Introduce a path iterator, which reliably walk a struct path.
Current version only support walking towards the root, which helper
path_parent. But the path iterator API can be extended to cover other
use cases, for example, walking the mount tree.
Signed-off-by: Song Liu <song@xxxxxxxxxx>
---
kernel/bpf/Makefile | 1 +
kernel/bpf/helpers.c | 3 ++
kernel/bpf/path_iter.c | 74 ++++++++++++++++++++++++++++++++++++++++++
kernel/bpf/verifier.c | 5 +++
4 files changed, 83 insertions(+)
create mode 100644 kernel/bpf/path_iter.c
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 70502f038b92..8075a83d5e08 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -53,6 +53,7 @@ obj-$(CONFIG_BPF_SYSCALL) += relo_core.o
obj-$(CONFIG_BPF_SYSCALL) += btf_iter.o
obj-$(CONFIG_BPF_SYSCALL) += btf_relocate.o
obj-$(CONFIG_BPF_SYSCALL) += kmem_cache_iter.o
+obj-$(CONFIG_BPF_SYSCALL) += path_iter.o
CFLAGS_REMOVE_percpu_freelist.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_bpf_lru_list.o = $(CC_FLAGS_FTRACE)
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index c1113b74e1e2..d77b055092e7 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -3386,6 +3386,9 @@ BTF_ID_FLAGS(func, bpf_copy_from_user_dynptr, KF_SLEEPABLE)
BTF_ID_FLAGS(func, bpf_copy_from_user_str_dynptr, KF_SLEEPABLE)
BTF_ID_FLAGS(func, bpf_copy_from_user_task_dynptr, KF_SLEEPABLE | KF_TRUSTED_ARGS)
BTF_ID_FLAGS(func, bpf_copy_from_user_task_str_dynptr, KF_SLEEPABLE | KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_iter_path_new, KF_ITER_NEW | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_iter_path_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_iter_path_destroy, KF_ITER_DESTROY | KF_SLEEPABLE)
BTF_KFUNCS_END(common_btf_ids)
static const struct btf_kfunc_id_set common_kfunc_set = {
diff --git a/kernel/bpf/path_iter.c b/kernel/bpf/path_iter.c
new file mode 100644
index 000000000000..838ebbeac6c2
--- /dev/null
+++ b/kernel/bpf/path_iter.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <linux/bpf.h>
+#include <linux/bpf_mem_alloc.h>
+#include <linux/namei.h>
+#include <linux/path.h>
+
+enum bpf_path_iter_mode {
+ BPF_PATH_ITER_MODE_PARENT = 1,
+};
+
+/* open-coded iterator */
+struct bpf_iter_path {
+ __u64 __opaque[3];
+} __aligned(8);
+
+struct bpf_iter_path_kern {
+ struct path path;
+ enum bpf_path_iter_mode mode;
+} __aligned(8);
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_iter_path_new(struct bpf_iter_path *it,
+ struct path *start,
+ enum bpf_path_iter_mode mode)
+{
+ struct bpf_iter_path_kern *kit = (void *)it;
+
+ BUILD_BUG_ON(sizeof(*kit) > sizeof(*it));
+ BUILD_BUG_ON(__alignof__(*kit) != __alignof__(*it));
+
+ kit->mode = mode;
+
+ switch (mode) {
+ case BPF_PATH_ITER_MODE_PARENT:
+ break;
+ default:
+ memset(&kit->path, 0, sizeof(struct path));
+ return -EINVAL;
+ }
+
+ kit->path = *start;
+ path_get(&kit->path);
+ return 0;
+}
+
+__bpf_kfunc struct path *bpf_iter_path_next(struct bpf_iter_path *it)
+{
+ struct bpf_iter_path_kern *kit = (void *)it;
+
+ switch (kit->mode) {
+ case BPF_PATH_ITER_MODE_PARENT:
+ enum path_parent_status status = path_parent(&kit->path);
+
+ /* If already at a root, return NULL */
+ if (status == PATH_PARENT_REAL_ROOT ||
+ status == PATH_PARENT_DISCONNECTED_ROOT)
+ return NULL;
+ break;
+ default:
+ return NULL;
+ }
+ return &kit->path;
+}
+
+__bpf_kfunc void bpf_iter_path_destroy(struct bpf_iter_path *it)
+{
+ struct bpf_iter_path_kern *kit = (void *)it;
+
+ path_put(&kit->path);
+}
+
+__bpf_kfunc_end_defs();
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d5807d2efc92..734c06809563 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7034,6 +7034,10 @@ BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket) {
struct sock *sk;
};
+BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct path) {
+ struct dentry *dentry;
+};
+
static bool type_is_rcu(struct bpf_verifier_env *env,
struct bpf_reg_state *reg,
const char *field_name, u32 btf_id)
@@ -7074,6 +7078,7 @@ static bool type_is_trusted_or_null(struct bpf_verifier_env *env,
const char *field_name, u32 btf_id)
{
BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket));
+ BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct path));
return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id,
"__safe_trusted_or_null");
--
2.47.1
