* [PATCHv5 bpf-next 17/28] libbpf: Add bpf_object_cleanup_btf function
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
Adding bpf_object_cleanup_btf function to cleanup btf objects.
It will be used in following changes.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/lib/bpf/libbpf.c | 16 ++++++++++++----
1 file changed, 12 insertions(+), 4 deletions(-)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index f1f627c86f35..59de338126fb 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8942,13 +8942,10 @@ static void bpf_object_unpin(struct bpf_object *obj)
bpf_map__unpin(&obj->maps[i], NULL);
}
-static void bpf_object_post_load_cleanup(struct bpf_object *obj)
+static void bpf_object_cleanup_btf(struct bpf_object *obj)
{
int i;
- /* clean up fd_array */
- zfree(&obj->fd_array);
-
/* clean up module BTFs */
for (i = 0; i < obj->btf_module_cnt; i++) {
close(obj->btf_modules[i].fd);
@@ -8956,6 +8953,8 @@ static void bpf_object_post_load_cleanup(struct bpf_object *obj)
free(obj->btf_modules[i].name);
}
obj->btf_module_cnt = 0;
+ obj->btf_module_cap = 0;
+ obj->btf_modules_loaded = false;
zfree(&obj->btf_modules);
/* clean up vmlinux BTF */
@@ -8963,6 +8962,15 @@ static void bpf_object_post_load_cleanup(struct bpf_object *obj)
obj->btf_vmlinux = NULL;
}
+static void bpf_object_post_load_cleanup(struct bpf_object *obj)
+{
+ /* clean up fd_array */
+ zfree(&obj->fd_array);
+
+ /* clean up BTF */
+ bpf_object_cleanup_btf(obj);
+}
+
static int bpf_object_prepare(struct bpf_object *obj, const char *target_btf_path)
{
int err;
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 16/28] bpf: Add support for tracing_multi link fdinfo
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
Adding tracing_multi link fdinfo support with following output:
pos: 0
flags: 02000000
mnt_id: 19
ino: 3087
link_type: tracing_multi
link_id: 9
prog_tag: 599ba0e317244f86
prog_id: 94
attach_type: 59
cnt: 10
obj-id btf-id cookie func
1 91593 8 bpf_fentry_test1+0x4/0x10
1 91595 9 bpf_fentry_test2+0x4/0x10
1 91596 7 bpf_fentry_test3+0x4/0x20
1 91597 5 bpf_fentry_test4+0x4/0x20
1 91598 4 bpf_fentry_test5+0x4/0x20
1 91599 2 bpf_fentry_test6+0x4/0x20
1 91600 3 bpf_fentry_test7+0x4/0x10
1 91601 1 bpf_fentry_test8+0x4/0x10
1 91602 10 bpf_fentry_test9+0x4/0x10
1 91594 6 bpf_fentry_test10+0x4/0x10
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
kernel/trace/bpf_trace.c | 30 ++++++++++++++++++++++++++++++
1 file changed, 30 insertions(+)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 8e71d56f337c..35927640c4f2 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -3622,9 +3622,39 @@ static void bpf_tracing_multi_link_dealloc(struct bpf_link *link)
kvfree(tr_link);
}
+#ifdef CONFIG_PROC_FS
+static void bpf_tracing_multi_show_fdinfo(const struct bpf_link *link,
+ struct seq_file *seq)
+{
+ struct bpf_tracing_multi_link *tr_link =
+ container_of(link, struct bpf_tracing_multi_link, link);
+ bool has_cookies = !!tr_link->cookies;
+
+ seq_printf(seq, "attach_type:\t%u\n", tr_link->link.attach_type);
+ seq_printf(seq, "cnt:\t%u\n", tr_link->nodes_cnt);
+
+ seq_printf(seq, "%s\t %s\t %s\t %s\n", "obj-id", "btf-id", "cookie", "func");
+ for (int i = 0; i < tr_link->nodes_cnt; i++) {
+ struct bpf_tracing_multi_node *mnode = &tr_link->nodes[i];
+ u32 btf_id, obj_id;
+
+ bpf_trampoline_unpack_key(mnode->trampoline->key, &obj_id, &btf_id);
+ seq_printf(seq, "%u\t %u\t %llu\t %pS\n",
+ obj_id, btf_id,
+ has_cookies ? tr_link->cookies[i] : 0,
+ (void *) mnode->trampoline->ip);
+
+ cond_resched();
+ }
+}
+#endif
+
static const struct bpf_link_ops bpf_tracing_multi_link_lops = {
.release = bpf_tracing_multi_link_release,
.dealloc_deferred = bpf_tracing_multi_link_dealloc,
+#ifdef CONFIG_PROC_FS
+ .show_fdinfo = bpf_tracing_multi_show_fdinfo,
+#endif
};
int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr)
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 15/28] bpf: Add support for tracing_multi link session
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
Adding support to use session attachment with tracing_multi link.
Adding new BPF_TRACE_FSESSION_MULTI program attach type, that follows
the BPF_TRACE_FSESSION behaviour but on the tracing_multi link.
Such program is called on entry and exit of the attached function
and allows to pass cookie value from entry to exit execution.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
include/linux/bpf.h | 6 ++++-
include/uapi/linux/bpf.h | 1 +
kernel/bpf/btf.c | 1 +
kernel/bpf/fixups.c | 1 +
kernel/bpf/syscall.c | 1 +
kernel/bpf/trampoline.c | 44 +++++++++++++++++++++++++++-------
kernel/bpf/verifier.c | 20 ++++++++++++----
kernel/trace/bpf_trace.c | 15 +++++++++++-
net/bpf/test_run.c | 1 +
tools/include/uapi/linux/bpf.h | 1 +
tools/lib/bpf/libbpf.c | 1 +
11 files changed, 77 insertions(+), 15 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e6e859cf64bf..c4cd751c962f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1932,6 +1932,7 @@ struct bpf_tracing_multi_link {
struct bpf_link link;
struct bpf_tracing_multi_data data;
u64 *cookies;
+ struct bpf_tramp_node *fexits;
int nodes_cnt;
struct bpf_tracing_multi_node nodes[] __counted_by(nodes_cnt);
};
@@ -2119,7 +2120,8 @@ static inline void bpf_prog_put_recursion_context(struct bpf_prog *prog)
static inline bool is_tracing_multi(enum bpf_attach_type type)
{
- return type == BPF_TRACE_FENTRY_MULTI || type == BPF_TRACE_FEXIT_MULTI;
+ return type == BPF_TRACE_FENTRY_MULTI || type == BPF_TRACE_FEXIT_MULTI ||
+ type == BPF_TRACE_FSESSION_MULTI;
}
#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL)
@@ -2243,6 +2245,8 @@ static inline int bpf_fsession_cnt(struct bpf_tramp_nodes *nodes)
for (int i = 0; i < nodes[BPF_TRAMP_FENTRY].nr_nodes; i++) {
if (fentries.nodes[i]->link->prog->expected_attach_type == BPF_TRACE_FSESSION)
cnt++;
+ if (fentries.nodes[i]->link->prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI)
+ cnt++;
}
return cnt;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 61f124992416..22f96ad0d00b 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1156,6 +1156,7 @@ enum bpf_attach_type {
BPF_TRACE_FSESSION,
BPF_TRACE_FENTRY_MULTI,
BPF_TRACE_FEXIT_MULTI,
+ BPF_TRACE_FSESSION_MULTI,
__MAX_BPF_ATTACH_TYPE
};
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index e76b549115d2..05c77743021d 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6282,6 +6282,7 @@ static int btf_validate_prog_ctx_type(struct bpf_verifier_log *log, const struct
case BPF_TRACE_FEXIT:
case BPF_MODIFY_RETURN:
case BPF_TRACE_FSESSION:
+ case BPF_TRACE_FSESSION_MULTI:
case BPF_TRACE_FENTRY_MULTI:
case BPF_TRACE_FEXIT_MULTI:
/* allow u64* as ctx */
diff --git a/kernel/bpf/fixups.c b/kernel/bpf/fixups.c
index 1388e292d1a5..3a70be72d7b6 100644
--- a/kernel/bpf/fixups.c
+++ b/kernel/bpf/fixups.c
@@ -2050,6 +2050,7 @@ int bpf_do_misc_fixups(struct bpf_verifier_env *env)
if (eatype == BPF_TRACE_FEXIT ||
eatype == BPF_TRACE_FSESSION ||
eatype == BPF_TRACE_FEXIT_MULTI ||
+ eatype == BPF_TRACE_FSESSION_MULTI ||
eatype == BPF_MODIFY_RETURN) {
/* Load nr_args from ctx - 8 */
insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 2730f8e8ac67..1b10ff323cd7 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4412,6 +4412,7 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
case BPF_TRACE_FENTRY:
case BPF_TRACE_FEXIT:
case BPF_TRACE_FSESSION:
+ case BPF_TRACE_FSESSION_MULTI:
case BPF_TRACE_FENTRY_MULTI:
case BPF_TRACE_FEXIT_MULTI:
case BPF_MODIFY_RETURN:
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index c0d85befe0f0..61dd7b0eae7a 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -182,7 +182,8 @@ bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
case BPF_PROG_TYPE_TRACING:
if (eatype == BPF_TRACE_FENTRY || eatype == BPF_TRACE_FEXIT ||
eatype == BPF_MODIFY_RETURN || eatype == BPF_TRACE_FSESSION ||
- eatype == BPF_TRACE_FENTRY_MULTI || eatype == BPF_TRACE_FEXIT_MULTI)
+ eatype == BPF_TRACE_FENTRY_MULTI || eatype == BPF_TRACE_FEXIT_MULTI ||
+ eatype == BPF_TRACE_FSESSION_MULTI)
return true;
return false;
case BPF_PROG_TYPE_LSM:
@@ -790,6 +791,7 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog)
case BPF_TRACE_FEXIT_MULTI:
return BPF_TRAMP_FEXIT;
case BPF_TRACE_FSESSION:
+ case BPF_TRACE_FSESSION_MULTI:
return BPF_TRAMP_FSESSION;
case BPF_LSM_MAC:
if (!prog->aux->attach_func_proto->type)
@@ -822,13 +824,30 @@ static int bpf_freplace_check_tgt_prog(struct bpf_prog *tgt_prog)
return 0;
}
+static struct bpf_tramp_node *fsession_exit(struct bpf_tramp_node *node)
+{
+ if (node->link->type == BPF_LINK_TYPE_TRACING) {
+ struct bpf_tracing_link *link;
+
+ link = container_of(node->link, struct bpf_tracing_link, link.link);
+ return &link->fexit;
+ } else if (node->link->type == BPF_LINK_TYPE_TRACING_MULTI) {
+ struct bpf_tracing_multi_link *link;
+ struct bpf_tracing_multi_node *mnode;
+
+ link = container_of(node->link, struct bpf_tracing_multi_link, link);
+ mnode = container_of(node, struct bpf_tracing_multi_node, node);
+ return &link->fexits[mnode - link->nodes];
+ }
+ return NULL;
+}
+
static int bpf_trampoline_add_prog(struct bpf_trampoline *tr,
struct bpf_tramp_node *node,
int cnt)
{
- struct bpf_tracing_link *tr_link = NULL;
enum bpf_tramp_prog_type kind;
- struct bpf_tramp_node *node_existing;
+ struct bpf_tramp_node *node_existing, *fexit;
struct hlist_head *prog_list;
kind = bpf_attach_type_to_tramp(node->link->prog);
@@ -853,8 +872,10 @@ static int bpf_trampoline_add_prog(struct bpf_trampoline *tr,
hlist_add_head(&node->tramp_hlist, prog_list);
if (kind == BPF_TRAMP_FSESSION) {
tr->progs_cnt[BPF_TRAMP_FENTRY]++;
- tr_link = container_of(node, struct bpf_tracing_link, link.node);
- hlist_add_head(&tr_link->fexit.tramp_hlist, &tr->progs_hlist[BPF_TRAMP_FEXIT]);
+ fexit = fsession_exit(node);
+ if (WARN_ON_ONCE(!fexit))
+ return -EINVAL;
+ hlist_add_head(&fexit->tramp_hlist, &tr->progs_hlist[BPF_TRAMP_FEXIT]);
tr->progs_cnt[BPF_TRAMP_FEXIT]++;
} else {
tr->progs_cnt[kind]++;
@@ -865,13 +886,15 @@ static int bpf_trampoline_add_prog(struct bpf_trampoline *tr,
static void bpf_trampoline_remove_prog(struct bpf_trampoline *tr,
struct bpf_tramp_node *node)
{
- struct bpf_tracing_link *tr_link;
enum bpf_tramp_prog_type kind;
+ struct bpf_tramp_node *fexit;
kind = bpf_attach_type_to_tramp(node->link->prog);
if (kind == BPF_TRAMP_FSESSION) {
- tr_link = container_of(node, struct bpf_tracing_link, link.node);
- hlist_del_init(&tr_link->fexit.tramp_hlist);
+ fexit = fsession_exit(node);
+ if (WARN_ON_ONCE(!fexit))
+ return;
+ hlist_del_init(&fexit->tramp_hlist);
tr->progs_cnt[BPF_TRAMP_FEXIT]--;
kind = BPF_TRAMP_FENTRY;
}
@@ -1615,6 +1638,11 @@ int bpf_trampoline_multi_attach(struct bpf_prog *prog, u32 *ids,
mnode->node.link = &link->link;
mnode->node.cookie = link->cookies ? link->cookies[i] : 0;
+ if (prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI) {
+ link->fexits[i].link = &link->link;
+ link->fexits[i].cookie = link->cookies ? link->cookies[i] : 0;
+ }
+
cond_resched();
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 4f5a21a4eddc..2689d93cd5e1 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -16767,6 +16767,7 @@ static bool return_retval_range(struct bpf_verifier_env *env, struct bpf_retval_
case BPF_TRACE_FSESSION:
case BPF_TRACE_FENTRY_MULTI:
case BPF_TRACE_FEXIT_MULTI:
+ case BPF_TRACE_FSESSION_MULTI:
*range = retval_range(0, 0);
break;
case BPF_TRACE_RAW_TP:
@@ -19294,7 +19295,8 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
tgt_prog->expected_attach_type == BPF_TRACE_FEXIT ||
tgt_prog->expected_attach_type == BPF_TRACE_FENTRY_MULTI ||
tgt_prog->expected_attach_type == BPF_TRACE_FEXIT_MULTI ||
- tgt_prog->expected_attach_type == BPF_TRACE_FSESSION)) {
+ tgt_prog->expected_attach_type == BPF_TRACE_FSESSION ||
+ tgt_prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI)) {
/* Program extensions can extend all program types
* except fentry/fexit. The reason is the following.
* The fentry/fexit programs are used for performance
@@ -19394,9 +19396,11 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
case BPF_TRACE_FENTRY:
case BPF_TRACE_FEXIT:
case BPF_TRACE_FSESSION:
+ case BPF_TRACE_FSESSION_MULTI:
case BPF_TRACE_FENTRY_MULTI:
case BPF_TRACE_FEXIT_MULTI:
- if (prog->expected_attach_type == BPF_TRACE_FSESSION &&
+ if ((prog->expected_attach_type == BPF_TRACE_FSESSION ||
+ prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI) &&
!bpf_jit_supports_fsession()) {
bpf_log(log, "JIT does not support fsession\n");
return -EOPNOTSUPP;
@@ -19547,6 +19551,7 @@ static bool can_be_sleepable(struct bpf_prog *prog)
case BPF_MODIFY_RETURN:
case BPF_TRACE_ITER:
case BPF_TRACE_FSESSION:
+ case BPF_TRACE_FSESSION_MULTI:
case BPF_TRACE_FENTRY_MULTI:
case BPF_TRACE_FEXIT_MULTI:
return true;
@@ -19631,6 +19636,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
return -EINVAL;
} else if ((prog->expected_attach_type == BPF_TRACE_FEXIT ||
prog->expected_attach_type == BPF_TRACE_FSESSION ||
+ prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI ||
prog->expected_attach_type == BPF_MODIFY_RETURN) &&
btf_id_set_contains(&noreturn_deny, btf_id)) {
verbose(env, "Attaching fexit/fsession/fmod_ret to __noreturn function '%s' is rejected.\n",
@@ -19670,7 +19676,8 @@ int bpf_check_attach_btf_id_multi(struct btf *btf, struct bpf_prog *prog, u32 bt
return -EINVAL;
/* Check noreturn attachment. */
- if (prog->expected_attach_type == BPF_TRACE_FEXIT_MULTI ||
+ if ((prog->expected_attach_type == BPF_TRACE_FEXIT_MULTI ||
+ prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI) &&
btf_id_set_contains(&noreturn_deny, btf_id))
return -EINVAL;
@@ -19947,7 +19954,9 @@ int bpf_fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1);
*cnt = 1;
} else if (desc->func_id == special_kfunc_list[KF_bpf_session_is_return] &&
- env->prog->expected_attach_type == BPF_TRACE_FSESSION) {
+ (env->prog->expected_attach_type == BPF_TRACE_FSESSION ||
+ env->prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI)) {
+
/*
* inline the bpf_session_is_return() for fsession:
* bool bpf_session_is_return(void *ctx)
@@ -19960,7 +19969,8 @@ int bpf_fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
insn_buf[2] = BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1);
*cnt = 3;
} else if (desc->func_id == special_kfunc_list[KF_bpf_session_cookie] &&
- env->prog->expected_attach_type == BPF_TRACE_FSESSION) {
+ (env->prog->expected_attach_type == BPF_TRACE_FSESSION ||
+ env->prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI)) {
/*
* inline bpf_session_cookie() for fsession:
* __u64 *bpf_session_cookie(void *ctx)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 59b65d3d789f..8e71d56f337c 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1306,7 +1306,8 @@ static inline bool is_uprobe_session(const struct bpf_prog *prog)
static inline bool is_trace_fsession(const struct bpf_prog *prog)
{
return prog->type == BPF_PROG_TYPE_TRACING &&
- prog->expected_attach_type == BPF_TRACE_FSESSION;
+ (prog->expected_attach_type == BPF_TRACE_FSESSION ||
+ prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI);
}
static const struct bpf_func_proto *
@@ -3616,6 +3617,7 @@ static void bpf_tracing_multi_link_dealloc(struct bpf_link *link)
struct bpf_tracing_multi_link *tr_link =
container_of(link, struct bpf_tracing_multi_link, link);
+ kvfree(tr_link->fexits);
kvfree(tr_link->cookies);
kvfree(tr_link);
}
@@ -3628,6 +3630,7 @@ static const struct bpf_link_ops bpf_tracing_multi_link_lops = {
int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr)
{
struct bpf_tracing_multi_link *link = NULL;
+ struct bpf_tramp_node *fexits = NULL;
struct bpf_link_primer link_primer;
u32 cnt, *ids = NULL;
u64 __user *ucookies;
@@ -3667,6 +3670,14 @@ int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr)
}
}
+ if (prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI) {
+ fexits = kvmalloc_objs(*fexits, cnt);
+ if (!fexits) {
+ err = -ENOMEM;
+ goto error;
+ }
+ }
+
link = kvzalloc_flex(*link, nodes, cnt);
if (!link) {
err = -ENOMEM;
@@ -3682,6 +3693,7 @@ int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr)
link->nodes_cnt = cnt;
link->cookies = cookies;
+ link->fexits = fexits;
err = bpf_trampoline_multi_attach(prog, ids, link);
kvfree(ids);
@@ -3692,6 +3704,7 @@ int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr)
return bpf_link_settle(&link_primer);
error:
+ kvfree(fexits);
kvfree(cookies);
kvfree(ids);
kvfree(link);
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 5495d105bc09..4f0bc4cb264f 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -705,6 +705,7 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog,
case BPF_TRACE_FSESSION:
case BPF_TRACE_FENTRY_MULTI:
case BPF_TRACE_FEXIT_MULTI:
+ case BPF_TRACE_FSESSION_MULTI:
if (bpf_fentry_test1(1) != 2 ||
bpf_fentry_test2(2, 3) != 5 ||
bpf_fentry_test3(4, 5, 6) != 15 ||
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 61f124992416..22f96ad0d00b 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1156,6 +1156,7 @@ enum bpf_attach_type {
BPF_TRACE_FSESSION,
BPF_TRACE_FENTRY_MULTI,
BPF_TRACE_FEXIT_MULTI,
+ BPF_TRACE_FSESSION_MULTI,
__MAX_BPF_ATTACH_TYPE
};
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index f0c663253fd6..f1f627c86f35 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -138,6 +138,7 @@ static const char * const attach_type_name[] = {
[BPF_TRACE_UPROBE_SESSION] = "trace_uprobe_session",
[BPF_TRACE_FENTRY_MULTI] = "trace_fentry_multi",
[BPF_TRACE_FEXIT_MULTI] = "trace_fexit_multi",
+ [BPF_TRACE_FSESSION_MULTI] = "trace_fsession_multi",
};
static const char * const link_type_name[] = {
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 14/28] bpf: Add support for tracing_multi link cookies
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
Add support to specify cookies for tracing_multi link.
Cookies are provided in array where each value is paired with provided
BTF ID value with the same array index.
Such cookie can be retrieved by bpf program with bpf_get_attach_cookie
helper call.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
include/linux/bpf.h | 1 +
include/uapi/linux/bpf.h | 1 +
kernel/bpf/trampoline.c | 1 +
kernel/trace/bpf_trace.c | 18 ++++++++++++++++++
tools/include/uapi/linux/bpf.h | 1 +
5 files changed, 22 insertions(+)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 37c96daaae9a..e6e859cf64bf 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1931,6 +1931,7 @@ struct bpf_tracing_multi_data {
struct bpf_tracing_multi_link {
struct bpf_link link;
struct bpf_tracing_multi_data data;
+ u64 *cookies;
int nodes_cnt;
struct bpf_tracing_multi_node nodes[] __counted_by(nodes_cnt);
};
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 9eeffc93faeb..61f124992416 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1866,6 +1866,7 @@ union bpf_attr {
} cgroup;
struct {
__aligned_u64 ids;
+ __aligned_u64 cookies;
__u32 cnt;
} tracing_multi;
};
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index f6180f15d5a4..c0d85befe0f0 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -1613,6 +1613,7 @@ int bpf_trampoline_multi_attach(struct bpf_prog *prog, u32 *ids,
mnode->trampoline = tr;
mnode->node.link = &link->link;
+ mnode->node.cookie = link->cookies ? link->cookies[i] : 0;
cond_resched();
}
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index df06a733a2e7..59b65d3d789f 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -3616,6 +3616,7 @@ static void bpf_tracing_multi_link_dealloc(struct bpf_link *link)
struct bpf_tracing_multi_link *tr_link =
container_of(link, struct bpf_tracing_multi_link, link);
+ kvfree(tr_link->cookies);
kvfree(tr_link);
}
@@ -3629,6 +3630,8 @@ int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr)
struct bpf_tracing_multi_link *link = NULL;
struct bpf_link_primer link_primer;
u32 cnt, *ids = NULL;
+ u64 __user *ucookies;
+ u64 *cookies = NULL;
u32 __user *uids;
int err;
@@ -3651,6 +3654,19 @@ int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr)
goto error;
}
+ ucookies = u64_to_user_ptr(attr->link_create.tracing_multi.cookies);
+ if (ucookies) {
+ cookies = kvmalloc_objs(*cookies, cnt);
+ if (!cookies) {
+ err = -ENOMEM;
+ goto error;
+ }
+ if (copy_from_user(cookies, ucookies, cnt * sizeof(*cookies))) {
+ err = -EFAULT;
+ goto error;
+ }
+ }
+
link = kvzalloc_flex(*link, nodes, cnt);
if (!link) {
err = -ENOMEM;
@@ -3665,6 +3681,7 @@ int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr)
goto error;
link->nodes_cnt = cnt;
+ link->cookies = cookies;
err = bpf_trampoline_multi_attach(prog, ids, link);
kvfree(ids);
@@ -3675,6 +3692,7 @@ int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr)
return bpf_link_settle(&link_primer);
error:
+ kvfree(cookies);
kvfree(ids);
kvfree(link);
return err;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 9eeffc93faeb..61f124992416 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1866,6 +1866,7 @@ union bpf_attr {
} cgroup;
struct {
__aligned_u64 ids;
+ __aligned_u64 cookies;
__u32 cnt;
} tracing_multi;
};
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 13/28] bpf: Add support for tracing multi link
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
Adding new link to allow to attach program to multiple function
BTF IDs. The link is represented by struct bpf_tracing_multi_link.
To configure the link, new fields are added to bpf_attr::link_create
to pass array of BTF IDs;
struct {
__aligned_u64 ids;
__u32 cnt;
} tracing_multi;
Each BTF ID represents function (BTF_KIND_FUNC) that the link will
attach bpf program to.
We use previously added bpf_trampoline_multi_attach/detach functions
to attach/detach the link.
The linkinfo/fdinfo callbacks will be implemented in following changes.
Note this is supported only for archs (x86_64) with ftrace direct and
have single ops support.
CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS &&
CONFIG_HAVE_SINGLE_FTRACE_DIRECT_OPS
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
include/linux/bpf_types.h | 1 +
include/linux/trace_events.h | 6 +++
include/uapi/linux/bpf.h | 5 ++
kernel/bpf/syscall.c | 2 +
kernel/trace/bpf_trace.c | 90 ++++++++++++++++++++++++++++++++++
tools/include/uapi/linux/bpf.h | 6 +++
tools/lib/bpf/libbpf.c | 1 +
7 files changed, 111 insertions(+)
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index b13de31e163f..96575b5b563e 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -155,3 +155,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf)
BPF_LINK_TYPE(BPF_LINK_TYPE_KPROBE_MULTI, kprobe_multi)
BPF_LINK_TYPE(BPF_LINK_TYPE_STRUCT_OPS, struct_ops)
BPF_LINK_TYPE(BPF_LINK_TYPE_UPROBE_MULTI, uprobe_multi)
+BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING_MULTI, tracing_multi)
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 40a43a4c7caf..de3569167118 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -786,6 +786,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
unsigned long *missed);
int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr);
#else
static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
{
@@ -838,6 +839,11 @@ bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
return -EOPNOTSUPP;
}
+static inline int
+bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr)
+{
+ return -EOPNOTSUPP;
+}
#endif
enum {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 5f814e7101cf..9eeffc93faeb 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1180,6 +1180,7 @@ enum bpf_link_type {
BPF_LINK_TYPE_UPROBE_MULTI = 12,
BPF_LINK_TYPE_NETKIT = 13,
BPF_LINK_TYPE_SOCKMAP = 14,
+ BPF_LINK_TYPE_TRACING_MULTI = 15,
__MAX_BPF_LINK_TYPE,
};
@@ -1863,6 +1864,10 @@ union bpf_attr {
};
__u64 expected_revision;
} cgroup;
+ struct {
+ __aligned_u64 ids;
+ __u32 cnt;
+ } tracing_multi;
};
} link_create;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 47c43c330c47..2730f8e8ac67 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5773,6 +5773,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
ret = bpf_iter_link_attach(attr, uattr, prog);
else if (prog->expected_attach_type == BPF_LSM_CGROUP)
ret = cgroup_bpf_link_attach(attr, prog);
+ else if (is_tracing_multi(prog->expected_attach_type))
+ ret = bpf_tracing_multi_attach(prog, attr);
else
ret = bpf_tracing_prog_attach(prog,
attr->link_create.target_fd,
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index af7079aa0f36..df06a733a2e7 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -42,6 +42,7 @@
#define MAX_UPROBE_MULTI_CNT (1U << 20)
#define MAX_KPROBE_MULTI_CNT (1U << 20)
+#define MAX_TRACING_MULTI_CNT (1U << 20)
#ifdef CONFIG_MODULES
struct bpf_trace_module {
@@ -3598,3 +3599,92 @@ __bpf_kfunc int bpf_copy_from_user_task_str_dynptr(struct bpf_dynptr *dptr, u64
}
__bpf_kfunc_end_defs();
+
+#if defined(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS) && \
+ defined(CONFIG_HAVE_SINGLE_FTRACE_DIRECT_OPS)
+
+static void bpf_tracing_multi_link_release(struct bpf_link *link)
+{
+ struct bpf_tracing_multi_link *tr_link =
+ container_of(link, struct bpf_tracing_multi_link, link);
+
+ WARN_ON_ONCE(bpf_trampoline_multi_detach(link->prog, tr_link));
+}
+
+static void bpf_tracing_multi_link_dealloc(struct bpf_link *link)
+{
+ struct bpf_tracing_multi_link *tr_link =
+ container_of(link, struct bpf_tracing_multi_link, link);
+
+ kvfree(tr_link);
+}
+
+static const struct bpf_link_ops bpf_tracing_multi_link_lops = {
+ .release = bpf_tracing_multi_link_release,
+ .dealloc_deferred = bpf_tracing_multi_link_dealloc,
+};
+
+int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr)
+{
+ struct bpf_tracing_multi_link *link = NULL;
+ struct bpf_link_primer link_primer;
+ u32 cnt, *ids = NULL;
+ u32 __user *uids;
+ int err;
+
+ uids = u64_to_user_ptr(attr->link_create.tracing_multi.ids);
+ cnt = attr->link_create.tracing_multi.cnt;
+
+ if (!cnt || !uids)
+ return -EINVAL;
+ if (cnt > MAX_TRACING_MULTI_CNT)
+ return -E2BIG;
+ if (attr->link_create.flags || attr->link_create.target_fd)
+ return -EINVAL;
+
+ ids = kvmalloc_objs(*ids, cnt);
+ if (!ids)
+ return -ENOMEM;
+
+ if (copy_from_user(ids, uids, cnt * sizeof(*ids))) {
+ err = -EFAULT;
+ goto error;
+ }
+
+ link = kvzalloc_flex(*link, nodes, cnt);
+ if (!link) {
+ err = -ENOMEM;
+ goto error;
+ }
+
+ bpf_link_init(&link->link, BPF_LINK_TYPE_TRACING_MULTI,
+ &bpf_tracing_multi_link_lops, prog, prog->expected_attach_type);
+
+ err = bpf_link_prime(&link->link, &link_primer);
+ if (err)
+ goto error;
+
+ link->nodes_cnt = cnt;
+
+ err = bpf_trampoline_multi_attach(prog, ids, link);
+ kvfree(ids);
+ if (err) {
+ bpf_link_cleanup(&link_primer);
+ return err;
+ }
+ return bpf_link_settle(&link_primer);
+
+error:
+ kvfree(ids);
+ kvfree(link);
+ return err;
+}
+
+#else
+
+int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr)
+{
+ return -EOPNOTSUPP;
+}
+
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS && CONFIG_HAVE_SINGLE_FTRACE_DIRECT_OPS */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 34615f905215..9eeffc93faeb 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1180,6 +1180,7 @@ enum bpf_link_type {
BPF_LINK_TYPE_UPROBE_MULTI = 12,
BPF_LINK_TYPE_NETKIT = 13,
BPF_LINK_TYPE_SOCKMAP = 14,
+ BPF_LINK_TYPE_TRACING_MULTI = 15,
__MAX_BPF_LINK_TYPE,
};
@@ -1863,6 +1864,10 @@ union bpf_attr {
};
__u64 expected_revision;
} cgroup;
+ struct {
+ __aligned_u64 ids;
+ __u32 cnt;
+ } tracing_multi;
};
} link_create;
@@ -7238,6 +7243,7 @@ enum {
TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */
SK_BPF_CB_FLAGS = 1009, /* Get or set sock ops flags in socket */
SK_BPF_BYPASS_PROT_MEM = 1010, /* Get or Set sk->sk_bypass_prot_mem */
+
};
enum {
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 24e02ff039eb..f0c663253fd6 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -156,6 +156,7 @@ static const char * const link_type_name[] = {
[BPF_LINK_TYPE_UPROBE_MULTI] = "uprobe_multi",
[BPF_LINK_TYPE_NETKIT] = "netkit",
[BPF_LINK_TYPE_SOCKMAP] = "sockmap",
+ [BPF_LINK_TYPE_TRACING_MULTI] = "tracing_multi",
};
static const char * const map_type_name[] = {
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 12/28] bpf: Add bpf_trampoline_multi_attach/detach functions
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
Adding bpf_trampoline_multi_attach/detach functions that allows to
attach/detach tracing program to multiple functions/trampolines.
The attachment is defined with bpf_program and array of BTF ids of
functions to attach the bpf program to.
Adding bpf_tracing_multi_link object that holds all the attached
trampolines and is initialized in attach and used in detach.
The attachment allocates or uses currently existing trampoline
for each function to attach and links it with the bpf program.
The attach works as follows:
- we get all the needed trampolines
- lock them and add the bpf program to each (__bpf_trampoline_link_prog)
- the trampoline_multi_ops passed in __bpf_trampoline_link_prog gathers
ftrace_hash (ip -> trampoline) objects
- we call update_ftrace_direct_add/mod to update needed locations
- we unlock all the trampolines
The detach works as follows:
- we lock all the needed trampolines
- remove the program from each (__bpf_trampoline_unlink_prog)
- the trampoline_multi_ops passed in __bpf_trampoline_unlink_prog gathers
ftrace_hash (ip -> trampoline) objects
- we call update_ftrace_direct_del/mod to update needed locations
- we unlock and put all the trampolines
We store the old image/flags in the trampoline before the update
and use it in case we need to rollback the attachment.
We keep the ftrace_hash objects allocated during attach in the link
so they can be used for detach as well.
Adding trampoline_(un)lock_all functions to (un)lock all trampolines
to gate the tracing_multi attachment.
Note this is supported only for archs (x86_64) with ftrace direct and
have single ops support.
CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS &&
CONFIG_HAVE_SINGLE_FTRACE_DIRECT_OPS
It also needs CONFIG_BPF_SYSCALL enabled.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
include/linux/bpf.h | 43 ++++++
include/linux/bpf_verifier.h | 4 +
kernel/bpf/trampoline.c | 270 +++++++++++++++++++++++++++++++++++
kernel/bpf/verifier.c | 52 +++++++
4 files changed, 369 insertions(+)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c815227f3bc6..37c96daaae9a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -31,6 +31,7 @@
#include <linux/static_call.h>
#include <linux/memcontrol.h>
#include <linux/cfi.h>
+#include <linux/ftrace.h>
#include <asm/rqspinlock.h>
struct bpf_verifier_env;
@@ -1355,6 +1356,11 @@ struct bpf_trampoline {
int progs_cnt[BPF_TRAMP_MAX];
/* Executable image of trampoline */
struct bpf_tramp_image *cur_image;
+ /* Used as temporary old image storage for multi_attach */
+ struct {
+ struct bpf_tramp_image *old_image;
+ u32 old_flags;
+ } multi_attach;
};
struct bpf_attach_target_info {
@@ -1452,6 +1458,8 @@ static inline int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u6
return 0;
}
+struct bpf_tracing_multi_link;
+
#ifdef CONFIG_BPF_JIT
int bpf_trampoline_link_prog(struct bpf_tramp_node *node,
struct bpf_trampoline *tr,
@@ -1464,6 +1472,11 @@ struct bpf_trampoline *bpf_trampoline_get(u64 key,
void bpf_trampoline_put(struct bpf_trampoline *tr);
int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs);
+int bpf_trampoline_multi_attach(struct bpf_prog *prog, u32 *ids,
+ struct bpf_tracing_multi_link *link);
+int bpf_trampoline_multi_detach(struct bpf_prog *prog,
+ struct bpf_tracing_multi_link *link);
+
/*
* When the architecture supports STATIC_CALL replace the bpf_dispatcher_fn
* indirection with a direct call to the bpf program. If the architecture does
@@ -1573,6 +1586,16 @@ static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
{
return false;
}
+static inline int bpf_trampoline_multi_attach(struct bpf_prog *prog, u32 *ids,
+ struct bpf_tracing_multi_link *link)
+{
+ return -ENOTSUPP;
+}
+static inline int bpf_trampoline_multi_detach(struct bpf_prog *prog,
+ struct bpf_tracing_multi_link *link)
+{
+ return -ENOTSUPP;
+}
#endif
struct bpf_func_info_aux {
@@ -1892,6 +1915,26 @@ struct bpf_tracing_link {
struct bpf_prog *tgt_prog;
};
+struct bpf_tracing_multi_node {
+ struct bpf_tramp_node node;
+ struct bpf_trampoline *trampoline;
+ struct ftrace_func_entry entry;
+};
+
+struct bpf_tracing_multi_data {
+ struct ftrace_hash *unreg;
+ struct ftrace_hash *modify;
+ struct ftrace_hash *reg;
+ struct ftrace_func_entry *entry;
+};
+
+struct bpf_tracing_multi_link {
+ struct bpf_link link;
+ struct bpf_tracing_multi_data data;
+ int nodes_cnt;
+ struct bpf_tracing_multi_node nodes[] __counted_by(nodes_cnt);
+};
+
struct bpf_raw_tp_link {
struct bpf_link link;
struct bpf_raw_event_map *btp;
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 53e8664cb566..055450f8d718 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -1476,6 +1476,10 @@ int bpf_add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, u16 offset);
int bpf_fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
struct bpf_insn *insn_buf, int insn_idx, int *cnt);
+/* Functions exported from verifier.c, used by trampoline.c */
+int bpf_check_attach_btf_id_multi(struct btf *btf, struct bpf_prog *prog, u32 btf_id,
+ struct bpf_attach_target_info *tgt_info);
+
/* Functions in fixups.c, called from bpf_check() */
int bpf_remove_fastcall_spills_fills(struct bpf_verifier_env *env);
int bpf_optimize_bpf_loop(struct bpf_verifier_env *env);
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 23856bd28d59..f6180f15d5a4 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -1447,6 +1447,276 @@ int __weak arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
return -ENOTSUPP;
}
+#if defined(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS) && \
+ defined(CONFIG_HAVE_SINGLE_FTRACE_DIRECT_OPS) && \
+ defined(CONFIG_BPF_SYSCALL)
+
+static void trampoline_lock_all(void)
+{
+ int i;
+
+ for (i = 0; i < TRAMPOLINE_LOCKS_TABLE_SIZE; i++)
+ mutex_lock(&trampoline_locks[i].mutex);
+}
+
+static void trampoline_unlock_all(void)
+{
+ int i;
+
+ for (i = 0; i < TRAMPOLINE_LOCKS_TABLE_SIZE; i++)
+ mutex_unlock(&trampoline_locks[i].mutex);
+}
+
+static void remove_tracing_multi_data(struct bpf_tracing_multi_data *data)
+{
+ ftrace_hash_remove(data->reg);
+ ftrace_hash_remove(data->unreg);
+ ftrace_hash_remove(data->modify);
+}
+
+static void clear_tracing_multi_data(struct bpf_tracing_multi_data *data)
+{
+ remove_tracing_multi_data(data);
+
+ free_ftrace_hash(data->reg);
+ free_ftrace_hash(data->unreg);
+ free_ftrace_hash(data->modify);
+}
+
+static int init_tracing_multi_data(struct bpf_tracing_multi_data *data)
+{
+ data->reg = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS);
+ data->unreg = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS);
+ data->modify = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS);
+
+ if (!data->reg || !data->unreg || !data->modify) {
+ clear_tracing_multi_data(data);
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+static void ftrace_hash_add(struct ftrace_hash *hash, struct ftrace_func_entry *entry,
+ unsigned long ip, unsigned long direct)
+{
+ entry->ip = ip;
+ entry->direct = direct;
+ add_ftrace_hash_entry(hash, entry);
+}
+
+static int register_fentry_multi(struct bpf_trampoline *tr, struct bpf_tramp_image *im, void *ptr)
+{
+ unsigned long addr = (unsigned long) im->image;
+ unsigned long ip = ftrace_location(tr->ip);
+ struct bpf_tracing_multi_data *data = ptr;
+
+ if (bpf_trampoline_use_jmp(tr->flags))
+ addr = ftrace_jmp_set(addr);
+
+ ftrace_hash_add(data->reg, data->entry, ip, addr);
+ tr->cur_image = im;
+ return 0;
+}
+
+static int unregister_fentry_multi(struct bpf_trampoline *tr, u32 orig_flags, void *ptr)
+{
+ unsigned long addr = (unsigned long) tr->cur_image->image;
+ unsigned long ip = ftrace_location(tr->ip);
+ struct bpf_tracing_multi_data *data = ptr;
+
+ if (bpf_trampoline_use_jmp(tr->flags))
+ addr = ftrace_jmp_set(addr);
+
+ ftrace_hash_add(data->unreg, data->entry, ip, addr);
+ tr->cur_image = NULL;
+ return 0;
+}
+
+static int modify_fentry_multi(struct bpf_trampoline *tr, u32 orig_flags, struct bpf_tramp_image *im,
+ bool lock_direct_mutex, void *ptr)
+{
+ unsigned long addr = (unsigned long) im->image;
+ unsigned long ip = ftrace_location(tr->ip);
+ struct bpf_tracing_multi_data *data = ptr;
+
+ if (bpf_trampoline_use_jmp(tr->flags))
+ addr = ftrace_jmp_set(addr);
+
+ ftrace_hash_add(data->modify, data->entry, ip, addr);
+ tr->cur_image = im;
+ return 0;
+}
+
+static const struct bpf_trampoline_ops trampoline_multi_ops = {
+ .register_fentry = register_fentry_multi,
+ .unregister_fentry = unregister_fentry_multi,
+ .modify_fentry = modify_fentry_multi,
+};
+
+static void bpf_trampoline_multi_attach_init(struct bpf_trampoline *tr)
+{
+ tr->multi_attach.old_image = tr->cur_image;
+ tr->multi_attach.old_flags = tr->flags;
+}
+
+static void bpf_trampoline_multi_attach_free(struct bpf_trampoline *tr)
+{
+ if (tr->multi_attach.old_image)
+ bpf_tramp_image_put(tr->multi_attach.old_image);
+
+ tr->multi_attach.old_image = NULL;
+ tr->multi_attach.old_flags = 0;
+}
+
+static void bpf_trampoline_multi_attach_rollback(struct bpf_trampoline *tr)
+{
+ if (tr->cur_image)
+ bpf_tramp_image_put(tr->cur_image);
+ tr->cur_image = tr->multi_attach.old_image;
+ tr->flags = tr->multi_attach.old_flags;
+
+ tr->multi_attach.old_image = NULL;
+ tr->multi_attach.old_flags = 0;
+}
+
+#define for_each_mnode_cnt(mnode, link, cnt) \
+ for (i = 0, mnode = &link->nodes[i]; i < cnt; i++, mnode = &link->nodes[i])
+
+#define for_each_mnode(mnode, link) \
+ for_each_mnode_cnt(mnode, link, link->nodes_cnt)
+
+int bpf_trampoline_multi_attach(struct bpf_prog *prog, u32 *ids,
+ struct bpf_tracing_multi_link *link)
+{
+ struct bpf_tracing_multi_data *data = &link->data;
+ struct bpf_attach_target_info tgt_info = {};
+ struct btf *btf = prog->aux->attach_btf;
+ struct bpf_tracing_multi_node *mnode;
+ struct bpf_trampoline *tr;
+ int i, err, rollback_cnt;
+ u64 key;
+
+ for_each_mnode(mnode, link) {
+ rollback_cnt = i;
+
+ err = bpf_check_attach_btf_id_multi(btf, prog, ids[i], &tgt_info);
+ if (err)
+ goto rollback_put;
+
+ key = bpf_trampoline_compute_key(NULL, btf, ids[i]);
+
+ tr = bpf_trampoline_get(key, &tgt_info);
+ if (!tr) {
+ err = -ENOMEM;
+ goto rollback_put;
+ }
+
+ mnode->trampoline = tr;
+ mnode->node.link = &link->link;
+
+ cond_resched();
+ }
+
+ err = init_tracing_multi_data(data);
+ if (err) {
+ rollback_cnt = link->nodes_cnt;
+ goto rollback_put;
+ }
+
+ trampoline_lock_all();
+
+ for_each_mnode(mnode, link) {
+ bpf_trampoline_multi_attach_init(mnode->trampoline);
+
+ data->entry = &mnode->entry;
+ err = __bpf_trampoline_link_prog(&mnode->node, mnode->trampoline, NULL,
+ &trampoline_multi_ops, data);
+ if (err) {
+ rollback_cnt = i;
+ goto rollback_unlink;
+ }
+ }
+
+ rollback_cnt = link->nodes_cnt;
+ if (ftrace_hash_count(data->reg)) {
+ err = update_ftrace_direct_add(&direct_ops, data->reg);
+ if (err)
+ goto rollback_unlink;
+ }
+
+ if (ftrace_hash_count(data->modify)) {
+ err = update_ftrace_direct_mod(&direct_ops, data->modify, true);
+ if (err) {
+ WARN_ON_ONCE(update_ftrace_direct_del(&direct_ops, data->reg));
+ goto rollback_unlink;
+ }
+ }
+
+ for_each_mnode(mnode, link)
+ bpf_trampoline_multi_attach_free(mnode->trampoline);
+
+ trampoline_unlock_all();
+
+ remove_tracing_multi_data(data);
+ return 0;
+
+rollback_unlink:
+ for_each_mnode_cnt(mnode, link, rollback_cnt) {
+ bpf_trampoline_remove_prog(mnode->trampoline, &mnode->node);
+ bpf_trampoline_multi_attach_rollback(mnode->trampoline);
+ }
+
+ trampoline_unlock_all();
+
+ clear_tracing_multi_data(data);
+ rollback_cnt = link->nodes_cnt;
+
+rollback_put:
+ for_each_mnode_cnt(mnode, link, rollback_cnt)
+ bpf_trampoline_put(mnode->trampoline);
+
+ return err;
+}
+
+int bpf_trampoline_multi_detach(struct bpf_prog *prog, struct bpf_tracing_multi_link *link)
+{
+ struct bpf_tracing_multi_data *data = &link->data;
+ struct bpf_tracing_multi_node *mnode;
+ int i;
+
+ trampoline_lock_all();
+
+ for_each_mnode(mnode, link) {
+ data->entry = &mnode->entry;
+ bpf_trampoline_multi_attach_init(mnode->trampoline);
+ WARN_ON_ONCE(__bpf_trampoline_unlink_prog(&mnode->node, mnode->trampoline,
+ NULL, &trampoline_multi_ops, data));
+ }
+
+ if (ftrace_hash_count(data->unreg))
+ WARN_ON_ONCE(update_ftrace_direct_del(&direct_ops, data->unreg));
+ if (ftrace_hash_count(data->modify))
+ WARN_ON_ONCE(update_ftrace_direct_mod(&direct_ops, data->modify, true));
+
+ for_each_mnode(mnode, link)
+ bpf_trampoline_multi_attach_free(mnode->trampoline);
+
+ trampoline_unlock_all();
+
+ for_each_mnode(mnode, link)
+ bpf_trampoline_put(mnode->trampoline);
+
+ clear_tracing_multi_data(data);
+ return 0;
+}
+
+#undef for_each_mnode_cnt
+#undef for_each_mnode
+
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS &&
+ CONFIG_HAVE_SINGLE_FTRACE_DIRECT_OPS &&
+ CONFIG_BPF_SYSCALL */
+
static int __init init_trampolines(void)
{
int i;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 739e730add96..4f5a21a4eddc 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -19658,6 +19658,58 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
return 0;
}
+int bpf_check_attach_btf_id_multi(struct btf *btf, struct bpf_prog *prog, u32 btf_id,
+ struct bpf_attach_target_info *tgt_info)
+{
+ const struct btf_type *t;
+ unsigned long addr;
+ const char *tname;
+ int err;
+
+ if (!btf_id || !btf)
+ return -EINVAL;
+
+ /* Check noreturn attachment. */
+ if (prog->expected_attach_type == BPF_TRACE_FEXIT_MULTI ||
+ btf_id_set_contains(&noreturn_deny, btf_id))
+ return -EINVAL;
+
+ /* Check and get function target data. */
+ t = btf_type_by_id(btf, btf_id);
+ if (!t)
+ return -EINVAL;
+ tname = btf_name_by_offset(btf, t->name_off);
+ if (!tname)
+ return -EINVAL;
+ if (!btf_type_is_func(t))
+ return -EINVAL;
+ t = btf_type_by_id(btf, t->type);
+ if (!btf_type_is_func_proto(t))
+ return -EINVAL;
+ err = btf_distill_func_proto(NULL, btf, t, tname, &tgt_info->fmodel);
+ if (err < 0)
+ return err;
+ if (btf_is_module(btf)) {
+ /* The bpf program already holds reference to module. */
+ if (WARN_ON_ONCE(!prog->aux->mod))
+ return -EINVAL;
+ addr = find_kallsyms_symbol_value(prog->aux->mod, tname);
+ } else {
+ addr = kallsyms_lookup_name(tname);
+ }
+ if (!addr || !ftrace_location(addr))
+ return -ENOENT;
+
+ /* Check sleepable program attachment. */
+ if (prog->sleepable) {
+ err = btf_id_allow_sleepable(btf_id, addr, prog, btf);
+ if (err)
+ return err;
+ }
+ tgt_info->tgt_addr = addr;
+ return 0;
+}
+
struct btf *bpf_get_btf_vmlinux(void)
{
if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) {
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 11/28] bpf: Move sleepable verification code to btf_id_allow_sleepable
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
Move sleepable verification code to btf_id_allow_sleepable function.
It will be used in following changes.
Adding code to retrieve type's name instead of passing it from
bpf_check_attach_target function, because this function will be
called from another place in following changes and it's easier
to retrieve the name directly in here.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
kernel/bpf/verifier.c | 79 +++++++++++++++++++++++++------------------
1 file changed, 47 insertions(+), 32 deletions(-)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9e913386aad5..739e730add96 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -19124,6 +19124,52 @@ static bool is_tracing_multi_id(const struct bpf_prog *prog, u32 btf_id)
return is_tracing_multi(prog->expected_attach_type) && bpf_multi_func_btf_id[0] == btf_id;
}
+static int btf_id_allow_sleepable(u32 btf_id, unsigned long addr, const struct bpf_prog *prog,
+ const struct btf *btf)
+{
+ const struct btf_type *t;
+ const char *tname;
+
+ switch (prog->type) {
+ case BPF_PROG_TYPE_TRACING:
+ t = btf_type_by_id(btf, btf_id);
+ if (!t)
+ return -EINVAL;
+ tname = btf_name_by_offset(btf, t->name_off);
+ if (!tname)
+ return -EINVAL;
+
+ /* *.multi sleepable programs will pass initial sleepable check,
+ * the actual attached btf ids are checked later during the link
+ * attachment.
+ */
+ if (is_tracing_multi_id(prog, btf_id))
+ return 0;
+ if (!check_attach_sleepable(btf_id, addr, tname))
+ return 0;
+ /* fentry/fexit/fmod_ret progs can also be sleepable if they are
+ * in the fmodret id set with the KF_SLEEPABLE flag.
+ */
+ else {
+ u32 *flags = btf_kfunc_is_modify_return(btf, btf_id, prog);
+
+ if (flags && (*flags & KF_SLEEPABLE))
+ return 0;
+ }
+ break;
+ case BPF_PROG_TYPE_LSM:
+ /* LSM progs check that they are attached to bpf_lsm_*() funcs.
+ * Only some of them are sleepable.
+ */
+ if (bpf_lsm_is_sleepable_hook(btf_id))
+ return 0;
+ break;
+ default:
+ break;
+ }
+ return -EINVAL;
+}
+
int bpf_check_attach_target(struct bpf_verifier_log *log,
const struct bpf_prog *prog,
const struct bpf_prog *tgt_prog,
@@ -19414,38 +19460,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
}
if (prog->sleepable) {
- ret = -EINVAL;
- switch (prog->type) {
- case BPF_PROG_TYPE_TRACING:
- /* *.multi sleepable programs will pass initial sleepable check,
- * the actual attached btf ids are checked later during the link
- * attachment.
- */
- if (is_tracing_multi_id(prog, btf_id))
- ret = 0;
- if (!check_attach_sleepable(btf_id, addr, tname))
- ret = 0;
- /* fentry/fexit/fmod_ret progs can also be sleepable if they are
- * in the fmodret id set with the KF_SLEEPABLE flag.
- */
- else {
- u32 *flags = btf_kfunc_is_modify_return(btf, btf_id,
- prog);
-
- if (flags && (*flags & KF_SLEEPABLE))
- ret = 0;
- }
- break;
- case BPF_PROG_TYPE_LSM:
- /* LSM progs check that they are attached to bpf_lsm_*() funcs.
- * Only some of them are sleepable.
- */
- if (bpf_lsm_is_sleepable_hook(btf_id))
- ret = 0;
- break;
- default:
- break;
- }
+ ret = btf_id_allow_sleepable(btf_id, addr, prog, btf);
if (ret) {
module_put(mod);
bpf_log(log, "%s is not sleepable\n", tname);
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 10/28] bpf: Add multi tracing attach types
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
Adding new program attach types multi tracing attachment:
BPF_TRACE_FENTRY_MULTI
BPF_TRACE_FEXIT_MULTI
and their base support in verifier code.
Programs with such attach type will use specific link attachment
interface coming in following changes.
This was suggested by Andrii some (long) time ago and turned out
to be easier than having special program flag for that.
Bpf programs with such types have 'bpf_multi_func' function set as
their attach_btf_id and keep module reference when it's specified
by attach_prog_fd.
They are also accepted as sleepable programs during verification,
and the real validation for specific BTF_IDs/functions will happen
during the multi link attachment in following changes.
