[Intel-wired-lan] [net-next PATCH v2 1/2] e1000: add initial XDP support
John Fastabend
john.fastabend at gmail.com
Fri Sep 9 23:33:10 UTC 2016
On 16-09-09 03:04 PM, Eric Dumazet wrote:
> On Fri, 2016-09-09 at 14:29 -0700, John Fastabend wrote:
>> From: Alexei Starovoitov <ast at fb.com>
>>
>
>
> So it looks like e1000_xmit_raw_frame() can return early,
> say if there is no available descriptor.
>
>> +static void e1000_xmit_raw_frame(struct e1000_rx_buffer *rx_buffer_info,
>> + unsigned int len,
>> + struct net_device *netdev,
>> + struct e1000_adapter *adapter)
>> +{
>> + struct netdev_queue *txq = netdev_get_tx_queue(netdev, 0);
>> + struct e1000_hw *hw = &adapter->hw;
>> + struct e1000_tx_ring *tx_ring;
>> +
>> + if (len > E1000_MAX_DATA_PER_TXD)
>> + return;
>> +
>> + /* e1000 only support a single txq at the moment so the queue is being
>> + * shared with stack. To support this requires locking to ensure the
>> + * stack and XDP are not running at the same time. Devices with
>> + * multiple queues should allocate a separate queue space.
>> + */
>> + HARD_TX_LOCK(netdev, txq, smp_processor_id());
>> +
>> + tx_ring = adapter->tx_ring;
>> +
>> + if (E1000_DESC_UNUSED(tx_ring) < 2) {
>> + HARD_TX_UNLOCK(netdev, txq);
>> + return;
>> + }
>> +
>> + e1000_tx_map_rxpage(tx_ring, rx_buffer_info, len);
>> + e1000_tx_queue(adapter, tx_ring, 0/*tx_flags*/, 1);
>> +
>> + writel(tx_ring->next_to_use, hw->hw_addr + tx_ring->tdt);
>> + mmiowb();
>> +
>> + HARD_TX_UNLOCK(netdev, txq);
>> +}
>> +
>> #define NUM_REGS 38 /* 1 based count */
>> static void e1000_regdump(struct e1000_adapter *adapter)
>> {
>> @@ -4142,6 +4247,19 @@ static struct sk_buff *e1000_alloc_rx_skb(struct e1000_adapter *adapter,
>> return skb;
>> }
>> + act = e1000_call_bpf(prog, page_address(p), length);
>> + switch (act) {
>> + case XDP_PASS:
>> + break;
>> + case XDP_TX:
>> + dma_sync_single_for_device(&pdev->dev,
>> + dma,
>> + length,
>> + DMA_TO_DEVICE);
>> + e1000_xmit_raw_frame(buffer_info, length,
>> + netdev, adapter);
>> + buffer_info->rxbuf.page = NULL;
>
>
> So I am trying to understand how pages are not leaked ?
>
>
Pages are being leaked thanks! v3 coming soon.
More information about the Intel-wired-lan
mailing list