bnxt: use the NAPI skb allocation cache

All callers of build_skb() (*) in bnxt are in NAPI context.
The budget checking is somewhat convoluted because in the shared
completion queue cases Rx packets are discarded by netpoll
by forcing an error (E). But that happens before skb allocation.
Only a call chain starting at __bnxt_poll_work() can lead to
an skb allocation and it checks budget (b).

* bnxt_rx_multi_page_skb
* bnxt_rx_skb
  ` bp->rx_skb_func
  * bnxt_tpa_end
    ` bnxt_rx_pkt
      E bnxt_force_rx_discard
      E bnxt_poll_nitroa0
      b __bnxt_poll_work

Use napi_build_skb() to take advantage of the skb cache.
In iperf tests with HW-GRO enabled it barely makes a difference
but in cases where HW-GRO is not as effective (or disabled) it
can give even a >10% boost (20.7Gbps -> 23.1Gbps).

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 5d6ea27..5cc0dbe 100644 (file)
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -994,7 +994,7 @@ static struct sk_buff *bnxt_rx_multi_page_skb(struct bnxt *bp,
        dma_addr -= bp->rx_dma_offset;
        dma_sync_single_for_cpu(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE,
                                bp->rx_dir);
-       skb = build_skb(data_ptr - bp->rx_offset, BNXT_RX_PAGE_SIZE);
+       skb = napi_build_skb(data_ptr - bp->rx_offset, BNXT_RX_PAGE_SIZE);
        if (!skb) {
                page_pool_recycle_direct(rxr->page_pool, page);
                return NULL;
@@ -1069,7 +1069,7 @@ static struct sk_buff *bnxt_rx_skb(struct bnxt *bp,
                return NULL;
        }
 
-       skb = build_skb(data, bp->rx_buf_size);
+       skb = napi_build_skb(data, bp->rx_buf_size);
        dma_unmap_single_attrs(&bp->pdev->dev, dma_addr, bp->rx_buf_use_size,
                               bp->rx_dir, DMA_ATTR_WEAK_ORDERING);
        if (!skb) {
@@ -1677,7 +1677,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
                tpa_info->data_ptr = new_data + bp->rx_offset;
                tpa_info->mapping = new_mapping;
 
-               skb = build_skb(data, bp->rx_buf_size);
+               skb = napi_build_skb(data, bp->rx_buf_size);
                dma_unmap_single_attrs(&bp->pdev->dev, mapping,
                                       bp->rx_buf_use_size, bp->rx_dir,
                                       DMA_ATTR_WEAK_ORDERING);