[RFC PATCH v2 13/17] sched: Add core wide task selection and scheduling.

From: Vineeth Remanan Pillai
Date: Tue Apr 23 2019 - 12:19:23 EST


From: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>

Instead of only selecting a local task, select a task for all SMT
siblings for every reschedule on the core (irrespective which logical
CPU does the reschedule).

NOTE: there is still potential for siblings rivalry.
NOTE: this is far too complicated; but thus far I've failed to
simplify it further.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
kernel/sched/core.c | 222 ++++++++++++++++++++++++++++++++++++++++++-
kernel/sched/sched.h | 5 +-
2 files changed, 224 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e5bdc1c4d8d7..9e6e90c6f9b9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3574,7 +3574,7 @@ static inline void schedule_debug(struct task_struct *prev)
* Pick up the highest-prio task:
*/
static inline struct task_struct *
-pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+__pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
const struct sched_class *class;
struct task_struct *p;
@@ -3619,6 +3619,220 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
BUG();
}

+#ifdef CONFIG_SCHED_CORE
+
+static inline bool cookie_match(struct task_struct *a, struct task_struct *b)
+{
+ if (is_idle_task(a) || is_idle_task(b))
+ return true;
+
+ return a->core_cookie == b->core_cookie;
+}
+
+// XXX fairness/fwd progress conditions
+static struct task_struct *
+pick_task(struct rq *rq, const struct sched_class *class, struct task_struct *max)
+{
+ struct task_struct *class_pick, *cookie_pick;
+ unsigned long cookie = 0UL;
+
+ /*
+ * We must not rely on rq->core->core_cookie here, because we fail to reset
+ * rq->core->core_cookie on new picks, such that we can detect if we need
+ * to do single vs multi rq task selection.
+ */
+
+ if (max && max->core_cookie) {
+ WARN_ON_ONCE(rq->core->core_cookie != max->core_cookie);
+ cookie = max->core_cookie;
+ }
+
+ class_pick = class->pick_task(rq);
+ if (!cookie)
+ return class_pick;
+
+ cookie_pick = sched_core_find(rq, cookie);
+ if (!class_pick)
+ return cookie_pick;
+
+ /*
+ * If class > max && class > cookie, it is the highest priority task on
+ * the core (so far) and it must be selected, otherwise we must go with
+ * the cookie pick in order to satisfy the constraint.
+ */
+ if (cpu_prio_less(cookie_pick, class_pick) && core_prio_less(max, class_pick))
+ return class_pick;
+
+ return cookie_pick;
+}
+
+static struct task_struct *
+pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+ struct task_struct *next, *max = NULL;
+ const struct sched_class *class;
+ const struct cpumask *smt_mask;
+ int i, j, cpu;
+
+ if (!sched_core_enabled(rq))
+ return __pick_next_task(rq, prev, rf);
+
+ /*
+ * If there were no {en,de}queues since we picked (IOW, the task
+ * pointers are all still valid), and we haven't scheduled the last
+ * pick yet, do so now.
+ */
+ if (rq->core->core_pick_seq == rq->core->core_task_seq &&
+ rq->core->core_pick_seq != rq->core_sched_seq) {
+ WRITE_ONCE(rq->core_sched_seq, rq->core->core_pick_seq);
+
+ next = rq->core_pick;
+ if (next != prev) {
+ put_prev_task(rq, prev);
+ set_next_task(rq, next);
+ }
+ return next;
+ }
+
+ prev->sched_class->put_prev_task(rq, prev, rf);
+ if (!rq->nr_running)
+ newidle_balance(rq, rf);
+
+ cpu = cpu_of(rq);
+ smt_mask = cpu_smt_mask(cpu);
+
+ /*
+ * core->core_task_seq, core->core_pick_seq, rq->core_sched_seq
+ *
+ * @task_seq guards the task state ({en,de}queues)
+ * @pick_seq is the @task_seq we did a selection on
+ * @sched_seq is the @pick_seq we scheduled
+ *
+ * However, preemptions can cause multiple picks on the same task set.
+ * 'Fix' this by also increasing @task_seq for every pick.
