[PATCH v4 bpf-next 3/5] bpf: Introduce path iterator

[Song Liu]

Introduce a path iterator, which walks a struct path toward the root.
This path iterator is based on path_walk_parent. A fixed zero'ed root
is passed to path_walk_parent(). Therefore, unless the user terminates
it earlier, the iterator will terminate at the real root.

Signed-off-by: Song Liu <song@xxxxxxxxxx>
---
 fs/bpf_fs_kfuncs.c    | 72 +++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/verifier.c |  5 +++
 2 files changed, 77 insertions(+)

diff --git a/fs/bpf_fs_kfuncs.c b/fs/bpf_fs_kfuncs.c
index 08412532db1b..1e7e94738c2b 100644
--- a/fs/bpf_fs_kfuncs.c
+++ b/fs/bpf_fs_kfuncs.c
@@ -10,6 +10,7 @@
 #include <linux/fsnotify.h>
 #include <linux/file.h>
 #include <linux/mm.h>
+#include <linux/namei.h>
 #include <linux/xattr.h>
 
 __bpf_kfunc_start_defs();
@@ -324,6 +325,74 @@ __bpf_kfunc int bpf_remove_dentry_xattr(struct dentry *dentry, const char *name_
 
 __bpf_kfunc_end_defs();
 
+/* open-coded path iterator */
+struct bpf_iter_path {
+	__u64 __opaque[2];
+} __aligned(8);
+
+struct bpf_iter_path_kern {
+	struct path path;
+} __aligned(8);
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_iter_path_new(struct bpf_iter_path *it,
+				  struct path *start,
+				  __u64 flags)
+{
+	struct bpf_iter_path_kern *kit = (void *)it;
+
+	BUILD_BUG_ON(sizeof(*kit) > sizeof(*it));
+	BUILD_BUG_ON(__alignof__(*kit) != __alignof__(*it));
+
+	if (flags) {
+		/*
+		 * _destroy() is still called when _new() fails. Zero
+		 * kit->path so that it be passed to path_put() safely.
+		 * Note: path_put() is no-op for zero'ed path.
+		 */
+		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;
+	struct path root = {};
+
+	/*
+	 * "root" is zero'ed. Therefore, unless the loop is explicitly
+	 * terminated, bpf_iter_path_next() will continue looping until
+	 * we've reached the global root of the VFS.
+	 *
+	 * If a root of walk is needed, the user can check "path" against
+	 * that root on each iteration.
+	 */
+	if (!path_walk_parent(&kit->path, &root))
+		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;
+
+	/*
+	 * kit->path might be zero'ed, but this is OK because path_put()
+	 * is no-op for zero'ed struct path
+	 */
+	path_put(&kit->path);
+}
+
+__bpf_kfunc_end_defs();
+
 BTF_KFUNCS_START(bpf_fs_kfunc_set_ids)
 BTF_ID_FLAGS(func, bpf_get_task_exe_file,
 	     KF_ACQUIRE | KF_TRUSTED_ARGS | KF_RET_NULL)
@@ -333,6 +402,9 @@ BTF_ID_FLAGS(func, bpf_get_dentry_xattr, KF_SLEEPABLE | KF_TRUSTED_ARGS)
 BTF_ID_FLAGS(func, bpf_get_file_xattr, KF_SLEEPABLE | KF_TRUSTED_ARGS)
 BTF_ID_FLAGS(func, bpf_set_dentry_xattr, KF_SLEEPABLE | KF_TRUSTED_ARGS)
 BTF_ID_FLAGS(func, bpf_remove_dentry_xattr, KF_SLEEPABLE | KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_iter_path_new, KF_ITER_NEW | KF_TRUSTED_ARGS | 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(bpf_fs_kfunc_set_ids)
 
 static int bpf_fs_kfuncs_filter(const struct bpf_prog *prog, u32 kfunc_id)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b1f797616f20..9b5ac7c02867 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7049,6 +7049,10 @@ 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)
@@ -7089,6 +7093,7 @@ 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