sched: fix a bug in sched domain degenerate

commit f29c9b1ccb52904ee442a933cf3dee628f9f4e62 upstream.

Impact: re-add incorrectly eliminated sched domain layers

(1) on i386 with SCHED_SMT and SCHED_MC enabled
	# mount -t cgroup -o cpuset xxx /mnt
	# echo 0 > /mnt/cpuset.sched_load_balance
	# mkdir /mnt/0
	# echo 0 > /mnt/0/cpuset.cpus
	# dmesg
	CPU0 attaching sched-domain:
	 domain 0: span 0 level CPU
	  groups: 0

(2) on i386 with SCHED_MC enabled but SCHED_SMT disabled
	# same with (1)
	# dmesg
	CPU0 attaching NULL sched-domain.

The bug is that some sched domains may be skipped unintentionally when
degenerating (optimizing) sched domains.

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: Gregory Haskins <ghaskins@novell.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/kernel/sched.c b/kernel/sched.c
index a992cbe01c73beef229fc19ee86313390d4c7f30..719f8ba2c35fde7f3c4e874d5a0a2af49e3e1d99 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -6802,15 +6802,17 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
        struct sched_domain *tmp;
 
        /* Remove the sched domains which do not contribute to scheduling. */
-       for (tmp = sd; tmp; tmp = tmp->parent) {
+       for (tmp = sd; tmp; ) {
                struct sched_domain *parent = tmp->parent;
                if (!parent)
                        break;
+
                if (sd_parent_degenerate(tmp, parent)) {
                        tmp->parent = parent->parent;
                        if (parent->parent)
                                parent->parent->child = tmp;
-               }
+               } else
+                       tmp = tmp->parent;
        }
 
        if (sd && sd_degenerate(sd)) {