| 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: <20220601021848.76943-1-zhouchengming@bytedance.com>
Date: Wed, 1 Jun 2022 10:18:48 +0800
From: Chengming Zhou <zhouchengming@...edance.com>
To: mingo@...hat.com, peterz@...radead.org, juri.lelli@...hat.com,
vincent.guittot@...aro.org, dietmar.eggemann@....com,
rostedt@...dmis.org, bsegall@...gle.com, mgorman@...e.de,
bristot@...hat.com, vschneid@...hat.com
Cc: linux-kernel@...r.kernel.org, duanxiongchun@...edance.com,
songmuchun@...edance.com, zhengqi.arch@...edance.com,
Chengming Zhou <zhouchengming@...edance.com>
Subject: [PATCH v4] sched/fair: optimize and simplify rq leaf_cfs_rq_list
We notice the rq leaf_cfs_rq_list has two problems when do bugfix
backports and some test profiling.
1. cfs_rqs under throttled subtree could be added to the list, and
make their fully decayed ancestors on the list, even though not needed.
2. #1 also make the leaf_cfs_rq_list management complex and error prone,
this is the list of related bugfix so far:
commit 31bc6aeaab1d ("sched/fair: Optimize update_blocked_averages()")
commit fe61468b2cbc ("sched/fair: Fix enqueue_task_fair warning")
commit b34cb07dde7c ("sched/fair: Fix enqueue_task_fair() warning some more")
commit 39f23ce07b93 ("sched/fair: Fix unthrottle_cfs_rq() for leaf_cfs_rq list")
commit 0258bdfaff5b ("sched/fair: Fix unfairness caused by missing load decay")
commit a7b359fc6a37 ("sched/fair: Correctly insert cfs_rq's to list on unthrottle")
commit fdaba61ef8a2 ("sched/fair: Ensure that the CFS parent is added after unthrottling")
commit 2630cde26711 ("sched/fair: Add ancestors of unthrottled undecayed cfs_rq")
commit 31bc6aeaab1d ("sched/fair: Optimize update_blocked_averages()")
delete every cfs_rq under throttled subtree from rq->leaf_cfs_rq_list,
and delete the throttled_hierarchy() test in update_blocked_averages(),
which optimized update_blocked_averages().
But those later bugfix add cfs_rqs under throttled subtree back to
rq->leaf_cfs_rq_list again, with their fully decayed ancestors, for
the integrity of rq->leaf_cfs_rq_list.
This patch takes another method, skip all cfs_rqs under throttled
hierarchy when list_add_leaf_cfs_rq(), to completely make cfs_rqs
under throttled subtree off the leaf_cfs_rq_list.
So we don't need to consider throttled related things in
enqueue_entity(), unthrottle_cfs_rq() and enqueue_task_fair(),
which simplify the code a lot. Also optimize update_blocked_averages()
since cfs_rqs under throttled hierarchy and their ancestors
won't be on the leaf_cfs_rq_list.
Signed-off-by: Chengming Zhou <zhouchengming@...edance.com>
---
v4:
- make sure the attach/detach is propagated down up to
the throttled cfs_rq. Thanks Vincent.
v3:
- fix !CONFIG_FAIR_GROUP_SCHED build error, reported by
kernel test robot <lkp@...el.com>
v2:
- move throttled_hierarchy() outside list_add_leaf_cfs_rq(),
suggested by Vincent.
---
kernel/sched/fair.c | 92 ++++++++++++++-------------------------------
1 file changed, 28 insertions(+), 64 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 77b2048a9326..b3371fa40548 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3144,6 +3144,8 @@ void reweight_task(struct task_struct *p, int prio)
load->inv_weight = sched_prio_to_wmult[prio];
}
+static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
+
#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_SMP
/*
@@ -3254,8 +3256,6 @@ static long calc_group_shares(struct cfs_rq *cfs_rq)
}
#endif /* CONFIG_SMP */
-static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
-
/*
* Recomputes the group entity based on the current state of its group
* runqueue.
@@ -4368,16 +4368,11 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
__enqueue_entity(cfs_rq, se);
se->on_rq = 1;
- /*
- * When bandwidth control is enabled, cfs might have been removed
- * because of a parent been throttled but cfs->nr_running > 1. Try to
- * add it unconditionally.
- */
- if (cfs_rq->nr_running == 1 || cfs_bandwidth_used())
- list_add_leaf_cfs_rq(cfs_rq);
-
- if (cfs_rq->nr_running == 1)
+ if (cfs_rq->nr_running == 1) {
check_enqueue_throttle(cfs_rq);
+ if (!throttled_hierarchy(cfs_rq))
+ list_add_leaf_cfs_rq(cfs_rq);
+ }
}
static void __clear_buddies_last(struct sched_entity *se)
@@ -4992,11 +4987,18 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
/* update hierarchical throttle state */
walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq);
- /* Nothing to run but something to decay (on_list)? Complete the branch */
if (!cfs_rq->load.weight) {
- if (cfs_rq->on_list)
- goto unthrottle_throttle;
- return;
+ if (!cfs_rq->on_list)
+ return;
+ /*
+ * Nothing to run but something to decay (on_list)?
+ * Complete the branch.
+ */
+ for_each_sched_entity(se) {
+ if (list_add_leaf_cfs_rq(cfs_rq_of(se)))
+ break;
+ }
+ goto unthrottle_throttle;
}
task_delta = cfs_rq->h_nr_running;
@@ -5034,31 +5036,12 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
/* end evaluation on encountering a throttled cfs_rq */
if (cfs_rq_throttled(qcfs_rq))
goto unthrottle_throttle;
-
- /*
- * One parent has been throttled and cfs_rq removed from the
- * list. Add it back to not break the leaf list.
- */
- if (throttled_hierarchy(qcfs_rq))
- list_add_leaf_cfs_rq(qcfs_rq);
}
/* At this point se is NULL and we are at root level*/
add_nr_running(rq, task_delta);
unthrottle_throttle:
- /*
- * The cfs_rq_throttled() breaks in the above iteration can result in
- * incomplete leaf list maintenance, resulting in triggering the
- * assertion below.
- */
- for_each_sched_entity(se) {
- struct cfs_rq *qcfs_rq = cfs_rq_of(se);
-
- if (list_add_leaf_cfs_rq(qcfs_rq))
- break;
- }
-
assert_list_leaf_cfs_rq(rq);
/* Determine whether we need to wake up potentially idle CPU: */
@@ -5713,13 +5696,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
/* end evaluation on encountering a throttled cfs_rq */
if (cfs_rq_throttled(cfs_rq))
goto enqueue_throttle;
-
- /*
- * One parent has been throttled and cfs_rq removed from the
- * list. Add it back to not break the leaf list.
- */
- if (throttled_hierarchy(cfs_rq))
- list_add_leaf_cfs_rq(cfs_rq);
}
/* At this point se is NULL and we are at root level*/
@@ -5743,21 +5719,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
update_overutilized_status(rq);
enqueue_throttle:
- if (cfs_bandwidth_used()) {
- /*
- * When bandwidth control is enabled; the cfs_rq_throttled()
- * breaks in the above iteration can result in incomplete
- * leaf list maintenance, resulting in triggering the assertion
- * below.
- */
- for_each_sched_entity(se) {
- cfs_rq = cfs_rq_of(se);
-
- if (list_add_leaf_cfs_rq(cfs_rq))
- break;
- }
- }
-
assert_list_leaf_cfs_rq(rq);
hrtick_update(rq);
@@ -11287,9 +11248,13 @@ static inline bool vruntime_normalized(struct task_struct *p)
*/
static void propagate_entity_cfs_rq(struct sched_entity *se)
{
- struct cfs_rq *cfs_rq;
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ if (cfs_rq_throttled(cfs_rq))
+ return;
- list_add_leaf_cfs_rq(cfs_rq_of(se));
+ if (!throttled_hierarchy(cfs_rq))
+ list_add_leaf_cfs_rq(cfs_rq);
/* Start to propagate at parent */
se = se->parent;
@@ -11297,14 +11262,13 @@ static void propagate_entity_cfs_rq(struct sched_entity *se)
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
- if (!cfs_rq_throttled(cfs_rq)){
- update_load_avg(cfs_rq, se, UPDATE_TG);
- list_add_leaf_cfs_rq(cfs_rq);
- continue;
- }
+ update_load_avg(cfs_rq, se, UPDATE_TG);
- if (list_add_leaf_cfs_rq(cfs_rq))
+ if (cfs_rq_throttled(cfs_rq))
break;
+
+ if (!throttled_hierarchy(cfs_rq))
+ list_add_leaf_cfs_rq(cfs_rq);
}
}
#else
--
2.36.1
Powered by blists - more mailing lists