| 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: <20230308100414.37114-1-jiahao.os@bytedance.com>
Date: Wed, 8 Mar 2023 18:04:13 +0800
From: Hao Jia <jiahao.os@...edance.com>
To: mingo@...hat.com, peterz@...radead.org, mingo@...nel.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,
mgorman@...hsingularity.net
Cc: linux-kernel@...r.kernel.org, Hao Jia <jiahao.os@...edance.com>
Subject: [PATCH] sched/core: Minor optimize pick_next_task() when core-sched enable
If core-sched is enabled, sometimes we will traverse each CPU on the core
to find the highest priority task 'max' on the entire core, and then try
and find a runnable task that matches @max.
But in the following case, we choose the runnable task is not the best.
core max: task2 (cookie 0)
rq0 rq1
task0(cookie non-zero) task2(cookie 0)
task1(cookie 0)
task3(cookie 0)
...
pick-task: idle pick-task: task2
CPU0 and CPU1 are two CPUs on the same core, task0 and task2 are the
highest priority tasks on rq0 and rq1 respectively, task2 is @max
on the entire core.
In the case that 'max' has a zero cookie, instead of continuing to
search for a runnable task on rq0 that matches @max's cookie, we
choose idle for rq0 directly.
At this time, it is obviously better to choose task1 to run for rq0,
which will increase the CPU utilization.
Therefore, we queue tasks with zero cookies in core_tree, and record
the number of non-zero cookie tasks of each rq to detect the status
of the sched-core.
Signed-off-by: Hao Jia <jiahao.os@...edance.com>
---
kernel/sched/core.c | 29 +++++++++++++++--------------
kernel/sched/core_sched.c | 9 ++++-----
kernel/sched/sched.h | 1 +
3 files changed, 20 insertions(+), 19 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index af017e038b48..765cd14c52e1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -236,8 +236,8 @@ void sched_core_enqueue(struct rq *rq, struct task_struct *p)
{
rq->core->core_task_seq++;
- if (!p->core_cookie)
- return;
+ if (p->core_cookie)
+ rq->cookied_count++;
rb_add(&p->core_node, &rq->core_tree, rb_sched_core_less);
}
@@ -246,11 +246,16 @@ void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags)
{
rq->core->core_task_seq++;
+ if (p->core_cookie)
+ rq->cookied_count--;
+
if (sched_core_enqueued(p)) {
rb_erase(&p->core_node, &rq->core_tree);
RB_CLEAR_NODE(&p->core_node);
}
+ if (!sched_core_enabled(rq))
+ return;
/*
* Migrating the last task off the cpu, with the cpu in forced idle
* state. Reschedule to create an accounting edge for forced idle,
@@ -370,7 +375,7 @@ static void sched_core_assert_empty(void)
int cpu;
for_each_possible_cpu(cpu)
- WARN_ON_ONCE(!RB_EMPTY_ROOT(&cpu_rq(cpu)->core_tree));
+ WARN_ON_ONCE(cpu_rq(cpu)->cookied_count);
}
static void __sched_core_enable(void)
@@ -2061,14 +2066,12 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
uclamp_rq_inc(rq, p);
p->sched_class->enqueue_task(rq, p, flags);
- if (sched_core_enabled(rq))
- sched_core_enqueue(rq, p);
+ sched_core_enqueue(rq, p);
}
static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
{
- if (sched_core_enabled(rq))
- sched_core_dequeue(rq, p, flags);
+ sched_core_dequeue(rq, p, flags);
if (!(flags & DEQUEUE_NOCLOCK))
update_rq_clock(rq);
@@ -6126,13 +6129,8 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
rq_i = cpu_rq(i);
p = rq_i->core_pick;
- if (!cookie_equals(p, cookie)) {
- p = NULL;
- if (cookie)
- p = sched_core_find(rq_i, cookie);
- if (!p)
- p = idle_sched_class.pick_task(rq_i);
- }
+ if (!cookie_equals(p, cookie))
+ p = sched_core_find(rq_i, cookie);
rq_i->core_pick = p;
@@ -6333,6 +6331,7 @@ static void sched_core_cpu_starting(unsigned int cpu)
sched_core_lock(cpu, &flags);
WARN_ON_ONCE(rq->core != rq);
+ WARN_ON_ONCE(rq->cookied_count);
/* if we're the first, we'll be our own leader */
if (cpumask_weight(smt_mask) == 1)
@@ -6425,6 +6424,7 @@ static inline void sched_core_cpu_dying(unsigned int cpu)
{
struct rq *rq = cpu_rq(cpu);
+ WARN_ON_ONCE(rq->cookied_count);
if (rq->core != rq)
rq->core = rq;
}
@@ -9917,6 +9917,7 @@ void __init sched_init(void)
rq->core = rq;
rq->core_pick = NULL;
rq->core_enabled = 0;
+ rq->cookied_count = 0;
rq->core_tree = RB_ROOT;
rq->core_forceidle_count = 0;
rq->core_forceidle_occupation = 0;
diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c
index a57fd8f27498..70f424abcc2b 100644
--- a/kernel/sched/core_sched.c
+++ b/kernel/sched/core_sched.c
@@ -56,6 +56,7 @@ static unsigned long sched_core_update_cookie(struct task_struct *p,
unsigned long old_cookie;
struct rq_flags rf;
struct rq *rq;
+ bool enqueued;
rq = task_rq_lock(p, &rf);
@@ -67,16 +68,14 @@ static unsigned long sched_core_update_cookie(struct task_struct *p,
*/
SCHED_WARN_ON((p->core_cookie || cookie) && !sched_core_enabled(rq));
- if (sched_core_enqueued(p))
+ enqueued = task_on_rq_queued(p);
+ if (enqueued)
sched_core_dequeue(rq, p, DEQUEUE_SAVE);
old_cookie = p->core_cookie;
p->core_cookie = cookie;
- /*
- * Consider the cases: !prev_cookie and !cookie.
- */
- if (cookie && task_on_rq_queued(p))
+ if (enqueued)
sched_core_enqueue(rq, p);
/*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 3e8df6d31c1e..f5a0ee7fccae 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1148,6 +1148,7 @@ struct rq {
unsigned int core_task_seq;
unsigned int core_pick_seq;
unsigned long core_cookie;
+ unsigned int cookied_count;
unsigned int core_forceidle_count;
unsigned int core_forceidle_seq;
unsigned int core_forceidle_occupation;
--
2.11.0
Powered by blists - more mailing lists