diff options
Diffstat (limited to 'tools')
1561 files changed, 307129 insertions, 34041 deletions
diff --git a/tools/Makefile b/tools/Makefile index c074e42fd92f..e497875fc7e3 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -78,6 +78,9 @@ bpf/%: FORCE libapi: FORCE $(call descend,lib/api) +nolibc: FORCE + $(call descend,include/nolibc) + nolibc_%: FORCE $(call descend,include/nolibc,$(patsubst nolibc_%,%,$@)) diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index e83e6e47a21e..938dec0dfaad 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -45,7 +45,6 @@ exit(code); \ } while (0) -int done; int rcvbufsz; char name[100]; int dbg; @@ -285,7 +284,6 @@ int main(int argc, char *argv[]) pid_t rtid = 0; int fd = 0; - int count = 0; int write_file = 0; int maskset = 0; char *logfile = NULL; @@ -495,7 +493,6 @@ int main(int argc, char *argv[]) len2 = 0; /* For nested attributes, na follows */ na = (struct nlattr *) NLA_DATA(na); - done = 0; while (len2 < aggr_len) { switch (na->nla_type) { case TASKSTATS_TYPE_PID: @@ -509,7 +506,6 @@ int main(int argc, char *argv[]) printf("TGID\t%d\n", rtid); break; case TASKSTATS_TYPE_STATS: - count++; if (print_delays) print_delayacct((struct taskstats *) NLA_DATA(na)); if (print_io_accounting) diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 8aa0d276a636..abc418650fec 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -60,6 +60,7 @@ #define ARM_CPU_IMP_FUJITSU 0x46 #define ARM_CPU_IMP_HISI 0x48 #define ARM_CPU_IMP_APPLE 0x61 +#define ARM_CPU_IMP_AMPERE 0xC0 #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -123,6 +124,8 @@ #define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028 #define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 +#define AMPERE_CPU_PART_AMPERE1 0xAC3 + #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) @@ -172,6 +175,7 @@ #define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO) #define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX) #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) +#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 3bb134355874..316917b98707 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -75,9 +75,11 @@ struct kvm_regs { /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */ #define KVM_ARM_DEVICE_TYPE_SHIFT 0 -#define KVM_ARM_DEVICE_TYPE_MASK (0xffff << KVM_ARM_DEVICE_TYPE_SHIFT) +#define KVM_ARM_DEVICE_TYPE_MASK GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \ + KVM_ARM_DEVICE_TYPE_SHIFT) #define KVM_ARM_DEVICE_ID_SHIFT 16 -#define KVM_ARM_DEVICE_ID_MASK (0xffff << KVM_ARM_DEVICE_ID_SHIFT) +#define KVM_ARM_DEVICE_ID_MASK GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \ + KVM_ARM_DEVICE_ID_SHIFT) /* Supported device IDs */ #define KVM_ARM_DEVICE_VGIC_V2 0 diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 7a6b14874d65..a73cf01a1606 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -74,6 +74,7 @@ struct kvm_s390_io_adapter_req { #define KVM_S390_VM_CRYPTO 2 #define KVM_S390_VM_CPU_MODEL 3 #define KVM_S390_VM_MIGRATION 4 +#define KVM_S390_VM_CPU_TOPOLOGY 5 /* kvm attributes for mem_ctrl */ #define KVM_S390_VM_MEM_ENABLE_CMMA 0 diff --git a/tools/arch/x86/include/asm/amd-ibs.h b/tools/arch/x86/include/asm/amd-ibs.h index 765e9e752d03..93807b437e4d 100644 --- a/tools/arch/x86/include/asm/amd-ibs.h +++ b/tools/arch/x86/include/asm/amd-ibs.h @@ -6,6 +6,22 @@ #include "msr-index.h" +/* IBS_OP_DATA2 DataSrc */ +#define IBS_DATA_SRC_LOC_CACHE 2 +#define IBS_DATA_SRC_DRAM 3 +#define IBS_DATA_SRC_REM_CACHE 4 +#define IBS_DATA_SRC_IO 7 + +/* IBS_OP_DATA2 DataSrc Extension */ +#define IBS_DATA_SRC_EXT_LOC_CACHE 1 +#define IBS_DATA_SRC_EXT_NEAR_CCX_CACHE 2 +#define IBS_DATA_SRC_EXT_DRAM 3 +#define IBS_DATA_SRC_EXT_FAR_CCX_CACHE 5 +#define IBS_DATA_SRC_EXT_PMEM 6 +#define IBS_DATA_SRC_EXT_IO 7 +#define IBS_DATA_SRC_EXT_EXT_MEM 8 +#define IBS_DATA_SRC_EXT_PEER_AGENT_MEM 12 + /* * IBS Hardware MSRs */ @@ -29,7 +45,10 @@ union ibs_fetch_ctl { rand_en:1, /* 57: random tagging enable */ fetch_l2_miss:1,/* 58: L2 miss for sampled fetch * (needs IbsFetchComp) */ - reserved:5; /* 59-63: reserved */ + l3_miss_only:1, /* 59: Collect L3 miss samples only */ + fetch_oc_miss:1,/* 60: Op cache miss for the sampled fetch */ + fetch_l3_miss:1,/* 61: L3 cache miss for the sampled fetch */ + reserved:2; /* 62-63: reserved */ }; }; @@ -38,14 +57,14 @@ union ibs_op_ctl { __u64 val; struct { __u64 opmaxcnt:16, /* 0-15: periodic op max. count */ - reserved0:1, /* 16: reserved */ + l3_miss_only:1, /* 16: Collect L3 miss samples only */ op_en:1, /* 17: op sampling enable */ op_val:1, /* 18: op sample valid */ cnt_ctl:1, /* 19: periodic op counter control */ opmaxcnt_ext:7, /* 20-26: upper 7 bits of periodic op maximum count */ - reserved1:5, /* 27-31: reserved */ + reserved0:5, /* 27-31: reserved */ opcurcnt:27, /* 32-58: periodic op counter current count */ - reserved2:5; /* 59-63: reserved */ + reserved1:5; /* 59-63: reserved */ }; }; @@ -71,11 +90,12 @@ union ibs_op_data { union ibs_op_data2 { __u64 val; struct { - __u64 data_src:3, /* 0-2: data source */ + __u64 data_src_lo:3, /* 0-2: data source low */ reserved0:1, /* 3: reserved */ rmt_node:1, /* 4: destination node */ cache_hit_st:1, /* 5: cache hit state */ - reserved1:57; /* 5-63: reserved */ + data_src_hi:2, /* 6-7: data source high */ + reserved1:56; /* 8-63: reserved */ }; }; diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 03acc823838a..b71f4f2ecdd5 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -96,7 +96,7 @@ #define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ -/* FREE! ( 3*32+17) */ +#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 */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ @@ -203,8 +203,8 @@ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ -#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */ +#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ +#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* "" Fill RSB on VM-Exit */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ @@ -219,7 +219,7 @@ #define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */ #define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ #define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 or above (Zen) */ +#define X86_FEATURE_ZEN (7*32+28) /* "" CPU based on Zen microarchitecture */ #define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ #define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */ #define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */ @@ -296,6 +296,14 @@ #define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ #define X86_FEATURE_SGX1 (11*32+ 8) /* "" Basic SGX */ #define X86_FEATURE_SGX2 (11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */ +#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* "" Issue an IBPB on kernel entry */ +#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* "" RET prediction control */ +#define X86_FEATURE_RETPOLINE (11*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */ +#define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */ +#define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ +#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ +#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ @@ -316,6 +324,7 @@ #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_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ #define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ @@ -345,6 +354,7 @@ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ #define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ #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_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ @@ -447,5 +457,8 @@ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ +#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 */ #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 36369e76cc63..33d2cd04d254 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -50,6 +50,25 @@ # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif +#ifdef CONFIG_RETPOLINE +# define DISABLE_RETPOLINE 0 +#else +# define DISABLE_RETPOLINE ((1 << (X86_FEATURE_RETPOLINE & 31)) | \ + (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31))) +#endif + +#ifdef CONFIG_RETHUNK +# define DISABLE_RETHUNK 0 +#else +# define DISABLE_RETHUNK (1 << (X86_FEATURE_RETHUNK & 31)) +#endif + +#ifdef CONFIG_CPU_UNRET_ENTRY +# define DISABLE_UNRET 0 +#else +# define DISABLE_UNRET (1 << (X86_FEATURE_UNRET & 31)) +#endif + #ifdef CONFIG_INTEL_IOMMU_SVM # define DISABLE_ENQCMD 0 #else @@ -82,7 +101,7 @@ #define DISABLED_MASK8 (DISABLE_TDX_GUEST) #define DISABLED_MASK9 (DISABLE_SGX) #define DISABLED_MASK10 0 -#define DISABLED_MASK11 0 +#define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET) #define DISABLED_MASK12 0 #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index d27e0581b777..10ac52705892 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -51,6 +51,8 @@ #define SPEC_CTRL_STIBP BIT(SPEC_CTRL_STIBP_SHIFT) /* STIBP mask */ #define SPEC_CTRL_SSBD_SHIFT 2 /* Speculative Store Bypass Disable bit */ #define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ +#define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ +#define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ @@ -93,6 +95,7 @@ #define MSR_IA32_ARCH_CAPABILITIES 0x0000010a #define ARCH_CAP_RDCL_NO BIT(0) /* Not susceptible to Meltdown */ #define ARCH_CAP_IBRS_ALL BIT(1) /* Enhanced IBRS support */ +#define ARCH_CAP_RSBA BIT(2) /* RET may use alternative branch predictors */ #define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH BIT(3) /* Skip L1D flush on vmentry */ #define ARCH_CAP_SSB_NO BIT(4) /* * Not susceptible to Speculative Store Bypass @@ -140,6 +143,22 @@ * bit available to control VERW * behavior. */ +#define ARCH_CAP_RRSBA BIT(19) /* + * Indicates RET may use predictors + * other than the RSB. With eIBRS + * enabled predictions in kernel mode + * are restricted to targets in + * kernel. + */ +#define ARCH_CAP_PBRSB_NO BIT(24) /* + * Not susceptible to Post-Barrier + * Return Stack Buffer Predictions. + */ + +#define ARCH_CAP_XAPIC_DISABLE BIT(21) /* + * IA32_XAPIC_DISABLE_STATUS MSR + * supported + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -221,6 +240,12 @@ #define PERF_CAP_PT_IDX 16 #define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 +#define PERF_CAP_PEBS_TRAP BIT_ULL(6) +#define PERF_CAP_ARCH_REG BIT_ULL(7) +#define PERF_CAP_PEBS_FORMAT 0xf00 +#define PERF_CAP_PEBS_BASELINE BIT_ULL(14) +#define PERF_CAP_PEBS_MASK (PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \ + PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE) #define MSR_IA32_RTIT_CTL 0x00000570 #define RTIT_CTL_TRACEEN BIT(0) @@ -378,6 +403,7 @@ #define MSR_TURBO_ACTIVATION_RATIO 0x0000064C #define MSR_PLATFORM_ENERGY_STATUS 0x0000064D +#define MSR_SECONDARY_TURBO_RATIO_LIMIT 0x00000650 #define MSR_PKG_WEIGHTED_CORE_C0_RES 0x00000658 #define MSR_PKG_ANY_CORE_C0_RES 0x00000659 @@ -564,9 +590,15 @@ #define MSR_AMD64_PERF_CNTR_GLOBAL_CTL 0xc0000301 #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR 0xc0000302 +/* AMD Last Branch Record MSRs */ +#define MSR_AMD64_LBR_SELECT 0xc000010e + /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 +#define MSR_ZEN2_SPECTRAL_CHICKEN 0xc00110e3 +#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT BIT_ULL(1) + /* Fam 16h MSRs */ #define MSR_F16H_L2I_PERF_CTL 0xc0010230 #define MSR_F16H_L2I_PERF_CTR 0xc0010231 @@ -732,6 +764,8 @@ #define MSR_AMD_DBG_EXTN_CFG 0xc000010f #define MSR_AMD_SAMP_BR_FROM 0xc0010300 +#define DBG_EXTN_CFG_LBRV2EN BIT_ULL(6) + #define MSR_IA32_MPERF 0x000000e7 #define MSR_IA32_APERF 0x000000e8 @@ -1005,6 +1039,7 @@ #define MSR_IA32_VMX_TRUE_EXIT_CTLS 0x0000048f #define MSR_IA32_VMX_TRUE_ENTRY_CTLS 0x00000490 #define MSR_IA32_VMX_VMFUNC 0x00000491 +#define MSR_IA32_VMX_PROCBASED_CTLS3 0x00000492 /* VMX_BASIC bits and bitmasks */ #define VMX_BASIC_VMCS_SIZE_SHIFT 32 @@ -1029,4 +1064,12 @@ #define MSR_IA32_HW_FEEDBACK_PTR 0x17d0 #define MSR_IA32_HW_FEEDBACK_CONFIG 0x17d1 +/* x2APIC locked status */ +#define MSR_IA32_XAPIC_DISABLE_STATUS 0xBD +#define LEGACY_XAPIC_DISABLED BIT(0) /* + * x2APIC mode is locked and + * disabling x2APIC will cause + * a #GP + */ + #endif /* _ASM_X86_MSR_INDEX_H */ diff --git a/tools/arch/x86/include/asm/rmwcc.h b/tools/arch/x86/include/asm/rmwcc.h index fee7983a90b4..11ff975242ca 100644 --- a/tools/arch/x86/include/asm/rmwcc.h +++ b/tools/arch/x86/include/asm/rmwcc.h @@ -2,8 +2,6 @@ #ifndef _TOOLS_LINUX_ASM_X86_RMWcc #define _TOOLS_LINUX_ASM_X86_RMWcc -#ifdef CONFIG_CC_HAS_ASM_GOTO - #define __GEN_RMWcc(fullop, var, cc, ...) \ do { \ asm_volatile_goto (fullop "; j" cc " %l[cc_label]" \ @@ -20,23 +18,4 @@ cc_label: \ #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \ __GEN_RMWcc(op " %1, " arg0, var, cc, vcon (val)) -#else /* !CONFIG_CC_HAS_ASM_GOTO */ - -#define __GEN_RMWcc(fullop, var, cc, ...) \ -do { \ - char c; \ - asm volatile (fullop "; set" cc " %1" \ - : "+m" (var), "=qm" (c) \ - : __VA_ARGS__ : "memory"); \ - return c != 0; \ -} while (0) - -#define GEN_UNARY_RMWcc(op, var, arg0, cc) \ - __GEN_RMWcc(op " " arg0, var, cc) - -#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \ - __GEN_RMWcc(op " %2, " arg0, var, cc, vcon (val)) - -#endif /* CONFIG_CC_HAS_ASM_GOTO */ - #endif /* _TOOLS_LINUX_ASM_X86_RMWcc */ diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 21614807a2cb..46de10a809ec 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -198,13 +198,13 @@ struct kvm_msrs { __u32 nmsrs; /* number of msrs in entries */ __u32 pad; - struct kvm_msr_entry entries[0]; + struct kvm_msr_entry entries[]; }; /* for KVM_GET_MSR_INDEX_LIST */ struct kvm_msr_list { __u32 nmsrs; /* number of msrs in entries */ - __u32 indices[0]; + __u32 indices[]; }; /* Maximum size of any access bitmap in bytes */ @@ -241,7 +241,7 @@ struct kvm_cpuid_entry { struct kvm_cpuid { __u32 nent; __u32 padding; - struct kvm_cpuid_entry entries[0]; + struct kvm_cpuid_entry entries[]; }; struct kvm_cpuid_entry2 { @@ -263,7 +263,7 @@ struct kvm_cpuid_entry2 { struct kvm_cpuid2 { __u32 nent; __u32 padding; - struct kvm_cpuid_entry2 entries[0]; + struct kvm_cpuid_entry2 entries[]; }; /* for KVM_GET_PIT and KVM_SET_PIT */ @@ -306,7 +306,8 @@ struct kvm_pit_state { struct kvm_pit_channel_state channels[3]; }; -#define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001 +#define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001 +#define KVM_PIT_FLAGS_SPEAKER_DATA_ON 0x00000002 struct kvm_pit_state2 { struct kvm_pit_channel_state channels[3]; @@ -325,6 +326,7 @@ struct kvm_reinject_control { #define KVM_VCPUEVENT_VALID_SHADOW 0x00000004 #define KVM_VCPUEVENT_VALID_SMM 0x00000008 #define KVM_VCPUEVENT_VALID_PAYLOAD 0x00000010 +#define KVM_VCPUEVENT_VALID_TRIPLE_FAULT 0x00000020 /* Interrupt shadow states */ #define KVM_X86_SHADOW_INT_MOV_SS 0x01 @@ -359,7 +361,10 @@ struct kvm_vcpu_events { __u8 smm_inside_nmi; __u8 latched_init; } smi; - __u8 reserved[27]; + struct { + __u8 pending; + } triple_fault; + __u8 reserved[26]; __u8 exception_has_payload; __u64 exception_payload; }; @@ -389,7 +394,7 @@ struct kvm_xsave { * the contents of CPUID leaf 0xD on the host. */ __u32 region[1024]; - __u32 extra[0]; + __u32 extra[]; }; #define KVM_MAX_XCRS 16 @@ -434,6 +439,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) #define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4) #define KVM_X86_QUIRK_FIX_HYPERCALL_INSN (1 << 5) +#define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS (1 << 6) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 @@ -516,7 +522,7 @@ struct kvm_pmu_event_filter { __u32 fixed_counter_bitmap; __u32 flags; __u32 pad[4]; - __u64 events[0]; + __u64 events[]; }; #define KVM_PMU_EVENT_ALLOW 0 diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index 946d761adbd3..a5faf6d88f1b 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -91,6 +91,7 @@ #define EXIT_REASON_UMWAIT 67 #define EXIT_REASON_TPAUSE 68 #define EXIT_REASON_BUS_LOCK 74 +#define EXIT_REASON_NOTIFY 75 #define VMX_EXIT_REASONS \ { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ @@ -153,7 +154,8 @@ { EXIT_REASON_XRSTORS, "XRSTORS" }, \ { EXIT_REASON_UMWAIT, "UMWAIT" }, \ { EXIT_REASON_TPAUSE, "TPAUSE" }, \ - { EXIT_REASON_BUS_LOCK, "BUS_LOCK" } + { EXIT_REASON_BUS_LOCK, "BUS_LOCK" }, \ + { EXIT_REASON_NOTIFY, "NOTIFY" } #define VMX_EXIT_REASON_FLAGS \ { VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" } diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index d0d7b9bc6cad..5418e2f99834 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -27,7 +27,7 @@ * Output: * rax original destination */ -SYM_FUNC_START(__memcpy) +SYM_TYPED_FUNC_START(__memcpy) ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index b11cfc86a3d0..243b79f2b451 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -34,8 +34,8 @@ else endif FEATURE_USER = .bpf -FEATURE_TESTS = libbfd disassembler-four-args -FEATURE_DISPLAY = libbfd disassembler-four-args +FEATURE_TESTS = libbfd disassembler-four-args disassembler-init-styled +FEATURE_DISPLAY = libbfd check_feat := 1 NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean resolve_btfids_clean @@ -56,6 +56,9 @@ endif ifeq ($(feature-disassembler-four-args), 1) CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE endif +ifeq ($(feature-disassembler-init-styled), 1) +CFLAGS += -DDISASM_INIT_STYLED +endif $(OUTPUT)%.yacc.c: $(srctree)/tools/bpf/%.y $(QUIET_BISON)$(YACC) -o $@ -d $< diff --git a/tools/bpf/bpf_jit_disasm.c b/tools/bpf/bpf_jit_disasm.c index c8ae95804728..a90a5d110f92 100644 --- a/tools/bpf/bpf_jit_disasm.c +++ b/tools/bpf/bpf_jit_disasm.c @@ -28,6 +28,7 @@ #include <sys/types.h> #include <sys/stat.h> #include <limits.h> +#include <tools/dis-asm-compat.h> #define CMD_ACTION_SIZE_BUFFER 10 #define CMD_ACTION_READ_ALL 3 @@ -64,7 +65,9 @@ static void get_asm_insns(uint8_t *image, size_t len, int opcodes) assert(bfdf); assert(bfd_check_format(bfdf, bfd_object)); - init_disassemble_info(&info, stdout, (fprintf_ftype) fprintf); + init_disassemble_info_compat(&info, stdout, + (fprintf_ftype) fprintf, + fprintf_styled); info.arch = bfd_get_arch(bfdf); info.mach = bfd_get_mach(bfdf); info.buffer = image; diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index a17e9aa314fd..bd015ec9847b 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -31,11 +31,17 @@ CGROUP COMMANDS | **bpftool** **cgroup help** | | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } -| *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** | -| **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** | -| **getpeername4** | **getpeername6** | **getsockname4** | **getsockname6** | **sendmsg4** | -| **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** | -| **sock_release** } +| *ATTACH_TYPE* := { **cgroup_inet_ingress** | **cgroup_inet_egress** | +| **cgroup_inet_sock_create** | **cgroup_sock_ops** | +| **cgroup_device** | **cgroup_inet4_bind** | **cgroup_inet6_bind** | +| **cgroup_inet4_post_bind** | **cgroup_inet6_post_bind** | +| **cgroup_inet4_connect** | **cgroup_inet6_connect** | +| **cgroup_inet4_getpeername** | **cgroup_inet6_getpeername** | +| **cgroup_inet4_getsockname** | **cgroup_inet6_getsockname** | +| **cgroup_udp4_sendmsg** | **cgroup_udp6_sendmsg** | +| **cgroup_udp4_recvmsg** | **cgroup_udp6_recvmsg** | +| **cgroup_sysctl** | **cgroup_getsockopt** | **cgroup_setsockopt** | +| **cgroup_inet_sock_release** } | *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst index 4ce9a77bc1e0..e44039f89be7 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-feature.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst @@ -24,9 +24,11 @@ FEATURE COMMANDS ================ | **bpftool** **feature probe** [*COMPONENT*] [**full**] [**unprivileged**] [**macros** [**prefix** *PREFIX*]] +| **bpftool** **feature list_builtins** *GROUP* | **bpftool** **feature help** | | *COMPONENT* := { **kernel** | **dev** *NAME* } +| *GROUP* := { **prog_types** | **map_types** | **attach_types** | **link_types** | **helpers** } DESCRIPTION =========== @@ -70,6 +72,16 @@ DESCRIPTION The keywords **full**, **macros** and **prefix** have the same role as when probing the kernel. + **bpftool feature list_builtins** *GROUP* + List items known to bpftool. These can be BPF program types + (**prog_types**), BPF map types (**map_types**), attach types + (**attach_types**), link types (**link_types**), or BPF helper + functions (**helpers**). The command does not probe the system, but + simply lists the elements that bpftool knows from compilation time, + as provided from libbpf (for all object types) or from the BPF UAPI + header (list of helpers). This can be used in scripts to iterate over + BPF types or helpers. + **bpftool feature help** Print short help message. diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 7c188a598444..7f3b67a8b48f 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -55,7 +55,7 @@ MAP COMMANDS | | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** | | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** | | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** | **inode_storage** -| | **task_storage** | **bloom_filter** } +| | **task_storage** | **bloom_filter** | **user_ringbuf** } DESCRIPTION =========== diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index a2e9359e554c..eb1b2a254eb1 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -53,8 +53,9 @@ PROG COMMANDS | **cgroup/getsockopt** | **cgroup/setsockopt** | **cgroup/sock_release** | | **struct_ops** | **fentry** | **fexit** | **freplace** | **sk_lookup** | } -| *ATTACH_TYPE* := { -| **msg_verdict** | **skb_verdict** | **stream_verdict** | **stream_parser** | **flow_dissector** +| *ATTACH_TYPE* := { +| **sk_msg_verdict** | **sk_skb_verdict** | **sk_skb_stream_verdict** | +| **sk_skb_stream_parser** | **flow_dissector** | } | *METRICs* := { | **cycles** | **instructions** | **l1d_loads** | **llc_misses** | diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index c6d2c77d0252..4a95c017ad4c 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -53,7 +53,7 @@ $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_ $(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT) $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \ DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR:/=) prefix= \ - ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) $@ install_headers + ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) AR=$(HOSTAR) $@ install_headers $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS): $(LIBBPF_BOOTSTRAP_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_BOOTSTRAP_HDRS_DIR) $(call QUIET_INSTALL, $@) @@ -93,10 +93,11 @@ INSTALL ?= install RM ?= rm -f FEATURE_USER = .bpftool -FEATURE_TESTS = libbfd disassembler-four-args zlib libcap \ - clang-bpf-co-re -FEATURE_DISPLAY = libbfd disassembler-four-args zlib libcap \ +FEATURE_TESTS = libbfd libbfd-liberty libbfd-liberty-z \ + disassembler-four-args disassembler-init-styled libcap \ clang-bpf-co-re +FEATURE_DISPLAY = libbfd libbfd-liberty libbfd-liberty-z \ + libcap clang-bpf-co-re check_feat := 1 NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall @@ -117,6 +118,9 @@ endif ifeq ($(feature-disassembler-four-args), 1) CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE endif +ifeq ($(feature-disassembler-init-styled), 1) + CFLAGS += -DDISASM_INIT_STYLED +endif LIBS = $(LIBBPF) -lelf -lz LIBS_BOOTSTRAP = $(LIBBPF_BOOTSTRAP) -lelf -lz @@ -204,11 +208,6 @@ $(BOOTSTRAP_OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@ -$(OUTPUT)feature.o: -ifneq ($(feature-zlib), 1) - $(error "No zlib found") -endif - $(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP) $(QUIET_LINK)$(HOSTCC) $(HOST_CFLAGS) $(LDFLAGS) $(BOOTSTRAP_OBJS) $(LIBS_BOOTSTRAP) -o $@ diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 5df8d72c5179..dc1641e3670e 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -407,8 +407,8 @@ _bpftool() return 0 ;; 5) - local BPFTOOL_PROG_ATTACH_TYPES='msg_verdict \ - skb_verdict stream_verdict stream_parser \ + local BPFTOOL_PROG_ATTACH_TYPES='sk_msg_verdict \ + sk_skb_verdict sk_skb_stream_verdict sk_skb_stream_parser \ flow_dissector' COMPREPLY=( $( compgen -W "$BPFTOOL_PROG_ATTACH_TYPES" -- "$cur" ) ) return 0 @@ -703,15 +703,8 @@ _bpftool() return 0 ;; type) - local BPFTOOL_MAP_CREATE_TYPES='hash array \ - prog_array perf_event_array percpu_hash \ - percpu_array stack_trace cgroup_array lru_hash \ - lru_percpu_hash lpm_trie array_of_maps \ - hash_of_maps devmap devmap_hash sockmap cpumap \ - xskmap sockhash cgroup_storage reuseport_sockarray \ - percpu_cgroup_storage queue stack sk_storage \ - struct_ops ringbuf inode_storage task_storage \ - bloom_filter' + local BPFTOOL_MAP_CREATE_TYPES="$(bpftool feature list_builtins map_types 2>/dev/null | \ + grep -v '^unspec$')" COMPREPLY=( $( compgen -W "$BPFTOOL_MAP_CREATE_TYPES" -- "$cur" ) ) return 0 ;; @@ -1039,12 +1032,8 @@ _bpftool() return 0 ;; attach|detach) - local BPFTOOL_CGROUP_ATTACH_TYPES='ingress egress \ - sock_create sock_ops device \ - bind4 bind6 post_bind4 post_bind6 connect4 connect6 \ - getpeername4 getpeername6 getsockname4 getsockname6 \ - sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl getsockopt \ - setsockopt sock_release' + local BPFTOOL_CGROUP_ATTACH_TYPES="$(bpftool feature list_builtins attach_types 2>/dev/null | \ + grep '^cgroup_')" local ATTACH_FLAGS='multi override' local PROG_TYPE='id pinned tag name' # Check for $prev = $command first @@ -1173,9 +1162,14 @@ _bpftool() _bpftool_once_attr 'full unprivileged' return 0 ;; + list_builtins) + [[ $prev != "$command" ]] && return 0 + COMPREPLY=( $( compgen -W 'prog_types map_types \ + attach_types link_types helpers' -- "$cur" ) ) + ;; *) [[ $prev == $object ]] && \ - COMPREPLY=( $( compgen -W 'help probe' -- "$cur" ) ) + COMPREPLY=( $( compgen -W 'help list_builtins probe' -- "$cur" ) ) ;; esac ;; diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 7e6accb9d9f7..68a70ac03c80 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -40,11 +40,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_FLOAT] = "FLOAT", [BTF_KIND_DECL_TAG] = "DECL_TAG", [BTF_KIND_TYPE_TAG] = "TYPE_TAG", -}; - -struct btf_attach_point { - __u32 obj_id; - __u32 btf_id; + [BTF_KIND_ENUM64] = "ENUM64", }; static const char *btf_int_enc_str(__u8 encoding) @@ -212,26 +208,76 @@ static int dump_btf_type(const struct btf *btf, __u32 id, case BTF_KIND_ENUM: { const struct btf_enum *v = (const void *)(t + 1); __u16 vlen = BTF_INFO_VLEN(t->info); + const char *encoding; int i; + encoding = btf_kflag(t) ? "SIGNED" : "UNSIGNED"; if (json_output) { + jsonw_string_field(w, "encoding", encoding); jsonw_uint_field(w, "size", t->size); jsonw_uint_field(w, "vlen", vlen); jsonw_name(w, "values"); jsonw_start_array(w); } else { - printf(" size=%u vlen=%u", t->size, vlen); + printf(" encoding=%s size=%u vlen=%u", encoding, t->size, vlen); + } + for (i = 0; i < vlen; i++, v++) { + const char *name = btf_str(btf, v->name_off); + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + if (btf_kflag(t)) + jsonw_int_field(w, "val", v->val); + else + jsonw_uint_field(w, "val", v->val); + jsonw_end_object(w); + } else { + if (btf_kflag(t)) + printf("\n\t'%s' val=%d", name, v->val); + else + printf("\n\t'%s' val=%u", name, v->val); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_ENUM64: { + const struct btf_enum64 *v = btf_enum64(t); + __u16 vlen = btf_vlen(t); + const char *encoding; + int i; + + encoding = btf_kflag(t) ? "SIGNED" : "UNSIGNED"; + if (json_output) { + jsonw_string_field(w, "encoding", encoding); + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "values"); + jsonw_start_array(w); + } else { + printf(" encoding=%s size=%u vlen=%u", encoding, t->size, vlen); } for (i = 0; i < vlen; i++, v++) { const char *name = btf_str(btf, v->name_off); + __u64 val = ((__u64)v->val_hi32 << 32) | v->val_lo32; if (json_output) { jsonw_start_object(w); jsonw_string_field(w, "name", name); - jsonw_uint_field(w, "val", v->val); + if (btf_kflag(t)) + jsonw_int_field(w, "val", val); + else + jsonw_uint_field(w, "val", val); jsonw_end_object(w); } else { - printf("\n\t'%s' val=%u", name, v->val); + if (btf_kflag(t)) + printf("\n\t'%s' val=%lldLL", name, + (unsigned long long)val); + else + printf("\n\t'%s' val=%lluULL", name, + (unsigned long long)val); } } if (json_output) @@ -589,10 +635,9 @@ static int do_dump(int argc, char **argv) btf = btf__parse_split(*argv, base ?: base_btf); err = libbpf_get_error(btf); - if (err) { - btf = NULL; + if (!btf) { p_err("failed to load BTF from %s: %s", - *argv, strerror(err)); + *argv, strerror(errno)); goto done; } NEXT_ARG(); @@ -637,8 +682,8 @@ static int do_dump(int argc, char **argv) btf = btf__load_from_kernel_by_id_split(btf_id, base_btf); err = libbpf_get_error(btf); - if (err) { - p_err("get btf by id (%u): %s", btf_id, strerror(err)); + if (!btf) { + p_err("get btf by id (%u): %s", btf_id, strerror(errno)); goto done; } } @@ -774,7 +819,7 @@ build_btf_type_table(struct hashmap *tab, enum bpf_obj_type type, u32_as_hash_field(id)); if (err) { p_err("failed to append entry to hashmap for BTF ID %u, object ID %u: %s", - btf_id, id, strerror(errno)); + btf_id, id, strerror(-err)); goto err_free; } } diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index f5dddf8ef404..19924b6ce796 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -182,6 +182,32 @@ static int btf_dumper_enum(const struct btf_dumper *d, return 0; } +static int btf_dumper_enum64(const struct btf_dumper *d, + const struct btf_type *t, + const void *data) +{ + const struct btf_enum64 *enums = btf_enum64(t); + __u32 val_lo32, val_hi32; + __u64 value; + __u16 i; + + value = *(__u64 *)data; + val_lo32 = (__u32)value; + val_hi32 = value >> 32; + + for (i = 0; i < btf_vlen(t); i++) { + if (val_lo32 == enums[i].val_lo32 && val_hi32 == enums[i].val_hi32) { + jsonw_string(d->jw, + btf__name_by_offset(d->btf, + enums[i].name_off)); + return 0; + } + } + + jsonw_int(d->jw, value); + return 0; +} + static bool is_str_array(const struct btf *btf, const struct btf_array *arr, const char *s) { @@ -426,7 +452,7 @@ static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset, *(char *)data); break; case BTF_INT_BOOL: - jsonw_bool(jw, *(int *)data); + jsonw_bool(jw, *(bool *)data); break; default: /* shouldn't happen */ @@ -542,6 +568,8 @@ static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, return btf_dumper_array(d, type_id, data); case BTF_KIND_ENUM: return btf_dumper_enum(d, t, data); + case BTF_KIND_ENUM64: + return btf_dumper_enum64(d, t, data); case BTF_KIND_PTR: btf_dumper_ptr(d, t, data); return 0; @@ -618,6 +646,7 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id, btf__name_by_offset(btf, t->name_off)); break; case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: BTF_PRINT_ARG("enum %s ", btf__name_by_offset(btf, t->name_off)); break; diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index effe136119d7..b46a998d8f8d 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -15,43 +15,92 @@ #include <unistd.h> #include <bpf/bpf.h> +#include <bpf/btf.h> #include "main.h" #define HELP_SPEC_ATTACH_FLAGS \ "ATTACH_FLAGS := { multi | override }" -#define HELP_SPEC_ATTACH_TYPES \ - " ATTACH_TYPE := { ingress | egress | sock_create |\n" \ - " sock_ops | device | bind4 | bind6 |\n" \ - " post_bind4 | post_bind6 | connect4 |\n" \ - " connect6 | getpeername4 | getpeername6 |\n" \ - " getsockname4 | getsockname6 | sendmsg4 |\n" \ - " sendmsg6 | recvmsg4 | recvmsg6 |\n" \ - " sysctl | getsockopt | setsockopt |\n" \ - " sock_release }" +#define HELP_SPEC_ATTACH_TYPES \ + " ATTACH_TYPE := { cgroup_inet_ingress | cgroup_inet_egress |\n" \ + " cgroup_inet_sock_create | cgroup_sock_ops |\n" \ + " cgroup_device | cgroup_inet4_bind |\n" \ + " cgroup_inet6_bind | cgroup_inet4_post_bind |\n" \ + " cgroup_inet6_post_bind | cgroup_inet4_connect |\n" \ + " cgroup_inet6_connect | cgroup_inet4_getpeername |\n" \ + " cgroup_inet6_getpeername | cgroup_inet4_getsockname |\n" \ + " cgroup_inet6_getsockname | cgroup_udp4_sendmsg |\n" \ + " cgroup_udp6_sendmsg | cgroup_udp4_recvmsg |\n" \ + " cgroup_udp6_recvmsg | cgroup_sysctl |\n" \ + " cgroup_getsockopt | cgroup_setsockopt |\n" \ + " cgroup_inet_sock_release }" static unsigned int query_flags; +static struct btf *btf_vmlinux; +static __u32 btf_vmlinux_id; static enum bpf_attach_type parse_attach_type(const char *str) { + const char *attach_type_str; enum bpf_attach_type type; - for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { - if (attach_type_name[type] && - is_prefix(str, attach_type_name[type])) + for (type = 0; ; type++) { + attach_type_str = libbpf_bpf_attach_type_str(type); + if (!attach_type_str) + break; + if (!strcmp(str, attach_type_str)) + return type; + } + + /* Also check traditionally used attach type strings. For these we keep + * allowing prefixed usage. + */ + for (type = 0; ; type++) { + attach_type_str = bpf_attach_type_input_str(type); + if (!attach_type_str) + break; + if (is_prefix(str, attach_type_str)) return type; } return __MAX_BPF_ATTACH_TYPE; } +static void guess_vmlinux_btf_id(__u32 attach_btf_obj_id) +{ + struct bpf_btf_info btf_info = {}; + __u32 btf_len = sizeof(btf_info); + char name[16] = {}; + int err; + int fd; + + btf_info.name = ptr_to_u64(name); + btf_info.name_len = sizeof(name); + + fd = bpf_btf_get_fd_by_id(attach_btf_obj_id); + if (fd < 0) + return; + + err = bpf_obj_get_info_by_fd(fd, &btf_info, &btf_len); + if (err) + goto out; + + if (btf_info.kernel_btf && strncmp(name, "vmlinux", sizeof(name)) == 0) + btf_vmlinux_id = btf_info.id; + +out: + close(fd); +} + static int show_bpf_prog(int id, enum bpf_attach_type attach_type, const char *attach_flags_str, int level) { char prog_name[MAX_PROG_FULL_NAME]; + const char *attach_btf_name = NULL; struct bpf_prog_info info = {}; + const char *attach_type_str; __u32 info_len = sizeof(info); int prog_fd; @@ -64,26 +113,53 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, return -1; } + attach_type_str = libbpf_bpf_attach_type_str(attach_type); + + if (btf_vmlinux) { + if (!btf_vmlinux_id) + guess_vmlinux_btf_id(info.attach_btf_obj_id); + + if (btf_vmlinux_id == info.attach_btf_obj_id && + info.attach_btf_id < btf__type_cnt(btf_vmlinux)) { + const struct btf_type *t = + btf__type_by_id(btf_vmlinux, info.attach_btf_id); + attach_btf_name = + btf__name_by_offset(btf_vmlinux, t->name_off); + } + } + get_prog_full_name(&info, prog_fd, prog_name, sizeof(prog_name)); if (json_output) { jsonw_start_object(json_wtr); jsonw_uint_field(json_wtr, "id", info.id); - if (attach_type < ARRAY_SIZE(attach_type_name)) - jsonw_string_field(json_wtr, "attach_type", - attach_type_name[attach_type]); + if (attach_type_str) + jsonw_string_field(json_wtr, "attach_type", attach_type_str); else jsonw_uint_field(json_wtr, "attach_type", attach_type); - jsonw_string_field(json_wtr, "attach_flags", - attach_flags_str); + if (!(query_flags & BPF_F_QUERY_EFFECTIVE)) + jsonw_string_field(json_wtr, "attach_flags", attach_flags_str); jsonw_string_field(json_wtr, "name", prog_name); + if (attach_btf_name) + jsonw_string_field(json_wtr, "attach_btf_name", attach_btf_name); + jsonw_uint_field(json_wtr, "attach_btf_obj_id", info.attach_btf_obj_id); + jsonw_uint_field(json_wtr, "attach_btf_id", info.attach_btf_id); jsonw_end_object(json_wtr); } else { printf("%s%-8u ", level ? " " : "", info.id); - if (attach_type < ARRAY_SIZE(attach_type_name)) - printf("%-15s", attach_type_name[attach_type]); + if (attach_type_str) + printf("%-15s", attach_type_str); else printf("type %-10u", attach_type); - printf(" %-15s %-15s\n", attach_flags_str, prog_name); + if (query_flags & BPF_F_QUERY_EFFECTIVE) + printf(" %-15s", prog_name); + else + printf(" %-15s %-15s", attach_flags_str, prog_name); + if (attach_btf_name) + printf(" %-15s", attach_btf_name); + else if (info.attach_btf_id) + printf(" attach_btf_obj_id=%d attach_btf_id=%d", + info.attach_btf_obj_id, info.attach_btf_id); + printf("\n"); } close(prog_fd); @@ -122,47 +198,90 @@ static int cgroup_has_attached_progs(int cgroup_fd) return no_prog ? 0 : 1; } + +static int show_effective_bpf_progs(int cgroup_fd, enum bpf_attach_type type, + int level) +{ + LIBBPF_OPTS(bpf_prog_query_opts, p); + __u32 prog_ids[1024] = {0}; + __u32 iter; + int ret; + + p.query_flags = query_flags; + p.prog_cnt = ARRAY_SIZE(prog_ids); + p.prog_ids = prog_ids; + + ret = bpf_prog_query_opts(cgroup_fd, type, &p); + if (ret) + return ret; + + if (p.prog_cnt == 0) + return 0; + + for (iter = 0; iter < p.prog_cnt; iter++) + show_bpf_prog(prog_ids[iter], type, NULL, level); + + return 0; +} + static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, int level) { + LIBBPF_OPTS(bpf_prog_query_opts, p); + __u32 prog_attach_flags[1024] = {0}; const char *attach_flags_str; __u32 prog_ids[1024] = {0}; - __u32 prog_cnt, iter; - __u32 attach_flags; char buf[32]; + __u32 iter; int ret; - prog_cnt = ARRAY_SIZE(prog_ids); - ret = bpf_prog_query(cgroup_fd, type, query_flags, &attach_flags, - prog_ids, &prog_cnt); + p.query_flags = query_flags; + p.prog_cnt = ARRAY_SIZE(prog_ids); + p.prog_ids = prog_ids; + p.prog_attach_flags = prog_attach_flags; + + ret = bpf_prog_query_opts(cgroup_fd, type, &p); if (ret) return ret; - if (prog_cnt == 0) + if (p.prog_cnt == 0) return 0; - switch (attach_flags) { - case BPF_F_ALLOW_MULTI: - attach_flags_str = "multi"; - break; - case BPF_F_ALLOW_OVERRIDE: - attach_flags_str = "override"; - break; - case 0: - attach_flags_str = ""; - break; - default: - snprintf(buf, sizeof(buf), "unknown(%x)", attach_flags); - attach_flags_str = buf; - } + for (iter = 0; iter < p.prog_cnt; iter++) { + __u32 attach_flags; + + attach_flags = prog_attach_flags[iter] ?: p.attach_flags; + + switch (attach_flags) { + case BPF_F_ALLOW_MULTI: + attach_flags_str = "multi"; + break; + case BPF_F_ALLOW_OVERRIDE: + attach_flags_str = "override"; + break; + case 0: + attach_flags_str = ""; + break; + default: + snprintf(buf, sizeof(buf), "unknown(%x)", attach_flags); + attach_flags_str = buf; + } - for (iter = 0; iter < prog_cnt; iter++) show_bpf_prog(prog_ids[iter], type, attach_flags_str, level); + } return 0; } +static int show_bpf_progs(int cgroup_fd, enum bpf_attach_type type, + int level) +{ + return query_flags & BPF_F_QUERY_EFFECTIVE ? + show_effective_bpf_progs(cgroup_fd, type, level) : + show_attached_bpf_progs(cgroup_fd, type, level); +} + static int do_show(int argc, char **argv) { enum bpf_attach_type type; @@ -210,10 +329,13 @@ static int do_show(int argc, char **argv) if (json_output) jsonw_start_array(json_wtr); + else if (query_flags & BPF_F_QUERY_EFFECTIVE) + printf("%-8s %-15s %-15s\n", "ID", "AttachType", "Name"); else printf("%-8s %-15s %-15s %-15s\n", "ID", "AttachType", "AttachFlags", "Name"); + btf_vmlinux = libbpf_find_kernel_btf(); for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { /* * Not all attach types may be supported, so it's expected, @@ -221,7 +343,7 @@ static int do_show(int argc, char **argv) * If we were able to get the show for at least one * attach type, let's return 0. */ - if (show_attached_bpf_progs(cgroup_fd, type, 0) == 0) + if (show_bpf_progs(cgroup_fd, type, 0) == 0) ret = 0; } @@ -277,8 +399,9 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb, printf("%s\n", fpath); } + btf_vmlinux = libbpf_find_kernel_btf(); for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) - show_attached_bpf_progs(cgroup_fd, type, ftw->level); + show_bpf_progs(cgroup_fd, type, ftw->level); if (errno == EINVAL) /* Last attach type does not support query. @@ -352,6 +475,11 @@ static int do_show_tree(int argc, char **argv) if (json_output) jsonw_start_array(json_wtr); + else if (query_flags & BPF_F_QUERY_EFFECTIVE) + printf("%s\n" + "%-8s %-15s %-15s\n", + "CgroupPath", + "ID", "AttachType", "Name"); else printf("%s\n" "%-8s %-15s %-15s %-15s\n", diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index c740142c24d8..0cdb4f711510 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -13,13 +13,17 @@ #include <stdlib.h> #include <string.h> #include <unistd.h> -#include <linux/limits.h> -#include <linux/magic.h> #include <net/if.h> #include <sys/mount.h> +#include <sys/resource.h> #include <sys/stat.h> #include <sys/vfs.h> +#include <linux/filter.h> +#include <linux/limits.h> +#include <linux/magic.h> +#include <linux/unistd.h> + #include <bpf/bpf.h> #include <bpf/hashmap.h> #include <bpf/libbpf.h> /* libbpf_num_possible_cpus */ @@ -31,52 +35,6 @@ #define BPF_FS_MAGIC 0xcafe4a11 #endif -const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = { - [BPF_CGROUP_INET_INGRESS] = "ingress", - [BPF_CGROUP_INET_EGRESS] = "egress", - [BPF_CGROUP_INET_SOCK_CREATE] = "sock_create", - [BPF_CGROUP_INET_SOCK_RELEASE] = "sock_release", - [BPF_CGROUP_SOCK_OPS] = "sock_ops", - [BPF_CGROUP_DEVICE] = "device", - [BPF_CGROUP_INET4_BIND] = "bind4", - [BPF_CGROUP_INET6_BIND] = "bind6", - [BPF_CGROUP_INET4_CONNECT] = "connect4", - [BPF_CGROUP_INET6_CONNECT] = "connect6", - [BPF_CGROUP_INET4_POST_BIND] = "post_bind4", - [BPF_CGROUP_INET6_POST_BIND] = "post_bind6", - [BPF_CGROUP_INET4_GETPEERNAME] = "getpeername4", - [BPF_CGROUP_INET6_GETPEERNAME] = "getpeername6", - [BPF_CGROUP_INET4_GETSOCKNAME] = "getsockname4", - [BPF_CGROUP_INET6_GETSOCKNAME] = "getsockname6", - [BPF_CGROUP_UDP4_SENDMSG] = "sendmsg4", - [BPF_CGROUP_UDP6_SENDMSG] = "sendmsg6", - [BPF_CGROUP_SYSCTL] = "sysctl", - [BPF_CGROUP_UDP4_RECVMSG] = "recvmsg4", - [BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6", - [BPF_CGROUP_GETSOCKOPT] = "getsockopt", - [BPF_CGROUP_SETSOCKOPT] = "setsockopt", - [BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser", - [BPF_SK_SKB_STREAM_VERDICT] = "sk_skb_stream_verdict", - [BPF_SK_SKB_VERDICT] = "sk_skb_verdict", - [BPF_SK_MSG_VERDICT] = "sk_msg_verdict", - [BPF_LIRC_MODE2] = "lirc_mode2", - [BPF_FLOW_DISSECTOR] = "flow_dissector", - [BPF_TRACE_RAW_TP] = "raw_tp", - [BPF_TRACE_FENTRY] = "fentry", - [BPF_TRACE_FEXIT] = "fexit", - [BPF_MODIFY_RETURN] = "mod_ret", - [BPF_LSM_MAC] = "lsm_mac", - [BPF_SK_LOOKUP] = "sk_lookup", - [BPF_TRACE_ITER] = "trace_iter", - [BPF_XDP_DEVMAP] = "xdp_devmap", - [BPF_XDP_CPUMAP] = "xdp_cpumap", - [BPF_XDP] = "xdp", - [BPF_SK_REUSEPORT_SELECT] = "sk_skb_reuseport_select", - [BPF_SK_REUSEPORT_SELECT_OR_MIGRATE] = "sk_skb_reuseport_select_or_migrate", - [BPF_PERF_EVENT] = "perf_event", - [BPF_TRACE_KPROBE_MULTI] = "trace_kprobe_multi", -}; - void p_err(const char *fmt, ...) { va_list ap; @@ -118,6 +76,75 @@ static bool is_bpffs(char *path) return (unsigned long)st_fs.f_type == BPF_FS_MAGIC; } +/* Probe whether kernel switched from memlock-based (RLIMIT_MEMLOCK) to + * memcg-based memory accounting for BPF maps and programs. This was done in + * commit 97306be45fbe ("Merge branch 'switch to memcg-based memory + * accounting'"), in Linux 5.11. + * + * Libbpf also offers to probe for memcg-based accounting vs rlimit, but does + * so by checking for the availability of a given BPF helper and this has + * failed on some kernels with backports in the past, see commit 6b4384ff1088 + * ("Revert "bpftool: Use libbpf 1.0 API mode instead of RLIMIT_MEMLOCK""). + * Instead, we can probe by lowering the process-based rlimit to 0, trying to + * load a BPF object, and resetting the rlimit. If the load succeeds then + * memcg-based accounting is supported. + * + * This would be too dangerous to do in the library, because multithreaded + * applications might attempt to load items while the rlimit is at 0. Given + * that bpftool is single-threaded, this is fine to do here. + */ +static bool known_to_need_rlimit(void) +{ + struct rlimit rlim_init, rlim_cur_zero = {}; + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + size_t insn_cnt = ARRAY_SIZE(insns); + union bpf_attr attr; + int prog_fd, err; + + memset(&attr, 0, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = insn_cnt; + attr.license = ptr_to_u64("GPL"); + + if (getrlimit(RLIMIT_MEMLOCK, &rlim_init)) + return false; + + /* Drop the soft limit to zero. We maintain the hard limit to its + * current value, because lowering it would be a permanent operation + * for unprivileged users. + */ + rlim_cur_zero.rlim_max = rlim_init.rlim_max; + if (setrlimit(RLIMIT_MEMLOCK, &rlim_cur_zero)) + return false; + + /* Do not use bpf_prog_load() from libbpf here, because it calls + * bump_rlimit_memlock(), interfering with the current probe. + */ + prog_fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); + err = errno; + + /* reset soft rlimit to its initial value */ + setrlimit(RLIMIT_MEMLOCK, &rlim_init); + + if (prog_fd < 0) + return err == EPERM; + + close(prog_fd); + return false; +} + +void set_max_rlimit(void) +{ + struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; + + if (known_to_need_rlimit()) + setrlimit(RLIMIT_MEMLOCK, &rinf); +} + static int mnt_fs(const char *target, const char *type, char *buff, size_t bufflen) { @@ -273,6 +300,9 @@ int do_pin_any(int argc, char **argv, int (*get_fd)(int *, char ***)) int err; int fd; + if (!REQ_ARGS(3)) + return -EINVAL; + fd = get_fd(&argc, &argv); if (fd < 0) return fd; @@ -289,6 +319,7 @@ const char *get_fd_type_name(enum bpf_obj_type type) [BPF_OBJ_UNKNOWN] = "unknown", [BPF_OBJ_PROG] = "prog", [BPF_OBJ_MAP] = "map", + [BPF_OBJ_LINK] = "link", }; if (type < 0 || type >= ARRAY_SIZE(names) || !names[type]) @@ -694,6 +725,7 @@ print_all_levels(__maybe_unused enum libbpf_print_level level, static int prog_fd_by_nametag(void *nametag, int **fds, bool tag) { + char prog_name[MAX_PROG_FULL_NAME]; unsigned int id = 0; int fd, nb_fds = 0; void *tmp; @@ -726,12 +758,20 @@ static int prog_fd_by_nametag(void *nametag, int **fds, bool tag) goto err_close_fd; } - if ((tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) || - (!tag && strncmp(nametag, info.name, BPF_OBJ_NAME_LEN))) { + if (tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) { close(fd); continue; } + if (!tag) { + get_prog_full_name(&info, fd, prog_name, + sizeof(prog_name)); + if (strncmp(nametag, prog_name, sizeof(prog_name))) { + close(fd); + continue; + } + } + if (nb_fds > 0) { tmp = realloc(*fds, (nb_fds + 1) * sizeof(int)); if (!tmp) { @@ -792,7 +832,7 @@ int prog_parse_fds(int *argc, char ***argv, int **fds) NEXT_ARGP(); name = **argv; - if (strlen(name) > BPF_OBJ_NAME_LEN - 1) { + if (strlen(name) > MAX_PROG_FULL_NAME - 1) { p_err("can't parse name"); return -1; } @@ -1009,3 +1049,39 @@ bool equal_fn_for_key_as_id(const void *k1, const void *k2, void *ctx) { return k1 == k2; } + +const char *bpf_attach_type_input_str(enum bpf_attach_type t) +{ + switch (t) { + case BPF_CGROUP_INET_INGRESS: return "ingress"; + case BPF_CGROUP_INET_EGRESS: return "egress"; + case BPF_CGROUP_INET_SOCK_CREATE: return "sock_create"; + case BPF_CGROUP_INET_SOCK_RELEASE: return "sock_release"; + case BPF_CGROUP_SOCK_OPS: return "sock_ops"; + case BPF_CGROUP_DEVICE: return "device"; + case BPF_CGROUP_INET4_BIND: return "bind4"; + case BPF_CGROUP_INET6_BIND: return "bind6"; + case BPF_CGROUP_INET4_CONNECT: return "connect4"; + case BPF_CGROUP_INET6_CONNECT: return "connect6"; + case BPF_CGROUP_INET4_POST_BIND: return "post_bind4"; + case BPF_CGROUP_INET6_POST_BIND: return "post_bind6"; + case BPF_CGROUP_INET4_GETPEERNAME: return "getpeername4"; + case BPF_CGROUP_INET6_GETPEERNAME: return "getpeername6"; + case BPF_CGROUP_INET4_GETSOCKNAME: return "getsockname4"; + case BPF_CGROUP_INET6_GETSOCKNAME: return "getsockname6"; + case BPF_CGROUP_UDP4_SENDMSG: return "sendmsg4"; + case BPF_CGROUP_UDP6_SENDMSG: return "sendmsg6"; + case BPF_CGROUP_SYSCTL: return "sysctl"; + case BPF_CGROUP_UDP4_RECVMSG: return "recvmsg4"; + case BPF_CGROUP_UDP6_RECVMSG: return "recvmsg6"; + case BPF_CGROUP_GETSOCKOPT: return "getsockopt"; + case BPF_CGROUP_SETSOCKOPT: return "setsockopt"; + case BPF_TRACE_RAW_TP: return "raw_tp"; + case BPF_TRACE_FENTRY: return "fentry"; + case BPF_TRACE_FEXIT: return "fexit"; + case BPF_MODIFY_RETURN: return "mod_ret"; + case BPF_SK_REUSEPORT_SELECT: return "sk_skb_reuseport_select"; + case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE: return "sk_skb_reuseport_select_or_migrate"; + default: return libbpf_bpf_attach_type_str(t); + } +} diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index d12f46051aac..36cf0f1517c9 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -548,8 +548,8 @@ static bool probe_prog_type_ifindex(enum bpf_prog_type prog_type, __u32 ifindex) } static void -probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, - const char *define_prefix, __u32 ifindex) +probe_prog_type(enum bpf_prog_type prog_type, const char *prog_type_str, + bool *supported_types, const char *define_prefix, __u32 ifindex) { char feat_name[128], plain_desc[128], define_name[128]; const char *plain_comment = "eBPF program_type "; @@ -580,20 +580,16 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, supported_types[prog_type] |= res; - if (!prog_type_name[prog_type]) { - p_info("program type name not found (type %d)", prog_type); - return; - } maxlen = sizeof(plain_desc) - strlen(plain_comment) - 1; - if (strlen(prog_type_name[prog_type]) > maxlen) { + if (strlen(prog_type_str) > maxlen) { p_info("program type name too long"); return; } - sprintf(feat_name, "have_%s_prog_type", prog_type_name[prog_type]); - sprintf(define_name, "%s_prog_type", prog_type_name[prog_type]); + sprintf(feat_name, "have_%s_prog_type", prog_type_str); + sprintf(define_name, "%s_prog_type", prog_type_str); uppercase(define_name, sizeof(define_name)); - sprintf(plain_desc, "%s%s", plain_comment, prog_type_name[prog_type]); + sprintf(plain_desc, "%s%s", plain_comment, prog_type_str); print_bool_feature(feat_name, plain_desc, define_name, res, define_prefix); } @@ -619,8 +615,8 @@ static bool probe_map_type_ifindex(enum bpf_map_type map_type, __u32 ifindex) } static void -probe_map_type(enum bpf_map_type map_type, const char *define_prefix, - __u32 ifindex) +probe_map_type(enum bpf_map_type map_type, char const *map_type_str, + const char *define_prefix, __u32 ifindex) { char feat_name[128], plain_desc[128], define_name[128]; const char *plain_comment = "eBPF map_type "; @@ -645,20 +641,16 @@ probe_map_type(enum bpf_map_type map_type, const char *define_prefix, * check required for unprivileged users */ - if (!map_type_name[map_type]) { - p_info("map type name not found (type %d)", map_type); - return; - } maxlen = sizeof(plain_desc) - strlen(plain_comment) - 1; - if (strlen(map_type_name[map_type]) > maxlen) { + if (strlen(map_type_str) > maxlen) { p_info("map type name too long"); return; } - sprintf(feat_name, "have_%s_map_type", map_type_name[map_type]); - sprintf(define_name, "%s_map_type", map_type_name[map_type]); + sprintf(feat_name, "have_%s_map_type", map_type_str); + sprintf(define_name, "%s_map_type", map_type_str); uppercase(define_name, sizeof(define_name)); - sprintf(plain_desc, "%s%s", plain_comment, map_type_name[map_type]); + sprintf(plain_desc, "%s%s", plain_comment, map_type_str); print_bool_feature(feat_name, plain_desc, define_name, res, define_prefix); } @@ -728,10 +720,10 @@ probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, } static void -probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, +probe_helpers_for_progtype(enum bpf_prog_type prog_type, + const char *prog_type_str, bool supported_type, const char *define_prefix, __u32 ifindex) { - const char *ptype_name = prog_type_name[prog_type]; char feat_name[128]; unsigned int id; bool probe_res = false; @@ -747,12 +739,12 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, } if (json_output) { - sprintf(feat_name, "%s_available_helpers", ptype_name); + sprintf(feat_name, "%s_available_helpers", prog_type_str); jsonw_name(json_wtr, feat_name); jsonw_start_array(json_wtr); } else if (!define_prefix) { printf("eBPF helpers supported for program type %s:", - ptype_name); + prog_type_str); } for (id = 1; id < ARRAY_SIZE(helper_name); id++) { @@ -768,7 +760,7 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, /* fallthrough */ default: probe_res |= probe_helper_for_progtype(prog_type, supported_type, - define_prefix, id, ptype_name, + define_prefix, id, prog_type_str, ifindex); } } @@ -943,30 +935,47 @@ static void section_program_types(bool *supported_types, const char *define_prefix, __u32 ifindex) { - unsigned int i; + unsigned int prog_type = BPF_PROG_TYPE_UNSPEC; + const char *prog_type_str; print_start_section("program_types", "Scanning eBPF program types...", "/*** eBPF program types ***/", define_prefix); - for (i = BPF_PROG_TYPE_UNSPEC + 1; i < prog_type_name_size; i++) - probe_prog_type(i, supported_types, define_prefix, ifindex); + while (true) { + prog_type++; + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + /* libbpf will return NULL for variants unknown to it. */ + if (!prog_type_str) + break; + + probe_prog_type(prog_type, prog_type_str, supported_types, define_prefix, + ifindex); + } print_end_section(); } static void section_map_types(const char *define_prefix, __u32 ifindex) { - unsigned int i; + unsigned int map_type = BPF_MAP_TYPE_UNSPEC; + const char *map_type_str; print_start_section("map_types", "Scanning eBPF map types...", "/*** eBPF map types ***/", define_prefix); - for (i = BPF_MAP_TYPE_UNSPEC + 1; i < map_type_name_size; i++) - probe_map_type(i, define_prefix, ifindex); + while (true) { + map_type++; + map_type_str = libbpf_bpf_map_type_str(map_type); + /* libbpf will return NULL for variants unknown to it. */ + if (!map_type_str) + break; + + probe_map_type(map_type, map_type_str, define_prefix, ifindex); + } print_end_section(); } @@ -974,7 +983,8 @@ static void section_map_types(const char *define_prefix, __u32 ifindex) static void section_helpers(bool *supported_types, const char *define_prefix, __u32 ifindex) { - unsigned int i; + unsigned int prog_type = BPF_PROG_TYPE_UNSPEC; + const char *prog_type_str; print_start_section("helpers", "Scanning eBPF helper functions...", @@ -996,9 +1006,18 @@ section_helpers(bool *supported_types, const char *define_prefix, __u32 ifindex) " %sBPF__PROG_TYPE_ ## prog_type ## __HELPER_ ## helper\n", define_prefix, define_prefix, define_prefix, define_prefix); - for (i = BPF_PROG_TYPE_UNSPEC + 1; i < prog_type_name_size; i++) - probe_helpers_for_progtype(i, supported_types[i], define_prefix, + while (true) { + prog_type++; + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + /* libbpf will return NULL for variants unknown to it. */ + if (!prog_type_str) + break; + + probe_helpers_for_progtype(prog_type, prog_type_str, + supported_types[prog_type], + define_prefix, ifindex); + } print_end_section(); } @@ -1128,7 +1147,7 @@ exit_free: return res; #else /* Detection assumes user has specific privileges. - * We do not use libpcap so let's approximate, and restrict usage to + * We do not use libcap so let's approximate, and restrict usage to * root user only. */ if (geteuid()) { @@ -1148,6 +1167,8 @@ static int do_probe(int argc, char **argv) __u32 ifindex = 0; char *ifname; + set_max_rlimit(); + while (argc) { if (is_prefix(*argv, "kernel")) { if (target != COMPONENT_UNSPEC) { @@ -1237,6 +1258,58 @@ exit_close_json: return 0; } +static const char *get_helper_name(unsigned int id) +{ + if (id >= ARRAY_SIZE(helper_name)) + return NULL; + + return helper_name[id]; +} + +static int do_list_builtins(int argc, char **argv) +{ + const char *(*get_name)(unsigned int id); + unsigned int id = 0; + + if (argc < 1) + usage(); + + if (is_prefix(*argv, "prog_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_prog_type_str; + } else if (is_prefix(*argv, "map_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_map_type_str; + } else if (is_prefix(*argv, "attach_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_attach_type_str; + } else if (is_prefix(*argv, "link_types")) { + get_name = (const char *(*)(unsigned int))libbpf_bpf_link_type_str; + } else if (is_prefix(*argv, "helpers")) { + get_name = get_helper_name; + } else { + p_err("expected 'prog_types', 'map_types', 'attach_types', 'link_types' or 'helpers', got: %s", *argv); + return -1; + } + + if (json_output) + jsonw_start_array(json_wtr); /* root array */ + + while (true) { + const char *name; + + name = get_name(id++); + if (!name) + break; + if (json_output) + jsonw_string(json_wtr, name); + else + printf("%s\n", name); + } + + if (json_output) + jsonw_end_array(json_wtr); /* root array */ + + return 0; +} + static int do_help(int argc, char **argv) { if (json_output) { @@ -1246,9 +1319,11 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %1$s %2$s probe [COMPONENT] [full] [unprivileged] [macros [prefix PREFIX]]\n" + " %1$s %2$s list_builtins GROUP\n" " %1$s %2$s help\n" "\n" " COMPONENT := { kernel | dev NAME }\n" + " GROUP := { prog_types | map_types | attach_types | link_types | helpers }\n" " " HELP_SPEC_OPTIONS " }\n" "", bin_name, argv[-2]); @@ -1257,8 +1332,9 @@ static int do_help(int argc, char **argv) } static const struct cmd cmds[] = { - { "probe", do_probe }, - { "help", do_help }, + { "probe", do_probe }, + { "list_builtins", do_list_builtins }, + { "help", do_help }, { 0 } }; diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 4c9477ff748d..cf8b4e525c88 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -474,6 +474,9 @@ static void codegen_asserts(struct bpf_object *obj, const char *obj_name) const struct btf_type *sec; char map_ident[256], var_ident[256]; + if (!btf) + return; + codegen("\ \n\ __attribute__((unused)) static void \n\ @@ -1172,7 +1175,7 @@ static int do_skeleton(int argc, char **argv) static inline void \n\ %1$s__detach(struct %1$s *obj) \n\ { \n\ - return bpf_object__detach_skeleton(obj->skeleton); \n\ + bpf_object__detach_skeleton(obj->skeleton); \n\ } \n\ ", obj_name @@ -1591,14 +1594,14 @@ static int do_object(int argc, char **argv) err = bpf_linker__add_file(linker, file, NULL); if (err) { - p_err("failed to link '%s': %s (%d)", file, strerror(err), err); + p_err("failed to link '%s': %s (%d)", file, strerror(errno), errno); goto out; } } err = bpf_linker__finalize(linker); if (err) { - p_err("failed to finalize ELF file: %s (%d)", strerror(err), err); + p_err("failed to finalize ELF file: %s (%d)", strerror(errno), errno); goto out; } @@ -1747,6 +1750,7 @@ btfgen_mark_type(struct btfgen_info *info, unsigned int type_id, bool follow_poi case BTF_KIND_INT: case BTF_KIND_FLOAT: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: case BTF_KIND_STRUCT: case BTF_KIND_UNION: break; @@ -1758,6 +1762,7 @@ btfgen_mark_type(struct btfgen_info *info, unsigned int type_id, bool follow_poi } break; case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: case BTF_KIND_VOLATILE: case BTF_KIND_TYPEDEF: err = btfgen_mark_type(info, btf_type->type, follow_pointers); @@ -1852,6 +1857,112 @@ static int btfgen_record_field_relo(struct btfgen_info *info, struct bpf_core_sp return 0; } +/* Mark types, members, and member types. Compared to btfgen_record_field_relo, + * this function does not rely on the target spec for inferring members, but + * uses the associated BTF. + * + * The `behind_ptr` argument is used to stop marking of composite types reached + * through a pointer. This way, we can keep BTF size in check while providing + * reasonable match semantics. + */ +static int btfgen_mark_type_match(struct btfgen_info *info, __u32 type_id, bool behind_ptr) +{ + const struct btf_type *btf_type; + struct btf *btf = info->src_btf; + struct btf_type *cloned_type; + int i, err; + + if (type_id == 0) + return 0; + + btf_type = btf__type_by_id(btf, type_id); + /* mark type on cloned BTF as used */ + cloned_type = (struct btf_type *)btf__type_by_id(info->marked_btf, type_id); + cloned_type->name_off = MARKED; + + switch (btf_kind(btf_type)) { + case BTF_KIND_UNKN: + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + struct btf_member *m = btf_members(btf_type); + __u16 vlen = btf_vlen(btf_type); + + if (behind_ptr) + break; + + for (i = 0; i < vlen; i++, m++) { + /* mark member */ + btfgen_mark_member(info, type_id, i); + + /* mark member's type */ + err = btfgen_mark_type_match(info, m->type, false); + if (err) + return err; + } + break; + } + case BTF_KIND_CONST: + case BTF_KIND_FWD: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + return btfgen_mark_type_match(info, btf_type->type, behind_ptr); + case BTF_KIND_PTR: + return btfgen_mark_type_match(info, btf_type->type, true); + case BTF_KIND_ARRAY: { + struct btf_array *array; + + array = btf_array(btf_type); + /* mark array type */ + err = btfgen_mark_type_match(info, array->type, false); + /* mark array's index type */ + err = err ? : btfgen_mark_type_match(info, array->index_type, false); + if (err) + return err; + break; + } + case BTF_KIND_FUNC_PROTO: { + __u16 vlen = btf_vlen(btf_type); + struct btf_param *param; + + /* mark ret type */ + err = btfgen_mark_type_match(info, btf_type->type, false); + if (err) + return err; + + /* mark parameters types */ + param = btf_params(btf_type); + for (i = 0; i < vlen; i++) { + err = btfgen_mark_type_match(info, param->type, false); + if (err) + return err; + param++; + } + break; + } + /* tells if some other type needs to be handled */ + default: + p_err("unsupported kind: %s (%d)", btf_kind_str(btf_type), type_id); + return -EINVAL; + } + + return 0; +} + +/* Mark types, members, and member types. Compared to btfgen_record_field_relo, + * this function does not rely on the target spec for inferring members, but + * uses the associated BTF. + */ +static int btfgen_record_type_match_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) +{ + return btfgen_mark_type_match(info, targ_spec->root_type_id, false); +} + static int btfgen_record_type_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) { return btfgen_mark_type(info, targ_spec->root_type_id, true); @@ -1878,6 +1989,8 @@ static int btfgen_record_reloc(struct btfgen_info *info, struct bpf_core_spec *r case BPF_CORE_TYPE_EXISTS: case BPF_CORE_TYPE_SIZE: return btfgen_record_type_relo(info, res); + case BPF_CORE_TYPE_MATCHES: + return btfgen_record_type_match_relo(info, res); case BPF_CORE_ENUMVAL_EXISTS: case BPF_CORE_ENUMVAL_VALUE: return btfgen_record_enumval_relo(info, res); diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c index 24734f2249d6..aaf99a0168c9 100644 --- a/tools/bpf/bpftool/jit_disasm.c +++ b/tools/bpf/bpftool/jit_disasm.c @@ -24,6 +24,7 @@ #include <sys/stat.h> #include <limits.h> #include <bpf/libbpf.h> +#include <tools/dis-asm-compat.h> #include "json_writer.h" #include "main.h" @@ -39,15 +40,12 @@ static void get_exec_path(char *tpath, size_t size) } static int oper_count; -static int fprintf_json(void *out, const char *fmt, ...) +static int printf_json(void *out, const char *fmt, va_list ap) { - va_list ap; char *s; int err; - va_start(ap, fmt); err = vasprintf(&s, fmt, ap); - va_end(ap); if (err < 0) return -1; @@ -73,6 +71,32 @@ static int fprintf_json(void *out, const char *fmt, ...) return 0; } +static int fprintf_json(void *out, const char *fmt, ...) +{ + va_list ap; + int r; + + va_start(ap, fmt); + r = printf_json(out, fmt, ap); + va_end(ap); + + return r; +} + +static int fprintf_json_styled(void *out, + enum disassembler_style style __maybe_unused, + const char *fmt, ...) +{ + va_list ap; + int r; + + va_start(ap, fmt); + r = printf_json(out, fmt, ap); + va_end(ap); + + return r; +} + void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, const char *arch, const char *disassembler_options, const struct btf *btf, @@ -99,11 +123,13 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, assert(bfd_check_format(bfdf, bfd_object)); if (json_output) - init_disassemble_info(&info, stdout, - (fprintf_ftype) fprintf_json); + init_disassemble_info_compat(&info, stdout, + (fprintf_ftype) fprintf_json, + fprintf_json_styled); else - init_disassemble_info(&info, stdout, - (fprintf_ftype) fprintf); + init_disassemble_info_compat(&info, stdout, + (fprintf_ftype) fprintf, + fprintf_styled); /* Update architecture info for offload. */ if (arch) { diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index 6353a789322b..2863639706dd 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -13,19 +13,6 @@ #include "json_writer.h" #include "main.h" -static const char * const link_type_name[] = { - [BPF_LINK_TYPE_UNSPEC] = "unspec", - [BPF_LINK_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", - [BPF_LINK_TYPE_TRACING] = "tracing", - [BPF_LINK_TYPE_CGROUP] = "cgroup", - [BPF_LINK_TYPE_ITER] = "iter", - [BPF_LINK_TYPE_NETNS] = "netns", - [BPF_LINK_TYPE_XDP] = "xdp", - [BPF_LINK_TYPE_PERF_EVENT] = "perf_event", - [BPF_LINK_TYPE_KPROBE_MULTI] = "kprobe_multi", - [BPF_LINK_TYPE_STRUCT_OPS] = "struct_ops", -}; - static struct hashmap *link_table; static int link_parse_fd(int *argc, char ***argv) @@ -67,9 +54,12 @@ static int link_parse_fd(int *argc, char ***argv) static void show_link_header_json(struct bpf_link_info *info, json_writer_t *wtr) { + const char *link_type_str; + jsonw_uint_field(wtr, "id", info->id); - if (info->type < ARRAY_SIZE(link_type_name)) - jsonw_string_field(wtr, "type", link_type_name[info->type]); + link_type_str = libbpf_bpf_link_type_str(info->type); + if (link_type_str) + jsonw_string_field(wtr, "type", link_type_str); else jsonw_uint_field(wtr, "type", info->type); @@ -78,9 +68,11 @@ show_link_header_json(struct bpf_link_info *info, json_writer_t *wtr) static void show_link_attach_type_json(__u32 attach_type, json_writer_t *wtr) { - if (attach_type < ARRAY_SIZE(attach_type_name)) - jsonw_string_field(wtr, "attach_type", - attach_type_name[attach_type]); + const char *attach_type_str; + + attach_type_str = libbpf_bpf_attach_type_str(attach_type); + if (attach_type_str) + jsonw_string_field(wtr, "attach_type", attach_type_str); else jsonw_uint_field(wtr, "attach_type", attach_type); } @@ -91,6 +83,36 @@ static bool is_iter_map_target(const char *target_name) strcmp(target_name, "bpf_sk_storage_map") == 0; } +static bool is_iter_cgroup_target(const char *target_name) +{ + return strcmp(target_name, "cgroup") == 0; +} + +static const char *cgroup_order_string(__u32 order) +{ + switch (order) { + case BPF_CGROUP_ITER_ORDER_UNSPEC: + return "order_unspec"; + case BPF_CGROUP_ITER_SELF_ONLY: + return "self_only"; + case BPF_CGROUP_ITER_DESCENDANTS_PRE: + return "descendants_pre"; + case BPF_CGROUP_ITER_DESCENDANTS_POST: + return "descendants_post"; + case BPF_CGROUP_ITER_ANCESTORS_UP: + return "ancestors_up"; + default: /* won't happen */ + return "unknown"; + } +} + +static bool is_iter_task_target(const char *target_name) +{ + return strcmp(target_name, "task") == 0 || + strcmp(target_name, "task_file") == 0 || + strcmp(target_name, "task_vma") == 0; +} + static void show_iter_json(struct bpf_link_info *info, json_writer_t *wtr) { const char *target_name = u64_to_ptr(info->iter.target_name); @@ -99,6 +121,18 @@ static void show_iter_json(struct bpf_link_info *info, json_writer_t *wtr) if (is_iter_map_target(target_name)) jsonw_uint_field(wtr, "map_id", info->iter.map.map_id); + else if (is_iter_task_target(target_name)) { + if (info->iter.task.tid) + jsonw_uint_field(wtr, "tid", info->iter.task.tid); + else if (info->iter.task.pid) + jsonw_uint_field(wtr, "pid", info->iter.task.pid); + } + + if (is_iter_cgroup_target(target_name)) { + jsonw_lluint_field(wtr, "cgroup_id", info->iter.cgroup.cgroup_id); + jsonw_string_field(wtr, "order", + cgroup_order_string(info->iter.cgroup.order)); + } } static int get_prog_info(int prog_id, struct bpf_prog_info *info) @@ -121,6 +155,7 @@ static int get_prog_info(int prog_id, struct bpf_prog_info *info) static int show_link_close_json(int fd, struct bpf_link_info *info) { struct bpf_prog_info prog_info; + const char *prog_type_str; int err; jsonw_start_object(json_wtr); @@ -137,12 +172,12 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) if (err) return err; - if (prog_info.type < prog_type_name_size) - jsonw_string_field(json_wtr, "prog_type", - prog_type_name[prog_info.type]); + prog_type_str = libbpf_bpf_prog_type_str(prog_info.type); + /* libbpf will return NULL for variants unknown to it. */ + if (prog_type_str) + jsonw_string_field(json_wtr, "prog_type", prog_type_str); else - jsonw_uint_field(json_wtr, "prog_type", - prog_info.type); + jsonw_uint_field(json_wtr, "prog_type", prog_info.type); show_link_attach_type_json(info->tracing.attach_type, json_wtr); @@ -184,9 +219,12 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) static void show_link_header_plain(struct bpf_link_info *info) { + const char *link_type_str; + printf("%u: ", info->id); - if (info->type < ARRAY_SIZE(link_type_name)) - printf("%s ", link_type_name[info->type]); + link_type_str = libbpf_bpf_link_type_str(info->type); + if (link_type_str) + printf("%s ", link_type_str); else printf("type %u ", info->type); @@ -195,8 +233,11 @@ static void show_link_header_plain(struct bpf_link_info *info) static void show_link_attach_type_plain(__u32 attach_type) { - if (attach_type < ARRAY_SIZE(attach_type_name)) - printf("attach_type %s ", attach_type_name[attach_type]); + const char *attach_type_str; + + attach_type_str = libbpf_bpf_attach_type_str(attach_type); + if (attach_type_str) + printf("attach_type %s ", attach_type_str); else printf("attach_type %u ", attach_type); } @@ -209,11 +250,24 @@ static void show_iter_plain(struct bpf_link_info *info) if (is_iter_map_target(target_name)) printf("map_id %u ", info->iter.map.map_id); + else if (is_iter_task_target(target_name)) { + if (info->iter.task.tid) + printf("tid %u ", info->iter.task.tid); + else if (info->iter.task.pid) + printf("pid %u ", info->iter.task.pid); + } + + if (is_iter_cgroup_target(target_name)) { + printf("cgroup_id %llu ", info->iter.cgroup.cgroup_id); + printf("order %s ", + cgroup_order_string(info->iter.cgroup.order)); + } } static int show_link_close_plain(int fd, struct bpf_link_info *info) { struct bpf_prog_info prog_info; + const char *prog_type_str; int err; show_link_header_plain(info); @@ -228,9 +282,10 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) if (err) return err; - if (prog_info.type < prog_type_name_size) - printf("\n\tprog_type %s ", - prog_type_name[prog_info.type]); + prog_type_str = libbpf_bpf_prog_type_str(prog_info.type); + /* libbpf will return NULL for variants unknown to it. */ + if (prog_type_str) + printf("\n\tprog_type %s ", prog_type_str); else printf("\n\tprog_type %u ", prog_info.type); diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 9062ef2b8767..ccd7457f92bf 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -435,6 +435,16 @@ int main(int argc, char **argv) setlinebuf(stdout); +#ifdef USE_LIBCAP + /* Libcap < 2.63 hooks before main() to compute the number of + * capabilities of the running kernel, and doing so it calls prctl() + * which may fail and set errno to non-zero. + * Let's reset errno to make sure this does not interfere with the + * batch mode. + */ + errno = 0; +#endif + last_do_help = do_help; pretty_output = false; json_output = false; @@ -508,8 +518,6 @@ int main(int argc, char **argv) * mode for loading generated skeleton. */ libbpf_set_strict_mode(LIBBPF_STRICT_ALL & ~LIBBPF_STRICT_MAP_DEFINITIONS); - } else { - libbpf_set_strict_mode(LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK); } argc -= optind; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index aa99ffab451a..5e5060c2ac04 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -63,14 +63,6 @@ static inline void *u64_to_ptr(__u64 ptr) #define HELP_SPEC_LINK \ "LINK := { id LINK_ID | pinned FILE }" -extern const char * const prog_type_name[]; -extern const size_t prog_type_name_size; - -extern const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE]; - -extern const char * const map_type_name[]; -extern const size_t map_type_name_size; - /* keep in sync with the definition in skeleton/pid_iter.bpf.c */ enum bpf_obj_type { BPF_OBJ_UNKNOWN, @@ -102,6 +94,8 @@ int detect_common_prefix(const char *arg, ...); void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep); void usage(void) __noreturn; +void set_max_rlimit(void); + int mount_tracefs(const char *target); struct obj_ref { @@ -249,6 +243,20 @@ int print_all_levels(__maybe_unused enum libbpf_print_level level, size_t hash_fn_for_key_as_id(const void *key, void *ctx); bool equal_fn_for_key_as_id(const void *k1, const void *k2, void *ctx); +/* bpf_attach_type_input_str - convert the provided attach type value into a + * textual representation that we accept for input purposes. + * + * This function is similar in nature to libbpf_bpf_attach_type_str, but + * recognizes some attach type names that have been used by the program in the + * past and which do not follow the string inference scheme that libbpf uses. + * These textual representations should only be used for user input. + * + * @t: The attach type + * Returns a pointer to a static string identifying the attach type. NULL is + * returned for unknown bpf_attach_type values. + */ +const char *bpf_attach_type_input_str(enum bpf_attach_type t); + static inline void *u32_as_hash_field(__u32 x) { return (void *)(uintptr_t)x; diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 877387ef79c7..9a6ca9f31133 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -22,42 +22,6 @@ #include "json_writer.h" #include "main.h" -const char * const map_type_name[] = { - [BPF_MAP_TYPE_UNSPEC] = "unspec", - [BPF_MAP_TYPE_HASH] = "hash", - [BPF_MAP_TYPE_ARRAY] = "array", - [BPF_MAP_TYPE_PROG_ARRAY] = "prog_array", - [BPF_MAP_TYPE_PERF_EVENT_ARRAY] = "perf_event_array", - [BPF_MAP_TYPE_PERCPU_HASH] = "percpu_hash", - [BPF_MAP_TYPE_PERCPU_ARRAY] = "percpu_array", - [BPF_MAP_TYPE_STACK_TRACE] = "stack_trace", - [BPF_MAP_TYPE_CGROUP_ARRAY] = "cgroup_array", - [BPF_MAP_TYPE_LRU_HASH] = "lru_hash", - [BPF_MAP_TYPE_LRU_PERCPU_HASH] = "lru_percpu_hash", - [BPF_MAP_TYPE_LPM_TRIE] = "lpm_trie", - [BPF_MAP_TYPE_ARRAY_OF_MAPS] = "array_of_maps", - [BPF_MAP_TYPE_HASH_OF_MAPS] = "hash_of_maps", - [BPF_MAP_TYPE_DEVMAP] = "devmap", - [BPF_MAP_TYPE_DEVMAP_HASH] = "devmap_hash", - [BPF_MAP_TYPE_SOCKMAP] = "sockmap", - [BPF_MAP_TYPE_CPUMAP] = "cpumap", - [BPF_MAP_TYPE_XSKMAP] = "xskmap", - [BPF_MAP_TYPE_SOCKHASH] = "sockhash", - [BPF_MAP_TYPE_CGROUP_STORAGE] = "cgroup_storage", - [BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray", - [BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE] = "percpu_cgroup_storage", - [BPF_MAP_TYPE_QUEUE] = "queue", - [BPF_MAP_TYPE_STACK] = "stack", - [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage", - [BPF_MAP_TYPE_STRUCT_OPS] = "struct_ops", - [BPF_MAP_TYPE_RINGBUF] = "ringbuf", - [BPF_MAP_TYPE_INODE_STORAGE] = "inode_storage", - [BPF_MAP_TYPE_TASK_STORAGE] = "task_storage", - [BPF_MAP_TYPE_BLOOM_FILTER] = "bloom_filter", -}; - -const size_t map_type_name_size = ARRAY_SIZE(map_type_name); - static struct hashmap *map_table; static bool map_is_per_cpu(__u32 type) @@ -81,12 +45,18 @@ static bool map_is_map_of_progs(__u32 type) static int map_type_from_str(const char *type) { + const char *map_type_str; unsigned int i; - for (i = 0; i < ARRAY_SIZE(map_type_name); i++) + for (i = 0; ; i++) { + map_type_str = libbpf_bpf_map_type_str(i); + if (!map_type_str) + break; + /* Don't allow prefixing in case of possible future shadowing */ - if (map_type_name[i] && !strcmp(map_type_name[i], type)) + if (!strcmp(map_type_str, type)) return i; + } return -1; } @@ -472,9 +442,12 @@ static int parse_elem(char **argv, struct bpf_map_info *info, static void show_map_header_json(struct bpf_map_info *info, json_writer_t *wtr) { + const char *map_type_str; + jsonw_uint_field(wtr, "id", info->id); - if (info->type < ARRAY_SIZE(map_type_name)) - jsonw_string_field(wtr, "type", map_type_name[info->type]); + map_type_str = libbpf_bpf_map_type_str(info->type); + if (map_type_str) + jsonw_string_field(wtr, "type", map_type_str); else jsonw_uint_field(wtr, "type", info->type); @@ -513,10 +486,12 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) if (owner_prog_type) { unsigned int prog_type = atoi(owner_prog_type); + const char *prog_type_str; - if (prog_type < prog_type_name_size) + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + if (prog_type_str) jsonw_string_field(json_wtr, "owner_prog_type", - prog_type_name[prog_type]); + prog_type_str); else jsonw_uint_field(json_wtr, "owner_prog_type", prog_type); @@ -559,9 +534,13 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) static void show_map_header_plain(struct bpf_map_info *info) { + const char *map_type_str; + printf("%u: ", info->id); - if (info->type < ARRAY_SIZE(map_type_name)) - printf("%s ", map_type_name[info->type]); + + map_type_str = libbpf_bpf_map_type_str(info->type); + if (map_type_str) + printf("%s ", map_type_str); else printf("type %u ", info->type); @@ -597,10 +576,11 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) printf("\n\t"); if (owner_prog_type) { unsigned int prog_type = atoi(owner_prog_type); + const char *prog_type_str; - if (prog_type < prog_type_name_size) - printf("owner_prog_type %s ", - prog_type_name[prog_type]); + prog_type_str = libbpf_bpf_prog_type_str(prog_type); + if (prog_type_str) + printf("owner_prog_type %s ", prog_type_str); else printf("owner_prog_type %d ", prog_type); } @@ -876,9 +856,13 @@ map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr, } if (info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && - info->value_size != 8) + info->value_size != 8) { + const char *map_type_str; + + map_type_str = libbpf_bpf_map_type_str(info->type); p_info("Warning: cannot read values from %s map with value_size != 8", - map_type_name[info->type]); + map_type_str); + } while (true) { err = bpf_map_get_next_key(fd, prev_key, key); if (err) { @@ -1342,6 +1326,8 @@ static int do_create(int argc, char **argv) goto exit; } + set_max_rlimit(); + fd = bpf_map_create(map_type, map_name, key_size, value_size, max_entries, &attr); if (fd < 0) { p_err("map create failed: %s", strerror(errno)); @@ -1473,7 +1459,7 @@ static int do_help(int argc, char **argv) " devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n" " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n" " queue | stack | sk_storage | struct_ops | ringbuf | inode_storage |\n" - " task_storage | bloom_filter }\n" + " task_storage | bloom_filter | user_ringbuf }\n" " " HELP_SPEC_OPTIONS " |\n" " {-f|--bpffs} | {-n|--nomount} }\n" "", diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c index 6b0c410152de..21d7d447e1f3 100644 --- a/tools/bpf/bpftool/map_perf_ring.c +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -29,13 +29,6 @@ static volatile bool stop; -struct event_ring_info { - int fd; - int key; - unsigned int cpu; - void *mem; -}; - struct perf_event_sample { struct perf_event_header header; __u64 time; @@ -195,10 +188,9 @@ int do_event_pipe(int argc, char **argv) opts.map_keys = &ctx.idx; pb = perf_buffer__new_raw(map_fd, MMAP_PAGE_CNT, &perf_attr, print_bpf_output, &ctx, &opts); - err = libbpf_get_error(pb); - if (err) { + if (!pb) { p_err("failed to create perf buffer: %s (%d)", - strerror(err), err); + strerror(errno), errno); goto err_close_map; } @@ -213,7 +205,7 @@ int do_event_pipe(int argc, char **argv) err = perf_buffer__poll(pb, 200); if (err < 0 && err != -EINTR) { p_err("perf buffer polling failed: %s (%d)", - strerror(err), err); + strerror(errno), errno); goto err_close_pb; } } diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c index e2d00d3cd868..bb6c969a114a 100644 --- a/tools/bpf/bpftool/pids.c +++ b/tools/bpf/bpftool/pids.c @@ -108,6 +108,7 @@ int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type) p_err("failed to create hashmap for PID references"); return -1; } + set_max_rlimit(); skel = pid_iter_bpf__open(); if (!skel) { diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 5c2c63df92e8..c81362a001ba 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -36,54 +36,28 @@ #define BPF_METADATA_PREFIX "bpf_metadata_" #define BPF_METADATA_PREFIX_LEN (sizeof(BPF_METADATA_PREFIX) - 1) -const char * const prog_type_name[] = { - [BPF_PROG_TYPE_UNSPEC] = "unspec", - [BPF_PROG_TYPE_SOCKET_FILTER] = "socket_filter", - [BPF_PROG_TYPE_KPROBE] = "kprobe", - [BPF_PROG_TYPE_SCHED_CLS] = "sched_cls", - [BPF_PROG_TYPE_SCHED_ACT] = "sched_act", - [BPF_PROG_TYPE_TRACEPOINT] = "tracepoint", - [BPF_PROG_TYPE_XDP] = "xdp", - [BPF_PROG_TYPE_PERF_EVENT] = "perf_event", - [BPF_PROG_TYPE_CGROUP_SKB] = "cgroup_skb", - [BPF_PROG_TYPE_CGROUP_SOCK] = "cgroup_sock", - [BPF_PROG_TYPE_LWT_IN] = "lwt_in", - [BPF_PROG_TYPE_LWT_OUT] = "lwt_out", - [BPF_PROG_TYPE_LWT_XMIT] = "lwt_xmit", - [BPF_PROG_TYPE_SOCK_OPS] = "sock_ops", - [BPF_PROG_TYPE_SK_SKB] = "sk_skb", - [BPF_PROG_TYPE_CGROUP_DEVICE] = "cgroup_device", - [BPF_PROG_TYPE_SK_MSG] = "sk_msg", - [BPF_PROG_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", - [BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr", - [BPF_PROG_TYPE_LWT_SEG6LOCAL] = "lwt_seg6local", - [BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2", - [BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport", - [BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector", - [BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl", - [BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE] = "raw_tracepoint_writable", - [BPF_PROG_TYPE_CGROUP_SOCKOPT] = "cgroup_sockopt", - [BPF_PROG_TYPE_TRACING] = "tracing", - [BPF_PROG_TYPE_STRUCT_OPS] = "struct_ops", - [BPF_PROG_TYPE_EXT] = "ext", - [BPF_PROG_TYPE_LSM] = "lsm", - [BPF_PROG_TYPE_SK_LOOKUP] = "sk_lookup", - [BPF_PROG_TYPE_SYSCALL] = "syscall", -}; - -const size_t prog_type_name_size = ARRAY_SIZE(prog_type_name); - enum dump_mode { DUMP_JITED, DUMP_XLATED, }; +static const bool attach_types[] = { + [BPF_SK_SKB_STREAM_PARSER] = true, + [BPF_SK_SKB_STREAM_VERDICT] = true, + [BPF_SK_SKB_VERDICT] = true, + [BPF_SK_MSG_VERDICT] = true, + [BPF_FLOW_DISSECTOR] = true, + [__MAX_BPF_ATTACH_TYPE] = false, +}; + +/* Textual representations traditionally used by the program and kept around + * for the sake of backwards compatibility. + */ static const char * const attach_type_strings[] = { [BPF_SK_SKB_STREAM_PARSER] = "stream_parser", [BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict", [BPF_SK_SKB_VERDICT] = "skb_verdict", [BPF_SK_MSG_VERDICT] = "msg_verdict", - [BPF_FLOW_DISSECTOR] = "flow_dissector", [__MAX_BPF_ATTACH_TYPE] = NULL, }; @@ -94,6 +68,14 @@ static enum bpf_attach_type parse_attach_type(const char *str) enum bpf_attach_type type; for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { + if (attach_types[type]) { + const char *attach_type_str; + + attach_type_str = libbpf_bpf_attach_type_str(type); + if (!strcmp(str, attach_type_str)) + return type; + } + if (attach_type_strings[type] && is_prefix(str, attach_type_strings[type])) return type; @@ -428,12 +410,14 @@ out_free: static void print_prog_header_json(struct bpf_prog_info *info, int fd) { + const char *prog_type_str; char prog_name[MAX_PROG_FULL_NAME]; jsonw_uint_field(json_wtr, "id", info->id); - if (info->type < ARRAY_SIZE(prog_type_name)) - jsonw_string_field(json_wtr, "type", - prog_type_name[info->type]); + prog_type_str = libbpf_bpf_prog_type_str(info->type); + + if (prog_type_str) + jsonw_string_field(json_wtr, "type", prog_type_str); else jsonw_uint_field(json_wtr, "type", info->type); @@ -515,11 +499,13 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) static void print_prog_header_plain(struct bpf_prog_info *info, int fd) { + const char *prog_type_str; char prog_name[MAX_PROG_FULL_NAME]; printf("%u: ", info->id); - if (info->type < ARRAY_SIZE(prog_type_name)) - printf("%s ", prog_type_name[info->type]); + prog_type_str = libbpf_bpf_prog_type_str(info->type); + if (prog_type_str) + printf("%s ", prog_type_str); else printf("type %u ", info->type); @@ -1604,6 +1590,8 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) } } + set_max_rlimit(); + if (verifier_logs) /* log_level1 + log_level2 + stats, but not stable UAPI */ open_opts.kernel_log_level = 1 + 2 + 4; @@ -1974,7 +1962,7 @@ static int profile_parse_metrics(int argc, char **argv) int selected_cnt = 0; unsigned int i; - metric_cnt = sizeof(metrics) / sizeof(struct profile_metric); + metric_cnt = ARRAY_SIZE(metrics); while (argc > 0) { for (i = 0; i < metric_cnt; i++) { @@ -2301,6 +2289,7 @@ static int do_profile(int argc, char **argv) } } + set_max_rlimit(); err = profiler_bpf__load(profile_obj); if (err) { p_err("failed to load profile_obj"); @@ -2374,8 +2363,8 @@ static int do_help(int argc, char **argv) " cgroup/sendmsg6 | cgroup/recvmsg4 | cgroup/recvmsg6 |\n" " cgroup/getsockopt | cgroup/setsockopt | cgroup/sock_release |\n" " struct_ops | fentry | fexit | freplace | sk_lookup }\n" - " ATTACH_TYPE := { msg_verdict | skb_verdict | stream_verdict |\n" - " stream_parser | flow_dissector }\n" + " ATTACH_TYPE := { sk_msg_verdict | sk_skb_verdict | sk_skb_stream_verdict |\n" + " sk_skb_stream_parser | flow_dissector }\n" " METRIC := { cycles | instructions | l1d_loads | llc_misses | itlb_misses | dtlb_misses }\n" " " HELP_SPEC_OPTIONS " |\n" " {-f|--bpffs} | {-m|--mapcompat} | {-n|--nomount} |\n" diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c index 2535f079ed67..e08a6ff2866c 100644 --- a/tools/bpf/bpftool/struct_ops.c +++ b/tools/bpf/bpftool/struct_ops.c @@ -501,6 +501,8 @@ static int do_register(int argc, char **argv) if (libbpf_get_error(obj)) return -1; + set_max_rlimit(); + if (bpf_object__load(obj)) { bpf_object__close(obj); return -1; diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index 5d26f3c6f918..80cd7843c677 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -45,6 +45,19 @@ * .zero 4 * __BTF_ID__func__vfs_fallocate__4: * .zero 4 + * + * set8 - store symbol size into first 4 bytes and sort following + * ID list + * + * __BTF_ID__set8__list: + * .zero 8 + * list: + * __BTF_ID__func__vfs_getattr__3: + * .zero 4 + * .word (1 << 0) | (1 << 2) + * __BTF_ID__func__vfs_fallocate__5: + * .zero 4 + * .word (1 << 3) | (1 << 1) | (1 << 2) */ #define _GNU_SOURCE @@ -72,6 +85,7 @@ #define BTF_TYPEDEF "typedef" #define BTF_FUNC "func" #define BTF_SET "set" +#define BTF_SET8 "set8" #define ADDR_CNT 100 @@ -84,6 +98,7 @@ struct btf_id { }; int addr_cnt; bool is_set; + bool is_set8; Elf64_Addr addr[ADDR_CNT]; }; @@ -231,14 +246,14 @@ static char *get_id(const char *prefix_end) return id; } -static struct btf_id *add_set(struct object *obj, char *name) +static struct btf_id *add_set(struct object *obj, char *name, bool is_set8) { /* * __BTF_ID__set__name * name = ^ * id = ^ */ - char *id = name + sizeof(BTF_SET "__") - 1; + char *id = name + (is_set8 ? sizeof(BTF_SET8 "__") : sizeof(BTF_SET "__")) - 1; int len = strlen(name); if (id >= name + len) { @@ -444,9 +459,21 @@ static int symbols_collect(struct object *obj) } else if (!strncmp(prefix, BTF_FUNC, sizeof(BTF_FUNC) - 1)) { obj->nr_funcs++; id = add_symbol(&obj->funcs, prefix, sizeof(BTF_FUNC) - 1); + /* set8 */ + } else if (!strncmp(prefix, BTF_SET8, sizeof(BTF_SET8) - 1)) { + id = add_set(obj, prefix, true); + /* + * SET8 objects store list's count, which is encoded + * in symbol's size, together with 'cnt' field hence + * that - 1. + */ + if (id) { + id->cnt = sym.st_size / sizeof(uint64_t) - 1; + id->is_set8 = true; + } /* set */ } else if (!strncmp(prefix, BTF_SET, sizeof(BTF_SET) - 1)) { - id = add_set(obj, prefix); + id = add_set(obj, prefix, false); /* * SET objects store list's count, which is encoded * in symbol's size, together with 'cnt' field hence @@ -571,7 +598,8 @@ static int id_patch(struct object *obj, struct btf_id *id) int *ptr = data->d_buf; int i; - if (!id->id && !id->is_set) + /* For set, set8, id->id may be 0 */ + if (!id->id && !id->is_set && !id->is_set8) pr_err("WARN: resolve_btfids: unresolved symbol %s\n", id->name); for (i = 0; i < id->addr_cnt; i++) { @@ -643,13 +671,13 @@ static int sets_patch(struct object *obj) } idx = idx / sizeof(int); - base = &ptr[idx] + 1; + base = &ptr[idx] + (id->is_set8 ? 2 : 1); cnt = ptr[idx]; pr_debug("sorting addr %5lu: cnt %6d [%s]\n", (idx + 1) * sizeof(int), cnt, id->name); - qsort(base, cnt, sizeof(int), cmp_id); + qsort(base, cnt, id->is_set8 ? sizeof(uint64_t) : sizeof(int), cmp_id); next = rb_next(next); } diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile index da6de16a3dfb..8b3d87b82b7a 100644 --- a/tools/bpf/runqslower/Makefile +++ b/tools/bpf/runqslower/Makefile @@ -4,7 +4,7 @@ include ../../scripts/Makefile.include OUTPUT ?= $(abspath .output)/ BPFTOOL_OUTPUT := $(OUTPUT)bpftool/ -DEFAULT_BPFTOOL := $(BPFTOOL_OUTPUT)bpftool +DEFAULT_BPFTOOL := $(BPFTOOL_OUTPUT)bootstrap/bpftool BPFTOOL ?= $(DEFAULT_BPFTOOL) LIBBPF_SRC := $(abspath ../../lib/bpf) BPFOBJ_OUTPUT := $(OUTPUT)libbpf/ @@ -86,6 +86,5 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(BPFOBJ_OU $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(BPFOBJ_OUTPUT) \ DESTDIR=$(BPFOBJ_OUTPUT) prefix= $(abspath $@) install_headers -$(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BPFTOOL_OUTPUT) - $(Q)$(MAKE) $(submake_extras) -C ../bpftool OUTPUT=$(BPFTOOL_OUTPUT) \ - ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) +$(DEFAULT_BPFTOOL): | $(BPFTOOL_OUTPUT) + $(Q)$(MAKE) $(submake_extras) -C ../bpftool OUTPUT=$(BPFTOOL_OUTPUT) bootstrap diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 888a0421d43b..38f8851bd7cb 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -70,6 +70,7 @@ FEATURE_TESTS_BASIC := \ libaio \ libzstd \ disassembler-four-args \ + disassembler-init-styled \ file-handle # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list @@ -102,6 +103,7 @@ FEATURE_TESTS_EXTRA := \ libbpf-bpf_prog_load \ libbpf-bpf_object__next_program \ libbpf-bpf_object__next_map \ + libbpf-bpf_program__set_insns \ libbpf-bpf_create_map \ libpfm4 \ libdebuginfod \ @@ -134,8 +136,13 @@ FEATURE_DISPLAY ?= \ get_cpuid \ bpf \ libaio \ - libzstd \ - disassembler-four-args + libzstd + +# +# Declare group members of a feature to display the logical OR of the detection +# result instead of each member result. +# +FEATURE_GROUP_MEMBERS-libbfd = libbfd-liberty libbfd-liberty-z # Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features. # If in the future we need per-feature checks/flags for features not @@ -177,19 +184,28 @@ endif # # Print the result of the feature test: # -feature_print_status = $(eval $(feature_print_status_code)) $(info $(MSG)) +feature_print_status = $(eval $(feature_print_status_code)) + +feature_group = $(eval $(feature_gen_group)) $(GROUP) + +define feature_gen_group + GROUP := $(1) + ifneq ($(feature_verbose),1) + GROUP += $(FEATURE_GROUP_MEMBERS-$(1)) + endif +endef define feature_print_status_code - ifeq ($(feature-$(1)), 1) - MSG = $(shell printf '...%30s: [ \033[32mon\033[m ]' $(1)) + ifneq (,$(filter 1,$(foreach feat,$(call feature_group,$(feat)),$(feature-$(feat))))) + MSG = $(shell printf '...%40s: [ \033[32mon\033[m ]' $(1)) else - MSG = $(shell printf '...%30s: [ \033[31mOFF\033[m ]' $(1)) + MSG = $(shell printf '...%40s: [ \033[31mOFF\033[m ]' $(1)) endif endef -feature_print_text = $(eval $(feature_print_text_code)) $(info $(MSG)) +feature_print_text = $(eval $(feature_print_text_code)) define feature_print_text_code - MSG = $(shell printf '...%30s: %s' $(1) $(2)) + MSG = $(shell printf '...%40s: %s' $(1) $(2)) endef # @@ -244,24 +260,29 @@ ifeq ($(VF),1) feature_verbose := 1 endif +ifneq ($(feature_verbose),1) + # + # Determine the features to omit from the displayed message, as only the + # logical OR of the detection result will be shown. + # + FEATURE_OMIT := $(foreach feat,$(FEATURE_DISPLAY),$(FEATURE_GROUP_MEMBERS-$(feat))) +endif + feature_display_entries = $(eval $(feature_display_entries_code)) define feature_display_entries_code ifeq ($(feature_display),1) - $(info ) - $(info Auto-detecting system features:) - $(foreach feat,$(FEATURE_DISPLAY),$(call feature_print_status,$(feat),)) - ifneq ($(feature_verbose),1) - $(info ) - endif + $$(info ) + $$(info Auto-detecting system features:) + $(foreach feat,$(filter-out $(FEATURE_OMIT),$(FEATURE_DISPLAY)),$(call feature_print_status,$(feat),) $$(info $(MSG))) endif ifeq ($(feature_verbose),1) - TMP := $(filter-out $(FEATURE_DISPLAY),$(FEATURE_TESTS)) - $(foreach feat,$(TMP),$(call feature_print_status,$(feat),)) - $(info ) + $(eval TMP := $(filter-out $(FEATURE_DISPLAY),$(FEATURE_TESTS))) + $(foreach feat,$(TMP),$(call feature_print_status,$(feat),) $$(info $(MSG))) endif endef ifeq ($(FEATURE_DISPLAY_DEFERRED),) $(call feature_display_entries) + $(info ) endif diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 7c2a17e23c30..690fe97be190 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -18,6 +18,7 @@ FILES= \ test-libbfd.bin \ test-libbfd-buildid.bin \ test-disassembler-four-args.bin \ + test-disassembler-init-styled.bin \ test-reallocarray.bin \ test-libbfd-liberty.bin \ test-libbfd-liberty-z.bin \ @@ -62,6 +63,7 @@ FILES= \ test-libbpf-bpf_map_create.bin \ test-libbpf-bpf_object__next_program.bin \ test-libbpf-bpf_object__next_map.bin \ + test-libbpf-bpf_program__set_insns.bin \ test-libbpf-btf__raw_data.bin \ test-get_cpuid.bin \ test-sdt.bin \ @@ -89,6 +91,8 @@ all: $(FILES) __BUILD = $(CC) $(CFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS) BUILD = $(__BUILD) > $(@:.bin=.make.output) 2>&1 + BUILD_BFD = $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl + BUILD_ALL = $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd -lcap __BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(@F)) $(LDFLAGS) BUILDXX = $(__BUILDXX) > $(@:.bin=.make.output) 2>&1 @@ -96,7 +100,7 @@ __BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$( ############################### $(OUTPUT)test-all.bin: - $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd -lcap + $(BUILD_ALL) || $(BUILD_ALL) -lopcodes -liberty $(OUTPUT)test-hello.bin: $(BUILD) @@ -240,13 +244,18 @@ $(OUTPUT)test-libpython.bin: $(BUILD) $(FLAGS_PYTHON_EMBED) $(OUTPUT)test-libbfd.bin: - $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl + $(BUILD_BFD) $(OUTPUT)test-libbfd-buildid.bin: - $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl + $(BUILD_BFD) || $(BUILD_BFD) -liberty || $(BUILD_BFD) -liberty -lz $(OUTPUT)test-disassembler-four-args.bin: - $(BUILD) -DPACKAGE='"perf"' -lbfd -lopcodes + $(BUILD_BFD) -lopcodes || $(BUILD_BFD) -lopcodes -liberty || \ + $(BUILD_BFD) -lopcodes -liberty -lz + +$(OUTPUT)test-disassembler-init-styled.bin: + $(BUILD_BFD) -lopcodes || $(BUILD_BFD) -lopcodes -liberty || \ + $(BUILD_BFD) -lopcodes -liberty -lz $(OUTPUT)test-reallocarray.bin: $(BUILD) @@ -308,6 +317,9 @@ $(OUTPUT)test-libbpf-bpf_object__next_program.bin: $(OUTPUT)test-libbpf-bpf_object__next_map.bin: $(BUILD) -lbpf +$(OUTPUT)test-libbpf-bpf_program__set_insns.bin: + $(BUILD) -lbpf + $(OUTPUT)test-libbpf-btf__raw_data.bin: $(BUILD) -lbpf diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 5ffafb967b6e..957c02c7b163 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -166,6 +166,10 @@ # include "test-disassembler-four-args.c" #undef main +#define main main_test_disassembler_init_styled +# include "test-disassembler-init-styled.c" +#undef main + #define main main_test_libzstd # include "test-libzstd.c" #undef main diff --git a/tools/build/feature/test-disassembler-init-styled.c b/tools/build/feature/test-disassembler-init-styled.c new file mode 100644 index 000000000000..f1ce0ec3bee9 --- /dev/null +++ b/tools/build/feature/test-disassembler-init-styled.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <dis-asm.h> + +int main(void) +{ + struct disassemble_info info; + + init_disassemble_info(&info, stdout, + NULL, NULL); + + return 0; +} diff --git a/tools/build/feature/test-libbpf-bpf_program__set_insns.c b/tools/build/feature/test-libbpf-bpf_program__set_insns.c new file mode 100644 index 000000000000..f3b7f18c8f49 --- /dev/null +++ b/tools/build/feature/test-libbpf-bpf_program__set_insns.c @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <bpf/libbpf.h> + +int main(void) +{ + bpf_program__set_insns(NULL /* prog */, NULL /* new_insns */, 0 /* new_insn_cnt */); + return 0; +} diff --git a/tools/build/feature/test-libcrypto.c b/tools/build/feature/test-libcrypto.c index a98174e0569c..bc34a5bbb504 100644 --- a/tools/build/feature/test-libcrypto.c +++ b/tools/build/feature/test-libcrypto.c @@ -1,16 +1,23 @@ // SPDX-License-Identifier: GPL-2.0 +#include <openssl/evp.h> #include <openssl/sha.h> #include <openssl/md5.h> int main(void) { - MD5_CTX context; + EVP_MD_CTX *mdctx; unsigned char md[MD5_DIGEST_LENGTH + SHA_DIGEST_LENGTH]; unsigned char dat[] = "12345"; + unsigned int digest_len; - MD5_Init(&context); - MD5_Update(&context, &dat[0], sizeof(dat)); - MD5_Final(&md[0], &context); + mdctx = EVP_MD_CTX_new(); + if (!mdctx) + return 0; + + EVP_DigestInit_ex(mdctx, EVP_md5(), NULL); + EVP_DigestUpdate(mdctx, &dat[0], sizeof(dat)); + EVP_DigestFinal_ex(mdctx, &md[0], &digest_len); + EVP_MD_CTX_free(mdctx); SHA1(&dat[0], sizeof(dat), &md[0]); diff --git a/tools/cgroup/iocost_monitor.py b/tools/cgroup/iocost_monitor.py index c4ff907c078b..0dbbc67400fc 100644 --- a/tools/cgroup/iocost_monitor.py +++ b/tools/cgroup/iocost_monitor.py @@ -61,6 +61,11 @@ autop_names = { } class BlkgIterator: + def __init__(self, root_blkcg, q_id, include_dying=False): + self.include_dying = include_dying + self.blkgs = [] + self.walk(root_blkcg, q_id, '') + def blkcg_name(blkcg): return blkcg.css.cgroup.kn.name.string_().decode('utf-8') @@ -82,11 +87,6 @@ class BlkgIterator: blkcg.css.children.address_of_(), 'css.sibling'): self.walk(c, q_id, path) - def __init__(self, root_blkcg, q_id, include_dying=False): - self.include_dying = include_dying - self.blkgs = [] - self.walk(root_blkcg, q_id, '') - def __iter__(self): return iter(self.blkgs) diff --git a/tools/cgroup/memcg_shrinker.py b/tools/cgroup/memcg_shrinker.py new file mode 100644 index 000000000000..706ab27666a4 --- /dev/null +++ b/tools/cgroup/memcg_shrinker.py @@ -0,0 +1,71 @@ +#!/usr/bin/env python3 +# +# Copyright (C) 2022 Roman Gushchin <roman.gushchin@linux.dev> +# Copyright (C) 2022 Meta + +import os +import argparse +import sys + + +def scan_cgroups(cgroup_root): + cgroups = {} + + for root, subdirs, _ in os.walk(cgroup_root): + for cgroup in subdirs: + path = os.path.join(root, cgroup) + ino = os.stat(path).st_ino + cgroups[ino] = path + + # (memcg ino, path) + return cgroups + + +def scan_shrinkers(shrinker_debugfs): + shrinkers = [] + + for root, subdirs, _ in os.walk(shrinker_debugfs): + for shrinker in subdirs: + count_path = os.path.join(root, shrinker, "count") + with open(count_path) as f: + for line in f.readlines(): + items = line.split(' ') + ino = int(items[0]) + # (count, shrinker, memcg ino) + shrinkers.append((int(items[1]), shrinker, ino)) + return shrinkers + + +def main(): + parser = argparse.ArgumentParser(description='Display biggest shrinkers') + parser.add_argument('-n', '--lines', type=int, help='Number of lines to print') + + args = parser.parse_args() + + cgroups = scan_cgroups("/sys/fs/cgroup/") + shrinkers = scan_shrinkers("/sys/kernel/debug/shrinker/") + shrinkers = sorted(shrinkers, reverse = True, key = lambda x: x[0]) + + n = 0 + for s in shrinkers: + count, name, ino = (s[0], s[1], s[2]) + if count == 0: + break + + if ino == 0 or ino == 1: + cg = "/" + else: + try: + cg = cgroups[ino] + except KeyError: + cg = "unknown (%d)" % ino + + print("%-8s %-20s %s" % (count, name, cg)) + + n += 1 + if args.lines and n >= args.lines: + break + + +if __name__ == '__main__': + main() diff --git a/tools/debugging/kernel-chktaint b/tools/debugging/kernel-chktaint index f1af27ce9f20..279be06332be 100755 --- a/tools/debugging/kernel-chktaint +++ b/tools/debugging/kernel-chktaint @@ -187,6 +187,7 @@ else echo " * auxiliary taint, defined for and used by distros (#16)" fi + T=`expr $T / 2` if [ `expr $T % 2` -eq 0 ]; then addout " " @@ -195,6 +196,14 @@ else echo " * kernel was built with the struct randomization plugin (#17)" fi +T=`expr $T / 2` +if [ `expr $T % 2` -eq 0 ]; then + addout " " +else + addout "N" + echo " * an in-kernel test (such as a KUnit test) has been run (#18)" +fi + echo "For a more detailed explanation of the various taint flags see" echo " Documentation/admin-guide/tainted-kernels.rst in the Linux kernel sources" echo " or https://kernel.org/doc/html/latest/admin-guide/tainted-kernels.html" diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index 1e6fd6ca513b..27f5e7dfc2f7 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -44,7 +44,7 @@ /* * KVP protocol: The user mode component first registers with the - * the kernel component. Subsequently, the kernel component requests, data + * kernel component. Subsequently, the kernel component requests, data * for the specified keys. In response to this message the user mode component * fills in the value corresponding to the specified key. We overload the * sequence field in the cn_msg header to define our KVP message types. @@ -772,11 +772,11 @@ static int kvp_process_ip_address(void *addrp, const char *str; if (family == AF_INET) { - addr = (struct sockaddr_in *)addrp; + addr = addrp; str = inet_ntop(family, &addr->sin_addr, tmp, 50); addr_length = INET_ADDRSTRLEN; } else { - addr6 = (struct sockaddr_in6 *)addrp; + addr6 = addrp; str = inet_ntop(family, &addr6->sin6_addr.s6_addr, tmp, 50); addr_length = INET6_ADDRSTRLEN; } diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c index 2f4581658859..0a5c2bb60030 100644 --- a/tools/iio/iio_event_monitor.c +++ b/tools/iio/iio_event_monitor.c @@ -69,12 +69,15 @@ static const char * const iio_ev_type_text[] = { [IIO_EV_TYPE_MAG_ADAPTIVE] = "mag_adaptive", [IIO_EV_TYPE_CHANGE] = "change", [IIO_EV_TYPE_MAG_REFERENCED] = "mag_referenced", + [IIO_EV_TYPE_GESTURE] = "gesture", }; static const char * const iio_ev_dir_text[] = { [IIO_EV_DIR_EITHER] = "either", [IIO_EV_DIR_RISING] = "rising", - [IIO_EV_DIR_FALLING] = "falling" + [IIO_EV_DIR_FALLING] = "falling", + [IIO_EV_DIR_SINGLETAP] = "singletap", + [IIO_EV_DIR_DOUBLETAP] = "doubletap", }; static const char * const iio_modifier_names[] = { @@ -122,6 +125,12 @@ static const char * const iio_modifier_names[] = { [IIO_MOD_PM4] = "pm4", [IIO_MOD_PM10] = "pm10", [IIO_MOD_O2] = "o2", + [IIO_MOD_LINEAR_X] = "linear_x", + [IIO_MOD_LINEAR_Y] = "linear_y", + [IIO_MOD_LINEAR_Z] = "linear_z", + [IIO_MOD_PITCH] = "pitch", + [IIO_MOD_YAW] = "yaw", + [IIO_MOD_ROLL] = "roll", }; static bool event_is_known(struct iio_event_data *event) @@ -227,6 +236,7 @@ static bool event_is_known(struct iio_event_data *event) case IIO_EV_TYPE_THRESH_ADAPTIVE: case IIO_EV_TYPE_MAG_ADAPTIVE: case IIO_EV_TYPE_CHANGE: + case IIO_EV_TYPE_GESTURE: break; default: return false; @@ -236,6 +246,8 @@ static bool event_is_known(struct iio_event_data *event) case IIO_EV_DIR_EITHER: case IIO_EV_DIR_RISING: case IIO_EV_DIR_FALLING: + case IIO_EV_DIR_SINGLETAP: + case IIO_EV_DIR_DOUBLETAP: case IIO_EV_DIR_NONE: break; default: diff --git a/tools/iio/iio_utils.c b/tools/iio/iio_utils.c index aadee6d34c74..8d35893b2fa8 100644 --- a/tools/iio/iio_utils.c +++ b/tools/iio/iio_utils.c @@ -547,6 +547,10 @@ static int calc_digits(int num) { int count = 0; + /* It takes a digit to represent zero */ + if (!num) + return 1; + while (num != 0) { num /= 10; count++; diff --git a/tools/include/asm-generic/bitops/non-atomic.h b/tools/include/asm-generic/bitops/non-atomic.h index 7e10c4b50c5d..0c472a833408 100644 --- a/tools/include/asm-generic/bitops/non-atomic.h +++ b/tools/include/asm-generic/bitops/non-atomic.h @@ -2,10 +2,10 @@ #ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ -#include <asm/types.h> +#include <linux/bits.h> /** - * __set_bit - Set a bit in memory + * ___set_bit - Set a bit in memory * @nr: the bit to set * @addr: the address to start counting from * @@ -13,7 +13,8 @@ * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ -static inline void __set_bit(int nr, volatile unsigned long *addr) +static __always_inline void +___set_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -21,7 +22,8 @@ static inline void __set_bit(int nr, volatile unsigned long *addr) *p |= mask; } -static inline void __clear_bit(int nr, volatile unsigned long *addr) +static __always_inline void +___clear_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -30,7 +32,7 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr) } /** - * __change_bit - Toggle a bit in memory + * ___change_bit - Toggle a bit in memory * @nr: the bit to change * @addr: the address to start counting from * @@ -38,7 +40,8 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr) * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ -static inline void __change_bit(int nr, volatile unsigned long *addr) +static __always_inline void +___change_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -47,7 +50,7 @@ static inline void __change_bit(int nr, volatile unsigned long *addr) } /** - * __test_and_set_bit - Set a bit and return its old value + * ___test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * @@ -55,7 +58,8 @@ static inline void __change_bit(int nr, volatile unsigned long *addr) * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ -static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) +static __always_inline bool +___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -66,7 +70,7 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) } /** - * __test_and_clear_bit - Clear a bit and return its old value + * ___test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * @@ -74,7 +78,8 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ -static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) +static __always_inline bool +___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -85,8 +90,8 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) } /* WARNING: non atomic and it can be reordered! */ -static inline int __test_and_change_bit(int nr, - volatile unsigned long *addr) +static __always_inline bool +___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -97,11 +102,12 @@ static inline int __test_and_change_bit(int nr, } /** - * test_bit - Determine whether a bit is set + * _test_bit - Determine whether a bit is set * @nr: bit number to test * @addr: Address to start counting from */ -static inline int test_bit(int nr, const volatile unsigned long *addr) +static __always_inline bool +_test_bit(unsigned long nr, const volatile unsigned long *addr) { return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); } diff --git a/tools/include/asm-generic/hugetlb_encode.h b/tools/include/asm-generic/hugetlb_encode.h index 4f3d5aaa11f5..de687009bfe5 100644 --- a/tools/include/asm-generic/hugetlb_encode.h +++ b/tools/include/asm-generic/hugetlb_encode.h @@ -20,18 +20,18 @@ #define HUGETLB_FLAG_ENCODE_SHIFT 26 #define HUGETLB_FLAG_ENCODE_MASK 0x3f -#define HUGETLB_FLAG_ENCODE_16KB (14 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_64KB (16 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_512KB (19 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_1MB (20 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_2MB (21 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_8MB (23 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_16MB (24 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_32MB (25 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_256MB (28 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_512MB (29 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_1GB (30 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_2GB (31 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_16GB (34 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16KB (14U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_64KB (16U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_512KB (19U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_1MB (20U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_2MB (21U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_8MB (23U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16MB (24U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_32MB (25U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_256MB (28U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_512MB (29U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_1GB (30U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_2GB (31U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16GB (34U << HUGETLB_FLAG_ENCODE_SHIFT) #endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */ diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index afdf93bebaaf..65d0747c5205 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -11,10 +11,10 @@ #define DECLARE_BITMAP(name,bits) \ unsigned long name[BITS_TO_LONGS(bits)] -int __bitmap_weight(const unsigned long *bitmap, int bits); +unsigned int __bitmap_weight(const unsigned long *bitmap, int bits); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); -int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, +bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits); bool __bitmap_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits); @@ -45,7 +45,7 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits); } -static inline int bitmap_empty(const unsigned long *src, unsigned nbits) +static inline bool bitmap_empty(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return ! (*src & BITMAP_LAST_WORD_MASK(nbits)); @@ -53,7 +53,7 @@ static inline int bitmap_empty(const unsigned long *src, unsigned nbits) return find_first_bit(src, nbits) == nbits; } -static inline int bitmap_full(const unsigned long *src, unsigned int nbits) +static inline bool bitmap_full(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits)); @@ -61,7 +61,7 @@ static inline int bitmap_full(const unsigned long *src, unsigned int nbits) return find_first_zero_bit(src, nbits) == nbits; } -static inline int bitmap_weight(const unsigned long *src, unsigned int nbits) +static inline unsigned int bitmap_weight(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits)); @@ -146,7 +146,7 @@ size_t bitmap_scnprintf(unsigned long *bitmap, unsigned int nbits, * @src2: operand 2 * @nbits: size of bitmap */ -static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, +static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h index 5fca38fe1ba8..f18683b95ea6 100644 --- a/tools/include/linux/bitops.h +++ b/tools/include/linux/bitops.h @@ -26,6 +26,22 @@ extern unsigned int __sw_hweight32(unsigned int w); extern unsigned long __sw_hweight64(__u64 w); /* + * Defined here because those may be needed by architecture-specific static + * inlines. + */ + +#define bitop(op, nr, addr) \ + op(nr, addr) + +#define __set_bit(nr, addr) bitop(___set_bit, nr, addr) +#define __clear_bit(nr, addr) bitop(___clear_bit, nr, addr) +#define __change_bit(nr, addr) bitop(___change_bit, nr, addr) +#define __test_and_set_bit(nr, addr) bitop(___test_and_set_bit, nr, addr) +#define __test_and_clear_bit(nr, addr) bitop(___test_and_clear_bit, nr, addr) +#define __test_and_change_bit(nr, addr) bitop(___test_and_change_bit, nr, addr) +#define test_bit(nr, addr) bitop(_test_bit, nr, addr) + +/* * Include this here because some architectures need generic_ffs/fls in * scope * diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h index 57890b357f85..71e54b1e3796 100644 --- a/tools/include/linux/btf_ids.h +++ b/tools/include/linux/btf_ids.h @@ -73,7 +73,7 @@ asm( \ __BTF_ID_LIST(name, local) \ extern u32 name[]; -#define BTF_ID_LIST_GLOBAL(name) \ +#define BTF_ID_LIST_GLOBAL(name, n) \ __BTF_ID_LIST(name, globl) /* The BTF_ID_LIST_SINGLE macro defines a BTF_ID_LIST with @@ -82,6 +82,9 @@ __BTF_ID_LIST(name, globl) #define BTF_ID_LIST_SINGLE(name, prefix, typename) \ BTF_ID_LIST(name) \ BTF_ID(prefix, typename) +#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) \ + BTF_ID_LIST_GLOBAL(name, 1) \ + BTF_ID(prefix, typename) /* * The BTF_ID_UNUSED macro defines 4 zero bytes. @@ -143,13 +146,14 @@ extern struct btf_id_set name; #else -#define BTF_ID_LIST(name) static u32 name[5]; +#define BTF_ID_LIST(name) static u32 __maybe_unused name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED -#define BTF_ID_LIST_GLOBAL(name) u32 name[1]; -#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1]; -#define BTF_SET_START(name) static struct btf_id_set name = { 0 }; -#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 }; +#define BTF_ID_LIST_GLOBAL(name, n) u32 __maybe_unused name[n]; +#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 __maybe_unused name[1]; +#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 __maybe_unused name[1]; +#define BTF_SET_START(name) static struct btf_id_set __maybe_unused name = { 0 }; +#define BTF_SET_START_GLOBAL(name) static struct btf_id_set __maybe_unused name = { 0 }; #define BTF_SET_END(name) #endif /* CONFIG_DEBUG_INFO_BTF */ @@ -172,7 +176,10 @@ extern struct btf_id_set name; BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, tcp_timewait_sock) \ BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock) \ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock) \ - BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) + BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_MPTCP, mptcp_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCKET, socket) enum { #define BTF_SOCK_TYPE(name, str) name, @@ -184,4 +191,18 @@ MAX_BTF_SOCK_TYPE, extern u32 btf_sock_ids[]; #endif +#define BTF_TRACING_TYPE_xxx \ + BTF_TRACING_TYPE(BTF_TRACING_TYPE_TASK, task_struct) \ + BTF_TRACING_TYPE(BTF_TRACING_TYPE_FILE, file) \ + BTF_TRACING_TYPE(BTF_TRACING_TYPE_VMA, vm_area_struct) + +enum { +#define BTF_TRACING_TYPE(name, type) name, +BTF_TRACING_TYPE_xxx +#undef BTF_TRACING_TYPE +MAX_BTF_TRACING_TYPE, +}; + +extern u32 btf_tracing_ids[]; + #endif diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h index 24ae3054f304..1bdd834bdd57 100644 --- a/tools/include/linux/compiler_types.h +++ b/tools/include/linux/compiler_types.h @@ -36,4 +36,8 @@ #include <linux/compiler-gcc.h> #endif +#ifndef asm_volatile_goto +#define asm_volatile_goto(x...) asm goto(x) +#endif + #endif /* __LINUX_COMPILER_TYPES_H */ diff --git a/tools/include/linux/find.h b/tools/include/linux/find.h index 47e2bd6c5174..38c0a542b0e2 100644 --- a/tools/include/linux/find.h +++ b/tools/include/linux/find.h @@ -8,21 +8,23 @@ #include <linux/bitops.h> -extern unsigned long _find_next_bit(const unsigned long *addr1, - const unsigned long *addr2, unsigned long nbits, - unsigned long start, unsigned long invert, unsigned long le); +unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits, + unsigned long start); +unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start); +unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, + unsigned long start); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); -extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); #ifndef find_next_bit /** * find_next_bit - find the next set bit in a memory region * @addr: The address to base the search on - * @offset: The bitnumber to start searching at * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. @@ -41,7 +43,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, return val ? __ffs(val) : size; } - return _find_next_bit(addr, NULL, size, offset, 0UL, 0); + return _find_next_bit(addr, size, offset); } #endif @@ -50,8 +52,8 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, * find_next_and_bit - find the next set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on - * @offset: The bitnumber to start searching at * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. @@ -71,7 +73,7 @@ unsigned long find_next_and_bit(const unsigned long *addr1, return val ? __ffs(val) : size; } - return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); + return _find_next_and_bit(addr1, addr2, size, offset); } #endif @@ -79,8 +81,8 @@ unsigned long find_next_and_bit(const unsigned long *addr1, /** * find_next_zero_bit - find the next cleared bit in a memory region * @addr: The address to base the search on - * @offset: The bitnumber to start searching at * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at * * Returns the bit number of the next zero bit * If no bits are zero, returns @size. @@ -99,7 +101,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, return val == ~0UL ? size : ffz(val); } - return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); + return _find_next_zero_bit(addr, size, offset); } #endif @@ -172,43 +174,4 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) } #endif -#ifndef find_last_bit -/** - * find_last_bit - find the last set bit in a memory region - * @addr: The address to start the search at - * @size: The number of bits to search - * - * Returns the bit number of the last set bit, or size. - */ -static inline -unsigned long find_last_bit(const unsigned long *addr, unsigned long size) -{ - if (small_const_nbits(size)) { - unsigned long val = *addr & GENMASK(size - 1, 0); - - return val ? __fls(val) : size; - } - - return _find_last_bit(addr, size); -} -#endif - -/** - * find_next_clump8 - find next 8-bit clump with set bits in a memory region - * @clump: location to store copy of found clump - * @addr: address to base the search on - * @size: bitmap size in number of bits - * @offset: bit offset at which to start searching - * - * Returns the bit offset for the next set clump; the found clump value is - * copied to the location pointed by @clump. If no bits are set, returns @size. - */ -extern unsigned long find_next_clump8(unsigned long *clump, - const unsigned long *addr, - unsigned long size, unsigned long offset); - -#define find_first_clump8(clump, bits, size) \ - find_next_clump8((clump), (bits), (size), 0) - - #endif /*__LINUX_FIND_H_ */ diff --git a/tools/include/linux/gfp.h b/tools/include/linux/gfp.h index b238dbc9eb85..6a10ff5f5be9 100644 --- a/tools/include/linux/gfp.h +++ b/tools/include/linux/gfp.h @@ -3,26 +3,7 @@ #define _TOOLS_INCLUDE_LINUX_GFP_H #include <linux/types.h> - -#define __GFP_BITS_SHIFT 26 -#define __GFP_BITS_MASK ((gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) - -#define __GFP_HIGH 0x20u -#define __GFP_IO 0x40u -#define __GFP_FS 0x80u -#define __GFP_NOWARN 0x200u -#define __GFP_ZERO 0x8000u -#define __GFP_ATOMIC 0x80000u -#define __GFP_ACCOUNT 0x100000u -#define __GFP_DIRECT_RECLAIM 0x400000u -#define __GFP_KSWAPD_RECLAIM 0x2000000u - -#define __GFP_RECLAIM (__GFP_DIRECT_RECLAIM | __GFP_KSWAPD_RECLAIM) - -#define GFP_ZONEMASK 0x0fu -#define GFP_ATOMIC (__GFP_HIGH | __GFP_ATOMIC | __GFP_KSWAPD_RECLAIM) -#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) -#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) +#include <linux/gfp_types.h> static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { diff --git a/tools/include/linux/gfp_types.h b/tools/include/linux/gfp_types.h new file mode 100644 index 000000000000..5f9f1ed190a0 --- /dev/null +++ b/tools/include/linux/gfp_types.h @@ -0,0 +1 @@ +#include "../../../include/linux/gfp_types.h" diff --git a/tools/include/linux/kallsyms.h b/tools/include/linux/kallsyms.h index efb6c3f5f2a9..5a37ccbec54f 100644 --- a/tools/include/linux/kallsyms.h +++ b/tools/include/linux/kallsyms.h @@ -6,7 +6,7 @@ #include <stdio.h> #include <unistd.h> -#define KSYM_NAME_LEN 128 +#define KSYM_NAME_LEN 512 struct module; diff --git a/tools/include/linux/list.h b/tools/include/linux/list.h index b2fc48d5478c..a4dfb6a7cc6a 100644 --- a/tools/include/linux/list.h +++ b/tools/include/linux/list.h @@ -385,6 +385,17 @@ static inline void list_splice_tail_init(struct list_head *list, (!list_empty(ptr) ? list_first_entry(ptr, type, member) : NULL) /** + * list_last_entry_or_null - get the last element from a list + * @ptr: the list head to take the element from. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_head within the struct. + * + * Note that if the list is empty, it returns NULL. + */ +#define list_last_entry_or_null(ptr, type, member) \ + (!list_empty(ptr) ? list_last_entry(ptr, type, member) : NULL) + +/** * list_next_entry - get the next element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h index 15b940ec1eac..62c54ffbeeaa 100644 --- a/tools/include/linux/objtool.h +++ b/tools/include/linux/objtool.h @@ -32,11 +32,16 @@ struct unwind_hint { * * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. */ #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 +#define UNWIND_HINT_TYPE_ENTRY 4 +#define UNWIND_HINT_TYPE_SAVE 5 +#define UNWIND_HINT_TYPE_RESTORE 6 #ifdef CONFIG_OBJTOOL @@ -62,7 +67,7 @@ struct unwind_hint { * It should only be used in special cases where you're 100% sure it won't * affect the reliability of frame pointers and kernel stack traces. * - * For more information, see tools/objtool/Documentation/stack-validation.txt. + * For more information, see tools/objtool/Documentation/objtool.txt. */ #define STACK_FRAME_NON_STANDARD(func) \ static void __used __section(".discard.func_stack_frame_non_standard") \ @@ -124,7 +129,7 @@ struct unwind_hint { * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .Lunwind_hint_ip_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ @@ -177,7 +182,7 @@ struct unwind_hint { #define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm diff --git a/tools/include/linux/sched/mm.h b/tools/include/linux/sched/mm.h index c8d9f19c1f35..967294b8edcf 100644 --- a/tools/include/linux/sched/mm.h +++ b/tools/include/linux/sched/mm.h @@ -1,4 +1,6 @@ #ifndef _TOOLS_PERF_LINUX_SCHED_MM_H #define _TOOLS_PERF_LINUX_SCHED_MM_H +#define might_alloc(gfp) do { } while (0) + #endif /* _TOOLS_PERF_LINUX_SCHED_MM_H */ diff --git a/tools/include/linux/slab.h b/tools/include/linux/slab.h index 0616409513eb..311759ea25e9 100644 --- a/tools/include/linux/slab.h +++ b/tools/include/linux/slab.h @@ -41,4 +41,8 @@ struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, unsigned int align, unsigned int flags, void (*ctor)(void *)); +void kmem_cache_free_bulk(struct kmem_cache *cachep, size_t size, void **list); +int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size, + void **list); + #endif /* _TOOLS_SLAB_H */ diff --git a/tools/include/nolibc/Makefile b/tools/include/nolibc/Makefile index 7a16d917c185..cfd06764b5ae 100644 --- a/tools/include/nolibc/Makefile +++ b/tools/include/nolibc/Makefile @@ -7,13 +7,46 @@ ifeq ($(srctree),) srctree := $(patsubst %/tools/include/,%,$(dir $(CURDIR))) endif +# when run as make -C tools/ nolibc_<foo> the arch is not set +ifeq ($(ARCH),) +include $(srctree)/scripts/subarch.include +ARCH = $(SUBARCH) +endif + +# OUTPUT is only set when run from the main makefile, otherwise +# it defaults to this nolibc directory. +OUTPUT ?= $(CURDIR)/ + +ifeq ($(V),1) +Q= +else +Q=@ +endif + nolibc_arch := $(patsubst arm64,aarch64,$(ARCH)) arch_file := arch-$(nolibc_arch).h all_files := ctype.h errno.h nolibc.h signal.h std.h stdio.h stdlib.h string.h \ sys.h time.h types.h unistd.h # install all headers needed to support a bare-metal compiler -all: +all: headers + +install: help + +help: + @echo "Supported targets under nolibc:" + @echo " all call \"headers\"" + @echo " clean clean the sysroot" + @echo " headers prepare a sysroot in tools/include/nolibc/sysroot" + @echo " headers_standalone like \"headers\", and also install kernel headers" + @echo " help this help" + @echo "" + @echo "These targets may also be called from tools as \"make nolibc_<target>\"." + @echo "" + @echo "Currently using the following variables:" + @echo " ARCH = $(ARCH)" + @echo " OUTPUT = $(OUTPUT)" + @echo "" # Note: when ARCH is "x86" we concatenate both x86_64 and i386 headers: @@ -36,7 +69,7 @@ headers: headers_standalone: headers $(Q)$(MAKE) -C $(srctree) headers - $(Q)$(MAKE) -C $(srctree) headers_install INSTALL_HDR_PATH=$(OUTPUT)/sysroot + $(Q)$(MAKE) -C $(srctree) headers_install INSTALL_HDR_PATH=$(OUTPUT)sysroot clean: $(call QUIET_CLEAN, nolibc) rm -rf "$(OUTPUT)sysroot" diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h index 95e2b7924925..ba04771cb3a3 100644 --- a/tools/include/nolibc/arch-riscv.h +++ b/tools/include/nolibc/arch-riscv.h @@ -190,7 +190,7 @@ __asm__ (".section .text\n" ".option norelax\n" "lla gp, __global_pointer$\n" ".option pop\n" - "ld a0, 0(sp)\n" // argc (a0) was in the stack + "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) diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h index 15dedf8d0902..a3cebc4bc3ac 100644 --- a/tools/include/nolibc/stdio.h +++ b/tools/include/nolibc/stdio.h @@ -273,7 +273,7 @@ int vfprintf(FILE *stream, const char *fmt, va_list args) return written; } -static __attribute__((unused)) +static __attribute__((unused, format(printf, 2, 3))) int fprintf(FILE *stream, const char *fmt, ...) { va_list args; @@ -285,7 +285,7 @@ int fprintf(FILE *stream, const char *fmt, ...) return ret; } -static __attribute__((unused)) +static __attribute__((unused, format(printf, 1, 2))) int printf(const char *fmt, ...) { va_list args; diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h index 8fd32eaf8037..92378c4b9660 100644 --- a/tools/include/nolibc/stdlib.h +++ b/tools/include/nolibc/stdlib.h @@ -128,10 +128,9 @@ void *malloc(size_t len) static __attribute__((unused)) void *calloc(size_t size, size_t nmemb) { - void *orig; - size_t res = 0; + size_t x = size * nmemb; - if (__builtin_expect(__builtin_mul_overflow(nmemb, size, &res), 0)) { + if (__builtin_expect(size && ((x / size) != nmemb), 0)) { SET_ERRNO(ENOMEM); return NULL; } @@ -140,7 +139,7 @@ void *calloc(size_t size, size_t nmemb) * No need to zero the heap, the MAP_ANONYMOUS in malloc() * already does it. */ - return malloc(res); + return malloc(x); } static __attribute__((unused)) diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h index bef35bee9c44..ad97c0d522b8 100644 --- a/tools/include/nolibc/string.h +++ b/tools/include/nolibc/string.h @@ -19,9 +19,9 @@ static __attribute__((unused)) int memcmp(const void *s1, const void *s2, size_t n) { size_t ofs = 0; - char c1 = 0; + int c1 = 0; - while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) { + while (ofs < n && !(c1 = ((unsigned char *)s1)[ofs] - ((unsigned char *)s2)[ofs])) { ofs++; } return c1; @@ -125,14 +125,18 @@ char *strcpy(char *dst, const char *src) } /* this function is only used with arguments that are not constants or when - * it's not known because optimizations are disabled. + * it's not known because optimizations are disabled. Note that gcc 12 + * recognizes an strlen() pattern and replaces it with a jump to strlen(), + * thus itself, hence the asm() statement below that's meant to disable this + * confusing practice. */ static __attribute__((unused)) -size_t nolibc_strlen(const char *str) +size_t strlen(const char *str) { size_t len; - for (len = 0; str[len]; len++); + for (len = 0; str[len]; len++) + asm(""); return len; } @@ -140,13 +144,12 @@ size_t nolibc_strlen(const char *str) * the two branches, then will rely on an external definition of strlen(). */ #if defined(__OPTIMIZE__) +#define nolibc_strlen(x) strlen(x) #define strlen(str) ({ \ __builtin_constant_p((str)) ? \ __builtin_strlen((str)) : \ nolibc_strlen((str)); \ }) -#else -#define strlen(str) nolibc_strlen((str)) #endif static __attribute__((unused)) diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index 08491070387b..ce3ee03aa679 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -692,12 +692,12 @@ void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd, { #ifndef my_syscall6 /* Function not implemented. */ - return -ENOSYS; + return (void *)-ENOSYS; #else int n; -#if defined(__i386__) +#if defined(__NR_mmap2) n = __NR_mmap2; offset >>= 12; #else diff --git a/tools/include/tools/dis-asm-compat.h b/tools/include/tools/dis-asm-compat.h new file mode 100644 index 000000000000..70f331e23ed3 --- /dev/null +++ b/tools/include/tools/dis-asm-compat.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */ +#ifndef _TOOLS_DIS_ASM_COMPAT_H +#define _TOOLS_DIS_ASM_COMPAT_H + +#include <stdio.h> +#include <dis-asm.h> + +/* define types for older binutils version, to centralize ifdef'ery a bit */ +#ifndef DISASM_INIT_STYLED +enum disassembler_style {DISASSEMBLER_STYLE_NOT_EMPTY}; +typedef int (*fprintf_styled_ftype) (void *, enum disassembler_style, const char*, ...); +#endif + +/* + * Trivial fprintf wrapper to be used as the fprintf_styled_func argument to + * init_disassemble_info_compat() when normal fprintf suffices. + */ +static inline int fprintf_styled(void *out, + enum disassembler_style style, + const char *fmt, ...) +{ + va_list args; + int r; + + (void)style; + + va_start(args, fmt); + r = vfprintf(out, fmt, args); + va_end(args); + + return r; +} + +/* + * Wrapper for init_disassemble_info() that hides version + * differences. Depending on binutils version and architecture either + * fprintf_func or fprintf_styled_func will be called. + */ +static inline void init_disassemble_info_compat(struct disassemble_info *info, + void *stream, + fprintf_ftype unstyled_func, + fprintf_styled_ftype styled_func) +{ +#ifdef DISASM_INIT_STYLED + init_disassemble_info(info, stream, + unstyled_func, + styled_func); +#else + (void)styled_func; + init_disassemble_info(info, stream, + unstyled_func); +#endif +} + +#endif /* _TOOLS_DIS_ASM_COMPAT_H */ diff --git a/tools/include/uapi/asm-generic/fcntl.h b/tools/include/uapi/asm-generic/fcntl.h index 0197042b7dfb..b02c8e0f4057 100644 --- a/tools/include/uapi/asm-generic/fcntl.h +++ b/tools/include/uapi/asm-generic/fcntl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_GENERIC_FCNTL_H #define _ASM_GENERIC_FCNTL_H @@ -90,7 +91,7 @@ /* a horrid kludge trying to make sure that this will fail on old kernels */ #define O_TMPFILE (__O_TMPFILE | O_DIRECTORY) -#define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT) +#define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT) #ifndef O_NDELAY #define O_NDELAY O_NONBLOCK @@ -115,11 +116,13 @@ #define F_GETSIG 11 /* for sockets. */ #endif +#if __BITS_PER_LONG == 32 || defined(__KERNEL__) #ifndef F_GETLK64 #define F_GETLK64 12 /* using 'struct flock64' */ #define F_SETLK64 13 #define F_SETLKW64 14 #endif +#endif /* __BITS_PER_LONG == 32 || defined(__KERNEL__) */ #ifndef F_SETOWN_EX #define F_SETOWN_EX 15 @@ -140,7 +143,7 @@ * record locks, but are "owned" by the open file description, not the * process. This means that they are inherited across fork() like BSD (flock) * locks, and they are only released automatically when the last reference to - * the the open file against which they were acquired is put. + * the open file against which they were acquired is put. */ #define F_OFD_GETLK 36 #define F_OFD_SETLK 37 @@ -178,6 +181,10 @@ struct f_owner_ex { blocking */ #define LOCK_UN 8 /* remove lock */ +/* + * LOCK_MAND support has been removed from the kernel. We leave the symbols + * here to not break legacy builds, but these should not be used in new code. + */ #define LOCK_MAND 32 /* This is a mandatory flock ... */ #define LOCK_READ 64 /* which allows concurrent read operations */ #define LOCK_WRITE 128 /* which allows concurrent write operations */ @@ -185,6 +192,7 @@ struct f_owner_ex { #define F_LINUX_SPECIFIC_BASE 1024 +#ifndef HAVE_ARCH_STRUCT_FLOCK struct flock { short l_type; short l_whence; @@ -209,5 +217,6 @@ struct flock64 { __ARCH_FLOCK64_PAD #endif }; +#endif /* HAVE_ARCH_STRUCT_FLOCK */ #endif /* _ASM_GENERIC_FCNTL_H */ diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h index 6c1aa92a92e4..6ce1f1ceb432 100644 --- a/tools/include/uapi/asm-generic/mman-common.h +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -77,6 +77,8 @@ #define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */ +#define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/tools/include/uapi/asm/errno.h b/tools/include/uapi/asm/errno.h index d30439b4b8ab..869379f91fe4 100644 --- a/tools/include/uapi/asm/errno.h +++ b/tools/include/uapi/asm/errno.h @@ -9,8 +9,8 @@ #include "../../../arch/alpha/include/uapi/asm/errno.h" #elif defined(__mips__) #include "../../../arch/mips/include/uapi/asm/errno.h" -#elif defined(__xtensa__) -#include "../../../arch/xtensa/include/uapi/asm/errno.h" +#elif defined(__hppa__) +#include "../../../arch/parisc/include/uapi/asm/errno.h" #else #include <asm-generic/errno.h> #endif diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index a2def7b27009..520ad2691a99 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -751,14 +751,27 @@ typedef struct drm_i915_irq_wait { /* Must be kept compact -- no holes and well documented */ -typedef struct drm_i915_getparam { +/** + * struct drm_i915_getparam - Driver parameter query structure. + */ +struct drm_i915_getparam { + /** @param: Driver parameter to query. */ __s32 param; - /* + + /** + * @value: Address of memory where queried value should be put. + * * WARNING: Using pointers instead of fixed-size u64 means we need to write * compat32 code. Don't repeat this mistake. */ int __user *value; -} drm_i915_getparam_t; +}; + +/** + * typedef drm_i915_getparam_t - Driver parameter query structure. + * See struct drm_i915_getparam. + */ +typedef struct drm_i915_getparam drm_i915_getparam_t; /* Ioctl to set kernel params: */ @@ -1239,76 +1252,119 @@ struct drm_i915_gem_exec_object2 { __u64 rsvd2; }; +/** + * struct drm_i915_gem_exec_fence - An input or output fence for the execbuf + * ioctl. + * + * The request will wait for input fence to signal before submission. + * + * The returned output fence will be signaled after the completion of the + * request. + */ struct drm_i915_gem_exec_fence { - /** - * User's handle for a drm_syncobj to wait on or signal. - */ + /** @handle: User's handle for a drm_syncobj to wait on or signal. */ __u32 handle; + /** + * @flags: Supported flags are: + * + * I915_EXEC_FENCE_WAIT: + * Wait for the input fence before request submission. + * + * I915_EXEC_FENCE_SIGNAL: + * Return request completion fence as output + */ + __u32 flags; #define I915_EXEC_FENCE_WAIT (1<<0) #define I915_EXEC_FENCE_SIGNAL (1<<1) #define __I915_EXEC_FENCE_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SIGNAL << 1)) - __u32 flags; }; -/* - * See drm_i915_gem_execbuffer_ext_timeline_fences. - */ -#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0 - -/* +/** + * struct drm_i915_gem_execbuffer_ext_timeline_fences - Timeline fences + * for execbuf ioctl. + * * This structure describes an array of drm_syncobj and associated points for * timeline variants of drm_syncobj. It is invalid to append this structure to * the execbuf if I915_EXEC_FENCE_ARRAY is set. */ struct drm_i915_gem_execbuffer_ext_timeline_fences { +#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0 + /** @base: Extension link. See struct i915_user_extension. */ struct i915_user_extension base; /** - * Number of element in the handles_ptr & value_ptr arrays. + * @fence_count: Number of elements in the @handles_ptr & @value_ptr + * arrays. */ __u64 fence_count; /** - * Pointer to an array of struct drm_i915_gem_exec_fence of length - * fence_count. + * @handles_ptr: Pointer to an array of struct drm_i915_gem_exec_fence + * of length @fence_count. */ __u64 handles_ptr; /** - * Pointer to an array of u64 values of length fence_count. Values - * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline - * drm_syncobj is invalid as it turns a drm_syncobj into a binary one. + * @values_ptr: Pointer to an array of u64 values of length + * @fence_count. + * Values must be 0 for a binary drm_syncobj. A Value of 0 for a + * timeline drm_syncobj is invalid as it turns a drm_syncobj into a + * binary one. */ __u64 values_ptr; }; +/** + * struct drm_i915_gem_execbuffer2 - Structure for DRM_I915_GEM_EXECBUFFER2 + * ioctl. + */ struct drm_i915_gem_execbuffer2 { - /** - * List of gem_exec_object2 structs - */ + /** @buffers_ptr: Pointer to a list of gem_exec_object2 structs */ __u64 buffers_ptr; + + /** @buffer_count: Number of elements in @buffers_ptr array */ __u32 buffer_count; - /** Offset in the batchbuffer to start execution from. */ + /** + * @batch_start_offset: Offset in the batchbuffer to start execution + * from. + */ __u32 batch_start_offset; - /** Bytes used in batchbuffer from batch_start_offset */ + + /** + * @batch_len: Length in bytes of the batch buffer, starting from the + * @batch_start_offset. If 0, length is assumed to be the batch buffer + * object size. + */ __u32 batch_len; + + /** @DR1: deprecated */ __u32 DR1; + + /** @DR4: deprecated */ __u32 DR4; + + /** @num_cliprects: See @cliprects_ptr */ __u32 num_cliprects; + /** - * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY - * & I915_EXEC_USE_EXTENSIONS are not set. + * @cliprects_ptr: Kernel clipping was a DRI1 misfeature. + * + * It is invalid to use this field if I915_EXEC_FENCE_ARRAY or + * I915_EXEC_USE_EXTENSIONS flags are not set. * * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array - * of struct drm_i915_gem_exec_fence and num_cliprects is the length - * of the array. + * of &drm_i915_gem_exec_fence and @num_cliprects is the length of the + * array. * * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a - * single struct i915_user_extension and num_cliprects is 0. + * single &i915_user_extension and num_cliprects is 0. */ __u64 cliprects_ptr; + + /** @flags: Execbuf flags */ + __u64 flags; #define I915_EXEC_RING_MASK (0x3f) #define I915_EXEC_DEFAULT (0<<0) #define I915_EXEC_RENDER (1<<0) @@ -1326,10 +1382,6 @@ struct drm_i915_gem_execbuffer2 { #define I915_EXEC_CONSTANTS_REL_GENERAL (0<<6) /* default */ #define I915_EXEC_CONSTANTS_ABSOLUTE (1<<6) #define I915_EXEC_CONSTANTS_REL_SURFACE (2<<6) /* gen4/5 only */ - __u64 flags; - __u64 rsvd1; /* now used for context info */ - __u64 rsvd2; -}; /** Resets the SO write offset registers for transform feedback on gen7. */ #define I915_EXEC_GEN7_SOL_RESET (1<<8) @@ -1432,9 +1484,23 @@ struct drm_i915_gem_execbuffer2 { * drm_i915_gem_execbuffer_ext enum. */ #define I915_EXEC_USE_EXTENSIONS (1 << 21) - #define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1)) + /** @rsvd1: Context id */ + __u64 rsvd1; + + /** + * @rsvd2: in and out sync_file file descriptors. + * + * When I915_EXEC_FENCE_IN or I915_EXEC_FENCE_SUBMIT flag is set, the + * lower 32 bits of this field will have the in sync_file fd (input). + * + * When I915_EXEC_FENCE_OUT flag is set, the upper 32 bits of this + * field will have the out sync_file fd (output). + */ + __u64 rsvd2; +}; + #define I915_EXEC_CONTEXT_ID_MASK (0xffffffff) #define i915_execbuffer2_set_context_id(eb2, context) \ (eb2).rsvd1 = context & I915_EXEC_CONTEXT_ID_MASK @@ -1814,19 +1880,58 @@ struct drm_i915_gem_context_create { __u32 pad; }; +/** + * struct drm_i915_gem_context_create_ext - Structure for creating contexts. + */ struct drm_i915_gem_context_create_ext { - __u32 ctx_id; /* output: id of new context*/ + /** @ctx_id: Id of the created context (output) */ + __u32 ctx_id; + + /** + * @flags: Supported flags are: + * + * I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS: + * + * Extensions may be appended to this structure and driver must check + * for those. See @extensions. + * + * I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE + * + * Created context will have single timeline. + */ __u32 flags; #define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS (1u << 0) #define I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE (1u << 1) #define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \ (-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1)) + + /** + * @extensions: Zero-terminated chain of extensions. + * + * I915_CONTEXT_CREATE_EXT_SETPARAM: + * Context parameter to set or query during context creation. + * See struct drm_i915_gem_context_create_ext_setparam. + * + * I915_CONTEXT_CREATE_EXT_CLONE: + * This extension has been removed. On the off chance someone somewhere + * has attempted to use it, never re-use this extension number. + */ __u64 extensions; +#define I915_CONTEXT_CREATE_EXT_SETPARAM 0 +#define I915_CONTEXT_CREATE_EXT_CLONE 1 }; +/** + * struct drm_i915_gem_context_param - Context parameter to set or query. + */ struct drm_i915_gem_context_param { + /** @ctx_id: Context id */ __u32 ctx_id; + + /** @size: Size of the parameter @value */ __u32 size; + + /** @param: Parameter to set or query */ __u64 param; #define I915_CONTEXT_PARAM_BAN_PERIOD 0x1 /* I915_CONTEXT_PARAM_NO_ZEROMAP has been removed. On the off chance @@ -1973,6 +2078,7 @@ struct drm_i915_gem_context_param { #define I915_CONTEXT_PARAM_PROTECTED_CONTENT 0xd /* Must be kept compact -- no holes and well documented */ + /** @value: Context parameter value to be set or queried */ __u64 value; }; @@ -2123,7 +2229,7 @@ struct i915_context_engines_load_balance { __u64 mbz64; /* reserved for future use; must be zero */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __attribute__((packed)); #define I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(name__, N__) struct { \ @@ -2161,7 +2267,7 @@ struct i915_context_engines_bond { __u64 flags; /* all undefined flags must be zero */ __u64 mbz64[4]; /* reserved for future use; must be zero */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __attribute__((packed)); #define I915_DEFINE_CONTEXT_ENGINES_BOND(name__, N__) struct { \ @@ -2288,7 +2394,7 @@ struct i915_context_engines_parallel_submit { * length = width (i) * num_siblings (j) * index = j + i * num_siblings */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __packed; @@ -2371,23 +2477,29 @@ struct i915_context_param_engines { struct i915_engine_class_instance engines[N__]; \ } __attribute__((packed)) name__ +/** + * struct drm_i915_gem_context_create_ext_setparam - Context parameter + * to set or query during context creation. + */ struct drm_i915_gem_context_create_ext_setparam { -#define I915_CONTEXT_CREATE_EXT_SETPARAM 0 + /** @base: Extension link. See struct i915_user_extension. */ struct i915_user_extension base; + + /** + * @param: Context parameter to set or query. + * See struct drm_i915_gem_context_param. + */ struct drm_i915_gem_context_param param; }; -/* This API has been removed. On the off chance someone somewhere has - * attempted to use it, never re-use this extension number. - */ -#define I915_CONTEXT_CREATE_EXT_CLONE 1 - struct drm_i915_gem_context_destroy { __u32 ctx_id; __u32 pad; }; -/* +/** + * struct drm_i915_gem_vm_control - Structure to create or destroy VM. + * * DRM_I915_GEM_VM_CREATE - * * Create a new virtual memory address space (ppGTT) for use within a context @@ -2397,20 +2509,23 @@ struct drm_i915_gem_context_destroy { * The id of new VM (bound to the fd) for use with I915_CONTEXT_PARAM_VM is * returned in the outparam @id. * - * No flags are defined, with all bits reserved and must be zero. - * * An extension chain maybe provided, starting with @extensions, and terminated * by the @next_extension being 0. Currently, no extensions are defined. * * DRM_I915_GEM_VM_DESTROY - * - * Destroys a previously created VM id, specified in @id. + * Destroys a previously created VM id, specified in @vm_id. * * No extensions or flags are allowed currently, and so must be zero. */ struct drm_i915_gem_vm_control { + /** @extensions: Zero-terminated chain of extensions. */ __u64 extensions; + + /** @flags: reserved for future usage, currently MBZ */ __u32 flags; + + /** @vm_id: Id of the VM created or to be destroyed */ __u32 vm_id; }; @@ -3207,36 +3322,6 @@ struct drm_i915_gem_memory_class_instance { * struct drm_i915_memory_region_info - Describes one region as known to the * driver. * - * Note that we reserve some stuff here for potential future work. As an example - * we might want expose the capabilities for a given region, which could include - * things like if the region is CPU mappable/accessible, what are the supported - * mapping types etc. - * - * Note that to extend struct drm_i915_memory_region_info and struct - * drm_i915_query_memory_regions in the future the plan is to do the following: - * - * .. code-block:: C - * - * struct drm_i915_memory_region_info { - * struct drm_i915_gem_memory_class_instance region; - * union { - * __u32 rsvd0; - * __u32 new_thing1; - * }; - * ... - * union { - * __u64 rsvd1[8]; - * struct { - * __u64 new_thing2; - * __u64 new_thing3; - * ... - * }; - * }; - * }; - * - * With this things should remain source compatible between versions for - * userspace, even as we add new fields. - * * Note this is using both struct drm_i915_query_item and struct drm_i915_query. * For this new query we are adding the new query id DRM_I915_QUERY_MEMORY_REGIONS * at &drm_i915_query_item.query_id. @@ -3248,14 +3333,81 @@ struct drm_i915_memory_region_info { /** @rsvd0: MBZ */ __u32 rsvd0; - /** @probed_size: Memory probed by the driver (-1 = unknown) */ + /** + * @probed_size: Memory probed by the driver + * + * Note that it should not be possible to ever encounter a zero value + * here, also note that no current region type will ever return -1 here. + * Although for future region types, this might be a possibility. The + * same applies to the other size fields. + */ __u64 probed_size; - /** @unallocated_size: Estimate of memory remaining (-1 = unknown) */ + /** + * @unallocated_size: Estimate of memory remaining + * + * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable accounting. + * Without this (or if this is an older kernel) the value here will + * always equal the @probed_size. Note this is only currently tracked + * for I915_MEMORY_CLASS_DEVICE regions (for other types the value here + * will always equal the @probed_size). + */ __u64 unallocated_size; - /** @rsvd1: MBZ */ - __u64 rsvd1[8]; + union { + /** @rsvd1: MBZ */ + __u64 rsvd1[8]; + struct { + /** + * @probed_cpu_visible_size: Memory probed by the driver + * that is CPU accessible. + * + * This will be always be <= @probed_size, and the + * remainder (if there is any) will not be CPU + * accessible. + * + * On systems without small BAR, the @probed_size will + * always equal the @probed_cpu_visible_size, since all + * of it will be CPU accessible. + * + * Note this is only tracked for + * I915_MEMORY_CLASS_DEVICE regions (for other types the + * value here will always equal the @probed_size). + * + * Note that if the value returned here is zero, then + * this must be an old kernel which lacks the relevant + * small-bar uAPI support (including + * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS), but on + * such systems we should never actually end up with a + * small BAR configuration, assuming we are able to load + * the kernel module. Hence it should be safe to treat + * this the same as when @probed_cpu_visible_size == + * @probed_size. + */ + __u64 probed_cpu_visible_size; + + /** + * @unallocated_cpu_visible_size: Estimate of CPU + * visible memory remaining. + * + * Note this is only tracked for + * I915_MEMORY_CLASS_DEVICE regions (for other types the + * value here will always equal the + * @probed_cpu_visible_size). + * + * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable + * accounting. Without this the value here will always + * equal the @probed_cpu_visible_size. Note this is only + * currently tracked for I915_MEMORY_CLASS_DEVICE + * regions (for other types the value here will also + * always equal the @probed_cpu_visible_size). + * + * If this is an older kernel the value here will be + * zero, see also @probed_cpu_visible_size. + */ + __u64 unallocated_cpu_visible_size; + }; + }; }; /** @@ -3329,11 +3481,11 @@ struct drm_i915_query_memory_regions { * struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added * extension support using struct i915_user_extension. * - * Note that in the future we want to have our buffer flags here, at least for - * the stuff that is immutable. Previously we would have two ioctls, one to - * create the object with gem_create, and another to apply various parameters, - * however this creates some ambiguity for the params which are considered - * immutable. Also in general we're phasing out the various SET/GET ioctls. + * Note that new buffer flags should be added here, at least for the stuff that + * is immutable. Previously we would have two ioctls, one to create the object + * with gem_create, and another to apply various parameters, however this + * creates some ambiguity for the params which are considered immutable. Also in + * general we're phasing out the various SET/GET ioctls. */ struct drm_i915_gem_create_ext { /** @@ -3341,7 +3493,6 @@ struct drm_i915_gem_create_ext { * * The (page-aligned) allocated size for the object will be returned. * - * * DG2 64K min page size implications: * * On discrete platforms, starting from DG2, we have to contend with GTT @@ -3353,7 +3504,9 @@ struct drm_i915_gem_create_ext { * * Note that the returned size here will always reflect any required * rounding up done by the kernel, i.e 4K will now become 64K on devices - * such as DG2. + * such as DG2. The kernel will always select the largest minimum + * page-size for the set of possible placements as the value to use when + * rounding up the @size. * * Special DG2 GTT address alignment requirement: * @@ -3377,14 +3530,58 @@ struct drm_i915_gem_create_ext { * is deemed to be a good compromise. */ __u64 size; + /** * @handle: Returned handle for the object. * * Object handles are nonzero. */ __u32 handle; - /** @flags: MBZ */ + + /** + * @flags: Optional flags. + * + * Supported values: + * + * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS - Signal to the kernel that + * the object will need to be accessed via the CPU. + * + * Only valid when placing objects in I915_MEMORY_CLASS_DEVICE, and only + * strictly required on configurations where some subset of the device + * memory is directly visible/mappable through the CPU (which we also + * call small BAR), like on some DG2+ systems. Note that this is quite + * undesirable, but due to various factors like the client CPU, BIOS etc + * it's something we can expect to see in the wild. See + * &drm_i915_memory_region_info.probed_cpu_visible_size for how to + * determine if this system applies. + * + * Note that one of the placements MUST be I915_MEMORY_CLASS_SYSTEM, to + * ensure the kernel can always spill the allocation to system memory, + * if the object can't be allocated in the mappable part of + * I915_MEMORY_CLASS_DEVICE. + * + * Also note that since the kernel only supports flat-CCS on objects + * that can *only* be placed in I915_MEMORY_CLASS_DEVICE, we therefore + * don't support I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS together with + * flat-CCS. + * + * Without this hint, the kernel will assume that non-mappable + * I915_MEMORY_CLASS_DEVICE is preferred for this object. Note that the + * kernel can still migrate the object to the mappable part, as a last + * resort, if userspace ever CPU faults this object, but this might be + * expensive, and so ideally should be avoided. + * + * On older kernels which lack the relevant small-bar uAPI support (see + * also &drm_i915_memory_region_info.probed_cpu_visible_size), + * usage of the flag will result in an error, but it should NEVER be + * possible to end up with a small BAR configuration, assuming we can + * also successfully load the i915 kernel module. In such cases the + * entire I915_MEMORY_CLASS_DEVICE region will be CPU accessible, and as + * such there are zero restrictions on where the object can be placed. + */ +#define I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS (1 << 0) __u32 flags; + /** * @extensions: The chain of extensions to apply to this object. * @@ -3443,6 +3640,22 @@ struct drm_i915_gem_create_ext { * At which point we get the object handle in &drm_i915_gem_create_ext.handle, * along with the final object size in &drm_i915_gem_create_ext.size, which * should account for any rounding up, if required. + * + * Note that userspace has no means of knowing the current backing region + * for objects where @num_regions is larger than one. The kernel will only + * ensure that the priority order of the @regions array is honoured, either + * when initially placing the object, or when moving memory around due to + * memory pressure + * + * On Flat-CCS capable HW, compression is supported for the objects residing + * in I915_MEMORY_CLASS_DEVICE. When such objects (compressed) have other + * memory class in @regions and migrated (by i915, due to memory + * constraints) to the non I915_MEMORY_CLASS_DEVICE region, then i915 needs to + * decompress the content. But i915 doesn't have the required information to + * decompress the userspace compressed objects. + * + * So i915 supports Flat-CCS, on the objects which can reside only on + * I915_MEMORY_CLASS_DEVICE regions. */ struct drm_i915_gem_create_ext_memory_regions { /** @base: Extension link. See struct i915_user_extension. */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f4009dbdf62d..51b9aa640ad2 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -87,10 +87,35 @@ struct bpf_cgroup_storage_key { __u32 attach_type; /* program attach type (enum bpf_attach_type) */ }; +enum bpf_cgroup_iter_order { + BPF_CGROUP_ITER_ORDER_UNSPEC = 0, + BPF_CGROUP_ITER_SELF_ONLY, /* process only a single object. */ + BPF_CGROUP_ITER_DESCENDANTS_PRE, /* walk descendants in pre-order. */ + BPF_CGROUP_ITER_DESCENDANTS_POST, /* walk descendants in post-order. */ + BPF_CGROUP_ITER_ANCESTORS_UP, /* walk ancestors upward. */ +}; + union bpf_iter_link_info { struct { __u32 map_fd; } map; + struct { + enum bpf_cgroup_iter_order order; + + /* At most one of cgroup_fd and cgroup_id can be non-zero. If + * both are zero, the walk starts from the default cgroup v2 + * root. For walking v1 hierarchy, one should always explicitly + * specify cgroup_fd. + */ + __u32 cgroup_fd; + __u64 cgroup_id; + } cgroup; + /* Parameters of task iterators. */ + struct { + __u32 tid; + __u32 pid; + __u32 pid_fd; + } task; }; /* BPF syscall commands, see bpf(2) man-page for more details. */ @@ -909,6 +934,7 @@ enum bpf_map_type { BPF_MAP_TYPE_INODE_STORAGE, BPF_MAP_TYPE_TASK_STORAGE, BPF_MAP_TYPE_BLOOM_FILTER, + BPF_MAP_TYPE_USER_RINGBUF, }; /* Note that tracing related programs such as @@ -998,6 +1024,7 @@ enum bpf_attach_type { BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, BPF_PERF_EVENT, BPF_TRACE_KPROBE_MULTI, + BPF_LSM_CGROUP, __MAX_BPF_ATTACH_TYPE }; @@ -1232,7 +1259,7 @@ enum { /* Query effective (directly attached + inherited from ancestor cgroups) * programs that will be executed for events within a cgroup. - * attach_flags with this flag are returned only for directly attached programs. + * attach_flags with this flag are always returned 0. */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) @@ -1431,6 +1458,10 @@ union bpf_attr { __u32 attach_flags; __aligned_u64 prog_ids; __u32 prog_cnt; + /* output: per-program attach_flags. + * not allowed to be set during effective query. + */ + __aligned_u64 prog_attach_flags; } query; struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ @@ -2359,7 +2390,8 @@ union bpf_attr { * Pull in non-linear data in case the *skb* is non-linear and not * all of *len* are part of the linear section. Make *len* bytes * from *skb* readable and writable. If a zero value is passed for - * *len*, then the whole length of the *skb* is pulled. + * *len*, then all bytes in the linear part of *skb* will be made + * readable and writable. * * This helper is only needed for reading and writing with direct * packet access. @@ -2570,10 +2602,12 @@ union bpf_attr { * There are two supported modes at this time: * * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer - * (room space is added or removed below the layer 2 header). + * (room space is added or removed between the layer 2 and + * layer 3 headers). * * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer - * (room space is added or removed below the layer 3 header). + * (room space is added or removed between the layer 3 and + * layer 4 headers). * * The following flags are supported at this time: * @@ -3005,8 +3039,18 @@ union bpf_attr { * **BPF_F_USER_STACK** * Collect a user space stack instead of a kernel stack. * **BPF_F_USER_BUILD_ID** - * Collect buildid+offset instead of ips for user stack, - * only valid if **BPF_F_USER_STACK** is also specified. + * Collect (build_id, file_offset) instead of ips for user + * stack, only valid if **BPF_F_USER_STACK** is also + * specified. + * + * *file_offset* is an offset relative to the beginning + * of the executable or shared object file backing the vma + * which the *ip* falls in. It is *not* an offset relative + * to that object's base address. Accordingly, it must be + * adjusted by adding (sh_addr - sh_offset), where + * sh_{addr,offset} correspond to the executable section + * containing *file_offset* in the object, for comparisons + * to symbols' st_value to be valid. * * **bpf_get_stack**\ () can collect up to * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject @@ -3597,10 +3641,11 @@ union bpf_attr { * * *iph* points to the start of the IPv4 or IPv6 header, while * *iph_len* contains **sizeof**\ (**struct iphdr**) or - * **sizeof**\ (**struct ip6hdr**). + * **sizeof**\ (**struct ipv6hdr**). * * *th* points to the start of the TCP header, while *th_len* - * contains **sizeof**\ (**struct tcphdr**). + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). * Return * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative * error otherwise. @@ -3783,10 +3828,11 @@ union bpf_attr { * * *iph* points to the start of the IPv4 or IPv6 header, while * *iph_len* contains **sizeof**\ (**struct iphdr**) or - * **sizeof**\ (**struct ip6hdr**). + * **sizeof**\ (**struct ipv6hdr**). * * *th* points to the start of the TCP header, while *th_len* - * contains the length of the TCP header. + * contains the length of the TCP header with options (at least + * **sizeof**\ (**struct tcphdr**)). * Return * On success, lower 32 bits hold the generated SYN cookie in * followed by 16 bits which hold the MSS value for that cookie, @@ -4420,7 +4466,7 @@ union bpf_attr { * * **-EEXIST** if the option already exists. * - * **-EFAULT** on failrue to parse the existing header options. + * **-EFAULT** on failure to parse the existing header options. * * **-EPERM** if the helper cannot be used under the current * *skops*\ **->op**. @@ -4629,7 +4675,7 @@ union bpf_attr { * a *map* with *task* as the **key**. From this * perspective, the usage is not much different from * **bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this - * helper enforces the key must be an task_struct and the map must also + * helper enforces the key must be a task_struct and the map must also * be a **BPF_MAP_TYPE_TASK_STORAGE**. * * Underneath, the value is stored locally at *task* instead of @@ -4687,7 +4733,7 @@ union bpf_attr { * * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size) * Description - * Returns the stored IMA hash of the *inode* (if it's avaialable). + * Returns the stored IMA hash of the *inode* (if it's available). * If the hash is larger than *size*, then only *size* * bytes will be copied to *dst* * Return @@ -4711,12 +4757,12 @@ union bpf_attr { * * The argument *len_diff* can be used for querying with a planned * size change. This allows to check MTU prior to changing packet - * ctx. Providing an *len_diff* adjustment that is larger than the + * ctx. Providing a *len_diff* adjustment that is larger than the * actual packet size (resulting in negative packet size) will in - * principle not exceed the MTU, why it is not considered a - * failure. Other BPF-helpers are needed for performing the - * planned size change, why the responsability for catch a negative - * packet size belong in those helpers. + * principle not exceed the MTU, which is why it is not considered + * a failure. Other BPF helpers are needed for performing the + * planned size change; therefore the responsibility for catching + * a negative packet size belongs in those helpers. * * Specifying *ifindex* zero means the MTU check is performed * against the current net device. This is practical if this isn't @@ -4914,6 +4960,7 @@ union bpf_attr { * Get address of the traced function (for tracing and kprobe programs). * Return * Address of the traced function. + * 0 for kprobes placed within the function (not at the entry). * * u64 bpf_get_attach_cookie(void *ctx) * Description @@ -5043,12 +5090,12 @@ union bpf_attr { * * long bpf_get_func_arg(void *ctx, u32 n, u64 *value) * Description - * Get **n**-th argument (zero based) of the traced function (for tracing programs) + * Get **n**-th argument register (zero based) of the traced function (for tracing programs) * returned in **value**. * * Return * 0 on success. - * **-EINVAL** if n >= arguments count of traced function. + * **-EINVAL** if n >= argument register count of traced function. * * long bpf_get_func_ret(void *ctx, u64 *value) * Description @@ -5061,24 +5108,37 @@ union bpf_attr { * * long bpf_get_func_arg_cnt(void *ctx) * Description - * Get number of arguments of the traced function (for tracing programs). + * Get number of registers of the traced function (for tracing programs) where + * function arguments are stored in these registers. * * Return - * The number of arguments of the traced function. + * The number of argument registers of the traced function. * * int bpf_get_retval(void) * Description - * Get the syscall's return value that will be returned to userspace. + * Get the BPF program's return value that will be returned to the upper layers. * - * This helper is currently supported by cgroup programs only. + * This helper is currently supported by cgroup programs and only by the hooks + * where BPF program's return value is returned to the userspace via errno. * Return - * The syscall's return value. + * The BPF program's return value. * * int bpf_set_retval(int retval) * Description - * Set the syscall's return value that will be returned to userspace. + * Set the BPF program's return value that will be returned to the upper layers. + * + * This helper is currently supported by cgroup programs and only by the hooks + * where BPF program's return value is returned to the userspace via errno. + * + * Note that there is the following corner case where the program exports an error + * via bpf_set_retval but signals success via 'return 1': + * + * bpf_set_retval(-EPERM); + * return 1; + * + * In this case, the BPF program's return value will use helper's -EPERM. This + * still holds true for cgroup/bind{4,6} which supports extra 'return 3' success case. * - * This helper is currently supported by cgroup programs only. * Return * 0 on success, or a negative error in case of failure. * @@ -5222,22 +5282,25 @@ union bpf_attr { * Return * Nothing. Always succeeds. * - * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset) + * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset, u64 flags) * Description * Read *len* bytes from *src* into *dst*, starting from *offset* * into *src*. + * *flags* is currently unused. * Return * 0 on success, -E2BIG if *offset* + *len* exceeds the length - * of *src*'s data, -EINVAL if *src* is an invalid dynptr. + * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if + * *flags* is not 0. * - * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len) + * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) * Description * Write *len* bytes from *src* into *dst*, starting from *offset* * into *dst*. + * *flags* is currently unused. * Return * 0 on success, -E2BIG if *offset* + *len* exceeds the length * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* - * is a read-only dynptr. + * is a read-only dynptr or if *flags* is not 0. * * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len) * Description @@ -5249,6 +5312,129 @@ union bpf_attr { * Pointer to the underlying dynptr data, NULL if the dynptr is * read-only, if the dynptr is invalid, or if the offset and length * is out of bounds. + * + * s64 bpf_tcp_raw_gen_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IPv4/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + * + * s64 bpf_tcp_raw_gen_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IPv6/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + * + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. + * + * long bpf_tcp_raw_check_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the TCP header. + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK. + * + * On failure, the returned value is one of the following: + * + * **-EACCES** if the SYN cookie is not valid. + * + * long bpf_tcp_raw_check_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the TCP header. + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK. + * + * On failure, the returned value is one of the following: + * + * **-EACCES** if the SYN cookie is not valid. + * + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. + * + * u64 bpf_ktime_get_tai_ns(void) + * Description + * A nonsettable system-wide clock derived from wall-clock time but + * ignoring leap seconds. This clock does not experience + * discontinuities and backwards jumps caused by NTP inserting leap + * seconds as CLOCK_REALTIME does. + * + * See: **clock_gettime**\ (**CLOCK_TAI**) + * Return + * Current *ktime*. + * + * long bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void *ctx, u64 flags) + * Description + * Drain samples from the specified user ring buffer, and invoke + * the provided callback for each such sample: + * + * long (\*callback_fn)(struct bpf_dynptr \*dynptr, void \*ctx); + * + * If **callback_fn** returns 0, the helper will continue to try + * and drain the next sample, up to a maximum of + * BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1, + * the helper will skip the rest of the samples and return. Other + * return values are not used now, and will be rejected by the + * verifier. + * Return + * The number of drained samples if no error was encountered while + * draining samples, or 0 if no samples were present in the ring + * buffer. If a user-space producer was epoll-waiting on this map, + * and at least one sample was drained, they will receive an event + * notification notifying them of available space in the ring + * buffer. If the BPF_RB_NO_WAKEUP flag is passed to this + * function, no wakeup notification will be sent. If the + * BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will + * be sent even if no sample was drained. + * + * On failure, the returned value is one of the following: + * + * **-EBUSY** if the ring buffer is contended, and another calling + * context was concurrently draining the ring buffer. + * + * **-EINVAL** if user-space is not properly tracking the ring + * buffer due to the producer position not being aligned to 8 + * bytes, a sample not being aligned to 8 bytes, or the producer + * position not matching the advertised length of a sample. + * + * **-E2BIG** if user-space has tried to publish a sample which is + * larger than the size of the ring buffer, or which cannot fit + * within a struct bpf_dynptr. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5455,6 +5641,12 @@ union bpf_attr { FN(dynptr_read), \ FN(dynptr_write), \ FN(dynptr_data), \ + FN(tcp_raw_gen_syncookie_ipv4), \ + FN(tcp_raw_gen_syncookie_ipv6), \ + FN(tcp_raw_check_syncookie_ipv4), \ + FN(tcp_raw_check_syncookie_ipv6), \ + FN(ktime_get_tai_ns), \ + FN(user_ringbuf_drain), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5517,6 +5709,11 @@ enum { BPF_F_SEQ_NUMBER = (1ULL << 3), }; +/* BPF_FUNC_skb_get_tunnel_key flags. */ +enum { + BPF_F_TUNINFO_FLAGS = (1ULL << 4), +}; + /* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and * BPF_FUNC_perf_event_read_value flags. */ @@ -5706,7 +5903,10 @@ struct bpf_tunnel_key { }; __u8 tunnel_tos; __u8 tunnel_ttl; - __u16 tunnel_ext; /* Padding, future use. */ + union { + __u16 tunnel_ext; /* compat */ + __be16 tunnel_flags; + }; __u32 tunnel_label; union { __u32 local_ipv4; @@ -5750,6 +5950,11 @@ enum bpf_ret_code { * represented by BPF_REDIRECT above). */ BPF_LWT_REROUTE = 128, + /* BPF_FLOW_DISSECTOR_CONTINUE: used by BPF_PROG_TYPE_FLOW_DISSECTOR + * to indicate that no custom dissection was performed, and + * fallback to standard dissector is requested. + */ + BPF_FLOW_DISSECTOR_CONTINUE = 129, }; struct bpf_sock { @@ -5995,6 +6200,8 @@ struct bpf_prog_info { __u64 run_cnt; __u64 recursion_misses; __u32 verified_insns; + __u32 attach_btf_obj_id; + __u32 attach_btf_id; } __attribute__((aligned(8))); struct bpf_map_info { @@ -6046,11 +6253,26 @@ struct bpf_link_info { struct { __aligned_u64 target_name; /* in/out: target_name buffer ptr */ __u32 target_name_len; /* in/out: target_name buffer len */ + + /* If the iter specific field is 32 bits, it can be put + * in the first or second union. Otherwise it should be + * put in the second union. + */ union { struct { __u32 map_id; } map; }; + union { + struct { + __u64 cgroup_id; + __u32 order; + } cgroup; + struct { + __u32 tid; + __u32 pid; + } task; + }; } iter; struct { __u32 netns_ino; @@ -6702,6 +6924,7 @@ enum bpf_core_relo_kind { BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */ BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ + BPF_CORE_TYPE_MATCHES = 12, /* type match in target kernel */ }; /* diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index a9162a6c0284..ec1798b6d3ff 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -36,10 +36,10 @@ struct btf_type { * bits 24-28: kind (e.g. int, ptr, array...etc) * bits 29-30: unused * bit 31: kind_flag, currently used by - * struct, union and fwd + * struct, union, enum, fwd and enum64 */ __u32 info; - /* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC. + /* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64. * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, @@ -63,7 +63,7 @@ enum { BTF_KIND_ARRAY = 3, /* Array */ BTF_KIND_STRUCT = 4, /* Struct */ BTF_KIND_UNION = 5, /* Union */ - BTF_KIND_ENUM = 6, /* Enumeration */ + BTF_KIND_ENUM = 6, /* Enumeration up to 32-bit values */ BTF_KIND_FWD = 7, /* Forward */ |