sched: Allow put_prev_task() to drop rq->lock

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

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0c42207890924889689909fb08524edb8dd14239..7bbe78a31ba59cbe1b5c8b12780a7e326088c6dd 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6090,7 +6090,7 @@ 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 6eae793503034f5f12369bbf1e3a9c5da79db25f..2872e15a87cdd121044a7745a90808a79883a33b 100644 (file)
--- 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 e7c27eda9f2477b6db5246c64a4847e199c4cfc8..4418c1998e6948cccc95661412110bbd2cdf1d62 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6901,7 +6901,7 @@ idle:
 /*
  * 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 54194d41035c25ba3e51cc5677d4575751c53c49..8d59de2e4a6ed1aa769e7fe64ad6b5500892e4be 100644 (file)
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -374,7 +374,7 @@ 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 f71bcbe1a00c18e6cf43233fca5e052bfc1e0f51..dbdabd76f192bd0f1dfb9fe503cd8247baab6371 100644 (file)
--- 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 304d98e712bf66a361ed8d42da47ec01368036c2..e085cffb8004244316782083eb8fd0265e098cf4 100644 (file)
--- 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 47a3d2a18a9a49d86cbb00b5bbc1c2230f079ba1..8f414018d5e0ef3ecc5095f347fa1a18a25df593 100644 (file)
--- 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;