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
include/linux/bpf.h | 5 +++++
include/linux/btf_ids.h | 1 +
include/uapi/linux/bpf.h | 2 ++
kernel/bpf/btf.c | 2 ++
kernel/bpf/fixups.c | 1 +
kernel/bpf/syscall.c | 33 ++++++++++++++++++++++++----
kernel/bpf/trampoline.c | 5 ++++-
kernel/bpf/verifier.c | 39 +++++++++++++++++++++++++++++++++-
net/bpf/test_run.c | 2 ++
tools/include/uapi/linux/bpf.h | 2 ++
tools/lib/bpf/libbpf.c | 2 ++
11 files changed, 88 insertions(+), 6 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 79e31fcab2c2..c815227f3bc6 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2073,6 +2073,11 @@ static inline void bpf_prog_put_recursion_context(struct bpf_prog *prog)
#endif
}
+static inline bool is_tracing_multi(enum bpf_attach_type type)
+{
+ return type == BPF_TRACE_FENTRY_MULTI || type == BPF_TRACE_FEXIT_MULTI;
+}
+
#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL)
/* This macro helps developer to register a struct_ops type and generate
* type information correctly. Developers should use this macro to register
diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index af011db39ab3..8b5a9ee92513 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -284,5 +284,6 @@ extern u32 bpf_cgroup_btf_id[];
extern u32 bpf_local_storage_map_btf_id[];
extern u32 btf_bpf_map_id[];
extern u32 bpf_kmem_cache_btf_id[];
+extern u32 bpf_multi_func_btf_id[];
#endif
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 552bc5d9afbd..5f814e7101cf 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1154,6 +1154,8 @@ enum bpf_attach_type {
BPF_TRACE_KPROBE_SESSION,
BPF_TRACE_UPROBE_SESSION,
BPF_TRACE_FSESSION,
+ BPF_TRACE_FENTRY_MULTI,
+ BPF_TRACE_FEXIT_MULTI,
__MAX_BPF_ATTACH_TYPE
};
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index a62d78581207..e76b549115d2 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6282,6 +6282,8 @@ static int btf_validate_prog_ctx_type(struct bpf_verifier_log *log, const struct
case BPF_TRACE_FEXIT:
case BPF_MODIFY_RETURN:
case BPF_TRACE_FSESSION:
+ case BPF_TRACE_FENTRY_MULTI:
+ case BPF_TRACE_FEXIT_MULTI:
/* allow u64* as ctx */
if (btf_is_int(t) && t->size == 8)
return 0;
diff --git a/kernel/bpf/fixups.c b/kernel/bpf/fixups.c
index 67c9b28767e1..1388e292d1a5 100644
--- a/kernel/bpf/fixups.c
+++ b/kernel/bpf/fixups.c
@@ -2049,6 +2049,7 @@ int bpf_do_misc_fixups(struct bpf_verifier_env *env)
insn->imm == BPF_FUNC_get_func_ret) {
if (eatype == BPF_TRACE_FEXIT ||
eatype == BPF_TRACE_FSESSION ||
+ eatype == BPF_TRACE_FEXIT_MULTI ||
eatype == BPF_MODIFY_RETURN) {
/* Load nr_args from ctx - 8 */
insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4ad41656fc8d..47c43c330c47 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -41,6 +41,7 @@
#include <linux/overflow.h>
#include <linux/cookie.h>
#include <linux/verification.h>
+#include <linux/btf_ids.h>
#include <net/netfilter/nf_bpf_link.h>
#include <net/netkit.h>
@@ -2646,7 +2647,8 @@ static int
bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
enum bpf_attach_type expected_attach_type,
struct btf *attach_btf, u32 btf_id,
- struct bpf_prog *dst_prog)
+ struct bpf_prog *dst_prog,
+ bool multi_func)
{
if (btf_id) {
if (btf_id > BTF_MAX_TYPE)
@@ -2666,6 +2668,14 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
}
}
+ if (multi_func) {
+ if (prog_type != BPF_PROG_TYPE_TRACING)
+ return -EINVAL;
+ if (!attach_btf || btf_id)
+ return -EINVAL;
+ return 0;
+ }
+
if (attach_btf && (!btf_id || dst_prog))
return -EINVAL;
@@ -2858,6 +2868,16 @@ static int bpf_prog_mark_insn_arrays_ready(struct bpf_prog *prog)
return 0;
}
+#define DEFINE_BPF_MULTI_FUNC(args...) \
+ extern int bpf_multi_func(args); \
+ int __init bpf_multi_func(args) { return 0; }
+
+DEFINE_BPF_MULTI_FUNC(unsigned long a1, unsigned long a2,
+ unsigned long a3, unsigned long a4,
+ unsigned long a5, unsigned long a6)
+
+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
@@ -2870,6 +2890,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
bool bpf_cap;
int err;
char license[128];
+ bool multi_func;
if (CHECK_ATTR(BPF_PROG_LOAD))
return -EINVAL;
@@ -2936,6 +2957,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON))
goto put_token;
+ multi_func = is_tracing_multi(attr->expected_attach_type);
+
/* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog
* or btf, we need to check which one it is
*/
@@ -2957,7 +2980,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
goto put_token;
}
}
- } else if (attr->attach_btf_id) {
+ } else if (attr->attach_btf_id || multi_func) {
/* fall back to vmlinux BTF, if BTF type ID is specified */
attach_btf = bpf_get_btf_vmlinux();
if (IS_ERR(attach_btf)) {
@@ -2973,7 +2996,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
if (bpf_prog_load_check_attach(type, attr->expected_attach_type,
attach_btf, attr->attach_btf_id,
- dst_prog)) {
+ dst_prog, multi_func)) {
if (dst_prog)
bpf_prog_put(dst_prog);
if (attach_btf)
@@ -2996,7 +3019,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
prog->expected_attach_type = attr->expected_attach_type;
prog->sleepable = !!(attr->prog_flags & BPF_F_SLEEPABLE);
prog->aux->attach_btf = attach_btf;
- prog->aux->attach_btf_id = attr->attach_btf_id;
+ prog->aux->attach_btf_id = multi_func ? bpf_multi_func_btf_id[0] : attr->attach_btf_id;
prog->aux->dst_prog = dst_prog;
prog->aux->dev_bound = !!attr->prog_ifindex;
prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS;
@@ -4389,6 +4412,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
case BPF_TRACE_FENTRY:
case BPF_TRACE_FEXIT:
case BPF_TRACE_FSESSION:
+ case BPF_TRACE_FENTRY_MULTI:
+ case BPF_TRACE_FEXIT_MULTI:
case BPF_MODIFY_RETURN:
return BPF_PROG_TYPE_TRACING;
case BPF_LSM_MAC:
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 91c380c34fcd..23856bd28d59 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -181,7 +181,8 @@ bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
switch (ptype) {
case BPF_PROG_TYPE_TRACING:
if (eatype == BPF_TRACE_FENTRY || eatype == BPF_TRACE_FEXIT ||
- eatype == BPF_MODIFY_RETURN || eatype == BPF_TRACE_FSESSION)
+ eatype == BPF_MODIFY_RETURN || eatype == BPF_TRACE_FSESSION ||
+ eatype == BPF_TRACE_FENTRY_MULTI || eatype == BPF_TRACE_FEXIT_MULTI)
return true;
return false;
case BPF_PROG_TYPE_LSM:
@@ -781,10 +782,12 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog)
{
switch (prog->expected_attach_type) {
case BPF_TRACE_FENTRY:
+ case BPF_TRACE_FENTRY_MULTI:
return BPF_TRAMP_FENTRY;
case BPF_MODIFY_RETURN:
return BPF_TRAMP_MODIFY_RETURN;
case BPF_TRACE_FEXIT:
+ case BPF_TRACE_FEXIT_MULTI:
return BPF_TRAMP_FEXIT;
case BPF_TRACE_FSESSION:
return BPF_TRAMP_FSESSION;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9e4980128151..9e913386aad5 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -16765,6 +16765,8 @@ static bool return_retval_range(struct bpf_verifier_env *env, struct bpf_retval_
case BPF_TRACE_FENTRY:
case BPF_TRACE_FEXIT:
case BPF_TRACE_FSESSION:
+ case BPF_TRACE_FENTRY_MULTI:
+ case BPF_TRACE_FEXIT_MULTI:
*range = retval_range(0, 0);
break;
case BPF_TRACE_RAW_TP:
@@ -19117,6 +19119,11 @@ static int check_attach_modify_return(unsigned long addr, const char *func_name)
#endif /* CONFIG_FUNCTION_ERROR_INJECTION */
+static bool is_tracing_multi_id(const struct bpf_prog *prog, u32 btf_id)
+{
+ return is_tracing_multi(prog->expected_attach_type) && bpf_multi_func_btf_id[0] == btf_id;
+}
+
int bpf_check_attach_target(struct bpf_verifier_log *log,
const struct bpf_prog *prog,
const struct bpf_prog *tgt_prog,
@@ -19239,6 +19246,8 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
prog_extension &&
(tgt_prog->expected_attach_type == BPF_TRACE_FENTRY ||
tgt_prog->expected_attach_type == BPF_TRACE_FEXIT ||
+ tgt_prog->expected_attach_type == BPF_TRACE_FENTRY_MULTI ||
+ tgt_prog->expected_attach_type == BPF_TRACE_FEXIT_MULTI ||
tgt_prog->expected_attach_type == BPF_TRACE_FSESSION)) {
/* Program extensions can extend all program types
* except fentry/fexit. The reason is the following.
@@ -19339,6 +19348,8 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
case BPF_TRACE_FENTRY:
case BPF_TRACE_FEXIT:
case BPF_TRACE_FSESSION:
+ case BPF_TRACE_FENTRY_MULTI:
+ case BPF_TRACE_FEXIT_MULTI:
if (prog->expected_attach_type == BPF_TRACE_FSESSION &&
!bpf_jit_supports_fsession()) {
bpf_log(log, "JIT does not support fsession\n");
@@ -19368,7 +19379,17 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
if (ret < 0)
return ret;
- if (tgt_prog) {
+ /* *.multi programs don't need an address during program
+ * verification, we just take the module ref if needed.
+ */
+ if (is_tracing_multi_id(prog, btf_id)) {
+ if (btf_is_module(btf)) {
+ mod = btf_try_get_module(btf);
+ if (!mod)
+ return -ENOENT;
+ }
+ addr = 0;
+ } else if (tgt_prog) {
if (subprog == 0)
addr = (long) tgt_prog->bpf_func;
else
@@ -19396,6 +19417,12 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
ret = -EINVAL;
switch (prog->type) {
case BPF_PROG_TYPE_TRACING:
+ /* *.multi sleepable programs will pass initial sleepable check,
+ * the actual attached btf ids are checked later during the link
+ * attachment.
+ */
+ if (is_tracing_multi_id(prog, btf_id))
+ ret = 0;
if (!check_attach_sleepable(btf_id, addr, tname))
ret = 0;
/* fentry/fexit/fmod_ret progs can also be sleepable if they are
@@ -19505,6 +19532,8 @@ static bool can_be_sleepable(struct bpf_prog *prog)
case BPF_MODIFY_RETURN:
case BPF_TRACE_ITER:
case BPF_TRACE_FSESSION:
+ case BPF_TRACE_FENTRY_MULTI:
+ case BPF_TRACE_FEXIT_MULTI:
return true;
default:
return false;
@@ -19594,6 +19623,14 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
return -EINVAL;
}
+ /*
+ * We don't get trampoline for tracing_multi programs at this point,
+ * it's done when tracing_multi link is created.
+ */
+ if (prog->type == BPF_PROG_TYPE_TRACING &&
+ is_tracing_multi(prog->expected_attach_type))
+ return 0;
+
key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id);
tr = bpf_trampoline_get(key, &tgt_info);
if (!tr)
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 2bc04feadfab..5495d105bc09 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -703,6 +703,8 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog,
case BPF_TRACE_FENTRY:
case BPF_TRACE_FEXIT:
case BPF_TRACE_FSESSION:
+ case BPF_TRACE_FENTRY_MULTI:
+ case BPF_TRACE_FEXIT_MULTI:
if (bpf_fentry_test1(1) != 2 ||
bpf_fentry_test2(2, 3) != 5 ||
bpf_fentry_test3(4, 5, 6) != 15 ||
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 677be9a47347..34615f905215 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1154,6 +1154,8 @@ enum bpf_attach_type {
BPF_TRACE_KPROBE_SESSION,
BPF_TRACE_UPROBE_SESSION,
BPF_TRACE_FSESSION,
+ BPF_TRACE_FENTRY_MULTI,
+ BPF_TRACE_FEXIT_MULTI,
__MAX_BPF_ATTACH_TYPE
};
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 79d9607d26e2..24e02ff039eb 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -136,6 +136,8 @@ static const char * const attach_type_name[] = {
[BPF_NETKIT_PEER] = "netkit_peer",
[BPF_TRACE_KPROBE_SESSION] = "trace_kprobe_session",
[BPF_TRACE_UPROBE_SESSION] = "trace_uprobe_session",
+ [BPF_TRACE_FENTRY_MULTI] = "trace_fentry_multi",
+ [BPF_TRACE_FEXIT_MULTI] = "trace_fexit_multi",
};
static const char * const link_type_name[] = {
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 09/28] bpf: Factor fsession link to use struct bpf_tramp_node
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
Now that we split trampoline attachment object (bpf_tramp_node) from
the link object (bpf_tramp_link) we can use bpf_tramp_node as fsession's
fexit attachment object and get rid of the bpf_fsession_link object.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
include/linux/bpf.h | 6 +-----
kernel/bpf/syscall.c | 21 ++++++---------------
kernel/bpf/trampoline.c | 12 ++++++------
3 files changed, 13 insertions(+), 26 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f826b65e4f68..79e31fcab2c2 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1887,15 +1887,11 @@ struct bpf_shim_tramp_link {
struct bpf_tracing_link {
struct bpf_tramp_link link;
+ struct bpf_tramp_node fexit;
struct bpf_trampoline *trampoline;
struct bpf_prog *tgt_prog;
};
-struct bpf_fsession_link {
- struct bpf_tracing_link link;
- struct bpf_tramp_link fexit;
-};
-
struct bpf_raw_tp_link {
struct bpf_link link;
struct bpf_raw_event_map *btp;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index fe00221de45c..4ad41656fc8d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3644,21 +3644,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
key = bpf_trampoline_compute_key(tgt_prog, NULL, btf_id);
}
- if (prog->expected_attach_type == BPF_TRACE_FSESSION) {
- struct bpf_fsession_link *fslink;
-
- fslink = kzalloc_obj(*fslink, GFP_USER);
- if (fslink) {
- bpf_tramp_link_init(&fslink->fexit, BPF_LINK_TYPE_TRACING,
- &bpf_tracing_link_lops, prog, attach_type,
- bpf_cookie);
- link = &fslink->link;
- } else {
- link = NULL;
- }
- } else {
- link = kzalloc_obj(*link, GFP_USER);
- }
+ link = kzalloc_obj(*link, GFP_USER);
if (!link) {
err = -ENOMEM;
goto out_put_prog;
@@ -3666,6 +3652,11 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
bpf_tramp_link_init(&link->link, BPF_LINK_TYPE_TRACING,
&bpf_tracing_link_lops, prog, attach_type, bpf_cookie);
+ if (prog->expected_attach_type == BPF_TRACE_FSESSION) {
+ link->fexit.link = &link->link.link;
+ link->fexit.cookie = bpf_cookie;
+ }
+
mutex_lock(&prog->aux->dst_mutex);
/* There are a few possible cases here:
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 452b82c654e9..91c380c34fcd 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -823,7 +823,7 @@ static int bpf_trampoline_add_prog(struct bpf_trampoline *tr,
struct bpf_tramp_node *node,
int cnt)
{
- struct bpf_fsession_link *fslink = NULL;
+ struct bpf_tracing_link *tr_link = NULL;
enum bpf_tramp_prog_type kind;
struct bpf_tramp_node *node_existing;
struct hlist_head *prog_list;
@@ -850,8 +850,8 @@ static int bpf_trampoline_add_prog(struct bpf_trampoline *tr,
hlist_add_head(&node->tramp_hlist, prog_list);
if (kind == BPF_TRAMP_FSESSION) {
tr->progs_cnt[BPF_TRAMP_FENTRY]++;
- fslink = container_of(node, struct bpf_fsession_link, link.link.node);
- hlist_add_head(&fslink->fexit.node.tramp_hlist, &tr->progs_hlist[BPF_TRAMP_FEXIT]);
+ tr_link = container_of(node, struct bpf_tracing_link, link.node);
+ hlist_add_head(&tr_link->fexit.tramp_hlist, &tr->progs_hlist[BPF_TRAMP_FEXIT]);
tr->progs_cnt[BPF_TRAMP_FEXIT]++;
} else {
tr->progs_cnt[kind]++;
@@ -862,13 +862,13 @@ static int bpf_trampoline_add_prog(struct bpf_trampoline *tr,
static void bpf_trampoline_remove_prog(struct bpf_trampoline *tr,
struct bpf_tramp_node *node)
{
- struct bpf_fsession_link *fslink;
+ struct bpf_tracing_link *tr_link;
enum bpf_tramp_prog_type kind;
kind = bpf_attach_type_to_tramp(node->link->prog);
if (kind == BPF_TRAMP_FSESSION) {
- fslink = container_of(node, struct bpf_fsession_link, link.link.node);
- hlist_del_init(&fslink->fexit.node.tramp_hlist);
+ tr_link = container_of(node, struct bpf_tracing_link, link.node);
+ hlist_del_init(&tr_link->fexit.tramp_hlist);
tr->progs_cnt[BPF_TRAMP_FEXIT]--;
kind = BPF_TRAMP_FENTRY;
}
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 08/28] bpf: Add struct bpf_tramp_node object
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: Hengqi Chen, bpf, linux-trace-kernel, Martin KaFai Lau,
Eduard Zingerman, Song Liu, Yonghong Song, Menglong Dong,
Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
Adding struct bpf_tramp_node to decouple the link out of the trampoline
attachment info.
At the moment the object for attaching bpf program to the trampoline is
'struct bpf_tramp_link':
struct bpf_tramp_link {
struct bpf_link link;
struct hlist_node tramp_hlist;
u64 cookie;
}
The link holds the bpf_prog pointer and forces one link - one program
binding logic. In following changes we want to attach program to multiple
trampolines but we want to keep just one bpf_link object.
Splitting struct bpf_tramp_link into:
struct bpf_tramp_link {
struct bpf_link link;
struct bpf_tramp_node node;
};
struct bpf_tramp_node {
struct bpf_link *link;
struct hlist_node tramp_hlist;
u64 cookie;
};
The 'struct bpf_tramp_link' defines standard single trampoline link
and 'struct bpf_tramp_node' is the attachment trampoline object with
pointer to the bpf_link object.
This will allow us to define link for multiple trampolines, like:
struct bpf_tracing_multi_link {
struct bpf_link link;
...
int nodes_cnt;
struct bpf_tracing_multi_node nodes[] __counted_by(nodes_cnt);
};
Cc: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
arch/arm64/net/bpf_jit_comp.c | 58 ++++++++--------
arch/loongarch/net/bpf_jit.c | 44 ++++++------
arch/powerpc/net/bpf_jit_comp.c | 50 +++++++-------
arch/riscv/net/bpf_jit_comp64.c | 52 +++++++--------
arch/s390/net/bpf_jit_comp.c | 44 ++++++------
arch/x86/net/bpf_jit_comp.c | 54 +++++++--------
include/linux/bpf.h | 60 ++++++++++-------
kernel/bpf/bpf_struct_ops.c | 27 ++++----
kernel/bpf/syscall.c | 39 ++++++-----
kernel/bpf/trampoline.c | 115 ++++++++++++++++----------------
net/bpf/bpf_dummy_struct_ops.c | 14 ++--
11 files changed, 288 insertions(+), 269 deletions(-)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index adf84962d579..6d08a6f08a0c 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -2288,24 +2288,24 @@ bool bpf_jit_supports_subprog_tailcalls(void)
return true;
}
-static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l,
+static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_node *node,
int bargs_off, int retval_off, int run_ctx_off,
bool save_ret)
{
__le32 *branch;
u64 enter_prog;
u64 exit_prog;
- struct bpf_prog *p = l->link.prog;
+ struct bpf_prog *p = node->link->prog;
int cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie);
enter_prog = (u64)bpf_trampoline_enter(p);
exit_prog = (u64)bpf_trampoline_exit(p);
- if (l->cookie == 0) {
+ if (node->cookie == 0) {
/* if cookie is zero, one instruction is enough to store it */
emit(A64_STR64I(A64_ZR, A64_SP, run_ctx_off + cookie_off), ctx);
} else {
- emit_a64_mov_i64(A64_R(10), l->cookie, ctx);
+ emit_a64_mov_i64(A64_R(10), node->cookie, ctx);
emit(A64_STR64I(A64_R(10), A64_SP, run_ctx_off + cookie_off),
ctx);
}
@@ -2355,7 +2355,7 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l,
emit_call(exit_prog, ctx);
}
-static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_links *tl,
+static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_nodes *tn,
int bargs_off, int retval_off, int run_ctx_off,
__le32 **branches)
{
@@ -2365,8 +2365,8 @@ static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_links *tl,
* Set this to 0 to avoid confusing the program.
