* [PATCH bpf-next 01/20] bpf: Accept the compiler's exception cleanup table at program load
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
@ 2026-09-17 5:56 ` Yonghong Song
2026-09-17 5:56 ` [PATCH bpf-next 02/20] bpf: Add the bpf_unwind_resume() kfunc Yonghong Song
` (18 subsequent siblings)
19 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:56 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
LLVM 23 added exception handling support for BPF with the .bpf_cleanup
section ([1]). Rust code compiled with panic=unwind runs cleanup code
(Drop glue) when bpf_throw() fires, and the LLVM BPF backend emits that
section from the landing pads the frontend produced. Plain C cannot
generate .bpf_cleanup unless inline asm is used. The Rust compiler does not
*properly* support BPF exception handling yet, but the kernel can support
the table today, and inline assembly is enough to test it.
Add the UAPI to carry the .bpf_cleanup table into the kernel. BPF_PROG_LOAD
grows cleanup_info, cleanup_info_cnt and cleanup_info_rec_size, and struct
bpf_cleanup_info describes one record as a triple of instruction indices:
the half-open call-site range [begin_off, end_off) and the landing_pad_off
the frame resumes at. check_cleanup_info() validates the table a program is
loaded with, so the rest of the kernel can rely on it.
[1] https://github.com/llvm/llvm-project/pull/192164
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
include/linux/bpf_verifier.h | 2 +
include/uapi/linux/bpf.h | 9 ++
kernel/bpf/check_btf.c | 147 +++++++++++++++++++++++++++++++++
kernel/bpf/syscall.c | 2 +-
kernel/bpf/verifier.c | 1 +
tools/include/uapi/linux/bpf.h | 9 ++
6 files changed, 169 insertions(+), 1 deletion(-)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index cf85141ea167..c08505b9ba82 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -987,6 +987,8 @@ struct bpf_verifier_env {
struct arg_track **callsite_at_stack;
u32 pass_cnt; /* number of times do_check() was called */
u32 subprog_cnt;
+ struct bpf_cleanup_info *cleanup_info;
+ u32 cleanup_info_cnt;
/* number of instructions analyzed by the verifier */
u32 prev_insn_processed, insn_processed;
/* number of jmps, calls, exits analyzed so far */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 732b35cc08d1..f7dc121be094 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1669,6 +1669,9 @@ union bpf_attr {
* verification.
*/
__s32 keyring_id;
+ __aligned_u64 cleanup_info; /* exception cleanup table */
+ __u32 cleanup_info_rec_size; /* userspace bpf_cleanup_info size */
+ __u32 cleanup_info_cnt; /* number of bpf_cleanup_info records */
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -7588,6 +7591,12 @@ struct bpf_line_info {
__u32 line_col;
};
+struct bpf_cleanup_info {
+ __u32 begin_off;
+ __u32 end_off;
+ __u32 landing_pad_off;
+};
+
struct bpf_spin_lock {
__u32 val;
};
diff --git a/kernel/bpf/check_btf.c b/kernel/bpf/check_btf.c
index 0e8b3ccc7a5b..d03dc791042a 100644
--- a/kernel/bpf/check_btf.c
+++ b/kernel/bpf/check_btf.c
@@ -407,6 +407,149 @@ static int check_core_relo(struct bpf_verifier_env *env,
return err;
}
+static int cleanup_insn_subprog(struct bpf_verifier_env *env, u32 off)
+{
+ struct bpf_subprog_info *info;
+
+ if (off >= env->prog->len)
+ return -1;
+ info = bpf_find_containing_subprog(env, off);
+ return info ? info - env->subprog_info : -1;
+}
+
+#define MIN_BPF_CLEANUP_INFO_SIZE 12
+#define MAX_CLEANUP_INFO_REC_SIZE MAX_FUNCINFO_REC_SIZE
+
+static int check_cleanup_info(struct bpf_verifier_env *env,
+ const union bpf_attr *attr,
+ bpfptr_t uattr)
+{
+ u32 krec_size = sizeof(struct bpf_cleanup_info);
+ u32 i, nrec, urec_size, min_size, prev_end = 0;
+ struct bpf_cleanup_info *krecord;
+ bpfptr_t urecord;
+ int ret = -EINVAL;
+
+ nrec = attr->cleanup_info_cnt;
+ if (!nrec)
+ return 0;
+ if (nrec > INT_MAX / krec_size)
+ return -EINVAL;
+
+ urec_size = attr->cleanup_info_rec_size;
+ if (urec_size < MIN_BPF_CLEANUP_INFO_SIZE ||
+ urec_size > MAX_CLEANUP_INFO_REC_SIZE ||
+ urec_size % sizeof(u32)) {
+ verbose(env, "invalid cleanup info rec size %u\n", urec_size);
+ return -EINVAL;
+ }
+
+ krecord = kvcalloc(nrec, krec_size, GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
+ if (!krecord)
+ return -ENOMEM;
+
+ min_size = min_t(u32, krec_size, urec_size);
+ urecord = make_bpfptr(attr->cleanup_info, uattr.is_kernel);
+ for (i = 0; i < nrec; i++) {
+ struct bpf_cleanup_info *rec = &krecord[i];
+ int sb, se, sl;
+
+ ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size);
+ if (ret) {
+ if (ret == -E2BIG) {
+ verbose(env, "nonzero tailing record in cleanup info\n");
+ if (copy_to_bpfptr_offset(uattr,
+ offsetof(union bpf_attr,
+ cleanup_info_rec_size),
+ &min_size, sizeof(min_size)))
+ ret = -EFAULT;
+ }
+ goto err_free;
+ }
+
+ if (copy_from_bpfptr(rec, urecord, min_size)) {
+ ret = -EFAULT;
+ goto err_free;
+ }
+ bpfptr_add(&urecord, urec_size);
+
+ ret = -EINVAL;
+ if (rec->begin_off >= rec->end_off) {
+ verbose(env, "cleanup_info[%u]: begin %u >= end %u\n",
+ i, rec->begin_off, rec->end_off);
+ goto err_free;
+ }
+ if (i && rec->begin_off < prev_end) {
+ verbose(env,
+ "cleanup_info[%u]: range [%u,%u) is unsorted or overlaps the previous record\n",
+ i, rec->begin_off, rec->end_off);
+ goto err_free;
+ }
+ prev_end = rec->end_off;
+
+ sb = cleanup_insn_subprog(env, rec->begin_off);
+ se = cleanup_insn_subprog(env, rec->end_off - 1);
+ sl = cleanup_insn_subprog(env, rec->landing_pad_off);
+ if (sb < 0 || se < 0 || sl < 0) {
+ verbose(env, "cleanup_info[%u]: offset out of range\n", i);
+ goto err_free;
+ }
+ if (sb != se || sb != sl) {
+ verbose(env,
+ "cleanup_info[%u]: range/landing pad span multiple subprogs\n",
+ i);
+ goto err_free;
+ }
+ /*
+ * The second half of a 16-byte instruction carries a zero
+ * opcode and is not an instruction of its own, so no offset
+ * may name one. end_off is exclusive, so it may also be one
+ * past the last instruction of the program.
+ */
+ if (!env->prog->insnsi[rec->begin_off].code ||
+ !env->prog->insnsi[rec->landing_pad_off].code ||
+ (rec->end_off < env->prog->len &&
+ !env->prog->insnsi[rec->end_off].code)) {
+ verbose(env, "cleanup_info[%u]: points at invalid insn\n", i);
+ goto err_free;
+ }
+ }
+
+ /*
+ * Reject a landing pad that lies inside a call-site range, its own
+ * included: it would be both a pad and a call that unwinds to one, and
+ * an exception out of it would have nowhere to go.
+ */
+ ret = -EINVAL;
+ for (i = 0; i < nrec; i++) {
+ u32 pad = krecord[i].landing_pad_off;
+ u32 l = 0, r = nrec;
+
+ while (l < r) {
+ u32 m = l + (r - l) / 2;
+
+ if (pad < krecord[m].begin_off) {
+ r = m;
+ } else if (pad >= krecord[m].end_off) {
+ l = m + 1;
+ } else {
+ verbose(env,
+ "cleanup_info[%u]: landing pad %u is inside the call-site range of cleanup_info[%u]\n",
+ i, pad, m);
+ goto err_free;
+ }
+ }
+ }
+
+ env->cleanup_info = krecord;
+ env->cleanup_info_cnt = nrec;
+ return 0;
+
+err_free:
+ kvfree(krecord);
+ return ret;
+}
+
int bpf_prepare_btf_info(struct bpf_verifier_env *env,
const union bpf_attr *attr,
bpfptr_t uattr)
@@ -441,6 +584,10 @@ int bpf_check_btf_info(struct bpf_verifier_env *env,
{
int err;
+ err = check_cleanup_info(env, attr, uattr);
+ if (err)
+ return err;
+
if (!attr->func_info_cnt && !attr->line_info_cnt) {
if (check_abnormal_return(env))
return -EINVAL;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index def57bddb092..ac7091469766 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2912,7 +2912,7 @@ int __init __used bpf_multi_func(void) { return 0; }
BTF_ID_LIST_GLOBAL_SINGLE(bpf_multi_func_btf_id, func, bpf_multi_func)
/* last field in 'union bpf_attr' used by this command */
-#define BPF_PROG_LOAD_LAST_FIELD keyring_id
+#define BPF_PROG_LOAD_LAST_FIELD cleanup_info_cnt
static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, struct bpf_log_attr *attr_log)
{
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6c6b8d8520cd..c65ff2e326bf 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -21845,6 +21845,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr,
kvfree(env->succ);
kvfree(env->gotox_tmp_buf);
bpf_diag_free(env);
+ kvfree(env->cleanup_info);
kvfree(env);
return ret;
}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 732b35cc08d1..f7dc121be094 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1669,6 +1669,9 @@ union bpf_attr {
* verification.
*/
__s32 keyring_id;
+ __aligned_u64 cleanup_info; /* exception cleanup table */
+ __u32 cleanup_info_rec_size; /* userspace bpf_cleanup_info size */
+ __u32 cleanup_info_cnt; /* number of bpf_cleanup_info records */
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -7588,6 +7591,12 @@ struct bpf_line_info {
__u32 line_col;
};
+struct bpf_cleanup_info {
+ __u32 begin_off;
+ __u32 end_off;
+ __u32 landing_pad_off;
+};
+
struct bpf_spin_lock {
__u32 val;
};
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH bpf-next 02/20] bpf: Add the bpf_unwind_resume() kfunc
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
2026-09-17 5:56 ` [PATCH bpf-next 01/20] bpf: Accept the compiler's exception cleanup table at program load Yonghong Song
@ 2026-09-17 5:56 ` Yonghong Song
2026-09-17 5:57 ` [PATCH bpf-next 03/20] bpf: Add lookups for exception cleanup resumes and landing pads Yonghong Song
` (17 subsequent siblings)
19 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:56 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
A compiler-emitted cleanup landing pad ends with a call to
_Unwind_Resume(), which carries the unwind on once that frame's cleanups
have run. The kernel provides the same terminator as a kfunc, named
bpf_unwind_resume() to keep the 'bpf_' prefix kfunc convention; a later
libbpf patch resolves the compiler's name to it.
The body never runs. A JIT emits the way back out of a landing pad in its
place.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
kernel/bpf/helpers.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 051b6654e57c..31d84de4d318 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -3407,6 +3407,17 @@ __bpf_kfunc void bpf_throw(u64 cookie)
WARN(1, "A call to BPF exception callback should never return\n");
}
+/*
+ * Terminator of a compiler-emitted cleanup landing pad. The compiler names
+ * this _Unwind_Resume, the base unwind ABI's entry point for carrying an
+ * unwind on once a frame's cleanups have run. To match kernel kfunc
+ * convention, the kernel calls it bpf_unwind_resume and libbpf maps the
+ * compiler's name onto it.
+ */
+__bpf_kfunc void bpf_unwind_resume(void)
+{
+}
+
__bpf_kfunc int bpf_wq_init(struct bpf_wq *wq, void *p__const_map, unsigned int flags)
{
struct bpf_async_kern *async = (struct bpf_async_kern *)wq;
@@ -4853,6 +4864,7 @@ BTF_ID_FLAGS(func, bpf_task_get_cgroup1, KF_ACQUIRE | KF_RCU | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_task_from_vpid, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_throw)
+BTF_ID_FLAGS(func, bpf_unwind_resume)
#ifdef CONFIG_BPF_EVENTS
BTF_ID_FLAGS(func, bpf_send_signal_task)
#endif
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH bpf-next 03/20] bpf: Add lookups for exception cleanup resumes and landing pads
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
2026-09-17 5:56 ` [PATCH bpf-next 01/20] bpf: Accept the compiler's exception cleanup table at program load Yonghong Song
2026-09-17 5:56 ` [PATCH bpf-next 02/20] bpf: Add the bpf_unwind_resume() kfunc Yonghong Song
@ 2026-09-17 5:57 ` Yonghong Song
2026-09-17 5:57 ` [PATCH bpf-next 04/20] bpf: Mark the call sites an exception cleanup table covers Yonghong Song
` (16 subsequent siblings)
19 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:57 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
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 mark
yet; the next patch does.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
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 context */
bool is_iter_next; /* bpf_iter_<type>_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 percpu 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);
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-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_
obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o
obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o bpf_insn_array.o
obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o
-obj-$(CONFIG_BPF_SYSCALL) += fixups.o cfg.o states.o backtrack.o check_btf.o
+obj-$(CONFIG_BPF_SYSCALL) += fixups.o cfg.o states.o backtrack.o check_btf.o exception.o
obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o
obj-$(CONFIG_BPF_SYSCALL) += disasm.o mprog.o
obj-$(CONFIG_BPF_JIT) += 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 <linux/bpf.h>
+#include <linux/bpf_verifier.h>
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
+#include <linux/filter.h>
+#include <linux/slab.h>
+#include "exception.h"
+
+#define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args)
+
+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 == 0 &&
+ insn->imm == 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 = 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 <linux/types.h>
+
+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,
}
}
+ 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
@@ -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 = env->insn_aux_data;
unsigned int orig_prog_len = env->prog->len;
int err;
+ u32 i;
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 -= 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;
}
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH bpf-next 04/20] bpf: Mark the call sites an exception cleanup table covers
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (2 preceding siblings ...)
2026-09-17 5:57 ` [PATCH bpf-next 03/20] bpf: Add lookups for exception cleanup resumes and landing pads Yonghong Song
@ 2026-09-17 5:57 ` Yonghong Song
2026-09-17 5:57 ` [PATCH bpf-next 05/20] bpf: Make exception landing pads reachable in the CFG Yonghong Song
` (15 subsequent siblings)
19 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:57 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
Some plumbing work is done before bpf_check_cfg(). More specifically,
insn_aux_data records cleanup_throw_site for every bpf_throw(), and
cleanup_pad, the landing pad a frame resumes at, for every call within the
[begin_off, end_off) range of a cleanup record. Subsequent commits consume
both.
bpf_prepare_cleanup_exceptions() runs before bpf_check_cfg(), because what
it produces is what the CFG walk consumes. It refuses a table on an
offloaded program, on a program whose JIT cannot dispatch landing pads or
which the JIT was not asked to compile, and on a program that also installs
an exception callback -- two different answers to what runs on the way out.
bpf_jit_supports_cleanup_pads() is weak here and says no; the arch patches
provide the real ones.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
include/linux/bpf_verifier.h | 1 +
include/linux/filter.h | 1 +
kernel/bpf/core.c | 5 ++++
kernel/bpf/exception.c | 55 ++++++++++++++++++++++++++++++++++++
kernel/bpf/exception.h | 1 +
kernel/bpf/verifier.c | 6 ++++
6 files changed, 69 insertions(+)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index f9bccd3e0f4d..7463e86d15ee 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -681,6 +681,7 @@ 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 context */
bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */
+ bool cleanup_throw_site; /* call to bpf_throw() */
/*
* 1 + the instruction index of the exception cleanup landing pad this
* call site unwinds to, or 0 for none.
diff --git a/include/linux/filter.h b/include/linux/filter.h
index b17222db2efc..9682b98ad890 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1242,6 +1242,7 @@ bool bpf_jit_supports_stack_args(void);
bool bpf_jit_supports_arena_args(void);
bool bpf_jit_supports_far_kfunc_call(void);
bool bpf_jit_supports_exceptions(void);
+bool bpf_jit_supports_cleanup_pads(void);
bool bpf_jit_supports_ptr_xchg(void);
bool bpf_jit_supports_arena(void);
bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 4e208cc94752..f0dd851264f4 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -3470,6 +3470,11 @@ void __weak arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp,
{
}
+bool __weak bpf_jit_supports_cleanup_pads(void)
+{
+ return false;
+}
+
bool __weak bpf_jit_supports_timed_may_goto(void)
{
return false;
diff --git a/kernel/bpf/exception.c b/kernel/bpf/exception.c
index 3895b9453639..dfe9c2a9ce7d 100644
--- a/kernel/bpf/exception.c
+++ b/kernel/bpf/exception.c
@@ -23,6 +23,61 @@ static bool insn_is_exc_kfunc(const struct bpf_insn *insn, int kf)
insn->imm == exc_kfunc_list[kf];
}
+static void cleanup_mark_throw_sites(struct bpf_verifier_env *env)
+{
+ u32 i;
+
+ for (i = 0; i < env->prog->len; i++)
+ if (bpf_is_throw_kfunc(&env->prog->insnsi[i]))
+ env->insn_aux_data[i].cleanup_throw_site = true;
+}
+
+static void cleanup_mark_call_sites(struct bpf_verifier_env *env)
+{
+ u32 i, j;
+
+ for (i = 0; i < env->cleanup_info_cnt; i++) {
+ struct bpf_cleanup_info *rec = &env->cleanup_info[i];
+
+ for (j = rec->begin_off; j < rec->end_off; j++) {
+ struct bpf_insn *insn = &env->prog->insnsi[j];
+
+ if (!bpf_pseudo_call(insn) && !bpf_is_throw_kfunc(insn))
+ continue;
+ env->insn_aux_data[j].cleanup_pad = rec->landing_pad_off + 1;
+ }
+ }
+}
+
+int bpf_prepare_cleanup_exceptions(struct bpf_verifier_env *env)
+{
+ if (!env->cleanup_info_cnt)
+ return 0;
+
+ if (bpf_prog_is_offloaded(env->prog->aux)) {
+ verbose(env,
+ "exception cleanup is not supported for offloaded programs\n");
+ return -EINVAL;
+ }
+
+ if (!bpf_jit_supports_cleanup_pads() || !env->prog->jit_requested) {
+ verbose(env,
+ "exception cleanup needs a JIT that can dispatch landing pads\n");
+ return -EOPNOTSUPP;
+ }
+ env->prog->jit_required = 1;
+
+ if (env->exception_callback_subprog) {
+ verbose(env,
+ "exception cleanup table cannot be combined with an exception callback\n");
+ return -EINVAL;
+ }
+
+ cleanup_mark_throw_sites(env);
+ cleanup_mark_call_sites(env);
+ return 0;
+}
+
bool bpf_is_unwind_resume_kfunc(const struct bpf_insn *insn)
{
return insn_is_exc_kfunc(insn, EXC_KF_bpf_unwind_resume);
diff --git a/kernel/bpf/exception.h b/kernel/bpf/exception.h
index 0f2b9624a2ce..f51383fd775c 100644
--- a/kernel/bpf/exception.h
+++ b/kernel/bpf/exception.h
@@ -7,6 +7,7 @@
struct bpf_verifier_env;
+int bpf_prepare_cleanup_exceptions(struct bpf_verifier_env *env);
int bpf_cleanup_pad_of_call(struct bpf_verifier_env *env, u32 idx);
#endif /* _LINUX_BPF_EXCEPTION_H */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c65ff2e326bf..6496c30a10f7 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -37,6 +37,7 @@
#include "diagnostics.h"
#include "disasm.h"
+#include "exception.h"
static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
@@ -21638,6 +21639,11 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr,
if (ret < 0)
goto skip_full_check;
+ /* The CFG needs an edge from a call in a cleanup range to its pad. */
+ ret = bpf_prepare_cleanup_exceptions(env);
+ if (ret < 0)
+ goto skip_full_check;
+
/* Validate instructions and resolve the program's referenced resources. */
ret = check_and_resolve_insns(env);
if (ret < 0)
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH bpf-next 05/20] bpf: Make exception landing pads reachable in the CFG
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (3 preceding siblings ...)
2026-09-17 5:57 ` [PATCH bpf-next 04/20] bpf: Mark the call sites an exception cleanup table covers Yonghong Song
@ 2026-09-17 5:57 ` Yonghong Song
2026-09-17 6:22 ` sashiko-bot
2026-09-17 5:57 ` [PATCH bpf-next 06/20] bpf: Explore the landing pads no call site reaches Yonghong Song
` (14 subsequent siblings)
19 siblings, 1 reply; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:57 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
Both the CFG walk and liveness are involved. A bpf_throw() or a bpf2bpf
call inside the [begin_off, end_off) range of a cleanup record can reach
that record's landing pad, so both grow that edge; and a
bpf_unwind_resume() reaches nothing after it, so it has no successors.
Liveness needs one more thing. bpf_stack_slot_alive() decides whether an
outer frame's stack slot is still read after the call the frame is
suspended at by looking at the instruction after the call. A slot whose
only remaining reader is the landing pad -- which is every slot a
compiler-generated pad reloads, since only four registers survive a call --
is dead by that measure, so clean_verifier_state() poisons it while the
callee runs and the pad is then rejected for reading it. Ask about the pad
as well when the call site names one.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
kernel/bpf/cfg.c | 47 ++++++++++++++++++++++++++++++++++++++++---
kernel/bpf/liveness.c | 20 ++++++++++++++++++
2 files changed, 64 insertions(+), 3 deletions(-)
diff --git a/kernel/bpf/cfg.c b/kernel/bpf/cfg.c
index 842c7d1eabcc..9f8b8b54d5ea 100644
--- a/kernel/bpf/cfg.c
+++ b/kernel/bpf/cfg.c
@@ -6,6 +6,7 @@
#include <linux/sort.h>
#include "diagnostics.h"
+#include "exception.h"
#define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args)
@@ -158,17 +159,57 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
return DONE_EXPLORING;
}
+static int visit_cleanup_pad_edge(int t, struct bpf_verifier_env *env)
+{
+ int *insn_stack = env->cfg.insn_stack;
+ int *insn_state = env->cfg.insn_state;
+ int w;
+
+ if (!env->cleanup_info_cnt)
+ return DONE_EXPLORING;
+ w = bpf_cleanup_pad_of_call(env, t);
+ if (w < 0)
+ return DONE_EXPLORING;
+
+ mark_prune_point(env, t);
+ mark_jmp_point(env, w);
+ mark_jump_target(env, w);
+
+ if (insn_state[w])
+ return DONE_EXPLORING;
+ if (env->cfg.cur_stack >= env->prog->len)
+ return -E2BIG;
+ insn_stack[env->cfg.cur_stack++] = w;
+ insn_state[w] |= DISCOVERED;
+ return KEEP_EXPLORING;
+}
+
+static int merge_visit_ret(int a, int b)
+{
+ if (a < 0)
+ return a;
+ if (b < 0)
+ return b;
+ if (a == KEEP_EXPLORING || b == KEEP_EXPLORING)
+ return KEEP_EXPLORING;
+ return DONE_EXPLORING;
+}
+
static int visit_func_call_insn(int t, struct bpf_insn *insns,
struct bpf_verifier_env *env,
bool visit_callee)
{
- int ret, insn_sz;
+ int ret, insn_sz, pad_ret;
int w;
+ pad_ret = visit_cleanup_pad_edge(t, env);
+ if (pad_ret < 0)
+ return pad_ret;
+
insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1;
ret = push_insn(t, t + insn_sz, FALLTHROUGH, env);
if (ret)
- return ret;
+ return merge_visit_ret(pad_ret, ret);
mark_prune_point(env, t + insn_sz);
/* when we exit from subprog, we need to record non-linear history */
@@ -180,7 +221,7 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
merge_callee_effects(env, t, w);
ret = push_insn(t, w, BRANCH, env);
}
- return ret;
+ return merge_visit_ret(pad_ret, ret);
}
struct bpf_iarray *bpf_iarray_realloc(struct bpf_iarray *old, size_t n_elem)
diff --git a/kernel/bpf/liveness.c b/kernel/bpf/liveness.c
index 44ecdc5b4ec2..9cfd05f970bc 100644
--- a/kernel/bpf/liveness.c
+++ b/kernel/bpf/liveness.c
@@ -8,6 +8,8 @@
#include <linux/slab.h>
#include <linux/sort.h>
+#include "exception.h"
+
#define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args)
struct per_frame_masks {
@@ -256,6 +258,9 @@ bpf_insn_successors(struct bpf_verifier_env *env, u32 idx)
succ = env->succ;
succ->cnt = 0;
+ if (unlikely(bpf_is_unwind_resume_kfunc(insn)))
+ return succ;
+
opcode_info = &opcode_info_tbl[BPF_CLASS(insn->code) | BPF_OP(insn->code)];
insn_sz = bpf_is_ldimm64(insn) ? 2 : 1;
if (opcode_info->can_fallthrough)
@@ -264,6 +269,13 @@ bpf_insn_successors(struct bpf_verifier_env *env, u32 idx)
if (opcode_info->can_jump)
succ->items[succ->cnt++] = idx + bpf_jmp_offset(insn) + 1;
+ if (unlikely(env->cleanup_info_cnt)) {
+ int pad = bpf_cleanup_pad_of_call(env, idx);
+
+ if (pad >= 0)
+ succ->items[succ->cnt++] = pad;
+ }
+
return succ;
}
@@ -397,6 +409,14 @@ bool bpf_stack_slot_alive(struct bpf_verifier_env *env, u32 frameno, u32 half_sp
alive = bpf_calls_callback(env, callsite)
? is_live_before(instance, callsite, rel, half_spi)
: is_live_before(instance, callsite + 1, rel, half_spi);
+
+ /* Control may also go to the landing pad. */
+ if (!alive && unlikely(env->cleanup_info_cnt)) {
+ int pad = bpf_cleanup_pad_of_call(env, callsite);
+
+ if (pad >= 0)
+ alive = is_live_before(instance, pad, rel, half_spi);
+ }
if (alive)
return true;
}
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 05/20] bpf: Make exception landing pads reachable in the CFG
2026-09-17 5:57 ` [PATCH bpf-next 05/20] bpf: Make exception landing pads reachable in the CFG Yonghong Song
@ 2026-09-17 6:22 ` sashiko-bot
2026-09-18 3:36 ` Yonghong Song
0 siblings, 1 reply; 40+ messages in thread
From: sashiko-bot @ 2026-09-17 6:22 UTC (permalink / raw)
To: Yonghong Song; +Cc: bpf
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] bpf: bpf_unwind_resume() retains fallthrough edge in CFG walk
--
commit 663c539069f6d8aab713a59c4d2aa7c90391da34
Author: Yonghong Song <yonghong.song@linux.dev>
bpf: Make exception landing pads reachable in the CFG
This commit updates the verifier's CFG walk and liveness analysis to account
for exception landing pads. It adds edges from calls within a cleanup record's
range to that record's landing pad. The commit message also states that
bpf_unwind_resume() reaches nothing after it and should have no successors.
> diff --git a/kernel/bpf/cfg.c b/kernel/bpf/cfg.c
> index 842c7d1eabccc..9f8b8b54d5ea7 100644
> --- a/kernel/bpf/cfg.c
> +++ b/kernel/bpf/cfg.c
[ ... ]
> @@ -158,17 +159,57 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
[ ... ]
> static int visit_func_call_insn(int t, struct bpf_insn *insns,
> struct bpf_verifier_env *env,
> bool visit_callee)
> {
> - int ret, insn_sz;
> + int ret, insn_sz, pad_ret;
> int w;
>
> + pad_ret = visit_cleanup_pad_edge(t, env);
> + if (pad_ret < 0)
> + return pad_ret;
> +
> insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1;
> ret = push_insn(t, t + insn_sz, FALLTHROUGH, env);
[Severity: High]
Does this unconditionally push a fallthrough edge for all call instructions,
failing to account for non-returning kfuncs like bpf_unwind_resume()?
If the compiler places a bpf_unwind_resume() call at the very end of the
program (the end of the .text section) without any trailing instructions, will
the CFG walk attempt to push a fallthrough edge out of bounds and incorrectly
reject valid BPF programs with a 'jump out of range' error?
> if (ret)
> - return ret;
> + return merge_visit_ret(pad_ret, ret);
>
> mark_prune_point(env, t + insn_sz);
[ ... ]
> diff --git a/kernel/bpf/liveness.c b/kernel/bpf/liveness.c
> index 44ecdc5b4ec2d..9cfd05f970bc9 100644
> --- a/kernel/bpf/liveness.c
> +++ b/kernel/bpf/liveness.c
[ ... ]
> @@ -256,6 +258,9 @@ bpf_insn_successors(struct bpf_verifier_env *env, u32 idx)
> succ = env->succ;
> succ->cnt = 0;
>
> + if (unlikely(bpf_is_unwind_resume_kfunc(insn)))
> + return succ;
> +
[Severity: High]
This correctly applies the logic mentioned in the commit message (that
bpf_unwind_resume() reaches nothing after it and has no successors) to the
liveness algorithm. Should visit_func_call_insn() in kernel/bpf/cfg.c be
updated with similar logic to avoid pushing a fallthrough edge?
> opcode_info = &opcode_info_tbl[BPF_CLASS(insn->code) | BPF_OP(insn->code)];
> insn_sz = bpf_is_ldimm64(insn) ? 2 : 1;
> if (opcode_info->can_fallthrough)
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260917055645.3926444-1-yonghong.song@linux.dev?part=5
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 05/20] bpf: Make exception landing pads reachable in the CFG
2026-09-17 6:22 ` sashiko-bot
@ 2026-09-18 3:36 ` Yonghong Song
0 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-18 3:36 UTC (permalink / raw)
To: sashiko-reviews; +Cc: bpf
On 9/16/26 11:22 PM, sashiko-bot@kernel.org wrote:
> Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
> - [High] bpf: bpf_unwind_resume() retains fallthrough edge in CFG walk
> --
>
> commit 663c539069f6d8aab713a59c4d2aa7c90391da34
> Author: Yonghong Song <yonghong.song@linux.dev>
>
> bpf: Make exception landing pads reachable in the CFG
>
> This commit updates the verifier's CFG walk and liveness analysis to account
> for exception landing pads. It adds edges from calls within a cleanup record's
> range to that record's landing pad. The commit message also states that
> bpf_unwind_resume() reaches nothing after it and should have no successors.
>
>> diff --git a/kernel/bpf/cfg.c b/kernel/bpf/cfg.c
>> index 842c7d1eabccc..9f8b8b54d5ea7 100644
>> --- a/kernel/bpf/cfg.c
>> +++ b/kernel/bpf/cfg.c
> [ ... ]
>> @@ -158,17 +159,57 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
> [ ... ]
>> static int visit_func_call_insn(int t, struct bpf_insn *insns,
>> struct bpf_verifier_env *env,
>> bool visit_callee)
>> {
>> - int ret, insn_sz;
>> + int ret, insn_sz, pad_ret;
>> int w;
>>
>> + pad_ret = visit_cleanup_pad_edge(t, env);
>> + if (pad_ret < 0)
>> + return pad_ret;
>> +
>> insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1;
>> ret = push_insn(t, t + insn_sz, FALLTHROUGH, env);
> [Severity: High]
> Does this unconditionally push a fallthrough edge for all call instructions,
> failing to account for non-returning kfuncs like bpf_unwind_resume()?
>
> If the compiler places a bpf_unwind_resume() call at the very end of the
> program (the end of the .text section) without any trailing instructions, will
> the CFG walk attempt to push a fallthrough edge out of bounds and incorrectly
> reject valid BPF programs with a 'jump out of range' error?
This won't happen. See verifier.c like below:
if (code != (BPF_JMP | BPF_EXIT) &&
code != (BPF_JMP32 | BPF_JA) &&
code != (BPF_JMP | BPF_JA)) {
verbose(env, "last insn is not an exit or jmp\n");
...
}
>
>> if (ret)
>> - return ret;
>> + return merge_visit_ret(pad_ret, ret);
>>
>> mark_prune_point(env, t + insn_sz);
> [ ... ]
>> diff --git a/kernel/bpf/liveness.c b/kernel/bpf/liveness.c
>> index 44ecdc5b4ec2d..9cfd05f970bc9 100644
>> --- a/kernel/bpf/liveness.c
>> +++ b/kernel/bpf/liveness.c
> [ ... ]
>> @@ -256,6 +258,9 @@ bpf_insn_successors(struct bpf_verifier_env *env, u32 idx)
>> succ = env->succ;
>> succ->cnt = 0;
>>
>> + if (unlikely(bpf_is_unwind_resume_kfunc(insn)))
>> + return succ;
>> +
> [Severity: High]
> This correctly applies the logic mentioned in the commit message (that
> bpf_unwind_resume() reaches nothing after it and has no successors) to the
> liveness algorithm. Should visit_func_call_insn() in kernel/bpf/cfg.c be
> updated with similar logic to avoid pushing a fallthrough edge?
The same as above, bpf_unwind_resume() cannot be the last insn in the prog.
>
>> opcode_info = &opcode_info_tbl[BPF_CLASS(insn->code) | BPF_OP(insn->code)];
>> insn_sz = bpf_is_ldimm64(insn) ? 2 : 1;
>> if (opcode_info->can_fallthrough)
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH bpf-next 06/20] bpf: Explore the landing pads no call site reaches
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (4 preceding siblings ...)
2026-09-17 5:57 ` [PATCH bpf-next 05/20] bpf: Make exception landing pads reachable in the CFG Yonghong Song
@ 2026-09-17 5:57 ` Yonghong Song
2026-09-17 5:57 ` [PATCH bpf-next 07/20] bpf: Refuse exception cleanup shapes bpf_throw() cannot dispatch Yonghong Song
` (13 subsequent siblings)
19 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:57 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
A cleanup record need not cover a call an exception can unwind out of: a
frontend is free to emit a region around a helper or an ordinary kfunc,
both nounwind here. Nothing marks a call site then, and that record's
landing pad is reached by nothing at all -- leaving bpf_check_cfg() to
refuse the program over code its own frontend had no way not to emit:
0: call bpf_preempt_disable
1: call bpf_preempt_enable record = { begin = 1, end = 2, pad = 4 }
2: r0 = 0
3: exit
4: r1 = pads_ran ll landing pad
6: r2 = *(u64 *)(r1 + 0)
7: r2 |= RAN_NOUNWIND_REC
8: *(u64 *)(r1 + 0) = r2
9: call bpf_unwind_resume
10: exit
The range [1,2) holds one call, and it is a kfunc, so an exception cannot
come out of it. cleanup_mark_call_sites() marks nothing, nothing pushes an
edge to 4, and 4 through 10 are reachable from nothing: "unreachable insn
4". The pad is dead, which is correct -- no exception can ever arrive at it
-- but the program is fine and has to load.
Walk every pad the table names that the edges did not reach, the way the
walk is already re-seeded at an exception callback. From there the pad is
code like any other: do_check() never enters it, because no call site
dispatches to it, so the dead code sweep removes it along with everything
else that was not reached.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
kernel/bpf/cfg.c | 17 +++++++++++++++++
1 file changed, 17 insertions(+)
diff --git a/kernel/bpf/cfg.c b/kernel/bpf/cfg.c
index 9f8b8b54d5ea..5a2b48b6a9e1 100644
--- a/kernel/bpf/cfg.c
+++ b/kernel/bpf/cfg.c
@@ -633,6 +633,7 @@ int bpf_check_cfg(struct bpf_verifier_env *env)
int insn_cnt = env->prog->len;
int *insn_stack, *insn_state;
int ex_insn_beg, i, ret = 0;
+ u32 pad_idx = 0;
insn_state = env->cfg.insn_state = kvzalloc_objs(int, insn_cnt,
GFP_KERNEL_ACCOUNT);
@@ -688,6 +689,22 @@ int bpf_check_cfg(struct bpf_verifier_env *env)
goto walk_cfg;
}
+ /*
+ * A landing pad no call site was marked with -- a record whose range
+ * holds no call an exception can unwind out of -- is reached by
+ * nothing. Walk it from here, and let the dead code sweep remove it.