+ */
+ rq->core->core_task_seq++;
+
+ /* reset state */
+ for_each_cpu(i, smt_mask) {
+ struct rq *rq_i = cpu_rq(i);
+
+ rq_i->core_pick = NULL;
+
+ if (i != cpu)
+ update_rq_clock(rq_i);
+ }
+
+ /*
+ * Try and select tasks for each sibling in decending sched_class
+ * order.
+ */
+ for_each_class(class) {
+again:
+ for_each_cpu_wrap(i, smt_mask, cpu) {
+ struct rq *rq_i = cpu_rq(i);
+ struct task_struct *p;
+
+ if (rq_i->core_pick)
+ continue;
+
+ /*
+ * If this sibling doesn't yet have a suitable task to
+ * run; ask for the most elegible task, given the
+ * highest priority task already selected for this
+ * core.
+ */
+ p = pick_task(rq_i, class, max);
+ if (!p) {
+ /*
+ * If there weren't no cookies; we don't need
+ * to bother with the other siblings.
+ */
+ if (i == cpu && !rq->core->core_cookie)
+ goto next_class;
+
+ continue;
+ }
+
+ /*
+ * Optimize the 'normal' case where there aren't any
+ * cookies and we don't need to sync up.
+ */
+ if (i == cpu && !rq->core->core_cookie && !p->core_cookie) {
+ next = p;
+ goto done;
+ }
+
+ rq_i->core_pick = p;
+
+ /*
+ * If this new candidate is of higher priority than the
+ * previous; and they're incompatible; we need to wipe
+ * the slate and start over.
+ *
+ * NOTE: this is a linear max-filter and is thus bounded
+ * in execution time.
+ */
+ if (!max || core_prio_less(max, p)) {
+ struct task_struct *old_max = max;
+
+ rq->core->core_cookie = p->core_cookie;
+ max = p;
+
+ if (old_max && !cookie_match(old_max, p)) {
+ for_each_cpu(j, smt_mask) {
+ if (j == i)
+ continue;
+
+ cpu_rq(j)->core_pick = NULL;
+ }
+ goto again;
+ }
+ }
+ }
+next_class:;
+ }
+
+ rq->core->core_pick_seq = rq->core->core_task_seq;
+
+ /*
+ * Reschedule siblings
+ *
+ * NOTE: L1TF -- at this point we're no longer running the old task and
+ * sending an IPI (below) ensures the sibling will no longer be running
+ * their task. This ensures there is no inter-sibling overlap between
+ * non-matching user state.
+ */
+ for_each_cpu(i, smt_mask) {
+ struct rq *rq_i = cpu_rq(i);
+
+ WARN_ON_ONCE(!rq_i->core_pick);
+
+ if (i == cpu)
+ continue;
+
+ if (rq_i->curr != rq_i->core_pick)
+ resched_curr(rq_i);
+ }
+
+ rq->core_sched_seq = rq->core->core_pick_seq;
+ next = rq->core_pick;
+
+done:
+ set_next_task(rq, next);
+ return next;
+}
+
+#else /* !CONFIG_SCHED_CORE */
+
+static struct task_struct *
+pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+ return __pick_next_task(rq, prev, rf);
+}
+
+#endif /* CONFIG_SCHED_CORE */
+
/*
* __schedule() is the main scheduler function.
*
@@ -5888,7 +6102,7 @@ static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf)
/*
* pick_next_task() assumes pinned rq->lock:
*/
- next = pick_next_task(rq, &fake_task, rf);
+ next = __pick_next_task(rq, &fake_task, rf);
BUG_ON(!next);
put_prev_task(rq, next);

@@ -6344,7 +6558,11 @@ void __init sched_init(void)

#ifdef CONFIG_SCHED_CORE
rq->core = NULL;
+ rq->core_pick = NULL;
rq->core_enabled = 0;
+ rq->core_tree = RB_ROOT;
+
+ rq->core_cookie = 0UL;
#endif
}

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 16fb236eab7b..4cfde289610d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -960,11 +960,15 @@ struct rq {
#ifdef CONFIG_SCHED_CORE
/* per rq */
struct rq *core;
+ struct task_struct *core_pick;
unsigned int core_enabled;
+ unsigned int core_sched_seq;
struct rb_root core_tree;

/* shared state */
unsigned int core_task_seq;
+ unsigned int core_pick_seq;
+ unsigned long core_cookie;
#endif
};

@@ -1770,7 +1774,6 @@ static inline void put_prev_task(struct rq *rq, struct task_struct *prev)

static inline void set_next_task(struct rq *rq, struct task_struct *next)
{
- WARN_ON_ONCE(rq->curr != next);
next->sched_class->set_next_task(rq, next);
}

--
2.17.1