Revert "sched: Improve scalability via 'CPU buddies', which withstand random perturbations"

This reverts commit 970e178985cadbca660feb02f4d2ee3a09f7fdda.

Nikolay Ulyanitsky reported thatthe 3.6-rc5 kernel has a 15-20%
performance drop on PostgreSQL 9.2 on his machine (running "pgbench").

Borislav Petkov was able to reproduce this, and bisected it to this
commit 970e178985ca ("sched: Improve scalability via 'CPU buddies' ...")
apparently because the new single-idle-buddy model simply doesn't find
idle CPU's to reschedule on aggressively enough.

Mike Galbraith suspects that it is likely due to the user-mode spinlocks
in PostgreSQL not reacting well to preemption, but we don't really know
the details - I'll just revert the commit for now.

There are hopefully other approaches to improve scheduler scalability
without it causing these kinds of downsides.

Reported-by: Nikolay Ulyanitsky <lystor@gmail.com>
Bisected-by: Borislav Petkov <bp@alien8.de>
Acked-by: Mike Galbraith <efault@gmx.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 22 insertions, 46 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b8c86648a2f9..23bddac4bad8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -954,7 +954,6 @@ struct sched_domain {
         unsigned int smt_gain;
         int flags;                      /* See SD_* */
         int level;
-        int idle_buddy;                 /* cpu assigned to select_idle_sibling() */
 
         /* Runtime fields. */
         unsigned long last_balance;     /* init to jiffies. units in jiffies */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a4ea245f3d85..649c9f876cb1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6014,11 +6014,6 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu)
  * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this
  * allows us to avoid some pointer chasing select_idle_sibling().
  *
- * Iterate domains and sched_groups downward, assigning CPUs to be
- * select_idle_sibling() hw buddy.  Cross-wiring hw makes bouncing
- * due to random perturbation self canceling, ie sw buddies pull
- * their counterpart to their CPU's hw counterpart.
- *
  * Also keep a unique ID per domain (we use the first cpu number in
  * the cpumask of the domain), this allows us to quickly tell if
  * two cpus are in the same cache domain, see cpus_share_cache().
@@ -6032,40 +6027,8 @@ static void update_top_cache_domain(int cpu)
         int id = cpu;
 
         sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
-        if (sd) {
-                struct sched_domain *tmp = sd;
-                struct sched_group *sg, *prev;
-                bool right;
-
-                /*
-                 * Traverse to first CPU in group, and count hops
-                 * to cpu from there, switching direction on each
-                 * hop, never ever pointing the last CPU rightward.
-                 */
-                do {
-                        id = cpumask_first(sched_domain_span(tmp));
-                        prev = sg = tmp->groups;
-                        right = 1;
-
-                        while (cpumask_first(sched_group_cpus(sg)) != id)
-                                sg = sg->next;
-
-                        while (!cpumask_test_cpu(cpu, sched_group_cpus(sg))) {
-                                prev = sg;
-                                sg = sg->next;
-                                right = !right;
-                        }
-
-                        /* A CPU went down, never point back to domain start. */
-                        if (right && cpumask_first(sched_group_cpus(sg->next)) == id)
-                                right = false;
-
-                        sg = right ? sg->next : prev;
-                        tmp->idle_buddy = cpumask_first(sched_group_cpus(sg));
-                } while ((tmp = tmp->child));
-
+        if (sd)
                 id = cpumask_first(sched_domain_span(sd));
-        }
 
         rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
         per_cpu(sd_llc_id, cpu) = id;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 42d9df6a5ca4..96e2b18b6283 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2637,6 +2637,8 @@ static int select_idle_sibling(struct task_struct *p, int target)
         int cpu = smp_processor_id();
         int prev_cpu = task_cpu(p);
         struct sched_domain *sd;
+        struct sched_group *sg;
+        int i;
 
         /*
          * If the task is going to be woken-up on this cpu and if it is
@@ -2653,17 +2655,29 @@ static int select_idle_sibling(struct task_struct *p, int target)
                 return prev_cpu;
 
         /*
-         * Otherwise, check assigned siblings to find an elegible idle cpu.
+         * Otherwise, iterate the domains and find an elegible idle cpu.
          */
         sd = rcu_dereference(per_cpu(sd_llc, target));
-
         for_each_lower_domain(sd) {
-                if (!cpumask_test_cpu(sd->idle_buddy, tsk_cpus_allowed(p)))
-                        continue;
-                if (idle_cpu(sd->idle_buddy))
-                        return sd->idle_buddy;
-        }
+                sg = sd->groups;
+                do {
+                        if (!cpumask_intersects(sched_group_cpus(sg),
+                                                tsk_cpus_allowed(p)))
+                                goto next;
 
+                        for_each_cpu(i, sched_group_cpus(sg)) {
+                                if (!idle_cpu(i))
+                                        goto next;
+                        }
+
+                        target = cpumask_first_and(sched_group_cpus(sg),
+                                        tsk_cpus_allowed(p));
+                        goto done;
+next:
+                        sg = sg->next;
+                } while (sg != sd->groups);
+        }
+done:
         return target;
 }