From: "Jan H. Schönherr" <jschoenh@amazon.de>
To: Ingo Molnar <mingo@redhat.com>, Peter Zijlstra <peterz@infradead.org>
Cc: "Jan H. Schönherr" <jschoenh@amazon.de>, linux-kernel@vger.kernel.org
Subject: [RFC 39/60] cosched: Adjust task group management for hierarchical runqueues
Date: Fri, 7 Sep 2018 23:40:26 +0200 [thread overview]
Message-ID: <20180907214047.26914-40-jschoenh@amazon.de> (raw)
In-Reply-To: <20180907214047.26914-1-jschoenh@amazon.de>
Provide variants of the task group CFS traversal constructs that also
reach the hierarchical runqueues. Adjust task group management functions
where necessary.
The most changes are in alloc_fair_sched_group(), where we now need to
be a bit more careful during initialization.
Signed-off-by: Jan H. Schönherr <jschoenh@amazon.de>
---
kernel/sched/cosched.c | 68 ++++++++++++++++++++++++++++++++++++++++++++++++++
kernel/sched/fair.c | 47 ++++++++++++++++++++++++++++------
kernel/sched/sched.h | 17 +++++++++++++
3 files changed, 124 insertions(+), 8 deletions(-)
diff --git a/kernel/sched/cosched.c b/kernel/sched/cosched.c
index 48394050ec34..b897319d046c 100644
--- a/kernel/sched/cosched.c
+++ b/kernel/sched/cosched.c
@@ -10,6 +10,63 @@
#include "sched.h"
+/*****************************************************************************
+ * Task group traversal
+ *****************************************************************************/
+
+static struct sdrq *leftmost_sdrq(struct sdrq *sdrq)
+{
+ while (!list_empty(&sdrq->children))
+ sdrq = list_first_entry(&sdrq->children, struct sdrq, siblings);
+ return sdrq;
+}
+
+struct cfs_rq *taskgroup_first_cfsrq(struct task_group *tg)
+{
+ if (!tg->top_cfsrq)
+ return NULL;
+ return leftmost_sdrq(&tg->top_cfsrq->sdrq)->cfs_rq;
+}
+
+struct cfs_rq *taskgroup_next_cfsrq(struct task_group *tg, struct cfs_rq *cfs)
+{
+ struct sdrq *sdrq = &cfs->sdrq;
+ struct sdrq *parent = sdrq->sd_parent;
+
+ if (cfs == tg->top_cfsrq)
+ return NULL;
+
+ list_for_each_entry_continue(sdrq, &parent->children, siblings)
+ return leftmost_sdrq(sdrq)->cfs_rq;
+
+ return parent->cfs_rq;
+}
+
+struct cfs_rq *taskgroup_first_cfsrq_topdown(struct task_group *tg)
+{
+ return tg->top_cfsrq;
+}
+
+struct cfs_rq *taskgroup_next_cfsrq_topdown(struct task_group *tg,
+ struct cfs_rq *cfs)
+{
+ struct sdrq *sdrq = &cfs->sdrq;
+ struct sdrq *parent = sdrq->sd_parent;
+
+ if (!list_empty(&sdrq->children)) {
+ sdrq = list_first_entry(&sdrq->children, struct sdrq, siblings);
+ return sdrq->cfs_rq;
+ }
+
+ while (sdrq != &tg->top_cfsrq->sdrq) {
+ list_for_each_entry_continue(sdrq, &parent->children, siblings)
+ return sdrq->cfs_rq;
+ sdrq = parent;
+ parent = sdrq->sd_parent;
+ }
+ return NULL;
+}
+
static int mask_to_node(const struct cpumask *span)
{
int node = cpu_to_node(cpumask_first(span));
@@ -427,3 +484,14 @@ void cosched_init_hierarchy(void)
list_add_tail(&sdrq->siblings, &sdrq->sd_parent->children);
}
}
+
+/*****************************************************************************
+ * Task group management functions
+ *****************************************************************************/
+
+void cosched_init_sdrq(struct task_group *tg, struct cfs_rq *cfs_rq,
+ struct cfs_rq *sd_parent, struct cfs_rq *tg_parent)
+{
+ init_sdrq(tg, &cfs_rq->sdrq, sd_parent ? &sd_parent->sdrq : NULL,
+ &tg_parent->sdrq, tg_parent->sdrq.data);
+}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 33e3f759eb99..f72a72c8c3b8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9895,10 +9895,29 @@ void free_fair_sched_group(struct task_group *tg)
kfree(tg->cfs_rq);
}
+#ifdef CONFIG_COSCHEDULING
+static struct cfs_rq *find_sd_parent(struct cfs_rq *sd_parent,
+ struct cfs_rq *tg_parent)
+{
+ if (!sd_parent)
+ return NULL;
+
+ while (sd_parent->sdrq.tg_parent != tg_parent->sdrq.sd_parent)
+ sd_parent = sd_parent->sdrq.sd_parent->cfs_rq;
+ return sd_parent;
+}
+#else
+static struct cfs_rq *find_sd_parent(struct cfs_rq *sd_parent,
+ struct cfs_rq *tg_parent)
+{
+ return NULL;
+}
+#endif
+
int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
struct sched_entity *se;
- struct cfs_rq *cfs_rq, *pcfs_rq;
+ struct cfs_rq *cfs_rq = NULL, *pcfs_rq;
tg->cfs_rq = kcalloc(nr_cpu_ids, sizeof(cfs_rq), GFP_KERNEL);
if (!tg->cfs_rq)
@@ -9908,18 +9927,30 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
init_cfs_bandwidth(tg_cfs_bandwidth(tg));
- taskgroup_for_each_cfsrq(parent, pcfs_rq) {
- struct rq *rq = rq_of(pcfs_rq);
- int node = cpu_to_node(cpu_of(rq));
+#ifdef CONFIG_COSCHEDULING
+ raw_spin_lock_init(&tg->lock);
+#endif
+
+ taskgroup_for_each_cfsrq_topdown(parent, pcfs_rq) {
+ struct rq *rq = hrq_of(pcfs_rq);
+ int node = node_of(rq);
+ struct cfs_rq *sdcfs_rq = find_sd_parent(cfs_rq, pcfs_rq);
cfs_rq = kzalloc_node(sizeof(*cfs_rq), GFP_KERNEL, node);
se = kzalloc_node(sizeof(*se), GFP_KERNEL, node);
if (!cfs_rq || !se)
goto err_free;
- tg->cfs_rq[cpu_of(rq)] = cfs_rq;
+#ifdef CONFIG_COSCHEDULING
+ if (!sdcfs_rq)
+ tg->top_cfsrq = cfs_rq;
+#endif
+ if (is_cpu_rq(rq))
+ tg->cfs_rq[cpu_of(rq)] = cfs_rq;
+
init_cfs_rq(cfs_rq);
init_tg_cfs_entry(tg, cfs_rq, se, rq, pcfs_rq);
+ cosched_init_sdrq(tg, cfs_rq, sdcfs_rq, pcfs_rq);
}
return 1;
@@ -9938,7 +9969,7 @@ void online_fair_sched_group(struct task_group *tg)
struct rq *rq;
taskgroup_for_each_cfsrq(tg, cfs) {
- rq = rq_of(cfs);
+ rq = hrq_of(cfs);
se = cfs->my_se;
raw_spin_lock_irq(&rq->lock);
@@ -9964,9 +9995,9 @@ void unregister_fair_sched_group(struct task_group *tg)
if (!cfs->on_list)
continue;
- raw_spin_lock_irqsave(&rq_of(cfs)->lock, flags);
+ raw_spin_lock_irqsave(&hrq_of(cfs)->lock, flags);
list_del_leaf_cfs_rq(cfs);
- raw_spin_unlock_irqrestore(&rq_of(cfs)->lock, flags);
+ raw_spin_unlock_irqrestore(&hrq_of(cfs)->lock, flags);
}
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index bc3631b8b955..38b4500095ca 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1109,6 +1109,17 @@ static inline int cpu_of(struct rq *rq)
(cfs) = (ncfs), \
(ncfs) = (cfs) ? taskgroup_next_cfsrq(tg, cfs) : NULL)
+#ifdef CONFIG_COSCHEDULING
+#define taskgroup_for_each_cfsrq_topdown(tg, cfs) \
+ for ((cfs) = taskgroup_first_cfsrq_topdown(tg); (cfs); \
+ (cfs) = taskgroup_next_cfsrq_topdown(tg, cfs))
+struct cfs_rq *taskgroup_first_cfsrq(struct task_group *tg);
+struct cfs_rq *taskgroup_next_cfsrq(struct task_group *tg, struct cfs_rq *cfs);
+struct cfs_rq *taskgroup_first_cfsrq_topdown(struct task_group *tg);
+struct cfs_rq *taskgroup_next_cfsrq_topdown(struct task_group *tg,
+ struct cfs_rq *cfs);
+#else /* !CONFIG_COSCHEDULING */
+#define taskgroup_for_each_cfsrq_topdown taskgroup_for_each_cfsrq
static inline struct cfs_rq *taskgroup_first_cfsrq(struct task_group *tg)
{
int cpu = cpumask_first(cpu_possible_mask);
@@ -1127,6 +1138,7 @@ static inline struct cfs_rq *taskgroup_next_cfsrq(struct task_group *tg,
return NULL;
return tg->cfs_rq[cpu];
}
+#endif /* !CONFIG_COSCHEDULING */
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_COSCHEDULING
@@ -1181,10 +1193,15 @@ static inline bool is_sd_se(struct sched_entity *se)
void cosched_init_bottom(void);
void cosched_init_topology(void);
void cosched_init_hierarchy(void);
+void cosched_init_sdrq(struct task_group *tg, struct cfs_rq *cfs,
+ struct cfs_rq *sd_parent, struct cfs_rq *tg_parent);
#else /* !CONFIG_COSCHEDULING */
static inline void cosched_init_bottom(void) { }
static inline void cosched_init_topology(void) { }
static inline void cosched_init_hierarchy(void) { }
+static inline void cosched_init_sdrq(struct task_group *tg, struct cfs_rq *cfs,
+ struct cfs_rq *sd_parent,
+ struct cfs_rq *tg_parent) { }
#endif /* !CONFIG_COSCHEDULING */
#ifdef CONFIG_SCHED_SMT
--
2.9.3.1.gcba166c.dirty
next prev parent reply other threads:[~2018-09-07 21:50 UTC|newest]
Thread overview: 114+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-09-07 21:39 [RFC 00/60] Coscheduling for Linux Jan H. Schönherr
2018-09-07 21:39 ` [RFC 01/60] sched: Store task_group->se[] pointers as part of cfs_rq Jan H. Schönherr
2018-09-07 21:39 ` [RFC 02/60] sched: Introduce set_entity_cfs() to place a SE into a certain CFS runqueue Jan H. Schönherr
2018-09-07 21:39 ` [RFC 03/60] sched: Setup sched_domain_shared for all sched_domains Jan H. Schönherr
2018-09-07 21:39 ` [RFC 04/60] sched: Replace sd_numa_mask() hack with something sane Jan H. Schönherr
2018-09-07 21:39 ` [RFC 05/60] sched: Allow to retrieve the sched_domain_topology Jan H. Schönherr
2018-09-07 21:39 ` [RFC 06/60] sched: Add a lock-free variant of resched_cpu() Jan H. Schönherr
2018-09-07 21:39 ` [RFC 07/60] sched: Reduce dependencies of init_tg_cfs_entry() Jan H. Schönherr
2018-09-07 21:39 ` [RFC 08/60] sched: Move init_entity_runnable_average() into init_tg_cfs_entry() Jan H. Schönherr
2018-09-07 21:39 ` [RFC 09/60] sched: Do not require a CFS in init_tg_cfs_entry() Jan H. Schönherr
2018-09-07 21:39 ` [RFC 10/60] sched: Use parent_entity() in more places Jan H. Schönherr
2018-09-07 21:39 ` [RFC 11/60] locking/lockdep: Increase number of supported lockdep subclasses Jan H. Schönherr
2018-09-07 21:39 ` [RFC 12/60] locking/lockdep: Make cookie generator accessible Jan H. Schönherr
2018-09-07 21:40 ` [RFC 13/60] sched: Remove useless checks for root task-group Jan H. Schönherr
2018-09-07 21:40 ` [RFC 14/60] sched: Refactor sync_throttle() to accept a CFS runqueue as argument Jan H. Schönherr
2018-09-07 21:40 ` [RFC 15/60] sched: Introduce parent_cfs_rq() and use it Jan H. Schönherr
2018-09-07 21:40 ` [RFC 16/60] sched: Preparatory code movement Jan H. Schönherr
2018-09-07 21:40 ` [RFC 17/60] sched: Introduce and use generic task group CFS traversal functions Jan H. Schönherr
2018-09-07 21:40 ` [RFC 18/60] sched: Fix return value of SCHED_WARN_ON() Jan H. Schönherr
2018-09-07 21:40 ` [RFC 19/60] sched: Add entity variants of enqueue_task_fair() and dequeue_task_fair() Jan H. Schönherr
2018-09-07 21:40 ` [RFC 20/60] sched: Let {en,de}queue_entity_fair() work with a varying amount of tasks Jan H. Schönherr
2018-09-07 21:40 ` [RFC 21/60] sched: Add entity variants of put_prev_task_fair() and set_curr_task_fair() Jan H. Schönherr
2018-09-07 21:40 ` [RFC 22/60] cosched: Add config option for coscheduling support Jan H. Schönherr
2018-09-07 21:40 ` [RFC 23/60] cosched: Add core data structures for coscheduling Jan H. Schönherr
2018-09-07 21:40 ` [RFC 24/60] cosched: Do minimal pre-SMP coscheduler initialization Jan H. Schönherr
2018-09-07 21:40 ` [RFC 25/60] cosched: Prepare scheduling domain topology for coscheduling Jan H. Schönherr
2018-09-07 21:40 ` [RFC 26/60] cosched: Construct runqueue hierarchy Jan H. Schönherr
2018-09-07 21:40 ` [RFC 27/60] cosched: Add some small helper functions for later use Jan H. Schönherr
2018-09-07 21:40 ` [RFC 28/60] cosched: Add is_sd_se() to distinguish SD-SEs from TG-SEs Jan H. Schönherr
2018-09-07 21:40 ` [RFC 29/60] cosched: Adjust code reflecting on the total number of CFS tasks on a CPU Jan H. Schönherr
2018-09-07 21:40 ` [RFC 30/60] cosched: Disallow share modification on task groups for now Jan H. Schönherr
2018-09-07 21:40 ` [RFC 31/60] cosched: Don't disable idle tick " Jan H. Schönherr
2018-09-07 21:40 ` [RFC 32/60] cosched: Specialize parent_cfs_rq() for hierarchical runqueues Jan H. Schönherr
2018-09-07 21:40 ` [RFC 33/60] cosched: Allow resched_curr() to be called " Jan H. Schönherr
2018-09-07 21:40 ` [RFC 34/60] cosched: Add rq_of() variants for different use cases Jan H. Schönherr
2018-09-07 21:40 ` [RFC 35/60] cosched: Adjust rq_lock() functions to work with hierarchical runqueues Jan H. Schönherr
2018-09-07 21:40 ` [RFC 36/60] cosched: Use hrq_of() for rq_clock() and rq_clock_task() Jan H. Schönherr
2018-09-07 21:40 ` [RFC 37/60] cosched: Use hrq_of() for (indirect calls to) ___update_load_sum() Jan H. Schönherr
2018-09-07 21:40 ` [RFC 38/60] cosched: Skip updates on non-CPU runqueues in cfs_rq_util_change() Jan H. Schönherr
2018-09-07 21:40 ` Jan H. Schönherr [this message]
2018-09-07 21:40 ` [RFC 40/60] cosched: Keep track of task group hierarchy within each SD-RQ Jan H. Schönherr
2018-09-07 21:40 ` [RFC 41/60] cosched: Introduce locking for leader activities Jan H. Schönherr
2018-09-07 21:40 ` [RFC 42/60] cosched: Introduce locking for (mostly) enqueuing and dequeuing Jan H. Schönherr
2018-09-07 21:40 ` [RFC 43/60] cosched: Add for_each_sched_entity() variant for owned entities Jan H. Schönherr
2018-09-07 21:40 ` [RFC 44/60] cosched: Perform various rq_of() adjustments in scheduler code Jan H. Schönherr
2018-09-07 21:40 ` [RFC 45/60] cosched: Continue to account all load on per-CPU runqueues Jan H. Schönherr
2018-09-07 21:40 ` [RFC 46/60] cosched: Warn on throttling attempts of non-CPU runqueues Jan H. Schönherr
2018-09-07 21:40 ` [RFC 47/60] cosched: Adjust SE traversal and locking for common leader activities Jan H. Schönherr
2018-09-07 21:40 ` [RFC 48/60] cosched: Adjust SE traversal and locking for yielding and buddies Jan H. Schönherr
2018-09-07 21:40 ` [RFC 49/60] cosched: Adjust locking for enqueuing and dequeueing Jan H. Schönherr
2018-09-07 21:40 ` [RFC 50/60] cosched: Propagate load changes across hierarchy levels Jan H. Schönherr
2018-09-07 21:40 ` [RFC 51/60] cosched: Hacky work-around to avoid observing zero weight SD-SE Jan H. Schönherr
2018-09-07 21:40 ` [RFC 52/60] cosched: Support SD-SEs in enqueuing and dequeuing Jan H. Schönherr
2018-09-07 21:40 ` [RFC 53/60] cosched: Prevent balancing related functions from crossing hierarchy levels Jan H. Schönherr
2018-09-07 21:40 ` [RFC 54/60] cosched: Support idling in a coscheduled set Jan H. Schönherr
2018-09-07 21:40 ` [RFC 55/60] cosched: Adjust task selection for coscheduling Jan H. Schönherr
2018-09-07 21:40 ` [RFC 56/60] cosched: Adjust wakeup preemption rules " Jan H. Schönherr
2018-09-07 21:40 ` [RFC 57/60] cosched: Add sysfs interface to configure coscheduling on cgroups Jan H. Schönherr
2018-09-07 21:40 ` [RFC 58/60] cosched: Switch runqueues between regular scheduling and coscheduling Jan H. Schönherr
2018-09-07 21:40 ` [RFC 59/60] cosched: Handle non-atomicity during switches to and from coscheduling Jan H. Schönherr
2018-09-07 21:40 ` [RFC 60/60] cosched: Add command line argument to enable coscheduling Jan H. Schönherr
2018-09-10 2:50 ` Randy Dunlap
2018-09-12 0:24 ` [RFC 00/60] Coscheduling for Linux Nishanth Aravamudan
2018-09-12 19:34 ` Jan H. Schönherr
2018-09-12 23:15 ` Nishanth Aravamudan
2018-09-13 11:31 ` Jan H. Schönherr
2018-09-13 18:16 ` Nishanth Aravamudan
2018-09-12 23:18 ` Jan H. Schönherr
2018-09-13 3:05 ` Nishanth Aravamudan
2018-09-13 19:19 ` [RFC 61/60] cosched: Accumulated fixes and improvements Jan H. Schönherr
2018-09-26 17:25 ` Nishanth Aravamudan
2018-09-26 21:05 ` Nishanth Aravamudan
2018-10-01 9:13 ` Jan H. Schönherr
2018-09-14 11:12 ` [RFC 00/60] Coscheduling for Linux Peter Zijlstra
2018-09-14 16:25 ` Jan H. Schönherr
2018-09-15 8:48 ` Task group cleanups and optimizations (was: Re: [RFC 00/60] Coscheduling for Linux) Jan H. Schönherr
2018-09-17 9:48 ` Peter Zijlstra
2018-09-18 13:22 ` Jan H. Schönherr
2018-09-18 13:38 ` Peter Zijlstra
2018-09-18 13:54 ` Jan H. Schönherr
2018-09-18 13:42 ` Peter Zijlstra
2018-09-18 14:35 ` Rik van Riel
2018-09-19 9:23 ` Jan H. Schönherr
2018-11-23 16:51 ` Frederic Weisbecker
2018-12-04 13:23 ` Jan H. Schönherr
2018-09-17 11:33 ` [RFC 00/60] Coscheduling for Linux Peter Zijlstra
2018-11-02 22:13 ` Nishanth Aravamudan
2018-09-17 12:25 ` Peter Zijlstra
2018-09-26 9:58 ` Jan H. Schönherr
2018-09-27 18:36 ` Subhra Mazumdar
2018-11-23 16:29 ` Frederic Weisbecker
2018-09-17 13:37 ` Peter Zijlstra
2018-09-26 9:35 ` Jan H. Schönherr
2018-09-18 14:40 ` Rik van Riel
2018-09-24 15:23 ` Jan H. Schönherr
2018-09-24 18:01 ` Rik van Riel
2018-09-18 0:33 ` Subhra Mazumdar
2018-09-18 11:44 ` Jan H. Schönherr
2018-09-19 21:53 ` Subhra Mazumdar
2018-09-24 15:43 ` Jan H. Schönherr
2018-09-27 18:12 ` Subhra Mazumdar
2018-10-04 13:29 ` Jon Masters
2018-10-17 2:09 ` Frederic Weisbecker
2018-10-19 11:40 ` Jan H. Schönherr
2018-10-19 14:52 ` Frederic Weisbecker
2018-10-19 15:16 ` Rik van Riel
2018-10-19 15:33 ` Frederic Weisbecker
2018-10-19 15:45 ` Rik van Riel
2018-10-19 19:07 ` Jan H. Schönherr
2018-10-19 0:26 ` Subhra Mazumdar
2018-10-26 23:44 ` Jan H. Schönherr
2018-10-29 22:52 ` Subhra Mazumdar
2018-10-26 23:05 ` Subhra Mazumdar
2018-10-27 0:07 ` Jan H. Schönherr
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=20180907214047.26914-40-jschoenh@amazon.de \
--to=jschoenh@amazon.de \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.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).