linux-kernel - [RFC 26/60] cosched: Construct runqueue hierarchy

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Fri,  7 Sep 2018 23:40:13 +0200
From:   Jan H. Schönherr <jschoenh@...zon.de>
To:     Ingo Molnar <mingo@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>
Cc:     Jan H. Schönherr <jschoenh@...zon.de>,
        linux-kernel@...r.kernel.org
Subject: [RFC 26/60] cosched: Construct runqueue hierarchy

With scheduling domains sufficiently prepared, we can now initialize
the full hierarchy of runqueues and link it with the already existing
bottom level, which we set up earlier.

Signed-off-by: Jan H. Schönherr <jschoenh@...zon.de>
---
 kernel/sched/core.c    |  1 +
 kernel/sched/cosched.c | 76 ++++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/sched.h   |  2 ++
 3 files changed, 79 insertions(+)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index cc801f84bf97..5350cab7ac4a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5876,6 +5876,7 @@ void __init sched_init_smp(void)
 	 */
 	mutex_lock(&sched_domains_mutex);
 	sched_init_domains(cpu_active_mask);
+	cosched_init_hierarchy();
 	mutex_unlock(&sched_domains_mutex);
 
 	/* Move init over to a non-isolated CPU */
diff --git a/kernel/sched/cosched.c b/kernel/sched/cosched.c
index 7a793aa93114..48394050ec34 100644
--- a/kernel/sched/cosched.c
+++ b/kernel/sched/cosched.c
@@ -351,3 +351,79 @@ void cosched_init_topology(void)
 	/* Make permanent */
 	set_sched_topology(tl);
 }
+
+/*
+ * Build the SD-RQ hierarchy according to the scheduling domains.
+ *
+ * Note, that the scheduler is already live at this point, but the scheduling
+ * domains only just have become available. That means, we only setup everything
+ * above the bottom level of the SD-RQ hierarchy and link it with the already
+ * active bottom level.
+ *
+ * We can do this without any locks, as nothing will automatically traverse into
+ * these data structures. This requires an update of the sdrq.is_root property,
+ * which will happen only later.
+ */
+void cosched_init_hierarchy(void)
+{
+	struct sched_domain *sd;
+	struct sdrq *sdrq;
+	int cpu, level = 1;
+
+	/* Only one CPU in the system, we are finished here */
+	if (cpumask_weight(cpu_possible_mask) == 1)
+		return;
+
+	/* Determine and initialize top */
+	for_each_domain(0, sd) {
+		if (!sd->parent)
+			break;
+		level++;
+	}
+
+	init_sdrq_data(&sd->shared->rq.sdrq_data, NULL, sched_domain_span(sd),
+		       level);
+	init_cfs_rq(&sd->shared->rq.cfs);
+	init_tg_cfs_entry(&root_task_group, &sd->shared->rq.cfs, NULL,
+			  &sd->shared->rq, NULL);
+	init_sdrq(&root_task_group, &sd->shared->rq.cfs.sdrq, NULL, NULL,
+		  &sd->shared->rq.sdrq_data);
+
+	root_task_group.top_cfsrq = &sd->shared->rq.cfs;
+
+	/* Initialize others top-down, per CPU */
+	for_each_possible_cpu(cpu) {
+		/* Find highest not-yet initialized position for this CPU */
+		for_each_domain(cpu, sd) {
+			if (sd->shared->rq.sdrq_data.span_weight)
+				break;
+		}
+		if (WARN(!sd, "SD hierarchy seems to have multiple roots"))
+			continue;
+		sd = sd->child;
+
+		/* Initialize from there downwards */
+		for_each_lower_domain(sd) {
+			init_sdrq_data(&sd->shared->rq.sdrq_data,
+				       &sd->parent->shared->rq.sdrq_data,
+				       sched_domain_span(sd), -1);
+			init_cfs_rq(&sd->shared->rq.cfs);
+			init_tg_cfs_entry(&root_task_group, &sd->shared->rq.cfs,
+					  NULL, &sd->shared->rq, NULL);
+			init_sdrq(&root_task_group, &sd->shared->rq.cfs.sdrq,
+				  &sd->parent->shared->rq.cfs.sdrq, NULL,
+				  &sd->shared->rq.sdrq_data);
+		}
+
+		/* Link up with local data structures */
+		sdrq = &cpu_rq(cpu)->cfs.sdrq;
+		sd = cpu_rq(cpu)->sd;
+
+		/* sdrq_data */
+		sdrq->data->parent = &sd->shared->rq.sdrq_data;
+
+		/* sdrq */
+		sdrq->sd_parent = &sd->shared->rq.cfs.sdrq;
+		list_add_tail(&sdrq->siblings, &sdrq->sd_parent->children);
+	}
+}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ed9c526b74ee..d65c98c34c13 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1132,9 +1132,11 @@ static inline struct cfs_rq *taskgroup_next_cfsrq(struct task_group *tg,
 #ifdef CONFIG_COSCHEDULING
 void cosched_init_bottom(void);
 void cosched_init_topology(void);
+void cosched_init_hierarchy(void);
 #else /* !CONFIG_COSCHEDULING */
 static inline void cosched_init_bottom(void) { }
 static inline void cosched_init_topology(void) { }
+static inline void cosched_init_hierarchy(void) { }
 #endif /* !CONFIG_COSCHEDULING */
 
 #ifdef CONFIG_SCHED_SMT
-- 
2.9.3.1.gcba166c.dirty