Unbound wq pool's node attribute is calculated at its allocation.
But it's now calculated based on possible cpu<->node information
which can be wrong after cpu hotplug/unplug.
If wrong pool->node is set, following allocation error will happen.
==
SLUB: Unable to allocate memory on node 2 (gfp=0x80d0)
cache: kmalloc-192, object size: 192, buffer size: 192, default order:
1, min order: 0
node 0: slabs: 6172, objs: 259224, free: 245741
node 1: slabs: 3261, objs: 136962, free: 127656
==
This patch fixes the node detection by making use of online cpu info.
Unlike cpumask, the best node can be calculated by degree of overlap
between attr->cpumask and numanode->online_cpumask.
This change doesn't corrupt original purpose of the old calculation.
Note: it's expected that this function is called as
pool_detect_best_node
get_unbound_pool
alloc_unbound_pwq
wq_update_unbound_numa
called at CPU_ONLINE/CPU_DOWN_PREPARE
and the latest online cpu info can be applied to a new wq pool,
which replaces old one.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hir...@jp.fujitsu.com>
---
kernel/workqueue.c | 38 ++++++++++++++++++++++++++------------
1 file changed, 26 insertions(+), 12 deletions(-)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 09b685d..7809154 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3440,6 +3440,31 @@ static void put_unbound_pool(struct worker_pool *pool)
}
/**
+ * pool_detect_best_node - detect a node which contains specified cpumask.
+ * Should be called with wq_pool_mutex held.
+ * Returns a online node where the most of given cpus are tied to.
+ */
+static int pool_detect_best_node(const struct cpumask *cpumask)
+{
+ int node, best, match, selected = NUMA_NO_NODE;
+ static struct cpumask andmask; /* under wq_pool_mutex */
+
+ if (!wq_numa_enabled ||
+ cpumask_subset(cpu_online_mask, cpumask))
+ goto out;
+ best = 0;
+ /* select a node which contains the most number of cpu */
+ for_each_node_state(node, N_ONLINE) {
+ cpumask_and(&andmask, cpumask, cpumask_of_node(node));
+ match = cpumask_weight(&andmask);
+ if (match > best)
+ selected = best;
+ }
+out:
+ return selected;
+}
+
+/**
* get_unbound_pool - get a worker_pool with the specified attributes
* @attrs: the attributes of the worker_pool to get
*
@@ -3457,7 +3482,6 @@ static struct worker_pool *get_unbound_pool(const struct
workqueue_attrs *attrs)
{
u32 hash = wqattrs_hash(attrs);
struct worker_pool *pool;
- int node;
lockdep_assert_held(&wq_pool_mutex);
@@ -3482,17 +3506,7 @@ static struct worker_pool *get_unbound_pool(const struct
workqueue_attrs *attrs)
* 'struct workqueue_attrs' comments for detail.
*/
pool->attrs->no_numa = false;
-
- /* if cpumask is contained inside a NUMA node, we belong to that node */
- if (wq_numa_enabled) {
- for_each_node(node) {
- if (cpumask_subset(pool->attrs->cpumask,
- wq_numa_possible_cpumask[node])) {
- pool->node = node;
- break;
- }
- }
- }
+ pool->node = pool_detect_best_node(pool->attrs->cpumask);
if (worker_pool_assign_id(pool) < 0)
goto fail;
--
1.8.3.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
