| 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: <20231106193524.866104-15-jstultz@google.com>
Date: Mon, 6 Nov 2023 19:34:57 +0000
From: John Stultz <jstultz@...gle.com>
To: LKML <linux-kernel@...r.kernel.org>
Cc: John Stultz <jstultz@...gle.com>,
Joel Fernandes <joelaf@...gle.com>,
Qais Yousef <qyousef@...gle.com>,
Ingo Molnar <mingo@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Juri Lelli <juri.lelli@...hat.com>,
Vincent Guittot <vincent.guittot@...aro.org>,
Dietmar Eggemann <dietmar.eggemann@....com>,
Valentin Schneider <vschneid@...hat.com>,
Steven Rostedt <rostedt@...dmis.org>,
Ben Segall <bsegall@...gle.com>,
Zimuzo Ezeozue <zezeozue@...gle.com>,
Youssef Esmat <youssefesmat@...gle.com>,
Mel Gorman <mgorman@...e.de>,
Daniel Bristot de Oliveira <bristot@...hat.com>,
Will Deacon <will@...nel.org>,
Waiman Long <longman@...hat.com>,
Boqun Feng <boqun.feng@...il.com>,
"Paul E . McKenney" <paulmck@...nel.org>, kernel-team@...roid.com
Subject: [PATCH v6 14/20] sched: Add a very simple proxy() function
This adds a very simple proxy() function so if
we select a blocked task to run, we will deactivate it
and pick again. The exception being if it has become
unblocked after proxy() was called.
Greatly simplified from patch by:
Peter Zijlstra (Intel) <peterz@...radead.org>
Juri Lelli <juri.lelli@...hat.com>
Valentin Schneider <valentin.schneider@....com>
Connor O'Brien <connoro@...gle.com>
Cc: Joel Fernandes <joelaf@...gle.com>
Cc: Qais Yousef <qyousef@...gle.com>
Cc: Ingo Molnar <mingo@...hat.com>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Juri Lelli <juri.lelli@...hat.com>
Cc: Vincent Guittot <vincent.guittot@...aro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@....com>
Cc: Valentin Schneider <vschneid@...hat.com>
Cc: Steven Rostedt <rostedt@...dmis.org>
Cc: Ben Segall <bsegall@...gle.com>
Cc: Zimuzo Ezeozue <zezeozue@...gle.com>
Cc: Youssef Esmat <youssefesmat@...gle.com>
Cc: Mel Gorman <mgorman@...e.de>
Cc: Daniel Bristot de Oliveira <bristot@...hat.com>
Cc: Will Deacon <will@...nel.org>
Cc: Waiman Long <longman@...hat.com>
Cc: Boqun Feng <boqun.feng@...il.com>
Cc: "Paul E . McKenney" <paulmck@...nel.org>
Cc: kernel-team@...roid.com
[jstultz: Split out from larger proxy patch and simplified
for review and testing.]
Signed-off-by: John Stultz <jstultz@...gle.com>
---
v5:
* Split out from larger proxy patch
---
kernel/sched/core.c | 89 +++++++++++++++++++++++++++++++++++++++++++--
kernel/sched/rt.c | 19 +++++++++-
2 files changed, 102 insertions(+), 6 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1b38b34d3f64..5770656b898d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6575,11 +6575,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
# define SM_MASK_PREEMPT SM_PREEMPT
#endif
-static bool try_to_deactivate_task(struct rq *rq, struct task_struct *p, unsigned long state)
+static bool try_to_deactivate_task(struct rq *rq, struct task_struct *p,
+ unsigned long state, bool deactivate_cond)
{
if (signal_pending_state(state, p)) {
WRITE_ONCE(p->__state, TASK_RUNNING);
- } else {
+ } else if (deactivate_cond) {
p->sched_contributes_to_load =
(state & TASK_UNINTERRUPTIBLE) &&
!(state & TASK_NOLOAD) &&
@@ -6610,6 +6611,74 @@ static bool try_to_deactivate_task(struct rq *rq, struct task_struct *p, unsigne
return false;
}
+#ifdef CONFIG_PROXY_EXEC
+/*
+ * Initial simple proxy that just returns the task if its waking
+ * or deactivates the blocked task so we can pick something that
+ * isn't blocked.
+ */
+static struct task_struct *
+proxy(struct rq *rq, struct task_struct *next, struct rq_flags *rf)
+{
+ struct task_struct *p = next;
+ struct mutex *mutex;
+ unsigned long state;
+
+ mutex = p->blocked_on;
+ /* Something changed in the chain, pick_again */
+ if (!mutex)
+ return NULL;
+ /*
+ * By taking mutex->wait_lock we hold off concurrent mutex_unlock()
+ * and ensure @owner sticks around.
+ */
+ raw_spin_lock(&mutex->wait_lock);
+ raw_spin_lock(&p->blocked_lock);
+
+ /* Check again that p is blocked with blocked_lock held */
+ if (!task_is_blocked(p) || mutex != p->blocked_on) {
+ /*
+ * Something changed in the blocked_on chain and
+ * we don't know if only at this level. So, let's
+ * just bail out completely and let __schedule
+ * figure things out (pick_again loop).
+ */
+ raw_spin_unlock(&p->blocked_lock);
+ raw_spin_unlock(&mutex->wait_lock);
+ return NULL;
+ }
+
+ state = READ_ONCE(p->__state);
+ /* Don't deactivate if the state has been changed to TASK_RUNNING */
+ if (!state) {
+ raw_spin_unlock(&p->blocked_lock);
+ raw_spin_unlock(&mutex->wait_lock);
+ return p;
+ }
+
+ try_to_deactivate_task(rq, next, state, true);
+
+ /*
+ * If next is the selected task, then remove lingering
+ * references to it from rq and sched_class structs after
+ * dequeueing.
+ */
+ put_prev_task(rq, next);
+ rq_set_selected(rq, rq->idle);
+ resched_curr(rq);
+ raw_spin_unlock(&p->blocked_lock);
+ raw_spin_unlock(&mutex->wait_lock);
+ return NULL;
+}
+#else /* PROXY_EXEC */
+static struct task_struct *
+proxy(struct rq *rq, struct task_struct *next, struct rq_flags *rf)
+{
+ BUG(); // This should never be called in the !PROXY case
+ return next;
+}
+#endif /* PROXY_EXEC */
+
/*
* __schedule() is the main scheduler function.
*
@@ -6700,12 +6769,24 @@ static void __sched notrace __schedule(unsigned int sched_mode)
*/
prev_state = READ_ONCE(prev->__state);
if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
- try_to_deactivate_task(rq, prev, prev_state);
+ try_to_deactivate_task(rq, prev, prev_state,
+ !task_is_blocked(prev));
switch_count = &prev->nvcsw;
}
- next = pick_next_task(rq, prev, &rf);
+pick_again:
+ next = pick_next_task(rq, rq_selected(rq), &rf);
rq_set_selected(rq, next);
+ if (unlikely(task_is_blocked(next))) {
+ next = proxy(rq, next, &rf);
+ if (!next) {
+ rq_unpin_lock(rq, &rf);
+ __balance_callbacks(rq);
+ rq_repin_lock(rq, &rf);
+ goto pick_again;
+ }
+ }
+
clear_tsk_need_resched(prev);
clear_preempt_need_resched();
#ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index bc243e70bc0e..0125a3ae5a7a 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1537,8 +1537,19 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
enqueue_rt_entity(rt_se, flags);
- if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
- enqueue_pushable_task(rq, p);
+ /*
+ * Current can't be pushed away. Selected is tied to current,
+ * so don't push it either.
+ */
+ if (task_current(rq, p) || task_current_selected(rq, p))
+ return;
+ /*
+ * Pinned tasks can't be pushed.
+ */
+ if (p->nr_cpus_allowed == 1)
+ return;
+
+ enqueue_pushable_task(rq, p);
}
static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
@@ -1825,6 +1836,10 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 1);
+ /* Avoid marking selected as pushable */
+ if (task_current_selected(rq, p))
+ return;
+
/*
* The previous task needs to be made eligible for pushing
* if it is still active
--
2.42.0.869.gea05f2083d-goog
Powered by blists - more mailing lists