Call slowpath __slab_alloc() from within the bulk loop, as the
side-effect of this call likely repopulates c->freelist.
Choose to reenable local IRQs while calling slowpath.
Saving some optimizations for later. E.g. it is possible to
extract parts of __slab_alloc() and avoid the unnecessary and
expensive (37 cycles) local_irq_{save,restore}. For now, be
happy calling __slab_alloc() this lower icache impact of this
func and I don't have to worry about correctness.
Signed-off-by: Jesper Dangaard Brouer <bro...@redhat.com>
---
mm/slub.c | 27 +++++++++++++++++----------
1 file changed, 17 insertions(+), 10 deletions(-)
diff --git a/mm/slub.c b/mm/slub.c
index 26f64005a347..98d0e6f73ec1 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2776,8 +2776,23 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t
flags, size_t size,
for (i = 0; i < size; i++) {
void *object = c->freelist;
- if (!object)
- break;
+ if (unlikely(!object)) {
+ c->tid = next_tid(c->tid);
+ local_irq_enable();
+
+ /* Invoke slow path one time, then retry fastpath
+ * as side-effect have updated c->freelist
+ */
+ p[i] = __slab_alloc(s, flags, NUMA_NO_NODE,
+ _RET_IP_, c);
+ if (unlikely(!p[i])) {
+ __kmem_cache_free_bulk(s, i, p);
+ return false;
+ }
+ local_irq_disable();
+ c = this_cpu_ptr(s->cpu_slab);
+ continue; /* goto for-loop */
+ }
c->freelist = get_freepointer(s, object);
p[i] = object;
@@ -2793,14 +2808,6 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t
flags, size_t size,
memset(p[j], 0, s->object_size);
}
- /* Fallback to single elem alloc */
- for (; i < size; i++) {
- void *x = p[i] = kmem_cache_alloc(s, flags);
- if (unlikely(!x)) {
- __kmem_cache_free_bulk(s, i, p);
- return false;
- }
- }
return true;
}
EXPORT_SYMBOL(kmem_cache_alloc_bulk);
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
