| 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: <20201020014336.2076526-10-joel@joelfernandes.org>
Date: Mon, 19 Oct 2020 21:43:19 -0400
From: "Joel Fernandes (Google)" <joel@...lfernandes.org>
To: Nishanth Aravamudan <naravamudan@...italocean.com>,
Julien Desfossez <jdesfossez@...italocean.com>,
Peter Zijlstra <peterz@...radead.org>,
Tim Chen <tim.c.chen@...ux.intel.com>,
Vineeth Pillai <viremana@...ux.microsoft.com>,
Aaron Lu <aaron.lwe@...il.com>,
Aubrey Li <aubrey.intel@...il.com>, tglx@...utronix.de,
linux-kernel@...r.kernel.org
Cc: mingo@...nel.org, torvalds@...ux-foundation.org,
fweisbec@...il.com, keescook@...omium.org, kerrnel@...gle.com,
Phil Auld <pauld@...hat.com>,
Valentin Schneider <valentin.schneider@....com>,
Mel Gorman <mgorman@...hsingularity.net>,
Pawan Gupta <pawan.kumar.gupta@...ux.intel.com>,
Paolo Bonzini <pbonzini@...hat.com>, joel@...lfernandes.org,
vineeth@...byteword.org, Chen Yu <yu.c.chen@...el.com>,
Christian Brauner <christian.brauner@...ntu.com>,
Agata Gruza <agata.gruza@...el.com>,
Antonio Gomez Iglesias <antonio.gomez.iglesias@...el.com>,
graf@...zon.com, konrad.wilk@...cle.com, dfaggioli@...e.com,
pjt@...gle.com, rostedt@...dmis.org, derkling@...gle.com,
benbjiang@...cent.com,
Alexandre Chartre <alexandre.chartre@...cle.com>,
James.Bottomley@...senpartnership.com, OWeisse@...ch.edu,
Dhaval Giani <dhaval.giani@...cle.com>,
Junaid Shahid <junaids@...gle.com>, jsbarnes@...gle.com,
chris.hyser@...cle.com, "Paul E . McKenney" <paulmck@...nel.org>,
Aubrey Li <aubrey.li@...ux.intel.com>,
Tim Chen <tim.c.chen@...el.com>
Subject: [PATCH v8 -tip 09/26] sched: Trivial forced-newidle balancer
From: Peter Zijlstra <peterz@...radead.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.
Tested-by: Julien Desfossez <jdesfossez@...italocean.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Signed-off-by: Joel Fernandes (Google) <joel@...lfernandes.org>
Acked-by: Paul E. McKenney <paulmck@...nel.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 c3563d7cab7f..d38e904dd603 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 a5404ec9e89a..02db5b024768 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:
*
@@ -4638,8 +4653,8 @@ 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);
@@ -4768,6 +4783,9 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
goto done;
}
+ if (!is_task_rq_idle(p))
+ occ++;
+
rq_i->core_pick = p;
/*
@@ -4793,6 +4811,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
cpu_rq(j)->core_pick = NULL;
}
+ occ = 1;
goto again;
} else {
/*
@@ -4842,6 +4861,8 @@ next_class:;
rq_i->core->core_forceidle = true;
}
+ rq_i->core_pick->core_occupation = occ;
+
if (i == cpu) {
rq_i->core_pick = NULL;
continue;
@@ -4871,6 +4892,113 @@ next_class:;
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 ce7552c6bc65..a74926be80ac 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -403,6 +403,7 @@ 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 dfdb0ebb07a8..58f741b52103 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1111,6 +1111,8 @@ 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)
@@ -1123,6 +1125,10 @@ 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
--
2.29.0.rc1.297.gfa9743e501-goog
Powered by blists - more mailing lists