diff options
Diffstat (limited to 'tools')
371 files changed, 8478 insertions, 2830 deletions
diff --git a/tools/Makefile b/tools/Makefile index e497875fc7e3..37e9f6804832 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -39,7 +39,7 @@ help: @echo ' turbostat - Intel CPU idle stats and freq reporting tool' @echo ' usb - USB testing tools' @echo ' virtio - vhost test module' - @echo ' vm - misc vm tools' + @echo ' mm - misc mm tools' @echo ' wmi - WMI interface examples' @echo ' x86_energy_perf_policy - Intel energy policy tool' @echo '' @@ -69,7 +69,7 @@ acpi: FORCE cpupower: FORCE $(call descend,power/$@) -cgroup counter firewire hv guest bootconfig spi usb virtio vm bpf iio gpio objtool leds wmi pci firmware debugging tracing: FORCE +cgroup counter firewire hv guest bootconfig spi usb virtio mm bpf iio gpio objtool leds wmi pci firmware debugging tracing: FORCE $(call descend,$@) bpf/%: FORCE @@ -118,7 +118,7 @@ kvm_stat: FORCE all: acpi cgroup counter cpupower gpio hv firewire \ perf selftests bootconfig spi turbostat usb \ - virtio vm bpf x86_energy_perf_policy \ + virtio mm bpf x86_energy_perf_policy \ tmon freefall iio objtool kvm_stat wmi \ pci debugging tracing thermal thermometer thermal-engine @@ -128,7 +128,7 @@ acpi_install: cpupower_install: $(call descend,power/$(@:_install=),install) -cgroup_install counter_install firewire_install gpio_install hv_install iio_install perf_install bootconfig_install spi_install usb_install virtio_install vm_install bpf_install objtool_install wmi_install pci_install debugging_install tracing_install: +cgroup_install counter_install firewire_install gpio_install hv_install iio_install perf_install bootconfig_install spi_install usb_install virtio_install mm_install bpf_install objtool_install wmi_install pci_install debugging_install tracing_install: $(call descend,$(@:_install=),install) selftests_install: @@ -158,7 +158,7 @@ kvm_stat_install: install: acpi_install cgroup_install counter_install cpupower_install gpio_install \ hv_install firewire_install iio_install \ perf_install selftests_install turbostat_install usb_install \ - virtio_install vm_install bpf_install x86_energy_perf_policy_install \ + virtio_install mm_install bpf_install x86_energy_perf_policy_install \ tmon_install freefall_install objtool_install kvm_stat_install \ wmi_install pci_install debugging_install intel-speed-select_install \ tracing_install thermometer_install thermal-engine_install @@ -169,7 +169,7 @@ acpi_clean: cpupower_clean: $(call descend,power/cpupower,clean) -cgroup_clean counter_clean hv_clean firewire_clean bootconfig_clean spi_clean usb_clean virtio_clean vm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean pci_clean firmware_clean debugging_clean tracing_clean: +cgroup_clean counter_clean hv_clean firewire_clean bootconfig_clean spi_clean usb_clean virtio_clean mm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean pci_clean firmware_clean debugging_clean tracing_clean: $(call descend,$(@:_clean=),clean) libapi_clean: @@ -211,7 +211,7 @@ build_clean: clean: acpi_clean cgroup_clean counter_clean cpupower_clean hv_clean firewire_clean \ perf_clean selftests_clean turbostat_clean bootconfig_clean spi_clean usb_clean virtio_clean \ - vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ + mm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ freefall_clean build_clean libbpf_clean libsubcmd_clean \ gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean \ intel-speed-select_clean tracing_clean thermal_clean thermometer_clean thermal-engine_clean diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index a7a857f1784d..f8129c624b07 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -109,6 +109,7 @@ struct kvm_regs { #define KVM_ARM_VCPU_SVE 4 /* enable SVE for this CPU */ #define KVM_ARM_VCPU_PTRAUTH_ADDRESS 5 /* VCPU uses address authentication */ #define KVM_ARM_VCPU_PTRAUTH_GENERIC 6 /* VCPU uses generic authentication */ +#define KVM_ARM_VCPU_HAS_EL2 7 /* Support nested virtualization */ struct kvm_vcpu_init { __u32 target; diff --git a/tools/arch/loongarch/include/uapi/asm/bitsperlong.h b/tools/arch/loongarch/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..00b4ba1e5cdf --- /dev/null +++ b/tools/arch/loongarch/include/uapi/asm/bitsperlong.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_LOONGARCH_BITSPERLONG_H +#define __ASM_LOONGARCH_BITSPERLONG_H + +#define __BITS_PER_LONG (__SIZEOF_LONG__ * 8) + +#include <asm-generic/bitsperlong.h> + +#endif /* __ASM_LOONGARCH_BITSPERLONG_H */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index b70111a75688..b89005819cd5 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 20 /* N 32-bit words worth of info */ +#define NCAPINTS 21 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index c44b56f7ffba..5dfa4fb76f4b 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -124,6 +124,7 @@ #define DISABLED_MASK17 0 #define DISABLED_MASK18 0 #define DISABLED_MASK19 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) +#define DISABLED_MASK20 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 37ff47552bcb..ad35355ee43e 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -25,6 +25,7 @@ #define _EFER_SVME 12 /* Enable virtualization */ #define _EFER_LMSLE 13 /* Long Mode Segment Limit Enable */ #define _EFER_FFXSR 14 /* Enable Fast FXSAVE/FXRSTOR */ +#define _EFER_AUTOIBRS 21 /* Enable Automatic IBRS */ #define EFER_SCE (1<<_EFER_SCE) #define EFER_LME (1<<_EFER_LME) @@ -33,6 +34,7 @@ #define EFER_SVME (1<<_EFER_SVME) #define EFER_LMSLE (1<<_EFER_LMSLE) #define EFER_FFXSR (1<<_EFER_FFXSR) +#define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) /* Intel MSRs. Some also available on other CPUs */ @@ -49,6 +51,10 @@ #define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ #define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) +/* A mask for bits which the kernel toggles when controlling mitigations */ +#define SPEC_CTRL_MITIGATIONS_MASK (SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \ + | SPEC_CTRL_RRSBA_DIS_S) + #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ @@ -189,6 +195,9 @@ #define MSR_TURBO_RATIO_LIMIT1 0x000001ae #define MSR_TURBO_RATIO_LIMIT2 0x000001af +#define MSR_SNOOP_RSP_0 0x00001328 +#define MSR_SNOOP_RSP_1 0x00001329 + #define MSR_LBR_SELECT 0x000001c8 #define MSR_LBR_TOS 0x000001c9 @@ -566,6 +575,26 @@ #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) #define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) +/* SNP feature bits enabled by the hypervisor */ +#define MSR_AMD64_SNP_VTOM BIT_ULL(3) +#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4) +#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5) +#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6) +#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7) +#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8) +#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9) +#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10) +#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11) +#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12) +#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14) +#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16) +#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17) + +/* SNP feature bits reserved for future use. */ +#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) +#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) +#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18) + #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f /* AMD Collaborative Processor Performance Control MSRs */ @@ -1061,6 +1090,8 @@ /* - AMD: */ #define MSR_IA32_MBA_BW_BASE 0xc0000200 +#define MSR_IA32_SMBA_BW_BASE 0xc0000280 +#define MSR_IA32_EVT_CFG_BASE 0xc0000400 /* MSR_IA32_VMX_MISC bits */ #define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14) diff --git a/tools/arch/x86/include/asm/orc_types.h b/tools/arch/x86/include/asm/orc_types.h index 5a2baf28a1dc..1343a62106de 100644 --- a/tools/arch/x86/include/asm/orc_types.h +++ b/tools/arch/x86/include/asm/orc_types.h @@ -57,12 +57,14 @@ struct orc_entry { unsigned sp_reg:4; unsigned bp_reg:4; unsigned type:2; + unsigned signal:1; unsigned end:1; #elif defined(__BIG_ENDIAN_BITFIELD) unsigned bp_reg:4; unsigned sp_reg:4; - unsigned unused:5; + unsigned unused:4; unsigned end:1; + unsigned signal:1; unsigned type:2; #endif } __packed; diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h index aff774775c67..7ba1726b71c7 100644 --- a/tools/arch/x86/include/asm/required-features.h +++ b/tools/arch/x86/include/asm/required-features.h @@ -98,6 +98,7 @@ #define REQUIRED_MASK17 0 #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) +#define REQUIRED_MASK20 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index e48deab8901d..7f467fe05d42 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -9,6 +9,7 @@ #include <linux/types.h> #include <linux/ioctl.h> +#include <linux/stddef.h> #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 @@ -507,8 +508,8 @@ struct kvm_nested_state { * KVM_{GET,PUT}_NESTED_STATE ioctl values. */ union { - struct kvm_vmx_nested_state_data vmx[0]; - struct kvm_svm_nested_state_data svm[0]; + __DECLARE_FLEX_ARRAY(struct kvm_vmx_nested_state_data, vmx); + __DECLARE_FLEX_ARRAY(struct kvm_svm_nested_state_data, svm); } data; }; @@ -525,6 +526,35 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 +#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0) +#define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS) + +/* + * Masked event layout. + * Bits Description + * ---- ----------- + * 7:0 event select (low bits) + * 15:8 umask match + * 31:16 unused + * 35:32 event select (high bits) + * 36:54 unused + * 55 exclude bit + * 63:56 umask mask + */ + +#define KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, exclude) \ + (((event_select) & 0xFFULL) | (((event_select) & 0XF00ULL) << 24) | \ + (((mask) & 0xFFULL) << 56) | \ + (((match) & 0xFFULL) << 8) | \ + ((__u64)(!!(exclude)) << 55)) + +#define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \ + (GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (GENMASK_ULL(63, 56)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (GENMASK_ULL(15, 8)) +#define KVM_PMU_MASKED_ENTRY_EXCLUDE (BIT_ULL(55)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT (56) + /* for KVM_{GET,SET,HAS}_DEVICE_ATTR */ #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h index f69c168391aa..80e1df482337 100644 --- a/tools/arch/x86/include/uapi/asm/svm.h +++ b/tools/arch/x86/include/uapi/asm/svm.h @@ -116,6 +116,12 @@ #define SVM_VMGEXIT_AP_CREATE 1 #define SVM_VMGEXIT_AP_DESTROY 2 #define SVM_VMGEXIT_HV_FEATURES 0x8000fffd +#define SVM_VMGEXIT_TERM_REQUEST 0x8000fffe +#define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code) \ + /* SW_EXITINFO1[3:0] */ \ + (((((u64)reason_set) & 0xf)) | \ + /* SW_EXITINFO1[11:4] */ \ + ((((u64)reason_code) & 0xff) << 4)) #define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff /* Exit code reserved for hypervisor/software use */ diff --git a/tools/arch/x86/kcpuid/cpuid.csv b/tools/arch/x86/kcpuid/cpuid.csv index 4f1c4b0c29e9..e0c25b75327e 100644 --- a/tools/arch/x86/kcpuid/cpuid.csv +++ b/tools/arch/x86/kcpuid/cpuid.csv @@ -184,8 +184,8 @@ 7, 0, EBX, 27, avx512er, AVX512 Exponent Reciproca instr 7, 0, EBX, 28, avx512cd, AVX512 Conflict Detection instr 7, 0, EBX, 29, sha, Intel Secure Hash Algorithm Extensions instr - 7, 0, EBX, 26, avx512bw, AVX512 Byte & Word instr - 7, 0, EBX, 28, avx512vl, AVX512 Vector Length Extentions (VL) + 7, 0, EBX, 30, avx512bw, AVX512 Byte & Word instr + 7, 0, EBX, 31, avx512vl, AVX512 Vector Length Extentions (VL) 7, 0, ECX, 0, prefetchwt1, X 7, 0, ECX, 1, avx512vbmi, AVX512 Vector Byte Manipulation Instructions 7, 0, ECX, 2, umip, User-mode Instruction Prevention @@ -340,19 +340,70 @@ # According to SDM # 40000000H - 4FFFFFFFH is invalid range - # Leaf 80000001H # Extended Processor Signature and Feature Bits +0x80000001, 0, EAX, 27:20, extfamily, Extended family +0x80000001, 0, EAX, 19:16, extmodel, Extended model +0x80000001, 0, EAX, 11:8, basefamily, Description of Family +0x80000001, 0, EAX, 11:8, basemodel, Model numbers vary with product +0x80000001, 0, EAX, 3:0, stepping, Processor stepping (revision) for a specific model + +0x80000001, 0, EBX, 31:28, pkgtype, Specifies the package type + 0x80000001, 0, ECX, 0, lahf_lm, LAHF/SAHF available in 64-bit mode +0x80000001, 0, ECX, 1, cmplegacy, Core multi-processing legacy mode +0x80000001, 0, ECX, 2, svm, Indicates support for: VMRUN, VMLOAD, VMSAVE, CLGI, VMMCALL, and INVLPGA +0x80000001, 0, ECX, 3, extapicspace, Extended APIC register space +0x80000001, 0, ECX, 4, altmovecr8, Indicates support for LOCK MOV CR0 means MOV CR8 0x80000001, 0, ECX, 5, lzcnt, LZCNT +0x80000001, 0, ECX, 6, sse4a, EXTRQ, INSERTQ, MOVNTSS, and MOVNTSD instruction support +0x80000001, 0, ECX, 7, misalignsse, Misaligned SSE Mode 0x80000001, 0, ECX, 8, prefetchw, PREFETCHW - +0x80000001, 0, ECX, 9, osvw, OS Visible Work-around support +0x80000001, 0, ECX, 10, ibs, Instruction Based Sampling +0x80000001, 0, ECX, 11, xop, Extended operation support +0x80000001, 0, ECX, 12, skinit, SKINIT and STGI support +0x80000001, 0, ECX, 13, wdt, Watchdog timer support +0x80000001, 0, ECX, 15, lwp, Lightweight profiling support +0x80000001, 0, ECX, 16, fma4, Four-operand FMA instruction support +0x80000001, 0, ECX, 17, tce, Translation cache extension +0x80000001, 0, ECX, 22, TopologyExtensions, Indicates support for Core::X86::Cpuid::CachePropEax0 and Core::X86::Cpuid::ExtApicId +0x80000001, 0, ECX, 23, perfctrextcore, Indicates support for Core::X86::Msr::PERF_CTL0 - 5 and Core::X86::Msr::PERF_CTR +0x80000001, 0, ECX, 24, perfctrextdf, Indicates support for Core::X86::Msr::DF_PERF_CTL and Core::X86::Msr::DF_PERF_CTR +0x80000001, 0, ECX, 26, databreakpointextension, Indicates data breakpoint support for Core::X86::Msr::DR0_ADDR_MASK, Core::X86::Msr::DR1_ADDR_MASK, Core::X86::Msr::DR2_ADDR_MASK and Core::X86::Msr::DR3_ADDR_MASK +0x80000001, 0, ECX, 27, perftsc, Performance time-stamp counter supported +0x80000001, 0, ECX, 28, perfctrextllc, Indicates support for L3 performance counter extensions +0x80000001, 0, ECX, 29, mwaitextended, MWAITX and MONITORX capability is supported +0x80000001, 0, ECX, 30, admskextn, Indicates support for address mask extension (to 32 bits and to all 4 DRs) for instruction breakpoints + +0x80000001, 0, EDX, 0, fpu, x87 floating point unit on-chip +0x80000001, 0, EDX, 1, vme, Virtual-mode enhancements +0x80000001, 0, EDX, 2, de, Debugging extensions, IO breakpoints, CR4.DE +0x80000001, 0, EDX, 3, pse, Page-size extensions (4 MB pages) +0x80000001, 0, EDX, 4, tsc, Time stamp counter, RDTSC/RDTSCP instructions, CR4.TSD +0x80000001, 0, EDX, 5, msr, Model-specific registers (MSRs), with RDMSR and WRMSR instructions +0x80000001, 0, EDX, 6, pae, Physical-address extensions (PAE) +0x80000001, 0, EDX, 7, mce, Machine Check Exception, CR4.MCE +0x80000001, 0, EDX, 8, cmpxchg8b, CMPXCHG8B instruction +0x80000001, 0, EDX, 9, apic, advanced programmable interrupt controller (APIC) exists and is enabled 0x80000001, 0, EDX, 11, sysret, SYSCALL/SYSRET supported +0x80000001, 0, EDX, 12, mtrr, Memory-type range registers +0x80000001, 0, EDX, 13, pge, Page global extension, CR4.PGE +0x80000001, 0, EDX, 14, mca, Machine check architecture, MCG_CAP +0x80000001, 0, EDX, 15, cmov, Conditional move instructions, CMOV, FCOMI, FCMOV +0x80000001, 0, EDX, 16, pat, Page attribute table +0x80000001, 0, EDX, 17, pse36, Page-size extensions 0x80000001, 0, EDX, 20, exec_dis, Execute Disable Bit available +0x80000001, 0, EDX, 22, mmxext, AMD extensions to MMX instructions +0x80000001, 0, EDX, 23, mmx, MMX instructions +0x80000001, 0, EDX, 24, fxsr, FXSAVE and FXRSTOR instructions +0x80000001, 0, EDX, 25, ffxsr, FXSAVE and FXRSTOR instruction optimizations 0x80000001, 0, EDX, 26, 1gb_page, 1GB page supported 0x80000001, 0, EDX, 27, rdtscp, RDTSCP and IA32_TSC_AUX are available -#0x80000001, 0, EDX, 29, 64b, 64b Architecture supported +0x80000001, 0, EDX, 29, lm, 64b Architecture supported +0x80000001, 0, EDX, 30, threednowext, AMD extensions to 3DNow! instructions +0x80000001, 0, EDX, 31, threednow, 3DNow! instructions # Leaf 80000002H/80000003H/80000004H # Processor Brand String diff --git a/tools/arch/x86/kcpuid/kcpuid.c b/tools/arch/x86/kcpuid/kcpuid.c index dae75511fef7..416f5b35dd8f 100644 --- a/tools/arch/x86/kcpuid/kcpuid.c +++ b/tools/arch/x86/kcpuid/kcpuid.c @@ -33,7 +33,7 @@ struct reg_desc { struct bits_desc descs[32]; }; -enum { +enum cpuid_reg { R_EAX = 0, R_EBX, R_ECX, @@ -41,6 +41,10 @@ enum { NR_REGS }; +static const char * const reg_names[] = { + "EAX", "EBX", "ECX", "EDX", +}; + struct subleaf { u32 index; u32 sub; @@ -428,12 +432,18 @@ static void parse_text(void) /* Decode every eax/ebx/ecx/edx */ -static void decode_bits(u32 value, struct reg_desc *rdesc) +static void decode_bits(u32 value, struct reg_desc *rdesc, enum cpuid_reg reg) { struct bits_desc *bdesc; int start, end, i; u32 mask; + if (!rdesc->nr) { + if (show_details) + printf("\t %s: 0x%08x\n", reg_names[reg], value); + return; + } + for (i = 0; i < rdesc->nr; i++) { bdesc = &rdesc->descs[i]; @@ -468,13 +478,21 @@ static void show_leaf(struct subleaf *leaf) if (!leaf) return; - if (show_raw) + if (show_raw) { leaf_print_raw(leaf); + } else { + if (show_details) + printf("CPUID_0x%x_ECX[0x%x]:\n", + leaf->index, leaf->sub); + } + + decode_bits(leaf->eax, &leaf->info[R_EAX], R_EAX); + decode_bits(leaf->ebx, &leaf->info[R_EBX], R_EBX); + decode_bits(leaf->ecx, &leaf->info[R_ECX], R_ECX); + decode_bits(leaf->edx, &leaf->info[R_EDX], R_EDX); - decode_bits(leaf->eax, &leaf->info[R_EAX]); - decode_bits(leaf->ebx, &leaf->info[R_EBX]); - decode_bits(leaf->ecx, &leaf->info[R_ECX]); - decode_bits(leaf->edx, &leaf->info[R_EDX]); + if (!show_raw && show_details) + printf("\n"); } static void show_func(struct cpuid_func *func) diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 5418e2f99834..a91ac666f758 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -7,7 +7,7 @@ #include <asm/alternative.h> #include <asm/export.h> -.pushsection .noinstr.text, "ax" +.section .noinstr.text, "ax" /* * We build a jump to memcpy_orig by default which gets NOPped out on @@ -42,7 +42,7 @@ SYM_TYPED_FUNC_START(__memcpy) SYM_FUNC_END(__memcpy) EXPORT_SYMBOL(__memcpy) -SYM_FUNC_ALIAS_WEAK(memcpy, __memcpy) +SYM_FUNC_ALIAS(memcpy, __memcpy) EXPORT_SYMBOL(memcpy) /* @@ -183,4 +183,3 @@ SYM_FUNC_START_LOCAL(memcpy_orig) RET SYM_FUNC_END(memcpy_orig) -.popsection diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index fc9ffd3ff3b2..6143b1a6fa2c 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -6,6 +6,8 @@ #include <asm/alternative.h> #include <asm/export.h> +.section .noinstr.text, "ax" + /* * ISO C memset - set a memory block to a byte value. This function uses fast * string to get better performance than the original function. The code is @@ -43,7 +45,7 @@ SYM_FUNC_START(__memset) SYM_FUNC_END(__memset) EXPORT_SYMBOL(__memset) -SYM_FUNC_ALIAS_WEAK(memset, __memset) +SYM_FUNC_ALIAS(memset, __memset) EXPORT_SYMBOL(memset) /* diff --git a/tools/bootconfig/scripts/ftrace2bconf.sh b/tools/bootconfig/scripts/ftrace2bconf.sh index 6183b36c6846..1603801cf126 100755 --- a/tools/bootconfig/scripts/ftrace2bconf.sh +++ b/tools/bootconfig/scripts/ftrace2bconf.sh @@ -93,7 +93,7 @@ referred_vars() { } event_is_enabled() { # enable-file - test -f $1 & grep -q "1" $1 + test -f $1 && grep -q "1" $1 } per_event_options() { # event-dir diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh index f68e2e9eef8b..a2c484c243f5 100755 --- a/tools/bootconfig/test-bootconfig.sh +++ b/tools/bootconfig/test-bootconfig.sh @@ -87,10 +87,14 @@ xfail grep -i "error" $OUTFILE echo "Max node number check" -echo -n > $TEMPCONF -for i in `seq 1 1024` ; do - echo "node$i" >> $TEMPCONF -done +awk ' +BEGIN { + for (i = 0; i < 26; i += 1) + printf("%c\n", 65 + i % 26) + for (i = 26; i < 8192; i += 1) + printf("%c%c%c\n", 65 + i % 26, 65 + (i / 26) % 26, 65 + (i / 26 / 26)) +} +' > $TEMPCONF xpass $BOOTCONF -a $TEMPCONF $INITRD echo "badnode" >> $TEMPCONF diff --git a/tools/cgroup/memcg_shrinker.py b/tools/cgroup/memcg_shrinker.py index 706ab27666a4..e81c3017ada9 100644 --- a/tools/cgroup/memcg_shrinker.py +++ b/tools/cgroup/memcg_shrinker.py @@ -5,7 +5,6 @@ import os import argparse -import sys def scan_cgroups(cgroup_root): @@ -44,7 +43,7 @@ def main(): cgroups = scan_cgroups("/sys/fs/cgroup/") shrinkers = scan_shrinkers("/sys/kernel/debug/shrinker/") - shrinkers = sorted(shrinkers, reverse = True, key = lambda x: x[0]) + shrinkers.sort(reverse = True, key = lambda x: x[0]) n = 0 for s in shrinkers: diff --git a/tools/iio/iio_utils.c b/tools/iio/iio_utils.c index 8d35893b2fa8..6a00a6eecaef 100644 --- a/tools/iio/iio_utils.c +++ b/tools/iio/iio_utils.c @@ -264,6 +264,7 @@ int iioutils_get_param_float(float *output, const char *param_name, if (fscanf(sysfsfp, "%f", output) != 1) ret = errno ? -errno : -ENODATA; + fclose(sysfsfp); break; } error_free_filename: @@ -345,9 +346,9 @@ int build_channel_array(const char *device_dir, int buffer_idx, } sysfsfp = fopen(filename, "r"); + free(filename); if (!sysfsfp) { ret = -errno; - free(filename); goto error_close_dir; } @@ -357,7 +358,6 @@ int build_channel_array(const char *device_dir, int buffer_idx, if (fclose(sysfsfp)) perror("build_channel_array(): Failed to close file"); - free(filename); goto error_close_dir; } if (ret == 1) @@ -365,11 +365,9 @@ int build_channel_array(const char *device_dir, int buffer_idx, if (fclose(sysfsfp)) { ret = -errno; - free(filename); goto error_close_dir; } - free(filename); } *ci_array = malloc(sizeof(**ci_array) * (*counter)); @@ -395,9 +393,9 @@ int build_channel_array(const char *device_dir, int buffer_idx, } sysfsfp = fopen(filename, "r"); + free(filename); if (!sysfsfp) { ret = -errno; - free(filename); count--; goto error_cleanup_array; } @@ -405,20 +403,17 @@ int build_channel_array(const char *device_dir, int buffer_idx, errno = 0; if (fscanf(sysfsfp, "%i", ¤t_enabled) != 1) { ret = errno ? -errno : -ENODATA; - free(filename); count--; goto error_cleanup_array; } if (fclose(sysfsfp)) { ret = -errno; - free(filename); count--; goto error_cleanup_array; } if (!current_enabled) { - free(filename); count--; continue; } @@ -429,7 +424,6 @@ int build_channel_array(const char *device_dir, int buffer_idx, strlen(ent->d_name) - strlen("_en")); if (!current->name) { - free(filename); ret = -ENOMEM; count--; goto error_cleanup_array; @@ -439,7 +433,6 @@ int build_channel_array(const char *device_dir, int buffer_idx, ret = iioutils_break_up_name(current->name, ¤t->generic_name); if (ret) { - free(filename); free(current->name); count--; goto error_cleanup_array; @@ -450,17 +443,16 @@ int build_channel_array(const char *device_dir, int buffer_idx, scan_el_dir, current->name); if (ret < 0) { - free(filename); ret = -ENOMEM; goto error_cleanup_array; } sysfsfp = fopen(filename, "r"); + free(filename); if (!sysfsfp) { ret = -errno; - fprintf(stderr, "failed to open %s\n", - filename); - free(filename); + fprintf(stderr, "failed to open %s/%s_index\n", + scan_el_dir, current->name); goto error_cleanup_array; } @@ -470,17 +462,14 @@ int build_channel_array(const char *device_dir, int buffer_idx, if (fclose(sysfsfp)) perror("build_channel_array(): Failed to close file"); - free(filename); goto error_cleanup_array; } if (fclose(sysfsfp)) { ret = -errno; - free(filename); goto error_cleanup_array; } - free(filename); /* Find the scale */ ret = iioutils_get_param_float(¤t->scale, "scale", diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h index 87d112650dfb..7c0cf5031abe 100644 --- a/tools/include/linux/bits.h +++ b/tools/include/linux/bits.h @@ -6,7 +6,6 @@ #include <vdso/bits.h> #include <asm/bitsperlong.h> -#define BIT_ULL(nr) (ULL(1) << (nr)) #define BIT_MASK(nr) (UL(1) << ((nr) % BITS_PER_LONG)) #define BIT_WORD(nr) ((nr) / BITS_PER_LONG) #define BIT_ULL_MASK(nr) (ULL(1) << ((nr) % BITS_PER_LONG_LONG)) diff --git a/tools/include/linux/err.h b/tools/include/linux/err.h index 25f2bb3a991d..332b983ead1e 100644 --- a/tools/include/linux/err.h +++ b/tools/include/linux/err.h @@ -20,7 +20,7 @@ * Userspace note: * The same principle works for userspace, because 'error' pointers * fall down to the unused hole far from user space, as described - * in Documentation/x86/x86_64/mm.rst for x86_64 arch: + * in Documentation/arch/x86/x86_64/mm.rst for x86_64 arch: * * 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm hole caused by [48:63] sign extension * ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h index 62c54ffbeeaa..9ac3df3fccf0 100644 --- a/tools/include/linux/objtool.h +++ b/tools/include/linux/objtool.h @@ -15,6 +15,7 @@ struct unwind_hint { s16 sp_offset; u8 sp_reg; u8 type; + u8 signal; u8 end; }; #endif @@ -49,7 +50,7 @@ struct unwind_hint { #ifndef __ASSEMBLY__ -#define UNWIND_HINT(sp_reg, sp_offset, type, end) \ +#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ "987: \n\t" \ ".pushsection .discard.unwind_hints\n\t" \ /* struct unwind_hint */ \ @@ -57,6 +58,7 @@ struct unwind_hint { ".short " __stringify(sp_offset) "\n\t" \ ".byte " __stringify(sp_reg) "\n\t" \ ".byte " __stringify(type) "\n\t" \ + ".byte " __stringify(signal) "\n\t" \ ".byte " __stringify(end) "\n\t" \ ".balign 4 \n\t" \ ".popsection\n\t" @@ -129,7 +131,7 @@ struct unwind_hint { * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 .Lunwind_hint_ip_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ @@ -137,6 +139,7 @@ struct unwind_hint { .short \sp_offset .byte \sp_reg .byte \type + .byte \signal .byte \end .balign 4 .popsection @@ -174,7 +177,7 @@ struct unwind_hint { #ifndef __ASSEMBLY__ -#define UNWIND_HINT(sp_reg, sp_offset, type, end) \ +#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) @@ -182,7 +185,7 @@ struct unwind_hint { #define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm diff --git a/tools/include/nolibc/.gitignore b/tools/include/nolibc/.gitignore new file mode 100644 index 000000000000..dea22eaaed2b --- /dev/null +++ b/tools/include/nolibc/.gitignore @@ -0,0 +1 @@ +sysroot diff --git a/tools/include/nolibc/Makefile b/tools/include/nolibc/Makefile index cfd06764b5ae..9839feafd38a 100644 --- a/tools/include/nolibc/Makefile +++ b/tools/include/nolibc/Makefile @@ -25,8 +25,8 @@ 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 +all_files := ctype.h errno.h nolibc.h signal.h stackprotector.h std.h stdint.h \ + stdio.h stdlib.h string.h sys.h time.h types.h unistd.h # install all headers needed to support a bare-metal compiler all: headers diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h index e8d0cf545bf1..2d98d78fd3f3 100644 --- a/tools/include/nolibc/arch-i386.h +++ b/tools/include/nolibc/arch-i386.h @@ -181,6 +181,8 @@ struct sys_stat_struct { char **environ __attribute__((weak)); const unsigned long *_auxv __attribute__((weak)); +#define __ARCH_SUPPORTS_STACK_PROTECTOR + /* startup code */ /* * i386 System V ABI mandates: @@ -188,9 +190,12 @@ const unsigned long *_auxv __attribute__((weak)); * 2) The deepest stack frame should be set to zero * */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"),no_stack_protector)) _start(void) { __asm__ volatile ( +#ifdef NOLIBC_STACKPROTECTOR + "call __stack_chk_init\n" // initialize stack protector +#endif "pop %eax\n" // argc (first arg, %eax) "mov %esp, %ebx\n" // argv[] (second arg, %ebx) "lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx) diff --git a/tools/include/nolibc/arch-loongarch.h b/tools/include/nolibc/arch-loongarch.h new file mode 100644 index 000000000000..029ee3cd6baf --- /dev/null +++ b/tools/include/nolibc/arch-loongarch.h @@ -0,0 +1,200 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * LoongArch specific definitions for NOLIBC + * Copyright (C) 2023 Loongson Technology Corporation Limited + */ + +#ifndef _NOLIBC_ARCH_LOONGARCH_H +#define _NOLIBC_ARCH_LOONGARCH_H + +/* Syscalls for LoongArch : + * - stack is 16-byte aligned + * - syscall number is passed in a7 + * - arguments are in a0, a1, a2, a3, a4, a5 + * - the system call is performed by calling "syscall 0" + * - syscall return comes in a0 + * - the arguments are cast to long and assigned into the target + * registers which are then simply passed as registers to the asm code, + * so that we don't have to experience issues with register constraints. + * + * On LoongArch, select() is not implemented so we have to use pselect6(). + */ +#define __ARCH_WANT_SYS_PSELECT6 + +#define my_syscall0(num) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0"); \ + \ + __asm__ volatile ( \ + "syscall 0\n" \ + : "=r"(_arg1) \ + : "r"(_num) \ + : "memory", "$t0", "$t1", "$t2", "$t3", \ + "$t4", "$t5", "$t6", "$t7", "$t8" \ + ); \ + _arg1; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + \ + __asm__ volatile ( \ + "syscall 0\n" \ + : "+r"(_arg1) \ + : "r"(_num) \ + : "memory", "$t0", "$t1", "$t2", "$t3", \ + "$t4", "$t5", "$t6", "$t7", "$t8" \ + ); \ + _arg1; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + \ + __asm__ volatile ( \ + "syscall 0\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), \ + "r"(_num) \ + : "memory", "$t0", "$t1", "$t2", "$t3", \ + "$t4", "$t5", "$t6", "$t7", "$t8" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "syscall 0\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), \ + "r"(_num) \ + : "memory", "$t0", "$t1", "$t2", "$t3", \ + "$t4", "$t5", "$t6", "$t7", "$t8" \ + ); \ + _arg1; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "syscall 0\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "r"(_num) \ + : "memory", "$t0", "$t1", "$t2", "$t3", \ + "$t4", "$t5", "$t6", "$t7", "$t8" \ + ); \ + _arg1; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3") = (long)(arg4); \ + register long _arg5 __asm__ ("a4") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "syscall 0\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_num) \ + : "memory", "$t0", "$t1", "$t2", "$t3", \ + "$t4", "$t5", "$t6", "$t7", "$t8" \ + ); \ + _arg1; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3") = (long)(arg4); \ + register long _arg5 __asm__ ("a4") = (long)(arg5); \ + register long _arg6 __asm__ ("a5") = (long)(arg6); \ + \ + __asm__ volatile ( \ + "syscall 0\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_arg6), \ + "r"(_num) \ + : "memory", "$t0", "$t1", "$t2", "$t3", \ + "$t4", "$t5", "$t6", "$t7", "$t8" \ + ); \ + _arg1; \ +}) + +char **environ __attribute__((weak)); +const unsigned long *_auxv __attribute__((weak)); + +#if __loongarch_grlen == 32 +#define LONGLOG "2" +#define SZREG "4" +#define REG_L "ld.w" +#define LONG_S "st.w" +#define LONG_ADD "add.w" +#define LONG_ADDI "addi.w" +#define LONG_SLL "slli.w" +#define LONG_BSTRINS "bstrins.w" +#else // __loongarch_grlen == 64 +#define LONGLOG "3" +#define SZREG "8" +#define REG_L "ld.d" +#define LONG_S "st.d" +#define LONG_ADD "add.d" +#define LONG_ADDI "addi.d" +#define LONG_SLL "slli.d" +#define LONG_BSTRINS "bstrins.d" +#endif + +/* startup code */ +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +{ + __asm__ volatile ( + REG_L " $a0, $sp, 0\n" // argc (a0) was in the stack + LONG_ADDI " $a1, $sp, "SZREG"\n" // argv (a1) = sp + SZREG + LONG_SLL " $a2, $a0, "LONGLOG"\n" // envp (a2) = SZREG*argc ... + LONG_ADDI " $a2, $a2, "SZREG"\n" // + SZREG (skip null) + LONG_ADD " $a2, $a2, $a1\n" // + argv + + "move $a3, $a2\n" // iterate a3 over envp to find auxv (after NULL) + "0:\n" // do { + REG_L " $a4, $a3, 0\n" // a4 = *a3; + LONG_ADDI " $a3, $a3, "SZREG"\n" // a3 += sizeof(void*); + "bne $a4, $zero, 0b\n" // } while (a4); + "la.pcrel $a4, _auxv\n" // a4 = &_auxv + LONG_S " $a3, $a4, 0\n" // store a3 into _auxv + + "la.pcrel $a3, environ\n" // a3 = &environ + LONG_S " $a2, $a3, 0\n" // store envp(a2) into environ + LONG_BSTRINS " $sp, $zero, 3, 0\n" // sp must be 16-byte aligned + "bl main\n" // main() returns the status code, we'll exit with it. + "li.w $a7, 93\n" // NR_exit == 93 + "syscall 0\n" + ); + __builtin_unreachable(); +} + +#endif // _NOLIBC_ARCH_LOONGARCH_H diff --git a/tools/include/nolibc/arch-x86_64.h b/tools/include/nolibc/arch-x86_64.h index 17f6751208e7..f7f2a11d4c3b 100644 --- a/tools/include/nolibc/arch-x86_64.h +++ b/tools/include/nolibc/arch-x86_64.h @@ -181,6 +181,8 @@ struct sys_stat_struct { char **environ __attribute__((weak)); const unsigned long *_auxv __attribute__((weak)); +#define __ARCH_SUPPORTS_STACK_PROTECTOR + /* startup code */ /* * x86-64 System V ABI mandates: @@ -191,6 +193,9 @@ const unsigned long *_auxv __attribute__((weak)); void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) { __asm__ volatile ( +#ifdef NOLIBC_STACKPROTECTOR + "call __stack_chk_init\n" // initialize stack protector +#endif "pop %rdi\n" // argc (first arg, %rdi) "mov %rsp, %rsi\n" // argv[] (second arg, %rsi) "lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx) diff --git a/tools/include/nolibc/arch.h b/tools/include/nolibc/arch.h index 78b067a4fa47..2d5386a8d6aa 100644 --- a/tools/include/nolibc/arch.h +++ b/tools/include/nolibc/arch.h @@ -29,6 +29,8 @@ #include "arch-riscv.h" #elif defined(__s390x__) #include "arch-s390.h" +#elif defined(__loongarch__) +#include "arch-loongarch.h" #endif #endif /* _NOLIBC_ARCH_H */ diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h index b2bc48d3cfe4..04739a6293c4 100644 --- a/tools/include/nolibc/nolibc.h +++ b/tools/include/nolibc/nolibc.h @@ -104,6 +104,7 @@ #include "string.h" #include "time.h" #include "unistd.h" +#include "stackprotector.h" /* Used by programs to avoid std includes */ #define NOLIBC diff --git a/tools/include/nolibc/stackprotector.h b/tools/include/nolibc/stackprotector.h new file mode 100644 index 000000000000..d119cbbbc256 --- /dev/null +++ b/tools/include/nolibc/stackprotector.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Stack protector support for NOLIBC + * Copyright (C) 2023 Thomas Weißschuh <linux@weissschuh.net> + */ + +#ifndef _NOLIBC_STACKPROTECTOR_H +#define _NOLIBC_STACKPROTECTOR_H + +#include "arch.h" + +#if defined(NOLIBC_STACKPROTECTOR) + +#if !defined(__ARCH_SUPPORTS_STACK_PROTECTOR) +#error "nolibc does not support stack protectors on this arch" +#endif + +#include "sys.h" +#include "stdlib.h" + +/* The functions in this header are using raw syscall macros to avoid + * triggering stack protector errors themselves + */ + +__attribute__((weak,noreturn,section(".text.nolibc_stack_chk"))) +void __stack_chk_fail(void) +{ + pid_t pid; + my_syscall3(__NR_write, STDERR_FILENO, "!!Stack smashing detected!!\n", 28); + pid = my_syscall0(__NR_getpid); + my_syscall2(__NR_kill, pid, SIGABRT); + for (;;); +} + +__attribute__((weak,noreturn,section(".text.nolibc_stack_chk"))) +void __stack_chk_fail_local(void) +{ + __stack_chk_fail(); +} + +__attribute__((weak,section(".data.nolibc_stack_chk"))) +uintptr_t __stack_chk_guard; + +__attribute__((weak,no_stack_protector,section(".text.nolibc_stack_chk"))) +void __stack_chk_init(void) +{ + my_syscall3(__NR_getrandom, &__stack_chk_guard, sizeof(__stack_chk_guard), 0); + /* a bit more randomness in case getrandom() fails */ + __stack_chk_guard ^= (uintptr_t) &__stack_chk_guard; +} +#endif // defined(NOLIBC_STACKPROTECTOR) + +#endif // _NOLIBC_STACKPROTECTOR_H diff --git a/tools/include/nolibc/std.h b/tools/include/nolibc/std.h index 1747ae125392..933bc0be7e1c 100644 --- a/tools/include/nolibc/std.h +++ b/tools/include/nolibc/std.h @@ -18,20 +18,7 @@ #define NULL ((void *)0) #endif -/* stdint types */ -typedef unsigned char uint8_t; -typedef signed char int8_t; -typedef unsigned short uint16_t; -typedef signed short int16_t; -typedef unsigned int uint32_t; -typedef signed int int32_t; -typedef unsigned long long uint64_t; -typedef signed long long int64_t; -typedef unsigned long size_t; -typedef signed long ssize_t; -typedef unsigned long uintptr_t; -typedef signed long intptr_t; -typedef signed long ptrdiff_t; +#include "stdint.h" /* those are commonly provided by sys/types.h */ typedef unsigned int dev_t; diff --git a/tools/include/nolibc/stdint.h b/tools/include/nolibc/stdint.h new file mode 100644 index 000000000000..c1ce4f5e0603 --- /dev/null +++ b/tools/include/nolibc/stdint.h @@ -0,0 +1,99 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Standard definitions and types for NOLIBC + * Copyright (C) 2023 Vincent Dagonneau <v@vda.io> + */ + +#ifndef _NOLIBC_STDINT_H +#define _NOLIBC_STDINT_H + +typedef unsigned char uint8_t; +typedef signed char int8_t; +typedef unsigned short uint16_t; +typedef signed short int16_t; +typedef unsigned int uint32_t; +typedef signed int int32_t; +typedef unsigned long long uint64_t; +typedef signed long long int64_t; +typedef unsigned long size_t; +typedef signed long ssize_t; +typedef unsigned long uintptr_t; +typedef signed long intptr_t; +typedef signed long ptrdiff_t; + +typedef int8_t int_least8_t; +typedef uint8_t uint_least8_t; +typedef int16_t int_least16_t; +typedef uint16_t uint_least16_t; +typedef int32_t int_least32_t; +typedef uint32_t uint_least32_t; +typedef int64_t int_least64_t; +typedef uint64_t uint_least64_t; + +typedef int8_t int_fast8_t; +typedef uint8_t uint_fast8_t; +typedef ssize_t int_fast16_t; +typedef size_t uint_fast16_t; +typedef ssize_t int_fast32_t; +typedef size_t uint_fast32_t; +typedef ssize_t int_fast64_t; +typedef size_t uint_fast64_t; + +typedef int64_t intmax_t; +typedef uint64_t uintmax_t; + +/* limits of integral types */ + +#define INT8_MIN (-128) +#define INT16_MIN (-32767-1) +#define INT32_MIN (-2147483647-1) +#define INT64_MIN (-9223372036854775807LL-1) + +#define INT8_MAX (127) +#define INT16_MAX (32767) +#define INT32_MAX (2147483647) +#define INT64_MAX (9223372036854775807LL) + +#define UINT8_MAX (255) +#define UINT16_MAX (65535) +#define UINT32_MAX (4294967295U) +#define UINT64_MAX (18446744073709551615ULL) + +#define INT_LEAST8_MIN INT8_MIN +#define INT_LEAST16_MIN INT16_MIN +#define INT_LEAST32_MIN INT32_MIN +#define INT_LEAST64_MIN INT64_MIN + +#define INT_LEAST8_MAX INT8_MAX +#define INT_LEAST16_MAX INT16_MAX +#define INT_LEAST32_MAX INT32_MAX +#define INT_LEAST64_MAX INT64_MAX + +#define UINT_LEAST8_MAX UINT8_MAX +#define UINT_LEAST16_MAX UINT16_MAX +#define UINT_LEAST32_MAX UINT32_MAX +#define UINT_LEAST64_MAX UINT64_MAX + +#define SIZE_MAX ((size_t)(__LONG_MAX__) * 2 + 1) +#define INTPTR_MIN (-__LONG_MAX__ - 1) +#define INTPTR_MAX __LONG_MAX__ +#define PTRDIFF_MIN INTPTR_MIN +#define PTRDIFF_MAX INTPTR_MAX +#define UINTPTR_MAX SIZE_MAX + +#define INT_FAST8_MIN INT8_MIN +#define INT_FAST16_MIN INTPTR_MIN +#define INT_FAST32_MIN INTPTR_MIN +#define INT_FAST64_MIN INTPTR_MIN + +#define INT_FAST8_MAX INT8_MAX +#define INT_FAST16_MAX INTPTR_MAX +#define INT_FAST32_MAX INTPTR_MAX +#define INT_FAST64_MAX INTPTR_MAX + +#define UINT_FAST8_MAX UINT8_MAX +#define UINT_FAST16_MAX SIZE_MAX +#define UINT_FAST32_MAX SIZE_MAX +#define UINT_FAST64_MAX SIZE_MAX + +#endif /* _NOLIBC_STDINT_H */ diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h index 96ac8afc5aee..6cbbb52836a0 100644 --- a/tools/include/nolibc/stdio.h +++ b/tools/include/nolibc/stdio.h @@ -273,6 +273,12 @@ int vfprintf(FILE *stream, const char *fmt, va_list args) return written; } +static __attribute__((unused)) +int vprintf(const char *fmt, va_list args) +{ + return vfprintf(stdout, fmt, args); +} + static __attribute__((unused, format(printf, 2, 3))) int fprintf(FILE *stream, const char *fmt, ...) { diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index b5f8cd35c03b..5d624dc63a42 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -11,7 +11,6 @@ #include "std.h" /* system includes */ -#include <asm/fcntl.h> // for O_* #include <asm/unistd.h> #include <asm/signal.h> // for SIGCHLD #include <asm/ioctls.h> @@ -20,6 +19,8 @@ #include <linux/loop.h> #include <linux/time.h> #include <linux/auxvec.h> +#include <linux/fcntl.h> // for O_* and AT_* +#include <linux/stat.h> // for statx() #include "arch.h" #include "errno.h" @@ -411,6 +412,27 @@ int getdents64(int fd, struct linux_dirent64 *dirp, int count) /* + * uid_t geteuid(void); + */ + +static __attribute__((unused)) +uid_t sys_geteuid(void) +{ +#ifdef __NR_geteuid32 + return my_syscall0(__NR_geteuid32); +#else + return my_syscall0(__NR_geteuid); +#endif +} + +static __attribute__((unused)) +uid_t geteuid(void) +{ + return sys_geteuid(); +} + + +/* * pid_t getpgid(pid_t pid); */ @@ -545,6 +567,27 @@ int gettimeofday(struct timeval *tv, struct timezone *tz) /* + * uid_t getuid(void); + */ + +static __attribute__((unused)) +uid_t sys_getuid(void) +{ +#ifdef __NR_getuid32 + return my_syscall0(__NR_getuid32); +#else + return my_syscall0(__NR_getuid); +#endif +} + +static __attribute__((unused)) +uid_t getuid(void) +{ + return sys_getuid(); +} + + +/* * int ioctl(int fd, unsigned long req, void *value); */ @@ -1048,12 +1091,66 @@ pid_t setsid(void) return ret; } +#if defined(__NR_statx) +/* + * int statx(int fd, const char *path, int flags, unsigned int mask, struct statx *buf); + */ + +static __attribute__((unused)) +int sys_statx(int fd, const char *path, int flags, unsigned int mask, struct statx *buf) +{ + return my_syscall5(__NR_statx, fd, path, flags, mask, buf); +} + +static __attribute__((unused)) +int statx(int fd, const char *path, int flags, unsigned int mask, struct statx *buf) +{ + int ret = sys_statx(fd, path, flags, mask, buf); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} +#endif /* * int stat(const char *path, struct stat *buf); * Warning: the struct stat's layout is arch-dependent. */ +#if defined(__NR_statx) && !defined(__NR_newfstatat) && !defined(__NR_stat) +/* + * Maybe we can just use statx() when available for all architectures? + */ +static __attribute__((unused)) +int sys_stat(const char *path, struct stat *buf) +{ + struct statx statx; + long ret; + + ret = sys_statx(AT_FDCWD, path, AT_NO_AUTOMOUNT, STATX_BASIC_STATS, &statx); + buf->st_dev = ((statx.stx_dev_minor & 0xff) + | (statx.stx_dev_major << 8) + | ((statx.stx_dev_minor & ~0xff) << 12)); + buf->st_ino = statx.stx_ino; + buf->st_mode = statx.stx_mode; + buf->st_nlink = statx.stx_nlink; + buf->st_uid = statx.stx_uid; + buf->st_gid = statx.stx_gid; + buf->st_rdev = ((statx.stx_rdev_minor & 0xff) + | (statx.stx_rdev_major << 8) + | ((statx.stx_rdev_minor & ~0xff) << 12)); + buf->st_size = statx.stx_size; + buf->st_blksize = statx.stx_blksize; + buf->st_blocks = statx.stx_blocks; + buf->st_atime = statx.stx_atime.tv_sec; + buf->st_mtime = statx.stx_mtime.tv_sec; + buf->st_ctime = statx.stx_ctime.tv_sec; + return ret; +} +#else static __attribute__((unused)) int sys_stat(const char *path, struct stat *buf) { @@ -1083,6 +1180,7 @@ int sys_stat(const char *path, struct stat *buf) buf->st_ctime = stat.st_ctime; return ret; } +#endif static __attribute__((unused)) int stat(const char *path, struct stat *buf) diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h index fbbc0e68c001..aedd7d9e3f64 100644 --- a/tools/include/nolibc/types.h +++ b/tools/include/nolibc/types.h @@ -9,6 +9,7 @@ #include "std.h" #include <linux/time.h> +#include <linux/stat.h> /* Only the generic macros and types may be defined here. The arch-specific @@ -16,7 +17,11 @@ * the layout of sys_stat_struct must not be defined here. */ -/* stat flags (WARNING, octal here) */ +/* stat flags (WARNING, octal here). We need to check for an existing + * definition because linux/stat.h may omit to define those if it finds + * that any glibc header was already included. + */ +#if !defined(S_IFMT) #define S_IFDIR 0040000 #define S_IFCHR 0020000 #define S_IFBLK 0060000 @@ -34,6 +39,22 @@ #define S_ISLNK(mode) (((mode) & S_IFMT) == S_IFLNK) #define S_ISSOCK(mode) (((mode) & S_IFMT) == S_IFSOCK) +#define S_IRWXU 00700 +#define S_IRUSR 00400 +#define S_IWUSR 00200 +#define S_IXUSR 00100 + +#define S_IRWXG 00070 +#define S_IRGRP 00040 +#define S_IWGRP 00020 +#define S_IXGRP 00010 + +#define S_IRWXO 00007 +#define S_IROTH 00004 +#define S_IWOTH 00002 +#define S_IXOTH 00001 +#endif + /* dirent types */ #define DT_UNKNOWN 0x0 #define DT_FIFO 0x1 @@ -60,11 +81,6 @@ #define MAXPATHLEN (PATH_MAX) #endif -/* Special FD used by all the *at functions */ -#ifndef AT_FDCWD -#define AT_FDCWD (-100) -#endif - /* whence values for lseek() */ #define SEEK_SET 0 #define SEEK_CUR 1 @@ -81,6 +97,8 @@ /* Macros used on waitpid()'s return status */ #define WEXITSTATUS(status) (((status) & 0xff00) >> 8) #define WIFEXITED(status) (((status) & 0x7f) == 0) +#define WTERMSIG(status) ((status) & 0x7f) +#define WIFSIGNALED(status) ((status) - 1 < 0xff) /* waitpid() flags */ #define WNOHANG 1 diff --git a/tools/include/nolibc/unistd.h b/tools/include/nolibc/unistd.h index 1cfcd52106a4..ac7d53d986cd 100644 --- a/tools/include/nolibc/unistd.h +++ b/tools/include/nolibc/unistd.h @@ -13,6 +13,11 @@ #include "sys.h" +#define STDIN_FILENO 0 +#define STDOUT_FILENO 1 +#define STDERR_FILENO 2 + + static __attribute__((unused)) int msleep(unsigned int msecs) { diff --git a/tools/include/uapi/asm-generic/fcntl.h b/tools/include/uapi/asm-generic/fcntl.h index b02c8e0f4057..1c7a0f6632c0 100644 --- a/tools/include/uapi/asm-generic/fcntl.h +++ b/tools/include/uapi/asm-generic/fcntl.h @@ -91,7 +91,6 @@ /* 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) #ifndef O_NDELAY #define O_NDELAY O_NONBLOCK diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h index 2f86b2ad6d7e..e8c07da58c9f 100644 --- a/tools/include/uapi/linux/fcntl.h +++ b/tools/include/uapi/linux/fcntl.h @@ -43,6 +43,7 @@ #define F_SEAL_GROW 0x0004 /* prevent file from growing */ #define F_SEAL_WRITE 0x0008 /* prevent writes */ #define F_SEAL_FUTURE_WRITE 0x0010 /* prevent future writes while mapped */ +#define F_SEAL_EXEC 0x0020 /* prevent chmod modifying exec bits */ /* (1U << 31) is reserved for signed error codes */ /* diff --git a/tools/include/uapi/linux/hw_breakpoint.h b/tools/include/uapi/linux/hw_breakpoint.h index 965e4d8606d8..1575d3ca6f0d 100644 --- a/tools/include/uapi/linux/hw_breakpoint.h +++ b/tools/include/uapi/linux/hw_breakpoint.h @@ -22,14 +22,4 @@ enum { HW_BREAKPOINT_INVALID = HW_BREAKPOINT_RW | HW_BREAKPOINT_X, }; -enum bp_type_idx { - TYPE_INST = 0, -#ifdef CONFIG_HAVE_MIXED_BREAKPOINTS_REGS - TYPE_DATA = 0, -#else - TYPE_DATA = 1, -#endif - TYPE_MAX -}; - #endif /* _UAPI_LINUX_HW_BREAKPOINT_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 55155e262646..d77aef872a0a 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -583,6 +583,8 @@ struct kvm_s390_mem_op { struct { __u8 ar; /* the access register number */ __u8 key; /* access key, ignored if flag unset */ + __u8 pad1[6]; /* ignored */ + __u64 old_addr; /* ignored if cmpxchg flag unset */ }; __u32 sida_offset; /* offset into the sida */ __u8 reserved[32]; /* ignored */ @@ -595,11 +597,17 @@ struct kvm_s390_mem_op { #define KVM_S390_MEMOP_SIDA_WRITE 3 #define KVM_S390_MEMOP_ABSOLUTE_READ 4 #define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 +#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6 + /* flags for kvm_s390_mem_op->flags */ #define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) #define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) #define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) +/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */ +#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0) +#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1) + /* for KVM_INTERRUPT */ struct kvm_interrupt { /* in */ @@ -1175,6 +1183,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223 #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225 +#define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 9ee459872600..639524b59930 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN uapi header */ @@ -19,7 +19,7 @@ * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP * in zero copy mode. * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw - * oflloading. + * offloading. * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear * XDP buffer support in the driver napi callback. * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements @@ -33,6 +33,8 @@ enum netdev_xdp_act { NETDEV_XDP_ACT_HW_OFFLOAD = 16, NETDEV_XDP_ACT_RX_SG = 32, NETDEV_XDP_ACT_NDO_XMIT_SG = 64, + + NETDEV_XDP_ACT_MASK = 127, }; enum { diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index ccb7f5dad59b..37675437b768 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -374,6 +374,7 @@ enum perf_event_read_format { #define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */ #define PERF_ATTR_SIZE_VER6 120 /* add: aux_sample_size */ #define PERF_ATTR_SIZE_VER7 128 /* add: sig_data */ +#define PERF_ATTR_SIZE_VER8 136 /* add: config3 */ /* * Hardware event_id to monitor via a performance monitoring event: @@ -515,6 +516,8 @@ struct perf_event_attr { * truncated accordingly on 32 bit architectures. */ __u64 sig_data; + + __u64 config3; /* extension of config2 */ }; /* diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index a5e06dcbba13..1312a137f7fb 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -281,6 +281,12 @@ struct prctl_mm_map { # define PR_SME_VL_LEN_MASK 0xffff # define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */ +/* Memory deny write / execute */ +#define PR_SET_MDWE 65 +# define PR_MDWE_REFUSE_EXEC_GAIN 1 + +#define PR_GET_MDWE 66 + #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index f9f115a7c75b..92e1b700b51c 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -180,4 +180,12 @@ */ #define VHOST_VDPA_SUSPEND _IO(VHOST_VIRTIO, 0x7D) +/* Resume a device so it can resume processing virtqueue requests + * + * After the return of this ioctl the device will have restored all the + * necessary states and it is fully operational to continue processing the + * virtqueue descriptors. + */ +#define VHOST_VDPA_RESUME _IO(VHOST_VIRTIO, 0x7E) + #endif diff --git a/tools/include/vdso/bits.h b/tools/include/vdso/bits.h index 6d005a1f5d94..388b212088ea 100644 --- a/tools/include/vdso/bits.h +++ b/tools/include/vdso/bits.h @@ -5,5 +5,6 @@ #include <vdso/const.h> #define BIT(nr) (UL(1) << (nr)) +#define BIT_ULL(nr) (ULL(1) << (nr)) #endif /* __VDSO_BITS_H */ diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index fbaf68335394..e4d05662a96c 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -20,8 +20,8 @@ /* make sure libbpf doesn't use kernel-only integer typedefs */ #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 -/* prevent accidental re-addition of reallocarray()/strlcpy() */ -#pragma GCC poison reallocarray strlcpy +/* prevent accidental re-addition of reallocarray() */ +#pragma GCC poison reallocarray #include "libbpf.h" #include "btf.h" diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt index 8e7085238470..6dc8b3642458 100644 --- a/tools/memory-model/Documentation/explanation.txt +++ b/tools/memory-model/Documentation/explanation.txt @@ -28,9 +28,10 @@ Explanation of the Linux-Kernel Memory Consistency Model 20. THE HAPPENS-BEFORE RELATION: hb 21. THE PROPAGATES-BEFORE RELATION: pb 22. RCU RELATIONS: rcu-link, rcu-gp, rcu-rscsi, rcu-order, rcu-fence, and rb - 23. LOCKING - 24. PLAIN ACCESSES AND DATA RACES - 25. ODDS AND ENDS + 23. SRCU READ-SIDE CRITICAL SECTIONS + 24. LOCKING + 25. PLAIN ACCESSES AND DATA RACES + 26. ODDS AND ENDS @@ -1848,14 +1849,169 @@ section in P0 both starts before P1's grace period does and ends before it does, and the critical section in P2 both starts after P1's grace period does and ends after it does. -Addendum: The LKMM now supports SRCU (Sleepable Read-Copy-Update) in -addition to normal RCU. The ideas involved are much the same as -above, with new relations srcu-gp and srcu-rscsi added to represent -SRCU grace periods and read-side critical sections. There is a -restriction on the srcu-gp and srcu-rscsi links that can appear in an -rcu-order sequence (the srcu-rscsi links must be paired with srcu-gp -links having the same SRCU domain with proper nesting); the details -are relatively unimportant. +The LKMM supports SRCU (Sleepable Read-Copy-Update) in addition to +normal RCU. The ideas involved are much the same as above, with new +relations srcu-gp and srcu-rscsi added to represent SRCU grace periods +and read-side critical sections. However, there are some significant +differences between RCU read-side critical sections and their SRCU +counterparts, as described in the next section. + + +SRCU READ-SIDE CRITICAL SECTIONS +-------------------------------- + +The LKMM uses the srcu-rscsi relation to model SRCU read-side critical +sections. They differ from RCU read-side critical sections in the +following respects: + +1. Unlike the analogous RCU primitives, synchronize_srcu(), + srcu_read_lock(), and srcu_read_unlock() take a pointer to a + struct srcu_struct as an argument. This structure is called + an SRCU domain, and calls linked by srcu-rscsi must have the + same domain. Read-side critical sections and grace periods + associated with different domains are independent of one + another; the SRCU version of the RCU Guarantee applies only + to pairs of critical sections and grace periods having the + same domain. + +2. srcu_read_lock() returns a value, called the index, which must + be passed to the matching srcu_read_unlock() call. Unlike + rcu_read_lock() and rcu_read_unlock(), an srcu_read_lock() + call does not always have to match the next unpaired + srcu_read_unlock(). In fact, it is possible for two SRCU + read-side critical sections to overlap partially, as in the + following example (where s is an srcu_struct and idx1 and idx2 + are integer variables): + + idx1 = srcu_read_lock(&s); // Start of first RSCS + idx2 = srcu_read_lock(&s); // Start of second RSCS + srcu_read_unlock(&s, idx1); // End of first RSCS + srcu_read_unlock(&s, idx2); // End of second RSCS + + The matching is determined entirely by the domain pointer and + index value. By contrast, if the calls had been + rcu_read_lock() and rcu_read_unlock() then they would have + created two nested (fully overlapping) read-side critical + sections: an inner one and an outer one. + +3. The srcu_down_read() and srcu_up_read() primitives work + exactly like srcu_read_lock() and srcu_read_unlock(), except + that matching calls don't have to execute on the same CPU. + (The names are meant to be suggestive of operations on + semaphores.) Since the matching is determined by the domain + pointer and index value, these primitives make it possible for + an SRCU read-side critical section to start on one CPU and end + on another, so to speak. + +In order to account for these properties of SRCU, the LKMM models +srcu_read_lock() as a special type of load event (which is +appropriate, since it takes a memory location as argument and returns +a value, just as a load does) and srcu_read_unlock() as a special type +of store event (again appropriate, since it takes as arguments a +memory location and a value). These loads and stores are annotated as +belonging to the "srcu-lock" and "srcu-unlock" event classes +respectively. + +This approach allows the LKMM to tell whether two events are +associated with the same SRCU domain, simply by checking whether they +access the same memory location (i.e., they are linked by the loc +relation). It also gives a way to tell which unlock matches a +particular lock, by checking for the presence of a data dependency +from the load (srcu-lock) to the store (srcu-unlock). For example, +given the situation outlined earlier (with statement labels added): + + A: idx1 = srcu_read_lock(&s); + B: idx2 = srcu_read_lock(&s); + C: srcu_read_unlock(&s, idx1); + D: srcu_read_unlock(&s, idx2); + +the LKMM will treat A and B as loads from s yielding values saved in +idx1 and idx2 respectively. Similarly, it will treat C and D as +though they stored the values from idx1 and idx2 in s. The end result +is much as if we had written: + + A: idx1 = READ_ONCE(s); + B: idx2 = READ_ONCE(s); + C: WRITE_ONCE(s, idx1); + D: WRITE_ONCE(s, idx2); + +except for the presence of the special srcu-lock and srcu-unlock +annotations. You can see at once that we have A ->data C and +B ->data D. These dependencies tell the LKMM that C is the +srcu-unlock event matching srcu-lock event A, and D is the +srcu-unlock event matching srcu-lock event B. + +This approach is admittedly a hack, and it has the potential to lead +to problems. For example, in: + + idx1 = srcu_read_lock(&s); + srcu_read_unlock(&s, idx1); + idx2 = srcu_read_lock(&s); + srcu_read_unlock(&s, idx2); + +the LKMM will believe that idx2 must have the same value as idx1, +since it reads from the immediately preceding store of idx1 in s. +Fortunately this won't matter, assuming that litmus tests never do +anything with SRCU index values other than pass them to +srcu_read_unlock() or srcu_up_read() calls. + +However, sometimes it is necessary to store an index value in a +shared variable temporarily. In fact, this is the only way for +srcu_down_read() to pass the index it gets to an srcu_up_read() call +on a different CPU. In more detail, we might have soething like: + + struct srcu_struct s; + int x; + + P0() + { + int r0; + + A: r0 = srcu_down_read(&s); + B: WRITE_ONCE(x, r0); + } + + P1() + { + int r1; + + C: r1 = READ_ONCE(x); + D: srcu_up_read(&s, r1); + } + +Assuming that P1 executes after P0 and does read the index value +stored in x, we can write this (using brackets to represent event +annotations) as: + + A[srcu-lock] ->data B[once] ->rf C[once] ->data D[srcu-unlock]. + +The LKMM defines a carry-srcu-data relation to express this pattern; +it permits an arbitrarily long sequence of + + data ; rf + +pairs (that is, a data link followed by an rf link) to occur between +an srcu-lock event and the final data dependency leading to the +matching srcu-unlock event. carry-srcu-data is complicated by the +need to ensure that none of the intermediate store events in this +sequence are instances of srcu-unlock. This is necessary because in a +pattern like the one above: + + A: idx1 = srcu_read_lock(&s); + B: srcu_read_unlock(&s, idx1); + C: idx2 = srcu_read_lock(&s); + D: srcu_read_unlock(&s, idx2); + +the LKMM treats B as a store to the variable s and C as a load from +that variable, creating an undesirable rf link from B to C: + + A ->data B ->rf C ->data D. + +This would cause carry-srcu-data to mistakenly extend a data +dependency from A to D, giving the impression that D was the +srcu-unlock event matching A's srcu-lock. To avoid such problems, +carry-srcu-data does not accept sequences in which the ends of any of +the intermediate ->data links (B above) is an srcu-unlock event. LOCKING diff --git a/tools/memory-model/Documentation/litmus-tests.txt b/tools/memory-model/Documentation/litmus-tests.txt index 26554b1c5575..acac527328a1 100644 --- a/tools/memory-model/Documentation/litmus-tests.txt +++ b/tools/memory-model/Documentation/litmus-tests.txt @@ -1028,32 +1028,7 @@ Limitations of the Linux-kernel memory model (LKMM) include: additional call_rcu() process to the site of the emulated rcu-barrier(). - e. Although sleepable RCU (SRCU) is now modeled, there - are some subtle differences between its semantics and - those in the Linux kernel. For example, the kernel - might interpret the following sequence as two partially - overlapping SRCU read-side critical sections: - - 1 r1 = srcu_read_lock(&my_srcu); - 2 do_something_1(); - 3 r2 = srcu_read_lock(&my_srcu); - 4 do_something_2(); - 5 srcu_read_unlock(&my_srcu, r1); - 6 do_something_3(); - 7 srcu_read_unlock(&my_srcu, r2); - - In contrast, LKMM will interpret this as a nested pair of - SRCU read-side critical sections, with the outer critical - section spanning lines 1-7 and the inner critical section - spanning lines 3-5. - - This difference would be more of a concern had anyone - identified a reasonable use case for partially overlapping - SRCU read-side critical sections. For more information - on the trickiness of such overlapping, please see: - https://paulmck.livejournal.com/40593.html - - f. Reader-writer locking is not modeled. It can be + e. Reader-writer locking is not modeled. It can be emulated in litmus tests using atomic read-modify-write operations. diff --git a/tools/memory-model/Documentation/locking.txt b/tools/memory-model/Documentation/locking.txt new file mode 100644 index 000000000000..65c898c64a93 --- /dev/null +++ b/tools/memory-model/Documentation/locking.txt @@ -0,0 +1,298 @@ +Locking +======= + +Locking is well-known and the common use cases are straightforward: Any +CPU holding a given lock sees any changes previously seen or made by any +CPU before it previously released that same lock. This last sentence +is the only part of this document that most developers will need to read. + +However, developers who would like to also access lock-protected shared +variables outside of their corresponding locks should continue reading. + + +Locking and Prior Accesses +-------------------------- + +The basic rule of locking is worth repeating: + + Any CPU holding a given lock sees any changes previously seen + or made by any CPU before it previously released that same lock. + +Note that this statement is a bit stronger than "Any CPU holding a +given lock sees all changes made by any CPU during the time that CPU was +previously holding this same lock". For example, consider the following +pair of code fragments: + + /* See MP+polocks.litmus. */ + void CPU0(void) + { + WRITE_ONCE(x, 1); + spin_lock(&mylock); + WRITE_ONCE(y, 1); + spin_unlock(&mylock); + } + + void CPU1(void) + { + spin_lock(&mylock); + r0 = READ_ONCE(y); + spin_unlock(&mylock); + r1 = READ_ONCE(x); + } + +The basic rule guarantees that if CPU0() acquires mylock before CPU1(), +then both r0 and r1 must be set to the value 1. This also has the +consequence that if the final value of r0 is equal to 1, then the final +value of r1 must also be equal to 1. In contrast, the weaker rule would +say nothing about the final value of r1. + + +Locking and Subsequent Accesses +------------------------------- + +The converse to the basic rule also holds: Any CPU holding a given +lock will not see any changes that will be made by any CPU after it +subsequently acquires this same lock. This converse statement is +illustrated by the following litmus test: + + /* See MP+porevlocks.litmus. */ + void CPU0(void) + { + r0 = READ_ONCE(y); + spin_lock(&mylock); + r1 = READ_ONCE(x); + spin_unlock(&mylock); + } + + void CPU1(void) + { + spin_lock(&mylock); + WRITE_ONCE(x, 1); + spin_unlock(&mylock); + WRITE_ONCE(y, 1); + } + +This converse to the basic rule guarantees that if CPU0() acquires +mylock before CPU1(), then both r0 and r1 must be set to the value 0. +This also has the consequence that if the final value of r1 is equal +to 0, then the final value of r0 must also be equal to 0. In contrast, +the weaker rule would say nothing about the final value of r0. + +These examples show only a single pair of CPUs, but the effects of the +locking basic rule extend across multiple acquisitions of a given lock +across multiple CPUs. + + +Double-Checked Locking +---------------------- + +It is well known that more than just a lock is required to make +double-checked locking work correctly, This litmus test illustrates +one incorrect approach: + + /* See Documentation/litmus-tests/locking/DCL-broken.litmus. */ + void CPU0(void) + { + r0 = READ_ONCE(flag); + if (r0 == 0) { + spin_lock(&lck); + r1 = READ_ONCE(flag); + if (r1 == 0) { + WRITE_ONCE(data, 1); + WRITE_ONCE(flag, 1); + } + spin_unlock(&lck); + } + r2 = READ_ONCE(data); + } + /* CPU1() is the exactly the same as CPU0(). */ + +There are two problems. First, there is no ordering between the first +READ_ONCE() of "flag" and the READ_ONCE() of "data". Second, there is +no ordering between the two WRITE_ONCE() calls. It should therefore be +no surprise that "r2" can be zero, and a quick herd7 run confirms this. + +One way to fix this is to use smp_load_acquire() and smp_store_release() +as shown in this corrected version: + + /* See Documentation/litmus-tests/locking/DCL-fixed.litmus. */ + void CPU0(void) + { + r0 = smp_load_acquire(&flag); + if (r0 == 0) { + spin_lock(&lck); + r1 = READ_ONCE(flag); + if (r1 == 0) { + WRITE_ONCE(data, 1); + smp_store_release(&flag, 1); + } + spin_unlock(&lck); + } + r2 = READ_ONCE(data); + } + /* CPU1() is the exactly the same as CPU0(). */ + +The smp_load_acquire() guarantees that its load from "flags" will +be ordered before the READ_ONCE() from data, thus solving the first +problem. The smp_store_release() guarantees that its store will be +ordered after the WRITE_ONCE() to "data", solving the second problem. +The smp_store_release() pairs with the smp_load_acquire(), thus ensuring +that the ordering provided by each actually takes effect. Again, a +quick herd7 run confirms this. + +In short, if you access a lock-protected variable without holding the +corresponding lock, you will need to provide additional ordering, in +this case, via the smp_load_acquire() and the smp_store_release(). + + +Ordering Provided by a Lock to CPUs Not Holding That Lock +--------------------------------------------------------- + +It is not necessarily the case that accesses ordered by locking will be +seen as ordered by CPUs not holding that lock. Consider this example: + + /* See Z6.0+pooncelock+pooncelock+pombonce.litmus. */ + void CPU0(void) + { + spin_lock(&mylock); + WRITE_ONCE(x, 1); + WRITE_ONCE(y, 1); + spin_unlock(&mylock); + } + + void CPU1(void) + { + spin_lock(&mylock); + r0 = READ_ONCE(y); + WRITE_ONCE(z, 1); + spin_unlock(&mylock); + } + + void CPU2(void) + { + WRITE_ONCE(z, 2); + smp_mb(); + r1 = READ_ONCE(x); + } + +Counter-intuitive though it might be, it is quite possible to have +the final value of r0 be 1, the final value of z be 2, and the final +value of r1 be 0. The reason for this surprising outcome is that CPU2() +never acquired the lock, and thus did not fully benefit from the lock's +ordering properties. + +Ordering can be extended to CPUs not holding the lock by careful use +of smp_mb__after_spinlock(): + + /* See Z6.0+pooncelock+poonceLock+pombonce.litmus. */ + void CPU0(void) + { + spin_lock(&mylock); + WRITE_ONCE(x, 1); + WRITE_ONCE(y, 1); + spin_unlock(&mylock); + } + + void CPU1(void) + { + spin_lock(&mylock); + smp_mb__after_spinlock(); + r0 = READ_ONCE(y); + WRITE_ONCE(z, 1); + spin_unlock(&mylock); + } + + void CPU2(void) + { + WRITE_ONCE(z, 2); + smp_mb(); + r1 = READ_ONCE(x); + } + +This addition of smp_mb__after_spinlock() strengthens the lock +acquisition sufficiently to rule out the counter-intuitive outcome. +In other words, the addition of the smp_mb__after_spinlock() prohibits +the counter-intuitive result where the final value of r0 is 1, the final +value of z is 2, and the final value of r1 is 0. + + +No Roach-Motel Locking! +----------------------- + +This example requires familiarity with the herd7 "filter" clause, so +please read up on that topic in litmus-tests.txt. + +It is tempting to allow memory-reference instructions to be pulled +into a critical section, but this cannot be allowed in the general case. +For example, consider a spin loop preceding a lock-based critical section. +Now, herd7 does not model spin loops, but we can emulate one with two +loads, with a "filter" clause to constrain the first to return the +initial value and the second to return the updated value, as shown below: + + /* See Documentation/litmus-tests/locking/RM-fixed.litmus. */ + void CPU0(void) + { + spin_lock(&lck); + r2 = atomic_inc_return(&y); + WRITE_ONCE(x, 1); + spin_unlock(&lck); + } + + void CPU1(void) + { + r0 = READ_ONCE(x); + r1 = READ_ONCE(x); + spin_lock(&lck); + r2 = atomic_inc_return(&y); + spin_unlock(&lck); + } + + filter (1:r0=0 /\ 1:r1=1) + exists (1:r2=1) + +The variable "x" is the control variable for the emulated spin loop. +CPU0() sets it to "1" while holding the lock, and CPU1() emulates the +spin loop by reading it twice, first into "1:r0" (which should get the +initial value "0") and then into "1:r1" (which should get the updated +value "1"). + +The "filter" clause takes this into account, constraining "1:r0" to +equal "0" and "1:r1" to equal 1. + +Then the "exists" clause checks to see if CPU1() acquired its lock first, +which should not happen given the filter clause because CPU0() updates +"x" while holding the lock. And herd7 confirms this. + +But suppose that the compiler was permitted to reorder the spin loop +into CPU1()'s critical section, like this: + + /* See Documentation/litmus-tests/locking/RM-broken.litmus. */ + void CPU0(void) + { + int r2; + + spin_lock(&lck); + r2 = atomic_inc_return(&y); + WRITE_ONCE(x, 1); + spin_unlock(&lck); + } + + void CPU1(void) + { + spin_lock(&lck); + r0 = READ_ONCE(x); + r1 = READ_ONCE(x); + r2 = atomic_inc_return(&y); + spin_unlock(&lck); + } + + filter (1:r0=0 /\ 1:r1=1) + exists (1:r2=1) + +If "1:r0" is equal to "0", "1:r1" can never equal "1" because CPU0() +cannot update "x" while CPU1() holds the lock. And herd7 confirms this, +showing zero executions matching the "filter" criteria. + +And this is why Linux-kernel lock and unlock primitives must prevent +code from entering critical sections. It is not sufficient to only +prevent code from leaving them. diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell index 70a9073dec3e..ce068700939c 100644 --- a/tools/memory-model/linux-kernel.bell +++ b/tools/memory-model/linux-kernel.bell @@ -31,7 +31,8 @@ enum Barriers = 'wmb (*smp_wmb*) || 'before-atomic (*smp_mb__before_atomic*) || 'after-atomic (*smp_mb__after_atomic*) || 'after-spinlock (*smp_mb__after_spinlock*) || - 'after-unlock-lock (*smp_mb__after_unlock_lock*) + 'after-unlock-lock (*smp_mb__after_unlock_lock*) || + 'after-srcu-read-unlock (*smp_mb__after_srcu_read_unlock*) instructions F[Barriers] (* SRCU *) @@ -53,38 +54,31 @@ let rcu-rscs = let rec in matched (* Validate nesting *) -flag ~empty Rcu-lock \ domain(rcu-rscs) as unbalanced-rcu-locking -flag ~empty Rcu-unlock \ range(rcu-rscs) as unbalanced-rcu-locking +flag ~empty Rcu-lock \ domain(rcu-rscs) as unmatched-rcu-lock +flag ~empty Rcu-unlock \ range(rcu-rscs) as unmatched-rcu-unlock (* Compute matching pairs of nested Srcu-lock and Srcu-unlock *) -let srcu-rscs = let rec - unmatched-locks = Srcu-lock \ domain(matched) - and unmatched-unlocks = Srcu-unlock \ range(matched) - and unmatched = unmatched-locks | unmatched-unlocks - and unmatched-po = ([unmatched] ; po ; [unmatched]) & loc - and unmatched-locks-to-unlocks = - ([unmatched-locks] ; po ; [unmatched-unlocks]) & loc - and matched = matched | (unmatched-locks-to-unlocks \ - (unmatched-po ; unmatched-po)) - in matched +let carry-srcu-data = (data ; [~ Srcu-unlock] ; rf)* +let srcu-rscs = ([Srcu-lock] ; carry-srcu-data ; data ; [Srcu-unlock]) & loc (* Validate nesting *) -flag ~empty Srcu-lock \ domain(srcu-rscs) as unbalanced-srcu-locking -flag ~empty Srcu-unlock \ range(srcu-rscs) as unbalanced-srcu-locking +flag ~empty Srcu-lock \ domain(srcu-rscs) as unmatched-srcu-lock +flag ~empty Srcu-unlock \ range(srcu-rscs) as unmatched-srcu-unlock +flag ~empty (srcu-rscs^-1 ; srcu-rscs) \ id as multiple-srcu-matches (* Check for use of synchronize_srcu() inside an RCU critical section *) flag ~empty rcu-rscs & (po ; [Sync-srcu] ; po) as invalid-sleep (* Validate SRCU dynamic match *) -flag ~empty different-values(srcu-rscs) as srcu-bad-nesting +flag ~empty different-values(srcu-rscs) as srcu-bad-value-match (* Compute marked and plain memory accesses *) let Marked = (~M) | IW | Once | Release | Acquire | domain(rmw) | range(rmw) | - LKR | LKW | UL | LF | RL | RU + LKR | LKW | UL | LF | RL | RU | Srcu-lock | Srcu-unlock let Plain = M \ Marked (* Redefine dependencies to include those carried through plain accesses *) -let carry-dep = (data ; rfi)* +let carry-dep = (data ; [~ Srcu-unlock] ; rfi)* let addr = carry-dep ; addr let ctrl = carry-dep ; ctrl let data = carry-dep ; data diff --git a/tools/memory-model/linux-kernel.cat b/tools/memory-model/linux-kernel.cat index 07f884f9b2bf..adf3c4f41229 100644 --- a/tools/memory-model/linux-kernel.cat +++ b/tools/memory-model/linux-kernel.cat @@ -37,8 +37,20 @@ let mb = ([M] ; fencerel(Mb) ; [M]) | ([M] ; fencerel(Before-atomic) ; [RMW] ; po? ; [M]) | ([M] ; po? ; [RMW] ; fencerel(After-atomic) ; [M]) | ([M] ; po? ; [LKW] ; fencerel(After-spinlock) ; [M]) | - ([M] ; po ; [UL] ; (co | po) ; [LKW] ; - fencerel(After-unlock-lock) ; [M]) +(* + * Note: The po-unlock-lock-po relation only passes the lock to the direct + * successor, perhaps giving the impression that the ordering of the + * smp_mb__after_unlock_lock() fence only affects a single lock handover. + * However, in a longer sequence of lock handovers, the implicit + * A-cumulative release fences of lock-release ensure that any stores that + * propagate to one of the involved CPUs before it hands over the lock to + * the next CPU will also propagate to the final CPU handing over the lock + * to the CPU that executes the fence. Therefore, all those stores are + * also affected by the fence. + *) + ([M] ; po-unlock-lock-po ; + [After-unlock-lock] ; po ; [M]) | + ([M] ; po? ; [Srcu-unlock] ; fencerel(After-srcu-read-unlock) ; [M]) let gp = po ; [Sync-rcu | Sync-srcu] ; po? let strong-fence = mb | gp @@ -69,8 +81,8 @@ let dep = addr | data let rwdep = (dep | ctrl) ; [W] let overwrite = co | fr let to-w = rwdep | (overwrite & int) | (addr ; [Plain] ; wmb) -let to-r = addr | (dep ; [Marked] ; rfi) -let ppo = to-r | to-w | fence | (po-unlock-lock-po & int) +let to-r = (addr ; [R]) | (dep ; [Marked] ; rfi) +let ppo = to-r | to-w | (fence & int) | (po-unlock-lock-po & int) (* Propagation: Ordering from release operations and strong fences. *) let A-cumul(r) = (rfe ; [Marked])? ; r diff --git a/tools/memory-model/linux-kernel.def b/tools/memory-model/linux-kernel.def index ef0f3c1850de..88a39601f525 100644 --- a/tools/memory-model/linux-kernel.def +++ b/tools/memory-model/linux-kernel.def @@ -24,6 +24,7 @@ smp_mb__before_atomic() { __fence{before-atomic}; } smp_mb__after_atomic() { __fence{after-atomic}; } smp_mb__after_spinlock() { __fence{after-spinlock}; } smp_mb__after_unlock_lock() { __fence{after-unlock-lock}; } +smp_mb__after_srcu_read_unlock() { __fence{after-srcu-read-unlock}; } barrier() { __fence{barrier}; } // Exchange @@ -49,8 +50,10 @@ synchronize_rcu() { __fence{sync-rcu}; } synchronize_rcu_expedited() { __fence{sync-rcu}; } // SRCU -srcu_read_lock(X) __srcu{srcu-lock}(X) -srcu_read_unlock(X,Y) { __srcu{srcu-unlock}(X,Y); } +srcu_read_lock(X) __load{srcu-lock}(*X) +srcu_read_unlock(X,Y) { __store{srcu-unlock}(*X,Y); } +srcu_down_read(X) __load{srcu-lock}(*X) +srcu_up_read(X,Y) { __store{srcu-unlock}(*X,Y); } synchronize_srcu(X) { __srcu{sync-srcu}(X); } synchronize_srcu_expedited(X) { __srcu{sync-srcu}(X); } diff --git a/tools/memory-model/litmus-tests/.gitignore b/tools/memory-model/litmus-tests/.gitignore index c492a1ddad91..19c379cf069d 100644 --- a/tools/memory-model/litmus-tests/.gitignore +++ b/tools/memory-model/litmus-tests/.gitignore @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -*.litmus.out +*.litmus.