From c0bc118372ddf35e190163b8ec6dbfd9f31840ca Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 29 May 2019 20:36:43 +0000
Subject: [PATCH] sched: Allow put_prev_task() to drop rq->lock
References: bnc#1155798 (CPU scheduler functional and performance backports)
Patch-mainline: v5.4-rc1
Git-commit: 5f2a45fc9e89e022233085e6f0f352eb6ff770bb
Currently the pick_next_task() loop is convoluted and ugly because of
how it can drop the rq->lock and needs to restart the picking.
For the RT/Deadline classes, it is put_prev_task() where we do
balancing, and we could do this before the picking loop. Make this
possible.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Aaron Lu <aaron.lwe@gmail.com>
Cc: mingo@kernel.org
Cc: Phil Auld <pauld@redhat.com>
Cc: Julien Desfossez <jdesfossez@digitalocean.com>
Cc: Nishanth Aravamudan <naravamudan@digitalocean.com>
Link: https://lkml.kernel.org/r/e4519f6850477ab7f3d257062796e6425ee4ba7c.1559129225.git.vpillai@digitalocean.com
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
kernel/sched/core.c | 2 +-
kernel/sched/deadline.c | 14 +++++++++++++-
kernel/sched/fair.c | 2 +-
kernel/sched/idle.c | 2 +-
kernel/sched/rt.c | 14 +++++++++++++-
kernel/sched/sched.h | 4 ++--
kernel/sched/stop_task.c | 2 +-
7 files changed, 32 insertions(+), 8 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b0ccbf6475ae..2b53d4939945 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6084,7 +6084,7 @@ static struct task_struct *__pick_migrate_task(struct rq *rq)
for_each_class(class) {
next = class->pick_next_task(rq, NULL, NULL);
if (next) {
- next->sched_class->put_prev_task(rq, next);
+ next->sched_class->put_prev_task(rq, next, NULL);
return next;
}
}
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index ea77c324f185..603118fd3bc7 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1804,13 +1804,25 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
return p;
}
-static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
+static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
{
update_curr_dl(rq);
update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1);
if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
enqueue_pushable_dl_task(rq, p);
+
+ if (rf && !on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) {
+ /*
+ * This is OK, because current is on_cpu, which avoids it being
+ * picked for load-balance and preemption/IRQs are still
+ * disabled avoiding further scheduler activity on it and we've
+ * not yet started the picking loop.
+ */
+ rq_unpin_lock(rq, rf);
+ pull_dl_task(rq);
+ rq_repin_lock(rq, rf);
+ }
}
/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 752fe22b7045..039fc2c00c31 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6914,7 +6914,7 @@ done: __maybe_unused;
/*
* Account for a descheduled task:
*/
-static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct sched_entity *se = &prev->se;
struct cfs_rq *cfs_rq;
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index f91b73653cc9..c47340435149 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -375,7 +375,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
resched_curr(rq);
}
-static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index f71bcbe1a00c..dbdabd76f192 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1592,7 +1592,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
return p;
}
-static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
+static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
{
update_curr_rt(rq);
@@ -1604,6 +1604,18 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
*/
if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
enqueue_pushable_task(rq, p);
+
+ if (rf && !on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) {
+ /*
+ * This is OK, because current is on_cpu, which avoids it being
+ * picked for load-balance and preemption/IRQs are still
+ * disabled avoiding further scheduler activity on it and we've
+ * not yet started the picking loop.
+ */
+ rq_unpin_lock(rq, rf);
+ pull_rt_task(rq);
+ rq_repin_lock(rq, rf);
+ }
}
#ifdef CONFIG_SMP
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 304d98e712bf..e085cffb8004 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1710,7 +1710,7 @@ struct sched_class {
struct task_struct * (*pick_next_task)(struct rq *rq,
struct task_struct *prev,
struct rq_flags *rf);
- void (*put_prev_task)(struct rq *rq, struct task_struct *p);
+ void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct rq_flags *rf);
void (*set_next_task)(struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
@@ -1756,7 +1756,7 @@ struct sched_class {
static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
{
WARN_ON_ONCE(rq->curr != prev);
- prev->sched_class->put_prev_task(rq, prev);
+ prev->sched_class->put_prev_task(rq, prev, NULL);
}
static inline void set_next_task(struct rq *rq, struct task_struct *next)
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 47a3d2a18a9a..8f414018d5e0 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -59,7 +59,7 @@ static void yield_task_stop(struct rq *rq)
BUG(); /* the stop task should never yield, its pointless. */
}
-static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct task_struct *curr = rq->curr;
u64 delta_exec;