Re: [PATCH bpf-next 3/6] bpf: Add link_info support for uprobe multi link

From: Yafang Shao <laoar.shao@gmail.com>
To: Jiri Olsa <jolsa@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	 Andrii Nakryiko <andrii@kernel.org>,
	bpf@vger.kernel.org, Martin KaFai Lau <kafai@fb.com>,
	 Song Liu <songliubraving@fb.com>, Yonghong Song <yhs@fb.com>,
	 John Fastabend <john.fastabend@gmail.com>,
	KP Singh <kpsingh@chromium.org>,
	 Stanislav Fomichev <sdf@google.com>, Hao Luo <haoluo@google.com>
Subject: Re: [PATCH bpf-next 3/6] bpf: Add link_info support for uprobe multi link
Date: Thu, 26 Oct 2023 19:57:27 +0800	[thread overview]
Message-ID: <CALOAHbAZ6=A9j3VFCLoAC_WhgQKU7injMf06=cM2sU4Hi4Sx+Q@mail.gmail.com> (raw)
In-Reply-To: <20231025202420.390702-4-jolsa@kernel.org>

On Thu, Oct 26, 2023 at 4:24 AM Jiri Olsa <jolsa@kernel.org> wrote:
>
> Adding support to get uprobe_link details through bpf_link_info
> interface.
>
> Adding new struct uprobe_multi to struct bpf_link_info to carry
> the uprobe_multi link details.
>
> The uprobe_multi.count is passed from user space to denote size
> of array fields (offsets/ref_ctr_offsets/cookies). The actual
> array size is stored back to uprobe_multi.count (allowing user
> to find out the actual array size) and array fields are populated
> up to the user passed size.
>
> All the non-array fields (path/count/flags/pid) are always set.
>
> Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> ---
>  include/uapi/linux/bpf.h       | 10 +++++
>  kernel/trace/bpf_trace.c       | 68 ++++++++++++++++++++++++++++++++++
>  tools/include/uapi/linux/bpf.h | 10 +++++
>  3 files changed, 88 insertions(+)
>
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 0f6cdf52b1da..960cf2914d63 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -6556,6 +6556,16 @@ struct bpf_link_info {
>                         __u32 flags;
>                         __u64 missed;
>                 } kprobe_multi;
> +               struct {
> +                       __aligned_u64 path;
> +                       __aligned_u64 offsets;
> +                       __aligned_u64 ref_ctr_offsets;
> +                       __aligned_u64 cookies;

The bpf cookie for the perf_event link is exposed through
'pid_iter.bpf.c,' while the cookies for the tracing link and
kprobe_multi link are not exposed at all. This inconsistency can be
confusing. I believe it would be better to include all of them in the
link_info. The reason is that 'pid_iter' depends on the task holding
the links, which may not exist. However, I think we handle this in a
separate patchset. What do you think?

> +                       __u32 path_max; /* in/out: uprobe_multi path size */
> +                       __u32 count;    /* in/out: uprobe_multi offsets/ref_ctr_offsets/cookies count */
> +                       __u32 flags;
> +                       __u32 pid;
> +               } uprobe_multi;
>                 struct {
>                         __u32 type; /* enum bpf_perf_event_type */
>                         __u32 :32;
> diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
> index 843b3846d3f8..9f8ad19a1a93 100644
> --- a/kernel/trace/bpf_trace.c
> +++ b/kernel/trace/bpf_trace.c
> @@ -3042,6 +3042,7 @@ struct bpf_uprobe_multi_link {
>         u32 cnt;
>         struct bpf_uprobe *uprobes;
>         struct task_struct *task;
> +       u32 flags;
>  };
>
>  struct bpf_uprobe_multi_run_ctx {
> @@ -3081,9 +3082,75 @@ static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link)
>         kfree(umulti_link);
>  }
>
> +static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link,
> +                                               struct bpf_link_info *info)
> +{
> +       u64 __user *uref_ctr_offsets = u64_to_user_ptr(info->uprobe_multi.ref_ctr_offsets);
> +       u64 __user *ucookies = u64_to_user_ptr(info->uprobe_multi.cookies);
> +       u64 __user *uoffsets = u64_to_user_ptr(info->uprobe_multi.offsets);
> +       u64 __user *upath = u64_to_user_ptr(info->uprobe_multi.path);
> +       u32 upath_max = info->uprobe_multi.path_max;
> +       struct bpf_uprobe_multi_link *umulti_link;
> +       u32 ucount = info->uprobe_multi.count;
> +       int err = 0, i;
> +       char *p, *buf;
> +       long left;
> +
> +       if (!upath ^ !upath_max)
> +               return -EINVAL;
> +
> +       if (!uoffsets ^ !ucount)
> +               return -EINVAL;
> +
> +       umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
> +       info->uprobe_multi.count = umulti_link->cnt;
> +       info->uprobe_multi.flags = umulti_link->flags;
> +       info->uprobe_multi.pid = umulti_link->task ?
> +                                task_pid_nr(umulti_link->task) : (u32) -1;
> +
> +       if (upath) {
> +               if (upath_max > PATH_MAX)
> +                       return -E2BIG;
> +               buf = kmalloc(upath_max, GFP_KERNEL);
> +               if (!buf)
> +                       return -ENOMEM;
> +               p = d_path(&umulti_link->path, buf, upath_max);
> +               if (IS_ERR(p)) {
> +                       kfree(buf);
> +                       return -ENOSPC;
> +               }
> +               left = copy_to_user(upath, p, buf + upath_max - p);
> +               kfree(buf);
> +               if (left)
> +                       return -EFAULT;
> +       }
> +
> +       if (!uoffsets)
> +               return 0;
> +
> +       if (ucount < umulti_link->cnt)
> +               err = -ENOSPC;
> +       else
> +               ucount = umulti_link->cnt;
> +
> +       for (i = 0; i < ucount; i++) {
> +               if (put_user(umulti_link->uprobes[i].offset, uoffsets + i))
> +                       return -EFAULT;
> +               if (uref_ctr_offsets &&
> +                   put_user(umulti_link->uprobes[i].ref_ctr_offset, uref_ctr_offsets + i))
> +                       return -EFAULT;
> +               if (ucookies &&
> +                   put_user(umulti_link->uprobes[i].cookie, ucookies + i))
> +                       return -EFAULT;
> +       }
> +
> +       return err;
> +}
> +
>  static const struct bpf_link_ops bpf_uprobe_multi_link_lops = {
>         .release = bpf_uprobe_multi_link_release,
>         .dealloc = bpf_uprobe_multi_link_dealloc,
> +       .fill_link_info = bpf_uprobe_multi_link_fill_link_info,
>  };
>
>  static int uprobe_prog_run(struct bpf_uprobe *uprobe,
> @@ -3272,6 +3339,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
>         link->uprobes = uprobes;
>         link->path = path;
>         link->task = task;
> +       link->flags = flags;
>
>         bpf_link_init(&link->link, BPF_LINK_TYPE_UPROBE_MULTI,
>                       &bpf_uprobe_multi_link_lops, prog);
> diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
> index 0f6cdf52b1da..960cf2914d63 100644
> --- a/tools/include/uapi/linux/bpf.h
> +++ b/tools/include/uapi/linux/bpf.h
> @@ -6556,6 +6556,16 @@ struct bpf_link_info {
>                         __u32 flags;
>                         __u64 missed;
>                 } kprobe_multi;
> +               struct {
> +                       __aligned_u64 path;
> +                       __aligned_u64 offsets;
> +                       __aligned_u64 ref_ctr_offsets;
> +                       __aligned_u64 cookies;
> +                       __u32 path_max; /* in/out: uprobe_multi path size */
> +                       __u32 count;    /* in/out: uprobe_multi offsets/ref_ctr_offsets/cookies count */
> +                       __u32 flags;
> +                       __u32 pid;
> +               } uprobe_multi;
>                 struct {
>                         __u32 type; /* enum bpf_perf_event_type */
>                         __u32 :32;
> --
> 2.41.0
>

-- 
Regards
Yafang