From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
To: Nishanth Aravamudan <naravamudan@digitalocean.com>,
Julien Desfossez <jdesfossez@digitalocean.com>,
Peter Zijlstra <peterz@infradead.org>,
Tim Chen <tim.c.chen@linux.intel.com>,
Vineeth Pillai <viremana@linux.microsoft.com>,
Aaron Lu <aaron.lwe@gmail.com>,
Aubrey Li <aubrey.intel@gmail.com>,
tglx@linutronix.de, linux-kernel@vger.kernel.org
Cc: mingo@kernel.org, torvalds@linux-foundation.org,
fweisbec@gmail.com, keescook@chromium.org, kerrnel@google.com,
Phil Auld <pauld@redhat.com>,
Valentin Schneider <valentin.schneider@arm.com>,
Mel Gorman <mgorman@techsingularity.net>,
Pawan Gupta <pawan.kumar.gupta@linux.intel.com>,
Paolo Bonzini <pbonzini@redhat.com>,
joel@joelfernandes.org, vineeth@bitbyteword.org,
Chen Yu <yu.c.chen@intel.com>,
Christian Brauner <christian.brauner@ubuntu.com>,
Agata Gruza <agata.gruza@intel.com>,
Antonio Gomez Iglesias <antonio.gomez.iglesias@intel.com>,
graf@amazon.com, konrad.wilk@oracle.com, dfaggioli@suse.com,
pjt@google.com, rostedt@goodmis.org, derkling@google.com,
benbjiang@tencent.com,
Alexandre Chartre <alexandre.chartre@oracle.com>,
James.Bottomley@hansenpartnership.com, OWeisse@umich.edu,
Dhaval Giani <dhaval.giani@oracle.com>,
Junaid Shahid <junaids@google.com>,
jsbarnes@google.com, chris.hyser@oracle.com,
Ben Segall <bsegall@google.com>, Josh Don <joshdon@google.com>,
Hao Luo <haoluo@google.com>,
Tom Lendacky <thomas.lendacky@amd.com>,
"Paul E . McKenney" <paulmck@kernel.org>,
Aubrey Li <aubrey.li@linux.intel.com>,
Tim Chen <tim.c.chen@intel.com>
Subject: [PATCH -tip 13/32] sched: Trivial forced-newidle balancer
Date: Tue, 17 Nov 2020 18:19:43 -0500 [thread overview]
Message-ID: <20201117232003.3580179-14-joel@joelfernandes.org> (raw)
In-Reply-To: <20201117232003.3580179-1-joel@joelfernandes.org>
From: Peter Zijlstra <peterz@infradead.org>
When a sibling is forced-idle to match the core-cookie; search for
matching tasks to fill the core.
rcu_read_unlock() can incur an infrequent deadlock in
sched_core_balance(). Fix this by using the RCU-sched flavor instead.
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: Julien Desfossez <jdesfossez@digitalocean.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
---
include/linux/sched.h | 1 +
kernel/sched/core.c | 130 +++++++++++++++++++++++++++++++++++++++++-
kernel/sched/idle.c | 1 +
kernel/sched/sched.h | 6 ++
4 files changed, 137 insertions(+), 1 deletion(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 344499ab29f2..7efce9c9d9cf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -688,6 +688,7 @@ struct task_struct {
#ifdef CONFIG_SCHED_CORE
struct rb_node core_node;
unsigned long core_cookie;
+ unsigned int core_occupation;
#endif
#ifdef CONFIG_CGROUP_SCHED
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 12e8e6627ab3..3b373b592680 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -202,6 +202,21 @@ static struct task_struct *sched_core_find(struct rq *rq, unsigned long cookie)
return match;
}
+static struct task_struct *sched_core_next(struct task_struct *p, unsigned long cookie)
+{
+ struct rb_node *node = &p->core_node;
+
+ node = rb_next(node);
+ if (!node)
+ return NULL;
+
+ p = container_of(node, struct task_struct, core_node);
+ if (p->core_cookie != cookie)
+ return NULL;
+
+ return p;
+}
+
/*
* The static-key + stop-machine variable are needed such that:
*
@@ -5134,8 +5149,8 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
const struct sched_class *class;
const struct cpumask *smt_mask;
bool fi_before = false;
+ int i, j, cpu, occ = 0;
bool need_sync;
- int i, j, cpu;
if (!sched_core_enabled(rq))
return __pick_next_task(rq, prev, rf);
@@ -5260,6 +5275,9 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
if (!p)
continue;
+ if (!is_task_rq_idle(p))
+ occ++;
+
rq_i->core_pick = p;
/*
@@ -5285,6 +5303,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
cpu_rq(j)->core_pick = NULL;
}
+ occ = 1;
goto again;
}
}
@@ -5324,6 +5343,8 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
rq_i->core->core_forceidle = true;
}
+ rq_i->core_pick->core_occupation = occ;
+
if (i == cpu) {
rq_i->core_pick = NULL;
continue;
@@ -5353,6 +5374,113 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
return next;
}
+static bool try_steal_cookie(int this, int that)
+{
+ struct rq *dst = cpu_rq(this), *src = cpu_rq(that);
+ struct task_struct *p;
+ unsigned long cookie;
+ bool success = false;
+
+ local_irq_disable();
+ double_rq_lock(dst, src);
+
+ cookie = dst->core->core_cookie;
+ if (!cookie)
+ goto unlock;
+
+ if (dst->curr != dst->idle)
+ goto unlock;
+
+ p = sched_core_find(src, cookie);
+ if (p == src->idle)
+ goto unlock;
+
+ do {
+ if (p == src->core_pick || p == src->curr)
+ goto next;
+
+ if (!cpumask_test_cpu(this, &p->cpus_mask))
+ goto next;
+
+ if (p->core_occupation > dst->idle->core_occupation)
+ goto next;
+
+ p->on_rq = TASK_ON_RQ_MIGRATING;
+ deactivate_task(src, p, 0);
+ set_task_cpu(p, this);
+ activate_task(dst, p, 0);
+ p->on_rq = TASK_ON_RQ_QUEUED;
+
+ resched_curr(dst);
+
+ success = true;
+ break;
+
+next:
+ p = sched_core_next(p, cookie);
+ } while (p);
+
+unlock:
+ double_rq_unlock(dst, src);
+ local_irq_enable();
+
+ return success;
+}
+
+static bool steal_cookie_task(int cpu, struct sched_domain *sd)
+{
+ int i;
+
+ for_each_cpu_wrap(i, sched_domain_span(sd), cpu) {
+ if (i == cpu)
+ continue;
+
+ if (need_resched())
+ break;
+
+ if (try_steal_cookie(cpu, i))
+ return true;
+ }
+
+ return false;
+}
+
+static void sched_core_balance(struct rq *rq)
+{
+ struct sched_domain *sd;
+ int cpu = cpu_of(rq);
+
+ preempt_disable();
+ rcu_read_lock();
+ raw_spin_unlock_irq(rq_lockp(rq));
+ for_each_domain(cpu, sd) {
+ if (need_resched())
+ break;
+
+ if (steal_cookie_task(cpu, sd))
+ break;
+ }
+ raw_spin_lock_irq(rq_lockp(rq));
+ rcu_read_unlock();
+ preempt_enable();
+}
+
+static DEFINE_PER_CPU(struct callback_head, core_balance_head);
+
+void queue_core_balance(struct rq *rq)
+{
+ if (!sched_core_enabled(rq))
+ return;
+
+ if (!rq->core->core_cookie)
+ return;
+
+ if (!rq->nr_running) /* not forced idle */
+ return;
+
+ queue_balance_callback(rq, &per_cpu(core_balance_head, rq->cpu), sched_core_balance);
+}
+
static inline void sched_core_cpu_starting(unsigned int cpu)
{
const struct cpumask *smt_mask = cpu_smt_mask(cpu);
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 33864193a2f9..8bdb214eb78f 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -404,6 +404,7 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir
{
update_idle_core(rq);
schedstat_inc(rq->sched_goidle);
+ queue_core_balance(rq);
}
#ifdef CONFIG_SMP
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d934cc51acf1..e72942a9ee11 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1135,6 +1135,8 @@ static inline raw_spinlock_t *rq_lockp(struct rq *rq)
bool cfs_prio_less(struct task_struct *a, struct task_struct *b);
+extern void queue_core_balance(struct rq *rq);
+
#else /* !CONFIG_SCHED_CORE */
static inline bool sched_core_enabled(struct rq *rq)
@@ -1147,6 +1149,10 @@ static inline raw_spinlock_t *rq_lockp(struct rq *rq)
return &rq->__lock;
}
+static inline void queue_core_balance(struct rq *rq)
+{
+}
+
#endif /* CONFIG_SCHED_CORE */
#ifdef CONFIG_SCHED_SMT
--
2.29.2.299.gdc1121823c-goog
next prev parent reply other threads:[~2020-11-17 23:22 UTC|newest]
Thread overview: 150+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-17 23:19 [PATCH -tip 00/32] Core scheduling (v9) Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 01/32] sched: Wrap rq::lock access Joel Fernandes (Google)
2020-11-19 23:31 ` Singh, Balbir
2020-11-20 16:55 ` Joel Fernandes
2020-11-22 8:52 ` Balbir Singh
2020-11-17 23:19 ` [PATCH -tip 02/32] sched: Introduce sched_class::pick_task() Joel Fernandes (Google)
2020-11-19 23:56 ` Singh, Balbir
2020-11-20 16:58 ` Joel Fernandes
2020-11-25 23:19 ` Balbir Singh
2020-11-25 16:28 ` Vincent Guittot
2020-11-26 9:07 ` Peter Zijlstra
2020-11-26 10:17 ` Vincent Guittot
2020-11-26 12:40 ` Peter Zijlstra
2020-11-17 23:19 ` [PATCH -tip 03/32] sched/fair: Fix pick_task_fair crashes due to empty rbtree Joel Fernandes (Google)
2020-11-20 10:15 ` Singh, Balbir
2020-11-20 18:11 ` Vineeth Pillai
2020-11-23 22:31 ` Balbir Singh
2020-11-24 8:31 ` Peter Zijlstra
2020-11-17 23:19 ` [PATCH -tip 04/32] sched: Core-wide rq->lock Joel Fernandes (Google)
2020-11-22 9:11 ` Balbir Singh
2020-11-24 8:16 ` Peter Zijlstra
2020-11-26 0:35 ` Balbir Singh
2020-11-17 23:19 ` [PATCH -tip 05/32] sched/fair: Add a few assertions Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 06/32] sched: Basic tracking of matching tasks Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 07/32] sched: Add core wide task selection and scheduling Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 08/32] sched/fair: Fix forced idle sibling starvation corner case Joel Fernandes (Google)
2020-11-22 10:35 ` Balbir Singh
2020-11-17 23:19 ` [PATCH -tip 09/32] sched/fair: Snapshot the min_vruntime of CPUs on force idle Joel Fernandes (Google)
2020-11-22 11:44 ` Balbir Singh
2020-11-23 12:31 ` Vineeth Pillai
2020-11-23 23:31 ` Balbir Singh
2020-11-24 9:09 ` Peter Zijlstra
2020-11-25 23:17 ` Balbir Singh
2020-11-26 8:23 ` Peter Zijlstra
2020-11-17 23:19 ` [PATCH -tip 10/32] sched: Fix priority inversion of cookied task with sibling Joel Fernandes (Google)
2020-11-22 22:41 ` Balbir Singh
2020-11-24 18:30 ` Joel Fernandes
2020-11-25 23:05 ` Balbir Singh
2020-11-26 8:29 ` Peter Zijlstra
2020-11-26 22:27 ` Balbir Singh
2020-12-01 17:49 ` Joel Fernandes
2020-11-17 23:19 ` [PATCH -tip 11/32] sched: Enqueue task into core queue only after vruntime is updated Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 12/32] sched: Simplify the core pick loop for optimized case Joel Fernandes (Google)
2020-11-24 12:04 ` Peter Zijlstra
