Re: [PATCH ref0] net: add Faraday FTMAC100 10/100 Ethernet driver

[Po-Yu Chuang]

Hi Eric,

On Fri, Feb 25, 2011 at 10:32 AM, Po-Yu Chuang <ratbert.chuang@xxxxxxxxx> wrote:
> On Fri, Feb 25, 2011 at 1:48 AM, Eric Dumazet <eric.dumazet@xxxxxxxxx> wrote:
>> Le jeudi 24 fÃvrier 2011 Ã 18:39 +0100, Eric Dumazet a Ãcrit :
>>> Le jeudi 24 fÃvrier 2011 Ã 17:29 +0800, Po-Yu Chuang a Ãcrit :
>>> > From: Po-Yu Chuang <ratbert@xxxxxxxxxxxxxxxx>
>>> > +
>>> > +static bool ftmac100_rx_packet(struct ftmac100 *priv, int *processed)
>>> > +{
>>> > + Â struct net_device *netdev = priv->netdev;
>>> > + Â struct ftmac100_rxdes *rxdes;
>>> > + Â struct sk_buff *skb;
>>> > + Â struct page *page;
>>> > + Â dma_addr_t map;
>>> > + Â int length;
>>> > +
>>> > + Â rxdes = ftmac100_rx_locate_first_segment(priv);
>>> > + Â if (!rxdes)
>>> > + Â Â Â Â Â return false;
>>> > +
>>> > + Â if (unlikely(ftmac100_rx_packet_error(priv, rxdes))) {
>>> > + Â Â Â Â Â ftmac100_rx_drop_packet(priv);
>>> > + Â Â Â Â Â return true;
>>> > + Â }
>>> > +
>>> > + Â /*
>>> > + Â Â* It is impossible to get multi-segment packets
>>> > + Â Â* because we always provide big enough receive buffers.
>>> > + Â Â*/
>>> > + Â if (unlikely(!ftmac100_rxdes_last_segment(rxdes)))
>>> > + Â Â Â Â Â BUG();
>>> > +
>>> > + Â /* start processing */
>>> > + Â skb = netdev_alloc_skb_ip_align(netdev, ETH_HLEN);
>>>
>>> Oh I see... You should allocate a bigger head (say... 128 bytes)
>>>
>>> And copy in it up to 128 bytes of first part... this to avoid upper
>>> stack to reallocate skb head (because IP/TCP processing need to get
>>> their headers in skb head)
>>
>> Take a look at drivers/net/niu.c :
>>
>> #define RX_SKB_ALLOC_SIZE Â 128 + NET_IP_ALIGN
>>
>> static int niu_process_rx_pkt(...)
>> {
>> Â Â Â Â...
>> Â Â Â Âskb = netdev_alloc_skb(np->dev, RX_SKB_ALLOC_SIZE);
>> Â Â Â Â...
>> Â Â Â Âwhile (1) {
>> Â Â Â Â Â Â Â Â...
>> Â Â Â Â Â Â Â Âniu_rx_skb_append(skb, page, off, append_size);
>> Â Â Â Â}
>> }
>
> Oh I got it.
>
> I will try this and redo the benchmarking.

It's a little faster than v5 now. Thanks.
I will submit the current version later.

One more question just curious, why 128 bytes?

best regards,
Po-Yu Chuang
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/