[PATCH bpf-next v8 04/22] bpf: Add lookups for exception cleanup resumes and landing pads

[Yonghong Song <yonghong.song@linux.dev>]

Add the first lookups to exception.c: recognising a call to bpf_unwind() or
bpf_unwind_resume(), and asking which landing pad, if any, a call site
unwinds to. Their users, and what fills in the pad of a call site, come in
later patches.

The pad of a call site is kept in insn_aux_data, so the three places that
move instructions around -- bpf_patch_insn_data(), verifier_remove_insns()
and bpf_opt_remove_nops() -- learn to keep it in step.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
 include/linux/bpf_verifier.h |  5 +++++
 kernel/bpf/exception.c       | 24 ++++++++++++++++++++++++
 kernel/bpf/exception.h       |  4 ++++
 kernel/bpf/fixups.c          | 26 +++++++++++++++++++++++++-
 4 files changed, 58 insertions(+), 1 deletion(-)

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index ad0ca8047712..a22ce69e9aff 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -700,6 +700,11 @@ struct bpf_insn_aux_data {
 	u64 jump_target:1;
 
 	unsigned int orig_idx; /* original instruction index, initialized once */
+	/*
+	 * 1 + the instruction index of the exception cleanup landing pad
+	 * this call site unwinds to, or 0 for none.
+	 */
+	u32 cleanup_pad;
 	/*
 	 * CFG strongly connected component this instruction belongs to,
 	 * zero if it is a singleton SCC.
diff --git a/kernel/bpf/exception.c b/kernel/bpf/exception.c
index d6b8ca98e71c..3ea1bff5cc90 100644
--- a/kernel/bpf/exception.c
+++ b/kernel/bpf/exception.c
@@ -2,6 +2,8 @@
 /* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
 #include <linux/bpf.h>
 #include <linux/bpf_verifier.h>
+#include <linux/btf_ids.h>
+#include <linux/filter.h>
 #include <linux/slab.h>
 #include "exception.h"
 
@@ -135,3 +137,25 @@ int bpf_exc_check_info(struct bpf_verifier_env *env, const union bpf_attr *attr,
 	kvfree(krecord);
 	return ret;
 }
+
+BTF_ID_LIST_SINGLE(bpf_unwind_id, func, bpf_unwind)
+BTF_ID_LIST_SINGLE(bpf_unwind_resume_id, func, bpf_unwind_resume)
+
+bool bpf_is_unwind_kfunc(const struct bpf_insn *insn)
+{
+	return bpf_pseudo_kfunc_call(insn) && insn->off == 0 &&
+	       insn->imm == bpf_unwind_id[0];
+}
+
+bool bpf_is_unwind_resume_kfunc(const struct bpf_insn *insn)
+{
+	return bpf_pseudo_kfunc_call(insn) && insn->off == 0 &&
+	       insn->imm == bpf_unwind_resume_id[0];
+}
+
+int bpf_exc_pad_of_call(struct bpf_verifier_env *env, u32 idx)
+{
+	u32 pad = 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
index cf099dcc5b74..d5c6ac459870 100644
--- a/kernel/bpf/exception.h
+++ b/kernel/bpf/exception.h
@@ -8,8 +8,12 @@
 
 union bpf_attr;
 struct bpf_verifier_env;
+struct bpf_insn;
 
 int bpf_exc_check_info(struct bpf_verifier_env *env, const union bpf_attr *attr,
 		       bpfptr_t uattr);
+int bpf_exc_pad_of_call(struct bpf_verifier_env *env, u32 idx);
+bool bpf_is_unwind_kfunc(const struct bpf_insn *insn);
+bool bpf_is_unwind_resume_kfunc(const struct bpf_insn *insn);
 
 #endif /* __BPF_EXCEPTION_H */
diff --git a/kernel/bpf/fixups.c b/kernel/bpf/fixups.c
index 37cf130ebb57..5b7fe4ba610b 100644
--- a/kernel/bpf/fixups.c
+++ b/kernel/bpf/fixups.c
@@ -268,11 +268,18 @@ static void adjust_insn_aux_data(struct bpf_verifier_env *env,
 			data[i].non_stack_access =
 				data[off + cnt - 1].non_stack_access;
 			data[off + cnt - 1].non_stack_access = false;
+			data[i].cleanup_pad = data[off + cnt - 1].cleanup_pad;
+			data[off + cnt - 1].cleanup_pad = 0;
 		} else if (bpf_is_mem_insn(insn + i)) {
 			data[i].non_stack_access = true;
 		}
 	}
 
+	if (env->cleanup_info_cnt)
+		for (i = 0; i < prog_len; i++)
+			if (data[i].cleanup_pad > off + 1)
+				data[i].cleanup_pad += cnt - 1;
+
 	/*
 	 * Last slot instruction could be a newly generated
 	 * BPF_ST/BPF_LDX/BPF_STX, systematically mark it for non-stack access
@@ -619,6 +626,7 @@ static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt)
 	struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
 	unsigned int orig_prog_len = env->prog->len;
 	int err;
+	u32 i;
 
 	if (bpf_rewrite_must_abort())
 		return -EINTR;
@@ -647,6 +655,17 @@ 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 -= cnt;
 
+	if (env->cleanup_info_cnt) {
+		for (i = 0; i < env->insn_aux_data_len; i++) {
+			u32 pad = aux_data[i].cleanup_pad;
+
+			if (pad > off + cnt)
+				aux_data[i].cleanup_pad = pad - cnt;
+			else if (pad > off)
+				aux_data[i].cleanup_pad = 0;
+		}
+	}
+
 	return 0;
 }
 
@@ -752,7 +771,7 @@ int bpf_opt_remove_nops(struct bpf_verifier_env *env)
 	struct bpf_insn *insn = env->prog->insnsi;
 	int insn_cnt = env->prog->len;
 	bool is_may_goto_0, is_ja;
-	int i, err;
+	int i, j, err;
 
 	for (i = 0; i < insn_cnt; i++) {
 		is_may_goto_0 = !memcmp(&insn[i], &MAY_GOTO_0, sizeof(MAY_GOTO_0));
@@ -763,6 +782,11 @@ int bpf_opt_remove_nops(struct bpf_verifier_env *env)
 		if (aux[i].indirect_target)
 			continue;
 
+		if (env->cleanup_info_cnt)
+			for (j = 0; j < insn_cnt; j++)
+				if (env->insn_aux_data[j].cleanup_pad == i + 1)
+					env->insn_aux_data[j].cleanup_pad = i + 2;
+
 		err = verifier_remove_insns(env, i, 1);
 		if (err)
 			return err;
-- 
2.53.0-Meta