, sizeof(struct mptcp_subflow_info))); + assert(mfi.num_subflows == 1); + + /* Tolerate future extension to mptcp_info struct and running newer + * test on top of older kernel. + * Anyway any kernel supporting MPTCP_FULL_INFO must at least include + * the following in mptcp_info. + */ + assert(olen > (socklen_t)__builtin_offsetof(struct mptcp_full_info, tcp_info)); + assert(mfi.mptcp_info.mptcpi_subflows == 0); + assert(mfi.mptcp_info.mptcpi_bytes_sent == s->last_sample.mptcpi_bytes_sent); + assert(mfi.mptcp_info.mptcpi_bytes_received == s->last_sample.mptcpi_bytes_received); + + assert(sfinfo[0].id == 1); + assert(tcp_info[0].tcpi_bytes_sent == s->tcp_info.tcpi_bytes_sent); + assert(tcp_info[0].tcpi_bytes_received == s->tcp_info.tcpi_bytes_received); + assert(!memcmp(&sfinfo->addrs, &s->addrs, sizeof(struct mptcp_subflow_addrs))); +} + static void do_getsockopts(struct so_state *s, int fd, size_t r, size_t w) { do_getsockopt_mptcp_info(s, fd, w); do_getsockopt_tcp_info(s, fd, r, w); - do_getsockopt_subflow_addrs(fd); + do_getsockopt_subflow_addrs(s, fd); + + if (r) + do_getsockopt_mptcp_full_info(s, fd); } static void connect_one_server(int fd, int pipefd) @@ -556,6 +659,23 @@ static void process_one_client(int fd, int pipefd) do_getsockopts(&s, fd, ret, ret2); if (s.mptcpi_rcv_delta != (uint64_t)ret + 1) xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64, s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - ret); + + /* be nice when running on top of older kernel */ + if (s.pkt_stats_avail) { + if (s.last_sample.mptcpi_bytes_sent != ret2) + xerror("mptcpi_bytes_sent %" PRIu64 ", expect %" PRIu64, + s.last_sample.mptcpi_bytes_sent, ret2, + s.last_sample.mptcpi_bytes_sent - ret2); + if (s.last_sample.mptcpi_bytes_received != ret) + xerror("mptcpi_bytes_received %" PRIu64 ", expect %" PRIu64, + s.last_sample.mptcpi_bytes_received, ret, + s.last_sample.mptcpi_bytes_received - ret); + if (s.last_sample.mptcpi_bytes_acked != ret) + xerror("mptcpi_bytes_acked %" PRIu64 ", expect %" PRIu64, + s.last_sample.mptcpi_bytes_acked, ret2, + s.last_sample.mptcpi_bytes_acked - ret2); + } + close(fd); } diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 1b70c0a304cef..f295a371ff148 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + ret=0 sin="" sout="" @@ -84,6 +86,9 @@ cleanup() rm -f "$sin" "$sout" } +mptcp_lib_check_mptcp +mptcp_lib_check_kallsyms + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" @@ -182,9 +187,14 @@ do_transfer() local_addr="0.0.0.0" fi + cmsg="TIMESTAMPNS" + if mptcp_lib_kallsyms_has "mptcp_ioctl$"; then + cmsg+=",TCPINQ" + fi + timeout ${timeout_test} \ ip netns exec ${listener_ns} \ - $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c TIMESTAMPNS,TCPINQ \ + $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \ ${local_addr} < "$sin" > "$sout" & local spid=$! @@ -192,7 +202,7 @@ do_transfer() timeout ${timeout_test} \ ip netns exec ${connector_ns} \ - $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c TIMESTAMPNS,TCPINQ \ + $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c "${cmsg}" \ $connect_addr < "$cin" > "$cout" & local cpid=$! @@ -249,6 +259,11 @@ do_mptcp_sockopt_tests() { local lret=0 + if ! mptcp_lib_kallsyms_has "mptcp_diag_fill_info$"; then + echo "INFO: MPTCP sockopt not supported: SKIP" + return + fi + ip netns exec "$ns_sbox" ./mptcp_sockopt lret=$? @@ -303,6 +318,11 @@ do_tcpinq_tests() { local lret=0 + if ! mptcp_lib_kallsyms_has "mptcp_ioctl$"; then + echo "INFO: TCP_INQ not supported: SKIP" + return + fi + local args for args in "-t tcp" "-r tcp"; do do_tcpinq_test $args diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 89839d1ff9d83..d02e0d63a8f91 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + ksft_skip=4 ret=0 @@ -34,6 +36,8 @@ cleanup() ip netns del $ns1 } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" @@ -69,8 +73,12 @@ check() } check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "defaults addr list" -check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 + +default_limits="$(ip netns exec $ns1 ./pm_nl_ctl limits)" +if mptcp_lib_expect_all_features; then + check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 subflows 2" "defaults limits" +fi ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.2 flags subflow dev lo @@ -117,12 +125,10 @@ ip netns exec $ns1 ./pm_nl_ctl flush check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "flush addrs" ip netns exec $ns1 ./pm_nl_ctl limits 9 1 -check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 2" "rcv addrs above hard limit" +check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "rcv addrs above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 1 9 -check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 2" "subflows above hard limit" +check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "subflows above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 8 8 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 8 @@ -172,14 +178,19 @@ subflow,backup 10.0.1.1" "set flags (backup)" ip netns exec $ns1 ./pm_nl_ctl set 10.0.1.1 flags nobackup check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow 10.0.1.1" " (nobackup)" + +# fullmesh support has been added later ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh -check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +if ip netns exec $ns1 ./pm_nl_ctl dump | grep -q "fullmesh" || + mptcp_lib_expect_all_features; then + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow,fullmesh 10.0.1.1" " (fullmesh)" -ip netns exec $ns1 ./pm_nl_ctl set id 1 flags nofullmesh -check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ + ip netns exec $ns1 ./pm_nl_ctl set id 1 flags nofullmesh + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow 10.0.1.1" " (nofullmesh)" -ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh -check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ + ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow,backup,fullmesh 10.0.1.1" " (backup,fullmesh)" +fi exit $ret diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 9f22f7e5027df..36a3c9d92e205 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + sec=$(date +%s) rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) ns1="ns1-$rndh" @@ -34,6 +36,8 @@ cleanup() done } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index b1eb7bce599dc..98d9e4d2d3fc2 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -1,10 +1,20 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + +mptcp_lib_check_mptcp +mptcp_lib_check_kallsyms + +if ! mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + echo "userspace pm tests are not supported by the kernel: SKIP" + exit ${KSFT_SKIP} +fi + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Cannot not run test without ip tool" - exit 1 + exit ${KSFT_SKIP} fi ANNOUNCED=6 # MPTCP_EVENT_ANNOUNCED @@ -905,6 +915,11 @@ test_listener() { print_title "Listener tests" + if ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then + stdbuf -o0 -e0 printf "LISTENER events \t[SKIP] Not supported\n" + return + fi + # Capture events on the network namespace running the client :>$client_evts diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index ee9a729827055..39a0e01f85547 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -76,7 +76,9 @@ struct sock_args { has_grp:1, has_expected_laddr:1, has_expected_raddr:1, - bind_test_only:1; + bind_test_only:1, + client_dontroute:1, + server_dontroute:1; unsigned short port; @@ -611,6 +613,18 @@ static int set_dsfield(int sd, int version, int dsfield) return 0; } +static int set_dontroute(int sd) +{ + unsigned int one = 1; + + if (setsockopt(sd, SOL_SOCKET, SO_DONTROUTE, &one, sizeof(one)) < 0) { + log_err_errno("setsockopt(SO_DONTROUTE)"); + return -1; + } + + return 0; +} + static int str_to_uint(const char *str, int min, int max, unsigned int *value) { int number; @@ -1351,6 +1365,14 @@ static int msock_init(struct sock_args *args, int server) if (set_dsfield(sd, AF_INET, args->dsfield) != 0) goto out_err; + if (server) { + if (args->server_dontroute && set_dontroute(sd) != 0) + goto out_err; + } else { + if (args->client_dontroute && set_dontroute(sd) != 0) + goto out_err; + } + if (args->dev && bind_to_device(sd, args->dev) != 0) goto out_err; else if (args->use_setsockopt && @@ -1482,6 +1504,9 @@ static int lsock_init(struct sock_args *args) if (set_dsfield(sd, args->version, args->dsfield) != 0) goto err; + if (args->server_dontroute && set_dontroute(sd) != 0) + goto err; + if (args->dev && bind_to_device(sd, args->dev) != 0) goto err; else if (args->use_setsockopt && @@ -1698,6 +1723,9 @@ static int connectsock(void *addr, socklen_t alen, struct sock_args *args) if (set_dsfield(sd, args->version, args->dsfield) != 0) goto err; + if (args->client_dontroute && set_dontroute(sd) != 0) + goto err; + if (args->dev && bind_to_device(sd, args->dev) != 0) goto err; else if (args->use_setsockopt && @@ -1905,10 +1933,14 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args) #define GETOPT_STR "sr:l:c:Q:p:t:g:P:DRn:M:X:m:d:I:BN:O:SUCi6xL:0:1:2:3:Fbqf" #define OPT_FORCE_BIND_KEY_IFINDEX 1001 #define OPT_NO_BIND_KEY_IFINDEX 1002 +#define OPT_CLIENT_DONTROUTE 1003 +#define OPT_SERVER_DONTROUTE 1004 static struct option long_opts[] = { {"force-bind-key-ifindex", 0, 0, OPT_FORCE_BIND_KEY_IFINDEX}, {"no-bind-key-ifindex", 0, 0, OPT_NO_BIND_KEY_IFINDEX}, + {"client-dontroute", 0, 0, OPT_CLIENT_DONTROUTE}, + {"server-dontroute", 0, 0, OPT_SERVER_DONTROUTE}, {0, 0, 0, 0} }; @@ -1954,6 +1986,12 @@ static void print_usage(char *prog) " --no-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX off\n" " --force-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX on\n" " (default: only if -I is passed)\n" + " --client-dontroute: don't use gateways for client socket: send\n" + " packets only if destination is on link (see\n" + " SO_DONTROUTE in socket(7))\n" + " --server-dontroute: don't use gateways for server socket: send\n" + " packets only if destination is on link (see\n" + " SO_DONTROUTE in socket(7))\n" "\n" " -g grp multicast group (e.g., 239.1.1.1)\n" " -i interactive mode (default is echo and terminate)\n" @@ -2076,6 +2114,12 @@ int main(int argc, char *argv[]) case OPT_NO_BIND_KEY_IFINDEX: args.bind_key_ifindex = -1; break; + case OPT_CLIENT_DONTROUTE: + args.client_dontroute = 1; + break; + case OPT_SERVER_DONTROUTE: + args.server_dontroute = 1; + break; case 'X': args.client_pw = optarg; break; diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 383ac6fc037d0..ba286d680fd9a 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -860,6 +860,7 @@ EOF fi # clean up any leftovers + echo 0 > /sys/bus/netdevsim/del_device $probed && rmmod netdevsim if [ $ret -ne 0 ]; then diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh index 1003119773e5d..f962823628119 100755 --- a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh @@ -232,10 +232,14 @@ setup_rt_networking() local nsname=rt-${rt} ip netns add ${nsname} + + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip link set veth-rt-${rt} netns ${nsname} ip -netns ${nsname} link set veth-rt-${rt} name veth0 - ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 + ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad ip -netns ${nsname} link set veth0 up ip -netns ${nsname} link set lo up @@ -254,6 +258,12 @@ setup_hs() # set the networking for the host ip netns add ${hsname} + + # disable the rp_filter otherwise the kernel gets confused about how + # to route decap ipv4 packets. + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip -netns ${hsname} link add veth0 type veth peer name ${rtveth} ip -netns ${hsname} link set ${rtveth} netns ${rtname} ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hs}/24 dev veth0 @@ -272,11 +282,6 @@ setup_hs() ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.proxy_arp=1 - # disable the rp_filter otherwise the kernel gets confused about how - # to route decap ipv4 packets. - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.rp_filter=0 - ip netns exec ${rtname} sh -c "echo 1 > /proc/sys/net/vrf/strict_mode" } diff --git a/tools/testing/selftests/net/test_vxlan_nolocalbypass.sh b/tools/testing/selftests/net/test_vxlan_nolocalbypass.sh new file mode 100755 index 0000000000000..f75212bf142cd --- /dev/null +++ b/tools/testing/selftests/net/test_vxlan_nolocalbypass.sh @@ -0,0 +1,240 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test is for checking the [no]localbypass VXLAN device option. The test +# configures two VXLAN devices in the same network namespace and a tc filter on +# the loopback device that drops encapsulated packets. The test sends packets +# from the first VXLAN device and verifies that by default these packets are +# received by the second VXLAN device. The test then enables the nolocalbypass +# option and verifies that packets are no longer received by the second VXLAN +# device. + +ret=0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +TESTS=" + nolocalbypass +" +VERBOSE=0 +PAUSE_ON_FAIL=no +PAUSE=no + +################################################################################ +# Utilities + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf "TEST: %-60s [ OK ]\n" "${msg}" + nsuccess=$((nsuccess+1)) + else + ret=1 + nfail=$((nfail+1)) + printf "TEST: %-60s [FAIL]\n" "${msg}" + if [ "$VERBOSE" = "1" ]; then + echo " rc=$rc, expected $expected" + fi + + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi + + if [ "${PAUSE}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + + [ "$VERBOSE" = "1" ] && echo +} + +run_cmd() +{ + local cmd="$1" + local out + local stderr="2>/dev/null" + + if [ "$VERBOSE" = "1" ]; then + printf "COMMAND: $cmd\n" + stderr= + fi + + out=$(eval $cmd $stderr) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo " $out" + fi + + return $rc +} + +tc_check_packets() +{ + local ns=$1; shift + local id=$1; shift + local handle=$1; shift + local count=$1; shift + local pkts + + sleep 0.1 + pkts=$(tc -n $ns -j -s filter show $id \ + | jq ".[] | select(.options.handle == $handle) | \ + .options.actions[0].stats.packets") + [[ $pkts == $count ]] +} + +################################################################################ +# Setup + +setup() +{ + ip netns add ns1 + + ip -n ns1 link set dev lo up + ip -n ns1 address add 192.0.2.1/32 dev lo + ip -n ns1 address add 198.51.100.1/32 dev lo + + ip -n ns1 link add name vx0 up type vxlan id 100 local 198.51.100.1 \ + dstport 4789 nolearning + ip -n ns1 link add name vx1 up type vxlan id 100 dstport 4790 +} + +cleanup() +{ + ip netns del ns1 &> /dev/null +} + +################################################################################ +# Tests + +nolocalbypass() +{ + local smac=00:01:02:03:04:05 + local dmac=00:0a:0b:0c:0d:0e + + run_cmd "bridge -n ns1 fdb add $dmac dev vx0 self static dst 192.0.2.1 port 4790" + + run_cmd "tc -n ns1 qdisc add dev vx1 clsact" + run_cmd "tc -n ns1 filter add dev vx1 ingress pref 1 handle 101 proto all flower src_mac $smac dst_mac $dmac action pass" + + run_cmd "tc -n ns1 qdisc add dev lo clsact" + run_cmd "tc -n ns1 filter add dev lo ingress pref 1 handle 101 proto ip flower ip_proto udp dst_port 4790 action drop" + + run_cmd "ip -n ns1 -d -j link show dev vx0 | jq -e '.[][\"linkinfo\"][\"info_data\"][\"localbypass\"] == true'" + log_test $? 0 "localbypass enabled" + + run_cmd "ip netns exec ns1 mausezahn vx0 -a $smac -b $dmac -c 1 -p 100 -q" + + tc_check_packets "ns1" "dev vx1 ingress" 101 1 + log_test $? 0 "Packet received by local VXLAN device - localbypass" + + run_cmd "ip -n ns1 link set dev vx0 type vxlan nolocalbypass" + + run_cmd "ip -n ns1 -d -j link show dev vx0 | jq -e '.[][\"linkinfo\"][\"info_data\"][\"localbypass\"] == false'" + log_test $? 0 "localbypass disabled" + + run_cmd "ip netns exec ns1 mausezahn vx0 -a $smac -b $dmac -c 1 -p 100 -q" + + tc_check_packets "ns1" "dev vx1 ingress" 101 1 + log_test $? 0 "Packet not received by local VXLAN device - nolocalbypass" + + run_cmd "ip -n ns1 link set dev vx0 type vxlan localbypass" + + run_cmd "ip -n ns1 -d -j link show dev vx0 | jq -e '.[][\"linkinfo\"][\"info_data\"][\"localbypass\"] == true'" + log_test $? 0 "localbypass enabled" + + run_cmd "ip netns exec ns1 mausezahn vx0 -a $smac -b $dmac -c 1 -p 100 -q" + + tc_check_packets "ns1" "dev vx1 ingress" 101 2 + log_test $? 0 "Packet received by local VXLAN device - localbypass" +} + +################################################################################ +# Usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -t <test> Test(s) to run (default: all) + (options: $TESTS) + -p Pause on fail + -P Pause after each test before cleanup + -v Verbose mode (show commands and output) +EOF +} + +################################################################################ +# Main + +trap cleanup EXIT + +while getopts ":t:pPvh" opt; do + case $opt in + t) TESTS=$OPTARG ;; + p) PAUSE_ON_FAIL=yes;; + P) PAUSE=yes;; + v) VERBOSE=$(($VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +# Make sure we don't pause twice. +[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit $ksft_skip; +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +if [ ! -x "$(command -v bridge)" ]; then + echo "SKIP: Could not run test without bridge tool" + exit $ksft_skip +fi + +if [ ! -x "$(command -v mausezahn)" ]; then + echo "SKIP: Could not run test without mausezahn tool" + exit $ksft_skip +fi + +if [ ! -x "$(command -v jq)" ]; then + echo "SKIP: Could not run test without jq tool" + exit $ksft_skip +fi + +ip link help vxlan 2>&1 | grep -q "localbypass" +if [ $? -ne 0 ]; then + echo "SKIP: iproute2 ip too old, missing VXLAN nolocalbypass support" + exit $ksft_skip +fi + +cleanup + +for t in $TESTS +do + setup; $t; cleanup; +done + +if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} +fi + +exit $ret diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index e699548d4247d..a3c57004344c6 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -15,6 +15,7 @@ #include <linux/tcp.h> #include <linux/socket.h> +#include <sys/epoll.h> #include <sys/types.h> #include <sys/sendfile.h> #include <sys/socket.h> @@ -25,6 +26,8 @@ #define TLS_PAYLOAD_MAX_LEN 16384 #define SOL_TLS 282 +static int fips_enabled; + struct tls_crypto_info_keys { union { struct tls12_crypto_info_aes_gcm_128 aes128; @@ -235,7 +238,7 @@ FIXTURE_VARIANT(tls) { uint16_t tls_version; uint16_t cipher_type; - bool nopad; + bool nopad, fips_non_compliant; }; FIXTURE_VARIANT_ADD(tls, 12_aes_gcm) @@ -254,24 +257,28 @@ FIXTURE_VARIANT_ADD(tls, 12_chacha) { .tls_version = TLS_1_2_VERSION, .cipher_type = TLS_CIPHER_CHACHA20_POLY1305, + .fips_non_compliant = true, }; FIXTURE_VARIANT_ADD(tls, 13_chacha) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_CHACHA20_POLY1305, + .fips_non_compliant = true, }; FIXTURE_VARIANT_ADD(tls, 13_sm4_gcm) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_SM4_GCM, + .fips_non_compliant = true, }; FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_SM4_CCM, + .fips_non_compliant = true, }; FIXTURE_VARIANT_ADD(tls, 12_aes_ccm) @@ -311,6 +318,9 @@ FIXTURE_SETUP(tls) int one = 1; int ret; + if (fips_enabled && variant->fips_non_compliant) + SKIP(return, "Unsupported cipher in FIPS mode"); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12); @@ -1637,6 +1647,136 @@ TEST_F(tls_err, timeo) } } +TEST_F(tls_err, poll_partial_rec) +{ + struct pollfd pfd = { }; + ssize_t rec_len; + char rec[256]; + char buf[128]; + + if (self->notls) + SKIP(return, "no TLS support"); + + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 1), 0); + + memrnd(buf, sizeof(buf)); + EXPECT_EQ(send(self->fd, buf, sizeof(buf), 0), sizeof(buf)); + rec_len = recv(self->cfd, rec, sizeof(rec), 0); + EXPECT_GT(rec_len, sizeof(buf)); + + /* Write 100B, not the full record ... */ + EXPECT_EQ(send(self->fd2, rec, 100, 0), 100); + /* ... no full record should mean no POLLIN */ + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 1), 0); + /* Now write the rest, and it should all pop out of the other end. */ + EXPECT_EQ(send(self->fd2, rec + 100, rec_len - 100, 0), rec_len - 100); + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 1), 1); + EXPECT_EQ(recv(self->cfd2, rec, sizeof(rec), 0), sizeof(buf)); + EXPECT_EQ(memcmp(buf, rec, sizeof(buf)), 0); +} + +TEST_F(tls_err, epoll_partial_rec) +{ + struct epoll_event ev, events[10]; + ssize_t rec_len; + char rec[256]; + char buf[128]; + int epollfd; + + if (self->notls) + SKIP(return, "no TLS support"); + + epollfd = epoll_create1(0); + ASSERT_GE(epollfd, 0); + + memset(&ev, 0, sizeof(ev)); + ev.events = EPOLLIN; + ev.data.fd = self->cfd2; + ASSERT_GE(epoll_ctl(epollfd, EPOLL_CTL_ADD, self->cfd2, &ev), 0); + + EXPECT_EQ(epoll_wait(epollfd, events, 10, 0), 0); + + memrnd(buf, sizeof(buf)); + EXPECT_EQ(send(self->fd, buf, sizeof(buf), 0), sizeof(buf)); + rec_len = recv(self->cfd, rec, sizeof(rec), 0); + EXPECT_GT(rec_len, sizeof(buf)); + + /* Write 100B, not the full record ... */ + EXPECT_EQ(send(self->fd2, rec, 100, 0), 100); + /* ... no full record should mean no POLLIN */ + EXPECT_EQ(epoll_wait(epollfd, events, 10, 0), 0); + /* Now write the rest, and it should all pop out of the other end. */ + EXPECT_EQ(send(self->fd2, rec + 100, rec_len - 100, 0), rec_len - 100); + EXPECT_EQ(epoll_wait(epollfd, events, 10, 0), 1); + EXPECT_EQ(recv(self->cfd2, rec, sizeof(rec), 0), sizeof(buf)); + EXPECT_EQ(memcmp(buf, rec, sizeof(buf)), 0); + + close(epollfd); +} + +TEST_F(tls_err, poll_partial_rec_async) +{ + struct pollfd pfd = { }; + ssize_t rec_len; + char rec[256]; + char buf[128]; + char token; + int p[2]; + int ret; + + if (self->notls) + SKIP(return, "no TLS support"); + + ASSERT_GE(pipe(p), 0); + + memrnd(buf, sizeof(buf)); + EXPECT_EQ(send(self->fd, buf, sizeof(buf), 0), sizeof(buf)); + rec_len = recv(self->cfd, rec, sizeof(rec), 0); + EXPECT_GT(rec_len, sizeof(buf)); + + ret = fork(); + ASSERT_GE(ret, 0); + + if (ret) { + int status, pid2; + + close(p[1]); + usleep(1000); /* Give child a head start */ + + EXPECT_EQ(send(self->fd2, rec, 100, 0), 100); + + EXPECT_EQ(read(p[0], &token, 1), 1); /* Barrier #1 */ + + EXPECT_EQ(send(self->fd2, rec + 100, rec_len - 100, 0), + rec_len - 100); + + pid2 = wait(&status); + EXPECT_EQ(pid2, ret); + EXPECT_EQ(status, 0); + } else { + close(p[0]); + + /* Child should sleep in poll(), never get a wake */ + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 5), 0); + + EXPECT_EQ(write(p[1], &token, 1), 1); /* Barrier #1 */ + + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 5), 1); + + exit(!_metadata->passed); + } +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; @@ -1865,4 +2005,17 @@ TEST(prequeue) { close(cfd); } +static void __attribute__((constructor)) fips_check(void) { + int res; + FILE *f; + + f = fopen("/proc/sys/crypto/fips_enabled", "r"); + if (f) { + res = fscanf(f, "%d", &fips_enabled); + if (res != 1) + ksft_print_msg("ERROR: Couldn't read /proc/sys/crypto/fips_enabled\n"); + fclose(f); + } +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/vrf-xfrm-tests.sh b/tools/testing/selftests/net/vrf-xfrm-tests.sh index 184da81f554ff..452638ae8aed8 100755 --- a/tools/testing/selftests/net/vrf-xfrm-tests.sh +++ b/tools/testing/selftests/net/vrf-xfrm-tests.sh @@ -264,60 +264,60 @@ setup_xfrm() ip -netns host1 xfrm state add src ${HOST1_4} dst ${HOST2_4} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_4} dst ${h2_4} ${devarg} ip -netns host2 xfrm state add src ${HOST1_4} dst ${HOST2_4} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_4} dst ${h2_4} ip -netns host1 xfrm state add src ${HOST2_4} dst ${HOST1_4} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_4} dst ${h1_4} ${devarg} ip -netns host2 xfrm state add src ${HOST2_4} dst ${HOST1_4} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_4} dst ${h1_4} ip -6 -netns host1 xfrm state add src ${HOST1_6} dst ${HOST2_6} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_6} dst ${h2_6} ${devarg} ip -6 -netns host2 xfrm state add src ${HOST1_6} dst ${HOST2_6} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_6} dst ${h2_6} ip -6 -netns host1 xfrm state add src ${HOST2_6} dst ${HOST1_6} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_6} dst ${h1_6} ${devarg} ip -6 -netns host2 xfrm state add src ${HOST2_6} dst ${HOST1_6} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_6} dst ${h1_6} } diff --git a/tools/testing/selftests/nolibc/.gitignore b/tools/testing/selftests/nolibc/.gitignore index 4696df589d68e..52f613cdad547 100644 --- a/tools/testing/selftests/nolibc/.gitignore +++ b/tools/testing/selftests/nolibc/.gitignore @@ -1,4 +1,5 @@ /initramfs/ +/libc-test /nolibc-test /run.out /sysroot/ diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index bbce57420465c..1b7b3c82f8add 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -64,7 +64,7 @@ QEMU_ARGS_mips = -M malta -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_riscv = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_s390 = -M s390-ccw-virtio -m 1G -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_loongarch = -M virt -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS = $(QEMU_ARGS_$(ARCH)) +QEMU_ARGS = $(QEMU_ARGS_$(ARCH)) $(QEMU_ARGS_EXTRA) # OUTPUT is only set when run from the main makefile, otherwise # it defaults to this nolibc directory. @@ -76,16 +76,12 @@ else Q=@ endif -CFLAGS_STACKPROTECTOR = -DNOLIBC_STACKPROTECTOR \ - $(call cc-option,-mstack-protector-guard=global) \ - $(call cc-option,-fstack-protector-all) -CFLAGS_STKP_i386 = $(CFLAGS_STACKPROTECTOR) -CFLAGS_STKP_x86_64 = $(CFLAGS_STACKPROTECTOR) -CFLAGS_STKP_x86 = $(CFLAGS_STACKPROTECTOR) CFLAGS_s390 = -m64 -CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables \ +CFLAGS_mips = -EL +CFLAGS_STACKPROTECTOR ?= $(call cc-option,-mstack-protector-guard=global $(call cc-option,-fstack-protector-all)) +CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables -std=c89 \ $(call cc-option,-fno-stack-protector) \ - $(CFLAGS_STKP_$(ARCH)) $(CFLAGS_$(ARCH)) + $(CFLAGS_$(ARCH)) $(CFLAGS_STACKPROTECTOR) LDFLAGS := -s help: @@ -94,6 +90,7 @@ help: @echo " help this help" @echo " sysroot create the nolibc sysroot here (uses \$$ARCH)" @echo " nolibc-test build the executable (uses \$$CC and \$$CROSS_COMPILE)" + @echo " libc-test build an executable using the compiler's default libc instead" @echo " run-user runs the executable under QEMU (uses \$$ARCH, \$$TEST)" @echo " initramfs prepare the initramfs with nolibc-test" @echo " defconfig create a fresh new default config (uses \$$ARCH)" @@ -128,10 +125,16 @@ nolibc-test: nolibc-test.c sysroot/$(ARCH)/include $(QUIET_CC)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ \ -nostdlib -static -Isysroot/$(ARCH)/include $< -lgcc +libc-test: nolibc-test.c + $(QUIET_CC)$(CC) -o $@ $< + # qemu user-land test run-user: nolibc-test $(Q)qemu-$(QEMU_ARCH) ./nolibc-test > "$(CURDIR)/run.out" || : - $(Q)grep -w FAIL "$(CURDIR)/run.out" && echo "See all results in $(CURDIR)/run.out" || echo "$$(grep -c ^[0-9].*OK $(CURDIR)/run.out) test(s) passed." + $(Q)awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{f++} /\[SKIPPED\][\r]*$$/{s++} \ + END{ printf("%d test(s) passed, %d skipped, %d failed.", p, s, f); \ + if (s+f > 0) printf(" See all results in %s\n", ARGV[1]); else print; }' \ + $(CURDIR)/run.out initramfs: nolibc-test $(QUIET_MKDIR)mkdir -p initramfs @@ -147,18 +150,26 @@ kernel: initramfs # run the tests after building the kernel run: kernel $(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(srctree)/$(IMAGE)" -serial stdio $(QEMU_ARGS) > "$(CURDIR)/run.out" - $(Q)grep -w FAIL "$(CURDIR)/run.out" && echo "See all results in $(CURDIR)/run.out" || echo "$$(grep -c ^[0-9].*OK $(CURDIR)/run.out) test(s) passed." + $(Q)awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{f++} /\[SKIPPED\][\r]*$$/{s++} \ + END{ printf("%d test(s) passed, %d skipped, %d failed.", p, s, f); \ + if (s+f > 0) printf(" See all results in %s\n", ARGV[1]); else print; }' \ + $(CURDIR)/run.out # re-run the tests from an existing kernel rerun: $(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(srctree)/$(IMAGE)" -serial stdio $(QEMU_ARGS) > "$(CURDIR)/run.out" - $(Q)grep -w FAIL "$(CURDIR)/run.out" && echo "See all results in $(CURDIR)/run.out" || echo "$$(grep -c ^[0-9].*OK $(CURDIR)/run.out) test(s) passed." + $(Q)awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{f++} /\[SKIPPED\][\r]*$$/{s++} \ + END{ printf("%d test(s) passed, %d skipped, %d failed.", p, s, f); \ + if (s+f > 0) printf(" See all results in %s\n", ARGV[1]); else print; }' \ + $(CURDIR)/run.out clean: $(call QUIET_CLEAN, sysroot) $(Q)rm -rf sysroot $(call QUIET_CLEAN, nolibc-test) $(Q)rm -f nolibc-test + $(call QUIET_CLEAN, libc-test) + $(Q)rm -f libc-test $(call QUIET_CLEAN, initramfs) $(Q)rm -rf initramfs $(call QUIET_CLEAN, run.out) diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index 21bacc928bf7b..486334981e601 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -1,10 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ #define _GNU_SOURCE -/* platform-specific include files coming from the compiler */ -#include <limits.h> - /* libc-specific include files * The program may be built in 3 ways: * $(CC) -nostdlib -include /path/to/nolibc.h => NOLIBC already defined @@ -20,7 +17,9 @@ #include <linux/reboot.h> #include <sys/io.h> #include <sys/ioctl.h> +#include <sys/mman.h> #include <sys/mount.h> +#include <sys/prctl.h> #include <sys/reboot.h> #include <sys/stat.h> #include <sys/syscall.h> @@ -34,7 +33,10 @@ #include <sched.h> #include <signal.h> #include <stdarg.h> +#include <stddef.h> +#include <stdint.h> #include <unistd.h> +#include <limits.h> #endif #endif @@ -43,8 +45,8 @@ char **environ; /* definition of a series of tests */ struct test { - const char *name; // test name - int (*func)(int min, int max); // handler + const char *name; /* test name */ + int (*func)(int min, int max); /* handler */ }; #ifndef _NOLIBC_STDLIB_H @@ -103,24 +105,32 @@ const char *errorname(int err) CASE_ERR(EDOM); CASE_ERR(ERANGE); CASE_ERR(ENOSYS); + CASE_ERR(EOVERFLOW); default: return itoa(err); } } +static void putcharn(char c, size_t n) +{ + char buf[64]; + + memset(buf, c, n); + buf[n] = '\0'; + fputs(buf, stdout); +} + static int pad_spc(int llen, int cnt, const char *fmt, ...) { va_list args; - int len; int ret; - for (len = 0; len < cnt - llen; len++) - putchar(' '); + putcharn(' ', cnt - llen); va_start(args, fmt); ret = vfprintf(stdout, fmt, args); va_end(args); - return ret < 0 ? ret : ret + len; + return ret < 0 ? ret : ret + cnt - llen; } /* The tests below are intended to be used by the macroes, which evaluate @@ -162,7 +172,7 @@ static int expect_eq(uint64_t expr, int llen, uint64_t val) { int ret = !(expr == val); - llen += printf(" = %lld ", expr); + llen += printf(" = %lld ", (long long)expr); pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); return ret; } @@ -290,18 +300,24 @@ static int expect_sysne(int expr, int llen, int val) } +#define EXPECT_SYSER2(cond, expr, expret, experr1, experr2) \ + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_syserr2(expr, expret, experr1, experr2, llen); } while (0) + #define EXPECT_SYSER(cond, expr, expret, experr) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_syserr(expr, expret, experr, llen); } while (0) + EXPECT_SYSER2(cond, expr, expret, experr, 0) -static int expect_syserr(int expr, int expret, int experr, int llen) +static int expect_syserr2(int expr, int expret, int experr1, int experr2, int llen) { int ret = 0; int _errno = errno; llen += printf(" = %d %s ", expr, errorname(_errno)); - if (expr != expret || _errno != experr) { + if (expr != expret || (_errno != experr1 && _errno != experr2)) { ret = 1; - llen += printf(" != (%d %s) ", expret, errorname(experr)); + if (experr2 == 0) + llen += printf(" != (%d %s) ", expret, errorname(experr1)); + else + llen += printf(" != (%d %s %s) ", expret, errorname(experr1), errorname(experr2)); llen += pad_spc(llen, 64, "[FAIL]\n"); } else { llen += pad_spc(llen, 64, " [OK]\n"); @@ -471,11 +487,60 @@ static int test_getpagesize(void) return !c; } +static int test_fork(void) +{ + int status; + pid_t pid; + + /* flush the printf buffer to avoid child flush it */ + fflush(stdout); + fflush(stderr); + + pid = fork(); + + switch (pid) { + case -1: + return 1; + + case 0: + exit(123); + + default: + pid = waitpid(pid, &status, 0); + + return pid == -1 || !WIFEXITED(status) || WEXITSTATUS(status) != 123; + } +} + +static int test_stat_timestamps(void) +{ + struct stat st; + + if (sizeof(st.st_atim.tv_sec) != sizeof(st.st_atime)) + return 1; + + if (stat("/proc/self/", &st)) + return 1; + + if (st.st_atim.tv_sec != st.st_atime || st.st_atim.tv_nsec > 1000000000) + return 1; + + if (st.st_mtim.tv_sec != st.st_mtime || st.st_mtim.tv_nsec > 1000000000) + return 1; + + if (st.st_ctim.tv_sec != st.st_ctime || st.st_ctim.tv_nsec > 1000000000) + return 1; + + return 0; +} + /* Run syscall tests between IDs <min> and <max>. * Return 0 on success, non-zero on failure. */ int run_syscall(int min, int max) { + struct timeval tv; + struct timezone tz; struct stat stat_buf; int euid0; int proc; @@ -491,7 +556,7 @@ int run_syscall(int min, int max) euid0 = geteuid() == 0; for (test = min; test >= 0 && test <= max; test++) { - int llen = 0; // line length + int llen = 0; /* line length */ /* avoid leaving empty lines below, this will insert holes into * test numbers. @@ -527,14 +592,11 @@ int run_syscall(int min, int max) CASE_TEST(dup3_0); tmp = dup3(0, 100, 0); EXPECT_SYSNE(1, tmp, -1); close(tmp); break; CASE_TEST(dup3_m1); tmp = dup3(-1, 100, 0); EXPECT_SYSER(1, tmp, -1, EBADF); if (tmp != -1) close(tmp); break; CASE_TEST(execve_root); EXPECT_SYSER(1, execve("/", (char*[]){ [0] = "/", [1] = NULL }, NULL), -1, EACCES); break; + CASE_TEST(fork); EXPECT_SYSZR(1, test_fork()); break; CASE_TEST(getdents64_root); EXPECT_SYSNE(1, test_getdents64("/"), -1); break; CASE_TEST(getdents64_null); EXPECT_SYSER(1, test_getdents64("/dev/null"), -1, ENOTDIR); break; - CASE_TEST(gettimeofday_null); EXPECT_SYSZR(1, gettimeofday(NULL, NULL)); break; -#ifdef NOLIBC - CASE_TEST(gettimeofday_bad1); EXPECT_SYSER(1, gettimeofday((void *)1, NULL), -1, EFAULT); break; - CASE_TEST(gettimeofday_bad2); EXPECT_SYSER(1, gettimeofday(NULL, (void *)1), -1, EFAULT); break; - CASE_TEST(gettimeofday_bad2); EXPECT_SYSER(1, gettimeofday(NULL, (void *)1), -1, EFAULT); break; -#endif + CASE_TEST(gettimeofday_tv); EXPECT_SYSZR(1, gettimeofday(&tv, NULL)); break; + CASE_TEST(gettimeofday_tv_tz);EXPECT_SYSZR(1, gettimeofday(&tv, &tz)); break; CASE_TEST(getpagesize); EXPECT_SYSZR(1, test_getpagesize()); break; CASE_TEST(ioctl_tiocinq); EXPECT_SYSZR(1, ioctl(0, TIOCINQ, &tmp)); break; CASE_TEST(ioctl_tiocinq); EXPECT_SYSZR(1, ioctl(0, TIOCINQ, &tmp)); break; @@ -550,6 +612,7 @@ int run_syscall(int min, int max) CASE_TEST(poll_null); EXPECT_SYSZR(1, poll(NULL, 0, 0)); break; CASE_TEST(poll_stdout); EXPECT_SYSNE(1, ({ struct pollfd fds = { 1, POLLOUT, 0}; poll(&fds, 1, 0); }), -1); break; CASE_TEST(poll_fault); EXPECT_SYSER(1, poll((void *)1, 1, 0), -1, EFAULT); break; + CASE_TEST(prctl); EXPECT_SYSER(1, prctl(PR_SET_NAME, (unsigned long)NULL, 0, 0, 0), -1, EFAULT); break; CASE_TEST(read_badf); EXPECT_SYSER(1, read(-1, &tmp, 1), -1, EBADF); break; CASE_TEST(sched_yield); EXPECT_SYSZR(1, sched_yield()); break; CASE_TEST(select_null); EXPECT_SYSZR(1, ({ struct timeval tv = { 0 }; select(0, NULL, NULL, NULL, &tv); })); break; @@ -557,6 +620,7 @@ int run_syscall(int min, int max) CASE_TEST(select_fault); EXPECT_SYSER(1, select(1, (void *)1, NULL, NULL, 0), -1, EFAULT); break; CASE_TEST(stat_blah); EXPECT_SYSER(1, stat("/proc/self/blah", &stat_buf), -1, ENOENT); break; CASE_TEST(stat_fault); EXPECT_SYSER(1, stat(NULL, &stat_buf), -1, EFAULT); break; + CASE_TEST(stat_timestamps); EXPECT_SYSZR(1, test_stat_timestamps()); break; CASE_TEST(symlink_root); EXPECT_SYSER(1, symlink("/", "/"), -1, EEXIST); break; CASE_TEST(unlink_root); EXPECT_SYSER(1, unlink("/"), -1, EISDIR); break; CASE_TEST(unlink_blah); EXPECT_SYSER(1, unlink("/proc/self/blah"), -1, ENOENT); break; @@ -565,6 +629,8 @@ int run_syscall(int min, int max) CASE_TEST(waitpid_child); EXPECT_SYSER(1, waitpid(getpid(), &tmp, WNOHANG), -1, ECHILD); break; CASE_TEST(write_badf); EXPECT_SYSER(1, write(-1, &tmp, 1), -1, EBADF); break; CASE_TEST(write_zero); EXPECT_SYSZR(1, write(1, &tmp, 0)); break; + CASE_TEST(syscall_noargs); EXPECT_SYSEQ(1, syscall(__NR_getpid), getpid()); break; + CASE_TEST(syscall_args); EXPECT_SYSER(1, syscall(__NR_statx, 0, NULL, 0, 0, NULL), -1, EFAULT); break; case __LINE__: return ret; /* must be last */ /* note: do not set any defaults so as to permit holes above */ @@ -581,7 +647,7 @@ int run_stdlib(int min, int max) void *p1, *p2; for (test = min; test >= 0 && test <= max; test++) { - int llen = 0; // line length + int llen = 0; /* line length */ /* avoid leaving empty lines below, this will insert holes into * test numbers. @@ -639,9 +705,9 @@ int run_stdlib(int min, int max) CASE_TEST(limit_int_fast32_min); EXPECT_EQ(1, INT_FAST32_MIN, (int_fast32_t) INTPTR_MIN); break; CASE_TEST(limit_int_fast32_max); EXPECT_EQ(1, INT_FAST32_MAX, (int_fast32_t) INTPTR_MAX); break; CASE_TEST(limit_uint_fast32_max); EXPECT_EQ(1, UINT_FAST32_MAX, (uint_fast32_t) UINTPTR_MAX); break; - CASE_TEST(limit_int_fast64_min); EXPECT_EQ(1, INT_FAST64_MIN, (int_fast64_t) INTPTR_MIN); break; - CASE_TEST(limit_int_fast64_max); EXPECT_EQ(1, INT_FAST64_MAX, (int_fast64_t) INTPTR_MAX); break; - CASE_TEST(limit_uint_fast64_max); EXPECT_EQ(1, UINT_FAST64_MAX, (uint_fast64_t) UINTPTR_MAX); break; + CASE_TEST(limit_int_fast64_min); EXPECT_EQ(1, INT_FAST64_MIN, (int_fast64_t) INT64_MIN); break; + CASE_TEST(limit_int_fast64_max); EXPECT_EQ(1, INT_FAST64_MAX, (int_fast64_t) INT64_MAX); break; + CASE_TEST(limit_uint_fast64_max); EXPECT_EQ(1, UINT_FAST64_MAX, (uint_fast64_t) UINT64_MAX); break; #if __SIZEOF_LONG__ == 8 CASE_TEST(limit_intptr_min); EXPECT_EQ(1, INTPTR_MIN, (intptr_t) 0x8000000000000000LL); break; CASE_TEST(limit_intptr_max); EXPECT_EQ(1, INTPTR_MAX, (intptr_t) 0x7fffffffffffffffLL); break; @@ -667,17 +733,98 @@ int run_stdlib(int min, int max) return ret; } -#if defined(__clang__) -__attribute__((optnone)) -#elif defined(__GNUC__) -__attribute__((optimize("O0"))) -#endif +#define EXPECT_VFPRINTF(c, expected, fmt, ...) \ + ret += expect_vfprintf(llen, c, expected, fmt, ##__VA_ARGS__) + +static int expect_vfprintf(int llen, size_t c, const char *expected, const char *fmt, ...) +{ + int ret, fd, w, r; + char buf[100]; + FILE *memfile; + va_list args; + + fd = memfd_create("vfprintf", 0); + if (fd == -1) { + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + } + + memfile = fdopen(fd, "w+"); + if (!memfile) { + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + } + + va_start(args, fmt); + w = vfprintf(memfile, fmt, args); + va_end(args); + + if (w != c) { + llen += printf(" written(%d) != %d", w, (int) c); + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + } + + fflush(memfile); + lseek(fd, 0, SEEK_SET); + + r = read(fd, buf, sizeof(buf) - 1); + buf[r] = '\0'; + + fclose(memfile); + + if (r != w) { + llen += printf(" written(%d) != read(%d)", w, r); + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + } + + llen += printf(" \"%s\" = \"%s\"", expected, buf); + ret = strncmp(expected, buf, c); + + pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); + return ret; +} + +static int run_vfprintf(int min, int max) +{ + int test; + int tmp; + int ret = 0; + void *p1, *p2; + + for (test = min; test >= 0 && test <= max; test++) { + int llen = 0; /* line length */ + + /* avoid leaving empty lines below, this will insert holes into + * test numbers. + */ + switch (test + __LINE__ + 1) { + CASE_TEST(empty); EXPECT_VFPRINTF(0, "", ""); break; + CASE_TEST(simple); EXPECT_VFPRINTF(3, "foo", "foo"); break; + CASE_TEST(string); EXPECT_VFPRINTF(3, "foo", "%s", "foo"); break; + CASE_TEST(number); EXPECT_VFPRINTF(4, "1234", "%d", 1234); break; + CASE_TEST(negnumber); EXPECT_VFPRINTF(5, "-1234", "%d", -1234); break; + CASE_TEST(unsigned); EXPECT_VFPRINTF(5, "12345", "%u", 12345); break; + CASE_TEST(char); EXPECT_VFPRINTF(1, "c", "%c", 'c'); break; + CASE_TEST(hex); EXPECT_VFPRINTF(1, "f", "%x", 0xf); break; + CASE_TEST(pointer); EXPECT_VFPRINTF(3, "0x1", "%p", (void *) 0x1); break; + case __LINE__: + return ret; /* must be last */ + /* note: do not set any defaults so as to permit holes above */ + } + } + return ret; +} + static int smash_stack(void) { char buf[100]; + volatile char *ptr = buf; + size_t i; - for (size_t i = 0; i < 200; i++) - buf[i] = 'P'; + for (i = 0; i < 200; i++) + ptr[i] = 'P'; return 1; } @@ -689,12 +836,20 @@ static int run_protection(int min, int max) llen += printf("0 -fstackprotector "); -#if !defined(NOLIBC_STACKPROTECTOR) +#if !defined(_NOLIBC_STACKPROTECTOR) llen += printf("not supported"); pad_spc(llen, 64, "[SKIPPED]\n"); return 0; #endif +#if defined(_NOLIBC_STACKPROTECTOR) + if (!__stack_chk_guard) { + llen += printf("__stack_chk_guard not initialized"); + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + } +#endif + pid = -1; pid = fork(); @@ -708,6 +863,7 @@ static int run_protection(int min, int max) close(STDOUT_FILENO); close(STDERR_FILENO); + prctl(PR_SET_DUMPABLE, 0, 0, 0, 0); smash_stack(); return 1; @@ -778,6 +934,7 @@ static const struct test test_names[] = { /* add new tests here */ { .name = "syscall", .func = run_syscall }, { .name = "stdlib", .func = run_stdlib }, + { .name = "vfprintf", .func = run_vfprintf }, { .name = "protection", .func = run_protection }, { 0 } }; @@ -785,7 +942,7 @@ static const struct test test_names[] = { int main(int argc, char **argv, char **envp) { int min = 0; - int max = __INT_MAX__; + int max = INT_MAX; int ret = 0; int err; int idx; @@ -833,7 +990,7 @@ int main(int argc, char **argv, char **envp) * here, which defaults to the full range. */ do { - min = 0; max = __INT_MAX__; + min = 0; max = INT_MAX; value = colon; if (value && *value) { colon = strchr(value, ':'); @@ -899,7 +1056,7 @@ int main(int argc, char **argv, char **envp) #else else if (ioperm(0x501, 1, 1) == 0) #endif - asm volatile ("outb %%al, %%dx" :: "d"(0x501), "a"(0)); + __asm__ volatile ("outb %%al, %%dx" :: "d"(0x501), "a"(0)); /* if it does nothing, fall back to the regular panic */ #endif } diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index 6922d6417e1cf..88d6830ee004d 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -90,7 +90,6 @@ again: } ret = WEXITSTATUS(status); - ksft_print_msg("waitpid WEXITSTATUS=%d\n", ret); return ret; } diff --git a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c index 3fd8e903118f5..4e86f927880c3 100644 --- a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c +++ b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c @@ -143,6 +143,7 @@ static inline int child_join(struct child *child, struct error *err) r = -1; } + ksft_print_msg("waitpid WEXITSTATUS=%d\n", r); return r; } diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index e2dd4ed849846..00a07e7c571cd 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -115,7 +115,8 @@ static int test_pidfd_send_signal_exited_fail(void) pidfd = open(buf, O_DIRECTORY | O_CLOEXEC); - (void)wait_for_pid(pid); + ret = wait_for_pid(pid); + ksft_print_msg("waitpid WEXITSTATUS=%d\n", ret); if (pidfd < 0) ksft_exit_fail_msg( diff --git a/tools/testing/selftests/prctl/set-anon-vma-name-test.c b/tools/testing/selftests/prctl/set-anon-vma-name-test.c index 26d853c5a0c17..4275cb256dcea 100644 --- a/tools/testing/selftests/prctl/set-anon-vma-name-test.c +++ b/tools/testing/selftests/prctl/set-anon-vma-name-test.c @@ -97,7 +97,7 @@ TEST_F(vma, renaming) { TH_LOG("Try to pass invalid name (with non-printable character \\1) to rename the VMA"); EXPECT_EQ(rename_vma((unsigned long)self->ptr_anon, AREA_SIZE, BAD_NAME), -EINVAL); - TH_LOG("Try to rename non-anonynous VMA"); + TH_LOG("Try to rename non-anonymous VMA"); EXPECT_EQ(rename_vma((unsigned long) self->ptr_not_anon, AREA_SIZE, GOOD_NAME), -EINVAL); } diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index 198ad5f321878..e9438a1862adf 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -110,7 +110,7 @@ static long ppb_to_scaled_ppm(int ppb) static int64_t pctns(struct ptp_clock_time *t) { - return t->sec * 1000000000LL + t->nsec; + return t->sec * NSEC_PER_SEC + t->nsec; } static void usage(char *progname) @@ -134,6 +134,7 @@ static void usage(char *progname) " 1 - external time stamp\n" " 2 - periodic output\n" " -n val shift the ptp clock time by 'val' nanoseconds\n" + " -o val phase offset (in nanoseconds) to be provided to the PHC servo\n" " -p val enable output with a period of 'val' nanoseconds\n" " -H val set output phase to 'val' nanoseconds (requires -p)\n" " -w val set output pulse width to 'val' nanoseconds (requires -p)\n" @@ -167,6 +168,7 @@ int main(int argc, char *argv[]) int adjfreq = 0x7fffffff; int adjtime = 0; int adjns = 0; + int adjphase = 0; int capabilities = 0; int extts = 0; int flagtest = 0; @@ -188,7 +190,7 @@ int main(int argc, char *argv[]) progname = strrchr(argv[0], '/'); progname = progname ? 1+progname : argv[0]; - while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:n:p:P:sSt:T:w:z"))) { + while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:n:o:p:P:sSt:T:w:z"))) { switch (c) { case 'c': capabilities = 1; @@ -228,6 +230,9 @@ int main(int argc, char *argv[]) case 'n': adjns = atoi(optarg); break; + case 'o': + adjphase = atoi(optarg); + break; case 'p': perout = atoll(optarg); break; @@ -287,7 +292,8 @@ int main(int argc, char *argv[]) " %d pulse per second\n" " %d programmable pins\n" " %d cross timestamping\n" - " %d adjust_phase\n", + " %d adjust_phase\n" + " %d maximum phase adjustment (ns)\n", caps.max_adj, caps.n_alarm, caps.n_ext_ts, @@ -295,7 +301,8 @@ int main(int argc, char *argv[]) caps.pps, caps.n_pins, caps.cross_timestamping, - caps.adjust_phase); + caps.adjust_phase, + caps.max_phase_adj); } } @@ -317,7 +324,7 @@ int main(int argc, char *argv[]) tx.time.tv_usec = adjns; while (tx.time.tv_usec < 0) { tx.time.tv_sec -= 1; - tx.time.tv_usec += 1000000000; + tx.time.tv_usec += NSEC_PER_SEC; } if (clock_adjtime(clkid, &tx) < 0) { @@ -327,6 +334,18 @@ int main(int argc, char *argv[]) } } + if (adjphase) { + memset(&tx, 0, sizeof(tx)); + tx.modes = ADJ_OFFSET | ADJ_NANO; + tx.offset = adjphase; + + if (clock_adjtime(clkid, &tx) < 0) { + perror("clock_adjtime"); + } else { + puts("phase adjustment okay"); + } + } + if (gettime) { if (clock_gettime(clkid, &ts)) { perror("clock_gettime"); @@ -502,11 +521,11 @@ int main(int argc, char *argv[]) interval = t2 - t1; offset = (t2 + t1) / 2 - tp; - printf("system time: %lld.%u\n", + printf("system time: %lld.%09u\n", (pct+2*i)->sec, (pct+2*i)->nsec); - printf("phc time: %lld.%u\n", + printf("phc time: %lld.%09u\n", (pct+2*i+1)->sec, (pct+2*i+1)->nsec); - printf("system time: %lld.%u\n", + printf("system time: %lld.%09u\n", (pct+2*i+2)->sec, (pct+2*i+2)->nsec); printf("system/phc clock time offset is %" PRId64 " ns\n" "system clock time delay is %" PRId64 " ns\n", diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index b52d5069563c6..48b9147e8c910 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -250,7 +250,7 @@ identify_qemu_args () { echo -machine virt,gic-version=host -cpu host ;; qemu-system-ppc64) - echo -enable-kvm -M pseries -nodefaults + echo -M pseries -nodefaults echo -device spapr-vscsi if test -n "$TORTURE_QEMU_INTERACTIVE" -a -n "$TORTURE_QEMU_MAC" then diff --git a/tools/testing/selftests/rcutorture/configs/rcu/BUSTED-BOOST.boot b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED-BOOST.boot index f57720c52c0f9..84f6bb98ce993 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/BUSTED-BOOST.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED-BOOST.boot @@ -5,4 +5,4 @@ rcutree.gp_init_delay=3 rcutree.gp_cleanup_delay=3 rcutree.kthread_prio=2 threadirqs -tree.use_softirq=0 +rcutree.use_softirq=0 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot index 64f864f1f361f..8e50bfd4b710d 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot @@ -4,4 +4,4 @@ rcutree.gp_init_delay=3 rcutree.gp_cleanup_delay=3 rcutree.kthread_prio=2 threadirqs -tree.use_softirq=0 +rcutree.use_softirq=0 diff --git a/tools/testing/selftests/run_kselftest.sh b/tools/testing/selftests/run_kselftest.sh index 97165a83df632..92743980e553b 100755 --- a/tools/testing/selftests/run_kselftest.sh +++ b/tools/testing/selftests/run_kselftest.sh @@ -26,6 +26,7 @@ Usage: $0 [OPTIONS] -l | --list List the available collection:test entries -d | --dry-run Don't actually run any tests -h | --help Show this usage info + -o | --override-timeout Number of seconds after which we timeout EOF exit $1 } @@ -33,6 +34,7 @@ EOF COLLECTIONS="" TESTS="" dryrun="" +kselftest_override_timeout="" while true; do case "$1" in -s | --summary) @@ -51,6 +53,9 @@ while true; do -d | --dry-run) dryrun="echo" shift ;; + -o | --override-timeout) + kselftest_override_timeout="$2" + shift 2 ;; -h | --help) usage 0 ;; "") @@ -85,7 +90,7 @@ if [ -n "$TESTS" ]; then available="$(echo "$valid" | sed -e 's/ /\n/g')" fi -collections=$(echo "$available" | cut -d: -f1 | uniq) +collections=$(echo "$available" | cut -d: -f1 | sort | uniq) for collection in $collections ; do [ -w /dev/kmsg ] && echo "kselftest: Running tests in $collection" >> /dev/kmsg tests=$(echo "$available" | grep "^$collection:" | cut -d: -f2) diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile index 75af864e07b65..50aab6b57da34 100644 --- a/tools/testing/selftests/sgx/Makefile +++ b/tools/testing/selftests/sgx/Makefile @@ -17,6 +17,7 @@ ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \ -fno-stack-protector -mrdrnd $(INCLUDES) TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx +TEST_FILES := $(OUTPUT)/test_encl.elf ifeq ($(CAN_BUILD_X86_64), 1) all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/test_encl.elf diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh index bfc54b422f25a..444b2befda827 100755 --- a/tools/testing/selftests/sysctl/sysctl.sh +++ b/tools/testing/selftests/sysctl/sysctl.sh @@ -14,23 +14,27 @@ TEST_FILE=$(mktemp) # This represents # -# TEST_ID:TEST_COUNT:ENABLED:TARGET +# TEST_ID:TEST_COUNT:ENABLED:TARGET:SKIP_NO_TARGET # # TEST_ID: is the test id number # TEST_COUNT: number of times we should run the test # ENABLED: 1 if enabled, 0 otherwise # TARGET: test target file required on the test_sysctl module +# SKIP_NO_TARGET: 1 skip if TARGET not there +# 0 run eventhough TARGET not there # # Once these are enabled please leave them as-is. Write your own test, # we have tons of space. -ALL_TESTS="0001:1:1:int_0001" -ALL_TESTS="$ALL_TESTS 0002:1:1:string_0001" -ALL_TESTS="$ALL_TESTS 0003:1:1:int_0002" -ALL_TESTS="$ALL_TESTS 0004:1:1:uint_0001" -ALL_TESTS="$ALL_TESTS 0005:3:1:int_0003" -ALL_TESTS="$ALL_TESTS 0006:50:1:bitmap_0001" -ALL_TESTS="$ALL_TESTS 0007:1:1:boot_int" -ALL_TESTS="$ALL_TESTS 0008:1:1:match_int" +ALL_TESTS="0001:1:1:int_0001:1" +ALL_TESTS="$ALL_TESTS 0002:1:1:string_0001:1" +ALL_TESTS="$ALL_TESTS 0003:1:1:int_0002:1" +ALL_TESTS="$ALL_TESTS 0004:1:1:uint_0001:1" +ALL_TESTS="$ALL_TESTS 0005:3:1:int_0003:1" +ALL_TESTS="$ALL_TESTS 0006:50:1:bitmap_0001:1" +ALL_TESTS="$ALL_TESTS 0007:1:1:boot_int:1" +ALL_TESTS="$ALL_TESTS 0008:1:1:match_int:1" +ALL_TESTS="$ALL_TESTS 0009:1:1:unregister_error:0" +ALL_TESTS="$ALL_TESTS 0010:1:1:mnt/mnt_error:0" function allow_user_defaults() { @@ -613,7 +617,6 @@ target_exists() TEST_ID="$2" if [ ! -f ${TARGET} ] ; then - echo "Target for test $TEST_ID: $TARGET not exist, skipping test ..." return 0 fi return 1 @@ -730,7 +733,7 @@ sysctl_test_0005() sysctl_test_0006() { - TARGET="${SYSCTL}/bitmap_0001" + TARGET="${SYSCTL}/$(get_test_target 0006)" reset_vals ORIG="" run_bitmaptest @@ -738,7 +741,7 @@ sysctl_test_0006() sysctl_test_0007() { - TARGET="${SYSCTL}/boot_int" + TARGET="${SYSCTL}/$(get_test_target 0007)" if [ ! -f $TARGET ]; then echo "Skipping test for $TARGET as it is not present ..." return $ksft_skip @@ -778,7 +781,7 @@ sysctl_test_0007() sysctl_test_0008() { - TARGET="${SYSCTL}/match_int" + TARGET="${SYSCTL}/$(get_test_target 0008)" if [ ! -f $TARGET ]; then echo "Skipping test for $TARGET as it is not present ..." return $ksft_skip @@ -797,6 +800,34 @@ sysctl_test_0008() return 0 } +sysctl_test_0009() +{ + TARGET="${SYSCTL}/$(get_test_target 0009)" + echo -n "Testing if $TARGET unregistered correctly ..." + if [ -d $TARGET ]; then + echo "TEST FAILED" + rc=1 + test_rc + fi + + echo "ok" + return 0 +} + +sysctl_test_0010() +{ + TARGET="${SYSCTL}/$(get_test_target 0010)" + echo -n "Testing that $TARGET was not created ..." + if [ -d $TARGET ]; then + echo "TEST FAILED" + rc=1 + test_rc + fi + + echo "ok" + return 0 +} + list_tests() { echo "Test ID list:" @@ -813,6 +844,8 @@ list_tests() echo "0006 x $(get_test_count 0006) - tests proc_do_large_bitmap()" echo "0007 x $(get_test_count 0007) - tests setting sysctl from kernel boot param" echo "0008 x $(get_test_count 0008) - tests sysctl macro values match" + echo "0009 x $(get_test_count 0009) - tests sysct unregister" + echo "0010 x $(get_test_count 0010) - tests sysct mount point" } usage() @@ -857,38 +890,65 @@ function test_num() usage fi } +function remove_leading_zeros() +{ + echo $1 | sed 's/^0*//' +} function get_test_count() { test_num $1 - TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + awk_field=$(remove_leading_zeros $1) + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$awk_field'}') echo ${TEST_DATA} | awk -F":" '{print $2}' } function get_test_enabled() { test_num $1 - TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + awk_field=$(remove_leading_zeros $1) + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$awk_field'}') echo ${TEST_DATA} | awk -F":" '{print $3}' } function get_test_target() { test_num $1 - TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + awk_field=$(remove_leading_zeros $1) + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$awk_field'}') echo ${TEST_DATA} | awk -F":" '{print $4}' } +function get_test_skip_no_target() +{ + test_num $1 + awk_field=$(remove_leading_zeros $1) + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$awk_field'}') + echo ${TEST_DATA} | awk -F":" '{print $5}' +} + +function skip_test() +{ + TEST_ID=$1 + TEST_TARGET=$2 + if target_exists $TEST_TARGET $TEST_ID; then + TEST_SKIP=$(get_test_skip_no_target $TEST_ID) + if [[ $TEST_SKIP -eq "1" ]]; then + echo "Target for test $TEST_ID: $TEST_TARGET not exist, skipping test ..." + return 0 + fi + fi + return 1 +} + function run_all_tests() { for i in $ALL_TESTS ; do - TEST_ID=${i%:*:*:*} + TEST_ID=${i%:*:*:*:*} ENABLED=$(get_test_enabled $TEST_ID) TEST_COUNT=$(get_test_count $TEST_ID) TEST_TARGET=$(get_test_target $TEST_ID) - if target_exists $TEST_TARGET $TEST_ID; then - continue - fi + if [[ $ENABLED -eq "1" ]]; then test_case $TEST_ID $TEST_COUNT $TEST_TARGET fi @@ -923,18 +983,19 @@ function watch_case() function test_case() { + TEST_ID=$1 NUM_TESTS=$2 + TARGET=$3 - i=0 - - if target_exists $3 $1; then - continue + if skip_test $TEST_ID $TARGET; then + return fi + i=0 while [ $i -lt $NUM_TESTS ]; do - test_num $1 - watch_log $i ${TEST_NAME}_test_$1 noclear - RUN_TEST=${TEST_NAME}_test_$1 + test_num $TEST_ID + watch_log $i ${TEST_NAME}_test_${TEST_ID} noclear + RUN_TEST=${TEST_NAME}_test_${TEST_ID} $RUN_TEST let i=$i+1 done diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index 4638c63a339ff..6e73b09c20c81 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -6,20 +6,18 @@ CONFIG_NF_CONNTRACK_MARK=y CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_CONNTRACK_LABELS=y CONFIG_NF_NAT=m +CONFIG_NETFILTER_XT_TARGET_LOG=m CONFIG_NET_SCHED=y # # Queueing/Scheduling # -CONFIG_NET_SCH_ATM=m CONFIG_NET_SCH_CAKE=m -CONFIG_NET_SCH_CBQ=m CONFIG_NET_SCH_CBS=m CONFIG_NET_SCH_CHOKE=m CONFIG_NET_SCH_CODEL=m CONFIG_NET_SCH_DRR=m -CONFIG_NET_SCH_DSMARK=m CONFIG_NET_SCH_ETF=m CONFIG_NET_SCH_FQ=m CONFIG_NET_SCH_FQ_CODEL=m @@ -57,8 +55,6 @@ CONFIG_NET_CLS_FLOW=m CONFIG_NET_CLS_FLOWER=m CONFIG_NET_CLS_MATCHALL=m CONFIG_NET_CLS_ROUTE4=m -CONFIG_NET_CLS_RSVP=m -CONFIG_NET_CLS_TCINDEX=m CONFIG_NET_EMATCH=y CONFIG_NET_EMATCH_STACK=32 CONFIG_NET_EMATCH_CMP=m diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json b/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json new file mode 100644 index 0000000000000..c4c778e83da2b --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json @@ -0,0 +1,25 @@ +[ + { + "id": "c2b4", + "name": "soft lockup alarm will be not generated after delete the prio 0 filter of the chain", + "category": [ + "filter", + "chain" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY root handle 1: htb default 1", + "$TC chain add dev $DUMMY", + "$TC filter del dev $DUMMY chain 0 parent 1: prio 0" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY chain 0 parent 1:", + "expExitCode": "2", + "verifyCmd": "$TC chain ls dev $DUMMY", + "matchPattern": "chain parent 1: chain 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: htb default 1", + "$IP link del dev $DUMMY type dummy" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json index 44fbfc6caec7b..e3d2de5c184fa 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json @@ -155,5 +155,28 @@ "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" ] - } + }, + { + "id": "0531", + "name": "Replace mq with invalid parent ID", + "category": [ + "qdisc", + "mq" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 16\" > /sys/bus/netdevsim/new_device", + "$TC qdisc add dev $ETH root handle ffff: mq" + ], + "cmdUnderTest": "$TC qdisc replace dev $ETH parent ffff:fff1 handle ffff: mq", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $ETH", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent ffff", + "matchCount": "16", + "teardown": [ + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] + } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json index ba2f5e79cdbfe..e21c7f22c6d4c 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json @@ -58,10 +58,10 @@ "setup": [ "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb db 10", + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb db 100", "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc sfb 1: root refcnt [0-9]+ rehash 600s db 10ms", + "matchPattern": "qdisc sfb 1: root refcnt [0-9]+ rehash 600s db 100ms", "matchCount": "1", "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root", diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh index afb0cd86fa3df..eb357bd7923c0 100755 --- a/tools/testing/selftests/tc-testing/tdc.sh +++ b/tools/testing/selftests/tc-testing/tdc.sh @@ -2,5 +2,6 @@ # SPDX-License-Identifier: GPL-2.0 modprobe netdevsim +modprobe sch_teql ./tdc.py -c actions --nobuildebpf ./tdc.py -c qdisc diff --git a/tools/testing/selftests/user_events/dyn_test.c b/tools/testing/selftests/user_events/dyn_test.c index 8879a7b04c6ac..d6979a48478fc 100644 --- a/tools/testing/selftests/user_events/dyn_test.c +++ b/tools/testing/selftests/user_events/dyn_test.c @@ -16,42 +16,140 @@ #include "../kselftest_harness.h" -const char *dyn_file = "/sys/kernel/tracing/dynamic_events"; -const char *clear = "!u:__test_event"; +const char *abi_file = "/sys/kernel/tracing/user_events_data"; +const char *enable_file = "/sys/kernel/tracing/events/user_events/__test_event/enable"; -static int Append(const char *value) +static bool wait_for_delete(void) { - int fd = open(dyn_file, O_RDWR | O_APPEND); - int ret = write(fd, value, strlen(value)); + int i; + + for (i = 0; i < 1000; ++i) { + int fd = open(enable_file, O_RDONLY); + + if (fd == -1) + return true; + + close(fd); + usleep(1000); + } + + return false; +} + +static int reg_event(int fd, int *check, int bit, const char *value) +{ + struct user_reg reg = {0}; + + reg.size = sizeof(reg); + reg.name_args = (__u64)value; + reg.enable_bit = bit; + reg.enable_addr = (__u64)check; + reg.enable_size = sizeof(*check); + + if (ioctl(fd, DIAG_IOCSREG, ®) == -1) + return -1; + + return 0; +} + +static int unreg_event(int fd, int *check, int bit) +{ + struct user_unreg unreg = {0}; + + unreg.size = sizeof(unreg); + unreg.disable_bit = bit; + unreg.disable_addr = (__u64)check; + + return ioctl(fd, DIAG_IOCSUNREG, &unreg); +} + +static int parse(int *check, const char *value) +{ + int fd = open(abi_file, O_RDWR); + int ret; + + if (fd == -1) + return -1; + + /* Until we have persist flags via dynamic events, use the base name */ + if (value[0] != 'u' || value[1] != ':') { + close(fd); + return -1; + } + + ret = reg_event(fd, check, 31, value + 2); + + if (ret != -1) { + if (unreg_event(fd, check, 31) == -1) + printf("WARN: Couldn't unreg event\n"); + } close(fd); + return ret; } -#define CLEAR() \ +static int check_match(int *check, const char *first, const char *second, bool *match) +{ + int fd = open(abi_file, O_RDWR); + int ret = -1; + + if (fd == -1) + return -1; + + if (reg_event(fd, check, 31, first) == -1) + goto cleanup; + + if (reg_event(fd, check, 30, second) == -1) { + if (errno == EADDRINUSE) { + /* Name is in use, with different fields */ + *match = false; + ret = 0; + } + + goto cleanup; + } + + *match = true; + ret = 0; +cleanup: + unreg_event(fd, check, 31); + unreg_event(fd, check, 30); + + close(fd); + + wait_for_delete(); + + return ret; +} + +#define TEST_MATCH(x, y) \ do { \ - int ret = Append(clear); \ - if (ret == -1) \ - ASSERT_EQ(ENOENT, errno); \ + bool match; \ + ASSERT_NE(-1, check_match(&self->check, x, y, &match)); \ + ASSERT_EQ(true, match); \ } while (0) -#define TEST_PARSE(x) \ +#define TEST_NMATCH(x, y) \ do { \ - ASSERT_NE(-1, Append(x)); \ - CLEAR(); \ + bool match; \ + ASSERT_NE(-1, check_match(&self->check, x, y, &match)); \ + ASSERT_EQ(false, match); \ } while (0) -#define TEST_NPARSE(x) ASSERT_EQ(-1, Append(x)) +#define TEST_PARSE(x) ASSERT_NE(-1, parse(&self->check, x)) + +#define TEST_NPARSE(x) ASSERT_EQ(-1, parse(&self->check, x)) FIXTURE(user) { + int check; }; FIXTURE_SETUP(user) { - CLEAR(); } FIXTURE_TEARDOWN(user) { - CLEAR(); + wait_for_delete(); } TEST_F(user, basic_types) { @@ -95,33 +193,30 @@ TEST_F(user, size_types) { TEST_NPARSE("u:__test_event char a 20"); } -TEST_F(user, flags) { - /* Should work */ - TEST_PARSE("u:__test_event:BPF_ITER u32 a"); - /* Forward compat */ - TEST_PARSE("u:__test_event:BPF_ITER,FLAG_FUTURE u32 a"); -} - TEST_F(user, matching) { - /* Register */ - ASSERT_NE(-1, Append("u:__test_event struct custom a 20")); - /* Should not match */ - TEST_NPARSE("!u:__test_event struct custom b"); - /* Should match */ - TEST_PARSE("!u:__test_event struct custom a"); - /* Multi field reg */ - ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b")); - /* Non matching cases */ - TEST_NPARSE("!u:__test_event u32 a"); - TEST_NPARSE("!u:__test_event u32 b"); - TEST_NPARSE("!u:__test_event u32 a; u32 "); - TEST_NPARSE("!u:__test_event u32 a; u32 a"); - /* Matching case */ - TEST_PARSE("!u:__test_event u32 a; u32 b"); - /* Register */ - ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b")); - /* Ensure trailing semi-colon case */ - TEST_PARSE("!u:__test_event u32 a; u32 b;"); + /* Single name matches */ + TEST_MATCH("__test_event u32 a", + "__test_event u32 a"); + + /* Multiple names match */ + TEST_MATCH("__test_event u32 a; u32 b", + "__test_event u32 a; u32 b"); + + /* Multiple names match with dangling ; */ + TEST_MATCH("__test_event u32 a; u32 b", + "__test_event u32 a; u32 b;"); + + /* Single name doesn't match */ + TEST_NMATCH("__test_event u32 a", + "__test_event u32 b"); + + /* Multiple names don't match */ + TEST_NMATCH("__test_event u32 a; u32 b", + "__test_event u32 b; u32 a"); + + /* Types don't match */ + TEST_NMATCH("__test_event u64 a; u64 b", + "__test_event u32 a; u32 b"); } int main(int argc, char **argv) diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c index 7c99cef94a655..5beb0aef1d814 100644 --- a/tools/testing/selftests/user_events/ftrace_test.c +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -102,30 +102,56 @@ err: return -1; } +static bool wait_for_delete(void) +{ + int i; + + for (i = 0; i < 1000; ++i) { + int fd = open(enable_file, O_RDONLY); + + if (fd == -1) + return true; + + close(fd); + usleep(1000); + } + + return false; +} + static int clear(int *check) { struct user_unreg unreg = {0}; + int fd; unreg.size = sizeof(unreg); unreg.disable_bit = 31; unreg.disable_addr = (__u64)check; - int fd = open(data_file, O_RDWR); + fd = open(data_file, O_RDWR); if (fd == -1) return -1; if (ioctl(fd, DIAG_IOCSUNREG, &unreg) == -1) if (errno != ENOENT) - return -1; - - if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) - if (errno != ENOENT) - return -1; + goto fail; + + if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) { + if (errno == EBUSY) { + if (!wait_for_delete()) + goto fail; + } else if (errno != ENOENT) + goto fail; + } close(fd); return 0; +fail: + close(fd); + + return -1; } static int check_print_fmt(const char *event, const char *expected, int *check) @@ -155,9 +181,8 @@ static int check_print_fmt(const char *event, const char *expected, int *check) /* Register should work */ ret = ioctl(fd, DIAG_IOCSREG, ®); - close(fd); - if (ret != 0) { + close(fd); printf("Reg failed in fmt\n"); return ret; } @@ -165,6 +190,8 @@ static int check_print_fmt(const char *event, const char *expected, int *check) /* Ensure correct print_fmt */ ret = get_print_fmt(print_fmt, sizeof(print_fmt)); + close(fd); + if (ret != 0) return ret; @@ -228,6 +255,12 @@ TEST_F(user, register_events) { ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); + /* Multiple registers to same name but different args should fail */ + reg.enable_bit = 29; + reg.name_args = (__u64)"__test_event u32 field1;"; + ASSERT_EQ(-1, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(EADDRINUSE, errno); + /* Ensure disabled */ self->enable_fd = open(enable_file, O_RDWR); ASSERT_NE(-1, self->enable_fd); @@ -250,10 +283,10 @@ TEST_F(user, register_events) { unreg.disable_bit = 30; ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSUNREG, &unreg)); - /* Delete should work only after close and unregister */ + /* Delete should have been auto-done after close and unregister */ close(self->data_fd); - self->data_fd = open(data_file, O_RDWR); - ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event")); + + ASSERT_EQ(true, wait_for_delete()); } TEST_F(user, write_events) { @@ -291,6 +324,10 @@ TEST_F(user, write_events) { io[0].iov_base = ®.write_index; io[0].iov_len = sizeof(reg.write_index); + /* Write should return -EBADF when event is not enabled */ + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + ASSERT_EQ(EBADF, errno); + /* Enable event */ self->enable_fd = open(enable_file, O_RDWR); ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) @@ -310,6 +347,39 @@ TEST_F(user, write_events) { ASSERT_EQ(EINVAL, errno); } +TEST_F(user, write_empty_events) { + struct user_reg reg = {0}; + struct iovec io[1]; + int before = 0, after = 0; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); + + io[0].iov_base = ®.write_index; + io[0].iov_len = sizeof(reg.write_index); + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_EQ(0, self->check); + + /* Enable event */ + self->enable_fd = open(enable_file, O_RDWR); + ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) + + /* Event should now be enabled */ + ASSERT_EQ(1 << reg.enable_bit, self->check); + + /* Write should make it out to ftrace buffers */ + before = trace_bytes(); + ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 1)); + after = trace_bytes(); + ASSERT_GT(after, before); +} + TEST_F(user, write_fault) { struct user_reg reg = {0}; struct iovec io[2]; @@ -334,6 +404,10 @@ TEST_F(user, write_fault) { ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); + /* Enable event */ + self->enable_fd = open(enable_file, O_RDWR); + ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) + /* Write should work normally */ ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 2)); diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c index a070258d4449e..8b09be566fa21 100644 --- a/tools/testing/selftests/user_events/perf_test.c +++ b/tools/testing/selftests/user_events/perf_test.c @@ -81,6 +81,32 @@ static int get_offset(void) return offset; } +static int clear(int *check) +{ + struct user_unreg unreg = {0}; + + unreg.size = sizeof(unreg); + unreg.disable_bit = 31; + unreg.disable_addr = (__u64)check; + + int fd = open(data_file, O_RDWR); + + if (fd == -1) + return -1; + + if (ioctl(fd, DIAG_IOCSUNREG, &unreg) == -1) + if (errno != ENOENT) + return -1; + + if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) + if (errno != ENOENT) + return -1; + + close(fd); + + return 0; +} + FIXTURE(user) { int data_fd; int check; @@ -93,6 +119,9 @@ FIXTURE_SETUP(user) { FIXTURE_TEARDOWN(user) { close(self->data_fd); + + if (clear(&self->check) != 0) + printf("WARNING: Clear didn't work!\n"); } TEST_F(user, perf_write) { @@ -160,6 +189,59 @@ TEST_F(user, perf_write) { ASSERT_EQ(0, self->check); } +TEST_F(user, perf_empty_events) { + struct perf_event_attr pe = {0}; + struct user_reg reg = {0}; + struct perf_event_mmap_page *perf_page; + int page_size = sysconf(_SC_PAGESIZE); + int id, fd; + __u32 *val; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_EQ(0, self->check); + + /* Id should be there */ + id = get_id(); + ASSERT_NE(-1, id); + + pe.type = PERF_TYPE_TRACEPOINT; + pe.size = sizeof(pe); + pe.config = id; + pe.sample_type = PERF_SAMPLE_RAW; + pe.sample_period = 1; + pe.wakeup_events = 1; + + /* Tracepoint attach should work */ + fd = perf_event_open(&pe, 0, -1, -1, 0); + ASSERT_NE(-1, fd); + + perf_page = mmap(NULL, page_size * 2, PROT_READ, MAP_SHARED, fd, 0); + ASSERT_NE(MAP_FAILED, perf_page); + + /* Status should be updated */ + ASSERT_EQ(1 << reg.enable_bit, self->check); + + /* Ensure write shows up at correct offset */ + ASSERT_NE(-1, write(self->data_fd, ®.write_index, + sizeof(reg.write_index))); + val = (void *)(((char *)perf_page) + perf_page->data_offset); + ASSERT_EQ(PERF_RECORD_SAMPLE, *val); + + munmap(perf_page, page_size * 2); + close(fd); + + /* Status should be updated */ + ASSERT_EQ(0, self->check); +} + int main(int argc, char **argv) { return test_harness_run(argc, argv); diff --git a/tools/testing/selftests/vDSO/vdso_test_clock_getres.c b/tools/testing/selftests/vDSO/vdso_test_clock_getres.c index 15dcee16ff726..38d46a8bf7cba 100644 --- a/tools/testing/selftests/vDSO/vdso_test_clock_getres.c +++ b/tools/testing/selftests/vDSO/vdso_test_clock_getres.c @@ -84,12 +84,12 @@ static inline int vdso_test_clock(unsigned int clock_id) int main(int argc, char **argv) { - int ret; + int ret = 0; #if _POSIX_TIMERS > 0 #ifdef CLOCK_REALTIME - ret = vdso_test_clock(CLOCK_REALTIME); + ret += vdso_test_clock(CLOCK_REALTIME); #endif #ifdef CLOCK_BOOTTIME diff --git a/tools/virtio/ringtest/.gitignore b/tools/virtio/ringtest/.gitignore new file mode 100644 index 0000000000000..100b9e30c0f47 --- /dev/null +++ b/tools/virtio/ringtest/.gitignore @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0-only +/noring +/ptr_ring +/ring +/virtio_ring_0_9 +/virtio_ring_inorder +/virtio_ring_poll diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h index b68920d527503..d18dd317e27f9 100644 --- a/tools/virtio/ringtest/main.h +++ b/tools/virtio/ringtest/main.h @@ -8,6 +8,7 @@ #ifndef MAIN_H #define MAIN_H +#include <assert.h> #include <stdbool.h> extern int param; @@ -95,6 +96,8 @@ extern unsigned ring_size; #define cpu_relax() asm ("rep; nop" ::: "memory") #elif defined(__s390x__) #define cpu_relax() barrier() +#elif defined(__aarch64__) +#define cpu_relax() asm ("yield" ::: "memory") #else #define cpu_relax() assert(0) #endif @@ -112,6 +115,8 @@ static inline void busy_wait(void) #if defined(__x86_64__) || defined(__i386__) #define smp_mb() asm volatile("lock; addl $0,-132(%%rsp)" ::: "memory", "cc") +#elif defined(__aarch64__) +#define smp_mb() asm volatile("dmb ish" ::: "memory") #else /* * Not using __ATOMIC_SEQ_CST since gcc docs say they are only synchronized @@ -136,10 +141,16 @@ static inline void busy_wait(void) #if defined(__i386__) || defined(__x86_64__) || defined(__s390x__) #define smp_wmb() barrier() +#elif defined(__aarch64__) +#define smp_wmb() asm volatile("dmb ishst" ::: "memory") #else #define smp_wmb() smp_release() #endif +#ifndef __always_inline +#define __always_inline inline __attribute__((always_inline)) +#endif + static __always_inline void __read_once_size(const volatile void *p, void *res, int size) { diff --git a/tools/virtio/virtio-trace/README b/tools/virtio/virtio-trace/README index 4fb9368bf7519..0127ff0c54b08 100644 --- a/tools/virtio/virtio-trace/README +++ b/tools/virtio/virtio-trace/README @@ -95,7 +95,7 @@ Run 1) Enable ftrace in the guest <Example> - # echo 1 > /sys/kernel/debug/tracing/events/sched/enable + # echo 1 > /sys/kernel/tracing/events/sched/enable 2) Run trace agent in the guest This agent must be operated as root. diff --git a/tools/virtio/virtio-trace/trace-agent.c b/tools/virtio/virtio-trace/trace-agent.c index cdfe77c2b4c8f..7e2d9bbf0b843 100644 --- a/tools/virtio/virtio-trace/trace-agent.c +++ b/tools/virtio/virtio-trace/trace-agent.c @@ -18,8 +18,9 @@ #define PIPE_DEF_BUFS 16 #define PIPE_MIN_SIZE (PAGE_SIZE*PIPE_DEF_BUFS) #define PIPE_MAX_SIZE (1024*1024) -#define READ_PATH_FMT \ - "/sys/kernel/debug/tracing/per_cpu/cpu%d/trace_pipe_raw" +#define TRACEFS "/sys/kernel/tracing" +#define DEBUGFS "/sys/kernel/debug/tracing" +#define READ_PATH_FMT "%s/per_cpu/cpu%d/trace_pipe_raw" #define WRITE_PATH_FMT "/dev/virtio-ports/trace-path-cpu%d" #define CTL_PATH "/dev/virtio-ports/agent-ctl-path" @@ -120,9 +121,12 @@ static const char *make_path(int cpu_num, bool this_is_write_path) if (this_is_write_path) /* write(output) path */ ret = snprintf(buf, PATH_MAX, WRITE_PATH_FMT, cpu_num); - else + else { /* read(input) path */ - ret = snprintf(buf, PATH_MAX, READ_PATH_FMT, cpu_num); + ret = snprintf(buf, PATH_MAX, READ_PATH_FMT, TRACEFS, cpu_num); + if (ret > 0 && access(buf, F_OK) != 0) + ret = snprintf(buf, PATH_MAX, READ_PATH_FMT, DEBUGFS, cpu_num); + } if (ret <= 0) { pr_err("Failed to generate %s path(CPU#%d):%d\n", diff --git a/tools/workqueue/wq_monitor.py b/tools/workqueue/wq_monitor.py new file mode 100644 index 0000000000000..6e258d123e8c7 --- /dev/null +++ b/tools/workqueue/wq_monitor.py @@ -0,0 +1,168 @@ +#!/usr/bin/env drgn +# +# Copyright (C) 2023 Tejun Heo <tj@kernel.org> +# Copyright (C) 2023 Meta Platforms, Inc. and affiliates. + +desc = """ +This is a drgn script to monitor workqueues. For more info on drgn, visit +https://github.com/osandov/drgn. + + total Total number of work items executed by the workqueue. + + infl The number of currently in-flight work items. + + CPUtime Total CPU time consumed by the workqueue in seconds. This is + sampled from scheduler ticks and only provides ballpark + measurement. "nohz_full=" CPUs are excluded from measurement. + + CPUitsv The number of times a concurrency-managed work item hogged CPU + longer than the threshold (workqueue.cpu_intensive_thresh_us) + and got excluded from concurrency management to avoid stalling + other work items. + + CMwake The number of concurrency-management wake-ups while executing a + work item of the workqueue. + + mayday The number of times the rescuer was requested while waiting for + new worker creation. + + rescued The number of work items executed by the rescuer. +""" + +import sys +import signal +import os +import re +import time +import json + +import drgn +from drgn.helpers.linux.list import list_for_each_entry,list_empty +from drgn.helpers.linux.cpumask import for_each_possible_cpu + +import argparse +parser = argparse.ArgumentParser(description=desc, + formatter_class=argparse.RawTextHelpFormatter) +parser.add_argument('workqueue', metavar='REGEX', nargs='*', + help='Target workqueue name patterns (all if empty)') +parser.add_argument('-i', '--interval', metavar='SECS', type=float, default=1, + help='Monitoring interval (0 to print once and exit)') +parser.add_argument('-j', '--json', action='store_true', + help='Output in json') +args = parser.parse_args() + +def err(s): + print(s, file=sys.stderr, flush=True) + sys.exit(1) + +workqueues = prog['workqueues'] + +WQ_UNBOUND = prog['WQ_UNBOUND'] +WQ_MEM_RECLAIM = prog['WQ_MEM_RECLAIM'] + +PWQ_STAT_STARTED = prog['PWQ_STAT_STARTED'] # work items started execution +PWQ_STAT_COMPLETED = prog['PWQ_STAT_COMPLETED'] # work items completed execution +PWQ_STAT_CPU_TIME = prog['PWQ_STAT_CPU_TIME'] # total CPU time consumed +PWQ_STAT_CPU_INTENSIVE = prog['PWQ_STAT_CPU_INTENSIVE'] # wq_cpu_intensive_thresh_us violations +PWQ_STAT_CM_WAKEUP = prog['PWQ_STAT_CM_WAKEUP'] # concurrency-management worker wakeups +PWQ_STAT_MAYDAY = prog['PWQ_STAT_MAYDAY'] # maydays to rescuer +PWQ_STAT_RESCUED = prog['PWQ_STAT_RESCUED'] # linked work items executed by rescuer +PWQ_NR_STATS = prog['PWQ_NR_STATS'] + +class WqStats: + def __init__(self, wq): + self.name = wq.name.string_().decode() + self.unbound = wq.flags & WQ_UNBOUND != 0 + self.mem_reclaim = wq.flags & WQ_MEM_RECLAIM != 0 + self.stats = [0] * PWQ_NR_STATS + for pwq in list_for_each_entry('struct pool_workqueue', wq.pwqs.address_of_(), 'pwqs_node'): + for i in range(PWQ_NR_STATS): + self.stats[i] += int(pwq.stats[i]) + + def dict(self, now): + return { 'timestamp' : now, + 'name' : self.name, + 'unbound' : self.unbound, + 'mem_reclaim' : self.mem_reclaim, + 'started' : self.stats[PWQ_STAT_STARTED], + 'completed' : self.stats[PWQ_STAT_COMPLETED], + 'cpu_time' : self.stats[PWQ_STAT_CPU_TIME], + 'cpu_intensive' : self.stats[PWQ_STAT_CPU_INTENSIVE], + 'cm_wakeup' : self.stats[PWQ_STAT_CM_WAKEUP], + 'mayday' : self.stats[PWQ_STAT_MAYDAY], + 'rescued' : self.stats[PWQ_STAT_RESCUED], } + + def table_header_str(): + return f'{"":>24} {"total":>8} {"infl":>5} {"CPUtime":>8} '\ + f'{"CPUitsv":>7} {"CMwake":>7} {"mayday":>7} {"rescued":>7}' + + def table_row_str(self): + cpu_intensive = '-' + cm_wakeup = '-' + mayday = '-' + rescued = '-' + + if not self.unbound: + cpu_intensive = str(self.stats[PWQ_STAT_CPU_INTENSIVE]) + cm_wakeup = str(self.stats[PWQ_STAT_CM_WAKEUP]) + + if self.mem_reclaim: + mayday = str(self.stats[PWQ_STAT_MAYDAY]) + rescued = str(self.stats[PWQ_STAT_RESCUED]) + + out = f'{self.name[-24:]:24} ' \ + f'{self.stats[PWQ_STAT_STARTED]:8} ' \ + f'{max(self.stats[PWQ_STAT_STARTED] - self.stats[PWQ_STAT_COMPLETED], 0):5} ' \ + f'{self.stats[PWQ_STAT_CPU_TIME] / 1000000:8.1f} ' \ + f'{cpu_intensive:>7} ' \ + f'{cm_wakeup:>7} ' \ + f'{mayday:>7} ' \ + f'{rescued:>7} ' + return out.rstrip(':') + +exit_req = False + +def sigint_handler(signr, frame): + global exit_req + exit_req = True + +def main(): + # handle args + table_fmt = not args.json + interval = args.interval + + re_str = None + if args.workqueue: + for r in args.workqueue: + if re_str is None: + re_str = r + else: + re_str += '|' + r + + filter_re = re.compile(re_str) if re_str else None + + # monitoring loop + signal.signal(signal.SIGINT, sigint_handler) + + while not exit_req: + now = time.time() + + if table_fmt: + print() + print(WqStats.table_header_str()) + + for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'): + stats = WqStats(wq) + if filter_re and not filter_re.search(stats.name): + continue + if table_fmt: + print(stats.table_row_str()) + else: + print(stats.dict(now)) + + if interval == 0: + break + time.sleep(interval) + +if __name__ == "__main__": + main() |