*/
emit(A64_STR64I(A64_ZR, A64_SP, retval_off), ctx);
- for (i = 0; i < tl->nr_links; i++) {
- invoke_bpf_prog(ctx, tl->links[i], bargs_off, retval_off,
+ for (i = 0; i < tn->nr_nodes; i++) {
+ invoke_bpf_prog(ctx, tn->nodes[i], bargs_off, retval_off,
run_ctx_off, true);
/* if (*(u64 *)(sp + retval_off) != 0)
* goto do_fexit;
@@ -2497,10 +2497,10 @@ static void restore_args(struct jit_ctx *ctx, int bargs_off, int nregs)
}
}
-static bool is_struct_ops_tramp(const struct bpf_tramp_links *fentry_links)
+static bool is_struct_ops_tramp(const struct bpf_tramp_nodes *fentry_nodes)
{
- return fentry_links->nr_links == 1 &&
- fentry_links->links[0]->link.type == BPF_LINK_TYPE_STRUCT_OPS;
+ return fentry_nodes->nr_nodes == 1 &&
+ fentry_nodes->nodes[0]->link->type == BPF_LINK_TYPE_STRUCT_OPS;
}
static void store_func_meta(struct jit_ctx *ctx, u64 func_meta, int func_meta_off)
@@ -2521,7 +2521,7 @@ static void store_func_meta(struct jit_ctx *ctx, u64 func_meta, int func_meta_of
*
*/
static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
- struct bpf_tramp_links *tlinks, void *func_addr,
+ struct bpf_tramp_nodes *tnodes, void *func_addr,
const struct btf_func_model *m,
const struct arg_aux *a,
u32 flags)
@@ -2537,14 +2537,14 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
int run_ctx_off;
int oargs_off;
int nfuncargs;
- struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
- struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
- struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
+ struct bpf_tramp_nodes *fentry = &tnodes[BPF_TRAMP_FENTRY];
+ struct bpf_tramp_nodes *fexit = &tnodes[BPF_TRAMP_FEXIT];
+ struct bpf_tramp_nodes *fmod_ret = &tnodes[BPF_TRAMP_MODIFY_RETURN];
bool save_ret;
__le32 **branches = NULL;
bool is_struct_ops = is_struct_ops_tramp(fentry);
int cookie_off, cookie_cnt, cookie_bargs_off;
- int fsession_cnt = bpf_fsession_cnt(tlinks);
+ int fsession_cnt = bpf_fsession_cnt(tnodes);
u64 func_meta;
/* trampoline stack layout:
@@ -2590,7 +2590,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
cookie_off = stack_size;
/* room for session cookies */
- cookie_cnt = bpf_fsession_cookie_cnt(tlinks);
+ cookie_cnt = bpf_fsession_cookie_cnt(tnodes);
stack_size += cookie_cnt * 8;
ip_off = stack_size;
@@ -2687,20 +2687,20 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
}
cookie_bargs_off = (bargs_off - cookie_off) / 8;
- for (i = 0; i < fentry->nr_links; i++) {
- if (bpf_prog_calls_session_cookie(fentry->links[i])) {
+ for (i = 0; i < fentry->nr_nodes; i++) {
+ if (bpf_prog_calls_session_cookie(fentry->nodes[i])) {
u64 meta = func_meta | (cookie_bargs_off << BPF_TRAMP_COOKIE_INDEX_SHIFT);
store_func_meta(ctx, meta, func_meta_off);
cookie_bargs_off--;
}
- invoke_bpf_prog(ctx, fentry->links[i], bargs_off,
+ invoke_bpf_prog(ctx, fentry->nodes[i], bargs_off,
retval_off, run_ctx_off,
flags & BPF_TRAMP_F_RET_FENTRY_RET);
}
- if (fmod_ret->nr_links) {
- branches = kcalloc(fmod_ret->nr_links, sizeof(__le32 *),
+ if (fmod_ret->nr_nodes) {
+ branches = kcalloc(fmod_ret->nr_nodes, sizeof(__le32 *),
GFP_KERNEL);
if (!branches)
return -ENOMEM;
@@ -2724,7 +2724,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
}
/* update the branches saved in invoke_bpf_mod_ret with cbnz */
- for (i = 0; i < fmod_ret->nr_links && ctx->image != NULL; i++) {
+ for (i = 0; i < fmod_ret->nr_nodes && ctx->image != NULL; i++) {
int offset = &ctx->image[ctx->idx] - branches[i];
*branches[i] = cpu_to_le32(A64_CBNZ(1, A64_R(10), offset));
}
@@ -2735,14 +2735,14 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
store_func_meta(ctx, func_meta, func_meta_off);
cookie_bargs_off = (bargs_off - cookie_off) / 8;
- for (i = 0; i < fexit->nr_links; i++) {
- if (bpf_prog_calls_session_cookie(fexit->links[i])) {
+ for (i = 0; i < fexit->nr_nodes; i++) {
+ if (bpf_prog_calls_session_cookie(fexit->nodes[i])) {
u64 meta = func_meta | (cookie_bargs_off << BPF_TRAMP_COOKIE_INDEX_SHIFT);
store_func_meta(ctx, meta, func_meta_off);
cookie_bargs_off--;
}
- invoke_bpf_prog(ctx, fexit->links[i], bargs_off, retval_off,
+ invoke_bpf_prog(ctx, fexit->nodes[i], bargs_off, retval_off,
run_ctx_off, false);
}
@@ -2800,7 +2800,7 @@ bool bpf_jit_supports_fsession(void)
}
int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_links *tlinks, void *func_addr)
+ struct bpf_tramp_nodes *tnodes, void *func_addr)
{
struct jit_ctx ctx = {
.image = NULL,
@@ -2814,7 +2814,7 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
if (ret < 0)
return ret;
- ret = prepare_trampoline(&ctx, &im, tlinks, func_addr, m, &aaux, flags);
+ ret = prepare_trampoline(&ctx, &im, tnodes, func_addr, m, &aaux, flags);
if (ret < 0)
return ret;
@@ -2838,7 +2838,7 @@ int arch_protect_bpf_trampoline(void *image, unsigned int size)
int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image,
void *ro_image_end, const struct btf_func_model *m,
- u32 flags, struct bpf_tramp_links *tlinks,
+ u32 flags, struct bpf_tramp_nodes *tnodes,
void *func_addr)
{
u32 size = ro_image_end - ro_image;
@@ -2865,7 +2865,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image,
ret = calc_arg_aux(m, &aaux);
if (ret)
goto out;
- ret = prepare_trampoline(&ctx, im, tlinks, func_addr, m, &aaux, flags);
+ ret = prepare_trampoline(&ctx, im, tnodes, func_addr, m, &aaux, flags);
if (ret > 0 && validate_code(&ctx) < 0) {
ret = -EINVAL;
diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index 9cb796e16379..af586827ad84 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -1486,16 +1486,16 @@ static void restore_args(struct jit_ctx *ctx, int nargs, int args_off)
}
}
-static int invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l,
+static int invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_node *n,
int args_off, int retval_off, int run_ctx_off, bool save_ret)
{
int ret;
u32 *branch;
- struct bpf_prog *p = l->link.prog;
+ struct bpf_prog *p = n->link->prog;
int cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie);
- if (l->cookie) {
- move_imm(ctx, LOONGARCH_GPR_T1, l->cookie, false);
+ if (n->cookie) {
+ move_imm(ctx, LOONGARCH_GPR_T1, n->cookie, false);
emit_insn(ctx, std, LOONGARCH_GPR_T1, LOONGARCH_GPR_FP, -run_ctx_off + cookie_off);
} else {
emit_insn(ctx, std, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_FP, -run_ctx_off + cookie_off);
@@ -1550,14 +1550,14 @@ static int invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l,
return ret;
}
-static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_links *tl,
+static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_nodes *tn,
int args_off, int retval_off, int run_ctx_off, u32 **branches)
{
int i;
emit_insn(ctx, std, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_FP, -retval_off);
- for (i = 0; i < tl->nr_links; i++) {
- invoke_bpf_prog(ctx, tl->links[i], args_off, retval_off, run_ctx_off, true);
+ for (i = 0; i < tn->nr_nodes; i++) {
+ invoke_bpf_prog(ctx, tn->nodes[i], args_off, retval_off, run_ctx_off, true);
emit_insn(ctx, ldd, LOONGARCH_GPR_T1, LOONGARCH_GPR_FP, -retval_off);
branches[i] = (u32 *)ctx->image + ctx->idx;
emit_insn(ctx, nop);
@@ -1611,7 +1611,7 @@ static void sign_extend(struct jit_ctx *ctx, int rd, int rj, u8 size, bool sign)
}
static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
- const struct btf_func_model *m, struct bpf_tramp_links *tlinks,
+ const struct btf_func_model *m, struct bpf_tramp_nodes *tnodes,
void *func_addr, u32 flags)
{
int i, ret, save_ret;
@@ -1619,9 +1619,9 @@ static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_i
int retval_off, args_off, nargs_off, ip_off, run_ctx_off, sreg_off, tcc_ptr_off;
bool is_struct_ops = flags & BPF_TRAMP_F_INDIRECT;
void *orig_call = func_addr;
- struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
- struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
- struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
+ struct bpf_tramp_nodes *fentry = &tnodes[BPF_TRAMP_FENTRY];
+ struct bpf_tramp_nodes *fexit = &tnodes[BPF_TRAMP_FEXIT];
+ struct bpf_tramp_nodes *fmod_ret = &tnodes[BPF_TRAMP_MODIFY_RETURN];
u32 **branches = NULL;
/*
@@ -1764,14 +1764,14 @@ static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_i
return ret;
}
- for (i = 0; i < fentry->nr_links; i++) {
- ret = invoke_bpf_prog(ctx, fentry->links[i], args_off, retval_off,
+ for (i = 0; i < fentry->nr_nodes; i++) {
+ ret = invoke_bpf_prog(ctx, fentry->nodes[i], args_off, retval_off,
run_ctx_off, flags & BPF_TRAMP_F_RET_FENTRY_RET);
if (ret)
return ret;
}
- if (fmod_ret->nr_links) {
- branches = kcalloc(fmod_ret->nr_links, sizeof(u32 *), GFP_KERNEL);
+ if (fmod_ret->nr_nodes) {
+ branches = kcalloc(fmod_ret->nr_nodes, sizeof(u32 *), GFP_KERNEL);
if (!branches)
return -ENOMEM;
@@ -1795,13 +1795,13 @@ static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_i
emit_insn(ctx, nop);
}
- for (i = 0; ctx->image && i < fmod_ret->nr_links; i++) {
+ for (i = 0; ctx->image && i < fmod_ret->nr_nodes; i++) {
int offset = (void *)(&ctx->image[ctx->idx]) - (void *)branches[i];
*branches[i] = larch_insn_gen_bne(LOONGARCH_GPR_T1, LOONGARCH_GPR_ZERO, offset);
}
- for (i = 0; i < fexit->nr_links; i++) {
- ret = invoke_bpf_prog(ctx, fexit->links[i], args_off, retval_off, run_ctx_off, false);
+ for (i = 0; i < fexit->nr_nodes; i++) {
+ ret = invoke_bpf_prog(ctx, fexit->nodes[i], args_off, retval_off, run_ctx_off, false);
if (ret)
goto out;
}
@@ -1869,7 +1869,7 @@ static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_i
int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image,
void *ro_image_end, const struct btf_func_model *m,
- u32 flags, struct bpf_tramp_links *tlinks, void *func_addr)
+ u32 flags, struct bpf_tramp_nodes *tnodes, void *func_addr)
{
int ret, size;
void *image, *tmp;
@@ -1885,7 +1885,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image,
ctx.idx = 0;
jit_fill_hole(image, (unsigned int)(ro_image_end - ro_image));
- ret = __arch_prepare_bpf_trampoline(&ctx, im, m, tlinks, func_addr, flags);
+ ret = __arch_prepare_bpf_trampoline(&ctx, im, m, tnodes, func_addr, flags);
if (ret < 0)
goto out;
@@ -1906,7 +1906,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image,
}
int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_links *tlinks, void *func_addr)
+ struct bpf_tramp_nodes *tnodes, void *func_addr)
{
int ret;
struct jit_ctx ctx;
@@ -1915,7 +1915,7 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
ctx.image = NULL;
ctx.idx = 0;
- ret = __arch_prepare_bpf_trampoline(&ctx, &im, m, tlinks, func_addr, flags);
+ ret = __arch_prepare_bpf_trampoline(&ctx, &im, m, tnodes, func_addr, flags);
return ret < 0 ? ret : ret * LOONGARCH_INSN_SIZE;
}
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 50103b3794fb..b97d9f68fc40 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -617,22 +617,22 @@ int arch_protect_bpf_trampoline(void *image, unsigned int size)
}
static int invoke_bpf_prog(u32 *image, u32 *ro_image, struct codegen_context *ctx,
- struct bpf_tramp_link *l, int regs_off, int retval_off,
+ struct bpf_tramp_node *n, int regs_off, int retval_off,
int run_ctx_off, bool save_ret)
{
- struct bpf_prog *p = l->link.prog;
+ struct bpf_prog *p = n->link->prog;
ppc_inst_t branch_insn;
u32 jmp_idx;
int ret = 0;
/* Save cookie */
if (IS_ENABLED(CONFIG_PPC64)) {
- PPC_LI64(_R3, l->cookie);
+ PPC_LI64(_R3, n->cookie);
EMIT(PPC_RAW_STD(_R3, _R1, run_ctx_off + offsetof(struct bpf_tramp_run_ctx,
bpf_cookie)));
} else {
- PPC_LI32(_R3, l->cookie >> 32);
- PPC_LI32(_R4, l->cookie);
+ PPC_LI32(_R3, n->cookie >> 32);
+ PPC_LI32(_R4, n->cookie);
EMIT(PPC_RAW_STW(_R3, _R1,
run_ctx_off + offsetof(struct bpf_tramp_run_ctx, bpf_cookie)));
EMIT(PPC_RAW_STW(_R4, _R1,
@@ -699,7 +699,7 @@ static int invoke_bpf_prog(u32 *image, u32 *ro_image, struct codegen_context *ct
}
static int invoke_bpf_mod_ret(u32 *image, u32 *ro_image, struct codegen_context *ctx,
- struct bpf_tramp_links *tl, int regs_off, int retval_off,
+ struct bpf_tramp_nodes *tn, int regs_off, int retval_off,
int run_ctx_off, u32 *branches)
{
int i;
@@ -710,8 +710,8 @@ static int invoke_bpf_mod_ret(u32 *image, u32 *ro_image, struct codegen_context
*/
EMIT(PPC_RAW_LI(_R3, 0));
EMIT(PPC_RAW_STL(_R3, _R1, retval_off));
- for (i = 0; i < tl->nr_links; i++) {
- if (invoke_bpf_prog(image, ro_image, ctx, tl->links[i], regs_off, retval_off,
+ for (i = 0; i < tn->nr_nodes; i++) {
+ if (invoke_bpf_prog(image, ro_image, ctx, tn->nodes[i], regs_off, retval_off,
run_ctx_off, true))
return -EINVAL;
@@ -827,14 +827,14 @@ static void bpf_trampoline_restore_args_stack(u32 *image, struct codegen_context
static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_image,
void *rw_image_end, void *ro_image,
const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_links *tlinks,
+ struct bpf_tramp_nodes *tnodes,
void *func_addr)
{
int regs_off, func_meta_off, ip_off, run_ctx_off, retval_off;
int nvr_off, alt_lr_off, r4_off = 0;
- struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
- struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
- struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
+ struct bpf_tramp_nodes *fmod_ret = &tnodes[BPF_TRAMP_MODIFY_RETURN];
+ struct bpf_tramp_nodes *fentry = &tnodes[BPF_TRAMP_FENTRY];
+ struct bpf_tramp_nodes *fexit = &tnodes[BPF_TRAMP_FEXIT];
int i, ret, nr_regs, retaddr_off, bpf_frame_size = 0;
struct codegen_context codegen_ctx, *ctx;
int cookie_off, cookie_cnt, cookie_ctx_off;
@@ -1050,21 +1050,21 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
cookie_ctx_off = (regs_off - cookie_off) / 8;
- for (i = 0; i < fentry->nr_links; i++) {
- if (bpf_prog_calls_session_cookie(fentry->links[i])) {
+ for (i = 0; i < fentry->nr_nodes; i++)
+ if (bpf_prog_calls_session_cookie(fentry->nodes[i])) {
u64 meta = func_meta | (cookie_ctx_off << BPF_TRAMP_COOKIE_INDEX_SHIFT);
store_func_meta(image, ctx, meta, func_meta_off);
cookie_ctx_off--;
}
- if (invoke_bpf_prog(image, ro_image, ctx, fentry->links[i], regs_off, retval_off,
+ if (invoke_bpf_prog(image, ro_image, ctx, fentry->nodes[i], regs_off, retval_off,
run_ctx_off, flags & BPF_TRAMP_F_RET_FENTRY_RET))
return -EINVAL;
}
- if (fmod_ret->nr_links) {
- branches = kcalloc(fmod_ret->nr_links, sizeof(u32), GFP_KERNEL);
+ if (fmod_ret->nr_nodes) {
+ branches = kcalloc(fmod_ret->nr_nodes, sizeof(u32), GFP_KERNEL);
if (!branches)
return -ENOMEM;
@@ -1113,7 +1113,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
}
/* Update branches saved in invoke_bpf_mod_ret with address of do_fexit */
- for (i = 0; i < fmod_ret->nr_links && image; i++) {
+ for (i = 0; i < fmod_ret->nr_nodes && image; i++) {
if (create_cond_branch(&branch_insn, &image[branches[i]],
(unsigned long)&image[ctx->idx], COND_NE << 16)) {
ret = -EINVAL;
@@ -1130,15 +1130,15 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
cookie_ctx_off = (regs_off - cookie_off) / 8;
- for (i = 0; i < fexit->nr_links; i++) {
- if (bpf_prog_calls_session_cookie(fexit->links[i])) {
+ for (i = 0; i < fexit->nr_nodes; i++) {
+ if (bpf_prog_calls_session_cookie(fexit->nodes[i])) {
u64 meta = func_meta | (cookie_ctx_off << BPF_TRAMP_COOKIE_INDEX_SHIFT);
store_func_meta(image, ctx, meta, func_meta_off);
cookie_ctx_off--;
}
- if (invoke_bpf_prog(image, ro_image, ctx, fexit->links[i], regs_off, retval_off,
+ if (invoke_bpf_prog(image, ro_image, ctx, fexit->nodes[i], regs_off, retval_off,
run_ctx_off, false)) {
ret = -EINVAL;
goto cleanup;
@@ -1205,18 +1205,18 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
}
int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_links *tlinks, void *func_addr)
+ struct bpf_tramp_nodes *tnodes, void *func_addr)
{
struct bpf_tramp_image im;
int ret;
- ret = __arch_prepare_bpf_trampoline(&im, NULL, NULL, NULL, m, flags, tlinks, func_addr);
+ ret = __arch_prepare_bpf_trampoline(&im, NULL, NULL, NULL, m, flags, tnodes, func_addr);
return ret;
}
int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_links *tlinks,
+ struct bpf_tramp_nodes *tnodes,
void *func_addr)
{
u32 size = image_end - image;
@@ -1232,7 +1232,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
return -ENOMEM;
ret = __arch_prepare_bpf_trampoline(im, rw_image, rw_image + size, image, m,
- flags, tlinks, func_addr);
+ flags, tnodes, func_addr);
if (ret < 0)
goto out;
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 2f1109dbf105..461b902a5f92 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -934,15 +934,15 @@ static void emit_store_stack_imm64(u8 reg, int stack_off, u64 imm64,
emit_sd(RV_REG_FP, stack_off, reg, ctx);
}
-static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_off,
+static int invoke_bpf_prog(struct bpf_tramp_node *node, int args_off, int retval_off,
int run_ctx_off, bool save_ret, struct rv_jit_context *ctx)
{
int ret, branch_off;
- struct bpf_prog *p = l->link.prog;
+ struct bpf_prog *p = node->link->prog;
int cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie);
- if (l->cookie)
- emit_store_stack_imm64(RV_REG_T1, -run_ctx_off + cookie_off, l->cookie, ctx);
+ if (node->cookie)
+ emit_store_stack_imm64(RV_REG_T1, -run_ctx_off + cookie_off, node->cookie, ctx);
else
emit_sd(RV_REG_FP, -run_ctx_off + cookie_off, RV_REG_ZERO, ctx);
@@ -996,22 +996,22 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of
return ret;
}
-static int invoke_bpf(struct bpf_tramp_links *tl, int args_off, int retval_off,
+static int invoke_bpf(struct bpf_tramp_nodes *tn, int args_off, int retval_off,
int run_ctx_off, int func_meta_off, bool save_ret, u64 func_meta,
int cookie_off, struct rv_jit_context *ctx)
{
int i, cur_cookie = (cookie_off - args_off) / 8;
- for (i = 0; i < tl->nr_links; i++) {
+ for (i = 0; i < tn->nr_nodes; i++) {
int err;
- if (bpf_prog_calls_session_cookie(tl->links[i])) {
+ if (bpf_prog_calls_session_cookie(tn->nodes[i])) {
u64 meta = func_meta | ((u64)cur_cookie << BPF_TRAMP_COOKIE_INDEX_SHIFT);
emit_store_stack_imm64(RV_REG_T1, -func_meta_off, meta, ctx);
cur_cookie--;
}
- err = invoke_bpf_prog(tl->links[i], args_off, retval_off, run_ctx_off,
+ err = invoke_bpf_prog(tn->nodes[i], args_off, retval_off, run_ctx_off,
save_ret, ctx);
if (err)
return err;
@@ -1021,7 +1021,7 @@ static int invoke_bpf(struct bpf_tramp_links *tl, int args_off, int retval_off,
static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
const struct btf_func_model *m,
- struct bpf_tramp_links *tlinks,
+ struct bpf_tramp_nodes *tnodes,
void *func_addr, u32 flags,
struct rv_jit_context *ctx)
{
@@ -1030,9 +1030,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
int stack_size = 0, nr_arg_slots = 0;
int retval_off, args_off, func_meta_off, ip_off, run_ctx_off, sreg_off, stk_arg_off;
int cookie_off, cookie_cnt;
- struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
- struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
- struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
+ struct bpf_tramp_nodes *fentry = &tnodes[BPF_TRAMP_FENTRY];
+ struct bpf_tramp_nodes *fexit = &tnodes[BPF_TRAMP_FEXIT];
+ struct bpf_tramp_nodes *fmod_ret = &tnodes[BPF_TRAMP_MODIFY_RETURN];
bool is_struct_ops = flags & BPF_TRAMP_F_INDIRECT;
void *orig_call = func_addr;
bool save_ret;
@@ -1115,7 +1115,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
ip_off = stack_size;
}
- cookie_cnt = bpf_fsession_cookie_cnt(tlinks);
+ cookie_cnt = bpf_fsession_cookie_cnt(tnodes);
/* room for session cookies */
stack_size += cookie_cnt * 8;
cookie_off = stack_size;
@@ -1172,7 +1172,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
store_args(nr_arg_slots, args_off, ctx);
- if (bpf_fsession_cnt(tlinks)) {
+ if (bpf_fsession_cnt(tnodes)) {
/* clear all session cookies' value */
for (i = 0; i < cookie_cnt; i++)
emit_sd(RV_REG_FP, -cookie_off + 8 * i, RV_REG_ZERO, ctx);
@@ -1187,22 +1187,22 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
return ret;
}
- if (fentry->nr_links) {
+ if (fentry->nr_nodes) {
ret = invoke_bpf(fentry, args_off, retval_off, run_ctx_off, func_meta_off,
flags & BPF_TRAMP_F_RET_FENTRY_RET, func_meta, cookie_off, ctx);
if (ret)
return ret;
}
- if (fmod_ret->nr_links) {
- branches_off = kzalloc_objs(int, fmod_ret->nr_links);
+ if (fmod_ret->nr_nodes) {
+ branches_off = kzalloc_objs(int, fmod_ret->nr_nodes);
if (!branches_off)
return -ENOMEM;
/* cleanup to avoid garbage return value confusion */
emit_sd(RV_REG_FP, -retval_off, RV_REG_ZERO, ctx);
- for (i = 0; i < fmod_ret->nr_links; i++) {
- ret = invoke_bpf_prog(fmod_ret->links[i], args_off, retval_off,
+ for (i = 0; i < fmod_ret->nr_nodes; i++) {
+ ret = invoke_bpf_prog(fmod_ret->nodes[i], args_off, retval_off,
run_ctx_off, true, ctx);
if (ret)
goto out;
@@ -1230,7 +1230,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
}
/* update branches saved in invoke_bpf_mod_ret with bnez */
- for (i = 0; ctx->insns && i < fmod_ret->nr_links; i++) {
+ for (i = 0; ctx->insns && i < fmod_ret->nr_nodes; i++) {
offset = ninsns_rvoff(ctx->ninsns - branches_off[i]);
insn = rv_bne(RV_REG_T1, RV_REG_ZERO, offset >> 1);
*(u32 *)(ctx->insns + branches_off[i]) = insn;
@@ -1238,10 +1238,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
/* set "is_return" flag for fsession */
func_meta |= (1ULL << BPF_TRAMP_IS_RETURN_SHIFT);
- if (bpf_fsession_cnt(tlinks))
+ if (bpf_fsession_cnt(tnodes))
emit_store_stack_imm64(RV_REG_T1, -func_meta_off, func_meta, ctx);
- if (fexit->nr_links) {
+ if (fexit->nr_nodes) {
ret = invoke_bpf(fexit, args_off, retval_off, run_ctx_off, func_meta_off,
false, func_meta, cookie_off, ctx);
if (ret)
@@ -1305,7 +1305,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
}
int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_links *tlinks, void *func_addr)
+ struct bpf_tramp_nodes *tnodes, void *func_addr)
{
struct bpf_tramp_image im;
struct rv_jit_context ctx;
@@ -1314,7 +1314,7 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
ctx.ninsns = 0;
ctx.insns = NULL;
ctx.ro_insns = NULL;
- ret = __arch_prepare_bpf_trampoline(&im, m, tlinks, func_addr, flags, &ctx);
+ ret = __arch_prepare_bpf_trampoline(&im, m, tnodes, func_addr, flags, &ctx);
return ret < 0 ? ret : ninsns_rvoff(ctx.ninsns);
}
@@ -1331,7 +1331,7 @@ void arch_free_bpf_trampoline(void *image, unsigned int size)
int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image,
void *ro_image_end, const struct btf_func_model *m,
- u32 flags, struct bpf_tramp_links *tlinks,
+ u32 flags, struct bpf_tramp_nodes *tnodes,
void *func_addr)
{
int ret;
@@ -1346,7 +1346,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image,
ctx.ninsns = 0;
ctx.insns = image;
ctx.ro_insns = ro_image;
- ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx);
+ ret = __arch_prepare_bpf_trampoline(im, m, tnodes, func_addr, flags, &ctx);
if (ret < 0)
goto out;
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index d08d159b6319..cfdba742660a 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -2531,19 +2531,19 @@ static void emit_store_stack_imm64(struct bpf_jit *jit, int tmp_reg, int stack_o
static int invoke_bpf_prog(struct bpf_tramp_jit *tjit,
const struct btf_func_model *m,
- struct bpf_tramp_link *tlink, bool save_ret)
+ struct bpf_tramp_node *node, bool save_ret)
{
struct bpf_jit *jit = &tjit->common;
int cookie_off = tjit->run_ctx_off +
offsetof(struct bpf_tramp_run_ctx, bpf_cookie);
- struct bpf_prog *p = tlink->link.prog;
+ struct bpf_prog *p = node->link->prog;
int patch;
/*
- * run_ctx.cookie = tlink->cookie;
+ * run_ctx.cookie = node->cookie;
*/
- emit_store_stack_imm64(jit, REG_W0, cookie_off, tlink->cookie);
+ emit_store_stack_imm64(jit, REG_W0, cookie_off, node->cookie);
/*
* if ((start = __bpf_prog_enter(p, &run_ctx)) == 0)
@@ -2603,20 +2603,20 @@ static int invoke_bpf_prog(struct bpf_tramp_jit *tjit,
static int invoke_bpf(struct bpf_tramp_jit *tjit,
const struct btf_func_model *m,
- struct bpf_tramp_links *tl, bool save_ret,
+ struct bpf_tramp_nodes *tn, bool save_ret,
u64 func_meta, int cookie_off)
{
int i, cur_cookie = (tjit->bpf_args_off - cookie_off) / sizeof(u64);
struct bpf_jit *jit = &tjit->common;
- for (i = 0; i < tl->nr_links; i++) {
- if (bpf_prog_calls_session_cookie(tl->links[i])) {
+ for (i = 0; i < tn->nr_nodes; i++) {
+ if (bpf_prog_calls_session_cookie(tn->nodes[i])) {
u64 meta = func_meta | ((u64)cur_cookie << BPF_TRAMP_COOKIE_INDEX_SHIFT);
emit_store_stack_imm64(jit, REG_0, tjit->func_meta_off, meta);
cur_cookie--;
}
- if (invoke_bpf_prog(tjit, m, tl->links[i], save_ret))
+ if (invoke_bpf_prog(tjit, m, tn->nodes[i], save_ret))
return -EINVAL;
}
@@ -2645,12 +2645,12 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
struct bpf_tramp_jit *tjit,
const struct btf_func_model *m,
u32 flags,
- struct bpf_tramp_links *tlinks,
+ struct bpf_tramp_nodes *tnodes,
void *func_addr)
{
- struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
- struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
- struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
+ struct bpf_tramp_nodes *fmod_ret = &tnodes[BPF_TRAMP_MODIFY_RETURN];
+ struct bpf_tramp_nodes *fentry = &tnodes[BPF_TRAMP_FENTRY];
+ struct bpf_tramp_nodes *fexit = &tnodes[BPF_TRAMP_FEXIT];
int nr_bpf_args, nr_reg_args, nr_stack_args;
int cookie_cnt, cookie_off, fsession_cnt;
struct bpf_jit *jit = &tjit->common;
@@ -2687,8 +2687,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
return -ENOTSUPP;
}
- cookie_cnt = bpf_fsession_cookie_cnt(tlinks);
- fsession_cnt = bpf_fsession_cnt(tlinks);
+ cookie_cnt = bpf_fsession_cookie_cnt(tnodes);
+ fsession_cnt = bpf_fsession_cnt(tnodes);
/*
* Calculate the stack layout.
@@ -2823,7 +2823,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
func_meta, cookie_off))
return -EINVAL;
- if (fmod_ret->nr_links) {
+ if (fmod_ret->nr_nodes) {
/*
* retval = 0;
*/
@@ -2832,8 +2832,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
_EMIT6(0xd707f000 | tjit->retval_off,
0xf000 | tjit->retval_off);
- for (i = 0; i < fmod_ret->nr_links; i++) {
- if (invoke_bpf_prog(tjit, m, fmod_ret->links[i], true))
+ for (i = 0; i < fmod_ret->nr_nodes; i++) {
+ if (invoke_bpf_prog(tjit, m, fmod_ret->nodes[i], true))
return -EINVAL;
/*
@@ -2958,7 +2958,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
}
int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_links *tlinks, void *orig_call)
+ struct bpf_tramp_nodes *tnodes, void *orig_call)
{
struct bpf_tramp_image im;
struct bpf_tramp_jit tjit;
@@ -2967,14 +2967,14 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
memset(&tjit, 0, sizeof(tjit));
ret = __arch_prepare_bpf_trampoline(&im, &tjit, m, flags,
- tlinks, orig_call);
+ tnodes, orig_call);
return ret < 0 ? ret : tjit.common.prg;
}
int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
void *image_end, const struct btf_func_model *m,
- u32 flags, struct bpf_tramp_links *tlinks,
+ u32 flags, struct bpf_tramp_nodes *tnodes,
void *func_addr)
{
struct bpf_tramp_jit tjit;
@@ -2983,7 +2983,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
/* Compute offsets, check whether the code fits. */
memset(&tjit, 0, sizeof(tjit));
ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags,
- tlinks, func_addr);
+ tnodes, func_addr);
if (ret < 0)
return ret;
@@ -2997,7 +2997,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
tjit.common.prg = 0;
tjit.common.prg_buf = image;
ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags,
- tlinks, func_addr);
+ tnodes, func_addr);
return ret < 0 ? ret : tjit.common.prg;
}
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index e9b78040d703..dc3f2e8d5ca7 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -2969,15 +2969,15 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog,
}
static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
- struct bpf_tramp_link *l, int stack_size,
+ struct bpf_tramp_node *node, int stack_size,
int run_ctx_off, bool save_ret,
void *image, void *rw_image)
{
u8 *prog = *pprog;
u8 *jmp_insn;
int ctx_cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie);
- struct bpf_prog *p = l->link.prog;
- u64 cookie = l->cookie;
+ struct bpf_prog *p = node->link->prog;
+ u64 cookie = node->cookie;
/* mov rdi, cookie */
emit_mov_imm64(&prog, BPF_REG_1, (long) cookie >> 32, (u32) (long) cookie);
@@ -3084,7 +3084,7 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond)
}
static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
- struct bpf_tramp_links *tl, int stack_size,
+ struct bpf_tramp_nodes *tl, int stack_size,
int run_ctx_off, int func_meta_off, bool save_ret,
void *image, void *rw_image, u64 func_meta,
int cookie_off)
@@ -3092,13 +3092,13 @@ static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
int i, cur_cookie = (cookie_off - stack_size) / 8;
u8 *prog = *pprog;
- for (i = 0; i < tl->nr_links; i++) {
- if (tl->links[i]->link.prog->call_session_cookie) {
+ for (i = 0; i < tl->nr_nodes; i++) {
+ if (tl->nodes[i]->link->prog->call_session_cookie) {
emit_store_stack_imm64(&prog, BPF_REG_0, -func_meta_off,
func_meta | (cur_cookie << BPF_TRAMP_COOKIE_INDEX_SHIFT));
cur_cookie--;
}
- if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size,
+ if (invoke_bpf_prog(m, &prog, tl->nodes[i], stack_size,
run_ctx_off, save_ret, image, rw_image))
return -EINVAL;
}
@@ -3107,7 +3107,7 @@ static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
}
static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
- struct bpf_tramp_links *tl, int stack_size,
+ struct bpf_tramp_nodes *tl, int stack_size,
int run_ctx_off, u8 **branches,
void *image, void *rw_image)
{
@@ -3119,8 +3119,8 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
*/
emit_mov_imm32(&prog, false, BPF_REG_0, 0);
emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
- for (i = 0; i < tl->nr_links; i++) {
- if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, run_ctx_off, true,
+ for (i = 0; i < tl->nr_nodes; i++) {
+ if (invoke_bpf_prog(m, &prog, tl->nodes[i], stack_size, run_ctx_off, true,
image, rw_image))
return -EINVAL;
@@ -3211,14 +3211,14 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_image,
void *rw_image_end, void *image,
const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_links *tlinks,
+ struct bpf_tramp_nodes *tnodes,
void *func_addr)
{
int i, ret, nr_regs = m->nr_args, stack_size = 0;
int regs_off, func_meta_off, ip_off, run_ctx_off, arg_stack_off, rbx_off;
- struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
- struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
- struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
+ struct bpf_tramp_nodes *fentry = &tnodes[BPF_TRAMP_FENTRY];
+ struct bpf_tramp_nodes *fexit = &tnodes[BPF_TRAMP_FEXIT];
+ struct bpf_tramp_nodes *fmod_ret = &tnodes[BPF_TRAMP_MODIFY_RETURN];
void *orig_call = func_addr;
int cookie_off, cookie_cnt;
u8 **branches = NULL;
@@ -3290,7 +3290,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
ip_off = stack_size;
- cookie_cnt = bpf_fsession_cookie_cnt(tlinks);
+ cookie_cnt = bpf_fsession_cookie_cnt(tnodes);
/* room for session cookies */
stack_size += cookie_cnt * 8;
cookie_off = stack_size;
@@ -3383,7 +3383,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
}
}
- if (bpf_fsession_cnt(tlinks)) {
+ if (bpf_fsession_cnt(tnodes)) {
/* clear all the session cookies' value */
for (int i = 0; i < cookie_cnt; i++)
emit_store_stack_imm64(&prog, BPF_REG_0, -cookie_off + 8 * i, 0);
@@ -3391,15 +3391,15 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
emit_store_stack_imm64(&prog, BPF_REG_0, -8, 0);
}
- if (fentry->nr_links) {
+ if (fentry->nr_nodes) {
if (invoke_bpf(m, &prog, fentry, regs_off, run_ctx_off, func_meta_off,
flags & BPF_TRAMP_F_RET_FENTRY_RET, image, rw_image,
func_meta, cookie_off))
return -EINVAL;
}
- if (fmod_ret->nr_links) {
- branches = kcalloc(fmod_ret->nr_links, sizeof(u8 *),
+ if (fmod_ret->nr_nodes) {
+ branches = kcalloc(fmod_ret->nr_nodes, sizeof(u8 *),
GFP_KERNEL);
if (!branches)
return -ENOMEM;
@@ -3438,7 +3438,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
emit_nops(&prog, X86_PATCH_SIZE);
}
- if (fmod_ret->nr_links) {
+ if (fmod_ret->nr_nodes) {
/* From Intel 64 and IA-32 Architectures Optimization
* Reference Manual, 3.4.1.4 Code Alignment, Assembly/Compiler
* Coding Rule 11: All branch targets should be 16-byte
@@ -3448,7 +3448,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
/* Update the branches saved in invoke_bpf_mod_ret with the
* aligned address of do_fexit.
