sched/numa: Fix task_numa_free() lockdep splat

From: Mike Galbraith
Date: Mon Apr 07 2014 - 04:55:15 EST


Sasha reported that lockdep claims that the following commit:
made numa_group.lock interrupt unsafe:

156654f491dd ("sched/numa: Move task_numa_free() to __put_task_struct()")

While I don't see how that could be, given the commit in question moved
task_numa_free() from one irq enabled region to another, the below does
make both gripes and lockups upon gripe with numa=fake=4 go away.

Reported-by: Sasha Levin <sasha.levin@xxxxxxxxxx>
Fixes: 156654f491dd ("sched/numa: Move task_numa_free() to __put_task_struct()")
Signed-off-by: Mike Galbraith <bitbucket@xxxxxxxxx>
Signed-off-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: torvalds@xxxxxxxxxxxxxxxxxxxx
Cc: mgorman@xxxxxxxx
Cc: akpm@xxxxxxxxxxxxxxxxxxxx
Cc: Dave Jones <davej@xxxxxxxxxx>
Link: http://lkml.kernel.org/r/1396860915.5170.5.camel@xxxxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>

---
kernel/sched/fair.c | 13 +++++++------
kernel/sched/sched.h | 9 +++++++++
2 files changed, 16 insertions(+), 6 deletions(-)

--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1371,7 +1371,7 @@ static void task_numa_placement(struct t
/* If the task is part of a group prevent parallel updates to group stats */
if (p->numa_group) {
group_lock = &p->numa_group->lock;
- spin_lock(group_lock);
+ spin_lock_irq(group_lock);
}

/* Find the node with the highest number of faults */
@@ -1432,7 +1432,7 @@ static void task_numa_placement(struct t
}
}

- spin_unlock(group_lock);
+ spin_unlock_irq(group_lock);
}

/* Preferred node as the node with the most faults */
@@ -1532,7 +1532,8 @@ static void task_numa_group(struct task_
if (!join)
return;

- double_lock(&my_grp->lock, &grp->lock);
+ BUG_ON(irqs_disabled());
+ double_lock_irq(&my_grp->lock, &grp->lock);

for (i = 0; i < 2*nr_node_ids; i++) {
my_grp->faults[i] -= p->numa_faults[i];
@@ -1546,7 +1547,7 @@ static void task_numa_group(struct task_
grp->nr_tasks++;

spin_unlock(&my_grp->lock);
- spin_unlock(&grp->lock);
+ spin_unlock_irq(&grp->lock);

rcu_assign_pointer(p->numa_group, grp);

@@ -1565,14 +1566,14 @@ void task_numa_free(struct task_struct *
void *numa_faults = p->numa_faults;

if (grp) {
- spin_lock(&grp->lock);
+ spin_lock_irq(&grp->lock);
for (i = 0; i < 2*nr_node_ids; i++)
grp->faults[i] -= p->numa_faults[i];
grp->total_faults -= p->total_numa_faults;

list_del(&p->numa_entry);
grp->nr_tasks--;
- spin_unlock(&grp->lock);
+ spin_unlock_irq(&grp->lock);
rcu_assign_pointer(p->numa_group, NULL);
put_numa_group(grp);
}
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1402,6 +1402,15 @@ static inline void double_lock(spinlock_
spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
}

+static inline void double_lock_irq(spinlock_t *l1, spinlock_t *l2)
+{
+ if (l1 > l2)
+ swap(l1, l2);
+
+ spin_lock_irq(l1);
+ spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
+}
+
static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2)
{
if (l1 > l2)






--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/