Re: [PATCH v3 net-next 08/14] mlx4: use order-0 pages for RX

@@ -68,6 +68,7 @@ static int mlx4_alloc_page(struct mlx4_en_priv *priv,
        frag->page = page;
        frag->dma = dma;
        frag->page_offset = priv->rx_headroom;
+       frag->pagecnt_bias = 1;
        return 0;
 }
 

@@ -97,7 +98,7 @@ static void mlx4_en_free_frag(const struct mlx4_en_priv *priv,
        if (frag->page) {
                dma_unmap_page(priv->ddev, frag->dma,
                               PAGE_SIZE, priv->dma_dir);
-               __free_page(frag->page);
+               __page_frag_cache_drain(frag->page, frag->pagecnt_bias);
        }
        /* We need to clear all fields, otherwise a change of priv->log_rx_info
         * could lead to see garbage later in frag->page.

@@ -470,6 +471,7 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 {
        const struct mlx4_en_frag_info *frag_info = priv->frag_info;
        unsigned int truesize = 0;
+       unsigned int pagecnt_bias;
        int nr, frag_size;
        struct page *page;
        dma_addr_t dma;

@@ -491,9 +493,10 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
                                     frag_size);
 
                truesize += frag_info->frag_stride;
+               pagecnt_bias = frags->pagecnt_bias--;
                if (frag_info->frag_stride == PAGE_SIZE / 2) {
                        frags->page_offset ^= PAGE_SIZE / 2;
-                       release = page_count(page) != 1 ||
+                       release = page_count(page) != pagecnt_bias ||
                                  page_is_pfmemalloc(page) ||
                                  page_to_nid(page) != numa_mem_id();
                } else {

@@ -504,9 +507,13 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
                }
                if (release) {
                        dma_unmap_page(priv->ddev, dma, PAGE_SIZE, priv->dma_dir);
+                       __page_frag_cache_drain(page, --pagecnt_bias);
                        frags->page = NULL;
                } else {
-                       page_ref_inc(page);
+                       if (pagecnt_bias == 1) {
+                               page_ref_add(page, USHRT_MAX);
+                               frags->pagecnt_bias = USHRT_MAX;
+                       }
                }
 
                nr++;

@@ -252,7 +252,12 @@ struct mlx4_en_tx_desc {
 struct mlx4_en_rx_alloc {
        struct page     *page;
        dma_addr_t      dma;
+#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
        u32             page_offset;
+#else
+       u16             page_offset;
+#endif
+       u16 pagecnt_bias;
 };
 
 #define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT)