From: Peter Zijlstra <peterz@infradead.org>
To: mingo@kernel.org, tglx@linutronix.de, pjt@google.com,
tim.c.chen@linux.intel.com, torvalds@linux-foundation.org
Cc: linux-kernel@vger.kernel.org, subhra.mazumdar@oracle.com,
fweisbec@gmail.com, keescook@chromium.org, kerrnel@google.com,
"Peter Zijlstra (Intel)" <peterz@infradead.org>
Subject: [RFC][PATCH 13/16] sched: Add core wide task selection and scheduling.
Date: Mon, 18 Feb 2019 17:56:33 +0100 [thread overview]
Message-ID: <20190218173514.667598558@infradead.org> (raw)
In-Reply-To: 20190218165620.383905466@infradead.org
Instead of only selecting a local task, select a task for all SMT
siblings for every reschedule on the core (irrespective which logical
CPU does the reschedule).
NOTE: there is still potential for siblings rivalry.
NOTE: this is far too complicated; but thus far I've failed to
simplify it further.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
kernel/sched/core.c | 222 ++++++++++++++++++++++++++++++++++++++++++++++++++-
kernel/sched/sched.h | 5 -
2 files changed, 224 insertions(+), 3 deletions(-)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3552,7 +3552,7 @@ static inline void schedule_debug(struct
* Pick up the highest-prio task:
*/
static inline struct task_struct *
-pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+__pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
const struct sched_class *class;
struct task_struct *p;
@@ -3597,6 +3597,220 @@ pick_next_task(struct rq *rq, struct tas
BUG();
}
+#ifdef CONFIG_SCHED_CORE
+
+static inline bool cookie_match(struct task_struct *a, struct task_struct *b)
+{
+ if (is_idle_task(a) || is_idle_task(b))
+ return true;
+
+ return a->core_cookie == b->core_cookie;
+}
+
+// XXX fairness/fwd progress conditions
+static struct task_struct *
+pick_task(struct rq *rq, const struct sched_class *class, struct task_struct *max)
+{
+ struct task_struct *class_pick, *cookie_pick;
+ unsigned long cookie = 0UL;
+
+ /*
+ * We must not rely on rq->core->core_cookie here, because we fail to reset
+ * rq->core->core_cookie on new picks, such that we can detect if we need
+ * to do single vs multi rq task selection.
+ */
+
+ if (max && max->core_cookie) {
+ WARN_ON_ONCE(rq->core->core_cookie != max->core_cookie);
+ cookie = max->core_cookie;
+ }
+
+ class_pick = class->pick_task(rq);
+ if (!cookie)
+ return class_pick;
+
+ cookie_pick = sched_core_find(rq, cookie);
+ if (!class_pick)
+ return cookie_pick;
+
+ /*
+ * If class > max && class > cookie, it is the highest priority task on
+ * the core (so far) and it must be selected, otherwise we must go with
+ * the cookie pick in order to satisfy the constraint.
+ */
+ if (cpu_prio_less(cookie_pick, class_pick) && cpu_prio_less(max, class_pick))
+ return class_pick;
+
+ return cookie_pick;
+}
+
+static struct task_struct *
+pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+ struct task_struct *next, *max = NULL;
+ const struct sched_class *class;
+ const struct cpumask *smt_mask;
+ int i, j, cpu;
+
+ if (!sched_core_enabled(rq))
+ return __pick_next_task(rq, prev, rf);
+
+ /*
+ * If there were no {en,de}queues since we picked (IOW, the task
+ * pointers are all still valid), and we haven't scheduled the last
+ * pick yet, do so now.
+ */
+ if (rq->core->core_pick_seq == rq->core->core_task_seq &&
+ rq->core->core_pick_seq != rq->core_sched_seq) {
+ WRITE_ONCE(rq->core_sched_seq, rq->core->core_pick_seq);
+
+ next = rq->core_pick;
+ if (next != prev) {
+ put_prev_task(rq, prev);
+ set_next_task(rq, next);
+ }
+ return next;
+ }
+
+ prev->sched_class->put_prev_task(rq, prev, rf);
+ if (!rq->nr_running)
+ newidle_balance(rq, rf);
+
+ cpu = cpu_of(rq);
+ smt_mask = cpu_smt_mask(cpu);
+
+ /*
+ * core->core_task_seq, core->core_pick_seq, rq->core_sched_seq
+ *
+ * @task_seq guards the task state ({en,de}queues)
+ * @pick_seq is the @task_seq we did a selection on
+ * @sched_seq is the @pick_seq we scheduled
+ *
+ * However, preemptions can cause multiple picks on the same task set.
+ * 'Fix' this by also increasing @task_seq for every pick.
+ */
+ rq->core->core_task_seq++;
+
+ /* reset state */
+ for_each_cpu(i, smt_mask) {
+ struct rq *rq_i = cpu_rq(i);
+
+ rq_i->core_pick = NULL;
+
+ if (i != cpu)
+ update_rq_clock(rq_i);
+ }
+
+ /*
+ * Try and select tasks for each sibling in decending sched_class
+ * order.
+ */
+ for_each_class(class) {
+again:
+ for_each_cpu_wrap(i, smt_mask, cpu) {
+ struct rq *rq_i = cpu_rq(i);
+ struct task_struct *p;
+
+ if (rq_i->core_pick)
+ continue;
+
+ /*
+ * If this sibling doesn't yet have a suitable task to
+ * run; ask for the most elegible task, given the
+ * highest priority task already selected for this
+ * core.
+ */
+ p = pick_task(rq_i, class, max);
+ if (!p) {
+ /*
+ * If there weren't no cookies; we don't need
+ * to bother with the other siblings.
+ */
+ if (i == cpu && !rq->core->core_cookie)
+ goto next_class;
+
+ continue;
+ }
+
+ /*
+ * Optimize the 'normal' case where there aren't any
+ * cookies and we don't need to sync up.
+ */
+ if (i == cpu && !rq->core->core_cookie && !p->core_cookie) {
+ next = p;
+ goto done;
+ }
+
+ rq_i->core_pick = p;
+
+ /*
+ * If this new candidate is of higher priority than the
+ * previous; and they're incompatible; we need to wipe
+ * the slate and start over.
+ *
+ * NOTE: this is a linear max-filter and is thus bounded
+ * in execution time.
+ */
+ if (!max || core_prio_less(max, p)) {
+ struct task_struct *old_max = max;
+
+ rq->core->core_cookie = p->core_cookie;
+ max = p;
+
+ if (old_max && !cookie_match(old_max, p)) {
+ for_each_cpu(j, smt_mask) {
+ if (j == i)
+ continue;
+
+ cpu_rq(j)->core_pick = NULL;
+ }
+ goto again;
+ }
+ }
+ }
+next_class:;
+ }
+
+ rq->core->core_pick_seq = rq->core->core_task_seq;
+
+ /*
+ * Reschedule siblings
+ *
+ * NOTE: L1TF -- at this point we're no longer running the old task and
+ * sending an IPI (below) ensures the sibling will no longer be running
+ * their task. This ensures there is no inter-sibling overlap between
+ * non-matching user state.
+ */
+ for_each_cpu(i, smt_mask) {
+ struct rq *rq_i = cpu_rq(i);
+
+ WARN_ON_ONCE(!rq_i->core_pick);
+
+ if (i == cpu)
+ continue;
+
+ if (rq_i->curr != rq_i->core_pick)
+ resched_curr(rq_i);
+ }
+
+ rq->core_sched_seq = rq->core->core_pick_seq;
+ next = rq->core_pick;
+
+done:
+ set_next_task(rq, next);
+ return next;
+}
+
+#else /* !CONFIG_SCHED_CORE */
+
+static struct task_struct *
+pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+ return __pick_next_task(rq, prev, rf);
+}
+
+#endif /* CONFIG_SCHED_CORE */
+
/*
* __schedule() is the main scheduler function.
*
@@ -5866,7 +6080,7 @@ static void migrate_tasks(struct rq *dea
/*
* pick_next_task() assumes pinned rq->lock:
*/
- next = pick_next_task(rq, &fake_task, rf);
+ next = __pick_next_task(rq, &fake_task, rf);
BUG_ON(!next);
put_prev_task(rq, next);
@@ -6322,7 +6536,11 @@ void __init sched_init(void)
#ifdef CONFIG_SCHED_CORE
rq->core = NULL;
+ rq->core_pick = NULL;
rq->core_enabled = 0;
+ rq->core_tree = RB_ROOT;
+
+ rq->core_cookie = 0UL;
#endif
}
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -960,11 +960,15 @@ struct rq {
#ifdef CONFIG_SCHED_CORE
/* per rq */
struct rq *core;
+ struct task_struct *core_pick;
unsigned int core_enabled;
+ unsigned int core_sched_seq;
struct rb_root core_tree;
/* shared state */
unsigned int core_task_seq;
+ unsigned int core_pick_seq;
+ unsigned long core_cookie;
#endif
};
@@ -1770,7 +1774,6 @@ static inline void put_prev_task(struct
static inline void set_next_task(struct rq *rq, struct task_struct *next)
{
- WARN_ON_ONCE(rq->curr != next);
next->sched_class->set_next_task(rq, next);
}
next prev parent reply other threads:[~2019-02-18 17:40 UTC|newest]
Thread overview: 99+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-02-18 16:56 [RFC][PATCH 00/16] sched: Core scheduling Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 01/16] stop_machine: Fix stop_cpus_in_progress ordering Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 02/16] sched: Fix kerneldoc comment for ia64_set_curr_task Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 03/16] sched: Wrap rq::lock access Peter Zijlstra
2019-02-19 16:13 ` Phil Auld
2019-02-19 16:22 ` Peter Zijlstra
2019-02-19 16:37 ` Phil Auld
2019-03-18 15:41 ` Julien Desfossez
2019-03-20 2:29 ` Subhra Mazumdar
2019-03-21 21:20 ` Julien Desfossez
2019-03-22 13:34 ` Peter Zijlstra
2019-03-22 20:59 ` Julien Desfossez
2019-03-23 0:06 ` Subhra Mazumdar
2019-03-27 1:02 ` Subhra Mazumdar
2019-03-29 13:35 ` Julien Desfossez
2019-03-29 22:23 ` Subhra Mazumdar
2019-04-01 21:35 ` Subhra Mazumdar
2019-04-03 20:16 ` Julien Desfossez
2019-04-05 1:30 ` Subhra Mazumdar
2019-04-02 7:42 ` Peter Zijlstra
2019-03-22 23:28 ` Tim Chen
2019-03-22 23:44 ` Tim Chen
2019-02-18 16:56 ` [RFC][PATCH 04/16] sched/{rt,deadline}: Fix set_next_task vs pick_next_task Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 05/16] sched: Add task_struct pointer to sched_class::set_curr_task Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 06/16] sched/fair: Export newidle_balance() Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 07/16] sched: Allow put_prev_task() to drop rq->lock Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 08/16] sched: Rework pick_next_task() slow-path Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 09/16] sched: Introduce sched_class::pick_task() Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 10/16] sched: Core-wide rq->lock Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 11/16] sched: Basic tracking of matching tasks Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 12/16] sched: A quick and dirty cgroup tagging interface Peter Zijlstra
2019-02-18 16:56 ` Peter Zijlstra [this message]
[not found] ` <20190402064612.GA46500@aaronlu>
2019-04-02 8:28 ` [RFC][PATCH 13/16] sched: Add core wide task selection and scheduling Peter Zijlstra
2019-04-02 13:20 ` Aaron Lu
2019-04-05 14:55 ` Aaron Lu
2019-04-09 18:09 ` Tim Chen
2019-04-10 4:36 ` Aaron Lu
2019-04-10 14:18 ` Aubrey Li
2019-04-11 2:11 ` Aaron Lu
2019-04-10 14:44 ` Peter Zijlstra
2019-04-11 3:05 ` Aaron Lu
2019-04-11 9:19 ` Peter Zijlstra
2019-04-10 8:06 ` Peter Zijlstra
2019-04-10 19:58 ` Vineeth Remanan Pillai
2019-04-15 16:59 ` Julien Desfossez
2019-04-16 13:43 ` Aaron Lu
2019-04-09 18:38 ` Julien Desfossez
2019-04-10 15:01 ` Peter Zijlstra
2019-04-11 0:11 ` Subhra Mazumdar
2019-04-19 8:40 ` Ingo Molnar
2019-04-19 23:16 ` Subhra Mazumdar
2019-02-18 16:56 ` [RFC][PATCH 14/16] sched/fair: Add a few assertions Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 15/16] sched: Trivial forced-newidle balancer Peter Zijlstra
2019-02-21 16:19 ` Valentin Schneider
2019-02-21 16:41 ` Peter Zijlstra
2019-02-21 16:47 ` Peter Zijlstra
2019-02-21 18:28 ` Valentin Schneider
2019-04-04 8:31 ` Aubrey Li
2019-04-06 1:36 ` Aubrey Li
2019-02-18 16:56 ` [RFC][PATCH 16/16] sched: Debug bits Peter Zijlstra
2019-02-18 17:49 ` [RFC][PATCH 00/16] sched: Core scheduling Linus Torvalds
2019-02-18 20:40 ` Peter Zijlstra
2019-02-19 0:29 ` Linus Torvalds
2019-02-19 15:15 ` Ingo Molnar
2019-02-22 12:17 ` Paolo Bonzini
2019-02-22 14:20 ` Peter Zijlstra
2019-02-22 19:26 ` Tim Chen
2019-02-26 8:26 ` Aubrey Li
2019-02-27 7:54 ` Aubrey Li
2019-02-21 2:53 ` Subhra Mazumdar
2019-02-21 14:03 ` Peter Zijlstra
2019-02-21 18:44 ` Subhra Mazumdar
2019-02-22 0:34 ` Subhra Mazumdar
2019-02-22 12:45 ` Mel Gorman
2019-02-22 16:10 ` Mel Gorman
2019-03-08 19:44 ` Subhra Mazumdar
2019-03-11 4:23 ` Aubrey Li
2019-03-11 18:34 ` Subhra Mazumdar
2019-03-11 23:33 ` Subhra Mazumdar
2019-03-12 0:20 ` Greg Kerr
2019-03-12 0:47 ` Subhra Mazumdar
2019-03-12 7:33 ` Aaron Lu
2019-03-12 7:45 ` Aubrey Li
2019-03-13 5:55 ` Aubrey Li
2019-03-14 0:35 ` Tim Chen
2019-03-14 5:30 ` Aubrey Li
2019-03-14 6:07 ` Li, Aubrey
2019-03-18 6:56 ` Aubrey Li
2019-03-12 19:07 ` Pawan Gupta
2019-03-26 7:32 ` Aaron Lu
2019-03-26 7:56 ` Aaron Lu
2019-02-19 22:07 ` Greg Kerr
2019-02-20 9:42 ` Peter Zijlstra
2019-02-20 18:33 ` Greg Kerr
2019-02-22 14:10 ` Peter Zijlstra
2019-03-07 22:06 ` Paolo Bonzini
2019-02-20 18:43 ` Subhra Mazumdar
2019-03-01 2:54 ` Subhra Mazumdar
2019-03-14 15:28 ` Julien Desfossez
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=20190218173514.667598558@infradead.org \
--to=peterz@infradead.org \
--cc=fweisbec@gmail.com \
--cc=keescook@chromium.org \
--cc=kerrnel@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=pjt@google.com \
--cc=subhra.mazumdar@oracle.com \
--cc=tglx@linutronix.de \
--cc=tim.c.chen@linux.intel.com \
--cc=torvalds@linux-foundation.org \
/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).