sched: Fix capacity calculations for SMT4

Handle cpu capacity being reported as 0 on cores with more number of
hardware threads. For example on a Power7 core with 4 hardware
threads, core power is 1177 and thus power of each hardware thread is
1177/4 = 294. This low power can lead to capacity for each hardware
thread being calculated as 0, which leads to tasks bouncing within the
core madly!

Fix this by reporting capacity for hardware threads as 1, provided
their power is not scaled down significantly because of frequency
scaling or real-time tasks usage of cpu.

Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arjan van de Ven <arjan@linux.intel.com>
LKML-Reference: <20100608045702.21D03CC895@localhost.localdomain>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

2 files changed, 44 insertions, 11 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index a3e5b1cd043..c731296e5e9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -857,7 +857,7 @@ struct sched_group {
          * CPU power of this group, SCHED_LOAD_SCALE being max power for a
          * single CPU.
          */
-        unsigned int cpu_power;
+        unsigned int cpu_power, cpu_power_orig;
 
         /*
          * The CPUs this group covers.
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 6ee2e0af665..b9b3462483b 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2285,13 +2285,6 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
         unsigned long power = SCHED_LOAD_SCALE;
         struct sched_group *sdg = sd->groups;
 
-        if (sched_feat(ARCH_POWER))
-                power *= arch_scale_freq_power(sd, cpu);
-        else
-                power *= default_scale_freq_power(sd, cpu);
-
-        power >>= SCHED_LOAD_SHIFT;
-
         if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
                 if (sched_feat(ARCH_POWER))
                         power *= arch_scale_smt_power(sd, cpu);
@@ -2301,6 +2294,15 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
                 power >>= SCHED_LOAD_SHIFT;
         }
 
+        sdg->cpu_power_orig = power;
+
+        if (sched_feat(ARCH_POWER))
+                power *= arch_scale_freq_power(sd, cpu);
+        else
+                power *= default_scale_freq_power(sd, cpu);
+
+        power >>= SCHED_LOAD_SHIFT;
+
         power *= scale_rt_power(cpu);
         power >>= SCHED_LOAD_SHIFT;
 
@@ -2333,6 +2335,31 @@ static void update_group_power(struct sched_domain *sd, int cpu)
         sdg->cpu_power = power;
 }
 
+/*
+ * Try and fix up capacity for tiny siblings, this is needed when
+ * things like SD_ASYM_PACKING need f_b_g to select another sibling
+ * which on its own isn't powerful enough.
+ *
+ * See update_sd_pick_busiest() and check_asym_packing().
+ */
+static inline int
+fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
+{
+        /*
+         * Only siblings can have significantly less than SCHED_LOAD_SCALE
+         */
+        if (sd->level != SD_LV_SIBLING)
+                return 0;
+
+        /*
+         * If ~90% of the cpu_power is still there, we're good.
+         */
+        if (group->cpu_power * 32 < group->cpu_power_orig * 29)
+                return 1;
+
+        return 0;
+}
+
 /**
  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
  * @sd: The sched_domain whose statistics are to be updated.
@@ -2426,6 +2453,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 
         sgs->group_capacity =
                 DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
+        if (!sgs->group_capacity)
+                sgs->group_capacity = fix_small_capacity(sd, group);
 }
 
 /**
@@ -2724,8 +2753,9 @@ ret:
  * find_busiest_queue - find the busiest runqueue among the cpus in group.
  */
 static struct rq *
-find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
-                   unsigned long imbalance, const struct cpumask *cpus)
+find_busiest_queue(struct sched_domain *sd, struct sched_group *group,
+                   enum cpu_idle_type idle, unsigned long imbalance,
+                   const struct cpumask *cpus)
 {
         struct rq *busiest = NULL, *rq;
         unsigned long max_load = 0;
@@ -2736,6 +2766,9 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
                 unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
                 unsigned long wl;
 
+                if (!capacity)
+                        capacity = fix_small_capacity(sd, group);
+
                 if (!cpumask_test_cpu(i, cpus))
                         continue;
 
@@ -2852,7 +2885,7 @@ redo:
                 goto out_balanced;
         }
 
-        busiest = find_busiest_queue(group, idle, imbalance, cpus);
+        busiest = find_busiest_queue(sd, group, idle, imbalance, cpus);
         if (!busiest) {
                 schedstat_inc(sd, lb_nobusyq[idle]);
                 goto out_balanced;