bpf: Introduce css open-coded iterator kfuncs

This Patch adds kfuncs bpf_iter_css_{new,next,destroy} which allow
creation and manipulation of struct bpf_iter_css in open-coded iterator
style. These kfuncs actually wrapps css_next_descendant_{pre, post}.
css_iter can be used to:

1) iterating a sepcific cgroup tree with pre/post/up order

2) iterating cgroup_subsystem in BPF Prog, like
for_each_mem_cgroup_tree/cpuset_for_each_descendant_pre in kernel.

The API design is consistent with cgroup_iter. bpf_iter_css_new accepts
parameters defining iteration order and starting css. Here we also reuse
BPF_CGROUP_ITER_DESCENDANTS_PRE, BPF_CGROUP_ITER_DESCENDANTS_POST,
BPF_CGROUP_ITER_ANCESTORS_UP enums.
Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20231018061746.111364-5-zhouchuyi@bytedance.comSigned-off-by: Alexei Starovoitov <ast@kernel.org>

kernel/bpf/cgroup_iter.c

@@ -294,3 +294,68 @@ static int __init bpf_cgroup_iter_init(void)
 }
 
 late_initcall(bpf_cgroup_iter_init);
+
+struct bpf_iter_css {
+	__u64 __opaque[3];
+} __attribute__((aligned(8)));
+
+struct bpf_iter_css_kern {
+	struct cgroup_subsys_state *start;
+	struct cgroup_subsys_state *pos;
+	unsigned int flags;
+} __attribute__((aligned(8)));
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		"Global functions as their definitions will be in vmlinux BTF");
+
+__bpf_kfunc int bpf_iter_css_new(struct bpf_iter_css *it,
+		struct cgroup_subsys_state *start, unsigned int flags)
+{
+	struct bpf_iter_css_kern *kit = (void *)it;
+
+	BUILD_BUG_ON(sizeof(struct bpf_iter_css_kern) > sizeof(struct bpf_iter_css));
+	BUILD_BUG_ON(__alignof__(struct bpf_iter_css_kern) != __alignof__(struct bpf_iter_css));
+
+	kit->start = NULL;
+	switch (flags) {
+	case BPF_CGROUP_ITER_DESCENDANTS_PRE:
+	case BPF_CGROUP_ITER_DESCENDANTS_POST:
+	case BPF_CGROUP_ITER_ANCESTORS_UP:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	kit->start = start;
+	kit->pos = NULL;
+	kit->flags = flags;
+	return 0;
+}
+
+__bpf_kfunc struct cgroup_subsys_state *bpf_iter_css_next(struct bpf_iter_css *it)
+{
+	struct bpf_iter_css_kern *kit = (void *)it;
+
+	if (!kit->start)
+		return NULL;
+
+	switch (kit->flags) {
+	case BPF_CGROUP_ITER_DESCENDANTS_PRE:
+		kit->pos = css_next_descendant_pre(kit->pos, kit->start);
+		break;
+	case BPF_CGROUP_ITER_DESCENDANTS_POST:
+		kit->pos = css_next_descendant_post(kit->pos, kit->start);
+		break;
+	case BPF_CGROUP_ITER_ANCESTORS_UP:
+		kit->pos = kit->pos ? kit->pos->parent : kit->start;
+	}
+
+	return kit->pos;
+}
+
+__bpf_kfunc void bpf_iter_css_destroy(struct bpf_iter_css *it)
+{
+}
+
+__diag_pop();
\ No newline at end of file

kernel/bpf/helpers.c

@@ -2566,6 +2566,9 @@ BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
 BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_iter_css_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_css_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_dynptr_adjust)
 BTF_ID_FLAGS(func, bpf_dynptr_is_null)
 BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)

tools/testing/selftests/bpf/bpf_experimental.h

@@ -471,4 +471,10 @@ extern int bpf_iter_task_new(struct bpf_iter_task *it,
 extern struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it) __weak __ksym;
 extern void bpf_iter_task_destroy(struct bpf_iter_task *it) __weak __ksym;
 
+struct bpf_iter_css;
+extern int bpf_iter_css_new(struct bpf_iter_css *it,
+				struct cgroup_subsys_state *start, unsigned int flags) __weak __ksym;
+extern struct cgroup_subsys_state *bpf_iter_css_next(struct bpf_iter_css *it) __weak __ksym;
+extern void bpf_iter_css_destroy(struct bpf_iter_css *it) __weak __ksym;
+
 #endif