net: hns3: batch the page reference count updates

Batch the page reference count updates instead of doing them
one at a time. By doing this we can improve the overall receive
performance by avoid some atomic increment operations when the
rx page is reused.
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/hisilicon/hns3/hns3_enet.c

@@ -2302,6 +2302,8 @@ static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
 	cb->buf  = page_address(p);
 	cb->length = hns3_page_size(ring);
 	cb->type = DESC_TYPE_PAGE;
+	page_ref_add(p, USHRT_MAX - 1);
+	cb->pagecnt_bias = USHRT_MAX;
 
 	return 0;
 }
@@ -2311,8 +2313,8 @@ static void hns3_free_buffer(struct hns3_enet_ring *ring,
 {
 	if (cb->type == DESC_TYPE_SKB)
 		dev_kfree_skb_any((struct sk_buff *)cb->priv);
-	else if (!HNAE3_IS_TX_RING(ring))
-		put_page((struct page *)cb->priv);
+	else if (!HNAE3_IS_TX_RING(ring) && cb->pagecnt_bias)
+		__page_frag_cache_drain(cb->priv, cb->pagecnt_bias);
 	memset(cb, 0, sizeof(*cb));
 }
 
@@ -2610,6 +2612,11 @@ static bool hns3_page_is_reusable(struct page *page)
 		!page_is_pfmemalloc(page);
 }
 
+static bool hns3_can_reuse_page(struct hns3_desc_cb *cb)
+{
+	return (page_count(cb->priv) - cb->pagecnt_bias) == 1;
+}
+
 static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
 				struct hns3_enet_ring *ring, int pull_len,
 				struct hns3_desc_cb *desc_cb)
@@ -2618,6 +2625,7 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
 	int size = le16_to_cpu(desc->rx.size);
 	u32 truesize = hns3_buf_size(ring);
 
+	desc_cb->pagecnt_bias--;
 	skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len,
 			size - pull_len, truesize);
 
@@ -2625,20 +2633,27 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
 	 * when page_offset rollback to zero, flag default unreuse
 	 */
 	if (unlikely(!hns3_page_is_reusable(desc_cb->priv)) ||
-	    (!desc_cb->page_offset && page_count(desc_cb->priv) > 1))
+	    (!desc_cb->page_offset && !hns3_can_reuse_page(desc_cb))) {
+		__page_frag_cache_drain(desc_cb->priv, desc_cb->pagecnt_bias);
 		return;
+	}
 
 	/* Move offset up to the next cache line */
 	desc_cb->page_offset += truesize;
 
 	if (desc_cb->page_offset + truesize <= hns3_page_size(ring)) {
 		desc_cb->reuse_flag = 1;
-		/* Bump ref count on page before it is given */
-		get_page(desc_cb->priv);
-	} else if (page_count(desc_cb->priv) == 1) {
+	} else if (hns3_can_reuse_page(desc_cb)) {
 		desc_cb->reuse_flag = 1;
 		desc_cb->page_offset = 0;
-		get_page(desc_cb->priv);
+	} else if (desc_cb->pagecnt_bias) {
+		__page_frag_cache_drain(desc_cb->priv, desc_cb->pagecnt_bias);
+		return;
+	}
+
+	if (unlikely(!desc_cb->pagecnt_bias)) {
+		page_ref_add(desc_cb->priv, USHRT_MAX);
+		desc_cb->pagecnt_bias = USHRT_MAX;
 	}
 }
 
@@ -2846,7 +2861,8 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length,
 		if (likely(hns3_page_is_reusable(desc_cb->priv)))
 			desc_cb->reuse_flag = 1;
 		else /* This page cannot be reused so discard it */
-			put_page(desc_cb->priv);
+			__page_frag_cache_drain(desc_cb->priv,
+						desc_cb->pagecnt_bias);
 
 		ring_ptr_move_fw(ring, next_to_clean);
 		return 0;

drivers/net/ethernet/hisilicon/hns3/hns3_enet.h

@@ -287,6 +287,7 @@ struct hns3_desc_cb {
 
 	/* desc type, used by the ring user to mark the type of the priv data */
 	u16 type;
+	u16 pagecnt_bias;
 };
 
 enum hns3_pkt_l3type {