mvneta: recycle buffers

Use the new recycling API for page_pool.
In a drop rate test, the packet rate increased by 10%,
from 296 Kpps to 326 Kpps.

perf top on a stock system shows:

Overhead  Shared Object     Symbol
  23.66%  [kernel]          [k] __pi___inval_dcache_area
  22.85%  [mvneta]          [k] mvneta_rx_swbm
   7.54%  [kernel]          [k] kmem_cache_alloc
   6.49%  [kernel]          [k] eth_type_trans
   3.94%  [kernel]          [k] dev_gro_receive
   3.91%  [kernel]          [k] __netif_receive_skb_core
   3.91%  [kernel]          [k] kmem_cache_free
   3.76%  [kernel]          [k] page_pool_release_page
   3.56%  [kernel]          [k] free_unref_page
   2.40%  [kernel]          [k] build_skb
   1.49%  [kernel]          [k] skb_release_data
   1.45%  [kernel]          [k] __alloc_pages_bulk
   1.30%  [kernel]          [k] page_frag_free

And this is the same output with recycling enabled:

Overhead  Shared Object     Symbol
  26.41%  [kernel]          [k] __pi___inval_dcache_area
  25.00%  [mvneta]          [k] mvneta_rx_swbm
   8.14%  [kernel]          [k] kmem_cache_alloc
   6.84%  [kernel]          [k] eth_type_trans
   4.44%  [kernel]          [k] __netif_receive_skb_core
   4.38%  [kernel]          [k] kmem_cache_free
   4.16%  [kernel]          [k] dev_gro_receive
   3.21%  [kernel]          [k] page_pool_put_page
   2.41%  [kernel]          [k] build_skb
   1.82%  [kernel]          [k] skb_release_data
   1.61%  [kernel]          [k] napi_gro_receive
   1.25%  [kernel]          [k] page_pool_refill_alloc_cache
   1.16%  [kernel]          [k] __netif_receive_skb_list_core

We can see that page_pool_release_page(), free_unref_page() and
__alloc_pages_bulk() are no longer on top of the list when receiving
traffic.

The test was done with mausezahn on the TX side with 64 byte raw
ethernet frames.
Signed-off-by: Matteo Croce <mcroce@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/marvell/mvneta.c

@@ -2320,7 +2320,7 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp,
 }
 
 static struct sk_buff *
-mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
+mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 		      struct xdp_buff *xdp, u32 desc_status)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
@@ -2331,7 +2331,7 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 
-	page_pool_release_page(rxq->page_pool, virt_to_page(xdp->data));
+	skb_mark_for_recycle(skb, virt_to_page(xdp->data), pool);
 
 	skb_reserve(skb, xdp->data - xdp->data_hard_start);
 	skb_put(skb, xdp->data_end - xdp->data);
@@ -2343,7 +2343,10 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 				skb_frag_page(frag), skb_frag_off(frag),
 				skb_frag_size(frag), PAGE_SIZE);
-		page_pool_release_page(rxq->page_pool, skb_frag_page(frag));
+		/* We don't need to reset pp_recycle here. It's already set, so
+		 * just mark fragments for recycling.
+		 */
+		page_pool_store_mem_info(skb_frag_page(frag), pool);
 	}
 
 	return skb;
@@ -2425,7 +2428,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 		    mvneta_run_xdp(pp, rxq, xdp_prog, &xdp_buf, frame_sz, &ps))
 			goto next;
 
-		skb = mvneta_swbm_build_skb(pp, rxq, &xdp_buf, desc_status);
+		skb = mvneta_swbm_build_skb(pp, rxq->page_pool, &xdp_buf, desc_status);
 		if (IS_ERR(skb)) {
 			struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);