diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 150d1c6543f7..7d4af64e3982 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -288,7 +288,7 @@ static bool is_lsi_offset(int offset, int scale) static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf) { const struct bpf_prog *prog = ctx->prog; - const bool is_main_prog = prog->aux->func_idx == 0; + const bool is_main_prog = !bpf_is_subprog(prog); const u8 r6 = bpf2a64[BPF_REG_6]; const u8 r7 = bpf2a64[BPF_REG_7]; const u8 r8 = bpf2a64[BPF_REG_8]; diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index de2fb12120d2..eeb42e5cd7d6 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -556,7 +556,7 @@ static void bpf_jit_prologue(struct bpf_jit *jit, struct bpf_prog *fp, EMIT6_PCREL_RILC(0xc0040000, 0, jit->prologue_plt); jit->prologue_plt_ret = jit->prg; - if (fp->aux->func_idx == 0) { + if (!bpf_is_subprog(fp)) { /* Initialize the tail call counter in the main program. */ /* xc STK_OFF_TCCNT(4,%r15),STK_OFF_TCCNT(%r15) */ _EMIT6(0xd703f000 | STK_OFF_TCCNT, 0xf000 | STK_OFF_TCCNT); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 2846c21d75bf..84005f2114e0 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -16,6 +16,9 @@ #include #include #include +#include + +static bool all_callee_regs_used[4] = {true, true, true, true}; static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) { @@ -255,6 +258,14 @@ struct jit_context { /* Number of bytes that will be skipped on tailcall */ #define X86_TAIL_CALL_OFFSET (11 + ENDBR_INSN_SIZE) +static void push_r12(u8 **pprog) +{ + u8 *prog = *pprog; + + EMIT2(0x41, 0x54); /* push r12 */ + *pprog = prog; +} + static void push_callee_regs(u8 **pprog, bool *callee_regs_used) { u8 *prog = *pprog; @@ -270,6 +281,14 @@ static void push_callee_regs(u8 **pprog, bool *callee_regs_used) *pprog = prog; } +static void pop_r12(u8 **pprog) +{ + u8 *prog = *pprog; + + EMIT2(0x41, 0x5C); /* pop r12 */ + *pprog = prog; +} + static void pop_callee_regs(u8 **pprog, bool *callee_regs_used) { u8 *prog = *pprog; @@ -291,7 +310,8 @@ static void pop_callee_regs(u8 **pprog, bool *callee_regs_used) * while jumping to another program */ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf, - bool tail_call_reachable, bool is_subprog) + bool tail_call_reachable, bool is_subprog, + bool is_exception_cb) { u8 *prog = *pprog; @@ -311,8 +331,22 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf, /* Keep the same instruction layout. */ EMIT2(0x66, 0x90); /* nop2 */ } - EMIT1(0x55); /* push rbp */ - EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ + /* Exception callback receives FP as third parameter */ + if (is_exception_cb) { + EMIT3(0x48, 0x89, 0xF4); /* mov rsp, rsi */ + EMIT3(0x48, 0x89, 0xD5); /* mov rbp, rdx */ + /* The main frame must have exception_boundary as true, so we + * first restore those callee-saved regs from stack, before + * reusing the stack frame. + */ + pop_callee_regs(&prog, all_callee_regs_used); + pop_r12(&prog); + /* Reset the stack frame. */ + EMIT3(0x48, 0x89, 0xEC); /* mov rsp, rbp */ + } else { + EMIT1(0x55); /* push rbp */ + EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ + } /* X86_TAIL_CALL_OFFSET is here */ EMIT_ENDBR(); @@ -471,7 +505,8 @@ static void emit_return(u8 **pprog, u8 *ip) * goto *(prog->bpf_func + prologue_size); * out: */ -static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, +static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog, + u8 **pprog, bool *callee_regs_used, u32 stack_depth, u8 *ip, struct jit_context *ctx) { @@ -521,7 +556,12 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, offset = ctx->tail_call_indirect_label - (prog + 2 - start); EMIT2(X86_JE, offset); /* je out */ - pop_callee_regs(&prog, callee_regs_used); + if (bpf_prog->aux->exception_boundary) { + pop_callee_regs(&prog, all_callee_regs_used); + pop_r12(&prog); + } else { + pop_callee_regs(&prog, callee_regs_used); + } EMIT1(0x58); /* pop rax */ if (stack_depth) @@ -545,7 +585,8 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, *pprog = prog; } -static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke, +static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog, + struct bpf_jit_poke_descriptor *poke, u8 **pprog, u8 *ip, bool *callee_regs_used, u32 stack_depth, struct jit_context *ctx) @@ -574,7 +615,13 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke, emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE, poke->tailcall_bypass); - pop_callee_regs(&prog, callee_regs_used); + if (bpf_prog->aux->exception_boundary) { + pop_callee_regs(&prog, all_callee_regs_used); + pop_r12(&prog); + } else { + pop_callee_regs(&prog, callee_regs_used); + } + EMIT1(0x58); /* pop rax */ if (stack_depth) EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8)); @@ -1049,8 +1096,20 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image emit_prologue(&prog, bpf_prog->aux->stack_depth, bpf_prog_was_classic(bpf_prog), tail_call_reachable, - bpf_prog->aux->func_idx != 0); - push_callee_regs(&prog, callee_regs_used); + bpf_is_subprog(bpf_prog), bpf_prog->aux->exception_cb); + /* Exception callback will clobber callee regs for its own use, and + * restore the original callee regs from main prog's stack frame. + */ + if (bpf_prog->aux->exception_boundary) { + /* We also need to save r12, which is not mapped to any BPF + * register, as we throw after entry into the kernel, which may + * overwrite r12. + */ + push_r12(&prog); + push_callee_regs(&prog, all_callee_regs_used); + } else { + push_callee_regs(&prog, callee_regs_used); + } ilen = prog - temp; if (rw_image) @@ -1647,13 +1706,15 @@ st: if (is_imm8(insn->off)) case BPF_JMP | BPF_TAIL_CALL: if (imm32) - emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1], + emit_bpf_tail_call_direct(bpf_prog, + &bpf_prog->aux->poke_tab[imm32 - 1], &prog, image + addrs[i - 1], callee_regs_used, bpf_prog->aux->stack_depth, ctx); else - emit_bpf_tail_call_indirect(&prog, + emit_bpf_tail_call_indirect(bpf_prog, + &prog, callee_regs_used, bpf_prog->aux->stack_depth, image + addrs[i - 1], @@ -1906,7 +1967,12 @@ emit_jmp: seen_exit = true; /* Update cleanup_addr */ ctx->cleanup_addr = proglen; - pop_callee_regs(&prog, callee_regs_used); + if (bpf_prog->aux->exception_boundary) { + pop_callee_regs(&prog, all_callee_regs_used); + pop_r12(&prog); + } else { + pop_callee_regs(&prog, callee_regs_used); + } EMIT1(0xC9); /* leave */ emit_return(&prog, image + addrs[i - 1] + (prog - temp)); break; @@ -2933,3 +2999,30 @@ void bpf_jit_free(struct bpf_prog *prog) bpf_prog_unlock_free(prog); } + +bool bpf_jit_supports_exceptions(void) +{ + /* We unwind through both kernel frames (starting from within bpf_throw + * call) and BPF frames. Therefore we require one of ORC or FP unwinder + * to be enabled to walk kernel frames and reach BPF frames in the stack + * trace. + */ + return IS_ENABLED(CONFIG_UNWINDER_ORC) || IS_ENABLED(CONFIG_UNWINDER_FRAME_POINTER); +} + +void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie) +{ +#if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER) + struct unwind_state state; + unsigned long addr; + + for (unwind_start(&state, current, NULL, NULL); !unwind_done(&state); + unwind_next_frame(&state)) { + addr = unwind_get_return_address(&state); + if (!addr || !consume_fn(cookie, (u64)addr, (u64)state.sp, (u64)state.bp)) + break; + } + return; +#endif + WARN(1, "verification of programs using bpf_throw should have failed\n"); +} diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b9e573159432..30063a760b5a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1389,6 +1389,7 @@ struct bpf_prog_aux { u32 stack_depth; u32 id; u32 func_cnt; /* used by non-func prog as the number of func progs */ + u32 real_func_cnt; /* includes hidden progs, only used for JIT and freeing progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ u32 attach_btf_id; /* in-kernel BTF type id to attach to */ u32 ctx_arg_info_size; @@ -1409,6 +1410,8 @@ struct bpf_prog_aux { bool sleepable; bool tail_call_reachable; bool xdp_has_frags; + bool exception_cb; + bool exception_boundary; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; /* function name for valid attach_btf_id */ @@ -1431,6 +1434,7 @@ struct bpf_prog_aux { int cgroup_atype; /* enum cgroup_bpf_attach_type */ struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; + unsigned int (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp); #ifdef CONFIG_SECURITY void *security; #endif @@ -2418,9 +2422,11 @@ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *reg); + struct bpf_reg_state *reg, bool is_ex_cb); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); +const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, + int comp_idx, const char *tag_key); struct bpf_prog *bpf_prog_by_id(u32 id); struct bpf_link *bpf_link_by_id(u32 id); @@ -3194,4 +3200,9 @@ static inline gfp_t bpf_memcg_flags(gfp_t flags) return flags; } +static inline bool bpf_is_subprog(const struct bpf_prog *prog) +{ + return prog->aux->func_idx != 0; +} + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index a3236651ec64..94ec766432f5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -300,6 +300,7 @@ struct bpf_func_state { bool in_callback_fn; struct tnum callback_ret_range; bool in_async_callback_fn; + bool in_exception_callback_fn; /* The following fields should be last. See copy_func_state() */ int acquired_refs; @@ -541,7 +542,9 @@ struct bpf_subprog_info { bool has_tail_call; bool tail_call_reachable; bool has_ld_abs; + bool is_cb; bool is_async_cb; + bool is_exception_cb; }; struct bpf_verifier_env; @@ -588,6 +591,8 @@ struct bpf_verifier_env { u32 used_map_cnt; /* number of used maps */ u32 used_btf_cnt; /* number of used BTF objects */ u32 id_gen; /* used to generate unique reg IDs */ + u32 hidden_subprog_cnt; /* number of hidden subprogs */ + int exception_callback_subprog; bool explore_alu_limits; bool allow_ptr_leaks; bool allow_uninit_stack; @@ -595,10 +600,11 @@ struct bpf_verifier_env { bool bypass_spec_v1; bool bypass_spec_v4; bool seen_direct_write; + bool seen_exception; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ const struct bpf_line_info *prev_linfo; struct bpf_verifier_log log; - struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1]; + struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 2]; /* max + 2 for the fake and exception subprogs */ union { struct bpf_idmap idmap_scratch; struct bpf_idset idset_scratch; diff --git a/include/linux/filter.h b/include/linux/filter.h index 0138832ad571..27406aee2d40 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -954,6 +954,8 @@ bool bpf_jit_needs_zext(void); bool bpf_jit_supports_subprog_tailcalls(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_far_kfunc_call(void); +bool bpf_jit_supports_exceptions(void); +void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); static inline bool bpf_dump_raw_ok(const struct cred *cred) @@ -1169,6 +1171,7 @@ const char *__bpf_address_lookup(unsigned long addr, unsigned long *size, bool is_bpf_text_address(unsigned long addr); int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); +struct bpf_prog *bpf_prog_ksym_find(unsigned long addr); static inline const char * bpf_address_lookup(unsigned long addr, unsigned long *size, @@ -1236,6 +1239,11 @@ static inline int bpf_get_kallsym(unsigned int symnum, unsigned long *value, return -ERANGE; } +static inline struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) +{ + return NULL; +} + static inline const char * bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 819b6bc8ac08..7a463f814db2 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -283,8 +283,10 @@ static inline bool kasan_check_byte(const void *address) #if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK) void kasan_unpoison_task_stack(struct task_struct *task); +asmlinkage void kasan_unpoison_task_stack_below(const void *watermark); #else static inline void kasan_unpoison_task_stack(struct task_struct *task) {} +static inline void kasan_unpoison_task_stack_below(const void *watermark) {} #endif #ifdef CONFIG_KASAN_GENERIC diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 187b57276fec..f93e835d90af 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3310,10 +3310,10 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, return BTF_FIELD_FOUND; } -static const char *btf_find_decl_tag_value(const struct btf *btf, - const struct btf_type *pt, - int comp_idx, const char *tag_key) +const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, + int comp_idx, const char *tag_key) { + const char *value = NULL; int i; for (i = 1; i < btf_nr_types(btf); i++) { @@ -3327,9 +3327,14 @@ static const char *btf_find_decl_tag_value(const struct btf *btf, continue; if (strncmp(__btf_name_by_offset(btf, t->name_off), tag_key, len)) continue; - return __btf_name_by_offset(btf, t->name_off) + len; + /* Prevent duplicate entries for same type */ + if (value) + return ERR_PTR(-EEXIST); + value = __btf_name_by_offset(btf, t->name_off) + len; } - return NULL; + if (!value) + return ERR_PTR(-ENOENT); + return value; } static int @@ -3347,7 +3352,7 @@ btf_find_graph_root(const struct btf *btf, const struct btf_type *pt, if (t->size != sz) return BTF_FIELD_IGNORE; value_type = btf_find_decl_tag_value(btf, pt, comp_idx, "contains:"); - if (!value_type) + if (IS_ERR(value_type)) return -EINVAL; node_field_name = strstr(value_type, ":"); if (!node_field_name) @@ -6954,7 +6959,7 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, * (either PTR_TO_CTX or SCALAR_VALUE). */ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *regs) + struct bpf_reg_state *regs, bool is_ex_cb) { struct bpf_verifier_log *log = &env->log; struct bpf_prog *prog = env->prog; @@ -7011,7 +7016,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, tname, nargs, MAX_BPF_FUNC_REG_ARGS); return -EINVAL; } - /* check that function returns int */ + /* check that function returns int, exception cb also requires this */ t = btf_type_by_id(btf, t->type); while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); @@ -7060,6 +7065,14 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, i, btf_type_str(t), tname); return -EINVAL; } + /* We have already ensured that the callback returns an integer, just + * like all global subprogs. We need to determine it only has a single + * scalar argument. + */ + if (is_ex_cb && (nargs != 1 || regs[BPF_REG_1].type != SCALAR_VALUE)) { + bpf_log(log, "exception cb only supports single integer argument\n"); + return -EINVAL; + } return 0; } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 95599df82ee4..8f921b6d6981 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -212,7 +212,7 @@ void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, const struct bpf_line_info *linfo; void **jited_linfo; - if (!prog->aux->jited_linfo) + if (!prog->aux->jited_linfo || prog->aux->func_idx > prog->aux->func_cnt) /* Userspace did not provide linfo */ return; @@ -539,7 +539,7 @@ static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp) { int i; - for (i = 0; i < fp->aux->func_cnt; i++) + for (i = 0; i < fp->aux->real_func_cnt; i++) bpf_prog_kallsyms_del(fp->aux->func[i]); } @@ -589,7 +589,7 @@ bpf_prog_ksym_set_name(struct bpf_prog *prog) sym = bin2hex(sym, prog->tag, sizeof(prog->tag)); /* prog->aux->name will be ignored if full btf name is available */ - if (prog->aux->func_info_cnt) { + if (prog->aux->func_info_cnt && prog->aux->func_idx < prog->aux->func_info_cnt) { type = btf_type_by_id(prog->aux->btf, prog->aux->func_info[prog->aux->func_idx].type_id); func_name = btf_name_by_offset(prog->aux->btf, type->name_off); @@ -623,7 +623,11 @@ static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n) if (val < ksym->start) return -1; - if (val >= ksym->end) + /* Ensure that we detect return addresses as part of the program, when + * the final instruction is a call for a program part of the stack + * trace. Therefore, do val > ksym->end instead of val >= ksym->end. + */ + if (val > ksym->end) return 1; return 0; @@ -733,7 +737,7 @@ bool is_bpf_text_address(unsigned long addr) return ret; } -static struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) +struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) { struct bpf_ksym *ksym = bpf_ksym_find(addr); @@ -1208,7 +1212,7 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog, if (!extra_pass) addr = NULL; else if (prog->aux->func && - off >= 0 && off < prog->aux->func_cnt) + off >= 0 && off < prog->aux->real_func_cnt) addr = (u8 *)prog->aux->func[off]->bpf_func; else return -EINVAL; @@ -2721,7 +2725,7 @@ static void bpf_prog_free_deferred(struct work_struct *work) #endif if (aux->dst_trampoline) bpf_trampoline_put(aux->dst_trampoline); - for (i = 0; i < aux->func_cnt; i++) { + for (i = 0; i < aux->real_func_cnt; i++) { /* We can just unlink the subprog poke descriptor table as * it was originally linked to the main program and is also * released along with it. @@ -2729,7 +2733,7 @@ static void bpf_prog_free_deferred(struct work_struct *work) aux->func[i]->aux->poke_tab = NULL; bpf_jit_free(aux->func[i]); } - if (aux->func_cnt) { + if (aux->real_func_cnt) { kfree(aux->func); bpf_prog_unlock_free(aux->prog); } else { @@ -2914,6 +2918,15 @@ int __weak bpf_arch_text_invalidate(void *dst, size_t len) return -ENOTSUPP; } +bool __weak bpf_jit_supports_exceptions(void) +{ + return false; +} + +void __weak arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie) +{ +} + #ifdef CONFIG_BPF_SYSCALL static int __init bpf_global_ma_init(void) { diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index b0a9834f1051..7ff2a42f1996 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "../../lib/kstrtox.h" @@ -2449,6 +2450,49 @@ __bpf_kfunc void bpf_rcu_read_unlock(void) rcu_read_unlock(); } +struct bpf_throw_ctx { + struct bpf_prog_aux *aux; + u64 sp; + u64 bp; + int cnt; +}; + +static bool bpf_stack_walker(void *cookie, u64 ip, u64 sp, u64 bp) +{ + struct bpf_throw_ctx *ctx = cookie; + struct bpf_prog *prog; + + if (!is_bpf_text_address(ip)) + return !ctx->cnt; + prog = bpf_prog_ksym_find(ip); + ctx->cnt++; + if (bpf_is_subprog(prog)) + return true; + ctx->aux = prog->aux; + ctx->sp = sp; + ctx->bp = bp; + return false; +} + +__bpf_kfunc void bpf_throw(u64 cookie) +{ + struct bpf_throw_ctx ctx = {}; + + arch_bpf_stack_walk(bpf_stack_walker, &ctx); + WARN_ON_ONCE(!ctx.aux); + if (ctx.aux) + WARN_ON_ONCE(!ctx.aux->exception_boundary); + WARN_ON_ONCE(!ctx.bp); + WARN_ON_ONCE(!ctx.cnt); + /* Prevent KASAN false positives for CONFIG_KASAN_STACK by unpoisoning + * deeper stack depths than ctx.sp as we do not return from bpf_throw, + * which skips compiler generated instrumentation to do the same. + */ + kasan_unpoison_task_stack_below((void *)ctx.sp); + ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp); + WARN(1, "A call to BPF exception callback should never return\n"); +} + __diag_pop(); BTF_SET8_START(generic_btf_ids) @@ -2478,6 +2522,7 @@ BTF_ID_FLAGS(func, bpf_cgroup_from_id, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_task_under_cgroup, KF_RCU) #endif BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_throw) BTF_SET8_END(generic_btf_ids) static const struct btf_kfunc_id_set generic_kfunc_set = { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 6a692f3bea15..85c1d908f70f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2749,7 +2749,7 @@ free_used_maps: * period before we can tear down JIT memory since symbols * are already exposed under kallsyms. */ - __bpf_prog_put_noref(prog, prog->aux->func_cnt); + __bpf_prog_put_noref(prog, prog->aux->real_func_cnt); return err; free_prog_sec: free_uid(prog->aux->user); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 18e673c0ac15..a7178ecf676d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -543,6 +543,7 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id) } static bool is_callback_calling_kfunc(u32 btf_id); +static bool is_bpf_throw_kfunc(struct bpf_insn *insn); static bool is_callback_calling_function(enum bpf_func_id func_id) { @@ -1748,7 +1749,9 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, return -ENOMEM; dst_state->jmp_history_cnt = src->jmp_history_cnt; - /* if dst has more stack frames then src frame, free them */ + /* if dst has more stack frames then src frame, free them, this is also + * necessary in case of exceptional exits using bpf_throw. + */ for (i = src->curframe + 1; i <= dst_state->curframe; i++) { free_func_state(dst_state->frame[i]); dst_state->frame[i] = NULL; @@ -2454,6 +2457,68 @@ static int add_subprog(struct bpf_verifier_env *env, int off) return env->subprog_cnt - 1; } +static int bpf_find_exception_callback_insn_off(struct bpf_verifier_env *env) +{ + struct bpf_prog_aux *aux = env->prog->aux; + struct btf *btf = aux->btf; + const struct btf_type *t; + u32 main_btf_id, id; + const char *name; + int ret, i; + + /* Non-zero func_info_cnt implies valid btf */ + if (!aux->func_info_cnt) + return 0; + main_btf_id = aux->func_info[0].type_id; + + t = btf_type_by_id(btf, main_btf_id); + if (!t) { + verbose(env, "invalid btf id for main subprog in func_info\n"); + return -EINVAL; + } + + name = btf_find_decl_tag_value(btf, t, -1, "exception_callback:"); + if (IS_ERR(name)) { + ret = PTR_ERR(name); + /* If there is no tag present, there is no exception callback */ + if (ret == -ENOENT) + ret = 0; + else if (ret == -EEXIST) + verbose(env, "multiple exception callback tags for main subprog\n"); + return ret; + } + + ret = btf_find_by_name_kind(btf, name, BTF_KIND_FUNC); + if (ret < 0) { + verbose(env, "exception callback '%s' could not be found in BTF\n", name); + return ret; + } + id = ret; + t = btf_type_by_id(btf, id); + if (btf_func_linkage(t) != BTF_FUNC_GLOBAL) { + verbose(env, "exception callback '%s' must have global linkage\n", name); + return -EINVAL; + } + ret = 0; + for (i = 0; i < aux->func_info_cnt; i++) { + if (aux->func_info[i].type_id != id) + continue; + ret = aux->func_info[i].insn_off; + /* Further func_info and subprog checks will also happen + * later, so assume this is the right insn_off for now. + */ + if (!ret) { + verbose(env, "invalid exception callback insn_off in func_info: 0\n"); + ret = -EINVAL; + } + } + if (!ret) { + verbose(env, "exception callback type id not found in func_info\n"); + ret = -EINVAL; + } + return ret; +} + #define MAX_KFUNC_DESCS 256 #define MAX_KFUNC_BTFS 256 @@ -2793,8 +2858,8 @@ bpf_jit_find_kfunc_model(const struct bpf_prog *prog, static int add_subprog_and_kfunc(struct bpf_verifier_env *env) { struct bpf_subprog_info *subprog = env->subprog_info; + int i, ret, insn_cnt = env->prog->len, ex_cb_insn; struct bpf_insn *insn = env->prog->insnsi; - int i, ret, insn_cnt = env->prog->len; /* Add entry function. */ ret = add_subprog(env, 0); @@ -2820,6 +2885,26 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env) return ret; } + ret = bpf_find_exception_callback_insn_off(env); + if (ret < 0) + return ret; + ex_cb_insn = ret; + + /* If ex_cb_insn > 0, this means that the main program has a subprog + * marked using BTF decl tag to serve as the exception callback. + */ + if (ex_cb_insn) { + ret = add_subprog(env, ex_cb_insn); + if (ret < 0) + return ret; + for (i = 1; i < env->subprog_cnt; i++) { + if (env->subprog_info[i].start != ex_cb_insn) + continue; + env->exception_callback_subprog = i; + break; + } + } + /* Add a fake 'exit' subprog which could simplify subprog iteration * logic. 'subprog_cnt' should not be increased. */ @@ -2868,7 +2953,7 @@ 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 + * or unconditional jump back or bpf_throw call */ if (code != (BPF_JMP | BPF_EXIT) && code != (BPF_JMP32 | BPF_JA) && @@ -5661,6 +5746,27 @@ continue_func: for (; i < subprog_end; i++) { int next_insn, sidx; + if (bpf_pseudo_kfunc_call(insn + i) && !insn[i].off) { + bool err = false; + + if (!is_bpf_throw_kfunc(insn + i)) + continue; + if (subprog[idx].is_cb) + err = true; + for (int c = 0; c < frame && !err; c++) { + if (subprog[ret_prog[c]].is_cb) { + err = true; + break; + } + } + if (!err) + continue; + verbose(env, + "bpf_throw kfunc (insn %d) cannot be called from callback subprog %d\n", + i, idx); + return -EINVAL; + } + if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i)) continue; /* remember insn and function to return to */ @@ -5683,6 +5789,10 @@ continue_func: /* async callbacks don't increase bpf prog stack size unless called directly */ if (!bpf_pseudo_call(insn + i)) continue; + if (subprog[sidx].is_exception_cb) { + verbose(env, "insn %d cannot call exception cb directly\n", i); + return -EINVAL; + } } i = next_insn; idx = sidx; @@ -5704,8 +5814,13 @@ continue_func: * tail call counter throughout bpf2bpf calls combined with tailcalls */ if (tail_call_reachable) - for (j = 0; j < frame; j++) + for (j = 0; j < frame; j++) { + if (subprog[ret_prog[j]].is_exception_cb) { + verbose(env, "cannot tail call within exception cb\n"); + return -EINVAL; + } subprog[ret_prog[j]].tail_call_reachable = true; + } if (subprog[0].tail_call_reachable) env->prog->aux->tail_call_reachable = true; @@ -8919,6 +9034,7 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn * callbacks */ if (set_callee_state_cb != set_callee_state) { + env->subprog_info[subprog].is_cb = true; if (bpf_pseudo_kfunc_call(insn) && !is_callback_calling_kfunc(insn->imm)) { verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n", @@ -9308,7 +9424,8 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) verbose(env, "to caller at %d:\n", *insn_idx); print_verifier_state(env, caller, true); } - /* clear everything in the callee */ + /* clear everything in the callee. In case of exceptional exits using + * bpf_throw, this will be done by copy_verifier_state for extra frames. */ free_func_state(callee); state->frame[state->curframe--] = NULL; return 0; @@ -9432,17 +9549,17 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, return 0; } -static int check_reference_leak(struct bpf_verifier_env *env) +static int check_reference_leak(struct bpf_verifier_env *env, bool exception_exit) { struct bpf_func_state *state = cur_func(env); bool refs_lingering = false; int i; - if (state->frameno && !state->in_callback_fn) + if (!exception_exit && state->frameno && !state->in_callback_fn) return 0; for (i = 0; i < state->acquired_refs; i++) { - if (state->in_callback_fn && state->refs[i].callback_ref != state->frameno) + if (!exception_exit && state->in_callback_fn && state->refs[i].callback_ref != state->frameno) continue; verbose(env, "Unreleased reference id=%d alloc_insn=%d\n", state->refs[i].id, state->refs[i].insn_idx); @@ -9697,7 +9814,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn switch (func_id) { case BPF_FUNC_tail_call: - err = check_reference_leak(env); + err = check_reference_leak(env, false); if (err) { verbose(env, "tail_call would lead to reference leak\n"); return err; @@ -10332,6 +10449,7 @@ enum special_kfunc_type { KF_bpf_dynptr_clone, KF_bpf_percpu_obj_new_impl, KF_bpf_percpu_obj_drop_impl, + KF_bpf_throw, }; BTF_SET_START(special_kfunc_set) @@ -10354,6 +10472,7 @@ BTF_ID(func, bpf_dynptr_slice_rdwr) BTF_ID(func, bpf_dynptr_clone) BTF_ID(func, bpf_percpu_obj_new_impl) BTF_ID(func, bpf_percpu_obj_drop_impl) +BTF_ID(func, bpf_throw) BTF_SET_END(special_kfunc_set) BTF_ID_LIST(special_kfunc_list) @@ -10378,6 +10497,7 @@ BTF_ID(func, bpf_dynptr_slice_rdwr) BTF_ID(func, bpf_dynptr_clone) BTF_ID(func, bpf_percpu_obj_new_impl) BTF_ID(func, bpf_percpu_obj_drop_impl) +BTF_ID(func, bpf_throw) static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) { @@ -10695,6 +10815,12 @@ static bool is_callback_calling_kfunc(u32 btf_id) return btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl]; } +static bool is_bpf_throw_kfunc(struct bpf_insn *insn) +{ + return bpf_pseudo_kfunc_call(insn) && insn->off == 0 && + insn->imm == special_kfunc_list[KF_bpf_throw]; +} + static bool is_rbtree_lock_required_kfunc(u32 btf_id) { return is_bpf_rbtree_api_kfunc(btf_id); @@ -11281,6 +11407,10 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ break; } case KF_ARG_PTR_TO_CALLBACK: + if (reg->type != PTR_TO_FUNC) { + verbose(env, "arg%d expected pointer to func\n", i); + return -EINVAL; + } meta->subprogno = reg->subprogno; break; case KF_ARG_PTR_TO_REFCOUNTED_KPTR: @@ -11359,6 +11489,8 @@ static int fetch_kfunc_meta(struct bpf_verifier_env *env, return 0; } +static int check_return_code(struct bpf_verifier_env *env, int regno); + static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) { @@ -11480,6 +11612,24 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } } + if (meta.func_id == special_kfunc_list[KF_bpf_throw]) { + if (!bpf_jit_supports_exceptions()) { + verbose(env, "JIT does not support calling kfunc %s#%d\n", + func_name, meta.func_id); + return -ENOTSUPP; + } + env->seen_exception = true; + + /* In the case of the default callback, the cookie value passed + * to bpf_throw becomes the return value of the program. + */ + if (!env->exception_callback_subprog) { + err = check_return_code(env, BPF_REG_1); + if (err < 0) + return err; + } + } + for (i = 0; i < CALLER_SAVED_REGS; i++) mark_reg_not_init(env, regs, caller_saved[i]); @@ -14525,7 +14675,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) * gen_ld_abs() may terminate the program at runtime, leading to * reference leak. */ - err = check_reference_leak(env); + err = check_reference_leak(env, false); if (err) { verbose(env, "BPF_LD_[ABS|IND] cannot be mixed with socket references\n"); return err; @@ -14574,7 +14724,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } -static int check_return_code(struct bpf_verifier_env *env) +static int check_return_code(struct bpf_verifier_env *env, int regno) { struct tnum enforce_attach_type_range = tnum_unknown; const struct bpf_prog *prog = env->prog; @@ -14586,7 +14736,7 @@ static int check_return_code(struct bpf_verifier_env *env) const bool is_subprog = frame->subprogno; /* LSM and struct_ops func-ptr's return type could be "void" */ - if (!is_subprog) { + if (!is_subprog || frame->in_exception_callback_fn) { switch (prog_type) { case BPF_PROG_TYPE_LSM: if (prog->expected_attach_type == BPF_LSM_CGROUP) @@ -14608,22 +14758,22 @@ static int check_return_code(struct bpf_verifier_env *env) * of bpf_exit, which means that program wrote * something into it earlier */ - err = check_reg_arg(env, BPF_REG_0, SRC_OP); + err = check_reg_arg(env, regno, SRC_OP); if (err) return err; - if (is_pointer_value(env, BPF_REG_0)) { - verbose(env, "R0 leaks addr as return value\n"); + if (is_pointer_value(env, regno)) { + verbose(env, "R%d leaks addr as return value\n", regno); return -EACCES; } - reg = cur_regs(env) + BPF_REG_0; + reg = cur_regs(env) + regno; if (frame->in_async_callback_fn) { /* enforce return zero from async callbacks like timer */ if (reg->type != SCALAR_VALUE) { - verbose(env, "In async callback the register R0 is not a known value (%s)\n", - reg_type_str(env, reg->type)); + verbose(env, "In async callback the register R%d is not a known value (%s)\n", + regno, reg_type_str(env, reg->type)); return -EINVAL; } @@ -14634,10 +14784,10 @@ static int check_return_code(struct bpf_verifier_env *env) return 0; } - if (is_subprog) { + if (is_subprog && !frame->in_exception_callback_fn) { if (reg->type != SCALAR_VALUE) { - verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n", - reg_type_str(env, reg->type)); + verbose(env, "At subprogram exit the register R%d is not a scalar value (%s)\n", + regno, reg_type_str(env, reg->type)); return -EINVAL; } return 0; @@ -14719,8 +14869,8 @@ static int check_return_code(struct bpf_verifier_env *env) } if (reg->type != SCALAR_VALUE) { - verbose(env, "At program exit the register R0 is not a known value (%s)\n", - reg_type_str(env, reg->type)); + verbose(env, "At program exit the register R%d is not a known value (%s)\n", + regno, reg_type_str(env, reg->type)); return -EINVAL; } @@ -14991,8 +15141,8 @@ static int check_cfg(struct bpf_verifier_env *env) { int insn_cnt = env->prog->len; int *insn_stack, *insn_state; - int ret = 0; - int i; + int ex_insn_beg, i, ret = 0; + bool ex_done = false; insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_state) @@ -15008,6 +15158,7 @@ static int check_cfg(struct bpf_verifier_env *env) insn_stack[0] = 0; /* 0 is the first instruction */ env->cfg.cur_stack = 1; +walk_cfg: while (env->cfg.cur_stack > 0) { int t = insn_stack[env->cfg.cur_stack - 1]; @@ -15034,6 +15185,16 @@ static int check_cfg(struct bpf_verifier_env *env) goto err_free; } + if (env->exception_callback_subprog && !ex_done) { + ex_insn_beg = env->subprog_info[env->exception_callback_subprog].start; + + insn_state[ex_insn_beg] = DISCOVERED; + insn_stack[0] = ex_insn_beg; + env->cfg.cur_stack = 1; + ex_done = true; + goto walk_cfg; + } + for (i = 0; i < insn_cnt; i++) { if (insn_state[i] != EXPLORED) { verbose(env, "unreachable insn %d\n", i); @@ -15071,20 +15232,18 @@ static int check_abnormal_return(struct bpf_verifier_env *env) #define MIN_BPF_FUNCINFO_SIZE 8 #define MAX_FUNCINFO_REC_SIZE 252 -static int check_btf_func(struct bpf_verifier_env *env, - const union bpf_attr *attr, - bpfptr_t uattr) +static int check_btf_func_early(struct bpf_verifier_env *env, + const union bpf_attr *attr, + bpfptr_t uattr) { - const struct btf_type *type, *func_proto, *ret_type; - u32 i, nfuncs, urec_size, min_size; u32 krec_size = sizeof(struct bpf_func_info); + const struct btf_type *type, *func_proto; + u32 i, nfuncs, urec_size, min_size; struct bpf_func_info *krecord; - struct bpf_func_info_aux *info_aux = NULL; struct bpf_prog *prog; const struct btf *btf; - bpfptr_t urecord; u32 prev_offset = 0; - bool scalar_return; + bpfptr_t urecord; int ret = -ENOMEM; nfuncs = attr->func_info_cnt; @@ -15094,11 +15253,6 @@ static int check_btf_func(struct bpf_verifier_env *env, return 0; } - if (nfuncs != env->subprog_cnt) { - verbose(env, "number of funcs in func_info doesn't match number of subprogs\n"); - return -EINVAL; - } - urec_size = attr->func_info_rec_size; if (urec_size < MIN_BPF_FUNCINFO_SIZE || urec_size > MAX_FUNCINFO_REC_SIZE || @@ -15116,9 +15270,6 @@ static int check_btf_func(struct bpf_verifier_env *env, krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN); if (!krecord) return -ENOMEM; - info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN); - if (!info_aux) - goto err_free; for (i = 0; i < nfuncs; i++) { ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size); @@ -15157,11 +15308,6 @@ static int check_btf_func(struct bpf_verifier_env *env, goto err_free; } - if (env->subprog_info[i].start != krecord[i].insn_off) { - verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n"); - goto err_free; - } - /* check type_id */ type = btf_type_by_id(btf, krecord[i].type_id); if (!type || !btf_type_is_func(type)) { @@ -15169,12 +15315,80 @@ static int check_btf_func(struct bpf_verifier_env *env, krecord[i].type_id); goto err_free; } - info_aux[i].linkage = BTF_INFO_VLEN(type->info); func_proto = btf_type_by_id(btf, type->type); if (unlikely(!func_proto || !btf_type_is_func_proto(func_proto))) /* btf_func_check() already verified it during BTF load */ goto err_free; + + prev_offset = krecord[i].insn_off; + bpfptr_add(&urecord, urec_size); + } + + prog->aux->func_info = krecord; + prog->aux->func_info_cnt = nfuncs; + return 0; + +err_free: + kvfree(krecord); + return ret; +} + +static int check_btf_func(struct bpf_verifier_env *env, + const union bpf_attr *attr, + bpfptr_t uattr) +{ + const struct btf_type *type, *func_proto, *ret_type; + u32 i, nfuncs, urec_size, min_size; + u32 krec_size = sizeof(struct bpf_func_info); + struct bpf_func_info *krecord; + struct bpf_func_info_aux *info_aux = NULL; + struct bpf_prog *prog; + const struct btf *btf; + bpfptr_t urecord; + u32 prev_offset = 0; + bool scalar_return; + int ret = -ENOMEM; + + nfuncs = attr->func_info_cnt; + if (!nfuncs) { + if (check_abnormal_return(env)) + return -EINVAL; + return 0; + } + if (nfuncs != env->subprog_cnt) { + verbose(env, "number of funcs in func_info doesn't match number of subprogs\n"); + return -EINVAL; + } + + urec_size = attr->func_info_rec_size; + + prog = env->prog; + btf = prog->aux->btf; + + urecord = make_bpfptr(attr->func_info, uattr.is_kernel); + min_size = min_t(u32, krec_size, urec_size); + + krecord = prog->aux->func_info; + info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN); + if (!info_aux) + return -ENOMEM; + + for (i = 0; i < nfuncs; i++) { + /* check insn_off */ + ret = -EINVAL; + + if (env->subprog_info[i].start != krecord[i].insn_off) { + verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n"); + goto err_free; + } + + /* Already checked type_id */ + type = btf_type_by_id(btf, krecord[i].type_id); + info_aux[i].linkage = BTF_INFO_VLEN(type->info); + /* Already checked func_proto */ + func_proto = btf_type_by_id(btf, type->type); + ret_type = btf_type_skip_modifiers(btf, func_proto->type, NULL); scalar_return = btf_type_is_small_int(ret_type) || btf_is_any_enum(ret_type); @@ -15191,13 +15405,10 @@ static int check_btf_func(struct bpf_verifier_env *env, bpfptr_add(&urecord, urec_size); } - prog->aux->func_info = krecord; - prog->aux->func_info_cnt = nfuncs; prog->aux->func_info_aux = info_aux; return 0; err_free: - kvfree(krecord); kfree(info_aux); return ret; } @@ -15210,7 +15421,8 @@ static void adjust_btf_func(struct bpf_verifier_env *env) if (!aux->func_info) return; - for (i = 0; i < env->subprog_cnt; i++) + /* func_info is not available for hidden subprogs */ + for (i = 0; i < env->subprog_cnt - env->hidden_subprog_cnt; i++) aux->func_info[i].insn_off = env->subprog_info[i].start; } @@ -15414,9 +15626,9 @@ static int check_core_relo(struct bpf_verifier_env *env, return err; } -static int check_btf_info(struct bpf_verifier_env *env, - const union bpf_attr *attr, - bpfptr_t uattr) +static int check_btf_info_early(struct bpf_verifier_env *env, + const union bpf_attr *attr, + bpfptr_t uattr) { struct btf *btf; int err; @@ -15436,6 +15648,24 @@ static int check_btf_info(struct bpf_verifier_env *env, } env->prog->aux->btf = btf; + err = check_btf_func_early(env, attr, uattr); + if (err) + return err; + return 0; +} + +static int check_btf_info(struct bpf_verifier_env *env, + const union bpf_attr *attr, + bpfptr_t uattr) +{ + int err; + + if (!attr->func_info_cnt && !attr->line_info_cnt) { + if (check_abnormal_return(env)) + return -EINVAL; + return 0; + } + err = check_btf_func(env, attr, uattr); if (err) return err; @@ -16538,6 +16768,7 @@ static int do_check(struct bpf_verifier_env *env) int prev_insn_idx = -1; for (;;) { + bool exception_exit = false; struct bpf_insn *insn; u8 class; int err; @@ -16752,12 +16983,17 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } } - if (insn->src_reg == BPF_PSEUDO_CALL) + if (insn->src_reg == BPF_PSEUDO_CALL) { err = check_func_call(env, insn, &env->insn_idx); - else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) + } else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { err = check_kfunc_call(env, insn, &env->insn_idx); - else + if (!err && is_bpf_throw_kfunc(insn)) { + exception_exit = true; + goto process_bpf_exit_full; + } + } else { err = check_helper_call(env, insn, &env->insn_idx); + } if (err) return err; @@ -16787,7 +17023,7 @@ static int do_check(struct bpf_verifier_env *env) verbose(env, "BPF_EXIT uses reserved fields\n"); return -EINVAL; } - +process_bpf_exit_full: if (env->cur_state->active_lock.ptr && !in_rbtree_lock_required_cb(env)) { verbose(env, "bpf_spin_unlock is missing\n"); @@ -16806,10 +17042,23 @@ static int do_check(struct bpf_verifier_env *env) * function, for which reference_state must * match caller reference state when it exits. */ - err = check_reference_leak(env); + err = check_reference_leak(env, exception_exit); if (err) return err; + /* The side effect of the prepare_func_exit + * which is being skipped is that it frees + * bpf_func_state. Typically, process_bpf_exit + * will only be hit with outermost exit. + * copy_verifier_state in pop_stack will handle + * freeing of any extra bpf_func_state left over + * from not processing all nested function + * exits. We also skip return code checks as + * they are not needed for exceptional exits. + */ + if (exception_exit) + goto process_bpf_exit; + if (state->curframe) { /* exit from nested function */ err = prepare_func_exit(env, &env->insn_idx); @@ -16819,7 +17068,7 @@ static int do_check(struct bpf_verifier_env *env) continue; } - err = check_return_code(env); + err = check_return_code(env, BPF_REG_0); if (err) return err; process_bpf_exit: @@ -18112,6 +18361,9 @@ static int jit_subprogs(struct bpf_verifier_env *env) } func[i]->aux->num_exentries = num_exentries; func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable; + func[i]->aux->exception_cb = env->subprog_info[i].is_exception_cb; + if (!i) + func[i]->aux->exception_boundary = env->seen_exception; func[i] = bpf_int_jit_compile(func[i]); if (!func[i]->jited) { err = -ENOTSUPP; @@ -18151,7 +18403,8 @@ static int jit_subprogs(struct bpf_verifier_env *env) * the call instruction, as an index for this list */ func[i]->aux->func = func; - func[i]->aux->func_cnt = env->subprog_cnt; + func[i]->aux->func_cnt = env->subprog_cnt - env->hidden_subprog_cnt; + func[i]->aux->real_func_cnt = env->subprog_cnt; } for (i = 0; i < env->subprog_cnt; i++) { old_bpf_func = func[i]->bpf_func; @@ -18197,7 +18450,10 @@ static int jit_subprogs(struct bpf_verifier_env *env) prog->aux->extable = func[0]->aux->extable; prog->aux->num_exentries = func[0]->aux->num_exentries; prog->aux->func = func; - prog->aux->func_cnt = env->subprog_cnt; + prog->aux->func_cnt = env->subprog_cnt - env->hidden_subprog_cnt; + prog->aux->real_func_cnt = env->subprog_cnt; + prog->aux->bpf_exception_cb = (void *)func[env->exception_callback_subprog]->bpf_func; + prog->aux->exception_boundary = func[0]->aux->exception_boundary; bpf_prog_jit_attempt_done(prog); return 0; out_free: @@ -18433,6 +18689,33 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return 0; } +/* The function requires that first instruction in 'patch' is insnsi[prog->len - 1] */ +static int add_hidden_subprog(struct bpf_verifier_env *env, struct bpf_insn *patch, int len) +{ + struct bpf_subprog_info *info = env->subprog_info; + int cnt = env->subprog_cnt; + struct bpf_prog *prog; + + /* We only reserve one slot for hidden subprogs in subprog_info. */ + if (env->hidden_subprog_cnt) { + verbose(env, "verifier internal error: only one hidden subprog supported\n"); + return -EFAULT; + } + /* We're not patching any existing instruction, just appending the new + * ones for the hidden subprog. Hence all of the adjustment operations + * in bpf_patch_insn_data are no-ops. + */ + prog = bpf_patch_insn_data(env, env->prog->len - 1, patch, len); + if (!prog) + return -ENOMEM; + env->prog = prog; + info[cnt + 1].start = info[cnt].start; + info[cnt].start = prog->len - len + 1; + env->subprog_cnt++; + env->hidden_subprog_cnt++; + return 0; +} + /* Do various post-verification rewrites in a single program pass. * These rewrites simplify JIT and interpreter implementations. */ @@ -18451,6 +18734,26 @@ static int do_misc_fixups(struct bpf_verifier_env *env) struct bpf_map *map_ptr; int i, ret, cnt, delta = 0; + if (env->seen_exception && !env->exception_callback_subprog) { + struct bpf_insn patch[] = { + env->prog->insnsi[insn_cnt - 1], + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }; + + ret = add_hidden_subprog(env, patch, ARRAY_SIZE(patch)); + if (ret < 0) + return ret; + prog = env->prog; + insn = prog->insnsi; + + env->exception_callback_subprog = env->subprog_cnt - 1; + /* Don't update insn_cnt, as add_hidden_subprog always appends insns */ + env->subprog_info[env->exception_callback_subprog].is_cb = true; + env->subprog_info[env->exception_callback_subprog].is_async_cb = true; + env->subprog_info[env->exception_callback_subprog].is_exception_cb = true; + } + for (i = 0; i < insn_cnt; i++, insn++) { /* Make divide-by-zero exceptions impossible. */ if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) || @@ -19148,7 +19451,7 @@ static void free_states(struct bpf_verifier_env *env) } } -static int do_check_common(struct bpf_verifier_env *env, int subprog) +static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex_cb) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); struct bpf_verifier_state *state; @@ -19179,7 +19482,7 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) regs = state->frame[state->curframe]->regs; if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) { - ret = btf_prepare_func_args(env, subprog, regs); + ret = btf_prepare_func_args(env, subprog, regs, is_ex_cb); if (ret) goto out; for (i = BPF_REG_1; i <= BPF_REG_5; i++) { @@ -19195,6 +19498,12 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) regs[i].id = ++env->id_gen; } } + if (is_ex_cb) { + state->frame[0]->in_exception_callback_fn = true; + env->subprog_info[subprog].is_cb = true; + env->subprog_info[subprog].is_async_cb = true; + env->subprog_info[subprog].is_exception_cb = true; + } } else { /* 1st arg to a function */ regs[BPF_REG_1].type = PTR_TO_CTX; @@ -19259,7 +19568,7 @@ static int do_check_subprogs(struct bpf_verifier_env *env) continue; env->insn_idx = env->subprog_info[i].start; WARN_ON_ONCE(env->insn_idx == 0); - ret = do_check_common(env, i); + ret = do_check_common(env, i, env->exception_callback_subprog == i); if (ret) { return ret; } else if (env->log.level & BPF_LOG_LEVEL) { @@ -19276,7 +19585,7 @@ static int do_check_main(struct bpf_verifier_env *env) int ret; env->insn_idx = 0; - ret = do_check_common(env, 0); + ret = do_check_common(env, 0, false); if (!ret) env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return ret; @@ -19445,6 +19754,12 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, bpf_log(log, "Subprog %s doesn't exist\n", tname); return -EINVAL; } + if (aux->func && aux->func[subprog]->aux->exception_cb) { + bpf_log(log, + "%s programs cannot attach to exception callback\n", + prog_extension ? "Extension" : "FENTRY/FEXIT"); + return -EINVAL; + } conservative = aux->func_info_aux[subprog].unreliable; if (prog_extension) { if (conservative) { @@ -19872,6 +20187,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (!env->explored_states) goto skip_full_check; + ret = check_btf_info_early(env, attr, uattr); + if (ret < 0) + goto skip_full_check; + ret = add_subprog_and_kfunc(env); if (ret < 0) goto skip_full_check; diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 2e973b36fe07..5eefe202bb8f 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -558,7 +558,6 @@ void kasan_restore_multi_shot(bool enabled); * code. Declared here to avoid warnings about missing declarations. */ -asmlinkage void kasan_unpoison_task_stack_below(const void *watermark); void __asan_register_globals(void *globals, ssize_t size); void __asan_unregister_globals(void *globals, ssize_t size); void __asan_handle_no_return(void); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 96ff1aa4bf6a..3a6108e3238b 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -436,9 +436,11 @@ struct bpf_program { int fd; bool autoload; bool autoattach; + bool sym_global; bool mark_btf_static; enum bpf_prog_type type; enum bpf_attach_type expected_attach_type; + int exception_cb_idx; int prog_ifindex; __u32 attach_btf_obj_fd; @@ -765,6 +767,7 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, prog->type = BPF_PROG_TYPE_UNSPEC; prog->fd = -1; + prog->exception_cb_idx = -1; /* libbpf's convention for SEC("?abc...") is that it's just like * SEC("abc...") but the corresponding bpf_program starts out with @@ -871,14 +874,16 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, if (err) return err; + if (ELF64_ST_BIND(sym->st_info) != STB_LOCAL) + prog->sym_global = true; + /* if function is a global/weak symbol, but has restricted * (STV_HIDDEN or STV_INTERNAL) visibility, mark its BTF FUNC * as static to enable more permissive BPF verification mode * with more outside context available to BPF verifier */ - if (ELF64_ST_BIND(sym->st_info) != STB_LOCAL - && (ELF64_ST_VISIBILITY(sym->st_other) == STV_HIDDEN - || ELF64_ST_VISIBILITY(sym->st_other) == STV_INTERNAL)) + if (prog->sym_global && (ELF64_ST_VISIBILITY(sym->st_other) == STV_HIDDEN + || ELF64_ST_VISIBILITY(sym->st_other) == STV_INTERNAL)) prog->mark_btf_static = true; nr_progs++; @@ -3142,6 +3147,86 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) } } + if (!kernel_supports(obj, FEAT_BTF_DECL_TAG)) + goto skip_exception_cb; + for (i = 0; i < obj->nr_programs; i++) { + struct bpf_program *prog = &obj->programs[i]; + int j, k, n; + + if (prog_is_subprog(obj, prog)) + continue; + n = btf__type_cnt(obj->btf); + for (j = 1; j < n; j++) { + const char *str = "exception_callback:", *name; + size_t len = strlen(str); + struct btf_type *t; + + t = btf_type_by_id(obj->btf, j); + if (!btf_is_decl_tag(t) || btf_decl_tag(t)->component_idx != -1) + continue; + + name = btf__str_by_offset(obj->btf, t->name_off); + if (strncmp(name, str, len)) + continue; + + t = btf_type_by_id(obj->btf, t->type); + if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL) { + pr_warn("prog '%s': exception_callback: decl tag not applied to the main program\n", + prog->name); + return -EINVAL; + } + if (strcmp(prog->name, btf__str_by_offset(obj->btf, t->name_off))) + continue; + /* Multiple callbacks are specified for the same prog, + * the verifier will eventually return an error for this + * case, hence simply skip appending a subprog. + */ + if (prog->exception_cb_idx >= 0) { + prog->exception_cb_idx = -1; + break; + } + + name += len; + if (str_is_empty(name)) { + pr_warn("prog '%s': exception_callback: decl tag contains empty value\n", + prog->name); + return -EINVAL; + } + + for (k = 0; k < obj->nr_programs; k++) { + struct bpf_program *subprog = &obj->programs[k]; + + if (!prog_is_subprog(obj, subprog)) + continue; + if (strcmp(name, subprog->name)) + continue; + /* Enforce non-hidden, as from verifier point of + * view it expects global functions, whereas the + * mark_btf_static fixes up linkage as static. + */ + if (!subprog->sym_global || subprog->mark_btf_static) { + pr_warn("prog '%s': exception callback %s must be a global non-hidden function\n", + prog->name, subprog->name); + return -EINVAL; + } + /* Let's see if we already saw a static exception callback with the same name */ + if (prog->exception_cb_idx >= 0) { + pr_warn("prog '%s': multiple subprogs with same name as exception callback '%s'\n", + prog->name, subprog->name); + return -EINVAL; + } + prog->exception_cb_idx = k; + break; + } + + if (prog->exception_cb_idx >= 0) + continue; + pr_warn("prog '%s': cannot find exception callback '%s'\n", prog->name, name); + return -ENOENT; + } + } +skip_exception_cb: + sanitize = btf_needs_sanitization(obj); if (sanitize) { const void *raw_data; @@ -6234,14 +6319,46 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra return 0; } +static int +bpf_object__append_subprog_code(struct bpf_object *obj, struct bpf_program *main_prog, + struct bpf_program *subprog) +{ + struct bpf_insn *insns; + size_t new_cnt; + int err; + + subprog->sub_insn_off = main_prog->insns_cnt; + + new_cnt = main_prog->insns_cnt + subprog->insns_cnt; + insns = libbpf_reallocarray(main_prog->insns, new_cnt, sizeof(*insns)); + if (!insns) { + pr_warn("prog '%s': failed to realloc prog code\n", main_prog->name); + return -ENOMEM; + } + main_prog->insns = insns; + main_prog->insns_cnt = new_cnt; + + memcpy(main_prog->insns + subprog->sub_insn_off, subprog->insns, + subprog->insns_cnt * sizeof(*insns)); + + pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n", + main_prog->name, subprog->insns_cnt, subprog->name); + + /* The subprog insns are now appended. Append its relos too. */ + err = append_subprog_relos(main_prog, subprog); + if (err) + return err; + return 0; +} + static int bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog, struct bpf_program *prog) { - size_t sub_insn_idx, insn_idx, new_cnt; + size_t sub_insn_idx, insn_idx; struct bpf_program *subprog; - struct bpf_insn *insns, *insn; struct reloc_desc *relo; + struct bpf_insn *insn; int err; err = reloc_prog_func_and_line_info(obj, main_prog, prog); @@ -6316,25 +6433,7 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog, * and relocate. */ if (subprog->sub_insn_off == 0) { - subprog->sub_insn_off = main_prog->insns_cnt; - - new_cnt = main_prog->insns_cnt + subprog->insns_cnt; - insns = libbpf_reallocarray(main_prog->insns, new_cnt, sizeof(*insns)); - if (!insns) { - pr_warn("prog '%s': failed to realloc prog code\n", main_prog->name); - return -ENOMEM; - } - main_prog->insns = insns; - main_prog->insns_cnt = new_cnt; - - memcpy(main_prog->insns + subprog->sub_insn_off, subprog->insns, - subprog->insns_cnt * sizeof(*insns)); - - pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n", - main_prog->name, subprog->insns_cnt, subprog->name); - - /* The subprog insns are now appended. Append its relos too. */ - err = append_subprog_relos(main_prog, subprog); + err = bpf_object__append_subprog_code(obj, main_prog, subprog); if (err) return err; err = bpf_object__reloc_code(obj, main_prog, subprog); @@ -6568,6 +6667,25 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) prog->name, err); return err; } + + /* Now, also append exception callback if it has not been done already. */ + if (prog->exception_cb_idx >= 0) { + struct bpf_program *subprog = &obj->programs[prog->exception_cb_idx]; + + /* Calling exception callback directly is disallowed, which the + * verifier will reject later. In case it was processed already, + * we can skip this step, otherwise for all other valid cases we + * have to append exception callback now. + */ + if (subprog->sub_insn_off == 0) { + err = bpf_object__append_subprog_code(obj, prog, subprog); + if (err) + return err; + err = bpf_object__reloc_code(obj, prog, subprog); + if (err) + return err; + } + } } /* Process data relos for main programs */ for (i = 0; i < obj->nr_programs; i++) { diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64 index 7f768d335698..f5065576cae9 100644 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ b/tools/testing/selftests/bpf/DENYLIST.aarch64 @@ -1,5 +1,6 @@ bpf_cookie/multi_kprobe_attach_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3 bpf_cookie/multi_kprobe_link_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3 +exceptions # JIT does not support calling kfunc bpf_throw: -524 fexit_sleep # The test never returns. The remaining tests cannot start. kprobe_multi_bench_attach # bpf_program__attach_kprobe_multi_opts unexpected error: -95 kprobe_multi_test/attach_api_addrs # bpf_program__attach_kprobe_multi_opts unexpected error: -95 diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x index 5061d9e24c16..ce6f291665cf 100644 --- a/tools/testing/selftests/bpf/DENYLIST.s390x +++ b/tools/testing/selftests/bpf/DENYLIST.s390x @@ -6,6 +6,7 @@ bpf_loop # attaches to __x64_sys_nanosleep cgrp_local_storage # prog_attach unexpected error: -524 (trampoline) dynptr/test_dynptr_skb_data dynptr/test_skb_readonly +exceptions # JIT does not support calling kfunc bpf_throw (exceptions) fexit_sleep # fexit_skel_load fexit skeleton failed (trampoline) get_stack_raw_tp # user_stack corrupted user stack (no backchain userspace) iters/testmod_seq* # s390x doesn't support kfuncs in modules yet diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h index 4494eaa9937e..9aa29564bd74 100644 --- a/tools/testing/selftests/bpf/bpf_experimental.h +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -162,4 +162,292 @@ extern void bpf_percpu_obj_drop_impl(void *kptr, void *meta) __ksym; /* Convenience macro to wrap over bpf_obj_drop_impl */ #define bpf_percpu_obj_drop(kptr) bpf_percpu_obj_drop_impl(kptr, NULL) +/* Description + * Throw a BPF exception from the program, immediately terminating its + * execution and unwinding the stack. The supplied 'cookie' parameter + * will be the return value of the program when an exception is thrown, + * and the default exception callback is used. Otherwise, if an exception + * callback is set using the '__exception_cb(callback)' declaration tag + * on the main program, the 'cookie' parameter will be the callback's only + * input argument. + * + * Thus, in case of default exception callback, 'cookie' is subjected to + * constraints on the program's return value (as with R0 on exit). + * Otherwise, the return value of the marked exception callback will be + * subjected to the same checks. + * + * Note that throwing an exception with lingering resources (locks, + * references, etc.) will lead to a verification error. + * + * Note that callbacks *cannot* call this helper. + * Returns + * Never. + * Throws + * An exception with the specified 'cookie' value. + */ +extern void bpf_throw(u64 cookie) __ksym; + +/* This macro must be used to mark the exception callback corresponding to the + * main program. For example: + * + * int exception_cb(u64 cookie) { + * return cookie; + * } + * + * SEC("tc") + * __exception_cb(exception_cb) + * int main_prog(struct __sk_buff *ctx) { + * ... + * return TC_ACT_OK; + * } + * + * Here, exception callback for the main program will be 'exception_cb'. Note + * that this attribute can only be used once, and multiple exception callbacks + * specified for the main program will lead to verification error. + */ +#define __exception_cb(name) __attribute__((btf_decl_tag("exception_callback:" #name))) + +#define __bpf_assert_signed(x) _Generic((x), \ + unsigned long: 0, \ + unsigned long long: 0, \ + signed long: 1, \ + signed long long: 1 \ +) + +#define __bpf_assert_check(LHS, op, RHS) \ + _Static_assert(sizeof(&(LHS)), "1st argument must be an lvalue expression"); \ + _Static_assert(sizeof(LHS) == 8, "Only 8-byte integers are supported\n"); \ + _Static_assert(__builtin_constant_p(__bpf_assert_signed(LHS)), "internal static assert"); \ + _Static_assert(__builtin_constant_p((RHS)), "2nd argument must be a constant expression") + +#define __bpf_assert(LHS, op, cons, RHS, VAL) \ + ({ \ + (void)bpf_throw; \ + asm volatile ("if %[lhs] " op " %[rhs] goto +2; r1 = %[value]; call bpf_throw" \ + : : [lhs] "r"(LHS), [rhs] cons(RHS), [value] "ri"(VAL) : ); \ + }) + +#define __bpf_assert_op_sign(LHS, op, cons, RHS, VAL, supp_sign) \ + ({ \ + __bpf_assert_check(LHS, op, RHS); \ + if (__bpf_assert_signed(LHS) && !(supp_sign)) \ + __bpf_assert(LHS, "s" #op, cons, RHS, VAL); \ + else \ + __bpf_assert(LHS, #op, cons, RHS, VAL); \ + }) + +#define __bpf_assert_op(LHS, op, RHS, VAL, supp_sign) \ + ({ \ + if (sizeof(typeof(RHS)) == 8) { \ + const typeof(RHS) rhs_var = (RHS); \ + __bpf_assert_op_sign(LHS, op, "r", rhs_var, VAL, supp_sign); \ + } else { \ + __bpf_assert_op_sign(LHS, op, "i", RHS, VAL, supp_sign); \ + } \ + }) + +/* Description + * Assert that a conditional expression is true. + * Returns + * Void. + * Throws + * An exception with the value zero when the assertion fails. + */ +#define bpf_assert(cond) if (!(cond)) bpf_throw(0); + +/* Description + * Assert that a conditional expression is true. + * Returns + * Void. + * Throws + * An exception with the specified value when the assertion fails. + */ +#define bpf_assert_with(cond, value) if (!