Re: [PATCH v0.8 3/6] sched/umcg: implement UMCG syscalls

+/**
+ * umcg_update_state: atomically update umcg_task.state_ts, set new timestamp.
+ * @state_ts   - points to the state_ts member of struct umcg_task to update;
+ * @expected   - the expected value of state_ts, including the timestamp;
+ * @desired    - the desired value of state_ts, state part only;
+ * @may_fault  - whether to use normal or _nofault cmpxchg.
+ *
+ * The function is basically cmpxchg(state_ts, expected, desired), with extra
+ * code to set the timestamp in @desired.
+ */
+static int umcg_update_state(u64 __user *state_ts, u64 *expected, u64 desired,
+				bool may_fault)
+{
+	u64 curr_ts = (*expected) >> (64 - UMCG_STATE_TIMESTAMP_BITS);
+	u64 next_ts = ktime_get_ns() >> UMCG_STATE_TIMESTAMP_GRANULARITY;
+
+	/* Cut higher order bits. */
+	next_ts &= UMCG_TASK_STATE_MASK_FULL;

+	if (next_ts == curr_ts)
+		++next_ts;
+
+	/* Remove an old timestamp, if any. */
+	desired &= UMCG_TASK_STATE_MASK_FULL;
+
+	/* Set the new timestamp. */
+	desired |= (next_ts << (64 - UMCG_STATE_TIMESTAMP_BITS));
+
+	if (may_fault)
+		return cmpxchg_user_64(state_ts, expected, desired);
+
+	return cmpxchg_user_64_nofault(state_ts, expected, desired);
+}
+
+/**
+ * sys_umcg_ctl: (un)register the current task as a UMCG task.
+ * @flags:       ORed values from enum umcg_ctl_flag; see below;
+ * @self:        a pointer to struct umcg_task that describes this
+ *               task and governs the behavior of sys_umcg_wait if
+ *               registering; must be NULL if unregistering.
+ *
+ * @flags & UMCG_CTL_REGISTER: register a UMCG task:
+ *         UMCG workers:
+ *              - @flags & UMCG_CTL_WORKER
+ *              - self->state must be UMCG_TASK_BLOCKED
+ *         UMCG servers:
+ *              - !(@flags & UMCG_CTL_WORKER)
+ *              - self->state must be UMCG_TASK_RUNNING
+ *
+ *         All tasks:
+ *              - self->next_tid must be zero
+ *
+ *         If the conditions above are met, sys_umcg_ctl() immediately returns
+ *         if the registered task is a server; a worker will be added to
+ *         idle_workers_ptr, and the worker put to sleep; an idle server
+ *         from idle_server_tid_ptr will be woken, if present.
+ *
+ * @flags == UMCG_CTL_UNREGISTER: unregister a UMCG task. If the current task
+ *           is a UMCG worker, the userspace is responsible for waking its
+ *           server (before or after calling sys_umcg_ctl).
+ *
+ * Return:
+ * 0                - success
+ * -EFAULT          - failed to read @self
+ * -EINVAL          - some other error occurred
+ */
+SYSCALL_DEFINE2(umcg_ctl, u32, flags, struct umcg_task __user *, self)
+{
+	struct umcg_task ut;
+
+	if (flags == UMCG_CTL_UNREGISTER) {
+		if (self || !current->umcg_task)
+			return -EINVAL;
+
+		if (current->flags & PF_UMCG_WORKER)
+			umcg_handle_exiting_worker();
+		else
+			umcg_clear_task(current);
+
+		return 0;
+	}
+
+	if (!(flags & UMCG_CTL_REGISTER))
+		return -EINVAL;
+
+	flags &= ~UMCG_CTL_REGISTER;
+	if (flags && flags != UMCG_CTL_WORKER)
+		return -EINVAL;
+
+	if (current->umcg_task || !self)
+		return -EINVAL;
+
+	if (copy_from_user(&ut, self, sizeof(ut)))
+		return -EFAULT;
+
+	if (ut.next_tid)
+		return -EINVAL;
+
+	if (flags == UMCG_CTL_WORKER) {
+		if ((ut.state_ts & UMCG_TASK_STATE_MASK_FULL) != UMCG_TASK_BLOCKED)

+			return -EINVAL;
+
+		WRITE_ONCE(current->umcg_task, self);
+		current->flags |= PF_UMCG_WORKER;
+
+		/* Trigger umcg_handle_resuming_worker() */
+		set_tsk_thread_flag(current, TIF_NOTIFY_RESUME);
+	} else {
+		if ((ut.state_ts & UMCG_TASK_STATE_MASK_FULL) != UMCG_TASK_RUNNING)

+			return -EINVAL;
+
+		WRITE_ONCE(current->umcg_task, self);
+	}
+
+	return 0;
+}
+