2020-11-24 17:04 ` Joel Fernandes
2020-11-25 8:37 ` Peter Zijlstra
2020-11-17 23:19 ` Joel Fernandes (Google) [this message]
2020-11-23 4:38 ` [PATCH -tip 13/32] sched: Trivial forced-newidle balancer Balbir Singh
2020-11-23 15:07 ` Li, Aubrey
2020-11-23 23:35 ` Balbir Singh
2020-11-24 0:32 ` Li, Aubrey
2020-11-25 21:28 ` Balbir Singh
2020-11-17 23:19 ` [PATCH -tip 14/32] sched: migration changes for core scheduling Joel Fernandes (Google)
2020-11-22 23:54 ` Balbir Singh
2020-11-23 4:36 ` Li, Aubrey
2020-11-24 15:42 ` Peter Zijlstra
2020-11-25 3:12 ` Li, Aubrey
2020-11-25 22:57 ` Balbir Singh
2020-11-26 3:20 ` Li, Aubrey
2020-11-26 8:32 ` Balbir Singh
2020-11-26 9:26 ` Li, Aubrey
2020-11-30 9:33 ` Balbir Singh
2020-11-30 12:29 ` Li, Aubrey
2020-12-02 14:09 ` Li, Aubrey
2020-12-03 1:06 ` Li, Aubrey
2020-11-30 10:35 ` Vincent Guittot
2020-11-30 12:32 ` Li, Aubrey
2020-11-17 23:19 ` [PATCH -tip 15/32] sched: Improve snapshotting of min_vruntime for CGroups Joel Fernandes (Google)
2020-11-24 10:27 ` Peter Zijlstra
2020-11-24 17:07 ` Joel Fernandes
2020-11-25 8:41 ` Peter Zijlstra
2020-11-24 10:41 ` Peter Zijlstra
2020-11-17 23:19 ` [PATCH -tip 16/32] irq_work: Cleanup Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 17/32] arch/x86: Add a new TIF flag for untrusted tasks Joel Fernandes (Google)
2020-11-23 5:18 ` Balbir Singh
2020-11-17 23:19 ` [PATCH -tip 18/32] kernel/entry: Add support for core-wide protection of kernel-mode Joel Fernandes (Google)
2020-11-24 16:09 ` Peter Zijlstra
2020-11-24 17:52 ` Joel Fernandes
2020-11-25 9:37 ` Peter Zijlstra
2020-12-01 17:55 ` Joel Fernandes
2020-11-26 5:37 ` Balbir Singh
2020-11-17 23:19 ` [PATCH -tip 19/32] entry/idle: Enter and exit kernel protection during idle entry and exit Joel Fernandes (Google)
2020-11-24 16:13 ` Peter Zijlstra
2020-11-24 18:03 ` Joel Fernandes
2020-11-25 8:49 ` Peter Zijlstra
2020-12-01 18:24 ` Joel Fernandes
2020-11-17 23:19 ` [PATCH -tip 20/32] entry/kvm: Protect the kernel when entering from guest Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 21/32] sched: CGroup tagging interface for core scheduling Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 22/32] sched: Split the cookie and setup per-task cookie on fork Joel Fernandes (Google)
2020-11-25 11:07 ` Peter Zijlstra
2020-12-01 18:56 ` Joel Fernandes
2020-11-25 11:10 ` Peter Zijlstra
2020-12-01 19:20 ` Joel Fernandes
2020-12-01 19:34 ` Peter Zijlstra
2020-12-02 6:36 ` Josh Don
2020-12-02 7:54 ` Peter Zijlstra
2020-12-04 0:20 ` Josh Don
2020-12-06 17:49 ` Joel Fernandes
2020-11-25 11:11 ` Peter Zijlstra
2020-12-01 19:16 ` Joel Fernandes
2020-11-25 11:15 ` Peter Zijlstra
2020-12-01 19:11 ` Joel Fernandes
2020-12-01 19:20 ` Peter Zijlstra
2020-12-06 18:15 ` Joel Fernandes
2020-11-25 12:54 ` Peter Zijlstra
2020-12-01 18:38 ` Joel Fernandes
2020-11-25 13:03 ` Peter Zijlstra
2020-12-01 18:52 ` Joel Fernandes
2020-11-30 23:05 ` Balbir Singh
2020-11-17 23:19 ` [PATCH -tip 23/32] sched: Add a per-thread core scheduling interface Joel Fernandes (Google)
2020-11-25 13:08 ` Peter Zijlstra
2020-12-01 19:36 ` Joel Fernandes
2020-12-02 21:47 ` Chris Hyser
2020-12-02 23:13 ` chris hyser
2020-12-06 17:34 ` Joel Fernandes
2020-12-07 21:48 ` chris hyser
2020-12-09 18:52 ` Chris Hyser
2020-12-14 19:31 ` Joel Fernandes