*/
- for (i = 0; i < fmod_ret->nr_links; i++) {
+ for (i = 0; i < fmod_ret->nr_nodes; i++) {
emit_cond_near_jump(&branches[i], image + (prog - (u8 *)rw_image),
image + (branches[i] - (u8 *)rw_image), X86_JNE);
}
@@ -3456,10 +3456,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
/* set the "is_return" flag for fsession */
func_meta |= (1ULL << BPF_TRAMP_IS_RETURN_SHIFT);
- if (bpf_fsession_cnt(tlinks))
+ if (bpf_fsession_cnt(tnodes))
emit_store_stack_imm64(&prog, BPF_REG_0, -func_meta_off, func_meta);
- if (fexit->nr_links) {
+ if (fexit->nr_nodes) {
if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off, func_meta_off,
false, image, rw_image, func_meta, cookie_off)) {
ret = -EINVAL;
@@ -3533,7 +3533,7 @@ int arch_protect_bpf_trampoline(void *image, unsigned int size)
int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_links *tlinks,
+ struct bpf_tramp_nodes *tnodes,
void *func_addr)
{
void *rw_image, *tmp;
@@ -3548,7 +3548,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
return -ENOMEM;
ret = __arch_prepare_bpf_trampoline(im, rw_image, rw_image + size, image, m,
- flags, tlinks, func_addr);
+ flags, tnodes, func_addr);
if (ret < 0)
goto out;
@@ -3561,7 +3561,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
}
int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_links *tlinks, void *func_addr)
+ struct bpf_tramp_nodes *tnodes, void *func_addr)
{
struct bpf_tramp_image im;
void *image;
@@ -3579,7 +3579,7 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
return -ENOMEM;
ret = __arch_prepare_bpf_trampoline(&im, image, image + PAGE_SIZE, image,
- m, flags, tlinks, func_addr);
+ m, flags, tnodes, func_addr);
bpf_jit_free_exec(image);
return ret;
}
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 801b78b31d9b..f826b65e4f68 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1233,9 +1233,9 @@ enum {
#define BPF_TRAMP_COOKIE_INDEX_SHIFT 8
#define BPF_TRAMP_IS_RETURN_SHIFT 63
-struct bpf_tramp_links {
- struct bpf_tramp_link *links[BPF_MAX_TRAMP_LINKS];
- int nr_links;
+struct bpf_tramp_nodes {
+ struct bpf_tramp_node *nodes[BPF_MAX_TRAMP_LINKS];
+ int nr_nodes;
};
struct bpf_tramp_run_ctx;
@@ -1263,13 +1263,13 @@ struct bpf_tramp_run_ctx;
struct bpf_tramp_image;
int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_links *tlinks,
+ struct bpf_tramp_nodes *tnodes,
void *func_addr);
void *arch_alloc_bpf_trampoline(unsigned int size);
void arch_free_bpf_trampoline(void *image, unsigned int size);
int __must_check arch_protect_bpf_trampoline(void *image, unsigned int size);
int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_links *tlinks, void *func_addr);
+ struct bpf_tramp_nodes *tnodes, void *func_addr);
u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
struct bpf_tramp_run_ctx *run_ctx);
@@ -1453,10 +1453,10 @@ static inline int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u6
}
#ifdef CONFIG_BPF_JIT
-int bpf_trampoline_link_prog(struct bpf_tramp_link *link,
+int bpf_trampoline_link_prog(struct bpf_tramp_node *node,
struct bpf_trampoline *tr,
struct bpf_prog *tgt_prog);
-int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
+int bpf_trampoline_unlink_prog(struct bpf_tramp_node *node,
struct bpf_trampoline *tr,
struct bpf_prog *tgt_prog);
struct bpf_trampoline *bpf_trampoline_get(u64 key,
@@ -1540,13 +1540,13 @@ int bpf_jit_charge_modmem(u32 size);
void bpf_jit_uncharge_modmem(u32 size);
bool bpf_prog_has_trampoline(const struct bpf_prog *prog);
#else
-static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link,
+static inline int bpf_trampoline_link_prog(struct bpf_tramp_node *node,
struct bpf_trampoline *tr,
struct bpf_prog *tgt_prog)
{
return -ENOTSUPP;
}
-static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
+static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_node *node,
struct bpf_trampoline *tr,
struct bpf_prog *tgt_prog)
{
@@ -1869,12 +1869,17 @@ struct bpf_link_ops {
__poll_t (*poll)(struct file *file, struct poll_table_struct *pts);
};
-struct bpf_tramp_link {
- struct bpf_link link;
+struct bpf_tramp_node {
+ struct bpf_link *link;
struct hlist_node tramp_hlist;
u64 cookie;
};
+struct bpf_tramp_link {
+ struct bpf_link link;
+ struct bpf_tramp_node node;
+};
+
struct bpf_shim_tramp_link {
struct bpf_tramp_link link;
struct bpf_trampoline *trampoline;
@@ -2092,8 +2097,8 @@ void bpf_struct_ops_put(const void *kdata);
int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff);
int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key,
void *value);
-int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
- struct bpf_tramp_link *link,
+int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_nodes *tnodes,
+ struct bpf_tramp_node *node,
const struct btf_func_model *model,
void *stub_func,
void **image, u32 *image_off,
@@ -2185,31 +2190,31 @@ static inline void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_op
#endif
-static inline int bpf_fsession_cnt(struct bpf_tramp_links *links)
+static inline int bpf_fsession_cnt(struct bpf_tramp_nodes *nodes)
{
- struct bpf_tramp_links fentries = links[BPF_TRAMP_FENTRY];
+ struct bpf_tramp_nodes fentries = nodes[BPF_TRAMP_FENTRY];
int cnt = 0;
- for (int i = 0; i < links[BPF_TRAMP_FENTRY].nr_links; i++) {
- if (fentries.links[i]->link.prog->expected_attach_type == BPF_TRACE_FSESSION)
+ for (int i = 0; i < nodes[BPF_TRAMP_FENTRY].nr_nodes; i++) {
+ if (fentries.nodes[i]->link->prog->expected_attach_type == BPF_TRACE_FSESSION)
cnt++;
}
return cnt;
}
-static inline bool bpf_prog_calls_session_cookie(struct bpf_tramp_link *link)
+static inline bool bpf_prog_calls_session_cookie(struct bpf_tramp_node *node)
{
- return link->link.prog->call_session_cookie;
+ return node->link->prog->call_session_cookie;
}
-static inline int bpf_fsession_cookie_cnt(struct bpf_tramp_links *links)
+static inline int bpf_fsession_cookie_cnt(struct bpf_tramp_nodes *nodes)
{
- struct bpf_tramp_links fentries = links[BPF_TRAMP_FENTRY];
+ struct bpf_tramp_nodes fentries = nodes[BPF_TRAMP_FENTRY];
int cnt = 0;
- for (int i = 0; i < links[BPF_TRAMP_FENTRY].nr_links; i++) {
- if (bpf_prog_calls_session_cookie(fentries.links[i]))
+ for (int i = 0; i < nodes[BPF_TRAMP_FENTRY].nr_nodes; i++) {
+ if (bpf_prog_calls_session_cookie(fentries.nodes[i]))
cnt++;
}
@@ -2757,6 +2762,9 @@ void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type,
const struct bpf_link_ops *ops, struct bpf_prog *prog,
enum bpf_attach_type attach_type, bool sleepable);
+void bpf_tramp_link_init(struct bpf_tramp_link *link, enum bpf_link_type type,
+ const struct bpf_link_ops *ops, struct bpf_prog *prog,
+ enum bpf_attach_type attach_type, u64 cookie);
int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer);
int bpf_link_settle(struct bpf_link_primer *primer);
void bpf_link_cleanup(struct bpf_link_primer *primer);
@@ -3122,6 +3130,12 @@ static inline void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_
{
}
+static inline void bpf_tramp_link_init(struct bpf_tramp_link *link, enum bpf_link_type type,
+ const struct bpf_link_ops *ops, struct bpf_prog *prog,
+ enum bpf_attach_type attach_type, u64 cookie)
+{
+}
+
static inline int bpf_link_prime(struct bpf_link *link,
struct bpf_link_primer *primer)
{
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 05b366b821c3..10a9301615ba 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -594,8 +594,8 @@ const struct bpf_link_ops bpf_struct_ops_link_lops = {
.dealloc = bpf_struct_ops_link_dealloc,
};
-int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
- struct bpf_tramp_link *link,
+int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_nodes *tnodes,
+ struct bpf_tramp_node *node,
const struct btf_func_model *model,
void *stub_func,
void **_image, u32 *_image_off,
@@ -605,13 +605,13 @@ int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
void *image = *_image;
int size;
- tlinks[BPF_TRAMP_FENTRY].links[0] = link;
- tlinks[BPF_TRAMP_FENTRY].nr_links = 1;
+ tnodes[BPF_TRAMP_FENTRY].nodes[0] = node;
+ tnodes[BPF_TRAMP_FENTRY].nr_nodes = 1;
if (model->ret_size > 0)
flags |= BPF_TRAMP_F_RET_FENTRY_RET;
- size = arch_bpf_trampoline_size(model, flags, tlinks, stub_func);
+ size = arch_bpf_trampoline_size(model, flags, tnodes, stub_func);
if (size <= 0)
return size ? : -EFAULT;
@@ -628,7 +628,7 @@ int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
size = arch_prepare_bpf_trampoline(NULL, image + image_off,
image + image_off + size,
- model, flags, tlinks, stub_func);
+ model, flags, tnodes, stub_func);
if (size <= 0) {
if (image != *_image)
bpf_struct_ops_image_free(image);
@@ -693,7 +693,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
const struct btf_type *module_type;
const struct btf_member *member;
const struct btf_type *t = st_ops_desc->type;
- struct bpf_tramp_links *tlinks;
+ struct bpf_tramp_nodes *tnodes;
void *udata, *kdata;
int prog_fd, err;
u32 i, trampoline_start, image_off = 0;
@@ -720,8 +720,8 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
if (uvalue->common.state || refcount_read(&uvalue->common.refcnt))
return -EINVAL;
- tlinks = kzalloc_objs(*tlinks, BPF_TRAMP_MAX);
- if (!tlinks)
+ tnodes = kzalloc_objs(*tnodes, BPF_TRAMP_MAX);
+ if (!tnodes)
return -ENOMEM;
uvalue = (struct bpf_struct_ops_value *)st_map->uvalue;
@@ -820,8 +820,9 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
err = -ENOMEM;
goto reset_unlock;
}
- bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS,
- &bpf_struct_ops_link_lops, prog, prog->expected_attach_type);
+ bpf_tramp_link_init(link, BPF_LINK_TYPE_STRUCT_OPS,
+ &bpf_struct_ops_link_lops, prog, prog->expected_attach_type, 0);
+
*plink++ = &link->link;
ksym = kzalloc_obj(*ksym, GFP_USER);
@@ -832,7 +833,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
*pksym++ = ksym;
trampoline_start = image_off;
- err = bpf_struct_ops_prepare_trampoline(tlinks, link,
+ err = bpf_struct_ops_prepare_trampoline(tnodes, &link->node,
&st_ops->func_models[i],
*(void **)(st_ops->cfi_stubs + moff),
&image, &image_off,
@@ -910,7 +911,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
memset(uvalue, 0, map->value_size);
memset(kvalue, 0, map->value_size);
unlock:
- kfree(tlinks);
+ kfree(tnodes);
mutex_unlock(&st_map->lock);
if (!err)
bpf_struct_ops_map_add_ksyms(st_map);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b73b25c63073..fe00221de45c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3202,6 +3202,15 @@ void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
bpf_link_init_sleepable(link, type, ops, prog, attach_type, false);
}
+void bpf_tramp_link_init(struct bpf_tramp_link *link, enum bpf_link_type type,
+ const struct bpf_link_ops *ops, struct bpf_prog *prog,
+ enum bpf_attach_type attach_type, u64 cookie)
+{
+ bpf_link_init(&link->link, type, ops, prog, attach_type);
+ link->node.link = &link->link;
+ link->node.cookie = cookie;
+}
+
static void bpf_link_free_id(int id)
{
if (!id)
@@ -3509,7 +3518,7 @@ static void bpf_tracing_link_release(struct bpf_link *link)
struct bpf_tracing_link *tr_link =
container_of(link, struct bpf_tracing_link, link.link);
- WARN_ON_ONCE(bpf_trampoline_unlink_prog(&tr_link->link,
+ WARN_ON_ONCE(bpf_trampoline_unlink_prog(&tr_link->link.node,
tr_link->trampoline,
tr_link->tgt_prog));
@@ -3522,8 +3531,7 @@ static void bpf_tracing_link_release(struct bpf_link *link)
static void bpf_tracing_link_dealloc(struct bpf_link *link)
{
- struct bpf_tracing_link *tr_link =
- container_of(link, struct bpf_tracing_link, link.link);
+ struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link);
kfree(tr_link);
}
@@ -3531,8 +3539,8 @@ static void bpf_tracing_link_dealloc(struct bpf_link *link)
static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link,
struct seq_file *seq)
{
- struct bpf_tracing_link *tr_link =
- container_of(link, struct bpf_tracing_link, link.link);
+ struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link);
+
u32 target_btf_id, target_obj_id;
bpf_trampoline_unpack_key(tr_link->trampoline->key,
@@ -3545,17 +3553,16 @@ static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link,
link->attach_type,
target_obj_id,
target_btf_id,
- tr_link->link.cookie);
+ tr_link->link.node.cookie);
}
static int bpf_tracing_link_fill_link_info(const struct bpf_link *link,
struct bpf_link_info *info)
{
- struct bpf_tracing_link *tr_link =
- container_of(link, struct bpf_tracing_link, link.link);
+ struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link);
info->tracing.attach_type = link->attach_type;
- info->tracing.cookie = tr_link->link.cookie;
+ info->tracing.cookie = tr_link->link.node.cookie;
bpf_trampoline_unpack_key(tr_link->trampoline->key,
&info->tracing.target_obj_id,
&info->tracing.target_btf_id);
@@ -3642,9 +3649,9 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
fslink = kzalloc_obj(*fslink, GFP_USER);
if (fslink) {
- bpf_link_init(&fslink->fexit.link, BPF_LINK_TYPE_TRACING,
- &bpf_tracing_link_lops, prog, attach_type);
- fslink->fexit.cookie = bpf_cookie;
+ bpf_tramp_link_init(&fslink->fexit, BPF_LINK_TYPE_TRACING,
+ &bpf_tracing_link_lops, prog, attach_type,
+ bpf_cookie);
link = &fslink->link;
} else {
link = NULL;
@@ -3656,10 +3663,8 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
err = -ENOMEM;
goto out_put_prog;
}
- bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING,
- &bpf_tracing_link_lops, prog, attach_type);
-
- link->link.cookie = bpf_cookie;
+ bpf_tramp_link_init(&link->link, BPF_LINK_TYPE_TRACING,
+ &bpf_tracing_link_lops, prog, attach_type, bpf_cookie);
mutex_lock(&prog->aux->dst_mutex);
@@ -3762,7 +3767,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
if (err)
goto out_unlock;
- err = bpf_trampoline_link_prog(&link->link, tr, tgt_prog);
+ err = bpf_trampoline_link_prog(&link->link.node, tr, tgt_prog);
if (err) {
bpf_link_cleanup(&link_primer);
link = NULL;
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 71e5a121c2fd..452b82c654e9 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -501,30 +501,29 @@ static const struct bpf_trampoline_ops trampoline_ops = {
.modify_fentry = modify_fentry,
};
-static struct bpf_tramp_links *
+static struct bpf_tramp_nodes *
bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_arg)
{
- struct bpf_tramp_link *link;
- struct bpf_tramp_links *tlinks;
- struct bpf_tramp_link **links;
+ struct bpf_tramp_node *node, **nodes;
+ struct bpf_tramp_nodes *tnodes;
int kind;
*total = 0;
- tlinks = kzalloc_objs(*tlinks, BPF_TRAMP_MAX);
- if (!tlinks)
+ tnodes = kzalloc_objs(*tnodes, BPF_TRAMP_MAX);
+ if (!tnodes)
return ERR_PTR(-ENOMEM);
for (kind = 0; kind < BPF_TRAMP_MAX; kind++) {
- tlinks[kind].nr_links = tr->progs_cnt[kind];
+ tnodes[kind].nr_nodes = tr->progs_cnt[kind];
*total += tr->progs_cnt[kind];
- links = tlinks[kind].links;
+ nodes = tnodes[kind].nodes;
- hlist_for_each_entry(link, &tr->progs_hlist[kind], tramp_hlist) {
- *ip_arg |= link->link.prog->call_get_func_ip;
- *links++ = link;
+ hlist_for_each_entry(node, &tr->progs_hlist[kind], tramp_hlist) {
+ *ip_arg |= node->link->prog->call_get_func_ip;
+ *nodes++ = node;
}
}
- return tlinks;
+ return tnodes;
}
static void bpf_tramp_image_free(struct bpf_tramp_image *im)
@@ -672,14 +671,14 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
const struct bpf_trampoline_ops *ops, void *data)
{
struct bpf_tramp_image *im;
- struct bpf_tramp_links *tlinks;
+ struct bpf_tramp_nodes *tnodes;
u32 orig_flags = tr->flags;
bool ip_arg = false;
int err, total, size;
- tlinks = bpf_trampoline_get_progs(tr, &total, &ip_arg);
- if (IS_ERR(tlinks))
- return PTR_ERR(tlinks);
+ tnodes = bpf_trampoline_get_progs(tr, &total, &ip_arg);
+ if (IS_ERR(tnodes))
+ return PTR_ERR(tnodes);
if (total == 0) {
err = ops->unregister_fentry(tr, orig_flags, data);
@@ -689,8 +688,8 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
/* clear all bits except SHARE_IPMODIFY and TAIL_CALL_CTX */
tr->flags &= (BPF_TRAMP_F_SHARE_IPMODIFY | BPF_TRAMP_F_TAIL_CALL_CTX);
- if (tlinks[BPF_TRAMP_FEXIT].nr_links ||
- tlinks[BPF_TRAMP_MODIFY_RETURN].nr_links) {
+ if (tnodes[BPF_TRAMP_FEXIT].nr_nodes ||
+ tnodes[BPF_TRAMP_MODIFY_RETURN].nr_nodes) {
/* NOTE: BPF_TRAMP_F_RESTORE_REGS and BPF_TRAMP_F_SKIP_FRAME
* should not be set together.
*/
@@ -721,7 +720,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
#endif
size = arch_bpf_trampoline_size(&tr->func.model, tr->flags,
- tlinks, tr->func.addr);
+ tnodes, tr->func.addr);
if (size < 0) {
err = size;
goto out;
@@ -739,7 +738,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
}
err = arch_prepare_bpf_trampoline(im, im->image, im->image + size,
- &tr->func.model, tr->flags, tlinks,
+ &tr->func.model, tr->flags, tnodes,
tr->func.addr);
if (err < 0)
goto out_free;
@@ -774,7 +773,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
/* If any error happens, restore previous flags */
if (err)
tr->flags = orig_flags;
- kfree(tlinks);
+ kfree(tnodes);
return err;
}
@@ -821,15 +820,15 @@ static int bpf_freplace_check_tgt_prog(struct bpf_prog *tgt_prog)
}
static int bpf_trampoline_add_prog(struct bpf_trampoline *tr,
- struct bpf_tramp_link *link,
+ struct bpf_tramp_node *node,
int cnt)
{
struct bpf_fsession_link *fslink = NULL;
enum bpf_tramp_prog_type kind;
- struct bpf_tramp_link *link_exiting;
+ struct bpf_tramp_node *node_existing;
struct hlist_head *prog_list;
- kind = bpf_attach_type_to_tramp(link->link.prog);
+ kind = bpf_attach_type_to_tramp(node->link->prog);
if (kind == BPF_TRAMP_FSESSION) {
prog_list = &tr->progs_hlist[BPF_TRAMP_FENTRY];
cnt++;
@@ -838,21 +837,21 @@ static int bpf_trampoline_add_prog(struct bpf_trampoline *tr,
}
if (cnt >= BPF_MAX_TRAMP_LINKS)
return -E2BIG;
- if (!hlist_unhashed(&link->tramp_hlist))
+ if (!hlist_unhashed(&node->tramp_hlist))
/* prog already linked */
return -EBUSY;
- hlist_for_each_entry(link_exiting, prog_list, tramp_hlist) {
- if (link_exiting->link.prog != link->link.prog)
+ hlist_for_each_entry(node_existing, prog_list, tramp_hlist) {
+ if (node_existing->link->prog != node->link->prog)
continue;
/* prog already linked */
return -EBUSY;
}
- hlist_add_head(&link->tramp_hlist, prog_list);
+ hlist_add_head(&node->tramp_hlist, prog_list);
if (kind == BPF_TRAMP_FSESSION) {
tr->progs_cnt[BPF_TRAMP_FENTRY]++;
- fslink = container_of(link, struct bpf_fsession_link, link.link);
- hlist_add_head(&fslink->fexit.tramp_hlist, &tr->progs_hlist[BPF_TRAMP_FEXIT]);
+ fslink = container_of(node, struct bpf_fsession_link, link.link.node);
+ hlist_add_head(&fslink->fexit.node.tramp_hlist, &tr->progs_hlist[BPF_TRAMP_FEXIT]);
tr->progs_cnt[BPF_TRAMP_FEXIT]++;
} else {
tr->progs_cnt[kind]++;
@@ -861,23 +860,23 @@ static int bpf_trampoline_add_prog(struct bpf_trampoline *tr,
}
static void bpf_trampoline_remove_prog(struct bpf_trampoline *tr,
- struct bpf_tramp_link *link)
+ struct bpf_tramp_node *node)
{
struct bpf_fsession_link *fslink;
enum bpf_tramp_prog_type kind;
- kind = bpf_attach_type_to_tramp(link->link.prog);
+ kind = bpf_attach_type_to_tramp(node->link->prog);
if (kind == BPF_TRAMP_FSESSION) {
- fslink = container_of(link, struct bpf_fsession_link, link.link);
- hlist_del_init(&fslink->fexit.tramp_hlist);
+ fslink = container_of(node, struct bpf_fsession_link, link.link.node);
+ hlist_del_init(&fslink->fexit.node.tramp_hlist);
tr->progs_cnt[BPF_TRAMP_FEXIT]--;
kind = BPF_TRAMP_FENTRY;
}
- hlist_del_init(&link->tramp_hlist);
+ hlist_del_init(&node->tramp_hlist);
tr->progs_cnt[kind]--;
}
-static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link,
+static int __bpf_trampoline_link_prog(struct bpf_tramp_node *node,
struct bpf_trampoline *tr,
struct bpf_prog *tgt_prog,
const struct bpf_trampoline_ops *ops,
@@ -887,7 +886,7 @@ static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link,
int err = 0;
int cnt = 0, i;
- kind = bpf_attach_type_to_tramp(link->link.prog);
+ kind = bpf_attach_type_to_tramp(node->link->prog);
if (tr->extension_prog)
/* cannot attach fentry/fexit if extension prog is attached.
* cannot overwrite extension prog either.
@@ -904,33 +903,33 @@ static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link,
err = bpf_freplace_check_tgt_prog(tgt_prog);
if (err)
return err;
- tr->extension_prog = link->link.prog;
+ tr->extension_prog = node->link->prog;
return bpf_arch_text_poke(tr->func.addr, BPF_MOD_NOP,
BPF_MOD_JUMP, NULL,
- link->link.prog->bpf_func);
+ node->link->prog->bpf_func);
}
- err = bpf_trampoline_add_prog(tr, link, cnt);
+ err = bpf_trampoline_add_prog(tr, node, cnt);
if (err)
return err;
err = bpf_trampoline_update(tr, true /* lock_direct_mutex */, ops, data);
if (err)
- bpf_trampoline_remove_prog(tr, link);
+ bpf_trampoline_remove_prog(tr, node);
return err;
}
-int bpf_trampoline_link_prog(struct bpf_tramp_link *link,
+int bpf_trampoline_link_prog(struct bpf_tramp_node *node,
struct bpf_trampoline *tr,
struct bpf_prog *tgt_prog)
{
int err;
trampoline_lock(tr);
- err = __bpf_trampoline_link_prog(link, tr, tgt_prog, &trampoline_ops, NULL);
+ err = __bpf_trampoline_link_prog(node, tr, tgt_prog, &trampoline_ops, NULL);
trampoline_unlock(tr);
return err;
}
-static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
+static int __bpf_trampoline_unlink_prog(struct bpf_tramp_node *node,
struct bpf_trampoline *tr,
struct bpf_prog *tgt_prog,
const struct bpf_trampoline_ops *ops,
@@ -939,7 +938,7 @@ static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
enum bpf_tramp_prog_type kind;
int err;
- kind = bpf_attach_type_to_tramp(link->link.prog);
+ kind = bpf_attach_type_to_tramp(node->link->prog);
if (kind == BPF_TRAMP_REPLACE) {
WARN_ON_ONCE(!tr->extension_prog);
err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP,
@@ -950,19 +949,19 @@ static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
tgt_prog->aux->is_extended = false;
return err;
}
- bpf_trampoline_remove_prog(tr, link);
+ bpf_trampoline_remove_prog(tr, node);
return bpf_trampoline_update(tr, true /* lock_direct_mutex */, ops, data);
}
/* bpf_trampoline_unlink_prog() should never fail. */
-int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
+int bpf_trampoline_unlink_prog(struct bpf_tramp_node *node,
struct bpf_trampoline *tr,
struct bpf_prog *tgt_prog)
{
int err;
trampoline_lock(tr);
- err = __bpf_trampoline_unlink_prog(link, tr, tgt_prog, &trampoline_ops, NULL);
+ err = __bpf_trampoline_unlink_prog(node, tr, tgt_prog, &trampoline_ops, NULL);
trampoline_unlock(tr);
return err;
}
@@ -977,7 +976,7 @@ static void bpf_shim_tramp_link_release(struct bpf_link *link)
if (!shim_link->trampoline)
return;
- WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline, NULL));
+ WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link.node, shim_link->trampoline, NULL));
bpf_trampoline_put(shim_link->trampoline);
}
@@ -1023,8 +1022,8 @@ static struct bpf_shim_tramp_link *cgroup_shim_alloc(const struct bpf_prog *prog
p->type = BPF_PROG_TYPE_LSM;
p->expected_attach_type = BPF_LSM_MAC;
bpf_prog_inc(p);
- bpf_link_init(&shim_link->link.link, BPF_LINK_TYPE_UNSPEC,
- &bpf_shim_tramp_link_lops, p, attach_type);
+ bpf_tramp_link_init(&shim_link->link, BPF_LINK_TYPE_UNSPEC,
+ &bpf_shim_tramp_link_lops, p, attach_type, 0);
bpf_cgroup_atype_get(p->aux->attach_btf_id, cgroup_atype);
return shim_link;
@@ -1033,15 +1032,15 @@ static struct bpf_shim_tramp_link *cgroup_shim_alloc(const struct bpf_prog *prog
static struct bpf_shim_tramp_link *cgroup_shim_find(struct bpf_trampoline *tr,
bpf_func_t bpf_func)
{
- struct bpf_tramp_link *link;
+ struct bpf_tramp_node *node;
int kind;
for (kind = 0; kind < BPF_TRAMP_MAX; kind++) {
- hlist_for_each_entry(link, &tr->progs_hlist[kind], tramp_hlist) {
- struct bpf_prog *p = link->link.prog;
+ hlist_for_each_entry(node, &tr->progs_hlist[kind], tramp_hlist) {
+ struct bpf_prog *p = node->link->prog;
if (p->bpf_func == bpf_func)
- return container_of(link, struct bpf_shim_tramp_link, link);
+ return container_of(node, struct bpf_shim_tramp_link, link.node);
}
}
@@ -1091,7 +1090,7 @@ int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
goto err;
}
- err = __bpf_trampoline_link_prog(&shim_link->link, tr, NULL, &trampoline_ops, NULL);
+ err = __bpf_trampoline_link_prog(&shim_link->link.node, tr, NULL, &trampoline_ops, NULL);
if (err)
goto err;
@@ -1406,7 +1405,7 @@ bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog)
int __weak
arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_links *tlinks,
+ struct bpf_tramp_nodes *tnodes,
void *func_addr)
{
return -ENOTSUPP;
@@ -1440,7 +1439,7 @@ int __weak arch_protect_bpf_trampoline(void *image, unsigned int size)
}
int __weak arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_links *tlinks, void *func_addr)
+ struct bpf_tramp_nodes *tnodes, void *func_addr)
{
return -ENOTSUPP;
}
diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c
index ae5a54c350b9..191a6b3ee254 100644
--- a/net/bpf/bpf_dummy_struct_ops.c
+++ b/net/bpf/bpf_dummy_struct_ops.c
@@ -132,7 +132,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
const struct bpf_struct_ops *st_ops = &bpf_bpf_dummy_ops;
const struct btf_type *func_proto;
struct bpf_dummy_ops_test_args *args;
- struct bpf_tramp_links *tlinks = NULL;
+ struct bpf_tramp_nodes *tnodes = NULL;
struct bpf_tramp_link *link = NULL;
void *image = NULL;
unsigned int op_idx;
@@ -158,8 +158,8 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
if (err)
goto out;
- tlinks = kzalloc_objs(*tlinks, BPF_TRAMP_MAX);
- if (!tlinks) {
+ tnodes = kzalloc_objs(*tnodes, BPF_TRAMP_MAX);
+ if (!tnodes) {
err = -ENOMEM;
goto out;
}
@@ -171,11 +171,11 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
}
/* prog doesn't take the ownership of the reference from caller */
bpf_prog_inc(prog);
- bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS, &bpf_struct_ops_link_lops, prog,
- prog->expected_attach_type);
+ bpf_tramp_link_init(link, BPF_LINK_TYPE_STRUCT_OPS, &bpf_struct_ops_link_lops,
+ prog, prog->expected_attach_type, 0);
op_idx = prog->expected_attach_type;
- err = bpf_struct_ops_prepare_trampoline(tlinks, link,
+ err = bpf_struct_ops_prepare_trampoline(tnodes, &link->node,
&st_ops->func_models[op_idx],
&dummy_ops_test_ret_function,
&image, &image_off,
@@ -198,7 +198,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
bpf_struct_ops_image_free(image);
if (link)
bpf_link_put(&link->link);
- kfree(tlinks);
+ kfree(tnodes);
return err;
}
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 07/28] bpf: Add bpf_trampoline_add/remove_prog functions
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
Separate bpf_trampoline_add/remove_prog functions from
__bpf_trampoline_link/unlink functions to be able to add/remove
trampoline programs without the image being updated in following
changes. No functional change is intended.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
kernel/bpf/trampoline.c | 108 +++++++++++++++++++++++-----------------
1 file changed, 61 insertions(+), 47 deletions(-)
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index ad4ddb62d22f..71e5a121c2fd 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -820,41 +820,16 @@ static int bpf_freplace_check_tgt_prog(struct bpf_prog *tgt_prog)
return 0;
}
-static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link,
- struct bpf_trampoline *tr,
- struct bpf_prog *tgt_prog,
- const struct bpf_trampoline_ops *ops,
- void *data)
+static int bpf_trampoline_add_prog(struct bpf_trampoline *tr,
+ struct bpf_tramp_link *link,
+ int cnt)
{
struct bpf_fsession_link *fslink = NULL;
enum bpf_tramp_prog_type kind;
struct bpf_tramp_link *link_exiting;
struct hlist_head *prog_list;
- int err = 0;
- int cnt = 0, i;
kind = bpf_attach_type_to_tramp(link->link.prog);
- if (tr->extension_prog)
- /* cannot attach fentry/fexit if extension prog is attached.
- * cannot overwrite extension prog either.
- */
- return -EBUSY;
-
- for (i = 0; i < BPF_TRAMP_MAX; i++)
- cnt += tr->progs_cnt[i];
-
- if (kind == BPF_TRAMP_REPLACE) {
- /* Cannot attach extension if fentry/fexit are in use. */
- if (cnt)
- return -EBUSY;
- err = bpf_freplace_check_tgt_prog(tgt_prog);
- if (err)
- return err;
- tr->extension_prog = link->link.prog;
- return bpf_arch_text_poke(tr->func.addr, BPF_MOD_NOP,
- BPF_MOD_JUMP, NULL,
- link->link.prog->bpf_func);
- }
if (kind == BPF_TRAMP_FSESSION) {
prog_list = &tr->progs_hlist[BPF_TRAMP_FENTRY];
cnt++;
@@ -882,17 +857,64 @@ static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link,
} else {
tr->progs_cnt[kind]++;
}
- err = bpf_trampoline_update(tr, true /* lock_direct_mutex */, ops, data);
- if (err) {
- hlist_del_init(&link->tramp_hlist);
- if (kind == BPF_TRAMP_FSESSION) {
- tr->progs_cnt[BPF_TRAMP_FENTRY]--;
- hlist_del_init(&fslink->fexit.tramp_hlist);
- tr->progs_cnt[BPF_TRAMP_FEXIT]--;
- } else {
- tr->progs_cnt[kind]--;
- }
+ return 0;
+}
+
+static void bpf_trampoline_remove_prog(struct bpf_trampoline *tr,
+ struct bpf_tramp_link *link)
+{
+ struct bpf_fsession_link *fslink;
+ enum bpf_tramp_prog_type kind;
+
+ kind = bpf_attach_type_to_tramp(link->link.prog);
+ if (kind == BPF_TRAMP_FSESSION) {
+ fslink = container_of(link, struct bpf_fsession_link, link.link);
+ hlist_del_init(&fslink->fexit.tramp_hlist);
+ tr->progs_cnt[BPF_TRAMP_FEXIT]--;
+ kind = BPF_TRAMP_FENTRY;
+ }
+ hlist_del_init(&link->tramp_hlist);
+ tr->progs_cnt[kind]--;
+}
+
+static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link,
+ struct bpf_trampoline *tr,
+ struct bpf_prog *tgt_prog,
+ const struct bpf_trampoline_ops *ops,
+ void *data)
+{
+ enum bpf_tramp_prog_type kind;
+ int err = 0;
+ int cnt = 0, i;
+
+ kind = bpf_attach_type_to_tramp(link->link.prog);
+ if (tr->extension_prog)
+ /* cannot attach fentry/fexit if extension prog is attached.
+ * cannot overwrite extension prog either.
+ */
+ return -EBUSY;
+
+ for (i = 0; i < BPF_TRAMP_MAX; i++)
+ cnt += tr->progs_cnt[i];
+
+ if (kind == BPF_TRAMP_REPLACE) {
+ /* Cannot attach extension if fentry/fexit are in use. */
+ if (cnt)
+ return -EBUSY;
+ err = bpf_freplace_check_tgt_prog(tgt_prog);
+ if (err)
+ return err;
+ tr->extension_prog = link->link.prog;
+ return bpf_arch_text_poke(tr->func.addr, BPF_MOD_NOP,
+ BPF_MOD_JUMP, NULL,
+ link->link.prog->bpf_func);
}
+ err = bpf_trampoline_add_prog(tr, link, cnt);
+ if (err)
+ return err;
+ err = bpf_trampoline_update(tr, true /* lock_direct_mutex */, ops, data);
+ if (err)
+ bpf_trampoline_remove_prog(tr, link);
return err;
}
@@ -927,16 +949,8 @@ static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
guard(mutex)(&tgt_prog->aux->ext_mutex);
tgt_prog->aux->is_extended = false;
return err;
- } else if (kind == BPF_TRAMP_FSESSION) {
- struct bpf_fsession_link *fslink =
- container_of(link, struct bpf_fsession_link, link.link);
-
- hlist_del_init(&fslink->fexit.tramp_hlist);
- tr->progs_cnt[BPF_TRAMP_FEXIT]--;
- kind = BPF_TRAMP_FENTRY;
}
- hlist_del_init(&link->tramp_hlist);
- tr->progs_cnt[kind]--;
+ bpf_trampoline_remove_prog(tr, link);
return bpf_trampoline_update(tr, true /* lock_direct_mutex */, ops, data);
}
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 06/28] bpf: Move trampoline image setup into bpf_trampoline_ops callbacks
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
Moving trampoline image setup into bpf_trampoline_ops callbacks,
so we can have different image handling for multi attachment which
is coming in following changes.
There's slight functional change for the unregister path, where we
currently free the image unconditionally even if the detach fails.
The new code keeps the image in place, possibly preventing the crash.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
kernel/bpf/trampoline.c | 66 ++++++++++++++++++++++++-----------------
1 file changed, 38 insertions(+), 28 deletions(-)
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index e3b4e504fdb2..ad4ddb62d22f 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -59,11 +59,10 @@ static void trampoline_unlock(struct bpf_trampoline *tr)
}
struct bpf_trampoline_ops {
- int (*register_fentry)(struct bpf_trampoline *tr, void *new_addr, void *data);
- int (*unregister_fentry)(struct bpf_trampoline *tr, u32 orig_flags, void *old_addr,
- void *data);
- int (*modify_fentry)(struct bpf_trampoline *tr, u32 orig_flags, void *old_addr,
- void *new_addr, bool lock_direct_mutex, void *data);
+ int (*register_fentry)(struct bpf_trampoline *tr, struct bpf_tramp_image *im, void *data);
+ int (*unregister_fentry)(struct bpf_trampoline *tr, u32 orig_flags, void *data);
+ int (*modify_fentry)(struct bpf_trampoline *tr, u32 orig_flags, struct bpf_tramp_image *im,
+ bool lock_direct_mutex, void *data);
};
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
@@ -425,9 +424,11 @@ static int bpf_trampoline_update_fentry(struct bpf_trampoline *tr, u32 orig_flag
return bpf_arch_text_poke(ip, old_t, new_t, old_addr, new_addr);
}
-static int unregister_fentry(struct bpf_trampoline *tr, u32 orig_flags,
- void *old_addr, void *data __maybe_unused)
+static void bpf_tramp_image_put(struct bpf_tramp_image *im);
+
+static int unregister_fentry(struct bpf_trampoline *tr, u32 orig_flags, void *data __maybe_unused)
{
+ void *old_addr = tr->cur_image->image;
int ret;
if (tr->func.ftrace_managed)
@@ -435,13 +436,19 @@ static int unregister_fentry(struct bpf_trampoline *tr, u32 orig_flags,
else
ret = bpf_trampoline_update_fentry(tr, orig_flags, old_addr, NULL);
- return ret;
+ if (ret)
+ return ret;
+
+ bpf_tramp_image_put(tr->cur_image);
+ tr->cur_image = NULL;
+ return 0;
}
-static int modify_fentry(struct bpf_trampoline *tr, u32 orig_flags,
- void *old_addr, void *new_addr,
+static int modify_fentry(struct bpf_trampoline *tr, u32 orig_flags, struct bpf_tramp_image *im,
bool lock_direct_mutex, void *data __maybe_unused)
{
+ void *old_addr = tr->cur_image->image;
+ void *new_addr = im->image;
int ret;
if (tr->func.ftrace_managed) {
@@ -450,12 +457,20 @@ static int modify_fentry(struct bpf_trampoline *tr, u32 orig_flags,
ret = bpf_trampoline_update_fentry(tr, orig_flags, old_addr,
new_addr);
}
- return ret;
+
+ if (ret)
+ return ret;
+
+ bpf_tramp_image_put(tr->cur_image);
+ tr->cur_image = im;
+ return 0;
}
/* first time registering */
-static int register_fentry(struct bpf_trampoline *tr, void *new_addr, void *data __maybe_unused)
+static int register_fentry(struct bpf_trampoline *tr, struct bpf_tramp_image *im,
+ void *data __maybe_unused)
{
+ void *new_addr = im->image;
void *ip = tr->func.addr;
unsigned long faddr;
int ret;
@@ -473,7 +488,11 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr, void *data
ret = bpf_trampoline_update_fentry(tr, 0, NULL, new_addr);
}
- return ret;
+ if (ret)
+ return ret;
+
+ tr->cur_image = im;
+ return 0;
}
static const struct bpf_trampoline_ops trampoline_ops = {
@@ -663,9 +682,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
return PTR_ERR(tlinks);
if (total == 0) {
- err = ops->unregister_fentry(tr, orig_flags, tr->cur_image->image, data);
- bpf_tramp_image_put(tr->cur_image);
- tr->cur_image = NULL;
+ err = ops->unregister_fentry(tr, orig_flags, data);
goto out;
}
@@ -734,11 +751,10 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
WARN_ON(tr->cur_image && total == 0);
if (tr->cur_image)
/* progs already running at this address */
- err = ops->modify_fentry(tr, orig_flags, tr->cur_image->image,
- im->image, lock_direct_mutex, data);
+ err = ops->modify_fentry(tr, orig_flags, im, lock_direct_mutex, data);
else
/* first time registering */
- err = ops->register_fentry(tr, im->image, data);
+ err = ops->register_fentry(tr, im, data);
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
if (err == -EAGAIN) {
@@ -750,22 +766,16 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
goto again;
}
#endif
- if (err)
- goto out_free;
- if (tr->cur_image)
- bpf_tramp_image_put(tr->cur_image);
- tr->cur_image = im;
+out_free:
+ if (err)
+ bpf_tramp_image_free(im);
out:
/* If any error happens, restore previous flags */
if (err)
tr->flags = orig_flags;
kfree(tlinks);
return err;
-
-out_free:
- bpf_tramp_image_free(im);
- goto out;
}
static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog)
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 05/28] bpf: Add struct bpf_trampoline_ops object
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
In following changes we will need to override ftrace direct attachment
behaviour. In order to do that we are adding struct bpf_trampoline_ops
object that defines callbacks for ftrace direct attachment:
register_fentry
unregister_fentry
modify_fentry
The new struct bpf_trampoline_ops object is passed as an argument to
__bpf_trampoline_link/unlink_prog functions.
At the moment the default trampoline_ops is set to the current ftrace
direct attachment functions, so there's no functional change for the
current code.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
kernel/bpf/trampoline.c | 59 ++++++++++++++++++++++++++++-------------
1 file changed, 41 insertions(+), 18 deletions(-)
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index eb4ea78ff77f..e3b4e504fdb2 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -58,8 +58,18 @@ static void trampoline_unlock(struct bpf_trampoline *tr)
mutex_unlock(select_trampoline_lock(tr));
}
+struct bpf_trampoline_ops {
+ int (*register_fentry)(struct bpf_trampoline *tr, void *new_addr, void *data);
+ int (*unregister_fentry)(struct bpf_trampoline *tr, u32 orig_flags, void *old_addr,
+ void *data);
+ int (*modify_fentry)(struct bpf_trampoline *tr, u32 orig_flags, void *old_addr,
+ void *new_addr, bool lock_direct_mutex, void *data);
+};
+
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
-static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mutex);
+static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mutex,
+ const struct bpf_trampoline_ops *ops, void *data);
+static const struct bpf_trampoline_ops trampoline_ops;
#ifdef CONFIG_HAVE_SINGLE_FTRACE_DIRECT_OPS
static struct bpf_trampoline *direct_ops_ip_lookup(struct ftrace_ops *ops, unsigned long ip)
@@ -144,13 +154,15 @@ static int bpf_tramp_ftrace_ops_func(struct ftrace_ops *ops, unsigned long ip,
if ((tr->flags & BPF_TRAMP_F_CALL_ORIG) &&
!(tr->flags & BPF_TRAMP_F_ORIG_STACK))
- ret = bpf_trampoline_update(tr, false /* lock_direct_mutex */);
+ ret = bpf_trampoline_update(tr, false /* lock_direct_mutex */,
+ &trampoline_ops, NULL);
break;
case FTRACE_OPS_CMD_DISABLE_SHARE_IPMODIFY_PEER:
tr->flags &= ~BPF_TRAMP_F_SHARE_IPMODIFY;
if (tr->flags & BPF_TRAMP_F_ORIG_STACK)
- ret = bpf_trampoline_update(tr, false /* lock_direct_mutex */);
+ ret = bpf_trampoline_update(tr, false /* lock_direct_mutex */,
+ &trampoline_ops, NULL);
break;
default:
ret = -EINVAL;
@@ -414,7 +426,7 @@ static int bpf_trampoline_update_fentry(struct bpf_trampoline *tr, u32 orig_flag
}
static int unregister_fentry(struct bpf_trampoline *tr, u32 orig_flags,
- void *old_addr)
+ void *old_addr, void *data __maybe_unused)
{
int ret;
@@ -428,7 +440,7 @@ static int unregister_fentry(struct bpf_trampoline *tr, u32 orig_flags,
static int modify_fentry(struct bpf_trampoline *tr, u32 orig_flags,
void *old_addr, void *new_addr,
- bool lock_direct_mutex)
+ bool lock_direct_mutex, void *data __maybe_unused)
{
int ret;
@@ -442,7 +454,7 @@ static int modify_fentry(struct bpf_trampoline *tr, u32 orig_flags,
}
/* first time registering */
-static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
+static int register_fentry(struct bpf_trampoline *tr, void *new_addr, void *data __maybe_unused)
{
void *ip = tr->func.addr;
unsigned long faddr;
@@ -464,6 +476,12 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
return ret;
}
+static const struct bpf_trampoline_ops trampoline_ops = {
+ .register_fentry = register_fentry,
+ .unregister_fentry = unregister_fentry,
+ .modify_fentry = modify_fentry,
+};
+
static struct bpf_tramp_links *
bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_arg)
{
@@ -631,7 +649,8 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, int size)
return ERR_PTR(err);
}
-static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mutex)
+static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mutex,
+ const struct bpf_trampoline_ops *ops, void *data)
{
struct bpf_tramp_image *im;
struct bpf_tramp_links *tlinks;
@@ -644,7 +663,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
return PTR_ERR(tlinks);
if (total == 0) {
- err = unregister_fentry(tr, orig_flags, tr->cur_image->image);
+ err = ops->unregister_fentry(tr, orig_flags, tr->cur_image->image, data);
bpf_tramp_image_put(tr->cur_image);
tr->cur_image = NULL;
goto out;
@@ -715,11 +734,11 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
WARN_ON(tr->cur_image && total == 0);
if (tr->cur_image)
/* progs already running at this address */
- err = modify_fentry(tr, orig_flags, tr->cur_image->image,
- im->image, lock_direct_mutex);
+ err = ops->modify_fentry(tr, orig_flags, tr->cur_image->image,
+ im->image, lock_direct_mutex, data);
else
/* first time registering */
- err = register_fentry(tr, im->image);
+ err = ops->register_fentry(tr, im->image, data);
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
if (err == -EAGAIN) {
@@ -793,7 +812,9 @@ static int bpf_freplace_check_tgt_prog(struct bpf_prog *tgt_prog)
static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link,
struct bpf_trampoline *tr,
- struct bpf_prog *tgt_prog)
+ struct bpf_prog *tgt_prog,
+ const struct bpf_trampoline_ops *ops,
+ void *data)
{
struct bpf_fsession_link *fslink = NULL;
enum bpf_tramp_prog_type kind;
@@ -851,7 +872,7 @@ static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link,
} else {
tr->progs_cnt[kind]++;
}
- err = bpf_trampoline_update(tr, true /* lock_direct_mutex */);
+ err = bpf_trampoline_update(tr, true /* lock_direct_mutex */, ops, data);
if (err) {
hlist_del_init(&link->tramp_hlist);
if (kind == BPF_TRAMP_FSESSION) {
@@ -872,14 +893,16 @@ int bpf_trampoline_link_prog(struct bpf_tramp_link *link,
int err;
trampoline_lock(tr);
- err = __bpf_trampoline_link_prog(link, tr, tgt_prog);
+ err = __bpf_trampoline_link_prog(link, tr, tgt_prog, &trampoline_ops, NULL);
trampoline_unlock(tr);
return err;
}
static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
struct bpf_trampoline *tr,
- struct bpf_prog *tgt_prog)
+ struct bpf_prog *tgt_prog,
+ const struct bpf_trampoline_ops *ops,
+ void *data)
{
enum bpf_tramp_prog_type kind;
int err;
@@ -904,7 +927,7 @@ static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
}
hlist_del_init(&link->tramp_hlist);
tr->progs_cnt[kind]--;
- return bpf_trampoline_update(tr, true /* lock_direct_mutex */);
+ return bpf_trampoline_update(tr, true /* lock_direct_mutex */, ops, data);
}
/* bpf_trampoline_unlink_prog() should never fail. */
@@ -915,7 +938,7 @@ int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
int err;
trampoline_lock(tr);
- err = __bpf_trampoline_unlink_prog(link, tr, tgt_prog);
+ err = __bpf_trampoline_unlink_prog(link, tr, tgt_prog, &trampoline_ops, NULL);
trampoline_unlock(tr);
return err;
}
@@ -1044,7 +1067,7 @@ int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
goto err;
}
- err = __bpf_trampoline_link_prog(&shim_link->link, tr, NULL);
+ err = __bpf_trampoline_link_prog(&shim_link->link, tr, NULL, &trampoline_ops, NULL);
if (err)
goto err;
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 04/28] bpf: Use mutex lock pool for bpf trampolines
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
Adding mutex lock pool that replaces bpf trampolines mutex.
For tracing_multi link coming in following changes we need to lock all
the involved trampolines during the attachment. This could mean thousands
of mutex locks, which is not convenient.
As suggested by Andrii we can replace bpf trampolines mutex with mutex
pool, where each trampoline is hash-ed to one of the locks from the pool.
It's better to lock all the pool mutexes (32 at the moment) than
thousands of them.
There is 48 (MAX_LOCK_DEPTH) lock limit allowed to be simultaneously
held by task, so we need to keep 32 mutexes (5 bits) in the pool, so
when we lock them all in following changes the lockdep won't scream.
Removing the mutex_is_locked in bpf_trampoline_put, because we removed
the mutex from bpf_trampoline.
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
include/linux/bpf.h | 2 --
kernel/bpf/trampoline.c | 76 ++++++++++++++++++++++++++++-------------
2 files changed, 52 insertions(+), 26 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 0136a108d083..801b78b31d9b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1335,8 +1335,6 @@ struct bpf_trampoline {
/* hlist for trampoline_ip_table */
struct hlist_node hlist_ip;
struct ftrace_ops *fops;
- /* serializes access to fields of this trampoline */
- struct mutex mutex;
refcount_t refcnt;
u32 flags;
u64 key;
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index f02254a21585..eb4ea78ff77f 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -30,6 +30,34 @@ static struct hlist_head trampoline_ip_table[TRAMPOLINE_TABLE_SIZE];
/* serializes access to trampoline tables */
static DEFINE_MUTEX(trampoline_mutex);
+/*
+ * We keep 32 trampoline locks (5 bits) in the pool, because there is
+ * 48 (MAX_LOCK_DEPTH) locks limit allowed to be simultaneously held
+ * by task. Each lock has its own lockdep key to keep it simple.
+ */
+#define TRAMPOLINE_LOCKS_BITS 5
+#define TRAMPOLINE_LOCKS_TABLE_SIZE (1 << TRAMPOLINE_LOCKS_BITS)
+
+static struct {
+ struct mutex mutex;
+ struct lock_class_key key;
+} trampoline_locks[TRAMPOLINE_LOCKS_TABLE_SIZE];
+
+static struct mutex *select_trampoline_lock(struct bpf_trampoline *tr)
+{
+ return &trampoline_locks[hash_64((u64)(uintptr_t) tr, TRAMPOLINE_LOCKS_BITS)].mutex;
+}
+
+static void trampoline_lock(struct bpf_trampoline *tr)
+{
+ mutex_lock(select_trampoline_lock(tr));
+}
+
+static void trampoline_unlock(struct bpf_trampoline *tr)
+{
+ mutex_unlock(select_trampoline_lock(tr));
+}
+
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mutex);
@@ -69,9 +97,9 @@ static int bpf_tramp_ftrace_ops_func(struct ftrace_ops *ops, unsigned long ip,
if (cmd == FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_SELF) {
/* This is called inside register_ftrace_direct_multi(), so
- * tr->mutex is already locked.
+ * trampoline's mutex is already locked.
*/
- lockdep_assert_held_once(&tr->mutex);
+ lockdep_assert_held_once(select_trampoline_lock(tr));
/* Instead of updating the trampoline here, we propagate
* -EAGAIN to register_ftrace_direct(). Then we can
@@ -91,7 +119,7 @@ static int bpf_tramp_ftrace_ops_func(struct ftrace_ops *ops, unsigned long ip,
}
/* The normal locking order is
- * tr->mutex => direct_mutex (ftrace.c) => ftrace_lock (ftrace.c)
+ * select_trampoline_lock(tr) => direct_mutex (ftrace.c) => ftrace_lock (ftrace.c)
*
* The following two commands are called from
*
@@ -99,12 +127,12 @@ static int bpf_tramp_ftrace_ops_func(struct ftrace_ops *ops, unsigned long ip,
* cleanup_direct_functions_after_ipmodify
*
* In both cases, direct_mutex is already locked. Use
- * mutex_trylock(&tr->mutex) to avoid deadlock in race condition
- * (something else is making changes to this same trampoline).
+ * mutex_trylock(select_trampoline_lock(tr)) to avoid deadlock in race condition
+ * (something else holds the same pool lock).
*/
- if (!mutex_trylock(&tr->mutex)) {
- /* sleep 1 ms to make sure whatever holding tr->mutex makes
- * some progress.
+ if (!mutex_trylock(select_trampoline_lock(tr))) {
+ /* sleep 1 ms to make sure whatever holding select_trampoline_lock(tr)
+ * makes some progress.
*/
msleep(1);
return -EAGAIN;
@@ -129,7 +157,7 @@ static int bpf_tramp_ftrace_ops_func(struct ftrace_ops *ops, unsigned long ip,
break;
}
- mutex_unlock(&tr->mutex);
+ trampoline_unlock(tr);
return ret;
}
#endif
@@ -359,7 +387,6 @@ static struct bpf_trampoline *bpf_trampoline_lookup(u64 key, unsigned long ip)
head = &trampoline_ip_table[hash_64(tr->ip, TRAMPOLINE_HASH_BITS)];
hlist_add_head(&tr->hlist_ip, head);
refcount_set(&tr->refcnt, 1);
- mutex_init(&tr->mutex);
for (i = 0; i < BPF_TRAMP_MAX; i++)
INIT_HLIST_HEAD(&tr->progs_hlist[i]);
out:
@@ -844,9 +871,9 @@ int bpf_trampoline_link_prog(struct bpf_tramp_link *link,
{
int err;
- mutex_lock(&tr->mutex);
+ trampoline_lock(tr);
err = __bpf_trampoline_link_prog(link, tr, tgt_prog);
- mutex_unlock(&tr->mutex);
+ trampoline_unlock(tr);
return err;
}
@@ -887,9 +914,9 @@ int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
{
int err;
- mutex_lock(&tr->mutex);
+ trampoline_lock(tr);
err = __bpf_trampoline_unlink_prog(link, tr, tgt_prog);
- mutex_unlock(&tr->mutex);
+ trampoline_unlock(tr);
return err;
}
@@ -999,12 +1026,12 @@ int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
if (!tr)
return -ENOMEM;
- mutex_lock(&tr->mutex);
+ trampoline_lock(tr);
shim_link = cgroup_shim_find(tr, bpf_func);
if (shim_link && !IS_ERR(bpf_link_inc_not_zero(&shim_link->link.link))) {
/* Reusing existing shim attached by the other program. */
- mutex_unlock(&tr->mutex);
+ trampoline_unlock(tr);
bpf_trampoline_put(tr); /* bpf_trampoline_get above */
return 0;
}
@@ -1024,16 +1051,16 @@ int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
shim_link->trampoline = tr;
/* note, we're still holding tr refcnt from above */
- mutex_unlock(&tr->mutex);
+ trampoline_unlock(tr);
return 0;
err:
- mutex_unlock(&tr->mutex);
+ trampoline_unlock(tr);
if (shim_link)
bpf_link_put(&shim_link->link.link);
- /* have to release tr while _not_ holding its mutex */
+ /* have to release tr while _not_ holding pool mutex for trampoline */
bpf_trampoline_put(tr); /* bpf_trampoline_get above */
return err;
@@ -1054,9 +1081,9 @@ void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog)
if (WARN_ON_ONCE(!tr))
return;
- mutex_lock(&tr->mutex);
+ trampoline_lock(tr);
shim_link = cgroup_shim_find(tr, bpf_func);
- mutex_unlock(&tr->mutex);
+ trampoline_unlock(tr);
if (shim_link)
bpf_link_put(&shim_link->link.link);
@@ -1074,14 +1101,14 @@ struct bpf_trampoline *bpf_trampoline_get(u64 key,
if (!tr)
return NULL;
- mutex_lock(&tr->mutex);
+ trampoline_lock(tr);
if (tr->func.addr)
goto out;
memcpy(&tr->func.model, &tgt_info->fmodel, sizeof(tgt_info->fmodel));
tr->func.addr = (void *)tgt_info->tgt_addr;
out:
- mutex_unlock(&tr->mutex);
+ trampoline_unlock(tr);
return tr;
}
@@ -1094,7 +1121,6 @@ void bpf_trampoline_put(struct bpf_trampoline *tr)
mutex_lock(&trampoline_mutex);
if (!refcount_dec_and_test(&tr->refcnt))
goto out;
- WARN_ON_ONCE(mutex_is_locked(&tr->mutex));
for (i = 0; i < BPF_TRAMP_MAX; i++)
if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[i])))
@@ -1380,6 +1406,8 @@ static int __init init_trampolines(void)
INIT_HLIST_HEAD(&trampoline_key_table[i]);
for (i = 0; i < TRAMPOLINE_TABLE_SIZE; i++)
INIT_HLIST_HEAD(&trampoline_ip_table[i]);
+ for (i = 0; i < TRAMPOLINE_LOCKS_TABLE_SIZE; i++)
+ __mutex_init(&trampoline_locks[i].mutex, "trampoline_lock", &trampoline_locks[i].key);
return 0;
}
late_initcall(init_trampolines);
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 03/28] ftrace: Add add_ftrace_hash_entry function
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
Renaming __add_hash_entry to add_ftrace_hash_entry and making it global,
it will be used in following changes outside ftrace.c object.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
include/linux/ftrace.h | 2 ++
kernel/trace/ftrace.c | 9 ++++-----
2 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index dc93dd332b07..b42697084fae 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -415,6 +415,8 @@ struct ftrace_hash *alloc_ftrace_hash(int size_bits);
void free_ftrace_hash(struct ftrace_hash *hash);
struct ftrace_func_entry *add_ftrace_hash_entry_direct(struct ftrace_hash *hash,
unsigned long ip, unsigned long direct);
+void add_ftrace_hash_entry(struct ftrace_hash *hash, struct ftrace_func_entry *entry);
+
unsigned long ftrace_hash_count(struct ftrace_hash *hash);
void ftrace_hash_remove(struct ftrace_hash *hash);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 5119d01ef322..7d57aa6e92e2 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1198,8 +1198,7 @@ ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip)
return __ftrace_lookup_ip(hash, ip);
}
-static void __add_hash_entry(struct ftrace_hash *hash,
- struct ftrace_func_entry *entry)
+void add_ftrace_hash_entry(struct ftrace_hash *hash, struct ftrace_func_entry *entry)
{
struct hlist_head *hhd;
unsigned long key;
@@ -1221,7 +1220,7 @@ add_ftrace_hash_entry_direct(struct ftrace_hash *hash, unsigned long ip, unsigne
entry->ip = ip;
entry->direct = direct;
- __add_hash_entry(hash, entry);
+ add_ftrace_hash_entry(hash, entry);
return entry;
}
@@ -1477,7 +1476,7 @@ static struct ftrace_hash *__move_hash(struct ftrace_hash *src, int size)
hhd = &src->buckets[i];
hlist_for_each_entry_safe(entry, tn, hhd, hlist) {
remove_hash_entry(src, entry);
- __add_hash_entry(new_hash, entry);
+ add_ftrace_hash_entry(new_hash, entry);
}
}
return new_hash;
@@ -5360,7 +5359,7 @@ int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper,
map->entry.ip = ip;
map->data = data;
- __add_hash_entry(&mapper->hash, &map->entry);
+ add_ftrace_hash_entry(&mapper->hash, &map->entry);
return 0;
}
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 02/28] ftrace: Add ftrace_hash_remove function
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
Adding ftrace_hash_remove function that removes all entries
from struct ftrace_hash object without freeing them.
It will be used in following changes where entries are allocated
as part of another structure and are free-ed separately.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
include/linux/ftrace.h | 1 +
kernel/trace/ftrace.c | 19 +++++++++++++++++++
2 files changed, 20 insertions(+)
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 401f8dfd05d3..dc93dd332b07 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -416,6 +416,7 @@ void free_ftrace_hash(struct ftrace_hash *hash);
struct ftrace_func_entry *add_ftrace_hash_entry_direct(struct ftrace_hash *hash,
unsigned long ip, unsigned long direct);
unsigned long ftrace_hash_count(struct ftrace_hash *hash);
+void ftrace_hash_remove(struct ftrace_hash *hash);
/* The hash used to know what functions callbacks trace */
struct ftrace_ops_hash {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 68a071e80f32..5119d01ef322 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1249,6 +1249,25 @@ remove_hash_entry(struct ftrace_hash *hash,
hash->count--;
}
+void ftrace_hash_remove(struct ftrace_hash *hash)
+{
+ struct hlist_head *hhd;
+ struct hlist_node *tn;
+ struct ftrace_func_entry *entry;
+ int size = 1 << hash->size_bits;
+ int i;
+
+ if (!hash || !hash->count)
+ return;
+
+ for (i = 0; i < size; i++) {
+ hhd = &hash->buckets[i];
+ hlist_for_each_entry_safe(entry, tn, hhd, hlist)
+ remove_hash_entry(hash, entry);
+ }
+ FTRACE_WARN_ON(hash->count);
+}
+
static void ftrace_hash_clear(struct ftrace_hash *hash)
{
struct hlist_head *hhd;
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 01/28] ftrace: Add ftrace_hash_count function
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260417192502.194548-1-jolsa@kernel.org>
Adding external ftrace_hash_count function so we could get hash
count outside of ftrace object.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
include/linux/ftrace.h | 1 +
kernel/trace/ftrace.c | 7 ++++++-
2 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index c242fe49af4c..401f8dfd05d3 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -415,6 +415,7 @@ struct ftrace_hash *alloc_ftrace_hash(int size_bits);
void free_ftrace_hash(struct ftrace_hash *hash);
struct ftrace_func_entry *add_ftrace_hash_entry_direct(struct ftrace_hash *hash,
unsigned long ip, unsigned long direct);
+unsigned long ftrace_hash_count(struct ftrace_hash *hash);
/* The hash used to know what functions callbacks trace */
struct ftrace_ops_hash {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 413310912609..68a071e80f32 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -6288,11 +6288,16 @@ int modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
}
EXPORT_SYMBOL_GPL(modify_ftrace_direct);
-static unsigned long hash_count(struct ftrace_hash *hash)
+static inline unsigned long hash_count(struct ftrace_hash *hash)
{
return hash ? hash->count : 0;
}
+unsigned long ftrace_hash_count(struct ftrace_hash *hash)
+{
+ return hash_count(hash);
+}
+
/**
* hash_add - adds two struct ftrace_hash and returns the result
* @a: struct ftrace_hash object
--
2.53.0
^ permalink raw reply related
* [PATCHv5 bpf-next 00/28] bpf: tracing_multi link
From: Jiri Olsa @ 2026-04-17 19:24 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: Hengqi Chen, bpf, linux-trace-kernel, Martin KaFai Lau,
Eduard Zingerman, Song Liu, Yonghong Song, Menglong Dong,
Steven Rostedt
hi,
adding tracing_multi link support that allows fast attachment
of tracing program to many functions.
RFC: https://lore.kernel.org/bpf/20260203093819.2105105-1-jolsa@kernel.org/
v1: https://lore.kernel.org/bpf/20260220100649.628307-1-jolsa@kernel.org/
v2: https://lore.kernel.org/bpf/20260304222141.497203-1-jolsa@kernel.org/
v3: https://lore.kernel.org/bpf/20260316075138.465430-1-jolsa@kernel.org/
v4: https://lore.kernel.org/bpf/20260324081846.2334094-1-jolsa@kernel.org/
v5 changes:
- add dedicated hashes used for detach, so there's no need to allocate
them on detach [sashiko]
- safely release old trampoline images [sashiko]
- add cond_resched() to couple of loops [sashiko]
- validate attr->link_create.target_fd [sashiko]
- allow only bpf_get_func_ret() for return value retrieval [sashiko]
- do not allow attachment of fexit/fsession_multi for noreturn functions [sashiko]
- fixed double free/close in libbpf btf cleanup, in separate patch [sashiko]
- make btf_type_is_traceable_func closer to btf_distill_func_proto [sashiko]
- add prog->attach_btf_obj_fd check to collect_func_ids_by_glob,
to check we don't load module programs for kernel [sashiko]
- make sure program is loaded in bpf_program__attach_tracing_multi [sashiko]
- several selftests fixes [sashiko]
- add attach_type to fdinfo output [Leon Hwang]
- selftests cleanup fixes [Leon Hwang]
v4 changes:
- unlink rollback fix (added ftrace_hash_count) [bot]
- use const for some bpf_link_create_opts tracing_multi members [bot]
- adding missing comment for lockdep keys [bot]
- selftest error path fixes (leaks) and other assorted test fixes [Leon Hwang]
- several compile fixes wrt CONFIG_BPF_SYSCALL and CONFIG_BPF_JIT [kernel test robot]
- make ftrace_hash_clear global, because it's needed in rollback
v3 changes:
- fix module parsing [Leon Hwang]
- use function traceable check from libbpf [Leon Hwang]
- use ptr_to_u64 and fix/updated few comments [ci]
- display cookies as decimal numbers [ci]
- added link_create.flags check [ci]
- fix error path in bpf_trampoline_multi_detach [ci]
- make fentry/fexit.multi not extendable [ci]
- add missing OPTS_VALID to bpf_program__attach_tracing_multi [ci]
v2 changes:
- allocate data.unreg in bpf_trampoline_multi_attach for rollback path [ci]
and fixed link count setup in rollback path [ci]
- several small assorted fixes [ci]
- added loongarch and powerpc changes for struct bpf_tramp_node change
- added support to attach functions from modules
- added tests for sleepable programs
- added rollback tests
v1 changes:
- added ftrace_hash_count as wrapper for hash_count [Steven]
- added trampoline mutex pool [Andrii]
- reworked 'struct bpf_tramp_node' separatoin [Andrii]
- the 'struct bpf_tramp_node' now holds pointer to bpf_link,
which is similar to what we do for uprobe_multi;
I understand it's not a fundamental change compared to previous
version which used bpf_prog pointer instead, but I don't see better
way of doing this.. I'm happy to discuss this further if there's
better idea
- reworked 'struct bpf_fsession_link' based on bpf_tramp_node
- made btf__find_by_glob_kind function internal helper [Andrii]
- many small assorted fixes [Andrii,CI]
- added session support [Leon Hwang]
- added cookies support
- added more tests
Note I plan to send linkinfo support separately, the patchset is big enough.
thanks,
jirka
Cc: Hengqi Chen <hengqi.chen@gmail.com>
---
Jiri Olsa (28):
ftrace: Add ftrace_hash_count function
ftrace: Add ftrace_hash_remove function
ftrace: Add add_ftrace_hash_entry function
bpf: Use mutex lock pool for bpf trampolines
bpf: Add struct bpf_trampoline_ops object
bpf: Move trampoline image setup into bpf_trampoline_ops callbacks
bpf: Add bpf_trampoline_add/remove_prog functions
bpf: Add struct bpf_tramp_node object
bpf: Factor fsession link to use struct bpf_tramp_node
bpf: Add multi tracing attach types
bpf: Move sleepable verification code to btf_id_allow_sleepable
bpf: Add bpf_trampoline_multi_attach/detach functions
bpf: Add support for tracing multi link
bpf: Add support for tracing_multi link cookies
bpf: Add support for tracing_multi link session
bpf: Add support for tracing_multi link fdinfo
libbpf: Add bpf_object_cleanup_btf function
libbpf: Add bpf_link_create support for tracing_multi link
libbpf: Add btf_type_is_traceable_func function
libbpf: Add support to create tracing multi link
selftests/bpf: Add tracing multi skel/pattern/ids attach tests
selftests/bpf: Add tracing multi skel/pattern/ids module attach tests
selftests/bpf: Add tracing multi intersect tests
selftests/bpf: Add tracing multi cookies test
selftests/bpf: Add tracing multi session test
selftests/bpf: Add tracing multi attach fails test
selftests/bpf: Add tracing multi attach benchmark test
selftests/bpf: Add tracing multi attach rollback tests
arch/arm64/net/bpf_jit_comp.c | 58 +++---
arch/loongarch/net/bpf_jit.c | 44 ++--
arch/powerpc/net/bpf_jit_comp.c | 50 ++---
arch/riscv/net/bpf_jit_comp64.c | 52 ++---
arch/s390/net/bpf_jit_comp.c | 44 ++--
arch/x86/net/bpf_jit_comp.c | 54 ++---
include/linux/bpf.h | 117 ++++++++---
include/linux/bpf_types.h | 1 +
include/linux/bpf_verifier.h | 4 +
include/linux/btf_ids.h | 1 +
include/linux/ftrace.h | 4 +
include/linux/trace_events.h | 6 +
include/uapi/linux/bpf.h | 9 +
kernel/bpf/bpf_struct_ops.c | 27 +--
kernel/bpf/btf.c | 3 +
kernel/bpf/fixups.c | 2 +
kernel/bpf/syscall.c | 88 +++++---
kernel/bpf/trampoline.c | 668 ++++++++++++++++++++++++++++++++++++++++++++++--------------
kernel/bpf/verifier.c | 176 +++++++++++++---
kernel/trace/bpf_trace.c | 153 +++++++++++++-
kernel/trace/ftrace.c | 35 +++-
net/bpf/bpf_dummy_struct_ops.c | 14 +-
net/bpf/test_run.c | 3 +
tools/include/uapi/linux/bpf.h | 10 +
tools/lib/bpf/bpf.c | 9 +
tools/lib/bpf/bpf.h | 5 +
tools/lib/bpf/libbpf.c | 367 ++++++++++++++++++++++++++++++++-
tools/lib/bpf/libbpf.h | 15 ++
tools/lib/bpf/libbpf.map | 1 +
tools/lib/bpf/libbpf_internal.h | 1 +
tools/testing/selftests/bpf/Makefile | 9 +-
tools/testing/selftests/bpf/prog_tests/tracing_multi.c | 927 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
tools/testing/selftests/bpf/progs/tracing_multi_attach.c | 39 ++++
tools/testing/selftests/bpf/progs/tracing_multi_attach_module.c | 25 +++
tools/testing/selftests/bpf/progs/tracing_multi_bench.c | 12 ++
tools/testing/selftests/bpf/progs/tracing_multi_check.c | 214 ++++++++++++++++++++
tools/testing/selftests/bpf/progs/tracing_multi_fail.c | 18 ++
tools/testing/selftests/bpf/progs/tracing_multi_intersect_attach.c | 41 ++++
tools/testing/selftests/bpf/progs/tracing_multi_rollback.c | 43 ++++
tools/testing/selftests/bpf/progs/tracing_multi_session_attach.c | 47 +++++
tools/testing/selftests/bpf/trace_helpers.c | 6 +-
tools/testing/selftests/bpf/trace_helpers.h | 1 +
42 files changed, 2980 insertions(+), 423 deletions(-)
create mode 100644 tools/testing/selftests/bpf/prog_tests/tracing_multi.c
create mode 100644 tools/testing/selftests/bpf/progs/tracing_multi_attach.c
create mode 100644 tools/testing/selftests/bpf/progs/tracing_multi_attach_module.c
create mode 100644 tools/testing/selftests/bpf/progs/tracing_multi_bench.c
create mode 100644 tools/testing/selftests/bpf/progs/tracing_multi_check.c
create mode 100644 tools/testing/selftests/bpf/progs/tracing_multi_fail.c
create mode 100644 tools/testing/selftests/bpf/progs/tracing_multi_intersect_attach.c
create mode 100644 tools/testing/selftests/bpf/progs/tracing_multi_rollback.c
create mode 100644 tools/testing/selftests/bpf/progs/tracing_multi_session_attach.c
^ permalink raw reply
* Re: [PATCH v3 2/2] blk-mq: expose tag starvation counts via debugfs
From: Bart Van Assche @ 2026-04-17 18:28 UTC (permalink / raw)
To: Aaron Tomlin, axboe, rostedt, mhiramat, mathieu.desnoyers
Cc: johannes.thumshirn, kch, dlemoal, ritesh.list, loberman, neelx,
sean, mproche, chjohnst, linux-block, linux-kernel,
linux-trace-kernel
In-Reply-To: <20260319221956.332770-3-atomlin@atomlin.com>
On 3/19/26 3:19 PM, Aaron Tomlin wrote:
> To guarantee zero performance overhead for production kernels compiled
> without debugfs, the underlying atomic_t variables and their associated
> increment routines are strictly guarded behind CONFIG_BLK_DEBUG_FS.
> When this configuration is disabled, the tracking logic compiles down
> to a safe no-op.
I don't think that's sufficient. Please use per-cpu counters to minimize
the overhead for kernels in which debugfs is enabled.
Thanks,
Bart.
^ permalink raw reply
* Re: [PATCH v3 0/2] blk-mq: introduce tag starvation observability
From: Aaron Tomlin @ 2026-04-17 18:15 UTC (permalink / raw)
To: axboe, rostedt, mhiramat, mathieu.desnoyers
Cc: johannes.thumshirn, kch, bvanassche, dlemoal, ritesh.list,
loberman, neelx, sean, mproche, chjohnst, nick.lange, linux-block,
linux-kernel, linux-trace-kernel
In-Reply-To: <20260319221956.332770-1-atomlin@atomlin.com>
[-- Attachment #1: Type: text/plain, Size: 1252 bytes --]
On Thu, Mar 19, 2026 at 06:19:54PM -0400, Aaron Tomlin wrote:
> In high-performance storage environments, particularly when utilising RAID
> controllers with shared tag sets (BLK_MQ_F_TAG_HCTX_SHARED), severe latency
> spikes can occur when fast devices are starved of available tags.
> Currently, diagnosing this specific queue contention requires deploying
> dynamic kprobes or inferring sleep states, which lacks a simple,
> out-of-the-box diagnostic path.
>
> This short series introduces dedicated, low-overhead observability for tag
> exhaustion events in the block layer:
>
> - Patch 1 introduces the "block_rq_tag_wait" tracepoint in the tag
> allocation slow-path to capture precise, event-based starvation.
>
> - Patch 2 complements this by exposing "wait_on_hw_tag" and
> "wait_on_sched_tag" atomic counters via debugfs for quick,
> point-in-time cumulative polling.
>
> Together, these provide storage engineers with zero-configuration
> mechanisms to definitively identify shared-tag bottlenecks.
Hi Jens, Steve, Masami,
Just a friendly ping on this patch.
Please let me know if there is any feedback, or if you need me to make any
adjustments.
Kind regards,
--
Aaron Tomlin
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply
* [PATCH v9 8/8] selftests/ftrace: Add a testcase for multiple fprobe events
From: Masami Hiramatsu (Google) @ 2026-04-17 16:18 UTC (permalink / raw)
To: Steven Rostedt, Masami Hiramatsu
Cc: Menglong Dong, Mathieu Desnoyers, jiang.biao, linux-kernel,
linux-trace-kernel
In-Reply-To: <177644266147.584467.8179035927318998910.stgit@mhiramat.tok.corp.google.com>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Add a testcase for multiple fprobe events on the same function
so that it clears ftrace hash map correctly when removing the
events.
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
.../test.d/dynevent/add_remove_multiple_fprobe.tc | 69 ++++++++++++++++++++
1 file changed, 69 insertions(+)
create mode 100644 tools/testing/selftests/ftrace/test.d/dynevent/add_remove_multiple_fprobe.tc
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_multiple_fprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_multiple_fprobe.tc
new file mode 100644
index 000000000000..f2cbf2ffd29b
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_multiple_fprobe.tc
@@ -0,0 +1,69 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Generic dynamic event - add/remove multiple fprobe events on the same function
+# requires: dynamic_events "f[:[<group>/][<event>]] <func-name>[%return] [<args>]":README enabled_functions
+
+echo 0 > events/enable
+echo > dynamic_events
+
+PLACE=vfs_read
+PLACE2=vfs_open
+
+:;: 'Ensure no other ftrace user' ;:
+test `cat enabled_functions | wc -l` -eq 0 || exit_unresolved
+
+:;: 'Test case 1: leave entry event' ;:
+:;: 'Add entry and exit events on the same place' ;:
+echo "f:event1 ${PLACE}" >> dynamic_events
+echo "f:event2 ${PLACE}%return" >> dynamic_events
+
+:;: 'Enable both of them' ;:
+echo 1 > events/fprobes/enable
+test `cat enabled_functions | wc -l` -eq 1
+
+:;: 'Disable and remove exit event' ;:
+echo 0 > events/fprobes/event2/enable
+echo -:event2 >> dynamic_events
+
+:;: 'Disable and remove all events' ;:
+echo 0 > events/fprobes/enable
+echo > dynamic_events
+
+:;: 'Add another event' ;:
+echo "f:event3 ${PLACE2}%return" > dynamic_events
+echo 1 > events/fprobes/enable
+test `cat enabled_functions | wc -l` -eq 1
+
+:;: 'No other ftrace user' ;:
+echo 0 > events/fprobes/enable
+echo > dynamic_events
+test `cat enabled_functions | wc -l` -eq 0
+
+:;: 'Test case 2: leave exit event' ;:
+:;: 'Add entry and exit events on the same place' ;:
+echo "f:event1 ${PLACE}" >> dynamic_events
+echo "f:event2 ${PLACE}%return" >> dynamic_events
+
+:;: 'Enable both of them' ;:
+echo 1 > events/fprobes/enable
+test `cat enabled_functions | wc -l` -eq 1
+
+:;: 'Disable and remove entry event' ;:
+echo 0 > events/fprobes/event1/enable
+echo -:event1 >> dynamic_events
+
+:;: 'Disable and remove all events' ;:
+echo 0 > events/fprobes/enable
+echo > dynamic_events
+
+:;: 'Add another event' ;:
+echo "f:event3 ${PLACE2}" > dynamic_events
+echo 1 > events/fprobes/enable
+test `cat enabled_functions | wc -l` -eq 1
+
+:;: 'No other ftrace user' ;:
+echo 0 > events/fprobes/enable
+echo > dynamic_events
+test `cat enabled_functions | wc -l` -eq 0
+
+clear_trace
^ permalink raw reply related
* [PATCH v9 7/8] selftests/ftrace: Add a testcase for fprobe events on module
From: Masami Hiramatsu (Google) @ 2026-04-17 16:18 UTC (permalink / raw)
To: Steven Rostedt, Masami Hiramatsu
Cc: Menglong Dong, Mathieu Desnoyers, jiang.biao, linux-kernel,
linux-trace-kernel
In-Reply-To: <177644266147.584467.8179035927318998910.stgit@mhiramat.tok.corp.google.com>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Add a testcase for fprobe events on module, which unloads a kernel
module on which fprobe events are probing and ensure the ftrace
hash map is cleared correctly.
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v9:
- Use "trace-events-sample" instead of "trace_events_sample"
- Add checking unload module and remove core-kernel event case.
- Check test module exists when unloading it in EXIT.
Changes in v8:
- Newly added.
