diff options
Diffstat (limited to 'tools')
143 files changed, 7797 insertions, 401 deletions
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index af9d9acaf997..ed5f3892674c 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -431,10 +431,11 @@ enum { /* Device Control API on vcpu fd */ #define KVM_ARM_VCPU_PMU_V3_CTRL 0 -#define KVM_ARM_VCPU_PMU_V3_IRQ 0 -#define KVM_ARM_VCPU_PMU_V3_INIT 1 -#define KVM_ARM_VCPU_PMU_V3_FILTER 2 -#define KVM_ARM_VCPU_PMU_V3_SET_PMU 3 +#define KVM_ARM_VCPU_PMU_V3_IRQ 0 +#define KVM_ARM_VCPU_PMU_V3_INIT 1 +#define KVM_ARM_VCPU_PMU_V3_FILTER 2 +#define KVM_ARM_VCPU_PMU_V3_SET_PMU 3 +#define KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS 4 #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 diff --git a/tools/arch/loongarch/include/asm/orc_types.h b/tools/arch/loongarch/include/asm/orc_types.h index caf1f71a1057..d5fa98d1d177 100644 --- a/tools/arch/loongarch/include/asm/orc_types.h +++ b/tools/arch/loongarch/include/asm/orc_types.h @@ -34,7 +34,7 @@ #define ORC_TYPE_REGS 3 #define ORC_TYPE_REGS_PARTIAL 4 -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ /* * This struct is more or less a vastly simplified version of the DWARF Call * Frame Information standard. It contains only the necessary parts of DWARF @@ -53,6 +53,6 @@ struct orc_entry { unsigned int type:3; unsigned int signal:1; }; -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* _ORC_TYPES_H */ diff --git a/tools/arch/x86/include/asm/amd/ibs.h b/tools/arch/x86/include/asm/amd/ibs.h index 300b6e0765b2..cbce54fec7b9 100644 --- a/tools/arch/x86/include/asm/amd/ibs.h +++ b/tools/arch/x86/include/asm/amd/ibs.h @@ -1,4 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_AMD_IBS_H +#define _ASM_X86_AMD_IBS_H + /* * From PPR Vol 1 for AMD Family 19h Model 01h B1 * 55898 Rev 0.35 - Feb 5, 2021 @@ -151,3 +154,5 @@ struct perf_ibs_data { }; u64 regs[MSR_AMD64_IBS_REG_COUNT_MAX]; }; + +#endif /* _ASM_X86_AMD_IBS_H */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index e02be2962a01..ee176236c2be 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -336,7 +336,7 @@ #define X86_FEATURE_AMD_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ #define X86_FEATURE_AMD_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ #define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* Single Thread Indirect Branch Predictors always-on preferred */ -#define X86_FEATURE_AMD_IBRS_SAME_MODE (13*32+19) /* Indirect Branch Restricted Speculation same mode protection*/ +#define X86_FEATURE_AMD_IBRS_SAME_MODE (13*32+19) /* Indirect Branch Restricted Speculation same mode protection*/ #define X86_FEATURE_AMD_PPIN (13*32+23) /* "amd_ppin" Protected Processor Inventory Number */ #define X86_FEATURE_AMD_SSBD (13*32+24) /* Speculative Store Bypass Disable */ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* "virt_ssbd" Virtualized Speculative Store Bypass Disable */ @@ -379,6 +379,7 @@ #define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* "v_spec_ctrl" Virtual SPEC_CTRL */ #define X86_FEATURE_VNMI (15*32+25) /* "vnmi" Virtual NMI */ #define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* SVME addr check */ +#define X86_FEATURE_BUS_LOCK_THRESHOLD (15*32+29) /* Bus lock threshold */ #define X86_FEATURE_IDLE_HLT (15*32+30) /* IDLE HLT intercept */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ @@ -447,6 +448,7 @@ #define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" SEV-ES full debug state swap support */ #define X86_FEATURE_RMPREAD (19*32+21) /* RMPREAD instruction */ #define X86_FEATURE_SEGMENTED_RMP (19*32+23) /* Segmented RMP support */ +#define X86_FEATURE_ALLOWED_SEV_FEATURES (19*32+27) /* Allowed SEV Features */ #define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */ #define X86_FEATURE_HV_INUSE_WR_ALLOWED (19*32+30) /* Allow Write to in-use hypervisor-owned pages */ @@ -458,6 +460,7 @@ #define X86_FEATURE_AUTOIBRS (20*32+ 8) /* Automatic IBRS */ #define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* SMM_CTL MSR is not present */ +#define X86_FEATURE_PREFETCHI (20*32+20) /* Prefetch Data/Instruction to Cache Level */ #define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */ #define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */ #define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */ @@ -482,7 +485,8 @@ #define X86_FEATURE_AMD_HTR_CORES (21*32+ 6) /* Heterogeneous Core Topology */ #define X86_FEATURE_AMD_WORKLOAD_CLASS (21*32+ 7) /* Workload Classification */ #define X86_FEATURE_PREFER_YMM (21*32+ 8) /* Avoid ZMM registers due to downclocking */ -#define X86_FEATURE_INDIRECT_THUNK_ITS (21*32+ 9) /* Use thunk for indirect branches in lower half of cacheline */ +#define X86_FEATURE_APX (21*32+ 9) /* Advanced Performance Extensions */ +#define X86_FEATURE_INDIRECT_THUNK_ITS (21*32+10) /* Use thunk for indirect branches in lower half of cacheline */ /* * BUG word(s) @@ -535,6 +539,8 @@ #define X86_BUG_BHI X86_BUG( 1*32+ 3) /* "bhi" CPU is affected by Branch History Injection */ #define X86_BUG_IBPB_NO_RET X86_BUG( 1*32+ 4) /* "ibpb_no_ret" IBPB omits return target predictions */ #define X86_BUG_SPECTRE_V2_USER X86_BUG( 1*32+ 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */ -#define X86_BUG_ITS X86_BUG( 1*32+ 6) /* "its" CPU is affected by Indirect Target Selection */ -#define X86_BUG_ITS_NATIVE_ONLY X86_BUG( 1*32+ 7) /* "its_native_only" CPU is affected by ITS, VMX is not affected */ +#define X86_BUG_OLD_MICROCODE X86_BUG( 1*32+ 6) /* "old_microcode" CPU has old microcode, it is surely vulnerable to something */ +#define X86_BUG_ITS X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */ +#define X86_BUG_ITS_NATIVE_ONLY X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */ + #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index e7d2f460fcc6..5cfb5d74dd5f 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -533,7 +533,7 @@ #define MSR_HWP_CAPABILITIES 0x00000771 #define MSR_HWP_REQUEST_PKG 0x00000772 #define MSR_HWP_INTERRUPT 0x00000773 -#define MSR_HWP_REQUEST 0x00000774 +#define MSR_HWP_REQUEST 0x00000774 #define MSR_HWP_STATUS 0x00000777 /* CPUID.6.EAX */ @@ -550,16 +550,16 @@ #define HWP_LOWEST_PERF(x) (((x) >> 24) & 0xff) /* IA32_HWP_REQUEST */ -#define HWP_MIN_PERF(x) (x & 0xff) -#define HWP_MAX_PERF(x) ((x & 0xff) << 8) +#define HWP_MIN_PERF(x) (x & 0xff) +#define HWP_MAX_PERF(x) ((x & 0xff) << 8) #define HWP_DESIRED_PERF(x) ((x & 0xff) << 16) -#define HWP_ENERGY_PERF_PREFERENCE(x) (((unsigned long long) x & 0xff) << 24) +#define HWP_ENERGY_PERF_PREFERENCE(x) (((u64)x & 0xff) << 24) #define HWP_EPP_PERFORMANCE 0x00 #define HWP_EPP_BALANCE_PERFORMANCE 0x80 #define HWP_EPP_BALANCE_POWERSAVE 0xC0 #define HWP_EPP_POWERSAVE 0xFF -#define HWP_ACTIVITY_WINDOW(x) ((unsigned long long)(x & 0xff3) << 32) -#define HWP_PACKAGE_CONTROL(x) ((unsigned long long)(x & 0x1) << 42) +#define HWP_ACTIVITY_WINDOW(x) ((u64)(x & 0xff3) << 32) +#define HWP_PACKAGE_CONTROL(x) ((u64)(x & 0x1) << 42) /* IA32_HWP_STATUS */ #define HWP_GUARANTEED_CHANGE(x) (x & 0x1) @@ -602,7 +602,11 @@ /* V6 PMON MSR range */ #define MSR_IA32_PMC_V6_GP0_CTR 0x1900 #define MSR_IA32_PMC_V6_GP0_CFG_A 0x1901 +#define MSR_IA32_PMC_V6_GP0_CFG_B 0x1902 +#define MSR_IA32_PMC_V6_GP0_CFG_C 0x1903 #define MSR_IA32_PMC_V6_FX0_CTR 0x1980 +#define MSR_IA32_PMC_V6_FX0_CFG_B 0x1982 +#define MSR_IA32_PMC_V6_FX0_CFG_C 0x1983 #define MSR_IA32_PMC_V6_STEP 4 /* KeyID partitioning between MKTME and TDX */ @@ -624,6 +628,7 @@ #define MSR_AMD64_OSVW_STATUS 0xc0010141 #define MSR_AMD_PPIN_CTL 0xc00102f0 #define MSR_AMD_PPIN 0xc00102f1 +#define MSR_AMD64_CPUID_FN_7 0xc0011002 #define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index b663d916f162..6f3499507c5e 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -441,6 +441,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS (1 << 6) #define KVM_X86_QUIRK_SLOT_ZAP_ALL (1 << 7) #define KVM_X86_QUIRK_STUFF_FEATURE_MSRS (1 << 8) +#define KVM_X86_QUIRK_IGNORE_GUEST_PAT (1 << 9) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 @@ -931,4 +932,74 @@ struct kvm_hyperv_eventfd { #define KVM_X86_SNP_VM 4 #define KVM_X86_TDX_VM 5 +/* Trust Domain eXtension sub-ioctl() commands. */ +enum kvm_tdx_cmd_id { + KVM_TDX_CAPABILITIES = 0, + KVM_TDX_INIT_VM, + KVM_TDX_INIT_VCPU, + KVM_TDX_INIT_MEM_REGION, + KVM_TDX_FINALIZE_VM, + KVM_TDX_GET_CPUID, + + KVM_TDX_CMD_NR_MAX, +}; + +struct kvm_tdx_cmd { + /* enum kvm_tdx_cmd_id */ + __u32 id; + /* flags for sub-commend. If sub-command doesn't use this, set zero. */ + __u32 flags; + /* + * data for each sub-command. An immediate or a pointer to the actual + * data in process virtual address. If sub-command doesn't use it, + * set zero. + */ + __u64 data; + /* + * Auxiliary error code. The sub-command may return TDX SEAMCALL + * status code in addition to -Exxx. + */ + __u64 hw_error; +}; + +struct kvm_tdx_capabilities { + __u64 supported_attrs; + __u64 supported_xfam; + __u64 reserved[254]; + + /* Configurable CPUID bits for userspace */ + struct kvm_cpuid2 cpuid; +}; + +struct kvm_tdx_init_vm { + __u64 attributes; + __u64 xfam; + __u64 mrconfigid[6]; /* sha384 digest */ + __u64 mrowner[6]; /* sha384 digest */ + __u64 mrownerconfig[6]; /* sha384 digest */ + + /* The total space for TD_PARAMS before the CPUIDs is 256 bytes */ + __u64 reserved[12]; + + /* + * Call KVM_TDX_INIT_VM before vcpu creation, thus before + * KVM_SET_CPUID2. + * This configuration supersedes KVM_SET_CPUID2s for VCPUs because the + * TDX module directly virtualizes those CPUIDs without VMM. The user + * space VMM, e.g. qemu, should make KVM_SET_CPUID2 consistent with + * those values. If it doesn't, KVM may have wrong idea of vCPUIDs of + * the guest, and KVM may wrongly emulate CPUIDs or MSRs that the TDX + * module doesn't virtualize. + */ + struct kvm_cpuid2 cpuid; +}; + +#define KVM_TDX_MEASURE_MEMORY_REGION _BITULL(0) + +struct kvm_tdx_init_mem_region { + __u64 source_addr; + __u64 gpa; + __u64 nr_pages; +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h index ec1321248dac..9c640a521a67 100644 --- a/tools/arch/x86/include/uapi/asm/svm.h +++ b/tools/arch/x86/include/uapi/asm/svm.h @@ -95,6 +95,7 @@ #define SVM_EXIT_CR14_WRITE_TRAP 0x09e #define SVM_EXIT_CR15_WRITE_TRAP 0x09f #define SVM_EXIT_INVPCID 0x0a2 +#define SVM_EXIT_BUS_LOCK 0x0a5 #define SVM_EXIT_IDLE_HLT 0x0a6 #define SVM_EXIT_NPF 0x400 #define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401 @@ -225,6 +226,7 @@ { SVM_EXIT_CR4_WRITE_TRAP, "write_cr4_trap" }, \ { SVM_EXIT_CR8_WRITE_TRAP, "write_cr8_trap" }, \ { SVM_EXIT_INVPCID, "invpcid" }, \ + { SVM_EXIT_BUS_LOCK, "buslock" }, \ { SVM_EXIT_IDLE_HLT, "idle-halt" }, \ { SVM_EXIT_NPF, "npf" }, \ { SVM_EXIT_AVIC_INCOMPLETE_IPI, "avic_incomplete_ipi" }, \ diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index a5faf6d88f1b..f0f4a4cf84a7 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -34,6 +34,7 @@ #define EXIT_REASON_TRIPLE_FAULT 2 #define EXIT_REASON_INIT_SIGNAL 3 #define EXIT_REASON_SIPI_SIGNAL 4 +#define EXIT_REASON_OTHER_SMI 6 #define EXIT_REASON_INTERRUPT_WINDOW 7 #define EXIT_REASON_NMI_WINDOW 8 @@ -92,6 +93,7 @@ #define EXIT_REASON_TPAUSE 68 #define EXIT_REASON_BUS_LOCK 74 #define EXIT_REASON_NOTIFY 75 +#define EXIT_REASON_TDCALL 77 #define VMX_EXIT_REASONS \ { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ @@ -155,7 +157,8 @@ { EXIT_REASON_UMWAIT, "UMWAIT" }, \ { EXIT_REASON_TPAUSE, "TPAUSE" }, \ { EXIT_REASON_BUS_LOCK, "BUS_LOCK" }, \ - { EXIT_REASON_NOTIFY, "NOTIFY" } + { EXIT_REASON_NOTIFY, "NOTIFY" }, \ + { EXIT_REASON_TDCALL, "TDCALL" } #define VMX_EXIT_REASON_FLAGS \ { VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" } diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 59cf6f9065aa..ccc3d923fc1e 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -40,6 +40,7 @@ SYM_FUNC_END(__memcpy) EXPORT_SYMBOL(__memcpy) SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy) +SYM_PIC_ALIAS(memcpy) EXPORT_SYMBOL(memcpy) SYM_FUNC_START_LOCAL(memcpy_orig) diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index d66b710d628f..fb5a03cf5ab7 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -42,6 +42,7 @@ SYM_FUNC_END(__memset) EXPORT_SYMBOL(__memset) SYM_FUNC_ALIAS_MEMFUNC(memset, __memset) +SYM_PIC_ALIAS(memset) EXPORT_SYMBOL(memset) SYM_FUNC_START_LOCAL(memset_orig) diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h index 14fd0ca9a6cd..7ad056219115 100644 --- a/tools/include/linux/bits.h +++ b/tools/include/linux/bits.h @@ -12,6 +12,7 @@ #define BIT_ULL_MASK(nr) (ULL(1) << ((nr) % BITS_PER_LONG_LONG)) #define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG) #define BITS_PER_BYTE 8 +#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) /* * Create a contiguous bitmask starting at bit position @l and ending at @@ -19,16 +20,68 @@ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. */ #if !defined(__ASSEMBLY__) + +/* + * Missing asm support + * + * GENMASK_U*() and BIT_U*() depend on BITS_PER_TYPE() which relies on sizeof(), + * something not available in asm. Nevertheless, fixed width integers is a C + * concept. Assembly code can rely on the long and long long versions instead. + */ + #include <linux/build_bug.h> #include <linux/compiler.h> +#include <linux/overflow.h> + #define GENMASK_INPUT_CHECK(h, l) BUILD_BUG_ON_ZERO(const_true((l) > (h))) -#else + +/* + * Generate a mask for the specified type @t. Additional checks are made to + * guarantee the value returned fits in that type, relying on + * -Wshift-count-overflow compiler check to detect incompatible arguments. + * For example, all these create build errors or warnings: + * + * - GENMASK(15, 20): wrong argument order + * - GENMASK(72, 15): doesn't fit unsigned long + * - GENMASK_U32(33, 15): doesn't fit in a u32 + */ +#define GENMASK_TYPE(t, h, l) \ + ((t)(GENMASK_INPUT_CHECK(h, l) + \ + (type_max(t) << (l) & \ + type_max(t) >> (BITS_PER_TYPE(t) - 1 - (h))))) + +#define GENMASK_U8(h, l) GENMASK_TYPE(u8, h, l) +#define GENMASK_U16(h, l) GENMASK_TYPE(u16, h, l) +#define GENMASK_U32(h, l) GENMASK_TYPE(u32, h, l) +#define GENMASK_U64(h, l) GENMASK_TYPE(u64, h, l) + +/* + * Fixed-type variants of BIT(), with additional checks like GENMASK_TYPE(). The + * following examples generate compiler warnings due to -Wshift-count-overflow: + * + * - BIT_U8(8) + * - BIT_U32(-1) + * - BIT_U32(40) + */ +#define BIT_INPUT_CHECK(type, nr) \ + BUILD_BUG_ON_ZERO(const_true((nr) >= BITS_PER_TYPE(type))) + +#define BIT_TYPE(type, nr) ((type)(BIT_INPUT_CHECK(type, nr) + BIT_ULL(nr))) + +#define BIT_U8(nr) BIT_TYPE(u8, nr) +#define BIT_U16(nr) BIT_TYPE(u16, nr) +#define BIT_U32(nr) BIT_TYPE(u32, nr) +#define BIT_U64(nr) BIT_TYPE(u64, nr) + +#else /* defined(__ASSEMBLY__) */ + /* * BUILD_BUG_ON_ZERO is not available in h files included from asm files, * disable the input check if that is the case. */ #define GENMASK_INPUT_CHECK(h, l) 0 -#endif + +#endif /* !defined(__ASSEMBLY__) */ #define GENMASK(h, l) \ (GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l)) diff --git a/tools/include/linux/build_bug.h b/tools/include/linux/build_bug.h index b4898ff085de..ab2aa97bd8ce 100644 --- a/tools/include/linux/build_bug.h +++ b/tools/include/linux/build_bug.h @@ -4,17 +4,17 @@ #include <linux/compiler.h> -#ifdef __CHECKER__ -#define BUILD_BUG_ON_ZERO(e) (0) -#else /* __CHECKER__ */ /* * Force a compilation error if condition is true, but also produce a * result (of value 0 and type int), so the expression can be used * e.g. in a structure initializer (or where-ever else comma expressions * aren't permitted). + * + * Take an error message as an optional second argument. If omitted, + * default to the stringification of the tested expression. */ -#define BUILD_BUG_ON_ZERO(e) ((int)(sizeof(struct { int:(-!!(e)); }))) -#endif /* __CHECKER__ */ +#define BUILD_BUG_ON_ZERO(e, ...) \ + __BUILD_BUG_ON_ZERO_MSG(e, ##__VA_ARGS__, #e " is true") /* Force a compilation error if a constant expression is not a power of 2 */ #define __BUILD_BUG_ON_NOT_POWER_OF_2(n) \ diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index d627e66a04a6..33411ca0cc90 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -244,6 +244,14 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s __asm__ ("" : "=r" (var) : "0" (var)) #endif +#ifndef __BUILD_BUG_ON_ZERO_MSG +#if defined(__clang__) +#define __BUILD_BUG_ON_ZERO_MSG(e, msg, ...) ((int)(sizeof(struct { int:(-!!(e)); }))) +#else +#define __BUILD_BUG_ON_ZERO_MSG(e, msg, ...) ((int)sizeof(struct {_Static_assert(!(e), msg);})) +#endif +#endif + #endif /* __ASSEMBLY__ */ #endif /* _TOOLS_LINUX_COMPILER_H */ diff --git a/tools/include/linux/kallsyms.h b/tools/include/linux/kallsyms.h index 5a37ccbec54f..f61a01dd7eb7 100644 --- a/tools/include/linux/kallsyms.h +++ b/tools/include/linux/kallsyms.h @@ -18,6 +18,7 @@ static inline const char *kallsyms_lookup(unsigned long addr, return NULL; } +#ifdef HAVE_BACKTRACE_SUPPORT #include <execinfo.h> #include <stdlib.h> static inline void print_ip_sym(const char *loglvl, unsigned long ip) @@ -30,5 +31,8 @@ static inline void print_ip_sym(const char *loglvl, unsigned long ip) free(name); } +#else +static inline void print_ip_sym(const char *loglvl, unsigned long ip) {} +#endif #endif diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 7fba37b94401..e63a71d3c607 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -905,13 +905,17 @@ struct drm_syncobj_destroy { }; #define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_IMPORT_SYNC_FILE (1 << 0) +#define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_TIMELINE (1 << 1) #define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_EXPORT_SYNC_FILE (1 << 0) +#define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_TIMELINE (1 << 1) struct drm_syncobj_handle { __u32 handle; __u32 flags; __s32 fd; __u32 pad; + + __u64 point; }; struct drm_syncobj_transfer { diff --git a/tools/include/uapi/linux/bits.h b/tools/include/uapi/linux/bits.h index 682b406e1067..a04afef9efca 100644 --- a/tools/include/uapi/linux/bits.h +++ b/tools/include/uapi/linux/bits.h @@ -4,9 +4,9 @@ #ifndef _UAPI_LINUX_BITS_H #define _UAPI_LINUX_BITS_H -#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (BITS_PER_LONG - 1 - (h)))) +#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (__BITS_PER_LONG - 1 - (h)))) -#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h)))) +#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) #define __GENMASK_U128(h, l) \ ((_BIT128((h)) << 1) - (_BIT128(l))) diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h index 7a8f4c290187..3aff99f2696a 100644 --- a/tools/include/uapi/linux/fscrypt.h +++ b/tools/include/uapi/linux/fscrypt.h @@ -119,7 +119,7 @@ struct fscrypt_key_specifier { */ struct fscrypt_provisioning_key_payload { __u32 type; - __u32 __reserved; + __u32 flags; __u8 raw[]; }; @@ -128,7 +128,9 @@ struct fscrypt_add_key_arg { struct fscrypt_key_specifier key_spec; __u32 raw_size; __u32 key_id; - __u32 __reserved[8]; +#define FSCRYPT_ADD_KEY_FLAG_HW_WRAPPED 0x00000001 + __u32 flags; + __u32 __reserved[7]; __u8 raw[]; }; diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h index 44f2bb93e7e6..23a062781468 100644 --- a/tools/include/uapi/linux/if_xdp.h +++ b/tools/include/uapi/linux/if_xdp.h @@ -79,6 +79,7 @@ struct xdp_mmap_offsets { #define XDP_UMEM_COMPLETION_RING 6 #define XDP_STATISTICS 7 #define XDP_OPTIONS 8 +#define XDP_MAX_TX_SKB_BUDGET 9 struct xdp_umem_reg { __u64 addr; /* Start of packet data area */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index b6ae8ad8934b..d00b85cb168c 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -375,6 +375,7 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_WAKEUP 4 #define KVM_SYSTEM_EVENT_SUSPEND 5 #define KVM_SYSTEM_EVENT_SEV_TERM 6 +#define KVM_SYSTEM_EVENT_TDX_FATAL 7 __u32 type; __u32 ndata; union { @@ -930,6 +931,9 @@ struct kvm_enable_cap { #define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237 #define KVM_CAP_X86_GUEST_MODE 238 #define KVM_CAP_ARM_WRITABLE_IMP_ID_REGS 239 +#define KVM_CAP_ARM_EL2 240 +#define KVM_CAP_ARM_EL2_E2H0 241 +#define KVM_CAP_RISCV_MP_STATE_RESET 242 struct kvm_irq_routing_irqchip { __u32 irqchip; diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 7eb9571786b8..1f3719a9a0eb 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -134,6 +134,7 @@ enum { NETDEV_A_NAPI_DEFER_HARD_IRQS, NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT, + NETDEV_A_NAPI_THREADED, __NETDEV_A_NAPI_MAX, NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h index f78ee3670dd5..1686861aae20 100644 --- a/tools/include/uapi/linux/stat.h +++ b/tools/include/uapi/linux/stat.h @@ -182,8 +182,12 @@ struct statx { /* File offset alignment for direct I/O reads */ __u32 stx_dio_read_offset_align; - /* 0xb8 */ - __u64 __spare3[9]; /* Spare space for future expansion */ + /* Optimised max atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max_opt; + __u32 __spare2[1]; + + /* 0xc0 */ + __u64 __spare3[8]; /* Spare space for future expansion */ /* 0x100 */ }; diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 460c3e57fadb..0381f209920a 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -226,6 +226,9 @@ static void btf_dump_free_names(struct hashmap *map) size_t bkt; struct hashmap_entry *cur; + if (!map) + return; + hashmap__for_each_entry(map, cur, bkt) free((void *)cur->pkey); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index e9c641a2fb20..52e353368f58 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -597,7 +597,7 @@ struct extern_desc { int sym_idx; int btf_id; int sec_btf_id; - const char *name; + char *name; char *essent_name; bool is_set; bool is_weak; @@ -4259,7 +4259,9 @@ static int bpf_object__collect_externs(struct bpf_object *obj) return ext->btf_id; } t = btf__type_by_id(obj->btf, ext->btf_id); - ext->name = btf__name_by_offset(obj->btf, t->name_off); + ext->name = strdup(btf__name_by_offset(obj->btf, t->name_off)); + if (!ext->name) + return -ENOMEM; ext->sym_idx = i; ext->is_weak = ELF64_ST_BIND(sym->st_info) == STB_WEAK; @@ -9138,8 +9140,10 @@ void bpf_object__close(struct bpf_object *obj) zfree(&obj->btf_custom_path); zfree(&obj->kconfig); - for (i = 0; i < obj->nr_extern; i++) + for (i = 0; i < obj->nr_extern; i++) { + zfree(&obj->externs[i].name); zfree(&obj->externs[i].essent_name); + } zfree(&obj->externs); obj->nr_extern = 0; diff --git a/tools/net/ynl/pyynl/cli.py b/tools/net/ynl/pyynl/cli.py index 33ccc5c1843b..8c192e900bd3 100755 --- a/tools/net/ynl/pyynl/cli.py +++ b/tools/net/ynl/pyynl/cli.py @@ -113,6 +113,8 @@ def main(): spec = f"{spec_dir()}/{args.family}.yaml" if args.schema is None and spec.startswith(sys_schema_dir): args.schema = '' # disable schema validation when installed + if args.process_unknown is None: + args.process_unknown = True else: spec = args.spec if not os.path.isfile(spec): diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py index 61deb5923067..8244a5f440b2 100644 --- a/tools/net/ynl/pyynl/lib/ynl.py +++ b/tools/net/ynl/pyynl/lib/ynl.py @@ -575,7 +575,9 @@ class YnlFamily(SpecFamily): elif attr["type"] == 'string': attr_payload = str(value).encode('ascii') + b'\x00' elif attr["type"] == 'binary': - if isinstance(value, bytes): + if value is None: + attr_payload = b'' + elif isinstance(value, bytes): attr_payload = value elif isinstance(value, str): if attr.display_hint: @@ -584,6 +586,9 @@ class YnlFamily(SpecFamily): attr_payload = bytes.fromhex(value) elif isinstance(value, dict) and attr.struct_name: attr_payload = self._encode_struct(attr.struct_name, value) + elif isinstance(value, list) and attr.sub_type in NlAttr.type_formats: + format = NlAttr.get_format(attr.sub_type) + attr_payload = b''.join([format.pack(x) for x in value]) else: raise Exception(f'Unknown type for binary attribute, value: {value}') elif attr['type'] in NlAttr.type_formats or attr.is_auto_scalar: @@ -618,6 +623,16 @@ class YnlFamily(SpecFamily): pad = b'\x00' * ((4 - len(attr_payload) % 4) % 4) return struct.pack('HH', len(attr_payload) + 4, nl_type) + attr_payload + pad + def _get_enum_or_unknown(self, enum, raw): + try: + name = enum.entries_by_val[raw].name + except KeyError as error: + if self.process_unknown: + name = f"Unknown({raw})" + else: + raise error + return name + def _decode_enum(self, raw, attr_spec): enum = self.consts[attr_spec['enum']] if enum.type == 'flags' or attr_spec.get('enum-as-flags', False): @@ -625,11 +640,11 @@ class YnlFamily(SpecFamily): value = set() while raw: if raw & 1: - value.add(enum.entries_by_val[i].name) + value.add(self._get_enum_or_unknown(enum, i)) raw >>= 1 i += 1 else: - value = enum.entries_by_val[raw].name + value = self._get_enum_or_unknown(enum, raw) return value def _decode_binary(self, attr, attr_spec): @@ -762,6 +777,8 @@ class YnlFamily(SpecFamily): decoded = True elif attr_spec.is_auto_scalar: decoded = attr.as_auto_scalar(attr_spec['type'], attr_spec.byte_order) + if 'enum' in attr_spec: + decoded = self._decode_enum(decoded, attr_spec) elif attr_spec["type"] in NlAttr.type_formats: decoded = attr.as_scalar(attr_spec['type'], attr_spec.byte_order) if 'enum' in attr_spec: diff --git a/tools/objtool/check.c b/tools/objtool/check.c index f23bdda737aa..d967ac001498 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -2318,6 +2318,7 @@ static int read_annotate(struct objtool_file *file, for_each_reloc(sec->rsec, reloc) { type = *(u32 *)(sec->data->d_buf + (reloc_idx(reloc) * sec->sh.sh_entsize) + 4); + type = bswap_if_needed(file->elf, type); offset = reloc->sym->offset + reloc_addend(reloc); insn = find_insn(file, reloc->sym->sec, offset); diff --git a/tools/perf/Documentation/perf-amd-ibs.txt b/tools/perf/Documentation/perf-amd-ibs.txt index 55f80beae037..548549935760 100644 --- a/tools/perf/Documentation/perf-amd-ibs.txt +++ b/tools/perf/Documentation/perf-amd-ibs.txt @@ -171,23 +171,48 @@ Below is a simple example of the perf mem tool. # perf mem report A normal perf mem report output will provide detailed memory access profile. -However, it can also be aggregated based on output fields. For example: - - # perf mem report -F mem,sample,snoop - Samples: 3M of event 'ibs_op//', Event count (approx.): 23524876 - Memory access Samples Snoop - N/A 1903343 N/A - L1 hit 1056754 N/A - L2 hit 75231 N/A - L3 hit 9496 HitM - L3 hit 2270 N/A - RAM hit 8710 N/A - Remote node, same socket RAM hit 3241 N/A - Remote core, same node Any cache hit 1572 HitM - Remote core, same node Any cache hit 514 N/A - Remote node, same socket Any cache hit 1216 HitM - Remote node, same socket Any cache hit 350 N/A - Uncached hit 18 N/A +New output fields will show related access info together. For example: + + # perf mem report -F overhead,cache,snoop,comm + ... + # Samples: 92K of event 'ibs_op//' + # Total weight : 531104 + # + # ---------- Cache ----------- --- Snoop ---- + # Overhead L1 L2 L1-buf Other HitM Other Command + # ........ ............................ .............. .......... + # + 76.07% 5.8% 35.7% 0.0% 34.6% 23.3% 52.8% cc1 + 5.79% 0.2% 0.0% 0.0% 5.6% 0.1% 5.7% make + 5.78% 0.1% 4.4% 0.0% 1.2% 0.5% 5.3% gcc + 5.33% 0.3% 3.9% 0.0% 1.1% 0.2% 5.2% as + 5.00% 0.1% 3.8% 0.0% 1.0% 0.3% 4.7% sh + 1.56% 0.1% 0.1% 0.0% 1.4% 0.6% 0.9% ld + 0.28% 0.1% 0.0% 0.0% 0.2% 0.1% 0.2% pkg-config + 0.09% 0.0% 0.0% 0.0% 0.1% 0.0% 0.1% git + 0.03% 0.0% 0.0% 0.0% 0.0% 0.0% 0.0% rm + ... + +Also, it can be aggregated based on various memory access info using the +sort keys. For example: + + # perf mem report -s mem,snoop + ... + # Samples: 92K of event 'ibs_op//' + # Total weight : 531104 + # Sort order : mem,snoop + # + # Overhead Samples Memory access Snoop + # ........ ............ ....................................... ............ + # + 47.99% 1509 L2 hit N/A + 25.08% 338 core, same node Any cache hit HitM + 10.24% 54374 N/A N/A + 6.77% 35938 L1 hit N/A + 6.39% 101 core, same node Any cache hit N/A + 3.50% 69 RAM hit N/A + 0.03% 158 LFB/MAB hit N/A + 0.00% 2 Uncached hit N/A Please refer to their man page for more detail. diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index 965e73d37772..4d164836d094 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -119,6 +119,22 @@ REPORT OPTIONS And the default sort keys are changed to local_weight, mem, sym, dso, symbol_daddr, dso_daddr, snoop, tlb, locked, blocked, local_ins_lat. +-F:: +--fields=:: + Specify output field - multiple keys can be specified in CSV format. + Please see linkperf:perf-report[1] for details. + + In addition to the default fields, 'perf mem report' will provide the + following fields to break down sample periods. + + - op: operation in the sample instruction (load, store, prefetch, ...) + - cache: location in CPU cache (L1, L2, ...) where the sample hit + - mem: location in memory or other places the sample hit + - dtlb: location in Data TLB (L1, L2) where the sample hit + - snoop: snoop result for the sampled data access + + Please take a look at the OUTPUT FIELD SELECTION section for caveats. + -T:: --type-profile:: Show data-type profile result instead of code symbols. This requires @@ -156,6 +172,40 @@ but one sample with weight 180 and the other with weight 20: 90% [k] memcpy 10% [.] strcmp +OUTPUT FIELD SELECTION +---------------------- +"perf mem report" adds a number of new output fields specific to data source +information in the sample. Some of them have the same name with the existing +sort keys ("mem" and "snoop"). So unlike other fields and sort keys, they'll +behave differently when it's used by -F/--fields or -s/--sort. + +Using those two as output fields will aggregate samples altogether and show +breakdown. + + $ perf mem report -F mem,snoop + ... + # ------ Memory ------- --- Snoop ---- + # RAM Uncach Other HitM Other + # ..................... .............. + # + 3.5% 0.0% 96.5% 25.1% 74.9% + +But using the same name for sort keys will aggregate samples for each type +separately. + + $ perf mem report -s mem,snoop + # Overhead Samples Memory access Snoop + # ........ ............ ....................................... ............ + # + 47.99% 1509 L2 hit N/A + 25.08% 338 core, same node Any cache hit HitM + 10.24% 54374 N/A N/A + 6.77% 35938 L1 hit N/A + 6.39% 101 core, same node Any cache hit N/A + 3.50% 69 RAM hit N/A + 0.03% 158 LFB/MAB hit N/A + 0.00% 2 Uncached hit N/A + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-arm-spe[1] diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index fdf133c9520f..d2d6d7f3ea33 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -18,7 +18,6 @@ #include <stdlib.h> #include <linux/compiler.h> #include <linux/kernel.h> -#include <linux/prctl.h> #include <linux/zalloc.h> #include <sys/time.h> #include <sys/mman.h> diff --git a/tools/perf/bench/futex.c b/tools/perf/bench/futex.c index 26382e4d8d4c..4c4fee107e59 100644 --- a/tools/perf/bench/futex.c +++ b/tools/perf/bench/futex.c @@ -2,11 +2,18 @@ #include <err.h> #include <stdio.h> #include <stdlib.h> -#include <linux/prctl.h> #include <sys/prctl.h> #include "futex.h" +#ifndef PR_FUTEX_HASH +#define PR_FUTEX_HASH 78 +# define PR_FUTEX_HASH_SET_SLOTS 1 +# define FH_FLAG_IMMUTABLE (1ULL << 0) +# define PR_FUTEX_HASH_GET_SLOTS 2 +# define PR_FUTEX_HASH_GET_IMMUTABLE 3 +#endif // PR_FUTEX_HASH + void futex_set_nbuckets_param(struct bench_futex_parameters *params) { unsigned long flags; diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index e9fab20e9330..8085e4d1d8af 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -186,7 +186,7 @@ done # diff with extra ignore lines check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))" -I"^#include <linux/cfi_types.h>"' check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"' -check arch/x86/include/asm/amd/ibs.h '-I "^#include [<\"]\(asm/\)*msr-index.h"' +check arch/x86/include/asm/amd/ibs.h '-I "^#include .*/msr-index.h"' check arch/arm64/include/asm/cputype.h '-I "^#include [<\"]\(asm/\)*sysreg.h"' check include/linux/unaligned.h '-I "^#include <linux/unaligned/packed_struct.h>" -I "^#include <asm/byteorder.h>" -I "^#pragma GCC diagnostic"' check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"' diff --git a/tools/perf/tests/shell/stat+event_uniquifying.sh b/tools/perf/tests/shell/stat+event_uniquifying.sh index 5ec35c52b7d9..bf54bd6c3e2e 100755 --- a/tools/perf/tests/shell/stat+event_uniquifying.sh +++ b/tools/perf/tests/shell/stat+event_uniquifying.sh @@ -9,7 +9,8 @@ perf_tool=perf err=0 test_event_uniquifying() { - # We use `clockticks` to verify the uniquify behavior. + # We use `clockticks` in `uncore_imc` to verify the uniquify behavior. + pmu="uncore_imc" event="clockticks" # If the `-A` option is added, the event should be uniquified. @@ -43,11 +44,18 @@ test_event_uniquifying() { echo "stat event uniquifying test" uniquified_event_array=() + # Skip if the machine does not have `uncore_imc` device. + if ! ${perf_tool} list pmu | grep -q ${pmu}; then + echo "Target does not support PMU ${pmu} [Skipped]" + err=2 + return + fi + # Check how many uniquified events. while IFS= read -r line; do uniquified_event=$(echo "$line" | awk '{print $1}') uniquified_event_array+=("${uniquified_event}") - done < <(${perf_tool} list -v ${event} | grep "\[Kernel PMU event\]") + done < <(${perf_tool} list -v ${event} | grep ${pmu}) perf_command="${perf_tool} stat -e $event -A -o ${stat_output} -- true" $perf_command diff --git a/tools/perf/tests/tests-scripts.c b/tools/perf/tests/tests-scripts.c index 1d5759d08141..3a2a8438f9af 100644 --- a/tools/perf/tests/tests-scripts.c +++ b/tools/perf/tests/tests-scripts.c @@ -260,6 +260,7 @@ static void append_scripts_in_dir(int dir_fd, continue; /* Skip scripts that have a separate driver. */ fd = openat(dir_fd, ent->d_name, O_PATH); append_scripts_in_dir(fd, result, result_sz); + close(fd); } for (i = 0; i < n_dirs; i++) /* Clean up */ zfree(&entlist[i]); diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index c3322eb3d686..3b262487ec06 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -168,7 +168,7 @@ static inline struct cmsghdr * cmsg_nxthdr (struct msghdr *__msg, struct cmsghdr return __cmsg_nxthdr(__msg->msg_control, __msg->msg_controllen, __cmsg); } -static inline size_t msg_data_left(struct msghdr *msg) +static inline size_t msg_data_left(const struct msghdr *msg) { return iov_iter_count(&msg->msg_iter); } diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h index e762e1af650c..0098b0ce8ccb 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fs.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h @@ -361,6 +361,7 @@ typedef int __bitwise __kernel_rwf_t; #define PAGE_IS_PFNZERO (1 << 5) #define PAGE_IS_HUGE (1 << 6) #define PAGE_IS_SOFT_DIRTY (1 << 7) +#define PAGE_IS_GUARD (1 << 8) /* * struct page_region - Page region with flags diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h index 15c18ef4eb11..43dec6eed559 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h +++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h @@ -364,4 +364,11 @@ struct prctl_mm_map { # define PR_TIMER_CREATE_RESTORE_IDS_ON 1 # define PR_TIMER_CREATE_RESTORE_IDS_GET 2 +/* FUTEX hash management */ +#define PR_FUTEX_HASH 78 +# define PR_FUTEX_HASH_SET_SLOTS 1 +# define FH_FLAG_IMMUTABLE (1ULL << 0) +# define PR_FUTEX_HASH_GET_SLOTS 2 +# define PR_FUTEX_HASH_GET_IMMUTABLE 3 + #endif /* _LINUX_PRCTL_H */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/stat.h b/tools/perf/trace/beauty/include/uapi/linux/stat.h index f78ee3670dd5..1686861aae20 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/stat.h +++ b/tools/perf/trace/beauty/include/uapi/linux/stat.h @@ -182,8 +182,12 @@ struct statx { /* File offset alignment for direct I/O reads */ __u32 stx_dio_read_offset_align; - /* 0xb8 */ - __u64 __spare3[9]; /* Spare space for future expansion */ + /* Optimised max atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max_opt; + __u32 __spare2[1]; + + /* 0xc0 */ + __u64 __spare3[8]; /* Spare space for future expansion */ /* 0x100 */ }; diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h index 178b00205fe6..89979ca23c3f 100644 --- a/tools/perf/util/include/linux/linkage.h +++ b/tools/perf/util/include/linux/linkage.h @@ -132,4 +132,8 @@ SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #endif +#ifndef SYM_PIC_ALIAS +#define SYM_PIC_ALIAS(sym) SYM_ALIAS(__pi_ ## sym, sym, SYM_T_FUNC, SYM_L_GLOBAL) +#endif + #endif /* PERF_LINUX_LINKAGE_H_ */ diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c index a786cbfb0ff5..83aaf7cda635 100644 --- a/tools/perf/util/print-events.c +++ b/tools/perf/util/print-events.c @@ -268,6 +268,7 @@ bool is_event_supported(u8 type, u64 config) ret = evsel__open(evsel, NULL, tmap) >= 0; } + evsel__close(evsel); evsel__delete(evsel); } diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index e2a2c46c008b..3d8378972d26 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -21,7 +21,6 @@ test_lirc_mode2_user flow_dissector_load test_tcpnotify_user test_libbpf -test_sysctl xdping test_cpp *.d diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index cf5ed3bee573..910d8d6402ef 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -73,7 +73,7 @@ endif # Order correspond to 'make run_tests' order TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_progs \ test_sockmap \ - test_tcpnotify_user test_sysctl \ + test_tcpnotify_user \ test_progs-no_alu32 TEST_INST_SUBDIRS := no_alu32 @@ -220,7 +220,7 @@ ifeq ($(VMLINUX_BTF),) $(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)") endif -# Define simple and short `make test_progs`, `make test_sysctl`, etc targets +# Define simple and short `make test_progs`, `make test_maps`, etc targets # to build individual tests. # NOTE: Semicolon at the end is critical to override lib.mk's default static # rule for binaries. @@ -329,7 +329,6 @@ NETWORK_HELPERS := $(OUTPUT)/network_helpers.o $(OUTPUT)/test_sockmap: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(OUTPUT)/test_tcpnotify_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(TRACE_HELPERS) $(OUTPUT)/test_sock_fields: $(CGROUP_HELPERS) $(TESTING_HELPERS) -$(OUTPUT)/test_sysctl: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(OUTPUT)/test_tag: $(TESTING_HELPERS) $(OUTPUT)/test_lirc_mode2_user: $(TESTING_HELPERS) $(OUTPUT)/xdping: $(TESTING_HELPERS) diff --git a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c index a4517bee34d5..27781df8f2fb 100644 --- a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c +++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c @@ -1,11 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2024 Meta +#include <poll.h> #include <test_progs.h> #include "network_helpers.h" #include "sock_iter_batch.skel.h" #define TEST_NS "sock_iter_batch_netns" +#define TEST_CHILD_NS "sock_iter_batch_child_netns" static const int init_batch_size = 16; static const int nr_soreuse = 4; @@ -118,6 +120,45 @@ done: return nth_sock_idx; } +static void destroy(int fd) +{ + struct sock_iter_batch *skel = NULL; + __u64 cookie = socket_cookie(fd); + struct bpf_link *link = NULL; + int iter_fd = -1; + int nread; + __u64 out; + + skel = sock_iter_batch__open(); + if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open")) + goto done; + + skel->rodata->destroy_cookie = cookie; + + if (!ASSERT_OK(sock_iter_batch__load(skel), "sock_iter_batch__load")) + goto done; + + link = bpf_program__attach_iter(skel->progs.iter_tcp_destroy, NULL); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter")) + goto done; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (!ASSERT_OK_FD(iter_fd, "bpf_iter_create")) + goto done; + + /* Delete matching socket. */ + nread = read(iter_fd, &out, sizeof(out)); + ASSERT_GE(nread, 0, "nread"); + if (nread) + ASSERT_EQ(out, cookie, "cookie matches"); +done: + if (iter_fd >= 0) + close(iter_fd); + bpf_link__destroy(link); + sock_iter_batch__destroy(skel); + close(fd); +} + static int get_seen_count(int fd, struct sock_count counts[], int n) { __u64 cookie = socket_cookie(fd); @@ -152,8 +193,71 @@ static void check_n_were_seen_once(int *fds, int fds_len, int n, ASSERT_EQ(seen_once, n, "seen_once"); } +static int accept_from_one(struct pollfd *server_poll_fds, + int server_poll_fds_len) +{ + static const int poll_timeout_ms = 5000; /* 5s */ + int ret; + int i; + + ret = poll(server_poll_fds, server_poll_fds_len, poll_timeout_ms); + if (!ASSERT_EQ(ret, 1, "poll")) + return -1; + + for (i = 0; i < server_poll_fds_len; i++) + if (server_poll_fds[i].revents & POLLIN) + return accept(server_poll_fds[i].fd, NULL, NULL); + + return -1; +} + +static int *connect_to_server(int family, int sock_type, const char *addr, + __u16 port, int nr_connects, int *server_fds, + int server_fds_len) +{ + struct pollfd *server_poll_fds = NULL; + int *established_socks = NULL; + int i; + + server_poll_fds = calloc(server_fds_len, sizeof(*server_poll_fds)); + if (!ASSERT_OK_PTR(server_poll_fds, "server_poll_fds")) + return NULL; + + for (i = 0; i < server_fds_len; i++) { + server_poll_fds[i].fd = server_fds[i]; + server_poll_fds[i].events = POLLIN; + } + + i = 0; + + established_socks = malloc(sizeof(*established_socks) * nr_connects*2); + if (!ASSERT_OK_PTR(established_socks, "established_socks")) + goto error; + + while (nr_connects--) { + established_socks[i] = connect_to_addr_str(family, sock_type, + addr, port, NULL); + if (!ASSERT_OK_FD(established_socks[i], "connect_to_addr_str")) + goto error; + i++; + established_socks[i] = accept_from_one(server_poll_fds, + server_fds_len); + if (!ASSERT_OK_FD(established_socks[i], "accept_from_one")) + goto error; + i++; + } + + free(server_poll_fds); + return established_socks; +error: + free_fds(established_socks, i); + free(server_poll_fds); + return NULL; +} + static void remove_seen(int family, int sock_type, const char *addr, __u16 port, - int *socks, int socks_len, struct sock_count *counts, + int *socks, int socks_len, int *established_socks, + int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { int close_idx; @@ -182,8 +286,46 @@ static void remove_seen(int family, int sock_type, const char *addr, __u16 port, counts_len); } +static void remove_seen_established(int family, int sock_type, const char *addr, + __u16 port, int *listen_socks, + int listen_socks_len, int *established_socks, + int established_socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + int close_idx; + + /* Iterate through all listening sockets. */ + read_n(iter_fd, listen_socks_len, counts, counts_len); + + /* Make sure we saw all listening sockets exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + + /* Leave one established socket. */ + read_n(iter_fd, established_socks_len - 1, counts, counts_len); + + /* Close a socket we've already seen to remove it from the bucket. */ + close_idx = get_nth_socket(established_socks, established_socks_len, + link, listen_socks_len + 1); + if (!ASSERT_GE(close_idx, 0, "close_idx")) + return; + destroy(established_socks[close_idx]); + established_socks[close_idx] = -1; + + /* Iterate through the rest of the sockets. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure the last socket wasn't skipped and that there were no + * repeats. + */ + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len - 1, counts, counts_len); +} + static void remove_unseen(int family, int sock_type, const char *addr, __u16 port, int *socks, int socks_len, + int *established_socks, int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { @@ -214,8 +356,54 @@ static void remove_unseen(int family, int sock_type, const char *addr, counts_len); } +static void remove_unseen_established(int family, int sock_type, + const char *addr, __u16 port, + int *listen_socks, int listen_socks_len, + int *established_socks, + int established_socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + int close_idx; + + /* Iterate through all listening sockets. */ + read_n(iter_fd, listen_socks_len, counts, counts_len); + + /* Make sure we saw all listening sockets exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + + /* Iterate through the first established socket. */ + read_n(iter_fd, 1, counts, counts_len); + + /* Make sure we saw one established socks. */ + check_n_were_seen_once(established_socks, established_socks_len, 1, + counts, counts_len); + + /* Close what would be the next socket in the bucket to exercise the + * condition where we need to skip past the first cookie we remembered. + */ + close_idx = get_nth_socket(established_socks, established_socks_len, + link, listen_socks_len + 1); + if (!ASSERT_GE(close_idx, 0, "close_idx")) + return; + + destroy(established_socks[close_idx]); + established_socks[close_idx] = -1; + + /* Iterate through the rest of the sockets. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure the remaining sockets were seen exactly once and that we + * didn't repeat the socket that was already seen. + */ + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len - 1, counts, counts_len); +} + static void remove_all(int family, int sock_type, const char *addr, __u16 port, int *socks, int socks_len, + int *established_socks, int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { @@ -242,8 +430,57 @@ static void remove_all(int family, int sock_type, const char *addr, ASSERT_EQ(read_n(iter_fd, -1, counts, counts_len), 0, "read_n"); } +static void remove_all_established(int family, int sock_type, const char *addr, + __u16 port, int *listen_socks, + int listen_socks_len, int *established_socks, + int established_socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + int *close_idx = NULL; + int i; + + /* Iterate through all listening sockets. */ + read_n(iter_fd, listen_socks_len, counts, counts_len); + + /* Make sure we saw all listening sockets exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + + /* Iterate through the first established socket. */ + read_n(iter_fd, 1, counts, counts_len); + + /* Make sure we saw one established socks. */ + check_n_were_seen_once(established_socks, established_socks_len, 1, + counts, counts_len); + + /* Close all remaining sockets to exhaust the list of saved cookies and + * exit without putting any sockets into the batch on the next read. + */ + close_idx = malloc(sizeof(int) * (established_socks_len - 1)); + if (!ASSERT_OK_PTR(close_idx, "close_idx malloc")) + return; + for (i = 0; i < established_socks_len - 1; i++) { + close_idx[i] = get_nth_socket(established_socks, + established_socks_len, link, + listen_socks_len + i); + if (!ASSERT_GE(close_idx[i], 0, "close_idx")) + return; + } + + for (i = 0; i < established_socks_len - 1; i++) { + destroy(established_socks[close_idx[i]]); + established_socks[close_idx[i]] = -1; + } + + /* Make sure there are no more sockets returned */ + ASSERT_EQ(read_n(iter_fd, -1, counts, counts_len), 0, "read_n"); + free(close_idx); +} + static void add_some(int family, int sock_type, const char *addr, __u16 port, - int *socks, int socks_len, struct sock_count *counts, + int *socks, int socks_len, int *established_socks, + int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { int *new_socks = NULL; @@ -271,8 +508,52 @@ done: free_fds(new_socks, socks_len); } +static void add_some_established(int family, int sock_type, const char *addr, + __u16 port, int *listen_socks, + int listen_socks_len, int *established_socks, + int established_socks_len, + struct sock_count *counts, + int counts_len, struct bpf_link *link, + int iter_fd) +{ + int *new_socks = NULL; + + /* Iterate through all listening sockets. */ + read_n(iter_fd, listen_socks_len, counts, counts_len); + + /* Make sure we saw all listening sockets exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + + /* Iterate through the first established_socks_len - 1 sockets. */ + read_n(iter_fd, established_socks_len - 1, counts, counts_len); + + /* Make sure we saw established_socks_len - 1 sockets exactly once. */ + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len - 1, counts, counts_len); + + /* Double the number of established sockets in the bucket. */ + new_socks = connect_to_server(family, sock_type, addr, port, + established_socks_len / 2, listen_socks, + listen_socks_len); + if (!ASSERT_OK_PTR(new_socks, "connect_to_server")) + goto done; + + /* Iterate through the rest of the sockets. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure each of the original sockets was seen exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len, counts, counts_len); +done: + free_fds(new_socks, established_socks_len); +} + static void force_realloc(int family, int sock_type, const char *addr, __u16 port, int *socks, int socks_len, + int *established_socks, int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { @@ -299,11 +580,32 @@ done: free_fds(new_socks, socks_len); } +static void force_realloc_established(int family, int sock_type, + const char *addr, __u16 port, + int *listen_socks, int listen_socks_len, + int *established_socks, + int established_socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + /* Iterate through all sockets to trigger a realloc. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure each socket was seen exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len, counts, counts_len); +} + struct test_case { void (*test)(int family, int sock_type, const char *addr, __u16 port, - int *socks, int socks_len, struct sock_count *counts, + int *socks, int socks_len, int *established_socks, + int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd); const char *description; + int ehash_buckets; + int connections; int init_socks; int max_socks; int sock_type; @@ -358,18 +660,140 @@ static struct test_case resume_tests[] = { .family = AF_INET6, .test = force_realloc, }, + { + .description = "tcp: resume after removing a seen socket (listening)", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_seen, + }, + { + .description = "tcp: resume after removing one unseen socket (listening)", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_unseen, + }, + { + .description = "tcp: resume after removing all unseen sockets (listening)", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_all, + }, + { + .description = "tcp: resume after adding a few sockets (listening)", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_STREAM, + /* Use AF_INET so that new sockets are added to the head of the + * bucket's list. + */ + .family = AF_INET, + .test = add_some, + }, + { + .description = "tcp: force a realloc to occur (listening)", + .init_socks = init_batch_size, + .max_socks = init_batch_size * 2, + .sock_type = SOCK_STREAM, + /* Use AF_INET6 so that new sockets are added to the tail of the + * bucket's list, needing to be added to the next batch to force + * a realloc. + */ + .family = AF_INET6, + .test = force_realloc, + }, + { + .description = "tcp: resume after removing a seen socket (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + .connections = nr_soreuse, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse * 3, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_seen_established, + }, + { + .description = "tcp: resume after removing one unseen socket (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + .connections = nr_soreuse, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse * 3, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_unseen_established, + }, + { + .description = "tcp: resume after removing all unseen sockets (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + .connections = nr_soreuse, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse * 3, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_all_established, + }, + { + .description = "tcp: resume after adding a few sockets (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + .connections = nr_soreuse, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse * 3, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = add_some_established, + }, + { + .description = "tcp: force a realloc to occur (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + /* Bucket size will need to double when going from listening to + * established sockets. + */ + .connections = init_batch_size, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse + (init_batch_size * 2), + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = force_realloc_established, + }, }; static void do_resume_test(struct test_case *tc) { struct sock_iter_batch *skel = NULL; + struct sock_count *counts = NULL; static const __u16 port = 10001; + struct nstoken *nstoken = NULL; struct bpf_link *link = NULL; - struct sock_count *counts; + int *established_fds = NULL; int err, iter_fd = -1; const char *addr; int *fds = NULL; - int local_port; + + if (tc->ehash_buckets) { + SYS_NOFAIL("ip netns del " TEST_CHILD_NS); + SYS(done, "sysctl -wq net.ipv4.tcp_child_ehash_entries=%d", + tc->ehash_buckets); + SYS(done, "ip netns add %s", TEST_CHILD_NS); + SYS(done, "ip -net %s link set dev lo up", TEST_CHILD_NS); + nstoken = open_netns(TEST_CHILD_NS); + if (!ASSERT_OK_PTR(nstoken, "open_child_netns")) + goto done; + } counts = calloc(tc->max_socks, sizeof(*counts)); if (!ASSERT_OK_PTR(counts, "counts")) @@ -384,11 +808,18 @@ static void do_resume_test(struct test_case *tc) tc->init_socks); if (!ASSERT_OK_PTR(fds, "start_reuseport_server")) goto done; - local_port = get_socket_local_port(*fds); - if (!ASSERT_GE(local_port, 0, "get_socket_local_port")) - goto done; - skel->rodata->ports[0] = ntohs(local_port); + if (tc->connections) { + established_fds = connect_to_server(tc->family, tc->sock_type, + addr, port, + tc->connections, fds, + tc->init_socks); + if (!ASSERT_OK_PTR(established_fds, "connect_to_server")) + goto done; + } + skel->rodata->ports[0] = 0; + skel->rodata->ports[1] = 0; skel->rodata->sf = tc->family; + skel->rodata->ss = 0; err = sock_iter_batch__load(skel); if (!ASSERT_OK(err, "sock_iter_batch__load")) @@ -406,10 +837,15 @@ static void do_resume_test(struct test_case *tc) goto done; tc->test(tc->family, tc->sock_type, addr, port, fds, tc->init_socks, - counts, tc->max_socks, link, iter_fd); + established_fds, tc->connections*2, counts, tc->max_socks, + link, iter_fd); done: + close_netns(nstoken); + SYS_NOFAIL("ip netns del " TEST_CHILD_NS); + SYS_NOFAIL("sysctl -w net.ipv4.tcp_child_ehash_entries=0"); free(counts); free_fds(fds, tc->init_socks); + free_fds(established_fds, tc->connections*2); if (iter_fd >= 0) close(iter_fd); bpf_link__destroy(link); @@ -454,6 +890,8 @@ static void do_test(int sock_type, bool onebyone) skel->rodata->ports[i] = ntohs(local_port); } skel->rodata->sf = AF_INET6; + if (sock_type == SOCK_STREAM) + skel->rodata->ss = TCP_LISTEN; err = sock_iter_batch__load(skel); if (!ASSERT_OK(err, "sock_iter_batch__load")) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c index b6c471da5c28..b87e7f39e15a 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c @@ -314,6 +314,95 @@ out: test_sockmap_ktls__destroy(skel); } +static void test_sockmap_ktls_tx_pop(int family, int sotype) +{ + char msg[37] = "0123456789abcdefghijklmnopqrstuvwxyz\0"; + int c = 0, p = 0, one = 1, sent, recvd; + struct test_sockmap_ktls *skel; + int prog_fd, map_fd; + char rcv[50] = {0}; + int err; + int i, m, r; + + skel = test_sockmap_ktls__open_and_load(); + if (!ASSERT_TRUE(skel, "open ktls skel")) + return; + + err = create_pair(family, sotype, &c, &p); + if (!ASSERT_OK(err, "create_pair()")) + goto out; + + prog_fd = bpf_program__fd(skel->progs.prog_sk_policy); + map_fd = bpf_map__fd(skel->maps.sock_map); + + err = bpf_prog_attach(prog_fd, map_fd, BPF_SK_MSG_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach sk msg")) + goto out; + + err = bpf_map_update_elem(map_fd, &one, &c, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(c)")) + goto out; + + err = init_ktls_pairs(c, p); + if (!ASSERT_OK(err, "init_ktls_pairs(c, p)")) + goto out; + + struct { + int pop_start; + int pop_len; + } pop_policy[] = { + /* trim the start */ + {0, 2}, + {0, 10}, + {1, 2}, + {1, 10}, + /* trim the end */ + {35, 2}, + /* New entries should be added before this line */ + {-1, -1}, + }; + + i = 0; + while (pop_policy[i].pop_start >= 0) { + skel->bss->pop_start = pop_policy[i].pop_start; + skel->bss->pop_end = pop_policy[i].pop_len; + + sent = send(c, msg, sizeof(msg), 0); + if (!ASSERT_EQ(sent, sizeof(msg), "send(msg)")) + goto out; + + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1); + if (!ASSERT_EQ(recvd, sizeof(msg) - pop_policy[i].pop_len, "pop len mismatch")) + goto out; + + /* verify the data + * msg: 0123456789a bcdefghij klmnopqrstuvwxyz + * | | + * popped data + */ + for (m = 0, r = 0; m < sizeof(msg);) { + /* skip checking the data that has been popped */ + if (m >= pop_policy[i].pop_start && + m <= pop_policy[i].pop_start + pop_policy[i].pop_len - 1) { + m++; + continue; + } + + if (!ASSERT_EQ(msg[m], rcv[r], "data mismatch")) + goto out; + m++; + r++; + } + i++; + } +out: + if (c) + close(c); + if (p) + close(p); + test_sockmap_ktls__destroy(skel); +} + static void run_tests(int family, enum bpf_map_type map_type) { int map; @@ -338,6 +427,8 @@ static void run_ktls_test(int family, int sotype) test_sockmap_ktls_tx_cork(family, sotype, true); if (test__start_subtest("tls tx egress with no buf")) test_sockmap_ktls_tx_no_buf(family, sotype, true); + if (test__start_subtest("tls tx with pop")) + test_sockmap_ktls_tx_pop(family, sotype); } void test_sockmap_ktls(void) diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c index bcdbd27f22f0..273dd41ca09e 100644 --- a/tools/testing/selftests/bpf/test_sysctl.c +++ b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c @@ -1,22 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook -#include <fcntl.h> -#include <stdint.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <unistd.h> - -#include <linux/filter.h> - -#include <bpf/bpf.h> -#include <bpf/libbpf.h> - -#include <bpf/bpf_endian.h> -#include "bpf_util.h" +#include "test_progs.h" #include "cgroup_helpers.h" -#include "testing_helpers.h" #define CG_PATH "/foo" #define MAX_INSNS 512 @@ -1608,26 +1594,19 @@ static int run_tests(int cgfd) return fails ? -1 : 0; } -int main(int argc, char **argv) +void test_sysctl(void) { - int cgfd = -1; - int err = 0; + int cgfd; cgfd = cgroup_setup_and_join(CG_PATH); - if (cgfd < 0) - goto err; + if (!ASSERT_OK_FD(cgfd < 0, "create_cgroup")) + goto out; - /* Use libbpf 1.0 API mode */ - libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + if (!ASSERT_OK(run_tests(cgfd), "run_tests")) + goto out; - if (run_tests(cgfd)) - goto err; - - goto out; -err: - err = -1; out: close(cgfd); cleanup_cgroup_environment(); - return err; + return; } diff --git a/tools/testing/selftests/bpf/progs/sock_iter_batch.c b/tools/testing/selftests/bpf/progs/sock_iter_batch.c index 8f483337e103..77966ded5467 100644 --- a/tools/testing/selftests/bpf/progs/sock_iter_batch.c +++ b/tools/testing/selftests/bpf/progs/sock_iter_batch.c @@ -23,6 +23,7 @@ static bool ipv4_addr_loopback(__be32 a) } volatile const unsigned int sf; +volatile const unsigned int ss; volatile const __u16 ports[2]; unsigned int bucket[2]; @@ -42,16 +43,18 @@ int iter_tcp_soreuse(struct bpf_iter__tcp *ctx) sock_cookie = bpf_get_socket_cookie(sk); sk = bpf_core_cast(sk, struct sock); if (sk->sk_family != sf || - sk->sk_state != TCP_LISTEN || - sk->sk_family == AF_INET6 ? + (ss && sk->sk_state != ss) || + (sk->sk_family == AF_INET6 ? !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr) : - !ipv4_addr_loopback(sk->sk_rcv_saddr)) + !ipv4_addr_loopback(sk->sk_rcv_saddr))) return 0; if (sk->sk_num == ports[0]) idx = 0; else if (sk->sk_num == ports[1]) idx = 1; + else if (!ports[0] && !ports[1]) + idx = 0; else return 0; @@ -67,6 +70,27 @@ int iter_tcp_soreuse(struct bpf_iter__tcp *ctx) return 0; } +volatile const __u64 destroy_cookie; + +SEC("iter/tcp") +int iter_tcp_destroy(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = (struct sock_common *)ctx->sk_common; + __u64 sock_cookie; + + if (!sk_common) + return 0; + + sock_cookie = bpf_get_socket_cookie(sk_common); + if (sock_cookie != destroy_cookie) + return 0; + + bpf_sock_destroy(sk_common); + bpf_seq_write(ctx->meta->seq, &sock_cookie, sizeof(sock_cookie)); + + return 0; +} + #define udp_sk(ptr) container_of(ptr, struct udp_sock, inet.sk) SEC("iter/udp") @@ -83,15 +107,17 @@ int iter_udp_soreuse(struct bpf_iter__udp *ctx) sock_cookie = bpf_get_socket_cookie(sk); sk = bpf_core_cast(sk, struct sock); if (sk->sk_family != sf || - sk->sk_family == AF_INET6 ? + (sk->sk_family == AF_INET6 ? !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr) : - !ipv4_addr_loopback(sk->sk_rcv_saddr)) + !ipv4_addr_loopback(sk->sk_rcv_saddr))) return 0; if (sk->sk_num == ports[0]) idx = 0; else if (sk->sk_num == ports[1]) idx = 1; + else if (!ports[0] && !ports[1]) + idx = 0; else return 0; diff --git a/tools/testing/selftests/bpf/progs/test_global_map_resize.c b/tools/testing/selftests/bpf/progs/test_global_map_resize.c index a3f220ba7025..ee65bad0436d 100644 --- a/tools/testing/selftests/bpf/progs/test_global_map_resize.c +++ b/tools/testing/selftests/bpf/progs/test_global_map_resize.c @@ -32,6 +32,16 @@ int my_int_last SEC(".data.array_not_last"); int percpu_arr[1] SEC(".data.percpu_arr"); +/* at least one extern is included, to ensure that a specific + * regression is tested whereby resizing resulted in a free-after-use + * bug after type information is invalidated by the resize operation. + * + * There isn't a particularly good API to test for this specific condition, + * but by having externs for the resizing tests it will cover this path. + */ +extern int LINUX_KERNEL_VERSION __kconfig; +long version_sink; + SEC("tp/syscalls/sys_enter_getpid") int bss_array_sum(void *ctx) { @@ -44,6 +54,9 @@ int bss_array_sum(void *ctx) for (size_t i = 0; i < bss_array_len; ++i) sum += array[i]; + /* see above; ensure this is not optimized out */ + version_sink = LINUX_KERNEL_VERSION; + return 0; } @@ -59,6 +72,9 @@ int data_array_sum(void *ctx) for (size_t i = 0; i < data_array_len; ++i) sum += my_array[i]; + /* see above; ensure this is not optimized out */ + version_sink = LINUX_KERNEL_VERSION; + return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c b/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c index 8bdb9987c0c7..83df4919c224 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c @@ -7,6 +7,8 @@ int cork_byte; int push_start; int push_end; int apply_bytes; +int pop_start; +int pop_end; struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); @@ -22,6 +24,8 @@ int prog_sk_policy(struct sk_msg_md *msg) bpf_msg_cork_bytes(msg, cork_byte); if (push_start > 0 && push_end > 0) bpf_msg_push_data(msg, push_start, push_end, 0); + if (pop_start >= 0 && pop_end > 0) + bpf_msg_pop_data(msg, pop_start, pop_end, 0); return SK_PASS; } diff --git a/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c b/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c index a7c0a553aa50..3e2d76ee8050 100644 --- a/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c +++ b/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c @@ -2,6 +2,7 @@ /* Copyright (c) 2024 Google LLC. */ #include <vmlinux.h> +#include <errno.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> @@ -82,4 +83,21 @@ int BPF_PROG(path_d_path_from_file_argument, struct file *file) return 0; } +SEC("lsm.s/inode_rename") +__success +int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) +{ + struct inode *inode = new_dentry->d_inode; + ino_t ino; + + if (!inode) + return 0; + ino = inode->i_ino; + if (ino == 0) + return -EACCES; + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c b/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c index d6d3f4fcb24c..4b392c6c8fc4 100644 --- a/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c +++ b/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c @@ -2,6 +2,7 @@ /* Copyright (c) 2024 Google LLC. */ #include <vmlinux.h> +#include <errno.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> #include <linux/limits.h> @@ -158,4 +159,18 @@ int BPF_PROG(path_d_path_kfunc_non_lsm, struct path *path, struct file *f) return 0; } +SEC("lsm.s/inode_rename") +__failure __msg("invalid mem access 'trusted_ptr_or_null_'") +int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) +{ + struct inode *inode = new_dentry->d_inode; + ino_t ino; + + ino = inode->i_ino; + if (ino == 0) + return -EACCES; + return 0; +} char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c index fda7589c5023..0921939532c6 100644 --- a/tools/testing/selftests/bpf/test_lru_map.c +++ b/tools/testing/selftests/bpf/test_lru_map.c @@ -138,6 +138,18 @@ static int sched_next_online(int pid, int *next_to_try) return ret; } +/* Derive target_free from map_size, same as bpf_common_lru_populate */ +static unsigned int __tgt_size(unsigned int map_size) +{ + return (map_size / nr_cpus) / 2; +} + +/* Inverse of how bpf_common_lru_populate derives target_free from map_size. */ +static unsigned int __map_size(unsigned int tgt_free) +{ + return tgt_free * nr_cpus * 2; +} + /* Size of the LRU map is 2 * Add key=1 (+1 key) * Add key=2 (+1 key) @@ -231,11 +243,11 @@ static void test_lru_sanity0(int map_type, int map_flags) printf("Pass\n"); } -/* Size of the LRU map is 1.5*tgt_free - * Insert 1 to tgt_free (+tgt_free keys) - * Lookup 1 to tgt_free/2 - * Insert 1+tgt_free to 2*tgt_free (+tgt_free keys) - * => 1+tgt_free/2 to LOCALFREE_TARGET will be removed by LRU +/* Verify that unreferenced elements are recycled before referenced ones. + * Insert elements. + * Reference a subset of these. + * Insert more, enough to trigger recycling. + * Verify that unreferenced are recycled. */ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) { @@ -257,7 +269,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) batch_size = tgt_free / 2; assert(batch_size * 2 == tgt_free); - map_size = tgt_free + batch_size; + map_size = __map_size(tgt_free) + batch_size; lru_map_fd = create_map(map_type, map_flags, map_size); assert(lru_map_fd != -1); @@ -266,13 +278,13 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) value[0] = 1234; - /* Insert 1 to tgt_free (+tgt_free keys) */ - end_key = 1 + tgt_free; + /* Insert map_size - batch_size keys */ + end_key = 1 + __map_size(tgt_free); for (key = 1; key < end_key; key++) assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); - /* Lookup 1 to tgt_free/2 */ + /* Lookup 1 to batch_size */ end_key = 1 + batch_size; for (key = 1; key < end_key; key++) { assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value)); @@ -280,12 +292,13 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) BPF_NOEXIST)); } - /* Insert 1+tgt_free to 2*tgt_free - * => 1+tgt_free/2 to LOCALFREE_TARGET will be + /* Insert another map_size - batch_size keys + * Map will contain 1 to batch_size plus these latest, i.e., + * => previous 1+batch_size to map_size - batch_size will have been * removed by LRU */ - key = 1 + tgt_free; - end_key = key + tgt_free; + key = 1 + __map_size(tgt_free); + end_key = key + __map_size(tgt_free); for (; key < end_key; key++) { assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); @@ -301,17 +314,8 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) printf("Pass\n"); } -/* Size of the LRU map 1.5 * tgt_free - * Insert 1 to tgt_free (+tgt_free keys) - * Update 1 to tgt_free/2 - * => The original 1 to tgt_free/2 will be removed due to - * the LRU shrink process - * Re-insert 1 to tgt_free/2 again and do a lookup immeidately - * Insert 1+tgt_free to tgt_free*3/2 - * Insert 1+tgt_free*3/2 to tgt_free*5/2 - * => Key 1+tgt_free to tgt_free*3/2 - * will be removed from LRU because it has never - * been lookup and ref bit is not set +/* Verify that insertions exceeding map size will recycle the oldest. + * Verify that unreferenced elements are recycled before referenced. */ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) { @@ -334,7 +338,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) batch_size = tgt_free / 2; assert(batch_size * 2 == tgt_free); - map_size = tgt_free + batch_size; + map_size = __map_size(tgt_free) + batch_size; lru_map_fd = create_map(map_type, map_flags, map_size); assert(lru_map_fd != -1); @@ -343,8 +347,8 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) value[0] = 1234; - /* Insert 1 to tgt_free (+tgt_free keys) */ - end_key = 1 + tgt_free; + /* Insert map_size - batch_size keys */ + end_key = 1 + __map_size(tgt_free); for (key = 1; key < end_key; key++) assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); @@ -357,8 +361,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) * shrink the inactive list to get tgt_free * number of free nodes. * - * Hence, the oldest key 1 to tgt_free/2 - * are removed from the LRU list. + * Hence, the oldest key is removed from the LRU list. */ key = 1; if (map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { @@ -370,8 +373,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) BPF_EXIST)); } - /* Re-insert 1 to tgt_free/2 again and do a lookup - * immeidately. + /* Re-insert 1 to batch_size again and do a lookup immediately. */ end_key = 1 + batch_size; value[0] = 4321; @@ -387,17 +389,18 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) value[0] = 1234; - /* Insert 1+tgt_free to tgt_free*3/2 */ - end_key = 1 + tgt_free + batch_size; - for (key = 1 + tgt_free; key < end_key; key++) + /* Insert batch_size new elements */ + key = 1 + __map_size(tgt_free); + end_key = key + batch_size; + for (; key < end_key; key++) /* These newly added but not referenced keys will be * gone during the next LRU shrink. */ assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); - /* Insert 1+tgt_free*3/2 to tgt_free*5/2 */ - end_key = key + tgt_free; + /* Insert map_size - batch_size elements */ + end_key += __map_size(tgt_free); for (; key < end_key; key++) { assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); @@ -413,12 +416,12 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) printf("Pass\n"); } -/* Size of the LRU map is 2*tgt_free - * It is to test the active/inactive list rotation - * Insert 1 to 2*tgt_free (+2*tgt_free keys) - * Lookup key 1 to tgt_free*3/2 - * Add 1+2*tgt_free to tgt_free*5/2 (+tgt_free/2 keys) - * => key 1+tgt_free*3/2 to 2*tgt_free are removed from LRU +/* Test the active/inactive list rotation + * + * Fill the whole map, deplete the free list. + * Reference all except the last lru->target_free elements. + * Insert lru->target_free new elements. This triggers one shrink. + * Verify that the non-referenced elements are replaced. */ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) { @@ -437,8 +440,7 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) assert(sched_next_online(0, &next_cpu) != -1); - batch_size = tgt_free / 2; - assert(batch_size * 2 == tgt_free); + batch_size = __tgt_size(tgt_free); map_size = tgt_free * 2; lru_map_fd = create_map(map_type, map_flags, map_size); @@ -449,23 +451,21 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) value[0] = 1234; - /* Insert 1 to 2*tgt_free (+2*tgt_free keys) */ - end_key = 1 + (2 * tgt_free); + /* Fill the map */ + end_key = 1 + map_size; for (key = 1; key < end_key; key++) assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); - /* Lookup key 1 to tgt_free*3/2 */ - end_key = tgt_free + batch_size; + /* Reference all but the last batch_size */ + end_key = 1 + map_size - batch_size; for (key = 1; key < end_key; key++) { assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value)); assert(!bpf_map_update_elem(expected_map_fd, &key, value, BPF_NOEXIST)); } - /* Add 1+2*tgt_free to tgt_free*5/2 - * (+tgt_free/2 keys) - */ + /* Insert new batch_size: replaces the non-referenced elements */ key = 2 * tgt_free + 1; end_key = key + batch_size; for (; key < end_key; key++) { @@ -500,7 +500,8 @@ static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free) lru_map_fd = create_map(map_type, map_flags, 3 * tgt_free * nr_cpus); else - lru_map_fd = create_map(map_type, map_flags, 3 * tgt_free); + lru_map_fd = create_map(map_type, map_flags, + 3 * __map_size(tgt_free)); assert(lru_map_fd != -1); expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c index 0ced4026ee44..a29de0713f19 100644 --- a/tools/testing/selftests/bpf/xskxceiver.c +++ b/tools/testing/selftests/bpf/xskxceiver.c @@ -109,6 +109,8 @@ #include <network_helpers.h> +#define MAX_TX_BUDGET_DEFAULT 32 + static bool opt_verbose; static bool opt_print_tests; static enum test_mode opt_mode = TEST_MODE_ALL; @@ -1091,11 +1093,45 @@ static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) return true; } +static u32 load_value(u32 *counter) +{ + return __atomic_load_n(counter, __ATOMIC_ACQUIRE); +} + +static bool kick_tx_with_check(struct xsk_socket_info *xsk, int *ret) +{ + u32 max_budget = MAX_TX_BUDGET_DEFAULT; + u32 cons, ready_to_send; + int delta; + + cons = load_value(xsk->tx.consumer); + ready_to_send = load_value(xsk->tx.producer) - cons; + *ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + + delta = load_value(xsk->tx.consumer) - cons; + /* By default, xsk should consume exact @max_budget descs at one + * send in this case where hitting the max budget limit in while + * loop is triggered in __xsk_generic_xmit(). Please make sure that + * the number of descs to be sent is larger than @max_budget, or + * else the tx.consumer will be updated in xskq_cons_peek_desc() + * in time which hides the issue we try to verify. + */ + if (ready_to_send > max_budget && delta != max_budget) + return false; + + return true; +} + static int kick_tx(struct xsk_socket_info *xsk) { int ret; - ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + if (xsk->check_consumer) { + if (!kick_tx_with_check(xsk, &ret)) + return TEST_FAILURE; + } else { + ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + } if (ret >= 0) return TEST_PASS; if (errno == ENOBUFS || errno == EAGAIN || errno == EBUSY || errno == ENETDOWN) { @@ -2613,6 +2649,23 @@ static int testapp_adjust_tail_grow_mb(struct test_spec *test) XSK_UMEM__LARGE_FRAME_SIZE * 2); } +static int testapp_tx_queue_consumer(struct test_spec *test) +{ + int nr_packets; + + if (test->mode == TEST_MODE_ZC) { + ksft_test_result_skip("Can not run TX_QUEUE_CONSUMER test for ZC mode\n"); + return TEST_SKIP; + } + + nr_packets = MAX_TX_BUDGET_DEFAULT + 1; + pkt_stream_replace(test, nr_packets, MIN_PKT_SIZE); + test->ifobj_tx->xsk->batch_size = nr_packets; + test->ifobj_tx->xsk->check_consumer = true; + + return testapp_validate_traffic(test); +} + static void run_pkt_test(struct test_spec *test) { int ret; @@ -2723,6 +2776,7 @@ static const struct test_spec tests[] = { {.name = "XDP_ADJUST_TAIL_SHRINK_MULTI_BUFF", .test_func = testapp_adjust_tail_shrink_mb}, {.name = "XDP_ADJUST_TAIL_GROW", .test_func = testapp_adjust_tail_grow}, {.name = "XDP_ADJUST_TAIL_GROW_MULTI_BUFF", .test_func = testapp_adjust_tail_grow_mb}, + {.name = "TX_QUEUE_CONSUMER", .test_func = testapp_tx_queue_consumer}, }; static void print_tests(void) diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h index 67fc44b2813b..4df3a5d329ac 100644 --- a/tools/testing/selftests/bpf/xskxceiver.h +++ b/tools/testing/selftests/bpf/xskxceiver.h @@ -95,6 +95,7 @@ struct xsk_socket_info { u32 batch_size; u8 dst_mac[ETH_ALEN]; u8 src_mac[ETH_ALEN]; + bool check_consumer; }; struct pkt { diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c index 9984413be9f0..68f8e479ac36 100644 --- a/tools/testing/selftests/coredump/stackdump_test.c +++ b/tools/testing/selftests/coredump/stackdump_test.c @@ -461,10 +461,15 @@ TEST_F(coredump, socket_detect_userspace_client) _exit(EXIT_FAILURE); } + ret = read(fd_coredump, &c, 1); + close(fd_coredump); close(fd_server); close(fd_peer_pidfd); close(fd_core_file); + + if (ret < 1) + _exit(EXIT_FAILURE); _exit(EXIT_SUCCESS); } self->pid_coredump_server = pid_coredump_server; diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index bd309b2d3909..3556f3563e08 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -16,11 +16,13 @@ TEST_PROGS := \ netcons_fragmented_msg.sh \ netcons_overflow.sh \ netcons_sysdata.sh \ + netpoll_basic.py \ ping.py \ queues.py \ stats.py \ shaper.py \ hds.py \ + xdp.py \ # end of TEST_PROGS include ../../lib.mk diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index df2c047ffa90..fdc97355588c 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -16,6 +16,7 @@ TEST_PROGS = \ irq.py \ loopback.sh \ pp_alloc_fail.py \ + rss_api.py \ rss_ctx.py \ rss_input_xfrm.py \ tso.py \ diff --git a/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py b/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py new file mode 100755 index 000000000000..835c357919a8 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py @@ -0,0 +1,466 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +Devlink Rate TC Bandwidth Test Suite +=================================== + +This test suite verifies the functionality of devlink-rate traffic class (TC) +bandwidth distribution in a virtualized environment. The tests validate that +bandwidth can be properly allocated between different traffic classes and +that TC mapping works as expected. + +Test Environment: +---------------- +- Creates 1 VF +- Establishes a bridge connecting the VF representor and the uplink representor +- Sets up 2 VLAN interfaces on the VF with different VLAN IDs (101, 102) +- Configures different traffic classes (TC3 and TC4) for each VLAN + +Test Cases: +---------- +1. test_no_tc_mapping_bandwidth: + - Verifies that without TC mapping, bandwidth is NOT distributed according to + the configured 80/20 split between TC4 and TC3 + - This test should fail if bandwidth matches the 80/20 split without TC + mapping + - Expected: Bandwidth should NOT be distributed as 80/20 + +2. test_tc_mapping_bandwidth: + - Configures TC mapping using mqprio qdisc + - Verifies that with TC mapping, bandwidth IS distributed according to the + configured 80/20 split between TC3 and TC4 + - Expected: Bandwidth should be distributed as 80/20 + +Bandwidth Distribution: +---------------------- +- TC3 (VLAN 101): Configured for 80% of total bandwidth +- TC4 (VLAN 102): Configured for 20% of total bandwidth +- Total bandwidth: 1Gbps +- Tolerance: +-12% + +Hardware-Specific Behavior (mlx5): +-------------------------- +mlx5 hardware enforces traffic class separation by ensuring that each transmit +queue (SQ) is associated with a single TC. If a packet is sent on a queue that +doesn't match the expected TC (based on DSCP or VLAN priority and hypervisor-set +mapping), the hardware moves the queue to the correct TC scheduler to preserve +traffic isolation. + +This behavior means that even without explicit TC-to-queue mapping, bandwidth +enforcement may still appear to work—because the hardware dynamically adjusts +the scheduling context. However, this can lead to performance issues in high +rates and HOL blocking if traffic from different TCs is mixed on the same queue. +""" + +import json +import os +import subprocess +import threading +import time + +from lib.py import ksft_pr, ksft_run, ksft_exit +from lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx +from lib.py import NetDrvEpEnv, DevlinkFamily +from lib.py import NlError +from lib.py import cmd, defer, ethtool, ip + + +class BandwidthValidator: + """ + Validates bandwidth totals and per-TC shares against expected values + with a tolerance. + """ + + def __init__(self): + self.tolerance_percent = 12 + self.expected_total_gbps = 1.0 + self.total_min_expected = self.min_expected(self.expected_total_gbps) + self.total_max_expected = self.max_expected(self.expected_total_gbps) + self.tc_expected_percent = { + 3: 20.0, + 4: 80.0, + } + + def min_expected(self, value): + """Calculates the minimum acceptable value based on tolerance.""" + return value - (value * self.tolerance_percent / 100) + + def max_expected(self, value): + """Calculates the maximum acceptable value based on tolerance.""" + return value + (value * self.tolerance_percent / 100) + + def bound(self, expected, value): + """Returns True if value is within expected tolerance.""" + return self.min_expected(expected) <= value <= self.max_expected(expected) + + def tc_bandwidth_bound(self, value, tc_ix): + """ + Returns True if the given bandwidth value is within tolerance + for the TC's expected bandwidth. + """ + expected = self.tc_expected_percent[tc_ix] + return self.bound(expected, value) + + +def setup_vf(cfg, set_tc_mapping=True): + """ + Sets up a VF on the given network interface. + + Enables SR-IOV and switchdev mode, brings the VF interface up, + and optionally configures TC mapping using mqprio. + """ + try: + cmd(f"devlink dev eswitch set pci/{cfg.pci} mode switchdev") + defer(cmd, f"devlink dev eswitch set pci/{cfg.pci} mode legacy") + except Exception as exc: + raise KsftSkipEx(f"Failed to enable switchdev mode on {cfg.pci}") from exc + try: + cmd(f"echo 1 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs") + defer(cmd, f"echo 0 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs") + except Exception as exc: + raise KsftSkipEx(f"Failed to enable SR-IOV on {cfg.ifname}") from exc + + time.sleep(2) + vf_ifc = (os.listdir( + f"/sys/class/net/{cfg.ifname}/device/virtfn0/net") or [None])[0] + if vf_ifc: + ip(f"link set dev {vf_ifc} up") + else: + raise KsftSkipEx("VF interface not found") + if set_tc_mapping: + cmd(f"tc qdisc add dev {vf_ifc} root handle 5 mqprio mode dcb hw 1 num_tc 8") + + return vf_ifc + + +def setup_vlans_on_vf(vf_ifc): + """ + Sets up two VLAN interfaces on the given VF, each mapped to a different TC. + """ + vlan_configs = [ + {"vlan_id": 101, "tc": 3, "ip": "198.51.100.2"}, + {"vlan_id": 102, "tc": 4, "ip": "198.51.100.10"}, + ] + + for config in vlan_configs: + vlan_dev = f"{vf_ifc}.