Re: [PATCH v2 bpf-next 1/3] bpf: add bpf_progenyof helper

[Martin Lau <kafai@fb.com>]

On Fri, Mar 01, 2019 at 10:06:12AM -0800, Javier Honduvilla Coto wrote:
> From: Javier Honduvilla Coto <javierhonduco@gmail.com>
> 
> This patch adds the bpf_progenyof helper which receives a PID and returns
> 1 if the process currently being executed is in the process hierarchy
> including itself or 0 if not.
> 
> This is very useful in tracing programs when we want to filter by a
> given PID and all the children it might spawn. The current workarounds
> most people implement for this purpose have issues:
> 
> - Attaching to process spawning syscalls and dynamically add those PIDs
>   to some bpf map that would be used to filter is cumbersome and
> potentially racy.
> - Unrolling some loop to perform what this helper is doing consumes lots
>   of instructions. That and the impossibility to jump backwards makes it
> really hard to be correct in really large process chains.
> 
> Signed-off-by: Javier Honduvilla Coto <javierhonduco@gmail.com>
> ---
>  include/linux/bpf.h      |  1 +
>  include/uapi/linux/bpf.h | 11 ++++++++++-
>  kernel/bpf/core.c        |  1 +
>  kernel/bpf/helpers.c     | 29 +++++++++++++++++++++++++++++
>  kernel/trace/bpf_trace.c |  2 ++
>  5 files changed, 43 insertions(+), 1 deletion(-)
> 
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index de18227b3d95..447395ba202b 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -921,6 +921,7 @@ extern const struct bpf_func_proto bpf_sk_redirect_map_proto;
>  extern const struct bpf_func_proto bpf_spin_lock_proto;
>  extern const struct bpf_func_proto bpf_spin_unlock_proto;
>  extern const struct bpf_func_proto bpf_get_local_storage_proto;
> +extern const struct bpf_func_proto bpf_progenyof_proto;
>  
>  /* Shared helpers among cBPF and eBPF. */
>  void bpf_user_rnd_init_once(void);
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index bcdd2474eee7..354ec295864c 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -2359,6 +2359,14 @@ union bpf_attr {
>   *	Return
>   *		A **struct bpf_tcp_sock** pointer on success, or NULL in
>   *		case of failure.
> + *
> + * int bpf_progenyof(int pid)
> + *	Description
> + *		This helper is useful in programs that want to filter events
> + *		happening to a pid of any of its descendants.
> + *	Return
> + *		1 if the currently executing process' pid is in the process
> + *		hierarchy of the passed pid. 0 Otherwise.
>   */
>  #define __BPF_FUNC_MAPPER(FN)		\
>  	FN(unspec),			\
> @@ -2457,7 +2465,8 @@ union bpf_attr {
>  	FN(spin_lock),			\
>  	FN(spin_unlock),		\
>  	FN(sk_fullsock),		\
> -	FN(tcp_sock),
> +	FN(tcp_sock),			\
> +	FN(progenyof),
>  
>  /* integer value in 'imm' field of BPF_CALL instruction selects which helper
>   * function eBPF program intends to call
> diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
> index ef88b167959d..69e209fbd128 100644
> --- a/kernel/bpf/core.c
> +++ b/kernel/bpf/core.c
> @@ -2015,6 +2015,7 @@ const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;
>  const struct bpf_func_proto bpf_get_current_comm_proto __weak;
>  const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
>  const struct bpf_func_proto bpf_get_local_storage_proto __weak;
> +const struct bpf_func_proto bpf_progenyof_proto __weak;
>  
>  const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
>  {
> diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
> index a411fc17d265..3899787e8dbf 100644
> --- a/kernel/bpf/helpers.c
> +++ b/kernel/bpf/helpers.c
> @@ -18,6 +18,7 @@
>  #include <linux/sched.h>
>  #include <linux/uidgid.h>
>  #include <linux/filter.h>
> +#include <linux/init_task.h>
>  
>  /* If kernel subsystem is allowing eBPF programs to call this function,
>   * inside its own verifier_ops->get_func_proto() callback it should return
> @@ -364,3 +365,31 @@ const struct bpf_func_proto bpf_get_local_storage_proto = {
>  };
>  #endif
>  #endif
> +
> +BPF_CALL_1(bpf_progenyof, int, pid)
> +{
> +	int result = 0;
> +	struct task_struct *task = current;
> +
> +	if (unlikely(!task))
> +		return -EINVAL;
> +
> +	rcu_read_lock();
I don't think it is needed.  It should already be under rcu_read_lock().
You may add 'WARN_ON_ONCE(!rcu_read_lock_held());' to be safe,
like other "bpf_map_xxx_elem()" helpers in the same file.

> +	while (task != &init_task) {
> +		if (task->pid == pid) {
> +			result = 1;
> +			break;
> +		}
> +		task = rcu_dereference(task->real_parent);
> +	}
> +	rcu_read_unlock();
> +
> +	return result;
> +}
> +
> +const struct bpf_func_proto bpf_progenyof_proto = {
> +	.func		= bpf_progenyof,
> +	.gpl_only	= false,
> +	.ret_type	= RET_INTEGER,
> +	.arg1_type	= ARG_ANYTHING,
> +};
> diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
> index f1a86a0d881d..8602ae83c799 100644
> --- a/kernel/trace/bpf_trace.c
> +++ b/kernel/trace/bpf_trace.c
> @@ -600,6 +600,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
>  		return &bpf_get_prandom_u32_proto;
>  	case BPF_FUNC_probe_read_str:
>  		return &bpf_probe_read_str_proto;
> +	case BPF_FUNC_progenyof:
> +		return &bpf_progenyof_proto;
>  #ifdef CONFIG_CGROUPS
>  	case BPF_FUNC_get_current_cgroup_id:
>  		return &bpf_get_current_cgroup_id_proto;
> -- 
> 2.17.1
>