(cond)) bpf_throw(value); + +/* Description + * Assert that LHS is equal to RHS. This statement updates the known value + * of LHS during verification. Note that RHS must be a constant value, and + * must fit within the data type of LHS. + * Returns + * Void. + * Throws + * An exception with the value zero when the assertion fails. + */ +#define bpf_assert_eq(LHS, RHS) \ + ({ \ + barrier_var(LHS); \ + __bpf_assert_op(LHS, ==, RHS, 0, true); \ + }) + +/* Description + * Assert that LHS is equal to RHS. This statement updates the known value + * of LHS during verification. Note that RHS must be a constant value, and + * must fit within the data type of LHS. + * Returns + * Void. + * Throws + * An exception with the specified value when the assertion fails. + */ +#define bpf_assert_eq_with(LHS, RHS, value) \ + ({ \ + barrier_var(LHS); \ + __bpf_assert_op(LHS, ==, RHS, value, true); \ + }) + +/* Description + * Assert that LHS is less than RHS. This statement updates the known + * bounds of LHS during verification. Note that RHS must be a constant + * value, and must fit within the data type of LHS. + * Returns + * Void. + * Throws + * An exception with the value zero when the assertion fails. + */ +#define bpf_assert_lt(LHS, RHS) \ + ({ \ + barrier_var(LHS); \ + __bpf_assert_op(LHS, <, RHS, 0, false); \ + }) + +/* Description + * Assert that LHS is less than RHS. This statement updates the known + * bounds of LHS during verification. Note that RHS must be a constant + * value, and must fit within the data type of LHS. + * Returns + * Void. + * Throws + * An exception with the specified value when the assertion fails. + */ +#define bpf_assert_lt_with(LHS, RHS, value) \ + ({ \ + barrier_var(LHS); \ + __bpf_assert_op(LHS, <, RHS, value, false); \ + }) + +/* Description + * Assert that LHS is greater than RHS. This statement updates the known + * bounds of LHS during verification. Note that RHS must be a constant + * value, and must fit within the data type of LHS. + * Returns + * Void. + * Throws + * An exception with the value zero when the assertion fails. + */ +#define bpf_assert_gt(LHS, RHS) \ + ({ \ + barrier_var(LHS); \ + __bpf_assert_op(LHS, >, RHS, 0, false); \ + }) + +/* Description + * Assert that LHS is greater than RHS. This statement updates the known + * bounds of LHS during verification. Note that RHS must be a constant + * value, and must fit within the data type of LHS. + * Returns + * Void. + * Throws + * An exception with the specified value when the assertion fails. + */ +#define bpf_assert_gt_with(LHS, RHS, value) \ + ({ \ + barrier_var(LHS); \ + __bpf_assert_op(LHS, >, RHS, value, false); \ + }) + +/* Description + * Assert that LHS is less than or equal to RHS. This statement updates the + * known bounds of LHS during verification. Note that RHS must be a + * constant value, and must fit within the data type of LHS. + * Returns + * Void. + * Throws + * An exception with the value zero when the assertion fails. + */ +#define bpf_assert_le(LHS, RHS) \ + ({ \ + barrier_var(LHS); \ + __bpf_assert_op(LHS, <=, RHS, 0, false); \ + }) + +/* Description + * Assert that LHS is less than or equal to RHS. This statement updates the + * known bounds of LHS during verification. Note that RHS must be a + * constant value, and must fit within the data type of LHS. + * Returns + * Void. + * Throws + * An exception with the specified value when the assertion fails. + */ +#define bpf_assert_le_with(LHS, RHS, value) \ + ({ \ + barrier_var(LHS); \ + __bpf_assert_op(LHS, <=, RHS, value, false); \ + }) + +/* Description + * Assert that LHS is greater than or equal to RHS. This statement updates + * the known bounds of LHS during verification. Note that RHS must be a + * constant value, and must fit within the data type of LHS. + * Returns + * Void. + * Throws + * An exception with the value zero when the assertion fails. + */ +#define bpf_assert_ge(LHS, RHS) \ + ({ \ + barrier_var(LHS); \ + __bpf_assert_op(LHS, >=, RHS, 0, false); \ + }) + +/* Description + * Assert that LHS is greater than or equal to RHS. This statement updates + * the known bounds of LHS during verification. Note that RHS must be a + * constant value, and must fit within the data type of LHS. + * Returns + * Void. + * Throws + * An exception with the specified value when the assertion fails. + */ +#define bpf_assert_ge_with(LHS, RHS, value) \ + ({ \ + barrier_var(LHS); \ + __bpf_assert_op(LHS, >=, RHS, value, false); \ + }) + +/* Description + * Assert that LHS is in the range [BEG, END] (inclusive of both). This + * statement updates the known bounds of LHS during verification. Note + * that both BEG and END must be constant values, and must fit within the + * data type of LHS. + * Returns + * Void. + * Throws + * An exception with the value zero when the assertion fails. + */ +#define bpf_assert_range(LHS, BEG, END) \ + ({ \ + _Static_assert(BEG <= END, "BEG must be <= END"); \ + barrier_var(LHS); \ + __bpf_assert_op(LHS, >=, BEG, 0, false); \ + __bpf_assert_op(LHS, <=, END, 0, false); \ + }) + +/* Description + * Assert that LHS is in the range [BEG, END] (inclusive of both). This + * statement updates the known bounds of LHS during verification. Note + * that both BEG and END must be constant values, and must fit within the + * data type of LHS. + * Returns + * Void. + * Throws + * An exception with the specified value when the assertion fails. + */ +#define bpf_assert_range_with(LHS, BEG, END, value) \ + ({ \ + _Static_assert(BEG <= END, "BEG must be <= END"); \ + barrier_var(LHS); \ + __bpf_assert_op(LHS, >=, BEG, value, false); \ + __bpf_assert_op(LHS, <=, END, value, false); \ + }) + #endif diff --git a/tools/testing/selftests/bpf/prog_tests/exceptions.c b/tools/testing/selftests/bpf/prog_tests/exceptions.c new file mode 100644 index 000000000000..5663e427dc00 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/exceptions.c @@ -0,0 +1,408 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include + +#include "exceptions.skel.h" +#include "exceptions_ext.skel.h" +#include "exceptions_fail.skel.h" +#include "exceptions_assert.skel.h" + +static char log_buf[1024 * 1024]; + +static void test_exceptions_failure(void) +{ + RUN_TESTS(exceptions_fail); +} + +static void test_exceptions_success(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, ropts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + struct exceptions_ext *eskel = NULL; + struct exceptions *skel; + int ret; + + skel = exceptions__open(); + if (!ASSERT_OK_PTR(skel, "exceptions__open")) + return; + + ret = exceptions__load(skel); + if (!ASSERT_OK(ret, "exceptions__load")) + goto done; + + if (!ASSERT_OK(bpf_map_update_elem(bpf_map__fd(skel->maps.jmp_table), &(int){0}, + &(int){bpf_program__fd(skel->progs.exception_tail_call_target)}, BPF_ANY), + "bpf_map_update_elem jmp_table")) + goto done; + +#define RUN_SUCCESS(_prog, return_val) \ + if (!test__start_subtest(#_prog)) goto _prog##_##return_val; \ + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs._prog), &ropts); \ + ASSERT_OK(ret, #_prog " prog run ret"); \ + ASSERT_EQ(ropts.retval, return_val, #_prog " prog run retval"); \ + _prog##_##return_val: + + RUN_SUCCESS(exception_throw_always_1, 64); + RUN_SUCCESS(exception_throw_always_2, 32); + RUN_SUCCESS(exception_throw_unwind_1, 16); + RUN_SUCCESS(exception_throw_unwind_2, 32); + RUN_SUCCESS(exception_throw_default, 0); + RUN_SUCCESS(exception_throw_default_value, 5); + RUN_SUCCESS(exception_tail_call, 24); + RUN_SUCCESS(exception_ext, 0); + RUN_SUCCESS(exception_ext_mod_cb_runtime, 35); + RUN_SUCCESS(exception_throw_subprog, 1); + RUN_SUCCESS(exception_assert_nz_gfunc, 1); + RUN_SUCCESS(exception_assert_zero_gfunc, 1); + RUN_SUCCESS(exception_assert_neg_gfunc, 1); + RUN_SUCCESS(exception_assert_pos_gfunc, 1); + RUN_SUCCESS(exception_assert_negeq_gfunc, 1); + RUN_SUCCESS(exception_assert_poseq_gfunc, 1); + RUN_SUCCESS(exception_assert_nz_gfunc_with, 1); + RUN_SUCCESS(exception_assert_zero_gfunc_with, 1); + RUN_SUCCESS(exception_assert_neg_gfunc_with, 1); + RUN_SUCCESS(exception_assert_pos_gfunc_with, 1); + RUN_SUCCESS(exception_assert_negeq_gfunc_with, 1); + RUN_SUCCESS(exception_assert_poseq_gfunc_with, 1); + RUN_SUCCESS(exception_bad_assert_nz_gfunc, 0); + RUN_SUCCESS(exception_bad_assert_zero_gfunc, 0); + RUN_SUCCESS(exception_bad_assert_neg_gfunc, 0); + RUN_SUCCESS(exception_bad_assert_pos_gfunc, 0); + RUN_SUCCESS(exception_bad_assert_negeq_gfunc, 0); + RUN_SUCCESS(exception_bad_assert_poseq_gfunc, 0); + RUN_SUCCESS(exception_bad_assert_nz_gfunc_with, 100); + RUN_SUCCESS(exception_bad_assert_zero_gfunc_with, 105); + RUN_SUCCESS(exception_bad_assert_neg_gfunc_with, 200); + RUN_SUCCESS(exception_bad_assert_pos_gfunc_with, 0); + RUN_SUCCESS(exception_bad_assert_negeq_gfunc_with, 101); + RUN_SUCCESS(exception_bad_assert_poseq_gfunc_with, 99); + RUN_SUCCESS(exception_assert_range, 1); + RUN_SUCCESS(exception_assert_range_with, 1); + RUN_SUCCESS(exception_bad_assert_range, 0); + RUN_SUCCESS(exception_bad_assert_range_with, 10); + +#define RUN_EXT(load_ret, attach_err, expr, msg, after_link) \ + { \ + LIBBPF_OPTS(bpf_object_open_opts, o, .kernel_log_buf = log_buf, \ + .kernel_log_size = sizeof(log_buf), \ + .kernel_log_level = 2); \ + exceptions_ext__destroy(eskel); \ + eskel = exceptions_ext__open_opts(&o); \ + struct bpf_program *prog = NULL; \ + struct bpf_link *link = NULL; \ + if (!ASSERT_OK_PTR(eskel, "exceptions_ext__open")) \ + goto done; \ + (expr); \ + ASSERT_OK_PTR(bpf_program__name(prog), bpf_program__name(prog)); \ + if (!ASSERT_EQ(exceptions_ext__load(eskel), load_ret, \ + "exceptions_ext__load")) { \ + printf("%s\n", log_buf); \ + goto done; \ + } \ + if (load_ret != 0) { \ + printf("%s\n", log_buf); \ + if (!ASSERT_OK_PTR(strstr(log_buf, msg), "strstr")) \ + goto done; \ + } \ + if (!load_ret && attach_err) { \ + if (!ASSERT_ERR_PTR(link = bpf_program__attach(prog), "attach err")) \ + goto done; \ + } else if (!load_ret) { \ + if (!ASSERT_OK_PTR(link = bpf_program__attach(prog), "attach ok")) \ + goto done; \ + (void)(after_link); \ + bpf_link__destroy(link); \ + } \ + } + + if (test__start_subtest("non-throwing fentry -> exception_cb")) + RUN_EXT(-EINVAL, true, ({ + prog = eskel->progs.pfentry; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime), + "exception_cb_mod"), "set_attach_target")) + goto done; + }), "FENTRY/FEXIT programs cannot attach to exception callback", 0); + + if (test__start_subtest("throwing fentry -> exception_cb")) + RUN_EXT(-EINVAL, true, ({ + prog = eskel->progs.throwing_fentry; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime), + "exception_cb_mod"), "set_attach_target")) + goto done; + }), "FENTRY/FEXIT programs cannot attach to exception callback", 0); + + if (test__start_subtest("non-throwing fexit -> exception_cb")) + RUN_EXT(-EINVAL, true, ({ + prog = eskel->progs.pfexit; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime), + "exception_cb_mod"), "set_attach_target")) + goto done; + }), "FENTRY/FEXIT programs cannot attach to exception callback", 0); + + if (test__start_subtest("throwing fexit -> exception_cb")) + RUN_EXT(-EINVAL, true, ({ + prog = eskel->progs.throwing_fexit; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime), + "exception_cb_mod"), "set_attach_target")) + goto done; + }), "FENTRY/FEXIT programs cannot attach to exception callback", 0); + + if (test__start_subtest("throwing extension (with custom cb) -> exception_cb")) + RUN_EXT(-EINVAL, true, ({ + prog = eskel->progs.throwing_exception_cb_extension; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime), + "exception_cb_mod"), "set_attach_target")) + goto done; + }), "Extension programs cannot attach to exception callback", 0); + + if (test__start_subtest("throwing extension -> global func in exception_cb")) + RUN_EXT(0, false, ({ + prog = eskel->progs.throwing_exception_cb_extension; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime), + "exception_cb_mod_global"), "set_attach_target")) + goto done; + }), "", ({ RUN_SUCCESS(exception_ext_mod_cb_runtime, 131); })); + + if (test__start_subtest("throwing extension (with custom cb) -> global func in exception_cb")) + RUN_EXT(0, false, ({ + prog = eskel->progs.throwing_extension; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_ext), + "exception_ext_global"), "set_attach_target")) + goto done; + }), "", ({ RUN_SUCCESS(exception_ext, 128); })); + + if (test__start_subtest("non-throwing fentry -> non-throwing subprog")) + /* non-throwing fentry -> non-throwing subprog : OK */ + RUN_EXT(0, false, ({ + prog = eskel->progs.pfentry; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "subprog"), "set_attach_target")) + goto done; + }), "", 0); + + if (test__start_subtest("throwing fentry -> non-throwing subprog")) + /* throwing fentry -> non-throwing subprog : OK */ + RUN_EXT(0, false, ({ + prog = eskel->progs.throwing_fentry; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "subprog"), "set_attach_target")) + goto done; + }), "", 0); + + if (test__start_subtest("non-throwing fentry -> throwing subprog")) + /* non-throwing fentry -> throwing subprog : OK */ + RUN_EXT(0, false, ({ + prog = eskel->progs.pfentry; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "throwing_subprog"), "set_attach_target")) + goto done; + }), "", 0); + + if (test__start_subtest("throwing fentry -> throwing subprog")) + /* throwing fentry -> throwing subprog : OK */ + RUN_EXT(0, false, ({ + prog = eskel->progs.throwing_fentry; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "throwing_subprog"), "set_attach_target")) + goto done; + }), "", 0); + + if (test__start_subtest("non-throwing fexit -> non-throwing subprog")) + /* non-throwing fexit -> non-throwing subprog : OK */ + RUN_EXT(0, false, ({ + prog = eskel->progs.pfexit; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "subprog"), "set_attach_target")) + goto done; + }), "", 0); + + if (test__start_subtest("throwing fexit -> non-throwing subprog")) + /* throwing fexit -> non-throwing subprog : OK */ + RUN_EXT(0, false, ({ + prog = eskel->progs.throwing_fexit; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "subprog"), "set_attach_target")) + goto done; + }), "", 0); + + if (test__start_subtest("non-throwing fexit -> throwing subprog")) + /* non-throwing fexit -> throwing subprog : OK */ + RUN_EXT(0, false, ({ + prog = eskel->progs.pfexit; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "throwing_subprog"), "set_attach_target")) + goto done; + }), "", 0); + + if (test__start_subtest("throwing fexit -> throwing subprog")) + /* throwing fexit -> throwing subprog : OK */ + RUN_EXT(0, false, ({ + prog = eskel->progs.throwing_fexit; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "throwing_subprog"), "set_attach_target")) + goto done; + }), "", 0); + + /* fmod_ret not allowed for subprog - Check so we remember to handle its + * throwing specification compatibility with target when supported. + */ + if (test__start_subtest("non-throwing fmod_ret -> non-throwing subprog")) + RUN_EXT(-EINVAL, true, ({ + prog = eskel->progs.pfmod_ret; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "subprog"), "set_attach_target")) + goto done; + }), "can't modify return codes of BPF program", 0); + + /* fmod_ret not allowed for subprog - Check so we remember to handle its + * throwing specification compatibility with target when supported. + */ + if (test__start_subtest("non-throwing fmod_ret -> non-throwing global subprog")) + RUN_EXT(-EINVAL, true, ({ + prog = eskel->progs.pfmod_ret; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "global_subprog"), "set_attach_target")) + goto done; + }), "can't modify return codes of BPF program", 0); + + if (test__start_subtest("non-throwing extension -> non-throwing subprog")) + /* non-throwing extension -> non-throwing subprog : BAD (!global) */ + RUN_EXT(-EINVAL, true, ({ + prog = eskel->progs.extension; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "subprog"), "set_attach_target")) + goto done; + }), "subprog() is not a global function", 0); + + if (test__start_subtest("non-throwing extension -> throwing subprog")) + /* non-throwing extension -> throwing subprog : BAD (!global) */ + RUN_EXT(-EINVAL, true, ({ + prog = eskel->progs.extension; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "throwing_subprog"), "set_attach_target")) + goto done; + }), "throwing_subprog() is not a global function", 0); + + if (test__start_subtest("non-throwing extension -> non-throwing subprog")) + /* non-throwing extension -> non-throwing global subprog : OK */ + RUN_EXT(0, false, ({ + prog = eskel->progs.extension; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "global_subprog"), "set_attach_target")) + goto done; + }), "", 0); + + if (test__start_subtest("non-throwing extension -> throwing global subprog")) + /* non-throwing extension -> throwing global subprog : OK */ + RUN_EXT(0, false, ({ + prog = eskel->progs.extension; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "throwing_global_subprog"), "set_attach_target")) + goto done; + }), "", 0); + + if (test__start_subtest("throwing extension -> throwing global subprog")) + /* throwing extension -> throwing global subprog : OK */ + RUN_EXT(0, false, ({ + prog = eskel->progs.throwing_extension; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "throwing_global_subprog"), "set_attach_target")) + goto done; + }), "", 0); + + if (test__start_subtest("throwing extension -> non-throwing global subprog")) + /* throwing extension -> non-throwing global subprog : OK */ + RUN_EXT(0, false, ({ + prog = eskel->progs.throwing_extension; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "global_subprog"), "set_attach_target")) + goto done; + }), "", 0); + + if (test__start_subtest("non-throwing extension -> main subprog")) + /* non-throwing extension -> main subprog : OK */ + RUN_EXT(0, false, ({ + prog = eskel->progs.extension; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "exception_throw_subprog"), "set_attach_target")) + goto done; + }), "", 0); + + if (test__start_subtest("throwing extension -> main subprog")) + /* throwing extension -> main subprog : OK */ + RUN_EXT(0, false, ({ + prog = eskel->progs.throwing_extension; + bpf_program__set_autoload(prog, true); + if (!ASSERT_OK(bpf_program__set_attach_target(prog, + bpf_program__fd(skel->progs.exception_throw_subprog), + "exception_throw_subprog"), "set_attach_target")) + goto done; + }), "", 0); + +done: + exceptions_ext__destroy(eskel); + exceptions__destroy(skel); +} + +static void test_exceptions_assertions(void) +{ + RUN_TESTS(exceptions_assert); +} + +void test_exceptions(void) +{ + test_exceptions_success(); + test_exceptions_failure(); + test_exceptions_assertions(); +} diff --git a/tools/testing/selftests/bpf/progs/exceptions.c b/tools/testing/selftests/bpf/progs/exceptions.c new file mode 100644 index 000000000000..2811ee842b01 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/exceptions.c @@ -0,0 +1,368 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include "bpf_misc.h" +#include "bpf_experimental.h" + +#ifndef ETH_P_IP +#define ETH_P_IP 0x0800 +#endif + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 4); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + +static __noinline int static_func(u64 i) +{ + bpf_throw(32); + return i; +} + +__noinline int global2static_simple(u64 i) +{ + static_func(i + 2); + return i - 1; +} + +__noinline int global2static(u64 i) +{ + if (i == ETH_P_IP) + bpf_throw(16); + return static_func(i); +} + +static __noinline int static2global(u64 i) +{ + return global2static(i) + i; +} + +SEC("tc") +int exception_throw_always_1(struct __sk_buff *ctx) +{ + bpf_throw(64); + return 0; +} + +/* In this case, the global func will never be seen executing after call to + * static subprog, hence verifier will DCE the remaining instructions. Ensure we + * are resilient to that. + */ +SEC("tc") +int exception_throw_always_2(struct __sk_buff *ctx) +{ + return global2static_simple(ctx->protocol); +} + +SEC("tc") +int exception_throw_unwind_1(struct __sk_buff *ctx) +{ + return static2global(bpf_ntohs(ctx->protocol)); +} + +SEC("tc") +int exception_throw_unwind_2(struct __sk_buff *ctx) +{ + return static2global(bpf_ntohs(ctx->protocol) - 1); +} + +SEC("tc") +int exception_throw_default(struct __sk_buff *ctx) +{ + bpf_throw(0); + return 1; +} + +SEC("tc") +int exception_throw_default_value(struct __sk_buff *ctx) +{ + bpf_throw(5); + return 1; +} + +SEC("tc") +int exception_tail_call_target(struct __sk_buff *ctx) +{ + bpf_throw(16); + return 0; +} + +static __noinline +int exception_tail_call_subprog(struct __sk_buff *ctx) +{ + volatile int ret = 10; + + bpf_tail_call_static(ctx, &jmp_table, 0); + return ret; +} + +SEC("tc") +int exception_tail_call(struct __sk_buff *ctx) { + volatile int ret = 0; + + ret = exception_tail_call_subprog(ctx); + return ret + 8; +} + +__noinline int exception_ext_global(struct __sk_buff *ctx) +{ + volatile int ret = 0; + + return ret; +} + +static __noinline int exception_ext_static(struct __sk_buff *ctx) +{ + return exception_ext_global(ctx); +} + +SEC("tc") +int exception_ext(struct __sk_buff *ctx) +{ + return exception_ext_static(ctx); +} + +__noinline int exception_cb_mod_global(u64 cookie) +{ + volatile int ret = 0; + + return ret; +} + +/* Example of how the exception callback supplied during verification can still + * introduce extensions by calling to dummy global functions, and alter runtime + * behavior. + * + * Right now we don't allow freplace attachment to exception callback itself, + * but if the need arises this restriction is technically feasible to relax in + * the future. + */ +__noinline int exception_cb_mod(u64 cookie) +{ + return exception_cb_mod_global(cookie) + cookie + 10; +} + +SEC("tc") +__exception_cb(exception_cb_mod) +int exception_ext_mod_cb_runtime(struct __sk_buff *ctx) +{ + bpf_throw(25); + return 0; +} + +__noinline static int subprog(struct __sk_buff *ctx) +{ + return bpf_ktime_get_ns(); +} + +__noinline static int throwing_subprog(struct __sk_buff *ctx) +{ + if (ctx->tstamp) + bpf_throw(0); + return bpf_ktime_get_ns(); +} + +__noinline int global_subprog(struct __sk_buff *ctx) +{ + return bpf_ktime_get_ns(); +} + +__noinline int throwing_global_subprog(struct __sk_buff *ctx) +{ + if (ctx->tstamp) + bpf_throw(0); + return bpf_ktime_get_ns(); +} + +SEC("tc") +int exception_throw_subprog(struct __sk_buff *ctx) +{ + switch (ctx->protocol) { + case 1: + return subprog(ctx); + case 2: + return global_subprog(ctx); + case 3: + return throwing_subprog(ctx); + case 4: + return throwing_global_subprog(ctx); + default: + break; + } + bpf_throw(1); + return 0; +} + +__noinline int assert_nz_gfunc(u64 c) +{ + volatile u64 cookie = c; + + bpf_assert(cookie != 0); + return 0; +} + +__noinline int assert_zero_gfunc(u64 c) +{ + volatile u64 cookie = c; + + bpf_assert_eq(cookie, 0); + return 0; +} + +__noinline int assert_neg_gfunc(s64 c) +{ + volatile s64 cookie = c; + + bpf_assert_lt(cookie, 0); + return 0; +} + +__noinline int assert_pos_gfunc(s64 c) +{ + volatile s64 cookie = c; + + bpf_assert_gt(cookie, 0); + return 0; +} + +__noinline int assert_negeq_gfunc(s64 c) +{ + volatile s64 cookie = c; + + bpf_assert_le(cookie, -1); + return 0; +} + +__noinline int assert_poseq_gfunc(s64 c) +{ + volatile s64 cookie = c; + + bpf_assert_ge(cookie, 1); + return 0; +} + +__noinline int assert_nz_gfunc_with(u64 c) +{ + volatile u64 cookie = c; + + bpf_assert_with(cookie != 0, cookie + 100); + return 0; +} + +__noinline int assert_zero_gfunc_with(u64 c) +{ + volatile u64 cookie = c; + + bpf_assert_eq_with(cookie, 0, cookie + 100); + return 0; +} + +__noinline int assert_neg_gfunc_with(s64 c) +{ + volatile s64 cookie = c; + + bpf_assert_lt_with(cookie, 0, cookie + 100); + return 0; +} + +__noinline int assert_pos_gfunc_with(s64 c) +{ + volatile s64 cookie = c; + + bpf_assert_gt_with(cookie, 0, cookie + 100); + return 0; +} + +__noinline int assert_negeq_gfunc_with(s64 c) +{ + volatile s64 cookie = c; + + bpf_assert_le_with(cookie, -1, cookie + 100); + return 0; +} + +__noinline int assert_poseq_gfunc_with(s64 c) +{ + volatile s64 cookie = c; + + bpf_assert_ge_with(cookie, 1, cookie + 100); + return 0; +} + +#define check_assert(name, cookie, tag) \ +SEC("tc") \ +int exception##tag##name(struct __sk_buff *ctx) \ +{ \ + return name(cookie) + 1; \ +} + +check_assert(assert_nz_gfunc, 5, _); +check_assert(assert_zero_gfunc, 0, _); +check_assert(assert_neg_gfunc, -100, _); +check_assert(assert_pos_gfunc, 100, _); +check_assert(assert_negeq_gfunc, -1, _); +check_assert(assert_poseq_gfunc, 1, _); + +check_assert(assert_nz_gfunc_with, 5, _); +check_assert(assert_zero_gfunc_with, 0, _); +check_assert(assert_neg_gfunc_with, -100, _); +check_assert(assert_pos_gfunc_with, 100, _); +check_assert(assert_negeq_gfunc_with, -1, _); +check_assert(assert_poseq_gfunc_with, 1, _); + +check_assert(assert_nz_gfunc, 0, _bad_); +check_assert(assert_zero_gfunc, 5, _bad_); +check_assert(assert_neg_gfunc, 100, _bad_); +check_assert(assert_pos_gfunc, -100, _bad_); +check_assert(assert_negeq_gfunc, 1, _bad_); +check_assert(assert_poseq_gfunc, -1, _bad_); + +check_assert(assert_nz_gfunc_with, 0, _bad_); +check_assert(assert_zero_gfunc_with, 5, _bad_); +check_assert(assert_neg_gfunc_with, 100, _bad_); +check_assert(assert_pos_gfunc_with, -100, _bad_); +check_assert(assert_negeq_gfunc_with, 1, _bad_); +check_assert(assert_poseq_gfunc_with, -1, _bad_); + +SEC("tc") +int exception_assert_range(struct __sk_buff *ctx) +{ + u64 time = bpf_ktime_get_ns(); + + bpf_assert_range(time, 0, ~0ULL); + return 1; +} + +SEC("tc") +int exception_assert_range_with(struct __sk_buff *ctx) +{ + u64 time = bpf_ktime_get_ns(); + + bpf_assert_range_with(time, 0, ~0ULL, 10); + return 1; +} + +SEC("tc") +int exception_bad_assert_range(struct __sk_buff *ctx) +{ + u64 time = bpf_ktime_get_ns(); + + bpf_assert_range(time, -100, 100); + return 1; +} + +SEC("tc") +int exception_bad_assert_range_with(struct __sk_buff *ctx) +{ + u64 time = bpf_ktime_get_ns(); + + bpf_assert_range_with(time, -1000, 1000, 10); + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c new file mode 100644 index 000000000000..fa35832e6748 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include "bpf_misc.h" +#include "bpf_experimental.h" + +#define check_assert(type, op, name, value) \ + SEC("?tc") \ + __log_level(2) __failure \ + int check_assert_##op##_##name(void *ctx) \ + { \ + type num = bpf_ktime_get_ns(); \ + bpf_assert_##op(num, value); \ + return *(u64 *)num; \ + } + +__msg(": R0_w=-2147483648 R10=fp0") +check_assert(s64, eq, int_min, INT_MIN); +__msg(": R0_w=2147483647 R10=fp0") +check_assert(s64, eq, int_max, INT_MAX); +__msg(": R0_w=0 R10=fp0") +check_assert(s64, eq, zero, 0); +__msg(": R0_w=-9223372036854775808 R1_w=-9223372036854775808 R10=fp0") +check_assert(s64, eq, llong_min, LLONG_MIN); +__msg(": R0_w=9223372036854775807 R1_w=9223372036854775807 R10=fp0") +check_assert(s64, eq, llong_max, LLONG_MAX); + +__msg(": R0_w=scalar(smax=2147483646) R10=fp0") +check_assert(s64, lt, pos, INT_MAX); +__msg(": R0_w=scalar(umin=9223372036854775808,var_off=(0x8000000000000000; 0x7fffffffffffffff))") +check_assert(s64, lt, zero, 0); +__msg(": R0_w=scalar(umin=9223372036854775808,umax=18446744071562067967,var_off=(0x8000000000000000; 0x7fffffffffffffff))") +check_assert(s64, lt, neg, INT_MIN); + +__msg(": R0_w=scalar(smax=2147483647) R10=fp0") +check_assert(s64, le, pos, INT_MAX); +__msg(": R0_w=scalar(smax=0) R10=fp0") +check_assert(s64, le, zero, 0); +__msg(": R0_w=scalar(umin=9223372036854775808,umax=18446744071562067968,var_off=(0x8000000000000000; 0x7fffffffffffffff))") +check_assert(s64, le, neg, INT_MIN); + +__msg(": R0_w=scalar(umin=2147483648,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))") +check_assert(s64, gt, pos, INT_MAX); +__msg(": R0_w=scalar(umin=1,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))") +check_assert(s64, gt, zero, 0); +__msg(": R0_w=scalar(smin=-2147483647) R10=fp0") +check_assert(s64, gt, neg, INT_MIN); + +__msg(": R0_w=scalar(umin=2147483647,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))") +check_assert(s64, ge, pos, INT_MAX); +__msg(": R0_w=scalar(umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff)) R10=fp0") +check_assert(s64, ge, zero, 0); +__msg(": R0_w=scalar(smin=-2147483648) R10=fp0") +check_assert(s64, ge, neg, INT_MIN); + +SEC("?tc") +__log_level(2) __failure +__msg(": R0=0 R1=ctx(off=0,imm=0) R2=scalar(smin=-2147483646,smax=2147483645) R10=fp0") +int check_assert_range_s64(struct __sk_buff *ctx) +{ + struct bpf_sock *sk = ctx->sk; + s64 num; + + _Static_assert(_Generic((sk->rx_queue_mapping), s32: 1, default: 0), "type match"); + if (!sk) + return 0; + num = sk->rx_queue_mapping; + bpf_assert_range(num, INT_MIN + 2, INT_MAX - 2); + return *((u8 *)ctx + num); +} + +SEC("?tc") +__log_level(2) __failure +__msg(": R1=ctx(off=0,imm=0) R2=scalar(umin=4096,umax=8192,var_off=(0x0; 0x3fff))") +int check_assert_range_u64(struct __sk_buff *ctx) +{ + u64 num = ctx->len; + + bpf_assert_range(num, 4096, 8192); + return *((u8 *)ctx + num); +} + +SEC("?tc") +__log_level(2) __failure +__msg(": R0=0 R1=ctx(off=0,imm=0) R2=4096 R10=fp0") +int check_assert_single_range_s64(struct __sk_buff *ctx) +{ + struct bpf_sock *sk = ctx->sk; + s64 num; + + _Static_assert(_Generic((sk->rx_queue_mapping), s32: 1, default: 0), "type match"); + if (!sk) + return 0; + num = sk->rx_queue_mapping; + + bpf_assert_range(num, 4096, 4096); + return *((u8 *)ctx + num); +} + +SEC("?tc") +__log_level(2) __failure +__msg(": R1=ctx(off=0,imm=0) R2=4096 R10=fp0") +int check_assert_single_range_u64(struct __sk_buff *ctx) +{ + u64 num = ctx->len; + + bpf_assert_range(num, 4096, 4096); + return *((u8 *)ctx + num); +} + +SEC("?tc") +__log_level(2) __failure +__msg(": R1=pkt(off=64,r=64,imm=0) R2=pkt_end(off=0,imm=0) R6=pkt(off=0,r=64,imm=0) R10=fp0") +int check_assert_generic(struct __sk_buff *ctx) +{ + u8 *data_end = (void *)(long)ctx->data_end; + u8 *data = (void *)(long)ctx->data; + + bpf_assert(data + 64 <= data_end); + return data[128]; +} + +SEC("?fentry/bpf_check") +__failure __msg("At program exit the register R0 has value (0x40; 0x0)") +int check_assert_with_return(void *ctx) +{ + bpf_assert_with(!ctx, 64); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/exceptions_ext.c b/tools/testing/selftests/bpf/progs/exceptions_ext.c new file mode 100644 index 000000000000..743c05185d9b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/exceptions_ext.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include "bpf_experimental.h" + +SEC("?fentry") +int pfentry(void *ctx) +{ + return 0; +} + +SEC("?fentry") +int throwing_fentry(void *ctx) +{ + bpf_throw(0); + return 0; +} + +__noinline int exception_cb(u64 cookie) +{ + return cookie + 64; +} + +SEC("?freplace") +int extension(struct __sk_buff *ctx) +{ + return 0; +} + +SEC("?freplace") +__exception_cb(exception_cb) +int throwing_exception_cb_extension(u64 cookie) +{ + bpf_throw(32); + return 0; +} + +SEC("?freplace") +__exception_cb(exception_cb) +int throwing_extension(struct __sk_buff *ctx) +{ + bpf_throw(64); + return 0; +} + +SEC("?fexit") +int pfexit(void *ctx) +{ + return 0; +} + +SEC("?fexit") +int throwing_fexit(void *ctx) +{ + bpf_throw(0); + return 0; +} + +SEC("?fmod_ret") +int pfmod_ret(void *ctx) +{ + return 0; +} + +SEC("?fmod_ret") +int throwing_fmod_ret(void *ctx) +{ + bpf_throw(0); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/exceptions_fail.c b/tools/testing/selftests/bpf/progs/exceptions_fail.c new file mode 100644 index 000000000000..4c39e920dac2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/exceptions_fail.c @@ -0,0 +1,347 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include + +#include "bpf_misc.h" +#include "bpf_experimental.h" + +extern void bpf_rcu_read_lock(void) __ksym; + +#define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8))) + +struct foo { + struct bpf_rb_node node; +}; + +struct hmap_elem { + struct bpf_timer timer; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 64); + __type(key, int); + __type(value, struct hmap_elem); +} hmap SEC(".maps"); + +private(A) struct bpf_spin_lock lock; +private(A) struct bpf_rb_root rbtree __contains(foo, node); + +__noinline void *exception_cb_bad_ret_type(u64 cookie) +{ + return NULL; +} + +__noinline int exception_cb_bad_arg_0(void) +{ + return 0; +} + +__noinline int exception_cb_bad_arg_2(int a, int b) +{ + return 0; +} + +__noinline int exception_cb_ok_arg_small(int a) +{ + return 0; +} + +SEC("?tc") +__exception_cb(exception_cb_bad_ret_type) +__failure __msg("Global function exception_cb_bad_ret_type() doesn't return scalar.") +int reject_exception_cb_type_1(struct __sk_buff *ctx) +{ + bpf_throw(0); + return 0; +} + +SEC("?tc") +__exception_cb(exception_cb_bad_arg_0) +__failure __msg("exception cb only supports single integer argument") +int reject_exception_cb_type_2(struct __sk_buff *ctx) +{ + bpf_throw(0); + return 0; +} + +SEC("?tc") +__exception_cb(exception_cb_bad_arg_2) +__failure __msg("exception cb only supports single integer argument") +int reject_exception_cb_type_3(struct __sk_buff *ctx) +{ + bpf_throw(0); + return 0; +} + +SEC("?tc") +__exception_cb(exception_cb_ok_arg_small) +__success +int reject_exception_cb_type_4(struct __sk_buff *ctx) +{ + bpf_throw(0); + return 0; +} + +__noinline +static int timer_cb(void *map, int *key, struct bpf_timer *timer) +{ + bpf_throw(0); + return 0; +} + +SEC("?tc") +__failure __msg("cannot be called from callback subprog") +int reject_async_callback_throw(struct __sk_buff *ctx) +{ + struct hmap_elem *elem; + + elem = bpf_map_lookup_elem(&hmap, &(int){0}); + if (!elem) + return 0; + return bpf_timer_set_callback(&elem->timer, timer_cb); +} + +__noinline static int subprog_lock(struct __sk_buff *ctx) +{ + volatile int ret = 0; + + bpf_spin_lock(&lock); + if (ctx->len) + bpf_throw(0); + return ret; +} + +SEC("?tc") +__failure __msg("function calls are not allowed while holding a lock") +int reject_with_lock(void *ctx) +{ + bpf_spin_lock(&lock); + bpf_throw(0); + return 0; +} + +SEC("?tc") +__failure __msg("function calls are not allowed while holding a lock") +int reject_subprog_with_lock(void *ctx) +{ + return subprog_lock(ctx); +} + +SEC("?tc") +__failure __msg("bpf_rcu_read_unlock is missing") +int reject_with_rcu_read_lock(void *ctx) +{ + bpf_rcu_read_lock(); + bpf_throw(0); + return 0; +} + +__noinline static int throwing_subprog(struct __sk_buff *ctx) +{ + if (ctx->len) + bpf_throw(0); + return 0; +} + +SEC("?tc") +__failure __msg("bpf_rcu_read_unlock is missing") +int reject_subprog_with_rcu_read_lock(void *ctx) +{ + bpf_rcu_read_lock(); + return throwing_subprog(ctx); +} + +static bool rbless(struct bpf_rb_node *n1, const struct bpf_rb_node *n2) +{ + bpf_throw(0); + return true; +} + +SEC("?tc") +__failure __msg("function calls are not allowed while holding a lock") +int reject_with_rbtree_add_throw(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_spin_lock(&lock); + bpf_rbtree_add(&rbtree, &f->node, rbless); + return 0; +} + +SEC("?tc") +__failure __msg("Unreleased reference") +int reject_with_reference(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_throw(0); + return 0; +} + +__noinline static int subprog_ref(struct __sk_buff *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_throw(0); + return 0; +} + +__noinline static int subprog_cb_ref(u32 i, void *ctx) +{ + bpf_throw(0); + return 0; +} + +SEC("?tc") +__failure __msg("Unreleased reference") +int reject_with_cb_reference(void *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + bpf_loop(5, subprog_cb_ref, NULL, 0); + return 0; +} + +SEC("?tc") +__failure __msg("cannot be called from callback") +int reject_with_cb(void *ctx) +{ + bpf_loop(5, subprog_cb_ref, NULL, 0); + return 0; +} + +SEC("?tc") +__failure __msg("Unreleased reference") +int reject_with_subprog_reference(void *ctx) +{ + return subprog_ref(ctx) + 1; +} + +__noinline int throwing_exception_cb(u64 c) +{ + bpf_throw(0); + return c; +} + +__noinline int exception_cb1(u64 c) +{ + return c; +} + +__noinline int exception_cb2(u64 c) +{ + return c; +} + +static __noinline int static_func(struct __sk_buff *ctx) +{ + return exception_cb1(ctx->tstamp); +} + +__noinline int global_func(struct __sk_buff *ctx) +{ + return exception_cb1(ctx->tstamp); +} + +SEC("?tc") +__exception_cb(throwing_exception_cb) +__failure __msg("cannot be called from callback subprog") +int reject_throwing_exception_cb(struct __sk_buff *ctx) +{ + return 0; +} + +SEC("?tc") +__exception_cb(exception_cb1) +__failure __msg("cannot call exception cb directly") +int reject_exception_cb_call_global_func(struct __sk_buff *ctx) +{ + return global_func(ctx); +} + +SEC("?tc") +__exception_cb(exception_cb1) +__failure __msg("cannot call exception cb directly") +int reject_exception_cb_call_static_func(struct __sk_buff *ctx) +{ + return static_func(ctx); +} + +SEC("?tc") +__exception_cb(exception_cb1) +__exception_cb(exception_cb2) +__failure __msg("multiple exception callback tags for main subprog") +int reject_multiple_exception_cb(struct __sk_buff *ctx) +{ + bpf_throw(0); + return 16; +} + +__noinline int exception_cb_bad_ret(u64 c) +{ + return c; +} + +SEC("?fentry/bpf_check") +__exception_cb(exception_cb_bad_ret) +__failure __msg("At program exit the register R0 has unknown scalar value should") +int reject_set_exception_cb_bad_ret1(void *ctx) +{ + return 0; +} + +SEC("?fentry/bpf_check") +__failure __msg("At program exit the register R0 has value (0x40; 0x0) should") +int reject_set_exception_cb_bad_ret2(void *ctx) +{ + bpf_throw(64); + return 0; +} + +__noinline static int loop_cb1(u32 index, int *ctx) +{ + bpf_throw(0); + return 0; +} + +__noinline static int loop_cb2(u32 index, int *ctx) +{ + bpf_throw(0); + return 0; +} + +SEC("?tc") +__failure __msg("cannot be called from callback") +int reject_exception_throw_cb(struct __sk_buff *ctx) +{ + bpf_loop(5, loop_cb1, NULL, 0); + return 0; +} + +SEC("?tc") +__failure __msg("cannot be called from callback") +int reject_exception_throw_cb_diff(struct __sk_buff *ctx) +{ + if (ctx->protocol) + bpf_loop(5, loop_cb1, NULL, 0); + else + bpf_loop(5, loop_cb2, NULL, 0); + return 0; +} + +char _license[] SEC("license") = "GPL";