net: page_pool: use alloc_pages_bulk in refill code path

There are cases where the page_pool need to refill with pages from the
page allocator.  Some workloads cause the page_pool to release pages
instead of recycling these pages.

For these workload it can improve performance to bulk alloc pages from the
page-allocator to refill the alloc cache.

For XDP-redirect workload with 100G mlx5 driver (that use page_pool)
redirecting xdp_frame packets into a veth, that does XDP_PASS to create an
SKB from the xdp_frame, which then cannot return the page to the
page_pool.

Performance results under GitHub xdp-project[1]:
 [1] https://github.com/xdp-project/xdp-project/blob/master/areas/mem/page_pool06_alloc_pages_bulk.org

Mel: The patch "net: page_pool: convert to use alloc_pages_bulk_array
variant" was squashed with this patch. From the test page, the array
variant was superior with one of the test results as follows.

	Kernel		XDP stats       CPU     pps           Delta
	Baseline	XDP-RX CPU      total   3,771,046       n/a
	List		XDP-RX CPU      total   3,940,242    +4.49%
	Array		XDP-RX CPU      total   4,249,224   +12.68%

Link: https://lkml.kernel.org/r/20210325114228.27719-10-mgorman@techsingularity.netSigned-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Reviewed-by: Alexander Lobakin <alobakin@pm.me>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: David Miller <davem@davemloft.net>
Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

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 {

net/core/page_pool.c

@@ -203,46 +203,76 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
 	return true;
 }
 
+static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
+						 gfp_t gfp)
+{
+	struct page *page;
+
+	gfp |= __GFP_COMP;
+	page = alloc_pages_node(pool->p.nid, gfp, pool->p.order);
+	if (unlikely(!page))
+		return NULL;
+
+	if ((pool->p.flags & PP_FLAG_DMA_MAP) &&
+	    unlikely(!page_pool_dma_map(pool, page))) {
+		put_page(page);
+		return NULL;
+	}
+
+	/* 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)
+						 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;
-	gfp_t gfp = _gfp;
+	int i, nr_pages;
 
-	/* 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;
+	/* Don't support bulk alloc for high-order pages */
+	if (unlikely(pp_order))
+		return __page_pool_alloc_page_order(pool, gfp);
 
-	/* 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.
-	 */
+	/* Unnecessary as alloc cache is empty, but guarantees zero count */
+	if (unlikely(pool->alloc.count > 0))
+		return pool->alloc.cache[--pool->alloc.count];
 
-	/* Cache was empty, do real allocation */
-#ifdef CONFIG_NUMA
-	page = alloc_pages_node(pool->p.nid, gfp, pool->p.order);
-#else
-	page = alloc_pages(gfp, pool->p.order);
-#endif
-	if (!page)
+	/* 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);
-		return NULL;
+			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);
+		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;