From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from 66-220-155-179.mail-mxout.facebook.com (66-220-155-179.mail-mxout.facebook.com [66.220.155.179]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 5068A3E3DAB for ; Fri, 18 Sep 2026 04:42:22 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=66.220.155.179 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1789706546; cv=none; b=SU2EjXPClvxxO/u/Yciks5IoOS5RupEIXDoHSrimoavQGh5Y3al93vvSEKJgTkXzsaOVSGRuPmF1W1M7++igly368tQ5nyuTviYsOAFKamyEF31cZFkBnywwknJNbnOWRMFbyG9ZaHWx8+/KELAeFbsk5BfNsqpXn9F5QTNNJNg= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1789706546; c=relaxed/simple; bh=lSgb5A/kXTfd9r0IzLJOMrsQNX7YJePUBHhW2efB4zQ=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=OlA4+RDVWppbQxfnAi9khv8+cg6p36oYxxfWsNVx6CKjzrjbQY7WhfO318InlECwhFun0dWxllYOh7B/h0XUFS5DzSfAzVxRtP8HBxzjywV0gZIXy13aJerT0+mcMMivWveKYmMlt1LSFHRbj/63+rNcXEGqlUBPUxCKfmc2mxw= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=fail (p=none dis=none) header.from=linux.dev; spf=fail smtp.mailfrom=linux.dev; arc=none smtp.client-ip=66.220.155.179 Authentication-Results: smtp.subspace.kernel.org; dmarc=fail (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=fail smtp.mailfrom=linux.dev Received: by devvm16039.vll0.facebook.com (Postfix, from userid 128203) id 58CE32B7C4C00C; Thu, 17 Sep 2026 21:42:11 -0700 (PDT) From: Yonghong Song To: bpf@vger.kernel.org Cc: Alexei Starovoitov , Andrii Nakryiko , Daniel Borkmann , Eduard Zingerman , kernel-team@fb.com Subject: [PATCH bpf-next v2 03/20] bpf: Add lookups for exception cleanup resumes and landing pads Date: Thu, 17 Sep 2026 21:42:11 -0700 Message-ID: <20260918044211.3286855-1-yonghong.song@linux.dev> X-Mailer: git-send-email 2.53.0 In-Reply-To: <20260918044156.3283973-1-yonghong.song@linux.dev> References: <20260918044156.3283973-1-yonghong.song@linux.dev> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Add two new files, exception.h and exception.c, to host the exception handling code. Only a few helpers so far: recognising a call to bpf_unwind_resume(), and asking which landing pad, if any, a call site unwinds to. The pad of a call site is kept in insn_aux_data, so the two places that move instructions around -- bpf_patch_insn_data() and verifier_remove_insns() -- learn to keep it in step. Nothing sets the mar= k yet; the next patch does. Signed-off-by: Yonghong Song --- include/linux/bpf_verifier.h | 6 ++++++ kernel/bpf/Makefile | 2 +- kernel/bpf/exception.c | 36 ++++++++++++++++++++++++++++++++++++ kernel/bpf/exception.h | 12 ++++++++++++ kernel/bpf/fixups.c | 17 +++++++++++++++++ 5 files changed, 72 insertions(+), 1 deletion(-) create mode 100644 kernel/bpf/exception.c create mode 100644 kernel/bpf/exception.h diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c08505b9ba82..f9bccd3e0f4d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -681,6 +681,11 @@ struct bpf_insn_aux_data { bool needs_zext; /* alu op needs to clear upper bits */ bool non_sleepable; /* helper/kfunc may be called from non-sleepable co= ntext */ bool is_iter_next; /* bpf_iter__next() kfunc call */ + /* + * 1 + the instruction index of the exception cleanup landing pad this + * call site unwinds to, or 0 for none. + */ + u32 cleanup_pad; bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog perc= pu alloc */ u8 alu_state; /* used in combination with alu_limit */ /* true if STX or LDX instruction is a part of a spill/fill @@ -1518,6 +1523,7 @@ u32 btf_func_arg_align(const struct btf *btf, const= struct btf_type *t); =20 int bpf_find_subprog(struct bpf_verifier_env *env, int off); bool bpf_is_throw_kfunc(struct bpf_insn *insn); +bool bpf_is_unwind_resume_kfunc(const struct bpf_insn *insn); int bpf_compute_const_regs(struct bpf_verifier_env *env); int bpf_prune_dead_branches(struct bpf_verifier_env *env); int bpf_check_cfg(struct bpf_verifier_env *env); diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 9a92c348bbda..af9bc60428ad 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -11,7 +11,7 @@ obj-$(CONFIG_BPF_SYSCALL) +=3D bpf_iter.o map_iter.o ta= sk_iter.o prog_iter.o link_ obj-$(CONFIG_BPF_SYSCALL) +=3D hashtab.o arraymap.o percpu_freelist.o bp= f_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o obj-$(CONFIG_BPF_SYSCALL) +=3D local_storage.o queue_stack_maps.o ringbu= f.o bpf_insn_array.o obj-$(CONFIG_BPF_SYSCALL) +=3D bpf_local_storage.o bpf_task_storage.o -obj-$(CONFIG_BPF_SYSCALL) +=3D fixups.o cfg.o states.o backtrack.o check= _btf.o +obj-$(CONFIG_BPF_SYSCALL) +=3D fixups.o cfg.o states.o backtrack.o check= _btf.o exception.o obj-${CONFIG_BPF_LSM} +=3D bpf_inode_storage.o obj-$(CONFIG_BPF_SYSCALL) +=3D disasm.o mprog.o obj-$(CONFIG_BPF_JIT) +=3D trampoline.o diff --git a/kernel/bpf/exception.c b/kernel/bpf/exception.c new file mode 100644 index 000000000000..3895b9453639 --- /dev/null +++ b/kernel/bpf/exception.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ +#include +#include +#include +#include +#include +#include +#include "exception.h" + +#define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##ar= gs) + +enum exc_kfunc { + EXC_KF_bpf_unwind_resume, +}; + +BTF_ID_LIST(exc_kfunc_list) +BTF_ID(func, bpf_unwind_resume) + +static bool insn_is_exc_kfunc(const struct bpf_insn *insn, int kf) +{ + return bpf_pseudo_kfunc_call(insn) && insn->off =3D=3D 0 && + insn->imm =3D=3D exc_kfunc_list[kf]; +} + +bool bpf_is_unwind_resume_kfunc(const struct bpf_insn *insn) +{ + return insn_is_exc_kfunc(insn, EXC_KF_bpf_unwind_resume); +} + +int bpf_cleanup_pad_of_call(struct bpf_verifier_env *env, u32 idx) +{ + u32 pad =3D env->insn_aux_data[idx].cleanup_pad; + + return pad ? (int)pad - 1 : -1; +} diff --git a/kernel/bpf/exception.h b/kernel/bpf/exception.h new file mode 100644 index 000000000000..0f2b9624a2ce --- /dev/null +++ b/kernel/bpf/exception.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ +#ifndef _LINUX_BPF_EXCEPTION_H +#define _LINUX_BPF_EXCEPTION_H + +#include + +struct bpf_verifier_env; + +int bpf_cleanup_pad_of_call(struct bpf_verifier_env *env, u32 idx); + +#endif /* _LINUX_BPF_EXCEPTION_H */ diff --git a/kernel/bpf/fixups.c b/kernel/bpf/fixups.c index 2add8001c3ec..82b00fac6bd6 100644 --- a/kernel/bpf/fixups.c +++ b/kernel/bpf/fixups.c @@ -261,6 +261,11 @@ static void adjust_insn_aux_data(struct bpf_verifier= _env *env, } } =20 + if (env->cleanup_info_cnt) + for (i =3D 0; i < prog_len; i++) + if (data[i].cleanup_pad > off + 1) + data[i].cleanup_pad +=3D cnt - 1; + /* * Last slot instruction could be a newly generated * BPF_ST/BPF_LDX/BPF_STX, systematically mark it for non-stack access @@ -549,6 +554,7 @@ static int verifier_remove_insns(struct bpf_verifier_= env *env, u32 off, u32 cnt) struct bpf_insn_aux_data *aux_data =3D env->insn_aux_data; unsigned int orig_prog_len =3D env->prog->len; int err; + u32 i; =20 if (bpf_prog_is_offloaded(env->prog->aux)) bpf_prog_offload_remove_insns(env, off, cnt); @@ -573,6 +579,17 @@ static int verifier_remove_insns(struct bpf_verifier= _env *env, u32 off, u32 cnt) sizeof(*aux_data) * (orig_prog_len - off - cnt)); env->insn_aux_data_len -=3D cnt; =20 + if (env->cleanup_info_cnt) { + for (i =3D 0; i < env->insn_aux_data_len; i++) { + u32 pad =3D aux_data[i].cleanup_pad; + + if (pad > off + cnt) + aux_data[i].cleanup_pad =3D pad - cnt; + else if (pad > off) + aux_data[i].cleanup_pad =3D 0; + } + } + return 0; } =20 --=20 2.53.0-Meta