2020-12-14 19:44 ` chris hyser
2020-12-14 23:25 ` Joel Fernandes
2020-12-15 14:56 ` chris hyser
2020-12-15 16:23 ` chris hyser
2020-12-15 18:13 ` Dhaval Giani
2020-12-16 0:35 ` Joel Fernandes
2020-11-17 23:19 ` [PATCH -tip 24/32] sched: Release references to the per-task cookie on exit Joel Fernandes (Google)
2020-11-25 13:03 ` Peter Zijlstra
2020-11-17 23:19 ` [PATCH -tip 25/32] sched: Refactor core cookie into struct Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 26/32] sched: Add a second-level tag for nested CGroup usecase Joel Fernandes (Google)
2020-11-25 13:42 ` Peter Zijlstra
2020-11-30 23:10 ` Balbir Singh
2020-12-01 20:08 ` Joel Fernandes
2020-12-02 6:18 ` Josh Don
2020-12-02 8:02 ` Peter Zijlstra
2020-12-02 18:53 ` Tejun Heo
2020-12-04 0:51 ` Josh Don
2020-12-04 15:45 ` Tejun Heo
2020-11-17 23:19 ` [PATCH -tip 27/32] sched/debug: Add CGroup node for printing group cookie if SCHED_DEBUG Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 28/32] kselftest: Add tests for core-sched interface Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 29/32] sched: Move core-scheduler interfacing code to a new file Joel Fernandes (Google)
2020-11-17 23:20 ` [PATCH -tip 30/32] Documentation: Add core scheduling documentation Joel Fernandes (Google)
2020-11-17 23:20 ` [PATCH -tip 31/32] sched: Add a coresched command line option Joel Fernandes (Google)
2020-11-19 23:39 ` Randy Dunlap
2020-11-25 13:45 ` Peter Zijlstra
2020-11-26 0:11 ` Balbir Singh
2020-11-17 23:20 ` [PATCH -tip 32/32] sched: Debug bits Joel Fernandes (Google)
2020-12-01 0:21 ` Balbir Singh
2021-01-15 15:10 ` Joel Fernandes
2020-11-24 11:48 ` [PATCH -tip 00/32] Core scheduling (v9) Vincent Guittot
2020-11-24 15:08 ` Joel Fernandes
2020-12-03 6:16 ` Ning, Hongyu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20201117232003.3580179-14-joel@joelfernandes.org \
--to=joel@joelfernandes.org \
--cc=James.Bottomley@hansenpartnership.com \
--cc=OWeisse@umich.edu \
--cc=aaron.lwe@gmail.com \
--cc=agata.gruza@intel.com \
--cc=alexandre.chartre@oracle.com \
--cc=antonio.gomez.iglesias@intel.com \
--cc=aubrey.intel@gmail.com \
--cc=aubrey.li@linux.intel.com \
--cc=benbjiang@tencent.com \
--cc=bsegall@google.com \
--cc=chris.hyser@oracle.com \
--cc=christian.brauner@ubuntu.com \
--cc=derkling@google.com \
--cc=dfaggioli@suse.com \
--cc=dhaval.giani@oracle.com \
--cc=fweisbec@gmail.com \
--cc=graf@amazon.com \
--cc=haoluo@google.com \
--cc=jdesfossez@digitalocean.com \
--cc=joshdon@google.com \
--cc=jsbarnes@google.com \
--cc=junaids@google.com \
--cc=keescook@chromium.org \
--cc=kerrnel@google.com \
--cc=konrad.wilk@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mgorman@techsingularity.net \
--cc=mingo@kernel.org \
--cc=naravamudan@digitalocean.com \
--cc=pauld@redhat.com \
--cc=paulmck@kernel.org \
--cc=pawan.kumar.gupta@linux.intel.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=pjt@google.com \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=thomas.lendacky@amd.com \
--cc=tim.c.chen@intel.com \
--cc=tim.c.chen@linux.intel.com \
--cc=torvalds@linux-foundation.org \
--cc=valentin.schneider@arm.com \
--cc=vineeth@bitbyteword.org \
--cc=viremana@linux.microsoft.com \
--cc=yu.c.chen@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).