From: Andrii Nakryiko <andrii@kernel.org> mainline inclusion from mainline-v6.8-rc1 commit 2afae08c9dcb8ac648414277cec70c2fe6a34d9e category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/IDC9YK Reference: https://web.git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commi... -------------------------------- Slightly change BPF verifier logic around eagerness and order of global subprog validation. Instead of going over every global subprog eagerly and validating it before main (entry) BPF program is verified, turn it around. Validate main program first, mark subprogs that were called from main program for later verification, but otherwise assume it is valid. Afterwards, go over marked global subprogs and validate those, potentially marking some more global functions as being called. Continue this process until all (transitively) callable global subprogs are validated. It's a BFS traversal at its heart and will always converge. This is an important change because it allows to feature-gate some subprograms that might not be verifiable on some older kernel, depending on supported set of features. E.g., at some point, global functions were allowed to accept a pointer to memory, which size is identified by user-provided type. Unfortunately, older kernels don't support this feature. With BPF CO-RE approach, the natural way would be to still compile BPF object file once and guard calls to this global subprog with some CO-RE check or using .rodata variables. That's what people do to guard usage of new helpers or kfuncs, and any other new BPF-side feature that might be missing on old kernels. That's currently impossible to do with global subprogs, unfortunately, because they are eagerly and unconditionally validated. This patch set aims to change this, so that in the future when global funcs gain new features, those can be guarded using BPF CO-RE techniques in the same fashion as any other new kernel feature. Two selftests had to be adjusted in sync with these changes. test_global_func12 relied on eager global subprog validation failing before main program failure is detected (unknown return value). Fix by making sure that main program is always valid. verifier_subprog_precision's parent_stack_slot_precise subtest relied on verifier checkpointing heuristic to do a checkpoint at instruction #5, but that's no longer true because we don't have enough jumps validated before reaching insn #5 due to global subprogs being validated later. Other than that, no changes, as one would expect. Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Eduard Zingerman <eddyz87@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20231124035937.403208-3-andrii@kernel.org Conflicts: kernel/bpf/verifier.c [Only pick the part modified by this mainline commit, and ignore the conflict part caused by higher version.] Signed-off-by: Zicheng Qu <quzicheng@huawei.com> --- include/linux/bpf.h | 2 + kernel/bpf/verifier.c | 44 ++++++++++++++++--- .../selftests/bpf/progs/test_global_func12.c | 4 +- .../bpf/progs/verifier_subprog_precision.c | 4 +- 4 files changed, 44 insertions(+), 10 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 92020ca0cc14..31d938e654f6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1434,6 +1434,8 @@ static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog) struct bpf_func_info_aux { u16 linkage; bool unreliable; + bool called : 1; + bool verified : 1; }; enum bpf_jit_poke_reason { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a5b36f5cb36d..f0a5c22a1eb5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -518,6 +518,11 @@ static const char *subprog_name(const struct bpf_verifier_env *env, int subprog) return btf_type_name(env->prog->aux->btf, info->type_id); } +static struct bpf_func_info_aux *subprog_aux(const struct bpf_verifier_env *env, int subprog) +{ + return &env->prog->aux->func_info_aux[subprog]; +} + static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK); @@ -9506,6 +9511,8 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, subprog, sub_name); if (env->subprog_info[subprog].changes_pkt_data) clear_all_pkt_pointers(env); + /* mark global subprog for verifying after main prog */ + subprog_aux(env, subprog)->called = true; clear_caller_saved_regs(env, caller->regs); /* All global functions return a 64-bit SCALAR_VALUE */ @@ -20039,8 +20046,11 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) return ret; } -/* Verify all global functions in a BPF program one by one based on their BTF. - * All global functions must pass verification. Otherwise the whole program is rejected. +/* Lazily verify all global functions based on their BTF, if they are called + * from main BPF program or any of subprograms transitively. + * BPF global subprogs called from dead code are not validated. + * All callable global functions must pass verification. + * Otherwise the whole program is rejected. * Consider: * int bar(int); * int foo(int f) @@ -20059,14 +20069,22 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) static int do_check_subprogs(struct bpf_verifier_env *env) { struct bpf_prog_aux *aux = env->prog->aux; - int i, ret; + struct bpf_func_info_aux *sub_aux; + int i, ret, new_cnt; if (!aux->func_info) return 0; +again: + new_cnt = 0; for (i = 1; i < env->subprog_cnt; i++) { - if (aux->func_info_aux[i].linkage != BTF_FUNC_GLOBAL) + if (!subprog_is_global(env, i)) continue; + + sub_aux = subprog_aux(env, i); + if (!sub_aux->called || sub_aux->verified) + continue; + env->insn_idx = env->subprog_info[i].start; WARN_ON_ONCE(env->insn_idx == 0); ret = do_check_common(env, i); @@ -20076,7 +20094,21 @@ static int do_check_subprogs(struct bpf_verifier_env *env) verbose(env, "Func#%d ('%s') is safe for any args that match its prototype\n", i, subprog_name(env, i)); } + + /* We verified new global subprog, it might have called some + * more global subprogs that we haven't verified yet, so we + * need to do another pass over subprogs to verify those. + */ + sub_aux->verified = true; + new_cnt++; } + + /* We can't loop forever as we verify at least one global subprog on + * each pass. + */ + if (new_cnt) + goto again; + return 0; } @@ -20798,8 +20830,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (ret) goto skip_full_check; - ret = do_check_subprogs(env); - ret = ret ?: do_check_main(env); + ret = do_check_main(env); + ret = ret ?: do_check_subprogs(env); if (ret == 0 && bpf_prog_is_offloaded(env->prog->aux)) ret = bpf_prog_offload_finalize(env); diff --git a/tools/testing/selftests/bpf/progs/test_global_func12.c b/tools/testing/selftests/bpf/progs/test_global_func12.c index 7f159d83c6f6..6e03d42519a6 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func12.c +++ b/tools/testing/selftests/bpf/progs/test_global_func12.c @@ -19,5 +19,7 @@ int global_func12(struct __sk_buff *skb) { const struct S s = {.x = skb->len }; - return foo(&s); + foo(&s); + + return 1; } diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c index 4b8b0f45d17d..83d187de7f6b 100644 --- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -370,12 +370,10 @@ __naked int parent_stack_slot_precise(void) SEC("?raw_tp") __success __log_level(2) __msg("9: (0f) r1 += r6") -__msg("mark_precise: frame0: last_idx 9 first_idx 6") +__msg("mark_precise: frame0: last_idx 9 first_idx 0") __msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7") __msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4") __msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)") -__msg("mark_precise: frame0: parent state regs= stack=-8:") -__msg("mark_precise: frame0: last_idx 5 first_idx 0") __msg("mark_precise: frame0: regs= stack=-8 before 5: (85) call pc+6") __msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0") __msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6") -- 2.34.1