提交 385565a1 编写于 作者: L Lendacky, Thomas 提交者: David S. Miller

amd-xgbe: Use napi_alloc_skb when allocating skb in softirq

Use the napi_alloc_skb function to allocate an skb when running within
the softirq context to avoid calls to local_irq_save/restore.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
上级 4a57ebcc
......@@ -1821,16 +1821,15 @@ static void xgbe_rx_refresh(struct xgbe_channel *channel)
lower_32_bits(rdata->rdesc_dma));
}
static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata,
static struct sk_buff *xgbe_create_skb(struct napi_struct *napi,
struct xgbe_ring_data *rdata,
unsigned int *len)
{
struct net_device *netdev = pdata->netdev;
struct sk_buff *skb;
u8 *packet;
unsigned int copy_len;
skb = netdev_alloc_skb_ip_align(netdev, rdata->rx.hdr.dma_len);
skb = napi_alloc_skb(napi, rdata->rx.hdr.dma_len);
if (!skb)
return NULL;
......@@ -2000,7 +1999,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
rdata->rx.hdr.dma_len,
DMA_FROM_DEVICE);
skb = xgbe_create_skb(pdata, rdata, &put_len);
skb = xgbe_create_skb(napi, rdata, &put_len);
if (!skb) {
error = 1;
goto skip_data;
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册