Re: [PATCH bpf-next v2 4/6] bpf: Introduce css_descendant open-coded iterator kfuncs

[Andrii Nakryiko]

On Tue, Sep 12, 2023 at 12:02 AM Chuyi Zhou <zhouchuyi@xxxxxxxxxxxxx> wrote:
>
> This Patch adds kfuncs bpf_iter_css_{pre,post}_{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}. BPF programs can use these kfuncs through bpf_for_each macro for
> iteration of all descendant css under a root css.
>
> Signed-off-by: Chuyi Zhou <zhouchuyi@xxxxxxxxxxxxx>
> ---
>  include/uapi/linux/bpf.h       |  8 +++++
>  kernel/bpf/helpers.c           |  6 ++++
>  kernel/bpf/task_iter.c         | 53 ++++++++++++++++++++++++++++++++++
>  tools/include/uapi/linux/bpf.h |  8 +++++
>  tools/lib/bpf/bpf_helpers.h    | 12 ++++++++
>  5 files changed, 87 insertions(+)
>
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index befa55b52e29..57760afc13d0 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -7326,4 +7326,12 @@ struct bpf_iter_process {
>         __u64 __opaque[1];
>  } __attribute__((aligned(8)));
>
> +struct bpf_iter_css_pre {
> +       __u64 __opaque[2];
> +} __attribute__((aligned(8)));
> +
> +struct bpf_iter_css_post {
> +       __u64 __opaque[2];
> +} __attribute__((aligned(8)));
> +
>  #endif /* _UAPI__LINUX_BPF_H__ */
> diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
> index 9b7d2c6f99d1..ca1f6404af9e 100644
> --- a/kernel/bpf/helpers.c
> +++ b/kernel/bpf/helpers.c
> @@ -2510,6 +2510,12 @@ BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY)
>  BTF_ID_FLAGS(func, bpf_iter_process_new, KF_ITER_NEW)
>  BTF_ID_FLAGS(func, bpf_iter_process_next, KF_ITER_NEXT | KF_RET_NULL)
>  BTF_ID_FLAGS(func, bpf_iter_process_destroy, KF_ITER_DESTROY)
> +BTF_ID_FLAGS(func, bpf_iter_css_pre_new, KF_ITER_NEW)
> +BTF_ID_FLAGS(func, bpf_iter_css_pre_next, KF_ITER_NEXT | KF_RET_NULL)
> +BTF_ID_FLAGS(func, bpf_iter_css_pre_destroy, KF_ITER_DESTROY)
> +BTF_ID_FLAGS(func, bpf_iter_css_post_new, KF_ITER_NEW)
> +BTF_ID_FLAGS(func, bpf_iter_css_post_next, KF_ITER_NEXT | KF_RET_NULL)
> +BTF_ID_FLAGS(func, bpf_iter_css_post_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)
> diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
> index 9d1927dc3a06..8963fc779b87 100644
> --- a/kernel/bpf/task_iter.c
> +++ b/kernel/bpf/task_iter.c
> @@ -880,6 +880,59 @@ __bpf_kfunc void bpf_iter_process_destroy(struct bpf_iter_process *it)
>  {
>  }
>
> +struct bpf_iter_css_kern {
> +       struct cgroup_subsys_state *root;
> +       struct cgroup_subsys_state *pos;
> +} __attribute__((aligned(8)));
> +
> +__bpf_kfunc int bpf_iter_css_pre_new(struct bpf_iter_css_pre *it,
> +               struct cgroup_subsys_state *root)

similar to my comment on previous patches, please see
kernel/bpf/cgroup_iter.c for iter/cgroup iterator program. Let's stay
consistent. We have one iterator that accepts parameters defining
iteration order and starting cgroup. Unless there are some technical
reasons we can't follow similar approach with this open-coded iter,
let's use the same approach. We can even reuse
BPF_CGROUP_ITER_DESCENDANTS_PRE, BPF_CGROUP_ITER_DESCENDANTS_POST,
BPF_CGROUP_ITER_ANCESTORS_UP enums.