* diff --git a/tools/memory-model/lock.cat b/tools/memory-model/lock.cat index 6b52f365d73a..53b5a492739d 100644 --- a/tools/memory-model/lock.cat +++ b/tools/memory-model/lock.cat @@ -36,9 +36,9 @@ let RU = try RU with emptyset (* Treat RL as a kind of LF: a read with no ordering properties *) let LF = LF | RL -(* There should be no ordinary R or W accesses to spinlocks *) -let ALL-LOCKS = LKR | LKW | UL | LF | RU -flag ~empty [M \ IW] ; loc ; [ALL-LOCKS] as mixed-lock-accesses +(* There should be no ordinary R or W accesses to spinlocks or SRCU structs *) +let ALL-LOCKS = LKR | LKW | UL | LF | RU | Srcu-lock | Srcu-unlock | Sync-srcu +flag ~empty [M \ IW \ ALL-LOCKS] ; loc ; [ALL-LOCKS] as mixed-lock-accesses (* Link Lock-Reads to their RMW-partner Lock-Writes *) let lk-rmw = ([LKR] ; po-loc ; [LKW]) \ (po ; po) diff --git a/tools/memory-model/scripts/README b/tools/memory-model/scripts/README index 095c7eb36f9f..fb39bd0fd1b9 100644 --- a/tools/memory-model/scripts/README +++ b/tools/memory-model/scripts/README @@ -27,6 +27,14 @@ checklitmushist.sh checklitmus.sh Check a single litmus test against its "Result:" expected result. + Not intended to for manual use. + +checktheselitmus.sh + + Check the specified list of litmus tests against their "Result:" + expected results. This takes optional parseargs.sh arguments, + followed by "--" followed by pathnames starting from the current + directory. cmplitmushist.sh @@ -43,10 +51,10 @@ initlitmushist.sh judgelitmus.sh - Given a .litmus file and its .litmus.out herd7 output, check the - .litmus.out file against the .litmus file's "Result:" comment to - judge whether the test ran correctly. Not normally run manually, - provided instead for use by other scripts. + Given a .litmus file and its herd7 output, check the output file + against the .litmus file's "Result:" comment to judge whether + the test ran correctly. Not normally run manually, provided + instead for use by other scripts. newlitmushist.sh @@ -68,3 +76,35 @@ runlitmushist.sh README This file + +Testing a change to LKMM might go as follows: + + # Populate expected results without that change, and + # runs for about an hour on an 8-CPU x86 system: + scripts/initlitmushist.sh --timeout 10m --procs 10 + # Incorporate the change: + git am -s -3 /path/to/patch # Or whatever it takes. + + # Test the new version of LKMM as follows... + + # Runs in seconds, good smoke test: + scripts/checkalllitmus.sh + + # Compares results to those produced by initlitmushist.sh, + # and runs for about an hour on an 8-CPU x86 system: + scripts/checklitmushist.sh --timeout 10m --procs 10 + + # Checks results against Result tags, runs in minutes: + scripts/checkghlitmus.sh --timeout 10m --procs 10 + +The checkghlitmus.sh should not report errors in cases where the +checklitmushist.sh script did not also report a change. However, +this check is nevertheless valuable because it can find errors in the +original version of LKMM. Note however, that given the above procedure, +an error in the original LKMM version that is fixed by the patch will +be reported both as a mismatch by checklitmushist.sh and as an error +by checkghlitmus.sh. One exception to this rule of thumb is when the +test fails completely on the original version of LKMM and passes on the +new version. In this case, checklitmushist.sh will report a mismatch +and checkghlitmus.sh will report success. This happens when the change +to LKMM introduces a new primitive for which litmus tests already existed. diff --git a/tools/memory-model/scripts/checkalllitmus.sh b/tools/memory-model/scripts/checkalllitmus.sh index 3c0c7fbbd223..2d3ee850a839 100755 --- a/tools/memory-model/scripts/checkalllitmus.sh +++ b/tools/memory-model/scripts/checkalllitmus.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0+ # # Run herd7 tests on all .litmus files in the litmus-tests directory @@ -8,6 +8,11 @@ # "^^^". It also outputs verification results to a file whose name is # that of the specified litmus test, but with ".out" appended. # +# If the --hw argument is specified, this script translates the .litmus +# C-language file to the specified type of assembly and verifies that. +# But in this case, litmus tests using complex synchronization (such as +# locking, RCU, and SRCU) are cheerfully ignored. +# # Usage: # checkalllitmus.sh # @@ -17,7 +22,7 @@ # # Copyright IBM Corporation, 2018 # -# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> +# Author: Paul E. McKenney <paulmck@linux.ibm.com> . scripts/parseargs.sh @@ -30,29 +35,23 @@ else exit 255 fi -# Create any new directories that have appeared in the github litmus -# repo since the last run. +# Create any new directories that have appeared in the litmus-tests +# directory since the last run. if test "$LKMM_DESTDIR" != "." then find $litmusdir -type d -print | ( cd "$LKMM_DESTDIR"; sed -e 's/^/mkdir -p /' | sh ) fi -# Find the checklitmus script. If it is not where we expect it, then -# assume that the caller has the PATH environment variable set -# appropriately. -if test -x scripts/checklitmus.sh -then - clscript=scripts/checklitmus.sh -else - clscript=checklitmus.sh -fi - # Run the script on all the litmus tests in the specified directory ret=0 for i in $litmusdir/*.litmus do - if ! $clscript $i + if test -n "$LKMM_HW_MAP_FILE" && ! scripts/simpletest.sh $i + then + continue + fi + if ! scripts/checklitmus.sh $i then ret=1 fi diff --git a/tools/memory-model/scripts/checkghlitmus.sh b/tools/memory-model/scripts/checkghlitmus.sh index 6589fbb6f653..d3dfb321259f 100755 --- a/tools/memory-model/scripts/checkghlitmus.sh +++ b/tools/memory-model/scripts/checkghlitmus.sh @@ -10,6 +10,7 @@ # parseargs.sh scripts for arguments. . scripts/parseargs.sh +. scripts/hwfnseg.sh T=/tmp/checkghlitmus.sh.$$ trap 'rm -rf $T' 0 @@ -32,19 +33,19 @@ then ( cd "$LKMM_DESTDIR"; sed -e 's/^/mkdir -p /' | sh ) fi -# Create a list of the C-language litmus tests previously run. -( cd $LKMM_DESTDIR; find litmus -name '*.litmus.out' -print ) | - sed -e 's/\.out$//' | - xargs -r egrep -l '^ \* Result: (Never|Sometimes|Always|DEADLOCK)' | +# Create a list of the specified litmus tests previously run. +( cd $LKMM_DESTDIR; find litmus -name "*.litmus${hwfnseg}.out" -print ) | + sed -e "s/${hwfnseg}"'\.out$//' | + xargs -r grep -E -l '^ \* Result: (Never|Sometimes|Always|DEADLOCK)' | xargs -r grep -L "^P${LKMM_PROCS}"> $T/list-C-already # Create a list of C-language litmus tests with "Result:" commands and # no more than the specified number of processes. -find litmus -name '*.litmus' -exec grep -l -m 1 "^C " {} \; > $T/list-C -xargs < $T/list-C -r egrep -l '^ \* Result: (Never|Sometimes|Always|DEADLOCK)' > $T/list-C-result +find litmus -name '*.litmus' -print | mselect7 -arch C > $T/list-C +xargs < $T/list-C -r grep -E -l '^ \* Result: (Never|Sometimes|Always|DEADLOCK)' > $T/list-C-result xargs < $T/list-C-result -r grep -L "^P${LKMM_PROCS}" > $T/list-C-result-short -# Form list of tests without corresponding .litmus.out files +# Form list of tests without corresponding .out files sort $T/list-C-already $T/list-C-result-short | uniq -u > $T/list-C-needed # Run any needed tests. diff --git a/tools/memory-model/scripts/checklitmus.sh b/tools/memory-model/scripts/checklitmus.sh index 11461ed40b5e..4c1d0cf0ddad 100755 --- a/tools/memory-model/scripts/checklitmus.sh +++ b/tools/memory-model/scripts/checklitmus.sh @@ -1,10 +1,8 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0+ # -# Run a herd7 test and invokes judgelitmus.sh to check the result against -# a "Result:" comment within the litmus test. It also outputs verification -# results to a file whose name is that of the specified litmus test, but -# with ".out" appended. +# Invokes runlitmus.sh and judgelitmus.sh on its arguments to run the +# specified litmus test and pass judgment on the results. # # Usage: # checklitmus.sh file.litmus @@ -15,20 +13,7 @@ # # Copyright IBM Corporation, 2018 # -# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> +# Author: Paul E. McKenney <paulmck@linux.ibm.com> -litmus=$1 -herdoptions=${LKMM_HERD_OPTIONS--conf linux-kernel.cfg} - -if test -f "$litmus" -a -r "$litmus" -then - : -else - echo ' --- ' error: \"$litmus\" is not a readable file - exit 255 -fi - -echo Herd options: $herdoptions > $LKMM_DESTDIR/$litmus.out -/usr/bin/time $LKMM_TIMEOUT_CMD herd7 $herdoptions $litmus >> $LKMM_DESTDIR/$litmus.out 2>&1 - -scripts/judgelitmus.sh $litmus +scripts/runlitmus.sh $1 +scripts/judgelitmus.sh $1 diff --git a/tools/memory-model/scripts/checklitmushist.sh b/tools/memory-model/scripts/checklitmushist.sh index 1d210ffb7c8a..406ecfc0aee4 100755 --- a/tools/memory-model/scripts/checklitmushist.sh +++ b/tools/memory-model/scripts/checklitmushist.sh @@ -12,7 +12,7 @@ # # Copyright IBM Corporation, 2018 # -# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> +# Author: Paul E. McKenney <paulmck@linux.ibm.com> . scripts/parseargs.sh diff --git a/tools/memory-model/scripts/checktheselitmus.sh b/tools/memory-model/scripts/checktheselitmus.sh new file mode 100755 index 000000000000..10eeb5ecea6d --- /dev/null +++ b/tools/memory-model/scripts/checktheselitmus.sh @@ -0,0 +1,43 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0+ +# +# Invokes checklitmus.sh on its arguments to run the specified litmus +# test and pass judgment on the results. +# +# Usage: +# checktheselitmus.sh -- [ file1.litmus [ file2.litmus ... ] ] +# +# Run this in the directory containing the memory model, specifying the +# pathname of the litmus test to check. The usual parseargs.sh arguments +# can be specified prior to the "--". +# +# This script is intended for use with pathnames that start from the +# tools/memory-model directory. If some of the pathnames instead start at +# the root directory, they all must do so and the "--destdir /" parseargs.sh +# argument must be specified prior to the "--". Alternatively, some other +# "--destdir" argument can be supplied as long as the needed subdirectories +# are populated. +# +# Copyright IBM Corporation, 2018 +# +# Author: Paul E. McKenney <paulmck@linux.ibm.com> + +. scripts/parseargs.sh + +ret=0 +for i in "$@" +do + if scripts/checklitmus.sh $i + then + : + else + ret=1 + fi +done +if test "$ret" -ne 0 +then + echo " ^^^ VERIFICATION MISMATCHES" 1>&2 +else + echo All litmus tests verified as was expected. 1>&2 +fi +exit $ret diff --git a/tools/memory-model/scripts/cmplitmushist.sh b/tools/memory-model/scripts/cmplitmushist.sh index 0f498aeeccf5..ca1ac8b64614 100755 --- a/tools/memory-model/scripts/cmplitmushist.sh +++ b/tools/memory-model/scripts/cmplitmushist.sh @@ -12,12 +12,49 @@ trap 'rm -rf $T' 0 mkdir $T # comparetest oldpath newpath +badmacnam=0 +timedout=0 perfect=0 obsline=0 noobsline=0 obsresult=0 badcompare=0 comparetest () { + if grep -q ': Unknown macro ' $1 || grep -q ': Unknown macro ' $2 + then + if grep -q ': Unknown macro ' $1 + then + badname=`grep ': Unknown macro ' $1 | + sed -e 's/^.*: Unknown macro //' | + sed -e 's/ (User error).*$//'` + echo 'Current LKMM version does not know "'$badname'"' $1 + fi + if grep -q ': Unknown macro ' $2 + then + badname=`grep ': Unknown macro ' $2 | + sed -e 's/^.*: Unknown macro //' | + sed -e 's/ (User error).*$//'` + echo 'Current LKMM version does not know "'$badname'"' $2 + fi + badmacnam=`expr "$badmacnam" + 1` + return 0 + elif grep -q '^Command exited with non-zero status 124' $1 || + grep -q '^Command exited with non-zero status 124' $2 + then + if grep -q '^Command exited with non-zero status 124' $1 && + grep -q '^Command exited with non-zero status 124' $2 + then + echo Both runs timed out: $2 + elif grep -q '^Command exited with non-zero status 124' $1 + then + echo Old run timed out: $2 + elif grep -q '^Command exited with non-zero status 124' $2 + then + echo New run timed out: $2 + fi + timedout=`expr "$timedout" + 1` + return 0 + fi grep -v 'maxresident)k\|minor)pagefaults\|^Time' $1 > $T/oldout grep -v 'maxresident)k\|minor)pagefaults\|^Time' $2 > $T/newout if cmp -s $T/oldout $T/newout && grep -q '^Observation' $1 @@ -38,7 +75,7 @@ comparetest () { return 0 fi else - echo Missing Observation line "(e.g., herd7 timeout)": $2 + echo Missing Observation line "(e.g., syntax error)": $2 noobsline=`expr "$noobsline" + 1` return 0 fi @@ -72,12 +109,20 @@ then fi if test "$noobsline" -ne 0 then - echo Missing Observation line "(e.g., herd7 timeout)": $noobsline 1>&2 + echo Missing Observation line "(e.g., syntax error)": $noobsline 1>&2 fi if test "$obsresult" -ne 0 then echo Matching Observation Always/Sometimes/Never result: $obsresult 1>&2 fi +if test "$timedout" -ne 0 +then + echo "!!!" Timed out: $timedout 1>&2 +fi +if test "$badmacnam" -ne 0 +then + echo "!!!" Unknown primitive: $badmacnam 1>&2 +fi if test "$badcompare" -ne 0 then echo "!!!" Result changed: $badcompare 1>&2 diff --git a/tools/memory-model/scripts/hwfnseg.sh b/tools/memory-model/scripts/hwfnseg.sh new file mode 100755 index 000000000000..580c3281181c --- /dev/null +++ b/tools/memory-model/scripts/hwfnseg.sh @@ -0,0 +1,20 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0+ +# +# Generate the hardware extension to the litmus-test filename, or the +# empty string if this is an LKMM run. The extension is placed in +# the shell variable hwfnseg. +# +# Usage: +# . hwfnseg.sh +# +# Copyright IBM Corporation, 2019 +# +# Author: Paul E. McKenney <paulmck@linux.ibm.com> + +if test -z "$LKMM_HW_MAP_FILE" +then + hwfnseg= +else + hwfnseg=".$LKMM_HW_MAP_FILE" +fi diff --git a/tools/memory-model/scripts/initlitmushist.sh b/tools/memory-model/scripts/initlitmushist.sh index 956b6957484d..31ea782955d3 100755 --- a/tools/memory-model/scripts/initlitmushist.sh +++ b/tools/memory-model/scripts/initlitmushist.sh @@ -60,7 +60,7 @@ fi # Create a list of the C-language litmus tests with no more than the # specified number of processes (per the --procs argument). -find litmus -name '*.litmus' -exec grep -l -m 1 "^C " {} \; > $T/list-C +find litmus -name '*.litmus' -print | mselect7 -arch C > $T/list-C xargs < $T/list-C -r grep -L "^P${LKMM_PROCS}" > $T/list-C-short scripts/runlitmushist.sh < $T/list-C-short diff --git a/tools/memory-model/scripts/judgelitmus.sh b/tools/memory-model/scripts/judgelitmus.sh index 0cc63875e395..1ec5d89fcfbb 100755 --- a/tools/memory-model/scripts/judgelitmus.sh +++ b/tools/memory-model/scripts/judgelitmus.sh @@ -1,9 +1,22 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0+ # -# Given a .litmus test and the corresponding .litmus.out file, check -# the .litmus.out file against the "Result:" comment to judge whether -# the test ran correctly. +# Given a .litmus test and the corresponding litmus output file, check +# the .litmus.out file against the "Result:" comment to judge whether the +# test ran correctly. If the --hw argument is omitted, check against the +# LKMM output, which is assumed to be in file.litmus.out. If either a +# "DATARACE" marker in the "Result:" comment or a "Flag data-race" marker +# in the LKMM output is present, the other must also be as well, at least +# for litmus tests having a "Result:" comment. In this case, a failure of +# the Always/Sometimes/Never portion of the "Result:" prediction will be +# noted, but forgiven. +# +# If the --hw argument is provided, this is assumed to be a hardware +# test, and the output is assumed to be in file.litmus.HW.out, where +# "HW" is the --hw argument. In addition, non-Sometimes verification +# results will be noted, but forgiven. Furthermore, if there is no +# "Result:" comment but there is an LKMM .litmus.out file, the observation +# in that file will be used to judge the assembly-language verification. # # Usage: # judgelitmus.sh file.litmus @@ -13,7 +26,7 @@ # # Copyright IBM Corporation, 2018 # -# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> +# Author: Paul E. McKenney <paulmck@linux.ibm.com> litmus=$1 @@ -24,55 +37,120 @@ else echo ' --- ' error: \"$litmus\" is not a readable file exit 255 fi -if test -f "$LKMM_DESTDIR/$litmus".out -a -r "$LKMM_DESTDIR/$litmus".out +if test -z "$LKMM_HW_MAP_FILE" +then + litmusout=$litmus.out + lkmmout= +else + litmusout="`echo $litmus | + sed -e 's/\.litmus$/.litmus.'${LKMM_HW_MAP_FILE}'/'`.out" + lkmmout=$litmus.out +fi +if test -f "$LKMM_DESTDIR/$litmusout" -a -r "$LKMM_DESTDIR/$litmusout" then : else - echo ' --- ' error: \"$LKMM_DESTDIR/$litmus\".out is not a readable file + echo ' --- ' error: \"$LKMM_DESTDIR/$litmusout is not a readable file exit 255 fi -if grep -q '^ \* Result: ' $litmus +if grep -q '^Flag data-race$' "$LKMM_DESTDIR/$litmusout" +then + datarace_modeled=1 +fi +if grep -q '^[( ]\* Result: ' $litmus +then + outcome=`grep -m 1 '^[( ]\* Result: ' $litmus | awk '{ print $3 }'` + if grep -m1 '^[( ]\* Result: .* DATARACE' $litmus + then + datarace_predicted=1 + fi + if test -n "$datarace_predicted" -a -z "$datarace_modeled" -a -z "$LKMM_HW_MAP_FILE" + then + echo '!!! Predicted data race not modeled' $litmus + exit 252 + elif test -z "$datarace_predicted" -a -n "$datarace_modeled" + then + # Note that hardware models currently don't model data races + echo '!!! Unexpected data race modeled' $litmus + exit 253 + fi +elif test -n "$LKMM_HW_MAP_FILE" && grep -q '^Observation' $LKMM_DESTDIR/$lkmmout > /dev/null 2>&1 then - outcome=`grep -m 1 '^ \* Result: ' $litmus | awk '{ print $3 }'` + outcome=`grep -m 1 '^Observation ' $LKMM_DESTDIR/$lkmmout | awk '{ print $3 }'` else outcome=specified fi -grep '^Observation' $LKMM_DESTDIR/$litmus.out -if grep -q '^Observation' $LKMM_DESTDIR/$litmus.out +grep '^Observation' $LKMM_DESTDIR/$litmusout +if grep -q '^Observation' $LKMM_DESTDIR/$litmusout then : +elif grep ': Unknown macro ' $LKMM_DESTDIR/$litmusout +then + badname=`grep ': Unknown macro ' $LKMM_DESTDIR/$litmusout | + sed -e 's/^.*: Unknown macro //' | + sed -e 's/ (User error).*$//'` + badmsg=' !!! Current LKMM version does not know "'$badname'"'" $litmus" + echo $badmsg + if ! grep -q '!!!' $LKMM_DESTDIR/$litmusout + then + echo ' !!! '$badmsg >> $LKMM_DESTDIR/$litmusout 2>&1 + fi + exit 254 +elif grep '^Command exited with non-zero status 124' $LKMM_DESTDIR/$litmusout +then + echo ' !!! Timeout' $litmus + if ! grep -q '!!!' $LKMM_DESTDIR/$litmusout + then + echo ' !!! Timeout' >> $LKMM_DESTDIR/$litmusout 2>&1 + fi + exit 124 else echo ' !!! Verification error' $litmus - if ! grep -q '!!!' $LKMM_DESTDIR/$litmus.out + if ! grep -q '!!!' $LKMM_DESTDIR/$litmusout then - echo ' !!! Verification error' >> $LKMM_DESTDIR/$litmus.out 2>&1 + echo ' !!! Verification error' >> $LKMM_DESTDIR/$litmusout 2>&1 fi exit 255 fi if test "$outcome" = DEADLOCK then - if grep '^Observation' $LKMM_DESTDIR/$litmus.out | grep -q 'Never 0 0$' + if grep '^Observation' $LKMM_DESTDIR/$litmusout | grep -q 'Never 0 0$' then ret=0 else echo " !!! Unexpected non-$outcome verification" $litmus - if ! grep -q '!!!' $LKMM_DESTDIR/$litmus.out + if ! grep -q '!!!' $LKMM_DESTDIR/$litmusout then - echo " !!! Unexpected non-$outcome verification" >> $LKMM_DESTDIR/$litmus.out 2>&1 + echo " !!! Unexpected non-$outcome verification" >> $LKMM_DESTDIR/$litmusout 2>&1 fi ret=1 fi -elif grep '^Observation' $LKMM_DESTDIR/$litmus.out | grep -q $outcome || test "$outcome" = Maybe +elif grep '^Observation' $LKMM_DESTDIR/$litmusout | grep -q 'Never 0 0$' +then + echo " !!! Unexpected non-$outcome deadlock" $litmus + if ! grep -q '!!!' $LKMM_DESTDIR/$litmusout + then + echo " !!! Unexpected non-$outcome deadlock" $litmus >> $LKMM_DESTDIR/$litmusout 2>&1 + fi + ret=1 +elif grep '^Observation' $LKMM_DESTDIR/$litmusout | grep -q $outcome || test "$outcome" = Maybe then ret=0 else - echo " !!! Unexpected non-$outcome verification" $litmus - if ! grep -q '!!!' $LKMM_DESTDIR/$litmus.out + if test \( -n "$LKMM_HW_MAP_FILE" -a "$outcome" = Sometimes \) -o -n "$datarace_modeled" then - echo " !!! Unexpected non-$outcome verification" >> $LKMM_DESTDIR/$litmus.out 2>&1 + flag="--- Forgiven" + ret=0 + else + flag="!!! Unexpected" + ret=1 + fi + echo " $flag non-$outcome verification" $litmus + if ! grep -qe "$flag" $LKMM_DESTDIR/$litmusout + then + echo " $flag non-$outcome verification" >> $LKMM_DESTDIR/$litmusout 2>&1 fi - ret=1 fi -tail -2 $LKMM_DESTDIR/$litmus.out | head -1 +tail -2 $LKMM_DESTDIR/$litmusout | head -1 exit $ret diff --git a/tools/memory-model/scripts/newlitmushist.sh b/tools/memory-model/scripts/newlitmushist.sh index 991f8f814881..25235e2049cf 100755 --- a/tools/memory-model/scripts/newlitmushist.sh +++ b/tools/memory-model/scripts/newlitmushist.sh @@ -12,7 +12,7 @@ # # Copyright IBM Corporation, 2018 # -# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> +# Author: Paul E. McKenney <paulmck@linux.ibm.com> . scripts/parseargs.sh @@ -43,7 +43,7 @@ fi # Form full list of litmus tests with no more than the specified # number of processes (per the --procs argument). -find litmus -name '*.litmus' -exec grep -l -m 1 "^C " {} \; > $T/list-C-all +find litmus -name '*.litmus' -print | mselect7 -arch C > $T/list-C-all xargs < $T/list-C-all -r grep -L "^P${LKMM_PROCS}" > $T/list-C-short # Form list of new tests. Note: This does not handle litmus-test deletion! diff --git a/tools/memory-model/scripts/parseargs.sh b/tools/memory-model/scripts/parseargs.sh index 40f52080fdbd..08ded5909860 100755 --- a/tools/memory-model/scripts/parseargs.sh +++ b/tools/memory-model/scripts/parseargs.sh @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0+ # -# the corresponding .litmus.out file, and does not judge the result. +# Parse arguments common to the various scripts. # # . scripts/parseargs.sh # @@ -9,7 +9,7 @@ # # Copyright IBM Corporation, 2018 # -# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> +# Author: Paul E. McKenney <paulmck@linux.ibm.com> T=/tmp/parseargs.sh.$$ mkdir $T @@ -27,6 +27,7 @@ initparam () { initparam LKMM_DESTDIR "." initparam LKMM_HERD_OPTIONS "-conf linux-kernel.cfg" +initparam LKMM_HW_MAP_FILE "" initparam LKMM_JOBS `getconf _NPROCESSORS_ONLN` initparam LKMM_PROCS "3" initparam LKMM_TIMEOUT "1m" @@ -37,10 +38,11 @@ usagehelp () { echo "Usage $scriptname [ arguments ]" echo " --destdir path (place for .litmus.out, default by .litmus)" echo " --herdopts -conf linux-kernel.cfg ..." + echo " --hw AArch64" echo " --jobs N (number of jobs, default one per CPU)" echo " --procs N (litmus tests with at most this many processes)" echo " --timeout N (herd7 timeout (e.g., 10s, 1m, 2hr, 1d, '')" - echo "Defaults: --destdir '$LKMM_DESTDIR_DEF' --herdopts '$LKMM_HERD_OPTIONS_DEF' --jobs '$LKMM_JOBS_DEF' --procs '$LKMM_PROCS_DEF' --timeout '$LKMM_TIMEOUT_DEF'" + echo "Defaults: --destdir '$LKMM_DESTDIR_DEF' --herdopts '$LKMM_HERD_OPTIONS_DEF' --hw '$LKMM_HW_MAP_FILE' --jobs '$LKMM_JOBS_DEF' --procs '$LKMM_PROCS_DEF' --timeout '$LKMM_TIMEOUT_DEF'" exit 1 } @@ -81,7 +83,7 @@ do echo "Cannot create directory --destdir '$LKMM_DESTDIR'" usage fi - if test -d "$LKMM_DESTDIR" -a -w "$LKMM_DESTDIR" -a -x "$LKMM_DESTDIR" + if test -d "$LKMM_DESTDIR" -a -x "$LKMM_DESTDIR" then : else @@ -95,6 +97,11 @@ do LKMM_HERD_OPTIONS="$2" shift ;; + --hw) + checkarg --hw "(.map file architecture name)" "$#" "$2" '^[A-Za-z0-9_-]\+' '^--' + LKMM_HW_MAP_FILE="$2" + shift + ;; -j[1-9]*) njobs="`echo $1 | sed -e 's/^-j//'`" trailchars="`echo $njobs | sed -e 's/[0-9]\+\(.*\)$/\1/'`" @@ -106,7 +113,7 @@ do LKMM_JOBS="`echo $njobs | sed -e 's/^\([0-9]\+\).*$/\1/'`" ;; --jobs|--job|-j) - checkarg --jobs "(number)" "$#" "$2" '^[1-9][0-9]\+$' '^--' + checkarg --jobs "(number)" "$#" "$2" '^[1-9][0-9]*$' '^--' LKMM_JOBS="$2" shift ;; @@ -120,6 +127,10 @@ do LKMM_TIMEOUT="$2" shift ;; + --) + shift + break + ;; *) echo Unknown argument $1 usage diff --git a/tools/memory-model/scripts/runlitmus.sh b/tools/memory-model/scripts/runlitmus.sh new file mode 100755 index 000000000000..94608d4b6502 --- /dev/null +++ b/tools/memory-model/scripts/runlitmus.sh @@ -0,0 +1,80 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0+ +# +# Without the -hw argument, runs a herd7 test and outputs verification +# results to a file whose name is that of the specified litmus test, +# but with ".out" appended. +# +# If the --hw argument is specified, this script translates the .litmus +# C-language file to the specified type of assembly and verifies that. +# But in this case, litmus tests using complex synchronization (such as +# locking, RCU, and SRCU) are cheerfully ignored. +# +# Either way, return the status of the herd7 command. +# +# Usage: +# runlitmus.sh file.litmus +# +# Run this in the directory containing the memory model, specifying the +# pathname of the litmus test to check. The caller is expected to have +# properly set up the LKMM environment variables. +# +# Copyright IBM Corporation, 2019 +# +# Author: Paul E. McKenney <paulmck@linux.ibm.com> + +litmus=$1 +if test -f "$litmus" -a -r "$litmus" +then + : +else + echo ' !!! ' error: \"$litmus\" is not a readable file + exit 255 +fi + +if test -z "$LKMM_HW_MAP_FILE" -o ! -e $LKMM_DESTDIR/$litmus.out +then + # LKMM run + herdoptions=${LKMM_HERD_OPTIONS--conf linux-kernel.cfg} + echo Herd options: $herdoptions > $LKMM_DESTDIR/$litmus.out + /usr/bin/time $LKMM_TIMEOUT_CMD herd7 $herdoptions $litmus >> $LKMM_DESTDIR/$litmus.out 2>&1 + ret=$? + if test -z "$LKMM_HW_MAP_FILE" + then + exit $ret + fi + echo " --- " Automatically generated LKMM output for '"'--hw $LKMM_HW_MAP_FILE'"' run +fi + +# Hardware run + +T=/tmp/checklitmushw.sh.$$ +trap 'rm -rf $T' 0 2 +mkdir $T + +# Generate filenames +mapfile="Linux2${LKMM_HW_MAP_FILE}.map" +themefile="$T/${LKMM_HW_MAP_FILE}.theme" +herdoptions="-model $LKMM_HW_CAT_FILE" +hwlitmus=`echo $litmus | sed -e 's/\.litmus$/.litmus.'${LKMM_HW_MAP_FILE}'/'` +hwlitmusfile=`echo $hwlitmus | sed -e 's,^.*/,,'` + +# Don't run on litmus tests with complex synchronization +if ! scripts/simpletest.sh $litmus +then + echo ' --- ' error: \"$litmus\" contains locking, RCU, or SRCU + exit 254 +fi + +# Generate the assembly code and run herd7 on it. +gen_theme7 -n 10 -map $mapfile -call Linux.call > $themefile +jingle7 -v -theme $themefile $litmus > $LKMM_DESTDIR/$hwlitmus 2> $T/$hwlitmusfile.jingle7.out +if grep -q "Generated 0 tests" $T/$hwlitmusfile.jingle7.out +then + echo ' !!! ' jingle7 failed, errors in $hwlitmus.err + cp $T/$hwlitmusfile.jingle7.out $LKMM_DESTDIR/$hwlitmus.err + exit 253 +fi +/usr/bin/time $LKMM_TIMEOUT_CMD herd7 -unroll 0 $LKMM_DESTDIR/$hwlitmus > $LKMM_DESTDIR/$hwlitmus.out 2>&1 + +exit $? diff --git a/tools/memory-model/scripts/runlitmushist.sh b/tools/memory-model/scripts/runlitmushist.sh index 6ed376f495bb..c6c2bdc67a50 100755 --- a/tools/memory-model/scripts/runlitmushist.sh +++ b/tools/memory-model/scripts/runlitmushist.sh @@ -13,7 +13,9 @@ # # Copyright IBM Corporation, 2018 # -# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> +# Author: Paul E. McKenney <paulmck@linux.ibm.com> + +. scripts/hwfnseg.sh T=/tmp/runlitmushist.sh.$$ trap 'rm -rf $T' 0 @@ -30,15 +32,12 @@ fi # Prefixes for per-CPU scripts for ((i=0;i<$LKMM_JOBS;i++)) do - echo dir="$LKMM_DESTDIR" > $T/$i.sh echo T=$T >> $T/$i.sh - echo herdoptions=\"$LKMM_HERD_OPTIONS\" >> $T/$i.sh cat << '___EOF___' >> $T/$i.sh runtest () { - echo ' ... ' /usr/bin/time $LKMM_TIMEOUT_CMD herd7 $herdoptions $1 '>' $dir/$1.out '2>&1' - if /usr/bin/time $LKMM_TIMEOUT_CMD herd7 $herdoptions $1 > $dir/$1.out 2>&1 + if scripts/runlitmus.sh $1 then - if ! grep -q '^Observation ' $dir/$1.out + if ! grep -q '^Observation ' $LKMM_DESTDIR/$1$2.out then echo ' !!! Herd failed, no Observation:' $1 fi @@ -47,10 +46,16 @@ do if test "$exitcode" -eq 124 then exitmsg="timed out" + elif test "$exitcode" -eq 253 + then + exitmsg= else exitmsg="failed, exit code $exitcode" fi - echo ' !!! Herd' ${exitmsg}: $1 + if test -n "$exitmsg" + then + echo ' !!! Herd' ${exitmsg}: $1 + fi fi } ___EOF___ @@ -59,11 +64,13 @@ done awk -v q="'" -v b='\\' ' { print "echo `grep " q "^P[0-9]" b "+(" q " " $0 " | tail -1 | sed -e " q "s/^P" b "([0-9]" b "+" b ")(.*$/" b "1/" q "` " $0 -}' | bash | -sort -k1n | -awk -v ncpu=$LKMM_JOBS -v t=$T ' +}' | sh | sort -k1n | +awk -v dq='"' -v hwfnseg="$hwfnseg" -v ncpu="$LKMM_JOBS" -v t="$T" ' { - print "runtest " $2 >> t "/" NR % ncpu ".sh"; + print "if test -z " dq hwfnseg dq " || scripts/simpletest.sh " dq $2 dq + print "then" + print "\techo runtest " dq $2 dq " " hwfnseg " >> " t "/" NR % ncpu ".sh"; + print "fi" } END { diff --git a/tools/memory-model/scripts/simpletest.sh b/tools/memory-model/scripts/simpletest.sh new file mode 100755 index 000000000000..7edc5d361665 --- /dev/null +++ b/tools/memory-model/scripts/simpletest.sh @@ -0,0 +1,35 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0+ +# +# Give zero status if this is a simple test and non-zero otherwise. +# Simple tests do not contain locking, RCU, or SRCU. +# +# Usage: +# simpletest.sh file.litmus +# +# Copyright IBM Corporation, 2019 +# +# Author: Paul E. McKenney <paulmck@linux.ibm.com> + + +litmus=$1 + +if test -f "$litmus" -a -r "$litmus" +then + : +else + echo ' --- ' error: \"$litmus\" is not a readable file + exit 255 +fi +exclude="^[[:space:]]*\(" +exclude="${exclude}spin_lock(\|spin_unlock(\|spin_trylock(\|spin_is_locked(" +exclude="${exclude}\|rcu_read_lock(\|rcu_read_unlock(" +exclude="${exclude}\|synchronize_rcu(\|synchronize_rcu_expedited(" +exclude="${exclude}\|srcu_read_lock(\|srcu_read_unlock(" +exclude="${exclude}\|synchronize_srcu(\|synchronize_srcu_expedited(" +exclude="${exclude}\)" +if grep -q $exclude $litmus +then + exit 255 +fi +exit 0 diff --git a/tools/vm/.gitignore b/tools/mm/.gitignore index 922879f93fc8..922879f93fc8 100644 --- a/tools/vm/.gitignore +++ b/tools/mm/.gitignore diff --git a/tools/vm/Makefile b/tools/mm/Makefile index 9860622cbb15..6c1da51f4177 100644 --- a/tools/vm/Makefile +++ b/tools/mm/Makefile @@ -8,8 +8,8 @@ TARGETS=page-types slabinfo page_owner_sort LIB_DIR = ../lib/api LIBS = $(LIB_DIR)/libapi.a -CFLAGS = -Wall -Wextra -I../lib/ -LDFLAGS = $(LIBS) +CFLAGS += -Wall -Wextra -I../lib/ +LDFLAGS += $(LIBS) all: $(TARGETS) diff --git a/tools/vm/page-types.c b/tools/mm/page-types.c index 381dcc00cb62..381dcc00cb62 100644 --- a/tools/vm/page-types.c +++ b/tools/mm/page-types.c diff --git a/tools/vm/page_owner_sort.c b/tools/mm/page_owner_sort.c index ce860ab94162..99798894b879 100644 --- a/tools/vm/page_owner_sort.c +++ b/tools/mm/page_owner_sort.c @@ -246,15 +246,16 @@ static int search_pattern(regex_t *pattern, char *pattern_str, char *buf) return 0; } -static void check_regcomp(regex_t *pattern, const char *regex) +static bool check_regcomp(regex_t *pattern, const char *regex) { int err; err = regcomp(pattern, regex, REG_EXTENDED | REG_NEWLINE); if (err != 0 || pattern->re_nsub != 1) { fprintf(stderr, "Invalid pattern %s code %d\n", regex, err); - exit(1); + return false; } + return true; } static char **explode(char sep, const char *str, int *size) @@ -494,28 +495,28 @@ static bool is_need(char *buf) return true; } -static void add_list(char *buf, int len, char *ext_buf) +static bool add_list(char *buf, int len, char *ext_buf) { if (list_size != 0 && len == list[list_size-1].len && memcmp(buf, list[list_size-1].txt, len) == 0) { list[list_size-1].num++; list[list_size-1].page_num += get_page_num(buf); - return; + return true; } if (list_size == max_size) { fprintf(stderr, "max_size too small??\n"); - exit(1); + return false; } if (!is_need(buf)) - return; + return true; list[list_size].pid = get_pid(buf); list[list_size].tgid = get_tgid(buf); list[list_size].comm = get_comm(buf); list[list_size].txt = malloc(len+1); if (!list[list_size].txt) { fprintf(stderr, "Out of memory\n"); - exit(1); + return false; } memcpy(list[list_size].txt, buf, len); list[list_size].txt[len] = 0; @@ -534,6 +535,7 @@ static void add_list(char *buf, int len, char *ext_buf) printf("loaded %d\r", list_size); fflush(stdout); } + return true; } static bool parse_cull_args(const char *arg_str) @@ -790,12 +792,19 @@ int main(int argc, char **argv) exit(1); } - check_regcomp(&order_pattern, "order\\s*([0-9]*),"); - check_regcomp(&pid_pattern, "pid\\s*([0-9]*),"); - check_regcomp(&tgid_pattern, "tgid\\s*([0-9]*) "); - check_regcomp(&comm_pattern, "tgid\\s*[0-9]*\\s*\\((.*)\\),\\s*ts"); - check_regcomp(&ts_nsec_pattern, "ts\\s*([0-9]*)\\s*ns,"); - check_regcomp(&free_ts_nsec_pattern, "free_ts\\s*([0-9]*)\\s*ns"); + if (!check_regcomp(&order_pattern, "order\\s*([0-9]*),")) + goto out_order; + if (!check_regcomp(&pid_pattern, "pid\\s*([0-9]*),")) + goto out_pid; + if (!check_regcomp(&tgid_pattern, "tgid\\s*([0-9]*) ")) + goto out_tgid; + if (!check_regcomp(&comm_pattern, "tgid\\s*[0-9]*\\s*\\((.*)\\),\\s*ts")) + goto out_comm; + if (!check_regcomp(&ts_nsec_pattern, "ts\\s*([0-9]*)\\s*ns,")) + goto out_ts; + if (!check_regcomp(&free_ts_nsec_pattern, "free_ts\\s*([0-9]*)\\s*ns")) + goto out_free_ts; + fstat(fileno(fin), &st); max_size = st.st_size / 100; /* hack ... */ @@ -804,7 +813,7 @@ int main(int argc, char **argv) ext_buf = malloc(BUF_SIZE); if (!list || !buf || !ext_buf) { fprintf(stderr, "Out of memory\n"); - exit(1); + goto out_free; } for ( ; ; ) { @@ -812,7 +821,8 @@ int main(int argc, char **argv) if (buf_len < 0) break; - add_list(buf, buf_len, ext_buf); + if (!add_list(buf, buf_len, ext_buf)) + goto out_free; } printf("loaded %d\n", list_size); @@ -847,7 +857,7 @@ int main(int argc, char **argv) if (cull & CULL_PID || filter & FILTER_PID) fprintf(fout, ", PID %d", list[i].pid); if (cull & CULL_TGID || filter & FILTER_TGID) - fprintf(fout, ", TGID %d", list[i].pid); + fprintf(fout, ", TGID %d", list[i].tgid); if (cull & CULL_COMM || filter & FILTER_COMM) fprintf(fout, ", task_comm_name: %s", list[i].comm); if (cull & CULL_ALLOCATOR) { @@ -862,11 +872,26 @@ int main(int argc, char **argv) fprintf(fout, "\n"); } } - regfree(&order_pattern); - regfree(&pid_pattern); - regfree(&tgid_pattern); - regfree(&comm_pattern); - regfree(&ts_nsec_pattern); + +out_free: + if (ext_buf) + free(ext_buf); + if (buf) + free(buf); + if (list) + free(list); +out_free_ts: regfree(&free_ts_nsec_pattern); +out_ts: + regfree(&ts_nsec_pattern); +out_comm: + regfree(&comm_pattern); +out_tgid: + regfree(&tgid_pattern); +out_pid: + regfree(&pid_pattern); +out_order: + regfree(&order_pattern); + return 0; } diff --git a/tools/vm/slabinfo-gnuplot.sh b/tools/mm/slabinfo-gnuplot.sh index 873a892147e5..873a892147e5 100644 --- a/tools/vm/slabinfo-gnuplot.sh +++ b/tools/mm/slabinfo-gnuplot.sh diff --git a/tools/vm/slabinfo.c b/tools/mm/slabinfo.c index cfaeaea71042..cfaeaea71042 100644 --- a/tools/vm/slabinfo.c +++ b/tools/mm/slabinfo.c diff --git a/tools/net/ynl/cli.py b/tools/net/ynl/cli.py index db410b74d539..ffaa8038aa8c 100755 --- a/tools/net/ynl/cli.py +++ b/tools/net/ynl/cli.py @@ -1,5 +1,5 @@ #!/usr/bin/env python3 -# SPDX-License-Identifier: BSD-3-Clause +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause import argparse import json diff --git a/tools/net/ynl/lib/.gitignore b/tools/net/ynl/lib/.gitignore new file mode 100644 index 000000000000..c18dd8d83cee --- /dev/null +++ b/tools/net/ynl/lib/.gitignore @@ -0,0 +1 @@ +__pycache__/ diff --git a/tools/net/ynl/lib/__init__.py b/tools/net/ynl/lib/__init__.py index 3c73f59eabab..4b3797fe784b 100644 --- a/tools/net/ynl/lib/__init__.py +++ b/tools/net/ynl/lib/__init__.py @@ -1,7 +1,8 @@ -# SPDX-License-Identifier: BSD-3-Clause +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause -from .nlspec import SpecAttr, SpecAttrSet, SpecFamily, SpecOperation +from .nlspec import SpecAttr, SpecAttrSet, SpecEnumEntry, SpecEnumSet, \ + SpecFamily, SpecOperation from .ynl import YnlFamily -__all__ = ["SpecAttr", "SpecAttrSet", "SpecFamily", "SpecOperation", - "YnlFamily"] +__all__ = ["SpecAttr", "SpecAttrSet", "SpecEnumEntry", "SpecEnumSet", + "SpecFamily", "SpecOperation", "YnlFamily"] diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/lib/nlspec.py index e204679ad8b7..d04450c2a44a 100644 --- a/tools/net/ynl/lib/nlspec.py +++ b/tools/net/ynl/lib/nlspec.py @@ -1,9 +1,8 @@ -# SPDX-License-Identifier: BSD-3-Clause +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause import collections import importlib import os -import traceback import yaml @@ -58,6 +57,92 @@ class SpecElement: pass +class SpecEnumEntry(SpecElement): + """ Entry within an enum declared in the Netlink spec. + + Attributes: + doc documentation string + enum_set back reference to the enum + value numerical value of this enum (use accessors in most situations!) + + Methods: + raw_value raw value, i.e. the id in the enum, unlike user value which is a mask for flags + user_value user value, same as raw value for enums, for flags it's the mask + """ + def __init__(self, enum_set, yaml, prev, value_start): + if isinstance(yaml, str): + yaml = {'name': yaml} + super().__init__(enum_set.family, yaml) + + self.doc = yaml.get('doc', '') + self.enum_set = enum_set + + if 'value' in yaml: + self.value = yaml['value'] + elif prev: + self.value = prev.value + 1 + else: + self.value = value_start + + def has_doc(self): + return bool(self.doc) + + def raw_value(self): + return self.value + + def user_value(self): + if self.enum_set['type'] == 'flags': + return 1 << self.value + else: + return self.value + + +class SpecEnumSet(SpecElement): + """ Enum type + + Represents an enumeration (list of numerical constants) + as declared in the "definitions" section of the spec. + + Attributes: + type enum or flags + entries entries by name + entries_by_val entries by value + Methods: + get_mask for flags compute the mask of all defined values + """ + def __init__(self, family, yaml): + super().__init__(family, yaml) + + self.type = yaml['type'] + + prev_entry = None + value_start = self.yaml.get('value-start', 0) + self.entries = dict() + self.entries_by_val = dict() + for entry in self.yaml['entries']: + e = self.new_entry(entry, prev_entry, value_start) + self.entries[e.name] = e + self.entries_by_val[e.raw_value()] = e + prev_entry = e + + def new_entry(self, entry, prev_entry, value_start): + return SpecEnumEntry(self, entry, prev_entry, value_start) + + def has_doc(self): + if 'doc' in self.yaml: + return True + for entry in self.entries.values(): + if entry.has_doc(): + return True + return False + + def get_mask(self): + mask = 0 + for e in self.entries.values(): + mask += e.user_value() + return mask + + class SpecAttr(SpecElement): """ Single Netlink atttribute type @@ -96,15 +181,22 @@ class SpecAttrSet(SpecElement): self.attrs = collections.OrderedDict() self.attrs_by_val = collections.OrderedDict() - val = 0 - for elem in self.yaml['attributes']: - if 'value' in elem: - val = elem['value'] + if self.subset_of is None: + val = 1 + for elem in self.yaml['attributes']: + if 'value' in elem: + val = elem['value'] - attr = self.new_attr(elem, val) - self.attrs[attr.name] = attr - self.attrs_by_val[attr.value] = attr - val += 1 + attr = self.new_attr(elem, val) + self.attrs[attr.name] = attr + self.attrs_by_val[attr.value] = attr + val += 1 + else: + real_set = family.attr_sets[self.subset_of] + for elem in self.yaml['attributes']: + attr = real_set[elem['name']] + self.attrs[attr.name] = attr + self.attrs_by_val[attr.value] = attr def new_attr(self, elem, value): return SpecAttr(self.family, self, elem, value) @@ -182,14 +274,23 @@ class SpecFamily(SpecElement): Attributes: proto protocol type (e.g. genetlink) + license spec license (loaded from an SPDX tag on the spec) attr_sets dict of attribute sets msgs dict of all messages (index by name) msgs_by_value dict of all messages (indexed by name) ops dict of all valid requests / responses + consts dict of all constants/enums """ def __init__(self, spec_path, schema_path=None): with open(spec_path, "r") as stream: + prefix = '# SPDX-License-Identifier: ' + first = stream.readline().strip() + if not first.startswith(prefix): + raise Exception('SPDX license tag required in the spec') + self.license = first[len(prefix):] + + stream.seek(0) spec = yaml.safe_load(stream) self._resolution_list = [] @@ -216,6 +317,7 @@ class SpecFamily(SpecElement): self.req_by_value = collections.OrderedDict() self.rsp_by_value = collections.OrderedDict() self.ops = collections.OrderedDict() + self.consts = collections.OrderedDict() last_exception = None while len(self._resolution_list) > 0: @@ -234,8 +336,10 @@ class SpecFamily(SpecElement): resolved.append(elem) if len(resolved) == 0: - traceback.print_exception(last_exception) - raise Exception("Could not resolve any spec element, infinite loop?") + raise last_exception + + def new_enum(self, elem): + return SpecEnumSet(self, elem) def new_attr_set(self, elem): return SpecAttrSet(self, elem) @@ -247,7 +351,7 @@ class SpecFamily(SpecElement): self._resolution_list.append(elem) def _dictify_ops_unified(self): - val = 0 + val = 1 for elem in self.yaml['operations']['list']: if 'value' in elem: val = elem['value'] @@ -258,7 +362,7 @@ class SpecFamily(SpecElement): self.msgs[op.name] = op def _dictify_ops_directional(self): - req_val = rsp_val = 0 + req_val = rsp_val = 1 for elem in self.yaml['operations']['list']: if 'notify' in elem: if 'value' in elem: @@ -291,6 +395,13 @@ class SpecFamily(SpecElement): def resolve(self): self.resolve_up(super()) + definitions = self.yaml.get('definitions', []) + for elem in definitions: + if elem['type'] == 'enum' or elem['type'] == 'flags': + self.consts[elem['name']] = self.new_enum(elem) + else: + self.consts[elem['name']] = elem + for elem in self.yaml['attribute-sets']: attr_set = self.new_attr_set(elem) self.attr_sets[elem['name']] = attr_set diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index 1c7411ee04dc..32536e1f9064 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: BSD-3-Clause +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause import functools import os @@ -200,7 +200,7 @@ def _genl_msg(nl_type, nl_flags, genl_cmd, genl_version, seq=None): if seq is None: seq = random.randint(1, 1024) nlmsg = struct.pack("HHII", nl_type, nl_flags, seq, 0) - genlmsg = struct.pack("bbH", genl_cmd, genl_version, 0) + genlmsg = struct.pack("BBH", genl_cmd, genl_version, 0) return nlmsg + genlmsg @@ -264,7 +264,7 @@ class GenlMsg: self.hdr = nl_msg.raw[0:4] self.raw = nl_msg.raw[4:] - self.genl_cmd, self.genl_version, _ = struct.unpack("bbH", self.hdr) + self.genl_cmd, self.genl_version, _ = struct.unpack("BBH", self.hdr) self.raw_attrs = NlAttrs(self.raw) @@ -303,11 +303,6 @@ class YnlFamily(SpecFamily): self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_CAP_ACK, 1) self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_EXT_ACK, 1) - self._types = dict() - - for elem in self.yaml.get('definitions', []): - self._types[elem['name']] = elem - self.async_msg_ids = set() self.async_msg_queue = [] @@ -353,17 +348,17 @@ class YnlFamily(SpecFamily): def _decode_enum(self, rsp, attr_spec): raw = rsp[attr_spec['name']] - enum = self._types[attr_spec['enum']] + enum = self.consts[attr_spec['enum']] i = attr_spec.get('value-start', 0) if 'enum-as-flags' in attr_spec and attr_spec['enum-as-flags']: value = set() while raw: if raw & 1: - value.add(enum['entries'][i]) + value.add(enum.entries_by_val[i].name) raw >>= 1 i += 1 else: - value = enum['entries'][raw - i] + value = enum.entries_by_val[raw - i].name rsp[attr_spec['name']] = value def _decode(self, attrs, space): diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index 3942f24b9163..c16671a02621 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -1,11 +1,12 @@ #!/usr/bin/env python3 +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) import argparse import collections import os import yaml -from lib import SpecFamily, SpecAttrSet, SpecAttr, SpecOperation +from lib import SpecFamily, SpecAttrSet, SpecAttr, SpecOperation, SpecEnumSet, SpecEnumEntry def c_upper(name): @@ -546,7 +547,7 @@ class Struct: max_val = 0 self.attr_max_val = None for name, attr in self.attr_list: - if attr.value > max_val: + if attr.value >= max_val: max_val = attr.value self.attr_max_val = attr self.attrs[name] = attr @@ -566,97 +567,37 @@ class Struct: self.inherited = [c_lower(x) for x in sorted(self._inherited)] -class EnumEntry: +class EnumEntry(SpecEnumEntry): def __init__(self, enum_set, yaml, prev, value_start): - if isinstance(yaml, str): - self.name = yaml - yaml = {} - self.doc = '' - else: - self.name = yaml['name'] - self.doc = yaml.get('doc', '') - - self.yaml = yaml - self.enum_set = enum_set - self.c_name = c_upper(enum_set.value_pfx + self.name) - - if 'value' in yaml: - self.value = yaml['value'] - if prev: - self.value_change = (self.value != prev.value + 1) - elif prev: - self.value_change = False - self.value = prev.value + 1 + super().__init__(enum_set, yaml, prev, value_start) + + if prev: + self.value_change = (self.value != prev.value + 1) else: - self.value = value_start self.value_change = (self.value != 0) - self.value_change = self.value_change or self.enum_set['type'] == 'flags' - def __getitem__(self, key): - return self.yaml[key] - - def __contains__(self, key): - return key in self.yaml - - def has_doc(self): - return bool(self.doc) + # Added by resolve: + self.c_name = None + delattr(self, "c_name") - # raw value, i.e. the id in the enum, unlike user value which is a mask for flags - def raw_value(self): - return self.value + def resolve(self): + self.resolve_up(super()) - # user value, same as raw value for enums, for flags it's the mask - def user_value(self): - if self.enum_set['type'] == 'flags': - return 1 << self.value - else: - return self.value + self.c_name = c_upper(self.enum_set.value_pfx + self.name) -class EnumSet: +class EnumSet(SpecEnumSet): def __init__(self, family, yaml): - self.yaml = yaml - self.family = family - self.render_name = c_lower(family.name + '-' + yaml['name']) self.enum_name = 'enum ' + self.render_name self.value_pfx = yaml.get('name-prefix', f"{family.name}-{yaml['name']}-") - self.type = yaml['type'] - - prev_entry = None - value_start = self.yaml.get('value-start', 0) - self.entries = {} - self.entry_list = [] - for entry in self.yaml['entries']: - e = EnumEntry(self, entry, prev_entry, value_start) - self.entries[e.name] = e - self.entry_list.append(e) - prev_entry = e - - def __getitem__(self, key): - return self.yaml[key] - - def __contains__(self, key): - return key in self.yaml - - def has_doc(self): - if 'doc' in self.yaml: - return True - for entry in self.entry_list: - if entry.has_doc(): - return True - return False + super().__init__(family, yaml) - def get_mask(self): - mask = 0 - idx = self.yaml.get('value-start', 0) - for _ in self.entry_list: - mask |= 1 << idx - idx += 1 - return mask + def new_entry(self, entry, prev_entry, value_start): + return EnumEntry(self, entry, prev_entry, value_start) class AttrSet(SpecAttrSet): @@ -791,8 +732,6 @@ class Family(SpecFamily): self.mcgrps = self.yaml.get('mcast-groups', {'list': []}) - self.consts = dict() - self.hooks = dict() for when in ['pre', 'post']: self.hooks[when] = dict() @@ -819,6 +758,9 @@ class Family(SpecFamily): if self.kernel_policy == 'global': self._load_global_policy() + def new_enum(self, elem): + return EnumSet(self, elem) + def new_attr_set(self, elem): return AttrSet(self, elem) @@ -836,12 +778,6 @@ class Family(SpecFamily): } def _dictify(self): - for elem in self.yaml['definitions']: - if elem['type'] == 'enum' or elem['type'] == 'flags': - self.consts[elem['name']] = EnumSet(self, elem) - else: - self.consts[elem['name']] = elem - ntf = [] for msg in self.msgs.values(): if 'notify' in msg: @@ -1979,7 +1915,7 @@ def render_uapi(family, cw): if 'doc' in enum: doc = ' - ' + enum['doc'] cw.write_doc_line(enum.enum_name + doc) - for entry in enum.entry_list: + for entry in enum.entries.values(): if entry.has_doc(): doc = '@' + entry.c_name + ': ' + entry['doc'] cw.write_doc_line(doc) @@ -1987,7 +1923,7 @@ def render_uapi(family, cw): uapi_enum_start(family, cw, const, 'name') name_pfx = const.get('name-prefix', f"{family.name}-{const['name']}-") - for entry in enum.entry_list: + for entry in enum.entries.values(): suffix = ',' if entry.value_change: suffix = f" = {entry.user_value()}" + suffix @@ -1995,9 +1931,14 @@ def render_uapi(family, cw): if const.get('render-max', False): cw.nl() - max_name = c_upper(name_pfx + 'max') - cw.p('__' + max_name + ',') - cw.p(max_name + ' = (__' + max_name + ' - 1)') + if const['type'] == 'flags': + max_name = c_upper(name_pfx + 'mask') + max_val = f' = {enum.get_mask()},' + cw.p(max_name + max_val) + else: + max_name = c_upper(name_pfx + 'max') + cw.p('__' + max_name + ',') + cw.p(max_name + ' = (__' + max_name + ' - 1)') cw.block_end(line=';') cw.nl() elif const['type'] == 'const': @@ -2044,14 +1985,17 @@ def render_uapi(family, cw): max_value = f"({cnt_name} - 1)" uapi_enum_start(family, cw, family['operations'], 'enum-name') + val = 0 for op in family.msgs.values(): if separate_ntf and ('notify' in op or 'event' in op): continue suffix = ',' - if 'value' in op: - suffix = f" = {op['value']}," + if op.value != val: + suffix = f" = {op.value}," + val = op.value cw.p(op.enum_name + suffix) + val += 1 cw.nl() cw.p(cnt_name + ('' if max_by_define else ',')) if not max_by_define: @@ -2115,6 +2059,10 @@ def main(): try: parsed = Family(args.spec) + if parsed.license != '((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)': + print('Spec license:', parsed.license) + print('License must be: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)') + os.sys.exit(1) except yaml.YAMLError as exc: print(exc) os.sys.exit(1) @@ -2123,13 +2071,10 @@ def main(): cw = CodeWriter(BaseNlLib(), out_file) _, spec_kernel = find_kernel_root(args.spec) - if args.mode == 'uapi': - cw.p('/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */') + if args.mode == 'uapi' or args.header: + cw.p(f'/* SPDX-License-Identifier: {parsed.license} */') else: - if args.header: - cw.p('/* SPDX-License-Identifier: BSD-3-Clause */') - else: - cw.p('// SPDX-License-Identifier: BSD-3-Clause') + cw.p(f'// SPDX-License-Identifier: {parsed.license}') cw.p("/* Do not edit directly, auto-generated from: */") cw.p(f"/*\t{spec_kernel} */") cw.p(f"/* YNL-GEN {args.mode} {'header' if args.header else 'source'} */") diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh index 43989ae48ed0..74f5de1c2399 100755 --- a/tools/net/ynl/ynl-regen.sh +++ b/tools/net/ynl/ynl-regen.sh @@ -1,5 +1,5 @@ #!/bin/bash -# SPDX-License-Identifier: BSD-3-Clause +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause TOOL=$(dirname $(realpath $0))/ynl-gen-c.py diff --git a/tools/objtool/.gitignore b/tools/objtool/.gitignore index 14236db3677f..4faa4dd72f35 100644 --- a/tools/objtool/.gitignore +++ b/tools/objtool/.gitignore @@ -2,3 +2,4 @@ arch/x86/lib/inat-tables.c /objtool fixdep +libsubcmd/ diff --git a/tools/objtool/Build b/tools/objtool/Build index 33f2ee5a46d3..a3cdf8af6635 100644 --- a/tools/objtool/Build +++ b/tools/objtool/Build @@ -16,8 +16,6 @@ objtool-y += libctype.o objtool-y += str_error_r.o objtool-y += librbtree.o -CFLAGS += -I$(srctree)/tools/lib - $(OUTPUT)libstring.o: ../lib/string.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) diff --git a/tools/objtool/Documentation/objtool.txt b/tools/objtool/Documentation/objtool.txt index 8a671902a187..744db4218e7a 100644 --- a/tools/objtool/Documentation/objtool.txt +++ b/tools/objtool/Documentation/objtool.txt @@ -181,7 +181,7 @@ b) ORC (Oops Rewind Capability) unwind table generation band. So it doesn't affect runtime performance and it can be reliable even when interrupts or exceptions are involved. - For more details, see Documentation/x86/orc-unwinder.rst. + For more details, see Documentation/arch/x86/orc-unwinder.rst. c) Higher live patching compatibility rate @@ -410,6 +410,14 @@ the objtool maintainers. can remove this warning by putting the ANNOTATE_INTRA_FUNCTION_CALL directive right before the call. +12. file.o: warning: func(): not an indirect call target + + This means that objtool is running with --ibt and a function expected + to be an indirect call target is not. In particular, this happens for + init_module() or cleanup_module() if a module relies on these special + names and does not use module_init() / module_exit() macros to create + them. + If the error doesn't seem to make sense, it could be a bug in objtool. Feel free to ask the objtool maintainer for help. diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index a3a9cc24e0e3..83b100c1e7f6 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -2,19 +2,18 @@ include ../scripts/Makefile.include include ../scripts/Makefile.arch -# always use the host compiler -AR = $(HOSTAR) -CC = $(HOSTCC) -LD = $(HOSTLD) - ifeq ($(srctree),) srctree := $(patsubst %/,%,$(dir $(CURDIR))) srctree := $(patsubst %/,%,$(dir $(srctree))) endif -SUBCMD_SRCDIR = $(srctree)/tools/lib/subcmd/ -LIBSUBCMD_OUTPUT = $(or $(OUTPUT),$(CURDIR)/) -LIBSUBCMD = $(LIBSUBCMD_OUTPUT)libsubcmd.a +LIBSUBCMD_DIR = $(srctree)/tools/lib/subcmd/ +ifneq ($(OUTPUT),) + LIBSUBCMD_OUTPUT = $(abspath $(OUTPUT))/libsubcmd +else + LIBSUBCMD_OUTPUT = $(CURDIR)/libsubcmd +endif +LIBSUBCMD = $(LIBSUBCMD_OUTPUT)/libsubcmd.a OBJTOOL := $(OUTPUT)objtool OBJTOOL_IN := $(OBJTOOL)-in.o @@ -28,16 +27,29 @@ INCLUDES := -I$(srctree)/tools/include \ -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \ -I$(srctree)/tools/arch/$(SRCARCH)/include \ -I$(srctree)/tools/objtool/include \ - -I$(srctree)/tools/objtool/arch/$(SRCARCH)/include + -I$(srctree)/tools/objtool/arch/$(SRCARCH)/include \ + -I$(LIBSUBCMD_OUTPUT)/include +# Note, EXTRA_WARNINGS here was determined for CC and not HOSTCC, it +# is passed here to match a legacy behavior. WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed -Wno-nested-externs -CFLAGS := -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) $(LIBELF_FLAGS) -LDFLAGS += $(LIBELF_LIBS) $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS) +OBJTOOL_CFLAGS := -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) $(LIBELF_FLAGS) +OBJTOOL_LDFLAGS := $(LIBELF_LIBS) $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS) # Allow old libelf to be used: -elfshdr := $(shell echo '$(pound)include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | grep elf_getshdr) -CFLAGS += $(if $(elfshdr),,-DLIBELF_USE_DEPRECATED) +elfshdr := $(shell echo '$(pound)include <libelf.h>' | $(HOSTCC) $(OBJTOOL_CFLAGS) -x c -E - | grep elf_getshdr) +OBJTOOL_CFLAGS += $(if $(elfshdr),,-DLIBELF_USE_DEPRECATED) + +# Always want host compilation. +HOST_OVERRIDES := CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" AWK = awk +MKDIR = mkdir + +ifeq ($(V),1) + Q = +else + Q = @ +endif BUILD_ORC := n @@ -49,21 +61,33 @@ export BUILD_ORC export srctree OUTPUT CFLAGS SRCARCH AWK include $(srctree)/tools/build/Makefile.include -$(OBJTOOL_IN): fixdep FORCE - @$(CONFIG_SHELL) ./sync-check.sh - @$(MAKE) $(build)=objtool +$(OBJTOOL_IN): fixdep $(LIBSUBCMD) FORCE + $(Q)$(CONFIG_SHELL) ./sync-check.sh + $(Q)$(MAKE) $(build)=objtool $(HOST_OVERRIDES) CFLAGS="$(OBJTOOL_CFLAGS)" \ + LDFLAGS="$(OBJTOOL_LDFLAGS)" + $(OBJTOOL): $(LIBSUBCMD) $(OBJTOOL_IN) - $(QUIET_LINK)$(CC) $(OBJTOOL_IN) $(LDFLAGS) -o $@ + $(QUIET_LINK)$(HOSTCC) $(OBJTOOL_IN) $(OBJTOOL_LDFLAGS) -o $@ + + +$(LIBSUBCMD_OUTPUT): + $(Q)$(MKDIR) -p $@ +$(LIBSUBCMD): fixdep $(LIBSUBCMD_OUTPUT) FORCE + $(Q)$(MAKE) -C $(LIBSUBCMD_DIR) O=$(LIBSUBCMD_OUTPUT) \ + DESTDIR=$(LIBSUBCMD_OUTPUT) prefix= subdir= \ + $(HOST_OVERRIDES) EXTRA_CFLAGS="$(OBJTOOL_CFLAGS)" \ + $@ install_headers -$(LIBSUBCMD): fixdep FORCE - $(Q)$(MAKE) -C $(SUBCMD_SRCDIR) OUTPUT=$(LIBSUBCMD_OUTPUT) +$(LIBSUBCMD)-clean: + $(call QUIET_CLEAN, libsubcmd) + $(Q)$(RM) -r -- $(LIBSUBCMD_OUTPUT) -clean: +clean: $(LIBSUBCMD)-clean $(call QUIET_CLEAN, objtool) $(RM) $(OBJTOOL) $(Q)find $(OUTPUT) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete - $(Q)$(RM) $(OUTPUT)arch/x86/lib/inat-tables.c $(OUTPUT)fixdep $(LIBSUBCMD) + $(Q)$(RM) $(OUTPUT)arch/x86/lib/inat-tables.c $(OUTPUT)fixdep FORCE: diff --git a/tools/objtool/arch/powerpc/decode.c b/tools/objtool/arch/powerpc/decode.c index 9c653805a08a..53b55690f320 100644 --- a/tools/objtool/arch/powerpc/decode.c +++ b/tools/objtool/arch/powerpc/decode.c @@ -41,38 +41,36 @@ const char *arch_ret_insn(int len) int arch_decode_instruction(struct objtool_file *file, const struct section *sec, unsigned long offset, unsigned int maxlen, - unsigned int *len, enum insn_type *type, - unsigned long *immediate, - struct list_head *ops_list) + struct instruction *insn) { unsigned int opcode; enum insn_type typ; unsigned long imm; - u32 insn; + u32 ins; - insn = bswap_if_needed(file->elf, *(u32 *)(sec->data->d_buf + offset)); - opcode = insn >> 26; + ins = bswap_if_needed(file->elf, *(u32 *)(sec->data->d_buf + offset)); + opcode = ins >> 26; typ = INSN_OTHER; imm = 0; switch (opcode) { case 18: /* b[l][a] */ - if ((insn & 3) == 1) /* bl */ + if ((ins & 3) == 1) /* bl */ typ = INSN_CALL; - imm = insn & 0x3fffffc; + imm = ins & 0x3fffffc; if (imm & 0x2000000) imm -= 0x4000000; break; } if (opcode == 1) - *len = 8; + insn->len = 8; else - *len = 4; + insn->len = 4; - *type = typ; - *immediate = imm; + insn->type = typ; + insn->immediate = imm; return 0; } diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index e7b030f7e2a5..9ef024fd648c 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -105,7 +105,7 @@ bool arch_pc_relative_reloc(struct reloc *reloc) #define ADD_OP(op) \ if (!(op = calloc(1, sizeof(*op)))) \ return -1; \ - else for (list_add_tail(&op->list, ops_list); op; op = NULL) + else for (*ops_list = op, ops_list = &op->next; op; op = NULL) /* * Helpers to decode ModRM/SIB: @@ -146,12 +146,11 @@ static bool has_notrack_prefix(struct insn *insn) int arch_decode_instruction(struct objtool_file *file, const struct section *sec, unsigned long offset, unsigned int maxlen, - unsigned int *len, enum insn_type *type, - unsigned long *immediate, - struct list_head *ops_list) + struct instruction *insn) { + struct stack_op **ops_list = &insn->stack_ops; const struct elf *elf = file->elf; - struct insn insn; + struct insn ins; int x86_64, ret; unsigned char op1, op2, op3, prefix, rex = 0, rex_b = 0, rex_r = 0, rex_w = 0, rex_x = 0, @@ -165,42 +164,42 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec if (x86_64 == -1) return -1; - ret = insn_decode(&insn, sec->data->d_buf + offset, maxlen, + ret = insn_decode(&ins, sec->data->d_buf + offset, maxlen, x86_64 ? INSN_MODE_64 : INSN_MODE_32); if (ret < 0) { WARN("can't decode instruction at %s:0x%lx", sec->name, offset); return -1; } - *len = insn.length; - *type = INSN_OTHER; + insn->len = ins.length; + insn->type = INSN_OTHER; - if (insn.vex_prefix.nbytes) + if (ins.vex_prefix.nbytes) return 0; - prefix = insn.prefixes.bytes[0]; + prefix = ins.prefixes.bytes[0]; - op1 = insn.opcode.bytes[0]; - op2 = insn.opcode.bytes[1]; - op3 = insn.opcode.bytes[2]; + op1 = ins.opcode.bytes[0]; + op2 = ins.opcode.bytes[1]; + op3 = ins.opcode.bytes[2]; - if (insn.rex_prefix.nbytes) { - rex = insn.rex_prefix.bytes[0]; + if (ins.rex_prefix.nbytes) { + rex = ins.rex_prefix.bytes[0]; rex_w = X86_REX_W(rex) >> 3; rex_r = X86_REX_R(rex) >> 2; rex_x = X86_REX_X(rex) >> 1; rex_b = X86_REX_B(rex); } - if (insn.modrm.nbytes) { - modrm = insn.modrm.bytes[0]; + if (ins.modrm.nbytes) { + modrm = ins.modrm.bytes[0]; modrm_mod = X86_MODRM_MOD(modrm); modrm_reg = X86_MODRM_REG(modrm) + 8*rex_r; modrm_rm = X86_MODRM_RM(modrm) + 8*rex_b; } - if (insn.sib.nbytes) { - sib = insn.sib.bytes[0]; + if (ins.sib.nbytes) { + sib = ins.sib.bytes[0]; /* sib_scale = X86_SIB_SCALE(sib); */ sib_index = X86_SIB_INDEX(sib) + 8*rex_x; sib_base = X86_SIB_BASE(sib) + 8*rex_b; @@ -254,7 +253,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec break; case 0x70 ... 0x7f: - *type = INSN_JUMP_CONDITIONAL; + insn->type = INSN_JUMP_CONDITIONAL; break; case 0x80 ... 0x83: @@ -278,7 +277,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec if (!rm_is_reg(CFI_SP)) break; - imm = insn.immediate.value; + imm = ins.immediate.value; if (op1 & 2) { /* sign extend */ if (op1 & 1) { /* imm32 */ imm <<= 32; @@ -309,7 +308,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec ADD_OP(op) { op->src.type = OP_SRC_AND; op->src.reg = CFI_SP; - op->src.offset = insn.immediate.value; + op->src.offset = ins.immediate.value; op->dest.type = OP_DEST_REG; op->dest.reg = CFI_SP; } @@ -356,7 +355,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec op->src.reg = CFI_SP; op->dest.type = OP_DEST_REG_INDIRECT; op->dest.reg = modrm_rm; - op->dest.offset = insn.displacement.value; + op->dest.offset = ins.displacement.value; } break; } @@ -389,7 +388,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec op->src.reg = modrm_reg; op->dest.type = OP_DEST_REG_INDIRECT; op->dest.reg = CFI_BP; - op->dest.offset = insn.displacement.value; + op->dest.offset = ins.displacement.value; } break; } @@ -402,7 +401,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec op->src.reg = modrm_reg; op->dest.type = OP_DEST_REG_INDIRECT; op->dest.reg = CFI_SP; - op->dest.offset = insn.displacement.value; + op->dest.offset = ins.displacement.value; } break; } @@ -419,7 +418,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec ADD_OP(op) { op->src.type = OP_SRC_REG_INDIRECT; op->src.reg = CFI_BP; - op->src.offset = insn.displacement.value; + op->src.offset = ins.displacement.value; op->dest.type = OP_DEST_REG; op->dest.reg = modrm_reg; } @@ -432,7 +431,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec ADD_OP(op) { op->src.type = OP_SRC_REG_INDIRECT; op->src.reg = CFI_SP; - op->src.offset = insn.displacement.value; + op->src.offset = ins.displacement.value; op->dest.type = OP_DEST_REG; op->dest.reg = modrm_reg; } @@ -464,7 +463,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec /* lea disp(%src), %dst */ ADD_OP(op) { - op->src.offset = insn.displacement.value; + op->src.offset = ins.displacement.value; if (!op->src.offset) { /* lea (%src), %dst */ op->src.type = OP_SRC_REG; @@ -487,7 +486,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec break; case 0x90: - *type = INSN_NOP; + insn->type = INSN_NOP; break; case 0x9c: @@ -511,39 +510,39 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec if (op2 == 0x01) { if (modrm == 0xca) - *type = INSN_CLAC; + insn->type = INSN_CLAC; else if (modrm == 0xcb) - *type = INSN_STAC; + insn->type = INSN_STAC; } else if (op2 >= 0x80 && op2 <= 0x8f) { - *type = INSN_JUMP_CONDITIONAL; + insn->type = INSN_JUMP_CONDITIONAL; } else if (op2 == 0x05 || op2 == 0x07 || op2 == 0x34 || op2 == 0x35) { /* sysenter, sysret */ - *type = INSN_CONTEXT_SWITCH; + insn->type = INSN_CONTEXT_SWITCH; } else if (op2 == 0x0b || op2 == 0xb9) { /* ud2 */ - *type = INSN_BUG; + insn->type = INSN_BUG; } else if (op2 == 0x0d || op2 == 0x1f) { /* nopl/nopw */ - *type = INSN_NOP; + insn->type = INSN_NOP; } else if (op2 == 0x1e) { if (prefix == 0xf3 && (modrm == 0xfa || modrm == 0xfb)) - *type = INSN_ENDBR; + insn->type = INSN_ENDBR; } else if (op2 == 0x38 && op3 == 0xf8) { - if (insn.prefixes.nbytes == 1 && - insn.prefixes.bytes[0] == 0xf2) { + if (ins.prefixes.nbytes == 1 && + ins.prefixes.bytes[0] == 0xf2) { /* ENQCMD cannot be used in the kernel. */ WARN("ENQCMD instruction at %s:%lx", sec->name, offset); @@ -591,29 +590,29 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec case 0xcc: /* int3 */ - *type = INSN_TRAP; + insn->type = INSN_TRAP; break; case 0xe3: /* jecxz/jrcxz */ - *type = INSN_JUMP_CONDITIONAL; + insn->type = INSN_JUMP_CONDITIONAL; break; case 0xe9: case 0xeb: - *type = INSN_JUMP_UNCONDITIONAL; + insn->type = INSN_JUMP_UNCONDITIONAL; break; case 0xc2: case 0xc3: - *type = INSN_RETURN; + insn->type = INSN_RETURN; break; case 0xc7: /* mov imm, r/m */ if (!opts.noinstr) break; - if (insn.length == 3+4+4 && !strncmp(sec->name, ".init.text", 10)) { + if (ins.length == 3+4+4 && !strncmp(sec->name, ".init.text", 10)) { struct reloc *immr, *disp; struct symbol *func; int idx; @@ -661,17 +660,17 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec case 0xca: /* retf */ case 0xcb: /* retf */ - *type = INSN_CONTEXT_SWITCH; + insn->type = INSN_CONTEXT_SWITCH; break; case 0xe0: /* loopne */ case 0xe1: /* loope */ case 0xe2: /* loop */ - *type = INSN_JUMP_CONDITIONAL; + insn->type = INSN_JUMP_CONDITIONAL; break; case 0xe8: - *type = INSN_CALL; + insn->type = INSN_CALL; /* * For the impact on the stack, a CALL behaves like * a PUSH of an immediate value (the return address). @@ -683,30 +682,30 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec break; case 0xfc: - *type = INSN_CLD; + insn->type = INSN_CLD; break; case 0xfd: - *type = INSN_STD; + insn->type = INSN_STD; break; case 0xff: if (modrm_reg == 2 || modrm_reg == 3) { - *type = INSN_CALL_DYNAMIC; - if (has_notrack_prefix(&insn)) + insn->type = INSN_CALL_DYNAMIC; + if (has_notrack_prefix(&ins)) WARN("notrack prefix found at %s:0x%lx", sec->name, offset); } else if (modrm_reg == 4) { - *type = INSN_JUMP_DYNAMIC; - if (has_notrack_prefix(&insn)) + insn->type = INSN_JUMP_DYNAMIC; + if (has_notrack_prefix(&ins)) WARN("notrack prefix found at %s:0x%lx", sec->name, offset); } else if (modrm_reg == 5) { /* jmpf */ - *type = INSN_CONTEXT_SWITCH; + insn->type = INSN_CONTEXT_SWITCH; } else if (modrm_reg == 6) { @@ -723,7 +722,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec break; } - *immediate = insn.immediate.nbytes ? insn.immediate.value : 0; + insn->immediate = ins.immediate.nbytes ? ins.immediate.value : 0; return 0; } diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index a4f39407bf59..7c175198d09f 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -65,7 +65,7 @@ static int parse_hacks(const struct option *opt, const char *str, int unset) return found ? 0 : -1; } -const struct option check_options[] = { +static const struct option check_options[] = { OPT_GROUP("Actions:"), OPT_CALLBACK_OPTARG('h', "hacks", NULL, NULL, "jump_label,noinstr,skylake", "patch toolchain bugs/limitations", parse_hacks), OPT_BOOLEAN('i', "ibt", &opts.ibt, "validate and annotate IBT"), diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 94b518c12f9a..50ed63f701f1 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -23,7 +23,7 @@ #include <linux/static_call_types.h> struct alternative { - struct list_head list; + struct alternative *next; struct instruction *insn; bool skip_orig; }; @@ -47,27 +47,29 @@ struct instruction *find_insn(struct objtool_file *file, return NULL; } -static struct instruction *next_insn_same_sec(struct objtool_file *file, - struct instruction *insn) +struct instruction *next_insn_same_sec(struct objtool_file *file, + struct instruction *insn) { - struct instruction *next = list_next_entry(insn, list); + if (insn->idx == INSN_CHUNK_MAX) + return find_insn(file, insn->sec, insn->offset + insn->len); - if (!next || &next->list == &file->insn_list || next->sec != insn->sec) + insn++; + if (!insn->len) return NULL; - return next; + return insn; } static struct instruction *next_insn_same_func(struct objtool_file *file, struct instruction *insn) { - struct instruction *next = list_next_entry(insn, list); + struct instruction *next = next_insn_same_sec(file, insn); struct symbol *func = insn_func(insn); if (!func) return NULL; - if (&next->list != &file->insn_list && insn_func(next) == func) + if (next && insn_func(next) == func) return next; /* Check if we're already in the subfunction: */ @@ -78,17 +80,35 @@ static struct instruction *next_insn_same_func(struct objtool_file *file, return find_insn(file, func->cfunc->sec, func->cfunc->offset); } +static struct instruction *prev_insn_same_sec(struct objtool_file *file, + struct instruction *insn) +{ + if (insn->idx == 0) { + if (insn->prev_len) + return find_insn(file, insn->sec, insn->offset - insn->prev_len); + return NULL; + } + + return insn - 1; +} + static struct instruction *prev_insn_same_sym(struct objtool_file *file, - struct instruction *insn) + struct instruction *insn) { - struct instruction *prev = list_prev_entry(insn, list); + struct instruction *prev = prev_insn_same_sec(file, insn); - if (&prev->list != &file->insn_list && insn_func(prev) == insn_func(insn)) + if (prev && insn_func(prev) == insn_func(insn)) return prev; return NULL; } +#define for_each_insn(file, insn) \ + for (struct section *__sec, *__fake = (struct section *)1; \ + __fake; __fake = NULL) \ + for_each_sec(file, __sec) \ + sec_for_each_insn(file, __sec, insn) + #define func_for_each_insn(file, func, insn) \ for (insn = find_insn(file, func->sec, func->offset); \ insn; \ @@ -96,16 +116,13 @@ static struct instruction *prev_insn_same_sym(struct objtool_file *file, #define sym_for_each_insn(file, sym, insn) \ for (insn = find_insn(file, sym->sec, sym->offset); \ - insn && &insn->list != &file->insn_list && \ - insn->sec == sym->sec && \ - insn->offset < sym->offset + sym->len; \ - insn = list_next_entry(insn, list)) + insn && insn->offset < sym->offset + sym->len; \ + insn = next_insn_same_sec(file, insn)) #define sym_for_each_insn_continue_reverse(file, sym, insn) \ - for (insn = list_prev_entry(insn, list); \ - &insn->list != &file->insn_list && \ - insn->sec == sym->sec && insn->offset >= sym->offset; \ - insn = list_prev_entry(insn, list)) + for (insn = prev_insn_same_sec(file, insn); \ + insn && insn->offset >= sym->offset; \ + insn = prev_insn_same_sec(file, insn)) #define sec_for_each_insn_from(file, insn) \ for (; insn; insn = next_insn_same_sec(file, insn)) @@ -114,16 +131,34 @@ static struct instruction *prev_insn_same_sym(struct objtool_file *file, for (insn = next_insn_same_sec(file, insn); insn; \ insn = next_insn_same_sec(file, insn)) +static inline struct symbol *insn_call_dest(struct instruction *insn) +{ + if (insn->type == INSN_JUMP_DYNAMIC || + insn->type == INSN_CALL_DYNAMIC) + return NULL; + + return insn->_call_dest; +} + +static inline struct reloc *insn_jump_table(struct instruction *insn) +{ + if (insn->type == INSN_JUMP_DYNAMIC || + insn->type == INSN_CALL_DYNAMIC) + return insn->_jump_table; + + return NULL; +} + static bool is_jump_table_jump(struct instruction *insn) { struct alt_group *alt_group = insn->alt_group; - if (insn->jump_table) + if (insn_jump_table(insn)) return true; /* Retpoline alternative for a jump table? */ return alt_group && alt_group->orig_group && - alt_group->orig_group->first_insn->jump_table; + insn_jump_table(alt_group->orig_group->first_insn); } static bool is_sibling_call(struct instruction *insn) @@ -137,8 +172,8 @@ static bool is_sibling_call(struct instruction *insn) return !is_jump_table_jump(insn); } - /* add_jump_destinations() sets insn->call_dest for sibling calls. */ - return (is_static_jump(insn) && insn->call_dest); + /* add_jump_destinations() sets insn_call_dest(insn) for sibling calls. */ + return (is_static_jump(insn) && insn_call_dest(insn)); } /* @@ -274,8 +309,8 @@ static void init_insn_state(struct objtool_file *file, struct insn_state *state, /* * We need the full vmlinux for noinstr validation, otherwise we can - * not correctly determine insn->call_dest->sec (external symbols do - * not have a section). + * not correctly determine insn_call_dest(insn)->sec (external symbols + * do not have a section). */ if (opts.link && opts.noinstr && sec) state->noinstr = sec->noinstr; @@ -366,6 +401,9 @@ static int decode_instructions(struct objtool_file *file) int ret; for_each_sec(file, sec) { + struct instruction *insns = NULL; + u8 prev_len = 0; + u8 idx = 0; if (!(sec->sh.sh_flags & SHF_EXECINSTR)) continue; @@ -391,26 +429,31 @@ static int decode_instructions(struct objtool_file *file) sec->init = true; for (offset = 0; offset < sec->sh.sh_size; offset += insn->len) { - insn = malloc(sizeof(*insn)); - if (!insn) { - WARN("malloc failed"); - return -1; + if (!insns || idx == INSN_CHUNK_MAX) { + insns = calloc(sizeof(*insn), INSN_CHUNK_SIZE); + if (!insns) { + WARN("malloc failed"); + return -1; + } + idx = 0; + } else { + idx++; } - memset(insn, 0, sizeof(*insn)); - INIT_LIST_HEAD(&insn->alts); - INIT_LIST_HEAD(&insn->stack_ops); - INIT_LIST_HEAD(&insn->call_node); + insn = &insns[idx]; + insn->idx = idx; + INIT_LIST_HEAD(&insn->call_node); insn->sec = sec; insn->offset = offset; + insn->prev_len = prev_len; ret = arch_decode_instruction(file, sec, offset, sec->sh.sh_size - offset, - &insn->len, &insn->type, - &insn->immediate, - &insn->stack_ops); + insn); if (ret) - goto err; + return ret; + + prev_len = insn->len; /* * By default, "ud2" is a dead end unless otherwise @@ -421,10 +464,11 @@ static int decode_instructions(struct objtool_file *file) insn->dead_end = true; hash_add(file->insn_hash, &insn->hash, sec_offset_hash(sec, insn->offset)); - list_add_tail(&insn->list, &file->insn_list); nr_insns++; } +// printf("%s: last chunk used: %d\n", sec->name, (int)idx); + list_for_each_entry(func, &sec->symbol_list, list) { if (func->type != STT_NOTYPE && func->type != STT_FUNC) continue; @@ -467,10 +511,6 @@ static int decode_instructions(struct objtool_file *file) printf("nr_insns: %lu\n", nr_insns); return 0; - -err: - free(insn); - return ret; } /* @@ -585,7 +625,7 @@ static int add_dead_ends(struct objtool_file *file) } insn = find_insn(file, reloc->sym->sec, reloc->addend); if (insn) - insn = list_prev_entry(insn, list); + insn = prev_insn_same_sec(file, insn); else if (reloc->addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { @@ -620,7 +660,7 @@ reachable: } insn = find_insn(file, reloc->sym->sec, reloc->addend); if (insn) - insn = list_prev_entry(insn, list); + insn = prev_insn_same_sec(file, insn); else if (reloc->addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { @@ -682,7 +722,7 @@ static int create_static_call_sections(struct objtool_file *file) return -1; /* find key symbol */ - key_name = strdup(insn->call_dest->name); + key_name = strdup(insn_call_dest(insn)->name); if (!key_name) { perror("strdup"); return -1; @@ -690,6 +730,7 @@ static int create_static_call_sections(struct objtool_file *file) if (strncmp(key_name, STATIC_CALL_TRAMP_PREFIX_STR, STATIC_CALL_TRAMP_PREFIX_LEN)) { WARN("static_call: trampoline name malformed: %s", key_name); + free(key_name); return -1; } tmp = key_name + STATIC_CALL_TRAMP_PREFIX_LEN - STATIC_CALL_KEY_PREFIX_LEN; @@ -699,6 +740,7 @@ static int create_static_call_sections(struct objtool_file *file) if (!key_sym) { if (!opts.module) { WARN("static_call: can't find static_call_key symbol: %s", tmp); + free(key_name); return -1; } @@ -711,7 +753,7 @@ static int create_static_call_sections(struct objtool_file *file) * trampoline address. This is fixed up in * static_call_add_module(). */ - key_sym = insn->call_dest; + key_sym = insn_call_dest(insn); } free(key_name); @@ -856,8 +898,15 @@ static int create_ibt_endbr_seal_sections(struct objtool_file *file) list_for_each_entry(insn, &file->endbr_list, call_node) { int *site = (int *)sec->data->d_buf + idx; + struct symbol *sym = insn->sym; *site = 0; + if (opts.module && sym && sym->type == STT_FUNC && + insn->offset == sym->offset && + (!strcmp(sym->name, "init_module") || + !strcmp(sym->name, "cleanup_module"))) + WARN("%s(): not an indirect call target", sym->name); + if (elf_add_reloc_to_insn(file->elf, sec, idx * sizeof(int), R_X86_64_PC32, @@ -1188,6 +1237,8 @@ static const char *uaccess_safe_builtin[] = { "__tsan_atomic64_compare_exchange_val", "__tsan_atomic_thread_fence", "__tsan_atomic_signal_fence", + "__tsan_unaligned_read16", + "__tsan_unaligned_write16", /* KCOV */ "write_comp_data", "check_kcov_mode", @@ -1233,9 +1284,9 @@ static const char *uaccess_safe_builtin[] = { "copy_mc_fragile_handle_tail", "copy_mc_enhanced_fast_string", "ftrace_likely_update", /* CONFIG_TRACE_BRANCH_PROFILING */ - "clear_user_erms", - "clear_user_rep_good", - "clear_user_original", + "rep_stos_alternative", + "rep_movs_alternative", + "__copy_user_nocache", NULL }; @@ -1300,43 +1351,42 @@ __weak bool arch_is_rethunk(struct symbol *sym) return false; } -#define NEGATIVE_RELOC ((void *)-1L) - static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *insn) { - if (insn->reloc == NEGATIVE_RELOC) + struct reloc *reloc; + + if (insn->no_reloc) return NULL; - if (!insn->reloc) { - if (!file) - return NULL; + if (!file) + return NULL; - insn->reloc = find_reloc_by_dest_range(file->elf, insn->sec, - insn->offset, insn->len); - if (!insn->reloc) { - insn->reloc = NEGATIVE_RELOC; - return NULL; - } + reloc = find_reloc_by_dest_range(file->elf, insn->sec, + insn->offset, insn->len); + if (!reloc) { + insn->no_reloc = 1; + return NULL; } - return insn->reloc; + return reloc; } static void remove_insn_ops(struct instruction *insn) { - struct stack_op *op, *tmp; + struct stack_op *op, *next; - list_for_each_entry_safe(op, tmp, &insn->stack_ops, list) { - list_del(&op->list); + for (op = insn->stack_ops; op; op = next) { + next = op->next; free(op); } + insn->stack_ops = NULL; } static void annotate_call_site(struct objtool_file *file, struct instruction *insn, bool sibling) { struct reloc *reloc = insn_reloc(file, insn); - struct symbol *sym = insn->call_dest; + struct symbol *sym = insn_call_dest(insn); if (!sym) sym = reloc->sym; @@ -1421,7 +1471,7 @@ static void annotate_call_site(struct objtool_file *file, static void add_call_dest(struct objtool_file *file, struct instruction *insn, struct symbol *dest, bool sibling) { - insn->call_dest = dest; + insn->_call_dest = dest; if (!dest) return; @@ -1679,12 +1729,12 @@ static int add_call_destinations(struct objtool_file *file) if (insn->ignore) continue; - if (!insn->call_dest) { + if (!insn_call_dest(insn)) { WARN_FUNC("unannotated intra-function call", insn->sec, insn->offset); return -1; } - if (insn_func(insn) && insn->call_dest->type != STT_FUNC) { + if (insn_func(insn) && insn_call_dest(insn)->type != STT_FUNC) { WARN_FUNC("unsupported call to non-function", insn->sec, insn->offset); return -1; @@ -1722,36 +1772,50 @@ static int handle_group_alt(struct objtool_file *file, struct instruction *orig_insn, struct instruction **new_insn) { - struct instruction *last_orig_insn, *last_new_insn = NULL, *insn, *nop = NULL; + struct instruction *last_new_insn = NULL, *insn, *nop = NULL; struct alt_group *orig_alt_group, *new_alt_group; unsigned long dest_off; - - orig_alt_group = malloc(sizeof(*orig_alt_group)); + orig_alt_group = orig_insn->alt_group; if (!orig_alt_group) { - WARN("malloc failed"); - return -1; - } - orig_alt_group->cfi = calloc(special_alt->orig_len, - sizeof(struct cfi_state *)); - if (!orig_alt_group->cfi) { - WARN("calloc failed"); - return -1; - } + struct instruction *last_orig_insn = NULL; - last_orig_insn = NULL; - insn = orig_insn; - sec_for_each_insn_from(file, insn) { - if (insn->offset >= special_alt->orig_off + special_alt->orig_len) - break; + orig_alt_group = malloc(sizeof(*orig_alt_group)); + if (!orig_alt_group) { + WARN("malloc failed"); + return -1; + } + orig_alt_group->cfi = calloc(special_alt->orig_len, + sizeof(struct cfi_state *)); + if (!orig_alt_group->cfi) { + WARN("calloc failed"); + return -1; + } - insn->alt_group = orig_alt_group; - last_orig_insn = insn; - } - orig_alt_group->orig_group = NULL; - orig_alt_group->first_insn = orig_insn; - orig_alt_group->last_insn = last_orig_insn; + insn = orig_insn; + sec_for_each_insn_from(file, insn) { + if (insn->offset >= special_alt->orig_off + special_alt->orig_len) + break; + insn->alt_group = orig_alt_group; + last_orig_insn = insn; + } + orig_alt_group->orig_group = NULL; + orig_alt_group->first_insn = orig_insn; + orig_alt_group->last_insn = last_orig_insn; + orig_alt_group->nop = NULL; + } else { + if (orig_alt_group->last_insn->offset + orig_alt_group->last_insn->len - + orig_alt_group->first_insn->offset != special_alt->orig_len) { + WARN_FUNC("weirdly overlapping alternative! %ld != %d", + orig_insn->sec, orig_insn->offset, + orig_alt_group->last_insn->offset + + orig_alt_group->last_insn->len - + orig_alt_group->first_insn->offset, + special_alt->orig_len); + return -1; + } + } new_alt_group = malloc(sizeof(*new_alt_group)); if (!new_alt_group) { @@ -1773,8 +1837,6 @@ static int handle_group_alt(struct objtool_file *file, return -1; } memset(nop, 0, sizeof(*nop)); - INIT_LIST_HEAD(&nop->alts); - INIT_LIST_HEAD(&nop->stack_ops); nop->sec = special_alt->new_sec; nop->offset = special_alt->new_off + special_alt->new_len; @@ -1828,7 +1890,7 @@ static int handle_group_alt(struct objtool_file *file, dest_off = arch_jump_destination(insn); if (dest_off == special_alt->new_off + special_alt->new_len) { - insn->jump_dest = next_insn_same_sec(file, last_orig_insn); + insn->jump_dest = next_insn_same_sec(file, orig_alt_group->last_insn); if (!insn->jump_dest) { WARN_FUNC("can't find alternative jump destination", insn->sec, insn->offset); @@ -1843,12 +1905,11 @@ static int handle_group_alt(struct objtool_file *file, return -1; } - if (nop) - list_add(&nop->list, &last_new_insn->list); end: new_alt_group->orig_group = orig_alt_group; new_alt_group->first_insn = *new_insn; - new_alt_group->last_insn = nop ? : last_new_insn; + new_alt_group->last_insn = last_new_insn; + new_alt_group->nop = nop; new_alt_group->cfi = orig_alt_group->cfi; return 0; } @@ -1898,7 +1959,7 @@ static int handle_jump_alt(struct objtool_file *file, else file->jl_long++; - *new_insn = list_next_entry(orig_insn, list); + *new_insn = next_insn_same_sec(file, orig_insn); return 0; } @@ -1972,7 +2033,8 @@ static int add_special_section_alts(struct objtool_file *file) alt->insn = new_insn; alt->skip_orig = special_alt->skip_orig; orig_insn->ignore_alts |= special_alt->skip_alt; - list_add_tail(&alt->list, &orig_insn->alts); + alt->next = orig_insn->alts; + orig_insn->alts = alt; list_del(&special_alt->list); free(special_alt); @@ -2031,7 +2093,8 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, } alt->insn = dest_insn; - list_add_tail(&alt->list, &insn->alts); + alt->next = insn->alts; + insn->alts = alt; prev_offset = reloc->offset; } @@ -2121,7 +2184,7 @@ static void mark_func_jump_tables(struct objtool_file *file, reloc = find_jump_table(file, func, insn); if (reloc) { reloc->jump_table_start = true; - insn->jump_table = reloc; + insn->_jump_table = reloc; } } } @@ -2133,10 +2196,10 @@ static int add_func_jump_tables(struct objtool_file *file, int ret; func_for_each_insn(file, func, insn) { - if (!insn->jump_table) + if (!insn_jump_table(insn)) continue; - ret = add_jump_table(file, insn, insn->jump_table); + ret = add_jump_table(file, insn, insn_jump_table(insn)); if (ret) return ret; } @@ -2269,6 +2332,7 @@ static int read_unwind_hints(struct objtool_file *file) cfi.cfa.offset = bswap_if_needed(file->elf, hint->sp_offset); cfi.type = hint->type; + cfi.signal = hint->signal; cfi.end = hint->end; insn->cfi = cfi_hash_find_or_add(&cfi); @@ -2608,8 +2672,8 @@ static int decode_sections(struct objtool_file *file) static bool is_fentry_call(struct instruction *insn) { if (insn->type == INSN_CALL && - insn->call_dest && - insn->call_dest->fentry) + insn_call_dest(insn) && + insn_call_dest(insn)->fentry) return true; return false; @@ -3204,8 +3268,12 @@ static int propagate_alt_cfi(struct objtool_file *file, struct instruction *insn alt_cfi[group_off] = insn->cfi; } else { if (cficmp(alt_cfi[group_off], insn->cfi)) { - WARN_FUNC("stack layout conflict in alternatives", - insn->sec, insn->offset); + struct alt_group *orig_group = insn->alt_group->orig_group ?: insn->alt_group; + struct instruction *orig = orig_group->first_insn; + char *where = offstr(insn->sec, insn->offset); + WARN_FUNC("stack layout conflict in alternatives: %s", + orig->sec, orig->offset, where); + free(where); return -1; } } @@ -3219,7 +3287,7 @@ static int handle_insn_ops(struct instruction *insn, { struct stack_op *op; - list_for_each_entry(op, &insn->stack_ops, list) { + for (op = insn->stack_ops; op; op = op->next) { if (update_cfi_state(insn, next_insn, &state->cfi, op)) return 1; @@ -3316,8 +3384,8 @@ static inline const char *call_dest_name(struct instruction *insn) struct reloc *rel; int idx; - if (insn->call_dest) - return insn->call_dest->name; + if (insn_call_dest(insn)) + return insn_call_dest(insn)->name; rel = insn_reloc(NULL, insn); if (rel && !strcmp(rel->sym->name, "pv_ops")) { @@ -3399,13 +3467,13 @@ static int validate_call(struct objtool_file *file, struct insn_state *state) { if (state->noinstr && state->instr <= 0 && - !noinstr_call_dest(file, insn, insn->call_dest)) { + !noinstr_call_dest(file, insn, insn_call_dest(insn))) { WARN_FUNC("call to %s() leaves .noinstr.text section", insn->sec, insn->offset, call_dest_name(insn)); return 1; } - if (state->uaccess && !func_uaccess_safe(insn->call_dest)) { + if (state->uaccess && !func_uaccess_safe(insn_call_dest(insn))) { WARN_FUNC("call to %s() with UACCESS enabled", insn->sec, insn->offset, call_dest_name(insn)); return 1; @@ -3483,11 +3551,28 @@ static struct instruction *next_insn_to_validate(struct objtool_file *file, * Simulate the fact that alternatives are patched in-place. When the * end of a replacement alt_group is reached, redirect objtool flow to * the end of the original alt_group. + * + * insn->alts->insn -> alt_group->first_insn + * ... + * alt_group->last_insn + * [alt_group->nop] -> next(orig_group->last_insn) */ - if (alt_group && insn == alt_group->last_insn && alt_group->orig_group) - return next_insn_same_sec(file, alt_group->orig_group->last_insn); + if (alt_group) { + if (alt_group->nop) { + /* ->nop implies ->orig_group */ + if (insn == alt_group->last_insn) + return alt_group->nop; + if (insn == alt_group->nop) + goto next_orig; + } + if (insn == alt_group->last_insn && alt_group->orig_group) + goto next_orig; + } return next_insn_same_sec(file, insn); + +next_orig: + return next_insn_same_sec(file, alt_group->orig_group->last_insn); } /* @@ -3588,10 +3673,10 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, if (propagate_alt_cfi(file, insn)) return 1; - if (!insn->ignore_alts && !list_empty(&insn->alts)) { + if (!insn->ignore_alts && insn->alts) { bool skip_orig = false; - list_for_each_entry(alt, &insn->alts, list) { + for (alt = insn->alts; alt; alt = alt->next) { if (alt->skip_orig) skip_orig = true; @@ -3738,11 +3823,25 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, return 0; } +static int validate_unwind_hint(struct objtool_file *file, + struct instruction *insn, + struct insn_state *state) +{ + if (insn->hint && !insn->visited && !insn->ignore) { + int ret = validate_branch(file, insn_func(insn), insn, *state); + if (ret && opts.backtrace) + BT_FUNC("<=== (hint)", insn); + return ret; + } + + return 0; +} + static int validate_unwind_hints(struct objtool_file *file, struct section *sec) { struct instruction *insn; struct insn_state state; - int ret, warnings = 0; + int warnings = 0; if (!file->hints) return 0; @@ -3750,22 +3849,11 @@ static int validate_unwind_hints(struct objtool_file *file, struct section *sec) init_insn_state(file, &state, sec); if (sec) { - insn = find_insn(file, sec, 0); - if (!insn) - return 0; + sec_for_each_insn(file, sec, insn) + warnings += validate_unwind_hint(file, insn, &state); } else { - insn = list_first_entry(&file->insn_list, typeof(*insn), list); - } - - while (&insn->list != &file->insn_list && (!sec || insn->sec == sec)) { - if (insn->hint && !insn->visited && !insn->ignore) { - ret = validate_branch(file, insn_func(insn), insn, state); - if (ret && opts.backtrace) - BT_FUNC("<=== (hint)", insn); - warnings += ret; - } - - insn = list_next_entry(insn, list); + for_each_insn(file, insn) + warnings += validate_unwind_hint(file, insn, &state); } return warnings; @@ -3790,11 +3878,11 @@ static int validate_entry(struct objtool_file *file, struct instruction *insn) insn->visited |= VISITED_ENTRY; - if (!insn->ignore_alts && !list_empty(&insn->alts)) { + if (!insn->ignore_alts && insn->alts) { struct alternative *alt; bool skip_orig = false; - list_for_each_entry(alt, &insn->alts, list) { + for (alt = insn->alts; alt; alt = alt->next) { if (alt->skip_orig) skip_orig = true; @@ -3843,11 +3931,11 @@ static int validate_entry(struct objtool_file *file, struct instruction *insn) /* fallthrough */ case INSN_CALL: - dest = find_insn(file, insn->call_dest->sec, - insn->call_dest->offset); + dest = find_insn(file, insn_call_dest(insn)->sec, + insn_call_dest(insn)->offset); if (!dest) { WARN("Unresolved function after linking!?: %s", - insn->call_dest->name); + insn_call_dest(insn)->name); return -1; } @@ -3948,13 +4036,13 @@ static int validate_retpoline(struct objtool_file *file) static bool is_kasan_insn(struct instruction *insn) { return (insn->type == INSN_CALL && - !strcmp(insn->call_dest->name, "__asan_handle_no_return")); + !strcmp(insn_call_dest(insn)->name, "__asan_handle_no_return")); } static bool is_ubsan_insn(struct instruction *insn) { return (insn->type == INSN_CALL && - !strcmp(insn->call_dest->name, + !strcmp(insn_call_dest(insn)->name, "__ubsan_handle_builtin_unreachable")); } @@ -4031,8 +4119,9 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio * * It may also insert a UD2 after calling a __noreturn function. */ - prev_insn = list_prev_entry(insn, list); - if ((prev_insn->dead_end || dead_end_function(file, prev_insn->call_dest)) && + prev_insn = prev_insn_same_sec(file, insn); + if ((prev_insn->dead_end || + dead_end_function(file, insn_call_dest(prev_insn))) && (insn->type == INSN_BUG || (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest && insn->jump_dest->type == INSN_BUG))) @@ -4062,7 +4151,7 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio if (insn->offset + insn->len >= insn_func(insn)->offset + insn_func(insn)->len) break; - insn = list_next_entry(insn, list); + insn = next_insn_same_sec(file, insn); } return false; @@ -4075,10 +4164,10 @@ static int add_prefix_symbol(struct objtool_file *file, struct symbol *func, return 0; for (;;) { - struct instruction *prev = list_prev_entry(insn, list); + struct instruction *prev = prev_insn_same_sec(file, insn); u64 offset; - if (&prev->list == &file->insn_list) + if (!prev) break; if (prev->type != INSN_NOP) @@ -4477,7 +4566,7 @@ int check(struct objtool_file *file) warnings += ret; - if (list_empty(&file->insn_list)) + if (!nr_insns) goto out; if (opts.retpoline) { @@ -4586,7 +4675,7 @@ int check(struct objtool_file *file) warnings += ret; } - if (opts.orc && !list_empty(&file->insn_list)) { + if (opts.orc && nr_insns) { ret = orc_create(file); if (ret < 0) goto out; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 64443a7f4bbf..6806ce01d933 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -284,13 +284,13 @@ static int read_sections(struct elf *elf) !elf_alloc_hash(section_name, sections_nr)) return -1; + elf->section_data = calloc(sections_nr, sizeof(*sec)); + if (!elf->section_data) { + perror("calloc"); + return -1; + } for (i = 0; i < sections_nr; i++) { - sec = malloc(sizeof(*sec)); - if (!sec) { - perror("malloc"); - return -1; - } - memset(sec, 0, sizeof(*sec)); + sec = &elf->section_data[i]; INIT_LIST_HEAD(&sec->symbol_list); INIT_LIST_HEAD(&sec->reloc_list); @@ -422,13 +422,13 @@ static int read_symbols(struct elf *elf) !elf_alloc_hash(symbol_name, symbols_nr)) return -1; + elf->symbol_data = calloc(symbols_nr, sizeof(*sym)); + if (!elf->symbol_data) { + perror("calloc"); + return -1; + } for (i = 0; i < symbols_nr; i++) { - sym = malloc(sizeof(*sym)); - if (!sym) { - perror("malloc"); - return -1; - } - memset(sym, 0, sizeof(*sym)); + sym = &elf->symbol_data[i]; sym->idx = i; @@ -918,13 +918,13 @@ static int read_relocs(struct elf *elf) sec->base->reloc = sec; nr_reloc = 0; + sec->reloc_data = calloc(sec->sh.sh_size / sec->sh.sh_entsize, sizeof(*reloc)); + if (!sec->reloc_data) { + perror("calloc"); + return -1; + } for (i = 0; i < sec->sh.sh_size / sec->sh.sh_entsize; i++) { - reloc = malloc(sizeof(*reloc)); - if (!reloc) { - perror("malloc"); - return -1; - } - memset(reloc, 0, sizeof(*reloc)); + reloc = &sec->reloc_data[i]; switch (sec->sh.sh_type) { case SHT_REL: if (read_rel_reloc(sec, i, reloc, &symndx)) @@ -1453,16 +1453,16 @@ void elf_close(struct elf *elf) list_for_each_entry_safe(sym, tmpsym, &sec->symbol_list, list) { list_del(&sym->list); hash_del(&sym->hash); - free(sym); } list_for_each_entry_safe(reloc, tmpreloc, &sec->reloc_list, list) { list_del(&reloc->list); hash_del(&reloc->hash); - free(reloc); } list_del(&sec->list); - free(sec); + free(sec->reloc_data); } + free(elf->symbol_data); + free(elf->section_data); free(elf); } diff --git a/tools/objtool/include/objtool/arch.h b/tools/objtool/include/objtool/arch.h index 4ecb480131c7..2b6d2ce4f9a5 100644 --- a/tools/objtool/include/objtool/arch.h +++ b/tools/objtool/include/objtool/arch.h @@ -62,9 +62,9 @@ struct op_src { }; struct stack_op { + struct stack_op *next; struct op_dest dest; struct op_src src; - struct list_head list; }; struct instruction; @@ -75,9 +75,7 @@ void arch_initial_func_cfi_state(struct cfi_init_state *state); int arch_decode_instruction(struct objtool_file *file, const struct section *sec, unsigned long offset, unsigned int maxlen, - unsigned int *len, enum insn_type *type, - unsigned long *immediate, - struct list_head *ops_list); + struct instruction *insn); bool arch_callee_saved_reg(unsigned char reg); diff --git a/tools/objtool/include/objtool/builtin.h b/tools/objtool/include/objtool/builtin.h index fa45044e3863..2a108e648b7a 100644 --- a/tools/objtool/include/objtool/builtin.h +++ b/tools/objtool/include/objtool/builtin.h @@ -7,8 +7,6 @@ #include <subcmd/parse-options.h> -extern const struct option check_options[]; - struct opts { /* actions: */ bool dump_orc; diff --git a/tools/objtool/include/objtool/cfi.h b/tools/objtool/include/objtool/cfi.h index f11d1ac1dadf..b1258e79a1b7 100644 --- a/tools/objtool/include/objtool/cfi.h +++ b/tools/objtool/include/objtool/cfi.h @@ -34,6 +34,7 @@ struct cfi_state { unsigned char type; bool bp_scratch; bool drap; + bool signal; bool end; }; diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h index acd7fae59348..3e7c7004f7df 100644 --- a/tools/objtool/include/objtool/check.h +++ b/tools/objtool/include/objtool/check.h @@ -27,7 +27,7 @@ struct alt_group { struct alt_group *orig_group; /* First and last instructions in the group */ - struct instruction *first_insn, *last_insn; + struct instruction *first_insn, *last_insn, *nop; /* * Byte-offset-addressed len-sized array of pointers to CFI structs. @@ -36,39 +36,46 @@ struct alt_group { struct cfi_state **cfi; }; +#define INSN_CHUNK_BITS 8 +#define INSN_CHUNK_SIZE (1 << INSN_CHUNK_BITS) +#define INSN_CHUNK_MAX (INSN_CHUNK_SIZE - 1) + struct instruction { - struct list_head list; struct hlist_node hash; struct list_head call_node; struct section *sec; unsigned long offset; - unsigned int len; - enum insn_type type; unsigned long immediate; - u16 dead_end : 1, - ignore : 1, - ignore_alts : 1, - hint : 1, - save : 1, - restore : 1, - retpoline_safe : 1, - noendbr : 1, - entry : 1; - /* 7 bit hole */ - + u8 len; + u8 prev_len; + u8 type; s8 instr; - u8 visited; + + u32 idx : INSN_CHUNK_BITS, + dead_end : 1, + ignore : 1, + ignore_alts : 1, + hint : 1, + save : 1, + restore : 1, + retpoline_safe : 1, + noendbr : 1, + entry : 1, + visited : 4, + no_reloc : 1; + /* 10 bit hole */ struct alt_group *alt_group; - struct symbol *call_dest; struct instruction *jump_dest; struct instruction *first_jump_src; - struct reloc *jump_table; - struct reloc *reloc; - struct list_head alts; + union { + struct symbol *_call_dest; + struct reloc *_jump_table; + }; + struct alternative *alts; struct symbol *sym; - struct list_head stack_ops; + struct stack_op *stack_ops; struct cfi_state *cfi; }; @@ -107,13 +114,11 @@ static inline bool is_jump(struct instruction *insn) struct instruction *find_insn(struct objtool_file *file, struct section *sec, unsigned long offset); -#define for_each_insn(file, insn) \ - list_for_each_entry(insn, &file->insn_list, list) +struct instruction *next_insn_same_sec(struct objtool_file *file, struct instruction *insn); -#define sec_for_each_insn(file, sec, insn) \ - for (insn = find_insn(file, sec, 0); \ - insn && &insn->list != &file->insn_list && \ - insn->sec == sec; \ - insn = list_next_entry(insn, list)) +#define sec_for_each_insn(file, _sec, insn) \ + for (insn = find_insn(file, _sec, 0); \ + insn && insn->sec == _sec; \ + insn = next_insn_same_sec(file, insn)) #endif /* _CHECK_H */ diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index bb60fd42b46f..ad0024da262b 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -39,6 +39,7 @@ struct section { char *name; int idx; bool changed, text, rodata, noinstr, init, truncate; + struct reloc *reloc_data; }; struct symbol { @@ -49,12 +50,11 @@ struct symbol { GElf_Sym sym; struct section *sec; char *name; - unsigned int idx; - unsigned char bind, type; + unsigned int idx, len; unsigned long offset; - unsigned int len; unsigned long __subtree_last; struct symbol *pfunc, *cfunc, *alias; + unsigned char bind, type; u8 uaccess_safe : 1; u8 static_call_tramp : 1; u8 retpoline_thunk : 1; @@ -104,6 +104,9 @@ struct elf { struct hlist_head *section_hash; struct hlist_head *section_name_hash; struct hlist_head *reloc_hash; + + struct section *section_data; + struct symbol *symbol_data; }; #define OFFSET_STRIDE_BITS 4 diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h index 6b40977bcdb1..94a33ee7b363 100644 --- a/tools/objtool/include/objtool/objtool.h +++ b/tools/objtool/include/objtool/objtool.h @@ -21,7 +21,6 @@ struct pv_state { struct objtool_file { struct elf *elf; - struct list_head insn_list; DECLARE_HASHTABLE(insn_hash, 20); struct list_head retpoline_call_list; struct list_head return_thunk_list; diff --git a/tools/objtool/include/objtool/special.h b/tools/objtool/include/objtool/special.h index dc4721e19002..86d4af9c5aa9 100644 --- a/tools/objtool/include/objtool/special.h +++ b/tools/objtool/include/objtool/special.h @@ -19,6 +19,7 @@ struct special_alt { bool skip_orig; bool skip_alt; bool jump_or_nop; + u8 key_addend; struct section *orig_sec; unsigned long orig_off; @@ -27,7 +28,6 @@ struct special_alt { unsigned long new_off; unsigned int orig_len, new_len; /* group only */ - u8 key_addend; }; int special_get_alts(struct elf *elf, struct list_head *alts); diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index 6affd8067f83..c54f7235c5d9 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -99,7 +99,6 @@ struct objtool_file *objtool_open_read(const char *_objname) return NULL; } - INIT_LIST_HEAD(&file.insn_list); hash_init(file.insn_hash); INIT_LIST_HEAD(&file.retpoline_call_list); INIT_LIST_HEAD(&file.return_thunk_list); diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c index 4f1211fec82c..2d8ebdcd1db3 100644 --- a/tools/objtool/orc_dump.c +++ b/tools/objtool/orc_dump.c @@ -211,8 +211,8 @@ int orc_dump(const char *_objname) print_reg(orc[i].bp_reg, bswap_if_needed(&dummy_elf, orc[i].bp_offset)); - printf(" type:%s end:%d\n", - orc_type_name(orc[i].type), orc[i].end); + printf(" type:%s signal:%d end:%d\n", + orc_type_name(orc[i].type), orc[i].signal, orc[i].end); } elf_end(elf); diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 1f22b7ebae58..57a4527d5988 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -27,6 +27,7 @@ static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, } orc->end = cfi->end; + orc->signal = cfi->signal; if (cfi->cfa.base == CFI_UNDEFINED) { orc->sp_reg = ORC_REG_UNDEFINED; diff --git a/tools/objtool/special.c b/tools/objtool/special.c index 9c8d827f69af..baa85c31526b 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -26,7 +26,7 @@ struct special_entry { unsigned char key; /* jump_label key */ }; -struct special_entry entries[] = { +static const struct special_entry entries[] = { { .sec = ".altinstructions", .group = true, @@ -65,7 +65,7 @@ static void reloc_to_sec_off(struct reloc *reloc, struct section **sec, *off = reloc->sym->offset + reloc->addend; } -static int get_alt_entry(struct elf *elf, struct special_entry *entry, +static int get_alt_entry(struct elf *elf, const struct special_entry *entry, struct section *sec, int idx, struct special_alt *alt) { @@ -139,7 +139,7 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, */ int special_get_alts(struct elf *elf, struct list_head *alts) { - struct special_entry *entry; + const struct special_entry *entry; struct section *sec; unsigned int nr_entries; struct special_alt *alt; diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index f8182417b734..10bb1d494258 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -538,6 +538,7 @@ static int perf_event__repipe_buildid_mmap2(struct perf_tool *tool, dso->hit = 1; } dso__put(dso); + perf_event__repipe(tool, event, sample, machine); return 0; } diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 8ae0a1535293..f3029742b800 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -653,7 +653,6 @@ static const struct { { "__GFP_HIGHMEM", "HM" }, { "GFP_DMA32", "D32" }, { "__GFP_HIGH", "H" }, - { "__GFP_ATOMIC", "_A" }, { "__GFP_IO", "I" }, { "__GFP_FS", "F" }, { "__GFP_NOWARN", "NWR" }, diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 5d18a5a6f662..fa7c40956d0f 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -539,12 +539,7 @@ static int enable_counters(void) return err; } - /* - * We need to enable counters only if: - * - we don't have tracee (attaching to task or cpu) - * - we have initial delay configured - */ - if (!target__none(&target)) { + if (!target__enable_on_exec(&target)) { if (!all_counters_use_bpf) evlist__enable(evsel_list); } @@ -914,7 +909,7 @@ try_again_reset: return err; } - if (stat_config.initial_delay) { + if (target.initial_delay) { pr_info(EVLIST_DISABLED_MSG); } else { err = enable_counters(); @@ -926,8 +921,8 @@ try_again_reset: if (forks) evlist__start_workload(evsel_list); - if (stat_config.initial_delay > 0) { - usleep(stat_config.initial_delay * USEC_PER_MSEC); + if (target.initial_delay > 0) { + usleep(target.initial_delay * USEC_PER_MSEC); err = enable_counters(); if (err) return -1; @@ -1248,7 +1243,7 @@ static struct option stat_options[] = { "aggregate counts per thread", AGGR_THREAD), OPT_SET_UINT(0, "per-node", &stat_config.aggr_mode, "aggregate counts per numa node", AGGR_NODE), - OPT_INTEGER('D', "delay", &stat_config.initial_delay, + OPT_INTEGER('D', "delay", &target.initial_delay, "ms to wait before starting measurement after program start (-1: start with events disabled)"), OPT_CALLBACK_NOOPT(0, "metric-only", &stat_config.metric_only, NULL, "Only print computed metrics. No raw values", enable_metric_only), diff --git a/tools/perf/tests/shell/lib/perf_json_output_lint.py b/tools/perf/tests/shell/lib/perf_json_output_lint.py index d90f8d102eb9..97598d14e532 100644 --- a/tools/perf/tests/shell/lib/perf_json_output_lint.py +++ b/tools/perf/tests/shell/lib/perf_json_output_lint.py @@ -40,19 +40,6 @@ def is_counter_value(num): return isfloat(num) or num == '<not counted>' or num == '<not supported>' def check_json_output(expected_items): - if expected_items != -1: - for line in Lines: - if 'failed' not in line: - count = 0 - count = line.count(',') - if count != expected_items and count >= 1 and count <= 3 and 'metric-value' in line: - # Events that generate >1 metric may have isolated metric - # values and possibly other prefixes like interval, core and - # aggregate-number. - continue - if count != expected_items: - raise RuntimeError(f'wrong number of fields. counted {count} expected {expected_items}' - f' in \'{line}\'') checks = { 'aggregate-number': lambda x: isfloat(x), 'core': lambda x: True, @@ -73,6 +60,16 @@ def check_json_output(expected_items): } input = '[\n' + ','.join(Lines) + '\n]' for item in json.loads(input): + if expected_items != -1: + count = len(item) + if count != expected_items and count >= 1 and count <= 4 and 'metric-value' in item: + # Events that generate >1 metric may have isolated metric + # values and possibly other prefixes like interval, core and + # aggregate-number. + pass + elif count != expected_items: + raise RuntimeError(f'wrong number of fields. counted {count} expected {expected_items}' + f' in \'{item}\'') for key, value in item.items(): if key not in checks: raise RuntimeError(f'Unexpected key: key={key} value={value}') @@ -82,11 +79,11 @@ def check_json_output(expected_items): try: if args.no_args or args.system_wide or args.event: - expected_items = 6 - elif args.interval or args.per_thread or args.system_wide_no_aggr: expected_items = 7 - elif args.per_core or args.per_socket or args.per_node or args.per_die: + elif args.interval or args.per_thread or args.system_wide_no_aggr: expected_items = 8 + elif args.per_core or args.per_socket or args.per_node or args.per_die: + expected_items = 9 else: # If no option is specified, don't check the number of items. expected_items = -1 diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh index b7f050aa6210..324fc9e6edd7 100755 --- a/tools/perf/tests/shell/stat+csv_output.sh +++ b/tools/perf/tests/shell/stat+csv_output.sh @@ -7,6 +7,7 @@ set -e skip_test=0 +csv_sep=@ function commachecker() { @@ -34,7 +35,7 @@ function commachecker() [ "$x" = "Failed" ] && continue # Count the number of commas - x=$(echo $line | tr -d -c ',') + x=$(echo $line | tr -d -c $csv_sep) cnt="${#x}" # echo $line $cnt [[ ! "$cnt" =~ $exp ]] && { @@ -54,7 +55,7 @@ function ParanoidAndNotRoot() check_no_args() { echo -n "Checking CSV output: no args " - perf stat -x, true 2>&1 | commachecker --no-args + perf stat -x$csv_sep true 2>&1 | commachecker --no-args echo "[Success]" } @@ -66,7 +67,7 @@ check_system_wide() echo "[Skip] paranoid and not root" return fi - perf stat -x, -a true 2>&1 | commachecker --system-wide + perf stat -x$csv_sep -a true 2>&1 | commachecker --system-wide echo "[Success]" } @@ -79,14 +80,14 @@ check_system_wide_no_aggr() return fi echo -n "Checking CSV output: system wide no aggregation " - perf stat -x, -A -a --no-merge true 2>&1 | commachecker --system-wide-no-aggr + perf stat -x$csv_sep -A -a --no-merge true 2>&1 | commachecker --system-wide-no-aggr echo "[Success]" } check_interval() { echo -n "Checking CSV output: interval " - perf stat -x, -I 1000 true 2>&1 | commachecker --interval + perf stat -x$csv_sep -I 1000 true 2>&1 | commachecker --interval echo "[Success]" } @@ -94,7 +95,7 @@ check_interval() check_event() { echo -n "Checking CSV output: event " - perf stat -x, -e cpu-clock true 2>&1 | commachecker --event + perf stat -x$csv_sep -e cpu-clock true 2>&1 | commachecker --event echo "[Success]" } @@ -106,7 +107,7 @@ check_per_core() echo "[Skip] paranoid and not root" return fi - perf stat -x, --per-core -a true 2>&1 | commachecker --per-core + perf stat -x$csv_sep --per-core -a true 2>&1 | commachecker --per-core echo "[Success]" } @@ -118,7 +119,7 @@ check_per_thread() echo "[Skip] paranoid and not root" return fi - perf stat -x, --per-thread -a true 2>&1 | commachecker --per-thread + perf stat -x$csv_sep --per-thread -a true 2>&1 | commachecker --per-thread echo "[Success]" } @@ -130,7 +131,7 @@ check_per_die() echo "[Skip] paranoid and not root" return fi - perf stat -x, --per-die -a true 2>&1 | commachecker --per-die + perf stat -x$csv_sep --per-die -a true 2>&1 | commachecker --per-die echo "[Success]" } @@ -142,7 +143,7 @@ check_per_node() echo "[Skip] paranoid and not root" return fi - perf stat -x, --per-node -a true 2>&1 | commachecker --per-node + perf stat -x$csv_sep --per-node -a true 2>&1 | commachecker --per-node echo "[Success]" } @@ -154,7 +155,7 @@ check_per_socket() echo "[Skip] paranoid and not root" return fi - perf stat -x, --per-socket -a true 2>&1 | commachecker --per-socket + perf stat -x$csv_sep --per-socket -a true 2>&1 | commachecker --per-socket echo "[Success]" } diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c index 38e3b287dbb2..d877a0a9731f 100644 --- a/tools/perf/util/bpf_skel/off_cpu.bpf.c +++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c @@ -277,7 +277,7 @@ int on_switch(u64 *ctx) else prev_state = get_task_state(prev); - return off_cpu_stat(ctx, prev, next, prev_state); + return off_cpu_stat(ctx, prev, next, prev_state & 0xff); } char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 534d36d26fc3..a07473703c6d 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -842,11 +842,7 @@ int create_perf_stat_counter(struct evsel *evsel, if (evsel__is_group_leader(evsel)) { attr->disabled = 1; - /* - * In case of initial_delay we enable tracee - * events manually. - */ - if (target__none(target) && !config->initial_delay) + if (target__enable_on_exec(target)) attr->enable_on_exec = 1; } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index b1c29156c560..bf1794ebc916 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -166,7 +166,6 @@ struct perf_stat_config { FILE *output; unsigned int interval; unsigned int timeout; - int initial_delay; unsigned int unit_width; unsigned int metric_only_len; int times; diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h index daec6cba500d..880f1af7f6ad 100644 --- a/tools/perf/util/target.h +++ b/tools/perf/util/target.h @@ -18,6 +18,7 @@ struct target { bool per_thread; bool use_bpf; bool hybrid; + int initial_delay; const char *attr_map; }; @@ -72,6 +73,17 @@ static inline bool target__none(struct target *target) return !target__has_task(target) && !target__has_cpu(target); } +static inline bool target__enable_on_exec(struct target *target) +{ + /* + * Normally enable_on_exec should be set if: + * 1) The tracee process is forked (not attaching to existed task or cpu). + * 2) And initial_delay is not configured. + * Otherwise, we enable tracee events manually. + */ + return target__none(target) && !target->initial_delay; +} + static inline bool target__has_per_thread(struct target *target) { return target->system_wide && target->per_thread; diff --git a/tools/power/acpi/tools/pfrut/pfrut.c b/tools/power/acpi/tools/pfrut/pfrut.c index 52aa0351533c..388c9e3ad040 100644 --- a/tools/power/acpi/tools/pfrut/pfrut.c +++ b/tools/power/acpi/tools/pfrut/pfrut.c @@ -97,7 +97,7 @@ static struct option long_options[] = { static void parse_options(int argc, char **argv) { int option_index = 0; - char *pathname; + char *pathname, *endptr; int opt; pathname = strdup(argv[0]); @@ -125,11 +125,23 @@ static void parse_options(int argc, char **argv) log_getinfo = 1; break; case 'T': - log_type = atoi(optarg); + log_type = strtol(optarg, &endptr, 0); + if (*endptr || (log_type != 0 && log_type != 1)) { + printf("Number expected: type(0:execution, 1:history) - Quit.\n"); + exit(1); + } + set_log_type = 1; break; case 'L': - log_level = atoi(optarg); + log_level = strtol(optarg, &endptr, 0); + if (*endptr || + (log_level != 0 && log_level != 1 && + log_level != 2 && log_level != 4)) { + printf("Number expected: level(0, 1, 2, 4) - Quit.\n"); + exit(1); + } + set_log_level = 1; break; case 'R': diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py index 82c09cd25cc2..bf4ac24a1c7a 100755 --- a/tools/power/pm-graph/sleepgraph.py +++ b/tools/power/pm-graph/sleepgraph.py @@ -5556,9 +5556,8 @@ def executeSuspend(quiet=False): if not quiet: pprint('CAPTURING TRACE') op = sv.writeDatafileHeader(sv.ftracefile, testdata) - fp = open(tp+'trace', 'r') - for line in fp: - op.write(line) + fp = open(tp+'trace', 'rb') + op.write(ascii(fp.read())) op.close() sv.fsetVal('', 'trace') sv.platforminfo(cmdafter) diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index c7b26a3603af..8f08c3fd498d 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -340,10 +340,12 @@ starts a new interval. must be run as root. Alternatively, non-root users can be enabled to run turbostat this way: -# setcap cap_sys_admin,cap_sys_rawio,cap_sys_nice=+ep ./turbostat +# setcap cap_sys_admin,cap_sys_rawio,cap_sys_nice=+ep path/to/turbostat # chmod +r /dev/cpu/*/msr +# chmod +r /dev/cpu_dma_latency + .B "turbostat " reads hardware counters, but doesn't write them. So it will not interfere with the OS or other programs, including diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index aba460410dbd..8a36ba5df9f9 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -3,7 +3,7 @@ * turbostat -- show CPU frequency and C-state residency * on modern Intel and AMD processors. * - * Copyright (c) 2022 Intel Corporation. + * Copyright (c) 2023 Intel Corporation. * Len Brown <len.brown@intel.com> */ @@ -670,7 +670,7 @@ static int perf_instr_count_open(int cpu_num) /* counter for cpu_num, including user + kernel and all processes */ fd = perf_event_open(&pea, -1, cpu_num, -1, 0); if (fd == -1) { - warn("cpu%d: perf instruction counter", cpu_num); + warnx("capget(CAP_PERFMON) failed, try \"# setcap cap_sys_admin=ep %s\"", progname); BIC_NOT_PRESENT(BIC_IPC); } @@ -2538,7 +2538,7 @@ static void dump_turbo_ratio_limits(int trl_msr_offset, int family, int model) get_msr(base_cpu, trl_msr_offset, &msr); fprintf(outf, "cpu%d: MSR_%sTURBO_RATIO_LIMIT: 0x%08llx\n", - base_cpu, trl_msr_offset == MSR_SECONDARY_TURBO_RATIO_LIMIT ? "SECONDARY" : "", msr); + base_cpu, trl_msr_offset == MSR_SECONDARY_TURBO_RATIO_LIMIT ? "SECONDARY_" : "", msr); if (has_turbo_ratio_group_limits(family, model)) { get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT1, &core_counts); @@ -3502,9 +3502,6 @@ release_msr: /* * set_my_sched_priority(pri) * return previous - * - * if non-root, do this: - * # /sbin/setcap cap_sys_rawio,cap_sys_nice=+ep /usr/bin/turbostat */ int set_my_sched_priority(int priority) { @@ -3518,7 +3515,7 @@ int set_my_sched_priority(int priority) retval = setpriority(PRIO_PROCESS, 0, priority); if (retval) - err(retval, "setpriority(%d)", priority); + errx(retval, "capget(CAP_SYS_NICE) failed,try \"# setcap cap_sys_nice=ep %s\"", progname); errno = 0; retval = getpriority(PRIO_PROCESS, 0); @@ -4426,7 +4423,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) fprintf(outf, "cpu%d: MSR_HWP_STATUS: 0x%08llx " "(%sGuaranteed_Perf_Change, %sExcursion_Min)\n", - cpu, msr, ((msr) & 0x1) ? "" : "No-", ((msr) & 0x2) ? "" : "No-"); + cpu, msr, ((msr) & 0x1) ? "" : "No-", ((msr) & 0x4) ? "" : "No-"); return 0; } @@ -5463,6 +5460,9 @@ unsigned int intel_model_duplicates(unsigned int model) case INTEL_FAM6_ICELAKE_D: return INTEL_FAM6_ICELAKE_X; + + case INTEL_FAM6_EMERALDRAPIDS_X: + return INTEL_FAM6_SAPPHIRERAPIDS_X; } return model; } @@ -5476,13 +5476,13 @@ void print_dev_latency(void) fd = open(path, O_RDONLY); if (fd < 0) { - warn("fopen %s\n", path); + warnx("capget(CAP_SYS_ADMIN) failed, try \"# setcap cap_sys_admin=ep %s\"", progname); return; } retval = read(fd, (void *)&value, sizeof(int)); if (retval != sizeof(int)) { - warn("read %s\n", path); + warn("read failed %s", path); close(fd); return; } @@ -5543,7 +5543,7 @@ void process_cpuid() edx_flags = edx; if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch)) - warnx("get_msr(UCODE)\n"); + warnx("get_msr(UCODE)"); /* * check max extended function levels of CPUID. @@ -6225,7 +6225,7 @@ int get_and_dump_counters(void) void print_version() { - fprintf(outf, "turbostat version 2022.10.04 - Len Brown <lenb@kernel.org>\n"); + fprintf(outf, "turbostat version 2023.03.17 - Len Brown <lenb@kernel.org>\n"); } #define COMMAND_LINE_SIZE 2048 diff --git a/tools/rcu/extract-stall.sh b/tools/rcu/extract-stall.sh index e565697c9f90..08a39ad44320 100644..100755 --- a/tools/rcu/extract-stall.sh +++ b/tools/rcu/extract-stall.sh @@ -1,11 +1,25 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0+ -# -# Extract any RCU CPU stall warnings present in specified file. -# Filter out clocksource lines. Note that preceding-lines excludes the -# initial line of the stall warning but trailing-lines includes it. -# -# Usage: extract-stall.sh dmesg-file [ preceding-lines [ trailing-lines ] ] + +usage() { + echo Extract any RCU CPU stall warnings present in specified file. + echo Filter out clocksource lines. Note that preceding-lines excludes the + echo initial line of the stall warning but trailing-lines includes it. + echo + echo Usage: $(basename $0) dmesg-file [ preceding-lines [ trailing-lines ] ] + echo + echo Error: $1 +} + +# Terminate the script, if the argument is missing + +if test -f "$1" && test -r "$1" +then + : +else + usage "Console log file \"$1\" missing or unreadable." + exit 1 +fi echo $1 preceding_lines="${2-3}" diff --git a/tools/scripts/Makefile.arch b/tools/scripts/Makefile.arch index 0c6c7f456887..1c72d07cb9fe 100644 --- a/tools/scripts/Makefile.arch +++ b/tools/scripts/Makefile.arch @@ -5,7 +5,7 @@ HOSTARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ -e s/s390x/s390/ -e s/parisc64/parisc/ \ -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \ - -e s/riscv.*/riscv/) + -e s/riscv.*/riscv/ -e s/loongarch.*/loongarch/) ifndef ARCH ARCH := $(HOSTARCH) @@ -34,6 +34,15 @@ ifeq ($(ARCH),sh64) SRCARCH := sh endif +# Additional ARCH settings for loongarch +ifeq ($(ARCH),loongarch32) + SRCARCH := loongarch +endif + +ifeq ($(ARCH),loongarch64) + SRCARCH := loongarch +endif + LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) ifeq ($(LP64), 1) IS_64_BIT := 1 diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index 0805f08af8b3..fba7bec96acd 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -10,6 +10,7 @@ ldflags-y += --wrap=devm_cxl_add_passthrough_decoder ldflags-y += --wrap=devm_cxl_enumerate_decoders ldflags-y += --wrap=cxl_await_media_ready ldflags-y += --wrap=cxl_hdm_decode_init +ldflags-y += --wrap=cxl_dvsec_rr_decode ldflags-y += --wrap=cxl_rcrb_to_component DRIVERS := ../../../drivers @@ -17,28 +18,34 @@ CXL_SRC := $(DRIVERS)/cxl CXL_CORE_SRC := $(DRIVERS)/cxl/core ccflags-y := -I$(srctree)/drivers/cxl/ ccflags-y += -D__mock=__weak +ccflags-y += -DTRACE_INCLUDE_PATH=$(CXL_CORE_SRC) -I$(srctree)/drivers/cxl/core/ obj-m += cxl_acpi.o cxl_acpi-y := $(CXL_SRC)/acpi.o cxl_acpi-y += mock_acpi.o cxl_acpi-y += config_check.o +cxl_acpi-y += cxl_acpi_test.o obj-m += cxl_pmem.o cxl_pmem-y := $(CXL_SRC)/pmem.o cxl_pmem-y += $(CXL_SRC)/security.o cxl_pmem-y += config_check.o +cxl_pmem-y += cxl_pmem_test.o obj-m += cxl_port.o cxl_port-y := $(CXL_SRC)/port.o cxl_port-y += config_check.o +cxl_port-y += cxl_port_test.o + obj-m += cxl_mem.o cxl_mem-y := $(CXL_SRC)/mem.o cxl_mem-y += config_check.o +cxl_mem-y += cxl_mem_test.o obj-m += cxl_core.o @@ -49,7 +56,9 @@ cxl_core-y += $(CXL_CORE_SRC)/memdev.o cxl_core-y += $(CXL_CORE_SRC)/mbox.o cxl_core-y += $(CXL_CORE_SRC)/pci.o cxl_core-y += $(CXL_CORE_SRC)/hdm.o +cxl_core-$(CONFIG_TRACING) += $(CXL_CORE_SRC)/trace.o cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o cxl_core-y += config_check.o +cxl_core-y += cxl_core_test.o obj-m += test/ diff --git a/tools/testing/cxl/config_check.c b/tools/testing/cxl/config_check.c index c4c457e59841..99b56b5f6edf 100644 --- a/tools/testing/cxl/config_check.c +++ b/tools/testing/cxl/config_check.c @@ -7,6 +7,7 @@ void check(void) * These kconfig symbols must be set to "m" for cxl_test to load * and operate. */ + BUILD_BUG_ON(!IS_ENABLED(CONFIG_64BIT)); BUILD_BUG_ON(!IS_MODULE(CONFIG_CXL_BUS)); BUILD_BUG_ON(!IS_MODULE(CONFIG_CXL_ACPI)); BUILD_BUG_ON(!IS_MODULE(CONFIG_CXL_PMEM)); diff --git a/tools/testing/cxl/cxl_acpi_test.c b/tools/testing/cxl/cxl_acpi_test.c new file mode 100644 index 000000000000..8602dc27c81c --- /dev/null +++ b/tools/testing/cxl/cxl_acpi_test.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ + +#include "watermark.h" + +cxl_test_watermark(cxl_acpi); diff --git a/tools/testing/cxl/cxl_core_test.c b/tools/testing/cxl/cxl_core_test.c new file mode 100644 index 000000000000..464a9255e4d6 --- /dev/null +++ b/tools/testing/cxl/cxl_core_test.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ + +#include "watermark.h" + +cxl_test_watermark(cxl_core); diff --git a/tools/testing/cxl/cxl_mem_test.c b/tools/testing/cxl/cxl_mem_test.c new file mode 100644 index 000000000000..ba7fb8a44288 --- /dev/null +++ b/tools/testing/cxl/cxl_mem_test.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ + +#include "watermark.h" + +cxl_test_watermark(cxl_mem); diff --git a/tools/testing/cxl/cxl_pmem_test.c b/tools/testing/cxl/cxl_pmem_test.c new file mode 100644 index 000000000000..3fd884fae537 --- /dev/null +++ b/tools/testing/cxl/cxl_pmem_test.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ + +#include "watermark.h" + +cxl_test_watermark(cxl_pmem); diff --git a/tools/testing/cxl/cxl_port_test.c b/tools/testing/cxl/cxl_port_test.c new file mode 100644 index 000000000000..be183917a9f6 --- /dev/null +++ b/tools/testing/cxl/cxl_port_test.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ + +#include "watermark.h" + +cxl_test_watermark(cxl_port); diff --git a/tools/testing/cxl/test/Kbuild b/tools/testing/cxl/test/Kbuild index 4e59e2c911f6..61d5f7bcddf9 100644 --- a/tools/testing/cxl/test/Kbuild +++ b/tools/testing/cxl/test/Kbuild @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -ccflags-y := -I$(srctree)/drivers/cxl/ +ccflags-y := -I$(srctree)/drivers/cxl/ -I$(srctree)/drivers/cxl/core obj-m += cxl_test.o obj-m += cxl_mock.o diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index 30ee680d38ff..bf00dc52fe96 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -9,6 +9,8 @@ #include <linux/pci.h> #include <linux/mm.h> #include <cxlmem.h> + +#include "../watermark.h" #include "mock.h" static int interleave_arithmetic; @@ -618,7 +620,8 @@ static struct acpi_pci_root *mock_acpi_pci_find_root(acpi_handle handle) return &mock_pci_root[host_bridge_index(adev)]; } -static struct cxl_hdm *mock_cxl_setup_hdm(struct cxl_port *port) +static struct cxl_hdm *mock_cxl_setup_hdm(struct cxl_port *port, + struct cxl_endpoint_dvsec_info *info) { struct cxl_hdm *cxlhdm = devm_kzalloc(&port->dev, sizeof(*cxlhdm), GFP_KERNEL); @@ -701,7 +704,144 @@ static int mock_decoder_reset(struct cxl_decoder *cxld) return 0; } -static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm) +static void default_mock_decoder(struct cxl_decoder *cxld) +{ + cxld->hpa_range = (struct range){ + .start = 0, + .end = -1, + }; + + cxld->interleave_ways = 1; + cxld->interleave_granularity = 256; + cxld->target_type = CXL_DECODER_EXPANDER; + cxld->commit = mock_decoder_commit; + cxld->reset = mock_decoder_reset; +} + +static int first_decoder(struct device *dev, void *data) +{ + struct cxl_decoder *cxld; + + if (!is_switch_decoder(dev)) + return 0; + cxld = to_cxl_decoder(dev); + if (cxld->id == 0) + return 1; + return 0; +} + +static void mock_init_hdm_decoder(struct cxl_decoder *cxld) +{ + struct acpi_cedt_cfmws *window = mock_cfmws[0]; + struct platform_device *pdev = NULL; + struct cxl_endpoint_decoder *cxled; + struct cxl_switch_decoder *cxlsd; + struct cxl_port *port, *iter; + const int size = SZ_512M; + struct cxl_memdev *cxlmd; + struct cxl_dport *dport; + struct device *dev; + bool hb0 = false; + u64 base; + int i; + + if (is_endpoint_decoder(&cxld->dev)) { + cxled = to_cxl_endpoint_decoder(&cxld->dev); + cxlmd = cxled_to_memdev(cxled); + WARN_ON(!dev_is_platform(cxlmd->dev.parent)); + pdev = to_platform_device(cxlmd->dev.parent); + + /* check is endpoint is attach to host-bridge0 */ + port = cxled_to_port(cxled); + do { + if (port->uport == &cxl_host_bridge[0]->dev) { + hb0 = true; + break; + } + if (is_cxl_port(port->dev.parent)) + port = to_cxl_port(port->dev.parent); + else + port = NULL; + } while (port); + port = cxled_to_port(cxled); + } + + /* + * The first decoder on the first 2 devices on the first switch + * attached to host-bridge0 mock a fake / static RAM region. All + * other decoders are default disabled. Given the round robin + * assignment those devices are named cxl_mem.0, and cxl_mem.4. + * + * See 'cxl list -BMPu -m cxl_mem.0,cxl_mem.4' + */ + if (!hb0 || pdev->id % 4 || pdev->id > 4 || cxld->id > 0) { + default_mock_decoder(cxld); + return; + } + + base = window->base_hpa; + cxld->hpa_range = (struct range) { + .start = base, + .end = base + size - 1, + }; + + cxld->interleave_ways = 2; + eig_to_granularity(window->granularity, &cxld->interleave_granularity); + cxld->target_type = CXL_DECODER_EXPANDER; + cxld->flags = CXL_DECODER_F_ENABLE; + cxled->state = CXL_DECODER_STATE_AUTO; + port->commit_end = cxld->id; + devm_cxl_dpa_reserve(cxled, 0, size / cxld->interleave_ways, 0); + cxld->commit = mock_decoder_commit; + cxld->reset = mock_decoder_reset; + + /* + * Now that endpoint decoder is set up, walk up the hierarchy + * and setup the switch and root port decoders targeting @cxlmd. + */ + iter = port; + for (i = 0; i < 2; i++) { + dport = iter->parent_dport; + iter = dport->port; + dev = device_find_child(&iter->dev, NULL, first_decoder); + /* + * Ancestor ports are guaranteed to be enumerated before + * @port, and all ports have at least one decoder. + */ + if (WARN_ON(!dev)) + continue; + cxlsd = to_cxl_switch_decoder(dev); + if (i == 0) { + /* put cxl_mem.4 second in the decode order */ + if (pdev->id == 4) + cxlsd->target[1] = dport; + else + cxlsd->target[0] = dport; + } else + cxlsd->target[0] = dport; + cxld = &cxlsd->cxld; + cxld->target_type = CXL_DECODER_EXPANDER; + cxld->flags = CXL_DECODER_F_ENABLE; + iter->commit_end = 0; + /* + * Switch targets 2 endpoints, while host bridge targets + * one root port + */ + if (i == 0) + cxld->interleave_ways = 2; + else + cxld->interleave_ways = 1; + cxld->interleave_granularity = 256; + cxld->hpa_range = (struct range) { + .start = base, + .end = base + size - 1, + }; + put_device(dev); + } +} + +static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, + struct cxl_endpoint_dvsec_info *info) { struct cxl_port *port = cxlhdm->port; struct cxl_port *parent_port = to_cxl_port(port->dev.parent); @@ -746,16 +886,7 @@ static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm) cxld = &cxled->cxld; } - cxld->hpa_range = (struct range) { - .start = 0, - .end = -1, - }; - - cxld->interleave_ways = min_not_zero(target_count, 1); - cxld->interleave_granularity = SZ_4K; - cxld->target_type = CXL_DECODER_EXPANDER; - cxld->commit = mock_decoder_commit; - cxld->reset = mock_decoder_reset; + mock_init_hdm_decoder(cxld); if (target_count) { rc = device_for_each_child(port->uport, &ctx, @@ -1119,6 +1250,12 @@ static __init int cxl_test_init(void) { int rc, i; + cxl_acpi_test(); + cxl_core_test(); + cxl_mem_test(); + cxl_pmem_test(); + cxl_port_test(); + register_cxl_mock_ops(&cxl_mock_ops); cxl_mock_pool = gen_pool_create(ilog2(SZ_2M), NUMA_NO_NODE); @@ -1135,11 +1272,9 @@ static __init int cxl_test_init(void) if (interleave_arithmetic == 1) { cfmws_start = CFMWS_XOR_ARRAY_START; cfmws_end = CFMWS_XOR_ARRAY_END; - dev_dbg(NULL, "cxl_test loading xor math option\n"); } else { cfmws_start = CFMWS_MOD_ARRAY_START; cfmws_end = CFMWS_MOD_ARRAY_END; - dev_dbg(NULL, "cxl_test loading modulo math option\n"); } rc = populate_cedt(); @@ -1326,7 +1461,7 @@ static __exit void cxl_test_exit(void) unregister_cxl_mock_ops(&cxl_mock_ops); } -module_param(interleave_arithmetic, int, 0000); +module_param(interleave_arithmetic, int, 0444); MODULE_PARM_DESC(interleave_arithmetic, "Modulo:0, XOR:1"); module_init(cxl_test_init); module_exit(cxl_test_exit); diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 5e4ecd93f1d2..9263b04d35f7 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -9,6 +9,8 @@ #include <linux/bits.h> #include <cxlmem.h> +#include "trace.h" + #define LSA_SIZE SZ_128K #define DEV_SIZE SZ_2G #define EFFECT(x) (1U << x) @@ -67,6 +69,26 @@ static struct { #define PASS_TRY_LIMIT 3 +#define CXL_TEST_EVENT_CNT_MAX 15 + +/* Set a number of events to return at a time for simulation. */ +#define CXL_TEST_EVENT_CNT 3 + +struct mock_event_log { + u16 clear_idx; + u16 cur_idx; + u16 nr_events; + u16 nr_overflow; + u16 overflow_reset; + struct cxl_event_record_raw *events[CXL_TEST_EVENT_CNT_MAX]; +}; + +struct mock_event_store { + struct cxl_dev_state *cxlds; + struct mock_event_log mock_logs[CXL_EVENT_TYPE_MAX]; + u32 ev_status; +}; + struct cxl_mockmem_data { void *lsa; u32 security_state; @@ -74,9 +96,317 @@ struct cxl_mockmem_data { u8 master_pass[NVDIMM_PASSPHRASE_LEN]; int user_limit; int master_limit; + struct mock_event_store mes; + u8 event_buf[SZ_4K]; +}; + +static struct mock_event_log *event_find_log(struct device *dev, int log_type) +{ + struct cxl_mockmem_data *mdata = dev_get_drvdata(dev); + + if (log_type >= CXL_EVENT_TYPE_MAX) + return NULL; + return &mdata->mes.mock_logs[log_type]; +} +static struct cxl_event_record_raw *event_get_current(struct mock_event_log *log) +{ + return log->events[log->cur_idx]; +} + +static void event_reset_log(struct mock_event_log *log) +{ + log->cur_idx = 0; + log->clear_idx = 0; + log->nr_overflow = log->overflow_reset; +} + +/* Handle can never be 0 use 1 based indexing for handle */ +static u16 event_get_clear_handle(struct mock_event_log *log) +{ + return log->clear_idx + 1; +} + +/* Handle can never be 0 use 1 based indexing for handle */ +static __le16 event_get_cur_event_handle(struct mock_event_log *log) +{ + u16 cur_handle = log->cur_idx + 1; + + return cpu_to_le16(cur_handle); +} + +static bool event_log_empty(struct mock_event_log *log) +{ + return log->cur_idx == log->nr_events; +} + +static void mes_add_event(struct mock_event_store *mes, + enum cxl_event_log_type log_type, + struct cxl_event_record_raw *event) +{ + struct mock_event_log *log; + + if (WARN_ON(log_type >= CXL_EVENT_TYPE_MAX)) + return; + + log = &mes->mock_logs[log_type]; + + if ((log->nr_events + 1) > CXL_TEST_EVENT_CNT_MAX) { + log->nr_overflow++; + log->overflow_reset = log->nr_overflow; + return; + } + + log->events[log->nr_events] = event; + log->nr_events++; +} + +static int mock_get_event(struct cxl_dev_state *cxlds, + struct cxl_mbox_cmd *cmd) +{ + struct cxl_get_event_payload *pl; + struct mock_event_log *log; + u16 nr_overflow; + u8 log_type; + int i; + + if (cmd->size_in != sizeof(log_type)) + return -EINVAL; + + if (cmd->size_out < struct_size(pl, records, CXL_TEST_EVENT_CNT)) + return -EINVAL; + + log_type = *((u8 *)cmd->payload_in); + if (log_type >= CXL_EVENT_TYPE_MAX) + return -EINVAL; + + memset(cmd->payload_out, 0, cmd->size_out); + + log = event_find_log(cxlds->dev, log_type); + if (!log || event_log_empty(log)) + return 0; + + pl = cmd->payload_out; + + for (i = 0; i < CXL_TEST_EVENT_CNT && !event_log_empty(log); i++) { + memcpy(&pl->records[i], event_get_current(log), + sizeof(pl->records[i])); + pl->records[i].hdr.handle = event_get_cur_event_handle(log); + log->cur_idx++; + } + + pl->record_count = cpu_to_le16(i); + if (!event_log_empty(log)) + pl->flags |= CXL_GET_EVENT_FLAG_MORE_RECORDS; + + if (log->nr_overflow) { + u64 ns; + + pl->flags |= CXL_GET_EVENT_FLAG_OVERFLOW; + pl->overflow_err_count = cpu_to_le16(nr_overflow); + ns = ktime_get_real_ns(); + ns -= 5000000000; /* 5s ago */ + pl->first_overflow_timestamp = cpu_to_le64(ns); + ns = ktime_get_real_ns(); + ns -= 1000000000; /* 1s ago */ + pl->last_overflow_timestamp = cpu_to_le64(ns); + } + + return 0; +} + +static int mock_clear_event(struct cxl_dev_state *cxlds, + struct cxl_mbox_cmd *cmd) +{ + struct cxl_mbox_clear_event_payload *pl = cmd->payload_in; + struct mock_event_log *log; + u8 log_type = pl->event_log; + u16 handle; + int nr; + + if (log_type >= CXL_EVENT_TYPE_MAX) + return -EINVAL; + + log = event_find_log(cxlds->dev, log_type); + if (!log) + return 0; /* No mock data in this log */ + + /* + * This check is technically not invalid per the specification AFAICS. + * (The host could 'guess' handles and clear them in order). + * However, this is not good behavior for the host so test it. + */ + if (log->clear_idx + pl->nr_recs > log->cur_idx) { + dev_err(cxlds->dev, + "Attempting to clear more events than returned!\n"); + return -EINVAL; + } + + /* Check handle order prior to clearing events */ + for (nr = 0, handle = event_get_clear_handle(log); + nr < pl->nr_recs; + nr++, handle++) { + if (handle != le16_to_cpu(pl->handles[nr])) { + dev_err(cxlds->dev, "Clearing events out of order\n"); + return -EINVAL; + } + } + + if (log->nr_overflow) + log->nr_overflow = 0; + + /* Clear events */ + log->clear_idx += pl->nr_recs; + return 0; +} + +static void cxl_mock_event_trigger(struct device *dev) +{ + struct cxl_mockmem_data *mdata = dev_get_drvdata(dev); + struct mock_event_store *mes = &mdata->mes; + int i; + + for (i = CXL_EVENT_TYPE_INFO; i < CXL_EVENT_TYPE_MAX; i++) { + struct mock_event_log *log; + + log = event_find_log(dev, i); + if (log) + event_reset_log(log); + } + + cxl_mem_get_event_records(mes->cxlds, mes->ev_status); +} + +struct cxl_event_record_raw maint_needed = { + .hdr = { + .id = UUID_INIT(0xBA5EBA11, 0xABCD, 0xEFEB, + 0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5), + .length = sizeof(struct cxl_event_record_raw), + .flags[0] = CXL_EVENT_RECORD_FLAG_MAINT_NEEDED, + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0xa5b6), + }, + .data = { 0xDE, 0xAD, 0xBE, 0xEF }, +}; + +struct cxl_event_record_raw hardware_replace = { + .hdr = { + .id = UUID_INIT(0xABCDEFEB, 0xBA11, 0xBA5E, + 0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5), + .length = sizeof(struct cxl_event_record_raw), + .flags[0] = CXL_EVENT_RECORD_FLAG_HW_REPLACE, + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0xb6a5), + }, + .data = { 0xDE, 0xAD, 0xBE, 0xEF }, +}; + +struct cxl_event_gen_media gen_media = { + .hdr = { + .id = UUID_INIT(0xfbcd0a77, 0xc260, 0x417f, + 0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6), + .length = sizeof(struct cxl_event_gen_media), + .flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT, + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0), + }, + .phys_addr = cpu_to_le64(0x2000), + .descriptor = CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT, + .type = CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR, + .transaction_type = CXL_GMER_TRANS_HOST_WRITE, + /* .validity_flags = <set below> */ + .channel = 1, + .rank = 30 +}; + +struct cxl_event_dram dram = { + .hdr = { + .id = UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, + 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24), + .length = sizeof(struct cxl_event_dram), + .flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED, + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0), + }, + .phys_addr = cpu_to_le64(0x8000), + .descriptor = CXL_GMER_EVT_DESC_THRESHOLD_EVENT, + .type = CXL_GMER_MEM_EVT_TYPE_INV_ADDR, + .transaction_type = CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB, + /* .validity_flags = <set below> */ + .channel = 1, + .bank_group = 5, + .bank = 2, + .column = {0xDE, 0xAD}, }; +struct cxl_event_mem_module mem_module = { + .hdr = { + .id = UUID_INIT(0xfe927475, 0xdd59, 0x4339, + 0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74), + .length = sizeof(struct cxl_event_mem_module), + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0), + }, + .event_type = CXL_MMER_TEMP_CHANGE, + .info = { + .health_status = CXL_DHI_HS_PERFORMANCE_DEGRADED, + .media_status = CXL_DHI_MS_ALL_DATA_LOST, + .add_status = (CXL_DHI_AS_CRITICAL << 2) | + (CXL_DHI_AS_WARNING << 4) | + (CXL_DHI_AS_WARNING << 5), + .device_temp = { 0xDE, 0xAD}, + .dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef }, + .cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef }, + .cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef }, + } +}; + +static void cxl_mock_add_event_logs(struct mock_event_store *mes) +{ + put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK, + &gen_media.validity_flags); + + put_unaligned_le16(CXL_DER_VALID_CHANNEL | CXL_DER_VALID_BANK_GROUP | + CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN, + &dram.validity_flags); + + mes_add_event(mes, CXL_EVENT_TYPE_INFO, &maint_needed); + mes_add_event(mes, CXL_EVENT_TYPE_INFO, + (struct cxl_event_record_raw *)&gen_media); + mes_add_event(mes, CXL_EVENT_TYPE_INFO, + (struct cxl_event_record_raw *)&mem_module); + mes->ev_status |= CXLDEV_EVENT_STATUS_INFO; + + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &maint_needed); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, + (struct cxl_event_record_raw *)&dram); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, + (struct cxl_event_record_raw *)&gen_media); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, + (struct cxl_event_record_raw *)&mem_module); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, + (struct cxl_event_record_raw *)&dram); + /* Overflow this log */ + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace); + mes->ev_status |= CXLDEV_EVENT_STATUS_FAIL; + + mes_add_event(mes, CXL_EVENT_TYPE_FATAL, &hardware_replace); + mes_add_event(mes, CXL_EVENT_TYPE_FATAL, + (struct cxl_event_record_raw *)&dram); + mes->ev_status |= CXLDEV_EVENT_STATUS_FATAL; +} + static int mock_gsl(struct cxl_mbox_cmd *cmd) { if (cmd->size_out < sizeof(mock_gsl_payload)) @@ -582,6 +912,12 @@ static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd * case CXL_MBOX_OP_GET_PARTITION_INFO: rc = mock_partition_info(cxlds, cmd); break; + case CXL_MBOX_OP_GET_EVENT_RECORD: + rc = mock_get_event(cxlds, cmd); + break; + case CXL_MBOX_OP_CLEAR_EVENT_RECORD: + rc = mock_clear_event(cxlds, cmd); + break; case CXL_MBOX_OP_SET_LSA: rc = mock_set_lsa(cxlds, cmd); break; @@ -628,6 +964,15 @@ static bool is_rcd(struct platform_device *pdev) return !!id->driver_data; } +static ssize_t event_trigger_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + cxl_mock_event_trigger(dev); + return count; +} +static DEVICE_ATTR_WO(event_trigger); + static int cxl_mock_mem_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -655,6 +1000,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) cxlds->serial = pdev->id; cxlds->mbox_send = cxl_mock_mbox_send; cxlds->payload_size = SZ_4K; + cxlds->event.buf = (struct cxl_get_event_payload *) mdata->event_buf; if (is_rcd(pdev)) { cxlds->rcd = true; cxlds->component_reg_phys = CXL_RESOURCE_NONE; @@ -672,10 +1018,15 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) if (rc) return rc; + mdata->mes.cxlds = cxlds; + cxl_mock_add_event_logs(&mdata->mes); + cxlmd = devm_cxl_add_memdev(cxlds); if (IS_ERR(cxlmd)) return PTR_ERR(cxlmd); + cxl_mem_get_event_records(cxlds, CXLDEV_EVENT_STATUS_ALL); + return 0; } @@ -714,6 +1065,7 @@ static DEVICE_ATTR_RW(security_lock); static struct attribute *cxl_mock_mem_attrs[] = { &dev_attr_security_lock.attr, + &dev_attr_event_trigger.attr, NULL }; ATTRIBUTE_GROUPS(cxl_mock_mem); diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index 5dface08e0de..c4e53f22e421 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -131,16 +131,18 @@ __wrap_nvdimm_bus_register(struct device *dev, } EXPORT_SYMBOL_GPL(__wrap_nvdimm_bus_register); -struct cxl_hdm *__wrap_devm_cxl_setup_hdm(struct cxl_port *port) +struct cxl_hdm *__wrap_devm_cxl_setup_hdm(struct cxl_port *port, + struct cxl_endpoint_dvsec_info *info) + { int index; struct cxl_hdm *cxlhdm; struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); if (ops && ops->is_mock_port(port->uport)) - cxlhdm = ops->devm_cxl_setup_hdm(port); + cxlhdm = ops->devm_cxl_setup_hdm(port, info); else - cxlhdm = devm_cxl_setup_hdm(port); + cxlhdm = devm_cxl_setup_hdm(port, info); put_cxl_mock_ops(index); return cxlhdm; @@ -162,16 +164,17 @@ int __wrap_devm_cxl_add_passthrough_decoder(struct cxl_port *port) } EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_add_passthrough_decoder, CXL); -int __wrap_devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm) +int __wrap_devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, + struct cxl_endpoint_dvsec_info *info) { int rc, index; struct cxl_port *port = cxlhdm->port; struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); if (ops && ops->is_mock_port(port->uport)) - rc = ops->devm_cxl_enumerate_decoders(cxlhdm); + rc = ops->devm_cxl_enumerate_decoders(cxlhdm, info); else - rc = devm_cxl_enumerate_decoders(cxlhdm); + rc = devm_cxl_enumerate_decoders(cxlhdm, info); put_cxl_mock_ops(index); return rc; @@ -209,7 +212,8 @@ int __wrap_cxl_await_media_ready(struct cxl_dev_state *cxlds) EXPORT_SYMBOL_NS_GPL(__wrap_cxl_await_media_ready, CXL); int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds, - struct cxl_hdm *cxlhdm) + struct cxl_hdm *cxlhdm, + struct cxl_endpoint_dvsec_info *info) { int rc = 0, index; struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); @@ -217,13 +221,29 @@ int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds, if (ops && ops->is_mock_dev(cxlds->dev)) rc = 0; else - rc = cxl_hdm_decode_init(cxlds, cxlhdm); + rc = cxl_hdm_decode_init(cxlds, cxlhdm, info); put_cxl_mock_ops(index); return rc; } EXPORT_SYMBOL_NS_GPL(__wrap_cxl_hdm_decode_init, CXL); +int __wrap_cxl_dvsec_rr_decode(struct device *dev, int dvsec, + struct cxl_endpoint_dvsec_info *info) +{ + int rc = 0, index; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + + if (ops && ops->is_mock_dev(dev)) + rc = 0; + else + rc = cxl_dvsec_rr_decode(dev, dvsec, info); + put_cxl_mock_ops(index); + + return rc; +} +EXPORT_SYMBOL_NS_GPL(__wrap_cxl_dvsec_rr_decode, CXL); + resource_size_t __wrap_cxl_rcrb_to_component(struct device *dev, resource_size_t rcrb, enum cxl_rcrb which) diff --git a/tools/testing/cxl/test/mock.h b/tools/testing/cxl/test/mock.h index ef33f159375e..bef8817b01f2 100644 --- a/tools/testing/cxl/test/mock.h +++ b/tools/testing/cxl/test/mock.h @@ -23,9 +23,11 @@ struct cxl_mock_ops { bool (*is_mock_port)(struct device *dev); bool (*is_mock_dev)(struct device *dev); int (*devm_cxl_port_enumerate_dports)(struct cxl_port *port); - struct cxl_hdm *(*devm_cxl_setup_hdm)(struct cxl_port *port); + struct cxl_hdm *(*devm_cxl_setup_hdm)( + struct cxl_port *port, struct cxl_endpoint_dvsec_info *info); int (*devm_cxl_add_passthrough_decoder)(struct cxl_port *port); - int (*devm_cxl_enumerate_decoders)(struct cxl_hdm *hdm); + int (*devm_cxl_enumerate_decoders)( + struct cxl_hdm *hdm, struct cxl_endpoint_dvsec_info *info); }; void register_cxl_mock_ops(struct cxl_mock_ops *ops); diff --git a/tools/testing/cxl/watermark.h b/tools/testing/cxl/watermark.h new file mode 100644 index 000000000000..9d81d4a5f6be --- /dev/null +++ b/tools/testing/cxl/watermark.h @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ +#ifndef _TEST_CXL_WATERMARK_H_ +#define _TEST_CXL_WATERMARK_H_ +#include <linux/module.h> +#include <linux/printk.h> + +int cxl_acpi_test(void); +int cxl_core_test(void); +int cxl_mem_test(void); +int cxl_pmem_test(void); +int cxl_port_test(void); + +/* + * dummy routine for cxl_test to validate it is linking to the properly + * mocked module and not the standard one from the base tree. + */ +#define cxl_test_watermark(x) \ +int x##_test(void) \ +{ \ + pr_debug("%s for cxl_test\n", KBUILD_MODNAME); \ + return 0; \ +} \ +EXPORT_SYMBOL(x##_test) +#endif /* _TEST_CXL_WATERMARK_H_ */ diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index 741f15420467..3905c43369c3 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -123,7 +123,7 @@ def _suites_from_test_list(tests: List[str]) -> List[str]: parts = t.split('.', maxsplit=2) if len(parts) != 2: raise ValueError(f'internal KUnit error, test name should be of the form "<suite>.<test>", got "{t}"') - suite, case = parts + suite, _ = parts if not suites or suites[-1] != suite: suites.append(suite) return suites @@ -269,7 +269,7 @@ def massage_argv(argv: Sequence[str]) -> Sequence[str]: def get_default_jobs() -> int: return len(os.sched_getaffinity(0)) -def add_common_opts(parser) -> None: +def add_common_opts(parser: argparse.ArgumentParser) -> None: parser.add_argument('--build_dir', help='As in the make command, it specifies the build ' 'directory.', @@ -320,13 +320,13 @@ def add_common_opts(parser) -> None: help='Additional QEMU arguments, e.g. "-smp 8"', action='append', metavar='') -def add_build_opts(parser) -> None: +def add_build_opts(parser: argparse.ArgumentParser) -> None: parser.add_argument('--jobs', help='As in the make command, "Specifies the number of ' 'jobs (commands) to run simultaneously."', type=int, default=get_default_jobs(), metavar='N') -def add_exec_opts(parser) -> None: +def add_exec_opts(parser: argparse.ArgumentParser) -> None: parser.add_argument('--timeout', help='maximum number of seconds to allow for all tests ' 'to run. This does not include time taken to build the ' @@ -351,7 +351,7 @@ def add_exec_opts(parser) -> None: type=str, choices=['suite', 'test']) -def add_parse_opts(parser) -> None: +def add_parse_opts(parser: argparse.ArgumentParser) -> None: parser.add_argument('--raw_output', help='If set don\'t parse output from kernel. ' 'By default, filters to just KUnit output. Use ' '--raw_output=all to show everything', @@ -386,7 +386,7 @@ def tree_from_args(cli_args: argparse.Namespace) -> kunit_kernel.LinuxSourceTree extra_qemu_args=qemu_args) -def run_handler(cli_args): +def run_handler(cli_args: argparse.Namespace) -> None: if not os.path.exists(cli_args.build_dir): os.mkdir(cli_args.build_dir) @@ -405,7 +405,7 @@ def run_handler(cli_args): sys.exit(1) -def config_handler(cli_args): +def config_handler(cli_args: argparse.Namespace) -> None: if cli_args.build_dir and ( not os.path.exists(cli_args.build_dir)): os.mkdir(cli_args.build_dir) @@ -421,7 +421,7 @@ def config_handler(cli_args): sys.exit(1) -def build_handler(cli_args): +def build_handler(cli_args: argparse.Namespace) -> None: linux = tree_from_args(cli_args) request = KunitBuildRequest(build_dir=cli_args.build_dir, make_options=cli_args.make_options, @@ -434,7 +434,7 @@ def build_handler(cli_args): sys.exit(1) -def exec_handler(cli_args): +def exec_handler(cli_args: argparse.Namespace) -> None: linux = tree_from_args(cli_args) exec_request = KunitExecRequest(raw_output=cli_args.raw_output, build_dir=cli_args.build_dir, @@ -450,10 +450,10 @@ def exec_handler(cli_args): sys.exit(1) -def parse_handler(cli_args): +def parse_handler(cli_args: argparse.Namespace) -> None: if cli_args.file is None: - sys.stdin.reconfigure(errors='backslashreplace') # pytype: disable=attribute-error - kunit_output = sys.stdin + sys.stdin.reconfigure(errors='backslashreplace') # type: ignore + kunit_output = sys.stdin # type: Iterable[str] else: with open(cli_args.file, 'r', errors='backslashreplace') as f: kunit_output = f.read().splitlines() @@ -475,7 +475,7 @@ subcommand_handlers_map = { } -def main(argv): +def main(argv: Sequence[str]) -> None: parser = argparse.ArgumentParser( description='Helps writing and running KUnit tests.') subparser = parser.add_subparsers(dest='subcommand') diff --git a/tools/testing/kunit/kunit_config.py b/tools/testing/kunit/kunit_config.py index 48b5f34b2e5d..eb5dd01210b1 100644 --- a/tools/testing/kunit/kunit_config.py +++ b/tools/testing/kunit/kunit_config.py @@ -8,7 +8,7 @@ from dataclasses import dataclass import re -from typing import Dict, Iterable, List, Set, Tuple +from typing import Any, Dict, Iterable, List, Tuple CONFIG_IS_NOT_SET_PATTERN = r'^# CONFIG_(\w+) is not set$' CONFIG_PATTERN = r'^CONFIG_(\w+)=(\S+|".