diff --git a/Documentation/bpf/bpf_iterators.rst b/Documentation/bpf/bpf_iterators.rst index 0743391..7f514cb 100644 --- a/Documentation/bpf/bpf_iterators.rst +++ b/Documentation/bpf/bpf_iterators.rst @@ -86,7 +86,7 @@ following steps: The following are a few examples of selftest BPF iterator programs: * `bpf_iter_tcp4.c `_ -* `bpf_iter_task_vma.c `_ +* `bpf_iter_task_vmas.c `_ * `bpf_iter_task_file.c `_ Let us look at ``bpf_iter_task_file.c``, which runs in kernel space: diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst index 2478cef..3b60583 100644 --- a/Documentation/bpf/btf.rst +++ b/Documentation/bpf/btf.rst @@ -102,7 +102,8 @@ Each type contains the following common data:: * bits 24-28: kind (e.g. int, ptr, array...etc) * bits 29-30: unused * bit 31: kind_flag, currently used by - * struct, union, fwd, enum and enum64. + * struct, union, enum, fwd, enum64, + * decl_tag and type_tag */ __u32 info; /* "size" is used by INT, ENUM, STRUCT, UNION and ENUM64. @@ -478,7 +479,7 @@ No additional type data follow ``btf_type``. ``struct btf_type`` encoding requirement: * ``name_off``: offset to a non-empty string - * ``info.kind_flag``: 0 + * ``info.kind_flag``: 0 or 1 * ``info.kind``: BTF_KIND_DECL_TAG * ``info.vlen``: 0 * ``type``: ``struct``, ``union``, ``func``, ``var`` or ``typedef`` @@ -489,7 +490,6 @@ No additional type data follow ``btf_type``. __u32 component_idx; }; -The ``name_off`` encodes btf_decl_tag attribute string. The ``type`` should be ``struct``, ``union``, ``func``, ``var`` or ``typedef``. For ``var`` or ``typedef`` type, ``btf_decl_tag.component_idx`` must be ``-1``. For the other three types, if the btf_decl_tag attribute is @@ -499,12 +499,21 @@ the attribute is applied to a ``struct``/``union`` member or a ``func`` argument, and ``btf_decl_tag.component_idx`` should be a valid index (starting from 0) pointing to a member or an argument. +If ``info.kind_flag`` is 0, then this is a normal decl tag, and the +``name_off`` encodes btf_decl_tag attribute string. + +If ``info.kind_flag`` is 1, then the decl tag represents an arbitrary +__attribute__. In this case, ``name_off`` encodes a string +representing the attribute-list of the attribute specifier. For +example, for an ``__attribute__((aligned(4)))`` the string's contents +is ``aligned(4)``. + 2.2.18 BTF_KIND_TYPE_TAG ~~~~~~~~~~~~~~~~~~~~~~~~ ``struct btf_type`` encoding requirement: * ``name_off``: offset to a non-empty string - * ``info.kind_flag``: 0 + * ``info.kind_flag``: 0 or 1 * ``info.kind``: BTF_KIND_TYPE_TAG * ``info.vlen``: 0 * ``type``: the type with ``btf_type_tag`` attribute @@ -522,6 +531,14 @@ type_tag, then zero or more const/volatile/restrict/typedef and finally the base type. The base type is one of int, ptr, array, struct, union, enum, func_proto and float types. +Similarly to decl tags, if the ``info.kind_flag`` is 0, then this is a +normal type tag, and the ``name_off`` encodes btf_type_tag attribute +string. + +If ``info.kind_flag`` is 1, then the type tag represents an arbitrary +__attribute__, and the ``name_off`` encodes a string representing the +attribute-list of the attribute specifier. + 2.2.19 BTF_KIND_ENUM64 ~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst index ab820d5..fbe9755 100644 --- a/Documentation/bpf/standardization/instruction-set.rst +++ b/Documentation/bpf/standardization/instruction-set.rst @@ -324,34 +324,42 @@ register. .. table:: Arithmetic instructions - ===== ===== ======= ========================================================== + ===== ===== ======= =================================================================================== name code offset description - ===== ===== ======= ========================================================== + ===== ===== ======= =================================================================================== ADD 0x0 0 dst += src SUB 0x1 0 dst -= src MUL 0x2 0 dst \*= src DIV 0x3 0 dst = (src != 0) ? (dst / src) : 0 - SDIV 0x3 1 dst = (src != 0) ? (dst s/ src) : 0 + SDIV 0x3 1 dst = (src == 0) ? 0 : ((src == -1 && dst == LLONG_MIN) ? LLONG_MIN : (dst s/ src)) OR 0x4 0 dst \|= src AND 0x5 0 dst &= src LSH 0x6 0 dst <<= (src & mask) RSH 0x7 0 dst >>= (src & mask) NEG 0x8 0 dst = -dst MOD 0x9 0 dst = (src != 0) ? (dst % src) : dst - SMOD 0x9 1 dst = (src != 0) ? (dst s% src) : dst + SMOD 0x9 1 dst = (src == 0) ? dst : ((src == -1 && dst == LLONG_MIN) ? 0: (dst s% src)) XOR 0xa 0 dst ^= src MOV 0xb 0 dst = src MOVSX 0xb 8/16/32 dst = (s8,s16,s32)src ARSH 0xc 0 :term:`sign extending` dst >>= (src & mask) END 0xd 0 byte swap operations (see `Byte swap instructions`_ below) - ===== ===== ======= ========================================================== + ===== ===== ======= =================================================================================== Underflow and overflow are allowed during arithmetic operations, meaning the 64-bit or 32-bit value will wrap. If BPF program execution would result in division by zero, the destination register is instead set to zero. +Otherwise, for ``ALU64``, if execution would result in ``LLONG_MIN`` +dividing -1, the desination register is instead set to ``LLONG_MIN``. For +``ALU``, if execution would result in ``INT_MIN`` dividing -1, the +desination register is instead set to ``INT_MIN``. + If execution would result in modulo by zero, for ``ALU64`` the value of the destination register is unchanged whereas for ``ALU`` the upper -32 bits of the destination register are zeroed. +32 bits of the destination register are zeroed. Otherwise, for ``ALU64``, +if execution would resuslt in ``LLONG_MIN`` modulo -1, the destination +register is instead set to 0. For ``ALU``, if execution would result in +``INT_MIN`` modulo -1, the destination register is instead set to 0. ``{ADD, X, ALU}``, where 'code' = ``ADD``, 'source' = ``X``, and 'class' = ``ALU``, means:: diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index e390c43..39577f1 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -188,8 +188,10 @@ enum aarch64_insn_ldst_type { AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX, AARCH64_INSN_LDST_LOAD_PAIR_POST_INDEX, AARCH64_INSN_LDST_STORE_PAIR_POST_INDEX, + AARCH64_INSN_LDST_LOAD_ACQ, AARCH64_INSN_LDST_LOAD_EX, AARCH64_INSN_LDST_LOAD_ACQ_EX, + AARCH64_INSN_LDST_STORE_REL, AARCH64_INSN_LDST_STORE_EX, AARCH64_INSN_LDST_STORE_REL_EX, AARCH64_INSN_LDST_SIGNED_LOAD_IMM_OFFSET, @@ -351,8 +353,10 @@ __AARCH64_INSN_FUNCS(ldr_imm, 0x3FC00000, 0x39400000) __AARCH64_INSN_FUNCS(ldr_lit, 0xBF000000, 0x18000000) __AARCH64_INSN_FUNCS(ldrsw_lit, 0xFF000000, 0x98000000) __AARCH64_INSN_FUNCS(exclusive, 0x3F800000, 0x08000000) -__AARCH64_INSN_FUNCS(load_ex, 0x3F400000, 0x08400000) -__AARCH64_INSN_FUNCS(store_ex, 0x3F400000, 0x08000000) +__AARCH64_INSN_FUNCS(load_acq, 0x3FDFFC00, 0x08DFFC00) +__AARCH64_INSN_FUNCS(store_rel, 0x3FDFFC00, 0x089FFC00) +__AARCH64_INSN_FUNCS(load_ex, 0x3FC00000, 0x08400000) +__AARCH64_INSN_FUNCS(store_ex, 0x3FC00000, 0x08000000) __AARCH64_INSN_FUNCS(mops, 0x3B200C00, 0x19000400) __AARCH64_INSN_FUNCS(stp, 0x7FC00000, 0x29000000) __AARCH64_INSN_FUNCS(ldp, 0x7FC00000, 0x29400000) @@ -602,6 +606,10 @@ u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1, int offset, enum aarch64_insn_variant variant, enum aarch64_insn_ldst_type type); +u32 aarch64_insn_gen_load_acq_store_rel(enum aarch64_insn_register reg, + enum aarch64_insn_register base, + enum aarch64_insn_size_type size, + enum aarch64_insn_ldst_type type); u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg, enum aarch64_insn_register base, enum aarch64_insn_register state, diff --git a/arch/arm64/lib/insn.c b/arch/arm64/lib/insn.c index b008a9b..9bef696 100644 --- a/arch/arm64/lib/insn.c +++ b/arch/arm64/lib/insn.c @@ -540,6 +540,35 @@ u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1, offset >> shift); } +u32 aarch64_insn_gen_load_acq_store_rel(enum aarch64_insn_register reg, + enum aarch64_insn_register base, + enum aarch64_insn_size_type size, + enum aarch64_insn_ldst_type type) +{ + u32 insn; + + switch (type) { + case AARCH64_INSN_LDST_LOAD_ACQ: + insn = aarch64_insn_get_load_acq_value(); + break; + case AARCH64_INSN_LDST_STORE_REL: + insn = aarch64_insn_get_store_rel_value(); + break; + default: + pr_err("%s: unknown load-acquire/store-release encoding %d\n", + __func__, type); + return AARCH64_BREAK_FAULT; + } + + insn = aarch64_insn_encode_ldst_size(size, insn); + + insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, + reg); + + return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, + base); +} + u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg, enum aarch64_insn_register base, enum aarch64_insn_register state, diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index b22ab2f..a3b0e69 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -119,6 +119,26 @@ aarch64_insn_gen_load_store_ex(Rt, Rn, Rs, A64_SIZE(sf), \ AARCH64_INSN_LDST_STORE_REL_EX) +/* Load-acquire & store-release */ +#define A64_LDAR(Rt, Rn, size) \ + aarch64_insn_gen_load_acq_store_rel(Rt, Rn, AARCH64_INSN_SIZE_##size, \ + AARCH64_INSN_LDST_LOAD_ACQ) +#define A64_STLR(Rt, Rn, size) \ + aarch64_insn_gen_load_acq_store_rel(Rt, Rn, AARCH64_INSN_SIZE_##size, \ + AARCH64_INSN_LDST_STORE_REL) + +/* Rt = [Rn] (load acquire) */ +#define A64_LDARB(Wt, Xn) A64_LDAR(Wt, Xn, 8) +#define A64_LDARH(Wt, Xn) A64_LDAR(Wt, Xn, 16) +#define A64_LDAR32(Wt, Xn) A64_LDAR(Wt, Xn, 32) +#define A64_LDAR64(Xt, Xn) A64_LDAR(Xt, Xn, 64) + +/* [Rn] = Rt (store release) */ +#define A64_STLRB(Wt, Xn) A64_STLR(Wt, Xn, 8) +#define A64_STLRH(Wt, Xn) A64_STLR(Wt, Xn, 16) +#define A64_STLR32(Wt, Xn) A64_STLR(Wt, Xn, 32) +#define A64_STLR64(Xt, Xn) A64_STLR(Xt, Xn, 64) + /* * LSE atomics * diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 8446848..70d7c89 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -272,7 +272,7 @@ static inline void emit_a64_add_i(const bool is64, const int dst, const int src, { if (is_addsub_imm(imm)) { emit(A64_ADD_I(is64, dst, src, imm), ctx); - } else if (is_addsub_imm(-imm)) { + } else if (is_addsub_imm(-(u32)imm)) { emit(A64_SUB_I(is64, dst, src, -imm), ctx); } else { emit_a64_mov_i(is64, tmp, imm, ctx); @@ -647,6 +647,81 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) return 0; } +static int emit_atomic_ld_st(const struct bpf_insn *insn, struct jit_ctx *ctx) +{ + const s32 imm = insn->imm; + const s16 off = insn->off; + const u8 code = insn->code; + const bool arena = BPF_MODE(code) == BPF_PROBE_ATOMIC; + const u8 arena_vm_base = bpf2a64[ARENA_VM_START]; + const u8 dst = bpf2a64[insn->dst_reg]; + const u8 src = bpf2a64[insn->src_reg]; + const u8 tmp = bpf2a64[TMP_REG_1]; + u8 reg; + + switch (imm) { + case BPF_LOAD_ACQ: + reg = src; + break; + case BPF_STORE_REL: + reg = dst; + break; + default: + pr_err_once("unknown atomic load/store op code %02x\n", imm); + return -EINVAL; + } + + if (off) { + emit_a64_add_i(1, tmp, reg, tmp, off, ctx); + reg = tmp; + } + if (arena) { + emit(A64_ADD(1, tmp, reg, arena_vm_base), ctx); + reg = tmp; + } + + switch (imm) { + case BPF_LOAD_ACQ: + switch (BPF_SIZE(code)) { + case BPF_B: + emit(A64_LDARB(dst, reg), ctx); + break; + case BPF_H: + emit(A64_LDARH(dst, reg), ctx); + break; + case BPF_W: + emit(A64_LDAR32(dst, reg), ctx); + break; + case BPF_DW: + emit(A64_LDAR64(dst, reg), ctx); + break; + } + break; + case BPF_STORE_REL: + switch (BPF_SIZE(code)) { + case BPF_B: + emit(A64_STLRB(src, reg), ctx); + break; + case BPF_H: + emit(A64_STLRH(src, reg), ctx); + break; + case BPF_W: + emit(A64_STLR32(src, reg), ctx); + break; + case BPF_DW: + emit(A64_STLR64(src, reg), ctx); + break; + } + break; + default: + pr_err_once("unexpected atomic load/store op code %02x\n", + imm); + return -EINVAL; + } + + return 0; +} + #ifdef CONFIG_ARM64_LSE_ATOMICS static int emit_lse_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx) { @@ -1159,7 +1234,7 @@ emit_bswap_uxt: case BPF_ALU64 | BPF_SUB | BPF_K: if (is_addsub_imm(imm)) { emit(A64_SUB_I(is64, dst, dst, imm), ctx); - } else if (is_addsub_imm(-imm)) { + } else if (is_addsub_imm(-(u32)imm)) { emit(A64_ADD_I(is64, dst, dst, -imm), ctx); } else { emit_a64_mov_i(is64, tmp, imm, ctx); @@ -1330,7 +1405,7 @@ emit_cond_jmp: case BPF_JMP32 | BPF_JSLE | BPF_K: if (is_addsub_imm(imm)) { emit(A64_CMP_I(is64, dst, imm), ctx); - } else if (is_addsub_imm(-imm)) { + } else if (is_addsub_imm(-(u32)imm)) { emit(A64_CMN_I(is64, dst, -imm), ctx); } else { emit_a64_mov_i(is64, tmp, imm, ctx); @@ -1641,11 +1716,17 @@ emit_cond_jmp: return ret; break; + case BPF_STX | BPF_ATOMIC | BPF_B: + case BPF_STX | BPF_ATOMIC | BPF_H: case BPF_STX | BPF_ATOMIC | BPF_W: case BPF_STX | BPF_ATOMIC | BPF_DW: + case BPF_STX | BPF_PROBE_ATOMIC | BPF_B: + case BPF_STX | BPF_PROBE_ATOMIC | BPF_H: case BPF_STX | BPF_PROBE_ATOMIC | BPF_W: case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW: - if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS)) + if (bpf_atomic_is_load_store(insn)) + ret = emit_atomic_ld_st(insn, ctx); + else if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS)) ret = emit_lse_atomic(insn, ctx); else ret = emit_ll_sc_atomic(insn, ctx); @@ -2669,7 +2750,8 @@ bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena) switch (insn->code) { case BPF_STX | BPF_ATOMIC | BPF_W: case BPF_STX | BPF_ATOMIC | BPF_DW: - if (!cpus_have_cap(ARM64_HAS_LSE_ATOMICS)) + if (!bpf_atomic_is_load_store(insn) && + !cpus_have_cap(ARM64_HAS_LSE_ATOMICS)) return false; } return true; diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 9d440a0..0776dfd 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -2919,10 +2919,16 @@ bool bpf_jit_supports_arena(void) bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena) { - /* - * Currently the verifier uses this function only to check which - * atomic stores to arena are supported, and they all are. - */ + if (!in_arena) + return true; + switch (insn->code) { + case BPF_STX | BPF_ATOMIC | BPF_B: + case BPF_STX | BPF_ATOMIC | BPF_H: + case BPF_STX | BPF_ATOMIC | BPF_W: + case BPF_STX | BPF_ATOMIC | BPF_DW: + if (bpf_atomic_is_load_store(insn)) + return false; + } return true; } diff --git a/arch/x86/net/Makefile b/arch/x86/net/Makefile index 383c873..dddbefc 100644 --- a/arch/x86/net/Makefile +++ b/arch/x86/net/Makefile @@ -6,5 +6,5 @@ ifeq ($(CONFIG_X86_32),y) obj-$(CONFIG_BPF_JIT) += bpf_jit_comp32.o else - obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o + obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o bpf_timed_may_goto.o endif diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 72776dc..9e5fe2b 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1250,8 +1250,8 @@ static void emit_st_r12(u8 **pprog, u32 size, u32 dst_reg, int off, int imm) emit_st_index(pprog, size, dst_reg, X86_REG_R12, off, imm); } -static int emit_atomic(u8 **pprog, u8 atomic_op, - u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size) +static int emit_atomic_rmw(u8 **pprog, u32 atomic_op, + u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size) { u8 *prog = *pprog; @@ -1291,8 +1291,9 @@ static int emit_atomic(u8 **pprog, u8 atomic_op, return 0; } -static int emit_atomic_index(u8 **pprog, u8 atomic_op, u32 size, - u32 dst_reg, u32 src_reg, u32 index_reg, int off) +static int emit_atomic_rmw_index(u8 **pprog, u32 atomic_op, u32 size, + u32 dst_reg, u32 src_reg, u32 index_reg, + int off) { u8 *prog = *pprog; @@ -1305,7 +1306,7 @@ static int emit_atomic_index(u8 **pprog, u8 atomic_op, u32 size, EMIT1(add_3mod(0x48, dst_reg, src_reg, index_reg)); break; default: - pr_err("bpf_jit: 1 and 2 byte atomics are not supported\n"); + pr_err("bpf_jit: 1- and 2-byte RMW atomics are not supported\n"); return -EFAULT; } @@ -1339,6 +1340,49 @@ static int emit_atomic_index(u8 **pprog, u8 atomic_op, u32 size, return 0; } +static int emit_atomic_ld_st(u8 **pprog, u32 atomic_op, u32 dst_reg, + u32 src_reg, s16 off, u8 bpf_size) +{ + switch (atomic_op) { + case BPF_LOAD_ACQ: + /* dst_reg = smp_load_acquire(src_reg + off16) */ + emit_ldx(pprog, bpf_size, dst_reg, src_reg, off); + break; + case BPF_STORE_REL: + /* smp_store_release(dst_reg + off16, src_reg) */ + emit_stx(pprog, bpf_size, dst_reg, src_reg, off); + break; + default: + pr_err("bpf_jit: unknown atomic load/store opcode %02x\n", + atomic_op); + return -EFAULT; + } + + return 0; +} + +static int emit_atomic_ld_st_index(u8 **pprog, u32 atomic_op, u32 size, + u32 dst_reg, u32 src_reg, u32 index_reg, + int off) +{ + switch (atomic_op) { + case BPF_LOAD_ACQ: + /* dst_reg = smp_load_acquire(src_reg + idx_reg + off16) */ + emit_ldx_index(pprog, size, dst_reg, src_reg, index_reg, off); + break; + case BPF_STORE_REL: + /* smp_store_release(dst_reg + idx_reg + off16, src_reg) */ + emit_stx_index(pprog, size, dst_reg, src_reg, index_reg, off); + break; + default: + pr_err("bpf_jit: unknown atomic load/store opcode %02x\n", + atomic_op); + return -EFAULT; + } + + return 0; +} + #define DONT_CLEAR 1 bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs) @@ -2121,6 +2165,13 @@ populate_extable: } break; + case BPF_STX | BPF_ATOMIC | BPF_B: + case BPF_STX | BPF_ATOMIC | BPF_H: + if (!bpf_atomic_is_load_store(insn)) { + pr_err("bpf_jit: 1- and 2-byte RMW atomics are not supported\n"); + return -EFAULT; + } + fallthrough; case BPF_STX | BPF_ATOMIC | BPF_W: case BPF_STX | BPF_ATOMIC | BPF_DW: if (insn->imm == (BPF_AND | BPF_FETCH) || @@ -2156,10 +2207,10 @@ populate_extable: EMIT2(simple_alu_opcodes[BPF_OP(insn->imm)], add_2reg(0xC0, AUX_REG, real_src_reg)); /* Attempt to swap in new value */ - err = emit_atomic(&prog, BPF_CMPXCHG, - real_dst_reg, AUX_REG, - insn->off, - BPF_SIZE(insn->code)); + err = emit_atomic_rmw(&prog, BPF_CMPXCHG, + real_dst_reg, AUX_REG, + insn->off, + BPF_SIZE(insn->code)); if (WARN_ON(err)) return err; /* @@ -2174,17 +2225,35 @@ populate_extable: break; } - err = emit_atomic(&prog, insn->imm, dst_reg, src_reg, - insn->off, BPF_SIZE(insn->code)); + if (bpf_atomic_is_load_store(insn)) + err = emit_atomic_ld_st(&prog, insn->imm, dst_reg, src_reg, + insn->off, BPF_SIZE(insn->code)); + else + err = emit_atomic_rmw(&prog, insn->imm, dst_reg, src_reg, + insn->off, BPF_SIZE(insn->code)); if (err) return err; break; + case BPF_STX | BPF_PROBE_ATOMIC | BPF_B: + case BPF_STX | BPF_PROBE_ATOMIC | BPF_H: + if (!bpf_atomic_is_load_store(insn)) { + pr_err("bpf_jit: 1- and 2-byte RMW atomics are not supported\n"); + return -EFAULT; + } + fallthrough; case BPF_STX | BPF_PROBE_ATOMIC | BPF_W: case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW: start_of_ldx = prog; - err = emit_atomic_index(&prog, insn->imm, BPF_SIZE(insn->code), - dst_reg, src_reg, X86_REG_R12, insn->off); + + if (bpf_atomic_is_load_store(insn)) + err = emit_atomic_ld_st_index(&prog, insn->imm, + BPF_SIZE(insn->code), dst_reg, + src_reg, X86_REG_R12, insn->off); + else + err = emit_atomic_rmw_index(&prog, insn->imm, BPF_SIZE(insn->code), + dst_reg, src_reg, X86_REG_R12, + insn->off); if (err) return err; goto populate_extable; @@ -3801,3 +3870,8 @@ u64 bpf_arch_uaddress_limit(void) { return 0; } + +bool bpf_jit_supports_timed_may_goto(void) +{ + return true; +} diff --git a/arch/x86/net/bpf_timed_may_goto.S b/arch/x86/net/bpf_timed_may_goto.S new file mode 100644 index 0000000..54c690c --- /dev/null +++ b/arch/x86/net/bpf_timed_may_goto.S @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include +#include +#include + + .code64 + .section .text, "ax" + +SYM_FUNC_START(arch_bpf_timed_may_goto) + ANNOTATE_NOENDBR + + /* + * r10 passes us stack depth, load the pointer to count and timestamp + * into r10 by adding it to BPF frame pointer. + */ + leaq (%rbp, %r10, 1), %r10 + + /* Setup frame. */ + pushq %rbp + movq %rsp, %rbp + + /* Save r0-r5. */ + pushq %rax + pushq %rdi + pushq %rsi + pushq %rdx + pushq %rcx + pushq %r8 + + /* + * r10 has the pointer to count and timestamp, pass it as first + * argument. + */ + movq %r10, %rdi + + /* Emit call depth accounting for call below. */ + CALL_DEPTH_ACCOUNT + call bpf_check_timed_may_goto + + /* BPF_REG_AX=r10 will be stored into count, so move return value to it. */ + movq %rax, %r10 + + /* Restore r5-r0. */ + popq %r8 + popq %rcx + popq %rdx + popq %rsi + popq %rdi + popq %rax + + leave + RET +SYM_FUNC_END(arch_bpf_timed_may_goto) diff --git a/fs/bpf_fs_kfuncs.c b/fs/bpf_fs_kfuncs.c index 3fe9f59..0841253 100644 --- a/fs/bpf_fs_kfuncs.c +++ b/fs/bpf_fs_kfuncs.c @@ -2,10 +2,12 @@ /* Copyright (c) 2024 Google LLC. */ #include +#include #include #include #include #include +#include #include #include #include @@ -93,6 +95,24 @@ __bpf_kfunc int bpf_path_d_path(struct path *path, char *buf, size_t buf__sz) return len; } +static bool match_security_bpf_prefix(const char *name__str) +{ + return !strncmp(name__str, XATTR_NAME_BPF_LSM, XATTR_NAME_BPF_LSM_LEN); +} + +static int bpf_xattr_read_permission(const char *name, struct inode *inode) +{ + if (WARN_ON(!inode)) + return -EINVAL; + + /* Allow reading xattr with user. and security.bpf. prefix */ + if (strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) && + !match_security_bpf_prefix(name)) + return -EPERM; + + return inode_permission(&nop_mnt_idmap, inode, MAY_READ); +} + /** * bpf_get_dentry_xattr - get xattr of a dentry * @dentry: dentry to get xattr from @@ -101,9 +121,10 @@ __bpf_kfunc int bpf_path_d_path(struct path *path, char *buf, size_t buf__sz) * * Get xattr *name__str* of *dentry* and store the output in *value_ptr*. * - * For security reasons, only *name__str* with prefix "user." is allowed. + * For security reasons, only *name__str* with prefixes "user." or + * "security.bpf." are allowed. * - * Return: 0 on success, a negative value on error. + * Return: length of the xattr value on success, a negative value on error. */ __bpf_kfunc int bpf_get_dentry_xattr(struct dentry *dentry, const char *name__str, struct bpf_dynptr *value_p) @@ -114,18 +135,12 @@ __bpf_kfunc int bpf_get_dentry_xattr(struct dentry *dentry, const char *name__st void *value; int ret; - if (WARN_ON(!inode)) - return -EINVAL; - - if (strncmp(name__str, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) - return -EPERM; - value_len = __bpf_dynptr_size(value_ptr); value = __bpf_dynptr_data_rw(value_ptr, value_len); if (!value) return -EINVAL; - ret = inode_permission(&nop_mnt_idmap, inode, MAY_READ); + ret = bpf_xattr_read_permission(name__str, inode); if (ret) return ret; return __vfs_getxattr(dentry, inode, name__str, value, value_len); @@ -139,9 +154,10 @@ __bpf_kfunc int bpf_get_dentry_xattr(struct dentry *dentry, const char *name__st * * Get xattr *name__str* of *file* and store the output in *value_ptr*. * - * For security reasons, only *name__str* with prefix "user." is allowed. + * For security reasons, only *name__str* with prefixes "user." or + * "security.bpf." are allowed. * - * Return: 0 on success, a negative value on error. + * Return: length of the xattr value on success, a negative value on error. */ __bpf_kfunc int bpf_get_file_xattr(struct file *file, const char *name__str, struct bpf_dynptr *value_p) @@ -154,6 +170,160 @@ __bpf_kfunc int bpf_get_file_xattr(struct file *file, const char *name__str, __bpf_kfunc_end_defs(); +static int bpf_xattr_write_permission(const char *name, struct inode *inode) +{ + if (WARN_ON(!inode)) + return -EINVAL; + + /* Only allow setting and removing security.bpf. xattrs */ + if (!match_security_bpf_prefix(name)) + return -EPERM; + + return inode_permission(&nop_mnt_idmap, inode, MAY_WRITE); +} + +/** + * bpf_set_dentry_xattr_locked - set a xattr of a dentry + * @dentry: dentry to get xattr from + * @name__str: name of the xattr + * @value_p: xattr value + * @flags: flags to pass into filesystem operations + * + * Set xattr *name__str* of *dentry* to the value in *value_ptr*. + * + * For security reasons, only *name__str* with prefix "security.bpf." + * is allowed. + * + * The caller already locked dentry->d_inode. + * + * Return: 0 on success, a negative value on error. + */ +int bpf_set_dentry_xattr_locked(struct dentry *dentry, const char *name__str, + const struct bpf_dynptr *value_p, int flags) +{ + + struct bpf_dynptr_kern *value_ptr = (struct bpf_dynptr_kern *)value_p; + struct inode *inode = d_inode(dentry); + const void *value; + u32 value_len; + int ret; + + value_len = __bpf_dynptr_size(value_ptr); + value = __bpf_dynptr_data(value_ptr, value_len); + if (!value) + return -EINVAL; + + ret = bpf_xattr_write_permission(name__str, inode); + if (ret) + return ret; + + ret = __vfs_setxattr(&nop_mnt_idmap, dentry, inode, name__str, + value, value_len, flags); + if (!ret) { + fsnotify_xattr(dentry); + + /* This xattr is set by BPF LSM, so we do not call + * security_inode_post_setxattr. Otherwise, we would + * risk deadlocks by calling back to the same kfunc. + * + * This is the same as security_inode_setsecurity(). + */ + } + return ret; +} + +/** + * bpf_remove_dentry_xattr_locked - remove a xattr of a dentry + * @dentry: dentry to get xattr from + * @name__str: name of the xattr + * + * Rmove xattr *name__str* of *dentry*. + * + * For security reasons, only *name__str* with prefix "security.bpf." + * is allowed. + * + * The caller already locked dentry->d_inode. + * + * Return: 0 on success, a negative value on error. + */ +int bpf_remove_dentry_xattr_locked(struct dentry *dentry, const char *name__str) +{ + struct inode *inode = d_inode(dentry); + int ret; + + ret = bpf_xattr_write_permission(name__str, inode); + if (ret) + return ret; + + ret = __vfs_removexattr(&nop_mnt_idmap, dentry, name__str); + if (!ret) { + fsnotify_xattr(dentry); + + /* This xattr is removed by BPF LSM, so we do not call + * security_inode_post_removexattr. Otherwise, we would + * risk deadlocks by calling back to the same kfunc. + */ + } + return ret; +} + +__bpf_kfunc_start_defs(); + +/** + * bpf_set_dentry_xattr - set a xattr of a dentry + * @dentry: dentry to get xattr from + * @name__str: name of the xattr + * @value_p: xattr value + * @flags: flags to pass into filesystem operations + * + * Set xattr *name__str* of *dentry* to the value in *value_ptr*. + * + * For security reasons, only *name__str* with prefix "security.bpf." + * is allowed. + * + * The caller has not locked dentry->d_inode. + * + * Return: 0 on success, a negative value on error. + */ +__bpf_kfunc int bpf_set_dentry_xattr(struct dentry *dentry, const char *name__str, + const struct bpf_dynptr *value_p, int flags) +{ + struct inode *inode = d_inode(dentry); + int ret; + + inode_lock(inode); + ret = bpf_set_dentry_xattr_locked(dentry, name__str, value_p, flags); + inode_unlock(inode); + return ret; +} + +/** + * bpf_remove_dentry_xattr - remove a xattr of a dentry + * @dentry: dentry to get xattr from + * @name__str: name of the xattr + * + * Rmove xattr *name__str* of *dentry*. + * + * For security reasons, only *name__str* with prefix "security.bpf." + * is allowed. + * + * The caller has not locked dentry->d_inode. + * + * Return: 0 on success, a negative value on error. + */ +__bpf_kfunc int bpf_remove_dentry_xattr(struct dentry *dentry, const char *name__str) +{ + struct inode *inode = d_inode(dentry); + int ret; + + inode_lock(inode); + ret = bpf_remove_dentry_xattr_locked(dentry, name__str); + inode_unlock(inode); + return ret; +} + +__bpf_kfunc_end_defs(); + BTF_KFUNCS_START(bpf_fs_kfunc_set_ids) BTF_ID_FLAGS(func, bpf_get_task_exe_file, KF_ACQUIRE | KF_TRUSTED_ARGS | KF_RET_NULL) @@ -161,6 +331,8 @@ BTF_ID_FLAGS(func, bpf_put_file, KF_RELEASE) BTF_ID_FLAGS(func, bpf_path_d_path, KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_get_dentry_xattr, KF_SLEEPABLE | KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_get_file_xattr, KF_SLEEPABLE | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_set_dentry_xattr, KF_SLEEPABLE | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_remove_dentry_xattr, KF_SLEEPABLE | KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_fs_kfunc_set_ids) static int bpf_fs_kfuncs_filter(const struct bpf_prog *prog, u32 kfunc_id) @@ -171,6 +343,37 @@ static int bpf_fs_kfuncs_filter(const struct bpf_prog *prog, u32 kfunc_id) return -EACCES; } +/* bpf_[set|remove]_dentry_xattr.* hooks have KF_TRUSTED_ARGS and + * KF_SLEEPABLE, so they are only available to sleepable hooks with + * dentry arguments. + * + * Setting and removing xattr requires exclusive lock on dentry->d_inode. + * Some hooks already locked d_inode, while some hooks have not locked + * d_inode. Therefore, we need different kfuncs for different hooks. + * Specifically, hooks in the following list (d_inode_locked_hooks) + * should call bpf_[set|remove]_dentry_xattr_locked; while other hooks + * should call bpf_[set|remove]_dentry_xattr. + */ +BTF_SET_START(d_inode_locked_hooks) +BTF_ID(func, bpf_lsm_inode_post_removexattr) +BTF_ID(func, bpf_lsm_inode_post_setattr) +BTF_ID(func, bpf_lsm_inode_post_setxattr) +BTF_ID(func, bpf_lsm_inode_removexattr) +BTF_ID(func, bpf_lsm_inode_rmdir) +BTF_ID(func, bpf_lsm_inode_setattr) +BTF_ID(func, bpf_lsm_inode_setxattr) +BTF_ID(func, bpf_lsm_inode_unlink) +#ifdef CONFIG_SECURITY_PATH +BTF_ID(func, bpf_lsm_path_unlink) +BTF_ID(func, bpf_lsm_path_rmdir) +#endif /* CONFIG_SECURITY_PATH */ +BTF_SET_END(d_inode_locked_hooks) + +bool bpf_lsm_has_d_inode_locked(const struct bpf_prog *prog) +{ + return btf_id_set_contains(&d_inode_locked_hooks, prog->aux->attach_btf_id); +} + static const struct btf_kfunc_id_set bpf_fs_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_fs_kfunc_set_ids, diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 7fc6908..9de7adb 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -111,6 +111,7 @@ struct bpf_prog_list { struct bpf_prog *prog; struct bpf_cgroup_link *link; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; + u32 flags; }; int cgroup_bpf_inherit(struct cgroup *cgrp); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f3f50e2..111bea4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -968,6 +968,7 @@ struct bpf_insn_access_aux { struct { struct btf *btf; u32 btf_id; + u32 ref_obj_id; }; }; struct bpf_verifier_log *log; /* for verbose logs */ @@ -990,6 +991,21 @@ static inline bool bpf_pseudo_func(const struct bpf_insn *insn) return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC; } +/* Given a BPF_ATOMIC instruction @atomic_insn, return true if it is an + * atomic load or store, and false if it is a read-modify-write instruction. + */ +static inline bool +bpf_atomic_is_load_store(const struct bpf_insn *atomic_insn) +{ + switch (atomic_insn->imm) { + case BPF_LOAD_ACQ: + case BPF_STORE_REL: + return true; + default: + return false; + } +} + struct bpf_prog_ops { int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); @@ -1481,6 +1497,8 @@ struct bpf_ctx_arg_aux { enum bpf_reg_type reg_type; struct btf *btf; u32 btf_id; + u32 ref_obj_id; + bool refcounted; }; struct btf_mod_pair { @@ -1503,11 +1521,12 @@ struct bpf_prog_aux { u32 real_func_cnt; /* includes hidden progs, only used for JIT and freeing progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ u32 attach_btf_id; /* in-kernel BTF type id to attach to */ + u32 attach_st_ops_member_off; u32 ctx_arg_info_size; u32 max_rdonly_access; u32 max_rdwr_access; struct btf *attach_btf; - const struct bpf_ctx_arg_aux *ctx_arg_info; + struct bpf_ctx_arg_aux *ctx_arg_info; void __percpu *priv_stack_ptr; struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */ struct bpf_prog *dst_prog; @@ -1528,6 +1547,7 @@ struct bpf_prog_aux { bool jits_use_priv_stack; bool priv_stack_requested; bool changes_pkt_data; + bool might_sleep; u64 prog_array_member_cnt; /* counts how many times as member of prog_array */ struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */ struct bpf_arena *arena; @@ -1547,6 +1567,7 @@ struct bpf_prog_aux { #endif struct bpf_ksym ksym; const struct bpf_prog_ops *ops; + const struct bpf_struct_ops *st_ops; struct bpf_map **used_maps; struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */ struct btf_mod_pair *used_btfs; @@ -1945,6 +1966,9 @@ static inline void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_op #endif +int bpf_prog_ctx_arg_info_init(struct bpf_prog *prog, + const struct bpf_ctx_arg_aux *info, u32 cnt); + #if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM) int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, int cgroup_atype); @@ -1980,6 +2004,7 @@ struct bpf_array { */ enum { BPF_MAX_LOOPS = 8 * 1024 * 1024, + BPF_MAX_TIMED_LOOPS = 0xffff, }; #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ @@ -2036,6 +2061,8 @@ int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void); +const struct bpf_func_proto *bpf_get_perf_event_read_value_proto(void); + typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, unsigned long off, unsigned long len); typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type, @@ -2546,7 +2573,7 @@ struct bpf_iter__bpf_map_elem { int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); -bool bpf_iter_prog_supported(struct bpf_prog *prog); +int bpf_iter_prog_supported(struct bpf_prog *prog); const struct bpf_func_proto * bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog); diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h index aefcd65..643809c 100644 --- a/include/linux/bpf_lsm.h +++ b/include/linux/bpf_lsm.h @@ -48,6 +48,11 @@ void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, bpf_func_t *bpf_func) int bpf_lsm_get_retval_range(const struct bpf_prog *prog, struct bpf_retval_range *range); +int bpf_set_dentry_xattr_locked(struct dentry *dentry, const char *name__str, + const struct bpf_dynptr *value_p, int flags); +int bpf_remove_dentry_xattr_locked(struct dentry *dentry, const char *name__str); +bool bpf_lsm_has_d_inode_locked(const struct bpf_prog *prog); + #else /* !CONFIG_BPF_LSM */ static inline bool bpf_lsm_is_sleepable_hook(u32 btf_id) @@ -86,6 +91,19 @@ static inline int bpf_lsm_get_retval_range(const struct bpf_prog *prog, { return -EOPNOTSUPP; } +static inline int bpf_set_dentry_xattr_locked(struct dentry *dentry, const char *name__str, + const struct bpf_dynptr *value_p, int flags) +{ + return -EOPNOTSUPP; +} +static inline int bpf_remove_dentry_xattr_locked(struct dentry *dentry, const char *name__str) +{ + return -EOPNOTSUPP; +} +static inline bool bpf_lsm_has_d_inode_locked(const struct bpf_prog *prog) +{ + return false; +} #endif /* CONFIG_BPF_LSM */ #endif /* _LINUX_BPF_LSM_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 32c23f2..d6cfc4e 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -427,11 +427,6 @@ struct bpf_verifier_state { bool active_rcu_lock; bool speculative; - /* If this state was ever pointed-to by other state's loop_entry field - * this flag would be set to true. Used to avoid freeing such states - * while they are still in use. - */ - bool used_as_loop_entry; bool in_sleepable; /* first and last insn idx of this verifier state */ @@ -458,6 +453,11 @@ struct bpf_verifier_state { u32 dfs_depth; u32 callback_unroll_depth; u32 may_goto_depth; + /* If this state was ever pointed-to by other state's loop_entry field + * this flag would be set to true. Used to avoid freeing such states + * while they are still in use. + */ + u32 used_as_loop_entry; }; #define bpf_get_spilled_reg(slot, frame, mask) \ @@ -498,8 +498,10 @@ struct bpf_verifier_state { /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; - struct bpf_verifier_state_list *next; - int miss_cnt, hit_cnt; + struct list_head node; + u32 miss_cnt; + u32 hit_cnt:31; + u32 in_free_list:1; }; struct bpf_loop_inline_state { @@ -589,6 +591,8 @@ struct bpf_insn_aux_data { * accepts callback function as a parameter. */ bool calls_callback; + /* registers alive before this instruction. */ + u16 live_regs_before; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ @@ -665,6 +669,7 @@ struct bpf_subprog_info { /* true if bpf_fastcall stack region is used by functions that can't be inlined */ bool keep_fastcall_stack: 1; bool changes_pkt_data: 1; + bool might_sleep: 1; enum priv_stack_mode priv_stack_mode; u8 arg_cnt; @@ -710,8 +715,11 @@ struct bpf_verifier_env { bool test_state_freq; /* test verifier with different pruning frequency */ bool test_reg_invariants; /* fail verification on register invariants violations */ struct bpf_verifier_state *cur_state; /* current verifier state */ - struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ - struct bpf_verifier_state_list *free_list; + /* Search pruning optimization, array of list_heads for + * lists of struct bpf_verifier_state_list. + */ + struct list_head *explored_states; + struct list_head free_list; /* list of struct bpf_verifier_state_list */ struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ struct btf_mod_pair used_btfs[MAX_USED_BTFS]; /* array of BTF's used by BPF program */ u32 used_map_cnt; /* number of used maps */ @@ -742,7 +750,11 @@ struct bpf_verifier_env { struct { int *insn_state; int *insn_stack; + /* vector of instruction indexes sorted in post-order */ + int *insn_postorder; int cur_stack; + /* current position in the insn_postorder vector */ + int cur_postorder; } cfg; struct backtrack_state bt; struct bpf_insn_hist_entry *insn_hist; @@ -767,6 +779,8 @@ struct bpf_verifier_env { u32 peak_states; /* longest register parentage chain walked for liveness marking */ u32 longest_mark_read_walk; + u32 free_list_size; + u32 explored_states_size; bpfptr_t fd_array; /* bit mask to keep track of whether a register has been accessed diff --git a/include/linux/btf.h b/include/linux/btf.h index 2a08a2b..ebc0c0c 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -76,6 +76,9 @@ #define KF_ITER_DESTROY (1 << 10) /* kfunc implements BPF iter destructor */ #define KF_RCU_PROTECTED (1 << 11) /* kfunc should be protected by rcu cs when they are invoked */ #define KF_FASTCALL (1 << 12) /* kfunc supports bpf_fastcall protocol */ +#define KF_ARENA_RET (1 << 13) /* kfunc returns an arena pointer */ +#define KF_ARENA_ARG1 (1 << 14) /* kfunc takes an arena pointer as its first argument */ +#define KF_ARENA_ARG2 (1 << 15) /* kfunc takes an arena pointer as its second argument */ /* * Tag marking a kernel function as a kfunc. This is meant to minimize the diff --git a/include/linux/filter.h b/include/linux/filter.h index d36d5d5..f5cf4d3 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -364,6 +364,8 @@ static inline bool insn_is_cast_user(const struct bpf_insn *insn) * BPF_XOR | BPF_FETCH src_reg = atomic_fetch_xor(dst_reg + off16, src_reg); * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) + * BPF_LOAD_ACQ dst_reg = smp_load_acquire(src_reg + off16) + * BPF_STORE_REL smp_store_release(dst_reg + off16, src_reg) */ #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ @@ -469,6 +471,16 @@ static inline bool insn_is_cast_user(const struct bpf_insn *insn) .off = 0, \ .imm = BPF_CALL_IMM(FUNC) }) +/* Kfunc call */ + +#define BPF_CALL_KFUNC(OFF, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_CALL, \ + .dst_reg = 0, \ + .src_reg = BPF_PSEUDO_KFUNC_CALL, \ + .off = OFF, \ + .imm = IMM }) + /* Raw code statement block */ #define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM) \ @@ -659,6 +671,11 @@ struct bpf_prog_stats { struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); +struct bpf_timed_may_goto { + u64 count; + u64 timestamp; +}; + struct sk_filter { refcount_t refcnt; struct rcu_head rcu; @@ -1120,8 +1137,11 @@ bool bpf_jit_supports_ptr_xchg(void); bool bpf_jit_supports_arena(void); bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena); bool bpf_jit_supports_private_stack(void); +bool bpf_jit_supports_timed_may_goto(void); u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); +u64 arch_bpf_timed_may_goto(void); +u64 bpf_check_timed_may_goto(struct bpf_timed_may_goto *); bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id); static inline bool bpf_dump_raw_ok(const struct cred *cred) diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 2bf909f..bf3bbac 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -426,14 +426,14 @@ LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule) #endif /* CONFIG_AUDIT */ #ifdef CONFIG_BPF_SYSCALL -LSM_HOOK(int, 0, bpf, int cmd, union bpf_attr *attr, unsigned int size) +LSM_HOOK(int, 0, bpf, int cmd, union bpf_attr *attr, unsigned int size, bool kernel) LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode) LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog) LSM_HOOK(int, 0, bpf_map_create, struct bpf_map *map, union bpf_attr *attr, - struct bpf_token *token) + struct bpf_token *token, bool kernel) LSM_HOOK(void, LSM_RET_VOID, bpf_map_free, struct bpf_map *map) LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr, - struct bpf_token *token) + struct bpf_token *token, bool kernel) LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog) LSM_HOOK(int, 0, bpf_token_create, struct bpf_token *token, union bpf_attr *attr, const struct path *path) diff --git a/include/linux/mm.h b/include/linux/mm.h index 386c9a7..4a50ba8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2477,6 +2477,11 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); +#ifdef CONFIG_BPF_SYSCALL +extern int copy_remote_vm_str(struct task_struct *tsk, unsigned long addr, + void *buf, int len, unsigned int gup_flags); +#endif + long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, diff --git a/include/linux/security.h b/include/linux/security.h index 1545d51..cc9b54d 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2249,14 +2249,14 @@ struct bpf_map; struct bpf_prog; struct bpf_token; #ifdef CONFIG_SECURITY -extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size); +extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size, bool kernel); extern int security_bpf_map(struct bpf_map *map, fmode_t fmode); extern int security_bpf_prog(struct bpf_prog *prog); extern int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, - struct bpf_token *token); + struct bpf_token *token, bool kernel); extern void security_bpf_map_free(struct bpf_map *map); extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, - struct bpf_token *token); + struct bpf_token *token, bool kernel); extern void security_bpf_prog_free(struct bpf_prog *prog); extern int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, const struct path *path); @@ -2265,7 +2265,7 @@ extern int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cm extern int security_bpf_token_capable(const struct bpf_token *token, int cap); #else static inline int security_bpf(int cmd, union bpf_attr *attr, - unsigned int size) + unsigned int size, bool kernel) { return 0; } @@ -2281,7 +2281,7 @@ static inline int security_bpf_prog(struct bpf_prog *prog) } static inline int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, - struct bpf_token *token) + struct bpf_token *token, bool kernel) { return 0; } @@ -2290,7 +2290,7 @@ static inline void security_bpf_map_free(struct bpf_map *map) { } static inline int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, - struct bpf_token *token) + struct bpf_token *token, bool kernel) { return 0; } diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index defa5bb..28705ae 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -51,6 +51,9 @@ #define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ #define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ +#define BPF_LOAD_ACQ 0x100 /* load-acquire */ +#define BPF_STORE_REL 0x110 /* store-release */ + enum bpf_cond_pseudo_jmp { BPF_MAY_GOTO = 0, }; @@ -1207,6 +1210,7 @@ enum bpf_perf_event_type { #define BPF_F_BEFORE (1U << 3) #define BPF_F_AFTER (1U << 4) #define BPF_F_ID (1U << 5) +#define BPF_F_PREORDER (1U << 6) #define BPF_F_LINK BPF_F_LINK /* 1 << 13 */ /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the @@ -1648,6 +1652,7 @@ union bpf_attr { }; __u32 next_id; __u32 open_flags; + __s32 fd_by_id_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ @@ -6019,7 +6024,10 @@ union bpf_attr { FN(user_ringbuf_drain, 209, ##ctx) \ FN(cgrp_storage_get, 210, ##ctx) \ FN(cgrp_storage_delete, 211, ##ctx) \ - /* */ + /* This helper list is effectively frozen. If you are trying to \ + * add a new helper, you should add a kfunc instead which has \ + * less stability guarantees. See Documentation/bpf/kfuncs.rst \ + */ /* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't * know or care about integer value that is now passed as second argument diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index ec1798b..266d4ff 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -36,7 +36,8 @@ struct btf_type { * bits 24-28: kind (e.g. int, ptr, array...etc) * bits 29-30: unused * bit 31: kind_flag, currently used by - * struct, union, enum, fwd and enum64 + * struct, union, enum, fwd, enum64, + * decl_tag and type_tag */ __u32 info; /* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64. diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h index 9854f9c..c7c85bb 100644 --- a/include/uapi/linux/xattr.h +++ b/include/uapi/linux/xattr.h @@ -83,6 +83,10 @@ struct xattr_args { #define XATTR_CAPS_SUFFIX "capability" #define XATTR_NAME_CAPS XATTR_SECURITY_PREFIX XATTR_CAPS_SUFFIX +#define XATTR_BPF_LSM_SUFFIX "bpf." +#define XATTR_NAME_BPF_LSM (XATTR_SECURITY_PREFIX XATTR_BPF_LSM_SUFFIX) +#define XATTR_NAME_BPF_LSM_LEN (sizeof(XATTR_NAME_BPF_LSM) - 1) + #define XATTR_POSIX_ACL_ACCESS "posix_acl_access" #define XATTR_NAME_POSIX_ACL_ACCESS XATTR_SYSTEM_PREFIX XATTR_POSIX_ACL_ACCESS #define XATTR_POSIX_ACL_DEFAULT "posix_acl_default" diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c index 095a955..647b709 100644 --- a/kernel/bpf/arena.c +++ b/kernel/bpf/arena.c @@ -577,8 +577,8 @@ __bpf_kfunc void bpf_arena_free_pages(void *p__map, void *ptr__ign, u32 page_cnt __bpf_kfunc_end_defs(); BTF_KFUNCS_START(arena_kfuncs) -BTF_ID_FLAGS(func, bpf_arena_alloc_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE) -BTF_ID_FLAGS(func, bpf_arena_free_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_arena_alloc_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE | KF_ARENA_RET | KF_ARENA_ARG2) +BTF_ID_FLAGS(func, bpf_arena_free_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE | KF_ARENA_ARG2) BTF_KFUNCS_END(arena_kfuncs) static const struct btf_kfunc_id_set common_kfunc_set = { diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c index 54ff2a8..148da8f 100644 --- a/kernel/bpf/bpf_cgrp_storage.c +++ b/kernel/bpf/bpf_cgrp_storage.c @@ -161,6 +161,7 @@ BPF_CALL_5(bpf_cgrp_storage_get, struct bpf_map *, map, struct cgroup *, cgroup, void *, value, u64, flags, gfp_t, gfp_flags) { struct bpf_local_storage_data *sdata; + bool nobusy; WARN_ON_ONCE(!bpf_rcu_lock_held()); if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) @@ -169,21 +170,21 @@ BPF_CALL_5(bpf_cgrp_storage_get, struct bpf_map *, map, struct cgroup *, cgroup, if (!cgroup) return (unsigned long)NULL; - if (!bpf_cgrp_storage_trylock()) - return (unsigned long)NULL; + nobusy = bpf_cgrp_storage_trylock(); - sdata = cgroup_storage_lookup(cgroup, map, true); + sdata = cgroup_storage_lookup(cgroup, map, nobusy); if (sdata) goto unlock; /* only allocate new storage, when the cgroup is refcounted */ if (!percpu_ref_is_dying(&cgroup->self.refcnt) && - (flags & BPF_LOCAL_STORAGE_GET_F_CREATE)) + (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) && nobusy) sdata = bpf_local_storage_update(cgroup, (struct bpf_local_storage_map *)map, value, BPF_NOEXIST, false, gfp_flags); unlock: - bpf_cgrp_storage_unlock(); + if (nobusy) + bpf_cgrp_storage_unlock(); return IS_ERR_OR_NULL(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data; } diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 1067351..380e9a7 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -335,7 +335,7 @@ static void cache_btf_id(struct bpf_iter_target_info *tinfo, tinfo->btf_id = prog->aux->attach_btf_id; } -bool bpf_iter_prog_supported(struct bpf_prog *prog) +int bpf_iter_prog_supported(struct bpf_prog *prog) { const char *attach_fname = prog->aux->attach_func_name; struct bpf_iter_target_info *tinfo = NULL, *iter; @@ -344,7 +344,7 @@ bool bpf_iter_prog_supported(struct bpf_prog *prog) int prefix_len = strlen(prefix); if (strncmp(attach_fname, prefix, prefix_len)) - return false; + return -EINVAL; mutex_lock(&targets_mutex); list_for_each_entry(iter, &targets, list) { @@ -360,12 +360,11 @@ bool bpf_iter_prog_supported(struct bpf_prog *prog) } mutex_unlock(&targets_mutex); - if (tinfo) { - prog->aux->ctx_arg_info_size = tinfo->reg_info->ctx_arg_info_size; - prog->aux->ctx_arg_info = tinfo->reg_info->ctx_arg_info; - } + if (!tinfo) + return -EINVAL; - return tinfo != NULL; + return bpf_prog_ctx_arg_info_init(prog, tinfo->reg_info->ctx_arg_info, + tinfo->reg_info->ctx_arg_info_size); } const struct bpf_func_proto * diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 967492b..0a59df1 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -316,7 +316,9 @@ BTF_ID(func, bpf_lsm_inode_getxattr) BTF_ID(func, bpf_lsm_inode_mknod) BTF_ID(func, bpf_lsm_inode_need_killpriv) BTF_ID(func, bpf_lsm_inode_post_setxattr) +BTF_ID(func, bpf_lsm_inode_post_removexattr) BTF_ID(func, bpf_lsm_inode_readlink) +BTF_ID(func, bpf_lsm_inode_removexattr) BTF_ID(func, bpf_lsm_inode_rename) BTF_ID(func, bpf_lsm_inode_rmdir) BTF_ID(func, bpf_lsm_inode_setattr) diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 040fb1c..db13ee7 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -146,39 +146,7 @@ void bpf_struct_ops_image_free(void *image) } #define MAYBE_NULL_SUFFIX "__nullable" -#define MAX_STUB_NAME 128 - -/* Return the type info of a stub function, if it exists. - * - * The name of a stub function is made up of the name of the struct_ops and - * the name of the function pointer member, separated by "__". For example, - * if the struct_ops type is named "foo_ops" and the function pointer - * member is named "bar", the stub function name would be "foo_ops__bar". - */ -static const struct btf_type * -find_stub_func_proto(const struct btf *btf, const char *st_op_name, - const char *member_name) -{ - char stub_func_name[MAX_STUB_NAME]; - const struct btf_type *func_type; - s32 btf_id; - int cp; - - cp = snprintf(stub_func_name, MAX_STUB_NAME, "%s__%s", - st_op_name, member_name); - if (cp >= MAX_STUB_NAME) { - pr_warn("Stub function name too long\n"); - return NULL; - } - btf_id = btf_find_by_name_kind(btf, stub_func_name, BTF_KIND_FUNC); - if (btf_id < 0) - return NULL; - func_type = btf_type_by_id(btf, btf_id); - if (!func_type) - return NULL; - - return btf_type_by_id(btf, func_type->type); /* FUNC_PROTO */ -} +#define REFCOUNTED_SUFFIX "__ref" /* Prepare argument info for every nullable argument of a member of a * struct_ops type. @@ -203,27 +171,44 @@ find_stub_func_proto(const struct btf *btf, const char *st_op_name, static int prepare_arg_info(struct btf *btf, const char *st_ops_name, const char *member_name, - const struct btf_type *func_proto, + const struct btf_type *func_proto, void *stub_func_addr, struct bpf_struct_ops_arg_info *arg_info) { const struct btf_type *stub_func_proto, *pointed_type; + bool is_nullable = false, is_refcounted = false; const struct btf_param *stub_args, *args; struct bpf_ctx_arg_aux *info, *info_buf; u32 nargs, arg_no, info_cnt = 0; + char ksym[KSYM_SYMBOL_LEN]; + const char *stub_fname; + const char *suffix; + s32 stub_func_id; u32 arg_btf_id; int offset; - stub_func_proto = find_stub_func_proto(btf, st_ops_name, member_name); - if (!stub_func_proto) - return 0; + stub_fname = kallsyms_lookup((unsigned long)stub_func_addr, NULL, NULL, NULL, ksym); + if (!stub_fname) { + pr_warn("Cannot find the stub function name for the %s in struct %s\n", + member_name, st_ops_name); + return -ENOENT; + } + + stub_func_id = btf_find_by_name_kind(btf, stub_fname, BTF_KIND_FUNC); + if (stub_func_id < 0) { + pr_warn("Cannot find the stub function %s in btf\n", stub_fname); + return -ENOENT; + } + + stub_func_proto = btf_type_by_id(btf, stub_func_id); + stub_func_proto = btf_type_by_id(btf, stub_func_proto->type); /* Check if the number of arguments of the stub function is the same * as the number of arguments of the function pointer. */ nargs = btf_type_vlen(func_proto); if (nargs != btf_type_vlen(stub_func_proto)) { - pr_warn("the number of arguments of the stub function %s__%s does not match the number of arguments of the member %s of struct %s\n", - st_ops_name, member_name, member_name, st_ops_name); + pr_warn("the number of arguments of the stub function %s does not match the number of arguments of the member %s of struct %s\n", + stub_fname, member_name, st_ops_name); return -EINVAL; } @@ -241,10 +226,18 @@ static int prepare_arg_info(struct btf *btf, info = info_buf; for (arg_no = 0; arg_no < nargs; arg_no++) { /* Skip arguments that is not suffixed with - * "__nullable". + * "__nullable or __ref". */ - if (!btf_param_match_suffix(btf, &stub_args[arg_no], - MAYBE_NULL_SUFFIX)) + is_nullable = btf_param_match_suffix(btf, &stub_args[arg_no], + MAYBE_NULL_SUFFIX); + is_refcounted = btf_param_match_suffix(btf, &stub_args[arg_no], + REFCOUNTED_SUFFIX); + + if (is_nullable) + suffix = MAYBE_NULL_SUFFIX; + else if (is_refcounted) + suffix = REFCOUNTED_SUFFIX; + else continue; /* Should be a pointer to struct */ @@ -253,30 +246,34 @@ static int prepare_arg_info(struct btf *btf, &arg_btf_id); if (!pointed_type || !btf_type_is_struct(pointed_type)) { - pr_warn("stub function %s__%s has %s tagging to an unsupported type\n", - st_ops_name, member_name, MAYBE_NULL_SUFFIX); + pr_warn("stub function %s has %s tagging to an unsupported type\n", + stub_fname, suffix); goto err_out; } offset = btf_ctx_arg_offset(btf, func_proto, arg_no); if (offset < 0) { - pr_warn("stub function %s__%s has an invalid trampoline ctx offset for arg#%u\n", - st_ops_name, member_name, arg_no); + pr_warn("stub function %s has an invalid trampoline ctx offset for arg#%u\n", + stub_fname, arg_no); goto err_out; } if (args[arg_no].type != stub_args[arg_no].type) { - pr_warn("arg#%u type in stub function %s__%s does not match with its original func_proto\n", - arg_no, st_ops_name, member_name); + pr_warn("arg#%u type in stub function %s does not match with its original func_proto\n", + arg_no, stub_fname); goto err_out; } /* Fill the information of the new argument */ - info->reg_type = - PTR_TRUSTED | PTR_TO_BTF_ID | PTR_MAYBE_NULL; info->btf_id = arg_btf_id; info->btf = btf; info->offset = offset; + if (is_nullable) { + info->reg_type = PTR_TRUSTED | PTR_TO_BTF_ID | PTR_MAYBE_NULL; + } else if (is_refcounted) { + info->reg_type = PTR_TRUSTED | PTR_TO_BTF_ID; + info->refcounted = true; + } info++; info_cnt++; @@ -324,6 +321,13 @@ static bool is_module_member(const struct btf *btf, u32 id) return !strcmp(btf_name_by_offset(btf, t->name_off), "module"); } +int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff) +{ + void *func_ptr = *(void **)(st_ops->cfi_stubs + moff); + + return func_ptr ? 0 : -ENOTSUPP; +} + int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, struct btf *btf, struct bpf_verifier_log *log) @@ -386,8 +390,11 @@ int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, st_ops_desc->value_type = btf_type_by_id(btf, value_id); for_each_member(i, t, member) { - const struct btf_type *func_proto; + const struct btf_type *func_proto, *ret_type; + void **stub_func_addr; + u32 moff; + moff = __btf_member_bit_offset(t, member) / 8; mname = btf_name_by_offset(btf, member->name_off); if (!*mname) { pr_warn("anon member in struct %s is not supported\n", @@ -413,9 +420,23 @@ int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, func_proto = btf_type_resolve_func_ptr(btf, member->type, NULL); - if (!func_proto) + + /* The member is not a function pointer or + * the function pointer is not supported. + */ + if (!func_proto || bpf_struct_ops_supported(st_ops, moff)) continue; + if (func_proto->type) { + ret_type = btf_type_resolve_ptr(btf, func_proto->type, NULL); + if (ret_type && !__btf_type_is_struct(ret_type)) { + pr_warn("func ptr %s in struct %s returns non-struct pointer, which is not supported\n", + mname, st_ops->name); + err = -EOPNOTSUPP; + goto errout; + } + } + if (btf_distill_func_proto(log, btf, func_proto, mname, &st_ops->func_models[i])) { @@ -425,8 +446,9 @@ int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, goto errout; } + stub_func_addr = *(void **)(st_ops->cfi_stubs + moff); err = prepare_arg_info(btf, st_ops->name, mname, - func_proto, + func_proto, stub_func_addr, arg_info + i); if (err) goto errout; @@ -1152,13 +1174,6 @@ void bpf_struct_ops_put(const void *kdata) bpf_map_put(&st_map->map); } -int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff) -{ - void *func_ptr = *(void **)(st_ops->cfi_stubs + moff); - - return func_ptr ? 0 : -ENOTSUPP; -} - static bool bpf_struct_ops_valid_to_reg(struct bpf_map *map) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index eacb701..91ce49b 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -606,6 +606,7 @@ s32 bpf_find_btf_id(const char *name, u32 kind, struct btf **btf_p) spin_unlock_bh(&btf_idr_lock); return ret; } +EXPORT_SYMBOL_GPL(bpf_find_btf_id); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, u32 id, u32 *res_id) @@ -2575,7 +2576,7 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env, return -EINVAL; } - if (btf_type_kflag(t)) { + if (btf_type_kflag(t) && !btf_type_is_type_tag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } @@ -3332,6 +3333,8 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, u32 off, int sz, struct btf_field_info *info, u32 field_mask) { enum btf_field_type type; + const char *tag_value; + bool is_type_tag; u32 res_id; /* Permit modifiers on the pointer itself */ @@ -3341,19 +3344,20 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, if (!btf_type_is_ptr(t)) return BTF_FIELD_IGNORE; t = btf_type_by_id(btf, t->type); - - if (!btf_type_is_type_tag(t)) + is_type_tag = btf_type_is_type_tag(t) && !btf_type_kflag(t); + if (!is_type_tag) return BTF_FIELD_IGNORE; /* Reject extra tags */ if (btf_type_is_type_tag(btf_type_by_id(btf, t->type))) return -EINVAL; - if (!strcmp("kptr_untrusted", __btf_name_by_offset(btf, t->name_off))) + tag_value = __btf_name_by_offset(btf, t->name_off); + if (!strcmp("kptr_untrusted", tag_value)) type = BPF_KPTR_UNREF; - else if (!strcmp("kptr", __btf_name_by_offset(btf, t->name_off))) + else if (!strcmp("kptr", tag_value)) type = BPF_KPTR_REF; - else if (!strcmp("percpu_kptr", __btf_name_by_offset(btf, t->name_off))) + else if (!strcmp("percpu_kptr", tag_value)) type = BPF_KPTR_PERCPU; - else if (!strcmp("uptr", __btf_name_by_offset(btf, t->name_off))) + else if (!strcmp("uptr", tag_value)) type = BPF_UPTR; else return -EINVAL; @@ -4944,11 +4948,6 @@ static s32 btf_decl_tag_check_meta(struct btf_verifier_env *env, return -EINVAL; } - if (btf_type_kflag(t)) { - btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); - return -EINVAL; - } - component_idx = btf_type_decl_tag(t)->component_idx; if (component_idx < -1) { btf_verifier_log_type(env, t, "Invalid component_idx"); @@ -6507,6 +6506,8 @@ static const struct bpf_raw_tp_null_args raw_tp_null_args[] = { /* rxrpc */ { "rxrpc_recvdata", 0x1 }, { "rxrpc_resend", 0x10 }, + { "rxrpc_tq", 0x10 }, + { "rxrpc_client", 0x1 }, /* skb */ {"kfree_skb", 0x1000}, /* sunrpc */ @@ -6529,6 +6530,103 @@ static const struct bpf_raw_tp_null_args raw_tp_null_args[] = { { "mr_integ_alloc", 0x2000 }, /* bpf_testmod */ { "bpf_testmod_test_read", 0x0 }, + /* amdgpu */ + { "amdgpu_vm_bo_map", 0x1 }, + { "amdgpu_vm_bo_unmap", 0x1 }, + /* netfs */ + { "netfs_folioq", 0x1 }, + /* xfs from xfs_defer_pending_class */ + { "xfs_defer_create_intent", 0x1 }, + { "xfs_defer_cancel_list", 0x1 }, + { "xfs_defer_pending_finish", 0x1 }, + { "xfs_defer_pending_abort", 0x1 }, + { "xfs_defer_relog_intent", 0x1 }, + { "xfs_defer_isolate_paused", 0x1 }, + { "xfs_defer_item_pause", 0x1 }, + { "xfs_defer_item_unpause", 0x1 }, + /* xfs from xfs_defer_pending_item_class */ + { "xfs_defer_add_item", 0x1 }, + { "xfs_defer_cancel_item", 0x1 }, + { "xfs_defer_finish_item", 0x1 }, + /* xfs from xfs_icwalk_class */ + { "xfs_ioc_free_eofblocks", 0x10 }, + { "xfs_blockgc_free_space", 0x10 }, + /* xfs from xfs_btree_cur_class */ + { "xfs_btree_updkeys", 0x100 }, + { "xfs_btree_overlapped_query_range", 0x100 }, + /* xfs from xfs_imap_class*/ + { "xfs_map_blocks_found", 0x10000 }, + { "xfs_map_blocks_alloc", 0x10000 }, + { "xfs_iomap_alloc", 0x1000 }, + { "xfs_iomap_found", 0x1000 }, + /* xfs from xfs_fs_class */ + { "xfs_inodegc_flush", 0x1 }, + { "xfs_inodegc_push", 0x1 }, + { "xfs_inodegc_start", 0x1 }, + { "xfs_inodegc_stop", 0x1 }, + { "xfs_inodegc_queue", 0x1 }, + { "xfs_inodegc_throttle", 0x1 }, + { "xfs_fs_sync_fs", 0x1 }, + { "xfs_blockgc_start", 0x1 }, + { "xfs_blockgc_stop", 0x1 }, + { "xfs_blockgc_worker", 0x1 }, + { "xfs_blockgc_flush_all", 0x1 }, + /* xfs_scrub */ + { "xchk_nlinks_live_update", 0x10 }, + /* xfs_scrub from xchk_metapath_class */ + { "xchk_metapath_lookup", 0x100 }, + /* nfsd */ + { "nfsd_dirent", 0x1 }, + { "nfsd_file_acquire", 0x1001 }, + { "nfsd_file_insert_err", 0x1 }, + { "nfsd_file_cons_err", 0x1 }, + /* nfs4 */ + { "nfs4_setup_sequence", 0x1 }, + { "pnfs_update_layout", 0x10000 }, + { "nfs4_inode_callback_event", 0x200 }, + { "nfs4_inode_stateid_callback_event", 0x200 }, + /* nfs from pnfs_layout_event */ + { "pnfs_mds_fallback_pg_init_read", 0x10000 }, + { "pnfs_mds_fallback_pg_init_write", 0x10000 }, + { "pnfs_mds_fallback_pg_get_mirror_count", 0x10000 }, + { "pnfs_mds_fallback_read_done", 0x10000 }, + { "pnfs_mds_fallback_write_done", 0x10000 }, + { "pnfs_mds_fallback_read_pagelist", 0x10000 }, + { "pnfs_mds_fallback_write_pagelist", 0x10000 }, + /* coda */ + { "coda_dec_pic_run", 0x10 }, + { "coda_dec_pic_done", 0x10 }, + /* cfg80211 */ + { "cfg80211_scan_done", 0x11 }, + { "rdev_set_coalesce", 0x10 }, + { "cfg80211_report_wowlan_wakeup", 0x100 }, + { "cfg80211_inform_bss_frame", 0x100 }, + { "cfg80211_michael_mic_failure", 0x10000 }, + /* cfg80211 from wiphy_work_event */ + { "wiphy_work_queue", 0x10 }, + { "wiphy_work_run", 0x10 }, + { "wiphy_work_cancel", 0x10 }, + { "wiphy_work_flush", 0x10 }, + /* hugetlbfs */ + { "hugetlbfs_alloc_inode", 0x10 }, + /* spufs */ + { "spufs_context", 0x10 }, + /* kvm_hv */ + { "kvm_page_fault_enter", 0x100 }, + /* dpu */ + { "dpu_crtc_setup_mixer", 0x100 }, + /* binder */ + { "binder_transaction", 0x100 }, + /* bcachefs */ + { "btree_path_free", 0x100 }, + /* hfi1_tx */ + { "hfi1_sdma_progress", 0x1000 }, + /* iptfs */ + { "iptfs_ingress_postq_event", 0x1000 }, + /* neigh */ + { "neigh_update", 0x10 }, + /* snd_firewire_lib */ + { "amdtp_packet", 0x100 }, }; bool btf_ctx_access(int off, int size, enum bpf_access_type type, @@ -6679,6 +6777,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, info->reg_type = ctx_arg_info->reg_type; info->btf = ctx_arg_info->btf ? : btf_vmlinux; info->btf_id = ctx_arg_info->btf_id; + info->ref_obj_id = ctx_arg_info->ref_obj_id; return true; } } @@ -6745,7 +6844,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, info->btf_id = t->type; t = btf_type_by_id(btf, t->type); - if (btf_type_is_type_tag(t)) { + if (btf_type_is_type_tag(t) && !btf_type_kflag(t)) { tag_value = __btf_name_by_offset(btf, t->name_off); if (strcmp(tag_value, "user") == 0) info->reg_type |= MEM_USER; @@ -7004,7 +7103,7 @@ error: /* check type tag */ t = btf_type_by_id(btf, mtype->type); - if (btf_type_is_type_tag(t)) { + if (btf_type_is_type_tag(t) && !btf_type_kflag(t)) { tag_value = __btf_name_by_offset(btf, t->name_off); /* check __user tag */ if (strcmp(tag_value, "user") == 0) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 46e5db6..84f58f3 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -369,7 +369,7 @@ static struct bpf_prog *prog_list_prog(struct bpf_prog_list *pl) /* count number of elements in the list. * it's slow but the list cannot be long */ -static u32 prog_list_length(struct hlist_head *head) +static u32 prog_list_length(struct hlist_head *head, int *preorder_cnt) { struct bpf_prog_list *pl; u32 cnt = 0; @@ -377,6 +377,8 @@ static u32 prog_list_length(struct hlist_head *head) hlist_for_each_entry(pl, head, node) { if (!prog_list_prog(pl)) continue; + if (preorder_cnt && (pl->flags & BPF_F_PREORDER)) + (*preorder_cnt)++; cnt++; } return cnt; @@ -400,7 +402,7 @@ static bool hierarchy_allows_attach(struct cgroup *cgrp, if (flags & BPF_F_ALLOW_MULTI) return true; - cnt = prog_list_length(&p->bpf.progs[atype]); + cnt = prog_list_length(&p->bpf.progs[atype], NULL); WARN_ON_ONCE(cnt > 1); if (cnt == 1) return !!(flags & BPF_F_ALLOW_OVERRIDE); @@ -423,12 +425,12 @@ static int compute_effective_progs(struct cgroup *cgrp, struct bpf_prog_array *progs; struct bpf_prog_list *pl; struct cgroup *p = cgrp; - int cnt = 0; + int i, j, cnt = 0, preorder_cnt = 0, fstart, bstart, init_bstart; /* count number of effective programs by walking parents */ do { if (cnt == 0 || (p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) - cnt += prog_list_length(&p->bpf.progs[atype]); + cnt += prog_list_length(&p->bpf.progs[atype], &preorder_cnt); p = cgroup_parent(p); } while (p); @@ -439,20 +441,34 @@ static int compute_effective_progs(struct cgroup *cgrp, /* populate the array with effective progs */ cnt = 0; p = cgrp; + fstart = preorder_cnt; + bstart = preorder_cnt - 1; do { if (cnt > 0 && !(p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) continue; + init_bstart = bstart; hlist_for_each_entry(pl, &p->bpf.progs[atype], node) { if (!prog_list_prog(pl)) continue; - item = &progs->items[cnt]; + if (pl->flags & BPF_F_PREORDER) { + item = &progs->items[bstart]; + bstart--; + } else { + item = &progs->items[fstart]; + fstart++; + } item->prog = prog_list_prog(pl); bpf_cgroup_storages_assign(item->cgroup_storage, pl->storage); cnt++; } + + /* reverse pre-ordering progs at this cgroup level */ + for (i = bstart + 1, j = init_bstart; i < j; i++, j--) + swap(progs->items[i], progs->items[j]); + } while ((p = cgroup_parent(p))); *array = progs; @@ -663,7 +679,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, */ return -EPERM; - if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) + if (prog_list_length(progs, NULL) >= BPF_CGROUP_MAX_PROGS) return -E2BIG; pl = find_attach_entry(progs, prog, link, replace_prog, @@ -698,6 +714,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, pl->prog = prog; pl->link = link; + pl->flags = flags; bpf_cgroup_storages_assign(pl->storage, storage); cgrp->bpf.flags[atype] = saved_flags; @@ -1073,7 +1090,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, lockdep_is_held(&cgroup_mutex)); total_cnt += bpf_prog_array_length(effective); } else { - total_cnt += prog_list_length(&cgrp->bpf.progs[atype]); + total_cnt += prog_list_length(&cgrp->bpf.progs[atype], NULL); } } @@ -1105,7 +1122,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, u32 id; progs = &cgrp->bpf.progs[atype]; - cnt = min_t(int, prog_list_length(progs), total_cnt); + cnt = min_t(int, prog_list_length(progs, NULL), total_cnt); i = 0; hlist_for_each_entry(pl, progs, node) { prog = prog_list_prog(pl); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index da729cb..ba6b611 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1663,14 +1663,17 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); INSN_3(JMP, JSET, K), \ INSN_2(JMP, JA), \ INSN_2(JMP32, JA), \ + /* Atomic operations. */ \ + INSN_3(STX, ATOMIC, B), \ + INSN_3(STX, ATOMIC, H), \ + INSN_3(STX, ATOMIC, W), \ + INSN_3(STX, ATOMIC, DW), \ /* Store instructions. */ \ /* Register based. */ \ INSN_3(STX, MEM, B), \ INSN_3(STX, MEM, H), \ INSN_3(STX, MEM, W), \ INSN_3(STX, MEM, DW), \ - INSN_3(STX, ATOMIC, W), \ - INSN_3(STX, ATOMIC, DW), \ /* Immediate based. */ \ INSN_3(ST, MEM, B), \ INSN_3(ST, MEM, H), \ @@ -2152,24 +2155,33 @@ out: if (BPF_SIZE(insn->code) == BPF_W) \ atomic_##KOP((u32) SRC, (atomic_t *)(unsigned long) \ (DST + insn->off)); \ - else \ + else if (BPF_SIZE(insn->code) == BPF_DW) \ atomic64_##KOP((u64) SRC, (atomic64_t *)(unsigned long) \ (DST + insn->off)); \ + else \ + goto default_label; \ break; \ case BOP | BPF_FETCH: \ if (BPF_SIZE(insn->code) == BPF_W) \ SRC = (u32) atomic_fetch_##KOP( \ (u32) SRC, \ (atomic_t *)(unsigned long) (DST + insn->off)); \ - else \ + else if (BPF_SIZE(insn->code) == BPF_DW) \ SRC = (u64) atomic64_fetch_##KOP( \ (u64) SRC, \ (atomic64_t *)(unsigned long) (DST + insn->off)); \ + else \ + goto default_label; \ break; STX_ATOMIC_DW: STX_ATOMIC_W: + STX_ATOMIC_H: + STX_ATOMIC_B: switch (IMM) { + /* Atomic read-modify-write instructions support only W and DW + * size modifiers. + */ ATOMIC_ALU_OP(BPF_ADD, add) ATOMIC_ALU_OP(BPF_AND, and) ATOMIC_ALU_OP(BPF_OR, or) @@ -2181,20 +2193,63 @@ out: SRC = (u32) atomic_xchg( (atomic_t *)(unsigned long) (DST + insn->off), (u32) SRC); - else + else if (BPF_SIZE(insn->code) == BPF_DW) SRC = (u64) atomic64_xchg( (atomic64_t *)(unsigned long) (DST + insn->off), (u64) SRC); + else + goto default_label; break; case BPF_CMPXCHG: if (BPF_SIZE(insn->code) == BPF_W) BPF_R0 = (u32) atomic_cmpxchg( (atomic_t *)(unsigned long) (DST + insn->off), (u32) BPF_R0, (u32) SRC); - else + else if (BPF_SIZE(insn->code) == BPF_DW) BPF_R0 = (u64) atomic64_cmpxchg( (atomic64_t *)(unsigned long) (DST + insn->off), (u64) BPF_R0, (u64) SRC); + else + goto default_label; + break; + /* Atomic load and store instructions support all size + * modifiers. + */ + case BPF_LOAD_ACQ: + switch (BPF_SIZE(insn->code)) { +#define LOAD_ACQUIRE(SIZEOP, SIZE) \ + case BPF_##SIZEOP: \ + DST = (SIZE)smp_load_acquire( \ + (SIZE *)(unsigned long)(SRC + insn->off)); \ + break; + LOAD_ACQUIRE(B, u8) + LOAD_ACQUIRE(H, u16) + LOAD_ACQUIRE(W, u32) +#ifdef CONFIG_64BIT + LOAD_ACQUIRE(DW, u64) +#endif +#undef LOAD_ACQUIRE + default: + goto default_label; + } + break; + case BPF_STORE_REL: + switch (BPF_SIZE(insn->code)) { +#define STORE_RELEASE(SIZEOP, SIZE) \ + case BPF_##SIZEOP: \ + smp_store_release( \ + (SIZE *)(unsigned long)(DST + insn->off), (SIZE)SRC); \ + break; + STORE_RELEASE(B, u8) + STORE_RELEASE(H, u16) + STORE_RELEASE(W, u32) +#ifdef CONFIG_64BIT + STORE_RELEASE(DW, u64) +#endif +#undef STORE_RELEASE + default: + goto default_label; + } break; default: @@ -2290,17 +2345,18 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth) insn->code = BPF_JMP | BPF_CALL_ARGS; } #endif -#else +#endif + static unsigned int __bpf_prog_ret0_warn(const void *ctx, const struct bpf_insn *insn) { /* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON - * is not working properly, so warn about it! + * is not working properly, or interpreter is being used when + * prog->jit_requested is not 0, so warn about it! */ WARN_ON_ONCE(1); return 0; } -#endif bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp) @@ -2380,8 +2436,18 @@ static void bpf_prog_select_func(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1); + u32 idx = (round_up(stack_depth, 32) / 32) - 1; - fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1]; + /* may_goto may cause stack size > 512, leading to idx out-of-bounds. + * But for non-JITed programs, we don't need bpf_func, so no bounds + * check needed. + */ + if (!fp->jit_requested && + !WARN_ON_ONCE(idx >= ARRAY_SIZE(interpreters))) { + fp->bpf_func = interpreters[idx]; + } else { + fp->bpf_func = __bpf_prog_ret0_warn; + } #else fp->bpf_func = __bpf_prog_ret0_warn; #endif @@ -2906,6 +2972,11 @@ const struct bpf_func_proto * __weak bpf_get_trace_vprintk_proto(void) return NULL; } +const struct bpf_func_proto * __weak bpf_get_perf_event_read_value_proto(void) +{ + return NULL; +} + u64 __weak bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) @@ -3058,6 +3129,32 @@ void __weak arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, { } +bool __weak bpf_jit_supports_timed_may_goto(void) +{ + return false; +} + +u64 __weak arch_bpf_timed_may_goto(void) +{ + return 0; +} + +u64 bpf_check_timed_may_goto(struct bpf_timed_may_goto *p) +{ + u64 time = ktime_get_mono_fast_ns(); + + /* Populate the timestamp for this stack frame, and refresh count. */ + if (!p->timestamp) { + p->timestamp = time; + return BPF_MAX_TIMED_LOOPS; + } + /* Check if we've exhausted our time slice, and zero count. */ + if (time - p->timestamp >= (NSEC_PER_SEC / 4)) + return 0; + /* Refresh the count for the stack frame. */ + return BPF_MAX_TIMED_LOOPS; +} + /* for configs without MMU or 32-bit */ __weak const struct bpf_map_ops arena_map_ops; __weak u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena) diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c index cfa1c18..9876c5f 100644 --- a/kernel/bpf/cpumask.c +++ b/kernel/bpf/cpumask.c @@ -45,6 +45,10 @@ __bpf_kfunc_start_defs(); * * bpf_cpumask_create() allocates memory using the BPF memory allocator, and * will not block. It may return NULL if no memory is available. + * + * Return: + * * A pointer to a new struct bpf_cpumask instance on success. + * * NULL if the BPF memory allocator is out of memory. */ __bpf_kfunc struct bpf_cpumask *bpf_cpumask_create(void) { @@ -71,6 +75,10 @@ __bpf_kfunc struct bpf_cpumask *bpf_cpumask_create(void) * Acquires a reference to a BPF cpumask. The cpumask returned by this function * must either be embedded in a map as a kptr, or freed with * bpf_cpumask_release(). + * + * Return: + * * The struct bpf_cpumask pointer passed to the function. + * */ __bpf_kfunc struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) { @@ -106,6 +114,9 @@ CFI_NOSEAL(bpf_cpumask_release_dtor); * * Find the index of the first nonzero bit of the cpumask. A struct bpf_cpumask * pointer may be safely passed to this function. + * + * Return: + * * The index of the first nonzero bit in the struct cpumask. */ __bpf_kfunc u32 bpf_cpumask_first(const struct cpumask *cpumask) { @@ -119,6 +130,9 @@ __bpf_kfunc u32 bpf_cpumask_first(const struct cpumask *cpumask) * * Find the index of the first unset bit of the cpumask. A struct bpf_cpumask * pointer may be safely passed to this function. + * + * Return: + * * The index of the first zero bit in the struct cpumask. */ __bpf_kfunc u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) { @@ -133,6 +147,9 @@ __bpf_kfunc u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) * * Find the index of the first nonzero bit of the AND of two cpumasks. * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. + * + * Return: + * * The index of the first bit that is nonzero in both cpumask instances. */ __bpf_kfunc u32 bpf_cpumask_first_and(const struct cpumask *src1, const struct cpumask *src2) @@ -414,12 +431,47 @@ __bpf_kfunc u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, * @cpumask: The cpumask being queried. * * Count the number of set bits in the given cpumask. + * + * Return: + * * The number of bits set in the mask. */ __bpf_kfunc u32 bpf_cpumask_weight(const struct cpumask *cpumask) { return cpumask_weight(cpumask); } +/** + * bpf_cpumask_populate() - Populate the CPU mask from the contents of + * a BPF memory region. + * + * @cpumask: The cpumask being populated. + * @src: The BPF memory holding the bit pattern. + * @src__sz: Length of the BPF memory region in bytes. + * + * Return: + * * 0 if the struct cpumask * instance was populated successfully. + * * -EACCES if the memory region is too small to populate the cpumask. + * * -EINVAL if the memory region is not aligned to the size of a long + * and the architecture does not support efficient unaligned accesses. + */ +__bpf_kfunc int bpf_cpumask_populate(struct cpumask *cpumask, void *src, size_t src__sz) +{ + unsigned long source = (unsigned long)src; + + /* The memory region must be large enough to populate the entire CPU mask. */ + if (src__sz < bitmap_size(nr_cpu_ids)) + return -EACCES; + + /* If avoiding unaligned accesses, the input region must be aligned to the nearest long. */ + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && + !IS_ALIGNED(source, sizeof(long))) + return -EINVAL; + + bitmap_copy(cpumask_bits(cpumask), src, nr_cpu_ids); + + return 0; +} + __bpf_kfunc_end_defs(); BTF_KFUNCS_START(cpumask_kfunc_btf_ids) @@ -448,6 +500,7 @@ BTF_ID_FLAGS(func, bpf_cpumask_copy, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_any_distribute, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_any_and_distribute, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_weight, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_populate, KF_RCU) BTF_KFUNCS_END(cpumask_kfunc_btf_ids) static const struct btf_kfunc_id_set cpumask_kfunc_set = { diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index 309c4aa..20883c6 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -202,7 +202,7 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, insn->dst_reg, class == BPF_ALU ? 'w' : 'r', insn->dst_reg); } else if (is_addr_space_cast(insn)) { - verbose(cbs->private_data, "(%02x) r%d = addr_space_cast(r%d, %d, %d)\n", + verbose(cbs->private_data, "(%02x) r%d = addr_space_cast(r%d, %u, %u)\n", insn->code, insn->dst_reg, insn->src_reg, ((u32)insn->imm) >> 16, (u16)insn->imm); } else if (is_mov_percpu_addr(insn)) { @@ -267,6 +267,18 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, BPF_SIZE(insn->code) == BPF_DW ? "64" : "", bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); + } else if (BPF_MODE(insn->code) == BPF_ATOMIC && + insn->imm == BPF_LOAD_ACQ) { + verbose(cbs->private_data, "(%02x) r%d = load_acquire((%s *)(r%d %+d))\n", + insn->code, insn->dst_reg, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->src_reg, insn->off); + } else if (BPF_MODE(insn->code) == BPF_ATOMIC && + insn->imm == BPF_STORE_REL) { + verbose(cbs->private_data, "(%02x) store_release((%s *)(r%d %+d), r%d)\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, insn->off, insn->src_reg); } else { verbose(cbs->private_data, "BUG_%02x\n", insn->code); } @@ -369,7 +381,7 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, insn->code, class == BPF_JMP32 ? 'w' : 'r', insn->dst_reg, bpf_jmp_string[BPF_OP(insn->code) >> 4], - insn->imm, insn->off); + (u32)insn->imm, insn->off); } } else { verbose(cbs->private_data, "(%02x) %s\n", diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 4a9eeb7..8772981 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -198,12 +198,12 @@ static bool htab_is_percpu(const struct bpf_htab *htab) static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size, void __percpu *pptr) { - *(void __percpu **)(l->key + key_size) = pptr; + *(void __percpu **)(l->key + roundup(key_size, 8)) = pptr; } static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size) { - return *(void __percpu **)(l->key + key_size); + return *(void __percpu **)(l->key + roundup(key_size, 8)); } static void *fd_htab_map_get_ptr(const struct bpf_map *map, struct htab_elem *l) @@ -787,6 +787,9 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map, static void check_and_free_fields(struct bpf_htab *htab, struct htab_elem *elem) { + if (IS_ERR_OR_NULL(htab->map.record)) + return; + if (htab_is_percpu(htab)) { void __percpu *pptr = htab_elem_get_ptr(elem, htab->map.key_size); int cpu; @@ -2354,7 +2357,7 @@ static int htab_percpu_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn *insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem); *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3); *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, - offsetof(struct htab_elem, key) + map->key_size); + offsetof(struct htab_elem, key) + roundup(map->key_size, 8)); *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0); *insn++ = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 672abe1..e3a2662 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1758,8 +1758,8 @@ static const struct bpf_func_proto bpf_dynptr_from_mem_proto = { .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT | MEM_WRITE, }; -BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src, - u32, offset, u64, flags) +static int __bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr_kern *src, + u32 offset, u64 flags) { enum bpf_dynptr_type type; int err; @@ -1792,6 +1792,12 @@ BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern } } +BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src, + u32, offset, u64, flags) +{ + return __bpf_dynptr_read(dst, len, src, offset, flags); +} + static const struct bpf_func_proto bpf_dynptr_read_proto = { .func = bpf_dynptr_read, .gpl_only = false, @@ -1803,8 +1809,8 @@ static const struct bpf_func_proto bpf_dynptr_read_proto = { .arg5_type = ARG_ANYTHING, }; -BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u32, offset, void *, src, - u32, len, u64, flags) +static int __bpf_dynptr_write(const struct bpf_dynptr_kern *dst, u32 offset, void *src, + u32 len, u64 flags) { enum bpf_dynptr_type type; int err; @@ -1842,6 +1848,12 @@ BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u32, offset, v } } +BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u32, offset, void *, src, + u32, len, u64, flags) +{ + return __bpf_dynptr_write(dst, offset, src, len, flags); +} + static const struct bpf_func_proto bpf_dynptr_write_proto = { .func = bpf_dynptr_write, .gpl_only = false, @@ -2043,6 +2055,8 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_task_pt_regs_proto; case BPF_FUNC_trace_vprintk: return bpf_get_trace_vprintk_proto(); + case BPF_FUNC_perf_event_read_value: + return bpf_get_perf_event_read_value_proto(); default: return NULL; } @@ -2757,6 +2771,61 @@ __bpf_kfunc int bpf_dynptr_clone(const struct bpf_dynptr *p, return 0; } +/** + * bpf_dynptr_copy() - Copy data from one dynptr to another. + * @dst_ptr: Destination dynptr - where data should be copied to + * @dst_off: Offset into the destination dynptr + * @src_ptr: Source dynptr - where data should be copied from + * @src_off: Offset into the source dynptr + * @size: Length of the data to copy from source to destination + * + * Copies data from source dynptr to destination dynptr. + * Returns 0 on success; negative error, otherwise. + */ +__bpf_kfunc int bpf_dynptr_copy(struct bpf_dynptr *dst_ptr, u32 dst_off, + struct bpf_dynptr *src_ptr, u32 src_off, u32 size) +{ + struct bpf_dynptr_kern *dst = (struct bpf_dynptr_kern *)dst_ptr; + struct bpf_dynptr_kern *src = (struct bpf_dynptr_kern *)src_ptr; + void *src_slice, *dst_slice; + char buf[256]; + u32 off; + + src_slice = bpf_dynptr_slice(src_ptr, src_off, NULL, size); + dst_slice = bpf_dynptr_slice_rdwr(dst_ptr, dst_off, NULL, size); + + if (src_slice && dst_slice) { + memmove(dst_slice, src_slice, size); + return 0; + } + + if (src_slice) + return __bpf_dynptr_write(dst, dst_off, src_slice, size, 0); + + if (dst_slice) + return __bpf_dynptr_read(dst_slice, size, src, src_off, 0); + + if (bpf_dynptr_check_off_len(dst, dst_off, size) || + bpf_dynptr_check_off_len(src, src_off, size)) + return -E2BIG; + + off = 0; + while (off < size) { + u32 chunk_sz = min_t(u32, sizeof(buf), size - off); + int err; + + err = __bpf_dynptr_read(buf, chunk_sz, src, src_off + off, 0); + if (err) + return err; + err = __bpf_dynptr_write(dst, dst_off + off, buf, chunk_sz, 0); + if (err) + return err; + + off += chunk_sz; + } + return 0; +} + __bpf_kfunc void *bpf_cast_to_kern_ctx(void *obj) { return obj; @@ -3066,6 +3135,50 @@ __bpf_kfunc int bpf_copy_from_user_str(void *dst, u32 dst__sz, const void __user return ret + 1; } +/** + * bpf_copy_from_user_task_str() - Copy a string from an task's address space + * @dst: Destination address, in kernel space. This buffer must be + * at least @dst__sz bytes long. + * @dst__sz: Maximum number of bytes to copy, includes the trailing NUL. + * @unsafe_ptr__ign: Source address in the task's address space. + * @tsk: The task whose address space will be used + * @flags: The only supported flag is BPF_F_PAD_ZEROS + * + * Copies a NUL terminated string from a task's address space to @dst__sz + * buffer. If user string is too long this will still ensure zero termination + * in the @dst__sz buffer unless buffer size is 0. + * + * If BPF_F_PAD_ZEROS flag is set, memset the tail of @dst__sz to 0 on success + * and memset all of @dst__sz on failure. + * + * Return: The number of copied bytes on success including the NUL terminator. + * A negative error code on failure. + */ +__bpf_kfunc int bpf_copy_from_user_task_str(void *dst, u32 dst__sz, + const void __user *unsafe_ptr__ign, + struct task_struct *tsk, u64 flags) +{ + int ret; + + if (unlikely(flags & ~BPF_F_PAD_ZEROS)) + return -EINVAL; + + if (unlikely(dst__sz == 0)) + return 0; + + ret = copy_remote_vm_str(tsk, (unsigned long)unsafe_ptr__ign, dst, dst__sz, 0); + if (ret < 0) { + if (flags & BPF_F_PAD_ZEROS) + memset(dst, 0, dst__sz); + return ret; + } + + if (flags & BPF_F_PAD_ZEROS) + memset(dst + ret, 0, dst__sz - ret); + + return ret + 1; +} + /* Keep unsinged long in prototype so that kfunc is usable when emitted to * vmlinux.h in BPF programs directly, but note that while in BPF prog, the * unsigned long always points to 8-byte region on stack, the kernel may only @@ -3161,6 +3274,7 @@ BTF_ID_FLAGS(func, bpf_dynptr_is_null) BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly) BTF_ID_FLAGS(func, bpf_dynptr_size) BTF_ID_FLAGS(func, bpf_dynptr_clone) +BTF_ID_FLAGS(func, bpf_dynptr_copy) #ifdef CONFIG_NET BTF_ID_FLAGS(func, bpf_modify_return_test_tp) #endif @@ -3173,6 +3287,7 @@ BTF_ID_FLAGS(func, bpf_iter_bits_new, KF_ITER_NEW) BTF_ID_FLAGS(func, bpf_iter_bits_next, KF_ITER_NEXT | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_bits_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, bpf_copy_from_user_str, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_copy_from_user_task_str, KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_get_kmem_cache) BTF_ID_FLAGS(func, bpf_iter_kmem_cache_new, KF_ITER_NEW | KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_iter_kmem_cache_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPABLE) diff --git a/kernel/bpf/preload/bpf_preload_kern.c b/kernel/bpf/preload/bpf_preload_kern.c index 0c63bc2..2fdf3c9 100644 --- a/kernel/bpf/preload/bpf_preload_kern.c +++ b/kernel/bpf/preload/bpf_preload_kern.c @@ -90,3 +90,4 @@ static void __exit fini(void) late_initcall(load); module_exit(fini); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Embedded BPF programs for introspection in bpffs"); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e1e42e9..380b445 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1315,7 +1315,7 @@ static bool bpf_net_capable(void) #define BPF_MAP_CREATE_LAST_FIELD map_token_fd /* called via syscall */ -static int map_create(union bpf_attr *attr) +static int map_create(union bpf_attr *attr, bool kernel) { const struct bpf_map_ops *ops; struct bpf_token *token = NULL; @@ -1505,7 +1505,7 @@ static int map_create(union bpf_attr *attr) attr->btf_vmlinux_value_type_id; } - err = security_bpf_map_create(map, attr, token); + err = security_bpf_map_create(map, attr, token, kernel); if (err) goto free_map_sec; @@ -1593,11 +1593,8 @@ struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref) struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map) { - spin_lock_bh(&map_idr_lock); - map = __bpf_map_inc_not_zero(map, false); - spin_unlock_bh(&map_idr_lock); - - return map; + lockdep_assert(rcu_read_lock_held()); + return __bpf_map_inc_not_zero(map, false); } EXPORT_SYMBOL_GPL(bpf_map_inc_not_zero); @@ -2314,6 +2311,7 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) kvfree(prog->aux->jited_linfo); kvfree(prog->aux->linfo); kfree(prog->aux->kfunc_tab); + kfree(prog->aux->ctx_arg_info); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); @@ -2944,7 +2942,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (err < 0) goto free_prog; - err = security_bpf_prog_load(prog, attr, token); + err = security_bpf_prog_load(prog, attr, token, uattr.is_kernel); if (err) goto free_prog_sec; @@ -4169,7 +4167,8 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, #define BPF_F_ATTACH_MASK_BASE \ (BPF_F_ALLOW_OVERRIDE | \ BPF_F_ALLOW_MULTI | \ - BPF_F_REPLACE) + BPF_F_REPLACE | \ + BPF_F_PREORDER) #define BPF_F_ATTACH_MASK_MPROG \ (BPF_F_REPLACE | \ @@ -4733,6 +4732,8 @@ static int bpf_prog_get_info_by_fd(struct file *file, info.recursion_misses = stats.misses; info.verified_insns = prog->aux->verified_insns; + if (prog->aux->btf) + info.btf_id = btf_obj_id(prog->aux->btf); if (!bpf_capable()) { info.jited_prog_len = 0; @@ -4879,8 +4880,6 @@ static int bpf_prog_get_info_by_fd(struct file *file, } } - if (prog->aux->btf) - info.btf_id = btf_obj_id(prog->aux->btf); info.attach_btf_id = prog->aux->attach_btf_id; if (attach_btf) info.attach_btf_obj_id = btf_obj_id(attach_btf); @@ -5121,15 +5120,34 @@ static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_ return btf_new_fd(attr, uattr, uattr_size); } -#define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id +#define BPF_BTF_GET_FD_BY_ID_LAST_FIELD fd_by_id_token_fd static int bpf_btf_get_fd_by_id(const union bpf_attr *attr) { + struct bpf_token *token = NULL; + if (CHECK_ATTR(BPF_BTF_GET_FD_BY_ID)) return -EINVAL; - if (!capable(CAP_SYS_ADMIN)) + if (attr->open_flags & ~BPF_F_TOKEN_FD) + return -EINVAL; + + if (attr->open_flags & BPF_F_TOKEN_FD) { + token = bpf_token_get_from_fd(attr->fd_by_id_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + if (!bpf_token_allow_cmd(token, BPF_BTF_GET_FD_BY_ID)) { + bpf_token_put(token); + token = NULL; + } + } + + if (!bpf_token_capable(token, CAP_SYS_ADMIN)) { + bpf_token_put(token); return -EPERM; + } + + bpf_token_put(token); return btf_get_fd_by_id(attr->btf_id); } @@ -5768,13 +5786,13 @@ static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size) if (copy_from_bpfptr(&attr, uattr, size) != 0) return -EFAULT; - err = security_bpf(cmd, &attr, size); + err = security_bpf(cmd, &attr, size, uattr.is_kernel); if (err < 0) return err; switch (cmd) { case BPF_MAP_CREATE: - err = map_create(&attr); + err = map_create(&attr, uattr.is_kernel); break; case BPF_MAP_LOOKUP_ELEM: err = map_lookup_elem(&attr); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6e604ca..5ae0df7 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -579,6 +579,13 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn) insn->imm == BPF_CMPXCHG; } +static bool is_atomic_load_insn(const struct bpf_insn *insn) +{ + return BPF_CLASS(insn->code) == BPF_STX && + BPF_MODE(insn->code) == BPF_ATOMIC && + insn->imm == BPF_LOAD_ACQ; +} + static int __get_spi(s32 off) { return (-off - 1) / BPF_REG_SIZE; @@ -1545,6 +1552,17 @@ static void release_reference_state(struct bpf_verifier_state *state, int idx) return; } +static bool find_reference_state(struct bpf_verifier_state *state, int ptr_id) +{ + int i; + + for (i = 0; i < state->acquired_refs; i++) + if (state->refs[i].id == ptr_id) + return true; + + return false; +} + static int release_lock_state(struct bpf_verifier_state *state, int type, int id, void *ptr) { int i; @@ -1600,6 +1618,14 @@ static struct bpf_reference_state *find_lock_state(struct bpf_verifier_state *st return NULL; } +static void update_peak_states(struct bpf_verifier_env *env) +{ + u32 cur_states; + + cur_states = env->explored_states_size + env->free_list_size; + env->peak_states = max(env->peak_states, cur_states); +} + static void free_func_state(struct bpf_func_state *state) { if (!state) @@ -1622,6 +1648,50 @@ static void free_verifier_state(struct bpf_verifier_state *state, kfree(state); } +/* struct bpf_verifier_state->{parent,loop_entry} refer to states + * that are in either of env->{expored_states,free_list}. + * In both cases the state is contained in struct bpf_verifier_state_list. + */ +static struct bpf_verifier_state_list *state_parent_as_list(struct bpf_verifier_state *st) +{ + if (st->parent) + return container_of(st->parent, struct bpf_verifier_state_list, state); + return NULL; +} + +static struct bpf_verifier_state_list *state_loop_entry_as_list(struct bpf_verifier_state *st) +{ + if (st->loop_entry) + return container_of(st->loop_entry, struct bpf_verifier_state_list, state); + return NULL; +} + +/* A state can be freed if it is no longer referenced: + * - is in the env->free_list; + * - has no children states; + * - is not used as loop_entry. + * + * Freeing a state can make it's loop_entry free-able. + */ +static void maybe_free_verifier_state(struct bpf_verifier_env *env, + struct bpf_verifier_state_list *sl) +{ + struct bpf_verifier_state_list *loop_entry_sl; + + while (sl && sl->in_free_list && + sl->state.branches == 0 && + sl->state.used_as_loop_entry == 0) { + loop_entry_sl = state_loop_entry_as_list(&sl->state); + if (loop_entry_sl) + loop_entry_sl->state.used_as_loop_entry--; + list_del(&sl->node); + free_verifier_state(&sl->state, false); + kfree(sl); + env->free_list_size--; + sl = loop_entry_sl; + } +} + /* copy verifier state from src to dst growing dst stack space * when necessary to accommodate larger src stack */ @@ -1661,6 +1731,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, dst_state->callback_unroll_depth = src->callback_unroll_depth; dst_state->used_as_loop_entry = src->used_as_loop_entry; dst_state->may_goto_depth = src->may_goto_depth; + dst_state->loop_entry = src->loop_entry; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { @@ -1681,7 +1752,7 @@ static u32 state_htab_size(struct bpf_verifier_env *env) return env->prog->len; } -static struct bpf_verifier_state_list **explored_state(struct bpf_verifier_env *env, int idx) +static struct list_head *explored_state(struct bpf_verifier_env *env, int idx) { struct bpf_verifier_state *cur = env->cur_state; struct bpf_func_state *state = cur->frame[cur->curframe]; @@ -1789,16 +1860,13 @@ static bool same_callsites(struct bpf_verifier_state *a, struct bpf_verifier_sta * # Find outermost loop entry known for n * def get_loop_entry(n): * h = entries.get(n, None) - * while h in entries and entries[h] != h: + * while h in entries: * h = entries[h] * return h * - * # Update n's loop entry if h's outermost entry comes - * # before n's outermost entry in current DFS path. + * # Update n's loop entry if h comes before n in current DFS path. * def update_loop_entry(n, h): - * n1 = get_loop_entry(n) or n - * h1 = get_loop_entry(h) or h - * if h1 in path and depths[h1] <= depths[n1]: + * if h in path and depths[entries.get(n, n)] < depths[n]: * entries[n] = h1 * * def dfs(n, depth): @@ -1810,7 +1878,7 @@ static bool same_callsites(struct bpf_verifier_state *a, struct bpf_verifier_sta * # Case A: explore succ and update cur's loop entry * # only if succ's entry is in current DFS path. * dfs(succ, depth + 1) - * h = get_loop_entry(succ) + * h = entries.get(succ, None) * update_loop_entry(n, h) * else: * # Case B or C depending on `h1 in path` check in update_loop_entry(). @@ -1822,46 +1890,49 @@ static bool same_callsites(struct bpf_verifier_state *a, struct bpf_verifier_sta * and cur's loop entry has to be updated (case A), handle this in * update_branch_counts(); * - use st->branch > 0 as a signal that st is in the current DFS path; - * - handle cases B and C in is_state_visited(); - * - update topmost loop entry for intermediate states in get_loop_entry(). + * - handle cases B and C in is_state_visited(). */ -static struct bpf_verifier_state *get_loop_entry(struct bpf_verifier_state *st) +static struct bpf_verifier_state *get_loop_entry(struct bpf_verifier_env *env, + struct bpf_verifier_state *st) { - struct bpf_verifier_state *topmost = st->loop_entry, *old; + struct bpf_verifier_state *topmost = st->loop_entry; + u32 steps = 0; - while (topmost && topmost->loop_entry && topmost != topmost->loop_entry) + while (topmost && topmost->loop_entry) { + if (steps++ > st->dfs_depth) { + WARN_ONCE(true, "verifier bug: infinite loop in get_loop_entry\n"); + verbose(env, "verifier bug: infinite loop in get_loop_entry()\n"); + return ERR_PTR(-EFAULT); + } topmost = topmost->loop_entry; - /* Update loop entries for intermediate states to avoid this - * traversal in future get_loop_entry() calls. - */ - while (st && st->loop_entry != topmost) { - old = st->loop_entry; - st->loop_entry = topmost; - st = old; } return topmost; } -static void update_loop_entry(struct bpf_verifier_state *cur, struct bpf_verifier_state *hdr) +static void update_loop_entry(struct bpf_verifier_env *env, + struct bpf_verifier_state *cur, struct bpf_verifier_state *hdr) { - struct bpf_verifier_state *cur1, *hdr1; - - cur1 = get_loop_entry(cur) ?: cur; - hdr1 = get_loop_entry(hdr) ?: hdr; - /* The head1->branches check decides between cases B and C in - * comment for get_loop_entry(). If hdr1->branches == 0 then + /* The hdr->branches check decides between cases B and C in + * comment for get_loop_entry(). If hdr->branches == 0 then * head's topmost loop entry is not in current DFS path, * hence 'cur' and 'hdr' are not in the same loop and there is * no need to update cur->loop_entry. */ - if (hdr1->branches && hdr1->dfs_depth <= cur1->dfs_depth) { + if (hdr->branches && hdr->dfs_depth < (cur->loop_entry ?: cur)->dfs_depth) { + if (cur->loop_entry) { + cur->loop_entry->used_as_loop_entry--; + maybe_free_verifier_state(env, state_loop_entry_as_list(cur)); + } cur->loop_entry = hdr; - hdr->used_as_loop_entry = true; + hdr->used_as_loop_entry++; } } static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { + struct bpf_verifier_state_list *sl = NULL, *parent_sl; + struct bpf_verifier_state *parent; + while (st) { u32 br = --st->branches; @@ -1871,7 +1942,7 @@ static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifi * This is a part of 'case A' in get_loop_entry() comment. */ if (br == 0 && st->parent && st->loop_entry) - update_loop_entry(st->parent, st->loop_entry); + update_loop_entry(env, st->parent, st->loop_entry); /* WARN_ON(br > 1) technically makes sense here, * but see comment in push_stack(), hence: @@ -1881,7 +1952,12 @@ static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifi br); if (br) break; - st = st->parent; + parent = st->parent; + parent_sl = state_parent_as_list(st); + if (sl) + maybe_free_verifier_state(env, sl); + st = parent; + sl = parent_sl; } } @@ -3206,6 +3282,21 @@ bpf_jit_find_kfunc_model(const struct bpf_prog *prog, return res ? &res->func_model : NULL; } +static int add_kfunc_in_insns(struct bpf_verifier_env *env, + struct bpf_insn *insn, int cnt) +{ + int i, ret; + + for (i = 0; i < cnt; i++, insn++) { + if (bpf_pseudo_kfunc_call(insn)) { + ret = add_kfunc_call(env, insn->imm, insn->off); + if (ret < 0) + return ret; + } + } + return 0; +} + static int add_subprog_and_kfunc(struct bpf_verifier_env *env) { struct bpf_subprog_info *subprog = env->subprog_info; @@ -3269,6 +3360,15 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env) return 0; } +static int jmp_offset(struct bpf_insn *insn) +{ + u8 code = insn->code; + + if (code == (BPF_JMP32 | BPF_JA)) + return insn->imm; + return insn->off; +} + static int check_subprogs(struct bpf_verifier_env *env) { int i, subprog_start, subprog_end, off, cur_subprog = 0; @@ -3295,10 +3395,7 @@ static int check_subprogs(struct bpf_verifier_env *env) goto next; if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL) goto next; - if (code == (BPF_JMP32 | BPF_JA)) - off = i + insn[i].imm + 1; - else - off = i + insn[i].off + 1; + off = i + jmp_offset(&insn[i]) + 1; if (off < subprog_start || off >= subprog_end) { verbose(env, "jump out of range from insn %d to %d\n", i, off); return -EINVAL; @@ -3483,7 +3580,7 @@ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn, } if (class == BPF_STX) { - /* BPF_STX (including atomic variants) has multiple source + /* BPF_STX (including atomic variants) has one or more source * operands, one of which is a ptr. Check whether the caller is * asking about it. */ @@ -3828,6 +3925,17 @@ static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn) return btf_name_by_offset(desc_btf, func->name_off); } +static void verbose_insn(struct bpf_verifier_env *env, struct bpf_insn *insn) +{ + const struct bpf_insn_cbs cbs = { + .cb_call = disasm_kfunc_name, + .cb_print = verbose, + .private_data = env, + }; + + print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); +} + static inline void bt_init(struct backtrack_state *bt, u32 frame) { bt->frame = frame; @@ -4028,11 +4136,6 @@ static bool calls_callback(struct bpf_verifier_env *env, int insn_idx); static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, struct bpf_insn_hist_entry *hist, struct backtrack_state *bt) { - const struct bpf_insn_cbs cbs = { - .cb_call = disasm_kfunc_name, - .cb_print = verbose, - .private_data = env, - }; struct bpf_insn *insn = env->prog->insnsi + idx; u8 class = BPF_CLASS(insn->code); u8 opcode = BPF_OP(insn->code); @@ -4050,7 +4153,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_stack_mask(bt)); verbose(env, "stack=%s before ", env->tmp_str_buf); verbose(env, "%d: ", idx); - print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); + verbose_insn(env, insn); } /* If there is a history record that some registers gained range at this insn, @@ -4097,7 +4200,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, * dreg still needs precision before this insn */ } - } else if (class == BPF_LDX) { + } else if (class == BPF_LDX || is_atomic_load_insn(insn)) { if (!bt_is_reg_set(bt, dreg)) return 0; bt_clear_reg(bt, dreg); @@ -5982,18 +6085,10 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, /* check access to 'struct bpf_context' fields. Supports fixed offsets only */ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size, - enum bpf_access_type t, enum bpf_reg_type *reg_type, - struct btf **btf, u32 *btf_id, bool *is_retval, bool is_ldsx) + enum bpf_access_type t, struct bpf_insn_access_aux *info) { - struct bpf_insn_access_aux info = { - .reg_type = *reg_type, - .log = &env->log, - .is_retval = false, - .is_ldsx = is_ldsx, - }; - if (env->ops->is_valid_access && - env->ops->is_valid_access(off, size, t, env->prog, &info)) { + env->ops->is_valid_access(off, size, t, env->prog, info)) { /* A non zero info.ctx_field_size indicates that this field is a * candidate for later verifier transformation to load the whole * field and then apply a mask when accessed with a narrower @@ -6001,14 +6096,15 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, * will only allow for whole field access and rejects any other * type of narrower access. */ - *reg_type = info.reg_type; - *is_retval = info.is_retval; - - if (base_type(*reg_type) == PTR_TO_BTF_ID) { - *btf = info.btf; - *btf_id = info.btf_id; + if (base_type(info->reg_type) == PTR_TO_BTF_ID) { + if (info->ref_obj_id && + !find_reference_state(env->cur_state, info->ref_obj_id)) { + verbose(env, "invalid bpf_context access off=%d. Reference may already be released\n", + off); + return -EACCES; + } } else { - env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; + env->insn_aux_data[insn_idx].ctx_field_size = info->ctx_field_size; } /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) @@ -6118,6 +6214,26 @@ static bool is_arena_reg(struct bpf_verifier_env *env, int regno) return reg->type == PTR_TO_ARENA; } +/* Return false if @regno contains a pointer whose type isn't supported for + * atomic instruction @insn. + */ +static bool atomic_ptr_type_ok(struct bpf_verifier_env *env, int regno, + struct bpf_insn *insn) +{ + if (is_ctx_reg(env, regno)) + return false; + if (is_pkt_reg(env, regno)) + return false; + if (is_flow_key_reg(env, regno)) + return false; + if (is_sk_reg(env, regno)) + return false; + if (is_arena_reg(env, regno)) + return bpf_jit_supports_insn(insn, true); + + return true; +} + static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { #ifdef CONFIG_NET [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], @@ -7365,11 +7481,12 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (!err && value_regno >= 0 && (t == BPF_READ || rdonly_mem)) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_CTX) { - bool is_retval = false; struct bpf_retval_range range; - enum bpf_reg_type reg_type = SCALAR_VALUE; - struct btf *btf = NULL; - u32 btf_id = 0; + struct bpf_insn_access_aux info = { + .reg_type = SCALAR_VALUE, + .is_ldsx = is_ldsx, + .log = &env->log, + }; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { @@ -7381,8 +7498,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (err < 0) return err; - err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf, - &btf_id, &is_retval, is_ldsx); + err = check_ctx_access(env, insn_idx, off, size, t, &info); if (err) verbose_linfo(env, insn_idx, "; "); if (!err && t == BPF_READ && value_regno >= 0) { @@ -7390,8 +7506,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn * PTR_TO_PACKET[_META,_END]. In the latter * case, we know the offset is zero. */ - if (reg_type == SCALAR_VALUE) { - if (is_retval && get_func_retval_range(env->prog, &range)) { + if (info.reg_type == SCALAR_VALUE) { + if (info.is_retval && get_func_retval_range(env->prog, &range)) { err = __mark_reg_s32_range(env, regs, value_regno, range.minval, range.maxval); if (err) @@ -7402,7 +7518,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else { mark_reg_known_zero(env, regs, value_regno); - if (type_may_be_null(reg_type)) + if (type_may_be_null(info.reg_type)) regs[value_regno].id = ++env->id_gen; /* A load of ctx field could have different * actual load size with the one encoded in the @@ -7410,12 +7526,13 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn * a sub-register. */ regs[value_regno].subreg_def = DEF_NOT_SUBREG; - if (base_type(reg_type) == PTR_TO_BTF_ID) { - regs[value_regno].btf = btf; - regs[value_regno].btf_id = btf_id; + if (base_type(info.reg_type) == PTR_TO_BTF_ID) { + regs[value_regno].btf = info.btf; + regs[value_regno].btf_id = info.btf_id; + regs[value_regno].ref_obj_id = info.ref_obj_id; } } - regs[value_regno].type = reg_type; + regs[value_regno].type = info.reg_type; } } else if (reg->type == PTR_TO_STACK) { @@ -7518,27 +7635,72 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type type, bool allow_trust_mismatch); -static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn) +static int check_load_mem(struct bpf_verifier_env *env, struct bpf_insn *insn, + bool strict_alignment_once, bool is_ldsx, + bool allow_trust_mismatch, const char *ctx) { - int load_reg; + struct bpf_reg_state *regs = cur_regs(env); + enum bpf_reg_type src_reg_type; int err; - switch (insn->imm) { - case BPF_ADD: - case BPF_ADD | BPF_FETCH: - case BPF_AND: - case BPF_AND | BPF_FETCH: - case BPF_OR: - case BPF_OR | BPF_FETCH: - case BPF_XOR: - case BPF_XOR | BPF_FETCH: - case BPF_XCHG: - case BPF_CMPXCHG: - break; - default: - verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", insn->imm); - return -EINVAL; - } + /* check src operand */ + err = check_reg_arg(env, insn->src_reg, SRC_OP); + if (err) + return err; + + /* check dst operand */ + err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); + if (err) + return err; + + src_reg_type = regs[insn->src_reg].type; + + /* Check if (src_reg + off) is readable. The state of dst_reg will be + * updated by this call. + */ + err = check_mem_access(env, env->insn_idx, insn->src_reg, insn->off, + BPF_SIZE(insn->code), BPF_READ, insn->dst_reg, + strict_alignment_once, is_ldsx); + err = err ?: save_aux_ptr_type(env, src_reg_type, + allow_trust_mismatch); + err = err ?: reg_bounds_sanity_check(env, ®s[insn->dst_reg], ctx); + + return err; +} + +static int check_store_reg(struct bpf_verifier_env *env, struct bpf_insn *insn, + bool strict_alignment_once) +{ + struct bpf_reg_state *regs = cur_regs(env); + enum bpf_reg_type dst_reg_type; + int err; + + /* check src1 operand */ + err = check_reg_arg(env, insn->src_reg, SRC_OP); + if (err) + return err; + + /* check src2 operand */ + err = check_reg_arg(env, insn->dst_reg, SRC_OP); + if (err) + return err; + + dst_reg_type = regs[insn->dst_reg].type; + + /* Check if (dst_reg + off) is writeable. */ + err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_WRITE, insn->src_reg, + strict_alignment_once, false); + err = err ?: save_aux_ptr_type(env, dst_reg_type, false); + + return err; +} + +static int check_atomic_rmw(struct bpf_verifier_env *env, + struct bpf_insn *insn) +{ + int load_reg; + int err; if (BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) { verbose(env, "invalid atomic operand size\n"); @@ -7574,11 +7736,7 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i return -EACCES; } - if (is_ctx_reg(env, insn->dst_reg) || - is_pkt_reg(env, insn->dst_reg) || - is_flow_key_reg(env, insn->dst_reg) || - is_sk_reg(env, insn->dst_reg) || - (is_arena_reg(env, insn->dst_reg) && !bpf_jit_supports_insn(insn, true))) { + if (!atomic_ptr_type_ok(env, insn->dst_reg, insn)) { verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n", insn->dst_reg, reg_type_str(env, reg_state(env, insn->dst_reg)->type)); @@ -7605,12 +7763,12 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i /* Check whether we can read the memory, with second call for fetch * case to simulate the register fill. */ - err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, + err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, -1, true, false); if (!err && load_reg >= 0) - err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_READ, load_reg, - true, false); + err = check_mem_access(env, env->insn_idx, insn->dst_reg, + insn->off, BPF_SIZE(insn->code), + BPF_READ, load_reg, true, false); if (err) return err; @@ -7620,13 +7778,86 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i return err; } /* Check whether we can write into the same memory. */ - err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, + err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1, true, false); if (err) return err; return 0; } +static int check_atomic_load(struct bpf_verifier_env *env, + struct bpf_insn *insn) +{ + int err; + + err = check_load_mem(env, insn, true, false, false, "atomic_load"); + if (err) + return err; + + if (!atomic_ptr_type_ok(env, insn->src_reg, insn)) { + verbose(env, "BPF_ATOMIC loads from R%d %s is not allowed\n", + insn->src_reg, + reg_type_str(env, reg_state(env, insn->src_reg)->type)); + return -EACCES; + } + + return 0; +} + +static int check_atomic_store(struct bpf_verifier_env *env, + struct bpf_insn *insn) +{ + int err; + + err = check_store_reg(env, insn, true); + if (err) + return err; + + if (!atomic_ptr_type_ok(env, insn->dst_reg, insn)) { + verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n", + insn->dst_reg, + reg_type_str(env, reg_state(env, insn->dst_reg)->type)); + return -EACCES; + } + + return 0; +} + +static int check_atomic(struct bpf_verifier_env *env, struct bpf_insn *insn) +{ + switch (insn->imm) { + case BPF_ADD: + case BPF_ADD | BPF_FETCH: + case BPF_AND: + case BPF_AND | BPF_FETCH: + case BPF_OR: + case BPF_OR | BPF_FETCH: + case BPF_XOR: + case BPF_XOR | BPF_FETCH: + case BPF_XCHG: + case BPF_CMPXCHG: + return check_atomic_rmw(env, insn); + case BPF_LOAD_ACQ: + if (BPF_SIZE(insn->code) == BPF_DW && BITS_PER_LONG != 64) { + verbose(env, + "64-bit load-acquires are only supported on 64-bit arches\n"); + return -EOPNOTSUPP; + } + return check_atomic_load(env, insn); + case BPF_STORE_REL: + if (BPF_SIZE(insn->code) == BPF_DW && BITS_PER_LONG != 64) { + verbose(env, + "64-bit store-releases are only supported on 64-bit arches\n"); + return -EOPNOTSUPP; + } + return check_atomic_store(env, insn); + default: + verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", + insn->imm); + return -EINVAL; + } +} + /* When register 'regno' is used to read the stack (either directly or through * a helper function) make sure that it's within stack boundary and, depending * on the access type and privileges, that all elements of the stack are @@ -8431,10 +8662,12 @@ static struct bpf_verifier_state *find_prev_entry(struct bpf_verifier_env *env, { struct bpf_verifier_state_list *sl; struct bpf_verifier_state *st; + struct list_head *pos, *head; /* Explored states are pushed in stack order, most recent states come first */ - sl = *explored_state(env, insn_idx); - for (; sl; sl = sl->next) { + head = explored_state(env, insn_idx); + list_for_each(pos, head) { + sl = container_of(pos, struct bpf_verifier_state_list, node); /* If st->branches != 0 state is a part of current DFS verification path, * hence cur & st for a loop. */ @@ -9666,7 +9899,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) goto error; if (env->subprog_cnt > 1 && !allow_tail_call_in_subprogs(env)) { - verbose(env, "tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls\n"); + verbose(env, "mixing of tail_calls and bpf-to-bpf calls is not supported\n"); return -EINVAL; } break; @@ -10237,23 +10470,18 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (subprog_is_global(env, subprog)) { const char *sub_name = subprog_name(env, subprog); - /* Only global subprogs cannot be called with a lock held. */ if (env->cur_state->active_locks) { verbose(env, "global function calls are not allowed while holding a lock,\n" "use static function instead\n"); return -EINVAL; } - /* Only global subprogs cannot be called with preemption disabled. */ - if (env->cur_state->active_preempt_locks) { - verbose(env, "global function calls are not allowed with preemption disabled,\n" - "use static function instead\n"); - return -EINVAL; - } - - if (env->cur_state->active_irq_id) { - verbose(env, "global function calls are not allowed with IRQs disabled,\n" - "use static function instead\n"); + if (env->subprog_info[subprog].might_sleep && + (env->cur_state->active_rcu_lock || env->cur_state->active_preempt_locks || + env->cur_state->active_irq_id || !in_sleepable(env))) { + verbose(env, "global functions that may sleep are not allowed in non-sleepable context,\n" + "i.e., in a RCU/IRQ/preempt-disabled section, or in\n" + "a non-sleepable BPF program context\n"); return -EINVAL; } @@ -10752,6 +10980,8 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, static int check_reference_leak(struct bpf_verifier_env *env, bool exception_exit) { struct bpf_verifier_state *state = env->cur_state; + enum bpf_prog_type type = resolve_prog_type(env->prog); + struct bpf_reg_state *reg = reg_state(env, BPF_REG_0); bool refs_lingering = false; int i; @@ -10761,6 +10991,12 @@ static int check_reference_leak(struct bpf_verifier_env *env, bool exception_exi for (i = 0; i < state->acquired_refs; i++) { if (state->refs[i].type != REF_TYPE_PTR) continue; + /* Allow struct_ops programs to return a referenced kptr back to + * kernel. Type checks are performed later in check_return_code. + */ + if (type == BPF_PROG_TYPE_STRUCT_OPS && !exception_exit && + reg->ref_obj_id == state->refs[i].id) + continue; verbose(env, "Unreleased reference id=%d alloc_insn=%d\n", state->refs[i].id, state->refs[i].insn_idx); refs_lingering = true; @@ -11781,6 +12017,8 @@ enum special_kfunc_type { KF_bpf_iter_num_new, KF_bpf_iter_num_next, KF_bpf_iter_num_destroy, + KF_bpf_set_dentry_xattr, + KF_bpf_remove_dentry_xattr, }; BTF_SET_START(special_kfunc_set) @@ -11810,6 +12048,10 @@ BTF_ID(func, bpf_wq_set_callback_impl) #ifdef CONFIG_CGROUPS BTF_ID(func, bpf_iter_css_task_new) #endif +#ifdef CONFIG_BPF_LSM +BTF_ID(func, bpf_set_dentry_xattr) +BTF_ID(func, bpf_remove_dentry_xattr) +#endif BTF_SET_END(special_kfunc_set) BTF_ID_LIST(special_kfunc_list) @@ -11859,6 +12101,13 @@ BTF_ID(func, bpf_local_irq_restore) BTF_ID(func, bpf_iter_num_new) BTF_ID(func, bpf_iter_num_next) BTF_ID(func, bpf_iter_num_destroy) +#ifdef CONFIG_BPF_LSM +BTF_ID(func, bpf_set_dentry_xattr) +BTF_ID(func, bpf_remove_dentry_xattr) +#else +BTF_ID_UNUSED +BTF_ID_UNUSED +#endif static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) { @@ -16399,13 +16648,14 @@ static int check_return_code(struct bpf_verifier_env *env, int regno, const char const char *exit_ctx = "At program exit"; struct tnum enforce_attach_type_range = tnum_unknown; const struct bpf_prog *prog = env->prog; - struct bpf_reg_state *reg; + struct bpf_reg_state *reg = reg_state(env, regno); struct bpf_retval_range range = retval_range(0, 1); enum bpf_prog_type prog_type = resolve_prog_type(env->prog); int err; struct bpf_func_state *frame = env->cur_state->frame[0]; const bool is_subprog = frame->subprogno; bool return_32bit = false; + const struct btf_type *reg_type, *ret_type = NULL; /* LSM and struct_ops func-ptr's return type could be "void" */ if (!is_subprog || frame->in_exception_callback_fn) { @@ -16414,10 +16664,26 @@ static int check_return_code(struct bpf_verifier_env *env, int regno, const char if (prog->expected_attach_type == BPF_LSM_CGROUP) /* See below, can be 0 or 0-1 depending on hook. */ break; - fallthrough; + if (!prog->aux->attach_func_proto->type) + return 0; + break; case BPF_PROG_TYPE_STRUCT_OPS: if (!prog->aux->attach_func_proto->type) return 0; + + if (frame->in_exception_callback_fn) + break; + + /* Allow a struct_ops program to return a referenced kptr if it + * matches the operator's return type and is in its unmodified + * form. A scalar zero (i.e., a null pointer) is also allowed. + */ + reg_type = reg->btf ? btf_type_by_id(reg->btf, reg->btf_id) : NULL; + ret_type = btf_type_resolve_ptr(prog->aux->attach_btf, + prog->aux->attach_func_proto->type, + NULL); + if (ret_type && ret_type == reg_type && reg->ref_obj_id) + return __check_ptr_off_reg(env, reg, regno, false); break; default: break; @@ -16439,8 +16705,6 @@ static int check_return_code(struct bpf_verifier_env *env, int regno, const char return -EACCES; } - reg = cur_regs(env) + regno; - if (frame->in_async_callback_fn) { /* enforce return zero from async callbacks like timer */ exit_ctx = "At async callback return"; @@ -16539,6 +16803,11 @@ static int check_return_code(struct bpf_verifier_env *env, int regno, const char case BPF_PROG_TYPE_NETFILTER: range = retval_range(NF_DROP, NF_ACCEPT); break; + case BPF_PROG_TYPE_STRUCT_OPS: + if (!ret_type) + return 0; + range = retval_range(0, 0); + break; case BPF_PROG_TYPE_EXT: /* freplace program can return anything as its return value * depends on the to-be-replaced kernel func or bpf program. @@ -16582,6 +16851,14 @@ static void mark_subprog_changes_pkt_data(struct bpf_verifier_env *env, int off) subprog->changes_pkt_data = true; } +static void mark_subprog_might_sleep(struct bpf_verifier_env *env, int off) +{ + struct bpf_subprog_info *subprog; + + subprog = find_containing_subprog(env, off); + subprog->might_sleep = true; +} + /* 't' is an index of a call-site. * 'w' is a callee entry point. * Eventually this function would be called when env->cfg.insn_state[w] == EXPLORED. @@ -16595,6 +16872,7 @@ static void merge_callee_effects(struct bpf_verifier_env *env, int t, int w) caller = find_containing_subprog(env, t); callee = find_containing_subprog(env, w); caller->changes_pkt_data |= callee->changes_pkt_data; + caller->might_sleep |= callee->might_sleep; } /* non-recursive DFS pseudo code @@ -16753,27 +17031,6 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns, /* Bitmask with 1s for all caller saved registers */ #define ALL_CALLER_SAVED_REGS ((1u << CALLER_SAVED_REGS) - 1) -/* Return a bitmask specifying which caller saved registers are - * clobbered by a call to a helper *as if* this helper follows - * bpf_fastcall contract: - * - includes R0 if function is non-void; - * - includes R1-R5 if corresponding parameter has is described - * in the function prototype. - */ -static u32 helper_fastcall_clobber_mask(const struct bpf_func_proto *fn) -{ - u32 mask; - int i; - - mask = 0; - if (fn->ret_type != RET_VOID) - mask |= BIT(BPF_REG_0); - for (i = 0; i < ARRAY_SIZE(fn->arg_type); ++i) - if (fn->arg_type[i] != ARG_DONTCARE) - mask |= BIT(BPF_REG_1 + i); - return mask; -} - /* True if do_misc_fixups() replaces calls to helper number 'imm', * replacement patch is presumed to follow bpf_fastcall contract * (see mark_fastcall_pattern_for_call() below). @@ -16790,34 +17047,64 @@ static bool verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm) } } -/* Same as helper_fastcall_clobber_mask() but for kfuncs, see comment above */ -static u32 kfunc_fastcall_clobber_mask(struct bpf_kfunc_call_arg_meta *meta) +struct call_summary { + u8 num_params; + bool is_void; + bool fastcall; +}; + +/* If @call is a kfunc or helper call, fills @cs and returns true, + * otherwise returns false. + */ +static bool get_call_summary(struct bpf_verifier_env *env, struct bpf_insn *call, + struct call_summary *cs) { - u32 vlen, i, mask; + struct bpf_kfunc_call_arg_meta meta; + const struct bpf_func_proto *fn; + int i; - vlen = btf_type_vlen(meta->func_proto); - mask = 0; - if (!btf_type_is_void(btf_type_by_id(meta->btf, meta->func_proto->type))) - mask |= BIT(BPF_REG_0); - for (i = 0; i < vlen; ++i) - mask |= BIT(BPF_REG_1 + i); - return mask; -} + if (bpf_helper_call(call)) { -/* Same as verifier_inlines_helper_call() but for kfuncs, see comment above */ -static bool is_fastcall_kfunc_call(struct bpf_kfunc_call_arg_meta *meta) -{ - return meta->kfunc_flags & KF_FASTCALL; -} + if (get_helper_proto(env, call->imm, &fn) < 0) + /* error would be reported later */ + return false; + cs->fastcall = fn->allow_fastcall && + (verifier_inlines_helper_call(env, call->imm) || + bpf_jit_inlines_helper_call(call->imm)); + cs->is_void = fn->ret_type == RET_VOID; + cs->num_params = 0; + for (i = 0; i < ARRAY_SIZE(fn->arg_type); ++i) { + if (fn->arg_type[i] == ARG_DONTCARE) + break; + cs->num_params++; + } + return true; + } -/* LLVM define a bpf_fastcall function attribute. - * This attribute means that function scratches only some of - * the caller saved registers defined by ABI. - * For BPF the set of such registers could be defined as follows: - * - R0 is scratched only if function is non-void; - * - R1-R5 are scratched only if corresponding parameter type is defined - * in the function prototype. - * + if (bpf_pseudo_kfunc_call(call)) { + int err; + + err = fetch_kfunc_meta(env, call, &meta, NULL); + if (err < 0) + /* error would be reported later */ + return false; + cs->num_params = btf_type_vlen(meta.func_proto); + cs->fastcall = meta.kfunc_flags & KF_FASTCALL; + cs->is_void = btf_type_is_void(btf_type_by_id(meta.btf, meta.func_proto->type)); + return true; + } + + return false; +} + +/* LLVM define a bpf_fastcall function attribute. + * This attribute means that function scratches only some of + * the caller saved registers defined by ABI. + * For BPF the set of such registers could be defined as follows: + * - R0 is scratched only if function is non-void; + * - R1-R5 are scratched only if corresponding parameter type is defined + * in the function prototype. + * * The contract between kernel and clang allows to simultaneously use * such functions and maintain backwards compatibility with old * kernels that don't understand bpf_fastcall calls: @@ -16890,39 +17177,23 @@ static void mark_fastcall_pattern_for_call(struct bpf_verifier_env *env, { struct bpf_insn *insns = env->prog->insnsi, *stx, *ldx; struct bpf_insn *call = &env->prog->insnsi[insn_idx]; - const struct bpf_func_proto *fn; - u32 clobbered_regs_mask = ALL_CALLER_SAVED_REGS; + u32 clobbered_regs_mask; + struct call_summary cs; u32 expected_regs_mask; - bool can_be_inlined = false; s16 off; int i; - if (bpf_helper_call(call)) { - if (get_helper_proto(env, call->imm, &fn) < 0) - /* error would be reported later */ - return; - clobbered_regs_mask = helper_fastcall_clobber_mask(fn); - can_be_inlined = fn->allow_fastcall && - (verifier_inlines_helper_call(env, call->imm) || - bpf_jit_inlines_helper_call(call->imm)); - } - - if (bpf_pseudo_kfunc_call(call)) { - struct bpf_kfunc_call_arg_meta meta; - int err; - - err = fetch_kfunc_meta(env, call, &meta, NULL); - if (err < 0) - /* error would be reported later */ - return; - - clobbered_regs_mask = kfunc_fastcall_clobber_mask(&meta); - can_be_inlined = is_fastcall_kfunc_call(&meta); - } - - if (clobbered_regs_mask == ALL_CALLER_SAVED_REGS) + if (!get_call_summary(env, call, &cs)) return; + /* A bitmask specifying which caller saved registers are clobbered + * by a call to a helper/kfunc *as if* this helper/kfunc follows + * bpf_fastcall contract: + * - includes R0 if function is non-void; + * - includes R1-R5 if corresponding parameter has is described + * in the function prototype. + */ + clobbered_regs_mask = GENMASK(cs.num_params, cs.is_void ? 1 : 0); /* e.g. if helper call clobbers r{0,1}, expect r{2,3,4,5} in the pattern */ expected_regs_mask = ~clobbered_regs_mask & ALL_CALLER_SAVED_REGS; @@ -16980,7 +17251,7 @@ static void mark_fastcall_pattern_for_call(struct bpf_verifier_env *env, * don't set 'fastcall_spills_num' for call B so that remove_fastcall_spills_fills() * does not remove spill/fill pair {4,6}. */ - if (can_be_inlined) + if (cs.fastcall) env->insn_aux_data[insn_idx].fastcall_spills_num = i - 1; else subprog->keep_fastcall_stack = 1; @@ -17062,9 +17333,20 @@ static int visit_insn(int t, struct bpf_verifier_env *env) mark_prune_point(env, t); mark_jmp_point(env, t); } - if (bpf_helper_call(insn) && bpf_helper_changes_pkt_data(insn->imm)) - mark_subprog_changes_pkt_data(env, t); - if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { + if (bpf_helper_call(insn)) { + const struct bpf_func_proto *fp; + + ret = get_helper_proto(env, insn->imm, &fp); + /* If called in a non-sleepable context program will be + * rejected anyway, so we should end up with precise + * sleepable marks on subprogs, except for dead code + * elimination. + */ + if (ret == 0 && fp->might_sleep) + mark_subprog_might_sleep(env, t); + if (bpf_helper_changes_pkt_data(insn->imm)) + mark_subprog_changes_pkt_data(env, t); + } else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { struct bpf_kfunc_call_arg_meta meta; ret = fetch_kfunc_meta(env, insn, &meta, NULL); @@ -17083,6 +17365,13 @@ static int visit_insn(int t, struct bpf_verifier_env *env) */ mark_force_checkpoint(env, t); } + /* Same as helpers, if called in a non-sleepable context + * program will be rejected anyway, so we should end up + * with precise sleepable marks on subprogs, except for + * dead code elimination. + */ + if (ret == 0 && is_kfunc_sleepable(&meta)) + mark_subprog_might_sleep(env, t); } return visit_func_call_insn(t, insns, env, insn->src_reg == BPF_PSEUDO_CALL); @@ -17125,9 +17414,8 @@ static int visit_insn(int t, struct bpf_verifier_env *env) static int check_cfg(struct bpf_verifier_env *env) { int insn_cnt = env->prog->len; - int *insn_stack, *insn_state; + int *insn_stack, *insn_state, *insn_postorder; int ex_insn_beg, i, ret = 0; - bool ex_done = false; insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_state) @@ -17139,6 +17427,17 @@ static int check_cfg(struct bpf_verifier_env *env) return -ENOMEM; } + insn_postorder = env->cfg.insn_postorder = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); + if (!insn_postorder) { + kvfree(insn_state); + kvfree(insn_stack); + return -ENOMEM; + } + + ex_insn_beg = env->exception_callback_subprog + ? env->subprog_info[env->exception_callback_subprog].start + : 0; + insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */ insn_stack[0] = 0; /* 0 is the first instruction */ env->cfg.cur_stack = 1; @@ -17152,6 +17451,7 @@ walk_cfg: case DONE_EXPLORING: insn_state[t] = EXPLORED; env->cfg.cur_stack--; + insn_postorder[env->cfg.cur_postorder++] = t; break; case KEEP_EXPLORING: break; @@ -17170,13 +17470,10 @@ walk_cfg: goto err_free; } - if (env->exception_callback_subprog && !ex_done) { - ex_insn_beg = env->subprog_info[env->exception_callback_subprog].start; - + if (ex_insn_beg && insn_state[ex_insn_beg] != EXPLORED) { insn_state[ex_insn_beg] = DISCOVERED; insn_stack[0] = ex_insn_beg; env->cfg.cur_stack = 1; - ex_done = true; goto walk_cfg; } @@ -17199,6 +17496,7 @@ walk_cfg: } ret = 0; /* cfg looks good */ env->prog->aux->changes_pkt_data = env->subprog_info[0].changes_pkt_data; + env->prog->aux->might_sleep = env->subprog_info[0].might_sleep; err_free: kvfree(insn_state); @@ -17815,18 +18113,22 @@ static void clean_verifier_state(struct bpf_verifier_env *env, static void clean_live_states(struct bpf_verifier_env *env, int insn, struct bpf_verifier_state *cur) { + struct bpf_verifier_state *loop_entry; struct bpf_verifier_state_list *sl; + struct list_head *pos, *head; - sl = *explored_state(env, insn); - while (sl) { + head = explored_state(env, insn); + list_for_each(pos, head) { + sl = container_of(pos, struct bpf_verifier_state_list, node); if (sl->state.branches) - goto next; + continue; + loop_entry = get_loop_entry(env, &sl->state); + if (!IS_ERR_OR_NULL(loop_entry) && loop_entry->branches) + continue; if (sl->state.insn_idx != insn || !same_callsites(&sl->state, cur)) - goto next; + continue; clean_verifier_state(env, &sl->state); -next: - sl = sl->next; } } @@ -18210,15 +18512,17 @@ static bool refsafe(struct bpf_verifier_state *old, struct bpf_verifier_state *c * the current state will reach 'bpf_exit' instruction safely */ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_state *old, - struct bpf_func_state *cur, enum exact_level exact) + struct bpf_func_state *cur, u32 insn_idx, enum exact_level exact) { - int i; + u16 live_regs = env->insn_aux_data[insn_idx].live_regs_before; + u16 i; if (old->callback_depth > cur->callback_depth) return false; for (i = 0; i < MAX_BPF_REG; i++) - if (!regsafe(env, &old->regs[i], &cur->regs[i], + if (((1 << i) & live_regs) && + !regsafe(env, &old->regs[i], &cur->regs[i], &env->idmap_scratch, exact)) return false; @@ -18239,6 +18543,7 @@ static bool states_equal(struct bpf_verifier_env *env, struct bpf_verifier_state *cur, enum exact_level exact) { + u32 insn_idx; int i; if (old->curframe != cur->curframe) @@ -18262,9 +18567,12 @@ static bool states_equal(struct bpf_verifier_env *env, * and all frame states need to be equivalent */ for (i = 0; i <= old->curframe; i++) { + insn_idx = i == old->curframe + ? env->insn_idx + : old->frame[i + 1]->callsite; if (old->frame[i]->callsite != cur->frame[i]->callsite) return false; - if (!func_states_equal(env, old->frame[i], cur->frame[i], exact)) + if (!func_states_equal(env, old->frame[i], cur->frame[i], insn_idx, exact)) return false; } return true; @@ -18517,10 +18825,11 @@ static bool iter_active_depths_differ(struct bpf_verifier_state *old, struct bpf static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state_list *new_sl; - struct bpf_verifier_state_list *sl, **pprev; + struct bpf_verifier_state_list *sl; struct bpf_verifier_state *cur = env->cur_state, *new, *loop_entry; int i, j, n, err, states_cnt = 0; bool force_new_state, add_new_state, force_exact; + struct list_head *pos, *tmp, *head; force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx) || /* Avoid accumulating infinitely long jmp history */ @@ -18539,15 +18848,14 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) env->insn_processed - env->prev_insn_processed >= 8) add_new_state = true; - pprev = explored_state(env, insn_idx); - sl = *pprev; - clean_live_states(env, insn_idx, cur); - while (sl) { + head = explored_state(env, insn_idx); + list_for_each_safe(pos, tmp, head) { + sl = container_of(pos, struct bpf_verifier_state_list, node); states_cnt++; if (sl->state.insn_idx != insn_idx) - goto next; + continue; if (sl->state.branches) { struct bpf_func_state *frame = sl->state.frame[sl->state.curframe]; @@ -18621,7 +18929,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) spi = __get_spi(iter_reg->off + iter_reg->var_off.value); iter_state = &func(env, iter_reg)->stack[spi].spilled_ptr; if (iter_state->iter.state == BPF_ITER_STATE_ACTIVE) { - update_loop_entry(cur, &sl->state); + update_loop_entry(env, cur, &sl->state); goto hit; } } @@ -18630,7 +18938,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) if (is_may_goto_insn_at(env, insn_idx)) { if (sl->state.may_goto_depth != cur->may_goto_depth && states_equal(env, &sl->state, cur, RANGE_WITHIN)) { - update_loop_entry(cur, &sl->state); + update_loop_entry(env, cur, &sl->state); goto hit; } } @@ -18697,11 +19005,13 @@ skip_inf_loop_check: * * Additional details are in the comment before get_loop_entry(). */ - loop_entry = get_loop_entry(&sl->state); + loop_entry = get_loop_entry(env, &sl->state); + if (IS_ERR(loop_entry)) + return PTR_ERR(loop_entry); force_exact = loop_entry && loop_entry->branches > 0; if (states_equal(env, &sl->state, cur, force_exact ? RANGE_WITHIN : NOT_EXACT)) { if (force_exact) - update_loop_entry(cur, loop_entry); + update_loop_entry(env, cur, loop_entry); hit: sl->hit_cnt++; /* reached equivalent register/stack state, @@ -18750,31 +19060,13 @@ miss: /* the state is unlikely to be useful. Remove it to * speed up verification */ - *pprev = sl->next; - if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE && - !sl->state.used_as_loop_entry) { - u32 br = sl->state.branches; - - WARN_ONCE(br, - "BUG live_done but branches_to_explore %d\n", - br); - free_verifier_state(&sl->state, false); - kfree(sl); - env->peak_states--; - } else { - /* cannot free this state, since parentage chain may - * walk it later. Add it for free_list instead to - * be freed at the end of verification - */ - sl->next = env->free_list; - env->free_list = sl; - } - sl = *pprev; - continue; + sl->in_free_list = true; + list_del(&sl->node); + list_add(&sl->node, &env->free_list); + env->free_list_size++; + env->explored_states_size--; + maybe_free_verifier_state(env, sl); } -next: - pprev = &sl->next; - sl = *pprev; } if (env->max_states_per_insn < states_cnt) @@ -18799,7 +19091,8 @@ next: if (!new_sl) return -ENOMEM; env->total_states++; - env->peak_states++; + env->explored_states_size++; + update_peak_states(env); env->prev_jmps_processed = env->jmps_processed; env->prev_insn_processed = env->insn_processed; @@ -18823,8 +19116,8 @@ next: cur->first_insn_idx = insn_idx; cur->insn_hist_start = cur->insn_hist_end; cur->dfs_depth = new->dfs_depth + 1; - new_sl->next = *explored_state(env, insn_idx); - *explored_state(env, insn_idx) = new_sl; + list_add(&new_sl->node, head); + /* connect new state to parentage chain. Current frame needs all * registers connected. Only r6 - r9 of the callers are alive (pushed * to the stack implicitly by JITs) so in callers' frames connect just @@ -19011,19 +19304,13 @@ static int do_check(struct bpf_verifier_env *env) } if (env->log.level & BPF_LOG_LEVEL) { - const struct bpf_insn_cbs cbs = { - .cb_call = disasm_kfunc_name, - .cb_print = verbose, - .private_data = env, - }; - if (verifier_state_scratched(env)) print_insn_state(env, state, state->curframe); verbose_linfo(env, env->insn_idx, "; "); env->prev_log_pos = env->log.end_pos; verbose(env, "%d: ", env->insn_idx); - print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); + verbose_insn(env, insn); env->prev_insn_print_pos = env->log.end_pos - env->prev_log_pos; env->prev_log_pos = env->log.end_pos; } @@ -19045,37 +19332,18 @@ static int do_check(struct bpf_verifier_env *env) return err; } else if (class == BPF_LDX) { - enum bpf_reg_type src_reg_type; - - /* check for reserved fields is already done */ - - /* check src operand */ - err = check_reg_arg(env, insn->src_reg, SRC_OP); - if (err) - return err; - - err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); - if (err) - return err; - - src_reg_type = regs[insn->src_reg].type; + bool is_ldsx = BPF_MODE(insn->code) == BPF_MEMSX; - /* check that memory (src_reg + off) is readable, - * the state of dst_reg will be updated by this func + /* Check for reserved fields is already done in + * resolve_pseudo_ldimm64(). */ - err = check_mem_access(env, env->insn_idx, insn->src_reg, - insn->off, BPF_SIZE(insn->code), - BPF_READ, insn->dst_reg, false, - BPF_MODE(insn->code) == BPF_MEMSX); - err = err ?: save_aux_ptr_type(env, src_reg_type, true); - err = err ?: reg_bounds_sanity_check(env, ®s[insn->dst_reg], "ldx"); + err = check_load_mem(env, insn, false, is_ldsx, true, + "ldx"); if (err) return err; } else if (class == BPF_STX) { - enum bpf_reg_type dst_reg_type; - if (BPF_MODE(insn->code) == BPF_ATOMIC) { - err = check_atomic(env, env->insn_idx, insn); + err = check_atomic(env, insn); if (err) return err; env->insn_idx++; @@ -19087,25 +19355,7 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } - /* check src1 operand */ - err = check_reg_arg(env, insn->src_reg, SRC_OP); - if (err) - return err; - /* check src2 operand */ - err = check_reg_arg(env, insn->dst_reg, SRC_OP); - if (err) - return err; - - dst_reg_type = regs[insn->dst_reg].type; - - /* check that memory (dst_reg + off) is writeable */ - err = check_mem_access(env, env->insn_idx, insn->dst_reg, - insn->off, BPF_SIZE(insn->code), - BPF_WRITE, insn->src_reg, false, false); - if (err) - return err; - - err = save_aux_ptr_type(env, dst_reg_type, false); + err = check_store_reg(env, insn, false); if (err) return err; } else if (class == BPF_ST) { @@ -19245,6 +19495,10 @@ process_bpf_exit: return err; break; } else { + if (WARN_ON_ONCE(env->cur_state->loop_entry)) { + verbose(env, "verifier bug: env->cur_state->loop_entry != NULL\n"); + return -EFAULT; + } do_print_state = true; continue; } @@ -20334,7 +20588,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) { struct bpf_subprog_info *subprogs = env->subprog_info; const struct bpf_verifier_ops *ops = env->ops; - int i, cnt, size, ctx_field_size, delta = 0, epilogue_cnt = 0; + int i, cnt, size, ctx_field_size, ret, delta = 0, epilogue_cnt = 0; const int insn_cnt = env->prog->len; struct bpf_insn *epilogue_buf = env->epilogue_buf; struct bpf_insn *insn_buf = env->insn_buf; @@ -20363,6 +20617,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) return -ENOMEM; env->prog = new_prog; delta += cnt - 1; + + ret = add_kfunc_in_insns(env, epilogue_buf, epilogue_cnt - 1); + if (ret < 0) + return ret; } } @@ -20383,6 +20641,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) env->prog = new_prog; delta += cnt - 1; + + ret = add_kfunc_in_insns(env, insn_buf, cnt - 1); + if (ret < 0) + return ret; } } @@ -20415,7 +20677,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) insn->code == (BPF_ST | BPF_MEM | BPF_W) || insn->code == (BPF_ST | BPF_MEM | BPF_DW)) { type = BPF_WRITE; - } else if ((insn->code == (BPF_STX | BPF_ATOMIC | BPF_W) || + } else if ((insn->code == (BPF_STX | BPF_ATOMIC | BPF_B) || + insn->code == (BPF_STX | BPF_ATOMIC | BPF_H) || + insn->code == (BPF_STX | BPF_ATOMIC | BPF_W) || insn->code == (BPF_STX | BPF_ATOMIC | BPF_DW)) && env->insn_aux_data[i + delta].ptr_type == PTR_TO_ARENA) { insn->code = BPF_STX | BPF_PROBE_ATOMIC | BPF_SIZE(insn->code); @@ -20723,6 +20987,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable; func[i]->aux->exception_cb = env->subprog_info[i].is_exception_cb; func[i]->aux->changes_pkt_data = env->subprog_info[i].changes_pkt_data; + func[i]->aux->might_sleep = env->subprog_info[i].might_sleep; if (!i) func[i]->aux->exception_boundary = env->seen_exception; func[i] = bpf_int_jit_compile(func[i]); @@ -20939,6 +21204,14 @@ static void specialize_kfunc(struct bpf_verifier_env *env, */ env->seen_direct_write = seen_direct_write; } + + if (func_id == special_kfunc_list[KF_bpf_set_dentry_xattr] && + bpf_lsm_has_d_inode_locked(prog)) + *addr = (unsigned long)bpf_set_dentry_xattr_locked; + + if (func_id == special_kfunc_list[KF_bpf_remove_dentry_xattr] && + bpf_lsm_has_d_inode_locked(prog)) + *addr = (unsigned long)bpf_remove_dentry_xattr_locked; } static void __fixup_collection_insert_kfunc(struct bpf_insn_aux_data *insn_aux, @@ -21373,7 +21646,50 @@ static int do_misc_fixups(struct bpf_verifier_env *env) goto next_insn; } - if (is_may_goto_insn(insn)) { + if (is_may_goto_insn(insn) && bpf_jit_supports_timed_may_goto()) { + int stack_off_cnt = -stack_depth - 16; + + /* + * Two 8 byte slots, depth-16 stores the count, and + * depth-8 stores the start timestamp of the loop. + * + * The starting value of count is BPF_MAX_TIMED_LOOPS + * (0xffff). Every iteration loads it and subs it by 1, + * until the value becomes 0 in AX (thus, 1 in stack), + * after which we call arch_bpf_timed_may_goto, which + * either sets AX to 0xffff to keep looping, or to 0 + * upon timeout. AX is then stored into the stack. In + * the next iteration, we either see 0 and break out, or + * continue iterating until the next time value is 0 + * after subtraction, rinse and repeat. + */ + stack_depth_extra = 16; + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_AX, BPF_REG_10, stack_off_cnt); + if (insn->off >= 0) + insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 5); + else + insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off - 1); + insn_buf[2] = BPF_ALU64_IMM(BPF_SUB, BPF_REG_AX, 1); + insn_buf[3] = BPF_JMP_IMM(BPF_JNE, BPF_REG_AX, 0, 2); + /* + * AX is used as an argument to pass in stack_off_cnt + * (to add to r10/fp), and also as the return value of + * the call to arch_bpf_timed_may_goto. + */ + insn_buf[4] = BPF_MOV64_IMM(BPF_REG_AX, stack_off_cnt); + insn_buf[5] = BPF_EMIT_CALL(arch_bpf_timed_may_goto); + insn_buf[6] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_AX, stack_off_cnt); + cnt = 7; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + goto next_insn; + } else if (is_may_goto_insn(insn)) { int stack_off = -stack_depth - 8; stack_depth_extra = 8; @@ -21897,6 +22213,13 @@ next_insn: if (subprogs[cur_subprog + 1].start == i + delta + 1) { subprogs[cur_subprog].stack_depth += stack_depth_extra; subprogs[cur_subprog].stack_extra = stack_depth_extra; + + stack_depth = subprogs[cur_subprog].stack_depth; + if (stack_depth > MAX_BPF_STACK && !prog->jit_requested) { + verbose(env, "stack size %d(extra %d) is too large\n", + stack_depth, stack_depth_extra); + return -EINVAL; + } cur_subprog++; stack_depth = subprogs[cur_subprog].stack_depth; stack_depth_extra = 0; @@ -21907,23 +22230,33 @@ next_insn: env->prog->aux->stack_depth = subprogs[0].stack_depth; for (i = 0; i < env->subprog_cnt; i++) { + int delta = bpf_jit_supports_timed_may_goto() ? 2 : 1; int subprog_start = subprogs[i].start; int stack_slots = subprogs[i].stack_extra / 8; + int slots = delta, cnt = 0; if (!stack_slots) continue; - if (stack_slots > 1) { + /* We need two slots in case timed may_goto is supported. */ + if (stack_slots > slots) { verbose(env, "verifier bug: stack_slots supports may_goto only\n"); return -EFAULT; } - /* Add ST insn to subprog prologue to init extra stack */ - insn_buf[0] = BPF_ST_MEM(BPF_DW, BPF_REG_FP, - -subprogs[i].stack_depth, BPF_MAX_LOOPS); + stack_depth = subprogs[i].stack_depth; + if (bpf_jit_supports_timed_may_goto()) { + insn_buf[cnt++] = BPF_ST_MEM(BPF_DW, BPF_REG_FP, -stack_depth, + BPF_MAX_TIMED_LOOPS); + insn_buf[cnt++] = BPF_ST_MEM(BPF_DW, BPF_REG_FP, -stack_depth + 8, 0); + } else { + /* Add ST insn to subprog prologue to init extra stack */ + insn_buf[cnt++] = BPF_ST_MEM(BPF_DW, BPF_REG_FP, -stack_depth, + BPF_MAX_LOOPS); + } /* Copy first actual insn to preserve it */ - insn_buf[1] = env->prog->insnsi[subprog_start]; + insn_buf[cnt++] = env->prog->insnsi[subprog_start]; - new_prog = bpf_patch_insn_data(env, subprog_start, insn_buf, 2); + new_prog = bpf_patch_insn_data(env, subprog_start, insn_buf, cnt); if (!new_prog) return -ENOMEM; env->prog = prog = new_prog; @@ -21933,7 +22266,7 @@ next_insn: * to insn after BPF_ST that inits may_goto count. * Adjustment will succeed because bpf_patch_insn_data() didn't fail. */ - WARN_ON(adjust_jmp_off(env->prog, subprog_start, 1)); + WARN_ON(adjust_jmp_off(env->prog, subprog_start, delta)); } /* Since poke tab is now finalized, publish aux to tracker. */ @@ -22131,31 +22464,29 @@ static int remove_fastcall_spills_fills(struct bpf_verifier_env *env) static void free_states(struct bpf_verifier_env *env) { - struct bpf_verifier_state_list *sl, *sln; + struct bpf_verifier_state_list *sl; + struct list_head *head, *pos, *tmp; int i; - sl = env->free_list; - while (sl) { - sln = sl->next; + list_for_each_safe(pos, tmp, &env->free_list) { + sl = container_of(pos, struct bpf_verifier_state_list, node); free_verifier_state(&sl->state, false); kfree(sl); - sl = sln; } - env->free_list = NULL; + INIT_LIST_HEAD(&env->free_list); if (!env->explored_states) return; for (i = 0; i < state_htab_size(env); i++) { - sl = env->explored_states[i]; + head = &env->explored_states[i]; - while (sl) { - sln = sl->next; + list_for_each_safe(pos, tmp, head) { + sl = container_of(pos, struct bpf_verifier_state_list, node); free_verifier_state(&sl->state, false); kfree(sl); - sl = sln; } - env->explored_states[i] = NULL; + INIT_LIST_HEAD(&env->explored_states[i]); } } @@ -22163,6 +22494,7 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); struct bpf_subprog_info *sub = subprog_info(env, subprog); + struct bpf_prog_aux *aux = env->prog->aux; struct bpf_verifier_state *state; struct bpf_reg_state *regs; int ret, i; @@ -22270,6 +22602,13 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) mark_reg_known_zero(env, regs, BPF_REG_1); } + /* Acquire references for struct_ops program arguments tagged with "__ref" */ + if (!subprog && env->prog->type == BPF_PROG_TYPE_STRUCT_OPS) { + for (i = 0; i < aux->ctx_arg_info_size; i++) + aux->ctx_arg_info[i].ref_obj_id = aux->ctx_arg_info[i].refcounted ? + acquire_reference(env, 0) : 0; + } + ret = do_check(env); out: /* check for NULL is necessary, since cur_state can be freed inside @@ -22392,6 +22731,15 @@ static void print_verification_stats(struct bpf_verifier_env *env) env->peak_states, env->longest_mark_read_walk); } +int bpf_prog_ctx_arg_info_init(struct bpf_prog *prog, + const struct bpf_ctx_arg_aux *info, u32 cnt) +{ + prog->aux->ctx_arg_info = kmemdup_array(info, cnt, sizeof(*info), GFP_KERNEL); + prog->aux->ctx_arg_info_size = cnt; + + return prog->aux->ctx_arg_info ? 0 : -ENOMEM; +} + static int check_struct_ops_btf_id(struct bpf_verifier_env *env) { const struct btf_type *t, *func_proto; @@ -22399,10 +22747,11 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) const struct bpf_struct_ops *st_ops; const struct btf_member *member; struct bpf_prog *prog = env->prog; - u32 btf_id, member_idx; + bool has_refcounted_arg = false; + u32 btf_id, member_idx, member_off; struct btf *btf; const char *mname; - int err; + int i, err; if (!prog->gpl_compatible) { verbose(env, "struct ops programs must have a GPL compatible license\n"); @@ -22450,7 +22799,8 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) return -EINVAL; } - err = bpf_struct_ops_supported(st_ops, __btf_member_bit_offset(t, member) / 8); + member_off = __btf_member_bit_offset(t, member) / 8; + err = bpf_struct_ops_supported(st_ops, member_off); if (err) { verbose(env, "attach to unsupported member %s of struct %s\n", mname, st_ops->name); @@ -22472,17 +22822,32 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) return -EACCES; } - /* btf_ctx_access() used this to provide argument type info */ - prog->aux->ctx_arg_info = - st_ops_desc->arg_info[member_idx].info; - prog->aux->ctx_arg_info_size = - st_ops_desc->arg_info[member_idx].cnt; + for (i = 0; i < st_ops_desc->arg_info[member_idx].cnt; i++) { + if (st_ops_desc->arg_info[member_idx].info->refcounted) { + has_refcounted_arg = true; + break; + } + } + + /* Tail call is not allowed for programs with refcounted arguments since we + * cannot guarantee that valid refcounted kptrs will be passed to the callee. + */ + for (i = 0; i < env->subprog_cnt; i++) { + if (has_refcounted_arg && env->subprog_info[i].has_tail_call) { + verbose(env, "program with __ref argument cannot tail call\n"); + return -EINVAL; + } + } + + prog->aux->st_ops = st_ops; + prog->aux->attach_st_ops_member_off = member_off; prog->aux->attach_func_proto = func_proto; prog->aux->attach_func_name = mname; env->ops = st_ops->verifier_ops; - return 0; + return bpf_prog_ctx_arg_info_init(prog, st_ops_desc->arg_info[member_idx].info, + st_ops_desc->arg_info[member_idx].cnt); } #define SECURITY_PREFIX "security_" @@ -22558,6 +22923,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, if (tgt_prog) { struct bpf_prog_aux *aux = tgt_prog->aux; bool tgt_changes_pkt_data; + bool tgt_might_sleep; if (bpf_prog_is_dev_bound(prog->aux) && !bpf_prog_dev_bound_match(prog, tgt_prog)) { @@ -22600,6 +22966,15 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, "Extension program changes packet data, while original does not\n"); return -EINVAL; } + + tgt_might_sleep = aux->func + ? aux->func[subprog]->aux->might_sleep + : aux->might_sleep; + if (prog->aux->might_sleep && !tgt_might_sleep) { + bpf_log(log, + "Extension program may sleep, while original does not\n"); + return -EINVAL; + } } if (!tgt_prog->jited) { bpf_log(log, "Can attach to only JITed progs\n"); @@ -22856,6 +23231,33 @@ BTF_ID(func, __rcu_read_unlock) #endif BTF_SET_END(btf_id_deny) +/* fexit and fmod_ret can't be used to attach to __noreturn functions. + * Currently, we must manually list all __noreturn functions here. Once a more + * robust solution is implemented, this workaround can be removed. + */ +BTF_SET_START(noreturn_deny) +#ifdef CONFIG_IA32_EMULATION +BTF_ID(func, __ia32_sys_exit) +BTF_ID(func, __ia32_sys_exit_group) +#endif +#ifdef CONFIG_KUNIT +BTF_ID(func, __kunit_abort) +BTF_ID(func, kunit_try_catch_throw) +#endif +#ifdef CONFIG_MODULES +BTF_ID(func, __module_put_and_kthread_exit) +#endif +#ifdef CONFIG_X86_64 +BTF_ID(func, __x64_sys_exit) +BTF_ID(func, __x64_sys_exit_group) +#endif +BTF_ID(func, do_exit) +BTF_ID(func, do_group_exit) +BTF_ID(func, kthread_complete_and_exit) +BTF_ID(func, kthread_exit) +BTF_ID(func, make_task_dead) +BTF_SET_END(noreturn_deny) + static bool can_be_sleepable(struct bpf_prog *prog) { if (prog->type == BPF_PROG_TYPE_TRACING) { @@ -22932,9 +23334,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) prog->aux->attach_btf_trace = true; return 0; } else if (prog->expected_attach_type == BPF_TRACE_ITER) { - if (!bpf_iter_prog_supported(prog)) - return -EINVAL; - return 0; + return bpf_iter_prog_supported(prog); } if (prog->type == BPF_PROG_TYPE_LSM) { @@ -22944,6 +23344,11 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) } else if (prog->type == BPF_PROG_TYPE_TRACING && btf_id_set_contains(&btf_id_deny, btf_id)) { return -EINVAL; + } else if ((prog->expected_attach_type == BPF_TRACE_FEXIT || + prog->expected_attach_type == BPF_MODIFY_RETURN) && + btf_id_set_contains(&noreturn_deny, btf_id)) { + verbose(env, "Attaching fexit/fmod_ret to __noreturn functions is rejected.\n"); + return -EINVAL; } key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id); @@ -23036,6 +23441,302 @@ static int process_fd_array(struct bpf_verifier_env *env, union bpf_attr *attr, return 0; } +static bool can_fallthrough(struct bpf_insn *insn) +{ + u8 class = BPF_CLASS(insn->code); + u8 opcode = BPF_OP(insn->code); + + if (class != BPF_JMP && class != BPF_JMP32) + return true; + + if (opcode == BPF_EXIT || opcode == BPF_JA) + return false; + + return true; +} + +static bool can_jump(struct bpf_insn *insn) +{ + u8 class = BPF_CLASS(insn->code); + u8 opcode = BPF_OP(insn->code); + + if (class != BPF_JMP && class != BPF_JMP32) + return false; + + switch (opcode) { + case BPF_JA: + case BPF_JEQ: + case BPF_JNE: + case BPF_JLT: + case BPF_JLE: + case BPF_JGT: + case BPF_JGE: + case BPF_JSGT: + case BPF_JSGE: + case BPF_JSLT: + case BPF_JSLE: + case BPF_JCOND: + return true; + } + + return false; +} + +static int insn_successors(struct bpf_prog *prog, u32 idx, u32 succ[2]) +{ + struct bpf_insn *insn = &prog->insnsi[idx]; + int i = 0, insn_sz; + u32 dst; + + insn_sz = bpf_is_ldimm64(insn) ? 2 : 1; + if (can_fallthrough(insn) && idx + 1 < prog->len) + succ[i++] = idx + insn_sz; + + if (can_jump(insn)) { + dst = idx + jmp_offset(insn) + 1; + if (i == 0 || succ[0] != dst) + succ[i++] = dst; + } + + return i; +} + +/* Each field is a register bitmask */ +struct insn_live_regs { + u16 use; /* registers read by instruction */ + u16 def; /* registers written by instruction */ + u16 in; /* registers that may be alive before instruction */ + u16 out; /* registers that may be alive after instruction */ +}; + +/* Bitmask with 1s for all caller saved registers */ +#define ALL_CALLER_SAVED_REGS ((1u << CALLER_SAVED_REGS) - 1) + +/* Compute info->{use,def} fields for the instruction */ +static void compute_insn_live_regs(struct bpf_verifier_env *env, + struct bpf_insn *insn, + struct insn_live_regs *info) +{ + struct call_summary cs; + u8 class = BPF_CLASS(insn->code); + u8 code = BPF_OP(insn->code); + u8 mode = BPF_MODE(insn->code); + u16 src = BIT(insn->src_reg); + u16 dst = BIT(insn->dst_reg); + u16 r0 = BIT(0); + u16 def = 0; + u16 use = 0xffff; + + switch (class) { + case BPF_LD: + switch (mode) { + case BPF_IMM: + if (BPF_SIZE(insn->code) == BPF_DW) { + def = dst; + use = 0; + } + break; + case BPF_LD | BPF_ABS: + case BPF_LD | BPF_IND: + /* stick with defaults */ + break; + } + break; + case BPF_LDX: + switch (mode) { + case BPF_MEM: + case BPF_MEMSX: + def = dst; + use = src; + break; + } + break; + case BPF_ST: + switch (mode) { + case BPF_MEM: + def = 0; + use = dst; + break; + } + break; + case BPF_STX: + switch (mode) { + case BPF_MEM: + def = 0; + use = dst | src; + break; + case BPF_ATOMIC: + switch (insn->imm) { + case BPF_CMPXCHG: + use = r0 | dst | src; + def = r0; + break; + case BPF_LOAD_ACQ: + def = dst; + use = src; + break; + case BPF_STORE_REL: + def = 0; + use = dst | src; + break; + default: + use = dst | src; + if (insn->imm & BPF_FETCH) + def = src; + else + def = 0; + } + break; + } + break; + case BPF_ALU: + case BPF_ALU64: + switch (code) { + case BPF_END: + use = dst; + def = dst; + break; + case BPF_MOV: + def = dst; + if (BPF_SRC(insn->code) == BPF_K) + use = 0; + else + use = src; + break; + default: + def = dst; + if (BPF_SRC(insn->code) == BPF_K) + use = dst; + else + use = dst | src; + } + break; + case BPF_JMP: + case BPF_JMP32: + switch (code) { + case BPF_JA: + case BPF_JCOND: + def = 0; + use = 0; + break; + case BPF_EXIT: + def = 0; + use = r0; + break; + case BPF_CALL: + def = ALL_CALLER_SAVED_REGS; + use = def & ~BIT(BPF_REG_0); + if (get_call_summary(env, insn, &cs)) + use = GENMASK(cs.num_params, 1); + break; + default: + def = 0; + if (BPF_SRC(insn->code) == BPF_K) + use = dst; + else + use = dst | src; + } + break; + } + + info->def = def; + info->use = use; +} + +/* Compute may-live registers after each instruction in the program. + * The register is live after the instruction I if it is read by some + * instruction S following I during program execution and is not + * overwritten between I and S. + * + * Store result in env->insn_aux_data[i].live_regs. + */ +static int compute_live_registers(struct bpf_verifier_env *env) +{ + struct bpf_insn_aux_data *insn_aux = env->insn_aux_data; + struct bpf_insn *insns = env->prog->insnsi; + struct insn_live_regs *state; + int insn_cnt = env->prog->len; + int err = 0, i, j; + bool changed; + + /* Use the following algorithm: + * - define the following: + * - I.use : a set of all registers read by instruction I; + * - I.def : a set of all registers written by instruction I; + * - I.in : a set of all registers that may be alive before I execution; + * - I.out : a set of all registers that may be alive after I execution; + * - insn_successors(I): a set of instructions S that might immediately + * follow I for some program execution; + * - associate separate empty sets 'I.in' and 'I.out' with each instruction; + * - visit each instruction in a postorder and update + * state[i].in, state[i].out as follows: + * + * state[i].out = U [state[s].in for S in insn_successors(i)] + * state[i].in = (state[i].out / state[i].def) U state[i].use + * + * (where U stands for set union, / stands for set difference) + * - repeat the computation while {in,out} fields changes for + * any instruction. + */ + state = kvcalloc(insn_cnt, sizeof(*state), GFP_KERNEL); + if (!state) { + err = -ENOMEM; + goto out; + } + + for (i = 0; i < insn_cnt; ++i) + compute_insn_live_regs(env, &insns[i], &state[i]); + + changed = true; + while (changed) { + changed = false; + for (i = 0; i < env->cfg.cur_postorder; ++i) { + int insn_idx = env->cfg.insn_postorder[i]; + struct insn_live_regs *live = &state[insn_idx]; + int succ_num; + u32 succ[2]; + u16 new_out = 0; + u16 new_in = 0; + + succ_num = insn_successors(env->prog, insn_idx, succ); + for (int s = 0; s < succ_num; ++s) + new_out |= state[succ[s]].in; + new_in = (new_out & ~live->def) | live->use; + if (new_out != live->out || new_in != live->in) { + live->in = new_in; + live->out = new_out; + changed = true; + } + } + } + + for (i = 0; i < insn_cnt; ++i) + insn_aux[i].live_regs_before = state[i].in; + + if (env->log.level & BPF_LOG_LEVEL2) { + verbose(env, "Live regs before insn:\n"); + for (i = 0; i < insn_cnt; ++i) { + verbose(env, "%3d: ", i); + for (j = BPF_REG_0; j < BPF_REG_10; ++j) + if (insn_aux[i].live_regs_before & BIT(j)) + verbose(env, "%d", j); + else + verbose(env, "."); + verbose(env, " "); + verbose_insn(env, &insns[i]); + if (bpf_is_ldimm64(&insns[i])) + i++; + } + } + +out: + kvfree(state); + kvfree(env->cfg.insn_postorder); + env->cfg.insn_postorder = NULL; + env->cfg.cur_postorder = 0; + return err; +} + int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { u64 start_time = ktime_get_ns(); @@ -23113,12 +23814,16 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS; env->explored_states = kvcalloc(state_htab_size(env), - sizeof(struct bpf_verifier_state_list *), + sizeof(struct list_head), GFP_USER); ret = -ENOMEM; if (!env->explored_states) goto skip_full_check; + for (i = 0; i < state_htab_size(env); i++) + INIT_LIST_HEAD(&env->explored_states[i]); + INIT_LIST_HEAD(&env->free_list); + ret = check_btf_info_early(env, attr, uattr); if (ret < 0) goto skip_full_check; @@ -23153,6 +23858,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (ret) goto skip_full_check; + ret = compute_live_registers(env); + if (ret < 0) + goto skip_full_check; + ret = mark_fastcall_patterns(env); if (ret < 0) goto skip_full_check; @@ -23291,6 +24000,7 @@ err_unlock: vfree(env->insn_aux_data); kvfree(env->insn_hist); err_free_env: + kvfree(env->cfg.insn_postorder); kvfree(env); return ret; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 997fb2a..d23dc3d 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -392,7 +392,7 @@ static const struct bpf_func_proto bpf_trace_printk_proto = { .arg2_type = ARG_CONST_SIZE, }; -static void __set_printk_clr_event(void) +static void __set_printk_clr_event(struct work_struct *work) { /* * This program might be calling bpf_trace_printk, @@ -405,10 +405,11 @@ static void __set_printk_clr_event(void) if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1)) pr_warn_ratelimited("could not enable bpf_trace_printk events"); } +static DECLARE_WORK(set_printk_work, __set_printk_clr_event); const struct bpf_func_proto *bpf_get_trace_printk_proto(void) { - __set_printk_clr_event(); + schedule_work(&set_printk_work); return &bpf_trace_printk_proto; } @@ -451,7 +452,7 @@ static const struct bpf_func_proto bpf_trace_vprintk_proto = { const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void) { - __set_printk_clr_event(); + schedule_work(&set_printk_work); return &bpf_trace_vprintk_proto; } @@ -606,6 +607,11 @@ static const struct bpf_func_proto bpf_perf_event_read_value_proto = { .arg4_type = ARG_CONST_SIZE, }; +const struct bpf_func_proto *bpf_get_perf_event_read_value_proto(void) +{ + return &bpf_perf_event_read_value_proto; +} + static __always_inline u64 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, u64 flags, struct perf_raw_record *raw, @@ -843,7 +849,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type, struct task_struc if (unlikely(is_global_init(task))) return -EPERM; - if (!preemptible()) { + if (preempt_count() != 0 || irqs_disabled()) { /* Do an early check on signal validity. Otherwise, * the error is lost in deferred irq_work. */ diff --git a/mm/memory.c b/mm/memory.c index b43428a..bea87c0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -6807,6 +6807,124 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, } EXPORT_SYMBOL_GPL(access_process_vm); +#ifdef CONFIG_BPF_SYSCALL +/* + * Copy a string from another process's address space as given in mm. + * If there is any error return -EFAULT. + */ +static int __copy_remote_vm_str(struct mm_struct *mm, unsigned long addr, + void *buf, int len, unsigned int gup_flags) +{ + void *old_buf = buf; + int err = 0; + + *(char *)buf = '\0'; + + if (mmap_read_lock_killable(mm)) + return -EFAULT; + + addr = untagged_addr_remote(mm, addr); + + /* Avoid triggering the temporary warning in __get_user_pages */ + if (!vma_lookup(mm, addr)) { + err = -EFAULT; + goto out; + } + + while (len) { + int bytes, offset, retval; + void *maddr; + struct page *page; + struct vm_area_struct *vma = NULL; + + page = get_user_page_vma_remote(mm, addr, gup_flags, &vma); + if (IS_ERR(page)) { + /* + * Treat as a total failure for now until we decide how + * to handle the CONFIG_HAVE_IOREMAP_PROT case and + * stack expansion. + */ + *(char *)buf = '\0'; + err = -EFAULT; + goto out; + } + + bytes = len; + offset = addr & (PAGE_SIZE - 1); + if (bytes > PAGE_SIZE - offset) + bytes = PAGE_SIZE - offset; + + maddr = kmap_local_page(page); + retval = strscpy(buf, maddr + offset, bytes); + if (retval >= 0) { + /* Found the end of the string */ + buf += retval; + unmap_and_put_page(page, maddr); + break; + } + + buf += bytes - 1; + /* + * Because strscpy always NUL terminates we need to + * copy the last byte in the page if we are going to + * load more pages + */ + if (bytes != len) { + addr += bytes - 1; + copy_from_user_page(vma, page, addr, buf, maddr + (PAGE_SIZE - 1), 1); + buf += 1; + addr += 1; + } + len -= bytes; + + unmap_and_put_page(page, maddr); + } + +out: + mmap_read_unlock(mm); + if (err) + return err; + return buf - old_buf; +} + +/** + * copy_remote_vm_str - copy a string from another process's address space. + * @tsk: the task of the target address space + * @addr: start address to read from + * @buf: destination buffer + * @len: number of bytes to copy + * @gup_flags: flags modifying lookup behaviour + * + * The caller must hold a reference on @mm. + * + * Return: number of bytes copied from @addr (source) to @buf (destination); + * not including the trailing NUL. Always guaranteed to leave NUL-terminated + * buffer. On any error, return -EFAULT. + */ +int copy_remote_vm_str(struct task_struct *tsk, unsigned long addr, + void *buf, int len, unsigned int gup_flags) +{ + struct mm_struct *mm; + int ret; + + if (unlikely(len == 0)) + return 0; + + mm = get_task_mm(tsk); + if (!mm) { + *(char *)buf = '\0'; + return -EFAULT; + } + + ret = __copy_remote_vm_str(mm, addr, buf, len, gup_flags); + + mmput(mm); + + return ret; +} +EXPORT_SYMBOL_GPL(copy_remote_vm_str); +#endif /* CONFIG_BPF_SYSCALL */ + /* * Print the name of a VMA. */ diff --git a/mm/nommu.c b/mm/nommu.c index acc18ce..7533846 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1714,6 +1714,85 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in } EXPORT_SYMBOL_GPL(access_process_vm); +#ifdef CONFIG_BPF_SYSCALL +/* + * Copy a string from another process's address space as given in mm. + * If there is any error return -EFAULT. + */ +static int __copy_remote_vm_str(struct mm_struct *mm, unsigned long addr, + void *buf, int len) +{ + unsigned long addr_end; + struct vm_area_struct *vma; + int ret = -EFAULT; + + *(char *)buf = '\0'; + + if (mmap_read_lock_killable(mm)) + return ret; + + /* the access must start within one of the target process's mappings */ + vma = find_vma(mm, addr); + if (!vma) + goto out; + + if (check_add_overflow(addr, len, &addr_end)) + goto out; + + /* don't overrun this mapping */ + if (addr_end > vma->vm_end) + len = vma->vm_end - addr; + + /* only read mappings where it is permitted */ + if (vma->vm_flags & VM_MAYREAD) { + ret = strscpy(buf, (char *)addr, len); + if (ret < 0) + ret = len - 1; + } + +out: + mmap_read_unlock(mm); + return ret; +} + +/** + * copy_remote_vm_str - copy a string from another process's address space. + * @tsk: the task of the target address space + * @addr: start address to read from + * @buf: destination buffer + * @len: number of bytes to copy + * @gup_flags: flags modifying lookup behaviour (unused) + * + * The caller must hold a reference on @mm. + * + * Return: number of bytes copied from @addr (source) to @buf (destination); + * not including the trailing NUL. Always guaranteed to leave NUL-terminated + * buffer. On any error, return -EFAULT. + */ +int copy_remote_vm_str(struct task_struct *tsk, unsigned long addr, + void *buf, int len, unsigned int gup_flags) +{ + struct mm_struct *mm; + int ret; + + if (unlikely(len == 0)) + return 0; + + mm = get_task_mm(tsk); + if (!mm) { + *(char *)buf = '\0'; + return -EFAULT; + } + + ret = __copy_remote_vm_str(mm, addr, buf, len); + + mmput(mm); + + return ret; +} +EXPORT_SYMBOL_GPL(copy_remote_vm_str); +#endif /* CONFIG_BPF_SYSCALL */ + /** * nommu_shrink_inode_mappings - Shrink the shared mappings on an inode * @inode: The inode to check diff --git a/net/core/filter.c b/net/core/filter.c index 46ae8eb..bc68287 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8137,6 +8137,8 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skb_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; + case BPF_FUNC_get_netns_cookie: + return &bpf_get_netns_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_perf_event_output: @@ -9697,7 +9699,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, queue_mapping): if (type == BPF_WRITE) { - u32 off = bpf_target_off(struct sk_buff, queue_mapping, 2, target_size); + u32 offset = bpf_target_off(struct sk_buff, queue_mapping, 2, target_size); if (BPF_CLASS(si->code) == BPF_ST && si->imm >= NO_QUEUE_MAPPING) { *insn++ = BPF_JMP_A(0); /* noop */ @@ -9706,7 +9708,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, if (BPF_CLASS(si->code) == BPF_STX) *insn++ = BPF_JMP_IMM(BPF_JGE, si->src_reg, NO_QUEUE_MAPPING, 1); - *insn++ = BPF_EMIT_STORE(BPF_H, si, off); + *insn++ = BPF_EMIT_STORE(BPF_H, si, offset); } else { *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index dd9944a..5b63263 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -307,7 +307,7 @@ $(obj)/$(TRACE_HELPERS): TPROGS_CFLAGS := $(TPROGS_CFLAGS) -D__must_check= VMLINUX_BTF_PATHS ?= $(abspath $(if $(O),$(O)/vmlinux)) \ $(abspath $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)) \ - $(abspath ./vmlinux) + $(abspath $(objtree)/vmlinux) VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) $(obj)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) diff --git a/scripts/Makefile.btf b/scripts/Makefile.btf index c3cbeb1..fbaaec2 100644 --- a/scripts/Makefile.btf +++ b/scripts/Makefile.btf @@ -24,7 +24,7 @@ else pahole-flags-$(call test-ge, $(pahole-ver), 126) = -j$(JOBS) --btf_features=encode_force,var,float,enum64,decl_tag,type_tag,optimized_func,consistent_func,decl_tag_kfuncs ifneq ($(KBUILD_EXTMOD),) -module-pahole-flags-$(call test-ge, $(pahole-ver), 126) += --btf_features=distilled_base +module-pahole-flags-$(call test-ge, $(pahole-ver), 128) += --btf_features=distilled_base endif endif diff --git a/security/security.c b/security/security.c index 8aa8392..fb57e8f 100644 --- a/security/security.c +++ b/security/security.c @@ -5627,6 +5627,7 @@ int security_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op, * @cmd: command * @attr: bpf attribute * @size: size + * @kernel: whether or not call originated from kernel * * Do a initial check for all bpf syscalls after the attribute is copied into * the kernel. The actual security module can implement their own rules to @@ -5634,9 +5635,9 @@ int security_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op, * * Return: Returns 0 if permission is granted. */ -int security_bpf(int cmd, union bpf_attr *attr, unsigned int size) +int security_bpf(int cmd, union bpf_attr *attr, unsigned int size, bool kernel) { - return call_int_hook(bpf, cmd, attr, size); + return call_int_hook(bpf, cmd, attr, size, kernel); } /** @@ -5673,6 +5674,7 @@ int security_bpf_prog(struct bpf_prog *prog) * @map: BPF map object * @attr: BPF syscall attributes used to create BPF map * @token: BPF token used to grant user access + * @kernel: whether or not call originated from kernel * * Do a check when the kernel creates a new BPF map. This is also the * point where LSM blob is allocated for LSMs that need them. @@ -5680,9 +5682,9 @@ int security_bpf_prog(struct bpf_prog *prog) * Return: Returns 0 on success, error on failure. */ int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, - struct bpf_token *token) + struct bpf_token *token, bool kernel) { - return call_int_hook(bpf_map_create, map, attr, token); + return call_int_hook(bpf_map_create, map, attr, token, kernel); } /** @@ -5690,6 +5692,7 @@ int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, * @prog: BPF program object * @attr: BPF syscall attributes used to create BPF program * @token: BPF token used to grant user access to BPF subsystem + * @kernel: whether or not call originated from kernel * * Perform an access control check when the kernel loads a BPF program and * allocates associated BPF program object. This hook is also responsible for @@ -5698,9 +5701,9 @@ int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, * Return: Returns 0 on success, error on failure. */ int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, - struct bpf_token *token) + struct bpf_token *token, bool kernel) { - return call_int_hook(bpf_prog_load, prog, attr, token); + return call_int_hook(bpf_prog_load, prog, attr, token, kernel); } /** diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 7150c95..fb66ed2 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6907,7 +6907,7 @@ static int selinux_ib_alloc_security(void *ib_sec) #ifdef CONFIG_BPF_SYSCALL static int selinux_bpf(int cmd, union bpf_attr *attr, - unsigned int size) + unsigned int size, bool kernel) { u32 sid = current_sid(); int ret; @@ -6994,7 +6994,7 @@ static int selinux_bpf_prog(struct bpf_prog *prog) } static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, - struct bpf_token *token) + struct bpf_token *token, bool kernel) { struct bpf_security_struct *bpfsec; @@ -7017,7 +7017,7 @@ static void selinux_bpf_map_free(struct bpf_map *map) } static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, - struct bpf_token *token) + struct bpf_token *token, bool kernel) { struct bpf_security_struct *bpfsec; diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 6ea4823..9e9a5f0 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -65,7 +65,12 @@ prefix ?= /usr/local bash_compdir ?= /usr/share/bash-completion/completions CFLAGS += -O2 -CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wno-missing-field-initializers +CFLAGS += -W +CFLAGS += -Wall +CFLAGS += -Wextra +CFLAGS += -Wformat-signedness +CFLAGS += -Wno-unused-parameter +CFLAGS += -Wno-missing-field-initializers CFLAGS += $(filter-out -Wswitch-enum -Wnested-externs,$(EXTRA_WARNINGS)) CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ -I$(or $(OUTPUT),.) \ diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 2636655..6b14cbf 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -253,7 +253,7 @@ static int dump_btf_type(const struct btf *btf, __u32 id, if (btf_kflag(t)) printf("\n\t'%s' val=%d", name, v->val); else - printf("\n\t'%s' val=%u", name, v->val); + printf("\n\t'%s' val=%u", name, (__u32)v->val); } } if (json_output) @@ -1022,7 +1022,7 @@ static int do_dump(int argc, char **argv) for (i = 0; i < root_type_cnt; i++) { if (root_type_ids[i] == root_id) { err = -EINVAL; - p_err("duplicate root_id %d supplied", root_id); + p_err("duplicate root_id %u supplied", root_id); goto done; } } @@ -1132,7 +1132,7 @@ build_btf_type_table(struct hashmap *tab, enum bpf_obj_type type, break; default: err = -1; - p_err("unexpected object type: %d", type); + p_err("unexpected object type: %u", type); goto err_free; } if (err) { @@ -1155,7 +1155,7 @@ build_btf_type_table(struct hashmap *tab, enum bpf_obj_type type, break; default: err = -1; - p_err("unexpected object type: %d", type); + p_err("unexpected object type: %u", type); goto err_free; } if (fd < 0) { @@ -1188,7 +1188,7 @@ build_btf_type_table(struct hashmap *tab, enum bpf_obj_type type, break; default: err = -1; - p_err("unexpected object type: %d", type); + p_err("unexpected object type: %u", type); goto err_free; } if (!btf_id) @@ -1254,12 +1254,12 @@ show_btf_plain(struct bpf_btf_info *info, int fd, n = 0; hashmap__for_each_key_entry(btf_prog_table, entry, info->id) { - printf("%s%lu", n++ == 0 ? " prog_ids " : ",", entry->value); + printf("%s%lu", n++ == 0 ? " prog_ids " : ",", (unsigned long)entry->value); } n = 0; hashmap__for_each_key_entry(btf_map_table, entry, info->id) { - printf("%s%lu", n++ == 0 ? " map_ids " : ",", entry->value); + printf("%s%lu", n++ == 0 ? " map_ids " : ",", (unsigned long)entry->value); } emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index 527fe86..4e896d8 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -653,7 +653,7 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id, case BTF_KIND_ARRAY: array = (struct btf_array *)(t + 1); BTF_PRINT_TYPE(array->type); - BTF_PRINT_ARG("[%d]", array->nelems); + BTF_PRINT_ARG("[%u]", array->nelems); break; case BTF_KIND_PTR: BTF_PRINT_TYPE(t->type); diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 9af426d..93b139b 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -191,7 +191,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, if (attach_btf_name) printf(" %-15s", attach_btf_name); else if (info.attach_btf_id) - printf(" attach_btf_obj_id=%d attach_btf_id=%d", + printf(" attach_btf_obj_id=%u attach_btf_id=%u", info.attach_btf_obj_id, info.attach_btf_id); printf("\n"); } diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 9b75639..ecfa790 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -461,10 +461,11 @@ int get_fd_type(int fd) p_err("can't read link type: %s", strerror(errno)); return -1; } - if (n == sizeof(path)) { + if (n == sizeof(buf)) { p_err("can't read link type: path too long!"); return -1; } + buf[n] = '\0'; if (strstr(buf, "bpf-map")) return BPF_OBJ_MAP; @@ -713,7 +714,7 @@ ifindex_to_arch(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, const char **opt) int vendor_id; if (!ifindex_to_name_ns(ifindex, ns_dev, ns_ino, devname)) { - p_err("Can't get net device name for ifindex %d: %s", ifindex, + p_err("Can't get net device name for ifindex %u: %s", ifindex, strerror(errno)); return NULL; } @@ -738,7 +739,7 @@ ifindex_to_arch(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, const char **opt) /* No NFP support in LLVM, we have no valid triple to return. */ default: p_err("Can't get arch name for device vendor id 0x%04x", - vendor_id); + (unsigned int)vendor_id); return NULL; } } diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 5a4d324..67a6011 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -670,7 +670,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name) continue; if (bpf_map__is_internal(map) && (bpf_map__map_flags(map) & BPF_F_MMAPABLE)) - printf("\tskel_free_map_data(skel->%1$s, skel->maps.%1$s.initial_value, %2$zd);\n", + printf("\tskel_free_map_data(skel->%1$s, skel->maps.%1$s.initial_value, %2$zu);\n", ident, bpf_map_mmap_sz(map)); codegen("\ \n\ @@ -984,7 +984,7 @@ static int walk_st_ops_shadow_vars(struct btf *btf, const char *ident, offset = m->offset / 8; if (next_offset < offset) - printf("\t\t\tchar __padding_%d[%d];\n", i, offset - next_offset); + printf("\t\t\tchar __padding_%d[%u];\n", i, offset - next_offset); switch (btf_kind(member_type)) { case BTF_KIND_INT: @@ -1052,7 +1052,7 @@ static int walk_st_ops_shadow_vars(struct btf *btf, const char *ident, /* Cannot fail since it must be a struct type */ size = btf__resolve_size(btf, map_type_id); if (next_offset < (__u32)size) - printf("\t\t\tchar __padding_end[%d];\n", size - next_offset); + printf("\t\t\tchar __padding_end[%u];\n", size - next_offset); out: btf_dump__free(d); @@ -2095,7 +2095,7 @@ btfgen_mark_type(struct btfgen_info *info, unsigned int type_id, bool follow_poi break; /* tells if some other type needs to be handled */ default: - p_err("unsupported kind: %s (%d)", btf_kind_str(btf_type), type_id); + p_err("unsupported kind: %s (%u)", btf_kind_str(btf_type), type_id); return -EINVAL; } @@ -2147,7 +2147,7 @@ static int btfgen_record_field_relo(struct btfgen_info *info, struct bpf_core_sp btf_type = btf__type_by_id(btf, type_id); break; default: - p_err("unsupported kind: %s (%d)", + p_err("unsupported kind: %s (%u)", btf_kind_str(btf_type), btf_type->type); return -EINVAL; } @@ -2246,7 +2246,7 @@ static int btfgen_mark_type_match(struct btfgen_info *info, __u32 type_id, bool } /* tells if some other type needs to be handled */ default: - p_err("unsupported kind: %s (%d)", btf_kind_str(btf_type), type_id); + p_err("unsupported kind: %s (%u)", btf_kind_str(btf_type), type_id); return -EINVAL; } diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c index c032d2c..8895b4e 100644 --- a/tools/bpf/bpftool/jit_disasm.c +++ b/tools/bpf/bpftool/jit_disasm.c @@ -343,7 +343,8 @@ int disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, { const struct bpf_line_info *linfo = NULL; unsigned int nr_skip = 0; - int count, i, pc = 0; + int count, i; + unsigned int pc = 0; disasm_ctx_t ctx; if (!len) diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index 5cd503b..52fd2c9 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -107,7 +107,7 @@ static int link_parse_fd(int *argc, char ***argv) fd = bpf_link_get_fd_by_id(id); if (fd < 0) - p_err("failed to get link with ID %d: %s", id, strerror(errno)); + p_err("failed to get link with ID %u: %s", id, strerror(errno)); return fd; } else if (is_prefix(**argv, "pinned")) { char *path; @@ -404,7 +404,7 @@ static char *perf_config_hw_cache_str(__u64 config) if (hw_cache) snprintf(str, PERF_HW_CACHE_LEN, "%s-", hw_cache); else - snprintf(str, PERF_HW_CACHE_LEN, "%lld-", config & 0xff); + snprintf(str, PERF_HW_CACHE_LEN, "%llu-", config & 0xff); op = perf_event_name(evsel__hw_cache_op, (config >> 8) & 0xff); if (op) @@ -412,7 +412,7 @@ static char *perf_config_hw_cache_str(__u64 config) "%s-", op); else snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str), - "%lld-", (config >> 8) & 0xff); + "%llu-", (config >> 8) & 0xff); result = perf_event_name(evsel__hw_cache_result, config >> 16); if (result) @@ -420,7 +420,7 @@ static char *perf_config_hw_cache_str(__u64 config) "%s", result); else snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str), - "%lld", config >> 16); + "%llu", config >> 16); return str; } @@ -623,7 +623,7 @@ static void show_link_ifindex_plain(__u32 ifindex) else snprintf(devname, sizeof(devname), "(detached)"); if (ret) - snprintf(devname, sizeof(devname), "%s(%d)", + snprintf(devname, sizeof(devname), "%s(%u)", tmpname, ifindex); printf("ifindex %s ", devname); } @@ -699,7 +699,7 @@ void netfilter_dump_plain(const struct bpf_link_info *info) if (pfname) printf("\n\t%s", pfname); else - printf("\n\tpf: %d", pf); + printf("\n\tpf: %u", pf); if (hookname) printf(" %s", hookname); @@ -773,7 +773,7 @@ static void show_uprobe_multi_plain(struct bpf_link_info *info) printf("func_cnt %u ", info->uprobe_multi.count); if (info->uprobe_multi.pid) - printf("pid %d ", info->uprobe_multi.pid); + printf("pid %u ", info->uprobe_multi.pid); printf("\n\t%-16s %-16s %-16s", "offset", "ref_ctr_offset", "cookies"); for (i = 0; i < info->uprobe_multi.count; i++) { diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 08d0ac5..cd5963c 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -152,7 +152,7 @@ static int do_version(int argc, char **argv) BPFTOOL_MINOR_VERSION, BPFTOOL_PATCH_VERSION); #endif jsonw_name(json_wtr, "libbpf_version"); - jsonw_printf(json_wtr, "\"%d.%d\"", + jsonw_printf(json_wtr, "\"%u.%u\"", libbpf_major_version(), libbpf_minor_version()); jsonw_name(json_wtr, "features"); @@ -370,7 +370,7 @@ static int do_batch(int argc, char **argv) while ((cp = strstr(buf, "\\\n")) != NULL) { if (!fgets(contline, sizeof(contline), fp) || strlen(contline) == 0) { - p_err("missing continuation line on command %d", + p_err("missing continuation line on command %u", lines); err = -1; goto err_close; @@ -381,7 +381,7 @@ static int do_batch(int argc, char **argv) *cp = '\0'; if (strlen(buf) + strlen(contline) + 1 > sizeof(buf)) { - p_err("command %d is too long", lines); + p_err("command %u is too long", lines); err = -1; goto err_close; } @@ -423,7 +423,7 @@ static int do_batch(int argc, char **argv) err = -1; } else { if (!json_output) - printf("processed %d commands\n", lines); + printf("processed %u commands\n", lines); } err_close: if (fp != stdin) diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index b89bd79..81cc668 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -285,7 +285,7 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, } if (info->value_size) { for (i = 0; i < n; i++) { - printf("value (CPU %02d):%c", + printf("value (CPU %02u):%c", i, info->value_size > 16 ? '\n' : ' '); fprint_hex(stdout, value + i * step, info->value_size, " "); @@ -316,7 +316,7 @@ static char **parse_bytes(char **argv, const char *name, unsigned char *val, } if (i != n) { - p_err("%s expected %d bytes got %d", name, n, i); + p_err("%s expected %u bytes got %u", name, n, i); return NULL; } @@ -462,7 +462,7 @@ static void show_map_header_json(struct bpf_map_info *info, json_writer_t *wtr) jsonw_string_field(wtr, "name", info->name); jsonw_name(wtr, "flags"); - jsonw_printf(wtr, "%d", info->map_flags); + jsonw_printf(wtr, "%u", info->map_flags); } static int show_map_close_json(int fd, struct bpf_map_info *info) @@ -588,7 +588,7 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) if (prog_type_str) printf("owner_prog_type %s ", prog_type_str); else - printf("owner_prog_type %d ", prog_type); + printf("owner_prog_type %u ", prog_type); } if (owner_jited) printf("owner%s jited", @@ -615,7 +615,7 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) printf("\n\t"); if (info->btf_id) - printf("btf_id %d", info->btf_id); + printf("btf_id %u", info->btf_id); if (frozen) printf("%sfrozen", info->btf_id ? " " : ""); @@ -1270,6 +1270,10 @@ static int do_create(int argc, char **argv) } else if (is_prefix(*argv, "name")) { NEXT_ARG(); map_name = GET_ARG(); + if (strlen(map_name) > BPF_OBJ_NAME_LEN - 1) { + p_info("Warning: map name is longer than %u characters, it will be truncated.", + BPF_OBJ_NAME_LEN - 1); + } } else if (is_prefix(*argv, "key")) { if (parse_u32_arg(&argc, &argv, &key_size, "key size")) diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c index 21d7d44..552b4ca 100644 --- a/tools/bpf/bpftool/map_perf_ring.c +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -91,15 +91,15 @@ print_bpf_output(void *private_data, int cpu, struct perf_event_header *event) jsonw_end_object(json_wtr); } else { if (e->header.type == PERF_RECORD_SAMPLE) { - printf("== @%lld.%09lld CPU: %d index: %d =====\n", + printf("== @%llu.%09llu CPU: %d index: %d =====\n", e->time / 1000000000ULL, e->time % 1000000000ULL, cpu, idx); fprint_hex(stdout, e->data, e->size, " "); printf("\n"); } else if (e->header.type == PERF_RECORD_LOST) { - printf("lost %lld events\n", lost->lost); + printf("lost %llu events\n", lost->lost); } else { - printf("unknown event type=%d size=%d\n", + printf("unknown event type=%u size=%u\n", e->header.type, e->header.size); } } diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index d2242d9..64f958f 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -476,7 +476,7 @@ static void __show_dev_tc_bpf(const struct ip_devname_ifindex *dev, for (i = 0; i < optq.count; i++) { NET_START_OBJECT; NET_DUMP_STR("devname", "%s", dev->devname); - NET_DUMP_UINT("ifindex", "(%u)", dev->ifindex); + NET_DUMP_UINT("ifindex", "(%u)", (unsigned int)dev->ifindex); NET_DUMP_STR("kind", " %s", attach_loc_strings[loc]); ret = __show_dev_tc_bpf_name(prog_ids[i], prog_name, sizeof(prog_name)); @@ -831,7 +831,7 @@ static void show_link_netfilter(void) if (err) { if (errno == ENOENT) break; - p_err("can't get next link: %s (id %d)", strerror(errno), id); + p_err("can't get next link: %s (id %u)", strerror(errno), id); break; } diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c index 5f65140..0a3c7e9 100644 --- a/tools/bpf/bpftool/netlink_dumper.c +++ b/tools/bpf/bpftool/netlink_dumper.c @@ -45,7 +45,7 @@ static int do_xdp_dump_one(struct nlattr *attr, unsigned int ifindex, NET_START_OBJECT; if (name) NET_DUMP_STR("devname", "%s", name); - NET_DUMP_UINT("ifindex", "(%d)", ifindex); + NET_DUMP_UINT("ifindex", "(%u)", ifindex); if (mode == XDP_ATTACHED_MULTI) { if (json_output) { @@ -74,7 +74,7 @@ int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb) if (!tb[IFLA_XDP]) return 0; - return do_xdp_dump_one(tb[IFLA_XDP], ifinfo->ifi_index, + return do_xdp_dump_one(tb[IFLA_XDP], (unsigned int)ifinfo->ifi_index, libbpf_nla_getattr_str(tb[IFLA_IFNAME])); } @@ -168,7 +168,7 @@ int do_filter_dump(struct tcmsg *info, struct nlattr **tb, const char *kind, NET_START_OBJECT; if (devname[0] != '\0') NET_DUMP_STR("devname", "%s", devname); - NET_DUMP_UINT("ifindex", "(%u)", ifindex); + NET_DUMP_UINT("ifindex", "(%u)", (unsigned int)ifindex); NET_DUMP_STR("kind", " %s", kind); ret = do_bpf_filter_dump(tb[TCA_OPTIONS]); NET_END_OBJECT_FINAL; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index e71be67..f010295 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -521,10 +521,10 @@ static void print_prog_header_plain(struct bpf_prog_info *info, int fd) print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino); printf("%s", info->gpl_compatible ? " gpl" : ""); if (info->run_time_ns) - printf(" run_time_ns %lld run_cnt %lld", + printf(" run_time_ns %llu run_cnt %llu", info->run_time_ns, info->run_cnt); if (info->recursion_misses) - printf(" recursion_misses %lld", info->recursion_misses); + printf(" recursion_misses %llu", info->recursion_misses); printf("\n"); } @@ -569,7 +569,7 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd, bool orphaned) } if (info->btf_id) - printf("\n\tbtf_id %d", info->btf_id); + printf("\n\tbtf_id %u", info->btf_id); emit_obj_refs_plain(refs_table, info->id, "\n\tpids "); @@ -1164,7 +1164,7 @@ static int get_run_data(const char *fname, void **data_ptr, unsigned int *size) } if (nb_read > buf_size - block_size) { if (buf_size == UINT32_MAX) { - p_err("data_in/ctx_in is too long (max: %d)", + p_err("data_in/ctx_in is too long (max: %u)", UINT32_MAX); goto err_free; } @@ -1928,6 +1928,7 @@ static int do_loader(int argc, char **argv) obj = bpf_object__open_file(file, &open_opts); if (!obj) { + err = -1; p_err("failed to open object file"); goto err_close_obj; } @@ -2251,7 +2252,7 @@ static char *profile_target_name(int tgt_fd) t = btf__type_by_id(btf, func_info.type_id); if (!t) { - p_err("btf %d doesn't have type %d", + p_err("btf %u doesn't have type %u", info.btf_id, func_info.type_id); goto out; } @@ -2329,7 +2330,7 @@ static int profile_open_perf_events(struct profiler_bpf *obj) continue; for (cpu = 0; cpu < obj->rodata->num_cpu; cpu++) { if (profile_open_perf_event(m, cpu, map_fd)) { - p_err("failed to create event %s on cpu %d", + p_err("failed to create event %s on cpu %u", metrics[m].name, cpu); return -1; } diff --git a/tools/bpf/bpftool/tracelog.c b/tools/bpf/bpftool/tracelog.c index bf1f022..31d806e 100644 --- a/tools/bpf/bpftool/tracelog.c +++ b/tools/bpf/bpftool/tracelog.c @@ -78,7 +78,7 @@ static bool get_tracefs_pipe(char *mnt) return false; /* Allow room for NULL terminating byte and pipe file name */ - snprintf(format, sizeof(format), "%%*s %%%zds %%99s %%*s %%*d %%*d\\n", + snprintf(format, sizeof(format), "%%*s %%%zus %%99s %%*s %%*d %%*d\\n", PATH_MAX - strlen(pipe_name) - 1); while (fscanf(fp, format, mnt, type) == 2) if (strcmp(type, fstype) == 0) { diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index d009434..5e7cb8b 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -199,13 +199,13 @@ 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); + "map[id:%d]", 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); + "map[id:%d][0]+%d", insn->imm, (insn + 1)->imm); else if (insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), - "map[idx:%u]+%u", insn->imm, (insn + 1)->imm); + "map[idx:%d]+%d", insn->imm, (insn + 1)->imm); else if (insn->src_reg == BPF_PSEUDO_FUNC) snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "subprog[%+d]", insn->imm); diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile index e49203e..78a436c 100644 --- a/tools/bpf/runqslower/Makefile +++ b/tools/bpf/runqslower/Makefile @@ -6,6 +6,7 @@ OUTPUT ?= $(abspath .output)/ BPFTOOL_OUTPUT := $(OUTPUT)bpftool/ DEFAULT_BPFTOOL := $(BPFTOOL_OUTPUT)bootstrap/bpftool BPFTOOL ?= $(DEFAULT_BPFTOOL) +BPF_TARGET_ENDIAN ?= --target=bpf LIBBPF_SRC := $(abspath ../../lib/bpf) BPFOBJ_OUTPUT := $(OUTPUT)libbpf/ BPFOBJ := $(BPFOBJ_OUTPUT)libbpf.a @@ -60,7 +61,7 @@ $(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL) $(QUIET_GEN)$(BPFTOOL) gen skeleton $< > $@ $(OUTPUT)/%.bpf.o: %.bpf.c $(BPFOBJ) | $(OUTPUT) - $(QUIET_GEN)$(CLANG) -g -O2 --target=bpf $(INCLUDES) \ + $(QUIET_GEN)$(CLANG) -g -O2 $(BPF_TARGET_ENDIAN) $(INCLUDES) \ -c $(filter %.c,$^) -o $@ && \ $(LLVM_STRIP) -g $@ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index defa5bb..28705ae 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -51,6 +51,9 @@ #define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ #define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ +#define BPF_LOAD_ACQ 0x100 /* load-acquire */ +#define BPF_STORE_REL 0x110 /* store-release */ + enum bpf_cond_pseudo_jmp { BPF_MAY_GOTO = 0, }; @@ -1207,6 +1210,7 @@ enum bpf_perf_event_type { #define BPF_F_BEFORE (1U << 3) #define BPF_F_AFTER (1U << 4) #define BPF_F_ID (1U << 5) +#define BPF_F_PREORDER (1U << 6) #define BPF_F_LINK BPF_F_LINK /* 1 << 13 */ /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the @@ -1648,6 +1652,7 @@ union bpf_attr { }; __u32 next_id; __u32 open_flags; + __s32 fd_by_id_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ @@ -6019,7 +6024,10 @@ union bpf_attr { FN(user_ringbuf_drain, 209, ##ctx) \ FN(cgrp_storage_get, 210, ##ctx) \ FN(cgrp_storage_delete, 211, ##ctx) \ - /* */ + /* This helper list is effectively frozen. If you are trying to \ + * add a new helper, you should add a kfunc instead which has \ + * less stability guarantees. See Documentation/bpf/kfuncs.rst \ + */ /* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't * know or care about integer value that is now passed as second argument diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index ec1798b..266d4ff 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -36,7 +36,8 @@ struct btf_type { * bits 24-28: kind (e.g. int, ptr, array...etc) * bits 29-30: unused * bit 31: kind_flag, currently used by - * struct, union, enum, fwd and enum64 + * struct, union, enum, fwd, enum64, + * decl_tag and type_tag */ __u32 info; /* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64. diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 359f73e..a9c3e33 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -1097,7 +1097,7 @@ int bpf_map_get_fd_by_id(__u32 id) int bpf_btf_get_fd_by_id_opts(__u32 id, const struct bpf_get_fd_by_id_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, open_flags); + const size_t attr_sz = offsetofend(union bpf_attr, fd_by_id_token_fd); union bpf_attr attr; int fd; @@ -1107,6 +1107,7 @@ int bpf_btf_get_fd_by_id_opts(__u32 id, memset(&attr, 0, attr_sz); attr.btf_id = id; attr.open_flags = OPTS_GET(opts, open_flags, 0); + attr.fd_by_id_token_fd = OPTS_GET(opts, token_fd, 0); fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, attr_sz); return libbpf_err_errno(fd); diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 435da95..777627d 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -487,9 +487,10 @@ LIBBPF_API int bpf_link_get_next_id(__u32 start_id, __u32 *next_id); struct bpf_get_fd_by_id_opts { size_t sz; /* size of this struct for forward/backward compatibility */ __u32 open_flags; /* permissions requested for the operation on fd */ + __u32 token_fd; size_t :0; }; -#define bpf_get_fd_by_id_opts__last_field open_flags +#define bpf_get_fd_by_id_opts__last_field token_fd LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id); LIBBPF_API int bpf_prog_get_fd_by_id_opts(__u32 id, diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 48c66f3..38bc6b1 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1619,12 +1619,18 @@ exit_free: return btf; } -struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf) +struct btf *btf_load_from_kernel(__u32 id, struct btf *base_btf, int token_fd) { struct btf *btf; int btf_fd; + LIBBPF_OPTS(bpf_get_fd_by_id_opts, opts); + + if (token_fd) { + opts.open_flags |= BPF_F_TOKEN_FD; + opts.token_fd = token_fd; + } - btf_fd = bpf_btf_get_fd_by_id(id); + btf_fd = bpf_btf_get_fd_by_id_opts(id, &opts); if (btf_fd < 0) return libbpf_err_ptr(-errno); @@ -1634,6 +1640,11 @@ struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf) return libbpf_ptr(btf); } +struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf) +{ + return btf_load_from_kernel(id, base_btf, 0); +} + struct btf *btf__load_from_kernel_by_id(__u32 id) { return btf__load_from_kernel_by_id_split(id, NULL); @@ -2090,7 +2101,7 @@ static int validate_type_id(int id) } /* generic append function for PTR, TYPEDEF, CONST/VOLATILE/RESTRICT */ -static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref_type_id) +static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref_type_id, int kflag) { struct btf_type *t; int sz, name_off = 0; @@ -2113,7 +2124,7 @@ static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref } t->name_off = name_off; - t->info = btf_type_info(kind, 0, 0); + t->info = btf_type_info(kind, 0, kflag); t->type = ref_type_id; return btf_commit_type(btf, sz); @@ -2128,7 +2139,7 @@ static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref */ int btf__add_ptr(struct btf *btf, int ref_type_id) { - return btf_add_ref_kind(btf, BTF_KIND_PTR, NULL, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_PTR, NULL, ref_type_id, 0); } /* @@ -2506,7 +2517,7 @@ int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind) struct btf_type *t; int id; - id = btf_add_ref_kind(btf, BTF_KIND_FWD, name, 0); + id = btf_add_ref_kind(btf, BTF_KIND_FWD, name, 0, 0); if (id <= 0) return id; t = btf_type_by_id(btf, id); @@ -2536,7 +2547,7 @@ int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id) if (!name || !name[0]) return libbpf_err(-EINVAL); - return btf_add_ref_kind(btf, BTF_KIND_TYPEDEF, name, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_TYPEDEF, name, ref_type_id, 0); } /* @@ -2548,7 +2559,7 @@ int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id) */ int btf__add_volatile(struct btf *btf, int ref_type_id) { - return btf_add_ref_kind(btf, BTF_KIND_VOLATILE, NULL, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_VOLATILE, NULL, ref_type_id, 0); } /* @@ -2560,7 +2571,7 @@ int btf__add_volatile(struct btf *btf, int ref_type_id) */ int btf__add_const(struct btf *btf, int ref_type_id) { - return btf_add_ref_kind(btf, BTF_KIND_CONST, NULL, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_CONST, NULL, ref_type_id, 0); } /* @@ -2572,7 +2583,7 @@ int btf__add_const(struct btf *btf, int ref_type_id) */ int btf__add_restrict(struct btf *btf, int ref_type_id) { - return btf_add_ref_kind(btf, BTF_KIND_RESTRICT, NULL, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_RESTRICT, NULL, ref_type_id, 0); } /* @@ -2588,7 +2599,24 @@ int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id) if (!value || !value[0]) return libbpf_err(-EINVAL); - return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id, 0); +} + +/* + * Append new BTF_KIND_TYPE_TAG type with: + * - *value*, non-empty/non-NULL tag value; + * - *ref_type_id* - referenced type ID, it might not exist yet; + * Set info->kflag to 1, indicating this tag is an __attribute__ + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_type_attr(struct btf *btf, const char *value, int ref_type_id) +{ + if (!value || !value[0]) + return libbpf_err(-EINVAL); + + return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id, 1); } /* @@ -2610,7 +2638,7 @@ int btf__add_func(struct btf *btf, const char *name, linkage != BTF_FUNC_EXTERN) return libbpf_err(-EINVAL); - id = btf_add_ref_kind(btf, BTF_KIND_FUNC, name, proto_type_id); + id = btf_add_ref_kind(btf, BTF_KIND_FUNC, name, proto_type_id, 0); if (id > 0) { struct btf_type *t = btf_type_by_id(btf, id); @@ -2845,18 +2873,8 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __ return 0; } -/* - * Append new BTF_KIND_DECL_TAG type with: - * - *value* - non-empty/non-NULL string; - * - *ref_type_id* - referenced type ID, it might not exist yet; - * - *component_idx* - -1 for tagging reference type, otherwise struct/union - * member or function argument index; - * Returns: - * - >0, type ID of newly added BTF type; - * - <0, on error. - */ -int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, - int component_idx) +static int btf_add_decl_tag(struct btf *btf, const char *value, int ref_type_id, + int component_idx, int kflag) { struct btf_type *t; int sz, value_off; @@ -2880,13 +2898,46 @@ int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, return value_off; t->name_off = value_off; - t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, false); + t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, kflag); t->type = ref_type_id; btf_decl_tag(t)->component_idx = component_idx; return btf_commit_type(btf, sz); } +/* + * Append new BTF_KIND_DECL_TAG type with: + * - *value* - non-empty/non-NULL string; + * - *ref_type_id* - referenced type ID, it might not exist yet; + * - *component_idx* - -1 for tagging reference type, otherwise struct/union + * member or function argument index; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, + int component_idx) +{ + return btf_add_decl_tag(btf, value, ref_type_id, component_idx, 0); +} + +/* + * Append new BTF_KIND_DECL_TAG type with: + * - *value* - non-empty/non-NULL string; + * - *ref_type_id* - referenced type ID, it might not exist yet; + * - *component_idx* - -1 for tagging reference type, otherwise struct/union + * member or function argument index; + * Set info->kflag to 1, indicating this tag is an __attribute__ + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_decl_attr(struct btf *btf, const char *value, int ref_type_id, + int component_idx) +{ + return btf_add_decl_tag(btf, value, ref_type_id, component_idx, 1); +} + struct btf_ext_sec_info_param { __u32 off; __u32 len; @@ -3015,8 +3066,6 @@ static int btf_ext_parse_info(struct btf_ext *btf_ext, bool is_native) .desc = "line_info", }; struct btf_ext_sec_info_param core_relo = { - .off = btf_ext->hdr->core_relo_off, - .len = btf_ext->hdr->core_relo_len, .min_rec_size = sizeof(struct bpf_core_relo), .ext_info = &btf_ext->core_relo_info, .desc = "core_relo", @@ -3034,6 +3083,8 @@ static int btf_ext_parse_info(struct btf_ext *btf_ext, bool is_native) if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) return 0; /* skip core relos parsing */ + core_relo.off = btf_ext->hdr->core_relo_off; + core_relo.len = btf_ext->hdr->core_relo_len; err = btf_ext_parse_sec_info(btf_ext, &core_relo, is_native); if (err) return err; diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 47ee8f6..4392451 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -227,6 +227,7 @@ LIBBPF_API int btf__add_volatile(struct btf *btf, int ref_type_id); LIBBPF_API int btf__add_const(struct btf *btf, int ref_type_id); LIBBPF_API int btf__add_restrict(struct btf *btf, int ref_type_id); LIBBPF_API int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id); +LIBBPF_API int btf__add_type_attr(struct btf *btf, const char *value, int ref_type_id); /* func and func_proto construction APIs */ LIBBPF_API int btf__add_func(struct btf *btf, const char *name, @@ -243,6 +244,8 @@ LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id, /* tag construction API */ LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, int component_idx); +LIBBPF_API int btf__add_decl_attr(struct btf *btf, const char *value, int ref_type_id, + int component_idx); struct btf_dedup_opts { size_t sz; diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index a3fc690..460c3e5 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -1494,7 +1494,10 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, case BTF_KIND_TYPE_TAG: btf_dump_emit_mods(d, decls); name = btf_name_of(d, t->name_off); - btf_dump_printf(d, " __attribute__((btf_type_tag(\"%s\")))", name); + if (btf_kflag(t)) + btf_dump_printf(d, " __attribute__((%s))", name); + else + btf_dump_printf(d, " __attribute__((btf_type_tag(\"%s\")))", name); break; case BTF_KIND_ARRAY: { const struct btf_array *a = btf_array(t); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 194809d..6b85060 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -670,11 +670,18 @@ struct elf_state { struct usdt_manager; +enum bpf_object_state { + OBJ_OPEN, + OBJ_PREPARED, + OBJ_LOADED, +}; + struct bpf_object { char name[BPF_OBJ_NAME_LEN]; char license[64]; __u32 kern_version; + enum bpf_object_state state; struct bpf_program *programs; size_t nr_programs; struct bpf_map *maps; @@ -686,7 +693,6 @@ struct bpf_object { int nr_extern; int kconfig_map_idx; - bool loaded; bool has_subcalls; bool has_rodata; @@ -1511,7 +1517,7 @@ static struct bpf_object *bpf_object__new(const char *path, obj->kconfig_map_idx = -1; obj->kern_version = get_kernel_version(); - obj->loaded = false; + obj->state = OBJ_OPEN; return obj; } @@ -2106,7 +2112,7 @@ static int set_kcfg_value_str(struct extern_desc *ext, char *ext_val, } len = strlen(value); - if (value[len - 1] != '"') { + if (len < 2 || value[len - 1] != '"') { pr_warn("extern (kcfg) '%s': invalid string config '%s'\n", ext->name, value); return -EINVAL; @@ -4845,6 +4851,11 @@ static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info) return 0; } +static bool map_is_created(const struct bpf_map *map) +{ + return map->obj->state >= OBJ_PREPARED || map->reused; +} + bool bpf_map__autocreate(const struct bpf_map *map) { return map->autocreate; @@ -4852,7 +4863,7 @@ bool bpf_map__autocreate(const struct bpf_map *map) int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate) { - if (map->obj->loaded) + if (map_is_created(map)) return libbpf_err(-EBUSY); map->autocreate = autocreate; @@ -4946,7 +4957,7 @@ struct bpf_map *bpf_map__inner_map(struct bpf_map *map) int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries) { - if (map->obj->loaded) + if (map_is_created(map)) return libbpf_err(-EBUSY); map->def.max_entries = max_entries; @@ -5191,11 +5202,6 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) static void bpf_map__destroy(struct bpf_map *map); -static bool map_is_created(const struct bpf_map *map) -{ - return map->obj->loaded || map->reused; -} - static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner) { LIBBPF_OPTS(bpf_map_create_opts, create_attr); @@ -7897,13 +7903,6 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; - err = bpf_object__sanitize_prog(obj, prog); - if (err) - return err; - } - - for (i = 0; i < obj->nr_programs; i++) { - prog = &obj->programs[i]; if (prog_is_subprog(obj, prog)) continue; if (!prog->autoload) { @@ -7927,6 +7926,21 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) return 0; } +static int bpf_object_prepare_progs(struct bpf_object *obj) +{ + struct bpf_program *prog; + size_t i; + int err; + + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + err = bpf_object__sanitize_prog(obj, prog); + if (err) + return err; + } + return 0; +} + static const struct bpf_sec_def *find_sec_def(const char *sec_name); static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object_open_opts *opts) @@ -8543,14 +8557,77 @@ static int bpf_object_prepare_struct_ops(struct bpf_object *obj) return 0; } +static void bpf_object_unpin(struct bpf_object *obj) +{ + int i; + + /* unpin any maps that were auto-pinned during load */ + for (i = 0; i < obj->nr_maps; i++) + if (obj->maps[i].pinned && !obj->maps[i].reused) + bpf_map__unpin(&obj->maps[i], NULL); +} + +static void bpf_object_post_load_cleanup(struct bpf_object *obj) +{ + int i; + + /* clean up fd_array */ + zfree(&obj->fd_array); + + /* clean up module BTFs */ + for (i = 0; i < obj->btf_module_cnt; i++) { + close(obj->btf_modules[i].fd); + btf__free(obj->btf_modules[i].btf); + free(obj->btf_modules[i].name); + } + obj->btf_module_cnt = 0; + zfree(&obj->btf_modules); + + /* clean up vmlinux BTF */ + btf__free(obj->btf_vmlinux); + obj->btf_vmlinux = NULL; +} + +static int bpf_object_prepare(struct bpf_object *obj, const char *target_btf_path) +{ + int err; + + if (obj->state >= OBJ_PREPARED) { + pr_warn("object '%s': prepare loading can't be attempted twice\n", obj->name); + return -EINVAL; + } + + err = bpf_object_prepare_token(obj); + err = err ? : bpf_object__probe_loading(obj); + err = err ? : bpf_object__load_vmlinux_btf(obj, false); + err = err ? : bpf_object__resolve_externs(obj, obj->kconfig); + err = err ? : bpf_object__sanitize_maps(obj); + err = err ? : bpf_object__init_kern_struct_ops_maps(obj); + err = err ? : bpf_object_adjust_struct_ops_autoload(obj); + err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : target_btf_path); + err = err ? : bpf_object__sanitize_and_load_btf(obj); + err = err ? : bpf_object__create_maps(obj); + err = err ? : bpf_object_prepare_progs(obj); + + if (err) { + bpf_object_unpin(obj); + bpf_object_unload(obj); + obj->state = OBJ_LOADED; + return err; + } + + obj->state = OBJ_PREPARED; + return 0; +} + static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const char *target_btf_path) { - int err, i; + int err; if (!obj) return libbpf_err(-EINVAL); - if (obj->loaded) { + if (obj->state >= OBJ_LOADED) { pr_warn("object '%s': load can't be attempted twice\n", obj->name); return libbpf_err(-EINVAL); } @@ -8565,17 +8642,12 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch return libbpf_err(-LIBBPF_ERRNO__ENDIAN); } - err = bpf_object_prepare_token(obj); - err = err ? : bpf_object__probe_loading(obj); - err = err ? : bpf_object__load_vmlinux_btf(obj, false); - err = err ? : bpf_object__resolve_externs(obj, obj->kconfig); - err = err ? : bpf_object__sanitize_maps(obj); - err = err ? : bpf_object__init_kern_struct_ops_maps(obj); - err = err ? : bpf_object_adjust_struct_ops_autoload(obj); - err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : target_btf_path); - err = err ? : bpf_object__sanitize_and_load_btf(obj); - err = err ? : bpf_object__create_maps(obj); - err = err ? : bpf_object__load_progs(obj, extra_log_level); + if (obj->state < OBJ_PREPARED) { + err = bpf_object_prepare(obj, target_btf_path); + if (err) + return libbpf_err(err); + } + err = bpf_object__load_progs(obj, extra_log_level); err = err ? : bpf_object_init_prog_arrays(obj); err = err ? : bpf_object_prepare_struct_ops(obj); @@ -8587,36 +8659,22 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps); } - /* clean up fd_array */ - zfree(&obj->fd_array); + bpf_object_post_load_cleanup(obj); + obj->state = OBJ_LOADED; /* doesn't matter if successfully or not */ - /* clean up module BTFs */ - for (i = 0; i < obj->btf_module_cnt; i++) { - close(obj->btf_modules[i].fd); - btf__free(obj->btf_modules[i].btf); - free(obj->btf_modules[i].name); + if (err) { + bpf_object_unpin(obj); + bpf_object_unload(obj); + pr_warn("failed to load object '%s'\n", obj->path); + return libbpf_err(err); } - free(obj->btf_modules); - - /* clean up vmlinux BTF */ - btf__free(obj->btf_vmlinux); - obj->btf_vmlinux = NULL; - - obj->loaded = true; /* doesn't matter if successfully or not */ - - if (err) - goto out; return 0; -out: - /* unpin any maps that were auto-pinned during load */ - for (i = 0; i < obj->nr_maps; i++) - if (obj->maps[i].pinned && !obj->maps[i].reused) - bpf_map__unpin(&obj->maps[i], NULL); +} - bpf_object_unload(obj); - pr_warn("failed to load object '%s'\n", obj->path); - return libbpf_err(err); +int bpf_object__prepare(struct bpf_object *obj) +{ + return libbpf_err(bpf_object_prepare(obj, NULL)); } int bpf_object__load(struct bpf_object *obj) @@ -8866,7 +8924,7 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path) if (!obj) return libbpf_err(-ENOENT); - if (!obj->loaded) { + if (obj->state < OBJ_PREPARED) { pr_warn("object not yet loaded; load it first\n"); return libbpf_err(-ENOENT); } @@ -8945,7 +9003,7 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path) if (!obj) return libbpf_err(-ENOENT); - if (!obj->loaded) { + if (obj->state < OBJ_LOADED) { pr_warn("object not yet loaded; load it first\n"); return libbpf_err(-ENOENT); } @@ -9064,6 +9122,13 @@ void bpf_object__close(struct bpf_object *obj) if (IS_ERR_OR_NULL(obj)) return; + /* + * if user called bpf_object__prepare() without ever getting to + * bpf_object__load(), we need to clean up stuff that is normally + * cleaned up at the end of loading step + */ + bpf_object_post_load_cleanup(obj); + usdt_manager_free(obj->usdt_man); obj->usdt_man = NULL; @@ -9132,7 +9197,7 @@ int bpf_object__btf_fd(const struct bpf_object *obj) int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version) { - if (obj->loaded) + if (obj->state >= OBJ_LOADED) return libbpf_err(-EINVAL); obj->kern_version = kern_version; @@ -9145,12 +9210,12 @@ int bpf_object__gen_loader(struct bpf_object *obj, struct gen_loader_opts *opts) struct bpf_gen *gen; if (!opts) - return -EFAULT; + return libbpf_err(-EFAULT); if (!OPTS_VALID(opts, gen_loader_opts)) - return -EINVAL; + return libbpf_err(-EINVAL); gen = calloc(sizeof(*gen), 1); if (!gen) - return -ENOMEM; + return libbpf_err(-ENOMEM); gen->opts = opts; gen->swapped_endian = !is_native_endianness(obj); obj->gen_loader = gen; @@ -9229,7 +9294,7 @@ bool bpf_program__autoload(const struct bpf_program *prog) int bpf_program__set_autoload(struct bpf_program *prog, bool autoload) { - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EINVAL); prog->autoload = autoload; @@ -9261,14 +9326,14 @@ int bpf_program__set_insns(struct bpf_program *prog, { struct bpf_insn *insns; - if (prog->obj->loaded) - return -EBUSY; + if (prog->obj->state >= OBJ_LOADED) + return libbpf_err(-EBUSY); insns = libbpf_reallocarray(prog->insns, new_insn_cnt, sizeof(*insns)); /* NULL is a valid return from reallocarray if the new count is zero */ if (!insns && new_insn_cnt) { pr_warn("prog '%s': failed to realloc prog code\n", prog->name); - return -ENOMEM; + return libbpf_err(-ENOMEM); } memcpy(insns, new_insns, new_insn_cnt * sizeof(*insns)); @@ -9304,7 +9369,7 @@ static int last_custom_sec_def_handler_id; int bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) { - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EBUSY); /* if type is not changed, do nothing */ @@ -9335,7 +9400,7 @@ enum bpf_attach_type bpf_program__expected_attach_type(const struct bpf_program int bpf_program__set_expected_attach_type(struct bpf_program *prog, enum bpf_attach_type type) { - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EBUSY); prog->expected_attach_type = type; @@ -9349,7 +9414,7 @@ __u32 bpf_program__flags(const struct bpf_program *prog) int bpf_program__set_flags(struct bpf_program *prog, __u32 flags) { - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EBUSY); prog->prog_flags = flags; @@ -9363,7 +9428,7 @@ __u32 bpf_program__log_level(const struct bpf_program *prog) int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_level) { - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EBUSY); prog->log_level = log_level; @@ -9379,11 +9444,11 @@ const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_siz int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size) { if (log_size && !log_buf) - return -EINVAL; + return libbpf_err(-EINVAL); if (prog->log_size > UINT_MAX) - return -EINVAL; - if (prog->obj->loaded) - return -EBUSY; + return libbpf_err(-EINVAL); + if (prog->obj->state >= OBJ_LOADED) + return libbpf_err(-EBUSY); prog->log_buf = log_buf; prog->log_size = log_size; @@ -9959,7 +10024,7 @@ int libbpf_find_vmlinux_btf_id(const char *name, return libbpf_err(err); } -static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) +static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd, int token_fd) { struct bpf_prog_info info; __u32 info_len = sizeof(info); @@ -9979,7 +10044,7 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) pr_warn("The target program doesn't have BTF\n"); goto out; } - btf = btf__load_from_kernel_by_id(info.btf_id); + btf = btf_load_from_kernel(info.btf_id, NULL, token_fd); err = libbpf_get_error(btf); if (err) { pr_warn("Failed to get BTF %d of the program: %s\n", info.btf_id, errstr(err)); @@ -10062,7 +10127,7 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attac pr_warn("prog '%s': attach program FD is not set\n", prog->name); return -EINVAL; } - err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd); + err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd, prog->obj->token_fd); if (err < 0) { pr_warn("prog '%s': failed to find BPF program (FD %d) BTF ID for '%s': %s\n", prog->name, attach_prog_fd, attach_name, errstr(err)); @@ -10299,7 +10364,7 @@ static int map_btf_datasec_resize(struct bpf_map *map, __u32 size) int bpf_map__set_value_size(struct bpf_map *map, __u32 size) { - if (map->obj->loaded || map->reused) + if (map_is_created(map)) return libbpf_err(-EBUSY); if (map->mmaped) { @@ -10307,7 +10372,7 @@ int bpf_map__set_value_size(struct bpf_map *map, __u32 size) int err; if (map->def.type != BPF_MAP_TYPE_ARRAY) - return -EOPNOTSUPP; + return libbpf_err(-EOPNOTSUPP); mmap_old_sz = bpf_map_mmap_sz(map); mmap_new_sz = array_map_mmap_sz(size, map->def.max_entries); @@ -10315,7 +10380,7 @@ int bpf_map__set_value_size(struct bpf_map *map, __u32 size) if (err) { pr_warn("map '%s': failed to resize memory-mapped region: %s\n", bpf_map__name(map), errstr(err)); - return err; + return libbpf_err(err); } err = map_btf_datasec_resize(map, size); if (err && err != -ENOENT) { @@ -10345,7 +10410,7 @@ int bpf_map__set_initial_value(struct bpf_map *map, { size_t actual_sz; - if (map->obj->loaded || map->reused) + if (map_is_created(map)) return libbpf_err(-EBUSY); if (!map->mmaped || map->libbpf_type == LIBBPF_MAP_KCONFIG) @@ -12858,7 +12923,7 @@ struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog, if (target_fd) { LIBBPF_OPTS(bpf_link_create_opts, target_opts); - btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd); + btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd, prog->obj->token_fd); if (btf_id < 0) return libbpf_err_ptr(btf_id); @@ -13070,17 +13135,17 @@ int bpf_link__update_map(struct bpf_link *link, const struct bpf_map *map) int err; if (!bpf_map__is_struct_ops(map)) - return -EINVAL; + return libbpf_err(-EINVAL); if (map->fd < 0) { pr_warn("map '%s': can't use BPF map without FD (was it created?)\n", map->name); - return -EINVAL; + return libbpf_err(-EINVAL); } st_ops_link = container_of(link, struct bpf_link_struct_ops, link); /* Ensure the type of a link is correct */ if (st_ops_link->map_fd < 0) - return -EINVAL; + return libbpf_err(-EINVAL); err = bpf_map_update_elem(map->fd, &zero, map->st_ops->kern_vdata, 0); /* It can be EBUSY if the map has been used to create or @@ -13666,7 +13731,7 @@ int bpf_program__set_attach_target(struct bpf_program *prog, if (!prog || attach_prog_fd < 0) return libbpf_err(-EINVAL); - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EINVAL); if (attach_prog_fd && !attach_func_name) { @@ -13679,7 +13744,7 @@ int bpf_program__set_attach_target(struct bpf_program *prog, if (attach_prog_fd) { btf_id = libbpf_find_prog_btf_id(attach_func_name, - attach_prog_fd); + attach_prog_fd, prog->obj->token_fd); if (btf_id < 0) return libbpf_err(btf_id); } else { diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 3020ee4..e060540 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -242,6 +242,19 @@ bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts); /** + * @brief **bpf_object__prepare()** prepares BPF object for loading: + * performs ELF processing, relocations, prepares final state of BPF program + * instructions (accessible with bpf_program__insns()), creates and + * (potentially) pins maps. Leaves BPF object in the state ready for program + * loading. + * @param obj Pointer to a valid BPF object instance returned by + * **bpf_object__open*()** API + * @return 0, on success; negative error code, otherwise, error code is + * stored in errno + */ +int bpf_object__prepare(struct bpf_object *obj); + +/** * @brief **bpf_object__load()** loads BPF object into kernel. * @param obj Pointer to a valid BPF object instance returned by * **bpf_object__open*()** APIs diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index a8b2936..d8b71f2 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -436,4 +436,7 @@ LIBBPF_1.6.0 { bpf_linker__add_buf; bpf_linker__add_fd; bpf_linker__new_fd; + bpf_object__prepare; + btf__add_decl_attr; + btf__add_type_attr; } LIBBPF_1.5.0; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index de498e2..76669c7 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -409,6 +409,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len, int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level, int token_fd); +struct btf *btf_load_from_kernel(__u32 id, struct btf *base_btf, int token_fd); struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf); void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index b52f71c..800e0ef 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -2163,7 +2163,7 @@ add_sym: obj->sym_map[src_sym_idx] = dst_sym_idx; - if (sym_type == STT_SECTION && dst_sym) { + if (sym_type == STT_SECTION && dst_sec) { dst_sec->sec_sym_idx = dst_sym_idx; dst_sym->st_value = 0; } diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c index 7632e9d..2b83c98 100644 --- a/tools/lib/bpf/relo_core.c +++ b/tools/lib/bpf/relo_core.c @@ -683,7 +683,7 @@ static int bpf_core_calc_field_relo(const char *prog_name, { const struct bpf_core_accessor *acc; const struct btf_type *t; - __u32 byte_off, byte_sz, bit_off, bit_sz, field_type_id; + __u32 byte_off, byte_sz, bit_off, bit_sz, field_type_id, elem_id; const struct btf_member *m; const struct btf_type *mt; bool bitfield; @@ -706,8 +706,14 @@ static int bpf_core_calc_field_relo(const char *prog_name, if (!acc->name) { if (relo->kind == BPF_CORE_FIELD_BYTE_OFFSET) { *val = spec->bit_offset / 8; - /* remember field size for load/store mem size */ - sz = btf__resolve_size(spec->btf, acc->type_id); + /* remember field size for load/store mem size; + * note, for arrays we care about individual element + * sizes, not the overall array size + */ + t = skip_mods_and_typedefs(spec->btf, acc->type_id, &elem_id); + while (btf_is_array(t)) + t = skip_mods_and_typedefs(spec->btf, btf_array(t)->type, &elem_id); + sz = btf__resolve_size(spec->btf, elem_id); if (sz < 0) return -EINVAL; *field_sz = sz; @@ -767,7 +773,17 @@ static int bpf_core_calc_field_relo(const char *prog_name, case BPF_CORE_FIELD_BYTE_OFFSET: *val = byte_off; if (!bitfield) { - *field_sz = byte_sz; + /* remember field size for load/store mem size; + * note, for arrays we care about individual element + * sizes, not the overall array size + */ + t = skip_mods_and_typedefs(spec->btf, field_type_id, &elem_id); + while (btf_is_array(t)) + t = skip_mods_and_typedefs(spec->btf, btf_array(t)->type, &elem_id); + sz = btf__resolve_size(spec->btf, elem_id); + if (sz < 0) + return -EINVAL; + *field_sz = sz; *type_id = field_type_id; } break; diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c index 8743049..9a54176 100644 --- a/tools/lib/bpf/str_error.c +++ b/tools/lib/bpf/str_error.c @@ -36,7 +36,7 @@ char *libbpf_strerror_r(int err, char *dst, int len) return dst; } -const char *errstr(int err) +const char *libbpf_errstr(int err) { static __thread char buf[12]; diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h index 66ffebd..53e7fbf 100644 --- a/tools/lib/bpf/str_error.h +++ b/tools/lib/bpf/str_error.h @@ -7,10 +7,13 @@ char *libbpf_strerror_r(int err, char *dst, int len); /** - * @brief **errstr()** returns string corresponding to numeric errno + * @brief **libbpf_errstr()** returns string corresponding to numeric errno * @param err negative numeric errno * @return pointer to string representation of the errno, that is invalidated * upon the next call. */ -const char *errstr(int err); +const char *libbpf_errstr(int err); + +#define errstr(err) libbpf_errstr(err) + #endif /* __LIBBPF_STR_ERROR_H */ diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h index b811f75..2a7865c 100644 --- a/tools/lib/bpf/usdt.bpf.h +++ b/tools/lib/bpf/usdt.bpf.h @@ -108,6 +108,38 @@ int bpf_usdt_arg_cnt(struct pt_regs *ctx) return spec->arg_cnt; } +/* Returns the size in bytes of the #*arg_num* (zero-indexed) USDT argument. + * Returns negative error if argument is not found or arg_num is invalid. + */ +static __always_inline +int bpf_usdt_arg_size(struct pt_regs *ctx, __u64 arg_num) +{ + struct __bpf_usdt_arg_spec *arg_spec; + struct __bpf_usdt_spec *spec; + int spec_id; + + spec_id = __bpf_usdt_spec_id(ctx); + if (spec_id < 0) + return -ESRCH; + + spec = bpf_map_lookup_elem(&__bpf_usdt_specs, &spec_id); + if (!spec) + return -ESRCH; + + if (arg_num >= BPF_USDT_MAX_ARG_CNT) + return -ENOENT; + barrier_var(arg_num); + if (arg_num >= spec->arg_cnt) + return -ENOENT; + + arg_spec = &spec->args[arg_num]; + + /* arg_spec->arg_bitshift = 64 - arg_sz * 8 + * so: arg_sz = (64 - arg_spec->arg_bitshift) / 8 + */ + return (unsigned int)(64 - arg_spec->arg_bitshift) / 8; +} + /* Fetch USDT argument #*arg_num* (zero-indexed) and put its value into *res. * Returns 0 on success; negative error, otherwise. * On error *res is guaranteed to be set to zero. diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64 index 901349d..6d8feda 100644 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ b/tools/testing/selftests/bpf/DENYLIST.aarch64 @@ -1,12 +1,3 @@ -bpf_cookie/multi_kprobe_attach_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3 -bpf_cookie/multi_kprobe_link_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3 -kprobe_multi_bench_attach # needs CONFIG_FPROBE -kprobe_multi_test # needs CONFIG_FPROBE -module_attach # prog 'kprobe_multi': failed to auto-attach: -95 fentry_test/fentry_many_args # fentry_many_args:FAIL:fentry_many_args_attach unexpected error: -524 fexit_test/fexit_many_args # fexit_many_args:FAIL:fexit_many_args_attach unexpected error: -524 tracing_struct/struct_many_args # struct_many_args:FAIL:tracing_struct_many_args__attach unexpected error: -524 -fill_link_info/kprobe_multi_link_info # bpf_program__attach_kprobe_multi_opts unexpected error: -95 -fill_link_info/kretprobe_multi_link_info # bpf_program__attach_kprobe_multi_opts unexpected error: -95 -fill_link_info/kprobe_multi_invalid_ubuff # bpf_program__attach_kprobe_multi_opts unexpected error: -95 -missed/kprobe_recursion # missed_kprobe_recursion__attach unexpected error: -95 (errno 95) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 8755162..66bb503 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -95,18 +95,12 @@ TEST_GEN_PROGS += test_progs-cpuv4 TEST_INST_SUBDIRS += cpuv4 endif -TEST_GEN_FILES = test_lwt_ip_encap.bpf.o test_tc_edt.bpf.o +TEST_GEN_FILES = test_tc_edt.bpf.o TEST_FILES = xsk_prereqs.sh $(wildcard progs/btf_dump_test_case_*.c) # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ - test_xdp_redirect_multi.sh \ - test_tunnel.sh \ - test_lwt_seg6local.sh \ test_lirc_mode2.sh \ - test_xdp_vlan_mode_generic.sh \ - test_xdp_vlan_mode_native.sh \ - test_lwt_ip_encap.sh \ test_tc_tunnel.sh \ test_tc_edt.sh \ test_xdping.sh \ @@ -117,9 +111,9 @@ TEST_PROGS := test_kmod.sh \ test_xsk.sh \ test_xdp_features.sh -TEST_PROGS_EXTENDED := with_addr.sh \ - with_tunnels.sh ima_setup.sh verify_sig_setup.sh \ - test_xdp_vlan.sh test_bpftool.py +TEST_PROGS_EXTENDED := \ + ima_setup.sh verify_sig_setup.sh \ + test_bpftool.py TEST_KMODS := bpf_testmod.ko bpf_test_no_cfi.ko bpf_test_modorder_x.ko \ bpf_test_modorder_y.ko @@ -135,7 +129,6 @@ TEST_GEN_PROGS_EXTENDED = \ veristat \ xdp_features \ xdp_hw_metadata \ - xdp_redirect_multi \ xdp_synproxy \ xdping \ xskxceiver @@ -184,9 +177,14 @@ ifeq ($(feature-llvm),1) LLVM_CONFIG_LIB_COMPONENTS := mcdisassembler all-targets # both llvm-config and lib.mk add -D_GNU_SOURCE, which ends up as conflict LLVM_CFLAGS += $(filter-out -D_GNU_SOURCE,$(shell $(LLVM_CONFIG) --cflags)) - LLVM_LDLIBS += $(shell $(LLVM_CONFIG) --link-static --libs $(LLVM_CONFIG_LIB_COMPONENTS)) - LLVM_LDLIBS += $(shell $(LLVM_CONFIG) --link-static --system-libs $(LLVM_CONFIG_LIB_COMPONENTS)) - LLVM_LDLIBS += -lstdc++ + # Prefer linking statically if it's available, otherwise fallback to shared + ifeq ($(shell $(LLVM_CONFIG) --link-static --libs >/dev/null 2>&1 && echo static),static) + LLVM_LDLIBS += $(shell $(LLVM_CONFIG) --link-static --libs $(LLVM_CONFIG_LIB_COMPONENTS)) + LLVM_LDLIBS += $(shell $(LLVM_CONFIG) --link-static --system-libs $(LLVM_CONFIG_LIB_COMPONENTS)) + LLVM_LDLIBS += -lstdc++ + else + LLVM_LDLIBS += $(shell $(LLVM_CONFIG) --link-shared --libs $(LLVM_CONFIG_LIB_COMPONENTS)) + endif LLVM_LDFLAGS += $(shell $(LLVM_CONFIG) --ldflags) endif @@ -306,6 +304,7 @@ $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT) BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf/ \ BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) \ + BPF_TARGET_ENDIAN=$(BPF_TARGET_ENDIAN) \ EXTRA_CFLAGS='-g $(OPT_FLAGS) $(SAN_CFLAGS) $(EXTRA_CFLAGS)' \ EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)' && \ cp $(RUNQSLOWER_OUTPUT)runqslower $@ @@ -684,6 +683,7 @@ $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ $(TRUNNER_EXTRA_OBJS) $$(BPFOBJ) \ $(RESOLVE_BTFIDS) \ $(TRUNNER_BPFTOOL) \ + $(OUTPUT)/veristat \ | $(TRUNNER_BINARY)-extras $$(call msg,BINARY,,$$@) $(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) $$(LDFLAGS) -o $$@ diff --git a/tools/testing/selftests/bpf/bpf_arena_spin_lock.h b/tools/testing/selftests/bpf/bpf_arena_spin_lock.h new file mode 100644 index 0000000..fb8dc07 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_arena_spin_lock.h @@ -0,0 +1,533 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#ifndef BPF_ARENA_SPIN_LOCK_H +#define BPF_ARENA_SPIN_LOCK_H + +#include +#include +#include "bpf_atomic.h" + +#define arch_mcs_spin_lock_contended_label(l, label) smp_cond_load_acquire_label(l, VAL, label) +#define arch_mcs_spin_unlock_contended(l) smp_store_release((l), 1) + +#if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST) + +#define EBUSY 16 +#define EOPNOTSUPP 95 +#define ETIMEDOUT 110 + +#ifndef __arena +#define __arena __attribute__((address_space(1))) +#endif + +extern unsigned long CONFIG_NR_CPUS __kconfig; + +/* + * Typically, we'd just rely on the definition in vmlinux.h for qspinlock, but + * PowerPC overrides the definition to define lock->val as u32 instead of + * atomic_t, leading to compilation errors. Import a local definition below so + * that we don't depend on the vmlinux.h version. + */ + +struct __qspinlock { + union { + atomic_t val; + struct { + u8 locked; + u8 pending; + }; + struct { + u16 locked_pending; + u16 tail; + }; + }; +}; + +#define arena_spinlock_t struct __qspinlock +/* FIXME: Using typedef causes CO-RE relocation error */ +/* typedef struct qspinlock arena_spinlock_t; */ + +struct arena_mcs_spinlock { + struct arena_mcs_spinlock __arena *next; + int locked; + int count; +}; + +struct arena_qnode { + struct arena_mcs_spinlock mcs; +}; + +#define _Q_MAX_NODES 4 +#define _Q_PENDING_LOOPS 1 + +/* + * Bitfields in the atomic value: + * + * 0- 7: locked byte + * 8: pending + * 9-15: not used + * 16-17: tail index + * 18-31: tail cpu (+1) + */ +#define _Q_MAX_CPUS 1024 + +#define _Q_SET_MASK(type) (((1U << _Q_ ## type ## _BITS) - 1)\ + << _Q_ ## type ## _OFFSET) +#define _Q_LOCKED_OFFSET 0 +#define _Q_LOCKED_BITS 8 +#define _Q_LOCKED_MASK _Q_SET_MASK(LOCKED) + +#define _Q_PENDING_OFFSET (_Q_LOCKED_OFFSET + _Q_LOCKED_BITS) +#define _Q_PENDING_BITS 8 +#define _Q_PENDING_MASK _Q_SET_MASK(PENDING) + +#define _Q_TAIL_IDX_OFFSET (_Q_PENDING_OFFSET + _Q_PENDING_BITS) +#define _Q_TAIL_IDX_BITS 2 +#define _Q_TAIL_IDX_MASK _Q_SET_MASK(TAIL_IDX) + +#define _Q_TAIL_CPU_OFFSET (_Q_TAIL_IDX_OFFSET + _Q_TAIL_IDX_BITS) +#define _Q_TAIL_CPU_BITS (32 - _Q_TAIL_CPU_OFFSET) +#define _Q_TAIL_CPU_MASK _Q_SET_MASK(TAIL_CPU) + +#define _Q_TAIL_OFFSET _Q_TAIL_IDX_OFFSET +#define _Q_TAIL_MASK (_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK) + +#define _Q_LOCKED_VAL (1U << _Q_LOCKED_OFFSET) +#define _Q_PENDING_VAL (1U << _Q_PENDING_OFFSET) + +#define likely(x) __builtin_expect(!!(x), 1) +#define unlikely(x) __builtin_expect(!!(x), 0) + +struct arena_qnode __arena qnodes[_Q_MAX_CPUS][_Q_MAX_NODES]; + +static inline u32 encode_tail(int cpu, int idx) +{ + u32 tail; + + tail = (cpu + 1) << _Q_TAIL_CPU_OFFSET; + tail |= idx << _Q_TAIL_IDX_OFFSET; /* assume < 4 */ + + return tail; +} + +static inline struct arena_mcs_spinlock __arena *decode_tail(u32 tail) +{ + u32 cpu = (tail >> _Q_TAIL_CPU_OFFSET) - 1; + u32 idx = (tail & _Q_TAIL_IDX_MASK) >> _Q_TAIL_IDX_OFFSET; + + return &qnodes[cpu][idx].mcs; +} + +static inline +struct arena_mcs_spinlock __arena *grab_mcs_node(struct arena_mcs_spinlock __arena *base, int idx) +{ + return &((struct arena_qnode __arena *)base + idx)->mcs; +} + +#define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK) + +/** + * xchg_tail - Put in the new queue tail code word & retrieve previous one + * @lock : Pointer to queued spinlock structure + * @tail : The new queue tail code word + * Return: The previous queue tail code word + * + * xchg(lock, tail) + * + * p,*,* -> n,*,* ; prev = xchg(lock, node) + */ +static __always_inline u32 xchg_tail(arena_spinlock_t __arena *lock, u32 tail) +{ + u32 old, new; + + old = atomic_read(&lock->val); + do { + new = (old & _Q_LOCKED_PENDING_MASK) | tail; + /* + * We can use relaxed semantics since the caller ensures that + * the MCS node is properly initialized before updating the + * tail. + */ + /* These loops are not expected to stall, but we still need to + * prove to the verifier they will terminate eventually. + */ + cond_break_label(out); + } while (!atomic_try_cmpxchg_relaxed(&lock->val, &old, new)); + + return old; +out: + bpf_printk("RUNTIME ERROR: %s unexpected cond_break exit!!!", __func__); + return old; +} + +/** + * clear_pending - clear the pending bit. + * @lock: Pointer to queued spinlock structure + * + * *,1,* -> *,0,* + */ +static __always_inline void clear_pending(arena_spinlock_t __arena *lock) +{ + WRITE_ONCE(lock->pending, 0); +} + +/** + * clear_pending_set_locked - take ownership and clear the pending bit. + * @lock: Pointer to queued spinlock structure + * + * *,1,0 -> *,0,1 + * + * Lock stealing is not allowed if this function is used. + */ +static __always_inline void clear_pending_set_locked(arena_spinlock_t __arena *lock) +{ + WRITE_ONCE(lock->locked_pending, _Q_LOCKED_VAL); +} + +/** + * set_locked - Set the lock bit and own the lock + * @lock: Pointer to queued spinlock structure + * + * *,*,0 -> *,0,1 + */ +static __always_inline void set_locked(arena_spinlock_t __arena *lock) +{ + WRITE_ONCE(lock->locked, _Q_LOCKED_VAL); +} + +static __always_inline +u32 arena_fetch_set_pending_acquire(arena_spinlock_t __arena *lock) +{ + u32 old, new; + + old = atomic_read(&lock->val); + do { + new = old | _Q_PENDING_VAL; + /* + * These loops are not expected to stall, but we still need to + * prove to the verifier they will terminate eventually. + */ + cond_break_label(out); + } while (!atomic_try_cmpxchg_acquire(&lock->val, &old, new)); + + return old; +out: + bpf_printk("RUNTIME ERROR: %s unexpected cond_break exit!!!", __func__); + return old; +} + +/** + * arena_spin_trylock - try to acquire the queued spinlock + * @lock : Pointer to queued spinlock structure + * Return: 1 if lock acquired, 0 if failed + */ +static __always_inline int arena_spin_trylock(arena_spinlock_t __arena *lock) +{ + int val = atomic_read(&lock->val); + + if (unlikely(val)) + return 0; + + return likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)); +} + +__noinline +int arena_spin_lock_slowpath(arena_spinlock_t __arena __arg_arena *lock, u32 val) +{ + struct arena_mcs_spinlock __arena *prev, *next, *node0, *node; + int ret = -ETIMEDOUT; + u32 old, tail; + int idx; + + /* + * Wait for in-progress pending->locked hand-overs with a bounded + * number of spins so that we guarantee forward progress. + * + * 0,1,0 -> 0,0,1 + */ + if (val == _Q_PENDING_VAL) { + int cnt = _Q_PENDING_LOOPS; + val = atomic_cond_read_relaxed_label(&lock->val, + (VAL != _Q_PENDING_VAL) || !cnt--, + release_err); + } + + /* + * If we observe any contention; queue. + */ + if (val & ~_Q_LOCKED_MASK) + goto queue; + + /* + * trylock || pending + * + * 0,0,* -> 0,1,* -> 0,0,1 pending, trylock + */ + val = arena_fetch_set_pending_acquire(lock); + + /* + * If we observe contention, there is a concurrent locker. + * + * Undo and queue; our setting of PENDING might have made the + * n,0,0 -> 0,0,0 transition fail and it will now be waiting + * on @next to become !NULL. + */ + if (unlikely(val & ~_Q_LOCKED_MASK)) { + + /* Undo PENDING if we set it. */ + if (!(val & _Q_PENDING_MASK)) + clear_pending(lock); + + goto queue; + } + + /* + * We're pending, wait for the owner to go away. + * + * 0,1,1 -> *,1,0 + * + * this wait loop must be a load-acquire such that we match the + * store-release that clears the locked bit and create lock + * sequentiality; this is because not all + * clear_pending_set_locked() implementations imply full + * barriers. + */ + if (val & _Q_LOCKED_MASK) + smp_cond_load_acquire_label(&lock->locked, !VAL, release_err); + + /* + * take ownership and clear the pending bit. + * + * 0,1,0 -> 0,0,1 + */ + clear_pending_set_locked(lock); + return 0; + + /* + * End of pending bit optimistic spinning and beginning of MCS + * queuing. + */ +queue: + node0 = &(qnodes[bpf_get_smp_processor_id()])[0].mcs; + idx = node0->count++; + tail = encode_tail(bpf_get_smp_processor_id(), idx); + + /* + * 4 nodes are allocated based on the assumption that there will not be + * nested NMIs taking spinlocks. That may not be true in some + * architectures even though the chance of needing more than 4 nodes + * will still be extremely unlikely. When that happens, we simply return + * an error. Original qspinlock has a trylock fallback in this case. + */ + if (unlikely(idx >= _Q_MAX_NODES)) { + ret = -EBUSY; + goto release_node_err; + } + + node = grab_mcs_node(node0, idx); + + /* + * Ensure that we increment the head node->count before initialising + * the actual node. If the compiler is kind enough to reorder these + * stores, then an IRQ could overwrite our assignments. + */ + barrier(); + + node->locked = 0; + node->next = NULL; + + /* + * We touched a (possibly) cold cacheline in the per-cpu queue node; + * attempt the trylock once more in the hope someone let go while we + * weren't watching. + */ + if (arena_spin_trylock(lock)) + goto release; + + /* + * Ensure that the initialisation of @node is complete before we + * publish the updated tail via xchg_tail() and potentially link + * @node into the waitqueue via WRITE_ONCE(prev->next, node) below. + */ + smp_wmb(); + + /* + * Publish the updated tail. + * We have already touched the queueing cacheline; don't bother with + * pending stuff. + * + * p,*,* -> n,*,* + */ + old = xchg_tail(lock, tail); + next = NULL; + + /* + * if there was a previous node; link it and wait until reaching the + * head of the waitqueue. + */ + if (old & _Q_TAIL_MASK) { + prev = decode_tail(old); + + /* Link @node into the waitqueue. */ + WRITE_ONCE(prev->next, node); + + arch_mcs_spin_lock_contended_label(&node->locked, release_node_err); + + /* + * While waiting for the MCS lock, the next pointer may have + * been set by another lock waiter. We cannot prefetch here + * due to lack of equivalent instruction in BPF ISA. + */ + next = READ_ONCE(node->next); + } + + /* + * we're at the head of the waitqueue, wait for the owner & pending to + * go away. + * + * *,x,y -> *,0,0 + * + * this wait loop must use a load-acquire such that we match the + * store-release that clears the locked bit and create lock + * sequentiality; this is because the set_locked() function below + * does not imply a full barrier. + */ + val = atomic_cond_read_acquire_label(&lock->val, !(VAL & _Q_LOCKED_PENDING_MASK), + release_node_err); + + /* + * claim the lock: + * + * n,0,0 -> 0,0,1 : lock, uncontended + * *,*,0 -> *,*,1 : lock, contended + * + * If the queue head is the only one in the queue (lock value == tail) + * and nobody is pending, clear the tail code and grab the lock. + * Otherwise, we only need to grab the lock. + */ + + /* + * In the PV case we might already have _Q_LOCKED_VAL set, because + * of lock stealing; therefore we must also allow: + * + * n,0,1 -> 0,0,1 + * + * Note: at this point: (val & _Q_PENDING_MASK) == 0, because of the + * above wait condition, therefore any concurrent setting of + * PENDING will make the uncontended transition fail. + */ + if ((val & _Q_TAIL_MASK) == tail) { + if (atomic_try_cmpxchg_relaxed(&lock->val, &val, _Q_LOCKED_VAL)) + goto release; /* No contention */ + } + + /* + * Either somebody is queued behind us or _Q_PENDING_VAL got set + * which will then detect the remaining tail and queue behind us + * ensuring we'll see a @next. + */ + set_locked(lock); + + /* + * contended path; wait for next if not observed yet, release. + */ + if (!next) + next = smp_cond_load_relaxed_label(&node->next, (VAL), release_node_err); + + arch_mcs_spin_unlock_contended(&next->locked); + +release:; + /* + * release the node + * + * Doing a normal dec vs this_cpu_dec is fine. An upper context always + * decrements count it incremented before returning, thus we're fine. + * For contexts interrupting us, they either observe our dec or not. + * Just ensure the compiler doesn't reorder this statement, as a + * this_cpu_dec implicitly implied that. + */ + barrier(); + node0->count--; + return 0; +release_node_err: + barrier(); + node0->count--; + goto release_err; +release_err: + return ret; +} + +/** + * arena_spin_lock - acquire a queued spinlock + * @lock: Pointer to queued spinlock structure + * + * On error, returned value will be negative. + * On success, zero is returned. + * + * The return value _must_ be tested against zero for success, + * instead of checking it against negative, for passing the + * BPF verifier. + * + * The user should do: + * if (arena_spin_lock(...) != 0) // failure + * or + * if (arena_spin_lock(...) == 0) // success + * or + * if (arena_spin_lock(...)) // failure + * or + * if (!arena_spin_lock(...)) // success + * instead of: + * if (arena_spin_lock(...) < 0) // failure + * + * The return value can still be inspected later. + */ +static __always_inline int arena_spin_lock(arena_spinlock_t __arena *lock) +{ + int val = 0; + + if (CONFIG_NR_CPUS > 1024) + return -EOPNOTSUPP; + + bpf_preempt_disable(); + if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL))) + return 0; + + val = arena_spin_lock_slowpath(lock, val); + /* FIXME: bpf_assert_range(-MAX_ERRNO, 0) once we have it working for all cases. */ + if (val) + bpf_preempt_enable(); + return val; +} + +/** + * arena_spin_unlock - release a queued spinlock + * @lock : Pointer to queued spinlock structure + */ +static __always_inline void arena_spin_unlock(arena_spinlock_t __arena *lock) +{ + /* + * unlock() needs release semantics: + */ + smp_store_release(&lock->locked, 0); + bpf_preempt_enable(); +} + +#define arena_spin_lock_irqsave(lock, flags) \ + ({ \ + int __ret; \ + bpf_local_irq_save(&(flags)); \ + __ret = arena_spin_lock((lock)); \ + if (__ret) \ + bpf_local_irq_restore(&(flags)); \ + (__ret); \ + }) + +#define arena_spin_unlock_irqrestore(lock, flags) \ + ({ \ + arena_spin_unlock((lock)); \ + bpf_local_irq_restore(&(flags)); \ + }) + +#endif + +#endif /* BPF_ARENA_SPIN_LOCK_H */ diff --git a/tools/testing/selftests/bpf/bpf_atomic.h b/tools/testing/selftests/bpf/bpf_atomic.h new file mode 100644 index 0000000..a9674e5 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_atomic.h @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#ifndef BPF_ATOMIC_H +#define BPF_ATOMIC_H + +#include +#include +#include "bpf_experimental.h" + +extern bool CONFIG_X86_64 __kconfig __weak; + +/* + * __unqual_typeof(x) - Declare an unqualified scalar type, leaving + * non-scalar types unchanged, + * + * Prefer C11 _Generic for better compile-times and simpler code. Note: 'char' + * is not type-compatible with 'signed char', and we define a separate case. + * + * This is copied verbatim from kernel's include/linux/compiler_types.h, but + * with default expression (for pointers) changed from (x) to (typeof(x)0). + * + * This is because LLVM has a bug where for lvalue (x), it does not get rid of + * an extra address_space qualifier, but does in case of rvalue (typeof(x)0). + * Hence, for pointers, we need to create an rvalue expression to get the + * desired type. See https://github.com/llvm/llvm-project/issues/53400. + */ +#define __scalar_type_to_expr_cases(type) \ + unsigned type : (unsigned type)0, signed type : (signed type)0 + +#define __unqual_typeof(x) \ + typeof(_Generic((x), \ + char: (char)0, \ + __scalar_type_to_expr_cases(char), \ + __scalar_type_to_expr_cases(short), \ + __scalar_type_to_expr_cases(int), \ + __scalar_type_to_expr_cases(long), \ + __scalar_type_to_expr_cases(long long), \ + default: (typeof(x))0)) + +/* No-op for BPF */ +#define cpu_relax() ({}) + +#define READ_ONCE(x) (*(volatile typeof(x) *)&(x)) + +#define WRITE_ONCE(x, val) ((*(volatile typeof(x) *)&(x)) = (val)) + +#define cmpxchg(p, old, new) __sync_val_compare_and_swap((p), old, new) + +#define try_cmpxchg(p, pold, new) \ + ({ \ + __unqual_typeof(*(pold)) __o = *(pold); \ + __unqual_typeof(*(p)) __r = cmpxchg(p, __o, new); \ + if (__r != __o) \ + *(pold) = __r; \ + __r == __o; \ + }) + +#define try_cmpxchg_relaxed(p, pold, new) try_cmpxchg(p, pold, new) + +#define try_cmpxchg_acquire(p, pold, new) try_cmpxchg(p, pold, new) + +#define smp_mb() \ + ({ \ + unsigned long __val; \ + __sync_fetch_and_add(&__val, 0); \ + }) + +#define smp_rmb() \ + ({ \ + if (!CONFIG_X86_64) \ + smp_mb(); \ + else \ + barrier(); \ + }) + +#define smp_wmb() \ + ({ \ + if (!CONFIG_X86_64) \ + smp_mb(); \ + else \ + barrier(); \ + }) + +/* Control dependency provides LOAD->STORE, provide LOAD->LOAD */ +#define smp_acquire__after_ctrl_dep() ({ smp_rmb(); }) + +#define smp_load_acquire(p) \ + ({ \ + __unqual_typeof(*(p)) __v = READ_ONCE(*(p)); \ + if (!CONFIG_X86_64) \ + smp_mb(); \ + barrier(); \ + __v; \ + }) + +#define smp_store_release(p, val) \ + ({ \ + if (!CONFIG_X86_64) \ + smp_mb(); \ + barrier(); \ + WRITE_ONCE(*(p), val); \ + }) + +#define smp_cond_load_relaxed_label(p, cond_expr, label) \ + ({ \ + typeof(p) __ptr = (p); \ + __unqual_typeof(*(p)) VAL; \ + for (;;) { \ + VAL = (__unqual_typeof(*(p)))READ_ONCE(*__ptr); \ + if (cond_expr) \ + break; \ + cond_break_label(label); \ + cpu_relax(); \ + } \ + (typeof(*(p)))VAL; \ + }) + +#define smp_cond_load_acquire_label(p, cond_expr, label) \ + ({ \ + __unqual_typeof(*p) __val = \ + smp_cond_load_relaxed_label(p, cond_expr, label); \ + smp_acquire__after_ctrl_dep(); \ + (typeof(*(p)))__val; \ + }) + +#define atomic_read(p) READ_ONCE((p)->counter) + +#define atomic_cond_read_relaxed_label(p, cond_expr, label) \ + smp_cond_load_relaxed_label(&(p)->counter, cond_expr, label) + +#define atomic_cond_read_acquire_label(p, cond_expr, label) \ + smp_cond_load_acquire_label(&(p)->counter, cond_expr, label) + +#define atomic_try_cmpxchg_relaxed(p, pold, new) \ + try_cmpxchg_relaxed(&(p)->counter, pold, new) + +#define atomic_try_cmpxchg_acquire(p, pold, new) \ + try_cmpxchg_acquire(&(p)->counter, pold, new) + +#endif /* BPF_ATOMIC_H */ diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h index cd8ecd3..6535c8a 100644 --- a/tools/testing/selftests/bpf/bpf_experimental.h +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -368,12 +368,12 @@ l_true: \ ret; \ }) -#define cond_break \ +#define __cond_break(expr) \ ({ __label__ l_break, l_continue; \ asm volatile goto("may_goto %l[l_break]" \ :::: l_break); \ goto l_continue; \ - l_break: break; \ + l_break: expr; \ l_continue:; \ }) #else @@ -392,7 +392,7 @@ l_true: \ ret; \ }) -#define cond_break \ +#define __cond_break(expr) \ ({ __label__ l_break, l_continue; \ asm volatile goto("1:.byte 0xe5; \ .byte 0; \ @@ -400,7 +400,7 @@ l_true: \ .short 0" \ :::: l_break); \ goto l_continue; \ - l_break: break; \ + l_break: expr; \ l_continue:; \ }) #else @@ -418,7 +418,7 @@ l_true: \ ret; \ }) -#define cond_break \ +#define __cond_break(expr) \ ({ __label__ l_break, l_continue; \ asm volatile goto("1:.byte 0xe5; \ .byte 0; \ @@ -426,12 +426,15 @@ l_true: \ .short 0" \ :::: l_break); \ goto l_continue; \ - l_break: break; \ + l_break: expr; \ l_continue:; \ }) #endif #endif +#define cond_break __cond_break(break) +#define cond_break_label(label) __cond_break(goto label) + #ifndef bpf_nop_mov #define bpf_nop_mov(var) \ asm volatile("%[reg]=%[reg]"::[reg]"r"((short)var)) diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h index 2eb3483..8215c9b 100644 --- a/tools/testing/selftests/bpf/bpf_kfuncs.h +++ b/tools/testing/selftests/bpf/bpf_kfuncs.h @@ -87,4 +87,9 @@ struct dentry; */ extern int bpf_get_dentry_xattr(struct dentry *dentry, const char *name, struct bpf_dynptr *value_ptr) __ksym __weak; + +extern int bpf_set_dentry_xattr(struct dentry *dentry, const char *name__str, + const struct bpf_dynptr *value_p, int flags) __ksym __weak; +extern int bpf_remove_dentry_xattr(struct dentry *dentry, const char *name__str) __ksym __weak; + #endif diff --git a/tools/testing/selftests/bpf/cap_helpers.c b/tools/testing/selftests/bpf/cap_helpers.c index d5ac507..98f840c 100644 --- a/tools/testing/selftests/bpf/cap_helpers.c +++ b/tools/testing/selftests/bpf/cap_helpers.c @@ -19,7 +19,7 @@ int cap_enable_effective(__u64 caps, __u64 *old_caps) err = capget(&hdr, data); if (err) - return err; + return -errno; if (old_caps) *old_caps = (__u64)(data[1].effective) << 32 | data[0].effective; @@ -32,7 +32,7 @@ int cap_enable_effective(__u64 caps, __u64 *old_caps) data[1].effective |= cap1; err = capset(&hdr, data); if (err) - return err; + return -errno; return 0; } @@ -49,7 +49,7 @@ int cap_disable_effective(__u64 caps, __u64 *old_caps) err = capget(&hdr, data); if (err) - return err; + return -errno; if (old_caps) *old_caps = (__u64)(data[1].effective) << 32 | data[0].effective; @@ -61,7 +61,7 @@ int cap_disable_effective(__u64 caps, __u64 *old_caps) data[1].effective &= ~cap1; err = capset(&hdr, data); if (err) - return err; + return -errno; return 0; } diff --git a/tools/testing/selftests/bpf/cap_helpers.h b/tools/testing/selftests/bpf/cap_helpers.h index 6d16353..8dcb285 100644 --- a/tools/testing/selftests/bpf/cap_helpers.h +++ b/tools/testing/selftests/bpf/cap_helpers.h @@ -4,6 +4,7 @@ #include #include +#include #ifndef CAP_PERFMON #define CAP_PERFMON 38 diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 29541d4..72b5c17 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -446,6 +446,23 @@ char *ping_command(int family) return "ping"; } +int append_tid(char *str, size_t sz) +{ + size_t end; + + if (!str) + return -1; + + end = strlen(str); + if (end + 8 > sz) + return -1; + + sprintf(&str[end], "%07d", gettid()); + str[end + 7] = '\0'; + + return 0; +} + int remove_netns(const char *name) { char *cmd; @@ -761,6 +778,36 @@ struct tmonitor_ctx { int pcap_fd; }; +static int __base_pr(const char *format, va_list args) +{ + return vfprintf(stdout, format, args); +} + +static tm_print_fn_t __tm_pr = __base_pr; + +tm_print_fn_t traffic_monitor_set_print(tm_print_fn_t fn) +{ + tm_print_fn_t old_print_fn; + + old_print_fn = __atomic_exchange_n(&__tm_pr, fn, __ATOMIC_RELAXED); + + return old_print_fn; +} + +void tm_print(const char *format, ...) +{ + tm_print_fn_t print_fn; + va_list args; + + print_fn = __atomic_load_n(&__tm_pr, __ATOMIC_RELAXED); + if (!print_fn) + return; + + va_start(args, format); + print_fn(format, args); + va_end(args); +} + /* Is this packet captured with a Ethernet protocol type? */ static bool is_ethernet(const u_char *packet) { @@ -778,7 +825,7 @@ static bool is_ethernet(const u_char *packet) case 770: /* ARPHRD_FRAD */ case 778: /* ARPHDR_IPGRE */ case 803: /* ARPHRD_IEEE80211_RADIOTAP */ - printf("Packet captured: arphdr_type=%d\n", arphdr_type); + tm_print("Packet captured: arphdr_type=%d\n", arphdr_type); return false; } return true; @@ -799,12 +846,13 @@ static const char *pkt_type_str(u16 pkt_type) return "Unknown"; } +#define MAX_FLAGS_STRLEN 21 /* Show the information of the transport layer in the packet */ static void show_transport(const u_char *packet, u16 len, u32 ifindex, const char *src_addr, const char *dst_addr, u16 proto, bool ipv6, u8 pkt_type) { - char *ifname, _ifname[IF_NAMESIZE]; + char *ifname, _ifname[IF_NAMESIZE], flags[MAX_FLAGS_STRLEN] = ""; const char *transport_str; u16 src_port, dst_port; struct udphdr *udp; @@ -827,47 +875,39 @@ static void show_transport(const u_char *packet, u16 len, u32 ifindex, dst_port = ntohs(tcp->dest); transport_str = "TCP"; } else if (proto == IPPROTO_ICMP) { - printf("%-7s %-3s IPv4 %s > %s: ICMP, length %d, type %d, code %d\n", - ifname, pkt_type_str(pkt_type), src_addr, dst_addr, len, - packet[0], packet[1]); + tm_print("%-7s %-3s IPv4 %s > %s: ICMP, length %d, type %d, code %d\n", + ifname, pkt_type_str(pkt_type), src_addr, dst_addr, len, + packet[0], packet[1]); return; } else if (proto == IPPROTO_ICMPV6) { - printf("%-7s %-3s IPv6 %s > %s: ICMPv6, length %d, type %d, code %d\n", - ifname, pkt_type_str(pkt_type), src_addr, dst_addr, len, - packet[0], packet[1]); + tm_print("%-7s %-3s IPv6 %s > %s: ICMPv6, length %d, type %d, code %d\n", + ifname, pkt_type_str(pkt_type), src_addr, dst_addr, len, + packet[0], packet[1]); return; } else { - printf("%-7s %-3s %s %s > %s: protocol %d\n", - ifname, pkt_type_str(pkt_type), ipv6 ? "IPv6" : "IPv4", - src_addr, dst_addr, proto); + tm_print("%-7s %-3s %s %s > %s: protocol %d\n", + ifname, pkt_type_str(pkt_type), ipv6 ? "IPv6" : "IPv4", + src_addr, dst_addr, proto); return; } /* TCP or UDP*/ - flockfile(stdout); + if (proto == IPPROTO_TCP) + snprintf(flags, MAX_FLAGS_STRLEN, "%s%s%s%s", + tcp->fin ? ", FIN" : "", + tcp->syn ? ", SYN" : "", + tcp->rst ? ", RST" : "", + tcp->ack ? ", ACK" : ""); + if (ipv6) - printf("%-7s %-3s IPv6 %s.%d > %s.%d: %s, length %d", - ifname, pkt_type_str(pkt_type), src_addr, src_port, - dst_addr, dst_port, transport_str, len); + tm_print("%-7s %-3s IPv6 %s.%d > %s.%d: %s, length %d%s\n", + ifname, pkt_type_str(pkt_type), src_addr, src_port, + dst_addr, dst_port, transport_str, len, flags); else - printf("%-7s %-3s IPv4 %s:%d > %s:%d: %s, length %d", - ifname, pkt_type_str(pkt_type), src_addr, src_port, - dst_addr, dst_port, transport_str, len); - - if (proto == IPPROTO_TCP) { - if (tcp->fin) - printf(", FIN"); - if (tcp->syn) - printf(", SYN"); - if (tcp->rst) - printf(", RST"); - if (tcp->ack) - printf(", ACK"); - } - - printf("\n"); - funlockfile(stdout); + tm_print("%-7s %-3s IPv4 %s:%d > %s:%d: %s, length %d%s\n", + ifname, pkt_type_str(pkt_type), src_addr, src_port, + dst_addr, dst_port, transport_str, len, flags); } static void show_ipv6_packet(const u_char *packet, u32 ifindex, u8 pkt_type) @@ -982,8 +1022,8 @@ static void *traffic_monitor_thread(void *arg) ifname = _ifname; } - printf("%-7s %-3s Unknown network protocol type 0x%x\n", - ifname, pkt_type_str(ptype), proto); + tm_print("%-7s %-3s Unknown network protocol type 0x%x\n", + ifname, pkt_type_str(ptype), proto); } } @@ -1183,8 +1223,9 @@ void traffic_monitor_stop(struct tmonitor_ctx *ctx) write(ctx->wake_fd, &w, sizeof(w)); pthread_join(ctx->thread, NULL); - printf("Packet file: %s\n", strrchr(ctx->pkt_fname, '/') + 1); + tm_print("Packet file: %s\n", strrchr(ctx->pkt_fname, '/') + 1); traffic_monitor_release(ctx); } + #endif /* TRAFFIC_MONITOR */ diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index 9235976..ef208ee 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -18,6 +18,7 @@ typedef __u16 __sum16; #include #include #include +#include #define MAGIC_VAL 0x1234 #define NUM_ITER 100000 @@ -101,6 +102,18 @@ int send_recv_data(int lfd, int fd, uint32_t total_bytes); int make_netns(const char *name); int remove_netns(const char *name); +/** + * append_tid() - Append thread ID to the given string. + * + * @str: string to extend + * @sz: string's size + * + * 8 characters are used to append the thread ID (7 digits + '\0') + * + * Returns -1 on errors, 0 otherwise + */ +int append_tid(char *str, size_t sz); + static __u16 csum_fold(__u32 csum) { csum = (csum & 0xffff) + (csum >> 16); @@ -240,10 +253,13 @@ static inline __sum16 build_udp_v6_csum(const struct ipv6hdr *ip6h, struct tmonitor_ctx; +typedef int (*tm_print_fn_t)(const char *format, va_list args); + #ifdef TRAFFIC_MONITOR struct tmonitor_ctx *traffic_monitor_start(const char *netns, const char *test_name, const char *subtest_name); void traffic_monitor_stop(struct tmonitor_ctx *ctx); +tm_print_fn_t traffic_monitor_set_print(tm_print_fn_t fn); #else static inline struct tmonitor_ctx *traffic_monitor_start(const char *netns, const char *test_name, const char *subtest_name) @@ -254,6 +270,11 @@ static inline struct tmonitor_ctx *traffic_monitor_start(const char *netns, cons static inline void traffic_monitor_stop(struct tmonitor_ctx *ctx) { } + +static inline tm_print_fn_t traffic_monitor_set_print(tm_print_fn_t fn) +{ + return NULL; +} #endif #endif diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c index 4ebd0da..1d53a85 100644 --- a/tools/testing/selftests/bpf/prog_tests/align.c +++ b/tools/testing/selftests/bpf/prog_tests/align.c @@ -610,9 +610,11 @@ static int do_test_single(struct bpf_align_test *test) .log_size = sizeof(bpf_vlog), .log_level = 2, ); + const char *main_pass_start = "0: R1=ctx() R10=fp0"; const char *line_ptr; int cur_line = -1; int prog_len, i; + char *start; int fd_prog; int ret; @@ -632,7 +634,13 @@ static int do_test_single(struct bpf_align_test *test) ret = 0; /* We make a local copy so that we can strtok() it */ strncpy(bpf_vlog_copy, bpf_vlog, sizeof(bpf_vlog_copy)); - line_ptr = strtok(bpf_vlog_copy, "\n"); + start = strstr(bpf_vlog_copy, main_pass_start); + if (!start) { + ret = 1; + printf("Can't find initial line '%s'\n", main_pass_start); + goto out; + } + line_ptr = strtok(start, "\n"); for (i = 0; i < MAX_MATCHES; i++) { struct bpf_reg_match m = test->matches[i]; const char *p; @@ -682,6 +690,7 @@ static int do_test_single(struct bpf_align_test *test) break; } } +out: if (fd_prog >= 0) close(fd_prog); } diff --git a/tools/testing/selftests/bpf/prog_tests/arena_atomics.c b/tools/testing/selftests/bpf/prog_tests/arena_atomics.c index 26e7c06..d98577a 100644 --- a/tools/testing/selftests/bpf/prog_tests/arena_atomics.c +++ b/tools/testing/selftests/bpf/prog_tests/arena_atomics.c @@ -162,6 +162,66 @@ static void test_uaf(struct arena_atomics *skel) ASSERT_EQ(skel->arena->uaf_recovery_fails, 0, "uaf_recovery_fails"); } +static void test_load_acquire(struct arena_atomics *skel) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts); + int err, prog_fd; + + if (skel->data->skip_lacq_srel_tests) { + printf("%s:SKIP: ENABLE_ATOMICS_TESTS not defined, Clang doesn't support addr_space_cast, and/or JIT doesn't support load-acquire\n", + __func__); + test__skip(); + return; + } + + /* No need to attach it, just run it directly */ + prog_fd = bpf_program__fd(skel->progs.load_acquire); + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; + + ASSERT_EQ(skel->arena->load_acquire8_result, 0x12, + "load_acquire8_result"); + ASSERT_EQ(skel->arena->load_acquire16_result, 0x1234, + "load_acquire16_result"); + ASSERT_EQ(skel->arena->load_acquire32_result, 0x12345678, + "load_acquire32_result"); + ASSERT_EQ(skel->arena->load_acquire64_result, 0x1234567890abcdef, + "load_acquire64_result"); +} + +static void test_store_release(struct arena_atomics *skel) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts); + int err, prog_fd; + + if (skel->data->skip_lacq_srel_tests) { + printf("%s:SKIP: ENABLE_ATOMICS_TESTS not defined, Clang doesn't support addr_space_cast, and/or JIT doesn't support store-release\n", + __func__); + test__skip(); + return; + } + + /* No need to attach it, just run it directly */ + prog_fd = bpf_program__fd(skel->progs.store_release); + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; + + ASSERT_EQ(skel->arena->store_release8_result, 0x12, + "store_release8_result"); + ASSERT_EQ(skel->arena->store_release16_result, 0x1234, + "store_release16_result"); + ASSERT_EQ(skel->arena->store_release32_result, 0x12345678, + "store_release32_result"); + ASSERT_EQ(skel->arena->store_release64_result, 0x1234567890abcdef, + "store_release64_result"); +} + void test_arena_atomics(void) { struct arena_atomics *skel; @@ -171,7 +231,7 @@ void test_arena_atomics(void) if (!ASSERT_OK_PTR(skel, "arena atomics skeleton open")) return; - if (skel->data->skip_tests) { + if (skel->data->skip_all_tests) { printf("%s:SKIP:no ENABLE_ATOMICS_TESTS or no addr_space_cast support in clang", __func__); test__skip(); @@ -198,6 +258,10 @@ void test_arena_atomics(void) test_xchg(skel); if (test__start_subtest("uaf")) test_uaf(skel); + if (test__start_subtest("load_acquire")) + test_load_acquire(skel); + if (test__start_subtest("store_release")) + test_store_release(skel); cleanup: arena_atomics__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c b/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c new file mode 100644 index 0000000..7565fc7 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include +#include +#include + +struct __qspinlock { int val; }; +typedef struct __qspinlock arena_spinlock_t; + +struct arena_qnode { + unsigned long next; + int count; + int locked; +}; + +#include "arena_spin_lock.skel.h" + +static long cpu; +static int repeat; + +pthread_barrier_t barrier; + +static void *spin_lock_thread(void *arg) +{ + int err, prog_fd = *(u32 *)arg; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = repeat, + ); + cpu_set_t cpuset; + + CPU_ZERO(&cpuset); + CPU_SET(__sync_fetch_and_add(&cpu, 1), &cpuset); + ASSERT_OK(pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset), "cpu affinity"); + + err = pthread_barrier_wait(&barrier); + if (err != PTHREAD_BARRIER_SERIAL_THREAD && err != 0) + ASSERT_FALSE(true, "pthread_barrier"); + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run err"); + ASSERT_EQ((int)topts.retval, 0, "test_run retval"); + + pthread_exit(arg); +} + +static void test_arena_spin_lock_size(int size) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts); + struct arena_spin_lock *skel; + pthread_t thread_id[16]; + int prog_fd, i, err; + void *ret; + + if (get_nprocs() < 2) { + test__skip(); + return; + } + + skel = arena_spin_lock__open_and_load(); + if (!ASSERT_OK_PTR(skel, "arena_spin_lock__open_and_load")) + return; + if (skel->data->test_skip == 2) { + test__skip(); + goto end; + } + skel->bss->cs_count = size; + skel->bss->limit = repeat * 16; + + ASSERT_OK(pthread_barrier_init(&barrier, NULL, 16), "barrier init"); + + prog_fd = bpf_program__fd(skel->progs.prog); + for (i = 0; i < 16; i++) { + err = pthread_create(&thread_id[i], NULL, &spin_lock_thread, &prog_fd); + if (!ASSERT_OK(err, "pthread_create")) + goto end_barrier; + } + + for (i = 0; i < 16; i++) { + if (!ASSERT_OK(pthread_join(thread_id[i], &ret), "pthread_join")) + goto end_barrier; + if (!ASSERT_EQ(ret, &prog_fd, "ret == prog_fd")) + goto end_barrier; + } + + ASSERT_EQ(skel->bss->counter, repeat * 16, "check counter value"); + +end_barrier: + pthread_barrier_destroy(&barrier); +end: + arena_spin_lock__destroy(skel); + return; +} + +void test_arena_spin_lock(void) +{ + repeat = 1000; + if (test__start_subtest("arena_spin_lock_1")) + test_arena_spin_lock_size(1); + cpu = 0; + if (test__start_subtest("arena_spin_lock_1000")) + test_arena_spin_lock_size(1000); + cpu = 0; + repeat = 100; + if (test__start_subtest("arena_spin_lock_50000")) + test_arena_spin_lock_size(50000); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c index cc184e4..67557cd 100644 --- a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c +++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c @@ -6,6 +6,10 @@ #include #include "bloom_filter_map.skel.h" +#ifndef NUMA_NO_NODE +#define NUMA_NO_NODE (-1) +#endif + static void test_fail_cases(void) { LIBBPF_OPTS(bpf_map_create_opts, opts); @@ -69,6 +73,7 @@ static void test_success_cases(void) /* Create a map */ opts.map_flags = BPF_F_ZERO_SEED | BPF_F_NUMA_NODE; + opts.numa_node = NUMA_NO_NODE; fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 100, &opts); if (!ASSERT_GE(fd, 0, "bpf_map_create bloom filter success case")) return; diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 6f1bfac..add4a18 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -323,19 +323,87 @@ static void test_task_pidfd(void) static void test_task_sleepable(void) { struct bpf_iter_tasks *skel; + int pid, status, err, data_pipe[2], finish_pipe[2], c; + char *test_data = NULL; + char *test_data_long = NULL; + char *data[2]; + + if (!ASSERT_OK(pipe(data_pipe), "data_pipe") || + !ASSERT_OK(pipe(finish_pipe), "finish_pipe")) + return; skel = bpf_iter_tasks__open_and_load(); if (!ASSERT_OK_PTR(skel, "bpf_iter_tasks__open_and_load")) return; + pid = fork(); + if (!ASSERT_GE(pid, 0, "fork")) + return; + + if (pid == 0) { + /* child */ + close(data_pipe[0]); + close(finish_pipe[1]); + + test_data = malloc(sizeof(char) * 10); + strncpy(test_data, "test_data", 10); + test_data[9] = '\0'; + + test_data_long = malloc(sizeof(char) * 5000); + for (int i = 0; i < 5000; ++i) { + if (i % 2 == 0) + test_data_long[i] = 'b'; + else + test_data_long[i] = 'a'; + } + test_data_long[4999] = '\0'; + + data[0] = test_data; + data[1] = test_data_long; + + write(data_pipe[1], &data, sizeof(data)); + + /* keep child alive until after the test */ + err = read(finish_pipe[0], &c, 1); + if (err != 1) + exit(-1); + + close(data_pipe[1]); + close(finish_pipe[0]); + _exit(0); + } + + /* parent */ + close(data_pipe[1]); + close(finish_pipe[0]); + + err = read(data_pipe[0], &data, sizeof(data)); + ASSERT_EQ(err, sizeof(data), "read_check"); + + skel->bss->user_ptr = data[0]; + skel->bss->user_ptr_long = data[1]; + skel->bss->pid = pid; + do_dummy_read(skel->progs.dump_task_sleepable); ASSERT_GT(skel->bss->num_expected_failure_copy_from_user_task, 0, "num_expected_failure_copy_from_user_task"); ASSERT_GT(skel->bss->num_success_copy_from_user_task, 0, "num_success_copy_from_user_task"); + ASSERT_GT(skel->bss->num_expected_failure_copy_from_user_task_str, 0, + "num_expected_failure_copy_from_user_task_str"); + ASSERT_GT(skel->bss->num_success_copy_from_user_task_str, 0, + "num_success_copy_from_user_task_str"); bpf_iter_tasks__destroy(skel); + + write(finish_pipe[1], &c, 1); + err = waitpid(pid, &status, 0); + ASSERT_EQ(err, pid, "waitpid"); + ASSERT_EQ(status, 0, "zero_child_exit"); + + close(data_pipe[0]); + close(finish_pipe[1]); } static void test_task_stack(void) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c index a4a1f93..dbd13f8 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c @@ -72,11 +72,14 @@ static void test_bpf_nf_ct(int mode) if (!ASSERT_OK(system(cmd), cmd)) goto end; - srv_port = (mode == TEST_XDP) ? 5005 : 5006; - srv_fd = start_server(AF_INET, SOCK_STREAM, "127.0.0.1", srv_port, TIMEOUT_MS); + srv_fd = start_server(AF_INET, SOCK_STREAM, "127.0.0.1", 0, TIMEOUT_MS); if (!ASSERT_GE(srv_fd, 0, "start_server")) goto end; + srv_port = get_socket_local_port(srv_fd); + if (!ASSERT_GE(srv_port, 0, "get_sock_local_port")) + goto end; + client_fd = connect_to_server(srv_fd); if (!ASSERT_GE(client_fd, 0, "connect_to_server")) goto end; @@ -91,7 +94,7 @@ static void test_bpf_nf_ct(int mode) skel->bss->saddr = peer_addr.sin_addr.s_addr; skel->bss->sport = peer_addr.sin_port; skel->bss->daddr = peer_addr.sin_addr.s_addr; - skel->bss->dport = htons(srv_port); + skel->bss->dport = srv_port; if (mode == TEST_XDP) prog_fd = bpf_program__fd(skel->progs.nf_xdp_ct_test); diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index e63d74c..8a9ba42 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -3866,11 +3866,11 @@ static struct btf_raw_test raw_tests[] = { .err_str = "vlen != 0", }, { - .descr = "decl_tag test #8, invalid kflag", + .descr = "decl_tag test #8, tag with kflag", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ - BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 1, 0), 2), (-1), + BTF_DECL_ATTR_ENC(NAME_TBD, 2, -1), BTF_END_RAW, }, BTF_STR_SEC("\0local\0tag1"), @@ -3881,8 +3881,6 @@ static struct btf_raw_test raw_tests[] = { .key_type_id = 1, .value_type_id = 1, .max_entries = 1, - .btf_load_err = true, - .err_str = "Invalid btf_info kind_flag", }, { .descr = "decl_tag test #9, var, invalid component_idx", @@ -4207,6 +4205,23 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Type tags don't precede modifiers", }, { + .descr = "type_tag test #7, tag with kflag", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_ATTR_ENC(NAME_TBD, 1), /* [2] */ + BTF_PTR_ENC(2), /* [3] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, +}, +{ .descr = "enum64 test #1, unsigned, size 8", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c index b293b85..c0a776f 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c @@ -126,26 +126,69 @@ done: return err; } -static char *dump_buf; -static size_t dump_buf_sz; -static FILE *dump_buf_file; +struct test_ctx { + struct btf *btf; + struct btf_dump *d; + char *dump_buf; + size_t dump_buf_sz; + FILE *dump_buf_file; +}; -static void test_btf_dump_incremental(void) +static void test_ctx__free(struct test_ctx *t) { - struct btf *btf = NULL; - struct btf_dump *d = NULL; - int id, err, i; + fclose(t->dump_buf_file); + free(t->dump_buf); + btf_dump__free(t->d); + btf__free(t->btf); +} - dump_buf_file = open_memstream(&dump_buf, &dump_buf_sz); - if (!ASSERT_OK_PTR(dump_buf_file, "dump_memstream")) - return; - btf = btf__new_empty(); - if (!ASSERT_OK_PTR(btf, "new_empty")) +static int test_ctx__init(struct test_ctx *t) +{ + t->dump_buf_file = open_memstream(&t->dump_buf, &t->dump_buf_sz); + if (!ASSERT_OK_PTR(t->dump_buf_file, "dump_memstream")) + return -1; + t->btf = btf__new_empty(); + if (!ASSERT_OK_PTR(t->btf, "new_empty")) goto err_out; - d = btf_dump__new(btf, btf_dump_printf, dump_buf_file, NULL); - if (!ASSERT_OK(libbpf_get_error(d), "btf_dump__new")) + t->d = btf_dump__new(t->btf, btf_dump_printf, t->dump_buf_file, NULL); + if (!ASSERT_OK(libbpf_get_error(t->d), "btf_dump__new")) goto err_out; + return 0; + +err_out: + test_ctx__free(t); + return -1; +} + +static void test_ctx__dump_and_compare(struct test_ctx *t, + const char *expected_output, + const char *message) +{ + int i, err; + + for (i = 1; i < btf__type_cnt(t->btf); i++) { + err = btf_dump__dump_type(t->d, i); + ASSERT_OK(err, "dump_type_ok"); + } + + fflush(t->dump_buf_file); + t->dump_buf[t->dump_buf_sz] = 0; /* some libc implementations don't do this */ + + ASSERT_STREQ(t->dump_buf, expected_output, message); +} + +static void test_btf_dump_incremental(void) +{ + struct test_ctx t = {}; + struct btf *btf; + int id, err; + + if (test_ctx__init(&t)) + return; + + btf = t.btf; + /* First, generate BTF corresponding to the following C code: * * enum x; @@ -182,15 +225,7 @@ static void test_btf_dump_incremental(void) err = btf__add_field(btf, "x", 4, 0, 0); ASSERT_OK(err, "field_ok"); - for (i = 1; i < btf__type_cnt(btf); i++) { - err = btf_dump__dump_type(d, i); - ASSERT_OK(err, "dump_type_ok"); - } - - fflush(dump_buf_file); - dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */ - - ASSERT_STREQ(dump_buf, + test_ctx__dump_and_compare(&t, "enum x;\n" "\n" "enum x {\n" @@ -221,7 +256,7 @@ static void test_btf_dump_incremental(void) * enum values don't conflict; * */ - fseek(dump_buf_file, 0, SEEK_SET); + fseek(t.dump_buf_file, 0, SEEK_SET); id = btf__add_struct(btf, "s", 4); ASSERT_EQ(id, 7, "struct_id"); @@ -232,14 +267,7 @@ static void test_btf_dump_incremental(void) err = btf__add_field(btf, "s", 6, 64, 0); ASSERT_OK(err, "field_ok"); - for (i = 1; i < btf__type_cnt(btf); i++) { - err = btf_dump__dump_type(d, i); - ASSERT_OK(err, "dump_type_ok"); - } - - fflush(dump_buf_file); - dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */ - ASSERT_STREQ(dump_buf, + test_ctx__dump_and_compare(&t, "struct s___2 {\n" " enum x x;\n" " enum {\n" @@ -248,11 +276,53 @@ static void test_btf_dump_incremental(void) " struct s s;\n" "};\n\n" , "c_dump1"); -err_out: - fclose(dump_buf_file); - free(dump_buf); - btf_dump__free(d); - btf__free(btf); + test_ctx__free(&t); +} + +static void test_btf_dump_type_tags(void) +{ + struct test_ctx t = {}; + struct btf *btf; + int id, err; + + if (test_ctx__init(&t)) + return; + + btf = t.btf; + + /* Generate BTF corresponding to the following C code: + * + * struct s { + * void __attribute__((btf_type_tag(\"void_tag\"))) *p1; + * void __attribute__((void_attr)) *p2; + * }; + * + */ + + id = btf__add_type_tag(btf, "void_tag", 0); + ASSERT_EQ(id, 1, "type_tag_id"); + id = btf__add_ptr(btf, id); + ASSERT_EQ(id, 2, "void_ptr_id1"); + + id = btf__add_type_attr(btf, "void_attr", 0); + ASSERT_EQ(id, 3, "type_attr_id"); + id = btf__add_ptr(btf, id); + ASSERT_EQ(id, 4, "void_ptr_id2"); + + id = btf__add_struct(btf, "s", 8); + ASSERT_EQ(id, 5, "struct_id"); + err = btf__add_field(btf, "p1", 2, 0, 0); + ASSERT_OK(err, "field_ok1"); + err = btf__add_field(btf, "p2", 4, 0, 0); + ASSERT_OK(err, "field_ok2"); + + test_ctx__dump_and_compare(&t, +"struct s {\n" +" void __attribute__((btf_type_tag(\"void_tag\"))) *p1;\n" +" void __attribute__((void_attr)) *p2;\n" +"};\n\n", "dump_and_compare"); + + test_ctx__free(&t); } #define STRSIZE 4096 @@ -874,6 +944,9 @@ void test_btf_dump() { if (test__start_subtest("btf_dump: incremental")) test_btf_dump_incremental(); + if (test__start_subtest("btf_dump: type_tags")) + test_btf_dump_type_tags(); + btf = libbpf_find_kernel_btf(); if (!ASSERT_OK_PTR(btf, "no kernel BTF found")) return; diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_preorder.c b/tools/testing/selftests/bpf/prog_tests/cgroup_preorder.c new file mode 100644 index 0000000..d4d5838 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_preorder.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include +#include "cgroup_helpers.h" +#include "cgroup_preorder.skel.h" + +static int run_getsockopt_test(int cg_parent, int cg_child, int sock_fd, bool all_preorder) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opts); + enum bpf_attach_type prog_c_atype, prog_c2_atype, prog_p_atype, prog_p2_atype; + int prog_c_fd, prog_c2_fd, prog_p_fd, prog_p2_fd; + struct cgroup_preorder *skel = NULL; + struct bpf_program *prog; + __u8 *result, buf; + socklen_t optlen; + int err = 0; + + skel = cgroup_preorder__open_and_load(); + if (!ASSERT_OK_PTR(skel, "cgroup_preorder__open_and_load")) + return 0; + + buf = 0x00; + err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1); + if (!ASSERT_OK(err, "setsockopt")) + goto close_skel; + + opts.flags = BPF_F_ALLOW_MULTI; + if (all_preorder) + opts.flags |= BPF_F_PREORDER; + prog = skel->progs.child; + prog_c_fd = bpf_program__fd(prog); + prog_c_atype = bpf_program__expected_attach_type(prog); + err = bpf_prog_attach_opts(prog_c_fd, cg_child, prog_c_atype, &opts); + if (!ASSERT_OK(err, "bpf_prog_attach_opts-child")) + goto close_skel; + + opts.flags = BPF_F_ALLOW_MULTI | BPF_F_PREORDER; + prog = skel->progs.child_2; + prog_c2_fd = bpf_program__fd(prog); + prog_c2_atype = bpf_program__expected_attach_type(prog); + err = bpf_prog_attach_opts(prog_c2_fd, cg_child, prog_c2_atype, &opts); + if (!ASSERT_OK(err, "bpf_prog_attach_opts-child_2")) + goto detach_child; + + optlen = 1; + err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen); + if (!ASSERT_OK(err, "getsockopt")) + goto detach_child_2; + + result = skel->bss->result; + if (all_preorder) + ASSERT_TRUE(result[0] == 1 && result[1] == 2, "child only"); + else + ASSERT_TRUE(result[0] == 2 && result[1] == 1, "child only"); + + skel->bss->idx = 0; + memset(result, 0, 4); + + opts.flags = BPF_F_ALLOW_MULTI; + if (all_preorder) + opts.flags |= BPF_F_PREORDER; + prog = skel->progs.parent; + prog_p_fd = bpf_program__fd(prog); + prog_p_atype = bpf_program__expected_attach_type(prog); + err = bpf_prog_attach_opts(prog_p_fd, cg_parent, prog_p_atype, &opts); + if (!ASSERT_OK(err, "bpf_prog_attach_opts-parent")) + goto detach_child_2; + + opts.flags = BPF_F_ALLOW_MULTI | BPF_F_PREORDER; + prog = skel->progs.parent_2; + prog_p2_fd = bpf_program__fd(prog); + prog_p2_atype = bpf_program__expected_attach_type(prog); + err = bpf_prog_attach_opts(prog_p2_fd, cg_parent, prog_p2_atype, &opts); + if (!ASSERT_OK(err, "bpf_prog_attach_opts-parent_2")) + goto detach_parent; + + err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen); + if (!ASSERT_OK(err, "getsockopt")) + goto detach_parent_2; + + if (all_preorder) + ASSERT_TRUE(result[0] == 3 && result[1] == 4 && result[2] == 1 && result[3] == 2, + "parent and child"); + else + ASSERT_TRUE(result[0] == 4 && result[1] == 2 && result[2] == 1 && result[3] == 3, + "parent and child"); + +detach_parent_2: + ASSERT_OK(bpf_prog_detach2(prog_p2_fd, cg_parent, prog_p2_atype), + "bpf_prog_detach2-parent_2"); +detach_parent: + ASSERT_OK(bpf_prog_detach2(prog_p_fd, cg_parent, prog_p_atype), + "bpf_prog_detach2-parent"); +detach_child_2: + ASSERT_OK(bpf_prog_detach2(prog_c2_fd, cg_child, prog_c2_atype), + "bpf_prog_detach2-child_2"); +detach_child: + ASSERT_OK(bpf_prog_detach2(prog_c_fd, cg_child, prog_c_atype), + "bpf_prog_detach2-child"); +close_skel: + cgroup_preorder__destroy(skel); + return err; +} + +void test_cgroup_preorder(void) +{ + int cg_parent = -1, cg_child = -1, sock_fd = -1; + + cg_parent = test__join_cgroup("/parent"); + if (!ASSERT_GE(cg_parent, 0, "join_cgroup /parent")) + goto out; + + cg_child = test__join_cgroup("/parent/child"); + if (!ASSERT_GE(cg_child, 0, "join_cgroup /parent/child")) + goto out; + + sock_fd = socket(AF_INET, SOCK_STREAM, 0); + if (!ASSERT_GE(sock_fd, 0, "socket")) + goto out; + + ASSERT_OK(run_getsockopt_test(cg_parent, cg_child, sock_fd, false), "getsockopt_test_1"); + ASSERT_OK(run_getsockopt_test(cg_parent, cg_child, sock_fd, true), "getsockopt_test_2"); + +out: + close(sock_fd); + close(cg_child); + close(cg_parent); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c index 64abba7..37c1cc5 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c @@ -10,12 +10,18 @@ static int run_test(int cgroup_fd, int server_fd, bool classid) { struct connect4_dropper *skel; - int fd, err = 0; + int fd, err = 0, port; skel = connect4_dropper__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel_open")) return -1; + port = get_socket_local_port(server_fd); + if (!ASSERT_GE(port, 0, "get_socket_local_port")) + return -1; + + skel->bss->port = ntohs(port); + skel->links.connect_v4_dropper = bpf_program__attach_cgroup(skel->progs.connect_v4_dropper, cgroup_fd); @@ -48,10 +54,9 @@ void test_cgroup_v1v2(void) { struct network_helper_opts opts = {}; int server_fd, client_fd, cgroup_fd; - static const int port = 60120; /* Step 1: Check base connectivity works without any BPF. */ - server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0); + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0); if (!ASSERT_GE(server_fd, 0, "server_fd")) return; client_fd = connect_to_fd_opts(server_fd, &opts); @@ -66,7 +71,7 @@ void test_cgroup_v1v2(void) cgroup_fd = test__join_cgroup("/connect_dropper"); if (!ASSERT_GE(cgroup_fd, 0, "cgroup_fd")) return; - server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0); + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0); if (!ASSERT_GE(server_fd, 0, "server_fd")) { close(cgroup_fd); return; diff --git a/tools/testing/selftests/bpf/prog_tests/compute_live_registers.c b/tools/testing/selftests/bpf/prog_tests/compute_live_registers.c new file mode 100644 index 0000000..285f202 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/compute_live_registers.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "compute_live_registers.skel.h" +#include "test_progs.h" + +void test_compute_live_registers(void) +{ + RUN_TESTS(compute_live_registers); +} diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index e10ea92..08963c8 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -85,11 +85,11 @@ static int duration = 0; #define NESTING_ERR_CASE(name) { \ NESTING_CASE_COMMON(name), \ .fails = true, \ - .run_btfgen_fails = true, \ + .run_btfgen_fails = true, \ } #define ARRAYS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ - .a = { [2] = 1 }, \ + .a = { [2] = 1, [3] = 11 }, \ .b = { [1] = { [2] = { [3] = 2 } } }, \ .c = { [1] = { .c = 3 } }, \ .d = { [0] = { [0] = { .d = 4 } } }, \ @@ -108,6 +108,7 @@ static int duration = 0; .input_len = sizeof(struct core_reloc_##name), \ .output = STRUCT_TO_CHAR_PTR(core_reloc_arrays_output) { \ .a2 = 1, \ + .a3 = 12, \ .b123 = 2, \ .c1c = 3, \ .d00d = 4, \ @@ -602,6 +603,7 @@ static const struct core_reloc_test_case test_cases[] = { ARRAYS_ERR_CASE(arrays___err_non_array), ARRAYS_ERR_CASE(arrays___err_wrong_val_type), ARRAYS_ERR_CASE(arrays___err_bad_zero_sz_arr), + ARRAYS_ERR_CASE(arrays___err_bad_signed_arr_elem_sz), /* enum/ptr/int handling scenarios */ PRIMITIVES_CASE(primitives), diff --git a/tools/testing/selftests/bpf/prog_tests/cpumask.c b/tools/testing/selftests/bpf/prog_tests/cpumask.c index e58a046..6c45330 100644 --- a/tools/testing/selftests/bpf/prog_tests/cpumask.c +++ b/tools/testing/selftests/bpf/prog_tests/cpumask.c @@ -25,6 +25,10 @@ static const char * const cpumask_success_testcases[] = { "test_global_mask_nested_deep_rcu", "test_global_mask_nested_deep_array_rcu", "test_cpumask_weight", + "test_refcount_null_tracking", + "test_populate_reject_small_mask", + "test_populate_reject_unaligned", + "test_populate", }; static void verify_success(const char *prog_name) @@ -78,6 +82,5 @@ void test_cpumask(void) verify_success(cpumask_success_testcases[i]); } - RUN_TESTS(cpumask_success); RUN_TESTS(cpumask_failure); } diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c index b614a52..e29cc16 100644 --- a/tools/testing/selftests/bpf/prog_tests/dynptr.c +++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c @@ -10,6 +10,7 @@ enum test_setup_type { SETUP_SYSCALL_SLEEP, SETUP_SKB_PROG, SETUP_SKB_PROG_TP, + SETUP_XDP_PROG, }; static struct { @@ -18,6 +19,8 @@ static struct { } success_tests[] = { {"test_read_write", SETUP_SYSCALL_SLEEP}, {"test_dynptr_data", SETUP_SYSCALL_SLEEP}, + {"test_dynptr_copy", SETUP_SYSCALL_SLEEP}, + {"test_dynptr_copy_xdp", SETUP_XDP_PROG}, {"test_ringbuf", SETUP_SYSCALL_SLEEP}, {"test_skb_readonly", SETUP_SKB_PROG}, {"test_dynptr_skb_data", SETUP_SKB_PROG}, @@ -120,6 +123,24 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ break; } + case SETUP_XDP_PROG: + { + char data[5000]; + int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &data, + .data_size_in = sizeof(data), + .repeat = 1, + ); + + prog_fd = bpf_program__fd(prog); + err = bpf_prog_test_run_opts(prog_fd, &opts); + + if (!ASSERT_OK(err, "test_run")) + goto cleanup; + + break; + } } ASSERT_EQ(skel->bss->err, 0, "err"); diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c index a1d52e7..9add890 100644 --- a/tools/testing/selftests/bpf/prog_tests/fd_array.c +++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c @@ -83,8 +83,8 @@ static inline int bpf_prog_get_map_ids(int prog_fd, __u32 *nr_map_ids, __u32 *ma int err; memset(&info, 0, len); - info.nr_map_ids = *nr_map_ids, - info.map_ids = ptr_to_u64(map_ids), + info.nr_map_ids = *nr_map_ids; + info.map_ids = ptr_to_u64(map_ids); err = bpf_prog_get_info_by_fd(prog_fd, &info, &len); if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd")) diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_noreturns.c b/tools/testing/selftests/bpf/prog_tests/fexit_noreturns.c new file mode 100644 index 0000000..568d3aa --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/fexit_noreturns.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include "fexit_noreturns.skel.h" + +void test_fexit_noreturns(void) +{ + RUN_TESTS(fexit_noreturns); +} diff --git a/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c b/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c index 5a0b511..43a26ec 100644 --- a/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c +++ b/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c @@ -8,11 +8,12 @@ #include #include #include "test_get_xattr.skel.h" +#include "test_set_remove_xattr.skel.h" #include "test_fsverity.skel.h" static const char testfile[] = "/tmp/test_progs_fs_kfuncs"; -static void test_xattr(void) +static void test_get_xattr(const char *name, const char *value, bool allow_access) { struct test_get_xattr *skel = NULL; int fd = -1, err; @@ -25,7 +26,7 @@ static void test_xattr(void) close(fd); fd = -1; - err = setxattr(testfile, "user.kfuncs", "hello", sizeof("hello"), 0); + err = setxattr(testfile, name, value, strlen(value) + 1, 0); if (err && errno == EOPNOTSUPP) { printf("%s:SKIP:local fs doesn't support xattr (%d)\n" "To run this test, make sure /tmp filesystem supports xattr.\n", @@ -48,16 +49,23 @@ static void test_xattr(void) goto out; fd = open(testfile, O_RDONLY, 0644); + if (!ASSERT_GE(fd, 0, "open_file")) goto out; - ASSERT_EQ(skel->bss->found_xattr_from_file, 1, "found_xattr_from_file"); - /* Trigger security_inode_getxattr */ - err = getxattr(testfile, "user.kfuncs", v, sizeof(v)); - ASSERT_EQ(err, -1, "getxattr_return"); - ASSERT_EQ(errno, EINVAL, "getxattr_errno"); - ASSERT_EQ(skel->bss->found_xattr_from_dentry, 1, "found_xattr_from_dentry"); + err = getxattr(testfile, name, v, sizeof(v)); + + if (allow_access) { + ASSERT_EQ(err, -1, "getxattr_return"); + ASSERT_EQ(errno, EINVAL, "getxattr_errno"); + ASSERT_EQ(skel->bss->found_xattr_from_file, 1, "found_xattr_from_file"); + ASSERT_EQ(skel->bss->found_xattr_from_dentry, 1, "found_xattr_from_dentry"); + } else { + ASSERT_EQ(err, strlen(value) + 1, "getxattr_return"); + ASSERT_EQ(skel->bss->found_xattr_from_file, 0, "found_xattr_from_file"); + ASSERT_EQ(skel->bss->found_xattr_from_dentry, 0, "found_xattr_from_dentry"); + } out: close(fd); @@ -65,6 +73,127 @@ out: remove(testfile); } +/* xattr value we will set to security.bpf.foo */ +static const char value_foo[] = "hello"; + +static void read_and_validate_foo(struct test_set_remove_xattr *skel) +{ + char value_out[32]; + int err; + + err = getxattr(testfile, skel->rodata->xattr_foo, value_out, sizeof(value_out)); + ASSERT_EQ(err, sizeof(value_foo), "getxattr size foo"); + ASSERT_EQ(strncmp(value_out, value_foo, sizeof(value_foo)), 0, "strncmp value_foo"); +} + +static void set_foo(struct test_set_remove_xattr *skel) +{ + ASSERT_OK(setxattr(testfile, skel->rodata->xattr_foo, value_foo, strlen(value_foo) + 1, 0), + "setxattr foo"); +} + +static void validate_bar_match(struct test_set_remove_xattr *skel) +{ + char value_out[32]; + int err; + + err = getxattr(testfile, skel->rodata->xattr_bar, value_out, sizeof(value_out)); + ASSERT_EQ(err, sizeof(skel->data->value_bar), "getxattr size bar"); + ASSERT_EQ(strncmp(value_out, skel->data->value_bar, sizeof(skel->data->value_bar)), 0, + "strncmp value_bar"); +} + +static void validate_bar_removed(struct test_set_remove_xattr *skel) +{ + char value_out[32]; + int err; + + err = getxattr(testfile, skel->rodata->xattr_bar, value_out, sizeof(value_out)); + ASSERT_LT(err, 0, "getxattr size bar should fail"); +} + +static void test_set_remove_xattr(void) +{ + struct test_set_remove_xattr *skel = NULL; + int fd = -1, err; + + fd = open(testfile, O_CREAT | O_RDONLY, 0644); + if (!ASSERT_GE(fd, 0, "create_file")) + return; + + close(fd); + fd = -1; + + skel = test_set_remove_xattr__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_set_remove_xattr__open_and_load")) + return; + + /* Set security.bpf.foo to "hello" */ + err = setxattr(testfile, skel->rodata->xattr_foo, value_foo, strlen(value_foo) + 1, 0); + if (err && errno == EOPNOTSUPP) { + printf("%s:SKIP:local fs doesn't support xattr (%d)\n" + "To run this test, make sure /tmp filesystem supports xattr.\n", + __func__, errno); + test__skip(); + goto out; + } + + if (!ASSERT_OK(err, "setxattr")) + goto out; + + skel->bss->monitored_pid = getpid(); + err = test_set_remove_xattr__attach(skel); + if (!ASSERT_OK(err, "test_set_remove_xattr__attach")) + goto out; + + /* First, test not _locked version of the kfuncs with getxattr. */ + + /* Read security.bpf.foo and trigger test_inode_getxattr. This + * bpf program will set security.bpf.bar to "world". + */ + read_and_validate_foo(skel); + validate_bar_match(skel); + + /* Read security.bpf.foo and trigger test_inode_getxattr again. + * This will remove xattr security.bpf.bar. + */ + read_and_validate_foo(skel); + validate_bar_removed(skel); + + ASSERT_TRUE(skel->bss->set_security_bpf_bar_success, "set_security_bpf_bar_success"); + ASSERT_TRUE(skel->bss->remove_security_bpf_bar_success, "remove_security_bpf_bar_success"); + ASSERT_TRUE(skel->bss->set_security_selinux_fail, "set_security_selinux_fail"); + ASSERT_TRUE(skel->bss->remove_security_selinux_fail, "remove_security_selinux_fail"); + + /* Second, test _locked version of the kfuncs, with setxattr */ + + /* Set security.bpf.foo and trigger test_inode_setxattr. This + * bpf program will set security.bpf.bar to "world". + */ + set_foo(skel); + validate_bar_match(skel); + + /* Set security.bpf.foo and trigger test_inode_setxattr again. + * This will remove xattr security.bpf.bar. + */ + set_foo(skel); + validate_bar_removed(skel); + + ASSERT_TRUE(skel->bss->locked_set_security_bpf_bar_success, + "locked_set_security_bpf_bar_success"); + ASSERT_TRUE(skel->bss->locked_remove_security_bpf_bar_success, + "locked_remove_security_bpf_bar_success"); + ASSERT_TRUE(skel->bss->locked_set_security_selinux_fail, + "locked_set_security_selinux_fail"); + ASSERT_TRUE(skel->bss->locked_remove_security_selinux_fail, + "locked_remove_security_selinux_fail"); + +out: + close(fd); + test_set_remove_xattr__destroy(skel); + remove(testfile); +} + #ifndef SHA256_DIGEST_SIZE #define SHA256_DIGEST_SIZE 32 #endif @@ -141,8 +270,21 @@ out: void test_fs_kfuncs(void) { - if (test__start_subtest("xattr")) - test_xattr(); + /* Matches xattr_names in progs/test_get_xattr.c */ + if (test__start_subtest("user_xattr")) + test_get_xattr("user.kfuncs", "hello", true); + + if (test__start_subtest("security_bpf_xattr")) + test_get_xattr("security.bpf.xxx", "hello", true); + + if (test__start_subtest("security_bpf_xattr_error")) + test_get_xattr("security.bpf", "hello", false); + + if (test__start_subtest("security_selinux_xattr_error")) + test_get_xattr("security.selinux", "hello", false); + + if (test__start_subtest("set_remove_xattr")) + test_set_remove_xattr(); if (test__start_subtest("fsverity")) test_fsverity(); diff --git a/tools/testing/selftests/bpf/prog_tests/kernel_flag.c b/tools/testing/selftests/bpf/prog_tests/kernel_flag.c new file mode 100644 index 0000000..a133354 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/kernel_flag.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Microsoft */ +#include +#include "kfunc_call_test.skel.h" +#include "kfunc_call_test.lskel.h" +#include "test_kernel_flag.skel.h" + +void test_kernel_flag(void) +{ + struct test_kernel_flag *lsm_skel; + struct kfunc_call_test *skel = NULL; + struct kfunc_call_test_lskel *lskel = NULL; + int ret; + + lsm_skel = test_kernel_flag__open_and_load(); + if (!ASSERT_OK_PTR(lsm_skel, "lsm_skel")) + return; + + lsm_skel->bss->monitored_tid = gettid(); + + ret = test_kernel_flag__attach(lsm_skel); + if (!ASSERT_OK(ret, "test_kernel_flag__attach")) + goto close_prog; + + /* Test with skel. This should pass the gatekeeper */ + skel = kfunc_call_test__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel")) + goto close_prog; + + /* Test with lskel. This should fail due to blocking kernel-based bpf() invocations */ + lskel = kfunc_call_test_lskel__open_and_load(); + if (!ASSERT_ERR_PTR(lskel, "lskel")) + goto close_prog; + +close_prog: + if (skel) + kfunc_call_test__destroy(skel); + if (lskel) + kfunc_call_test_lskel__destroy(lskel); + + lsm_skel->bss->monitored_tid = 0; + test_kernel_flag__destroy(lsm_skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c b/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c new file mode 100644 index 0000000..b6391af --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c @@ -0,0 +1,540 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include + +#include "network_helpers.h" +#include "test_progs.h" + +#define BPF_FILE "test_lwt_ip_encap.bpf.o" + +#define NETNS_NAME_SIZE 32 +#define NETNS_BASE "ns-lwt-ip-encap" + +#define IP4_ADDR_1 "172.16.1.100" +#define IP4_ADDR_2 "172.16.2.100" +#define IP4_ADDR_3 "172.16.3.100" +#define IP4_ADDR_4 "172.16.4.100" +#define IP4_ADDR_5 "172.16.5.100" +#define IP4_ADDR_6 "172.16.6.100" +#define IP4_ADDR_7 "172.16.7.100" +#define IP4_ADDR_8 "172.16.8.100" +#define IP4_ADDR_GRE "172.16.16.100" + +#define IP4_ADDR_SRC IP4_ADDR_1 +#define IP4_ADDR_DST IP4_ADDR_4 + +#define IP6_ADDR_1 "fb01::1" +#define IP6_ADDR_2 "fb02::1" +#define IP6_ADDR_3 "fb03::1" +#define IP6_ADDR_4 "fb04::1" +#define IP6_ADDR_5 "fb05::1" +#define IP6_ADDR_6 "fb06::1" +#define IP6_ADDR_7 "fb07::1" +#define IP6_ADDR_8 "fb08::1" +#define IP6_ADDR_GRE "fb10::1" + +#define IP6_ADDR_SRC IP6_ADDR_1 +#define IP6_ADDR_DST IP6_ADDR_4 + +/* Setup/topology: + * + * NS1 NS2 NS3 + * veth1 <---> veth2 veth3 <---> veth4 (the top route) + * veth5 <---> veth6 veth7 <---> veth8 (the bottom route) + * + * Each vethN gets IP[4|6]_ADDR_N address. + * + * IP*_ADDR_SRC = IP*_ADDR_1 + * IP*_ADDR_DST = IP*_ADDR_4 + * + * All tests test pings from IP*_ADDR__SRC to IP*_ADDR_DST. + * + * By default, routes are configured to allow packets to go + * IP*_ADDR_1 <=> IP*_ADDR_2 <=> IP*_ADDR_3 <=> IP*_ADDR_4 (the top route). + * + * A GRE device is installed in NS3 with IP*_ADDR_GRE, and + * NS1/NS2 are configured to route packets to IP*_ADDR_GRE via IP*_ADDR_8 + * (the bottom route). + * + * Tests: + * + * 1. Routes NS2->IP*_ADDR_DST are brought down, so the only way a ping + * from IP*_ADDR_SRC to IP*_ADDR_DST can work is via IP*_ADDR_GRE. + * + * 2a. In an egress test, a bpf LWT_XMIT program is installed on veth1 + * that encaps the packets with an IP/GRE header to route to IP*_ADDR_GRE. + * + * ping: SRC->[encap at veth1:egress]->GRE:decap->DST + * ping replies go DST->SRC directly + * + * 2b. In an ingress test, a bpf LWT_IN program is installed on veth2 + * that encaps the packets with an IP/GRE header to route to IP*_ADDR_GRE. + * + * ping: SRC->[encap at veth2:ingress]->GRE:decap->DST + * ping replies go DST->SRC directly + */ + +static int create_ns(char *name, size_t name_sz) +{ + if (!name) + goto fail; + + if (!ASSERT_OK(append_tid(name, name_sz), "append TID")) + goto fail; + + SYS(fail, "ip netns add %s", name); + + /* rp_filter gets confused by what these tests are doing, so disable it */ + SYS(fail, "ip netns exec %s sysctl -wq net.ipv4.conf.all.rp_filter=0", name); + SYS(fail, "ip netns exec %s sysctl -wq net.ipv4.conf.default.rp_filter=0", name); + /* Disable IPv6 DAD because it sometimes takes too long and fails tests */ + SYS(fail, "ip netns exec %s sysctl -wq net.ipv6.conf.all.accept_dad=0", name); + SYS(fail, "ip netns exec %s sysctl -wq net.ipv6.conf.default.accept_dad=0", name); + + return 0; +fail: + return -1; +} + +static int set_top_addr(const char *ns1, const char *ns2, const char *ns3) +{ + SYS(fail, "ip -n %s a add %s/24 dev veth1", ns1, IP4_ADDR_1); + SYS(fail, "ip -n %s a add %s/24 dev veth2", ns2, IP4_ADDR_2); + SYS(fail, "ip -n %s a add %s/24 dev veth3", ns2, IP4_ADDR_3); + SYS(fail, "ip -n %s a add %s/24 dev veth4", ns3, IP4_ADDR_4); + SYS(fail, "ip -n %s -6 a add %s/128 dev veth1", ns1, IP6_ADDR_1); + SYS(fail, "ip -n %s -6 a add %s/128 dev veth2", ns2, IP6_ADDR_2); + SYS(fail, "ip -n %s -6 a add %s/128 dev veth3", ns2, IP6_ADDR_3); + SYS(fail, "ip -n %s -6 a add %s/128 dev veth4", ns3, IP6_ADDR_4); + + SYS(fail, "ip -n %s link set dev veth1 up", ns1); + SYS(fail, "ip -n %s link set dev veth2 up", ns2); + SYS(fail, "ip -n %s link set dev veth3 up", ns2); + SYS(fail, "ip -n %s link set dev veth4 up", ns3); + + return 0; +fail: + return 1; +} + +static int set_bottom_addr(const char *ns1, const char *ns2, const char *ns3) +{ + SYS(fail, "ip -n %s a add %s/24 dev veth5", ns1, IP4_ADDR_5); + SYS(fail, "ip -n %s a add %s/24 dev veth6", ns2, IP4_ADDR_6); + SYS(fail, "ip -n %s a add %s/24 dev veth7", ns2, IP4_ADDR_7); + SYS(fail, "ip -n %s a add %s/24 dev veth8", ns3, IP4_ADDR_8); + SYS(fail, "ip -n %s -6 a add %s/128 dev veth5", ns1, IP6_ADDR_5); + SYS(fail, "ip -n %s -6 a add %s/128 dev veth6", ns2, IP6_ADDR_6); + SYS(fail, "ip -n %s -6 a add %s/128 dev veth7", ns2, IP6_ADDR_7); + SYS(fail, "ip -n %s -6 a add %s/128 dev veth8", ns3, IP6_ADDR_8); + + SYS(fail, "ip -n %s link set dev veth5 up", ns1); + SYS(fail, "ip -n %s link set dev veth6 up", ns2); + SYS(fail, "ip -n %s link set dev veth7 up", ns2); + SYS(fail, "ip -n %s link set dev veth8 up", ns3); + + return 0; +fail: + return 1; +} + +static int configure_vrf(const char *ns1, const char *ns2) +{ + if (!ns1 || !ns2) + goto fail; + + SYS(fail, "ip -n %s link add red type vrf table 1001", ns1); + SYS(fail, "ip -n %s link set red up", ns1); + SYS(fail, "ip -n %s route add table 1001 unreachable default metric 8192", ns1); + SYS(fail, "ip -n %s -6 route add table 1001 unreachable default metric 8192", ns1); + SYS(fail, "ip -n %s link set veth1 vrf red", ns1); + SYS(fail, "ip -n %s link set veth5 vrf red", ns1); + + SYS(fail, "ip -n %s link add red type vrf table 1001", ns2); + SYS(fail, "ip -n %s link set red up", ns2); + SYS(fail, "ip -n %s route add table 1001 unreachable default metric 8192", ns2); + SYS(fail, "ip -n %s -6 route add table 1001 unreachable default metric 8192", ns2); + SYS(fail, "ip -n %s link set veth2 vrf red", ns2); + SYS(fail, "ip -n %s link set veth3 vrf red", ns2); + SYS(fail, "ip -n %s link set veth6 vrf red", ns2); + SYS(fail, "ip -n %s link set veth7 vrf red", ns2); + + return 0; +fail: + return -1; +} + +static int configure_ns1(const char *ns1, const char *vrf) +{ + struct nstoken *nstoken = NULL; + + if (!ns1 || !vrf) + goto fail; + + nstoken = open_netns(ns1); + if (!ASSERT_OK_PTR(nstoken, "open ns1")) + goto fail; + + /* Top route */ + SYS(fail, "ip route add %s/32 dev veth1 %s", IP4_ADDR_2, vrf); + SYS(fail, "ip route add default dev veth1 via %s %s", IP4_ADDR_2, vrf); + SYS(fail, "ip -6 route add %s/128 dev veth1 %s", IP6_ADDR_2, vrf); + SYS(fail, "ip -6 route add default dev veth1 via %s %s", IP6_ADDR_2, vrf); + /* Bottom route */ + SYS(fail, "ip route add %s/32 dev veth5 %s", IP4_ADDR_6, vrf); + SYS(fail, "ip route add %s/32 dev veth5 via %s %s", IP4_ADDR_7, IP4_ADDR_6, vrf); + SYS(fail, "ip route add %s/32 dev veth5 via %s %s", IP4_ADDR_8, IP4_ADDR_6, vrf); + SYS(fail, "ip -6 route add %s/128 dev veth5 %s", IP6_ADDR_6, vrf); + SYS(fail, "ip -6 route add %s/128 dev veth5 via %s %s", IP6_ADDR_7, IP6_ADDR_6, vrf); + SYS(fail, "ip -6 route add %s/128 dev veth5 via %s %s", IP6_ADDR_8, IP6_ADDR_6, vrf); + + close_netns(nstoken); + return 0; +fail: + close_netns(nstoken); + return -1; +} + +static int configure_ns2(const char *ns2, const char *vrf) +{ + struct nstoken *nstoken = NULL; + + if (!ns2 || !vrf) + goto fail; + + nstoken = open_netns(ns2); + if (!ASSERT_OK_PTR(nstoken, "open ns2")) + goto fail; + + SYS(fail, "ip netns exec %s sysctl -wq net.ipv4.ip_forward=1", ns2); + SYS(fail, "ip netns exec %s sysctl -wq net.ipv6.conf.all.forwarding=1", ns2); + + /* Top route */ + SYS(fail, "ip route add %s/32 dev veth2 %s", IP4_ADDR_1, vrf); + SYS(fail, "ip route add %s/32 dev veth3 %s", IP4_ADDR_4, vrf); + SYS(fail, "ip -6 route add %s/128 dev veth2 %s", IP6_ADDR_1, vrf); + SYS(fail, "ip -6 route add %s/128 dev veth3 %s", IP6_ADDR_4, vrf); + /* Bottom route */ + SYS(fail, "ip route add %s/32 dev veth6 %s", IP4_ADDR_5, vrf); + SYS(fail, "ip route add %s/32 dev veth7 %s", IP4_ADDR_8, vrf); + SYS(fail, "ip -6 route add %s/128 dev veth6 %s", IP6_ADDR_5, vrf); + SYS(fail, "ip -6 route add %s/128 dev veth7 %s", IP6_ADDR_8, vrf); + + close_netns(nstoken); + return 0; +fail: + close_netns(nstoken); + return -1; +} + +static int configure_ns3(const char *ns3) +{ + struct nstoken *nstoken = NULL; + + if (!ns3) + goto fail; + + nstoken = open_netns(ns3); + if (!ASSERT_OK_PTR(nstoken, "open ns3")) + goto fail; + + /* Top route */ + SYS(fail, "ip route add %s/32 dev veth4", IP4_ADDR_3); + SYS(fail, "ip route add %s/32 dev veth4 via %s", IP4_ADDR_1, IP4_ADDR_3); + SYS(fail, "ip route add %s/32 dev veth4 via %s", IP4_ADDR_2, IP4_ADDR_3); + SYS(fail, "ip -6 route add %s/128 dev veth4", IP6_ADDR_3); + SYS(fail, "ip -6 route add %s/128 dev veth4 via %s", IP6_ADDR_1, IP6_ADDR_3); + SYS(fail, "ip -6 route add %s/128 dev veth4 via %s", IP6_ADDR_2, IP6_ADDR_3); + /* Bottom route */ + SYS(fail, "ip route add %s/32 dev veth8", IP4_ADDR_7); + SYS(fail, "ip route add %s/32 dev veth8 via %s", IP4_ADDR_5, IP4_ADDR_7); + SYS(fail, "ip route add %s/32 dev veth8 via %s", IP4_ADDR_6, IP4_ADDR_7); + SYS(fail, "ip -6 route add %s/128 dev veth8", IP6_ADDR_7); + SYS(fail, "ip -6 route add %s/128 dev veth8 via %s", IP6_ADDR_5, IP6_ADDR_7); + SYS(fail, "ip -6 route add %s/128 dev veth8 via %s", IP6_ADDR_6, IP6_ADDR_7); + + /* Configure IPv4 GRE device */ + SYS(fail, "ip tunnel add gre_dev mode gre remote %s local %s ttl 255", + IP4_ADDR_1, IP4_ADDR_GRE); + SYS(fail, "ip link set gre_dev up"); + SYS(fail, "ip a add %s dev gre_dev", IP4_ADDR_GRE); + + /* Configure IPv6 GRE device */ + SYS(fail, "ip tunnel add gre6_dev mode ip6gre remote %s local %s ttl 255", + IP6_ADDR_1, IP6_ADDR_GRE); + SYS(fail, "ip link set gre6_dev up"); + SYS(fail, "ip a add %s dev gre6_dev", IP6_ADDR_GRE); + + close_netns(nstoken); + return 0; +fail: + close_netns(nstoken); + return -1; +} + +static int setup_network(char *ns1, char *ns2, char *ns3, const char *vrf) +{ + if (!ns1 || !ns2 || !ns3 || !vrf) + goto fail; + + SYS(fail, "ip -n %s link add veth1 type veth peer name veth2 netns %s", ns1, ns2); + SYS(fail, "ip -n %s link add veth3 type veth peer name veth4 netns %s", ns2, ns3); + SYS(fail, "ip -n %s link add veth5 type veth peer name veth6 netns %s", ns1, ns2); + SYS(fail, "ip -n %s link add veth7 type veth peer name veth8 netns %s", ns2, ns3); + + if (vrf[0]) { + if (!ASSERT_OK(configure_vrf(ns1, ns2), "configure vrf")) + goto fail; + } + if (!ASSERT_OK(set_top_addr(ns1, ns2, ns3), "set top addresses")) + goto fail; + + if (!ASSERT_OK(set_bottom_addr(ns1, ns2, ns3), "set bottom addresses")) + goto fail; + + if (!ASSERT_OK(configure_ns1(ns1, vrf), "configure ns1 routes")) + goto fail; + + if (!ASSERT_OK(configure_ns2(ns2, vrf), "configure ns2 routes")) + goto fail; + + if (!ASSERT_OK(configure_ns3(ns3), "configure ns3 routes")) + goto fail; + + /* Link bottom route to the GRE tunnels */ + SYS(fail, "ip -n %s route add %s/32 dev veth5 via %s %s", + ns1, IP4_ADDR_GRE, IP4_ADDR_6, vrf); + SYS(fail, "ip -n %s route add %s/32 dev veth7 via %s %s", + ns2, IP4_ADDR_GRE, IP4_ADDR_8, vrf); + SYS(fail, "ip -n %s -6 route add %s/128 dev veth5 via %s %s", + ns1, IP6_ADDR_GRE, IP6_ADDR_6, vrf); + SYS(fail, "ip -n %s -6 route add %s/128 dev veth7 via %s %s", + ns2, IP6_ADDR_GRE, IP6_ADDR_8, vrf); + + return 0; +fail: + return -1; +} + +static int remove_routes_to_gredev(const char *ns1, const char *ns2, const char *vrf) +{ + SYS(fail, "ip -n %s route del %s dev veth5 %s", ns1, IP4_ADDR_GRE, vrf); + SYS(fail, "ip -n %s route del %s dev veth7 %s", ns2, IP4_ADDR_GRE, vrf); + SYS(fail, "ip -n %s -6 route del %s/128 dev veth5 %s", ns1, IP6_ADDR_GRE, vrf); + SYS(fail, "ip -n %s -6 route del %s/128 dev veth7 %s", ns2, IP6_ADDR_GRE, vrf); + + return 0; +fail: + return -1; +} + +static int add_unreachable_routes_to_gredev(const char *ns1, const char *ns2, const char *vrf) +{ + SYS(fail, "ip -n %s route add unreachable %s/32 %s", ns1, IP4_ADDR_GRE, vrf); + SYS(fail, "ip -n %s route add unreachable %s/32 %s", ns2, IP4_ADDR_GRE, vrf); + SYS(fail, "ip -n %s -6 route add unreachable %s/128 %s", ns1, IP6_ADDR_GRE, vrf); + SYS(fail, "ip -n %s -6 route add unreachable %s/128 %s", ns2, IP6_ADDR_GRE, vrf); + + return 0; +fail: + return -1; +} + +#define GSO_SIZE 5000 +#define GSO_TCP_PORT 9000 +/* This tests the fix from commit ea0371f78799 ("net: fix GSO in bpf_lwt_push_ip_encap") */ +static int test_gso_fix(const char *ns1, const char *ns3, int family) +{ + const char *ip_addr = family == AF_INET ? IP4_ADDR_DST : IP6_ADDR_DST; + char gso_packet[GSO_SIZE] = {}; + struct nstoken *nstoken = NULL; + int sfd, cfd, afd; + ssize_t bytes; + int ret = -1; + + if (!ns1 || !ns3) + return ret; + + nstoken = open_netns(ns3); + if (!ASSERT_OK_PTR(nstoken, "open ns3")) + return ret; + + sfd = start_server_str(family, SOCK_STREAM, ip_addr, GSO_TCP_PORT, NULL); + if (!ASSERT_OK_FD(sfd, "start server")) + goto close_netns; + + close_netns(nstoken); + + nstoken = open_netns(ns1); + if (!ASSERT_OK_PTR(nstoken, "open ns1")) + goto close_server; + + cfd = connect_to_addr_str(family, SOCK_STREAM, ip_addr, GSO_TCP_PORT, NULL); + if (!ASSERT_OK_FD(cfd, "connect to server")) + goto close_server; + + close_netns(nstoken); + nstoken = NULL; + + afd = accept(sfd, NULL, NULL); + if (!ASSERT_OK_FD(afd, "accept")) + goto close_client; + + /* Send a packet larger than MTU */ + bytes = send(cfd, gso_packet, GSO_SIZE, 0); + if (!ASSERT_EQ(bytes, GSO_SIZE, "send packet")) + goto close_accept; + + /* Verify we received all expected bytes */ + bytes = read(afd, gso_packet, GSO_SIZE); + if (!ASSERT_EQ(bytes, GSO_SIZE, "receive packet")) + goto close_accept; + + ret = 0; + +close_accept: + close(afd); +close_client: + close(cfd); +close_server: + close(sfd); +close_netns: + close_netns(nstoken); + + return ret; +} + +static int check_ping_ok(const char *ns1) +{ + SYS(fail, "ip netns exec %s ping -c 1 -W1 -I veth1 %s > /dev/null", ns1, IP4_ADDR_DST); + SYS(fail, "ip netns exec %s ping6 -c 1 -W1 -I veth1 %s > /dev/null", ns1, IP6_ADDR_DST); + return 0; +fail: + return -1; +} + +static int check_ping_fails(const char *ns1) +{ + int ret; + + ret = SYS_NOFAIL("ip netns exec %s ping -c 1 -W1 -I veth1 %s", ns1, IP4_ADDR_DST); + if (!ret) + return -1; + + ret = SYS_NOFAIL("ip netns exec %s ping6 -c 1 -W1 -I veth1 %s", ns1, IP6_ADDR_DST); + if (!ret) + return -1; + + return 0; +} + +#define EGRESS true +#define INGRESS false +#define IPV4_ENCAP true +#define IPV6_ENCAP false +static void lwt_ip_encap(bool ipv4_encap, bool egress, const char *vrf) +{ + char ns1[NETNS_NAME_SIZE] = NETNS_BASE "-1-"; + char ns2[NETNS_NAME_SIZE] = NETNS_BASE "-2-"; + char ns3[NETNS_NAME_SIZE] = NETNS_BASE "-3-"; + char *sec = ipv4_encap ? "encap_gre" : "encap_gre6"; + + if (!vrf) + return; + + if (!ASSERT_OK(create_ns(ns1, NETNS_NAME_SIZE), "create ns1")) + goto out; + if (!ASSERT_OK(create_ns(ns2, NETNS_NAME_SIZE), "create ns2")) + goto out; + if (!ASSERT_OK(create_ns(ns3, NETNS_NAME_SIZE), "create ns3")) + goto out; + + if (!ASSERT_OK(setup_network(ns1, ns2, ns3, vrf), "setup network")) + goto out; + + /* By default, pings work */ + if (!ASSERT_OK(check_ping_ok(ns1), "ping OK")) + goto out; + + /* Remove NS2->DST routes, ping fails */ + SYS(out, "ip -n %s route del %s/32 dev veth3 %s", ns2, IP4_ADDR_DST, vrf); + SYS(out, "ip -n %s -6 route del %s/128 dev veth3 %s", ns2, IP6_ADDR_DST, vrf); + if (!ASSERT_OK(check_ping_fails(ns1), "ping expected fail")) + goto out; + + /* Install replacement routes (LWT/eBPF), pings succeed */ + if (egress) { + SYS(out, "ip -n %s route add %s encap bpf xmit obj %s sec %s dev veth1 %s", + ns1, IP4_ADDR_DST, BPF_FILE, sec, vrf); + SYS(out, "ip -n %s -6 route add %s encap bpf xmit obj %s sec %s dev veth1 %s", + ns1, IP6_ADDR_DST, BPF_FILE, sec, vrf); + } else { + SYS(out, "ip -n %s route add %s encap bpf in obj %s sec %s dev veth2 %s", + ns2, IP4_ADDR_DST, BPF_FILE, sec, vrf); + SYS(out, "ip -n %s -6 route add %s encap bpf in obj %s sec %s dev veth2 %s", + ns2, IP6_ADDR_DST, BPF_FILE, sec, vrf); + } + + if (!ASSERT_OK(check_ping_ok(ns1), "ping OK")) + goto out; + + /* Skip GSO tests with VRF: VRF routing needs properly assigned + * source IP/device, which is easy to do with ping but hard with TCP. + */ + if (egress && !vrf[0]) { + if (!ASSERT_OK(test_gso_fix(ns1, ns3, AF_INET), "test GSO")) + goto out; + } + + /* Negative test: remove routes to GRE devices: ping fails */ + if (!ASSERT_OK(remove_routes_to_gredev(ns1, ns2, vrf), "remove routes to gredev")) + goto out; + if (!ASSERT_OK(check_ping_fails(ns1), "ping expected fail")) + goto out; + + /* Another negative test */ + if (!ASSERT_OK(add_unreachable_routes_to_gredev(ns1, ns2, vrf), + "add unreachable routes")) + goto out; + ASSERT_OK(check_ping_fails(ns1), "ping expected fail"); + +out: + SYS_NOFAIL("ip netns del %s", ns1); + SYS_NOFAIL("ip netns del %s", ns2); + SYS_NOFAIL("ip netns del %s", ns3); +} + +void test_lwt_ip_encap_vrf_ipv6(void) +{ + if (test__start_subtest("egress")) + lwt_ip_encap(IPV6_ENCAP, EGRESS, "vrf red"); + + if (test__start_subtest("ingress")) + lwt_ip_encap(IPV6_ENCAP, INGRESS, "vrf red"); +} + +void test_lwt_ip_encap_vrf_ipv4(void) +{ + if (test__start_subtest("egress")) + lwt_ip_encap(IPV4_ENCAP, EGRESS, "vrf red"); + + if (test__start_subtest("ingress")) + lwt_ip_encap(IPV4_ENCAP, INGRESS, "vrf red"); +} + +void test_lwt_ip_encap_ipv6(void) +{ + if (test__start_subtest("egress")) + lwt_ip_encap(IPV6_ENCAP, EGRESS, ""); + + if (test__start_subtest("ingress")) + lwt_ip_encap(IPV6_ENCAP, INGRESS, ""); +} + +void test_lwt_ip_encap_ipv4(void) +{ + if (test__start_subtest("egress")) + lwt_ip_encap(IPV4_ENCAP, EGRESS, ""); + + if (test__start_subtest("ingress")) + lwt_ip_encap(IPV4_ENCAP, INGRESS, ""); +} diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c b/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c new file mode 100644 index 0000000..3bc730b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c @@ -0,0 +1,176 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* Connects 6 network namespaces through veths. + * Each NS may have different IPv6 global scope addresses : + * + * NS1 NS2 NS3 NS4 NS5 NS6 + * lo veth1 <-> veth2 veth3 <-> veth4 veth5 <-> veth6 lo veth7 <-> veth8 veth9 <-> veth10 lo + * fb00 ::1 ::12 ::21 ::34 ::43 ::56 ::65 ::78 ::87 ::910 ::109 ::6 + * fd00 ::4 + * fc42 ::1 + * + * All IPv6 packets going to fb00::/16 through NS2 will be encapsulated in a + * IPv6 header with a Segment Routing Header, with segments : + * fd00::1 -> fd00::2 -> fd00::3 -> fd00::4 + * + * 3 fd00::/16 IPv6 addresses are binded to seg6local End.BPF actions : + * - fd00::1 : add a TLV, change the flags and apply a End.X action to fc42::1 + * - fd00::2 : remove the TLV, change the flags, add a tag + * - fd00::3 : apply an End.T action to fd00::4, through routing table 117 + * + * fd00::4 is a simple Segment Routing node decapsulating the inner IPv6 packet. + * Each End.BPF action will validate the operations applied on the SRH by the + * previous BPF program in the chain, otherwise the packet is dropped. + * + * An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this + * datagram can be read on NS6 when binding to fb00::6. + */ + +#include "network_helpers.h" +#include "test_progs.h" + +#define NETNS_BASE "lwt-seg6local-" +#define BPF_FILE "test_lwt_seg6local.bpf.o" + +static void cleanup(void) +{ + int ns; + + for (ns = 1; ns < 7; ns++) + SYS_NOFAIL("ip netns del %s%d", NETNS_BASE, ns); +} + +static int setup(void) +{ + int ns; + + for (ns = 1; ns < 7; ns++) + SYS(fail, "ip netns add %s%d", NETNS_BASE, ns); + + SYS(fail, "ip -n %s6 link set dev lo up", NETNS_BASE); + + for (ns = 1; ns < 6; ns++) { + int local_id = ns * 2 - 1; + int peer_id = ns * 2; + int next_ns = ns + 1; + + SYS(fail, "ip -n %s%d link add veth%d type veth peer name veth%d netns %s%d", + NETNS_BASE, ns, local_id, peer_id, NETNS_BASE, next_ns); + + SYS(fail, "ip -n %s%d link set dev veth%d up", NETNS_BASE, ns, local_id); + SYS(fail, "ip -n %s%d link set dev veth%d up", NETNS_BASE, next_ns, peer_id); + + /* All link scope addresses to veths */ + SYS(fail, "ip -n %s%d -6 addr add fb00::%d%d/16 dev veth%d scope link", + NETNS_BASE, ns, local_id, peer_id, local_id); + SYS(fail, "ip -n %s%d -6 addr add fb00::%d%d/16 dev veth%d scope link", + NETNS_BASE, next_ns, peer_id, local_id, peer_id); + } + + + SYS(fail, "ip -n %s5 -6 route add fb00::109 table 117 dev veth9 scope link", NETNS_BASE); + + SYS(fail, "ip -n %s1 -6 addr add fb00::1/16 dev lo", NETNS_BASE); + SYS(fail, "ip -n %s1 -6 route add fb00::6 dev veth1 via fb00::21", NETNS_BASE); + + SYS(fail, "ip -n %s2 -6 route add fb00::6 encap bpf in obj %s sec encap_srh dev veth2", + NETNS_BASE, BPF_FILE); + SYS(fail, "ip -n %s2 -6 route add fd00::1 dev veth3 via fb00::43 scope link", NETNS_BASE); + + SYS(fail, "ip -n %s3 -6 route add fc42::1 dev veth5 via fb00::65", NETNS_BASE); + SYS(fail, + "ip -n %s3 -6 route add fd00::1 encap seg6local action End.BPF endpoint obj %s sec add_egr_x dev veth4", + NETNS_BASE, BPF_FILE); + + SYS(fail, + "ip -n %s4 -6 route add fd00::2 encap seg6local action End.BPF endpoint obj %s sec pop_egr dev veth6", + NETNS_BASE, BPF_FILE); + SYS(fail, "ip -n %s4 -6 addr add fc42::1 dev lo", NETNS_BASE); + SYS(fail, "ip -n %s4 -6 route add fd00::3 dev veth7 via fb00::87", NETNS_BASE); + + SYS(fail, "ip -n %s5 -6 route add fd00::4 table 117 dev veth9 via fb00::109", NETNS_BASE); + SYS(fail, + "ip -n %s5 -6 route add fd00::3 encap seg6local action End.BPF endpoint obj %s sec inspect_t dev veth8", + NETNS_BASE, BPF_FILE); + + SYS(fail, "ip -n %s6 -6 addr add fb00::6/16 dev lo", NETNS_BASE); + SYS(fail, "ip -n %s6 -6 addr add fd00::4/16 dev lo", NETNS_BASE); + + for (ns = 1; ns < 6; ns++) + SYS(fail, "ip netns exec %s%d sysctl -wq net.ipv6.conf.all.forwarding=1", + NETNS_BASE, ns); + + SYS(fail, "ip netns exec %s6 sysctl -wq net.ipv6.conf.all.seg6_enabled=1", NETNS_BASE); + SYS(fail, "ip netns exec %s6 sysctl -wq net.ipv6.conf.lo.seg6_enabled=1", NETNS_BASE); + SYS(fail, "ip netns exec %s6 sysctl -wq net.ipv6.conf.veth10.seg6_enabled=1", NETNS_BASE); + + return 0; +fail: + return -1; +} + +#define SERVER_PORT 7330 +#define CLIENT_PORT 2121 +void test_lwt_seg6local(void) +{ + struct sockaddr_in6 server_addr = {}; + const char *ns1 = NETNS_BASE "1"; + const char *ns6 = NETNS_BASE "6"; + struct nstoken *nstoken = NULL; + const char *foobar = "foobar"; + ssize_t bytes; + int sfd, cfd; + char buf[7]; + + if (!ASSERT_OK(setup(), "setup")) + goto out; + + nstoken = open_netns(ns6); + if (!ASSERT_OK_PTR(nstoken, "open ns6")) + goto out; + + sfd = start_server_str(AF_INET6, SOCK_DGRAM, "fb00::6", SERVER_PORT, NULL); + if (!ASSERT_OK_FD(sfd, "start server")) + goto close_netns; + + close_netns(nstoken); + + nstoken = open_netns(ns1); + if (!ASSERT_OK_PTR(nstoken, "open ns1")) + goto close_server; + + cfd = start_server_str(AF_INET6, SOCK_DGRAM, "fb00::1", CLIENT_PORT, NULL); + if (!ASSERT_OK_FD(cfd, "start client")) + goto close_server; + + close_netns(nstoken); + nstoken = NULL; + + /* Send a packet larger than MTU */ + server_addr.sin6_family = AF_INET6; + server_addr.sin6_port = htons(SERVER_PORT); + if (!ASSERT_EQ(inet_pton(AF_INET6, "fb00::6", &server_addr.sin6_addr), 1, + "build target addr")) + goto close_client; + + bytes = sendto(cfd, foobar, sizeof(foobar), 0, + (struct sockaddr *)&server_addr, sizeof(server_addr)); + if (!ASSERT_EQ(bytes, sizeof(foobar), "send packet")) + goto close_client; + + /* Verify we received all expected bytes */ + bytes = read(sfd, buf, sizeof(buf)); + if (!ASSERT_EQ(bytes, sizeof(buf), "receive packet")) + goto close_client; + ASSERT_STREQ(buf, foobar, "check udp packet"); + +close_client: + close(cfd); +close_server: + close(sfd); +close_netns: + close_netns(nstoken); + +out: + cleanup(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/netns_cookie.c b/tools/testing/selftests/bpf/prog_tests/netns_cookie.c index ac3c3c0..e00cd34 100644 --- a/tools/testing/selftests/bpf/prog_tests/netns_cookie.c +++ b/tools/testing/selftests/bpf/prog_tests/netns_cookie.c @@ -33,20 +33,25 @@ void test_netns_cookie(void) skel->links.get_netns_cookie_sockops = bpf_program__attach_cgroup( skel->progs.get_netns_cookie_sockops, cgroup_fd); - if (!ASSERT_OK_PTR(skel->links.get_netns_cookie_sockops, "prog_attach")) + if (!ASSERT_OK_PTR(skel->links.get_netns_cookie_sockops, "prog_attach_sockops")) goto done; verdict = bpf_program__fd(skel->progs.get_netns_cookie_sk_msg); map = bpf_map__fd(skel->maps.sock_map); err = bpf_prog_attach(verdict, map, BPF_SK_MSG_VERDICT, 0); - if (!ASSERT_OK(err, "prog_attach")) + if (!ASSERT_OK(err, "prog_attach_sk_msg")) goto done; tc_fd = bpf_program__fd(skel->progs.get_netns_cookie_tcx); err = bpf_prog_attach_opts(tc_fd, loopback, BPF_TCX_INGRESS, &opta); - if (!ASSERT_OK(err, "prog_attach")) + if (!ASSERT_OK(err, "prog_attach_tcx")) goto done; + skel->links.get_netns_cookie_cgroup_skb = bpf_program__attach_cgroup( + skel->progs.get_netns_cookie_cgroup_skb, cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.get_netns_cookie_cgroup_skb, "prog_attach_cgroup_skb")) + goto cleanup_tc; + server_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0); if (CHECK(server_fd < 0, "start_server", "errno %d\n", errno)) goto cleanup_tc; @@ -69,16 +74,18 @@ void test_netns_cookie(void) if (!ASSERT_OK(err, "getsockopt")) goto cleanup_tc; - ASSERT_EQ(val, cookie_expected_value, "cookie_value"); + ASSERT_EQ(val, cookie_expected_value, "cookie_value_sockops"); err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.sk_msg_netns_cookies), &client_fd, &val); if (!ASSERT_OK(err, "map_lookup(sk_msg_netns_cookies)")) goto cleanup_tc; - ASSERT_EQ(val, cookie_expected_value, "cookie_value"); - ASSERT_EQ(skel->bss->tcx_init_netns_cookie, cookie_expected_value, "cookie_value"); - ASSERT_EQ(skel->bss->tcx_netns_cookie, cookie_expected_value, "cookie_value"); + ASSERT_EQ(val, cookie_expected_value, "cookie_value_sk_msg"); + ASSERT_EQ(skel->bss->tcx_init_netns_cookie, cookie_expected_value, "cookie_value_init_tcx"); + ASSERT_EQ(skel->bss->tcx_netns_cookie, cookie_expected_value, "cookie_value_tcx"); + ASSERT_EQ(skel->bss->cgroup_skb_init_netns_cookie, cookie_expected_value, "cookie_value_init_cgroup_skb"); + ASSERT_EQ(skel->bss->cgroup_skb_netns_cookie, cookie_expected_value, "cookie_value_cgroup_skb"); cleanup_tc: err = bpf_prog_detach_opts(tc_fd, loopback, BPF_TCX_INGRESS, &optd); diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c index 761ce24..99c953f 100644 --- a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c +++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c @@ -200,41 +200,28 @@ static void test_ns_current_pid_tgid_new_ns(int (*fn)(void *), void *arg) return; } -static void test_in_netns(int (*fn)(void *), void *arg) -{ - struct nstoken *nstoken = NULL; - - SYS(cleanup, "ip netns add ns_current_pid_tgid"); - SYS(cleanup, "ip -net ns_current_pid_tgid link set dev lo up"); - - nstoken = open_netns("ns_current_pid_tgid"); - if (!ASSERT_OK_PTR(nstoken, "open_netns")) - goto cleanup; - - test_ns_current_pid_tgid_new_ns(fn, arg); - -cleanup: - if (nstoken) - close_netns(nstoken); - SYS_NOFAIL("ip netns del ns_current_pid_tgid"); -} - /* TODO: use a different tracepoint */ -void serial_test_ns_current_pid_tgid(void) +void serial_test_current_pid_tgid(void) { if (test__start_subtest("root_ns_tp")) test_current_pid_tgid_tp(NULL); if (test__start_subtest("new_ns_tp")) test_ns_current_pid_tgid_new_ns(test_current_pid_tgid_tp, NULL); - if (test__start_subtest("new_ns_cgrp")) { - int cgroup_fd = -1; - - cgroup_fd = test__join_cgroup("/sock_addr"); - if (ASSERT_GE(cgroup_fd, 0, "join_cgroup")) { - test_in_netns(test_current_pid_tgid_cgrp, &cgroup_fd); - close(cgroup_fd); - } +} + +void test_ns_current_pid_tgid_cgrp(void) +{ + int cgroup_fd = test__join_cgroup("/sock_addr"); + + if (ASSERT_OK_FD(cgroup_fd, "join_cgroup")) { + test_ns_current_pid_tgid_new_ns(test_current_pid_tgid_cgrp, &cgroup_fd); + close(cgroup_fd); } - if (test__start_subtest("new_ns_sk_msg")) - test_in_netns(test_current_pid_tgid_sk_msg, NULL); } + +void test_ns_current_pid_tgid_sk_msg(void) +{ + test_ns_current_pid_tgid_new_ns(test_current_pid_tgid_sk_msg, NULL); +} + + diff --git a/tools/testing/selftests/bpf/prog_tests/prepare.c b/tools/testing/selftests/bpf/prog_tests/prepare.c new file mode 100644 index 0000000..fb5cdad --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/prepare.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta */ + +#include +#include +#include "prepare.skel.h" + +static bool check_prepared(struct bpf_object *obj) +{ + bool is_prepared = true; + const struct bpf_map *map; + + bpf_object__for_each_map(map, obj) { + if (bpf_map__fd(map) < 0) + is_prepared = false; + } + + return is_prepared; +} + +static void test_prepare_no_load(void) +{ + struct prepare *skel; + int err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + ); + + skel = prepare__open(); + if (!ASSERT_OK_PTR(skel, "prepare__open")) + return; + + if (!ASSERT_FALSE(check_prepared(skel->obj), "not check_prepared")) + goto cleanup; + + err = bpf_object__prepare(skel->obj); + + if (!ASSERT_TRUE(check_prepared(skel->obj), "check_prepared")) + goto cleanup; + + if (!ASSERT_OK(err, "bpf_object__prepare")) + goto cleanup; + +cleanup: + prepare__destroy(skel); +} + +static void test_prepare_load(void) +{ + struct prepare *skel; + int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + ); + + skel = prepare__open(); + if (!ASSERT_OK_PTR(skel, "prepare__open")) + return; + + if (!ASSERT_FALSE(check_prepared(skel->obj), "not check_prepared")) + goto cleanup; + + err = bpf_object__prepare(skel->obj); + if (!ASSERT_OK(err, "bpf_object__prepare")) + goto cleanup; + + err = prepare__load(skel); + if (!ASSERT_OK(err, "prepare__load")) + goto cleanup; + + if (!ASSERT_TRUE(check_prepared(skel->obj), "check_prepared")) + goto cleanup; + + prog_fd = bpf_program__fd(skel->progs.program); + if (!ASSERT_GE(prog_fd, 0, "prog_fd")) + goto cleanup; + + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + goto cleanup; + + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + goto cleanup; + + ASSERT_EQ(skel->bss->err, 0, "err"); + +cleanup: + prepare__destroy(skel); +} + +void test_prepare(void) +{ + if (test__start_subtest("prepare_load")) + test_prepare_load(); + if (test__start_subtest("prepare_no_load")) + test_prepare_no_load(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/pro_epilogue.c b/tools/testing/selftests/bpf/prog_tests/pro_epilogue.c index 509883e..5d3c00a 100644 --- a/tools/testing/selftests/bpf/prog_tests/pro_epilogue.c +++ b/tools/testing/selftests/bpf/prog_tests/pro_epilogue.c @@ -6,6 +6,7 @@ #include "epilogue_tailcall.skel.h" #include "pro_epilogue_goto_start.skel.h" #include "epilogue_exit.skel.h" +#include "pro_epilogue_with_kfunc.skel.h" struct st_ops_args { __u64 a; @@ -55,6 +56,7 @@ void test_pro_epilogue(void) RUN_TESTS(pro_epilogue); RUN_TESTS(pro_epilogue_goto_start); RUN_TESTS(epilogue_exit); + RUN_TESTS(pro_epilogue_with_kfunc); if (test__start_subtest("tailcall")) test_tailcall(); } diff --git a/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c b/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c index ebe0c12..c9f855e 100644 --- a/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c @@ -81,6 +81,9 @@ static const char * const inproper_region_tests[] = { "nested_rcu_region", "rcu_read_lock_global_subprog_lock", "rcu_read_lock_global_subprog_unlock", + "rcu_read_lock_sleepable_helper_global_subprog", + "rcu_read_lock_sleepable_kfunc_global_subprog", + "rcu_read_lock_sleepable_global_subprog_indirect", }; static void test_inproper_region(void) diff --git a/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c index c7b9ba8..a8d1eaa 100644 --- a/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c +++ b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c @@ -24,6 +24,7 @@ struct read_ret_desc { { .name = "copy_from_user", .ret = -EFAULT }, { .name = "copy_from_user_task", .ret = -EFAULT }, { .name = "copy_from_user_str", .ret = -EFAULT }, + { .name = "copy_from_user_task_str", .ret = -EFAULT }, }; void test_read_vsyscall(void) diff --git a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c index e122551..e4dac52 100644 --- a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c +++ b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c @@ -202,7 +202,7 @@ err_out: void test_setget_sockopt(void) { cg_fd = test__join_cgroup(CG_NAME); - if (cg_fd < 0) + if (!ASSERT_OK_FD(cg_fd, "join cgroup")) return; if (create_netns()) diff --git a/tools/testing/selftests/bpf/prog_tests/spin_lock.c b/tools/testing/selftests/bpf/prog_tests/spin_lock.c index 2b00687..e3ea5dc 100644 --- a/tools/testing/selftests/bpf/prog_tests/spin_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/spin_lock.c @@ -50,6 +50,9 @@ static struct { { "lock_id_mismatch_innermapval_mapval", "bpf_spin_unlock of different lock" }, { "lock_global_subprog_call1", "global function calls are not allowed while holding a lock" }, { "lock_global_subprog_call2", "global function calls are not allowed while holding a lock" }, + { "lock_global_sleepable_helper_subprog", "global function calls are not allowed while holding a lock" }, + { "lock_global_sleepable_kfunc_subprog", "global function calls are not allowed while holding a lock" }, + { "lock_global_sleepable_subprog_indirect", "global function calls are not allowed while holding a lock" }, }; static int match_regex(const char *pattern, const char *string) diff --git a/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c b/tools/testing/selftests/bpf/prog_tests/summarization.c similarity index 56% rename from tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c rename to tools/testing/selftests/bpf/prog_tests/summarization.c index 7526de3..5dd6c12 100644 --- a/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c +++ b/tools/testing/selftests/bpf/prog_tests/summarization.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "bpf/libbpf.h" -#include "changes_pkt_data_freplace.skel.h" -#include "changes_pkt_data.skel.h" +#include "summarization_freplace.skel.h" +#include "summarization.skel.h" #include static void print_verifier_log(const char *log) @@ -13,13 +13,14 @@ static void print_verifier_log(const char *log) static void test_aux(const char *main_prog_name, const char *to_be_replaced, const char *replacement, - bool expect_load) + bool expect_load, + const char *err_msg) { - struct changes_pkt_data_freplace *freplace = NULL; + struct summarization_freplace *freplace = NULL; struct bpf_program *freplace_prog = NULL; struct bpf_program *main_prog = NULL; LIBBPF_OPTS(bpf_object_open_opts, opts); - struct changes_pkt_data *main = NULL; + struct summarization *main = NULL; char log[16*1024]; int err; @@ -27,19 +28,19 @@ static void test_aux(const char *main_prog_name, opts.kernel_log_size = sizeof(log); if (env.verbosity >= VERBOSE_SUPER) opts.kernel_log_level = 1 | 2 | 4; - main = changes_pkt_data__open_opts(&opts); - if (!ASSERT_OK_PTR(main, "changes_pkt_data__open")) + main = summarization__open_opts(&opts); + if (!ASSERT_OK_PTR(main, "summarization__open")) goto out; main_prog = bpf_object__find_program_by_name(main->obj, main_prog_name); if (!ASSERT_OK_PTR(main_prog, "main_prog")) goto out; bpf_program__set_autoload(main_prog, true); - err = changes_pkt_data__load(main); + err = summarization__load(main); print_verifier_log(log); - if (!ASSERT_OK(err, "changes_pkt_data__load")) + if (!ASSERT_OK(err, "summarization__load")) goto out; - freplace = changes_pkt_data_freplace__open_opts(&opts); - if (!ASSERT_OK_PTR(freplace, "changes_pkt_data_freplace__open")) + freplace = summarization_freplace__open_opts(&opts); + if (!ASSERT_OK_PTR(freplace, "summarization_freplace__open")) goto out; freplace_prog = bpf_object__find_program_by_name(freplace->obj, replacement); if (!ASSERT_OK_PTR(freplace_prog, "freplace_prog")) @@ -49,21 +50,33 @@ static void test_aux(const char *main_prog_name, bpf_program__set_attach_target(freplace_prog, bpf_program__fd(main_prog), to_be_replaced); - err = changes_pkt_data_freplace__load(freplace); + err = summarization_freplace__load(freplace); print_verifier_log(log); + + /* The might_sleep extension doesn't work yet as sleepable calls are not + * allowed, but preserve the check in case it's supported later and then + * this particular combination can be enabled. + */ + if (!strcmp("might_sleep", replacement) && err) { + ASSERT_HAS_SUBSTR(log, "helper call might sleep in a non-sleepable prog", "error log"); + ASSERT_EQ(err, -EINVAL, "err"); + test__skip(); + goto out; + } + if (expect_load) { - ASSERT_OK(err, "changes_pkt_data_freplace__load"); + ASSERT_OK(err, "summarization_freplace__load"); } else { - ASSERT_ERR(err, "changes_pkt_data_freplace__load"); - ASSERT_HAS_SUBSTR(log, "Extension program changes packet data", "error log"); + ASSERT_ERR(err, "summarization_freplace__load"); + ASSERT_HAS_SUBSTR(log, err_msg, "error log"); } out: - changes_pkt_data_freplace__destroy(freplace); - changes_pkt_data__destroy(main); + summarization_freplace__destroy(freplace); + summarization__destroy(main); } -/* There are two global subprograms in both changes_pkt_data.skel.h: +/* There are two global subprograms in both summarization.skel.h: * - one changes packet data; * - another does not. * It is ok to freplace subprograms that change packet data with those @@ -72,36 +85,60 @@ out: * The below tests check outcomes for each combination of such freplace. * Also test a case when main subprogram itself is replaced and is a single * subprogram in a program. + * + * This holds for might_sleep programs. It is ok to replace might_sleep with + * might_sleep and with does_not_sleep, but does_not_sleep cannot be replaced + * with might_sleep. */ -void test_changes_pkt_data_freplace(void) +void test_summarization_freplace(void) { struct { const char *main; const char *to_be_replaced; - bool changes; - } mains[] = { - { "main_with_subprogs", "changes_pkt_data", true }, - { "main_with_subprogs", "does_not_change_pkt_data", false }, - { "main_changes", "main_changes", true }, - { "main_does_not_change", "main_does_not_change", false }, + bool has_side_effect; + } mains[2][4] = { + { + { "main_changes_with_subprogs", "changes_pkt_data", true }, + { "main_changes_with_subprogs", "does_not_change_pkt_data", false }, + { "main_changes", "main_changes", true }, + { "main_does_not_change", "main_does_not_change", false }, + }, + { + { "main_might_sleep_with_subprogs", "might_sleep", true }, + { "main_might_sleep_with_subprogs", "does_not_sleep", false }, + { "main_might_sleep", "main_might_sleep", true }, + { "main_does_not_sleep", "main_does_not_sleep", false }, + }, }; + const char *pkt_err = "Extension program changes packet data"; + const char *slp_err = "Extension program may sleep"; struct { const char *func; - bool changes; - } replacements[] = { - { "changes_pkt_data", true }, - { "does_not_change_pkt_data", false } + bool has_side_effect; + const char *err_msg; + } replacements[2][2] = { + { + { "changes_pkt_data", true, pkt_err }, + { "does_not_change_pkt_data", false, pkt_err }, + }, + { + { "might_sleep", true, slp_err }, + { "does_not_sleep", false, slp_err }, + }, }; char buf[64]; - for (int i = 0; i < ARRAY_SIZE(mains); ++i) { - for (int j = 0; j < ARRAY_SIZE(replacements); ++j) { - snprintf(buf, sizeof(buf), "%s_with_%s", - mains[i].to_be_replaced, replacements[j].func); - if (!test__start_subtest(buf)) - continue; - test_aux(mains[i].main, mains[i].to_be_replaced, replacements[j].func, - mains[i].changes || !replacements[j].changes); + for (int t = 0; t < 2; t++) { + for (int i = 0; i < ARRAY_SIZE(mains); ++i) { + for (int j = 0; j < ARRAY_SIZE(replacements); ++j) { + snprintf(buf, sizeof(buf), "%s_with_%s", + mains[t][i].to_be_replaced, replacements[t][j].func); + if (!test__start_subtest(buf)) + continue; + test_aux(mains[t][i].main, mains[t][i].to_be_replaced, replacements[t][j].func, + mains[t][i].has_side_effect || !replacements[t][j].has_side_effect, + replacements[t][j].err_msg); + } } } } diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c index 5441446..66a9003 100644 --- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c +++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c @@ -1600,6 +1600,7 @@ static void test_tailcall_bpf2bpf_freplace(void) goto out; err = bpf_link__destroy(freplace_link); + freplace_link = NULL; if (!ASSERT_OK(err, "destroy link")) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/tc_links.c b/tools/testing/selftests/bpf/prog_tests/tc_links.c index 1af9ec1..2186a24 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_links.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_links.c @@ -13,7 +13,7 @@ #include "netlink_helpers.h" #include "tc_helpers.h" -void serial_test_tc_links_basic(void) +void test_ns_tc_links_basic(void) { LIBBPF_OPTS(bpf_prog_query_opts, optq); LIBBPF_OPTS(bpf_tcx_opts, optl); @@ -260,7 +260,7 @@ cleanup: assert_mprog_count(target, 0); } -void serial_test_tc_links_before(void) +void test_ns_tc_links_before(void) { test_tc_links_before_target(BPF_TCX_INGRESS); test_tc_links_before_target(BPF_TCX_EGRESS); @@ -414,7 +414,7 @@ cleanup: assert_mprog_count(target, 0); } -void serial_test_tc_links_after(void) +void test_ns_tc_links_after(void) { test_tc_links_after_target(BPF_TCX_INGRESS); test_tc_links_after_target(BPF_TCX_EGRESS); @@ -514,7 +514,7 @@ cleanup: assert_mprog_count(target, 0); } -void serial_test_tc_links_revision(void) +void test_ns_tc_links_revision(void) { test_tc_links_revision_target(BPF_TCX_INGRESS); test_tc_links_revision_target(BPF_TCX_EGRESS); @@ -618,7 +618,7 @@ cleanup: assert_mprog_count(target, 0); } -void serial_test_tc_links_chain_classic(void) +void test_ns_tc_links_chain_classic(void) { test_tc_chain_classic(BPF_TCX_INGRESS, false); test_tc_chain_classic(BPF_TCX_EGRESS, false); @@ -846,7 +846,7 @@ cleanup: assert_mprog_count(target, 0); } -void serial_test_tc_links_replace(void) +void test_ns_tc_links_replace(void) { test_tc_links_replace_target(BPF_TCX_INGRESS); test_tc_links_replace_target(BPF_TCX_EGRESS); @@ -1158,7 +1158,7 @@ cleanup: assert_mprog_count(target, 0); } -void serial_test_tc_links_invalid(void) +void test_ns_tc_links_invalid(void) { test_tc_links_invalid_target(BPF_TCX_INGRESS); test_tc_links_invalid_target(BPF_TCX_EGRESS); @@ -1314,7 +1314,7 @@ cleanup: assert_mprog_count(target, 0); } -void serial_test_tc_links_prepend(void) +void test_ns_tc_links_prepend(void) { test_tc_links_prepend_target(BPF_TCX_INGRESS); test_tc_links_prepend_target(BPF_TCX_EGRESS); @@ -1470,7 +1470,7 @@ cleanup: assert_mprog_count(target, 0); } -void serial_test_tc_links_append(void) +void test_ns_tc_links_append(void) { test_tc_links_append_target(BPF_TCX_INGRESS); test_tc_links_append_target(BPF_TCX_EGRESS); @@ -1568,7 +1568,7 @@ cleanup: ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed"); } -void serial_test_tc_links_dev_cleanup(void) +void test_ns_tc_links_dev_cleanup(void) { test_tc_links_dev_cleanup_target(BPF_TCX_INGRESS); test_tc_links_dev_cleanup_target(BPF_TCX_EGRESS); @@ -1672,7 +1672,7 @@ cleanup: test_tc_link__destroy(skel); } -void serial_test_tc_links_chain_mixed(void) +void test_ns_tc_links_chain_mixed(void) { test_tc_chain_mixed(BPF_TCX_INGRESS); test_tc_chain_mixed(BPF_TCX_EGRESS); @@ -1782,7 +1782,7 @@ cleanup: assert_mprog_count(target, 0); } -void serial_test_tc_links_ingress(void) +void test_ns_tc_links_ingress(void) { test_tc_links_ingress(BPF_TCX_INGRESS, true, true); test_tc_links_ingress(BPF_TCX_INGRESS, true, false); @@ -1823,7 +1823,7 @@ static int qdisc_replace(int ifindex, const char *kind, bool block) return err; } -void serial_test_tc_links_dev_chain0(void) +void test_ns_tc_links_dev_chain0(void) { int err, ifindex; @@ -1955,7 +1955,7 @@ cleanup: ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed"); } -void serial_test_tc_links_dev_mixed(void) +void test_ns_tc_links_dev_mixed(void) { test_tc_links_dev_mixed(BPF_TCX_INGRESS); test_tc_links_dev_mixed(BPF_TCX_EGRESS); diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c index f77f604..dd7a138 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c @@ -10,7 +10,7 @@ #include "test_tc_link.skel.h" #include "tc_helpers.h" -void serial_test_tc_opts_basic(void) +void test_ns_tc_opts_basic(void) { LIBBPF_OPTS(bpf_prog_attach_opts, opta); LIBBPF_OPTS(bpf_prog_detach_opts, optd); @@ -254,7 +254,7 @@ cleanup: test_tc_link__destroy(skel); } -void serial_test_tc_opts_before(void) +void test_ns_tc_opts_before(void) { test_tc_opts_before_target(BPF_TCX_INGRESS); test_tc_opts_before_target(BPF_TCX_EGRESS); @@ -445,7 +445,7 @@ cleanup: test_tc_link__destroy(skel); } -void serial_test_tc_opts_after(void) +void test_ns_tc_opts_after(void) { test_tc_opts_after_target(BPF_TCX_INGRESS); test_tc_opts_after_target(BPF_TCX_EGRESS); @@ -554,7 +554,7 @@ cleanup: test_tc_link__destroy(skel); } -void serial_test_tc_opts_revision(void) +void test_ns_tc_opts_revision(void) { test_tc_opts_revision_target(BPF_TCX_INGRESS); test_tc_opts_revision_target(BPF_TCX_EGRESS); @@ -655,7 +655,7 @@ cleanup: assert_mprog_count(target, 0); } -void serial_test_tc_opts_chain_classic(void) +void test_ns_tc_opts_chain_classic(void) { test_tc_chain_classic(BPF_TCX_INGRESS, false); test_tc_chain_classic(BPF_TCX_EGRESS, false); @@ -864,7 +864,7 @@ cleanup: test_tc_link__destroy(skel); } -void serial_test_tc_opts_replace(void) +void test_ns_tc_opts_replace(void) { test_tc_opts_replace_target(BPF_TCX_INGRESS); test_tc_opts_replace_target(BPF_TCX_EGRESS); @@ -1017,7 +1017,7 @@ cleanup: test_tc_link__destroy(skel); } -void serial_test_tc_opts_invalid(void) +void test_ns_tc_opts_invalid(void) { test_tc_opts_invalid_target(BPF_TCX_INGRESS); test_tc_opts_invalid_target(BPF_TCX_EGRESS); @@ -1157,7 +1157,7 @@ cleanup: test_tc_link__destroy(skel); } -void serial_test_tc_opts_prepend(void) +void test_ns_tc_opts_prepend(void) { test_tc_opts_prepend_target(BPF_TCX_INGRESS); test_tc_opts_prepend_target(BPF_TCX_EGRESS); @@ -1297,7 +1297,7 @@ cleanup: test_tc_link__destroy(skel); } -void serial_test_tc_opts_append(void) +void test_ns_tc_opts_append(void) { test_tc_opts_append_target(BPF_TCX_INGRESS); test_tc_opts_append_target(BPF_TCX_EGRESS); @@ -1387,7 +1387,7 @@ cleanup: ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed"); } -void serial_test_tc_opts_dev_cleanup(void) +void test_ns_tc_opts_dev_cleanup(void) { test_tc_opts_dev_cleanup_target(BPF_TCX_INGRESS); test_tc_opts_dev_cleanup_target(BPF_TCX_EGRESS); @@ -1563,7 +1563,7 @@ cleanup: assert_mprog_count(target, 0); } -void serial_test_tc_opts_mixed(void) +void test_ns_tc_opts_mixed(void) { test_tc_opts_mixed_target(BPF_TCX_INGRESS); test_tc_opts_mixed_target(BPF_TCX_EGRESS); @@ -1642,7 +1642,7 @@ cleanup: assert_mprog_count(target, 0); } -void serial_test_tc_opts_demixed(void) +void test_ns_tc_opts_demixed(void) { test_tc_opts_demixed_target(BPF_TCX_INGRESS); test_tc_opts_demixed_target(BPF_TCX_EGRESS); @@ -1813,7 +1813,7 @@ cleanup: test_tc_link__destroy(skel); } -void serial_test_tc_opts_detach(void) +void test_ns_tc_opts_detach(void) { test_tc_opts_detach_target(BPF_TCX_INGRESS); test_tc_opts_detach_target(BPF_TCX_EGRESS); @@ -2020,7 +2020,7 @@ cleanup: test_tc_link__destroy(skel); } -void serial_test_tc_opts_detach_before(void) +void test_ns_tc_opts_detach_before(void) { test_tc_opts_detach_before_target(BPF_TCX_INGRESS); test_tc_opts_detach_before_target(BPF_TCX_EGRESS); @@ -2236,7 +2236,7 @@ cleanup: test_tc_link__destroy(skel); } -void serial_test_tc_opts_detach_after(void) +void test_ns_tc_opts_detach_after(void) { test_tc_opts_detach_after_target(BPF_TCX_INGRESS); test_tc_opts_detach_after_target(BPF_TCX_EGRESS); @@ -2265,7 +2265,7 @@ static void test_tc_opts_delete_empty(int target, bool chain_tc_old) assert_mprog_count(target, 0); } -void serial_test_tc_opts_delete_empty(void) +void test_ns_tc_opts_delete_empty(void) { test_tc_opts_delete_empty(BPF_TCX_INGRESS, false); test_tc_opts_delete_empty(BPF_TCX_EGRESS, false); @@ -2372,7 +2372,7 @@ cleanup: test_tc_link__destroy(skel); } -void serial_test_tc_opts_chain_mixed(void) +void test_ns_tc_opts_chain_mixed(void) { test_tc_chain_mixed(BPF_TCX_INGRESS); test_tc_chain_mixed(BPF_TCX_EGRESS); @@ -2446,7 +2446,7 @@ cleanup: ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed"); } -void serial_test_tc_opts_max(void) +void test_ns_tc_opts_max(void) { test_tc_opts_max_target(BPF_TCX_INGRESS, 0, false); test_tc_opts_max_target(BPF_TCX_EGRESS, 0, false); @@ -2748,7 +2748,7 @@ cleanup: test_tc_link__destroy(skel); } -void serial_test_tc_opts_query(void) +void test_ns_tc_opts_query(void) { test_tc_opts_query_target(BPF_TCX_INGRESS); test_tc_opts_query_target(BPF_TCX_EGRESS); @@ -2807,7 +2807,7 @@ cleanup: test_tc_link__destroy(skel); } -void serial_test_tc_opts_query_attach(void) +void test_ns_tc_opts_query_attach(void) { test_tc_opts_query_attach_target(BPF_TCX_INGRESS); test_tc_opts_query_attach_target(BPF_TCX_EGRESS); diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_kptr_return.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_kptr_return.c new file mode 100644 index 0000000..467cc72 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_kptr_return.c @@ -0,0 +1,16 @@ +#include + +#include "struct_ops_kptr_return.skel.h" +#include "struct_ops_kptr_return_fail__wrong_type.skel.h" +#include "struct_ops_kptr_return_fail__invalid_scalar.skel.h" +#include "struct_ops_kptr_return_fail__nonzero_offset.skel.h" +#include "struct_ops_kptr_return_fail__local_kptr.skel.h" + +void test_struct_ops_kptr_return(void) +{ + RUN_TESTS(struct_ops_kptr_return); + RUN_TESTS(struct_ops_kptr_return_fail__wrong_type); + RUN_TESTS(struct_ops_kptr_return_fail__invalid_scalar); + RUN_TESTS(struct_ops_kptr_return_fail__nonzero_offset); + RUN_TESTS(struct_ops_kptr_return_fail__local_kptr); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_refcounted.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_refcounted.c new file mode 100644 index 0000000..da60c71 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_refcounted.c @@ -0,0 +1,14 @@ +#include + +#include "struct_ops_refcounted.skel.h" +#include "struct_ops_refcounted_fail__ref_leak.skel.h" +#include "struct_ops_refcounted_fail__global_subprog.skel.h" +#include "struct_ops_refcounted_fail__tail_call.skel.h" + +void test_struct_ops_refcounted(void) +{ + RUN_TESTS(struct_ops_refcounted); + RUN_TESTS(struct_ops_refcounted_fail__ref_leak); + RUN_TESTS(struct_ops_refcounted_fail__global_subprog); + RUN_TESTS(struct_ops_refcounted_fail__tail_call); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c index cec746e..bae0e9d 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c +++ b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c @@ -71,6 +71,8 @@ #define IP4_ADDR2_VETH1 "172.16.1.20" #define IP4_ADDR_TUNL_DEV0 "10.1.1.100" #define IP4_ADDR_TUNL_DEV1 "10.1.1.200" +#define IP6_ADDR_TUNL_DEV0 "fc80::100" +#define IP6_ADDR_TUNL_DEV1 "fc80::200" #define IP6_ADDR_VETH0 "::11" #define IP6_ADDR1_VETH1 "::22" @@ -98,6 +100,27 @@ #define XFRM_SPI_IN_TO_OUT 0x1 #define XFRM_SPI_OUT_TO_IN 0x2 +#define GRE_TUNL_DEV0 "gre00" +#define GRE_TUNL_DEV1 "gre11" + +#define IP6GRE_TUNL_DEV0 "ip6gre00" +#define IP6GRE_TUNL_DEV1 "ip6gre11" + +#define ERSPAN_TUNL_DEV0 "erspan00" +#define ERSPAN_TUNL_DEV1 "erspan11" + +#define IP6ERSPAN_TUNL_DEV0 "ip6erspan00" +#define IP6ERSPAN_TUNL_DEV1 "ip6erspan11" + +#define GENEVE_TUNL_DEV0 "geneve00" +#define GENEVE_TUNL_DEV1 "geneve11" + +#define IP6GENEVE_TUNL_DEV0 "ip6geneve00" +#define IP6GENEVE_TUNL_DEV1 "ip6geneve11" + +#define IP6TNL_TUNL_DEV0 "ip6tnl00" +#define IP6TNL_TUNL_DEV1 "ip6tnl11" + #define PING_ARGS "-i 0.01 -c 3 -w 10 -q" static int config_device(void) @@ -216,6 +239,18 @@ fail: return -1; } +static int set_ipv4_addr(const char *dev0, const char *dev1) +{ + SYS(fail, "ip -n at_ns0 link set dev %s up", dev0); + SYS(fail, "ip -n at_ns0 addr add dev %s %s/24", dev0, IP4_ADDR_TUNL_DEV0); + SYS(fail, "ip link set dev %s up", dev1); + SYS(fail, "ip addr add dev %s %s/24", dev1, IP4_ADDR_TUNL_DEV1); + + return 0; +fail: + return 1; +} + static int add_ipip_tunnel(enum ipip_encap encap) { int err; @@ -356,6 +391,99 @@ static void delete_xfrm_tunnel(void) IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN); } +static int add_ipv4_tunnel(const char *dev0, const char *dev1, + const char *type, const char *opt) +{ + if (!type || !opt || !dev0 || !dev1) + return -1; + + SYS(fail, "ip -n at_ns0 link add dev %s type %s %s local %s remote %s", + dev0, type, opt, IP4_ADDR_VETH0, IP4_ADDR1_VETH1); + + SYS(fail, "ip link add dev %s type %s external", dev1, type); + + return set_ipv4_addr(dev0, dev1); +fail: + return -1; +} + +static void delete_tunnel(const char *dev0, const char *dev1) +{ + if (!dev0 || !dev1) + return; + + SYS_NOFAIL("ip netns exec at_ns0 ip link delete dev %s", dev0); + SYS_NOFAIL("ip link delete dev %s", dev1); +} + +static int set_ipv6_addr(const char *dev0, const char *dev1) +{ + /* disable IPv6 DAD because it might take too long and fail tests */ + SYS(fail, "ip -n at_ns0 addr add %s/96 dev veth0 nodad", IP6_ADDR_VETH0); + SYS(fail, "ip -n at_ns0 link set dev veth0 up"); + SYS(fail, "ip addr add %s/96 dev veth1 nodad", IP6_ADDR1_VETH1); + SYS(fail, "ip link set dev veth1 up"); + + SYS(fail, "ip -n at_ns0 addr add dev %s %s/24", dev0, IP4_ADDR_TUNL_DEV0); + SYS(fail, "ip -n at_ns0 addr add dev %s %s/96 nodad", dev0, IP6_ADDR_TUNL_DEV0); + SYS(fail, "ip -n at_ns0 link set dev %s up", dev0); + + SYS(fail, "ip addr add dev %s %s/24", dev1, IP4_ADDR_TUNL_DEV1); + SYS(fail, "ip addr add dev %s %s/96 nodad", dev1, IP6_ADDR_TUNL_DEV1); + SYS(fail, "ip link set dev %s up", dev1); + return 0; +fail: + return 1; +} + +static int add_ipv6_tunnel(const char *dev0, const char *dev1, + const char *type, const char *opt) +{ + if (!type || !opt || !dev0 || !dev1) + return -1; + + SYS(fail, "ip -n at_ns0 link add dev %s type %s %s local %s remote %s", + dev0, type, opt, IP6_ADDR_VETH0, IP6_ADDR1_VETH1); + + SYS(fail, "ip link add dev %s type %s external", dev1, type); + + return set_ipv6_addr(dev0, dev1); +fail: + return -1; +} + +static int add_geneve_tunnel(const char *dev0, const char *dev1, + const char *type, const char *opt) +{ + if (!type || !opt || !dev0 || !dev1) + return -1; + + SYS(fail, "ip -n at_ns0 link add dev %s type %s id 2 %s remote %s", + dev0, type, opt, IP4_ADDR1_VETH1); + + SYS(fail, "ip link add dev %s type %s %s external", dev1, type, opt); + + return set_ipv4_addr(dev0, dev1); +fail: + return -1; +} + +static int add_ip6geneve_tunnel(const char *dev0, const char *dev1, + const char *type, const char *opt) +{ + if (!type || !opt || !dev0 || !dev1) + return -1; + + SYS(fail, "ip -n at_ns0 link add dev %s type %s id 22 %s remote %s", + dev0, type, opt, IP6_ADDR1_VETH1); + + SYS(fail, "ip link add dev %s type %s %s external", dev1, type, opt); + + return set_ipv6_addr(dev0, dev1); +fail: + return -1; +} + static int test_ping(int family, const char *addr) { SYS(fail, "%s %s %s > /dev/null", ping_command(family), PING_ARGS, addr); @@ -364,32 +492,76 @@ fail: return -1; } -static int attach_tc_prog(struct bpf_tc_hook *hook, int igr_fd, int egr_fd) +static void ping_dev0(void) { + /* ping from root namespace test */ + test_ping(AF_INET, IP4_ADDR_TUNL_DEV0); +} + +static void ping_dev1(void) +{ + struct nstoken *nstoken; + + /* ping from at_ns0 namespace test */ + nstoken = open_netns("at_ns0"); + if (!ASSERT_OK_PTR(nstoken, "setns")) + return; + + test_ping(AF_INET, IP4_ADDR_TUNL_DEV1); + close_netns(nstoken); +} + +static void ping6_veth0(void) +{ + test_ping(AF_INET6, IP6_ADDR_VETH0); +} + +static void ping6_dev0(void) +{ + test_ping(AF_INET6, IP6_ADDR_TUNL_DEV0); +} + +static void ping6_dev1(void) +{ + struct nstoken *nstoken; + + /* ping from at_ns0 namespace test */ + nstoken = open_netns("at_ns0"); + if (!ASSERT_OK_PTR(nstoken, "setns")) + return; + + test_ping(AF_INET, IP6_ADDR_TUNL_DEV1); + close_netns(nstoken); +} + +static int attach_tc_prog(int ifindex, int igr_fd, int egr_fd) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = ifindex, + .attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS); DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts1, .handle = 1, .priority = 1, .prog_fd = igr_fd); DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts2, .handle = 1, .priority = 1, .prog_fd = egr_fd); int ret; - ret = bpf_tc_hook_create(hook); + ret = bpf_tc_hook_create(&hook); if (!ASSERT_OK(ret, "create tc hook")) return ret; if (igr_fd >= 0) { - hook->attach_point = BPF_TC_INGRESS; - ret = bpf_tc_attach(hook, &opts1); + hook.attach_point = BPF_TC_INGRESS; + ret = bpf_tc_attach(&hook, &opts1); if (!ASSERT_OK(ret, "bpf_tc_attach")) { - bpf_tc_hook_destroy(hook); + bpf_tc_hook_destroy(&hook); return ret; } } if (egr_fd >= 0) { - hook->attach_point = BPF_TC_EGRESS; - ret = bpf_tc_attach(hook, &opts2); + hook.attach_point = BPF_TC_EGRESS; + ret = bpf_tc_attach(&hook, &opts2); if (!ASSERT_OK(ret, "bpf_tc_attach")) { - bpf_tc_hook_destroy(hook); + bpf_tc_hook_destroy(&hook); return ret; } } @@ -397,6 +569,50 @@ static int attach_tc_prog(struct bpf_tc_hook *hook, int igr_fd, int egr_fd) return 0; } +static int generic_attach(const char *dev, int igr_fd, int egr_fd) +{ + int ifindex; + + if (!ASSERT_OK_FD(igr_fd, "check ingress fd")) + return -1; + if (!ASSERT_OK_FD(egr_fd, "check egress fd")) + return -1; + + ifindex = if_nametoindex(dev); + if (!ASSERT_NEQ(ifindex, 0, "get ifindex")) + return -1; + + return attach_tc_prog(ifindex, igr_fd, egr_fd); +} + +static int generic_attach_igr(const char *dev, int igr_fd) +{ + int ifindex; + + if (!ASSERT_OK_FD(igr_fd, "check ingress fd")) + return -1; + + ifindex = if_nametoindex(dev); + if (!ASSERT_NEQ(ifindex, 0, "get ifindex")) + return -1; + + return attach_tc_prog(ifindex, igr_fd, -1); +} + +static int generic_attach_egr(const char *dev, int egr_fd) +{ + int ifindex; + + if (!ASSERT_OK_FD(egr_fd, "check egress fd")) + return -1; + + ifindex = if_nametoindex(dev); + if (!ASSERT_NEQ(ifindex, 0, "get ifindex")) + return -1; + + return attach_tc_prog(ifindex, -1, egr_fd); +} + static void test_vxlan_tunnel(void) { struct test_tunnel_kern *skel = NULL; @@ -404,11 +620,9 @@ static void test_vxlan_tunnel(void) int local_ip_map_fd = -1; int set_src_prog_fd, get_src_prog_fd; int set_dst_prog_fd; - int key = 0, ifindex = -1; + int key = 0; uint local_ip; int err; - DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook, - .attach_point = BPF_TC_INGRESS); /* add vxlan tunnel */ err = add_vxlan_tunnel(); @@ -419,42 +633,22 @@ static void test_vxlan_tunnel(void) skel = test_tunnel_kern__open_and_load(); if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load")) goto done; - ifindex = if_nametoindex(VXLAN_TUNL_DEV1); - if (!ASSERT_NEQ(ifindex, 0, "vxlan11 ifindex")) - goto done; - tc_hook.ifindex = ifindex; get_src_prog_fd = bpf_program__fd(skel->progs.vxlan_get_tunnel_src); set_src_prog_fd = bpf_program__fd(skel->progs.vxlan_set_tunnel_src); - if (!ASSERT_GE(get_src_prog_fd, 0, "bpf_program__fd")) - goto done; - if (!ASSERT_GE(set_src_prog_fd, 0, "bpf_program__fd")) - goto done; - if (attach_tc_prog(&tc_hook, get_src_prog_fd, set_src_prog_fd)) + if (generic_attach(VXLAN_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd)) goto done; /* load and attach bpf prog to veth dev tc hook point */ - ifindex = if_nametoindex("veth1"); - if (!ASSERT_NEQ(ifindex, 0, "veth1 ifindex")) - goto done; - tc_hook.ifindex = ifindex; set_dst_prog_fd = bpf_program__fd(skel->progs.veth_set_outer_dst); - if (!ASSERT_GE(set_dst_prog_fd, 0, "bpf_program__fd")) - goto done; - if (attach_tc_prog(&tc_hook, set_dst_prog_fd, -1)) + if (generic_attach_igr("veth1", set_dst_prog_fd)) goto done; /* load and attach prog set_md to tunnel dev tc hook point at_ns0 */ nstoken = open_netns("at_ns0"); if (!ASSERT_OK_PTR(nstoken, "setns src")) goto done; - ifindex = if_nametoindex(VXLAN_TUNL_DEV0); - if (!ASSERT_NEQ(ifindex, 0, "vxlan00 ifindex")) - goto done; - tc_hook.ifindex = ifindex; set_dst_prog_fd = bpf_program__fd(skel->progs.vxlan_set_tunnel_dst); - if (!ASSERT_GE(set_dst_prog_fd, 0, "bpf_program__fd")) - goto done; - if (attach_tc_prog(&tc_hook, -1, set_dst_prog_fd)) + if (generic_attach_egr(VXLAN_TUNL_DEV0, set_dst_prog_fd)) goto done; close_netns(nstoken); @@ -468,9 +662,7 @@ static void test_vxlan_tunnel(void) goto done; /* ping test */ - err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV0); - if (!ASSERT_OK(err, "test_ping")) - goto done; + ping_dev0(); done: /* delete vxlan tunnel */ @@ -488,11 +680,9 @@ static void test_ip6vxlan_tunnel(void) int local_ip_map_fd = -1; int set_src_prog_fd, get_src_prog_fd; int set_dst_prog_fd; - int key = 0, ifindex = -1; + int key = 0; uint local_ip; int err; - DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook, - .attach_point = BPF_TC_INGRESS); /* add vxlan tunnel */ err = add_ip6vxlan_tunnel(); @@ -503,31 +693,17 @@ static void test_ip6vxlan_tunnel(void) skel = test_tunnel_kern__open_and_load(); if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load")) goto done; - ifindex = if_nametoindex(IP6VXLAN_TUNL_DEV1); - if (!ASSERT_NEQ(ifindex, 0, "ip6vxlan11 ifindex")) - goto done; - tc_hook.ifindex = ifindex; get_src_prog_fd = bpf_program__fd(skel->progs.ip6vxlan_get_tunnel_src); set_src_prog_fd = bpf_program__fd(skel->progs.ip6vxlan_set_tunnel_src); - if (!ASSERT_GE(set_src_prog_fd, 0, "bpf_program__fd")) - goto done; - if (!ASSERT_GE(get_src_prog_fd, 0, "bpf_program__fd")) - goto done; - if (attach_tc_prog(&tc_hook, get_src_prog_fd, set_src_prog_fd)) + if (generic_attach(IP6VXLAN_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd)) goto done; /* load and attach prog set_md to tunnel dev tc hook point at_ns0 */ nstoken = open_netns("at_ns0"); if (!ASSERT_OK_PTR(nstoken, "setns src")) goto done; - ifindex = if_nametoindex(IP6VXLAN_TUNL_DEV0); - if (!ASSERT_NEQ(ifindex, 0, "ip6vxlan00 ifindex")) - goto done; - tc_hook.ifindex = ifindex; set_dst_prog_fd = bpf_program__fd(skel->progs.ip6vxlan_set_tunnel_dst); - if (!ASSERT_GE(set_dst_prog_fd, 0, "bpf_program__fd")) - goto done; - if (attach_tc_prog(&tc_hook, -1, set_dst_prog_fd)) + if (generic_attach_egr(IP6VXLAN_TUNL_DEV0, set_dst_prog_fd)) goto done; close_netns(nstoken); @@ -541,9 +717,7 @@ static void test_ip6vxlan_tunnel(void) goto done; /* ping test */ - err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV0); - if (!ASSERT_OK(err, "test_ping")) - goto done; + ping_dev0(); done: /* delete ipv6 vxlan tunnel */ @@ -557,12 +731,8 @@ done: static void test_ipip_tunnel(enum ipip_encap encap) { struct test_tunnel_kern *skel = NULL; - struct nstoken *nstoken; int set_src_prog_fd, get_src_prog_fd; - int ifindex = -1; int err; - DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook, - .attach_point = BPF_TC_INGRESS); /* add ipip tunnel */ err = add_ipip_tunnel(encap); @@ -573,10 +743,6 @@ static void test_ipip_tunnel(enum ipip_encap encap) skel = test_tunnel_kern__open_and_load(); if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load")) goto done; - ifindex = if_nametoindex(IPIP_TUNL_DEV1); - if (!ASSERT_NEQ(ifindex, 0, "ipip11 ifindex")) - goto done; - tc_hook.ifindex = ifindex; switch (encap) { case FOU: @@ -598,26 +764,11 @@ static void test_ipip_tunnel(enum ipip_encap encap) skel->progs.ipip_set_tunnel); } - if (!ASSERT_GE(set_src_prog_fd, 0, "bpf_program__fd")) - goto done; - if (!ASSERT_GE(get_src_prog_fd, 0, "bpf_program__fd")) - goto done; - if (attach_tc_prog(&tc_hook, get_src_prog_fd, set_src_prog_fd)) + if (generic_attach(IPIP_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd)) goto done; - /* ping from root namespace test */ - err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV0); - if (!ASSERT_OK(err, "test_ping")) - goto done; - - /* ping from at_ns0 namespace test */ - nstoken = open_netns("at_ns0"); - if (!ASSERT_OK_PTR(nstoken, "setns")) - goto done; - err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV1); - if (!ASSERT_OK(err, "test_ping")) - goto done; - close_netns(nstoken); + ping_dev0(); + ping_dev1(); done: /* delete ipip tunnel */ @@ -628,11 +779,8 @@ done: static void test_xfrm_tunnel(void) { - DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook, - .attach_point = BPF_TC_INGRESS); LIBBPF_OPTS(bpf_xdp_attach_opts, opts); struct test_tunnel_kern *skel = NULL; - struct nstoken *nstoken; int xdp_prog_fd; int tc_prog_fd; int ifindex; @@ -646,19 +794,16 @@ static void test_xfrm_tunnel(void) if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load")) goto done; - ifindex = if_nametoindex("veth1"); - if (!ASSERT_NEQ(ifindex, 0, "veth1 ifindex")) - goto done; /* attach tc prog to tunnel dev */ - tc_hook.ifindex = ifindex; tc_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state); - if (!ASSERT_GE(tc_prog_fd, 0, "bpf_program__fd")) - goto done; - if (attach_tc_prog(&tc_hook, tc_prog_fd, -1)) + if (generic_attach_igr("veth1", tc_prog_fd)) goto done; /* attach xdp prog to tunnel dev */ + ifindex = if_nametoindex("veth1"); + if (!ASSERT_NEQ(ifindex, 0, "veth1 ifindex")) + goto done; xdp_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state_xdp); if (!ASSERT_GE(xdp_prog_fd, 0, "bpf_program__fd")) goto done; @@ -666,14 +811,7 @@ static void test_xfrm_tunnel(void) if (!ASSERT_OK(err, "bpf_xdp_attach")) goto done; - /* ping from at_ns0 namespace test */ - nstoken = open_netns("at_ns0"); - if (!ASSERT_OK_PTR(nstoken, "setns")) - goto done; - err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV1); - close_netns(nstoken); - if (!ASSERT_OK(err, "test_ping")) - goto done; + ping_dev1(); if (!ASSERT_EQ(skel->bss->xfrm_reqid, 1, "req_id")) goto done; @@ -690,6 +828,281 @@ done: test_tunnel_kern__destroy(skel); } +enum gre_test { + GRE, + GRE_NOKEY, + GRETAP, + GRETAP_NOKEY, +}; + +static void test_gre_tunnel(enum gre_test test) +{ + struct test_tunnel_kern *skel; + int set_fd, get_fd; + int err; + + skel = test_tunnel_kern__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load")) + return; + + switch (test) { + case GRE: + err = add_ipv4_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1, "gre", "seq"); + set_fd = bpf_program__fd(skel->progs.gre_set_tunnel_no_key); + get_fd = bpf_program__fd(skel->progs.gre_get_tunnel); + break; + case GRE_NOKEY: + err = add_ipv4_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1, "gre", "seq key 2"); + set_fd = bpf_program__fd(skel->progs.gre_set_tunnel); + get_fd = bpf_program__fd(skel->progs.gre_get_tunnel); + break; + case GRETAP: + err = add_ipv4_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1, "gretap", "seq"); + set_fd = bpf_program__fd(skel->progs.gre_set_tunnel_no_key); + get_fd = bpf_program__fd(skel->progs.gre_get_tunnel); + break; + case GRETAP_NOKEY: + err = add_ipv4_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1, "gretap", "seq key 2"); + set_fd = bpf_program__fd(skel->progs.gre_set_tunnel); + get_fd = bpf_program__fd(skel->progs.gre_get_tunnel); + break; + } + if (!ASSERT_OK(err, "add tunnel")) + goto done; + + if (generic_attach(GRE_TUNL_DEV1, get_fd, set_fd)) + goto done; + + ping_dev0(); + ping_dev1(); + +done: + delete_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1); + test_tunnel_kern__destroy(skel); +} + +enum ip6gre_test { + IP6GRE, + IP6GRETAP +}; + +static void test_ip6gre_tunnel(enum ip6gre_test test) +{ + struct test_tunnel_kern *skel; + int set_fd, get_fd; + int err; + + skel = test_tunnel_kern__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load")) + return; + + switch (test) { + case IP6GRE: + err = add_ipv6_tunnel(IP6GRE_TUNL_DEV0, IP6GRE_TUNL_DEV1, + "ip6gre", "flowlabel 0xbcdef key 2"); + break; + case IP6GRETAP: + err = add_ipv6_tunnel(IP6GRE_TUNL_DEV0, IP6GRE_TUNL_DEV1, + "ip6gretap", "flowlabel 0xbcdef key 2"); + break; + } + if (!ASSERT_OK(err, "add tunnel")) + goto done; + + set_fd = bpf_program__fd(skel->progs.ip6gretap_set_tunnel); + get_fd = bpf_program__fd(skel->progs.ip6gretap_get_tunnel); + if (generic_attach(IP6GRE_TUNL_DEV1, get_fd, set_fd)) + goto done; + + ping6_veth0(); + ping6_dev1(); + ping_dev0(); + ping_dev1(); +done: + delete_tunnel(IP6GRE_TUNL_DEV0, IP6GRE_TUNL_DEV1); + test_tunnel_kern__destroy(skel); +} + +enum erspan_test { + V1, + V2 +}; + +static void test_erspan_tunnel(enum erspan_test test) +{ + struct test_tunnel_kern *skel; + int set_fd, get_fd; + int err; + + skel = test_tunnel_kern__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load")) + return; + + switch (test) { + case V1: + err = add_ipv4_tunnel(ERSPAN_TUNL_DEV0, ERSPAN_TUNL_DEV1, + "erspan", "seq key 2 erspan_ver 1 erspan 123"); + break; + case V2: + err = add_ipv4_tunnel(ERSPAN_TUNL_DEV0, ERSPAN_TUNL_DEV1, + "erspan", + "seq key 2 erspan_ver 2 erspan_dir egress erspan_hwid 3"); + break; + } + if (!ASSERT_OK(err, "add tunnel")) + goto done; + + set_fd = bpf_program__fd(skel->progs.erspan_set_tunnel); + get_fd = bpf_program__fd(skel->progs.erspan_get_tunnel); + if (generic_attach(ERSPAN_TUNL_DEV1, get_fd, set_fd)) + goto done; + + ping_dev0(); + ping_dev1(); +done: + delete_tunnel(ERSPAN_TUNL_DEV0, ERSPAN_TUNL_DEV1); + test_tunnel_kern__destroy(skel); +} + +static void test_ip6erspan_tunnel(enum erspan_test test) +{ + struct test_tunnel_kern *skel; + int set_fd, get_fd; + int err; + + skel = test_tunnel_kern__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load")) + return; + + switch (test) { + case V1: + err = add_ipv6_tunnel(IP6ERSPAN_TUNL_DEV0, IP6ERSPAN_TUNL_DEV1, + "ip6erspan", "seq key 2 erspan_ver 1 erspan 123"); + break; + case V2: + err = add_ipv6_tunnel(IP6ERSPAN_TUNL_DEV0, IP6ERSPAN_TUNL_DEV1, + "ip6erspan", + "seq key 2 erspan_ver 2 erspan_dir egress erspan_hwid 7"); + break; + } + if (!ASSERT_OK(err, "add tunnel")) + goto done; + + set_fd = bpf_program__fd(skel->progs.ip4ip6erspan_set_tunnel); + get_fd = bpf_program__fd(skel->progs.ip4ip6erspan_get_tunnel); + if (generic_attach(IP6ERSPAN_TUNL_DEV1, get_fd, set_fd)) + goto done; + + ping6_veth0(); + ping_dev1(); +done: + delete_tunnel(IP6ERSPAN_TUNL_DEV0, IP6ERSPAN_TUNL_DEV1); + test_tunnel_kern__destroy(skel); +} + +static void test_geneve_tunnel(void) +{ + struct test_tunnel_kern *skel; + int set_fd, get_fd; + int err; + + skel = test_tunnel_kern__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load")) + return; + + err = add_geneve_tunnel(GENEVE_TUNL_DEV0, GENEVE_TUNL_DEV1, + "geneve", "dstport 6081"); + if (!ASSERT_OK(err, "add tunnel")) + goto done; + + set_fd = bpf_program__fd(skel->progs.geneve_set_tunnel); + get_fd = bpf_program__fd(skel->progs.geneve_get_tunnel); + if (generic_attach(GENEVE_TUNL_DEV1, get_fd, set_fd)) + goto done; + + ping_dev0(); + ping_dev1(); +done: + delete_tunnel(GENEVE_TUNL_DEV0, GENEVE_TUNL_DEV1); + test_tunnel_kern__destroy(skel); +} + +static void test_ip6geneve_tunnel(void) +{ + struct test_tunnel_kern *skel; + int set_fd, get_fd; + int err; + + skel = test_tunnel_kern__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load")) + return; + + err = add_ip6geneve_tunnel(IP6GENEVE_TUNL_DEV0, IP6GENEVE_TUNL_DEV1, + "geneve", ""); + if (!ASSERT_OK(err, "add tunnel")) + goto done; + + set_fd = bpf_program__fd(skel->progs.ip6geneve_set_tunnel); + get_fd = bpf_program__fd(skel->progs.ip6geneve_get_tunnel); + if (generic_attach(IP6GENEVE_TUNL_DEV1, get_fd, set_fd)) + goto done; + + ping_dev0(); + ping_dev1(); +done: + delete_tunnel(IP6GENEVE_TUNL_DEV0, IP6GENEVE_TUNL_DEV1); + test_tunnel_kern__destroy(skel); +} + +enum ip6tnl_test { + IPIP6, + IP6IP6 +}; + +static void test_ip6tnl_tunnel(enum ip6tnl_test test) +{ + struct test_tunnel_kern *skel; + int set_fd, get_fd; + int err; + + skel = test_tunnel_kern__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load")) + return; + + err = add_ipv6_tunnel(IP6TNL_TUNL_DEV0, IP6TNL_TUNL_DEV1, "ip6tnl", ""); + if (!ASSERT_OK(err, "add tunnel")) + goto done; + + switch (test) { + case IPIP6: + set_fd = bpf_program__fd(skel->progs.ipip6_set_tunnel); + get_fd = bpf_program__fd(skel->progs.ipip6_get_tunnel); + break; + case IP6IP6: + set_fd = bpf_program__fd(skel->progs.ip6ip6_set_tunnel); + get_fd = bpf_program__fd(skel->progs.ip6ip6_get_tunnel); + break; + } + if (generic_attach(IP6TNL_TUNL_DEV1, get_fd, set_fd)) + goto done; + + ping6_veth0(); + switch (test) { + case IPIP6: + ping_dev0(); + ping_dev1(); + break; + case IP6IP6: + ping6_dev0(); + ping6_dev1(); + break; + } + +done: + delete_tunnel(IP6TNL_TUNL_DEV0, IP6TNL_TUNL_DEV1); + test_tunnel_kern__destroy(skel); +} + #define RUN_TEST(name, ...) \ ({ \ if (test__start_subtest(#name)) { \ @@ -707,6 +1120,20 @@ static void *test_tunnel_run_tests(void *arg) RUN_TEST(ipip_tunnel, FOU); RUN_TEST(ipip_tunnel, GUE); RUN_TEST(xfrm_tunnel); + RUN_TEST(gre_tunnel, GRE); + RUN_TEST(gre_tunnel, GRE_NOKEY); + RUN_TEST(gre_tunnel, GRETAP); + RUN_TEST(gre_tunnel, GRETAP_NOKEY); + RUN_TEST(ip6gre_tunnel, IP6GRE); + RUN_TEST(ip6gre_tunnel, IP6GRETAP); + RUN_TEST(erspan_tunnel, V1); + RUN_TEST(erspan_tunnel, V2); + RUN_TEST(ip6erspan_tunnel, V1); + RUN_TEST(ip6erspan_tunnel, V2); + RUN_TEST(geneve_tunnel); + RUN_TEST(ip6geneve_tunnel); + RUN_TEST(ip6tnl_tunnel, IPIP6); + RUN_TEST(ip6tnl_tunnel, IP6IP6); return NULL; } diff --git a/tools/testing/selftests/bpf/prog_tests/test_veristat.c b/tools/testing/selftests/bpf/prog_tests/test_veristat.c new file mode 100644 index 0000000..a95b42b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_veristat.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include +#include +#include + +#define __CHECK_STR(str, name) \ + do { \ + if (!ASSERT_HAS_SUBSTR(fix->output, (str), (name))) \ + goto out; \ + } while (0) + +struct fixture { + char tmpfile[80]; + int fd; + char *output; + size_t sz; + char veristat[80]; +}; + +static struct fixture *init_fixture(void) +{ + struct fixture *fix = malloc(sizeof(struct fixture)); + + /* for no_alu32 and cpuv4 veristat is in parent folder */ + if (access("./veristat", F_OK) == 0) + strcpy(fix->veristat, "./veristat"); + else if (access("../veristat", F_OK) == 0) + strcpy(fix->veristat, "../veristat"); + else + PRINT_FAIL("Can't find veristat binary"); + + snprintf(fix->tmpfile, sizeof(fix->tmpfile), "/tmp/test_veristat.XXXXXX"); + fix->fd = mkstemp(fix->tmpfile); + fix->sz = 1000000; + fix->output = malloc(fix->sz); + return fix; +} + +static void teardown_fixture(struct fixture *fix) +{ + free(fix->output); + close(fix->fd); + remove(fix->tmpfile); + free(fix); +} + +static void test_set_global_vars_succeeds(void) +{ + struct fixture *fix = init_fixture(); + + SYS(out, + "%s set_global_vars.bpf.o"\ + " -G \"var_s64 = 0xf000000000000001\" "\ + " -G \"var_u64 = 0xfedcba9876543210\" "\ + " -G \"var_s32 = -0x80000000\" "\ + " -G \"var_u32 = 0x76543210\" "\ + " -G \"var_s16 = -32768\" "\ + " -G \"var_u16 = 60652\" "\ + " -G \"var_s8 = -128\" "\ + " -G \"var_u8 = 255\" "\ + " -G \"var_ea = EA2\" "\ + " -G \"var_eb = EB2\" "\ + " -G \"var_ec = EC2\" "\ + " -G \"var_b = 1\" "\ + "-vl2 > %s", fix->veristat, fix->tmpfile); + + read(fix->fd, fix->output, fix->sz); + __CHECK_STR("_w=0xf000000000000001 ", "var_s64 = 0xf000000000000001"); + __CHECK_STR("_w=0xfedcba9876543210 ", "var_u64 = 0xfedcba9876543210"); + __CHECK_STR("_w=0x80000000 ", "var_s32 = -0x80000000"); + __CHECK_STR("_w=0x76543210 ", "var_u32 = 0x76543210"); + __CHECK_STR("_w=0x8000 ", "var_s16 = -32768"); + __CHECK_STR("_w=0xecec ", "var_u16 = 60652"); + __CHECK_STR("_w=128 ", "var_s8 = -128"); + __CHECK_STR("_w=255 ", "var_u8 = 255"); + __CHECK_STR("_w=11 ", "var_ea = EA2"); + __CHECK_STR("_w=12 ", "var_eb = EB2"); + __CHECK_STR("_w=13 ", "var_ec = EC2"); + __CHECK_STR("_w=1 ", "var_b = 1"); + +out: + teardown_fixture(fix); +} + +static void test_set_global_vars_from_file_succeeds(void) +{ + struct fixture *fix = init_fixture(); + char input_file[80]; + const char *vars = "var_s16 = -32768\nvar_u16 = 60652"; + int fd; + + snprintf(input_file, sizeof(input_file), "/tmp/veristat_input.XXXXXX"); + fd = mkstemp(input_file); + if (!ASSERT_GE(fd, 0, "valid fd")) + goto out; + + write(fd, vars, strlen(vars)); + syncfs(fd); + SYS(out, "%s set_global_vars.bpf.o -G \"@%s\" -vl2 > %s", + fix->veristat, input_file, fix->tmpfile); + read(fix->fd, fix->output, fix->sz); + __CHECK_STR("_w=0x8000 ", "var_s16 = -32768"); + __CHECK_STR("_w=0xecec ", "var_u16 = 60652"); + +out: + close(fd); + remove(input_file); + teardown_fixture(fix); +} + +static void test_set_global_vars_out_of_range(void) +{ + struct fixture *fix = init_fixture(); + + SYS_FAIL(out, + "%s set_global_vars.bpf.o -G \"var_s32 = 2147483648\" -vl2 2> %s", + fix->veristat, fix->tmpfile); + + read(fix->fd, fix->output, fix->sz); + __CHECK_STR("is out of range [-2147483648; 2147483647]", "out of range"); + +out: + teardown_fixture(fix); +} + +void test_veristat(void) +{ + if (test__start_subtest("set_global_vars_succeeds")) + test_set_global_vars_succeeds(); + + if (test__start_subtest("set_global_vars_out_of_range")) + test_set_global_vars_out_of_range(); + + if (test__start_subtest("set_global_vars_from_file_succeeds")) + test_set_global_vars_from_file_succeeds(); +} + +#undef __CHECK_STR diff --git a/tools/testing/selftests/bpf/prog_tests/test_xdp_veth.c b/tools/testing/selftests/bpf/prog_tests/test_xdp_veth.c index 8d75424..3e98a16 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_xdp_veth.c +++ b/tools/testing/selftests/bpf/prog_tests/test_xdp_veth.c @@ -3,17 +3,50 @@ /* Create 3 namespaces with 3 veth peers, and forward packets in-between using * native XDP * - * XDP_TX - * NS1(veth11) NS2(veth22) NS3(veth33) - * | | | - * | | | - * (veth1, (veth2, (veth3, - * id:111) id:122) id:133) - * ^ | ^ | ^ | - * | | XDP_REDIRECT | | XDP_REDIRECT | | - * | ------------------ ------------------ | - * ----------------------------------------- - * XDP_REDIRECT + * Network topology: + * ---------- ---------- ---------- + * | NS1 | | NS2 | | NS3 | + * | veth11 | | veth22 | | veth33 | + * ----|----- -----|---- -----|---- + * | | | + * ----|------------------|----------------|---- + * | veth1 veth2 veth3 | + * | | + * | NSO | + * --------------------------------------------- + * + * Test cases: + * - [test_xdp_veth_redirect] : ping veth33 from veth11 + * + * veth11 veth22 veth33 + * (XDP_PASS) (XDP_TX) (XDP_PASS) + * | | | + * | | | + * veth1 veth2 veth3 + * (XDP_REDIRECT) (XDP_REDIRECT) (XDP_REDIRECT) + * ^ | ^ | ^ | + * | | | | | | + * | ------------------ ------------------ | + * ----------------------------------------- + * + * - [test_xdp_veth_broadcast_redirect]: broadcast from veth11 + * - IPv4 ping : BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS + * -> echo request received by all except veth11 + * - IPv4 ping : BPF_F_BROADCAST + * -> echo request received by all veth + * - [test_xdp_veth_egress]: + * - all src mac should be the magic mac + * + * veth11 veth22 veth33 + * (XDP_PASS) (XDP_PASS) (XDP_PASS) + * | | | + * | | | + * veth1 veth2 veth3 + * (XDP_REDIRECT) (XDP_REDIRECT) (XDP_REDIRECT) + * | ^ ^ + * | | | + * ---------------------------------------- + * */ #define _GNU_SOURCE @@ -22,192 +55,545 @@ #include "network_helpers.h" #include "xdp_dummy.skel.h" #include "xdp_redirect_map.skel.h" +#include "xdp_redirect_multi_kern.skel.h" #include "xdp_tx.skel.h" +#include #define VETH_PAIRS_COUNT 3 -#define NS_SUFFIX_LEN 6 -#define VETH_NAME_MAX_LEN 16 +#define VETH_NAME_MAX_LEN 32 +#define IP_MAX_LEN 16 #define IP_SRC "10.1.1.11" #define IP_DST "10.1.1.33" -#define IP_CMD_MAX_LEN 128 - -struct skeletons { - struct xdp_dummy *xdp_dummy; - struct xdp_tx *xdp_tx; - struct xdp_redirect_map *xdp_redirect_maps; -}; +#define IP_NEIGH "10.1.1.253" +#define PROG_NAME_MAX_LEN 128 +#define NS_NAME_MAX_LEN 32 struct veth_configuration { char local_veth[VETH_NAME_MAX_LEN]; /* Interface in main namespace */ char remote_veth[VETH_NAME_MAX_LEN]; /* Peer interface in dedicated namespace*/ - const char *namespace; /* Namespace for the remote veth */ - char next_veth[VETH_NAME_MAX_LEN]; /* Local interface to redirect traffic to */ - char *remote_addr; /* IP address of the remote veth */ + char namespace[NS_NAME_MAX_LEN]; /* Namespace for the remote veth */ + int next_veth; /* Local interface to redirect traffic to */ + char remote_addr[IP_MAX_LEN]; /* IP address of the remote veth */ }; -static struct veth_configuration config[VETH_PAIRS_COUNT] = { - { - .local_veth = "veth1", - .remote_veth = "veth11", - .next_veth = "veth2", - .remote_addr = IP_SRC, - .namespace = "ns-veth11" - }, - { - .local_veth = "veth2", - .remote_veth = "veth22", - .next_veth = "veth3", - .remote_addr = NULL, - .namespace = "ns-veth22" - }, +struct net_configuration { + char ns0_name[NS_NAME_MAX_LEN]; + struct veth_configuration veth_cfg[VETH_PAIRS_COUNT]; +}; + +static const struct net_configuration default_config = { + .ns0_name = "ns0-", { - .local_veth = "veth3", - .remote_veth = "veth33", - .next_veth = "veth1", - .remote_addr = IP_DST, - .namespace = "ns-veth33" + { + .local_veth = "veth1-", + .remote_veth = "veth11", + .next_veth = 1, + .remote_addr = IP_SRC, + .namespace = "ns-veth11-" + }, + { + .local_veth = "veth2-", + .remote_veth = "veth22", + .next_veth = 2, + .remote_addr = "", + .namespace = "ns-veth22-" + }, + { + .local_veth = "veth3-", + .remote_veth = "veth33", + .next_veth = 0, + .remote_addr = IP_DST, + .namespace = "ns-veth33-" + } } }; -static int attach_programs_to_veth_pair(struct skeletons *skeletons, int index) +struct prog_configuration { + char local_name[PROG_NAME_MAX_LEN]; /* BPF prog to attach to local_veth */ + char remote_name[PROG_NAME_MAX_LEN]; /* BPF prog to attach to remote_veth */ + u32 local_flags; /* XDP flags to use on local_veth */ + u32 remote_flags; /* XDP flags to use on remote_veth */ +}; + +static int attach_programs_to_veth_pair(struct bpf_object **objs, size_t nb_obj, + struct net_configuration *net_config, + struct prog_configuration *prog, int index) { struct bpf_program *local_prog, *remote_prog; - struct bpf_link **local_link, **remote_link; struct nstoken *nstoken; - struct bpf_link *link; - int interface; - - switch (index) { - case 0: - local_prog = skeletons->xdp_redirect_maps->progs.xdp_redirect_map_0; - local_link = &skeletons->xdp_redirect_maps->links.xdp_redirect_map_0; - remote_prog = skeletons->xdp_dummy->progs.xdp_dummy_prog; - remote_link = &skeletons->xdp_dummy->links.xdp_dummy_prog; - break; - case 1: - local_prog = skeletons->xdp_redirect_maps->progs.xdp_redirect_map_1; - local_link = &skeletons->xdp_redirect_maps->links.xdp_redirect_map_1; - remote_prog = skeletons->xdp_tx->progs.xdp_tx; - remote_link = &skeletons->xdp_tx->links.xdp_tx; - break; - case 2: - local_prog = skeletons->xdp_redirect_maps->progs.xdp_redirect_map_2; - local_link = &skeletons->xdp_redirect_maps->links.xdp_redirect_map_2; - remote_prog = skeletons->xdp_dummy->progs.xdp_dummy_prog; - remote_link = &skeletons->xdp_dummy->links.xdp_dummy_prog; - break; + int interface, ret, i; + + for (i = 0; i < nb_obj; i++) { + local_prog = bpf_object__find_program_by_name(objs[i], prog[index].local_name); + if (local_prog) + break; } - interface = if_nametoindex(config[index].local_veth); + if (!ASSERT_OK_PTR(local_prog, "find local program")) + return -1; + + for (i = 0; i < nb_obj; i++) { + remote_prog = bpf_object__find_program_by_name(objs[i], prog[index].remote_name); + if (remote_prog) + break; + } + if (!ASSERT_OK_PTR(remote_prog, "find remote program")) + return -1; + + interface = if_nametoindex(net_config->veth_cfg[index].local_veth); if (!ASSERT_NEQ(interface, 0, "non zero interface index")) return -1; - link = bpf_program__attach_xdp(local_prog, interface); - if (!ASSERT_OK_PTR(link, "attach xdp program to local veth")) + + ret = bpf_xdp_attach(interface, bpf_program__fd(local_prog), + prog[index].local_flags, NULL); + if (!ASSERT_OK(ret, "attach xdp program to local veth")) return -1; - *local_link = link; - nstoken = open_netns(config[index].namespace); + + nstoken = open_netns(net_config->veth_cfg[index].namespace); if (!ASSERT_OK_PTR(nstoken, "switch to remote veth namespace")) return -1; - interface = if_nametoindex(config[index].remote_veth); + + interface = if_nametoindex(net_config->veth_cfg[index].remote_veth); if (!ASSERT_NEQ(interface, 0, "non zero interface index")) { close_netns(nstoken); return -1; } - link = bpf_program__attach_xdp(remote_prog, interface); - *remote_link = link; - close_netns(nstoken); - if (!ASSERT_OK_PTR(link, "attach xdp program to remote veth")) + + ret = bpf_xdp_attach(interface, bpf_program__fd(remote_prog), + prog[index].remote_flags, NULL); + if (!ASSERT_OK(ret, "attach xdp program to remote veth")) { + close_netns(nstoken); return -1; + } + close_netns(nstoken); return 0; } -static int configure_network(struct skeletons *skeletons) +static int create_network(struct net_configuration *net_config) { - int interface_id; - int map_fd; - int err; - int i = 0; + struct nstoken *nstoken = NULL; + int i, err; + + memcpy(net_config, &default_config, sizeof(struct net_configuration)); + + /* Create unique namespaces */ + err = append_tid(net_config->ns0_name, NS_NAME_MAX_LEN); + if (!ASSERT_OK(err, "append TID to ns0 name")) + goto fail; + SYS(fail, "ip netns add %s", net_config->ns0_name); - /* First create and configure all interfaces */ for (i = 0; i < VETH_PAIRS_COUNT; i++) { - SYS(fail, "ip netns add %s", config[i].namespace); - SYS(fail, "ip link add %s type veth peer name %s netns %s", - config[i].local_veth, config[i].remote_veth, config[i].namespace); - SYS(fail, "ip link set dev %s up", config[i].local_veth); - if (config[i].remote_addr) - SYS(fail, "ip -n %s addr add %s/24 dev %s", config[i].namespace, - config[i].remote_addr, config[i].remote_veth); - SYS(fail, "ip -n %s link set dev %s up", config[i].namespace, - config[i].remote_veth); + err = append_tid(net_config->veth_cfg[i].namespace, NS_NAME_MAX_LEN); + if (!ASSERT_OK(err, "append TID to ns name")) + goto fail; + SYS(fail, "ip netns add %s", net_config->veth_cfg[i].namespace); } - /* Then configure the redirect map and attach programs to interfaces */ - map_fd = bpf_map__fd(skeletons->xdp_redirect_maps->maps.tx_port); - if (!ASSERT_GE(map_fd, 0, "open redirect map")) + /* Create interfaces */ + nstoken = open_netns(net_config->ns0_name); + if (!nstoken) goto fail; + for (i = 0; i < VETH_PAIRS_COUNT; i++) { - interface_id = if_nametoindex(config[i].next_veth); - if (!ASSERT_NEQ(interface_id, 0, "non zero interface index")) - goto fail; - err = bpf_map_update_elem(map_fd, &i, &interface_id, BPF_ANY); - if (!ASSERT_OK(err, "configure interface redirection through map")) - goto fail; - if (attach_programs_to_veth_pair(skeletons, i)) - goto fail; + SYS(fail, "ip link add %s type veth peer name %s netns %s", + net_config->veth_cfg[i].local_veth, net_config->veth_cfg[i].remote_veth, + net_config->veth_cfg[i].namespace); + SYS(fail, "ip link set dev %s up", net_config->veth_cfg[i].local_veth); + if (net_config->veth_cfg[i].remote_addr[0]) + SYS(fail, "ip -n %s addr add %s/24 dev %s", + net_config->veth_cfg[i].namespace, + net_config->veth_cfg[i].remote_addr, + net_config->veth_cfg[i].remote_veth); + SYS(fail, "ip -n %s link set dev %s up", net_config->veth_cfg[i].namespace, + net_config->veth_cfg[i].remote_veth); } + close_netns(nstoken); return 0; fail: + close_netns(nstoken); return -1; } -static void cleanup_network(void) +static void cleanup_network(struct net_configuration *net_config) { int i; - /* Deleting namespaces is enough to automatically remove veth pairs as well - */ + SYS_NOFAIL("ip netns del %s", net_config->ns0_name); for (i = 0; i < VETH_PAIRS_COUNT; i++) - SYS_NOFAIL("ip netns del %s", config[i].namespace); + SYS_NOFAIL("ip netns del %s", net_config->veth_cfg[i].namespace); } -static int check_ping(struct skeletons *skeletons) +#define VETH_REDIRECT_SKEL_NB 3 +static void xdp_veth_redirect(u32 flags) { + struct prog_configuration ping_config[VETH_PAIRS_COUNT] = { + { + .local_name = "xdp_redirect_map_0", + .remote_name = "xdp_dummy_prog", + .local_flags = flags, + .remote_flags = flags, + }, + { + .local_name = "xdp_redirect_map_1", + .remote_name = "xdp_tx", + .local_flags = flags, + .remote_flags = flags, + }, + { + .local_name = "xdp_redirect_map_2", + .remote_name = "xdp_dummy_prog", + .local_flags = flags, + .remote_flags = flags, + } + }; + struct bpf_object *bpf_objs[VETH_REDIRECT_SKEL_NB]; + struct xdp_redirect_map *xdp_redirect_map; + struct net_configuration net_config; + struct nstoken *nstoken = NULL; + struct xdp_dummy *xdp_dummy; + struct xdp_tx *xdp_tx; + int map_fd; + int i; + + xdp_dummy = xdp_dummy__open_and_load(); + if (!ASSERT_OK_PTR(xdp_dummy, "xdp_dummy__open_and_load")) + return; + + xdp_tx = xdp_tx__open_and_load(); + if (!ASSERT_OK_PTR(xdp_tx, "xdp_tx__open_and_load")) + goto destroy_xdp_dummy; + + xdp_redirect_map = xdp_redirect_map__open_and_load(); + if (!ASSERT_OK_PTR(xdp_redirect_map, "xdp_redirect_map__open_and_load")) + goto destroy_xdp_tx; + + if (!ASSERT_OK(create_network(&net_config), "create network")) + goto destroy_xdp_redirect_map; + + /* Then configure the redirect map and attach programs to interfaces */ + map_fd = bpf_map__fd(xdp_redirect_map->maps.tx_port); + if (!ASSERT_OK_FD(map_fd, "open redirect map")) + goto destroy_xdp_redirect_map; + + bpf_objs[0] = xdp_dummy->obj; + bpf_objs[1] = xdp_tx->obj; + bpf_objs[2] = xdp_redirect_map->obj; + + nstoken = open_netns(net_config.ns0_name); + if (!ASSERT_OK_PTR(nstoken, "open NS0")) + goto destroy_xdp_redirect_map; + + for (i = 0; i < VETH_PAIRS_COUNT; i++) { + int next_veth = net_config.veth_cfg[i].next_veth; + int interface_id; + int err; + + interface_id = if_nametoindex(net_config.veth_cfg[next_veth].local_veth); + if (!ASSERT_NEQ(interface_id, 0, "non zero interface index")) + goto destroy_xdp_redirect_map; + err = bpf_map_update_elem(map_fd, &i, &interface_id, BPF_ANY); + if (!ASSERT_OK(err, "configure interface redirection through map")) + goto destroy_xdp_redirect_map; + if (attach_programs_to_veth_pair(bpf_objs, VETH_REDIRECT_SKEL_NB, + &net_config, ping_config, i)) + goto destroy_xdp_redirect_map; + } + /* Test: if all interfaces are properly configured, we must be able to ping * veth33 from veth11 */ - return SYS_NOFAIL("ip netns exec %s ping -c 1 -W 1 %s > /dev/null", - config[0].namespace, IP_DST); + ASSERT_OK(SYS_NOFAIL("ip netns exec %s ping -c 1 -W 1 %s > /dev/null", + net_config.veth_cfg[0].namespace, IP_DST), "ping"); + +destroy_xdp_redirect_map: + close_netns(nstoken); + xdp_redirect_map__destroy(xdp_redirect_map); +destroy_xdp_tx: + xdp_tx__destroy(xdp_tx); +destroy_xdp_dummy: + xdp_dummy__destroy(xdp_dummy); + + cleanup_network(&net_config); } -void test_xdp_veth_redirect(void) +#define BROADCAST_REDIRECT_SKEL_NB 2 +static void xdp_veth_broadcast_redirect(u32 attach_flags, u64 redirect_flags) { - struct skeletons skeletons = {}; + struct prog_configuration prog_cfg[VETH_PAIRS_COUNT] = { + { + .local_name = "xdp_redirect_map_multi_prog", + .remote_name = "xdp_count_0", + .local_flags = attach_flags, + .remote_flags = attach_flags, + }, + { + .local_name = "xdp_redirect_map_multi_prog", + .remote_name = "xdp_count_1", + .local_flags = attach_flags, + .remote_flags = attach_flags, + }, + { + .local_name = "xdp_redirect_map_multi_prog", + .remote_name = "xdp_count_2", + .local_flags = attach_flags, + .remote_flags = attach_flags, + } + }; + struct bpf_object *bpf_objs[BROADCAST_REDIRECT_SKEL_NB]; + struct xdp_redirect_multi_kern *xdp_redirect_multi_kern; + struct xdp_redirect_map *xdp_redirect_map; + struct bpf_devmap_val devmap_val = {}; + struct net_configuration net_config; + struct nstoken *nstoken = NULL; + u16 protocol = ETH_P_IP; + int group_map; + int flags_map; + int cnt_map; + u64 cnt = 0; + int i, err; - skeletons.xdp_dummy = xdp_dummy__open_and_load(); - if (!ASSERT_OK_PTR(skeletons.xdp_dummy, "xdp_dummy__open_and_load")) + xdp_redirect_multi_kern = xdp_redirect_multi_kern__open_and_load(); + if (!ASSERT_OK_PTR(xdp_redirect_multi_kern, "xdp_redirect_multi_kern__open_and_load")) return; - skeletons.xdp_tx = xdp_tx__open_and_load(); - if (!ASSERT_OK_PTR(skeletons.xdp_tx, "xdp_tx__open_and_load")) + xdp_redirect_map = xdp_redirect_map__open_and_load(); + if (!ASSERT_OK_PTR(xdp_redirect_map, "xdp_redirect_map__open_and_load")) + goto destroy_xdp_redirect_multi_kern; + + if (!ASSERT_OK(create_network(&net_config), "create network")) + goto destroy_xdp_redirect_map; + + group_map = bpf_map__fd(xdp_redirect_multi_kern->maps.map_all); + if (!ASSERT_OK_FD(group_map, "open map_all")) + goto destroy_xdp_redirect_map; + + flags_map = bpf_map__fd(xdp_redirect_multi_kern->maps.redirect_flags); + if (!ASSERT_OK_FD(group_map, "open map_all")) + goto destroy_xdp_redirect_map; + + err = bpf_map_update_elem(flags_map, &protocol, &redirect_flags, BPF_NOEXIST); + if (!ASSERT_OK(err, "init IP count")) + goto destroy_xdp_redirect_map; + + cnt_map = bpf_map__fd(xdp_redirect_map->maps.rxcnt); + if (!ASSERT_OK_FD(cnt_map, "open rxcnt map")) + goto destroy_xdp_redirect_map; + + bpf_objs[0] = xdp_redirect_multi_kern->obj; + bpf_objs[1] = xdp_redirect_map->obj; + + nstoken = open_netns(net_config.ns0_name); + if (!ASSERT_OK_PTR(nstoken, "open NS0")) + goto destroy_xdp_redirect_map; + + for (i = 0; i < VETH_PAIRS_COUNT; i++) { + int ifindex = if_nametoindex(net_config.veth_cfg[i].local_veth); + + if (attach_programs_to_veth_pair(bpf_objs, BROADCAST_REDIRECT_SKEL_NB, + &net_config, prog_cfg, i)) + goto destroy_xdp_redirect_map; + + SYS(destroy_xdp_redirect_map, + "ip -n %s neigh add %s lladdr 00:00:00:00:00:01 dev %s", + net_config.veth_cfg[i].namespace, IP_NEIGH, net_config.veth_cfg[i].remote_veth); + + devmap_val.ifindex = ifindex; + err = bpf_map_update_elem(group_map, &ifindex, &devmap_val, 0); + if (!ASSERT_OK(err, "bpf_map_update_elem")) + goto destroy_xdp_redirect_map; + + } + + SYS_NOFAIL("ip netns exec %s ping %s -i 0.1 -c 4 -W1 > /dev/null ", + net_config.veth_cfg[0].namespace, IP_NEIGH); + + for (i = 0; i < VETH_PAIRS_COUNT; i++) { + err = bpf_map_lookup_elem(cnt_map, &i, &cnt); + if (!ASSERT_OK(err, "get IP cnt")) + goto destroy_xdp_redirect_map; + + if (redirect_flags & BPF_F_EXCLUDE_INGRESS) + /* veth11 shouldn't receive the ICMP requests; + * others should + */ + ASSERT_EQ(cnt, i ? 4 : 0, "compare IP cnt"); + else + /* All remote veth should receive the ICMP requests */ + ASSERT_EQ(cnt, 4, "compare IP cnt"); + } + +destroy_xdp_redirect_map: + close_netns(nstoken); + xdp_redirect_map__destroy(xdp_redirect_map); +destroy_xdp_redirect_multi_kern: + xdp_redirect_multi_kern__destroy(xdp_redirect_multi_kern); + + cleanup_network(&net_config); +} + +#define VETH_EGRESS_SKEL_NB 3 +static void xdp_veth_egress(u32 flags) +{ + struct prog_configuration prog_cfg[VETH_PAIRS_COUNT] = { + { + .local_name = "xdp_redirect_map_all_prog", + .remote_name = "xdp_dummy_prog", + .local_flags = flags, + .remote_flags = flags, + }, + { + .local_name = "xdp_redirect_map_all_prog", + .remote_name = "store_mac_1", + .local_flags = flags, + .remote_flags = flags, + }, + { + .local_name = "xdp_redirect_map_all_prog", + .remote_name = "store_mac_2", + .local_flags = flags, + .remote_flags = flags, + } + }; + const char magic_mac[6] = { 0xAA, 0xBB, 0xCC, 0xDD, 0xEE, 0xFF}; + struct xdp_redirect_multi_kern *xdp_redirect_multi_kern; + struct bpf_object *bpf_objs[VETH_EGRESS_SKEL_NB]; + struct xdp_redirect_map *xdp_redirect_map; + struct bpf_devmap_val devmap_val = {}; + struct net_configuration net_config; + int mac_map, egress_map, res_map; + struct nstoken *nstoken = NULL; + struct xdp_dummy *xdp_dummy; + int err; + int i; + + xdp_dummy = xdp_dummy__open_and_load(); + if (!ASSERT_OK_PTR(xdp_dummy, "xdp_dummy__open_and_load")) + return; + + xdp_redirect_multi_kern = xdp_redirect_multi_kern__open_and_load(); + if (!ASSERT_OK_PTR(xdp_redirect_multi_kern, "xdp_redirect_multi_kern__open_and_load")) goto destroy_xdp_dummy; - skeletons.xdp_redirect_maps = xdp_redirect_map__open_and_load(); - if (!ASSERT_OK_PTR(skeletons.xdp_redirect_maps, "xdp_redirect_map__open_and_load")) - goto destroy_xdp_tx; + xdp_redirect_map = xdp_redirect_map__open_and_load(); + if (!ASSERT_OK_PTR(xdp_redirect_map, "xdp_redirect_map__open_and_load")) + goto destroy_xdp_redirect_multi_kern; - if (configure_network(&skeletons)) + if (!ASSERT_OK(create_network(&net_config), "create network")) goto destroy_xdp_redirect_map; - ASSERT_OK(check_ping(&skeletons), "ping"); + mac_map = bpf_map__fd(xdp_redirect_multi_kern->maps.mac_map); + if (!ASSERT_OK_FD(mac_map, "open mac_map")) + goto destroy_xdp_redirect_map; + + egress_map = bpf_map__fd(xdp_redirect_multi_kern->maps.map_egress); + if (!ASSERT_OK_FD(egress_map, "open map_egress")) + goto destroy_xdp_redirect_map; + + devmap_val.bpf_prog.fd = bpf_program__fd(xdp_redirect_multi_kern->progs.xdp_devmap_prog); + + bpf_objs[0] = xdp_dummy->obj; + bpf_objs[1] = xdp_redirect_multi_kern->obj; + bpf_objs[2] = xdp_redirect_map->obj; + + nstoken = open_netns(net_config.ns0_name); + if (!ASSERT_OK_PTR(nstoken, "open NS0")) + goto destroy_xdp_redirect_map; + + for (i = 0; i < VETH_PAIRS_COUNT; i++) { + int ifindex = if_nametoindex(net_config.veth_cfg[i].local_veth); + + SYS(destroy_xdp_redirect_map, + "ip -n %s neigh add %s lladdr 00:00:00:00:00:01 dev %s", + net_config.veth_cfg[i].namespace, IP_NEIGH, net_config.veth_cfg[i].remote_veth); + + if (attach_programs_to_veth_pair(bpf_objs, VETH_REDIRECT_SKEL_NB, + &net_config, prog_cfg, i)) + goto destroy_xdp_redirect_map; + + err = bpf_map_update_elem(mac_map, &ifindex, magic_mac, 0); + if (!ASSERT_OK(err, "bpf_map_update_elem")) + goto destroy_xdp_redirect_map; + + devmap_val.ifindex = ifindex; + err = bpf_map_update_elem(egress_map, &ifindex, &devmap_val, 0); + if (!ASSERT_OK(err, "bpf_map_update_elem")) + goto destroy_xdp_redirect_map; + } + + SYS_NOFAIL("ip netns exec %s ping %s -i 0.1 -c 4 -W1 > /dev/null ", + net_config.veth_cfg[0].namespace, IP_NEIGH); + + res_map = bpf_map__fd(xdp_redirect_map->maps.rx_mac); + if (!ASSERT_OK_FD(res_map, "open rx_map")) + goto destroy_xdp_redirect_map; + + for (i = 0; i < 2; i++) { + u32 key = i; + u64 res; + + err = bpf_map_lookup_elem(res_map, &key, &res); + if (!ASSERT_OK(err, "get MAC res")) + goto destroy_xdp_redirect_map; + + ASSERT_STRNEQ((const char *)&res, magic_mac, ETH_ALEN, "compare mac"); + } destroy_xdp_redirect_map: - xdp_redirect_map__destroy(skeletons.xdp_redirect_maps); -destroy_xdp_tx: - xdp_tx__destroy(skeletons.xdp_tx); + close_netns(nstoken); + xdp_redirect_map__destroy(xdp_redirect_map); +destroy_xdp_redirect_multi_kern: + xdp_redirect_multi_kern__destroy(xdp_redirect_multi_kern); destroy_xdp_dummy: - xdp_dummy__destroy(skeletons.xdp_dummy); + xdp_dummy__destroy(xdp_dummy); + + cleanup_network(&net_config); +} + +void test_xdp_veth_redirect(void) +{ + if (test__start_subtest("0")) + xdp_veth_redirect(0); + + if (test__start_subtest("DRV_MODE")) + xdp_veth_redirect(XDP_FLAGS_DRV_MODE); + + if (test__start_subtest("SKB_MODE")) + xdp_veth_redirect(XDP_FLAGS_SKB_MODE); +} + +void test_xdp_veth_broadcast_redirect(void) +{ + if (test__start_subtest("0/BROADCAST")) + xdp_veth_broadcast_redirect(0, BPF_F_BROADCAST); + + if (test__start_subtest("0/(BROADCAST | EXCLUDE_INGRESS)")) + xdp_veth_broadcast_redirect(0, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS); + + if (test__start_subtest("DRV_MODE/BROADCAST")) + xdp_veth_broadcast_redirect(XDP_FLAGS_DRV_MODE, BPF_F_BROADCAST); + + if (test__start_subtest("DRV_MODE/(BROADCAST | EXCLUDE_INGRESS)")) + xdp_veth_broadcast_redirect(XDP_FLAGS_DRV_MODE, + BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS); + + if (test__start_subtest("SKB_MODE/BROADCAST")) + xdp_veth_broadcast_redirect(XDP_FLAGS_SKB_MODE, BPF_F_BROADCAST); + + if (test__start_subtest("SKB_MODE/(BROADCAST | EXCLUDE_INGRESS)")) + xdp_veth_broadcast_redirect(XDP_FLAGS_SKB_MODE, + BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS); +} + +void test_xdp_veth_egress(void) +{ + if (test__start_subtest("0/egress")) + xdp_veth_egress(0); + + if (test__start_subtest("DRV_MODE/egress")) + xdp_veth_egress(XDP_FLAGS_DRV_MODE); - cleanup_network(); + if (test__start_subtest("SKB_MODE/egress")) + xdp_veth_egress(XDP_FLAGS_SKB_MODE); } diff --git a/tools/testing/selftests/bpf/prog_tests/token.c b/tools/testing/selftests/bpf/prog_tests/token.c index c3ab9b6..f9392df 100644 --- a/tools/testing/selftests/bpf/prog_tests/token.c +++ b/tools/testing/selftests/bpf/prog_tests/token.c @@ -19,6 +19,7 @@ #include "priv_prog.skel.h" #include "dummy_st_ops_success.skel.h" #include "token_lsm.skel.h" +#include "priv_freplace_prog.skel.h" static inline int sys_mount(const char *dev_name, const char *dir_name, const char *type, unsigned long flags, @@ -788,6 +789,84 @@ static int userns_obj_priv_prog(int mnt_fd, struct token_lsm *lsm_skel) return 0; } +static int userns_obj_priv_freplace_setup(int mnt_fd, struct priv_freplace_prog **fr_skel, + struct priv_prog **skel, int *tgt_fd) +{ + LIBBPF_OPTS(bpf_object_open_opts, opts); + int err; + char buf[256]; + + /* use bpf_token_path to provide BPF FS path */ + snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd); + opts.bpf_token_path = buf; + *skel = priv_prog__open_opts(&opts); + if (!ASSERT_OK_PTR(*skel, "priv_prog__open_opts")) + return -EINVAL; + err = priv_prog__load(*skel); + if (!ASSERT_OK(err, "priv_prog__load")) + return -EINVAL; + + *fr_skel = priv_freplace_prog__open_opts(&opts); + if (!ASSERT_OK_PTR(*skel, "priv_freplace_prog__open_opts")) + return -EINVAL; + + *tgt_fd = bpf_program__fd((*skel)->progs.xdp_prog1); + return 0; +} + +/* Verify that freplace works from user namespace, because bpf token is loaded + * in bpf_object__prepare + */ +static int userns_obj_priv_freplace_prog(int mnt_fd, struct token_lsm *lsm_skel) +{ + struct priv_freplace_prog *fr_skel = NULL; + struct priv_prog *skel = NULL; + int err, tgt_fd; + + err = userns_obj_priv_freplace_setup(mnt_fd, &fr_skel, &skel, &tgt_fd); + if (!ASSERT_OK(err, "setup")) + goto out; + + err = bpf_object__prepare(fr_skel->obj); + if (!ASSERT_OK(err, "freplace__prepare")) + goto out; + + err = bpf_program__set_attach_target(fr_skel->progs.new_xdp_prog2, tgt_fd, "xdp_prog1"); + if (!ASSERT_OK(err, "set_attach_target")) + goto out; + + err = priv_freplace_prog__load(fr_skel); + ASSERT_OK(err, "priv_freplace_prog__load"); + +out: + priv_freplace_prog__destroy(fr_skel); + priv_prog__destroy(skel); + return err; +} + +/* Verify that replace fails to set attach target from user namespace without bpf token */ +static int userns_obj_priv_freplace_prog_fail(int mnt_fd, struct token_lsm *lsm_skel) +{ + struct priv_freplace_prog *fr_skel = NULL; + struct priv_prog *skel = NULL; + int err, tgt_fd; + + err = userns_obj_priv_freplace_setup(mnt_fd, &fr_skel, &skel, &tgt_fd); + if (!ASSERT_OK(err, "setup")) + goto out; + + err = bpf_program__set_attach_target(fr_skel->progs.new_xdp_prog2, tgt_fd, "xdp_prog1"); + if (ASSERT_ERR(err, "attach fails")) + err = 0; + else + err = -EINVAL; + +out: + priv_freplace_prog__destroy(fr_skel); + priv_prog__destroy(skel); + return err; +} + /* this test is called with BPF FS that doesn't delegate BPF_BTF_LOAD command, * which should cause struct_ops application to fail, as BTF won't be uploaded * into the kernel, even if STRUCT_OPS programs themselves are allowed @@ -1004,12 +1083,28 @@ void test_token(void) if (test__start_subtest("obj_priv_prog")) { struct bpffs_opts opts = { .cmds = bit(BPF_PROG_LOAD), - .progs = bit(BPF_PROG_TYPE_KPROBE), + .progs = bit(BPF_PROG_TYPE_XDP), .attachs = ~0ULL, }; subtest_userns(&opts, userns_obj_priv_prog); } + if (test__start_subtest("obj_priv_freplace_prog")) { + struct bpffs_opts opts = { + .cmds = bit(BPF_BTF_LOAD) | bit(BPF_PROG_LOAD) | bit(BPF_BTF_GET_FD_BY_ID), + .progs = bit(BPF_PROG_TYPE_EXT) | bit(BPF_PROG_TYPE_XDP), + .attachs = ~0ULL, + }; + subtest_userns(&opts, userns_obj_priv_freplace_prog); + } + if (test__start_subtest("obj_priv_freplace_prog_fail")) { + struct bpffs_opts opts = { + .cmds = bit(BPF_BTF_LOAD) | bit(BPF_PROG_LOAD) | bit(BPF_BTF_GET_FD_BY_ID), + .progs = bit(BPF_PROG_TYPE_EXT) | bit(BPF_PROG_TYPE_XDP), + .attachs = ~0ULL, + }; + subtest_userns(&opts, userns_obj_priv_freplace_prog_fail); + } if (test__start_subtest("obj_priv_btf_fail")) { struct bpffs_opts opts = { /* disallow BTF loading */ diff --git a/tools/testing/selftests/bpf/prog_tests/usdt.c b/tools/testing/selftests/bpf/prog_tests/usdt.c index 56ed1eb..495d664 100644 --- a/tools/testing/selftests/bpf/prog_tests/usdt.c +++ b/tools/testing/selftests/bpf/prog_tests/usdt.c @@ -45,7 +45,7 @@ static void subtest_basic_usdt(void) LIBBPF_OPTS(bpf_usdt_opts, opts); struct test_usdt *skel; struct test_usdt__bss *bss; - int err; + int err, i; skel = test_usdt__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel_open")) @@ -75,6 +75,7 @@ static void subtest_basic_usdt(void) ASSERT_EQ(bss->usdt0_cookie, 0xcafedeadbeeffeed, "usdt0_cookie"); ASSERT_EQ(bss->usdt0_arg_cnt, 0, "usdt0_arg_cnt"); ASSERT_EQ(bss->usdt0_arg_ret, -ENOENT, "usdt0_arg_ret"); + ASSERT_EQ(bss->usdt0_arg_size, -ENOENT, "usdt0_arg_size"); /* auto-attached usdt3 gets default zero cookie value */ ASSERT_EQ(bss->usdt3_cookie, 0, "usdt3_cookie"); @@ -86,6 +87,9 @@ static void subtest_basic_usdt(void) ASSERT_EQ(bss->usdt3_args[0], 1, "usdt3_arg1"); ASSERT_EQ(bss->usdt3_args[1], 42, "usdt3_arg2"); ASSERT_EQ(bss->usdt3_args[2], (uintptr_t)&bla, "usdt3_arg3"); + ASSERT_EQ(bss->usdt3_arg_sizes[0], 4, "usdt3_arg1_size"); + ASSERT_EQ(bss->usdt3_arg_sizes[1], 8, "usdt3_arg2_size"); + ASSERT_EQ(bss->usdt3_arg_sizes[2], 8, "usdt3_arg3_size"); /* auto-attached usdt12 gets default zero cookie value */ ASSERT_EQ(bss->usdt12_cookie, 0, "usdt12_cookie"); @@ -104,6 +108,11 @@ static void subtest_basic_usdt(void) ASSERT_EQ(bss->usdt12_args[10], nums[idx], "usdt12_arg11"); ASSERT_EQ(bss->usdt12_args[11], t1.y, "usdt12_arg12"); + int usdt12_expected_arg_sizes[12] = { 4, 4, 8, 8, 4, 8, 8, 8, 4, 2, 2, 1 }; + + for (i = 0; i < 12; i++) + ASSERT_EQ(bss->usdt12_arg_sizes[i], usdt12_expected_arg_sizes[i], "usdt12_arg_size"); + /* trigger_func() is marked __always_inline, so USDT invocations will be * inlined in two different places, meaning that each USDT will have * at least 2 different places to be attached to. This verifies that diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 8a0e1ff..e66a579 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -45,6 +45,7 @@ #include "verifier_ldsx.skel.h" #include "verifier_leak_ptr.skel.h" #include "verifier_linked_scalars.skel.h" +#include "verifier_load_acquire.skel.h" #include "verifier_loops1.skel.h" #include "verifier_lwt.skel.h" #include "verifier_map_in_map.skel.h" @@ -80,6 +81,7 @@ #include "verifier_spill_fill.skel.h" #include "verifier_spin_lock.skel.h" #include "verifier_stack_ptr.skel.h" +#include "verifier_store_release.skel.h" #include "verifier_subprog_precision.skel.h" #include "verifier_subreg.skel.h" #include "verifier_tailcall_jit.skel.h" @@ -121,7 +123,7 @@ static void run_tests_aux(const char *skel_name, /* test_verifier tests are executed w/o CAP_SYS_ADMIN, do the same here */ err = cap_disable_effective(1ULL << CAP_SYS_ADMIN, &old_caps); if (err) { - PRINT_FAIL("failed to drop CAP_SYS_ADMIN: %i, %s\n", err, strerror(err)); + PRINT_FAIL("failed to drop CAP_SYS_ADMIN: %i, %s\n", err, strerror(-err)); return; } @@ -131,7 +133,7 @@ static void run_tests_aux(const char *skel_name, err = cap_enable_effective(old_caps, NULL); if (err) - PRINT_FAIL("failed to restore CAP_SYS_ADMIN: %i, %s\n", err, strerror(err)); + PRINT_FAIL("failed to restore CAP_SYS_ADMIN: %i, %s\n", err, strerror(-err)); } #define RUN(skel) run_tests_aux(#skel, skel##__elf_bytes, NULL) @@ -173,6 +175,7 @@ void test_verifier_int_ptr(void) { RUN(verifier_int_ptr); } void test_verifier_iterating_callbacks(void) { RUN(verifier_iterating_callbacks); } void test_verifier_jeq_infer_not_null(void) { RUN(verifier_jeq_infer_not_null); } void test_verifier_jit_convergence(void) { RUN(verifier_jit_convergence); } +void test_verifier_load_acquire(void) { RUN(verifier_load_acquire); } void test_verifier_ld_ind(void) { RUN(verifier_ld_ind); } void test_verifier_ldsx(void) { RUN(verifier_ldsx); } void test_verifier_leak_ptr(void) { RUN(verifier_leak_ptr); } @@ -211,6 +214,7 @@ void test_verifier_sockmap_mutate(void) { RUN(verifier_sockmap_mutate); } void test_verifier_spill_fill(void) { RUN(verifier_spill_fill); } void test_verifier_spin_lock(void) { RUN(verifier_spin_lock); } void test_verifier_stack_ptr(void) { RUN(verifier_stack_ptr); } +void test_verifier_store_release(void) { RUN(verifier_store_release); } void test_verifier_subprog_precision(void) { RUN(verifier_subprog_precision); } void test_verifier_subreg(void) { RUN(verifier_subreg); } void test_verifier_tailcall_jit(void) { RUN(verifier_tailcall_jit); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_vlan.c b/tools/testing/selftests/bpf/prog_tests/xdp_vlan.c new file mode 100644 index 0000000..18dd253 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_vlan.c @@ -0,0 +1,175 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Network topology: + * ----------- ----------- + * | NS1 | | NS2 | + * | veth0 -|--------|- veth0 | + * ----------- ----------- + * + */ + +#define _GNU_SOURCE +#include +#include + +#include "network_helpers.h" +#include "test_progs.h" +#include "test_xdp_vlan.skel.h" + + +#define VETH_NAME "veth0" +#define NS_MAX_SIZE 32 +#define NS1_NAME "ns-xdp-vlan-1-" +#define NS2_NAME "ns-xdp-vlan-2-" +#define NS1_IP_ADDR "100.64.10.1" +#define NS2_IP_ADDR "100.64.10.2" +#define VLAN_ID 4011 + +static int setup_network(char *ns1, char *ns2) +{ + if (!ASSERT_OK(append_tid(ns1, NS_MAX_SIZE), "create ns1 name")) + goto fail; + if (!ASSERT_OK(append_tid(ns2, NS_MAX_SIZE), "create ns2 name")) + goto fail; + + SYS(fail, "ip netns add %s", ns1); + SYS(fail, "ip netns add %s", ns2); + SYS(fail, "ip -n %s link add %s type veth peer name %s netns %s", + ns1, VETH_NAME, VETH_NAME, ns2); + + /* NOTICE: XDP require VLAN header inside packet payload + * - Thus, disable VLAN offloading driver features + */ + SYS(fail, "ip netns exec %s ethtool -K %s rxvlan off txvlan off", ns1, VETH_NAME); + SYS(fail, "ip netns exec %s ethtool -K %s rxvlan off txvlan off", ns2, VETH_NAME); + + /* NS1 configuration */ + SYS(fail, "ip -n %s addr add %s/24 dev %s", ns1, NS1_IP_ADDR, VETH_NAME); + SYS(fail, "ip -n %s link set %s up", ns1, VETH_NAME); + + /* NS2 configuration */ + SYS(fail, "ip -n %s link add link %s name %s.%d type vlan id %d", + ns2, VETH_NAME, VETH_NAME, VLAN_ID, VLAN_ID); + SYS(fail, "ip -n %s addr add %s/24 dev %s.%d", ns2, NS2_IP_ADDR, VETH_NAME, VLAN_ID); + SYS(fail, "ip -n %s link set %s up", ns2, VETH_NAME); + SYS(fail, "ip -n %s link set %s.%d up", ns2, VETH_NAME, VLAN_ID); + + /* At this point ping should fail because VLAN tags are only used by NS2 */ + return !SYS_NOFAIL("ip netns exec %s ping -W 1 -c1 %s", ns2, NS1_IP_ADDR); + +fail: + return -1; +} + +static void cleanup_network(const char *ns1, const char *ns2) +{ + SYS_NOFAIL("ip netns del %s", ns1); + SYS_NOFAIL("ip netns del %s", ns2); +} + +static void xdp_vlan(struct bpf_program *xdp, struct bpf_program *tc, u32 flags) +{ + LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_EGRESS); + LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); + char ns1[NS_MAX_SIZE] = NS1_NAME; + char ns2[NS_MAX_SIZE] = NS2_NAME; + struct nstoken *nstoken = NULL; + int interface; + int ret; + + if (!ASSERT_OK(setup_network(ns1, ns2), "setup network")) + goto cleanup; + + nstoken = open_netns(ns1); + if (!ASSERT_OK_PTR(nstoken, "open NS1")) + goto cleanup; + + interface = if_nametoindex(VETH_NAME); + if (!ASSERT_NEQ(interface, 0, "get interface index")) + goto cleanup; + + ret = bpf_xdp_attach(interface, bpf_program__fd(xdp), flags, NULL); + if (!ASSERT_OK(ret, "attach xdp_vlan_change")) + goto cleanup; + + tc_hook.ifindex = interface; + ret = bpf_tc_hook_create(&tc_hook); + if (!ASSERT_OK(ret, "bpf_tc_hook_create")) + goto detach_xdp; + + /* Now we'll use BPF programs to pop/push the VLAN tags */ + tc_opts.prog_fd = bpf_program__fd(tc); + ret = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) + goto detach_xdp; + + close_netns(nstoken); + nstoken = NULL; + + /* Now the namespaces can reach each-other, test with pings */ + SYS(detach_tc, "ip netns exec %s ping -i 0.2 -W 2 -c 2 %s > /dev/null", ns1, NS2_IP_ADDR); + SYS(detach_tc, "ip netns exec %s ping -i 0.2 -W 2 -c 2 %s > /dev/null", ns2, NS1_IP_ADDR); + + +detach_tc: + bpf_tc_detach(&tc_hook, &tc_opts); +detach_xdp: + bpf_xdp_detach(interface, flags, NULL); +cleanup: + close_netns(nstoken); + cleanup_network(ns1, ns2); +} + +/* First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change" + * egress use TC to add back VLAN tag 4011 + */ +void test_xdp_vlan_change(void) +{ + struct test_xdp_vlan *skel; + + skel = test_xdp_vlan__open_and_load(); + if (!ASSERT_OK_PTR(skel, "xdp_vlan__open_and_load")) + return; + + if (test__start_subtest("0")) + xdp_vlan(skel->progs.xdp_vlan_change, skel->progs.tc_vlan_push, 0); + + if (test__start_subtest("DRV_MODE")) + xdp_vlan(skel->progs.xdp_vlan_change, skel->progs.tc_vlan_push, + XDP_FLAGS_DRV_MODE); + + if (test__start_subtest("SKB_MODE")) + xdp_vlan(skel->progs.xdp_vlan_change, skel->progs.tc_vlan_push, + XDP_FLAGS_SKB_MODE); + + test_xdp_vlan__destroy(skel); +} + +/* Second test: XDP prog fully remove vlan header + * + * Catch kernel bug for generic-XDP, that doesn't allow us to + * remove a VLAN header, because skb->protocol still contain VLAN + * ETH_P_8021Q indication, and this cause overwriting of our changes. + */ +void test_xdp_vlan_remove(void) +{ + struct test_xdp_vlan *skel; + + skel = test_xdp_vlan__open_and_load(); + if (!ASSERT_OK_PTR(skel, "xdp_vlan__open_and_load")) + return; + + if (test__start_subtest("0")) + xdp_vlan(skel->progs.xdp_vlan_remove_outer2, skel->progs.tc_vlan_push, 0); + + if (test__start_subtest("DRV_MODE")) + xdp_vlan(skel->progs.xdp_vlan_remove_outer2, skel->progs.tc_vlan_push, + XDP_FLAGS_DRV_MODE); + + if (test__start_subtest("SKB_MODE")) + xdp_vlan(skel->progs.xdp_vlan_remove_outer2, skel->progs.tc_vlan_push, + XDP_FLAGS_SKB_MODE); + + test_xdp_vlan__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/arena_atomics.c b/tools/testing/selftests/bpf/progs/arena_atomics.c index 40dd57f..a52feff 100644 --- a/tools/testing/selftests/bpf/progs/arena_atomics.c +++ b/tools/testing/selftests/bpf/progs/arena_atomics.c @@ -6,6 +6,8 @@ #include #include #include "bpf_arena_common.h" +#include "../../../include/linux/filter.h" +#include "bpf_misc.h" struct { __uint(type, BPF_MAP_TYPE_ARENA); @@ -19,9 +21,17 @@ struct { } arena SEC(".maps"); #if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST) -bool skip_tests __attribute((__section__(".data"))) = false; +bool skip_all_tests __attribute((__section__(".data"))) = false; #else -bool skip_tests = true; +bool skip_all_tests = true; +#endif + +#if defined(ENABLE_ATOMICS_TESTS) && \ + defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \ + (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) +bool skip_lacq_srel_tests __attribute((__section__(".data"))) = false; +#else +bool skip_lacq_srel_tests = true; #endif __u32 pid = 0; @@ -274,4 +284,111 @@ int uaf(const void *ctx) return 0; } +#if __clang_major__ >= 18 +__u8 __arena_global load_acquire8_value = 0x12; +__u16 __arena_global load_acquire16_value = 0x1234; +__u32 __arena_global load_acquire32_value = 0x12345678; +__u64 __arena_global load_acquire64_value = 0x1234567890abcdef; + +__u8 __arena_global load_acquire8_result = 0; +__u16 __arena_global load_acquire16_result = 0; +__u32 __arena_global load_acquire32_result = 0; +__u64 __arena_global load_acquire64_result = 0; +#else +/* clang-17 crashes if the .addr_space.1 ELF section has holes. Work around + * this issue by defining the below variables as 64-bit. + */ +__u64 __arena_global load_acquire8_value; +__u64 __arena_global load_acquire16_value; +__u64 __arena_global load_acquire32_value; +__u64 __arena_global load_acquire64_value; + +__u64 __arena_global load_acquire8_result; +__u64 __arena_global load_acquire16_result; +__u64 __arena_global load_acquire32_result; +__u64 __arena_global load_acquire64_result; +#endif + +SEC("raw_tp/sys_enter") +int load_acquire(const void *ctx) +{ +#if defined(ENABLE_ATOMICS_TESTS) && \ + defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \ + (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) + +#define LOAD_ACQUIRE_ARENA(SIZEOP, SIZE, SRC, DST) \ + { asm volatile ( \ + "r1 = %[" #SRC "] ll;" \ + "r1 = addr_space_cast(r1, 0x0, 0x1);" \ + ".8byte %[load_acquire_insn];" \ + "r3 = %[" #DST "] ll;" \ + "r3 = addr_space_cast(r3, 0x0, 0x1);" \ + "*(" #SIZE " *)(r3 + 0) = r2;" \ + : \ + : __imm_addr(SRC), \ + __imm_insn(load_acquire_insn, \ + BPF_ATOMIC_OP(BPF_##SIZEOP, BPF_LOAD_ACQ, \ + BPF_REG_2, BPF_REG_1, 0)), \ + __imm_addr(DST) \ + : __clobber_all); } \ + + LOAD_ACQUIRE_ARENA(B, u8, load_acquire8_value, load_acquire8_result) + LOAD_ACQUIRE_ARENA(H, u16, load_acquire16_value, + load_acquire16_result) + LOAD_ACQUIRE_ARENA(W, u32, load_acquire32_value, + load_acquire32_result) + LOAD_ACQUIRE_ARENA(DW, u64, load_acquire64_value, + load_acquire64_result) +#undef LOAD_ACQUIRE_ARENA + +#endif + return 0; +} + +#if __clang_major__ >= 18 +__u8 __arena_global store_release8_result = 0; +__u16 __arena_global store_release16_result = 0; +__u32 __arena_global store_release32_result = 0; +__u64 __arena_global store_release64_result = 0; +#else +/* clang-17 crashes if the .addr_space.1 ELF section has holes. Work around + * this issue by defining the below variables as 64-bit. + */ +__u64 __arena_global store_release8_result; +__u64 __arena_global store_release16_result; +__u64 __arena_global store_release32_result; +__u64 __arena_global store_release64_result; +#endif + +SEC("raw_tp/sys_enter") +int store_release(const void *ctx) +{ +#if defined(ENABLE_ATOMICS_TESTS) && \ + defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \ + (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) + +#define STORE_RELEASE_ARENA(SIZEOP, DST, VAL) \ + { asm volatile ( \ + "r1 = " VAL ";" \ + "r2 = %[" #DST "] ll;" \ + "r2 = addr_space_cast(r2, 0x0, 0x1);" \ + ".8byte %[store_release_insn];" \ + : \ + : __imm_addr(DST), \ + __imm_insn(store_release_insn, \ + BPF_ATOMIC_OP(BPF_##SIZEOP, BPF_STORE_REL, \ + BPF_REG_2, BPF_REG_1, 0)) \ + : __clobber_all); } \ + + STORE_RELEASE_ARENA(B, store_release8_result, "0x12") + STORE_RELEASE_ARENA(H, store_release16_result, "0x1234") + STORE_RELEASE_ARENA(W, store_release32_result, "0x12345678") + STORE_RELEASE_ARENA(DW, store_release64_result, + "0x1234567890abcdef ll") +#undef STORE_RELEASE_ARENA + +#endif + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/arena_spin_lock.c b/tools/testing/selftests/bpf/progs/arena_spin_lock.c new file mode 100644 index 0000000..c4500c3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/arena_spin_lock.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include +#include +#include +#include "bpf_misc.h" +#include "bpf_arena_spin_lock.h" + +struct { + __uint(type, BPF_MAP_TYPE_ARENA); + __uint(map_flags, BPF_F_MMAPABLE); + __uint(max_entries, 100); /* number of pages */ +#ifdef __TARGET_ARCH_arm64 + __ulong(map_extra, 0x1ull << 32); /* start of mmap() region */ +#else + __ulong(map_extra, 0x1ull << 44); /* start of mmap() region */ +#endif +} arena SEC(".maps"); + +int cs_count; + +#if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST) +arena_spinlock_t __arena lock; +int test_skip = 1; +#else +int test_skip = 2; +#endif + +int counter; +int limit; + +SEC("tc") +int prog(void *ctx) +{ + int ret = -2; + +#if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST) + unsigned long flags; + + if ((ret = arena_spin_lock_irqsave(&lock, flags))) + return ret; + if (counter != limit) + counter++; + bpf_repeat(cs_count); + ret = 0; + arena_spin_unlock_irqrestore(&lock, flags); +#endif + return ret; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c index bc10c4e..966ee5a 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c @@ -9,6 +9,13 @@ char _license[] SEC("license") = "GPL"; uint32_t tid = 0; int num_unknown_tid = 0; int num_known_tid = 0; +void *user_ptr = 0; +void *user_ptr_long = 0; +uint32_t pid = 0; + +static char big_str1[5000]; +static char big_str2[5005]; +static char big_str3[4996]; SEC("iter/task") int dump_task(struct bpf_iter__task *ctx) @@ -35,7 +42,9 @@ int dump_task(struct bpf_iter__task *ctx) } int num_expected_failure_copy_from_user_task = 0; +int num_expected_failure_copy_from_user_task_str = 0; int num_success_copy_from_user_task = 0; +int num_success_copy_from_user_task_str = 0; SEC("iter.s/task") int dump_task_sleepable(struct bpf_iter__task *ctx) @@ -44,6 +53,9 @@ int dump_task_sleepable(struct bpf_iter__task *ctx) struct task_struct *task = ctx->task; static const char info[] = " === END ==="; struct pt_regs *regs; + char task_str1[10] = "aaaaaaaaaa"; + char task_str2[10], task_str3[10]; + char task_str4[20] = "aaaaaaaaaaaaaaaaaaaa"; void *ptr; uint32_t user_data = 0; int ret; @@ -78,8 +90,106 @@ int dump_task_sleepable(struct bpf_iter__task *ctx) BPF_SEQ_PRINTF(seq, "%s\n", info); return 0; } + ++num_success_copy_from_user_task; + /* Read an invalid pointer and ensure we get an error */ + ptr = NULL; + ret = bpf_copy_from_user_task_str((char *)task_str1, sizeof(task_str1), ptr, task, 0); + if (ret >= 0 || task_str1[9] != 'a' || task_str1[0] != '\0') { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* Read an invalid pointer and ensure we get error with pad zeros flag */ + ptr = NULL; + ret = bpf_copy_from_user_task_str((char *)task_str1, sizeof(task_str1), + ptr, task, BPF_F_PAD_ZEROS); + if (ret >= 0 || task_str1[9] != '\0' || task_str1[0] != '\0') { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + ++num_expected_failure_copy_from_user_task_str; + + /* Same length as the string */ + ret = bpf_copy_from_user_task_str((char *)task_str2, 10, user_ptr, task, 0); + /* only need to do the task pid check once */ + if (bpf_strncmp(task_str2, 10, "test_data\0") != 0 || ret != 10 || task->tgid != pid) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* Shorter length than the string */ + ret = bpf_copy_from_user_task_str((char *)task_str3, 2, user_ptr, task, 0); + if (bpf_strncmp(task_str3, 2, "t\0") != 0 || ret != 2) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* Longer length than the string */ + ret = bpf_copy_from_user_task_str((char *)task_str4, 20, user_ptr, task, 0); + if (bpf_strncmp(task_str4, 10, "test_data\0") != 0 || ret != 10 + || task_str4[sizeof(task_str4) - 1] != 'a') { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* Longer length than the string with pad zeros flag */ + ret = bpf_copy_from_user_task_str((char *)task_str4, 20, user_ptr, task, BPF_F_PAD_ZEROS); + if (bpf_strncmp(task_str4, 10, "test_data\0") != 0 || ret != 10 + || task_str4[sizeof(task_str4) - 1] != '\0') { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* Longer length than the string past a page boundary */ + ret = bpf_copy_from_user_task_str(big_str1, 5000, user_ptr, task, 0); + if (bpf_strncmp(big_str1, 10, "test_data\0") != 0 || ret != 10) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* String that crosses a page boundary */ + ret = bpf_copy_from_user_task_str(big_str1, 5000, user_ptr_long, task, BPF_F_PAD_ZEROS); + if (bpf_strncmp(big_str1, 4, "baba") != 0 || ret != 5000 + || bpf_strncmp(big_str1 + 4996, 4, "bab\0") != 0) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + for (int i = 0; i < 4999; ++i) { + if (i % 2 == 0) { + if (big_str1[i] != 'b') { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + } else { + if (big_str1[i] != 'a') { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + } + } + + /* Longer length than the string that crosses a page boundary */ + ret = bpf_copy_from_user_task_str(big_str2, 5005, user_ptr_long, task, BPF_F_PAD_ZEROS); + if (bpf_strncmp(big_str2, 4, "baba") != 0 || ret != 5000 + || bpf_strncmp(big_str2 + 4996, 5, "bab\0\0") != 0) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* Shorter length than the string that crosses a page boundary */ + ret = bpf_copy_from_user_task_str(big_str3, 4996, user_ptr_long, task, 0); + if (bpf_strncmp(big_str3, 4, "baba") != 0 || ret != 4996 + || bpf_strncmp(big_str3 + 4992, 4, "bab\0") != 0) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + ++num_success_copy_from_user_task_str; + if (ctx->meta->seq_num == 0) BPF_SEQ_PRINTF(seq, " tgid gid data\n"); diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h index f45f435..13a2e22 100644 --- a/tools/testing/selftests/bpf/progs/bpf_misc.h +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -135,6 +135,8 @@ #define __arch_arm64 __arch("ARM64") #define __arch_riscv64 __arch("RISCV64") #define __caps_unpriv(caps) __attribute__((btf_decl_tag("comment:test_caps_unpriv=" EXPAND_QUOTE(caps)))) +#define __load_if_JITed() __attribute__((btf_decl_tag("comment:load_mode=jited"))) +#define __load_if_no_JITed() __attribute__((btf_decl_tag("comment:load_mode=no_jited"))) /* Define common capabilities tested using __caps_unpriv */ #define CAP_NET_ADMIN 12 @@ -172,6 +174,9 @@ #elif defined(__TARGET_ARCH_riscv) #define SYSCALL_WRAPPER 1 #define SYS_PREFIX "__riscv_" +#elif defined(__TARGET_ARCH_powerpc) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "" #else #define SYSCALL_WRAPPER 0 #define SYS_PREFIX "__se_" @@ -208,4 +213,21 @@ #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) #endif +#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \ + defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \ + defined(__TARGET_ARCH_loongarch)) && \ + __clang_major__ >= 18 +#define CAN_USE_GOTOL +#endif + +#if _clang_major__ >= 18 +#define CAN_USE_BPF_ST +#endif + +#if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) && \ + (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) +#define CAN_USE_LOAD_ACQ_STORE_REL +#endif + #endif diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index eb6ed1b..6596941 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -15,7 +15,11 @@ #define SO_KEEPALIVE 9 #define SO_PRIORITY 12 #define SO_REUSEPORT 15 +#if defined(__TARGET_ARCH_powerpc) +#define SO_RCVLOWAT 16 +#else #define SO_RCVLOWAT 18 +#endif #define SO_BINDTODEVICE 25 #define SO_MARK 36 #define SO_MAX_PACING_RATE 47 diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_signed_arr_elem_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_signed_arr_elem_sz.c new file mode 100644 index 0000000..21a5604 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_signed_arr_elem_sz.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_bad_signed_arr_elem_sz x) {} diff --git a/tools/testing/selftests/bpf/progs/cgroup_preorder.c b/tools/testing/selftests/bpf/progs/cgroup_preorder.c new file mode 100644 index 0000000..4ef6202 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_preorder.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include +#include + +char _license[] SEC("license") = "GPL"; + +unsigned int idx; +__u8 result[4]; + +SEC("cgroup/getsockopt") +int child(struct bpf_sockopt *ctx) +{ + if (idx < 4) + result[idx++] = 1; + return 1; +} + +SEC("cgroup/getsockopt") +int child_2(struct bpf_sockopt *ctx) +{ + if (idx < 4) + result[idx++] = 2; + return 1; +} + +SEC("cgroup/getsockopt") +int parent(struct bpf_sockopt *ctx) +{ + if (idx < 4) + result[idx++] = 3; + return 1; +} + +SEC("cgroup/getsockopt") +int parent_2(struct bpf_sockopt *ctx) +{ + if (idx < 4) + result[idx++] = 4; + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/compute_live_registers.c b/tools/testing/selftests/bpf/progs/compute_live_registers.c new file mode 100644 index 0000000..f3d79ae --- /dev/null +++ b/tools/testing/selftests/bpf/progs/compute_live_registers.c @@ -0,0 +1,424 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include "../../../include/linux/filter.h" +#include "bpf_arena_common.h" +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} test_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARENA); + __uint(map_flags, BPF_F_MMAPABLE); + __uint(max_entries, 1); +} arena SEC(".maps"); + +SEC("socket") +__log_level(2) +__msg(" 0: .......... (b7) r0 = 42") +__msg(" 1: 0......... (bf) r1 = r0") +__msg(" 2: .1........ (bf) r2 = r1") +__msg(" 3: ..2....... (bf) r3 = r2") +__msg(" 4: ...3...... (bf) r4 = r3") +__msg(" 5: ....4..... (bf) r5 = r4") +__msg(" 6: .....5.... (bf) r6 = r5") +__msg(" 7: ......6... (bf) r7 = r6") +__msg(" 8: .......7.. (bf) r8 = r7") +__msg(" 9: ........8. (bf) r9 = r8") +__msg("10: .........9 (bf) r0 = r9") +__msg("11: 0......... (95) exit") +__naked void assign_chain(void) +{ + asm volatile ( + "r0 = 42;" + "r1 = r0;" + "r2 = r1;" + "r3 = r2;" + "r4 = r3;" + "r5 = r4;" + "r6 = r5;" + "r7 = r6;" + "r8 = r7;" + "r9 = r8;" + "r0 = r9;" + "exit;" + ::: __clobber_all); +} + +SEC("socket") +__log_level(2) +__msg("0: .......... (b7) r1 = 7") +__msg("1: .1........ (07) r1 += 7") +__msg("2: .......... (b7) r2 = 7") +__msg("3: ..2....... (b7) r3 = 42") +__msg("4: ..23...... (0f) r2 += r3") +__msg("5: .......... (b7) r0 = 0") +__msg("6: 0......... (95) exit") +__naked void arithmetics(void) +{ + asm volatile ( + "r1 = 7;" + "r1 += 7;" + "r2 = 7;" + "r3 = 42;" + "r2 += r3;" + "r0 = 0;" + "exit;" + ::: __clobber_all); +} + +#ifdef CAN_USE_BPF_ST +SEC("socket") +__log_level(2) +__msg(" 1: .1........ (07) r1 += -8") +__msg(" 2: .1........ (7a) *(u64 *)(r1 +0) = 7") +__msg(" 3: .1........ (b7) r2 = 42") +__msg(" 4: .12....... (7b) *(u64 *)(r1 +0) = r2") +__msg(" 5: .12....... (7b) *(u64 *)(r1 +0) = r2") +__msg(" 6: .......... (b7) r0 = 0") +__naked void store(void) +{ + asm volatile ( + "r1 = r10;" + "r1 += -8;" + "*(u64 *)(r1 +0) = 7;" + "r2 = 42;" + "*(u64 *)(r1 +0) = r2;" + "*(u64 *)(r1 +0) = r2;" + "r0 = 0;" + "exit;" + ::: __clobber_all); +} +#endif + +SEC("socket") +__log_level(2) +__msg("1: ....4..... (07) r4 += -8") +__msg("2: ....4..... (79) r5 = *(u64 *)(r4 +0)") +__msg("3: ....45.... (07) r4 += -8") +__naked void load(void) +{ + asm volatile ( + "r4 = r10;" + "r4 += -8;" + "r5 = *(u64 *)(r4 +0);" + "r4 += -8;" + "r0 = r5;" + "exit;" + ::: __clobber_all); +} + +SEC("socket") +__log_level(2) +__msg("0: .1........ (61) r2 = *(u32 *)(r1 +0)") +__msg("1: ..2....... (d4) r2 = le64 r2") +__msg("2: ..2....... (bf) r0 = r2") +__naked void endian(void) +{ + asm volatile ( + "r2 = *(u32 *)(r1 +0);" + "r2 = le64 r2;" + "r0 = r2;" + "exit;" + ::: __clobber_all); +} + +SEC("socket") +__log_level(2) +__msg(" 8: 0......... (b7) r1 = 1") +__msg(" 9: 01........ (db) r1 = atomic64_fetch_add((u64 *)(r0 +0), r1)") +__msg("10: 01........ (c3) lock *(u32 *)(r0 +0) += r1") +__msg("11: 01........ (db) r1 = atomic64_xchg((u64 *)(r0 +0), r1)") +__msg("12: 01........ (bf) r2 = r0") +__msg("13: .12....... (bf) r0 = r1") +__msg("14: 012....... (db) r0 = atomic64_cmpxchg((u64 *)(r2 +0), r0, r1)") +__naked void atomic(void) +{ + asm volatile ( + "r2 = r10;" + "r2 += -8;" + "r1 = 0;" + "*(u64 *)(r2 +0) = r1;" + "r1 = %[test_map] ll;" + "call %[bpf_map_lookup_elem];" + "if r0 == 0 goto 1f;" + "r1 = 1;" + "r1 = atomic_fetch_add((u64 *)(r0 +0), r1);" + ".8byte %[add_nofetch];" /* same as "lock *(u32 *)(r0 +0) += r1;" */ + "r1 = xchg_64(r0 + 0, r1);" + "r2 = r0;" + "r0 = r1;" + "r0 = cmpxchg_64(r2 + 0, r0, r1);" + "1: exit;" + : + : __imm(bpf_map_lookup_elem), + __imm_addr(test_map), + __imm_insn(add_nofetch, BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_0, BPF_REG_1, 0)) + : __clobber_all); +} + +#ifdef CAN_USE_LOAD_ACQ_STORE_REL + +SEC("socket") +__log_level(2) +__msg("2: .12....... (db) store_release((u64 *)(r2 -8), r1)") +__msg("3: .......... (bf) r3 = r10") +__msg("4: ...3...... (db) r4 = load_acquire((u64 *)(r3 -8))") +__naked void atomic_load_acq_store_rel(void) +{ + asm volatile ( + "r1 = 42;" + "r2 = r10;" + ".8byte %[store_release_insn];" /* store_release((u64 *)(r2 - 8), r1); */ + "r3 = r10;" + ".8byte %[load_acquire_insn];" /* r4 = load_acquire((u64 *)(r3 + 0)); */ + "r0 = r4;" + "exit;" + : + : __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_2, BPF_REG_1, -8)), + __imm_insn(load_acquire_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_4, BPF_REG_3, -8)) + : __clobber_all); +} + +#endif /* CAN_USE_LOAD_ACQ_STORE_REL */ + +SEC("socket") +__log_level(2) +__msg("4: .12....7.. (85) call bpf_trace_printk#6") +__msg("5: 0......7.. (0f) r0 += r7") +__naked void regular_call(void) +{ + asm volatile ( + "r7 = 1;" + "r1 = r10;" + "r1 += -8;" + "r2 = 1;" + "call %[bpf_trace_printk];" + "r0 += r7;" + "exit;" + : + : __imm(bpf_trace_printk) + : __clobber_all); +} + +SEC("socket") +__log_level(2) +__msg("2: 012....... (25) if r1 > 0x7 goto pc+1") +__msg("3: ..2....... (bf) r0 = r2") +__naked void if1(void) +{ + asm volatile ( + "r0 = 1;" + "r2 = 2;" + "if r1 > 0x7 goto +1;" + "r0 = r2;" + "exit;" + ::: __clobber_all); +} + +SEC("socket") +__log_level(2) +__msg("3: 0123...... (2d) if r1 > r3 goto pc+1") +__msg("4: ..2....... (bf) r0 = r2") +__naked void if2(void) +{ + asm volatile ( + "r0 = 1;" + "r2 = 2;" + "r3 = 7;" + "if r1 > r3 goto +1;" + "r0 = r2;" + "exit;" + ::: __clobber_all); +} + +SEC("socket") +__log_level(2) +__msg("0: .......... (b7) r1 = 0") +__msg("1: .1........ (b7) r2 = 7") +__msg("2: .12....... (25) if r1 > 0x7 goto pc+4") +__msg("3: .12....... (07) r1 += 1") +__msg("4: .12....... (27) r2 *= 2") +__msg("5: .12....... (05) goto pc+0") +__msg("6: .12....... (05) goto pc-5") +__msg("7: .......... (b7) r0 = 0") +__msg("8: 0......... (95) exit") +__naked void loop(void) +{ + asm volatile ( + "r1 = 0;" + "r2 = 7;" + "if r1 > 0x7 goto +4;" + "r1 += 1;" + "r2 *= 2;" + "goto +0;" + "goto -5;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_trace_printk) + : __clobber_all); +} + +#ifdef CAN_USE_GOTOL +SEC("socket") +__log_level(2) +__msg("2: .123...... (25) if r1 > 0x7 goto pc+2") +__msg("3: ..2....... (bf) r0 = r2") +__msg("4: 0......... (06) gotol pc+1") +__msg("5: ...3...... (bf) r0 = r3") +__msg("6: 0......... (95) exit") +__naked void gotol(void) +{ + asm volatile ( + "r2 = 42;" + "r3 = 24;" + "if r1 > 0x7 goto +2;" + "r0 = r2;" + "gotol +1;" + "r0 = r3;" + "exit;" + : + : __imm(bpf_trace_printk) + : __clobber_all); +} +#endif + +SEC("socket") +__log_level(2) +__msg("0: .......... (b7) r1 = 1") +__msg("1: .1........ (e5) may_goto pc+1") +__msg("2: .......... (05) goto pc-3") +__msg("3: .1........ (bf) r0 = r1") +__msg("4: 0......... (95) exit") +__naked void may_goto(void) +{ + asm volatile ( + "1: r1 = 1;" + ".8byte %[may_goto];" + "goto 1b;" + "r0 = r1;" + "exit;" + : + : __imm(bpf_get_smp_processor_id), + __imm_insn(may_goto, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, +1 /* offset */, 0)) + : __clobber_all); +} + +SEC("socket") +__log_level(2) +__msg("1: 0......... (18) r2 = 0x7") +__msg("3: 0.2....... (0f) r0 += r2") +__naked void ldimm64(void) +{ + asm volatile ( + "r0 = 0;" + "r2 = 0x7 ll;" + "r0 += r2;" + "exit;" + : + :: __clobber_all); +} + +/* No rules specific for LD_ABS/LD_IND, default behaviour kicks in */ +SEC("socket") +__log_level(2) +__msg("2: 0123456789 (30) r0 = *(u8 *)skb[42]") +__msg("3: 012.456789 (0f) r7 += r0") +__msg("4: 012.456789 (b7) r3 = 42") +__msg("5: 0123456789 (50) r0 = *(u8 *)skb[r3 + 0]") +__msg("6: 0......7.. (0f) r7 += r0") +__naked void ldabs(void) +{ + asm volatile ( + "r6 = r1;" + "r7 = 0;" + "r0 = *(u8 *)skb[42];" + "r7 += r0;" + "r3 = 42;" + ".8byte %[ld_ind];" /* same as "r0 = *(u8 *)skb[r3];" */ + "r7 += r0;" + "r0 = r7;" + "exit;" + : + : __imm_insn(ld_ind, BPF_LD_IND(BPF_B, BPF_REG_3, 0)) + : __clobber_all); +} + + +#ifdef __BPF_FEATURE_ADDR_SPACE_CAST +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__log_level(2) +__msg(" 6: .12345.... (85) call bpf_arena_alloc_pages") +__msg(" 7: 0......... (bf) r1 = addr_space_cast(r0, 0, 1)") +__msg(" 8: .1........ (b7) r2 = 42") +__naked void addr_space_cast(void) +{ + asm volatile ( + "r1 = %[arena] ll;" + "r2 = 0;" + "r3 = 1;" + "r4 = 0;" + "r5 = 0;" + "call %[bpf_arena_alloc_pages];" + "r1 = addr_space_cast(r0, 0, 1);" + "r2 = 42;" + "*(u64 *)(r1 +0) = r2;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_arena_alloc_pages), + __imm_addr(arena) + : __clobber_all); +} +#endif + +static __used __naked int aux1(void) +{ + asm volatile ( + "r0 = r1;" + "r0 += r2;" + "exit;" + ::: __clobber_all); +} + +SEC("socket") +__log_level(2) +__msg("0: ....45.... (b7) r1 = 1") +__msg("1: .1..45.... (b7) r2 = 2") +__msg("2: .12.45.... (b7) r3 = 3") +/* Conservative liveness for subprog parameters. */ +__msg("3: .12345.... (85) call pc+2") +__msg("4: .......... (b7) r0 = 0") +__msg("5: 0......... (95) exit") +__msg("6: .12....... (bf) r0 = r1") +__msg("7: 0.2....... (0f) r0 += r2") +/* Conservative liveness for subprog return value. */ +__msg("8: 0......... (95) exit") +__naked void subprog1(void) +{ + asm volatile ( + "r1 = 1;" + "r2 = 2;" + "r3 = 3;" + "call aux1;" + "r0 = 0;" + "exit;" + ::: __clobber_all); +} + +/* to retain debug info for BTF generation */ +void kfunc_root(void) +{ + bpf_arena_alloc_pages(0, 0, 0, 0, 0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/connect4_dropper.c b/tools/testing/selftests/bpf/progs/connect4_dropper.c index d3f4c5e..a3819a5 100644 --- a/tools/testing/selftests/bpf/progs/connect4_dropper.c +++ b/tools/testing/selftests/bpf/progs/connect4_dropper.c @@ -13,12 +13,14 @@ #define VERDICT_REJECT 0 #define VERDICT_PROCEED 1 +int port; + SEC("cgroup/connect4") int connect_v4_dropper(struct bpf_sock_addr *ctx) { if (ctx->type != SOCK_STREAM) return VERDICT_PROCEED; - if (ctx->user_port == bpf_htons(60120)) + if (ctx->user_port == bpf_htons(port)) return VERDICT_REJECT; return VERDICT_PROCEED; } diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h index fd8e1b4..5760ae0 100644 --- a/tools/testing/selftests/bpf/progs/core_reloc_types.h +++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h @@ -347,6 +347,7 @@ struct core_reloc_nesting___err_too_deep { */ struct core_reloc_arrays_output { int a2; + int a3; char b123; int c1c; int d00d; @@ -455,6 +456,15 @@ struct core_reloc_arrays___err_bad_zero_sz_arr { struct core_reloc_arrays_substruct d[1][2]; }; +struct core_reloc_arrays___err_bad_signed_arr_elem_sz { + /* int -> short (signed!): not supported case */ + short a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; +}; + /* * PRIMITIVES */ diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h index 4ece787..86085b7 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_common.h +++ b/tools/testing/selftests/bpf/progs/cpumask_common.h @@ -61,6 +61,7 @@ u32 bpf_cpumask_any_distribute(const struct cpumask *src) __ksym __weak; u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, const struct cpumask *src2) __ksym __weak; u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym __weak; +int bpf_cpumask_populate(struct cpumask *cpumask, void *src, size_t src__sz) __ksym __weak; void bpf_rcu_read_lock(void) __ksym __weak; void bpf_rcu_read_unlock(void) __ksym __weak; diff --git a/tools/testing/selftests/bpf/progs/cpumask_failure.c b/tools/testing/selftests/bpf/progs/cpumask_failure.c index b40b525..8a2fd59 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_failure.c +++ b/tools/testing/selftests/bpf/progs/cpumask_failure.c @@ -222,3 +222,41 @@ int BPF_PROG(test_invalid_nested_array, struct task_struct *task, u64 clone_flag return 0; } + +SEC("tp_btf/task_newtask") +__failure __msg("type=scalar expected=fp") +int BPF_PROG(test_populate_invalid_destination, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *invalid = (struct bpf_cpumask *)0x123456; + u64 bits; + int ret; + + ret = bpf_cpumask_populate((struct cpumask *)invalid, &bits, sizeof(bits)); + if (!ret) + err = 2; + + return 0; +} + +SEC("tp_btf/task_newtask") +__failure __msg("leads to invalid memory access") +int BPF_PROG(test_populate_invalid_source, struct task_struct *task, u64 clone_flags) +{ + void *garbage = (void *)0x123456; + struct bpf_cpumask *local; + int ret; + + local = create_cpumask(); + if (!local) { + err = 1; + return 0; + } + + ret = bpf_cpumask_populate((struct cpumask *)local, garbage, 8); + if (!ret) + err = 2; + + bpf_cpumask_release(local); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c index 80ee469..0e04c31 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_success.c +++ b/tools/testing/selftests/bpf/progs/cpumask_success.c @@ -749,7 +749,6 @@ out: } SEC("tp_btf/task_newtask") -__success int BPF_PROG(test_refcount_null_tracking, struct task_struct *task, u64 clone_flags) { struct bpf_cpumask *mask1, *mask2; @@ -770,3 +769,122 @@ free_masks_return: bpf_cpumask_release(mask2); return 0; } + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_populate_reject_small_mask, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *local; + u8 toofewbits; + int ret; + + if (!is_test_task()) + return 0; + + local = create_cpumask(); + if (!local) + return 0; + + /* The kfunc should prevent this operation */ + ret = bpf_cpumask_populate((struct cpumask *)local, &toofewbits, sizeof(toofewbits)); + if (ret != -EACCES) + err = 2; + + bpf_cpumask_release(local); + + return 0; +} + +/* Mask is guaranteed to be large enough for bpf_cpumask_t. */ +#define CPUMASK_TEST_MASKLEN (sizeof(cpumask_t)) + +/* Add an extra word for the test_populate_reject_unaligned test. */ +u64 bits[CPUMASK_TEST_MASKLEN / 8 + 1]; +extern bool CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS __kconfig __weak; + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_populate_reject_unaligned, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *mask; + char *src; + int ret; + + if (!is_test_task()) + return 0; + + /* Skip if unaligned accesses are fine for this arch. */ + if (CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) + return 0; + + mask = bpf_cpumask_create(); + if (!mask) { + err = 1; + return 0; + } + + /* Misalign the source array by a byte. */ + src = &((char *)bits)[1]; + + ret = bpf_cpumask_populate((struct cpumask *)mask, src, CPUMASK_TEST_MASKLEN); + if (ret != -EINVAL) + err = 2; + + bpf_cpumask_release(mask); + + return 0; +} + + +SEC("tp_btf/task_newtask") +int BPF_PROG(test_populate, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *mask; + bool bit; + int ret; + int i; + + if (!is_test_task()) + return 0; + + /* Set only odd bits. */ + __builtin_memset(bits, 0xaa, CPUMASK_TEST_MASKLEN); + + mask = bpf_cpumask_create(); + if (!mask) { + err = 1; + return 0; + } + + /* Pass the entire bits array, the kfunc will only copy the valid bits. */ + ret = bpf_cpumask_populate((struct cpumask *)mask, bits, CPUMASK_TEST_MASKLEN); + if (ret) { + err = 2; + goto out; + } + + /* + * Test is there to appease the verifier. We cannot directly + * access NR_CPUS, the upper bound for nr_cpus, so we infer + * it from the size of cpumask_t. + */ + if (nr_cpus < 0 || nr_cpus >= CPUMASK_TEST_MASKLEN * 8) { + err = 3; + goto out; + } + + bpf_for(i, 0, nr_cpus) { + /* Odd-numbered bits should be set, even ones unset. */ + bit = bpf_cpumask_test_cpu(i, (const struct cpumask *)mask); + if (bit == (i % 2 != 0)) + continue; + + err = 4; + break; + } + +out: + bpf_cpumask_release(mask); + + return 0; +} + +#undef CPUMASK_TEST_MASKLEN diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c index bfcc856..e1fba28 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_success.c +++ b/tools/testing/selftests/bpf/progs/dynptr_success.c @@ -1,20 +1,19 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2022 Facebook */ +#include #include #include -#include #include #include #include "bpf_misc.h" -#include "bpf_kfuncs.h" #include "errno.h" char _license[] SEC("license") = "GPL"; int pid, err, val; -struct sample { +struct ringbuf_sample { int pid; int seq; long value; @@ -121,7 +120,7 @@ int test_dynptr_data(void *ctx) static int ringbuf_callback(__u32 index, void *data) { - struct sample *sample; + struct ringbuf_sample *sample; struct bpf_dynptr *ptr = (struct bpf_dynptr *)data; @@ -138,7 +137,7 @@ SEC("?tp/syscalls/sys_enter_nanosleep") int test_ringbuf(void *ctx) { struct bpf_dynptr ptr; - struct sample *sample; + struct ringbuf_sample *sample; if (bpf_get_current_pid_tgid() >> 32 != pid) return 0; @@ -567,3 +566,117 @@ int BPF_PROG(test_dynptr_skb_tp_btf, void *skb, void *location) return 1; } + +static inline int bpf_memcmp(const char *a, const char *b, u32 size) +{ + int i; + + bpf_for(i, 0, size) { + if (a[i] != b[i]) + return a[i] < b[i] ? -1 : 1; + } + return 0; +} + +SEC("?tp/syscalls/sys_enter_nanosleep") +int test_dynptr_copy(void *ctx) +{ + char data[] = "hello there, world!!"; + char buf[32] = {'\0'}; + __u32 sz = sizeof(data); + struct bpf_dynptr src, dst; + + bpf_ringbuf_reserve_dynptr(&ringbuf, sz, 0, &src); + bpf_ringbuf_reserve_dynptr(&ringbuf, sz, 0, &dst); + + /* Test basic case of copying contiguous memory backed dynptrs */ + err = bpf_dynptr_write(&src, 0, data, sz, 0); + err = err ?: bpf_dynptr_copy(&dst, 0, &src, 0, sz); + err = err ?: bpf_dynptr_read(buf, sz, &dst, 0, 0); + err = err ?: bpf_memcmp(data, buf, sz); + + /* Test that offsets are handled correctly */ + err = err ?: bpf_dynptr_copy(&dst, 3, &src, 5, sz - 5); + err = err ?: bpf_dynptr_read(buf, sz - 5, &dst, 3, 0); + err = err ?: bpf_memcmp(data + 5, buf, sz - 5); + + bpf_ringbuf_discard_dynptr(&src, 0); + bpf_ringbuf_discard_dynptr(&dst, 0); + return 0; +} + +SEC("xdp") +int test_dynptr_copy_xdp(struct xdp_md *xdp) +{ + struct bpf_dynptr ptr_buf, ptr_xdp; + char data[] = "qwertyuiopasdfghjkl"; + char buf[32] = {'\0'}; + __u32 len = sizeof(data); + int i, chunks = 200; + + /* ptr_xdp is backed by non-contiguous memory */ + bpf_dynptr_from_xdp(xdp, 0, &ptr_xdp); + bpf_ringbuf_reserve_dynptr(&ringbuf, len * chunks, 0, &ptr_buf); + + /* Destination dynptr is backed by non-contiguous memory */ + bpf_for(i, 0, chunks) { + err = bpf_dynptr_write(&ptr_buf, i * len, data, len, 0); + if (err) + goto out; + } + + err = bpf_dynptr_copy(&ptr_xdp, 0, &ptr_buf, 0, len * chunks); + if (err) + goto out; + + bpf_for(i, 0, chunks) { + __builtin_memset(buf, 0, sizeof(buf)); + err = bpf_dynptr_read(&buf, len, &ptr_xdp, i * len, 0); + if (err) + goto out; + if (bpf_memcmp(data, buf, len) != 0) + goto out; + } + + /* Source dynptr is backed by non-contiguous memory */ + __builtin_memset(buf, 0, sizeof(buf)); + bpf_for(i, 0, chunks) { + err = bpf_dynptr_write(&ptr_buf, i * len, buf, len, 0); + if (err) + goto out; + } + + err = bpf_dynptr_copy(&ptr_buf, 0, &ptr_xdp, 0, len * chunks); + if (err) + goto out; + + bpf_for(i, 0, chunks) { + __builtin_memset(buf, 0, sizeof(buf)); + err = bpf_dynptr_read(&buf, len, &ptr_buf, i * len, 0); + if (err) + goto out; + if (bpf_memcmp(data, buf, len) != 0) + goto out; + } + + /* Both source and destination dynptrs are backed by non-contiguous memory */ + err = bpf_dynptr_copy(&ptr_xdp, 2, &ptr_xdp, len, len * (chunks - 1)); + if (err) + goto out; + + bpf_for(i, 0, chunks - 1) { + __builtin_memset(buf, 0, sizeof(buf)); + err = bpf_dynptr_read(&buf, len, &ptr_xdp, 2 + i * len, 0); + if (err) + goto out; + if (bpf_memcmp(data, buf, len) != 0) + goto out; + } + + if (bpf_dynptr_copy(&ptr_xdp, 2000, &ptr_xdp, 0, len * chunks) != -E2BIG) + err = 1; + +out: + bpf_ringbuf_discard_dynptr(&ptr_buf, 0); + return XDP_DROP; +} diff --git a/tools/testing/selftests/bpf/progs/fexit_noreturns.c b/tools/testing/selftests/bpf/progs/fexit_noreturns.c new file mode 100644 index 0000000..5465453 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fexit_noreturns.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +SEC("fexit/do_exit") +__failure __msg("Attaching fexit/fmod_ret to __noreturn functions is rejected.") +int BPF_PROG(noreturns) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/irq.c b/tools/testing/selftests/bpf/progs/irq.c index b0b53d9..298d48d 100644 --- a/tools/testing/selftests/bpf/progs/irq.c +++ b/tools/testing/selftests/bpf/progs/irq.c @@ -222,7 +222,7 @@ int __noinline global_local_irq_balance(void) } SEC("?tc") -__failure __msg("global function calls are not allowed with IRQs disabled") +__success int irq_global_subprog(struct __sk_buff *ctx) { unsigned long flags; @@ -441,4 +441,73 @@ int irq_ooo_refs_array(struct __sk_buff *ctx) return 0; } +int __noinline +global_subprog(int i) +{ + if (i) + bpf_printk("%p", &i); + return i; +} + +int __noinline +global_sleepable_helper_subprog(int i) +{ + if (i) + bpf_copy_from_user(&i, sizeof(i), NULL); + return i; +} + +int __noinline +global_sleepable_kfunc_subprog(int i) +{ + if (i) + bpf_copy_from_user_str(&i, sizeof(i), NULL, 0); + global_subprog(i); + return i; +} + +int __noinline +global_subprog_calling_sleepable_global(int i) +{ + if (!i) + global_sleepable_kfunc_subprog(i); + return i; +} + +SEC("?syscall") +__success +int irq_non_sleepable_global_subprog(void *ctx) +{ + unsigned long flags; + + bpf_local_irq_save(&flags); + global_subprog(0); + bpf_local_irq_restore(&flags); + return 0; +} + +SEC("?syscall") +__failure __msg("global functions that may sleep are not allowed in non-sleepable context") +int irq_sleepable_helper_global_subprog(void *ctx) +{ + unsigned long flags; + + bpf_local_irq_save(&flags); + global_sleepable_helper_subprog(0); + bpf_local_irq_restore(&flags); + return 0; +} + +SEC("?syscall") +__failure __msg("global functions that may sleep are not allowed in non-sleepable context") +int irq_sleepable_global_subprog_indirect(void *ctx) +{ + unsigned long flags; + + bpf_local_irq_save(&flags); + global_subprog_calling_sleepable_global(0); + bpf_local_irq_restore(&flags); + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index 190822b..427b729 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -7,6 +7,8 @@ #include "bpf_misc.h" #include "bpf_compiler.h" +#define unlikely(x) __builtin_expect(!!(x), 0) + static volatile int zero = 0; int my_pid; @@ -1175,6 +1177,122 @@ __naked int loop_state_deps2(void) } SEC("?raw_tp") +__failure +__msg("math between fp pointer and register with unbounded") +__flag(BPF_F_TEST_STATE_FREQ) +__naked int loop_state_deps3(void) +{ + /* This is equivalent to a C program below. + * + * if (random() != 24) { // assume false branch is placed first + * i = iter_new(); // fp[-8] + * while (iter_next(i)); + * iter_destroy(i); + * return; + * } + * + * for (i = 10; i > 0; i--); // increase dfs_depth for child states + * + * i = iter_new(); // fp[-8] + * b = -24; // r8 + * for (;;) { // checkpoint (L) + * if (iter_next(i)) // checkpoint (N) + * break; + * if (random() == 77) { // assume false branch is placed first + * *(u64 *)(r10 + b) = 7; // this is not safe when b == -25 + * iter_destroy(i); + * return; + * } + * if (random() == 42) { // assume false branch is placed first + * b = -25; + * } + * } + * iter_destroy(i); + * + * In case of a buggy verifier first loop might poison + * env->cur_state->loop_entry with a state having 0 branches + * and small dfs_depth. This would trigger NOT_EXACT states + * comparison for some states within second loop. + * Specifically, checkpoint (L) might be problematic if: + * - branch with '*(u64 *)(r10 + b) = 7' is not explored yet; + * - checkpoint (L) is first reached in state {b=-24}; + * - traversal is pruned at checkpoint (N) setting checkpoint's (L) + * branch count to 0, thus making it eligible for use in pruning; + * - checkpoint (L) is next reached in state {b=-25}, + * this would cause NOT_EXACT comparison with a state {b=-24} + * while 'b' is not marked precise yet. + */ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "if r0 == 24 goto 2f;" + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 5;" + "call %[bpf_iter_num_new];" + "1:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 != 0 goto 1b;" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + "2:" + /* loop to increase dfs_depth */ + "r0 = 10;" + "3:" + "r0 -= 1;" + "if r0 != 0 goto 3b;" + /* end of loop */ + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r8 = -24;" + "main_loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto main_loop_end_%=;" + /* first if */ + "call %[bpf_get_prandom_u32];" + "if r0 == 77 goto unsafe_write_%=;" + /* second if */ + "call %[bpf_get_prandom_u32];" + "if r0 == 42 goto poison_r8_%=;" + /* iterate */ + "goto main_loop_%=;" + "main_loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + + "unsafe_write_%=:" + "r0 = r10;" + "r0 += r8;" + "r1 = 7;" + "*(u64 *)(r0 + 0) = r1;" + "goto main_loop_end_%=;" + + "poison_r8_%=:" + "r8 = -25;" + "goto main_loop_%=;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy) + : __clobber_all + ); +} + +SEC("?raw_tp") __success __naked int triple_continue(void) { @@ -1512,4 +1630,25 @@ int iter_destroy_bad_arg(const void *ctx) return 0; } +SEC("raw_tp") +__success +int clean_live_states(const void *ctx) +{ + char buf[1]; + int i, j, k, l, m, n, o; + + bpf_for(i, 0, 10) + bpf_for(j, 0, 10) + bpf_for(k, 0, 10) + bpf_for(l, 0, 10) + bpf_for(m, 0, 10) + bpf_for(n, 0, 10) + bpf_for(o, 0, 10) { + if (unlikely(bpf_get_prandom_u32())) + buf[0] = 42; + bpf_printk("%s", buf); + } + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/netns_cookie_prog.c b/tools/testing/selftests/bpf/progs/netns_cookie_prog.c index c6edf8d..9404071 100644 --- a/tools/testing/selftests/bpf/progs/netns_cookie_prog.c +++ b/tools/testing/selftests/bpf/progs/netns_cookie_prog.c @@ -28,6 +28,7 @@ struct { } sock_map SEC(".maps"); int tcx_init_netns_cookie, tcx_netns_cookie; +int cgroup_skb_init_netns_cookie, cgroup_skb_netns_cookie; SEC("sockops") int get_netns_cookie_sockops(struct bpf_sock_ops *ctx) @@ -91,4 +92,12 @@ int get_netns_cookie_tcx(struct __sk_buff *skb) return TCX_PASS; } +SEC("cgroup_skb/ingress") +int get_netns_cookie_cgroup_skb(struct __sk_buff *skb) +{ + cgroup_skb_init_netns_cookie = bpf_get_netns_cookie(NULL); + cgroup_skb_netns_cookie = bpf_get_netns_cookie(skb); + return SK_PASS; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/preempt_lock.c b/tools/testing/selftests/bpf/progs/preempt_lock.c index 6c5797b..7d04254 100644 --- a/tools/testing/selftests/bpf/progs/preempt_lock.c +++ b/tools/testing/selftests/bpf/progs/preempt_lock.c @@ -134,7 +134,7 @@ int __noinline preempt_global_subprog(void) } SEC("?tc") -__failure __msg("global function calls are not allowed with preemption disabled") +__success int preempt_global_subprog_test(struct __sk_buff *ctx) { preempt_disable(); @@ -143,4 +143,70 @@ int preempt_global_subprog_test(struct __sk_buff *ctx) return 0; } +int __noinline +global_subprog(int i) +{ + if (i) + bpf_printk("%p", &i); + return i; +} + +int __noinline +global_sleepable_helper_subprog(int i) +{ + if (i) + bpf_copy_from_user(&i, sizeof(i), NULL); + return i; +} + +int __noinline +global_sleepable_kfunc_subprog(int i) +{ + if (i) + bpf_copy_from_user_str(&i, sizeof(i), NULL, 0); + global_subprog(i); + return i; +} + +int __noinline +global_subprog_calling_sleepable_global(int i) +{ + if (!i) + global_sleepable_kfunc_subprog(i); + return i; +} + +SEC("?syscall") +__failure __msg("global functions that may sleep are not allowed in non-sleepable context") +int preempt_global_sleepable_helper_subprog(struct __sk_buff *ctx) +{ + preempt_disable(); + if (ctx->mark) + global_sleepable_helper_subprog(ctx->mark); + preempt_enable(); + return 0; +} + +SEC("?syscall") +__failure __msg("global functions that may sleep are not allowed in non-sleepable context") +int preempt_global_sleepable_kfunc_subprog(struct __sk_buff *ctx) +{ + preempt_disable(); + if (ctx->mark) + global_sleepable_kfunc_subprog(ctx->mark); + preempt_enable(); + return 0; +} + +SEC("?syscall") +__failure __msg("global functions that may sleep are not allowed in non-sleepable context") +int preempt_global_sleepable_subprog_indirect(struct __sk_buff *ctx) +{ + preempt_disable(); + if (ctx->mark) + global_subprog_calling_sleepable_global(ctx->mark); + preempt_enable(); + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/prepare.c b/tools/testing/selftests/bpf/progs/prepare.c new file mode 100644 index 0000000..1f1dd54 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/prepare.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta */ +#include +#include +//#include + +char _license[] SEC("license") = "GPL"; + +int err; + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 4096); +} ringbuf SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} array_map SEC(".maps"); + +SEC("cgroup_skb/egress") +int program(struct __sk_buff *skb) +{ + err = 0; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/priv_freplace_prog.c b/tools/testing/selftests/bpf/progs/priv_freplace_prog.c new file mode 100644 index 0000000..ccf1b04 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/priv_freplace_prog.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include + +char _license[] SEC("license") = "GPL"; + +SEC("freplace/xdp_prog1") +int new_xdp_prog2(struct xdp_md *xd) +{ + return XDP_DROP; +} diff --git a/tools/testing/selftests/bpf/progs/priv_prog.c b/tools/testing/selftests/bpf/progs/priv_prog.c index 3c7b2b6..725e295 100644 --- a/tools/testing/selftests/bpf/progs/priv_prog.c +++ b/tools/testing/selftests/bpf/progs/priv_prog.c @@ -6,8 +6,8 @@ char _license[] SEC("license") = "GPL"; -SEC("kprobe") -int kprobe_prog(void *ctx) +SEC("xdp") +int xdp_prog1(struct xdp_md *xdp) { - return 1; + return XDP_DROP; } diff --git a/tools/testing/selftests/bpf/progs/pro_epilogue_with_kfunc.c b/tools/testing/selftests/bpf/progs/pro_epilogue_with_kfunc.c new file mode 100644 index 0000000..a5a8f08 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pro_epilogue_with_kfunc.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include +#include +#include "bpf_misc.h" +#include "../test_kmods/bpf_testmod.h" +#include "../test_kmods/bpf_testmod_kfunc.h" + +char _license[] SEC("license") = "GPL"; + +void __kfunc_btf_root(void) +{ + bpf_kfunc_st_ops_inc10(NULL); +} + +static __noinline __used int subprog(struct st_ops_args *args) +{ + args->a += 1; + return args->a; +} + +__success +/* prologue */ +__xlated("0: r8 = r1") +__xlated("1: r1 = 0") +__xlated("2: call kernel-function") +__xlated("3: if r0 != 0x0 goto pc+5") +__xlated("4: r6 = *(u64 *)(r8 +0)") +__xlated("5: r7 = *(u64 *)(r6 +0)") +__xlated("6: r7 += 1000") +__xlated("7: *(u64 *)(r6 +0) = r7") +__xlated("8: goto pc+2") +__xlated("9: r1 = r0") +__xlated("10: call kernel-function") +__xlated("11: r1 = r8") +/* save __u64 *ctx to stack */ +__xlated("12: *(u64 *)(r10 -8) = r1") +/* main prog */ +__xlated("13: r1 = *(u64 *)(r1 +0)") +__xlated("14: r6 = r1") +__xlated("15: call kernel-function") +__xlated("16: r1 = r6") +__xlated("17: call pc+") +/* epilogue */ +__xlated("18: r1 = 0") +__xlated("19: r6 = 0") +__xlated("20: call kernel-function") +__xlated("21: if r0 != 0x0 goto pc+6") +__xlated("22: r1 = *(u64 *)(r10 -8)") +__xlated("23: r1 = *(u64 *)(r1 +0)") +__xlated("24: r6 = *(u64 *)(r1 +0)") +__xlated("25: r6 += 10000") +__xlated("26: *(u64 *)(r1 +0) = r6") +__xlated("27: goto pc+2") +__xlated("28: r1 = r0") +__xlated("29: call kernel-function") +__xlated("30: r0 = r6") +__xlated("31: r0 *= 2") +__xlated("32: exit") +SEC("struct_ops/test_pro_epilogue") +__naked int test_kfunc_pro_epilogue(void) +{ + asm volatile ( + "r1 = *(u64 *)(r1 +0);" + "r6 = r1;" + "call %[bpf_kfunc_st_ops_inc10];" + "r1 = r6;" + "call subprog;" + "exit;" + : + : __imm(bpf_kfunc_st_ops_inc10) + : __clobber_all); +} + +SEC("syscall") +__retval(22022) /* (PROLOGUE_A [1000] + KFUNC_INC10 + SUBPROG_A [1] + EPILOGUE_A [10000]) * 2 */ +int syscall_pro_epilogue(void *ctx) +{ + struct st_ops_args args = {}; + + return bpf_kfunc_st_ops_test_pro_epilogue(&args); +} + +SEC(".struct_ops.link") +struct bpf_testmod_st_ops pro_epilogue_with_kfunc = { + .test_pro_epilogue = (void *)test_kfunc_pro_epilogue, +}; diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c b/tools/testing/selftests/bpf/progs/rcu_read_lock.c index ab3a532..43637ee 100644 --- a/tools/testing/selftests/bpf/progs/rcu_read_lock.c +++ b/tools/testing/selftests/bpf/progs/rcu_read_lock.c @@ -242,7 +242,8 @@ out: } SEC("?lsm.s/bpf") -int BPF_PROG(inproper_sleepable_kfunc, int cmd, union bpf_attr *attr, unsigned int size) +int BPF_PROG(inproper_sleepable_kfunc, int cmd, union bpf_attr *attr, unsigned int size, + bool kernel) { struct bpf_key *bkey; @@ -439,3 +440,61 @@ int rcu_read_lock_global_subprog_unlock(void *ctx) ret += global_subprog_unlock(ret); return 0; } + +int __noinline +global_sleepable_helper_subprog(int i) +{ + if (i) + bpf_copy_from_user(&i, sizeof(i), NULL); + return i; +} + +int __noinline +global_sleepable_kfunc_subprog(int i) +{ + if (i) + bpf_copy_from_user_str(&i, sizeof(i), NULL, 0); + global_subprog(i); + return i; +} + +int __noinline +global_subprog_calling_sleepable_global(int i) +{ + if (!i) + global_sleepable_kfunc_subprog(i); + return i; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int rcu_read_lock_sleepable_helper_global_subprog(void *ctx) +{ + volatile int ret = 0; + + bpf_rcu_read_lock(); + ret += global_sleepable_helper_subprog(ret); + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int rcu_read_lock_sleepable_kfunc_global_subprog(void *ctx) +{ + volatile int ret = 0; + + bpf_rcu_read_lock(); + ret += global_sleepable_kfunc_subprog(ret); + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int rcu_read_lock_sleepable_global_subprog_indirect(void *ctx) +{ + volatile int ret = 0; + + bpf_rcu_read_lock(); + ret += global_subprog_calling_sleepable_global(ret); + bpf_rcu_read_unlock(); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/read_vsyscall.c b/tools/testing/selftests/bpf/progs/read_vsyscall.c index 39ebef4..3955913 100644 --- a/tools/testing/selftests/bpf/progs/read_vsyscall.c +++ b/tools/testing/selftests/bpf/progs/read_vsyscall.c @@ -8,14 +8,16 @@ int target_pid = 0; void *user_ptr = 0; -int read_ret[9]; +int read_ret[10]; char _license[] SEC("license") = "GPL"; /* - * This is the only kfunc, the others are helpers + * These are the kfuncs, the others are helpers */ int bpf_copy_from_user_str(void *dst, u32, const void *, u64) __weak __ksym; +int bpf_copy_from_user_task_str(void *dst, u32, const void *, + struct task_struct *, u64) __weak __ksym; SEC("fentry/" SYS_PREFIX "sys_nanosleep") int do_probe_read(void *ctx) @@ -47,6 +49,11 @@ int do_copy_from_user(void *ctx) read_ret[7] = bpf_copy_from_user_task(buf, sizeof(buf), user_ptr, bpf_get_current_task_btf(), 0); read_ret[8] = bpf_copy_from_user_str((char *)buf, sizeof(buf), user_ptr, 0); + read_ret[9] = bpf_copy_from_user_task_str((char *)buf, + sizeof(buf), + user_ptr, + bpf_get_current_task_btf(), + 0); return 0; } diff --git a/tools/testing/selftests/bpf/progs/set_global_vars.c b/tools/testing/selftests/bpf/progs/set_global_vars.c new file mode 100644 index 0000000..9adb5ba --- /dev/null +++ b/tools/testing/selftests/bpf/progs/set_global_vars.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include "bpf_experimental.h" +#include +#include "bpf_misc.h" +#include + +char _license[] SEC("license") = "GPL"; + +enum Enum { EA1 = 0, EA2 = 11 }; +enum Enumu64 {EB1 = 0llu, EB2 = 12llu }; +enum Enums64 { EC1 = 0ll, EC2 = 13ll }; + +const volatile __s64 var_s64 = -1; +const volatile __u64 var_u64 = 0; +const volatile __s32 var_s32 = -1; +const volatile __u32 var_u32 = 0; +const volatile __s16 var_s16 = -1; +const volatile __u16 var_u16 = 0; +const volatile __s8 var_s8 = -1; +const volatile __u8 var_u8 = 0; +const volatile enum Enum var_ea = EA1; +const volatile enum Enumu64 var_eb = EB1; +const volatile enum Enums64 var_ec = EC1; +const volatile bool var_b = false; + +char arr[4] = {0}; + +SEC("socket") +int test_set_globals(void *ctx) +{ + volatile __s8 a; + + a = var_s64; + a = var_u64; + a = var_s32; + a = var_u32; + a = var_s16; + a = var_u16; + a = var_s8; + a = var_u8; + a = var_ea; + a = var_eb; + a = var_ec; + a = var_b; + return a; +} diff --git a/tools/testing/selftests/bpf/progs/strncmp_bench.c b/tools/testing/selftests/bpf/progs/strncmp_bench.c index 18373a7..f47bf88 100644 --- a/tools/testing/selftests/bpf/progs/strncmp_bench.c +++ b/tools/testing/selftests/bpf/progs/strncmp_bench.c @@ -35,7 +35,10 @@ static __always_inline int local_strncmp(const char *s1, unsigned int sz, SEC("tp/syscalls/sys_enter_getpgid") int strncmp_no_helper(void *ctx) { - if (local_strncmp(str, cmp_str_len + 1, target) < 0) + const char *target_str = target; + + barrier_var(target_str); + if (local_strncmp(str, cmp_str_len + 1, target_str) < 0) __sync_add_and_fetch(&hits, 1); return 0; } diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c new file mode 100644 index 0000000..36386b3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c @@ -0,0 +1,30 @@ +#include +#include +#include "../test_kmods/bpf_testmod.h" +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +void bpf_task_release(struct task_struct *p) __ksym; + +/* This test struct_ops BPF programs returning referenced kptr. The verifier should + * allow a referenced kptr or a NULL pointer to be returned. A referenced kptr to task + * here is acquried automatically as the task argument is tagged with "__ref". + */ +SEC("struct_ops/test_return_ref_kptr") +struct task_struct *BPF_PROG(kptr_return, int dummy, + struct task_struct *task, struct cgroup *cgrp) +{ + if (dummy % 2) { + bpf_task_release(task); + return NULL; + } + return task; +} + +SEC(".struct_ops.link") +struct bpf_testmod_ops testmod_kptr_return = { + .test_return_ref_kptr = (void *)kptr_return, +}; + + diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__invalid_scalar.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__invalid_scalar.c new file mode 100644 index 0000000..caeea15 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__invalid_scalar.c @@ -0,0 +1,26 @@ +#include +#include +#include "../test_kmods/bpf_testmod.h" +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym; +void bpf_task_release(struct task_struct *p) __ksym; + +/* This test struct_ops BPF programs returning referenced kptr. The verifier should + * reject programs returning a non-zero scalar value. + */ +SEC("struct_ops/test_return_ref_kptr") +__failure __msg("At program exit the register R0 has smin=1 smax=1 should have been in [0, 0]") +struct task_struct *BPF_PROG(kptr_return_fail__invalid_scalar, int dummy, + struct task_struct *task, struct cgroup *cgrp) +{ + bpf_task_release(task); + return (struct task_struct *)1; +} + +SEC(".struct_ops.link") +struct bpf_testmod_ops testmod_kptr_return = { + .test_return_ref_kptr = (void *)kptr_return_fail__invalid_scalar, +}; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__local_kptr.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__local_kptr.c new file mode 100644 index 0000000..b8b4f05 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__local_kptr.c @@ -0,0 +1,34 @@ +#include +#include +#include "../test_kmods/bpf_testmod.h" +#include "bpf_experimental.h" +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym; +void bpf_task_release(struct task_struct *p) __ksym; + +/* This test struct_ops BPF programs returning referenced kptr. The verifier should + * reject programs returning a local kptr. + */ +SEC("struct_ops/test_return_ref_kptr") +__failure __msg("At program exit the register R0 is not a known value (ptr_or_null_)") +struct task_struct *BPF_PROG(kptr_return_fail__local_kptr, int dummy, + struct task_struct *task, struct cgroup *cgrp) +{ + struct task_struct *t; + + bpf_task_release(task); + + t = bpf_obj_new(typeof(*task)); + if (!t) + return NULL; + + return t; +} + +SEC(".struct_ops.link") +struct bpf_testmod_ops testmod_kptr_return = { + .test_return_ref_kptr = (void *)kptr_return_fail__local_kptr, +}; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__nonzero_offset.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__nonzero_offset.c new file mode 100644 index 0000000..7ddeb28 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__nonzero_offset.c @@ -0,0 +1,25 @@ +#include +#include +#include "../test_kmods/bpf_testmod.h" +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym; +void bpf_task_release(struct task_struct *p) __ksym; + +/* This test struct_ops BPF programs returning referenced kptr. The verifier should + * reject programs returning a modified referenced kptr. + */ +SEC("struct_ops/test_return_ref_kptr") +__failure __msg("dereference of modified trusted_ptr_ ptr R0 off={{[0-9]+}} disallowed") +struct task_struct *BPF_PROG(kptr_return_fail__nonzero_offset, int dummy, + struct task_struct *task, struct cgroup *cgrp) +{ + return (struct task_struct *)&task->jobctl; +} + +SEC(".struct_ops.link") +struct bpf_testmod_ops testmod_kptr_return = { + .test_return_ref_kptr = (void *)kptr_return_fail__nonzero_offset, +}; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c new file mode 100644 index 0000000..6a2dd53 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c @@ -0,0 +1,30 @@ +#include +#include +#include "../test_kmods/bpf_testmod.h" +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym; +void bpf_task_release(struct task_struct *p) __ksym; + +/* This test struct_ops BPF programs returning referenced kptr. The verifier should + * reject programs returning a referenced kptr of the wrong type. + */ +SEC("struct_ops/test_return_ref_kptr") +__failure __msg("At program exit the register R0 is not a known value (ptr_or_null_)") +struct task_struct *BPF_PROG(kptr_return_fail__wrong_type, int dummy, + struct task_struct *task, struct cgroup *cgrp) +{ + struct task_struct *ret; + + ret = (struct task_struct *)bpf_cgroup_acquire(cgrp); + bpf_task_release(task); + + return ret; +} + +SEC(".struct_ops.link") +struct bpf_testmod_ops testmod_kptr_return = { + .test_return_ref_kptr = (void *)kptr_return_fail__wrong_type, +}; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c new file mode 100644 index 0000000..76dcb60 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c @@ -0,0 +1,31 @@ +#include +#include +#include "../test_kmods/bpf_testmod.h" +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +__attribute__((nomerge)) extern void bpf_task_release(struct task_struct *p) __ksym; + +/* This is a test BPF program that uses struct_ops to access a referenced + * kptr argument. This is a test for the verifier to ensure that it + * 1) recongnizes the task as a referenced object (i.e., ref_obj_id > 0), and + * 2) the same reference can be acquired from multiple paths as long as it + * has not been released. + */ +SEC("struct_ops/test_refcounted") +int BPF_PROG(refcounted, int dummy, struct task_struct *task) +{ + if (dummy == 1) + bpf_task_release(task); + else + bpf_task_release(task); + return 0; +} + +SEC(".struct_ops.link") +struct bpf_testmod_ops testmod_refcounted = { + .test_refcounted = (void *)refcounted, +}; + + diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__global_subprog.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__global_subprog.c new file mode 100644 index 0000000..ae074aa --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__global_subprog.c @@ -0,0 +1,39 @@ +#include +#include +#include "../test_kmods/bpf_testmod.h" +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +extern void bpf_task_release(struct task_struct *p) __ksym; + +__noinline int subprog_release(__u64 *ctx __arg_ctx) +{ + struct task_struct *task = (struct task_struct *)ctx[1]; + int dummy = (int)ctx[0]; + + bpf_task_release(task); + + return dummy + 1; +} + +/* Test that the verifier rejects a program that contains a global + * subprogram with referenced kptr arguments + */ +SEC("struct_ops/test_refcounted") +__failure __log_level(2) +__msg("Validating subprog_release() func#1...") +__msg("invalid bpf_context access off=8. Reference may already be released") +int refcounted_fail__global_subprog(unsigned long long *ctx) +{ + struct task_struct *task = (struct task_struct *)ctx[1]; + + bpf_task_release(task); + + return subprog_release(ctx); +} + +SEC(".struct_ops.link") +struct bpf_testmod_ops testmod_ref_acquire = { + .test_refcounted = (void *)refcounted_fail__global_subprog, +}; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__ref_leak.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__ref_leak.c new file mode 100644 index 0000000..e945b1a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__ref_leak.c @@ -0,0 +1,22 @@ +#include +#include +#include "../test_kmods/bpf_testmod.h" +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +/* Test that the verifier rejects a program that acquires a referenced + * kptr through context without releasing the reference + */ +SEC("struct_ops/test_refcounted") +__failure __msg("Unreleased reference id=1 alloc_insn=0") +int BPF_PROG(refcounted_fail__ref_leak, int dummy, + struct task_struct *task) +{ + return 0; +} + +SEC(".struct_ops.link") +struct bpf_testmod_ops testmod_ref_acquire = { + .test_refcounted = (void *)refcounted_fail__ref_leak, +}; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__tail_call.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__tail_call.c new file mode 100644 index 0000000..3b12502 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__tail_call.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include +#include +#include "../test_kmods/bpf_testmod.h" +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} prog_array SEC(".maps"); + +/* Test that the verifier rejects a program with referenced kptr arguments + * that tail call + */ +SEC("struct_ops/test_refcounted") +__failure __msg("program with __ref argument cannot tail call") +int refcounted_fail__tail_call(unsigned long long *ctx) +{ + struct task_struct *task = (struct task_struct *)ctx[1]; + + bpf_task_release(task); + bpf_tail_call(ctx, &prog_array, 0); + + return 0; +} + +SEC(".struct_ops.link") +struct bpf_testmod_ops testmod_ref_acquire = { + .test_refcounted = (void *)refcounted_fail__tail_call, +}; + diff --git a/tools/testing/selftests/bpf/progs/changes_pkt_data.c b/tools/testing/selftests/bpf/progs/summarization.c similarity index 62% rename from tools/testing/selftests/bpf/progs/changes_pkt_data.c rename to tools/testing/selftests/bpf/progs/summarization.c index 43cada4..f89effe 100644 --- a/tools/testing/selftests/bpf/progs/changes_pkt_data.c +++ b/tools/testing/selftests/bpf/progs/summarization.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include +#include #include +#include "bpf_misc.h" __noinline long changes_pkt_data(struct __sk_buff *sk) @@ -16,7 +17,7 @@ long does_not_change_pkt_data(struct __sk_buff *sk) } SEC("?tc") -int main_with_subprogs(struct __sk_buff *sk) +int main_changes_with_subprogs(struct __sk_buff *sk) { changes_pkt_data(sk); does_not_change_pkt_data(sk); @@ -36,4 +37,42 @@ int main_does_not_change(struct __sk_buff *sk) return 0; } +__noinline +long might_sleep(struct pt_regs *ctx __arg_ctx) +{ + int i; + + bpf_copy_from_user(&i, sizeof(i), NULL); + return i; +} + +__noinline __weak +long does_not_sleep(struct pt_regs *ctx __arg_ctx) +{ + return 0; +} + +SEC("?uprobe.s") +int main_might_sleep_with_subprogs(struct pt_regs *ctx) +{ + might_sleep(ctx); + does_not_sleep(ctx); + return 0; +} + +SEC("?uprobe.s") +int main_might_sleep(struct pt_regs *ctx) +{ + int i; + + bpf_copy_from_user(&i, sizeof(i), NULL); + return i; +} + +SEC("?uprobe.s") +int main_does_not_sleep(struct pt_regs *ctx) +{ + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c b/tools/testing/selftests/bpf/progs/summarization_freplace.c similarity index 65% rename from tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c rename to tools/testing/selftests/bpf/progs/summarization_freplace.c index f9a6227..935f00e 100644 --- a/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c +++ b/tools/testing/selftests/bpf/progs/summarization_freplace.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 -#include +#include #include SEC("?freplace") @@ -15,4 +15,19 @@ long does_not_change_pkt_data(struct __sk_buff *sk) return 0; } +SEC("?freplace") +long might_sleep(struct pt_regs *ctx) +{ + int i; + + bpf_copy_from_user(&i, sizeof(i), NULL); + return i; +} + +SEC("?freplace") +long does_not_sleep(struct pt_regs *ctx) +{ + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c b/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c index 4462886..4fee0fd 100644 --- a/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c +++ b/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c @@ -51,13 +51,13 @@ out: } SEC("lsm/bpf") -int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size) +int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size, bool kernel) { return bpf_link_create_verify(cmd); } SEC("lsm.s/bpf") -int BPF_PROG(lsm_s_run, int cmd, union bpf_attr *attr, unsigned int size) +int BPF_PROG(lsm_s_run, int cmd, union bpf_attr *attr, unsigned int size, bool kernel) { return bpf_link_create_verify(cmd); } diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c index 51b3f79..4484036 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c @@ -15,6 +15,7 @@ struct { struct core_reloc_arrays_output { int a2; + int a3; char b123; int c1c; int d00d; @@ -41,6 +42,7 @@ int test_core_arrays(void *ctx) { struct core_reloc_arrays *in = (void *)&data.in; struct core_reloc_arrays_output *out = (void *)&data.out; + int *a; if (CORE_READ(&out->a2, &in->a[2])) return 1; @@ -53,6 +55,9 @@ int test_core_arrays(void *ctx) if (CORE_READ(&out->f01c, &in->f[0][1].c)) return 1; + a = __builtin_preserve_access_index(({ in->a; })); + out->a3 = a[0] + a[1] + a[2] + a[3]; + return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_get_xattr.c b/tools/testing/selftests/bpf/progs/test_get_xattr.c index 66e7377..54305f4 100644 --- a/tools/testing/selftests/bpf/progs/test_get_xattr.c +++ b/tools/testing/selftests/bpf/progs/test_get_xattr.c @@ -6,6 +6,7 @@ #include #include #include "bpf_kfuncs.h" +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -17,12 +18,23 @@ static const char expected_value[] = "hello"; char value1[32]; char value2[32]; +/* Matches caller of test_get_xattr() in prog_tests/fs_kfuncs.c */ +static const char xattr_names[][64] = { + /* The following work. */ + "user.kfuncs", + "security.bpf.xxx", + + /* The following do not work. */ + "security.bpf", + "security.selinux" +}; + SEC("lsm.s/file_open") int BPF_PROG(test_file_open, struct file *f) { struct bpf_dynptr value_ptr; __u32 pid; - int ret; + int ret, i; pid = bpf_get_current_pid_tgid() >> 32; if (pid != monitored_pid) @@ -30,7 +42,11 @@ int BPF_PROG(test_file_open, struct file *f) bpf_dynptr_from_mem(value1, sizeof(value1), 0, &value_ptr); - ret = bpf_get_file_xattr(f, "user.kfuncs", &value_ptr); + for (i = 0; i < ARRAY_SIZE(xattr_names); i++) { + ret = bpf_get_file_xattr(f, xattr_names[i], &value_ptr); + if (ret == sizeof(expected_value)) + break; + } if (ret != sizeof(expected_value)) return 0; if (bpf_strncmp(value1, ret, expected_value)) @@ -44,7 +60,7 @@ int BPF_PROG(test_inode_getxattr, struct dentry *dentry, char *name) { struct bpf_dynptr value_ptr; __u32 pid; - int ret; + int ret, i; pid = bpf_get_current_pid_tgid() >> 32; if (pid != monitored_pid) @@ -52,7 +68,11 @@ int BPF_PROG(test_inode_getxattr, struct dentry *dentry, char *name) bpf_dynptr_from_mem(value2, sizeof(value2), 0, &value_ptr); - ret = bpf_get_dentry_xattr(dentry, "user.kfuncs", &value_ptr); + for (i = 0; i < ARRAY_SIZE(xattr_names); i++) { + ret = bpf_get_dentry_xattr(dentry, xattr_names[i], &value_ptr); + if (ret == sizeof(expected_value)) + break; + } if (ret != sizeof(expected_value)) return 0; if (bpf_strncmp(value2, ret, expected_value)) diff --git a/tools/testing/selftests/bpf/progs/test_kernel_flag.c b/tools/testing/selftests/bpf/progs/test_kernel_flag.c new file mode 100644 index 0000000..b45fab3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_kernel_flag.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (C) 2025 Microsoft Corporation + * + * Author: Blaise Boscaccy + */ + +#include "vmlinux.h" +#include +#include +#include + +char _license[] SEC("license") = "GPL"; + +__u32 monitored_tid; + +SEC("lsm.s/bpf") +int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size, bool kernel) +{ + __u32 tid; + + tid = bpf_get_current_pid_tgid() & 0xFFFFFFFF; + if (!kernel || tid != monitored_tid) + return 0; + else + return -EINVAL; +} diff --git a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c index cd4d752..061befb 100644 --- a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c +++ b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c @@ -36,7 +36,7 @@ char _license[] SEC("license") = "GPL"; SEC("?lsm.s/bpf") __failure __msg("cannot pass in dynptr at an offset=-8") -int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size) +int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size, bool kernel) { unsigned long val; @@ -46,7 +46,7 @@ int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size) SEC("?lsm.s/bpf") __failure __msg("arg#0 expected pointer to stack or const struct bpf_dynptr") -int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size) +int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size, bool kernel) { unsigned long val = 0; @@ -55,7 +55,7 @@ int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size) } SEC("lsm.s/bpf") -int BPF_PROG(dynptr_data_null, int cmd, union bpf_attr *attr, unsigned int size) +int BPF_PROG(dynptr_data_null, int cmd, union bpf_attr *attr, unsigned int size, bool kernel) { struct bpf_key *trusted_keyring; struct bpf_dynptr ptr; diff --git a/tools/testing/selftests/bpf/progs/test_lookup_key.c b/tools/testing/selftests/bpf/progs/test_lookup_key.c index c737769..cdbbb12 100644 --- a/tools/testing/selftests/bpf/progs/test_lookup_key.c +++ b/tools/testing/selftests/bpf/progs/test_lookup_key.c @@ -23,7 +23,7 @@ extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym; extern void bpf_key_put(struct bpf_key *key) __ksym; SEC("lsm.s/bpf") -int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size) +int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size, bool kernel) { struct bpf_key *bkey; __u32 pid; diff --git a/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c index 2fdc44e..89b0cd5 100644 --- a/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c +++ b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c @@ -7,7 +7,7 @@ char tp_name[128]; SEC("lsm.s/bpf") -int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size) +int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size, bool kernel) { switch (cmd) { case BPF_RAW_TRACEPOINT_OPEN: diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c index 5eb25c6..a5be326 100644 --- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c +++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018 Facebook */ -#include #include #include #include diff --git a/tools/testing/selftests/bpf/progs/test_set_remove_xattr.c b/tools/testing/selftests/bpf/progs/test_set_remove_xattr.c new file mode 100644 index 0000000..6a612cf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_set_remove_xattr.c @@ -0,0 +1,133 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include +#include +#include "bpf_kfuncs.h" +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +__u32 monitored_pid; + +const char xattr_foo[] = "security.bpf.foo"; +const char xattr_bar[] = "security.bpf.bar"; +static const char xattr_selinux[] = "security.selinux"; +char value_bar[] = "world"; +char read_value[32]; + +bool set_security_bpf_bar_success; +bool remove_security_bpf_bar_success; +bool set_security_selinux_fail; +bool remove_security_selinux_fail; + +char name_buf[32]; + +static inline bool name_match_foo(const char *name) +{ + bpf_probe_read_kernel(name_buf, sizeof(name_buf), name); + + return !bpf_strncmp(name_buf, sizeof(xattr_foo), xattr_foo); +} + +/* Test bpf_set_dentry_xattr and bpf_remove_dentry_xattr */ +SEC("lsm.s/inode_getxattr") +int BPF_PROG(test_inode_getxattr, struct dentry *dentry, char *name) +{ + struct bpf_dynptr value_ptr; + __u32 pid; + int ret; + + pid = bpf_get_current_pid_tgid() >> 32; + if (pid != monitored_pid) + return 0; + + /* Only do the following for security.bpf.foo */ + if (!name_match_foo(name)) + return 0; + + bpf_dynptr_from_mem(read_value, sizeof(read_value), 0, &value_ptr); + + /* read security.bpf.bar */ + ret = bpf_get_dentry_xattr(dentry, xattr_bar, &value_ptr); + + if (ret < 0) { + /* If security.bpf.bar doesn't exist, set it */ + bpf_dynptr_from_mem(value_bar, sizeof(value_bar), 0, &value_ptr); + + ret = bpf_set_dentry_xattr(dentry, xattr_bar, &value_ptr, 0); + if (!ret) + set_security_bpf_bar_success = true; + ret = bpf_set_dentry_xattr(dentry, xattr_selinux, &value_ptr, 0); + if (ret) + set_security_selinux_fail = true; + } else { + /* If security.bpf.bar exists, remove it */ + ret = bpf_remove_dentry_xattr(dentry, xattr_bar); + if (!ret) + remove_security_bpf_bar_success = true; + + ret = bpf_remove_dentry_xattr(dentry, xattr_selinux); + if (ret) + remove_security_selinux_fail = true; + } + + return 0; +} + +bool locked_set_security_bpf_bar_success; +bool locked_remove_security_bpf_bar_success; +bool locked_set_security_selinux_fail; +bool locked_remove_security_selinux_fail; + +/* Test bpf_set_dentry_xattr_locked and bpf_remove_dentry_xattr_locked. + * It not necessary to differentiate the _locked version and the + * not-_locked version in the BPF program. The verifier will fix them up + * properly. + */ +SEC("lsm.s/inode_setxattr") +int BPF_PROG(test_inode_setxattr, struct mnt_idmap *idmap, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + struct bpf_dynptr value_ptr; + __u32 pid; + int ret; + + pid = bpf_get_current_pid_tgid() >> 32; + if (pid != monitored_pid) + return 0; + + /* Only do the following for security.bpf.foo */ + if (!name_match_foo(name)) + return 0; + + bpf_dynptr_from_mem(read_value, sizeof(read_value), 0, &value_ptr); + + /* read security.bpf.bar */ + ret = bpf_get_dentry_xattr(dentry, xattr_bar, &value_ptr); + + if (ret < 0) { + /* If security.bpf.bar doesn't exist, set it */ + bpf_dynptr_from_mem(value_bar, sizeof(value_bar), 0, &value_ptr); + + ret = bpf_set_dentry_xattr(dentry, xattr_bar, &value_ptr, 0); + if (!ret) + locked_set_security_bpf_bar_success = true; + ret = bpf_set_dentry_xattr(dentry, xattr_selinux, &value_ptr, 0); + if (ret) + locked_set_security_selinux_fail = true; + } else { + /* If security.bpf.bar exists, remove it */ + ret = bpf_remove_dentry_xattr(dentry, xattr_bar); + if (!ret) + locked_remove_security_bpf_bar_success = true; + + ret = bpf_remove_dentry_xattr(dentry, xattr_selinux); + if (ret) + locked_remove_security_selinux_fail = true; + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c index 1c8b678..f678ee6 100644 --- a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c +++ b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c @@ -245,4 +245,73 @@ int lock_global_subprog_call2(struct __sk_buff *ctx) return ret; } +int __noinline +global_subprog_int(int i) +{ + if (i) + bpf_printk("%p", &i); + return i; +} + +int __noinline +global_sleepable_helper_subprog(int i) +{ + if (i) + bpf_copy_from_user(&i, sizeof(i), NULL); + return i; +} + +int __noinline +global_sleepable_kfunc_subprog(int i) +{ + if (i) + bpf_copy_from_user_str(&i, sizeof(i), NULL, 0); + global_subprog_int(i); + return i; +} + +int __noinline +global_subprog_calling_sleepable_global(int i) +{ + if (!i) + global_sleepable_kfunc_subprog(i); + return i; +} + +SEC("?syscall") +int lock_global_sleepable_helper_subprog(struct __sk_buff *ctx) +{ + int ret = 0; + + bpf_spin_lock(&lockA); + if (ctx->mark == 42) + ret = global_sleepable_helper_subprog(ctx->mark); + bpf_spin_unlock(&lockA); + return ret; +} + +SEC("?syscall") +int lock_global_sleepable_kfunc_subprog(struct __sk_buff *ctx) +{ + int ret = 0; + + bpf_spin_lock(&lockA); + if (ctx->mark == 42) + ret = global_sleepable_kfunc_subprog(ctx->mark); + bpf_spin_unlock(&lockA); + return ret; +} + +SEC("?syscall") +int lock_global_sleepable_subprog_indirect(struct __sk_buff *ctx) +{ + int ret = 0; + + bpf_spin_lock(&lockA); + if (ctx->mark == 42) + ret = global_subprog_calling_sleepable_global(ctx->mark); + bpf_spin_unlock(&lockA); + return ret; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c index 7e75030..0b74b8b 100644 --- a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c +++ b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c @@ -49,7 +49,7 @@ out: } SEC("lsm.s/bpf") -int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size) +int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size, bool kernel) { struct cgroup *cgrp = NULL; struct task_struct *task; diff --git a/tools/testing/selftests/bpf/progs/test_usdt.c b/tools/testing/selftests/bpf/progs/test_usdt.c index 505aab9..096488f 100644 --- a/tools/testing/selftests/bpf/progs/test_usdt.c +++ b/tools/testing/selftests/bpf/progs/test_usdt.c @@ -11,6 +11,7 @@ int usdt0_called; u64 usdt0_cookie; int usdt0_arg_cnt; int usdt0_arg_ret; +int usdt0_arg_size; SEC("usdt") int usdt0(struct pt_regs *ctx) @@ -26,6 +27,7 @@ int usdt0(struct pt_regs *ctx) usdt0_arg_cnt = bpf_usdt_arg_cnt(ctx); /* should return -ENOENT for any arg_num */ usdt0_arg_ret = bpf_usdt_arg(ctx, bpf_get_prandom_u32(), &tmp); + usdt0_arg_size = bpf_usdt_arg_size(ctx, bpf_get_prandom_u32()); return 0; } @@ -34,6 +36,7 @@ u64 usdt3_cookie; int usdt3_arg_cnt; int usdt3_arg_rets[3]; u64 usdt3_args[3]; +int usdt3_arg_sizes[3]; SEC("usdt//proc/self/exe:test:usdt3") int usdt3(struct pt_regs *ctx) @@ -50,12 +53,15 @@ int usdt3(struct pt_regs *ctx) usdt3_arg_rets[0] = bpf_usdt_arg(ctx, 0, &tmp); usdt3_args[0] = (int)tmp; + usdt3_arg_sizes[0] = bpf_usdt_arg_size(ctx, 0); usdt3_arg_rets[1] = bpf_usdt_arg(ctx, 1, &tmp); usdt3_args[1] = (long)tmp; + usdt3_arg_sizes[1] = bpf_usdt_arg_size(ctx, 1); usdt3_arg_rets[2] = bpf_usdt_arg(ctx, 2, &tmp); usdt3_args[2] = (uintptr_t)tmp; + usdt3_arg_sizes[2] = bpf_usdt_arg_size(ctx, 2); return 0; } @@ -64,12 +70,15 @@ int usdt12_called; u64 usdt12_cookie; int usdt12_arg_cnt; u64 usdt12_args[12]; +int usdt12_arg_sizes[12]; SEC("usdt//proc/self/exe:test:usdt12") int BPF_USDT(usdt12, int a1, int a2, long a3, long a4, unsigned a5, long a6, __u64 a7, uintptr_t a8, int a9, short a10, short a11, signed char a12) { + int i; + if (my_pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -90,6 +99,11 @@ int BPF_USDT(usdt12, int a1, int a2, long a3, long a4, unsigned a5, usdt12_args[9] = a10; usdt12_args[10] = a11; usdt12_args[11] = a12; + + bpf_for(i, 0, 12) { + usdt12_arg_sizes[i] = bpf_usdt_arg_size(ctx, i); + } + return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c index 12034a7..e96d09e 100644 --- a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c +++ b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c @@ -37,7 +37,7 @@ struct { char _license[] SEC("license") = "GPL"; SEC("lsm.s/bpf") -int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size) +int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size, bool kernel) { struct bpf_dynptr data_ptr, sig_ptr; struct data *data_val; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c index a758830..a80cc5f 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c @@ -102,8 +102,8 @@ bool parse_eth_frame(struct ethhdr *eth, void *data_end, struct parse_pkt *pkt) #define TESTVLAN 4011 /* 0xFAB */ // #define TO_VLAN 4000 /* 0xFA0 (hint 0xOA0 = 160) */ -SEC("xdp_drop_vlan_4011") -int xdp_prognum0(struct xdp_md *ctx) +SEC("xdp") +int xdp_drop_vlan_4011(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; void *data = (void *)(long)ctx->data; @@ -144,8 +144,8 @@ Load prog with ip tool: /* Changing VLAN to zero, have same practical effect as removing the VLAN. */ #define TO_VLAN 0 -SEC("xdp_vlan_change") -int xdp_prognum1(struct xdp_md *ctx) +SEC("xdp") +int xdp_vlan_change(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; void *data = (void *)(long)ctx->data; @@ -178,8 +178,8 @@ int xdp_prognum1(struct xdp_md *ctx) #endif #define VLAN_HDR_SZ 4 /* bytes */ -SEC("xdp_vlan_remove_outer") -int xdp_prognum2(struct xdp_md *ctx) +SEC("xdp") +int xdp_vlan_remove_outer(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; void *data = (void *)(long)ctx->data; @@ -224,8 +224,8 @@ void shift_mac_4bytes_32bit(void *data) p[1] = p[0]; } -SEC("xdp_vlan_remove_outer2") -int xdp_prognum3(struct xdp_md *ctx) +SEC("xdp") +int xdp_vlan_remove_outer2(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; void *data = (void *)(long)ctx->data; @@ -254,8 +254,8 @@ int xdp_prognum3(struct xdp_md *ctx) * The TC-clsact eBPF programs (currently) need to be attach via TC commands */ -SEC("tc_vlan_push") -int _tc_progA(struct __sk_buff *ctx) +SEC("tc") +int tc_vlan_push(struct __sk_buff *ctx) { bpf_skb_vlan_push(ctx, bpf_htons(ETH_P_8021Q), TESTVLAN); diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c index 5094c28..a9be6ae 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c +++ b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c @@ -620,23 +620,61 @@ __naked void helper_call_does_not_prevent_bpf_fastcall(void) SEC("raw_tp") __arch_x86_64 +__log_level(4) __msg("stack depth 24") +/* may_goto counter at -24 */ +__xlated("0: *(u64 *)(r10 -24) =") +/* may_goto timestamp at -16 */ +__xlated("1: *(u64 *)(r10 -16) =") +__xlated("2: r1 = 1") +__xlated("...") +__xlated("4: r0 = &(void __percpu *)(r0)") +__xlated("...") +/* may_goto expansion starts */ +__xlated("6: r11 = *(u64 *)(r10 -24)") +__xlated("7: if r11 == 0x0 goto pc+6") +__xlated("8: r11 -= 1") +__xlated("9: if r11 != 0x0 goto pc+2") +__xlated("10: r11 = -24") +__xlated("11: call unknown") +__xlated("12: *(u64 *)(r10 -24) = r11") +/* may_goto expansion ends */ +__xlated("13: *(u64 *)(r10 -8) = r1") +__xlated("14: exit") +__success +__naked void may_goto_interaction_x86_64(void) +{ + asm volatile ( + "r1 = 1;" + "*(u64 *)(r10 - 16) = r1;" + "call %[bpf_get_smp_processor_id];" + "r1 = *(u64 *)(r10 - 16);" + ".8byte %[may_goto];" + /* just touch some stack at -8 */ + "*(u64 *)(r10 - 8) = r1;" + "exit;" + : + : __imm(bpf_get_smp_processor_id), + __imm_insn(may_goto, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, +1 /* offset */, 0)) + : __clobber_all); +} + +SEC("raw_tp") +__arch_arm64 __log_level(4) __msg("stack depth 16") /* may_goto counter at -16 */ __xlated("0: *(u64 *)(r10 -16) =") __xlated("1: r1 = 1") -__xlated("...") -__xlated("3: r0 = &(void __percpu *)(r0)") -__xlated("...") +__xlated("2: call bpf_get_smp_processor_id") /* may_goto expansion starts */ -__xlated("5: r11 = *(u64 *)(r10 -16)") -__xlated("6: if r11 == 0x0 goto pc+3") -__xlated("7: r11 -= 1") -__xlated("8: *(u64 *)(r10 -16) = r11") +__xlated("3: r11 = *(u64 *)(r10 -16)") +__xlated("4: if r11 == 0x0 goto pc+3") +__xlated("5: r11 -= 1") +__xlated("6: *(u64 *)(r10 -16) = r11") /* may_goto expansion ends */ -__xlated("9: *(u64 *)(r10 -8) = r1") -__xlated("10: exit") +__xlated("7: *(u64 *)(r10 -8) = r1") +__xlated("8: exit") __success -__naked void may_goto_interaction(void) +__naked void may_goto_interaction_arm64(void) { asm volatile ( "r1 = 1;" diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c index 05a329e..d5d8f24 100644 --- a/tools/testing/selftests/bpf/progs/verifier_gotol.c +++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c @@ -4,11 +4,7 @@ #include #include "bpf_misc.h" -#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ - (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \ - defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \ - defined(__TARGET_ARCH_loongarch)) && \ - __clang_major__ >= 18 +#ifdef CAN_USE_GOTOL SEC("socket") __description("gotol, small_imm") diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c index e54bb53..75dd922 100644 --- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c +++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c @@ -407,11 +407,7 @@ l0_%=: call %[bpf_jiffies64]; \ : __clobber_all); } -#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ - (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \ - defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \ - defined(__TARGET_ARCH_loongarch)) && \ - __clang_major__ >= 18 +#ifdef CAN_USE_GOTOL SEC("socket") __success __retval(0) __naked void gotol_and_may_goto(void) diff --git a/tools/testing/selftests/bpf/progs/verifier_load_acquire.c b/tools/testing/selftests/bpf/progs/verifier_load_acquire.c new file mode 100644 index 0000000..77698d5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_load_acquire.c @@ -0,0 +1,218 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Google LLC. */ + +#include +#include +#include "../../../include/linux/filter.h" +#include "bpf_misc.h" + +#ifdef CAN_USE_LOAD_ACQ_STORE_REL + +SEC("socket") +__description("load-acquire, 8-bit") +__success __success_unpriv __retval(0x12) +__naked void load_acquire_8(void) +{ + asm volatile ( + "w1 = 0x12;" + "*(u8 *)(r10 - 1) = w1;" + ".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r10 - 1)); + "exit;" + : + : __imm_insn(load_acquire_insn, + BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -1)) + : __clobber_all); +} + +SEC("socket") +__description("load-acquire, 16-bit") +__success __success_unpriv __retval(0x1234) +__naked void load_acquire_16(void) +{ + asm volatile ( + "w1 = 0x1234;" + "*(u16 *)(r10 - 2) = w1;" + ".8byte %[load_acquire_insn];" // w0 = load_acquire((u16 *)(r10 - 2)); + "exit;" + : + : __imm_insn(load_acquire_insn, + BPF_ATOMIC_OP(BPF_H, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -2)) + : __clobber_all); +} + +SEC("socket") +__description("load-acquire, 32-bit") +__success __success_unpriv __retval(0x12345678) +__naked void load_acquire_32(void) +{ + asm volatile ( + "w1 = 0x12345678;" + "*(u32 *)(r10 - 4) = w1;" + ".8byte %[load_acquire_insn];" // w0 = load_acquire((u32 *)(r10 - 4)); + "exit;" + : + : __imm_insn(load_acquire_insn, + BPF_ATOMIC_OP(BPF_W, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -4)) + : __clobber_all); +} + +SEC("socket") +__description("load-acquire, 64-bit") +__success __success_unpriv __retval(0x1234567890abcdef) +__naked void load_acquire_64(void) +{ + asm volatile ( + "r1 = 0x1234567890abcdef ll;" + "*(u64 *)(r10 - 8) = r1;" + ".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r10 - 8)); + "exit;" + : + : __imm_insn(load_acquire_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -8)) + : __clobber_all); +} + +SEC("socket") +__description("load-acquire with uninitialized src_reg") +__failure __failure_unpriv __msg("R2 !read_ok") +__naked void load_acquire_with_uninitialized_src_reg(void) +{ + asm volatile ( + ".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r2 + 0)); + "exit;" + : + : __imm_insn(load_acquire_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_2, 0)) + : __clobber_all); +} + +SEC("socket") +__description("load-acquire with non-pointer src_reg") +__failure __failure_unpriv __msg("R1 invalid mem access 'scalar'") +__naked void load_acquire_with_non_pointer_src_reg(void) +{ + asm volatile ( + "r1 = 0;" + ".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r1 + 0)); + "exit;" + : + : __imm_insn(load_acquire_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_1, 0)) + : __clobber_all); +} + +SEC("socket") +__description("misaligned load-acquire") +__failure __failure_unpriv __msg("misaligned stack access off") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void load_acquire_misaligned(void) +{ + asm volatile ( + "r1 = 0;" + "*(u64 *)(r10 - 8) = r1;" + ".8byte %[load_acquire_insn];" // w0 = load_acquire((u32 *)(r10 - 5)); + "exit;" + : + : __imm_insn(load_acquire_insn, + BPF_ATOMIC_OP(BPF_W, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -5)) + : __clobber_all); +} + +SEC("socket") +__description("load-acquire from ctx pointer") +__failure __failure_unpriv __msg("BPF_ATOMIC loads from R1 ctx is not allowed") +__naked void load_acquire_from_ctx_pointer(void) +{ + asm volatile ( + ".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r1 + 0)); + "exit;" + : + : __imm_insn(load_acquire_insn, + BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_1, 0)) + : __clobber_all); +} + +SEC("xdp") +__description("load-acquire from pkt pointer") +__failure __msg("BPF_ATOMIC loads from R2 pkt is not allowed") +__naked void load_acquire_from_pkt_pointer(void) +{ + asm volatile ( + "r2 = *(u32 *)(r1 + %[xdp_md_data]);" + "r3 = *(u32 *)(r1 + %[xdp_md_data_end]);" + "r1 = r2;" + "r1 += 8;" + "if r1 >= r3 goto l0_%=;" + ".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r2 + 0)); +"l0_%=: r0 = 0;" + "exit;" + : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)), + __imm_insn(load_acquire_insn, + BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_2, 0)) + : __clobber_all); +} + +SEC("flow_dissector") +__description("load-acquire from flow_keys pointer") +__failure __msg("BPF_ATOMIC loads from R2 flow_keys is not allowed") +__naked void load_acquire_from_flow_keys_pointer(void) +{ + asm volatile ( + "r2 = *(u64 *)(r1 + %[__sk_buff_flow_keys]);" + ".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r2 + 0)); + "exit;" + : + : __imm_const(__sk_buff_flow_keys, + offsetof(struct __sk_buff, flow_keys)), + __imm_insn(load_acquire_insn, + BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_2, 0)) + : __clobber_all); +} + +SEC("sk_reuseport") +__description("load-acquire from sock pointer") +__failure __msg("BPF_ATOMIC loads from R2 sock is not allowed") +__naked void load_acquire_from_sock_pointer(void) +{ + asm volatile ( + "r2 = *(u64 *)(r1 + %[sk_reuseport_md_sk]);" + // w0 = load_acquire((u8 *)(r2 + offsetof(struct bpf_sock, family))); + ".8byte %[load_acquire_insn];" + "exit;" + : + : __imm_const(sk_reuseport_md_sk, offsetof(struct sk_reuseport_md, sk)), + __imm_insn(load_acquire_insn, + BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_2, + offsetof(struct bpf_sock, family))) + : __clobber_all); +} + +SEC("socket") +__description("load-acquire with invalid register R15") +__failure __failure_unpriv __msg("R15 is invalid") +__naked void load_acquire_with_invalid_reg(void) +{ + asm volatile ( + ".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r15 + 0)); + "exit;" + : + : __imm_insn(load_acquire_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, 15 /* invalid reg */, 0)) + : __clobber_all); +} + +#else /* CAN_USE_LOAD_ACQ_STORE_REL */ + +SEC("socket") +__description("Clang version < 18, ENABLE_ATOMICS_TESTS not defined, and/or JIT doesn't support load-acquire, use a dummy test") +__success +int dummy_test(void) +{ + return 0; +} + +#endif /* CAN_USE_LOAD_ACQ_STORE_REL */ + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c b/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c index e81097c..3966d82 100644 --- a/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c +++ b/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c @@ -69,8 +69,38 @@ __naked void may_goto_batch_1(void) } SEC("raw_tp") -__description("may_goto batch with offsets 2/0") +__description("may_goto batch with offsets 2/0 - x86_64") __arch_x86_64 +__xlated("0: *(u64 *)(r10 -16) = 65535") +__xlated("1: *(u64 *)(r10 -8) = 0") +__xlated("2: r11 = *(u64 *)(r10 -16)") +__xlated("3: if r11 == 0x0 goto pc+6") +__xlated("4: r11 -= 1") +__xlated("5: if r11 != 0x0 goto pc+2") +__xlated("6: r11 = -16") +__xlated("7: call unknown") +__xlated("8: *(u64 *)(r10 -16) = r11") +__xlated("9: r0 = 1") +__xlated("10: r0 = 2") +__xlated("11: exit") +__success +__naked void may_goto_batch_2_x86_64(void) +{ + asm volatile ( + ".8byte %[may_goto1];" + ".8byte %[may_goto3];" + "r0 = 1;" + "r0 = 2;" + "exit;" + : + : __imm_insn(may_goto1, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 2 /* offset */, 0)), + __imm_insn(may_goto3, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0)) + : __clobber_all); +} + +SEC("raw_tp") +__description("may_goto batch with offsets 2/0 - arm64") +__arch_arm64 __xlated("0: *(u64 *)(r10 -8) = 8388608") __xlated("1: r11 = *(u64 *)(r10 -8)") __xlated("2: if r11 == 0x0 goto pc+3") @@ -80,7 +110,7 @@ __xlated("5: r0 = 1") __xlated("6: r0 = 2") __xlated("7: exit") __success -__naked void may_goto_batch_2(void) +__naked void may_goto_batch_2_arm64(void) { asm volatile ( ".8byte %[may_goto1];" diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c index 6b564d4..6662d4b 100644 --- a/tools/testing/selftests/bpf/progs/verifier_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_precision.c @@ -2,6 +2,7 @@ /* Copyright (C) 2023 SUSE LLC */ #include #include +#include "../../../include/linux/filter.h" #include "bpf_misc.h" SEC("?raw_tp") @@ -90,6 +91,54 @@ __naked int bpf_end_bswap(void) ::: __clobber_all); } +#if defined(ENABLE_ATOMICS_TESTS) && \ + (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) + +SEC("?raw_tp") +__success __log_level(2) +__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r3 = r10") +__msg("mark_precise: frame0: regs=r2 stack= before 2: (db) r2 = load_acquire((u64 *)(r10 -8))") +__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1") +__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8") +__naked int bpf_load_acquire(void) +{ + asm volatile ( + "r1 = 8;" + "*(u64 *)(r10 - 8) = r1;" + ".8byte %[load_acquire_insn];" /* r2 = load_acquire((u64 *)(r10 - 8)); */ + "r3 = r10;" + "r3 += r2;" /* mark_precise */ + "r0 = 0;" + "exit;" + : + : __imm_insn(load_acquire_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -8)) + : __clobber_all); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("mark_precise: frame0: regs=r1 stack= before 3: (bf) r2 = r10") +__msg("mark_precise: frame0: regs=r1 stack= before 2: (79) r1 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: regs= stack=-8 before 1: (db) store_release((u64 *)(r10 -8), r1)") +__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8") +__naked int bpf_store_release(void) +{ + asm volatile ( + "r1 = 8;" + ".8byte %[store_release_insn];" /* store_release((u64 *)(r10 - 8), r1); */ + "r1 = *(u64 *)(r10 - 8);" + "r2 = r10;" + "r2 += r1;" /* mark_precise */ + "r0 = 0;" + "exit;" + : + : __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -8)) + : __clobber_all); +} + +#endif /* load-acquire, store-release */ #endif /* v4 instruction */ SEC("?raw_tp") diff --git a/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c b/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c index 417c61c..24aabc6 100644 --- a/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c +++ b/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c @@ -481,4 +481,56 @@ l1_%=: r0 = 42; \ : __clobber_all); } +SEC("socket") +__description("PTR_TO_STACK stack size > 512") +__failure __msg("invalid write to stack R1 off=-520 size=8") +__naked void stack_check_size_gt_512(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -520; \ + r0 = 42; \ + *(u64*)(r1 + 0) = r0; \ + exit; \ +" ::: __clobber_all); +} + +#ifdef __BPF_FEATURE_MAY_GOTO +SEC("socket") +__description("PTR_TO_STACK stack size 512 with may_goto with jit") +__load_if_JITed() +__success __retval(42) +__naked void stack_check_size_512_with_may_goto_jit(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -512; \ + r0 = 42; \ + *(u32*)(r1 + 0) = r0; \ + may_goto l0_%=; \ + r2 = 100; \ + l0_%=: \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("PTR_TO_STACK stack size 512 with may_goto without jit") +__load_if_no_JITed() +__failure __msg("stack size 520(extra 8) is too large") +__naked void stack_check_size_512_with_may_goto(void) +{ + asm volatile (" \ + r1 = r10; \ + r1 += -512; \ + r0 = 42; \ + *(u32*)(r1 + 0) = r0; \ + may_goto l0_%=; \ + r2 = 100; \ + l0_%=: \ + exit; \ +" ::: __clobber_all); +} +#endif + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_store_release.c b/tools/testing/selftests/bpf/progs/verifier_store_release.c new file mode 100644 index 0000000..c0442d5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_store_release.c @@ -0,0 +1,286 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Google LLC. */ + +#include +#include +#include "../../../include/linux/filter.h" +#include "bpf_misc.h" + +#if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) && \ + (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) + +SEC("socket") +__description("store-release, 8-bit") +__success __success_unpriv __retval(0x12) +__naked void store_release_8(void) +{ + asm volatile ( + "w1 = 0x12;" + ".8byte %[store_release_insn];" // store_release((u8 *)(r10 - 1), w1); + "w0 = *(u8 *)(r10 - 1);" + "exit;" + : + : __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -1)) + : __clobber_all); +} + +SEC("socket") +__description("store-release, 16-bit") +__success __success_unpriv __retval(0x1234) +__naked void store_release_16(void) +{ + asm volatile ( + "w1 = 0x1234;" + ".8byte %[store_release_insn];" // store_release((u16 *)(r10 - 2), w1); + "w0 = *(u16 *)(r10 - 2);" + "exit;" + : + : __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_H, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -2)) + : __clobber_all); +} + +SEC("socket") +__description("store-release, 32-bit") +__success __success_unpriv __retval(0x12345678) +__naked void store_release_32(void) +{ + asm volatile ( + "w1 = 0x12345678;" + ".8byte %[store_release_insn];" // store_release((u32 *)(r10 - 4), w1); + "w0 = *(u32 *)(r10 - 4);" + "exit;" + : + : __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_W, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -4)) + : __clobber_all); +} + +SEC("socket") +__description("store-release, 64-bit") +__success __success_unpriv __retval(0x1234567890abcdef) +__naked void store_release_64(void) +{ + asm volatile ( + "r1 = 0x1234567890abcdef ll;" + ".8byte %[store_release_insn];" // store_release((u64 *)(r10 - 8), r1); + "r0 = *(u64 *)(r10 - 8);" + "exit;" + : + : __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -8)) + : __clobber_all); +} + +SEC("socket") +__description("store-release with uninitialized src_reg") +__failure __failure_unpriv __msg("R2 !read_ok") +__naked void store_release_with_uninitialized_src_reg(void) +{ + asm volatile ( + ".8byte %[store_release_insn];" // store_release((u64 *)(r10 - 8), r2); + "exit;" + : + : __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_10, BPF_REG_2, -8)) + : __clobber_all); +} + +SEC("socket") +__description("store-release with uninitialized dst_reg") +__failure __failure_unpriv __msg("R2 !read_ok") +__naked void store_release_with_uninitialized_dst_reg(void) +{ + asm volatile ( + "r1 = 0;" + ".8byte %[store_release_insn];" // store_release((u64 *)(r2 - 8), r1); + "exit;" + : + : __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_2, BPF_REG_1, -8)) + : __clobber_all); +} + +SEC("socket") +__description("store-release with non-pointer dst_reg") +__failure __failure_unpriv __msg("R1 invalid mem access 'scalar'") +__naked void store_release_with_non_pointer_dst_reg(void) +{ + asm volatile ( + "r1 = 0;" + ".8byte %[store_release_insn];" // store_release((u64 *)(r1 + 0), r1); + "exit;" + : + : __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_1, BPF_REG_1, 0)) + : __clobber_all); +} + +SEC("socket") +__description("misaligned store-release") +__failure __failure_unpriv __msg("misaligned stack access off") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void store_release_misaligned(void) +{ + asm volatile ( + "w0 = 0;" + ".8byte %[store_release_insn];" // store_release((u32 *)(r10 - 5), w0); + "exit;" + : + : __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_W, BPF_STORE_REL, BPF_REG_10, BPF_REG_0, -5)) + : __clobber_all); +} + +SEC("socket") +__description("store-release to ctx pointer") +__failure __failure_unpriv __msg("BPF_ATOMIC stores into R1 ctx is not allowed") +__naked void store_release_to_ctx_pointer(void) +{ + asm volatile ( + "w0 = 0;" + // store_release((u8 *)(r1 + offsetof(struct __sk_buff, cb[0])), w0); + ".8byte %[store_release_insn];" + "exit;" + : + : __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0]))) + : __clobber_all); +} + +SEC("xdp") +__description("store-release to pkt pointer") +__failure __msg("BPF_ATOMIC stores into R2 pkt is not allowed") +__naked void store_release_to_pkt_pointer(void) +{ + asm volatile ( + "w0 = 0;" + "r2 = *(u32 *)(r1 + %[xdp_md_data]);" + "r3 = *(u32 *)(r1 + %[xdp_md_data_end]);" + "r1 = r2;" + "r1 += 8;" + "if r1 >= r3 goto l0_%=;" + ".8byte %[store_release_insn];" // store_release((u8 *)(r2 + 0), w0); +"l0_%=: r0 = 0;" + "exit;" + : + : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)), + __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)), + __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_2, BPF_REG_0, 0)) + : __clobber_all); +} + +SEC("flow_dissector") +__description("store-release to flow_keys pointer") +__failure __msg("BPF_ATOMIC stores into R2 flow_keys is not allowed") +__naked void store_release_to_flow_keys_pointer(void) +{ + asm volatile ( + "w0 = 0;" + "r2 = *(u64 *)(r1 + %[__sk_buff_flow_keys]);" + ".8byte %[store_release_insn];" // store_release((u8 *)(r2 + 0), w0); + "exit;" + : + : __imm_const(__sk_buff_flow_keys, + offsetof(struct __sk_buff, flow_keys)), + __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_2, BPF_REG_0, 0)) + : __clobber_all); +} + +SEC("sk_reuseport") +__description("store-release to sock pointer") +__failure __msg("R2 cannot write into sock") +__naked void store_release_to_sock_pointer(void) +{ + asm volatile ( + "w0 = 0;" + "r2 = *(u64 *)(r1 + %[sk_reuseport_md_sk]);" + ".8byte %[store_release_insn];" // store_release((u8 *)(r2 + 0), w0); + "exit;" + : + : __imm_const(sk_reuseport_md_sk, offsetof(struct sk_reuseport_md, sk)), + __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_2, BPF_REG_0, 0)) + : __clobber_all); +} + +SEC("socket") +__description("store-release, leak pointer to stack") +__success __success_unpriv __retval(0) +__naked void store_release_leak_pointer_to_stack(void) +{ + asm volatile ( + ".8byte %[store_release_insn];" // store_release((u64 *)(r10 - 8), r1); + "r0 = 0;" + "exit;" + : + : __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -8)) + : __clobber_all); +} + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, long long); + __type(value, long long); +} map_hash_8b SEC(".maps"); + +SEC("socket") +__description("store-release, leak pointer to map") +__success __retval(0) +__failure_unpriv __msg_unpriv("R6 leaks addr into map") +__naked void store_release_leak_pointer_to_map(void) +{ + asm volatile ( + "r6 = r1;" + "r1 = %[map_hash_8b] ll;" + "r2 = 0;" + "*(u64 *)(r10 - 8) = r2;" + "r2 = r10;" + "r2 += -8;" + "call %[bpf_map_lookup_elem];" + "if r0 == 0 goto l0_%=;" + ".8byte %[store_release_insn];" // store_release((u64 *)(r0 + 0), r6); +"l0_%=:" + "r0 = 0;" + "exit;" + : + : __imm_addr(map_hash_8b), + __imm(bpf_map_lookup_elem), + __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_0, BPF_REG_6, 0)) + : __clobber_all); +} + +SEC("socket") +__description("store-release with invalid register R15") +__failure __failure_unpriv __msg("R15 is invalid") +__naked void store_release_with_invalid_reg(void) +{ + asm volatile ( + ".8byte %[store_release_insn];" // store_release((u64 *)(r15 + 0), r1); + "exit;" + : + : __imm_insn(store_release_insn, + BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, 15 /* invalid reg */, BPF_REG_1, 0)) + : __clobber_all); +} + +#else + +SEC("socket") +__description("Clang version < 18, ENABLE_ATOMICS_TESTS not defined, and/or JIT doesn't support store-release, use a dummy test") +__success +int dummy_test(void) +{ + return 0; +} + +#endif + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c index 682dda8..50c8958 100644 --- a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c +++ b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c @@ -1,7 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 +#include + #include #include +#include struct { __uint(type, BPF_MAP_TYPE_DEVMAP); @@ -28,4 +31,89 @@ int xdp_redirect_map_2(struct xdp_md *xdp) return bpf_redirect_map(&tx_port, 2, 0); } +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 3); + __type(key, __u32); + __type(value, __u64); +} rxcnt SEC(".maps"); + +static int xdp_count(struct xdp_md *xdp, __u32 key) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eth = data; + __u64 *count; + + if (data + sizeof(*eth) > data_end) + return XDP_DROP; + + if (bpf_htons(eth->h_proto) == ETH_P_IP) { + /* We only count IPv4 packets */ + count = bpf_map_lookup_elem(&rxcnt, &key); + if (count) + *count += 1; + } + + return XDP_PASS; +} + +SEC("xdp") +int xdp_count_0(struct xdp_md *xdp) +{ + return xdp_count(xdp, 0); +} + +SEC("xdp") +int xdp_count_1(struct xdp_md *xdp) +{ + return xdp_count(xdp, 1); +} + +SEC("xdp") +int xdp_count_2(struct xdp_md *xdp) +{ + return xdp_count(xdp, 2); +} + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, __be64); +} rx_mac SEC(".maps"); + +static int store_mac(struct xdp_md *xdp, __u32 id) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eth = data; + __u32 key = id; + __be64 mac = 0; + + if (data + sizeof(*eth) > data_end) + return XDP_DROP; + + /* Only store IPv4 MAC to avoid being polluted by IPv6 packets */ + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + __builtin_memcpy(&mac, eth->h_source, ETH_ALEN); + bpf_map_update_elem(&rx_mac, &key, &mac, 0); + bpf_printk("%s - %x", __func__, mac); + } + + return XDP_PASS; +} + +SEC("xdp") +int store_mac_1(struct xdp_md *xdp) +{ + return store_mac(xdp, 0); +} + +SEC("xdp") +int store_mac_2(struct xdp_md *xdp) +{ + return store_mac(xdp, 1); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c index 97b26a3..bc2945e 100644 --- a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c @@ -34,6 +34,14 @@ struct { __uint(max_entries, 128); } mac_map SEC(".maps"); +/* map to store redirect flags for each protocol*/ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u16); + __type(value, __u64); + __uint(max_entries, 16); +} redirect_flags SEC(".maps"); + SEC("xdp") int xdp_redirect_map_multi_prog(struct xdp_md *ctx) { @@ -41,25 +49,34 @@ int xdp_redirect_map_multi_prog(struct xdp_md *ctx) void *data = (void *)(long)ctx->data; int if_index = ctx->ingress_ifindex; struct ethhdr *eth = data; + __u64 *flags_from_map; __u16 h_proto; __u64 nh_off; + __u64 flags; nh_off = sizeof(*eth); if (data + nh_off > data_end) return XDP_DROP; - h_proto = eth->h_proto; - - /* Using IPv4 for (BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) testing */ - if (h_proto == bpf_htons(ETH_P_IP)) - return bpf_redirect_map(&map_all, 0, - BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS); - /* Using IPv6 for none flag testing */ - else if (h_proto == bpf_htons(ETH_P_IPV6)) - return bpf_redirect_map(&map_all, if_index, 0); - /* All others for BPF_F_BROADCAST testing */ - else - return bpf_redirect_map(&map_all, 0, BPF_F_BROADCAST); + h_proto = bpf_htons(eth->h_proto); + + flags_from_map = bpf_map_lookup_elem(&redirect_flags, &h_proto); + + /* Default flags for IPv4 : (BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) */ + if (h_proto == ETH_P_IP) { + flags = flags_from_map ? *flags_from_map : BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS; + return bpf_redirect_map(&map_all, 0, flags); + } + /* Default flags for IPv6 : 0 */ + if (h_proto == ETH_P_IPV6) { + flags = flags_from_map ? *flags_from_map : 0; + return bpf_redirect_map(&map_all, if_index, flags); + } + /* Default flags for others BPF_F_BROADCAST : 0 */ + else { + flags = flags_from_map ? *flags_from_map : BPF_F_BROADCAST; + return bpf_redirect_map(&map_all, 0, flags); + } } /* The following 2 progs are for 2nd devmap prog testing */ diff --git a/tools/testing/selftests/bpf/test_btf.h b/tools/testing/selftests/bpf/test_btf.h index fb4f471..e65889a 100644 --- a/tools/testing/selftests/bpf/test_btf.h +++ b/tools/testing/selftests/bpf/test_btf.h @@ -72,9 +72,15 @@ #define BTF_TYPE_FLOAT_ENC(name, sz) \ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz) +#define BTF_DECL_ATTR_ENC(value, type, component_idx) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 1, 0), type), (component_idx) + #define BTF_DECL_TAG_ENC(value, type, component_idx) \ BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx) +#define BTF_TYPE_ATTR_ENC(value, type) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TYPE_TAG, 1, 0), type) + #define BTF_TYPE_TAG_ENC(value, type) \ BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TYPE_TAG, 0, 0), type) diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c index cc9dde5..3220f1d 100644 --- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c @@ -1130,6 +1130,7 @@ static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = { }; static const struct bpf_verifier_ops bpf_testmod_verifier_ops = { + .get_func_proto = bpf_base_func_proto, .is_valid_access = bpf_testmod_ops_is_valid_access, }; @@ -1176,10 +1177,25 @@ static int bpf_testmod_ops__test_maybe_null(int dummy, return 0; } +static int bpf_testmod_ops__test_refcounted(int dummy, + struct task_struct *task__ref) +{ + return 0; +} + +static struct task_struct * +bpf_testmod_ops__test_return_ref_kptr(int dummy, struct task_struct *task__ref, + struct cgroup *cgrp) +{ + return NULL; +} + static struct bpf_testmod_ops __bpf_testmod_ops = { .test_1 = bpf_testmod_test_1, .test_2 = bpf_testmod_test_2, .test_maybe_null = bpf_testmod_ops__test_maybe_null, + .test_refcounted = bpf_testmod_ops__test_refcounted, + .test_return_ref_kptr = bpf_testmod_ops__test_return_ref_kptr, }; struct bpf_struct_ops bpf_bpf_testmod_ops = { @@ -1293,6 +1309,85 @@ static int bpf_test_mod_st_ops__test_pro_epilogue(struct st_ops_args *args) return 0; } +static int bpf_cgroup_from_id_id; +static int bpf_cgroup_release_id; + +static int st_ops_gen_prologue_with_kfunc(struct bpf_insn *insn_buf, bool direct_write, + const struct bpf_prog *prog) +{ + struct bpf_insn *insn = insn_buf; + + /* r8 = r1; // r8 will be "u64 *ctx". + * r1 = 0; + * r0 = bpf_cgroup_from_id(r1); + * if r0 != 0 goto pc+5; + * r6 = r8[0]; // r6 will be "struct st_ops *args". + * r7 = r6->a; + * r7 += 1000; + * r6->a = r7; + * goto pc+2; + * r1 = r0; + * bpf_cgroup_release(r1); + * r1 = r8; + */ + *insn++ = BPF_MOV64_REG(BPF_REG_8, BPF_REG_1); + *insn++ = BPF_MOV64_IMM(BPF_REG_1, 0); + *insn++ = BPF_CALL_KFUNC(0, bpf_cgroup_from_id_id); + *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 5); + *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_8, 0); + *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_6, offsetof(struct st_ops_args, a)); + *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 1000); + *insn++ = BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_7, offsetof(struct st_ops_args, a)); + *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 2); + *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_0); + *insn++ = BPF_CALL_KFUNC(0, bpf_cgroup_release_id), + *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_8); + *insn++ = prog->insnsi[0]; + + return insn - insn_buf; +} + +static int st_ops_gen_epilogue_with_kfunc(struct bpf_insn *insn_buf, const struct bpf_prog *prog, + s16 ctx_stack_off) +{ + struct bpf_insn *insn = insn_buf; + + /* r1 = 0; + * r6 = 0; + * r0 = bpf_cgroup_from_id(r1); + * if r0 != 0 goto pc+6; + * r1 = stack[ctx_stack_off]; // r1 will be "u64 *ctx" + * r1 = r1[0]; // r1 will be "struct st_ops *args" + * r6 = r1->a; + * r6 += 10000; + * r1->a = r6; + * goto pc+2 + * r1 = r0; + * bpf_cgroup_release(r1); + * r0 = r6; + * r0 *= 2; + * BPF_EXIT; + */ + *insn++ = BPF_MOV64_IMM(BPF_REG_1, 0); + *insn++ = BPF_MOV64_IMM(BPF_REG_6, 0); + *insn++ = BPF_CALL_KFUNC(0, bpf_cgroup_from_id_id); + *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 6); + *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_FP, ctx_stack_off); + *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0); + *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, offsetof(struct st_ops_args, a)); + *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 10000); + *insn++ = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, offsetof(struct st_ops_args, a)); + *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 2); + *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_0); + *insn++ = BPF_CALL_KFUNC(0, bpf_cgroup_release_id), + *insn++ = BPF_MOV64_REG(BPF_REG_0, BPF_REG_6); + *insn++ = BPF_ALU64_IMM(BPF_MUL, BPF_REG_0, 2); + *insn++ = BPF_EXIT_INSN(); + + return insn - insn_buf; +} + +#define KFUNC_PRO_EPI_PREFIX "test_kfunc_" static int st_ops_gen_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { @@ -1302,6 +1397,9 @@ static int st_ops_gen_prologue(struct bpf_insn *insn_buf, bool direct_write, strcmp(prog->aux->attach_func_name, "test_pro_epilogue")) return 0; + if (!strncmp(prog->aux->name, KFUNC_PRO_EPI_PREFIX, strlen(KFUNC_PRO_EPI_PREFIX))) + return st_ops_gen_prologue_with_kfunc(insn_buf, direct_write, prog); + /* r6 = r1[0]; // r6 will be "struct st_ops *args". r1 is "u64 *ctx". * r7 = r6->a; * r7 += 1000; @@ -1325,6 +1423,9 @@ static int st_ops_gen_epilogue(struct bpf_insn *insn_buf, const struct bpf_prog strcmp(prog->aux->attach_func_name, "test_pro_epilogue")) return 0; + if (!strncmp(prog->aux->name, KFUNC_PRO_EPI_PREFIX, strlen(KFUNC_PRO_EPI_PREFIX))) + return st_ops_gen_epilogue_with_kfunc(insn_buf, prog, ctx_stack_off); + /* r1 = stack[ctx_stack_off]; // r1 will be "u64 *ctx" * r1 = r1[0]; // r1 will be "struct st_ops *args" * r6 = r1->a; @@ -1395,6 +1496,13 @@ static void st_ops_unreg(void *kdata, struct bpf_link *link) static int st_ops_init(struct btf *btf) { + struct btf *kfunc_btf; + + bpf_cgroup_from_id_id = bpf_find_btf_id("bpf_cgroup_from_id", BTF_KIND_FUNC, &kfunc_btf); + bpf_cgroup_release_id = bpf_find_btf_id("bpf_cgroup_release", BTF_KIND_FUNC, &kfunc_btf); + if (bpf_cgroup_from_id_id < 0 || bpf_cgroup_release_id < 0) + return -EINVAL; + return 0; } diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h index 356803d..c9fab51 100644 --- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h @@ -6,6 +6,7 @@ #include struct task_struct; +struct cgroup; struct bpf_testmod_test_read_ctx { char *buf; @@ -36,6 +37,11 @@ struct bpf_testmod_ops { /* Used to test nullable arguments. */ int (*test_maybe_null)(int dummy, struct task_struct *task); int (*unsupported_ops)(void); + /* Used to test ref_acquired arguments. */ + int (*test_refcounted)(int dummy, struct task_struct *task); + /* Used to test returning referenced kptr. */ + struct task_struct *(*test_return_ref_kptr)(int dummy, struct task_struct *task, + struct cgroup *cgrp); /* The following fields are used to test shadow copies. */ char onebyte; diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c index 53b0664..49f2fc6 100644 --- a/tools/testing/selftests/bpf/test_loader.c +++ b/tools/testing/selftests/bpf/test_loader.c @@ -37,6 +37,7 @@ #define TEST_TAG_JITED_PFX "comment:test_jited=" #define TEST_TAG_JITED_PFX_UNPRIV "comment:test_jited_unpriv=" #define TEST_TAG_CAPS_UNPRIV "comment:test_caps_unpriv=" +#define TEST_TAG_LOAD_MODE_PFX "comment:load_mode=" /* Warning: duplicated in bpf_misc.h */ #define POINTER_VALUE 0xcafe4all @@ -55,6 +56,11 @@ enum mode { UNPRIV = 2 }; +enum load_mode { + JITED = 1 << 0, + NO_JITED = 1 << 1, +}; + struct expect_msg { const char *substr; /* substring match */ regex_t regex; @@ -87,6 +93,7 @@ struct test_spec { int prog_flags; int mode_mask; int arch_mask; + int load_mask; bool auxiliary; bool valid; }; @@ -406,6 +413,7 @@ static int parse_test_spec(struct test_loader *tester, bool collect_jit = false; int func_id, i, err = 0; u32 arch_mask = 0; + u32 load_mask = 0; struct btf *btf; enum arch arch; @@ -580,10 +588,22 @@ static int parse_test_spec(struct test_loader *tester, if (err) goto cleanup; spec->mode_mask |= UNPRIV; + } else if (str_has_pfx(s, TEST_TAG_LOAD_MODE_PFX)) { + val = s + sizeof(TEST_TAG_LOAD_MODE_PFX) - 1; + if (strcmp(val, "jited") == 0) { + load_mask = JITED; + } else if (strcmp(val, "no_jited") == 0) { + load_mask = NO_JITED; + } else { + PRINT_FAIL("bad load spec: '%s'", val); + err = -EINVAL; + goto cleanup; + } } } spec->arch_mask = arch_mask ?: -1; + spec->load_mask = load_mask ?: (JITED | NO_JITED); if (spec->mode_mask == 0) spec->mode_mask = PRIV; @@ -773,7 +793,7 @@ static int drop_capabilities(struct cap_state *caps) err = cap_disable_effective(caps_to_drop, &caps->old_caps); if (err) { - PRINT_FAIL("failed to drop capabilities: %i, %s\n", err, strerror(err)); + PRINT_FAIL("failed to drop capabilities: %i, %s\n", err, strerror(-err)); return err; } @@ -790,7 +810,7 @@ static int restore_capabilities(struct cap_state *caps) err = cap_enable_effective(caps->old_caps, NULL); if (err) - PRINT_FAIL("failed to restore capabilities: %i, %s\n", err, strerror(err)); + PRINT_FAIL("failed to restore capabilities: %i, %s\n", err, strerror(-err)); caps->initialized = false; return err; } @@ -928,6 +948,7 @@ void run_subtest(struct test_loader *tester, bool unpriv) { struct test_subspec *subspec = unpriv ? &spec->unpriv : &spec->priv; + int current_runtime = is_jit_enabled() ? JITED : NO_JITED; struct bpf_program *tprog = NULL, *tprog_iter; struct bpf_link *link, *links[32] = {}; struct test_spec *spec_iter; @@ -946,6 +967,11 @@ void run_subtest(struct test_loader *tester, return; } + if ((current_runtime & spec->load_mask) == 0) { + test__skip(); + return; + } + if (unpriv) { if (!can_execute_unpriv(tester, spec)) { test__skip(); @@ -959,7 +985,7 @@ void run_subtest(struct test_loader *tester, if (subspec->caps) { err = cap_enable_effective(subspec->caps, NULL); if (err) { - PRINT_FAIL("failed to set capabilities: %i, %s\n", err, strerror(err)); + PRINT_FAIL("failed to set capabilities: %i, %s\n", err, strerror(-err)); goto subtest_cleanup; } } diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh deleted file mode 100755 index 1e565f4..0000000 --- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh +++ /dev/null @@ -1,476 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# Setup/topology: -# -# NS1 NS2 NS3 -# veth1 <---> veth2 veth3 <---> veth4 (the top route) -# veth5 <---> veth6 veth7 <---> veth8 (the bottom route) -# -# each vethN gets IPv[4|6]_N address -# -# IPv*_SRC = IPv*_1 -# IPv*_DST = IPv*_4 -# -# all tests test pings from IPv*_SRC to IPv*_DST -# -# by default, routes are configured to allow packets to go -# IP*_1 <=> IP*_2 <=> IP*_3 <=> IP*_4 (the top route) -# -# a GRE device is installed in NS3 with IPv*_GRE, and -# NS1/NS2 are configured to route packets to IPv*_GRE via IP*_8 -# (the bottom route) -# -# Tests: -# -# 1. routes NS2->IPv*_DST are brought down, so the only way a ping -# from IP*_SRC to IP*_DST can work is via IPv*_GRE -# -# 2a. in an egress test, a bpf LWT_XMIT program is installed on veth1 -# that encaps the packets with an IP/GRE header to route to IPv*_GRE -# -# ping: SRC->[encap at veth1:egress]->GRE:decap->DST -# ping replies go DST->SRC directly -# -# 2b. in an ingress test, a bpf LWT_IN program is installed on veth2 -# that encaps the packets with an IP/GRE header to route to IPv*_GRE -# -# ping: SRC->[encap at veth2:ingress]->GRE:decap->DST -# ping replies go DST->SRC directly - -BPF_FILE="test_lwt_ip_encap.bpf.o" -if [[ $EUID -ne 0 ]]; then - echo "This script must be run as root" - echo "FAIL" - exit 1 -fi - -readonly NS1="ns1-$(mktemp -u XXXXXX)" -readonly NS2="ns2-$(mktemp -u XXXXXX)" -readonly NS3="ns3-$(mktemp -u XXXXXX)" - -readonly IPv4_1="172.16.1.100" -readonly IPv4_2="172.16.2.100" -readonly IPv4_3="172.16.3.100" -readonly IPv4_4="172.16.4.100" -readonly IPv4_5="172.16.5.100" -readonly IPv4_6="172.16.6.100" -readonly IPv4_7="172.16.7.100" -readonly IPv4_8="172.16.8.100" -readonly IPv4_GRE="172.16.16.100" - -readonly IPv4_SRC=$IPv4_1 -readonly IPv4_DST=$IPv4_4 - -readonly IPv6_1="fb01::1" -readonly IPv6_2="fb02::1" -readonly IPv6_3="fb03::1" -readonly IPv6_4="fb04::1" -readonly IPv6_5="fb05::1" -readonly IPv6_6="fb06::1" -readonly IPv6_7="fb07::1" -readonly IPv6_8="fb08::1" -readonly IPv6_GRE="fb10::1" - -readonly IPv6_SRC=$IPv6_1 -readonly IPv6_DST=$IPv6_4 - -TEST_STATUS=0 -TESTS_SUCCEEDED=0 -TESTS_FAILED=0 - -TMPFILE="" - -process_test_results() -{ - if [[ "${TEST_STATUS}" -eq 0 ]] ; then - echo "PASS" - TESTS_SUCCEEDED=$((TESTS_SUCCEEDED+1)) - else - echo "FAIL" - TESTS_FAILED=$((TESTS_FAILED+1)) - fi -} - -print_test_summary_and_exit() -{ - echo "passed tests: ${TESTS_SUCCEEDED}" - echo "failed tests: ${TESTS_FAILED}" - if [ "${TESTS_FAILED}" -eq "0" ] ; then - exit 0 - else - exit 1 - fi -} - -setup() -{ - set -e # exit on error - TEST_STATUS=0 - - # create devices and namespaces - ip netns add "${NS1}" - ip netns add "${NS2}" - ip netns add "${NS3}" - - # rp_filter gets confused by what these tests are doing, so disable it - ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${NS1} sysctl -wq net.ipv4.conf.default.rp_filter=0 - ip netns exec ${NS2} sysctl -wq net.ipv4.conf.default.rp_filter=0 - ip netns exec ${NS3} sysctl -wq net.ipv4.conf.default.rp_filter=0 - - # disable IPv6 DAD because it sometimes takes too long and fails tests - ip netns exec ${NS1} sysctl -wq net.ipv6.conf.all.accept_dad=0 - ip netns exec ${NS2} sysctl -wq net.ipv6.conf.all.accept_dad=0 - ip netns exec ${NS3} sysctl -wq net.ipv6.conf.all.accept_dad=0 - ip netns exec ${NS1} sysctl -wq net.ipv6.conf.default.accept_dad=0 - ip netns exec ${NS2} sysctl -wq net.ipv6.conf.default.accept_dad=0 - ip netns exec ${NS3} sysctl -wq net.ipv6.conf.default.accept_dad=0 - - ip link add veth1 type veth peer name veth2 - ip link add veth3 type veth peer name veth4 - ip link add veth5 type veth peer name veth6 - ip link add veth7 type veth peer name veth8 - - ip netns exec ${NS2} sysctl -wq net.ipv4.ip_forward=1 - ip netns exec ${NS2} sysctl -wq net.ipv6.conf.all.forwarding=1 - - ip link set veth1 netns ${NS1} - ip link set veth2 netns ${NS2} - ip link set veth3 netns ${NS2} - ip link set veth4 netns ${NS3} - ip link set veth5 netns ${NS1} - ip link set veth6 netns ${NS2} - ip link set veth7 netns ${NS2} - ip link set veth8 netns ${NS3} - - if [ ! -z "${VRF}" ] ; then - ip -netns ${NS1} link add red type vrf table 1001 - ip -netns ${NS1} link set red up - ip -netns ${NS1} route add table 1001 unreachable default metric 8192 - ip -netns ${NS1} -6 route add table 1001 unreachable default metric 8192 - ip -netns ${NS1} link set veth1 vrf red - ip -netns ${NS1} link set veth5 vrf red - - ip -netns ${NS2} link add red type vrf table 1001 - ip -netns ${NS2} link set red up - ip -netns ${NS2} route add table 1001 unreachable default metric 8192 - ip -netns ${NS2} -6 route add table 1001 unreachable default metric 8192 - ip -netns ${NS2} link set veth2 vrf red - ip -netns ${NS2} link set veth3 vrf red - ip -netns ${NS2} link set veth6 vrf red - ip -netns ${NS2} link set veth7 vrf red - fi - - # configure addesses: the top route (1-2-3-4) - ip -netns ${NS1} addr add ${IPv4_1}/24 dev veth1 - ip -netns ${NS2} addr add ${IPv4_2}/24 dev veth2 - ip -netns ${NS2} addr add ${IPv4_3}/24 dev veth3 - ip -netns ${NS3} addr add ${IPv4_4}/24 dev veth4 - ip -netns ${NS1} -6 addr add ${IPv6_1}/128 nodad dev veth1 - ip -netns ${NS2} -6 addr add ${IPv6_2}/128 nodad dev veth2 - ip -netns ${NS2} -6 addr add ${IPv6_3}/128 nodad dev veth3 - ip -netns ${NS3} -6 addr add ${IPv6_4}/128 nodad dev veth4 - - # configure addresses: the bottom route (5-6-7-8) - ip -netns ${NS1} addr add ${IPv4_5}/24 dev veth5 - ip -netns ${NS2} addr add ${IPv4_6}/24 dev veth6 - ip -netns ${NS2} addr add ${IPv4_7}/24 dev veth7 - ip -netns ${NS3} addr add ${IPv4_8}/24 dev veth8 - ip -netns ${NS1} -6 addr add ${IPv6_5}/128 nodad dev veth5 - ip -netns ${NS2} -6 addr add ${IPv6_6}/128 nodad dev veth6 - ip -netns ${NS2} -6 addr add ${IPv6_7}/128 nodad dev veth7 - ip -netns ${NS3} -6 addr add ${IPv6_8}/128 nodad dev veth8 - - ip -netns ${NS1} link set dev veth1 up - ip -netns ${NS2} link set dev veth2 up - ip -netns ${NS2} link set dev veth3 up - ip -netns ${NS3} link set dev veth4 up - ip -netns ${NS1} link set dev veth5 up - ip -netns ${NS2} link set dev veth6 up - ip -netns ${NS2} link set dev veth7 up - ip -netns ${NS3} link set dev veth8 up - - # configure routes: IP*_SRC -> veth1/IP*_2 (= top route) default; - # the bottom route to specific bottom addresses - - # NS1 - # top route - ip -netns ${NS1} route add ${IPv4_2}/32 dev veth1 ${VRF} - ip -netns ${NS1} route add default dev veth1 via ${IPv4_2} ${VRF} # go top by default - ip -netns ${NS1} -6 route add ${IPv6_2}/128 dev veth1 ${VRF} - ip -netns ${NS1} -6 route add default dev veth1 via ${IPv6_2} ${VRF} # go top by default - # bottom route - ip -netns ${NS1} route add ${IPv4_6}/32 dev veth5 ${VRF} - ip -netns ${NS1} route add ${IPv4_7}/32 dev veth5 via ${IPv4_6} ${VRF} - ip -netns ${NS1} route add ${IPv4_8}/32 dev veth5 via ${IPv4_6} ${VRF} - ip -netns ${NS1} -6 route add ${IPv6_6}/128 dev veth5 ${VRF} - ip -netns ${NS1} -6 route add ${IPv6_7}/128 dev veth5 via ${IPv6_6} ${VRF} - ip -netns ${NS1} -6 route add ${IPv6_8}/128 dev veth5 via ${IPv6_6} ${VRF} - - # NS2 - # top route - ip -netns ${NS2} route add ${IPv4_1}/32 dev veth2 ${VRF} - ip -netns ${NS2} route add ${IPv4_4}/32 dev veth3 ${VRF} - ip -netns ${NS2} -6 route add ${IPv6_1}/128 dev veth2 ${VRF} - ip -netns ${NS2} -6 route add ${IPv6_4}/128 dev veth3 ${VRF} - # bottom route - ip -netns ${NS2} route add ${IPv4_5}/32 dev veth6 ${VRF} - ip -netns ${NS2} route add ${IPv4_8}/32 dev veth7 ${VRF} - ip -netns ${NS2} -6 route add ${IPv6_5}/128 dev veth6 ${VRF} - ip -netns ${NS2} -6 route add ${IPv6_8}/128 dev veth7 ${VRF} - - # NS3 - # top route - ip -netns ${NS3} route add ${IPv4_3}/32 dev veth4 - ip -netns ${NS3} route add ${IPv4_1}/32 dev veth4 via ${IPv4_3} - ip -netns ${NS3} route add ${IPv4_2}/32 dev veth4 via ${IPv4_3} - ip -netns ${NS3} -6 route add ${IPv6_3}/128 dev veth4 - ip -netns ${NS3} -6 route add ${IPv6_1}/128 dev veth4 via ${IPv6_3} - ip -netns ${NS3} -6 route add ${IPv6_2}/128 dev veth4 via ${IPv6_3} - # bottom route - ip -netns ${NS3} route add ${IPv4_7}/32 dev veth8 - ip -netns ${NS3} route add ${IPv4_5}/32 dev veth8 via ${IPv4_7} - ip -netns ${NS3} route add ${IPv4_6}/32 dev veth8 via ${IPv4_7} - ip -netns ${NS3} -6 route add ${IPv6_7}/128 dev veth8 - ip -netns ${NS3} -6 route add ${IPv6_5}/128 dev veth8 via ${IPv6_7} - ip -netns ${NS3} -6 route add ${IPv6_6}/128 dev veth8 via ${IPv6_7} - - # configure IPv4 GRE device in NS3, and a route to it via the "bottom" route - ip -netns ${NS3} tunnel add gre_dev mode gre remote ${IPv4_1} local ${IPv4_GRE} ttl 255 - ip -netns ${NS3} link set gre_dev up - ip -netns ${NS3} addr add ${IPv4_GRE} dev gre_dev - ip -netns ${NS1} route add ${IPv4_GRE}/32 dev veth5 via ${IPv4_6} ${VRF} - ip -netns ${NS2} route add ${IPv4_GRE}/32 dev veth7 via ${IPv4_8} ${VRF} - - - # configure IPv6 GRE device in NS3, and a route to it via the "bottom" route - ip -netns ${NS3} -6 tunnel add name gre6_dev mode ip6gre remote ${IPv6_1} local ${IPv6_GRE} ttl 255 - ip -netns ${NS3} link set gre6_dev up - ip -netns ${NS3} -6 addr add ${IPv6_GRE} nodad dev gre6_dev - ip -netns ${NS1} -6 route add ${IPv6_GRE}/128 dev veth5 via ${IPv6_6} ${VRF} - ip -netns ${NS2} -6 route add ${IPv6_GRE}/128 dev veth7 via ${IPv6_8} ${VRF} - - TMPFILE=$(mktemp /tmp/test_lwt_ip_encap.XXXXXX) - - sleep 1 # reduce flakiness - set +e -} - -cleanup() -{ - if [ -f ${TMPFILE} ] ; then - rm ${TMPFILE} - fi - - ip netns del ${NS1} 2> /dev/null - ip netns del ${NS2} 2> /dev/null - ip netns del ${NS3} 2> /dev/null -} - -trap cleanup EXIT - -remove_routes_to_gredev() -{ - ip -netns ${NS1} route del ${IPv4_GRE} dev veth5 ${VRF} - ip -netns ${NS2} route del ${IPv4_GRE} dev veth7 ${VRF} - ip -netns ${NS1} -6 route del ${IPv6_GRE}/128 dev veth5 ${VRF} - ip -netns ${NS2} -6 route del ${IPv6_GRE}/128 dev veth7 ${VRF} -} - -add_unreachable_routes_to_gredev() -{ - ip -netns ${NS1} route add unreachable ${IPv4_GRE}/32 ${VRF} - ip -netns ${NS2} route add unreachable ${IPv4_GRE}/32 ${VRF} - ip -netns ${NS1} -6 route add unreachable ${IPv6_GRE}/128 ${VRF} - ip -netns ${NS2} -6 route add unreachable ${IPv6_GRE}/128 ${VRF} -} - -test_ping() -{ - local readonly PROTO=$1 - local readonly EXPECTED=$2 - local RET=0 - - if [ "${PROTO}" == "IPv4" ] ; then - ip netns exec ${NS1} ping -c 1 -W 1 -I veth1 ${IPv4_DST} 2>&1 > /dev/null - RET=$? - elif [ "${PROTO}" == "IPv6" ] ; then - ip netns exec ${NS1} ping6 -c 1 -W 1 -I veth1 ${IPv6_DST} 2>&1 > /dev/null - RET=$? - else - echo " test_ping: unknown PROTO: ${PROTO}" - TEST_STATUS=1 - fi - - if [ "0" != "${RET}" ]; then - RET=1 - fi - - if [ "${EXPECTED}" != "${RET}" ] ; then - echo " test_ping failed: expected: ${EXPECTED}; got ${RET}" - TEST_STATUS=1 - fi -} - -test_gso() -{ - local readonly PROTO=$1 - local readonly PKT_SZ=5000 - local IP_DST="" - : > ${TMPFILE} # trim the capture file - - # check that nc is present - command -v nc >/dev/null 2>&1 || \ - { echo >&2 "nc is not available: skipping TSO tests"; return; } - - # listen on port 9000, capture TCP into $TMPFILE - if [ "${PROTO}" == "IPv4" ] ; then - IP_DST=${IPv4_DST} - ip netns exec ${NS3} bash -c \ - "nc -4 -l -p 9000 > ${TMPFILE} &" - elif [ "${PROTO}" == "IPv6" ] ; then - IP_DST=${IPv6_DST} - ip netns exec ${NS3} bash -c \ - "nc -6 -l -p 9000 > ${TMPFILE} &" - RET=$? - else - echo " test_gso: unknown PROTO: ${PROTO}" - TEST_STATUS=1 - fi - sleep 1 # let nc start listening - - # send a packet larger than MTU - ip netns exec ${NS1} bash -c \ - "dd if=/dev/zero bs=$PKT_SZ count=1 > /dev/tcp/${IP_DST}/9000 2>/dev/null" - sleep 2 # let the packet get delivered - - # verify we received all expected bytes - SZ=$(stat -c %s ${TMPFILE}) - if [ "$SZ" != "$PKT_SZ" ] ; then - echo " test_gso failed: ${PROTO}" - TEST_STATUS=1 - fi -} - -test_egress() -{ - local readonly ENCAP=$1 - echo "starting egress ${ENCAP} encap test ${VRF}" - setup - - # by default, pings work - test_ping IPv4 0 - test_ping IPv6 0 - - # remove NS2->DST routes, ping fails - ip -netns ${NS2} route del ${IPv4_DST}/32 dev veth3 ${VRF} - ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3 ${VRF} - test_ping IPv4 1 - test_ping IPv6 1 - - # install replacement routes (LWT/eBPF), pings succeed - if [ "${ENCAP}" == "IPv4" ] ; then - ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj \ - ${BPF_FILE} sec encap_gre dev veth1 ${VRF} - ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj \ - ${BPF_FILE} sec encap_gre dev veth1 ${VRF} - elif [ "${ENCAP}" == "IPv6" ] ; then - ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj \ - ${BPF_FILE} sec encap_gre6 dev veth1 ${VRF} - ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj \ - ${BPF_FILE} sec encap_gre6 dev veth1 ${VRF} - else - echo " unknown encap ${ENCAP}" - TEST_STATUS=1 - fi - test_ping IPv4 0 - test_ping IPv6 0 - - # skip GSO tests with VRF: VRF routing needs properly assigned - # source IP/device, which is easy to do with ping and hard with dd/nc. - if [ -z "${VRF}" ] ; then - test_gso IPv4 - test_gso IPv6 - fi - - # a negative test: remove routes to GRE devices: ping fails - remove_routes_to_gredev - test_ping IPv4 1 - test_ping IPv6 1 - - # another negative test - add_unreachable_routes_to_gredev - test_ping IPv4 1 - test_ping IPv6 1 - - cleanup - process_test_results -} - -test_ingress() -{ - local readonly ENCAP=$1 - echo "starting ingress ${ENCAP} encap test ${VRF}" - setup - - # need to wait a bit for IPv6 to autoconf, otherwise - # ping6 sometimes fails with "unable to bind to address" - - # by default, pings work - test_ping IPv4 0 - test_ping IPv6 0 - - # remove NS2->DST routes, pings fail - ip -netns ${NS2} route del ${IPv4_DST}/32 dev veth3 ${VRF} - ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3 ${VRF} - test_ping IPv4 1 - test_ping IPv6 1 - - # install replacement routes (LWT/eBPF), pings succeed - if [ "${ENCAP}" == "IPv4" ] ; then - ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj \ - ${BPF_FILE} sec encap_gre dev veth2 ${VRF} - ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj \ - ${BPF_FILE} sec encap_gre dev veth2 ${VRF} - elif [ "${ENCAP}" == "IPv6" ] ; then - ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj \ - ${BPF_FILE} sec encap_gre6 dev veth2 ${VRF} - ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj \ - ${BPF_FILE} sec encap_gre6 dev veth2 ${VRF} - else - echo "FAIL: unknown encap ${ENCAP}" - TEST_STATUS=1 - fi - test_ping IPv4 0 - test_ping IPv6 0 - - # a negative test: remove routes to GRE devices: ping fails - remove_routes_to_gredev - test_ping IPv4 1 - test_ping IPv6 1 - - # another negative test - add_unreachable_routes_to_gredev - test_ping IPv4 1 - test_ping IPv6 1 - - cleanup - process_test_results -} - -VRF="" -test_egress IPv4 -test_egress IPv6 -test_ingress IPv4 -test_ingress IPv6 - -VRF="vrf red" -test_egress IPv4 -test_egress IPv6 -test_ingress IPv4 -test_ingress IPv6 - -print_test_summary_and_exit diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh deleted file mode 100755 index 0efea22..0000000 --- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh +++ /dev/null @@ -1,156 +0,0 @@ -#!/bin/bash -# Connects 6 network namespaces through veths. -# Each NS may have different IPv6 global scope addresses : -# NS1 ---- NS2 ---- NS3 ---- NS4 ---- NS5 ---- NS6 -# fb00::1 fd00::1 fd00::2 fd00::3 fb00::6 -# fc42::1 fd00::4 -# -# All IPv6 packets going to fb00::/16 through NS2 will be encapsulated in a -# IPv6 header with a Segment Routing Header, with segments : -# fd00::1 -> fd00::2 -> fd00::3 -> fd00::4 -# -# 3 fd00::/16 IPv6 addresses are binded to seg6local End.BPF actions : -# - fd00::1 : add a TLV, change the flags and apply a End.X action to fc42::1 -# - fd00::2 : remove the TLV, change the flags, add a tag -# - fd00::3 : apply an End.T action to fd00::4, through routing table 117 -# -# fd00::4 is a simple Segment Routing node decapsulating the inner IPv6 packet. -# Each End.BPF action will validate the operations applied on the SRH by the -# previous BPF program in the chain, otherwise the packet is dropped. -# -# An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this -# datagram can be read on NS6 when binding to fb00::6. - -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 -BPF_FILE="test_lwt_seg6local.bpf.o" -readonly NS1="ns1-$(mktemp -u XXXXXX)" -readonly NS2="ns2-$(mktemp -u XXXXXX)" -readonly NS3="ns3-$(mktemp -u XXXXXX)" -readonly NS4="ns4-$(mktemp -u XXXXXX)" -readonly NS5="ns5-$(mktemp -u XXXXXX)" -readonly NS6="ns6-$(mktemp -u XXXXXX)" - -msg="skip all tests:" -if [ $UID != 0 ]; then - echo $msg please run this as root >&2 - exit $ksft_skip -fi - -TMP_FILE="/tmp/selftest_lwt_seg6local.txt" - -cleanup() -{ - if [ "$?" = "0" ]; then - echo "selftests: test_lwt_seg6local [PASS]"; - else - echo "selftests: test_lwt_seg6local [FAILED]"; - fi - - set +e - ip netns del ${NS1} 2> /dev/null - ip netns del ${NS2} 2> /dev/null - ip netns del ${NS3} 2> /dev/null - ip netns del ${NS4} 2> /dev/null - ip netns del ${NS5} 2> /dev/null - ip netns del ${NS6} 2> /dev/null - rm -f $TMP_FILE -} - -set -e - -ip netns add ${NS1} -ip netns add ${NS2} -ip netns add ${NS3} -ip netns add ${NS4} -ip netns add ${NS5} -ip netns add ${NS6} - -trap cleanup 0 2 3 6 9 - -ip link add veth1 type veth peer name veth2 -ip link add veth3 type veth peer name veth4 -ip link add veth5 type veth peer name veth6 -ip link add veth7 type veth peer name veth8 -ip link add veth9 type veth peer name veth10 - -ip link set veth1 netns ${NS1} -ip link set veth2 netns ${NS2} -ip link set veth3 netns ${NS2} -ip link set veth4 netns ${NS3} -ip link set veth5 netns ${NS3} -ip link set veth6 netns ${NS4} -ip link set veth7 netns ${NS4} -ip link set veth8 netns ${NS5} -ip link set veth9 netns ${NS5} -ip link set veth10 netns ${NS6} - -ip netns exec ${NS1} ip link set dev veth1 up -ip netns exec ${NS2} ip link set dev veth2 up -ip netns exec ${NS2} ip link set dev veth3 up -ip netns exec ${NS3} ip link set dev veth4 up -ip netns exec ${NS3} ip link set dev veth5 up -ip netns exec ${NS4} ip link set dev veth6 up -ip netns exec ${NS4} ip link set dev veth7 up -ip netns exec ${NS5} ip link set dev veth8 up -ip netns exec ${NS5} ip link set dev veth9 up -ip netns exec ${NS6} ip link set dev veth10 up -ip netns exec ${NS6} ip link set dev lo up - -# All link scope addresses and routes required between veths -ip netns exec ${NS1} ip -6 addr add fb00::12/16 dev veth1 scope link -ip netns exec ${NS1} ip -6 route add fb00::21 dev veth1 scope link -ip netns exec ${NS2} ip -6 addr add fb00::21/16 dev veth2 scope link -ip netns exec ${NS2} ip -6 addr add fb00::34/16 dev veth3 scope link -ip netns exec ${NS2} ip -6 route add fb00::43 dev veth3 scope link -ip netns exec ${NS3} ip -6 route add fb00::65 dev veth5 scope link -ip netns exec ${NS3} ip -6 addr add fb00::43/16 dev veth4 scope link -ip netns exec ${NS3} ip -6 addr add fb00::56/16 dev veth5 scope link -ip netns exec ${NS4} ip -6 addr add fb00::65/16 dev veth6 scope link -ip netns exec ${NS4} ip -6 addr add fb00::78/16 dev veth7 scope link -ip netns exec ${NS4} ip -6 route add fb00::87 dev veth7 scope link -ip netns exec ${NS5} ip -6 addr add fb00::87/16 dev veth8 scope link -ip netns exec ${NS5} ip -6 addr add fb00::910/16 dev veth9 scope link -ip netns exec ${NS5} ip -6 route add fb00::109 dev veth9 scope link -ip netns exec ${NS5} ip -6 route add fb00::109 table 117 dev veth9 scope link -ip netns exec ${NS6} ip -6 addr add fb00::109/16 dev veth10 scope link - -ip netns exec ${NS1} ip -6 addr add fb00::1/16 dev lo -ip netns exec ${NS1} ip -6 route add fb00::6 dev veth1 via fb00::21 - -ip netns exec ${NS2} ip -6 route add fb00::6 encap bpf in obj ${BPF_FILE} sec encap_srh dev veth2 -ip netns exec ${NS2} ip -6 route add fd00::1 dev veth3 via fb00::43 scope link - -ip netns exec ${NS3} ip -6 route add fc42::1 dev veth5 via fb00::65 -ip netns exec ${NS3} ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj ${BPF_FILE} sec add_egr_x dev veth4 - -ip netns exec ${NS4} ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj ${BPF_FILE} sec pop_egr dev veth6 -ip netns exec ${NS4} ip -6 addr add fc42::1 dev lo -ip netns exec ${NS4} ip -6 route add fd00::3 dev veth7 via fb00::87 - -ip netns exec ${NS5} ip -6 route add fd00::4 table 117 dev veth9 via fb00::109 -ip netns exec ${NS5} ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj ${BPF_FILE} sec inspect_t dev veth8 - -ip netns exec ${NS6} ip -6 addr add fb00::6/16 dev lo -ip netns exec ${NS6} ip -6 addr add fd00::4/16 dev lo - -ip netns exec ${NS1} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null -ip netns exec ${NS2} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null -ip netns exec ${NS3} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null -ip netns exec ${NS4} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null -ip netns exec ${NS5} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null - -ip netns exec ${NS6} sysctl net.ipv6.conf.all.seg6_enabled=1 > /dev/null -ip netns exec ${NS6} sysctl net.ipv6.conf.lo.seg6_enabled=1 > /dev/null -ip netns exec ${NS6} sysctl net.ipv6.conf.veth10.seg6_enabled=1 > /dev/null - -ip netns exec ${NS6} nc -l -6 -u -d 7330 > $TMP_FILE & -ip netns exec ${NS1} bash -c "echo 'foobar' | nc -w0 -6 -u -p 2121 -s fb00::1 fb00::6 7330" -sleep 5 # wait enough time to ensure the UDP datagram arrived to the last segment -kill -TERM $! - -if [[ $(< $TMP_FILE) != "foobar" ]]; then - exit 1 -fi - -exit 0 diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 8b40e94..986ce32 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -1396,9 +1396,10 @@ static void test_map_stress(void) #define MAX_DELAY_US 50000 #define MIN_DELAY_RANGE_US 5000 -static bool retry_for_again_or_busy(int err) +static bool can_retry(int err) { - return (err == EAGAIN || err == EBUSY); + return (err == EAGAIN || err == EBUSY || + (err == ENOMEM && map_opts.map_flags == BPF_F_NO_PREALLOC)); } int map_update_retriable(int map_fd, const void *key, const void *value, int flags, int attempts, @@ -1451,12 +1452,12 @@ static void test_update_delete(unsigned int fn, void *data) if (do_update) { err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES, - retry_for_again_or_busy); + can_retry); if (err) printf("error %d %d\n", err, errno); assert(err == 0); err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES, - retry_for_again_or_busy); + can_retry); if (err) printf("error %d %d\n", err, errno); assert(err == 0); diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index c9e745d..309d9d4 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -88,7 +88,9 @@ static void stdio_hijack(char **log_buf, size_t *log_cnt) #endif } -static void stdio_restore_cleanup(void) +static pthread_mutex_t stdout_lock = PTHREAD_MUTEX_INITIALIZER; + +static void stdio_restore(void) { #ifdef __GLIBC__ if (verbose() && env.worker_id == -1) { @@ -98,34 +100,33 @@ static void stdio_restore_cleanup(void) fflush(stdout); + pthread_mutex_lock(&stdout_lock); + if (env.subtest_state) { - fclose(env.subtest_state->stdout_saved); + if (env.subtest_state->stdout_saved) + fclose(env.subtest_state->stdout_saved); env.subtest_state->stdout_saved = NULL; stdout = env.test_state->stdout_saved; stderr = env.test_state->stdout_saved; } else { - fclose(env.test_state->stdout_saved); + if (env.test_state->stdout_saved) + fclose(env.test_state->stdout_saved); env.test_state->stdout_saved = NULL; + stdout = env.stdout_saved; + stderr = env.stderr_saved; } + + pthread_mutex_unlock(&stdout_lock); #endif } -static void stdio_restore(void) +static int traffic_monitor_print_fn(const char *format, va_list args) { -#ifdef __GLIBC__ - if (verbose() && env.worker_id == -1) { - /* nothing to do, output to stdout by default */ - return; - } - - if (stdout == env.stdout_saved) - return; - - stdio_restore_cleanup(); + pthread_mutex_lock(&stdout_lock); + vfprintf(stdout, format, args); + pthread_mutex_unlock(&stdout_lock); - stdout = env.stdout_saved; - stderr = env.stderr_saved; -#endif + return 0; } /* Adapted from perf/util/string.c */ @@ -474,8 +475,6 @@ static void dump_test_log(const struct prog_test_def *test, print_test_result(test, test_state); } -static void stdio_restore(void); - /* A bunch of tests set custom affinity per-thread and/or per-process. Reset * it after each test/sub-test. */ @@ -490,13 +489,11 @@ static void reset_affinity(void) err = sched_setaffinity(0, sizeof(cpuset), &cpuset); if (err < 0) { - stdio_restore(); fprintf(stderr, "Failed to reset process affinity: %d!\n", err); exit(EXIT_ERR_SETUP_INFRA); } err = pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset); if (err < 0) { - stdio_restore(); fprintf(stderr, "Failed to reset thread affinity: %d!\n", err); exit(EXIT_ERR_SETUP_INFRA); } @@ -514,7 +511,6 @@ static void save_netns(void) static void restore_netns(void) { if (setns(env.saved_netns_fd, CLONE_NEWNET) == -1) { - stdio_restore(); perror("setns(CLONE_NEWNS)"); exit(EXIT_ERR_SETUP_INFRA); } @@ -541,7 +537,8 @@ void test__end_subtest(void) test_result(subtest_state->error_cnt, subtest_state->skipped)); - stdio_restore_cleanup(); + stdio_restore(); + env.subtest_state = NULL; } @@ -1270,8 +1267,10 @@ void crash_handler(int signum) sz = backtrace(bt, ARRAY_SIZE(bt)); - if (env.stdout_saved) - stdio_restore(); + fflush(stdout); + stdout = env.stdout_saved; + stderr = env.stderr_saved; + if (env.test) { env.test_state->error_cnt++; dump_test_log(env.test, env.test_state, true, false, NULL); @@ -1365,10 +1364,19 @@ static int recv_message(int sock, struct msg *msg) return ret; } +static bool ns_is_needed(const char *test_name) +{ + if (strlen(test_name) < 3) + return false; + + return !strncmp(test_name, "ns_", 3); +} + static void run_one_test(int test_num) { struct prog_test_def *test = &prog_test_defs[test_num]; struct test_state *state = &test_states[test_num]; + struct netns_obj *ns = NULL; env.test = test; env.test_state = state; @@ -1376,10 +1384,13 @@ static void run_one_test(int test_num) stdio_hijack(&state->log_buf, &state->log_cnt); watchdog_start(); + if (ns_is_needed(test->test_name)) + ns = netns_new(test->test_name, true); if (test->run_test) test->run_test(); else if (test->run_serial_test) test->run_serial_test(); + netns_free(ns); watchdog_stop(); /* ensure last sub-test is finalized properly */ @@ -1388,6 +1399,8 @@ static void run_one_test(int test_num) state->tested = true; + stdio_restore(); + if (verbose() && env.worker_id == -1) print_test_result(test, state); @@ -1396,7 +1409,6 @@ static void run_one_test(int test_num) if (test->need_cgroup_cleanup) cleanup_cgroup_environment(); - stdio_restore(); free(stop_libbpf_log_capture()); dump_test_log(test, state, false, false, NULL); @@ -1931,6 +1943,9 @@ int main(int argc, char **argv) sigaction(SIGSEGV, &sigact, NULL); + env.stdout_saved = stdout; + env.stderr_saved = stderr; + env.secs_till_notify = 10; env.secs_till_kill = 120; err = argp_parse(&argp, argc, argv, 0, NULL, &env); @@ -1947,6 +1962,8 @@ int main(int argc, char **argv) libbpf_set_strict_mode(LIBBPF_STRICT_ALL); libbpf_set_print(libbpf_print_fn); + traffic_monitor_set_print(traffic_monitor_print_fn); + srand(time(NULL)); env.jit_enabled = is_jit_enabled(); @@ -1957,9 +1974,6 @@ int main(int argc, char **argv) return -1; } - env.stdout_saved = stdout; - env.stderr_saved = stderr; - env.has_testmod = true; if (!env.list_test_names) { /* ensure previous instance of the module is unloaded */ diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 404d0d4..870694f 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -427,6 +427,14 @@ void hexdump(const char *prefix, const void *buf, size_t len); goto goto_label; \ }) +#define SYS_FAIL(goto_label, fmt, ...) \ + ({ \ + char cmd[1024]; \ + snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__); \ + if (!ASSERT_NEQ(0, system(cmd), cmd)) \ + goto goto_label; \ + }) + #define ALL_TO_DEV_NULL " >/dev/null 2>&1" #define SYS_NOFAIL(fmt, ...) \ diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh deleted file mode 100755 index d9661b9..0000000 --- a/tools/testing/selftests/bpf/test_tunnel.sh +++ /dev/null @@ -1,645 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -# End-to-end eBPF tunnel test suite -# The script tests BPF network tunnel implementation. -# -# Topology: -# --------- -# root namespace | at_ns0 namespace -# | -# ----------- | ----------- -# | tnl dev | | | tnl dev | (overlay network) -# ----------- | ----------- -# metadata-mode | native-mode -# with bpf | -# | -# ---------- | ---------- -# | veth1 | --------- | veth0 | (underlay network) -# ---------- peer ---------- -# -# -# Device Configuration -# -------------------- -# Root namespace with metadata-mode tunnel + BPF -# Device names and addresses: -# veth1 IP: 172.16.1.200, IPv6: 00::22 (underlay) -# tunnel dev 11, ex: gre11, IPv4: 10.1.1.200, IPv6: 1::22 (overlay) -# -# Namespace at_ns0 with native tunnel -# Device names and addresses: -# veth0 IPv4: 172.16.1.100, IPv6: 00::11 (underlay) -# tunnel dev 00, ex: gre00, IPv4: 10.1.1.100, IPv6: 1::11 (overlay) -# -# -# End-to-end ping packet flow -# --------------------------- -# Most of the tests start by namespace creation, device configuration, -# then ping the underlay and overlay network. When doing 'ping 10.1.1.100' -# from root namespace, the following operations happen: -# 1) Route lookup shows 10.1.1.100/24 belongs to tnl dev, fwd to tnl dev. -# 2) Tnl device's egress BPF program is triggered and set the tunnel metadata, -# with remote_ip=172.16.1.100 and others. -# 3) Outer tunnel header is prepended and route the packet to veth1's egress -# 4) veth0's ingress queue receive the tunneled packet at namespace at_ns0 -# 5) Tunnel protocol handler, ex: vxlan_rcv, decap the packet -# 6) Forward the packet to the overlay tnl dev - -BPF_FILE="test_tunnel_kern.bpf.o" -BPF_PIN_TUNNEL_DIR="/sys/fs/bpf/tc/tunnel" -PING_ARG="-c 3 -w 10 -q" -ret=0 -GREEN='\033[0;92m' -RED='\033[0;31m' -NC='\033[0m' # No Color - -config_device() -{ - ip netns add at_ns0 - ip link add veth0 type veth peer name veth1 - ip link set veth0 netns at_ns0 - ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0 - ip netns exec at_ns0 ip link set dev veth0 up - ip link set dev veth1 up mtu 1500 - ip addr add dev veth1 172.16.1.200/24 -} - -add_gre_tunnel() -{ - tun_key= - if [ -n "$1" ]; then - tun_key="key $1" - fi - - # at_ns0 namespace - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE seq $tun_key \ - local 172.16.1.100 remote 172.16.1.200 - ip netns exec at_ns0 ip link set dev $DEV_NS up - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - - # root namespace - ip link add dev $DEV type $TYPE $tun_key external - ip link set dev $DEV up - ip addr add dev $DEV 10.1.1.200/24 -} - -add_ip6gretap_tunnel() -{ - - # assign ipv6 address - ip netns exec at_ns0 ip addr add ::11/96 dev veth0 - ip netns exec at_ns0 ip link set dev veth0 up - ip addr add dev veth1 ::22/96 - ip link set dev veth1 up - - # at_ns0 namespace - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \ - local ::11 remote ::22 - - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - ip netns exec at_ns0 ip addr add dev $DEV_NS fc80::100/96 - ip netns exec at_ns0 ip link set dev $DEV_NS up - - # root namespace - ip link add dev $DEV type $TYPE external - ip addr add dev $DEV 10.1.1.200/24 - ip addr add dev $DEV fc80::200/24 - ip link set dev $DEV up -} - -add_erspan_tunnel() -{ - # at_ns0 namespace - if [ "$1" == "v1" ]; then - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE seq key 2 \ - local 172.16.1.100 remote 172.16.1.200 \ - erspan_ver 1 erspan 123 - else - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE seq key 2 \ - local 172.16.1.100 remote 172.16.1.200 \ - erspan_ver 2 erspan_dir egress erspan_hwid 3 - fi - ip netns exec at_ns0 ip link set dev $DEV_NS up - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - - # root namespace - ip link add dev $DEV type $TYPE external - ip link set dev $DEV up - ip addr add dev $DEV 10.1.1.200/24 -} - -add_ip6erspan_tunnel() -{ - - # assign ipv6 address - ip netns exec at_ns0 ip addr add ::11/96 dev veth0 - ip netns exec at_ns0 ip link set dev veth0 up - ip addr add dev veth1 ::22/96 - ip link set dev veth1 up - - # at_ns0 namespace - if [ "$1" == "v1" ]; then - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE seq key 2 \ - local ::11 remote ::22 \ - erspan_ver 1 erspan 123 - else - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE seq key 2 \ - local ::11 remote ::22 \ - erspan_ver 2 erspan_dir egress erspan_hwid 7 - fi - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - ip netns exec at_ns0 ip link set dev $DEV_NS up - - # root namespace - ip link add dev $DEV type $TYPE external - ip addr add dev $DEV 10.1.1.200/24 - ip link set dev $DEV up -} - -add_geneve_tunnel() -{ - # at_ns0 namespace - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE \ - id 2 dstport 6081 remote 172.16.1.200 - ip netns exec at_ns0 ip link set dev $DEV_NS up - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - - # root namespace - ip link add dev $DEV type $TYPE dstport 6081 external - ip link set dev $DEV up - ip addr add dev $DEV 10.1.1.200/24 -} - -add_ip6geneve_tunnel() -{ - ip netns exec at_ns0 ip addr add ::11/96 dev veth0 - ip netns exec at_ns0 ip link set dev veth0 up - ip addr add dev veth1 ::22/96 - ip link set dev veth1 up - - # at_ns0 namespace - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE id 22 \ - remote ::22 # geneve has no local option - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - ip netns exec at_ns0 ip link set dev $DEV_NS up - - # root namespace - ip link add dev $DEV type $TYPE external - ip addr add dev $DEV 10.1.1.200/24 - ip link set dev $DEV up -} - -add_ipip_tunnel() -{ - # at_ns0 namespace - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE \ - local 172.16.1.100 remote 172.16.1.200 - ip netns exec at_ns0 ip link set dev $DEV_NS up - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - - # root namespace - ip link add dev $DEV type $TYPE external - ip link set dev $DEV up - ip addr add dev $DEV 10.1.1.200/24 -} - -add_ip6tnl_tunnel() -{ - ip netns exec at_ns0 ip addr add ::11/96 dev veth0 - ip netns exec at_ns0 ip link set dev veth0 up - ip addr add dev veth1 ::22/96 - ip link set dev veth1 up - - # at_ns0 namespace - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE \ - local ::11 remote ::22 - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - ip netns exec at_ns0 ip addr add dev $DEV_NS 1::11/96 - ip netns exec at_ns0 ip link set dev $DEV_NS up - - # root namespace - ip link add dev $DEV type $TYPE external - ip addr add dev $DEV 10.1.1.200/24 - ip addr add dev $DEV 1::22/96 - ip link set dev $DEV up -} - -test_gre() -{ - TYPE=gretap - DEV_NS=gretap00 - DEV=gretap11 - ret=0 - - check $TYPE - config_device - add_gre_tunnel 2 - attach_bpf $DEV gre_set_tunnel gre_get_tunnel - ping $PING_ARG 10.1.1.100 - check_err $? - ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 - check_err $? - cleanup - - if [ $ret -ne 0 ]; then - echo -e ${RED}"FAIL: $TYPE"${NC} - return 1 - fi - echo -e ${GREEN}"PASS: $TYPE"${NC} -} - -test_gre_no_tunnel_key() -{ - TYPE=gre - DEV_NS=gre00 - DEV=gre11 - ret=0 - - check $TYPE - config_device - add_gre_tunnel - attach_bpf $DEV gre_set_tunnel_no_key gre_get_tunnel - ping $PING_ARG 10.1.1.100 - check_err $? - ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 - check_err $? - cleanup - - if [ $ret -ne 0 ]; then - echo -e ${RED}"FAIL: $TYPE"${NC} - return 1 - fi - echo -e ${GREEN}"PASS: $TYPE"${NC} -} - -test_ip6gre() -{ - TYPE=ip6gre - DEV_NS=ip6gre00 - DEV=ip6gre11 - ret=0 - - check $TYPE - config_device - # reuse the ip6gretap function - add_ip6gretap_tunnel - attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel - # underlay - ping6 $PING_ARG ::11 - # overlay: ipv4 over ipv6 - ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 - ping $PING_ARG 10.1.1.100 - check_err $? - # overlay: ipv6 over ipv6 - ip netns exec at_ns0 ping6 $PING_ARG fc80::200 - check_err $? - cleanup - - if [ $ret -ne 0 ]; then - echo -e ${RED}"FAIL: $TYPE"${NC} - return 1 - fi - echo -e ${GREEN}"PASS: $TYPE"${NC} -} - -test_ip6gretap() -{ - TYPE=ip6gretap - DEV_NS=ip6gretap00 - DEV=ip6gretap11 - ret=0 - - check $TYPE - config_device - add_ip6gretap_tunnel - attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel - # underlay - ping6 $PING_ARG ::11 - # overlay: ipv4 over ipv6 - ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 - ping $PING_ARG 10.1.1.100 - check_err $? - # overlay: ipv6 over ipv6 - ip netns exec at_ns0 ping6 $PING_ARG fc80::200 - check_err $? - cleanup - - if [ $ret -ne 0 ]; then - echo -e ${RED}"FAIL: $TYPE"${NC} - return 1 - fi - echo -e ${GREEN}"PASS: $TYPE"${NC} -} - -test_erspan() -{ - TYPE=erspan - DEV_NS=erspan00 - DEV=erspan11 - ret=0 - - check $TYPE - config_device - add_erspan_tunnel $1 - attach_bpf $DEV erspan_set_tunnel erspan_get_tunnel - ping $PING_ARG 10.1.1.100 - check_err $? - ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 - check_err $? - cleanup - - if [ $ret -ne 0 ]; then - echo -e ${RED}"FAIL: $TYPE"${NC} - return 1 - fi - echo -e ${GREEN}"PASS: $TYPE"${NC} -} - -test_ip6erspan() -{ - TYPE=ip6erspan - DEV_NS=ip6erspan00 - DEV=ip6erspan11 - ret=0 - - check $TYPE - config_device - add_ip6erspan_tunnel $1 - attach_bpf $DEV ip4ip6erspan_set_tunnel ip4ip6erspan_get_tunnel - ping6 $PING_ARG ::11 - ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 - check_err $? - cleanup - - if [ $ret -ne 0 ]; then - echo -e ${RED}"FAIL: $TYPE"${NC} - return 1 - fi - echo -e ${GREEN}"PASS: $TYPE"${NC} -} - -test_geneve() -{ - TYPE=geneve - DEV_NS=geneve00 - DEV=geneve11 - ret=0 - - check $TYPE - config_device - add_geneve_tunnel - attach_bpf $DEV geneve_set_tunnel geneve_get_tunnel - ping $PING_ARG 10.1.1.100 - check_err $? - ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 - check_err $? - cleanup - - if [ $ret -ne 0 ]; then - echo -e ${RED}"FAIL: $TYPE"${NC} - return 1 - fi - echo -e ${GREEN}"PASS: $TYPE"${NC} -} - -test_ip6geneve() -{ - TYPE=geneve - DEV_NS=ip6geneve00 - DEV=ip6geneve11 - ret=0 - - check $TYPE - config_device - add_ip6geneve_tunnel - attach_bpf $DEV ip6geneve_set_tunnel ip6geneve_get_tunnel - ping $PING_ARG 10.1.1.100 - check_err $? - ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 - check_err $? - cleanup - - if [ $ret -ne 0 ]; then - echo -e ${RED}"FAIL: ip6$TYPE"${NC} - return 1 - fi - echo -e ${GREEN}"PASS: ip6$TYPE"${NC} -} - -test_ipip() -{ - TYPE=ipip - DEV_NS=ipip00 - DEV=ipip11 - ret=0 - - check $TYPE - config_device - add_ipip_tunnel - ip link set dev veth1 mtu 1500 - attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel - ping $PING_ARG 10.1.1.100 - check_err $? - ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 - check_err $? - cleanup - - if [ $ret -ne 0 ]; then - echo -e ${RED}"FAIL: $TYPE"${NC} - return 1 - fi - echo -e ${GREEN}"PASS: $TYPE"${NC} -} - -test_ipip6() -{ - TYPE=ip6tnl - DEV_NS=ipip6tnl00 - DEV=ipip6tnl11 - ret=0 - - check $TYPE - config_device - add_ip6tnl_tunnel - ip link set dev veth1 mtu 1500 - attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel - # underlay - ping6 $PING_ARG ::11 - # ip4 over ip6 - ping $PING_ARG 10.1.1.100 - check_err $? - ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 - check_err $? - cleanup - - if [ $ret -ne 0 ]; then - echo -e ${RED}"FAIL: $TYPE"${NC} - return 1 - fi - echo -e ${GREEN}"PASS: $TYPE"${NC} -} - -test_ip6ip6() -{ - TYPE=ip6tnl - DEV_NS=ip6ip6tnl00 - DEV=ip6ip6tnl11 - ret=0 - - check $TYPE - config_device - add_ip6tnl_tunnel - ip link set dev veth1 mtu 1500 - attach_bpf $DEV ip6ip6_set_tunnel ip6ip6_get_tunnel - # underlay - ping6 $PING_ARG ::11 - # ip6 over ip6 - ping6 $PING_ARG 1::11 - check_err $? - ip netns exec at_ns0 ping6 $PING_ARG 1::22 - check_err $? - cleanup - - if [ $ret -ne 0 ]; then - echo -e ${RED}"FAIL: ip6$TYPE"${NC} - return 1 - fi - echo -e ${GREEN}"PASS: ip6$TYPE"${NC} -} - -attach_bpf() -{ - DEV=$1 - SET=$2 - GET=$3 - mkdir -p ${BPF_PIN_TUNNEL_DIR} - bpftool prog loadall ${BPF_FILE} ${BPF_PIN_TUNNEL_DIR}/ - tc qdisc add dev $DEV clsact - tc filter add dev $DEV egress bpf da object-pinned ${BPF_PIN_TUNNEL_DIR}/$SET - tc filter add dev $DEV ingress bpf da object-pinned ${BPF_PIN_TUNNEL_DIR}/$GET -} - -cleanup() -{ - rm -rf ${BPF_PIN_TUNNEL_DIR} - - ip netns delete at_ns0 2> /dev/null - ip link del veth1 2> /dev/null - ip link del ipip11 2> /dev/null - ip link del ipip6tnl11 2> /dev/null - ip link del ip6ip6tnl11 2> /dev/null - ip link del gretap11 2> /dev/null - ip link del gre11 2> /dev/null - ip link del ip6gre11 2> /dev/null - ip link del ip6gretap11 2> /dev/null - ip link del geneve11 2> /dev/null - ip link del ip6geneve11 2> /dev/null - ip link del erspan11 2> /dev/null - ip link del ip6erspan11 2> /dev/null -} - -cleanup_exit() -{ - echo "CATCH SIGKILL or SIGINT, cleanup and exit" - cleanup - exit 0 -} - -check() -{ - ip link help 2>&1 | grep -q "\s$1\s" - if [ $? -ne 0 ];then - echo "SKIP $1: iproute2 not support" - cleanup - return 1 - fi -} - -enable_debug() -{ - echo 'file ip_gre.c +p' > /sys/kernel/debug/dynamic_debug/control - echo 'file ip6_gre.c +p' > /sys/kernel/debug/dynamic_debug/control - echo 'file geneve.c +p' > /sys/kernel/debug/dynamic_debug/control - echo 'file ipip.c +p' > /sys/kernel/debug/dynamic_debug/control -} - -check_err() -{ - if [ $ret -eq 0 ]; then - ret=$1 - fi -} - -bpf_tunnel_test() -{ - local errors=0 - - echo "Testing GRE tunnel..." - test_gre - errors=$(( $errors + $? )) - - echo "Testing GRE tunnel (without tunnel keys)..." - test_gre_no_tunnel_key - errors=$(( $errors + $? )) - - echo "Testing IP6GRE tunnel..." - test_ip6gre - errors=$(( $errors + $? )) - - echo "Testing IP6GRETAP tunnel..." - test_ip6gretap - errors=$(( $errors + $? )) - - echo "Testing ERSPAN tunnel..." - test_erspan v2 - errors=$(( $errors + $? )) - - echo "Testing IP6ERSPAN tunnel..." - test_ip6erspan v2 - errors=$(( $errors + $? )) - - echo "Testing GENEVE tunnel..." - test_geneve - errors=$(( $errors + $? )) - - echo "Testing IP6GENEVE tunnel..." - test_ip6geneve - errors=$(( $errors + $? )) - - echo "Testing IPIP tunnel..." - test_ipip - errors=$(( $errors + $? )) - - echo "Testing IPIP6 tunnel..." - test_ipip6 - errors=$(( $errors + $? )) - - echo "Testing IP6IP6 tunnel..." - test_ip6ip6 - errors=$(( $errors + $? )) - - return $errors -} - -trap cleanup 0 3 6 -trap cleanup_exit 2 9 - -cleanup -bpf_tunnel_test - -if [ $? -ne 0 ]; then - echo -e "$(basename $0): ${RED}FAIL${NC}" - exit 1 -fi -echo -e "$(basename $0): ${GREEN}PASS${NC}" -exit 0 diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh deleted file mode 100755 index 4c3c3fd..0000000 --- a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh +++ /dev/null @@ -1,214 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# Test topology: -# - - - - - - - - - - - - - - - - - - - -# | veth1 veth2 veth3 | ns0 -# - -| - - - - - - | - - - - - - | - - -# --------- --------- --------- -# | veth0 | | veth0 | | veth0 | -# --------- --------- --------- -# ns1 ns2 ns3 -# -# Test modules: -# XDP modes: generic, native, native + egress_prog -# -# Test cases: -# ARP: Testing BPF_F_BROADCAST, the ingress interface also should receive -# the redirects. -# ns1 -> gw: ns1, ns2, ns3, should receive the arp request -# IPv4: Testing BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, the ingress -# interface should not receive the redirects. -# ns1 -> gw: ns1 should not receive, ns2, ns3 should receive redirects. -# IPv6: Testing none flag, all the pkts should be redirected back -# ping test: ns1 -> ns2 (block), echo requests will be redirect back -# egress_prog: -# all src mac should be egress interface's mac - -# netns numbers -NUM=3 -IFACES="" -DRV_MODE="xdpgeneric xdpdrv xdpegress" -PASS=0 -FAIL=0 -LOG_DIR=$(mktemp -d) -declare -a NS -NS[0]="ns0-$(mktemp -u XXXXXX)" -NS[1]="ns1-$(mktemp -u XXXXXX)" -NS[2]="ns2-$(mktemp -u XXXXXX)" -NS[3]="ns3-$(mktemp -u XXXXXX)" - -test_pass() -{ - echo "Pass: $@" - PASS=$((PASS + 1)) -} - -test_fail() -{ - echo "fail: $@" - FAIL=$((FAIL + 1)) -} - -clean_up() -{ - for i in $(seq 0 $NUM); do - ip netns del ${NS[$i]} 2> /dev/null - done -} - -# Kselftest framework requirement - SKIP code is 4. -check_env() -{ - ip link set dev lo xdpgeneric off &>/dev/null - if [ $? -ne 0 ];then - echo "selftests: [SKIP] Could not run test without the ip xdpgeneric support" - exit 4 - fi - - which tcpdump &>/dev/null - if [ $? -ne 0 ];then - echo "selftests: [SKIP] Could not run test without tcpdump" - exit 4 - fi -} - -setup_ns() -{ - local mode=$1 - IFACES="" - - if [ "$mode" = "xdpegress" ]; then - mode="xdpdrv" - fi - - ip netns add ${NS[0]} - for i in $(seq $NUM); do - ip netns add ${NS[$i]} - ip -n ${NS[$i]} link add veth0 type veth peer name veth$i netns ${NS[0]} - ip -n ${NS[$i]} link set veth0 up - ip -n ${NS[0]} link set veth$i up - - ip -n ${NS[$i]} addr add 192.0.2.$i/24 dev veth0 - ip -n ${NS[$i]} addr add 2001:db8::$i/64 dev veth0 - # Add a neigh entry for IPv4 ping test - ip -n ${NS[$i]} neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0 - ip -n ${NS[$i]} link set veth0 $mode obj \ - xdp_dummy.bpf.o sec xdp &> /dev/null || \ - { test_fail "Unable to load dummy xdp" && exit 1; } - IFACES="$IFACES veth$i" - veth_mac[$i]=$(ip -n ${NS[0]} link show veth$i | awk '/link\/ether/ {print $2}') - done -} - -do_egress_tests() -{ - local mode=$1 - - # mac test - ip netns exec ${NS[2]} tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-2_${mode}.log & - ip netns exec ${NS[3]} tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-3_${mode}.log & - sleep 0.5 - ip netns exec ${NS[1]} ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null - sleep 0.5 - pkill tcpdump - - # mac check - grep -q "${veth_mac[2]} > ff:ff:ff:ff:ff:ff" ${LOG_DIR}/mac_ns1-2_${mode}.log && \ - test_pass "$mode mac ns1-2" || test_fail "$mode mac ns1-2" - grep -q "${veth_mac[3]} > ff:ff:ff:ff:ff:ff" ${LOG_DIR}/mac_ns1-3_${mode}.log && \ - test_pass "$mode mac ns1-3" || test_fail "$mode mac ns1-3" -} - -do_ping_tests() -{ - local mode=$1 - - # ping6 test: echo request should be redirect back to itself, not others - ip netns exec ${NS[1]} ip neigh add 2001:db8::2 dev veth0 lladdr 00:00:00:00:00:02 - - ip netns exec ${NS[1]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-1_${mode}.log & - ip netns exec ${NS[2]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-2_${mode}.log & - ip netns exec ${NS[3]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-3_${mode}.log & - sleep 0.5 - # ARP test - ip netns exec ${NS[1]} arping -q -c 2 -I veth0 192.0.2.254 - # IPv4 test - ip netns exec ${NS[1]} ping 192.0.2.253 -i 0.1 -c 4 &> /dev/null - # IPv6 test - ip netns exec ${NS[1]} ping6 2001:db8::2 -i 0.1 -c 2 &> /dev/null - sleep 0.5 - pkill tcpdump - - # All netns should receive the redirect arp requests - [ $(grep -cF "who-has 192.0.2.254" ${LOG_DIR}/ns1-1_${mode}.log) -eq 4 ] && \ - test_pass "$mode arp(F_BROADCAST) ns1-1" || \ - test_fail "$mode arp(F_BROADCAST) ns1-1" - [ $(grep -cF "who-has 192.0.2.254" ${LOG_DIR}/ns1-2_${mode}.log) -eq 2 ] && \ - test_pass "$mode arp(F_BROADCAST) ns1-2" || \ - test_fail "$mode arp(F_BROADCAST) ns1-2" - [ $(grep -cF "who-has 192.0.2.254" ${LOG_DIR}/ns1-3_${mode}.log) -eq 2 ] && \ - test_pass "$mode arp(F_BROADCAST) ns1-3" || \ - test_fail "$mode arp(F_BROADCAST) ns1-3" - - # ns1 should not receive the redirect echo request, others should - [ $(grep -c "ICMP echo request" ${LOG_DIR}/ns1-1_${mode}.log) -eq 4 ] && \ - test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1" || \ - test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1" - [ $(grep -c "ICMP echo request" ${LOG_DIR}/ns1-2_${mode}.log) -eq 4 ] && \ - test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2" || \ - test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2" - [ $(grep -c "ICMP echo request" ${LOG_DIR}/ns1-3_${mode}.log) -eq 4 ] && \ - test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3" || \ - test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3" - - # ns1 should receive the echo request, ns2 should not - [ $(grep -c "ICMP6, echo request" ${LOG_DIR}/ns1-1_${mode}.log) -eq 4 ] && \ - test_pass "$mode IPv6 (no flags) ns1-1" || \ - test_fail "$mode IPv6 (no flags) ns1-1" - [ $(grep -c "ICMP6, echo request" ${LOG_DIR}/ns1-2_${mode}.log) -eq 0 ] && \ - test_pass "$mode IPv6 (no flags) ns1-2" || \ - test_fail "$mode IPv6 (no flags) ns1-2" -} - -do_tests() -{ - local mode=$1 - local drv_p - - case ${mode} in - xdpdrv) drv_p="-N";; - xdpegress) drv_p="-X";; - xdpgeneric) drv_p="-S";; - esac - - ip netns exec ${NS[0]} ./xdp_redirect_multi $drv_p $IFACES &> ${LOG_DIR}/xdp_redirect_${mode}.log & - xdp_pid=$! - sleep 1 - if ! ps -p $xdp_pid > /dev/null; then - test_fail "$mode xdp_redirect_multi start failed" - return 1 - fi - - if [ "$mode" = "xdpegress" ]; then - do_egress_tests $mode - else - do_ping_tests $mode - fi - - kill $xdp_pid -} - -check_env - -trap clean_up EXIT - -for mode in ${DRV_MODE}; do - setup_ns $mode - do_tests $mode - clean_up -done -rm -rf ${LOG_DIR} - -echo "Summary: PASS $PASS, FAIL $FAIL" -[ $FAIL -eq 0 ] && exit 0 || exit 1 diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh deleted file mode 100755 index fbcaa9f..0000000 --- a/tools/testing/selftests/bpf/test_xdp_vlan.sh +++ /dev/null @@ -1,233 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# Author: Jesper Dangaard Brouer - -# Kselftest framework requirement - SKIP code is 4. -readonly KSFT_SKIP=4 -readonly NS1="ns1-$(mktemp -u XXXXXX)" -readonly NS2="ns2-$(mktemp -u XXXXXX)" - -# Allow wrapper scripts to name test -if [ -z "$TESTNAME" ]; then - TESTNAME=xdp_vlan -fi - -# Default XDP mode -XDP_MODE=xdpgeneric - -usage() { - echo "Testing XDP + TC eBPF VLAN manipulations: $TESTNAME" - echo "" - echo "Usage: $0 [-vfh]" - echo " -v | --verbose : Verbose" - echo " --flush : Flush before starting (e.g. after --interactive)" - echo " --interactive : Keep netns setup running after test-run" - echo " --mode=XXX : Choose XDP mode (xdp | xdpgeneric | xdpdrv)" - echo "" -} - -valid_xdp_mode() -{ - local mode=$1 - - case "$mode" in - xdpgeneric | xdpdrv | xdp) - return 0 - ;; - *) - return 1 - esac -} - -cleanup() -{ - local status=$? - - if [ "$status" = "0" ]; then - echo "selftests: $TESTNAME [PASS]"; - else - echo "selftests: $TESTNAME [FAILED]"; - fi - - if [ -n "$INTERACTIVE" ]; then - echo "Namespace setup still active explore with:" - echo " ip netns exec ${NS1} bash" - echo " ip netns exec ${NS2} bash" - exit $status - fi - - set +e - ip link del veth1 2> /dev/null - ip netns del ${NS1} 2> /dev/null - ip netns del ${NS2} 2> /dev/null -} - -# Using external program "getopt" to get --long-options -OPTIONS=$(getopt -o hvfi: \ - --long verbose,flush,help,interactive,debug,mode: -- "$@") -if (( $? != 0 )); then - usage - echo "selftests: $TESTNAME [FAILED] Error calling getopt, unknown option?" - exit 2 -fi -eval set -- "$OPTIONS" - -## --- Parse command line arguments / parameters --- -while true; do - case "$1" in - -v | --verbose) - export VERBOSE=yes - shift - ;; - -i | --interactive | --debug ) - INTERACTIVE=yes - shift - ;; - -f | --flush ) - cleanup - shift - ;; - --mode ) - shift - XDP_MODE=$1 - shift - ;; - -- ) - shift - break - ;; - -h | --help ) - usage; - echo "selftests: $TESTNAME [SKIP] usage help info requested" - exit $KSFT_SKIP - ;; - * ) - shift - break - ;; - esac -done - -if [ "$EUID" -ne 0 ]; then - echo "selftests: $TESTNAME [FAILED] need root privileges" - exit 1 -fi - -valid_xdp_mode $XDP_MODE -if [ $? -ne 0 ]; then - echo "selftests: $TESTNAME [FAILED] unknown XDP mode ($XDP_MODE)" - exit 1 -fi - -ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null -if [ $? -ne 0 ]; then - echo "selftests: $TESTNAME [SKIP] need ip xdp support" - exit $KSFT_SKIP -fi - -# Interactive mode likely require us to cleanup netns -if [ -n "$INTERACTIVE" ]; then - ip link del veth1 2> /dev/null - ip netns del ${NS1} 2> /dev/null - ip netns del ${NS2} 2> /dev/null -fi - -# Exit on failure -set -e - -# Some shell-tools dependencies -which ip > /dev/null -which tc > /dev/null -which ethtool > /dev/null - -# Make rest of shell verbose, showing comments as doc/info -if [ -n "$VERBOSE" ]; then - set -v -fi - -# Create two namespaces -ip netns add ${NS1} -ip netns add ${NS2} - -# Run cleanup if failing or on kill -trap cleanup 0 2 3 6 9 - -# Create veth pair -ip link add veth1 type veth peer name veth2 - -# Move veth1 and veth2 into the respective namespaces -ip link set veth1 netns ${NS1} -ip link set veth2 netns ${NS2} - -# NOTICE: XDP require VLAN header inside packet payload -# - Thus, disable VLAN offloading driver features -# - For veth REMEMBER TX side VLAN-offload -# -# Disable rx-vlan-offload (mostly needed on ns1) -ip netns exec ${NS1} ethtool -K veth1 rxvlan off -ip netns exec ${NS2} ethtool -K veth2 rxvlan off -# -# Disable tx-vlan-offload (mostly needed on ns2) -ip netns exec ${NS2} ethtool -K veth2 txvlan off -ip netns exec ${NS1} ethtool -K veth1 txvlan off - -export IPADDR1=100.64.41.1 -export IPADDR2=100.64.41.2 - -# In ns1/veth1 add IP-addr on plain net_device -ip netns exec ${NS1} ip addr add ${IPADDR1}/24 dev veth1 -ip netns exec ${NS1} ip link set veth1 up - -# In ns2/veth2 create VLAN device -export VLAN=4011 -export DEVNS2=veth2 -ip netns exec ${NS2} ip link add link $DEVNS2 name $DEVNS2.$VLAN type vlan id $VLAN -ip netns exec ${NS2} ip addr add ${IPADDR2}/24 dev $DEVNS2.$VLAN -ip netns exec ${NS2} ip link set $DEVNS2 up -ip netns exec ${NS2} ip link set $DEVNS2.$VLAN up - -# Bringup lo in netns (to avoids confusing people using --interactive) -ip netns exec ${NS1} ip link set lo up -ip netns exec ${NS2} ip link set lo up - -# At this point, the hosts cannot reach each-other, -# because ns2 are using VLAN tags on the packets. - -ip netns exec ${NS2} sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Success: First ping must fail"' - - -# Now we can use the test_xdp_vlan.c program to pop/push these VLAN tags -# ---------------------------------------------------------------------- -# In ns1: ingress use XDP to remove VLAN tags -export DEVNS1=veth1 -export BPF_FILE=test_xdp_vlan.bpf.o - -# First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change" -export XDP_PROG=xdp_vlan_change -ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE object $BPF_FILE section $XDP_PROG - -# In ns1: egress use TC to add back VLAN tag 4011 -# (del cmd) -# tc qdisc del dev $DEVNS1 clsact 2> /dev/null -# -ip netns exec ${NS1} tc qdisc add dev $DEVNS1 clsact -ip netns exec ${NS1} tc filter add dev $DEVNS1 egress \ - prio 1 handle 1 bpf da obj $BPF_FILE sec tc_vlan_push - -# Now the namespaces can reach each-other, test with ping: -ip netns exec ${NS2} ping -i 0.2 -W 2 -c 2 $IPADDR1 -ip netns exec ${NS1} ping -i 0.2 -W 2 -c 2 $IPADDR2 - -# Second test: Replace xdp prog, that fully remove vlan header -# -# Catch kernel bug for generic-XDP, that does didn't allow us to -# remove a VLAN header, because skb->protocol still contain VLAN -# ETH_P_8021Q indication, and this cause overwriting of our changes. -# -export XDP_PROG=xdp_vlan_remove_outer2 -ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE off -ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE object $BPF_FILE section $XDP_PROG - -# Now the namespaces should still be able reach each-other, test with ping: -ip netns exec ${NS2} ping -i 0.2 -W 2 -c 2 $IPADDR1 -ip netns exec ${NS1} ping -i 0.2 -W 2 -c 2 $IPADDR2 diff --git a/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh b/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh deleted file mode 100755 index c515326..0000000 --- a/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh +++ /dev/null @@ -1,9 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -# Exit on failure -set -e - -# Wrapper script to test generic-XDP -export TESTNAME=xdp_vlan_mode_generic -./test_xdp_vlan.sh --mode=xdpgeneric diff --git a/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh b/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh deleted file mode 100755 index 5cf7ce1..0000000 --- a/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh +++ /dev/null @@ -1,9 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -# Exit on failure -set -e - -# Wrapper script to test native-XDP -export TESTNAME=xdp_vlan_mode_native -./test_xdp_vlan.sh --mode=xdpdrv diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index 06af502..a18972f 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -3,6 +3,7 @@ #define _GNU_SOURCE #include #include +#include #include #include #include @@ -154,6 +155,16 @@ struct filter { bool abs; }; +struct var_preset { + char *name; + enum { INTEGRAL, ENUMERATOR } type; + union { + long long ivalue; + char *svalue; + }; + bool applied; +}; + static struct env { char **filenames; int filename_cnt; @@ -195,6 +206,8 @@ static struct env { int progs_processed; int progs_skipped; int top_src_lines; + struct var_preset *presets; + int npresets; } env; static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args) @@ -246,16 +259,20 @@ static const struct argp_option opts[] = { { "test-reg-invariants", 'r', NULL, 0, "Force BPF verifier failure on register invariant violation (BPF_F_TEST_REG_INVARIANTS program flag)" }, { "top-src-lines", 'S', "N", 0, "Emit N most frequent source code lines" }, + { "set-global-vars", 'G', "GLOBAL", 0, "Set global variables provided in the expression, for example \"var1 = 1\"" }, {}, }; static int parse_stats(const char *stats_str, struct stat_specs *specs); static int append_filter(struct filter **filters, int *cnt, const char *str); static int append_filter_file(const char *path); +static int append_var_preset(struct var_preset **presets, int *cnt, const char *expr); +static int append_var_preset_file(const char *filename); +static int append_file(const char *path); +static int append_file_from_file(const char *path); static error_t parse_arg(int key, char *arg, struct argp_state *state) { - void *tmp; int err; switch (key) { @@ -353,15 +370,26 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) argp_usage(state); } break; + case 'G': { + if (arg[0] == '@') + err = append_var_preset_file(arg + 1); + else + err = append_var_preset(&env.presets, &env.npresets, arg); + if (err) { + fprintf(stderr, "Failed to parse global variable presets: %s\n", arg); + return err; + } + break; + } case ARGP_KEY_ARG: - tmp = realloc(env.filenames, (env.filename_cnt + 1) * sizeof(*env.filenames)); - if (!tmp) - return -ENOMEM; - env.filenames = tmp; - env.filenames[env.filename_cnt] = strdup(arg); - if (!env.filenames[env.filename_cnt]) - return -ENOMEM; - env.filename_cnt++; + if (arg[0] == '@') + err = append_file_from_file(arg + 1); + else + err = append_file(arg); + if (err) { + fprintf(stderr, "Failed to collect BPF object files: %d\n", err); + return err; + } break; default: return ARGP_ERR_UNKNOWN; @@ -632,7 +660,7 @@ static int append_filter_file(const char *path) f = fopen(path, "r"); if (!f) { err = -errno; - fprintf(stderr, "Failed to open filters in '%s': %d\n", path, err); + fprintf(stderr, "Failed to open filters in '%s': %s\n", path, strerror(-err)); return err; } @@ -662,6 +690,49 @@ static const struct stat_specs default_output_spec = { }, }; +static int append_file(const char *path) +{ + void *tmp; + + tmp = realloc(env.filenames, (env.filename_cnt + 1) * sizeof(*env.filenames)); + if (!tmp) + return -ENOMEM; + env.filenames = tmp; + env.filenames[env.filename_cnt] = strdup(path); + if (!env.filenames[env.filename_cnt]) + return -ENOMEM; + env.filename_cnt++; + return 0; +} + +static int append_file_from_file(const char *path) +{ + char buf[1024]; + int err = 0; + FILE *f; + + f = fopen(path, "r"); + if (!f) { + err = -errno; + fprintf(stderr, "Failed to open object files list in '%s': %s\n", + path, strerror(errno)); + return err; + } + + while (fscanf(f, " %1023[^\n]\n", buf) == 1) { + /* lines starting with # are comments, skip them */ + if (buf[0] == '\0' || buf[0] == '#') + continue; + err = append_file(buf); + if (err) + goto cleanup; + } + +cleanup: + fclose(f); + return err; +} + static const struct stat_specs default_csv_output_spec = { .spec_cnt = 14, .ids = { @@ -1163,13 +1234,13 @@ static void fixup_obj(struct bpf_object *obj, struct bpf_program *prog, const ch bpf_program__set_expected_attach_type(prog, attach_type); if (!env.quiet) { - printf("Using guessed program type '%s' for %s/%s...\n", + fprintf(stderr, "Using guessed program type '%s' for %s/%s...\n", libbpf_bpf_prog_type_str(prog_type), filename, prog_name); } } else { if (!env.quiet) { - printf("Failed to guess program type for freplace program with context type name '%s' for %s/%s. Consider using canonical type names to help veristat...\n", + fprintf(stderr, "Failed to guess program type for freplace program with context type name '%s' for %s/%s. Consider using canonical type names to help veristat...\n", ctx_name, filename, prog_name); } } @@ -1292,6 +1363,261 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf return 0; }; +static int append_var_preset(struct var_preset **presets, int *cnt, const char *expr) +{ + void *tmp; + struct var_preset *cur; + char var[256], val[256], *val_end; + long long value; + int n; + + tmp = realloc(*presets, (*cnt + 1) * sizeof(**presets)); + if (!tmp) + return -ENOMEM; + *presets = tmp; + cur = &(*presets)[*cnt]; + memset(cur, 0, sizeof(*cur)); + (*cnt)++; + + if (sscanf(expr, "%s = %s %n", var, val, &n) != 2 || n != strlen(expr)) { + fprintf(stderr, "Failed to parse expression '%s'\n", expr); + return -EINVAL; + } + + if (val[0] == '-' || isdigit(val[0])) { + /* must be a number */ + errno = 0; + value = strtoll(val, &val_end, 0); + if (errno == ERANGE) { + errno = 0; + value = strtoull(val, &val_end, 0); + } + if (errno || *val_end != '\0') { + fprintf(stderr, "Failed to parse value '%s'\n", val); + return -EINVAL; + } + cur->ivalue = value; + cur->type = INTEGRAL; + } else { + /* if not a number, consider it enum value */ + cur->svalue = strdup(val); + if (!cur->svalue) + return -ENOMEM; + cur->type = ENUMERATOR; + } + + cur->name = strdup(var); + if (!cur->name) + return -ENOMEM; + + return 0; +} + +static int append_var_preset_file(const char *filename) +{ + char buf[1024]; + FILE *f; + int err = 0; + + f = fopen(filename, "rt"); + if (!f) { + err = -errno; + fprintf(stderr, "Failed to open presets in '%s': %s\n", filename, strerror(-err)); + return -EINVAL; + } + + while (fscanf(f, " %1023[^\n]\n", buf) == 1) { + if (buf[0] == '\0' || buf[0] == '#') + continue; + + err = append_var_preset(&env.presets, &env.npresets, buf); + if (err) + goto cleanup; + } + +cleanup: + fclose(f); + return err; +} + +static bool is_signed_type(const struct btf_type *t) +{ + if (btf_is_int(t)) + return btf_int_encoding(t) & BTF_INT_SIGNED; + if (btf_is_any_enum(t)) + return btf_kflag(t); + return true; +} + +static int enum_value_from_name(const struct btf *btf, const struct btf_type *t, + const char *evalue, long long *retval) +{ + if (btf_is_enum(t)) { + struct btf_enum *e = btf_enum(t); + int i, n = btf_vlen(t); + + for (i = 0; i < n; ++i, ++e) { + const char *cur_name = btf__name_by_offset(btf, e->name_off); + + if (strcmp(cur_name, evalue) == 0) { + *retval = e->val; + return 0; + } + } + } else if (btf_is_enum64(t)) { + struct btf_enum64 *e = btf_enum64(t); + int i, n = btf_vlen(t); + + for (i = 0; i < n; ++i, ++e) { + const char *cur_name = btf__name_by_offset(btf, e->name_off); + __u64 value = btf_enum64_value(e); + + if (strcmp(cur_name, evalue) == 0) { + *retval = value; + return 0; + } + } + } + return -EINVAL; +} + +static bool is_preset_supported(const struct btf_type *t) +{ + return btf_is_int(t) || btf_is_enum(t) || btf_is_enum64(t); +} + +static int set_global_var(struct bpf_object *obj, struct btf *btf, const struct btf_type *t, + struct bpf_map *map, struct btf_var_secinfo *sinfo, + struct var_preset *preset) +{ + const struct btf_type *base_type; + void *ptr; + long long value = preset->ivalue; + size_t size; + + base_type = btf__type_by_id(btf, btf__resolve_type(btf, t->type)); + if (!base_type) { + fprintf(stderr, "Failed to resolve type %d\n", t->type); + return -EINVAL; + } + if (!is_preset_supported(base_type)) { + fprintf(stderr, "Setting value for type %s is not supported\n", + btf__name_by_offset(btf, base_type->name_off)); + return -EINVAL; + } + + if (preset->type == ENUMERATOR) { + if (btf_is_any_enum(base_type)) { + if (enum_value_from_name(btf, base_type, preset->svalue, &value)) { + fprintf(stderr, + "Failed to find integer value for enum element %s\n", + preset->svalue); + return -EINVAL; + } + } else { + fprintf(stderr, "Value %s is not supported for type %s\n", + preset->svalue, btf__name_by_offset(btf, base_type->name_off)); + return -EINVAL; + } + } + + /* Check if value fits into the target variable size */ + if (sinfo->size < sizeof(value)) { + bool is_signed = is_signed_type(base_type); + __u32 unsigned_bits = sinfo->size * 8 - (is_signed ? 1 : 0); + long long max_val = 1ll << unsigned_bits; + + if (value >= max_val || value < -max_val) { + fprintf(stderr, + "Variable %s value %lld is out of range [%lld; %lld]\n", + btf__name_by_offset(btf, t->name_off), value, + is_signed ? -max_val : 0, max_val - 1); + return -EINVAL; + } + } + + ptr = bpf_map__initial_value(map, &size); + if (!ptr || sinfo->offset + sinfo->size > size) + return -EINVAL; + + if (__BYTE_ORDER == __LITTLE_ENDIAN) { + memcpy(ptr + sinfo->offset, &value, sinfo->size); + } else { /* __BYTE_ORDER == __BIG_ENDIAN */ + __u8 src_offset = sizeof(value) - sinfo->size; + + memcpy(ptr + sinfo->offset, (void *)&value + src_offset, sinfo->size); + } + return 0; +} + +static int set_global_vars(struct bpf_object *obj, struct var_preset *presets, int npresets) +{ + struct btf_var_secinfo *sinfo; + const char *sec_name; + const struct btf_type *t; + struct bpf_map *map; + struct btf *btf; + int i, j, k, n, cnt, err = 0; + + if (npresets == 0) + return 0; + + btf = bpf_object__btf(obj); + if (!btf) + return -EINVAL; + + cnt = btf__type_cnt(btf); + for (i = 1; i != cnt; ++i) { + t = btf__type_by_id(btf, i); + + if (!btf_is_datasec(t)) + continue; + + sinfo = btf_var_secinfos(t); + sec_name = btf__name_by_offset(btf, t->name_off); + map = bpf_object__find_map_by_name(obj, sec_name); + if (!map) + continue; + + n = btf_vlen(t); + for (j = 0; j < n; ++j, ++sinfo) { + const struct btf_type *var_type = btf__type_by_id(btf, sinfo->type); + const char *var_name; + + if (!btf_is_var(var_type)) + continue; + + var_name = btf__name_by_offset(btf, var_type->name_off); + + for (k = 0; k < npresets; ++k) { + if (strcmp(var_name, presets[k].name) != 0) + continue; + + if (presets[k].applied) { + fprintf(stderr, "Variable %s is set more than once", + var_name); + return -EINVAL; + } + + err = set_global_var(obj, btf, var_type, map, sinfo, presets + k); + if (err) + return err; + + presets[k].applied = true; + break; + } + } + } + for (i = 0; i < npresets; ++i) { + if (!presets[i].applied) { + fprintf(stderr, "Global variable preset %s has not been applied\n", + presets[i].name); + } + presets[i].applied = false; + } + return err; +} + static int process_obj(const char *filename) { const char *base_filename = basename(strdupa(filename)); @@ -1341,6 +1667,11 @@ static int process_obj(const char *filename) if (prog_cnt == 1) { prog = bpf_object__next_program(obj, NULL); bpf_program__set_autoload(prog, true); + err = set_global_vars(obj, env.presets, env.npresets); + if (err) { + fprintf(stderr, "Failed to set global variables %d\n", err); + goto cleanup; + } process_prog(filename, obj, prog); goto cleanup; } @@ -1355,6 +1686,12 @@ static int process_obj(const char *filename) goto cleanup; } + err = set_global_vars(tobj, env.presets, env.npresets); + if (err) { + fprintf(stderr, "Failed to set global variables %d\n", err); + goto cleanup; + } + lprog = NULL; bpf_object__for_each_program(tprog, tobj) { const char *tprog_name = bpf_program__name(tprog); @@ -2460,5 +2797,11 @@ int main(int argc, char **argv) free(env.deny_filters[i].prog_glob); } free(env.deny_filters); + for (i = 0; i < env.npresets; ++i) { + free(env.presets[i].name); + if (env.presets[i].type == ENUMERATOR) + free(env.presets[i].svalue); + } + free(env.presets); return -err; } diff --git a/tools/testing/selftests/bpf/with_addr.sh b/tools/testing/selftests/bpf/with_addr.sh deleted file mode 100755 index ffcd395..0000000 --- a/tools/testing/selftests/bpf/with_addr.sh +++ /dev/null @@ -1,54 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# add private ipv4 and ipv6 addresses to loopback - -readonly V6_INNER='100::a/128' -readonly V4_INNER='192.168.0.1/32' - -if getopts ":s" opt; then - readonly SIT_DEV_NAME='sixtofourtest0' - readonly V6_SIT='2::/64' - readonly V4_SIT='172.17.0.1/32' - shift -fi - -fail() { - echo "error: $*" 1>&2 - exit 1 -} - -setup() { - ip -6 addr add "${V6_INNER}" dev lo || fail 'failed to setup v6 address' - ip -4 addr add "${V4_INNER}" dev lo || fail 'failed to setup v4 address' - - if [[ -n "${V6_SIT}" ]]; then - ip link add "${SIT_DEV_NAME}" type sit remote any local any \ - || fail 'failed to add sit' - ip link set dev "${SIT_DEV_NAME}" up \ - || fail 'failed to bring sit device up' - ip -6 addr add "${V6_SIT}" dev "${SIT_DEV_NAME}" \ - || fail 'failed to setup v6 SIT address' - ip -4 addr add "${V4_SIT}" dev "${SIT_DEV_NAME}" \ - || fail 'failed to setup v4 SIT address' - fi - - sleep 2 # avoid race causing bind to fail -} - -cleanup() { - if [[ -n "${V6_SIT}" ]]; then - ip -4 addr del "${V4_SIT}" dev "${SIT_DEV_NAME}" - ip -6 addr del "${V6_SIT}" dev "${SIT_DEV_NAME}" - ip link del "${SIT_DEV_NAME}" - fi - - ip -4 addr del "${V4_INNER}" dev lo - ip -6 addr del "${V6_INNER}" dev lo -} - -trap cleanup EXIT - -setup -"$@" -exit "$?" diff --git a/tools/testing/selftests/bpf/with_tunnels.sh b/tools/testing/selftests/bpf/with_tunnels.sh deleted file mode 100755 index e24949e..0000000 --- a/tools/testing/selftests/bpf/with_tunnels.sh +++ /dev/null @@ -1,36 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# setup tunnels for flow dissection test - -readonly SUFFIX="test_$(mktemp -u XXXX)" -CONFIG="remote 127.0.0.2 local 127.0.0.1 dev lo" - -setup() { - ip link add "ipip_${SUFFIX}" type ipip ${CONFIG} - ip link add "gre_${SUFFIX}" type gre ${CONFIG} - ip link add "sit_${SUFFIX}" type sit ${CONFIG} - - echo "tunnels before test:" - ip tunnel show - - ip link set "ipip_${SUFFIX}" up - ip link set "gre_${SUFFIX}" up - ip link set "sit_${SUFFIX}" up -} - - -cleanup() { - ip tunnel del "ipip_${SUFFIX}" - ip tunnel del "gre_${SUFFIX}" - ip tunnel del "sit_${SUFFIX}" - - echo "tunnels after test:" - ip tunnel show -} - -trap cleanup EXIT - -setup -"$@" -exit "$?" diff --git a/tools/testing/selftests/bpf/xdp_redirect_multi.c b/tools/testing/selftests/bpf/xdp_redirect_multi.c deleted file mode 100644 index c1fc44c..0000000 --- a/tools/testing/selftests/bpf/xdp_redirect_multi.c +++ /dev/null @@ -1,226 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "bpf_util.h" -#include -#include - -#define MAX_IFACE_NUM 32 -#define MAX_INDEX_NUM 1024 - -static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; -static int ifaces[MAX_IFACE_NUM] = {}; - -static void int_exit(int sig) -{ - __u32 prog_id = 0; - int i; - - for (i = 0; ifaces[i] > 0; i++) { - if (bpf_xdp_query_id(ifaces[i], xdp_flags, &prog_id)) { - printf("bpf_xdp_query_id failed\n"); - exit(1); - } - if (prog_id) - bpf_xdp_detach(ifaces[i], xdp_flags, NULL); - } - - exit(0); -} - -static int get_mac_addr(unsigned int ifindex, void *mac_addr) -{ - char ifname[IF_NAMESIZE]; - struct ifreq ifr; - int fd, ret = -1; - - fd = socket(AF_INET, SOCK_DGRAM, 0); - if (fd < 0) - return ret; - - if (!if_indextoname(ifindex, ifname)) - goto err_out; - - strcpy(ifr.ifr_name, ifname); - - if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0) - goto err_out; - - memcpy(mac_addr, ifr.ifr_hwaddr.sa_data, 6 * sizeof(char)); - ret = 0; - -err_out: - close(fd); - return ret; -} - -static void usage(const char *prog) -{ - fprintf(stderr, - "usage: %s [OPTS] ...\n" - "OPTS:\n" - " -S use skb-mode\n" - " -N enforce native mode\n" - " -F force loading prog\n" - " -X load xdp program on egress\n", - prog); -} - -int main(int argc, char **argv) -{ - int prog_fd, group_all, mac_map; - struct bpf_program *ingress_prog, *egress_prog; - int i, err, ret, opt, egress_prog_fd = 0; - struct bpf_devmap_val devmap_val; - bool attach_egress_prog = false; - unsigned char mac_addr[6]; - char ifname[IF_NAMESIZE]; - struct bpf_object *obj; - unsigned int ifindex; - char filename[256]; - - while ((opt = getopt(argc, argv, "SNFX")) != -1) { - switch (opt) { - case 'S': - xdp_flags |= XDP_FLAGS_SKB_MODE; - break; - case 'N': - /* default, set below */ - break; - case 'F': - xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; - break; - case 'X': - attach_egress_prog = true; - break; - default: - usage(basename(argv[0])); - return 1; - } - } - - if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) { - xdp_flags |= XDP_FLAGS_DRV_MODE; - } else if (attach_egress_prog) { - printf("Load xdp program on egress with SKB mode not supported yet\n"); - goto err_out; - } - - if (optind == argc) { - printf("usage: %s ...\n", argv[0]); - goto err_out; - } - - printf("Get interfaces:"); - for (i = 0; i < MAX_IFACE_NUM && argv[optind + i]; i++) { - ifaces[i] = if_nametoindex(argv[optind + i]); - if (!ifaces[i]) - ifaces[i] = strtoul(argv[optind + i], NULL, 0); - if (!if_indextoname(ifaces[i], ifname)) { - perror("Invalid interface name or i"); - goto err_out; - } - if (ifaces[i] > MAX_INDEX_NUM) { - printf(" interface index too large\n"); - goto err_out; - } - printf(" %d", ifaces[i]); - } - printf("\n"); - - snprintf(filename, sizeof(filename), "%s_kern.bpf.o", argv[0]); - obj = bpf_object__open_file(filename, NULL); - err = libbpf_get_error(obj); - if (err) - goto err_out; - err = bpf_object__load(obj); - if (err) - goto err_out; - prog_fd = bpf_program__fd(bpf_object__next_program(obj, NULL)); - - if (attach_egress_prog) - group_all = bpf_object__find_map_fd_by_name(obj, "map_egress"); - else - group_all = bpf_object__find_map_fd_by_name(obj, "map_all"); - mac_map = bpf_object__find_map_fd_by_name(obj, "mac_map"); - - if (group_all < 0 || mac_map < 0) { - printf("bpf_object__find_map_fd_by_name failed\n"); - goto err_out; - } - - if (attach_egress_prog) { - /* Find ingress/egress prog for 2nd xdp prog */ - ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_all_prog"); - egress_prog = bpf_object__find_program_by_name(obj, "xdp_devmap_prog"); - if (!ingress_prog || !egress_prog) { - printf("finding ingress/egress_prog in obj file failed\n"); - goto err_out; - } - prog_fd = bpf_program__fd(ingress_prog); - egress_prog_fd = bpf_program__fd(egress_prog); - if (prog_fd < 0 || egress_prog_fd < 0) { - printf("find egress_prog fd failed\n"); - goto err_out; - } - } - - signal(SIGINT, int_exit); - signal(SIGTERM, int_exit); - - /* Init forward multicast groups and exclude group */ - for (i = 0; ifaces[i] > 0; i++) { - ifindex = ifaces[i]; - - if (attach_egress_prog) { - ret = get_mac_addr(ifindex, mac_addr); - if (ret < 0) { - printf("get interface %d mac failed\n", ifindex); - goto err_out; - } - ret = bpf_map_update_elem(mac_map, &ifindex, mac_addr, 0); - if (ret) { - perror("bpf_update_elem mac_map failed\n"); - goto err_out; - } - } - - /* Add all the interfaces to group all */ - devmap_val.ifindex = ifindex; - devmap_val.bpf_prog.fd = egress_prog_fd; - ret = bpf_map_update_elem(group_all, &ifindex, &devmap_val, 0); - if (ret) { - perror("bpf_map_update_elem"); - goto err_out; - } - - /* bind prog_fd to each interface */ - ret = bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL); - if (ret) { - printf("Set xdp fd failed on %d\n", ifindex); - goto err_out; - } - } - - /* sleep some time for testing */ - sleep(999); - - return 0; - -err_out: - return 1; -}