+ */
+ while (pad_idx < env->cleanup_info_cnt) {
+ u32 pad = env->cleanup_info[pad_idx++].landing_pad_off;
+
+ if (insn_state[pad] != EXPLORED) {
+ insn_state[pad] = DISCOVERED;
+ insn_stack[0] = pad;
+ env->cfg.cur_stack = 1;
+ goto walk_cfg;
+ }
+ }
+
for (i = 0; i < insn_cnt; i++) {
struct bpf_insn *insn = &env->prog->insnsi[i];
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH bpf-next 07/20] bpf: Refuse exception cleanup shapes bpf_throw() cannot dispatch
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (5 preceding siblings ...)
2026-09-17 5:57 ` [PATCH bpf-next 06/20] bpf: Explore the landing pads no call site reaches Yonghong Song
@ 2026-09-17 5:57 ` Yonghong Song
2026-09-19 4:57 ` Alexei Starovoitov
2026-09-17 5:57 ` [PATCH bpf-next 08/20] bpf: Walk the exception unwind in the verifier Yonghong Song
` (12 subsequent siblings)
19 siblings, 1 reply; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:57 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
The table is on the instructions and the landing pads are in the control
flow graph. What is left before bpf_throw() can be taught to dispatch them
is to work out what that walk will need, and refuse the shapes it could not
handle.
bpf_check_cleanup_exceptions() runs after bpf_check_cfg(). Everything it
needs is control flow, so it reads what that walk has already worked out
rather than working it out again:
subprog_info.might_throw which subprograms an exception may leave,
closed over the call graph by
merge_callee_effects() as the walk pops each
callee
cleanup_reachability() what each instruction can reach -- a resume, a
plain exit, a throw, an indirect jump
cleanup_mark_pad_bodies() which instructions only ever run with an
exception already in flight
What it refuses:
- a pad that reaches both a resume and a plain exit, or neither: nothing
says whether it is a cleanup pad or a catch pad
- a catch pad, which ends in a plain exit: the walker calls a pad as a
subroutine and cannot hand a frame back its own execution
- a throw in a pad, or a call from a pad to a subprogram that can throw:
a second unwind over frames the first is still discarding
- a bpf_unwind_resume() outside a pad body
- a subprogram that may unwind used as a helper callback: the helper's
own kernel frame would end the walk before it found a boundary
- a tail call, an indirect jump, or an outgoing on-stack call argument in
a pad body, all of which touch a stack the pad does not own
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
include/linux/bpf_verifier.h | 1 +
kernel/bpf/exception.c | 397 +++++++++++++++++++++++++++++++++++
kernel/bpf/exception.h | 2 +
kernel/bpf/fixups.c | 1 +
kernel/bpf/verifier.c | 8 +
5 files changed, 409 insertions(+)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 7463e86d15ee..fe8b26351a15 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -682,6 +682,7 @@ struct bpf_insn_aux_data {
bool non_sleepable; /* helper/kfunc may be called from non-sleepable context */
bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */
bool cleanup_throw_site; /* call to bpf_throw() */
+ bool in_cleanup_pad; /* only runs with an exception in flight */
/*
* 1 + the instruction index of the exception cleanup landing pad this
* call site unwinds to, or 0 for none.
diff --git a/kernel/bpf/exception.c b/kernel/bpf/exception.c
index dfe9c2a9ce7d..b2bf831242b8 100644
--- a/kernel/bpf/exception.c
+++ b/kernel/bpf/exception.c
@@ -6,6 +6,7 @@
#include <linux/btf_ids.h>
#include <linux/filter.h>
#include <linux/slab.h>
+#include <linux/sort.h>
#include "exception.h"
#define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args)
@@ -23,6 +24,130 @@ static bool insn_is_exc_kfunc(const struct bpf_insn *insn, int kf)
insn->imm == exc_kfunc_list[kf];
}
+/* What an instruction does to intra-subprog control flow. */
+enum cleanup_insn_kind {
+ CLEANUP_INSN_PLAIN, /* the next insn runs */
+ CLEANUP_INSN_JUMP, /* unconditional jump */
+ CLEANUP_INSN_COND, /* the next insn runs, or the branch target */
+ CLEANUP_INSN_EXIT,
+ CLEANUP_INSN_THROW, /* call bpf_throw: nothing after it runs */
+ CLEANUP_INSN_RESUME, /* call bpf_unwind_resume: likewise */
+ CLEANUP_INSN_CALL, /* call to another subprog */
+ CLEANUP_INSN_GOTOX, /* indirect jump: successors not known here */
+};
+
+/* What each instruction can reach, computed once by cleanup_reachability(). */
+#define CLEANUP_REACH_RESUME BIT(0) /* a bpf_unwind_resume() call */
+#define CLEANUP_REACH_EXIT BIT(1) /* a plain BPF_EXIT */
+#define CLEANUP_REACH_UNKNOWN BIT(2) /* an indirect jump */
+#define CLEANUP_REACH_THROW BIT(3) /* a bpf_throw() call */
+
+/* Scratch shared by the analyses, sized once so no walker has to allocate. */
+struct cleanup_ctx {
+ struct bpf_verifier_env *env;
+ u8 *reach; /* per insn: CLEANUP_REACH_* mask */
+ u32 *stack; /* per insn: DFS stack */
+ void *scratch; /* the one allocation all of the above live in */
+};
+
+static bool in_pad(struct bpf_verifier_env *env, u32 i)
+{
+ return env->insn_aux_data[i].in_cleanup_pad;
+}
+
+/* One scratch array for cleanup_alloc() to hand out. */
+struct cleanup_alloc_req {
+ void **dst;
+ size_t n, sz;
+};
+
+static void *cleanup_alloc(const struct cleanup_alloc_req *tab, u32 cnt)
+{
+ size_t total = 0;
+ char *block, *p;
+ u32 i;
+
+ for (i = 0; i < cnt; i++)
+ total += round_up(tab[i].n * tab[i].sz, 8);
+
+ block = kvzalloc(total, GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
+ if (!block)
+ return NULL;
+
+ for (i = 0, p = block; i < cnt; i++) {
+ *tab[i].dst = p;
+ p += round_up(tab[i].n * tab[i].sz, 8);
+ }
+ return block;
+}
+
+static int cleanup_subprog_of(struct bpf_verifier_env *env, u32 off)
+{
+ struct bpf_subprog_info *info = bpf_find_containing_subprog(env, off);
+
+ return info ? info - env->subprog_info : -1;
+}
+
+/* The subprogram a linear pass is currently in. */
+struct cleanup_cursor {
+ u32 start, end; /* [start, end) of the current subprogram */
+ int sub; /* its index */
+};
+
+#define CLEANUP_CURSOR_INIT { .sub = -1 }
+
+static void cleanup_cursor_to(struct bpf_verifier_env *env, struct cleanup_cursor *c, u32 i)
+{
+ while (i >= c->end) {
+ c->sub++;
+ c->start = env->subprog_info[c->sub].start;
+ c->end = env->subprog_info[c->sub + 1].start;
+ }
+}
+
+static enum cleanup_insn_kind cleanup_classify(struct bpf_verifier_env *env, u32 i,
+ int *next, int *target)
+{
+ struct bpf_insn *insn = &env->prog->insnsi[i];
+ u8 class = BPF_CLASS(insn->code);
+
+ *next = i + 1;
+ *target = -1;
+
+ if (insn->code == (BPF_LD | BPF_IMM | BPF_DW)) {
+ *next = i + 2;
+ return CLEANUP_INSN_PLAIN;
+ }
+ if (class != BPF_JMP && class != BPF_JMP32)
+ return CLEANUP_INSN_PLAIN;
+
+ switch (BPF_OP(insn->code)) {
+ case BPF_EXIT:
+ *next = -1;
+ return CLEANUP_INSN_EXIT;
+ case BPF_JA:
+ *next = -1;
+ if (BPF_SRC(insn->code) == BPF_X)
+ return CLEANUP_INSN_GOTOX;
+ *target = class == BPF_JMP32 ? i + insn->imm + 1 : i + insn->off + 1;
+ return CLEANUP_INSN_JUMP;
+ case BPF_CALL:
+ if (bpf_is_throw_kfunc(insn)) {
+ *next = -1;
+ return CLEANUP_INSN_THROW;
+ }
+ if (insn_is_exc_kfunc(insn, EXC_KF_bpf_unwind_resume)) {
+ *next = -1;
+ return CLEANUP_INSN_RESUME;
+ }
+ return bpf_pseudo_call(insn) ? CLEANUP_INSN_CALL : CLEANUP_INSN_PLAIN;
+ default:
+ /* Conditional jump, including BPF_JCOND. */
+ *target = i + insn->off + 1;
+ return CLEANUP_INSN_COND;
+ }
+}
+
static void cleanup_mark_throw_sites(struct bpf_verifier_env *env)
{
u32 i;
@@ -32,6 +157,247 @@ static void cleanup_mark_throw_sites(struct bpf_verifier_env *env)
env->insn_aux_data[i].cleanup_throw_site = true;
}
+int bpf_cleanup_check_callback(struct bpf_verifier_env *env, int subprog)
+{
+ if (!env->cleanup_info_cnt || !env->subprog_info[subprog].might_throw)
+ return 0;
+
+ verbose(env, "subprog %d may unwind and is used as a callback\n", subprog);
+ return -EINVAL;
+}
+
+/* Intra-subprog successors of @i, or -1 each when absent. */
+static enum cleanup_insn_kind cleanup_succ(struct bpf_verifier_env *env, u32 i,
+ u32 start, u32 end, int *next, int *target)
+{
+ enum cleanup_insn_kind kind = cleanup_classify(env, i, next, target);
+
+ if (*next < (int)start || *next >= (int)end)
+ *next = -1;
+ if (*target < (int)start || *target >= (int)end)
+ *target = -1;
+ return kind;
+}
+
+static void cleanup_add_pred(u32 *head, u32 *link, u32 to, u32 e)
+{
+ link[e] = head[to];
+ head[to] = e + 1;
+}
+
+/* What every instruction can reach along intra-subprog edges, for
+ * cleanup_pad_is_catch(). One backward walk over a predecessor index, rather
+ * than a forward walk from each landing pad, which would be quadratic.
+ */
+static int cleanup_reachability(struct cleanup_ctx *ctx)
+{
+ struct bpf_verifier_env *env = ctx->env;
+ u32 len = env->prog->len;
+ struct cleanup_cursor c = CLEANUP_CURSOR_INIT;
+ u32 *head = NULL, *link = NULL;
+ bool *queued = NULL;
+ u32 i, sp = 0;
+ void *scratch;
+ const struct cleanup_alloc_req tab[] = {
+ { (void **)&head, len, sizeof(*head) },
+ { (void **)&link, 2 * (size_t)len, sizeof(*link) },
+ { (void **)&queued, len, sizeof(*queued) },
+ };
+
+ scratch = cleanup_alloc(tab, ARRAY_SIZE(tab));
+ if (!scratch)
+ return -ENOMEM;
+
+ /* Index the predecessors, and seed the walk at the terminators. */
+ for (i = 0; i < len; i++) {
+ enum cleanup_insn_kind kind;
+ int next, target;
+
+ cleanup_cursor_to(env, &c, i);
+ kind = cleanup_succ(env, i, c.start, c.end, &next, &target);
+
+ if (kind == CLEANUP_INSN_RESUME)
+ ctx->reach[i] |= CLEANUP_REACH_RESUME;
+ else if (kind == CLEANUP_INSN_EXIT)
+ ctx->reach[i] |= CLEANUP_REACH_EXIT;
+ else if (kind == CLEANUP_INSN_GOTOX)
+ ctx->reach[i] |= CLEANUP_REACH_UNKNOWN;
+ else if (kind == CLEANUP_INSN_THROW)
+ ctx->reach[i] |= CLEANUP_REACH_THROW;
+
+ if (next >= 0)
+ cleanup_add_pred(head, link, next, 2 * i);
+ if (target >= 0)
+ cleanup_add_pred(head, link, target, 2 * i + 1);
+
+ if (ctx->reach[i]) {
+ queued[i] = true;
+ ctx->stack[sp++] = i;
+ }
+ }
+
+ /* Each instruction re-enters the worklist at most once per bit it
+ * gains, so this is linear in the number of edges.
+ */
+ while (sp) {
+ u32 j = ctx->stack[--sp];
+ u8 flags = ctx->reach[j];
+ u32 e;
+
+ queued[j] = false;
+ for (e = head[j]; e; e = link[e - 1]) {
+ u32 p = (e - 1) / 2;
+
+ if ((ctx->reach[p] | flags) == ctx->reach[p])
+ continue;
+ ctx->reach[p] |= flags;
+ if (!queued[p]) {
+ queued[p] = true;
+ ctx->stack[sp++] = p;
+ }
+ }
+ }
+ kvfree(scratch);
+ return 0;
+}
+
+static int cleanup_pad_is_catch(struct cleanup_ctx *ctx, u32 pad)
+{
+ u8 reach = ctx->reach[pad];
+
+ if (reach & CLEANUP_REACH_UNKNOWN) {
+ verbose(ctx->env, "cleanup landing pad %u reaches an indirect jump\n", pad);
+ return -EINVAL;
+ }
+ if (reach & CLEANUP_REACH_THROW) {
+ verbose(ctx->env,
+ "cleanup landing pad %u can throw while an exception is in flight\n",
+ pad);
+ return -EINVAL;
+ }
+ if (!(reach & CLEANUP_REACH_RESUME) == !(reach & CLEANUP_REACH_EXIT)) {
+ verbose(ctx->env, "cleanup landing pad %u %s\n", pad,
+ (reach & CLEANUP_REACH_RESUME) ?
+ "reaches both bpf_unwind_resume() and a plain exit" :
+ "reaches neither bpf_unwind_resume() nor an exit");
+ return -EINVAL;
+ }
+ return !!(reach & CLEANUP_REACH_EXIT);
+}
+
+static int cleanup_check_pad_insn(struct bpf_verifier_env *env, u32 i)
+{
+ struct bpf_insn *insn = &env->prog->insnsi[i];
+
+ if (bpf_helper_call(insn) && insn->imm == BPF_FUNC_tail_call) {
+ verbose(env,
+ "bpf_tail_call() at insn %u is in an exception cleanup landing pad\n",
+ i);
+ return -EINVAL;
+ }
+ /* Stack arguments are not supported. */
+ if (is_stack_arg_st(insn) || is_stack_arg_stx(insn)) {
+ verbose(env,
+ "insn %u passes an on-stack call argument in an exception cleanup landing pad\n",
+ i);
+ return -EINVAL;
+ }
+ /* Likewise, stack arguments are not supported. */
+ if (bpf_pseudo_kfunc_call(insn)) {
+ struct bpf_call_summary cs;
+
+ if (bpf_get_call_summary(env, insn, &cs) &&
+ cs.arg_slot_cnt > MAX_BPF_FUNC_REG_ARGS) {
+ verbose(env,
+ "insn %u passes an on-stack call argument in an exception cleanup landing pad\n",
+ i);
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+
+static int cleanup_mark_pad_bodies(struct cleanup_ctx *ctx)
+{
+ struct bpf_verifier_env *env = ctx->env;
+ u32 i, sp = 0;
+ int ret;
+
+ for (i = 0; i < env->cleanup_info_cnt; i++) {
+ u32 pad = env->cleanup_info[i].landing_pad_off;
+
+ if (in_pad(env, pad))
+ continue;
+
+ ret = cleanup_pad_is_catch(ctx, pad);
+ if (ret < 0)
+ return ret;
+ if (ret) {
+ verbose(env,
+ "catch landing pad %u is not supported yet, only cleanup pads that resume\n",
+ pad);
+ return -EOPNOTSUPP;
+ }
+ env->insn_aux_data[pad].in_cleanup_pad = true;
+ ctx->stack[sp++] = pad;
+ }
+
+ while (sp) {
+ u32 j = ctx->stack[--sp];
+ enum cleanup_insn_kind kind;
+ int next, target, sub;
+ u32 start, end;
+
+ ret = cleanup_check_pad_insn(env, j);
+ if (ret)
+ return ret;
+
+ sub = cleanup_subprog_of(env, j);
+ start = env->subprog_info[sub].start;
+ end = env->subprog_info[sub + 1].start;
+ kind = cleanup_succ(env, j, start, end, &next, &target);
+
+ if (kind == CLEANUP_INSN_CALL) {
+ int callee = cleanup_subprog_of(env, j + env->prog->insnsi[j].imm + 1);
+
+ if (env->subprog_info[callee].might_throw) {
+ verbose(env,
+ "cleanup landing pad calls subprog %d at insn %u, which can throw while an exception is in flight\n",
+ callee, j);
+ return -EINVAL;
+ }
+ }
+
+ if (next >= 0 && !in_pad(env, next)) {
+ env->insn_aux_data[next].in_cleanup_pad = true;
+ ctx->stack[sp++] = next;
+ }
+ if (target >= 0 && !in_pad(env, target)) {
+ env->insn_aux_data[target].in_cleanup_pad = true;
+ ctx->stack[sp++] = target;
+ }
+ }
+ return 0;
+}
+
+static int cleanup_check_resumes(struct cleanup_ctx *ctx)
+{
+ struct bpf_verifier_env *env = ctx->env;
+ u32 i;
+
+ for (i = 0; i < env->prog->len; i++) {
+ if (!insn_is_exc_kfunc(&env->prog->insnsi[i], EXC_KF_bpf_unwind_resume))
+ continue;
+ if (in_pad(env, i))
+ continue;
+ verbose(env,
+ "bpf_unwind_resume() at insn %u is not in an exception cleanup landing pad\n",
+ i);
+ return -EINVAL;
+ }
+ return 0;
+}
+
static void cleanup_mark_call_sites(struct bpf_verifier_env *env)
{
u32 i, j;
@@ -78,6 +444,37 @@ int bpf_prepare_cleanup_exceptions(struct bpf_verifier_env *env)
return 0;
}
+int bpf_check_cleanup_exceptions(struct bpf_verifier_env *env)
+{
+ u32 len = env->prog->len;
+ struct cleanup_ctx ctx = { .env = env };
+ const struct cleanup_alloc_req tab[] = {
+ { (void **)&ctx.reach, len, sizeof(*ctx.reach) },
+ { (void **)&ctx.stack, len, sizeof(*ctx.stack) },
+ };
+ int ret;
+
+ if (!env->cleanup_info_cnt)
+ return 0;
+
+ ctx.scratch = cleanup_alloc(tab, ARRAY_SIZE(tab));
+ if (!ctx.scratch)
+ return -ENOMEM;
+
+ ret = cleanup_reachability(&ctx);
+ if (ret)
+ goto out;
+
+ ret = cleanup_mark_pad_bodies(&ctx);
+ if (ret)
+ goto out;
+
+ ret = cleanup_check_resumes(&ctx);
+out:
+ kvfree(ctx.scratch);
+ return ret;
+}
+
bool bpf_is_unwind_resume_kfunc(const struct bpf_insn *insn)
{
return insn_is_exc_kfunc(insn, EXC_KF_bpf_unwind_resume);
diff --git a/kernel/bpf/exception.h b/kernel/bpf/exception.h
index f51383fd775c..7313dd2b65a1 100644
--- a/kernel/bpf/exception.h
+++ b/kernel/bpf/exception.h
@@ -8,6 +8,8 @@
struct bpf_verifier_env;
int bpf_prepare_cleanup_exceptions(struct bpf_verifier_env *env);
+int bpf_check_cleanup_exceptions(struct bpf_verifier_env *env);
+int bpf_cleanup_check_callback(struct bpf_verifier_env *env, int subprog);
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 82b00fac6bd6..f120ae66dbbc 100644
--- a/kernel/bpf/fixups.c
+++ b/kernel/bpf/fixups.c
@@ -252,6 +252,7 @@ static void adjust_insn_aux_data(struct bpf_verifier_env *env,
/* Expand insni[off]'s seen count to the patched range. */
data[i].seen = old_seen;
data[i].zext_dst = bpf_insn_def32(new_prog, insn + i) >= 0;
+ data[i].in_cleanup_pad = data[off + cnt - 1].in_cleanup_pad;
if (!memcmp(insn + i, original_insn, sizeof(struct bpf_insn))) {
data[i].non_stack_access =
data[off + cnt - 1].non_stack_access;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6496c30a10f7..9cbdb8339701 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -10485,6 +10485,10 @@ static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *ins
* callbacks
*/
env->subprog_info[subprog].is_cb = true;
+ err = bpf_cleanup_check_callback(env, subprog);
+ if (err)
+ return err;
+
if (bpf_pseudo_kfunc_call(insn) &&
!is_callback_calling_kfunc(insn->imm)) {
verifier_bug(env, "kfunc %s#%d not marked as callback-calling",
@@ -21664,6 +21668,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr,
if (ret < 0)
goto skip_full_check;
+ ret = bpf_check_cleanup_exceptions(env);
+ if (ret < 0)
+ goto skip_full_check;
+
ret = bpf_compute_postorder(env);
if (ret < 0)
goto skip_full_check;
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 07/20] bpf: Refuse exception cleanup shapes bpf_throw() cannot dispatch
2026-09-17 5:57 ` [PATCH bpf-next 07/20] bpf: Refuse exception cleanup shapes bpf_throw() cannot dispatch Yonghong Song
@ 2026-09-19 4:57 ` Alexei Starovoitov
2026-09-19 17:32 ` Yonghong Song
0 siblings, 1 reply; 40+ messages in thread
From: Alexei Starovoitov @ 2026-09-19 4:57 UTC (permalink / raw)
To: Yonghong Song, bpf
Cc: Andrii Nakryiko, Daniel Borkmann, Eduard Zingerman, kernel-team
On Wed, Sep 16, 2026 at 10:57 PM Yonghong Song <yonghong.song@linux.dev> wrote:
> diff --git a/kernel/bpf/exception.c b/kernel/bpf/exception.c
> index dfe9c2a9ce7d..b2bf831242b8 100644
> --- a/kernel/bpf/exception.c
> +++ b/kernel/bpf/exception.c
[...]
> +static enum cleanup_insn_kind cleanup_classify(struct bpf_verifier_env *env, u32 i,
> + int *next, int *target)
> +{
> + struct bpf_insn *insn = &env->prog->insnsi[i];
> + u8 class = BPF_CLASS(insn->code);
> +
> + *next = i + 1;
> + *target = -1;
> +
> + if (insn->code == (BPF_LD | BPF_IMM | BPF_DW)) {
> + *next = i + 2;
> + return CLEANUP_INSN_PLAIN;
> + }
> + if (class != BPF_JMP && class != BPF_JMP32)
> + return CLEANUP_INSN_PLAIN;
robot voice:
LD_ABS/LD_IND is not plain. bpf_check_cfg() treats it as an abnormal
return and gen_ld_abs() later patches in a real "r0 = 0; exit" for the
failed load. With this classification a pad in a tc prog that keeps
skb in r6 and does an ld_abs passes t
he "reaches no exit" check,
cleanup_check_pad_insn() doesn't look at it, and check_ld_abs() only
wants no locks/refs held at that point. At run time a failed load runs
the subprog epilogue on the walker's stack: callee regs get popped
from arch_bpf_run_cleanup_pad()'s frame, leave/ret with rbp == the
unwinding frame goes straight back into the BPF caller with garbage
in rbx/r13-r15, and the rest of bpf_throw() is abandoned.
Treat it like BPF_EXIT here or refuse it in a pad body like tail call.
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 07/20] bpf: Refuse exception cleanup shapes bpf_throw() cannot dispatch
2026-09-19 4:57 ` Alexei Starovoitov
@ 2026-09-19 17:32 ` Yonghong Song
0 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-19 17:32 UTC (permalink / raw)
To: Alexei Starovoitov, bpf
Cc: Andrii Nakryiko, Daniel Borkmann, Eduard Zingerman, kernel-team
On 9/18/26 9:57 PM, Alexei Starovoitov wrote:
> On Wed, Sep 16, 2026 at 10:57 PM Yonghong Song <yonghong.song@linux.dev> wrote:
>> diff --git a/kernel/bpf/exception.c b/kernel/bpf/exception.c
>> index dfe9c2a9ce7d..b2bf831242b8 100644
>> --- a/kernel/bpf/exception.c
>> +++ b/kernel/bpf/exception.c
> [...]
>
>> +static enum cleanup_insn_kind cleanup_classify(struct bpf_verifier_env *env, u32 i,
>> + int *next, int *target)
>> +{
>> + struct bpf_insn *insn = &env->prog->insnsi[i];
>> + u8 class = BPF_CLASS(insn->code);
>> +
>> + *next = i + 1;
>> + *target = -1;
>> +
>> + if (insn->code == (BPF_LD | BPF_IMM | BPF_DW)) {
>> + *next = i + 2;
>> + return CLEANUP_INSN_PLAIN;
>> + }
>> + if (class != BPF_JMP && class != BPF_JMP32)
>> + return CLEANUP_INSN_PLAIN;
> robot voice:
>
> LD_ABS/LD_IND is not plain. bpf_check_cfg() treats it as an abnormal
> return and gen_ld_abs() later patches in a real "r0 = 0; exit" for the
> failed load. With this classification a pad in a tc prog that keeps
> skb in r6 and does an ld_abs passes t
> he "reaches no exit" check,
> cleanup_check_pad_insn() doesn't look at it, and check_ld_abs() only
> wants no locks/refs held at that point. At run time a failed load runs
> the subprog epilogue on the walker's stack: callee regs get popped
> from arch_bpf_run_cleanup_pad()'s frame, leave/ret with rbp == the
> unwinding frame goes straight back into the BPF caller with garbage
> in rbx/r13-r15, and the rest of bpf_throw() is abandoned.
> Treat it like BPF_EXIT here or refuse it in a pad body like tail call.
Yes, this is an issue. For insns in landing pad, we should not allow
LD_ABS/LD_IND since they will have a hidden return. So the above suggestion
to refuse it in a pad body is correct.
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH bpf-next 08/20] bpf: Walk the exception unwind in the verifier
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (6 preceding siblings ...)
2026-09-17 5:57 ` [PATCH bpf-next 07/20] bpf: Refuse exception cleanup shapes bpf_throw() cannot dispatch Yonghong Song
@ 2026-09-17 5:57 ` Yonghong Song
2026-09-19 4:57 ` Alexei Starovoitov
2026-09-17 5:57 ` [PATCH bpf-next 09/20] bpf: Refuse a private stack for a program with an exception cleanup table Yonghong Song
` (11 subsequent siblings)
19 siblings, 1 reply; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:57 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
bpf_throw() is about to stop discarding the frames it unwinds and start
running their landing pads instead. Have the verifier walk the same thing,
step for step:
at a throw, with the frame chain in env->cur_state->frame[]
if a record covers the call control is at
run that record's landing pad in this frame
on reaching its resume, pop the frame and carry on
else
pop the frame and carry on
at the boundary, deliver
Doing it this way is what keeps the resource rules unchanged. Whatever a
pad releases is released in the verifier state too, so by the time the walk
reaches the boundary the state says exactly what the program will really
hold there -- and check_resource_leak(), which used to fire the moment a
throw was seen, simply moves to the end of the walk. A frame that no record
covers contributes nothing, so anything it held is still held when the walk
ends, and that is what gets reported.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
include/linux/bpf_cleanup_abi.h | 16 +++++
include/linux/bpf_verifier.h | 1 +
kernel/bpf/states.c | 3 +
kernel/bpf/verifier.c | 102 +++++++++++++++++++++++++-------
4 files changed, 99 insertions(+), 23 deletions(-)
create mode 100644 include/linux/bpf_cleanup_abi.h
diff --git a/include/linux/bpf_cleanup_abi.h b/include/linux/bpf_cleanup_abi.h
new file mode 100644
index 000000000000..b6c1d589abda
--- /dev/null
+++ b/include/linux/bpf_cleanup_abi.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#ifndef _LINUX_BPF_CLEANUP_ABI_H
+#define _LINUX_BPF_CLEANUP_ABI_H
+
+/*
+ * Value arch_bpf_run_cleanup_pad() leaves in r0 on the way into a landing pad.
+ * It has to be a constant the verifier knows: LLVM names r0 as both the
+ * exception pointer and the exception selector register, so every pad reads it
+ * before anything else and is free to store what it read. Kept on its own
+ * because the verifier and the arch dispatchers, which are assembly, have to
+ * agree on it.
+ */
+#define BPF_PAD_ENTRY_R0 1
+
+#endif /* _LINUX_BPF_CLEANUP_ABI_H */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index fe8b26351a15..09fb89fda40a 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -509,6 +509,7 @@ struct bpf_verifier_state {
bool speculative;
bool in_sleepable;
+ bool unwinding;
/* first and last insn idx of this verifier state */
u32 first_insn_idx;
diff --git a/kernel/bpf/states.c b/kernel/bpf/states.c
index 66fb11b6c6a7..be0f529f7ecc 100644
--- a/kernel/bpf/states.c
+++ b/kernel/bpf/states.c
@@ -996,6 +996,9 @@ static bool states_equal(struct bpf_verifier_env *env,
if (old->in_sleepable != cur->in_sleepable)
return false;
+ if (old->unwinding != cur->unwinding)
+ return false;
+
if (!refsafe(old, cur, &env->idmap_scratch))
return false;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9cbdb8339701..a3b34ded1392 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -10,6 +10,7 @@
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/btf.h>
+#include <linux/bpf_cleanup_abi.h>
#include <linux/bpf_verifier.h>
#include <linux/filter.h>
#include <net/netlink.h>
@@ -1715,6 +1716,7 @@ int bpf_copy_verifier_state(struct bpf_verifier_state *dst_state,
return err;
dst_state->speculative = src->speculative;
dst_state->in_sleepable = src->in_sleepable;
+ dst_state->unwinding = src->unwinding;
dst_state->curframe = src->curframe;
dst_state->branches = src->branches;
dst_state->parent = src->parent;
@@ -10540,8 +10542,8 @@ static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *ins
return 0;
}
-static int process_bpf_exit_full(struct bpf_verifier_env *env,
- bool *do_print_state, bool exception_exit);
+static int process_bpf_exit_full(struct bpf_verifier_env *env, bool *do_print_state);
+static int unwind_step(struct bpf_verifier_env *env, u32 callsite, int *insn_idx);
static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int *insn_idx)
@@ -10631,7 +10633,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
verbose(env, "failed to push state for global subprog exception path\n");
return PTR_ERR(branch);
}
- return process_bpf_exit_full(env, NULL, true);
+ return unwind_step(env, *insn_idx, insn_idx);
}
/* continue with next insn after call */
@@ -14511,7 +14513,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
env->prog->call_session_cookie = true;
if (bpf_is_throw_kfunc(insn))
- return process_bpf_exit_full(env, NULL, true);
+ return unwind_step(env, insn_idx, &env->insn_idx);
return 0;
}
@@ -18436,9 +18438,75 @@ enum {
INSN_IDX_UPDATED = 2,
};
-static int process_bpf_exit_full(struct bpf_verifier_env *env,
- bool *do_print_state,
- bool exception_exit)
+static u32 unwind_pop_frame(struct bpf_verifier_env *env)
+{
+ struct bpf_verifier_state *state = env->cur_state;
+ struct bpf_func_state *callee = state->frame[state->curframe];
+ u32 callsite = callee->callsite;
+ struct bpf_func_state *caller;
+
+ caller = state->frame[state->curframe - 1];
+ account_processed_insns(env, callee, caller);
+ free_func_state(callee);
+ state->frame[state->curframe--] = NULL;
+ invalidate_outgoing_stack_args(env, caller);
+ return callsite;
+}
+
+static void unwind_enter_pad(struct bpf_verifier_env *env)
+{
+ struct bpf_func_state *frame = cur_func(env);
+
+ clear_caller_saved_regs(env, frame->regs);
+ mark_reg_unknown(env, frame->regs, BPF_REG_0);
+ __mark_reg_known(&frame->regs[BPF_REG_0], BPF_PAD_ENTRY_R0);
+}
+
+static int unwind_finish(struct bpf_verifier_env *env)
+{
+ int err = check_resource_leak(env, true, true, "bpf_throw");
+
+ if (err)
+ return err;
+ return PROCESS_BPF_EXIT;
+}
+
+static int unwind_step(struct bpf_verifier_env *env, u32 callsite, int *insn_idx)
+{
+ struct bpf_verifier_state *state = env->cur_state;
+
+ state->unwinding = true;
+ for (;;) {
+ int pad = bpf_cleanup_pad_of_call(env, callsite);
+
+ if (pad >= 0) {
+ unwind_enter_pad(env);
+ *insn_idx = pad;
+ return INSN_IDX_UPDATED;
+ }
+ if (!state->curframe)
+ return unwind_finish(env);
+ callsite = unwind_pop_frame(env);
+ }
+}
+
+static int process_cleanup_resume(struct bpf_verifier_env *env, int *insn_idx)
+{
+ struct bpf_verifier_state *state = env->cur_state;
+
+ /* A pad entered by ordinary control flow. */
+ if (!state->unwinding) {
+ verbose(env,
+ "bpf_unwind_resume() at insn %d reached without an exception in flight\n",
+ *insn_idx);
+ return -EINVAL;
+ }
+ if (!state->curframe)
+ return unwind_finish(env);
+ return unwind_step(env, unwind_pop_frame(env), insn_idx);
+}
+
+static int process_bpf_exit_full(struct bpf_verifier_env *env, bool *do_print_state)
{
struct bpf_func_state *cur_frame = cur_func(env);
@@ -18448,25 +18516,11 @@ static int process_bpf_exit_full(struct bpf_verifier_env *env,
* for which reference_state must match caller reference
* state when it exits.
*/
- int err = check_resource_leak(env, exception_exit,
- exception_exit || !env->cur_state->curframe,
- exception_exit ? "bpf_throw" :
+ int err = check_resource_leak(env, false, !env->cur_state->curframe,
"BPF_EXIT instruction in main prog");
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)
- return PROCESS_BPF_EXIT;
-
if (env->cur_state->curframe) {
/* exit from nested function */
err = prepare_func_exit(env, &env->insn_idx);
@@ -18640,6 +18694,8 @@ static int do_check_insn(struct bpf_verifier_env *env, bool *do_print_state)
env->jmps_processed++;
if (opcode == BPF_CALL) {
+ if (bpf_is_unwind_resume_kfunc(insn))
+ return process_cleanup_resume(env, &env->insn_idx);
if (env->cur_state->active_locks) {
if ((insn->src_reg == BPF_REG_0 &&
insn->imm != BPF_FUNC_spin_unlock &&
@@ -18673,7 +18729,7 @@ static int do_check_insn(struct bpf_verifier_env *env, bool *do_print_state)
env->insn_idx += insn->imm + 1;
return INSN_IDX_UPDATED;
} else if (opcode == BPF_EXIT) {
- return process_bpf_exit_full(env, do_print_state, false);
+ return process_bpf_exit_full(env, do_print_state);
}
return check_cond_jmp_op(env, insn, &env->insn_idx);
}
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 08/20] bpf: Walk the exception unwind in the verifier
2026-09-17 5:57 ` [PATCH bpf-next 08/20] bpf: Walk the exception unwind in the verifier Yonghong Song
@ 2026-09-19 4:57 ` Alexei Starovoitov
2026-09-19 17:36 ` Yonghong Song
0 siblings, 1 reply; 40+ messages in thread
From: Alexei Starovoitov @ 2026-09-19 4:57 UTC (permalink / raw)
To: Yonghong Song, bpf
Cc: Andrii Nakryiko, Daniel Borkmann, Eduard Zingerman, kernel-team
On Wed, Sep 16, 2026 at 10:57 PM Yonghong Song <yonghong.song@linux.dev> wrote:
> diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
> index 9cbdb8339701..a3b34ded1392 100644
> --- a/kernel/bpf/verifier.c
> +++ b/kernel/bpf/verifier.c
[...]
> +static int unwind_step(struct bpf_verifier_env *env, u32 callsite, int *insn_idx)
> +{
> + struct bpf_verifier_state *state = env->cur_state;
> +
> + state->unwinding = true;
> + for (;;) {
> + int pad = bpf_cleanup_pad_of_call(env, callsite);
> +
> + if (pad >= 0) {
> + unwind_enter_pad(env);
> + *insn_idx = pad;
> + return INSN_IDX_UPDATED;
> + }
> + if (!state->curframe)
> + return unwind_finish(env);
> + callsite = unwind_pop_frame(env);
> + }
> +}
robot voice:
mark_chain_precision() doesn't know about this edge. The jmp history
gets (bpf_throw in frame N+k) -> (pad in frame N), or (resume in N+1)
-> (pad in N), with no BPF_EXIT in between, and backtrack_insn() only
switches frames on E
XIT and pseudo calls. So bt->frame stays at N
while it walks the callee's insns backwards. If the callee wrote its
own r6 the request for the caller's r6 is cleared there, the caller's
def of r6 is never marked precise, and a later state with a different
r6 is pruned at the call site checkpoint even though the pad does
r10 + r6 with it. If the callee didn't touch r6 the walk reaches the
static call insn with r6 still set and hits
verifier_bug("static subprog unexpected regs"). For a throwing global
subprog it's verifier_bug_if(idx + 1 != subseq_idx) right away.