{config['vlan_id']}" + ip(f"link add link {vf_ifc} name {vlan_dev} type vlan id {config['vlan_id']}") + ip(f"addr add {config['ip']}/29 dev {vlan_dev}") + ip(f"link set dev {vlan_dev} up") + ip(f"link set dev {vlan_dev} type vlan egress-qos-map 0:{config['tc']}") + ksft_pr(f"Created VLAN {vlan_dev} on {vf_ifc} with tc {config['tc']} and IP {config['ip']}") + + +def get_vf_info(cfg): + """ + Finds the VF representor interface and devlink port index + for the given PCI device used in the test environment. + """ + cfg.vf_representor = None + cfg.vf_port_index = None + out = subprocess.check_output(["devlink", "-j", "port", "show"], encoding="utf-8") + ports = json.loads(out)["port"] + + for port_name, props in ports.items(): + netdev = props.get("netdev") + + if (port_name.startswith(f"pci/{cfg.pci}/") and + props.get("vfnum") == 0): + cfg.vf_representor = netdev + cfg.vf_port_index = int(port_name.split("/")[-1]) + break + + +def setup_bridge(cfg): + """ + Creates and configures a Linux bridge, with both the uplink + and VF representor interfaces attached to it. + """ + bridge_name = f"br_{os.getpid()}" + ip(f"link add name {bridge_name} type bridge") + defer(cmd, f"ip link del name {bridge_name} type bridge") + + ip(f"link set dev {cfg.ifname} master {bridge_name}") + + rep_name = cfg.vf_representor + if rep_name: + ip(f"link set dev {rep_name} master {bridge_name}") + ip(f"link set dev {rep_name} up") + ksft_pr(f"Set representor {rep_name} up and added to bridge") + else: + raise KsftSkipEx("Could not find representor for the VF") + + ip(f"link set dev {bridge_name} up") + + +def setup_devlink_rate(cfg): + """ + Configures devlink rate tx_max and traffic class bandwidth for the VF. + """ + port_index = cfg.vf_port_index + if port_index is None: + raise KsftSkipEx("Could not find VF port index") + try: + cfg.devnl.rate_set({ + "bus-name": "pci", + "dev-name": cfg.pci, + "port-index": port_index, + "rate-tx-max": 125000000, + "rate-tc-bws": [ + {"index": 0, "bw": 0}, + {"index": 1, "bw": 0}, + {"index": 2, "bw": 0}, + {"index": 3, "bw": 20}, + {"index": 4, "bw": 80}, + {"index": 5, "bw": 0}, + {"index": 6, "bw": 0}, + {"index": 7, "bw": 0}, + ] + }) + except NlError as exc: + if exc.error == 95: # EOPNOTSUPP + raise KsftSkipEx("devlink rate configuration is not supported on the VF") from exc + raise KsftFailEx(f"rate_set failed on VF port {port_index}") from exc + + +def setup_remote_server(cfg): + """ + Sets up VLAN interfaces and starts iperf3 servers on the remote side. + """ + remote_dev = cfg.remote_ifname + vlan_ids = [101, 102] + remote_ips = ["198.51.100.1", "198.51.100.9"] + + for vlan_id, ip_addr in zip(vlan_ids, remote_ips): + vlan_dev = f"{remote_dev}.{vlan_id}" + cmd(f"ip link add link {remote_dev} name {vlan_dev} " + f"type vlan id {vlan_id}", host=cfg.remote) + cmd(f"ip addr add {ip_addr}/29 dev {vlan_dev}", host=cfg.remote) + cmd(f"ip link set dev {vlan_dev} up", host=cfg.remote) + cmd(f"iperf3 -s -1 -B {ip_addr}",background=True, host=cfg.remote) + defer(cmd, f"ip link del {vlan_dev}", host=cfg.remote) + + +def setup_test_environment(cfg, set_tc_mapping=True): + """ + Sets up the complete test environment including VF creation, VLANs, + bridge configuration, devlink rate setup, and the remote server. + """ + vf_ifc = setup_vf(cfg, set_tc_mapping) + ksft_pr(f"Created VF interface: {vf_ifc}") + + setup_vlans_on_vf(vf_ifc) + + get_vf_info(cfg) + setup_bridge(cfg) + + setup_devlink_rate(cfg) + setup_remote_server(cfg) + time.sleep(2) + + +def run_iperf_client(server_ip, local_ip, barrier, min_expected_gbps=0.1): + """ + Runs a single iperf3 client instance, binding to the given local IP. + Waits on a barrier to synchronize with other threads. + """ + try: + barrier.wait(timeout=10) + except Exception as exc: + raise KsftFailEx("iperf3 barrier wait timed") from exc + + iperf_cmd = ["iperf3", "-c", server_ip, "-B", local_ip, "-J"] + result = subprocess.run(iperf_cmd, capture_output=True, text=True, + check=True) + + try: + output = json.loads(result.stdout) + bits_per_second = output["end"]["sum_received"]["bits_per_second"] + gbps = bits_per_second / 1e9 + if gbps < min_expected_gbps: + ksft_pr( + f"iperf3 bandwidth too low: {gbps:.2f} Gbps " + f"(expected ≥ {min_expected_gbps} Gbps)" + ) + return None + return gbps + except json.JSONDecodeError as exc: + ksft_pr(f"Failed to parse iperf3 JSON output: {exc}") + return None + + +def run_bandwidth_test(): + """ + Launches iperf3 client threads for each VLAN/TC pair and collects results. + """ + def _run_iperf_client_thread(server_ip, local_ip, results, barrier, tc_ix): + results[tc_ix] = run_iperf_client(server_ip, local_ip, barrier) + + vf_vlan_data = [ + # (local_ip, remote_ip, TC) + ("198.51.100.2", "198.51.100.1", 3), + ("198.51.100.10", "198.51.100.9", 4), + ] + + results = {} + threads = [] + start_barrier = threading.Barrier(len(vf_vlan_data)) + + for local_ip, remote_ip, tc_ix in vf_vlan_data: + thread = threading.Thread( + target=_run_iperf_client_thread, + args=(remote_ip, local_ip, results, start_barrier, tc_ix) + ) + thread.start() + threads.append(thread) + + for thread in threads: + thread.join() + + for tc_ix, tc_bw in results.items(): + if tc_bw is None: + raise KsftFailEx("iperf3 client failed; cannot evaluate bandwidth") + + return results + +def calculate_bandwidth_percentages(results): + """ + Calculates the percentage of total bandwidth received by TC3 and TC4. + """ + if 3 not in results or 4 not in results: + raise KsftFailEx(f"Missing expected TC results in {results}") + + tc3_bw = results[3] + tc4_bw = results[4] + total_bw = tc3_bw + tc4_bw + tc3_percentage = (tc3_bw / total_bw) * 100 + tc4_percentage = (tc4_bw / total_bw) * 100 + + return { + 'tc3_bw': tc3_bw, + 'tc4_bw': tc4_bw, + 'tc3_percentage': tc3_percentage, + 'tc4_percentage': tc4_percentage, + 'total_bw': total_bw + } + + +def print_bandwidth_results(bw_data, test_name): + """ + Prints bandwidth measurements and TC usage summary for a given test. + """ + ksft_pr(f"Bandwidth check results {test_name}:") + ksft_pr(f"TC 3: {bw_data['tc3_bw']:.2f} Gbits/sec") + ksft_pr(f"TC 4: {bw_data['tc4_bw']:.2f} Gbits/sec") + ksft_pr(f"Total bandwidth: {bw_data['total_bw']:.2f} Gbits/sec") + ksft_pr(f"TC 3 percentage: {bw_data['tc3_percentage']:.1f}%") + ksft_pr(f"TC 4 percentage: {bw_data['tc4_percentage']:.1f}%") + + +def verify_total_bandwidth(bw_data, validator): + """ + Ensures the total measured bandwidth falls within the acceptable tolerance. + """ + total = bw_data['total_bw'] + + if validator.bound(validator.expected_total_gbps, total): + return + + if total < validator.total_min_expected: + raise KsftSkipEx( + f"Total bandwidth {total:.2f} Gbps < minimum " + f"{validator.total_min_expected:.2f} Gbps; " + f"parent tx_max ({validator.expected_total_gbps:.1f} G) " + f"not reached, cannot validate share" + ) + + raise KsftFailEx( + f"Total bandwidth {total:.2f} Gbps exceeds allowed ceiling " + f"{validator.total_max_expected:.2f} Gbps " + f"(VF tx_max set to {validator.expected_total_gbps:.1f} G)" + ) + + +def check_bandwidth_distribution(bw_data, validator): + """ + Checks whether the measured TC3 and TC4 bandwidth percentages + fall within their expected tolerance ranges. + + Returns: + bool: True if both TC3 and TC4 percentages are within bounds. + """ + tc3_valid = validator.tc_bandwidth_bound(bw_data['tc3_percentage'], 3) + tc4_valid = validator.tc_bandwidth_bound(bw_data['tc4_percentage'], 4) + + return tc3_valid and tc4_valid + + +def run_bandwidth_distribution_test(cfg, set_tc_mapping): + """ + Runs parallel iperf3 tests for both TCs and collects results. + """ + setup_test_environment(cfg, set_tc_mapping) + bandwidths = run_bandwidth_test() + bw_data = calculate_bandwidth_percentages(bandwidths) + test_name = "with TC mapping" if set_tc_mapping else "without TC mapping" + print_bandwidth_results(bw_data, test_name) + + verify_total_bandwidth(bw_data, cfg.bw_validator) + + return check_bandwidth_distribution(bw_data, cfg.bw_validator) + + +def test_no_tc_mapping_bandwidth(cfg): + """ + Verifies that bandwidth is not split 80/20 without traffic class mapping. + """ + pass_bw_msg = "Bandwidth is NOT distributed as 80/20 without TC mapping" + fail_bw_msg = "Bandwidth matched 80/20 split without TC mapping" + is_mlx5 = "driver: mlx5" in ethtool(f"-i {cfg.ifname}").stdout + + if run_bandwidth_distribution_test(cfg, set_tc_mapping=False): + if is_mlx5: + raise KsftXfailEx(fail_bw_msg) + raise KsftFailEx(fail_bw_msg) + if is_mlx5: + raise KsftFailEx("mlx5 behavior changed:" + pass_bw_msg) + ksft_pr(pass_bw_msg) + + +def test_tc_mapping_bandwidth(cfg): + """ + Verifies that bandwidth is correctly split 80/20 between TC3 and TC4 + when traffic class mapping is set. + """ + if run_bandwidth_distribution_test(cfg, set_tc_mapping=True): + ksft_pr("Bandwidth is distributed as 80/20 with TC mapping") + else: + raise KsftFailEx("Bandwidth did not match 80/20 split with TC mapping") + + +def main() -> None: + """ + Main entry point for running the test cases. + """ + with NetDrvEpEnv(__file__, nsim_test=False) as cfg: + cfg.devnl = DevlinkFamily() + + cfg.pci = os.path.basename( + os.path.realpath(f"/sys/class/net/{cfg.ifname}/device") + ) + if not cfg.pci: + raise KsftSkipEx("Could not get PCI address of the interface") + cfg.require_cmd("iperf3") + cfg.require_cmd("iperf3", remote=True) + + cfg.bw_validator = BandwidthValidator() + + cases = [test_no_tc_mapping_bandwidth, test_tc_mapping_bandwidth] + + ksft_run(cases=cases, args=(cfg,)) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py index 9c03fd777f3d..712c806508b5 100755 --- a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py +++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py @@ -3,37 +3,37 @@ import re from os import path -from lib.py import ksft_run, ksft_exit +from lib.py import ksft_run, ksft_exit, KsftSkipEx from lib.py import NetDrvEpEnv from lib.py import bkg, cmd, defer, ethtool, rand_port, wait_port_listen def _get_current_settings(cfg): - output = ethtool(f"-g {cfg.ifname}", json=True, host=cfg.remote)[0] + output = ethtool(f"-g {cfg.ifname}", json=True)[0] return (output['rx'], output['hds-thresh']) def _get_combined_channels(cfg): - output = ethtool(f"-l {cfg.ifname}", host=cfg.remote).stdout + output = ethtool(f"-l {cfg.ifname}").stdout values = re.findall(r'Combined:\s+(\d+)', output) return int(values[1]) def _create_rss_ctx(cfg, chan): - output = ethtool(f"-X {cfg.ifname} context new start {chan} equal 1", host=cfg.remote).stdout + output = ethtool(f"-X {cfg.ifname} context new start {chan} equal 1").stdout values = re.search(r'New RSS context is (\d+)', output).group(1) ctx_id = int(values) - return (ctx_id, defer(ethtool, f"-X {cfg.ifname} delete context {ctx_id}", host=cfg.remote)) + return (ctx_id, defer(ethtool, f"-X {cfg.ifname} delete context {ctx_id}")) def _set_flow_rule(cfg, port, chan): - output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {port} action {chan}", host=cfg.remote).stdout + output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {port} action {chan}").stdout values = re.search(r'ID (\d+)', output).group(1) return int(values) def _set_flow_rule_rss(cfg, port, ctx_id): - output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {port} context {ctx_id}", host=cfg.remote).stdout + output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {port} context {ctx_id}").stdout values = re.search(r'ID (\d+)', output).group(1) return int(values) @@ -47,26 +47,26 @@ def test_zcrx(cfg) -> None: (rx_ring, hds_thresh) = _get_current_settings(cfg) port = rand_port() - ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote) + ethtool(f"-G {cfg.ifname} tcp-data-split on") + defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto") - ethtool(f"-G {cfg.ifname} hds-thresh 0", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}", host=cfg.remote) + ethtool(f"-G {cfg.ifname} hds-thresh 0") + defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}") - ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote) + ethtool(f"-G {cfg.ifname} rx 64") + defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}") - ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote) - defer(ethtool, f"-X {cfg.ifname} default", host=cfg.remote) + ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}") + defer(ethtool, f"-X {cfg.ifname} default") flow_rule_id = _set_flow_rule(cfg, port, combined_chans - 1) - defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote) + defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}") - rx_cmd = f"{cfg.bin_remote} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1}" - tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p {port} -l 12840" - with bkg(rx_cmd, host=cfg.remote, exit_wait=True): - wait_port_listen(port, proto="tcp", host=cfg.remote) - cmd(tx_cmd) + rx_cmd = f"{cfg.bin_local} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1}" + tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {port} -l 12840" + with bkg(rx_cmd, exit_wait=True): + wait_port_listen(port, proto="tcp") + cmd(tx_cmd, host=cfg.remote) def test_zcrx_oneshot(cfg) -> None: @@ -78,26 +78,26 @@ def test_zcrx_oneshot(cfg) -> None: (rx_ring, hds_thresh) = _get_current_settings(cfg) port = rand_port() - ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote) + ethtool(f"-G {cfg.ifname} tcp-data-split on") + defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto") - ethtool(f"-G {cfg.ifname} hds-thresh 0", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}", host=cfg.remote) + ethtool(f"-G {cfg.ifname} hds-thresh 0") + defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}") - ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote) + ethtool(f"-G {cfg.ifname} rx 64") + defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}") - ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote) - defer(ethtool, f"-X {cfg.ifname} default", host=cfg.remote) + ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}") + defer(ethtool, f"-X {cfg.ifname} default") flow_rule_id = _set_flow_rule(cfg, port, combined_chans - 1) - defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote) + defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}") - rx_cmd = f"{cfg.bin_remote} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1} -o 4" - tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p {port} -l 4096 -z 16384" - with bkg(rx_cmd, host=cfg.remote, exit_wait=True): - wait_port_listen(port, proto="tcp", host=cfg.remote) - cmd(tx_cmd) + rx_cmd = f"{cfg.bin_local} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1} -o 4" + tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {port} -l 4096 -z 16384" + with bkg(rx_cmd, exit_wait=True): + wait_port_listen(port, proto="tcp") + cmd(tx_cmd, host=cfg.remote) def test_zcrx_rss(cfg) -> None: @@ -109,27 +109,27 @@ def test_zcrx_rss(cfg) -> None: (rx_ring, hds_thresh) = _get_current_settings(cfg) port = rand_port() - ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote) + ethtool(f"-G {cfg.ifname} tcp-data-split on") + defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto") - ethtool(f"-G {cfg.ifname} hds-thresh 0", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}", host=cfg.remote) + ethtool(f"-G {cfg.ifname} hds-thresh 0") + defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}") - ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote) + ethtool(f"-G {cfg.ifname} rx 64") + defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}") - ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote) - defer(ethtool, f"-X {cfg.ifname} default", host=cfg.remote) + ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}") + defer(ethtool, f"-X {cfg.ifname} default") (ctx_id, delete_ctx) = _create_rss_ctx(cfg, combined_chans - 1) flow_rule_id = _set_flow_rule_rss(cfg, port, ctx_id) - defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote) + defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}") - rx_cmd = f"{cfg.bin_remote} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1}" - tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p {port} -l 12840" - with bkg(rx_cmd, host=cfg.remote, exit_wait=True): - wait_port_listen(port, proto="tcp", host=cfg.remote) - cmd(tx_cmd) + rx_cmd = f"{cfg.bin_local} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1}" + tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {port} -l 12840" + with bkg(rx_cmd, exit_wait=True): + wait_port_listen(port, proto="tcp") + cmd(tx_cmd, host=cfg.remote) def main() -> None: diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py index b582885786f5..1462a339a74b 100644 --- a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py @@ -7,8 +7,25 @@ KSFT_DIR = (Path(__file__).parent / "../../../../..").resolve() try: sys.path.append(KSFT_DIR.as_posix()) + from net.lib.py import * from drivers.net.lib.py import * + + # Import one by one to avoid pylint false positives + from net.lib.py import EthtoolFamily, NetdevFamily, NetshaperFamily, \ + NlError, RtnlFamily, DevlinkFamily + from net.lib.py import CmdExitFailure + from net.lib.py import bkg, cmd, defer, ethtool, fd_read_timeout, ip, \ + rand_port, tool, wait_port_listen + from net.lib.py import fd_read_timeout + from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx + from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \ + ksft_setup + from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \ + ksft_ne, ksft_not_in, ksft_raises, ksft_true + from net.lib.py import NetNSEnter + from drivers.net.lib.py import GenerateTraffic + from drivers.net.lib.py import NetDrvEnv, NetDrvEpEnv except ModuleNotFoundError as e: ksft_pr("Failed importing `net` library from kernel sources") ksft_pr(str(e)) diff --git a/tools/testing/selftests/drivers/net/hw/rss_api.py b/tools/testing/selftests/drivers/net/hw/rss_api.py new file mode 100755 index 000000000000..19847f3d4a00 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/rss_api.py @@ -0,0 +1,476 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +API level tests for RSS (mostly Netlink vs IOCTL). +""" + +import errno +import glob +import random +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_is, ksft_ne, ksft_raises +from lib.py import KsftSkipEx, KsftFailEx +from lib.py import defer, ethtool, CmdExitFailure +from lib.py import EthtoolFamily, NlError +from lib.py import NetDrvEnv + + +def _require_2qs(cfg): + qcnt = len(glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*")) + if qcnt < 2: + raise KsftSkipEx(f"Local has only {qcnt} queues") + return qcnt + + +def _ethtool_create(cfg, act, opts): + output = ethtool(f"{act} {cfg.ifname} {opts}").stdout + # Output will be something like: "New RSS context is 1" or + # "Added rule with ID 7", we want the integer from the end + return int(output.split()[-1]) + + +def _ethtool_get_cfg(cfg, fl_type, to_nl=False): + descr = ethtool(f"-n {cfg.ifname} rx-flow-hash {fl_type}").stdout + + if to_nl: + converter = { + "IP SA": "ip-src", + "IP DA": "ip-dst", + "L4 bytes 0 & 1 [TCP/UDP src port]": "l4-b-0-1", + "L4 bytes 2 & 3 [TCP/UDP dst port]": "l4-b-2-3", + } + + ret = set() + else: + converter = { + "IP SA": "s", + "IP DA": "d", + "L3 proto": "t", + "L4 bytes 0 & 1 [TCP/UDP src port]": "f", + "L4 bytes 2 & 3 [TCP/UDP dst port]": "n", + } + + ret = "" + + for line in descr.split("\n")[1:-2]: + # if this raises we probably need to add more keys to converter above + if to_nl: + ret.add(converter[line]) + else: + ret += converter[line] + return ret + + +def test_rxfh_nl_set_fail(cfg): + """ + Test error path of Netlink SET. + """ + _require_2qs(cfg) + + ethnl = EthtoolFamily() + ethnl.ntf_subscribe("monitor") + + with ksft_raises(NlError): + ethnl.rss_set({"header": {"dev-name": "lo"}, + "indir": None}) + + with ksft_raises(NlError): + ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "indir": [100000]}) + ntf = next(ethnl.poll_ntf(duration=0.2), None) + ksft_is(ntf, None) + + +def test_rxfh_nl_set_indir(cfg): + """ + Test setting indirection table via Netlink. + """ + qcnt = _require_2qs(cfg) + + # Test some SETs with a value + reset = defer(cfg.ethnl.rss_set, + {"header": {"dev-index": cfg.ifindex}, "indir": None}) + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "indir": [1]}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(set(rss.get("indir", [-1])), {1}) + + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "indir": [0, 1]}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(set(rss.get("indir", [-1])), {0, 1}) + + # Make sure we can't set the queue count below max queue used + with ksft_raises(CmdExitFailure): + ethtool(f"-L {cfg.ifname} combined 0 rx 1") + with ksft_raises(CmdExitFailure): + ethtool(f"-L {cfg.ifname} combined 1 rx 0") + + # Test reset back to default + reset.exec() + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(set(rss.get("indir", [-1])), set(range(qcnt))) + + +def test_rxfh_nl_set_indir_ctx(cfg): + """ + Test setting indirection table for a custom context via Netlink. + """ + _require_2qs(cfg) + + # Get setting for ctx 0, we'll make sure they don't get clobbered + dflt = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + + # Create context + ctx_id = _ethtool_create(cfg, "-X", "context new") + defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete") + + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "context": ctx_id, "indir": [1]}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}, + "context": ctx_id}) + ksft_eq(set(rss.get("indir", [-1])), {1}) + + ctx0 = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(ctx0, dflt) + + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "context": ctx_id, "indir": [0, 1]}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}, + "context": ctx_id}) + ksft_eq(set(rss.get("indir", [-1])), {0, 1}) + + ctx0 = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(ctx0, dflt) + + # Make sure we can't set the queue count below max queue used + with ksft_raises(CmdExitFailure): + ethtool(f"-L {cfg.ifname} combined 0 rx 1") + with ksft_raises(CmdExitFailure): + ethtool(f"-L {cfg.ifname} combined 1 rx 0") + + +def test_rxfh_indir_ntf(cfg): + """ + Check that Netlink notifications are generated when RSS indirection + table was modified. + """ + _require_2qs(cfg) + + ethnl = EthtoolFamily() + ethnl.ntf_subscribe("monitor") + + ethtool(f"--disable-netlink -X {cfg.ifname} weight 0 1") + reset = defer(ethtool, f"-X {cfg.ifname} default") + + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("No notification received") + ksft_eq(ntf["name"], "rss-ntf") + ksft_eq(set(ntf["msg"]["indir"]), {1}) + + reset.exec() + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("No notification received after reset") + ksft_eq(ntf["name"], "rss-ntf") + ksft_is(ntf["msg"].get("context"), None) + ksft_ne(set(ntf["msg"]["indir"]), {1}) + + +def test_rxfh_indir_ctx_ntf(cfg): + """ + Check that Netlink notifications are generated when RSS indirection + table was modified on an additional RSS context. + """ + _require_2qs(cfg) + + ctx_id = _ethtool_create(cfg, "-X", "context new") + defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete") + + ethnl = EthtoolFamily() + ethnl.ntf_subscribe("monitor") + + ethtool(f"--disable-netlink -X {cfg.ifname} context {ctx_id} weight 0 1") + + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("No notification received") + ksft_eq(ntf["name"], "rss-ntf") + ksft_eq(ntf["msg"].get("context"), ctx_id) + ksft_eq(set(ntf["msg"]["indir"]), {1}) + + +def test_rxfh_nl_set_key(cfg): + """ + Test setting hashing key via Netlink. + """ + + dflt = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + defer(cfg.ethnl.rss_set, + {"header": {"dev-index": cfg.ifindex}, + "hkey": dflt["hkey"], "indir": None}) + + # Empty key should error out + with ksft_raises(NlError) as cm: + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "hkey": None}) + ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.hkey') + + # Set key to random + mod = random.randbytes(len(dflt["hkey"])) + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "hkey": mod}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(rss.get("hkey", [-1]), mod) + + # Set key to random and indir tbl to something at once + mod = random.randbytes(len(dflt["hkey"])) + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "indir": [0, 1], "hkey": mod}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(rss.get("hkey", [-1]), mod) + ksft_eq(set(rss.get("indir", [-1])), {0, 1}) + + +def test_rxfh_fields(cfg): + """ + Test reading Rx Flow Hash over Netlink. + """ + + flow_types = ["tcp4", "tcp6", "udp4", "udp6"] + ethnl = EthtoolFamily() + + cfg_nl = ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + for fl_type in flow_types: + one = _ethtool_get_cfg(cfg, fl_type, to_nl=True) + ksft_eq(one, cfg_nl["flow-hash"][fl_type], + comment="Config for " + fl_type) + + +def test_rxfh_fields_set(cfg): + """ Test configuring Rx Flow Hash over Netlink. """ + + flow_types = ["tcp4", "tcp6", "udp4", "udp6"] + + # Collect current settings + cfg_old = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + # symmetric hashing is config-order-sensitive make sure we leave + # symmetric mode, or make the flow-hash sym-compatible first + changes = [{"flow-hash": cfg_old["flow-hash"],}, + {"input-xfrm": cfg_old.get("input-xfrm", {}),}] + if cfg_old.get("input-xfrm"): + changes = list(reversed(changes)) + for old in changes: + defer(cfg.ethnl.rss_set, {"header": {"dev-index": cfg.ifindex},} | old) + + # symmetric hashing prevents some of the configs below + if cfg_old.get("input-xfrm"): + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "input-xfrm": {}}) + + for fl_type in flow_types: + cur = _ethtool_get_cfg(cfg, fl_type) + if cur == "sdfn": + change_nl = {"ip-src", "ip-dst"} + change_ic = "sd" + else: + change_nl = {"l4-b-0-1", "l4-b-2-3", "ip-src", "ip-dst"} + change_ic = "sdfn" + + cfg.ethnl.rss_set({ + "header": {"dev-index": cfg.ifindex}, + "flow-hash": {fl_type: change_nl} + }) + reset = defer(ethtool, f"--disable-netlink -N {cfg.ifname} " + f"rx-flow-hash {fl_type} {cur}") + + cfg_nl = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(change_nl, cfg_nl["flow-hash"][fl_type], + comment=f"Config for {fl_type} over Netlink") + cfg_ic = _ethtool_get_cfg(cfg, fl_type) + ksft_eq(change_ic, cfg_ic, + comment=f"Config for {fl_type} over IOCTL") + + reset.exec() + cfg_nl = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(cfg_old["flow-hash"][fl_type], cfg_nl["flow-hash"][fl_type], + comment=f"Un-config for {fl_type} over Netlink") + cfg_ic = _ethtool_get_cfg(cfg, fl_type) + ksft_eq(cur, cfg_ic, comment=f"Un-config for {fl_type} over IOCTL") + + # Try to set multiple at once, the defer was already installed at the start + change = {"ip-src"} + if change == cfg_old["flow-hash"]["tcp4"]: + change = {"ip-dst"} + cfg.ethnl.rss_set({ + "header": {"dev-index": cfg.ifindex}, + "flow-hash": {x: change for x in flow_types} + }) + + cfg_nl = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + for fl_type in flow_types: + ksft_eq(change, cfg_nl["flow-hash"][fl_type], + comment=f"multi-config for {fl_type} over Netlink") + + +def test_rxfh_fields_set_xfrm(cfg): + """ Test changing Rx Flow Hash vs xfrm_input at once. """ + + def set_rss(cfg, xfrm, fh): + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "input-xfrm": xfrm, "flow-hash": fh}) + + # Install the reset handler + cfg_old = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + # symmetric hashing is config-order-sensitive make sure we leave + # symmetric mode, or make the flow-hash sym-compatible first + changes = [{"flow-hash": cfg_old["flow-hash"],}, + {"input-xfrm": cfg_old.get("input-xfrm", {}),}] + if cfg_old.get("input-xfrm"): + changes = list(reversed(changes)) + for old in changes: + defer(cfg.ethnl.rss_set, {"header": {"dev-index": cfg.ifindex},} | old) + + # Make sure we start with input-xfrm off, and tcp4 config non-sym + set_rss(cfg, {}, {}) + set_rss(cfg, {}, {"tcp4": {"ip-src"}}) + + # Setting sym and fixing tcp4 config not expected to pass right now + with ksft_raises(NlError): + set_rss(cfg, {"sym-xor"}, {"tcp4": {"ip-src", "ip-dst"}}) + # One at a time should work, hopefully + set_rss(cfg, 0, {"tcp4": {"ip-src", "ip-dst"}}) + no_support = False + try: + set_rss(cfg, {"sym-xor"}, {}) + except NlError: + try: + set_rss(cfg, {"sym-or-xor"}, {}) + except NlError: + no_support = True + if no_support: + raise KsftSkipEx("no input-xfrm supported") + # Disabling two at once should not work either without kernel changes + with ksft_raises(NlError): + set_rss(cfg, {}, {"tcp4": {"ip-src"}}) + + +def test_rxfh_fields_ntf(cfg): + """ Test Rx Flow Hash notifications. """ + + cur = _ethtool_get_cfg(cfg, "tcp4") + if cur == "sdfn": + change = {"ip-src", "ip-dst"} + else: + change = {"l4-b-0-1", "l4-b-2-3", "ip-src", "ip-dst"} + + ethnl = EthtoolFamily() + ethnl.ntf_subscribe("monitor") + + ethnl.rss_set({ + "header": {"dev-index": cfg.ifindex}, + "flow-hash": {"tcp4": change} + }) + reset = defer(ethtool, + f"--disable-netlink -N {cfg.ifname} rx-flow-hash tcp4 {cur}") + + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("No notification received after IOCTL change") + ksft_eq(ntf["name"], "rss-ntf") + ksft_eq(ntf["msg"]["flow-hash"]["tcp4"], change) + ksft_eq(next(ethnl.poll_ntf(duration=0.01), None), None) + + reset.exec() + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("No notification received after Netlink change") + ksft_eq(ntf["name"], "rss-ntf") + ksft_ne(ntf["msg"]["flow-hash"]["tcp4"], change) + ksft_eq(next(ethnl.poll_ntf(duration=0.01), None), None) + + +def test_rss_ctx_add(cfg): + """ Test creating an additional RSS context via Netlink """ + + _require_2qs(cfg) + + # Test basic creation + ctx = cfg.ethnl.rss_create_act({"header": {"dev-index": cfg.ifindex}}) + d = defer(ethtool, f"-X {cfg.ifname} context {ctx.get('context')} delete") + ksft_ne(ctx.get("context", 0), 0) + ksft_ne(set(ctx.get("indir", [0])), {0}, + comment="Driver should init the indirection table") + + # Try requesting the ID we just got allocated + with ksft_raises(NlError) as cm: + ctx = cfg.ethnl.rss_create_act({ + "header": {"dev-index": cfg.ifindex}, + "context": ctx.get("context"), + }) + ethtool(f"-X {cfg.ifname} context {ctx.get('context')} delete") + d.exec() + ksft_eq(cm.exception.nl_msg.error, -errno.EBUSY) + + # Test creating with a specified RSS table, and context ID + ctx_id = ctx.get("context") + ctx = cfg.ethnl.rss_create_act({ + "header": {"dev-index": cfg.ifindex}, + "context": ctx_id, + "indir": [1], + }) + ethtool(f"-X {cfg.ifname} context {ctx.get('context')} delete") + ksft_eq(ctx.get("context"), ctx_id) + ksft_eq(set(ctx.get("indir", [0])), {1}) + + +def test_rss_ctx_ntf(cfg): + """ Test notifications for creating additional RSS contexts """ + + ethnl = EthtoolFamily() + ethnl.ntf_subscribe("monitor") + + # Create / delete via Netlink + ctx = cfg.ethnl.rss_create_act({"header": {"dev-index": cfg.ifindex}}) + cfg.ethnl.rss_delete_act({ + "header": {"dev-index": cfg.ifindex}, + "context": ctx["context"], + }) + + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("[NL] No notification after context creation") + ksft_eq(ntf["name"], "rss-create-ntf") + ksft_eq(ctx, ntf["msg"]) + + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("[NL] No notification after context deletion") + ksft_eq(ntf["name"], "rss-delete-ntf") + + # Create / deleve via IOCTL + ctx_id = _ethtool_create(cfg, "--disable-netlink -X", "context new") + ethtool(f"--disable-netlink -X {cfg.ifname} context {ctx_id} delete") + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("[IOCTL] No notification after context creation") + ksft_eq(ntf["name"], "rss-create-ntf") + + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("[IOCTL] No notification after context deletion") + ksft_eq(ntf["name"], "rss-delete-ntf") + + +def main() -> None: + """ Ksft boiler plate main """ + + with NetDrvEnv(__file__, nsim_test=False) as cfg: + cfg.ethnl = EthtoolFamily() + ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, )) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py index f439c434ba36..6e90fb290564 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py +++ b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py @@ -37,11 +37,11 @@ def test_rss_input_xfrm(cfg, ipver): if not hasattr(socket, "SO_INCOMING_CPU"): raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11") - input_xfrm = cfg.ethnl.rss_get( - {'header': {'dev-name': cfg.ifname}}).get('input_xfrm') + rss = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}}) + input_xfrm = set(filter(lambda x: 'sym' in x, rss.get('input-xfrm', {}))) # Check for symmetric xor/or-xor - if not input_xfrm or (input_xfrm != 1 and input_xfrm != 2): + if not input_xfrm: raise KsftSkipEx("Symmetric RSS hash not requested") cpus = set() diff --git a/tools/testing/selftests/drivers/net/lib/py/__init__.py b/tools/testing/selftests/drivers/net/lib/py/__init__.py index 401e70f7f136..8711c67ad658 100644 --- a/tools/testing/selftests/drivers/net/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/lib/py/__init__.py @@ -7,7 +7,21 @@ KSFT_DIR = (Path(__file__).parent / "../../../..").resolve() try: sys.path.append(KSFT_DIR.as_posix()) + from net.lib.py import * + + # Import one by one to avoid pylint false positives + from net.lib.py import EthtoolFamily, NetdevFamily, NetshaperFamily, \ + NlError, RtnlFamily, DevlinkFamily + from net.lib.py import CmdExitFailure + from net.lib.py import bkg, cmd, bpftool, bpftrace, defer, ethtool, \ + fd_read_timeout, ip, rand_port, tool, wait_port_listen + from net.lib.py import fd_read_timeout + from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx + from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \ + ksft_setup + from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \ + ksft_ne, ksft_not_in, ksft_raises, ksft_true except ModuleNotFoundError as e: ksft_pr("Failed importing `net` library from kernel sources") ksft_pr(str(e)) diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh index 3fcf85a34596..258af805497b 100644 --- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh +++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh @@ -11,9 +11,11 @@ set -euo pipefail LIBDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") SRCIF="" # to be populated later -SRCIP=192.0.2.1 +SRCIP4="192.0.2.1" +SRCIP6="fc00::1" DSTIF="" # to be populated later -DSTIP=192.0.2.2 +DSTIP4="192.0.2.2" +DSTIP6="fc00::2" PORT="6666" MSG="netconsole selftest" @@ -80,7 +82,23 @@ function configure_ip() { ip link set "${SRCIF}" up } +function select_ipv4_or_ipv6() +{ + local VERSION=${1} + + if [[ "$VERSION" == "ipv6" ]] + then + DSTIP="${DSTIP6}" + SRCIP="${SRCIP6}" + else + DSTIP="${DSTIP4}" + SRCIP="${SRCIP4}" + fi +} + function set_network() { + local IP_VERSION=${1:-"ipv4"} + # setup_ns function is coming from lib.sh setup_ns NAMESPACE @@ -91,6 +109,7 @@ function set_network() { # Link both interfaces back to back link_ifaces + select_ipv4_or_ipv6 "${IP_VERSION}" configure_ip } @@ -119,6 +138,11 @@ function create_dynamic_target() { fi echo 1 > "${NETCONS_PATH}"/enabled + + # This will make sure that the kernel was able to + # load the netconsole driver configuration. The console message + # gets more organized/sequential as well. + sleep 1 } # Generate the command line argument for netconsole following: @@ -179,9 +203,18 @@ function set_user_data() { function listen_port_and_save_to() { local OUTPUT=${1} + local IPVERSION=${2:-"ipv4"} + + if [ "${IPVERSION}" == "ipv4" ] + then + SOCAT_MODE="UDP-LISTEN" + else + SOCAT_MODE="UDP6-LISTEN" + fi + # Just wait for 2 seconds timeout 2 ip netns exec "${NAMESPACE}" \ - socat UDP-LISTEN:"${PORT}",fork "${OUTPUT}" + socat "${SOCAT_MODE}":"${PORT}",fork "${OUTPUT}" } # Only validate that the message arrived properly @@ -263,8 +296,15 @@ function check_for_dependencies() { exit "${ksft_skip}" fi - if ip addr list | grep -E "inet.*(${SRCIP}|${DSTIP})" 2> /dev/null; then - echo "SKIP: IPs already in use. Skipping it" >&2 + REGEXP4="inet.*(${SRCIP4}|${DSTIP4})" + REGEXP6="inet.