sched/core: Explain sleep/wakeup in a better way

There were a few questions wrt. how sleep-wakeup works. Try and explain
it more.

Requested-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 348f51b0ec92ed02e72a2060eedb03f37cd0995f..3762fe4e3a808cfc5318770896207745cbb7da2d 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -262,20 +262,9 @@ extern char ___assert_task_state[1 - 2*!!(
 #define set_task_state(tsk, state_value)                       \
        do {                                                    \
                (tsk)->task_state_change = _THIS_IP_;           \
-               smp_store_mb((tsk)->state, (state_value));              \
+               smp_store_mb((tsk)->state, (state_value));      \
        } while (0)
 
-/*
- * set_current_state() includes a barrier so that the write of current->state
- * is correctly serialised wrt the caller's subsequent test of whether to
- * actually sleep:
- *
- *     set_current_state(TASK_UNINTERRUPTIBLE);
- *     if (do_i_need_to_sleep())
- *             schedule();
- *
- * If the caller does not need such serialisation then use __set_current_state()
- */
 #define __set_current_state(state_value)                       \
        do {                                                    \
                current->task_state_change = _THIS_IP_;         \
@@ -284,11 +273,19 @@ extern char ___assert_task_state[1 - 2*!!(
 #define set_current_state(state_value)                         \
        do {                                                    \
                current->task_state_change = _THIS_IP_;         \
-               smp_store_mb(current->state, (state_value));            \
+               smp_store_mb(current->state, (state_value));    \
        } while (0)
 
 #else
 
+/*
+ * @tsk had better be current, or you get to keep the pieces.
+ *
+ * The only reason is that computing current can be more expensive than
+ * using a pointer that's already available.
+ *
+ * Therefore, see set_current_state().
+ */
 #define __set_task_state(tsk, state_value)             \
        do { (tsk)->state = (state_value); } while (0)
 #define set_task_state(tsk, state_value)               \
@@ -299,11 +296,34 @@ extern char ___assert_task_state[1 - 2*!!(
  * is correctly serialised wrt the caller's subsequent test of whether to
  * actually sleep:
  *
+ *   for (;;) {
  *     set_current_state(TASK_UNINTERRUPTIBLE);
- *     if (do_i_need_to_sleep())
- *             schedule();
+ *     if (!need_sleep)
+ *             break;
+ *
+ *     schedule();
+ *   }
+ *   __set_current_state(TASK_RUNNING);
+ *
+ * If the caller does not need such serialisation (because, for instance, the
+ * condition test and condition change and wakeup are under the same lock) then
+ * use __set_current_state().
+ *
+ * The above is typically ordered against the wakeup, which does:
+ *
+ *     need_sleep = false;
+ *     wake_up_state(p, TASK_UNINTERRUPTIBLE);
+ *
+ * Where wake_up_state() (and all other wakeup primitives) imply enough
+ * barriers to order the store of the variable against wakeup.
+ *
+ * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is,
+ * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
+ * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING).
+ *
+ * This is obviously fine, since they both store the exact same value.
  *
- * If the caller does not need such serialisation then use __set_current_state()
+ * Also see the comments of try_to_wake_up().
  */
 #define __set_current_state(state_value)               \
        do { current->state = (state_value); } while (0)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 94732d1ab00ab9d9afdebad41642e279249776cb..b8c86ba44ca9bc88c1a682e607bd6b2045e49e1d 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1995,14 +1995,15 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * @state: the mask of task states that can be woken
  * @wake_flags: wake modifier flags (WF_*)
  *
- * Put it on the run-queue if it's not already there. The "current"
- * thread is always on the run-queue (except when the actual
- * re-schedule is in progress), and as such you're allowed to do
- * the simpler "current->state = TASK_RUNNING" to mark yourself
- * runnable without the overhead of this.
- *
- * Return: %true if @p was woken up, %false if it was already running.
- * or @state didn't match @p's state.
+ * If (@state & @p->state) @p->state = TASK_RUNNING.
+ *
+ * If the task was not queued/runnable, also place it back on a runqueue.
+ *
+ * Atomic against schedule() which would dequeue a task, also see
+ * set_current_state().
+ *
+ * Return: %true if @p->state changes (an actual wakeup was done),
+ *        %false otherwise.
  */
 static int
 try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)