Re: [PATCH bpf-next 1/3] bpf: introduce helper bpf_get_task_stack_trace()

[Alexei Starovoitov <alexei.starovoitov@gmail.com>]

On Tue, Jun 23, 2020 at 12:08 AM Song Liu <songliubraving@fb.com> wrote:
>
> This helper can be used with bpf_iter__task to dump all /proc/*/stack to
> a seq_file.
>
> Signed-off-by: Song Liu <songliubraving@fb.com>
> ---
>  include/uapi/linux/bpf.h       | 10 +++++++++-
>  kernel/trace/bpf_trace.c       | 21 +++++++++++++++++++++
>  scripts/bpf_helpers_doc.py     |  2 ++
>  tools/include/uapi/linux/bpf.h | 10 +++++++++-
>  4 files changed, 41 insertions(+), 2 deletions(-)
>
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 19684813faaed..a30416b822fe3 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -3252,6 +3252,13 @@ union bpf_attr {
>   *             case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level
>   *             is returned or the error code -EACCES in case the skb is not
>   *             subject to CHECKSUM_UNNECESSARY.
> + *
> + * int bpf_get_task_stack_trace(struct task_struct *task, void *entries, u32 size)
> + *     Description
> + *             Save a task stack trace into array *entries*. This is a wrapper
> + *             over stack_trace_save_tsk().
> + *     Return
> + *             Number of trace entries stored.
>   */
>  #define __BPF_FUNC_MAPPER(FN)          \
>         FN(unspec),                     \
> @@ -3389,7 +3396,8 @@ union bpf_attr {
>         FN(ringbuf_submit),             \
>         FN(ringbuf_discard),            \
>         FN(ringbuf_query),              \
> -       FN(csum_level),
> +       FN(csum_level),                 \
> +       FN(get_task_stack_trace),
>
>  /* integer value in 'imm' field of BPF_CALL instruction selects which helper
>   * function eBPF program intends to call
> diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
> index e729c9e587a07..2c13bcb5c2bce 100644
> --- a/kernel/trace/bpf_trace.c
> +++ b/kernel/trace/bpf_trace.c
> @@ -1488,6 +1488,23 @@ static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = {
>         .arg4_type      = ARG_ANYTHING,
>  };
>
> +BPF_CALL_3(bpf_get_task_stack_trace, struct task_struct *, task,
> +          void *, entries, u32, size)
> +{
> +       return stack_trace_save_tsk(task, (unsigned long *)entries, size, 0);
> +}
> +
> +static int bpf_get_task_stack_trace_btf_ids[5];
> +static const struct bpf_func_proto bpf_get_task_stack_trace_proto = {
> +       .func           = bpf_get_task_stack_trace,
> +       .gpl_only       = true,

why?

> +       .ret_type       = RET_INTEGER,
> +       .arg1_type      = ARG_PTR_TO_BTF_ID,
> +       .arg2_type      = ARG_PTR_TO_MEM,
> +       .arg3_type      = ARG_CONST_SIZE_OR_ZERO,

OR_ZERO ? why?

> +       .btf_id         = bpf_get_task_stack_trace_btf_ids,
> +};
> +
>  static const struct bpf_func_proto *
>  raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
>  {
> @@ -1521,6 +1538,10 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
>                 return prog->expected_attach_type == BPF_TRACE_ITER ?
>                        &bpf_seq_write_proto :
>                        NULL;
> +       case BPF_FUNC_get_task_stack_trace:
> +               return prog->expected_attach_type == BPF_TRACE_ITER ?
> +                       &bpf_get_task_stack_trace_proto :

why limit to iter only?

> + *
> + * int bpf_get_task_stack_trace(struct task_struct *task, void *entries, u32 size)
> + *     Description
> + *             Save a task stack trace into array *entries*. This is a wrapper
> + *             over stack_trace_save_tsk().

size is not documented and looks wrong.
the verifier checks it in bytes, but it's consumed as number of u32s.