> +{
> +       struct bpf_iter_css_kern *kit = (void *)it;
> +
> +       BUILD_BUG_ON(sizeof(struct bpf_iter_css_kern) != sizeof(struct bpf_iter_css_pre));
> +       BUILD_BUG_ON(__alignof__(struct bpf_iter_css_kern) != __alignof__(struct bpf_iter_css_pre));
> +       kit->root = root;
> +       kit->pos = NULL;
> +       return 0;
> +}
> +
> +__bpf_kfunc struct cgroup_subsys_state *bpf_iter_css_pre_next(struct bpf_iter_css_pre *it)
> +{
> +       struct bpf_iter_css_kern *kit = (void *)it;
> +
> +       kit->pos = css_next_descendant_pre(kit->pos, kit->root);
> +       return kit->pos;
> +}
> +
> +__bpf_kfunc void bpf_iter_css_pre_destroy(struct bpf_iter_css_pre *it)
> +{
> +}
> +
> +__bpf_kfunc int bpf_iter_css_post_new(struct bpf_iter_css_post *it,
> +               struct cgroup_subsys_state *root)
> +{
> +       struct bpf_iter_css_kern *kit = (void *)it;
> +
> +       BUILD_BUG_ON(sizeof(struct bpf_iter_css_kern) != sizeof(struct bpf_iter_css_post));
> +       BUILD_BUG_ON(__alignof__(struct bpf_iter_css_kern) != __alignof__(struct bpf_iter_css_post));
> +       kit->root = root;
> +       kit->pos = NULL;
> +       return 0;
> +}
> +
> +__bpf_kfunc struct cgroup_subsys_state *bpf_iter_css_post_next(struct bpf_iter_css_post *it)
> +{
> +       struct bpf_iter_css_kern *kit = (void *)it;
> +
> +       kit->pos = css_next_descendant_post(kit->pos, kit->root);
> +       return kit->pos;
> +}
> +
> +__bpf_kfunc void bpf_iter_css_post_destroy(struct bpf_iter_css_post *it)
> +{
> +}
> +
>  DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
>
>  static void do_mmap_read_unlock(struct irq_work *entry)
> diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
> index befa55b52e29..57760afc13d0 100644
> --- a/tools/include/uapi/linux/bpf.h
> +++ b/tools/include/uapi/linux/bpf.h
> @@ -7326,4 +7326,12 @@ struct bpf_iter_process {
>         __u64 __opaque[1];
>  } __attribute__((aligned(8)));
>
> +struct bpf_iter_css_pre {
> +       __u64 __opaque[2];
> +} __attribute__((aligned(8)));
> +
> +struct bpf_iter_css_post {
> +       __u64 __opaque[2];
> +} __attribute__((aligned(8)));
> +
>  #endif /* _UAPI__LINUX_BPF_H__ */
> diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
> index 858252c2641c..6e5bd9ef14d6 100644
> --- a/tools/lib/bpf/bpf_helpers.h
> +++ b/tools/lib/bpf/bpf_helpers.h
> @@ -315,6 +315,18 @@ extern int bpf_iter_process_new(struct bpf_iter_process *it) __weak __ksym;
>  extern struct task_struct *bpf_iter_process_next(struct bpf_iter_process *it) __weak __ksym;
>  extern void bpf_iter_process_destroy(struct bpf_iter_process *it) __weak __ksym;
>
> +struct bpf_iter_css_pre;
> +extern int bpf_iter_css_pre_new(struct bpf_iter_css_pre *it,
> +               struct cgroup_subsys_state *root) __weak __ksym;
> +extern struct cgroup_subsys_state *bpf_iter_css_pre_next(struct bpf_iter_css_pre *it) __weak __ksym;
> +extern void bpf_iter_css_pre_destroy(struct bpf_iter_css_pre *it) __weak __ksym;
> +
> +struct bpf_iter_css_post;
> +extern int bpf_iter_css_post_new(struct bpf_iter_css_post *it,
> +               struct cgroup_subsys_state *root) __weak __ksym;
> +extern struct cgroup_subsys_state *bpf_iter_css_post_next(struct bpf_iter_css_post *it) __weak __ksym;
> +extern void bpf_iter_css_post_destroy(struct bpf_iter_css_post *it) __weak __ksym;
> +
>  #ifndef bpf_for_each
>  /* bpf_for_each(iter_type, cur_elem, args...) provides generic construct for
>   * using BPF open-coded iterators without having to write mundane explicit
> --
> 2.20.1
>