2 files changed, 57 insertions, 27 deletions

diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index b5b195305346..6d517a37c18b 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -65,7 +65,7 @@
 #define PP_ALLOC_CACHE_REFILL	64
 struct pp_alloc_cache {
 	u32 count;
-	void *cache[PP_ALLOC_CACHE_SIZE];
+	struct page *cache[PP_ALLOC_CACHE_SIZE];
 };
 
 struct page_pool_params {
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 40e1b2beaa6c..9ec1aa9640ad 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -203,38 +203,17 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
 	return true;
 }
 
-/* slow path */
-noinline
-static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
-						 gfp_t _gfp)
+static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
+						 gfp_t gfp)
 {
-	unsigned int pp_flags = pool->p.flags;
 	struct page *page;
-	gfp_t gfp = _gfp;
-
-	/* We could always set __GFP_COMP, and avoid this branch, as
-	 * prep_new_page() can handle order-0 with __GFP_COMP.
-	 */
-	if (pool->p.order)
-		gfp |= __GFP_COMP;
-
-	/* FUTURE development:
-	 *
-	 * Current slow-path essentially falls back to single page
-	 * allocations, which doesn't improve performance.  This code
-	 * need bulk allocation support from the page allocator code.
-	 */
 
-	/* Cache was empty, do real allocation */
-#ifdef CONFIG_NUMA
+	gfp |= __GFP_COMP;
 	page = alloc_pages_node(pool->p.nid, gfp, pool->p.order);
-#else
-	page = alloc_pages(gfp, pool->p.order);
-#endif
-	if (!page)
+	if (unlikely(!page))
 		return NULL;
 
-	if ((pp_flags & PP_FLAG_DMA_MAP) &&
+	if ((pool->p.flags & PP_FLAG_DMA_MAP) &&
 	    unlikely(!page_pool_dma_map(pool, page))) {
 		put_page(page);
 		return NULL;
@@ -243,6 +222,57 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
 	/* Track how many pages are held 'in-flight' */
 	pool->pages_state_hold_cnt++;
 	trace_page_pool_state_hold(pool, page, pool->pages_state_hold_cnt);
+	return page;
+}
+
+/* slow path */
+noinline
+static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
+						 gfp_t gfp)
+{
+	const int bulk = PP_ALLOC_CACHE_REFILL;
+	unsigned int pp_flags = pool->p.flags;
+	unsigned int pp_order = pool->p.order;
+	struct page *page;
+	int i, nr_pages;
+
+	/* Don't support bulk alloc for high-order pages */
+	if (unlikely(pp_order))
+		return __page_pool_alloc_page_order(pool, gfp);
+
+	/* Unnecessary as alloc cache is empty, but guarantees zero count */
+	if (unlikely(pool->alloc.count > 0))
+		return pool->alloc.cache[--pool->alloc.count];
+
+	/* Mark empty alloc.cache slots "empty" for alloc_pages_bulk_array */
+	memset(&pool->alloc.cache, 0, sizeof(void *) * bulk);
+
+	nr_pages = alloc_pages_bulk_array(gfp, bulk, pool->alloc.cache);
+	if (unlikely(!nr_pages))
+		return NULL;
+
+	/* Pages have been filled into alloc.cache array, but count is zero and
+	 * page element have not been (possibly) DMA mapped.
+	 */
+	for (i = 0; i < nr_pages; i++) {
+		page = pool->alloc.cache[i];
+		if ((pp_flags & PP_FLAG_DMA_MAP) &&
+		    unlikely(!page_pool_dma_map(pool, page))) {
+			put_page(page);
+			continue;
+		}
+		pool->alloc.cache[pool->alloc.count++] = page;
+		/* Track how many pages are held 'in-flight' */
+		pool->pages_state_hold_cnt++;
+		trace_page_pool_state_hold(pool, page,
+					   pool->pages_state_hold_cnt);
+	}
+
+	/* Return last page */
+	if (likely(pool->alloc.count > 0))
+		page = pool->alloc.cache[--pool->alloc.count];
+	else
+		page = NULL;
 
 	/* When page just alloc'ed is should/must have refcnt 1. */
 	return page;