summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2017-04-25 14:00:49 +0200
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2017-07-21 08:12:23 +0200
commit8f70f49650b428378320c12dee41122d9f9e258e (patch)
tree5f5cdd5542bf9d22958cd7312fb09b612e23b50d /kernel
parent49c159f59d5328cc86900fbb175356e1cb0be7f2 (diff)
downloadlinux-stable-8f70f49650b428378320c12dee41122d9f9e258e.tar.gz
linux-stable-8f70f49650b428378320c12dee41122d9f9e258e.tar.bz2
linux-stable-8f70f49650b428378320c12dee41122d9f9e258e.zip
sched/topology: Fix overlapping sched_group_mask
commit 73bb059f9b8a00c5e1bf2f7ca83138c05d05e600 upstream. The point of sched_group_mask is to select those CPUs from sched_group_cpus that can actually arrive at this balance domain. The current code gets it wrong, as can be readily demonstrated with a topology like: node 0 1 2 3 0: 10 20 30 20 1: 20 10 20 30 2: 30 20 10 20 3: 20 30 20 10 Where (for example) domain 1 on CPU1 ends up with a mask that includes CPU0: [] CPU1 attaching sched-domain: [] domain 0: span 0-2 level NUMA [] groups: 1 (mask: 1), 2, 0 [] domain 1: span 0-3 level NUMA [] groups: 0-2 (mask: 0-2) (cpu_capacity: 3072), 0,2-3 (cpu_capacity: 3072) This causes sched_balance_cpu() to compute the wrong CPU and consequently should_we_balance() will terminate early resulting in missed load-balance opportunities. The fixed topology looks like: [] CPU1 attaching sched-domain: [] domain 0: span 0-2 level NUMA [] groups: 1 (mask: 1), 2, 0 [] domain 1: span 0-3 level NUMA [] groups: 0-2 (mask: 1) (cpu_capacity: 3072), 0,2-3 (cpu_capacity: 3072) (note: this relies on OVERLAP domains to always have children, this is true because the regular topology domains are still here -- this is before degenerate trimming) Debugged-by: Lauro Ramos Venancio <lvenanci@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Fixes: e3589f6c81e4 ("sched: Allow for overlapping sched_domain spans") Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/sched/core.c18
1 files changed, 17 insertions, 1 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index de691daea709..d0eb16373bf0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5852,6 +5852,9 @@ enum s_alloc {
* Build an iteration mask that can exclude certain CPUs from the upwards
* domain traversal.
*
+ * Only CPUs that can arrive at this group should be considered to continue
+ * balancing.
+ *
* Asymmetric node setups can result in situations where the domain tree is of
* unequal depth, make sure to skip domains that already cover the entire
* range.
@@ -5870,11 +5873,24 @@ static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
for_each_cpu(i, sg_span) {
sibling = *per_cpu_ptr(sdd->sd, i);
- if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+
+ /*
+ * Can happen in the asymmetric case, where these siblings are
+ * unused. The mask will not be empty because those CPUs that
+ * do have the top domain _should_ span the domain.
+ */
+ if (!sibling->child)
+ continue;
+
+ /* If we would not end up here, we can't continue from here */
+ if (!cpumask_equal(sg_span, sched_domain_span(sibling->child)))
continue;
cpumask_set_cpu(i, sched_group_mask(sg));
}
+
+ /* We must not have empty masks here */
+ WARN_ON_ONCE(cpumask_empty(sched_group_mask(sg)));
}
/*