[PATCH net-next v4 4/4] mvneta: recycle buffers

[Matteo Croce <mcroce@linux.microsoft.com>]

From: Matteo Croce <mcroce@microsoft.com>

Use the new recycling API for page_pool.
In a drop rate test, the packet rate increased di 10%,
from 269 Kpps to 296 Kpps.

perf top on a stock system shows:

Overhead  Shared Object     Symbol
  21.78%  [kernel]          [k] __pi___inval_dcache_area
  21.66%  [mvneta]          [k] mvneta_rx_swbm
   7.00%  [kernel]          [k] kmem_cache_alloc
   6.05%  [kernel]          [k] eth_type_trans
   4.44%  [kernel]          [k] kmem_cache_free.part.0
   3.80%  [kernel]          [k] __netif_receive_skb_core
   3.68%  [kernel]          [k] dev_gro_receive
   3.65%  [kernel]          [k] get_page_from_freelist
   3.43%  [kernel]          [k] page_pool_release_page
   3.35%  [kernel]          [k] free_unref_page

And this is the same output with recycling enabled:

Overhead  Shared Object     Symbol
  24.10%  [kernel]          [k] __pi___inval_dcache_area
  23.02%  [mvneta]          [k] mvneta_rx_swbm
   7.19%  [kernel]          [k] kmem_cache_alloc
   6.50%  [kernel]          [k] eth_type_trans
   4.93%  [kernel]          [k] __netif_receive_skb_core
   4.77%  [kernel]          [k] kmem_cache_free.part.0
   3.93%  [kernel]          [k] dev_gro_receive
   3.03%  [kernel]          [k] build_skb
   2.91%  [kernel]          [k] page_pool_put_page
   2.85%  [kernel]          [k] __xdp_return

The test was done with mausezahn on the TX side with 64 byte raw
ethernet frames.

Signed-off-by: Matteo Croce <mcroce@microsoft.com>
---
 drivers/net/ethernet/marvell/mvneta.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 7d5cd9bc6c99..6d2f8dce4900 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/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, pp, &xdp_buf, desc_status);
 		if (IS_ERR(skb)) {
 			struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
 
-- 
2.31.1