[tip:sched/core] sched/topology: Fix memory leak in __sdt_alloc()

[tip-bot for Shu Wang]

Commit-ID:  213c5a459ae0a7ef0a092f576aae2d5db6819360
Gitweb:     http://git.kernel.org/tip/213c5a459ae0a7ef0a092f576aae2d5db6819360
Author:     Shu Wang <shuwang@xxxxxxxxxx>
AuthorDate: Thu, 10 Aug 2017 15:52:16 +0800
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Fri, 25 Aug 2017 11:12:19 +0200

sched/topology: Fix memory leak in __sdt_alloc()

Found this issue by kmemleak: the 'sg' and 'sgc' pointers from
__sdt_alloc() might be leaked as each domain holds many groups' ref,
but in destroy_sched_domain(), it only declined the first group ref.

Onlining and offlining a CPU can trigger this leak, and cause OOM.

Reproducer for my 6 CPUs machine:

  while true
  do
      echo 0 > /sys/devices/system/cpu/cpu5/online;
      echo 1 > /sys/devices/system/cpu/cpu5/online;
  done

  unreferenced object 0xffff88007d772a80 (size 64):
    comm "cpuhp/5", pid 39, jiffies 4294719962 (age 35.251s)
    hex dump (first 32 bytes):
      c0 22 77 7d 00 88 ff ff 02 00 00 00 01 00 00 00  ."w}............
      40 2a 77 7d 00 88 ff ff 00 00 00 00 00 00 00 00  @*w}............
    backtrace:
      [<ffffffff8176525a>] kmemleak_alloc+0x4a/0xa0
      [<ffffffff8121efe1>] __kmalloc_node+0xf1/0x280
      [<ffffffff810d94a8>] build_sched_domains+0x1e8/0xf20
      [<ffffffff810da674>] partition_sched_domains+0x304/0x360
      [<ffffffff81139557>] cpuset_update_active_cpus+0x17/0x40
      [<ffffffff810bdb2e>] sched_cpu_activate+0xae/0xc0
      [<ffffffff810900e0>] cpuhp_invoke_callback+0x90/0x400
      [<ffffffff81090597>] cpuhp_up_callbacks+0x37/0xb0
      [<ffffffff81090887>] cpuhp_thread_fun+0xd7/0xf0
      [<ffffffff810b37e0>] smpboot_thread_fn+0x110/0x160
      [<ffffffff810af5d9>] kthread+0x109/0x140
      [<ffffffff81770e45>] ret_from_fork+0x25/0x30
      [<ffffffffffffffff>] 0xffffffffffffffff

  unreferenced object 0xffff88007d772a40 (size 64):
    comm "cpuhp/5", pid 39, jiffies 4294719962 (age 35.251s)
    hex dump (first 32 bytes):
      03 00 00 00 00 00 00 00 00 04 00 00 00 00 00 00  ................
      00 04 00 00 00 00 00 00 4f 3c fc ff 00 00 00 00  ........O<......
    backtrace:
      [<ffffffff8176525a>] kmemleak_alloc+0x4a/0xa0
      [<ffffffff8121efe1>] __kmalloc_node+0xf1/0x280
      [<ffffffff810da16d>] build_sched_domains+0xead/0xf20
      [<ffffffff810da674>] partition_sched_domains+0x304/0x360
      [<ffffffff81139557>] cpuset_update_active_cpus+0x17/0x40
      [<ffffffff810bdb2e>] sched_cpu_activate+0xae/0xc0
      [<ffffffff810900e0>] cpuhp_invoke_callback+0x90/0x400
      [<ffffffff81090597>] cpuhp_up_callbacks+0x37/0xb0
      [<ffffffff81090887>] cpuhp_thread_fun+0xd7/0xf0
      [<ffffffff810b37e0>] smpboot_thread_fn+0x110/0x160
      [<ffffffff810af5d9>] kthread+0x109/0x140
      [<ffffffff81770e45>] ret_from_fork+0x25/0x30
      [<ffffffffffffffff>] 0xffffffffffffffff

Reported-by: Chunyu Hu <chuhu@xxxxxxxxxx>
Signed-off-by: Shu Wang <shuwang@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Acked-by: Chunyu Hu <chuhu@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: liwang@xxxxxxxxxx
Link: http://lkml.kernel.org/r/1502351536-9108-1-git-send-email-shuwang@xxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 kernel/sched/topology.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index bd8b6d6..4197f13 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -335,7 +335,8 @@ static void free_sched_groups(struct sched_group *sg, int free_sgc)
 		if (free_sgc && atomic_dec_and_test(&sg->sgc->ref))
 			kfree(sg->sgc);
 
-		kfree(sg);
+		if (atomic_dec_and_test(&sg->ref))
+			kfree(sg);
 		sg = tmp;
 	} while (sg != first);
 }
@@ -343,15 +344,11 @@ static void free_sched_groups(struct sched_group *sg, int free_sgc)
 static void destroy_sched_domain(struct sched_domain *sd)
 {
 	/*
-	 * If its an overlapping domain it has private groups, iterate and
-	 * nuke them all.
+	 * A sched domain has many groups' reference, and an overlapping
+	 * domain has private groups, iterate and nuke them all.
 	 */
-	if (sd->flags & SD_OVERLAP) {
-		free_sched_groups(sd->groups, 1);
-	} else if (atomic_dec_and_test(&sd->groups->ref)) {
-		kfree(sd->groups->sgc);
-		kfree(sd->groups);
-	}
+	free_sched_groups(sd->groups, 1);
+
 	if (sd->shared && atomic_dec_and_test(&sd->shared->ref))
 		kfree(sd->shared);
 	kfree(sd);
@@ -668,6 +665,7 @@ build_group_from_child_sched_domain(struct sched_domain *sd, int cpu)
 	else
 		cpumask_copy(sg_span, sched_domain_span(sd));
 
+	atomic_inc(&sg->ref);
 	return sg;
 }