summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJeffrey Hugo <jhugo@codeaurora.org>2017-06-07 13:18:57 -0600
committerIngo Molnar <mingo@kernel.org>2017-07-05 16:28:48 +0200
commit65a4433aebe36c8c6abeb69b99ef00274b971c6c (patch)
treef31dbba847c65ce9470dec8fc8a42cfd7a0824ff
parent2a42eb9594a1480b4ead9e036e06ee1290e5fa6d (diff)
sched/fair: Fix load_balance() affinity redo path
If load_balance() fails to migrate any tasks because all tasks were affined, load_balance() removes the source CPU from consideration and attempts to redo and balance among the new subset of CPUs. There is a bug in this code path where the algorithm considers all active CPUs in the system (minus the source that was just masked out). This is not valid for two reasons: some active CPUs may not be in the current scheduling domain and one of the active CPUs is dst_cpu. These CPUs should not be considered, as we cannot pull load from them. Instead of failing out of load_balance(), we may end up redoing the search with no valid CPUs and incorrectly concluding the domain is balanced. Additionally, if the group_imbalance flag was just set, it may also be incorrectly unset, thus the flag will not be seen by other CPUs in future load_balance() runs as that algorithm intends. Fix the check by removing CPUs not in the current domain and the dst_cpu from considertation, thus limiting the evaluation to valid remaining CPUs from which load might be migrated. Co-authored-by: Austin Christ <austinwc@codeaurora.org> Co-authored-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Tested-by: Tyler Baicar <tbaicar@codeaurora.org> Signed-off-by: Jeffrey Hugo <jhugo@codeaurora.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Austin Christ <austinwc@codeaurora.org> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Timur Tabi <timur@codeaurora.org> Link: http://lkml.kernel.org/r/1496863138-11322-2-git-send-email-jhugo@codeaurora.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
-rw-r--r--kernel/sched/fair.c32
1 files changed, 20 insertions, 12 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 008c514dc241..c95880e216f6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6646,10 +6646,10 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
* our sched_group. We may want to revisit it if we couldn't
* meet load balance goals by pulling other tasks on src_cpu.
*
- * Also avoid computing new_dst_cpu if we have already computed
- * one in current iteration.
+ * Avoid computing new_dst_cpu for NEWLY_IDLE or if we have
+ * already computed one in current iteration.
*/
- if (!env->dst_grpmask || (env->flags & LBF_DST_PINNED))
+ if (env->idle == CPU_NEWLY_IDLE || (env->flags & LBF_DST_PINNED))
return 0;
/* Prevent to re-select dst_cpu via env's cpus */
@@ -8022,14 +8022,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
.tasks = LIST_HEAD_INIT(env.tasks),
};
- /*
- * For NEWLY_IDLE load_balancing, we don't need to consider
- * other cpus in our group
- */
- if (idle == CPU_NEWLY_IDLE)
- env.dst_grpmask = NULL;
-
- cpumask_copy(cpus, cpu_active_mask);
+ cpumask_and(cpus, sched_domain_span(sd), cpu_active_mask);
schedstat_inc(sd->lb_count[idle]);
@@ -8151,7 +8144,15 @@ more_balance:
/* All tasks on this runqueue were pinned by CPU affinity */
if (unlikely(env.flags & LBF_ALL_PINNED)) {
cpumask_clear_cpu(cpu_of(busiest), cpus);
- if (!cpumask_empty(cpus)) {
+ /*
+ * Attempting to continue load balancing at the current
+ * sched_domain level only makes sense if there are
+ * active CPUs remaining as possible busiest CPUs to
+ * pull load from which are not contained within the
+ * destination group that is receiving any migrated
+ * load.
+ */
+ if (!cpumask_subset(cpus, env.dst_grpmask)) {
env.loop = 0;
env.loop_break = sched_nr_migrate_break;
goto redo;
@@ -8447,6 +8448,13 @@ static int active_load_balance_cpu_stop(void *data)
.src_cpu = busiest_rq->cpu,
.src_rq = busiest_rq,
.idle = CPU_IDLE,
+ /*
+ * can_migrate_task() doesn't need to compute new_dst_cpu
+ * for active balancing. Since we have CPU_IDLE, but no
+ * @dst_grpmask we need to make that test go away with lying
+ * about DST_PINNED.
+ */
+ .flags = LBF_DST_PINNED,
};
schedstat_inc(sd->alb_count);