The unwind transition needs its own jmp history flag and
backtrack_insn() has to bt_subprog_enter() once per popped frame,
like it does for BPF_EXIT.
Pls add a test that does a variable offset stack access in a pad
with the offset coming from r6-r9 set before the throwing call.
> +static int process_cleanup_resume(struct bpf_verifier_env *env, int *insn_idx)
> +{
> + struct bpf_verifier_state *state = env->cur_
state;
> +
> + /* A pad entered by ordinary control flow. */
> + if (!state->unwinding) {
> + verbose(env,
> + "bpf_unwind_resume() at insn %d reached without an exception in flight\n",
> + *insn_idx);
> + return -EINVAL;
> + }
> + if (!state->curframe)
> + return unwind_finish(env);
> + return unwind_step(env, unwind_pop_frame(env), insn_idx);
> +}
unwinding is one bit for the whole state, so once a throw happened a
bpf_unwind_resume() is accepted in any frame, not only in the frame
whose pad the walker dispatched. The in_pad rule from patch 7 doesn't
close it: take subprog S that never throws, has its own record, and
whose pad is just "call bpf_unwind_resume" reachable by a plain branch
from S's entry. F's pad does "call S" and S branches into its pad.
Here the verifier pops S, finds no pad for the "call S" site, pops F
and finishes, so whatever follows "call S" in F's pad is never walked
in this state. On x86 S's resume is a bare ret, so at run time it
returns into F's pad right after "call S" and keeps executing it with
S's leftover registers. On arm64 br x23 ends F's pad early instead.
Remember the frame unwind_step() entered the pad in and reject
bpf_unwind_resume() when curframe doesn't match.
pw-bot: cr
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 08/20] bpf: Walk the exception unwind in the verifier
2026-09-19 4:57 ` Alexei Starovoitov
@ 2026-09-19 17:36 ` Yonghong Song
0 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-19 17:36 UTC (permalink / raw)
To: Alexei Starovoitov, bpf
Cc: Andrii Nakryiko, Daniel Borkmann, Eduard Zingerman, kernel-team
On 9/18/26 9:57 PM, Alexei Starovoitov wrote:
> On Wed, Sep 16, 2026 at 10:57 PM Yonghong Song <yonghong.song@linux.dev> wrote:
>> diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
>> index 9cbdb8339701..a3b34ded1392 100644
>> --- a/kernel/bpf/verifier.c
>> +++ b/kernel/bpf/verifier.c
> [...]
>
>> +static int unwind_step(struct bpf_verifier_env *env, u32 callsite, int *insn_idx)
>> +{
>> + struct bpf_verifier_state *state = env->cur_state;
>> +
>> + state->unwinding = true;
>> + for (;;) {
>> + int pad = bpf_cleanup_pad_of_call(env, callsite);
>> +
>> + if (pad >= 0) {
>> + unwind_enter_pad(env);
>> + *insn_idx = pad;
>> + return INSN_IDX_UPDATED;
>> + }
>> + if (!state->curframe)
>> + return unwind_finish(env);
>> + callsite = unwind_pop_frame(env);
>> + }
>> +}
> robot voice:
>
> mark_chain_precision() doesn't know about this edge. The jmp history
> gets (bpf_throw in frame N+k) -> (pad in frame N), or (resume in N+1)
> -> (pad in N), with no BPF_EXIT in between, and backtrack_insn() only
> switches frames on E
> XIT and pseudo calls. So bt->frame stays at N
> while it walks the callee's insns backwards. If the callee wrote its
> own r6 the request for the caller's r6 is cleared there, the caller's
> def of r6 is never marked precise, and a later state with a different
> r6 is pruned at the call site checkpoint even though the pad does
> r10 + r6 with it. If the callee didn't touch r6 the walk reaches the
> static call insn with r6 still set and hits
> verifier_bug("static subprog unexpected regs"). For a throwing global
> subprog it's verifier_bug_if(idx + 1 != subseq_idx) right away.
> The unwind transition needs its own jmp history flag and
> backtrack_insn() has to bt_subprog_enter() once per popped frame,
> like it does for BPF_EXIT.
> Pls add a test that does a variable offset stack access in a pad
> with the offset coming from r6-r9 set before the throwing call.
>
>> +static int process_cleanup_resume(struct bpf_verifier_env *env, int *insn_idx)
>> +{
>> + struct bpf_verifier_state *state = env->cur_
> state;
>> +
>> + /* A pad entered by ordinary control flow. */
>> + if (!state->unwinding) {
>> + verbose(env,
>> + "bpf_unwind_resume() at insn %d reached without an exception in flight\n",
>> + *insn_idx);
>> + return -EINVAL;
>> + }
>> + if (!state->curframe)
>> + return unwind_finish(env);
>> + return unwind_step(env, unwind_pop_frame(env), insn_idx);
>> +}
> unwinding is one bit for the whole state, so once a throw happened a
> bpf_unwind_resume() is accepted in any frame, not only in the frame
> whose pad the walker dispatched. The in_pad rule from patch 7 doesn't
> close it: take subprog S that never throws, has its own record, and
> whose pad is just "call bpf_unwind_resume" reachable by a plain branch
> from S's entry. F's pad does "call S" and S branches into its pad.
> Here the verifier pops S, finds no pad for the "call S" site, pops F
> and finishes, so whatever follows "call S" in F's pad is never walked
> in this state. On x86 S's resume is a bare ret, so at run time it
>
>
> returns into F's pad right after "call S" and keeps executing it with
> S's leftover registers. On arm64 br x23 ends F's pad early instead.
> Remember the frame unwind_step() entered the pad in and reject
> bpf_unwind_resume() when curframe doesn't match.
Yes, this is a real issue for backtracking. The problem is stated in
the above curframe doesn't match for frames after unwind_step(), mostly
due to backtracking from landing pad insn to bpf_throw. Will fix.
>
> pw-bot: cr
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH bpf-next 09/20] bpf: Refuse a private stack for a program with an exception cleanup table
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (7 preceding siblings ...)
2026-09-17 5:57 ` [PATCH bpf-next 08/20] bpf: Walk the exception unwind in the verifier Yonghong Song
@ 2026-09-17 5:57 ` Yonghong Song
2026-09-17 5:57 ` [PATCH bpf-next 10/20] bpf: Dispatch exception cleanup pads from bpf_throw() Yonghong Song
` (10 subsequent siblings)
19 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:57 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
A landing pad is about to start running outside its own frame, on the
bpf_throw() walker's stack, with that frame's registers put back from a
spill area whose contents arch_bpf_run_cleanup_pad() knows how to read. The
x86-64 JIT addresses a private-stack program's frame through a scratch
register that it recomputes after each call rather than through rbp, and no
spill area holds that register, so a pad there would address its frame
through whatever the kernel left behind.
Refuse the combination in check_max_stack_depth(), where the choice is
made. Everywhere rather than arch-conditionally: arm64 keeps its private
stack pointer in x27, which is in the prologue spill and so survives, but a
rule that holds on one arch and not the other is not worth the second code
path when nothing is lost but an optimization.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
kernel/bpf/verifier.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a3b34ded1392..43ecf79baa4a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5591,6 +5591,14 @@ static int check_max_stack_depth(struct bpf_verifier_env *env)
}
}
+ /*
+ * A pad rebuilds its frame from a spill area, and on x86-64 a private
+ * stack's frame pointer is in no spill area. Refused on every arch
+ * rather than just that one.
+ */
+ if (env->cleanup_info_cnt)
+ priv_stack_mode = NO_PRIV_STACK;
+
if (priv_stack_mode == PRIV_STACK_UNKNOWN)
priv_stack_mode = bpf_enable_priv_stack(env->prog);
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH bpf-next 10/20] bpf: Dispatch exception cleanup pads from bpf_throw()
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (8 preceding siblings ...)
2026-09-17 5:57 ` [PATCH bpf-next 09/20] bpf: Refuse a private stack for a program with an exception cleanup table Yonghong Song
@ 2026-09-17 5:57 ` Yonghong Song
2026-09-17 5:57 ` [PATCH bpf-next 11/20] bpf, x86: Dispatch exception cleanup pads at run time Yonghong Song
` (9 subsequent siblings)
19 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:57 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
Stop discarding the frames an exception unwinds through. bpf_throw()
already walks the BPF call stack with arch_bpf_stack_walk() to find the
exception boundary; have it look each frame's return address up in that
(sub)program's cleanup table on the way and run the landing pad a matching
record names.
A pad is run as a subroutine of the walker, not jumped to. It executes with
the unwinding frame's frame pointer and BPF callee-saved registers, so
everything it reads is that frame's, but on the current stack far below it,
so nothing it calls can disturb the frame it is cleaning up after. It ends
in what the JIT emits for its bpf_unwind_resume(), which hands control back
to the walker rather than to the frame's caller. That is exactly the
procedure the LLVM commit emitting the section describes.
Restoring the frame's r6-r9 is what makes this work, and it is only
possible because the callee about to be discarded spilled them in its own
prologue. bpf_cleanup_force_spill() tells a JIT to make that spill
unconditional and of a known shape for every subprogram of a program
carrying a cleanup table, and aux->exc->spill_off records where it starts,
so the walker needs no per-frame metadata. The frame that called
bpf_throw() has no callee to have spilled anything and never runs its own
epilogue, so the JIT spills that frame's registers at the throw site
instead, in the area aux->exc->throw_spill_off names.
The main program needs the table handed to it rather than built for it.
jit_subprogs() compiles it as func[0], but the ksym covering that image is
the one bpf_prog_load() registers for the outer bpf_prog, and that is what
the walker finds -- so without the handover a landing pad in the main
program's own frame is never dispatched, silently, since the exception
still reaches the boundary and the cookie still comes back.
All of it hangs off bpf_prog_aux by a single pointer. bpf_prog_aux is on
every BPF program and this is a niche feature, so struct bpf_exception_info
exists only for a program that carries a table, and aux->exc being set is
what says the program carries one at all.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
include/linux/bpf.h | 75 +++++++++++++++++++
include/linux/filter.h | 1 +
kernel/bpf/core.c | 30 +++++++-
kernel/bpf/exception.c | 166 +++++++++++++++++++++++++++++++++++++++++
kernel/bpf/exception.h | 7 ++
kernel/bpf/fixups.c | 125 +++++++++++++++++++++++++++++++
kernel/bpf/helpers.c | 34 +++++++++
7 files changed, 435 insertions(+), 3 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 2a5fa346aada..83f2b0d7e596 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1770,6 +1770,80 @@ enum bpf_sig_keyring {
BPF_SIG_KEYRING_BPF,
};
+/*
+ * One cleanup region of a JITed (sub)program: @pad is the landing pad to run
+ * for a return address in (begin, end], the native code of its call sites.
+ */
+struct bpf_cleanup_range {
+ u64 begin;
+ u64 end;
+ u64 pad;
+};
+
+struct bpf_exception_info {
+ struct bpf_cleanup_info *info;
+ struct bpf_cleanup_range *ranges;
+ /* Landing pad instruction indices, sorted and deduplicated. */
+ u32 *pad_at;
+ /* bpf_throw() call instruction indices, sorted. */
+ u32 *throw_at;
+ /* One bit per instruction that only runs while unwinding. */
+ unsigned long *pad_body;
+ u32 nr_info;
+ u32 nr_ranges;
+ u32 nr_pad_at;
+ u32 nr_throw_at;
+ u32 nr_pad_body;
+ /* Offset from a frame's FP to the caller's spilled r6-r9. */
+ s32 spill_off;
+ /* Likewise, to the registers a frame spills before calling bpf_throw(). */
+ s32 throw_spill_off;
+};
+
+#ifdef CONFIG_BPF_SYSCALL
+bool bpf_cleanup_force_spill(const struct bpf_prog *prog);
+bool bpf_cleanup_insn_is_pad(const struct bpf_prog *prog, u32 idx);
+bool bpf_cleanup_insn_in_pad(const struct bpf_prog *prog, u32 idx);
+bool bpf_cleanup_insn_is_throw(const struct bpf_prog *prog, u32 idx);
+int bpf_cleanup_attach_main_prog(struct bpf_verifier_env *env, struct bpf_prog *prog);
+void bpf_cleanup_fill_native_ranges(struct bpf_prog *prog, u32 *addrs, void *image);
+void bpf_cleanup_free_info(struct bpf_prog_aux *aux);
+#else
+static inline bool bpf_cleanup_force_spill(const struct bpf_prog *prog)
+{
+ return false;
+}
+
+static inline bool bpf_cleanup_insn_is_pad(const struct bpf_prog *prog, u32 idx)
+{
+ return false;
+}
+
+static inline bool bpf_cleanup_insn_in_pad(const struct bpf_prog *prog, u32 idx)
+{
+ return false;
+}
+
+static inline bool bpf_cleanup_insn_is_throw(const struct bpf_prog *prog, u32 idx)
+{
+ return false;
+}
+
+static inline int bpf_cleanup_attach_main_prog(struct bpf_verifier_env *env,
+ struct bpf_prog *prog)
+{
+ return 0;
+}
+
+static inline void bpf_cleanup_fill_native_ranges(struct bpf_prog *prog, u32 *addrs, void *image)
+{
+}
+
+static inline void bpf_cleanup_free_info(struct bpf_prog_aux *aux)
+{
+}
+#endif
+
struct bpf_prog_aux {
atomic64_t refcnt;
u32 used_map_cnt;
@@ -1850,6 +1924,7 @@ struct bpf_prog_aux {
char name[BPF_OBJ_NAME_LEN];
u64 (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp, u64, u64);
u16 stack_arg_sp_adjust;
+ struct bpf_exception_info *exc;
#ifdef CONFIG_SECURITY
void *security;
#endif
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 9682b98ad890..287cd9b59aa9 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1243,6 +1243,7 @@ bool bpf_jit_supports_arena_args(void);
bool bpf_jit_supports_far_kfunc_call(void);
bool bpf_jit_supports_exceptions(void);
bool bpf_jit_supports_cleanup_pads(void);
+void arch_bpf_run_cleanup_pad(u64 pad, u64 frame_fp, u64 spill_base);
bool bpf_jit_supports_ptr_xchg(void);
bool bpf_jit_supports_arena(void);
bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index f0dd851264f4..bd2919063cec 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -292,6 +292,7 @@ void __bpf_prog_free(struct bpf_prog *fp)
mutex_destroy(&fp->aux->dst_mutex);
mutex_destroy(&fp->aux->st_ops_assoc_mutex);
kfree(fp->aux->poke_tab);
+ bpf_cleanup_free_info(fp->aux);
kfree(fp->aux);
}
free_percpu(fp->stats);
@@ -2625,13 +2626,21 @@ static bool bpf_prog_select_interpreter(struct bpf_prog *fp)
return select_interpreter;
}
-static struct bpf_prog *bpf_prog_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog)
+static struct bpf_prog *bpf_prog_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog,
+ int *err)
{
#ifdef CONFIG_BPF_JIT
struct bpf_prog *orig_prog;
+ int ret;
- if (!bpf_prog_need_blind(prog))
+ if (!bpf_prog_need_blind(prog)) {
+ ret = bpf_cleanup_attach_main_prog(env, prog);
+ if (ret) {
+ *err = ret;
+ return prog;
+ }
return bpf_int_jit_compile(env, prog);
+ }
orig_prog = prog;
prog = bpf_jit_blind_constants(env, prog);
@@ -2642,6 +2651,13 @@ static struct bpf_prog *bpf_prog_jit_compile(struct bpf_verifier_env *env, struc
if (IS_ERR(prog))
goto out_restore;
+ ret = bpf_cleanup_attach_main_prog(env, prog);
+ if (ret) {
+ *err = ret;
+ bpf_jit_prog_release_other(orig_prog, prog);
+ goto out_restore;
+ }
+
prog = bpf_int_jit_compile(env, prog);
if (prog->jited) {
bpf_jit_prog_release_other(prog, orig_prog);
@@ -2681,8 +2697,10 @@ struct bpf_prog *__bpf_prog_select_runtime(struct bpf_verifier_env *env, struct
if (*err)
return fp;
- fp = bpf_prog_jit_compile(env, fp);
+ fp = bpf_prog_jit_compile(env, fp, err);
bpf_prog_jit_attempt_done(fp);
+ if (*err)
+ return fp;
if (!fp->jited && jit_needed) {
*err = -ENOTSUPP;
return fp;
@@ -3475,6 +3493,12 @@ bool __weak bpf_jit_supports_cleanup_pads(void)
return false;
}
+/* Call @pad with the frame pointer @frame_fp and r6-r9 spilled at @spill_base. */
+void __weak arch_bpf_run_cleanup_pad(u64 pad, u64 frame_fp, u64 spill_base)
+{
+ WARN_ON_ONCE(1);
+}
+
bool __weak bpf_jit_supports_timed_may_goto(void)
{
return false;
diff --git a/kernel/bpf/exception.c b/kernel/bpf/exception.c
index b2bf831242b8..521086d084a3 100644
--- a/kernel/bpf/exception.c
+++ b/kernel/bpf/exception.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <linux/bitmap.h>
#include <linux/bpf.h>
#include <linux/bpf_verifier.h>
#include <linux/btf.h>
@@ -486,3 +487,168 @@ int bpf_cleanup_pad_of_call(struct bpf_verifier_env *env, u32 idx)
return pad ? (int)pad - 1 : -1;
}
+
+/*
+ * Every subprogram of a cleanup-carrying program spills the BPF callee-saved
+ * registers, even one that never throws: a frame's spill holds its caller's
+ * registers, and that is what the walker restores before running the caller's
+ * pad. The exception callback does not, because it reuses the boundary frame
+ * rather than building one of its own.
+ */
+bool bpf_cleanup_force_spill(const struct bpf_prog *prog)
+{
+ return prog->aux->exc && !prog->aux->exception_cb;
+}
+
+const struct bpf_cleanup_range *bpf_cleanup_pad_for_ip(const struct bpf_prog *prog, u64 ip)
+{
+ const struct bpf_exception_info *exc = prog->aux->exc;
+ u32 l = 0, r = exc ? exc->nr_ranges : 0;
+
+ while (l < r) {
+ u32 m = l + (r - l) / 2;
+ const struct bpf_cleanup_range *rec = &exc->ranges[m];
+
+ if (ip <= rec->begin)
+ r = m;
+ else if (ip > rec->end)
+ l = m + 1;
+ else
+ return rec;
+ }
+ return NULL;
+}
+
+static int cmp_u32(const void *a, const void *b)
+{
+ u32 x = *(const u32 *)a, y = *(const u32 *)b;
+
+ return x < y ? -1 : x > y;
+}
+
+int bpf_cleanup_alloc_info(struct bpf_prog_aux *aux)
+{
+ if (aux->exc)
+ return 0;
+ aux->exc = kzalloc_obj(struct bpf_exception_info, GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
+ return aux->exc ? 0 : -ENOMEM;
+}
+
+int bpf_cleanup_attach_info(struct bpf_prog_aux *aux, struct bpf_cleanup_info *recs, u32 cnt)
+{
+ struct bpf_exception_info *exc = aux->exc;
+ struct bpf_cleanup_range *ranges;
+ u32 i, n_at, *at;
+
+ if (!cnt) {
+ kvfree(recs);
+ return 0;
+ }
+
+ ranges = kvcalloc(cnt, sizeof(*ranges), GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
+ if (!ranges) {
+ kvfree(recs);
+ return -ENOMEM;
+ }
+
+ /* The pads on their own, sorted and deduplicated. */
+ at = kvmalloc_array(cnt, sizeof(*at), GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
+ if (!at) {
+ kvfree(ranges);
+ kvfree(recs);
+ return -ENOMEM;
+ }
+ for (i = 0; i < cnt; i++)
+ at[i] = recs[i].landing_pad_off;
+ sort(at, cnt, sizeof(*at), cmp_u32, NULL);
+ for (i = 0, n_at = 0; i < cnt; i++)
+ if (!n_at || at[n_at - 1] != at[i])
+ at[n_at++] = at[i];
+
+ exc->pad_at = at;
+ exc->nr_pad_at = n_at;
+ exc->info = recs;
+ exc->nr_info = cnt;
+ exc->ranges = ranges;
+ /* Withheld until the JIT has filled the table in. */
+ exc->nr_ranges = 0;
+ return 0;
+}
+
+void bpf_cleanup_fill_native_ranges(struct bpf_prog *prog, u32 *addrs, void *image)
+{
+ struct bpf_exception_info *exc = prog->aux->exc;
+ u32 i, n;
+
+ if (!exc || !exc->nr_info || !exc->ranges)
+ return;
+
+ n = exc->nr_info;
+ for (i = 0; i < n; i++) {
+ const struct bpf_cleanup_info *rec = &exc->info[i];
+
+ if (WARN_ON_ONCE(rec->begin_off >= prog->len ||
+ rec->end_off > prog->len ||
+ rec->landing_pad_off >= prog->len))
+ return;
+ exc->ranges[i].begin = (u64)(long)image + addrs[rec->begin_off];
+ exc->ranges[i].end = (u64)(long)image + addrs[rec->end_off];
+ exc->ranges[i].pad = (u64)(long)image + addrs[rec->landing_pad_off];
+ }
+ exc->nr_ranges = n;
+}
+
+void bpf_cleanup_free_info(struct bpf_prog_aux *aux)
+{
+ struct bpf_exception_info *exc = aux->exc;
+
+ if (!exc)
+ return;
+ kvfree(exc->ranges);
+ kvfree(exc->info);
+ kvfree(exc->pad_at);
+ kvfree(exc->throw_at);
+ bitmap_free(exc->pad_body);
+ kfree(exc);
+ aux->exc = NULL;
+}
+
+/* Is @idx in the sorted array @at of @n instruction indices? */
+static bool insn_idx_in(const u32 *at, u32 n, u32 idx)
+{
+ u32 l = 0, r = n;
+
+ while (l < r) {
+ u32 m = l + (r - l) / 2;
+
+ if (idx < at[m])
+ r = m;
+ else if (idx > at[m])
+ l = m + 1;
+ else
+ return true;
+ }
+ return false;
+}
+
+bool bpf_cleanup_insn_is_pad(const struct bpf_prog *prog, u32 idx)
+{
+ const struct bpf_exception_info *exc = prog->aux->exc;
+
+ return exc && insn_idx_in(exc->pad_at, exc->nr_pad_at, idx);
+}
+
+bool bpf_cleanup_insn_is_throw(const struct bpf_prog *prog, u32 idx)
+{
+ const struct bpf_exception_info *exc = prog->aux->exc;
+
+ return exc && insn_idx_in(exc->throw_at, exc->nr_throw_at, idx);
+}
+
+bool bpf_cleanup_insn_in_pad(const struct bpf_prog *prog, u32 idx)
+{
+ const struct bpf_exception_info *exc = prog->aux->exc;
+
+ return exc && exc->pad_body && idx < exc->nr_pad_body &&
+ test_bit(idx, exc->pad_body);
+}
diff --git a/kernel/bpf/exception.h b/kernel/bpf/exception.h
index 7313dd2b65a1..c0e68ce227c8 100644
--- a/kernel/bpf/exception.h
+++ b/kernel/bpf/exception.h
@@ -5,11 +5,18 @@
#include <linux/types.h>
+struct bpf_cleanup_info;
+struct bpf_cleanup_range;
+struct bpf_prog;
+struct bpf_prog_aux;
struct bpf_verifier_env;
int bpf_prepare_cleanup_exceptions(struct bpf_verifier_env *env);
int bpf_check_cleanup_exceptions(struct bpf_verifier_env *env);
int bpf_cleanup_check_callback(struct bpf_verifier_env *env, int subprog);
int bpf_cleanup_pad_of_call(struct bpf_verifier_env *env, u32 idx);
+int bpf_cleanup_alloc_info(struct bpf_prog_aux *aux);
+int bpf_cleanup_attach_info(struct bpf_prog_aux *aux, struct bpf_cleanup_info *recs, u32 cnt);
+const struct bpf_cleanup_range *bpf_cleanup_pad_for_ip(const struct bpf_prog *prog, u64 ip);
#endif /* _LINUX_BPF_EXCEPTION_H */
diff --git a/kernel/bpf/fixups.c b/kernel/bpf/fixups.c
index f120ae66dbbc..134aafa6a6c9 100644
--- a/kernel/bpf/fixups.c
+++ b/kernel/bpf/fixups.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <linux/bitmap.h>
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/bpf_verifier.h>
@@ -10,6 +11,7 @@
#include <linux/perf_event.h>
#include <net/xdp.h>
#include "disasm.h"
+#include "exception.h"
#define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args)
@@ -257,6 +259,11 @@ 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_throw_site =
+ data[off + cnt - 1].cleanup_throw_site;
+ data[off + cnt - 1].cleanup_throw_site = 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;
}
@@ -1113,6 +1120,116 @@ static void bpf_restore_subprog_starts(struct bpf_verifier_env *env, u32 *orig_s
env->subprog_info[env->subprog_cnt].start = env->prog->len;
}
+static int cleanup_throw_sites_for_subprog(struct bpf_verifier_env *env, struct bpf_prog *sub,
+ u32 start, u32 end)
+{
+ u32 i, cnt = 0, *at;
+
+ for (i = start; i < end; i++)
+ if (env->insn_aux_data[i].cleanup_throw_site)
+ cnt++;
+ if (!cnt)
+ return 0;
+
+ at = kvmalloc_array(cnt, sizeof(*at), GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
+ if (!at)
+ return -ENOMEM;
+
+ for (i = start, cnt = 0; i < end; i++) {
+ if (!env->insn_aux_data[i].cleanup_throw_site)
+ continue;
+ at[cnt++] = i - start;
+ }
+
+ sub->aux->exc->throw_at = at;
+ sub->aux->exc->nr_throw_at = cnt;
+ return 0;
+}
+
+static int cleanup_pad_body_for_subprog(struct bpf_verifier_env *env, struct bpf_prog *sub,
+ u32 start, u32 end)
+{
+ unsigned long *bits;
+ u32 i, cnt = 0;
+
+ for (i = start; i < end; i++)
+ if (env->insn_aux_data[i].in_cleanup_pad)
+ cnt++;
+ if (!cnt)
+ return 0;
+
+ bits = bitmap_zalloc(end - start, GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
+ if (!bits)
+ return -ENOMEM;
+
+ for (i = start; i < end; i++)
+ if (env->insn_aux_data[i].in_cleanup_pad)
+ __set_bit(i - start, bits);
+
+ sub->aux->exc->pad_body = bits;
+ sub->aux->exc->nr_pad_body = end - start;
+ return 0;
+}
+
+static int cleanup_info_for_subprog(struct bpf_verifier_env *env, struct bpf_prog *sub,
+ u32 start, u32 end)
+{
+ struct bpf_cleanup_info *recs;
+ u32 i, cnt = 0;
+ int err;
+
+ if (!env->cleanup_info_cnt)
+ return 0;
+
+ err = bpf_cleanup_alloc_info(sub->aux);
+ if (err)
+ return err;
+
+ err = cleanup_throw_sites_for_subprog(env, sub, start, end);
+ if (err)
+ return err;
+
+ err = cleanup_pad_body_for_subprog(env, sub, start, end);
+ if (err)
+ return err;
+
+ for (i = start; i < end; i++)
+ if (env->insn_aux_data[i].cleanup_pad)
+ cnt++;
+ if (!cnt)
+ return 0;
+
+ recs = kvmalloc_array(cnt, sizeof(*recs), GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
+ if (!recs)
+ return -ENOMEM;
+
+ for (i = start, cnt = 0; i < end; i++) {
+ u32 pad = env->insn_aux_data[i].cleanup_pad;
+
+ if (!pad)
+ continue;
+ pad--;
+ if (verifier_bug_if(pad < start || pad >= end, env,
+ "insn %u is covered by a landing pad at %u outside its subprog [%u, %u)",
+ i, pad, start, end)) {
+ kvfree(recs);
+ return -EFAULT;
+ }
+ recs[cnt].begin_off = i - start;
+ recs[cnt].end_off = i - start + 1;
+ recs[cnt].landing_pad_off = pad - start;
+ cnt++;
+ }
+ return bpf_cleanup_attach_info(sub->aux, recs, cnt);
+}
+
+int bpf_cleanup_attach_main_prog(struct bpf_verifier_env *env, struct bpf_prog *prog)
+{
+ if (!env || env->subprog_cnt > 1)
+ return 0;
+ return cleanup_info_for_subprog(env, prog, 0, prog->len);
+}
+
static int jit_subprogs(struct bpf_verifier_env *env)
{
struct bpf_prog *prog = env->prog, **func, *tmp;
@@ -1250,6 +1367,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
func[i]->aux->token = prog->aux->token;
if (!i)
func[i]->aux->exception_boundary = env->seen_exception;
+ err = cleanup_info_for_subprog(env, func[i], subprog_start,
+ env->subprog_info[i + 1].start);
+ if (err)
+ goto out_free;
func[i] = bpf_int_jit_compile(env, func[i]);
if (!func[i]->jited) {
err = -ENOTSUPP;
@@ -1354,6 +1475,8 @@ static int jit_subprogs(struct bpf_verifier_env *env)
prog->aux->bpf_exception_cb = (void *)func[env->exception_callback_subprog]->bpf_func;
prog->aux->exception_boundary = func[0]->aux->exception_boundary;
prog->aux->stack_arg_sp_adjust = func[0]->aux->stack_arg_sp_adjust;
+ prog->aux->exc = func[0]->aux->exc;
+ func[0]->aux->exc = NULL;
bpf_prog_jit_attempt_done(prog);
return 0;
out_free:
@@ -1934,6 +2057,8 @@ int bpf_do_misc_fixups(struct bpf_verifier_env *env)
goto next_insn;
if (insn->src_reg == BPF_PSEUDO_CALL)
goto next_insn;
+ if (bpf_is_unwind_resume_kfunc(insn))
+ goto next_insn;
if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
ret = bpf_fixup_kfunc_call(env, insn, insn_buf, i + delta, &cnt);
if (ret)
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 31d84de4d318..ffef72804fc9 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -31,6 +31,7 @@
#include <linux/buildid.h>
#include "../../lib/kstrtox.h"
+#include "exception.h"
/* If kernel subsystem is allowing eBPF programs to call this function,
* inside its own verifier_ops->get_func_proto() callback it should return
@@ -3360,8 +3361,36 @@ struct bpf_throw_ctx {
u64 sp;
u64 bp;
int cnt;
+ const struct bpf_prog *callee;
+ u64 callee_fp;
};
+static void bpf_run_cleanup_pad(struct bpf_throw_ctx *ctx, const struct bpf_prog *prog,
+ u64 ip, u64 fp)
+{
+ const struct bpf_exception_info *exc = prog->aux->exc;
+ const struct bpf_cleanup_range *rec;
+ u64 spill_base;
+
+ if (!exc || !exc->nr_ranges)
+ return;
+ rec = bpf_cleanup_pad_for_ip(prog, ip);
+ if (!rec)
+ return;
+
+ /*
+ * The callee is always another subprogram of this program -- the walk
+ * ends at any frame that is not one -- so its prologue spilled these
+ * registers and its exc is there to say where.
+ */
+ if (ctx->callee)
+ spill_base = ctx->callee_fp + ctx->callee->aux->exc->spill_off;
+ else
+ spill_base = fp + exc->throw_spill_off;
+
+ arch_bpf_run_cleanup_pad(rec->pad, fp, spill_base);
+}
+
static bool bpf_stack_walker(void *cookie, u64 ip, u64 sp, u64 bp)
{
struct bpf_throw_ctx *ctx = cookie;
@@ -3378,6 +3407,11 @@ static bool bpf_stack_walker(void *cookie, u64 ip, u64 sp, u64 bp)
if (!prog)
return !ctx->cnt;
ctx->cnt++;
+
+ bpf_run_cleanup_pad(ctx, prog, ip, bp);
+ ctx->callee = prog;
+ ctx->callee_fp = bp;
+
if (bpf_is_subprog(prog))
return true;
ctx->aux = prog->aux;
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH bpf-next 11/20] bpf, x86: Dispatch exception cleanup pads at run time
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (9 preceding siblings ...)
2026-09-17 5:57 ` [PATCH bpf-next 10/20] bpf: Dispatch exception cleanup pads from bpf_throw() Yonghong Song
@ 2026-09-17 5:57 ` Yonghong Song
2026-09-19 5:02 ` Alexei Starovoitov
2026-09-17 5:57 ` [PATCH bpf-next 12/20] bpf, arm64: " Yonghong Song
` (8 subsequent siblings)
19 siblings, 1 reply; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:57 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
Provide the arch half for x86-64: force the full callee-saved spill for a
program carrying a cleanup table so the walker can find a frame's r6-r9 in
its callee's prologue, record where that spill area starts, build the
native cleanup table from the JIT's addrs[], emit a bare return for a pad's
bpf_unwind_resume(), and hand control to a pad from
arch_bpf_run_cleanup_pad().
Support is gated on CONFIG_UNWINDER_ORC, the same requirement
arch_bpf_stack_walk() and therefore bpf_throw() already have here.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
arch/x86/net/Makefile | 2 +-
arch/x86/net/bpf_cleanup_pad.S | 74 ++++++++++++++++++++++++++++++++
arch/x86/net/bpf_jit_comp.c | 78 ++++++++++++++++++++++++++++------
3 files changed, 141 insertions(+), 13 deletions(-)
create mode 100644 arch/x86/net/bpf_cleanup_pad.S
diff --git a/arch/x86/net/Makefile b/arch/x86/net/Makefile
index dddbefc0f439..9d574d972df3 100644
--- a/arch/x86/net/Makefile
+++ b/arch/x86/net/Makefile
@@ -6,5 +6,5 @@
ifeq ($(CONFIG_X86_32),y)
obj-$(CONFIG_BPF_JIT) += bpf_jit_comp32.o
else
- obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o bpf_timed_may_goto.o
+ obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o bpf_timed_may_goto.o bpf_cleanup_pad.o
endif
diff --git a/arch/x86/net/bpf_cleanup_pad.S b/arch/x86/net/bpf_cleanup_pad.S
new file mode 100644
index 000000000000..da4b448ecf09
--- /dev/null
+++ b/arch/x86/net/bpf_cleanup_pad.S
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+
+#include <linux/bpf_cleanup_abi.h>
+#include <linux/linkage.h>
+#include <asm/nospec-branch.h>
+
+/*
+ * The x86-64 BPF JIT prologue spills, once bpf_cleanup_force_spill() makes it
+ * unconditional, r12, rbx, r13, r14 and r15 in that order -- so within the
+ * spill area the lowest address holds r15 and the highest r12. The throw-site
+ * spill the JIT emits uses the same layout, so the routine below reads both
+ * the same way:
+ *
+ * spill_base + 0 BPF r9 (r15)
+ * spill_base + 8 BPF r8 (r14)
+ * spill_base + 16 BPF r7 (r13)
+ * spill_base + 24 BPF r6 (rbx)
+ * spill_base + 32 r12 (arena base, not a BPF register)
+ */
+
+ .code64
+ .section .text, "ax"
+
+/*
+ * void arch_bpf_run_cleanup_pad(u64 pad, u64 frame_fp, u64 spill_base)
+ *
+ * rdi = native address of the landing pad
+ * rsi = frame pointer of the frame the pad belongs to
+ * rdx = spill area holding that frame's BPF callee-saved registers
+ *
+ * Give the pad the register state of its own frame and call it. The pad ends
+ * in the bare return the JIT emits for its bpf_unwind_resume(), so it comes
+ * back here rather than returning to its frame's caller. It runs on this
+ * stack, far below the frame it is cleaning up after, so nothing it calls can
+ * reach into that frame.
+ */
+SYM_FUNC_START(arch_bpf_run_cleanup_pad)
+ ANNOTATE_NOENDBR
+
+ pushq %rbp
+ pushq %rbx
+ pushq %r12
+ pushq %r13
+ pushq %r14
+ pushq %r15
+ /* Keep the pad's entry rsp congruent to a normal call's. */
+ subq $8, %rsp
+
+ movq 0(%rdx), %r15
+ movq 8(%rdx), %r14
+ movq 16(%rdx), %r13
+ movq 24(%rdx), %rbx
+ movq 32(%rdx), %r12
+ /* rbp is BPF r10, so this is the whole of the pad's frame setup. */
+ movq %rsi, %rbp
+
+ /* CALL_NOSPEC needs the target in a register; rcx is BPF r4, dead. */
+ movq %rdi, %rcx
+
+ /* BPF r0 on the way into a pad, not whatever the kernel left in rax. */
+ movl $BPF_PAD_ENTRY_R0, %eax
+
+ CALL_NOSPEC rcx
+
+ addq $8, %rsp
+ popq %r15
+ popq %r14
+ popq %r13
+ popq %r12
+ popq %rbx
+ popq %rbp
+ RET
+SYM_FUNC_END(arch_bpf_run_cleanup_pad)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index d4a980140b48..9d0dd54773e8 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -357,6 +357,11 @@ struct jit_context {
/* Number of bytes that will be skipped on tailcall */
#define X86_TAIL_CALL_OFFSET (12 + ENDBR_INSN_SIZE)
+/* Throw-site spill: r15, r14, r13, rbx, r12 low to high, the layout the
+ * prologue's pushes leave, so arch_bpf_run_cleanup_pad() reads both alike.
+ */
+#define X86_CLEANUP_SPILL_SZ (5 * 8)
+
static void push_r9(u8 **pprog)
{
u8 *prog = *pprog;
@@ -832,7 +837,7 @@ static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog,
/* Inc tail_call_cnt if the slot is populated. */
EMIT4(0x48, 0x83, 0x00, 0x01); /* add qword ptr [rax], 1 */
- if (bpf_prog->aux->exception_boundary) {
+ if (bpf_prog->aux->exception_boundary || bpf_cleanup_force_spill(bpf_prog)) {
pop_callee_regs(&prog, all_callee_regs_used);
pop_r12(&prog);
} else {
@@ -899,7 +904,7 @@ static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog,
/* Inc tail_call_cnt if the slot is populated. */
EMIT4(0x48, 0x83, 0x00, 0x01); /* add qword ptr [rax], 1 */
- if (bpf_prog->aux->exception_boundary) {
+ if (bpf_prog->aux->exception_boundary || bpf_cleanup_force_spill(bpf_prog)) {
pop_callee_regs(&prog, all_callee_regs_used);
pop_r12(&prog);
} else {
@@ -1977,6 +1982,7 @@ static int do_jit(struct bpf_verifier_env *env, struct bpf_prog *bpf_prog, int *
u8 *ip, *prog = temp;
u32 stack_depth;
int callee_saved_size;
+ u32 throw_spill, prologue_depth;
s32 outgoing_arg_base;
int err;
@@ -2015,7 +2021,10 @@ static int do_jit(struct bpf_verifier_env *env, struct bpf_prog *bpf_prog, int *
detect_reg_usage(insn, insn_cnt, callee_regs_used);
- emit_prologue(&prog, image, stack_depth,
+ throw_spill = bpf_cleanup_force_spill(bpf_prog) ? X86_CLEANUP_SPILL_SZ : 0;
+ prologue_depth = stack_depth + throw_spill;
+
+ emit_prologue(&prog, image, prologue_depth,
bpf_prog_was_classic(bpf_prog), tail_call_reachable,
bpf_is_subprog(bpf_prog), bpf_prog->aux->exception_cb);
@@ -2024,7 +2033,7 @@ static int do_jit(struct bpf_verifier_env *env, struct bpf_prog *bpf_prog, int *
/* 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) {
+ if (bpf_prog->aux->exception_boundary || bpf_cleanup_force_spill(bpf_prog)) {
/* 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.
@@ -2039,9 +2048,10 @@ static int do_jit(struct bpf_verifier_env *env, struct bpf_prog *bpf_prog, int *
/* Compute callee-saved register area size. */
callee_saved_size = 0;
- if (bpf_prog->aux->exception_boundary || arena_vm_start)
+ if (bpf_prog->aux->exception_boundary || bpf_cleanup_force_spill(bpf_prog) ||
+ arena_vm_start)
callee_saved_size += 8; /* r12 */
- if (bpf_prog->aux->exception_boundary) {
+ if (bpf_prog->aux->exception_boundary || bpf_cleanup_force_spill(bpf_prog)) {
callee_saved_size += 4 * 8; /* rbx, r13, r14, r15 */
} else {
int j;
@@ -2063,7 +2073,19 @@ static int do_jit(struct bpf_verifier_env *env, struct bpf_prog *bpf_prog, int *
* Note that tail_call_reachable is guaranteed to be false when
* stack args exist, so tcc pushes need not be accounted for.
*/
- outgoing_arg_base = -(round_up(stack_depth, 8) + callee_saved_size);
+ outgoing_arg_base = -(round_up(stack_depth, 8) + throw_spill + callee_saved_size);
+
+ /*
+ * Lowest address of each spill area, as an offset from rbp; see
+ * bpf_cleanup_pad.S for the layout. The 16 is the tail call counter
+ * pair emit_prologue_tail_call() pushes above the callee-saved one.
+ */
+ if (bpf_cleanup_force_spill(bpf_prog)) {
+ bpf_prog->aux->exc->spill_off = -(round_up(stack_depth, 8) + throw_spill +
+ (tail_call_reachable ? 16 : 0) +
+ callee_saved_size);
+ bpf_prog->aux->exc->throw_spill_off = -(round_up(stack_depth, 8) + throw_spill);
+ }
/*
* Allocate outgoing stack arg area for args 7+ only.
@@ -2110,7 +2132,8 @@ static int do_jit(struct bpf_verifier_env *env, struct bpf_prog *bpf_prog, int *
dst_reg = X86_REG_R9;
}
- if (bpf_insn_is_indirect_target(env, bpf_prog, i - 1))
+ if (bpf_insn_is_indirect_target(env, bpf_prog, i - 1) ||
+ bpf_cleanup_insn_is_pad(bpf_prog, i - 1))
EMIT_ENDBR();
ip = image + addrs[i - 1] + (prog - temp);
@@ -2903,9 +2926,27 @@ static int do_jit(struct bpf_verifier_env *env, struct bpf_prog *bpf_prog, int *
case BPF_JMP | BPF_CALL: {
const struct btf_func_model *fm = NULL;
+ if (bpf_cleanup_insn_is_throw(bpf_prog, i - 1)) {
+ /* Spill r6-r9 and r12 where the bpf_throw() walker looks. */
+ s32 off = bpf_prog->aux->exc->throw_spill_off;
+ u8 *spill = prog;
+
+ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_9, off + 0);
+ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_8, off + 8);
+ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_7, off + 16);
+ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_6, off + 24);
+ emit_stx(&prog, BPF_DW, BPF_REG_FP, X86_REG_R12, off + 32);
+ ip += prog - spill;
+ }
+
+ if (bpf_is_unwind_resume_kfunc(insn)) {
+ emit_return(&prog, image + addrs[i - 1] + (prog - temp));
+ break;
+ }
+
func = (u8 *) __bpf_call_base + imm32;
if (src_reg == BPF_PSEUDO_CALL && tail_call_reachable) {
- LOAD_TAIL_CALL_CNT_PTR(stack_depth);
+ LOAD_TAIL_CALL_CNT_PTR(prologue_depth);
ip += 7;
}
if (!imm32)
@@ -2948,13 +2989,13 @@ static int do_jit(struct bpf_verifier_env *env, struct bpf_prog *bpf_prog, int *
&prog,
ip,
callee_regs_used,
- stack_depth,
+ prologue_depth,
ctx);
else
emit_bpf_tail_call_indirect(bpf_prog,
&prog,
callee_regs_used,
- stack_depth,
+ prologue_depth,
ip,
ctx);
break;
@@ -3215,7 +3256,8 @@ static int do_jit(struct bpf_verifier_env *env, struct bpf_prog *bpf_prog, int *
}
/* Deallocate outgoing args 7+ area. */
emit_add_rsp(&prog, outgoing_rsp);
- if (bpf_prog->aux->exception_boundary) {
+ if (bpf_prog->aux->exception_boundary ||
+ bpf_cleanup_force_spill(bpf_prog)) {
pop_callee_regs(&prog, all_callee_regs_used);
pop_r12(&prog);
} else {
@@ -4385,6 +4427,13 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
*/
bpf_prog_update_insn_ptrs(prog, addrs, image);
+ /*
+ * Same mapping, consumed by the bpf_throw() frame walker:
+ * turn the cleanup records into native address ranges now
+ * that the image is final.
+ */
+ bpf_cleanup_fill_native_ranges(prog, addrs, image);
+
/*
* ctx.prog_offset is used when CFI preambles put code *before*
* the function. See emit_cfi(). For FineIBT specifically this code
@@ -4501,6 +4550,11 @@ bool bpf_jit_supports_exceptions(void)
return IS_ENABLED(CONFIG_UNWINDER_ORC);
}
+bool bpf_jit_supports_cleanup_pads(void)
+{
+ return IS_ENABLED(CONFIG_UNWINDER_ORC);
+}
+
bool bpf_jit_supports_private_stack(void)
{
return true;
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 11/20] bpf, x86: Dispatch exception cleanup pads at run time
2026-09-17 5:57 ` [PATCH bpf-next 11/20] bpf, x86: Dispatch exception cleanup pads at run time Yonghong Song
@ 2026-09-19 5:02 ` Alexei Starovoitov
2026-09-19 19:13 ` Yonghong Song
0 siblings, 1 reply; 40+ messages in thread
From: Alexei Starovoitov @ 2026-09-19 5:02 UTC (permalink / raw)
To: Yonghong Song, bpf
Cc: Andrii Nakryiko, Daniel Borkmann, Eduard Zingerman, kernel-team
On Wed, Sep 16, 2026 at 10:57 PM Yonghong Song <yonghong.song@linux.dev> wrote:
> diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
> index d4a980140b48..9d0dd54773e8 100644
> --- a/arch/x86/net/bpf_jit_comp.c
> +++ b/arch/x86/net/bpf_jit_comp.c
[...]
> + if (bpf_is_unwind_resume_kfunc(insn)) {
> + emit_return(&prog, image + addrs[i - 1] + (prog - temp));
> + break;
> + }
> +
> func = (u8 *) __bpf_call_base + imm32;
bpf_is_unwind_resume_kfunc() matches imm == btf_id && off == 0, but by
now bpf_fixup_kfunc_call() has rewritten every other kfunc's imm to an
offset from __bpf_call_base. A vmlinux kfunc that happens to sit
btf_id bytes after __bpf_call_base gets JITed as a bare ret in the
middle of a normal prog. Looks incorrect.
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 11/20] bpf, x86: Dispatch exception cleanup pads at run time
2026-09-19 5:02 ` Alexei Starovoitov
@ 2026-09-19 19:13 ` Yonghong Song
0 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-19 19:13 UTC (permalink / raw)
To: Alexei Starovoitov, bpf
Cc: Andrii Nakryiko, Daniel Borkmann, Eduard Zingerman, kernel-team
On 9/18/26 10:02 PM, Alexei Starovoitov wrote:
> On Wed, Sep 16, 2026 at 10:57 PM Yonghong Song <yonghong.song@linux.dev> wrote:
>> diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
>> index d4a980140b48..9d0dd54773e8 100644
>> --- a/arch/x86/net/bpf_jit_comp.c
>> +++ b/arch/x86/net/bpf_jit_comp.c
> [...]
>
>> + if (bpf_is_unwind_resume_kfunc(insn)) {
>> + emit_return(&prog, image + addrs[i - 1] + (prog - temp));
>> + break;
>> + }
>> +
>> func = (u8 *) __bpf_call_base + imm32;
> bpf_is_unwind_resume_kfunc() matches imm == btf_id && off == 0, but by
> now bpf_fixup_kfunc_call() has rewritten every other kfunc's imm to an
> offset from __bpf_call_base. A vmlinux kfunc that happens to sit
> btf_id bytes after __bpf_call_base gets JITed as a bare ret in the
> middle of a normal prog. Looks incorrect.
Right, bpf_is_unwind_resume_kfunc() is not correct as it compares
'imm == bpf_id' while imm has been rewritten.
Will fix.
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH bpf-next 12/20] bpf, arm64: Dispatch exception cleanup pads at run time
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (10 preceding siblings ...)
2026-09-17 5:57 ` [PATCH bpf-next 11/20] bpf, x86: Dispatch exception cleanup pads at run time Yonghong Song
@ 2026-09-17 5:57 ` Yonghong Song
2026-09-17 5:57 ` [PATCH bpf-next 13/20] libbpf: Resolve the compiler's _Unwind_Resume to the kernel's kfunc Yonghong Song
` (7 subsequent siblings)
19 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:57 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
The same arch half for arm64: force the full callee-saved spill, record
where it starts, build the native table from the JIT's byte offsets, and
hand control to a pad from arch_bpf_run_cleanup_pad().
Unlike x86-64 a pad cannot simply return: every call it makes clobbers x30,
so no return address survives to its resume. x23 carries it instead.
bpf2a64[] maps nothing to x23 or x24 -- they are pushed only to keep the
frame shape the exception callback expects -- so nothing else in generated
code touches them, and being callee-saved they survive every kfunc the pad
calls. The JIT emits "br x23" for a pad's bpf_unwind_resume().
x24 is the other one, and it is what makes a pad able to touch its own
frame at all. Generated code addresses the BPF frame through the stack
pointer -- the frame sits directly on top of it, which turns every offset
positive and each access into one instruction -- and in a pad the stack
pointer is the walker's. So the JIT has a pad recompute the equivalent of
its frame's stack pointer from BPF r10 on entry, into x24, and addresses
the frame off x24 for every instruction the previous patches marked as
running only while unwinding. One instruction per pad, and the accesses
keep the shape and the immediate range they have everywhere else.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
arch/arm64/net/Makefile | 2 +-
arch/arm64/net/bpf_cleanup_pad.S | 95 +++++++++++++++++++++++++++++++
arch/arm64/net/bpf_jit_comp.c | 97 ++++++++++++++++++++++++++++++--
3 files changed, 187 insertions(+), 7 deletions(-)
create mode 100644 arch/arm64/net/bpf_cleanup_pad.S
diff --git a/arch/arm64/net/Makefile b/arch/arm64/net/Makefile
index 3ae382bfca87..ebec2a44a52b 100644
--- a/arch/arm64/net/Makefile
+++ b/arch/arm64/net/Makefile
@@ -2,4 +2,4 @@
#
# ARM64 networking code
#
-obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o bpf_timed_may_goto.o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o bpf_timed_may_goto.o bpf_cleanup_pad.o
diff --git a/arch/arm64/net/bpf_cleanup_pad.S b/arch/arm64/net/bpf_cleanup_pad.S
new file mode 100644
index 000000000000..ef441241949e
--- /dev/null
+++ b/arch/arm64/net/bpf_cleanup_pad.S
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+
+#include <linux/bpf_cleanup_abi.h>
+#include <linux/linkage.h>
+
+/*
+ * A frame's prologue pushes the tail call counter pair, and then -- once
+ * bpf_cleanup_force_spill() says so -- x19/x20, x21/x22, x23/x24, x25/x26 and
+ * x27/x28. Each A64_PUSH pre-decrements, so the lowest address of the spill
+ * area holds x27 and the highest x20:
+ *
+ * spill_base + 0 x27 (private stack pointer)
+ * spill_base + 8 x28 (arena base)
+ * spill_base + 16 x25 (BPF r10, the frame pointer)
+ * spill_base + 24 x26 (tail call counter pointer)
+ * spill_base + 32 x23 -- the pad's own, see below
+ * spill_base + 40 x24 -- likewise
+ * spill_base + 48 x21 (BPF r8)
+ * spill_base + 56 x22 (BPF r9)
+ * spill_base + 64 x19 (BPF r6)
+ * spill_base + 72 x20 (BPF r7)
+ *
+ * Neither x23 nor x24 is restored from that spill: the pad has its own use for
+ * both. bpf2a64[] maps nothing to either -- they are pushed only to keep the
+ * frame shape the exception callback expects -- so nothing else in generated
+ * code touches them, and being callee-saved they survive every call the pad
+ * makes.
+ *
+ * x23 is the pad's return address. Unlike x86-64 a pad cannot simply return:
+ * every call it makes clobbers x30, so nothing is left to return through by
+ * the time it reaches its resume. The JIT emits "br x23" for the pad's
+ * bpf_unwind_resume() and this routine puts .Lcleanup_pad_done there.
+ *
+ * x24 is where the pad's frame is anchored. Generated code addresses the BPF
+ * frame through the stack pointer, which here is this routine's rather than
+ * the unwinding frame's, so the JIT has the pad recompute the equivalent from
+ * BPF r10 on entry and address its frame off x24 for as long as it runs.
+ *
+ * Both of those branches are indirect, so both targets carry a BTI landing
+ * marker: the JIT emits one at each pad, and .Lcleanup_pad_done below has one
+ * of its own.
+ */
+
+ .text
+
+/*
+ * void arch_bpf_run_cleanup_pad(u64 pad, u64 frame_fp, u64 spill_base)
+ *
+ * x0 = native address of the landing pad
+ * x1 = frame pointer of the frame the pad belongs to (unused here: BPF r10 is
+ * x25, which the spill area already holds)
+ * x2 = spill area holding that frame's BPF callee-saved registers
+ *
+ * Give the pad the register state of its own frame and call it. It runs on
+ * this stack, far below the frame it is cleaning up after, so nothing it
+ * calls can reach into that frame.
+ */
+SYM_FUNC_START(arch_bpf_run_cleanup_pad)
+ /* Save the kernel's callee-saved registers; the pad owns them next. */
+ stp x29, x30, [sp, #-96]!
+ mov x29, sp
+ stp x19, x20, [sp, #16]
+ stp x21, x22, [sp, #32]
+ stp x23, x24, [sp, #48]
+ stp x25, x26, [sp, #64]
+ stp x27, x28, [sp, #80]
+
+ /* x9 is BPF_REG_AX, so the pad's address does not stay in BPF r1. */
+ mov x9, x0
+
+ ldp x27, x28, [x2, #0]
+ ldp x25, x26, [x2, #16]
+ ldp x21, x22, [x2, #48]
+ ldp x19, x20, [x2, #64]
+
+ /* BPF r0 (x8) on the way into a pad, not whatever the kernel left. */
+ mov x8, #BPF_PAD_ENTRY_R0
+
+ /* Where the pad's resume branches back to. */
+ adr x23, .Lcleanup_pad_done
+
+ br x9
+
+.Lcleanup_pad_done:
+ /* Reached by the pad's "br x23", so it is an indirect branch target. */
+ bti j
+ ldp x19, x20, [sp, #16]
+ ldp x21, x22, [sp, #32]
+ ldp x23, x24, [sp, #48]
+ ldp x25, x26, [sp, #64]
+ ldp x27, x28, [sp, #80]
+ ldp x29, x30, [sp], #96
+ ret
+SYM_FUNC_END(arch_bpf_run_cleanup_pad)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 6c04fee46876..560eba305bca 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -11,6 +11,7 @@
#include <linux/bitfield.h>
#include <linux/bpf.h>
#include <linux/cfi.h>
+#include <linux/bpf_verifier.h>
#include <linux/filter.h>
#include <linux/memory.h>
#include <linux/printk.h>
@@ -75,7 +76,21 @@ static const int bpf2a64[] = {
[ARENA_VM_START] = A64_R(28),
};
+/* Throw-site spill: the five pairs push_callee_regs() forces on, same size and
+ * slot order, so arch_bpf_run_cleanup_pad() reads both alike.
+ */
+#define A64_CLEANUP_SPILL_SZ (5 * 16)
+
+/*
+ * Where a landing pad's frame is anchored, since the stack pointer generated
+ * code normally addresses it through is the walker's inside a pad. bpf2a64[]
+ * maps nothing to x24, so nothing else in generated code touches it.
+ */
+#define A64_CLEANUP_FP A64_R(24)
+
struct jit_ctx {
+ /* Bytes reserved for the throw-site spill; see bpf_cleanup_force_spill(). */
+ u32 throw_spill;
const struct bpf_prog *prog;
int idx;
int epilogue_offset;
@@ -432,7 +447,7 @@ static void push_callee_regs(struct jit_ctx *ctx)
* Callee-saved registers as the exception callback needs to recover
* all ARM64 Callee-saved registers in its epilogue.
*/
- if (ctx->prog->aux->exception_boundary) {
+ if (ctx->prog->aux->exception_boundary || bpf_cleanup_force_spill(ctx->prog)) {
emit(A64_PUSH(A64_R(19), A64_R(20), A64_SP), ctx);
emit(A64_PUSH(A64_R(21), A64_R(22), A64_SP), ctx);
emit(A64_PUSH(A64_R(23), A64_R(24), A64_SP), ctx);
@@ -466,7 +481,8 @@ static void pop_callee_regs(struct jit_ctx *ctx)
* program's stack frame, so recover these extra registers in the above
* two cases.
*/
- if (aux->exception_boundary || aux->exception_cb) {
+ if (aux->exception_boundary || aux->exception_cb ||
+ bpf_cleanup_force_spill(ctx->prog)) {
emit(A64_POP(A64_R(27), A64_R(28), A64_SP), ctx);
emit(A64_POP(A64_R(25), A64_R(26), A64_SP), ctx);
emit(A64_POP(A64_R(23), A64_R(24), A64_SP), ctx);
@@ -602,6 +618,20 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
emit(A64_SUB_I(1, A64_SP, A64_FP, 96), ctx);
}
+ /*
+ * Lowest address of each spill area, as an offset from A64_FP; see
+ * bpf_cleanup_pad.S for the layout. The 16 is the tail call counter
+ * pair pushed just below the frame record, and the throw-site area
+ * sits below the callee-saved one rather than in the program stack.
+ */
+ if (bpf_cleanup_force_spill(prog)) {
+ prog->aux->exc->spill_off = -(16 + A64_CLEANUP_SPILL_SZ);
+ ctx->throw_spill = A64_CLEANUP_SPILL_SZ;
+ emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->throw_spill), ctx);
+ prog->aux->exc->throw_spill_off =
+ -(16 + A64_CLEANUP_SPILL_SZ) - ctx->throw_spill;
+ }
+
/* Stack must be multiples of 16B */
ctx->stack_size = round_up(prog->aux->stack_depth, 16);
@@ -691,6 +721,10 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
if (ctx->stack_size && !ctx->priv_sp_used)
emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
+ /* Release it for the same reason build_epilogue() does. */
+ if (ctx->throw_spill)
+ emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->throw_spill), ctx);
+
pop_callee_regs(ctx);
/* goto *(prog->bpf_func + prologue_offset); */
@@ -1055,6 +1089,9 @@ static void build_epilogue(struct jit_ctx *ctx, bool was_classic)
if (ctx->stack_size && !ctx->priv_sp_used)
emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
+ if (ctx->throw_spill)
+ emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->throw_spill), ctx);
+
pop_callee_regs(ctx);
emit(A64_POP(A64_ZR, ptr, A64_SP), ctx);
@@ -1230,6 +1267,13 @@ static const u8 stack_arg_reg[] = { A64_R(5), A64_R(6), A64_R(7) };
#define NR_STACK_ARG_REGS ARRAY_SIZE(stack_arg_reg)
+/*
+ * This reads the incoming argument area off A64_FP, which in an exception
+ * cleanup landing pad would be arch_bpf_run_cleanup_pad()'s frame record
+ * rather than the unwinding frame's -- but a pad cannot contain one of these:
+ * check_stack_arg_read() requires every r11 load to come before the frame's
+ * first call, and a pad only ever runs after one.
+ */
static void emit_stack_arg_load(u8 dst, s16 bpf_off, struct jit_ctx *ctx)
{
int idx = bpf_off / sizeof(u64) - 1;
@@ -1367,6 +1411,7 @@ static int build_insn(const struct bpf_verifier_env *env, const struct bpf_insn
const s16 off = insn->off;
const s32 imm = insn->imm;
const int i = insn - ctx->prog->insnsi;
+ const bool in_pad = bpf_cleanup_insn_in_pad(ctx->prog, i);
const bool is64 = BPF_CLASS(code) == BPF_ALU64 ||
BPF_CLASS(code) == BPF_JMP;
u8 jmp_cond;
@@ -1378,9 +1423,14 @@ static int build_insn(const struct bpf_verifier_env *env, const struct bpf_insn
int ret;
bool sign_extend;
- if (bpf_insn_is_indirect_target(env, ctx->prog, i))
+ if (bpf_insn_is_indirect_target(env, ctx->prog, i) ||
+ bpf_cleanup_insn_is_pad(ctx->prog, i))
emit_bti(A64_BTI_J, ctx);
+ if (bpf_cleanup_insn_is_pad(ctx->prog, i))
+ emit(A64_SUB_I(1, A64_CLEANUP_FP, fp,
+ ctx->stack_size + ctx->stack_arg_size), ctx);
+
switch (code) {
/* dst = src */
case BPF_ALU | BPF_MOV | BPF_X:
@@ -1743,6 +1793,26 @@ static int build_insn(const struct bpf_verifier_env *env, const struct bpf_insn
u64 func_addr;
u32 cpu_offset;
+ if (bpf_cleanup_insn_is_throw(ctx->prog, insn - ctx->prog->insnsi)) {
+ /* Spill where the bpf_throw() walker looks. */
+ const s32 off = ctx->prog->aux->exc->throw_spill_off;
+
+ emit(A64_SUB_I(1, tmp, A64_FP, -off), ctx);
+ emit(A64_STR64I(bpf2a64[PRIVATE_SP], tmp, 0), ctx);
+ emit(A64_STR64I(bpf2a64[ARENA_VM_START], tmp, 8), ctx);
+ emit(A64_STR64I(bpf2a64[BPF_REG_FP], tmp, 16), ctx);
+ emit(A64_STR64I(bpf2a64[TCCNT_PTR], tmp, 24), ctx);
+ emit(A64_STR64I(bpf2a64[BPF_REG_8], tmp, 48), ctx);
+ emit(A64_STR64I(bpf2a64[BPF_REG_9], tmp, 56), ctx);
+ emit(A64_STR64I(bpf2a64[BPF_REG_6], tmp, 64), ctx);
+ emit(A64_STR64I(bpf2a64[BPF_REG_7], tmp, 72), ctx);
+ }
+
+ if (bpf_is_unwind_resume_kfunc(insn)) {
+ emit(A64_BR(A64_R(23)), ctx);
+ break;
+ }
+
/* Implement helper call to bpf_get_smp_processor_id() inline */
if (insn->src_reg == 0 && insn->imm == BPF_FUNC_get_smp_processor_id) {
cpu_offset = offsetof(struct thread_info, cpu);
@@ -1854,7 +1924,8 @@ static int build_insn(const struct bpf_verifier_env *env, const struct bpf_insn
src = tmp2;
}
if (src == fp) {
- src_adj = ctx->priv_sp_used ? priv_sp : A64_SP;
+ src_adj = ctx->priv_sp_used ? priv_sp :
+ in_pad ? A64_CLEANUP_FP : A64_SP;
off_adj = off + ctx->stack_size;
if (!ctx->priv_sp_used)
off_adj += ctx->stack_arg_size;
@@ -1952,7 +2023,8 @@ static int build_insn(const struct bpf_verifier_env *env, const struct bpf_insn
dst = tmp3;
}
if (dst == fp) {
- dst_adj = ctx->priv_sp_used ? priv_sp : A64_SP;
+ dst_adj = ctx->priv_sp_used ? priv_sp :
+ in_pad ? A64_CLEANUP_FP : A64_SP;
off_adj = off + ctx->stack_size;
if (!ctx->priv_sp_used)
off_adj += ctx->stack_arg_size;
@@ -2021,7 +2093,8 @@ static int build_insn(const struct bpf_verifier_env *env, const struct bpf_insn
dst = tmp2;
}
if (dst == fp) {
- dst_adj = ctx->priv_sp_used ? priv_sp : A64_SP;
+ dst_adj = ctx->priv_sp_used ? priv_sp :
+ in_pad ? A64_CLEANUP_FP : A64_SP;
off_adj = off + ctx->stack_size;
if (!ctx->priv_sp_used)
off_adj += ctx->stack_arg_size;
@@ -2410,6 +2483,13 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
* reasons, expects to point to the next instruction)
*/
bpf_prog_update_insn_ptrs(prog, ctx.offset, ctx.ro_image);
+
+ /*
+ * Same byte offsets, consumed by the bpf_throw() frame walker:
+ * turn the cleanup records into native address ranges now that
+ * the image is final.
+ */
+ bpf_cleanup_fill_native_ranges(prog, ctx.offset, ctx.ro_image);
out_off:
if (!ro_header && priv_stack_ptr) {
free_percpu(priv_stack_ptr);
@@ -3385,6 +3465,11 @@ bool bpf_jit_supports_exceptions(void)
return true;
}
+bool bpf_jit_supports_cleanup_pads(void)
+{
+ return true;
+}
+
bool bpf_jit_supports_arena(void)
{
return true;
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH bpf-next 13/20] libbpf: Resolve the compiler's _Unwind_Resume to the kernel's kfunc
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (11 preceding siblings ...)
2026-09-17 5:57 ` [PATCH bpf-next 12/20] bpf, arm64: " Yonghong Song
@ 2026-09-17 5:57 ` Yonghong Song
2026-09-17 6:08 ` sashiko-bot
2026-09-17 7:00 ` bot+bpf-ci
2026-09-17 5:57 ` [PATCH bpf-next 14/20] libbpf: Add cleanup_info to bpf_prog_load_opts Yonghong Song
` (6 subsequent siblings)
19 siblings, 2 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:57 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
LLVM terminates a cleanup landing pad with a call to _Unwind_Resume: the
base unwind ABI's entry point for carrying an unwind on once a frame's
cleanups have run. The kernel provides that terminator as a kfunc, but
not under that name: claiming _Unwind_Resume in the kernel's own symbol
table, for a function whose body never runs, would be needlessly confusing,
so it is called bpf_unwind_resume.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
tools/lib/bpf/libbpf.c | 17 ++++++++++++++---
1 file changed, 14 insertions(+), 3 deletions(-)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 613afae26519..ea1c09fa3793 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8346,6 +8346,15 @@ static void fixup_verifier_log(struct bpf_program *prog, char *buf, size_t buf_s
}
}
+/* LLVM terminates a cleanup landing pad with a call to _Unwind_Resume, the
+ * base unwind ABI's entry point for carrying an unwind on once a frame's
+ * cleanups have run. The kernel knows it as bpf_unwind_resume.
+ */
+static const char *kern_extern_name(const char *name)
+{
+ return strcmp(name, "_Unwind_Resume") ? name : "bpf_unwind_resume";
+}
+
static int bpf_program_record_relos(struct bpf_program *prog)
{
struct bpf_object *obj = prog->obj;
@@ -8807,17 +8816,19 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj,
struct module_btf *mod_btf = NULL;
const struct btf_type *kern_func;
struct btf *kern_btf = NULL;
+ const char *kern_name;
int ret;
local_func_proto_id = ext->ksym.type_id;
- kfunc_id = find_ksym_btf_id(obj, ext->essent_name ?: ext->name, BTF_KIND_FUNC, &kern_btf,
- &mod_btf);
+ kern_name = kern_extern_name(ext->essent_name ?: ext->name);
+
+ kfunc_id = find_ksym_btf_id(obj, kern_name, BTF_KIND_FUNC, &kern_btf, &mod_btf);
if (kfunc_id < 0) {
if (kfunc_id == -ESRCH && ext->is_weak)
return 0;
pr_warn("extern (func ksym) '%s': not found in kernel or module BTFs\n",
- ext->name);
+ strcmp(kern_name, "bpf_unwind_resume") ? ext->name : kern_name);
return kfunc_id;
}
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 13/20] libbpf: Resolve the compiler's _Unwind_Resume to the kernel's kfunc
2026-09-17 5:57 ` [PATCH bpf-next 13/20] libbpf: Resolve the compiler's _Unwind_Resume to the kernel's kfunc Yonghong Song
@ 2026-09-17 6:08 ` sashiko-bot
2026-09-17 7:00 ` bot+bpf-ci
1 sibling, 0 replies; 40+ messages in thread
From: sashiko-bot @ 2026-09-17 6:08 UTC (permalink / raw)
To: Yonghong Song; +Cc: bpf
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] bpf: multi-line comment violates BPF subsystem style guide
--
commit 082b791c15a0d9341a2e4f4d61c9b916d48b95fc
Author: Yonghong Song <yonghong.song@linux.dev>
libbpf: Resolve the compiler's _Unwind_Resume to the kernel's kfunc
This commit maps LLVM's _Unwind_Resume function calls in cleanup landing pads
to the kernel's corresponding bpf_unwind_resume kfunc. This ensures proper
symbol resolution without polluting the kernel's symbol table.
> diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> index 613afae265199..ea1c09fa37939 100644
> --- a/tools/lib/bpf/libbpf.c
> +++ b/tools/lib/bpf/libbpf.c
> @@ -8346,6 +8346,15 @@ static void fixup_verifier_log(struct bpf_program *prog, char *buf, size_t buf_s
> }
> }
>
> +/* LLVM terminates a cleanup landing pad with a call to _Unwind_Resume, the
> + * base unwind ABI's entry point for carrying an unwind on once a frame's
> + * cleanups have run. The kernel knows it as bpf_unwind_resume.
> + */
[Severity: Low]
This isn't a bug, but does this multi-line comment format violate the
BPF subsystem style guide? The guide specifies that multi-line comments
must have the opening /* on its own line, rather than starting the text
on the same line as the opening characters.
> +static const char *kern_extern_name(const char *name)
> +{
> + return strcmp(name, "_Unwind_Resume") ? name : "bpf_unwind_resume";
> +}
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260917055645.3926444-1-yonghong.song@linux.dev?part=13
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 13/20] libbpf: Resolve the compiler's _Unwind_Resume to the kernel's kfunc
2026-09-17 5:57 ` [PATCH bpf-next 13/20] libbpf: Resolve the compiler's _Unwind_Resume to the kernel's kfunc Yonghong Song
2026-09-17 6:08 ` sashiko-bot
@ 2026-09-17 7:00 ` bot+bpf-ci
2026-09-18 3:40 ` Yonghong Song
1 sibling, 1 reply; 40+ messages in thread
From: bot+bpf-ci @ 2026-09-17 7:00 UTC (permalink / raw)
To: yonghong.song, bpf
Cc: ast, andrii, daniel, eddyz87, kernel-team, ast, andrii, daniel,
martin.lau, eddyz87, yonghong.song, mason, ihor.solodrai
[-- Attachment #1: Type: text/plain, Size: 3549 bytes --]
> diff --git tools/lib/bpf/libbpf.c tools/lib/bpf/libbpf.c
> index 613afae265199..ea1c09fa37939 100644
> --- tools/lib/bpf/libbpf.c
> +++ tools/lib/bpf/libbpf.c
> @@ -8346,6 +8346,15 @@ static void fixup_verifier_log(struct bpf_program *prog, char *buf, size_t buf_s
> }
> }
>
> +/* LLVM terminates a cleanup landing pad with a call to _Unwind_Resume, the
> + * base unwind ABI's entry point for carrying an unwind on once a frame's
> + * cleanups have run. The kernel knows it as bpf_unwind_resume.
> + */
> +static const char *kern_extern_name(const char *name)
> +{
> + return strcmp(name, "_Unwind_Resume") ? name : "bpf_unwind_resume";
> +}
> +
> static int bpf_program_record_relos(struct bpf_program *prog)
> {
> struct bpf_object *obj = prog->obj;
Is the kern_extern_name() mapping applied on the light skeleton load
path?
Looking at bpf_program_record_relos() below kern_extern_name(), the
RELO_EXTERN_CALL case records ext->name directly without calling
kern_extern_name():
static int bpf_program_record_relos(struct bpf_program *prog)
{
...
case RELO_EXTERN_CALL:
bpf_gen__record_extern(obj->gen_loader, ext->name,
ext->is_weak, false, false, BTF_KIND_FUNC,
relo->insn_idx);
break;
...
}
This means the generated loader program would ask the kernel for
BTF_KIND_FUNC '_Unwind_Resume', which doesn't exist in vmlinux BTF. The
kernel only knows bpf_unwind_resume per BTF_ID_FLAGS(func,
bpf_unwind_resume) in kernel/bpf/helpers.c.
For comparison, the direct BPF_PROG_LOAD path does use the mapping:
bpf_object__resolve_ksym_func_btf_id() calls kern_extern_name() at
libbpf.c:8824, but that resolution is deliberately skipped when
obj->gen_loader is set:
bpf_object__resolve_ksyms_btf_id() {
...
if (obj->gen_loader) {
ext->is_set = true;
ext->ksym.kernel_btf_obj_fd = 0;
ext->ksym.kernel_btf_id = 0;
continue;
}
...
