+/* Count the number of tasks in a cgroup. Could be made more
+ * time-efficient but less space-efficient with more linked lists
+ * running through each cgroup and the css_set structures that
+ * referenced it. Must be called with tasklist_lock held for read or
+ * write or in an rcu critical section.
+ */
+int __cgroup_task_count(const struct cgroup *cont)
+{
+ int count = 0;
+ struct task_struct *g, *p;
+ struct cgroup_subsys_state *css;
+ int subsys_id;
+
+ get_first_subsys(cont, &css, &subsys_id);
+ do_each_thread(g, p) {
+ if (task_subsys_state(p, subsys_id) == css)
+ count ++;
+ } while_each_thread(g, p);
+ return count;
+}
+
+/*
+ * Stuff for reading the 'tasks' file.
+ *
+ * Reading this file can return large amounts of data if a cgroup has
+ * *lots* of attached tasks. So it may need several calls to read(),
+ * but we cannot guarantee that the information we produce is correct
+ * unless we produce it entirely atomically.
+ *
+ * Upon tasks file open(), a struct ctr_struct is allocated, that
+ * will have a pointer to an array (also allocated here). The struct
+ * ctr_struct * is stored in file->private_data. Its resources will
+ * be freed by release() when the file is closed. The array is used
+ * to sprintf the PIDs and then used by read().
+ */
+struct ctr_struct {
+ char *buf;
+ int bufsz;
+};
+
+/*
+ * Load into 'pidarray' up to 'npids' of the tasks using cgroup
+ * 'cont'. Return actual number of pids loaded. No need to
+ * task_lock(p) when reading out p->cgroup, since we're in an RCU
+ * read section, so the css_set can't go away, and is
+ * immutable after creation.
+ */
+static int pid_array_load(pid_t *pidarray, int npids, struct cgroup *cont)
+{
+ int n = 0;
+ struct task_struct *g, *p;
+ struct cgroup_subsys_state *css;
+ int subsys_id;
+
+ get_first_subsys(cont, &css, &subsys_id);
+ rcu_read_lock();
+ do_each_thread(g, p) {
+ if (task_subsys_state(p, subsys_id) == css) {
+ pidarray[n++] = pid_nr(task_pid(p));
+ if (unlikely(n == npids))
+ goto array_full;
+ }
+ } while_each_thread(g, p);
+
+array_full:
+ rcu_read_unlock();
+ return n;
+}
+
+static int cmppid(const void *a, const void *b)
+{
+ return *(pid_t *)a - *(pid_t *)b;
+}
+
+/*
+ * Convert array 'a' of 'npids' pid_t's to a string of newline separated
+ * decimal pids in 'buf'. Don't write more than 'sz' chars, but return
+ * count 'cnt' of how many chars would be written if buf were large enough.
+ */
+static int pid_array_to_buf(char *buf, int sz, pid_t *a, int npids)
+{
+ int cnt = 0;
+ int i;
+
+ for (i = 0; i < npids; i++)
+ cnt += snprintf(buf + cnt, max(sz - cnt, 0), "%d\n", a[i]);
+ return cnt;
+}
+
+/*
+ * Handle an open on 'tasks' file. Prepare a buffer listing the
+ * process id's of tasks currently attached to the cgroup being opened.
+ *
+ * Does not require any specific cgroup mutexes, and does not take any.
+ */
+static int cgroup_tasks_open(struct inode *unused, struct file *file)
+{
+ struct cgroup *cont = __d_cont(file->f_dentry->d_parent);
+ struct ctr_struct *ctr;
+ pid_t *pidarray;
+ int npids;
+ char c;
+
+ if (!(file->f_mode & FMODE_READ))
+ return 0;
+
+ ctr = kmalloc(sizeof(*ctr), GFP_KERNEL);
+ if (!ctr)
+ goto err0;
+
+ /*
+ * If cgroup gets more users after we read count, we won't have
+ * enough space - tough. This race is indistinguishable to the
+ * caller from the case that the additional cgroup users didn't
+ * show up until sometime later on.
+ */
+ npids = cgroup_task_count(cont);
+ if (npids) {
+ pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL);
+ if (!pidarray)
+ goto err1;
+
+ npids = pid_array_load(pidarray, npids, cont);
+ sort(pidarray, npids, sizeof(pid_t), cmppid, NULL);
+
+ /* Call pid_array_to_buf() twice, first just to get bufsz */
+ ctr->bufsz = pid_array_to_buf(&c, sizeof(c), pidarray, npids) + 1;
+ ctr->buf = kmalloc(ctr->bufsz, GFP_KERNEL);
+ if (!ctr->buf)
+ goto err2;
+ ctr->bufsz = pid_array_to_buf(ctr->buf, ctr->bufsz, pidarray, npids);
+
+ kfree(pidarray);
+ } else {
+ ctr->buf = 0;
+ ctr->bufsz = 0;
+ }
+ file->private_data = ctr;
+ return 0;
+
+err2:
+ kfree(pidarray);
+err1:
+ kfree(ctr);
+err0:
+ return -ENOMEM;
+}
+
+static ssize_t cgroup_tasks_read(struct cgroup *cont,
+ struct cftype *cft,
+ struct file *file, char __user *buf,
+ size_t nbytes, loff_t *ppos)
+{
+ struct ctr_struct *ctr = file->private_data;
+
+ return simple_read_from_buffer(buf, nbytes, ppos, ctr->buf, ctr->bufsz);
+}
+
+static int cgroup_tasks_release(struct inode *unused_inode,
+ struct file *file)
+{
+ struct ctr_struct *ctr;
+
+ if (file->f_mode & FMODE_READ) {
+ ctr = file->private_data;
+ kfree(ctr->buf);
+ kfree(ctr);
+ }
+ return 0;
+}
+
+/*
+ * for the common functions, 'private' gives the type of file
+ */
+static struct cftype cft_tasks = {
+ .name = "tasks",
+ .open = cgroup_tasks_open,
+ .read = cgroup_tasks_read,
+ .write = cgroup_common_file_write,
+ .release = cgroup_tasks_release,
+ .private = FILE_TASKLIST,
+};
+