diff options
Diffstat (limited to 'tools')
102 files changed, 5030 insertions, 666 deletions
diff --git a/tools/arch/alpha/include/uapi/asm/mman.h b/tools/arch/alpha/include/uapi/asm/mman.h index c317d3e6867a..ea6a255ae61f 100644 --- a/tools/arch/alpha/include/uapi/asm/mman.h +++ b/tools/arch/alpha/include/uapi/asm/mman.h @@ -27,8 +27,6 @@ #define MAP_NONBLOCK 0x40000 #define MAP_NORESERVE 0x10000 #define MAP_POPULATE 0x20000 -#define MAP_PRIVATE 0x02 -#define MAP_SHARED 0x01 #define MAP_STACK 0x80000 #define PROT_EXEC 0x4 #define PROT_GROWSDOWN 0x01000000 diff --git a/tools/arch/arm64/include/asm/barrier.h b/tools/arch/arm64/include/asm/barrier.h index 378c051fa177..3b9b41331c4f 100644 --- a/tools/arch/arm64/include/asm/barrier.h +++ b/tools/arch/arm64/include/asm/barrier.h @@ -14,6 +14,16 @@ #define wmb() asm volatile("dmb ishst" ::: "memory") #define rmb() asm volatile("dmb ishld" ::: "memory") +/* + * Kernel uses dmb variants on arm64 for smp_*() barriers. Pretty much the same + * implementation as above mb()/wmb()/rmb(), though for the latter kernel uses + * dsb. In any case, should above mb()/wmb()/rmb() change, make sure the below + * smp_*() don't. + */ +#define smp_mb() asm volatile("dmb ish" ::: "memory") +#define smp_wmb() asm volatile("dmb ishst" ::: "memory") +#define smp_rmb() asm volatile("dmb ishld" ::: "memory") + #define smp_store_release(p, v) \ do { \ union { typeof(*p) __val; char __c[1]; } __u = \ diff --git a/tools/arch/mips/include/uapi/asm/mman.h b/tools/arch/mips/include/uapi/asm/mman.h index de2206883abc..c8acaa138d46 100644 --- a/tools/arch/mips/include/uapi/asm/mman.h +++ b/tools/arch/mips/include/uapi/asm/mman.h @@ -28,8 +28,6 @@ #define MAP_NONBLOCK 0x20000 #define MAP_NORESERVE 0x0400 #define MAP_POPULATE 0x10000 -#define MAP_PRIVATE 0x002 -#define MAP_SHARED 0x001 #define MAP_STACK 0x40000 #define PROT_EXEC 0x04 #define PROT_GROWSDOWN 0x01000000 diff --git a/tools/arch/parisc/include/uapi/asm/mman.h b/tools/arch/parisc/include/uapi/asm/mman.h index 1bd78758bde9..f9fd1325f5bd 100644 --- a/tools/arch/parisc/include/uapi/asm/mman.h +++ b/tools/arch/parisc/include/uapi/asm/mman.h @@ -27,8 +27,6 @@ #define MAP_NONBLOCK 0x20000 #define MAP_NORESERVE 0x4000 #define MAP_POPULATE 0x10000 -#define MAP_PRIVATE 0x02 -#define MAP_SHARED 0x01 #define MAP_STACK 0x40000 #define PROT_EXEC 0x4 #define PROT_GROWSDOWN 0x01000000 diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 8c876c166ef2..26ca425f4c2c 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -463,10 +463,12 @@ struct kvm_ppc_cpu_char { #define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED (1ULL << 58) #define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF (1ULL << 57) #define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS (1ULL << 56) +#define KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST (1ull << 54) #define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY (1ULL << 63) #define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR (1ULL << 62) #define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ULL << 61) +#define KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE (1ull << 58) /* Per-vcpu XICS interrupt controller state */ #define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c) diff --git a/tools/arch/x86/include/asm/barrier.h b/tools/arch/x86/include/asm/barrier.h index 58919868473c..0adf295dd5b6 100644 --- a/tools/arch/x86/include/asm/barrier.h +++ b/tools/arch/x86/include/asm/barrier.h @@ -21,9 +21,12 @@ #define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") #define wmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") #elif defined(__x86_64__) -#define mb() asm volatile("mfence":::"memory") -#define rmb() asm volatile("lfence":::"memory") +#define mb() asm volatile("mfence" ::: "memory") +#define rmb() asm volatile("lfence" ::: "memory") #define wmb() asm volatile("sfence" ::: "memory") +#define smp_rmb() barrier() +#define smp_wmb() barrier() +#define smp_mb() asm volatile("lock; addl $0,-132(%%rsp)" ::: "memory", "cc") #endif #if defined(__x86_64__) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 6d6122524711..981ff9479648 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -344,6 +344,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ diff --git a/tools/arch/xtensa/include/uapi/asm/mman.h b/tools/arch/xtensa/include/uapi/asm/mman.h index 34dde6f44dae..f2b08c990afc 100644 --- a/tools/arch/xtensa/include/uapi/asm/mman.h +++ b/tools/arch/xtensa/include/uapi/asm/mman.h @@ -27,8 +27,6 @@ #define MAP_NONBLOCK 0x20000 #define MAP_NORESERVE 0x0400 #define MAP_POPULATE 0x10000 -#define MAP_PRIVATE 0x002 -#define MAP_SHARED 0x001 #define MAP_STACK 0x40000 #define PROT_EXEC 0x4 #define PROT_GROWSDOWN 0x01000000 diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index e63bce0755eb..8cafb9b31467 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -309,6 +309,48 @@ static int btf_dumper_struct(const struct btf_dumper *d, __u32 type_id, return ret; } +static int btf_dumper_var(const struct btf_dumper *d, __u32 type_id, + __u8 bit_offset, const void *data) +{ + const struct btf_type *t = btf__type_by_id(d->btf, type_id); + int ret; + + jsonw_start_object(d->jw); + jsonw_name(d->jw, btf__name_by_offset(d->btf, t->name_off)); + ret = btf_dumper_do_type(d, t->type, bit_offset, data); + jsonw_end_object(d->jw); + + return ret; +} + +static int btf_dumper_datasec(const struct btf_dumper *d, __u32 type_id, + const void *data) +{ + struct btf_var_secinfo *vsi; + const struct btf_type *t; + int ret = 0, i, vlen; + + t = btf__type_by_id(d->btf, type_id); + if (!t) + return -EINVAL; + + vlen = BTF_INFO_VLEN(t->info); + vsi = (struct btf_var_secinfo *)(t + 1); + + jsonw_start_object(d->jw); + jsonw_name(d->jw, btf__name_by_offset(d->btf, t->name_off)); + jsonw_start_array(d->jw); + for (i = 0; i < vlen; i++) { + ret = btf_dumper_do_type(d, vsi[i].type, 0, data + vsi[i].offset); + if (ret) + break; + } + jsonw_end_array(d->jw); + jsonw_end_object(d->jw); + + return ret; +} + static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, __u8 bit_offset, const void *data) { @@ -341,6 +383,10 @@ static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, case BTF_KIND_CONST: case BTF_KIND_RESTRICT: return btf_dumper_modifier(d, type_id, bit_offset, data); + case BTF_KIND_VAR: + return btf_dumper_var(d, type_id, bit_offset, data); + case BTF_KIND_DATASEC: + return btf_dumper_datasec(d, type_id, data); default: jsonw_printf(d->jw, "(unsupported-kind"); return -EINVAL; @@ -377,6 +423,7 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id, { const struct btf_type *proto_type; const struct btf_array *array; + const struct btf_var *var; const struct btf_type *t; if (!type_id) { @@ -440,6 +487,18 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id, if (pos == -1) return -1; break; + case BTF_KIND_VAR: + var = (struct btf_var *)(t + 1); + if (var->linkage == BTF_VAR_STATIC) + BTF_PRINT_ARG("static "); + BTF_PRINT_TYPE(t->type); + BTF_PRINT_ARG(" %s", + btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_DATASEC: + BTF_PRINT_ARG("section (\"%s\") ", + btf__name_by_offset(btf, t->name_off)); + break; case BTF_KIND_UNKN: default: return -1; diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index e0c650d91784..e96903078991 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -153,11 +153,13 @@ static int do_dump_btf(const struct btf_dumper *d, /* start of key-value pair */ jsonw_start_object(d->jw); - jsonw_name(d->jw, "key"); + if (map_info->btf_key_type_id) { + jsonw_name(d->jw, "key"); - ret = btf_dumper_type(d, map_info->btf_key_type_id, key); - if (ret) - goto err_end_obj; + ret = btf_dumper_type(d, map_info->btf_key_type_id, key); + if (ret) + goto err_end_obj; + } if (!map_is_per_cpu(map_info->type)) { jsonw_name(d->jw, "value"); diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index d2be5a06c339..81067803189e 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -249,6 +249,9 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) if (info->nr_map_ids) show_prog_maps(fd, info->nr_map_ids); + if (info->btf_id) + jsonw_int_field(json_wtr, "btf_id", info->btf_id); + if (!hash_empty(prog_table.table)) { struct pinned_obj *obj; @@ -319,6 +322,9 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) } } + if (info->btf_id) + printf("\n\tbtf_id %d\n", info->btf_id); + printf("\n"); } diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 7073dbe1ff27..0bb17bf88b18 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -195,6 +195,9 @@ static const char *print_imm(void *private_data, if (insn->src_reg == BPF_PSEUDO_MAP_FD) snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "map[id:%u]", insn->imm); + else if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "map[id:%u][0]+%u", insn->imm, (insn + 1)->imm); else snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "0x%llx", (unsigned long long)full_imm); diff --git a/tools/build/feature/test-libopencsd.c b/tools/build/feature/test-libopencsd.c index d68eb4fb40cc..2b0e02c38870 100644 --- a/tools/build/feature/test-libopencsd.c +++ b/tools/build/feature/test-libopencsd.c @@ -4,9 +4,9 @@ /* * Check OpenCSD library version is sufficient to provide required features */ -#define OCSD_MIN_VER ((0 << 16) | (10 << 8) | (0)) +#define OCSD_MIN_VER ((0 << 16) | (11 << 8) | (0)) #if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER) -#error "OpenCSD >= 0.10.0 is required" +#error "OpenCSD >= 0.11.0 is required" #endif int main(void) diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h index cce0b02c0e28..ca28b6ab8db7 100644 --- a/tools/include/linux/filter.h +++ b/tools/include/linux/filter.h @@ -278,10 +278,29 @@ .off = 0, \ .imm = ((__u64) (IMM)) >> 32 }) +#define BPF_LD_IMM64_RAW_FULL(DST, SRC, OFF1, OFF2, IMM1, IMM2) \ + ((struct bpf_insn) { \ + .code = BPF_LD | BPF_DW | BPF_IMM, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF1, \ + .imm = IMM1 }), \ + ((struct bpf_insn) { \ + .code = 0, /* zero is reserved opcode */ \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = OFF2, \ + .imm = IMM2 }) + /* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */ #define BPF_LD_MAP_FD(DST, MAP_FD) \ - BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD) + BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_FD, 0, 0, \ + MAP_FD, 0) + +#define BPF_LD_MAP_VALUE(DST, MAP_FD, VALUE_OFF) \ + BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_VALUE, 0, 0, \ + MAP_FD, VALUE_OFF) /* Relative call */ diff --git a/tools/include/uapi/asm-generic/mman-common-tools.h b/tools/include/uapi/asm-generic/mman-common-tools.h new file mode 100644 index 000000000000..af7d0d3a3182 --- /dev/null +++ b/tools/include/uapi/asm-generic/mman-common-tools.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H +#define __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H + +#include <asm-generic/mman-common.h> + +/* We need this because we need to have tools/include/uapi/ included in the tools + * header search path to get access to stuff that is not yet in the system's + * copy of the files in that directory, but since this cset: + * + * 746c9398f5ac ("arch: move common mmap flags to linux/mman.h") + * + * We end up making sys/mman.h, that is in the system headers, to not find the + * MAP_SHARED and MAP_PRIVATE defines because they are not anymore in our copy + * of asm-generic/mman-common.h. So we define them here and include this header + * from each of the per arch mman.h headers. + */ +#ifndef MAP_SHARED +#define MAP_SHARED 0x01 /* Share changes */ +#define MAP_PRIVATE 0x02 /* Changes are private */ +#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +#endif +#endif // __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h index e7ee32861d51..abd238d0f7a4 100644 --- a/tools/include/uapi/asm-generic/mman-common.h +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -15,9 +15,7 @@ #define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */ #define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */ -#define MAP_SHARED 0x01 /* Share changes */ -#define MAP_PRIVATE 0x02 /* Changes are private */ -#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +/* 0x01 - 0x03 are defined in linux/mman.h */ #define MAP_TYPE 0x0f /* Mask for type of mapping */ #define MAP_FIXED 0x10 /* Interpret addr exactly */ #define MAP_ANONYMOUS 0x20 /* don't use a file */ diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h index 653687d9771b..36c197fc44a0 100644 --- a/tools/include/uapi/asm-generic/mman.h +++ b/tools/include/uapi/asm-generic/mman.h @@ -2,7 +2,7 @@ #ifndef __ASM_GENERIC_MMAN_H #define __ASM_GENERIC_MMAN_H -#include <asm-generic/mman-common.h> +#include <asm-generic/mman-common-tools.h> #define MAP_GROWSDOWN 0x0100 /* stack-like segment */ #define MAP_DENYWRITE 0x0800 /* ETXTBSY */ diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 12cdf611d217..dee7292e1df6 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -824,8 +824,17 @@ __SYSCALL(__NR_futex_time64, sys_futex) __SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval) #endif +#define __NR_pidfd_send_signal 424 +__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal) +#define __NR_io_uring_setup 425 +__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup) +#define __NR_io_uring_enter 426 +__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter) +#define __NR_io_uring_register 427 +__SYSCALL(__NR_io_uring_register, sys_io_uring_register) + #undef __NR_syscalls -#define __NR_syscalls 424 +#define __NR_syscalls 428 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 298b2e197744..397810fa2d33 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -1486,9 +1486,73 @@ struct drm_i915_gem_context_param { #define I915_CONTEXT_MAX_USER_PRIORITY 1023 /* inclusive */ #define I915_CONTEXT_DEFAULT_PRIORITY 0 #define I915_CONTEXT_MIN_USER_PRIORITY -1023 /* inclusive */ + /* + * When using the following param, value should be a pointer to + * drm_i915_gem_context_param_sseu. + */ +#define I915_CONTEXT_PARAM_SSEU 0x7 __u64 value; }; +/** + * Context SSEU programming + * + * It may be necessary for either functional or performance reason to configure + * a context to run with a reduced number of SSEU (where SSEU stands for Slice/ + * Sub-slice/EU). + * + * This is done by configuring SSEU configuration using the below + * @struct drm_i915_gem_context_param_sseu for every supported engine which + * userspace intends to use. + * + * Not all GPUs or engines support this functionality in which case an error + * code -ENODEV will be returned. + * + * Also, flexibility of possible SSEU configuration permutations varies between + * GPU generations and software imposed limitations. Requesting such a + * combination will return an error code of -EINVAL. + * + * NOTE: When perf/OA is active the context's SSEU configuration is ignored in + * favour of a single global setting. + */ +struct drm_i915_gem_context_param_sseu { + /* + * Engine class & instance to be configured or queried. + */ + __u16 engine_class; + __u16 engine_instance; + + /* + * Unused for now. Must be cleared to zero. + */ + __u32 flags; + + /* + * Mask of slices to enable for the context. Valid values are a subset + * of the bitmask value returned for I915_PARAM_SLICE_MASK. + */ + __u64 slice_mask; + + /* + * Mask of subslices to enable for the context. Valid values are a + * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK. + */ + __u64 subslice_mask; + + /* + * Minimum/Maximum number of EUs to enable per subslice for the + * context. min_eus_per_subslice must be inferior or equal to + * max_eus_per_subslice. + */ + __u16 min_eus_per_subslice; + __u16 max_eus_per_subslice; + + /* + * Unused for now. Must be cleared to zero. + */ + __u32 rsvd; +}; + enum drm_i915_oa_format { I915_OA_FORMAT_A13 = 1, /* HSW only */ I915_OA_FORMAT_A29, /* HSW only */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 837024512baf..2e96d0b4bf65 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -105,6 +105,7 @@ enum bpf_cmd { BPF_BTF_GET_FD_BY_ID, BPF_TASK_FD_QUERY, BPF_MAP_LOOKUP_AND_DELETE_ELEM, + BPF_MAP_FREEZE, }; enum bpf_map_type { @@ -255,8 +256,19 @@ enum bpf_attach_type { */ #define BPF_F_ANY_ALIGNMENT (1U << 1) -/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */ +/* When BPF ldimm64's insn[0].src_reg != 0 then this can have + * two extensions: + * + * insn[0].src_reg: BPF_PSEUDO_MAP_FD BPF_PSEUDO_MAP_VALUE + * insn[0].imm: map fd map fd + * insn[1].imm: 0 offset into value + * insn[0].off: 0 0 + * insn[1].off: 0 0 + * ldimm64 rewrite: address of map address of map[0]+offset + * verifier type: CONST_PTR_TO_MAP PTR_TO_MAP_VALUE + */ #define BPF_PSEUDO_MAP_FD 1 +#define BPF_PSEUDO_MAP_VALUE 2 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative * offset to another bpf function @@ -283,7 +295,7 @@ enum bpf_attach_type { #define BPF_OBJ_NAME_LEN 16U -/* Flags for accessing BPF object */ +/* Flags for accessing BPF object from syscall side. */ #define BPF_F_RDONLY (1U << 3) #define BPF_F_WRONLY (1U << 4) @@ -293,6 +305,10 @@ enum bpf_attach_type { /* Zero-initialize hash function seed. This should only be used for testing. */ #define BPF_F_ZERO_SEED (1U << 6) +/* Flags for accessing BPF object from program side. */ +#define BPF_F_RDONLY_PROG (1U << 7) +#define BPF_F_WRONLY_PROG (1U << 8) + /* flags for BPF_PROG_QUERY */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) @@ -396,6 +412,13 @@ union bpf_attr { __aligned_u64 data_out; __u32 repeat; __u32 duration; + __u32 ctx_size_in; /* input: len of ctx_in */ + __u32 ctx_size_out; /* input/output: len of ctx_out + * returns ENOSPC if ctx_out + * is too small. + */ + __aligned_u64 ctx_in; + __aligned_u64 ctx_out; } test; struct { /* anonymous struct used by BPF_*_GET_*_ID */ @@ -1500,6 +1523,10 @@ union bpf_attr { * * **BPF_F_ADJ_ROOM_ENCAP_L4_UDP **: * Use with ENCAP_L3 flags to further specify the tunnel type. * + * * **BPF_F_ADJ_ROOM_ENCAP_L2(len) **: + * Use with ENCAP_L3/L4 flags to further specify the tunnel + * type; **len** is the length of the inner MAC header. + * * A call to this helper is susceptible to change the underlaying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be @@ -2641,10 +2668,16 @@ enum bpf_func_id { /* BPF_FUNC_skb_adjust_room flags. */ #define BPF_F_ADJ_ROOM_FIXED_GSO (1ULL << 0) +#define BPF_ADJ_ROOM_ENCAP_L2_MASK 0xff +#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT 56 + #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1) #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 (1ULL << 2) #define BPF_F_ADJ_ROOM_ENCAP_L4_GRE (1ULL << 3) #define BPF_F_ADJ_ROOM_ENCAP_L4_UDP (1ULL << 4) +#define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \ + BPF_ADJ_ROOM_ENCAP_L2_MASK) \ + << BPF_ADJ_ROOM_ENCAP_L2_SHIFT) /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 7b7475ef2f17..9310652ca4f9 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -39,11 +39,11 @@ struct btf_type { * struct, union and fwd */ __u32 info; - /* "size" is used by INT, ENUM, STRUCT and UNION. + /* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC. * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC and FUNC_PROTO. + * FUNC, FUNC_PROTO and VAR. * "type" is a type_id referring to another type. */ union { @@ -70,8 +70,10 @@ struct btf_type { #define BTF_KIND_RESTRICT 11 /* Restrict */ #define BTF_KIND_FUNC 12 /* Function */ #define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ -#define BTF_KIND_MAX 13 -#define NR_BTF_KINDS 14 +#define BTF_KIND_VAR 14 /* Variable */ +#define BTF_KIND_DATASEC 15 /* Section */ +#define BTF_KIND_MAX BTF_KIND_DATASEC +#define NR_BTF_KINDS (BTF_KIND_MAX + 1) /* For some specific BTF_KIND, "struct btf_type" is immediately * followed by extra data. @@ -138,4 +140,26 @@ struct btf_param { __u32 type; }; +enum { + BTF_VAR_STATIC = 0, + BTF_VAR_GLOBAL_ALLOCATED, +}; + +/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe + * additional information related to the variable such as its linkage. + */ +struct btf_var { + __u32 linkage; +}; + +/* BTF_KIND_DATASEC is followed by multiple "struct btf_var_secinfo" + * to describe all BTF_KIND_VAR types it contains along with it's + * in-section offset as well as size. + */ +struct btf_var_secinfo { + __u32 type; + __u32 offset; + __u32 size; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h index 6448cdd9a350..a2f8658f1c55 100644 --- a/tools/include/uapi/linux/fcntl.h +++ b/tools/include/uapi/linux/fcntl.h @@ -41,6 +41,7 @@ #define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */ #define F_SEAL_GROW 0x0004 /* prevent file from growing */ #define F_SEAL_WRITE 0x0008 /* prevent writes */ +#define F_SEAL_FUTURE_WRITE 0x0010 /* prevent future writes while mapped */ /* (1U << 31) is reserved for signed error codes */ /* diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h index d0f515d53299..fc1a64c3447b 100644 --- a/tools/include/uapi/linux/mman.h +++ b/tools/include/uapi/linux/mman.h @@ -12,6 +12,10 @@ #define OVERCOMMIT_ALWAYS 1 #define OVERCOMMIT_NEVER 2 +#define MAP_SHARED 0x01 /* Share changes */ +#define MAP_PRIVATE 0x02 /* Changes are private */ +#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ + /* * Huge page size encoding when MAP_HUGETLB is specified, and a huge page * size other than the default is desired. See hugetlb_encode.h. diff --git a/tools/io_uring/io_uring-bench.c b/tools/io_uring/io_uring-bench.c index 512306a37531..0f257139b003 100644 --- a/tools/io_uring/io_uring-bench.c +++ b/tools/io_uring/io_uring-bench.c @@ -32,10 +32,6 @@ #include "liburing.h" #include "barrier.h" -#ifndef IOCQE_FLAG_CACHEHIT -#define IOCQE_FLAG_CACHEHIT (1U << 0) -#endif - #define min(a, b) ((a < b) ? (a) : (b)) struct io_sq_ring { @@ -85,7 +81,6 @@ struct submitter { unsigned long reaps; unsigned long done; unsigned long calls; - unsigned long cachehit, cachemiss; volatile int finish; __s32 *fds; @@ -270,10 +265,6 @@ static int reap_events(struct submitter *s) return -1; } } - if (cqe->flags & IOCQE_FLAG_CACHEHIT) - s->cachehit++; - else - s->cachemiss++; reaped++; head++; } while (1); @@ -489,7 +480,7 @@ static void file_depths(char *buf) int main(int argc, char *argv[]) { struct submitter *s = &submitters[0]; - unsigned long done, calls, reap, cache_hit, cache_miss; + unsigned long done, calls, reap; int err, i, flags, fd; char *fdepths; void *ret; @@ -569,44 +560,29 @@ int main(int argc, char *argv[]) pthread_create(&s->thread, NULL, submitter_fn, s); fdepths = malloc(8 * s->nr_files); - cache_hit = cache_miss = reap = calls = done = 0; + reap = calls = done = 0; do { unsigned long this_done = 0; unsigned long this_reap = 0; unsigned long this_call = 0; - unsigned long this_cache_hit = 0; - unsigned long this_cache_miss = 0; unsigned long rpc = 0, ipc = 0; - double hit = 0.0; sleep(1); this_done += s->done; this_call += s->calls; this_reap += s->reaps; - this_cache_hit += s->cachehit; - this_cache_miss += s->cachemiss; - if (this_cache_hit && this_cache_miss) { - unsigned long hits, total; - - hits = this_cache_hit - cache_hit; - total = hits + this_cache_miss - cache_miss; - hit = (double) hits / (double) total; - hit *= 100.0; - } if (this_call - calls) { rpc = (this_done - done) / (this_call - calls); ipc = (this_reap - reap) / (this_call - calls); } else rpc = ipc = -1; file_depths(fdepths); - printf("IOPS=%lu, IOS/call=%ld/%ld, inflight=%u (%s), Cachehit=%0.2f%%\n", + printf("IOPS=%lu, IOS/call=%ld/%ld, inflight=%u (%s)\n", this_done - done, rpc, ipc, s->inflight, - fdepths, hit); + fdepths); done = this_done; calls = this_call; reap = this_reap; - cache_hit = s->cachehit; - cache_miss = s->cachemiss; } while (!finish); pthread_join(s->thread, &ret); diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore index 4db74758c674..7d9e182a1f51 100644 --- a/tools/lib/bpf/.gitignore +++ b/tools/lib/bpf/.gitignore @@ -1,3 +1,4 @@ libbpf_version.h +libbpf.pc FEATURE-DUMP.libbpf test_libbpf diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 5bf8e52c41fc..c6c06bc6683c 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -3,7 +3,7 @@ BPF_VERSION = 0 BPF_PATCHLEVEL = 0 -BPF_EXTRAVERSION = 2 +BPF_EXTRAVERSION = 3 MAKEFLAGS += --no-print-directory @@ -90,6 +90,7 @@ LIBBPF_VERSION = $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION) LIB_TARGET = libbpf.a libbpf.so.$(LIBBPF_VERSION) LIB_FILE = libbpf.a libbpf.so* +PC_FILE = libbpf.pc # Set compile option CFLAGS ifdef EXTRA_CFLAGS @@ -134,13 +135,14 @@ VERSION_SCRIPT := libbpf.map LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) +PC_FILE := $(addprefix $(OUTPUT),$(PC_FILE)) GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {s++} END{print s}') VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) -CMD_TARGETS = $(LIB_TARGET) +CMD_TARGETS = $(LIB_TARGET) $(PC_FILE) CXX_TEST_TARGET = $(OUTPUT)test_libbpf @@ -177,7 +179,7 @@ $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN) $(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(VERSION) \ - -Wl,--version-script=$(VERSION_SCRIPT) $^ -o $@ + -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@ @ln -sf $(@F) $(OUTPUT)libbpf.so @ln -sf $(@F) $(OUTPUT)libbpf.so.$(VERSION) @@ -187,6 +189,12 @@ $(OUTPUT)libbpf.a: $(BPF_IN) $(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a $(QUIET_LINK)$(CXX) $(INCLUDES) $^ -lelf -o $@ +$(OUTPUT)libbpf.pc: + $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \ + -e "s|@LIBDIR@|$(libdir_SQ)|" \ + -e "s|@VERSION@|$(LIBBPF_VERSION)|" \ + < libbpf.pc.template > $@ + check: check_abi check_abi: $(OUTPUT)libbpf.so @@ -220,10 +228,15 @@ install_lib: all_cmd install_headers: $(call QUIET_INSTALL, headers) \ $(call do_install,bpf.h,$(prefix)/include/bpf,644); \ - $(call do_install,libbpf.h,$(prefix)/include/bpf,644); - $(call do_install,btf.h,$(prefix)/include/bpf,644); + $(call do_install,libbpf.h,$(prefix)/include/bpf,644); \ + $(call do_install,btf.h,$(prefix)/include/bpf,644); \ + $(call do_install,xsk.h,$(prefix)/include/bpf,644); + +install_pkgconfig: $(PC_FILE) + $(call QUIET_INSTALL, $(PC_FILE)) \ + $(call do_install,$(PC_FILE),$(libdir_SQ)/pkgconfig,644) -install: install_lib +install: install_lib install_pkgconfig ### Cleaning rules @@ -233,7 +246,7 @@ config-clean: clean: $(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \ - *.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd LIBBPF-CFLAGS + *.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd *.pc LIBBPF-CFLAGS $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 9cd015574e83..955191c64b64 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -79,7 +79,6 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size) int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) { - __u32 name_len = create_attr->name ? strlen(create_attr->name) : 0; union bpf_attr attr; memset(&attr, '\0', sizeof(attr)); @@ -89,8 +88,9 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) attr.value_size = create_attr->value_size; attr.max_entries = create_attr->max_entries; attr.map_flags = create_attr->map_flags; - memcpy(attr.map_name, create_attr->name, - min(name_len, BPF_OBJ_NAME_LEN - 1)); + if (create_attr->name) + memcpy(attr.map_name, create_attr->name, + min(strlen(create_attr->name), BPF_OBJ_NAME_LEN - 1)); attr.numa_node = create_attr->numa_node; attr.btf_fd = create_attr->btf_fd; attr.btf_key_type_id = create_attr->btf_key_type_id; @@ -155,7 +155,6 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, int key_size, int inner_map_fd, int max_entries, __u32 map_flags, int node) { - __u32 name_len = name ? strlen(name) : 0; union bpf_attr attr; memset(&attr, '\0', sizeof(attr)); @@ -166,7 +165,9 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, attr.inner_map_fd = inner_map_fd; attr.max_entries = max_entries; attr.map_flags = map_flags; - memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1)); + if (name) + memcpy(attr.map_name, name, + min(strlen(name), BPF_OBJ_NAME_LEN - 1)); if (node >= 0) { attr.map_flags |= BPF_F_NUMA_NODE; @@ -216,18 +217,15 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, void *finfo = NULL, *linfo = NULL; union bpf_attr attr; __u32 log_level; - __u32 name_len; int fd; if (!load_attr || !log_buf != !log_buf_sz) return -EINVAL; log_level = load_attr->log_level; - if (log_level > 2 || (log_level && !log_buf)) + if (log_level > (4 | 2 | 1) || (log_level && !log_buf)) return -EINVAL; - name_len = load_attr->name ? strlen(load_attr->name) : 0; - memset(&attr, 0, sizeof(attr)); attr.prog_type = load_attr->prog_type; attr.expected_attach_type = load_attr->expected_attach_type; @@ -253,8 +251,9 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, attr.line_info_rec_size = load_attr->line_info_rec_size; attr.line_info_cnt = load_attr->line_info_cnt; attr.line_info = ptr_to_u64(load_attr->line_info); - memcpy(attr.prog_name, load_attr->name, - min(name_len, BPF_OBJ_NAME_LEN - 1)); + if (load_attr->name) + memcpy(attr.prog_name, load_attr->name, + min(strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1)); fd = sys_bpf_prog_load(&attr, sizeof(attr)); if (fd >= 0) @@ -429,6 +428,16 @@ int bpf_map_get_next_key(int fd, const void *key, void *next_key) return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr)); } +int bpf_map_freeze(int fd) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.map_fd = fd; + + return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr)); +} + int bpf_obj_pin(int fd, const char *pathname) { union bpf_attr attr; @@ -545,10 +554,15 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr) attr.test.data_out = ptr_to_u64(test_attr->data_out); attr.test.data_size_in = test_attr->data_size_in; attr.test.data_size_out = test_attr->data_size_out; + attr.test.ctx_in = ptr_to_u64(test_attr->ctx_in); + attr.test.ctx_out = ptr_to_u64(test_attr->ctx_out); + attr.test.ctx_size_in = test_attr->ctx_size_in; + attr.test.ctx_size_out = test_attr->ctx_size_out; attr.test.repeat = test_attr->repeat; ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr)); test_attr->data_size_out = attr.test.data_size_out; + test_attr->ctx_size_out = attr.test.ctx_size_out; test_attr->retval = attr.test.retval; test_attr->duration = attr.test.duration; return ret; diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 6ffdd79bea89..bc30783d1403 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -92,7 +92,7 @@ struct bpf_load_program_attr { #define MAPS_RELAX_COMPAT 0x01 /* Recommend log buffer size */ -#define BPF_LOG_BUF_SIZE (256 * 1024) +#define BPF_LOG_BUF_SIZE (16 * 1024 * 1024) /* verifier maximum in kernels <= 5.1 */ LIBBPF_API int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, char *log_buf, size_t log_buf_sz); @@ -117,6 +117,7 @@ LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value); LIBBPF_API int bpf_map_delete_elem(int fd, const void *key); LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key); +LIBBPF_API int bpf_map_freeze(int fd); LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); LIBBPF_API int bpf_obj_get(const char *pathname); LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd, @@ -135,6 +136,11 @@ struct bpf_prog_test_run_attr { * out: length of data_out */ __u32 retval; /* out: return code of the BPF program */ __u32 duration; /* out: average per repetition in ns */ + const void *ctx_in; /* optional */ + __u32 ctx_size_in; + void *ctx_out; /* optional */ + __u32 ctx_size_out; /* in: max length of ctx_out + * out: length of cxt_out */ }; LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr); diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 87e3020ac1bc..701e7e28ada3 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -24,6 +24,8 @@ ((k) == BTF_KIND_CONST) || \ ((k) == BTF_KIND_RESTRICT)) +#define IS_VAR(k) ((k) == BTF_KIND_VAR) + static struct btf_type btf_void; struct btf { @@ -212,6 +214,10 @@ static int btf_type_size(struct btf_type *t) return base_size + vlen * sizeof(struct btf_member); case BTF_KIND_FUNC_PROTO: return base_size + vlen * sizeof(struct btf_param); + case BTF_KIND_VAR: + return base_size + sizeof(struct btf_var); + case BTF_KIND_DATASEC: + return base_size + vlen * sizeof(struct btf_var_secinfo); default: pr_debug("Unsupported BTF_KIND:%u\n", BTF_INFO_KIND(t->info)); return -EINVAL; @@ -283,6 +289,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) case BTF_KIND_STRUCT: case BTF_KIND_UNION: case BTF_KIND_ENUM: + case BTF_KIND_DATASEC: size = t->size; goto done; case BTF_KIND_PTR: @@ -292,6 +299,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: + case BTF_KIND_VAR: type_id = t->type; break; case BTF_KIND_ARRAY: @@ -326,7 +334,8 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id) t = btf__type_by_id(btf, type_id); while (depth < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t) && - IS_MODIFIER(BTF_INFO_KIND(t->info))) { + (IS_MODIFIER(BTF_INFO_KIND(t->info)) || + IS_VAR(BTF_INFO_KIND(t->info)))) { type_id = t->type; t = btf__type_by_id(btf, type_id); depth++; @@ -408,6 +417,92 @@ done: return btf; } +static int compare_vsi_off(const void *_a, const void *_b) +{ + const struct btf_var_secinfo *a = _a; + const struct btf_var_secinfo *b = _b; + + return a->offset - b->offset; +} + +static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, + struct btf_type *t) +{ + __u32 size = 0, off = 0, i, vars = BTF_INFO_VLEN(t->info); + const char *name = btf__name_by_offset(btf, t->name_off); + const struct btf_type *t_var; + struct btf_var_secinfo *vsi; + struct btf_var *var; + int ret; + + if (!name) { + pr_debug("No name found in string section for DATASEC kind.\n"); + return -ENOENT; + } + + ret = bpf_object__section_size(obj, name, &size); + if (ret || !size || (t->size && t->size != size)) { + pr_debug("Invalid size for section %s: %u bytes\n", name, size); + return -ENOENT; + } + + t->size = size; + + for (i = 0, vsi = (struct btf_var_secinfo *)(t + 1); + i < vars; i++, vsi++) { + t_var = btf__type_by_id(btf, vsi->type); + var = (struct btf_var *)(t_var + 1); + + if (BTF_INFO_KIND(t_var->info) != BTF_KIND_VAR) { + pr_debug("Non-VAR type seen in section %s\n", name); + return -EINVAL; + } + + if (var->linkage == BTF_VAR_STATIC) + continue; + + name = btf__name_by_offset(btf, t_var->name_off); + if (!name) { + pr_debug("No name found in string section for VAR kind\n"); + return -ENOENT; + } + + ret = bpf_object__variable_offset(obj, name, &off); + if (ret) { + pr_debug("No offset found in symbol table for VAR %s\n", name); + return -ENOENT; + } + + vsi->offset = off; + } + + qsort(t + 1, vars, sizeof(*vsi), compare_vsi_off); + return 0; +} + +int btf__finalize_data(struct bpf_object *obj, struct btf *btf) +{ + int err = 0; + __u32 i; + + for (i = 1; i <= btf->nr_types; i++) { + struct btf_type *t = btf->types[i]; + + /* Loader needs to fix up some of the things compiler + * couldn't get its hands on while emitting BTF. This + * is section size and global variable offset. We use + * the info from the ELF itself for this purpose. + */ + if (BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC) { + err = btf_fixup_datasec(obj, btf, t); + if (err) + break; + } + } + + return err; +} + int btf__load(struct btf *btf) { __u32 log_buf_size = BPF_LOG_BUF_SIZE; @@ -2107,6 +2202,9 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, return fwd_kind == real_kind; } + if (cand_kind != canon_kind) + return 0; + switch (cand_kind) { case BTF_KIND_INT: return btf_equal_int(cand_type, canon_type); diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 28a1e1e59861..c7b399e81fce 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -21,6 +21,8 @@ struct btf; struct btf_ext; struct btf_type; +struct bpf_object; + /* * The .BTF.ext ELF section layout defined as * struct btf_ext_header @@ -57,6 +59,7 @@ struct btf_ext_header { LIBBPF_API void btf__free(struct btf *btf); LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size); +LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf); LIBBPF_API int btf__load(struct btf *btf); LIBBPF_API __s32 btf__find_by_name(const struct btf *btf, const char *type_name); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 11c25d9ea431..67484cf32b2e 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -7,6 +7,7 @@ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> * Copyright (C) 2015 Huawei Inc. * Copyright (C) 2017 Nicira, Inc. + * Copyright (C) 2019 Isovalent, Inc. */ #ifndef _GNU_SOURCE @@ -52,6 +53,11 @@ #define BPF_FS_MAGIC 0xcafe4a11 #endif +/* vsprintf() in __base_pr() uses nonliteral format string. It may break + * compilation if user enables corresponding warning. Disable it explicitly. + */ +#pragma GCC diagnostic ignored "-Wformat-nonliteral" + #define __printf(a, b) __attribute__((format(printf, a, b))) static int __base_pr(enum libbpf_print_level level, const char *format, @@ -144,6 +150,7 @@ struct bpf_program { enum { RELO_LD64, RELO_CALL, + RELO_DATA, } type; int insn_idx; union { @@ -152,6 +159,7 @@ struct bpf_program { }; } *reloc_desc; int nr_reloc; + int log_level; struct { int nr; @@ -176,6 +184,19 @@ struct bpf_program { __u32 line_info_cnt; }; +enum libbpf_map_type { + LIBBPF_MAP_UNSPEC, + LIBBPF_MAP_DATA, + LIBBPF_MAP_BSS, + LIBBPF_MAP_RODATA, +}; + +static const char * const libbpf_type_to_btf_name[] = { + [LIBBPF_MAP_DATA] = ".data", + [LIBBPF_MAP_BSS] = ".bss", + [LIBBPF_MAP_RODATA] = ".rodata", +}; + struct bpf_map { int fd; char *name; @@ -187,11 +208,18 @@ struct bpf_map { __u32 btf_value_type_id; void *priv; bpf_map_clear_priv_t clear_priv; + enum libbpf_map_type libbpf_type; +}; + +struct bpf_secdata { + void *rodata; + void *data; }; static LIST_HEAD(bpf_objects_list); struct bpf_object { + char name[BPF_OBJ_NAME_LEN]; char license[64]; __u32 kern_version; @@ -199,6 +227,7 @@ struct bpf_object { size_t nr_programs; struct bpf_map *maps; size_t nr_maps; + struct bpf_secdata sections; bool loaded; bool has_pseudo_calls; @@ -214,6 +243,9 @@ struct bpf_object { Elf *elf; GElf_Ehdr ehdr; Elf_Data *symbols; + Elf_Data *data; + Elf_Data *rodata; + Elf_Data *bss; size_t strtabidx; struct { GElf_Shdr shdr; @@ -222,6 +254,9 @@ struct bpf_object { int nr_reloc; int maps_shndx; int text_shndx; + int data_shndx; + int rodata_shndx; + int bss_shndx; } efile; /* * All loaded bpf_object is linked in a list, which is @@ -443,6 +478,7 @@ static struct bpf_object *bpf_object__new(const char *path, size_t obj_buf_sz) { struct bpf_object *obj; + char *end; obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1); if (!obj) { @@ -451,8 +487,14 @@ static struct bpf_object *bpf_object__new(const char *path, } strcpy(obj->path, path); - obj->efile.fd = -1; + /* Using basename() GNU version which doesn't modify arg. */ + strncpy(obj->name, basename((void *)path), + sizeof(obj->name) - 1); + end = strchr(obj->name, '.'); + if (end) + *end = 0; + obj->efile.fd = -1; /* * Caller of this function should also calls * bpf_object__elf_finish() after data collection to return @@ -462,6 +504,9 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.obj_buf = obj_buf; obj->efile.obj_buf_sz = obj_buf_sz; obj->efile.maps_shndx = -1; + obj->efile.data_shndx = -1; + obj->efile.rodata_shndx = -1; + obj->efile.bss_shndx = -1; obj->loaded = false; @@ -480,6 +525,9 @@ static void bpf_object__elf_finish(struct bpf_object *obj) obj->efile.elf = NULL; } obj->efile.symbols = NULL; + obj->efile.data = NULL; + obj->efile.rodata = NULL; + obj->efile.bss = NULL; zfree(&obj->efile.reloc); obj->efile.nr_reloc = 0; @@ -621,27 +669,182 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) return false; } +static int bpf_object_search_section_size(const struct bpf_object *obj, + const char *name, size_t *d_size) +{ + const GElf_Ehdr *ep = &obj->efile.ehdr; + Elf *elf = obj->efile.elf; + Elf_Scn *scn = NULL; + int idx = 0; + + while ((scn = elf_nextscn(elf, scn)) != NULL) { + const char *sec_name; + Elf_Data *data; + GElf_Shdr sh; + + idx++; + if (gelf_getshdr(scn, &sh) != &sh) { + pr_warning("failed to get section(%d) header from %s\n", + idx, obj->path); + return -EIO; + } + + sec_name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name); + if (!sec_name) { + pr_warning("failed to get section(%d) name from %s\n", + idx, obj->path); + return -EIO; + } + + if (strcmp(name, sec_name)) + continue; + + data = elf_getdata(scn, 0); + if (!data) { + pr_warning("failed to get section(%d) data from %s(%s)\n", + idx, name, obj->path); + return -EIO; + } + + *d_size = data->d_size; + return 0; + } + + return -ENOENT; +} + +int bpf_object__section_size(const struct bpf_object *obj, const char *name, + __u32 *size) +{ + int ret = -ENOENT; + size_t d_size; + + *size = 0; + if (!name) { + return -EINVAL; + } else if (!strcmp(name, ".data")) { + if (obj->efile.data) + *size = obj->efile.data->d_size; + } else if (!strcmp(name, ".bss")) { + if (obj->efile.bss) + *size = obj->efile.bss->d_size; + } else if (!strcmp(name, ".rodata")) { + if (obj->efile.rodata) + *size = obj->efile.rodata->d_size; + } else { + ret = bpf_object_search_section_size(obj, name, &d_size); + if (!ret) + *size = d_size; + } + + return *size ? 0 : ret; +} + +int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, + __u32 *off) +{ + Elf_Data *symbols = obj->efile.symbols; + const char *sname; + size_t si; + + if (!name || !off) + return -EINVAL; + + for (si = 0; si < symbols->d_size / sizeof(GElf_Sym); si++) { + GElf_Sym sym; + + if (!gelf_getsym(symbols, si, &sym)) + continue; + if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL || + GELF_ST_TYPE(sym.st_info) != STT_OBJECT) + continue; + + sname = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name); + if (!sname) { + pr_warning("failed to get sym name string for var %s\n", + name); + return -EIO; + } + if (strcmp(name, sname) == 0) { + *off = sym.st_value; + return 0; + } + } + + return -ENOENT; +} + +static bool bpf_object__has_maps(const struct bpf_object *obj) +{ + return obj->efile.maps_shndx >= 0 || + obj->efile.data_shndx >= 0 || + obj->efile.rodata_shndx >= 0 || + obj->efile.bss_shndx >= 0; +} + +static int +bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map, + enum libbpf_map_type type, Elf_Data *data, + void **data_buff) +{ + struct bpf_map_def *def = &map->def; + char map_name[BPF_OBJ_NAME_LEN]; + + map->libbpf_type = type; + map->offset = ~(typeof(map->offset))0; + snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name, + libbpf_type_to_btf_name[type]); + map->name = strdup(map_name); + if (!map->name) { + pr_warning("failed to alloc map name\n"); + return -ENOMEM; + } + + def->type = BPF_MAP_TYPE_ARRAY; + def->key_size = sizeof(int); + def->value_size = data->d_size; + def->max_entries = 1; + def->map_flags = type == LIBBPF_MAP_RODATA ? + BPF_F_RDONLY_PROG : 0; + if (data_buff) { + *data_buff = malloc(data->d_size); + if (!*data_buff) { + zfree(&map->name); + pr_warning("failed to alloc map content buffer\n"); + return -ENOMEM; + } + memcpy(*data_buff, data->d_buf, data->d_size); + } + + pr_debug("map %ld is \"%s\"\n", map - obj->maps, map->name); + return 0; +} + static int bpf_object__init_maps(struct bpf_object *obj, int flags) { + int i, map_idx, map_def_sz = 0, nr_syms, nr_maps = 0, nr_maps_glob = 0; bool strict = !(flags & MAPS_RELAX_COMPAT); - int i, map_idx, map_def_sz, nr_maps = 0; - Elf_Scn *scn; - Elf_Data *data = NULL; Elf_Data *symbols = obj->efile.symbols; + Elf_Data *data = NULL; + int ret = 0; - if (obj->efile.maps_shndx < 0) - return -EINVAL; if (!symbols) return -EINVAL; + nr_syms = symbols->d_size / sizeof(GElf_Sym); - scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx); - if (scn) - data = elf_getdata(scn, NULL); - if (!scn || !data) { - pr_warning("failed to get Elf_Data from map section %d\n", - obj->efile.maps_shndx); - return -EINVAL; + if (obj->efile.maps_shndx >= 0) { + Elf_Scn *scn = elf_getscn(obj->efile.elf, + obj->efile.maps_shndx); + + if (scn) + data = elf_getdata(scn, NULL); + if (!scn || !data) { + pr_warning("failed to get Elf_Data from map section %d\n", + obj->efile.maps_shndx); + return -EINVAL; + } } /* @@ -651,7 +854,13 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) * * TODO: Detect array of map and report error. */ - for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { + if (obj->efile.data_shndx >= 0) + nr_maps_glob++; + if (obj->efile.rodata_shndx >= 0) + nr_maps_glob++; + if (obj->efile.bss_shndx >= 0) + nr_maps_glob++; + for (i = 0; data && i < nr_syms; i++) { GElf_Sym sym; if (!gelf_getsym(symbols, i, &sym)) @@ -664,19 +873,21 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) /* Alloc obj->maps and fill nr_maps. */ pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path, nr_maps, data->d_size); - - if (!nr_maps) + if (!nr_maps && !nr_maps_glob) return 0; /* Assume equally sized map definitions */ - map_def_sz = data->d_size / nr_maps; - if (!data->d_size || (data->d_size % nr_maps) != 0) { - pr_warning("unable to determine map definition size " - "section %s, %d maps in %zd bytes\n", - obj->path, nr_maps, data->d_size); - return -EINVAL; + if (data) { + map_def_sz = data->d_size / nr_maps; + if (!data->d_size || (data->d_size % nr_maps) != 0) { + pr_warning("unable to determine map definition size " + "section %s, %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); + return -EINVAL; + } } + nr_maps += nr_maps_glob; obj->maps = calloc(nr_maps, sizeof(obj->maps[0])); if (!obj->maps) { pr_warning("alloc maps for object failed\n"); @@ -697,7 +908,7 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) /* * Fill obj->maps using data in "maps" section. */ - for (i = 0, map_idx = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { + for (i = 0, map_idx = 0; data && i < nr_syms; i++) { GElf_Sym sym; const char *map_name; struct bpf_map_def *def; @@ -710,6 +921,8 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) map_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, sym.st_name); + + obj->maps[map_idx].libbpf_type = LIBBPF_MAP_UNSPEC; obj->maps[map_idx].offset = sym.st_value; if (sym.st_value + map_def_sz > data->d_size) { pr_warning("corrupted maps section in %s: last map \"%s\" too small\n", @@ -758,8 +971,27 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) map_idx++; } - qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map); - return 0; + /* + * Populate rest of obj->maps with libbpf internal maps. + */ + if (obj->efile.data_shndx >= 0) + ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], + LIBBPF_MAP_DATA, + obj->efile.data, + &obj->sections.data); + if (!ret && obj->efile.rodata_shndx >= 0) + ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], + LIBBPF_MAP_RODATA, + obj->efile.rodata, + &obj->sections.rodata); + if (!ret && obj->efile.bss_shndx >= 0) + ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], + LIBBPF_MAP_BSS, + obj->efile.bss, NULL); + if (!ret) + qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), + compare_bpf_map); + return ret; } static bool section_have_execinstr(struct bpf_object *obj, int idx) @@ -785,6 +1017,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) Elf *elf = obj->efile.elf; GElf_Ehdr *ep = &obj->efile.ehdr; Elf_Data *btf_ext_data = NULL; + Elf_Data *btf_data = NULL; Elf_Scn *scn = NULL; int idx = 0, err = 0; @@ -828,32 +1061,18 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) (int)sh.sh_link, (unsigned long)sh.sh_flags, (int)sh.sh_type); - if (strcmp(name, "license") == 0) + if (strcmp(name, "license") == 0) { err = bpf_object__init_license(obj, data->d_buf, data->d_size); - else if (strcmp(name, "version") == 0) + } else if (strcmp(name, "version") == 0) { err = bpf_object__init_kversion(obj, data->d_buf, data->d_size); - else if (strcmp(name, "maps") == 0) + } else if (strcmp(name, "maps") == 0) { obj->efile.maps_shndx = idx; - else if (strcmp(name, BTF_ELF_SEC) == 0) { - obj->btf = btf__new(data->d_buf, data->d_size); - if (IS_ERR(obj->btf)) { - pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", - BTF_ELF_SEC, PTR_ERR(obj->btf)); - obj->btf = NULL; - continue; - } - err = btf__load(obj->btf); - if (err) { - pr_warning("Error loading %s into kernel: %d. Ignored and continue.\n", - BTF_ELF_SEC, err); - btf__free(obj->btf); - obj->btf = NULL; - err = 0; - } + } else if (strcmp(name, BTF_ELF_SEC) == 0) { + btf_data = data; } else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) { btf_ext_data = data; } else if (sh.sh_type == SHT_SYMTAB) { @@ -865,20 +1084,28 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) obj->efile.symbols = data; obj->efile.strtabidx = sh.sh_link; } - } else if ((sh.sh_type == SHT_PROGBITS) && - (sh.sh_flags & SHF_EXECINSTR) && - (data->d_size > 0)) { - if (strcmp(name, ".text") == 0) - obj->efile.text_shndx = idx; - err = bpf_object__add_program(obj, data->d_buf, - data->d_size, name, idx); - if (err) { - char errmsg[STRERR_BUFSIZE]; - char *cp = libbpf_strerror_r(-err, errmsg, - sizeof(errmsg)); - - pr_warning("failed to alloc program %s (%s): %s", - name, obj->path, cp); + } else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) { + if (sh.sh_flags & SHF_EXECINSTR) { + if (strcmp(name, ".text") == 0) + obj->efile.text_shndx = idx; + err = bpf_object__add_program(obj, data->d_buf, + data->d_size, name, idx); + if (err) { + char errmsg[STRERR_BUFSIZE]; + char *cp = libbpf_strerror_r(-err, errmsg, + sizeof(errmsg)); + + pr_warning("failed to alloc program %s (%s): %s", + name, obj->path, cp); + } + } else if (strcmp(name, ".data") == 0) { + obj->efile.data = data; + obj->efile.data_shndx = idx; + } else if (strcmp(name, ".rodata") == 0) { + obj->efile.rodata = data; + obj->efile.rodata_shndx = idx; + } else { + pr_debug("skip section(%d) %s\n", idx, name); } } else if (sh.sh_type == SHT_REL) { void *reloc = obj->efile.reloc; @@ -906,6 +1133,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) obj->efile.reloc[n].shdr = sh; obj->efile.reloc[n].data = data; } + } else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) { + obj->efile.bss = data; + obj->efile.bss_shndx = idx; } else { pr_debug("skip section(%d) %s\n", idx, name); } @@ -917,6 +1147,25 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) pr_warning("Corrupted ELF file: index of strtab invalid\n"); return LIBBPF_ERRNO__FORMAT; } + if (btf_data) { + obj->btf = btf__new(btf_data->d_buf, btf_data->d_size); + if (IS_ERR(obj->btf)) { + pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", + BTF_ELF_SEC, PTR_ERR(obj->btf)); + obj->btf = NULL; + } else { + err = btf__finalize_data(obj, obj->btf); + if (!err) + err = btf__load(obj->btf); + if (err) { + pr_warning("Error finalizing and loading %s into kernel: %d. Ignored and continue.\n", + BTF_ELF_SEC, err); + btf__free(obj->btf); + obj->btf = NULL; + err = 0; + } + } + } if (btf_ext_data) { if (!obj->btf) { pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n", @@ -932,7 +1181,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) } } } - if (obj->efile.maps_shndx >= 0) { + if (bpf_object__has_maps(obj)) { err = bpf_object__init_maps(obj, flags); if (err) goto out; @@ -968,13 +1217,46 @@ bpf_object__find_program_by_title(struct bpf_object *obj, const char *title) return NULL; } +static bool bpf_object__shndx_is_data(const struct bpf_object *obj, + int shndx) +{ + return shndx == obj->efile.data_shndx || + shndx == obj->efile.bss_shndx || + shndx == obj->efile.rodata_shndx; +} + +static bool bpf_object__shndx_is_maps(const struct bpf_object *obj, + int shndx) +{ + return shndx == obj->efile.maps_shndx; +} + +static bool bpf_object__relo_in_known_section(const struct bpf_object *obj, + int shndx) +{ + return shndx == obj->efile.text_shndx || + bpf_object__shndx_is_maps(obj, shndx) || + bpf_object__shndx_is_data(obj, shndx); +} + +static enum libbpf_map_type +bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx) +{ + if (shndx == obj->efile.data_shndx) + return LIBBPF_MAP_DATA; + else if (shndx == obj->efile.bss_shndx) + return LIBBPF_MAP_BSS; + else if (shndx == obj->efile.rodata_shndx) + return LIBBPF_MAP_RODATA; + else + return LIBBPF_MAP_UNSPEC; +} + static int bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, Elf_Data *data, struct bpf_object *obj) { Elf_Data *symbols = obj->efile.symbols; - int text_shndx = obj->efile.text_shndx; - int maps_shndx = obj->efile.maps_shndx; struct bpf_map *maps = obj->maps; size_t nr_maps = obj->nr_maps; int i, nrels; @@ -994,7 +1276,10 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, GElf_Sym sym; GElf_Rel rel; unsigned int insn_idx; + unsigned int shdr_idx; struct bpf_insn *insns = prog->insns; + enum libbpf_map_type type; + const char *name; size_t map_idx; if (!gelf_getrel(data, i, &rel)) { @@ -1009,13 +1294,18 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, GELF_R_SYM(rel.r_info)); return -LIBBPF_ERRNO__FORMAT; } - pr_debug("relo for %lld value %lld name %d\n", + + name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name) ? : "<?>"; + + pr_debug("relo for %lld value %lld name %d (\'%s\')\n", (long long) (rel.r_info >> 32), - (long long) sym.st_value, sym.st_name); + (long long) sym.st_value, sym.st_name, name); - if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) { - pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n", - prog->section_name, sym.st_shndx); + shdr_idx = sym.st_shndx; + if (!bpf_object__relo_in_known_section(obj, shdr_idx)) { + pr_warning("Program '%s' contains unrecognized relo data pointing to section %u\n", + prog->section_name, shdr_idx); return -LIBBPF_ERRNO__RELOC; } @@ -1040,24 +1330,39 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, return -LIBBPF_ERRNO__RELOC; } - /* TODO: 'maps' is sorted. We can use bsearch to make it faster. */ - for (map_idx = 0; map_idx < nr_maps; map_idx++) { - if (maps[map_idx].offset == sym.st_value) { - pr_debug("relocation: find map %zd (%s) for insn %u\n", - map_idx, maps[map_idx].name, insn_idx); - break; + if (bpf_object__shndx_is_maps(obj, shdr_idx) || + bpf_object__shndx_is_data(obj, shdr_idx)) { + type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx); + if (type != LIBBPF_MAP_UNSPEC && + GELF_ST_BIND(sym.st_info) == STB_GLOBAL) { + pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n", + name, insn_idx, insns[insn_idx].code); + return -LIBBPF_ERRNO__RELOC; } - } - if (map_idx >= nr_maps) { - pr_warning("bpf relocation: map_idx %d large than %d\n", - (int)map_idx, (int)nr_maps - 1); - return -LIBBPF_ERRNO__RELOC; - } + for (map_idx = 0; map_idx < nr_maps; map_idx++) { + if (maps[map_idx].libbpf_type != type) + continue; + if (type != LIBBPF_MAP_UNSPEC || + (type == LIBBPF_MAP_UNSPEC && + maps[map_idx].offset == sym.st_value)) { + pr_debug("relocation: find map %zd (%s) for insn %u\n", + map_idx, maps[map_idx].name, insn_idx); + break; + } + } + + if (map_idx >= nr_maps) { + pr_warning("bpf relocation: map_idx %d large than %d\n", + (int)map_idx, (int)nr_maps - 1); + return -LIBBPF_ERRNO__RELOC; + } - prog->reloc_desc[i].type = RELO_LD64; - prog->reloc_desc[i].insn_idx = insn_idx; - prog->reloc_desc[i].map_idx = map_idx; + prog->reloc_desc[i].type = type != LIBBPF_MAP_UNSPEC ? + RELO_DATA : RELO_LD64; + prog->reloc_desc[i].insn_idx = insn_idx; + prog->reloc_desc[i].map_idx = map_idx; + } } return 0; } @@ -1065,18 +1370,27 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) { struct bpf_map_def *def = &map->def; - __u32 key_type_id, value_type_id; + __u32 key_type_id = 0, value_type_id = 0; int ret; - ret = btf__get_map_kv_tids(btf, map->name, def->key_size, - def->value_size, &key_type_id, - &value_type_id); - if (ret) + if (!bpf_map__is_internal(map)) { + ret = btf__get_map_kv_tids(btf, map->name, def->key_size, + def->value_size, &key_type_id, + &value_type_id); + } else { + /* + * LLVM annotates global data differently in BTF, that is, + * only as '.data', '.bss' or '.rodata'. + */ + ret = btf__find_by_name(btf, + libbpf_type_to_btf_name[map->libbpf_type]); + } + if (ret < 0) return ret; map->btf_key_type_id = key_type_id; - map->btf_value_type_id = value_type_id; - + map->btf_value_type_id = bpf_map__is_internal(map) ? + ret : value_type_id; return 0; } @@ -1188,6 +1502,34 @@ bpf_object__probe_caps(struct bpf_object *obj) } static int +bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + int err, zero = 0; + __u8 *data; + + /* Nothing to do here since kernel already zero-initializes .bss map. */ + if (map->libbpf_type == LIBBPF_MAP_BSS) + return 0; + + data = map->libbpf_type == LIBBPF_MAP_DATA ? + obj->sections.data : obj->sections.rodata; + + err = bpf_map_update_elem(map->fd, &zero, data, 0); + /* Freeze .rodata map as read-only from syscall side. */ + if (!err && map->libbpf_type == LIBBPF_MAP_RODATA) { + err = bpf_map_freeze(map->fd); + if (err) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warning("Error freezing map(%s) as read-only: %s\n", + map->name, cp); + err = 0; + } + } + return err; +} + +static int bpf_object__create_maps(struct bpf_object *obj) { struct bpf_create_map_attr create_attr = {}; @@ -1244,6 +1586,7 @@ bpf_object__create_maps(struct bpf_object *obj) size_t j; err = *pfd; +err_out: cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); pr_warning("failed to create map (name: '%s'): %s\n", map->name, cp); @@ -1251,6 +1594,15 @@ bpf_object__create_maps(struct bpf_object *obj) zclose(obj->maps[j].fd); return err; } + + if (bpf_map__is_internal(map)) { + err = bpf_object__populate_internal_map(obj, map); + if (err < 0) { + zclose(*pfd); + goto err_out; + } + } + pr_debug("create map %s: fd=%d\n", map->name, *pfd); } @@ -1405,21 +1757,29 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) return 0; for (i = 0; i < prog->nr_reloc; i++) { - if (prog->reloc_desc[i].type == RELO_LD64) { + if (prog->reloc_desc[i].type == RELO_LD64 || + prog->reloc_desc[i].type == RELO_DATA) { + bool relo_data = prog->reloc_desc[i].type == RELO_DATA; struct bpf_insn *insns = prog->insns; int insn_idx, map_idx; insn_idx = prog->reloc_desc[i].insn_idx; map_idx = prog->reloc_desc[i].map_idx; - if (insn_idx >= (int)prog->insns_cnt) { + if (insn_idx + 1 >= (int)prog->insns_cnt) { pr_warning("relocation out of range: '%s'\n", prog->section_name); return -LIBBPF_ERRNO__RELOC; } - insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; + + if (!relo_data) { + insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; + } else { + insns[insn_idx].src_reg = BPF_PSEUDO_MAP_VALUE; + insns[insn_idx + 1].imm = insns[insn_idx].imm; + } insns[insn_idx].imm = obj->maps[map_idx].fd; - } else { + } else if (prog->reloc_desc[i].type == RELO_CALL) { err = bpf_program__reloc_text(prog, obj, &prog->reloc_desc[i]); if (err) @@ -1494,6 +1854,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, { struct bpf_load_program_attr load_attr; char *cp, errmsg[STRERR_BUFSIZE]; + int log_buf_size = BPF_LOG_BUF_SIZE; char *log_buf; int ret; @@ -1514,21 +1875,30 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.line_info = prog->line_info; load_attr.line_info_rec_size = prog->line_info_rec_size; load_attr.line_info_cnt = prog->line_info_cnt; + load_attr.log_level = prog->log_level; if (!load_attr.insns || !load_attr.insns_cnt) return -EINVAL; - log_buf = malloc(BPF_LOG_BUF_SIZE); +retry_load: + log_buf = malloc(log_buf_size); if (!log_buf) pr_warning("Alloc log buffer for bpf loader error, continue without log\n"); - ret = bpf_load_program_xattr(&load_attr, log_buf, BPF_LOG_BUF_SIZE); + ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size); if (ret >= 0) { + if (load_attr.log_level) + pr_debug("verifier log:\n%s", log_buf); *pfd = ret; ret = 0; goto out; } + if (errno == ENOSPC) { + log_buf_size <<= 1; + free(log_buf); + goto retry_load; + } ret = -LIBBPF_ERRNO__LOAD; cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); pr_warning("load bpf program failed: %s\n", cp); @@ -2303,6 +2673,9 @@ void bpf_object__close(struct bpf_object *obj) obj->maps[i].priv = NULL; obj->maps[i].clear_priv = NULL; } + + zfree(&obj->sections.rodata); + zfree(&obj->sections.data); zfree(&obj->maps); obj->nr_maps = 0; @@ -2780,6 +3153,11 @@ bool bpf_map__is_offload_neutral(struct bpf_map *map) return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; } +bool bpf_map__is_internal(struct bpf_map *map) +{ + return map->libbpf_type != LIBBPF_MAP_UNSPEC; +} + void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex) { map->map_ifindex = ifindex; @@ -2938,6 +3316,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, bpf_program__set_expected_attach_type(prog, expected_attach_type); + prog->log_level = attr->log_level; if (!first_prog) first_prog = prog; } diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index c70785cc8ef5..c5ff00515ce7 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -75,6 +75,10 @@ struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr, LIBBPF_API struct bpf_object *bpf_object__open_buffer(void *obj_buf, size_t obj_buf_sz, const char *name); +int bpf_object__section_size(const struct bpf_object *obj, const char *name, + __u32 *size); +int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, + __u32 *off); LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path); LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj, const char *path); @@ -301,6 +305,7 @@ LIBBPF_API void *bpf_map__priv(struct bpf_map *map); LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries); LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map); +LIBBPF_API bool bpf_map__is_internal(struct bpf_map *map); LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path); LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path); @@ -314,6 +319,7 @@ struct bpf_prog_load_attr { enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; int ifindex; + int log_level; }; LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index f3ce50500cf2..673001787cba 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -157,3 +157,10 @@ LIBBPF_0.0.2 { bpf_program__bpil_addr_to_offs; bpf_program__bpil_offs_to_addr; } LIBBPF_0.0.1; + +LIBBPF_0.0.3 { + global: + bpf_map__is_internal; + bpf_map_freeze; + btf__finalize_data; +} LIBBPF_0.0.2; diff --git a/tools/lib/bpf/libbpf.pc.template b/tools/lib/bpf/libbpf.pc.template new file mode 100644 index 000000000000..ac17fcef2108 --- /dev/null +++ b/tools/lib/bpf/libbpf.pc.template @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +prefix=@PREFIX@ +libdir=@LIBDIR@ +includedir=${prefix}/include + +Name: libbpf +Description: BPF library +Version: @VERSION@ +Libs: -L${libdir} -lbpf +Requires.private: libelf +Cflags: -I${includedir} diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 8d0078b65486..557ef8d1250d 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -259,7 +259,8 @@ out_umem_alloc: static int xsk_load_xdp_prog(struct xsk_socket *xsk) { - char bpf_log_buf[BPF_LOG_BUF_SIZE]; + static const int log_buf_size = 16 * 1024; + char log_buf[log_buf_size]; int err, prog_fd; /* This is the C-program: @@ -308,10 +309,10 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); prog_fd = bpf_load_program(BPF_PROG_TYPE_XDP, prog, insns_cnt, - "LGPL-2.1 or BSD-2-Clause", 0, bpf_log_buf, - BPF_LOG_BUF_SIZE); + "LGPL-2.1 or BSD-2-Clause", 0, log_buf, + log_buf_size); if (prog_fd < 0) { - pr_warning("BPF log buffer:\n%s", bpf_log_buf); + pr_warning("BPF log buffer:\n%s", log_buf); return prog_fd; } diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index c9d038f91af6..53f8be0f4a1f 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -25,14 +25,17 @@ LIBSUBCMD = $(LIBSUBCMD_OUTPUT)libsubcmd.a OBJTOOL := $(OUTPUT)objtool OBJTOOL_IN := $(OBJTOOL)-in.o +LIBELF_FLAGS := $(shell pkg-config libelf --cflags 2>/dev/null) +LIBELF_LIBS := $(shell pkg-config libelf --libs 2>/dev/null || echo -lelf) + all: $(OBJTOOL) INCLUDES := -I$(srctree)/tools/include \ -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \ -I$(srctree)/tools/objtool/arch/$(ARCH)/include WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed -CFLAGS += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) -LDFLAGS += -lelf $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS) +CFLAGS += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) $(LIBELF_FLAGS) +LDFLAGS += $(LIBELF_LIBS) $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS) # Allow old libelf to be used: elfshdr := $(shell echo '$(pound)include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | grep elf_getshdr) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 5dde107083c6..479196aeb409 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -165,6 +165,7 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func, "fortify_panic", "usercopy_abort", "machine_real_restart", + "rewind_stack_do_exit", }; if (func->bind == STB_WEAK) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 01f7555fd933..e8c9f77e9010 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -481,8 +481,8 @@ $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_t mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh -$(mmap_flags_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl) - $(Q)$(SHELL) '$(mmap_flags_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@ +$(mmap_flags_array): $(linux_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl) + $(Q)$(SHELL) '$(mmap_flags_tbl)' $(linux_uapi_dir) $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@ mount_flags_array := $(beauty_outdir)/mount_flags_array.c mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 2ae92fddb6d5..92ee0b4378d4 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -345,6 +345,10 @@ 334 common rseq __x64_sys_rseq # don't use numbers 387 through 423, add new calls after the last # 'common' entry +424 common pidfd_send_signal __x64_sys_pidfd_send_signal +425 common io_uring_setup __x64_sys_io_uring_setup +426 common io_uring_enter __x64_sys_io_uring_enter +427 common io_uring_register __x64_sys_io_uring_register # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 7b55613924de..c68ee06cae63 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -103,7 +103,7 @@ done # diff with extra ignore lines check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"' check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"' -check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"' +check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"' check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"' # diff non-symmetric files diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index e38518cdcbc3..74ef92f1d19a 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -107,6 +107,7 @@ import os from PySide.QtCore import * from PySide.QtGui import * from PySide.QtSql import * +pyside_version_1 = True from decimal import * from ctypes import * from multiprocessing import Process, Array, Value, Event @@ -1526,6 +1527,19 @@ def BranchDataPrep(query): " (" + dsoname(query.value(15)) + ")") return data +def BranchDataPrepWA(query): + data = [] + data.append(query.value(0)) + # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string + data.append("{:>19}".format(query.value(1))) + for i in xrange(2, 8): + data.append(query.value(i)) + data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) + + " (" + dsoname(query.value(11)) + ")" + " -> " + + tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) + + " (" + dsoname(query.value(15)) + ")") + return data + # Branch data model class BranchModel(TreeModel): @@ -1553,7 +1567,11 @@ class BranchModel(TreeModel): " AND evsel_id = " + str(self.event_id) + " ORDER BY samples.id" " LIMIT " + str(glb_chunk_sz)) - self.fetcher = SQLFetcher(glb, sql, BranchDataPrep, self.AddSample) + if pyside_version_1 and sys.version_info[0] == 3: + prep = BranchDataPrepWA + else: + prep = BranchDataPrep + self.fetcher = SQLFetcher(glb, sql, prep, self.AddSample) self.fetcher.done.connect(self.Update) self.fetcher.Fetch(glb_chunk_sz) @@ -2079,14 +2097,6 @@ def IsSelectable(db, table, sql = ""): return False return True -# SQL data preparation - -def SQLTableDataPrep(query, count): - data = [] - for i in xrange(count): - data.append(query.value(i)) - return data - # SQL table data model item class SQLTableItem(): @@ -2110,7 +2120,7 @@ class SQLTableModel(TableModel): self.more = True self.populated = 0 self.column_headers = column_headers - self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): SQLTableDataPrep(x, y), self.AddSample) + self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): self.SQLTableDataPrep(x, y), self.AddSample) self.fetcher.done.connect(self.Update) self.fetcher.Fetch(glb_chunk_sz) @@ -2154,6 +2164,12 @@ class SQLTableModel(TableModel): def columnHeader(self, column): return self.column_headers[column] + def SQLTableDataPrep(self, query, count): + data = [] + for i in xrange(count): + data.append(query.value(i)) + return data + # SQL automatic table data model class SQLAutoTableModel(SQLTableModel): @@ -2182,8 +2198,32 @@ class SQLAutoTableModel(SQLTableModel): QueryExec(query, "SELECT column_name FROM information_schema.columns WHERE table_schema = '" + schema + "' and table_name = '" + select_table_name + "'") while query.next(): column_headers.append(query.value(0)) + if pyside_version_1 and sys.version_info[0] == 3: + if table_name == "samples_view": + self.SQLTableDataPrep = self.samples_view_DataPrep + if table_name == "samples": + self.SQLTableDataPrep = self.samples_DataPrep super(SQLAutoTableModel, self).__init__(glb, sql, column_headers, parent) + def samples_view_DataPrep(self, query, count): + data = [] + data.append(query.value(0)) + # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string + data.append("{:>19}".format(query.value(1))) + for i in xrange(2, count): + data.append(query.value(i)) + return data + + def samples_DataPrep(self, query, count): + data = [] + for i in xrange(9): + data.append(query.value(i)) + # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string + data.append("{:>19}".format(query.value(9))) + for i in xrange(10, count): + data.append(query.value(i)) + return data + # Base class for custom ResizeColumnsToContents class ResizeColumnsToContentsBase(QObject): @@ -2868,9 +2908,13 @@ class LibXED(): ok = self.xed_format_context(2, inst.xedp, inst.bufferp, sizeof(inst.buffer), ip, 0, 0) if not ok: return 0, "" + if sys.version_info[0] == 2: + result = inst.buffer.value + else: + result = inst.buffer.value.decode() # Return instruction length and the disassembled instruction text # For now, assume the length is in byte 166 - return inst.xedd[166], inst.buffer.value + return inst.xedd[166], result def TryOpen(file_name): try: @@ -2886,9 +2930,14 @@ def Is64Bit(f): header = f.read(7) f.seek(pos) magic = header[0:4] - eclass = ord(header[4]) - encoding = ord(header[5]) - version = ord(header[6]) + if sys.version_info[0] == 2: + eclass = ord(header[4]) + encoding = ord(header[5]) + version = ord(header[6]) + else: + eclass = header[4] + encoding = header[5] + version = header[6] if magic == chr(127) + "ELF" and eclass > 0 and eclass < 3 and encoding > 0 and encoding < 3 and version == 1: result = True if eclass == 2 else False return result diff --git a/tools/perf/trace/beauty/mmap_flags.sh b/tools/perf/trace/beauty/mmap_flags.sh index 32bac9c0d694..5f5eefcb3c74 100755 --- a/tools/perf/trace/beauty/mmap_flags.sh +++ b/tools/perf/trace/beauty/mmap_flags.sh @@ -1,15 +1,18 @@ #!/bin/sh # SPDX-License-Identifier: LGPL-2.1 -if [ $# -ne 2 ] ; then +if [ $# -ne 3 ] ; then [ $# -eq 1 ] && hostarch=$1 || hostarch=`uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/` + linux_header_dir=tools/include/uapi/linux header_dir=tools/include/uapi/asm-generic arch_header_dir=tools/arch/${hostarch}/include/uapi/asm else - header_dir=$1 - arch_header_dir=$2 + linux_header_dir=$1 + header_dir=$2 + arch_header_dir=$3 fi +linux_mman=${linux_header_dir}/mman.h arch_mman=${arch_header_dir}/mman.h # those in egrep -vw are flags, we want just the bits @@ -20,6 +23,11 @@ egrep -q $regex ${arch_mman} && \ (egrep $regex ${arch_mman} | \ sed -r "s/$regex/\2 \1/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n") +egrep -q $regex ${linux_mman} && \ +(egrep $regex ${linux_mman} | \ + egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \ + sed -r "s/$regex/\2 \1/g" | \ + xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n") ([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman}) && (egrep $regex ${header_dir}/mman-common.h | \ egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \ diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index ba4c623cd8de..39fe21e1cf93 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -387,6 +387,7 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder, break; case OCSD_INSTR_ISB: case OCSD_INSTR_DSB_DMB: + case OCSD_INSTR_WFI_WFE: case OCSD_INSTR_OTHER: default: packet->last_instr_taken_branch = false; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index ec78e93085de..6689378ee577 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -231,35 +231,6 @@ void perf_evlist__set_leader(struct perf_evlist *evlist) } } -void perf_event_attr__set_max_precise_ip(struct perf_event_attr *pattr) -{ - struct perf_event_attr attr = { - .type = PERF_TYPE_HARDWARE, - .config = PERF_COUNT_HW_CPU_CYCLES, - .exclude_kernel = 1, - .precise_ip = 3, - }; - - event_attr_init(&attr); - - /* - * Unnamed union member, not supported as struct member named - * initializer in older compilers such as gcc 4.4.7 - */ - attr.sample_period = 1; - - while (attr.precise_ip != 0) { - int fd = sys_perf_event_open(&attr, 0, -1, -1, 0); - if (fd != -1) { - close(fd); - break; - } - --attr.precise_ip; - } - - pattr->precise_ip = attr.precise_ip; -} - int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise) { struct perf_evsel *evsel = perf_evsel__new_cycles(precise); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index dcb68f34d2cd..6a94785b9100 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -315,8 +315,6 @@ void perf_evlist__to_front(struct perf_evlist *evlist, void perf_evlist__set_tracking_event(struct perf_evlist *evlist, struct perf_evsel *tracking_evsel); -void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr); - struct perf_evsel * perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 7835e05f0c0a..66d066f18b5b 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -295,7 +295,6 @@ struct perf_evsel *perf_evsel__new_cycles(bool precise) if (!precise) goto new_event; - perf_event_attr__set_max_precise_ip(&attr); /* * Now let the usual logic to set up the perf_event_attr defaults * to kick in when we return and before perf_evsel__open() is called. @@ -305,6 +304,8 @@ new_event: if (evsel == NULL) goto out; + evsel->precise_max = true; + /* use asprintf() because free(evsel) assumes name is allocated */ if (asprintf(&evsel->name, "cycles%s%s%.*s", (attr.precise_ip || attr.exclude_kernel) ? ":" : "", @@ -1083,7 +1084,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, } if (evsel->precise_max) - perf_event_attr__set_max_precise_ip(attr); + attr->precise_ip = 3; if (opts->all_user) { attr->exclude_kernel = 1; @@ -1749,6 +1750,59 @@ static bool ignore_missing_thread(struct perf_evsel *evsel, return true; } +static void display_attr(struct perf_event_attr *attr) +{ + if (verbose >= 2) { + fprintf(stderr, "%.60s\n", graph_dotted_line); + fprintf(stderr, "perf_event_attr:\n"); + perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL); + fprintf(stderr, "%.60s\n", graph_dotted_line); + } +} + +static int perf_event_open(struct perf_evsel *evsel, + pid_t pid, int cpu, int group_fd, + unsigned long flags) +{ + int precise_ip = evsel->attr.precise_ip; + int fd; + + while (1) { + pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", + pid, cpu, group_fd, flags); + + fd = sys_perf_event_open(&evsel->attr, pid, cpu, group_fd, flags); + if (fd >= 0) + break; + + /* + * Do quick precise_ip fallback if: + * - there is precise_ip set in perf_event_attr + * - maximum precise is requested + * - sys_perf_event_open failed with ENOTSUP error, + * which is associated with wrong precise_ip + */ + if (!precise_ip || !evsel->precise_max || (errno != ENOTSUP)) + break; + + /* + * We tried all the precise_ip values, and it's + * still failing, so leave it to standard fallback. + */ + if (!evsel->attr.precise_ip) { + evsel->attr.precise_ip = precise_ip; + break; + } + + pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP); + evsel->attr.precise_ip--; + pr_debug2("decreasing precise_ip by one (%d)\n", evsel->attr.precise_ip); + display_attr(&evsel->attr); + } + + return fd; +} + int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, struct thread_map *threads) { @@ -1824,12 +1878,7 @@ retry_sample_id: if (perf_missing_features.sample_id_all) evsel->attr.sample_id_all = 0; - if (verbose >= 2) { - fprintf(stderr, "%.60s\n", graph_dotted_line); - fprintf(stderr, "perf_event_attr:\n"); - perf_event_attr__fprintf(stderr, &evsel->attr, __open_attr__fprintf, NULL); - fprintf(stderr, "%.60s\n", graph_dotted_line); - } + display_attr(&evsel->attr); for (cpu = 0; cpu < cpus->nr; cpu++) { @@ -1841,13 +1890,10 @@ retry_sample_id: group_fd = get_group_fd(evsel, cpu, thread); retry_open: - pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", - pid, cpus->map[cpu], group_fd, flags); - test_attr__ready(); - fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu], - group_fd, flags); + fd = perf_event_open(evsel, pid, cpus->map[cpu], + group_fd, flags); FD(evsel, cpu, thread) = fd; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 6e03db142091..872fab163585 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -251,19 +251,15 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) if (!(decoder->tsc_ctc_ratio_n % decoder->tsc_ctc_ratio_d)) decoder->tsc_ctc_mult = decoder->tsc_ctc_ratio_n / decoder->tsc_ctc_ratio_d; - - /* - * Allow for timestamps appearing to backwards because a TSC - * packet has slipped past a MTC packet, so allow 2 MTC ticks - * or ... - */ - decoder->tsc_slip = multdiv(2 << decoder->mtc_shift, - decoder->tsc_ctc_ratio_n, - decoder->tsc_ctc_ratio_d); } - /* ... or 0x100 paranoia */ - if (decoder->tsc_slip < 0x100) - decoder->tsc_slip = 0x100; + + /* + * A TSC packet can slip past MTC packets so that the timestamp appears + * to go backwards. One estimate is that can be up to about 40 CPU + * cycles, which is certainly less than 0x1000 TSC ticks, but accept + * slippage an order of magnitude more to be on the safe side. + */ + decoder->tsc_slip = 0x10000; intel_pt_log("timestamp: mtc_shift %u\n", decoder->mtc_shift); intel_pt_log("timestamp: tsc_ctc_ratio_n %u\n", decoder->tsc_ctc_ratio_n); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 61959aba7e27..3c520baa198c 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1421,6 +1421,20 @@ static void machine__set_kernel_mmap(struct machine *machine, machine->vmlinux_map->end = ~0ULL; } +static void machine__update_kernel_mmap(struct machine *machine, + u64 start, u64 end) +{ + struct map *map = machine__kernel_map(machine); + + map__get(map); + map_groups__remove(&machine->kmaps, map); + + machine__set_kernel_mmap(machine, start, end); + + map_groups__insert(&machine->kmaps, map); + map__put(map); +} + int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); @@ -1453,17 +1467,11 @@ int machine__create_kernel_maps(struct machine *machine) goto out_put; } - /* we have a real start address now, so re-order the kmaps */ - map = machine__kernel_map(machine); - - map__get(map); - map_groups__remove(&machine->kmaps, map); - - /* assume it's the last in the kmaps */ - machine__set_kernel_mmap(machine, addr, ~0ULL); - - map_groups__insert(&machine->kmaps, map); - map__put(map); + /* + * we have a real start address now, so re-order the kmaps + * assume it's the last in the kmaps + */ + machine__update_kernel_mmap(machine, addr, ~0ULL); } if (machine__create_extra_kernel_maps(machine, kernel)) @@ -1599,7 +1607,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, if (strstr(kernel->long_name, "vmlinux")) dso__set_short_name(kernel, "[kernel.vmlinux]", false); - machine__set_kernel_mmap(machine, event->mmap.start, + machine__update_kernel_mmap(machine, event->mmap.start, event->mmap.start + event->mmap.len); /* diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 6199a3174ab9..e0429f4ef335 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -732,10 +732,20 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) if (!is_arm_pmu_core(name)) { pname = pe->pmu ? pe->pmu : "cpu"; + + /* + * uncore alias may be from different PMU + * with common prefix + */ + if (pmu_is_uncore(name) && + !strncmp(pname, name, strlen(pname))) + goto new_alias; + if (strcmp(pname, name)) continue; } +new_alias: /* need type casts to override 'const' */ __perf_pmu__new_alias(head, NULL, (char *)pe->name, (char *)pe->desc, (char *)pe->event, diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index c3fad065c89c..c7727be9719f 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -44,6 +44,7 @@ #include <cpuid.h> #include <linux/capability.h> #include <errno.h> +#include <math.h> char *proc_stat = "/proc/stat"; FILE *outf; @@ -63,7 +64,6 @@ unsigned int dump_only; unsigned int do_snb_cstates; unsigned int do_knl_cstates; unsigned int do_slm_cstates; -unsigned int do_cnl_cstates; unsigned int use_c1_residency_msr; unsigned int has_aperf; unsigned int has_epb; @@ -141,9 +141,21 @@ unsigned int first_counter_read = 1; #define RAPL_CORES_ENERGY_STATUS (1 << 9) /* 0x639 MSR_PP0_ENERGY_STATUS */ +#define RAPL_PER_CORE_ENERGY (1 << 10) + /* Indicates cores energy collection is per-core, + * not per-package. */ +#define RAPL_AMD_F17H (1 << 11) + /* 0xc0010299 MSR_RAPL_PWR_UNIT */ + /* 0xc001029a MSR_CORE_ENERGY_STAT */ + /* 0xc001029b MSR_PKG_ENERGY_STAT */ #define RAPL_CORES (RAPL_CORES_ENERGY_STATUS | RAPL_CORES_POWER_LIMIT) #define TJMAX_DEFAULT 100 +/* MSRs that are not yet in the kernel-provided header. */ +#define MSR_RAPL_PWR_UNIT 0xc0010299 +#define MSR_CORE_ENERGY_STAT 0xc001029a +#define MSR_PKG_ENERGY_STAT 0xc001029b + #define MAX(a, b) ((a) > (b) ? (a) : (b)) /* @@ -187,6 +199,7 @@ struct core_data { unsigned long long c7; unsigned long long mc6_us; /* duplicate as per-core for now, even though per module */ unsigned int core_temp_c; + unsigned int core_energy; /* MSR_CORE_ENERGY_STAT */ unsigned int core_id; unsigned long long counter[MAX_ADDED_COUNTERS]; } *core_even, *core_odd; @@ -273,6 +286,7 @@ struct system_summary { struct cpu_topology { int physical_package_id; + int die_id; int logical_cpu_id; int physical_node_id; int logical_node_id; /* 0-based count within the package */ @@ -283,6 +297,7 @@ struct cpu_topology { struct topo_params { int num_packages; + int num_die; int num_cpus; int num_cores; int max_cpu_num; @@ -314,9 +329,8 @@ int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg int retval, pkg_no, core_no, thread_no, node_no; for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) { - for (core_no = 0; core_no < topo.cores_per_node; ++core_no) { - for (node_no = 0; node_no < topo.nodes_per_pkg; - node_no++) { + for (node_no = 0; node_no < topo.nodes_per_pkg; node_no++) { + for (core_no = 0; core_no < topo.cores_per_node; ++core_no) { for (thread_no = 0; thread_no < topo.threads_per_core; ++thread_no) { struct thread_data *t; @@ -442,6 +456,7 @@ struct msr_counter bic[] = { { 0x0, "CPU" }, { 0x0, "APIC" }, { 0x0, "X2APIC" }, + { 0x0, "Die" }, }; #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) @@ -495,6 +510,7 @@ struct msr_counter bic[] = { #define BIC_CPU (1ULL << 47) #define BIC_APIC (1ULL << 48) #define BIC_X2APIC (1ULL << 49) +#define BIC_Die (1ULL << 50) #define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) @@ -621,6 +637,8 @@ void print_header(char *delim) outp += sprintf(outp, "%sTime_Of_Day_Seconds", (printed++ ? delim : "")); if (DO_BIC(BIC_Package)) outp += sprintf(outp, "%sPackage", (printed++ ? delim : "")); + if (DO_BIC(BIC_Die)) + outp += sprintf(outp, "%sDie", (printed++ ? delim : "")); if (DO_BIC(BIC_Node)) outp += sprintf(outp, "%sNode", (printed++ ? delim : "")); if (DO_BIC(BIC_Core)) @@ -667,7 +685,7 @@ void print_header(char *delim) if (DO_BIC(BIC_CPU_c1)) outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : "")); - if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) + if (DO_BIC(BIC_CPU_c3)) outp += sprintf(outp, "%sCPU%%c3", (printed++ ? delim : "")); if (DO_BIC(BIC_CPU_c6)) outp += sprintf(outp, "%sCPU%%c6", (printed++ ? delim : "")); @@ -680,6 +698,14 @@ void print_header(char *delim) if (DO_BIC(BIC_CoreTmp)) outp += sprintf(outp, "%sCoreTmp", (printed++ ? delim : "")); + if (do_rapl && !rapl_joules) { + if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY)) + outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : "")); + } else if (do_rapl && rapl_joules) { + if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY)) + outp += sprintf(outp, "%sCor_J", (printed++ ? delim : "")); + } + for (mp = sys.cp; mp; mp = mp->next) { if (mp->format == FORMAT_RAW) { if (mp->width == 64) @@ -734,7 +760,7 @@ void print_header(char *delim) if (do_rapl && !rapl_joules) { if (DO_BIC(BIC_PkgWatt)) outp += sprintf(outp, "%sPkgWatt", (printed++ ? delim : "")); - if (DO_BIC(BIC_CorWatt)) + if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY)) outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : "")); if (DO_BIC(BIC_GFXWatt)) outp += sprintf(outp, "%sGFXWatt", (printed++ ? delim : "")); @@ -747,7 +773,7 @@ void print_header(char *delim) } else if (do_rapl && rapl_joules) { if (DO_BIC(BIC_Pkg_J)) outp += sprintf(outp, "%sPkg_J", (printed++ ? delim : "")); - if (DO_BIC(BIC_Cor_J)) + if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY)) outp += sprintf(outp, "%sCor_J", (printed++ ? delim : "")); if (DO_BIC(BIC_GFX_J)) outp += sprintf(outp, "%sGFX_J", (printed++ ? delim : "")); @@ -808,6 +834,7 @@ int dump_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "c6: %016llX\n", c->c6); outp += sprintf(outp, "c7: %016llX\n", c->c7); outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c); + outp += sprintf(outp, "Joules: %0X\n", c->core_energy); for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n", @@ -904,6 +931,8 @@ int format_counters(struct thread_data *t, struct core_data *c, if (t == &average.threads) { if (DO_BIC(BIC_Package)) outp += sprintf(outp, "%s-", (printed++ ? delim : "")); + if (DO_BIC(BIC_Die)) + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); if (DO_BIC(BIC_Node)) outp += sprintf(outp, "%s-", (printed++ ? delim : "")); if (DO_BIC(BIC_Core)) @@ -921,6 +950,12 @@ int format_counters(struct thread_data *t, struct core_data *c, else outp += sprintf(outp, "%s-", (printed++ ? delim : "")); } + if (DO_BIC(BIC_Die)) { + if (c) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), cpus[t->cpu_id].die_id); + else + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); + } if (DO_BIC(BIC_Node)) { if (t) outp += sprintf(outp, "%s%d", @@ -1003,7 +1038,7 @@ int format_counters(struct thread_data *t, struct core_data *c, if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) goto done; - if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) + if (DO_BIC(BIC_CPU_c3)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c3/tsc); if (DO_BIC(BIC_CPU_c6)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c6/tsc); @@ -1033,6 +1068,20 @@ int format_counters(struct thread_data *t, struct core_data *c, } } + /* + * If measurement interval exceeds minimum RAPL Joule Counter range, + * indicate that results are suspect by printing "**" in fraction place. + */ + if (interval_float < rapl_joule_counter_range) + fmt8 = "%s%.2f"; + else + fmt8 = "%6.0f**"; + + if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float); + if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units); + /* print per-package data only for 1st core in package */ if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) goto done; @@ -1085,18 +1134,9 @@ int format_counters(struct thread_data *t, struct core_data *c, if (DO_BIC(BIC_SYS_LPI)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float); - /* - * If measurement interval exceeds minimum RAPL Joule Counter range, - * indicate that results are suspect by printing "**" in fraction place. - */ - if (interval_float < rapl_joule_counter_range) - fmt8 = "%s%.2f"; - else - fmt8 = "%6.0f**"; - if (DO_BIC(BIC_PkgWatt)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float); - if (DO_BIC(BIC_CorWatt)) + if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float); if (DO_BIC(BIC_GFXWatt)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units / interval_float); @@ -1104,7 +1144,7 @@ int format_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units / interval_float); if (DO_BIC(BIC_Pkg_J)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units); - if (DO_BIC(BIC_Cor_J)) + if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units); if (DO_BIC(BIC_GFX_J)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units); @@ -1249,6 +1289,8 @@ delta_core(struct core_data *new, struct core_data *old) old->core_temp_c = new->core_temp_c; old->mc6_us = new->mc6_us - old->mc6_us; + DELTA_WRAP32(new->core_energy, old->core_energy); + for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) old->counter[i] = new->counter[i]; @@ -1391,6 +1433,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data c->c7 = 0; c->mc6_us = 0; c->core_temp_c = 0; + c->core_energy = 0; p->pkg_wtd_core_c0 = 0; p->pkg_any_core_c0 = 0; @@ -1473,6 +1516,8 @@ int sum_counters(struct thread_data *t, struct core_data *c, average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c); + average.cores.core_energy += c->core_energy; + for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) continue; @@ -1818,7 +1863,7 @@ retry: if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) goto done; - if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) { + if (DO_BIC(BIC_CPU_c3)) { if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3)) return -6; } @@ -1845,6 +1890,12 @@ retry: c->core_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F); } + if (do_rapl & RAPL_AMD_F17H) { + if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr)) + return -14; + c->core_energy = msr & 0xFFFFFFFF; + } + for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (get_mp(cpu, mp, &c->counter[i])) return -10; @@ -1934,6 +1985,11 @@ retry: return -16; p->rapl_dram_perf_status = msr & 0xFFFFFFFF; } + if (do_rapl & RAPL_AMD_F17H) { + if (get_msr(cpu, MSR_PKG_ENERGY_STAT, &msr)) + return -13; + p->energy_pkg = msr & 0xFFFFFFFF; + } if (DO_BIC(BIC_PkgTmp)) { if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr)) return -17; @@ -2456,6 +2512,8 @@ void free_all_buffers(void) /* * Parse a file containing a single int. + * Return 0 if file can not be opened + * Exit if file can be opened, but can not be parsed */ int parse_int_file(const char *fmt, ...) { @@ -2467,7 +2525,9 @@ int parse_int_file(const char *fmt, ...) va_start(args, fmt); vsnprintf(path, sizeof(path), fmt, args); va_end(args); - filep = fopen_or_die(path, "r"); + filep = fopen(path, "r"); + if (!filep) + return 0; if (fscanf(filep, "%d", &value) != 1) err(1, "%s: failed to parse number from file", path); fclose(filep); @@ -2488,6 +2548,11 @@ int get_physical_package_id(int cpu) return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/physical_package_id", cpu); } +int get_die_id(int cpu) +{ + return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/die_id", cpu); +} + int get_core_id(int cpu) { return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_id", cpu); @@ -2578,7 +2643,8 @@ int get_thread_siblings(struct cpu_topology *thiscpu) filep = fopen_or_die(path, "r"); do { offset -= BITMASK_SIZE; - fscanf(filep, "%lx%c", &map, &character); + if (fscanf(filep, "%lx%c", &map, &character) != 2) + err(1, "%s: failed to parse file", path); for (shift = 0; shift < BITMASK_SIZE; shift++) { if ((map >> shift) & 0x1) { so = shift + offset; @@ -2855,8 +2921,11 @@ int snapshot_cpu_lpi_us(void) fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", "r"); retval = fscanf(fp, "%lld", &cpuidle_cur_cpu_lpi_us); - if (retval != 1) - err(1, "CPU LPI"); + if (retval != 1) { + fprintf(stderr, "Disabling Low Power Idle CPU output\n"); + BIC_NOT_PRESENT(BIC_CPU_LPI); + return -1; + } fclose(fp); @@ -2878,9 +2947,11 @@ int snapshot_sys_lpi_us(void) fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", "r"); retval = fscanf(fp, "%lld", &cpuidle_cur_sys_lpi_us); - if (retval != 1) - err(1, "SYS LPI"); - + if (retval != 1) { + fprintf(stderr, "Disabling Low Power Idle System output\n"); + BIC_NOT_PRESENT(BIC_SYS_LPI); + return -1; + } fclose(fp); return 0; @@ -3410,14 +3481,14 @@ dump_sysfs_cstate_config(void) input = fopen(path, "r"); if (input == NULL) continue; - fgets(name_buf, sizeof(name_buf), input); + if (!fgets(name_buf, sizeof(name_buf), input)) + err(1, "%s: failed to read file", path); /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */ sp = strchr(name_buf, '-'); if (!sp) sp = strchrnul(name_buf, '\n'); *sp = '\0'; - fclose(input); sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc", @@ -3425,7 +3496,8 @@ dump_sysfs_cstate_config(void) input = fopen(path, "r"); if (input == NULL) continue; - fgets(desc, sizeof(desc), input); + if (!fgets(desc, sizeof(desc), input)) + err(1, "%s: failed to read file", path); fprintf(outf, "cpu%d: %s: %s", base_cpu, name_buf, desc); fclose(input); @@ -3444,20 +3516,22 @@ dump_sysfs_pstate_config(void) base_cpu); input = fopen(path, "r"); if (input == NULL) { - fprintf(stderr, "NSFOD %s\n", path); + fprintf(outf, "NSFOD %s\n", path); return; } - fgets(driver_buf, sizeof(driver_buf), input); + if (!fgets(driver_buf, sizeof(driver_buf), input)) + err(1, "%s: failed to read file", path); fclose(input); sprintf(path, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_governor", base_cpu); input = fopen(path, "r"); if (input == NULL) { - fprintf(stderr, "NSFOD %s\n", path); + fprintf(outf, "NSFOD %s\n", path); return; } - fgets(governor_buf, sizeof(governor_buf), input); + if (!fgets(governor_buf, sizeof(governor_buf), input)) + err(1, "%s: failed to read file", path); fclose(input); fprintf(outf, "cpu%d: cpufreq driver: %s", base_cpu, driver_buf); @@ -3466,7 +3540,8 @@ dump_sysfs_pstate_config(void) sprintf(path, "/sys/devices/system/cpu/cpufreq/boost"); input = fopen(path, "r"); if (input != NULL) { - fscanf(input, "%d", &turbo); + if (fscanf(input, "%d", &turbo) != 1) + err(1, "%s: failed to parse number from file", path); fprintf(outf, "cpufreq boost: %d\n", turbo); fclose(input); } @@ -3474,7 +3549,8 @@ dump_sysfs_pstate_config(void) sprintf(path, "/sys/devices/system/cpu/intel_pstate/no_turbo"); input = fopen(path, "r"); if (input != NULL) { - fscanf(input, "%d", &turbo); + if (fscanf(input, "%d", &turbo) != 1) + err(1, "%s: failed to parse number from file", path); fprintf(outf, "cpufreq intel_pstate no_turbo: %d\n", turbo); fclose(input); } @@ -3718,7 +3794,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data #define RAPL_POWER_GRANULARITY 0x7FFF /* 15 bit power granularity */ #define RAPL_TIME_GRANULARITY 0x3F /* 6 bit time granularity */ -double get_tdp(unsigned int model) +double get_tdp_intel(unsigned int model) { unsigned long long msr; @@ -3735,6 +3811,16 @@ double get_tdp(unsigned int model) } } +double get_tdp_amd(unsigned int family) +{ + switch (family) { + case 0x17: + default: + /* This is the max stock TDP of HEDT/Server Fam17h chips */ + return 250.0; + } +} + /* * rapl_dram_energy_units_probe() * Energy units are either hard-coded, or come from RAPL Energy Unit MSR. @@ -3754,21 +3840,12 @@ rapl_dram_energy_units_probe(int model, double rapl_energy_units) } } - -/* - * rapl_probe() - * - * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units - */ -void rapl_probe(unsigned int family, unsigned int model) +void rapl_probe_intel(unsigned int family, unsigned int model) { unsigned long long msr; unsigned int time_unit; double tdp; - if (!genuine_intel) - return; - if (family != 6) return; @@ -3892,13 +3969,69 @@ void rapl_probe(unsigned int family, unsigned int model) rapl_time_units = 1.0 / (1 << (time_unit)); - tdp = get_tdp(model); + tdp = get_tdp_intel(model); rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp; if (!quiet) fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp); +} - return; +void rapl_probe_amd(unsigned int family, unsigned int model) +{ + unsigned long long msr; + unsigned int eax, ebx, ecx, edx; + unsigned int has_rapl = 0; + double tdp; + + if (max_extended_level >= 0x80000007) { + __cpuid(0x80000007, eax, ebx, ecx, edx); + /* RAPL (Fam 17h) */ + has_rapl = edx & (1 << 14); + } + + if (!has_rapl) + return; + + switch (family) { + case 0x17: /* Zen, Zen+ */ + do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY; + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); + } + break; + default: + return; + } + + if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr)) + return; + + rapl_time_units = ldexp(1.0, -(msr >> 16 & 0xf)); + rapl_energy_units = ldexp(1.0, -(msr >> 8 & 0x1f)); + rapl_power_units = ldexp(1.0, -(msr & 0xf)); + + tdp = get_tdp_amd(model); + + rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp; + if (!quiet) + fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp); +} + +/* + * rapl_probe() + * + * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units + */ +void rapl_probe(unsigned int family, unsigned int model) +{ + if (genuine_intel) + rapl_probe_intel(family, model); + if (authentic_amd) + rapl_probe_amd(family, model); } void perf_limit_reasons_probe(unsigned int family, unsigned int model) @@ -4003,6 +4136,7 @@ void print_power_limit_msr(int cpu, unsigned long long msr, char *label) int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) { unsigned long long msr; + const char *msr_name; int cpu; if (!do_rapl) @@ -4018,10 +4152,17 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) return -1; } - if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr)) - return -1; + if (do_rapl & RAPL_AMD_F17H) { + msr_name = "MSR_RAPL_PWR_UNIT"; + if (get_msr(cpu, MSR_RAPL_PWR_UNIT, &msr)) + return -1; + } else { + msr_name = "MSR_RAPL_POWER_UNIT"; + if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr)) + return -1; + } - fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr, + fprintf(outf, "cpu%d: %s: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr_name, msr, rapl_power_units, rapl_energy_units, rapl_time_units); if (do_rapl & RAPL_PKG_POWER_INFO) { @@ -4451,6 +4592,9 @@ unsigned int intel_model_duplicates(unsigned int model) case INTEL_FAM6_KABYLAKE_MOBILE: case INTEL_FAM6_KABYLAKE_DESKTOP: return INTEL_FAM6_SKYLAKE_MOBILE; + + case INTEL_FAM6_ICELAKE_MOBILE: + return INTEL_FAM6_CANNONLAKE_MOBILE; } return model; } @@ -4702,7 +4846,9 @@ void process_cpuid() } do_slm_cstates = is_slm(family, model); do_knl_cstates = is_knl(family, model); - do_cnl_cstates = is_cnl(family, model); + + if (do_slm_cstates || do_knl_cstates || is_cnl(family, model)) + BIC_NOT_PRESENT(BIC_CPU_c3); if (!quiet) decode_misc_pwr_mgmt_msr(); @@ -4769,6 +4915,7 @@ void topology_probe() int i; int max_core_id = 0; int max_package_id = 0; + int max_die_id = 0; int max_siblings = 0; /* Initialize num_cpus, max_cpu_num */ @@ -4835,6 +4982,11 @@ void topology_probe() if (cpus[i].physical_package_id > max_package_id) max_package_id = cpus[i].physical_package_id; + /* get die information */ + cpus[i].die_id = get_die_id(i); + if (cpus[i].die_id > max_die_id) + max_die_id = cpus[i].die_id; + /* get numa node information */ cpus[i].physical_node_id = get_physical_node_id(&cpus[i]); if (cpus[i].physical_node_id > topo.max_node_num) @@ -4860,6 +5012,13 @@ void topology_probe() if (!summary_only && topo.cores_per_node > 1) BIC_PRESENT(BIC_Core); + topo.num_die = max_die_id + 1; + if (debug > 1) + fprintf(outf, "max_die_id %d, sizing for %d die\n", + max_die_id, topo.num_die); + if (!summary_only && topo.num_die > 1) + BIC_PRESENT(BIC_Die); + topo.num_packages = max_package_id + 1; if (debug > 1) fprintf(outf, "max_package_id %d, sizing for %d packages\n", @@ -4884,8 +5043,8 @@ void topology_probe() if (cpu_is_not_present(i)) continue; fprintf(outf, - "cpu %d pkg %d node %d lnode %d core %d thread %d\n", - i, cpus[i].physical_package_id, + "cpu %d pkg %d die %d node %d lnode %d core %d thread %d\n", + i, cpus[i].physical_package_id, cpus[i].die_id, cpus[i].physical_node_id, cpus[i].logical_node_id, cpus[i].physical_core_id, @@ -5122,7 +5281,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 18.07.27" + fprintf(outf, "turbostat version 19.03.20" " - Len Brown <lenb@kernel.org>\n"); } @@ -5319,7 +5478,8 @@ void probe_sysfs(void) input = fopen(path, "r"); if (input == NULL) continue; - fgets(name_buf, sizeof(name_buf), input); + if (!fgets(name_buf, sizeof(name_buf), input)) + err(1, "%s: failed to read file", path); /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */ sp = strchr(name_buf, '-'); @@ -5346,7 +5506,8 @@ void probe_sysfs(void) input = fopen(path, "r"); if (input == NULL) continue; - fgets(name_buf, sizeof(name_buf), input); + if (!fgets(name_buf, sizeof(name_buf), input)) + err(1, "%s: failed to read file", path); /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */ sp = strchr(name_buf, '-'); if (!sp) diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index b579f962451d..85ffdcfa596b 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -146,6 +146,7 @@ static int dimm_fail_cmd_code[ARRAY_SIZE(handle)]; struct nfit_test_sec { u8 state; u8 ext_state; + u8 old_state; u8 passphrase[32]; u8 master_passphrase[32]; u64 overwrite_end_time; @@ -225,6 +226,8 @@ static struct workqueue_struct *nfit_wq; static struct gen_pool *nfit_pool; +static const char zero_key[NVDIMM_PASSPHRASE_LEN]; + static struct nfit_test *to_nfit_test(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); @@ -1059,8 +1062,7 @@ static int nd_intel_test_cmd_secure_erase(struct nfit_test *t, struct device *dev = &t->pdev.dev; struct nfit_test_sec *sec = &dimm_sec_info[dimm]; - if (!(sec->state & ND_INTEL_SEC_STATE_ENABLED) || - (sec->state & ND_INTEL_SEC_STATE_FROZEN)) { + if (sec->state & ND_INTEL_SEC_STATE_FROZEN) { nd_cmd->status = ND_INTEL_STATUS_INVALID_STATE; dev_dbg(dev, "secure erase: wrong security state\n"); } else if (memcmp(nd_cmd->passphrase, sec->passphrase, @@ -1068,6 +1070,12 @@ static int nd_intel_test_cmd_secure_erase(struct nfit_test *t, nd_cmd->status = ND_INTEL_STATUS_INVALID_PASS; dev_dbg(dev, "secure erase: wrong passphrase\n"); } else { + if (!(sec->state & ND_INTEL_SEC_STATE_ENABLED) + && (memcmp(nd_cmd->passphrase, zero_key, + ND_INTEL_PASSPHRASE_SIZE) != 0)) { + dev_dbg(dev, "invalid zero key\n"); + return 0; + } memset(sec->passphrase, 0, ND_INTEL_PASSPHRASE_SIZE); memset(sec->master_passphrase, 0, ND_INTEL_PASSPHRASE_SIZE); sec->state = 0; @@ -1093,7 +1101,7 @@ static int nd_intel_test_cmd_overwrite(struct nfit_test *t, return 0; } - memset(sec->passphrase, 0, ND_INTEL_PASSPHRASE_SIZE); + sec->old_state = sec->state; sec->state = ND_INTEL_SEC_STATE_OVERWRITE; dev_dbg(dev, "overwrite progressing.\n"); sec->overwrite_end_time = get_jiffies_64() + 5 * HZ; @@ -1115,7 +1123,8 @@ static int nd_intel_test_cmd_query_overwrite(struct nfit_test *t, if (time_is_before_jiffies64(sec->overwrite_end_time)) { sec->overwrite_end_time = 0; - sec->state = 0; + sec->state = sec->old_state; + sec->old_state = 0; sec->ext_state = ND_INTEL_SEC_ESTATE_ENABLED; dev_dbg(dev, "overwrite is complete\n"); } else diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 77b73b892136..078283d073b0 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -209,7 +209,7 @@ ifeq ($(DWARF2BTF),y) endif PROG_TESTS_H := $(OUTPUT)/prog_tests/tests.h -$(OUTPUT)/test_progs: $(PROG_TESTS_H) +test_progs.c: $(PROG_TESTS_H) $(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS) $(OUTPUT)/test_progs: prog_tests/*.c @@ -232,7 +232,7 @@ $(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES) ) > $(PROG_TESTS_H)) VERIFIER_TESTS_H := $(OUTPUT)/verifier/tests.h -$(OUTPUT)/test_verifier: $(VERIFIER_TESTS_H) +test_verifier.c: $(VERIFIER_TESTS_H) $(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS) VERIFIER_TESTS_DIR = $(OUTPUT)/verifier diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 97d140961438..e85d62cb53d0 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -9,14 +9,14 @@ #define SEC(NAME) __attribute__((section(NAME), used)) /* helper functions called from eBPF programs written in C */ -static void *(*bpf_map_lookup_elem)(void *map, void *key) = +static void *(*bpf_map_lookup_elem)(void *map, const void *key) = (void *) BPF_FUNC_map_lookup_elem; -static int (*bpf_map_update_elem)(void *map, void *key, void *value, +static int (*bpf_map_update_elem)(void *map, const void *key, const void *value, unsigned long long flags) = (void *) BPF_FUNC_map_update_elem; -static int (*bpf_map_delete_elem)(void *map, void *key) = +static int (*bpf_map_delete_elem)(void *map, const void *key) = (void *) BPF_FUNC_map_delete_elem; -static int (*bpf_map_push_elem)(void *map, void *value, +static int (*bpf_map_push_elem)(void *map, const void *value, unsigned long long flags) = (void *) BPF_FUNC_map_push_elem; static int (*bpf_map_pop_elem)(void *map, void *value) = diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index a42f4fc4dc11..8c976476f6fd 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -25,3 +25,11 @@ CONFIG_XDP_SOCKETS=y CONFIG_FTRACE_SYSCALLS=y CONFIG_IPV6_TUNNEL=y CONFIG_IPV6_GRE=y +CONFIG_NET_FOU=m +CONFIG_NET_FOU_IP_TUNNELS=y +CONFIG_IPV6_FOU=m +CONFIG_IPV6_FOU_TUNNEL=m +CONFIG_MPLS=y +CONFIG_NET_MPLS_GSO=m +CONFIG_MPLS_ROUTING=m +CONFIG_MPLS_IPTUNNEL=m diff --git a/tools/testing/selftests/bpf/flow_dissector_load.c b/tools/testing/selftests/bpf/flow_dissector_load.c index 77cafa66d048..7136ab9ffa73 100644 --- a/tools/testing/selftests/bpf/flow_dissector_load.c +++ b/tools/testing/selftests/bpf/flow_dissector_load.c @@ -52,7 +52,7 @@ static void detach_program(void) sprintf(command, "rm -r %s", cfg_pin_path); ret = system(command); if (ret) - error(1, errno, command); + error(1, errno, "%s", command); } static void parse_opts(int argc, char **argv) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c index a64f7a02139c..cb827383db4d 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c @@ -73,7 +73,7 @@ void test_bpf_obj_id(void) info_len != sizeof(struct bpf_map_info) || strcmp((char *)map_infos[i].name, expected_map_name), "get-map-info(fd)", - "err %d errno %d type %d(%d) info_len %u(%Zu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n", + "err %d errno %d type %d(%d) info_len %u(%zu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n", err, errno, map_infos[i].type, BPF_MAP_TYPE_ARRAY, info_len, sizeof(struct bpf_map_info), @@ -117,7 +117,7 @@ void test_bpf_obj_id(void) *(int *)(long)prog_infos[i].map_ids != map_infos[i].id || strcmp((char *)prog_infos[i].name, expected_prog_name), "get-prog-info(fd)", - "err %d errno %d i %d type %d(%d) info_len %u(%Zu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n", + "err %d errno %d i %d type %d(%d) info_len %u(%zu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n", err, errno, i, prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER, info_len, sizeof(struct bpf_prog_info), @@ -185,7 +185,7 @@ void test_bpf_obj_id(void) memcmp(&prog_info, &prog_infos[i], info_len) || *(int *)(long)prog_info.map_ids != saved_map_id, "get-prog-info(next_id->fd)", - "err %d errno %d info_len %u(%Zu) memcmp %d map_id %u(%u)\n", + "err %d errno %d info_len %u(%zu) memcmp %d map_id %u(%u)\n", err, errno, info_len, sizeof(struct bpf_prog_info), memcmp(&prog_info, &prog_infos[i], info_len), *(int *)(long)prog_info.map_ids, saved_map_id); @@ -231,7 +231,7 @@ void test_bpf_obj_id(void) memcmp(&map_info, &map_infos[i], info_len) || array_value != array_magic_value, "check get-map-info(next_id->fd)", - "err %d errno %d info_len %u(%Zu) memcmp %d array_value %llu(%llu)\n", + "err %d errno %d info_len %u(%zu) memcmp %d array_value %llu(%llu)\n", err, errno, info_len, sizeof(struct bpf_map_info), memcmp(&map_info, &map_infos[i], info_len), array_value, array_magic_value); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c new file mode 100644 index 000000000000..23b159d95c3f --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <test_progs.h> +static int libbpf_debug_print(enum libbpf_print_level level, + const char *format, va_list args) +{ + if (level != LIBBPF_DEBUG) + return 0; + + if (!strstr(format, "verifier log")) + return 0; + return vfprintf(stderr, "%s", args); +} + +static int check_load(const char *file) +{ + struct bpf_prog_load_attr attr; + struct bpf_object *obj; + int err, prog_fd; + + memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); + attr.file = file; + attr.prog_type = BPF_PROG_TYPE_SCHED_CLS; + attr.log_level = 4; + err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); + bpf_object__close(obj); + if (err) + error_cnt++; + return err; +} + +void test_bpf_verif_scale(void) +{ + const char *file1 = "./test_verif_scale1.o"; + const char *file2 = "./test_verif_scale2.o"; + const char *file3 = "./test_verif_scale3.o"; + int err; + + if (verifier_stats) + libbpf_set_print(libbpf_debug_print); + + err = check_load(file1); + err |= check_load(file2); + err |= check_load(file3); + if (!err) + printf("test_verif_scale:OK\n"); + else + printf("test_verif_scale:FAIL\n"); +} diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index bcbd928c96ab..fc818bc1d729 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -39,6 +39,58 @@ static struct bpf_flow_keys pkt_v6_flow_keys = { .n_proto = __bpf_constant_htons(ETH_P_IPV6), }; +#define VLAN_HLEN 4 + +static struct { + struct ethhdr eth; + __u16 vlan_tci; + __u16 vlan_proto; + struct iphdr iph; + struct tcphdr tcp; +} __packed pkt_vlan_v4 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_8021Q), + .vlan_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_TCP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .tcp.urg_ptr = 123, + .tcp.doff = 5, +}; + +static struct bpf_flow_keys pkt_vlan_v4_flow_keys = { + .nhoff = VLAN_HLEN, + .thoff = VLAN_HLEN + sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IP), +}; + +static struct { + struct ethhdr eth; + __u16 vlan_tci; + __u16 vlan_proto; + __u16 vlan_tci2; + __u16 vlan_proto2; + struct ipv6hdr iph; + struct tcphdr tcp; +} __packed pkt_vlan_v6 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_8021AD), + .vlan_proto = __bpf_constant_htons(ETH_P_8021Q), + .vlan_proto2 = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_TCP, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .tcp.urg_ptr = 123, + .tcp.doff = 5, +}; + +static struct bpf_flow_keys pkt_vlan_v6_flow_keys = { + .nhoff = VLAN_HLEN * 2, + .thoff = VLAN_HLEN * 2 + sizeof(struct ipv6hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), +}; + void test_flow_dissector(void) { struct bpf_flow_keys flow_keys; @@ -68,5 +120,21 @@ void test_flow_dissector(void) err, errno, retval, duration, size, sizeof(flow_keys)); CHECK_FLOW_KEYS("ipv6_flow_keys", flow_keys, pkt_v6_flow_keys); + err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v4, sizeof(pkt_vlan_v4), + &flow_keys, &size, &retval, &duration); + CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv4", + "err %d errno %d retval %d duration %d size %u/%lu\n", + err, errno, retval, duration, size, sizeof(flow_keys)); + CHECK_FLOW_KEYS("vlan_ipv4_flow_keys", flow_keys, + pkt_vlan_v4_flow_keys); + + err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v6, sizeof(pkt_vlan_v6), + &flow_keys, &size, &retval, &duration); + CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv6", + "err %d errno %d retval %d duration %d size %u/%lu\n", + err, errno, retval, duration, size, sizeof(flow_keys)); + CHECK_FLOW_KEYS("vlan_ipv6_flow_keys", flow_keys, + pkt_vlan_v6_flow_keys); + bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c index d7bb5beb1c57..c2a0a9d5591b 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c +++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c @@ -39,7 +39,7 @@ static int get_stack_print_output(void *data, int size) } else { for (i = 0; i < num_stack; i++) { ks = ksym_search(raw_data[i]); - if (strcmp(ks->name, nonjit_func) == 0) { + if (ks && (strcmp(ks->name, nonjit_func) == 0)) { found = true; break; } @@ -56,7 +56,7 @@ static int get_stack_print_output(void *data, int size) } else { for (i = 0; i < num_stack; i++) { ks = ksym_search(e->kern_stack[i]); - if (strcmp(ks->name, nonjit_func) == 0) { + if (ks && (strcmp(ks->name, nonjit_func) == 0)) { good_kern_stack = true; break; } diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c new file mode 100644 index 000000000000..d011079fb0bf --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/global_data.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> + +static void test_global_data_number(struct bpf_object *obj, __u32 duration) +{ + int i, err, map_fd; + uint64_t num; + + map_fd = bpf_find_map(__func__, obj, "result_number"); + if (map_fd < 0) { + error_cnt++; + return; + } + + struct { + char *name; + uint32_t key; + uint64_t num; + } tests[] = { + { "relocate .bss reference", 0, 0 }, + { "relocate .data reference", 1, 42 }, + { "relocate .rodata reference", 2, 24 }, + { "relocate .bss reference", 3, 0 }, + { "relocate .data reference", 4, 0xffeeff }, + { "relocate .rodata reference", 5, 0xabab }, + { "relocate .bss reference", 6, 1234 }, + { "relocate .bss reference", 7, 0 }, + { "relocate .rodata reference", 8, 0xab }, + { "relocate .rodata reference", 9, 0x1111111111111111 }, + { "relocate .rodata reference", 10, ~0 }, + }; + + for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + err = bpf_map_lookup_elem(map_fd, &tests[i].key, &num); + CHECK(err || num != tests[i].num, tests[i].name, + "err %d result %lx expected %lx\n", + err, num, tests[i].num); + } +} + +static void test_global_data_string(struct bpf_object *obj, __u32 duration) +{ + int i, err, map_fd; + char str[32]; + + map_fd = bpf_find_map(__func__, obj, "result_string"); + if (map_fd < 0) { + error_cnt++; + return; + } + + struct { + char *name; + uint32_t key; + char str[32]; + } tests[] = { + { "relocate .rodata reference", 0, "abcdefghijklmnopqrstuvwxyz" }, + { "relocate .data reference", 1, "abcdefghijklmnopqrstuvwxyz" }, + { "relocate .bss reference", 2, "" }, + { "relocate .data reference", 3, "abcdexghijklmnopqrstuvwxyz" }, + { "relocate .bss reference", 4, "\0\0hello" }, + }; + + for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + err = bpf_map_lookup_elem(map_fd, &tests[i].key, str); + CHECK(err || memcmp(str, tests[i].str, sizeof(str)), + tests[i].name, "err %d result \'%s\' expected \'%s\'\n", + err, str, tests[i].str); + } +} + +struct foo { + __u8 a; + __u32 b; + __u64 c; +}; + +static void test_global_data_struct(struct bpf_object *obj, __u32 duration) +{ + int i, err, map_fd; + struct foo val; + + map_fd = bpf_find_map(__func__, obj, "result_struct"); + if (map_fd < 0) { + error_cnt++; + return; + } + + struct { + char *name; + uint32_t key; + struct foo val; + } tests[] = { + { "relocate .rodata reference", 0, { 42, 0xfefeefef, 0x1111111111111111ULL, } }, + { "relocate .bss reference", 1, { } }, + { "relocate .rodata reference", 2, { } }, + { "relocate .data reference", 3, { 41, 0xeeeeefef, 0x2111111111111111ULL, } }, + }; + + for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + err = bpf_map_lookup_elem(map_fd, &tests[i].key, &val); + CHECK(err || memcmp(&val, &tests[i].val, sizeof(val)), + tests[i].name, "err %d result { %u, %u, %llu } expected { %u, %u, %llu }\n", + err, val.a, val.b, val.c, tests[i].val.a, tests[i].val.b, tests[i].val.c); + } +} + +static void test_global_data_rdonly(struct bpf_object *obj, __u32 duration) +{ + int err = -ENOMEM, map_fd, zero = 0; + struct bpf_map *map; + __u8 *buff; + + map = bpf_object__find_map_by_name(obj, "test_glo.rodata"); + if (!map || !bpf_map__is_internal(map)) { + error_cnt++; + return; + } + + map_fd = bpf_map__fd(map); + if (map_fd < 0) { + error_cnt++; + return; + } + + buff = malloc(bpf_map__def(map)->value_size); + if (buff) + err = bpf_map_update_elem(map_fd, &zero, buff, 0); + free(buff); + CHECK(!err || errno != EPERM, "test .rodata read-only map", + "err %d errno %d\n", err, errno); +} + +void test_global_data(void) +{ + const char *file = "./test_global_data.o"; + __u32 duration = 0, retval; + struct bpf_object *obj; + int err, prog_fd; + + err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); + if (CHECK(err, "load program", "error %d loading %s\n", err, file)) + return; + + err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), + NULL, NULL, &retval, &duration); + CHECK(err || retval, "pass global data run", + "err %d errno %d retval %d duration %d\n", + err, errno, retval, duration); + + test_global_data_number(obj, duration); + test_global_data_string(obj, duration); + test_global_data_struct(obj, duration); + test_global_data_rdonly(obj, duration); + + bpf_object__close(obj); +} diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c new file mode 100644 index 000000000000..e95baa32e277 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> + +void test_skb_ctx(void) +{ + struct __sk_buff skb = { + .cb[0] = 1, + .cb[1] = 2, + .cb[2] = 3, + .cb[3] = 4, + .cb[4] = 5, + .priority = 6, + }; + struct bpf_prog_test_run_attr tattr = { + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .ctx_in = &skb, + .ctx_size_in = sizeof(skb), + .ctx_out = &skb, + .ctx_size_out = sizeof(skb), + }; + struct bpf_object *obj; + int err; + int i; + + err = bpf_prog_load("./test_skb_ctx.o", BPF_PROG_TYPE_SCHED_CLS, &obj, + &tattr.prog_fd); + if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno)) + return; + + /* ctx_in != NULL, ctx_size_in == 0 */ + + tattr.ctx_size_in = 0; + err = bpf_prog_test_run_xattr(&tattr); + CHECK_ATTR(err == 0, "ctx_size_in", "err %d errno %d\n", err, errno); + tattr.ctx_size_in = sizeof(skb); + + /* ctx_out != NULL, ctx_size_out == 0 */ + + tattr.ctx_size_out = 0; + err = bpf_prog_test_run_xattr(&tattr); + CHECK_ATTR(err == 0, "ctx_size_out", "err %d errno %d\n", err, errno); + tattr.ctx_size_out = sizeof(skb); + + /* non-zero [len, tc_index] fields should be rejected*/ + + skb.len = 1; + err = bpf_prog_test_run_xattr(&tattr); + CHECK_ATTR(err == 0, "len", "err %d errno %d\n", err, errno); + skb.len = 0; + + skb.tc_index = 1; + err = bpf_prog_test_run_xattr(&tattr); + CHECK_ATTR(err == 0, "tc_index", "err %d errno %d\n", err, errno); + skb.tc_index = 0; + + /* non-zero [hash, sk] fields should be rejected */ + + skb.hash = 1; + err = bpf_prog_test_run_xattr(&tattr); + CHECK_ATTR(err == 0, "hash", "err %d errno %d\n", err, errno); + skb.hash = 0; + + skb.sk = (struct bpf_sock *)1; + err = bpf_prog_test_run_xattr(&tattr); + CHECK_ATTR(err == 0, "sk", "err %d errno %d\n", err, errno); + skb.sk = 0; + + err = bpf_prog_test_run_xattr(&tattr); + CHECK_ATTR(err != 0 || tattr.retval, + "run", + "err %d errno %d retval %d\n", + err, errno, tattr.retval); + + CHECK_ATTR(tattr.ctx_size_out != sizeof(skb), + "ctx_size_out", + "incorrect output size, want %lu have %u\n", + sizeof(skb), tattr.ctx_size_out); + + for (i = 0; i < 5; i++) + CHECK_ATTR(skb.cb[i] != i + 2, + "ctx_out_cb", + "skb->cb[i] == %d, expected %d\n", + skb.cb[i], i + 2); + CHECK_ATTR(skb.priority != 7, + "ctx_out_priority", + "skb->priority == %d, expected %d\n", + skb.priority, 7); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 284660f5aa95..75b17cada539 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -92,7 +92,6 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto) { struct bpf_flow_keys *keys = skb->flow_keys; - keys->n_proto = proto; switch (proto) { case bpf_htons(ETH_P_IP): bpf_tail_call(skb, &jmp_table, IP); @@ -119,10 +118,9 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto) SEC("flow_dissector") int _dissect(struct __sk_buff *skb) { - if (!skb->vlan_present) - return parse_eth_proto(skb, skb->protocol); - else - return parse_eth_proto(skb, skb->vlan_proto); + struct bpf_flow_keys *keys = skb->flow_keys; + + return parse_eth_proto(skb, keys->n_proto); } /* Parses on IPPROTO_* */ @@ -336,15 +334,9 @@ PROG(VLAN)(struct __sk_buff *skb) { struct bpf_flow_keys *keys = skb->flow_keys; struct vlan_hdr *vlan, _vlan; - __be16 proto; - - /* Peek back to see if single or double-tagging */ - if (bpf_skb_load_bytes(skb, keys->thoff - sizeof(proto), &proto, - sizeof(proto))) - return BPF_DROP; /* Account for double-tagging */ - if (proto == bpf_htons(ETH_P_8021AD)) { + if (keys->n_proto == bpf_htons(ETH_P_8021AD)) { vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan); if (!vlan) return BPF_DROP; @@ -352,6 +344,7 @@ PROG(VLAN)(struct __sk_buff *skb) if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q)) return BPF_DROP; + keys->nhoff += sizeof(*vlan); keys->thoff += sizeof(*vlan); } @@ -359,12 +352,14 @@ PROG(VLAN)(struct __sk_buff *skb) if (!vlan) return BPF_DROP; + keys->nhoff += sizeof(*vlan); keys->thoff += sizeof(*vlan); /* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/ if (vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021AD) || vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q)) return BPF_DROP; + keys->n_proto = vlan->h_vlan_encapsulated_proto; return parse_eth_proto(skb, vlan->h_vlan_encapsulated_proto); } diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c new file mode 100644 index 000000000000..5ab14e941980 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_data.c @@ -0,0 +1,106 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Isovalent, Inc. + +#include <linux/bpf.h> +#include <linux/pkt_cls.h> +#include <string.h> + +#include "bpf_helpers.h" + +struct bpf_map_def SEC("maps") result_number = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u64), + .max_entries = 11, +}; + +struct bpf_map_def SEC("maps") result_string = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = 32, + .max_entries = 5, +}; + +struct foo { + __u8 a; + __u32 b; + __u64 c; +}; + +struct bpf_map_def SEC("maps") result_struct = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct foo), + .max_entries = 5, +}; + +/* Relocation tests for __u64s. */ +static __u64 num0; +static __u64 num1 = 42; +static const __u64 num2 = 24; +static __u64 num3 = 0; +static __u64 num4 = 0xffeeff; +static const __u64 num5 = 0xabab; +static const __u64 num6 = 0xab; + +/* Relocation tests for strings. */ +static const char str0[32] = "abcdefghijklmnopqrstuvwxyz"; +static char str1[32] = "abcdefghijklmnopqrstuvwxyz"; +static char str2[32]; + +/* Relocation tests for structs. */ +static const struct foo struct0 = { + .a = 42, + .b = 0xfefeefef, + .c = 0x1111111111111111ULL, +}; +static struct foo struct1; +static const struct foo struct2; +static struct foo struct3 = { + .a = 41, + .b = 0xeeeeefef, + .c = 0x2111111111111111ULL, +}; + +#define test_reloc(map, num, var) \ + do { \ + __u32 key = num; \ + bpf_map_update_elem(&result_##map, &key, var, 0); \ + } while (0) + +SEC("static_data_load") +int load_static_data(struct __sk_buff *skb) +{ + static const __u64 bar = ~0; + + test_reloc(number, 0, &num0); + test_reloc(number, 1, &num1); + test_reloc(number, 2, &num2); + test_reloc(number, 3, &num3); + test_reloc(number, 4, &num4); + test_reloc(number, 5, &num5); + num4 = 1234; + test_reloc(number, 6, &num4); + test_reloc(number, 7, &num0); + test_reloc(number, 8, &num6); + + test_reloc(string, 0, str0); + test_reloc(string, 1, str1); + test_reloc(string, 2, str2); + str1[5] = 'x'; + test_reloc(string, 3, str1); + __builtin_memcpy(&str2[2], "hello", sizeof("hello")); + test_reloc(string, 4, str2); + + test_reloc(struct, 0, &struct0); + test_reloc(struct, 1, &struct1); + test_reloc(struct, 2, &struct2); + test_reloc(struct, 3, &struct3); + + test_reloc(number, 9, &struct0.c); + test_reloc(number, 10, &bar); + + return TC_ACT_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_jhash.h b/tools/testing/selftests/bpf/progs/test_jhash.h new file mode 100644 index 000000000000..3d12c11a8d47 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_jhash.h @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +typedef unsigned int u32; + +static __attribute__((always_inline)) u32 rol32(u32 word, unsigned int shift) +{ + return (word << shift) | (word >> ((-shift) & 31)); +} + +#define __jhash_mix(a, b, c) \ +{ \ + a -= c; a ^= rol32(c, 4); c += b; \ + b -= a; b ^= rol32(a, 6); a += c; \ + c -= b; c ^= rol32(b, 8); b += a; \ + a -= c; a ^= rol32(c, 16); c += b; \ + b -= a; b ^= rol32(a, 19); a += c; \ + c -= b; c ^= rol32(b, 4); b += a; \ +} + +#define __jhash_final(a, b, c) \ +{ \ + c ^= b; c -= rol32(b, 14); \ + a ^= c; a -= rol32(c, 11); \ + b ^= a; b -= rol32(a, 25); \ + c ^= b; c -= rol32(b, 16); \ + a ^= c; a -= rol32(c, 4); \ + b ^= a; b -= rol32(a, 14); \ + c ^= b; c -= rol32(b, 24); \ +} + +#define JHASH_INITVAL 0xdeadbeef + +static ATTR +u32 jhash(const void *key, u32 length, u32 initval) +{ + u32 a, b, c; + const unsigned char *k = key; + + a = b = c = JHASH_INITVAL + length + initval; + + while (length > 12) { + a += *(volatile u32 *)(k); + b += *(volatile u32 *)(k + 4); + c += *(volatile u32 *)(k + 8); + __jhash_mix(a, b, c); + length -= 12; + k += 12; + } + switch (length) { + case 12: c += (u32)k[11]<<24; + case 11: c += (u32)k[10]<<16; + case 10: c += (u32)k[9]<<8; + case 9: c += k[8]; + case 8: b += (u32)k[7]<<24; + case 7: b += (u32)k[6]<<16; + case 6: b += (u32)k[5]<<8; + case 5: b += k[4]; + case 4: a += (u32)k[3]<<24; + case 3: a += (u32)k[2]<<16; + case 2: a += (u32)k[1]<<8; + case 1: a += k[0]; + c ^= a; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } + + return c; +} diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c new file mode 100644 index 000000000000..7a80960d7df1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include "bpf_helpers.h" + +int _version SEC("version") = 1; +char _license[] SEC("license") = "GPL"; + +SEC("skb_ctx") +int process(struct __sk_buff *skb) +{ + #pragma clang loop unroll(full) + for (int i = 0; i < 5; i++) { + if (skb->cb[i] != i + 1) + return 1; + skb->cb[i]++; + } + skb->priority++; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c index f541c2de947d..bcb00d737e95 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c +++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c @@ -11,7 +11,9 @@ #include <linux/in.h> #include <linux/ip.h> #include <linux/ipv6.h> +#include <linux/mpls.h> #include <linux/tcp.h> +#include <linux/udp.h> #include <linux/pkt_cls.h> #include <linux/types.h> @@ -20,16 +22,36 @@ static const int cfg_port = 8000; -struct grev4hdr { - struct iphdr ip; +static const int cfg_udp_src = 20000; + +#define UDP_PORT 5555 +#define MPLS_OVER_UDP_PORT 6635 +#define ETH_OVER_UDP_PORT 7777 + +/* MPLS label 1000 with S bit (last label) set and ttl of 255. */ +static const __u32 mpls_label = __bpf_constant_htonl(1000 << 12 | + MPLS_LS_S_MASK | 0xff); + +struct gre_hdr { __be16 flags; __be16 protocol; } __attribute__((packed)); -struct grev6hdr { +union l4hdr { + struct udphdr udp; + struct gre_hdr gre; +}; + +struct v4hdr { + struct iphdr ip; + union l4hdr l4hdr; + __u8 pad[16]; /* enough space for L2 header */ +} __attribute__((packed)); + +struct v6hdr { struct ipv6hdr ip; - __be16 flags; - __be16 protocol; + union l4hdr l4hdr; + __u8 pad[16]; /* enough space for L2 header */ } __attribute__((packed)); static __always_inline void set_ipv4_csum(struct iphdr *iph) @@ -47,13 +69,15 @@ static __always_inline void set_ipv4_csum(struct iphdr *iph) iph->check = ~((csum & 0xffff) + (csum >> 16)); } -static __always_inline int encap_ipv4(struct __sk_buff *skb, bool with_gre) +static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto, + __u16 l2_proto) { - struct grev4hdr h_outer; + __u16 udp_dst = UDP_PORT; struct iphdr iph_inner; + struct v4hdr h_outer; struct tcphdr tcph; + int olen, l2_len; __u64 flags; - int olen; if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner, sizeof(iph_inner)) < 0) @@ -70,13 +94,58 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, bool with_gre) if (tcph.dest != __bpf_constant_htons(cfg_port)) return TC_ACT_OK; + olen = sizeof(h_outer.ip); + l2_len = 0; + flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV4; - if (with_gre) { + + switch (l2_proto) { + case ETH_P_MPLS_UC: + l2_len = sizeof(mpls_label); + udp_dst = MPLS_OVER_UDP_PORT; + break; + case ETH_P_TEB: + l2_len = ETH_HLEN; + udp_dst = ETH_OVER_UDP_PORT; + break; + } + flags |= BPF_F_ADJ_ROOM_ENCAP_L2(l2_len); + + switch (encap_proto) { + case IPPROTO_GRE: flags |= BPF_F_ADJ_ROOM_ENCAP_L4_GRE; - olen = sizeof(h_outer); - } else { - olen = sizeof(h_outer.ip); + olen += sizeof(h_outer.l4hdr.gre); + h_outer.l4hdr.gre.protocol = bpf_htons(l2_proto); + h_outer.l4hdr.gre.flags = 0; + break; + case IPPROTO_UDP: + flags |= BPF_F_ADJ_ROOM_ENCAP_L4_UDP; + olen += sizeof(h_outer.l4hdr.udp); + h_outer.l4hdr.udp.source = __bpf_constant_htons(cfg_udp_src); + h_outer.l4hdr.udp.dest = bpf_htons(udp_dst); + h_outer.l4hdr.udp.check = 0; + h_outer.l4hdr.udp.len = bpf_htons(bpf_ntohs(iph_inner.tot_len) + + sizeof(h_outer.l4hdr.udp) + + l2_len); + break; + case IPPROTO_IPIP: + break; + default: + return TC_ACT_OK; + } + + /* add L2 encap (if specified) */ + switch (l2_proto) { + case ETH_P_MPLS_UC: + *((__u32 *)((__u8 *)&h_outer + olen)) = mpls_label; + break; + case ETH_P_TEB: + if (bpf_skb_load_bytes(skb, 0, (__u8 *)&h_outer + olen, + ETH_HLEN)) + return TC_ACT_SHOT; + break; } + olen += l2_len; /* add room between mac and network header */ if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags)) @@ -85,16 +154,10 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, bool with_gre) /* prepare new outer network header */ h_outer.ip = iph_inner; h_outer.ip.tot_len = bpf_htons(olen + - bpf_htons(h_outer.ip.tot_len)); - if (with_gre) { - h_outer.ip.protocol = IPPROTO_GRE; - h_outer.protocol = bpf_htons(ETH_P_IP); - h_outer.flags = 0; - } else { - h_outer.ip.protocol = IPPROTO_IPIP; - } + bpf_ntohs(h_outer.ip.tot_len)); + h_outer.ip.protocol = encap_proto; - set_ipv4_csum((void *)&h_outer.ip); + set_ipv4_csum(&h_outer.ip); /* store new outer network header */ if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen, @@ -104,13 +167,16 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, bool with_gre) return TC_ACT_OK; } -static __always_inline int encap_ipv6(struct __sk_buff *skb, bool with_gre) +static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto, + __u16 l2_proto) { + __u16 udp_dst = UDP_PORT; struct ipv6hdr iph_inner; - struct grev6hdr h_outer; + struct v6hdr h_outer; struct tcphdr tcph; + int olen, l2_len; + __u16 tot_len; __u64 flags; - int olen; if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner, sizeof(iph_inner)) < 0) @@ -124,14 +190,58 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, bool with_gre) if (tcph.dest != __bpf_constant_htons(cfg_port)) return TC_ACT_OK; + olen = sizeof(h_outer.ip); + l2_len = 0; + flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV6; - if (with_gre) { + + switch (l2_proto) { + case ETH_P_MPLS_UC: + l2_len = sizeof(mpls_label); + udp_dst = MPLS_OVER_UDP_PORT; + break; + case ETH_P_TEB: + l2_len = ETH_HLEN; + udp_dst = ETH_OVER_UDP_PORT; + break; + } + flags |= BPF_F_ADJ_ROOM_ENCAP_L2(l2_len); + + switch (encap_proto) { + case IPPROTO_GRE: flags |= BPF_F_ADJ_ROOM_ENCAP_L4_GRE; - olen = sizeof(h_outer); - } else { - olen = sizeof(h_outer.ip); + olen += sizeof(h_outer.l4hdr.gre); + h_outer.l4hdr.gre.protocol = bpf_htons(l2_proto); + h_outer.l4hdr.gre.flags = 0; + break; + case IPPROTO_UDP: + flags |= BPF_F_ADJ_ROOM_ENCAP_L4_UDP; + olen += sizeof(h_outer.l4hdr.udp); + h_outer.l4hdr.udp.source = __bpf_constant_htons(cfg_udp_src); + h_outer.l4hdr.udp.dest = bpf_htons(udp_dst); + tot_len = bpf_ntohs(iph_inner.payload_len) + sizeof(iph_inner) + + sizeof(h_outer.l4hdr.udp); + h_outer.l4hdr.udp.check = 0; + h_outer.l4hdr.udp.len = bpf_htons(tot_len); + break; + case IPPROTO_IPV6: + break; + default: + return TC_ACT_OK; } + /* add L2 encap (if specified) */ + switch (l2_proto) { + case ETH_P_MPLS_UC: + *((__u32 *)((__u8 *)&h_outer + olen)) = mpls_label; + break; + case ETH_P_TEB: + if (bpf_skb_load_bytes(skb, 0, (__u8 *)&h_outer + olen, + ETH_HLEN)) + return TC_ACT_SHOT; + break; + } + olen += l2_len; /* add room between mac and network header */ if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags)) @@ -141,13 +251,8 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, bool with_gre) h_outer.ip = iph_inner; h_outer.ip.payload_len = bpf_htons(olen + bpf_ntohs(h_outer.ip.payload_len)); - if (with_gre) { - h_outer.ip.nexthdr = IPPROTO_GRE; - h_outer.protocol = bpf_htons(ETH_P_IPV6); - h_outer.flags = 0; - } else { - h_outer.ip.nexthdr = IPPROTO_IPV6; - } + + h_outer.ip.nexthdr = encap_proto; /* store new outer network header */ if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen, @@ -157,54 +262,168 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, bool with_gre) return TC_ACT_OK; } -SEC("encap_ipip") -int __encap_ipip(struct __sk_buff *skb) +SEC("encap_ipip_none") +int __encap_ipip_none(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) - return encap_ipv4(skb, false); + return encap_ipv4(skb, IPPROTO_IPIP, ETH_P_IP); else return TC_ACT_OK; } -SEC("encap_gre") -int __encap_gre(struct __sk_buff *skb) +SEC("encap_gre_none") +int __encap_gre_none(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) - return encap_ipv4(skb, true); + return encap_ipv4(skb, IPPROTO_GRE, ETH_P_IP); else return TC_ACT_OK; } -SEC("encap_ip6tnl") -int __encap_ip6tnl(struct __sk_buff *skb) +SEC("encap_gre_mpls") +int __encap_gre_mpls(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_GRE, ETH_P_MPLS_UC); + else + return TC_ACT_OK; +} + +SEC("encap_gre_eth") +int __encap_gre_eth(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_GRE, ETH_P_TEB); + else + return TC_ACT_OK; +} + +SEC("encap_udp_none") +int __encap_udp_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_UDP, ETH_P_IP); + else + return TC_ACT_OK; +} + +SEC("encap_udp_mpls") +int __encap_udp_mpls(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_UDP, ETH_P_MPLS_UC); + else + return TC_ACT_OK; +} + +SEC("encap_udp_eth") +int __encap_udp_eth(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) + return encap_ipv4(skb, IPPROTO_UDP, ETH_P_TEB); + else + return TC_ACT_OK; +} + +SEC("encap_ip6tnl_none") +int __encap_ip6tnl_none(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) - return encap_ipv6(skb, false); + return encap_ipv6(skb, IPPROTO_IPV6, ETH_P_IPV6); else return TC_ACT_OK; } -SEC("encap_ip6gre") -int __encap_ip6gre(struct __sk_buff *skb) +SEC("encap_ip6gre_none") +int __encap_ip6gre_none(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) - return encap_ipv6(skb, true); + return encap_ipv6(skb, IPPROTO_GRE, ETH_P_IPV6); + else + return TC_ACT_OK; +} + +SEC("encap_ip6gre_mpls") +int __encap_ip6gre_mpls(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_GRE, ETH_P_MPLS_UC); + else + return TC_ACT_OK; +} + +SEC("encap_ip6gre_eth") +int __encap_ip6gre_eth(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_GRE, ETH_P_TEB); + else + return TC_ACT_OK; +} + +SEC("encap_ip6udp_none") +int __encap_ip6udp_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_UDP, ETH_P_IPV6); + else + return TC_ACT_OK; +} + +SEC("encap_ip6udp_mpls") +int __encap_ip6udp_mpls(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_UDP, ETH_P_MPLS_UC); + else + return TC_ACT_OK; +} + +SEC("encap_ip6udp_eth") +int __encap_ip6udp_eth(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv6(skb, IPPROTO_UDP, ETH_P_TEB); else return TC_ACT_OK; } static int decap_internal(struct __sk_buff *skb, int off, int len, char proto) { - char buf[sizeof(struct grev6hdr)]; - int olen; + char buf[sizeof(struct v6hdr)]; + struct gre_hdr greh; + struct udphdr udph; + int olen = len; switch (proto) { case IPPROTO_IPIP: case IPPROTO_IPV6: - olen = len; break; case IPPROTO_GRE: - olen = len + 4 /* gre hdr */; + olen += sizeof(struct gre_hdr); + if (bpf_skb_load_bytes(skb, off + len, &greh, sizeof(greh)) < 0) + return TC_ACT_OK; + switch (bpf_ntohs(greh.protocol)) { + case ETH_P_MPLS_UC: + olen += sizeof(mpls_label); + break; + case ETH_P_TEB: + olen += ETH_HLEN; + break; + } + break; + case IPPROTO_UDP: + olen += sizeof(struct udphdr); + if (bpf_skb_load_bytes(skb, off + len, &udph, sizeof(udph)) < 0) + return TC_ACT_OK; + switch (bpf_ntohs(udph.dest)) { + case MPLS_OVER_UDP_PORT: + olen += sizeof(mpls_label); + break; + case ETH_OVER_UDP_PORT: + olen += ETH_HLEN; + break; + } break; default: return TC_ACT_OK; diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale1.c b/tools/testing/selftests/bpf/progs/test_verif_scale1.c new file mode 100644 index 000000000000..f3236ce35f31 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_verif_scale1.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include "bpf_helpers.h" +#define ATTR __attribute__((noinline)) +#include "test_jhash.h" + +SEC("scale90_noinline") +int balancer_ingress(struct __sk_buff *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + void *ptr; + int ret = 0, nh_off, i = 0; + + nh_off = 14; + + /* pragma unroll doesn't work on large loops */ + +#define C do { \ + ptr = data + i; \ + if (ptr + nh_off > data_end) \ + break; \ + ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \ + } while (0); +#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C; + C30;C30;C30; /* 90 calls */ + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale2.c b/tools/testing/selftests/bpf/progs/test_verif_scale2.c new file mode 100644 index 000000000000..77830693eccb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_verif_scale2.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include "bpf_helpers.h" +#define ATTR __attribute__((always_inline)) +#include "test_jhash.h" + +SEC("scale90_inline") +int balancer_ingress(struct __sk_buff *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + void *ptr; + int ret = 0, nh_off, i = 0; + + nh_off = 14; + + /* pragma unroll doesn't work on large loops */ + +#define C do { \ + ptr = data + i; \ + if (ptr + nh_off > data_end) \ + break; \ + ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \ + } while (0); +#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C; + C30;C30;C30; /* 90 calls */ + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale3.c b/tools/testing/selftests/bpf/progs/test_verif_scale3.c new file mode 100644 index 000000000000..1848da04ea41 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_verif_scale3.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include "bpf_helpers.h" +#define ATTR __attribute__((noinline)) +#include "test_jhash.h" + +SEC("scale90_noinline32") +int balancer_ingress(struct __sk_buff *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + void *ptr; + int ret = 0, nh_off, i = 0; + + nh_off = 32; + + /* pragma unroll doesn't work on large loops */ + +#define C do { \ + ptr = data + i; \ + if (ptr + nh_off > data_end) \ + break; \ + ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \ + } while (0); +#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C; + C30;C30;C30; /* 90 calls */ + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 23e3b314ca60..44cd3378d216 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -85,6 +85,11 @@ static int __base_pr(enum libbpf_print_level level __attribute__((unused)), #define BTF_UNION_ENC(name, nr_elems, sz) \ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_UNION, 0, nr_elems), sz) +#define BTF_VAR_ENC(name, type, linkage) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), type), (linkage) +#define BTF_VAR_SECINFO_ENC(type, offset, size) \ + (type), (offset), (size) + #define BTF_MEMBER_ENC(name, type, bits_offset) \ (name), (type), (bits_offset) #define BTF_ENUM_ENC(name, val) (name), (val) @@ -291,7 +296,6 @@ static struct btf_raw_test raw_tests[] = { .value_type_id = 3, .max_entries = 4, }, - { .descr = "struct test #3 Invalid member offset", .raw_types = { @@ -319,7 +323,664 @@ static struct btf_raw_test raw_tests[] = { .btf_load_err = true, .err_str = "Invalid member bits_offset", }, - +/* + * struct A { + * unsigned long long m; + * int n; + * char o; + * [3 bytes hole] + * int p[8]; + * }; + */ +{ + .descr = "global data test #1", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* unsigned long long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + /* char */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */ + /* int[8] */ + BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */ + /* struct A { */ /* [5] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48), + BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/ + BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */ + BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */ + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0o\0p", + .str_sec_size = sizeof("\0A\0m\0n\0o\0p"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "struct_test1_map", + .key_size = sizeof(int), + .value_size = 48, + .key_type_id = 1, + .value_type_id = 5, + .max_entries = 4, +}, +/* + * struct A { + * unsigned long long m; + * int n; + * char o; + * [3 bytes hole] + * int p[8]; + * }; + * static struct A t; <- in .bss + */ +{ + .descr = "global data test #2", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* unsigned long long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + /* char */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */ + /* int[8] */ + BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */ + /* struct A { */ /* [5] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48), + BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/ + BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */ + BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */ + /* } */ + /* static struct A t */ + BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */ + /* .bss section */ /* [7] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 48), + BTF_VAR_SECINFO_ENC(6, 0, 48), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0o\0p\0t\0.bss", + .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0.bss"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 48, + .key_type_id = 0, + .value_type_id = 7, + .max_entries = 1, +}, +{ + .descr = "global data test #3", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* static int t */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + /* .bss section */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(2, 0, 4), + BTF_END_RAW, + }, + .str_sec = "\0t\0.bss", + .str_sec_size = sizeof("\0t\0.bss"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 0, + .value_type_id = 3, + .max_entries = 1, +}, +{ + .descr = "global data test #4, unsupported linkage", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* static int t */ + BTF_VAR_ENC(NAME_TBD, 1, 2), /* [2] */ + /* .bss section */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(2, 0, 4), + BTF_END_RAW, + }, + .str_sec = "\0t\0.bss", + .str_sec_size = sizeof("\0t\0.bss"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 0, + .value_type_id = 3, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Linkage not supported", +}, +{ + .descr = "global data test #5, invalid var type", + .raw_types = { + /* static void t */ + BTF_VAR_ENC(NAME_TBD, 0, 0), /* [1] */ + /* .bss section */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(1, 0, 4), + BTF_END_RAW, + }, + .str_sec = "\0t\0.bss", + .str_sec_size = sizeof("\0t\0.bss"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 0, + .value_type_id = 2, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid type_id", +}, +{ + .descr = "global data test #6, invalid var type (fwd type)", + .raw_types = { + /* union A */ + BTF_TYPE_ENC(NAME_TBD, + BTF_INFO_ENC(BTF_KIND_FWD, 1, 0), 0), /* [1] */ + /* static union A t */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + /* .bss section */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(2, 0, 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0t\0.bss", + .str_sec_size = sizeof("\0A\0t\0.bss"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 0, + .value_type_id = 2, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid type", +}, +{ + .descr = "global data test #7, invalid var type (fwd type)", + .raw_types = { + /* union A */ + BTF_TYPE_ENC(NAME_TBD, + BTF_INFO_ENC(BTF_KIND_FWD, 1, 0), 0), /* [1] */ + /* static union A t */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + /* .bss section */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(1, 0, 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0t\0.bss", + .str_sec_size = sizeof("\0A\0t\0.bss"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 0, + .value_type_id = 2, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid type", +}, +{ + .descr = "global data test #8, invalid var size", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* unsigned long long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + /* char */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */ + /* int[8] */ + BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */ + /* struct A { */ /* [5] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48), + BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/ + BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */ + BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */ + /* } */ + /* static struct A t */ + BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */ + /* .bss section */ /* [7] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 48), + BTF_VAR_SECINFO_ENC(6, 0, 47), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0o\0p\0t\0.bss", + .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0.bss"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 48, + .key_type_id = 0, + .value_type_id = 7, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid size", +}, +{ + .descr = "global data test #9, invalid var size", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* unsigned long long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + /* char */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */ + /* int[8] */ + BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */ + /* struct A { */ /* [5] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48), + BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/ + BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */ + BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */ + /* } */ + /* static struct A t */ + BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */ + /* .bss section */ /* [7] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 46), + BTF_VAR_SECINFO_ENC(6, 0, 48), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0o\0p\0t\0.bss", + .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0.bss"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 48, + .key_type_id = 0, + .value_type_id = 7, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid size", +}, +{ + .descr = "global data test #10, invalid var size", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* unsigned long long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + /* char */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */ + /* int[8] */ + BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */ + /* struct A { */ /* [5] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48), + BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/ + BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */ + BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */ + /* } */ + /* static struct A t */ + BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */ + /* .bss section */ /* [7] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 46), + BTF_VAR_SECINFO_ENC(6, 0, 46), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0o\0p\0t\0.bss", + .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0.bss"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 48, + .key_type_id = 0, + .value_type_id = 7, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid size", +}, +{ + .descr = "global data test #11, multiple section members", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* unsigned long long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + /* char */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */ + /* int[8] */ + BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */ + /* struct A { */ /* [5] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48), + BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/ + BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */ + BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */ + /* } */ + /* static struct A t */ + BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */ + /* static int u */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [7] */ + /* .bss section */ /* [8] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 2), 62), + BTF_VAR_SECINFO_ENC(6, 10, 48), + BTF_VAR_SECINFO_ENC(7, 58, 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0o\0p\0t\0u\0.bss", + .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0u\0.bss"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 62, + .key_type_id = 0, + .value_type_id = 8, + .max_entries = 1, +}, +{ + .descr = "global data test #12, invalid offset", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* unsigned long long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + /* char */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */ + /* int[8] */ + BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */ + /* struct A { */ /* [5] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48), + BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/ + BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */ + BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */ + /* } */ + /* static struct A t */ + BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */ + /* static int u */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [7] */ + /* .bss section */ /* [8] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 2), 62), + BTF_VAR_SECINFO_ENC(6, 10, 48), + BTF_VAR_SECINFO_ENC(7, 60, 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0o\0p\0t\0u\0.bss", + .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0u\0.bss"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 62, + .key_type_id = 0, + .value_type_id = 8, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid offset+size", +}, +{ + .descr = "global data test #13, invalid offset", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* unsigned long long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + /* char */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */ + /* int[8] */ + BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */ + /* struct A { */ /* [5] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48), + BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/ + BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */ + BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */ + /* } */ + /* static struct A t */ + BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */ + /* static int u */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [7] */ + /* .bss section */ /* [8] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 2), 62), + BTF_VAR_SECINFO_ENC(6, 10, 48), + BTF_VAR_SECINFO_ENC(7, 12, 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0o\0p\0t\0u\0.bss", + .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0u\0.bss"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 62, + .key_type_id = 0, + .value_type_id = 8, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid offset", +}, +{ + .descr = "global data test #14, invalid offset", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* unsigned long long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + /* char */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */ + /* int[8] */ + BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */ + /* struct A { */ /* [5] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48), + BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/ + BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */ + BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */ + /* } */ + /* static struct A t */ + BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */ + /* static int u */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [7] */ + /* .bss section */ /* [8] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 2), 62), + BTF_VAR_SECINFO_ENC(7, 58, 4), + BTF_VAR_SECINFO_ENC(6, 10, 48), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0o\0p\0t\0u\0.bss", + .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0u\0.bss"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 62, + .key_type_id = 0, + .value_type_id = 8, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid offset", +}, +{ + .descr = "global data test #15, not var kind", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + /* .bss section */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(1, 0, 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0t\0.bss", + .str_sec_size = sizeof("\0A\0t\0.bss"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 0, + .value_type_id = 3, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Not a VAR kind member", +}, +{ + .descr = "global data test #16, invalid var referencing sec", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 5, 0), /* [2] */ + BTF_VAR_ENC(NAME_TBD, 2, 0), /* [3] */ + /* a section */ /* [4] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(3, 0, 4), + /* a section */ /* [5] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(6, 0, 4), + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [6] */ + BTF_END_RAW, + }, + .str_sec = "\0A\0t\0s\0a\0a", + .str_sec_size = sizeof("\0A\0t\0s\0a\0a"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 0, + .value_type_id = 4, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid type_id", +}, +{ + .descr = "global data test #17, invalid var referencing var", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_VAR_ENC(NAME_TBD, 2, 0), /* [3] */ + /* a section */ /* [4] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(3, 0, 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0t\0s\0a\0a", + .str_sec_size = sizeof("\0A\0t\0s\0a\0a"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 0, + .value_type_id = 4, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid type_id", +}, +{ + .descr = "global data test #18, invalid var loop", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 2, 0), /* [2] */ + /* .bss section */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(2, 0, 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0t\0aaa", + .str_sec_size = sizeof("\0A\0t\0aaa"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 0, + .value_type_id = 4, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid type_id", +}, +{ + .descr = "global data test #19, invalid var referencing var", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 3, 0), /* [2] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [3] */ + BTF_END_RAW, + }, + .str_sec = "\0A\0t\0s\0a\0a", + .str_sec_size = sizeof("\0A\0t\0s\0a\0a"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 0, + .value_type_id = 4, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid type_id", +}, +{ + .descr = "global data test #20, invalid ptr referencing var", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* PTR type_id=3 */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3), + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [3] */ + BTF_END_RAW, + }, + .str_sec = "\0A\0t\0s\0a\0a", + .str_sec_size = sizeof("\0A\0t\0s\0a\0a"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 0, + .value_type_id = 4, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid type_id", +}, +{ + .descr = "global data test #21, var included in struct", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* struct A { */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 2), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 32),/* VAR type_id=3; */ + /* } */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [3] */ + BTF_END_RAW, + }, + .str_sec = "\0A\0t\0s\0a\0a", + .str_sec_size = sizeof("\0A\0t\0s\0a\0a"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 0, + .value_type_id = 4, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid member", +}, +{ + .descr = "global data test #22, array of var", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_ARRAY_ENC(3, 1, 4), /* [2] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [3] */ + BTF_END_RAW, + }, + .str_sec = "\0A\0t\0s\0a\0a", + .str_sec_size = sizeof("\0A\0t\0s\0a\0a"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 0, + .value_type_id = 4, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid elem", +}, /* Test member exceeds the size of struct. * * struct A { @@ -3677,6 +4338,7 @@ struct pprint_mapv { } aenum; uint32_t ui32b; uint32_t bits2c:2; + uint8_t si8_4[2][2]; }; #ifdef __SIZEOF_INT128__ @@ -3729,7 +4391,7 @@ static struct btf_raw_test pprint_test_template[] = { BTF_ENUM_ENC(NAME_TBD, 2), BTF_ENUM_ENC(NAME_TBD, 3), /* struct pprint_mapv */ /* [16] */ - BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 10), 40), + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 11), 40), BTF_MEMBER_ENC(NAME_TBD, 11, 0), /* uint32_t ui32 */ BTF_MEMBER_ENC(NAME_TBD, 10, 32), /* uint16_t ui16 */ BTF_MEMBER_ENC(NAME_TBD, 12, 64), /* int32_t si32 */ @@ -3740,9 +4402,12 @@ static struct btf_raw_test pprint_test_template[] = { BTF_MEMBER_ENC(NAME_TBD, 15, 192), /* aenum */ BTF_MEMBER_ENC(NAME_TBD, 11, 224), /* uint32_t ui32b */ BTF_MEMBER_ENC(NAME_TBD, 6, 256), /* bits2c */ + BTF_MEMBER_ENC(NAME_TBD, 17, 264), /* si8_4 */ + BTF_TYPE_ARRAY_ENC(18, 1, 2), /* [17] */ + BTF_TYPE_ARRAY_ENC(1, 1, 2), /* [18] */ BTF_END_RAW, }, - BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c"), + BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c\0si8_4"), .key_size = sizeof(unsigned int), .value_size = sizeof(struct pprint_mapv), .key_type_id = 3, /* unsigned int */ @@ -3791,7 +4456,7 @@ static struct btf_raw_test pprint_test_template[] = { BTF_ENUM_ENC(NAME_TBD, 2), BTF_ENUM_ENC(NAME_TBD, 3), /* struct pprint_mapv */ /* [16] */ - BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 10), 40), + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 11), 40), BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 0)), /* uint32_t ui32 */ BTF_MEMBER_ENC(NAME_TBD, 10, BTF_MEMBER_OFFSET(0, 32)), /* uint16_t ui16 */ BTF_MEMBER_ENC(NAME_TBD, 12, BTF_MEMBER_OFFSET(0, 64)), /* int32_t si32 */ @@ -3802,9 +4467,12 @@ static struct btf_raw_test pprint_test_template[] = { BTF_MEMBER_ENC(NAME_TBD, 15, BTF_MEMBER_OFFSET(0, 192)), /* aenum */ BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 224)), /* uint32_t ui32b */ BTF_MEMBER_ENC(NAME_TBD, 6, BTF_MEMBER_OFFSET(2, 256)), /* bits2c */ + BTF_MEMBER_ENC(NAME_TBD, 17, 264), /* si8_4 */ + BTF_TYPE_ARRAY_ENC(18, 1, 2), /* [17] */ + BTF_TYPE_ARRAY_ENC(1, 1, 2), /* [18] */ BTF_END_RAW, }, - BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c"), + BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c\0si8_4"), .key_size = sizeof(unsigned int), .value_size = sizeof(struct pprint_mapv), .key_type_id = 3, /* unsigned int */ @@ -3855,7 +4523,7 @@ static struct btf_raw_test pprint_test_template[] = { BTF_ENUM_ENC(NAME_TBD, 2), BTF_ENUM_ENC(NAME_TBD, 3), /* struct pprint_mapv */ /* [16] */ - BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 10), 40), + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 11), 40), BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 0)), /* uint32_t ui32 */ BTF_MEMBER_ENC(NAME_TBD, 10, BTF_MEMBER_OFFSET(0, 32)), /* uint16_t ui16 */ BTF_MEMBER_ENC(NAME_TBD, 12, BTF_MEMBER_OFFSET(0, 64)), /* int32_t si32 */ @@ -3866,13 +4534,16 @@ static struct btf_raw_test pprint_test_template[] = { BTF_MEMBER_ENC(NAME_TBD, 15, BTF_MEMBER_OFFSET(0, 192)), /* aenum */ BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 224)), /* uint32_t ui32b */ BTF_MEMBER_ENC(NAME_TBD, 17, BTF_MEMBER_OFFSET(2, 256)), /* bits2c */ + BTF_MEMBER_ENC(NAME_TBD, 20, BTF_MEMBER_OFFSET(0, 264)), /* si8_4 */ /* typedef unsigned int ___int */ /* [17] */ BTF_TYPEDEF_ENC(NAME_TBD, 18), BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_VOLATILE, 0, 0), 6), /* [18] */ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 15), /* [19] */ + BTF_TYPE_ARRAY_ENC(21, 1, 2), /* [20] */ + BTF_TYPE_ARRAY_ENC(1, 1, 2), /* [21] */ BTF_END_RAW, }, - BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c\0___int"), + BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c\0___int\0si8_4"), .key_size = sizeof(unsigned int), .value_size = sizeof(struct pprint_mapv), .key_type_id = 3, /* unsigned int */ @@ -4007,6 +4678,10 @@ static void set_pprint_mapv(enum pprint_mapv_kind_t mapv_kind, v->aenum = i & 0x03; v->ui32b = 4; v->bits2c = 1; + v->si8_4[0][0] = (cpu + i) & 0xff; + v->si8_4[0][1] = (cpu + i + 1) & 0xff; + v->si8_4[1][0] = (cpu + i + 2) & 0xff; + v->si8_4[1][1] = (cpu + i + 3) & 0xff; v = (void *)v + rounded_value_size; } } @@ -4040,7 +4715,7 @@ ssize_t get_pprint_expected_line(enum pprint_mapv_kind_t mapv_kind, nexpected_line = snprintf(expected_line, line_size, "%s%u: {%u,0,%d,0x%x,0x%x,0x%x," "{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s," - "%u,0x%x}\n", + "%u,0x%x,[[%d,%d],[%d,%d]]}\n", percpu_map ? "\tcpu" : "", percpu_map ? cpu : next_key, v->ui32, v->si32, @@ -4054,7 +4729,9 @@ ssize_t get_pprint_expected_line(enum pprint_mapv_kind_t mapv_kind, v->ui8a[6], v->ui8a[7], pprint_enum_str[v->aenum], v->ui32b, - v->bits2c); + v->bits2c, + v->si8_4[0][0], v->si8_4[0][1], + v->si8_4[1][0], v->si8_4[1][1]); } #ifdef __SIZEOF_INT128__ @@ -5777,6 +6454,53 @@ const struct btf_dedup_test dedup_tests[] = { }, }, { + .descr = "dedup: void equiv check", + /* + * // CU 1: + * struct s { + * struct {} *x; + * }; + * // CU 2: + * struct s { + * int *x; + * }; + */ + .input = { + .raw_types = { + /* CU 1 */ + BTF_STRUCT_ENC(0, 0, 1), /* [1] struct {} */ + BTF_PTR_ENC(1), /* [2] ptr -> [1] */ + BTF_STRUCT_ENC(NAME_NTH(1), 1, 8), /* [3] struct s */ + BTF_MEMBER_ENC(NAME_NTH(2), 2, 0), + /* CU 2 */ + BTF_PTR_ENC(0), /* [4] ptr -> void */ + BTF_STRUCT_ENC(NAME_NTH(1), 1, 8), /* [5] struct s */ + BTF_MEMBER_ENC(NAME_NTH(2), 4, 0), + BTF_END_RAW, + }, + BTF_STR_SEC("\0s\0x"), + }, + .expect = { + .raw_types = { + /* CU 1 */ + BTF_STRUCT_ENC(0, 0, 1), /* [1] struct {} */ + BTF_PTR_ENC(1), /* [2] ptr -> [1] */ + BTF_STRUCT_ENC(NAME_NTH(1), 1, 8), /* [3] struct s */ + BTF_MEMBER_ENC(NAME_NTH(2), 2, 0), + /* CU 2 */ + BTF_PTR_ENC(0), /* [4] ptr -> void */ + BTF_STRUCT_ENC(NAME_NTH(1), 1, 8), /* [5] struct s */ + BTF_MEMBER_ENC(NAME_NTH(2), 4, 0), + BTF_END_RAW, + }, + BTF_STR_SEC("\0s\0x"), + }, + .opts = { + .dont_resolve_fwds = false, + .dedup_table_size = 1, /* force hash collisions */ + }, +}, +{ .descr = "dedup: all possible kinds (no duplicates)", .input = { .raw_types = { diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 84bea3985d64..a7f95106119f 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -1055,7 +1055,7 @@ try: start_test("Test if netdev removal waits for translation...") delay_msec = 500 - sim.dfs["bpf_bind_verifier_delay"] = delay_msec + sim.dfs["sdev/bpf_bind_verifier_delay"] = delay_msec start = time.time() cmd_line = "tc filter add dev %s ingress bpf %s da skip_sw" % \ (sim['ifname'], obj) diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 5d10aee9e277..bf5c90998916 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -9,6 +9,7 @@ int error_cnt, pass_cnt; bool jit_enabled; +bool verifier_stats = false; struct ipv4_packet pkt_v4 = { .eth.h_proto = __bpf_constant_htons(ETH_P_IP), @@ -162,12 +163,15 @@ void *spin_lock_thread(void *arg) #include <prog_tests/tests.h> #undef DECLARE -int main(void) +int main(int ac, char **av) { srand(time(NULL)); jit_enabled = is_jit_enabled(); + if (ac == 2 && strcmp(av[1], "-s") == 0) + verifier_stats = true; + #define CALL #include <prog_tests/tests.h> #undef CALL diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 51a07367cd43..f095e1d4c657 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -40,6 +40,7 @@ typedef __u16 __sum16; extern int error_cnt, pass_cnt; extern bool jit_enabled; +extern bool verifier_stats; #define MAGIC_BYTES 123 diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh index c805adb88f3a..d4d8d5d3b06e 100755 --- a/tools/testing/selftests/bpf/test_tc_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh @@ -15,6 +15,12 @@ readonly ns2_v4=192.168.1.2 readonly ns1_v6=fd::1 readonly ns2_v6=fd::2 +# Must match port used by bpf program +readonly udpport=5555 +# MPLSoverUDP +readonly mplsudpport=6635 +readonly mplsproto=137 + readonly infile="$(mktemp)" readonly outfile="$(mktemp)" @@ -38,8 +44,8 @@ setup() { # clamp route to reserve room for tunnel headers ip -netns "${ns1}" -4 route flush table main ip -netns "${ns1}" -6 route flush table main - ip -netns "${ns1}" -4 route add "${ns2_v4}" mtu 1476 dev veth1 - ip -netns "${ns1}" -6 route add "${ns2_v6}" mtu 1456 dev veth1 + ip -netns "${ns1}" -4 route add "${ns2_v4}" mtu 1458 dev veth1 + ip -netns "${ns1}" -6 route add "${ns2_v6}" mtu 1438 dev veth1 sleep 1 @@ -86,30 +92,44 @@ set -e # no arguments: automated test, run all if [[ "$#" -eq "0" ]]; then echo "ipip" - $0 ipv4 ipip 100 + $0 ipv4 ipip none 100 echo "ip6ip6" - $0 ipv6 ip6tnl 100 + $0 ipv6 ip6tnl none 100 + + for mac in none mpls eth ; do + echo "ip gre $mac" + $0 ipv4 gre $mac 100 + + echo "ip6 gre $mac" + $0 ipv6 ip6gre $mac 100 + + echo "ip gre $mac gso" + $0 ipv4 gre $mac 2000 - echo "ip gre" - $0 ipv4 gre 100 + echo "ip6 gre $mac gso" + $0 ipv6 ip6gre $mac 2000 - echo "ip6 gre" - $0 ipv6 ip6gre 100 + echo "ip udp $mac" + $0 ipv4 udp $mac 100 - echo "ip gre gso" - $0 ipv4 gre 2000 + echo "ip6 udp $mac" + $0 ipv6 ip6udp $mac 100 - echo "ip6 gre gso" - $0 ipv6 ip6gre 2000 + echo "ip udp $mac gso" + $0 ipv4 udp $mac 2000 + + echo "ip6 udp $mac gso" + $0 ipv6 ip6udp $mac 2000 + done echo "OK. All tests passed" exit 0 fi -if [[ "$#" -ne "3" ]]; then +if [[ "$#" -ne "4" ]]; then echo "Usage: $0" - echo " or: $0 <ipv4|ipv6> <tuntype> <data_len>" + echo " or: $0 <ipv4|ipv6> <tuntype> <none|mpls|eth> <data_len>" exit 1 fi @@ -117,12 +137,24 @@ case "$1" in "ipv4") readonly addr1="${ns1_v4}" readonly addr2="${ns2_v4}" - readonly netcat_opt=-4 + readonly ipproto=4 + readonly netcat_opt=-${ipproto} + readonly foumod=fou + readonly foutype=ipip + readonly fouproto=4 + readonly fouproto_mpls=${mplsproto} + readonly gretaptype=gretap ;; "ipv6") readonly addr1="${ns1_v6}" readonly addr2="${ns2_v6}" - readonly netcat_opt=-6 + readonly ipproto=6 + readonly netcat_opt=-${ipproto} + readonly foumod=fou6 + readonly foutype=ip6tnl + readonly fouproto="41 -6" + readonly fouproto_mpls="${mplsproto} -6" + readonly gretaptype=ip6gretap ;; *) echo "unknown arg: $1" @@ -131,9 +163,10 @@ case "$1" in esac readonly tuntype=$2 -readonly datalen=$3 +readonly mac=$3 +readonly datalen=$4 -echo "encap ${addr1} to ${addr2}, type ${tuntype}, len ${datalen}" +echo "encap ${addr1} to ${addr2}, type ${tuntype}, mac ${mac} len ${datalen}" trap cleanup EXIT @@ -150,16 +183,63 @@ verify_data ip netns exec "${ns1}" tc qdisc add dev veth1 clsact ip netns exec "${ns1}" tc filter add dev veth1 egress \ bpf direct-action object-file ./test_tc_tunnel.o \ - section "encap_${tuntype}" + section "encap_${tuntype}_${mac}" echo "test bpf encap without decap (expect failure)" server_listen ! client_connect +if [[ "$tuntype" =~ "udp" ]]; then + # Set up fou tunnel. + ttype="${foutype}" + targs="encap fou encap-sport auto encap-dport $udpport" + # fou may be a module; allow this to fail. + modprobe "${foumod}" ||true + if [[ "$mac" == "mpls" ]]; then + dport=${mplsudpport} + dproto=${fouproto_mpls} + tmode="mode any ttl 255" + else + dport=${udpport} + dproto=${fouproto} + fi + ip netns exec "${ns2}" ip fou add port $dport ipproto ${dproto} + targs="encap fou encap-sport auto encap-dport $dport" +elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then + ttype=$gretaptype +else + ttype=$tuntype + targs="" +fi + # serverside, insert decap module # server is still running # client can connect again -ip netns exec "${ns2}" ip link add dev testtun0 type "${tuntype}" \ - remote "${addr1}" local "${addr2}" +ip netns exec "${ns2}" ip link add name testtun0 type "${ttype}" \ + ${tmode} remote "${addr1}" local "${addr2}" $targs + +expect_tun_fail=0 + +if [[ "$tuntype" == "ip6udp" && "$mac" == "mpls" ]]; then + # No support for MPLS IPv6 fou tunnel; expect failure. + expect_tun_fail=1 +elif [[ "$tuntype" =~ "udp" && "$mac" == "eth" ]]; then + # No support for TEB fou tunnel; expect failure. + expect_tun_fail=1 +elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then + # Share ethernet address between tunnel/veth2 so L2 decap works. + ethaddr=$(ip netns exec "${ns2}" ip link show veth2 | \ + awk '/ether/ { print $2 }') + ip netns exec "${ns2}" ip link set testtun0 address $ethaddr +elif [[ "$mac" == "mpls" ]]; then + modprobe mpls_iptunnel ||true + modprobe mpls_gso ||true + ip netns exec "${ns2}" sysctl -qw net.mpls.platform_labels=65536 + ip netns exec "${ns2}" ip -f mpls route add 1000 dev lo + ip netns exec "${ns2}" ip link set lo up + ip netns exec "${ns2}" sysctl -qw net.mpls.conf.testtun0.input=1 + ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.lo.rp_filter=0 +fi + # Because packets are decapped by the tunnel they arrive on testtun0 from # the IP stack perspective. Ensure reverse path filtering is disabled # otherwise we drop the TCP SYN as arriving on testtun0 instead of the @@ -169,16 +249,22 @@ ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.rp_filter=0 # selected as the max of the "all" and device-specific values. ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.testtun0.rp_filter=0 ip netns exec "${ns2}" ip link set dev testtun0 up -echo "test bpf encap with tunnel device decap" -client_connect -verify_data +if [[ "$expect_tun_fail" == 1 ]]; then + # This tunnel mode is not supported, so we expect failure. + echo "test bpf encap with tunnel device decap (expect failure)" + ! client_connect +else + echo "test bpf encap with tunnel device decap" + client_connect + verify_data + server_listen +fi # serverside, use BPF for decap ip netns exec "${ns2}" ip link del dev testtun0 ip netns exec "${ns2}" tc qdisc add dev veth2 clsact ip netns exec "${ns2}" tc filter add dev veth2 ingress \ bpf direct-action object-file ./test_tc_tunnel.o section decap -server_listen echo "test bpf encap with bpf decap" client_connect verify_data diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 19b5d03acc2a..e2ebcaddbe78 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -50,8 +50,9 @@ #include "../../../include/linux/filter.h" #define MAX_INSNS BPF_MAXINSNS +#define MAX_TEST_INSNS 1000000 #define MAX_FIXUPS 8 -#define MAX_NR_MAPS 14 +#define MAX_NR_MAPS 16 #define MAX_TEST_RUNS 8 #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 @@ -66,6 +67,7 @@ static int skips; struct bpf_test { const char *descr; struct bpf_insn insns[MAX_INSNS]; + struct bpf_insn *fill_insns; int fixup_map_hash_8b[MAX_FIXUPS]; int fixup_map_hash_48b[MAX_FIXUPS]; int fixup_map_hash_16b[MAX_FIXUPS]; @@ -80,9 +82,13 @@ struct bpf_test { int fixup_cgroup_storage[MAX_FIXUPS]; int fixup_percpu_cgroup_storage[MAX_FIXUPS]; int fixup_map_spin_lock[MAX_FIXUPS]; + int fixup_map_array_ro[MAX_FIXUPS]; + int fixup_map_array_wo[MAX_FIXUPS]; + int fixup_map_array_small[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; uint32_t retval, retval_unpriv, insn_processed; + int prog_len; enum { UNDEF, ACCEPT, @@ -119,10 +125,11 @@ struct other_val { static void bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self) { - /* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */ + /* test: {skb->data[0], vlan_push} x 51 + {skb->data[0], vlan_pop} x 51 */ #define PUSH_CNT 51 - unsigned int len = BPF_MAXINSNS; - struct bpf_insn *insn = self->insns; + /* jump range is limited to 16 bit. PUSH_CNT of ld_abs needs room */ + unsigned int len = (1 << 15) - PUSH_CNT * 2 * 5 * 6; + struct bpf_insn *insn = self->fill_insns; int i = 0, j, k = 0; insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); @@ -156,12 +163,14 @@ loop: for (; i < len - 1; i++) insn[i] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 0xbef); insn[len - 1] = BPF_EXIT_INSN(); + self->prog_len = len; } static void bpf_fill_jump_around_ld_abs(struct bpf_test *self) { - struct bpf_insn *insn = self->insns; - unsigned int len = BPF_MAXINSNS; + struct bpf_insn *insn = self->fill_insns; + /* jump range is limited to 16 bit. every ld_abs is replaced by 6 insns */ + unsigned int len = (1 << 15) / 6; int i = 0; insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); @@ -171,11 +180,12 @@ static void bpf_fill_jump_around_ld_abs(struct bpf_test *self) while (i < len - 1) insn[i++] = BPF_LD_ABS(BPF_B, 1); insn[i] = BPF_EXIT_INSN(); + self->prog_len = i + 1; } static void bpf_fill_rand_ld_dw(struct bpf_test *self) { - struct bpf_insn *insn = self->insns; + struct bpf_insn *insn = self->fill_insns; uint64_t res = 0; int i = 0; @@ -193,6 +203,7 @@ static void bpf_fill_rand_ld_dw(struct bpf_test *self) insn[i++] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 32); insn[i++] = BPF_ALU64_REG(BPF_XOR, BPF_REG_0, BPF_REG_1); insn[i] = BPF_EXIT_INSN(); + self->prog_len = i + 1; res ^= (res >> 32); self->retval = (uint32_t)res; } @@ -277,13 +288,15 @@ static bool skip_unsupported_map(enum bpf_map_type map_type) return false; } -static int create_map(uint32_t type, uint32_t size_key, - uint32_t size_value, uint32_t max_elem) +static int __create_map(uint32_t type, uint32_t size_key, + uint32_t size_value, uint32_t max_elem, + uint32_t extra_flags) { int fd; fd = bpf_create_map(type, size_key, size_value, max_elem, - type == BPF_MAP_TYPE_HASH ? BPF_F_NO_PREALLOC : 0); + (type == BPF_MAP_TYPE_HASH ? + BPF_F_NO_PREALLOC : 0) | extra_flags); if (fd < 0) { if (skip_unsupported_map(type)) return -1; @@ -293,6 +306,12 @@ static int create_map(uint32_t type, uint32_t size_key, return fd; } +static int create_map(uint32_t type, uint32_t size_key, + uint32_t size_value, uint32_t max_elem) +{ + return __create_map(type, size_key, size_value, max_elem, 0); +} + static void update_map(int fd, int index) { struct test_val value = { @@ -519,9 +538,14 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_cgroup_storage = test->fixup_cgroup_storage; int *fixup_percpu_cgroup_storage = test->fixup_percpu_cgroup_storage; int *fixup_map_spin_lock = test->fixup_map_spin_lock; + int *fixup_map_array_ro = test->fixup_map_array_ro; + int *fixup_map_array_wo = test->fixup_map_array_wo; + int *fixup_map_array_small = test->fixup_map_array_small; - if (test->fill_helper) + if (test->fill_helper) { + test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); test->fill_helper(test); + } /* Allocating HTs with 1 elem is fine here, since we only test * for verifier and not do a runtime lookup, so the only thing @@ -642,6 +666,35 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_map_spin_lock++; } while (*fixup_map_spin_lock); } + if (*fixup_map_array_ro) { + map_fds[14] = __create_map(BPF_MAP_TYPE_ARRAY, sizeof(int), + sizeof(struct test_val), 1, + BPF_F_RDONLY_PROG); + update_map(map_fds[14], 0); + do { + prog[*fixup_map_array_ro].imm = map_fds[14]; + fixup_map_array_ro++; + } while (*fixup_map_array_ro); + } + if (*fixup_map_array_wo) { + map_fds[15] = __create_map(BPF_MAP_TYPE_ARRAY, sizeof(int), + sizeof(struct test_val), 1, + BPF_F_WRONLY_PROG); + update_map(map_fds[15], 0); + do { + prog[*fixup_map_array_wo].imm = map_fds[15]; + fixup_map_array_wo++; + } while (*fixup_map_array_wo); + } + if (*fixup_map_array_small) { + map_fds[16] = __create_map(BPF_MAP_TYPE_ARRAY, sizeof(int), + 1, 1, 0); + update_map(map_fds[16], 0); + do { + prog[*fixup_map_array_small].imm = map_fds[16]; + fixup_map_array_small++; + } while (*fixup_map_array_small); + } } static int set_admin(bool admin) @@ -718,12 +771,17 @@ static void do_test_single(struct bpf_test *test, bool unpriv, prog_type = BPF_PROG_TYPE_SOCKET_FILTER; fixup_skips = skips; do_test_fixup(test, prog_type, prog, map_fds); + if (test->fill_insns) { + prog = test->fill_insns; + prog_len = test->prog_len; + } else { + prog_len = probe_filter_length(prog); + } /* If there were some map skips during fixup due to missing bpf * features, skip this test. */ if (fixup_skips != skips) return; - prog_len = probe_filter_length(prog); pflags = 0; if (test->flags & F_LOAD_WITH_STRICT_ALIGNMENT) @@ -731,7 +789,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) pflags |= BPF_F_ANY_ALIGNMENT; fd_prog = bpf_verify_program(prog_type, prog, prog_len, pflags, - "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 1); + "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 4); if (fd_prog < 0 && !bpf_probe_prog_type(prog_type, 0)) { printf("SKIP (unsupported program type %d)\n", prog_type); skips++; @@ -830,6 +888,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv, goto fail_log; } close_fds: + if (test->fill_insns) + free(test->fill_insns); close(fd_prog); for (i = 0; i < MAX_NR_MAPS; i++) close(map_fds[i]); diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 4cdb63bf0521..9a9fc6c9b70b 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -52,6 +52,10 @@ struct ksym *ksym_search(long key) int start = 0, end = sym_cnt; int result; + /* kallsyms not loaded. return NULL */ + if (sym_cnt <= 0) + return NULL; + while (start < end) { size_t mid = start + (end - start) / 2; diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c index 0dcecaf3ec6f..bcb83196e459 100644 --- a/tools/testing/selftests/bpf/verifier/array_access.c +++ b/tools/testing/selftests/bpf/verifier/array_access.c @@ -217,3 +217,162 @@ .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, +{ + "valid read map access into a read-only array 1", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_ro = { 3 }, + .result = ACCEPT, + .retval = 28, +}, +{ + "valid read map access into a read-only array 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_csum_diff), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_map_array_ro = { 3 }, + .result = ACCEPT, + .retval = -29, +}, +{ + "invalid write map access into a read-only array 1", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42), + BPF_EXIT_INSN(), + }, + .fixup_map_array_ro = { 3 }, + .result = REJECT, + .errstr = "write into map forbidden", +}, +{ + "invalid write map access into a read-only array 2", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_map_array_ro = { 4 }, + .result = REJECT, + .errstr = "write into map forbidden", +}, +{ + "valid write map access into a write-only array 1", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_wo = { 3 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "valid write map access into a write-only array 2", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_map_array_wo = { 4 }, + .result = ACCEPT, + .retval = 0, +}, +{ + "invalid read map access into a write-only array 1", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_wo = { 3 }, + .result = REJECT, + .errstr = "read from map forbidden", +}, +{ + "invalid read map access into a write-only array 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_csum_diff), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_map_array_wo = { 3 }, + .result = REJECT, + .errstr = "read from map forbidden", +}, diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index f2ccae39ee66..fb11240b758b 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -908,6 +908,44 @@ .result = REJECT, }, { + "calls: stack depth check in dead code", + .insns = { + /* main */ + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call A */ + BPF_EXIT_INSN(), + /* A */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 2), /* call B */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + /* B */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call C */ + BPF_EXIT_INSN(), + /* C */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call D */ + BPF_EXIT_INSN(), + /* D */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call E */ + BPF_EXIT_INSN(), + /* E */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call F */ + BPF_EXIT_INSN(), + /* F */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call G */ + BPF_EXIT_INSN(), + /* G */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call H */ + BPF_EXIT_INSN(), + /* H */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_XDP, + .errstr = "call stack", + .result = REJECT, +}, +{ "calls: spill into caller stack frame", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c index c660deb582f1..b0fda2877119 100644 --- a/tools/testing/selftests/bpf/verifier/ctx_skb.c +++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c @@ -705,7 +705,6 @@ .errstr = "invalid bpf_context access", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, - .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "check cb access: half, wrong type", diff --git a/tools/testing/selftests/bpf/verifier/direct_value_access.c b/tools/testing/selftests/bpf/verifier/direct_value_access.c new file mode 100644 index 000000000000..b9fb28e8e224 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/direct_value_access.c @@ -0,0 +1,347 @@ +{ + "direct map access, write test 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 4242), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "direct map access, write test 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 8), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 4242), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "direct map access, write test 3", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 8), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 8, 4242), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "direct map access, write test 4", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 40), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 4242), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "direct map access, write test 5", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 32), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 8, 4242), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "direct map access, write test 6", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 40), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 4, 4242), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = REJECT, + .errstr = "R1 min value is outside of the array range", +}, +{ + "direct map access, write test 7", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, -1), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 4, 4242), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = REJECT, + .errstr = "direct value offset of 4294967295 is not allowed", +}, +{ + "direct map access, write test 8", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_1, -1, 4242), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "direct map access, write test 9", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 48), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 4242), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = REJECT, + .errstr = "invalid access to map value pointer", +}, +{ + "direct map access, write test 10", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 47), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 4), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "direct map access, write test 11", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 48), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 4), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = REJECT, + .errstr = "invalid access to map value pointer", +}, +{ + "direct map access, write test 12", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, (1<<29)), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 4), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = REJECT, + .errstr = "direct value offset of 536870912 is not allowed", +}, +{ + "direct map access, write test 13", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, (1<<29)-1), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 4), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = REJECT, + .errstr = "invalid access to map value pointer, value_size=48 off=536870911", +}, +{ + "direct map access, write test 14", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 47), + BPF_LD_MAP_VALUE(BPF_REG_2, 0, 46), + BPF_ST_MEM(BPF_H, BPF_REG_2, 0, 0xffff), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1, 3 }, + .result = ACCEPT, + .retval = 0xff, +}, +{ + "direct map access, write test 15", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 46), + BPF_LD_MAP_VALUE(BPF_REG_2, 0, 46), + BPF_ST_MEM(BPF_H, BPF_REG_2, 0, 0xffff), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1, 3 }, + .result = ACCEPT, + .retval = 0xffff, +}, +{ + "direct map access, write test 16", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 46), + BPF_LD_MAP_VALUE(BPF_REG_2, 0, 47), + BPF_ST_MEM(BPF_H, BPF_REG_2, 0, 0xffff), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1, 3 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=48 off=47 size=2", +}, +{ + "direct map access, write test 17", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 46), + BPF_LD_MAP_VALUE(BPF_REG_2, 0, 46), + BPF_ST_MEM(BPF_H, BPF_REG_2, 1, 0xffff), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1, 3 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=48 off=47 size=2", +}, +{ + "direct map access, write test 18", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 0), + BPF_ST_MEM(BPF_H, BPF_REG_1, 0, 42), + BPF_EXIT_INSN(), + }, + .fixup_map_array_small = { 1 }, + .result = REJECT, + .errstr = "R1 min value is outside of the array range", +}, +{ + "direct map access, write test 19", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 0), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42), + BPF_EXIT_INSN(), + }, + .fixup_map_array_small = { 1 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "direct map access, write test 20", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 1), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42), + BPF_EXIT_INSN(), + }, + .fixup_map_array_small = { 1 }, + .result = REJECT, + .errstr = "invalid access to map value pointer", +}, +{ + "direct map access, invalid insn test 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, 0, 1, 0, 47), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = REJECT, + .errstr = "invalid bpf_ld_imm64 insn", +}, +{ + "direct map access, invalid insn test 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, 1, 0, 0, 47), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = REJECT, + .errstr = "BPF_LD_IMM64 uses reserved fields", +}, +{ + "direct map access, invalid insn test 3", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, ~0, 0, 0, 47), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = REJECT, + .errstr = "BPF_LD_IMM64 uses reserved fields", +}, +{ + "direct map access, invalid insn test 4", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, 0, ~0, 0, 47), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = REJECT, + .errstr = "invalid bpf_ld_imm64 insn", +}, +{ + "direct map access, invalid insn test 5", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, ~0, ~0, 0, 47), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = REJECT, + .errstr = "invalid bpf_ld_imm64 insn", +}, +{ + "direct map access, invalid insn test 6", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_FD, ~0, 0, 0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = REJECT, + .errstr = "BPF_LD_IMM64 uses reserved fields", +}, +{ + "direct map access, invalid insn test 7", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_FD, 0, ~0, 0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = REJECT, + .errstr = "invalid bpf_ld_imm64 insn", +}, +{ + "direct map access, invalid insn test 8", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_FD, ~0, ~0, 0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = REJECT, + .errstr = "invalid bpf_ld_imm64 insn", +}, +{ + "direct map access, invalid insn test 9", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_FD, 0, 0, 0, 47), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 1 }, + .result = REJECT, + .errstr = "unrecognized bpf_ld_imm64 insn", +}, diff --git a/tools/testing/selftests/bpf/verifier/ld_dw.c b/tools/testing/selftests/bpf/verifier/ld_dw.c index d2c75b889598..0f18e62f0099 100644 --- a/tools/testing/selftests/bpf/verifier/ld_dw.c +++ b/tools/testing/selftests/bpf/verifier/ld_dw.c @@ -34,3 +34,12 @@ .result = ACCEPT, .retval = 5, }, +{ + "ld_dw: xor semi-random 64 bit imms, test 5", + .insns = { }, + .data = { }, + .fill_helper = bpf_fill_rand_ld_dw, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 1000000 - 6, +}, diff --git a/tools/testing/selftests/bpf/verifier/var_off.c b/tools/testing/selftests/bpf/verifier/var_off.c index 1e536ff121a5..8504ac937809 100644 --- a/tools/testing/selftests/bpf/verifier/var_off.c +++ b/tools/testing/selftests/bpf/verifier/var_off.c @@ -40,7 +40,35 @@ .prog_type = BPF_PROG_TYPE_LWT_IN, }, { - "indirect variable-offset stack access", + "indirect variable-offset stack access, unbounded", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 6), + BPF_MOV64_IMM(BPF_REG_3, 28), + /* Fill the top 16 bytes of the stack. */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + /* Get an unknown value. */ + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_1, offsetof(struct bpf_sock_ops, + bytes_received)), + /* Check the lower bound but don't check the upper one. */ + BPF_JMP_IMM(BPF_JSLT, BPF_REG_4, 0, 4), + /* Point the lower bound to initialized stack. Offset is now in range + * from fp-16 to fp+0x7fffffffffffffef, i.e. max value is unbounded. + */ + BPF_ALU64_IMM(BPF_SUB, BPF_REG_4, 16), + BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_10), + BPF_MOV64_IMM(BPF_REG_5, 8), + /* Dereference it indirectly. */ + BPF_EMIT_CALL(BPF_FUNC_getsockopt), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R4 unbounded indirect variable offset stack access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SOCK_OPS, +}, +{ + "indirect variable-offset stack access, max out of bound", .insns = { /* Fill the top 8 bytes of the stack */ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), @@ -60,7 +88,161 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_8b = { 5 }, - .errstr = "variable stack read R2", + .errstr = "R2 max value is outside of stack bound", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_LWT_IN, +}, +{ + "indirect variable-offset stack access, min out of bound", + .insns = { + /* Fill the top 8 bytes of the stack */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + /* Get an unknown value */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), + /* Make it small and 4-byte aligned */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 516), + /* add it to fp. We now have either fp-516 or fp-512, but + * we don't know which + */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10), + /* dereference it indirectly */ + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 5 }, + .errstr = "R2 min value is outside of stack bound", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_LWT_IN, +}, +{ + "indirect variable-offset stack access, max_off+size > max_initialized", + .insns = { + /* Fill only the second from top 8 bytes of the stack. */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0), + /* Get an unknown value. */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), + /* Make it small and 4-byte aligned. */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16), + /* Add it to fp. We now have either fp-12 or fp-16, but we don't know + * which. fp-12 size 8 is partially uninitialized stack. + */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10), + /* Dereference it indirectly. */ + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 5 }, + .errstr = "invalid indirect read from stack var_off", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_LWT_IN, +}, +{ + "indirect variable-offset stack access, min_off < min_initialized", + .insns = { + /* Fill only the top 8 bytes of the stack. */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + /* Get an unknown value */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), + /* Make it small and 4-byte aligned. */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16), + /* Add it to fp. We now have either fp-12 or fp-16, but we don't know + * which. fp-16 size 8 is partially uninitialized stack. + */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10), + /* Dereference it indirectly. */ + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 5 }, + .errstr = "invalid indirect read from stack var_off", .result = REJECT, .prog_type = BPF_PROG_TYPE_LWT_IN, }, +{ + "indirect variable-offset stack access, priv vs unpriv", + .insns = { + /* Fill the top 16 bytes of the stack. */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + /* Get an unknown value. */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), + /* Make it small and 4-byte aligned. */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16), + /* Add it to fp. We now have either fp-12 or fp-16, we don't know + * which, but either way it points to initialized stack. + */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10), + /* Dereference it indirectly. */ + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 6 }, + .errstr_unpriv = "R2 stack pointer arithmetic goes out of range, prohibited for !root", + .result_unpriv = REJECT, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "indirect variable-offset stack access, uninitialized", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 6), + BPF_MOV64_IMM(BPF_REG_3, 28), + /* Fill the top 16 bytes of the stack. */ + BPF_ST_MEM(BPF_W, BPF_REG_10, -16, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + /* Get an unknown value. */ + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, 0), + /* Make it small and 4-byte aligned. */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_4, 4), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_4, 16), + /* Add it to fp. We now have either fp-12 or fp-16, we don't know + * which, but either way it points to initialized stack. + */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_10), + BPF_MOV64_IMM(BPF_REG_5, 8), + /* Dereference it indirectly. */ + BPF_EMIT_CALL(BPF_FUNC_getsockopt), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid indirect read from stack var_off", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SOCK_OPS, +}, +{ + "indirect variable-offset stack access, ok", + .insns = { + /* Fill the top 16 bytes of the stack. */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + /* Get an unknown value. */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), + /* Make it small and 4-byte aligned. */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16), + /* Add it to fp. We now have either fp-12 or fp-16, we don't know + * which, but either way it points to initialized stack. + */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10), + /* Dereference it indirectly. */ + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 6 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_LWT_IN, +}, diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh index c4cf6e6d800e..1c30f302a1e7 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh @@ -11,6 +11,7 @@ lib_dir=$(dirname $0)/../../../net/forwarding ALL_TESTS=" rif_set_addr_test + rif_vrf_set_addr_test rif_inherit_bridge_addr_test rif_non_inherit_bridge_addr_test vlan_interface_deletion_test @@ -26,6 +27,7 @@ ALL_TESTS=" lag_dev_deletion_test vlan_interface_uppers_test bridge_extern_learn_test + neigh_offload_test devlink_reload_test " NUM_NETIFS=2 @@ -98,6 +100,25 @@ rif_set_addr_test() ip link set dev $swp1 addr $swp1_mac } +rif_vrf_set_addr_test() +{ + # Test that it is possible to set an IP address on a VRF upper despite + # its random MAC address. + RET=0 + + ip link add name vrf-test type vrf table 10 + ip link set dev $swp1 master vrf-test + + ip -4 address add 192.0.2.1/24 dev vrf-test + check_err $? "failed to set IPv4 address on VRF" + ip -6 address add 2001:db8:1::1/64 dev vrf-test + check_err $? "failed to set IPv6 address on VRF" + + log_test "RIF - setting IP address on VRF" + + ip link del dev vrf-test +} + rif_inherit_bridge_addr_test() { RET=0 @@ -561,6 +582,31 @@ bridge_extern_learn_test() ip link del dev br0 } +neigh_offload_test() +{ + # Test that IPv4 and IPv6 neighbour entries are marked as offloaded + RET=0 + + ip -4 address add 192.0.2.1/24 dev $swp1 + ip -6 address add 2001:db8:1::1/64 dev $swp1 + + ip -4 neigh add 192.0.2.2 lladdr de:ad:be:ef:13:37 nud perm dev $swp1 + ip -6 neigh add 2001:db8:1::2 lladdr de:ad:be:ef:13:37 nud perm \ + dev $swp1 + + ip -4 neigh show dev $swp1 | grep 192.0.2.2 | grep -q offload + check_err $? "ipv4 neigh entry not marked as offloaded when should" + ip -6 neigh show dev $swp1 | grep 2001:db8:1::2 | grep -q offload + check_err $? "ipv6 neigh entry not marked as offloaded when should" + + log_test "neighbour offload indication" + + ip -6 neigh del 2001:db8:1::2 dev $swp1 + ip -4 neigh del 192.0.2.2 dev $swp1 + ip -6 address del 2001:db8:1::1/64 dev $swp1 + ip -4 address del 192.0.2.1/24 dev $swp1 +} + devlink_reload_test() { # Test that after executing all the above configuration tests, a diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 3c1f4bdf9000..f8588cca2bef 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -1,3 +1,5 @@ +include ../../../../scripts/Kbuild.include + all: top_srcdir = ../../../.. @@ -17,6 +19,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test +TEST_GEN_PROGS_x86_64 += x86_64/smm_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += clear_dirty_log_test @@ -29,8 +32,12 @@ LIBKVM += $(LIBKVM_$(UNAME_M)) INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include -CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I.. -LDFLAGS += -pthread +CFLAGS += -O2 -g -std=gnu99 -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I.. + +no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ + $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) + +LDFLAGS += -pthread $(no-pie-option) # After inclusion, $(OUTPUT) is defined and # $(TEST_GEN_PROGS) starts with $(OUTPUT)/ diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index a84785b02557..07b71ad9734a 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -102,6 +102,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva); struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); +void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_mp_state *mp_state); void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index e2884c2b81ff..6063d5b2f356 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -778,6 +778,33 @@ void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, #define MSR_IA32_APICBASE_ENABLE (1<<11) #define MSR_IA32_APICBASE_BASE (0xfffff<<12) +#define APIC_BASE_MSR 0x800 +#define X2APIC_ENABLE (1UL << 10) +#define APIC_ICR 0x300 +#define APIC_DEST_SELF 0x40000 +#define APIC_DEST_ALLINC 0x80000 +#define APIC_DEST_ALLBUT 0xC0000 +#define APIC_ICR_RR_MASK 0x30000 +#define APIC_ICR_RR_INVALID 0x00000 +#define APIC_ICR_RR_INPROG 0x10000 +#define APIC_ICR_RR_VALID 0x20000 +#define APIC_INT_LEVELTRIG 0x08000 +#define APIC_INT_ASSERT 0x04000 +#define APIC_ICR_BUSY 0x01000 +#define APIC_DEST_LOGICAL 0x00800 +#define APIC_DEST_PHYSICAL 0x00000 +#define APIC_DM_FIXED 0x00000 +#define APIC_DM_FIXED_MASK 0x00700 +#define APIC_DM_LOWEST 0x00100 +#define APIC_DM_SMI 0x00200 +#define APIC_DM_REMRD 0x00300 +#define APIC_DM_NMI 0x00400 +#define APIC_DM_INIT 0x00500 +#define APIC_DM_STARTUP 0x00600 +#define APIC_DM_EXTINT 0x00700 +#define APIC_VECTOR_MASK 0x000FF +#define APIC_ICR2 0x310 + #define MSR_IA32_TSCDEADLINE 0x000006e0 #define MSR_IA32_UCODE_WRITE 0x00000079 diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index b52cfdefecbf..4ca96b228e46 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -91,6 +91,11 @@ static void vm_open(struct kvm_vm *vm, int perm, unsigned long type) if (vm->kvm_fd < 0) exit(KSFT_SKIP); + if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) { + fprintf(stderr, "immediate_exit not available, skipping test\n"); + exit(KSFT_SKIP); + } + vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, type); TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, " "rc: %i errno: %i", vm->fd, errno); @@ -1121,6 +1126,22 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid) return rc; } +void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + int ret; + + TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); + + vcpu->state->immediate_exit = 1; + ret = ioctl(vcpu->fd, KVM_RUN, NULL); + vcpu->state->immediate_exit = 0; + + TEST_ASSERT(ret == -1 && errno == EINTR, + "KVM_RUN IOCTL didn't exit immediately, rc: %i, errno: %i", + ret, errno); +} + /* * VM VCPU Set MP State * diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index f28127f4a3af..dc7fae9fa424 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1030,6 +1030,14 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) nested_size, sizeof(state->nested_)); } + /* + * When KVM exits to userspace with KVM_EXIT_IO, KVM guarantees + * guest state is consistent only after userspace re-enters the + * kernel with KVM_RUN. Complete IO prior to migrating state + * to a new VM. + */ + vcpu_run_complete_io(vm, vcpuid); + nmsrs = kvm_get_num_msrs(vm); list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); list->nmsrs = nmsrs; @@ -1093,12 +1101,6 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s struct vcpu *vcpu = vcpu_find(vm, vcpuid); int r; - if (state->nested.size) { - r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i", - r); - } - r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave); TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i", r); @@ -1130,4 +1132,10 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs); TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i", r); + + if (state->nested.size) { + r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i", + r); + } } diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c index d503a51fad30..7c2c4d4055a8 100644 --- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c +++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c @@ -87,22 +87,25 @@ int main(int argc, char *argv[]) while (1) { rc = _vcpu_run(vm, VCPU_ID); - if (run->exit_reason == KVM_EXIT_IO) { - switch (get_ucall(vm, VCPU_ID, &uc)) { - case UCALL_SYNC: - /* emulate hypervisor clearing CR4.OSXSAVE */ - vcpu_sregs_get(vm, VCPU_ID, &sregs); - sregs.cr4 &= ~X86_CR4_OSXSAVE; - vcpu_sregs_set(vm, VCPU_ID, &sregs); - break; - case UCALL_ABORT: - TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit."); - break; - case UCALL_DONE: - goto done; - default: - TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); - } + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_SYNC: + /* emulate hypervisor clearing CR4.OSXSAVE */ + vcpu_sregs_get(vm, VCPU_ID, &sregs); + sregs.cr4 &= ~X86_CR4_OSXSAVE; + vcpu_sregs_set(vm, VCPU_ID, &sregs); + break; + case UCALL_ABORT: + TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit."); + break; + case UCALL_DONE: + goto done; + default: + TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); } } diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index c49c2a28b0eb..36669684eca5 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -123,8 +123,6 @@ int main(int argc, char *argv[]) stage, run->exit_reason, exit_reason_str(run->exit_reason)); - memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vm, VCPU_ID, ®s1); switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_ABORT: TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0], @@ -144,6 +142,9 @@ int main(int argc, char *argv[]) stage, (ulong)uc.args[1]); state = vcpu_save_state(vm, VCPU_ID); + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vm, VCPU_ID, ®s1); + kvm_vm_release(vm); /* Restore state in a new VM. */ diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c new file mode 100644 index 000000000000..fb8086964d83 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2018, Red Hat, Inc. + * + * Tests for SMM. + */ +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdint.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" + +#include "kvm_util.h" + +#include "vmx.h" + +#define VCPU_ID 1 + +#define PAGE_SIZE 4096 + +#define SMRAM_SIZE 65536 +#define SMRAM_MEMSLOT ((1 << 16) | 1) +#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) +#define SMRAM_GPA 0x1000000 +#define SMRAM_STAGE 0xfe + +#define STR(x) #x +#define XSTR(s) STR(s) + +#define SYNC_PORT 0xe +#define DONE 0xff + +/* + * This is compiled as normal 64-bit code, however, SMI handler is executed + * in real-address mode. To stay simple we're limiting ourselves to a mode + * independent subset of asm here. + * SMI handler always report back fixed stage SMRAM_STAGE. + */ +uint8_t smi_handler[] = { + 0xb0, SMRAM_STAGE, /* mov $SMRAM_STAGE, %al */ + 0xe4, SYNC_PORT, /* in $SYNC_PORT, %al */ + 0x0f, 0xaa, /* rsm */ +}; + +void sync_with_host(uint64_t phase) +{ + asm volatile("in $" XSTR(SYNC_PORT)", %%al \n" + : : "a" (phase)); +} + +void self_smi(void) +{ + wrmsr(APIC_BASE_MSR + (APIC_ICR >> 4), + APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI); +} + +void guest_code(struct vmx_pages *vmx_pages) +{ + uint64_t apicbase = rdmsr(MSR_IA32_APICBASE); + + sync_with_host(1); + + wrmsr(MSR_IA32_APICBASE, apicbase | X2APIC_ENABLE); + + sync_with_host(2); + + self_smi(); + + sync_with_host(4); + + if (vmx_pages) { + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + + sync_with_host(5); + + self_smi(); + + sync_with_host(7); + } + + sync_with_host(DONE); +} + +int main(int argc, char *argv[]) +{ + struct vmx_pages *vmx_pages = NULL; + vm_vaddr_t vmx_pages_gva = 0; + + struct kvm_regs regs; + struct kvm_vm *vm; + struct kvm_run *run; + struct kvm_x86_state *state; + int stage, stage_reported; + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + + run = vcpu_state(vm, VCPU_ID); + + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA, + SMRAM_MEMSLOT, SMRAM_PAGES, 0); + TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, SMRAM_GPA, SMRAM_MEMSLOT) + == SMRAM_GPA, "could not allocate guest physical addresses?"); + + memset(addr_gpa2hva(vm, SMRAM_GPA), 0x0, SMRAM_SIZE); + memcpy(addr_gpa2hva(vm, SMRAM_GPA) + 0x8000, smi_handler, + sizeof(smi_handler)); + + vcpu_set_msr(vm, VCPU_ID, MSR_IA32_SMBASE, SMRAM_GPA); + + if (kvm_check_cap(KVM_CAP_NESTED_STATE)) { + vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + } else { + printf("will skip SMM test with VMX enabled\n"); + vcpu_args_set(vm, VCPU_ID, 1, 0); + } + + for (stage = 1;; stage++) { + _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Stage %d: unexpected exit reason: %u (%s),\n", + stage, run->exit_reason, + exit_reason_str(run->exit_reason)); + + memset(®s, 0, sizeof(regs)); + vcpu_regs_get(vm, VCPU_ID, ®s); + + stage_reported = regs.rax & 0xff; + + if (stage_reported == DONE) + goto done; + + TEST_ASSERT(stage_reported == stage || + stage_reported == SMRAM_STAGE, + "Unexpected stage: #%x, got %x", + stage, stage_reported); + + state = vcpu_save_state(vm, VCPU_ID); + kvm_vm_release(vm); + kvm_vm_restart(vm, O_RDWR); + vm_vcpu_add(vm, VCPU_ID, 0, 0); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + vcpu_load_state(vm, VCPU_ID, state); + run = vcpu_state(vm, VCPU_ID); + free(state); + } + +done: + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index 4b3f556265f1..e0a3c0204b7c 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -156,8 +156,6 @@ int main(int argc, char *argv[]) stage, run->exit_reason, exit_reason_str(run->exit_reason)); - memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vm, VCPU_ID, ®s1); switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_ABORT: TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0], @@ -177,6 +175,9 @@ int main(int argc, char *argv[]) stage, (ulong)uc.args[1]); state = vcpu_save_state(vm, VCPU_ID); + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vm, VCPU_ID, ®s1); + kvm_vm_release(vm); /* Restore state in a new VM. */ diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 1080ff55a788..9457aaeae092 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -9,7 +9,8 @@ ret=0 ksft_skip=4 # all tests in this script. Can be overridden with -t option -TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics" +TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw" + VERBOSE=0 PAUSE_ON_FAIL=no PAUSE=no @@ -48,6 +49,7 @@ setup() { set -e ip netns add ns1 + ip netns set ns1 auto $IP link set dev lo up ip netns exec ns1 sysctl -qw net.ipv4.ip_forward=1 ip netns exec ns1 sysctl -qw net.ipv6.conf.all.forwarding=1 @@ -605,6 +607,39 @@ run_cmd() return $rc } +check_expected() +{ + local out="$1" + local expected="$2" + local rc=0 + + [ "${out}" = "${expected}" ] && return 0 + + if [ -z "${out}" ]; then + if [ "$VERBOSE" = "1" ]; then + printf "\nNo route entry found\n" + printf "Expected:\n" + printf " ${expected}\n" + fi + return 1 + fi + + # tricky way to convert output to 1-line without ip's + # messy '\'; this drops all extra white space + out=$(echo ${out}) + if [ "${out}" != "${expected}" ]; then + rc=1 + if [ "${VERBOSE}" = "1" ]; then + printf " Unexpected route entry. Have:\n" + printf " ${out}\n" + printf " Expected:\n" + printf " ${expected}\n\n" + fi + fi + + return $rc +} + # add route for a prefix, flushing any existing routes first # expected to be the first step of a test add_route6() @@ -652,31 +687,7 @@ check_route6() pfx=$1 out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//') - [ "${out}" = "${expected}" ] && return 0 - - if [ -z "${out}" ]; then - if [ "$VERBOSE" = "1" ]; then - printf "\nNo route entry found\n" - printf "Expected:\n" - printf " ${expected}\n" - fi - return 1 - fi - - # tricky way to convert output to 1-line without ip's - # messy '\'; this drops all extra white space - out=$(echo ${out}) - if [ "${out}" != "${expected}" ]; then - rc=1 - if [ "${VERBOSE}" = "1" ]; then - printf " Unexpected route entry. Have:\n" - printf " ${out}\n" - printf " Expected:\n" - printf " ${expected}\n\n" - fi - fi - - return $rc + check_expected "${out}" "${expected}" } route_cleanup() @@ -698,6 +709,7 @@ route_setup() set -e ip netns add ns2 + ip netns set ns2 auto ip -netns ns2 link set dev lo up ip netns exec ns2 sysctl -qw net.ipv4.ip_forward=1 ip netns exec ns2 sysctl -qw net.ipv6.conf.all.forwarding=1 @@ -725,7 +737,7 @@ route_setup() ip -netns ns2 addr add 172.16.103.2/24 dev veth4 ip -netns ns2 addr add 172.16.104.1/24 dev dummy1 - set +ex + set +e } # assumption is that basic add of a single path route works @@ -960,7 +972,8 @@ ipv6_addr_metric_test() run_cmd "$IP li set dev dummy2 down" rc=$? if [ $rc -eq 0 ]; then - check_route6 "" + out=$($IP -6 ro ls match 2001:db8:104::/64) + check_expected "${out}" "" rc=$? fi log_test $rc 0 "Prefix route removed on link down" @@ -1091,38 +1104,13 @@ check_route() local pfx local expected="$1" local out - local rc=0 set -- $expected pfx=$1 [ "${pfx}" = "unreachable" ] && pfx=$2 out=$($IP ro ls match ${pfx}) - [ "${out}" = "${expected}" ] && return 0 - - if [ -z "${out}" ]; then - if [ "$VERBOSE" = "1" ]; then - printf "\nNo route entry found\n" - printf "Expected:\n" - printf " ${expected}\n" - fi - return 1 - fi - - # tricky way to convert output to 1-line without ip's - # messy '\'; this drops all extra white space - out=$(echo ${out}) - if [ "${out}" != "${expected}" ]; then - rc=1 - if [ "${VERBOSE}" = "1" ]; then - printf " Unexpected route entry. Have:\n" - printf " ${out}\n" - printf " Expected:\n" - printf " ${expected}\n\n" - fi - fi - - return $rc + check_expected "${out}" "${expected}" } # assumption is that basic add of a single path route works @@ -1387,7 +1375,8 @@ ipv4_addr_metric_test() run_cmd "$IP li set dev dummy2 down" rc=$? if [ $rc -eq 0 ]; then - check_route "" + out=$($IP ro ls match 172.16.104.0/24) + check_expected "${out}" "" rc=$? fi log_test $rc 0 "Prefix route removed on link down" @@ -1442,6 +1431,70 @@ ipv4_route_metrics_test() route_cleanup } +ipv4_route_v6_gw_test() +{ + local rc + + echo + echo "IPv4 route with IPv6 gateway tests" + + route_setup + sleep 2 + + # + # single path route + # + run_cmd "$IP ro add 172.16.104.0/24 via inet6 2001:db8:101::2" + rc=$? + log_test $rc 0 "Single path route with IPv6 gateway" + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 via inet6 2001:db8:101::2 dev veth1" + fi + + run_cmd "ip netns exec ns1 ping -w1 -c1 172.16.104.1" + log_test $rc 0 "Single path route with IPv6 gateway - ping" + + run_cmd "$IP ro del 172.16.104.0/24 via inet6 2001:db8:101::2" + rc=$? + log_test $rc 0 "Single path route delete" + if [ $rc -eq 0 ]; then + check_route "172.16.112.0/24" + fi + + # + # multipath - v6 then v4 + # + run_cmd "$IP ro add 172.16.104.0/24 nexthop via inet6 2001:db8:101::2 dev veth1 nexthop via 172.16.103.2 dev veth3" + rc=$? + log_test $rc 0 "Multipath route add - v6 nexthop then v4" + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 nexthop via inet6 2001:db8:101::2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + fi + + run_cmd "$IP ro del 172.16.104.0/24 nexthop via 172.16.103.2 dev veth3 nexthop via inet6 2001:db8:101::2 dev veth1" + log_test $? 2 " Multipath route delete - nexthops in wrong order" + + run_cmd "$IP ro del 172.16.104.0/24 nexthop via inet6 2001:db8:101::2 dev veth1 nexthop via 172.16.103.2 dev veth3" + log_test $? 0 " Multipath route delete exact match" + + # + # multipath - v4 then v6 + # + run_cmd "$IP ro add 172.16.104.0/24 nexthop via 172.16.103.2 dev veth3 nexthop via inet6 2001:db8:101::2 dev veth1" + rc=$? + log_test $rc 0 "Multipath route add - v4 nexthop then v6" + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 nexthop via 172.16.103.2 dev veth3 weight 1 nexthop via inet6 2001:db8:101::2 dev veth1 weight 1" + fi + + run_cmd "$IP ro del 172.16.104.0/24 nexthop via inet6 2001:db8:101::2 dev veth1 nexthop via 172.16.103.2 dev veth3" + log_test $? 2 " Multipath route delete - nexthops in wrong order" + + run_cmd "$IP ro del 172.16.104.0/24 nexthop via 172.16.103.2 dev veth3 nexthop via inet6 2001:db8:101::2 dev veth1" + log_test $? 0 " Multipath route delete exact match" + + route_cleanup +} ################################################################################ # usage @@ -1511,6 +1564,7 @@ do ipv4_addr_metric) ipv4_addr_metric_test;; ipv6_route_metrics) ipv6_route_metrics_test;; ipv4_route_metrics) ipv4_route_metrics_test;; + ipv4_route_v6_gw) ipv4_route_v6_gw_test;; help) echo "Test names: $TESTS"; exit 0;; esac diff --git a/tools/testing/selftests/net/forwarding/bridge_igmp.sh b/tools/testing/selftests/net/forwarding/bridge_igmp.sh new file mode 100755 index 000000000000..88d2472ba151 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/bridge_igmp.sh @@ -0,0 +1,152 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS="reportleave_test" +NUM_NETIFS=4 +CHECK_TC="yes" +TEST_GROUP="239.10.10.10" +TEST_GROUP_MAC="01:00:5e:0a:0a:0a" +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/24 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/24 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/24 2001:db8:1::2/64 +} + +h2_destroy() +{ + simple_if_fini $h2 192.0.2.2/24 2001:db8:1::2/64 +} + +switch_create() +{ + ip link add dev br0 type bridge mcast_snooping 1 mcast_querier 1 + + ip link set dev $swp1 master br0 + ip link set dev $swp2 master br0 + + ip link set dev br0 up + ip link set dev $swp1 up + ip link set dev $swp2 up +} + +switch_destroy() +{ + ip link set dev $swp2 down + ip link set dev $swp1 down + + ip link del dev br0 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + + # Always cleanup the mcast group + ip address del dev $h2 $TEST_GROUP/32 2>&1 1>/dev/null + + h2_destroy + h1_destroy + + vrf_cleanup +} + +# return 0 if the packet wasn't seen on host2_if or 1 if it was +mcast_packet_test() +{ + local mac=$1 + local ip=$2 + local host1_if=$3 + local host2_if=$4 + local seen=0 + + # Add an ACL on `host2_if` which will tell us whether the packet + # was received by it or not. + tc qdisc add dev $host2_if ingress + tc filter add dev $host2_if ingress protocol ip pref 1 handle 101 \ + flower dst_mac $mac action drop + + $MZ $host1_if -c 1 -p 64 -b $mac -B $ip -t udp "dp=4096,sp=2048" -q + sleep 1 + + tc -j -s filter show dev $host2_if ingress \ + | jq -e ".[] | select(.options.handle == 101) \ + | select(.options.actions[0].stats.packets == 1)" &> /dev/null + if [[ $? -eq 0 ]]; then + seen=1 + fi + + tc filter del dev $host2_if ingress protocol ip pref 1 handle 101 flower + tc qdisc del dev $host2_if ingress + + return $seen +} + +reportleave_test() +{ + RET=0 + ip address add dev $h2 $TEST_GROUP/32 autojoin + check_err $? "Could not join $TEST_GROUP" + + sleep 5 + bridge mdb show dev br0 | grep $TEST_GROUP 1>/dev/null + check_err $? "Report didn't create mdb entry for $TEST_GROUP" + + mcast_packet_test $TEST_GROUP_MAC $TEST_GROUP $h1 $h2 + check_fail $? "Traffic to $TEST_GROUP wasn't forwarded" + + log_test "IGMP report $TEST_GROUP" + + RET=0 + bridge mdb show dev br0 | grep $TEST_GROUP 1>/dev/null + check_err $? "mdb entry for $TEST_GROUP is missing" + + ip address del dev $h2 $TEST_GROUP/32 + check_err $? "Could not leave $TEST_GROUP" + + sleep 5 + bridge mdb show dev br0 | grep $TEST_GROUP 1>/dev/null + check_fail $? "Leave didn't delete mdb entry for $TEST_GROUP" + + mcast_packet_test $TEST_GROUP_MAC $TEST_GROUP $h1 $h2 + check_err $? "Traffic to $TEST_GROUP was forwarded without mdb entry" + + log_test "IGMP leave $TEST_GROUP" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 912b2dc50be3..524b15dabb3c 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -116,6 +116,10 @@ # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +PAUSE_ON_FAIL=no +VERBOSE=0 +TRACING=0 + # Some systems don't have a ping6 binary anymore which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) @@ -222,6 +226,23 @@ err_flush() { err_buf= } +run_cmd() { + cmd="$*" + + if [ "$VERBOSE" = "1" ]; then + printf " COMMAND: $cmd\n" + fi + + out="$($cmd 2>&1)" + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo " $out" + echo + fi + + return $rc +} + # Find the auto-generated name for this namespace nsname() { eval echo \$NS_$1 @@ -258,22 +279,22 @@ setup_fou_or_gue() { fi fi - ${ns_a} ip fou add port 5555 ipproto ${ipproto} || return 2 - ${ns_a} ip link add ${encap}_a type ${type} ${mode} local ${a_addr} remote ${b_addr} encap ${encap} encap-sport auto encap-dport 5556 || return 2 + run_cmd ${ns_a} ip fou add port 5555 ipproto ${ipproto} || return 2 + run_cmd ${ns_a} ip link add ${encap}_a type ${type} ${mode} local ${a_addr} remote ${b_addr} encap ${encap} encap-sport auto encap-dport 5556 || return 2 - ${ns_b} ip fou add port 5556 ipproto ${ipproto} - ${ns_b} ip link add ${encap}_b type ${type} ${mode} local ${b_addr} remote ${a_addr} encap ${encap} encap-sport auto encap-dport 5555 + run_cmd ${ns_b} ip fou add port 5556 ipproto ${ipproto} + run_cmd ${ns_b} ip link add ${encap}_b type ${type} ${mode} local ${b_addr} remote ${a_addr} encap ${encap} encap-sport auto encap-dport 5555 if [ "${inner}" = "4" ]; then - ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${encap}_a - ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${encap}_b + run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${encap}_a + run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${encap}_b else - ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${encap}_a - ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${encap}_b + run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${encap}_a + run_cmd ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${encap}_b fi - ${ns_a} ip link set ${encap}_a up - ${ns_b} ip link set ${encap}_b up + run_cmd ${ns_a} ip link set ${encap}_a up + run_cmd ${ns_b} ip link set ${encap}_b up } setup_fou44() { @@ -319,17 +340,17 @@ setup_namespaces() { } setup_veth() { - ${ns_a} ip link add veth_a type veth peer name veth_b || return 1 - ${ns_a} ip link set veth_b netns ${NS_B} + run_cmd ${ns_a} ip link add veth_a type veth peer name veth_b || return 1 + run_cmd ${ns_a} ip link set veth_b netns ${NS_B} - ${ns_a} ip addr add ${veth4_a_addr}/${veth4_mask} dev veth_a - ${ns_b} ip addr add ${veth4_b_addr}/${veth4_mask} dev veth_b + run_cmd ${ns_a} ip addr add ${veth4_a_addr}/${veth4_mask} dev veth_a + run_cmd ${ns_b} ip addr add ${veth4_b_addr}/${veth4_mask} dev veth_b - ${ns_a} ip addr add ${veth6_a_addr}/${veth6_mask} dev veth_a - ${ns_b} ip addr add ${veth6_b_addr}/${veth6_mask} dev veth_b + run_cmd ${ns_a} ip addr add ${veth6_a_addr}/${veth6_mask} dev veth_a + run_cmd ${ns_b} ip addr add ${veth6_b_addr}/${veth6_mask} dev veth_b - ${ns_a} ip link set veth_a up - ${ns_b} ip link set veth_b up + run_cmd ${ns_a} ip link set veth_a up + run_cmd ${ns_b} ip link set veth_b up } setup_vti() { @@ -342,14 +363,14 @@ setup_vti() { [ ${proto} -eq 6 ] && vti_type="vti6" || vti_type="vti" - ${ns_a} ip link add vti${proto}_a type ${vti_type} local ${veth_a_addr} remote ${veth_b_addr} key 10 || return 1 - ${ns_b} ip link add vti${proto}_b type ${vti_type} local ${veth_b_addr} remote ${veth_a_addr} key 10 + run_cmd ${ns_a} ip link add vti${proto}_a type ${vti_type} local ${veth_a_addr} remote ${veth_b_addr} key 10 || return 1 + run_cmd ${ns_b} ip link add vti${proto}_b type ${vti_type} local ${veth_b_addr} remote ${veth_a_addr} key 10 - ${ns_a} ip addr add ${vti_a_addr}/${vti_mask} dev vti${proto}_a - ${ns_b} ip addr add ${vti_b_addr}/${vti_mask} dev vti${proto}_b + run_cmd ${ns_a} ip addr add ${vti_a_addr}/${vti_mask} dev vti${proto}_a + run_cmd ${ns_b} ip addr add ${vti_b_addr}/${vti_mask} dev vti${proto}_b - ${ns_a} ip link set vti${proto}_a up - ${ns_b} ip link set vti${proto}_b up + run_cmd ${ns_a} ip link set vti${proto}_a up + run_cmd ${ns_b} ip link set vti${proto}_b up } setup_vti4() { @@ -375,17 +396,17 @@ setup_vxlan_or_geneve() { opts_b="" fi - ${ns_a} ip link add ${type}_a type ${type} id 1 ${opts_a} remote ${b_addr} ${opts} || return 1 - ${ns_b} ip link add ${type}_b type ${type} id 1 ${opts_b} remote ${a_addr} ${opts} + run_cmd ${ns_a} ip link add ${type}_a type ${type} id 1 ${opts_a} remote ${b_addr} ${opts} || return 1 + run_cmd ${ns_b} ip link add ${type}_b type ${type} id 1 ${opts_b} remote ${a_addr} ${opts} - ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${type}_a - ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b + run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${type}_a + run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b - ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${type}_a - ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${type}_b + run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${type}_a + run_cmd ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${type}_b - ${ns_a} ip link set ${type}_a up - ${ns_b} ip link set ${type}_b up + run_cmd ${ns_a} ip link set ${type}_a up + run_cmd ${ns_b} ip link set ${type}_b up } setup_geneve4() { @@ -409,15 +430,15 @@ setup_xfrm() { veth_a_addr="${2}" veth_b_addr="${3}" - ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel || return 1 - ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel - ${ns_a} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel - ${ns_a} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel + run_cmd "${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel" || return 1 + run_cmd "${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel" + run_cmd "${ns_a} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel" + run_cmd "${ns_a} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel" - ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel - ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel - ${ns_b} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel - ${ns_b} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel + run_cmd "${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel" + run_cmd "${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel" + run_cmd "${ns_b} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel" + run_cmd "${ns_b} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel" } setup_xfrm4() { @@ -481,7 +502,7 @@ setup() { } trace() { - [ $tracing -eq 0 ] && return + [ $TRACING -eq 0 ] && return for arg do [ "${ns_cmd}" = "" ] && ns_cmd="${arg}" && continue @@ -597,8 +618,8 @@ test_pmtu_ipvX() { mtu "${ns_b}" veth_B-R2 1500 # Create route exceptions - ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst1} > /dev/null - ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst2} > /dev/null + run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst1} + run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst2} # Check that exceptions have been created with the correct PMTU pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})" @@ -630,7 +651,7 @@ test_pmtu_ipvX() { # Decrease remote MTU on path via R2, get new exception mtu "${ns_r2}" veth_R2-B 400 mtu "${ns_b}" veth_B-R2 400 - ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1400 ${dst2} > /dev/null + run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1400 ${dst2} pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})" check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1 @@ -647,7 +668,7 @@ test_pmtu_ipvX() { check_pmtu_value "1500" "${pmtu_2}" "increasing local MTU" || return 1 # Get new exception - ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1400 ${dst2} > /dev/null + run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1400 ${dst2} pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})" check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1 } @@ -696,7 +717,7 @@ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception() { mtu "${ns_a}" ${type}_a $((${ll_mtu} + 1000)) mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000)) - ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} > /dev/null + run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} # Check that exception was created pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" @@ -776,7 +797,7 @@ test_pmtu_ipvX_over_fouY_or_gueY() { mtu "${ns_a}" ${encap}_a $((${ll_mtu} + 1000)) mtu "${ns_b}" ${encap}_b $((${ll_mtu} + 1000)) - ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} > /dev/null + run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} # Check that exception was created pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" @@ -834,13 +855,13 @@ test_pmtu_vti4_exception() { # Send DF packet without exceeding link layer MTU, check that no # exception is created - ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr} > /dev/null + run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr} pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})" check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1 # Now exceed link layer MTU by one byte, check that exception is created # with the right PMTU value - ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload + 1)) ${tunnel4_b_addr} > /dev/null + run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload + 1)) ${tunnel4_b_addr} pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})" check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))" } @@ -856,7 +877,7 @@ test_pmtu_vti6_exception() { mtu "${ns_b}" veth_b 4000 mtu "${ns_a}" vti6_a 5000 mtu "${ns_b}" vti6_b 5000 - ${ns_a} ${ping6} -q -i 0.1 -w 1 -s 60000 ${tunnel6_b_addr} > /dev/null + run_cmd ${ns_a} ${ping6} -q -i 0.1 -w 1 -s 60000 ${tunnel6_b_addr} # Check that exception was created pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})" @@ -902,9 +923,9 @@ test_pmtu_vti6_default_mtu() { test_pmtu_vti4_link_add_mtu() { setup namespaces || return 2 - ${ns_a} ip link add vti4_a type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10 + run_cmd ${ns_a} ip link add vti4_a type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10 [ $? -ne 0 ] && err " vti not supported" && return 2 - ${ns_a} ip link del vti4_a + run_cmd ${ns_a} ip link del vti4_a fail=0 @@ -912,7 +933,7 @@ test_pmtu_vti4_link_add_mtu() { max=$((65535 - 20)) # Check invalid values first for v in $((min - 1)) $((max + 1)); do - ${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10 2>/dev/null + run_cmd ${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10 # This can fail, or MTU can be adjusted to a proper value [ $? -ne 0 ] && continue mtu="$(link_get_mtu "${ns_a}" vti4_a)" @@ -920,14 +941,14 @@ test_pmtu_vti4_link_add_mtu() { err " vti tunnel created with invalid MTU ${mtu}" fail=1 fi - ${ns_a} ip link del vti4_a + run_cmd ${ns_a} ip link del vti4_a done # Now check valid values for v in ${min} 1300 ${max}; do - ${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10 + run_cmd ${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10 mtu="$(link_get_mtu "${ns_a}" vti4_a)" - ${ns_a} ip link del vti4_a + run_cmd ${ns_a} ip link del vti4_a if [ "${mtu}" != "${v}" ]; then err " vti MTU ${mtu} doesn't match configured value ${v}" fail=1 @@ -940,9 +961,9 @@ test_pmtu_vti4_link_add_mtu() { test_pmtu_vti6_link_add_mtu() { setup namespaces || return 2 - ${ns_a} ip link add vti6_a type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10 + run_cmd ${ns_a} ip link add vti6_a type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10 [ $? -ne 0 ] && err " vti6 not supported" && return 2 - ${ns_a} ip link del vti6_a + run_cmd ${ns_a} ip link del vti6_a fail=0 @@ -950,7 +971,7 @@ test_pmtu_vti6_link_add_mtu() { max=$((65535 - 40)) # Check invalid values first for v in $((min - 1)) $((max + 1)); do - ${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10 2>/dev/null + run_cmd ${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10 # This can fail, or MTU can be adjusted to a proper value [ $? -ne 0 ] && continue mtu="$(link_get_mtu "${ns_a}" vti6_a)" @@ -958,14 +979,14 @@ test_pmtu_vti6_link_add_mtu() { err " vti6 tunnel created with invalid MTU ${v}" fail=1 fi - ${ns_a} ip link del vti6_a + run_cmd ${ns_a} ip link del vti6_a done # Now check valid values for v in 68 1280 1300 $((65535 - 40)); do - ${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10 + run_cmd ${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10 mtu="$(link_get_mtu "${ns_a}" vti6_a)" - ${ns_a} ip link del vti6_a + run_cmd ${ns_a} ip link del vti6_a if [ "${mtu}" != "${v}" ]; then err " vti6 MTU ${mtu} doesn't match configured value ${v}" fail=1 @@ -978,19 +999,19 @@ test_pmtu_vti6_link_add_mtu() { test_pmtu_vti6_link_change_mtu() { setup namespaces || return 2 - ${ns_a} ip link add dummy0 mtu 1500 type dummy + run_cmd ${ns_a} ip link add dummy0 mtu 1500 type dummy [ $? -ne 0 ] && err " dummy not supported" && return 2 - ${ns_a} ip link add dummy1 mtu 3000 type dummy - ${ns_a} ip link set dummy0 up - ${ns_a} ip link set dummy1 up + run_cmd ${ns_a} ip link add dummy1 mtu 3000 type dummy + run_cmd ${ns_a} ip link set dummy0 up + run_cmd ${ns_a} ip link set dummy1 up - ${ns_a} ip addr add ${dummy6_0_addr}/${dummy6_mask} dev dummy0 - ${ns_a} ip addr add ${dummy6_1_addr}/${dummy6_mask} dev dummy1 + run_cmd ${ns_a} ip addr add ${dummy6_0_addr}/${dummy6_mask} dev dummy0 + run_cmd ${ns_a} ip addr add ${dummy6_1_addr}/${dummy6_mask} dev dummy1 fail=0 # Create vti6 interface bound to device, passing MTU, check it - ${ns_a} ip link add vti6_a mtu 1300 type vti6 remote ${dummy6_0_addr} local ${dummy6_0_addr} + run_cmd ${ns_a} ip link add vti6_a mtu 1300 type vti6 remote ${dummy6_0_addr} local ${dummy6_0_addr} mtu="$(link_get_mtu "${ns_a}" vti6_a)" if [ ${mtu} -ne 1300 ]; then err " vti6 MTU ${mtu} doesn't match configured value 1300" @@ -999,7 +1020,7 @@ test_pmtu_vti6_link_change_mtu() { # Move to another device with different MTU, without passing MTU, check # MTU is adjusted - ${ns_a} ip link set vti6_a type vti6 remote ${dummy6_1_addr} local ${dummy6_1_addr} + run_cmd ${ns_a} ip link set vti6_a type vti6 remote ${dummy6_1_addr} local ${dummy6_1_addr} mtu="$(link_get_mtu "${ns_a}" vti6_a)" if [ ${mtu} -ne $((3000 - 40)) ]; then err " vti MTU ${mtu} is not dummy MTU 3000 minus IPv6 header length" @@ -1007,7 +1028,7 @@ test_pmtu_vti6_link_change_mtu() { fi # Move it back, passing MTU, check MTU is not overridden - ${ns_a} ip link set vti6_a mtu 1280 type vti6 remote ${dummy6_0_addr} local ${dummy6_0_addr} + run_cmd ${ns_a} ip link set vti6_a mtu 1280 type vti6 remote ${dummy6_0_addr} local ${dummy6_0_addr} mtu="$(link_get_mtu "${ns_a}" vti6_a)" if [ ${mtu} -ne 1280 ]; then err " vti6 MTU ${mtu} doesn't match configured value 1280" @@ -1052,7 +1073,7 @@ test_cleanup_vxlanX_exception() { # Fill exception cache for multiple CPUs (2) # we can always use inner IPv4 for that for cpu in ${cpu_list}; do - taskset --cpu-list ${cpu} ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${tunnel4_b_addr} > /dev/null + run_cmd taskset --cpu-list ${cpu} ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${tunnel4_b_addr} done ${ns_a} ip link del dev veth_A-R1 & @@ -1084,29 +1105,33 @@ usage() { exit 1 } +################################################################################ +# exitcode=0 desc=0 + +while getopts :ptv o +do + case $o in + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=1;; + t) if which tcpdump > /dev/null 2>&1; then + TRACING=1 + else + echo "=== tcpdump not available, tracing disabled" + fi + ;; + *) usage;; + esac +done +shift $(($OPTIND-1)) + IFS=" " -tracing=0 for arg do - if [ "${arg}" != "${arg#--*}" ]; then - opt="${arg#--}" - if [ "${opt}" = "trace" ]; then - if which tcpdump > /dev/null 2>&1; then - tracing=1 - else - echo "=== tcpdump not available, tracing disabled" - fi - else - usage - fi - else - # Check first that all requested tests are available before - # running any - command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; } - fi + # Check first that all requested tests are available before running any + command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; } done trap cleanup EXIT @@ -1124,6 +1149,11 @@ for t in ${tests}; do ( unset IFS + + if [ "$VERBOSE" = "1" ]; then + printf "\n##########################################################################\n\n" + fi + eval test_${name} ret=$? cleanup @@ -1132,6 +1162,11 @@ for t in ${tests}; do printf "TEST: %-60s [ OK ]\n" "${t}" elif [ $ret -eq 1 ]; then printf "TEST: %-60s [FAIL]\n" "${t}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "Pausing. Hit enter to continue" + read a + fi err_flush exit 1 elif [ $ret -eq 2 ]; then diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index c9ff2b47bd1c..80dae72a25c7 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for netfilter selftests -TEST_PROGS := nft_trans_stress.sh nft_nat.sh +TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh include ../lib.mk diff --git a/tools/testing/selftests/netfilter/bridge_brouter.sh b/tools/testing/selftests/netfilter/bridge_brouter.sh new file mode 100755 index 000000000000..29f3955b9af7 --- /dev/null +++ b/tools/testing/selftests/netfilter/bridge_brouter.sh @@ -0,0 +1,146 @@ +#!/bin/bash +# +# This test is for bridge 'brouting', i.e. make some packets being routed +# rather than getting bridged even though they arrive on interface that is +# part of a bridge. + +# eth0 br0 eth0 +# setup is: ns1 <-> ns0 <-> ns2 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +ebtables -V > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ebtables" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +ip netns add ns0 +ip netns add ns1 +ip netns add ns2 + +ip link add veth0 netns ns0 type veth peer name eth0 netns ns1 +if [ $? -ne 0 ]; then + echo "SKIP: Can't create veth device" + exit $ksft_skip +fi +ip link add veth1 netns ns0 type veth peer name eth0 netns ns2 + +ip -net ns0 link set lo up +ip -net ns0 link set veth0 up +ip -net ns0 link set veth1 up + +ip -net ns0 link add br0 type bridge +if [ $? -ne 0 ]; then + echo "SKIP: Can't create bridge br0" + exit $ksft_skip +fi + +ip -net ns0 link set veth0 master br0 +ip -net ns0 link set veth1 master br0 +ip -net ns0 link set br0 up +ip -net ns0 addr add 10.0.0.1/24 dev br0 + +# place both in same subnet, ns1 and ns2 connected via ns0:br0 +for i in 1 2; do + ip -net ns$i link set lo up + ip -net ns$i link set eth0 up + ip -net ns$i addr add 10.0.0.1$i/24 dev eth0 +done + +test_ebtables_broute() +{ + local cipt + + # redirect is needed so the dstmac is rewritten to the bridge itself, + # ip stack won't process OTHERHOST (foreign unicast mac) packets. + ip netns exec ns0 ebtables -t broute -A BROUTING -p ipv4 --ip-protocol icmp -j redirect --redirect-target=DROP + if [ $? -ne 0 ]; then + echo "SKIP: Could not add ebtables broute redirect rule" + return $ksft_skip + fi + + # ping netns1, expected to not work (ip forwarding is off) + ip netns exec ns1 ping -q -c 1 10.0.0.12 > /dev/null 2>&1 + if [ $? -eq 0 ]; then + echo "ERROR: ping works, should have failed" 1>&2 + return 1 + fi + + # enable forwarding on both interfaces. + # neither needs an ip address, but at least the bridge needs + # an ip address in same network segment as ns1 and ns2 (ns0 + # needs to be able to determine route for to-be-forwarded packet). + ip netns exec ns0 sysctl -q net.ipv4.conf.veth0.forwarding=1 + ip netns exec ns0 sysctl -q net.ipv4.conf.veth1.forwarding=1 + + sleep 1 + + ip netns exec ns1 ping -q -c 1 10.0.0.12 > /dev/null + if [ $? -ne 0 ]; then + echo "ERROR: ping did not work, but it should (broute+forward)" 1>&2 + return 1 + fi + + echo "PASS: ns1/ns2 connectivity with active broute rule" + ip netns exec ns0 ebtables -t broute -F + + # ping netns1, expected to work (frames are bridged) + ip netns exec ns1 ping -q -c 1 10.0.0.12 > /dev/null + if [ $? -ne 0 ]; then + echo "ERROR: ping did not work, but it should (bridged)" 1>&2 + return 1 + fi + + ip netns exec ns0 ebtables -t filter -A FORWARD -p ipv4 --ip-protocol icmp -j DROP + + # ping netns1, expected to not work (DROP in bridge forward) + ip netns exec ns1 ping -q -c 1 10.0.0.12 > /dev/null 2>&1 + if [ $? -eq 0 ]; then + echo "ERROR: ping works, should have failed (icmp forward drop)" 1>&2 + return 1 + fi + + # re-activate brouter + ip netns exec ns0 ebtables -t broute -A BROUTING -p ipv4 --ip-protocol icmp -j redirect --redirect-target=DROP + + ip netns exec ns2 ping -q -c 1 10.0.0.11 > /dev/null + if [ $? -ne 0 ]; then + echo "ERROR: ping did not work, but it should (broute+forward 2)" 1>&2 + return 1 + fi + + echo "PASS: ns1/ns2 connectivity with active broute rule and bridge forward drop" + return 0 +} + +# test basic connectivity +ip netns exec ns1 ping -c 1 -q 10.0.0.12 > /dev/null +if [ $? -ne 0 ]; then + echo "ERROR: Could not reach ns2 from ns1" 1>&2 + ret=1 +fi + +ip netns exec ns2 ping -c 1 -q 10.0.0.11 > /dev/null +if [ $? -ne 0 ]; then + echo "ERROR: Could not reach ns1 from ns2" 1>&2 + ret=1 +fi + +if [ $ret -eq 0 ];then + echo "PASS: netns connectivity: ns1 and ns2 can reach each other" +fi + +test_ebtables_broute +ret=$? +for i in 0 1 2; do ip netns del ns$i;done + +exit $ret diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 8ec76681605c..248905130d5d 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -6,6 +6,7 @@ # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 ret=0 +test_inet_nat=true nft --version > /dev/null 2>&1 if [ $? -ne 0 ];then @@ -141,17 +142,24 @@ reset_counters() test_local_dnat6() { + local family=$1 local lret=0 + local IPF="" + + if [ $family = "inet" ];then + IPF="ip6" + fi + ip netns exec ns0 nft -f - <<EOF -table ip6 nat { +table $family nat { chain output { type nat hook output priority 0; policy accept; - ip6 daddr dead:1::99 dnat to dead:2::99 + ip6 daddr dead:1::99 dnat $IPF to dead:2::99 } } EOF if [ $? -ne 0 ]; then - echo "SKIP: Could not add add ip6 dnat hook" + echo "SKIP: Could not add add $family dnat hook" return $ksft_skip fi @@ -201,7 +209,7 @@ EOF fi done - test $lret -eq 0 && echo "PASS: ipv6 ping to ns1 was NATted to ns2" + test $lret -eq 0 && echo "PASS: ipv6 ping to ns1 was $family NATted to ns2" ip netns exec ns0 nft flush chain ip6 nat output return $lret @@ -209,15 +217,32 @@ EOF test_local_dnat() { + local family=$1 local lret=0 -ip netns exec ns0 nft -f - <<EOF -table ip nat { + local IPF="" + + if [ $family = "inet" ];then + IPF="ip" + fi + +ip netns exec ns0 nft -f - <<EOF 2>/dev/null +table $family nat { chain output { type nat hook output priority 0; policy accept; - ip daddr 10.0.1.99 dnat to 10.0.2.99 + ip daddr 10.0.1.99 dnat $IPF to 10.0.2.99 } } EOF + if [ $? -ne 0 ]; then + if [ $family = "inet" ];then + echo "SKIP: inet nat tests" + test_inet_nat=false + return $ksft_skip + fi + echo "SKIP: Could not add add $family dnat hook" + return $ksft_skip + fi + # ping netns1, expect rewrite to netns2 ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null if [ $? -ne 0 ]; then @@ -264,9 +289,9 @@ EOF fi done - test $lret -eq 0 && echo "PASS: ping to ns1 was NATted to ns2" + test $lret -eq 0 && echo "PASS: ping to ns1 was $family NATted to ns2" - ip netns exec ns0 nft flush chain ip nat output + ip netns exec ns0 nft flush chain $family nat output reset_counters ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null @@ -313,7 +338,7 @@ EOF fi done - test $lret -eq 0 && echo "PASS: ping to ns1 OK after nat output chain flush" + test $lret -eq 0 && echo "PASS: ping to ns1 OK after $family nat output chain flush" return $lret } @@ -321,6 +346,7 @@ EOF test_masquerade6() { + local family=$1 local lret=0 ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null @@ -351,16 +377,21 @@ test_masquerade6() # add masquerading rule ip netns exec ns0 nft -f - <<EOF -table ip6 nat { +table $family nat { chain postrouting { type nat hook postrouting priority 0; policy accept; meta oif veth0 masquerade } } EOF + if [ $? -ne 0 ]; then + echo "SKIP: Could not add add $family masquerade hook" + return $ksft_skip + fi + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading" + echo "ERROR: cannot ping ns1 from ns2 with active $family masquerading" lret=1 fi @@ -397,19 +428,20 @@ EOF fi done - ip netns exec ns0 nft flush chain ip6 nat postrouting + ip netns exec ns0 nft flush chain $family nat postrouting if [ $? -ne 0 ]; then - echo "ERROR: Could not flush ip6 nat postrouting" 1>&2 + echo "ERROR: Could not flush $family nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2" + test $lret -eq 0 && echo "PASS: $family IPv6 masquerade for ns2" return $lret } test_masquerade() { + local family=$1 local lret=0 ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null @@ -440,16 +472,21 @@ test_masquerade() # add masquerading rule ip netns exec ns0 nft -f - <<EOF -table ip nat { +table $family nat { chain postrouting { type nat hook postrouting priority 0; policy accept; meta oif veth0 masquerade } } EOF + if [ $? -ne 0 ]; then + echo "SKIP: Could not add add $family masquerade hook" + return $ksft_skip + fi + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading" + echo "ERROR: cannot ping ns1 from ns2 with active $family masquerading" lret=1 fi @@ -485,19 +522,20 @@ EOF fi done - ip netns exec ns0 nft flush chain ip nat postrouting + ip netns exec ns0 nft flush chain $family nat postrouting if [ $? -ne 0 ]; then - echo "ERROR: Could not flush nat postrouting" 1>&2 + echo "ERROR: Could not flush $family nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: IP masquerade for ns2" + test $lret -eq 0 && echo "PASS: $family IP masquerade for ns2" return $lret } test_redirect6() { + local family=$1 local lret=0 ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null @@ -527,16 +565,21 @@ test_redirect6() # add redirect rule ip netns exec ns0 nft -f - <<EOF -table ip6 nat { +table $family nat { chain prerouting { type nat hook prerouting priority 0; policy accept; meta iif veth1 meta l4proto icmpv6 ip6 saddr dead:2::99 ip6 daddr dead:1::99 redirect } } EOF + if [ $? -ne 0 ]; then + echo "SKIP: Could not add add $family redirect hook" + return $ksft_skip + fi + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ip6 redirect" + echo "ERROR: cannot ping ns1 from ns2 via ipv6 with active $family redirect" lret=1 fi @@ -560,19 +603,20 @@ EOF fi done - ip netns exec ns0 nft delete table ip6 nat + ip netns exec ns0 nft delete table $family nat if [ $? -ne 0 ]; then - echo "ERROR: Could not delete ip6 nat table" 1>&2 + echo "ERROR: Could not delete $family nat table" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: IPv6 redirection for ns2" + test $lret -eq 0 && echo "PASS: $family IPv6 redirection for ns2" return $lret } test_redirect() { + local family=$1 local lret=0 ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null @@ -603,16 +647,21 @@ test_redirect() # add redirect rule ip netns exec ns0 nft -f - <<EOF -table ip nat { +table $family nat { chain prerouting { type nat hook prerouting priority 0; policy accept; meta iif veth1 ip protocol icmp ip saddr 10.0.2.99 ip daddr 10.0.1.99 redirect } } EOF + if [ $? -ne 0 ]; then + echo "SKIP: Could not add add $family redirect hook" + return $ksft_skip + fi + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ip redirect" + echo "ERROR: cannot ping ns1 from ns2 with active $family ip redirect" lret=1 fi @@ -637,13 +686,13 @@ EOF fi done - ip netns exec ns0 nft delete table ip nat + ip netns exec ns0 nft delete table $family nat if [ $? -ne 0 ]; then - echo "ERROR: Could not delete nat table" 1>&2 + echo "ERROR: Could not delete $family nat table" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: IP redirection for ns2" + test $lret -eq 0 && echo "PASS: $family IP redirection for ns2" return $lret } @@ -746,16 +795,25 @@ if [ $ret -eq 0 ];then fi reset_counters -test_local_dnat -test_local_dnat6 +test_local_dnat ip +test_local_dnat6 ip6 +reset_counters +$test_inet_nat && test_local_dnat inet +$test_inet_nat && test_local_dnat6 inet reset_counters -test_masquerade -test_masquerade6 +test_masquerade ip +test_masquerade6 ip6 +reset_counters +$test_inet_nat && test_masquerade inet +$test_inet_nat && test_masquerade6 inet reset_counters -test_redirect -test_redirect6 +test_redirect ip +test_redirect6 ip6 +reset_counters +$test_inet_nat && test_redirect inet +$test_inet_nat && test_redirect6 inet for i in 0 1 2; do ip netns del ns$i;done diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json index 27f0acaed880..ddabb160a11b 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json @@ -144,6 +144,30 @@ ] }, { + "id": "7571", + "name": "Add sample action with invalid rate", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 0 group 1 index 2", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 2", + "matchPattern": "action order [0-9]+: sample rate 1/0 group 1.*index 2 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { "id": "b6d4", "name": "Add sample action with mandatory arguments and invalid control action", "category": [ diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json index 99a5ffca1088..e2f92cefb8d5 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json @@ -19,6 +19,26 @@ ] }, { + "id": "2638", + "name": "Add matchall and try to get it", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$TC qdisc add dev $DEV1 clsact", + "$TC filter add dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall action ok" + ], + "cmdUnderTest": "$TC filter get dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "filter protocol all pref 1 matchall chain 0 handle 0x1234", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 clsact" + ] + }, + { "id": "d052", "name": "Add 1M filters with the same action", "category": [ @@ -38,5 +58,25 @@ "$TC qdisc del dev $DEV2 ingress", "/bin/rm $BATCH_FILE" ] + }, + { + "id": "4cbd", + "name": "Try to add filter with duplicate key", + "category": [ + "filter", + "flower" + ], + "setup": [ + "$TC qdisc add dev $DEV2 ingress", + "$TC filter add dev $DEV2 protocol ip prio 1 parent ffff: flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop" + ], + "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip prio 1 parent ffff: flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop", + "expExitCode": "2", + "verifyCmd": "$TC -s filter show dev $DEV2 ingress", + "matchPattern": "filter protocol ip pref 1 flower chain 0 handle", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV2 ingress" + ] } ] diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py index 40ea95ce2ead..828c18584624 100644 --- a/tools/testing/selftests/tpm2/tpm2.py +++ b/tools/testing/selftests/tpm2/tpm2.py @@ -22,6 +22,7 @@ TPM2_CC_UNSEAL = 0x015E TPM2_CC_FLUSH_CONTEXT = 0x0165 TPM2_CC_START_AUTH_SESSION = 0x0176 TPM2_CC_GET_CAPABILITY = 0x017A +TPM2_CC_GET_RANDOM = 0x017B TPM2_CC_PCR_READ = 0x017E TPM2_CC_POLICY_PCR = 0x017F TPM2_CC_PCR_EXTEND = 0x0182 @@ -357,9 +358,9 @@ class Client: self.flags = flags if (self.flags & Client.FLAG_SPACE) == 0: - self.tpm = open('/dev/tpm0', 'r+b') + self.tpm = open('/dev/tpm0', 'r+b', buffering=0) else: - self.tpm = open('/dev/tpmrm0', 'r+b') + self.tpm = open('/dev/tpmrm0', 'r+b', buffering=0) def close(self): self.tpm.close() diff --git a/tools/testing/selftests/tpm2/tpm2_tests.py b/tools/testing/selftests/tpm2/tpm2_tests.py index 3bb066fea4a0..d4973be53493 100644 --- a/tools/testing/selftests/tpm2/tpm2_tests.py +++ b/tools/testing/selftests/tpm2/tpm2_tests.py @@ -158,6 +158,69 @@ class SmokeTest(unittest.TestCase): pass self.assertEqual(rejected, True) + def test_read_partial_resp(self): + try: + fmt = '>HIIH' + cmd = struct.pack(fmt, + tpm2.TPM2_ST_NO_SESSIONS, + struct.calcsize(fmt), + tpm2.TPM2_CC_GET_RANDOM, + 0x20) + self.client.tpm.write(cmd) + hdr = self.client.tpm.read(10) + sz = struct.unpack('>I', hdr[2:6])[0] + rsp = self.client.tpm.read() + except: + pass + self.assertEqual(sz, 10 + 2 + 32) + self.assertEqual(len(rsp), 2 + 32) + + def test_read_partial_overwrite(self): + try: + fmt = '>HIIH' + cmd = struct.pack(fmt, + tpm2.TPM2_ST_NO_SESSIONS, + struct.calcsize(fmt), + tpm2.TPM2_CC_GET_RANDOM, + 0x20) + self.client.tpm.write(cmd) + # Read part of the respone + rsp1 = self.client.tpm.read(15) + + # Send a new cmd + self.client.tpm.write(cmd) + + # Read the whole respone + rsp2 = self.client.tpm.read() + except: + pass + self.assertEqual(len(rsp1), 15) + self.assertEqual(len(rsp2), 10 + 2 + 32) + + def test_send_two_cmds(self): + rejected = False + try: + fmt = '>HIIH' + cmd = struct.pack(fmt, + tpm2.TPM2_ST_NO_SESSIONS, + struct.calcsize(fmt), + tpm2.TPM2_CC_GET_RANDOM, + 0x20) + self.client.tpm.write(cmd) + + # expect the second one to raise -EBUSY error + self.client.tpm.write(cmd) + rsp = self.client.tpm.read() + + except IOError, e: + # read the response + rsp = self.client.tpm.read() + rejected = True + pass + except: + pass + self.assertEqual(rejected, True) + class SpaceTest(unittest.TestCase): def setUp(self): logging.basicConfig(filename='SpaceTest.log', level=logging.DEBUG) |