path: root/kernel/bpf/task_iter.c

// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2020 Facebook */

#include <linux/init.h>
#include <linux/namei.h>
#include <linux/pid_namespace.h>
#include <linux/fs.h>
#include <linux/fdtable.h>
#include <linux/filter.h>
#include <linux/bpf_mem_alloc.h>
#include <linux/btf_ids.h>
#include <linux/mm_types.h>
#include "mmap_unlock_work.h"

static const char * const iter_task_type_names[] = {
	"ALL",
	"TID",
	"PID",
};

struct bpf_iter_seq_task_common {
	struct pid_namespace *ns;
	enum bpf_iter_task_type	type;
	u32 pid;
	u32 pid_visiting;
};

struct bpf_iter_seq_task_info {
	/* The first field must be struct bpf_iter_seq_task_common.
	 * this is assumed by {init, fini}_seq_pidns() callback functions.
	 */
	struct bpf_iter_seq_task_common common;
	u32 tid;
};

static struct task_struct *task_group_seq_get_next(struct bpf_iter_seq_task_common *common,
						   u32 *tid,
						   bool skip_if_dup_files)
{
	struct task_struct *task;
	struct pid *pid;
	u32 next_tid;

	if (!*tid) {
		/* The first time, the iterator calls this function. */
		pid = find_pid_ns(common->pid, common->ns);
		task = get_pid_task(pid, PIDTYPE_TGID);
		if (!task)
			return NULL;

		*tid = common->pid;
		common->pid_visiting = common->pid;

		return task;
	}

	/* If the control returns to user space and comes back to the
	 * kernel again, *tid and common->pid_visiting should be the
	 * same for task_seq_start() to pick up the correct task.
	 */
	if (*tid == common->pid_visiting) {
		pid = find_pid_ns(common->pid_visiting, common->ns);
		task = get_pid_task(pid, PIDTYPE_PID);

		return task;
	}

	task = find_task_by_pid_ns(common->pid_visiting, common->ns);
	if (!task)
		return NULL;

retry:
	task = __next_thread(task);
	if (!task)
		return NULL;

	next_tid = __task_pid_nr_ns(task, PIDTYPE_PID, common->ns);
	if (!next_tid)
		goto retry;

	if (skip_if_dup_files && task->files == task->group_leader->files)
		goto retry;

	*tid = common->pid_visiting = next_tid;
	get_task_struct(task);
	return task;
}

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;
	}

	if (common->type == BPF_TASK_ITER_TGID) {
		rcu_read_lock();
		task = task_group_seq_get_next(common, tid, skip_if_dup_files);
		rcu_read_unlock();

		return task;
	}

	rcu_read_lock();
retry:
	pid = find_ge_pid(*tid, common->ns);
	if (pid) {
		*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) {
			put_task_struct(task);
			task = NULL;
			++*tid;
			goto retry;
		}
	}
	rcu_read_unlock();

	return task;
}

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, &info->tid, false);
	if (!task)
		return NULL;

	if (*pos == 0)
		++*pos;
	return task;
}

static void *task_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct bpf_iter_seq_task_info *info = seq->private;
	struct task_struct *task;

	++*pos;
	++info->tid;
	put_task_struct((struct task_struct *)v);
	task = task_seq_get_next(&info->common, &info->tid, false);
	if (!task)
		return NULL;

	return task;
}

struct bpf_iter__task {
	__bpf_md_ptr(struct bpf_iter_meta *, meta);
	__bpf_md_ptr(struct task_struct *, task);
};

DEFINE_BPF_ITER_FUNC(task, struct bpf_iter_meta *meta, struct task_struct *task)