| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20230223191041.577305-9-vincent.guittot@linaro.org>
Date: Thu, 23 Feb 2023 20:10:41 +0100
From: Vincent Guittot <vincent.guittot@...aro.org>
To: mingo@...hat.com, peterz@...radead.org, juri.lelli@...hat.com,
dietmar.eggemann@....com, rostedt@...dmis.org, bsegall@...gle.com,
mgorman@...e.de, bristot@...hat.com, vschneid@...hat.com,
linux-kernel@...r.kernel.org, parth@...ux.ibm.com,
lizefan.x@...edance.com, hannes@...xchg.org,
cgroups@...r.kernel.org, corbet@....net, linux-doc@...r.kernel.org
Cc: tj@...nel.org, qyousef@...alina.io, chris.hyser@...cle.com,
patrick.bellasi@...bug.net, David.Laight@...lab.com,
pjt@...gle.com, pavel@....cz, qperret@...gle.com,
tim.c.chen@...ux.intel.com, joshdon@...gle.com, timj@....org,
kprateek.nayak@....com, yu.c.chen@...el.com,
youssefesmat@...omium.org, joel@...lfernandes.org,
Vincent Guittot <vincent.guittot@...aro.org>
Subject: [PATCH v11 8/8] sched/fair: Add latency list
Add a rb tree for latency sensitive entities so we can schedule the most
sensitive one first even when it failed to preempt current at wakeup or
when it got quickly preempted by another entity of higher priority.
In order to keep fairness, the latency is used once at wakeup to get a
minimum slice and not during the following scheduling slice to prevent
long running entity to got more running time than allocated to his nice
priority.
The rb tree enables to cover the last corner case where latency
sensitive entity can't got schedule quickly after the wakeup.
Signed-off-by: Vincent Guittot <vincent.guittot@...aro.org>
Tested-by: K Prateek Nayak <kprateek.nayak@....com>
---
include/linux/sched.h | 1 +
kernel/sched/core.c | 1 +
kernel/sched/fair.c | 108 ++++++++++++++++++++++++++++++++++++++++--
kernel/sched/sched.h | 1 +
4 files changed, 108 insertions(+), 3 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 38decae3e156..41bb92be5ecc 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -548,6 +548,7 @@ struct sched_entity {
/* For load-balancing: */
struct load_weight load;
struct rb_node run_node;
+ struct rb_node latency_node;
struct list_head group_node;
unsigned int on_rq;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 093cc1af73dc..752fd364216c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4434,6 +4434,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
p->se.nr_migrations = 0;
p->se.vruntime = 0;
INIT_LIST_HEAD(&p->se.group_node);
+ RB_CLEAR_NODE(&p->se.latency_node);
#ifdef CONFIG_FAIR_GROUP_SCHED
p->se.cfs_rq = NULL;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 125a6ff53378..9fb0461197bd 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -680,7 +680,85 @@ struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
return __node_2_se(last);
}
+#endif
+/**************************************************************
+ * Scheduling class tree data structure manipulation methods:
+ * for latency
+ */
+
+static inline bool latency_before(struct sched_entity *a,
+ struct sched_entity *b)
+{
+ return (s64)(a->vruntime + a->latency_offset - b->vruntime - b->latency_offset) < 0;
+}
+
+#define __latency_node_2_se(node) \
+ rb_entry((node), struct sched_entity, latency_node)
+
+static inline bool __latency_less(struct rb_node *a, const struct rb_node *b)
+{
+ return latency_before(__latency_node_2_se(a), __latency_node_2_se(b));
+}
+
+/*
+ * Enqueue an entity into the latency rb-tree:
+ */
+static void __enqueue_latency(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+{
+
+ /* Only latency sensitive entity can be added to the list */
+ if (se->latency_offset >= 0)
+ return;
+
+ if (!RB_EMPTY_NODE(&se->latency_node))
+ return;
+
+ /*
+ * The entity is always added the latency list at wakeup.
+ * Then, a not waking up entity that is put back in the list after an
+ * execution time less than sysctl_sched_min_granularity, means that
+ * the entity has been preempted by a higher sched class or an entity
+ * with higher latency constraint. In thi case, the entity is also put
+ * back in the latency list so it gets a chance to run 1st during the
+ * next slice.
+ */
+ if (!(flags & ENQUEUE_WAKEUP)) {
+ u64 delta_exec = se->sum_exec_runtime - se->prev_sum_exec_runtime;
+
+ if (delta_exec >= sysctl_sched_min_granularity)
+ return;
+ }
+
+ rb_add_cached(&se->latency_node, &cfs_rq->latency_timeline, __latency_less);
+}
+
+/*
+ * Dequeue an entity from the latency rb-tree and return true if it was really
+ * part of the rb-tree:
+ */
+static bool __dequeue_latency(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ if (!RB_EMPTY_NODE(&se->latency_node)) {
+ rb_erase_cached(&se->latency_node, &cfs_rq->latency_timeline);
+ RB_CLEAR_NODE(&se->latency_node);
+ return true;
+ }
+
+ return false;
+}
+
+static struct sched_entity *__pick_first_latency(struct cfs_rq *cfs_rq)
+{
+ struct rb_node *left = rb_first_cached(&cfs_rq->latency_timeline);
+
+ if (!left)
+ return NULL;
+
+ return __latency_node_2_se(left);
+}
+
+#ifdef CONFIG_SCHED_DEBUG
/**************************************************************
* Scheduling class statistics methods:
*/
@@ -4758,8 +4836,10 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
check_schedstat_required();
update_stats_enqueue_fair(cfs_rq, se, flags);
check_spread(cfs_rq, se);
- if (!curr)
+ if (!curr) {
__enqueue_entity(cfs_rq, se);
+ __enqueue_latency(cfs_rq, se, flags);
+ }
se->on_rq = 1;
if (cfs_rq->nr_running == 1) {
@@ -4845,8 +4925,10 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
clear_buddies(cfs_rq, se);
- if (se != cfs_rq->curr)
+ if (se != cfs_rq->curr) {
__dequeue_entity(cfs_rq, se);
+ __dequeue_latency(cfs_rq, se);
+ }
se->on_rq = 0;
account_entity_dequeue(cfs_rq, se);
@@ -4941,6 +5023,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
*/
update_stats_wait_end_fair(cfs_rq, se);
__dequeue_entity(cfs_rq, se);
+ __dequeue_latency(cfs_rq, se);
update_load_avg(cfs_rq, se, UPDATE_TG);
}
@@ -4979,7 +5062,7 @@ static struct sched_entity *
pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
struct sched_entity *left = __pick_first_entity(cfs_rq);
- struct sched_entity *se;
+ struct sched_entity *latency, *se;
/*
* If curr is set we have to see if its left of the leftmost entity
@@ -5021,6 +5104,12 @@ pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
se = cfs_rq->last;
}
+ /* Check for latency sensitive entity waiting for running */
+ latency = __pick_first_latency(cfs_rq);
+ if (latency && (latency != se) &&
+ wakeup_preempt_entity(latency, se) < 1)
+ se = latency;
+
return se;
}
@@ -5044,6 +5133,7 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
update_stats_wait_start_fair(cfs_rq, prev);
/* Put 'current' back into the tree. */
__enqueue_entity(cfs_rq, prev);
+ __enqueue_latency(cfs_rq, prev, 0);
/* in !on_rq case, update occurred at dequeue */
update_load_avg(cfs_rq, prev, 0);
}
@@ -12222,6 +12312,7 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
void init_cfs_rq(struct cfs_rq *cfs_rq)
{
cfs_rq->tasks_timeline = RB_ROOT_CACHED;
+ cfs_rq->latency_timeline = RB_ROOT_CACHED;
u64_u32_store(cfs_rq->min_vruntime, (u64)(-(1LL << 20)));
#ifdef CONFIG_SMP
raw_spin_lock_init(&cfs_rq->removed.lock);
@@ -12529,8 +12620,19 @@ int sched_group_set_latency(struct task_group *tg, int prio)
for_each_possible_cpu(i) {
struct sched_entity *se = tg->se[i];
+ struct rq *rq = cpu_rq(i);
+ struct rq_flags rf;
+ bool queued;
+
+ rq_lock_irqsave(rq, &rf);
+ queued = __dequeue_latency(se->cfs_rq, se);
WRITE_ONCE(se->latency_offset, latency_offset);
+ if (queued)
+ __enqueue_latency(se->cfs_rq, se, ENQUEUE_WAKEUP);
+
+
+ rq_unlock_irqrestore(rq, &rf);
}
mutex_unlock(&shares_mutex);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9a2e71231083..21dd309e98a9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -570,6 +570,7 @@ struct cfs_rq {
#endif
struct rb_root_cached tasks_timeline;
+ struct rb_root_cached latency_timeline;
/*
* 'curr' points to currently running entity on this cfs_rq.
--
2.34.1
Powered by blists - more mailing lists