*(${SRCIP6}|${DSTIP6})" + if ip addr list | grep -E "${REGEXP4}" 2> /dev/null; then + echo "SKIP: IPv4s already in use. Skipping it" >&2 + exit "${ksft_skip}" + fi + + if ip addr list | grep -E "${REGEXP6}" 2> /dev/null; then + echo "SKIP: IPv6s already in use. Skipping it" >&2 exit "${ksft_skip}" fi } @@ -278,11 +318,13 @@ function check_for_taskset() { # This is necessary if running multiple tests in a row function pkill_socat() { - PROCESS_NAME="socat UDP-LISTEN:6666,fork ${OUTPUT_FILE}" + PROCESS_NAME4="socat UDP-LISTEN:6666,fork ${OUTPUT_FILE}" + PROCESS_NAME6="socat UDP6-LISTEN:6666,fork ${OUTPUT_FILE}" # socat runs under timeout(1), kill it if it is still alive # do not fail if socat doesn't exist anymore set +e - pkill -f "${PROCESS_NAME}" + pkill -f "${PROCESS_NAME4}" + pkill -f "${PROCESS_NAME6}" set -e } @@ -294,3 +336,23 @@ function check_netconsole_module() { exit "${ksft_skip}" fi } + +# A wrapper to translate protocol version to udp version +function wait_for_port() { + local NAMESPACE=${1} + local PORT=${2} + IP_VERSION=${3} + + if [ "${IP_VERSION}" == "ipv6" ] + then + PROTOCOL="udp6" + else + PROTOCOL="udp" + fi + + wait_local_port_listen "${NAMESPACE}" "${PORT}" "${PROTOCOL}" + # even after the port is open, let's wait 1 second before writing + # otherwise the packet could be missed, and the test will fail. Happens + # more frequently on IPv6 + sleep 1 +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh index 899b6892603f..d7505b933aef 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh @@ -51,7 +51,7 @@ for current_test in ${TESTS:-$ALL_TESTS}; do fi ${current_test}_setup_prepare - setup_wait $num_netifs + setup_wait_n $num_netifs # Update target in case occupancy of a certain resource changed # following the test setup. target=$(${current_test}_get_target "$should_fail") diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh index 482ebb744eba..7b98cdd0580d 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh @@ -55,7 +55,7 @@ for current_test in ${TESTS:-$ALL_TESTS}; do continue fi ${current_test}_setup_prepare - setup_wait $num_netifs + setup_wait_n $num_netifs # Update target in case occupancy of a certain resource # changed following the test setup. target=$(${current_test}_get_target "$should_fail") diff --git a/tools/testing/selftests/drivers/net/napi_id.py b/tools/testing/selftests/drivers/net/napi_id.py index 356bac46ba04..d05eddcad539 100755 --- a/tools/testing/selftests/drivers/net/napi_id.py +++ b/tools/testing/selftests/drivers/net/napi_id.py @@ -7,10 +7,10 @@ from lib.py import bkg, cmd, rand_port, NetNSEnter def test_napi_id(cfg) -> None: port = rand_port() - listen_cmd = f"{cfg.test_dir}/napi_id_helper {cfg.addr_v['4']} {port}" + listen_cmd = f"{cfg.test_dir}/napi_id_helper {cfg.addr} {port}" with bkg(listen_cmd, ksft_wait=3) as server: - cmd(f"echo a | socat - TCP:{cfg.addr_v['4']}:{port}", host=cfg.remote, shell=True) + cmd(f"echo a | socat - TCP:{cfg.baddr}:{port}", host=cfg.remote, shell=True) ksft_eq(0, server.ret) diff --git a/tools/testing/selftests/drivers/net/napi_id_helper.c b/tools/testing/selftests/drivers/net/napi_id_helper.c index eecd610c2109..7f49ca6c8637 100644 --- a/tools/testing/selftests/drivers/net/napi_id_helper.c +++ b/tools/testing/selftests/drivers/net/napi_id_helper.c @@ -7,41 +7,58 @@ #include <unistd.h> #include <arpa/inet.h> #include <sys/socket.h> +#include <netdb.h> #include "../../net/lib/ksft.h" int main(int argc, char *argv[]) { - struct sockaddr_in address; + struct sockaddr_storage address; + struct addrinfo *result; + struct addrinfo hints; unsigned int napi_id; - unsigned int port; + socklen_t addr_len; socklen_t optlen; char buf[1024]; int opt = 1; + int family; int server; int client; int ret; - server = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); + memset(&hints, 0, sizeof(hints)); + hints.ai_family = AF_UNSPEC; + hints.ai_socktype = SOCK_STREAM; + hints.ai_flags = AI_PASSIVE; + + ret = getaddrinfo(argv[1], argv[2], &hints, &result); + if (ret != 0) { + fprintf(stderr, "getaddrinfo: %s\n", gai_strerror(ret)); + return 1; + } + + family = result->ai_family; + addr_len = result->ai_addrlen; + + server = socket(family, SOCK_STREAM, IPPROTO_TCP); if (server < 0) { perror("socket creation failed"); + freeaddrinfo(result); if (errno == EAFNOSUPPORT) return -1; return 1; } - port = atoi(argv[2]); - if (setsockopt(server, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt))) { perror("setsockopt"); + freeaddrinfo(result); return 1; } - address.sin_family = AF_INET; - inet_pton(AF_INET, argv[1], &address.sin_addr); - address.sin_port = htons(port); + memcpy(&address, result->ai_addr, result->ai_addrlen); + freeaddrinfo(result); - if (bind(server, (struct sockaddr *)&address, sizeof(address)) < 0) { + if (bind(server, (struct sockaddr *)&address, addr_len) < 0) { perror("bind failed"); return 1; } diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh index 40a6ac6191b8..a3446b569976 100755 --- a/tools/testing/selftests/drivers/net/netcons_basic.sh +++ b/tools/testing/selftests/drivers/net/netcons_basic.sh @@ -36,30 +36,37 @@ trap cleanup EXIT # Run the test twice, with different format modes for FORMAT in "basic" "extended" do - echo "Running with target mode: ${FORMAT}" - # Create one namespace and two interfaces - set_network - # Create a dynamic target for netconsole - create_dynamic_target "${FORMAT}" - # Only set userdata for extended format - if [ "$FORMAT" == "extended" ] - then - # Set userdata "key" with the "value" value - set_user_data - fi - # Listed for netconsole port inside the namespace and destination interface - listen_port_and_save_to "${OUTPUT_FILE}" & - # Wait for socat to start and listen to the port. - wait_local_port_listen "${NAMESPACE}" "${PORT}" udp - # Send the message - echo "${MSG}: ${TARGET}" > /dev/kmsg - # Wait until socat saves the file to disk - busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" + for IP_VERSION in "ipv6" "ipv4" + do + echo "Running with target mode: ${FORMAT} (${IP_VERSION})" + # Create one namespace and two interfaces + set_network "${IP_VERSION}" + # Create a dynamic target for netconsole + create_dynamic_target "${FORMAT}" + # Only set userdata for extended format + if [ "$FORMAT" == "extended" ] + then + # Set userdata "key" with the "value" value + set_user_data + fi + # Listed for netconsole port inside the namespace and + # destination interface + listen_port_and_save_to "${OUTPUT_FILE}" "${IP_VERSION}" & + # Wait for socat to start and listen to the port. + wait_for_port "${NAMESPACE}" "${PORT}" "${IP_VERSION}" + # Send the message + echo "${MSG}: ${TARGET}" > /dev/kmsg + # Wait until socat saves the file to disk + busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" - # Make sure the message was received in the dst part - # and exit - validate_result "${OUTPUT_FILE}" "${FORMAT}" - cleanup + # Make sure the message was received in the dst part + # and exit + validate_result "${OUTPUT_FILE}" "${FORMAT}" + # kill socat in case it is still running + pkill_socat + cleanup + echo "${FORMAT} : ${IP_VERSION} : Test passed" >&2 + done done trap - EXIT diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh index b5ea2526f23c..030762b203d7 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh @@ -40,6 +40,8 @@ fw_flash_test() return fi + echo "10"> $DEBUGFS_DIR/fw_update_flash_chunk_time_ms + devlink dev flash $DL_HANDLE file $DUMMYFILE check_err $? "Failed to flash with status updates on" @@ -608,6 +610,46 @@ rate_attr_parent_check() check_err $? "Unexpected parent attr value $api_value != $parent" } +rate_attr_tc_bw_check() +{ + local handle=$1 + local tc_bw=$2 + local debug_file=$3 + + local tc_bw_str="" + for bw in $tc_bw; do + local tc=${bw%%:*} + local value=${bw##*:} + tc_bw_str="$tc_bw_str $tc:$value" + done + tc_bw_str=${tc_bw_str# } + + rate_attr_set "$handle" tc-bw "$tc_bw_str" + check_err $? "Failed to set tc-bw values" + + for bw in $tc_bw; do + local tc=${bw%%:*} + local value=${bw##*:} + local debug_value + debug_value=$(cat "$debug_file"/tc"${tc}"_bw) + check_err $? "Failed to read tc-bw value from debugfs for tc$tc" + [ "$debug_value" == "$value" ] + check_err $? "Unexpected tc-bw debug value for tc$tc: $debug_value != $value" + done + + for bw in $tc_bw; do + local tc=${bw%%:*} + local expected_value=${bw##*:} + local api_value + api_value=$(rate_attr_get "$handle" tc_"$tc") + if [ "$api_value" = "null" ]; then + api_value=0 + fi + [ "$api_value" == "$expected_value" ] + check_err $? "Unexpected tc-bw value for tc$tc: $api_value != $expected_value" + done +} + rate_node_add() { local handle=$1 @@ -649,6 +691,13 @@ rate_test() rate=$(($rate+100)) done + local tc_bw="0:0 1:40 2:0 3:0 4:0 5:0 6:60 7:0" + for r_obj in $leafs + do + rate_attr_tc_bw_check "$r_obj" "$tc_bw" \ + "$DEBUGFS_DIR"/ports/"${r_obj##*/}" + done + local node1_name='group1' local node1="$DL_HANDLE/$node1_name" rate_node_add "$node1" @@ -666,6 +715,12 @@ rate_test() rate_attr_tx_rate_check $node1 tx_max $node_tx_max \ $DEBUGFS_DIR/rate_nodes/${node1##*/}/tx_max + + local tc_bw="0:20 1:0 2:0 3:0 4:0 5:20 6:60 7:0" + rate_attr_tc_bw_check $node1 "$tc_bw" \ + "$DEBUGFS_DIR"/rate_nodes/"${node1##*/}" + + rate_node_del "$node1" check_err $? "Failed to delete node $node1" local num_nodes=`rate_nodes_get $DL_HANDLE | wc -w` diff --git a/tools/testing/selftests/drivers/net/netpoll_basic.py b/tools/testing/selftests/drivers/net/netpoll_basic.py new file mode 100755 index 000000000000..408bd54d6779 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netpoll_basic.py @@ -0,0 +1,396 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# Author: Breno Leitao <leitao@debian.org> +""" + This test aims to evaluate the netpoll polling mechanism (as in + netpoll_poll_dev()). It presents a complex scenario where the network + attempts to send a packet but fails, prompting it to poll the NIC from within + the netpoll TX side. + + This has been a crucial path in netpoll that was previously untested. Jakub + suggested using a single RX/TX queue, pushing traffic to the NIC, and then + sending netpoll messages (via netconsole) to trigger the poll. + + In parallel, bpftrace is used to detect if netpoll_poll_dev() was called. If + so, the test passes, otherwise it will be skipped. This test is very dependent on + the driver and environment, given we are trying to trigger a tricky scenario. +""" + +import errno +import logging +import os +import random +import string +import threading +import time +from typing import Optional + +from lib.py import ( + bpftrace, + CmdExitFailure, + defer, + ethtool, + GenerateTraffic, + ksft_exit, + ksft_pr, + ksft_run, + KsftFailEx, + KsftSkipEx, + NetDrvEpEnv, + KsftXfailEx, +) + +# Configure logging +logging.basicConfig( + level=logging.INFO, + format="%(asctime)s - %(levelname)s - %(message)s", +) + +NETCONSOLE_CONFIGFS_PATH: str = "/sys/kernel/config/netconsole" +NETCONS_REMOTE_PORT: int = 6666 +NETCONS_LOCAL_PORT: int = 1514 + +# Max number of netcons messages to send. Each iteration will setup +# netconsole and send MAX_WRITES messages +ITERATIONS: int = 20 +# Number of writes to /dev/kmsg per iteration +MAX_WRITES: int = 40 +# MAPS contains the information coming from bpftrace it will have only one +# key: "hits", which tells the number of times netpoll_poll_dev() was called +MAPS: dict[str, int] = {} +# Thread to run bpftrace in parallel +BPF_THREAD: Optional[threading.Thread] = None +# Time bpftrace will be running in parallel. +BPFTRACE_TIMEOUT: int = 10 + + +def ethtool_get_ringsize(interface_name: str) -> tuple[int, int]: + """ + Read the ringsize using ethtool. This will be used to restore it after the test + """ + try: + ethtool_result = ethtool(f"-g {interface_name}", json=True)[0] + rxs = ethtool_result["rx"] + txs = ethtool_result["tx"] + except (KeyError, IndexError) as exception: + raise KsftSkipEx( + f"Failed to read RX/TX ringsize: {exception}. Not going to mess with them." + ) from exception + + return rxs, txs + + +def ethtool_set_ringsize(interface_name: str, ring_size: tuple[int, int]) -> bool: + """Try to the number of RX and TX ringsize.""" + rxs = ring_size[0] + txs = ring_size[1] + + logging.debug("Setting ring size to %d/%d", rxs, txs) + try: + ethtool(f"-G {interface_name} rx {rxs} tx {txs}") + except CmdExitFailure: + # This might fail on real device, retry with a higher value, + # worst case, keep it as it is. + return False + + return True + + +def ethtool_get_queues_cnt(interface_name: str) -> tuple[int, int, int]: + """Read the number of RX, TX and combined queues using ethtool""" + + try: + ethtool_result = ethtool(f"-l {interface_name}", json=True)[0] + rxq = ethtool_result.get("rx", -1) + txq = ethtool_result.get("tx", -1) + combined = ethtool_result.get("combined", -1) + + except IndexError as exception: + raise KsftSkipEx( + f"Failed to read queues numbers: {exception}. Not going to mess with them." + ) from exception + + return rxq, txq, combined + + +def ethtool_set_queues_cnt(interface_name: str, queues: tuple[int, int, int]) -> None: + """Set the number of RX, TX and combined queues using ethtool""" + rxq, txq, combined = queues + + cmdline = f"-L {interface_name}" + + if rxq != -1: + cmdline += f" rx {rxq}" + if txq != -1: + cmdline += f" tx {txq}" + if combined != -1: + cmdline += f" combined {combined}" + + logging.debug("calling: ethtool %s", cmdline) + + try: + ethtool(cmdline) + except CmdExitFailure as exception: + raise KsftSkipEx( + f"Failed to configure RX/TX queues: {exception}. Ethtool not available?" + ) from exception + + +def netcons_generate_random_target_name() -> str: + """Generate a random target name starting with 'netcons'""" + random_suffix = "".join(random.choices(string.ascii_lowercase + string.digits, k=8)) + return f"netcons_{random_suffix}" + + +def netcons_create_target( + config_data: dict[str, str], + target_name: str, +) -> None: + """Create a netconsole dynamic target against the interfaces""" + logging.debug("Using netconsole name: %s", target_name) + try: + os.makedirs(f"{NETCONSOLE_CONFIGFS_PATH}/{target_name}", exist_ok=True) + logging.debug( + "Created target directory: %s/%s", NETCONSOLE_CONFIGFS_PATH, target_name + ) + except OSError as exception: + if exception.errno != errno.EEXIST: + raise KsftFailEx( + f"Failed to create netconsole target directory: {exception}" + ) from exception + + try: + for key, value in config_data.items(): + path = f"{NETCONSOLE_CONFIGFS_PATH}/{target_name}/{key}" + logging.debug("Writing %s to %s", key, path) + with open(path, "w", encoding="utf-8") as file: + # Always convert to string to write to file + file.write(str(value)) + + # Read all configuration values for debugging purposes + for debug_key in config_data.keys(): + with open( + f"{NETCONSOLE_CONFIGFS_PATH}/{target_name}/{debug_key}", + "r", + encoding="utf-8", + ) as file: + content = file.read() + logging.debug( + "%s/%s/%s : %s", + NETCONSOLE_CONFIGFS_PATH, + target_name, + debug_key, + content.strip(), + ) + + except Exception as exception: + raise KsftFailEx( + f"Failed to configure netconsole target: {exception}" + ) from exception + + +def netcons_configure_target( + cfg: NetDrvEpEnv, interface_name: str, target_name: str +) -> None: + """Configure netconsole on the interface with the given target name""" + config_data = { + "extended": "1", + "dev_name": interface_name, + "local_port": NETCONS_LOCAL_PORT, + "remote_port": NETCONS_REMOTE_PORT, + "local_ip": cfg.addr, + "remote_ip": cfg.remote_addr, + "remote_mac": "00:00:00:00:00:00", # Not important for this test + "enabled": "1", + } + + netcons_create_target(config_data, target_name) + logging.debug( + "Created netconsole target: %s on interface %s", target_name, interface_name + ) + + +def netcons_delete_target(name: str) -> None: + """Delete a netconsole dynamic target""" + target_path = f"{NETCONSOLE_CONFIGFS_PATH}/{name}" + try: + if os.path.exists(target_path): + os.rmdir(target_path) + except OSError as exception: + raise KsftFailEx( + f"Failed to delete netconsole target: {exception}" + ) from exception + + +def netcons_load_module() -> None: + """Try to load the netconsole module""" + os.system("modprobe netconsole") + + +def bpftrace_call() -> None: + """Call bpftrace to find how many times netpoll_poll_dev() is called. + Output is saved in the global variable `maps`""" + + # This is going to update the global variable, that will be seen by the + # main function + global MAPS # pylint: disable=W0603 + + # This will be passed to bpftrace as in bpftrace -e "expr" + expr = "kprobe:netpoll_poll_dev { @hits = count(); }" + + MAPS = bpftrace(expr, timeout=BPFTRACE_TIMEOUT, json=True) + logging.debug("BPFtrace output: %s", MAPS) + + +def bpftrace_start(): + """Start a thread to call `call_bpf` in a parallel thread""" + global BPF_THREAD # pylint: disable=W0603 + + BPF_THREAD = threading.Thread(target=bpftrace_call) + BPF_THREAD.start() + if not BPF_THREAD.is_alive(): + raise KsftSkipEx("BPFtrace thread is not alive. Skipping test") + + +def bpftrace_stop() -> None: + """Stop the bpftrace thread""" + if BPF_THREAD: + BPF_THREAD.join() + + +def bpftrace_any_hit(join: bool) -> bool: + """Check if netpoll_poll_dev() was called by checking the global variable `maps`""" + if not BPF_THREAD: + raise KsftFailEx("BPFtrace didn't start") + + if BPF_THREAD.is_alive(): + if join: + # Wait for bpftrace to finish + BPF_THREAD.join() + else: + # bpftrace is still running, so, we will not check the result yet + return False + + logging.debug("MAPS coming from bpftrace = %s", MAPS) + if "hits" not in MAPS.keys(): + raise KsftFailEx(f"bpftrace failed to run!?: {MAPS}") + + logging.debug("Got a total of %d hits", MAPS["hits"]) + return MAPS["hits"] > 0 + + +def do_netpoll_flush_monitored(cfg: NetDrvEpEnv, ifname: str, target_name: str) -> None: + """Print messages to the console, trying to trigger a netpoll poll""" + # Start bpftrace in parallel, so, it is watching + # netpoll_poll_dev() while we are sending netconsole messages + bpftrace_start() + defer(bpftrace_stop) + + do_netpoll_flush(cfg, ifname, target_name) + + if bpftrace_any_hit(join=True): + ksft_pr("netpoll_poll_dev() was called. Success") + return + + raise KsftXfailEx("netpoll_poll_dev() was not called during the test...") + + +def do_netpoll_flush(cfg: NetDrvEpEnv, ifname: str, target_name: str) -> None: + """Print messages to the console, trying to trigger a netpoll poll""" + netcons_configure_target(cfg, ifname, target_name) + retry = 0 + + for i in range(int(ITERATIONS)): + if not BPF_THREAD.is_alive() or bpftrace_any_hit(join=False): + # bpftrace is done, stop sending messages + break + + msg = f"netcons test #{i}" + with open("/dev/kmsg", "w", encoding="utf-8") as kmsg: + for j in range(MAX_WRITES): + try: + kmsg.write(f"{msg}-{j}\n") + except OSError as exception: + # in some cases, kmsg can be busy, so, we will retry + time.sleep(1) + retry += 1 + if retry < 5: + logging.info("Failed to write to kmsg. Retrying") + # Just retry a few times + continue + raise KsftFailEx( + f"Failed to write to kmsg: {exception}" + ) from exception + + netcons_delete_target(target_name) + netcons_configure_target(cfg, ifname, target_name) + # If we sleep here, we will have a better chance of triggering + # This number is based on a few tests I ran while developing this test + time.sleep(0.4) + + +def configure_network(ifname: str) -> None: + """Configure ring size and queue numbers""" + + # Set defined queues to 1 to force congestion + prev_queues = ethtool_get_queues_cnt(ifname) + logging.debug("RX/TX/combined queues: %s", prev_queues) + # Only set the queues to 1 if they exists in the device. I.e, they are > 0 + ethtool_set_queues_cnt(ifname, tuple(1 if x > 0 else x for x in prev_queues)) + defer(ethtool_set_queues_cnt, ifname, prev_queues) + + # Try to set the ring size to some low value. + # Do not fail if the hardware do not accepted desired values + prev_ring_size = ethtool_get_ringsize(ifname) + for size in [(1, 1), (128, 128), (256, 256)]: + if ethtool_set_ringsize(ifname, size): + # hardware accepted the desired ringsize + logging.debug("Set RX/TX ringsize to: %s from %s", size, prev_ring_size) + break + defer(ethtool_set_ringsize, ifname, prev_ring_size) + + +def test_netpoll(cfg: NetDrvEpEnv) -> None: + """ + Test netpoll by sending traffic to the interface and then sending + netconsole messages to trigger a poll + """ + + ifname = cfg.ifname + configure_network(ifname) + target_name = netcons_generate_random_target_name() + traffic = None + + try: + traffic = GenerateTraffic(cfg) + do_netpoll_flush_monitored(cfg, ifname, target_name) + finally: + if traffic: + traffic.stop() + + # Revert RX/TX queues + netcons_delete_target(target_name) + + +def test_check_dependencies() -> None: + """Check if the dependencies are met""" + if not os.path.exists(NETCONSOLE_CONFIGFS_PATH): + raise KsftSkipEx( + f"Directory {NETCONSOLE_CONFIGFS_PATH} does not exist. CONFIG_NETCONSOLE_DYNAMIC might not be set." # pylint: disable=C0301 + ) + + +def main() -> None: + """Main function to run the test""" + netcons_load_module() + test_check_dependencies() + with NetDrvEpEnv(__file__) as cfg: + ksft_run( + [test_netpoll], + args=(cfg,), + ) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py index efcc1e10575b..c2bb5d3f1ca1 100755 --- a/tools/testing/selftests/drivers/net/stats.py +++ b/tools/testing/selftests/drivers/net/stats.py @@ -1,12 +1,16 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 +""" +Tests related to standard netdevice statistics. +""" + import errno import subprocess import time from lib.py import ksft_run, ksft_exit, ksft_pr from lib.py import ksft_ge, ksft_eq, ksft_is, ksft_in, ksft_lt, ksft_true, ksft_raises -from lib.py import KsftSkipEx, KsftXfailEx +from lib.py import KsftSkipEx, KsftFailEx from lib.py import ksft_disruptive from lib.py import EthtoolFamily, NetdevFamily, RtnlFamily, NlError from lib.py import NetDrvEnv @@ -18,13 +22,16 @@ rtnl = RtnlFamily() def check_pause(cfg) -> None: - global ethnl + """ + Check that drivers which support Pause config also report standard + pause stats. + """ try: ethnl.pause_get({"header": {"dev-index": cfg.ifindex}}) except NlError as e: if e.error == errno.EOPNOTSUPP: - raise KsftXfailEx("pause not supported by the device") + raise KsftSkipEx("pause not supported by the device") from e raise data = ethnl.pause_get({"header": {"dev-index": cfg.ifindex, @@ -33,13 +40,16 @@ def check_pause(cfg) -> None: def check_fec(cfg) -> None: - global ethnl + """ + Check that drivers which support FEC config also report standard + FEC stats. + """ try: ethnl.fec_get({"header": {"dev-index": cfg.ifindex}}) except NlError as e: if e.error == errno.EOPNOTSUPP: - raise KsftXfailEx("FEC not supported by the device") + raise KsftSkipEx("FEC not supported by the device") from e raise data = ethnl.fec_get({"header": {"dev-index": cfg.ifindex, @@ -48,15 +58,17 @@ def check_fec(cfg) -> None: def pkt_byte_sum(cfg) -> None: - global netfam, rtnl + """ + Check that qstat and interface stats match in value. + """ def get_qstat(test): - global netfam stats = netfam.qstats_get({}, dump=True) if stats: for qs in stats: if qs["ifindex"]== test.ifindex: return qs + return None qstat = get_qstat(cfg) if qstat is None: @@ -77,15 +89,14 @@ def pkt_byte_sum(cfg) -> None: for _ in range(10): rtstat = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] if stat_cmp(rtstat, qstat) < 0: - raise Exception("RTNL stats are lower, fetched later") + raise KsftFailEx("RTNL stats are lower, fetched later") qstat = get_qstat(cfg) if stat_cmp(rtstat, qstat) > 0: - raise Exception("Qstats are lower, fetched later") + raise KsftFailEx("Qstats are lower, fetched later") def qstat_by_ifindex(cfg) -> None: - global netfam - global rtnl + """ Qstats Netlink API tests - querying by ifindex. """ # Construct a map ifindex -> [dump, by-index, dump] ifindexes = {} @@ -93,7 +104,7 @@ def qstat_by_ifindex(cfg) -> None: for entry in stats: ifindexes[entry['ifindex']] = [entry, None, None] - for ifindex in ifindexes.keys(): + for ifindex in ifindexes: entry = netfam.qstats_get({"ifindex": ifindex}, dump=True) ksft_eq(len(entry), 1) ifindexes[entry[0]['ifindex']][1] = entry[0] @@ -145,7 +156,7 @@ def qstat_by_ifindex(cfg) -> None: # Try to get stats for lowest unused ifindex but not 0 devs = rtnl.getlink({}, dump=True) - all_ifindexes = set([dev["ifi-index"] for dev in devs]) + all_ifindexes = set(dev["ifi-index"] for dev in devs) lowest = 2 while lowest in all_ifindexes: lowest += 1 @@ -158,18 +169,20 @@ def qstat_by_ifindex(cfg) -> None: @ksft_disruptive def check_down(cfg) -> None: + """ Test statistics (interface and qstat) are not impacted by ifdown """ + try: qstat = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] except NlError as e: if e.error == errno.EOPNOTSUPP: - raise KsftSkipEx("qstats not supported by the device") + raise KsftSkipEx("qstats not supported by the device") from e raise ip(f"link set dev {cfg.dev['ifname']} down") defer(ip, f"link set dev {cfg.dev['ifname']} up") qstat2 = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] - for k, v in qstat.items(): + for k in qstat: ksft_ge(qstat2[k], qstat[k], comment=f"{k} went backwards on device down") # exercise per-queue API to make sure that "device down" state @@ -263,6 +276,8 @@ def procfs_downup_hammer(cfg) -> None: def main() -> None: + """ Ksft boiler plate main """ + with NetDrvEnv(__file__, queue_count=100) as cfg: ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex, check_down, procfs_hammer, procfs_downup_hammer], diff --git a/tools/testing/selftests/drivers/net/xdp.py b/tools/testing/selftests/drivers/net/xdp.py new file mode 100755 index 000000000000..887d662ad128 --- /dev/null +++ b/tools/testing/selftests/drivers/net/xdp.py @@ -0,0 +1,656 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +This file contains tests to verify native XDP support in network drivers. +The tests utilize the BPF program `xdp_native.bpf.o` from the `selftests.net.lib` +directory, with each test focusing on a specific aspect of XDP functionality. +""" +import random +import string +from dataclasses import dataclass +from enum import Enum + +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ne, ksft_pr +from lib.py import KsftFailEx, NetDrvEpEnv, EthtoolFamily, NlError +from lib.py import bkg, cmd, rand_port +from lib.py import ip, bpftool, defer + + +class TestConfig(Enum): + """Enum for XDP configuration options.""" + MODE = 0 # Configures the BPF program for a specific test + PORT = 1 # Port configuration to communicate with the remote host + ADJST_OFFSET = 2 # Tail/Head adjustment offset for extension/shrinking + ADJST_TAG = 3 # Adjustment tag to annotate the start and end of extension + + +class XDPAction(Enum): + """Enum for XDP actions.""" + PASS = 0 # Pass the packet up to the stack + DROP = 1 # Drop the packet + TX = 2 # Route the packet to the remote host + TAIL_ADJST = 3 # Adjust the tail of the packet + HEAD_ADJST = 4 # Adjust the head of the packet + + +class XDPStats(Enum): + """Enum for XDP statistics.""" + RX = 0 # Count of valid packets received for testing + PASS = 1 # Count of packets passed up to the stack + DROP = 2 # Count of packets dropped + TX = 3 # Count of incoming packets routed to the remote host + ABORT = 4 # Count of packets that were aborted + + +@dataclass +class BPFProgInfo: + """Data class to store information about a BPF program.""" + name: str # Name of the BPF program + file: str # BPF program object file + xdp_sec: str = "xdp" # XDP section name (e.g., "xdp" or "xdp.frags") + mtu: int = 1500 # Maximum Transmission Unit, default is 1500 + + +def _exchg_udp(cfg, port, test_string): + """ + Exchanges UDP packets between a local and remote host using the socat tool. + + Args: + cfg: Configuration object containing network settings. + port: Port number to use for the UDP communication. + test_string: String that the remote host will send. + + Returns: + The string received by the test host. + """ + cfg.require_cmd("socat", remote=True) + + rx_udp_cmd = f"socat -{cfg.addr_ipver} -T 2 -u UDP-RECV:{port},reuseport STDOUT" + tx_udp_cmd = f"echo -n {test_string} | socat -t 2 -u STDIN UDP:{cfg.baddr}:{port}" + + with bkg(rx_udp_cmd, exit_wait=True) as nc: + cmd(tx_udp_cmd, host=cfg.remote, shell=True) + + return nc.stdout.strip() + + +def _test_udp(cfg, port, size=256): + """ + Tests UDP packet exchange between a local and remote host. + + Args: + cfg: Configuration object containing network settings. + port: Port number to use for the UDP communication. + size: The length of the test string to be exchanged, default is 256 characters. + + Returns: + bool: True if the received string matches the sent string, False otherwise. + """ + test_str = "".join(random.choice(string.ascii_lowercase) for _ in range(size)) + recvd_str = _exchg_udp(cfg, port, test_str) + + return recvd_str == test_str + + +def _load_xdp_prog(cfg, bpf_info): + """ + Loads an XDP program onto a network interface. + + Args: + cfg: Configuration object containing network settings. + bpf_info: BPFProgInfo object containing information about the BPF program. + + Returns: + dict: A dictionary containing the XDP program ID, name, and associated map IDs. + """ + abs_path = cfg.net_lib_dir / bpf_info.file + prog_info = {} + + cmd(f"ip link set dev {cfg.remote_ifname} mtu {bpf_info.mtu}", shell=True, host=cfg.remote) + defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote) + + cmd( + f"ip link set dev {cfg.ifname} mtu {bpf_info.mtu} xdp obj {abs_path} sec {bpf_info.xdp_sec}", + shell=True + ) + defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off") + + xdp_info = ip(f"-d link show dev {cfg.ifname}", json=True)[0] + prog_info["id"] = xdp_info["xdp"]["prog"]["id"] + prog_info["name"] = xdp_info["xdp"]["prog"]["name"] + prog_id = prog_info["id"] + + map_ids = bpftool(f"prog show id {prog_id}", json=True)["map_ids"] + prog_info["maps"] = {} + for map_id in map_ids: + name = bpftool(f"map show id {map_id}", json=True)["name"] + prog_info["maps"][name] = map_id + + return prog_info + + +def format_hex_bytes(value): + """ + Helper function that converts an integer into a formatted hexadecimal byte string. + + Args: + value: An integer representing the number to be converted. + + Returns: + A string representing hexadecimal equivalent of value, with bytes separated by spaces. + """ + hex_str = value.to_bytes(4, byteorder='little', signed=True) + return ' '.join(f'{byte:02x}' for byte in hex_str) + + +def _set_xdp_map(map_name, key, value): + """ + Updates an XDP map with a given key-value pair using bpftool. + + Args: + map_name: The name of the XDP map to update. + key: The key to update in the map, formatted as a hexadecimal string. + value: The value to associate with the key, formatted as a hexadecimal string. + """ + key_formatted = format_hex_bytes(key) + value_formatted = format_hex_bytes(value) + bpftool( + f"map update name {map_name} key hex {key_formatted} value hex {value_formatted}" + ) + + +def _get_stats(xdp_map_id): + """ + Retrieves and formats statistics from an XDP map. + + Args: + xdp_map_id: The ID of the XDP map from which to retrieve statistics. + + Returns: + A dictionary containing formatted packet statistics for various XDP actions. + The keys are based on the XDPStats Enum values. + + Raises: + KsftFailEx: If the stats retrieval fails. + """ + stats_dump = bpftool(f"map dump id {xdp_map_id}", json=True) + if not stats_dump: + raise KsftFailEx(f"Failed to get stats for map {xdp_map_id}") + + stats_formatted = {} + for key in range(0, 5): + val = stats_dump[key]["formatted"]["value"] + if stats_dump[key]["formatted"]["key"] == XDPStats.RX.value: + stats_formatted[XDPStats.RX.value] = val + elif stats_dump[key]["formatted"]["key"] == XDPStats.PASS.value: + stats_formatted[XDPStats.PASS.value] = val + elif stats_dump[key]["formatted"]["key"] == XDPStats.DROP.value: + stats_formatted[XDPStats.DROP.value] = val + elif stats_dump[key]["formatted"]["key"] == XDPStats.TX.value: + stats_formatted[XDPStats.TX.value] = val + elif stats_dump[key]["formatted"]["key"] == XDPStats.ABORT.value: + stats_formatted[XDPStats.ABORT.value] = val + + return stats_formatted + + +def _test_pass(cfg, bpf_info, msg_sz): + """ + Tests the XDP_PASS action by exchanging UDP packets. + + Args: + cfg: Configuration object containing network settings. + bpf_info: BPFProgInfo object containing information about the BPF program. + msg_sz: Size of the test message to send. + """ + + prog_info = _load_xdp_prog(cfg, bpf_info) + port = rand_port() + + _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.PASS.value) + _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port) + + ksft_eq(_test_udp(cfg, port, msg_sz), True, "UDP packet exchange failed") + stats = _get_stats(prog_info["maps"]["map_xdp_stats"]) + + ksft_ne(stats[XDPStats.RX.value], 0, "RX stats should not be zero") + ksft_eq(stats[XDPStats.RX.value], stats[XDPStats.PASS.value], "RX and PASS stats mismatch") + + +def test_xdp_native_pass_sb(cfg): + """ + Tests the XDP_PASS action for single buffer case. + + Args: + cfg: Configuration object containing network settings. + """ + bpf_info = BPFProgInfo("xdp_prog", "xdp_native.bpf.o", "xdp", 1500) + + _test_pass(cfg, bpf_info, 256) + + +def test_xdp_native_pass_mb(cfg): + """ + Tests the XDP_PASS action for a multi-buff size. + + Args: + cfg: Configuration object containing network settings. + """ + bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o", "xdp.frags", 9000) + + _test_pass(cfg, bpf_info, 8000) + + +def _test_drop(cfg, bpf_info, msg_sz): + """ + Tests the XDP_DROP action by exchanging UDP packets. + + Args: + cfg: Configuration object containing network settings. + bpf_info: BPFProgInfo object containing information about the BPF program. + msg_sz: Size of the test message to send. + """ + + prog_info = _load_xdp_prog(cfg, bpf_info) + port = rand_port() + + _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.DROP.value) + _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port) + + ksft_eq(_test_udp(cfg, port, msg_sz), False, "UDP packet exchange should fail") + stats = _get_stats(prog_info["maps"]["map_xdp_stats"]) + + ksft_ne(stats[XDPStats.RX.value], 0, "RX stats should be zero") + ksft_eq(stats[XDPStats.RX.value], stats[XDPStats.DROP.value], "RX and DROP stats mismatch") + + +def test_xdp_native_drop_sb(cfg): + """ + Tests the XDP_DROP action for a signle-buff case. + + Args: + cfg: Configuration object containing network settings. + """ + bpf_info = BPFProgInfo("xdp_prog", "xdp_native.bpf.o", "xdp", 1500) + + _test_drop(cfg, bpf_info, 256) + + +def test_xdp_native_drop_mb(cfg): + """ + Tests the XDP_DROP action for a multi-buff case. + + Args: + cfg: Configuration object containing network settings. + """ + bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o", "xdp.frags", 9000) + + _test_drop(cfg, bpf_info, 8000) + + +def test_xdp_native_tx_mb(cfg): + """ + Tests the XDP_TX action for a multi-buff case. + + Args: + cfg: Configuration object containing network settings. + """ + cfg.require_cmd("socat", remote=True) + + bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o", "xdp.frags", 9000) + prog_info = _load_xdp_prog(cfg, bpf_info) + port = rand_port() + + _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.TX.value) + _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port) + + test_string = ''.join(random.choice(string.ascii_lowercase) for _ in range(8000)) + rx_udp = f"socat -{cfg.addr_ipver} -T 2 -u UDP-RECV:{port},reuseport STDOUT" + tx_udp = f"echo {test_string} | socat -t 2 -u STDIN UDP:{cfg.baddr}:{port}" + + with bkg(rx_udp, host=cfg.remote, exit_wait=True) as rnc: + cmd(tx_udp, host=cfg.remote, shell=True) + + stats = _get_stats(prog_info['maps']['map_xdp_stats']) + + ksft_eq(rnc.stdout.strip(), test_string, "UDP packet exchange failed") + ksft_eq(stats[XDPStats.TX.value], 1, "TX stats mismatch") + + +def _validate_res(res, offset_lst, pkt_sz_lst): + """ + Validates the result of a test. + + Args: + res: The result of the test, which should be a dictionary with a "status" key. + + Raises: + KsftFailEx: If the test fails to pass any combination of offset and packet size. + """ + if "status" not in res: + raise KsftFailEx("Missing 'status' key in result dictionary") + + # Validate that not a single case was successful + if res["status"] == "fail": + if res["offset"] == offset_lst[0] and res["pkt_sz"] == pkt_sz_lst[0]: + raise KsftFailEx(f"{res['reason']}") + + # Get the previous offset and packet size to report the successful run + tmp_idx = offset_lst.index(res["offset"]) + prev_offset = offset_lst[tmp_idx - 1] + if tmp_idx == 0: + tmp_idx = pkt_sz_lst.index(res["pkt_sz"]) + prev_pkt_sz = pkt_sz_lst[tmp_idx - 1] + else: + prev_pkt_sz = res["pkt_sz"] + + # Use these values for error reporting + ksft_pr( + f"Failed run: pkt_sz {res['pkt_sz']}, offset {res['offset']}. " + f"Last successful run: pkt_sz {prev_pkt_sz}, offset {prev_offset}. " + f"Reason: {res['reason']}" + ) + + +def _check_for_failures(recvd_str, stats): + """ + Checks for common failures while adjusting headroom or tailroom. + + Args: + recvd_str: The string received from the remote host after sending a test string. + stats: A dictionary containing formatted packet statistics for various XDP actions. + + Returns: + str: A string describing the failure reason if a failure is detected, otherwise None. + """ + + # Any adjustment failure result in an abort hence, we track this counter + if stats[XDPStats.ABORT.value] != 0: + return "Adjustment failed" + + # Since we are using aggregate stats for a single test across all offsets and packet sizes + # we can't use RX stats only to track data exchange failure without taking a previous + # snapshot. An easier way is to simply check for non-zero length of received string. + if len(recvd_str) == 0: + return "Data exchange failed" + + # Check for RX and PASS stats mismatch. Ideally, they should be equal for a successful run + if stats[XDPStats.RX.value] != stats[XDPStats.PASS.value]: + return "RX stats mismatch" + + return None + + +def _test_xdp_native_tail_adjst(cfg, pkt_sz_lst, offset_lst): + """ + Tests the XDP tail adjustment functionality. + + This function loads the appropriate XDP program based on the provided + program name and configures the XDP map for tail adjustment. It then + validates the tail adjustment by sending and receiving UDP packets + with specified packet sizes and offsets. + + Args: + cfg: Configuration object containing network settings. + prog: Name of the XDP program to load. + pkt_sz_lst: List of packet sizes to test. + offset_lst: List of offsets to validate support for tail adjustment. + + Returns: + dict: A dictionary with test status and failure details if applicable. + """ + port = rand_port() + bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o", "xdp.frags", 9000) + + prog_info = _load_xdp_prog(cfg, bpf_info) + + # Configure the XDP map for tail adjustment + _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.TAIL_ADJST.value) + _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port) + + for offset in offset_lst: + tag = format(random.randint(65, 90), "02x") + + _set_xdp_map("map_xdp_setup", TestConfig.ADJST_OFFSET.value, offset) + if offset > 0: + _set_xdp_map("map_xdp_setup", TestConfig.ADJST_TAG.value, int(tag, 16)) + + for pkt_sz in pkt_sz_lst: + test_str = "".join(random.choice(string.ascii_lowercase) for _ in range(pkt_sz)) + recvd_str = _exchg_udp(cfg, port, test_str) + stats = _get_stats(prog_info["maps"]["map_xdp_stats"]) + + failure = _check_for_failures(recvd_str, stats) + if failure is not None: + return { + "status": "fail", + "reason": failure, + "offset": offset, + "pkt_sz": pkt_sz, + } + + # Validate data content based on offset direction + expected_data = None + if offset > 0: + expected_data = test_str + (offset * chr(int(tag, 16))) + else: + expected_data = test_str[0:pkt_sz + offset] + + if recvd_str != expected_data: + return { + "status": "fail", + "reason": "Data mismatch", + "offset": offset, + "pkt_sz": pkt_sz, + } + + return {"status": "pass"} + + +def test_xdp_native_adjst_tail_grow_data(cfg): + """ + Tests the XDP tail adjustment by growing packet data. + + Args: + cfg: Configuration object containing network settings. + """ + pkt_sz_lst = [512, 1024, 2048] + offset_lst = [1, 16, 32, 64, 128, 256] + res = _test_xdp_native_tail_adjst( + cfg, + pkt_sz_lst, + offset_lst, + ) + + _validate_res(res, offset_lst, pkt_sz_lst) + + +def test_xdp_native_adjst_tail_shrnk_data(cfg): + """ + Tests the XDP tail adjustment by shrinking packet data. + + Args: + cfg: Configuration object containing network settings. + """ + pkt_sz_lst = [512, 1024, 2048] + offset_lst = [-16, -32, -64, -128, -256] + res = _test_xdp_native_tail_adjst( + cfg, + pkt_sz_lst, + offset_lst, + ) + + _validate_res(res, offset_lst, pkt_sz_lst) + + +def get_hds_thresh(cfg): + """ + Retrieves the header data split (HDS) threshold for a network interface. + + Args: + cfg: Configuration object containing network settings. + + Returns: + The HDS threshold value. If the threshold is not supported or an error occurs, + a default value of 1500 is returned. + """ + netnl = cfg.netnl + hds_thresh = 1500 + + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + if 'hds-thresh' not in rings: + ksft_pr(f'hds-thresh not supported. Using default: {hds_thresh}') + return hds_thresh + hds_thresh = rings['hds-thresh'] + except NlError as e: + ksft_pr(f"Failed to get rings: {e}. Using default: {hds_thresh}") + + return hds_thresh + + +def _test_xdp_native_head_adjst(cfg, prog, pkt_sz_lst, offset_lst): + """ + Tests the XDP head adjustment action for a multi-buffer case. + + Args: + cfg: Configuration object containing network settings. + netnl: Network namespace or link object (not used in this function). + + This function sets up the packet size and offset lists, then performs + the head adjustment test by sending and receiving UDP packets. + """ + cfg.require_cmd("socat", remote=True) + + prog_info = _load_xdp_prog(cfg, BPFProgInfo(prog, "xdp_native.bpf.o", "xdp.frags", 9000)) + port = rand_port() + + _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.HEAD_ADJST.value) + _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port) + + hds_thresh = get_hds_thresh(cfg) + for offset in offset_lst: + for pkt_sz in pkt_sz_lst: + # The "head" buffer must contain at least the Ethernet header + # after we eat into it. We send large-enough packets, but if HDS + # is enabled head will only contain headers. Don't try to eat + # more than 28 bytes (UDPv4 + eth hdr left: (14 + 20 + 8) - 14) + l2_cut_off = 28 if cfg.addr_ipver == 4 else 48 + if pkt_sz > hds_thresh and offset > l2_cut_off: + ksft_pr( + f"Failed run: pkt_sz ({pkt_sz}) > HDS threshold ({hds_thresh}) and " + f"offset {offset} > {l2_cut_off}" + ) + return {"status": "pass"} + + test_str = ''.join(random.choice(string.ascii_lowercase) for _ in range(pkt_sz)) + tag = format(random.randint(65, 90), '02x') + + _set_xdp_map("map_xdp_setup", + TestConfig.ADJST_OFFSET.value, + offset) + _set_xdp_map("map_xdp_setup", TestConfig.ADJST_TAG.value, int(tag, 16)) + _set_xdp_map("map_xdp_setup", TestConfig.ADJST_OFFSET.value, offset) + + recvd_str = _exchg_udp(cfg, port, test_str) + + # Check for failures around adjustment and data exchange + failure = _check_for_failures(recvd_str, _get_stats(prog_info['maps']['map_xdp_stats'])) + if failure is not None: + return { + "status": "fail", + "reason": failure, + "offset": offset, + "pkt_sz": pkt_sz + } + + # Validate data content based on offset direction + expected_data = None + if offset < 0: + expected_data = chr(int(tag, 16)) * (0 - offset) + test_str + else: + expected_data = test_str[offset:] + + if recvd_str != expected_data: + return { + "status": "fail", + "reason": "Data mismatch", + "offset": offset, + "pkt_sz": pkt_sz + } + + return {"status": "pass"} + + +def test_xdp_native_adjst_head_grow_data(cfg): + """ + Tests the XDP headroom growth support. + + Args: + cfg: Configuration object containing network settings. + + This function sets up the packet size and offset lists, then calls the + _test_xdp_native_head_adjst_mb function to perform the actual test. The + test is passed if the headroom is successfully extended for given packet + sizes and offsets. + """ + pkt_sz_lst = [512, 1024, 2048] + + # Negative values result in headroom shrinking, resulting in growing of payload + offset_lst = [-16, -32, -64, -128, -256] + res = _test_xdp_native_head_adjst(cfg, "xdp_prog_frags", pkt_sz_lst, offset_lst) + + _validate_res(res, offset_lst, pkt_sz_lst) + + +def test_xdp_native_adjst_head_shrnk_data(cfg): + """ + Tests the XDP headroom shrinking support. + + Args: + cfg: Configuration object containing network settings. + + This function sets up the packet size and offset lists, then calls the + _test_xdp_native_head_adjst_mb function to perform the actual test. The + test is passed if the headroom is successfully shrunk for given packet + sizes and offsets. + """ + pkt_sz_lst = [512, 1024, 2048] + + # Positive values result in headroom growing, resulting in shrinking of payload + offset_lst = [16, 32, 64, 128, 256] + res = _test_xdp_native_head_adjst(cfg, "xdp_prog_frags", pkt_sz_lst, offset_lst) + + _validate_res(res, offset_lst, pkt_sz_lst) + + +def main(): + """ + Main function to execute the XDP tests. + + This function runs a series of tests to validate the XDP support for + both the single and multi-buffer. It uses the NetDrvEpEnv context + manager to manage the network driver environment and the ksft_run + function to execute the tests. + """ + with NetDrvEpEnv(__file__) as cfg: + cfg.netnl = EthtoolFamily() + ksft_run( + [ + test_xdp_native_pass_sb, + test_xdp_native_pass_mb, + test_xdp_native_drop_sb, + test_xdp_native_drop_mb, + test_xdp_native_tx_mb, + test_xdp_native_adjst_tail_grow_data, + test_xdp_native_adjst_tail_shrnk_data, + test_xdp_native_adjst_head_grow_data, + test_xdp_native_adjst_head_shrnk_data, + ], + args=(cfg,)) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/futex/functional/.gitignore b/tools/testing/selftests/futex/functional/.gitignore index 7b24ae89594a..776ad658f75e 100644 --- a/tools/testing/selftests/futex/functional/.gitignore +++ b/tools/testing/selftests/futex/functional/.gitignore @@ -11,3 +11,4 @@ futex_wait_timeout futex_wait_uninitialized_heap futex_wait_wouldblock futex_waitv +futex_numa diff --git a/tools/testing/selftests/futex/functional/futex_numa_mpol.c b/tools/testing/selftests/futex/functional/futex_numa_mpol.c index 20a9d3ecf743..a9ecfb2d3932 100644 --- a/tools/testing/selftests/futex/functional/futex_numa_mpol.c +++ b/tools/testing/selftests/futex/functional/futex_numa_mpol.c @@ -144,7 +144,7 @@ int main(int argc, char *argv[]) struct futex32_numa *futex_numa; int mem_size, i; void *futex_ptr; - char c; + int c; while ((c = getopt(argc, argv, "chv:")) != -1) { switch (c) { @@ -210,6 +210,10 @@ int main(int argc, char *argv[]) ret = mbind(futex_ptr, mem_size, MPOL_BIND, &nodemask, sizeof(nodemask) * 8, 0); if (ret == 0) { + ret = numa_set_mempolicy_home_node(futex_ptr, mem_size, i, 0); + if (ret != 0) + ksft_exit_fail_msg("Failed to set home node: %m, %d\n", errno); + ksft_print_msg("Node %d test\n", i); futex_numa->futex = 0; futex_numa->numa = FUTEX_NO_NODE; @@ -220,8 +224,8 @@ int main(int argc, char *argv[]) if (0) test_futex_mpol(futex_numa, 0); if (futex_numa->numa != i) { - ksft_test_result_fail("Returned NUMA node is %d expected %d\n", - futex_numa->numa, i); + ksft_exit_fail_msg("Returned NUMA node is %d expected %d\n", + futex_numa->numa, i); } } } diff --git a/tools/testing/selftests/futex/functional/futex_priv_hash.c b/tools/testing/selftests/futex/functional/futex_priv_hash.c index 2dca18fefedc..24a92dc94eb8 100644 --- a/tools/testing/selftests/futex/functional/futex_priv_hash.c +++ b/tools/testing/selftests/futex/functional/futex_priv_hash.c @@ -130,7 +130,7 @@ int main(int argc, char *argv[]) pthread_mutexattr_t mutex_attr_pi; int use_global_hash = 0; int ret; - char c; + int c; while ((c = getopt(argc, argv, "cghv:")) != -1) { switch (c) { diff --git a/tools/testing/selftests/hid/tests/test_mouse.py b/tools/testing/selftests/hid/tests/test_mouse.py index 66daf7e5975c..eb4e15a0e53b 100644 --- a/tools/testing/selftests/hid/tests/test_mouse.py +++ b/tools/testing/selftests/hid/tests/test_mouse.py @@ -439,6 +439,68 @@ class BadResolutionMultiplierMouse(ResolutionMultiplierMouse): return 32 # EPIPE +class BadReportDescriptorMouse(BaseMouse): + """ + This "device" was one autogenerated by syzbot. There are a lot of issues in + it, and the most problematic is that it declares features that have no + size. + + This leads to report->size being set to 0 and can mess up with usbhid + internals. Fortunately, uhid merely passes the incoming buffer, without + touching it so a buffer of size 0 will be translated to [] without + triggering a kernel oops. + + Because the report descriptor is wrong, no input are created, and we need + to tweak a little bit the parameters to make it look correct. + """ + + # fmt: off + report_descriptor = [ + 0x96, 0x01, 0x00, # Report Count (1) 0 + 0x06, 0x01, 0x00, # Usage Page (Generic Desktop) 3 + # 0x03, 0x00, 0x00, 0x00, 0x00, # Ignored by the kernel somehow + 0x2a, 0x90, 0xa0, # Usage Maximum (41104) 6 + 0x27, 0x00, 0x00, 0x00, 0x00, # Logical Maximum (0) 9 + 0xb3, 0x81, 0x3e, 0x25, 0x03, # Feature (Cnst,Arr,Abs,Vol) 14 + 0x1b, 0xdd, 0xe8, 0x40, 0x50, # Usage Minimum (1346431197) 19 + 0x3b, 0x5d, 0x8c, 0x3d, 0xda, # Designator Index 24 + ] + # fmt: on + + def __init__( + self, rdesc=report_descriptor, name=None, input_info=(3, 0x045E, 0x07DA) + ): + super().__init__(rdesc, name, input_info) + self.high_resolution_report_called = False + + def get_evdev(self, application=None): + assert self._input_nodes is None + return ( + "Ok" # should be a list or None, but both would fail, so abusing the system + ) + + def next_sync_events(self, application=None): + # there are no evdev nodes, so no events + return [] + + def is_ready(self): + # we wait for the SET_REPORT command to come + return self.high_resolution_report_called + + def set_report(self, req, rnum, rtype, data): + if rtype != self.UHID_FEATURE_REPORT: + raise InvalidHIDCommunication(f"Unexpected report type: {rtype}") + if rnum != 0x0: + raise InvalidHIDCommunication(f"Unexpected report number: {rnum}") + + if len(data) != 1: + raise InvalidHIDCommunication(f"Unexpected data: {data}, expected '[0]'") + + self.high_resolution_report_called = True + + return 0 + + class ResolutionMultiplierHWheelMouse(TwoWheelMouse): # fmt: off report_descriptor = [ @@ -975,3 +1037,11 @@ class TestMiMouse(TestWheelMouse): # assert below print out the real error pass assert remaining == [] + + +class TestBadReportDescriptorMouse(base.BaseTestCase.TestUhid): + def create_device(self): + return BadReportDescriptorMouse() + + def assertName(self, uhdev): + pass diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 1a8e85afe9aa..1926ef6b40ab 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -54,6 +54,8 @@ static __attribute__((constructor)) void setup_sizes(void) mfd_buffer = memfd_mmap(BUFFER_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, &mfd); + assert(mfd_buffer != MAP_FAILED); + assert(mfd > 0); } FIXTURE(iommufd) @@ -1746,13 +1748,15 @@ TEST_F(iommufd_mock_domain, all_aligns) unsigned int end; uint8_t *buf; int prot = PROT_READ | PROT_WRITE; - int mfd; + int mfd = -1; if (variant->file) buf = memfd_mmap(buf_size, prot, MAP_SHARED, &mfd); else buf = mmap(0, buf_size, prot, self->mmap_flags, -1, 0); ASSERT_NE(MAP_FAILED, buf); + if (variant->file) + ASSERT_GT(mfd, 0); check_refs(buf, buf_size, 0); /* @@ -1798,13 +1802,15 @@ TEST_F(iommufd_mock_domain, all_aligns_copy) unsigned int end; uint8_t *buf; int prot = PROT_READ | PROT_WRITE; - int mfd; + int mfd = -1; if (variant->file) buf = memfd_mmap(buf_size, prot, MAP_SHARED, &mfd); else buf = mmap(0, buf_size, prot, self->mmap_flags, -1, 0); ASSERT_NE(MAP_FAILED, buf); + if (variant->file) + ASSERT_GT(mfd, 0); check_refs(buf, buf_size, 0); /* @@ -2008,6 +2014,7 @@ FIXTURE_VARIANT(iommufd_dirty_tracking) FIXTURE_SETUP(iommufd_dirty_tracking) { + size_t mmap_buffer_size; unsigned long size; int mmap_flags; void *vrc; @@ -2022,22 +2029,33 @@ FIXTURE_SETUP(iommufd_dirty_tracking) self->fd = open("/dev/iommu", O_RDWR); ASSERT_NE(-1, self->fd); - rc = posix_memalign(&self->buffer, HUGEPAGE_SIZE, variant->buffer_size); - if (rc || !self->buffer) { - SKIP(return, "Skipping buffer_size=%lu due to errno=%d", - variant->buffer_size, rc); - } - mmap_flags = MAP_SHARED | MAP_ANONYMOUS | MAP_FIXED; + mmap_buffer_size = variant->buffer_size; if (variant->hugepages) { /* * MAP_POPULATE will cause the kernel to fail mmap if THPs are * not available. */ mmap_flags |= MAP_HUGETLB | MAP_POPULATE; + + /* + * Allocation must be aligned to the HUGEPAGE_SIZE, because the + * following mmap() will automatically align the length to be a + * multiple of the underlying huge page size. Failing to do the + * same at this allocation will result in a memory overwrite by + * the mmap(). + */ + if (mmap_buffer_size < HUGEPAGE_SIZE) + mmap_buffer_size = HUGEPAGE_SIZE; + } + + rc = posix_memalign(&self->buffer, HUGEPAGE_SIZE, mmap_buffer_size); + if (rc || !self->buffer) { + SKIP(return, "Skipping buffer_size=%lu due to errno=%d", + mmap_buffer_size, rc); } assert((uintptr_t)self->buffer % HUGEPAGE_SIZE == 0); - vrc = mmap(self->buffer, variant->buffer_size, PROT_READ | PROT_WRITE, + vrc = mmap(self->buffer, mmap_buffer_size, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); assert(vrc == self->buffer); @@ -2066,8 +2084,8 @@ FIXTURE_SETUP(iommufd_dirty_tracking) FIXTURE_TEARDOWN(iommufd_dirty_tracking) { - munmap(self->buffer, variant->buffer_size); - munmap(self->bitmap, DIV_ROUND_UP(self->bitmap_size, BITS_PER_BYTE)); + free(self->buffer); + free(self->bitmap); teardown_iommufd(self->fd, _metadata); } diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 72f6636e5d90..6e967b58acfd 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -60,13 +60,18 @@ static inline void *memfd_mmap(size_t length, int prot, int flags, int *mfd_p) { int mfd_flags = (flags & MAP_HUGETLB) ? MFD_HUGETLB : 0; int mfd = memfd_create("buffer", mfd_flags); + void *buf = MAP_FAILED; if (mfd <= 0) return MAP_FAILED; if (ftruncate(mfd, length)) - return MAP_FAILED; + goto out; *mfd_p = mfd; - return mmap(0, length, prot, flags, mfd, 0); + buf = mmap(0, length, prot, flags, mfd, 0); +out: + if (buf == MAP_FAILED) + close(mfd); + return buf; } /* diff --git a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c index b4d22b3ab7cc..4e71740a098b 100644 --- a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c +++ b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c @@ -954,6 +954,8 @@ static void test_init_timer_irq(struct kvm_vm *vm, struct kvm_vcpu *vcpu) pr_debug("ptimer_irq: %d; vtimer_irq: %d\n", ptimer_irq, vtimer_irq); } +static int gic_fd; + static void test_vm_create(struct kvm_vm **vm, struct kvm_vcpu **vcpu, enum arch_timer timer) { @@ -968,12 +970,20 @@ static void test_vm_create(struct kvm_vm **vm, struct kvm_vcpu **vcpu, vcpu_args_set(*vcpu, 1, timer); test_init_timer_irq(*vm, *vcpu); - vgic_v3_setup(*vm, 1, 64); + gic_fd = vgic_v3_setup(*vm, 1, 64); + __TEST_REQUIRE(gic_fd >= 0, "Failed to create vgic-v3"); + sync_global_to_guest(*vm, test_args); sync_global_to_guest(*vm, CVAL_MAX); sync_global_to_guest(*vm, DEF_CNT); } +static void test_vm_cleanup(struct kvm_vm *vm) +{ + close(gic_fd); + kvm_vm_free(vm); +} + static void test_print_help(char *name) { pr_info("Usage: %s [-h] [-b] [-i iterations] [-l long_wait_ms] [-p] [-v]\n" @@ -1060,13 +1070,13 @@ int main(int argc, char *argv[]) if (test_args.test_virtual) { test_vm_create(&vm, &vcpu, VIRTUAL); test_run(vm, vcpu); - kvm_vm_free(vm); + test_vm_cleanup(vm); } if (test_args.test_physical) { test_vm_create(&vm, &vcpu, PHYSICAL); test_run(vm, vcpu); - kvm_vm_free(vm); + test_vm_cleanup(vm); } return 0; diff --git a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c index 390ae2d87493..0eb371c62ab8 100644 --- a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c +++ b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c @@ -74,6 +74,7 @@ int main(int argc, char *argv[]) int testcase; char test[80]; + TEST_REQUIRE(this_cpu_has(X86_FEATURE_MWAIT)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_DISABLE_QUIRKS2)); ksft_print_header(); diff --git a/tools/testing/selftests/mm/config b/tools/testing/selftests/mm/config index a28baa536332..deba93379c80 100644 --- a/tools/testing/selftests/mm/config +++ b/tools/testing/selftests/mm/config @@ -8,3 +8,6 @@ CONFIG_GUP_TEST=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_MEM_SOFT_DIRTY=y CONFIG_ANON_VMA_NAME=y +CONFIG_FTRACE=y +CONFIG_PROFILING=y +CONFIG_UPROBES=y diff --git a/tools/testing/selftests/mm/merge.c b/tools/testing/selftests/mm/merge.c index bbae66fc5038..cc26480098ae 100644 --- a/tools/testing/selftests/mm/merge.c +++ b/tools/testing/selftests/mm/merge.c @@ -470,7 +470,9 @@ TEST_F(merge, handle_uprobe_upon_merged_vma) ASSERT_GE(fd, 0); ASSERT_EQ(ftruncate(fd, page_size), 0); - ASSERT_EQ(read_sysfs("/sys/bus/event_source/devices/uprobe/type", &type), 0); + if (read_sysfs("/sys/bus/event_source/devices/uprobe/type", &type) != 0) { + SKIP(goto out, "Failed to read uprobe sysfs file, skipping"); + } memset(&attr, 0, attr_sz); attr.size = attr_sz; @@ -491,6 +493,7 @@ TEST_F(merge, handle_uprobe_upon_merged_vma) ASSERT_NE(mremap(ptr2, page_size, page_size, MREMAP_MAYMOVE | MREMAP_FIXED, ptr1), MAP_FAILED); +out: close(fd); remove(probe_file); } diff --git a/tools/testing/selftests/mm/settings b/tools/testing/selftests/mm/settings index a953c96aa16e..e2206265f67c 100644 --- a/tools/testing/selftests/mm/settings +++ b/tools/testing/selftests/mm/settings @@ -1 +1 @@ -timeout=180 +timeout=900 diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index b380e102b22f..169dbd692bf5 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -77,8 +77,11 @@ static void validate_addr(char *ptr, int high_addr) { unsigned long addr = (unsigned long) ptr; - if (high_addr && addr < HIGH_ADDR_MARK) - ksft_exit_fail_msg("Bad address %lx\n", addr); + if (high_addr) { + if (addr < HIGH_ADDR_MARK) + ksft_exit_fail_msg("Bad address %lx\n", addr); + return; + } if (addr > HIGH_ADDR_MARK) ksft_exit_fail_msg("Bad address %lx\n", addr); diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index c6dd2a335cf4..47c293c2962f 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -34,6 +34,7 @@ reuseport_bpf_numa reuseport_dualstack rxtimestamp sctp_hello +scm_inq scm_pidfd scm_rights sk_bind_sendto_listen diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 227f9e067d25..13e2678d418b 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -63,6 +63,7 @@ TEST_PROGS += ip_local_port_range.sh TEST_PROGS += rps_default_mask.sh TEST_PROGS += big_tcp.sh TEST_PROGS += netns-sysctl.sh +TEST_PROGS += netdev-l2addr.sh TEST_PROGS_EXTENDED := toeplitz_client.sh toeplitz.sh xfrm_policy_add_speed.sh TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any @@ -100,6 +101,7 @@ TEST_PROGS += test_vxlan_mdb.sh TEST_PROGS += test_bridge_neigh_suppress.sh TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_PROGS += test_bridge_backup_port.sh +TEST_PROGS += test_neigh.sh TEST_PROGS += fdb_flush.sh fdb_notify.sh TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh @@ -113,6 +115,7 @@ TEST_PROGS += skf_net_off.sh TEST_GEN_FILES += skf_net_off TEST_GEN_FILES += tfo TEST_PROGS += tfo_passive.sh +TEST_PROGS += broadcast_pmtu.sh # YNL files, must be before "include ..lib.mk" YNL_GEN_FILES := busy_poller netlink-dumps diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 50584479540b..a4b61c6d0290 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,4 +1,4 @@ CFLAGS += $(KHDR_INCLUDES) -TEST_GEN_PROGS := diag_uid msg_oob scm_pidfd scm_rights unix_connect +TEST_GEN_PROGS := diag_uid msg_oob scm_inq scm_pidfd scm_rights unix_connect include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c index 3ed3882a93b8..b5f474969917 100644 --- a/tools/testing/selftests/net/af_unix/msg_oob.c +++ b/tools/testing/selftests/net/af_unix/msg_oob.c @@ -210,7 +210,7 @@ static void __sendpair(struct __test_metadata *_metadata, static void __recvpair(struct __test_metadata *_metadata, FIXTURE_DATA(msg_oob) *self, const char *expected_buf, int expected_len, - int buf_len, int flags) + int buf_len, int flags, bool is_sender) { int i, ret[2], recv_errno[2], expected_errno = 0; char recv_buf[2][BUF_SZ] = {}; @@ -221,7 +221,9 @@ static void __recvpair(struct __test_metadata *_metadata, errno = 0; for (i = 0; i < 2; i++) { - ret[i] = recv(self->fd[i * 2 + 1], recv_buf[i], buf_len, flags); + int index = is_sender ? i * 2 : i * 2 + 1; + + ret[i] = recv(self->fd[index], recv_buf[i], buf_len, flags); recv_errno[i] = errno; } @@ -308,6 +310,20 @@ static void __siocatmarkpair(struct __test_metadata *_metadata, ASSERT_EQ(answ[0], answ[1]); } +static void __resetpair(struct __test_metadata *_metadata, + FIXTURE_DATA(msg_oob) *self, + const FIXTURE_VARIANT(msg_oob) *variant, + bool reset) +{ + int i; + + for (i = 0; i < 2; i++) + close(self->fd[i * 2 + 1]); + + __recvpair(_metadata, self, "", reset ? -ECONNRESET : 0, 1, + variant->peek ? MSG_PEEK : 0, true); +} + #define sendpair(buf, len, flags) \ __sendpair(_metadata, self, buf, len, flags) @@ -316,9 +332,10 @@ static void __siocatmarkpair(struct __test_metadata *_metadata, if (variant->peek) \ __recvpair(_metadata, self, \ expected_buf, expected_len, \ - buf_len, (flags) | MSG_PEEK); \ + buf_len, (flags) | MSG_PEEK, false); \ __recvpair(_metadata, self, \ - expected_buf, expected_len, buf_len, flags); \ + expected_buf, expected_len, \ + buf_len, flags, false); \ } while (0) #define epollpair(oob_remaining) \ @@ -330,6 +347,9 @@ static void __siocatmarkpair(struct __test_metadata *_metadata, #define setinlinepair() \ __setinlinepair(_metadata, self) +#define resetpair(reset) \ + __resetpair(_metadata, self, variant, reset) + #define tcp_incompliant \ for (self->tcp_compliant = false; \ self->tcp_compliant == false; \ @@ -344,6 +364,21 @@ TEST_F(msg_oob, non_oob) recvpair("", -EINVAL, 1, MSG_OOB); epollpair(false); siocatmarkpair(false); + + resetpair(true); +} + +TEST_F(msg_oob, non_oob_no_reset) +{ + sendpair("x", 1, 0); + epollpair(false); + siocatmarkpair(false); + + recvpair("x", 1, 1, 0); + epollpair(false); + siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, oob) @@ -355,6 +390,19 @@ TEST_F(msg_oob, oob) recvpair("x", 1, 1, MSG_OOB); epollpair(false); siocatmarkpair(true); + + tcp_incompliant { + resetpair(false); /* TCP sets -ECONNRESET for ex-OOB. */ + } +} + +TEST_F(msg_oob, oob_reset) +{ + sendpair("x", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + resetpair(true); } TEST_F(msg_oob, oob_drop) @@ -370,6 +418,8 @@ TEST_F(msg_oob, oob_drop) recvpair("", -EINVAL, 1, MSG_OOB); epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, oob_ahead) @@ -385,6 +435,10 @@ TEST_F(msg_oob, oob_ahead) recvpair("hell", 4, 4, 0); epollpair(false); siocatmarkpair(true); + + tcp_incompliant { + resetpair(false); /* TCP sets -ECONNRESET for ex-OOB. */ + } } TEST_F(msg_oob, oob_break) @@ -403,6 +457,8 @@ TEST_F(msg_oob, oob_break) recvpair("", -EAGAIN, 1, 0); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, oob_ahead_break) @@ -426,6 +482,8 @@ TEST_F(msg_oob, oob_ahead_break) recvpair("world", 5, 5, 0); epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, oob_break_drop) @@ -449,6 +507,8 @@ TEST_F(msg_oob, oob_break_drop) recvpair("", -EINVAL, 1, MSG_OOB); epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, ex_oob_break) @@ -476,6 +536,8 @@ TEST_F(msg_oob, ex_oob_break) recvpair("ld", 2, 2, 0); epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, ex_oob_drop) @@ -498,6 +560,8 @@ TEST_F(msg_oob, ex_oob_drop) epollpair(false); siocatmarkpair(true); } + + resetpair(false); } TEST_F(msg_oob, ex_oob_drop_2) @@ -523,6 +587,8 @@ TEST_F(msg_oob, ex_oob_drop_2) epollpair(false); siocatmarkpair(true); } + + resetpair(false); } TEST_F(msg_oob, ex_oob_oob) @@ -546,6 +612,54 @@ TEST_F(msg_oob, ex_oob_oob) recvpair("", -EINVAL, 1, MSG_OOB); epollpair(false); siocatmarkpair(false); + + resetpair(false); +} + +TEST_F(msg_oob, ex_oob_ex_oob) +{ + sendpair("x", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + recvpair("x", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(true); + + sendpair("y", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + recvpair("y", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(true); + + tcp_incompliant { + resetpair(false); /* TCP sets -ECONNRESET for ex-OOB. */ + } +} + +TEST_F(msg_oob, ex_oob_ex_oob_oob) +{ + sendpair("x", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + recvpair("x", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(true); + + sendpair("y", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + recvpair("y", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(true); + + sendpair("z", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); } TEST_F(msg_oob, ex_oob_ahead_break) @@ -576,6 +690,10 @@ TEST_F(msg_oob, ex_oob_ahead_break) recvpair("d", 1, 1, MSG_OOB); epollpair(false); siocatmarkpair(true); + + tcp_incompliant { + resetpair(false); /* TCP sets -ECONNRESET for ex-OOB. */ + } } TEST_F(msg_oob, ex_oob_siocatmark) @@ -595,6 +713,8 @@ TEST_F(msg_oob, ex_oob_siocatmark) recvpair("hell", 4, 4, 0); /* Intentionally stop at ex-OOB. */ epollpair(true); siocatmarkpair(false); + + resetpair(true); } TEST_F(msg_oob, inline_oob) @@ -612,6 +732,8 @@ TEST_F(msg_oob, inline_oob) recvpair("x", 1, 1, 0); epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, inline_oob_break) @@ -633,6 +755,8 @@ TEST_F(msg_oob, inline_oob_break) recvpair("o", 1, 1, 0); epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, inline_oob_ahead_break) @@ -661,6 +785,8 @@ TEST_F(msg_oob, inline_oob_ahead_break) epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, inline_ex_oob_break) @@ -686,6 +812,8 @@ TEST_F(msg_oob, inline_ex_oob_break) recvpair("rld", 3, 3, 0); epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, inline_ex_oob_no_drop) @@ -707,6 +835,8 @@ TEST_F(msg_oob, inline_ex_oob_no_drop) recvpair("y", 1, 1, 0); epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, inline_ex_oob_drop) @@ -731,6 +861,8 @@ TEST_F(msg_oob, inline_ex_oob_drop) epollpair(false); siocatmarkpair(false); } + + resetpair(false); } TEST_F(msg_oob, inline_ex_oob_siocatmark) @@ -752,6 +884,8 @@ TEST_F(msg_oob, inline_ex_oob_siocatmark) recvpair("hell", 4, 4, 0); /* Intentionally stop at ex-OOB. */ epollpair(true); siocatmarkpair(false); + + resetpair(true); } TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/af_unix/scm_inq.c b/tools/testing/selftests/net/af_unix/scm_inq.c new file mode 100644 index 000000000000..9d22561e7b8f --- /dev/null +++ b/tools/testing/selftests/net/af_unix/scm_inq.c @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2025 Google LLC */ + +#include <linux/sockios.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <sys/types.h> + +#include "../../kselftest_harness.h" + +#define NR_CHUNKS 100 +#define MSG_LEN 256 + +struct scm_inq { + struct cmsghdr cmsghdr; + int inq; +}; + +FIXTURE(scm_inq) +{ + int fd[2]; +}; + +FIXTURE_VARIANT(scm_inq) +{ + int type; +}; + +FIXTURE_VARIANT_ADD(scm_inq, stream) +{ + .type = SOCK_STREAM, +}; + +FIXTURE_VARIANT_ADD(scm_inq, dgram) +{ + .type = SOCK_DGRAM, +}; + +FIXTURE_VARIANT_ADD(scm_inq, seqpacket) +{ + .type = SOCK_SEQPACKET, +}; + +FIXTURE_SETUP(scm_inq) +{ + int err; + + err = socketpair(AF_UNIX, variant->type | SOCK_NONBLOCK, 0, self->fd); + ASSERT_EQ(0, err); +} + +FIXTURE_TEARDOWN(scm_inq) +{ + close(self->fd[0]); + close(self->fd[1]); +} + +static void send_chunks(struct __test_metadata *_metadata, + FIXTURE_DATA(scm_inq) *self) +{ + char buf[MSG_LEN] = {}; + int i, ret; + + for (i = 0; i < NR_CHUNKS; i++) { + ret = send(self->fd[0], buf, sizeof(buf), 0); + ASSERT_EQ(sizeof(buf), ret); + } +} + +static void recv_chunks(struct __test_metadata *_metadata, + FIXTURE_DATA(scm_inq) *self) +{ + struct msghdr msg = {}; + struct iovec iov = {}; + struct scm_inq cmsg; + char buf[MSG_LEN]; + int i, ret; + int inq; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = &cmsg; + msg.msg_controllen = CMSG_SPACE(sizeof(cmsg.inq)); + + iov.iov_base = buf; + iov.iov_len = sizeof(buf); + + for (i = 0; i < NR_CHUNKS; i++) { + memset(buf, 0, sizeof(buf)); + memset(&cmsg, 0, sizeof(cmsg)); + + ret = recvmsg(self->fd[1], &msg, 0); + ASSERT_EQ(MSG_LEN, ret); + ASSERT_NE(NULL, CMSG_FIRSTHDR(&msg)); + ASSERT_EQ(CMSG_LEN(sizeof(cmsg.inq)), cmsg.cmsghdr.cmsg_len); + ASSERT_EQ(SOL_SOCKET, cmsg.cmsghdr.cmsg_level); + ASSERT_EQ(SCM_INQ, cmsg.cmsghdr.cmsg_type); + + ret = ioctl(self->fd[1], SIOCINQ, &inq); + ASSERT_EQ(0, ret); + ASSERT_EQ(cmsg.inq, inq); + } +} + +TEST_F(scm_inq, basic) +{ + int err, inq; + + err = setsockopt(self->fd[1], SOL_SOCKET, SO_INQ, &(int){1}, sizeof(int)); + if (variant->type != SOCK_STREAM) { + ASSERT_EQ(-ENOPROTOOPT, -errno); + return; + } + + ASSERT_EQ(0, err); + + err = ioctl(self->fd[1], SIOCINQ, &inq); + ASSERT_EQ(0, err); + ASSERT_EQ(0, inq); + + send_chunks(_metadata, self); + recv_chunks(_metadata, self); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/bench/Makefile b/tools/testing/selftests/net/bench/Makefile new file mode 100644 index 000000000000..2546c45e42f7 --- /dev/null +++ b/tools/testing/selftests/net/bench/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 + +TEST_GEN_MODS_DIR := page_pool + +TEST_PROGS += test_bench_page_pool.sh + +include ../../lib.mk diff --git a/tools/testing/selftests/net/bench/page_pool/Makefile b/tools/testing/selftests/net/bench/page_pool/Makefile new file mode 100644 index 000000000000..0549a16ba275 --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/Makefile @@ -0,0 +1,17 @@ +BENCH_PAGE_POOL_SIMPLE_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= /lib/modules/$(shell uname -r)/build + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +obj-m += bench_page_pool.o +bench_page_pool-y += bench_page_pool_simple.o time_bench.o + +all: + +$(Q)make -C $(KDIR) M=$(BENCH_PAGE_POOL_SIMPLE_TEST_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(BENCH_PAGE_POOL_SIMPLE_TEST_DIR) clean diff --git a/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c b/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c new file mode 100644 index 000000000000..cb6468adbda4 --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c @@ -0,0 +1,267 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Benchmark module for page_pool. + * + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/interrupt.h> +#include <linux/limits.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <net/page_pool/helpers.h> + +#include "time_bench.h" + +static int verbose = 1; +#define MY_POOL_SIZE 1024 + +/* Makes tests selectable. Useful for perf-record to analyze a single test. + * Hint: Bash shells support writing binary number like: $((2#101010) + * + * # modprobe bench_page_pool_simple run_flags=$((2#100)) + */ +static unsigned long run_flags = 0xFFFFFFFF; +module_param(run_flags, ulong, 0); +MODULE_PARM_DESC(run_flags, "Limit which bench test that runs"); + +/* Count the bit number from the enum */ +enum benchmark_bit { + bit_run_bench_baseline, + bit_run_bench_no_softirq01, + bit_run_bench_no_softirq02, + bit_run_bench_no_softirq03, +}; + +#define bit(b) (1 << (b)) +#define enabled(b) ((run_flags & (bit(b)))) + +/* notice time_bench is limited to U32_MAX nr loops */ +static unsigned long loops = 10000000; +module_param(loops, ulong, 0); +MODULE_PARM_DESC(loops, "Specify loops bench will run"); + +/* Timing at the nanosec level, we need to know the overhead + * introduced by the for loop itself + */ +static int time_bench_for_loop(struct time_bench_record *rec, void *data) +{ + uint64_t loops_cnt = 0; + int i; + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + loops_cnt++; + barrier(); /* avoid compiler to optimize this loop */ + } + time_bench_stop(rec, loops_cnt); + return loops_cnt; +} + +static int time_bench_atomic_inc(struct time_bench_record *rec, void *data) +{ + uint64_t loops_cnt = 0; + atomic_t cnt; + int i; + + atomic_set(&cnt, 0); + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + atomic_inc(&cnt); + barrier(); /* avoid compiler to optimize this loop */ + } + loops_cnt = atomic_read(&cnt); + time_bench_stop(rec, loops_cnt); + return loops_cnt; +} + +/* The ptr_ping in page_pool uses a spinlock. We need to know the minimum + * overhead of taking+releasing a spinlock, to know the cycles that can be saved + * by e.g. amortizing this via bulking. + */ +static int time_bench_lock(struct time_bench_record *rec, void *data) +{ + uint64_t loops_cnt = 0; + spinlock_t lock; + int i; + + spin_lock_init(&lock); + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + spin_lock(&lock); + loops_cnt++; + barrier(); /* avoid compiler to optimize this loop */ + spin_unlock(&lock); + } + time_bench_stop(rec, loops_cnt); + return loops_cnt; +} + +/* Helper for filling some page's into ptr_ring */ +static void pp_fill_ptr_ring(struct page_pool *pp, int elems) +{ + /* GFP_ATOMIC needed when under run softirq */ + gfp_t gfp_mask = GFP_ATOMIC; + struct page **array; + int i; + + array = kcalloc(elems, sizeof(struct page *), gfp_mask); + + for (i = 0; i < elems; i++) + array[i] = page_pool_alloc_pages(pp, gfp_mask); + for (i = 0; i < elems; i++) + page_pool_put_page(pp, array[i], -1, false); + + kfree(array); +} + +enum test_type { type_fast_path, type_ptr_ring, type_page_allocator }; + +/* Depends on compile optimizing this function */ +static int time_bench_page_pool(struct time_bench_record *rec, void *data, + enum test_type type, const char *func) +{ + uint64_t loops_cnt = 0; + gfp_t gfp_mask = GFP_ATOMIC; /* GFP_ATOMIC is not really needed */ + int i, err; + + struct page_pool *pp; + struct page *page; + + struct page_pool_params pp_params = { + .order = 0, + .flags = 0, + .pool_size = MY_POOL_SIZE, + .nid = NUMA_NO_NODE, + .dev = NULL, /* Only use for DMA mapping */ + .dma_dir = DMA_BIDIRECTIONAL, + }; + + pp = page_pool_create(&pp_params); + if (IS_ERR(pp)) { + err = PTR_ERR(pp); + pr_warn("%s: Error(%d) creating page_pool\n", func, err); + goto out; + } + pp_fill_ptr_ring(pp, 64); + + if (in_serving_softirq()) + pr_warn("%s(): in_serving_softirq fast-path\n", func); + else + pr_warn("%s(): Cannot use page_pool fast-path\n", func); + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + /* Common fast-path alloc that depend on in_serving_softirq() */ + page = page_pool_alloc_pages(pp, gfp_mask); + if (!page) + break; + loops_cnt++; + barrier(); /* avoid compiler to optimize this loop */ + + /* The benchmarks purpose it to test different return paths. + * Compiler should inline optimize other function calls out + */ + if (type == type_fast_path) { + /* Fast-path recycling e.g. XDP_DROP use-case */ + page_pool_recycle_direct(pp, page); + + } else if (type == type_ptr_ring) { + /* Normal return path */ + page_pool_put_page(pp, page, -1, false); + + } else if (type == type_page_allocator) { + /* Test if not pages are recycled, but instead + * returned back into systems page allocator + */ + get_page(page); /* cause no-recycling */ + page_pool_put_page(pp, page, -1, false); + put_page(page); + } else { + BUILD_BUG(); + } + } + time_bench_stop(rec, loops_cnt); +out: + page_pool_destroy(pp); + return loops_cnt; +} + +static int time_bench_page_pool01_fast_path(struct time_bench_record *rec, + void *data) +{ + return time_bench_page_pool(rec, data, type_fast_path, __func__); +} + +static int time_bench_page_pool02_ptr_ring(struct time_bench_record *rec, + void *data) +{ + return time_bench_page_pool(rec, data, type_ptr_ring, __func__); +} + +static int time_bench_page_pool03_slow(struct time_bench_record *rec, + void *data) +{ + return time_bench_page_pool(rec, data, type_page_allocator, __func__); +} + +static int run_benchmark_tests(void) +{ + uint32_t nr_loops = loops; + + /* Baseline tests */ + if (enabled(bit_run_bench_baseline)) { + time_bench_loop(nr_loops * 10, 0, "for_loop", NULL, + time_bench_for_loop); + time_bench_loop(nr_loops * 10, 0, "atomic_inc", NULL, + time_bench_atomic_inc); + time_bench_loop(nr_loops, 0, "lock", NULL, time_bench_lock); + } + + /* This test cannot activate correct code path, due to no-softirq ctx */ + if (enabled(bit_run_bench_no_softirq01)) + time_bench_loop(nr_loops, 0, "no-softirq-page_pool01", NULL, + time_bench_page_pool01_fast_path); + if (enabled(bit_run_bench_no_softirq02)) + time_bench_loop(nr_loops, 0, "no-softirq-page_pool02", NULL, + time_bench_page_pool02_ptr_ring); + if (enabled(bit_run_bench_no_softirq03)) + time_bench_loop(nr_loops, 0, "no-softirq-page_pool03", NULL, + time_bench_page_pool03_slow); + + return 0; +} + +static int __init bench_page_pool_simple_module_init(void) +{ + if (verbose) + pr_info("Loaded\n"); + + if (loops > U32_MAX) { + pr_err("Module param loops(%lu) exceeded U32_MAX(%u)\n", loops, + U32_MAX); + return -ECHRNG; + } + + run_benchmark_tests(); + + return 0; +} +module_init(bench_page_pool_simple_module_init); + +static void __exit bench_page_pool_simple_module_exit(void) +{ + if (verbose) + pr_info("Unloaded\n"); +} +module_exit(bench_page_pool_simple_module_exit); + +MODULE_DESCRIPTION("Benchmark of page_pool simple cases"); +MODULE_AUTHOR("Jesper Dangaard Brouer <netoptimizer@brouer.com>"); +MODULE_LICENSE("GPL"); diff --git a/tools/testing/selftests/net/bench/page_pool/time_bench.c b/tools/testing/selftests/net/bench/page_pool/time_bench.c new file mode 100644 index 000000000000..073bb36ec5f2 --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/time_bench.c @@ -0,0 +1,394 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Benchmarking code execution time inside the kernel + * + * Copyright (C) 2014, Red Hat, Inc., Jesper Dangaard Brouer + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/time.h> + +#include <linux/perf_event.h> /* perf_event_create_kernel_counter() */ + +/* For concurrency testing */ +#include <linux/completion.h> +#include <linux/sched.h> +#include <linux/workqueue.h> +#include <linux/kthread.h> + +#include "time_bench.h" + +static int verbose = 1; + +/** TSC (Time-Stamp Counter) based ** + * See: linux/time_bench.h + * tsc_start_clock() and tsc_stop_clock() + */ + +/** Wall-clock based ** + */ + +/** PMU (Performance Monitor Unit) based ** + */ +#define PERF_FORMAT \ + (PERF_FORMAT_GROUP | PERF_FORMAT_ID | PERF_FORMAT_TOTAL_TIME_ENABLED | \ + PERF_FORMAT_TOTAL_TIME_RUNNING) + +struct raw_perf_event { + uint64_t config; /* event */ + uint64_t config1; /* umask */ + struct perf_event *save; + char *desc; +}; + +/* if HT is enable a maximum of 4 events (5 if one is instructions + * retired can be specified, if HT is disabled a maximum of 8 (9 if + * one is instructions retired) can be specified. + * + * From Table 19-1. Architectural Performance Events + * Architectures Software Developer’s Manual Volume 3: System Programming + * Guide + */ +struct raw_perf_event perf_events[] = { + { 0x3c, 0x00, NULL, "Unhalted CPU Cycles" }, + { 0xc0, 0x00, NULL, "Instruction Retired" } +}; + +#define NUM_EVTS (ARRAY_SIZE(perf_events)) + +/* WARNING: PMU config is currently broken! + */ +bool time_bench_PMU_config(bool enable) +{ + int i; + struct perf_event_attr perf_conf; + struct perf_event *perf_event; + int cpu; + + preempt_disable(); + cpu = smp_processor_id(); + pr_info("DEBUG: cpu:%d\n", cpu); + preempt_enable(); + + memset(&perf_conf, 0, sizeof(struct perf_event_attr)); + perf_conf.type = PERF_TYPE_RAW; + perf_conf.size = sizeof(struct perf_event_attr); + perf_conf.read_format = PERF_FORMAT; + perf_conf.pinned = 1; + perf_conf.exclude_user = 1; /* No userspace events */ + perf_conf.exclude_kernel = 0; /* Only kernel events */ + + for (i = 0; i < NUM_EVTS; i++) { + perf_conf.disabled = enable; + //perf_conf.disabled = (i == 0) ? 1 : 0; + perf_conf.config = perf_events[i].config; + perf_conf.config1 = perf_events[i].config1; + if (verbose) + pr_info("%s() enable PMU counter: %s\n", + __func__, perf_events[i].desc); + perf_event = perf_event_create_kernel_counter(&perf_conf, cpu, + NULL /* task */, + NULL /* overflow_handler*/, + NULL /* context */); + if (perf_event) { + perf_events[i].save = perf_event; + pr_info("%s():DEBUG perf_event success\n", __func__); + + perf_event_enable(perf_event); + } else { + pr_info("%s():DEBUG perf_event is NULL\n", __func__); + } + } + + return true; +} + +/** Generic functions ** + */ + +/* Calculate stats, store results in record */ +bool time_bench_calc_stats(struct time_bench_record *rec) +{ +#define NANOSEC_PER_SEC 1000000000 /* 10^9 */ + uint64_t ns_per_call_tmp_rem = 0; + uint32_t ns_per_call_remainder = 0; + uint64_t pmc_ipc_tmp_rem = 0; + uint32_t pmc_ipc_remainder = 0; + uint32_t pmc_ipc_div = 0; + uint32_t invoked_cnt_precision = 0; + uint32_t invoked_cnt = 0; /* 32-bit due to div_u64_rem() */ + + if (rec->flags & TIME_BENCH_LOOP) { + if (rec->invoked_cnt < 1000) { + pr_err("ERR: need more(>1000) loops(%llu) for timing\n", + rec->invoked_cnt); + return false; + } + if (rec->invoked_cnt > ((1ULL << 32) - 1)) { + /* div_u64_rem() can only support div with 32bit*/ + pr_err("ERR: Invoke cnt(%llu) too big overflow 32bit\n", + rec->invoked_cnt); + return false; + } + invoked_cnt = (uint32_t)rec->invoked_cnt; + } + + /* TSC (Time-Stamp Counter) records */ + if (rec->flags & TIME_BENCH_TSC) { + rec->tsc_interval = rec->tsc_stop - rec->tsc_start; + if (rec->tsc_interval == 0) { + pr_err("ABORT: timing took ZERO TSC time\n"); + return false; + } + /* Calculate stats */ + if (rec->flags & TIME_BENCH_LOOP) + rec->tsc_cycles = rec->tsc_interval / invoked_cnt; + else + rec->tsc_cycles = rec->tsc_interval; + } + + /* Wall-clock time calc */ + if (rec->flags & TIME_BENCH_WALLCLOCK) { + rec->time_start = rec->ts_start.tv_nsec + + (NANOSEC_PER_SEC * rec->ts_start.tv_sec); + rec->time_stop = rec->ts_stop.tv_nsec + + (NANOSEC_PER_SEC * rec->ts_stop.tv_sec); + rec->time_interval = rec->time_stop - rec->time_start; + if (rec->time_interval == 0) { + pr_err("ABORT: timing took ZERO wallclock time\n"); + return false; + } + /* Calculate stats */ + /*** Division in kernel it tricky ***/ + /* Orig: time_sec = (time_interval / NANOSEC_PER_SEC); */ + /* remainder only correct because NANOSEC_PER_SEC is 10^9 */ + rec->time_sec = div_u64_rem(rec->time_interval, NANOSEC_PER_SEC, + &rec->time_sec_remainder); + //TODO: use existing struct timespec records instead of div? + + if (rec->flags & TIME_BENCH_LOOP) { + /*** Division in kernel it tricky ***/ + /* Orig: ns = ((double)time_interval / invoked_cnt); */ + /* First get quotient */ + rec->ns_per_call_quotient = + div_u64_rem(rec->time_interval, invoked_cnt, + &ns_per_call_remainder); + /* Now get decimals .xxx precision (incorrect roundup)*/ + ns_per_call_tmp_rem = ns_per_call_remainder; + invoked_cnt_precision = invoked_cnt / 1000; + if (invoked_cnt_precision > 0) { + rec->ns_per_call_decimal = + div_u64_rem(ns_per_call_tmp_rem, + invoked_cnt_precision, + &ns_per_call_remainder); + } + } + } + + /* Performance Monitor Unit (PMU) counters */ + if (rec->flags & TIME_BENCH_PMU) { + //FIXME: Overflow handling??? + rec->pmc_inst = rec->pmc_inst_stop - rec->pmc_inst_start; + rec->pmc_clk = rec->pmc_clk_stop - rec->pmc_clk_start; + + /* Calc Instruction Per Cycle (IPC) */ + /* First get quotient */ + rec->pmc_ipc_quotient = div_u64_rem(rec->pmc_inst, rec->pmc_clk, + &pmc_ipc_remainder); + /* Now get decimals .xxx precision (incorrect roundup)*/ + pmc_ipc_tmp_rem = pmc_ipc_remainder; + pmc_ipc_div = rec->pmc_clk / 1000; + if (pmc_ipc_div > 0) { + rec->pmc_ipc_decimal = div_u64_rem(pmc_ipc_tmp_rem, + pmc_ipc_div, + &pmc_ipc_remainder); + } + } + + return true; +} + +/* Generic function for invoking a loop function and calculating + * execution time stats. The function being called/timed is assumed + * to perform a tight loop, and update the timing record struct. + */ +bool time_bench_loop(uint32_t loops, int step, char *txt, void *data, + int (*func)(struct time_bench_record *record, void *data)) +{ + struct time_bench_record rec; + + /* Setup record */ + memset(&rec, 0, sizeof(rec)); /* zero func might not update all */ + rec.version_abi = 1; + rec.loops = loops; + rec.step = step; + rec.flags = (TIME_BENCH_LOOP | TIME_BENCH_TSC | TIME_BENCH_WALLCLOCK); + + /*** Loop function being timed ***/ + if (!func(&rec, data)) { + pr_err("ABORT: function being timed failed\n"); + return false; + } + + if (rec.invoked_cnt < loops) + pr_warn("WARNING: Invoke count(%llu) smaller than loops(%d)\n", + rec.invoked_cnt, loops); + + /* Calculate stats */ + time_bench_calc_stats(&rec); + + pr_info("Type:%s Per elem: %llu cycles(tsc) %llu.%03llu ns (step:%d) - (measurement period time:%llu.%09u sec time_interval:%llu) - (invoke count:%llu tsc_interval:%llu)\n", + txt, rec.tsc_cycles, rec.ns_per_call_quotient, + rec.ns_per_call_decimal, rec.step, rec.time_sec, + rec.time_sec_remainder, rec.time_interval, rec.invoked_cnt, + rec.tsc_interval); + if (rec.flags & TIME_BENCH_PMU) + pr_info("Type:%s PMU inst/clock%llu/%llu = %llu.%03llu IPC (inst per cycle)\n", + txt, rec.pmc_inst, rec.pmc_clk, rec.pmc_ipc_quotient, + rec.pmc_ipc_decimal); + return true; +} + +/* Function getting invoked by kthread */ +static int invoke_test_on_cpu_func(void *private) +{ + struct time_bench_cpu *cpu = private; + struct time_bench_sync *sync = cpu->sync; + cpumask_t newmask = CPU_MASK_NONE; + void *data = cpu->data; + + /* Restrict CPU */ + cpumask_set_cpu(cpu->rec.cpu, &newmask); + set_cpus_allowed_ptr(current, &newmask); + + /* Synchronize start of concurrency test */ + atomic_inc(&sync->nr_tests_running); + wait_for_completion(&sync->start_event); + + /* Start benchmark function */ + if (!cpu->bench_func(&cpu->rec, data)) { + pr_err("ERROR: function being timed failed on CPU:%d(%d)\n", + cpu->rec.cpu, smp_processor_id()); + } else { + if (verbose) + pr_info("SUCCESS: ran on CPU:%d(%d)\n", cpu->rec.cpu, + smp_processor_id()); + } + cpu->did_bench_run = true; + + /* End test */ + atomic_dec(&sync->nr_tests_running); + /* Wait for kthread_stop() telling us to stop */ + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +void time_bench_print_stats_cpumask(const char *desc, + struct time_bench_cpu *cpu_tasks, + const struct cpumask *mask) +{ + uint64_t average = 0; + int cpu; + int step = 0; + struct sum { + uint64_t tsc_cycles; + int records; + } sum = { 0 }; + + /* Get stats */ + for_each_cpu(cpu, mask) { + struct time_bench_cpu *c = &cpu_tasks[cpu]; + struct time_bench_record *rec = &c->rec; + + /* Calculate stats */ + time_bench_calc_stats(rec); + + pr_info("Type:%s CPU(%d) %llu cycles(tsc) %llu.%03llu ns (step:%d) - (measurement period time:%llu.%09u sec time_interval:%llu) - (invoke count:%llu tsc_interval:%llu)\n", + desc, cpu, rec->tsc_cycles, rec->ns_per_call_quotient, + rec->ns_per_call_decimal, rec->step, rec->time_sec, + rec->time_sec_remainder, rec->time_interval, + rec->invoked_cnt, rec->tsc_interval); + + /* Collect average */ + sum.records++; + sum.tsc_cycles += rec->tsc_cycles; + step = rec->step; + } + + if (sum.records) /* avoid div-by-zero */ + average = sum.tsc_cycles / sum.records; + pr_info("Sum Type:%s Average: %llu cycles(tsc) CPUs:%d step:%d\n", desc, + average, sum.records, step); +} + +void time_bench_run_concurrent(uint32_t loops, int step, void *data, + const struct cpumask *mask, /* Support masking outsome CPUs*/ + struct time_bench_sync *sync, + struct time_bench_cpu *cpu_tasks, + int (*func)(struct time_bench_record *record, void *data)) +{ + int cpu, running = 0; + + if (verbose) // DEBUG + pr_warn("%s() Started on CPU:%d\n", __func__, + smp_processor_id()); + + /* Reset sync conditions */ + atomic_set(&sync->nr_tests_running, 0); + init_completion(&sync->start_event); + + /* Spawn off jobs on all CPUs */ + for_each_cpu(cpu, mask) { + struct time_bench_cpu *c = &cpu_tasks[cpu]; + + running++; + c->sync = sync; /* Send sync variable along */ + c->data = data; /* Send opaque along */ + + /* Init benchmark record */ + memset(&c->rec, 0, sizeof(struct time_bench_record)); + c->rec.version_abi = 1; + c->rec.loops = loops; + c->rec.step = step; + c->rec.flags = (TIME_BENCH_LOOP | TIME_BENCH_TSC | + TIME_BENCH_WALLCLOCK); + c->rec.cpu = cpu; + c->bench_func = func; + c->task = kthread_run(invoke_test_on_cpu_func, c, + "time_bench%d", cpu); + if (IS_ERR(c->task)) { + pr_err("%s(): Failed to start test func\n", __func__); + return; /* Argh, what about cleanup?! */ + } + } + + /* Wait until all processes are running */ + while (atomic_read(&sync->nr_tests_running) < running) { + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(10); + } + /* Kick off all CPU concurrently on completion event */ + complete_all(&sync->start_event); + + /* Wait for CPUs to finish */ + while (atomic_read(&sync->nr_tests_running)) { + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(10); + } + + /* Stop the kthreads */ + for_each_cpu(cpu, mask) { + struct time_bench_cpu *c = &cpu_tasks[cpu]; + + kthread_stop(c->task); + } + + if (verbose) // DEBUG - happens often, finish on another CPU + pr_warn("%s() Finished on CPU:%d\n", __func__, + smp_processor_id()); +} diff --git a/tools/testing/selftests/net/bench/page_pool/time_bench.h b/tools/testing/selftests/net/bench/page_pool/time_bench.h new file mode 100644 index 000000000000..e113fcf341dc --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/time_bench.h @@ -0,0 +1,238 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Benchmarking code execution time inside the kernel + * + * Copyright (C) 2014, Red Hat, Inc., Jesper Dangaard Brouer + * for licensing details see kernel-base/COPYING + */ +#ifndef _LINUX_TIME_BENCH_H +#define _LINUX_TIME_BENCH_H + +/* Main structure used for recording a benchmark run */ +struct time_bench_record { + uint32_t version_abi; + uint32_t loops; /* Requested loop invocations */ + uint32_t step; /* option for e.g. bulk invocations */ + + uint32_t flags; /* Measurements types enabled */ +#define TIME_BENCH_LOOP BIT(0) +#define TIME_BENCH_TSC BIT(1) +#define TIME_BENCH_WALLCLOCK BIT(2) +#define TIME_BENCH_PMU BIT(3) + + uint32_t cpu; /* Used when embedded in time_bench_cpu */ + + /* Records */ + uint64_t invoked_cnt; /* Returned actual invocations */ + uint64_t tsc_start; + uint64_t tsc_stop; + struct timespec64 ts_start; + struct timespec64 ts_stop; + /* PMU counters for instruction and cycles + * instructions counter including pipelined instructions + */ + uint64_t pmc_inst_start; + uint64_t pmc_inst_stop; + /* CPU unhalted clock counter */ + uint64_t pmc_clk_start; + uint64_t pmc_clk_stop; + + /* Result records */ + uint64_t tsc_interval; + uint64_t time_start, time_stop, time_interval; /* in nanosec */ + uint64_t pmc_inst, pmc_clk; + + /* Derived result records */ + uint64_t tsc_cycles; // +decimal? + uint64_t ns_per_call_quotient, ns_per_call_decimal; + uint64_t time_sec; + uint32_t time_sec_remainder; + uint64_t pmc_ipc_quotient, pmc_ipc_decimal; /* inst per cycle */ +}; + +/* For synchronizing parallel CPUs to run concurrently */ +struct time_bench_sync { + atomic_t nr_tests_running; + struct completion start_event; +}; + +/* Keep track of CPUs executing our bench function. + * + * Embed a time_bench_record for storing info per cpu + */ +struct time_bench_cpu { + struct time_bench_record rec; + struct time_bench_sync *sync; /* back ptr */ + struct task_struct *task; + /* "data" opaque could have been placed in time_bench_sync, + * but to avoid any false sharing, place it per CPU + */ + void *data; + /* Support masking outsome CPUs, mark if it ran */ + bool did_bench_run; + /* int cpu; // note CPU stored in time_bench_record */ + int (*bench_func)(struct time_bench_record *record, void *data); +}; + +/* + * Below TSC assembler code is not compatible with other archs, and + * can also fail on guests if cpu-flags are not correct. + * + * The way TSC reading is used, many iterations, does not require as + * high accuracy as described below (in Intel Doc #324264). + * + * Considering changing to use get_cycles() (#include <asm/timex.h>). + */ + +/** TSC (Time-Stamp Counter) based ** + * Recommend reading, to understand details of reading TSC accurately: + * Intel Doc #324264, "How to Benchmark Code Execution Times on Intel" + * + * Consider getting exclusive ownership of CPU by using: + * unsigned long flags; + * preempt_disable(); + * raw_local_irq_save(flags); + * _your_code_ + * raw_local_irq_restore(flags); + * preempt_enable(); + * + * Clobbered registers: "%rax", "%rbx", "%rcx", "%rdx" + * RDTSC only change "%rax" and "%rdx" but + * CPUID clears the high 32-bits of all (rax/rbx/rcx/rdx) + */ +static __always_inline uint64_t tsc_start_clock(void) +{ + /* See: Intel Doc #324264 */ + unsigned int hi, lo; + + asm volatile("CPUID\n\t" + "RDTSC\n\t" + "mov %%edx, %0\n\t" + "mov %%eax, %1\n\t" + : "=r"(hi), "=r"(lo)::"%rax", "%rbx", "%rcx", "%rdx"); + //FIXME: on 32bit use clobbered %eax + %edx + return ((uint64_t)lo) | (((uint64_t)hi) << 32); +} + +static __always_inline uint64_t tsc_stop_clock(void) +{ + /* See: Intel Doc #324264 */ + unsigned int hi, lo; + + asm volatile("RDTSCP\n\t" + "mov %%edx, %0\n\t" + "mov %%eax, %1\n\t" + "CPUID\n\t" + : "=r"(hi), "=r"(lo)::"%rax", "%rbx", "%rcx", "%rdx"); + return ((uint64_t)lo) | (((uint64_t)hi) << 32); +} + +/** Wall-clock based ** + * + * use: getnstimeofday() + * getnstimeofday(&rec->ts_start); + * getnstimeofday(&rec->ts_stop); + * + * API changed see: Documentation/core-api/timekeeping.rst + * https://www.kernel.org/doc/html/latest/core-api/timekeeping.html#c.getnstimeofday + * + * We should instead use: ktime_get_real_ts64() is a direct + * replacement, but consider using monotonic time (ktime_get_ts64()) + * and/or a ktime_t based interface (ktime_get()/ktime_get_real()). + */ + +/** PMU (Performance Monitor Unit) based ** + * + * Needed for calculating: Instructions Per Cycle (IPC) + * - The IPC number tell how efficient the CPU pipelining were + */ +//lookup: perf_event_create_kernel_counter() + +bool time_bench_PMU_config(bool enable); + +/* Raw reading via rdpmc() using fixed counters + * + * From: https://github.com/andikleen/simple-pmu + */ +enum { + FIXED_SELECT = (1U << 30), /* == 0x40000000 */ + FIXED_INST_RETIRED_ANY = 0, + FIXED_CPU_CLK_UNHALTED_CORE = 1, + FIXED_CPU_CLK_UNHALTED_REF = 2, +}; + +static __always_inline unsigned int long long p_rdpmc(unsigned int in) +{ + unsigned int d, a; + + asm volatile("rdpmc" : "=d"(d), "=a"(a) : "c"(in) : "memory"); + return ((unsigned long long)d << 32) | a; +} + +/* These PMU counter needs to be enabled, but I don't have the + * configure code implemented. My current hack is running: + * sudo perf stat -e cycles:k -e instructions:k insmod lib/ring_queue_test.ko + */ +/* Reading all pipelined instruction */ +static __always_inline unsigned long long pmc_inst(void) +{ + return p_rdpmc(FIXED_SELECT | FIXED_INST_RETIRED_ANY); +} + +/* Reading CPU clock cycles */ +static __always_inline unsigned long long pmc_clk(void) +{ + return p_rdpmc(FIXED_SELECT | FIXED_CPU_CLK_UNHALTED_CORE); +} + +/* Raw reading via MSR rdmsr() is likely wrong + * FIXME: How can I know which raw MSR registers are conf for what? + */ +#define MSR_IA32_PCM0 0x400000C1 /* PERFCTR0 */ +#define MSR_IA32_PCM1 0x400000C2 /* PERFCTR1 */ +#define MSR_IA32_PCM2 0x400000C3 +static inline uint64_t msr_inst(unsigned long long *msr_result) +{ + return rdmsrq_safe(MSR_IA32_PCM0, msr_result); +} + +/** Generic functions ** + */ +bool time_bench_loop(uint32_t loops, int step, char *txt, void *data, + int (*func)(struct time_bench_record *rec, void *data)); +bool time_bench_calc_stats(struct time_bench_record *rec); + +void time_bench_run_concurrent(uint32_t loops, int step, void *data, + const struct cpumask *mask, /* Support masking outsome CPUs*/ + struct time_bench_sync *sync, struct time_bench_cpu *cpu_tasks, + int (*func)(struct time_bench_record *record, void *data)); +void time_bench_print_stats_cpumask(const char *desc, + struct time_bench_cpu *cpu_tasks, + const struct cpumask *mask); + +//FIXME: use rec->flags to select measurement, should be MACRO +static __always_inline void time_bench_start(struct time_bench_record *rec) +{ + //getnstimeofday(&rec->ts_start); + ktime_get_real_ts64(&rec->ts_start); + if (rec->flags & TIME_BENCH_PMU) { + rec->pmc_inst_start = pmc_inst(); + rec->pmc_clk_start = pmc_clk(); + } + rec->tsc_start = tsc_start_clock(); +} + +static __always_inline void time_bench_stop(struct time_bench_record *rec, + uint64_t invoked_cnt) +{ + rec->tsc_stop = tsc_stop_clock(); + if (rec->flags & TIME_BENCH_PMU) { + rec->pmc_inst_stop = pmc_inst(); + rec->pmc_clk_stop = pmc_clk(); + } + //getnstimeofday(&rec->ts_stop); + ktime_get_real_ts64(&rec->ts_stop); + rec->invoked_cnt = invoked_cnt; +} + +#endif /* _LINUX_TIME_BENCH_H */ diff --git a/tools/testing/selftests/net/bench/test_bench_page_pool.sh b/tools/testing/selftests/net/bench/test_bench_page_pool.sh new file mode 100755 index 000000000000..7b8b18cfedce --- /dev/null +++ b/tools/testing/selftests/net/bench/test_bench_page_pool.sh @@ -0,0 +1,32 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# + +set -e + +DRIVER="./page_pool/bench_page_pool.ko" +result="" + +function run_test() +{ + rmmod "bench_page_pool.ko" || true + insmod $DRIVER > /dev/null 2>&1 + result=$(dmesg | tail -10) + echo "$result" + + echo + echo "Fast path results:" + echo "${result}" | grep -o -E "no-softirq-page_pool01 Per elem: ([0-9]+) cycles\(tsc\) ([0-9]+\.[0-9]+) ns" + + echo + echo "ptr_ring results:" + echo "${result}" | grep -o -E "no-softirq-page_pool02 Per elem: ([0-9]+) cycles\(tsc\) ([0-9]+\.[0-9]+) ns" + + echo + echo "slow path results:" + echo "${result}" | grep -o -E "no-softirq-page_pool03 Per elem: ([0-9]+) cycles\(tsc\) ([0-9]+\.[0-9]+) ns" +} + +run_test + +exit 0 diff --git a/tools/testing/selftests/net/broadcast_pmtu.sh b/tools/testing/selftests/net/broadcast_pmtu.sh new file mode 100755 index 000000000000..726eb5d25839 --- /dev/null +++ b/tools/testing/selftests/net/broadcast_pmtu.sh @@ -0,0 +1,47 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Ensures broadcast route MTU is respected + +CLIENT_NS=$(mktemp -u client-XXXXXXXX) +CLIENT_IP4="192.168.0.1/24" +CLIENT_BROADCAST_ADDRESS="192.168.0.255" + +SERVER_NS=$(mktemp -u server-XXXXXXXX) +SERVER_IP4="192.168.0.2/24" + +setup() { + ip netns add "${CLIENT_NS}" + ip netns add "${SERVER_NS}" + + ip -net "${SERVER_NS}" link add link1 type veth peer name link0 netns "${CLIENT_NS}" + + ip -net "${CLIENT_NS}" link set link0 up + ip -net "${CLIENT_NS}" link set link0 mtu 9000 + ip -net "${CLIENT_NS}" addr add "${CLIENT_IP4}" dev link0 + + ip -net "${SERVER_NS}" link set link1 up + ip -net "${SERVER_NS}" link set link1 mtu 1500 + ip -net "${SERVER_NS}" addr add "${SERVER_IP4}" dev link1 + + read -r -a CLIENT_BROADCAST_ENTRY <<< "$(ip -net "${CLIENT_NS}" route show table local type broadcast)" + ip -net "${CLIENT_NS}" route del "${CLIENT_BROADCAST_ENTRY[@]}" + ip -net "${CLIENT_NS}" route add "${CLIENT_BROADCAST_ENTRY[@]}" mtu 1500 + + ip net exec "${SERVER_NS}" sysctl -wq net.ipv4.icmp_echo_ignore_broadcasts=0 +} + +cleanup() { + ip -net "${SERVER_NS}" link del link1 + ip netns del "${CLIENT_NS}" + ip netns del "${SERVER_NS}" +} + +trap cleanup EXIT + +setup && + echo "Testing for broadcast route MTU" && + ip net exec "${CLIENT_NS}" ping -f -M want -q -c 1 -s 8000 -w 1 -b "${CLIENT_BROADCAST_ADDRESS}" > /dev/null 2>&1 + +exit $? + diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 83ee6a07e072..890b3374dacd 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -142,6 +142,20 @@ check_tc_version() fi } +check_tc_erspan_support() +{ + local dev=$1; shift + + tc filter add dev $dev ingress pref 1 handle 1 flower \ + erspan_opts 1:0:0:0 &> /dev/null + if [[ $? -ne 0 ]]; then + echo "SKIP: iproute2 too old; tc is missing erspan support" + return $ksft_skip + fi + tc filter del dev $dev ingress pref 1 handle 1 flower \ + erspan_opts 1:0:0:0 &> /dev/null +} + # Old versions of tc don't understand "mpls_uc" check_tc_mpls_support() { @@ -526,9 +540,9 @@ setup_wait_dev_with_timeout() return 1 } -setup_wait() +setup_wait_n() { - local num_netifs=${1:-$NUM_NETIFS} + local num_netifs=$1; shift local i for ((i = 1; i <= num_netifs; ++i)); do @@ -539,6 +553,11 @@ setup_wait() sleep $WAIT_TIME } +setup_wait() +{ + setup_wait_n "$NUM_NETIFS" +} + wait_for_dev() { local dev=$1; shift diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh index b1daad19b01e..b58909a93112 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower.sh @@ -6,7 +6,7 @@ ALL_TESTS="match_dst_mac_test match_src_mac_test match_dst_ip_test \ match_ip_tos_test match_indev_test match_ip_ttl_test match_mpls_label_test \ match_mpls_tc_test match_mpls_bos_test match_mpls_ttl_test \ - match_mpls_lse_test" + match_mpls_lse_test match_erspan_opts_test" NUM_NETIFS=2 source tc_common.sh source lib.sh @@ -676,6 +676,56 @@ match_mpls_lse_test() log_test "mpls lse match ($tcflags)" } +match_erspan_opts_test() +{ + RET=0 + + check_tc_erspan_support $h2 || return 0 + + # h1 erspan setup + tunnel_create erspan1 erspan 192.0.2.1 192.0.2.2 dev $h1 seq key 1001 \ + tos C ttl 64 erspan_ver 1 erspan 6789 # ERSPAN Type II + tunnel_create erspan2 erspan 192.0.2.1 192.0.2.2 dev $h1 seq key 1002 \ + tos C ttl 64 erspan_ver 2 erspan_dir egress erspan_hwid 63 \ + # ERSPAN Type III + ip link set dev erspan1 master v$h1 + ip link set dev erspan2 master v$h1 + # h2 erspan setup + ip link add ep-ex type erspan ttl 64 external # To collect tunnel info + ip link set ep-ex up + ip link set dev ep-ex master v$h2 + tc qdisc add dev ep-ex clsact + + # ERSPAN Type II [decap direction] + tc filter add dev ep-ex ingress protocol ip handle 101 flower \ + $tcflags enc_src_ip 192.0.2.1 enc_dst_ip 192.0.2.2 \ + enc_key_id 1001 erspan_opts 1:6789:0:0 \ + action drop + # ERSPAN Type III [decap direction] + tc filter add dev ep-ex ingress protocol ip handle 102 flower \ + $tcflags enc_src_ip 192.0.2.1 enc_dst_ip 192.0.2.2 \ + enc_key_id 1002 erspan_opts 2:0:1:63 action drop + + ep1mac=$(mac_get erspan1) + $MZ erspan1 -c 1 -p 64 -a $ep1mac -b $h2mac -t ip -q + tc_check_packets "dev ep-ex ingress" 101 1 + check_err $? "ERSPAN Type II" + + ep2mac=$(mac_get erspan2) + $MZ erspan2 -c 1 -p 64 -a $ep1mac -b $h2mac -t ip -q + tc_check_packets "dev ep-ex ingress" 102 1 + check_err $? "ERSPAN Type III" + + # h2 erspan cleanup + tc qdisc del dev ep-ex clsact + tunnel_destroy ep-ex + # h1 erspan cleanup + tunnel_destroy erspan2 # ERSPAN Type III + tunnel_destroy erspan1 # ERSPAN Type II + + log_test "erspan_opts match ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh index 7ec58b6b1128..462db0b603e7 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh @@ -765,7 +765,7 @@ ipv6_mcroute_fdb_sep_rx() trap cleanup EXIT setup_prepare -setup_wait "$NUM_NETIFS" +setup_wait tests_run exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/gre_ipv6_lladdr.sh b/tools/testing/selftests/net/gre_ipv6_lladdr.sh index 5b34f6e1f831..48eb999a3120 100755 --- a/tools/testing/selftests/net/gre_ipv6_lladdr.sh +++ b/tools/testing/selftests/net/gre_ipv6_lladdr.sh @@ -24,7 +24,10 @@ setup_basenet() ip -netns "${NS0}" address add dev lo 2001:db8::10/64 nodad } -# Check if network device has an IPv6 link-local address assigned. +# Check the IPv6 configuration of a network device. +# +# We currently check the generation of the link-local IPv6 address and the +# creation of the ff00::/8 multicast route. # # Parameters: # @@ -35,7 +38,7 @@ setup_basenet() # a link-local address) # * $4: The user visible name for the scenario being tested # -check_ipv6_ll_addr() +check_ipv6_device_config() { local DEV="$1" local EXTRA_MATCH="$2" @@ -45,7 +48,11 @@ check_ipv6_ll_addr() RET=0 set +e ip -netns "${NS0}" -6 address show dev "${DEV}" scope link | grep "fe80::" | grep -q "${EXTRA_MATCH}" - check_err_fail "${XRET}" $? "" + check_err_fail "${XRET}" $? "IPv6 link-local address generation" + + ip -netns "${NS0}" -6 route show table local type multicast ff00::/8 proto kernel | grep -q "${DEV}" + check_err_fail 0 $? "IPv6 multicast route creation" + log_test "${MSG}" set -e } @@ -102,20 +109,20 @@ test_gre_device() ;; esac - # Check that IPv6 link-local address is generated when device goes up + # Check the IPv6 device configuration when it goes up ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}" ip -netns "${NS0}" link set dev gretest up - check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "config: ${MSG}" + check_ipv6_device_config gretest "${MATCH_REGEXP}" "${XRET}" "config: ${MSG}" # Now disable link-local address generation ip -netns "${NS0}" link set dev gretest down ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode=1 ip -netns "${NS0}" link set dev gretest up - # Check that link-local address generation works when re-enabled while - # the device is already up + # Check the IPv6 device configuration when link-local address + # generation is re-enabled while the device is already up ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}" - check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "update: ${MSG}" + check_ipv6_device_config gretest "${MATCH_REGEXP}" "${XRET}" "update: ${MSG}" ip -netns "${NS0}" link del dev gretest } @@ -126,7 +133,7 @@ test_gre4() local MODE for GRE_TYPE in "gre" "gretap"; do - printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n" + printf "\n####\nTesting IPv6 configuration of ${GRE_TYPE} devices\n####\n\n" for MODE in "eui64" "none" "stable-privacy" "random"; do test_gre_device "${GRE_TYPE}" 192.0.2.10 192.0.2.11 "${MODE}" @@ -142,7 +149,7 @@ test_gre6() local MODE for GRE_TYPE in "ip6gre" "ip6gretap"; do - printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n" + printf "\n####\nTesting IPv6 configuration of ${GRE_TYPE} devices\n####\n\n" for MODE in "eui64" "none" "stable-privacy" "random"; do test_gre_device "${GRE_TYPE}" 2001:db8::10 2001:db8::11 "${MODE}" diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index ff0dbe23e8e0..c7add0dc4c60 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -240,6 +240,29 @@ create_netdevsim() { echo nsim$id } +create_netdevsim_port() { + local nsim_id="$1" + local ns="$2" + local port_id="$3" + local perm_addr="$4" + local orig_dev + local new_dev + local nsim_path + + nsim_path="/sys/bus/netdevsim/devices/netdevsim$nsim_id" + + echo "$port_id $perm_addr" | ip netns exec "$ns" tee "$nsim_path"/new_port > /dev/null || return 1 + + orig_dev=$(ip netns exec "$ns" find "$nsim_path"/net/ -maxdepth 1 -name 'e*' | tail -n 1) + orig_dev=$(basename "$orig_dev") + new_dev="nsim${nsim_id}p$port_id" + + ip -netns "$ns" link set dev "$orig_dev" name "$new_dev" + ip -netns "$ns" link set dev "$new_dev" up + + echo "$new_dev" +} + # Remove netdevsim with given id. cleanup_netdevsim() { local id="$1" @@ -312,7 +335,7 @@ log_test_result() local test_name=$1; shift local opt_str=$1; shift local result=$1; shift - local retmsg=$1; shift + local retmsg=$1 printf "TEST: %-60s [%s]\n" "$test_name $opt_str" "$result" if [[ $retmsg ]]; then diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py index 8697bd27dc30..02be28dcc089 100644 --- a/tools/testing/selftests/net/lib/py/__init__.py +++ b/tools/testing/selftests/net/lib/py/__init__.py @@ -6,4 +6,4 @@ from .netns import NetNS, NetNSEnter from .nsim import * from .utils import * from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily -from .ynl import NetshaperFamily +from .ynl import NetshaperFamily, DevlinkFamily diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 61287c203b6e..8e35ed12ed9e 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -32,6 +32,7 @@ class KsftTerminate(KeyboardInterrupt): def ksft_pr(*objs, **kwargs): + kwargs["flush"] = True print("#", *objs, **kwargs) @@ -139,7 +140,7 @@ def ktap_result(ok, cnt=1, case="", comment=""): res += "." + str(case.__name__) if comment: res += " # " + comment - print(res) + print(res, flush=True) def ksft_flush_defer(): @@ -227,8 +228,8 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()): totals = {"pass": 0, "fail": 0, "skip": 0, "xfail": 0} - print("TAP version 13") - print("1.." + str(len(cases))) + print("TAP version 13", flush=True) + print("1.." + str(len(cases)), flush=True) global KSFT_RESULT cnt = 0 diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py index 34470d65d871..f395c90fb0f1 100644 --- a/tools/testing/selftests/net/lib/py/utils.py +++ b/tools/testing/selftests/net/lib/py/utils.py @@ -175,6 +175,10 @@ def tool(name, args, json=None, ns=None, host=None): return cmd_obj +def bpftool(args, json=None, ns=None, host=None): + return tool('bpftool', args, json=json, ns=ns, host=host) + + def ip(args, json=None, ns=None, host=None): if ns: args = f'-netns {ns} ' + args @@ -185,6 +189,41 @@ def ethtool(args, json=None, ns=None, host=None): return tool('ethtool', args, json=json, ns=ns, host=host) +def bpftrace(expr, json=None, ns=None, host=None, timeout=None): + """ + Run bpftrace and return map data (if json=True). + The output of bpftrace is inconvenient, so the helper converts + to a dict indexed by map name, e.g.: + { + "@": { ... }, + "@map2": { ... }, + } + """ + cmd_arr = ['bpftrace'] + # Throw in --quiet if json, otherwise the output has two objects + if json: + cmd_arr += ['-f', 'json', '-q'] + if timeout: + expr += ' interval:s:' + str(timeout) + ' { exit(); }' + cmd_arr += ['-e', expr] + cmd_obj = cmd(cmd_arr, ns=ns, host=host, shell=False) + if json: + # bpftrace prints objects as lines + ret = {} + for l in cmd_obj.stdout.split('\n'): + if not l.strip(): + continue + one = _json.loads(l) + if one.get('type') != 'map': + continue + for k, v in one["data"].items(): + if k.startswith('@'): + k = k.lstrip('@') + ret[k] = v + return ret + return cmd_obj + + def rand_port(type=socket.SOCK_STREAM): """ Get a random unprivileged port. diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py index 6329ae805abf..2b3a61ea3bfa 100644 --- a/tools/testing/selftests/net/lib/py/ynl.py +++ b/tools/testing/selftests/net/lib/py/ynl.py @@ -56,3 +56,8 @@ class NetshaperFamily(YnlFamily): def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('net_shaper.yaml')).as_posix(), schema='', recv_size=recv_size) + +class DevlinkFamily(YnlFamily): + def __init__(self, recv_size=0): + super().__init__((SPEC_PATH / Path('devlink.yaml')).as_posix(), + schema='', recv_size=recv_size) diff --git a/tools/testing/selftests/net/lib/xdp_native.bpf.c b/tools/testing/selftests/net/lib/xdp_native.bpf.c new file mode 100644 index 000000000000..521ba38f2ddd --- /dev/null +++ b/tools/testing/selftests/net/lib/xdp_native.bpf.c @@ -0,0 +1,621 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stddef.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/udp.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +#define MAX_ADJST_OFFSET 256 +#define MAX_PAYLOAD_LEN 5000 +#define MAX_HDR_LEN 64 + +enum { + XDP_MODE = 0, + XDP_PORT = 1, + XDP_ADJST_OFFSET = 2, + XDP_ADJST_TAG = 3, +} xdp_map_setup_keys; + +enum { + XDP_MODE_PASS = 0, + XDP_MODE_DROP = 1, + XDP_MODE_TX = 2, + XDP_MODE_TAIL_ADJST = 3, + XDP_MODE_HEAD_ADJST = 4, +} xdp_map_modes; + +enum { + STATS_RX = 0, + STATS_PASS = 1, + STATS_DROP = 2, + STATS_TX = 3, + STATS_ABORT = 4, +} xdp_stats; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 5); + __type(key, __u32); + __type(value, __s32); +} map_xdp_setup SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 5); + __type(key, __u32); + __type(value, __u64); +} map_xdp_stats SEC(".maps"); + +static __u32 min(__u32 a, __u32 b) +{ + return a < b ? a : b; +} + +static void record_stats(struct xdp_md *ctx, __u32 stat_type) +{ + __u64 *count; + + count = bpf_map_lookup_elem(&map_xdp_stats, &stat_type); + + if (count) + __sync_fetch_and_add(count, 1); +} + +static struct udphdr *filter_udphdr(struct xdp_md *ctx, __u16 port) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct udphdr *udph = NULL; + struct ethhdr *eth = data; + + if (data + sizeof(*eth) > data_end) + return NULL; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = data + sizeof(*eth); + + if (iph + 1 > (struct iphdr *)data_end || + iph->protocol != IPPROTO_UDP) + return NULL; + + udph = (void *)eth + sizeof(*iph) + sizeof(*eth); + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ipv6h = data + sizeof(*eth); + + if (ipv6h + 1 > (struct ipv6hdr *)data_end || + ipv6h->nexthdr != IPPROTO_UDP) + return NULL; + + udph = (void *)eth + sizeof(*ipv6h) + sizeof(*eth); + } else { + return NULL; + } + + if (udph + 1 > (struct udphdr *)data_end) + return NULL; + + if (udph->dest != bpf_htons(port)) + return NULL; + + record_stats(ctx, STATS_RX); + + return udph; +} + +static int xdp_mode_pass(struct xdp_md *ctx, __u16 port) +{ + struct udphdr *udph = NULL; + + udph = filter_udphdr(ctx, port); + if (!udph) + return XDP_PASS; + + record_stats(ctx, STATS_PASS); + + return XDP_PASS; +} + +static int xdp_mode_drop_handler(struct xdp_md *ctx, __u16 port) +{ + struct udphdr *udph = NULL; + + udph = filter_udphdr(ctx, port); + if (!udph) + return XDP_PASS; + + record_stats(ctx, STATS_DROP); + + return XDP_DROP; +} + +static void swap_machdr(void *data) +{ + struct ethhdr *eth = data; + __u8 tmp_mac[ETH_ALEN]; + + __builtin_memcpy(tmp_mac, eth->h_source, ETH_ALEN); + __builtin_memcpy(eth->h_source, eth->h_dest, ETH_ALEN); + __builtin_memcpy(eth->h_dest, tmp_mac, ETH_ALEN); +} + +static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct udphdr *udph = NULL; + struct ethhdr *eth = data; + + if (data + sizeof(*eth) > data_end) + return XDP_PASS; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = data + sizeof(*eth); + __be32 tmp_ip = iph->saddr; + + if (iph + 1 > (struct iphdr *)data_end || + iph->protocol != IPPROTO_UDP) + return XDP_PASS; + + udph = data + sizeof(*iph) + sizeof(*eth); + + if (udph + 1 > (struct udphdr *)data_end) + return XDP_PASS; + if (udph->dest != bpf_htons(port)) + return XDP_PASS; + + record_stats(ctx, STATS_RX); + swap_machdr((void *)eth); + + iph->saddr = iph->daddr; + iph->daddr = tmp_ip; + + record_stats(ctx, STATS_TX); + + return XDP_TX; + + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ipv6h = data + sizeof(*eth); + struct in6_addr tmp_ipv6; + + if (ipv6h + 1 > (struct ipv6hdr *)data_end || + ipv6h->nexthdr != IPPROTO_UDP) + return XDP_PASS; + + udph = data + sizeof(*ipv6h) + sizeof(*eth); + + if (udph + 1 > (struct udphdr *)data_end) + return XDP_PASS; + if (udph->dest != bpf_htons(port)) + return XDP_PASS; + + record_stats(ctx, STATS_RX); + swap_machdr((void *)eth); + + __builtin_memcpy(&tmp_ipv6, &ipv6h->saddr, sizeof(tmp_ipv6)); + __builtin_memcpy(&ipv6h->saddr, &ipv6h->daddr, + sizeof(tmp_ipv6)); + __builtin_memcpy(&ipv6h->daddr, &tmp_ipv6, sizeof(tmp_ipv6)); + + record_stats(ctx, STATS_TX); + + return XDP_TX; + } + + return XDP_PASS; +} + +static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct udphdr *udph = NULL; + struct ethhdr *eth = data; + __u32 len, len_new; + + if (data + sizeof(*eth) > data_end) + return NULL; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = data + sizeof(*eth); + __u16 total_len; + + if (iph + 1 > (struct iphdr *)data_end) + return NULL; + + iph->tot_len = bpf_htons(bpf_ntohs(iph->tot_len) + offset); + + udph = (void *)eth + sizeof(*iph) + sizeof(*eth); + if (!udph || udph + 1 > (struct udphdr *)data_end) + return NULL; + + len_new = bpf_htons(bpf_ntohs(udph->len) + offset); + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ipv6h = data + sizeof(*eth); + __u16 payload_len; + + if (ipv6h + 1 > (struct ipv6hdr *)data_end) + return NULL; + + udph = (void *)eth + sizeof(*ipv6h) + sizeof(*eth); + if (!udph || udph + 1 > (struct udphdr *)data_end) + return NULL; + + *udp_csum = ~((__u32)udph->check); + + len = ipv6h->payload_len; + len_new = bpf_htons(bpf_ntohs(len) + offset); + ipv6h->payload_len = len_new; + + *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), *udp_csum); + + len = udph->len; + len_new = bpf_htons(bpf_ntohs(udph->len) + offset); + *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), *udp_csum); + } else { + return NULL; + } + + udph->len = len_new; + + return udph; +} + +static __u16 csum_fold_helper(__u32 csum) +{ + return ~((csum & 0xffff) + (csum >> 16)) ? : 0xffff; +} + +static int xdp_adjst_tail_shrnk_data(struct xdp_md *ctx, __u16 offset, + __u32 hdr_len) +{ + char tmp_buff[MAX_ADJST_OFFSET]; + __u32 buff_pos, udp_csum = 0; + struct udphdr *udph = NULL; + __u32 buff_len; + + udph = update_pkt(ctx, 0 - offset, &udp_csum); + if (!udph) + return -1; + + buff_len = bpf_xdp_get_buff_len(ctx); + + offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET : + offset & 0xff; + if (offset == 0) + return -1; + + /* Make sure we have enough data to avoid eating the header */ + if (buff_len - offset < hdr_len) + return -1; + + buff_pos = buff_len - offset; + if (bpf_xdp_load_bytes(ctx, buff_pos, tmp_buff, offset) < 0) + return -1; + + udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum); + udph->check = (__u16)csum_fold_helper(udp_csum); + + if (bpf_xdp_adjust_tail(ctx, 0 - offset) < 0) + return -1; + + return 0; +} + +static int xdp_adjst_tail_grow_data(struct xdp_md *ctx, __u16 offset) +{ + char tmp_buff[MAX_ADJST_OFFSET]; + __u32 buff_pos, udp_csum = 0; + __u32 buff_len, hdr_len, key; + struct udphdr *udph; + __s32 *val; + __u8 tag; + + /* Proceed to update the packet headers before attempting to adjuste + * the tail. Once the tail is adjusted we lose access to the offset + * amount of data at the end of the packet which is crucial to update + * the checksum. + * Since any failure beyond this would abort the packet, we should + * not worry about passing a packet up the stack with wrong headers + */ + udph = update_pkt(ctx, offset, &udp_csum); + if (!udph) + return -1; + + key = XDP_ADJST_TAG; + val = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!val) + return -1; + + tag = (__u8)(*val); + + for (int i = 0; i < MAX_ADJST_OFFSET; i++) + __builtin_memcpy(&tmp_buff[i], &tag, 1); + + offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET : + offset & 0xff; + if (offset == 0) + return -1; + + udp_csum = bpf_csum_diff(0, 0, (__be32 *)tmp_buff, offset, udp_csum); + udph->check = (__u16)csum_fold_helper(udp_csum); + + buff_len = bpf_xdp_get_buff_len(ctx); + + if (bpf_xdp_adjust_tail(ctx, offset) < 0) { + bpf_printk("Failed to adjust tail\n"); + return -1; + } + + if (bpf_xdp_store_bytes(ctx, buff_len, tmp_buff, offset) < 0) + return -1; + + return 0; +} + +static int xdp_adjst_tail(struct xdp_md *ctx, __u16 port) +{ + void *data = (void *)(long)ctx->data; + struct udphdr *udph = NULL; + __s32 *adjust_offset, *val; + __u32 key, hdr_len; + void *offset_ptr; + __u8 tag; + int ret; + + udph = filter_udphdr(ctx, port); + if (!udph) + return XDP_PASS; + + hdr_len = (void *)udph - data + sizeof(struct udphdr); + key = XDP_ADJST_OFFSET; + adjust_offset = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!adjust_offset) + return XDP_PASS; + + if (*adjust_offset < 0) + ret = xdp_adjst_tail_shrnk_data(ctx, + (__u16)(0 - *adjust_offset), + hdr_len); + else + ret = xdp_adjst_tail_grow_data(ctx, (__u16)(*adjust_offset)); + if (ret) + goto abort_pkt; + + record_stats(ctx, STATS_PASS); + return XDP_PASS; + +abort_pkt: + record_stats(ctx, STATS_ABORT); + return XDP_ABORTED; +} + +static int xdp_adjst_head_shrnk_data(struct xdp_md *ctx, __u64 hdr_len, + __u32 offset) +{ + char tmp_buff[MAX_ADJST_OFFSET]; + struct udphdr *udph; + void *offset_ptr; + __u32 udp_csum = 0; + + /* Update the length information in the IP and UDP headers before + * adjusting the headroom. This simplifies accessing the relevant + * fields in the IP and UDP headers for fragmented packets. Any + * failure beyond this point will result in the packet being aborted, + * so we don't need to worry about incorrect length information for + * passed packets. + */ + udph = update_pkt(ctx, (__s16)(0 - offset), &udp_csum); + if (!udph) + return -1; + + offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET : + offset & 0xff; + if (offset == 0) + return -1; + + if (bpf_xdp_load_bytes(ctx, hdr_len, tmp_buff, offset) < 0) + return -1; + + udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum); + + udph->check = (__u16)csum_fold_helper(udp_csum); + + if (bpf_xdp_load_bytes(ctx, 0, tmp_buff, MAX_ADJST_OFFSET) < 0) + return -1; + + if (bpf_xdp_adjust_head(ctx, offset) < 0) + return -1; + + if (offset > MAX_ADJST_OFFSET) + return -1; + + if (hdr_len > MAX_ADJST_OFFSET || hdr_len == 0) + return -1; + + /* Added here to handle clang complain about negative value */ + hdr_len = hdr_len & 0xff; + + if (hdr_len == 0) + return -1; + + if (bpf_xdp_store_bytes(ctx, 0, tmp_buff, hdr_len) < 0) + return -1; + + return 0; +} + +static int xdp_adjst_head_grow_data(struct xdp_md *ctx, __u64 hdr_len, + __u32 offset) +{ + char hdr_buff[MAX_HDR_LEN]; + char data_buff[MAX_ADJST_OFFSET]; + void *offset_ptr; + __s32 *val; + __u32 key; + __u8 tag; + __u32 udp_csum = 0; + struct udphdr *udph; + + udph = update_pkt(ctx, (__s16)(offset), &udp_csum); + if (!udph) + return -1; + + key = XDP_ADJST_TAG; + val = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!val) + return -1; + + tag = (__u8)(*val); + for (int i = 0; i < MAX_ADJST_OFFSET; i++) + __builtin_memcpy(&data_buff[i], &tag, 1); + + offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET : + offset & 0xff; + if (offset == 0) + return -1; + + udp_csum = bpf_csum_diff(0, 0, (__be32 *)data_buff, offset, udp_csum); + udph->check = (__u16)csum_fold_helper(udp_csum); + + if (hdr_len > MAX_ADJST_OFFSET || hdr_len == 0) + return -1; + + /* Added here to handle clang complain about negative value */ + hdr_len = hdr_len & 0xff; + + if (hdr_len == 0) + return -1; + + if (bpf_xdp_load_bytes(ctx, 0, hdr_buff, hdr_len) < 0) + return -1; + + if (offset > MAX_ADJST_OFFSET) + return -1; + + if (bpf_xdp_adjust_head(ctx, 0 - offset) < 0) + return -1; + + if (bpf_xdp_store_bytes(ctx, 0, hdr_buff, hdr_len) < 0) + return -1; + + if (bpf_xdp_store_bytes(ctx, hdr_len, data_buff, offset) < 0) + return -1; + + return 0; +} + +static int xdp_head_adjst(struct xdp_md *ctx, __u16 port) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct udphdr *udph_ptr = NULL; + __u32 key, size, hdr_len; + __s32 *val; + int res; + + /* Filter packets based on UDP port */ + udph_ptr = filter_udphdr(ctx, port); + if (!udph_ptr) + return XDP_PASS; + + hdr_len = (void *)udph_ptr - data + sizeof(struct udphdr); + + key = XDP_ADJST_OFFSET; + val = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!val) + return XDP_PASS; + + switch (*val) { + case -16: + case 16: + size = 16; + break; + case -32: + case 32: + size = 32; + break; + case -64: + case 64: + size = 64; + break; + case -128: + case 128: + size = 128; + break; + case -256: + case 256: + size = 256; + break; + default: + bpf_printk("Invalid adjustment offset: %d\n", *val); + goto abort; + } + + if (*val < 0) + res = xdp_adjst_head_grow_data(ctx, hdr_len, size); + else + res = xdp_adjst_head_shrnk_data(ctx, hdr_len, size); + + if (res) + goto abort; + + record_stats(ctx, STATS_PASS); + return XDP_PASS; + +abort: + record_stats(ctx, STATS_ABORT); + return XDP_ABORTED; +} + +static int xdp_prog_common(struct xdp_md *ctx) +{ + __u32 key, *port; + __s32 *mode; + + key = XDP_MODE; + mode = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!mode) + return XDP_PASS; + + key = XDP_PORT; + port = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!port) + return XDP_PASS; + + switch (*mode) { + case XDP_MODE_PASS: + return xdp_mode_pass(ctx, (__u16)(*port)); + case XDP_MODE_DROP: + return xdp_mode_drop_handler(ctx, (__u16)(*port)); + case XDP_MODE_TX: + return xdp_mode_tx_handler(ctx, (__u16)(*port)); + case XDP_MODE_TAIL_ADJST: + return xdp_adjst_tail(ctx, (__u16)(*port)); + case XDP_MODE_HEAD_ADJST: + return xdp_head_adjst(ctx, (__u16)(*port)); + } + + /* Default action is to simple pass */ + return XDP_PASS; +} + +SEC("xdp") +int xdp_prog(struct xdp_md *ctx) +{ + return xdp_prog_common(ctx); +} + +SEC("xdp.frags") +int xdp_prog_frags(struct xdp_md *ctx) +{ + return xdp_prog_common(ctx); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index 7ea5fb28c93d..1d5d3c4e7e87 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -77,6 +77,7 @@ static int cfg_cork; static bool cfg_cork_mixed; static int cfg_cpu = -1; /* default: pin to last cpu */ +static int cfg_expect_zerocopy = -1; static int cfg_family = PF_UNSPEC; static int cfg_ifindex = 1; static int cfg_payload_len; @@ -92,9 +93,9 @@ static socklen_t cfg_alen; static struct sockaddr_storage cfg_dst_addr; static struct sockaddr_storage cfg_src_addr; +static int exitcode; static char payload[IP_MAXPACKET]; static long packets, bytes, completions, expected_completions; -static int zerocopied = -1; static uint32_t next_completion; static uint32_t sends_since_notify; @@ -444,11 +445,13 @@ static bool do_recv_completion(int fd, int domain) next_completion = hi + 1; zerocopy = !(serr->ee_code & SO_EE_CODE_ZEROCOPY_COPIED); - if (zerocopied == -1) - zerocopied = zerocopy; - else if (zerocopied != zerocopy) { - fprintf(stderr, "serr: inconsistent\n"); - zerocopied = zerocopy; + if (cfg_expect_zerocopy != -1 && + cfg_expect_zerocopy != zerocopy) { + fprintf(stderr, "serr: ee_code: %u != expected %u\n", + zerocopy, cfg_expect_zerocopy); + exitcode = 1; + /* suppress repeated messages */ + cfg_expect_zerocopy = zerocopy; } if (cfg_verbose >= 2) @@ -571,7 +574,7 @@ static void do_tx(int domain, int type, int protocol) fprintf(stderr, "tx=%lu (%lu MB) txc=%lu zc=%c\n", packets, bytes >> 20, completions, - zerocopied == 1 ? 'y' : 'n'); + cfg_zerocopy && cfg_expect_zerocopy == 1 ? 'y' : 'n'); } static int do_setup_rx(int domain, int type, int protocol) @@ -715,7 +718,7 @@ static void parse_opts(int argc, char **argv) cfg_payload_len = max_payload_len; - while ((c = getopt(argc, argv, "46c:C:D:i:l:mp:rs:S:t:vz")) != -1) { + while ((c = getopt(argc, argv, "46c:C:D:i:l:mp:rs:S:t:vzZ:")) != -1) { switch (c) { case '4': if (cfg_family != PF_UNSPEC) @@ -770,6 +773,9 @@ static void parse_opts(int argc, char **argv) case 'z': cfg_zerocopy = true; break; + case 'Z': + cfg_expect_zerocopy = !!atoi(optarg); + break; } } @@ -817,5 +823,5 @@ int main(int argc, char **argv) else error(1, 0, "unknown cfg_test %s", cfg_test); - return 0; + return exitcode; } diff --git a/tools/testing/selftests/net/msg_zerocopy.sh b/tools/testing/selftests/net/msg_zerocopy.sh index 89c22f5320e0..28178a38a4e7 100755 --- a/tools/testing/selftests/net/msg_zerocopy.sh +++ b/tools/testing/selftests/net/msg_zerocopy.sh @@ -6,6 +6,7 @@ set -e readonly DEV="veth0" +readonly DUMMY_DEV="dummy0" readonly DEV_MTU=65535 readonly BIN="./msg_zerocopy" @@ -14,21 +15,25 @@ readonly NSPREFIX="ns-${RAND}" readonly NS1="${NSPREFIX}1" readonly NS2="${NSPREFIX}2" -readonly SADDR4='192.168.1.1' -readonly DADDR4='192.168.1.2' -readonly SADDR6='fd::1' -readonly DADDR6='fd::2' +readonly LPREFIX4='192.168.1' +readonly RPREFIX4='192.168.2' +readonly LPREFIX6='fd' +readonly RPREFIX6='fc' + readonly path_sysctl_mem="net.core.optmem_max" # No arguments: automated test if [[ "$#" -eq "0" ]]; then - $0 4 tcp -t 1 - $0 6 tcp -t 1 - $0 4 udp -t 1 - $0 6 udp -t 1 - echo "OK. All tests passed" - exit 0 + ret=0 + + $0 4 tcp -t 1 || ret=1 + $0 6 tcp -t 1 || ret=1 + $0 4 udp -t 1 || ret=1 + $0 6 udp -t 1 || ret=1 + + [[ "$ret" == "0" ]] && echo "OK. All tests passed" + exit $ret fi # Argument parsing @@ -45,11 +50,18 @@ readonly EXTRA_ARGS="$@" # Argument parsing: configure addresses if [[ "${IP}" == "4" ]]; then - readonly SADDR="${SADDR4}" - readonly DADDR="${DADDR4}" + readonly SADDR="${LPREFIX4}.1" + readonly DADDR="${LPREFIX4}.2" + readonly DUMMY_ADDR="${RPREFIX4}.1" + readonly DADDR_TXONLY="${RPREFIX4}.2" + readonly MASK="24" elif [[ "${IP}" == "6" ]]; then - readonly SADDR="${SADDR6}" - readonly DADDR="${DADDR6}" + readonly SADDR="${LPREFIX6}::1" + readonly DADDR="${LPREFIX6}::2" + readonly DUMMY_ADDR="${RPREFIX6}::1" + readonly DADDR_TXONLY="${RPREFIX6}::2" + readonly MASK="64" + readonly NODAD="nodad" else echo "Invalid IP version ${IP}" exit 1 @@ -89,33 +101,61 @@ ip netns exec "${NS2}" sysctl -w -q "${path_sysctl_mem}=1000000" ip link add "${DEV}" mtu "${DEV_MTU}" netns "${NS1}" type veth \ peer name "${DEV}" mtu "${DEV_MTU}" netns "${NS2}" +ip link add "${DUMMY_DEV}" mtu "${DEV_MTU}" netns "${NS2}" type dummy + # Bring the devices up ip -netns "${NS1}" link set "${DEV}" up ip -netns "${NS2}" link set "${DEV}" up +ip -netns "${NS2}" link set "${DUMMY_DEV}" up # Set fixed MAC addresses on the devices ip -netns "${NS1}" link set dev "${DEV}" address 02:02:02:02:02:02 ip -netns "${NS2}" link set dev "${DEV}" address 06:06:06:06:06:06 # Add fixed IP addresses to the devices -ip -netns "${NS1}" addr add 192.168.1.1/24 dev "${DEV}" -ip -netns "${NS2}" addr add 192.168.1.2/24 dev "${DEV}" -ip -netns "${NS1}" addr add fd::1/64 dev "${DEV}" nodad -ip -netns "${NS2}" addr add fd::2/64 dev "${DEV}" nodad +ip -netns "${NS1}" addr add "${SADDR}/${MASK}" dev "${DEV}" ${NODAD} +ip -netns "${NS2}" addr add "${DADDR}/${MASK}" dev "${DEV}" ${NODAD} +ip -netns "${NS2}" addr add "${DUMMY_ADDR}/${MASK}" dev "${DUMMY_DEV}" ${NODAD} + +ip -netns "${NS1}" route add default via "${DADDR}" dev "${DEV}" +ip -netns "${NS2}" route add default via "${DADDR_TXONLY}" dev "${DUMMY_DEV}" + +ip netns exec "${NS2}" sysctl -wq net.ipv4.ip_forward=1 +ip netns exec "${NS2}" sysctl -wq net.ipv6.conf.all.forwarding=1 # Optionally disable sg or csum offload to test edge cases # ip netns exec "${NS1}" ethtool -K "${DEV}" sg off +ret=0 + do_test() { local readonly ARGS="$1" - echo "ipv${IP} ${TXMODE} ${ARGS}" - ip netns exec "${NS2}" "${BIN}" "-${IP}" -i "${DEV}" -t 2 -C 2 -S "${SADDR}" -D "${DADDR}" ${ARGS} -r "${RXMODE}" & + # tx-rx test + # packets queued to a local socket are copied, + # sender notification has SO_EE_CODE_ZEROCOPY_COPIED. + + echo -e "\nipv${IP} ${TXMODE} ${ARGS} tx-rx\n" + ip netns exec "${NS2}" "${BIN}" "-${IP}" -i "${DEV}" -t 2 -C 2 \ + -S "${SADDR}" -D "${DADDR}" ${ARGS} -r "${RXMODE}" & sleep 0.2 - ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 -S "${SADDR}" -D "${DADDR}" ${ARGS} "${TXMODE}" + ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 \ + -S "${SADDR}" -D "${DADDR}" ${ARGS} "${TXMODE}" -Z 0 || ret=1 wait + + # next test is unconnected tx to dummy0, cannot exercise with tcp + [[ "${TXMODE}" == "tcp" ]] && return + + # tx-only test: send out dummy0 + # packets leaving the host are not copied, + # sender notification does not have SO_EE_CODE_ZEROCOPY_COPIED. + + echo -e "\nipv${IP} ${TXMODE} ${ARGS} tx-only\n" + ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 \ + -S "${SADDR}" -D "${DADDR_TXONLY}" ${ARGS} "${TXMODE}" -Z 1 || ret=1 } do_test "${EXTRA_ARGS}" do_test "-z ${EXTRA_ARGS}" -echo ok + +[[ "$ret" == "0" ]] && echo "OK" diff --git a/tools/testing/selftests/net/netdev-l2addr.sh b/tools/testing/selftests/net/netdev-l2addr.sh new file mode 100755 index 000000000000..18509da293e5 --- /dev/null +++ b/tools/testing/selftests/net/netdev-l2addr.sh @@ -0,0 +1,59 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh +set -o pipefail + +NSIM_ADDR=2025 +TEST_ADDR="d0:be:d0:be:d0:00" + +RET_CODE=0 + +cleanup() { + cleanup_netdevsim "$NSIM_ADDR" + cleanup_ns "$NS" +} + +trap cleanup EXIT + +fail() { + echo "ERROR: ${1:-unexpected return code} (ret: $_)" >&2 + RET_CODE=1 +} + +get_addr() +{ + local type="$1" + local dev="$2" + local ns="$3" + + ip -j -n "$ns" link show dev "$dev" | jq -er ".[0].$type" +} + +setup_ns NS + +nsim=$(create_netdevsim $NSIM_ADDR "$NS") + +get_addr address "$nsim" "$NS" >/dev/null || fail "Couldn't get ether addr" +get_addr broadcast "$nsim" "$NS" >/dev/null || fail "Couldn't get brd addr" +get_addr permaddr "$nsim" "$NS" >/dev/null && fail "Found perm_addr without setting it" + +ip -n "$NS" link set dev "$nsim" address "$TEST_ADDR" +ip -n "$NS" link set dev "$nsim" brd "$TEST_ADDR" + +[[ "$(get_addr address "$nsim" "$NS")" == "$TEST_ADDR" ]] || fail "Couldn't set ether addr" +[[ "$(get_addr broadcast "$nsim" "$NS")" == "$TEST_ADDR" ]] || fail "Couldn't set brd addr" + +if create_netdevsim_port "$NSIM_ADDR" "$NS" 2 "FF:FF:FF:FF:FF:FF" 2>/dev/null; then + fail "Created netdevsim with broadcast permaddr" +fi + +nsim_port=$(create_netdevsim_port "$NSIM_ADDR" "$NS" 2 "$TEST_ADDR") + +get_addr address "$nsim_port" "$NS" >/dev/null || fail "Couldn't get ether addr" +get_addr broadcast "$nsim_port" "$NS" >/dev/null || fail "Couldn't get brd addr" +[[ "$(get_addr permaddr "$nsim_port" "$NS")" == "$TEST_ADDR" ]] || fail "Couldn't get permaddr" + +cleanup_netdevsim "$NSIM_ADDR" "$NS" + +exit $RET_CODE diff --git a/tools/testing/selftests/net/netfilter/.gitignore b/tools/testing/selftests/net/netfilter/.gitignore index 64c4f8d9aa6c..5d2be9a00627 100644 --- a/tools/testing/selftests/net/netfilter/.gitignore +++ b/tools/testing/selftests/net/netfilter/.gitignore @@ -5,3 +5,4 @@ conntrack_dump_flush conntrack_reverse_clash sctp_collision nf_queue +udpclash diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile index e9b2f553588d..a98ed892f55f 100644 --- a/tools/testing/selftests/net/netfilter/Makefile +++ b/tools/testing/selftests/net/netfilter/Makefile @@ -15,6 +15,7 @@ TEST_PROGS += conntrack_tcp_unreplied.sh TEST_PROGS += conntrack_resize.sh TEST_PROGS += conntrack_sctp_collision.sh TEST_PROGS += conntrack_vrf.sh +TEST_PROGS += conntrack_clash.sh TEST_PROGS += conntrack_reverse_clash.sh TEST_PROGS += ipvs.sh TEST_PROGS += nf_conntrack_packetdrill.sh @@ -44,6 +45,7 @@ TEST_GEN_FILES += connect_close nf_queue TEST_GEN_FILES += conntrack_dump_flush TEST_GEN_FILES += conntrack_reverse_clash TEST_GEN_FILES += sctp_collision +TEST_GEN_FILES += udpclash include ../../lib.mk @@ -52,6 +54,7 @@ $(OUTPUT)/nf_queue: LDLIBS += $(MNL_LDLIBS) $(OUTPUT)/conntrack_dump_flush: CFLAGS += $(MNL_CFLAGS) $(OUTPUT)/conntrack_dump_flush: LDLIBS += $(MNL_LDLIBS) +$(OUTPUT)/udpclash: LDLIBS += -lpthread TEST_FILES := lib.sh TEST_FILES += packetdrill diff --git a/tools/testing/selftests/net/netfilter/conntrack_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_clash.sh new file mode 100755 index 000000000000..3712c1b9b38b --- /dev/null +++ b/tools/testing/selftests/net/netfilter/conntrack_clash.sh @@ -0,0 +1,175 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh + +clash_resolution_active=0 +dport=22111 +ret=0 + +cleanup() +{ + # netns cleanup also zaps any remaining socat echo server. + cleanup_all_ns +} + +checktool "nft --version" "run test without nft" +checktool "conntrack --version" "run test without conntrack" +checktool "socat -h" "run test without socat" + +trap cleanup EXIT + +setup_ns nsclient1 nsclient2 nsrouter + +ip netns exec "$nsrouter" nft -f -<<EOF +table ip t { + chain lb { + meta l4proto udp dnat to numgen random mod 3 map { 0 : 10.0.2.1 . 9000, 1 : 10.0.2.1 . 9001, 2 : 10.0.2.1 . 9002 } + } + + chain prerouting { + type nat hook prerouting priority dstnat + + udp dport $dport counter jump lb + } + + chain output { + type nat hook output priority dstnat + + udp dport $dport counter jump lb + } +} +EOF + +load_simple_ruleset() +{ +ip netns exec "$1" nft -f -<<EOF +table ip t { + chain forward { + type filter hook forward priority 0 + + ct state new counter + } +} +EOF +} + +spawn_servers() +{ + local ns="$1" + local ports="9000 9001 9002" + + for port in $ports; do + ip netns exec "$ns" socat UDP-RECVFROM:$port,fork PIPE 2>/dev/null & + done + + for port in $ports; do + wait_local_port_listen "$ns" $port udp + done +} + +add_addr() +{ + local ns="$1" + local dev="$2" + local i="$3" + local j="$4" + + ip -net "$ns" link set "$dev" up + ip -net "$ns" addr add "10.0.$i.$j/24" dev "$dev" +} + +ping_test() +{ + local ns="$1" + local daddr="$2" + + if ! ip netns exec "$ns" ping -q -c 1 $daddr > /dev/null;then + echo "FAIL: ping from $ns to $daddr" + exit 1 + fi +} + +run_one_clash_test() +{ + local ns="$1" + local daddr="$2" + local dport="$3" + local entries + local cre + + if ! ip netns exec "$ns" ./udpclash $daddr $dport;then + echo "FAIL: did not receive expected number of replies for $daddr:$dport" + ret=1 + return 1 + fi + + entries=$(conntrack -S | wc -l) + cre=$(conntrack -S | grep -v "clash_resolve=0" | wc -l) + + if [ "$cre" -ne "$entries" ] ;then + clash_resolution_active=1 + return 0 + fi + + # 1 cpu -> parallel insertion impossible + if [ "$entries" -eq 1 ]; then + return 0 + fi + + # not a failure: clash resolution logic did not trigger, but all replies + # were received. With right timing, xmit completed sequentially and + # no parallel insertion occurs. + return $ksft_skip +} + +run_clash_test() +{ + local ns="$1" + local daddr="$2" + local dport="$3" + + for i in $(seq 1 10);do + run_one_clash_test "$ns" "$daddr" "$dport" + local rv=$? + if [ $rv -eq 0 ];then + echo "PASS: clash resolution test for $daddr:$dport on attempt $i" + return 0 + elif [ $rv -eq 1 ];then + echo "FAIL: clash resolution test for $daddr:$dport on attempt $i" + return 1 + fi + done +} + +ip link add veth0 netns "$nsclient1" type veth peer name veth0 netns "$nsrouter" +ip link add veth0 netns "$nsclient2" type veth peer name veth1 netns "$nsrouter" +add_addr "$nsclient1" veth0 1 1 +add_addr "$nsclient2" veth0 2 1 +add_addr "$nsrouter" veth0 1 99 +add_addr "$nsrouter" veth1 2 99 + +ip -net "$nsclient1" route add default via 10.0.1.99 +ip -net "$nsclient2" route add default via 10.0.2.99 +ip netns exec "$nsrouter" sysctl -q net.ipv4.ip_forward=1 + +ping_test "$nsclient1" 10.0.1.99 +ping_test "$nsclient1" 10.0.2.1 +ping_test "$nsclient2" 10.0.1.1 + +spawn_servers "$nsclient2" + +# exercise clash resolution with nat: +# nsrouter is supposed to dnat to 10.0.2.1:900{0,1,2,3}. +run_clash_test "$nsclient1" 10.0.1.99 "$dport" + +# exercise clash resolution without nat. +load_simple_ruleset "$nsclient2" +run_clash_test "$nsclient2" 127.0.0.1 9001 + +if [ $clash_resolution_active -eq 0 ];then + [ "$ret" -eq 0 ] && ret=$ksft_skip + echo "SKIP: Clash resolution did not trigger" +fi + +exit $ret diff --git a/tools/testing/selftests/net/netfilter/conntrack_resize.sh b/tools/testing/selftests/net/netfilter/conntrack_resize.sh index 9e033e80219e..788cd56ea4a0 100755 --- a/tools/testing/selftests/net/netfilter/conntrack_resize.sh +++ b/tools/testing/selftests/net/netfilter/conntrack_resize.sh @@ -12,6 +12,9 @@ tmpfile="" tmpfile_proc="" tmpfile_uniq="" ret=0 +have_socat=0 + +socat -h > /dev/null && have_socat=1 insert_count=2000 [ "$KSFT_MACHINE_SLOW" = "yes" ] && insert_count=400 @@ -123,7 +126,7 @@ ctflush() { done } -ctflood() +ct_pingflood() { local ns="$1" local duration="$2" @@ -152,6 +155,44 @@ ctflood() wait } +ct_udpflood() +{ + local ns="$1" + local duration="$2" + local now=$(date +%s) + local end=$((now + duration)) + + [ $have_socat -ne "1" ] && return + + while [ $now -lt $end ]; do +ip netns exec "$ns" bash<<"EOF" + for i in $(seq 1 100);do + dport=$(((RANDOM%65536)+1)) + + echo bar | socat -u STDIN UDP:"127.0.0.1:$dport" & + done > /dev/null 2>&1 + wait +EOF + now=$(date +%s) + done +} + +ct_udpclash() +{ + local ns="$1" + local duration="$2" + local now=$(date +%s) + local end=$((now + duration)) + + [ -x udpclash ] || return + + while [ $now -lt $end ]; do + ip netns exec "$ns" ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1 + + now=$(date +%s) + done +} + # dump to /dev/null. We don't want dumps to cause infinite loops # or use-after-free even when conntrack table is altered while dumps # are in progress. @@ -169,6 +210,48 @@ ct_nulldump() wait } +ct_nulldump_loop() +{ + local ns="$1" + local duration="$2" + local now=$(date +%s) + local end=$((now + duration)) + + while [ $now -lt $end ]; do + ct_nulldump "$ns" + sleep $((RANDOM%2)) + now=$(date +%s) + done +} + +change_timeouts() +{ + local ns="$1" + local r1=$((RANDOM%2)) + local r2=$((RANDOM%2)) + + [ "$r1" -eq 1 ] && ip netns exec "$ns" sysctl -q net.netfilter.nf_conntrack_icmp_timeout=$((RANDOM%5)) + [ "$r2" -eq 1 ] && ip netns exec "$ns" sysctl -q net.netfilter.nf_conntrack_udp_timeout=$((RANDOM%5)) +} + +ct_change_timeouts_loop() +{ + local ns="$1" + local duration="$2" + local now=$(date +%s) + local end=$((now + duration)) + + while [ $now -lt $end ]; do + change_timeouts "$ns" + sleep $((RANDOM%2)) + now=$(date +%s) + done + + # restore defaults + ip netns exec "$ns" sysctl -q net.netfilter.nf_conntrack_icmp_timeout=30 + ip netns exec "$ns" sysctl -q net.netfilter.nf_conntrack_udp_timeout=30 +} + check_taint() { local tainted_then="$1" @@ -198,10 +281,14 @@ insert_flood() r=$((RANDOM%$insert_count)) - ctflood "$n" "$timeout" "floodresize" & + ct_pingflood "$n" "$timeout" "floodresize" & + ct_udpflood "$n" "$timeout" & + ct_udpclash "$n" "$timeout" & + insert_ctnetlink "$n" "$r" & ctflush "$n" "$timeout" & - ct_nulldump "$n" & + ct_nulldump_loop "$n" "$timeout" & + ct_change_timeouts_loop "$n" "$timeout" & wait } @@ -306,7 +393,7 @@ test_dump_all() ip netns exec "$nsclient1" sysctl -q net.netfilter.nf_conntrack_icmp_timeout=3600 - ctflood "$nsclient1" $timeout "dumpall" & + ct_pingflood "$nsclient1" $timeout "dumpall" & insert_ctnetlink "$nsclient2" $insert_count wait @@ -368,7 +455,7 @@ test_conntrack_disable() ct_flush_once "$nsclient1" ct_flush_once "$nsclient2" - ctflood "$nsclient1" "$timeout" "conntrack disable" + ct_pingflood "$nsclient1" "$timeout" "conntrack disable" ip netns exec "$nsclient2" ping -q -c 1 127.0.0.1 >/dev/null 2>&1 # Disabled, should not have picked up any connection. diff --git a/tools/testing/selftests/net/netfilter/nft_concat_range.sh b/tools/testing/selftests/net/netfilter/nft_concat_range.sh index cd12b8b5ac0e..20e76b395c85 100755 --- a/tools/testing/selftests/net/netfilter/nft_concat_range.sh +++ b/tools/testing/selftests/net/netfilter/nft_concat_range.sh @@ -1311,6 +1311,9 @@ maybe_send_match() { # - remove some elements, check that packets don't match anymore test_correctness_main() { range_size=1 + + send_nomatch $((end + 1)) $((end + 1 + src_delta)) || return 1 + for i in $(seq "${start}" $((start + count))); do local elem="" diff --git a/tools/testing/selftests/net/netfilter/udpclash.c b/tools/testing/selftests/net/netfilter/udpclash.c new file mode 100644 index 000000000000..85c7b906ad08 --- /dev/null +++ b/tools/testing/selftests/net/netfilter/udpclash.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Usage: ./udpclash <IP> <PORT> + * + * Emit THREAD_COUNT UDP packets sharing the same saddr:daddr pair. + * + * This mimics DNS resolver libraries that emit A and AAAA requests + * in parallel. + * + * This exercises conntrack clash resolution logic added and later + * refined in + * + * 71d8c47fc653 ("netfilter: conntrack: introduce clash resolution on insertion race") + * ed07d9a021df ("netfilter: nf_conntrack: resolve clash for matching conntracks") + * 6a757c07e51f ("netfilter: conntrack: allow insertion of clashing entries") + */ +#include <stdio.h> +#include <string.h> +#include <stdlib.h> +#include <unistd.h> +#include <arpa/inet.h> +#include <sys/socket.h> +#include <pthread.h> + +#define THREAD_COUNT 128 + +struct thread_args { + const struct sockaddr_in *si_remote; + int sockfd; +}; + +static int wait = 1; + +static void *thread_main(void *varg) +{ + const struct sockaddr_in *si_remote; + const struct thread_args *args = varg; + static const char msg[] = "foo"; + + si_remote = args->si_remote; + + while (wait == 1) + ; + + if (sendto(args->sockfd, msg, strlen(msg), MSG_NOSIGNAL, + (struct sockaddr *)si_remote, sizeof(*si_remote)) < 0) + exit(111); + + return varg; +} + +static int run_test(int fd, const struct sockaddr_in *si_remote) +{ + struct thread_args thread_args = { + .si_remote = si_remote, + .sockfd = fd, + }; + pthread_t *tid = calloc(THREAD_COUNT, sizeof(pthread_t)); + unsigned int repl_count = 0, timeout = 0; + int i; + + if (!tid) { + perror("calloc"); + return 1; + } + + for (i = 0; i < THREAD_COUNT; i++) { + int err = pthread_create(&tid[i], NULL, &thread_main, &thread_args); + + if (err != 0) { + perror("pthread_create"); + exit(1); + } + } + + wait = 0; + + for (i = 0; i < THREAD_COUNT; i++) + pthread_join(tid[i], NULL); + + while (repl_count < THREAD_COUNT) { + struct sockaddr_in si_repl; + socklen_t si_repl_len = sizeof(si_repl); + char repl[512]; + ssize_t ret; + + ret = recvfrom(fd, repl, sizeof(repl), MSG_NOSIGNAL, + (struct sockaddr *) &si_repl, &si_repl_len); + if (ret < 0) { + if (timeout++ > 5000) { + fputs("timed out while waiting for reply from thread\n", stderr); + break; + } + + /* give reply time to pass though the stack */ + usleep(1000); + continue; + } + + if (si_repl_len != sizeof(*si_remote)) { + fprintf(stderr, "warning: reply has unexpected repl_len %d vs %d\n", + (int)si_repl_len, (int)sizeof(si_repl)); + } else if (si_remote->sin_addr.s_addr != si_repl.sin_addr.s_addr || + si_remote->sin_port != si_repl.sin_port) { + char a[64], b[64]; + + inet_ntop(AF_INET, &si_remote->sin_addr, a, sizeof(a)); + inet_ntop(AF_INET, &si_repl.sin_addr, b, sizeof(b)); + + fprintf(stderr, "reply from wrong source: want %s:%d got %s:%d\n", + a, ntohs(si_remote->sin_port), b, ntohs(si_repl.sin_port)); + } + + repl_count++; + } + + printf("got %d of %d replies\n", repl_count, THREAD_COUNT); + + free(tid); + + return repl_count == THREAD_COUNT ? 0 : 1; +} + +int main(int argc, char *argv[]) +{ + struct sockaddr_in si_local = { + .sin_family = AF_INET, + }; + struct sockaddr_in si_remote = { + .sin_family = AF_INET, + }; + int fd, ret; + + if (argc < 3) { + fputs("Usage: send_udp <daddr> <dport>\n", stderr); + return 1; + } + + si_remote.sin_port = htons(atoi(argv[2])); + si_remote.sin_addr.s_addr = inet_addr(argv[1]); + + fd = socket(AF_INET, SOCK_DGRAM|SOCK_CLOEXEC|SOCK_NONBLOCK, IPPROTO_UDP); + if (fd < 0) { + perror("socket"); + return 1; + } + + if (bind(fd, (struct sockaddr *)&si_local, sizeof(si_local)) < 0) { + perror("bind"); + return 1; + } + + ret = run_test(fd, &si_remote); + + close(fd); + + return ret; +} diff --git a/tools/testing/selftests/net/nl_netdev.py b/tools/testing/selftests/net/nl_netdev.py index c9109627a741..c8ffade79a52 100755 --- a/tools/testing/selftests/net/nl_netdev.py +++ b/tools/testing/selftests/net/nl_netdev.py @@ -35,6 +35,91 @@ def napi_list_check(nf) -> None: ksft_eq(len(napis), 100, comment=f"queue count after reset queue {q} mode {i}") +def napi_set_threaded(nf) -> None: + """ + Test that verifies various cases of napi threaded + set and unset at napi and device level. + """ + with NetdevSimDev(queue_count=2) as nsimdev: + nsim = nsimdev.nsims[0] + + ip(f"link set dev {nsim.ifname} up") + + napis = nf.napi_get({'ifindex': nsim.ifindex}, dump=True) + ksft_eq(len(napis), 2) + + napi0_id = napis[0]['id'] + napi1_id = napis[1]['id'] + + # set napi threaded and verify + nf.napi_set({'id': napi0_id, 'threaded': 1}) + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], 1) + ksft_ne(napi0.get('pid'), None) + + # check it is not set for napi1 + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], 0) + ksft_eq(napi1.get('pid'), None) + + ip(f"link set dev {nsim.ifname} down") + ip(f"link set dev {nsim.ifname} up") + + # verify if napi threaded is still set + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], 1) + ksft_ne(napi0.get('pid'), None) + + # check it is still not set for napi1 + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], 0) + ksft_eq(napi1.get('pid'), None) + + # unset napi threaded and verify + nf.napi_set({'id': napi0_id, 'threaded': 0}) + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], 0) + ksft_eq(napi0.get('pid'), None) + + # set threaded at device level + system(f"echo 1 > /sys/class/net/{nsim.ifname}/threaded") + + # check napi threaded is set for both napis + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], 1) + ksft_ne(napi0.get('pid'), None) + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], 1) + ksft_ne(napi1.get('pid'), None) + + # unset threaded at device level + system(f"echo 0 > /sys/class/net/{nsim.ifname}/threaded") + + # check napi threaded is unset for both napis + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], 0) + ksft_eq(napi0.get('pid'), None) + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], 0) + ksft_eq(napi1.get('pid'), None) + + # set napi threaded for napi0 + nf.napi_set({'id': napi0_id, 'threaded': 1}) + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], 1) + ksft_ne(napi0.get('pid'), None) + + # unset threaded at device level + system(f"echo 0 > /sys/class/net/{nsim.ifname}/threaded") + + # check napi threaded is unset for both napis + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], 0) + ksft_eq(napi0.get('pid'), None) + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], 0) + ksft_eq(napi1.get('pid'), None) + def dev_set_threaded(nf) -> None: """ Test that verifies various cases of napi threaded @@ -56,8 +141,10 @@ def dev_set_threaded(nf) -> None: # check napi threaded is set for both napis napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], 1) ksft_ne(napi0.get('pid'), None) napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], 1) ksft_ne(napi1.get('pid'), None) # unset threaded @@ -65,8 +152,10 @@ def dev_set_threaded(nf) -> None: # check napi threaded is unset for both napis napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], 0) ksft_eq(napi0.get('pid'), None) napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], 0) ksft_eq(napi1.get('pid'), None) def nsim_rxq_reset_down(nf) -> None: @@ -156,7 +245,7 @@ def page_pool_check(nf) -> None: def main() -> None: nf = NetdevFamily() ksft_run([empty_check, lo_check, page_pool_check, napi_list_check, - dev_set_threaded, nsim_rxq_reset_down], + dev_set_threaded, napi_set_threaded, nsim_rxq_reset_down], args=(nf, )) ksft_exit() diff --git a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt index 914eabab367a..657e42ca65b5 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Test for blocking read. + --tolerance_usecs=10000 +--mss=1000 `./defaults.sh` diff --git a/tools/testing/selftests/net/packetdrill/tcp_dsack_mult.pkt b/tools/testing/selftests/net/packetdrill/tcp_dsack_mult.pkt new file mode 100644 index 000000000000..c790d0af635e --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_dsack_mult.pkt @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test various DSACK (RFC 2883) behaviors. + +--mss=1000 + +`./defaults.sh` + + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 1024 + +0 accept(3, ..., ...) = 4 + +// First SACK range. + +0 < P. 1001:2001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 1 <nop, nop, sack 1001:2001> + +// Check SACK coalescing (contiguous sequence). + +0 < P. 2001:3001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 1 <nop,nop,sack 1001:3001> + +// Check we have two SACK ranges for non contiguous sequences. + +0 < P. 4001:5001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 1 <nop,nop,sack 4001:5001 1001:3001> + +// Three ranges. + +0 < P. 7001:8001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 1 <nop,nop,sack 7001:8001 4001:5001 1001:3001> + +// DSACK (1001:3001) + SACK (6001:7001) + +0 < P. 1:6001(6000) ack 1 win 1024 + +0 > . 1:1(0) ack 6001 <nop,nop,sack 1001:3001 7001:8001> + +// DSACK (7001:8001) + +0 < P. 6001:8001(2000) ack 1 win 1024 + +0 > . 1:1(0) ack 8001 <nop,nop,sack 7001:8001> + +// DSACK for an older segment. + +0 < P. 1:1001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 8001 <nop,nop,sack 1:1001> diff --git a/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt b/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt index df49c67645ac..e13f0eee9795 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt @@ -1,5 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Test TCP_INQ and TCP_CM_INQ on the client side. + +--mss=1000 + `./defaults.sh ` diff --git a/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt b/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt index 04a5e2590c62..14dd5f813d50 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt @@ -1,5 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Test TCP_INQ and TCP_CM_INQ on the server side. + +--mss=1000 + `./defaults.sh ` diff --git a/tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt b/tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt new file mode 100644 index 000000000000..09aabc775e80 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 + +--mss=1000 + +`./defaults.sh +sysctl -q net.ipv4.tcp_rmem="4096 131072 $((32*1024*1024))"` + +// Test that a not-yet-accepted socket does not change +// its initial sk_rcvbuf (tcp_rmem[1]) when receiving ooo packets. + + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 65535 <mss 1000,nop,nop,sackOK,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 10> + +.1 < . 1:1(0) ack 1 win 257 + +0 < . 2001:41001(39000) ack 1 win 257 + +0 > . 1:1(0) ack 1 <nop,nop,sack 2001:41001> + +0 < . 41001:101001(60000) ack 1 win 257 + +0 > . 1:1(0) ack 1 <nop,nop,sack 2001:101001> + +0 < . 1:1001(1000) ack 1 win 257 + +0 > . 1:1(0) ack 1001 <nop,nop,sack 2001:101001> + +0 < . 1001:2001(1000) ack 1 win 257 + +0 > . 1:1(0) ack 101001 + + +0 accept(3, ..., ...) = 4 + + +0 %{ assert SK_MEMINFO_RCVBUF == 131072, SK_MEMINFO_RCVBUF }% + + +0 close(4) = 0 + +0 close(3) = 0 + +// Test that ooo packets for accepted sockets do increase sk_rcvbuf + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 65535 <mss 1000,nop,nop,sackOK,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 10> + +.1 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + + +0 < . 2001:41001(39000) ack 1 win 257 + +0 > . 1:1(0) ack 1 <nop,nop,sack 2001:41001> + +0 < . 41001:101001(60000) ack 1 win 257 + +0 > . 1:1(0) ack 1 <nop,nop,sack 2001:101001> + + +0 %{ assert SK_MEMINFO_RCVBUF > 131072, SK_MEMINFO_RCVBUF }% + diff --git a/tools/testing/selftests/net/packetdrill/tcp_ooo_rcv_mss.pkt b/tools/testing/selftests/net/packetdrill/tcp_ooo_rcv_mss.pkt new file mode 100644 index 000000000000..7e6bc5fb0c8d --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_ooo_rcv_mss.pkt @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 + +--mss=1000 + +`./defaults.sh +sysctl -q net.ipv4.tcp_rmem="4096 131072 $((32*1024*1024))"` + + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 65535 <mss 1000,nop,nop,sackOK,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 10> + +.1 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + + +0 < . 2001:11001(9000) ack 1 win 257 + +0 > . 1:1(0) ack 1 win 81 <nop,nop,sack 2001:11001> + +// check that ooo packet properly updates tcpi_rcv_mss + +0 %{ assert tcpi_rcv_mss == 1000, tcpi_rcv_mss }% + + +0 < . 11001:21001(10000) ack 1 win 257 + +0 > . 1:1(0) ack 1 win 81 <nop,nop,sack 2001:21001> + diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt new file mode 100644 index 000000000000..3848b419e68c --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 + +--mss=1000 + +`./defaults.sh` + + 0 `nstat -n` + +// Establish a connection. + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [10000], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 0> + +.1 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + + +0 < P. 1:4001(4000) ack 1 win 257 + +0 > . 1:1(0) ack 4001 win 5000 + +// packet in sequence : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW + +0 < P. 4001:54001(50000) ack 1 win 257 + +0 > . 1:1(0) ack 4001 win 5000 + +// ooo packet. : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW + +1 < P. 5001:55001(50000) ack 1 win 257 + +0 > . 1:1(0) ack 4001 win 5000 + +// SKB_DROP_REASON_TCP_INVALID_SEQUENCE / LINUX_MIB_BEYOND_WINDOW + +0 < P. 70001:80001(10000) ack 1 win 257 + +0 > . 1:1(0) ack 4001 win 5000 + + +0 read(4, ..., 100000) = 4000 + +// If queue is empty, accept a packet even if its end_seq is above wup + rcv_wnd + +0 < P. 4001:54001(50000) ack 1 win 257 + +0 > . 1:1(0) ack 54001 win 0 + +// Check LINUX_MIB_BEYOND_WINDOW has been incremented 3 times. ++0 `nstat | grep TcpExtBeyondWindow | grep -q " 3 "` diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt new file mode 100644 index 000000000000..f575c0ff89da --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 + +--mss=1000 + +`./defaults.sh` + + 0 `nstat -n` + +// Establish a connection. + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 win 18980 <mss 1460,nop,wscale 0> + +.1 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + + +0 < P. 1:20001(20000) ack 1 win 257 + +.04 > . 1:1(0) ack 20001 win 18000 + + +0 setsockopt(4, SOL_SOCKET, SO_RCVBUF, [12000], 4) = 0 + +0 < P. 20001:80001(60000) ack 1 win 257 + +0 > . 1:1(0) ack 20001 win 18000 + + +0 read(4, ..., 20000) = 20000 +// A too big packet is accepted if the receive queue is empty + +0 < P. 20001:80001(60000) ack 1 win 257 + +0 > . 1:1(0) ack 80001 win 0 + diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 2e8243a65b50..441b17947230 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -30,6 +30,7 @@ ALL_TESTS=" kci_test_address_proto kci_test_enslave_bonding kci_test_mngtmpaddr + kci_test_operstate " devdummy="test-dummy0" @@ -291,6 +292,17 @@ kci_test_route_get() end_test "PASS: route get" } +check_addr_not_exist() +{ + dev=$1 + addr=$2 + if ip addr show dev $dev | grep -q $addr; then + return 1 + else + return 0 + fi +} + kci_test_addrlft() { for i in $(seq 10 100) ;do @@ -298,9 +310,8 @@ kci_test_addrlft() run_cmd ip addr add 10.23.11.$i/32 dev "$devdummy" preferred_lft $lft valid_lft $((lft+1)) done - sleep 5 - run_cmd_grep_fail "10.23.11." ip addr show dev "$devdummy" - if [ $? -eq 0 ]; then + slowwait 5 check_addr_not_exist "$devdummy" "10.23.11." + if [ $? -eq 1 ]; then check_err 1 end_test "FAIL: preferred_lft addresses remaining" return @@ -1334,6 +1345,39 @@ kci_test_mngtmpaddr() return $ret } +kci_test_operstate() +{ + local ret=0 + + # Check that it is possible to set operational state during device + # creation and that it is preserved when the administrative state of + # the device is toggled. + run_cmd ip link add name vx0 up state up type vxlan id 10010 dstport 4789 + run_cmd_grep "state UP" ip link show dev vx0 + run_cmd ip link set dev vx0 down + run_cmd_grep "state DOWN" ip link show dev vx0 + run_cmd ip link set dev vx0 up + run_cmd_grep "state UP" ip link show dev vx0 + + run_cmd ip link del dev vx0 + + # Check that it is possible to set the operational state of the device + # after creation. + run_cmd ip link add name vx0 up type vxlan id 10010 dstport 4789 + run_cmd_grep "state UNKNOWN" ip link show dev vx0 + run_cmd ip link set dev vx0 state up + run_cmd_grep "state UP" ip link show dev vx0 + + run_cmd ip link del dev vx0 + + if [ "$ret" -ne 0 ]; then + end_test "FAIL: operstate" + return 1 + fi + + end_test "PASS: operstate" +} + kci_test_rtnl() { local current_test diff --git a/tools/testing/selftests/net/rtnetlink_notification.sh b/tools/testing/selftests/net/rtnetlink_notification.sh index 39c1b815bbe4..3f9780232bd6 100755 --- a/tools/testing/selftests/net/rtnetlink_notification.sh +++ b/tools/testing/selftests/net/rtnetlink_notification.sh @@ -8,9 +8,11 @@ ALL_TESTS=" kci_test_mcast_addr_notification + kci_test_anycast_addr_notification " source lib.sh +test_dev="test-dummy1" kci_test_mcast_addr_notification() { @@ -18,7 +20,6 @@ kci_test_mcast_addr_notification() local tmpfile local monitor_pid local match_result - local test_dev="test-dummy1" tmpfile=$(mktemp) defer rm "$tmpfile" @@ -56,6 +57,47 @@ kci_test_mcast_addr_notification() return $RET } +kci_test_anycast_addr_notification() +{ + RET=0 + local tmpfile + local monitor_pid + local match_result + + tmpfile=$(mktemp) + defer rm "$tmpfile" + + ip monitor acaddress > "$tmpfile" & + monitor_pid=$! + defer kill_process "$monitor_pid" + sleep 1 + + if [ ! -e "/proc/$monitor_pid" ]; then + RET=$ksft_skip + log_test "anycast addr notification: iproute2 too old" + return "$RET" + fi + + ip link add name "$test_dev" type dummy + check_err $? "failed to add dummy interface" + ip link set "$test_dev" up + check_err $? "failed to set dummy interface up" + sysctl -qw net.ipv6.conf."$test_dev".forwarding=1 + ip link del dev "$test_dev" + check_err $? "Failed to delete dummy interface" + sleep 1 + + # There should be 2 line matches as follows. + # 9: dummy2 inet6 any fe80:: scope global + # Deleted 9: dummy2 inet6 any fe80:: scope global + match_result=$(grep -cE "$test_dev.*(fe80::)" "$tmpfile") + if [ "$match_result" -ne 2 ]; then + RET=$ksft_fail + fi + log_test "anycast addr notification: Expected 2 matches, got $match_result" + return "$RET" +} + #check for needed privileges if [ "$(id -u)" -ne 0 ];then RET=$ksft_skip diff --git a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh index ba730655a7bf..4bc135e5c22c 100755 --- a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh @@ -594,7 +594,7 @@ setup_rt_local_sids() dev "${DUMMY_DEVNAME}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behavior instaces are grouped together in the 'localsid' + # Endpoint behavior instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule \ add to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh index bedf0ce885c2..34b781a2ae74 100755 --- a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh @@ -681,7 +681,7 @@ setup_rt_local_sids() set_underlay_sids_reachability "${rt}" "${rt_neighs}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behavior instaces are grouped together in the 'localsid' + # Endpoint behavior instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule \ add to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh index 3efce1718c5f..6a68c7eff1dc 100755 --- a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh @@ -395,7 +395,7 @@ setup_rt_local_sids() dev "${VRF_DEVNAME}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behavior instaces are grouped together in the 'localsid' + # Endpoint behavior instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule \ add to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh index cabc70538ffe..0979b5316fdf 100755 --- a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh +++ b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh @@ -343,7 +343,7 @@ setup_rt_local_sids() encap seg6local action End dev "${DUMMY_DEVNAME}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behaviors instaces are grouped together in the 'localsid' + # Endpoint behaviors instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule add \ to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/test_neigh.sh b/tools/testing/selftests/net/test_neigh.sh new file mode 100755 index 000000000000..388056472b5b --- /dev/null +++ b/tools/testing/selftests/net/test_neigh.sh @@ -0,0 +1,366 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh +TESTS=" + extern_valid_ipv4 + extern_valid_ipv6 +" +VERBOSE=0 + +################################################################################ +# Utilities + +run_cmd() +{ + local cmd="$1" + local out + local stderr="2>/dev/null" + + if [ "$VERBOSE" = "1" ]; then + echo "COMMAND: $cmd" + stderr= + fi + + out=$(eval "$cmd" "$stderr") + rc=$? + if [ "$VERBOSE" -eq 1 ] && [ -n "$out" ]; then + echo " $out" + fi + + return $rc +} + +################################################################################ +# Setup + +setup() +{ + set -e + + setup_ns ns1 ns2 + + ip -n "$ns1" link add veth0 type veth peer name veth1 netns "$ns2" + ip -n "$ns1" link set dev veth0 up + ip -n "$ns2" link set dev veth1 up + + ip -n "$ns1" address add 192.0.2.1/24 dev veth0 + ip -n "$ns1" address add 2001:db8:1::1/64 dev veth0 nodad + ip -n "$ns2" address add 192.0.2.2/24 dev veth1 + ip -n "$ns2" address add 2001:db8:1::2/64 dev veth1 nodad + + ip netns exec "$ns1" sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + ip netns exec "$ns2" sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + + sleep 5 + + set +e +} + +exit_cleanup_all() +{ + cleanup_all_ns + exit "${EXIT_STATUS}" +} + +################################################################################ +# Tests + +extern_valid_common() +{ + local af_str=$1; shift + local ip_addr=$1; shift + local tbl_name=$1; shift + local subnet=$1; shift + local mac + + mac=$(ip -n "$ns2" -j link show dev veth1 | jq -r '.[]["address"]') + + RET=0 + + # Check that simple addition works. + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "No \"extern_valid\" flag after addition" + + log_test "$af_str \"extern_valid\" flag: Add entry" + + RET=0 + + # Check that an entry cannot be added with "extern_valid" flag and an + # invalid state. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr nud none dev veth0 extern_valid" + check_fail $? "Managed to add an entry with \"extern_valid\" flag and an invalid state" + + log_test "$af_str \"extern_valid\" flag: Add with an invalid state" + + RET=0 + + # Check that entry cannot be added with both "extern_valid" flag and + # "use" / "managed" flag. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid use" + check_fail $? "Managed to add an entry with \"extern_valid\" flag and \"use\" flag" + + log_test "$af_str \"extern_valid\" flag: Add with \"use\" flag" + + RET=0 + + # Check that "extern_valid" flag can be toggled using replace. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Did not manage to set \"extern_valid\" flag with replace" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_fail $? "Did not manage to clear \"extern_valid\" flag with replace" + + log_test "$af_str \"extern_valid\" flag: Replace entry" + + RET=0 + + # Check that an existing "extern_valid" entry can be marked as + # "managed". + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid managed" + check_err $? "Did not manage to add \"managed\" flag to an existing \"extern_valid\" entry" + + log_test "$af_str \"extern_valid\" flag: Replace entry with \"managed\" flag" + + RET=0 + + # Check that entry cannot be replaced with "extern_valid" flag and an + # invalid state. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh replace $ip_addr nud none dev veth0 extern_valid" + check_fail $? "Managed to replace an entry with \"extern_valid\" flag and an invalid state" + + log_test "$af_str \"extern_valid\" flag: Replace with an invalid state" + + RET=0 + + # Check that an "extern_valid" entry is flushed when the interface is + # put administratively down. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 link set dev veth0 down" + run_cmd "ip -n $ns1 link set dev veth0 up" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0" + check_fail $? "\"extern_valid\" entry not flushed upon interface down" + + log_test "$af_str \"extern_valid\" flag: Interface down" + + RET=0 + + # Check that an "extern_valid" entry is not flushed when the interface + # loses its carrier. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns2 link set dev veth1 down" + run_cmd "ip -n $ns2 link set dev veth1 up" + run_cmd "sleep 2" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0" + check_err $? "\"extern_valid\" entry flushed upon carrier down" + + log_test "$af_str \"extern_valid\" flag: Carrier down" + + RET=0 + + # Check that when entry transitions to "reachable" state it maintains + # the "extern_valid" flag. Wait "delay_probe" seconds for ARP request / + # NS to be sent. + local delay_probe + + delay_probe=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["delay_probe"]') + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid use" + run_cmd "sleep $((delay_probe / 1000 + 2))" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"REACHABLE\"" + check_err $? "Entry did not transition to \"reachable\" state" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Entry did not maintain \"extern_valid\" flag after transition to \"reachable\" state" + + log_test "$af_str \"extern_valid\" flag: Transition to \"reachable\" state" + + RET=0 + + # Drop all packets, trigger resolution and check that entry goes back + # to "stale" state instead of "failed". + local mcast_reprobes + local retrans_time + local ucast_probes + local app_probes + local probes + local delay + + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "tc -n $ns2 qdisc add dev veth1 clsact" + run_cmd "tc -n $ns2 filter add dev veth1 ingress proto all matchall action drop" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid use" + retrans_time=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["retrans"]') + ucast_probes=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["ucast_probes"]') + app_probes=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["app_probes"]') + mcast_reprobes=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["mcast_reprobes"]') + delay=$((delay_probe + (ucast_probes + app_probes + mcast_reprobes) * retrans_time)) + run_cmd "sleep $((delay / 1000 + 2))" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"STALE\"" + check_err $? "Entry did not return to \"stale\" state" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Entry did not maintain \"extern_valid\" flag after returning to \"stale\" state" + probes=$(ip -n "$ns1" -j -s neigh get "$ip_addr" dev veth0 | jq '.[]["probes"]') + if [[ $probes -eq 0 ]]; then + check_err 1 "No probes were sent" + fi + + log_test "$af_str \"extern_valid\" flag: Transition back to \"stale\" state" + + run_cmd "tc -n $ns2 qdisc del dev veth1 clsact" + + RET=0 + + # Forced garbage collection runs whenever the number of entries is + # larger than "thresh3" and deletes stale entries that have not been + # updated in the last 5 seconds. + # + # Check that an "extern_valid" entry survives a forced garbage + # collection. Add an entry, wait 5 seconds and add more entries than + # "thresh3" so that forced garbage collection will run. + # + # Note that the garbage collection thresholds are global resources and + # that changes in the initial namespace affect all the namespaces. + local forced_gc_runs_t0 + local forced_gc_runs_t1 + local orig_thresh1 + local orig_thresh2 + local orig_thresh3 + + run_cmd "ip -n $ns1 neigh flush dev veth0" + orig_thresh1=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh1")) | .["thresh1"]') + orig_thresh2=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh2")) | .["thresh2"]') + orig_thresh3=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh3")) | .["thresh3"]') + run_cmd "ip ntable change name $tbl_name thresh3 10 thresh2 9 thresh1 8" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh add ${subnet}3 lladdr $mac nud stale dev veth0" + run_cmd "sleep 5" + forced_gc_runs_t0=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("forced_gc_runs")) | .["forced_gc_runs"]') + for i in {1..20}; do + run_cmd "ip -n $ns1 neigh add ${subnet}$((i + 4)) nud none dev veth0" + done + forced_gc_runs_t1=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("forced_gc_runs")) | .["forced_gc_runs"]') + if [[ $forced_gc_runs_t1 -eq $forced_gc_runs_t0 ]]; then + check_err 1 "Forced garbage collection did not run" + fi + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Entry with \"extern_valid\" flag did not survive forced garbage collection" + run_cmd "ip -n $ns1 neigh get ${subnet}3 dev veth0" + check_fail $? "Entry without \"extern_valid\" flag survived forced garbage collection" + + log_test "$af_str \"extern_valid\" flag: Forced garbage collection" + + run_cmd "ip ntable change name $tbl_name thresh3 $orig_thresh3 thresh2 $orig_thresh2 thresh1 $orig_thresh1" + + RET=0 + + # Periodic garbage collection runs every "base_reachable"/2 seconds and + # if the number of entries is larger than "thresh1", then it deletes + # stale entries that have not been used in the last "gc_stale" seconds. + # + # Check that an "extern_valid" entry survives a periodic garbage + # collection. Add an "extern_valid" entry, add more than "thresh1" + # regular entries, wait "base_reachable" (longer than "gc_stale") + # seconds and check that the "extern_valid" entry was not deleted. + # + # Note that the garbage collection thresholds and "base_reachable" are + # global resources and that changes in the initial namespace affect all + # the namespaces. + local periodic_gc_runs_t0 + local periodic_gc_runs_t1 + local orig_base_reachable + local orig_gc_stale + + run_cmd "ip -n $ns1 neigh flush dev veth0" + orig_thresh1=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh1")) | .["thresh1"]') + orig_base_reachable=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh1")) | .["base_reachable"]') + run_cmd "ip ntable change name $tbl_name thresh1 10 base_reachable 10000" + orig_gc_stale=$(ip -n "$ns1" -j ntable show name "$tbl_name" dev veth0 | jq '.[]["gc_stale"]') + run_cmd "ip -n $ns1 ntable change name $tbl_name dev veth0 gc_stale 5000" + # Wait orig_base_reachable/2 for the new interval to take effect. + run_cmd "sleep $(((orig_base_reachable / 1000) / 2 + 2))" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh add ${subnet}3 lladdr $mac nud stale dev veth0" + for i in {1..20}; do + run_cmd "ip -n $ns1 neigh add ${subnet}$((i + 4)) nud none dev veth0" + done + periodic_gc_runs_t0=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("periodic_gc_runs")) | .["periodic_gc_runs"]') + run_cmd "sleep 10" + periodic_gc_runs_t1=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("periodic_gc_runs")) | .["periodic_gc_runs"]') + [[ $periodic_gc_runs_t1 -ne $periodic_gc_runs_t0 ]] + check_err $? "Periodic garbage collection did not run" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Entry with \"extern_valid\" flag did not survive periodic garbage collection" + run_cmd "ip -n $ns1 neigh get ${subnet}3 dev veth0" + check_fail $? "Entry without \"extern_valid\" flag survived periodic garbage collection" + + log_test "$af_str \"extern_valid\" flag: Periodic garbage collection" + + run_cmd "ip -n $ns1 ntable change name $tbl_name dev veth0 gc_stale $orig_gc_stale" + run_cmd "ip ntable change name $tbl_name thresh1 $orig_thresh1 base_reachable $orig_base_reachable" +} + +extern_valid_ipv4() +{ + extern_valid_common "IPv4" 192.0.2.2 "arp_cache" 192.0.2. +} + +extern_valid_ipv6() +{ + extern_valid_common "IPv6" 2001:db8:1::2 "ndisc_cache" 2001:db8:1:: +} + +################################################################################ +# Usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -t <test> Test(s) to run (default: all) + (options: $TESTS) + -p Pause on fail + -v Verbose mode (show commands and output) +EOF +} + +################################################################################ +# Main + +while getopts ":t:pvh" opt; do + case $opt in + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=$((VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +require_command jq + +if ! ip neigh help 2>&1 | grep -q "extern_valid"; then + echo "SKIP: iproute2 ip too old, missing \"extern_valid\" support" + exit "$ksft_skip" +fi + +trap exit_cleanup_all EXIT + +for t in $TESTS +do + setup; $t; cleanup_all_ns; +done diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index 1dc337c709f8..b17e032a6d75 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -48,7 +48,7 @@ run_one() { cfg_veth - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 100 ${rx_args} & local PID1=$! wait_local_port_listen ${PEER_NS} 8000 udp @@ -95,7 +95,7 @@ run_one_nat() { # will land on the 'plain' one ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 & local PID1=$! - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 100 ${family} -b ${addr2%/*} ${rx_args} & local PID2=$! wait_local_port_listen "${PEER_NS}" 8000 udp @@ -117,9 +117,9 @@ run_one_2sock() { cfg_veth - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} -p 12345 & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 100 ${rx_args} -p 12345 & local PID1=$! - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 100 ${rx_args} & local PID2=$! wait_local_port_listen "${PEER_NS}" 12345 udp diff --git a/tools/testing/selftests/net/vlan_hw_filter.sh b/tools/testing/selftests/net/vlan_hw_filter.sh index 7bc804ffaf7c..0fb56baf28e4 100755 --- a/tools/testing/selftests/net/vlan_hw_filter.sh +++ b/tools/testing/selftests/net/vlan_hw_filter.sh @@ -3,27 +3,101 @@ readonly NETNS="ns-$(mktemp -u XXXXXX)" +ALL_TESTS=" + test_vlan_filter_check + test_vlan0_del_crash_01 + test_vlan0_del_crash_02 + test_vlan0_del_crash_03 + test_vid0_memleak +" + ret=0 +setup() { + ip netns add ${NETNS} +} + cleanup() { - ip netns del $NETNS + ip netns del $NETNS 2>/dev/null } trap cleanup EXIT fail() { - echo "ERROR: ${1:-unexpected return code} (ret: $_)" >&2 - ret=1 + echo "ERROR: ${1:-unexpected return code} (ret: $_)" >&2 + ret=1 +} + +tests_run() +{ + local current_test + for current_test in ${TESTS:-$ALL_TESTS}; do + $current_test + done +} + +test_vlan_filter_check() { + setup + ip netns exec ${NETNS} ip link add bond0 type bond mode 0 + ip netns exec ${NETNS} ip link add bond_slave_1 type veth peer veth2 + ip netns exec ${NETNS} ip link set bond_slave_1 master bond0 + ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off + ip netns exec ${NETNS} ip link add link bond_slave_1 name bond_slave_1.0 type vlan id 0 + ip netns exec ${NETNS} ip link add link bond0 name bond0.0 type vlan id 0 + ip netns exec ${NETNS} ip link set bond_slave_1 nomaster + ip netns exec ${NETNS} ip link del veth2 || fail "Please check vlan HW filter function" + cleanup } -ip netns add ${NETNS} -ip netns exec ${NETNS} ip link add bond0 type bond mode 0 -ip netns exec ${NETNS} ip link add bond_slave_1 type veth peer veth2 -ip netns exec ${NETNS} ip link set bond_slave_1 master bond0 -ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off -ip netns exec ${NETNS} ip link add link bond_slave_1 name bond_slave_1.0 type vlan id 0 -ip netns exec ${NETNS} ip link add link bond0 name bond0.0 type vlan id 0 -ip netns exec ${NETNS} ip link set bond_slave_1 nomaster -ip netns exec ${NETNS} ip link del veth2 || fail "Please check vlan HW filter function" +#enable vlan_filter feature of real_dev with vlan0 during running time +test_vlan0_del_crash_01() { + setup + ip netns exec ${NETNS} ip link add bond0 type bond mode 0 + ip netns exec ${NETNS} ip link add link bond0 name vlan0 type vlan id 0 protocol 802.1q + ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off + ip netns exec ${NETNS} ifconfig bond0 up + ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter on + ip netns exec ${NETNS} ifconfig bond0 down + ip netns exec ${NETNS} ifconfig bond0 up + ip netns exec ${NETNS} ip link del vlan0 || fail "Please check vlan HW filter function" + cleanup +} + +#enable vlan_filter feature and add vlan0 for real_dev during running time +test_vlan0_del_crash_02() { + setup + ip netns exec ${NETNS} ip link add bond0 type bond mode 0 + ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off + ip netns exec ${NETNS} ifconfig bond0 up + ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter on + ip netns exec ${NETNS} ip link add link bond0 name vlan0 type vlan id 0 protocol 802.1q + ip netns exec ${NETNS} ifconfig bond0 down + ip netns exec ${NETNS} ifconfig bond0 up + ip netns exec ${NETNS} ip link del vlan0 || fail "Please check vlan HW filter function" + cleanup +} + +#enable vlan_filter feature of real_dev during running time +#test kernel_bug of vlan unregister +test_vlan0_del_crash_03() { + setup + ip netns exec ${NETNS} ip link add bond0 type bond mode 0 + ip netns exec ${NETNS} ip link add link bond0 name vlan0 type vlan id 0 protocol 802.1q + ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off + ip netns exec ${NETNS} ifconfig bond0 up + ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter on + ip netns exec ${NETNS} ifconfig bond0 down + ip netns exec ${NETNS} ip link del vlan0 || fail "Please check vlan HW filter function" + cleanup +} + +test_vid0_memleak() { + setup + ip netns exec ${NETNS} ip link add bond0 up type bond mode 0 + ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off + ip netns exec ${NETNS} ip link del dev bond0 || fail "Please check vlan HW filter function" + cleanup +} +tests_run exit $ret diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index edc08a4433fd..ed1e2886ba3c 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -120,6 +120,7 @@ static void usage(char *progname) " -c query the ptp clock's capabilities\n" " -d name device to open\n" " -e val read 'val' external time stamp events\n" + " -E val enable rising (1), falling (2), or both (3) edges\n" " -f val adjust the ptp clock frequency by 'val' ppb\n" " -F chan Enable single channel mask and keep device open for debugfs verification.\n" " -g get the ptp clock time\n" @@ -178,6 +179,7 @@ int main(int argc, char *argv[]) int adjphase = 0; int capabilities = 0; int extts = 0; + int edge = 0; int flagtest = 0; int gettime = 0; int index = 0; @@ -202,7 +204,7 @@ int main(int argc, char *argv[]) progname = strrchr(argv[0], '/'); progname = progname ? 1+progname : argv[0]; - while (EOF != (c = getopt(argc, argv, "cd:e:f:F:ghH:i:k:lL:n:o:p:P:rsSt:T:w:x:Xy:z"))) { + while (EOF != (c = getopt(argc, argv, "cd:e:E:f:F:ghH:i:k:lL:n:o:p:P:rsSt:T:w:x:Xy:z"))) { switch (c) { case 'c': capabilities = 1; @@ -213,6 +215,11 @@ int main(int argc, char *argv[]) case 'e': extts = atoi(optarg); break; + case 'E': + edge = atoi(optarg); + edge = (edge & 1 ? PTP_RISING_EDGE : 0) | + (edge & 2 ? PTP_FALLING_EDGE : 0); + break; case 'f': adjfreq = atoi(optarg); break; @@ -444,7 +451,7 @@ int main(int argc, char *argv[]) if (!readonly) { memset(&extts_request, 0, sizeof(extts_request)); extts_request.index = index; - extts_request.flags = PTP_ENABLE_FEATURE; + extts_request.flags = PTP_ENABLE_FEATURE | edge; if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) { perror("PTP_EXTTS_REQUEST"); extts = 0; diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index db176fe7d0c3..c20aa16b1d63 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -21,6 +21,7 @@ CONFIG_NF_NAT=m CONFIG_NETFILTER_XT_TARGET_LOG=m CONFIG_NET_SCHED=y +CONFIG_IP_SET=m # # Queueing/Scheduling @@ -30,6 +31,7 @@ CONFIG_NET_SCH_CBS=m CONFIG_NET_SCH_CHOKE=m CONFIG_NET_SCH_CODEL=m CONFIG_NET_SCH_DRR=m +CONFIG_NET_SCH_DUALPI2=m CONFIG_NET_SCH_ETF=m CONFIG_NET_SCH_FQ=m CONFIG_NET_SCH_FQ_CODEL=m diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index 9aa44d8176d9..23a61e5b99d0 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -128,6 +128,32 @@ ] }, { + "id": "5456", + "name": "Test htb_dequeue_tree with deactivation and row emptying", + "category": [ + "qdisc", + "htb" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: htb default 1", + "$TC class add dev $DUMMY parent 1: classid 1:1 htb rate 64bit ", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2: netem", + "$TC qdisc add dev $DUMMY parent 2:1 handle 3: blackhole" + ], + "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.11.11", + "expExitCode": "1", + "verifyCmd": "$TC -j qdisc show dev $DUMMY", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DUMMY root" + ] + }, + { "id": "c024", "name": "Test TBF with SKBPRIO - catch qlen corner cases", "category": [ @@ -478,7 +504,6 @@ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%", "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip dst 10.10.10.1/32 flowid 1:1", "$TC class add dev $DUMMY parent 1:0 classid 1:2 hfsc ls m2 10Mbit", - "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 netem duplicate 100%", "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 2 u32 match ip dst 10.10.10.2/32 flowid 1:2", "ping -c 1 10.10.10.1 -I$DUMMY > /dev/null || true", "$TC filter del dev $DUMMY parent 1:0 protocol ip prio 1", @@ -491,8 +516,8 @@ { "kind": "hfsc", "handle": "1:", - "bytes": 392, - "packets": 4 + "bytes": 294, + "packets": 3 } ], "matchCount": "1", @@ -635,5 +660,108 @@ "$TC qdisc del dev $DUMMY handle 1:0 root", "$IP addr del 10.10.10.10/24 dev $DUMMY || true" ] + }, + { + "id": "d74b", + "name": "Test use-after-free with DRR/NETEM/BLACKHOLE chain", + "category": [ + "qdisc", + "hfsc", + "drr", + "netem", + "blackhole" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: drr", + "$TC filter add dev $DUMMY parent 1: basic classid 1:1", + "$TC class add dev $DUMMY parent 1: classid 1:1 drr", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2: hfsc def 1", + "$TC class add dev $DUMMY parent 2: classid 2:1 hfsc rt m1 8 d 1 m2 0", + "$TC qdisc add dev $DUMMY parent 2:1 handle 3: netem", + "$TC qdisc add dev $DUMMY parent 3:1 handle 4: blackhole", + "ping -c1 -W0.01 -I $DUMMY 10.10.11.11 || true", + "$TC class del dev $DUMMY classid 1:1" + ], + "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.11.11", + "expExitCode": "1", + "verifyCmd": "$TC -j class ls dev $DUMMY classid 1:1", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: drr" + ] + }, + { + "id": "be28", + "name": "Try to add fq_codel qdisc as a child of an hhf qdisc", + "category": [ + "qdisc", + "fq_codel", + "hhf" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle a: hhf" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent a: handle b: fq_codel", + "expExitCode": "2", + "verifyCmd": "$TC -j qdisc ls dev $DUMMY handle b:", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DUMMY root" + ] + }, + { + "id": "fcb5", + "name": "Try to add pie qdisc as a child of a drr qdisc", + "category": [ + "qdisc", + "pie", + "drr" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle a: drr" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent a: handle b: pie", + "expExitCode": "2", + "verifyCmd": "$TC -j qdisc ls dev $DUMMY handle b:", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DUMMY root" + ] + }, + { + "id": "7801", + "name": "Try to add fq qdisc as a child of an inexistent hfsc class", + "category": [ + "qdisc", + "sfq", + "hfsc" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle a: hfsc" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent a:fff2 sfq limit 4", + "expExitCode": "2", + "verifyCmd": "$TC -j qdisc ls dev $DUMMY handle b:", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DUMMY root" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json new file mode 100644 index 000000000000..cd1f2ee8f354 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json @@ -0,0 +1,254 @@ +[ + { + "id": "a4c7", + "name": "Create DualPI2 with default setting", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* step_thresh 1ms min_qlen_step 0p coupling_factor 2 drop_on_overload drop_dequeue classic_protection 10% l4s_ect split_gso", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "1ea4", + "name": "Create DualPI2 with memlimit", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 memlimit 20000000", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* memlimit 20000000B", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "2130", + "name": "Create DualPI2 with typical_rtt and max_rtt", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 typical_rtt 20ms max_rtt 200ms", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* target 20ms tupdate 20ms alpha 0.042969 beta 1.496094", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "90c1", + "name": "Create DualPI2 with max_rtt", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 max_rtt 300ms", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* target 50ms tupdate 50ms alpha 0.050781 beta 0.996094", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "7b3c", + "name": "Create DualPI2 with any_ect option", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 any_ect", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* any_ect", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "49a3", + "name": "Create DualPI2 with overflow option", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 overflow", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* overflow", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "d0a1", + "name": "Create DualPI2 with drop_enqueue option", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 drop_enqueue", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* drop_enqueue", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "f051", + "name": "Create DualPI2 with no_split_gso option", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 no_split_gso", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* no_split_gso", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "456b", + "name": "Create DualPI2 with packet step_thresh", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 step_thresh 3p", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* step_thresh 3p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "610c", + "name": "Create DualPI2 with packet min_qlen_step", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 min_qlen_step 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* min_qlen_step 1p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "b4fa", + "name": "Create DualPI2 with packet coupling_factor", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 coupling_factor 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* coupling_factor 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "37f1", + "name": "Create DualPI2 with packet classic_protection", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 classic_protection 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* classic_protection 0%", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/netem.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/netem.json index 3c4444961488..718d2df2aafa 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/netem.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/netem.json @@ -336,5 +336,86 @@ "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root" ] + }, + { + "id": "d34d", + "name": "NETEM test qdisc duplication restriction in qdisc tree in netem_change root", + "category": ["qdisc", "netem"], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle 1: netem limit 1", + "$TC qdisc add dev $DUMMY parent 1: handle 2: netem limit 1" + ], + "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 1: netem duplicate 50%", + "expExitCode": "2", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "qdisc netem", + "matchCount": "2", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1:0 root" + ] + }, + { + "id": "b33f", + "name": "NETEM test qdisc duplication restriction in qdisc tree in netem_change non-root", + "category": ["qdisc", "netem"], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle 1: netem limit 1", + "$TC qdisc add dev $DUMMY parent 1: handle 2: netem limit 1" + ], + "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 2: netem duplicate 50%", + "expExitCode": "2", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "qdisc netem", + "matchCount": "2", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1:0 root" + ] + }, + { + "id": "cafe", + "name": "NETEM test qdisc duplication restriction in qdisc tree", + "category": ["qdisc", "netem"], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle 1: netem limit 1 duplicate 100%" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent 1: handle 2: netem duplicate 100%", + "expExitCode": "2", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "qdisc netem", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1:0 root" + ] + }, + { + "id": "1337", + "name": "NETEM test qdisc duplication restriction in qdisc tree across branches", + "category": ["qdisc", "netem"], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY parent root handle 1:0 hfsc", + "$TC class add dev $DUMMY parent 1:0 classid 1:1 hfsc rt m2 10Mbit", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem", + "$TC class add dev $DUMMY parent 1:0 classid 1:2 hfsc rt m2 10Mbit" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 netem duplicate 100%", + "expExitCode": "2", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "qdisc netem", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1:0 root" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh index 589b18ed758a..dae19687912d 100755 --- a/tools/testing/selftests/tc-testing/tdc.sh +++ b/tools/testing/selftests/tc-testing/tdc.sh @@ -4,8 +4,7 @@ # If a module is required and was not compiled # the test that requires it will fail anyways try_modprobe() { - modprobe -q -R "$1" - if [ $? -ne 0 ]; then + if ! modprobe -q -R "$1"; then echo "Module $1 not found... skipping." else modprobe "$1" @@ -67,4 +66,5 @@ try_modprobe sch_hfsc try_modprobe sch_hhf try_modprobe sch_htb try_modprobe sch_teql -./tdc.py -J`nproc` +try_modprobe sch_dualpi2 +./tdc.py -J"$(nproc)" diff --git a/tools/testing/selftests/ublk/test_stress_03.sh b/tools/testing/selftests/ublk/test_stress_03.sh index 6eef282d569f..3ed4c9b2d8c0 100755 --- a/tools/testing/selftests/ublk/test_stress_03.sh +++ b/tools/testing/selftests/ublk/test_stress_03.sh @@ -32,22 +32,23 @@ _create_backfile 2 128M ublk_io_and_remove 8G -t null -q 4 -z & ublk_io_and_remove 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" & ublk_io_and_remove 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait if _have_feature "AUTO_BUF_REG"; then ublk_io_and_remove 8G -t null -q 4 --auto_zc & ublk_io_and_remove 256M -t loop -q 4 --auto_zc "${UBLK_BACKFILES[0]}" & ublk_io_and_remove 256M -t stripe -q 4 --auto_zc "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & ublk_io_and_remove 8G -t null -q 4 -z --auto_zc --auto_zc_fallback & + wait fi -wait if _have_feature "PER_IO_DAEMON"; then ublk_io_and_remove 8G -t null -q 4 --auto_zc --nthreads 8 --per_io_tasks & ublk_io_and_remove 256M -t loop -q 4 --auto_zc --nthreads 8 --per_io_tasks "${UBLK_BACKFILES[0]}" & ublk_io_and_remove 256M -t stripe -q 4 --auto_zc --nthreads 8 --per_io_tasks "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & ublk_io_and_remove 8G -t null -q 4 -z --auto_zc --auto_zc_fallback --nthreads 8 --per_io_tasks & + wait fi -wait _cleanup_test "stress" _show_result $TID $ERR_CODE diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile index 6e0b4e95e230..88211fd132d2 100644 --- a/tools/testing/vsock/Makefile +++ b/tools/testing/vsock/Makefile @@ -5,6 +5,7 @@ vsock_test: vsock_test.o vsock_test_zerocopy.o timeout.o control.o util.o msg_ze vsock_diag_test: vsock_diag_test.o timeout.o control.o util.o vsock_perf: vsock_perf.o msg_zerocopy_common.o +vsock_test: LDLIBS = -lpthread vsock_uring_test: LDLIBS = -luring vsock_uring_test: control.o util.o vsock_uring_test.o timeout.o msg_zerocopy_common.o diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index 803f1e075b62..7b861a8e997a 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -17,6 +17,7 @@ #include <unistd.h> #include <assert.h> #include <sys/epoll.h> +#include <sys/ioctl.h> #include <sys/mman.h> #include <linux/sockios.h> @@ -101,28 +102,39 @@ void vsock_wait_remote_close(int fd) close(epollfd); } -/* Wait until transport reports no data left to be sent. - * Return false if transport does not implement the unsent_bytes() callback. +/* Wait until ioctl gives an expected int value. + * Return false if the op is not supported. */ -bool vsock_wait_sent(int fd) +bool vsock_ioctl_int(int fd, unsigned long op, int expected) { - int ret, sock_bytes_unsent; + int actual, ret; + char name[32]; + + snprintf(name, sizeof(name), "ioctl(%lu)", op); timeout_begin(TIMEOUT); do { - ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent); + ret = ioctl(fd, op, &actual); if (ret < 0) { - if (errno == EOPNOTSUPP) + if (errno == EOPNOTSUPP || errno == ENOTTY) break; - perror("ioctl(SIOCOUTQ)"); + perror(name); exit(EXIT_FAILURE); } - timeout_check("SIOCOUTQ"); - } while (sock_bytes_unsent != 0); + timeout_check(name); + } while (actual != expected); timeout_end(); - return !ret; + return ret >= 0; +} + +/* Wait until transport reports no data left to be sent. + * Return false if transport does not implement the unsent_bytes() callback. + */ +bool vsock_wait_sent(int fd) +{ + return vsock_ioctl_int(fd, SIOCOUTQ, 0); } /* Create socket <type>, bind to <cid, port>. diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index 71895192cc02..142c02a6834a 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -33,6 +33,10 @@ static const char * const transport_ksyms[] = { static_assert(ARRAY_SIZE(transport_ksyms) == TRANSPORT_NUM); static_assert(BITS_PER_TYPE(int) >= TRANSPORT_NUM); +#define TRANSPORTS_G2H (TRANSPORT_VIRTIO | TRANSPORT_VMCI | TRANSPORT_HYPERV) +#define TRANSPORTS_H2G (TRANSPORT_VHOST | TRANSPORT_VMCI) +#define TRANSPORTS_LOCAL (TRANSPORT_LOOPBACK) + /* Tests can either run as the client or the server */ enum test_mode { TEST_MODE_UNSET, @@ -83,6 +87,7 @@ int vsock_stream_listen(unsigned int cid, unsigned int port); int vsock_seqpacket_accept(unsigned int cid, unsigned int port, struct sockaddr_vm *clientaddrp); void vsock_wait_remote_close(int fd); +bool vsock_ioctl_int(int fd, unsigned long op, int expected); bool vsock_wait_sent(int fd); void send_buf(int fd, const void *buf, size_t len, int flags, ssize_t expected_ret); diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index eb6f54378667..d4517386e551 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -22,6 +22,9 @@ #include <signal.h> #include <sys/ioctl.h> #include <linux/time64.h> +#include <pthread.h> +#include <fcntl.h> +#include <linux/sockios.h> #include "vsock_test_zerocopy.h" #include "timeout.h" @@ -1305,6 +1308,54 @@ static void test_unsent_bytes_client(const struct test_opts *opts, int type) close(fd); } +static void test_unread_bytes_server(const struct test_opts *opts, int type) +{ + unsigned char buf[MSG_BUF_IOCTL_LEN]; + int client_fd; + + client_fd = vsock_accept(VMADDR_CID_ANY, opts->peer_port, NULL, type); + if (client_fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + for (int i = 0; i < sizeof(buf); i++) + buf[i] = rand() & 0xFF; + + send_buf(client_fd, buf, sizeof(buf), 0, sizeof(buf)); + control_writeln("SENT"); + + close(client_fd); +} + +static void test_unread_bytes_client(const struct test_opts *opts, int type) +{ + unsigned char buf[MSG_BUF_IOCTL_LEN]; + int fd; + + fd = vsock_connect(opts->peer_cid, opts->peer_port, type); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + control_expectln("SENT"); + /* The data has arrived but has not been read. The expected is + * MSG_BUF_IOCTL_LEN. + */ + if (!vsock_ioctl_int(fd, SIOCINQ, MSG_BUF_IOCTL_LEN)) { + fprintf(stderr, "Test skipped, SIOCINQ not supported.\n"); + goto out; + } + + recv_buf(fd, buf, sizeof(buf), 0, sizeof(buf)); + /* All data has been consumed, so the expected is 0. */ + vsock_ioctl_int(fd, SIOCINQ, 0); + +out: + close(fd); +} + static void test_stream_unsent_bytes_client(const struct test_opts *opts) { test_unsent_bytes_client(opts, SOCK_STREAM); @@ -1325,6 +1376,26 @@ static void test_seqpacket_unsent_bytes_server(const struct test_opts *opts) test_unsent_bytes_server(opts, SOCK_SEQPACKET); } +static void test_stream_unread_bytes_client(const struct test_opts *opts) +{ + test_unread_bytes_client(opts, SOCK_STREAM); +} + +static void test_stream_unread_bytes_server(const struct test_opts *opts) +{ + test_unread_bytes_server(opts, SOCK_STREAM); +} + +static void test_seqpacket_unread_bytes_client(const struct test_opts *opts) +{ + test_unread_bytes_client(opts, SOCK_SEQPACKET); +} + +static void test_seqpacket_unread_bytes_server(const struct test_opts *opts) +{ + test_unread_bytes_server(opts, SOCK_SEQPACKET); +} + #define RCVLOWAT_CREDIT_UPD_BUF_SIZE (1024 * 128) /* This define is the same as in 'include/linux/virtio_vsock.h': * it is used to decide when to send credit update message during @@ -1867,6 +1938,180 @@ static void test_stream_connect_retry_server(const struct test_opts *opts) close(fd); } +#define TRANSPORT_CHANGE_TIMEOUT 2 /* seconds */ + +static void *test_stream_transport_change_thread(void *vargp) +{ + pid_t *pid = (pid_t *)vargp; + int ret; + + ret = pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, NULL); + if (ret) { + fprintf(stderr, "pthread_setcanceltype: %d\n", ret); + exit(EXIT_FAILURE); + } + + while (true) { + if (kill(*pid, SIGUSR1) < 0) { + perror("kill"); + exit(EXIT_FAILURE); + } + } + return NULL; +} + +static void test_transport_change_signal_handler(int signal) +{ + /* We need a custom handler for SIGUSR1 as the default one terminates the process. */ +} + +static void test_stream_transport_change_client(const struct test_opts *opts) +{ + __sighandler_t old_handler; + pid_t pid = getpid(); + pthread_t thread_id; + time_t tout; + int ret, tr; + + tr = get_transports(); + + /* Print a warning if there is a G2H transport loaded. + * This is on a best effort basis because VMCI can be either G2H and H2G, and there is + * no easy way to understand it. + * The bug we are testing only appears when G2H transports are not loaded. + * This is because `vsock_assign_transport`, when using CID 0, assigns a G2H transport + * to vsk->transport. If none is available it is set to NULL, causing the null-ptr-deref. + */ + if (tr & TRANSPORTS_G2H) + fprintf(stderr, "G2H Transport detected. This test will not fail.\n"); + + old_handler = signal(SIGUSR1, test_transport_change_signal_handler); + if (old_handler == SIG_ERR) { + perror("signal"); + exit(EXIT_FAILURE); + } + + ret = pthread_create(&thread_id, NULL, test_stream_transport_change_thread, &pid); + if (ret) { + fprintf(stderr, "pthread_create: %d\n", ret); + exit(EXIT_FAILURE); + } + + control_expectln("LISTENING"); + + tout = current_nsec() + TRANSPORT_CHANGE_TIMEOUT * NSEC_PER_SEC; + do { + struct sockaddr_vm sa = { + .svm_family = AF_VSOCK, + .svm_cid = opts->peer_cid, + .svm_port = opts->peer_port, + }; + bool send_control = false; + int s; + + s = socket(AF_VSOCK, SOCK_STREAM, 0); + if (s < 0) { + perror("socket"); + exit(EXIT_FAILURE); + } + + ret = connect(s, (struct sockaddr *)&sa, sizeof(sa)); + /* The connect can fail due to signals coming from the thread, + * or because the receiver connection queue is full. + * Ignoring also the latter case because there is no way + * of synchronizing client's connect and server's accept when + * connect(s) are constantly being interrupted by signals. + */ + if (ret == -1 && (errno != EINTR && errno != ECONNRESET)) { + perror("connect"); + exit(EXIT_FAILURE); + } + + /* Notify the server if the connect() is successful or the + * receiver connection queue is full, so it will do accept() + * to drain it. + */ + if (!ret || errno == ECONNRESET) + send_control = true; + + /* Set CID to 0 cause a transport change. */ + sa.svm_cid = 0; + + /* There is a case where this will not fail: + * if the previous connect() is interrupted while the + * connection request is already sent, this second + * connect() will wait for the response. + */ + ret = connect(s, (struct sockaddr *)&sa, sizeof(sa)); + if (!ret || errno == ECONNRESET) + send_control = true; + + close(s); + + if (send_control) + control_writeulong(CONTROL_CONTINUE); + + } while (current_nsec() < tout); + + control_writeulong(CONTROL_DONE); + + ret = pthread_cancel(thread_id); + if (ret) { + fprintf(stderr, "pthread_cancel: %d\n", ret); + exit(EXIT_FAILURE); + } + + ret = pthread_join(thread_id, NULL); + if (ret) { + fprintf(stderr, "pthread_join: %d\n", ret); + exit(EXIT_FAILURE); + } + + if (signal(SIGUSR1, old_handler) == SIG_ERR) { + perror("signal"); + exit(EXIT_FAILURE); + } +} + +static void test_stream_transport_change_server(const struct test_opts *opts) +{ + int s = vsock_stream_listen(VMADDR_CID_ANY, opts->peer_port); + + /* Set the socket to be nonblocking because connects that have been interrupted + * (EINTR) can fill the receiver's accept queue anyway, leading to connect failure. + * As of today (6.15) in such situation there is no way to understand, from the + * client side, if the connection has been queued in the server or not. + */ + if (fcntl(s, F_SETFL, fcntl(s, F_GETFL, 0) | O_NONBLOCK) < 0) { + perror("fcntl"); + exit(EXIT_FAILURE); + } + control_writeln("LISTENING"); + + while (control_readulong() == CONTROL_CONTINUE) { + /* Must accept the connection, otherwise the `listen` + * queue will fill up and new connections will fail. + * There can be more than one queued connection, + * clear them all. + */ + while (true) { + int client = accept(s, NULL, NULL); + + if (client < 0) { + if (errno == EAGAIN) + break; + + perror("accept"); + exit(EXIT_FAILURE); + } + + close(client); + } + } + + close(s); +} + static void test_stream_linger_client(const struct test_opts *opts) { int fd; @@ -2106,6 +2351,21 @@ static struct test_case test_cases[] = { .run_client = test_stream_nolinger_client, .run_server = test_stream_nolinger_server, }, + { + .name = "SOCK_STREAM transport change null-ptr-deref", + .run_client = test_stream_transport_change_client, + .run_server = test_stream_transport_change_server, + }, + { + .name = "SOCK_STREAM ioctl(SIOCINQ) functionality", + .run_client = test_stream_unread_bytes_client, + .run_server = test_stream_unread_bytes_server, + }, + { + .name = "SOCK_SEQPACKET ioctl(SIOCINQ) functionality", + .run_client = test_seqpacket_unread_bytes_client, + .run_server = test_seqpacket_unread_bytes_server, + }, {}, }; |