[PATCH] sched/fair: core vruntime comparison

[Aaron Lu]

This patch provides a vruntime based way to compare two cfs task's
priority, be it on the same cpu or different threads of the same core.

When the two tasks are on the same CPU, we just need to find a common
cfs_rq both sched_entities are on and then do the comparison.

When the two tasks are on differen threads of the same core, each thread
will choose the next task to run the usual way and then the root level
sched entities which the two tasks belong to will be used to decide
which task runs next core wide.

An illustration for the cross CPU case:

   cpu0         cpu1
 /   |  \     /   |  \
se1 se2 se3  se4 se5 se6
    /  \            /   \
  se21 se22       se61  se62
  (A)                    /
                       se621
                        (B)

Assume CPU0 and CPU1 are smt siblings and cpu0 has decided task A to
run next and cpu1 has decided task B to run next. To compare priority
of task A and B, we compare priority of se2 and se6. Whose vruntime is
smaller, who wins.

To make this work, the root level sched entities' vruntime of the two
threads must be directly comparable. So a new core wide cfs_rq
min_vruntime is introduced to serve the purpose of normalizing these
root level sched entities' vruntime.

All sub cfs_rqs and sched entities are not interesting in cross cpu
priority comparison as they will only participate in the usual cpu local
schedule decision so no need to normalize their vruntimes.

Signed-off-by: Aaron Lu <ziqian.lzq@xxxxxxxxxx>
---
 kernel/sched/core.c  |  24 ++++------
 kernel/sched/fair.c  | 101 ++++++++++++++++++++++++++++++++++++++++++-
 kernel/sched/sched.h |   3 ++
 3 files changed, 111 insertions(+), 17 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5f322922f5ae..d6c8c76cb07a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -119,19 +119,8 @@ static inline bool prio_less(struct task_struct *a, struct task_struct *b)
 	if (pa == -1) /* dl_prio() doesn't work because of stop_class above */
 		return !dl_time_before(a->dl.deadline, b->dl.deadline);
 
-	if (pa == MAX_RT_PRIO + MAX_NICE)  { /* fair */
-		u64 vruntime = b->se.vruntime;
-
-		/*
-		 * Normalize the vruntime if tasks are in different cpus.
-		 */
-		if (task_cpu(a) != task_cpu(b)) {
-			vruntime -= task_cfs_rq(b)->min_vruntime;
-			vruntime += task_cfs_rq(a)->min_vruntime;
-		}
-
-		return !((s64)(a->se.vruntime - vruntime) <= 0);
-	}
+	if (pa == MAX_RT_PRIO + MAX_NICE) /* fair */
+		return cfs_prio_less(a, b);
 
 	return false;
 }
@@ -291,8 +280,13 @@ static int __sched_core_stopper(void *data)
 	}
 
 	for_each_online_cpu(cpu) {
-		if (!enabled || (enabled && cpumask_weight(cpu_smt_mask(cpu)) >= 2))
-			cpu_rq(cpu)->core_enabled = enabled;
+		if (!enabled || (enabled && cpumask_weight(cpu_smt_mask(cpu)) >= 2)) {
+			struct rq *rq = cpu_rq(cpu);
+
+			rq->core_enabled = enabled;
+			if (rq->core == rq)
+				sched_core_adjust_se_vruntime(cpu);
+		}
 	}
 
 	return 0;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d99ea6ee7af2..7eecf590d6c0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -449,9 +449,103 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 
 #endif	/* CONFIG_FAIR_GROUP_SCHED */
 