---
.../test.d/dynevent/add_remove_fprobe_module.tc | 87 ++++++++++++++++++++
1 file changed, 87 insertions(+)
create mode 100644 tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_module.tc
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_module.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_module.tc
new file mode 100644
index 000000000000..c358c5071f15
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_module.tc
@@ -0,0 +1,87 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Generic dynamic event - add/remove fprobe events on module
+# requires: dynamic_events "f[:[<group>/][<event>]] <func-name>[%return] [<args>]":README enabled_functions
+
+rmmod trace-events-sample ||:
+if ! modprobe trace-events-sample ; then
+ echo "No trace-events sample module - please make CONFIG_SAMPLE_TRACE_EVENTS=m"
+ exit_unresolved;
+fi
+trap "lsmod | grep -q trace-event-sample && rmmod trace-events-sample" EXIT
+
+echo 0 > events/enable
+echo > dynamic_events
+
+FUNC1='foo_bar*'
+FUNC2='vfs_read'
+
+:;: "Add an event on the test module" ;:
+echo "f:test1 $FUNC1" >> dynamic_events
+echo 1 > events/fprobes/test1/enable
+
+:;: "Ensure it is enabled" ;:
+funcs=`cat enabled_functions | wc -l`
+test $funcs -ne 0
+
+:;: "Check the enabled_functions is cleared on unloading" ;:
+rmmod trace-events-sample
+funcs=`cat enabled_functions | wc -l`
+test $funcs -eq 0
+
+:;: "Check it is kept clean" ;:
+modprobe trace-events-sample
+echo 1 > events/fprobes/test1/enable || echo "OK"
+funcs=`cat enabled_functions | wc -l`
+test $funcs -eq 0
+
+:;: "Add another event not on the test module" ;:
+echo "f:test2 $FUNC2" >> dynamic_events
+echo 1 > events/fprobes/test2/enable
+
+:;: "Ensure it is enabled" ;:
+ofuncs=`cat enabled_functions | wc -l`
+test $ofuncs -ne 0
+
+:;: "Disable and remove the first event"
+echo 0 > events/fprobes/test1/enable
+echo "-:fprobes/test1" >> dynamic_events
+funcs=`cat enabled_functions | wc -l`
+test $ofuncs -eq $funcs
+
+:;: "Disable and remove other events" ;:
+echo 0 > events/fprobes/enable
+echo > dynamic_events
+funcs=`cat enabled_functions | wc -l`
+test $funcs -eq 0
+
+rmmod trace-events-sample
+
+:;: "Add events on kernel and test module" ;:
+modprobe trace-events-sample
+echo "f:test1 $FUNC1" >> dynamic_events
+echo 1 > events/fprobes/test1/enable
+echo "f:test2 $FUNC2" >> dynamic_events
+echo 1 > events/fprobes/test2/enable
+ofuncs=`cat enabled_functions | wc -l`
+test $ofuncs -ne 0
+
+:;: "Unload module (ftrace entry should be removed)" ;:
+rmmod trace-events-sample
+funcs=`cat enabled_functions | wc -l`
+test $funcs -ne 0
+test $ofuncs -ne $funcs
+
+:;: "Disable and remove core-kernel fprobe event" ;:
+echo 0 > events/fprobes/test2/enable
+echo "-:fprobes/test2" >> dynamic_events
+
+:;: "Ensure ftrace is disabled." ;:
+funcs=`cat enabled_functions | wc -l`
+test $funcs -eq 0
+
+echo 0 > events/fprobes/enable
+echo > dynamic_events
+
+trap "" EXIT
+clear_trace
^ permalink raw reply related
* [PATCH v9 6/8] tracing/fprobe: Fix to unregister ftrace_ops if it is empty on module unloading
From: Masami Hiramatsu (Google) @ 2026-04-17 16:18 UTC (permalink / raw)
To: Steven Rostedt, Masami Hiramatsu
Cc: Menglong Dong, Mathieu Desnoyers, jiang.biao, linux-kernel,
linux-trace-kernel
In-Reply-To: <177644266147.584467.8179035927318998910.stgit@mhiramat.tok.corp.google.com>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Fix fprobe to unregister ftrace_ops if corresponding type of fprobe
does not exist on the fprobe_ip_table and it is expected to be empty
when unloading modules.
Since ftrace thinks that the empty hash means everything to be traced,
if we set fprobes only on the unloaded module, all functions are traced
unexpectedly after unloading module.
e.g.
# modprobe xt_LOG.ko
# echo 'f:test log_tg*' > dynamic_events
# echo 1 > events/fprobes/test/enable
# cat enabled_functions
log_tg [xt_LOG] (1) tramp: 0xffffffffa0004000 (fprobe_ftrace_entry+0x0/0x490) ->fprobe_ftrace_entry+0x0/0x490
log_tg_check [xt_LOG] (1) tramp: 0xffffffffa0004000 (fprobe_ftrace_entry+0x0/0x490) ->fprobe_ftrace_entry+0x0/0x490
log_tg_destroy [xt_LOG] (1) tramp: 0xffffffffa0004000 (fprobe_ftrace_entry+0x0/0x490) ->fprobe_ftrace_entry+0x0/0x490
# rmmod xt_LOG
# wc -l enabled_functions
34085 enabled_functions
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v9:
- Remove fprobe_graph_active and fprobe_ftrace_active to fix
remove fprobe after unload module case.
Changes in v8:
- Fix to check fprobe_graph/ftrace_registered flag directly
when registering ftrace_ops.
Changes in v7:
- Fix to split checking whether ftrace_ops is registered from
the number of registered fprobes, because ftrace_ops can be
unregistered in module unloading.
Changes in v6:
- Newly added.
---
kernel/trace/fprobe.c | 206 ++++++++++++++++++++++++++++++++++++-------------
1 file changed, 151 insertions(+), 55 deletions(-)
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index e3b5cc76151e..6a392936238a 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -79,7 +79,7 @@ static const struct rhashtable_params fprobe_rht_params = {
};
/* Node insertion and deletion requires the fprobe_mutex */
-static int insert_fprobe_node(struct fprobe_hlist_node *node, struct fprobe *fp)
+static int __insert_fprobe_node(struct fprobe_hlist_node *node, struct fprobe *fp)
{
int ret;
@@ -92,7 +92,7 @@ static int insert_fprobe_node(struct fprobe_hlist_node *node, struct fprobe *fp)
return ret;
}
-static void delete_fprobe_node(struct fprobe_hlist_node *node)
+static void __delete_fprobe_node(struct fprobe_hlist_node *node)
{
lockdep_assert_held(&fprobe_mutex);
@@ -250,7 +250,65 @@ static inline int __fprobe_kprobe_handler(unsigned long ip, unsigned long parent
return ret;
}
+static int fprobe_fgraph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops,
+ struct ftrace_regs *fregs);
+static void fprobe_return(struct ftrace_graph_ret *trace,
+ struct fgraph_ops *gops,
+ struct ftrace_regs *fregs);
+
+static struct fgraph_ops fprobe_graph_ops = {
+ .entryfunc = fprobe_fgraph_entry,
+ .retfunc = fprobe_return,
+};
+/* Number of fgraph fprobe nodes */
+static int nr_fgraph_fprobes;
+/* Is fprobe_graph_ops registered? */
+static bool fprobe_graph_registered;
+
+/* Add @addrs to the ftrace filter and register fgraph if needed. */
+static int fprobe_graph_add_ips(unsigned long *addrs, int num)
+{
+ int ret;
+
+ lockdep_assert_held(&fprobe_mutex);
+
+ ret = ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 0, 0);
+ if (ret)
+ return ret;
+
+ if (!fprobe_graph_registered) {
+ ret = register_ftrace_graph(&fprobe_graph_ops);
+ if (WARN_ON_ONCE(ret)) {
+ ftrace_free_filter(&fprobe_graph_ops.ops);
+ return ret;
+ }
+ fprobe_graph_registered = true;
+ }
+ return 0;
+}
+
+static void __fprobe_graph_unregister(void)
+{
+ if (fprobe_graph_registered) {
+ unregister_ftrace_graph(&fprobe_graph_ops);
+ ftrace_free_filter(&fprobe_graph_ops.ops);
+ fprobe_graph_registered = false;
+ }
+}
+
+/* Remove @addrs from the ftrace filter and unregister fgraph if possible. */
+static void fprobe_graph_remove_ips(unsigned long *addrs, int num)
+{
+ lockdep_assert_held(&fprobe_mutex);
+
+ if (!nr_fgraph_fprobes)
+ __fprobe_graph_unregister();
+ else if (num)
+ ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0);
+}
+
#if defined(CONFIG_DYNAMIC_FTRACE_WITH_ARGS) || defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS)
+
/* ftrace_ops callback, this processes fprobes which have only entry_handler. */
static void fprobe_ftrace_entry(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *ops, struct ftrace_regs *fregs)
@@ -293,7 +351,10 @@ static struct ftrace_ops fprobe_ftrace_ops = {
.func = fprobe_ftrace_entry,
.flags = FTRACE_OPS_FL_SAVE_ARGS,
};
-static int fprobe_ftrace_active;
+/* Number of ftrace fprobe nodes */
+static int nr_ftrace_fprobes;
+/* Is fprobe_ftrace_ops registered? */
+static bool fprobe_ftrace_registered;
static int fprobe_ftrace_add_ips(unsigned long *addrs, int num)
{
@@ -305,26 +366,33 @@ static int fprobe_ftrace_add_ips(unsigned long *addrs, int num)
if (ret)
return ret;
- if (!fprobe_ftrace_active) {
+ if (!fprobe_ftrace_registered) {
ret = register_ftrace_function(&fprobe_ftrace_ops);
if (ret) {
ftrace_free_filter(&fprobe_ftrace_ops);
return ret;
}
+ fprobe_ftrace_registered = true;
}
- fprobe_ftrace_active++;
return 0;
}
+static void __fprobe_ftrace_unregister(void)
+{
+ if (fprobe_ftrace_registered) {
+ unregister_ftrace_function(&fprobe_ftrace_ops);
+ ftrace_free_filter(&fprobe_ftrace_ops);
+ fprobe_ftrace_registered = false;
+ }
+}
+
static void fprobe_ftrace_remove_ips(unsigned long *addrs, int num)
{
lockdep_assert_held(&fprobe_mutex);
- fprobe_ftrace_active--;
- if (!fprobe_ftrace_active) {
- unregister_ftrace_function(&fprobe_ftrace_ops);
- ftrace_free_filter(&fprobe_ftrace_ops);
- } else if (num)
+ if (!nr_ftrace_fprobes)
+ __fprobe_ftrace_unregister();
+ else if (num)
ftrace_set_filter_ips(&fprobe_ftrace_ops, addrs, num, 1, 0);
}
@@ -333,6 +401,40 @@ static bool fprobe_is_ftrace(struct fprobe *fp)
return !fp->exit_handler;
}
+/* Node insertion and deletion requires the fprobe_mutex */
+static int insert_fprobe_node(struct fprobe_hlist_node *node, struct fprobe *fp)
+{
+ int ret;
+
+ lockdep_assert_held(&fprobe_mutex);
+
+ ret = __insert_fprobe_node(node, fp);
+ if (!ret) {
+ if (fprobe_is_ftrace(fp))
+ nr_ftrace_fprobes++;
+ else
+ nr_fgraph_fprobes++;
+ }
+
+ return ret;
+}
+
+static void delete_fprobe_node(struct fprobe_hlist_node *node)
+{
+ struct fprobe *fp;
+
+ lockdep_assert_held(&fprobe_mutex);
+
+ fp = READ_ONCE(node->fp);
+ if (fp) {
+ if (fprobe_is_ftrace(fp))
+ nr_ftrace_fprobes--;
+ else
+ nr_fgraph_fprobes--;
+ }
+ __delete_fprobe_node(node);
+}
+
static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace)
{
struct rhlist_head *head, *pos;
@@ -362,8 +464,15 @@ static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace)
#ifdef CONFIG_MODULES
static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt)
{
- ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, 1, 0);
- ftrace_set_filter_ips(&fprobe_ftrace_ops, ips, cnt, 1, 0);
+ if (!nr_fgraph_fprobes)
+ __fprobe_graph_unregister();
+ else
+ ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, 1, 0);
+
+ if (!nr_ftrace_fprobes)
+ __fprobe_ftrace_unregister();
+ else
+ ftrace_set_filter_ips(&fprobe_ftrace_ops, ips, cnt, 1, 0);
}
#endif
#else
@@ -381,6 +490,32 @@ static bool fprobe_is_ftrace(struct fprobe *fp)
return false;
}
+/* Node insertion and deletion requires the fprobe_mutex */
+static int insert_fprobe_node(struct fprobe_hlist_node *node, struct fprobe *fp)
+{
+ int ret;
+
+ lockdep_assert_held(&fprobe_mutex);
+
+ ret = __insert_fprobe_node(node, fp);
+ if (!ret)
+ nr_fgraph_fprobes++;
+
+ return ret;
+}
+
+static void delete_fprobe_node(struct fprobe_hlist_node *node)
+{
+ struct fprobe *fp;
+
+ lockdep_assert_held(&fprobe_mutex);
+
+ fp = READ_ONCE(node->fp);
+ if (fp)
+ nr_fgraph_fprobes--;
+ __delete_fprobe_node(node);
+}
+
static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace __maybe_unused)
{
struct rhlist_head *head, *pos;
@@ -407,7 +542,10 @@ static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace __maybe_unused)
#ifdef CONFIG_MODULES
static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt)
{
- ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, 1, 0);
+ if (!nr_fgraph_fprobes)
+ __fprobe_graph_unregister();
+ else
+ ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, 1, 0);
}
#endif
#endif /* !CONFIG_DYNAMIC_FTRACE_WITH_ARGS && !CONFIG_DYNAMIC_FTRACE_WITH_REGS */
@@ -535,48 +673,6 @@ static void fprobe_return(struct ftrace_graph_ret *trace,
}
NOKPROBE_SYMBOL(fprobe_return);
-static struct fgraph_ops fprobe_graph_ops = {
- .entryfunc = fprobe_fgraph_entry,
- .retfunc = fprobe_return,
-};
-static int fprobe_graph_active;
-
-/* Add @addrs to the ftrace filter and register fgraph if needed. */
-static int fprobe_graph_add_ips(unsigned long *addrs, int num)
-{
- int ret;
-
- lockdep_assert_held(&fprobe_mutex);
-
- ret = ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 0, 0);
- if (ret)
- return ret;
-
- if (!fprobe_graph_active) {
- ret = register_ftrace_graph(&fprobe_graph_ops);
- if (WARN_ON_ONCE(ret)) {
- ftrace_free_filter(&fprobe_graph_ops.ops);
- return ret;
- }
- }
- fprobe_graph_active++;
- return 0;
-}
-
-/* Remove @addrs from the ftrace filter and unregister fgraph if possible. */
-static void fprobe_graph_remove_ips(unsigned long *addrs, int num)
-{
- lockdep_assert_held(&fprobe_mutex);
-
- fprobe_graph_active--;
- /* Q: should we unregister it ? */
- if (!fprobe_graph_active) {
- unregister_ftrace_graph(&fprobe_graph_ops);
- ftrace_free_filter(&fprobe_graph_ops.ops);
- } else if (num)
- ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0);
-}
-
#ifdef CONFIG_MODULES
#define FPROBE_IPS_BATCH_INIT 128
^ permalink raw reply related
* [PATCH v9 5/8] tracing/fprobe: Check the same type fprobe on table as the unregistered one
From: Masami Hiramatsu (Google) @ 2026-04-17 16:18 UTC (permalink / raw)
To: Steven Rostedt, Masami Hiramatsu
Cc: Menglong Dong, Mathieu Desnoyers, jiang.biao, linux-kernel,
linux-trace-kernel
In-Reply-To: <177644266147.584467.8179035927318998910.stgit@mhiramat.tok.corp.google.com>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Commit 2c67dc457bc6 ("tracing: fprobe: optimization for entry only case")
introduced a different ftrace_ops for entry-only fprobes.
However, when unregistering an fprobe, the kernel only checks if another
fprobe exists at the same address, without checking which type of fprobe
it is.
If different fprobes are registered at the same address, the same address
will be registered in both fgraph_ops and ftrace_ops, but only one of
them will be deleted when unregistering. (the one removed first will not
be deleted from the ops).
This results in junk entries remaining in either fgraph_ops or ftrace_ops.
For example:
=======
cd /sys/kernel/tracing
# 'Add entry and exit events on the same place'
echo 'f:event1 vfs_read' >> dynamic_events
echo 'f:event2 vfs_read%return' >> dynamic_events
# 'Enable both of them'
echo 1 > events/fprobes/enable
cat enabled_functions
vfs_read (2) ->arch_ftrace_ops_list_func+0x0/0x210
# 'Disable and remove exit event'
echo 0 > events/fprobes/event2/enable
echo -:event2 >> dynamic_events
# 'Disable and remove all events'
echo 0 > events/fprobes/enable
echo > dynamic_events
# 'Add another event'
echo 'f:event3 vfs_open%return' > dynamic_events
cat dynamic_events
f:fprobes/event3 vfs_open%return
echo 1 > events/fprobes/enable
cat enabled_functions
vfs_open (1) tramp: 0xffffffffa0001000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 subops: {ent:fprobe_fgraph_entry+0x0/0x620 ret:fprobe_return+0x0/0x150}
vfs_read (1) tramp: 0xffffffffa0001000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 subops: {ent:fprobe_fgraph_entry+0x0/0x620 ret:fprobe_return+0x0/0x150}
=======
As you can see, an entry for the vfs_read remains.
To fix this issue, when unregistering, the kernel should also check if
there is the same type of fprobes still exist at the same address, and
if not, delete its entry from either fgraph_ops or ftrace_ops.
Fixes: 2c67dc457bc6 ("tracing: fprobe: optimization for entry only case")
Cc: stable@vger.kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
kernel/trace/fprobe.c | 82 +++++++++++++++++++++++++++++++++++++++----------
1 file changed, 65 insertions(+), 17 deletions(-)
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 49016c3e7cd9..e3b5cc76151e 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -92,11 +92,8 @@ static int insert_fprobe_node(struct fprobe_hlist_node *node, struct fprobe *fp)
return ret;
}
-/* Return true if there are synonims */
-static bool delete_fprobe_node(struct fprobe_hlist_node *node)
+static void delete_fprobe_node(struct fprobe_hlist_node *node)
{
- bool ret;
-
lockdep_assert_held(&fprobe_mutex);
/* Avoid double deleting and non-inserted nodes */
@@ -105,13 +102,6 @@ static bool delete_fprobe_node(struct fprobe_hlist_node *node)
rhltable_remove(&fprobe_ip_table, &node->hlist,
fprobe_rht_params);
}
-
- rcu_read_lock();
- ret = !!rhltable_lookup(&fprobe_ip_table, &node->addr,
- fprobe_rht_params);
- rcu_read_unlock();
-
- return ret;
}
/* Check existence of the fprobe */
@@ -343,6 +333,32 @@ static bool fprobe_is_ftrace(struct fprobe *fp)
return !fp->exit_handler;
}
+static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace)
+{
+ struct rhlist_head *head, *pos;
+ struct fprobe_hlist_node *node;
+ struct fprobe *fp;
+
+ guard(rcu)();
+ head = rhltable_lookup(&fprobe_ip_table, &ip,
+ fprobe_rht_params);
+ if (!head)
+ return false;
+ /* We have to check the same type on the list. */
+ rhl_for_each_entry_rcu(node, pos, head, hlist) {
+ if (node->addr != ip)
+ break;
+ fp = READ_ONCE(node->fp);
+ if (likely(fp)) {
+ if ((!ftrace && fp->exit_handler) ||
+ (ftrace && !fp->exit_handler))
+ return true;
+ }
+ }
+
+ return false;
+}
+
#ifdef CONFIG_MODULES
static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt)
{
@@ -365,6 +381,29 @@ static bool fprobe_is_ftrace(struct fprobe *fp)
return false;
}
+static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace __maybe_unused)
+{
+ struct rhlist_head *head, *pos;
+ struct fprobe_hlist_node *node;
+ struct fprobe *fp;
+
+ guard(rcu)();
+ head = rhltable_lookup(&fprobe_ip_table, &ip,
+ fprobe_rht_params);
+ if (!head)
+ return false;
+ /* We only need to check fp is there. */
+ rhl_for_each_entry_rcu(node, pos, head, hlist) {
+ if (node->addr != ip)
+ break;
+ fp = READ_ONCE(node->fp);
+ if (likely(fp))
+ return true;
+ }
+
+ return false;
+}
+
#ifdef CONFIG_MODULES
static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt)
{
@@ -551,18 +590,25 @@ struct fprobe_addr_list {
static int fprobe_remove_node_in_module(struct module *mod, struct fprobe_hlist_node *node,
struct fprobe_addr_list *alist)
{
+ lockdep_assert_in_rcu_read_lock();
+
if (!within_module(node->addr, mod))
return 0;
- if (delete_fprobe_node(node))
- return 0;
+ delete_fprobe_node(node);
/* If no address list is available, we can't track this address. */
if (!alist->addrs)
return 0;
+ /*
+ * Don't care the type here, because all fprobes on the same
+ * address must be removed eventually.
+ */
+ if (!rhltable_lookup(&fprobe_ip_table, &node->addr, fprobe_rht_params)) {
+ alist->addrs[alist->index++] = node->addr;
+ if (alist->index == alist->size)
+ return -ENOSPC;
+ }
- alist->addrs[alist->index++] = node->addr;
- if (alist->index == alist->size)
- return -ENOSPC;
return 0;
}
@@ -930,7 +976,9 @@ static int unregister_fprobe_nolock(struct fprobe *fp)
/* Remove non-synonim ips from table and hash */
count = 0;
for (i = 0; i < hlist_array->size; i++) {
- if (!delete_fprobe_node(&hlist_array->array[i]) && addrs)
+ delete_fprobe_node(&hlist_array->array[i]);
+ if (addrs && !fprobe_exists_on_hash(hlist_array->array[i].addr,
+ fprobe_is_ftrace(fp)))
addrs[count++] = hlist_array->array[i].addr;
}
del_fprobe_hash(fp);
^ permalink raw reply related
* [PATCH v9 4/8] tracing/fprobe: Avoid kcalloc() in rcu_read_lock section
From: Masami Hiramatsu (Google) @ 2026-04-17 16:18 UTC (permalink / raw)
To: Steven Rostedt, Masami Hiramatsu
Cc: Menglong Dong, Mathieu Desnoyers, jiang.biao, linux-kernel,
linux-trace-kernel
In-Reply-To: <177644266147.584467.8179035927318998910.stgit@mhiramat.tok.corp.google.com>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
fprobe_remove_node_in_module() is called under RCU read locked, but
this invokes kcalloc() if there are more than 8 fprobes installed
on the module. Sashiko warns it because kcalloc() can sleep [1].
[1] https://sashiko.dev/#/patchset/177552432201.853249.5125045538812833325.stgit%40mhiramat.tok.corp.google.com
To fix this issue, expand the batch size to 128 and do not expand
the fprobe_addr_list, but just cancel walking on fprobe_ip_table,
update fgraph/ftrace_ops and retry the loop again.
Fixes: 0de4c70d04a4 ("tracing: fprobe: use rhltable for fprobe_ip_table")
Cc: stable@vger.kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v6:
- Retry outside rhltable_walk_enter/exit() again.
Changes in v5:
- Skip updating ftrace_ops when fails to allocate memory in module
unloading.
Changes in v4:
- fix a build error typo in case of CONFIG_DYNAMIC_FTRACE=n.
Changes in v3:
- Retry inside rhltable_walk_enter/exit().
- Rename fprobe_set_ips() to fprobe_remove_ips().
- Rename 'retry' label to 'again'.
---
kernel/trace/fprobe.c | 92 ++++++++++++++++++++++++-------------------------
1 file changed, 45 insertions(+), 47 deletions(-)
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 2e232342cbd4..49016c3e7cd9 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -344,11 +344,10 @@ static bool fprobe_is_ftrace(struct fprobe *fp)
}
#ifdef CONFIG_MODULES
-static void fprobe_set_ips(unsigned long *ips, unsigned int cnt, int remove,
- int reset)
+static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt)
{
- ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, remove, reset);
- ftrace_set_filter_ips(&fprobe_ftrace_ops, ips, cnt, remove, reset);
+ ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, 1, 0);
+ ftrace_set_filter_ips(&fprobe_ftrace_ops, ips, cnt, 1, 0);
}
#endif
#else
@@ -367,10 +366,9 @@ static bool fprobe_is_ftrace(struct fprobe *fp)
}
#ifdef CONFIG_MODULES
-static void fprobe_set_ips(unsigned long *ips, unsigned int cnt, int remove,
- int reset)
+static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt)
{
- ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, remove, reset);
+ ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, 1, 0);
}
#endif
#endif /* !CONFIG_DYNAMIC_FTRACE_WITH_ARGS && !CONFIG_DYNAMIC_FTRACE_WITH_REGS */
@@ -542,7 +540,7 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num)
#ifdef CONFIG_MODULES
-#define FPROBE_IPS_BATCH_INIT 8
+#define FPROBE_IPS_BATCH_INIT 128
/* instruction pointer address list */
struct fprobe_addr_list {
int index;
@@ -550,45 +548,24 @@ struct fprobe_addr_list {
unsigned long *addrs;
};
-static int fprobe_addr_list_add(struct fprobe_addr_list *alist, unsigned long addr)
+static int fprobe_remove_node_in_module(struct module *mod, struct fprobe_hlist_node *node,
+ struct fprobe_addr_list *alist)
{
- unsigned long *addrs;
-
- /* Previously we failed to expand the list. */
- if (alist->index == alist->size)
- return -ENOSPC;
-
- alist->addrs[alist->index++] = addr;
- if (alist->index < alist->size)
+ if (!within_module(node->addr, mod))
return 0;
- /* Expand the address list */
- addrs = kcalloc(alist->size * 2, sizeof(*addrs), GFP_KERNEL);
- if (!addrs)
- return -ENOMEM;
-
- memcpy(addrs, alist->addrs, alist->size * sizeof(*addrs));
- alist->size *= 2;
- kfree(alist->addrs);
- alist->addrs = addrs;
+ if (delete_fprobe_node(node))
+ return 0;
+ /* If no address list is available, we can't track this address. */
+ if (!alist->addrs)
+ return 0;
+ alist->addrs[alist->index++] = node->addr;
+ if (alist->index == alist->size)
+ return -ENOSPC;
return 0;
}
-static void fprobe_remove_node_in_module(struct module *mod, struct fprobe_hlist_node *node,
- struct fprobe_addr_list *alist)
-{
- if (!within_module(node->addr, mod))
- return;
- if (delete_fprobe_node(node))
- return;
- /*
- * If failed to update alist, just continue to update hlist.
- * Therefore, at list user handler will not hit anymore.
- */
- fprobe_addr_list_add(alist, node->addr);
-}
-
/* Handle module unloading to manage fprobe_ip_table. */
static int fprobe_module_callback(struct notifier_block *nb,
unsigned long val, void *data)
@@ -597,29 +574,50 @@ static int fprobe_module_callback(struct notifier_block *nb,
struct fprobe_hlist_node *node;
struct rhashtable_iter iter;
struct module *mod = data;
+ bool retry;
if (val != MODULE_STATE_GOING)
return NOTIFY_DONE;
alist.addrs = kcalloc(alist.size, sizeof(*alist.addrs), GFP_KERNEL);
- /* If failed to alloc memory, we can not remove ips from hash. */
- if (!alist.addrs)
- return NOTIFY_DONE;
+ /*
+ * If failed to alloc memory, ftrace_ops will not be able to remove ips from
+ * hash, but we can still remove nodes from fprobe_ip_table, so we can avoid
+ * the potential wrong callback. So just print a warning here and try to
+ * continue without address list.
+ */
+ WARN_ONCE(!alist.addrs,
+ "Failed to allocate memory for fprobe_addr_list, ftrace_ops will not be updated");
mutex_lock(&fprobe_mutex);
+again:
+ retry = false;
+ alist.index = 0;
rhltable_walk_enter(&fprobe_ip_table, &iter);
do {
rhashtable_walk_start(&iter);
while ((node = rhashtable_walk_next(&iter)) && !IS_ERR(node))
- fprobe_remove_node_in_module(mod, node, &alist);
+ if (fprobe_remove_node_in_module(mod, node, &alist) < 0) {
+ retry = true;
+ break;
+ }
rhashtable_walk_stop(&iter);
- } while (node == ERR_PTR(-EAGAIN));
+ } while (node == ERR_PTR(-EAGAIN) && !retry);
rhashtable_walk_exit(&iter);
+ /* Remove any ips from hash table(s) */
+ if (alist.index > 0) {
+ fprobe_remove_ips(alist.addrs, alist.index);
+ /*
+ * If we break rhashtable walk loop except for -EAGAIN, we need
+ * to restart looping from start for safety. Anyway, this is
+ * not a hotpath.
+ */
+ if (retry)
+ goto again;
+ }
- if (alist.index > 0)
- fprobe_set_ips(alist.addrs, alist.index, 1, 0);
mutex_unlock(&fprobe_mutex);
kfree(alist.addrs);
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox