sched: recover SD_WAKE_AFFINE in select_task_rq_fair and code clean up

Since power saving code was removed from sched now, the implement
code is out of service in this function, and even pollute other logical.
like, 'want_sd' never has chance to be set '0', that remove the effect
of SD_WAKE_AFFINE here.

So, clean up the obsolete code, includes SD_PREFER_LOCAL.

Signed-off-by: Alex Shi <alex.shi@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/5028F431.6000306@intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

4 files changed, 3 insertions, 35 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b8c86648a2f9..f3eebc121ebc 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -860,7 +860,6 @@ enum cpu_idle_type {
 #define SD_BALANCE_FORK         0x0008  /* Balance on fork, clone */
 #define SD_BALANCE_WAKE         0x0010  /* Balance on wakeup */
 #define SD_WAKE_AFFINE          0x0020  /* Wake task to waking CPU */
-#define SD_PREFER_LOCAL         0x0040  /* Prefer to keep tasks local to this domain */
 #define SD_SHARE_CPUPOWER       0x0080  /* Domain members share cpu power */
 #define SD_SHARE_PKG_RESOURCES  0x0200  /* Domain members share cpu pkg resources */
 #define SD_SERIALIZE            0x0400  /* Only a single load balancing instance */
diff --git a/include/linux/topology.h b/include/linux/topology.h
index fec12d667211..d3cf0d6e7712 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -129,7 +129,6 @@ int arch_update_cpu_topology(void);
                                 | 1*SD_BALANCE_FORK                     \
                                 | 0*SD_BALANCE_WAKE                     \
                                 | 1*SD_WAKE_AFFINE                      \
-                                | 0*SD_PREFER_LOCAL                     \
                                 | 0*SD_SHARE_CPUPOWER                   \
                                 | 1*SD_SHARE_PKG_RESOURCES              \
                                 | 0*SD_SERIALIZE                        \
@@ -160,7 +159,6 @@ int arch_update_cpu_topology(void);
                                 | 1*SD_BALANCE_FORK                     \
                                 | 0*SD_BALANCE_WAKE                     \
                                 | 1*SD_WAKE_AFFINE                      \
-                                | 0*SD_PREFER_LOCAL                     \
                                 | 0*SD_SHARE_CPUPOWER                   \
                                 | 0*SD_SHARE_PKG_RESOURCES              \
                                 | 0*SD_SERIALIZE                        \
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c9a3655e572d..4376c9f34790 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6622,7 +6622,6 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
                                         | 0*SD_BALANCE_FORK
                                         | 0*SD_BALANCE_WAKE
                                         | 0*SD_WAKE_AFFINE
-                                        | 0*SD_PREFER_LOCAL
                                         | 0*SD_SHARE_CPUPOWER
                                         | 0*SD_SHARE_PKG_RESOURCES
                                         | 1*SD_SERIALIZE
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 287bfaca6420..01d3eda6b7f9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2686,7 +2686,6 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
         int prev_cpu = task_cpu(p);
         int new_cpu = cpu;
         int want_affine = 0;
-        int want_sd = 1;
         int sync = wake_flags & WF_SYNC;
 
         if (p->nr_cpus_allowed == 1)
@@ -2704,48 +2703,21 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
                         continue;
 
                 /*
-                 * If power savings logic is enabled for a domain, see if we
-                 * are not overloaded, if so, don't balance wider.
-                 */
-                if (tmp->flags & (SD_PREFER_LOCAL)) {
-                        unsigned long power = 0;
-                        unsigned long nr_running = 0;
-                        unsigned long capacity;
-                        int i;
-
-                        for_each_cpu(i, sched_domain_span(tmp)) {
-                                power += power_of(i);
-                                nr_running += cpu_rq(i)->cfs.nr_running;
-                        }
-
-                        capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE);
-
-                        if (nr_running < capacity)
-                                want_sd = 0;
-                }
-
-                /*
                  * If both cpu and prev_cpu are part of this domain,
                  * cpu is a valid SD_WAKE_AFFINE target.
                  */
                 if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
                     cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
                         affine_sd = tmp;
-                        want_affine = 0;
-                }
-
-                if (!want_sd && !want_affine)
                         break;
+                }
 
-                if (!(tmp->flags & sd_flag))
-                        continue;
-
-                if (want_sd)
+                if (tmp->flags & sd_flag)
                         sd = tmp;
         }
 
         if (affine_sd) {
-                if (cpu == prev_cpu || wake_affine(affine_sd, p, sync))
+                if (cpu != prev_cpu && wake_affine(affine_sd, p, sync))
                         prev_cpu = cpu;
 
                 new_cpu = select_idle_sibling(p, prev_cpu);