summaryrefslogtreecommitdiff
path: root/kernel/sched/topology.c
diff options
context:
space:
mode:
authorQuentin Perret <quentin.perret@arm.com>2018-12-03 09:56:18 +0000
committerIngo Molnar <mingo@kernel.org>2018-12-11 15:16:59 +0100
commit6aa140fa4508933a6ac6717d65a403eb904d6c02 (patch)
tree04a92f60e1d10a656d3f46dbe3e673178be51dce /kernel/sched/topology.c
parent27871f7a8a341ef5c636a337856369acf8013e4e (diff)
sched/topology: Reference the Energy Model of CPUs when available
The existing scheduling domain hierarchy is defined to map to the cache topology of the system. However, Energy Aware Scheduling (EAS) requires more knowledge about the platform, and specifically needs to know about the span of Performance Domains (PD), which do not always align with caches. To address this issue, use the Energy Model (EM) of the system to extend the scheduler topology code with a representation of the PDs, alongside the scheduling domains. More specifically, a linked list of PDs is attached to each root domain. When multiple root domains are in use, each list contains only the PDs covering the CPUs of its root domain. If a PD spans over CPUs of multiple different root domains, it will be duplicated in all lists. The lists are fully maintained by the scheduler from partition_sched_domains() in order to cope with hotplug and cpuset changes. As for scheduling domains, the list are protected by RCU to ensure safe concurrent updates. Signed-off-by: Quentin Perret <quentin.perret@arm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: rjw@rjwysocki.net Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-6-quentin.perret@arm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/sched/topology.c')
-rw-r--r--kernel/sched/topology.c134
1 files changed, 130 insertions, 4 deletions
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 7364e0b427b7..169d25cafab5 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -201,6 +201,116 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
return 1;
}
+#ifdef CONFIG_ENERGY_MODEL
+static void free_pd(struct perf_domain *pd)
+{
+ struct perf_domain *tmp;
+
+ while (pd) {
+ tmp = pd->next;
+ kfree(pd);
+ pd = tmp;
+ }
+}
+
+static struct perf_domain *find_pd(struct perf_domain *pd, int cpu)
+{
+ while (pd) {
+ if (cpumask_test_cpu(cpu, perf_domain_span(pd)))
+ return pd;
+ pd = pd->next;
+ }
+
+ return NULL;
+}
+
+static struct perf_domain *pd_init(int cpu)
+{
+ struct em_perf_domain *obj = em_cpu_get(cpu);
+ struct perf_domain *pd;
+
+ if (!obj) {
+ if (sched_debug())
+ pr_info("%s: no EM found for CPU%d\n", __func__, cpu);
+ return NULL;
+ }
+
+ pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+ if (!pd)
+ return NULL;
+ pd->em_pd = obj;
+
+ return pd;
+}
+
+static void perf_domain_debug(const struct cpumask *cpu_map,
+ struct perf_domain *pd)
+{
+ if (!sched_debug() || !pd)
+ return;
+
+ printk(KERN_DEBUG "root_domain %*pbl:", cpumask_pr_args(cpu_map));
+
+ while (pd) {
+ printk(KERN_CONT " pd%d:{ cpus=%*pbl nr_cstate=%d }",
+ cpumask_first(perf_domain_span(pd)),
+ cpumask_pr_args(perf_domain_span(pd)),
+ em_pd_nr_cap_states(pd->em_pd));
+ pd = pd->next;
+ }
+
+ printk(KERN_CONT "\n");
+}
+
+static void destroy_perf_domain_rcu(struct rcu_head *rp)
+{
+ struct perf_domain *pd;
+
+ pd = container_of(rp, struct perf_domain, rcu);
+ free_pd(pd);
+}
+
+static void build_perf_domains(const struct cpumask *cpu_map)
+{
+ struct perf_domain *pd = NULL, *tmp;
+ int cpu = cpumask_first(cpu_map);
+ struct root_domain *rd = cpu_rq(cpu)->rd;
+ int i;
+
+ for_each_cpu(i, cpu_map) {
+ /* Skip already covered CPUs. */
+ if (find_pd(pd, i))
+ continue;
+
+ /* Create the new pd and add it to the local list. */
+ tmp = pd_init(i);
+ if (!tmp)
+ goto free;
+ tmp->next = pd;
+ pd = tmp;
+ }
+
+ perf_domain_debug(cpu_map, pd);
+
+ /* Attach the new list of performance domains to the root domain. */
+ tmp = rd->pd;
+ rcu_assign_pointer(rd->pd, pd);
+ if (tmp)
+ call_rcu(&tmp->rcu, destroy_perf_domain_rcu);
+
+ return;
+
+free:
+ free_pd(pd);
+ tmp = rd->pd;
+ rcu_assign_pointer(rd->pd, NULL);
+ if (tmp)
+ call_rcu(&tmp->rcu, destroy_perf_domain_rcu);
+}
+#else
+static void free_pd(struct perf_domain *pd) { }
+#endif /* CONFIG_ENERGY_MODEL */
+
static void free_rootdomain(struct rcu_head *rcu)
{
struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
@@ -211,6 +321,7 @@ static void free_rootdomain(struct rcu_head *rcu)
free_cpumask_var(rd->rto_mask);
free_cpumask_var(rd->online);
free_cpumask_var(rd->span);
+ free_pd(rd->pd);
kfree(rd);
}
@@ -1959,8 +2070,8 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
/* Destroy deleted domains: */
for (i = 0; i < ndoms_cur; i++) {
for (j = 0; j < n && !new_topology; j++) {
- if (cpumask_equal(doms_cur[i], doms_new[j])
- && dattrs_equal(dattr_cur, i, dattr_new, j))
+ if (cpumask_equal(doms_cur[i], doms_new[j]) &&
+ dattrs_equal(dattr_cur, i, dattr_new, j))
goto match1;
}
/* No match - a current sched domain not in new doms_new[] */
@@ -1980,8 +2091,8 @@ match1:
/* Build new domains: */
for (i = 0; i < ndoms_new; i++) {
for (j = 0; j < n && !new_topology; j++) {
- if (cpumask_equal(doms_new[i], doms_cur[j])
- && dattrs_equal(dattr_new, i, dattr_cur, j))
+ if (cpumask_equal(doms_new[i], doms_cur[j]) &&
+ dattrs_equal(dattr_new, i, dattr_cur, j))
goto match2;
}
/* No match - add a new doms_new */
@@ -1990,6 +2101,21 @@ match2:
;
}
+#ifdef CONFIG_ENERGY_MODEL
+ /* Build perf. domains: */
+ for (i = 0; i < ndoms_new; i++) {
+ for (j = 0; j < n; j++) {
+ if (cpumask_equal(doms_new[i], doms_cur[j]) &&
+ cpu_rq(cpumask_first(doms_cur[j]))->rd->pd)
+ goto match3;
+ }
+ /* No match - add perf. domains for a new rd */
+ build_perf_domains(doms_new[i]);
+match3:
+ ;
+ }
+#endif
+
/* Remember the new sched domains: */
if (doms_cur != &fallback_doms)
free_sched_domains(doms_cur, ndoms_cur);