+static inline struct cfs_rq *root_cfs_rq(struct cfs_rq *cfs_rq)
+{
+	return &rq_of(cfs_rq)->cfs;
+}
+
+static inline bool is_root_cfs_rq(struct cfs_rq *cfs_rq)
+{
+	return cfs_rq == root_cfs_rq(cfs_rq);
+}
+
+static inline struct cfs_rq *core_cfs_rq(struct cfs_rq *cfs_rq)
+{
+	return &rq_of(cfs_rq)->core->cfs;
+}
+
 static inline u64 cfs_rq_min_vruntime(struct cfs_rq *cfs_rq)
 {
-	return cfs_rq->min_vruntime;
+	if (!sched_core_enabled(rq_of(cfs_rq)) || !is_root_cfs_rq(cfs_rq))
+		return cfs_rq->min_vruntime;
+
+	return core_cfs_rq(cfs_rq)->min_vruntime;
+}
+
+bool cfs_prio_less(struct task_struct *a, struct task_struct *b)
+{
+	struct sched_entity *sea = &a->se;
+	struct sched_entity *seb = &b->se;
+	bool samecpu = task_cpu(a) == task_cpu(b);
+	s64 delta;
+
+	if (samecpu) {
+		/* vruntime is per cfs_rq */
+		while (!is_same_group(sea, seb)) {
+			int sea_depth = sea->depth;
+			int seb_depth = seb->depth;
+
+			if (sea_depth >= seb_depth)
+				sea = parent_entity(sea);
+			if (sea_depth <= seb_depth)
+				seb = parent_entity(seb);
+		}
+
+		delta = (s64)(sea->vruntime - seb->vruntime);
+		goto out;
+	}
+
+	/* crosscpu: compare root level se's vruntime to decide priority */
+	while (sea->parent)
+		sea = sea->parent;
+	while (seb->parent)
+		seb = seb->parent;
+	delta = (s64)(sea->vruntime - seb->vruntime);
+
+out:
+	return delta > 0;
+}
+
+/*
+ * This is called in stop machine context so no need to take the rq lock.
+ *
+ * Core scheduling is going to be enabled and the root level sched entities
+ * of both siblings will use cfs_rq->min_vruntime as the common cfs_rq
+ * min_vruntime, so it's necessary to normalize vruntime of existing root
+ * level sched entities in sibling_cfs_rq.
+ *
+ * Update of sibling_cfs_rq's min_vruntime isn't necessary as we will be
+ * only using cfs_rq->min_vruntime during the entire run of core scheduling.
+ */
+void sched_core_adjust_se_vruntime(int cpu)
+{
+	int i;
+
+	for_each_cpu(i, cpu_smt_mask(cpu)) {
+		struct cfs_rq *cfs_rq, *sibling_cfs_rq;
+		struct sched_entity *se, *next;
+		s64 delta;
+
+		if (i == cpu)
+			continue;
+
+		sibling_cfs_rq = &cpu_rq(i)->cfs;
+		if (!sibling_cfs_rq->nr_running)
+			continue;
+
+		cfs_rq = &cpu_rq(cpu)->cfs;
+		delta = cfs_rq->min_vruntime - sibling_cfs_rq->min_vruntime;
+		/*
+		 * XXX Malicious user can create a ton of runnable tasks in root
+		 * sibling_cfs_rq and cause the below vruntime normalization
+		 * potentially taking a long time.
+		 */
+		rbtree_postorder_for_each_entry_safe(se, next,
+				&sibling_cfs_rq->tasks_timeline.rb_root,
+				run_node) {
+			se->vruntime += delta;
+		}
+	}
 }
 
 static __always_inline
@@ -509,8 +603,11 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
 			vruntime = min_vruntime(vruntime, se->vruntime);
 	}
 
+	if (sched_core_enabled(rq_of(cfs_rq)) && is_root_cfs_rq(cfs_rq))
+		cfs_rq = core_cfs_rq(cfs_rq);
+
 	/* ensure we never gain time by being placed backwards. */
-	cfs_rq->min_vruntime = max_vruntime(cfs_rq_min_vruntime(cfs_rq), vruntime);
+	cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime);
 #ifndef CONFIG_64BIT
 	smp_wmb();
 	cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 50a5675e941a..24bae760f764 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2594,3 +2594,6 @@ static inline void membarrier_switch_mm(struct rq *rq,
 {
 }
 #endif
+
+bool cfs_prio_less(struct task_struct *a, struct task_struct *b);
+void sched_core_adjust_se_vruntime(int cpu);
-- 
2.19.1.3.ge56e4f7