Re: [PATCH bpf-next v7 1/5] bpf: Parameterize task iterators.

[Yonghong Song <yhs@fb.com>]

On 8/25/22 5:37 PM, Kui-Feng Lee wrote:
> Allow creating an iterator that loops through resources of one
> thread/process.
> 
> People could only create iterators to loop through all resources of
> files, vma, and tasks in the system, even though they were interested
> in only the resources of a specific task or process.  Passing the
> additional parameters, people can now create an iterator to go
> through all resources or only the resources of a task.
> 
> Signed-off-by: Kui-Feng Lee <kuifeng@fb.com>
> Acked-by: Yonghong Song <yhs@fb.com>
> ---
>   include/linux/bpf.h            |  25 +++++++
>   include/uapi/linux/bpf.h       |   6 ++
>   kernel/bpf/task_iter.c         | 128 ++++++++++++++++++++++++++-------
>   tools/include/uapi/linux/bpf.h |   6 ++
>   4 files changed, 141 insertions(+), 24 deletions(-)
> 
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index 9c1674973e03..31ac2c1181f5 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -1730,6 +1730,27 @@ int bpf_obj_get_user(const char __user *pathname, int flags);
>   	extern int bpf_iter_ ## target(args);			\
>   	int __init bpf_iter_ ## target(args) { return 0; }
>   
> +/*
> + * The task type of iterators.
> + *
> + * For BPF task iterators, they can be parameterized with various
> + * parameters to visit only some of tasks.
> + *
> + * BPF_TASK_ITER_ALL (default)
> + *	Iterate over resources of every task.
> + *
> + * BPF_TASK_ITER_TID
> + *	Iterate over resources of a task/tid.
> + *
> + * BPF_TASK_ITER_TGID
> + *	Iterate over resources of every task of a process / task group.
> + */
> +enum bpf_iter_task_type {
> +	BPF_TASK_ITER_ALL = 0,
> +	BPF_TASK_ITER_TID,
> +	BPF_TASK_ITER_TGID,
> +};
> +
>   struct bpf_iter_aux_info {
>   	/* for map_elem iter */
>   	struct bpf_map *map;
> @@ -1739,6 +1760,10 @@ struct bpf_iter_aux_info {
>   		struct cgroup *start; /* starting cgroup */
>   		enum bpf_cgroup_iter_order order;
>   	} cgroup;
> +	struct {
> +		enum bpf_iter_task_type	type;
> +		u32 pid;
> +	} task;
>   };
>   
>   typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog,
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 0f61f09f467a..385deab984e1 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -110,6 +110,12 @@ union bpf_iter_link_info {
>   		__u32	cgroup_fd;
>   		__u64	cgroup_id;
>   	} cgroup;
> +	/* Parameters of task iterators. */
> +	struct {
> +		__u32	tid;
> +		__u32	pid;
> +		__u32	pid_fd;
> +	} task;
>   };
>   
>   /* BPF syscall commands, see bpf(2) man-page for more details. */
> diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
> index 8c921799def4..1200cfde71e3 100644
> --- a/kernel/bpf/task_iter.c
> +++ b/kernel/bpf/task_iter.c
> @@ -12,6 +12,8 @@
>   
>   struct bpf_iter_seq_task_common {
>   	struct pid_namespace *ns;
> +	enum bpf_iter_task_type	type;
> +	u32 pid;
>   };
>   
>   struct bpf_iter_seq_task_info {
> @@ -22,24 +24,54 @@ struct bpf_iter_seq_task_info {
>   	u32 tid;
>   };
>   
> -static struct task_struct *task_seq_get_next(struct pid_namespace *ns,
> +static bool matched_task(struct task_struct *task,
> +			 struct bpf_iter_seq_task_common *common,
> +			 bool skip_if_dup_file)
> +{
> +	/* Should not have the same 'files' if skip_if_dup_file is true */
> +	bool diff_files_if =
> +		!skip_if_dup_file ||
> +		(thread_group_leader(task) &&
> +		 task->files != task->group_leader->files);

Should this be
	!skip_if_dup_file || thread_group_leader(task) ||
	task->files != task->group_leader->files
?

> +	/* Should have the given tgid if the type is BPF_TASK_ITER_TGI */

BPF_TASK_ITER_TGID?

> +	bool have_tgid_if =
> +		common->type != BPF_TASK_ITER_TGID ||
> +		__task_pid_nr_ns(task, PIDTYPE_TGID,
> +				 common->ns) == common->pid;
> +	return diff_files_if && have_tgid_if;
> +}
> +
> +
> +static struct task_struct *task_seq_get_next(struct bpf_iter_seq_task_common *common,
>   					     u32 *tid,
>   					     bool skip_if_dup_files)
>   {
>   	struct task_struct *task = NULL;
>   	struct pid *pid;
>   
> +	if (common->type == BPF_TASK_ITER_TID) {
> +		if (*tid && *tid != common->pid)
> +			return NULL;
> +		rcu_read_lock();
> +		pid = find_pid_ns(common->pid, common->ns);
> +		if (pid) {
> +			task = get_pid_task(pid, PIDTYPE_PID);
> +			*tid = common->pid;
> +		}
> +		rcu_read_unlock();
> +		return task;
> +	}
> +
>   	rcu_read_lock();
>   retry:
> -	pid = find_ge_pid(*tid, ns);
> +	pid = find_ge_pid(*tid, common->ns);
>   	if (pid) {
> -		*tid = pid_nr_ns(pid, ns);
> +		*tid = pid_nr_ns(pid, common->ns);
>   		task = get_pid_task(pid, PIDTYPE_PID);
>   		if (!task) {
>   			++*tid;
>   			goto retry;
> -		} else if (skip_if_dup_files && !thread_group_leader(task) &&
> -			   task->files == task->group_leader->files) {
> +		} else if (!matched_task(task, common, skip_if_dup_files)) {
>   			put_task_struct(task);
>   			task = NULL;
>   			++*tid;
> @@ -56,7 +88,7 @@ static void *task_seq_start(struct seq_file *seq, loff_t *pos)
>   	struct bpf_iter_seq_task_info *info = seq->private;
>   	struct task_struct *task;
>   
> -	task = task_seq_get_next(info->common.ns, &info->tid, false);
> +	task = task_seq_get_next(&info->common, &info->tid, false);
>   	if (!task)
>   		return NULL;
>   
[...]