| To: | Lennert Buytenhek <buytenh@xxxxxxxxxxxxxx> |
|---|---|
| Subject: | Re: [PATCH]: was Re: LLTX and netif_stop_queue |
| From: | "David S. Miller" <davem@xxxxxxxxxxxxx> |
| Date: | Tue, 25 Jan 2005 22:27:05 -0800 |
| Cc: | shemminger@xxxxxxxx, roland@xxxxxxxxxxx, hadi@xxxxxxxxxx, iod00d@xxxxxx, eric.lemoine@xxxxxxxxx, netdev@xxxxxxxxxxx, ak@xxxxxxx, openib-general@xxxxxxxxxx, kaber@xxxxxxxxx |
| In-reply-to: | <20050121105452.GA12988@xxxxxxxxxxxxxxxxx> |
| References: | <527jmu8nbw.fsf@xxxxxxxxxxx> <5cac192f0501030907c755135@xxxxxxxxxxxxxx> <20050103171227.GD7370@xxxxxxxxxxxxxxxxx> <1104812294.1085.53.camel@xxxxxxxxxxxxxxxx> <20050119144711.3fdd3d93.davem@xxxxxxxxxxxxx> <20050119151853.259de49a@xxxxxxxxxxxxxxxxx> <20050119164640.6c67bdfa.davem@xxxxxxxxxxxxx> <52r7kgu5n5.fsf@xxxxxxxxxxx> <20050119230526.393a5184.davem@xxxxxxxxxxxxx> <20050120085611.33f9485e@xxxxxxxxxxxxxxxxx> <20050121105452.GA12988@xxxxxxxxxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Fri, 21 Jan 2005 11:54:52 +0100 Lennert Buytenhek <buytenh@xxxxxxxxxxxxxx> wrote: > If multiple CPUs can call into the tunneling drivers without taking > any locks, we'd need some extra locking in there, or just do what > Alexey describes and keep track of recursion in the skb. Another idea is that, just like how loopback made it's statistics per-cpu for LLTX support, this recursion variable could be per-cpu as well. |
| Previous by Date: | [PATCH] atalk: remove gcc warning when PROC_FS=n, Randy.Dunlap |
|---|---|
| Next by Date: | [PATCH] arlan: remove gcc warning with CONFIG_PROC_FS=n, Randy.Dunlap |
| Previous by Thread: | Re: [PATCH]: was Re: LLTX and netif_stop_queue, Lennert Buytenhek |
| Next by Thread: | Re: [PATCH]: was Re: LLTX and netif_stop_queue, Lennert Buytenhek |
| Indexes: | [Date] [Thread] [Top] [All Lists] |