[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1366387006.2716.3.camel@bwh-desktop.uk.solarflarecom.com>
Date: Fri, 19 Apr 2013 16:56:46 +0100
From: Ben Hutchings <bhutchings@...arflare.com>
To: Jim Baxter <jim_baxter@...tor.com>
CC: Eric Dumazet <eric.dumazet@...il.com>,
"David S. Miller" <davem@...emloft.net>,
Fabio Estevam <fabio.estevam@...escale.com>,
Frank Li <Frank.Li@...escale.com>,
Fugang Duan <B38611@...escale.com>, <netdev@...r.kernel.org>
Subject: Re: [PATCH net-next v4 1/1] net: fec: Enable imx6 enet checksum
acceleration.
On Fri, 2013-04-19 at 16:55 +0100, Jim Baxter wrote:
> On 19/04/13 16:29, Eric Dumazet wrote:
> > On Fri, 2013-04-19 at 16:10 +0100, Jim Baxter wrote:
> >>
> >> +static int
> >> +fec_enet_clear_csum(struct sk_buff *skb, struct net_device *ndev)
> >> +{
> >> + /* Only run for packets requiring a checksum. */
> >> + if (skb->ip_summed != CHECKSUM_PARTIAL)
> >> + return 0;
> >> +
> >> + if (unlikely(skb_cow_head(skb, 0)))
> >> + return -1;
> >> +
> >> + *(__sum16 *)(skb->head + skb->csum_start + skb->csum_offset) = 0;
> >> +
> >> + return 0;
> >> +}
> >
> >
> >
> >> + /* HW acceleration for ICMP TCP UDP checksum */
> >> + if (fec_enet_clear_csum(skb, ndev))
> >> + return NETDEV_TX_BUSY;
> >
> > No : You must drop the packet and return NETDEV_TX_OK
> >
> >
> >
>
> I have no issue with changing it, but I am curious, by returning OK will
> the kernel not regard it a sent packet and it will be lost?
Correct. This is normal behaviour when short of memory; look at any
other driver that allocates memory on the TX path.
Ben.
--
Ben Hutchings, Staff Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists