diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index c199990e12b6..4425189bb24c 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -1824,7 +1824,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) /* If BPF JIT was not enabled then we must fall back to * the interpreter. */ - if (!bpf_jit_enable) + if (!prog->jit_requested) return orig_prog; /* If constant blinding was enabled and we failed during blinding diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index ba38d403abb2..396490cf7316 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -99,6 +99,20 @@ static inline void emit_a64_mov_i64(const int reg, const u64 val, } } +static inline void emit_addr_mov_i64(const int reg, const u64 val, + struct jit_ctx *ctx) +{ + u64 tmp = val; + int shift = 0; + + emit(A64_MOVZ(1, reg, tmp & 0xffff, shift), ctx); + for (;shift < 48;) { + tmp >>= 16; + shift += 16; + emit(A64_MOVK(1, reg, tmp & 0xffff, shift), ctx); + } +} + static inline void emit_a64_mov_i(const int is64, const int reg, const s32 val, struct jit_ctx *ctx) { @@ -603,7 +617,10 @@ emit_cond_jmp: const u8 r0 = bpf2a64[BPF_REG_0]; const u64 func = (u64)__bpf_call_base + imm; - emit_a64_mov_i64(tmp, func, ctx); + if (ctx->prog->is_func) + emit_addr_mov_i64(tmp, func, ctx); + else + emit_a64_mov_i64(tmp, func, ctx); emit(A64_BLR(tmp), ctx); emit(A64_MOV(1, r0, A64_R(0)), ctx); break; @@ -835,16 +852,24 @@ static inline void bpf_flush_icache(void *start, void *end) flush_icache_range((unsigned long)start, (unsigned long)end); } +struct arm64_jit_data { + struct bpf_binary_header *header; + u8 *image; + struct jit_ctx ctx; +}; + struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { struct bpf_prog *tmp, *orig_prog = prog; struct bpf_binary_header *header; + struct arm64_jit_data *jit_data; bool tmp_blinded = false; + bool extra_pass = false; struct jit_ctx ctx; int image_size; u8 *image_ptr; - if (!bpf_jit_enable) + if (!prog->jit_requested) return orig_prog; tmp = bpf_jit_blind_constants(prog); @@ -858,13 +883,29 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) prog = tmp; } + jit_data = prog->aux->jit_data; + if (!jit_data) { + jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL); + if (!jit_data) { + prog = orig_prog; + goto out; + } + prog->aux->jit_data = jit_data; + } + if (jit_data->ctx.offset) { + ctx = jit_data->ctx; + image_ptr = jit_data->image; + header = jit_data->header; + extra_pass = true; + goto skip_init_ctx; + } memset(&ctx, 0, sizeof(ctx)); ctx.prog = prog; ctx.offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL); if (ctx.offset == NULL) { prog = orig_prog; - goto out; + goto out_off; } /* 1. Initial fake pass to compute ctx->idx. */ @@ -895,6 +936,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) /* 2. Now, the actual pass. */ ctx.image = (__le32 *)image_ptr; +skip_init_ctx: ctx.idx = 0; build_prologue(&ctx); @@ -920,13 +962,31 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) bpf_flush_icache(header, ctx.image + ctx.idx); - bpf_jit_binary_lock_ro(header); + if (!prog->is_func || extra_pass) { + if (extra_pass && ctx.idx != jit_data->ctx.idx) { + pr_err_once("multi-func JIT bug %d != %d\n", + ctx.idx, jit_data->ctx.idx); + bpf_jit_binary_free(header); + prog->bpf_func = NULL; + prog->jited = 0; + goto out_off; + } + bpf_jit_binary_lock_ro(header); + } else { + jit_data->ctx = ctx; + jit_data->image = image_ptr; + jit_data->header = header; + } prog->bpf_func = (void *)ctx.image; prog->jited = 1; prog->jited_len = image_size; + if (!prog->is_func || extra_pass) { out_off: - kfree(ctx.offset); + kfree(ctx.offset); + kfree(jit_data); + prog->aux->jit_data = NULL; + } out: if (tmp_blinded) bpf_jit_prog_release_other(prog, prog == orig_prog ? diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index 962b0259b4b6..97069a1b6f43 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -1869,7 +1869,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) unsigned int image_size; u8 *image_ptr; - if (!bpf_jit_enable || !cpu_has_mips64r2) + if (!prog->jit_requested || !cpu_has_mips64r2) return prog; tmp = bpf_jit_blind_constants(prog); diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 46d74e81aff1..d5a5bc43cf8f 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -993,7 +993,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) struct bpf_prog *tmp_fp; bool bpf_blinded = false; - if (!bpf_jit_enable) + if (!fp->jit_requested) return org_fp; tmp_fp = bpf_jit_blind_constants(org_fp); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index e81c16838b90..f4baa8c514d3 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1300,7 +1300,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) struct bpf_jit jit; int pass; - if (!bpf_jit_enable) + if (!fp->jit_requested) return orig_fp; tmp = bpf_jit_blind_constants(fp); diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index 5765e7e711f7..a2f1b5e774a7 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -1517,7 +1517,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) u8 *image_ptr; int pass; - if (!bpf_jit_enable) + if (!prog->jit_requested) return orig_prog; tmp = bpf_jit_blind_constants(prog); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 0554e8aef4d5..87f214fbe66e 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1109,19 +1109,29 @@ common_load: return proglen; } +struct x64_jit_data { + struct bpf_binary_header *header; + int *addrs; + u8 *image; + int proglen; + struct jit_context ctx; +}; + struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { struct bpf_binary_header *header = NULL; struct bpf_prog *tmp, *orig_prog = prog; + struct x64_jit_data *jit_data; int proglen, oldproglen = 0; struct jit_context ctx = {}; bool tmp_blinded = false; + bool extra_pass = false; u8 *image = NULL; int *addrs; int pass; int i; - if (!bpf_jit_enable) + if (!prog->jit_requested) return orig_prog; tmp = bpf_jit_blind_constants(prog); @@ -1135,10 +1145,28 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) prog = tmp; } + jit_data = prog->aux->jit_data; + if (!jit_data) { + jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL); + if (!jit_data) { + prog = orig_prog; + goto out; + } + prog->aux->jit_data = jit_data; + } + addrs = jit_data->addrs; + if (addrs) { + ctx = jit_data->ctx; + oldproglen = jit_data->proglen; + image = jit_data->image; + header = jit_data->header; + extra_pass = true; + goto skip_init_addrs; + } addrs = kmalloc(prog->len * sizeof(*addrs), GFP_KERNEL); if (!addrs) { prog = orig_prog; - goto out; + goto out_addrs; } /* Before first pass, make a rough estimation of addrs[] @@ -1149,6 +1177,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) addrs[i] = proglen; } ctx.cleanup_addr = proglen; +skip_init_addrs: /* JITed image shrinks with every pass and the loop iterates * until the image stops shrinking. Very large bpf programs @@ -1189,7 +1218,15 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) if (image) { bpf_flush_icache(header, image + proglen); - bpf_jit_binary_lock_ro(header); + if (!prog->is_func || extra_pass) { + bpf_jit_binary_lock_ro(header); + } else { + jit_data->addrs = addrs; + jit_data->ctx = ctx; + jit_data->proglen = proglen; + jit_data->image = image; + jit_data->header = header; + } prog->bpf_func = (void *)image; prog->jited = 1; prog->jited_len = proglen; @@ -1197,8 +1234,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) prog = orig_prog; } + if (!prog->is_func || extra_pass) { out_addrs: - kfree(addrs); + kfree(addrs); + kfree(jit_data); + prog->aux->jit_data = NULL; + } out: if (tmp_blinded) bpf_jit_prog_release_other(prog, prog == orig_prog ? diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 54dc7cae2949..da54ef644fcd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -200,6 +200,9 @@ struct bpf_prog_aux { u32 max_ctx_offset; u32 stack_depth; u32 id; + u32 func_cnt; + struct bpf_prog **func; + void *jit_data; /* JIT specific data. arch dependent */ struct latch_tree_node ksym_tnode; struct list_head ksym_lnode; const struct bpf_prog_ops *ops; @@ -402,6 +405,7 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); +void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); /* Map specifics */ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c561b986bab0..aaac589e490c 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -76,6 +76,14 @@ struct bpf_reg_state { s64 smax_value; /* maximum possible (s64)value */ u64 umin_value; /* minimum possible (u64)value */ u64 umax_value; /* maximum possible (u64)value */ + /* Inside the callee two registers can be both PTR_TO_STACK like + * R1=fp-8 and R2=fp-8, but one of them points to this function stack + * while another to the caller's stack. To differentiate them 'frameno' + * is used which is an index in bpf_verifier_state->frame[] array + * pointing to bpf_func_state. + * This field must be second to last, for states_equal() reasons. + */ + u32 frameno; /* This field must be last, for states_equal() reasons. */ enum bpf_reg_liveness live; }; @@ -83,7 +91,8 @@ struct bpf_reg_state { enum bpf_stack_slot_type { STACK_INVALID, /* nothing was stored in this stack slot */ STACK_SPILL, /* register spilled into stack */ - STACK_MISC /* BPF program wrote some data into this slot */ + STACK_MISC, /* BPF program wrote some data into this slot */ + STACK_ZERO, /* BPF program wrote constant zero */ }; #define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ @@ -96,13 +105,34 @@ struct bpf_stack_state { /* state of the program: * type of all registers and stack info */ -struct bpf_verifier_state { +struct bpf_func_state { struct bpf_reg_state regs[MAX_BPF_REG]; struct bpf_verifier_state *parent; + /* index of call instruction that called into this func */ + int callsite; + /* stack frame number of this function state from pov of + * enclosing bpf_verifier_state. + * 0 = main function, 1 = first callee. + */ + u32 frameno; + /* subprog number == index within subprog_stack_depth + * zero == main subprog + */ + u32 subprogno; + + /* should be second to last. See copy_func_state() */ int allocated_stack; struct bpf_stack_state *stack; }; +#define MAX_CALL_FRAMES 8 +struct bpf_verifier_state { + /* call stack tracking */ + struct bpf_func_state *frame[MAX_CALL_FRAMES]; + struct bpf_verifier_state *parent; + u32 curframe; +}; + /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; @@ -113,6 +143,7 @@ struct bpf_insn_aux_data { union { enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ struct bpf_map *map_ptr; /* pointer for call insn into lookup_elem */ + s32 call_imm; /* saved imm field of call insn */ }; int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ bool seen; /* this insn was processed by the verifier */ @@ -141,6 +172,8 @@ struct bpf_ext_analyzer_ops { int insn_idx, int prev_insn_idx); }; +#define BPF_MAX_SUBPROGS 256 + /* single container for all structs * one verifier_env per bpf_check() call */ @@ -159,13 +192,17 @@ struct bpf_verifier_env { bool allow_ptr_leaks; bool seen_direct_write; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ - struct bpf_verifer_log log; + u32 subprog_starts[BPF_MAX_SUBPROGS]; + u16 subprog_stack_depth[BPF_MAX_SUBPROGS + 1]; + u32 subprog_cnt; }; static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) { - return env->cur_state->regs; + struct bpf_verifier_state *cur = env->cur_state; + + return cur->frame[cur->curframe]->regs; } #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) diff --git a/include/linux/filter.h b/include/linux/filter.h index 5feb441d3dd9..e872b4ebaa57 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -58,6 +58,9 @@ struct bpf_prog_aux; /* unused opcode to mark special call to bpf_tail_call() helper */ #define BPF_TAIL_CALL 0xf0 +/* unused opcode to mark call to interpreter with arguments */ +#define BPF_CALL_ARGS 0xe0 + /* As per nm, we expose JITed images as text (code) section for * kallsyms. That way, tools like perf can find it to match * addresses. @@ -455,10 +458,13 @@ struct bpf_binary_header { struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ + jit_requested:1,/* archs need to JIT the prog */ locked:1, /* Program image locked? */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ + blinded:1, /* Was blinded */ + is_func:1, /* program is a bpf function */ kprobe_override:1; /* Do we override a kprobe? */ enum bpf_prog_type type; /* Type of BPF program */ u32 len; /* Number of filter blocks */ @@ -710,6 +716,9 @@ bool sk_filter_charge(struct sock *sk, struct sk_filter *fp); void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +#define __bpf_call_base_args \ + ((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \ + __bpf_call_base) struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); @@ -798,7 +807,7 @@ static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) return fp->jited && bpf_jit_is_ebpf(); } -static inline bool bpf_jit_blinding_enabled(void) +static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) { /* These are the prerequisites, should someone ever have the * idea to call blinding outside of them, we make sure to @@ -806,7 +815,7 @@ static inline bool bpf_jit_blinding_enabled(void) */ if (!bpf_jit_is_ebpf()) return false; - if (!bpf_jit_enable) + if (!prog->jit_requested) return false; if (!bpf_jit_harden) return false; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 595bda120cfb..d01f1cb3cfc0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -197,8 +197,14 @@ enum bpf_attach_type { */ #define BPF_F_STRICT_ALIGNMENT (1U << 0) +/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */ #define BPF_PSEUDO_MAP_FD 1 +/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative + * offset to another bpf function + */ +#define BPF_PSEUDO_CALL 1 + /* flags for BPF_MAP_UPDATE_ELEM command */ #define BPF_ANY 0 /* create new element or update existing */ #define BPF_NOEXIST 1 /* create new element if it didn't exist */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index d32bebf4f2de..768e0a02d8c8 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -94,6 +94,7 @@ struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) fp->pages = size / PAGE_SIZE; fp->aux = aux; fp->aux->prog = fp; + fp->jit_requested = ebpf_jit_enabled(); INIT_LIST_HEAD_RCU(&fp->aux->ksym_lnode); @@ -217,30 +218,40 @@ int bpf_prog_calc_tag(struct bpf_prog *fp) return 0; } -static bool bpf_is_jmp_and_has_target(const struct bpf_insn *insn) -{ - return BPF_CLASS(insn->code) == BPF_JMP && - /* Call and Exit are both special jumps with no - * target inside the BPF instruction image. - */ - BPF_OP(insn->code) != BPF_CALL && - BPF_OP(insn->code) != BPF_EXIT; -} - static void bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta) { struct bpf_insn *insn = prog->insnsi; u32 i, insn_cnt = prog->len; + bool pseudo_call; + u8 code; + int off; for (i = 0; i < insn_cnt; i++, insn++) { - if (!bpf_is_jmp_and_has_target(insn)) + code = insn->code; + if (BPF_CLASS(code) != BPF_JMP) continue; + if (BPF_OP(code) == BPF_EXIT) + continue; + if (BPF_OP(code) == BPF_CALL) { + if (insn->src_reg == BPF_PSEUDO_CALL) + pseudo_call = true; + else + continue; + } else { + pseudo_call = false; + } + off = pseudo_call ? insn->imm : insn->off; /* Adjust offset of jmps if we cross boundaries. */ - if (i < pos && i + insn->off + 1 > pos) - insn->off += delta; - else if (i > pos + delta && i + insn->off + 1 <= pos + delta) - insn->off -= delta; + if (i < pos && i + off + 1 > pos) + off += delta; + else if (i > pos + delta && i + off + 1 <= pos + delta) + off -= delta; + + if (pseudo_call) + insn->imm = off; + else + insn->off = off; } } @@ -711,7 +722,7 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) struct bpf_insn *insn; int i, rewritten; - if (!bpf_jit_blinding_enabled()) + if (!bpf_jit_blinding_enabled(prog) || prog->blinded) return prog; clone = bpf_prog_clone_create(prog, GFP_USER); @@ -753,6 +764,7 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) i += insn_delta; } + clone->blinded = 1; return clone; } #endif /* CONFIG_BPF_JIT */ @@ -774,8 +786,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); * * Decode and execute eBPF instructions. */ -static unsigned int ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, - u64 *stack) +static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) { u64 tmp; static const void *jumptable[256] = { @@ -835,6 +846,7 @@ static unsigned int ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, [BPF_ALU64 | BPF_NEG] = &&ALU64_NEG, /* Call instruction */ [BPF_JMP | BPF_CALL] = &&JMP_CALL, + [BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS, [BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL, /* Jumps */ [BPF_JMP | BPF_JA] = &&JMP_JA, @@ -1025,6 +1037,13 @@ select_insn: BPF_R4, BPF_R5); CONT; + JMP_CALL_ARGS: + BPF_R0 = (__bpf_call_base_args + insn->imm)(BPF_R1, BPF_R2, + BPF_R3, BPF_R4, + BPF_R5, + insn + insn->off + 1); + CONT; + JMP_TAIL_CALL: { struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2; struct bpf_array *array = container_of(map, struct bpf_array, map); @@ -1297,6 +1316,23 @@ static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn return ___bpf_prog_run(regs, insn, stack); \ } +#define PROG_NAME_ARGS(stack_size) __bpf_prog_run_args##stack_size +#define DEFINE_BPF_PROG_RUN_ARGS(stack_size) \ +static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \ + const struct bpf_insn *insn) \ +{ \ + u64 stack[stack_size / sizeof(u64)]; \ + u64 regs[MAX_BPF_REG]; \ +\ + FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ + BPF_R1 = r1; \ + BPF_R2 = r2; \ + BPF_R3 = r3; \ + BPF_R4 = r4; \ + BPF_R5 = r5; \ + return ___bpf_prog_run(regs, insn, stack); \ +} + #define EVAL1(FN, X) FN(X) #define EVAL2(FN, X, Y...) FN(X) EVAL1(FN, Y) #define EVAL3(FN, X, Y...) FN(X) EVAL2(FN, Y) @@ -1308,6 +1344,10 @@ EVAL6(DEFINE_BPF_PROG_RUN, 32, 64, 96, 128, 160, 192); EVAL6(DEFINE_BPF_PROG_RUN, 224, 256, 288, 320, 352, 384); EVAL4(DEFINE_BPF_PROG_RUN, 416, 448, 480, 512); +EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 32, 64, 96, 128, 160, 192); +EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 224, 256, 288, 320, 352, 384); +EVAL4(DEFINE_BPF_PROG_RUN_ARGS, 416, 448, 480, 512); + #define PROG_NAME_LIST(stack_size) PROG_NAME(stack_size), static unsigned int (*interpreters[])(const void *ctx, @@ -1316,6 +1356,24 @@ EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192) EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384) EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) }; +#undef PROG_NAME_LIST +#define PROG_NAME_LIST(stack_size) PROG_NAME_ARGS(stack_size), +static u64 (*interpreters_args[])(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, + const struct bpf_insn *insn) = { +EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192) +EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384) +EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) +}; +#undef PROG_NAME_LIST + +void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth) +{ + stack_depth = max_t(u32, stack_depth, 1); + insn->off = (s16) insn->imm; + insn->imm = interpreters_args[(round_up(stack_depth, 32) / 32) - 1] - + __bpf_call_base_args; + insn->code = BPF_JMP | BPF_CALL_ARGS; +} bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp) @@ -1572,11 +1630,19 @@ int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array, static void bpf_prog_free_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; + int i; aux = container_of(work, struct bpf_prog_aux, work); if (bpf_prog_is_dev_bound(aux)) bpf_prog_offload_destroy(aux->prog); - bpf_jit_free(aux->prog); + for (i = 0; i < aux->func_cnt; i++) + bpf_jit_free(aux->func[i]); + if (aux->func_cnt) { + kfree(aux->func); + bpf_prog_unlock_free(aux->prog); + } else { + bpf_jit_free(aux->prog); + } } /* Free internal BPF program */ diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index e682850c9715..883f88fa5bfc 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -189,8 +189,12 @@ void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env, u8 opcode = BPF_OP(insn->code); if (opcode == BPF_CALL) { - verbose(env, "(%02x) call %s#%d\n", insn->code, - func_id_name(insn->imm), insn->imm); + if (insn->src_reg == BPF_PSEUDO_CALL) + verbose(env, "(%02x) call pc%+d\n", insn->code, + insn->imm); + else + verbose(env, "(%02x) call %s#%d\n", insn->code, + func_id_name(insn->imm), insn->imm); } else if (insn->code == (BPF_JMP | BPF_JA)) { verbose(env, "(%02x) goto pc%+d\n", insn->code, insn->off); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 2c4cfeaa8d5e..e2e1c78ce1dc 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1194,7 +1194,8 @@ static int bpf_prog_load(union bpf_attr *attr) goto free_used_maps; /* eBPF program is ready to be JITed */ - prog = bpf_prog_select_runtime(prog, &err); + if (!prog->bpf_func) + prog = bpf_prog_select_runtime(prog, &err); if (err < 0) goto free_used_maps; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e807bda7fe29..48b2901cf483 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -20,6 +20,8 @@ #include #include #include +#include +#include #include "disasm.h" @@ -227,13 +229,23 @@ static void print_liveness(struct bpf_verifier_env *env, verbose(env, "w"); } -static void print_verifier_state(struct bpf_verifier_env *env, - struct bpf_verifier_state *state) +static struct bpf_func_state *func(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg) { - struct bpf_reg_state *reg; + struct bpf_verifier_state *cur = env->cur_state; + + return cur->frame[reg->frameno]; +} + +static void print_verifier_state(struct bpf_verifier_env *env, + const struct bpf_func_state *state) +{ + const struct bpf_reg_state *reg; enum bpf_reg_type t; int i; + if (state->frameno) + verbose(env, " frame%d:", state->frameno); for (i = 0; i < MAX_BPF_REG; i++) { reg = &state->regs[i]; t = reg->type; @@ -246,6 +258,8 @@ static void print_verifier_state(struct bpf_verifier_env *env, tnum_is_const(reg->var_off)) { /* reg->off should be 0 for SCALAR_VALUE */ verbose(env, "%lld", reg->var_off.value + reg->off); + if (t == PTR_TO_STACK) + verbose(env, ",call_%d", func(env, reg)->callsite); } else { verbose(env, "(id=%d", reg->id); if (t != SCALAR_VALUE) @@ -297,12 +311,14 @@ static void print_verifier_state(struct bpf_verifier_env *env, verbose(env, "=%s", reg_type_str[state->stack[i].spilled_ptr.type]); } + if (state->stack[i].slot_type[0] == STACK_ZERO) + verbose(env, " fp%d=0", (-i - 1) * BPF_REG_SIZE); } verbose(env, "\n"); } -static int copy_stack_state(struct bpf_verifier_state *dst, - const struct bpf_verifier_state *src) +static int copy_stack_state(struct bpf_func_state *dst, + const struct bpf_func_state *src) { if (!src->stack) return 0; @@ -318,13 +334,13 @@ static int copy_stack_state(struct bpf_verifier_state *dst, /* do_check() starts with zero-sized stack in struct bpf_verifier_state to * make it consume minimal amount of memory. check_stack_write() access from - * the program calls into realloc_verifier_state() to grow the stack size. + * the program calls into realloc_func_state() to grow the stack size. * Note there is a non-zero 'parent' pointer inside bpf_verifier_state * which this function copies over. It points to previous bpf_verifier_state * which is never reallocated */ -static int realloc_verifier_state(struct bpf_verifier_state *state, int size, - bool copy_old) +static int realloc_func_state(struct bpf_func_state *state, int size, + bool copy_old) { u32 old_size = state->allocated_stack; struct bpf_stack_state *new_stack; @@ -357,10 +373,21 @@ static int realloc_verifier_state(struct bpf_verifier_state *state, int size, return 0; } +static void free_func_state(struct bpf_func_state *state) +{ + kfree(state->stack); + kfree(state); +} + static void free_verifier_state(struct bpf_verifier_state *state, bool free_self) { - kfree(state->stack); + int i; + + for (i = 0; i <= state->curframe; i++) { + free_func_state(state->frame[i]); + state->frame[i] = NULL; + } if (free_self) kfree(state); } @@ -368,18 +395,46 @@ static void free_verifier_state(struct bpf_verifier_state *state, /* copy verifier state from src to dst growing dst stack space * when necessary to accommodate larger src stack */ -static int copy_verifier_state(struct bpf_verifier_state *dst, - const struct bpf_verifier_state *src) +static int copy_func_state(struct bpf_func_state *dst, + const struct bpf_func_state *src) { int err; - err = realloc_verifier_state(dst, src->allocated_stack, false); + err = realloc_func_state(dst, src->allocated_stack, false); if (err) return err; - memcpy(dst, src, offsetof(struct bpf_verifier_state, allocated_stack)); + memcpy(dst, src, offsetof(struct bpf_func_state, allocated_stack)); return copy_stack_state(dst, src); } +static int copy_verifier_state(struct bpf_verifier_state *dst_state, + const struct bpf_verifier_state *src) +{ + struct bpf_func_state *dst; + int i, err; + + /* if dst has more stack frames then src frame, free them */ + for (i = src->curframe + 1; i <= dst_state->curframe; i++) { + free_func_state(dst_state->frame[i]); + dst_state->frame[i] = NULL; + } + dst_state->curframe = src->curframe; + dst_state->parent = src->parent; + for (i = 0; i <= src->curframe; i++) { + dst = dst_state->frame[i]; + if (!dst) { + dst = kzalloc(sizeof(*dst), GFP_KERNEL); + if (!dst) + return -ENOMEM; + dst_state->frame[i] = dst; + } + err = copy_func_state(dst, src->frame[i]); + if (err) + return err; + } + return 0; +} + static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx, int *insn_idx) { @@ -441,6 +496,10 @@ err: static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; +#define CALLEE_SAVED_REGS 5 +static const int callee_saved[CALLEE_SAVED_REGS] = { + BPF_REG_6, BPF_REG_7, BPF_REG_8, BPF_REG_9 +}; static void __mark_reg_not_init(struct bpf_reg_state *reg); @@ -465,6 +524,13 @@ static void __mark_reg_known_zero(struct bpf_reg_state *reg) __mark_reg_known(reg, 0); } +static void __mark_reg_const_zero(struct bpf_reg_state *reg) +{ + __mark_reg_known(reg, 0); + reg->off = 0; + reg->type = SCALAR_VALUE; +} + static void mark_reg_known_zero(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno) { @@ -576,6 +642,7 @@ static void __mark_reg_unknown(struct bpf_reg_state *reg) reg->id = 0; reg->off = 0; reg->var_off = tnum_unknown; + reg->frameno = 0; __mark_reg_unbounded(reg); } @@ -612,8 +679,9 @@ static void mark_reg_not_init(struct bpf_verifier_env *env, } static void init_reg_state(struct bpf_verifier_env *env, - struct bpf_reg_state *regs) + struct bpf_func_state *state) { + struct bpf_reg_state *regs = state->regs; int i; for (i = 0; i < MAX_BPF_REG; i++) { @@ -624,41 +692,217 @@ static void init_reg_state(struct bpf_verifier_env *env, /* frame pointer */ regs[BPF_REG_FP].type = PTR_TO_STACK; mark_reg_known_zero(env, regs, BPF_REG_FP); + regs[BPF_REG_FP].frameno = state->frameno; /* 1st arg to a function */ regs[BPF_REG_1].type = PTR_TO_CTX; mark_reg_known_zero(env, regs, BPF_REG_1); } +#define BPF_MAIN_FUNC (-1) +static void init_func_state(struct bpf_verifier_env *env, + struct bpf_func_state *state, + int callsite, int frameno, int subprogno) +{ + state->callsite = callsite; + state->frameno = frameno; + state->subprogno = subprogno; + init_reg_state(env, state); +} + enum reg_arg_type { SRC_OP, /* register is used as source operand */ DST_OP, /* register is used as destination operand */ DST_OP_NO_MARK /* same as above, check only, don't mark */ }; -static void mark_reg_read(const struct bpf_verifier_state *state, u32 regno) +static int cmp_subprogs(const void *a, const void *b) { - struct bpf_verifier_state *parent = state->parent; + return *(int *)a - *(int *)b; +} + +static int find_subprog(struct bpf_verifier_env *env, int off) +{ + u32 *p; + + p = bsearch(&off, env->subprog_starts, env->subprog_cnt, + sizeof(env->subprog_starts[0]), cmp_subprogs); + if (!p) + return -ENOENT; + return p - env->subprog_starts; + +} + +static int add_subprog(struct bpf_verifier_env *env, int off) +{ + int insn_cnt = env->prog->len; + int ret; + + if (off >= insn_cnt || off < 0) { + verbose(env, "call to invalid destination\n"); + return -EINVAL; + } + ret = find_subprog(env, off); + if (ret >= 0) + return 0; + if (env->subprog_cnt >= BPF_MAX_SUBPROGS) { + verbose(env, "too many subprograms\n"); + return -E2BIG; + } + env->subprog_starts[env->subprog_cnt++] = off; + sort(env->subprog_starts, env->subprog_cnt, + sizeof(env->subprog_starts[0]), cmp_subprogs, NULL); + return 0; +} + +static int check_subprogs(struct bpf_verifier_env *env) +{ + int i, ret, subprog_start, subprog_end, off, cur_subprog = 0; + struct bpf_insn *insn = env->prog->insnsi; + int insn_cnt = env->prog->len; + + /* determine subprog starts. The end is one before the next starts */ + for (i = 0; i < insn_cnt; i++) { + if (insn[i].code != (BPF_JMP | BPF_CALL)) + continue; + if (insn[i].src_reg != BPF_PSEUDO_CALL) + continue; + if (!env->allow_ptr_leaks) { + verbose(env, "function calls to other bpf functions are allowed for root only\n"); + return -EPERM; + } + if (bpf_prog_is_dev_bound(env->prog->aux)) { + verbose(env, "funcation calls in offloaded programs are not supported yet\n"); + return -EINVAL; + } + ret = add_subprog(env, i + insn[i].imm + 1); + if (ret < 0) + return ret; + } + + if (env->log.level > 1) + for (i = 0; i < env->subprog_cnt; i++) + verbose(env, "func#%d @%d\n", i, env->subprog_starts[i]); + + /* now check that all jumps are within the same subprog */ + subprog_start = 0; + if (env->subprog_cnt == cur_subprog) + subprog_end = insn_cnt; + else + subprog_end = env->subprog_starts[cur_subprog++]; + for (i = 0; i < insn_cnt; i++) { + u8 code = insn[i].code; + + if (BPF_CLASS(code) != BPF_JMP) + goto next; + if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL) + goto next; + off = i + insn[i].off + 1; + if (off < subprog_start || off >= subprog_end) { + verbose(env, "jump out of range from insn %d to %d\n", i, off); + return -EINVAL; + } +next: + if (i == subprog_end - 1) { + /* to avoid fall-through from one subprog into another + * the last insn of the subprog should be either exit + * or unconditional jump back + */ + if (code != (BPF_JMP | BPF_EXIT) && + code != (BPF_JMP | BPF_JA)) { + verbose(env, "last insn is not an exit or jmp\n"); + return -EINVAL; + } + subprog_start = subprog_end; + if (env->subprog_cnt == cur_subprog) + subprog_end = insn_cnt; + else + subprog_end = env->subprog_starts[cur_subprog++]; + } + } + return 0; +} + +struct bpf_verifier_state *skip_callee(struct bpf_verifier_env *env, + const struct bpf_verifier_state *state, + struct bpf_verifier_state *parent, + u32 regno) +{ + struct bpf_verifier_state *tmp = NULL; + + /* 'parent' could be a state of caller and + * 'state' could be a state of callee. In such case + * parent->curframe < state->curframe + * and it's ok for r1 - r5 registers + * + * 'parent' could be a callee's state after it bpf_exit-ed. + * In such case parent->curframe > state->curframe + * and it's ok for r0 only + */ + if (parent->curframe == state->curframe || + (parent->curframe < state->curframe && + regno >= BPF_REG_1 && regno <= BPF_REG_5) || + (parent->curframe > state->curframe && + regno == BPF_REG_0)) + return parent; + + if (parent->curframe > state->curframe && + regno >= BPF_REG_6) { + /* for callee saved regs we have to skip the whole chain + * of states that belong to callee and mark as LIVE_READ + * the registers before the call + */ + tmp = parent; + while (tmp && tmp->curframe != state->curframe) { + tmp = tmp->parent; + } + if (!tmp) + goto bug; + parent = tmp; + } else { + goto bug; + } + return parent; +bug: + verbose(env, "verifier bug regno %d tmp %p\n", regno, tmp); + verbose(env, "regno %d parent frame %d current frame %d\n", + regno, parent->curframe, state->curframe); + return 0; +} + +static int mark_reg_read(struct bpf_verifier_env *env, + const struct bpf_verifier_state *state, + struct bpf_verifier_state *parent, + u32 regno) +{ + bool writes = parent == state->parent; /* Observe write marks */ if (regno == BPF_REG_FP) /* We don't need to worry about FP liveness because it's read-only */ - return; + return 0; while (parent) { /* if read wasn't screened by an earlier write ... */ - if (state->regs[regno].live & REG_LIVE_WRITTEN) + if (writes && state->frame[state->curframe]->regs[regno].live & REG_LIVE_WRITTEN) break; + parent = skip_callee(env, state, parent, regno); + if (!parent) + return -EFAULT; /* ... then we depend on parent's value */ - parent->regs[regno].live |= REG_LIVE_READ; + parent->frame[parent->curframe]->regs[regno].live |= REG_LIVE_READ; state = parent; parent = state->parent; + writes = true; } + return 0; } static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, enum reg_arg_type t) { - struct bpf_reg_state *regs = env->cur_state->regs; + struct bpf_verifier_state *vstate = env->cur_state; + struct bpf_func_state *state = vstate->frame[vstate->curframe]; + struct bpf_reg_state *regs = state->regs; if (regno >= MAX_BPF_REG) { verbose(env, "R%d is invalid\n", regno); @@ -671,7 +915,7 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, verbose(env, "R%d !read_ok\n", regno); return -EACCES; } - mark_reg_read(env->cur_state, regno); + return mark_reg_read(env, vstate, vstate->parent, regno); } else { /* check whether register used as dest operand can be written to */ if (regno == BPF_REG_FP) { @@ -702,17 +946,25 @@ static bool is_spillable_regtype(enum bpf_reg_type type) } } +/* Does this register contain a constant zero? */ +static bool register_is_null(struct bpf_reg_state *reg) +{ + return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0); +} + /* check_stack_read/write functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ static int check_stack_write(struct bpf_verifier_env *env, - struct bpf_verifier_state *state, int off, - int size, int value_regno) + struct bpf_func_state *state, /* func where register points to */ + int off, int size, int value_regno) { + struct bpf_func_state *cur; /* state of the current function */ int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err; + enum bpf_reg_type type; - err = realloc_verifier_state(state, round_up(slot + 1, BPF_REG_SIZE), - true); + err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE), + true); if (err) return err; /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, @@ -725,8 +977,9 @@ static int check_stack_write(struct bpf_verifier_env *env, return -EACCES; } + cur = env->cur_state->frame[env->cur_state->curframe]; if (value_regno >= 0 && - is_spillable_regtype(state->regs[value_regno].type)) { + is_spillable_regtype((type = cur->regs[value_regno].type))) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { @@ -734,51 +987,116 @@ static int check_stack_write(struct bpf_verifier_env *env, return -EACCES; } + if (state != cur && type == PTR_TO_STACK) { + verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); + return -EINVAL; + } + /* save register state */ - state->stack[spi].spilled_ptr = state->regs[value_regno]; + state->stack[spi].spilled_ptr = cur->regs[value_regno]; state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; for (i = 0; i < BPF_REG_SIZE; i++) state->stack[spi].slot_type[i] = STACK_SPILL; } else { + u8 type = STACK_MISC; + /* regular write of data into stack */ state->stack[spi].spilled_ptr = (struct bpf_reg_state) {}; + /* only mark the slot as written if all 8 bytes were written + * otherwise read propagation may incorrectly stop too soon + * when stack slots are partially written. + * This heuristic means that read propagation will be + * conservative, since it will add reg_live_read marks + * to stack slots all the way to first state when programs + * writes+reads less than 8 bytes + */ + if (size == BPF_REG_SIZE) + state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + + /* when we zero initialize stack slots mark them as such */ + if (value_regno >= 0 && + register_is_null(&cur->regs[value_regno])) + type = STACK_ZERO; + for (i = 0; i < size; i++) state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = - STACK_MISC; + type; } return 0; } -static void mark_stack_slot_read(const struct bpf_verifier_state *state, int slot) +/* registers of every function are unique and mark_reg_read() propagates + * the liveness in the following cases: + * - from callee into caller for R1 - R5 that were used as arguments + * - from caller into callee for R0 that used as result of the call + * - from caller to the same caller skipping states of the callee for R6 - R9, + * since R6 - R9 are callee saved by implicit function prologue and + * caller's R6 != callee's R6, so when we propagate liveness up to + * parent states we need to skip callee states for R6 - R9. + * + * stack slot marking is different, since stacks of caller and callee are + * accessible in both (since caller can pass a pointer to caller's stack to + * callee which can pass it to another function), hence mark_stack_slot_read() + * has to propagate the stack liveness to all parent states at given frame number. + * Consider code: + * f1() { + * ptr = fp - 8; + * *ptr = ctx; + * call f2 { + * .. = *ptr; + * } + * .. = *ptr; + * } + * First *ptr is reading from f1's stack and mark_stack_slot_read() has + * to mark liveness at the f1's frame and not f2's frame. + * Second *ptr is also reading from f1's stack and mark_stack_slot_read() has + * to propagate liveness to f2 states at f1's frame level and further into + * f1 states at f1's frame level until write into that stack slot + */ +static void mark_stack_slot_read(struct bpf_verifier_env *env, + const struct bpf_verifier_state *state, + struct bpf_verifier_state *parent, + int slot, int frameno) { - struct bpf_verifier_state *parent = state->parent; + bool writes = parent == state->parent; /* Observe write marks */ while (parent) { + if (parent->frame[frameno]->allocated_stack <= slot * BPF_REG_SIZE) + /* since LIVE_WRITTEN mark is only done for full 8-byte + * write the read marks are conservative and parent + * state may not even have the stack allocated. In such case + * end the propagation, since the loop reached beginning + * of the function + */ + break; /* if read wasn't screened by an earlier write ... */ - if (state->stack[slot].spilled_ptr.live & REG_LIVE_WRITTEN) + if (writes && state->frame[frameno]->stack[slot].spilled_ptr.live & REG_LIVE_WRITTEN) break; /* ... then we depend on parent's value */ - parent->stack[slot].spilled_ptr.live |= REG_LIVE_READ; + parent->frame[frameno]->stack[slot].spilled_ptr.live |= REG_LIVE_READ; state = parent; parent = state->parent; + writes = true; } } static int check_stack_read(struct bpf_verifier_env *env, - struct bpf_verifier_state *state, int off, int size, - int value_regno) + struct bpf_func_state *reg_state /* func where register points to */, + int off, int size, int value_regno) { + struct bpf_verifier_state *vstate = env->cur_state; + struct bpf_func_state *state = vstate->frame[vstate->curframe]; int i, slot = -off - 1, spi = slot / BPF_REG_SIZE; u8 *stype; - if (state->allocated_stack <= slot) { + if (reg_state->allocated_stack <= slot) { verbose(env, "invalid read from stack off %d+0 size %d\n", off, size); return -EACCES; } - stype = state->stack[spi].slot_type; + stype = reg_state->stack[spi].slot_type; if (stype[0] == STACK_SPILL) { if (size != BPF_REG_SIZE) { @@ -794,26 +1112,44 @@ static int check_stack_read(struct bpf_verifier_env *env, if (value_regno >= 0) { /* restore register state from stack */ - state->regs[value_regno] = state->stack[spi].spilled_ptr; + state->regs[value_regno] = reg_state->stack[spi].spilled_ptr; /* mark reg as written since spilled pointer state likely * has its liveness marks cleared by is_state_visited() * which resets stack/reg liveness for state transitions */ state->regs[value_regno].live |= REG_LIVE_WRITTEN; - mark_stack_slot_read(state, spi); } + mark_stack_slot_read(env, vstate, vstate->parent, spi, + reg_state->frameno); return 0; } else { + int zeros = 0; + for (i = 0; i < size; i++) { - if (stype[(slot - i) % BPF_REG_SIZE] != STACK_MISC) { - verbose(env, "invalid read from stack off %d+%d size %d\n", - off, i, size); - return -EACCES; + if (stype[(slot - i) % BPF_REG_SIZE] == STACK_MISC) + continue; + if (stype[(slot - i) % BPF_REG_SIZE] == STACK_ZERO) { + zeros++; + continue; } + verbose(env, "invalid read from stack off %d+%d size %d\n", + off, i, size); + return -EACCES; + } + mark_stack_slot_read(env, vstate, vstate->parent, spi, + reg_state->frameno); + if (value_regno >= 0) { + if (zeros == size) { + /* any size read into register is zero extended, + * so the whole register == const_zero + */ + __mark_reg_const_zero(&state->regs[value_regno]); + } else { + /* have read misc data from the stack */ + mark_reg_unknown(env, state->regs, value_regno); + } + state->regs[value_regno].live |= REG_LIVE_WRITTEN; } - if (value_regno >= 0) - /* have read misc data from the stack */ - mark_reg_unknown(env, state->regs, value_regno); return 0; } } @@ -838,7 +1174,8 @@ static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off, static int check_map_access(struct bpf_verifier_env *env, u32 regno, int off, int size, bool zero_size_allowed) { - struct bpf_verifier_state *state = env->cur_state; + struct bpf_verifier_state *vstate = env->cur_state; + struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regno]; int err; @@ -1088,6 +1425,54 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, strict); } +static int update_stack_depth(struct bpf_verifier_env *env, + const struct bpf_func_state *func, + int off) +{ + u16 stack = env->subprog_stack_depth[func->subprogno], total = 0; + struct bpf_verifier_state *cur = env->cur_state; + int i; + + if (stack >= -off) + return 0; + + /* update known max for given subprogram */ + env->subprog_stack_depth[func->subprogno] = -off; + + /* compute the total for current call chain */ + for (i = 0; i <= cur->curframe; i++) { + u32 depth = env->subprog_stack_depth[cur->frame[i]->subprogno]; + + /* round up to 32-bytes, since this is granularity + * of interpreter stack sizes + */ + depth = round_up(depth, 32); + total += depth; + } + + if (total > MAX_BPF_STACK) { + verbose(env, "combined stack size of %d calls is %d. Too large\n", + cur->curframe, total); + return -EACCES; + } + return 0; +} + +static int get_callee_stack_depth(struct bpf_verifier_env *env, + const struct bpf_insn *insn, int idx) +{ + int start = idx + insn->imm + 1, subprog; + + subprog = find_subprog(env, start); + if (subprog < 0) { + WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", + start); + return -EFAULT; + } + subprog++; + return env->subprog_stack_depth[subprog]; +} + /* check whether memory at (regno + off) is accessible for t = (read | write) * if t==write, value_regno is a register which value is stored into memory * if t==read, value_regno is a register which will receive the value from memory @@ -1098,9 +1483,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn int bpf_size, enum bpf_access_type t, int value_regno) { - struct bpf_verifier_state *state = env->cur_state; struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; + struct bpf_func_state *state; int size, err = 0; size = bpf_size_to_bytes(bpf_size); @@ -1189,8 +1574,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn return -EACCES; } - if (env->prog->aux->stack_depth < -off) - env->prog->aux->stack_depth = -off; + state = func(env, reg); + err = update_stack_depth(env, state, off); + if (err) + return err; if (t == BPF_WRITE) err = check_stack_write(env, state, off, size, @@ -1264,12 +1651,6 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins BPF_SIZE(insn->code), BPF_WRITE, -1); } -/* Does this register contain a constant zero? */ -static bool register_is_null(struct bpf_reg_state *reg) -{ - return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0); -} - /* when register 'regno' is passed into function that will read 'access_size' * bytes from that pointer, make sure that it's within stack boundary * and all elements of stack are initialized. @@ -1281,7 +1662,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *reg = cur_regs(env) + regno; - struct bpf_verifier_state *state = env->cur_state; + struct bpf_func_state *state = func(env, reg); int off, i, slot, spi; if (reg->type != PTR_TO_STACK) { @@ -1312,9 +1693,6 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, return -EACCES; } - if (env->prog->aux->stack_depth < -off) - env->prog->aux->stack_depth = -off; - if (meta && meta->raw_mode) { meta->access_size = access_size; meta->regno = regno; @@ -1322,17 +1700,32 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, } for (i = 0; i < access_size; i++) { + u8 *stype; + slot = -(off + i) - 1; spi = slot / BPF_REG_SIZE; - if (state->allocated_stack <= slot || - state->stack[spi].slot_type[slot % BPF_REG_SIZE] != - STACK_MISC) { - verbose(env, "invalid indirect read from stack off %d+%d size %d\n", - off, i, access_size); - return -EACCES; + if (state->allocated_stack <= slot) + goto err; + stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE]; + if (*stype == STACK_MISC) + goto mark; + if (*stype == STACK_ZERO) { + /* helper can write anything into the stack */ + *stype = STACK_MISC; + goto mark; } +err: + verbose(env, "invalid indirect read from stack off %d+%d size %d\n", + off, i, access_size); + return -EACCES; +mark: + /* reading any byte out of 8-byte 'spill_slot' will cause + * the whole slot to be marked as 'read' + */ + mark_stack_slot_read(env, env->cur_state, env->cur_state->parent, + spi, state->frameno); } - return 0; + return update_stack_depth(env, state, off); } static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, @@ -1585,6 +1978,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_FUNC_tail_call: if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) goto error; + if (env->subprog_cnt) { + verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n"); + return -EINVAL; + } break; case BPF_FUNC_perf_event_read: case BPF_FUNC_perf_event_output: @@ -1646,9 +2043,9 @@ static int check_raw_mode(const struct bpf_func_proto *fn) /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] * are now invalid, so turn them into unknown SCALAR_VALUE. */ -static void clear_all_pkt_pointers(struct bpf_verifier_env *env) +static void __clear_all_pkt_pointers(struct bpf_verifier_env *env, + struct bpf_func_state *state) { - struct bpf_verifier_state *state = env->cur_state; struct bpf_reg_state *regs = state->regs, *reg; int i; @@ -1665,7 +2062,121 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) } } -static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) +static void clear_all_pkt_pointers(struct bpf_verifier_env *env) +{ + struct bpf_verifier_state *vstate = env->cur_state; + int i; + + for (i = 0; i <= vstate->curframe; i++) + __clear_all_pkt_pointers(env, vstate->frame[i]); +} + +static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, + int *insn_idx) +{ + struct bpf_verifier_state *state = env->cur_state; + struct bpf_func_state *caller, *callee; + int i, subprog, target_insn; + + if (state->curframe >= MAX_CALL_FRAMES) { + verbose(env, "the call stack of %d frames is too deep\n", + state->curframe); + return -E2BIG; + } + + target_insn = *insn_idx + insn->imm; + subprog = find_subprog(env, target_insn + 1); + if (subprog < 0) { + verbose(env, "verifier bug. No program starts at insn %d\n", + target_insn + 1); + return -EFAULT; + } + + caller = state->frame[state->curframe]; + if (state->frame[state->curframe + 1]) { + verbose(env, "verifier bug. Frame %d already allocated\n", + state->curframe + 1); + return -EFAULT; + } + + callee = kzalloc(sizeof(*callee), GFP_KERNEL); + if (!callee) + return -ENOMEM; + state->frame[state->curframe + 1] = callee; + + /* callee cannot access r0, r6 - r9 for reading and has to write + * into its own stack before reading from it. + * callee can read/write into caller's stack + */ + init_func_state(env, callee, + /* remember the callsite, it will be used by bpf_exit */ + *insn_idx /* callsite */, + state->curframe + 1 /* frameno within this callchain */, + subprog + 1 /* subprog number within this prog */); + + /* copy r1 - r5 args that callee can access */ + for (i = BPF_REG_1; i <= BPF_REG_5; i++) + callee->regs[i] = caller->regs[i]; + + /* after the call regsiters r0 - r5 were scratched */ + for (i = 0; i < CALLER_SAVED_REGS; i++) { + mark_reg_not_init(env, caller->regs, caller_saved[i]); + check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); + } + + /* only increment it after check_reg_arg() finished */ + state->curframe++; + + /* and go analyze first insn of the callee */ + *insn_idx = target_insn; + + if (env->log.level) { + verbose(env, "caller:\n"); + print_verifier_state(env, caller); + verbose(env, "callee:\n"); + print_verifier_state(env, callee); + } + return 0; +} + +static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) +{ + struct bpf_verifier_state *state = env->cur_state; + struct bpf_func_state *caller, *callee; + struct bpf_reg_state *r0; + + callee = state->frame[state->curframe]; + r0 = &callee->regs[BPF_REG_0]; + if (r0->type == PTR_TO_STACK) { + /* technically it's ok to return caller's stack pointer + * (or caller's caller's pointer) back to the caller, + * since these pointers are valid. Only current stack + * pointer will be invalid as soon as function exits, + * but let's be conservative + */ + verbose(env, "cannot return stack pointer to the caller\n"); + return -EINVAL; + } + + state->curframe--; + caller = state->frame[state->curframe]; + /* return to the caller whatever r0 had in the callee */ + caller->regs[BPF_REG_0] = *r0; + + *insn_idx = callee->callsite + 1; + if (env->log.level) { + verbose(env, "returning from callee:\n"); + print_verifier_state(env, callee); + verbose(env, "to caller at %d:\n", *insn_idx); + print_verifier_state(env, caller); + } + /* clear everything in the callee */ + free_func_state(callee); + state->frame[state->curframe + 1] = NULL; + return 0; +} + +static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx) { const struct bpf_func_proto *fn = NULL; struct bpf_reg_state *regs; @@ -1825,7 +2336,9 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, const struct bpf_reg_state *ptr_reg, const struct bpf_reg_state *off_reg) { - struct bpf_reg_state *regs = cur_regs(env), *dst_reg; + struct bpf_verifier_state *vstate = env->cur_state; + struct bpf_func_state *state = vstate->frame[vstate->curframe]; + struct bpf_reg_state *regs = state->regs, *dst_reg; bool known = tnum_is_const(off_reg->var_off); s64 smin_val = off_reg->smin_value, smax_val = off_reg->smax_value, smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value; @@ -1837,13 +2350,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg = ®s[dst]; if (WARN_ON_ONCE(known && (smin_val != smax_val))) { - print_verifier_state(env, env->cur_state); + print_verifier_state(env, state); verbose(env, "verifier internal error: known but bad sbounds\n"); return -EINVAL; } if (WARN_ON_ONCE(known && (umin_val != umax_val))) { - print_verifier_state(env, env->cur_state); + print_verifier_state(env, state); verbose(env, "verifier internal error: known but bad ubounds\n"); return -EINVAL; @@ -2245,7 +2758,9 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn) { - struct bpf_reg_state *regs = cur_regs(env), *dst_reg, *src_reg; + struct bpf_verifier_state *vstate = env->cur_state; + struct bpf_func_state *state = vstate->frame[vstate->curframe]; + struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg; struct bpf_reg_state *ptr_reg = NULL, off_reg = {0}; u8 opcode = BPF_OP(insn->code); int rc; @@ -2319,12 +2834,12 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, /* Got here implies adding two SCALAR_VALUEs */ if (WARN_ON_ONCE(ptr_reg)) { - print_verifier_state(env, env->cur_state); + print_verifier_state(env, state); verbose(env, "verifier internal error: unexpected ptr_reg\n"); return -EINVAL; } if (WARN_ON(!src_reg)) { - print_verifier_state(env, env->cur_state); + print_verifier_state(env, state); verbose(env, "verifier internal error: no src_reg\n"); return -EINVAL; } @@ -2478,14 +2993,15 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } -static void find_good_pkt_pointers(struct bpf_verifier_state *state, +static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, struct bpf_reg_state *dst_reg, enum bpf_reg_type type, bool range_right_open) { + struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *regs = state->regs, *reg; u16 new_range; - int i; + int i, j; if (dst_reg->off < 0 || (dst_reg->off == 0 && range_right_open)) @@ -2555,12 +3071,15 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, /* keep the maximum range already checked */ regs[i].range = max(regs[i].range, new_range); - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) - continue; - reg = &state->stack[i].spilled_ptr; - if (reg->type == type && reg->id == dst_reg->id) - reg->range = max(reg->range, new_range); + for (j = 0; j <= vstate->curframe; j++) { + state = vstate->frame[j]; + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { + if (state->stack[i].slot_type[0] != STACK_SPILL) + continue; + reg = &state->stack[i].spilled_ptr; + if (reg->type == type && reg->id == dst_reg->id) + reg->range = max(reg->range, new_range); + } } } @@ -2798,20 +3317,24 @@ static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id, /* The logic is similar to find_good_pkt_pointers(), both could eventually * be folded together at some point. */ -static void mark_map_regs(struct bpf_verifier_state *state, u32 regno, +static void mark_map_regs(struct bpf_verifier_state *vstate, u32 regno, bool is_null) { + struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *regs = state->regs; u32 id = regs[regno].id; - int i; + int i, j; for (i = 0; i < MAX_BPF_REG; i++) mark_map_reg(regs, i, id, is_null); - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) - continue; - mark_map_reg(&state->stack[i].spilled_ptr, 0, id, is_null); + for (j = 0; j <= vstate->curframe; j++) { + state = vstate->frame[j]; + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { + if (state->stack[i].slot_type[0] != STACK_SPILL) + continue; + mark_map_reg(&state->stack[i].spilled_ptr, 0, id, is_null); + } } } @@ -2911,8 +3434,10 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { - struct bpf_verifier_state *other_branch, *this_branch = env->cur_state; - struct bpf_reg_state *regs = this_branch->regs, *dst_reg; + struct bpf_verifier_state *this_branch = env->cur_state; + struct bpf_verifier_state *other_branch; + struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs; + struct bpf_reg_state *dst_reg, *other_branch_regs; u8 opcode = BPF_OP(insn->code); int err; @@ -2975,6 +3500,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx); if (!other_branch) return -EFAULT; + other_branch_regs = other_branch->frame[other_branch->curframe]->regs; /* detect if we are comparing against a constant value so we can adjust * our min/max values for our dst register. @@ -2987,22 +3513,22 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, if (dst_reg->type == SCALAR_VALUE && regs[insn->src_reg].type == SCALAR_VALUE) { if (tnum_is_const(regs[insn->src_reg].var_off)) - reg_set_min_max(&other_branch->regs[insn->dst_reg], + reg_set_min_max(&other_branch_regs[insn->dst_reg], dst_reg, regs[insn->src_reg].var_off.value, opcode); else if (tnum_is_const(dst_reg->var_off)) - reg_set_min_max_inv(&other_branch->regs[insn->src_reg], + reg_set_min_max_inv(&other_branch_regs[insn->src_reg], ®s[insn->src_reg], dst_reg->var_off.value, opcode); else if (opcode == BPF_JEQ || opcode == BPF_JNE) /* Comparing for equality, we can combine knowledge */ - reg_combine_min_max(&other_branch->regs[insn->src_reg], - &other_branch->regs[insn->dst_reg], + reg_combine_min_max(&other_branch_regs[insn->src_reg], + &other_branch_regs[insn->dst_reg], ®s[insn->src_reg], ®s[insn->dst_reg], opcode); } } else if (dst_reg->type == SCALAR_VALUE) { - reg_set_min_max(&other_branch->regs[insn->dst_reg], + reg_set_min_max(&other_branch_regs[insn->dst_reg], dst_reg, insn->imm, opcode); } @@ -3023,7 +3549,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return -EACCES; } if (env->log.level) - print_verifier_state(env, this_branch); + print_verifier_state(env, this_branch->frame[this_branch->curframe]); return 0; } @@ -3108,6 +3634,18 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } + if (env->subprog_cnt) { + /* when program has LD_ABS insn JITs and interpreter assume + * that r1 == ctx == skb which is not the case for callees + * that can have arbitrary arguments. It's problematic + * for main prog as well since JITs would need to analyze + * all functions in order to make proper register save/restore + * decisions in the main prog. Hence disallow LD_ABS with calls + */ + verbose(env, "BPF_LD_[ABS|IND] instructions cannot be mixed with bpf-to-bpf calls\n"); + return -EINVAL; + } + if (insn->dst_reg != BPF_REG_0 || insn->off != 0 || BPF_SIZE(insn->code) == BPF_DW || (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) { @@ -3284,6 +3822,10 @@ static int check_cfg(struct bpf_verifier_env *env) int ret = 0; int i, t; + ret = check_subprogs(env); + if (ret < 0) + return ret; + insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_state) return -ENOMEM; @@ -3316,6 +3858,14 @@ peek_stack: goto err_free; if (t + 1 < insn_cnt) env->explored_states[t + 1] = STATE_LIST_MARK; + if (insns[t].src_reg == BPF_PSEUDO_CALL) { + env->explored_states[t] = STATE_LIST_MARK; + ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env); + if (ret == 1) + goto peek_stack; + else if (ret < 0) + goto err_free; + } } else if (opcode == BPF_JA) { if (BPF_SRC(insns[t].code) != BPF_K) { ret = -EINVAL; @@ -3434,11 +3984,21 @@ static bool check_ids(u32 old_id, u32 cur_id, struct idpair *idmap) static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, struct idpair *idmap) { + bool equal; + if (!(rold->live & REG_LIVE_READ)) /* explored state didn't use this */ return true; - if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, live)) == 0) + equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, frameno)) == 0; + + if (rold->type == PTR_TO_STACK) + /* two stack pointers are equal only if they're pointing to + * the same stack frame, since fp-8 in foo != fp-8 in bar + */ + return equal && rold->frameno == rcur->frameno; + + if (equal) return true; if (rold->type == NOT_INIT) @@ -3511,7 +4071,6 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, tnum_in(rold->var_off, rcur->var_off); case PTR_TO_CTX: case CONST_PTR_TO_MAP: - case PTR_TO_STACK: case PTR_TO_PACKET_END: /* Only valid matches are exact, which memcmp() above * would have accepted @@ -3526,8 +4085,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return false; } -static bool stacksafe(struct bpf_verifier_state *old, - struct bpf_verifier_state *cur, +static bool stacksafe(struct bpf_func_state *old, + struct bpf_func_state *cur, struct idpair *idmap) { int i, spi; @@ -3545,8 +4104,19 @@ static bool stacksafe(struct bpf_verifier_state *old, for (i = 0; i < old->allocated_stack; i++) { spi = i / BPF_REG_SIZE; + if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) + /* explored state didn't use this */ + return true; + if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID) continue; + /* if old state was safe with misc data in the stack + * it will be safe with zero-initialized stack. + * The opposite is not true + */ + if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_MISC && + cur->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_ZERO) + continue; if (old->stack[spi].slot_type[i % BPF_REG_SIZE] != cur->stack[spi].slot_type[i % BPF_REG_SIZE]) /* Ex: old explored (safe) state has STACK_SPILL in @@ -3603,9 +4173,8 @@ static bool stacksafe(struct bpf_verifier_state *old, * whereas register type in current state is meaningful, it means that * the current state will reach 'bpf_exit' instruction safely */ -static bool states_equal(struct bpf_verifier_env *env, - struct bpf_verifier_state *old, - struct bpf_verifier_state *cur) +static bool func_states_equal(struct bpf_func_state *old, + struct bpf_func_state *cur) { struct idpair *idmap; bool ret = false; @@ -3629,71 +4198,72 @@ out_free: return ret; } -/* A write screens off any subsequent reads; but write marks come from the - * straight-line code between a state and its parent. When we arrive at a - * jump target (in the first iteration of the propagate_liveness() loop), - * we didn't arrive by the straight-line code, so read marks in state must - * propagate to parent regardless of state's write marks. - */ -static bool do_propagate_liveness(const struct bpf_verifier_state *state, - struct bpf_verifier_state *parent) +static bool states_equal(struct bpf_verifier_env *env, + struct bpf_verifier_state *old, + struct bpf_verifier_state *cur) { - bool writes = parent == state->parent; /* Observe write marks */ - bool touched = false; /* any changes made? */ int i; - if (!parent) - return touched; + if (old->curframe != cur->curframe) + return false; + + /* for states to be equal callsites have to be the same + * and all frame states need to be equivalent + */ + for (i = 0; i <= old->curframe; i++) { + if (old->frame[i]->callsite != cur->frame[i]->callsite) + return false; + if (!func_states_equal(old->frame[i], cur->frame[i])) + return false; + } + return true; +} + +/* A write screens off any subsequent reads; but write marks come from the + * straight-line code between a state and its parent. When we arrive at an + * equivalent state (jump target or such) we didn't arrive by the straight-line + * code, so read marks in the state must propagate to the parent regardless + * of the state's write marks. That's what 'parent == state->parent' comparison + * in mark_reg_read() and mark_stack_slot_read() is for. + */ +static int propagate_liveness(struct bpf_verifier_env *env, + const struct bpf_verifier_state *vstate, + struct bpf_verifier_state *vparent) +{ + int i, frame, err = 0; + struct bpf_func_state *state, *parent; + + if (vparent->curframe != vstate->curframe) { + WARN(1, "propagate_live: parent frame %d current frame %d\n", + vparent->curframe, vstate->curframe); + return -EFAULT; + } /* Propagate read liveness of registers... */ BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG); /* We don't need to worry about FP liveness because it's read-only */ for (i = 0; i < BPF_REG_FP; i++) { - if (parent->regs[i].live & REG_LIVE_READ) + if (vparent->frame[vparent->curframe]->regs[i].live & REG_LIVE_READ) continue; - if (writes && (state->regs[i].live & REG_LIVE_WRITTEN)) - continue; - if (state->regs[i].live & REG_LIVE_READ) { - parent->regs[i].live |= REG_LIVE_READ; - touched = true; + if (vstate->frame[vstate->curframe]->regs[i].live & REG_LIVE_READ) { + err = mark_reg_read(env, vstate, vparent, i); + if (err) + return err; } } - /* ... and stack slots */ - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE && - i < parent->allocated_stack / BPF_REG_SIZE; i++) { - if (parent->stack[i].slot_type[0] != STACK_SPILL) - continue; - if (state->stack[i].slot_type[0] != STACK_SPILL) - continue; - if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ) - continue; - if (writes && - (state->stack[i].spilled_ptr.live & REG_LIVE_WRITTEN)) - continue; - if (state->stack[i].spilled_ptr.live & REG_LIVE_READ) { - parent->stack[i].spilled_ptr.live |= REG_LIVE_READ; - touched = true; - } - } - return touched; -} -/* "parent" is "a state from which we reach the current state", but initially - * it is not the state->parent (i.e. "the state whose straight-line code leads - * to the current state"), instead it is the state that happened to arrive at - * a (prunable) equivalent of the current state. See comment above - * do_propagate_liveness() for consequences of this. - * This function is just a more efficient way of calling mark_reg_read() or - * mark_stack_slot_read() on each reg in "parent" that is read in "state", - * though it requires that parent != state->parent in the call arguments. - */ -static void propagate_liveness(const struct bpf_verifier_state *state, - struct bpf_verifier_state *parent) -{ - while (do_propagate_liveness(state, parent)) { - /* Something changed, so we need to feed those changes onward */ - state = parent; - parent = state->parent; + /* ... and stack slots */ + for (frame = 0; frame <= vstate->curframe; frame++) { + state = vstate->frame[frame]; + parent = vparent->frame[frame]; + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE && + i < parent->allocated_stack / BPF_REG_SIZE; i++) { + if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ) + continue; + if (state->stack[i].spilled_ptr.live & REG_LIVE_READ) + mark_stack_slot_read(env, vstate, vparent, i, frame); + } } + return err; } static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) @@ -3701,7 +4271,7 @@ 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; struct bpf_verifier_state *cur = env->cur_state; - int i, err; + int i, j, err; sl = env->explored_states[insn_idx]; if (!sl) @@ -3722,7 +4292,9 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) * they'll be immediately forgotten as we're pruning * this state and will pop a new one. */ - propagate_liveness(&sl->state, cur); + err = propagate_liveness(env, &sl->state, cur); + if (err) + return err; return 1; } sl = sl->next; @@ -3730,9 +4302,10 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) /* there were no equivalent states, remember current one. * technically the current state is not proven to be safe yet, - * but it will either reach bpf_exit (which means it's safe) or - * it will be rejected. Since there are no loops, we won't be - * seeing this 'insn_idx' instruction again on the way to bpf_exit + * but it will either reach outer most bpf_exit (which means it's safe) + * or it will be rejected. Since there are no loops, we won't be + * seeing this tuple (frame[0].callsite, frame[1].callsite, .. insn_idx) + * again on the way to bpf_exit */ new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL); if (!new_sl) @@ -3756,10 +4329,15 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) * explored_states can get read marks.) */ for (i = 0; i < BPF_REG_FP; i++) - cur->regs[i].live = REG_LIVE_NONE; - for (i = 0; i < cur->allocated_stack / BPF_REG_SIZE; i++) - if (cur->stack[i].slot_type[0] == STACK_SPILL) - cur->stack[i].spilled_ptr.live = REG_LIVE_NONE; + cur->frame[cur->curframe]->regs[i].live = REG_LIVE_NONE; + + /* all stack frames are accessible from callee, clear them all */ + for (j = 0; j <= cur->curframe; j++) { + struct bpf_func_state *frame = cur->frame[j]; + + for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++) + frame->stack[i].spilled_ptr.live = REG_LIVE_NONE; + } return 0; } @@ -3777,7 +4355,7 @@ static int do_check(struct bpf_verifier_env *env) struct bpf_verifier_state *state; struct bpf_insn *insns = env->prog->insnsi; struct bpf_reg_state *regs; - int insn_cnt = env->prog->len; + int insn_cnt = env->prog->len, i; int insn_idx, prev_insn_idx = 0; int insn_processed = 0; bool do_print_state = false; @@ -3785,9 +4363,18 @@ static int do_check(struct bpf_verifier_env *env) state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL); if (!state) return -ENOMEM; - env->cur_state = state; - init_reg_state(env, state->regs); + state->curframe = 0; state->parent = NULL; + state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL); + if (!state->frame[0]) { + kfree(state); + return -ENOMEM; + } + env->cur_state = state; + init_func_state(env, state->frame[0], + BPF_MAIN_FUNC /* callsite */, + 0 /* frameno */, + 0 /* subprogno, zero == main subprog */); insn_idx = 0; for (;;) { struct bpf_insn *insn; @@ -3834,7 +4421,7 @@ static int do_check(struct bpf_verifier_env *env) else verbose(env, "\nfrom %d to %d:", prev_insn_idx, insn_idx); - print_verifier_state(env, state); + print_verifier_state(env, state->frame[state->curframe]); do_print_state = false; } @@ -3967,13 +4554,17 @@ static int do_check(struct bpf_verifier_env *env) if (opcode == BPF_CALL) { if (BPF_SRC(insn->code) != BPF_K || insn->off != 0 || - insn->src_reg != BPF_REG_0 || + (insn->src_reg != BPF_REG_0 && + insn->src_reg != BPF_PSEUDO_CALL) || insn->dst_reg != BPF_REG_0) { verbose(env, "BPF_CALL uses reserved fields\n"); return -EINVAL; } - err = check_call(env, insn->imm, insn_idx); + if (insn->src_reg == BPF_PSEUDO_CALL) + err = check_func_call(env, insn, &insn_idx); + else + err = check_helper_call(env, insn->imm, insn_idx); if (err) return err; @@ -3998,6 +4589,16 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } + if (state->curframe) { + /* exit from nested function */ + prev_insn_idx = insn_idx; + err = prepare_func_exit(env, &insn_idx); + if (err) + return err; + do_print_state = true; + continue; + } + /* eBPF calling convetion is such that R0 is used * to return the value from eBPF program. * Make sure that it's readable at this time @@ -4058,8 +4659,16 @@ process_bpf_exit: insn_idx++; } - verbose(env, "processed %d insns, stack depth %d\n", insn_processed, - env->prog->aux->stack_depth); + verbose(env, "processed %d insns, stack depth ", insn_processed); + for (i = 0; i < env->subprog_cnt + 1; i++) { + u32 depth = env->subprog_stack_depth[i]; + + verbose(env, "%d", depth); + if (i + 1 < env->subprog_cnt + 1) + verbose(env, "+"); + } + verbose(env, "\n"); + env->prog->aux->stack_depth = env->subprog_stack_depth[0]; return 0; } @@ -4245,6 +4854,19 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len, return 0; } +static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len) +{ + int i; + + if (len == 1) + return; + for (i = 0; i < env->subprog_cnt; i++) { + if (env->subprog_starts[i] < off) + continue; + env->subprog_starts[i] += len - 1; + } +} + static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off, const struct bpf_insn *patch, u32 len) { @@ -4255,6 +4877,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of return NULL; if (adjust_insn_aux_data(env, new_prog->len, off, len)) return NULL; + adjust_subprog_starts(env, off, len); return new_prog; } @@ -4389,6 +5012,150 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) return 0; } +static int jit_subprogs(struct bpf_verifier_env *env) +{ + struct bpf_prog *prog = env->prog, **func, *tmp; + int i, j, subprog_start, subprog_end = 0, len, subprog; + struct bpf_insn *insn = prog->insnsi; + void *old_bpf_func; + int err = -ENOMEM; + + if (env->subprog_cnt == 0) + return 0; + + for (i = 0; i < prog->len; i++, insn++) { + if (insn->code != (BPF_JMP | BPF_CALL) || + insn->src_reg != BPF_PSEUDO_CALL) + continue; + subprog = find_subprog(env, i + insn->imm + 1); + if (subprog < 0) { + WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", + i + insn->imm + 1); + return -EFAULT; + } + /* temporarily remember subprog id inside insn instead of + * aux_data, since next loop will split up all insns into funcs + */ + insn->off = subprog + 1; + /* remember original imm in case JIT fails and fallback + * to interpreter will be needed + */ + env->insn_aux_data[i].call_imm = insn->imm; + /* point imm to __bpf_call_base+1 from JITs point of view */ + insn->imm = 1; + } + + func = kzalloc(sizeof(prog) * (env->subprog_cnt + 1), GFP_KERNEL); + if (!func) + return -ENOMEM; + + for (i = 0; i <= env->subprog_cnt; i++) { + subprog_start = subprog_end; + if (env->subprog_cnt == i) + subprog_end = prog->len; + else + subprog_end = env->subprog_starts[i]; + + len = subprog_end - subprog_start; + func[i] = bpf_prog_alloc(bpf_prog_size(len), GFP_USER); + if (!func[i]) + goto out_free; + memcpy(func[i]->insnsi, &prog->insnsi[subprog_start], + len * sizeof(struct bpf_insn)); + func[i]->len = len; + func[i]->is_func = 1; + /* Use bpf_prog_F_tag to indicate functions in stack traces. + * Long term would need debug info to populate names + */ + func[i]->aux->name[0] = 'F'; + func[i]->aux->stack_depth = env->subprog_stack_depth[i]; + func[i]->jit_requested = 1; + func[i] = bpf_int_jit_compile(func[i]); + if (!func[i]->jited) { + err = -ENOTSUPP; + goto out_free; + } + cond_resched(); + } + /* at this point all bpf functions were successfully JITed + * now populate all bpf_calls with correct addresses and + * run last pass of JIT + */ + for (i = 0; i <= env->subprog_cnt; i++) { + insn = func[i]->insnsi; + for (j = 0; j < func[i]->len; j++, insn++) { + if (insn->code != (BPF_JMP | BPF_CALL) || + insn->src_reg != BPF_PSEUDO_CALL) + continue; + subprog = insn->off; + insn->off = 0; + insn->imm = (u64 (*)(u64, u64, u64, u64, u64)) + func[subprog]->bpf_func - + __bpf_call_base; + } + } + for (i = 0; i <= env->subprog_cnt; i++) { + old_bpf_func = func[i]->bpf_func; + tmp = bpf_int_jit_compile(func[i]); + if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) { + verbose(env, "JIT doesn't support bpf-to-bpf calls\n"); + err = -EFAULT; + goto out_free; + } + cond_resched(); + } + + /* finally lock prog and jit images for all functions and + * populate kallsysm + */ + for (i = 0; i <= env->subprog_cnt; i++) { + bpf_prog_lock_ro(func[i]); + bpf_prog_kallsyms_add(func[i]); + } + prog->jited = 1; + prog->bpf_func = func[0]->bpf_func; + prog->aux->func = func; + prog->aux->func_cnt = env->subprog_cnt + 1; + return 0; +out_free: + for (i = 0; i <= env->subprog_cnt; i++) + if (func[i]) + bpf_jit_free(func[i]); + kfree(func); + /* cleanup main prog to be interpreted */ + prog->jit_requested = 0; + for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { + if (insn->code != (BPF_JMP | BPF_CALL) || + insn->src_reg != BPF_PSEUDO_CALL) + continue; + insn->off = 0; + insn->imm = env->insn_aux_data[i].call_imm; + } + return err; +} + +static int fixup_call_args(struct bpf_verifier_env *env) +{ + struct bpf_prog *prog = env->prog; + struct bpf_insn *insn = prog->insnsi; + int i, depth; + + if (env->prog->jit_requested) + if (jit_subprogs(env) == 0) + return 0; + + for (i = 0; i < prog->len; i++, insn++) { + if (insn->code != (BPF_JMP | BPF_CALL) || + insn->src_reg != BPF_PSEUDO_CALL) + continue; + depth = get_callee_stack_depth(env, insn, i); + if (depth < 0) + return depth; + bpf_patch_call_args(insn, depth); + } + return 0; +} + /* fixup insn->imm field of bpf_call instructions * and inline eligible helpers as explicit sequence of BPF instructions * @@ -4408,6 +5175,8 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) for (i = 0; i < insn_cnt; i++, insn++) { if (insn->code != (BPF_JMP | BPF_CALL)) continue; + if (insn->src_reg == BPF_PSEUDO_CALL) + continue; if (insn->imm == BPF_FUNC_get_route_realm) prog->dst_needed = 1; @@ -4437,7 +5206,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) /* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup * handlers are currently limited to 64 bit only. */ - if (ebpf_jit_enabled() && BITS_PER_LONG == 64 && + if (prog->jit_requested && BITS_PER_LONG == 64 && insn->imm == BPF_FUNC_map_lookup_elem) { map_ptr = env->insn_aux_data[i + delta].map_ptr; if (map_ptr == BPF_MAP_PTR_POISON || @@ -4589,12 +5358,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (!env->explored_states) goto skip_full_check; + env->allow_ptr_leaks = capable(CAP_SYS_ADMIN); + ret = check_cfg(env); if (ret < 0) goto skip_full_check; - env->allow_ptr_leaks = capable(CAP_SYS_ADMIN); - ret = do_check(env); if (env->cur_state) { free_verifier_state(env->cur_state, true); @@ -4615,6 +5384,9 @@ skip_full_check: if (ret == 0) ret = fixup_bpf_calls(env); + if (ret == 0) + ret = fixup_call_args(env); + if (log->level && bpf_verifier_log_full(log)) ret = -ENOSPC; if (log->level && !log->ubuf) { diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index cf446c25c0ec..db1b0923a308 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -197,8 +197,14 @@ enum bpf_attach_type { */ #define BPF_F_STRICT_ALIGNMENT (1U << 0) +/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */ #define BPF_PSEUDO_MAP_FD 1 +/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative + * offset to another bpf function + */ +#define BPF_PSEUDO_CALL 1 + /* flags for BPF_MAP_UPDATE_ELEM command */ #define BPF_ANY 0 /* create new element or update existing */ #define BPF_NOEXIST 1 /* create new element if it didn't exist */ diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 6534889e2b2f..9f44c196931e 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -40,7 +40,7 @@ int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name, __u32 map_flags); /* Recommend log buffer size */ -#define BPF_LOG_BUF_SIZE 65536 +#define BPF_LOG_BUF_SIZE (256 * 1024) int bpf_load_program_name(enum bpf_prog_type type, const char *name, const struct bpf_insn *insns, size_t insns_cnt, const char *license, diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 65d0d0aff4fa..5b83875b3594 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -174,12 +174,19 @@ struct bpf_program { char *name; char *section_name; struct bpf_insn *insns; - size_t insns_cnt; + size_t insns_cnt, main_prog_cnt; enum bpf_prog_type type; - struct { + struct reloc_desc { + enum { + RELO_LD64, + RELO_CALL, + } type; int insn_idx; - int map_idx; + union { + int map_idx; + int text_off; + }; } *reloc_desc; int nr_reloc; @@ -234,6 +241,7 @@ struct bpf_object { } *reloc; int nr_reloc; int maps_shndx; + int text_shndx; } efile; /* * All loaded bpf_object is linked in a list, which is @@ -375,9 +383,13 @@ bpf_object__init_prog_names(struct bpf_object *obj) size_t pi, si; for (pi = 0; pi < obj->nr_programs; pi++) { - char *name = NULL; + const char *name = NULL; prog = &obj->programs[pi]; + if (prog->idx == obj->efile.text_shndx) { + name = ".text"; + goto skip_search; + } for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name; si++) { @@ -405,7 +417,7 @@ bpf_object__init_prog_names(struct bpf_object *obj) prog->section_name); return -EINVAL; } - +skip_search: prog->name = strdup(name); if (!prog->name) { pr_warning("failed to allocate memory for prog sym %s\n", @@ -795,6 +807,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj) } else if ((sh.sh_type == SHT_PROGBITS) && (sh.sh_flags & SHF_EXECINSTR) && (data->d_size > 0)) { + if (strcmp(name, ".text") == 0) + obj->efile.text_shndx = idx; err = bpf_object__add_program(obj, data->d_buf, data->d_size, name, idx); if (err) { @@ -856,11 +870,14 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx) } static int -bpf_program__collect_reloc(struct bpf_program *prog, - size_t nr_maps, GElf_Shdr *shdr, - Elf_Data *data, Elf_Data *symbols, - int maps_shndx, struct bpf_map *maps) +bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, + Elf_Data *data, struct bpf_object *obj) { + Elf_Data *symbols = obj->efile.symbols; + int text_shndx = obj->efile.text_shndx; + int maps_shndx = obj->efile.maps_shndx; + struct bpf_map *maps = obj->maps; + size_t nr_maps = obj->nr_maps; int i, nrels; pr_debug("collecting relocating info for: '%s'\n", @@ -893,8 +910,10 @@ bpf_program__collect_reloc(struct bpf_program *prog, GELF_R_SYM(rel.r_info)); return -LIBBPF_ERRNO__FORMAT; } + pr_debug("relo for %ld value %ld name %d\n", + rel.r_info >> 32, sym.st_value, sym.st_name); - if (sym.st_shndx != maps_shndx) { + if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) { pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n", prog->section_name, sym.st_shndx); return -LIBBPF_ERRNO__RELOC; @@ -903,6 +922,17 @@ bpf_program__collect_reloc(struct bpf_program *prog, insn_idx = rel.r_offset / sizeof(struct bpf_insn); pr_debug("relocation: insn_idx=%u\n", insn_idx); + if (insns[insn_idx].code == (BPF_JMP | BPF_CALL)) { + if (insns[insn_idx].src_reg != BPF_PSEUDO_CALL) { + pr_warning("incorrect bpf_call opcode\n"); + return -LIBBPF_ERRNO__RELOC; + } + prog->reloc_desc[i].type = RELO_CALL; + prog->reloc_desc[i].insn_idx = insn_idx; + prog->reloc_desc[i].text_off = sym.st_value; + continue; + } + if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) { pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n", insn_idx, insns[insn_idx].code); @@ -924,6 +954,7 @@ bpf_program__collect_reloc(struct bpf_program *prog, return -LIBBPF_ERRNO__RELOC; } + prog->reloc_desc[i].type = RELO_LD64; prog->reloc_desc[i].insn_idx = insn_idx; prog->reloc_desc[i].map_idx = map_idx; } @@ -962,28 +993,77 @@ bpf_object__create_maps(struct bpf_object *obj) return 0; } +static int +bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, + struct reloc_desc *relo) +{ + struct bpf_insn *insn, *new_insn; + struct bpf_program *text; + size_t new_cnt; + + if (relo->type != RELO_CALL) + return -LIBBPF_ERRNO__RELOC; + + if (prog->idx == obj->efile.text_shndx) { + pr_warning("relo in .text insn %d into off %d\n", + relo->insn_idx, relo->text_off); + return -LIBBPF_ERRNO__RELOC; + } + + if (prog->main_prog_cnt == 0) { + text = bpf_object__find_prog_by_idx(obj, obj->efile.text_shndx); + if (!text) { + pr_warning("no .text section found yet relo into text exist\n"); + return -LIBBPF_ERRNO__RELOC; + } + new_cnt = prog->insns_cnt + text->insns_cnt; + new_insn = realloc(prog->insns, new_cnt * sizeof(*insn)); + if (!new_insn) { + pr_warning("oom in prog realloc\n"); + return -ENOMEM; + } + memcpy(new_insn + prog->insns_cnt, text->insns, + text->insns_cnt * sizeof(*insn)); + prog->insns = new_insn; + prog->main_prog_cnt = prog->insns_cnt; + prog->insns_cnt = new_cnt; + } + insn = &prog->insns[relo->insn_idx]; + insn->imm += prog->main_prog_cnt - relo->insn_idx; + pr_debug("added %zd insn from %s to prog %s\n", + text->insns_cnt, text->section_name, prog->section_name); + return 0; +} + static int bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) { - int i; + int i, err; if (!prog || !prog->reloc_desc) return 0; for (i = 0; i < prog->nr_reloc; i++) { - int insn_idx, map_idx; - struct bpf_insn *insns = prog->insns; + if (prog->reloc_desc[i].type == RELO_LD64) { + struct bpf_insn *insns = prog->insns; + int insn_idx, map_idx; - insn_idx = prog->reloc_desc[i].insn_idx; - map_idx = prog->reloc_desc[i].map_idx; + insn_idx = prog->reloc_desc[i].insn_idx; + map_idx = prog->reloc_desc[i].map_idx; - if (insn_idx >= (int)prog->insns_cnt) { - pr_warning("relocation out of range: '%s'\n", - prog->section_name); - return -LIBBPF_ERRNO__RELOC; + if (insn_idx >= (int)prog->insns_cnt) { + pr_warning("relocation out of range: '%s'\n", + prog->section_name); + return -LIBBPF_ERRNO__RELOC; + } + insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; + insns[insn_idx].imm = obj->maps[map_idx].fd; + } else { + err = bpf_program__reloc_text(prog, obj, + &prog->reloc_desc[i]); + if (err) + return err; } - insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; - insns[insn_idx].imm = obj->maps[map_idx].fd; } zfree(&prog->reloc_desc); @@ -1026,7 +1106,6 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) Elf_Data *data = obj->efile.reloc[i].data; int idx = shdr->sh_info; struct bpf_program *prog; - size_t nr_maps = obj->nr_maps; if (shdr->sh_type != SHT_REL) { pr_warning("internal error at %d\n", __LINE__); @@ -1040,11 +1119,9 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) return -LIBBPF_ERRNO__RELOC; } - err = bpf_program__collect_reloc(prog, nr_maps, + err = bpf_program__collect_reloc(prog, shdr, data, - obj->efile.symbols, - obj->efile.maps_shndx, - obj->maps); + obj); if (err) return err; } @@ -1197,6 +1274,8 @@ bpf_object__load_progs(struct bpf_object *obj) int err; for (i = 0; i < obj->nr_programs; i++) { + if (obj->programs[i].idx == obj->efile.text_shndx) + continue; err = bpf_program__load(&obj->programs[i], obj->license, obj->kern_version); @@ -1859,7 +1938,7 @@ long libbpf_get_error(const void *ptr) int bpf_prog_load(const char *file, enum bpf_prog_type type, struct bpf_object **pobj, int *prog_fd) { - struct bpf_program *prog; + struct bpf_program *prog, *first_prog = NULL; struct bpf_object *obj; int err; @@ -1867,25 +1946,30 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type, if (IS_ERR(obj)) return -ENOENT; - prog = bpf_program__next(NULL, obj); - if (!prog) { + bpf_object__for_each_program(prog, obj) { + /* + * If type is not specified, try to guess it based on + * section name. + */ + if (type == BPF_PROG_TYPE_UNSPEC) { + type = bpf_program__guess_type(prog); + if (type == BPF_PROG_TYPE_UNSPEC) { + bpf_object__close(obj); + return -EINVAL; + } + } + + bpf_program__set_type(prog, type); + if (prog->idx != obj->efile.text_shndx && !first_prog) + first_prog = prog; + } + + if (!first_prog) { + pr_warning("object file doesn't contain bpf program\n"); bpf_object__close(obj); return -ENOENT; } - /* - * If type is not specified, try to guess it based on - * section name. - */ - if (type == BPF_PROG_TYPE_UNSPEC) { - type = bpf_program__guess_type(prog); - if (type == BPF_PROG_TYPE_UNSPEC) { - bpf_object__close(obj); - return -EINVAL; - } - } - - bpf_program__set_type(prog, type); err = bpf_object__load(obj); if (err) { bpf_object__close(obj); @@ -1893,6 +1977,6 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type, } *pobj = obj; - *prog_fd = bpf_program__fd(prog); + *prog_fd = bpf_program__fd(first_prog); return 0; } diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 255fb1f50f6b..7ef9601d04bf 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -17,7 +17,8 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \ test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \ - sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o + sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \ + test_l4lb_noinline.o test_xdp_noinline.o TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh \ test_offload.py @@ -49,8 +50,13 @@ else CPU ?= generic endif +CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \ + -Wno-compare-distinct-pointer-types + +$(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline +$(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline + %.o: %.c - $(CLANG) -I. -I./include/uapi -I../../../include/uapi \ - -Wno-compare-distinct-pointer-types \ + $(CLANG) $(CLANG_FLAGS) \ -O2 -target bpf -emit-llvm -c $< -o - | \ $(LLC) -march=bpf -mcpu=$(CPU) -filetype=obj -o $@ diff --git a/tools/testing/selftests/bpf/test_l4lb_noinline.c b/tools/testing/selftests/bpf/test_l4lb_noinline.c new file mode 100644 index 000000000000..ba44a14e6dc4 --- /dev/null +++ b/tools/testing/selftests/bpf/test_l4lb_noinline.c @@ -0,0 +1,473 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017 Facebook +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "bpf_helpers.h" +#include "test_iptunnel_common.h" +#include "bpf_endian.h" + +int _version SEC("version") = 1; + +static __u32 rol32(__u32 word, unsigned int shift) +{ + return (word << shift) | (word >> ((-shift) & 31)); +} + +/* copy paste of jhash from kernel sources to make sure llvm + * can compile it into valid sequence of bpf instructions + */ +#define __jhash_mix(a, b, c) \ +{ \ + a -= c; a ^= rol32(c, 4); c += b; \ + b -= a; b ^= rol32(a, 6); a += c; \ + c -= b; c ^= rol32(b, 8); b += a; \ + a -= c; a ^= rol32(c, 16); c += b; \ + b -= a; b ^= rol32(a, 19); a += c; \ + c -= b; c ^= rol32(b, 4); b += a; \ +} + +#define __jhash_final(a, b, c) \ +{ \ + c ^= b; c -= rol32(b, 14); \ + a ^= c; a -= rol32(c, 11); \ + b ^= a; b -= rol32(a, 25); \ + c ^= b; c -= rol32(b, 16); \ + a ^= c; a -= rol32(c, 4); \ + b ^= a; b -= rol32(a, 14); \ + c ^= b; c -= rol32(b, 24); \ +} + +#define JHASH_INITVAL 0xdeadbeef + +typedef unsigned int u32; + +static u32 jhash(const void *key, u32 length, u32 initval) +{ + u32 a, b, c; + const unsigned char *k = key; + + a = b = c = JHASH_INITVAL + length + initval; + + while (length > 12) { + a += *(u32 *)(k); + b += *(u32 *)(k + 4); + c += *(u32 *)(k + 8); + __jhash_mix(a, b, c); + length -= 12; + k += 12; + } + switch (length) { + case 12: c += (u32)k[11]<<24; + case 11: c += (u32)k[10]<<16; + case 10: c += (u32)k[9]<<8; + case 9: c += k[8]; + case 8: b += (u32)k[7]<<24; + case 7: b += (u32)k[6]<<16; + case 6: b += (u32)k[5]<<8; + case 5: b += k[4]; + case 4: a += (u32)k[3]<<24; + case 3: a += (u32)k[2]<<16; + case 2: a += (u32)k[1]<<8; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } + + return c; +} + +static u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) +{ + a += initval; + b += initval; + c += initval; + __jhash_final(a, b, c); + return c; +} + +static u32 jhash_2words(u32 a, u32 b, u32 initval) +{ + return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); +} + +#define PCKT_FRAGMENTED 65343 +#define IPV4_HDR_LEN_NO_OPT 20 +#define IPV4_PLUS_ICMP_HDR 28 +#define IPV6_PLUS_ICMP_HDR 48 +#define RING_SIZE 2 +#define MAX_VIPS 12 +#define MAX_REALS 5 +#define CTL_MAP_SIZE 16 +#define CH_RINGS_SIZE (MAX_VIPS * RING_SIZE) +#define F_IPV6 (1 << 0) +#define F_HASH_NO_SRC_PORT (1 << 0) +#define F_ICMP (1 << 0) +#define F_SYN_SET (1 << 1) + +struct packet_description { + union { + __be32 src; + __be32 srcv6[4]; + }; + union { + __be32 dst; + __be32 dstv6[4]; + }; + union { + __u32 ports; + __u16 port16[2]; + }; + __u8 proto; + __u8 flags; +}; + +struct ctl_value { + union { + __u64 value; + __u32 ifindex; + __u8 mac[6]; + }; +}; + +struct vip_meta { + __u32 flags; + __u32 vip_num; +}; + +struct real_definition { + union { + __be32 dst; + __be32 dstv6[4]; + }; + __u8 flags; +}; + +struct vip_stats { + __u64 bytes; + __u64 pkts; +}; + +struct eth_hdr { + unsigned char eth_dest[ETH_ALEN]; + unsigned char eth_source[ETH_ALEN]; + unsigned short eth_proto; +}; + +struct bpf_map_def SEC("maps") vip_map = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(struct vip), + .value_size = sizeof(struct vip_meta), + .max_entries = MAX_VIPS, +}; + +struct bpf_map_def SEC("maps") ch_rings = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u32), + .max_entries = CH_RINGS_SIZE, +}; + +struct bpf_map_def SEC("maps") reals = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct real_definition), + .max_entries = MAX_REALS, +}; + +struct bpf_map_def SEC("maps") stats = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct vip_stats), + .max_entries = MAX_VIPS, +}; + +struct bpf_map_def SEC("maps") ctl_array = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct ctl_value), + .max_entries = CTL_MAP_SIZE, +}; + +static __u32 get_packet_hash(struct packet_description *pckt, + bool ipv6) +{ + if (ipv6) + return jhash_2words(jhash(pckt->srcv6, 16, MAX_VIPS), + pckt->ports, CH_RINGS_SIZE); + else + return jhash_2words(pckt->src, pckt->ports, CH_RINGS_SIZE); +} + +static bool get_packet_dst(struct real_definition **real, + struct packet_description *pckt, + struct vip_meta *vip_info, + bool is_ipv6) +{ + __u32 hash = get_packet_hash(pckt, is_ipv6); + __u32 key = RING_SIZE * vip_info->vip_num + hash % RING_SIZE; + __u32 *real_pos; + + if (hash != 0x358459b7 /* jhash of ipv4 packet */ && + hash != 0x2f4bc6bb /* jhash of ipv6 packet */) + return 0; + + real_pos = bpf_map_lookup_elem(&ch_rings, &key); + if (!real_pos) + return false; + key = *real_pos; + *real = bpf_map_lookup_elem(&reals, &key); + if (!(*real)) + return false; + return true; +} + +static int parse_icmpv6(void *data, void *data_end, __u64 off, + struct packet_description *pckt) +{ + struct icmp6hdr *icmp_hdr; + struct ipv6hdr *ip6h; + + icmp_hdr = data + off; + if (icmp_hdr + 1 > data_end) + return TC_ACT_SHOT; + if (icmp_hdr->icmp6_type != ICMPV6_PKT_TOOBIG) + return TC_ACT_OK; + off += sizeof(struct icmp6hdr); + ip6h = data + off; + if (ip6h + 1 > data_end) + return TC_ACT_SHOT; + pckt->proto = ip6h->nexthdr; + pckt->flags |= F_ICMP; + memcpy(pckt->srcv6, ip6h->daddr.s6_addr32, 16); + memcpy(pckt->dstv6, ip6h->saddr.s6_addr32, 16); + return TC_ACT_UNSPEC; +} + +static int parse_icmp(void *data, void *data_end, __u64 off, + struct packet_description *pckt) +{ + struct icmphdr *icmp_hdr; + struct iphdr *iph; + + icmp_hdr = data + off; + if (icmp_hdr + 1 > data_end) + return TC_ACT_SHOT; + if (icmp_hdr->type != ICMP_DEST_UNREACH || + icmp_hdr->code != ICMP_FRAG_NEEDED) + return TC_ACT_OK; + off += sizeof(struct icmphdr); + iph = data + off; + if (iph + 1 > data_end) + return TC_ACT_SHOT; + if (iph->ihl != 5) + return TC_ACT_SHOT; + pckt->proto = iph->protocol; + pckt->flags |= F_ICMP; + pckt->src = iph->daddr; + pckt->dst = iph->saddr; + return TC_ACT_UNSPEC; +} + +static bool parse_udp(void *data, __u64 off, void *data_end, + struct packet_description *pckt) +{ + struct udphdr *udp; + udp = data + off; + + if (udp + 1 > data_end) + return false; + + if (!(pckt->flags & F_ICMP)) { + pckt->port16[0] = udp->source; + pckt->port16[1] = udp->dest; + } else { + pckt->port16[0] = udp->dest; + pckt->port16[1] = udp->source; + } + return true; +} + +static bool parse_tcp(void *data, __u64 off, void *data_end, + struct packet_description *pckt) +{ + struct tcphdr *tcp; + + tcp = data + off; + if (tcp + 1 > data_end) + return false; + + if (tcp->syn) + pckt->flags |= F_SYN_SET; + + if (!(pckt->flags & F_ICMP)) { + pckt->port16[0] = tcp->source; + pckt->port16[1] = tcp->dest; + } else { + pckt->port16[0] = tcp->dest; + pckt->port16[1] = tcp->source; + } + return true; +} + +static int process_packet(void *data, __u64 off, void *data_end, + bool is_ipv6, struct __sk_buff *skb) +{ + void *pkt_start = (void *)(long)skb->data; + struct packet_description pckt = {}; + struct eth_hdr *eth = pkt_start; + struct bpf_tunnel_key tkey = {}; + struct vip_stats *data_stats; + struct real_definition *dst; + struct vip_meta *vip_info; + struct ctl_value *cval; + __u32 v4_intf_pos = 1; + __u32 v6_intf_pos = 2; + struct ipv6hdr *ip6h; + struct vip vip = {}; + struct iphdr *iph; + int tun_flag = 0; + __u16 pkt_bytes; + __u64 iph_len; + __u32 ifindex; + __u8 protocol; + __u32 vip_num; + int action; + + tkey.tunnel_ttl = 64; + if (is_ipv6) { + ip6h = data + off; + if (ip6h + 1 > data_end) + return TC_ACT_SHOT; + + iph_len = sizeof(struct ipv6hdr); + protocol = ip6h->nexthdr; + pckt.proto = protocol; + pkt_bytes = bpf_ntohs(ip6h->payload_len); + off += iph_len; + if (protocol == IPPROTO_FRAGMENT) { + return TC_ACT_SHOT; + } else if (protocol == IPPROTO_ICMPV6) { + action = parse_icmpv6(data, data_end, off, &pckt); + if (action >= 0) + return action; + off += IPV6_PLUS_ICMP_HDR; + } else { + memcpy(pckt.srcv6, ip6h->saddr.s6_addr32, 16); + memcpy(pckt.dstv6, ip6h->daddr.s6_addr32, 16); + } + } else { + iph = data + off; + if (iph + 1 > data_end) + return TC_ACT_SHOT; + if (iph->ihl != 5) + return TC_ACT_SHOT; + + protocol = iph->protocol; + pckt.proto = protocol; + pkt_bytes = bpf_ntohs(iph->tot_len); + off += IPV4_HDR_LEN_NO_OPT; + + if (iph->frag_off & PCKT_FRAGMENTED) + return TC_ACT_SHOT; + if (protocol == IPPROTO_ICMP) { + action = parse_icmp(data, data_end, off, &pckt); + if (action >= 0) + return action; + off += IPV4_PLUS_ICMP_HDR; + } else { + pckt.src = iph->saddr; + pckt.dst = iph->daddr; + } + } + protocol = pckt.proto; + + if (protocol == IPPROTO_TCP) { + if (!parse_tcp(data, off, data_end, &pckt)) + return TC_ACT_SHOT; + } else if (protocol == IPPROTO_UDP) { + if (!parse_udp(data, off, data_end, &pckt)) + return TC_ACT_SHOT; + } else { + return TC_ACT_SHOT; + } + + if (is_ipv6) + memcpy(vip.daddr.v6, pckt.dstv6, 16); + else + vip.daddr.v4 = pckt.dst; + + vip.dport = pckt.port16[1]; + vip.protocol = pckt.proto; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) { + vip.dport = 0; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) + return TC_ACT_SHOT; + pckt.port16[1] = 0; + } + + if (vip_info->flags & F_HASH_NO_SRC_PORT) + pckt.port16[0] = 0; + + if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6)) + return TC_ACT_SHOT; + + if (dst->flags & F_IPV6) { + cval = bpf_map_lookup_elem(&ctl_array, &v6_intf_pos); + if (!cval) + return TC_ACT_SHOT; + ifindex = cval->ifindex; + memcpy(tkey.remote_ipv6, dst->dstv6, 16); + tun_flag = BPF_F_TUNINFO_IPV6; + } else { + cval = bpf_map_lookup_elem(&ctl_array, &v4_intf_pos); + if (!cval) + return TC_ACT_SHOT; + ifindex = cval->ifindex; + tkey.remote_ipv4 = dst->dst; + } + vip_num = vip_info->vip_num; + data_stats = bpf_map_lookup_elem(&stats, &vip_num); + if (!data_stats) + return TC_ACT_SHOT; + data_stats->pkts++; + data_stats->bytes += pkt_bytes; + bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), tun_flag); + *(u32 *)eth->eth_dest = tkey.remote_ipv4; + return bpf_redirect(ifindex, 0); +} + +SEC("l4lb-demo") +int balancer_ingress(struct __sk_buff *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct eth_hdr *eth = data; + __u32 eth_proto; + __u32 nh_off; + + nh_off = sizeof(struct eth_hdr); + if (data + nh_off > data_end) + return TC_ACT_SHOT; + eth_proto = eth->eth_proto; + if (eth_proto == bpf_htons(ETH_P_IP)) + return process_packet(data, nh_off, data_end, false, ctx); + else if (eth_proto == bpf_htons(ETH_P_IPV6)) + return process_packet(data, nh_off, data_end, true, ctx); + else + return TC_ACT_SHOT; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 1d7d2149163a..6472ca98690e 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -169,10 +169,9 @@ out: #define NUM_ITER 100000 #define VIP_NUM 5 -static void test_l4lb(void) +static void test_l4lb(const char *file) { unsigned int nr_cpus = bpf_num_possible_cpus(); - const char *file = "./test_l4lb.o"; struct vip key = {.protocol = 6}; struct vip_meta { __u32 flags; @@ -249,6 +248,95 @@ out: bpf_object__close(obj); } +static void test_l4lb_all(void) +{ + const char *file1 = "./test_l4lb.o"; + const char *file2 = "./test_l4lb_noinline.o"; + + test_l4lb(file1); + test_l4lb(file2); +} + +static void test_xdp_noinline(void) +{ + const char *file = "./test_xdp_noinline.o"; + unsigned int nr_cpus = bpf_num_possible_cpus(); + struct vip key = {.protocol = 6}; + struct vip_meta { + __u32 flags; + __u32 vip_num; + } value = {.vip_num = VIP_NUM}; + __u32 stats_key = VIP_NUM; + struct vip_stats { + __u64 bytes; + __u64 pkts; + } stats[nr_cpus]; + struct real_definition { + union { + __be32 dst; + __be32 dstv6[4]; + }; + __u8 flags; + } real_def = {.dst = MAGIC_VAL}; + __u32 ch_key = 11, real_num = 3; + __u32 duration, retval, size; + int err, i, prog_fd, map_fd; + __u64 bytes = 0, pkts = 0; + struct bpf_object *obj; + char buf[128]; + u32 *magic = (u32 *)buf; + + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + if (err) { + error_cnt++; + return; + } + + map_fd = bpf_find_map(__func__, obj, "vip_map"); + if (map_fd < 0) + goto out; + bpf_map_update_elem(map_fd, &key, &value, 0); + + map_fd = bpf_find_map(__func__, obj, "ch_rings"); + if (map_fd < 0) + goto out; + bpf_map_update_elem(map_fd, &ch_key, &real_num, 0); + + map_fd = bpf_find_map(__func__, obj, "reals"); + if (map_fd < 0) + goto out; + bpf_map_update_elem(map_fd, &real_num, &real_def, 0); + + err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4), + buf, &size, &retval, &duration); + CHECK(err || errno || retval != 1 || size != 54 || + *magic != MAGIC_VAL, "ipv4", + "err %d errno %d retval %d size %d magic %x\n", + err, errno, retval, size, *magic); + + err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6), + buf, &size, &retval, &duration); + CHECK(err || errno || retval != 1 || size != 74 || + *magic != MAGIC_VAL, "ipv6", + "err %d errno %d retval %d size %d magic %x\n", + err, errno, retval, size, *magic); + + map_fd = bpf_find_map(__func__, obj, "stats"); + if (map_fd < 0) + goto out; + bpf_map_lookup_elem(map_fd, &stats_key, stats); + for (i = 0; i < nr_cpus; i++) { + bytes += stats[i].bytes; + pkts += stats[i].pkts; + } + if (bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2) { + error_cnt++; + printf("test_xdp_noinline:FAIL:stats %lld %lld\n", bytes, pkts); + } +out: + bpf_object__close(obj); +} + static void test_tcp_estats(void) { const char *file = "./test_tcp_estats.o"; @@ -757,7 +845,8 @@ int main(void) test_pkt_access(); test_xdp(); - test_l4lb(); + test_l4lb_all(); + test_xdp_noinline(); test_tcp_estats(); test_bpf_obj_id(); test_pkt_md_access(); diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 3c64f30cf63c..3bacff0d6f91 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -2,6 +2,7 @@ * Testsuite for eBPF verifier * * Copyright (c) 2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2017 Facebook * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -277,7 +278,7 @@ static struct bpf_test tests[] = { .insns = { BPF_ALU64_REG(BPF_MOV, BPF_REG_0, BPF_REG_2), }, - .errstr = "jump out of range", + .errstr = "not an exit", .result = REJECT, }, { @@ -5648,7 +5649,7 @@ static struct bpf_test tests[] = { "helper access to variable memory: size > 0 not allowed on NULL (ARG_PTR_TO_MEM_OR_NULL)", .insns = { BPF_MOV64_IMM(BPF_REG_1, 0), - BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_2, 1), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64), @@ -5883,7 +5884,7 @@ static struct bpf_test tests[] = { BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), - BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_2, 1), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 63), @@ -8097,6 +8098,1623 @@ static struct bpf_test tests[] = { .result = REJECT, .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, }, + { + "calls: basic sanity", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .result = ACCEPT, + }, + { + "calls: not on unpriviledged", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "calls: overlapping caller/callee", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "last insn is not an exit or jmp", + .result = REJECT, + }, + { + "calls: wrong recursive calls", + .insns = { + BPF_JMP_IMM(BPF_JA, 0, 0, 4), + BPF_JMP_IMM(BPF_JA, 0, 0, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "jump out of range", + .result = REJECT, + }, + { + "calls: wrong src reg", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 2, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "BPF_CALL uses reserved fields", + .result = REJECT, + }, + { + "calls: wrong off value", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, -1, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "BPF_CALL uses reserved fields", + .result = REJECT, + }, + { + "calls: jump back loop", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "back-edge from insn 0 to 0", + .result = REJECT, + }, + { + "calls: conditional call", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "jump out of range", + .result = REJECT, + }, + { + "calls: conditional call 2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 3), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .result = ACCEPT, + }, + { + "calls: conditional call 3", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_JMP_IMM(BPF_JA, 0, 0, 4), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, -6), + BPF_MOV64_IMM(BPF_REG_0, 3), + BPF_JMP_IMM(BPF_JA, 0, 0, -6), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "back-edge from insn", + .result = REJECT, + }, + { + "calls: conditional call 4", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, -5), + BPF_MOV64_IMM(BPF_REG_0, 3), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .result = ACCEPT, + }, + { + "calls: conditional call 5", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, -6), + BPF_MOV64_IMM(BPF_REG_0, 3), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "back-edge from insn", + .result = REJECT, + }, + { + "calls: conditional call 6", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -2), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "back-edge from insn", + .result = REJECT, + }, + { + "calls: using r0 returned by callee", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .result = ACCEPT, + }, + { + "calls: using uninit r0 from callee", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "!read_ok", + .result = REJECT, + }, + { + "calls: callee is using r1", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_ACT, + .result = ACCEPT, + }, + { + "calls: callee using args1", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "allowed for root only", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "calls: callee using wrong args2", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "R2 !read_ok", + .result = REJECT, + }, + { + "calls: callee using two args", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6, + offsetof(struct __sk_buff, len)), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_6, + offsetof(struct __sk_buff, len)), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "allowed for root only", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "calls: callee changing pkt pointers", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_8, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_8, BPF_REG_7, 2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + /* clear_all_pkt_pointers() has to walk all frames + * to make sure that pkt pointers in the caller + * are cleared when callee is calling a helper that + * adjusts packet size + */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_xdp_adjust_head), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "R6 invalid mem access 'inv'", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "calls: two calls with args", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 6), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_7), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "calls: calls with stack arith", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -64), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -64), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -64), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "calls: calls with misaligned stack access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -63), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -61), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -63), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, + .errstr = "misaligned stack access", + .result = REJECT, + }, + { + "calls: calls control flow, jump test", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 43), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, -3), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "calls: calls control flow, jump test 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 43), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -3), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "jump out of range from insn 1 to 4", + .result = REJECT, + }, + { + "calls: two calls with bad jump", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 6), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_7), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -3), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "jump out of range from insn 11 to 9", + .result = REJECT, + }, + { + "calls: recursive call. test1", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -1), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "back-edge", + .result = REJECT, + }, + { + "calls: recursive call. test2", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -3), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "back-edge", + .result = REJECT, + }, + { + "calls: unreachable code", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "unreachable insn 6", + .result = REJECT, + }, + { + "calls: invalid call", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -4), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "invalid destination", + .result = REJECT, + }, + { + "calls: invalid call 2", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 0x7fffffff), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "invalid destination", + .result = REJECT, + }, + { + "calls: jumping across function bodies. test1", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, -3), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "jump out of range", + .result = REJECT, + }, + { + "calls: jumping across function bodies. test2", + .insns = { + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "jump out of range", + .result = REJECT, + }, + { + "calls: call without exit", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, -2), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "not an exit", + .result = REJECT, + }, + { + "calls: call into middle of ld_imm64", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "last insn", + .result = REJECT, + }, + { + "calls: call into middle of other call", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "last insn", + .result = REJECT, + }, + { + "calls: ld_abs with changing ctx data in callee", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_B, 0), + BPF_LD_ABS(BPF_H, 0), + BPF_LD_ABS(BPF_W, 0), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_6), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_7), + BPF_LD_ABS(BPF_B, 0), + BPF_LD_ABS(BPF_H, 0), + BPF_LD_ABS(BPF_W, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_2, 1), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_vlan_push), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "BPF_LD_[ABS|IND] instructions cannot be mixed", + .result = REJECT, + }, + { + "calls: two calls with bad fallthrough", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 6), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_7), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .errstr = "not an exit", + .result = REJECT, + }, + { + "calls: two calls with stack read", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 6), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_7), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_XDP, + .result = ACCEPT, + }, + { + "calls: two calls with stack write", + .insns = { + /* main prog */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -16), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 7), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_8), + /* write into stack frame of main prog */ + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_EXIT_INSN(), + + /* subprog 2 */ + /* read from stack frame of main prog */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_XDP, + .result = ACCEPT, + }, + { + "calls: spill into caller stack frame", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_XDP, + .errstr = "cannot spill", + .result = REJECT, + }, + { + "calls: write into caller stack frame", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_XDP, + .result = ACCEPT, + }, + { + "calls: write into callee stack frame", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, -8), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_XDP, + .errstr = "cannot return stack pointer", + .result = REJECT, + }, + { + "calls: two calls with stack write and void return", + .insns = { + /* main prog */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -16), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + + /* subprog 2 */ + /* write into stack frame of main prog */ + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0), + BPF_EXIT_INSN(), /* void return */ + }, + .prog_type = BPF_PROG_TYPE_XDP, + .result = ACCEPT, + }, + { + "calls: ambiguous return value", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "allowed for root only", + .result_unpriv = REJECT, + .errstr = "R0 !read_ok", + .result = REJECT, + }, + { + "calls: two calls that return map_value", + .insns = { + /* main prog */ + /* pass fp-16, fp-8 into a function */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 8), + + /* fetch map_value_ptr from the stack of this function */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + /* write into map value */ + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + /* fetch secound map_value_ptr from the stack */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -16), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + /* write into map value */ + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + /* call 3rd function twice */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_2), + /* first time with fp-8 */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + /* second time with fp-16 */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + + /* subprog 2 */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + /* lookup from map */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + /* write map_value_ptr into stack frame of main prog */ + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), /* return 0 */ + }, + .prog_type = BPF_PROG_TYPE_XDP, + .fixup_map1 = { 23 }, + .result = ACCEPT, + }, + { + "calls: two calls that return map_value with bool condition", + .insns = { + /* main prog */ + /* pass fp-16, fp-8 into a function */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + /* call 3rd function twice */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_2), + /* first time with fp-8 */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 9), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + /* fetch map_value_ptr from the stack of this function */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + /* write into map value */ + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + /* second time with fp-16 */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + /* fetch secound map_value_ptr from the stack */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0), + /* write into map value */ + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + BPF_EXIT_INSN(), + + /* subprog 2 */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + /* lookup from map */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), /* return 0 */ + /* write map_value_ptr into stack frame of main prog */ + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), /* return 1 */ + }, + .prog_type = BPF_PROG_TYPE_XDP, + .fixup_map1 = { 23 }, + .result = ACCEPT, + }, + { + "calls: two calls that return map_value with incorrect bool check", + .insns = { + /* main prog */ + /* pass fp-16, fp-8 into a function */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + /* call 3rd function twice */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_2), + /* first time with fp-8 */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 9), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + /* fetch map_value_ptr from the stack of this function */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + /* write into map value */ + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + /* second time with fp-16 */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + /* fetch secound map_value_ptr from the stack */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0), + /* write into map value */ + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + BPF_EXIT_INSN(), + + /* subprog 2 */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + /* lookup from map */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), /* return 0 */ + /* write map_value_ptr into stack frame of main prog */ + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), /* return 1 */ + }, + .prog_type = BPF_PROG_TYPE_XDP, + .fixup_map1 = { 23 }, + .result = REJECT, + .errstr = "invalid read from stack off -16+0 size 8", + }, + { + "calls: two calls that receive map_value via arg=ptr_stack_of_caller. test1", + .insns = { + /* main prog */ + /* pass fp-16, fp-8 into a function */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_2), + /* 1st lookup from map */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_8, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + /* write map_value_ptr into stack frame of main prog at fp-8 */ + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_8, 1), + + /* 2nd lookup from map */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), /* 20 */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, /* 24 */ + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_9, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + /* write map_value_ptr into stack frame of main prog at fp-16 */ + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_9, 1), + + /* call 3rd func with fp-8, 0|1, fp-16, 0|1 */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), /* 30 */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_8), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_7), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_9), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), /* 34 */ + BPF_EXIT_INSN(), + + /* subprog 2 */ + /* if arg2 == 1 do *arg1 = 0 */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 1, 2), + /* fetch map_value_ptr from the stack of this function */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0), + /* write into map value */ + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + + /* if arg4 == 1 do *arg3 = 0 */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_4, 1, 2), + /* fetch map_value_ptr from the stack of this function */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0), + /* write into map value */ + BPF_ST_MEM(BPF_DW, BPF_REG_0, 2, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_map1 = { 12, 22 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=8 off=2 size=8", + }, + { + "calls: two calls that receive map_value via arg=ptr_stack_of_caller. test2", + .insns = { + /* main prog */ + /* pass fp-16, fp-8 into a function */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_2), + /* 1st lookup from map */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_8, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + /* write map_value_ptr into stack frame of main prog at fp-8 */ + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_8, 1), + + /* 2nd lookup from map */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), /* 20 */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, /* 24 */ + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_9, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + /* write map_value_ptr into stack frame of main prog at fp-16 */ + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_9, 1), + + /* call 3rd func with fp-8, 0|1, fp-16, 0|1 */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), /* 30 */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_8), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_7), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_9), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), /* 34 */ + BPF_EXIT_INSN(), + + /* subprog 2 */ + /* if arg2 == 1 do *arg1 = 0 */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 1, 2), + /* fetch map_value_ptr from the stack of this function */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0), + /* write into map value */ + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + + /* if arg4 == 1 do *arg3 = 0 */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_4, 1, 2), + /* fetch map_value_ptr from the stack of this function */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0), + /* write into map value */ + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_map1 = { 12, 22 }, + .result = ACCEPT, + }, + { + "calls: two jumps that receive map_value via arg=ptr_stack_of_jumper. test3", + .insns = { + /* main prog */ + /* pass fp-16, fp-8 into a function */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_2), + /* 1st lookup from map */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -24, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -24), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_8, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + /* write map_value_ptr into stack frame of main prog at fp-8 */ + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_8, 1), + + /* 2nd lookup from map */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -24), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_9, 0), // 26 + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + /* write map_value_ptr into stack frame of main prog at fp-16 */ + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_9, 1), + + /* call 3rd func with fp-8, 0|1, fp-16, 0|1 */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), // 30 + BPF_MOV64_REG(BPF_REG_2, BPF_REG_8), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_7), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_9), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1), // 34 + BPF_JMP_IMM(BPF_JA, 0, 0, -30), + + /* subprog 2 */ + /* if arg2 == 1 do *arg1 = 0 */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 1, 2), + /* fetch map_value_ptr from the stack of this function */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0), + /* write into map value */ + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + + /* if arg4 == 1 do *arg3 = 0 */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_4, 1, 2), + /* fetch map_value_ptr from the stack of this function */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0), + /* write into map value */ + BPF_ST_MEM(BPF_DW, BPF_REG_0, 2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, -8), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_map1 = { 12, 22 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=8 off=2 size=8", + }, + { + "calls: two calls that receive map_value_ptr_or_null via arg. test1", + .insns = { + /* main prog */ + /* pass fp-16, fp-8 into a function */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_2), + /* 1st lookup from map */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + /* write map_value_ptr_or_null into stack frame of main prog at fp-8 */ + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_8, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_MOV64_IMM(BPF_REG_8, 1), + + /* 2nd lookup from map */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + /* write map_value_ptr_or_null into stack frame of main prog at fp-16 */ + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_9, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_MOV64_IMM(BPF_REG_9, 1), + + /* call 3rd func with fp-8, 0|1, fp-16, 0|1 */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_8), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_7), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_9), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + + /* subprog 2 */ + /* if arg2 == 1 do *arg1 = 0 */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 1, 2), + /* fetch map_value_ptr from the stack of this function */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0), + /* write into map value */ + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + + /* if arg4 == 1 do *arg3 = 0 */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_4, 1, 2), + /* fetch map_value_ptr from the stack of this function */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0), + /* write into map value */ + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_map1 = { 12, 22 }, + .result = ACCEPT, + }, + { + "calls: two calls that receive map_value_ptr_or_null via arg. test2", + .insns = { + /* main prog */ + /* pass fp-16, fp-8 into a function */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_2), + /* 1st lookup from map */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + /* write map_value_ptr_or_null into stack frame of main prog at fp-8 */ + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_8, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_MOV64_IMM(BPF_REG_8, 1), + + /* 2nd lookup from map */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + /* write map_value_ptr_or_null into stack frame of main prog at fp-16 */ + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_9, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_MOV64_IMM(BPF_REG_9, 1), + + /* call 3rd func with fp-8, 0|1, fp-16, 0|1 */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_8), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_7), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_9), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + + /* subprog 2 */ + /* if arg2 == 1 do *arg1 = 0 */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 1, 2), + /* fetch map_value_ptr from the stack of this function */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0), + /* write into map value */ + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + + /* if arg4 == 0 do *arg3 = 0 */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_4, 0, 2), + /* fetch map_value_ptr from the stack of this function */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0), + /* write into map value */ + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_map1 = { 12, 22 }, + .result = REJECT, + .errstr = "R0 invalid mem access 'inv'", + }, + { + "calls: pkt_ptr spill into caller stack", + .insns = { + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + /* spill unchecked pkt_ptr into stack of caller */ + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 2), + /* now the pkt range is verified, read pkt_ptr from stack */ + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0), + /* write 4 bytes into packet */ + BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "calls: pkt_ptr spill into caller stack 2", + .insns = { + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + /* Marking is still kept, but not in all cases safe. */ + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), + BPF_ST_MEM(BPF_W, BPF_REG_4, 0, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + /* spill unchecked pkt_ptr into stack of caller */ + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 2), + /* now the pkt range is verified, read pkt_ptr from stack */ + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0), + /* write 4 bytes into packet */ + BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "invalid access to packet", + .result = REJECT, + }, + { + "calls: pkt_ptr spill into caller stack 3", + .insns = { + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + /* Marking is still kept and safe here. */ + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), + BPF_ST_MEM(BPF_W, BPF_REG_4, 0, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + /* spill unchecked pkt_ptr into stack of caller */ + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3), + BPF_MOV64_IMM(BPF_REG_5, 1), + /* now the pkt range is verified, read pkt_ptr from stack */ + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0), + /* write 4 bytes into packet */ + BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_5), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "calls: pkt_ptr spill into caller stack 4", + .insns = { + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + /* Check marking propagated. */ + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), + BPF_ST_MEM(BPF_W, BPF_REG_4, 0, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + /* spill unchecked pkt_ptr into stack of caller */ + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_5, 1), + /* don't read back pkt_ptr from stack here */ + /* write 4 bytes into packet */ + BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_5), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "calls: pkt_ptr spill into caller stack 5", + .insns = { + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_4, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3), + /* spill checked pkt_ptr into stack of caller */ + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_5, 1), + /* don't read back pkt_ptr from stack here */ + /* write 4 bytes into packet */ + BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_5), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "same insn cannot be used with different", + .result = REJECT, + }, + { + "calls: pkt_ptr spill into caller stack 6", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_4, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3), + /* spill checked pkt_ptr into stack of caller */ + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_5, 1), + /* don't read back pkt_ptr from stack here */ + /* write 4 bytes into packet */ + BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_5), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "R4 invalid mem access", + .result = REJECT, + }, + { + "calls: pkt_ptr spill into caller stack 7", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_4, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3), + /* spill checked pkt_ptr into stack of caller */ + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_5, 1), + /* don't read back pkt_ptr from stack here */ + /* write 4 bytes into packet */ + BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_5), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "R4 invalid mem access", + .result = REJECT, + }, + { + "calls: pkt_ptr spill into caller stack 8", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_0, BPF_REG_3, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_4, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3), + /* spill checked pkt_ptr into stack of caller */ + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_5, 1), + /* don't read back pkt_ptr from stack here */ + /* write 4 bytes into packet */ + BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_5), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "calls: pkt_ptr spill into caller stack 9", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_0, BPF_REG_3, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_4, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_MOV64_IMM(BPF_REG_5, 0), + /* spill unchecked pkt_ptr into stack of caller */ + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_5, 1), + /* don't read back pkt_ptr from stack here */ + /* write 4 bytes into packet */ + BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_5), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "invalid access to packet", + .result = REJECT, + }, + { + "calls: caller stack init to zero or map_value_or_null", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), + /* fetch map_value_or_null or const_zero from stack */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + /* store into map_value */ + BPF_ST_MEM(BPF_W, BPF_REG_0, 0, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + /* if (ctx == 0) return; */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 8), + /* else bpf_map_lookup() and *(fp - 8) = r0 */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + /* write map_value_ptr_or_null into stack frame of main prog at fp-8 */ + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 13 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "calls: stack init to zero and pruning", + .insns = { + /* first make allocated_stack 16 byte */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0), + /* now fork the execution such that the false branch + * of JGT insn will be verified second and it skisp zero + * init of fp-8 stack slot. If stack liveness marking + * is missing live_read marks from call map_lookup + * processing then pruning will incorrectly assume + * that fp-8 stack slot was unused in the fall-through + * branch and will accept the program incorrectly + */ + BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 2, 2), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 6 }, + .errstr = "invalid indirect read from stack off -8+0 size 8", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + }, }; static int probe_filter_length(const struct bpf_insn *fp) diff --git a/tools/testing/selftests/bpf/test_xdp_noinline.c b/tools/testing/selftests/bpf/test_xdp_noinline.c new file mode 100644 index 000000000000..5e4aac74f9d0 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_noinline.c @@ -0,0 +1,833 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017 Facebook +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "bpf_helpers.h" + +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +static __u32 rol32(__u32 word, unsigned int shift) +{ + return (word << shift) | (word >> ((-shift) & 31)); +} + +/* copy paste of jhash from kernel sources to make sure llvm + * can compile it into valid sequence of bpf instructions + */ +#define __jhash_mix(a, b, c) \ +{ \ + a -= c; a ^= rol32(c, 4); c += b; \ + b -= a; b ^= rol32(a, 6); a += c; \ + c -= b; c ^= rol32(b, 8); b += a; \ + a -= c; a ^= rol32(c, 16); c += b; \ + b -= a; b ^= rol32(a, 19); a += c; \ + c -= b; c ^= rol32(b, 4); b += a; \ +} + +#define __jhash_final(a, b, c) \ +{ \ + c ^= b; c -= rol32(b, 14); \ + a ^= c; a -= rol32(c, 11); \ + b ^= a; b -= rol32(a, 25); \ + c ^= b; c -= rol32(b, 16); \ + a ^= c; a -= rol32(c, 4); \ + b ^= a; b -= rol32(a, 14); \ + c ^= b; c -= rol32(b, 24); \ +} + +#define JHASH_INITVAL 0xdeadbeef + +typedef unsigned int u32; + +static __attribute__ ((noinline)) +u32 jhash(const void *key, u32 length, u32 initval) +{ + u32 a, b, c; + const unsigned char *k = key; + + a = b = c = JHASH_INITVAL + length + initval; + + while (length > 12) { + a += *(u32 *)(k); + b += *(u32 *)(k + 4); + c += *(u32 *)(k + 8); + __jhash_mix(a, b, c); + length -= 12; + k += 12; + } + switch (length) { + case 12: c += (u32)k[11]<<24; + case 11: c += (u32)k[10]<<16; + case 10: c += (u32)k[9]<<8; + case 9: c += k[8]; + case 8: b += (u32)k[7]<<24; + case 7: b += (u32)k[6]<<16; + case 6: b += (u32)k[5]<<8; + case 5: b += k[4]; + case 4: a += (u32)k[3]<<24; + case 3: a += (u32)k[2]<<16; + case 2: a += (u32)k[1]<<8; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } + + return c; +} + +static __attribute__ ((noinline)) +u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) +{ + a += initval; + b += initval; + c += initval; + __jhash_final(a, b, c); + return c; +} + +static __attribute__ ((noinline)) +u32 jhash_2words(u32 a, u32 b, u32 initval) +{ + return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); +} + +struct flow_key { + union { + __be32 src; + __be32 srcv6[4]; + }; + union { + __be32 dst; + __be32 dstv6[4]; + }; + union { + __u32 ports; + __u16 port16[2]; + }; + __u8 proto; +}; + +struct packet_description { + struct flow_key flow; + __u8 flags; +}; + +struct ctl_value { + union { + __u64 value; + __u32 ifindex; + __u8 mac[6]; + }; +}; + +struct vip_definition { + union { + __be32 vip; + __be32 vipv6[4]; + }; + __u16 port; + __u16 family; + __u8 proto; +}; + +struct vip_meta { + __u32 flags; + __u32 vip_num; +}; + +struct real_pos_lru { + __u32 pos; + __u64 atime; +}; + +struct real_definition { + union { + __be32 dst; + __be32 dstv6[4]; + }; + __u8 flags; +}; + +struct lb_stats { + __u64 v2; + __u64 v1; +}; + +struct bpf_map_def __attribute__ ((section("maps"), used)) vip_map = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(struct vip_definition), + .value_size = sizeof(struct vip_meta), + .max_entries = 512, + .map_flags = 0, +}; + +struct bpf_map_def __attribute__ ((section("maps"), used)) lru_cache = { + .type = BPF_MAP_TYPE_LRU_HASH, + .key_size = sizeof(struct flow_key), + .value_size = sizeof(struct real_pos_lru), + .max_entries = 300, + .map_flags = 1U << 1, +}; + +struct bpf_map_def __attribute__ ((section("maps"), used)) ch_rings = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u32), + .max_entries = 12 * 655, + .map_flags = 0, +}; + +struct bpf_map_def __attribute__ ((section("maps"), used)) reals = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct real_definition), + .max_entries = 40, + .map_flags = 0, +}; + +struct bpf_map_def __attribute__ ((section("maps"), used)) stats = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct lb_stats), + .max_entries = 515, + .map_flags = 0, +}; + +struct bpf_map_def __attribute__ ((section("maps"), used)) ctl_array = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct ctl_value), + .max_entries = 16, + .map_flags = 0, +}; + +struct eth_hdr { + unsigned char eth_dest[6]; + unsigned char eth_source[6]; + unsigned short eth_proto; +}; + +static inline __u64 calc_offset(bool is_ipv6, bool is_icmp) +{ + __u64 off = sizeof(struct eth_hdr); + if (is_ipv6) { + off += sizeof(struct ipv6hdr); + if (is_icmp) + off += sizeof(struct icmp6hdr) + sizeof(struct ipv6hdr); + } else { + off += sizeof(struct iphdr); + if (is_icmp) + off += sizeof(struct icmphdr) + sizeof(struct iphdr); + } + return off; +} + +static __attribute__ ((noinline)) +bool parse_udp(void *data, void *data_end, + bool is_ipv6, struct packet_description *pckt) +{ + + bool is_icmp = !((pckt->flags & (1 << 0)) == 0); + __u64 off = calc_offset(is_ipv6, is_icmp); + struct udphdr *udp; + udp = data + off; + + if (udp + 1 > data_end) + return 0; + if (!is_icmp) { + pckt->flow.port16[0] = udp->source; + pckt->flow.port16[1] = udp->dest; + } else { + pckt->flow.port16[0] = udp->dest; + pckt->flow.port16[1] = udp->source; + } + return 1; +} + +static __attribute__ ((noinline)) +bool parse_tcp(void *data, void *data_end, + bool is_ipv6, struct packet_description *pckt) +{ + + bool is_icmp = !((pckt->flags & (1 << 0)) == 0); + __u64 off = calc_offset(is_ipv6, is_icmp); + struct tcphdr *tcp; + + tcp = data + off; + if (tcp + 1 > data_end) + return 0; + if (tcp->syn) + pckt->flags |= (1 << 1); + if (!is_icmp) { + pckt->flow.port16[0] = tcp->source; + pckt->flow.port16[1] = tcp->dest; + } else { + pckt->flow.port16[0] = tcp->dest; + pckt->flow.port16[1] = tcp->source; + } + return 1; +} + +static __attribute__ ((noinline)) +bool encap_v6(struct xdp_md *xdp, struct ctl_value *cval, + struct packet_description *pckt, + struct real_definition *dst, __u32 pkt_bytes) +{ + struct eth_hdr *new_eth; + struct eth_hdr *old_eth; + struct ipv6hdr *ip6h; + __u32 ip_suffix; + void *data_end; + void *data; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr))) + return 0; + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + new_eth = data; + ip6h = data + sizeof(struct eth_hdr); + old_eth = data + sizeof(struct ipv6hdr); + if (new_eth + 1 > data_end || + old_eth + 1 > data_end || ip6h + 1 > data_end) + return 0; + memcpy(new_eth->eth_dest, cval->mac, 6); + memcpy(new_eth->eth_source, old_eth->eth_dest, 6); + new_eth->eth_proto = 56710; + ip6h->version = 6; + ip6h->priority = 0; + memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl)); + + ip6h->nexthdr = IPPROTO_IPV6; + ip_suffix = pckt->flow.srcv6[3] ^ pckt->flow.port16[0]; + ip6h->payload_len = + __builtin_bswap16(pkt_bytes + sizeof(struct ipv6hdr)); + ip6h->hop_limit = 4; + + ip6h->saddr.in6_u.u6_addr32[0] = 1; + ip6h->saddr.in6_u.u6_addr32[1] = 2; + ip6h->saddr.in6_u.u6_addr32[2] = 3; + ip6h->saddr.in6_u.u6_addr32[3] = ip_suffix; + memcpy(ip6h->daddr.in6_u.u6_addr32, dst->dstv6, 16); + return 1; +} + +static __attribute__ ((noinline)) +bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval, + struct packet_description *pckt, + struct real_definition *dst, __u32 pkt_bytes) +{ + + __u32 ip_suffix = __builtin_bswap16(pckt->flow.port16[0]); + struct eth_hdr *new_eth; + struct eth_hdr *old_eth; + __u16 *next_iph_u16; + struct iphdr *iph; + __u32 csum = 0; + void *data_end; + void *data; + + ip_suffix <<= 15; + ip_suffix ^= pckt->flow.src; + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr))) + return 0; + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + new_eth = data; + iph = data + sizeof(struct eth_hdr); + old_eth = data + sizeof(struct iphdr); + if (new_eth + 1 > data_end || + old_eth + 1 > data_end || iph + 1 > data_end) + return 0; + memcpy(new_eth->eth_dest, cval->mac, 6); + memcpy(new_eth->eth_source, old_eth->eth_dest, 6); + new_eth->eth_proto = 8; + iph->version = 4; + iph->ihl = 5; + iph->frag_off = 0; + iph->protocol = IPPROTO_IPIP; + iph->check = 0; + iph->tos = 1; + iph->tot_len = __builtin_bswap16(pkt_bytes + sizeof(struct iphdr)); + /* don't update iph->daddr, since it will overwrite old eth_proto + * and multiple iterations of bpf_prog_run() will fail + */ + + iph->saddr = ((0xFFFF0000 & ip_suffix) | 4268) ^ dst->dst; + iph->ttl = 4; + + next_iph_u16 = (__u16 *) iph; +#pragma clang loop unroll(full) + for (int i = 0; i < sizeof(struct iphdr) >> 1; i++) + csum += *next_iph_u16++; + iph->check = ~((csum & 0xffff) + (csum >> 16)); + if (bpf_xdp_adjust_head(xdp, (int)sizeof(struct iphdr))) + return 0; + return 1; +} + +static __attribute__ ((noinline)) +bool decap_v6(struct xdp_md *xdp, void **data, void **data_end, bool inner_v4) +{ + struct eth_hdr *new_eth; + struct eth_hdr *old_eth; + + old_eth = *data; + new_eth = *data + sizeof(struct ipv6hdr); + memcpy(new_eth->eth_source, old_eth->eth_source, 6); + memcpy(new_eth->eth_dest, old_eth->eth_dest, 6); + if (inner_v4) + new_eth->eth_proto = 8; + else + new_eth->eth_proto = 56710; + if (bpf_xdp_adjust_head(xdp, (int)sizeof(struct ipv6hdr))) + return 0; + *data = (void *)(long)xdp->data; + *data_end = (void *)(long)xdp->data_end; + return 1; +} + +static __attribute__ ((noinline)) +bool decap_v4(struct xdp_md *xdp, void **data, void **data_end) +{ + struct eth_hdr *new_eth; + struct eth_hdr *old_eth; + + old_eth = *data; + new_eth = *data + sizeof(struct iphdr); + memcpy(new_eth->eth_source, old_eth->eth_source, 6); + memcpy(new_eth->eth_dest, old_eth->eth_dest, 6); + new_eth->eth_proto = 8; + if (bpf_xdp_adjust_head(xdp, (int)sizeof(struct iphdr))) + return 0; + *data = (void *)(long)xdp->data; + *data_end = (void *)(long)xdp->data_end; + return 1; +} + +static __attribute__ ((noinline)) +int swap_mac_and_send(void *data, void *data_end) +{ + unsigned char tmp_mac[6]; + struct eth_hdr *eth; + + eth = data; + memcpy(tmp_mac, eth->eth_source, 6); + memcpy(eth->eth_source, eth->eth_dest, 6); + memcpy(eth->eth_dest, tmp_mac, 6); + return XDP_TX; +} + +static __attribute__ ((noinline)) +int send_icmp_reply(void *data, void *data_end) +{ + struct icmphdr *icmp_hdr; + __u16 *next_iph_u16; + __u32 tmp_addr = 0; + struct iphdr *iph; + __u32 csum1 = 0; + __u32 csum = 0; + __u64 off = 0; + + if (data + sizeof(struct eth_hdr) + + sizeof(struct iphdr) + sizeof(struct icmphdr) > data_end) + return XDP_DROP; + off += sizeof(struct eth_hdr); + iph = data + off; + off += sizeof(struct iphdr); + icmp_hdr = data + off; + icmp_hdr->type = 0; + icmp_hdr->checksum += 0x0007; + iph->ttl = 4; + tmp_addr = iph->daddr; + iph->daddr = iph->saddr; + iph->saddr = tmp_addr; + iph->check = 0; + next_iph_u16 = (__u16 *) iph; +#pragma clang loop unroll(full) + for (int i = 0; i < sizeof(struct iphdr) >> 1; i++) + csum += *next_iph_u16++; + iph->check = ~((csum & 0xffff) + (csum >> 16)); + return swap_mac_and_send(data, data_end); +} + +static __attribute__ ((noinline)) +int send_icmp6_reply(void *data, void *data_end) +{ + struct icmp6hdr *icmp_hdr; + struct ipv6hdr *ip6h; + __be32 tmp_addr[4]; + __u64 off = 0; + + if (data + sizeof(struct eth_hdr) + + sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr) > data_end) + return XDP_DROP; + off += sizeof(struct eth_hdr); + ip6h = data + off; + off += sizeof(struct ipv6hdr); + icmp_hdr = data + off; + icmp_hdr->icmp6_type = 129; + icmp_hdr->icmp6_cksum -= 0x0001; + ip6h->hop_limit = 4; + memcpy(tmp_addr, ip6h->saddr.in6_u.u6_addr32, 16); + memcpy(ip6h->saddr.in6_u.u6_addr32, ip6h->daddr.in6_u.u6_addr32, 16); + memcpy(ip6h->daddr.in6_u.u6_addr32, tmp_addr, 16); + return swap_mac_and_send(data, data_end); +} + +static __attribute__ ((noinline)) +int parse_icmpv6(void *data, void *data_end, __u64 off, + struct packet_description *pckt) +{ + struct icmp6hdr *icmp_hdr; + struct ipv6hdr *ip6h; + + icmp_hdr = data + off; + if (icmp_hdr + 1 > data_end) + return XDP_DROP; + if (icmp_hdr->icmp6_type == 128) + return send_icmp6_reply(data, data_end); + if (icmp_hdr->icmp6_type != 3) + return XDP_PASS; + off += sizeof(struct icmp6hdr); + ip6h = data + off; + if (ip6h + 1 > data_end) + return XDP_DROP; + pckt->flow.proto = ip6h->nexthdr; + pckt->flags |= (1 << 0); + memcpy(pckt->flow.srcv6, ip6h->daddr.in6_u.u6_addr32, 16); + memcpy(pckt->flow.dstv6, ip6h->saddr.in6_u.u6_addr32, 16); + return -1; +} + +static __attribute__ ((noinline)) +int parse_icmp(void *data, void *data_end, __u64 off, + struct packet_description *pckt) +{ + struct icmphdr *icmp_hdr; + struct iphdr *iph; + + icmp_hdr = data + off; + if (icmp_hdr + 1 > data_end) + return XDP_DROP; + if (icmp_hdr->type == 8) + return send_icmp_reply(data, data_end); + if ((icmp_hdr->type != 3) || (icmp_hdr->code != 4)) + return XDP_PASS; + off += sizeof(struct icmphdr); + iph = data + off; + if (iph + 1 > data_end) + return XDP_DROP; + if (iph->ihl != 5) + return XDP_DROP; + pckt->flow.proto = iph->protocol; + pckt->flags |= (1 << 0); + pckt->flow.src = iph->daddr; + pckt->flow.dst = iph->saddr; + return -1; +} + +static __attribute__ ((noinline)) +__u32 get_packet_hash(struct packet_description *pckt, + bool hash_16bytes) +{ + if (hash_16bytes) + return jhash_2words(jhash(pckt->flow.srcv6, 16, 12), + pckt->flow.ports, 24); + else + return jhash_2words(pckt->flow.src, pckt->flow.ports, + 24); +} + +__attribute__ ((noinline)) +static bool get_packet_dst(struct real_definition **real, + struct packet_description *pckt, + struct vip_meta *vip_info, + bool is_ipv6, void *lru_map) +{ + struct real_pos_lru new_dst_lru = { }; + bool hash_16bytes = is_ipv6; + __u32 *real_pos, hash, key; + __u64 cur_time; + + if (vip_info->flags & (1 << 2)) + hash_16bytes = 1; + if (vip_info->flags & (1 << 3)) { + pckt->flow.port16[0] = pckt->flow.port16[1]; + memset(pckt->flow.srcv6, 0, 16); + } + hash = get_packet_hash(pckt, hash_16bytes); + if (hash != 0x358459b7 /* jhash of ipv4 packet */ && + hash != 0x2f4bc6bb /* jhash of ipv6 packet */) + return 0; + key = 2 * vip_info->vip_num + hash % 2; + real_pos = bpf_map_lookup_elem(&ch_rings, &key); + if (!real_pos) + return 0; + key = *real_pos; + *real = bpf_map_lookup_elem(&reals, &key); + if (!(*real)) + return 0; + if (!(vip_info->flags & (1 << 1))) { + __u32 conn_rate_key = 512 + 2; + struct lb_stats *conn_rate_stats = + bpf_map_lookup_elem(&stats, &conn_rate_key); + + if (!conn_rate_stats) + return 1; + cur_time = bpf_ktime_get_ns(); + if ((cur_time - conn_rate_stats->v2) >> 32 > 0xffFFFF) { + conn_rate_stats->v1 = 1; + conn_rate_stats->v2 = cur_time; + } else { + conn_rate_stats->v1 += 1; + if (conn_rate_stats->v1 >= 1) + return 1; + } + if (pckt->flow.proto == IPPROTO_UDP) + new_dst_lru.atime = cur_time; + new_dst_lru.pos = key; + bpf_map_update_elem(lru_map, &pckt->flow, &new_dst_lru, 0); + } + return 1; +} + +__attribute__ ((noinline)) +static void connection_table_lookup(struct real_definition **real, + struct packet_description *pckt, + void *lru_map) +{ + + struct real_pos_lru *dst_lru; + __u64 cur_time; + __u32 key; + + dst_lru = bpf_map_lookup_elem(lru_map, &pckt->flow); + if (!dst_lru) + return; + if (pckt->flow.proto == IPPROTO_UDP) { + cur_time = bpf_ktime_get_ns(); + if (cur_time - dst_lru->atime > 300000) + return; + dst_lru->atime = cur_time; + } + key = dst_lru->pos; + *real = bpf_map_lookup_elem(&reals, &key); +} + +/* don't believe your eyes! + * below function has 6 arguments whereas bpf and llvm allow maximum of 5 + * but since it's _static_ llvm can optimize one argument away + */ +__attribute__ ((noinline)) +static int process_l3_headers_v6(struct packet_description *pckt, + __u8 *protocol, __u64 off, + __u16 *pkt_bytes, void *data, + void *data_end) +{ + struct ipv6hdr *ip6h; + __u64 iph_len; + int action; + + ip6h = data + off; + if (ip6h + 1 > data_end) + return XDP_DROP; + iph_len = sizeof(struct ipv6hdr); + *protocol = ip6h->nexthdr; + pckt->flow.proto = *protocol; + *pkt_bytes = __builtin_bswap16(ip6h->payload_len); + off += iph_len; + if (*protocol == 45) { + return XDP_DROP; + } else if (*protocol == 59) { + action = parse_icmpv6(data, data_end, off, pckt); + if (action >= 0) + return action; + } else { + memcpy(pckt->flow.srcv6, ip6h->saddr.in6_u.u6_addr32, 16); + memcpy(pckt->flow.dstv6, ip6h->daddr.in6_u.u6_addr32, 16); + } + return -1; +} + +__attribute__ ((noinline)) +static int process_l3_headers_v4(struct packet_description *pckt, + __u8 *protocol, __u64 off, + __u16 *pkt_bytes, void *data, + void *data_end) +{ + struct iphdr *iph; + __u64 iph_len; + int action; + + iph = data + off; + if (iph + 1 > data_end) + return XDP_DROP; + if (iph->ihl != 5) + return XDP_DROP; + *protocol = iph->protocol; + pckt->flow.proto = *protocol; + *pkt_bytes = __builtin_bswap16(iph->tot_len); + off += 20; + if (iph->frag_off & 65343) + return XDP_DROP; + if (*protocol == IPPROTO_ICMP) { + action = parse_icmp(data, data_end, off, pckt); + if (action >= 0) + return action; + } else { + pckt->flow.src = iph->saddr; + pckt->flow.dst = iph->daddr; + } + return -1; +} + +__attribute__ ((noinline)) +static int process_packet(void *data, __u64 off, void *data_end, + bool is_ipv6, struct xdp_md *xdp) +{ + + struct real_definition *dst = NULL; + struct packet_description pckt = { }; + struct vip_definition vip = { }; + struct lb_stats *data_stats; + struct eth_hdr *eth = data; + void *lru_map = &lru_cache; + struct vip_meta *vip_info; + __u32 lru_stats_key = 513; + __u32 mac_addr_pos = 0; + __u32 stats_key = 512; + struct ctl_value *cval; + __u16 pkt_bytes; + __u64 iph_len; + __u8 protocol; + __u32 vip_num; + int action; + + if (is_ipv6) + action = process_l3_headers_v6(&pckt, &protocol, off, + &pkt_bytes, data, data_end); + else + action = process_l3_headers_v4(&pckt, &protocol, off, + &pkt_bytes, data, data_end); + if (action >= 0) + return action; + protocol = pckt.flow.proto; + if (protocol == IPPROTO_TCP) { + if (!parse_tcp(data, data_end, is_ipv6, &pckt)) + return XDP_DROP; + } else if (protocol == IPPROTO_UDP) { + if (!parse_udp(data, data_end, is_ipv6, &pckt)) + return XDP_DROP; + } else { + return XDP_TX; + } + + if (is_ipv6) + memcpy(vip.vipv6, pckt.flow.dstv6, 16); + else + vip.vip = pckt.flow.dst; + vip.port = pckt.flow.port16[1]; + vip.proto = pckt.flow.proto; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) { + vip.port = 0; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) + return XDP_PASS; + if (!(vip_info->flags & (1 << 4))) + pckt.flow.port16[1] = 0; + } + if (data_end - data > 1400) + return XDP_DROP; + data_stats = bpf_map_lookup_elem(&stats, &stats_key); + if (!data_stats) + return XDP_DROP; + data_stats->v1 += 1; + if (!dst) { + if (vip_info->flags & (1 << 0)) + pckt.flow.port16[0] = 0; + if (!(pckt.flags & (1 << 1)) && !(vip_info->flags & (1 << 1))) + connection_table_lookup(&dst, &pckt, lru_map); + if (dst) + goto out; + if (pckt.flow.proto == IPPROTO_TCP) { + struct lb_stats *lru_stats = + bpf_map_lookup_elem(&stats, &lru_stats_key); + + if (!lru_stats) + return XDP_DROP; + if (pckt.flags & (1 << 1)) + lru_stats->v1 += 1; + else + lru_stats->v2 += 1; + } + if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6, lru_map)) + return XDP_DROP; + data_stats->v2 += 1; + } +out: + cval = bpf_map_lookup_elem(&ctl_array, &mac_addr_pos); + if (!cval) + return XDP_DROP; + if (dst->flags & (1 << 0)) { + if (!encap_v6(xdp, cval, &pckt, dst, pkt_bytes)) + return XDP_DROP; + } else { + if (!encap_v4(xdp, cval, &pckt, dst, pkt_bytes)) + return XDP_DROP; + } + vip_num = vip_info->vip_num; + data_stats = bpf_map_lookup_elem(&stats, &vip_num); + if (!data_stats) + return XDP_DROP; + data_stats->v1 += 1; + data_stats->v2 += pkt_bytes; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + if (data + 4 > data_end) + return XDP_DROP; + *(u32 *)data = dst->dst; + return XDP_DROP; +} + +__attribute__ ((section("xdp-test"), used)) +int balancer_ingress(struct xdp_md *ctx) +{ + void *data = (void *)(long)ctx->data; + void *data_end = (void *)(long)ctx->data_end; + struct eth_hdr *eth = data; + __u32 eth_proto; + __u32 nh_off; + + nh_off = sizeof(struct eth_hdr); + if (data + nh_off > data_end) + return XDP_DROP; + eth_proto = eth->eth_proto; + if (eth_proto == 8) + return process_packet(data, nh_off, data_end, 0, ctx); + else if (eth_proto == 56710) + return process_packet(data, nh_off, data_end, 1, ctx); + else + return XDP_DROP; +} + +char _license[] __attribute__ ((section("license"), used)) = "GPL"; +int _version __attribute__ ((section("version"), used)) = 1;