Re: [PATCH bpf-next v1 8/9] bpf: Introduce cgroup iter

[Yonghong Song <yhs@fb.com>]

On 2/25/22 3:43 PM, Hao Luo wrote:
> Introduce a new type of iter prog: cgroup. Unlike other bpf_iter, this
> iter doesn't iterate a set of kernel objects. Instead, it is supposed to
> be parameterized by a cgroup id and prints only that cgroup. So one
> needs to specify a target cgroup id when attaching this iter.
> 
> The target cgroup's state can be read out via a link of this iter.
> Typically, we can monitor cgroup creation and deletion using sleepable
> tracing and use it to create corresponding directories in bpffs and pin
> a cgroup id parameterized link in the directory. Then we can read the
> auto-pinned iter link to get cgroup's state. The output of the iter link
> is determined by the program. See the selftest test_cgroup_stats.c for
> an example.
> 
> Signed-off-by: Hao Luo <haoluo@google.com>
> ---
>   include/linux/bpf.h            |   1 +
>   include/uapi/linux/bpf.h       |   6 ++
>   kernel/bpf/Makefile            |   2 +-
>   kernel/bpf/cgroup_iter.c       | 141 +++++++++++++++++++++++++++++++++
>   tools/include/uapi/linux/bpf.h |   6 ++
>   5 files changed, 155 insertions(+), 1 deletion(-)
>   create mode 100644 kernel/bpf/cgroup_iter.c
> 
[...]
> +
> +static const struct seq_operations cgroup_iter_seq_ops = {
> +	.start  = cgroup_iter_seq_start,
> +	.next   = cgroup_iter_seq_next,
> +	.stop   = cgroup_iter_seq_stop,
> +	.show   = cgroup_iter_seq_show,
> +};
> +
> +BTF_ID_LIST_SINGLE(bpf_cgroup_btf_id, struct, cgroup)
> +
> +static int cgroup_iter_seq_init(void *priv_data, struct bpf_iter_aux_info *aux)
> +{
> +	*(u64 *)priv_data = aux->cgroup_id;
> +	return 0;
> +}
> +
> +static void cgroup_iter_seq_fini(void *priv_data)
> +{
> +}
> +
> +static const struct bpf_iter_seq_info cgroup_iter_seq_info = {
> +	.seq_ops                = &cgroup_iter_seq_ops,
> +	.init_seq_private       = cgroup_iter_seq_init,
> +	.fini_seq_private       = cgroup_iter_seq_fini,

Since cgroup_iter_seq_fini() is a nop, you can just have
	.fini_seq_private	= NULL,

> +	.seq_priv_size          = sizeof(u64),
> +};
> +
> +static int bpf_iter_attach_cgroup(struct bpf_prog *prog,
> +				  union bpf_iter_link_info *linfo,
> +				  struct bpf_iter_aux_info *aux)
> +{
> +	aux->cgroup_id = linfo->cgroup.cgroup_id;
> +	return 0;
> +}
> +
> +static void bpf_iter_detach_cgroup(struct bpf_iter_aux_info *aux)
> +{
> +}
> +
> +void bpf_iter_cgroup_show_fdinfo(const struct bpf_iter_aux_info *aux,
> +				 struct seq_file *seq)
> +{
> +	char buf[64] = {0};

Is this 64 the maximum possible cgroup path length?
If there is a macro for that, I think it would be good to use it.

> +
> +	cgroup_path_from_kernfs_id(aux->cgroup_id, buf, sizeof(buf));

cgroup_path_from_kernfs_id() might fail in which case, buf will be 0.
and cgroup_path will be nothing. I guess this might be the expected
result. I might be good to add a comment to clarify in the code.


> +	seq_printf(seq, "cgroup_id:\t%lu\n", aux->cgroup_id);
> +	seq_printf(seq, "cgroup_path:\t%s\n", buf);
> +}
> +
> +int bpf_iter_cgroup_fill_link_info(const struct bpf_iter_aux_info *aux,
> +				   struct bpf_link_info *info)
> +{
> +	info->iter.cgroup.cgroup_id = aux->cgroup_id;
> +	return 0;
> +}
> +
> +DEFINE_BPF_ITER_FUNC(cgroup, struct bpf_iter_meta *meta,
> +		     struct cgroup *cgroup)
> +
> +static struct bpf_iter_reg bpf_cgroup_reg_info = {
> +	.target			= "cgroup",
> +	.attach_target		= bpf_iter_attach_cgroup,
> +	.detach_target		= bpf_iter_detach_cgroup,

The same ehre, since bpf_iter_detach_cgroup() is a nop,
you can replace it with NULL in the above.

> +	.show_fdinfo		= bpf_iter_cgroup_show_fdinfo,
> +	.fill_link_info		= bpf_iter_cgroup_fill_link_info,
> +	.ctx_arg_info_size	= 1,
> +	.ctx_arg_info		= {
> +		{ offsetof(struct bpf_iter__cgroup, cgroup),
> +		  PTR_TO_BTF_ID },
> +	},
> +	.seq_info		= &cgroup_iter_seq_info,
> +};
> +
> +static int __init bpf_cgroup_iter_init(void)
> +{
> +	bpf_cgroup_reg_info.ctx_arg_info[0].btf_id = bpf_cgroup_btf_id[0];
> +	return bpf_iter_reg_target(&bpf_cgroup_reg_info);
> +}
> +
[...]