This patch implements the alloc side of bulk API for the SLAB
allocator.
Further optimization are still possible by changing the call to
__do_cache_alloc() into something that can return multiple
objects. This optimization is left for later, given end results
already show in the area of 80% speedup.
Signed-off-by: Jesper Dangaard Brouer <brouer@xxxxxxxxxx>
---
mm/slab.c | 37 +++++++++++++++++++++++++++++++++++--
1 file changed, 35 insertions(+), 2 deletions(-)
diff --git a/mm/slab.c b/mm/slab.c
index a05f716031de..17931ea961d1 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3392,9 +3392,42 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
EXPORT_SYMBOL(kmem_cache_free_bulk);
int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
- void **p)
+ void **p)
{
- return __kmem_cache_alloc_bulk(s, flags, size, p);
+ size_t i;
+
+ s = slab_pre_alloc_hook(s, flags);
+ if (!s)
+ return 0;
+
+ cache_alloc_debugcheck_before(s, flags);
+
+ local_irq_disable();
+ for (i = 0; i < size; i++) {
+ void *objp = __do_cache_alloc(s, flags);
+
+ /* this call could be done outside IRQ disabled section */
+ objp = cache_alloc_debugcheck_after(s, flags, objp, _RET_IP_);
+
+ if (unlikely(!objp))
+ goto error;
+ p[i] = objp;
+ }
+ local_irq_enable();
+
+ /* Clear memory outside IRQ disabled section */
+ if (unlikely(flags & __GFP_ZERO))
+ for (i = 0; i < size; i++)
+ memset(p[i], 0, s->object_size);
+
+ slab_post_alloc_hook(s, flags, size, p);
+ /* FIXME: Trace call missing. Christoph would like a bulk variant */
+ return size;
+error:
+ local_irq_enable();
+ slab_post_alloc_hook(s, flags, i, p);
+ __kmem_cache_free_bulk(s, i, p);
+ return 0;
}
EXPORT_SYMBOL(kmem_cache_alloc_bulk);
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>