}
On the light skeleton path, bpf_btf_find_by_name_kind() would return
-ESRCH for '_Unwind_Resume', causing emit_check_err() to jump to cleanup
and fail the load. If the extern were weak, insn->imm/off would be
stored as 0, which the verifier would reject as an invalid kfunc call.
The test added later in the series
(selftests/bpf/progs/exceptions_cleanup_light.c) writes 'call
bpf_unwind_resume' directly in inline asm, so it uses the kernel name
and never exercises the mapping.
> @@ -8807,17 +8816,19 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj,
> struct module_btf *mod_btf = NULL;
> const struct btf_type *kern_func;
> struct btf *kern_btf = NULL;
> + const char *kern_name;
> int ret;
>
> local_func_proto_id = ext->ksym.type_id;
>
> - kfunc_id = find_ksym_btf_id(obj, ext->essent_name ?: ext->name, BTF_KIND_FUNC, &kern_btf,
> - &mod_btf);
> + kern_name = kern_extern_name(ext->essent_name ?: ext->name);
> +
> + kfunc_id = find_ksym_btf_id(obj, kern_name, BTF_KIND_FUNC, &kern_btf, &mod_btf);
> if (kfunc_id < 0) {
> if (kfunc_id == -ESRCH && ext->is_weak)
> return 0;
> pr_warn("extern (func ksym) '%s': not found in kernel or module BTFs\n",
> - ext->name);
> + strcmp(kern_name, "bpf_unwind_resume") ? ext->name : kern_name);
> return kfunc_id;
> }
---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md
CI run summary: https://github.com/kernel-patches/bpf/actions/runs/35188619605
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 13/20] libbpf: Resolve the compiler's _Unwind_Resume to the kernel's kfunc
2026-09-17 7:00 ` bot+bpf-ci
@ 2026-09-18 3:40 ` Yonghong Song
0 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-18 3:40 UTC (permalink / raw)
To: bot+bpf-ci, bpf
Cc: ast, andrii, daniel, eddyz87, kernel-team, martin.lau, mason,
ihor.solodrai
On 9/17/26 12:00 AM, bot+bpf-ci@kernel.org wrote:
>> diff --git tools/lib/bpf/libbpf.c tools/lib/bpf/libbpf.c
>> index 613afae265199..ea1c09fa37939 100644
>> --- tools/lib/bpf/libbpf.c
>> +++ tools/lib/bpf/libbpf.c
>> @@ -8346,6 +8346,15 @@ static void fixup_verifier_log(struct bpf_program *prog, char *buf, size_t buf_s
>> }
>> }
>>
>> +/* LLVM terminates a cleanup landing pad with a call to _Unwind_Resume, the
>> + * base unwind ABI's entry point for carrying an unwind on once a frame's
>> + * cleanups have run. The kernel knows it as bpf_unwind_resume.
>> + */
>> +static const char *kern_extern_name(const char *name)
>> +{
>> + return strcmp(name, "_Unwind_Resume") ? name : "bpf_unwind_resume";
>> +}
>> +
>> static int bpf_program_record_relos(struct bpf_program *prog)
>> {
>> struct bpf_object *obj = prog->obj;
> Is the kern_extern_name() mapping applied on the light skeleton load
> path?
>
> Looking at bpf_program_record_relos() below kern_extern_name(), the
> RELO_EXTERN_CALL case records ext->name directly without calling
> kern_extern_name():
>
> static int bpf_program_record_relos(struct bpf_program *prog)
> {
> ...
> case RELO_EXTERN_CALL:
> bpf_gen__record_extern(obj->gen_loader, ext->name,
> ext->is_weak, false, false, BTF_KIND_FUNC,
> relo->insn_idx);
> break;
> ...
> }
>
> This means the generated loader program would ask the kernel for
> BTF_KIND_FUNC '_Unwind_Resume', which doesn't exist in vmlinux BTF. The
> kernel only knows bpf_unwind_resume per BTF_ID_FLAGS(func,
> bpf_unwind_resume) in kernel/bpf/helpers.c.
>
> For comparison, the direct BPF_PROG_LOAD path does use the mapping:
>
> bpf_object__resolve_ksym_func_btf_id() calls kern_extern_name() at
> libbpf.c:8824, but that resolution is deliberately skipped when
> obj->gen_loader is set:
>
> bpf_object__resolve_ksyms_btf_id() {
> ...
> if (obj->gen_loader) {
> ext->is_set = true;
> ext->ksym.kernel_btf_obj_fd = 0;
> ext->ksym.kernel_btf_id = 0;
> continue;
> }
> ...
> }
>
> On the light skeleton path, bpf_btf_find_by_name_kind() would return
> -ESRCH for '_Unwind_Resume', causing emit_check_err() to jump to cleanup
> and fail the load. If the extern were weak, insn->imm/off would be
> stored as 0, which the verifier would reject as an invalid kfunc call.
>
> The test added later in the series
> (selftests/bpf/progs/exceptions_cleanup_light.c) writes 'call
> bpf_unwind_resume' directly in inline asm, so it uses the kernel name
> and never exercises the mapping.
Indeed, later patch in selftests/bpf/progs/exceptions_cleanup_light.c
fixed the issue with bpf_undiwn_resume properly. So this is not really
a bug. But we can do better than this. We can change from ext->name to
bpf_unwind_resume in file selftests/bpf/progs/exceptions_cleanup_light.c
for this patch. This will make things easier to understand.
>
>> @@ -8807,17 +8816,19 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj,
>> struct module_btf *mod_btf = NULL;
>> const struct btf_type *kern_func;
>> struct btf *kern_btf = NULL;
>> + const char *kern_name;
>> int ret;
>>
>> local_func_proto_id = ext->ksym.type_id;
>>
>> - kfunc_id = find_ksym_btf_id(obj, ext->essent_name ?: ext->name, BTF_KIND_FUNC, &kern_btf,
>> - &mod_btf);
>> + kern_name = kern_extern_name(ext->essent_name ?: ext->name);
>> +
>> + kfunc_id = find_ksym_btf_id(obj, kern_name, BTF_KIND_FUNC, &kern_btf, &mod_btf);
>> if (kfunc_id < 0) {
>> if (kfunc_id == -ESRCH && ext->is_weak)
>> return 0;
>> pr_warn("extern (func ksym) '%s': not found in kernel or module BTFs\n",
>> - ext->name);
>> + strcmp(kern_name, "bpf_unwind_resume") ? ext->name : kern_name);
>> return kfunc_id;
>> }
>
> ---
> AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
> See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md
>
> CI run summary: https://github.com/kernel-patches/bpf/actions/runs/35188619605
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH bpf-next 14/20] libbpf: Add cleanup_info to bpf_prog_load_opts
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (12 preceding siblings ...)
2026-09-17 5:57 ` [PATCH bpf-next 13/20] libbpf: Resolve the compiler's _Unwind_Resume to the kernel's kfunc Yonghong Song
@ 2026-09-17 5:57 ` Yonghong Song
2026-09-17 5:58 ` [PATCH bpf-next 15/20] libbpf: Collect .bpf_cleanup records and pass them to the kernel Yonghong Song
` (5 subsequent siblings)
19 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:57 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
Let a caller hand the kernel an exception cleanup table. Extend struct
bpf_prog_load_opts with cleanup_info, cleanup_info_cnt and
cleanup_info_rec_size, pass them through to BPF_PROG_LOAD, and grow the
attr size bpf_prog_load() computes to cover the new fields.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
tools/lib/bpf/bpf.c | 6 +++++-
tools/lib/bpf/bpf.h | 7 ++++++-
2 files changed, 11 insertions(+), 2 deletions(-)
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 96819c082c77..bcf490570961 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -295,7 +295,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
const struct bpf_insn *insns, size_t insn_cnt,
struct bpf_prog_load_opts *opts)
{
- const size_t attr_sz = offsetofend(union bpf_attr, keyring_id);
+ const size_t attr_sz = offsetofend(union bpf_attr, cleanup_info_cnt);
void *finfo = NULL, *linfo = NULL;
const char *func_info, *line_info;
__u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd;
@@ -370,6 +370,10 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
attr.fd_array = ptr_to_u64(OPTS_GET(opts, fd_array, NULL));
attr.fd_array_cnt = OPTS_GET(opts, fd_array_cnt, 0);
+ attr.cleanup_info = ptr_to_u64(OPTS_GET(opts, cleanup_info, NULL));
+ attr.cleanup_info_cnt = OPTS_GET(opts, cleanup_info_cnt, 0);
+ attr.cleanup_info_rec_size = OPTS_GET(opts, cleanup_info_rec_size, 0);
+
if (log_level) {
attr.log_buf = ptr_to_u64(log_buf);
attr.log_size = log_size;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 7534a593edae..6f62a99e1e3e 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -128,9 +128,14 @@ struct bpf_prog_load_opts {
/* if set, provides the length of fd_array */
__u32 fd_array_cnt;
+
+ /* exception cleanup table, from the .bpf_cleanup section */
+ const void *cleanup_info;
+ __u32 cleanup_info_cnt;
+ __u32 cleanup_info_rec_size;
size_t :0;
};
-#define bpf_prog_load_opts__last_field fd_array_cnt
+#define bpf_prog_load_opts__last_field cleanup_info_rec_size
LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type,
const char *prog_name, const char *license,
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH bpf-next 15/20] libbpf: Collect .bpf_cleanup records and pass them to the kernel
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (13 preceding siblings ...)
2026-09-17 5:57 ` [PATCH bpf-next 14/20] libbpf: Add cleanup_info to bpf_prog_load_opts Yonghong Song
@ 2026-09-17 5:58 ` Yonghong Song
2026-09-17 6:12 ` sashiko-bot
2026-09-17 5:58 ` [PATCH bpf-next 16/20] libbpf: Carry the exception cleanup table through the light skeleton Yonghong Song
` (4 subsequent siblings)
19 siblings, 1 reply; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:58 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
Parse the compiler-emitted .bpf_cleanup section and hand the resulting
table to BPF_PROG_LOAD.
Each record is three 4-byte fields, and each field is a byte offset into
some code section named by a matching .rel.bpf_cleanup relocation.
bpf_object__init_cleanup_info() resolves both halves once at open time and
keeps (section, instruction index) pairs; it rejects a record whose field
has no relocation, whose relocation is not one of the two 32-bit types that
spell a data reference to a code section -- R_BPF_64_NODYLD32 from LLVM,
R_BPF_64_ABS32 from GNU as -- or whose offset is not instruction aligned.
The records are sorted by begin_off once the offsets are final: the kernel
wants the table sorted with disjoint ranges so that it can find the record
covering a call site with a binary search, and records arrive in
.bpf_cleanup order, which says nothing about where the subprograms they
describe were appended. Overlapping ranges are reported here, where the
program name and both regions are still at hand.
bpf_object_load_prog() then passes the per-program table through the
bpf_prog_load() options added in the previous patch, with the record size
carried on the program the way func_info and line_info carry theirs rather
than taken from a sizeof() at the call site. bpf_program__clone() carries
it too. That is a second load path -- the one veristat uses -- and without
the table the kernel sees landing pads nothing reaches and refuses the
program with "unreachable insn".
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
tools/lib/bpf/libbpf.c | 284 ++++++++++++++++++++++++++++++++
tools/lib/bpf/libbpf_internal.h | 3 +
2 files changed, 287 insertions(+)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ea1c09fa3793..d7cb93a70f58 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -514,6 +514,11 @@ struct bpf_program {
void *line_info;
__u32 line_info_rec_size;
__u32 line_info_cnt;
+
+ struct bpf_cleanup_info *cleanup_info;
+ __u32 cleanup_info_rec_size;
+ __u32 cleanup_info_cnt;
+
__u32 prog_flags;
__u8 hash[SHA256_DIGEST_LENGTH];
@@ -549,6 +554,7 @@ struct bpf_struct_ops {
#define STRUCT_OPS_SEC ".struct_ops"
#define STRUCT_OPS_LINK_SEC ".struct_ops.link"
#define ARENA_SEC ".addr_space.1"
+#define CLEANUP_SEC ".bpf_cleanup"
enum libbpf_map_type {
LIBBPF_MAP_UNSPEC,
@@ -677,6 +683,25 @@ struct elf_sec_desc {
Elf_Data *data;
};
+#define CLEANUP_REC_FIELDS (sizeof(struct bpf_cleanup_info) / sizeof(__u32))
+
+/* Index of each field of struct bpf_cleanup_info, read as an array of __u32. */
+enum {
+ CLEANUP_REC_BEGIN,
+ CLEANUP_REC_END,
+ CLEANUP_REC_PAD,
+};
+
+/* One (begin, end, landing_pad) triple from .bpf_cleanup, with each field
+ * resolved from its relocation to an ELF section plus a section-relative
+ * instruction index. The mapping to final program instruction indices can only
+ * happen after subprogram placement, which differs per main program.
+ */
+struct cleanup_raw_rec {
+ int sec_idx[CLEANUP_REC_FIELDS];
+ size_t insn_idx[CLEANUP_REC_FIELDS];
+};
+
struct elf_state {
int fd;
const void *obj_buf;
@@ -696,6 +721,8 @@ struct elf_state {
bool has_st_ops;
int arena_data_shndx;
int jumptables_data_shndx;
+ Elf_Data *cleanup_data;
+ int cleanup_shndx;
};
struct usdt_manager;
@@ -771,6 +798,9 @@ struct bpf_object {
void *jumptables_data;
size_t jumptables_data_sz;
+ struct cleanup_raw_rec *cleanup_recs;
+ size_t cleanup_rec_cnt;
+
struct {
struct bpf_program *prog;
unsigned int sym_off;
@@ -817,7 +847,10 @@ static void bpf_program__exit(struct bpf_program *prog)
zfree(&prog->sec_name);
zfree(&prog->insns);
zfree(&prog->reloc_desc);
+ zfree(&prog->cleanup_info);
+ prog->cleanup_info_rec_size = 0;
+ prog->cleanup_info_cnt = 0;
prog->nr_reloc = 0;
prog->insns_cnt = 0;
prog->sec_idx = -1;
@@ -1554,6 +1587,7 @@ static struct bpf_object *bpf_object__new(const char *path,
obj->efile.obj_buf = obj_buf;
obj->efile.obj_buf_sz = obj_buf_sz;
obj->efile.btf_maps_shndx = -1;
+ obj->efile.cleanup_shndx = -1;
obj->kconfig_map_idx = -1;
obj->arena_map_idx = -1;
@@ -4040,6 +4074,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
sec_desc->shdr = sh;
sec_desc->data = data;
obj->efile.has_st_ops = true;
+ } else if (strcmp(name, CLEANUP_SEC) == 0) {
+ obj->efile.cleanup_data = data;
+ obj->efile.cleanup_shndx = idx;
} else if (strcmp(name, ARENA_SEC) == 0) {
obj->efile.arena_data = data;
obj->efile.arena_data_shndx = idx;
@@ -4067,6 +4104,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
strcmp(name, ".rel" STRUCT_OPS_LINK_SEC) &&
strcmp(name, ".rel?" STRUCT_OPS_SEC) &&
strcmp(name, ".rel?" STRUCT_OPS_LINK_SEC) &&
+ strcmp(name, ".rel" CLEANUP_SEC) &&
strcmp(name, ".rel" MAPS_ELF_SEC)) {
pr_info("elf: skipping relo section(%d) %s for section(%d) %s\n",
idx, name, targ_sec_idx,
@@ -4847,6 +4885,214 @@ static struct bpf_program *find_prog_by_sec_insn(const struct bpf_object *obj,
return NULL;
}
+static int bpf_object__init_cleanup_info(struct bpf_object *obj)
+{
+ Elf_Data *data = obj->efile.cleanup_data;
+ Elf_Data *relo = NULL;
+ size_t i, nrels, nslots, nrecs;
+ struct cleanup_raw_rec *recs;
+ int *slot_sec, ret = 0;
+ size_t *slot_val;
+ const __u32 *vals;
+ bool native;
+
+ if (!data || obj->efile.cleanup_shndx < 0)
+ return 0;
+
+ native = is_native_endianness(obj);
+
+ for (i = 0; i < obj->efile.sec_cnt; i++) {
+ struct elf_sec_desc *sd = &obj->efile.secs[i];
+
+ if (sd->sec_type == SEC_RELO && sd->shdr &&
+ sd->shdr->sh_info == (Elf64_Word)obj->efile.cleanup_shndx) {
+ relo = sd->data;
+ break;
+ }
+ }
+ if (!relo) {
+ pr_warn("%s present without relocations\n", CLEANUP_SEC);
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+ if (data->d_size % sizeof(struct bpf_cleanup_info)) {
+ pr_warn("%s size %zu is not a multiple of the record size %zu\n",
+ CLEANUP_SEC, data->d_size, sizeof(struct bpf_cleanup_info));
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+
+ vals = data->d_buf;
+ nslots = data->d_size / sizeof(__u32);
+ nrecs = data->d_size / sizeof(struct bpf_cleanup_info);
+
+ slot_sec = calloc(nslots, sizeof(*slot_sec));
+ slot_val = calloc(nslots, sizeof(*slot_val));
+ recs = calloc(nrecs ?: 1, sizeof(*recs));
+ if (!slot_sec || !slot_val || !recs) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ for (i = 0; i < nslots; i++)
+ slot_sec[i] = -1;
+
+ /* One relocation per 4-byte field, naming the section it points into. */
+ nrels = relo->d_size / sizeof(Elf64_Rel);
+ for (i = 0; i < nrels; i++) {
+ Elf64_Rel *rel = elf_rel_by_idx(relo, i);
+ Elf64_Sym *sym = elf_sym_by_idx(obj, ELF64_R_SYM(rel->r_info));
+ size_t type = ELF64_R_TYPE(rel->r_info);
+ size_t slot = rel->r_offset / sizeof(__u32);
+
+ if (type != R_BPF_64_NODYLD32 && type != R_BPF_64_ABS32) {
+ pr_warn("%s: relocation %zu has unexpected type %zu\n",
+ CLEANUP_SEC, i, type);
+ ret = -LIBBPF_ERRNO__FORMAT;
+ goto out;
+ }
+ if (!sym || slot >= nslots || rel->r_offset % sizeof(__u32)) {
+ pr_warn("%s: bad relocation %zu\n", CLEANUP_SEC, i);
+ ret = -LIBBPF_ERRNO__FORMAT;
+ goto out;
+ }
+ slot_sec[slot] = sym->st_shndx;
+ /* The addend lives in the section data, which libelf leaves in
+ * the object's byte order; a non-section symbol additionally
+ * contributes its own value.
+ */
+ slot_val[slot] = (native ? vals[slot] : bswap_32(vals[slot])) +
+ sym->st_value;
+ }
+
+ for (i = 0; i < nslots; i++) {
+ struct cleanup_raw_rec *rec = &recs[i / CLEANUP_REC_FIELDS];
+ size_t field = i % CLEANUP_REC_FIELDS;
+
+ if (slot_sec[i] < 0) {
+ pr_warn("%s: field %zu has no relocation\n", CLEANUP_SEC, i);
+ ret = -LIBBPF_ERRNO__FORMAT;
+ goto out;
+ }
+ if (slot_val[i] % BPF_INSN_SZ) {
+ pr_warn("%s: field %zu offset %zu is not instruction aligned\n",
+ CLEANUP_SEC, i, slot_val[i]);
+ ret = -LIBBPF_ERRNO__FORMAT;
+ goto out;
+ }
+ rec->sec_idx[field] = slot_sec[i];
+ rec->insn_idx[field] = slot_val[i] / BPF_INSN_SZ;
+ }
+
+ obj->cleanup_recs = recs;
+ obj->cleanup_rec_cnt = nrecs;
+ recs = NULL;
+out:
+ free(recs);
+ free(slot_val);
+ free(slot_sec);
+ return ret;
+}
+
+static int cmp_cleanup_info(const void *a, const void *b)
+{
+ const struct bpf_cleanup_info *x = a, *y = b;
+
+ if (x->begin_off == y->begin_off)
+ return 0;
+ return x->begin_off < y->begin_off ? -1 : 1;
+}
+
+static int bpf_prog_collect_cleanup_info(struct bpf_object *obj,
+ struct bpf_program *prog)
+{
+ size_t i;
+ int j;
+
+ for (i = 0; i < obj->cleanup_rec_cnt; i++) {
+ struct cleanup_raw_rec *raw = &obj->cleanup_recs[i];
+ struct bpf_program *owner = NULL;
+ struct bpf_cleanup_info ci = {};
+ __u32 *fields = (__u32 *)&ci;
+ void *tmp;
+
+ for (j = 0; j < CLEANUP_REC_FIELDS; j++) {
+ size_t idx = raw->insn_idx[j], final;
+ struct bpf_program *p;
+
+ /* The end of a range is exclusive, so it may name the
+ * instruction just past the last one of a function,
+ * which belongs to the next function or to nothing at
+ * all. Ask about the last instruction the range covers,
+ * the way the kernel does.
+ */
+ if (j == CLEANUP_REC_END) {
+ if (!idx) {
+ pr_warn("%s: record %zu is an empty range\n",
+ CLEANUP_SEC, i);
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+ idx--;
+ }
+
+ p = find_prog_by_sec_insn(obj, raw->sec_idx[j], idx);
+ if (!p) {
+ pr_warn("%s: record %zu field %d is not inside a function\n",
+ CLEANUP_SEC, i, j);
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+ if (!owner) {
+ owner = p;
+ } else if (owner != p) {
+ pr_warn("%s: record %zu spans functions '%s' and '%s'\n",
+ CLEANUP_SEC, i, owner->name, p->name);
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+
+ if (owner == prog) {
+ final = raw->insn_idx[j] - prog->sec_insn_off;
+ } else if (prog_is_subprog(obj, owner) && owner->sub_insn_off) {
+ /* sub_insn_off is where this subprogram was
+ * appended to the main program being relocated;
+ * zero means it is not part of it.
+ */
+ final = owner->sub_insn_off +
+ raw->insn_idx[j] - owner->sec_insn_off;
+ } else {
+ owner = NULL;
+ break;
+ }
+ fields[j] = final;
+ }
+ if (!owner)
+ continue;
+
+ tmp = libbpf_reallocarray(prog->cleanup_info, prog->cleanup_info_cnt + 1,
+ sizeof(*prog->cleanup_info));
+ if (!tmp)
+ return -ENOMEM;
+ prog->cleanup_info = tmp;
+ prog->cleanup_info_rec_size = sizeof(struct bpf_cleanup_info);
+ prog->cleanup_info[prog->cleanup_info_cnt++] = ci;
+
+ pr_debug("prog '%s': cleanup region [%u,%u) -> landing pad %u\n",
+ prog->name, ci.begin_off, ci.end_off, ci.landing_pad_off);
+ }
+
+ qsort(prog->cleanup_info, prog->cleanup_info_cnt,
+ sizeof(*prog->cleanup_info), cmp_cleanup_info);
+ for (i = 1; i < prog->cleanup_info_cnt; i++) {
+ struct bpf_cleanup_info *prev = &prog->cleanup_info[i - 1];
+ struct bpf_cleanup_info *cur = &prog->cleanup_info[i];
+
+ if (cur->begin_off < prev->end_off) {
+ pr_warn("prog '%s': overlapping cleanup regions [%u,%u) and [%u,%u)\n",
+ prog->name, prev->begin_off, prev->end_off,
+ cur->begin_off, cur->end_off);
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+ }
+
+ return 0;
+}
+
static int
bpf_object__collect_prog_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Data *data)
{
@@ -7556,6 +7802,13 @@ static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_pat
return err;
}
}
+
+ err = bpf_prog_collect_cleanup_info(obj, prog);
+ if (err) {
+ pr_warn("prog '%s': failed to collect cleanup info: %s\n",
+ prog->name, errstr(err));
+ return err;
+ }
}
for (i = 0; i < obj->nr_programs; i++) {
prog = &obj->programs[i];
@@ -7746,6 +7999,9 @@ static int bpf_object__collect_relos(struct bpf_object *obj)
return -LIBBPF_ERRNO__INTERNAL;
}
+ if (idx == obj->efile.cleanup_shndx)
+ continue;
+
if (obj->efile.secs[idx].sec_type == SEC_ST_OPS)
err = bpf_object__collect_st_ops_relos(obj, shdr, data);
else if (idx == obj->efile.btf_maps_shndx)
@@ -8018,6 +8274,11 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
load_attr.line_info_rec_size = prog->line_info_rec_size;
load_attr.line_info_cnt = prog->line_info_cnt;
}
+ if (prog->cleanup_info_cnt) {
+ load_attr.cleanup_info = prog->cleanup_info;
+ load_attr.cleanup_info_cnt = prog->cleanup_info_cnt;
+ load_attr.cleanup_info_rec_size = prog->cleanup_info_rec_size;
+ }
load_attr.log_level = log_level;
load_attr.prog_flags = prog->prog_flags;
load_attr.fd_array = obj->fd_array;
@@ -8574,6 +8835,7 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf,
err = err ? : bpf_object__init_maps(obj, opts);
err = err ? : bpf_object_init_progs(obj, opts);
err = err ? : bpf_object__collect_relos(obj);
+ err = err ? : bpf_object__init_cleanup_info(obj);
if (err)
goto out;
@@ -9687,6 +9949,9 @@ void bpf_object__close(struct bpf_object *obj)
zfree(&obj->jumptables_data);
obj->jumptables_data_sz = 0;
+ zfree(&obj->cleanup_recs);
+ obj->cleanup_rec_cnt = 0;
+
for (i = 0; i < obj->jumptable_map_cnt; i++)
close(obj->jumptable_maps[i].fd);
zfree(&obj->jumptable_maps);
@@ -10079,6 +10344,25 @@ int bpf_program__clone(struct bpf_program *prog, const struct bpf_prog_load_opts
attr.line_info_rec_size = info ? info_rec_size : prog->line_info_rec_size;
}
+ /* exception cleanup table */
+ info = OPTS_GET(opts, cleanup_info, NULL);
+ info_cnt = OPTS_GET(opts, cleanup_info_cnt, 0);
+ info_rec_size = OPTS_GET(opts, cleanup_info_rec_size, 0);
+ if (!!info != !!info_cnt || !!info != !!info_rec_size) {
+ pr_warn("prog '%s': cleanup_info, cleanup_info_cnt, and cleanup_info_rec_size must all be specified or all omitted\n",
+ prog->name);
+ return libbpf_err(-EINVAL);
+ }
+ if (info) {
+ attr.cleanup_info = info;
+ attr.cleanup_info_cnt = info_cnt;
+ attr.cleanup_info_rec_size = info_rec_size;
+ } else if (prog->cleanup_info_cnt) {
+ attr.cleanup_info = prog->cleanup_info;
+ attr.cleanup_info_cnt = prog->cleanup_info_cnt;
+ attr.cleanup_info_rec_size = prog->cleanup_info_rec_size;
+ }
+
/* Logging is caller-controlled; no fallback to prog/obj log settings */
attr.log_buf = OPTS_GET(opts, log_buf, NULL);
attr.log_size = OPTS_GET(opts, log_size, 0);
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index cb4d96233844..3ba6d9090368 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -56,6 +56,9 @@
#ifndef R_BPF_64_ABS32
#define R_BPF_64_ABS32 3
#endif
+#ifndef R_BPF_64_NODYLD32
+#define R_BPF_64_NODYLD32 4
+#endif
#ifndef R_BPF_64_32
#define R_BPF_64_32 10
#endif
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 15/20] libbpf: Collect .bpf_cleanup records and pass them to the kernel
2026-09-17 5:58 ` [PATCH bpf-next 15/20] libbpf: Collect .bpf_cleanup records and pass them to the kernel Yonghong Song
@ 2026-09-17 6:12 ` sashiko-bot
2026-09-18 3:44 ` Yonghong Song
0 siblings, 1 reply; 40+ messages in thread
From: sashiko-bot @ 2026-09-17 6:12 UTC (permalink / raw)
To: Yonghong Song; +Cc: bpf
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Medium] bpf: undefined behavior when calling qsort with a NULL pointer
- [Low] bpf: array bounds violation via type-punned pointer arithmetic
--
commit 1e591245d7ec663b872eae44c8fa7f02cfd956a4
Author: Yonghong Song <yonghong.song@linux.dev>
libbpf: Collect .bpf_cleanup records and pass them to the kernel
This commit parses the compiler-emitted .bpf_cleanup section and hands
the resulting table to BPF_PROG_LOAD so the kernel can resolve exceptions.
> diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> index ea1c09fa37939..d7cb93a70f58d 100644
> --- a/tools/lib/bpf/libbpf.c
> +++ b/tools/lib/bpf/libbpf.c
[ ... ]
> @@ -4847,6 +4885,214 @@ static struct bpf_program *find_prog_by_sec_insn(const struct bpf_object *obj,
[ ... ]
> +static int bpf_prog_collect_cleanup_info(struct bpf_object *obj,
> + struct bpf_program *prog)
> +{
> + size_t i;
> + int j;
> +
> + for (i = 0; i < obj->cleanup_rec_cnt; i++) {
> + struct cleanup_raw_rec *raw = &obj->cleanup_recs[i];
> + struct bpf_program *owner = NULL;
> + struct bpf_cleanup_info ci = {};
> + __u32 *fields = (__u32 *)&ci;
> + void *tmp;
> +
> + for (j = 0; j < CLEANUP_REC_FIELDS; j++) {
> + size_t idx = raw->insn_idx[j], final;
> + struct bpf_program *p;
[ ... ]
> + if (owner == prog) {
> + final = raw->insn_idx[j] - prog->sec_insn_off;
> + } else if (prog_is_subprog(obj, owner) && owner->sub_insn_off) {
> + /* sub_insn_off is where this subprogram was
> + * appended to the main program being relocated;
> + * zero means it is not part of it.
> + */
> + final = owner->sub_insn_off +
> + raw->insn_idx[j] - owner->sec_insn_off;
> + } else {
> + owner = NULL;
> + break;
> + }
> + fields[j] = final;
[Severity: Low]
Is it safe to cast a pointer to a struct field into an array pointer and access
subsequent members via pointer arithmetic in this loop?
The struct bpf_cleanup_info fields are populated by casting a pointer to the
struct to a __u32 * array and indexing into it in a loop.
According to C11 6.5.6, pointer arithmetic on a pointer to a scalar (the first
struct field) only allows accessing up to one element past it, making fields[1]
and fields[2] undefined behavior.
This can trigger compiler warnings (-Warray-bounds) and potentially cause
aggressive optimizers to generate incorrect code.
> + }
> + if (!owner)
> + continue;
> +
> + tmp = libbpf_reallocarray(prog->cleanup_info, prog->cleanup_info_cnt + 1,
> + sizeof(*prog->cleanup_info));
> + if (!tmp)
> + return -ENOMEM;
> + prog->cleanup_info = tmp;
> + prog->cleanup_info_rec_size = sizeof(struct bpf_cleanup_info);
> + prog->cleanup_info[prog->cleanup_info_cnt++] = ci;
> +
> + pr_debug("prog '%s': cleanup region [%u,%u) -> landing pad %u\n",
> + prog->name, ci.begin_off, ci.end_off, ci.landing_pad_off);
> + }
> +
> + qsort(prog->cleanup_info, prog->cleanup_info_cnt,
> + sizeof(*prog->cleanup_info), cmp_cleanup_info);
[Severity: Medium]
Can this unconditionally call qsort() with a NULL base pointer?
If obj->cleanup_rec_cnt is 0, or if none of the records match the program,
prog->cleanup_info_cnt remains 0 and prog->cleanup_info will be NULL.
Calling qsort() with a NULL pointer invokes undefined behavior under C11 7.1.4,
even if the element count is 0. This triggers UBSAN errors (nonnull attribute
violation in libc headers) and can fail runtime checks.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260917055645.3926444-1-yonghong.song@linux.dev?part=15
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 15/20] libbpf: Collect .bpf_cleanup records and pass them to the kernel
2026-09-17 6:12 ` sashiko-bot
@ 2026-09-18 3:44 ` Yonghong Song
0 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-18 3:44 UTC (permalink / raw)
To: sashiko-reviews; +Cc: bpf
On 9/16/26 11:12 PM, sashiko-bot@kernel.org wrote:
> Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
> - [Medium] bpf: undefined behavior when calling qsort with a NULL pointer
> - [Low] bpf: array bounds violation via type-punned pointer arithmetic
> --
>
> commit 1e591245d7ec663b872eae44c8fa7f02cfd956a4
> Author: Yonghong Song <yonghong.song@linux.dev>
>
> libbpf: Collect .bpf_cleanup records and pass them to the kernel
>
> This commit parses the compiler-emitted .bpf_cleanup section and hands
> the resulting table to BPF_PROG_LOAD so the kernel can resolve exceptions.
>
>> diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
>> index ea1c09fa37939..d7cb93a70f58d 100644
>> --- a/tools/lib/bpf/libbpf.c
>> +++ b/tools/lib/bpf/libbpf.c
> [ ... ]
>
>> @@ -4847,6 +4885,214 @@ static struct bpf_program *find_prog_by_sec_insn(const struct bpf_object *obj,
> [ ... ]
>
>> +static int bpf_prog_collect_cleanup_info(struct bpf_object *obj,
>> + struct bpf_program *prog)
>> +{
>> + size_t i;
>> + int j;
>> +
>> + for (i = 0; i < obj->cleanup_rec_cnt; i++) {
>> + struct cleanup_raw_rec *raw = &obj->cleanup_recs[i];
>> + struct bpf_program *owner = NULL;
>> + struct bpf_cleanup_info ci = {};
>> + __u32 *fields = (__u32 *)&ci;
>> + void *tmp;
>> +
>> + for (j = 0; j < CLEANUP_REC_FIELDS; j++) {
>> + size_t idx = raw->insn_idx[j], final;
>> + struct bpf_program *p;
> [ ... ]
>
>> + if (owner == prog) {
>> + final = raw->insn_idx[j] - prog->sec_insn_off;
>> + } else if (prog_is_subprog(obj, owner) && owner->sub_insn_off) {
>> + /* sub_insn_off is where this subprogram was
>> + * appended to the main program being relocated;
>> + * zero means it is not part of it.
>> + */
>> + final = owner->sub_insn_off +
>> + raw->insn_idx[j] - owner->sec_insn_off;
>> + } else {
>> + owner = NULL;
>> + break;
>> + }
>> + fields[j] = final;
> [Severity: Low]
> Is it safe to cast a pointer to a struct field into an array pointer and access
> subsequent members via pointer arithmetic in this loop?
>
> The struct bpf_cleanup_info fields are populated by casting a pointer to the
> struct to a __u32 * array and indexing into it in a loop.
>
> According to C11 6.5.6, pointer arithmetic on a pointer to a scalar (the first
> struct field) only allows accessing up to one element past it, making fields[1]
> and fields[2] undefined behavior.
>
> This can trigger compiler warnings (-Warray-bounds) and potentially cause
> aggressive optimizers to generate incorrect code.
Yes, the code is correct but it is awkward and my trigger compiler warnings with
additional compiler flag. Will make it explicit with bpf_cleanup_info fields.
>
>> + }
>> + if (!owner)
>> + continue;
>> +
>> + tmp = libbpf_reallocarray(prog->cleanup_info, prog->cleanup_info_cnt + 1,
>> + sizeof(*prog->cleanup_info));
>> + if (!tmp)
>> + return -ENOMEM;
>> + prog->cleanup_info = tmp;
>> + prog->cleanup_info_rec_size = sizeof(struct bpf_cleanup_info);
>> + prog->cleanup_info[prog->cleanup_info_cnt++] = ci;
>> +
>> + pr_debug("prog '%s': cleanup region [%u,%u) -> landing pad %u\n",
>> + prog->name, ci.begin_off, ci.end_off, ci.landing_pad_off);
>> + }
>> +
>> + qsort(prog->cleanup_info, prog->cleanup_info_cnt,
>> + sizeof(*prog->cleanup_info), cmp_cleanup_info);
> [Severity: Medium]
> Can this unconditionally call qsort() with a NULL base pointer?
You are right. It is possible prog->cleanup_info_cnt is 0 and in such cases,
cleanup_info will be NULL. Will add a condition like 'prog->cleanup_info_cnt > 0'.
>
> If obj->cleanup_rec_cnt is 0, or if none of the records match the program,
> prog->cleanup_info_cnt remains 0 and prog->cleanup_info will be NULL.
>
> Calling qsort() with a NULL pointer invokes undefined behavior under C11 7.1.4,
> even if the element count is 0. This triggers UBSAN errors (nonnull attribute
> violation in libc headers) and can fail runtime checks.
>
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH bpf-next 16/20] libbpf: Carry the exception cleanup table through the light skeleton
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (14 preceding siblings ...)
2026-09-17 5:58 ` [PATCH bpf-next 15/20] libbpf: Collect .bpf_cleanup records and pass them to the kernel Yonghong Song
@ 2026-09-17 5:58 ` Yonghong Song
2026-09-17 6:18 ` sashiko-bot
2026-09-17 5:58 ` [PATCH bpf-next 17/20] libbpf: Let the static linker carry .bpf_cleanup relocations Yonghong Song
` (3 subsequent siblings)
19 siblings, 1 reply; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:58 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
A light skeleton does not call bpf_prog_load(). bpf_gen__prog_load() builds
its own union bpf_attr field by field, and the loader program it emits is
what issues BPF_PROG_LOAD when the skeleton runs -- so a program loaded
this way reached the kernel without the table the previous patch collected
for it. The load then fails, because the landing pads are code nothing
reaches and the verifier says so. It says "unreachable insn", which names
neither the skeleton nor the table.
Carry it the way func_info and line_info are carried: the records go into
the loader's blob of bytes, the count and record size into the attr, and a
relocation stores the blob's address into attr.cleanup_info once that
address is known. The attr grows to its new last field, cleanup_info_cnt.
Records are 4-byte fields like the other info blobs, so a cross-endian
build has to swap them too.
The kfunc names take the same detour. The light skeleton writes the name
into the blob for the loader program to resolve when it runs, rather than
resolving it against the kernel's BTF while libbpf runs, so the name
recorded there has to go through kern_extern_name() as well.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
tools/lib/bpf/gen_loader.c | 27 +++++++++++++++++++++++----
tools/lib/bpf/libbpf.c | 4 ++--
tools/lib/bpf/libbpf_internal.h | 7 +++++++
3 files changed, 32 insertions(+), 6 deletions(-)
diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index af3a04f161ac..e9bb282a557a 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -981,13 +981,15 @@ static void cleanup_relos(struct bpf_gen *gen, int insns)
cleanup_core_relo(gen);
}
-/* Convert func, line, and core relo info blobs to target endianness */
+/* Convert func, line, core relo and cleanup info blobs to target endianness */
static void info_blob_bswap(struct bpf_gen *gen, int func_info, int line_info,
- int core_relos, struct bpf_prog_load_opts *load_attr)
+ int core_relos, int cleanup_info,
+ struct bpf_prog_load_opts *load_attr)
{
struct bpf_func_info *fi = gen->data_start + func_info;
struct bpf_line_info *li = gen->data_start + line_info;
struct bpf_core_relo *cr = gen->data_start + core_relos;
+ struct bpf_cleanup_info *ci = gen->data_start + cleanup_info;
int i;
for (i = 0; i < load_attr->func_info_cnt; i++)
@@ -998,6 +1000,9 @@ static void info_blob_bswap(struct bpf_gen *gen, int func_info, int line_info,
for (i = 0; i < gen->core_relo_cnt; i++)
bpf_core_relo_bswap(cr++);
+
+ for (i = 0; i < load_attr->cleanup_info_cnt; i++)
+ bpf_cleanup_info_bswap(ci++);
}
void bpf_gen__prog_load(struct bpf_gen *gen,
@@ -1011,8 +1016,11 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
load_attr->line_info_rec_size;
int core_relo_tot_sz = gen->core_relo_cnt *
sizeof(struct bpf_core_relo);
+ int cleanup_info_tot_sz = load_attr->cleanup_info_cnt *
+ load_attr->cleanup_info_rec_size;
int prog_load_attr, license_off, insns_off, func_info, line_info, core_relos;
- int attr_size = offsetofend(union bpf_attr, core_relo_rec_size);
+ int attr_size = offsetofend(union bpf_attr, cleanup_info_cnt);
+ int cleanup_info;
union bpf_attr attr;
memset(&attr, 0, attr_size);
@@ -1061,9 +1069,17 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
core_relos, gen->core_relo_cnt,
sizeof(struct bpf_core_relo));
+ attr.cleanup_info_rec_size = tgt_endian(load_attr->cleanup_info_rec_size);
+ attr.cleanup_info_cnt = tgt_endian(load_attr->cleanup_info_cnt);
+ cleanup_info = add_data(gen, load_attr->cleanup_info, cleanup_info_tot_sz);
+ pr_debug("gen: prog_load: cleanup_info: off %d cnt %u rec size %u\n",
+ cleanup_info, load_attr->cleanup_info_cnt,
+ load_attr->cleanup_info_rec_size);
+
/* convert all info blobs to target endianness */
if (gen->swapped_endian && !gen->error)
- info_blob_bswap(gen, func_info, line_info, core_relos, load_attr);
+ info_blob_bswap(gen, func_info, line_info, core_relos, cleanup_info,
+ load_attr);
libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
prog_load_attr = add_data(gen, &attr, attr_size);
@@ -1085,6 +1101,9 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
/* populate union bpf_attr with a pointer to core_relos */
emit_rel_store(gen, attr_field(prog_load_attr, core_relos), core_relos);
+ /* populate union bpf_attr with a pointer to cleanup_info */
+ emit_rel_store(gen, attr_field(prog_load_attr, cleanup_info), cleanup_info);
+
/* populate union bpf_attr fd_array with a pointer to data where map_fds are saved */
emit_rel_store(gen, attr_field(prog_load_attr, fd_array), gen->fd_array);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d7cb93a70f58..ebb21c9cdfe0 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8632,12 +8632,12 @@ static int bpf_program_record_relos(struct bpf_program *prog)
continue;
kind = btf_is_var(btf__type_by_id(obj->btf, ext->btf_id)) ?
BTF_KIND_VAR : BTF_KIND_FUNC;
- bpf_gen__record_extern(obj->gen_loader, ext->name,
+ bpf_gen__record_extern(obj->gen_loader, kern_extern_name(ext->name),
ext->is_weak, !ext->ksym.type_id,
true, kind, relo->insn_idx);
break;
case RELO_EXTERN_CALL:
- bpf_gen__record_extern(obj->gen_loader, ext->name,
+ bpf_gen__record_extern(obj->gen_loader, kern_extern_name(ext->name),
ext->is_weak, false, false, BTF_KIND_FUNC,
relo->insn_idx);
break;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 3ba6d9090368..78519f24fb40 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -572,6 +572,13 @@ static inline void bpf_core_relo_bswap(struct bpf_core_relo *i)
i->kind = bswap_32(i->kind);
}
+static inline void bpf_cleanup_info_bswap(struct bpf_cleanup_info *i)
+{
+ i->begin_off = bswap_32(i->begin_off);
+ i->end_off = bswap_32(i->end_off);
+ i->landing_pad_off = bswap_32(i->landing_pad_off);
+}
+
enum btf_field_iter_kind {
BTF_FIELD_ITER_IDS,
BTF_FIELD_ITER_STRS,
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 16/20] libbpf: Carry the exception cleanup table through the light skeleton
2026-09-17 5:58 ` [PATCH bpf-next 16/20] libbpf: Carry the exception cleanup table through the light skeleton Yonghong Song
@ 2026-09-17 6:18 ` sashiko-bot
2026-09-18 3:52 ` Yonghong Song
0 siblings, 1 reply; 40+ messages in thread
From: sashiko-bot @ 2026-09-17 6:18 UTC (permalink / raw)
To: Yonghong Song; +Cc: bpf
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] libbpf: unconditional cleanup_info emission breaks backward compatibility on older kernels
- [Medium] libbpf: integer overflow in cleanup_info size calculation leads to OOB read/write
--
commit 076a2794e54df3a939c1a2aebf4467a8a0af5e41
Author: Yonghong Song <yonghong.song@linux.dev>
libbpf: Carry the exception cleanup table through the light skeleton
This commit adds support for carrying the exception cleanup table through
the light skeleton during BPF program loads. It expands the bpf_attr union
to include cleanup_info fields and handles endianness byte-swapping for the
records.
> diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
> index af3a04f161ac1..e9bb282a557a3 100644
> --- a/tools/lib/bpf/gen_loader.c
> +++ b/tools/lib/bpf/gen_loader.c
[ ... ]
> @@ -1011,8 +1016,11 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
> load_attr->line_info_rec_size;
> int core_relo_tot_sz = gen->core_relo_cnt *
> sizeof(struct bpf_core_relo);
> + int cleanup_info_tot_sz = load_attr->cleanup_info_cnt *
> + load_attr->cleanup_info_rec_size;
[Severity: Medium]
Is there a risk of integer overflow here when parsing untrusted ELF files?
If load_attr->cleanup_info_cnt is large enough, the multiplication with
load_attr->cleanup_info_rec_size could overflow the 32-bit signed integer
cleanup_info_tot_sz, resulting in a truncated heap allocation.
Later in info_blob_bswap(), the loop executes load_attr->cleanup_info_cnt
times:
info_blob_bswap() {
...
for (i = 0; i < load_attr->cleanup_info_cnt; i++)
bpf_cleanup_info_bswap(ci++);
}
Could this lead to an out-of-bounds memory read and write over the
truncated buffer, potentially causing memory corruption in userspace
tooling like bpftool?
[ ... ]
> @@ -1085,6 +1101,9 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
> /* populate union bpf_attr with a pointer to core_relos */
> emit_rel_store(gen, attr_field(prog_load_attr, core_relos), core_relos);
>
> + /* populate union bpf_attr with a pointer to cleanup_info */
> + emit_rel_store(gen, attr_field(prog_load_attr, cleanup_info), cleanup_info);
[Severity: High]
Will this unconditional emission cause light skeletons to fail to load on
older kernels?
By unconditionally writing a non-zero pointer (the offset in the data blob)
into the tail of the BPF attribute structure, older target kernels that do
not support the cleanup_info field might reject the BPF_PROG_LOAD syscall.
Because sys_bpf verifies that all fields beyond its known sizeof(union
bpf_attr) are zero using bpf_check_uarg_tail_zero(), it seems this could
fail with -E2BIG. Does this break backward compatibility for all light
skeletons running on older kernels, even those that do not use exceptions?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260917055645.3926444-1-yonghong.song@linux.dev?part=16
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 16/20] libbpf: Carry the exception cleanup table through the light skeleton
2026-09-17 6:18 ` sashiko-bot
@ 2026-09-18 3:52 ` Yonghong Song
0 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-18 3:52 UTC (permalink / raw)
To: sashiko-reviews; +Cc: bpf
On 9/16/26 11:18 PM, sashiko-bot@kernel.org wrote:
> Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
> - [High] libbpf: unconditional cleanup_info emission breaks backward compatibility on older kernels
> - [Medium] libbpf: integer overflow in cleanup_info size calculation leads to OOB read/write
> --
>
> commit 076a2794e54df3a939c1a2aebf4467a8a0af5e41
> Author: Yonghong Song <yonghong.song@linux.dev>
>
> libbpf: Carry the exception cleanup table through the light skeleton
>
> This commit adds support for carrying the exception cleanup table through
> the light skeleton during BPF program loads. It expands the bpf_attr union
> to include cleanup_info fields and handles endianness byte-swapping for the
> records.
>
>> diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
>> index af3a04f161ac1..e9bb282a557a3 100644
>> --- a/tools/lib/bpf/gen_loader.c
>> +++ b/tools/lib/bpf/gen_loader.c
> [ ... ]
>> @@ -1011,8 +1016,11 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
>> load_attr->line_info_rec_size;
>> int core_relo_tot_sz = gen->core_relo_cnt *
>> sizeof(struct bpf_core_relo);
>> + int cleanup_info_tot_sz = load_attr->cleanup_info_cnt *
>> + load_attr->cleanup_info_rec_size;
> [Severity: Medium]
> Is there a risk of integer overflow here when parsing untrusted ELF files?
>
> If load_attr->cleanup_info_cnt is large enough, the multiplication with
> load_attr->cleanup_info_rec_size could overflow the 32-bit signed integer
> cleanup_info_tot_sz, resulting in a truncated heap allocation.
We should be okay here. In add_data, we will see:
static int add_data(struct bpf_gen *gen, const void *data, __u32 size)
{
__u64 zero = 0;
__u32 size8;
void *prev;
if (size > INT32_MAX) {
gen->error = -ERANGE;
return 0;
}
size8 = roundup(size, 8);
...
}
So size guarding above prevents integer overflow. add_data() also
applies to func_info_tot_sz, line_info_tot_sz, core_relo_tot_sz and
here cleanup_info_tot_sz.
>
> Later in info_blob_bswap(), the loop executes load_attr->cleanup_info_cnt
> times:
>
> info_blob_bswap() {
> ...
> for (i = 0; i < load_attr->cleanup_info_cnt; i++)
> bpf_cleanup_info_bswap(ci++);
> }
>
> Could this lead to an out-of-bounds memory read and write over the
> truncated buffer, potentially causing memory corruption in userspace
> tooling like bpftool?
>
> [ ... ]
>> @@ -1085,6 +1101,9 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
>> /* populate union bpf_attr with a pointer to core_relos */
>> emit_rel_store(gen, attr_field(prog_load_attr, core_relos), core_relos);
>>
>> + /* populate union bpf_attr with a pointer to cleanup_info */
>> + emit_rel_store(gen, attr_field(prog_load_attr, cleanup_info), cleanup_info);
> [Severity: High]
> Will this unconditional emission cause light skeletons to fail to load on
> older kernels?
You are right. We cannot unconditional emit. We can only do emit
if cleanup_info_cnt > 0.
>
> By unconditionally writing a non-zero pointer (the offset in the data blob)
> into the tail of the BPF attribute structure, older target kernels that do
> not support the cleanup_info field might reject the BPF_PROG_LOAD syscall.
>
> Because sys_bpf verifies that all fields beyond its known sizeof(union
> bpf_attr) are zero using bpf_check_uarg_tail_zero(), it seems this could
> fail with -E2BIG. Does this break backward compatibility for all light
> skeletons running on older kernels, even those that do not use exceptions?
>
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH bpf-next 17/20] libbpf: Let the static linker carry .bpf_cleanup relocations
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (15 preceding siblings ...)
2026-09-17 5:58 ` [PATCH bpf-next 16/20] libbpf: Carry the exception cleanup table through the light skeleton Yonghong Song
@ 2026-09-17 5:58 ` Yonghong Song
2026-09-17 6:16 ` sashiko-bot
2026-09-17 5:58 ` [PATCH bpf-next 18/20] selftests/bpf: Add an end-to-end .bpf_cleanup exception test Yonghong Song
` (2 subsequent siblings)
19 siblings, 1 reply; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:58 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
An object that carries a compiler-emitted exception cleanup table cannot be
linked today. The table's fields are byte offsets into a code section,
materialised by a 32-bit relocation against that section's symbol with the
offset itself as the implicit addend, and the linker rejects both halves of
that: the relocation type is not in the list it accepts, and a relocation
against an STT_SECTION symbol from a non-executable section is an outright
error.
Both spellings of that relocation have to be taken. LLVM emits
R_BPF_64_NODYLD32 for a .long against a section symbol; GNU as emits
R_BPF_64_ABS32, which is what bpf_reloc_type_lookup() maps BFD_RELOC_32 to.
They describe the same value, and the selftests are built with both
compilers.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
tools/lib/bpf/linker.c | 19 ++++++++++++++++++-
1 file changed, 18 insertions(+), 1 deletion(-)
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index 78f92c39290a..e5c06023cb5b 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -1036,7 +1036,8 @@ static int linker_sanity_check_elf_relos(struct src_obj *obj, struct src_sec *se
size_t sym_type = ELF64_R_TYPE(relo->r_info);
if (sym_type != R_BPF_64_64 && sym_type != R_BPF_64_32 &&
- sym_type != R_BPF_64_ABS64 && sym_type != R_BPF_64_ABS32) {
+ sym_type != R_BPF_64_ABS64 && sym_type != R_BPF_64_ABS32 &&
+ sym_type != R_BPF_64_NODYLD32) {
pr_warn("ELF relo #%d in section #%zu has unexpected type %zu in %s\n",
i, sec->sec_idx, sym_type, obj->filename);
return -EINVAL;
@@ -2274,6 +2275,22 @@ static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *ob
insn->imm += sec->dst_off / sizeof(struct bpf_insn);
else
insn->imm += sec->dst_off;
+ } else if (sym_type == R_BPF_64_NODYLD32 ||
+ sym_type == R_BPF_64_ABS32) {
+ __u32 *val;
+
+ /* Two spellings of the one thing: LLVM
+ * emits NODYLD32 for a .long against a
+ * section symbol, GNU as emits ABS32
+ * (bpf_reloc_type_lookup() maps
+ * BFD_RELOC_32 to it), and the value
+ * they describe is the same.
+ */
+ val = dst_linked_sec->raw_data + dst_rel->r_offset;
+ if (linker->swapped_endian)
+ *val = bswap_32(bswap_32(*val) + sec->dst_off);
+ else
+ *val += sec->dst_off;
} else {
pr_warn("relocation against STT_SECTION in non-exec section is not supported!\n");
return -EINVAL;
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 17/20] libbpf: Let the static linker carry .bpf_cleanup relocations
2026-09-17 5:58 ` [PATCH bpf-next 17/20] libbpf: Let the static linker carry .bpf_cleanup relocations Yonghong Song
@ 2026-09-17 6:16 ` sashiko-bot
2026-09-18 3:58 ` Yonghong Song
0 siblings, 1 reply; 40+ messages in thread
From: sashiko-bot @ 2026-09-17 6:16 UTC (permalink / raw)
To: Yonghong Song; +Cc: bpf
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] libbpf: unaligned memory access in linker for 32-bit relocations
--
commit 408d36d153c1766697801912b5eb3e8087995ef9
Author: Yonghong Song <yonghong.song@linux.dev>
libbpf: Let the static linker carry .bpf_cleanup relocations
This commit allows the BPF static linker to process 32-bit relocations
against non-executable sections by handling R_BPF_64_NODYLD32 and
R_BPF_64_ABS32 relocation types. It updates the 32-bit values directly in
the raw data of the relocated section.
> diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
> index 78f92c39290af..e5c06023cb5b1 100644
> --- a/tools/lib/bpf/linker.c
> +++ b/tools/lib/bpf/linker.c
[ ... ]
> @@ -2274,6 +2275,22 @@ static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *ob
> insn->imm += sec->dst_off / sizeof(struct bpf_insn);
> else
> insn->imm += sec->dst_off;
> + } else if (sym_type == R_BPF_64_NODYLD32 ||
> + sym_type == R_BPF_64_ABS32) {
> + __u32 *val;
> +
> + /* Two spellings of the one thing: LLVM
> + * emits NODYLD32 for a .long against a
> + * section symbol, GNU as emits ABS32
> + * (bpf_reloc_type_lookup() maps
> + * BFD_RELOC_32 to it), and the value
> + * they describe is the same.
> + */
> + val = dst_linked_sec->raw_data + dst_rel->r_offset;
> + if (linker->swapped_endian)
> + *val = bswap_32(bswap_32(*val) + sec->dst_off);
> + else
> + *val += sec->dst_off;
[Severity: Medium]
Can this lead to an unaligned memory access crash?
The static linker processes these 32-bit relocations against non-executable
sections by casting the relocated offset to a 32-bit integer pointer and
directly dereferencing it.
If a user supplies a malformed BPF object file with an unaligned relocation
offset, this could result in undefined behavior and a crash (SIGBUS) on
host architectures with strict alignment requirements.
Should linker_sanity_check_elf_relos() be updated to ensure the relocation
offset is a multiple of 4 for non-executable sections, similar to how it
checks alignment for SHF_EXECINSTR sections?
tools/lib/bpf/linker.c:linker_sanity_check_elf_relos() {
if (link_sec->shdr->sh_flags & SHF_EXECINSTR) {
if (relo->r_offset % sizeof(struct bpf_insn) != 0) {
pr_warn("ELF relo #%d in section #%zu points to missing symbol #%zu in %s\n",
i, sec->sec_idx, sym_idx, obj->filename);
return -EINVAL;
}
}
}
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260917055645.3926444-1-yonghong.song@linux.dev?part=17
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 17/20] libbpf: Let the static linker carry .bpf_cleanup relocations
2026-09-17 6:16 ` sashiko-bot
@ 2026-09-18 3:58 ` Yonghong Song
0 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-18 3:58 UTC (permalink / raw)
To: sashiko-reviews; +Cc: bpf
On 9/16/26 11:16 PM, sashiko-bot@kernel.org wrote:
> Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
> - [Medium] libbpf: unaligned memory access in linker for 32-bit relocations
> --
>
> commit 408d36d153c1766697801912b5eb3e8087995ef9
> Author: Yonghong Song <yonghong.song@linux.dev>
>
> libbpf: Let the static linker carry .bpf_cleanup relocations
>
> This commit allows the BPF static linker to process 32-bit relocations
> against non-executable sections by handling R_BPF_64_NODYLD32 and
> R_BPF_64_ABS32 relocation types. It updates the 32-bit values directly in
> the raw data of the relocated section.
>
>> diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
>> index 78f92c39290af..e5c06023cb5b1 100644
>> --- a/tools/lib/bpf/linker.c
>> +++ b/tools/lib/bpf/linker.c
> [ ... ]
>
>> @@ -2274,6 +2275,22 @@ static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *ob
>> insn->imm += sec->dst_off / sizeof(struct bpf_insn);
>> else
>> insn->imm += sec->dst_off;
>> + } else if (sym_type == R_BPF_64_NODYLD32 ||
>> + sym_type == R_BPF_64_ABS32) {
>> + __u32 *val;
>> +
>> + /* Two spellings of the one thing: LLVM
>> + * emits NODYLD32 for a .long against a
>> + * section symbol, GNU as emits ABS32
>> + * (bpf_reloc_type_lookup() maps
>> + * BFD_RELOC_32 to it), and the value
>> + * they describe is the same.
>> + */
>> + val = dst_linked_sec->raw_data + dst_rel->r_offset;
>> + if (linker->swapped_endian)
>> + *val = bswap_32(bswap_32(*val) + sec->dst_off);
>> + else
>> + *val += sec->dst_off;
> [Severity: Medium]
> Can this lead to an unaligned memory access crash?
>
> The static linker processes these 32-bit relocations against non-executable
> sections by casting the relocated offset to a 32-bit integer pointer and
> directly dereferencing it.
>
> If a user supplies a malformed BPF object file with an unaligned relocation
> offset, this could result in undefined behavior and a crash (SIGBUS) on
> host architectures with strict alignment requirements.
This only happen for a malformed BPF object file and we don't care if
the BPF object file is indeed malformed.
>
> Should linker_sanity_check_elf_relos() be updated to ensure the relocation
> offset is a multiple of 4 for non-executable sections, similar to how it
> checks alignment for SHF_EXECINSTR sections?
>
> tools/lib/bpf/linker.c:linker_sanity_check_elf_relos() {
> if (link_sec->shdr->sh_flags & SHF_EXECINSTR) {
> if (relo->r_offset % sizeof(struct bpf_insn) != 0) {
> pr_warn("ELF relo #%d in section #%zu points to missing symbol #%zu in %s\n",
> i, sec->sec_idx, sym_idx, obj->filename);
> return -EINVAL;
> }
> }
> }
>
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH bpf-next 18/20] selftests/bpf: Add an end-to-end .bpf_cleanup exception test
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (16 preceding siblings ...)
2026-09-17 5:58 ` [PATCH bpf-next 17/20] libbpf: Let the static linker carry .bpf_cleanup relocations Yonghong Song
@ 2026-09-17 5:58 ` Yonghong Song
2026-09-17 6:12 ` sashiko-bot
2026-09-17 5:58 ` [PATCH bpf-next 19/20] selftests/bpf: Cover the exception cleanup shapes the chain does not reach Yonghong Song
2026-09-17 5:58 ` [PATCH bpf-next 20/20] selftests/bpf: Load an exception cleanup program from a light skeleton Yonghong Song
19 siblings, 1 reply; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:58 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
C has no unwinding, so nothing here comes out of the frontend: the frames
that own a resource are written as __naked inline assembly, which spells
out by hand exactly what a frontend emits -- a call site bracketed by two
labels, a landing pad unreachable in the compiler's CFG, and a .bpf_cleanup
record tying them together. The assembler turns ".long <text label>" into
the same R_BPF_64_NODYLD32 relocation the BPF AsmPrinter emits, so libbpf
and the kernel see an object indistinguishable from a compiler-generated
one.
Call chain: entry -> foo1 -> foo1v -> foo2 -> foo3. foo3 holds a
non-preemptible section and throws inside it; foo2 holds an RCU read lock
and has two call sites sharing one pad, one of them its own throw; foo1v is
a void frame whose pad ends in a jump to a resume block placed after an
unrelated block that ends in a plain exit; foo1 owns nothing and gets no
record; entry is the boundary.
There are also some shapes the kernel refuses -- the ones with no correct
answer, and the ones a pad running on the bpf_throw() walker's stack cannot
express -- plus the return-value rejection that delivering an exception at
the boundary of a program type which constrains its return value produces.
The test skips rather than fails where the JIT cannot dispatch a landing
pad at all.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
.../selftests/bpf/exceptions_cleanup.h | 29 +
.../bpf/prog_tests/exceptions_cleanup.c | 79 +++
.../selftests/bpf/progs/exceptions_cleanup.c | 152 +++++
.../bpf/progs/exceptions_cleanup_fail.c | 600 ++++++++++++++++++
4 files changed, 860 insertions(+)
create mode 100644 tools/testing/selftests/bpf/exceptions_cleanup.h
create mode 100644 tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c
create mode 100644 tools/testing/selftests/bpf/progs/exceptions_cleanup.c
create mode 100644 tools/testing/selftests/bpf/progs/exceptions_cleanup_fail.c
diff --git a/tools/testing/selftests/bpf/exceptions_cleanup.h b/tools/testing/selftests/bpf/exceptions_cleanup.h
new file mode 100644
index 000000000000..630d2e207119
--- /dev/null
+++ b/tools/testing/selftests/bpf/exceptions_cleanup.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#ifndef __EXCEPTIONS_CLEANUP_H__
+#define __EXCEPTIONS_CLEANUP_H__
+
+#define THROW_COOKIE 0x100
+
+/* progs/exceptions_cleanup.c: one bit per frame that reports it ran. */
+#define RAN_FOO3_PREEMPT 0x1
+#define RAN_FOO2_RCU 0x2
+#define RAN_FOO1V_PREEMPT 0x4
+#define RAN_FOO2_DROP 0x8
+#define RAN_BUMP 0x10
+
+#define CLEANUP_REC(begin, end, landing_pad) \
+ ".pushsection .bpf_cleanup,\"a\",@progbits;" \
+ ".long " begin ";" \
+ ".long " end ";" \
+ ".long " landing_pad ";" \
+ ".popsection;"
+
+/* Set a bit in @pads_ran. */
+#define PAD_RAN(bit) \
+ "r1 = %[pads_ran] ll;" \
+ "r2 = *(u64 *)(r1 + 0);" \
+ "r2 |= " bit ";" \
+ "*(u64 *)(r1 + 0) = r2;"
+
+#endif /* __EXCEPTIONS_CLEANUP_H__ */
diff --git a/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c b/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c
new file mode 100644
index 000000000000..d1e45b765af2
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include "exceptions_cleanup.h"
+#include "exceptions_cleanup.skel.h"
+#include "exceptions_cleanup_fail.skel.h"
+
+/* foo3 threw: every frame that has a pad ran it. */
+#define PADS_FOO3_THREW \
+ (RAN_FOO3_PREEMPT | RAN_FOO2_RCU | RAN_FOO1V_PREEMPT | RAN_FOO2_DROP)
+
+/* foo2 threw after foo3 returned normally: foo3's pad must not run. */
+#define PADS_FOO2_THREW \
+ (RAN_FOO2_RCU | RAN_FOO1V_PREEMPT | RAN_FOO2_DROP)
+
+static void run(struct exceptions_cleanup *skel, __u64 input, __u32 retval,
+ __u64 pads)
+{
+ __u64 ctx = 0;
+ int err;
+
+ LIBBPF_OPTS(bpf_test_run_opts, topts,
+ .ctx_in = &ctx,
+ .ctx_size_in = sizeof(ctx),
+ );
+
+ skel->bss->input = input;
+ skel->bss->pads_ran = 0;
+ skel->bss->result = 0;
+
+ err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.entry), &topts);
+ if (!ASSERT_OK(err, "run"))
+ return;
+ ASSERT_EQ(topts.retval, retval, "retval");
+ ASSERT_EQ(skel->bss->pads_ran, pads | RAN_BUMP, "pads_ran");
+}
+
+void test_exceptions_cleanup(void)
+{
+ char log[8192] = {};
+ LIBBPF_OPTS(bpf_object_open_opts, opts,
+ .kernel_log_buf = log,
+ .kernel_log_size = sizeof(log));
+ struct exceptions_cleanup *skel;
+ int err;
+
+ skel = exceptions_cleanup__open_opts(&opts);
+ if (!ASSERT_OK_PTR(skel, "open"))
+ return;
+
+ err = exceptions_cleanup__load(skel);
+ if (err) {
+ if (err == -EOPNOTSUPP &&
+ strstr(log, "exception cleanup needs a JIT that can dispatch landing pads"))
+ test__skip();
+ else if (!ASSERT_OK(err, "load"))
+ fprintf(stderr, "%s", log);
+ exceptions_cleanup__destroy(skel);
+ return;
+ }
+
+ /* No throw: foo3 returns 1 ^ 1 == 0, foo2 adds one, no pad runs. */
+ if (test__start_subtest("no_throw"))
+ run(skel, 1, 1, 0);
+
+ /* foo3 throws; every pad runs and the cookie is delivered at entry. */
+ if (test__start_subtest("throw_from_foo3"))
+ run(skel, 101, THROW_COOKIE, PADS_FOO3_THREW);
+
+ /* foo3 returns 2 ^ 1 == 3, so foo2 throws from its own second region;
+ * foo3's frame is long gone, so its pad must not run.
+ */
+ if (test__start_subtest("throw_from_foo2"))
+ run(skel, 2, THROW_COOKIE, PADS_FOO2_THREW);
+
+ exceptions_cleanup__destroy(skel);
+
+ RUN_TESTS(exceptions_cleanup_fail);
+}
diff --git a/tools/testing/selftests/bpf/progs/exceptions_cleanup.c b/tools/testing/selftests/bpf/progs/exceptions_cleanup.c
new file mode 100644
index 000000000000..95199a2828fa
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/exceptions_cleanup.c
@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "exceptions_cleanup.h"
+
+static __used __noinline void __kfunc_btf_anchor(void)
+{
+ bpf_throw(0);
+ bpf_rcu_read_lock();
+ bpf_rcu_read_unlock();
+ bpf_preempt_disable();
+ bpf_preempt_enable();
+ bpf_unwind_resume();
+}
+
+__u64 input = 0;
+__u64 pads_ran = 0;
+__u64 result = 0;
+
+static __used __noinline __u64 foo3(__u64 x)
+{
+ bpf_preempt_disable();
+ if (x > 100)
+ asm volatile (
+ "r1 = %[cookie];"
+ "1:" "call bpf_throw;" /* cleanup region */
+ "2:"
+ "goto 3f;"
+ "4:" /* landing pad */
+ "r7 = r0;"
+ "call bpf_preempt_enable;"
+ PAD_RAN("%[ran]")
+ "r1 = r7;"
+ "call bpf_unwind_resume;"
+ "3:"
+ CLEANUP_REC("1b", "2b", "4b")
+ :
+ : [cookie]"i"(THROW_COOKIE), [ran]"i"(RAN_FOO3_PREEMPT),
+ __imm_addr(pads_ran)
+ : __clobber_all);
+ bpf_preempt_enable();
+ return x ^ 1;
+}
+
+__u64 never = 0;
+
+static __used __naked __noinline void drop_glue(void)
+{
+ asm volatile (
+ PAD_RAN("%[ran]")
+ "exit;"
+ :
+ : [ran]"i"(RAN_FOO2_DROP), __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+static __used __naked __noinline __u64 foo2(void)
+{
+ asm volatile (
+ "r6 = r1;"
+ "call bpf_rcu_read_lock;"
+ "r1 = r6;"
+"1:" "call foo3;" /* cleanup region #1 */
+"2:"
+ "r6 = r0;"
+ "if r6 == 0 goto 5f;"
+ "r1 = %[cookie];"
+"3:" "call bpf_throw;" /* cleanup region #2 */
+"4:"
+ "r0 = 0;"
+ "exit;"
+"5:"
+ "call bpf_rcu_read_unlock;"
+ "r0 = r6;"
+ "r0 += 1;"
+ "exit;"
+"6:" /* landing pad, shared by both regions */
+ "call drop_glue;"
+ "call bpf_rcu_read_unlock;"
+ PAD_RAN("%[ran_rcu]")
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "6b")
+ CLEANUP_REC("3b", "4b", "6b")
+ :
+ : [cookie]"i"(THROW_COOKIE), [ran_rcu]"i"(RAN_FOO2_RCU),
+ __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+static __used __naked __noinline void foo1v(void)
+{
+ asm volatile (
+ "call bpf_preempt_disable;"
+ "r1 = %[input] ll;"
+ "r1 = *(u64 *)(r1 + 0);"
+"1:" "call foo2;" /* cleanup region */
+"2:"
+ "r6 = r0;"
+ "call bpf_preempt_enable;"
+ "r1 = %[result] ll;"
+ "*(u64 *)(r1 + 0) = r6;"
+ "goto 7f;"
+"8:" /* landing pad */
+ "call bpf_preempt_enable;"
+ PAD_RAN("%[ran]")
+ "goto 9f;"
+"7:" /* the frame's own exit block */
+ "r0 = 0;"
+ "exit;"
+"9:" /* shared resume block */
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "8b")
+ :
+ : [ran]"i"(RAN_FOO1V_PREEMPT), __imm_addr(input),
+ __imm_addr(result), __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+static __used __naked __noinline void bump(void)
+{
+ asm volatile (
+ PAD_RAN("%[ran]")
+ "r1 = %[never] ll;"
+ "r1 = *(u64 *)(r1 + 0);"
+ "if r1 == 0 goto 1f;"
+ "r1 = 0;"
+ "call bpf_throw;"
+"1:"
+ "exit;" /* r0 deliberately left alone */
+ :
+ : [ran]"i"(RAN_BUMP), __imm_addr(never), __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+__noinline __u64 foo1(void)
+{
+ bump();
+ foo1v();
+ return result;
+}
+
+SEC("syscall")
+int entry(void *ctx)
+{
+ return foo1();
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/exceptions_cleanup_fail.c b/tools/testing/selftests/bpf/progs/exceptions_cleanup_fail.c
new file mode 100644
index 000000000000..ce2dac306a84
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/exceptions_cleanup_fail.c
@@ -0,0 +1,600 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_experimental.h"
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+#include "exceptions_cleanup.h"
+
+__u64 input = 0;
+
+static __used __noinline void __kfunc_btf_anchor(void)
+{
+ bpf_throw(0);
+ bpf_preempt_disable();
+ bpf_preempt_enable();
+ bpf_unwind_resume();
+}
+
+/*
+ * 1. A subprogram that may unwind, also used as a helper callback:
+ * bpf_loop()'s own kernel frame would end the walk before it found a
+ * boundary.
+ */
+static int throwing_cb(__u32 idx, void *ctx)
+{
+ bpf_throw(0xbad);
+ return 0;
+}
+
+static __used __naked __noinline __u64 cb_frame(void)
+{
+ asm volatile (
+ "call bpf_preempt_disable;"
+"1:" "call throwing_cb;" /* cleanup region */
+"2:"
+ "call bpf_preempt_enable;"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ "call bpf_preempt_enable;"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ ::: __clobber_all);
+}
+
+SEC("?syscall")
+__failure __msg("may unwind and is used as a callback")
+int callback_may_unwind(void *ctx)
+{
+ bpf_loop(1, throwing_cb, NULL, 0);
+ return cb_frame();
+}
+
+/*
+ * 2. A landing pad that reaches both an unwind resume and a plain exit, so
+ * nothing says whether it is a cleanup pad or a catch pad.
+ */
+static __used __naked __noinline __u64 inner_throw(void)
+{
+ asm volatile (
+ "r1 = 1;"
+ "call bpf_throw;"
+ "r0 = 0;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+static __used __naked __noinline __u64 ambiguous_pad_frame(void)
+{
+ asm volatile (
+ "r6 = r1;"
+ "call bpf_preempt_disable;"
+"1:" "call inner_throw;" /* cleanup region */
+"2:"
+ "call bpf_preempt_enable;"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad: two ways out */
+ "call bpf_preempt_enable;"
+ "if r6 > 10 goto 4f;"
+ "call bpf_unwind_resume;"
+ "exit;"
+"4:"
+ "r0 = 0;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ ::: __clobber_all);
+}
+
+SEC("?syscall")
+__failure __msg("reaches both bpf_unwind_resume() and a plain exit")
+int ambiguous_landing_pad(void *ctx)
+{
+ return ambiguous_pad_frame();
+}
+
+/*
+ * 3. A throw from inside a landing pad: a second walk over the frames the
+ * first one is in the middle of discarding.
+ */
+static __used __naked __noinline __u64 throw_in_pad_frame(void)
+{
+ asm volatile (
+ "call bpf_preempt_disable;"
+"1:" "call inner_throw;" /* cleanup region */
+"2:"
+ "call bpf_preempt_enable;"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad that throws again */
+ "call bpf_preempt_enable;"
+ "r1 = 2;"
+ "call bpf_throw;"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ ::: __clobber_all);
+}
+
+SEC("?syscall")
+__failure __msg("can throw while an exception is in flight")
+int throw_from_landing_pad(void *ctx)
+{
+ return throw_in_pad_frame();
+}
+
+/*
+ * 4. A cleanup table in a program that also installs an exception callback,
+ * two different answers to what runs on the way out.
+ */
+__noinline int unused_exc_cb(u64 cookie)
+{
+ return 0;
+}
+
+static __used __naked __noinline __u64 cb_and_table_frame(void)
+{
+ asm volatile (
+ "call bpf_preempt_disable;"
+ "r1 = 9;"
+"1:" "call bpf_throw;" /* cleanup region */
+"2:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ "call bpf_preempt_enable;"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ ::: __clobber_all);
+}
+
+SEC("?syscall")
+__exception_cb(unused_exc_cb)
+__failure __msg("cannot be combined with an exception callback")
+int table_with_exception_cb(void *ctx)
+{
+ return cb_and_table_frame();
+}
+
+__u64 never;
+
+/*
+ * 5. A landing pad that calls a subprogram which can throw. Not case 3: the
+ * throw is in another subprogram, so what catches it is the walk of the pad's
+ * body, off subprog_info.might_throw.
+ */
+static __used __noinline void pad_callee_that_throws(void)
+{
+ if (never)
+ bpf_throw(0);
+}
+
+static __used __naked __noinline __u64 pad_calls_thrower_frame(void)
+{
+ asm volatile (
+ "call bpf_preempt_disable;"
+ "r1 = 11;"
+"1:" "call bpf_throw;" /* cleanup region */
+"2:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ "call pad_callee_that_throws;" /* ...which can throw: refused */
+ "call bpf_preempt_enable;"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ ::: __clobber_all);
+}
+
+SEC("?syscall")
+__failure __msg("which can throw while an exception is in flight")
+int pad_calls_thrower(void *ctx)
+{
+ return pad_calls_thrower_frame();
+}
+
+/*
+ * 6. A catch pad: it ends in a plain exit rather than a resume, and a walker
+ * that calls pads as subroutines cannot hand a frame back its own execution.
+ */
+static __used __naked __noinline __u64 catch_pad_frame(void)
+{
+ asm volatile (
+ "call bpf_preempt_disable;"
+ "r1 = 12;"
+"1:" "call bpf_throw;" /* cleanup region */
+"2:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* catch pad: no resume, it stops here */
+ "call bpf_preempt_enable;"
+ "r0 = 0;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ ::: __clobber_all);
+}
+
+SEC("?syscall")
+__failure __msg("is not supported yet, only cleanup pads that resume")
+int catch_landing_pad(void *ctx)
+{
+ return catch_pad_frame();
+}
+
+/*
+ * 7. An exception reaching the boundary of a program type that constrains
+ * its return value: delivery makes the cookie that return value, and fentry
+ * has to return 0.
+ */
+static __used __naked __noinline __u64 boundary_throw_frame(void)
+{
+ asm volatile (
+ "call bpf_preempt_disable;"
+ "r1 = 7;"
+"1:" "call bpf_throw;" /* cleanup region */
+"2:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ "call bpf_preempt_enable;"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ ::: __clobber_all);
+}
+
+SEC("?fentry/bpf_fentry_test1")
+__failure __msg("the register R1 has smin=7 smax=7 should have been in [0, 0]")
+int boundary_delivers(void *ctx)
+{
+ return boundary_throw_frame();
+}
+
+/*
+ * 8. A bpf_unwind_resume() outside any landing pad. Both JITs lower it as
+ * the way back out of a pad, which in ordinary code leaves a live frame
+ * standing with its epilogue skipped.
+ */
+static __used __naked __noinline __u64 stray_resume_frame(void)
+{
+ asm volatile (
+ "call bpf_preempt_disable;"
+ "r1 = 13;"
+"1:" "call bpf_throw;" /* cleanup region */
+"2:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ "call bpf_preempt_enable;"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ ::: __clobber_all);
+}
+
+SEC("?syscall")
+__failure __msg("is not in an exception cleanup landing pad")
+int resume_outside_pad(void *ctx)
+{
+ /* Never taken, but reachable, which is all the verifier needs. */
+ if (never)
+ bpf_unwind_resume();
+ return stray_resume_frame();
+}
+
+/*
+ * 9. A bpf_unwind_resume() in a subprogram a landing pad calls. The
+ * verifier's walk cannot tell it from a resume in the pad itself -- an
+ * exception is in flight either way -- so the rule is static: a resume sits in
+ * a pad body.
+ */
+static __used __naked __noinline void resume_in_callee(void)
+{
+ asm volatile (
+ "call bpf_unwind_resume;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+static __used __naked __noinline __u64 pad_calls_resumer_frame(void)
+{
+ asm volatile (
+ "call bpf_preempt_disable;"
+ "r1 = 14;"
+"1:" "call bpf_throw;" /* cleanup region */
+"2:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ "call bpf_preempt_enable;"
+ "call resume_in_callee;" /* ...which resumes: refused */
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ ::: __clobber_all);
+}
+
+SEC("?syscall")
+__failure __msg("is not in an exception cleanup landing pad")
+int resume_in_pad_callee(void *ctx)
+{
+ return pad_calls_resumer_frame();
+}
+
+/*
+ * 10. A bpf_unwind_resume() in a program carrying no cleanup table, where
+ * that static rule does not run at all. do_check() refuses it on the state not
+ * unwinding, and has to: the JITs lower every one of these the same way.
+ */
+static __used __naked __noinline __u64 no_table_resume_frame(void)
+{
+ asm volatile (
+ "call bpf_unwind_resume;"
+ "r0 = 0;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+SEC("?syscall")
+__failure __msg("reached without an exception in flight")
+int resume_without_table(void *ctx)
+{
+ return no_table_resume_frame();
+}
+
+/*
+ * 11. A landing pad that is itself a covered call site, so an exception out
+ * of it would have nowhere to go. Hand-written only: LLVM sinks a function's
+ * pads past every range it emits.
+ */
+static __used __naked __noinline __u64 nested_pad_frame(void)
+{
+ asm volatile (
+ "call bpf_preempt_disable;"
+"1:" "call inner_throw;" /* first cleanup region */
+"2:"
+ "call bpf_preempt_enable;"
+ "r0 = 0;"
+ "exit;"
+"3:" /* first pad, second region's call */
+ "call bpf_preempt_enable;"
+"4:"
+ "call bpf_unwind_resume;"
+ "exit;"
+"5:" /* second pad */
+ "call bpf_preempt_enable;"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ CLEANUP_REC("3b", "4b", "5b")
+ ::: __clobber_all);
+}
+
+SEC("?syscall")
+__failure __msg("is inside the call-site range of")
+int nested_landing_pad(void *ctx)
+{
+ return nested_pad_frame();
+}
+
+/*
+ * 12. A tail call in a landing pad: it unwinds the prologue off the stack
+ * pointer, which in a pad is the walker's.
+ */
+struct {
+ __uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+ __uint(max_entries, 1);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u32));
+} tc_map SEC(".maps");
+
+static __used __naked __noinline __u64 tail_call_pad_frame(void)
+{
+ asm volatile (
+ "r6 = r1;"
+"1:" "call inner_throw;" /* cleanup region */
+"2:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ "r1 = r6;"
+ "r2 = %[tc_map] ll;"
+ "r3 = 0;"
+ "call %[bpf_tail_call];"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : __imm(bpf_tail_call), __imm_addr(tc_map)
+ : __clobber_all);
+}
+
+SEC("?syscall")
+__failure __msg("is in an exception cleanup landing pad")
+int tail_call_in_pad(void *ctx)
+{
+ return tail_call_pad_frame();
+}
+
+#if defined(__BPF_FEATURE_STACK_ARGUMENT)
+
+/*
+ * 13. A call that passes an argument on the stack, in a landing pad: the
+ * outgoing area the callee reads is not the one the caller wrote, the frame
+ * being the unwinding one and the stack pointer the walker's.
+ */
+static __used __noinline __u64 six_args(__u64 a, __u64 b, __u64 c, __u64 d,
+ __u64 e, __u64 f)
+{
+ return a + b + c + d + e + f;
+}
+
+static __used __naked __noinline __u64 stack_arg_pad_frame(void)
+{
+ asm volatile (
+ "call bpf_preempt_disable;"
+"1:" "call inner_throw;" /* cleanup region */
+"2:"
+ "call bpf_preempt_enable;"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ "call bpf_preempt_enable;"
+ "r1 = 1;"
+ "r2 = 2;"
+ "r3 = 3;"
+ "r4 = 4;"
+ "r5 = 5;"
+ "*(u64 *)(r11 - 8) = 6;" /* the sixth argument */
+ "call six_args;"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ ::: __clobber_all);
+}
+
+SEC("?syscall")
+__failure __msg("on-stack call argument in an exception cleanup landing pad")
+int stack_arg_in_pad(void *ctx)
+{
+ return stack_arg_pad_frame();
+}
+
+/*
+ * 14. The same, reached the other way: a kfunc whose by-value argument runs
+ * past the five argument registers, where the JIT fills the outgoing area and
+ * the rule above has no store to catch. The C call gives the extern its BTF.
+ */
+static __used __noinline void __nofit_btf_anchor(void)
+{
+ struct prog_test_pair_arg s = {};
+
+ bpf_kfunc_call_test_pair_arg_nofit(1, 2, 3, 4, s);
+}
+
+static __used __naked __noinline __u64 kfunc_arg_pad_frame(void)
+{
+ asm volatile (
+ "call bpf_preempt_disable;"
+"1:" "call inner_throw;" /* cleanup region */
+"2:"
+ "call bpf_preempt_enable;"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ "call bpf_preempt_enable;"
+ "r1 = 1;"
+ "r2 = 2;"
+ "r3 = 3;"
+ "r4 = 4;"
+ "r5 = 5;"
+ "call bpf_kfunc_call_test_pair_arg_nofit;"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ ::: __clobber_all);
+}
+
+SEC("?syscall")
+__failure __msg("on-stack call argument in an exception cleanup landing pad")
+int kfunc_stack_arg_in_pad(void *ctx)
+{
+ return kfunc_arg_pad_frame();
+}
+
+#endif /* __BPF_FEATURE_STACK_ARGUMENT */
+
+/*
+ * 15. A landing pad entered by ordinary control flow, arriving with none of
+ * what the walker sets up. Nothing static sees it -- the resume really is in a
+ * pad body -- so do_check() refuses it on the state not unwinding.
+ */
+static __used __naked __noinline __u64 jump_into_pad_frame(void)
+{
+ asm volatile (
+ "r1 = %[input] ll;"
+ "r6 = *(u64 *)(r1 + 0);"
+ "if r6 > 7 goto 4f;" /* an ordinary branch into the pad */
+"1:" "call inner_throw;" /* cleanup region */
+"2:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ "r7 = r0;"
+"4:" /* ... and its second instruction */
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : __imm_addr(input)
+ : __clobber_all);
+}
+
+SEC("?syscall")
+__failure __msg("reached without an exception in flight")
+int jump_into_pad(void *ctx)
+{
+ return jump_into_pad_frame();
+}
+
+#if defined(__TARGET_ARCH_x86) || defined(__TARGET_ARCH_arm64)
+
+/*
+ * 16. A landing pad that reaches an indirect jump, which cannot be told from
+ * a catch pad. SEC("socket") because a jump table entry is an offset from the
+ * program's section symbol, and "?syscall" is not a name assembly can use.
+ */
+static __used __naked __noinline void gotox_thrower(void)
+{
+ asm volatile (
+ "r1 = 15;"
+ "call bpf_throw;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+SEC("socket")
+__failure __msg("reaches an indirect jump")
+__naked void gotox_in_pad(void)
+{
+ asm volatile (
+ ".pushsection .jumptables,\"\",@progbits;"
+"jt0_%=:"
+ ".quad l0_%= - socket;"
+ ".quad l1_%= - socket;"
+ ".size jt0_%=, 16;"
+ ".global jt0_%=;"
+ ".popsection;"
+
+"1:" "call gotox_thrower;" /* cleanup region */
+"2:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ "r1 = jt0_%= ll;"
+ "r1 += 8;"
+ "r2 = *(u64 *)(r1 + 0);"
+ /* gotox r2. Spelled as a raw insn on purpose: the "gotox" mnemonic
+ * only reached the LLVM assembler in llvm 22, and BPF_RAW_INSN()
+ * needs <linux/bpf.h>, which this file cannot have -- vmlinux.h
+ * already defines the uapi enums.
+ */
+ ".8byte 0x20d;"
+"l0_%=:"
+ "call bpf_unwind_resume;"
+ "exit;"
+"l1_%=:"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ ::: __clobber_all);
+}
+
+#endif /* x86 || arm64 */
+
+char _license[] SEC("license") = "GPL";
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 18/20] selftests/bpf: Add an end-to-end .bpf_cleanup exception test
2026-09-17 5:58 ` [PATCH bpf-next 18/20] selftests/bpf: Add an end-to-end .bpf_cleanup exception test Yonghong Song
@ 2026-09-17 6:12 ` sashiko-bot
0 siblings, 0 replies; 40+ messages in thread
From: sashiko-bot @ 2026-09-17 6:12 UTC (permalink / raw)
To: Yonghong Song; +Cc: bpf
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] bpf: multi-line comments do not follow subsystem style
--
commit 5918cbd599a9ba7808857475f6ca49093862b54a
Author: Yonghong Song <yonghong.song@linux.dev>
selftests/bpf: Add an end-to-end .bpf_cleanup exception test
This commit adds an end-to-end test for .bpf_cleanup exception handling, using
inline assembly to construct landing pads and cleanup records. It validates
both successful exception propagation scenarios and various edge cases that
the kernel is expected to refuse.
> diff --git a/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c b/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c
> index d1e45b765af26..0000000000000 100644
> --- a/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c
> +++ b/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c
[ ... ]
> + /* foo3 throws; every pad runs and the cookie is delivered at entry. */
> + if (test__start_subtest("throw_from_foo3"))
> + run(skel, 101, THROW_COOKIE, PADS_FOO3_THREW);
> +
> + /* foo3 returns 2 ^ 1 == 3, so foo2 throws from its own second region;
> + * foo3's frame is long gone, so its pad must not run.
> + */
[Severity: Low]
This isn't a bug, but does this multi-line comment follow the BPF subsystem
style? The guidelines prefer placing the opening /* on its own line for
multi-line comments.
> + if (test__start_subtest("throw_from_foo2"))
> + run(skel, 2, THROW_COOKIE, PADS_FOO2_THREW);
> +
> + exceptions_cleanup__destroy(skel);
[ ... ]
> diff --git a/tools/testing/selftests/bpf/progs/exceptions_cleanup_fail.c b/tools/testing/selftests/bpf/progs/exceptions_cleanup_fail.c
> index ce2dac306a84c..0000000000000 100644
> --- a/tools/testing/selftests/bpf/progs/exceptions_cleanup_fail.c
> +++ b/tools/testing/selftests/bpf/progs/exceptions_cleanup_fail.c
[ ... ]
> +"3:" /* landing pad */
> + "r1 = jt0_%= ll;"
> + "r1 += 8;"
> + "r2 = *(u64 *)(r1 + 0);"
> + /* gotox r2. Spelled as a raw insn on purpose: the "gotox" mnemonic
> + * only reached the LLVM assembler in llvm 22, and BPF_RAW_INSN()
> + * needs <linux/bpf.h>, which this file cannot have -- vmlinux.h
> + * already defines the uapi enums.
> + */
[Severity: Low]
This is also not a bug, but does this comment formatting comply with the
subsystem guidelines? Like the previous instance, the preferred BPF style
places the opening /* on a separate line.
> + ".8byte 0x20d;"
> +"l0_%=:"
> + "call bpf_unwind_resume;"
> + "exit;"
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260917055645.3926444-1-yonghong.song@linux.dev?part=18
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH bpf-next 19/20] selftests/bpf: Cover the exception cleanup shapes the chain does not reach
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (17 preceding siblings ...)
2026-09-17 5:58 ` [PATCH bpf-next 18/20] selftests/bpf: Add an end-to-end .bpf_cleanup exception test Yonghong Song
@ 2026-09-17 5:58 ` Yonghong Song
2026-09-17 6:16 ` sashiko-bot
2026-09-17 5:58 ` [PATCH bpf-next 20/20] selftests/bpf: Load an exception cleanup program from a light skeleton Yonghong Song
19 siblings, 1 reply; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:58 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
The end-to-end test walks one call chain with a pad in most of its frames.
This adds the shapes that chain does not reach: a callee called from both a
covered and an uncovered site, a pad that reads its frame's callee-saved
registers, a tail-call-reachable callee, a tail call that is taken, an
extension standing in for a covered call, a pad in the main program's own
frame, a record covering bpf_throw() itself, a record covering only a
nounwind call, a throwing subprogram named by a BPF_PSEUDO_FUNC, a region
ending on a 16-byte instruction, a pad that reloads from and writes to its
own frame, a pad two frames up, a pad that calls a subprogram which tail
calls, an extension carrying a table of its own, and a pad terminated by
_Unwind_Resume rather than bpf_unwind_resume.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
.../selftests/bpf/exceptions_cleanup.h | 20 +
.../bpf/prog_tests/exceptions_cleanup.c | 314 +++++++
.../bpf/progs/exceptions_cleanup_ext_table.c | 48 +
.../bpf/progs/exceptions_cleanup_freplace.c | 17 +
.../progs/exceptions_cleanup_pad_freplace.c | 17 +
.../bpf/progs/exceptions_cleanup_shapes.c | 863 ++++++++++++++++++
6 files changed, 1279 insertions(+)
create mode 100644 tools/testing/selftests/bpf/progs/exceptions_cleanup_ext_table.c
create mode 100644 tools/testing/selftests/bpf/progs/exceptions_cleanup_freplace.c
create mode 100644 tools/testing/selftests/bpf/progs/exceptions_cleanup_pad_freplace.c
create mode 100644 tools/testing/selftests/bpf/progs/exceptions_cleanup_shapes.c
diff --git a/tools/testing/selftests/bpf/exceptions_cleanup.h b/tools/testing/selftests/bpf/exceptions_cleanup.h
index 630d2e207119..5896cf83d15e 100644
--- a/tools/testing/selftests/bpf/exceptions_cleanup.h
+++ b/tools/testing/selftests/bpf/exceptions_cleanup.h
@@ -4,6 +4,7 @@
#define __EXCEPTIONS_CLEANUP_H__
#define THROW_COOKIE 0x100
+#define INNER_COOKIE 0x200
/* progs/exceptions_cleanup.c: one bit per frame that reports it ran. */
#define RAN_FOO3_PREEMPT 0x1
@@ -12,6 +13,25 @@
#define RAN_FOO2_DROP 0x8
#define RAN_BUMP 0x10
+/* progs/exceptions_cleanup_shapes.c: one bit per shape, numbered its own way. */
+#define RAN_SWEEP 0x1
+#define RAN_SHARED 0x2
+#define RAN_REGS 0x4
+#define RAN_TAIL_CALL 0x8
+#define RAN_MAIN_PAD 0x10
+#define RAN_TC_TAKEN 0x20
+#define RAN_FREPLACE 0x40
+#define RAN_ADDR_TAKEN 0x80
+#define RAN_NO_SUBPROG 0x100
+#define RAN_PAD_CALLS 0x200
+#define RAN_PAD_FIRST 0x400
+#define RAN_WIDE_REC 0x800
+#define RAN_PAD_STACK 0x1000
+#define RAN_DEEP_PAD 0x2000
+#define RAN_NOUNWIND_REC 0x4000
+#define RAN_RESUME_ALIAS 0x8000
+#define RAN_PAD_TAIL_CALL 0x10000
+
#define CLEANUP_REC(begin, end, landing_pad) \
".pushsection .bpf_cleanup,\"a\",@progbits;" \
".long " begin ";" \
diff --git a/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c b/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c
index d1e45b765af2..ffc0b9519168 100644
--- a/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c
+++ b/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c
@@ -4,6 +4,10 @@
#include "exceptions_cleanup.h"
#include "exceptions_cleanup.skel.h"
#include "exceptions_cleanup_fail.skel.h"
+#include "exceptions_cleanup_shapes.skel.h"
+#include "exceptions_cleanup_freplace.skel.h"
+#include "exceptions_cleanup_pad_freplace.skel.h"
+#include "exceptions_cleanup_ext_table.skel.h"
/* foo3 threw: every frame that has a pad ran it. */
#define PADS_FOO3_THREW \
@@ -35,6 +39,314 @@ static void run(struct exceptions_cleanup *skel, __u64 input, __u32 retval,
ASSERT_EQ(skel->bss->pads_ran, pads | RAN_BUMP, "pads_ran");
}
+static void run_shape(struct exceptions_cleanup_shapes *skel, struct bpf_program *prog,
+ __u64 input, __u32 retval, __u64 pads)
+{
+ __u64 ctx = 0;
+ int err;
+
+ LIBBPF_OPTS(bpf_test_run_opts, topts,
+ .ctx_in = &ctx,
+ .ctx_size_in = sizeof(ctx),
+ );
+
+ skel->bss->input = input;
+ skel->bss->pads_ran = 0;
+
+ err = bpf_prog_test_run_opts(bpf_program__fd(prog), &topts);
+ if (!ASSERT_OK(err, "run"))
+ return;
+ ASSERT_EQ(topts.retval, retval, "retval");
+ ASSERT_EQ(skel->bss->pads_ran, pads, "pads_ran");
+}
+
+static void test_freplace(struct exceptions_cleanup_shapes *skel)
+{
+ struct exceptions_cleanup_freplace *fr;
+ struct bpf_link *link;
+ int tgt_fd;
+
+ tgt_fd = bpf_program__fd(skel->progs.entry_freplace);
+
+ fr = exceptions_cleanup_freplace__open();
+ if (!ASSERT_OK_PTR(fr, "freplace open"))
+ return;
+
+ if (!ASSERT_OK(bpf_program__set_attach_target(fr->progs.new_fr_callee,
+ tgt_fd, "fr_callee"),
+ "set_attach_target"))
+ goto out;
+ if (!ASSERT_OK(exceptions_cleanup_freplace__load(fr), "freplace load"))
+ goto out;
+
+ link = bpf_program__attach_freplace(fr->progs.new_fr_callee, tgt_fd,
+ "fr_callee");
+ if (!ASSERT_OK_PTR(link, "attach_freplace"))
+ goto out;
+
+ run_shape(skel, skel->progs.entry_freplace, 101, THROW_COOKIE, 0);
+ bpf_link__destroy(link);
+out:
+ exceptions_cleanup_freplace__destroy(fr);
+}
+
+static void test_pad_calls_freplace(struct exceptions_cleanup_shapes *skel)
+{
+ struct exceptions_cleanup_pad_freplace *fr;
+ struct bpf_link *link;
+ __u64 ctx = 0;
+ int tgt_fd, err;
+
+ LIBBPF_OPTS(bpf_test_run_opts, topts,
+ .ctx_in = &ctx,
+ .ctx_size_in = sizeof(ctx),
+ );
+
+ tgt_fd = bpf_program__fd(skel->progs.entry_pad_calls);
+
+ fr = exceptions_cleanup_pad_freplace__open();
+ if (!ASSERT_OK_PTR(fr, "pad freplace open"))
+ return;
+
+ if (!ASSERT_OK(bpf_program__set_attach_target(fr->progs.new_pad_callee,
+ tgt_fd, "pad_callee"),
+ "set_attach_target"))
+ goto out;
+ if (!ASSERT_OK(exceptions_cleanup_pad_freplace__load(fr), "pad freplace load"))
+ goto out;
+
+ link = bpf_program__attach_freplace(fr->progs.new_pad_callee, tgt_fd,
+ "pad_callee");
+ if (!ASSERT_OK_PTR(link, "attach_freplace"))
+ goto out;
+
+ skel->bss->input = 101;
+ skel->bss->pads_ran = 0;
+ skel->bss->pad_runs = 0;
+
+ err = bpf_prog_test_run_opts(tgt_fd, &topts);
+ if (!ASSERT_OK(err, "run"))
+ goto out_link;
+
+ ASSERT_EQ(skel->bss->pad_runs, 1, "pad_runs");
+ ASSERT_EQ(skel->bss->pads_ran, RAN_PAD_CALLS, "pads_ran");
+ ASSERT_EQ(topts.retval, THROW_COOKIE, "retval");
+out_link:
+ bpf_link__destroy(link);
+out:
+ exceptions_cleanup_pad_freplace__destroy(fr);
+}
+
+static void test_ext_table(struct exceptions_cleanup_shapes *skel)
+{
+ struct exceptions_cleanup_ext_table *fr;
+ struct bpf_link *link;
+ int tgt_fd;
+
+ tgt_fd = bpf_program__fd(skel->progs.entry_freplace);
+
+ fr = exceptions_cleanup_ext_table__open();
+ if (!ASSERT_OK_PTR(fr, "ext table open"))
+ return;
+
+ if (!ASSERT_OK(bpf_program__set_attach_target(fr->progs.new_fr_callee,
+ tgt_fd, "fr_callee"),
+ "set_attach_target"))
+ goto out;
+ if (!ASSERT_OK(exceptions_cleanup_ext_table__load(fr), "ext table load"))
+ goto out;
+
+ link = bpf_program__attach_freplace(fr->progs.new_fr_callee, tgt_fd,
+ "fr_callee");
+ if (!ASSERT_OK_PTR(link, "attach_freplace"))
+ goto out;
+
+ fr->bss->ext_pad_ran = 0;
+ run_shape(skel, skel->progs.entry_freplace, 101, THROW_COOKIE, 0);
+ ASSERT_EQ(fr->bss->ext_pad_ran, 1, "ext_pad_ran");
+
+ bpf_link__destroy(link);
+out:
+ exceptions_cleanup_ext_table__destroy(fr);
+}
+
+static void test_shapes(void)
+{
+ struct exceptions_cleanup_shapes *skel;
+
+ skel = exceptions_cleanup_shapes__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "shapes open_and_load"))
+ return;
+
+ /* The frame loads at all only if everything unreachable in it went. */
+ if (test__start_subtest("sweep_no_throw"))
+ run_shape(skel, skel->progs.entry_sweep, 1, 0, 0);
+ if (test__start_subtest("sweep_throw"))
+ run_shape(skel, skel->progs.entry_sweep, 101, THROW_COOKIE, RAN_SWEEP);
+
+ /* The covered call unwinds to the pad; the uncovered one never does. */
+ if (test__start_subtest("shared_callee_no_throw"))
+ run_shape(skel, skel->progs.entry_shared, 1, 2, 0);
+ if (test__start_subtest("shared_callee_throw"))
+ run_shape(skel, skel->progs.entry_shared, 101, THROW_COOKIE, RAN_SHARED);
+
+ /* The pad only sets its bit if it got the frame's own r6-r9 back. */
+ if (test__start_subtest("pad_sees_callee_saved"))
+ run_shape(skel, skel->progs.entry_regs, 101, THROW_COOKIE, RAN_REGS);
+
+ /* Same check, with a tail-call-reachable callee: its spill moves. */
+ if (test__start_subtest("tail_call_no_throw"))
+ run_shape(skel, skel->progs.entry_tail_call, 1, 0, 0);
+ if (test__start_subtest("tail_call_throw"))
+ run_shape(skel, skel->progs.entry_tail_call, 101, THROW_COOKIE,
+ RAN_TAIL_CALL);
+
+ /* A region around a nounwind call: no pad dispatched, still loads. */
+ if (test__start_subtest("nounwind_region"))
+ run_shape(skel, skel->progs.entry_nounwind_rec, 1, 0, 0);
+
+ /* A pad in the main program's own frame, not in a subprogram. */
+ if (test__start_subtest("main_program_pad"))
+ run_shape(skel, skel->progs.entry_main_pad, 101, THROW_COOKIE,
+ RAN_MAIN_PAD);
+
+ /* The same call site either way: the subprogram's throw unwinds into
+ * this frame and runs its pad, an extension's stops at its own boundary.
+ */
+ if (test__start_subtest("freplace_subprog_throws"))
+ run_shape(skel, skel->progs.entry_freplace, 7, THROW_COOKIE,
+ RAN_FREPLACE);
+ if (test__start_subtest("freplace_extension_throws"))
+ test_freplace(skel);
+
+ /* A tail call that is taken: the walk ends at the target, so the cookie
+ * comes back from there and this frame's pad does not run.
+ */
+ if (test__start_subtest("tail_call_taken")) {
+ int key = 0, prog_fd = bpf_program__fd(skel->progs.tc_target);
+
+ if (ASSERT_OK(bpf_map_update_elem(bpf_map__fd(skel->maps.taken_table),
+ &key, &prog_fd, BPF_ANY),
+ "populate taken_table"))
+ run_shape(skel, skel->progs.entry_tail_taken, 101,
+ THROW_COOKIE, 0);
+ }
+
+ /* A throwing subprog named by a BPF_PSEUDO_FUNC no helper is handed: the
+ * callback check has to look at the bpf_loop(), not at the ld_imm64.
+ */
+ if (test__start_subtest("addr_taken_no_throw"))
+ run_shape(skel, skel->progs.entry_addr_taken, 1, 2, 0);
+ if (test__start_subtest("addr_taken_throw"))
+ run_shape(skel, skel->progs.entry_addr_taken, 101, THROW_COOKIE,
+ RAN_ADDR_TAKEN);
+
+ /* A record covering bpf_throw() itself rather than a call to a frame
+ * that throws: raised, caught up with and delivered in one frame.
+ */
+ if (test__start_subtest("no_subprog_no_throw"))
+ run_shape(skel, skel->progs.entry_no_subprog, 1, 0, 0);
+ if (test__start_subtest("no_subprog_throw"))
+ run_shape(skel, skel->progs.entry_no_subprog, 101, THROW_COOKIE,
+ RAN_NO_SUBPROG);
+
+ /* A pad that calls a subprogram; with a throwing extension in its place,
+ * the nested exception has to stop there, not restart this pad.
+ */
+ if (test__start_subtest("pad_calls_subprog")) {
+ skel->bss->pad_runs = 0;
+ run_shape(skel, skel->progs.entry_pad_calls, 101, THROW_COOKIE,
+ RAN_PAD_CALLS);
+ ASSERT_EQ(skel->bss->pad_runs, 1, "pad_runs");
+ }
+ if (test__start_subtest("pad_calls_throwing_extension"))
+ test_pad_calls_freplace(skel);
+
+ /* A covered throw the sweep leaves last, where the default exception
+ * callback is patched in; the pad's bit needs r6-r9 still spilled.
+ */
+ if (test__start_subtest("pad_before_throw"))
+ run_shape(skel, skel->progs.entry_pad_first, 101, THROW_COOKIE,
+ RAN_PAD_FIRST);
+
+ /* A region whose last instruction is a 16-byte one, so that end - 1
+ * names the half of it that is not an instruction.
+ */
+ if (test__start_subtest("region_ends_on_ldimm64"))
+ run_shape(skel, skel->progs.entry_wide_rec, 101, THROW_COOKIE,
+ RAN_WIDE_REC);
+
+ /* A pad that reloads from and writes to its own frame's stack, which a
+ * JIT addressing the frame through the stack pointer gets wrong.
+ */
+ if (test__start_subtest("pad_uses_own_frame"))
+ run_shape(skel, skel->progs.entry_pad_stack, 101, THROW_COOKIE,
+ RAN_PAD_STACK);
+
+ /* The same, with an uncovered frame between the throw and the pad. */
+ if (test__start_subtest("pad_two_frames_up"))
+ run_shape(skel, skel->progs.entry_deep_pad, 101, THROW_COOKIE,
+ RAN_DEEP_PAD);
+
+ /* An extension program with a cleanup table of its own. */
+ if (test__start_subtest("extension_carries_table"))
+ test_ext_table(skel);
+
+ /* A pad terminated by _Unwind_Resume, which libbpf maps onto the kfunc;
+ * every other program here calls bpf_unwind_resume directly.
+ */
+ if (test__start_subtest("resume_alias"))
+ run_shape(skel, skel->progs.entry_resume_alias, 101,
+ THROW_COOKIE, RAN_RESUME_ALIAS);
+
+ /* A pad that calls a subprogram which tail calls, array empty and then
+ * populated: the tail call releases only the callee's own prologue.
+ */
+ if (test__start_subtest("pad_callee_tail_call")) {
+ int key = 0, prog_fd = bpf_program__fd(skel->progs.pad_tc_target);
+
+ skel->bss->pad_tc_target_ran = 0;
+ skel->bss->pad_runs = 0;
+ run_shape(skel, skel->progs.entry_pad_tail_call, 101,
+ THROW_COOKIE, RAN_PAD_TAIL_CALL);
+ ASSERT_EQ(skel->bss->pad_tc_target_ran, 0, "target not run");
+ ASSERT_EQ(skel->bss->pad_runs, 1, "pad_runs");
+
+ if (ASSERT_OK(bpf_map_update_elem(bpf_map__fd(skel->maps.pad_tc_table),
+ &key, &prog_fd, BPF_ANY),
+ "populate pad_tc_table")) {
+ skel->bss->pad_runs = 0;
+ run_shape(skel, skel->progs.entry_pad_tail_call, 101,
+ THROW_COOKIE, RAN_PAD_TAIL_CALL);
+ ASSERT_EQ(skel->bss->pad_tc_target_ran, 1, "target ran");
+ ASSERT_EQ(skel->bss->pad_runs, 1, "pad_runs");
+ }
+ }
+
+ /* The same, into a target that carries a table and throws: that target
+ * is a boundary, so the outer pad runs once, not twice.
+ */
+ if (test__start_subtest("pad_callee_tail_call_throws")) {
+ int key = 0, prog_fd = bpf_program__fd(skel->progs.pad_tc_throw_target);
+
+ if (ASSERT_OK(bpf_map_update_elem(bpf_map__fd(skel->maps.pad_tc_table),
+ &key, &prog_fd, BPF_ANY),
+ "populate pad_tc_table")) {
+ skel->bss->pad_runs = 0;
+ skel->bss->tc_target_pad_runs = 0;
+ run_shape(skel, skel->progs.entry_pad_tail_call, 101,
+ THROW_COOKIE, RAN_PAD_TAIL_CALL);
+ /* The target cleaned up after itself, once. */
+ ASSERT_EQ(skel->bss->tc_target_pad_runs, 1,
+ "tc_target_pad_runs");
+ /* And the outer pad was not started over. */
+ ASSERT_EQ(skel->bss->pad_runs, 1, "pad_runs");
+ }
+ }
+
+ exceptions_cleanup_shapes__destroy(skel);
+}
+
void test_exceptions_cleanup(void)
{
char log[8192] = {};
@@ -75,5 +387,7 @@ void test_exceptions_cleanup(void)
exceptions_cleanup__destroy(skel);
+ test_shapes();
+
RUN_TESTS(exceptions_cleanup_fail);
}
diff --git a/tools/testing/selftests/bpf/progs/exceptions_cleanup_ext_table.c b/tools/testing/selftests/bpf/progs/exceptions_cleanup_ext_table.c
new file mode 100644
index 000000000000..d14db48d6b29
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/exceptions_cleanup_ext_table.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "exceptions_cleanup.h"
+
+__u64 ext_pad_ran = 0;
+
+/* Without a 32-bit int in BTF, libbpf's dummy_ksym var gets type id 0. */
+int btf_int_anchor;
+
+static __used __noinline void __kfunc_btf_anchor(void)
+{
+ bpf_throw(0);
+ bpf_preempt_disable();
+ bpf_preempt_enable();
+ bpf_unwind_resume();
+}
+
+static __used __naked __noinline __u64 ext_frame(void)
+{
+ asm volatile (
+ "call bpf_preempt_disable;"
+ "r1 = %[cookie];"
+"1:" "call bpf_throw;" /* cleanup region */
+"2:"
+ "exit;"
+"3:" /* landing pad */
+ "call bpf_preempt_enable;"
+ "r1 = %[ext_pad_ran] ll;"
+ "r2 = 1;"
+ "*(u64 *)(r1 + 0) = r2;"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [cookie]"i"(THROW_COOKIE), __imm_addr(ext_pad_ran)
+ : __clobber_all);
+}
+
+SEC("freplace/fr_callee")
+__u64 new_fr_callee(__u64 x)
+{
+ return ext_frame();
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/exceptions_cleanup_freplace.c b/tools/testing/selftests/bpf/progs/exceptions_cleanup_freplace.c
new file mode 100644
index 000000000000..afb358fd3d40
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/exceptions_cleanup_freplace.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "exceptions_cleanup.h"
+
+/* Without a 32-bit int in BTF, libbpf's dummy_ksym var gets type id 0. */
+int btf_int_anchor;
+
+SEC("freplace/fr_callee")
+__u64 new_fr_callee(__u64 x)
+{
+ bpf_throw(THROW_COOKIE);
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/exceptions_cleanup_pad_freplace.c b/tools/testing/selftests/bpf/progs/exceptions_cleanup_pad_freplace.c
new file mode 100644
index 000000000000..eabac6baabb7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/exceptions_cleanup_pad_freplace.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "exceptions_cleanup.h"
+
+/* Without a 32-bit int in BTF, libbpf's dummy_ksym var gets type id 0. */
+int btf_int_anchor;
+
+SEC("freplace/pad_callee")
+__u64 new_pad_callee(__u64 x)
+{
+ bpf_throw(INNER_COOKIE);
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/exceptions_cleanup_shapes.c b/tools/testing/selftests/bpf/progs/exceptions_cleanup_shapes.c
new file mode 100644
index 000000000000..f5eb2ff15c89
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/exceptions_cleanup_shapes.c
@@ -0,0 +1,863 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "exceptions_cleanup.h"
+
+#define PAD_COUNT \
+ "r1 = %[pad_runs] ll;" \
+ "r2 = *(u64 *)(r1 + 0);" \
+ "r2 += 1;" \
+ "*(u64 *)(r1 + 0) = r2;"
+
+static __used __noinline void __kfunc_btf_anchor(void)
+{
+ bpf_throw(0);
+ bpf_rcu_read_lock();
+ bpf_rcu_read_unlock();
+ bpf_preempt_disable();
+ bpf_preempt_enable();
+ bpf_unwind_resume();
+}
+
+__u64 input = 0;
+__u64 magic = 0x5eed;
+__u64 pads_ran = 0;
+__u64 pad_runs = 0;
+
+/*
+ * 1. Everything a cleanup table leaves dead: the continuation after a throw,
+ * the tail after a pad's resume, an ld_imm64 and a conditional branch inside
+ * that tail, and a block reached only by the dead continuation.
+ */
+static __used __naked __noinline __u64 sweep_frame(void)
+{
+ asm volatile (
+ "r1 = %[input] ll;"
+ "r6 = *(u64 *)(r1 + 0);"
+ "call bpf_preempt_disable;"
+ "if r6 < 101 goto 6f;"
+ "r1 = %[cookie];"
+"1:" "call bpf_throw;" /* cleanup region */
+"2:"
+ "goto 3f;"
+"4:" /* landing pad */
+ "r7 = r0;"
+ "call bpf_preempt_enable;"
+ PAD_RAN("%[ran]")
+ "r1 = r7;"
+ "call bpf_unwind_resume;"
+ "r1 = %[pads_ran] ll;"
+ "r2 = *(u64 *)(r1 + 0);"
+ "if r2 == 0 goto 5f;"
+ "call bpf_preempt_enable;"
+ "r0 = 7;"
+ "exit;"
+"5:"
+ "r0 = 8;"
+ "exit;"
+"3:" /* dead: only the dead goto reaches it */
+ "r0 = 9;"
+ "exit;"
+"6:" /* live: the ordinary return */
+ "call bpf_preempt_enable;"
+ "r0 = 0;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "4b")
+ :
+ : [cookie]"i"(THROW_COOKIE), [ran]"i"(RAN_SWEEP),
+ __imm_addr(input), __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+SEC("syscall")
+int entry_sweep(void *ctx)
+{
+ return sweep_frame();
+}
+
+/*
+ * 2. A callee called from both a covered and an uncovered site: the pad is
+ * recorded on the call site, not on the callee. The lock sits between the two
+ * calls because the frame really would leak it if the uncovered call unwound.
+ */
+static __used __noinline __u64 shared_callee(__u64 x)
+{
+ if (x > 100)
+ bpf_throw(THROW_COOKIE);
+ return x + 1;
+}
+
+static __used __naked __noinline __u64 shared_frame(void)
+{
+ asm volatile (
+ "r1 = %[input] ll;"
+ "r6 = *(u64 *)(r1 + 0);"
+ "r1 = 0;"
+ "call shared_callee;"
+ "call bpf_rcu_read_lock;"
+ "r1 = r6;"
+"1:" "call shared_callee;" /* cleanup region */
+"2:"
+ "r6 = r0;"
+ "call bpf_rcu_read_unlock;"
+ "r0 = r6;"
+ "exit;"
+"3:" /* landing pad */
+ "r7 = r0;"
+ "call bpf_rcu_read_unlock;"
+ PAD_RAN("%[ran]")
+ "r1 = r7;"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [ran]"i"(RAN_SHARED), __imm_addr(input), __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+SEC("syscall")
+int entry_shared(void *ctx)
+{
+ return shared_frame();
+}
+
+/*
+ * 3. A landing pad that reads its frame's callee-saved registers, which only
+ * the spill in the discarded callee's prologue still holds. The callee fills
+ * r6-r9 with something else before it throws, so the pad's check passes only
+ * if the walker found that spill.
+ */
+#define LOAD_MAGIC_REGS \
+ "r1 = %[magic] ll;" \
+ "r6 = *(u64 *)(r1 + 0);" \
+ "r7 = r6;" \
+ "r7 += 1;" \
+ "r8 = r6;" \
+ "r8 += 2;" \
+ "r9 = r6;" \
+ "r9 += 3;"
+
+/* Set @bit only if r6-r9 still hold what LOAD_MAGIC_REGS put there. */
+#define CHECK_MAGIC_REGS(bit) \
+ "r1 = %[magic] ll;" \
+ "r2 = *(u64 *)(r1 + 0);" \
+ "if r6 != r2 goto 9f;" \
+ "r2 += 1;" \
+ "if r7 != r2 goto 9f;" \
+ "r2 += 1;" \
+ "if r8 != r2 goto 9f;" \
+ "r2 += 1;" \
+ "if r9 != r2 goto 9f;" \
+ PAD_RAN(bit) \
+ "9:"
+
+static __used __naked __noinline __u64 regs_thrower(void)
+{
+ asm volatile (
+ /* Not this frame's to keep, and that is the point. */
+ "r6 = 0xdead;"
+ "r7 = 0xbeef;"
+ "r8 = 0xcafe;"
+ "r9 = 0xf00d;"
+ "r1 = %[cookie];"
+ "call bpf_throw;"
+ "r0 = 0;"
+ "exit;"
+ :
+ : [cookie]"i"(THROW_COOKIE)
+ : __clobber_all);
+}
+
+static __used __naked __noinline __u64 regs_frame(void)
+{
+ asm volatile (
+ LOAD_MAGIC_REGS
+ "call bpf_preempt_disable;"
+"1:" "call regs_thrower;" /* cleanup region */
+"2:"
+ "call bpf_preempt_enable;"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ "call bpf_preempt_enable;"
+ CHECK_MAGIC_REGS("%[ran]")
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [cookie]"i"(THROW_COOKIE), [ran]"i"(RAN_REGS),
+ __imm_addr(magic), __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+SEC("syscall")
+int entry_regs(void *ctx)
+{
+ return regs_frame();
+}
+
+/*
+ * 4. The same, with a tail-call-reachable callee: its prologue pushes the tail
+ * call counter between the program stack and the spill area, so the spill the
+ * walker reads moves. The array is left empty; being reachable is the point.
+ */
+struct {
+ __uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+ __uint(max_entries, 1);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+static __used __noinline __u64 tc_thrower(void *ctx)
+{
+ /* Never taken; its presence is what makes this frame, whose spill the
+ * walker reads, tail-call-reachable.
+ */
+ bpf_tail_call_static(ctx, &jmp_table, 0);
+ asm volatile (
+ "r6 = 0xdead;"
+ "r7 = 0xbeef;"
+ "r8 = 0xcafe;"
+ "r9 = 0xf00d;"
+ "r1 = %[cookie];"
+ "call bpf_throw;"
+ :
+ : [cookie]"i"(THROW_COOKIE)
+ : __clobber_all);
+ return 0;
+}
+
+/*
+ * The frame with the pad is the program itself, and __naked: r1 holds the
+ * context at entry, which is the only place to get one for bpf_tail_call().
+ */
+SEC("syscall")
+__naked int entry_tail_call(void)
+{
+ asm volatile (
+ "*(u64 *)(r10 - 8) = r1;" /* the context, straight from entry */
+ LOAD_MAGIC_REGS
+ "r1 = %[input] ll;"
+ "r1 = *(u64 *)(r1 + 0);"
+ "if r1 < 101 goto 8f;"
+ "r1 = *(u64 *)(r10 - 8);"
+"1:" "call tc_thrower;" /* cleanup region */
+"2:"
+"8:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ CHECK_MAGIC_REGS("%[ran]")
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [ran]"i"(RAN_TAIL_CALL), __imm_addr(input),
+ __imm_addr(magic), __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+/*
+ * 5. A landing pad in the main program's own frame. jit_subprogs() compiles it
+ * as func[0], but the ksym the walker finds is the outer bpf_prog's, so the
+ * table has to be handed over or the pad is never dispatched -- silently.
+ */
+SEC("syscall")
+__naked int entry_main_pad(void)
+{
+ asm volatile (
+ LOAD_MAGIC_REGS
+ "r1 = %[input] ll;"
+ "r1 = *(u64 *)(r1 + 0);"
+ "if r1 < 101 goto 8f;"
+"1:" "call regs_thrower;" /* cleanup region */
+"2:"
+"8:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ CHECK_MAGIC_REGS("%[ran]")
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [ran]"i"(RAN_MAIN_PAD), __imm_addr(input),
+ __imm_addr(magic), __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+/*
+ * 6. A tail call that is really taken: the target is a program in its own
+ * right, so the walk ends there and this frame's pad does not run. The callee
+ * can also throw on a path never taken, which keeps the pad out of the sweep.
+ */
+struct {
+ __uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+ __uint(max_entries, 1);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u32));
+} taken_table SEC(".maps");
+
+SEC("syscall")
+int tc_target(void *ctx)
+{
+ bpf_throw(THROW_COOKIE);
+ return 0;
+}
+
+static __used __noinline __u64 tc_taken_callee(void *ctx, __u64 x)
+{
+ /* Never true at run time; the verifier cannot know that, and its
+ * unwind out of here is what keeps the caller's pad alive.
+ */
+ if (x == 7)
+ bpf_throw(THROW_COOKIE);
+ bpf_tail_call_static(ctx, &taken_table, 0);
+ return 0;
+}
+
+SEC("syscall")
+__naked int entry_tail_taken(void)
+{
+ asm volatile (
+ "*(u64 *)(r10 - 8) = r1;" /* the context, straight from entry */
+ "r1 = %[input] ll;"
+ "r2 = *(u64 *)(r1 + 0);"
+ "if r2 < 101 goto 8f;"
+ "r1 = *(u64 *)(r10 - 8);"
+"1:" "call tc_taken_callee;" /* cleanup region */
+"2:"
+ "exit;" /* the cookie, delivered at tc_target */
+"8:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad: must not run */
+ PAD_RAN("%[ran]")
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [ran]"i"(RAN_TC_TAKEN), __imm_addr(input), __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+/*
+ * 7. An extension program over the callee of a covered call. The walk ends in
+ * the extension's frame, as it does for a tail call target, so the pad does
+ * not run; fr_callee() can also throw by itself, giving the same call site
+ * both answers.
+ */
+__noinline __u64 fr_callee(__u64 x)
+{
+ if (x == 7)
+ bpf_throw(THROW_COOKIE);
+ return x + 1;
+}
+
+SEC("syscall")
+__naked int entry_freplace(void)
+{
+ asm volatile (
+ "r1 = %[input] ll;"
+ "r1 = *(u64 *)(r1 + 0);"
+"1:" "call fr_callee;" /* cleanup region */
+"2:"
+ "exit;"
+"3:" /* landing pad */
+ PAD_RAN("%[ran]")
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [ran]"i"(RAN_FREPLACE), __imm_addr(input), __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+/*
+ * 8. A throwing subprogram named by a BPF_PSEUDO_FUNC on a path never taken.
+ * Handing one to a helper is what is refused, not naming it, so anything going
+ * by the ld_imm64 alone turns this program away.
+ */
+static __used __noinline int cb_thrower(__u32 idx, void *ctx)
+{
+ bpf_throw(THROW_COOKIE);
+ return 0;
+}
+
+static __used __noinline __u64 addr_taken_callee(__u64 x)
+{
+ if (x <= 100)
+ return x + 1;
+ bpf_throw(THROW_COOKIE);
+ return bpf_loop(1, cb_thrower, NULL, 0);
+}
+
+SEC("syscall")
+__naked int entry_addr_taken(void)
+{
+ asm volatile (
+ "r1 = %[input] ll;"
+ "r1 = *(u64 *)(r1 + 0);"
+"1:" "call addr_taken_callee;" /* cleanup region */
+"2:"
+ "exit;"
+"3:" /* landing pad */
+ PAD_RAN("%[ran]")
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [ran]"i"(RAN_ADDR_TAKEN), __imm_addr(input), __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+/*
+ * 9. A record that covers bpf_throw() itself: the frame that raises the
+ * exception is the frame the record covers and the boundary both, so the pad
+ * runs on the way to delivering the cookie out of the program it came from.
+ */
+SEC("syscall")
+__naked int entry_no_subprog(void)
+{
+ asm volatile (
+ "r1 = %[input] ll;"
+ "r1 = *(u64 *)(r1 + 0);"
+ "if r1 < 101 goto 8f;"
+ "call bpf_preempt_disable;"
+ "r1 = %[cookie];"
+"1:" "call bpf_throw;" /* cleanup region */
+"2:"
+ "exit;"
+"8:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ "call bpf_preempt_enable;"
+ PAD_RAN("%[ran]")
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [cookie]"i"(THROW_COOKIE), [ran]"i"(RAN_NO_SUBPROG),
+ __imm_addr(input), __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+/*
+ * 10. A landing pad that calls a subprogram an extension can replace. The
+ * load-time rule cannot see the extension coming, so what stops a nested
+ * exception is the walk, which ends in the extension's own frame. pad_runs
+ * says the pad ran once rather than twice.
+ */
+__noinline __u64 pad_callee(__u64 x)
+{
+ return x + 1;
+}
+
+static __used __noinline __u64 pc_thrower(__u64 x)
+{
+ if (x > 100)
+ bpf_throw(THROW_COOKIE);
+ return x + 1;
+}
+
+static __used __naked __noinline __u64 pad_calls_frame(void)
+{
+ asm volatile (
+ "r1 = %[input] ll;"
+ "r1 = *(u64 *)(r1 + 0);"
+"1:" "call pc_thrower;" /* cleanup region */
+"2:"
+ "exit;"
+"3:" /* landing pad */
+ "r6 = r0;"
+ "r1 = 1;"
+ "call pad_callee;" /* an extension can stand in here */
+ PAD_COUNT
+ PAD_RAN("%[ran]")
+ "r1 = r6;"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [ran]"i"(RAN_PAD_CALLS), __imm_addr(input), __imm_addr(pads_ran),
+ __imm_addr(pad_runs)
+ : __clobber_all);
+}
+
+SEC("syscall")
+int entry_pad_calls(void *ctx)
+{
+ return pad_calls_frame();
+}
+
+/*
+ * 11. A covered bpf_throw() the sweep leaves as the last instruction, where
+ * the default exception callback is then patched in -- the one patchlet that
+ * does not keep the call it replaced in the last slot, so the marks have to
+ * follow it. The r6-r9 check is what reports a lost throw site mark.
+ */
+SEC("syscall")
+__naked int entry_pad_first(void)
+{
+ asm volatile (
+ LOAD_MAGIC_REGS
+ "r1 = %[input] ll;"
+ "r1 = *(u64 *)(r1 + 0);"
+ "if r1 < 101 goto 7f;"
+ "goto 4f;"
+"3:" /* landing pad, ahead of the call */
+ CHECK_MAGIC_REGS("%[ran]")
+ "call bpf_unwind_resume;"
+ "exit;"
+"7:"
+ "r0 = 0;"
+ "exit;"
+"4:"
+ "r1 = %[cookie];"
+"1:" "call bpf_throw;" /* cleanup region */
+"2:"
+ "exit;" /* dead: swept, leaving the call last */
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [cookie]"i"(THROW_COOKIE), [ran]"i"(RAN_PAD_FIRST),
+ __imm_addr(input), __imm_addr(magic), __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+/*
+ * 12. A cleanup region whose last instruction is a 16-byte one, so end - 1
+ * names the half that is not an instruction of its own. A well formed region
+ * that a rule against it would turn away.
+ */
+static __used __naked __noinline __u64 wide_rec_frame(void)
+{
+ asm volatile (
+ "r1 = %[input] ll;"
+ "r6 = *(u64 *)(r1 + 0);"
+ "call bpf_rcu_read_lock;"
+ "r1 = r6;"
+"1:" "call shared_callee;" /* cleanup region begins */
+ "r1 = %[magic] ll;" /* ... and ends on this pair */
+"2:"
+ "r6 = r0;"
+ "call bpf_rcu_read_unlock;"
+ "r0 = r6;"
+ "exit;"
+"3:" /* landing pad */
+ "r7 = r0;"
+ "call bpf_rcu_read_unlock;"
+ PAD_RAN("%[ran]")
+ "r1 = r7;"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [ran]"i"(RAN_WIDE_REC), __imm_addr(input), __imm_addr(magic),
+ __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+SEC("syscall")
+int entry_wide_rec(void *ctx)
+{
+ return wide_rec_frame();
+}
+
+/*
+ * 13. A pad that works out of its own frame's stack, the shape every
+ * compiler-generated pad has. A JIT that addresses the frame through the
+ * stack pointer -- arm64 -- has to address a pad's frame some other way. Both
+ * directions are here: the reload sees the frame, and the store lands in it.
+ */
+static __used __naked __noinline __u64 pad_stack_frame(void)
+{
+ asm volatile (
+ "r1 = %[magic] ll;"
+ "r1 = *(u64 *)(r1 + 0);"
+ "*(u64 *)(r10 - 8) = r1;" /* what the pad will want */
+ "r1 = %[input] ll;"
+ "r1 = *(u64 *)(r1 + 0);"
+"1:" "call pc_thrower;" /* cleanup region */
+"2:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ "r6 = r0;"
+ "r7 = *(u64 *)(r10 - 8);" /* reload it out of the frame */
+ "*(u64 *)(r10 - 16) = r7;" /* and write the frame while here */
+ "r1 = %[magic] ll;"
+ "r2 = *(u64 *)(r1 + 0);"
+ "if r7 != r2 goto 9f;"
+ "r3 = *(u64 *)(r10 - 16);"
+ "if r3 != r2 goto 9f;"
+ PAD_RAN("%[ran]")
+"9:"
+ "r1 = r6;"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [ran]"i"(RAN_PAD_STACK), __imm_addr(input), __imm_addr(magic),
+ __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+SEC("syscall")
+int entry_pad_stack(void *ctx)
+{
+ return pad_stack_frame();
+}
+
+/*
+ * 14. The same, with a frame in between that has no pad of its own, so the
+ * liveness query for an outer frame has more than one frame to walk and the
+ * pad has to be counted at every step.
+ */
+static __used __noinline __u64 deep_mid(__u64 x)
+{
+ return pc_thrower(x) + 1;
+}
+
+static __used __naked __noinline __u64 deep_frame(void)
+{
+ asm volatile (
+ "r1 = %[magic] ll;"
+ "r1 = *(u64 *)(r1 + 0);"
+ "*(u64 *)(r10 - 8) = r1;" /* nothing but the pad reads this */
+ "r1 = %[input] ll;"
+ "r1 = *(u64 *)(r1 + 0);"
+"1:" "call deep_mid;" /* cleanup region */
+"2:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ "r6 = r0;"
+ "r7 = *(u64 *)(r10 - 8);"
+ "r1 = %[magic] ll;"
+ "r2 = *(u64 *)(r1 + 0);"
+ "if r7 != r2 goto 9f;"
+ PAD_RAN("%[ran]")
+"9:"
+ "r1 = r6;"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [ran]"i"(RAN_DEEP_PAD), __imm_addr(input), __imm_addr(magic),
+ __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+SEC("syscall")
+int entry_deep_pad(void *ctx)
+{
+ return deep_frame();
+}
+
+/*
+ * 15. A region around a call the kernel knows cannot unwind: no call site is
+ * marked, nothing reaches the pad, and the sweep removes it. The program is
+ * otherwise ordinary and has to load.
+ */
+static __used __naked __noinline __u64 nounwind_rec_frame(void)
+{
+ asm volatile (
+ "call bpf_preempt_disable;"
+"1:" "call bpf_preempt_enable;" /* cleanup region: nounwind */
+"2:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad, never dispatched */
+ PAD_RAN("%[ran]")
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [ran]"i"(RAN_NOUNWIND_REC), __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+SEC("syscall")
+int entry_nounwind_rec(void *ctx)
+{
+ return nounwind_rec_frame();
+}
+
+/*
+ * 16. The name a frontend gives the resume. Every pad above calls
+ * bpf_unwind_resume(); LLVM emits _Unwind_Resume() and libbpf maps one onto
+ * the other, so this program is what keeps that mapping tested.
+ */
+extern void _Unwind_Resume(void) __ksym;
+
+static __used __noinline void __resume_alias_btf_anchor(void)
+{
+ _Unwind_Resume();
+}
+
+static __used __naked __noinline __u64 resume_alias_frame(void)
+{
+ asm volatile (
+"1:" "call regs_thrower;" /* cleanup region */
+"2:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ PAD_RAN("%[ran]")
+ "call _Unwind_Resume;" /* the frontend's name for it */
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [ran]"i"(RAN_RESUME_ALIAS), __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+SEC("syscall")
+int entry_resume_alias(void *ctx)
+{
+ return resume_alias_frame();
+}
+
+/*
+ * 17. A landing pad that calls a subprogram which tail calls. What a pad may
+ * not contain is a tail call of its own, which would unwind a prologue the
+ * walker's stack never held; a callee's prologue really did run there, so its
+ * tail call releases exactly that and the target returns into the pad. The
+ * tail call counter comes out of the unwinding frame, which is one of the
+ * pad's own subprogram and so really holds one.
+ */
+struct {
+ __uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+ __uint(max_entries, 1);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u32));
+} pad_tc_table SEC(".maps");
+
+__u64 pad_tc_target_ran = 0;
+
+SEC("syscall")
+int pad_tc_target(void *ctx)
+{
+ pad_tc_target_ran += 1;
+ return 0;
+}
+
+static __used __noinline __u64 pad_tc_callee(void *ctx)
+{
+ /* Taken only once the test has populated the array. */
+ bpf_tail_call_static(ctx, &pad_tc_table, 0);
+ return 0;
+}
+
+/*
+ * The frame with the pad is the program itself, and __naked: r1 holds the
+ * context at entry, which is the only place to get one for bpf_tail_call().
+ * The pad reloads it from its own frame's stack.
+ */
+SEC("syscall")
+__naked int entry_pad_tail_call(void)
+{
+ asm volatile (
+ "*(u64 *)(r10 - 8) = r1;" /* the context, straight from entry */
+ LOAD_MAGIC_REGS
+ "r1 = %[input] ll;"
+ "r1 = *(u64 *)(r1 + 0);"
+ "if r1 < 101 goto 8f;"
+"1:" "call regs_thrower;" /* cleanup region */
+"2:"
+"8:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ PAD_COUNT
+ "r1 = *(u64 *)(r10 - 8);"
+ "call pad_tc_callee;"
+ /* Only if the frame survived the callee's tail call. */
+ CHECK_MAGIC_REGS("%[ran]")
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [ran]"i"(RAN_PAD_TAIL_CALL), __imm_addr(input),
+ __imm_addr(magic), __imm_addr(pads_ran), __imm_addr(pad_runs)
+ : __clobber_all);
+}
+
+/*
+ * 18. The other target for that same tail call: a program carrying a cleanup
+ * table of its own, which throws while the outer exception is still in flight.
+ * The tail call made it a boundary, so the inner walk runs its pad and ends in
+ * its own frame, never reaching the walker's frames above it: the outer pad is
+ * not restarted and the outer cookie is still the one delivered. The outer
+ * pad's r6-r9, which this target overwrites, come back with its frame.
+ */
+__u64 tc_target_pad_runs = 0;
+__u64 inner_magic = 0xd00d;
+
+static __used __naked __noinline __u64 inner_thrower(void)
+{
+ asm volatile (
+ /* Not this frame's to keep, the same as regs_thrower. */
+ "r6 = 0xf00d;"
+ "r7 = 0xcafe;"
+ "r8 = 0xbeef;"
+ "r9 = 0xdead;"
+ "r1 = %[cookie];"
+ "call bpf_throw;"
+ "r0 = 0;"
+ "exit;"
+ :
+ : [cookie]"i"(INNER_COOKIE)
+ : __clobber_all);
+}
+
+SEC("syscall")
+__naked int pad_tc_throw_target(void)
+{
+ asm volatile (
+ /* Distinct from the outer pad's, so neither can stand in for it. */
+ "r1 = %[inner_magic] ll;"
+ "r6 = *(u64 *)(r1 + 0);"
+ "r7 = r6;"
+ "r7 += 1;"
+ "r8 = r6;"
+ "r8 += 2;"
+ "r9 = r6;"
+ "r9 += 3;"
+ "r1 = %[input] ll;"
+ "r1 = *(u64 *)(r1 + 0);"
+ "if r1 < 101 goto 8f;"
+"1:" "call inner_thrower;" /* cleanup region */
+"2:"
+"8:"
+ "r0 = 0;"
+ "exit;"
+"3:" /* landing pad */
+ /* This frame's own r6-r9, not the outer pad's. */
+ "r1 = %[inner_magic] ll;"
+ "r2 = *(u64 *)(r1 + 0);"
+ "if r6 != r2 goto 9f;"
+ "r2 += 1;"
+ "if r7 != r2 goto 9f;"
+ "r2 += 1;"
+ "if r8 != r2 goto 9f;"
+ "r2 += 1;"
+ "if r9 != r2 goto 9f;"
+ "r1 = %[tc_target_pad_runs] ll;"
+ "r2 = *(u64 *)(r1 + 0);"
+ "r2 += 1;"
+ "*(u64 *)(r1 + 0) = r2;"
+"9:"
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : __imm_addr(input), __imm_addr(inner_magic),
+ __imm_addr(tc_target_pad_runs)
+ : __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH bpf-next 19/20] selftests/bpf: Cover the exception cleanup shapes the chain does not reach
2026-09-17 5:58 ` [PATCH bpf-next 19/20] selftests/bpf: Cover the exception cleanup shapes the chain does not reach Yonghong Song
@ 2026-09-17 6:16 ` sashiko-bot
0 siblings, 0 replies; 40+ messages in thread
From: sashiko-bot @ 2026-09-17 6:16 UTC (permalink / raw)
To: Yonghong Song; +Cc: bpf
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] bpf: multi-line comments violate BPF subsystem style
--
commit 621c13df81280f1c0c32e09255ce8c64860bd768
Author: Yonghong Song <yonghong.song@linux.dev>
selftests/bpf: Cover the exception cleanup shapes the chain does not reach
The end-to-end test walks one call chain with a pad in most of its frames.
This adds the shapes that chain does not reach: a callee called from both a
covered and an uncovered site, a pad that reads its frame's callee-saved
registers, a tail-call-reachable callee, a tail call that is taken, an
extension standing in for a covered call, a pad in the main program's own
frame, a record covering bpf_throw() itself, a record covering only a
nounwind call, a throwing subprogram named by a BPF_PSEUDO_FUNC, a region
ending on a 16-byte instruction, a pad that reloads from and writes to its
own frame, a pad two frames up, a pad that calls a subprogram which tail
calls, an extension carrying a table of its own, and a pad terminated by
_Unwind_Resume rather than bpf_unwind_resume.
> diff --git a/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c b/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c
> index d1e45b765af26..ffc0b95191681 100644
> --- a/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c
> +++ b/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c
> @@ -212,6 +212,9 @@ static void test_shapes(void)
>
[ ... ]
> + /* The same call site either way: the subprogram's throw unwinds into
> + * this frame and runs its pad, an extension's stops at its own boundary.
> + */
[Severity: Low]
Does this multi-line comment in test_shapes() violate the BPF subsystem style?
The style guidelines prefer the opening /* on its own line:
/*
* The same call site either way: the subprogram's throw unwinds into
* this frame and runs its pad, an extension's stops at its own boundary.
*/
[ ... ]
> + /* A tail call that is taken: the walk ends at the target, so the cookie
> + * comes back from there and this frame's pad does not run.
> + */
[Severity: Low]
Could this multi-line comment in test_shapes() also be updated to start the text
on the line following the opening /* to match the preferred BPF style?
> diff --git a/tools/testing/selftests/bpf/progs/exceptions_cleanup_shapes.c b/tools/testing/selftests/bpf/progs/exceptions_cleanup_shapes.c
> new file mode 100644
> index 0000000000000..f5eb2ff15c896
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/progs/exceptions_cleanup_shapes.c
> @@ -214,6 +214,9 @@ static __used __noinline __u64 tc_thrower(void *ctx)
> {
> + /* Never taken; its presence is what makes this frame, whose spill the
> + * walker reads, tail-call-reachable.
> + */
[Severity: Low]
Is this multi-line comment in tc_thrower() formatted correctly?
The BPF subsystem style requires the opening /* on its own line for multi-line
comments.
[ ... ]
> @@ -311,6 +311,9 @@ static __used __noinline __u64 tc_taken_callee(void *ctx, __u64 x)
> {
> + /* Never true at run time; the verifier cannot know that, and its
> + * unwind out of here is what keeps the caller's pad alive.
> + */
[Severity: Low]
Should this multi-line comment in tc_taken_callee() also be adjusted so the text
starts on the next line after the opening /* marker?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260917055645.3926444-1-yonghong.song@linux.dev?part=19
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH bpf-next 20/20] selftests/bpf: Load an exception cleanup program from a light skeleton
2026-09-17 5:56 [PATCH bpf-next 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
` (18 preceding siblings ...)
2026-09-17 5:58 ` [PATCH bpf-next 19/20] selftests/bpf: Cover the exception cleanup shapes the chain does not reach Yonghong Song
@ 2026-09-17 5:58 ` Yonghong Song
19 siblings, 0 replies; 40+ messages in thread
From: Yonghong Song @ 2026-09-17 5:58 UTC (permalink / raw)
To: bpf
Cc: Alexei Starovoitov, Andrii Nakryiko, Daniel Borkmann,
Eduard Zingerman, kernel-team
For a light skeleton, libbpf hands the records to bpf_gen__prog_load(),
which writes them into a blob and emits a loader program that issues
BPF_PROG_LOAD from inside the kernel. Nothing about that is shared with the
ordinary path: the attr is built field by field, and the kfunc names are
resolved by the loader program when it runs.
exceptions_cleanup_light.c is the smallest program that can tell whether a
table survives that trip: one record covering the bpf_throw() call itself,
one pad that sets a bit and resumes. If the table arrives, the pad runs and
the cookie comes back; if it does not, the program does not load at all.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
tools/testing/selftests/bpf/Makefile | 2 +-
.../selftests/bpf/exceptions_cleanup.h | 3 ++
.../bpf/prog_tests/exceptions_cleanup.c | 28 +++++++++++++
.../bpf/progs/exceptions_cleanup_light.c | 39 +++++++++++++++++++
4 files changed, 71 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/bpf/progs/exceptions_cleanup_light.c
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 7ea5ba1df29e..981cc2643049 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -523,7 +523,7 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \
LSKELS := fexit_sleep.c trace_printk.c trace_vprintk.c map_ptr_kern.c \
core_kern.c core_kern_overflow.c test_ringbuf.c \
test_ringbuf_n.c test_ringbuf_map_key.c test_ringbuf_write.c \
- test_ringbuf_overwrite.c
+ test_ringbuf_overwrite.c exceptions_cleanup_light.c
LSKELS_SIGNED := fentry_test.c fexit_test.c atomics.c
diff --git a/tools/testing/selftests/bpf/exceptions_cleanup.h b/tools/testing/selftests/bpf/exceptions_cleanup.h
index 5896cf83d15e..0c088d96ca01 100644
--- a/tools/testing/selftests/bpf/exceptions_cleanup.h
+++ b/tools/testing/selftests/bpf/exceptions_cleanup.h
@@ -32,6 +32,9 @@
#define RAN_RESUME_ALIAS 0x8000
#define RAN_PAD_TAIL_CALL 0x10000
+/* progs/exceptions_cleanup_light.c: the one pad it has. */
+#define RAN_LIGHT 0x1
+
#define CLEANUP_REC(begin, end, landing_pad) \
".pushsection .bpf_cleanup,\"a\",@progbits;" \
".long " begin ";" \
diff --git a/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c b/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c
index ffc0b9519168..ad0ff949f10d 100644
--- a/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c
+++ b/tools/testing/selftests/bpf/prog_tests/exceptions_cleanup.c
@@ -8,6 +8,7 @@
#include "exceptions_cleanup_freplace.skel.h"
#include "exceptions_cleanup_pad_freplace.skel.h"
#include "exceptions_cleanup_ext_table.skel.h"
+#include "exceptions_cleanup_light.lskel.h"
/* foo3 threw: every frame that has a pad ran it. */
#define PADS_FOO3_THREW \
@@ -170,6 +171,30 @@ static void test_ext_table(struct exceptions_cleanup_shapes *skel)
exceptions_cleanup_ext_table__destroy(fr);
}
+static void test_light_skeleton(void)
+{
+ struct exceptions_cleanup_light_lskel *skel;
+ __u64 ctx = 0;
+ int err;
+
+ LIBBPF_OPTS(bpf_test_run_opts, topts,
+ .ctx_in = &ctx,
+ .ctx_size_in = sizeof(ctx),
+ );
+
+ skel = exceptions_cleanup_light_lskel__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "light open_and_load"))
+ return;
+
+ err = bpf_prog_test_run_opts(skel->progs.entry_light.prog_fd, &topts);
+ if (!ASSERT_OK(err, "run"))
+ goto out;
+ ASSERT_EQ(topts.retval, THROW_COOKIE, "retval");
+ ASSERT_EQ(skel->bss->pads_ran, RAN_LIGHT, "pads_ran");
+out:
+ exceptions_cleanup_light_lskel__destroy(skel);
+}
+
static void test_shapes(void)
{
struct exceptions_cleanup_shapes *skel;
@@ -387,6 +412,9 @@ void test_exceptions_cleanup(void)
exceptions_cleanup__destroy(skel);
+ if (test__start_subtest("light_skeleton"))
+ test_light_skeleton();
+
test_shapes();
RUN_TESTS(exceptions_cleanup_fail);
diff --git a/tools/testing/selftests/bpf/progs/exceptions_cleanup_light.c b/tools/testing/selftests/bpf/progs/exceptions_cleanup_light.c
new file mode 100644
index 000000000000..de7ae478d67f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/exceptions_cleanup_light.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "exceptions_cleanup.h"
+
+static __used __noinline void __kfunc_btf_anchor(void)
+{
+ bpf_throw(0);
+ bpf_preempt_disable();
+ bpf_preempt_enable();
+ bpf_unwind_resume();
+}
+
+__u64 pads_ran = 0;
+
+SEC("syscall")
+__naked int entry_light(void)
+{
+ asm volatile (
+ "call bpf_preempt_disable;"
+ "r1 = %[cookie];"
+"1:" "call bpf_throw;" /* cleanup region */
+"2:"
+ "exit;"
+"3:" /* landing pad */
+ "call bpf_preempt_enable;"
+ PAD_RAN("%[ran]")
+ "call bpf_unwind_resume;"
+ "exit;"
+ CLEANUP_REC("1b", "2b", "3b")
+ :
+ : [cookie]"i"(THROW_COOKIE), [ran]"i"(RAN_LIGHT),
+ __imm_addr(pads_ran)
+ : __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 40+ messages in thread