| To: | Tommy Christensen <tommy.christensen@xxxxxxxxx> |
|---|---|
| Subject: | Re: [NET] Move local_bh_disable back in dev_queue_xmit |
| From: | "David S. Miller" <davem@xxxxxxxxxxxxx> |
| Date: | Wed, 3 Nov 2004 12:50:30 -0800 |
| Cc: | herbert@xxxxxxxxxxxxxxxxxxx, mingo@xxxxxxx, netdev@xxxxxxxxxxx |
| In-reply-to: | <4188EFD1.4050909@tpack.net> |
| References: | <20041102225406.GA13760@gondor.apana.org.au> <4188EFD1.4050909@tpack.net> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Wed, 03 Nov 2004 15:48:49 +0100 Tommy Christensen <tommy.christensen@xxxxxxxxx> wrote: > Herbert Xu wrote: > > Hi Ingo: > > > > Your recent fix to dev_queue_xmit moved the local_bh_disable to > > include stuff like skb_linearize and skb_checksum_help. These > > are potentially expensive operations. Since they don't need to > > run with preempt off, we could simply move the local_bh_enable > > up instead. > > No, this breaks the normal return path. > > How about this instead? Yep, this one is better. Patch applied, thanks everyone. |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: [TCP] Modular IPv6 support in tcpdiag, David S. Miller |
|---|---|
| Next by Date: | Re: [NET] Move local_bh_disable back in dev_queue_xmit, Herbert Xu |
| Previous by Thread: | Re: [NET] Move local_bh_disable back in dev_queue_xmit, Tommy Christensen |
| Next by Thread: | Re: [NET] Move local_bh_disable back in dev_queue_xmit, Herbert Xu |
| Indexes: | [Date] [Thread] [Top] [All Lists] |