*")$' @@ -34,7 +34,7 @@ class Kconfig: def __init__(self) -> None: self._entries = {} # type: Dict[str, str] - def __eq__(self, other) -> bool: + def __eq__(self, other: Any) -> bool: if not isinstance(other, self.__class__): return False return self._entries == other._entries diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 53e90c335834..f01f94106129 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -16,9 +16,9 @@ import shutil import signal import threading from typing import Iterator, List, Optional, Tuple +from types import FrameType import kunit_config -from kunit_printer import stdout import qemu_config KCONFIG_PATH = '.config' @@ -57,7 +57,7 @@ class LinuxSourceTreeOperations: def make_arch_config(self, base_kunitconfig: kunit_config.Kconfig) -> kunit_config.Kconfig: return base_kunitconfig - def make_olddefconfig(self, build_dir: str, make_options) -> None: + def make_olddefconfig(self, build_dir: str, make_options: Optional[List[str]]) -> None: command = ['make', 'ARCH=' + self._linux_arch, 'O=' + build_dir, 'olddefconfig'] if self._cross_compile: command += ['CROSS_COMPILE=' + self._cross_compile] @@ -71,7 +71,7 @@ class LinuxSourceTreeOperations: except subprocess.CalledProcessError as e: raise ConfigError(e.output.decode()) - def make(self, jobs, build_dir: str, make_options) -> None: + def make(self, jobs: int, build_dir: str, make_options: Optional[List[str]]) -> None: command = ['make', 'ARCH=' + self._linux_arch, 'O=' + build_dir, '--jobs=' + str(jobs)] if make_options: command.extend(make_options) @@ -92,7 +92,7 @@ class LinuxSourceTreeOperations: if stderr: # likely only due to build warnings print(stderr.decode()) - def start(self, params: List[str], build_dir: str) -> subprocess.Popen: + def start(self, params: List[str], build_dir: str) -> subprocess.Popen[str]: raise RuntimeError('not implemented!') @@ -106,13 +106,14 @@ class LinuxSourceTreeOperationsQemu(LinuxSourceTreeOperations): self._kernel_path = qemu_arch_params.kernel_path self._kernel_command_line = qemu_arch_params.kernel_command_line + ' kunit_shutdown=reboot' self._extra_qemu_params = qemu_arch_params.extra_qemu_params + self._serial = qemu_arch_params.serial def make_arch_config(self, base_kunitconfig: kunit_config.Kconfig) -> kunit_config.Kconfig: kconfig = kunit_config.parse_from_string(self._kconfig) kconfig.merge_in_entries(base_kunitconfig) return kconfig - def start(self, params: List[str], build_dir: str) -> subprocess.Popen: + def start(self, params: List[str], build_dir: str) -> subprocess.Popen[str]: kernel_path = os.path.join(build_dir, self._kernel_path) qemu_command = ['qemu-system-' + self._qemu_arch, '-nodefaults', @@ -121,7 +122,7 @@ class LinuxSourceTreeOperationsQemu(LinuxSourceTreeOperations): '-append', ' '.join(params + [self._kernel_command_line]), '-no-reboot', '-nographic', - '-serial', 'stdio'] + self._extra_qemu_params + '-serial', self._serial] + self._extra_qemu_params # Note: shlex.join() does what we want, but requires python 3.8+. print('Running tests with:\n$', ' '.join(shlex.quote(arg) for arg in qemu_command)) return subprocess.Popen(qemu_command, @@ -133,7 +134,7 @@ class LinuxSourceTreeOperationsQemu(LinuxSourceTreeOperations): class LinuxSourceTreeOperationsUml(LinuxSourceTreeOperations): """An abstraction over command line operations performed on a source tree.""" - def __init__(self, cross_compile=None): + def __init__(self, cross_compile: Optional[str]=None): super().__init__(linux_arch='um', cross_compile=cross_compile) def make_arch_config(self, base_kunitconfig: kunit_config.Kconfig) -> kunit_config.Kconfig: @@ -141,7 +142,7 @@ class LinuxSourceTreeOperationsUml(LinuxSourceTreeOperations): kconfig.merge_in_entries(base_kunitconfig) return kconfig - def start(self, params: List[str], build_dir: str) -> subprocess.Popen: + def start(self, params: List[str], build_dir: str) -> subprocess.Popen[str]: """Runs the Linux UML binary. Must be named 'linux'.""" linux_bin = os.path.join(build_dir, 'linux') params.extend(['mem=1G', 'console=tty', 'kunit_shutdown=halt']) @@ -216,7 +217,7 @@ def _get_qemu_ops(config_path: str, if not hasattr(config, 'QEMU_ARCH'): raise ValueError('qemu_config module missing "QEMU_ARCH": ' + config_path) - params: qemu_config.QemuArchParams = config.QEMU_ARCH # type: ignore + params: qemu_config.QemuArchParams = config.QEMU_ARCH if extra_qemu_args: params.extra_qemu_params.extend(extra_qemu_args) return params.linux_arch, LinuxSourceTreeOperationsQemu( @@ -230,10 +231,10 @@ class LinuxSourceTree: build_dir: str, kunitconfig_paths: Optional[List[str]]=None, kconfig_add: Optional[List[str]]=None, - arch=None, - cross_compile=None, - qemu_config_path=None, - extra_qemu_args=None) -> None: + arch: Optional[str]=None, + cross_compile: Optional[str]=None, + qemu_config_path: Optional[str]=None, + extra_qemu_args: Optional[List[str]]=None) -> None: signal.signal(signal.SIGINT, self.signal_handler) if qemu_config_path: self._arch, self._ops = _get_qemu_ops(qemu_config_path, extra_qemu_args, cross_compile) @@ -276,7 +277,7 @@ class LinuxSourceTree: logging.error(message) return False - def build_config(self, build_dir: str, make_options) -> bool: + def build_config(self, build_dir: str, make_options: Optional[List[str]]) -> bool: kconfig_path = get_kconfig_path(build_dir) if build_dir and not os.path.exists(build_dir): os.mkdir(build_dir) @@ -304,7 +305,7 @@ class LinuxSourceTree: old_kconfig = kunit_config.parse_file(old_path) return old_kconfig != self._kconfig - def build_reconfig(self, build_dir: str, make_options) -> bool: + def build_reconfig(self, build_dir: str, make_options: Optional[List[str]]) -> bool: """Creates a new .config if it is not a subset of the .kunitconfig.""" kconfig_path = get_kconfig_path(build_dir) if not os.path.exists(kconfig_path): @@ -320,7 +321,7 @@ class LinuxSourceTree: os.remove(kconfig_path) return self.build_config(build_dir, make_options) - def build_kernel(self, jobs, build_dir: str, make_options) -> bool: + def build_kernel(self, jobs: int, build_dir: str, make_options: Optional[List[str]]) -> bool: try: self._ops.make_olddefconfig(build_dir, make_options) self._ops.make(jobs, build_dir, make_options) @@ -329,7 +330,7 @@ class LinuxSourceTree: return False return self.validate_config(build_dir) - def run_kernel(self, args=None, build_dir='', filter_glob='', timeout=None) -> Iterator[str]: + def run_kernel(self, args: Optional[List[str]]=None, build_dir: str='', filter_glob: str='', timeout: Optional[int]=None) -> Iterator[str]: if not args: args = [] if filter_glob: @@ -340,7 +341,7 @@ class LinuxSourceTree: assert process.stdout is not None # tell mypy it's set # Enforce the timeout in a background thread. - def _wait_proc(): + def _wait_proc() -> None: try: process.wait(timeout=timeout) except Exception as e: @@ -366,6 +367,6 @@ class LinuxSourceTree: waiter.join() subprocess.call(['stty', 'sane']) - def signal_handler(self, unused_sig, unused_frame) -> None: + def signal_handler(self, unused_sig: int, unused_frame: Optional[FrameType]) -> None: logging.error('Build interruption occurred. Cleaning console.') subprocess.call(['stty', 'sane']) diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index a225799f6b1b..fbc094f0567e 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -12,7 +12,6 @@ from __future__ import annotations from dataclasses import dataclass import re -import sys import textwrap from enum import Enum, auto diff --git a/tools/testing/kunit/kunit_printer.py b/tools/testing/kunit/kunit_printer.py index 5f1cc55ecdf5..015adf87dc2c 100644 --- a/tools/testing/kunit/kunit_printer.py +++ b/tools/testing/kunit/kunit_printer.py @@ -15,7 +15,7 @@ _RESET = '\033[0;0m' class Printer: """Wraps a file object, providing utilities for coloring output, etc.""" - def __init__(self, output: typing.IO): + def __init__(self, output: typing.IO[str]): self._output = output self._use_color = output.isatty() diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 0c2190514103..be35999bb84f 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -328,7 +328,7 @@ class KUnitParserTest(unittest.TestCase): def test_parse_subtest_header(self): ktap_log = test_data_path('test_parse_subtest_header.log') with open(ktap_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + kunit_parser.parse_run_tests(file.readlines()) self.print_mock.assert_any_call(StrContains('suite (1 subtest)')) def test_show_test_output_on_failure(self): diff --git a/tools/testing/kunit/qemu_config.py b/tools/testing/kunit/qemu_config.py index 0b6a80398ccc..b1fba9016eed 100644 --- a/tools/testing/kunit/qemu_config.py +++ b/tools/testing/kunit/qemu_config.py @@ -17,3 +17,4 @@ class QemuArchParams: kernel_path: str kernel_command_line: str extra_qemu_params: List[str] + serial: str = 'stdio' diff --git a/tools/testing/kunit/qemu_configs/m68k.py b/tools/testing/kunit/qemu_configs/m68k.py new file mode 100644 index 000000000000..287fc386f8a7 --- /dev/null +++ b/tools/testing/kunit/qemu_configs/m68k.py @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0-only +from ..qemu_config import QemuArchParams + +QEMU_ARCH = QemuArchParams(linux_arch='m68k', + kconfig=''' +CONFIG_VIRT=y''', + qemu_arch='m68k', + kernel_path='vmlinux', + kernel_command_line='console=hvc0', + extra_qemu_params=['-machine', 'virt']) diff --git a/tools/testing/kunit/qemu_configs/sh.py b/tools/testing/kunit/qemu_configs/sh.py new file mode 100644 index 000000000000..78a474a5b95f --- /dev/null +++ b/tools/testing/kunit/qemu_configs/sh.py @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0-only +from ..qemu_config import QemuArchParams + +QEMU_ARCH = QemuArchParams(linux_arch='sh', + kconfig=''' +CONFIG_CPU_SUBTYPE_SH7751R=y +CONFIG_MEMORY_START=0x0c000000 +CONFIG_SH_RTS7751R2D=y +CONFIG_RTS7751R2D_PLUS=y +CONFIG_SERIAL_SH_SCI=y''', + qemu_arch='sh4', + kernel_path='arch/sh/boot/zImage', + kernel_command_line='console=ttySC1', + serial='null', + extra_qemu_params=[ + '-machine', 'r2d', + '-serial', 'mon:stdio']) diff --git a/tools/testing/kunit/run_checks.py b/tools/testing/kunit/run_checks.py index 066e6f938f6d..8208c3b3135e 100755 --- a/tools/testing/kunit/run_checks.py +++ b/tools/testing/kunit/run_checks.py @@ -23,7 +23,7 @@ commands: Dict[str, Sequence[str]] = { 'kunit_tool_test.py': ['./kunit_tool_test.py'], 'kunit smoke test': ['./kunit.py', 'run', '--kunitconfig=lib/kunit', '--build_dir=kunit_run_checks'], 'pytype': ['/bin/sh', '-c', 'pytype *.py'], - 'mypy': ['/bin/sh', '-c', 'mypy *.py'], + 'mypy': ['mypy', '--strict', '--exclude', '_test.py$', '--exclude', 'qemu_configs/', '.'], } # The user might not have mypy or pytype installed, skip them if so. @@ -37,7 +37,7 @@ def main(argv: Sequence[str]) -> None: if argv: raise RuntimeError('This script takes no arguments') - future_to_name: Dict[futures.Future, str] = {} + future_to_name: Dict[futures.Future[None], str] = {} executor = futures.ThreadPoolExecutor(max_workers=len(commands)) for name, argv in commands.items(): if name in necessary_deps and shutil.which(necessary_deps[name]) is None: @@ -73,7 +73,7 @@ def main(argv: Sequence[str]) -> None: sys.exit(1) -def run_cmd(argv: Sequence[str]): +def run_cmd(argv: Sequence[str]) -> None: subprocess.check_output(argv, stderr=subprocess.STDOUT, cwd=ABS_TOOL_PATH, timeout=TIMEOUT) diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 81fa7ec2e66a..4c89ff333f6f 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -108,6 +108,7 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mn->slot[1] != NULL); MT_BUG_ON(mt, mas_allocated(&mas) != 0); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); mas.node = MAS_START; mas_nomem(&mas, GFP_KERNEL); @@ -160,6 +161,7 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mas_allocated(&mas) != i); MT_BUG_ON(mt, !mn); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } @@ -173,11 +175,11 @@ static noinline void check_new_node(struct maple_tree *mt) if (!MAPLE_32BIT) { if (i >= 35) - e = i - 35; + e = i - 34; else if (i >= 5) - e = i - 5; + e = i - 4; else if (i >= 2) - e = i - 2; + e = i - 1; } else { if (i >= 4) e = i - 4; @@ -192,6 +194,7 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, not_empty(mn)); MT_BUG_ON(mt, mas_allocated(&mas) != i - 1); MT_BUG_ON(mt, !mn); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } @@ -210,6 +213,7 @@ static noinline void check_new_node(struct maple_tree *mt) mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); MT_BUG_ON(mt, mas_allocated(&mas) != j - 1); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } MT_BUG_ON(mt, mas_allocated(&mas) != 0); @@ -233,6 +237,7 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mas_allocated(&mas) != i - j); mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); MT_BUG_ON(mt, mas_allocated(&mas) != i - j - 1); } @@ -269,6 +274,7 @@ static noinline void check_new_node(struct maple_tree *mt) mn = mas_pop_node(&mas); /* get the next node. */ MT_BUG_ON(mt, mn == NULL); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } MT_BUG_ON(mt, mas_allocated(&mas) != 0); @@ -294,6 +300,7 @@ static noinline void check_new_node(struct maple_tree *mt) mn = mas_pop_node(&mas2); /* get the next node. */ MT_BUG_ON(mt, mn == NULL); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } MT_BUG_ON(mt, mas_allocated(&mas2) != 0); @@ -305,17 +312,17 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mas.node != MA_ERROR(-ENOMEM)); MT_BUG_ON(mt, !mas_nomem(&mas, GFP_KERNEL)); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 1); - MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS - 1); + MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS); mn = mas_pop_node(&mas); /* get the next node. */ MT_BUG_ON(mt, mn == NULL); MT_BUG_ON(mt, not_empty(mn)); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS); - MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS - 2); + MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS - 1); mas_push_node(&mas, mn); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 1); - MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS - 1); + MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS); /* Check the limit of pop/push/pop */ mas_node_count(&mas, MAPLE_ALLOC_SLOTS + 2); /* Request */ @@ -323,21 +330,23 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mas.node != MA_ERROR(-ENOMEM)); MT_BUG_ON(mt, !mas_nomem(&mas, GFP_KERNEL)); MT_BUG_ON(mt, mas_alloc_req(&mas)); - MT_BUG_ON(mt, mas.alloc->node_count); + MT_BUG_ON(mt, mas.alloc->node_count != 1); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 2); mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 1); - MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS - 1); + MT_BUG_ON(mt, mas.alloc->node_count != MAPLE_ALLOC_SLOTS); mas_push_node(&mas, mn); - MT_BUG_ON(mt, mas.alloc->node_count); + MT_BUG_ON(mt, mas.alloc->node_count != 1); MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 2); mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); for (i = 1; i <= MAPLE_ALLOC_SLOTS + 1; i++) { mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } MT_BUG_ON(mt, mas_allocated(&mas) != 0); @@ -375,6 +384,7 @@ static noinline void check_new_node(struct maple_tree *mt) mas_node_count(&mas, i); /* Request */ mas_nomem(&mas, GFP_KERNEL); /* Fill request */ mn = mas_pop_node(&mas); /* get the next node. */ + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); mas_destroy(&mas); @@ -382,10 +392,13 @@ static noinline void check_new_node(struct maple_tree *mt) mas_node_count(&mas, i); /* Request */ mas_nomem(&mas, GFP_KERNEL); /* Fill request */ mn = mas_pop_node(&mas); /* get the next node. */ + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); mn = mas_pop_node(&mas); /* get the next node. */ + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); mn = mas_pop_node(&mas); /* get the next node. */ + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); mas_destroy(&mas); } @@ -35342,7 +35355,7 @@ static noinline void check_prealloc(struct maple_tree *mt) for (i = 0; i <= max; i++) mtree_test_store_range(mt, i * 10, i * 10 + 5, &i); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35351,44 +35364,46 @@ static noinline void check_prealloc(struct maple_tree *mt) allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); mn = mas_pop_node(&mas); MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); mn = mas_pop_node(&mas); MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35397,12 +35412,12 @@ static noinline void check_prealloc(struct maple_tree *mt) MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1); mas_push_node(&mas, mn); MT_BUG_ON(mt, mas_allocated(&mas) != allocated); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35410,21 +35425,21 @@ static noinline void check_prealloc(struct maple_tree *mt) mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); MT_BUG_ON(mt, allocated != 1 + height * 3); mas_store_prealloc(&mas, ptr); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35432,14 +35447,14 @@ static noinline void check_prealloc(struct maple_tree *mt) mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); mt_set_non_kernel(1); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL & GFP_NOWAIT) == 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL & GFP_NOWAIT) == 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated != 0); mas_destroy(&mas); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated == 0); @@ -35447,7 +35462,7 @@ static noinline void check_prealloc(struct maple_tree *mt) mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); mt_set_non_kernel(1); - MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL & GFP_NOWAIT) == 0); + MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL & GFP_NOWAIT) == 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); MT_BUG_ON(mt, allocated != 0); @@ -35756,6 +35771,7 @@ void farmer_tests(void) tree.ma_root = mt_mk_node(node, maple_leaf_64); mt_dump(&tree); + node->parent = ma_parent_ptr(node); ma_free_rcu(node); /* Check things that will make lockdep angry */ diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 0ebd9cce49b9..97dcdaa656f6 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -58,6 +58,7 @@ TARGETS += nsfs TARGETS += pidfd TARGETS += pid_namespace TARGETS += powerpc +TARGETS += prctl TARGETS += proc TARGETS += pstore TARGETS += ptrace @@ -86,7 +87,7 @@ TARGETS += tmpfs TARGETS += tpm2 TARGETS += user TARGETS += vDSO -TARGETS += vm +TARGETS += mm TARGETS += x86 TARGETS += zram #Please keep the TARGETS list alphabetically sorted diff --git a/tools/testing/selftests/amd-pstate/Makefile b/tools/testing/selftests/amd-pstate/Makefile index 5fd1424db37d..c382f579fe94 100644 --- a/tools/testing/selftests/amd-pstate/Makefile +++ b/tools/testing/selftests/amd-pstate/Makefile @@ -4,10 +4,15 @@ # No binaries, but make sure arg-less "make" doesn't trigger "run_tests" all: -uname_M := $(shell uname -m 2>/dev/null || echo not) -ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) +ARCH ?= $(shell uname -m 2>/dev/null || echo not) +ARCH := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/) -TEST_PROGS := run.sh -TEST_FILES := basic.sh tbench.sh gitsource.sh +ifeq (x86,$(ARCH)) +TEST_FILES += ../../../power/x86/amd_pstate_tracer/amd_pstate_trace.py +TEST_FILES += ../../../power/x86/intel_pstate_tracer/intel_pstate_tracer.py +endif + +TEST_PROGS += run.sh +TEST_FILES += basic.sh tbench.sh gitsource.sh include ../lib.mk diff --git a/tools/testing/selftests/amd-pstate/gitsource.sh b/tools/testing/selftests/amd-pstate/gitsource.sh index dbc1fe45599d..5f2171f0116d 100755 --- a/tools/testing/selftests/amd-pstate/gitsource.sh +++ b/tools/testing/selftests/amd-pstate/gitsource.sh @@ -117,7 +117,7 @@ parse_gitsource() printf "Gitsource-$1-#$2 power consumption(J): $en_sum\n" | tee -a $OUTFILE_GIT.result # Permance is the number of run gitsource per second, denoted 1/t, where 1 is the number of run gitsource in t - # senconds. It is well known that P=E/t, where P is power measured in watts(W), E is energy measured in joules(J), + # seconds. It is well known that P=E/t, where P is power measured in watts(W), E is energy measured in joules(J), # and t is time measured in seconds(s). This means that performance per watt becomes # 1/t 1/t 1 # ----- = ----- = --- @@ -175,7 +175,7 @@ gather_gitsource() printf "Gitsource-$1 avg power consumption(J): $avg_en\n" | tee -a $OUTFILE_GIT.result # Permance is the number of run gitsource per second, denoted 1/t, where 1 is the number of run gitsource in t - # senconds. It is well known that P=E/t, where P is power measured in watts(W), E is energy measured in joules(J), + # seconds. It is well known that P=E/t, where P is power measured in watts(W), E is energy measured in joules(J), # and t is time measured in seconds(s). This means that performance per watt becomes # 1/t 1/t 1 # ----- = ----- = --- diff --git a/tools/testing/selftests/amd-pstate/run.sh b/tools/testing/selftests/amd-pstate/run.sh index 57cad57e59c0..de4d8e9c9565 100755 --- a/tools/testing/selftests/amd-pstate/run.sh +++ b/tools/testing/selftests/amd-pstate/run.sh @@ -244,7 +244,7 @@ prerequisite() if [ "$scaling_driver" != "$CURRENT_TEST" ]; then echo "$0 # Skipped: Test can only run on $CURRENT_TEST driver or run comparative test." echo "$0 # Please set X86_AMD_PSTATE enabled or run comparative test." - echo "$0 # Current cpufreq scaling drvier is $scaling_driver." + echo "$0 # Current cpufreq scaling driver is $scaling_driver." exit $ksft_skip fi else @@ -252,7 +252,7 @@ prerequisite() "tbench" | "gitsource") if [ "$scaling_driver" != "$COMPARATIVE_TEST" ]; then echo "$0 # Skipped: Comparison test can only run on $COMPARISON_TEST driver." - echo "$0 # Current cpufreq scaling drvier is $scaling_driver." + echo "$0 # Current cpufreq scaling driver is $scaling_driver." exit $ksft_skip fi ;; diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile index 48f56c86ad45..b413b0af07f9 100644 --- a/tools/testing/selftests/arm64/fp/Makefile +++ b/tools/testing/selftests/arm64/fp/Makefile @@ -38,7 +38,7 @@ $(OUTPUT)/vec-syscfg: vec-syscfg.c $(OUTPUT)/rdvl.o $(OUTPUT)/vlset: vlset.c $(OUTPUT)/za-fork: za-fork.c $(OUTPUT)/za-fork-asm.o $(CC) -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \ - -include ../../../../include/nolibc/nolibc.h \ + -include ../../../../include/nolibc/nolibc.h -I../..\ -static -ffreestanding -Wall $^ -o $@ $(OUTPUT)/za-ptrace: za-ptrace.c $(OUTPUT)/za-test: za-test.S $(OUTPUT)/asm-utils.o diff --git a/tools/testing/selftests/arm64/fp/za-fork.c b/tools/testing/selftests/arm64/fp/za-fork.c index ff475c649e96..b86cb1049497 100644 --- a/tools/testing/selftests/arm64/fp/za-fork.c +++ b/tools/testing/selftests/arm64/fp/za-fork.c @@ -9,42 +9,9 @@ #include <linux/sched.h> #include <linux/wait.h> -#define EXPECTED_TESTS 1 - -static void putstr(const char *str) -{ - write(1, str, strlen(str)); -} - -static void putnum(unsigned int num) -{ - char c; - - if (num / 10) - putnum(num / 10); - - c = '0' + (num % 10); - write(1, &c, 1); -} +#include "kselftest.h" -static int tests_run; -static int tests_passed; -static int tests_failed; -static int tests_skipped; - -static void print_summary(void) -{ - if (tests_passed + tests_failed + tests_skipped != EXPECTED_TESTS) - putstr("# UNEXPECTED TEST COUNT: "); - - putstr("# Totals: pass:"); - putnum(tests_passed); - putstr(" fail:"); - putnum(tests_failed); - putstr(" xfail:0 xpass:0 skip:"); - putnum(tests_skipped); - putstr(" error:0\n"); -} +#define EXPECTED_TESTS 1 int fork_test(void); int verify_fork(void); @@ -63,22 +30,21 @@ int fork_test_c(void) if (newpid == 0) { /* In child */ if (!verify_fork()) { - putstr("# ZA state invalid in child\n"); + ksft_print_msg("ZA state invalid in child\n"); exit(0); } else { exit(1); } } if (newpid < 0) { - putstr("# fork() failed: -"); - putnum(-newpid); - putstr("\n"); + ksft_print_msg("fork() failed: %d\n", newpid); + return 0; } parent_result = verify_fork(); if (!parent_result) - putstr("# ZA state invalid in parent\n"); + ksft_print_msg("ZA state invalid in parent\n"); for (;;) { waiting = waitpid(newpid, &child_status, 0); @@ -86,18 +52,16 @@ int fork_test_c(void) if (waiting < 0) { if (errno == EINTR) continue; - putstr("# waitpid() failed: "); - putnum(errno); - putstr("\n"); + ksft_print_msg("waitpid() failed: %d\n", errno); return 0; } if (waiting != newpid) { - putstr("# waitpid() returned wrong PID\n"); + ksft_print_msg("waitpid() returned wrong PID\n"); return 0; } if (!WIFEXITED(child_status)) { - putstr("# child did not exit\n"); + ksft_print_msg("child did not exit\n"); return 0; } @@ -105,29 +69,14 @@ int fork_test_c(void) } } -#define run_test(name) \ - if (name()) { \ - tests_passed++; \ - } else { \ - tests_failed++; \ - putstr("not "); \ - } \ - putstr("ok "); \ - putnum(++tests_run); \ - putstr(" " #name "\n"); - int main(int argc, char **argv) { int ret, i; - putstr("TAP version 13\n"); - putstr("1.."); - putnum(EXPECTED_TESTS); - putstr("\n"); + ksft_print_header(); + ksft_set_plan(EXPECTED_TESTS); - putstr("# PID: "); - putnum(getpid()); - putstr("\n"); + ksft_print_msg("PID: %d\n", getpid()); /* * This test is run with nolibc which doesn't support hwcap and @@ -136,21 +85,16 @@ int main(int argc, char **argv) */ ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0); if (ret >= 0) { - run_test(fork_test); + ksft_test_result(fork_test(), "fork_test"); } else { - putstr("# SME support not present\n"); - + ksft_print_msg("SME not supported\n"); for (i = 0; i < EXPECTED_TESTS; i++) { - putstr("ok "); - putnum(i); - putstr(" skipped\n"); + ksft_test_result_skip("fork_test\n"); } - - tests_skipped += EXPECTED_TESTS; } - print_summary(); + ksft_finished(); return 0; } diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index cbb600be943d..210d643fda6c 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -879,6 +879,34 @@ static struct btf_raw_test raw_tests[] = { .btf_load_err = true, .err_str = "Invalid elem", }, +{ + .descr = "var after datasec, ptr followed by modifier", + .raw_types = { + /* .bss section */ /* [1] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 2), + sizeof(void*)+4), + BTF_VAR_SECINFO_ENC(4, 0, sizeof(void*)), + BTF_VAR_SECINFO_ENC(6, sizeof(void*), 4), + /* int */ /* [2] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int* */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), + BTF_VAR_ENC(NAME_TBD, 3, 0), /* [4] */ + /* const int */ /* [5] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 2), + BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */ + BTF_END_RAW, + }, + .str_sec = "\0a\0b\0c\0", + .str_sec_size = sizeof("\0a\0b\0c\0"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = sizeof(void*)+4, + .key_type_id = 0, + .value_type_id = 1, + .max_entries = 1, +}, /* Test member exceeds the size of struct. * * struct A { diff --git a/tools/testing/selftests/bpf/prog_tests/uninit_stack.c b/tools/testing/selftests/bpf/prog_tests/uninit_stack.c new file mode 100644 index 000000000000..e64c71948491 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/uninit_stack.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include "uninit_stack.skel.h" + +void test_uninit_stack(void) +{ + RUN_TESTS(uninit_stack); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c index 2666c84dbd01..8251a0fc6ee9 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c @@ -65,12 +65,13 @@ static int attach_tc_prog(struct bpf_tc_hook *hook, int fd) } /* The maximum permissible size is: PAGE_SIZE - sizeof(struct xdp_page_head) - - * sizeof(struct skb_shared_info) - XDP_PACKET_HEADROOM = 3368 bytes + * SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) - XDP_PACKET_HEADROOM = + * 3408 bytes for 64-byte cacheline and 3216 for 256-byte one. */ #if defined(__s390x__) -#define MAX_PKT_SIZE 3176 +#define MAX_PKT_SIZE 3216 #else -#define MAX_PKT_SIZE 3368 +#define MAX_PKT_SIZE 3408 #endif static void test_max_pkt_size(int fd) { @@ -166,8 +167,7 @@ void test_xdp_do_redirect(void) if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | - NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | - NETDEV_XDP_ACT_NDO_XMIT_SG, + NETDEV_XDP_ACT_RX_SG, "veth_src query_opts.feature_flags")) goto out; @@ -177,9 +177,34 @@ void test_xdp_do_redirect(void) if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG, + "veth_dst query_opts.feature_flags")) + goto out; + + /* Enable GRO */ + SYS("ethtool -K veth_src gro on"); + SYS("ethtool -K veth_dst gro on"); + + err = bpf_xdp_query(ifindex_src, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "veth_src bpf_xdp_query gro on")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | NETDEV_XDP_ACT_NDO_XMIT_SG, - "veth_dst query_opts.feature_flags")) + "veth_src query_opts.feature_flags gro on")) + goto out; + + err = bpf_xdp_query(ifindex_dst, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "veth_dst bpf_xdp_query gro on")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "veth_dst query_opts.feature_flags gro on")) goto out; memcpy(skel->rodata->expect_dst, &pkt_udp.eth.h_dest, ETH_ALEN); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c index aa4beae99f4f..8c5e98da9ae9 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c @@ -273,6 +273,8 @@ static int verify_xsk_metadata(struct xsk *xsk) if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash")) return -1; + ASSERT_EQ(meta->rx_hash_type, 0, "rx_hash_type"); + xsk_ring_cons__release(&xsk->rx, 1); refill_rx(xsk, comp_addr); diff --git a/tools/testing/selftests/bpf/progs/find_vma_fail1.c b/tools/testing/selftests/bpf/progs/find_vma_fail1.c index b3b326b8e2d1..6dab9cffda13 100644 --- a/tools/testing/selftests/bpf/progs/find_vma_fail1.c +++ b/tools/testing/selftests/bpf/progs/find_vma_fail1.c @@ -2,6 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include "vmlinux.h" #include <bpf/bpf_helpers.h> +#define vm_flags vm_start char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_deny_namespace.c b/tools/testing/selftests/bpf/progs/test_deny_namespace.c index 09ad5a4ebd1f..e96b901a733c 100644 --- a/tools/testing/selftests/bpf/progs/test_deny_namespace.c +++ b/tools/testing/selftests/bpf/progs/test_deny_namespace.c @@ -5,12 +5,10 @@ #include <errno.h> #include <linux/capability.h> -struct kernel_cap_struct { - __u32 cap[_LINUX_CAPABILITY_U32S_3]; -} __attribute__((preserve_access_index)); +typedef struct { unsigned long long val; } kernel_cap_t; struct cred { - struct kernel_cap_struct cap_effective; + kernel_cap_t cap_effective; } __attribute__((preserve_access_index)); char _license[] SEC("license") = "GPL"; @@ -18,15 +16,14 @@ char _license[] SEC("license") = "GPL"; SEC("lsm.s/userns_create") int BPF_PROG(test_userns_create, const struct cred *cred, int ret) { - struct kernel_cap_struct caps = cred->cap_effective; - int cap_index = CAP_TO_INDEX(CAP_SYS_ADMIN); - __u32 cap_mask = CAP_TO_MASK(CAP_SYS_ADMIN); + kernel_cap_t caps = cred->cap_effective; + __u64 cap_mask = 1ULL << CAP_SYS_ADMIN; if (ret) return 0; ret = -EPERM; - if (caps.cap[cap_index] & cap_mask) + if (caps.val & cap_mask) return 0; return -EPERM; diff --git a/tools/testing/selftests/bpf/progs/test_global_func10.c b/tools/testing/selftests/bpf/progs/test_global_func10.c index 98327bdbbfd2..8fba3f3649e2 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func10.c +++ b/tools/testing/selftests/bpf/progs/test_global_func10.c @@ -5,12 +5,12 @@ #include "bpf_misc.h" struct Small { - int x; + long x; }; struct Big { - int x; - int y; + long x; + long y; }; __noinline int foo(const struct Big *big) @@ -22,7 +22,7 @@ __noinline int foo(const struct Big *big) } SEC("cgroup_skb/ingress") -__failure __msg("invalid indirect read from stack") +__failure __msg("invalid indirect access to stack") int global_func10(struct __sk_buff *skb) { const struct Small small = {.x = skb->len }; diff --git a/tools/testing/selftests/bpf/progs/uninit_stack.c b/tools/testing/selftests/bpf/progs/uninit_stack.c new file mode 100644 index 000000000000..8a403470e557 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/uninit_stack.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +/* Read an uninitialized value from stack at a fixed offset */ +SEC("socket") +__naked int read_uninit_stack_fixed_off(void *ctx) +{ + asm volatile (" \ + r0 = 0; \ + /* force stack depth to be 128 */ \ + *(u64*)(r10 - 128) = r1; \ + r1 = *(u8 *)(r10 - 8 ); \ + r0 += r1; \ + r1 = *(u8 *)(r10 - 11); \ + r1 = *(u8 *)(r10 - 13); \ + r1 = *(u8 *)(r10 - 15); \ + r1 = *(u16*)(r10 - 16); \ + r1 = *(u32*)(r10 - 32); \ + r1 = *(u64*)(r10 - 64); \ + /* read from a spill of a wrong size, it is a separate \ + * branch in check_stack_read_fixed_off() \ + */ \ + *(u32*)(r10 - 72) = r1; \ + r1 = *(u64*)(r10 - 72); \ + r0 = 0; \ + exit; \ +" + ::: __clobber_all); +} + +/* Read an uninitialized value from stack at a variable offset */ +SEC("socket") +__naked int read_uninit_stack_var_off(void *ctx) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + /* force stack depth to be 64 */ \ + *(u64*)(r10 - 64) = r0; \ + r0 = -r0; \ + /* give r0 a range [-31, -1] */ \ + if r0 s<= -32 goto exit_%=; \ + if r0 s>= 0 goto exit_%=; \ + /* access stack using r0 */ \ + r1 = r10; \ + r1 += r0; \ + r2 = *(u8*)(r1 + 0); \ +exit_%=: r0 = 0; \ + exit; \ +" + : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +static __noinline void dummy(void) {} + +/* Pass a pointer to uninitialized stack memory to a helper. + * Passed memory block should be marked as STACK_MISC after helper call. + */ +SEC("socket") +__log_level(7) __msg("fp-104=mmmmmmmm") +__naked int helper_uninit_to_misc(void *ctx) +{ + asm volatile (" \ + /* force stack depth to be 128 */ \ + *(u64*)(r10 - 128) = r1; \ + r1 = r10; \ + r1 += -128; \ + r2 = 32; \ + call %[bpf_trace_printk]; \ + /* Call to dummy() forces print_verifier_state(..., true), \ + * thus showing the stack state, matched by __msg(). \ + */ \ + call %[dummy]; \ + r0 = 0; \ + exit; \ +" + : + : __imm(bpf_trace_printk), + __imm(dummy) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c index 4c55b4d79d3d..e1c787815e44 100644 --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -12,10 +12,14 @@ struct { __type(value, __u32); } xsk SEC(".maps"); +__u64 pkts_skip = 0; +__u64 pkts_fail = 0; +__u64 pkts_redir = 0; + extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, __u64 *timestamp) __ksym; -extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, - __u32 *hash) __ksym; +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, + enum xdp_rss_hash_type *rss_type) __ksym; SEC("xdp") int rx(struct xdp_md *ctx) @@ -26,7 +30,7 @@ int rx(struct xdp_md *ctx) struct udphdr *udp = NULL; struct iphdr *iph = NULL; struct xdp_meta *meta; - int ret; + int err; data = (void *)(long)ctx->data; data_end = (void *)(long)ctx->data_end; @@ -46,17 +50,20 @@ int rx(struct xdp_md *ctx) udp = NULL; } - if (!udp) + if (!udp) { + __sync_add_and_fetch(&pkts_skip, 1); return XDP_PASS; + } - if (udp->dest != bpf_htons(9091)) + /* Forwarding UDP:9091 to AF_XDP */ + if (udp->dest != bpf_htons(9091)) { + __sync_add_and_fetch(&pkts_skip, 1); return XDP_PASS; + } - bpf_printk("forwarding UDP:9091 to AF_XDP"); - - ret = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta)); - if (ret != 0) { - bpf_printk("bpf_xdp_adjust_meta returned %d", ret); + err = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta)); + if (err) { + __sync_add_and_fetch(&pkts_fail, 1); return XDP_PASS; } @@ -65,20 +72,19 @@ int rx(struct xdp_md *ctx) meta = data_meta; if (meta + 1 > data) { - bpf_printk("bpf_xdp_adjust_meta doesn't appear to work"); + __sync_add_and_fetch(&pkts_fail, 1); return XDP_PASS; } - if (!bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp)) - bpf_printk("populated rx_timestamp with %llu", meta->rx_timestamp); - else + err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp); + if (err) meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */ - if (!bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash)) - bpf_printk("populated rx_hash with %u", meta->rx_hash); - else - meta->rx_hash = 0; /* Used by AF_XDP as not avail signal */ + err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); + if (err < 0) + meta->rx_hash_err = err; /* Used by AF_XDP as no hash signal */ + __sync_add_and_fetch(&pkts_redir, 1); return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); } diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata.c b/tools/testing/selftests/bpf/progs/xdp_metadata.c index 77678b034389..d151d406a123 100644 --- a/tools/testing/selftests/bpf/progs/xdp_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_metadata.c @@ -21,8 +21,8 @@ struct { extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, __u64 *timestamp) __ksym; -extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, - __u32 *hash) __ksym; +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, + enum xdp_rss_hash_type *rss_type) __ksym; SEC("xdp") int rx(struct xdp_md *ctx) @@ -56,7 +56,7 @@ int rx(struct xdp_md *ctx) if (timestamp == 0) meta->rx_timestamp = 1; - bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash); + bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); } diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata2.c b/tools/testing/selftests/bpf/progs/xdp_metadata2.c index cf69d05451c3..85f88d9d7a78 100644 --- a/tools/testing/selftests/bpf/progs/xdp_metadata2.c +++ b/tools/testing/selftests/bpf/progs/xdp_metadata2.c @@ -5,17 +5,18 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> -extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, - __u32 *hash) __ksym; +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, + enum xdp_rss_hash_type *rss_type) __ksym; int called; SEC("freplace/rx") int freplace_rx(struct xdp_md *ctx) { + enum xdp_rss_hash_type type = 0; u32 hash = 0; /* Call _any_ metadata function to make sure we don't crash. */ - bpf_xdp_metadata_rx_hash(ctx, &hash); + bpf_xdp_metadata_rx_hash(ctx, &hash, &type); called++; return XDP_PASS; } diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 9d993926bf0e..289ed202ec66 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -2221,19 +2221,22 @@ * that fp-8 stack slot was unused in the fall-through * branch and will accept the program incorrectly */ - BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 2, 2), + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_JMP_IMM(BPF_JGT, BPF_REG_0, 2, 2), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_JMP_IMM(BPF_JA, 0, 0, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_48b = { 6 }, - .errstr = "invalid indirect read from stack R2 off -8+0 size 8", - .result = REJECT, - .prog_type = BPF_PROG_TYPE_XDP, + .fixup_map_hash_48b = { 7 }, + .errstr_unpriv = "invalid indirect read from stack R2 off -8+0 size 8", + .result_unpriv = REJECT, + /* in privileged mode reads from uninitialized stack locations are permitted */ + .result = ACCEPT, }, { "calls: ctx read at start of subprog", diff --git a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c index a6c869a7319c..9c4885885aba 100644 --- a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c +++ b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c @@ -29,19 +29,30 @@ { "helper access to variable memory: stack, bitwise AND, zero included", .insns = { - BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), - BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), - BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), - BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), - BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64), - BPF_MOV64_IMM(BPF_REG_3, 0), - BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel), + /* set max stack size */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -128, 0), + /* set r3 to a random value */ + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + /* use bitwise AND to limit r3 range to [0, 64] */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_3, 64), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -64), + BPF_MOV64_IMM(BPF_REG_4, 0), + /* Call bpf_ringbuf_output(), it is one of a few helper functions with + * ARG_CONST_SIZE_OR_ZERO parameter allowed in unpriv mode. + * For unpriv this should signal an error, because memory at &fp[-64] is + * not initialized. + */ + BPF_EMIT_CALL(BPF_FUNC_ringbuf_output), BPF_EXIT_INSN(), }, - .errstr = "invalid indirect read from stack R1 off -64+0 size 64", - .result = REJECT, - .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .fixup_map_ringbuf = { 4 }, + .errstr_unpriv = "invalid indirect read from stack R2 off -64+0 size 64", + .result_unpriv = REJECT, + /* in privileged mode reads from uninitialized stack locations are permitted */ + .result = ACCEPT, }, { "helper access to variable memory: stack, bitwise AND + JMP, wrong max", @@ -183,20 +194,31 @@ { "helper access to variable memory: stack, JMP, no min check", .insns = { - BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), - BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), - BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), - BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), - BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 3), - BPF_MOV64_IMM(BPF_REG_3, 0), - BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel), + /* set max stack size */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -128, 0), + /* set r3 to a random value */ + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + /* use JMP to limit r3 range to [0, 64] */ + BPF_JMP_IMM(BPF_JGT, BPF_REG_3, 64, 6), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -64), + BPF_MOV64_IMM(BPF_REG_4, 0), + /* Call bpf_ringbuf_output(), it is one of a few helper functions with + * ARG_CONST_SIZE_OR_ZERO parameter allowed in unpriv mode. + * For unpriv this should signal an error, because memory at &fp[-64] is + * not initialized. + */ + BPF_EMIT_CALL(BPF_FUNC_ringbuf_output), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr = "invalid indirect read from stack R1 off -64+0 size 64", - .result = REJECT, - .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .fixup_map_ringbuf = { 4 }, + .errstr_unpriv = "invalid indirect read from stack R2 off -64+0 size 64", + .result_unpriv = REJECT, + /* in privileged mode reads from uninitialized stack locations are permitted */ + .result = ACCEPT, }, { "helper access to variable memory: stack, JMP (signed), no min check", @@ -564,29 +586,41 @@ { "helper access to variable memory: 8 bytes leak", .insns = { - BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), - BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), + /* set max stack size */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -128, 0), + /* set r3 to a random value */ + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -64), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -64), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -56), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -48), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -40), + /* Note: fp[-32] left uninitialized */ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), - BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), - BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), - BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 63), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1), - BPF_MOV64_IMM(BPF_REG_3, 0), - BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel), - BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + /* Limit r3 range to [1, 64] */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_3, 63), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 1), + BPF_MOV64_IMM(BPF_REG_4, 0), + /* Call bpf_ringbuf_output(), it is one of a few helper functions with + * ARG_CONST_SIZE_OR_ZERO parameter allowed in unpriv mode. + * For unpriv this should signal an error, because memory region [1, 64] + * at &fp[-64] is not fully initialized. + */ + BPF_EMIT_CALL(BPF_FUNC_ringbuf_output), + BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr = "invalid indirect read from stack R1 off -64+32 size 64", - .result = REJECT, - .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .fixup_map_ringbuf = { 3 }, + .errstr_unpriv = "invalid indirect read from stack R2 off -64+32 size 64", + .result_unpriv = REJECT, + /* in privileged mode reads from uninitialized stack locations are permitted */ + .result = ACCEPT, }, { "helper access to variable memory: 8 bytes no leak (init memory)", diff --git a/tools/testing/selftests/bpf/verifier/int_ptr.c b/tools/testing/selftests/bpf/verifier/int_ptr.c index 070893fb2900..02d9e004260b 100644 --- a/tools/testing/selftests/bpf/verifier/int_ptr.c +++ b/tools/testing/selftests/bpf/verifier/int_ptr.c @@ -54,12 +54,13 @@ /* bpf_strtoul() */ BPF_EMIT_CALL(BPF_FUNC_strtoul), - BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .result = REJECT, - .prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL, - .errstr = "invalid indirect read from stack R4 off -16+4 size 8", + .result_unpriv = REJECT, + .errstr_unpriv = "invalid indirect read from stack R4 off -16+4 size 8", + /* in privileged mode reads from uninitialized stack locations are permitted */ + .result = ACCEPT, }, { "ARG_PTR_TO_LONG misaligned", diff --git a/tools/testing/selftests/bpf/verifier/search_pruning.c b/tools/testing/selftests/bpf/verifier/search_pruning.c index d63fd8991b03..745d6b5842fd 100644 --- a/tools/testing/selftests/bpf/verifier/search_pruning.c +++ b/tools/testing/selftests/bpf/verifier/search_pruning.c @@ -128,9 +128,10 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_8b = { 3 }, - .errstr = "invalid read from stack off -16+0 size 8", - .result = REJECT, - .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr_unpriv = "invalid read from stack off -16+0 size 8", + .result_unpriv = REJECT, + /* in privileged mode reads from uninitialized stack locations are permitted */ + .result = ACCEPT, }, { "precision tracking for u32 spill/fill", @@ -258,6 +259,8 @@ BPF_EXIT_INSN(), }, .flags = BPF_F_TEST_STATE_FREQ, - .errstr = "invalid read from stack off -8+1 size 8", - .result = REJECT, + .errstr_unpriv = "invalid read from stack off -8+1 size 8", + .result_unpriv = REJECT, + /* in privileged mode reads from uninitialized stack locations are permitted */ + .result = ACCEPT, }, diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c index d11d0b28be41..108dd3ee1edd 100644 --- a/tools/testing/selftests/bpf/verifier/sock.c +++ b/tools/testing/selftests/bpf/verifier/sock.c @@ -531,33 +531,6 @@ .result = ACCEPT, }, { - "sk_storage_get(map, skb->sk, &stack_value, 1): partially init stack_value", - .insns = { - BPF_MOV64_IMM(BPF_REG_2, 0), - BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8), - BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), - BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - BPF_MOV64_IMM(BPF_REG_4, 1), - BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -8), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_EMIT_CALL(BPF_FUNC_sk_storage_get), - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }, - .fixup_sk_storage_map = { 14 }, - .prog_type = BPF_PROG_TYPE_SCHED_CLS, - .result = REJECT, - .errstr = "invalid indirect read from stack", -}, -{ "bpf_map_lookup_elem(smap, &key)", .insns = { BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c index 9bb302dade23..d1463bf4949a 100644 --- a/tools/testing/selftests/bpf/verifier/spill_fill.c +++ b/tools/testing/selftests/bpf/verifier/spill_fill.c @@ -171,9 +171,10 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .result = REJECT, - .errstr = "invalid read from stack off -4+0 size 4", - .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result_unpriv = REJECT, + .errstr_unpriv = "invalid read from stack off -4+0 size 4", + /* in privileged mode reads from uninitialized stack locations are permitted */ + .result = ACCEPT, }, { "Spill a u32 const scalar. Refill as u16. Offset to skb->data", diff --git a/tools/testing/selftests/bpf/verifier/var_off.c b/tools/testing/selftests/bpf/verifier/var_off.c index d37f512fad16..b183e26c03f1 100644 --- a/tools/testing/selftests/bpf/verifier/var_off.c +++ b/tools/testing/selftests/bpf/verifier/var_off.c @@ -213,31 +213,6 @@ .prog_type = BPF_PROG_TYPE_LWT_IN, }, { - "indirect variable-offset stack access, max_off+size > max_initialized", - .insns = { - /* Fill only the second from top 8 bytes of the stack. */ - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0), - /* Get an unknown value. */ - BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), - /* Make it small and 4-byte aligned. */ - BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4), - BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16), - /* Add it to fp. We now have either fp-12 or fp-16, but we don't know - * which. fp-12 size 8 is partially uninitialized stack. - */ - BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10), - /* Dereference it indirectly. */ - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }, - .fixup_map_hash_8b = { 5 }, - .errstr = "invalid indirect read from stack R2 var_off", - .result = REJECT, - .prog_type = BPF_PROG_TYPE_LWT_IN, -}, -{ "indirect variable-offset stack access, min_off < min_initialized", .insns = { /* Fill only the top 8 bytes of the stack. */ @@ -290,33 +265,6 @@ .prog_type = BPF_PROG_TYPE_CGROUP_SKB, }, { - "indirect variable-offset stack access, uninitialized", - .insns = { - BPF_MOV64_IMM(BPF_REG_2, 6), - BPF_MOV64_IMM(BPF_REG_3, 28), - /* Fill the top 16 bytes of the stack. */ - BPF_ST_MEM(BPF_W, BPF_REG_10, -16, 0), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), - /* Get an unknown value. */ - BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, 0), - /* Make it small and 4-byte aligned. */ - BPF_ALU64_IMM(BPF_AND, BPF_REG_4, 4), - BPF_ALU64_IMM(BPF_SUB, BPF_REG_4, 16), - /* Add it to fp. We now have either fp-12 or fp-16, we don't know - * which, but either way it points to initialized stack. - */ - BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_10), - BPF_MOV64_IMM(BPF_REG_5, 8), - /* Dereference it indirectly. */ - BPF_EMIT_CALL(BPF_FUNC_getsockopt), - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }, - .errstr = "invalid indirect read from stack R4 var_off", - .result = REJECT, - .prog_type = BPF_PROG_TYPE_SOCK_OPS, -}, -{ "indirect variable-offset stack access, ok", .insns = { /* Fill the top 16 bytes of the stack. */ diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 1c8acb68b977..987cf0db5ebc 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -141,7 +141,11 @@ static void verify_xdp_metadata(void *data) meta = data - sizeof(*meta); printf("rx_timestamp: %llu\n", meta->rx_timestamp); - printf("rx_hash: %u\n", meta->rx_hash); + if (meta->rx_hash_err < 0) + printf("No rx_hash err=%d\n", meta->rx_hash_err); + else + printf("rx_hash: 0x%X with RSS type:0x%X\n", + meta->rx_hash, meta->rx_hash_type); } static void verify_skb_metadata(int fd) @@ -212,7 +216,9 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd) while (true) { errno = 0; ret = poll(fds, rxq + 1, 1000); - printf("poll: %d (%d)\n", ret, errno); + printf("poll: %d (%d) skip=%llu fail=%llu redir=%llu\n", + ret, errno, bpf_obj->bss->pkts_skip, + bpf_obj->bss->pkts_fail, bpf_obj->bss->pkts_redir); if (ret < 0) break; if (ret == 0) diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h index f6780fbb0a21..0c4624dc6f2f 100644 --- a/tools/testing/selftests/bpf/xdp_metadata.h +++ b/tools/testing/selftests/bpf/xdp_metadata.h @@ -12,4 +12,8 @@ struct xdp_meta { __u64 rx_timestamp; __u32 rx_hash; + union { + __u32 rx_hash_type; + __s32 rx_hash_err; + }; }; diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index 1e616a8c6a9c..f4f7c0aef702 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -98,6 +98,11 @@ static int alloc_anon_50M_check(const char *cgroup, void *arg) int ret = -1; buf = malloc(size); + if (buf == NULL) { + fprintf(stderr, "malloc() failed\n"); + return -1; + } + for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE) *ptr = 0; @@ -211,6 +216,11 @@ static int alloc_anon_noexit(const char *cgroup, void *arg) char *buf, *ptr; buf = malloc(size); + if (buf == NULL) { + fprintf(stderr, "malloc() failed\n"); + return -1; + } + for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE) *ptr = 0; @@ -778,6 +788,11 @@ static int alloc_anon_50M_check_swap(const char *cgroup, void *arg) int ret = -1; buf = malloc(size); + if (buf == NULL) { + fprintf(stderr, "malloc() failed\n"); + return -1; + } + for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE) *ptr = 0; diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index cd4582129c7d..e495f895a2cd 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -129,7 +129,7 @@ int main(int argc, char *argv[]) uid_t uid = getuid(); ksft_print_header(); - ksft_set_plan(17); + ksft_set_plan(18); test_clone3_supported(); /* Just a simple clone3() should return 0.*/ @@ -195,5 +195,8 @@ int main(int argc, char *argv[]) test_clone3(CLONE_NEWPID, getpagesize() + 8, -E2BIG, CLONE3_ARGS_NO_TEST); - return !ksft_get_fail_cnt() ? ksft_exit_pass() : ksft_exit_fail(); + /* Do a clone3() in a new time namespace */ + test_clone3(CLONE_NEWTIME, 0, 0, CLONE3_ARGS_NO_TEST); + + ksft_finished(); } diff --git a/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh b/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh index 48b7af6b022c..f3ffeb1343cf 100644 --- a/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh +++ b/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh @@ -10,7 +10,7 @@ dmesg -C for file in "$DBGFS/"* do - echo "$(basename "$f")" > "$DBGFS/rm_contexts" + (echo "$(basename "$f")" > "$DBGFS/rm_contexts") &> /dev/null if dmesg | grep -q BUG then dmesg diff --git a/tools/testing/selftests/damon/sysfs.sh b/tools/testing/selftests/damon/sysfs.sh index db4942383a50..bcd4734ca094 100644 --- a/tools/testing/selftests/damon/sysfs.sh +++ b/tools/testing/selftests/damon/sysfs.sh @@ -24,7 +24,7 @@ ensure_write_fail() content=$2 reason=$3 - if echo "$content" > "$file" + if (echo "$content" > "$file") 2> /dev/null then echo "writing $content to $file succeed ($fail_reason)" echo "expected failure because $reason" @@ -96,6 +96,34 @@ test_stats() done } +test_filter() +{ + filter_dir=$1 + ensure_file "$filter_dir/type" "exist" "600" + ensure_write_succ "$filter_dir/type" "anon" "valid input" + ensure_write_succ "$filter_dir/type" "memcg" "valid input" + ensure_write_fail "$filter_dir/type" "foo" "invalid input" + ensure_file "$filter_dir/matching" "exist" "600" + ensure_file "$filter_dir/memcg_path" "exist" "600" +} + +test_filters() +{ + filters_dir=$1 + ensure_dir "$filters_dir" "exist" + ensure_file "$filters_dir/nr_filters" "exist" "600" + ensure_write_succ "$filters_dir/nr_filters" "1" "valid input" + test_filter "$filters_dir/0" + + ensure_write_succ "$filters_dir/nr_filters" "2" "valid input" + test_filter "$filters_dir/0" + test_filter "$filters_dir/1" + + ensure_write_succ "$filters_dir/nr_filters" "0" "valid input" + ensure_dir "$filters_dir/0" "not_exist" + ensure_dir "$filters_dir/1" "not_exist" +} + test_watermarks() { watermarks_dir=$1 @@ -143,6 +171,7 @@ test_scheme() test_access_pattern "$scheme_dir/access_pattern" test_quotas "$scheme_dir/quotas" test_watermarks "$scheme_dir/watermarks" + test_filters "$scheme_dir/filters" test_stats "$scheme_dir/stats" test_tried_regions "$scheme_dir/tried_regions" } diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile index 8e3b786a748f..03f92d7aeb19 100644 --- a/tools/testing/selftests/drivers/net/bonding/Makefile +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -8,10 +8,12 @@ TEST_PROGS := \ dev_addr_lists.sh \ mode-1-recovery-updelay.sh \ mode-2-recovery-updelay.sh \ - option_prio.sh + bond_options.sh \ + bond-eth-type-change.sh TEST_FILES := \ lag_lib.sh \ + bond_topo_3d1c.sh \ net_forwarding_lib.sh include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh b/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh new file mode 100755 index 000000000000..5cdd22048ba7 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh @@ -0,0 +1,85 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test bond device ether type changing +# + +ALL_TESTS=" + bond_test_unsuccessful_enslave_type_change + bond_test_successful_enslave_type_change +" +REQUIRE_MZ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +source "$lib_dir"/net_forwarding_lib.sh + +bond_check_flags() +{ + local bonddev=$1 + + ip -d l sh dev "$bonddev" | grep -q "MASTER" + check_err $? "MASTER flag is missing from the bond device" + + ip -d l sh dev "$bonddev" | grep -q "SLAVE" + check_err $? "SLAVE flag is missing from the bond device" +} + +# test enslaved bond dev type change from ARPHRD_ETHER and back +# this allows us to test both MASTER and SLAVE flags at once +bond_test_enslave_type_change() +{ + local test_success=$1 + local devbond0="test-bond0" + local devbond1="test-bond1" + local devbond2="test-bond2" + local nonethdev="test-noneth0" + + # create a non-ARPHRD_ETHER device for testing (e.g. nlmon type) + ip link add name "$nonethdev" type nlmon + check_err $? "could not create a non-ARPHRD_ETHER device (nlmon)" + ip link add name "$devbond0" type bond + if [ $test_success -eq 1 ]; then + # we need devbond0 in active-backup mode to successfully enslave nonethdev + ip link set dev "$devbond0" type bond mode active-backup + check_err $? "could not change bond mode to active-backup" + fi + ip link add name "$devbond1" type bond + ip link add name "$devbond2" type bond + ip link set dev "$devbond0" master "$devbond1" + check_err $? "could not enslave $devbond0 to $devbond1" + # change bond type to non-ARPHRD_ETHER + ip link set dev "$nonethdev" master "$devbond0" 1>/dev/null 2>/dev/null + ip link set dev "$nonethdev" nomaster 1>/dev/null 2>/dev/null + # restore ARPHRD_ETHER type by enslaving such device + ip link set dev "$devbond2" master "$devbond0" + check_err $? "could not enslave $devbond2 to $devbond0" + ip link set dev "$devbond1" nomaster + + bond_check_flags "$devbond0" + + # clean up + ip link del dev "$devbond0" + ip link del dev "$devbond1" + ip link del dev "$devbond2" + ip link del dev "$nonethdev" +} + +bond_test_unsuccessful_enslave_type_change() +{ + RET=0 + + bond_test_enslave_type_change 0 + log_test "Change ether type of an enslaved bond device with unsuccessful enslave" +} + +bond_test_successful_enslave_type_change() +{ + RET=0 + + bond_test_enslave_type_change 1 + log_test "Change ether type of an enslaved bond device with successful enslave" +} + +tests_run + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh new file mode 100755 index 000000000000..db29a3146a86 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -0,0 +1,264 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test bonding options with mode 1,5,6 + +ALL_TESTS=" + prio + arp_validate +" + +REQUIRE_MZ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +source ${lib_dir}/net_forwarding_lib.sh +source ${lib_dir}/bond_topo_3d1c.sh + +skip_prio() +{ + local skip=1 + + # check if iproute support prio option + ip -n ${s_ns} link set eth0 type bond_slave prio 10 + [[ $? -ne 0 ]] && skip=0 + + # check if kernel support prio option + ip -n ${s_ns} -d link show eth0 | grep -q "prio 10" + [[ $? -ne 0 ]] && skip=0 + + return $skip +} + +skip_ns() +{ + local skip=1 + + # check if iproute support ns_ip6_target option + ip -n ${s_ns} link add bond1 type bond ns_ip6_target ${g_ip6} + [[ $? -ne 0 ]] && skip=0 + + # check if kernel support ns_ip6_target option + ip -n ${s_ns} -d link show bond1 | grep -q "ns_ip6_target ${g_ip6}" + [[ $? -ne 0 ]] && skip=0 + + ip -n ${s_ns} link del bond1 + + return $skip +} + +active_slave="" +check_active_slave() +{ + local target_active_slave=$1 + active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + test "$active_slave" = "$target_active_slave" + check_err $? "Current active slave is $active_slave but not $target_active_slave" +} + + +# Test bonding prio option +prio_test() +{ + local param="$1" + RET=0 + + # create bond + bond_reset "${param}" + + # check bonding member prio value + ip -n ${s_ns} link set eth0 type bond_slave prio 0 + ip -n ${s_ns} link set eth1 type bond_slave prio 10 + ip -n ${s_ns} link set eth2 type bond_slave prio 11 + cmd_jq "ip -n ${s_ns} -d -j link show eth0" \ + ".[].linkinfo.info_slave_data | select (.prio == 0)" "-e" &> /dev/null + check_err $? "eth0 prio is not 0" + cmd_jq "ip -n ${s_ns} -d -j link show eth1" \ + ".[].linkinfo.info_slave_data | select (.prio == 10)" "-e" &> /dev/null + check_err $? "eth1 prio is not 10" + cmd_jq "ip -n ${s_ns} -d -j link show eth2" \ + ".[].linkinfo.info_slave_data | select (.prio == 11)" "-e" &> /dev/null + check_err $? "eth2 prio is not 11" + + bond_check_connection "setup" + + # active slave should be the primary slave + check_active_slave eth1 + + # active slave should be the higher prio slave + ip -n ${s_ns} link set $active_slave down + bond_check_connection "fail over" + check_active_slave eth2 + + # when only 1 slave is up + ip -n ${s_ns} link set $active_slave down + bond_check_connection "only 1 slave up" + check_active_slave eth0 + + # when a higher prio slave change to up + ip -n ${s_ns} link set eth2 up + bond_check_connection "higher prio slave up" + case $primary_reselect in + "0") + check_active_slave "eth2" + ;; + "1") + check_active_slave "eth0" + ;; + "2") + check_active_slave "eth0" + ;; + esac + local pre_active_slave=$active_slave + + # when the primary slave change to up + ip -n ${s_ns} link set eth1 up + bond_check_connection "primary slave up" + case $primary_reselect in + "0") + check_active_slave "eth1" + ;; + "1") + check_active_slave "$pre_active_slave" + ;; + "2") + check_active_slave "$pre_active_slave" + ip -n ${s_ns} link set $active_slave down + bond_check_connection "pre_active slave down" + check_active_slave "eth1" + ;; + esac + + # Test changing bond slave prio + if [[ "$primary_reselect" == "0" ]];then + ip -n ${s_ns} link set eth0 type bond_slave prio 1000000 + ip -n ${s_ns} link set eth1 type bond_slave prio 0 + ip -n ${s_ns} link set eth2 type bond_slave prio -50 + ip -n ${s_ns} -d link show eth0 | grep -q 'prio 1000000' + check_err $? "eth0 prio is not 1000000" + ip -n ${s_ns} -d link show eth1 | grep -q 'prio 0' + check_err $? "eth1 prio is not 0" + ip -n ${s_ns} -d link show eth2 | grep -q 'prio -50' + check_err $? "eth3 prio is not -50" + check_active_slave "eth1" + + ip -n ${s_ns} link set $active_slave down + bond_check_connection "change slave prio" + check_active_slave "eth0" + fi +} + +prio_miimon() +{ + local primary_reselect + local mode=$1 + + for primary_reselect in 0 1 2; do + prio_test "mode $mode miimon 100 primary eth1 primary_reselect $primary_reselect" + log_test "prio" "$mode miimon primary_reselect $primary_reselect" + done +} + +prio_arp() +{ + local primary_reselect + local mode=$1 + + for primary_reselect in 0 1 2; do + prio_test "mode active-backup arp_interval 100 arp_ip_target ${g_ip4} primary eth1 primary_reselect $primary_reselect" + log_test "prio" "$mode arp_ip_target primary_reselect $primary_reselect" + done +} + +prio_ns() +{ + local primary_reselect + local mode=$1 + + if skip_ns; then + log_test_skip "prio ns" "Current iproute or kernel doesn't support bond option 'ns_ip6_target'." + return 0 + fi + + for primary_reselect in 0 1 2; do + prio_test "mode active-backup arp_interval 100 ns_ip6_target ${g_ip6} primary eth1 primary_reselect $primary_reselect" + log_test "prio" "$mode ns_ip6_target primary_reselect $primary_reselect" + done +} + +prio() +{ + local mode modes="active-backup balance-tlb balance-alb" + + if skip_prio; then + log_test_skip "prio" "Current iproute or kernel doesn't support bond option 'prio'." + return 0 + fi + + for mode in $modes; do + prio_miimon $mode + prio_arp $mode + prio_ns $mode + done +} + +arp_validate_test() +{ + local param="$1" + RET=0 + + # create bond + bond_reset "${param}" + + bond_check_connection + [ $RET -ne 0 ] && log_test "arp_validate" "$retmsg" + + # wait for a while to make sure the mii status stable + sleep 5 + for i in $(seq 0 2); do + mii_status=$(cmd_jq "ip -n ${s_ns} -j -d link show eth$i" ".[].linkinfo.info_slave_data.mii_status") + if [ ${mii_status} != "UP" ]; then + RET=1 + log_test "arp_validate" "interface eth$i mii_status $mii_status" + fi + done +} + +arp_validate_arp() +{ + local mode=$1 + local val + for val in $(seq 0 6); do + arp_validate_test "mode $mode arp_interval 100 arp_ip_target ${g_ip4} arp_validate $val" + log_test "arp_validate" "$mode arp_ip_target arp_validate $val" + done +} + +arp_validate_ns() +{ + local mode=$1 + local val + + if skip_ns; then + log_test_skip "arp_validate ns" "Current iproute or kernel doesn't support bond option 'ns_ip6_target'." + return 0 + fi + + for val in $(seq 0 6); do + arp_validate_test "mode $mode arp_interval 100 ns_ip6_target ${g_ip6} arp_validate $val" + log_test "arp_validate" "$mode ns_ip6_target arp_validate $val" + done +} + +arp_validate() +{ + arp_validate_arp "active-backup" + arp_validate_ns "active-backup" +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh new file mode 100644 index 000000000000..4045ca97fb22 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh @@ -0,0 +1,143 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Topology for Bond mode 1,5,6 testing +# +# +-------------------------------------+ +# | bond0 | +# | + | Server +# | eth0 | eth1 eth2 | 192.0.2.1/24 +# | +-------------------+ | 2001:db8::1/24 +# | | | | | +# +-------------------------------------+ +# | | | +# +-------------------------------------+ +# | | | | | +# | +---+---------+---------+---+ | Gateway +# | | br0 | | 192.0.2.254/24 +# | +-------------+-------------+ | 2001:db8::254/24 +# | | | +# +-------------------------------------+ +# | +# +-------------------------------------+ +# | | | Client +# | + | 192.0.2.10/24 +# | eth0 | 2001:db8::10/24 +# +-------------------------------------+ + +s_ns="s-$(mktemp -u XXXXXX)" +c_ns="c-$(mktemp -u XXXXXX)" +g_ns="g-$(mktemp -u XXXXXX)" +s_ip4="192.0.2.1" +c_ip4="192.0.2.10" +g_ip4="192.0.2.254" +s_ip6="2001:db8::1" +c_ip6="2001:db8::10" +g_ip6="2001:db8::254" + +gateway_create() +{ + ip netns add ${g_ns} + ip -n ${g_ns} link add br0 type bridge + ip -n ${g_ns} link set br0 up + ip -n ${g_ns} addr add ${g_ip4}/24 dev br0 + ip -n ${g_ns} addr add ${g_ip6}/24 dev br0 +} + +gateway_destroy() +{ + ip -n ${g_ns} link del br0 + ip netns del ${g_ns} +} + +server_create() +{ + ip netns add ${s_ns} + ip -n ${s_ns} link add bond0 type bond mode active-backup miimon 100 + + for i in $(seq 0 2); do + ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns} + + ip -n ${g_ns} link set s${i} up + ip -n ${g_ns} link set s${i} master br0 + ip -n ${s_ns} link set eth${i} master bond0 + done + + ip -n ${s_ns} link set bond0 up + ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0 + ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0 + sleep 2 +} + +# Reset bond with new mode and options +bond_reset() +{ + local param="$1" + + ip -n ${s_ns} link set bond0 down + ip -n ${s_ns} link del bond0 + + ip -n ${s_ns} link add bond0 type bond $param + for i in $(seq 0 2); do + ip -n ${s_ns} link set eth$i master bond0 + done + + ip -n ${s_ns} link set bond0 up + ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0 + ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0 + sleep 2 +} + +server_destroy() +{ + for i in $(seq 0 2); do + ip -n ${s_ns} link del eth${i} + done + ip netns del ${s_ns} +} + +client_create() +{ + ip netns add ${c_ns} + ip -n ${c_ns} link add eth0 type veth peer name c0 netns ${g_ns} + + ip -n ${g_ns} link set c0 up + ip -n ${g_ns} link set c0 master br0 + + ip -n ${c_ns} link set eth0 up + ip -n ${c_ns} addr add ${c_ip4}/24 dev eth0 + ip -n ${c_ns} addr add ${c_ip6}/24 dev eth0 +} + +client_destroy() +{ + ip -n ${c_ns} link del eth0 + ip netns del ${c_ns} +} + +setup_prepare() +{ + gateway_create + server_create + client_create +} + +cleanup() +{ + pre_cleanup + + client_destroy + server_destroy + gateway_destroy +} + +bond_check_connection() +{ + local msg=${1:-"check connection"} + + sleep 2 + ip netns exec ${s_ns} ping ${c_ip4} -c5 -i 0.1 &>/dev/null + check_err $? "${msg}: ping failed" + ip netns exec ${s_ns} ping6 ${c_ip6} -c5 -i 0.1 &>/dev/null + check_err $? "${msg}: ping6 failed" +} diff --git a/tools/testing/selftests/drivers/net/bonding/option_prio.sh b/tools/testing/selftests/drivers/net/bonding/option_prio.sh deleted file mode 100755 index c32eebff5005..000000000000 --- a/tools/testing/selftests/drivers/net/bonding/option_prio.sh +++ /dev/null @@ -1,245 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# Test bonding option prio -# - -ALL_TESTS=" - prio_arp_ip_target_test - prio_miimon_test -" - -REQUIRE_MZ=no -REQUIRE_JQ=no -NUM_NETIFS=0 -lib_dir=$(dirname "$0") -source "$lib_dir"/net_forwarding_lib.sh - -destroy() -{ - ip link del bond0 &>/dev/null - ip link del br0 &>/dev/null - ip link del veth0 &>/dev/null - ip link del veth1 &>/dev/null - ip link del veth2 &>/dev/null - ip netns del ns1 &>/dev/null - ip link del veth3 &>/dev/null -} - -cleanup() -{ - pre_cleanup - - destroy -} - -skip() -{ - local skip=1 - ip link add name bond0 type bond mode 1 miimon 100 &>/dev/null - ip link add name veth0 type veth peer name veth0_p - ip link set veth0 master bond0 - - # check if iproute support prio option - ip link set dev veth0 type bond_slave prio 10 - [[ $? -ne 0 ]] && skip=0 - - # check if bonding support prio option - ip -d link show veth0 | grep -q "prio 10" - [[ $? -ne 0 ]] && skip=0 - - ip link del bond0 &>/dev/null - ip link del veth0 - - return $skip -} - -active_slave="" -check_active_slave() -{ - local target_active_slave=$1 - active_slave="$(cat /sys/class/net/bond0/bonding/active_slave)" - test "$active_slave" = "$target_active_slave" - check_err $? "Current active slave is $active_slave but not $target_active_slave" -} - - -# Test bonding prio option with mode=$mode monitor=$monitor -# and primary_reselect=$primary_reselect -prio_test() -{ - RET=0 - - local monitor=$1 - local mode=$2 - local primary_reselect=$3 - - local bond_ip4="192.169.1.2" - local peer_ip4="192.169.1.1" - local bond_ip6="2009:0a:0b::02" - local peer_ip6="2009:0a:0b::01" - - - # create veths - ip link add name veth0 type veth peer name veth0_p - ip link add name veth1 type veth peer name veth1_p - ip link add name veth2 type veth peer name veth2_p - - # create bond - if [[ "$monitor" == "miimon" ]];then - ip link add name bond0 type bond mode $mode miimon 100 primary veth1 primary_reselect $primary_reselect - elif [[ "$monitor" == "arp_ip_target" ]];then - ip link add name bond0 type bond mode $mode arp_interval 1000 arp_ip_target $peer_ip4 primary veth1 primary_reselect $primary_reselect - elif [[ "$monitor" == "ns_ip6_target" ]];then - ip link add name bond0 type bond mode $mode arp_interval 1000 ns_ip6_target $peer_ip6 primary veth1 primary_reselect $primary_reselect - fi - ip link set bond0 up - ip link set veth0 master bond0 - ip link set veth1 master bond0 - ip link set veth2 master bond0 - # check bonding member prio value - ip link set dev veth0 type bond_slave prio 0 - ip link set dev veth1 type bond_slave prio 10 - ip link set dev veth2 type bond_slave prio 11 - ip -d link show veth0 | grep -q 'prio 0' - check_err $? "veth0 prio is not 0" - ip -d link show veth1 | grep -q 'prio 10' - check_err $? "veth0 prio is not 10" - ip -d link show veth2 | grep -q 'prio 11' - check_err $? "veth0 prio is not 11" - - ip link set veth0 up - ip link set veth1 up - ip link set veth2 up - ip link set veth0_p up - ip link set veth1_p up - ip link set veth2_p up - - # prepare ping target - ip link add name br0 type bridge - ip link set br0 up - ip link set veth0_p master br0 - ip link set veth1_p master br0 - ip link set veth2_p master br0 - ip link add name veth3 type veth peer name veth3_p - ip netns add ns1 - ip link set veth3_p master br0 up - ip link set veth3 netns ns1 up - ip netns exec ns1 ip addr add $peer_ip4/24 dev veth3 - ip netns exec ns1 ip addr add $peer_ip6/64 dev veth3 - ip addr add $bond_ip4/24 dev bond0 - ip addr add $bond_ip6/64 dev bond0 - sleep 5 - - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 1." - ping6 $peer_ip6 -c5 -I bond0 &>/dev/null - check_err $? "ping6 failed 1." - - # active salve should be the primary slave - check_active_slave veth1 - - # active slave should be the higher prio slave - ip link set $active_slave down - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 2." - check_active_slave veth2 - - # when only 1 slave is up - ip link set $active_slave down - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 3." - check_active_slave veth0 - - # when a higher prio slave change to up - ip link set veth2 up - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 4." - case $primary_reselect in - "0") - check_active_slave "veth2" - ;; - "1") - check_active_slave "veth0" - ;; - "2") - check_active_slave "veth0" - ;; - esac - local pre_active_slave=$active_slave - - # when the primary slave change to up - ip link set veth1 up - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 5." - case $primary_reselect in - "0") - check_active_slave "veth1" - ;; - "1") - check_active_slave "$pre_active_slave" - ;; - "2") - check_active_slave "$pre_active_slave" - ip link set $active_slave down - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 6." - check_active_slave "veth1" - ;; - esac - - # Test changing bond salve prio - if [[ "$primary_reselect" == "0" ]];then - ip link set dev veth0 type bond_slave prio 1000000 - ip link set dev veth1 type bond_slave prio 0 - ip link set dev veth2 type bond_slave prio -50 - ip -d link show veth0 | grep -q 'prio 1000000' - check_err $? "veth0 prio is not 1000000" - ip -d link show veth1 | grep -q 'prio 0' - check_err $? "veth1 prio is not 0" - ip -d link show veth2 | grep -q 'prio -50' - check_err $? "veth3 prio is not -50" - check_active_slave "veth1" - - ip link set $active_slave down - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 7." - check_active_slave "veth0" - fi - - cleanup - - log_test "prio_test" "Test bonding option 'prio' with mode=$mode monitor=$monitor and primary_reselect=$primary_reselect" -} - -prio_miimon_test() -{ - local mode - local primary_reselect - - for mode in 1 5 6; do - for primary_reselect in 0 1 2; do - prio_test "miimon" $mode $primary_reselect - done - done -} - -prio_arp_ip_target_test() -{ - local primary_reselect - - for primary_reselect in 0 1 2; do - prio_test "arp_ip_target" 1 $primary_reselect - done -} - -if skip;then - log_test_skip "option_prio.sh" "Current iproute doesn't support 'prio'." - exit 0 -fi - -trap cleanup EXIT - -tests_run - -exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc index 459741565222..a4f8e7c53c1f 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc @@ -28,6 +28,9 @@ s390*) mips*) ARG1=%r4 ;; +loongarch*) + ARG1=%r4 +;; *) echo "Please implement other architecture here" exit_untested diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc index d4662c8cf407..1df61e13a812 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc @@ -40,6 +40,10 @@ mips*) GOODREG=%r4 BADREG=%r12 ;; +loongarch*) + GOODREG=%r4 + BADREG=%r12 +;; *) echo "Please implement other architecture here" exit_untested diff --git a/tools/testing/selftests/hid/config b/tools/testing/selftests/hid/config index 9c5a55abca6b..5b5cef445b54 100644 --- a/tools/testing/selftests/hid/config +++ b/tools/testing/selftests/hid/config @@ -17,5 +17,6 @@ CONFIG_FTRACE_SYSCALLS=y CONFIG_FUNCTION_TRACER=y CONFIG_HIDRAW=y CONFIG_HID=y +CONFIG_HID_BPF=y CONFIG_INPUT_EVDEV=y CONFIG_UHID=y diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 8aa8a346cf22..fa08209268c4 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -1259,7 +1259,7 @@ TEST_F(iommufd_mock_domain, user_copy) test_cmd_destroy_access_pages( access_cmd.id, access_cmd.access_pages.out_access_pages_id); - test_cmd_destroy_access(access_cmd.id) test_ioctl_destroy(ioas_id); + test_cmd_destroy_access(access_cmd.id); test_ioctl_destroy(ioas_id); } diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 33a0dbd26bd3..829be379545a 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -43,11 +43,13 @@ #ifndef __KSELFTEST_H #define __KSELFTEST_H +#ifndef NOLIBC #include <errno.h> #include <stdlib.h> #include <unistd.h> #include <stdarg.h> #include <stdio.h> +#endif #ifndef ARRAY_SIZE #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) diff --git a/tools/testing/selftests/kselftest_deps.sh b/tools/testing/selftests/kselftest_deps.sh index 7424a1f5babc..4bc14d9e8ff1 100755 --- a/tools/testing/selftests/kselftest_deps.sh +++ b/tools/testing/selftests/kselftest_deps.sh @@ -12,9 +12,9 @@ usage() echo -e "Usage: $0 -[p] <compiler> [test_name]\n" echo -e "\tkselftest_deps.sh [-p] gcc" -echo -e "\tkselftest_deps.sh [-p] gcc vm" +echo -e "\tkselftest_deps.sh [-p] gcc mm" echo -e "\tkselftest_deps.sh [-p] aarch64-linux-gnu-gcc" -echo -e "\tkselftest_deps.sh [-p] aarch64-linux-gnu-gcc vm\n" +echo -e "\tkselftest_deps.sh [-p] aarch64-linux-gnu-gcc mm\n" echo "- Should be run in selftests directory in the kernel repo." echo "- Checks if Kselftests can be built/cross-built on a system." echo "- Parses all test/sub-test Makefile to find library dependencies." @@ -120,7 +120,7 @@ l1_tests=$(grep -r --include=Makefile "^LDLIBS" | \ # Level 2 # Some tests have multiple valid LDLIBS lines for individual sub-tests # that need dependency checks. Find them and append them to the tests -# e.g: vm/Makefile:$(OUTPUT)/userfaultfd: LDLIBS += -lpthread +# e.g: mm/Makefile:$(OUTPUT)/userfaultfd: LDLIBS += -lpthread # Filter out VAR_LDLIBS to discard the following: # memfd/Makefile:$(OUTPUT)/fuse_mnt: LDLIBS += $(VAR_LDLIBS) # Append space at the end of the list to append more tests. diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 1750f91dd936..84a627c43795 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -67,6 +67,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/fix_hypercall_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid TEST_GEN_PROGS_x86_64 += x86_64/hyperv_evmcs +TEST_GEN_PROGS_x86_64 += x86_64/hyperv_extended_hypercalls TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features TEST_GEN_PROGS_x86_64 += x86_64/hyperv_ipi TEST_GEN_PROGS_x86_64 += x86_64/hyperv_svm_test @@ -200,6 +201,9 @@ CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ -I$(<D) -Iinclude/$(ARCH_DIR) -I ../rseq -I.. $(EXTRA_CFLAGS) \ $(KHDR_INCLUDES) +ifeq ($(ARCH),s390) + CFLAGS += -march=z10 +endif no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \ $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c index 54680dc5887f..df10f1ffa20d 100644 --- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c +++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c @@ -1112,8 +1112,6 @@ int main(int argc, char *argv[]) enum vm_mem_backing_src_type src_type; int opt; - setbuf(stdout, NULL); - src_type = DEFAULT_VM_MEM_SRC; while ((opt = getopt(argc, argv, "hm:s:")) != -1) { diff --git a/tools/testing/selftests/kvm/aarch64/psci_test.c b/tools/testing/selftests/kvm/aarch64/psci_test.c index cfa36f387948..9b004905d1d3 100644 --- a/tools/testing/selftests/kvm/aarch64/psci_test.c +++ b/tools/testing/selftests/kvm/aarch64/psci_test.c @@ -180,9 +180,7 @@ static void host_test_system_suspend(void) enter_guest(source); - TEST_ASSERT(run->exit_reason == KVM_EXIT_SYSTEM_EVENT, - "Unhandled exit reason: %u (%s)", - run->exit_reason, exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(source, KVM_EXIT_SYSTEM_EVENT); TEST_ASSERT(run->system_event.type == KVM_SYSTEM_EVENT_SUSPEND, "Unhandled system event: %u (expected: %u)", run->system_event.type, KVM_SYSTEM_EVENT_SUSPEND); diff --git a/tools/testing/selftests/kvm/config b/tools/testing/selftests/kvm/config index 63ed533f73d6..d011b38e259e 100644 --- a/tools/testing/selftests/kvm/config +++ b/tools/testing/selftests/kvm/config @@ -1,3 +1,4 @@ CONFIG_KVM=y CONFIG_KVM_INTEL=y CONFIG_KVM_AMD=y +CONFIG_USERFAULTFD=y diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index 80d6416f3012..a6e9f215ce70 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -63,6 +63,15 @@ void test_assert(bool exp, const char *exp_str, #a, #b, #a, (unsigned long) __a, #b, (unsigned long) __b); \ } while (0) +#define TEST_ASSERT_KVM_EXIT_REASON(vcpu, expected) do { \ + __u32 exit_reason = (vcpu)->run->exit_reason; \ + \ + TEST_ASSERT(exit_reason == (expected), \ + "Wanted KVM exit reason: %u (%s), got: %u (%s)", \ + (expected), exit_reason_str((expected)), \ + exit_reason, exit_reason_str(exit_reason)); \ +} while (0) + #define TEST_FAIL(fmt, ...) do { \ TEST_ASSERT(false, fmt, ##__VA_ARGS__); \ __builtin_unreachable(); \ diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86_64/hyperv.h index 9218bb5f44bf..fa65b908b13e 100644 --- a/tools/testing/selftests/kvm/include/x86_64/hyperv.h +++ b/tools/testing/selftests/kvm/include/x86_64/hyperv.h @@ -85,61 +85,110 @@ #define HV_X64_MSR_SYNDBG_OPTIONS 0x400000FF /* HYPERV_CPUID_FEATURES.EAX */ -#define HV_MSR_VP_RUNTIME_AVAILABLE BIT(0) -#define HV_MSR_TIME_REF_COUNT_AVAILABLE BIT(1) -#define HV_MSR_SYNIC_AVAILABLE BIT(2) -#define HV_MSR_SYNTIMER_AVAILABLE BIT(3) -#define HV_MSR_APIC_ACCESS_AVAILABLE BIT(4) -#define HV_MSR_HYPERCALL_AVAILABLE BIT(5) -#define HV_MSR_VP_INDEX_AVAILABLE BIT(6) -#define HV_MSR_RESET_AVAILABLE BIT(7) -#define HV_MSR_STAT_PAGES_AVAILABLE BIT(8) -#define HV_MSR_REFERENCE_TSC_AVAILABLE BIT(9) -#define HV_MSR_GUEST_IDLE_AVAILABLE BIT(10) -#define HV_ACCESS_FREQUENCY_MSRS BIT(11) -#define HV_ACCESS_REENLIGHTENMENT BIT(13) -#define HV_ACCESS_TSC_INVARIANT BIT(15) +#define HV_MSR_VP_RUNTIME_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 0) +#define HV_MSR_TIME_REF_COUNT_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 1) +#define HV_MSR_SYNIC_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 2) +#define HV_MSR_SYNTIMER_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 3) +#define HV_MSR_APIC_ACCESS_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 4) +#define HV_MSR_HYPERCALL_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 5) +#define HV_MSR_VP_INDEX_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 6) +#define HV_MSR_RESET_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 7) +#define HV_MSR_STAT_PAGES_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 8) +#define HV_MSR_REFERENCE_TSC_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 9) +#define HV_MSR_GUEST_IDLE_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 10) +#define HV_ACCESS_FREQUENCY_MSRS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 11) +#define HV_ACCESS_REENLIGHTENMENT \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 13) +#define HV_ACCESS_TSC_INVARIANT \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 15) /* HYPERV_CPUID_FEATURES.EBX */ -#define HV_CREATE_PARTITIONS BIT(0) -#define HV_ACCESS_PARTITION_ID BIT(1) -#define HV_ACCESS_MEMORY_POOL BIT(2) -#define HV_ADJUST_MESSAGE_BUFFERS BIT(3) -#define HV_POST_MESSAGES BIT(4) -#define HV_SIGNAL_EVENTS BIT(5) -#define HV_CREATE_PORT BIT(6) -#define HV_CONNECT_PORT BIT(7) -#define HV_ACCESS_STATS BIT(8) -#define HV_DEBUGGING BIT(11) -#define HV_CPU_MANAGEMENT BIT(12) -#define HV_ISOLATION BIT(22) +#define HV_CREATE_PARTITIONS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 0) +#define HV_ACCESS_PARTITION_ID \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 1) +#define HV_ACCESS_MEMORY_POOL \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 2) +#define HV_ADJUST_MESSAGE_BUFFERS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 3) +#define HV_POST_MESSAGES \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 4) +#define HV_SIGNAL_EVENTS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 5) +#define HV_CREATE_PORT \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 6) +#define HV_CONNECT_PORT \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 7) +#define HV_ACCESS_STATS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 8) +#define HV_DEBUGGING \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 11) +#define HV_CPU_MANAGEMENT \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 12) +#define HV_ENABLE_EXTENDED_HYPERCALLS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 20) +#define HV_ISOLATION \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 22) /* HYPERV_CPUID_FEATURES.EDX */ -#define HV_X64_MWAIT_AVAILABLE BIT(0) -#define HV_X64_GUEST_DEBUGGING_AVAILABLE BIT(1) -#define HV_X64_PERF_MONITOR_AVAILABLE BIT(2) -#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE BIT(3) -#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE BIT(4) -#define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5) -#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8) -#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) -#define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11) -#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19) +#define HV_X64_MWAIT_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 0) +#define HV_X64_GUEST_DEBUGGING_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 1) +#define HV_X64_PERF_MONITOR_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 2) +#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 3) +#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 4) +#define HV_X64_GUEST_IDLE_STATE_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 5) +#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 8) +#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 10) +#define HV_FEATURE_DEBUG_MSRS_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 11) +#define HV_STIMER_DIRECT_MODE_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 19) /* HYPERV_CPUID_ENLIGHTMENT_INFO.EAX */ -#define HV_X64_AS_SWITCH_RECOMMENDED BIT(0) -#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED BIT(1) -#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED BIT(2) -#define HV_X64_APIC_ACCESS_RECOMMENDED BIT(3) -#define HV_X64_SYSTEM_RESET_RECOMMENDED BIT(4) -#define HV_X64_RELAXED_TIMING_RECOMMENDED BIT(5) -#define HV_DEPRECATING_AEOI_RECOMMENDED BIT(9) -#define HV_X64_CLUSTER_IPI_RECOMMENDED BIT(10) -#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED BIT(11) -#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14) +#define HV_X64_AS_SWITCH_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 0) +#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 1) +#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 2) +#define HV_X64_APIC_ACCESS_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 3) +#define HV_X64_SYSTEM_RESET_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 4) +#define HV_X64_RELAXED_TIMING_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 5) +#define HV_DEPRECATING_AEOI_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 9) +#define HV_X64_CLUSTER_IPI_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 10) +#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 11) +#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 14) /* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */ -#define HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING BIT(1) +#define HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES, 0, EAX, 1) /* Hypercalls */ #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002 @@ -166,6 +215,9 @@ #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0 +/* Extended hypercalls */ +#define HV_EXT_CALL_QUERY_CAPABILITIES 0x8001 + #define HV_FLUSH_ALL_PROCESSORS BIT(0) #define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES BIT(1) #define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY BIT(2) @@ -288,4 +340,7 @@ struct hyperv_test_pages { struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm, vm_vaddr_t *p_hv_pages_gva); +/* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */ +#define HV_INVARIANT_TSC_EXPOSED BIT_ULL(0) + #endif /* !SELFTEST_KVM_HYPERV_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index b1a31de7108a..90387ddcb2a9 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -19,6 +19,9 @@ #include "../kvm_util.h" +extern bool host_cpu_is_intel; +extern bool host_cpu_is_amd; + #define NMI_VECTOR 0x02 #define X86_EFLAGS_FIXED (1u << 1) @@ -137,6 +140,7 @@ struct kvm_x86_cpu_feature { #define X86_FEATURE_GBPAGES KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 26) #define X86_FEATURE_RDTSCP KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 27) #define X86_FEATURE_LM KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 29) +#define X86_FEATURE_INVTSC KVM_X86_CPU_FEATURE(0x80000007, 0, EDX, 8) #define X86_FEATURE_RDPRU KVM_X86_CPU_FEATURE(0x80000008, 0, EBX, 4) #define X86_FEATURE_AMD_IBPB KVM_X86_CPU_FEATURE(0x80000008, 0, EBX, 12) #define X86_FEATURE_NPT KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 0) @@ -554,6 +558,28 @@ static inline uint32_t this_cpu_model(void) return x86_model(this_cpu_fms()); } +static inline bool this_cpu_vendor_string_is(const char *vendor) +{ + const uint32_t *chunk = (const uint32_t *)vendor; + uint32_t eax, ebx, ecx, edx; + + cpuid(0, &eax, &ebx, &ecx, &edx); + return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]); +} + +static inline bool this_cpu_is_intel(void) +{ + return this_cpu_vendor_string_is("GenuineIntel"); +} + +/* + * Exclude early K5 samples with a vendor string of "AMDisbetter!" + */ +static inline bool this_cpu_is_amd(void) +{ + return this_cpu_vendor_string_is("AuthenticAMD"); +} + static inline uint32_t __this_cpu_has(uint32_t function, uint32_t index, uint8_t reg, uint8_t lo, uint8_t hi) { @@ -690,9 +716,6 @@ static inline void cpu_relax(void) "hlt\n" \ ) -bool is_intel_cpu(void); -bool is_amd_cpu(void); - struct kvm_x86_state *vcpu_save_state(struct kvm_vcpu *vcpu); void vcpu_load_state(struct kvm_vcpu *vcpu, struct kvm_x86_state *state); void kvm_x86_state_cleanup(struct kvm_x86_state *state); @@ -716,7 +739,7 @@ static inline void vcpu_msrs_set(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs) int r = __vcpu_ioctl(vcpu, KVM_SET_MSRS, msrs); TEST_ASSERT(r == msrs->nmsrs, - "KVM_GET_MSRS failed, r: %i (failed on MSR %x)", + "KVM_SET_MSRS failed, r: %i (failed on MSR %x)", r, r < 0 || r >= msrs->nmsrs ? -1 : msrs->entries[r].index); } static inline void vcpu_debugregs_get(struct kvm_vcpu *vcpu, @@ -1040,6 +1063,8 @@ uint64_t *vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr); uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, uint64_t a3); +uint64_t __xen_hypercall(uint64_t nr, uint64_t a0, void *a1); +void xen_hypercall(uint64_t nr, uint64_t a0, void *a1); void __vm_xsave_require_permission(int bit, const char *name); diff --git a/tools/testing/selftests/kvm/kvm_binary_stats_test.c b/tools/testing/selftests/kvm/kvm_binary_stats_test.c index 0b45ac593387..a7001e29dc06 100644 --- a/tools/testing/selftests/kvm/kvm_binary_stats_test.c +++ b/tools/testing/selftests/kvm/kvm_binary_stats_test.c @@ -19,6 +19,7 @@ #include "kvm_util.h" #include "asm/kvm.h" #include "linux/kvm.h" +#include "kselftest.h" static void stats_test(int stats_fd) { @@ -51,7 +52,7 @@ static void stats_test(int stats_fd) /* Sanity check for other fields in header */ if (header.num_desc == 0) { - printf("No KVM stats defined!"); + ksft_print_msg("No KVM stats defined!\n"); return; } /* @@ -133,7 +134,7 @@ static void stats_test(int stats_fd) "Bucket size of stats (%s) is not zero", pdesc->name); } - size_data += pdesc->size * sizeof(*stats_data); + size_data = max(size_data, pdesc->offset + pdesc->size * sizeof(*stats_data)); } /* @@ -148,14 +149,6 @@ static void stats_test(int stats_fd) TEST_ASSERT(size_data >= header.num_desc * sizeof(*stats_data), "Data size is not correct"); - /* Check stats offset */ - for (i = 0; i < header.num_desc; ++i) { - pdesc = get_stats_descriptor(stats_desc, i, &header); - TEST_ASSERT(pdesc->offset < size_data, - "Invalid offset (%u) for stats: %s", - pdesc->offset, pdesc->name); - } - /* Allocate memory for stats data */ stats_data = malloc(size_data); TEST_ASSERT(stats_data, "Allocate memory for stats data"); @@ -224,9 +217,13 @@ int main(int argc, char *argv[]) max_vcpu = DEFAULT_NUM_VCPU; } + ksft_print_header(); + /* Check the extension for binary stats */ TEST_REQUIRE(kvm_has_cap(KVM_CAP_BINARY_STATS_FD)); + ksft_set_plan(max_vm); + /* Create VMs and VCPUs */ vms = malloc(sizeof(vms[0]) * max_vm); TEST_ASSERT(vms, "Allocate memory for storing VM pointers"); @@ -245,10 +242,12 @@ int main(int argc, char *argv[]) vm_stats_test(vms[i]); for (j = 0; j < max_vcpu; ++j) vcpu_stats_test(vcpus[i * max_vcpu + j]); + ksft_test_result_pass("vm%i\n", i); } for (i = 0; i < max_vm; ++i) kvm_vm_free(vms[i]); free(vms); - return 0; + + ksft_finished(); /* Print results and exit() accordingly */ } diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c index 820ac2d08c98..266f3876e10a 100644 --- a/tools/testing/selftests/kvm/lib/elf.c +++ b/tools/testing/selftests/kvm/lib/elf.c @@ -90,6 +90,7 @@ static void elfhdr_get(const char *filename, Elf64_Ehdr *hdrp) " hdrp->e_shentsize: %x\n" " expected: %zx", hdrp->e_shentsize, sizeof(Elf64_Shdr)); + close(fd); } /* VM ELF Load @@ -190,4 +191,5 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename) phdr.p_filesz); } } + close(fd); } diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c index 99a575bbbc52..1df3ce4b16fd 100644 --- a/tools/testing/selftests/kvm/lib/guest_modes.c +++ b/tools/testing/selftests/kvm/lib/guest_modes.c @@ -127,7 +127,7 @@ void guest_modes_cmdline(const char *arg) mode_selected = true; } - mode = strtoul(optarg, NULL, 10); + mode = atoi_non_negative("Guest mode ID", arg); TEST_ASSERT(mode < NUM_VM_MODES, "Guest mode ID %d too big", mode); guest_modes[mode].enabled = true; } diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 56d5ea949cbb..8ec20ac33de0 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1815,37 +1815,53 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) vcpu_dump(stream, vcpu, indent + 2); } +#define KVM_EXIT_STRING(x) {KVM_EXIT_##x, #x} + /* Known KVM exit reasons */ static struct exit_reason { unsigned int reason; const char *name; } exit_reasons_known[] = { - {KVM_EXIT_UNKNOWN, "UNKNOWN"}, - {KVM_EXIT_EXCEPTION, "EXCEPTION"}, - {KVM_EXIT_IO, "IO"}, - {KVM_EXIT_HYPERCALL, "HYPERCALL"}, - {KVM_EXIT_DEBUG, "DEBUG"}, - {KVM_EXIT_HLT, "HLT"}, - {KVM_EXIT_MMIO, "MMIO"}, - {KVM_EXIT_IRQ_WINDOW_OPEN, "IRQ_WINDOW_OPEN"}, - {KVM_EXIT_SHUTDOWN, "SHUTDOWN"}, - {KVM_EXIT_FAIL_ENTRY, "FAIL_ENTRY"}, - {KVM_EXIT_INTR, "INTR"}, - {KVM_EXIT_SET_TPR, "SET_TPR"}, - {KVM_EXIT_TPR_ACCESS, "TPR_ACCESS"}, - {KVM_EXIT_S390_SIEIC, "S390_SIEIC"}, - {KVM_EXIT_S390_RESET, "S390_RESET"}, - {KVM_EXIT_DCR, "DCR"}, - {KVM_EXIT_NMI, "NMI"}, - {KVM_EXIT_INTERNAL_ERROR, "INTERNAL_ERROR"}, - {KVM_EXIT_OSI, "OSI"}, - {KVM_EXIT_PAPR_HCALL, "PAPR_HCALL"}, - {KVM_EXIT_DIRTY_RING_FULL, "DIRTY_RING_FULL"}, - {KVM_EXIT_X86_RDMSR, "RDMSR"}, - {KVM_EXIT_X86_WRMSR, "WRMSR"}, - {KVM_EXIT_XEN, "XEN"}, + KVM_EXIT_STRING(UNKNOWN), + KVM_EXIT_STRING(EXCEPTION), + KVM_EXIT_STRING(IO), + KVM_EXIT_STRING(HYPERCALL), + KVM_EXIT_STRING(DEBUG), + KVM_EXIT_STRING(HLT), + KVM_EXIT_STRING(MMIO), + KVM_EXIT_STRING(IRQ_WINDOW_OPEN), + KVM_EXIT_STRING(SHUTDOWN), + KVM_EXIT_STRING(FAIL_ENTRY), + KVM_EXIT_STRING(INTR), + KVM_EXIT_STRING(SET_TPR), + KVM_EXIT_STRING(TPR_ACCESS), + KVM_EXIT_STRING(S390_SIEIC), + KVM_EXIT_STRING(S390_RESET), + KVM_EXIT_STRING(DCR), + KVM_EXIT_STRING(NMI), + KVM_EXIT_STRING(INTERNAL_ERROR), + KVM_EXIT_STRING(OSI), + KVM_EXIT_STRING(PAPR_HCALL), + KVM_EXIT_STRING(S390_UCONTROL), + KVM_EXIT_STRING(WATCHDOG), + KVM_EXIT_STRING(S390_TSCH), + KVM_EXIT_STRING(EPR), + KVM_EXIT_STRING(SYSTEM_EVENT), + KVM_EXIT_STRING(S390_STSI), + KVM_EXIT_STRING(IOAPIC_EOI), + KVM_EXIT_STRING(HYPERV), + KVM_EXIT_STRING(ARM_NISV), + KVM_EXIT_STRING(X86_RDMSR), + KVM_EXIT_STRING(X86_WRMSR), + KVM_EXIT_STRING(DIRTY_RING_FULL), + KVM_EXIT_STRING(AP_RESET_HOLD), + KVM_EXIT_STRING(X86_BUS_LOCK), + KVM_EXIT_STRING(XEN), + KVM_EXIT_STRING(RISCV_SBI), + KVM_EXIT_STRING(RISCV_CSR), + KVM_EXIT_STRING(NOTIFY), #ifdef KVM_EXIT_MEMORY_NOT_PRESENT - {KVM_EXIT_MEMORY_NOT_PRESENT, "MEMORY_NOT_PRESENT"}, + KVM_EXIT_STRING(MEMORY_NOT_PRESENT), #endif }; @@ -1941,9 +1957,6 @@ vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, return vm_phy_pages_alloc(vm, 1, paddr_min, memslot); } -/* Arbitrary minimum physical address used for virtual translation tables. */ -#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 - vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm) { return vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, diff --git a/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c b/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c index cdb7daeed5fd..2c432fa164f1 100644 --- a/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c +++ b/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c @@ -35,8 +35,7 @@ static uint64_t diag318_handler(void) vcpu_run(vcpu); run = vcpu->run; - TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC, - "DIAGNOSE 0x0318 instruction was not intercepted"); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC); TEST_ASSERT(run->s390_sieic.icptcode == ICPT_INSTRUCTION, "Unexpected intercept code: 0x%x", run->s390_sieic.icptcode); TEST_ASSERT((run->s390_sieic.ipa & 0xff00) == IPA0_DIAG, diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 5c22fa4c2825..b772193f6c18 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -165,26 +165,33 @@ size_t get_trans_hugepagesz(void) size_t get_def_hugetlb_pagesz(void) { char buf[64]; - const char *tag = "Hugepagesize:"; + const char *hugepagesize = "Hugepagesize:"; + const char *hugepages_total = "HugePages_Total:"; FILE *f; f = fopen("/proc/meminfo", "r"); TEST_ASSERT(f != NULL, "Error in opening /proc/meminfo"); while (fgets(buf, sizeof(buf), f) != NULL) { - if (strstr(buf, tag) == buf) { + if (strstr(buf, hugepages_total) == buf) { + unsigned long long total = strtoull(buf + strlen(hugepages_total), NULL, 10); + if (!total) { + fprintf(stderr, "HUGETLB is not enabled in /proc/sys/vm/nr_hugepages\n"); + exit(KSFT_SKIP); + } + } + if (strstr(buf, hugepagesize) == buf) { fclose(f); - return strtoull(buf + strlen(tag), NULL, 10) << 10; + return strtoull(buf + strlen(hugepagesize), NULL, 10) << 10; } } - if (feof(f)) - TEST_FAIL("HUGETLB is not configured in host kernel"); - else - TEST_FAIL("Error in reading /proc/meminfo"); + if (feof(f)) { + fprintf(stderr, "HUGETLB is not configured in host kernel"); + exit(KSFT_SKIP); + } - fclose(f); - return 0; + TEST_FAIL("Error in reading /proc/meminfo"); } #define ANON_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS) diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index acfa1d01e7df..c39a4353ba19 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -19,6 +19,8 @@ #define MAX_NR_CPUID_ENTRIES 100 vm_vaddr_t exception_handlers; +bool host_cpu_is_amd; +bool host_cpu_is_intel; static void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent) { @@ -113,7 +115,7 @@ static void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent) bool kvm_is_tdp_enabled(void) { - if (is_intel_cpu()) + if (host_cpu_is_intel) return get_kvm_intel_param_bool("ept"); else return get_kvm_amd_param_bool("npt"); @@ -555,6 +557,8 @@ static void vcpu_setup(struct kvm_vm *vm, struct kvm_vcpu *vcpu) void kvm_arch_vm_post_create(struct kvm_vm *vm) { vm_create_irqchip(vm); + sync_global_to_guest(vm, host_cpu_is_intel); + sync_global_to_guest(vm, host_cpu_is_amd); } struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, @@ -1006,28 +1010,6 @@ void kvm_x86_state_cleanup(struct kvm_x86_state *state) free(state); } -static bool cpu_vendor_string_is(const char *vendor) -{ - const uint32_t *chunk = (const uint32_t *)vendor; - uint32_t eax, ebx, ecx, edx; - - cpuid(0, &eax, &ebx, &ecx, &edx); - return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]); -} - -bool is_intel_cpu(void) -{ - return cpu_vendor_string_is("GenuineIntel"); -} - -/* - * Exclude early K5 samples with a vendor string of "AMDisbetter!" - */ -bool is_amd_cpu(void) -{ - return cpu_vendor_string_is("AuthenticAMD"); -} - void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) { if (!kvm_cpu_has_p(X86_PROPERTY_MAX_PHY_ADDR)) { @@ -1157,15 +1139,36 @@ const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, return NULL; } +#define X86_HYPERCALL(inputs...) \ +({ \ + uint64_t r; \ + \ + asm volatile("test %[use_vmmcall], %[use_vmmcall]\n\t" \ + "jnz 1f\n\t" \ + "vmcall\n\t" \ + "jmp 2f\n\t" \ + "1: vmmcall\n\t" \ + "2:" \ + : "=a"(r) \ + : [use_vmmcall] "r" (host_cpu_is_amd), inputs); \ + \ + r; \ +}) + uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, uint64_t a3) { - uint64_t r; + return X86_HYPERCALL("a"(nr), "b"(a0), "c"(a1), "d"(a2), "S"(a3)); +} + +uint64_t __xen_hypercall(uint64_t nr, uint64_t a0, void *a1) +{ + return X86_HYPERCALL("a"(nr), "D"(a0), "S"(a1)); +} - asm volatile("vmcall" - : "=a"(r) - : "a"(nr), "b"(a0), "c"(a1), "d"(a2), "S"(a3)); - return r; +void xen_hypercall(uint64_t nr, uint64_t a0, void *a1) +{ + GUEST_ASSERT(!__xen_hypercall(nr, a0, a1)); } const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void) @@ -1236,7 +1239,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1; /* Avoid reserved HyperTransport region on AMD processors. */ - if (!is_amd_cpu()) + if (!host_cpu_is_amd) return max_gfn; /* On parts with <40 physical address bits, the area is fully hidden */ @@ -1276,3 +1279,9 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm) return get_kvm_intel_param_bool("unrestricted_guest"); } + +void kvm_selftest_arch_init(void) +{ + host_cpu_is_intel = this_cpu_is_intel(); + host_cpu_is_amd = this_cpu_is_amd(); +} diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index e6587e193490..4210cd21d159 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -308,8 +308,6 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, data->hva_slots = malloc(sizeof(*data->hva_slots) * data->nslots); TEST_ASSERT(data->hva_slots, "malloc() fail"); - data->vm = __vm_create_with_one_vcpu(&data->vcpu, mempages, guest_code); - pr_info_v("Adding slots 1..%i, each slot with %"PRIu64" pages + %"PRIu64" extra pages last\n", data->nslots, data->pages_per_slot, rempages); @@ -349,6 +347,7 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, virt_map(data->vm, MEM_GPA, MEM_GPA, data->npages); sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL); + sync->guest_page_size = data->vm->page_size; atomic_init(&sync->start_flag, false); atomic_init(&sync->exit_flag, false); atomic_init(&sync->sync_flag, false); @@ -810,8 +809,6 @@ static bool test_execute(int nslots, uint64_t *maxslots, } sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL); - - sync->guest_page_size = data->vm->page_size; if (tdata->prepare && !tdata->prepare(data, sync, maxslots)) { ret = false; diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c index 3fd81e58f40c..8e4b94d7b8dd 100644 --- a/tools/testing/selftests/kvm/s390x/memop.c +++ b/tools/testing/selftests/kvm/s390x/memop.c @@ -9,6 +9,7 @@ #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> +#include <pthread.h> #include <linux/bits.h> @@ -26,6 +27,7 @@ enum mop_target { enum mop_access_mode { READ, WRITE, + CMPXCHG, }; struct mop_desc { @@ -44,57 +46,67 @@ struct mop_desc { enum mop_access_mode mode; void *buf; uint32_t sida_offset; + void *old; + uint8_t old_value[16]; + bool *cmpxchg_success; uint8_t ar; uint8_t key; }; -static struct kvm_s390_mem_op ksmo_from_desc(struct mop_desc desc) +const uint8_t NO_KEY = 0xff; + +static struct kvm_s390_mem_op ksmo_from_desc(struct mop_desc *desc) { struct kvm_s390_mem_op ksmo = { - .gaddr = (uintptr_t)desc.gaddr, - .size = desc.size, - .buf = ((uintptr_t)desc.buf), + .gaddr = (uintptr_t)desc->gaddr, + .size = desc->size, + .buf = ((uintptr_t)desc->buf), .reserved = "ignored_ignored_ignored_ignored" }; - switch (desc.target) { + switch (desc->target) { case LOGICAL: - if (desc.mode == READ) + if (desc->mode == READ) ksmo.op = KVM_S390_MEMOP_LOGICAL_READ; - if (desc.mode == WRITE) + if (desc->mode == WRITE) ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE; break; case SIDA: - if (desc.mode == READ) + if (desc->mode == READ) ksmo.op = KVM_S390_MEMOP_SIDA_READ; - if (desc.mode == WRITE) + if (desc->mode == WRITE) ksmo.op = KVM_S390_MEMOP_SIDA_WRITE; break; case ABSOLUTE: - if (desc.mode == READ) + if (desc->mode == READ) ksmo.op = KVM_S390_MEMOP_ABSOLUTE_READ; - if (desc.mode == WRITE) + if (desc->mode == WRITE) ksmo.op = KVM_S390_MEMOP_ABSOLUTE_WRITE; + if (desc->mode == CMPXCHG) { + ksmo.op = KVM_S390_MEMOP_ABSOLUTE_CMPXCHG; + ksmo.old_addr = (uint64_t)desc->old; + memcpy(desc->old_value, desc->old, desc->size); + } break; case INVALID: ksmo.op = -1; } - if (desc.f_check) + if (desc->f_check) ksmo.flags |= KVM_S390_MEMOP_F_CHECK_ONLY; - if (desc.f_inject) + if (desc->f_inject) ksmo.flags |= KVM_S390_MEMOP_F_INJECT_EXCEPTION; - if (desc._set_flags) - ksmo.flags = desc.set_flags; - if (desc.f_key) { + if (desc->_set_flags) + ksmo.flags = desc->set_flags; + if (desc->f_key && desc->key != NO_KEY) { ksmo.flags |= KVM_S390_MEMOP_F_SKEY_PROTECTION; - ksmo.key = desc.key; + ksmo.key = desc->key; } - if (desc._ar) - ksmo.ar = desc.ar; + if (desc->_ar) + ksmo.ar = desc->ar; else ksmo.ar = 0; - if (desc._sida_offset) - ksmo.sida_offset = desc.sida_offset; + if (desc->_sida_offset) + ksmo.sida_offset = desc->sida_offset; return ksmo; } @@ -133,9 +145,13 @@ static void print_memop(struct kvm_vcpu *vcpu, const struct kvm_s390_mem_op *ksm case KVM_S390_MEMOP_ABSOLUTE_WRITE: printf("ABSOLUTE, WRITE, "); break; + case KVM_S390_MEMOP_ABSOLUTE_CMPXCHG: + printf("ABSOLUTE, CMPXCHG, "); + break; } - printf("gaddr=%llu, size=%u, buf=%llu, ar=%u, key=%u", - ksmo->gaddr, ksmo->size, ksmo->buf, ksmo->ar, ksmo->key); + printf("gaddr=%llu, size=%u, buf=%llu, ar=%u, key=%u, old_addr=%llx", + ksmo->gaddr, ksmo->size, ksmo->buf, ksmo->ar, ksmo->key, + ksmo->old_addr); if (ksmo->flags & KVM_S390_MEMOP_F_CHECK_ONLY) printf(", CHECK_ONLY"); if (ksmo->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) @@ -145,24 +161,30 @@ static void print_memop(struct kvm_vcpu *vcpu, const struct kvm_s390_mem_op *ksm puts(")"); } -static void memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo) +static int err_memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo, + struct mop_desc *desc) { struct kvm_vcpu *vcpu = info.vcpu; if (!vcpu) - vm_ioctl(info.vm, KVM_S390_MEM_OP, ksmo); + return __vm_ioctl(info.vm, KVM_S390_MEM_OP, ksmo); else - vcpu_ioctl(vcpu, KVM_S390_MEM_OP, ksmo); + return __vcpu_ioctl(vcpu, KVM_S390_MEM_OP, ksmo); } -static int err_memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo) +static void memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo, + struct mop_desc *desc) { - struct kvm_vcpu *vcpu = info.vcpu; + int r; - if (!vcpu) - return __vm_ioctl(info.vm, KVM_S390_MEM_OP, ksmo); - else - return __vcpu_ioctl(vcpu, KVM_S390_MEM_OP, ksmo); + r = err_memop_ioctl(info, ksmo, desc); + if (ksmo->op == KVM_S390_MEMOP_ABSOLUTE_CMPXCHG) { + if (desc->cmpxchg_success) { + int diff = memcmp(desc->old_value, desc->old, desc->size); + *desc->cmpxchg_success = !diff; + } + } + TEST_ASSERT(!r, __KVM_IOCTL_ERROR("KVM_S390_MEM_OP", r)); } #define MEMOP(err, info_p, mop_target_p, access_mode_p, buf_p, size_p, ...) \ @@ -183,9 +205,9 @@ static int err_memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo) else \ __desc.gaddr = __desc.gaddr_v; \ } \ - __ksmo = ksmo_from_desc(__desc); \ + __ksmo = ksmo_from_desc(&__desc); \ print_memop(__info.vcpu, &__ksmo); \ - err##memop_ioctl(__info, &__ksmo); \ + err##memop_ioctl(__info, &__ksmo, &__desc); \ }) #define MOP(...) MEMOP(, __VA_ARGS__) @@ -199,6 +221,8 @@ static int err_memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo) #define AR(a) ._ar = 1, .ar = (a) #define KEY(a) .f_key = 1, .key = (a) #define INJECT .f_inject = 1 +#define CMPXCHG_OLD(o) .old = (o) +#define CMPXCHG_SUCCESS(s) .cmpxchg_success = (s) #define CHECK_N_DO(f, ...) ({ f(__VA_ARGS__, CHECK_ONLY); f(__VA_ARGS__); }) @@ -208,8 +232,8 @@ static int err_memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo) #define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38)) #define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39)) -static uint8_t mem1[65536]; -static uint8_t mem2[65536]; +static uint8_t __aligned(PAGE_SIZE) mem1[65536]; +static uint8_t __aligned(PAGE_SIZE) mem2[65536]; struct test_default { struct kvm_vm *kvm_vm; @@ -241,6 +265,8 @@ enum stage { STAGE_SKEYS_SET, /* Guest copied memory (locations up to test case) */ STAGE_COPIED, + /* End of guest code reached */ + STAGE_DONE, }; #define HOST_SYNC(info_p, stage) \ @@ -252,6 +278,9 @@ enum stage { \ vcpu_run(__vcpu); \ get_ucall(__vcpu, &uc); \ + if (uc.cmd == UCALL_ABORT) { \ + REPORT_GUEST_ASSERT_2(uc, "hints: %lu, %lu"); \ + } \ ASSERT_EQ(uc.cmd, UCALL_SYNC); \ ASSERT_EQ(uc.args[1], __stage); \ }) \ @@ -268,34 +297,66 @@ static void prepare_mem12(void) #define ASSERT_MEM_EQ(p1, p2, size) \ TEST_ASSERT(!memcmp(p1, p2, size), "Memory contents do not match!") -#define DEFAULT_WRITE_READ(copy_cpu, mop_cpu, mop_target_p, size, ...) \ -({ \ - struct test_info __copy_cpu = (copy_cpu), __mop_cpu = (mop_cpu); \ - enum mop_target __target = (mop_target_p); \ - uint32_t __size = (size); \ - \ - prepare_mem12(); \ - CHECK_N_DO(MOP, __mop_cpu, __target, WRITE, mem1, __size, \ - GADDR_V(mem1), ##__VA_ARGS__); \ - HOST_SYNC(__copy_cpu, STAGE_COPIED); \ - CHECK_N_DO(MOP, __mop_cpu, __target, READ, mem2, __size, \ - GADDR_V(mem2), ##__VA_ARGS__); \ - ASSERT_MEM_EQ(mem1, mem2, __size); \ -}) +static void default_write_read(struct test_info copy_cpu, struct test_info mop_cpu, + enum mop_target mop_target, uint32_t size, uint8_t key) +{ + prepare_mem12(); + CHECK_N_DO(MOP, mop_cpu, mop_target, WRITE, mem1, size, + GADDR_V(mem1), KEY(key)); + HOST_SYNC(copy_cpu, STAGE_COPIED); + CHECK_N_DO(MOP, mop_cpu, mop_target, READ, mem2, size, + GADDR_V(mem2), KEY(key)); + ASSERT_MEM_EQ(mem1, mem2, size); +} -#define DEFAULT_READ(copy_cpu, mop_cpu, mop_target_p, size, ...) \ -({ \ - struct test_info __copy_cpu = (copy_cpu), __mop_cpu = (mop_cpu); \ - enum mop_target __target = (mop_target_p); \ - uint32_t __size = (size); \ - \ - prepare_mem12(); \ - CHECK_N_DO(MOP, __mop_cpu, __target, WRITE, mem1, __size, \ - GADDR_V(mem1)); \ - HOST_SYNC(__copy_cpu, STAGE_COPIED); \ - CHECK_N_DO(MOP, __mop_cpu, __target, READ, mem2, __size, ##__VA_ARGS__);\ - ASSERT_MEM_EQ(mem1, mem2, __size); \ -}) +static void default_read(struct test_info copy_cpu, struct test_info mop_cpu, + enum mop_target mop_target, uint32_t size, uint8_t key) +{ + prepare_mem12(); + CHECK_N_DO(MOP, mop_cpu, mop_target, WRITE, mem1, size, GADDR_V(mem1)); + HOST_SYNC(copy_cpu, STAGE_COPIED); + CHECK_N_DO(MOP, mop_cpu, mop_target, READ, mem2, size, + GADDR_V(mem2), KEY(key)); + ASSERT_MEM_EQ(mem1, mem2, size); +} + +static void default_cmpxchg(struct test_default *test, uint8_t key) +{ + for (int size = 1; size <= 16; size *= 2) { + for (int offset = 0; offset < 16; offset += size) { + uint8_t __aligned(16) new[16] = {}; + uint8_t __aligned(16) old[16]; + bool succ; + + prepare_mem12(); + default_write_read(test->vcpu, test->vcpu, LOGICAL, 16, NO_KEY); + + memcpy(&old, mem1, 16); + MOP(test->vm, ABSOLUTE, CMPXCHG, new + offset, + size, GADDR_V(mem1 + offset), + CMPXCHG_OLD(old + offset), + CMPXCHG_SUCCESS(&succ), KEY(key)); + HOST_SYNC(test->vcpu, STAGE_COPIED); + MOP(test->vm, ABSOLUTE, READ, mem2, 16, GADDR_V(mem2)); + TEST_ASSERT(succ, "exchange of values should succeed"); + memcpy(mem1 + offset, new + offset, size); + ASSERT_MEM_EQ(mem1, mem2, 16); + + memcpy(&old, mem1, 16); + new[offset]++; + old[offset]++; + MOP(test->vm, ABSOLUTE, CMPXCHG, new + offset, + size, GADDR_V(mem1 + offset), + CMPXCHG_OLD(old + offset), + CMPXCHG_SUCCESS(&succ), KEY(key)); + HOST_SYNC(test->vcpu, STAGE_COPIED); + MOP(test->vm, ABSOLUTE, READ, mem2, 16, GADDR_V(mem2)); + TEST_ASSERT(!succ, "exchange of values should not succeed"); + ASSERT_MEM_EQ(mem1, mem2, 16); + ASSERT_MEM_EQ(&old, mem1, 16); + } + } +} static void guest_copy(void) { @@ -310,7 +371,7 @@ static void test_copy(void) HOST_SYNC(t.vcpu, STAGE_INITED); - DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size); + default_write_read(t.vcpu, t.vcpu, LOGICAL, t.size, NO_KEY); kvm_vm_free(t.kvm_vm); } @@ -357,26 +418,268 @@ static void test_copy_key(void) HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); /* vm, no key */ - DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, t.size); + default_write_read(t.vcpu, t.vm, ABSOLUTE, t.size, NO_KEY); /* vm/vcpu, machting key or key 0 */ - DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size, KEY(0)); - DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size, KEY(9)); - DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, t.size, KEY(0)); - DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, t.size, KEY(9)); + default_write_read(t.vcpu, t.vcpu, LOGICAL, t.size, 0); + default_write_read(t.vcpu, t.vcpu, LOGICAL, t.size, 9); + default_write_read(t.vcpu, t.vm, ABSOLUTE, t.size, 0); + default_write_read(t.vcpu, t.vm, ABSOLUTE, t.size, 9); /* * There used to be different code paths for key handling depending on * if the region crossed a page boundary. * There currently are not, but the more tests the merrier. */ - DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, 1, KEY(0)); - DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, 1, KEY(9)); - DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, 1, KEY(0)); - DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, 1, KEY(9)); + default_write_read(t.vcpu, t.vcpu, LOGICAL, 1, 0); + default_write_read(t.vcpu, t.vcpu, LOGICAL, 1, 9); + default_write_read(t.vcpu, t.vm, ABSOLUTE, 1, 0); + default_write_read(t.vcpu, t.vm, ABSOLUTE, 1, 9); /* vm/vcpu, mismatching keys on read, but no fetch protection */ - DEFAULT_READ(t.vcpu, t.vcpu, LOGICAL, t.size, GADDR_V(mem2), KEY(2)); - DEFAULT_READ(t.vcpu, t.vm, ABSOLUTE, t.size, GADDR_V(mem1), KEY(2)); + default_read(t.vcpu, t.vcpu, LOGICAL, t.size, 2); + default_read(t.vcpu, t.vm, ABSOLUTE, t.size, 2); + + kvm_vm_free(t.kvm_vm); +} + +static void test_cmpxchg_key(void) +{ + struct test_default t = test_default_init(guest_copy_key); + + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + + default_cmpxchg(&t, NO_KEY); + default_cmpxchg(&t, 0); + default_cmpxchg(&t, 9); + + kvm_vm_free(t.kvm_vm); +} + +static __uint128_t cut_to_size(int size, __uint128_t val) +{ + switch (size) { + case 1: + return (uint8_t)val; + case 2: + return (uint16_t)val; + case 4: + return (uint32_t)val; + case 8: + return (uint64_t)val; + case 16: + return val; + } + GUEST_ASSERT_1(false, "Invalid size"); + return 0; +} + +static bool popcount_eq(__uint128_t a, __uint128_t b) +{ + unsigned int count_a, count_b; + + count_a = __builtin_popcountl((uint64_t)(a >> 64)) + + __builtin_popcountl((uint64_t)a); + count_b = __builtin_popcountl((uint64_t)(b >> 64)) + + __builtin_popcountl((uint64_t)b); + return count_a == count_b; +} + +static __uint128_t rotate(int size, __uint128_t val, int amount) +{ + unsigned int bits = size * 8; + + amount = (amount + bits) % bits; + val = cut_to_size(size, val); + return (val << (bits - amount)) | (val >> amount); +} + +const unsigned int max_block = 16; + +static void choose_block(bool guest, int i, int *size, int *offset) +{ + unsigned int rand; + + rand = i; + if (guest) { + rand = rand * 19 + 11; + *size = 1 << ((rand % 3) + 2); + rand = rand * 19 + 11; + *offset = (rand % max_block) & ~(*size - 1); + } else { + rand = rand * 17 + 5; + *size = 1 << (rand % 5); + rand = rand * 17 + 5; + *offset = (rand % max_block) & ~(*size - 1); + } +} + +static __uint128_t permutate_bits(bool guest, int i, int size, __uint128_t old) +{ + unsigned int rand; + int amount; + bool swap; + + rand = i; + rand = rand * 3 + 1; + if (guest) + rand = rand * 3 + 1; + swap = rand % 2 == 0; + if (swap) { + int i, j; + __uint128_t new; + uint8_t byte0, byte1; + + rand = rand * 3 + 1; + i = rand % size; + rand = rand * 3 + 1; + j = rand % size; + if (i == j) + return old; + new = rotate(16, old, i * 8); + byte0 = new & 0xff; + new &= ~0xff; + new = rotate(16, new, -i * 8); + new = rotate(16, new, j * 8); + byte1 = new & 0xff; + new = (new & ~0xff) | byte0; + new = rotate(16, new, -j * 8); + new = rotate(16, new, i * 8); + new = new | byte1; + new = rotate(16, new, -i * 8); + return new; + } + rand = rand * 3 + 1; + amount = rand % (size * 8); + return rotate(size, old, amount); +} + +static bool _cmpxchg(int size, void *target, __uint128_t *old_addr, __uint128_t new) +{ + bool ret; + + switch (size) { + case 4: { + uint32_t old = *old_addr; + + asm volatile ("cs %[old],%[new],%[address]" + : [old] "+d" (old), + [address] "+Q" (*(uint32_t *)(target)) + : [new] "d" ((uint32_t)new) + : "cc" + ); + ret = old == (uint32_t)*old_addr; + *old_addr = old; + return ret; + } + case 8: { + uint64_t old = *old_addr; + + asm volatile ("csg %[old],%[new],%[address]" + : [old] "+d" (old), + [address] "+Q" (*(uint64_t *)(target)) + : [new] "d" ((uint64_t)new) + : "cc" + ); + ret = old == (uint64_t)*old_addr; + *old_addr = old; + return ret; + } + case 16: { + __uint128_t old = *old_addr; + + asm volatile ("cdsg %[old],%[new],%[address]" + : [old] "+d" (old), + [address] "+Q" (*(__uint128_t *)(target)) + : [new] "d" (new) + : "cc" + ); + ret = old == *old_addr; + *old_addr = old; + return ret; + } + } + GUEST_ASSERT_1(false, "Invalid size"); + return 0; +} + +const unsigned int cmpxchg_iter_outer = 100, cmpxchg_iter_inner = 10000; + +static void guest_cmpxchg_key(void) +{ + int size, offset; + __uint128_t old, new; + + set_storage_key_range(mem1, max_block, 0x10); + set_storage_key_range(mem2, max_block, 0x10); + GUEST_SYNC(STAGE_SKEYS_SET); + + for (int i = 0; i < cmpxchg_iter_outer; i++) { + do { + old = 1; + } while (!_cmpxchg(16, mem1, &old, 0)); + for (int j = 0; j < cmpxchg_iter_inner; j++) { + choose_block(true, i + j, &size, &offset); + do { + new = permutate_bits(true, i + j, size, old); + } while (!_cmpxchg(size, mem2 + offset, &old, new)); + } + } + + GUEST_SYNC(STAGE_DONE); +} + +static void *run_guest(void *data) +{ + struct test_info *info = data; + + HOST_SYNC(*info, STAGE_DONE); + return NULL; +} + +static char *quad_to_char(__uint128_t *quad, int size) +{ + return ((char *)quad) + (sizeof(*quad) - size); +} + +static void test_cmpxchg_key_concurrent(void) +{ + struct test_default t = test_default_init(guest_cmpxchg_key); + int size, offset; + __uint128_t old, new; + bool success; + pthread_t thread; + + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + prepare_mem12(); + MOP(t.vcpu, LOGICAL, WRITE, mem1, max_block, GADDR_V(mem2)); + pthread_create(&thread, NULL, run_guest, &t.vcpu); + + for (int i = 0; i < cmpxchg_iter_outer; i++) { + do { + old = 0; + new = 1; + MOP(t.vm, ABSOLUTE, CMPXCHG, &new, + sizeof(new), GADDR_V(mem1), + CMPXCHG_OLD(&old), + CMPXCHG_SUCCESS(&success), KEY(1)); + } while (!success); + for (int j = 0; j < cmpxchg_iter_inner; j++) { + choose_block(false, i + j, &size, &offset); + do { + new = permutate_bits(false, i + j, size, old); + MOP(t.vm, ABSOLUTE, CMPXCHG, quad_to_char(&new, size), + size, GADDR_V(mem2 + offset), + CMPXCHG_OLD(quad_to_char(&old, size)), + CMPXCHG_SUCCESS(&success), KEY(1)); + } while (!success); + } + } + + pthread_join(thread, NULL); + + MOP(t.vcpu, LOGICAL, READ, mem2, max_block, GADDR_V(mem2)); + TEST_ASSERT(popcount_eq(*(__uint128_t *)mem1, *(__uint128_t *)mem2), + "Must retain number of set bits"); kvm_vm_free(t.kvm_vm); } @@ -409,7 +712,7 @@ static void test_copy_key_storage_prot_override(void) HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); /* vcpu, mismatching keys, storage protection override in effect */ - DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size, KEY(2)); + default_write_read(t.vcpu, t.vcpu, LOGICAL, t.size, 2); kvm_vm_free(t.kvm_vm); } @@ -422,8 +725,8 @@ static void test_copy_key_fetch_prot(void) HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); /* vm/vcpu, matching key, fetch protection in effect */ - DEFAULT_READ(t.vcpu, t.vcpu, LOGICAL, t.size, GADDR_V(mem2), KEY(9)); - DEFAULT_READ(t.vcpu, t.vm, ABSOLUTE, t.size, GADDR_V(mem2), KEY(9)); + default_read(t.vcpu, t.vcpu, LOGICAL, t.size, 9); + default_read(t.vcpu, t.vm, ABSOLUTE, t.size, 9); kvm_vm_free(t.kvm_vm); } @@ -454,9 +757,27 @@ static void test_errors_key(void) /* vm/vcpu, mismatching keys, fetch protection in effect */ CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, WRITE, mem1, t.size, GADDR_V(mem1), KEY(2)); - CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, t.size, GADDR_V(mem2), KEY(2)); + CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, t.size, GADDR_V(mem1), KEY(2)); CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, WRITE, mem1, t.size, GADDR_V(mem1), KEY(2)); - CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, t.size, GADDR_V(mem2), KEY(2)); + CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, t.size, GADDR_V(mem1), KEY(2)); + + kvm_vm_free(t.kvm_vm); +} + +static void test_errors_cmpxchg_key(void) +{ + struct test_default t = test_default_init(guest_copy_key_fetch_prot); + int i; + + HOST_SYNC(t.vcpu, STAGE_INITED); + HOST_SYNC(t.vcpu, STAGE_SKEYS_SET); + + for (i = 1; i <= 16; i *= 2) { + __uint128_t old = 0; + + ERR_PROT_MOP(t.vm, ABSOLUTE, CMPXCHG, mem2, i, GADDR_V(mem2), + CMPXCHG_OLD(&old), KEY(2)); + } kvm_vm_free(t.kvm_vm); } @@ -518,7 +839,7 @@ static void guest_copy_key_fetch_prot_override(void) GUEST_SYNC(STAGE_INITED); set_storage_key_range(0, PAGE_SIZE, 0x18); set_storage_key_range((void *)last_page_addr, PAGE_SIZE, 0x0); - asm volatile ("sske %[key],%[addr]\n" :: [addr] "r"(0), [key] "r"(0x18) : "cc"); + asm volatile ("sske %[key],%[addr]\n" :: [addr] "r"(0L), [key] "r"(0x18) : "cc"); GUEST_SYNC(STAGE_SKEYS_SET); for (;;) { @@ -606,7 +927,7 @@ static void test_errors_key_fetch_prot_override_enabled(void) /* * vcpu, mismatching keys on fetch, - * fetch protection override does not apply because memory range acceeded + * fetch protection override does not apply because memory range exceeded */ CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, 2048 + 1, GADDR_V(0), KEY(2)); CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, PAGE_SIZE + 2048 + 1, @@ -645,7 +966,9 @@ static void _test_errors_common(struct test_info info, enum mop_target target, i /* Bad guest address: */ rv = ERR_MOP(info, target, WRITE, mem1, size, GADDR((void *)~0xfffUL), CHECK_ONLY); - TEST_ASSERT(rv > 0, "ioctl does not report bad guest memory access"); + TEST_ASSERT(rv > 0, "ioctl does not report bad guest memory address with CHECK_ONLY"); + rv = ERR_MOP(info, target, WRITE, mem1, size, GADDR((void *)~0xfffUL)); + TEST_ASSERT(rv > 0, "ioctl does not report bad guest memory address on write"); /* Bad host address: */ rv = ERR_MOP(info, target, WRITE, 0, size, GADDR_V(mem1)); @@ -694,85 +1017,138 @@ static void test_errors(void) kvm_vm_free(t.kvm_vm); } -struct testdef { - const char *name; - void (*test)(void); - int extension; -} testlist[] = { - { - .name = "simple copy", - .test = test_copy, - }, - { - .name = "generic error checks", - .test = test_errors, - }, - { - .name = "copy with storage keys", - .test = test_copy_key, - .extension = 1, - }, - { - .name = "copy with key storage protection override", - .test = test_copy_key_storage_prot_override, - .extension = 1, - }, - { - .name = "copy with key fetch protection", - .test = test_copy_key_fetch_prot, - .extension = 1, - }, - { - .name = "copy with key fetch protection override", - .test = test_copy_key_fetch_prot_override, - .extension = 1, - }, - { - .name = "error checks with key", - .test = test_errors_key, - .extension = 1, - }, - { - .name = "termination", - .test = test_termination, - .extension = 1, - }, - { - .name = "error checks with key storage protection override", - .test = test_errors_key_storage_prot_override, - .extension = 1, - }, - { - .name = "error checks without key fetch prot override", - .test = test_errors_key_fetch_prot_override_not_enabled, - .extension = 1, - }, - { - .name = "error checks with key fetch prot override", - .test = test_errors_key_fetch_prot_override_enabled, - .extension = 1, - }, -}; +static void test_errors_cmpxchg(void) +{ + struct test_default t = test_default_init(guest_idle); + __uint128_t old; + int rv, i, power = 1; + + HOST_SYNC(t.vcpu, STAGE_INITED); + + for (i = 0; i < 32; i++) { + if (i == power) { + power *= 2; + continue; + } + rv = ERR_MOP(t.vm, ABSOLUTE, CMPXCHG, mem1, i, GADDR_V(mem1), + CMPXCHG_OLD(&old)); + TEST_ASSERT(rv == -1 && errno == EINVAL, + "ioctl allows bad size for cmpxchg"); + } + for (i = 1; i <= 16; i *= 2) { + rv = ERR_MOP(t.vm, ABSOLUTE, CMPXCHG, mem1, i, GADDR((void *)~0xfffUL), + CMPXCHG_OLD(&old)); + TEST_ASSERT(rv > 0, "ioctl allows bad guest address for cmpxchg"); + } + for (i = 2; i <= 16; i *= 2) { + rv = ERR_MOP(t.vm, ABSOLUTE, CMPXCHG, mem1, i, GADDR_V(mem1 + 1), + CMPXCHG_OLD(&old)); + TEST_ASSERT(rv == -1 && errno == EINVAL, + "ioctl allows bad alignment for cmpxchg"); + } + + kvm_vm_free(t.kvm_vm); +} int main(int argc, char *argv[]) { int extension_cap, idx; TEST_REQUIRE(kvm_has_cap(KVM_CAP_S390_MEM_OP)); + extension_cap = kvm_check_cap(KVM_CAP_S390_MEM_OP_EXTENSION); - ksft_print_header(); + struct testdef { + const char *name; + void (*test)(void); + bool requirements_met; + } testlist[] = { + { + .name = "simple copy", + .test = test_copy, + .requirements_met = true, + }, + { + .name = "generic error checks", + .test = test_errors, + .requirements_met = true, + }, + { + .name = "copy with storage keys", + .test = test_copy_key, + .requirements_met = extension_cap > 0, + }, + { + .name = "cmpxchg with storage keys", + .test = test_cmpxchg_key, + .requirements_met = extension_cap & 0x2, + }, + { + .name = "concurrently cmpxchg with storage keys", + .test = test_cmpxchg_key_concurrent, + .requirements_met = extension_cap & 0x2, + }, + { + .name = "copy with key storage protection override", + .test = test_copy_key_storage_prot_override, + .requirements_met = extension_cap > 0, + }, + { + .name = "copy with key fetch protection", + .test = test_copy_key_fetch_prot, + .requirements_met = extension_cap > 0, + }, + { + .name = "copy with key fetch protection override", + .test = test_copy_key_fetch_prot_override, + .requirements_met = extension_cap > 0, + }, + { + .name = "error checks with key", + .test = test_errors_key, + .requirements_met = extension_cap > 0, + }, + { + .name = "error checks for cmpxchg with key", + .test = test_errors_cmpxchg_key, + .requirements_met = extension_cap & 0x2, + }, + { + .name = "error checks for cmpxchg", + .test = test_errors_cmpxchg, + .requirements_met = extension_cap & 0x2, + }, + { + .name = "termination", + .test = test_termination, + .requirements_met = extension_cap > 0, + }, + { + .name = "error checks with key storage protection override", + .test = test_errors_key_storage_prot_override, + .requirements_met = extension_cap > 0, + }, + { + .name = "error checks without key fetch prot override", + .test = test_errors_key_fetch_prot_override_not_enabled, + .requirements_met = extension_cap > 0, + }, + { + .name = "error checks with key fetch prot override", + .test = test_errors_key_fetch_prot_override_enabled, + .requirements_met = extension_cap > 0, + }, + }; + ksft_print_header(); ksft_set_plan(ARRAY_SIZE(testlist)); - extension_cap = kvm_check_cap(KVM_CAP_S390_MEM_OP_EXTENSION); for (idx = 0; idx < ARRAY_SIZE(testlist); idx++) { - if (extension_cap >= testlist[idx].extension) { + if (testlist[idx].requirements_met) { testlist[idx].test(); ksft_test_result_pass("%s\n", testlist[idx].name); } else { - ksft_test_result_skip("%s - extension level %d not supported\n", - testlist[idx].name, - testlist[idx].extension); + ksft_test_result_skip("%s - requirements not met (kernel has extension cap %#x)\n", + testlist[idx].name, extension_cap); } } diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390x/sync_regs_test.c index 2ddde41c44ba..636a70ddac1e 100644 --- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c +++ b/tools/testing/selftests/kvm/s390x/sync_regs_test.c @@ -126,10 +126,7 @@ void test_req_and_verify_all_valid_regs(struct kvm_vcpu *vcpu) run->kvm_valid_regs = TEST_SYNC_FIELDS; rv = _vcpu_run(vcpu); TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv); - TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC, - "Unexpected exit reason: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC); TEST_ASSERT(run->s390_sieic.icptcode == 4 && (run->s390_sieic.ipa >> 8) == 0x83 && (run->s390_sieic.ipb >> 16) == 0x501, @@ -165,10 +162,7 @@ void test_set_and_verify_various_reg_values(struct kvm_vcpu *vcpu) rv = _vcpu_run(vcpu); TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv); - TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC, - "Unexpected exit reason: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC); TEST_ASSERT(run->s.regs.gprs[11] == 0xBAD1DEA + 1, "r11 sync regs value incorrect 0x%llx.", run->s.regs.gprs[11]); @@ -200,10 +194,7 @@ void test_clear_kvm_dirty_regs_bits(struct kvm_vcpu *vcpu) run->s.regs.diag318 = 0x4B1D; rv = _vcpu_run(vcpu); TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv); - TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC, - "Unexpected exit reason: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC); TEST_ASSERT(run->s.regs.gprs[11] != 0xDEADBEEF, "r11 sync regs value incorrect 0x%llx.", run->s.regs.gprs[11]); diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index 2ef1d1b72ce4..a849ce23ca97 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -308,7 +308,6 @@ static void test_delete_memory_region(void) static void test_zero_memory_regions(void) { struct kvm_vcpu *vcpu; - struct kvm_run *run; struct kvm_vm *vm; pr_info("Testing KVM_RUN with zero added memory regions\n"); @@ -318,10 +317,7 @@ static void test_zero_memory_regions(void) vm_ioctl(vm, KVM_SET_NR_MMU_PAGES, (void *)64ul); vcpu_run(vcpu); - - run = vcpu->run; - TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR, - "Unexpected exit_reason = %u\n", run->exit_reason); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_INTERNAL_ERROR); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index bd72c6eb3b67..b646cdb5055a 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -241,7 +241,6 @@ int main(int argc, char *argv[]) struct kvm_regs regs1, regs2; struct kvm_vcpu *vcpu; struct kvm_vm *vm; - struct kvm_run *run; struct kvm_x86_state *state; int xsave_restore_size; vm_vaddr_t amx_cfg, tiledata, xsavedata; @@ -268,7 +267,6 @@ int main(int argc, char *argv[]) "KVM should enumerate max XSAVE size when XSAVE is supported"); xsave_restore_size = kvm_cpu_property(X86_PROPERTY_XSTATE_MAX_SIZE); - run = vcpu->run; vcpu_regs_get(vcpu, ®s1); /* Register #NM handler */ @@ -291,10 +289,7 @@ int main(int argc, char *argv[]) for (stage = 1; ; stage++) { vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Stage %d: unexpected exit reason: %u (%s),\n", - stage, run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: @@ -350,7 +345,6 @@ int main(int argc, char *argv[]) /* Restore state in a new VM. */ vcpu = vm_recreate_with_one_vcpu(vm); vcpu_load_state(vcpu, state); - run = vcpu->run; kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c index 1027a671c7d3..624dc725e14d 100644 --- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c +++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c @@ -50,7 +50,6 @@ static void guest_code(void) int main(int argc, char *argv[]) { struct kvm_vcpu *vcpu; - struct kvm_run *run; struct kvm_vm *vm; struct kvm_sregs sregs; struct ucall uc; @@ -58,15 +57,10 @@ int main(int argc, char *argv[]) TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XSAVE)); vm = vm_create_with_one_vcpu(&vcpu, guest_code); - run = vcpu->run; while (1) { vcpu_run(vcpu); - - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Unexpected exit reason: %u (%s),\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c index 7ef99c3359a0..f6b295e0b2d2 100644 --- a/tools/testing/selftests/kvm/x86_64/debug_regs.c +++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c @@ -204,7 +204,7 @@ int main(void) vcpu_guest_debug_set(vcpu, &debug); vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "KVM_EXIT_IO"); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); cmd = get_ucall(vcpu, &uc); TEST_ASSERT(cmd == UCALL_DONE, "UCALL_DONE"); diff --git a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c b/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c index 37c61f712fd5..e334844d6e1d 100644 --- a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c +++ b/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c @@ -26,9 +26,6 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - TEST_REQUIRE(kvm_has_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE)); vm = vm_create_with_one_vcpu(&vcpu, guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c index 32f7e09ef67c..0f728f05ea82 100644 --- a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c +++ b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c @@ -48,10 +48,10 @@ static void guest_main(void) const uint8_t *other_hypercall_insn; uint64_t ret; - if (is_intel_cpu()) { + if (host_cpu_is_intel) { native_hypercall_insn = vmx_vmcall; other_hypercall_insn = svm_vmmcall; - } else if (is_amd_cpu()) { + } else if (host_cpu_is_amd) { native_hypercall_insn = svm_vmmcall; other_hypercall_insn = vmx_vmcall; } else { diff --git a/tools/testing/selftests/kvm/x86_64/flds_emulation.h b/tools/testing/selftests/kvm/x86_64/flds_emulation.h index e43a7df25f2c..0a1573d52882 100644 --- a/tools/testing/selftests/kvm/x86_64/flds_emulation.h +++ b/tools/testing/selftests/kvm/x86_64/flds_emulation.h @@ -24,10 +24,7 @@ static inline void handle_flds_emulation_failure_exit(struct kvm_vcpu *vcpu) uint8_t *insn_bytes; uint64_t flags; - TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR, - "Unexpected exit reason: %u (%s)", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_INTERNAL_ERROR); TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION, "Unexpected suberror: %u", diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c index d576bc8ce823..f25749eaa6a8 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c @@ -104,7 +104,7 @@ static void guest_main(struct ms_hyperv_tsc_page *tsc_page, vm_paddr_t tsc_page_ /* Set Guest OS id to enable Hyper-V emulation */ GUEST_SYNC(1); - wrmsr(HV_X64_MSR_GUEST_OS_ID, (u64)0x8100 << 48); + wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); GUEST_SYNC(2); check_tsc_msr_rdtsc(); @@ -207,13 +207,11 @@ int main(void) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; - struct kvm_run *run; struct ucall uc; vm_vaddr_t tsc_page_gva; int stage; vm = vm_create_with_one_vcpu(&vcpu, guest_main); - run = vcpu->run; vcpu_set_hv_cpuid(vcpu); @@ -227,10 +225,7 @@ int main(void) for (stage = 1;; stage++) { vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Stage %d: unexpected exit reason: %u (%s),\n", - stage, run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c index af29e5776d40..7bde0c4dfdbd 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c @@ -237,7 +237,6 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; - struct kvm_run *run; struct ucall uc; int stage; @@ -266,13 +265,8 @@ int main(int argc, char *argv[]) pr_info("Running L1 which uses EVMCS to run L2\n"); for (stage = 1;; stage++) { - run = vcpu->run; - vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Stage %d: unexpected exit reason: %u (%s),\n", - stage, run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c new file mode 100644 index 000000000000..73af44d2167f --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test Hyper-V extended hypercall, HV_EXT_CALL_QUERY_CAPABILITIES (0x8001), + * exit to userspace and receive result in guest. + * + * Negative tests are present in hyperv_features.c + * + * Copyright 2022 Google LLC + * Author: Vipin Sharma <vipinsh@google.com> + */ + +#include "kvm_util.h" +#include "processor.h" +#include "hyperv.h" + +/* Any value is fine */ +#define EXT_CAPABILITIES 0xbull + +static void guest_code(vm_paddr_t in_pg_gpa, vm_paddr_t out_pg_gpa, + vm_vaddr_t out_pg_gva) +{ + uint64_t *output_gva; + + wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); + wrmsr(HV_X64_MSR_HYPERCALL, in_pg_gpa); + + output_gva = (uint64_t *)out_pg_gva; + + hyperv_hypercall(HV_EXT_CALL_QUERY_CAPABILITIES, in_pg_gpa, out_pg_gpa); + + /* TLFS states output will be a uint64_t value */ + GUEST_ASSERT_EQ(*output_gva, EXT_CAPABILITIES); + + GUEST_DONE(); +} + +int main(void) +{ + vm_vaddr_t hcall_out_page; + vm_vaddr_t hcall_in_page; + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct kvm_vm *vm; + uint64_t *outval; + struct ucall uc; + + /* Verify if extended hypercalls are supported */ + if (!kvm_cpuid_has(kvm_get_supported_hv_cpuid(), + HV_ENABLE_EXTENDED_HYPERCALLS)) { + print_skip("Extended calls not supported by the kernel"); + exit(KSFT_SKIP); + } + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; + vcpu_set_hv_cpuid(vcpu); + + /* Hypercall input */ + hcall_in_page = vm_vaddr_alloc_pages(vm, 1); + memset(addr_gva2hva(vm, hcall_in_page), 0x0, vm->page_size); + + /* Hypercall output */ + hcall_out_page = vm_vaddr_alloc_pages(vm, 1); + memset(addr_gva2hva(vm, hcall_out_page), 0x0, vm->page_size); + + vcpu_args_set(vcpu, 3, addr_gva2gpa(vm, hcall_in_page), + addr_gva2gpa(vm, hcall_out_page), hcall_out_page); + + vcpu_run(vcpu); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_HYPERV, + "Unexpected exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + outval = addr_gpa2hva(vm, run->hyperv.u.hcall.params[1]); + *outval = EXT_CAPABILITIES; + run->hyperv.u.hcall.result = HV_STATUS_SUCCESS; + + vcpu_run(vcpu); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT_2(uc, "arg1 = %ld, arg2 = %ld"); + break; + case UCALL_DONE: + break; + default: + TEST_FAIL("Unhandled ucall: %ld", uc.cmd); + } + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index 3163c3e8db0a..78606de9385d 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -13,9 +13,17 @@ #include "processor.h" #include "hyperv.h" +/* + * HYPERV_CPUID_ENLIGHTMENT_INFO.EBX is not a 'feature' CPUID leaf + * but to activate the feature it is sufficient to set it to a non-zero + * value. Use BIT(0) for that. + */ +#define HV_PV_SPINLOCKS_TEST \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EBX, 0) + struct msr_data { uint32_t idx; - bool available; + bool fault_expected; bool write; u64 write_val; }; @@ -26,22 +34,46 @@ struct hcall_data { bool ud_expected; }; +static bool is_write_only_msr(uint32_t msr) +{ + return msr == HV_X64_MSR_EOI; +} + static void guest_msr(struct msr_data *msr) { - uint64_t ignored; - uint8_t vector; + uint8_t vector = 0; + uint64_t msr_val = 0; GUEST_ASSERT(msr->idx); - if (!msr->write) - vector = rdmsr_safe(msr->idx, &ignored); - else + if (msr->write) vector = wrmsr_safe(msr->idx, msr->write_val); - if (msr->available) - GUEST_ASSERT_2(!vector, msr->idx, vector); + if (!vector && (!msr->write || !is_write_only_msr(msr->idx))) + vector = rdmsr_safe(msr->idx, &msr_val); + + if (msr->fault_expected) + GUEST_ASSERT_3(vector == GP_VECTOR, msr->idx, vector, GP_VECTOR); else - GUEST_ASSERT_2(vector == GP_VECTOR, msr->idx, vector); + GUEST_ASSERT_3(!vector, msr->idx, vector, 0); + + if (vector || is_write_only_msr(msr->idx)) + goto done; + + if (msr->write) + GUEST_ASSERT_3(msr_val == msr->write_val, msr->idx, + msr_val, msr->write_val); + + /* Invariant TSC bit appears when TSC invariant control MSR is written to */ + if (msr->idx == HV_X64_MSR_TSC_INVARIANT_CONTROL) { + if (!this_cpu_has(HV_ACCESS_TSC_INVARIANT)) + GUEST_ASSERT(this_cpu_has(X86_FEATURE_INVTSC)); + else + GUEST_ASSERT(this_cpu_has(X86_FEATURE_INVTSC) == + !!(msr_val & HV_INVARIANT_TSC_EXPOSED)); + } + +done: GUEST_DONE(); } @@ -89,14 +121,13 @@ static void vcpu_reset_hv_cpuid(struct kvm_vcpu *vcpu) static void guest_test_msrs_access(void) { struct kvm_cpuid2 *prev_cpuid = NULL; - struct kvm_cpuid_entry2 *feat, *dbg; struct kvm_vcpu *vcpu; - struct kvm_run *run; struct kvm_vm *vm; struct ucall uc; int stage = 0; vm_vaddr_t msr_gva; struct msr_data *msr; + bool has_invtsc = kvm_cpu_has(X86_FEATURE_INVTSC); while (true) { vm = vm_create_with_one_vcpu(&vcpu, guest_msr); @@ -116,14 +147,9 @@ static void guest_test_msrs_access(void) vcpu_init_cpuid(vcpu, prev_cpuid); } - feat = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES); - dbg = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES); - vm_init_descriptor_tables(vm); vcpu_init_descriptor_tables(vcpu); - run = vcpu->run; - /* TODO: Make this entire test easier to maintain. */ if (stage >= 21) vcpu_enable_cap(vcpu, KVM_CAP_HYPERV_SYNIC2, 0); @@ -134,133 +160,139 @@ static void guest_test_msrs_access(void) * Only available when Hyper-V identification is set */ msr->idx = HV_X64_MSR_GUEST_OS_ID; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 1: msr->idx = HV_X64_MSR_HYPERCALL; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 2: - feat->eax |= HV_MSR_HYPERCALL_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_HYPERCALL_AVAILABLE); /* * HV_X64_MSR_GUEST_OS_ID has to be written first to make * HV_X64_MSR_HYPERCALL available. */ msr->idx = HV_X64_MSR_GUEST_OS_ID; - msr->write = 1; + msr->write = true; msr->write_val = HYPERV_LINUX_OS_ID; - msr->available = 1; + msr->fault_expected = false; break; case 3: msr->idx = HV_X64_MSR_GUEST_OS_ID; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 4: msr->idx = HV_X64_MSR_HYPERCALL; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 5: msr->idx = HV_X64_MSR_VP_RUNTIME; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 6: - feat->eax |= HV_MSR_VP_RUNTIME_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_VP_RUNTIME_AVAILABLE); msr->idx = HV_X64_MSR_VP_RUNTIME; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 7: /* Read only */ msr->idx = HV_X64_MSR_VP_RUNTIME; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 0; + msr->fault_expected = true; break; case 8: msr->idx = HV_X64_MSR_TIME_REF_COUNT; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 9: - feat->eax |= HV_MSR_TIME_REF_COUNT_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_TIME_REF_COUNT_AVAILABLE); msr->idx = HV_X64_MSR_TIME_REF_COUNT; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 10: /* Read only */ msr->idx = HV_X64_MSR_TIME_REF_COUNT; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 0; + msr->fault_expected = true; break; case 11: msr->idx = HV_X64_MSR_VP_INDEX; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 12: - feat->eax |= HV_MSR_VP_INDEX_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_VP_INDEX_AVAILABLE); msr->idx = HV_X64_MSR_VP_INDEX; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 13: /* Read only */ msr->idx = HV_X64_MSR_VP_INDEX; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 0; + msr->fault_expected = true; break; case 14: msr->idx = HV_X64_MSR_RESET; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 15: - feat->eax |= HV_MSR_RESET_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_RESET_AVAILABLE); msr->idx = HV_X64_MSR_RESET; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 16: msr->idx = HV_X64_MSR_RESET; - msr->write = 1; + msr->write = true; + /* + * TODO: the test only writes '0' to HV_X64_MSR_RESET + * at the moment, writing some other value there will + * trigger real vCPU reset and the code is not prepared + * to handle it yet. + */ msr->write_val = 0; - msr->available = 1; + msr->fault_expected = false; break; case 17: msr->idx = HV_X64_MSR_REFERENCE_TSC; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 18: - feat->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_REFERENCE_TSC_AVAILABLE); msr->idx = HV_X64_MSR_REFERENCE_TSC; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 19: msr->idx = HV_X64_MSR_REFERENCE_TSC; - msr->write = 1; + msr->write = true; msr->write_val = 0; - msr->available = 1; + msr->fault_expected = false; break; case 20: msr->idx = HV_X64_MSR_EOM; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 21: /* @@ -268,149 +300,185 @@ static void guest_test_msrs_access(void) * capability enabled and guest visible CPUID bit unset. */ msr->idx = HV_X64_MSR_EOM; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 22: - feat->eax |= HV_MSR_SYNIC_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_SYNIC_AVAILABLE); msr->idx = HV_X64_MSR_EOM; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 23: msr->idx = HV_X64_MSR_EOM; - msr->write = 1; + msr->write = true; msr->write_val = 0; - msr->available = 1; + msr->fault_expected = false; break; case 24: msr->idx = HV_X64_MSR_STIMER0_CONFIG; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 25: - feat->eax |= HV_MSR_SYNTIMER_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_SYNTIMER_AVAILABLE); msr->idx = HV_X64_MSR_STIMER0_CONFIG; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 26: msr->idx = HV_X64_MSR_STIMER0_CONFIG; - msr->write = 1; + msr->write = true; msr->write_val = 0; - msr->available = 1; + msr->fault_expected = false; break; case 27: /* Direct mode test */ msr->idx = HV_X64_MSR_STIMER0_CONFIG; - msr->write = 1; + msr->write = true; msr->write_val = 1 << 12; - msr->available = 0; + msr->fault_expected = true; break; case 28: - feat->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_STIMER_DIRECT_MODE_AVAILABLE); msr->idx = HV_X64_MSR_STIMER0_CONFIG; - msr->write = 1; + msr->write = true; msr->write_val = 1 << 12; - msr->available = 1; + msr->fault_expected = false; break; case 29: msr->idx = HV_X64_MSR_EOI; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 30: - feat->eax |= HV_MSR_APIC_ACCESS_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_APIC_ACCESS_AVAILABLE); msr->idx = HV_X64_MSR_EOI; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 1; + msr->fault_expected = false; break; case 31: msr->idx = HV_X64_MSR_TSC_FREQUENCY; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 32: - feat->eax |= HV_ACCESS_FREQUENCY_MSRS; + vcpu_set_cpuid_feature(vcpu, HV_ACCESS_FREQUENCY_MSRS); msr->idx = HV_X64_MSR_TSC_FREQUENCY; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 33: /* Read only */ msr->idx = HV_X64_MSR_TSC_FREQUENCY; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 0; + msr->fault_expected = true; break; case 34: msr->idx = HV_X64_MSR_REENLIGHTENMENT_CONTROL; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 35: - feat->eax |= HV_ACCESS_REENLIGHTENMENT; + vcpu_set_cpuid_feature(vcpu, HV_ACCESS_REENLIGHTENMENT); msr->idx = HV_X64_MSR_REENLIGHTENMENT_CONTROL; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 36: msr->idx = HV_X64_MSR_REENLIGHTENMENT_CONTROL; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 1; + msr->fault_expected = false; break; case 37: /* Can only write '0' */ msr->idx = HV_X64_MSR_TSC_EMULATION_STATUS; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 0; + msr->fault_expected = true; break; case 38: msr->idx = HV_X64_MSR_CRASH_P0; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 39: - feat->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE); msr->idx = HV_X64_MSR_CRASH_P0; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 40: msr->idx = HV_X64_MSR_CRASH_P0; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 1; + msr->fault_expected = false; break; case 41: msr->idx = HV_X64_MSR_SYNDBG_STATUS; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 42: - feat->edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE; - dbg->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + vcpu_set_cpuid_feature(vcpu, HV_FEATURE_DEBUG_MSRS_AVAILABLE); + vcpu_set_cpuid_feature(vcpu, HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING); msr->idx = HV_X64_MSR_SYNDBG_STATUS; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 43: msr->idx = HV_X64_MSR_SYNDBG_STATUS; - msr->write = 1; + msr->write = true; msr->write_val = 0; - msr->available = 1; + msr->fault_expected = false; break; case 44: + /* MSR is not available when CPUID feature bit is unset */ + if (!has_invtsc) + continue; + msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL; + msr->write = false; + msr->fault_expected = true; + break; + case 45: + /* MSR is vailable when CPUID feature bit is set */ + if (!has_invtsc) + continue; + vcpu_set_cpuid_feature(vcpu, HV_ACCESS_TSC_INVARIANT); + msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL; + msr->write = false; + msr->fault_expected = false; + break; + case 46: + /* Writing bits other than 0 is forbidden */ + if (!has_invtsc) + continue; + msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL; + msr->write = true; + msr->write_val = 0xdeadbeef; + msr->fault_expected = true; + break; + case 47: + /* Setting bit 0 enables the feature */ + if (!has_invtsc) + continue; + msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL; + msr->write = true; + msr->write_val = 1; + msr->fault_expected = false; + break; + + default: kvm_vm_free(vm); return; } @@ -423,13 +491,11 @@ static void guest_test_msrs_access(void) msr->idx, msr->write ? "write" : "read"); vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "unexpected exit reason: %u (%s)", - run->exit_reason, exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - REPORT_GUEST_ASSERT_2(uc, "MSR = %lx, vector = %lx"); + REPORT_GUEST_ASSERT_3(uc, "MSR = %lx, arg1 = %lx, arg2 = %lx"); return; case UCALL_DONE: break; @@ -445,10 +511,8 @@ static void guest_test_msrs_access(void) static void guest_test_hcalls_access(void) { - struct kvm_cpuid_entry2 *feat, *recomm, *dbg; struct kvm_cpuid2 *prev_cpuid = NULL; struct kvm_vcpu *vcpu; - struct kvm_run *run; struct kvm_vm *vm; struct ucall uc; int stage = 0; @@ -480,15 +544,9 @@ static void guest_test_hcalls_access(void) vcpu_init_cpuid(vcpu, prev_cpuid); } - feat = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES); - recomm = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_ENLIGHTMENT_INFO); - dbg = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES); - - run = vcpu->run; - switch (stage) { case 0: - feat->eax |= HV_MSR_HYPERCALL_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_HYPERCALL_AVAILABLE); hcall->control = 0xbeef; hcall->expect = HV_STATUS_INVALID_HYPERCALL_CODE; break; @@ -498,7 +556,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 2: - feat->ebx |= HV_POST_MESSAGES; + vcpu_set_cpuid_feature(vcpu, HV_POST_MESSAGES); hcall->control = HVCALL_POST_MESSAGE; hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; break; @@ -508,7 +566,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 4: - feat->ebx |= HV_SIGNAL_EVENTS; + vcpu_set_cpuid_feature(vcpu, HV_SIGNAL_EVENTS); hcall->control = HVCALL_SIGNAL_EVENT; hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; break; @@ -518,12 +576,12 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_INVALID_HYPERCALL_CODE; break; case 6: - dbg->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + vcpu_set_cpuid_feature(vcpu, HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING); hcall->control = HVCALL_RESET_DEBUG_SESSION; hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 7: - feat->ebx |= HV_DEBUGGING; + vcpu_set_cpuid_feature(vcpu, HV_DEBUGGING); hcall->control = HVCALL_RESET_DEBUG_SESSION; hcall->expect = HV_STATUS_OPERATION_DENIED; break; @@ -533,7 +591,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 9: - recomm->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; + vcpu_set_cpuid_feature(vcpu, HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED); hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE; hcall->expect = HV_STATUS_SUCCESS; break; @@ -542,7 +600,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 11: - recomm->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED; + vcpu_set_cpuid_feature(vcpu, HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED); hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX; hcall->expect = HV_STATUS_SUCCESS; break; @@ -552,7 +610,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 13: - recomm->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; + vcpu_set_cpuid_feature(vcpu, HV_X64_CLUSTER_IPI_RECOMMENDED); hcall->control = HVCALL_SEND_IPI; hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; break; @@ -567,7 +625,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 16: - recomm->ebx = 0xfff; + vcpu_set_cpuid_feature(vcpu, HV_PV_SPINLOCKS_TEST); hcall->control = HVCALL_NOTIFY_LONG_SPIN_WAIT; hcall->expect = HV_STATUS_SUCCESS; break; @@ -577,12 +635,21 @@ static void guest_test_hcalls_access(void) hcall->ud_expected = true; break; case 18: - feat->edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE); hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | HV_HYPERCALL_FAST_BIT; hcall->ud_expected = false; hcall->expect = HV_STATUS_SUCCESS; break; case 19: + hcall->control = HV_EXT_CALL_QUERY_CAPABILITIES; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 20: + vcpu_set_cpuid_feature(vcpu, HV_ENABLE_EXTENDED_HYPERCALLS); + hcall->control = HV_EXT_CALL_QUERY_CAPABILITIES | HV_HYPERCALL_FAST_BIT; + hcall->expect = HV_STATUS_INVALID_PARAMETER; + break; + case 21: kvm_vm_free(vm); return; } @@ -594,9 +661,7 @@ static void guest_test_hcalls_access(void) pr_debug("Stage %d: testing hcall: 0x%lx\n", stage, hcall->control); vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "unexpected exit reason: %u (%s)", - run->exit_reason, exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c index 0cbb0e646ef8..6feb5ddb031d 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c @@ -243,7 +243,6 @@ int main(int argc, char *argv[]) { struct kvm_vm *vm; struct kvm_vcpu *vcpu[3]; - unsigned int exit_reason; vm_vaddr_t hcall_page; pthread_t threads[2]; int stage = 1, r; @@ -283,10 +282,7 @@ int main(int argc, char *argv[]) while (true) { vcpu_run(vcpu[0]); - exit_reason = vcpu[0]->run->exit_reason; - TEST_ASSERT(exit_reason == KVM_EXIT_IO, - "unexpected exit reason: %u (%s)", - exit_reason, exit_reason_str(exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu[0], KVM_EXIT_IO); switch (get_ucall(vcpu[0], &uc)) { case UCALL_SYNC: diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c index 68a7d354ea07..e446d76d1c0c 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c @@ -156,7 +156,6 @@ int main(int argc, char *argv[]) vm_vaddr_t hcall_page; struct kvm_vcpu *vcpu; struct kvm_vm *vm; - struct kvm_run *run; struct ucall uc; int stage; @@ -165,7 +164,6 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); vcpu_set_hv_cpuid(vcpu); - run = vcpu->run; vcpu_alloc_svm(vm, &nested_gva); vcpu_alloc_hyperv_test_pages(vm, &hv_pages_gva); @@ -177,10 +175,7 @@ int main(int argc, char *argv[]) for (stage = 1;; stage++) { vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Stage %d: unexpected exit reason: %u (%s),\n", - stage, run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c index 68f97ff720a7..4758b6ef5618 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c @@ -542,18 +542,13 @@ static void *vcpu_thread(void *arg) struct ucall uc; int old; int r; - unsigned int exit_reason; r = pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, &old); TEST_ASSERT(!r, "pthread_setcanceltype failed on vcpu_id=%u with errno=%d", vcpu->id, r); vcpu_run(vcpu); - exit_reason = vcpu->run->exit_reason; - - TEST_ASSERT(exit_reason == KVM_EXIT_IO, - "vCPU %u exited with unexpected exit reason %u-%s, expected KVM_EXIT_IO", - vcpu->id, exit_reason, exit_reason_str(exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: @@ -587,7 +582,6 @@ int main(int argc, char *argv[]) { struct kvm_vm *vm; struct kvm_vcpu *vcpu[3]; - unsigned int exit_reason; pthread_t threads[2]; vm_vaddr_t test_data_page, gva; vm_paddr_t gpa; @@ -657,11 +651,7 @@ int main(int argc, char *argv[]) while (true) { vcpu_run(vcpu[0]); - exit_reason = vcpu[0]->run->exit_reason; - - TEST_ASSERT(exit_reason == KVM_EXIT_IO, - "unexpected exit reason: %u (%s)", - exit_reason, exit_reason_str(exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu[0], KVM_EXIT_IO); switch (get_ucall(vcpu[0], &uc)) { case UCALL_SYNC: diff --git a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c b/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c index 813ce282cf56..1778704360a6 100644 --- a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c +++ b/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c @@ -105,7 +105,6 @@ static void setup_clock(struct kvm_vm *vm, struct test_case *test_case) static void enter_guest(struct kvm_vcpu *vcpu) { struct kvm_clock_data start, end; - struct kvm_run *run = vcpu->run; struct kvm_vm *vm = vcpu->vm; struct ucall uc; int i; @@ -118,9 +117,7 @@ static void enter_guest(struct kvm_vcpu *vcpu) vcpu_run(vcpu); vm_ioctl(vm, KVM_GET_CLOCK, &end); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "unexpected exit reason: %u (%s)", - run->exit_reason, exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c index 619655c1a1f3..f774a9e62858 100644 --- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c +++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c @@ -111,14 +111,11 @@ static void pr_hcall(struct ucall *uc) static void enter_guest(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu->run; struct ucall uc; while (true) { vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "unexpected exit reason: %u (%s)", - run->exit_reason, exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_PR_MSR: diff --git a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c index fb02581953a3..ce1ccc4c1503 100644 --- a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c +++ b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c @@ -93,7 +93,7 @@ int main(void) { int warnings_before, warnings_after; - TEST_REQUIRE(is_intel_cpu()); + TEST_REQUIRE(host_cpu_is_intel); TEST_REQUIRE(!vm_is_unrestricted_guest(NULL)); diff --git a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c index 016070cad36e..72812644d7f5 100644 --- a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c +++ b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c @@ -64,7 +64,6 @@ int main(int argc, char *argv[]) { uint64_t disabled_quirks; struct kvm_vcpu *vcpu; - struct kvm_run *run; struct kvm_vm *vm; struct ucall uc; int testcase; @@ -74,18 +73,12 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu, guest_code); vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_MWAIT); - run = vcpu->run; - vm_init_descriptor_tables(vm); vcpu_init_descriptor_tables(vcpu); while (1) { vcpu_run(vcpu); - - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Unexpected exit reason: %u (%s),\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: diff --git a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c index ac33835f78f4..6502aa23c2f8 100644 --- a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c +++ b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c @@ -166,12 +166,9 @@ static void __attribute__((__flatten__)) l1_guest_code(void *test_data) static void assert_ucall_vector(struct kvm_vcpu *vcpu, int vector) { - struct kvm_run *run = vcpu->run; struct ucall uc; - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Unexpected exit reason: %u (%s),\n", - run->exit_reason, exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c index 310a104d94f0..c9a07963d68a 100644 --- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c +++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c @@ -36,15 +36,12 @@ static void guest_code(void) static void test_msr_platform_info_enabled(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu->run; struct ucall uc; vm_enable_cap(vcpu->vm, KVM_CAP_MSR_PLATFORM_INFO, true); vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Exit_reason other than KVM_EXIT_IO: %u (%s),\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + get_ucall(vcpu, &uc); TEST_ASSERT(uc.cmd == UCALL_SYNC, "Received ucall other than UCALL_SYNC: %lu\n", uc.cmd); @@ -56,14 +53,9 @@ static void test_msr_platform_info_enabled(struct kvm_vcpu *vcpu) static void test_msr_platform_info_disabled(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu->run; - vm_enable_cap(vcpu->vm, KVM_CAP_MSR_PLATFORM_INFO, false); vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, - "Exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_SHUTDOWN); } int main(int argc, char *argv[]) diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 2de98fce7edd..2feef25ba691 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -151,14 +151,10 @@ static void amd_guest_code(void) */ static uint64_t run_vcpu_to_sync(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu->run; struct ucall uc; vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Exit_reason other than KVM_EXIT_IO: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); get_ucall(vcpu, &uc); TEST_ASSERT(uc.cmd == UCALL_SYNC, "Received ucall other than UCALL_SYNC: %lu", uc.cmd); @@ -198,14 +194,15 @@ static struct kvm_pmu_event_filter *alloc_pmu_event_filter(uint32_t nevents) static struct kvm_pmu_event_filter * -create_pmu_event_filter(const uint64_t event_list[], - int nevents, uint32_t action) +create_pmu_event_filter(const uint64_t event_list[], int nevents, + uint32_t action, uint32_t flags) { struct kvm_pmu_event_filter *f; int i; f = alloc_pmu_event_filter(nevents); f->action = action; + f->flags = flags; for (i = 0; i < nevents; i++) f->events[i] = event_list[i]; @@ -216,7 +213,7 @@ static struct kvm_pmu_event_filter *event_filter(uint32_t action) { return create_pmu_event_filter(event_list, ARRAY_SIZE(event_list), - action); + action, 0); } /* @@ -263,7 +260,7 @@ static void test_amd_deny_list(struct kvm_vcpu *vcpu) struct kvm_pmu_event_filter *f; uint64_t count; - f = create_pmu_event_filter(&event, 1, KVM_PMU_EVENT_DENY); + f = create_pmu_event_filter(&event, 1, KVM_PMU_EVENT_DENY, 0); count = test_with_filter(vcpu, f); free(f); @@ -363,7 +360,7 @@ static void test_pmu_config_disable(void (*guest_code)(void)) */ static bool use_intel_pmu(void) { - return is_intel_cpu() && + return host_cpu_is_intel && kvm_cpu_property(X86_PROPERTY_PMU_VERSION) && kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS) && kvm_pmu_has(X86_PMU_FEATURE_BRANCH_INSNS_RETIRED); @@ -397,19 +394,378 @@ static bool use_amd_pmu(void) uint32_t family = kvm_cpu_family(); uint32_t model = kvm_cpu_model(); - return is_amd_cpu() && + return host_cpu_is_amd && (is_zen1(family, model) || is_zen2(family, model) || is_zen3(family, model)); } +/* + * "MEM_INST_RETIRED.ALL_LOADS", "MEM_INST_RETIRED.ALL_STORES", and + * "MEM_INST_RETIRED.ANY" from https://perfmon-events.intel.com/ + * supported on Intel Xeon processors: + * - Sapphire Rapids, Ice Lake, Cascade Lake, Skylake. + */ +#define MEM_INST_RETIRED 0xD0 +#define MEM_INST_RETIRED_LOAD EVENT(MEM_INST_RETIRED, 0x81) +#define MEM_INST_RETIRED_STORE EVENT(MEM_INST_RETIRED, 0x82) +#define MEM_INST_RETIRED_LOAD_STORE EVENT(MEM_INST_RETIRED, 0x83) + +static bool supports_event_mem_inst_retired(void) +{ + uint32_t eax, ebx, ecx, edx; + + cpuid(1, &eax, &ebx, &ecx, &edx); + if (x86_family(eax) == 0x6) { + switch (x86_model(eax)) { + /* Sapphire Rapids */ + case 0x8F: + /* Ice Lake */ + case 0x6A: + /* Skylake */ + /* Cascade Lake */ + case 0x55: + return true; + } + } + + return false; +} + +/* + * "LS Dispatch", from Processor Programming Reference + * (PPR) for AMD Family 17h Model 01h, Revision B1 Processors, + * Preliminary Processor Programming Reference (PPR) for AMD Family + * 17h Model 31h, Revision B0 Processors, and Preliminary Processor + * Programming Reference (PPR) for AMD Family 19h Model 01h, Revision + * B1 Processors Volume 1 of 2. + */ +#define LS_DISPATCH 0x29 +#define LS_DISPATCH_LOAD EVENT(LS_DISPATCH, BIT(0)) +#define LS_DISPATCH_STORE EVENT(LS_DISPATCH, BIT(1)) +#define LS_DISPATCH_LOAD_STORE EVENT(LS_DISPATCH, BIT(2)) + +#define INCLUDE_MASKED_ENTRY(event_select, mask, match) \ + KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, false) +#define EXCLUDE_MASKED_ENTRY(event_select, mask, match) \ + KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, true) + +struct perf_counter { + union { + uint64_t raw; + struct { + uint64_t loads:22; + uint64_t stores:22; + uint64_t loads_stores:20; + }; + }; +}; + +static uint64_t masked_events_guest_test(uint32_t msr_base) +{ + uint64_t ld0, ld1, st0, st1, ls0, ls1; + struct perf_counter c; + int val; + + /* + * The acutal value of the counters don't determine the outcome of + * the test. Only that they are zero or non-zero. + */ + ld0 = rdmsr(msr_base + 0); + st0 = rdmsr(msr_base + 1); + ls0 = rdmsr(msr_base + 2); + + __asm__ __volatile__("movl $0, %[v];" + "movl %[v], %%eax;" + "incl %[v];" + : [v]"+m"(val) :: "eax"); + + ld1 = rdmsr(msr_base + 0); + st1 = rdmsr(msr_base + 1); + ls1 = rdmsr(msr_base + 2); + + c.loads = ld1 - ld0; + c.stores = st1 - st0; + c.loads_stores = ls1 - ls0; + + return c.raw; +} + +static void intel_masked_events_guest_code(void) +{ + uint64_t r; + + for (;;) { + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); + + wrmsr(MSR_P6_EVNTSEL0 + 0, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | MEM_INST_RETIRED_LOAD); + wrmsr(MSR_P6_EVNTSEL0 + 1, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | MEM_INST_RETIRED_STORE); + wrmsr(MSR_P6_EVNTSEL0 + 2, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | MEM_INST_RETIRED_LOAD_STORE); + + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0x7); + + r = masked_events_guest_test(MSR_IA32_PMC0); + + GUEST_SYNC(r); + } +} + +static void amd_masked_events_guest_code(void) +{ + uint64_t r; + + for (;;) { + wrmsr(MSR_K7_EVNTSEL0, 0); + wrmsr(MSR_K7_EVNTSEL1, 0); + wrmsr(MSR_K7_EVNTSEL2, 0); + + wrmsr(MSR_K7_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | LS_DISPATCH_LOAD); + wrmsr(MSR_K7_EVNTSEL1, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | LS_DISPATCH_STORE); + wrmsr(MSR_K7_EVNTSEL2, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | LS_DISPATCH_LOAD_STORE); + + r = masked_events_guest_test(MSR_K7_PERFCTR0); + + GUEST_SYNC(r); + } +} + +static struct perf_counter run_masked_events_test(struct kvm_vcpu *vcpu, + const uint64_t masked_events[], + const int nmasked_events) +{ + struct kvm_pmu_event_filter *f; + struct perf_counter r; + + f = create_pmu_event_filter(masked_events, nmasked_events, + KVM_PMU_EVENT_ALLOW, + KVM_PMU_EVENT_FLAG_MASKED_EVENTS); + r.raw = test_with_filter(vcpu, f); + free(f); + + return r; +} + +/* Matches KVM_PMU_EVENT_FILTER_MAX_EVENTS in pmu.c */ +#define MAX_FILTER_EVENTS 300 +#define MAX_TEST_EVENTS 10 + +#define ALLOW_LOADS BIT(0) +#define ALLOW_STORES BIT(1) +#define ALLOW_LOADS_STORES BIT(2) + +struct masked_events_test { + uint64_t intel_events[MAX_TEST_EVENTS]; + uint64_t intel_event_end; + uint64_t amd_events[MAX_TEST_EVENTS]; + uint64_t amd_event_end; + const char *msg; + uint32_t flags; +}; + +/* + * These are the test cases for the masked events tests. + * + * For each test, the guest enables 3 PMU counters (loads, stores, + * loads + stores). The filter is then set in KVM with the masked events + * provided. The test then verifies that the counters agree with which + * ones should be counting and which ones should be filtered. + */ +const struct masked_events_test test_cases[] = { + { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFF, 0x81), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xFF, BIT(0)), + }, + .msg = "Only allow loads.", + .flags = ALLOW_LOADS, + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFF, 0x82), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xFF, BIT(1)), + }, + .msg = "Only allow stores.", + .flags = ALLOW_STORES, + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFF, 0x83), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xFF, BIT(2)), + }, + .msg = "Only allow loads + stores.", + .flags = ALLOW_LOADS_STORES, + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0x7C, 0), + EXCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFF, 0x83), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, ~(BIT(0) | BIT(1)), 0), + }, + .msg = "Only allow loads and stores.", + .flags = ALLOW_LOADS | ALLOW_STORES, + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0x7C, 0), + EXCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFF, 0x82), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xF8, 0), + EXCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xFF, BIT(1)), + }, + .msg = "Only allow loads and loads + stores.", + .flags = ALLOW_LOADS | ALLOW_LOADS_STORES + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFE, 0x82), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xF8, 0), + EXCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xFF, BIT(0)), + }, + .msg = "Only allow stores and loads + stores.", + .flags = ALLOW_STORES | ALLOW_LOADS_STORES + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0x7C, 0), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xF8, 0), + }, + .msg = "Only allow loads, stores, and loads + stores.", + .flags = ALLOW_LOADS | ALLOW_STORES | ALLOW_LOADS_STORES + }, +}; + +static int append_test_events(const struct masked_events_test *test, + uint64_t *events, int nevents) +{ + const uint64_t *evts; + int i; + + evts = use_intel_pmu() ? test->intel_events : test->amd_events; + for (i = 0; i < MAX_TEST_EVENTS; i++) { + if (evts[i] == 0) + break; + + events[nevents + i] = evts[i]; + } + + return nevents + i; +} + +static bool bool_eq(bool a, bool b) +{ + return a == b; +} + +static void run_masked_events_tests(struct kvm_vcpu *vcpu, uint64_t *events, + int nevents) +{ + int ntests = ARRAY_SIZE(test_cases); + struct perf_counter c; + int i, n; + + for (i = 0; i < ntests; i++) { + const struct masked_events_test *test = &test_cases[i]; + + /* Do any test case events overflow MAX_TEST_EVENTS? */ + assert(test->intel_event_end == 0); + assert(test->amd_event_end == 0); + + n = append_test_events(test, events, nevents); + + c = run_masked_events_test(vcpu, events, n); + TEST_ASSERT(bool_eq(c.loads, test->flags & ALLOW_LOADS) && + bool_eq(c.stores, test->flags & ALLOW_STORES) && + bool_eq(c.loads_stores, + test->flags & ALLOW_LOADS_STORES), + "%s loads: %u, stores: %u, loads + stores: %u", + test->msg, c.loads, c.stores, c.loads_stores); + } +} + +static void add_dummy_events(uint64_t *events, int nevents) +{ + int i; + + for (i = 0; i < nevents; i++) { + int event_select = i % 0xFF; + bool exclude = ((i % 4) == 0); + + if (event_select == MEM_INST_RETIRED || + event_select == LS_DISPATCH) + event_select++; + + events[i] = KVM_PMU_ENCODE_MASKED_ENTRY(event_select, 0, + 0, exclude); + } +} + +static void test_masked_events(struct kvm_vcpu *vcpu) +{ + int nevents = MAX_FILTER_EVENTS - MAX_TEST_EVENTS; + uint64_t events[MAX_FILTER_EVENTS]; + + /* Run the test cases against a sparse PMU event filter. */ + run_masked_events_tests(vcpu, events, 0); + + /* Run the test cases against a dense PMU event filter. */ + add_dummy_events(events, MAX_FILTER_EVENTS); + run_masked_events_tests(vcpu, events, nevents); +} + +static int run_filter_test(struct kvm_vcpu *vcpu, const uint64_t *events, + int nevents, uint32_t flags) +{ + struct kvm_pmu_event_filter *f; + int r; + + f = create_pmu_event_filter(events, nevents, KVM_PMU_EVENT_ALLOW, flags); + r = __vm_ioctl(vcpu->vm, KVM_SET_PMU_EVENT_FILTER, f); + free(f); + + return r; +} + +static void test_filter_ioctl(struct kvm_vcpu *vcpu) +{ + uint64_t e = ~0ul; + int r; + + /* + * Unfortunately having invalid bits set in event data is expected to + * pass when flags == 0 (bits other than eventsel+umask). + */ + r = run_filter_test(vcpu, &e, 1, 0); + TEST_ASSERT(r == 0, "Valid PMU Event Filter is failing"); + + r = run_filter_test(vcpu, &e, 1, KVM_PMU_EVENT_FLAG_MASKED_EVENTS); + TEST_ASSERT(r != 0, "Invalid PMU Event Filter is expected to fail"); + + e = KVM_PMU_ENCODE_MASKED_ENTRY(0xff, 0xff, 0xff, 0xf); + r = run_filter_test(vcpu, &e, 1, KVM_PMU_EVENT_FLAG_MASKED_EVENTS); + TEST_ASSERT(r == 0, "Valid PMU Event Filter is failing"); +} + int main(int argc, char *argv[]) { void (*guest_code)(void); - struct kvm_vcpu *vcpu; + struct kvm_vcpu *vcpu, *vcpu2 = NULL; struct kvm_vm *vm; TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_FILTER)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_MASKED_EVENTS)); TEST_REQUIRE(use_intel_pmu() || use_amd_pmu()); guest_code = use_intel_pmu() ? intel_guest_code : amd_guest_code; @@ -430,6 +786,17 @@ int main(int argc, char *argv[]) test_not_member_deny_list(vcpu); test_not_member_allow_list(vcpu); + if (use_intel_pmu() && + supports_event_mem_inst_retired() && + kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS) >= 3) + vcpu2 = vm_vcpu_add(vm, 2, intel_masked_events_guest_code); + else if (use_amd_pmu()) + vcpu2 = vm_vcpu_add(vm, 2, amd_masked_events_guest_code); + + if (vcpu2) + test_masked_events(vcpu2); + test_filter_ioctl(vcpu); + kvm_vm_free(vm); test_pmu_config_disable(guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index cb38a478e1f6..e18b86666e1f 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -133,7 +133,6 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_regs regs; struct kvm_vm *vm; - struct kvm_run *run; struct kvm_x86_state *state; int stage, stage_reported; @@ -142,8 +141,6 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); - run = vcpu->run; - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA, SMRAM_MEMSLOT, SMRAM_PAGES, 0); TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, SMRAM_GPA, SMRAM_MEMSLOT) @@ -169,10 +166,7 @@ int main(int argc, char *argv[]) for (stage = 1;; stage++) { vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Stage %d: unexpected exit reason: %u (%s),\n", - stage, run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); memset(®s, 0, sizeof(regs)); vcpu_regs_get(vcpu, ®s); @@ -208,7 +202,6 @@ int main(int argc, char *argv[]) vcpu = vm_recreate_with_one_vcpu(vm); vcpu_load_state(vcpu, state); - run = vcpu->run; kvm_x86_state_cleanup(state); } diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index ea578971fb9f..4c4925a8ab45 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -158,14 +158,12 @@ int main(int argc, char *argv[]) struct kvm_regs regs1, regs2; struct kvm_vcpu *vcpu; struct kvm_vm *vm; - struct kvm_run *run; struct kvm_x86_state *state; struct ucall uc; int stage; /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); - run = vcpu->run; vcpu_regs_get(vcpu, ®s1); @@ -183,10 +181,7 @@ int main(int argc, char *argv[]) for (stage = 1;; stage++) { vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Stage %d: unexpected exit reason: %u (%s),\n", - stage, run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: @@ -214,7 +209,6 @@ int main(int argc, char *argv[]) /* Restore state in a new VM. */ vcpu = vm_recreate_with_one_vcpu(vm); vcpu_load_state(vcpu, state); - run = vcpu->run; kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c index 4a07ba227b99..32bef39bec21 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c @@ -85,7 +85,6 @@ static void l1_guest_code(struct svm_test_data *svm) int main(int argc, char *argv[]) { struct kvm_vcpu *vcpu; - struct kvm_run *run; vm_vaddr_t svm_gva; struct kvm_vm *vm; struct ucall uc; @@ -103,13 +102,8 @@ int main(int argc, char *argv[]) vcpu_alloc_svm(vm, &svm_gva); vcpu_args_set(vcpu, 1, svm_gva); - run = vcpu->run; - vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c index e73fcdef47bb..d6fcdcc3af31 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c @@ -42,7 +42,6 @@ static void l1_guest_code(struct svm_test_data *svm, struct idt_entry *idt) int main(int argc, char *argv[]) { struct kvm_vcpu *vcpu; - struct kvm_run *run; vm_vaddr_t svm_gva; struct kvm_vm *vm; @@ -55,13 +54,9 @@ int main(int argc, char *argv[]) vcpu_alloc_svm(vm, &svm_gva); vcpu_args_set(vcpu, 2, svm_gva, vm->idt); - run = vcpu->run; vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, - "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_SHUTDOWN); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c index b34980d45648..4e2479716da6 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c @@ -176,16 +176,12 @@ static void run_test(bool is_nmi) memset(&debug, 0, sizeof(debug)); vcpu_guest_debug_set(vcpu, &debug); - struct kvm_run *run = vcpu->run; struct ucall uc; alarm(2); vcpu_run(vcpu); alarm(0); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c index c3ac45df7483..8a62cca28cfb 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c @@ -47,14 +47,10 @@ int main(int argc, char *argv[]) vcpu_args_set(vcpu, 1, svm_gva); for (;;) { - volatile struct kvm_run *run = vcpu->run; struct ucall uc; vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c index d2f9b5bdfab2..2da89fdc2471 100644 --- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c +++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c @@ -132,10 +132,7 @@ int main(int argc, char *argv[]) /* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */ run->kvm_valid_regs = TEST_SYNC_FIELDS; rv = _vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Unexpected exit reason: %u (%s),\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); vcpu_regs_get(vcpu, ®s); compare_regs(®s, &run->s.regs.regs); @@ -154,10 +151,7 @@ int main(int argc, char *argv[]) run->kvm_valid_regs = TEST_SYNC_FIELDS; run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS; rv = _vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Unexpected exit reason: %u (%s),\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); TEST_ASSERT(run->s.regs.regs.rbx == 0xBAD1DEA + 1, "rbx sync regs value incorrect 0x%llx.", run->s.regs.regs.rbx); @@ -181,10 +175,7 @@ int main(int argc, char *argv[]) run->kvm_dirty_regs = 0; run->s.regs.regs.rbx = 0xDEADBEEF; rv = _vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Unexpected exit reason: %u (%s),\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); TEST_ASSERT(run->s.regs.regs.rbx != 0xDEADBEEF, "rbx sync regs value incorrect 0x%llx.", run->s.regs.regs.rbx); @@ -199,10 +190,7 @@ int main(int argc, char *argv[]) regs.rbx = 0xBAC0; vcpu_regs_set(vcpu, ®s); rv = _vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Unexpected exit reason: %u (%s),\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); TEST_ASSERT(run->s.regs.regs.rbx == 0xAAAA, "rbx sync regs value incorrect 0x%llx.", run->s.regs.regs.rbx); @@ -219,10 +207,7 @@ int main(int argc, char *argv[]) run->kvm_dirty_regs = TEST_SYNC_FIELDS; run->s.regs.regs.rbx = 0xBBBB; rv = _vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Unexpected exit reason: %u (%s),\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); TEST_ASSERT(run->s.regs.regs.rbx == 0xBBBB, "rbx sync regs value incorrect 0x%llx.", run->s.regs.regs.rbx); diff --git a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c b/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c index ead5d878a71c..56306a19144a 100644 --- a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c +++ b/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c @@ -89,9 +89,7 @@ int main(void) run = vcpu->run; vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Expected KVM_EXIT_IO, got: %u (%s)\n", - run->exit_reason, exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); TEST_ASSERT(run->io.port == ARBITRARY_IO_PORT, "Expected IN from port %d from L2, got port %d", ARBITRARY_IO_PORT, run->io.port); @@ -111,10 +109,7 @@ int main(void) if (has_svm) { - TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, - "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_SHUTDOWN); } else { switch (get_ucall(vcpu, &uc)) { case UCALL_DONE: diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c index 22d366c697f7..c9f67702f657 100644 --- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c +++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c @@ -72,11 +72,16 @@ static void run_vcpu(struct kvm_vcpu *vcpu, int stage) switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: - TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && - uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx", - stage + 1, (ulong)uc.args[1]); + if (!strcmp((const char *)uc.args[0], "hello") && + uc.args[1] == stage + 1) + ksft_test_result_pass("stage %d passed\n", stage + 1); + else + ksft_test_result_fail( + "stage %d: Unexpected register values vmexit, got %lx", + stage + 1, (ulong)uc.args[1]); return; case UCALL_DONE: + ksft_test_result_pass("stage %d passed\n", stage + 1); return; case UCALL_ABORT: REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); @@ -92,6 +97,9 @@ int main(void) struct kvm_vm *vm; uint64_t val; + ksft_print_header(); + ksft_set_plan(5); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); val = 0; @@ -149,5 +157,5 @@ int main(void) kvm_vm_free(vm); - return 0; + ksft_finished(); /* Print results and exit() accordingly */ } diff --git a/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c b/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c index 47139aab7408..5b669818e39a 100644 --- a/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c +++ b/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c @@ -64,14 +64,10 @@ static void *run_vcpu(void *_cpu_nr) pthread_spin_unlock(&create_lock); for (;;) { - volatile struct kvm_run *run = vcpu->run; struct ucall uc; vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_DONE: diff --git a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c index a897c7fd8abe..85f34ca7e49e 100644 --- a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c +++ b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c @@ -137,15 +137,11 @@ static void guest_gp_handler(struct ex_regs *regs) static void run_vcpu_expect_gp(struct kvm_vcpu *vcpu) { - unsigned int exit_reason; struct ucall uc; vcpu_run(vcpu); - exit_reason = vcpu->run->exit_reason; - TEST_ASSERT(exit_reason == KVM_EXIT_IO, - "exited with unexpected exit reason %u-%s, expected KVM_EXIT_IO", - exit_reason, exit_reason_str(exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_SYNC, "Expect UCALL_SYNC\n"); TEST_ASSERT(uc.args[1] == SYNC_GP, "#GP is expected."); @@ -182,7 +178,6 @@ static void *run_ucna_injection(void *arg) struct ucall uc; int old; int r; - unsigned int exit_reason; r = pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, &old); TEST_ASSERT(r == 0, @@ -191,10 +186,7 @@ static void *run_ucna_injection(void *arg) vcpu_run(params->vcpu); - exit_reason = params->vcpu->run->exit_reason; - TEST_ASSERT(exit_reason == KVM_EXIT_IO, - "unexpected exit reason %u-%s, expected KVM_EXIT_IO", - exit_reason, exit_reason_str(exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(params->vcpu, KVM_EXIT_IO); TEST_ASSERT(get_ucall(params->vcpu, &uc) == UCALL_SYNC, "Expect UCALL_SYNC\n"); TEST_ASSERT(uc.args[1] == SYNC_FIRST_UCNA, "Injecting first UCNA."); @@ -204,10 +196,7 @@ static void *run_ucna_injection(void *arg) inject_ucna(params->vcpu, FIRST_UCNA_ADDR); vcpu_run(params->vcpu); - exit_reason = params->vcpu->run->exit_reason; - TEST_ASSERT(exit_reason == KVM_EXIT_IO, - "unexpected exit reason %u-%s, expected KVM_EXIT_IO", - exit_reason, exit_reason_str(exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(params->vcpu, KVM_EXIT_IO); TEST_ASSERT(get_ucall(params->vcpu, &uc) == UCALL_SYNC, "Expect UCALL_SYNC\n"); TEST_ASSERT(uc.args[1] == SYNC_SECOND_UCNA, "Injecting second UCNA."); @@ -217,10 +206,7 @@ static void *run_ucna_injection(void *arg) inject_ucna(params->vcpu, SECOND_UCNA_ADDR); vcpu_run(params->vcpu); - exit_reason = params->vcpu->run->exit_reason; - TEST_ASSERT(exit_reason == KVM_EXIT_IO, - "unexpected exit reason %u-%s, expected KVM_EXIT_IO", - exit_reason, exit_reason_str(exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(params->vcpu, KVM_EXIT_IO); if (get_ucall(params->vcpu, &uc) == UCALL_ABORT) { TEST_ASSERT(false, "vCPU assertion failure: %s.\n", (const char *)uc.args[0]); diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c index 91076c9787b4..0cb51fa42773 100644 --- a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c +++ b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c @@ -63,11 +63,7 @@ int main(int argc, char *argv[]) while (1) { vcpu_run(vcpu); - - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Unexpected exit reason: %u (%s),\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); if (get_ucall(vcpu, &uc)) break; diff --git a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c index 25fa55344a10..3533dc2fbfee 100644 --- a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c +++ b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c @@ -410,10 +410,7 @@ static void process_rdmsr(struct kvm_vcpu *vcpu, uint32_t msr_index) check_for_guest_assert(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_X86_RDMSR, - "Unexpected exit reason: %u (%s),\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_X86_RDMSR); TEST_ASSERT(run->msr.index == msr_index, "Unexpected msr (0x%04x), expected 0x%04x", run->msr.index, msr_index); @@ -445,10 +442,7 @@ static void process_wrmsr(struct kvm_vcpu *vcpu, uint32_t msr_index) check_for_guest_assert(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_X86_WRMSR, - "Unexpected exit reason: %u (%s),\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_X86_WRMSR); TEST_ASSERT(run->msr.index == msr_index, "Unexpected msr (0x%04x), expected 0x%04x", run->msr.index, msr_index); @@ -472,15 +466,11 @@ static void process_wrmsr(struct kvm_vcpu *vcpu, uint32_t msr_index) static void process_ucall_done(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu->run; struct ucall uc; check_for_guest_assert(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Unexpected exit reason: %u (%s)", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_DONE, "Unexpected ucall command: %lu, expected UCALL_DONE (%d)", @@ -489,15 +479,11 @@ static void process_ucall_done(struct kvm_vcpu *vcpu) static uint64_t process_ucall(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu->run; struct ucall uc = {}; check_for_guest_assert(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Unexpected exit reason: %u (%s)", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: diff --git a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c index 5abecf06329e..2bed5fb3a0d6 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c @@ -96,21 +96,14 @@ int main(int argc, char *argv[]) vcpu_run(vcpu); if (apic_access_addr == high_gpa) { - TEST_ASSERT(run->exit_reason == - KVM_EXIT_INTERNAL_ERROR, - "Got exit reason other than KVM_EXIT_INTERNAL_ERROR: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_INTERNAL_ERROR); TEST_ASSERT(run->internal.suberror == KVM_INTERNAL_ERROR_EMULATION, "Got internal suberror other than KVM_INTERNAL_ERROR_EMULATION: %u\n", run->internal.suberror); break; } - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c index d79651b02740..dad988351493 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c @@ -64,10 +64,7 @@ int main(int argc, char *argv[]) struct ucall uc; vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); if (run->io.port == PORT_L0_EXIT) break; diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c index f0456fb031b1..e4ad5fef52ff 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c @@ -73,7 +73,6 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; - struct kvm_run *run; struct ucall uc; bool done = false; @@ -84,7 +83,6 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva); vcpu_args_set(vcpu, 1, vmx_pages_gva); - run = vcpu->run; /* Add an extra memory slot for testing dirty logging */ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, @@ -117,10 +115,7 @@ int main(int argc, char *argv[]) while (!done) { memset(host_test_mem, 0xaa, TEST_MEM_PAGES * 4096); vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Unexpected exit reason: %u (%s),\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c index 2641b286b4ed..be0bdb8c6f78 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c @@ -26,9 +26,7 @@ static void __run_vcpu_with_invalid_state(struct kvm_vcpu *vcpu) vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR, - "Expected KVM_EXIT_INTERNAL_ERROR, got %d (%s)\n", - run->exit_reason, exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_INTERNAL_ERROR); TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION, "Expected emulation failure, got %d\n", run->emulation_failure.suberror); @@ -111,7 +109,7 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; - TEST_REQUIRE(is_intel_cpu()); + TEST_REQUIRE(host_cpu_is_intel); TEST_REQUIRE(!vm_is_unrestricted_guest(NULL)); vm = vm_create_with_one_vcpu(&vcpu, guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c index 6bfb4bb471ca..a100ee5f0009 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c @@ -74,9 +74,7 @@ int main(int argc, char *argv[]) * The first exit to L0 userspace should be an I/O access from L2. * Running L1 should launch L2 without triggering an exit to userspace. */ - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Expected KVM_EXIT_IO, got: %u (%s)\n", - run->exit_reason, exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); TEST_ASSERT(run->io.port == ARBITRARY_IO_PORT, "Expected IN from port %d from L2, got port %d", diff --git a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c index 465a9434d61c..d427eb146bc5 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c @@ -183,14 +183,10 @@ int main(int argc, char *argv[]) vcpu_ioctl(vcpu, KVM_SET_TSC_KHZ, (void *) (tsc_khz / l1_scale_factor)); for (;;) { - volatile struct kvm_run *run = vcpu->run; struct ucall uc; vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: diff --git a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c index 0efdc05969a5..affc32800158 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c @@ -157,7 +157,6 @@ int main(int argc, char *argv[]) struct kvm_regs regs1, regs2; struct kvm_vm *vm; - struct kvm_run *run; struct kvm_vcpu *vcpu; struct kvm_x86_state *state; struct ucall uc; @@ -173,7 +172,6 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); - run = vcpu->run; vcpu_regs_get(vcpu, ®s1); @@ -182,10 +180,7 @@ int main(int argc, char *argv[]) for (stage = 1;; stage++) { vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Stage %d: unexpected exit reason: %u (%s),\n", - stage, run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: @@ -237,7 +232,6 @@ int main(int argc, char *argv[]) /* Restore state in a new VM. */ vcpu = vm_recreate_with_one_vcpu(vm); vcpu_load_state(vcpu, state); - run = vcpu->run; kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index ff8ecdf32ae0..2ceb5c78c442 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -131,14 +131,10 @@ int main(int argc, char *argv[]) vcpu_args_set(vcpu, 1, vmx_pages_gva); for (;;) { - volatile struct kvm_run *run = vcpu->run; struct ucall uc; vcpu_run(vcpu); - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: diff --git a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c index 3d272d7f961e..67ac2a3292ef 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c @@ -198,7 +198,6 @@ static void *vcpu_thread(void *arg) struct ucall uc; int old; int r; - unsigned int exit_reason; r = pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, &old); TEST_ASSERT(r == 0, @@ -207,11 +206,8 @@ static void *vcpu_thread(void *arg) fprintf(stderr, "vCPU thread running vCPU %u\n", vcpu->id); vcpu_run(vcpu); - exit_reason = vcpu->run->exit_reason; - TEST_ASSERT(exit_reason == KVM_EXIT_IO, - "vCPU %u exited with unexpected exit reason %u-%s, expected KVM_EXIT_IO", - vcpu->id, exit_reason, exit_reason_str(exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); if (get_ucall(vcpu, &uc) == UCALL_ABORT) { TEST_ASSERT(false, diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c index d7d37dae3eeb..396c13f42457 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c @@ -132,6 +132,59 @@ static void test_icr(struct xapic_vcpu *x) __test_icr(x, -1ull & ~APIC_DM_FIXED_MASK); } +static void __test_apic_id(struct kvm_vcpu *vcpu, uint64_t apic_base) +{ + uint32_t apic_id, expected; + struct kvm_lapic_state xapic; + + vcpu_set_msr(vcpu, MSR_IA32_APICBASE, apic_base); + + vcpu_ioctl(vcpu, KVM_GET_LAPIC, &xapic); + + expected = apic_base & X2APIC_ENABLE ? vcpu->id : vcpu->id << 24; + apic_id = *((u32 *)&xapic.regs[APIC_ID]); + + TEST_ASSERT(apic_id == expected, + "APIC_ID not set back to %s format; wanted = %x, got = %x", + (apic_base & X2APIC_ENABLE) ? "x2APIC" : "xAPIC", + expected, apic_id); +} + +/* + * Verify that KVM switches the APIC_ID between xAPIC and x2APIC when userspace + * stuffs MSR_IA32_APICBASE. Setting the APIC_ID when x2APIC is enabled and + * when the APIC transitions for DISABLED to ENABLED is architectural behavior + * (on Intel), whereas the x2APIC => xAPIC transition behavior is KVM ABI since + * attempted to transition from x2APIC to xAPIC without disabling the APIC is + * architecturally disallowed. + */ +static void test_apic_id(void) +{ + const uint32_t NR_VCPUS = 3; + struct kvm_vcpu *vcpus[NR_VCPUS]; + uint64_t apic_base; + struct kvm_vm *vm; + int i; + + vm = vm_create_with_vcpus(NR_VCPUS, NULL, vcpus); + vm_enable_cap(vm, KVM_CAP_X2APIC_API, KVM_X2APIC_API_USE_32BIT_IDS); + + for (i = 0; i < NR_VCPUS; i++) { + apic_base = vcpu_get_msr(vcpus[i], MSR_IA32_APICBASE); + + TEST_ASSERT(apic_base & MSR_IA32_APICBASE_ENABLE, + "APIC not in ENABLED state at vCPU RESET"); + TEST_ASSERT(!(apic_base & X2APIC_ENABLE), + "APIC not in xAPIC mode at vCPU RESET"); + + __test_apic_id(vcpus[i], apic_base); + __test_apic_id(vcpus[i], apic_base | X2APIC_ENABLE); + __test_apic_id(vcpus[i], apic_base); + } + + kvm_vm_free(vm); +} + int main(int argc, char *argv[]) { struct xapic_vcpu x = { @@ -157,4 +210,6 @@ int main(int argc, char *argv[]) virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); test_icr(&x); kvm_vm_free(vm); + + test_apic_id(); } diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index 13c75dc18c10..05898ad9f4d9 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -19,9 +19,6 @@ #include <sys/eventfd.h> -/* Defined in include/linux/kvm_types.h */ -#define GPA_INVALID (~(ulong)0) - #define SHINFO_REGION_GVA 0xc0000000ULL #define SHINFO_REGION_GPA 0xc0000000ULL #define SHINFO_REGION_SLOT 10 @@ -29,6 +26,9 @@ #define DUMMY_REGION_GPA (SHINFO_REGION_GPA + (3 * PAGE_SIZE)) #define DUMMY_REGION_SLOT 11 +#define DUMMY_REGION_GPA_2 (SHINFO_REGION_GPA + (4 * PAGE_SIZE)) +#define DUMMY_REGION_SLOT_2 12 + #define SHINFO_ADDR (SHINFO_REGION_GPA) #define VCPU_INFO_ADDR (SHINFO_REGION_GPA + 0x40) #define PVTIME_ADDR (SHINFO_REGION_GPA + PAGE_SIZE) @@ -44,6 +44,37 @@ #define EVTCHN_TEST2 66 #define EVTCHN_TIMER 13 +enum { + TEST_INJECT_VECTOR = 0, + TEST_RUNSTATE_runnable, + TEST_RUNSTATE_blocked, + TEST_RUNSTATE_offline, + TEST_RUNSTATE_ADJUST, + TEST_RUNSTATE_DATA, + TEST_STEAL_TIME, + TEST_EVTCHN_MASKED, + TEST_EVTCHN_UNMASKED, + TEST_EVTCHN_SLOWPATH, + TEST_EVTCHN_SEND_IOCTL, + TEST_EVTCHN_HCALL, + TEST_EVTCHN_HCALL_SLOWPATH, + TEST_EVTCHN_HCALL_EVENTFD, + TEST_TIMER_SETUP, + TEST_TIMER_WAIT, + TEST_TIMER_RESTORE, + TEST_POLL_READY, + TEST_POLL_TIMEOUT, + TEST_POLL_MASKED, + TEST_POLL_WAKE, + TEST_TIMER_PAST, + TEST_LOCKING_SEND_RACE, + TEST_LOCKING_POLL_RACE, + TEST_LOCKING_POLL_TIMEOUT, + TEST_DONE, + + TEST_GUEST_SAW_IRQ, +}; + #define XEN_HYPERCALL_MSR 0x40000000 #define MIN_STEAL_TIME 50000 @@ -147,7 +178,7 @@ static void evtchn_handler(struct ex_regs *regs) vi->evtchn_pending_sel = 0; guest_saw_irq = true; - GUEST_SYNC(0x20); + GUEST_SYNC(TEST_GUEST_SAW_IRQ); } static void guest_wait_for_irq(void) @@ -168,41 +199,41 @@ static void guest_code(void) ); /* Trigger an interrupt injection */ - GUEST_SYNC(0); + GUEST_SYNC(TEST_INJECT_VECTOR); guest_wait_for_irq(); /* Test having the host set runstates manually */ - GUEST_SYNC(RUNSTATE_runnable); + GUEST_SYNC(TEST_RUNSTATE_runnable); GUEST_ASSERT(rs->time[RUNSTATE_runnable] != 0); GUEST_ASSERT(rs->state == 0); - GUEST_SYNC(RUNSTATE_blocked); + GUEST_SYNC(TEST_RUNSTATE_blocked); GUEST_ASSERT(rs->time[RUNSTATE_blocked] != 0); GUEST_ASSERT(rs->state == 0); - GUEST_SYNC(RUNSTATE_offline); + GUEST_SYNC(TEST_RUNSTATE_offline); GUEST_ASSERT(rs->time[RUNSTATE_offline] != 0); GUEST_ASSERT(rs->state == 0); /* Test runstate time adjust */ - GUEST_SYNC(4); + GUEST_SYNC(TEST_RUNSTATE_ADJUST); GUEST_ASSERT(rs->time[RUNSTATE_blocked] == 0x5a); GUEST_ASSERT(rs->time[RUNSTATE_offline] == 0x6b6b); /* Test runstate time set */ - GUEST_SYNC(5); + GUEST_SYNC(TEST_RUNSTATE_DATA); GUEST_ASSERT(rs->state_entry_time >= 0x8000); GUEST_ASSERT(rs->time[RUNSTATE_runnable] == 0); GUEST_ASSERT(rs->time[RUNSTATE_blocked] == 0x6b6b); GUEST_ASSERT(rs->time[RUNSTATE_offline] == 0x5a); /* sched_yield() should result in some 'runnable' time */ - GUEST_SYNC(6); + GUEST_SYNC(TEST_STEAL_TIME); GUEST_ASSERT(rs->time[RUNSTATE_runnable] >= MIN_STEAL_TIME); /* Attempt to deliver a *masked* interrupt */ - GUEST_SYNC(7); + GUEST_SYNC(TEST_EVTCHN_MASKED); /* Wait until we see the bit set */ struct shared_info *si = (void *)SHINFO_VADDR; @@ -210,71 +241,65 @@ static void guest_code(void) __asm__ __volatile__ ("rep nop" : : : "memory"); /* Now deliver an *unmasked* interrupt */ - GUEST_SYNC(8); + GUEST_SYNC(TEST_EVTCHN_UNMASKED); guest_wait_for_irq(); /* Change memslots and deliver an interrupt */ - GUEST_SYNC(9); + GUEST_SYNC(TEST_EVTCHN_SLOWPATH); guest_wait_for_irq(); /* Deliver event channel with KVM_XEN_HVM_EVTCHN_SEND */ - GUEST_SYNC(10); + GUEST_SYNC(TEST_EVTCHN_SEND_IOCTL); guest_wait_for_irq(); - GUEST_SYNC(11); + GUEST_SYNC(TEST_EVTCHN_HCALL); /* Our turn. Deliver event channel (to ourselves) with * EVTCHNOP_send hypercall. */ - unsigned long rax; struct evtchn_send s = { .port = 127 }; - __asm__ __volatile__ ("vmcall" : - "=a" (rax) : - "a" (__HYPERVISOR_event_channel_op), - "D" (EVTCHNOP_send), - "S" (&s)); + xen_hypercall(__HYPERVISOR_event_channel_op, EVTCHNOP_send, &s); + + guest_wait_for_irq(); + + GUEST_SYNC(TEST_EVTCHN_HCALL_SLOWPATH); - GUEST_ASSERT(rax == 0); + /* + * Same again, but this time the host has messed with memslots so it + * should take the slow path in kvm_xen_set_evtchn(). + */ + xen_hypercall(__HYPERVISOR_event_channel_op, EVTCHNOP_send, &s); guest_wait_for_irq(); - GUEST_SYNC(12); + GUEST_SYNC(TEST_EVTCHN_HCALL_EVENTFD); /* Deliver "outbound" event channel to an eventfd which * happens to be one of our own irqfds. */ s.port = 197; - __asm__ __volatile__ ("vmcall" : - "=a" (rax) : - "a" (__HYPERVISOR_event_channel_op), - "D" (EVTCHNOP_send), - "S" (&s)); - - GUEST_ASSERT(rax == 0); + xen_hypercall(__HYPERVISOR_event_channel_op, EVTCHNOP_send, &s); guest_wait_for_irq(); - GUEST_SYNC(13); + GUEST_SYNC(TEST_TIMER_SETUP); /* Set a timer 100ms in the future. */ - __asm__ __volatile__ ("vmcall" : - "=a" (rax) : - "a" (__HYPERVISOR_set_timer_op), - "D" (rs->state_entry_time + 100000000)); - GUEST_ASSERT(rax == 0); + xen_hypercall(__HYPERVISOR_set_timer_op, + rs->state_entry_time + 100000000, NULL); - GUEST_SYNC(14); + GUEST_SYNC(TEST_TIMER_WAIT); /* Now wait for the timer */ guest_wait_for_irq(); - GUEST_SYNC(15); + GUEST_SYNC(TEST_TIMER_RESTORE); /* The host has 'restored' the timer. Just wait for it. */ guest_wait_for_irq(); - GUEST_SYNC(16); + GUEST_SYNC(TEST_POLL_READY); /* Poll for an event channel port which is already set */ u32 ports[1] = { EVTCHN_TIMER }; @@ -284,65 +309,41 @@ static void guest_code(void) .timeout = 0, }; - __asm__ __volatile__ ("vmcall" : - "=a" (rax) : - "a" (__HYPERVISOR_sched_op), - "D" (SCHEDOP_poll), - "S" (&p)); - - GUEST_ASSERT(rax == 0); + xen_hypercall(__HYPERVISOR_sched_op, SCHEDOP_poll, &p); - GUEST_SYNC(17); + GUEST_SYNC(TEST_POLL_TIMEOUT); /* Poll for an unset port and wait for the timeout. */ p.timeout = 100000000; - __asm__ __volatile__ ("vmcall" : - "=a" (rax) : - "a" (__HYPERVISOR_sched_op), - "D" (SCHEDOP_poll), - "S" (&p)); + xen_hypercall(__HYPERVISOR_sched_op, SCHEDOP_poll, &p); - GUEST_ASSERT(rax == 0); - - GUEST_SYNC(18); + GUEST_SYNC(TEST_POLL_MASKED); /* A timer will wake the masked port we're waiting on, while we poll */ p.timeout = 0; - __asm__ __volatile__ ("vmcall" : - "=a" (rax) : - "a" (__HYPERVISOR_sched_op), - "D" (SCHEDOP_poll), - "S" (&p)); - - GUEST_ASSERT(rax == 0); + xen_hypercall(__HYPERVISOR_sched_op, SCHEDOP_poll, &p); - GUEST_SYNC(19); + GUEST_SYNC(TEST_POLL_WAKE); /* A timer wake an *unmasked* port which should wake us with an * actual interrupt, while we're polling on a different port. */ ports[0]++; p.timeout = 0; - __asm__ __volatile__ ("vmcall" : - "=a" (rax) : - "a" (__HYPERVISOR_sched_op), - "D" (SCHEDOP_poll), - "S" (&p)); - - GUEST_ASSERT(rax == 0); + xen_hypercall(__HYPERVISOR_sched_op, SCHEDOP_poll, &p); guest_wait_for_irq(); - GUEST_SYNC(20); + GUEST_SYNC(TEST_TIMER_PAST); /* Timer should have fired already */ guest_wait_for_irq(); - GUEST_SYNC(21); + GUEST_SYNC(TEST_LOCKING_SEND_RACE); /* Racing host ioctls */ guest_wait_for_irq(); - GUEST_SYNC(22); + GUEST_SYNC(TEST_LOCKING_POLL_RACE); /* Racing vmcall against host ioctl */ ports[0] = 0; @@ -363,24 +364,19 @@ wait_for_timer: * timer IRQ is dropped due to an invalid event channel. */ for (i = 0; i < 100 && !guest_saw_irq; i++) - asm volatile("vmcall" - : "=a" (rax) - : "a" (__HYPERVISOR_sched_op), - "D" (SCHEDOP_poll), - "S" (&p) - : "memory"); + __xen_hypercall(__HYPERVISOR_sched_op, SCHEDOP_poll, &p); /* * Re-send the timer IRQ if it was (likely) dropped due to the timer * expiring while the event channel was invalid. */ if (!guest_saw_irq) { - GUEST_SYNC(23); + GUEST_SYNC(TEST_LOCKING_POLL_TIMEOUT); goto wait_for_timer; } guest_saw_irq = false; - GUEST_SYNC(24); + GUEST_SYNC(TEST_DONE); } static int cmp_timespec(struct timespec *a, struct timespec *b) @@ -412,21 +408,21 @@ static void *juggle_shinfo_state(void *arg) { struct kvm_vm *vm = (struct kvm_vm *)arg; - struct kvm_xen_hvm_attr cache_init = { + struct kvm_xen_hvm_attr cache_activate = { .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, .u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE }; - struct kvm_xen_hvm_attr cache_destroy = { + struct kvm_xen_hvm_attr cache_deactivate = { .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, - .u.shared_info.gfn = GPA_INVALID + .u.shared_info.gfn = KVM_XEN_INVALID_GFN }; for (;;) { - __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_init); - __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_destroy); + __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_activate); + __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_deactivate); pthread_testcancel(); - }; + } return NULL; } @@ -626,15 +622,10 @@ int main(int argc, char *argv[]) bool evtchn_irq_expected = false; for (;;) { - volatile struct kvm_run *run = vcpu->run; struct ucall uc; vcpu_run(vcpu); - - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: @@ -650,25 +641,26 @@ int main(int argc, char *argv[]) "runstate times don't add up"); switch (uc.args[1]) { - case 0: + case TEST_INJECT_VECTOR: if (verbose) printf("Delivering evtchn upcall\n"); evtchn_irq_expected = true; vinfo->evtchn_upcall_pending = 1; break; - case RUNSTATE_runnable...RUNSTATE_offline: + case TEST_RUNSTATE_runnable...TEST_RUNSTATE_offline: TEST_ASSERT(!evtchn_irq_expected, "Event channel IRQ not seen"); if (!do_runstate_tests) goto done; if (verbose) printf("Testing runstate %s\n", runstate_names[uc.args[1]]); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT; - rst.u.runstate.state = uc.args[1]; + rst.u.runstate.state = uc.args[1] + RUNSTATE_runnable - + TEST_RUNSTATE_runnable; vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &rst); break; - case 4: + case TEST_RUNSTATE_ADJUST: if (verbose) printf("Testing RUNSTATE_ADJUST\n"); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST; @@ -683,7 +675,7 @@ int main(int argc, char *argv[]) vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &rst); break; - case 5: + case TEST_RUNSTATE_DATA: if (verbose) printf("Testing RUNSTATE_DATA\n"); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA; @@ -695,7 +687,7 @@ int main(int argc, char *argv[]) vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &rst); break; - case 6: + case TEST_STEAL_TIME: if (verbose) printf("Testing steal time\n"); /* Yield until scheduler delay exceeds target */ @@ -705,7 +697,7 @@ int main(int argc, char *argv[]) } while (get_run_delay() < rundelay); break; - case 7: + case TEST_EVTCHN_MASKED: if (!do_eventfd_tests) goto done; if (verbose) @@ -715,7 +707,7 @@ int main(int argc, char *argv[]) alarm(1); break; - case 8: + case TEST_EVTCHN_UNMASKED: if (verbose) printf("Testing unmasked event channel\n"); /* Unmask that, but deliver the other one */ @@ -726,7 +718,7 @@ int main(int argc, char *argv[]) alarm(1); break; - case 9: + case TEST_EVTCHN_SLOWPATH: TEST_ASSERT(!evtchn_irq_expected, "Expected event channel IRQ but it didn't happen"); shinfo->evtchn_pending[1] = 0; @@ -739,7 +731,7 @@ int main(int argc, char *argv[]) alarm(1); break; - case 10: + case TEST_EVTCHN_SEND_IOCTL: TEST_ASSERT(!evtchn_irq_expected, "Expected event channel IRQ but it didn't happen"); if (!do_evtchn_tests) @@ -759,7 +751,7 @@ int main(int argc, char *argv[]) alarm(1); break; - case 11: + case TEST_EVTCHN_HCALL: TEST_ASSERT(!evtchn_irq_expected, "Expected event channel IRQ but it didn't happen"); shinfo->evtchn_pending[1] = 0; @@ -770,7 +762,20 @@ int main(int argc, char *argv[]) alarm(1); break; - case 12: + case TEST_EVTCHN_HCALL_SLOWPATH: + TEST_ASSERT(!evtchn_irq_expected, + "Expected event channel IRQ but it didn't happen"); + shinfo->evtchn_pending[0] = 0; + + if (verbose) + printf("Testing guest EVTCHNOP_send direct to evtchn after memslot change\n"); + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + DUMMY_REGION_GPA_2, DUMMY_REGION_SLOT_2, 1, 0); + evtchn_irq_expected = true; + alarm(1); + break; + + case TEST_EVTCHN_HCALL_EVENTFD: TEST_ASSERT(!evtchn_irq_expected, "Expected event channel IRQ but it didn't happen"); shinfo->evtchn_pending[0] = 0; @@ -781,7 +786,7 @@ int main(int argc, char *argv[]) alarm(1); break; - case 13: + case TEST_TIMER_SETUP: TEST_ASSERT(!evtchn_irq_expected, "Expected event channel IRQ but it didn't happen"); shinfo->evtchn_pending[1] = 0; @@ -790,7 +795,7 @@ int main(int argc, char *argv[]) printf("Testing guest oneshot timer\n"); break; - case 14: + case TEST_TIMER_WAIT: memset(&tmr, 0, sizeof(tmr)); tmr.type = KVM_XEN_VCPU_ATTR_TYPE_TIMER; vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &tmr); @@ -804,7 +809,7 @@ int main(int argc, char *argv[]) alarm(1); break; - case 15: + case TEST_TIMER_RESTORE: TEST_ASSERT(!evtchn_irq_expected, "Expected event channel IRQ but it didn't happen"); shinfo->evtchn_pending[0] = 0; @@ -818,7 +823,7 @@ int main(int argc, char *argv[]) alarm(1); break; - case 16: + case TEST_POLL_READY: TEST_ASSERT(!evtchn_irq_expected, "Expected event channel IRQ but it didn't happen"); @@ -828,14 +833,14 @@ int main(int argc, char *argv[]) alarm(1); break; - case 17: + case TEST_POLL_TIMEOUT: if (verbose) printf("Testing SCHEDOP_poll timeout\n"); shinfo->evtchn_pending[0] = 0; alarm(1); break; - case 18: + case TEST_POLL_MASKED: if (verbose) printf("Testing SCHEDOP_poll wake on masked event\n"); @@ -844,7 +849,7 @@ int main(int argc, char *argv[]) alarm(1); break; - case 19: + case TEST_POLL_WAKE: shinfo->evtchn_pending[0] = shinfo->evtchn_mask[0] = 0; if (verbose) printf("Testing SCHEDOP_poll wake on unmasked event\n"); @@ -861,7 +866,7 @@ int main(int argc, char *argv[]) alarm(1); break; - case 20: + case TEST_TIMER_PAST: TEST_ASSERT(!evtchn_irq_expected, "Expected event channel IRQ but it didn't happen"); /* Read timer and check it is no longer pending */ @@ -878,7 +883,7 @@ int main(int argc, char *argv[]) alarm(1); break; - case 21: + case TEST_LOCKING_SEND_RACE: TEST_ASSERT(!evtchn_irq_expected, "Expected event channel IRQ but it didn't happen"); alarm(0); @@ -900,7 +905,7 @@ int main(int argc, char *argv[]) __vm_ioctl(vm, KVM_XEN_HVM_EVTCHN_SEND, &uxe); break; - case 22: + case TEST_LOCKING_POLL_RACE: TEST_ASSERT(!evtchn_irq_expected, "Expected event channel IRQ but it didn't happen"); @@ -915,7 +920,7 @@ int main(int argc, char *argv[]) vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); break; - case 23: + case TEST_LOCKING_POLL_TIMEOUT: /* * Optional and possibly repeated sync point. * Injecting the timer IRQ may fail if the @@ -937,7 +942,7 @@ int main(int argc, char *argv[]) SHINFO_RACE_TIMEOUT * 1000000000ULL; vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); break; - case 24: + case TEST_DONE: TEST_ASSERT(!evtchn_irq_expected, "Expected event channel IRQ but it didn't happen"); @@ -948,7 +953,7 @@ int main(int argc, char *argv[]) TEST_ASSERT(ret == 0, "pthread_join() failed: %s", strerror(ret)); goto done; - case 0x20: + case TEST_GUEST_SAW_IRQ: TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ"); evtchn_irq_expected = false; break; diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c index 88914d48c65e..c94cde3b523f 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c @@ -122,10 +122,7 @@ int main(int argc, char *argv[]) continue; } - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index f7900e75d230..05400462c779 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -10,12 +10,14 @@ endif CLANG_TARGET_FLAGS_arm := arm-linux-gnueabi CLANG_TARGET_FLAGS_arm64 := aarch64-linux-gnu CLANG_TARGET_FLAGS_hexagon := hexagon-linux-musl +CLANG_TARGET_FLAGS_i386 := i386-linux-gnu CLANG_TARGET_FLAGS_m68k := m68k-linux-gnu CLANG_TARGET_FLAGS_mips := mipsel-linux-gnu CLANG_TARGET_FLAGS_powerpc := powerpc64le-linux-gnu CLANG_TARGET_FLAGS_riscv := riscv64-linux-gnu CLANG_TARGET_FLAGS_s390 := s390x-linux-gnu CLANG_TARGET_FLAGS_x86 := x86_64-linux-gnu +CLANG_TARGET_FLAGS_x86_64 := x86_64-linux-gnu CLANG_TARGET_FLAGS := $(CLANG_TARGET_FLAGS_$(ARCH)) ifeq ($(CROSS_COMPILE),) diff --git a/tools/testing/selftests/memfd/fuse_test.c b/tools/testing/selftests/memfd/fuse_test.c index be675002f918..93798c8c5d54 100644 --- a/tools/testing/selftests/memfd/fuse_test.c +++ b/tools/testing/selftests/memfd/fuse_test.c @@ -22,6 +22,7 @@ #include <linux/falloc.h> #include <fcntl.h> #include <linux/memfd.h> +#include <linux/types.h> #include <sched.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 94df2692e6e4..ae71f15f790d 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -28,12 +28,46 @@ #define MFD_DEF_SIZE 8192 #define STACK_SIZE 65536 +#define F_SEAL_EXEC 0x0020 + +#define F_WX_SEALS (F_SEAL_SHRINK | \ + F_SEAL_GROW | \ + F_SEAL_WRITE | \ + F_SEAL_FUTURE_WRITE | \ + F_SEAL_EXEC) + +#define MFD_NOEXEC_SEAL 0x0008U + /* * Default is not to test hugetlbfs */ static size_t mfd_def_size = MFD_DEF_SIZE; static const char *memfd_str = MEMFD_STR; +static ssize_t fd2name(int fd, char *buf, size_t bufsize) +{ + char buf1[PATH_MAX]; + int size; + ssize_t nbytes; + + size = snprintf(buf1, PATH_MAX, "/proc/self/fd/%d", fd); + if (size < 0) { + printf("snprintf(%d) failed on %m\n", fd); + abort(); + } + + /* + * reserver one byte for string termination. + */ + nbytes = readlink(buf1, buf, bufsize-1); + if (nbytes == -1) { + printf("readlink(%s) failed %m\n", buf1); + abort(); + } + buf[nbytes] = '\0'; + return nbytes; +} + static int mfd_assert_new(const char *name, loff_t sz, unsigned int flags) { int r, fd; @@ -54,6 +88,37 @@ static int mfd_assert_new(const char *name, loff_t sz, unsigned int flags) return fd; } +static void sysctl_assert_write(const char *val) +{ + int fd = open("/proc/sys/vm/memfd_noexec", O_WRONLY | O_CLOEXEC); + + if (fd < 0) { + printf("open sysctl failed\n"); + abort(); + } + + if (write(fd, val, strlen(val)) < 0) { + printf("write sysctl failed\n"); + abort(); + } +} + +static void sysctl_fail_write(const char *val) +{ + int fd = open("/proc/sys/vm/memfd_noexec", O_WRONLY | O_CLOEXEC); + + if (fd < 0) { + printf("open sysctl failed\n"); + abort(); + } + + if (write(fd, val, strlen(val)) >= 0) { + printf("write sysctl %s succeeded, but failure expected\n", + val); + abort(); + } +} + static int mfd_assert_reopen_fd(int fd_in) { int fd; @@ -98,11 +163,14 @@ static unsigned int mfd_assert_get_seals(int fd) static void mfd_assert_has_seals(int fd, unsigned int seals) { + char buf[PATH_MAX]; + int nbytes; unsigned int s; + fd2name(fd, buf, PATH_MAX); s = mfd_assert_get_seals(fd); if (s != seals) { - printf("%u != %u = GET_SEALS(%d)\n", seals, s, fd); + printf("%u != %u = GET_SEALS(%s)\n", seals, s, buf); abort(); } } @@ -594,6 +662,64 @@ static void mfd_fail_grow_write(int fd) } } +static void mfd_assert_mode(int fd, int mode) +{ + struct stat st; + char buf[PATH_MAX]; + int nbytes; + + fd2name(fd, buf, PATH_MAX); + + if (fstat(fd, &st) < 0) { + printf("fstat(%s) failed: %m\n", buf); + abort(); + } + + if ((st.st_mode & 07777) != mode) { + printf("fstat(%s) wrong file mode 0%04o, but expected 0%04o\n", + buf, (int)st.st_mode & 07777, mode); + abort(); + } +} + +static void mfd_assert_chmod(int fd, int mode) +{ + char buf[PATH_MAX]; + int nbytes; + + fd2name(fd, buf, PATH_MAX); + + if (fchmod(fd, mode) < 0) { + printf("fchmod(%s, 0%04o) failed: %m\n", buf, mode); + abort(); + } + + mfd_assert_mode(fd, mode); +} + +static void mfd_fail_chmod(int fd, int mode) +{ + struct stat st; + char buf[PATH_MAX]; + int nbytes; + + fd2name(fd, buf, PATH_MAX); + + if (fstat(fd, &st) < 0) { + printf("fstat(%s) failed: %m\n", buf); + abort(); + } + + if (fchmod(fd, mode) == 0) { + printf("fchmod(%s, 0%04o) didn't fail as expected\n", + buf, mode); + abort(); + } + + /* verify that file mode bits did not change */ + mfd_assert_mode(fd, st.st_mode & 07777); +} + static int idle_thread_fn(void *arg) { sigset_t set; @@ -671,6 +797,9 @@ static void test_create(void) mfd_fail_new("", ~0); mfd_fail_new("", 0x80000000U); + /* verify EXEC and NOEXEC_SEAL can't both be set */ + mfd_fail_new("", MFD_EXEC | MFD_NOEXEC_SEAL); + /* verify MFD_CLOEXEC is allowed */ fd = mfd_assert_new("", 0, MFD_CLOEXEC); close(fd); @@ -881,6 +1010,211 @@ static void test_seal_resize(void) } /* + * Test SEAL_EXEC + * Test fd is created with exec and allow sealing. + * chmod() cannot change x bits after sealing. + */ +static void test_exec_seal(void) +{ + int fd; + + printf("%s SEAL-EXEC\n", memfd_str); + + printf("%s Apply SEAL_EXEC\n", memfd_str); + fd = mfd_assert_new("kern_memfd_seal_exec", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_EXEC); + + mfd_assert_mode(fd, 0777); + mfd_assert_chmod(fd, 0644); + + mfd_assert_has_seals(fd, 0); + mfd_assert_add_seals(fd, F_SEAL_EXEC); + mfd_assert_has_seals(fd, F_SEAL_EXEC); + + mfd_assert_chmod(fd, 0600); + mfd_fail_chmod(fd, 0777); + mfd_fail_chmod(fd, 0670); + mfd_fail_chmod(fd, 0605); + mfd_fail_chmod(fd, 0700); + mfd_fail_chmod(fd, 0100); + mfd_assert_chmod(fd, 0666); + mfd_assert_write(fd); + close(fd); + + printf("%s Apply ALL_SEALS\n", memfd_str); + fd = mfd_assert_new("kern_memfd_seal_exec", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_EXEC); + + mfd_assert_mode(fd, 0777); + mfd_assert_chmod(fd, 0700); + + mfd_assert_has_seals(fd, 0); + mfd_assert_add_seals(fd, F_SEAL_EXEC); + mfd_assert_has_seals(fd, F_WX_SEALS); + + mfd_fail_chmod(fd, 0711); + mfd_fail_chmod(fd, 0600); + mfd_fail_write(fd); + close(fd); +} + +/* + * Test EXEC_NO_SEAL + * Test fd is created with exec and not allow sealing. + */ +static void test_exec_no_seal(void) +{ + int fd; + + printf("%s EXEC_NO_SEAL\n", memfd_str); + + /* Create with EXEC but without ALLOW_SEALING */ + fd = mfd_assert_new("kern_memfd_exec_no_sealing", + mfd_def_size, + MFD_CLOEXEC | MFD_EXEC); + mfd_assert_mode(fd, 0777); + mfd_assert_has_seals(fd, F_SEAL_SEAL); + mfd_assert_chmod(fd, 0666); + close(fd); +} + +/* + * Test memfd_create with MFD_NOEXEC flag + */ +static void test_noexec_seal(void) +{ + int fd; + + printf("%s NOEXEC_SEAL\n", memfd_str); + + /* Create with NOEXEC and ALLOW_SEALING */ + fd = mfd_assert_new("kern_memfd_noexec", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_NOEXEC_SEAL); + mfd_assert_mode(fd, 0666); + mfd_assert_has_seals(fd, F_SEAL_EXEC); + mfd_fail_chmod(fd, 0777); + close(fd); + + /* Create with NOEXEC but without ALLOW_SEALING */ + fd = mfd_assert_new("kern_memfd_noexec", + mfd_def_size, + MFD_CLOEXEC | MFD_NOEXEC_SEAL); + mfd_assert_mode(fd, 0666); + mfd_assert_has_seals(fd, F_SEAL_EXEC); + mfd_fail_chmod(fd, 0777); + close(fd); +} + +static void test_sysctl_child(void) +{ + int fd; + + printf("%s sysctl 0\n", memfd_str); + sysctl_assert_write("0"); + fd = mfd_assert_new("kern_memfd_sysctl_0", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + mfd_assert_mode(fd, 0777); + mfd_assert_has_seals(fd, 0); + mfd_assert_chmod(fd, 0644); + close(fd); + + printf("%s sysctl 1\n", memfd_str); + sysctl_assert_write("1"); + fd = mfd_assert_new("kern_memfd_sysctl_1", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + mfd_assert_mode(fd, 0666); + mfd_assert_has_seals(fd, F_SEAL_EXEC); + mfd_fail_chmod(fd, 0777); + sysctl_fail_write("0"); + close(fd); + + printf("%s sysctl 2\n", memfd_str); + sysctl_assert_write("2"); + mfd_fail_new("kern_memfd_sysctl_2", + MFD_CLOEXEC | MFD_ALLOW_SEALING); + sysctl_fail_write("0"); + sysctl_fail_write("1"); +} + +static int newpid_thread_fn(void *arg) +{ + test_sysctl_child(); + return 0; +} + +static void test_sysctl_child2(void) +{ + int fd; + + sysctl_fail_write("0"); + fd = mfd_assert_new("kern_memfd_sysctl_1", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + mfd_assert_mode(fd, 0666); + mfd_assert_has_seals(fd, F_SEAL_EXEC); + mfd_fail_chmod(fd, 0777); + close(fd); +} + +static int newpid_thread_fn2(void *arg) +{ + test_sysctl_child2(); + return 0; +} +static pid_t spawn_newpid_thread(unsigned int flags, int (*fn)(void *)) +{ + uint8_t *stack; + pid_t pid; + + stack = malloc(STACK_SIZE); + if (!stack) { + printf("malloc(STACK_SIZE) failed: %m\n"); + abort(); + } + + pid = clone(fn, + stack + STACK_SIZE, + SIGCHLD | flags, + NULL); + if (pid < 0) { + printf("clone() failed: %m\n"); + abort(); + } + + return pid; +} + +static void join_newpid_thread(pid_t pid) +{ + waitpid(pid, NULL, 0); +} + +/* + * Test sysctl + * A very basic sealing test to see whether setting/retrieving seals works. + */ +static void test_sysctl(void) +{ + int pid = spawn_newpid_thread(CLONE_NEWPID, newpid_thread_fn); + + join_newpid_thread(pid); + + printf("%s child ns\n", memfd_str); + sysctl_assert_write("1"); + + pid = spawn_newpid_thread(CLONE_NEWPID, newpid_thread_fn2); + join_newpid_thread(pid); +} + +/* * Test sharing via dup() * Test that seals are shared between dupped FDs and they're all equal. */ @@ -1053,6 +1387,9 @@ int main(int argc, char **argv) test_create(); test_basic(); + test_exec_seal(); + test_exec_no_seal(); + test_noexec_seal(); test_seal_write(); test_seal_future_write(); @@ -1074,6 +1411,8 @@ int main(int argc, char **argv) test_share_fork("SHARE-FORK", SHARED_FT_STR); join_idle_thread(pid); + test_sysctl(); + printf("memfd: DONE\n"); return 0; diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/mm/.gitignore index 1f8c36a9fa10..1f8c36a9fa10 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/mm/Makefile index ac9366065fd2..c31d952cff68 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -1,11 +1,15 @@ # SPDX-License-Identifier: GPL-2.0 -# Makefile for vm selftests +# Makefile for mm selftests -LOCAL_HDRS += $(selfdir)/vm/local_config.h $(top_srcdir)/mm/gup_test.h +LOCAL_HDRS += $(selfdir)/mm/local_config.h $(top_srcdir)/mm/gup_test.h include local_config.mk +ifeq ($(CROSS_COMPILE),) uname_M := $(shell uname -m 2>/dev/null || echo not) +else +uname_M := $(shell echo $(CROSS_COMPILE) | grep -o '^[a-z0-9]\+') +endif MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') # Without this, failed build products remain, with up-to-date timestamps, @@ -56,6 +60,7 @@ TEST_GEN_PROGS += soft-dirty TEST_GEN_PROGS += split_huge_page_test TEST_GEN_FILES += ksm_tests TEST_GEN_PROGS += ksm_functional_tests +TEST_GEN_PROGS += mdwe_test ifeq ($(MACHINE),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_program.c -m32) diff --git a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh index a5cb4b09a46c..a5cb4b09a46c 100644 --- a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh +++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh diff --git a/tools/testing/selftests/vm/check_config.sh b/tools/testing/selftests/mm/check_config.sh index bcba3af0acea..bcba3af0acea 100644 --- a/tools/testing/selftests/vm/check_config.sh +++ b/tools/testing/selftests/mm/check_config.sh diff --git a/tools/testing/selftests/vm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index 9b420140ba2b..9b420140ba2b 100644 --- a/tools/testing/selftests/vm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c diff --git a/tools/testing/selftests/vm/config b/tools/testing/selftests/mm/config index be087c4bc396..be087c4bc396 100644 --- a/tools/testing/selftests/vm/config +++ b/tools/testing/selftests/mm/config diff --git a/tools/testing/selftests/vm/cow.c b/tools/testing/selftests/mm/cow.c index 26f6ea3079e2..0eb2e8180aa5 100644 --- a/tools/testing/selftests/vm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -30,6 +30,13 @@ #include "../kselftest.h" #include "vm_util.h" +#ifndef MADV_PAGEOUT +#define MADV_PAGEOUT 21 +#endif +#ifndef MADV_COLLAPSE +#define MADV_COLLAPSE 25 +#endif + static size_t pagesize; static int pagemap_fd; static size_t thpsize; @@ -1178,6 +1185,228 @@ static int tests_per_anon_test_case(void) return tests; } +enum anon_thp_collapse_test { + ANON_THP_COLLAPSE_UNSHARED, + ANON_THP_COLLAPSE_FULLY_SHARED, + ANON_THP_COLLAPSE_LOWER_SHARED, + ANON_THP_COLLAPSE_UPPER_SHARED, +}; + +static void do_test_anon_thp_collapse(char *mem, size_t size, + enum anon_thp_collapse_test test) +{ + struct comm_pipes comm_pipes; + char buf; + int ret; + + ret = setup_comm_pipes(&comm_pipes); + if (ret) { + ksft_test_result_fail("pipe() failed\n"); + return; + } + + /* + * Trigger PTE-mapping the THP by temporarily mapping a single subpage + * R/O, such that we can try collapsing it later. + */ + ret = mprotect(mem + pagesize, pagesize, PROT_READ); + if (ret) { + ksft_test_result_fail("mprotect() failed\n"); + goto close_comm_pipes; + } + ret = mprotect(mem + pagesize, pagesize, PROT_READ | PROT_WRITE); + if (ret) { + ksft_test_result_fail("mprotect() failed\n"); + goto close_comm_pipes; + } + + switch (test) { + case ANON_THP_COLLAPSE_UNSHARED: + /* Collapse before actually COW-sharing the page. */ + ret = madvise(mem, size, MADV_COLLAPSE); + if (ret) { + ksft_test_result_skip("MADV_COLLAPSE failed: %s\n", + strerror(errno)); + goto close_comm_pipes; + } + break; + case ANON_THP_COLLAPSE_FULLY_SHARED: + /* COW-share the full PTE-mapped THP. */ + break; + case ANON_THP_COLLAPSE_LOWER_SHARED: + /* Don't COW-share the upper part of the THP. */ + ret = madvise(mem + size / 2, size / 2, MADV_DONTFORK); + if (ret) { + ksft_test_result_fail("MADV_DONTFORK failed\n"); + goto close_comm_pipes; + } + break; + case ANON_THP_COLLAPSE_UPPER_SHARED: + /* Don't COW-share the lower part of the THP. */ + ret = madvise(mem, size / 2, MADV_DONTFORK); + if (ret) { + ksft_test_result_fail("MADV_DONTFORK failed\n"); + goto close_comm_pipes; + } + break; + default: + assert(false); + } + + ret = fork(); + if (ret < 0) { + ksft_test_result_fail("fork() failed\n"); + goto close_comm_pipes; + } else if (!ret) { + switch (test) { + case ANON_THP_COLLAPSE_UNSHARED: + case ANON_THP_COLLAPSE_FULLY_SHARED: + exit(child_memcmp_fn(mem, size, &comm_pipes)); + break; + case ANON_THP_COLLAPSE_LOWER_SHARED: + exit(child_memcmp_fn(mem, size / 2, &comm_pipes)); + break; + case ANON_THP_COLLAPSE_UPPER_SHARED: + exit(child_memcmp_fn(mem + size / 2, size / 2, + &comm_pipes)); + break; + default: + assert(false); + } + } + + while (read(comm_pipes.child_ready[0], &buf, 1) != 1) + ; + + switch (test) { + case ANON_THP_COLLAPSE_UNSHARED: + break; + case ANON_THP_COLLAPSE_UPPER_SHARED: + case ANON_THP_COLLAPSE_LOWER_SHARED: + /* + * Revert MADV_DONTFORK such that we merge the VMAs and are + * able to actually collapse. + */ + ret = madvise(mem, size, MADV_DOFORK); + if (ret) { + ksft_test_result_fail("MADV_DOFORK failed\n"); + write(comm_pipes.parent_ready[1], "0", 1); + wait(&ret); + goto close_comm_pipes; + } + /* FALLTHROUGH */ + case ANON_THP_COLLAPSE_FULLY_SHARED: + /* Collapse before anyone modified the COW-shared page. */ + ret = madvise(mem, size, MADV_COLLAPSE); + if (ret) { + ksft_test_result_skip("MADV_COLLAPSE failed: %s\n", + strerror(errno)); + write(comm_pipes.parent_ready[1], "0", 1); + wait(&ret); + goto close_comm_pipes; + } + break; + default: + assert(false); + } + + /* Modify the page. */ + memset(mem, 0xff, size); + write(comm_pipes.parent_ready[1], "0", 1); + + wait(&ret); + if (WIFEXITED(ret)) + ret = WEXITSTATUS(ret); + else + ret = -EINVAL; + + ksft_test_result(!ret, "No leak from parent into child\n"); +close_comm_pipes: + close_comm_pipes(&comm_pipes); +} + +static void test_anon_thp_collapse_unshared(char *mem, size_t size) +{ + do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_UNSHARED); +} + +static void test_anon_thp_collapse_fully_shared(char *mem, size_t size) +{ + do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_FULLY_SHARED); +} + +static void test_anon_thp_collapse_lower_shared(char *mem, size_t size) +{ + do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_LOWER_SHARED); +} + +static void test_anon_thp_collapse_upper_shared(char *mem, size_t size) +{ + do_test_anon_thp_collapse(mem, size, ANON_THP_COLLAPSE_UPPER_SHARED); +} + +/* + * Test cases that are specific to anonymous THP: pages in private mappings + * that may get shared via COW during fork(). + */ +static const struct test_case anon_thp_test_cases[] = { + /* + * Basic COW test for fork() without any GUP when collapsing a THP + * before fork(). + * + * Re-mapping a PTE-mapped anon THP using a single PMD ("in-place + * collapse") might easily get COW handling wrong when not collapsing + * exclusivity information properly. + */ + { + "Basic COW after fork() when collapsing before fork()", + test_anon_thp_collapse_unshared, + }, + /* Basic COW test, but collapse after COW-sharing a full THP. */ + { + "Basic COW after fork() when collapsing after fork() (fully shared)", + test_anon_thp_collapse_fully_shared, + }, + /* + * Basic COW test, but collapse after COW-sharing the lower half of a + * THP. + */ + { + "Basic COW after fork() when collapsing after fork() (lower shared)", + test_anon_thp_collapse_lower_shared, + }, + /* + * Basic COW test, but collapse after COW-sharing the upper half of a + * THP. + */ + { + "Basic COW after fork() when collapsing after fork() (upper shared)", + test_anon_thp_collapse_upper_shared, + }, +}; + +static void run_anon_thp_test_cases(void) +{ + int i; + + if (!thpsize) + return; + + ksft_print_msg("[INFO] Anonymous THP tests\n"); + + for (i = 0; i < ARRAY_SIZE(anon_thp_test_cases); i++) { + struct test_case const *test_case = &anon_thp_test_cases[i]; + + ksft_print_msg("[RUN] %s\n", test_case->desc); + do_run_with_thp(test_case->fn, THP_RUN_PMD); + } +} + +static int tests_per_anon_thp_test_case(void) +{ + return thpsize ? 1 : 0; +} + typedef void (*non_anon_test_fn)(char *mem, const char *smem, size_t size); static void test_cow(char *mem, const char *smem, size_t size) @@ -1518,6 +1747,7 @@ int main(int argc, char **argv) ksft_print_header(); ksft_set_plan(ARRAY_SIZE(anon_test_cases) * tests_per_anon_test_case() + + ARRAY_SIZE(anon_thp_test_cases) * tests_per_anon_thp_test_case() + ARRAY_SIZE(non_anon_test_cases) * tests_per_non_anon_test_case()); gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); @@ -1526,6 +1756,7 @@ int main(int argc, char **argv) ksft_exit_fail_msg("opening pagemap failed\n"); run_anon_test_cases(); + run_anon_thp_test_cases(); run_non_anon_test_cases(); err = ksft_get_fail_cnt(); diff --git a/tools/testing/selftests/vm/gup_test.c b/tools/testing/selftests/mm/gup_test.c index e43879291dac..e43879291dac 100644 --- a/tools/testing/selftests/vm/gup_test.c +++ b/tools/testing/selftests/mm/gup_test.c diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/mm/hmm-tests.c index 4adaad1b822f..4adaad1b822f 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/mm/hmm-tests.c diff --git a/tools/testing/selftests/vm/hugepage-mmap.c b/tools/testing/selftests/mm/hugepage-mmap.c index 955ef87f382c..955ef87f382c 100644 --- a/tools/testing/selftests/vm/hugepage-mmap.c +++ b/tools/testing/selftests/mm/hugepage-mmap.c diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/mm/hugepage-mremap.c index e53b5eaa8fce..e53b5eaa8fce 100644 --- a/tools/testing/selftests/vm/hugepage-mremap.c +++ b/tools/testing/selftests/mm/hugepage-mremap.c diff --git a/tools/testing/selftests/vm/hugepage-shm.c b/tools/testing/selftests/mm/hugepage-shm.c index e2527f32005b..e2527f32005b 100644 --- a/tools/testing/selftests/vm/hugepage-shm.c +++ b/tools/testing/selftests/mm/hugepage-shm.c diff --git a/tools/testing/selftests/vm/hugepage-vmemmap.c b/tools/testing/selftests/mm/hugepage-vmemmap.c index 557bdbd4f87e..557bdbd4f87e 100644 --- a/tools/testing/selftests/vm/hugepage-vmemmap.c +++ b/tools/testing/selftests/mm/hugepage-vmemmap.c diff --git a/tools/testing/selftests/vm/hugetlb-madvise.c b/tools/testing/selftests/mm/hugetlb-madvise.c index 9a127a8fe176..9a127a8fe176 100644 --- a/tools/testing/selftests/vm/hugetlb-madvise.c +++ b/tools/testing/selftests/mm/hugetlb-madvise.c diff --git a/tools/testing/selftests/vm/hugetlb_reparenting_test.sh b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh index bf2d2a684edf..bf2d2a684edf 100644 --- a/tools/testing/selftests/vm/hugetlb_reparenting_test.sh +++ b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c index 64126c8cd561..64126c8cd561 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/mm/khugepaged.c diff --git a/tools/testing/selftests/vm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index b11b7e5115dc..d8b5b4930412 100644 --- a/tools/testing/selftests/vm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -37,7 +37,7 @@ static bool range_maps_duplicates(char *addr, unsigned long size) /* * There is no easy way to check if there are KSM pages mapped into * this range. We only check that the range does not map the same PFN - * twice by comaring each pair of mapped pages. + * twice by comparing each pair of mapped pages. */ for (offs_a = 0; offs_a < size; offs_a += pagesize) { pfn_a = pagemap_get_pfn(pagemap_fd, addr + offs_a); diff --git a/tools/testing/selftests/vm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index f9eb4d67e0dd..f9eb4d67e0dd 100644 --- a/tools/testing/selftests/vm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c diff --git a/tools/testing/selftests/vm/madv_populate.c b/tools/testing/selftests/mm/madv_populate.c index 262eae6b58f2..262eae6b58f2 100644 --- a/tools/testing/selftests/vm/madv_populate.c +++ b/tools/testing/selftests/mm/madv_populate.c diff --git a/tools/testing/selftests/vm/map_fixed_noreplace.c b/tools/testing/selftests/mm/map_fixed_noreplace.c index eed44322d1a6..eed44322d1a6 100644 --- a/tools/testing/selftests/vm/map_fixed_noreplace.c +++ b/tools/testing/selftests/mm/map_fixed_noreplace.c diff --git a/tools/testing/selftests/vm/map_hugetlb.c b/tools/testing/selftests/mm/map_hugetlb.c index 312889edb84a..312889edb84a 100644 --- a/tools/testing/selftests/vm/map_hugetlb.c +++ b/tools/testing/selftests/mm/map_hugetlb.c diff --git a/tools/testing/selftests/vm/map_populate.c b/tools/testing/selftests/mm/map_populate.c index 6b8aeaa0bf7a..6b8aeaa0bf7a 100644 --- a/tools/testing/selftests/vm/map_populate.c +++ b/tools/testing/selftests/mm/map_populate.c diff --git a/tools/testing/selftests/mm/mdwe_test.c b/tools/testing/selftests/mm/mdwe_test.c new file mode 100644 index 000000000000..bc91bef5d254 --- /dev/null +++ b/tools/testing/selftests/mm/mdwe_test.c @@ -0,0 +1,196 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifdef __aarch64__ +#include <asm/hwcap.h> +#endif + +#include <linux/mman.h> +#include <linux/prctl.h> + +#include <stdio.h> +#include <stdlib.h> +#include <sys/auxv.h> +#include <sys/prctl.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "../kselftest_harness.h" + +#ifndef __aarch64__ +# define PROT_BTI 0 +#endif + +TEST(prctl_flags) +{ + EXPECT_LT(prctl(PR_SET_MDWE, 7L, 0L, 0L, 0L), 0); + EXPECT_LT(prctl(PR_SET_MDWE, 0L, 7L, 0L, 0L), 0); + EXPECT_LT(prctl(PR_SET_MDWE, 0L, 0L, 7L, 0L), 0); + EXPECT_LT(prctl(PR_SET_MDWE, 0L, 0L, 0L, 7L), 0); + + EXPECT_LT(prctl(PR_GET_MDWE, 7L, 0L, 0L, 0L), 0); + EXPECT_LT(prctl(PR_GET_MDWE, 0L, 7L, 0L, 0L), 0); + EXPECT_LT(prctl(PR_GET_MDWE, 0L, 0L, 7L, 0L), 0); + EXPECT_LT(prctl(PR_GET_MDWE, 0L, 0L, 0L, 7L), 0); +} + +FIXTURE(mdwe) +{ + void *p; + int flags; + size_t size; + pid_t pid; +}; + +FIXTURE_VARIANT(mdwe) +{ + bool enabled; + bool forked; +}; + +FIXTURE_VARIANT_ADD(mdwe, stock) +{ + .enabled = false, + .forked = false, +}; + +FIXTURE_VARIANT_ADD(mdwe, enabled) +{ + .enabled = true, + .forked = false, +}; + +FIXTURE_VARIANT_ADD(mdwe, forked) +{ + .enabled = true, + .forked = true, +}; + +FIXTURE_SETUP(mdwe) +{ + int ret, status; + + self->p = NULL; + self->flags = MAP_SHARED | MAP_ANONYMOUS; + self->size = getpagesize(); + + if (!variant->enabled) + return; + + ret = prctl(PR_SET_MDWE, PR_MDWE_REFUSE_EXEC_GAIN, 0L, 0L, 0L); + ASSERT_EQ(ret, 0) { + TH_LOG("PR_SET_MDWE failed or unsupported"); + } + + ret = prctl(PR_GET_MDWE, 0L, 0L, 0L, 0L); + ASSERT_EQ(ret, 1); + + if (variant->forked) { + self->pid = fork(); + ASSERT_GE(self->pid, 0) { + TH_LOG("fork failed\n"); + } + + if (self->pid > 0) { + ret = waitpid(self->pid, &status, 0); + ASSERT_TRUE(WIFEXITED(status)); + exit(WEXITSTATUS(status)); + } + } +} + +FIXTURE_TEARDOWN(mdwe) +{ + if (self->p && self->p != MAP_FAILED) + munmap(self->p, self->size); +} + +TEST_F(mdwe, mmap_READ_EXEC) +{ + self->p = mmap(NULL, self->size, PROT_READ | PROT_EXEC, self->flags, 0, 0); + EXPECT_NE(self->p, MAP_FAILED); +} + +TEST_F(mdwe, mmap_WRITE_EXEC) +{ + self->p = mmap(NULL, self->size, PROT_WRITE | PROT_EXEC, self->flags, 0, 0); + if (variant->enabled) { + EXPECT_EQ(self->p, MAP_FAILED); + } else { + EXPECT_NE(self->p, MAP_FAILED); + } +} + +TEST_F(mdwe, mprotect_stay_EXEC) +{ + int ret; + + self->p = mmap(NULL, self->size, PROT_READ | PROT_EXEC, self->flags, 0, 0); + ASSERT_NE(self->p, MAP_FAILED); + + ret = mprotect(self->p, self->size, PROT_READ | PROT_EXEC); + EXPECT_EQ(ret, 0); +} + +TEST_F(mdwe, mprotect_add_EXEC) +{ + int ret; + + self->p = mmap(NULL, self->size, PROT_READ, self->flags, 0, 0); + ASSERT_NE(self->p, MAP_FAILED); + + ret = mprotect(self->p, self->size, PROT_READ | PROT_EXEC); + if (variant->enabled) { + EXPECT_LT(ret, 0); + } else { + EXPECT_EQ(ret, 0); + } +} + +TEST_F(mdwe, mprotect_WRITE_EXEC) +{ + int ret; + + self->p = mmap(NULL, self->size, PROT_WRITE, self->flags, 0, 0); + ASSERT_NE(self->p, MAP_FAILED); + + ret = mprotect(self->p, self->size, PROT_WRITE | PROT_EXEC); + if (variant->enabled) { + EXPECT_LT(ret, 0); + } else { + EXPECT_EQ(ret, 0); + } +} + +TEST_F(mdwe, mmap_FIXED) +{ + void *p; + + self->p = mmap(NULL, self->size, PROT_READ, self->flags, 0, 0); + ASSERT_NE(self->p, MAP_FAILED); + + p = mmap(self->p + self->size, self->size, PROT_READ | PROT_EXEC, + self->flags | MAP_FIXED, 0, 0); + if (variant->enabled) { + EXPECT_EQ(p, MAP_FAILED); + } else { + EXPECT_EQ(p, self->p); + } +} + +TEST_F(mdwe, arm64_BTI) +{ + int ret; + +#ifdef __aarch64__ + if (!(getauxval(AT_HWCAP2) & HWCAP2_BTI)) +#endif + SKIP(return, "HWCAP2_BTI not supported"); + + self->p = mmap(NULL, self->size, PROT_EXEC, self->flags, 0, 0); + ASSERT_NE(self->p, MAP_FAILED); + + ret = mprotect(self->p, self->size, PROT_EXEC | PROT_BTI); + EXPECT_EQ(ret, 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/vm/memfd_secret.c b/tools/testing/selftests/mm/memfd_secret.c index 957b9e18c729..957b9e18c729 100644 --- a/tools/testing/selftests/vm/memfd_secret.c +++ b/tools/testing/selftests/mm/memfd_secret.c diff --git a/tools/testing/selftests/vm/migration.c b/tools/testing/selftests/mm/migration.c index 1cec8425e3ca..1cec8425e3ca 100644 --- a/tools/testing/selftests/vm/migration.c +++ b/tools/testing/selftests/mm/migration.c diff --git a/tools/testing/selftests/vm/mlock-random-test.c b/tools/testing/selftests/mm/mlock-random-test.c index 782ea94dee2f..782ea94dee2f 100644 --- a/tools/testing/selftests/vm/mlock-random-test.c +++ b/tools/testing/selftests/mm/mlock-random-test.c diff --git a/tools/testing/selftests/vm/mlock2-tests.c b/tools/testing/selftests/mm/mlock2-tests.c index 11b2301f3aa3..11b2301f3aa3 100644 --- a/tools/testing/selftests/vm/mlock2-tests.c +++ b/tools/testing/selftests/mm/mlock2-tests.c diff --git a/tools/testing/selftests/vm/mlock2.h b/tools/testing/selftests/mm/mlock2.h index 2a6e76c226bc..2a6e76c226bc 100644 --- a/tools/testing/selftests/vm/mlock2.h +++ b/tools/testing/selftests/mm/mlock2.h diff --git a/tools/testing/selftests/vm/mrelease_test.c b/tools/testing/selftests/mm/mrelease_test.c index 6c62966ab5db..6c62966ab5db 100644 --- a/tools/testing/selftests/vm/mrelease_test.c +++ b/tools/testing/selftests/mm/mrelease_test.c diff --git a/tools/testing/selftests/vm/mremap_dontunmap.c b/tools/testing/selftests/mm/mremap_dontunmap.c index f01dc4a85b0b..f01dc4a85b0b 100644 --- a/tools/testing/selftests/vm/mremap_dontunmap.c +++ b/tools/testing/selftests/mm/mremap_dontunmap.c diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index 9496346973d4..5c3773de9f0f 100644 --- a/tools/testing/selftests/vm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -119,47 +119,109 @@ static unsigned long long get_mmap_min_addr(void) } /* - * This test validates that merge is called when expanding a mapping. - * Mapping containing three pages is created, middle page is unmapped - * and then the mapping containing the first page is expanded so that - * it fills the created hole. The two parts should merge creating - * single mapping with three pages. + * Using /proc/self/maps, assert that the specified address range is contained + * within a single mapping. */ -static void mremap_expand_merge(unsigned long page_size) +static bool is_range_mapped(FILE *maps_fp, void *start, void *end) { - char *test_name = "mremap expand merge"; - FILE *fp; char *line = NULL; size_t len = 0; bool success = false; - char *start = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); - - munmap(start + page_size, page_size); - mremap(start, page_size, 2 * page_size, 0); - fp = fopen("/proc/self/maps", "r"); - if (fp == NULL) { - ksft_test_result_fail("%s\n", test_name); - return; - } + rewind(maps_fp); - while (getline(&line, &len, fp) != -1) { + while (getline(&line, &len, maps_fp) != -1) { char *first = strtok(line, "- "); void *first_val = (void *)strtol(first, NULL, 16); char *second = strtok(NULL, "- "); void *second_val = (void *) strtol(second, NULL, 16); - if (first_val == start && second_val == start + 3 * page_size) { + if (first_val <= start && second_val >= end) { success = true; break; } } + + return success; +} + +/* + * This test validates that merge is called when expanding a mapping. + * Mapping containing three pages is created, middle page is unmapped + * and then the mapping containing the first page is expanded so that + * it fills the created hole. The two parts should merge creating + * single mapping with three pages. + */ +static void mremap_expand_merge(FILE *maps_fp, unsigned long page_size) +{ + char *test_name = "mremap expand merge"; + bool success = false; + char *remap, *start; + + start = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + + if (start == MAP_FAILED) { + ksft_print_msg("mmap failed: %s\n", strerror(errno)); + goto out; + } + + munmap(start + page_size, page_size); + remap = mremap(start, page_size, 2 * page_size, 0); + if (remap == MAP_FAILED) { + ksft_print_msg("mremap failed: %s\n", strerror(errno)); + munmap(start, page_size); + munmap(start + 2 * page_size, page_size); + goto out; + } + + success = is_range_mapped(maps_fp, start, start + 3 * page_size); + munmap(start, 3 * page_size); + +out: + if (success) + ksft_test_result_pass("%s\n", test_name); + else + ksft_test_result_fail("%s\n", test_name); +} + +/* + * Similar to mremap_expand_merge() except instead of removing the middle page, + * we remove the last then attempt to remap offset from the second page. This + * should result in the mapping being restored to its former state. + */ +static void mremap_expand_merge_offset(FILE *maps_fp, unsigned long page_size) +{ + + char *test_name = "mremap expand merge offset"; + bool success = false; + char *remap, *start; + + start = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + + if (start == MAP_FAILED) { + ksft_print_msg("mmap failed: %s\n", strerror(errno)); + goto out; + } + + /* Unmap final page to ensure we have space to expand. */ + munmap(start + 2 * page_size, page_size); + remap = mremap(start + page_size, page_size, 2 * page_size, 0); + if (remap == MAP_FAILED) { + ksft_print_msg("mremap failed: %s\n", strerror(errno)); + munmap(start, 2 * page_size); + goto out; + } + + success = is_range_mapped(maps_fp, start, start + 3 * page_size); + munmap(start, 3 * page_size); + +out: if (success) ksft_test_result_pass("%s\n", test_name); else ksft_test_result_fail("%s\n", test_name); - fclose(fp); } /* @@ -380,11 +442,12 @@ int main(int argc, char **argv) int i, run_perf_tests; unsigned int threshold_mb = VALIDATION_DEFAULT_THRESHOLD; unsigned int pattern_seed; - int num_expand_tests = 1; + int num_expand_tests = 2; struct test test_cases[MAX_TEST]; struct test perf_test_cases[MAX_PERF_TEST]; int page_size; time_t t; + FILE *maps_fp; pattern_seed = (unsigned int) time(&t); @@ -458,7 +521,17 @@ int main(int argc, char **argv) run_mremap_test_case(test_cases[i], &failures, threshold_mb, pattern_seed); - mremap_expand_merge(page_size); + maps_fp = fopen("/proc/self/maps", "r"); + + if (maps_fp == NULL) { + ksft_print_msg("Failed to read /proc/self/maps: %s\n", strerror(errno)); + exit(KSFT_FAIL); + } + + mremap_expand_merge(maps_fp, page_size); + mremap_expand_merge_offset(maps_fp, page_size); + + fclose(maps_fp); if (run_perf_tests) { ksft_print_msg("\n%s\n", diff --git a/tools/testing/selftests/vm/on-fault-limit.c b/tools/testing/selftests/mm/on-fault-limit.c index 634d87dfb2a4..634d87dfb2a4 100644 --- a/tools/testing/selftests/vm/on-fault-limit.c +++ b/tools/testing/selftests/mm/on-fault-limit.c diff --git a/tools/testing/selftests/vm/pkey-helpers.h b/tools/testing/selftests/mm/pkey-helpers.h index 92f3be3dd8e5..92f3be3dd8e5 100644 --- a/tools/testing/selftests/vm/pkey-helpers.h +++ b/tools/testing/selftests/mm/pkey-helpers.h diff --git a/tools/testing/selftests/vm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h index 1ebb586b2fbc..1ebb586b2fbc 100644 --- a/tools/testing/selftests/vm/pkey-powerpc.h +++ b/tools/testing/selftests/mm/pkey-powerpc.h diff --git a/tools/testing/selftests/vm/pkey-x86.h b/tools/testing/selftests/mm/pkey-x86.h index 72c14cd3ddc7..72c14cd3ddc7 100644 --- a/tools/testing/selftests/vm/pkey-x86.h +++ b/tools/testing/selftests/mm/pkey-x86.h diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index 95f403a0c46d..95f403a0c46d 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/mm/protection_keys.c diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 8984e0bb58c7..8984e0bb58c7 100755..100644 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh diff --git a/tools/testing/selftests/vm/settings b/tools/testing/selftests/mm/settings index 9abfc60e9e6f..9abfc60e9e6f 100644 --- a/tools/testing/selftests/vm/settings +++ b/tools/testing/selftests/mm/settings diff --git a/tools/testing/selftests/vm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c index 21d8830c5f24..21d8830c5f24 100644 --- a/tools/testing/selftests/vm/soft-dirty.c +++ b/tools/testing/selftests/mm/soft-dirty.c diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 76e1c36dd9e5..76e1c36dd9e5 100644 --- a/tools/testing/selftests/vm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c diff --git a/tools/testing/selftests/vm/test_hmm.sh b/tools/testing/selftests/mm/test_hmm.sh index 46e19b5d648d..46e19b5d648d 100755..100644 --- a/tools/testing/selftests/vm/test_hmm.sh +++ b/tools/testing/selftests/mm/test_hmm.sh diff --git a/tools/testing/selftests/vm/test_vmalloc.sh b/tools/testing/selftests/mm/test_vmalloc.sh index d73b846736f1..d73b846736f1 100755..100644 --- a/tools/testing/selftests/vm/test_vmalloc.sh +++ b/tools/testing/selftests/mm/test_vmalloc.sh diff --git a/tools/testing/selftests/vm/thuge-gen.c b/tools/testing/selftests/mm/thuge-gen.c index 361ef7192cc6..361ef7192cc6 100644 --- a/tools/testing/selftests/vm/thuge-gen.c +++ b/tools/testing/selftests/mm/thuge-gen.c diff --git a/tools/testing/selftests/vm/transhuge-stress.c b/tools/testing/selftests/mm/transhuge-stress.c index e3f00adb1b82..e3f00adb1b82 100644 --- a/tools/testing/selftests/vm/transhuge-stress.c +++ b/tools/testing/selftests/mm/transhuge-stress.c diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/mm/userfaultfd.c index 7f22844ed704..7f22844ed704 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/mm/userfaultfd.c diff --git a/tools/testing/selftests/vm/util.h b/tools/testing/selftests/mm/util.h index b27d26199334..b27d26199334 100644 --- a/tools/testing/selftests/vm/util.h +++ b/tools/testing/selftests/mm/util.h diff --git a/tools/testing/selftests/vm/va_128TBswitch.c b/tools/testing/selftests/mm/va_128TBswitch.c index 1d2068989883..1d2068989883 100644 --- a/tools/testing/selftests/vm/va_128TBswitch.c +++ b/tools/testing/selftests/mm/va_128TBswitch.c diff --git a/tools/testing/selftests/vm/va_128TBswitch.sh b/tools/testing/selftests/mm/va_128TBswitch.sh index 41580751dc51..41580751dc51 100755..100644 --- a/tools/testing/selftests/vm/va_128TBswitch.sh +++ b/tools/testing/selftests/mm/va_128TBswitch.sh diff --git a/tools/testing/selftests/vm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index c0592646ed93..c0592646ed93 100644 --- a/tools/testing/selftests/vm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c diff --git a/tools/testing/selftests/vm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 40e795624ff3..40e795624ff3 100644 --- a/tools/testing/selftests/vm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c diff --git a/tools/testing/selftests/vm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index 1995ee911ef2..1995ee911ef2 100644 --- a/tools/testing/selftests/vm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h diff --git a/tools/testing/selftests/vm/write_hugetlb_memory.sh b/tools/testing/selftests/mm/write_hugetlb_memory.sh index 70a02301f4c2..70a02301f4c2 100644 --- a/tools/testing/selftests/vm/write_hugetlb_memory.sh +++ b/tools/testing/selftests/mm/write_hugetlb_memory.sh diff --git a/tools/testing/selftests/vm/write_to_hugetlbfs.c b/tools/testing/selftests/mm/write_to_hugetlbfs.c index 6a2caba19ee1..6a2caba19ee1 100644 --- a/tools/testing/selftests/vm/write_to_hugetlbfs.c +++ b/tools/testing/selftests/mm/write_to_hugetlbfs.c diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index 582669ca38e9..c6a8c732b802 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -18,6 +18,7 @@ #include <grp.h> #include <stdbool.h> #include <stdarg.h> +#include <linux/mount.h> #include "../kselftest_harness.h" diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index a6911cae368c..80f06aa62034 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only bind_bhash bind_timewait +bind_wildcard csum cmsg_sender diag_uid diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 6cd8993454d7..80fbfe0330f6 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -80,6 +80,7 @@ TEST_GEN_FILES += sctp_hello TEST_GEN_FILES += csum TEST_GEN_FILES += nat6to4.o TEST_GEN_FILES += ip_local_port_range +TEST_GEN_FILES += bind_wildcard TEST_FILES := settings diff --git a/tools/testing/selftests/net/bind_wildcard.c b/tools/testing/selftests/net/bind_wildcard.c new file mode 100644 index 000000000000..58edfc15d28b --- /dev/null +++ b/tools/testing/selftests/net/bind_wildcard.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ + +#include <sys/socket.h> +#include <netinet/in.h> + +#include "../kselftest_harness.h" + +FIXTURE(bind_wildcard) +{ + struct sockaddr_in addr4; + struct sockaddr_in6 addr6; + int expected_errno; +}; + +FIXTURE_VARIANT(bind_wildcard) +{ + const __u32 addr4_const; + const struct in6_addr *addr6_const; +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v4_any_v6_any) +{ + .addr4_const = INADDR_ANY, + .addr6_const = &in6addr_any, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v4_any_v6_local) +{ + .addr4_const = INADDR_ANY, + .addr6_const = &in6addr_loopback, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v4_local_v6_any) +{ + .addr4_const = INADDR_LOOPBACK, + .addr6_const = &in6addr_any, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v4_local_v6_local) +{ + .addr4_const = INADDR_LOOPBACK, + .addr6_const = &in6addr_loopback, +}; + +FIXTURE_SETUP(bind_wildcard) +{ + self->addr4.sin_family = AF_INET; + self->addr4.sin_port = htons(0); + self->addr4.sin_addr.s_addr = htonl(variant->addr4_const); + + self->addr6.sin6_family = AF_INET6; + self->addr6.sin6_port = htons(0); + self->addr6.sin6_addr = *variant->addr6_const; + + if (variant->addr6_const == &in6addr_any) + self->expected_errno = EADDRINUSE; + else + self->expected_errno = 0; +} + +FIXTURE_TEARDOWN(bind_wildcard) +{ +} + +void bind_sockets(struct __test_metadata *_metadata, + FIXTURE_DATA(bind_wildcard) *self, + struct sockaddr *addr1, socklen_t addrlen1, + struct sockaddr *addr2, socklen_t addrlen2) +{ + int fd[2]; + int ret; + + fd[0] = socket(addr1->sa_family, SOCK_STREAM, 0); + ASSERT_GT(fd[0], 0); + + ret = bind(fd[0], addr1, addrlen1); + ASSERT_EQ(ret, 0); + + ret = getsockname(fd[0], addr1, &addrlen1); + ASSERT_EQ(ret, 0); + + ((struct sockaddr_in *)addr2)->sin_port = ((struct sockaddr_in *)addr1)->sin_port; + + fd[1] = socket(addr2->sa_family, SOCK_STREAM, 0); + ASSERT_GT(fd[1], 0); + + ret = bind(fd[1], addr2, addrlen2); + if (self->expected_errno) { + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, self->expected_errno); + } else { + ASSERT_EQ(ret, 0); + } + + close(fd[1]); + close(fd[0]); +} + +TEST_F(bind_wildcard, v4_v6) +{ + bind_sockets(_metadata, self, + (struct sockaddr *)&self->addr4, sizeof(self->addr6), + (struct sockaddr *)&self->addr6, sizeof(self->addr6)); +} + +TEST_F(bind_wildcard, v6_v4) +{ + bind_sockets(_metadata, self, + (struct sockaddr *)&self->addr6, sizeof(self->addr6), + (struct sockaddr *)&self->addr4, sizeof(self->addr4)); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index cc9fd55ab869..2529226ce87c 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -48,3 +48,4 @@ CONFIG_BAREUDP=m CONFIG_IPV6_IOAM6_LWTUNNEL=y CONFIG_CRYPTO_SM4_GENERIC=y CONFIG_AMT=m +CONFIG_IP_SCTP=m diff --git a/tools/testing/selftests/net/devlink_port_split.py b/tools/testing/selftests/net/devlink_port_split.py index 2b5d6ff87373..2d84c7a0be6b 100755 --- a/tools/testing/selftests/net/devlink_port_split.py +++ b/tools/testing/selftests/net/devlink_port_split.py @@ -59,6 +59,8 @@ class devlink_ports(object): assert stderr == "" ports = json.loads(stdout)['port'] + validate_devlink_output(ports, 'flavour') + for port in ports: if dev in port: if ports[port]['flavour'] == 'physical': @@ -220,6 +222,27 @@ def split_splittable_port(port, k, lanes, dev): unsplit(port.bus_info) +def validate_devlink_output(devlink_data, target_property=None): + """ + Determine if test should be skipped by checking: + 1. devlink_data contains values + 2. The target_property exist in devlink_data + """ + skip_reason = None + if any(devlink_data.values()): + if target_property: + skip_reason = "{} not found in devlink output, test skipped".format(target_property) + for key in devlink_data: + if target_property in devlink_data[key]: + skip_reason = None + else: + skip_reason = 'devlink output is empty, test skipped' + + if skip_reason: + print(skip_reason) + sys.exit(KSFT_SKIP) + + def make_parser(): parser = argparse.ArgumentParser(description='A test for port splitting.') parser.add_argument('--dev', @@ -240,12 +263,9 @@ def main(cmdline=None): stdout, stderr = run_command(cmd) assert stderr == "" + validate_devlink_output(json.loads(stdout)) devs = json.loads(stdout)['dev'] - if devs: - dev = list(devs.keys())[0] - else: - print("no devlink device was found, test skipped") - sys.exit(KSFT_SKIP) + dev = list(devs.keys())[0] cmd = "devlink dev show %s" % dev stdout, stderr = run_command(cmd) @@ -255,6 +275,7 @@ def main(cmdline=None): ports = devlink_ports(dev) + found_max_lanes = False for port in ports.if_names: max_lanes = get_max_lanes(port.name) @@ -277,6 +298,11 @@ def main(cmdline=None): split_splittable_port(port, lane, max_lanes, dev) lane //= 2 + found_max_lanes = True + + if not found_max_lanes: + print(f"Test not started, no port of device {dev} reports max_lanes") + sys.exit(KSFT_SKIP) if __name__ == "__main__": diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 70ea8798b1f6..7da8ec838c63 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -9,7 +9,7 @@ ret=0 ksft_skip=4 # all tests in this script. Can be overridden with -t option -TESTS="unregister down carrier nexthop suppress ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh" +TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh" VERBOSE=0 PAUSE_ON_FAIL=no @@ -655,6 +655,98 @@ fib_nexthop_test() cleanup } +fib6_notify_test() +{ + setup + + echo + echo "Fib6 info length calculation in route notify test" + set -e + + for i in 10 20 30 40 50 60 70; + do + $IP link add dummy_$i type dummy + $IP link set dev dummy_$i up + $IP -6 address add 2001:$i::1/64 dev dummy_$i + done + + $NS_EXEC ip monitor route &> errors.txt & + sleep 2 + + $IP -6 route add 2001::/64 \ + nexthop via 2001:10::2 dev dummy_10 \ + nexthop encap ip6 dst 2002::20 via 2001:20::2 dev dummy_20 \ + nexthop encap ip6 dst 2002::30 via 2001:30::2 dev dummy_30 \ + nexthop encap ip6 dst 2002::40 via 2001:40::2 dev dummy_40 \ + nexthop encap ip6 dst 2002::50 via 2001:50::2 dev dummy_50 \ + nexthop encap ip6 dst 2002::60 via 2001:60::2 dev dummy_60 \ + nexthop encap ip6 dst 2002::70 via 2001:70::2 dev dummy_70 + + set +e + + err=`cat errors.txt |grep "Message too long"` + if [ -z "$err" ];then + ret=0 + else + ret=1 + fi + + log_test $ret 0 "ipv6 route add notify" + + { kill %% && wait %%; } 2>/dev/null + + #rm errors.txt + + cleanup &> /dev/null +} + + +fib_notify_test() +{ + setup + + echo + echo "Fib4 info length calculation in route notify test" + + set -e + + for i in 10 20 30 40 50 60 70; + do + $IP link add dummy_$i type dummy + $IP link set dev dummy_$i up + $IP address add 20.20.$i.2/24 dev dummy_$i + done + + $NS_EXEC ip monitor route &> errors.txt & + sleep 2 + + $IP route add 10.0.0.0/24 \ + nexthop via 20.20.10.1 dev dummy_10 \ + nexthop encap ip dst 192.168.10.20 via 20.20.20.1 dev dummy_20 \ + nexthop encap ip dst 192.168.10.30 via 20.20.30.1 dev dummy_30 \ + nexthop encap ip dst 192.168.10.40 via 20.20.40.1 dev dummy_40 \ + nexthop encap ip dst 192.168.10.50 via 20.20.50.1 dev dummy_50 \ + nexthop encap ip dst 192.168.10.60 via 20.20.60.1 dev dummy_60 \ + nexthop encap ip dst 192.168.10.70 via 20.20.70.1 dev dummy_70 + + set +e + + err=`cat errors.txt |grep "Message too long"` + if [ -z "$err" ];then + ret=0 + else + ret=1 + fi + + log_test $ret 0 "ipv4 route add notify" + + { kill %% && wait %%; } 2>/dev/null + + rm errors.txt + + cleanup &> /dev/null +} + fib_suppress_test() { echo @@ -2111,6 +2203,8 @@ do fib_carrier_test|carrier) fib_carrier_test;; fib_rp_filter_test|rp_filter) fib_rp_filter_test;; fib_nexthop_test|nexthop) fib_nexthop_test;; + fib_notify_test|ipv4_notify) fib_notify_test;; + fib6_notify_test|ipv6_notify) fib6_notify_test;; fib_suppress_test|suppress) fib_suppress_test;; ipv6_route_test|ipv6_rt) ipv6_route_test;; ipv4_route_test|ipv4_rt) ipv4_route_test;; diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 66c5be25c13d..b1eb7bce599d 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -240,7 +240,7 @@ check_expected_one() fi stdbuf -o0 -e0 printf "\tExpected value for '%s': '%s', got '%s'.\n" \ - "${var}" "${!var}" "${!exp}" + "${var}" "${!exp}" "${!var}" return 1 } @@ -913,6 +913,7 @@ test_listener() $client4_port > /dev/null 2>&1 & local listener_pid=$! + sleep 0.5 verify_listener_events $client_evts $LISTENER_CREATED $AF_INET 10.0.2.2 $client4_port # ADD_ADDR from client to server machine reusing the subflow port @@ -928,6 +929,7 @@ test_listener() # Delete the listener from the client ns, if one was created kill_wait $listener_pid + sleep 0.5 verify_listener_events $client_evts $LISTENER_CLOSED $AF_INET 10.0.2.2 $client4_port } diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index 3243c90d449e..5d467d1993cb 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -62,7 +62,7 @@ class OvsDatapath(GenericNetlinkSocket): nla_map = ( ("OVS_DP_ATTR_UNSPEC", "none"), ("OVS_DP_ATTR_NAME", "asciiz"), - ("OVS_DP_ATTR_UPCALL_PID", "uint32"), + ("OVS_DP_ATTR_UPCALL_PID", "array(uint32)"), ("OVS_DP_ATTR_STATS", "dpstats"), ("OVS_DP_ATTR_MEGAFLOW_STATS", "megaflowstats"), ("OVS_DP_ATTR_USER_FEATURES", "uint32"), diff --git a/tools/testing/selftests/net/rps_default_mask.sh b/tools/testing/selftests/net/rps_default_mask.sh index 0fd0d2db3abc..a26c5624429f 100755 --- a/tools/testing/selftests/net/rps_default_mask.sh +++ b/tools/testing/selftests/net/rps_default_mask.sh @@ -60,6 +60,7 @@ ip link set dev $VETH up ip -n $NETNS link set dev $VETH up chk_rps "changing rps_default_mask affect newly created devices" "" $VETH 3 chk_rps "changing rps_default_mask don't affect newly child netns[II]" $NETNS $VETH 0 +ip link del dev $VETH ip netns del $NETNS setup diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 924ecb3f1f73..dd40d9f6f259 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -404,6 +404,8 @@ EOF echo SERVER-$family | ip netns exec "$ns1" timeout 5 socat -u STDIN TCP-LISTEN:2000 & sc_s=$! + sleep 1 + result=$(ip netns exec "$ns0" timeout 1 socat TCP:$daddr:2000 STDOUT) if [ "$result" = "SERVER-inet" ];then diff --git a/tools/testing/selftests/netfilter/rpath.sh b/tools/testing/selftests/netfilter/rpath.sh index f7311e66d219..5289c8447a41 100755 --- a/tools/testing/selftests/netfilter/rpath.sh +++ b/tools/testing/selftests/netfilter/rpath.sh @@ -62,10 +62,16 @@ ip -net "$ns1" a a fec0:42::2/64 dev v0 nodad ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad # firewall matches to test -[ -n "$iptables" ] && ip netns exec "$ns2" \ - "$iptables" -t raw -A PREROUTING -s 192.168.0.0/16 -m rpfilter -[ -n "$ip6tables" ] && ip netns exec "$ns2" \ - "$ip6tables" -t raw -A PREROUTING -s fec0::/16 -m rpfilter +[ -n "$iptables" ] && { + common='-t raw -A PREROUTING -s 192.168.0.0/16' + ip netns exec "$ns2" "$iptables" $common -m rpfilter + ip netns exec "$ns2" "$iptables" $common -m rpfilter --invert +} +[ -n "$ip6tables" ] && { + common='-t raw -A PREROUTING -s fec0::/16' + ip netns exec "$ns2" "$ip6tables" $common -m rpfilter + ip netns exec "$ns2" "$ip6tables" $common -m rpfilter --invert +} [ -n "$nft" ] && ip netns exec "$ns2" $nft -f - <<EOF table inet t { chain c { @@ -89,6 +95,11 @@ ipt_zero_rule() { # (command) [ -n "$1" ] || return 0 ip netns exec "$ns2" "$1" -t raw -vS | grep -q -- "-m rpfilter -c 0 0" } +ipt_zero_reverse_rule() { # (command) + [ -n "$1" ] || return 0 + ip netns exec "$ns2" "$1" -t raw -vS | \ + grep -q -- "-m rpfilter --invert -c 0 0" +} nft_zero_rule() { # (family) [ -n "$nft" ] || return 0 ip netns exec "$ns2" "$nft" list chain inet t c | \ @@ -101,8 +112,7 @@ netns_ping() { # (netns, args...) ip netns exec "$netns" ping -q -c 1 -W 1 "$@" >/dev/null } -testrun() { - # clear counters first +clear_counters() { [ -n "$iptables" ] && ip netns exec "$ns2" "$iptables" -t raw -Z [ -n "$ip6tables" ] && ip netns exec "$ns2" "$ip6tables" -t raw -Z if [ -n "$nft" ]; then @@ -111,6 +121,10 @@ testrun() { ip netns exec "$ns2" $nft -s list table inet t; ) | ip netns exec "$ns2" $nft -f - fi +} + +testrun() { + clear_counters # test 1: martian traffic should fail rpfilter matches netns_ping "$ns1" -I v0 192.168.42.1 && \ @@ -120,9 +134,13 @@ testrun() { ipt_zero_rule "$iptables" || die "iptables matched martian" ipt_zero_rule "$ip6tables" || die "ip6tables matched martian" + ipt_zero_reverse_rule "$iptables" && die "iptables not matched martian" + ipt_zero_reverse_rule "$ip6tables" && die "ip6tables not matched martian" nft_zero_rule ip || die "nft IPv4 matched martian" nft_zero_rule ip6 || die "nft IPv6 matched martian" + clear_counters + # test 2: rpfilter match should pass for regular traffic netns_ping "$ns1" 192.168.23.1 || \ die "regular ping 192.168.23.1 failed" @@ -131,6 +149,8 @@ testrun() { ipt_zero_rule "$iptables" && die "iptables match not effective" ipt_zero_rule "$ip6tables" && die "ip6tables match not effective" + ipt_zero_reverse_rule "$iptables" || die "iptables match over-effective" + ipt_zero_reverse_rule "$ip6tables" || die "ip6tables match over-effective" nft_zero_rule ip && die "nft IPv4 match not effective" nft_zero_rule ip6 && die "nft IPv6 match not effective" diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index 8fe61d3e3cce..bbce57420465 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -1,6 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for nolibc tests include ../../../scripts/Makefile.include +# We need this for the "cc-option" macro. +include ../../../build/Build.include # we're in ".../tools/testing/selftests/nolibc" ifeq ($(srctree),) @@ -13,52 +15,56 @@ ARCH = $(SUBARCH) endif # kernel image names by architecture -IMAGE_i386 = arch/x86/boot/bzImage -IMAGE_x86_64 = arch/x86/boot/bzImage -IMAGE_x86 = arch/x86/boot/bzImage -IMAGE_arm64 = arch/arm64/boot/Image -IMAGE_arm = arch/arm/boot/zImage -IMAGE_mips = vmlinuz -IMAGE_riscv = arch/riscv/boot/Image -IMAGE_s390 = arch/s390/boot/bzImage -IMAGE = $(IMAGE_$(ARCH)) -IMAGE_NAME = $(notdir $(IMAGE)) +IMAGE_i386 = arch/x86/boot/bzImage +IMAGE_x86_64 = arch/x86/boot/bzImage +IMAGE_x86 = arch/x86/boot/bzImage +IMAGE_arm64 = arch/arm64/boot/Image +IMAGE_arm = arch/arm/boot/zImage +IMAGE_mips = vmlinuz +IMAGE_riscv = arch/riscv/boot/Image +IMAGE_s390 = arch/s390/boot/bzImage +IMAGE_loongarch = arch/loongarch/boot/vmlinuz.efi +IMAGE = $(IMAGE_$(ARCH)) +IMAGE_NAME = $(notdir $(IMAGE)) # default kernel configurations that appear to be usable -DEFCONFIG_i386 = defconfig -DEFCONFIG_x86_64 = defconfig -DEFCONFIG_x86 = defconfig -DEFCONFIG_arm64 = defconfig -DEFCONFIG_arm = multi_v7_defconfig -DEFCONFIG_mips = malta_defconfig -DEFCONFIG_riscv = defconfig -DEFCONFIG_s390 = defconfig -DEFCONFIG = $(DEFCONFIG_$(ARCH)) +DEFCONFIG_i386 = defconfig +DEFCONFIG_x86_64 = defconfig +DEFCONFIG_x86 = defconfig +DEFCONFIG_arm64 = defconfig +DEFCONFIG_arm = multi_v7_defconfig +DEFCONFIG_mips = malta_defconfig +DEFCONFIG_riscv = defconfig +DEFCONFIG_s390 = defconfig +DEFCONFIG_loongarch = defconfig +DEFCONFIG = $(DEFCONFIG_$(ARCH)) # optional tests to run (default = all) TEST = # QEMU_ARCH: arch names used by qemu -QEMU_ARCH_i386 = i386 -QEMU_ARCH_x86_64 = x86_64 -QEMU_ARCH_x86 = x86_64 -QEMU_ARCH_arm64 = aarch64 -QEMU_ARCH_arm = arm -QEMU_ARCH_mips = mipsel # works with malta_defconfig -QEMU_ARCH_riscv = riscv64 -QEMU_ARCH_s390 = s390x -QEMU_ARCH = $(QEMU_ARCH_$(ARCH)) +QEMU_ARCH_i386 = i386 +QEMU_ARCH_x86_64 = x86_64 +QEMU_ARCH_x86 = x86_64 +QEMU_ARCH_arm64 = aarch64 +QEMU_ARCH_arm = arm +QEMU_ARCH_mips = mipsel # works with malta_defconfig +QEMU_ARCH_riscv = riscv64 +QEMU_ARCH_s390 = s390x +QEMU_ARCH_loongarch = loongarch64 +QEMU_ARCH = $(QEMU_ARCH_$(ARCH)) # QEMU_ARGS : some arch-specific args to pass to qemu -QEMU_ARGS_i386 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_x86_64 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_x86 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_arm64 = -M virt -cpu cortex-a53 -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_arm = -M virt -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_mips = -M malta -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_riscv = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_s390 = -M s390-ccw-virtio -m 1G -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS = $(QEMU_ARGS_$(ARCH)) +QEMU_ARGS_i386 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_x86_64 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_x86 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_arm64 = -M virt -cpu cortex-a53 -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_arm = -M virt -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_mips = -M malta -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_riscv = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_s390 = -M s390-ccw-virtio -m 1G -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_loongarch = -M virt -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS = $(QEMU_ARGS_$(ARCH)) # OUTPUT is only set when run from the main makefile, otherwise # it defaults to this nolibc directory. @@ -70,8 +76,16 @@ else Q=@ endif +CFLAGS_STACKPROTECTOR = -DNOLIBC_STACKPROTECTOR \ + $(call cc-option,-mstack-protector-guard=global) \ + $(call cc-option,-fstack-protector-all) +CFLAGS_STKP_i386 = $(CFLAGS_STACKPROTECTOR) +CFLAGS_STKP_x86_64 = $(CFLAGS_STACKPROTECTOR) +CFLAGS_STKP_x86 = $(CFLAGS_STACKPROTECTOR) CFLAGS_s390 = -m64 -CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables $(CFLAGS_$(ARCH)) +CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables \ + $(call cc-option,-fno-stack-protector) \ + $(CFLAGS_STKP_$(ARCH)) $(CFLAGS_$(ARCH)) LDFLAGS := -s help: diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index c4a0c915139c..21bacc928bf7 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -130,111 +130,111 @@ static int pad_spc(int llen, int cnt, const char *fmt, ...) */ #define EXPECT_ZR(cond, expr) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_zr(expr, llen); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_zr(expr, llen); } while (0) static int expect_zr(int expr, int llen) { int ret = !(expr == 0); llen += printf(" = %d ", expr); - pad_spc(llen, 40, ret ? "[FAIL]\n" : " [OK]\n"); + pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); return ret; } #define EXPECT_NZ(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_nz(expr, llen; } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_nz(expr, llen; } while (0) static int expect_nz(int expr, int llen) { int ret = !(expr != 0); llen += printf(" = %d ", expr); - pad_spc(llen, 40, ret ? "[FAIL]\n" : " [OK]\n"); + pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); return ret; } #define EXPECT_EQ(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_eq(expr, llen, val); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_eq(expr, llen, val); } while (0) -static int expect_eq(int expr, int llen, int val) +static int expect_eq(uint64_t expr, int llen, uint64_t val) { int ret = !(expr == val); - llen += printf(" = %d ", expr); - pad_spc(llen, 40, ret ? "[FAIL]\n" : " [OK]\n"); + llen += printf(" = %lld ", expr); + pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); return ret; } #define EXPECT_NE(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_ne(expr, llen, val); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_ne(expr, llen, val); } while (0) static int expect_ne(int expr, int llen, int val) { int ret = !(expr != val); llen += printf(" = %d ", expr); - pad_spc(llen, 40, ret ? "[FAIL]\n" : " [OK]\n"); + pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); return ret; } #define EXPECT_GE(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_ge(expr, llen, val); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_ge(expr, llen, val); } while (0) static int expect_ge(int expr, int llen, int val) { int ret = !(expr >= val); llen += printf(" = %d ", expr); - pad_spc(llen, 40, ret ? "[FAIL]\n" : " [OK]\n"); + pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); return ret; } #define EXPECT_GT(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_gt(expr, llen, val); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_gt(expr, llen, val); } while (0) static int expect_gt(int expr, int llen, int val) { int ret = !(expr > val); llen += printf(" = %d ", expr); - pad_spc(llen, 40, ret ? "[FAIL]\n" : " [OK]\n"); + pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); return ret; } #define EXPECT_LE(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_le(expr, llen, val); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_le(expr, llen, val); } while (0) static int expect_le(int expr, int llen, int val) { int ret = !(expr <= val); llen += printf(" = %d ", expr); - pad_spc(llen, 40, ret ? "[FAIL]\n" : " [OK]\n"); + pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); return ret; } #define EXPECT_LT(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_lt(expr, llen, val); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_lt(expr, llen, val); } while (0) static int expect_lt(int expr, int llen, int val) { int ret = !(expr < val); llen += printf(" = %d ", expr); - pad_spc(llen, 40, ret ? "[FAIL]\n" : " [OK]\n"); + pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); return ret; } #define EXPECT_SYSZR(cond, expr) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_syszr(expr, llen); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_syszr(expr, llen); } while (0) static int expect_syszr(int expr, int llen) { @@ -243,17 +243,17 @@ static int expect_syszr(int expr, int llen) if (expr) { ret = 1; llen += printf(" = %d %s ", expr, errorname(errno)); - llen += pad_spc(llen, 40, "[FAIL]\n"); + llen += pad_spc(llen, 64, "[FAIL]\n"); } else { llen += printf(" = %d ", expr); - llen += pad_spc(llen, 40, " [OK]\n"); + llen += pad_spc(llen, 64, " [OK]\n"); } return ret; } #define EXPECT_SYSEQ(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_syseq(expr, llen, val); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_syseq(expr, llen, val); } while (0) static int expect_syseq(int expr, int llen, int val) { @@ -262,17 +262,17 @@ static int expect_syseq(int expr, int llen, int val) if (expr != val) { ret = 1; llen += printf(" = %d %s ", expr, errorname(errno)); - llen += pad_spc(llen, 40, "[FAIL]\n"); + llen += pad_spc(llen, 64, "[FAIL]\n"); } else { llen += printf(" = %d ", expr); - llen += pad_spc(llen, 40, " [OK]\n"); + llen += pad_spc(llen, 64, " [OK]\n"); } return ret; } #define EXPECT_SYSNE(cond, expr, val) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_sysne(expr, llen, val); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_sysne(expr, llen, val); } while (0) static int expect_sysne(int expr, int llen, int val) { @@ -281,17 +281,17 @@ static int expect_sysne(int expr, int llen, int val) if (expr == val) { ret = 1; llen += printf(" = %d %s ", expr, errorname(errno)); - llen += pad_spc(llen, 40, "[FAIL]\n"); + llen += pad_spc(llen, 64, "[FAIL]\n"); } else { llen += printf(" = %d ", expr); - llen += pad_spc(llen, 40, " [OK]\n"); + llen += pad_spc(llen, 64, " [OK]\n"); } return ret; } #define EXPECT_SYSER(cond, expr, expret, experr) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_syserr(expr, expret, experr, llen); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_syserr(expr, expret, experr, llen); } while (0) static int expect_syserr(int expr, int expret, int experr, int llen) { @@ -302,16 +302,16 @@ static int expect_syserr(int expr, int expret, int experr, int llen) if (expr != expret || _errno != experr) { ret = 1; llen += printf(" != (%d %s) ", expret, errorname(experr)); - llen += pad_spc(llen, 40, "[FAIL]\n"); + llen += pad_spc(llen, 64, "[FAIL]\n"); } else { - llen += pad_spc(llen, 40, " [OK]\n"); + llen += pad_spc(llen, 64, " [OK]\n"); } return ret; } #define EXPECT_PTRZR(cond, expr) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_ptrzr(expr, llen); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_ptrzr(expr, llen); } while (0) static int expect_ptrzr(const void *expr, int llen) { @@ -320,16 +320,16 @@ static int expect_ptrzr(const void *expr, int llen) llen += printf(" = <%p> ", expr); if (expr) { ret = 1; - llen += pad_spc(llen, 40, "[FAIL]\n"); + llen += pad_spc(llen, 64, "[FAIL]\n"); } else { - llen += pad_spc(llen, 40, " [OK]\n"); + llen += pad_spc(llen, 64, " [OK]\n"); } return ret; } #define EXPECT_PTRNZ(cond, expr) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_ptrnz(expr, llen); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_ptrnz(expr, llen); } while (0) static int expect_ptrnz(const void *expr, int llen) { @@ -338,16 +338,16 @@ static int expect_ptrnz(const void *expr, int llen) llen += printf(" = <%p> ", expr); if (!expr) { ret = 1; - llen += pad_spc(llen, 40, "[FAIL]\n"); + llen += pad_spc(llen, 64, "[FAIL]\n"); } else { - llen += pad_spc(llen, 40, " [OK]\n"); + llen += pad_spc(llen, 64, " [OK]\n"); } return ret; } #define EXPECT_STRZR(cond, expr) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_strzr(expr, llen); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_strzr(expr, llen); } while (0) static int expect_strzr(const char *expr, int llen) { @@ -356,16 +356,16 @@ static int expect_strzr(const char *expr, int llen) llen += printf(" = <%s> ", expr); if (expr) { ret = 1; - llen += pad_spc(llen, 40, "[FAIL]\n"); + llen += pad_spc(llen, 64, "[FAIL]\n"); } else { - llen += pad_spc(llen, 40, " [OK]\n"); + llen += pad_spc(llen, 64, " [OK]\n"); } return ret; } #define EXPECT_STRNZ(cond, expr) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_strnz(expr, llen); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_strnz(expr, llen); } while (0) static int expect_strnz(const char *expr, int llen) { @@ -374,16 +374,16 @@ static int expect_strnz(const char *expr, int llen) llen += printf(" = <%s> ", expr); if (!expr) { ret = 1; - llen += pad_spc(llen, 40, "[FAIL]\n"); + llen += pad_spc(llen, 64, "[FAIL]\n"); } else { - llen += pad_spc(llen, 40, " [OK]\n"); + llen += pad_spc(llen, 64, " [OK]\n"); } return ret; } #define EXPECT_STREQ(cond, expr, cmp) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_streq(expr, llen, cmp); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_streq(expr, llen, cmp); } while (0) static int expect_streq(const char *expr, int llen, const char *cmp) { @@ -392,16 +392,16 @@ static int expect_streq(const char *expr, int llen, const char *cmp) llen += printf(" = <%s> ", expr); if (strcmp(expr, cmp) != 0) { ret = 1; - llen += pad_spc(llen, 40, "[FAIL]\n"); + llen += pad_spc(llen, 64, "[FAIL]\n"); } else { - llen += pad_spc(llen, 40, " [OK]\n"); + llen += pad_spc(llen, 64, " [OK]\n"); } return ret; } #define EXPECT_STRNE(cond, expr, cmp) \ - do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_strne(expr, llen, cmp); } while (0) + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_strne(expr, llen, cmp); } while (0) static int expect_strne(const char *expr, int llen, const char *cmp) { @@ -410,9 +410,9 @@ static int expect_strne(const char *expr, int llen, const char *cmp) llen += printf(" = <%s> ", expr); if (strcmp(expr, cmp) == 0) { ret = 1; - llen += pad_spc(llen, 40, "[FAIL]\n"); + llen += pad_spc(llen, 64, "[FAIL]\n"); } else { - llen += pad_spc(llen, 40, " [OK]\n"); + llen += pad_spc(llen, 64, " [OK]\n"); } return ret; } @@ -477,6 +477,7 @@ static int test_getpagesize(void) int run_syscall(int min, int max) { struct stat stat_buf; + int euid0; int proc; int test; int tmp; @@ -486,6 +487,9 @@ int run_syscall(int min, int max) /* <proc> indicates whether or not /proc is mounted */ proc = stat("/proc", &stat_buf) == 0; + /* this will be used to skip certain tests that can't be run unprivileged */ + euid0 = geteuid() == 0; + for (test = min; test >= 0 && test <= max; test++) { int llen = 0; // line length @@ -511,7 +515,7 @@ int run_syscall(int min, int max) CASE_TEST(chmod_net); EXPECT_SYSZR(proc, chmod("/proc/self/net", 0555)); break; CASE_TEST(chmod_self); EXPECT_SYSER(proc, chmod("/proc/self", 0555), -1, EPERM); break; CASE_TEST(chown_self); EXPECT_SYSER(proc, chown("/proc/self", 0, 0), -1, EPERM); break; - CASE_TEST(chroot_root); EXPECT_SYSZR(1, chroot("/")); break; + CASE_TEST(chroot_root); EXPECT_SYSZR(euid0, chroot("/")); break; CASE_TEST(chroot_blah); EXPECT_SYSER(1, chroot("/proc/self/blah"), -1, ENOENT); break; CASE_TEST(chroot_exe); EXPECT_SYSER(proc, chroot("/proc/self/exe"), -1, ENOTDIR); break; CASE_TEST(close_m1); EXPECT_SYSER(1, close(-1), -1, EBADF); break; @@ -536,7 +540,7 @@ int run_syscall(int min, int max) CASE_TEST(ioctl_tiocinq); EXPECT_SYSZR(1, ioctl(0, TIOCINQ, &tmp)); break; CASE_TEST(link_root1); EXPECT_SYSER(1, link("/", "/"), -1, EEXIST); break; CASE_TEST(link_blah); EXPECT_SYSER(1, link("/proc/self/blah", "/blah"), -1, ENOENT); break; - CASE_TEST(link_dir); EXPECT_SYSER(1, link("/", "/blah"), -1, EPERM); break; + CASE_TEST(link_dir); EXPECT_SYSER(euid0, link("/", "/blah"), -1, EPERM); break; CASE_TEST(link_cross); EXPECT_SYSER(proc, link("/proc/self/net", "/blah"), -1, EXDEV); break; CASE_TEST(lseek_m1); EXPECT_SYSER(1, lseek(-1, 0, SEEK_SET), -1, EBADF); break; CASE_TEST(lseek_0); EXPECT_SYSER(1, lseek(0, 0, SEEK_SET), -1, ESPIPE); break; @@ -602,6 +606,59 @@ int run_stdlib(int min, int max) CASE_TEST(memcmp_e0_20); EXPECT_GT(1, memcmp("aaa\xe0", "aaa\x20", 4), 0); break; CASE_TEST(memcmp_80_e0); EXPECT_LT(1, memcmp("aaa\x80", "aaa\xe0", 4), 0); break; CASE_TEST(memcmp_e0_80); EXPECT_GT(1, memcmp("aaa\xe0", "aaa\x80", 4), 0); break; + CASE_TEST(limit_int8_max); EXPECT_EQ(1, INT8_MAX, (int8_t) 0x7f); break; + CASE_TEST(limit_int8_min); EXPECT_EQ(1, INT8_MIN, (int8_t) 0x80); break; + CASE_TEST(limit_uint8_max); EXPECT_EQ(1, UINT8_MAX, (uint8_t) 0xff); break; + CASE_TEST(limit_int16_max); EXPECT_EQ(1, INT16_MAX, (int16_t) 0x7fff); break; + CASE_TEST(limit_int16_min); EXPECT_EQ(1, INT16_MIN, (int16_t) 0x8000); break; + CASE_TEST(limit_uint16_max); EXPECT_EQ(1, UINT16_MAX, (uint16_t) 0xffff); break; + CASE_TEST(limit_int32_max); EXPECT_EQ(1, INT32_MAX, (int32_t) 0x7fffffff); break; + CASE_TEST(limit_int32_min); EXPECT_EQ(1, INT32_MIN, (int32_t) 0x80000000); break; + CASE_TEST(limit_uint32_max); EXPECT_EQ(1, UINT32_MAX, (uint32_t) 0xffffffff); break; + CASE_TEST(limit_int64_max); EXPECT_EQ(1, INT64_MAX, (int64_t) 0x7fffffffffffffff); break; + CASE_TEST(limit_int64_min); EXPECT_EQ(1, INT64_MIN, (int64_t) 0x8000000000000000); break; + CASE_TEST(limit_uint64_max); EXPECT_EQ(1, UINT64_MAX, (uint64_t) 0xffffffffffffffff); break; + CASE_TEST(limit_int_least8_max); EXPECT_EQ(1, INT_LEAST8_MAX, (int_least8_t) 0x7f); break; + CASE_TEST(limit_int_least8_min); EXPECT_EQ(1, INT_LEAST8_MIN, (int_least8_t) 0x80); break; + CASE_TEST(limit_uint_least8_max); EXPECT_EQ(1, UINT_LEAST8_MAX, (uint_least8_t) 0xff); break; + CASE_TEST(limit_int_least16_max); EXPECT_EQ(1, INT_LEAST16_MAX, (int_least16_t) 0x7fff); break; + CASE_TEST(limit_int_least16_min); EXPECT_EQ(1, INT_LEAST16_MIN, (int_least16_t) 0x8000); break; + CASE_TEST(limit_uint_least16_max); EXPECT_EQ(1, UINT_LEAST16_MAX, (uint_least16_t) 0xffff); break; + CASE_TEST(limit_int_least32_max); EXPECT_EQ(1, INT_LEAST32_MAX, (int_least32_t) 0x7fffffff); break; + CASE_TEST(limit_int_least32_min); EXPECT_EQ(1, INT_LEAST32_MIN, (int_least32_t) 0x80000000); break; + CASE_TEST(limit_uint_least32_max); EXPECT_EQ(1, UINT_LEAST32_MAX, (uint_least32_t) 0xffffffffU); break; + CASE_TEST(limit_int_least64_min); EXPECT_EQ(1, INT_LEAST64_MIN, (int_least64_t) 0x8000000000000000LL); break; + CASE_TEST(limit_int_least64_max); EXPECT_EQ(1, INT_LEAST64_MAX, (int_least64_t) 0x7fffffffffffffffLL); break; + CASE_TEST(limit_uint_least64_max); EXPECT_EQ(1, UINT_LEAST64_MAX, (uint_least64_t) 0xffffffffffffffffULL); break; + CASE_TEST(limit_int_fast8_max); EXPECT_EQ(1, INT_FAST8_MAX, (int_fast8_t) 0x7f); break; + CASE_TEST(limit_int_fast8_min); EXPECT_EQ(1, INT_FAST8_MIN, (int_fast8_t) 0x80); break; + CASE_TEST(limit_uint_fast8_max); EXPECT_EQ(1, UINT_FAST8_MAX, (uint_fast8_t) 0xff); break; + CASE_TEST(limit_int_fast16_min); EXPECT_EQ(1, INT_FAST16_MIN, (int_fast16_t) INTPTR_MIN); break; + CASE_TEST(limit_int_fast16_max); EXPECT_EQ(1, INT_FAST16_MAX, (int_fast16_t) INTPTR_MAX); break; + CASE_TEST(limit_uint_fast16_max); EXPECT_EQ(1, UINT_FAST16_MAX, (uint_fast16_t) UINTPTR_MAX); break; + CASE_TEST(limit_int_fast32_min); EXPECT_EQ(1, INT_FAST32_MIN, (int_fast32_t) INTPTR_MIN); break; + CASE_TEST(limit_int_fast32_max); EXPECT_EQ(1, INT_FAST32_MAX, (int_fast32_t) INTPTR_MAX); break; + CASE_TEST(limit_uint_fast32_max); EXPECT_EQ(1, UINT_FAST32_MAX, (uint_fast32_t) UINTPTR_MAX); break; + CASE_TEST(limit_int_fast64_min); EXPECT_EQ(1, INT_FAST64_MIN, (int_fast64_t) INTPTR_MIN); break; + CASE_TEST(limit_int_fast64_max); EXPECT_EQ(1, INT_FAST64_MAX, (int_fast64_t) INTPTR_MAX); break; + CASE_TEST(limit_uint_fast64_max); EXPECT_EQ(1, UINT_FAST64_MAX, (uint_fast64_t) UINTPTR_MAX); break; +#if __SIZEOF_LONG__ == 8 + CASE_TEST(limit_intptr_min); EXPECT_EQ(1, INTPTR_MIN, (intptr_t) 0x8000000000000000LL); break; + CASE_TEST(limit_intptr_max); EXPECT_EQ(1, INTPTR_MAX, (intptr_t) 0x7fffffffffffffffLL); break; + CASE_TEST(limit_uintptr_max); EXPECT_EQ(1, UINTPTR_MAX, (uintptr_t) 0xffffffffffffffffULL); break; + CASE_TEST(limit_ptrdiff_min); EXPECT_EQ(1, PTRDIFF_MIN, (ptrdiff_t) 0x8000000000000000LL); break; + CASE_TEST(limit_ptrdiff_max); EXPECT_EQ(1, PTRDIFF_MAX, (ptrdiff_t) 0x7fffffffffffffffLL); break; + CASE_TEST(limit_size_max); EXPECT_EQ(1, SIZE_MAX, (size_t) 0xffffffffffffffffULL); break; +#elif __SIZEOF_LONG__ == 4 + CASE_TEST(limit_intptr_min); EXPECT_EQ(1, INTPTR_MIN, (intptr_t) 0x80000000); break; + CASE_TEST(limit_intptr_max); EXPECT_EQ(1, INTPTR_MAX, (intptr_t) 0x7fffffff); break; + CASE_TEST(limit_uintptr_max); EXPECT_EQ(1, UINTPTR_MAX, (uintptr_t) 0xffffffffU); break; + CASE_TEST(limit_ptrdiff_min); EXPECT_EQ(1, PTRDIFF_MIN, (ptrdiff_t) 0x80000000); break; + CASE_TEST(limit_ptrdiff_max); EXPECT_EQ(1, PTRDIFF_MAX, (ptrdiff_t) 0x7fffffff); break; + CASE_TEST(limit_size_max); EXPECT_EQ(1, SIZE_MAX, (size_t) 0xffffffffU); break; +#else +# warning "__SIZEOF_LONG__ is undefined" +#endif /* __SIZEOF_LONG__ */ case __LINE__: return ret; /* must be last */ /* note: do not set any defaults so as to permit holes above */ @@ -610,6 +667,63 @@ int run_stdlib(int min, int max) return ret; } +#if defined(__clang__) +__attribute__((optnone)) +#elif defined(__GNUC__) +__attribute__((optimize("O0"))) +#endif +static int smash_stack(void) +{ + char buf[100]; + + for (size_t i = 0; i < 200; i++) + buf[i] = 'P'; + + return 1; +} + +static int run_protection(int min, int max) +{ + pid_t pid; + int llen = 0, status; + + llen += printf("0 -fstackprotector "); + +#if !defined(NOLIBC_STACKPROTECTOR) + llen += printf("not supported"); + pad_spc(llen, 64, "[SKIPPED]\n"); + return 0; +#endif + + pid = -1; + pid = fork(); + + switch (pid) { + case -1: + llen += printf("fork()"); + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + + case 0: + close(STDOUT_FILENO); + close(STDERR_FILENO); + + smash_stack(); + return 1; + + default: + pid = waitpid(pid, &status, 0); + + if (pid == -1 || !WIFSIGNALED(status) || WTERMSIG(status) != SIGABRT) { + llen += printf("waitpid()"); + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + } + pad_spc(llen, 64, " [OK]\n"); + return 0; + } +} + /* prepare what needs to be prepared for pid 1 (stdio, /dev, /proc, etc) */ int prepare(void) { @@ -660,10 +774,11 @@ int prepare(void) } /* This is the definition of known test names, with their functions */ -static struct test test_names[] = { +static const struct test test_names[] = { /* add new tests here */ - { .name = "syscall", .func = run_syscall }, - { .name = "stdlib", .func = run_stdlib }, + { .name = "syscall", .func = run_syscall }, + { .name = "stdlib", .func = run_stdlib }, + { .name = "protection", .func = run_protection }, { 0 } }; diff --git a/tools/testing/selftests/powerpc/dscr/dscr.h b/tools/testing/selftests/powerpc/dscr/dscr.h index b703714e7d98..2c54998d4715 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr.h +++ b/tools/testing/selftests/powerpc/dscr/dscr.h @@ -64,48 +64,26 @@ inline void set_dscr_usr(unsigned long val) /* Default DSCR access */ unsigned long get_default_dscr(void) { - int fd = -1, ret; - char buf[16]; + int err; unsigned long val; - if (fd == -1) { - fd = open(DSCR_DEFAULT, O_RDONLY); - if (fd == -1) { - perror("open() failed"); - exit(1); - } - } - memset(buf, 0, sizeof(buf)); - lseek(fd, 0, SEEK_SET); - ret = read(fd, buf, sizeof(buf)); - if (ret == -1) { + err = read_ulong(DSCR_DEFAULT, &val, 16); + if (err) { perror("read() failed"); exit(1); } - sscanf(buf, "%lx", &val); - close(fd); return val; } void set_default_dscr(unsigned long val) { - int fd = -1, ret; - char buf[16]; + int err; - if (fd == -1) { - fd = open(DSCR_DEFAULT, O_RDWR); - if (fd == -1) { - perror("open() failed"); - exit(1); - } - } - sprintf(buf, "%lx\n", val); - ret = write(fd, buf, strlen(buf)); - if (ret == -1) { + err = write_ulong(DSCR_DEFAULT, val, 16); + if (err) { perror("write() failed"); exit(1); } - close(fd); } double uniform_deviate(int seed) diff --git a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c index f20d1c166d1e..4f1fef6198fc 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c @@ -12,27 +12,16 @@ static int check_cpu_dscr_default(char *file, unsigned long val) { - char buf[10]; - int fd, rc; + unsigned long cpu_dscr; + int err; - fd = open(file, O_RDWR); - if (fd == -1) { - perror("open() failed"); - return 1; - } - - rc = read(fd, buf, sizeof(buf)); - if (rc == -1) { - perror("read() failed"); - close(fd); - return 1; - } - close(fd); + err = read_ulong(file, &cpu_dscr, 16); + if (err) + return err; - buf[rc] = '\0'; - if (strtol(buf, NULL, 16) != val) { + if (cpu_dscr != val) { printf("DSCR match failed: %ld (system) %ld (cpu)\n", - val, strtol(buf, NULL, 16)); + val, cpu_dscr); return 1; } return 0; diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h index e222a5858450..eed7dd7582b2 100644 --- a/tools/testing/selftests/powerpc/include/utils.h +++ b/tools/testing/selftests/powerpc/include/utils.h @@ -33,8 +33,24 @@ void *get_auxv_entry(int type); int pick_online_cpu(void); -int read_debugfs_file(char *debugfs_file, int *result); -int write_debugfs_file(char *debugfs_file, int result); +int parse_intmax(const char *buffer, size_t count, intmax_t *result, int base); +int parse_uintmax(const char *buffer, size_t count, uintmax_t *result, int base); +int parse_int(const char *buffer, size_t count, int *result, int base); +int parse_uint(const char *buffer, size_t count, unsigned int *result, int base); +int parse_long(const char *buffer, size_t count, long *result, int base); +int parse_ulong(const char *buffer, size_t count, unsigned long *result, int base); + +int read_file(const char *path, char *buf, size_t count, size_t *len); +int write_file(const char *path, const char *buf, size_t count); +int read_file_alloc(const char *path, char **buf, size_t *len); +int read_long(const char *path, long *result, int base); +int write_long(const char *path, long result, int base); +int read_ulong(const char *path, unsigned long *result, int base); +int write_ulong(const char *path, unsigned long result, int base); +int read_debugfs_file(const char *debugfs_file, char *buf, size_t count); +int write_debugfs_file(const char *debugfs_file, const char *buf, size_t count); +int read_debugfs_int(const char *debugfs_file, int *result); +int write_debugfs_int(const char *debugfs_file, int result); int read_sysfs_file(char *debugfs_file, char *result, size_t result_size); int perf_event_open_counter(unsigned int type, unsigned long config, int group_fd); diff --git a/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c index 095195a25687..4de079923ccb 100644 --- a/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c +++ b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c @@ -143,54 +143,6 @@ int gzip_header_blank(char *buf) return i; } -/* Caller must free the allocated buffer return nonzero on error. */ -int read_alloc_input_file(char *fname, char **buf, size_t *bufsize) -{ - struct stat statbuf; - FILE *fp; - char *p; - size_t num_bytes; - - if (stat(fname, &statbuf)) { - perror(fname); - return(-1); - } - fp = fopen(fname, "r"); - if (fp == NULL) { - perror(fname); - return(-1); - } - assert(NULL != (p = (char *) malloc(statbuf.st_size))); - num_bytes = fread(p, 1, statbuf.st_size, fp); - if (ferror(fp) || (num_bytes != statbuf.st_size)) { - perror(fname); - return(-1); - } - *buf = p; - *bufsize = num_bytes; - return 0; -} - -/* Returns nonzero on error */ -int write_output_file(char *fname, char *buf, size_t bufsize) -{ - FILE *fp; - size_t num_bytes; - - fp = fopen(fname, "w"); - if (fp == NULL) { - perror(fname); - return(-1); - } - num_bytes = fwrite(buf, 1, bufsize, fp); - if (ferror(fp) || (num_bytes != bufsize)) { - perror(fname); - return(-1); - } - fclose(fp); - return 0; -} - /* * Z_SYNC_FLUSH as described in zlib.h. * Returns number of appended bytes @@ -257,7 +209,7 @@ int compress_file(int argc, char **argv, void *handle) fprintf(stderr, "usage: %s <fname>\n", argv[0]); exit(-1); } - if (read_alloc_input_file(argv[1], &inbuf, &inlen)) + if (read_file_alloc(argv[1], &inbuf, &inlen)) exit(-1); fprintf(stderr, "file %s read, %ld bytes\n", argv[1], inlen); @@ -399,7 +351,7 @@ int compress_file(int argc, char **argv, void *handle) assert(FNAME_MAX > (strlen(argv[1]) + strlen(FEXT))); strcpy(outname, argv[1]); strcat(outname, FEXT); - if (write_output_file(outname, outbuf, dsttotlen)) { + if (write_file(outname, outbuf, dsttotlen)) { fprintf(stderr, "write error: %s\n", outname); exit(-1); } diff --git a/tools/testing/selftests/powerpc/pmu/lib.c b/tools/testing/selftests/powerpc/pmu/lib.c index 88690b97b7b9..719f94f10d41 100644 --- a/tools/testing/selftests/powerpc/pmu/lib.c +++ b/tools/testing/selftests/powerpc/pmu/lib.c @@ -190,38 +190,14 @@ int parse_proc_maps(void) bool require_paranoia_below(int level) { + int err; long current; - char *end, buf[16]; - FILE *f; - bool rc; - - rc = false; - - f = fopen(PARANOID_PATH, "r"); - if (!f) { - perror("fopen"); - goto out; - } - if (!fgets(buf, sizeof(buf), f)) { - printf("Couldn't read " PARANOID_PATH "?\n"); - goto out_close; - } - - current = strtol(buf, &end, 10); - - if (end == buf) { + err = read_long(PARANOID_PATH, ¤t, 10); + if (err) { printf("Couldn't parse " PARANOID_PATH "?\n"); - goto out_close; + return false; } - if (current >= level) - goto out_close; - - rc = true; -out_close: - fclose(f); -out: - return rc; + return current < level; } - diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile index 2f02cb54224d..cbeeaeae8837 100644 --- a/tools/testing/selftests/powerpc/ptrace/Makefile +++ b/tools/testing/selftests/powerpc/ptrace/Makefile @@ -33,7 +33,7 @@ TESTS_64 := $(patsubst %,$(OUTPUT)/%,$(TESTS_64)) $(TESTS_64): CFLAGS += -m64 $(TM_TESTS): CFLAGS += -I../tm -mhtm -CFLAGS += -I../../../../../usr/include -fno-pie +CFLAGS += $(KHDR_INCLUDES) -fno-pie $(OUTPUT)/ptrace-gpr: ptrace-gpr.S $(OUTPUT)/ptrace-pkey $(OUTPUT)/core-pkey: LDLIBS += -pthread diff --git a/tools/testing/selftests/powerpc/ptrace/core-pkey.c b/tools/testing/selftests/powerpc/ptrace/core-pkey.c index 4e8d0ce1ff58..f6f8596ce8e1 100644 --- a/tools/testing/selftests/powerpc/ptrace/core-pkey.c +++ b/tools/testing/selftests/powerpc/ptrace/core-pkey.c @@ -348,15 +348,11 @@ static int parent(struct shared_info *info, pid_t pid) static int write_core_pattern(const char *core_pattern) { - size_t len = strlen(core_pattern), ret; - FILE *f; + int err; - f = fopen(core_pattern_file, "w"); - SKIP_IF_MSG(!f, "Try with root privileges"); - - ret = fwrite(core_pattern, 1, len, f); - fclose(f); - if (ret != len) { + err = write_file(core_pattern_file, core_pattern, strlen(core_pattern)); + if (err) { + SKIP_IF_MSG(err == -EPERM, "Try with root privileges"); perror("Error writing to core_pattern file"); return TEST_FAIL; } @@ -366,8 +362,8 @@ static int write_core_pattern(const char *core_pattern) static int setup_core_pattern(char **core_pattern_, bool *changed_) { - FILE *f; char *core_pattern; + size_t len; int ret; core_pattern = malloc(PATH_MAX); @@ -376,22 +372,14 @@ static int setup_core_pattern(char **core_pattern_, bool *changed_) return TEST_FAIL; } - f = fopen(core_pattern_file, "r"); - if (!f) { - perror("Error opening core_pattern file"); - ret = TEST_FAIL; - goto out; - } - - ret = fread(core_pattern, 1, PATH_MAX - 1, f); - fclose(f); - if (!ret) { + ret = read_file(core_pattern_file, core_pattern, PATH_MAX - 1, &len); + if (ret) { perror("Error reading core_pattern file"); ret = TEST_FAIL; goto out; } - core_pattern[ret] = '\0'; + core_pattern[len] = '\0'; /* Check whether we can predict the name of the core file. */ if (!strcmp(core_pattern, "core") || !strcmp(core_pattern, "core.%p")) diff --git a/tools/testing/selftests/powerpc/security/Makefile b/tools/testing/selftests/powerpc/security/Makefile index 7488315fd847..e0d979ab0204 100644 --- a/tools/testing/selftests/powerpc/security/Makefile +++ b/tools/testing/selftests/powerpc/security/Makefile @@ -5,7 +5,7 @@ TEST_PROGS := mitigation-patching.sh top_srcdir = ../../../../.. -CFLAGS += -I../../../../../usr/include +CFLAGS += $(KHDR_INCLUDES) include ../../lib.mk diff --git a/tools/testing/selftests/powerpc/security/entry_flush.c b/tools/testing/selftests/powerpc/security/entry_flush.c index 68ce377b205e..e01c573deadd 100644 --- a/tools/testing/selftests/powerpc/security/entry_flush.c +++ b/tools/testing/selftests/powerpc/security/entry_flush.c @@ -34,18 +34,18 @@ int entry_flush_test(void) // The PMU event we use only works on Power7 or later SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); - if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) { + if (read_debugfs_int("powerpc/rfi_flush", &rfi_flush_orig) < 0) { perror("Unable to read powerpc/rfi_flush debugfs file"); SKIP_IF(1); } - if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) { + if (read_debugfs_int("powerpc/entry_flush", &entry_flush_orig) < 0) { perror("Unable to read powerpc/entry_flush debugfs file"); SKIP_IF(1); } if (rfi_flush_orig != 0) { - if (write_debugfs_file("powerpc/rfi_flush", 0) < 0) { + if (write_debugfs_int("powerpc/rfi_flush", 0) < 0) { perror("error writing to powerpc/rfi_flush debugfs file"); FAIL_IF(1); } @@ -105,7 +105,7 @@ again: if (entry_flush == entry_flush_orig) { entry_flush = !entry_flush_orig; - if (write_debugfs_file("powerpc/entry_flush", entry_flush) < 0) { + if (write_debugfs_int("powerpc/entry_flush", entry_flush) < 0) { perror("error writing to powerpc/entry_flush debugfs file"); return 1; } @@ -120,12 +120,12 @@ again: set_dscr(0); - if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) { + if (write_debugfs_int("powerpc/rfi_flush", rfi_flush_orig) < 0) { perror("unable to restore original value of powerpc/rfi_flush debugfs file"); return 1; } - if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) { + if (write_debugfs_int("powerpc/entry_flush", entry_flush_orig) < 0) { perror("unable to restore original value of powerpc/entry_flush debugfs file"); return 1; } diff --git a/tools/testing/selftests/powerpc/security/rfi_flush.c b/tools/testing/selftests/powerpc/security/rfi_flush.c index f73484a6470f..6bedc86443a6 100644 --- a/tools/testing/selftests/powerpc/security/rfi_flush.c +++ b/tools/testing/selftests/powerpc/security/rfi_flush.c @@ -34,18 +34,18 @@ int rfi_flush_test(void) // The PMU event we use only works on Power7 or later SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); - if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) { + if (read_debugfs_int("powerpc/rfi_flush", &rfi_flush_orig) < 0) { perror("Unable to read powerpc/rfi_flush debugfs file"); SKIP_IF(1); } - if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) { + if (read_debugfs_int("powerpc/entry_flush", &entry_flush_orig) < 0) { have_entry_flush = 0; } else { have_entry_flush = 1; if (entry_flush_orig != 0) { - if (write_debugfs_file("powerpc/entry_flush", 0) < 0) { + if (write_debugfs_int("powerpc/entry_flush", 0) < 0) { perror("error writing to powerpc/entry_flush debugfs file"); return 1; } @@ -105,7 +105,7 @@ again: if (rfi_flush == rfi_flush_orig) { rfi_flush = !rfi_flush_orig; - if (write_debugfs_file("powerpc/rfi_flush", rfi_flush) < 0) { + if (write_debugfs_int("powerpc/rfi_flush", rfi_flush) < 0) { perror("error writing to powerpc/rfi_flush debugfs file"); return 1; } @@ -120,13 +120,13 @@ again: set_dscr(0); - if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) { + if (write_debugfs_int("powerpc/rfi_flush", rfi_flush_orig) < 0) { perror("unable to restore original value of powerpc/rfi_flush debugfs file"); return 1; } if (have_entry_flush) { - if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) { + if (write_debugfs_int("powerpc/entry_flush", entry_flush_orig) < 0) { perror("unable to restore original value of powerpc/entry_flush " "debugfs file"); return 1; diff --git a/tools/testing/selftests/powerpc/security/uaccess_flush.c b/tools/testing/selftests/powerpc/security/uaccess_flush.c index cf80f960e38a..fcf23ea9b183 100644 --- a/tools/testing/selftests/powerpc/security/uaccess_flush.c +++ b/tools/testing/selftests/powerpc/security/uaccess_flush.c @@ -36,30 +36,30 @@ int uaccess_flush_test(void) // The PMU event we use only works on Power7 or later SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); - if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) { + if (read_debugfs_int("powerpc/rfi_flush", &rfi_flush_orig) < 0) { perror("Unable to read powerpc/rfi_flush debugfs file"); SKIP_IF(1); } - if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) { + if (read_debugfs_int("powerpc/entry_flush", &entry_flush_orig) < 0) { perror("Unable to read powerpc/entry_flush debugfs file"); SKIP_IF(1); } - if (read_debugfs_file("powerpc/uaccess_flush", &uaccess_flush_orig) < 0) { + if (read_debugfs_int("powerpc/uaccess_flush", &uaccess_flush_orig) < 0) { perror("Unable to read powerpc/entry_flush debugfs file"); SKIP_IF(1); } if (rfi_flush_orig != 0) { - if (write_debugfs_file("powerpc/rfi_flush", 0) < 0) { + if (write_debugfs_int("powerpc/rfi_flush", 0) < 0) { perror("error writing to powerpc/rfi_flush debugfs file"); FAIL_IF(1); } } if (entry_flush_orig != 0) { - if (write_debugfs_file("powerpc/entry_flush", 0) < 0) { + if (write_debugfs_int("powerpc/entry_flush", 0) < 0) { perror("error writing to powerpc/entry_flush debugfs file"); FAIL_IF(1); } @@ -119,7 +119,7 @@ again: if (uaccess_flush == uaccess_flush_orig) { uaccess_flush = !uaccess_flush_orig; - if (write_debugfs_file("powerpc/uaccess_flush", uaccess_flush) < 0) { + if (write_debugfs_int("powerpc/uaccess_flush", uaccess_flush) < 0) { perror("error writing to powerpc/uaccess_flush debugfs file"); return 1; } @@ -134,17 +134,17 @@ again: set_dscr(0); - if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) { + if (write_debugfs_int("powerpc/rfi_flush", rfi_flush_orig) < 0) { perror("unable to restore original value of powerpc/rfi_flush debugfs file"); return 1; } - if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) { + if (write_debugfs_int("powerpc/entry_flush", entry_flush_orig) < 0) { perror("unable to restore original value of powerpc/entry_flush debugfs file"); return 1; } - if (write_debugfs_file("powerpc/uaccess_flush", uaccess_flush_orig) < 0) { + if (write_debugfs_int("powerpc/uaccess_flush", uaccess_flush_orig) < 0) { perror("unable to restore original value of powerpc/uaccess_flush debugfs file"); return 1; } diff --git a/tools/testing/selftests/powerpc/syscalls/Makefile b/tools/testing/selftests/powerpc/syscalls/Makefile index b63f8459c704..ee1740ddfb0c 100644 --- a/tools/testing/selftests/powerpc/syscalls/Makefile +++ b/tools/testing/selftests/powerpc/syscalls/Makefile @@ -1,9 +1,9 @@ # SPDX-License-Identifier: GPL-2.0-only TEST_GEN_PROGS := ipc_unmuxed rtas_filter -CFLAGS += -I../../../../../usr/include +CFLAGS += $(KHDR_INCLUDES) top_srcdir = ../../../../.. include ../../lib.mk -$(TEST_GEN_PROGS): ../harness.c +$(TEST_GEN_PROGS): ../harness.c ../utils.c diff --git a/tools/testing/selftests/powerpc/syscalls/rtas_filter.c b/tools/testing/selftests/powerpc/syscalls/rtas_filter.c index 03b487f18d00..9b17780f0b18 100644 --- a/tools/testing/selftests/powerpc/syscalls/rtas_filter.c +++ b/tools/testing/selftests/powerpc/syscalls/rtas_filter.c @@ -8,6 +8,7 @@ #include <byteswap.h> #include <stdint.h> #include <inttypes.h> +#include <linux/limits.h> #include <stdio.h> #include <string.h> #include <sys/syscall.h> @@ -50,70 +51,16 @@ struct region { struct region *next; }; -int read_entire_file(int fd, char **buf, size_t *len) -{ - size_t buf_size = 0; - size_t off = 0; - int rc; - - *buf = NULL; - do { - buf_size += BLOCK_SIZE; - if (*buf == NULL) - *buf = malloc(buf_size); - else - *buf = realloc(*buf, buf_size); - - if (*buf == NULL) - return -ENOMEM; - - rc = read(fd, *buf + off, BLOCK_SIZE); - if (rc < 0) - return -EIO; - - off += rc; - } while (rc == BLOCK_SIZE); - - if (len) - *len = off; - - return 0; -} - -static int open_prop_file(const char *prop_path, const char *prop_name, int *fd) -{ - char *path; - int len; - - /* allocate enough for two string, a slash and trailing NULL */ - len = strlen(prop_path) + strlen(prop_name) + 1 + 1; - path = malloc(len); - if (path == NULL) - return -ENOMEM; - - snprintf(path, len, "%s/%s", prop_path, prop_name); - - *fd = open(path, O_RDONLY); - free(path); - if (*fd < 0) - return -errno; - - return 0; -} - static int get_property(const char *prop_path, const char *prop_name, char **prop_val, size_t *prop_len) { - int rc, fd; - - rc = open_prop_file(prop_path, prop_name, &fd); - if (rc) - return rc; + char path[PATH_MAX]; - rc = read_entire_file(fd, prop_val, prop_len); - close(fd); + int len = snprintf(path, sizeof(path), "%s/%s", prop_path, prop_name); + if (len < 0 || len >= sizeof(path)) + return -ENOMEM; - return rc; + return read_file_alloc(path, prop_val, prop_len); } int rtas_token(const char *call_name) @@ -138,22 +85,14 @@ err: static int read_kregion_bounds(struct region *kregion) { char *buf; - int fd; - int rc; + int err; - fd = open("/proc/ppc64/rtas/rmo_buffer", O_RDONLY); - if (fd < 0) { - printf("Could not open rmo_buffer file\n"); + err = read_file_alloc("/proc/ppc64/rtas/rmo_buffer", &buf, NULL); + if (err) { + perror("Could not open rmo_buffer file"); return RTAS_IO_ASSERT; } - rc = read_entire_file(fd, &buf, NULL); - close(fd); - if (rc) { - free(buf); - return rc; - } - sscanf(buf, "%" SCNx64 " %x", &kregion->addr, &kregion->size); free(buf); diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index 5881e97c73c1..3876805c2f31 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -17,7 +17,7 @@ $(TEST_GEN_PROGS): ../harness.c ../utils.c CFLAGS += -mhtm $(OUTPUT)/tm-syscall: tm-syscall-asm.S -$(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include +$(OUTPUT)/tm-syscall: CFLAGS += $(KHDR_INCLUDES) $(OUTPUT)/tm-tmspr: CFLAGS += -pthread $(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64 $(OUTPUT)/tm-resched-dscr: ../pmu/lib.c diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c index 1f36ee1a909a..7c8cfedb012a 100644 --- a/tools/testing/selftests/powerpc/utils.c +++ b/tools/testing/selftests/powerpc/utils.c @@ -8,6 +8,8 @@ #include <elf.h> #include <errno.h> #include <fcntl.h> +#include <inttypes.h> +#include <limits.h> #include <link.h> #include <sched.h> #include <stdio.h> @@ -26,34 +28,360 @@ static char auxv[4096]; -int read_auxv(char *buf, ssize_t buf_size) +int read_file(const char *path, char *buf, size_t count, size_t *len) { - ssize_t num; - int rc, fd; + ssize_t rc; + int fd; + int err; + char eof; - fd = open("/proc/self/auxv", O_RDONLY); - if (fd == -1) { - perror("open"); + fd = open(path, O_RDONLY); + if (fd < 0) return -errno; + + rc = read(fd, buf, count); + if (rc < 0) { + err = -errno; + goto out; } - num = read(fd, buf, buf_size); - if (num < 0) { - perror("read"); - rc = -EIO; + if (len) + *len = rc; + + /* Overflow if there are still more bytes after filling the buffer */ + if (rc == count) { + rc = read(fd, &eof, 1); + if (rc != 0) { + err = -EOVERFLOW; + goto out; + } + } + + err = 0; + +out: + close(fd); + errno = -err; + return err; +} + +int read_file_alloc(const char *path, char **buf, size_t *len) +{ + size_t read_offset = 0; + size_t buffer_len = 0; + char *buffer = NULL; + int err; + int fd; + + fd = open(path, O_RDONLY); + if (fd < 0) + return -errno; + + /* + * We don't use stat & preallocate st_size because some non-files + * report 0 file size. Instead just dynamically grow the buffer + * as needed. + */ + while (1) { + ssize_t rc; + + if (read_offset >= buffer_len / 2) { + char *next_buffer; + + buffer_len = buffer_len ? buffer_len * 2 : 4096; + next_buffer = realloc(buffer, buffer_len); + if (!next_buffer) { + err = -errno; + goto out; + } + buffer = next_buffer; + } + + rc = read(fd, buffer + read_offset, buffer_len - read_offset); + if (rc < 0) { + err = -errno; + goto out; + } + + if (rc == 0) + break; + + read_offset += rc; + } + + *buf = buffer; + if (len) + *len = read_offset; + + err = 0; + +out: + close(fd); + if (err) + free(buffer); + errno = -err; + return err; +} + +int write_file(const char *path, const char *buf, size_t count) +{ + int fd; + int err; + ssize_t rc; + + fd = open(path, O_WRONLY | O_CREAT | O_TRUNC, 0644); + if (fd < 0) + return -errno; + + rc = write(fd, buf, count); + if (rc < 0) { + err = -errno; goto out; } - if (num > buf_size) { - printf("overflowed auxv buffer\n"); - rc = -EOVERFLOW; + if (rc != count) { + err = -EOVERFLOW; goto out; } - rc = 0; + err = 0; + out: close(fd); - return rc; + errno = -err; + return err; +} + +int read_auxv(char *buf, ssize_t buf_size) +{ + int err; + + err = read_file("/proc/self/auxv", buf, buf_size, NULL); + if (err) { + perror("Error reading /proc/self/auxv"); + return err; + } + + return 0; +} + +int read_debugfs_file(const char *subpath, char *buf, size_t count) +{ + char path[PATH_MAX] = "/sys/kernel/debug/"; + + strncat(path, subpath, sizeof(path) - strlen(path) - 1); + + return read_file(path, buf, count, NULL); +} + +int write_debugfs_file(const char *subpath, const char *buf, size_t count) +{ + char path[PATH_MAX] = "/sys/kernel/debug/"; + + strncat(path, subpath, sizeof(path) - strlen(path) - 1); + + return write_file(path, buf, count); +} + +static int validate_int_parse(const char *buffer, size_t count, char *end) +{ + int err = 0; + + /* Require at least one digit */ + if (end == buffer) { + err = -EINVAL; + goto out; + } + + /* Require all remaining characters be whitespace-ish */ + for (; end < buffer + count; end++) { + if (*end == '\0') + break; + + if (*end != ' ' && *end != '\n') { + err = -EINVAL; + goto out; + } + } + +out: + errno = -err; + return err; +} + +static int parse_bounded_int(const char *buffer, size_t count, intmax_t *result, + int base, intmax_t min, intmax_t max) +{ + int err; + char *end; + + errno = 0; + *result = strtoimax(buffer, &end, base); + + if (errno) + return -errno; + + err = validate_int_parse(buffer, count, end); + if (err) + goto out; + + if (*result < min || *result > max) + err = -EOVERFLOW; + +out: + errno = -err; + return err; +} + +static int parse_bounded_uint(const char *buffer, size_t count, uintmax_t *result, + int base, uintmax_t max) +{ + int err = 0; + char *end; + + errno = 0; + *result = strtoumax(buffer, &end, base); + + if (errno) + return -errno; + + err = validate_int_parse(buffer, count, end); + if (err) + goto out; + + if (*result > max) + err = -EOVERFLOW; + +out: + errno = -err; + return err; +} + +int parse_intmax(const char *buffer, size_t count, intmax_t *result, int base) +{ + return parse_bounded_int(buffer, count, result, base, INTMAX_MIN, INTMAX_MAX); +} + +int parse_uintmax(const char *buffer, size_t count, uintmax_t *result, int base) +{ + return parse_bounded_uint(buffer, count, result, base, UINTMAX_MAX); +} + +int parse_int(const char *buffer, size_t count, int *result, int base) +{ + intmax_t parsed; + int err = parse_bounded_int(buffer, count, &parsed, base, INT_MIN, INT_MAX); + + *result = parsed; + return err; +} + +int parse_uint(const char *buffer, size_t count, unsigned int *result, int base) +{ + uintmax_t parsed; + int err = parse_bounded_uint(buffer, count, &parsed, base, UINT_MAX); + + *result = parsed; + return err; +} + +int parse_long(const char *buffer, size_t count, long *result, int base) +{ + intmax_t parsed; + int err = parse_bounded_int(buffer, count, &parsed, base, LONG_MIN, LONG_MAX); + + *result = parsed; + return err; +} + +int parse_ulong(const char *buffer, size_t count, unsigned long *result, int base) +{ + uintmax_t parsed; + int err = parse_bounded_uint(buffer, count, &parsed, base, ULONG_MAX); + + *result = parsed; + return err; +} + +int read_long(const char *path, long *result, int base) +{ + int err; + char buffer[32] = {0}; + + err = read_file(path, buffer, sizeof(buffer) - 1, NULL); + if (err) + return err; + + return parse_long(buffer, sizeof(buffer), result, base); +} + +int read_ulong(const char *path, unsigned long *result, int base) +{ + int err; + char buffer[32] = {0}; + + err = read_file(path, buffer, sizeof(buffer) - 1, NULL); + if (err) + return err; + + return parse_ulong(buffer, sizeof(buffer), result, base); +} + +int write_long(const char *path, long result, int base) +{ + int err; + int len; + char buffer[32]; + + /* Decimal only for now: no format specifier for signed hex values */ + if (base != 10) { + err = -EINVAL; + goto out; + } + + len = snprintf(buffer, sizeof(buffer), "%ld", result); + if (len < 0 || len >= sizeof(buffer)) { + err = -EOVERFLOW; + goto out; + } + + err = write_file(path, buffer, len); + +out: + errno = -err; + return err; +} + +int write_ulong(const char *path, unsigned long result, int base) +{ + int err; + int len; + char buffer[32]; + char *fmt; + + switch (base) { + case 10: + fmt = "%lu"; + break; + case 16: + fmt = "%lx"; + break; + default: + err = -EINVAL; + goto out; + } + + len = snprintf(buffer, sizeof(buffer), fmt, result); + if (len < 0 || len >= sizeof(buffer)) { + err = -errno; + goto out; + } + + err = write_file(path, buffer, len); + +out: + errno = -err; + return err; } void *find_auxv_entry(int type, char *auxv) @@ -142,65 +470,31 @@ bool is_ppc64le(void) int read_sysfs_file(char *fpath, char *result, size_t result_size) { char path[PATH_MAX] = "/sys/"; - int rc = -1, fd; strncat(path, fpath, PATH_MAX - strlen(path) - 1); - if ((fd = open(path, O_RDONLY)) < 0) - return rc; - - rc = read(fd, result, result_size); - - close(fd); - - if (rc < 0) - return rc; - - return 0; + return read_file(path, result, result_size, NULL); } -int read_debugfs_file(char *debugfs_file, int *result) +int read_debugfs_int(const char *debugfs_file, int *result) { - int rc = -1, fd; - char path[PATH_MAX]; - char value[16]; - - strcpy(path, "/sys/kernel/debug/"); - strncat(path, debugfs_file, PATH_MAX - strlen(path) - 1); + int err; + char value[16] = {0}; - if ((fd = open(path, O_RDONLY)) < 0) - return rc; + err = read_debugfs_file(debugfs_file, value, sizeof(value) - 1); + if (err) + return err; - if ((rc = read(fd, value, sizeof(value))) < 0) - return rc; - - value[15] = 0; - *result = atoi(value); - close(fd); - - return 0; + return parse_int(value, sizeof(value), result, 10); } -int write_debugfs_file(char *debugfs_file, int result) +int write_debugfs_int(const char *debugfs_file, int result) { - int rc = -1, fd; - char path[PATH_MAX]; char value[16]; - strcpy(path, "/sys/kernel/debug/"); - strncat(path, debugfs_file, PATH_MAX - strlen(path) - 1); - - if ((fd = open(path, O_WRONLY)) < 0) - return rc; - snprintf(value, 16, "%d", result); - if ((rc = write(fd, value, strlen(value))) < 0) - return rc; - - close(fd); - - return 0; + return write_debugfs_file(debugfs_file, value, strlen(value)); } static long perf_event_open(struct perf_event_attr *hw_event, pid_t pid, diff --git a/tools/testing/selftests/prctl/.gitignore b/tools/testing/selftests/prctl/.gitignore index 91af2b631bc9..7a657b25f686 100644 --- a/tools/testing/selftests/prctl/.gitignore +++ b/tools/testing/selftests/prctl/.gitignore @@ -2,3 +2,4 @@ disable-tsc-ctxt-sw-stress-test disable-tsc-on-off-stress-test disable-tsc-test +set-anon-vma-name-test diff --git a/tools/testing/selftests/prctl/Makefile b/tools/testing/selftests/prctl/Makefile index c7923b205222..c058b81eeb41 100644 --- a/tools/testing/selftests/prctl/Makefile +++ b/tools/testing/selftests/prctl/Makefile @@ -5,7 +5,7 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) ifeq ($(ARCH),x86) TEST_PROGS := disable-tsc-ctxt-sw-stress-test disable-tsc-on-off-stress-test \ - disable-tsc-test + disable-tsc-test set-anon-vma-name-test all: $(TEST_PROGS) include ../lib.mk diff --git a/tools/testing/selftests/prctl/config b/tools/testing/selftests/prctl/config new file mode 100644 index 000000000000..c6ed03c544e5 --- /dev/null +++ b/tools/testing/selftests/prctl/config @@ -0,0 +1 @@ +CONFIG_ANON_VMA_NAME=y diff --git a/tools/testing/selftests/prctl/set-anon-vma-name-test.c b/tools/testing/selftests/prctl/set-anon-vma-name-test.c new file mode 100644 index 000000000000..26d853c5a0c1 --- /dev/null +++ b/tools/testing/selftests/prctl/set-anon-vma-name-test.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This test covers the anonymous VMA naming functionality through prctl calls + */ + +#include <errno.h> +#include <sys/prctl.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/mman.h> +#include <string.h> + +#include "../kselftest_harness.h" + +#define AREA_SIZE 1024 + +#define GOOD_NAME "goodname" +#define BAD_NAME "badname\1" + +#ifndef PR_SET_VMA +#define PR_SET_VMA 0x53564d41 +#define PR_SET_VMA_ANON_NAME 0 +#endif + + +int rename_vma(unsigned long addr, unsigned long size, char *name) +{ + int res; + + res = prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME, addr, size, name); + if (res < 0) + return -errno; + return res; +} + +int was_renaming_successful(char *target_name, unsigned long ptr) +{ + FILE *maps_file; + + char line_buf[512], name[128], mode[8]; + unsigned long start_addr, end_addr, offset; + unsigned int major_id, minor_id, node_id; + + char target_buf[128]; + int res = 0, sscanf_res; + + // The entry name in maps will be in format [anon:<target_name>] + sprintf(target_buf, "[anon:%s]", target_name); + maps_file = fopen("/proc/self/maps", "r"); + if (!maps_file) { + printf("## /proc/self/maps file opening error\n"); + return 0; + } + + // Parse the maps file to find the entry we renamed + while (fgets(line_buf, sizeof(line_buf), maps_file)) { + sscanf_res = sscanf(line_buf, "%lx-%lx %7s %lx %u:%u %u %s", &start_addr, + &end_addr, mode, &offset, &major_id, + &minor_id, &node_id, name); + if (sscanf_res == EOF) { + res = 0; + printf("## EOF while parsing the maps file\n"); + break; + } + if (!strcmp(name, target_buf) && start_addr == ptr) { + res = 1; + break; + } + } + fclose(maps_file); + return res; +} + +FIXTURE(vma) { + void *ptr_anon, *ptr_not_anon; +}; + +FIXTURE_SETUP(vma) { + self->ptr_anon = mmap(NULL, AREA_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, 0, 0); + ASSERT_NE(self->ptr_anon, NULL); + self->ptr_not_anon = mmap(NULL, AREA_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE, 0, 0); + ASSERT_NE(self->ptr_not_anon, NULL); +} + +FIXTURE_TEARDOWN(vma) { + munmap(self->ptr_anon, AREA_SIZE); + munmap(self->ptr_not_anon, AREA_SIZE); +} + +TEST_F(vma, renaming) { + TH_LOG("Try to rename the VMA with correct parameters"); + EXPECT_GE(rename_vma((unsigned long)self->ptr_anon, AREA_SIZE, GOOD_NAME), 0); + EXPECT_TRUE(was_renaming_successful(GOOD_NAME, (unsigned long)self->ptr_anon)); + + TH_LOG("Try to pass invalid name (with non-printable character \\1) to rename the VMA"); + EXPECT_EQ(rename_vma((unsigned long)self->ptr_anon, AREA_SIZE, BAD_NAME), -EINVAL); + + TH_LOG("Try to rename non-anonynous VMA"); + EXPECT_EQ(rename_vma((unsigned long) self->ptr_not_anon, AREA_SIZE, GOOD_NAME), -EINVAL); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/proc/proc-uptime-001.c b/tools/testing/selftests/proc/proc-uptime-001.c index 781f7a50fc3f..f335eec5067e 100644 --- a/tools/testing/selftests/proc/proc-uptime-001.c +++ b/tools/testing/selftests/proc/proc-uptime-001.c @@ -13,7 +13,9 @@ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ -// Test that values in /proc/uptime increment monotonically. +// Test that boottime value in /proc/uptime and CLOCK_BOOTTIME increment +// monotonically. We don't test idle time monotonicity due to broken iowait +// task counting, cf: comment above get_cpu_idle_time_us() #undef NDEBUG #include <assert.h> #include <stdint.h> @@ -25,20 +27,31 @@ int main(void) { - uint64_t start, u0, u1, i0, i1; + uint64_t start, u0, u1, c0, c1; int fd; fd = open("/proc/uptime", O_RDONLY); assert(fd >= 0); - proc_uptime(fd, &u0, &i0); + u0 = proc_uptime(fd); start = u0; + c0 = clock_boottime(); + do { - proc_uptime(fd, &u1, &i1); + u1 = proc_uptime(fd); + c1 = clock_boottime(); + + /* Is /proc/uptime monotonic ? */ assert(u1 >= u0); - assert(i1 >= i0); + + /* Is CLOCK_BOOTTIME monotonic ? */ + assert(c1 >= c0); + + /* Is CLOCK_BOOTTIME VS /proc/uptime monotonic ? */ + assert(c0 >= u0); + u0 = u1; - i0 = i1; + c0 = c1; } while (u1 - start < 100); return 0; diff --git a/tools/testing/selftests/proc/proc-uptime-002.c b/tools/testing/selftests/proc/proc-uptime-002.c index 7d0aa22bdc12..ae453daa96c1 100644 --- a/tools/testing/selftests/proc/proc-uptime-002.c +++ b/tools/testing/selftests/proc/proc-uptime-002.c @@ -13,8 +13,10 @@ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ -// Test that values in /proc/uptime increment monotonically -// while shifting across CPUs. +// Test that boottime value in /proc/uptime and CLOCK_BOOTTIME increment +// monotonically while shifting across CPUs. We don't test idle time +// monotonicity due to broken iowait task counting, cf: comment above +// get_cpu_idle_time_us() #undef NDEBUG #include <assert.h> #include <errno.h> @@ -42,10 +44,10 @@ static inline int sys_sched_setaffinity(pid_t pid, unsigned int len, unsigned lo int main(void) { + uint64_t u0, u1, c0, c1; unsigned int len; unsigned long *m; unsigned int cpu; - uint64_t u0, u1, i0, i1; int fd; /* find out "nr_cpu_ids" */ @@ -60,7 +62,9 @@ int main(void) fd = open("/proc/uptime", O_RDONLY); assert(fd >= 0); - proc_uptime(fd, &u0, &i0); + u0 = proc_uptime(fd); + c0 = clock_boottime(); + for (cpu = 0; cpu < len * 8; cpu++) { memset(m, 0, len); m[cpu / (8 * sizeof(unsigned long))] |= 1UL << (cpu % (8 * sizeof(unsigned long))); @@ -68,11 +72,20 @@ int main(void) /* CPU might not exist, ignore error */ sys_sched_setaffinity(0, len, m); - proc_uptime(fd, &u1, &i1); + u1 = proc_uptime(fd); + c1 = clock_boottime(); + + /* Is /proc/uptime monotonic ? */ assert(u1 >= u0); - assert(i1 >= i0); + + /* Is CLOCK_BOOTTIME monotonic ? */ + assert(c1 >= c0); + + /* Is CLOCK_BOOTTIME VS /proc/uptime monotonic ? */ + assert(c0 >= u0); + u0 = u1; - i0 = i1; + c0 = c1; } return 0; diff --git a/tools/testing/selftests/proc/proc-uptime.h b/tools/testing/selftests/proc/proc-uptime.h index dc6a42b1d6b0..730cce4a3d73 100644 --- a/tools/testing/selftests/proc/proc-uptime.h +++ b/tools/testing/selftests/proc/proc-uptime.h @@ -19,10 +19,22 @@ #include <string.h> #include <stdlib.h> #include <unistd.h> +#include <time.h> #include "proc.h" -static void proc_uptime(int fd, uint64_t *uptime, uint64_t *idle) +static uint64_t clock_boottime(void) +{ + struct timespec ts; + int err; + + err = clock_gettime(CLOCK_BOOTTIME, &ts); + assert(err >= 0); + + return (ts.tv_sec * 100) + (ts.tv_nsec / 10000000); +} + +static uint64_t proc_uptime(int fd) { uint64_t val1, val2; char buf[64], *p; @@ -43,18 +55,6 @@ static void proc_uptime(int fd, uint64_t *uptime, uint64_t *idle) assert(p[3] == ' '); val2 = (p[1] - '0') * 10 + p[2] - '0'; - *uptime = val1 * 100 + val2; - - p += 4; - - val1 = xstrtoull(p, &p); - assert(p[0] == '.'); - assert('0' <= p[1] && p[1] <= '9'); - assert('0' <= p[2] && p[2] <= '9'); - assert(p[3] == '\n'); - - val2 = (p[1] - '0') * 10 + p[2] - '0'; - *idle = val1 * 100 + val2; - assert(p + 4 == buf + rv); + return val1 * 100 + val2; } diff --git a/tools/testing/selftests/ptrace/.gitignore b/tools/testing/selftests/ptrace/.gitignore index 792318aaa30c..b7dde152e75a 100644 --- a/tools/testing/selftests/ptrace/.gitignore +++ b/tools/testing/selftests/ptrace/.gitignore @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only get_syscall_info +get_set_sud peeksiginfo vmaccess diff --git a/tools/testing/selftests/ptrace/Makefile b/tools/testing/selftests/ptrace/Makefile index 96ffa94afb91..1c631740a730 100644 --- a/tools/testing/selftests/ptrace/Makefile +++ b/tools/testing/selftests/ptrace/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only CFLAGS += -std=c99 -pthread -Wall $(KHDR_INCLUDES) -TEST_GEN_PROGS := get_syscall_info peeksiginfo vmaccess +TEST_GEN_PROGS := get_syscall_info peeksiginfo vmaccess get_set_sud include ../lib.mk diff --git a/tools/testing/selftests/ptrace/get_set_sud.c b/tools/testing/selftests/ptrace/get_set_sud.c new file mode 100644 index 000000000000..5297b10d25c3 --- /dev/null +++ b/tools/testing/selftests/ptrace/get_set_sud.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include "../kselftest_harness.h" +#include <stdio.h> +#include <string.h> +#include <errno.h> +#include <sys/wait.h> +#include <sys/syscall.h> +#include <sys/prctl.h> + +#include "linux/ptrace.h" + +static int sys_ptrace(int request, pid_t pid, void *addr, void *data) +{ + return syscall(SYS_ptrace, request, pid, addr, data); +} + +TEST(get_set_sud) +{ + struct ptrace_sud_config config; + pid_t child; + int ret = 0; + int status; + + child = fork(); + ASSERT_GE(child, 0); + if (child == 0) { + ASSERT_EQ(0, sys_ptrace(PTRACE_TRACEME, 0, 0, 0)) { + TH_LOG("PTRACE_TRACEME: %m"); + } + kill(getpid(), SIGSTOP); + _exit(1); + } + + waitpid(child, &status, 0); + + memset(&config, 0xff, sizeof(config)); + config.mode = PR_SYS_DISPATCH_ON; + + ret = sys_ptrace(PTRACE_GET_SYSCALL_USER_DISPATCH_CONFIG, child, + (void *)sizeof(config), &config); + + ASSERT_EQ(ret, 0); + ASSERT_EQ(config.mode, PR_SYS_DISPATCH_OFF); + ASSERT_EQ(config.selector, 0); + ASSERT_EQ(config.offset, 0); + ASSERT_EQ(config.len, 0); + + config.mode = PR_SYS_DISPATCH_ON; + config.selector = 0; + config.offset = 0x400000; + config.len = 0x1000; + + ret = sys_ptrace(PTRACE_SET_SYSCALL_USER_DISPATCH_CONFIG, child, + (void *)sizeof(config), &config); + + ASSERT_EQ(ret, 0); + + memset(&config, 1, sizeof(config)); + ret = sys_ptrace(PTRACE_GET_SYSCALL_USER_DISPATCH_CONFIG, child, + (void *)sizeof(config), &config); + + ASSERT_EQ(ret, 0); + ASSERT_EQ(config.mode, PR_SYS_DISPATCH_ON); + ASSERT_EQ(config.selector, 0); + ASSERT_EQ(config.offset, 0x400000); + ASSERT_EQ(config.len, 0x1000); + + kill(child, SIGKILL); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/ptrace/peeksiginfo.c b/tools/testing/selftests/ptrace/peeksiginfo.c index 54900657eb44..a6884f66dc01 100644 --- a/tools/testing/selftests/ptrace/peeksiginfo.c +++ b/tools/testing/selftests/ptrace/peeksiginfo.c @@ -151,7 +151,7 @@ out: int main(int argc, char *argv[]) { - siginfo_t siginfo[SIGNR]; + siginfo_t siginfo; int i, exit_code = 1; sigset_t blockmask; pid_t child; @@ -176,13 +176,13 @@ int main(int argc, char *argv[]) /* Send signals in process-wide and per-thread queues */ for (i = 0; i < SIGNR; i++) { - siginfo->si_code = TEST_SICODE_SHARE; - siginfo->si_int = i; - sys_rt_sigqueueinfo(child, SIGRTMIN, siginfo); + siginfo.si_code = TEST_SICODE_SHARE; + siginfo.si_int = i; + sys_rt_sigqueueinfo(child, SIGRTMIN, &siginfo); - siginfo->si_code = TEST_SICODE_PRIV; - siginfo->si_int = i; - sys_rt_tgsigqueueinfo(child, child, SIGRTMIN, siginfo); + siginfo.si_code = TEST_SICODE_PRIV; + siginfo.si_int = i; + sys_rt_tgsigqueueinfo(child, child, SIGRTMIN, &siginfo); } if (sys_ptrace(PTRACE_ATTACH, child, NULL, NULL) == -1) diff --git a/tools/testing/selftests/rcutorture/bin/kvm-again.sh b/tools/testing/selftests/rcutorture/bin/kvm-again.sh index 8a968fbda02c..88ca4e368489 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-again.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-again.sh @@ -193,7 +193,7 @@ do qemu_cmd_dir="`dirname "$i"`" kernel_dir="`echo $qemu_cmd_dir | sed -e 's/\.[0-9]\+$//'`" jitter_dir="`dirname "$kernel_dir"`" - kvm-transform.sh "$kernel_dir/bzImage" "$qemu_cmd_dir/console.log" "$jitter_dir" $dur "$bootargs" < $T/qemu-cmd > $i + kvm-transform.sh "$kernel_dir/bzImage" "$qemu_cmd_dir/console.log" "$jitter_dir" "$dur" "$bootargs" < $T/qemu-cmd > $i if test -n "$arg_remote" then echo "# TORTURE_KCONFIG_GDB_ARG=''" >> $i diff --git a/tools/testing/selftests/rcutorture/bin/srcu_lockdep.sh b/tools/testing/selftests/rcutorture/bin/srcu_lockdep.sh new file mode 100755 index 000000000000..2e63ef009d59 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/srcu_lockdep.sh @@ -0,0 +1,78 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Run SRCU-lockdep tests and report any that fail to meet expectations. +# +# Copyright (C) 2021 Meta Platforms, Inc. +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +usage () { + echo "Usage: $scriptname optional arguments:" + echo " --datestamp string" + exit 1 +} + +ds=`date +%Y.%m.%d-%H.%M.%S`-srcu_lockdep +scriptname="$0" + +T="`mktemp -d ${TMPDIR-/tmp}/srcu_lockdep.sh.XXXXXX`" +trap 'rm -rf $T' 0 + +RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE +PATH=${RCUTORTURE}/bin:$PATH; export PATH +. functions.sh + +while test $# -gt 0 +do + case "$1" in + --datestamp) + checkarg --datestamp "(relative pathname)" "$#" "$2" '^[a-zA-Z0-9._/-]*$' '^--' + ds=$2 + shift + ;; + *) + echo Unknown argument $1 + usage + ;; + esac + shift +done + +err= +nerrs=0 +for d in 0 1 +do + for t in 0 1 2 + do + for c in 1 2 3 + do + err= + val=$((d*1000+t*10+c)) + tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration 5s --configs "SRCU-P" --bootargs "rcutorture.test_srcu_lockdep=$val" --trust-make --datestamp "$ds/$val" > "$T/kvm.sh.out" 2>&1 + ret=$? + mv "$T/kvm.sh.out" "$RCUTORTURE/res/$ds/$val" + if test "$d" -ne 0 && test "$ret" -eq 0 + then + err=1 + echo -n Unexpected success for > "$RCUTORTURE/res/$ds/$val/kvm.sh.err" + fi + if test "$d" -eq 0 && test "$ret" -ne 0 + then + err=1 + echo -n Unexpected failure for > "$RCUTORTURE/res/$ds/$val/kvm.sh.err" + fi + if test -n "$err" + then + grep "rcu_torture_init_srcu_lockdep: test_srcu_lockdep = " "$RCUTORTURE/res/$ds/$val/SRCU-P/console.log" | sed -e 's/^.*rcu_torture_init_srcu_lockdep://' >> "$RCUTORTURE/res/$ds/$val/kvm.sh.err" + cat "$RCUTORTURE/res/$ds/$val/kvm.sh.err" + nerrs=$((nerrs+1)) + fi + done + done +done +if test "$nerrs" -ne 0 +then + exit 1 +fi +exit 0 diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh index 130d0de4c3bb..5a2ae2264403 100755 --- a/tools/testing/selftests/rcutorture/bin/torture.sh +++ b/tools/testing/selftests/rcutorture/bin/torture.sh @@ -497,16 +497,16 @@ fi if test "$do_clocksourcewd" = "yes" then - torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000" + torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 tsc=watchdog" torture_set "clocksourcewd-1" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration 45s --configs TREE03 --kconfig "CONFIG_TEST_CLOCKSOURCE_WATCHDOG=y" --trust-make - torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 clocksource.max_cswd_read_retries=1" + torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 clocksource.max_cswd_read_retries=1 tsc=watchdog" torture_set "clocksourcewd-2" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration 45s --configs TREE03 --kconfig "CONFIG_TEST_CLOCKSOURCE_WATCHDOG=y" --trust-make # In case our work is already done... if test "$do_rcutorture" != "yes" then - torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000" + torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 tsc=watchdog" torture_set "clocksourcewd-3" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration 45s --configs TREE03 --trust-make fi fi diff --git a/tools/testing/selftests/rcutorture/configs/lock/CFLIST b/tools/testing/selftests/rcutorture/configs/lock/CFLIST index 41bae5824339..28e23d05d5a5 100644 --- a/tools/testing/selftests/rcutorture/configs/lock/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/lock/CFLIST @@ -5,3 +5,5 @@ LOCK04 LOCK05 LOCK06 LOCK07 +LOCK08 +LOCK09 diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK08 b/tools/testing/selftests/rcutorture/configs/lock/LOCK08 new file mode 100644 index 000000000000..1d1da1477fc3 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK08 @@ -0,0 +1,6 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=4 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK08.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK08.boot new file mode 100644 index 000000000000..b8b6caebb89e --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK08.boot @@ -0,0 +1 @@ +locktorture.torture_type=mutex_lock locktorture.nested_locks=8 diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK09 b/tools/testing/selftests/rcutorture/configs/lock/LOCK09 new file mode 100644 index 000000000000..1d1da1477fc3 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK09 @@ -0,0 +1,6 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=4 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK09.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK09.boot new file mode 100644 index 000000000000..fd5eff148a93 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK09.boot @@ -0,0 +1 @@ +locktorture.torture_type=rtmutex_lock locktorture.nested_locks=8 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 index 8ae41d5f81a3..04831ef1f9b5 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 @@ -15,3 +15,4 @@ CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_BOOTPARAM_HOTPLUG_CPU0=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 index ae395981b5e5..dc4985064b3a 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 @@ -15,3 +15,4 @@ CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y CONFIG_RCU_EQS_DEBUG=y +CONFIG_RCU_LAZY=y diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt index 42acb1a64ce1..3f5fb66f16df 100644 --- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt +++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt @@ -71,9 +71,5 @@ CONFIG_TASKS_RCU These are controlled by CONFIG_PREEMPT and/or CONFIG_SMP. -CONFIG_SRCU - - Selected by CONFIG_RCU_TORTURE_TEST, so cannot disable. - boot parameters ignored: TBD diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index 68ff856d36f0..8a4fe8693be6 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -48,7 +48,7 @@ static int perf_event_open_llc_miss(pid_t pid, int cpu_no) return 0; } -static int initialize_llc_perf(void) +static void initialize_llc_perf(void) { memset(&pea_llc_miss, 0, sizeof(struct perf_event_attr)); memset(&rf_cqm, 0, sizeof(struct read_format)); @@ -59,8 +59,6 @@ static int initialize_llc_perf(void) pea_llc_miss.config = PERF_COUNT_HW_CACHE_MISSES; rf_cqm.nr = 1; - - return 0; } static int reset_enable_llc_perf(pid_t pid, int cpu_no) @@ -79,7 +77,7 @@ static int reset_enable_llc_perf(pid_t pid, int cpu_no) /* * get_llc_perf: llc cache miss through perf events - * @cpu_no: CPU number that the benchmark PID is binded to + * @llc_perf_miss: LLC miss counter that is filled on success * * Perf events like HW_CACHE_MISSES could be used to validate number of * cache lines allocated. @@ -234,20 +232,19 @@ int cat_val(struct resctrl_val_param *param) if (ret) return ret; - if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR))) { - ret = initialize_llc_perf(); - if (ret) - return ret; - } + if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR))) + initialize_llc_perf(); /* Test runs until the callback setup() tells the test to stop. */ while (1) { if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR))) { ret = param->setup(1, param); - if (ret) { + if (ret == END_OF_TESTS) { ret = 0; break; } + if (ret < 0) + break; ret = reset_enable_llc_perf(bm_pid, param->cpu_no); if (ret) break; diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index 1c5e90c63254..fb1443f888c4 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -40,7 +40,7 @@ static int cat_setup(int num, ...) /* Run NUM_OF_RUNS times */ if (p->num_of_runs >= NUM_OF_RUNS) - return -1; + return END_OF_TESTS; if (p->num_of_runs == 0) { sprintf(schemata, "%lx", p->mask); @@ -103,7 +103,6 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) unsigned long l_mask, l_mask_1; int ret, pipefd[2], sibling_cpu_no; char pipe_message; - pid_t bm_pid; cache_size = 0; @@ -145,7 +144,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) struct resctrl_val_param param = { .resctrl_val = CAT_STR, .cpu_no = cpu_no, - .mum_resctrlfs = 0, + .mum_resctrlfs = false, .setup = cat_setup, }; @@ -167,6 +166,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) return errno; } + fflush(stdout); bm_pid = fork(); /* Set param values for child thread which will be allocated bitmask @@ -180,28 +180,31 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) strcpy(param.filename, RESULT_FILE_NAME1); param.num_of_runs = 0; param.cpu_no = sibling_cpu_no; + } else { + ret = signal_handler_register(); + if (ret) { + kill(bm_pid, SIGKILL); + goto out; + } } remove(param.filename); ret = cat_val(¶m); - if (ret) - return ret; - - ret = check_results(¶m); - if (ret) - return ret; + if (ret == 0) + ret = check_results(¶m); if (bm_pid == 0) { /* Tell parent that child is ready */ close(pipefd[0]); pipe_message = 1; if (write(pipefd[1], &pipe_message, sizeof(pipe_message)) < - sizeof(pipe_message)) { - close(pipefd[1]); + sizeof(pipe_message)) + /* + * Just print the error message. + * Let while(1) run and wait for itself to be killed. + */ perror("# failed signaling parent process"); - return errno; - } close(pipefd[1]); while (1) @@ -219,11 +222,13 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) } close(pipefd[0]); kill(bm_pid, SIGKILL); + signal_handler_unregister(); } +out: cat_test_cleanup(); if (bm_pid) umount_resctrlfs(); - return 0; + return ret; } diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index 8968e36db99d..af71b2141271 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -32,7 +32,7 @@ static int cmt_setup(int num, ...) /* Run NUM_OF_RUNS times */ if (p->num_of_runs >= NUM_OF_RUNS) - return -1; + return END_OF_TESTS; p->num_of_runs++; @@ -82,12 +82,11 @@ void cmt_test_cleanup(void) int cmt_resctrl_val(int cpu_no, int n, char **benchmark_cmd) { - int ret, mum_resctrlfs; + int ret; cache_size = 0; - mum_resctrlfs = 1; - ret = remount_resctrlfs(mum_resctrlfs); + ret = remount_resctrlfs(true); if (ret) return ret; @@ -118,7 +117,7 @@ int cmt_resctrl_val(int cpu_no, int n, char **benchmark_cmd) .ctrlgrp = "c1", .mongrp = "m1", .cpu_no = cpu_no, - .mum_resctrlfs = 0, + .mum_resctrlfs = false, .filename = RESULT_FILE_NAME, .mask = ~(long_mask << n) & long_mask, .span = cache_size * n / count_of_bits, @@ -133,13 +132,12 @@ int cmt_resctrl_val(int cpu_no, int n, char **benchmark_cmd) ret = resctrl_val(benchmark_cmd, ¶m); if (ret) - return ret; + goto out; ret = check_results(¶m, n); - if (ret) - return ret; +out: cmt_test_cleanup(); - return 0; + return ret; } diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c index 56ccbeae0638..341cc93ca84c 100644 --- a/tools/testing/selftests/resctrl/fill_buf.c +++ b/tools/testing/selftests/resctrl/fill_buf.c @@ -14,7 +14,6 @@ #include <sys/types.h> #include <sys/wait.h> #include <inttypes.h> -#include <malloc.h> #include <string.h> #include "resctrl.h" @@ -33,14 +32,6 @@ static void sb(void) #endif } -static void ctrl_handler(int signo) -{ - free(startptr); - printf("\nEnding\n"); - sb(); - exit(EXIT_SUCCESS); -} - static void cl_flush(void *p) { #if defined(__i386) || defined(__x86_64) @@ -64,10 +55,14 @@ static void mem_flush(void *p, size_t s) static void *malloc_and_init_memory(size_t s) { + void *p = NULL; uint64_t *p64; size_t s64; + int ret; - void *p = memalign(PAGE_SIZE, s); + ret = posix_memalign(&p, PAGE_SIZE, s); + if (ret < 0) + return NULL; p64 = (uint64_t *)p; s64 = s / sizeof(uint64_t); @@ -198,12 +193,6 @@ int run_fill_buf(unsigned long span, int malloc_and_init_memory, unsigned long long cache_size = span; int ret; - /* set up ctrl-c handler */ - if (signal(SIGINT, ctrl_handler) == SIG_ERR) - printf("Failed to catch SIGINT!\n"); - if (signal(SIGHUP, ctrl_handler) == SIG_ERR) - printf("Failed to catch SIGHUP!\n"); - ret = fill_cache(cache_size, malloc_and_init_memory, memflush, op, resctrl_val); if (ret) { diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index 1a1bdb6180cf..cde3781a9ab0 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -28,6 +28,7 @@ static int mba_setup(int num, ...) struct resctrl_val_param *p; char allocation_str[64]; va_list param; + int ret; va_start(param, num); p = va_arg(param, struct resctrl_val_param *); @@ -41,20 +42,24 @@ static int mba_setup(int num, ...) return 0; if (allocation < ALLOCATION_MIN || allocation > ALLOCATION_MAX) - return -1; + return END_OF_TESTS; sprintf(allocation_str, "%d", allocation); - write_schemata(p->ctrlgrp, allocation_str, p->cpu_no, p->resctrl_val); + ret = write_schemata(p->ctrlgrp, allocation_str, p->cpu_no, + p->resctrl_val); + if (ret < 0) + return ret; + allocation -= ALLOCATION_STEP; return 0; } -static void show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc) +static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc) { int allocation, runs; - bool failed = false; + bool ret = false; ksft_print_msg("Results are displayed in (MB)\n"); /* Memory bandwidth from 100% down to 10% */ @@ -90,13 +95,15 @@ static void show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc) ksft_print_msg("avg_bw_imc: %lu\n", avg_bw_imc); ksft_print_msg("avg_bw_resc: %lu\n", avg_bw_resc); if (avg_diff_per > MAX_DIFF_PERCENT) - failed = true; + ret = true; } ksft_print_msg("%s Check schemata change using MBA\n", - failed ? "Fail:" : "Pass:"); - if (failed) + ret ? "Fail:" : "Pass:"); + if (ret) ksft_print_msg("At least one test failed\n"); + + return ret; } static int check_results(void) @@ -132,9 +139,7 @@ static int check_results(void) fclose(fp); - show_mba_info(bw_imc, bw_resc); - - return 0; + return show_mba_info(bw_imc, bw_resc); } void mba_test_cleanup(void) @@ -149,7 +154,7 @@ int mba_schemata_change(int cpu_no, char *bw_report, char **benchmark_cmd) .ctrlgrp = "c1", .mongrp = "m1", .cpu_no = cpu_no, - .mum_resctrlfs = 1, + .mum_resctrlfs = true, .filename = RESULT_FILE_NAME, .bw_report = bw_report, .setup = mba_setup @@ -160,13 +165,12 @@ int mba_schemata_change(int cpu_no, char *bw_report, char **benchmark_cmd) ret = resctrl_val(benchmark_cmd, ¶m); if (ret) - return ret; + goto out; ret = check_results(); - if (ret) - return ret; +out: mba_test_cleanup(); - return 0; + return ret; } diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c index 8392e5c55ed0..538d35a6485a 100644 --- a/tools/testing/selftests/resctrl/mbm_test.c +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -89,23 +89,24 @@ static int check_results(int span) static int mbm_setup(int num, ...) { struct resctrl_val_param *p; - static int num_of_runs; va_list param; int ret = 0; - /* Run NUM_OF_RUNS times */ - if (num_of_runs++ >= NUM_OF_RUNS) - return -1; - va_start(param, num); p = va_arg(param, struct resctrl_val_param *); va_end(param); + /* Run NUM_OF_RUNS times */ + if (p->num_of_runs >= NUM_OF_RUNS) + return END_OF_TESTS; + /* Set up shemata with 100% allocation on the first run. */ - if (num_of_runs == 0) + if (p->num_of_runs == 0) ret = write_schemata(p->ctrlgrp, "100", p->cpu_no, p->resctrl_val); + p->num_of_runs++; + return ret; } @@ -122,7 +123,7 @@ int mbm_bw_change(int span, int cpu_no, char *bw_report, char **benchmark_cmd) .mongrp = "m1", .span = span, .cpu_no = cpu_no, - .mum_resctrlfs = 1, + .mum_resctrlfs = true, .filename = RESULT_FILE_NAME, .bw_report = bw_report, .setup = mbm_setup @@ -133,13 +134,12 @@ int mbm_bw_change(int span, int cpu_no, char *bw_report, char **benchmark_cmd) ret = resctrl_val(benchmark_cmd, ¶m); if (ret) - return ret; + goto out; ret = check_results(span); - if (ret) - return ret; +out: mbm_test_cleanup(); - return 0; + return ret; } diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index f0ded31fb3c7..87e39456dee0 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -28,7 +28,7 @@ #define MB (1024 * 1024) #define RESCTRL_PATH "/sys/fs/resctrl" #define PHYS_ID_PATH "/sys/devices/system/cpu/cpu" -#define CBM_MASK_PATH "/sys/fs/resctrl/info" +#define INFO_PATH "/sys/fs/resctrl/info" #define L3_PATH "/sys/fs/resctrl/info/L3" #define MB_PATH "/sys/fs/resctrl/info/MB" #define L3_MON_PATH "/sys/fs/resctrl/info/L3_MON" @@ -37,6 +37,8 @@ #define ARCH_INTEL 1 #define ARCH_AMD 2 +#define END_OF_TESTS 1 + #define PARENT_EXIT(err_msg) \ do { \ perror(err_msg); \ @@ -62,7 +64,7 @@ struct resctrl_val_param { char mongrp[64]; int cpu_no; unsigned long span; - int mum_resctrlfs; + bool mum_resctrlfs; char filename[64]; char *bw_report; unsigned long mask; @@ -107,6 +109,8 @@ void mba_test_cleanup(void); int get_cbm_mask(char *cache_type, char *cbm_mask); int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size); void ctrlc_handler(int signum, siginfo_t *info, void *ptr); +int signal_handler_register(void); +void signal_handler_unregister(void); int cat_val(struct resctrl_val_param *param); void cat_test_cleanup(void); int cat_perf_miss_val(int cpu_no, int no_of_bits, char *cache_type); diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c index df0d8d8526fc..9b9751206e1c 100644 --- a/tools/testing/selftests/resctrl/resctrl_tests.c +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -77,7 +77,7 @@ static void run_mbm_test(bool has_ben, char **benchmark_cmd, int span, ksft_print_msg("Starting MBM BW change ...\n"); - if (!validate_resctrl_feature_request(MBM_STR)) { + if (!validate_resctrl_feature_request(MBM_STR) || (get_vendor() != ARCH_INTEL)) { ksft_test_result_skip("Hardware does not support MBM or MBM is disabled\n"); return; } @@ -88,7 +88,6 @@ static void run_mbm_test(bool has_ben, char **benchmark_cmd, int span, ksft_test_result(!res, "MBM: bw change\n"); if ((get_vendor() == ARCH_INTEL) && res) ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); - mbm_test_cleanup(); } static void run_mba_test(bool has_ben, char **benchmark_cmd, int span, @@ -98,7 +97,7 @@ static void run_mba_test(bool has_ben, char **benchmark_cmd, int span, ksft_print_msg("Starting MBA Schemata change ...\n"); - if (!validate_resctrl_feature_request(MBA_STR)) { + if (!validate_resctrl_feature_request(MBA_STR) || (get_vendor() != ARCH_INTEL)) { ksft_test_result_skip("Hardware does not support MBA or MBA is disabled\n"); return; } @@ -107,7 +106,6 @@ static void run_mba_test(bool has_ben, char **benchmark_cmd, int span, sprintf(benchmark_cmd[1], "%d", span); res = mba_schemata_change(cpu_no, bw_report, benchmark_cmd); ksft_test_result(!res, "MBA: schemata change\n"); - mba_test_cleanup(); } static void run_cmt_test(bool has_ben, char **benchmark_cmd, int cpu_no) @@ -126,7 +124,6 @@ static void run_cmt_test(bool has_ben, char **benchmark_cmd, int cpu_no) ksft_test_result(!res, "CMT: test\n"); if ((get_vendor() == ARCH_INTEL) && res) ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); - cmt_test_cleanup(); } static void run_cat_test(int cpu_no, int no_of_bits) @@ -142,7 +139,6 @@ static void run_cat_test(int cpu_no, int no_of_bits) res = cat_perf_miss_val(cpu_no, no_of_bits, "L3"); ksft_test_result(!res, "CAT: test\n"); - cat_test_cleanup(); } int main(int argc, char **argv) @@ -258,10 +254,10 @@ int main(int argc, char **argv) ksft_set_plan(tests ? : 4); - if ((get_vendor() == ARCH_INTEL) && mbm_test) + if (mbm_test) run_mbm_test(has_ben, benchmark_cmd, span, cpu_no, bw_report); - if ((get_vendor() == ARCH_INTEL) && mba_test) + if (mba_test) run_mba_test(has_ben, benchmark_cmd, span, cpu_no, bw_report); if (cmt_test) @@ -272,5 +268,5 @@ int main(int argc, char **argv) umount_resctrlfs(); - return ksft_exit_pass(); + ksft_finished(); } diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index b32b96356ec7..ab1eab1e7ff6 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -477,6 +477,45 @@ void ctrlc_handler(int signum, siginfo_t *info, void *ptr) } /* + * Register CTRL-C handler for parent, as it has to kill + * child process before exiting. + */ +int signal_handler_register(void) +{ + struct sigaction sigact; + int ret = 0; + + sigact.sa_sigaction = ctrlc_handler; + sigemptyset(&sigact.sa_mask); + sigact.sa_flags = SA_SIGINFO; + if (sigaction(SIGINT, &sigact, NULL) || + sigaction(SIGTERM, &sigact, NULL) || + sigaction(SIGHUP, &sigact, NULL)) { + perror("# sigaction"); + ret = -1; + } + return ret; +} + +/* + * Reset signal handler to SIG_DFL. + * Non-Value return because the caller should keep + * the error code of other path even if sigaction fails. + */ +void signal_handler_unregister(void) +{ + struct sigaction sigact; + + sigact.sa_handler = SIG_DFL; + sigemptyset(&sigact.sa_mask); + if (sigaction(SIGINT, &sigact, NULL) || + sigaction(SIGTERM, &sigact, NULL) || + sigaction(SIGHUP, &sigact, NULL)) { + perror("# sigaction"); + } +} + +/* * print_results_bw: the memory bandwidth results are stored in a file * @filename: file that stores the results * @bm_pid: child pid that runs benchmark @@ -629,6 +668,7 @@ int resctrl_val(char **benchmark_cmd, struct resctrl_val_param *param) * Fork to start benchmark, save child's pid so that it can be killed * when needed */ + fflush(stdout); bm_pid = fork(); if (bm_pid == -1) { perror("# Unable to fork"); @@ -670,39 +710,28 @@ int resctrl_val(char **benchmark_cmd, struct resctrl_val_param *param) ksft_print_msg("Benchmark PID: %d\n", bm_pid); - /* - * Register CTRL-C handler for parent, as it has to kill benchmark - * before exiting - */ - sigact.sa_sigaction = ctrlc_handler; - sigemptyset(&sigact.sa_mask); - sigact.sa_flags = SA_SIGINFO; - if (sigaction(SIGINT, &sigact, NULL) || - sigaction(SIGTERM, &sigact, NULL) || - sigaction(SIGHUP, &sigact, NULL)) { - perror("# sigaction"); - ret = errno; + ret = signal_handler_register(); + if (ret) goto out; - } value.sival_ptr = benchmark_cmd; /* Taskset benchmark to specified cpu */ ret = taskset_benchmark(bm_pid, param->cpu_no); if (ret) - goto out; + goto unregister; /* Write benchmark to specified control&monitoring grp in resctrl FS */ ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp, resctrl_val); if (ret) - goto out; + goto unregister; if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) || !strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) { ret = initialize_mem_bw_imc(); if (ret) - goto out; + goto unregister; initialize_mem_bw_resctrl(param->ctrlgrp, param->mongrp, param->cpu_no, resctrl_val); @@ -717,7 +746,7 @@ int resctrl_val(char **benchmark_cmd, struct resctrl_val_param *param) sizeof(pipe_message)) { perror("# failed reading message from child process"); close(pipefd[0]); - goto out; + goto unregister; } } close(pipefd[0]); @@ -726,7 +755,7 @@ int resctrl_val(char **benchmark_cmd, struct resctrl_val_param *param) if (sigqueue(bm_pid, SIGUSR1, value) == -1) { perror("# sigqueue SIGUSR1 to child"); ret = errno; - goto out; + goto unregister; } /* Give benchmark enough time to fully run */ @@ -734,32 +763,29 @@ int resctrl_val(char **benchmark_cmd, struct resctrl_val_param *param) /* Test runs until the callback setup() tells the test to stop. */ while (1) { + ret = param->setup(1, param); + if (ret == END_OF_TESTS) { + ret = 0; + break; + } + if (ret < 0) + break; + if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) || !strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) { - ret = param->setup(1, param); - if (ret) { - ret = 0; - break; - } - ret = measure_vals(param, &bw_resc_start); if (ret) break; } else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) { - ret = param->setup(1, param); - if (ret) { - ret = 0; - break; - } sleep(1); ret = measure_cache_vals(param, bm_pid); if (ret) break; - } else { - break; } } +unregister: + signal_handler_unregister(); out: kill(bm_pid, SIGKILL); umount_resctrlfs(); diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index 6f543e470ad4..fb00245dee92 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -210,7 +210,7 @@ int get_cbm_mask(char *cache_type, char *cbm_mask) if (!cbm_mask) return -1; - sprintf(cbm_mask_path, "%s/%s/cbm_mask", CBM_MASK_PATH, cache_type); + sprintf(cbm_mask_path, "%s/%s/cbm_mask", INFO_PATH, cache_type); fp = fopen(cbm_mask_path, "r"); if (!fp) { @@ -498,6 +498,7 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val) FILE *fp; if (strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) && + strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) && strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) && strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) return -ENOENT; @@ -523,7 +524,8 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val) if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) || !strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) sprintf(schema, "%s%d%c%s", "L3:", resource_id, '=', schemata); - if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) + if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) || + !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) sprintf(schema, "%s%d%c%s", "MB:", resource_id, '=', schemata); fp = fopen(controlgroup, "w"); @@ -676,6 +678,7 @@ int filter_dmesg(void) perror("pipe"); return ret; } + fflush(stdout); pid = fork(); if (pid == 0) { close(pipefds[0]); diff --git a/tools/testing/selftests/sched/cs_prctl_test.c b/tools/testing/selftests/sched/cs_prctl_test.c index 25e0d95d3713..3e1619b6bf2d 100644 --- a/tools/testing/selftests/sched/cs_prctl_test.c +++ b/tools/testing/selftests/sched/cs_prctl_test.c @@ -334,6 +334,12 @@ int main(int argc, char *argv[]) validate(get_cs_cookie(pid) != 0); validate(get_cs_cookie(pid) == get_cs_cookie(procs[pidx].thr_tids[0])); + validate(_prctl(PR_SCHED_CORE, PR_SCHED_CORE_MAX, 0, PIDTYPE_PGID, 0) < 0 + && errno == EINVAL); + + validate(_prctl(PR_SCHED_CORE, PR_SCHED_CORE_SHARE_TO, 0, PIDTYPE_PGID, 1) < 0 + && errno == EINVAL); + if (errors) { printf("TESTS FAILED. errors: %d\n", errors); res = 10; diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 61386e499b77..43ec36b179dc 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -128,6 +128,8 @@ struct seccomp_data { # define __NR_seccomp 277 # elif defined(__csky__) # define __NR_seccomp 277 +# elif defined(__loongarch__) +# define __NR_seccomp 277 # elif defined(__hppa__) # define __NR_seccomp 338 # elif defined(__powerpc__) @@ -1755,6 +1757,10 @@ TEST_F(TRACE_poke, getpid_runs_normally) NT_ARM_SYSTEM_CALL, &__v)); \ } while (0) # define SYSCALL_RET(_regs) (_regs).regs[0] +#elif defined(__loongarch__) +# define ARCH_REGS struct user_pt_regs +# define SYSCALL_NUM(_regs) (_regs).regs[11] +# define SYSCALL_RET(_regs) (_regs).regs[4] #elif defined(__riscv) && __riscv_xlen == 64 # define ARCH_REGS struct user_regs_struct # define SYSCALL_NUM(_regs) (_regs).a7 diff --git a/tools/testing/selftests/sigaltstack/current_stack_pointer.h b/tools/testing/selftests/sigaltstack/current_stack_pointer.h new file mode 100644 index 000000000000..ea9bdf3a90b1 --- /dev/null +++ b/tools/testing/selftests/sigaltstack/current_stack_pointer.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#if __alpha__ +register unsigned long sp asm("$30"); +#elif __arm__ || __aarch64__ || __csky__ || __m68k__ || __mips__ || __riscv +register unsigned long sp asm("sp"); +#elif __i386__ +register unsigned long sp asm("esp"); +#elif __loongarch64 +register unsigned long sp asm("$sp"); +#elif __ppc__ +register unsigned long sp asm("r1"); +#elif __s390x__ +register unsigned long sp asm("%15"); +#elif __sh__ +register unsigned long sp asm("r15"); +#elif __x86_64__ +register unsigned long sp asm("rsp"); +#elif __XTENSA__ +register unsigned long sp asm("a1"); +#else +#error "implement current_stack_pointer equivalent" +#endif diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c index c53b070755b6..98d37cb744fb 100644 --- a/tools/testing/selftests/sigaltstack/sas.c +++ b/tools/testing/selftests/sigaltstack/sas.c @@ -20,6 +20,7 @@ #include <sys/auxv.h> #include "../kselftest.h" +#include "current_stack_pointer.h" #ifndef SS_AUTODISARM #define SS_AUTODISARM (1U << 31) @@ -46,12 +47,6 @@ void my_usr1(int sig, siginfo_t *si, void *u) stack_t stk; struct stk_data *p; -#if __s390x__ - register unsigned long sp asm("%15"); -#else - register unsigned long sp asm("sp"); -#endif - if (sp < (unsigned long)sstack || sp >= (unsigned long)sstack + stack_size) { ksft_exit_fail_msg("SP is not on sigaltstack\n"); diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index 0ba500056e63..8a17c0e8d82b 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -188,6 +188,80 @@ static int check_timer_create(int which) return 0; } +int remain; +__thread int got_signal; + +static void *distribution_thread(void *arg) +{ + while (__atomic_load_n(&remain, __ATOMIC_RELAXED)); + return NULL; +} + +static void distribution_handler(int nr) +{ + if (!__atomic_exchange_n(&got_signal, 1, __ATOMIC_RELAXED)) + __atomic_fetch_sub(&remain, 1, __ATOMIC_RELAXED); +} + +/* + * Test that all running threads _eventually_ receive CLOCK_PROCESS_CPUTIME_ID + * timer signals. This primarily tests that the kernel does not favour any one. + */ +static int check_timer_distribution(void) +{ + int err, i; + timer_t id; + const int nthreads = 10; + pthread_t threads[nthreads]; + struct itimerspec val = { + .it_value.tv_sec = 0, + .it_value.tv_nsec = 1000 * 1000, + .it_interval.tv_sec = 0, + .it_interval.tv_nsec = 1000 * 1000, + }; + + printf("Check timer_create() per process signal distribution... "); + fflush(stdout); + + remain = nthreads + 1; /* worker threads + this thread */ + signal(SIGALRM, distribution_handler); + err = timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id); + if (err < 0) { + perror("Can't create timer\n"); + return -1; + } + err = timer_settime(id, 0, &val, NULL); + if (err < 0) { + perror("Can't set timer\n"); + return -1; + } + + for (i = 0; i < nthreads; i++) { + if (pthread_create(&threads[i], NULL, distribution_thread, NULL)) { + perror("Can't create thread\n"); + return -1; + } + } + + /* Wait for all threads to receive the signal. */ + while (__atomic_load_n(&remain, __ATOMIC_RELAXED)); + + for (i = 0; i < nthreads; i++) { + if (pthread_join(threads[i], NULL)) { + perror("Can't join thread\n"); + return -1; + } + } + + if (timer_delete(id)) { + perror("Can't delete timer\n"); + return -1; + } + + printf("[OK]\n"); + return 0; +} + int main(int argc, char **argv) { printf("Testing posix timers. False negative may happen on CPU execution \n"); @@ -217,5 +291,8 @@ int main(int argc, char **argv) if (check_timer_create(CLOCK_PROCESS_CPUTIME_ID) < 0) return ksft_exit_fail(); + if (check_timer_distribution() < 0) + return ksft_exit_fail(); + return ksft_exit_pass(); } diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c index 625e42901237..d884fd69dd51 100644 --- a/tools/testing/selftests/x86/amx.c +++ b/tools/testing/selftests/x86/amx.c @@ -14,8 +14,10 @@ #include <sys/auxv.h> #include <sys/mman.h> #include <sys/shm.h> +#include <sys/ptrace.h> #include <sys/syscall.h> #include <sys/wait.h> +#include <sys/uio.h> #include "../kselftest.h" /* For __cpuid_count() */ @@ -583,6 +585,13 @@ static void test_dynamic_state(void) _exit(0); } +static inline int __compare_tiledata_state(struct xsave_buffer *xbuf1, struct xsave_buffer *xbuf2) +{ + return memcmp(&xbuf1->bytes[xtiledata.xbuf_offset], + &xbuf2->bytes[xtiledata.xbuf_offset], + xtiledata.size); +} + /* * Save current register state and compare it to @xbuf1.' * @@ -599,9 +608,7 @@ static inline bool __validate_tiledata_regs(struct xsave_buffer *xbuf1) fatal_error("failed to allocate XSAVE buffer\n"); xsave(xbuf2, XFEATURE_MASK_XTILEDATA); - ret = memcmp(&xbuf1->bytes[xtiledata.xbuf_offset], - &xbuf2->bytes[xtiledata.xbuf_offset], - xtiledata.size); + ret = __compare_tiledata_state(xbuf1, xbuf2); free(xbuf2); @@ -826,6 +833,99 @@ static void test_context_switch(void) free(finfo); } +/* Ptrace test */ + +/* + * Make sure the ptracee has the expanded kernel buffer on the first + * use. Then, initialize the state before performing the state + * injection from the ptracer. + */ +static inline void ptracee_firstuse_tiledata(void) +{ + load_rand_tiledata(stashed_xsave); + init_xtiledata(); +} + +/* + * Ptracer injects the randomized tile data state. It also reads + * before and after that, which will execute the kernel's state copy + * functions. So, the tester is advised to double-check any emitted + * kernel messages. + */ +static void ptracer_inject_tiledata(pid_t target) +{ + struct xsave_buffer *xbuf; + struct iovec iov; + + xbuf = alloc_xbuf(); + if (!xbuf) + fatal_error("unable to allocate XSAVE buffer"); + + printf("\tRead the init'ed tiledata via ptrace().\n"); + + iov.iov_base = xbuf; + iov.iov_len = xbuf_size; + + memset(stashed_xsave, 0, xbuf_size); + + if (ptrace(PTRACE_GETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov)) + fatal_error("PTRACE_GETREGSET"); + + if (!__compare_tiledata_state(stashed_xsave, xbuf)) + printf("[OK]\tThe init'ed tiledata was read from ptracee.\n"); + else + printf("[FAIL]\tThe init'ed tiledata was not read from ptracee.\n"); + + printf("\tInject tiledata via ptrace().\n"); + + load_rand_tiledata(xbuf); + + memcpy(&stashed_xsave->bytes[xtiledata.xbuf_offset], + &xbuf->bytes[xtiledata.xbuf_offset], + xtiledata.size); + + if (ptrace(PTRACE_SETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov)) + fatal_error("PTRACE_SETREGSET"); + + if (ptrace(PTRACE_GETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov)) + fatal_error("PTRACE_GETREGSET"); + + if (!__compare_tiledata_state(stashed_xsave, xbuf)) + printf("[OK]\tTiledata was correctly written to ptracee.\n"); + else + printf("[FAIL]\tTiledata was not correctly written to ptracee.\n"); +} + +static void test_ptrace(void) +{ + pid_t child; + int status; + + child = fork(); + if (child < 0) { + err(1, "fork"); + } else if (!child) { + if (ptrace(PTRACE_TRACEME, 0, NULL, NULL)) + err(1, "PTRACE_TRACEME"); + + ptracee_firstuse_tiledata(); + + raise(SIGTRAP); + _exit(0); + } + + do { + wait(&status); + } while (WSTOPSIG(status) != SIGTRAP); + + ptracer_inject_tiledata(child); + + ptrace(PTRACE_DETACH, child, NULL, NULL); + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + err(1, "ptrace test"); +} + int main(void) { /* Check hardware availability at first */ @@ -846,6 +946,8 @@ int main(void) ctxtswtest_config.num_threads = 5; test_context_switch(); + test_ptrace(); + clearhandler(SIGILL); free_stashed_xsave(); diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 67e9f9df3a8c..12b97c92fbb2 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -860,6 +860,199 @@ static void test_stream_poll_rcvlowat_client(const struct test_opts *opts) close(fd); } +#define INV_BUF_TEST_DATA_LEN 512 + +static void test_inv_buf_client(const struct test_opts *opts, bool stream) +{ + unsigned char data[INV_BUF_TEST_DATA_LEN] = {0}; + ssize_t ret; + int fd; + + if (stream) + fd = vsock_stream_connect(opts->peer_cid, 1234); + else + fd = vsock_seqpacket_connect(opts->peer_cid, 1234); + + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + control_expectln("SENDDONE"); + + /* Use invalid buffer here. */ + ret = recv(fd, NULL, sizeof(data), 0); + if (ret != -1) { + fprintf(stderr, "expected recv(2) failure, got %zi\n", ret); + exit(EXIT_FAILURE); + } + + if (errno != ENOMEM) { + fprintf(stderr, "unexpected recv(2) errno %d\n", errno); + exit(EXIT_FAILURE); + } + + ret = recv(fd, data, sizeof(data), MSG_DONTWAIT); + + if (stream) { + /* For SOCK_STREAM we must continue reading. */ + if (ret != sizeof(data)) { + fprintf(stderr, "expected recv(2) success, got %zi\n", ret); + exit(EXIT_FAILURE); + } + /* Don't check errno in case of success. */ + } else { + /* For SOCK_SEQPACKET socket's queue must be empty. */ + if (ret != -1) { + fprintf(stderr, "expected recv(2) failure, got %zi\n", ret); + exit(EXIT_FAILURE); + } + + if (errno != EAGAIN) { + fprintf(stderr, "unexpected recv(2) errno %d\n", errno); + exit(EXIT_FAILURE); + } + } + + control_writeln("DONE"); + + close(fd); +} + +static void test_inv_buf_server(const struct test_opts *opts, bool stream) +{ + unsigned char data[INV_BUF_TEST_DATA_LEN] = {0}; + ssize_t res; + int fd; + + if (stream) + fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + else + fd = vsock_seqpacket_accept(VMADDR_CID_ANY, 1234, NULL); + + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + res = send(fd, data, sizeof(data), 0); + if (res != sizeof(data)) { + fprintf(stderr, "unexpected send(2) result %zi\n", res); + exit(EXIT_FAILURE); + } + + control_writeln("SENDDONE"); + + control_expectln("DONE"); + + close(fd); +} + +static void test_stream_inv_buf_client(const struct test_opts *opts) +{ + test_inv_buf_client(opts, true); +} + +static void test_stream_inv_buf_server(const struct test_opts *opts) +{ + test_inv_buf_server(opts, true); +} + +static void test_seqpacket_inv_buf_client(const struct test_opts *opts) +{ + test_inv_buf_client(opts, false); +} + +static void test_seqpacket_inv_buf_server(const struct test_opts *opts) +{ + test_inv_buf_server(opts, false); +} + +#define HELLO_STR "HELLO" +#define WORLD_STR "WORLD" + +static void test_stream_virtio_skb_merge_client(const struct test_opts *opts) +{ + ssize_t res; + int fd; + + fd = vsock_stream_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + /* Send first skbuff. */ + res = send(fd, HELLO_STR, strlen(HELLO_STR), 0); + if (res != strlen(HELLO_STR)) { + fprintf(stderr, "unexpected send(2) result %zi\n", res); + exit(EXIT_FAILURE); + } + + control_writeln("SEND0"); + /* Peer reads part of first skbuff. */ + control_expectln("REPLY0"); + + /* Send second skbuff, it will be appended to the first. */ + res = send(fd, WORLD_STR, strlen(WORLD_STR), 0); + if (res != strlen(WORLD_STR)) { + fprintf(stderr, "unexpected send(2) result %zi\n", res); + exit(EXIT_FAILURE); + } + + control_writeln("SEND1"); + /* Peer reads merged skbuff packet. */ + control_expectln("REPLY1"); + + close(fd); +} + +static void test_stream_virtio_skb_merge_server(const struct test_opts *opts) +{ + unsigned char buf[64]; + ssize_t res; + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + control_expectln("SEND0"); + + /* Read skbuff partially. */ + res = recv(fd, buf, 2, 0); + if (res != 2) { + fprintf(stderr, "expected recv(2) returns 2 bytes, got %zi\n", res); + exit(EXIT_FAILURE); + } + + control_writeln("REPLY0"); + control_expectln("SEND1"); + + res = recv(fd, buf + 2, sizeof(buf) - 2, 0); + if (res != 8) { + fprintf(stderr, "expected recv(2) returns 8 bytes, got %zi\n", res); + exit(EXIT_FAILURE); + } + + res = recv(fd, buf, sizeof(buf) - 8 - 2, MSG_DONTWAIT); + if (res != -1) { + fprintf(stderr, "expected recv(2) failure, got %zi\n", res); + exit(EXIT_FAILURE); + } + + if (memcmp(buf, HELLO_STR WORLD_STR, strlen(HELLO_STR WORLD_STR))) { + fprintf(stderr, "pattern mismatch\n"); + exit(EXIT_FAILURE); + } + + control_writeln("REPLY1"); + + close(fd); +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -920,6 +1113,21 @@ static struct test_case test_cases[] = { .run_client = test_seqpacket_bigmsg_client, .run_server = test_seqpacket_bigmsg_server, }, + { + .name = "SOCK_STREAM test invalid buffer", + .run_client = test_stream_inv_buf_client, + .run_server = test_stream_inv_buf_server, + }, + { + .name = "SOCK_SEQPACKET test invalid buffer", + .run_client = test_seqpacket_inv_buf_client, + .run_server = test_seqpacket_inv_buf_server, + }, + { + .name = "SOCK_STREAM virtio skb merge", + .run_client = test_stream_virtio_skb_merge_client, + .run_server = test_stream_virtio_skb_merge_server, + }, {}, }; diff --git a/tools/virtio/.gitignore b/tools/virtio/.gitignore index 075588c4da08..9934d48d9a55 100644 --- a/tools/virtio/.gitignore +++ b/tools/virtio/.gitignore @@ -2,3 +2,4 @@ *.d virtio_test vringh_test +virtio-trace/trace-agent diff --git a/tools/virtio/Makefile b/tools/virtio/Makefile index 1b25cc7c64bb..7b7139d97d74 100644 --- a/tools/virtio/Makefile +++ b/tools/virtio/Makefile @@ -4,7 +4,7 @@ test: virtio_test vringh_test virtio_test: virtio_ring.o virtio_test.o vringh_test: vringh_test.o vringh.o virtio_ring.o -CFLAGS += -g -O2 -Werror -Wno-maybe-uninitialized -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -include ../../include/linux/kconfig.h +CFLAGS += -g -O2 -Werror -Wno-maybe-uninitialized -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -include ../../include/linux/kconfig.h -mfunction-return=thunk -fcf-protection=none -mindirect-branch-register CFLAGS += -pthread LDFLAGS += -pthread vpath %.c ../../drivers/virtio ../../drivers/vhost diff --git a/tools/virtio/virtio-trace/README b/tools/virtio/virtio-trace/README index b64845b823ab..4fb9368bf751 100644 --- a/tools/virtio/virtio-trace/README +++ b/tools/virtio/virtio-trace/README @@ -61,7 +61,7 @@ and id=channel0,name=agent-ctl-path\ ##data path## -chardev pipe,id=charchannel1,path=/tmp/virtio-trace/trace-path-cpu0\ - -device virtserialport,bus=virtio-serial0.0,nr=2,chardev=charchannel0,\ + -device virtserialport,bus=virtio-serial0.0,nr=2,chardev=charchannel1,\ id=channel1,name=trace-path-cpu0\ ... |