| 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: <20090216165111.12804.41620.stgit@sofia.in.ibm.com>
Date: Mon, 16 Feb 2009 22:21:11 +0530
From: Gautham R Shenoy <ego@...ibm.com>
To: linux-kernel@...r.kernel.org, svaidy@...ux.vnet.ibm.com,
mingo@...e.hu, a.p.zijlstra@...llo.nl, suresh.b.siddha@...el.com,
ego@...ibm.com
Cc: balbir@...ibm.com, dipankar@...ibm.com, efault@....de,
andi@...stfloor.org, Gautham R Shenoy <ego@...ibm.com>
Subject: [PATCH 2/3] sched: Fix the wakeup nomination for
sched_mc/smt_power_savings.
The existing algorithm to nominate a preferred wake up cpu would not
work on a machine which has both sched_mc_power_savings and
sched_smt_power_savings enabled. On such machines, the nomination at a lower
level would keep overwriting the nominations by it's peer-level as well as
higher level sched_domains. This would lead to the ping-ponging of the
nominated wake-up cpu, thereby preventing us from effectively consolidating
tasks.
Correct this by defining the authorized nomination sched_domain level, which
is either the highest sched_domain level containing the
SD_POWERSAVINGS_BALANCE flag or a lower level which contains the previously
nominated wake-up cpu in it's span.
Signed-off-by: Gautham R Shenoy <ego@...ibm.com>
---
include/linux/sched.h | 1 +
kernel/sched.c | 43 ++++++++++++++++++++++++++++++++++++++++---
kernel/sched_fair.c | 2 +-
3 files changed, 42 insertions(+), 4 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 06c5c6c..9827297 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -776,6 +776,7 @@ enum powersavings_balance_level {
};
extern int sched_mc_power_savings, sched_smt_power_savings;
+extern enum powersavings_balance_level active_power_savings_level;
enum sched_domain_level {
SD_LV_NONE = 0,
diff --git a/kernel/sched.c b/kernel/sched.c
index 52bbf1c..af88f5a 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -520,6 +520,11 @@ struct root_domain {
* low system utilisation. Triggered at POWERSAVINGS_BALANCE_WAKEUP(2)
*/
unsigned int sched_mc_preferred_wakeup_cpu;
+ /*
+ * The sched-domain level which is authorized to nominate the preferred
+ * wake up cpu.
+ */
+ enum sched_domain_level authorized_nomination_level;
#endif
};
@@ -3397,9 +3402,17 @@ out_balanced:
goto ret;
if (this == group_leader && group_leader != group_min) {
+ struct root_domain *my_rd = cpu_rq(this_cpu)->rd;
*imbalance = min_load_per_task;
- if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) {
- cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu =
+ /*
+ * The preferred wakeup cpu should be nominated by power-aware
+ * sched-domains which contain the currently nominated cpu.
+ */
+ if (sd->level == my_rd->authorized_nomination_level ||
+ (sd->level < my_rd->authorized_nomination_level &&
+ cpu_isset(my_rd->sched_mc_preferred_wakeup_cpu,
+ *sched_domain_span(sd)))) {
+ my_rd->sched_mc_preferred_wakeup_cpu =
cpumask_first(sched_group_cpus(group_leader));
}
return group_min;
@@ -3683,7 +3696,8 @@ redo:
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
return -1;
- if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
+ if (active_power_savings_level <
+ POWERSAVINGS_BALANCE_WAKEUP)
return -1;
if (sd->nr_balance_failed++ < 2)
@@ -7192,6 +7206,7 @@ static void sched_domain_node_span(int node, struct cpumask *span)
#endif /* CONFIG_NUMA */
int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
+enum powersavings_balance_level active_power_savings_level;
/*
* The cpus mask in sched_group and sched_domain hangs off the end.
@@ -7781,6 +7796,25 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
err = 0;
+/* Assign the sched-domain level which can nominate preferred wake-up cpu */
+ rd->sched_mc_preferred_wakeup_cpu = UINT_MAX;
+ rd->authorized_nomination_level = SD_LV_NONE;
+
+ if (active_power_savings_level >= POWERSAVINGS_BALANCE_WAKEUP) {
+ struct sched_domain *sd;
+ enum sched_domain_level authorized_nomination_level =
+ SD_LV_NONE;
+
+ for_each_domain(first_cpu(*cpu_map), sd) {
+ if (!(sd->flags & SD_POWERSAVINGS_BALANCE))
+ continue;
+ authorized_nomination_level = sd->level;
+ }
+
+ rd->authorized_nomination_level = authorized_nomination_level;
+ }
+
+
free_tmpmask:
free_cpumask_var(tmpmask);
free_send_covered:
@@ -8027,6 +8061,9 @@ static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
else
sched_mc_power_savings = level;
+ active_power_savings_level = max(sched_smt_power_savings,
+ sched_mc_power_savings);
+
arch_reinit_sched_domains();
return count;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5cc1c16..bddee3e 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1042,7 +1042,7 @@ static int wake_idle(int cpu, struct task_struct *p)
chosen_wakeup_cpu =
cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu;
- if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP &&
+ if (active_power_savings_level >= POWERSAVINGS_BALANCE_WAKEUP &&
idle_cpu(cpu) && idle_cpu(this_cpu) &&
p->mm && !(p->flags & PF_KTHREAD) &&
cpu_isset(chosen_wakeup_cpu, p->cpus_allowed))
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists