[<prev] [next>] [day] [month] [year] [list]
Message-ID: <tip-jssl8t34ho7afo6w4xufmhrs@git.kernel.org>
Date: Sat, 19 May 2012 04:32:00 -0700
From: tip-bot for Peter Zijlstra <a.p.zijlstra@...llo.nl>
To: linux-tip-commits@...r.kernel.org
Cc: linux-kernel@...r.kernel.org, hpa@...or.com, mingo@...nel.org,
torvalds@...ux-foundation.org, a.p.zijlstra@...llo.nl,
pjt@...gle.com, cl@...ux.com, riel@...hat.com,
akpm@...ux-foundation.org, bharata.rao@...il.com,
aarcange@...hat.com, Lee.Schermerhorn@...com,
suresh.b.siddha@...el.com, danms@...ibm.com, tglx@...utronix.de
Subject: [tip:sched/numa] sched/numa: Implement hotplug callbacks
Commit-ID: 56ec1b7e22d71a9981409f79f5d78509a3efd61f
Gitweb: http://git.kernel.org/tip/56ec1b7e22d71a9981409f79f5d78509a3efd61f
Author: Peter Zijlstra <a.p.zijlstra@...llo.nl>
AuthorDate: Tue, 6 Mar 2012 17:37:25 +0100
Committer: Ingo Molnar <mingo@...nel.org>
CommitDate: Sat, 19 May 2012 12:55:20 +0200
sched/numa: Implement hotplug callbacks
start/stop numa balance threads on-demand using cpu-hotplug.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Cc: Suresh Siddha <suresh.b.siddha@...el.com>
Cc: Paul Turner <pjt@...gle.com>
Cc: Dan Smith <danms@...ibm.com>
Cc: Bharata B Rao <bharata.rao@...il.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@...com>
Cc: Christoph Lameter <cl@...ux.com>
Cc: Rik van Riel <riel@...hat.com>
Cc: Andrea Arcangeli <aarcange@...hat.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>
Link: http://lkml.kernel.org/n/tip-jssl8t34ho7afo6w4xufmhrs@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@...nel.org>
---
kernel/sched/numa.c | 88 ++++++++++++++++++++++++++++++++++++++++++---------
1 files changed, 73 insertions(+), 15 deletions(-)
diff --git a/kernel/sched/numa.c b/kernel/sched/numa.c
index c9ec90d..7447903 100644
--- a/kernel/sched/numa.c
+++ b/kernel/sched/numa.c
@@ -200,9 +200,15 @@ static struct node_queue *lock_ne_nq(struct numa_entity *ne)
for (;;) {
node = ACCESS_ONCE(ne->node);
- BUG_ON(node == -1);
- nq = nq_of(node);
+ /*
+ * Make sure any dequeue is properly done before
+ * we can observe node == -1, see dequeue_ne().
+ */
+ smp_rmb();
+ if (node == -1)
+ return NULL;
+ nq = nq_of(node);
spin_lock(&nq->lock);
if (likely(ne->node == node))
break;
@@ -264,13 +270,17 @@ static void dequeue_ne(struct numa_entity *ne)
{
struct node_queue *nq;
- if (ne->node == -1) // XXX serialization
- return;
-
nq = lock_ne_nq(ne);
- ne->node = -1;
- __dequeue_ne(nq, ne);
- spin_unlock(&nq->lock);
+ if (nq) {
+ __dequeue_ne(nq, ne);
+ /*
+ * ensure the dequeue is complete before lock_ne_nq()
+ * can observe the ne->node == -1.
+ */
+ smp_wmb();
+ ne->node = -1;
+ spin_unlock(&nq->lock);
+ }
}
static void init_ne(struct numa_entity *ne)
@@ -710,31 +720,79 @@ static int numad_thread(void *data)
return 0;
}
+static int __cpuinit
+numa_hotplug(struct notifier_block *nb, unsigned long action, void *hcpu)
+{
+ int cpu = (long)hcpu;
+ int node = cpu_to_node(cpu);
+ struct node_queue *nq = nq_of(node);
+ struct task_struct *numad;
+ int err = 0;
+
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_UP_PREPARE:
+ if (nq->numad)
+ break;
+
+ numad = kthread_create_on_node(numad_thread,
+ nq, node, "numad/%d", node);
+ if (IS_ERR(numad)) {
+ err = PTR_ERR(numad);
+ break;
+ }
+
+ nq->numad = numad;
+ nq->next_schedule = jiffies + HZ; // XXX sync-up?
+ break;
+
+ case CPU_ONLINE:
+ wake_up_process(nq->numad);
+ break;
+
+ case CPU_DEAD:
+ case CPU_UP_CANCELED:
+ if (!nq->numad)
+ break;
+
+ if (cpumask_any_and(cpu_online_mask,
+ cpumask_of_node(node)) >= nr_cpu_ids) {
+ kthread_stop(nq->numad);
+ nq->numad = NULL;
+ }
+ break;
+ }
+
+ return notifier_from_errno(err);
+}
+
static __init int numa_init(void)
{
- int node;
+ int node, cpu, err;
nqs = kzalloc(sizeof(struct node_queue*) * nr_node_ids, GFP_KERNEL);
BUG_ON(!nqs);
- for_each_node(node) { // XXX hotplug
+ for_each_node(node) {
struct node_queue *nq = kmalloc_node(sizeof(*nq),
GFP_KERNEL | __GFP_ZERO, node);
BUG_ON(!nq);
- nq->numad = kthread_create_on_node(numad_thread,
- nq, node, "numad/%d", node);
- BUG_ON(IS_ERR(nq->numad));
-
spin_lock_init(&nq->lock);
INIT_LIST_HEAD(&nq->entity_list);
nq->next_schedule = jiffies + HZ;
nq->node = node;
nqs[node] = nq;
+ }
- wake_up_process(nq->numad);
+ get_online_cpus();
+ cpu_notifier(numa_hotplug, 0);
+ for_each_online_cpu(cpu) {
+ err = numa_hotplug(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
+ BUG_ON(notifier_to_errno(err));
+ numa_hotplug(NULL, CPU_ONLINE, (void *)(long)cpu);
}
+ put_online_cpus();
return 0;
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists