| To: | "David S. Miller" <davem@xxxxxxxxxxxxx> |
|---|---|
| Subject: | Re: [PATCH] I/O space write barrier |
| From: | Greg Banks <gnb@xxxxxxxxxxxxxxxxx> |
| Date: | Thu, 30 Sep 2004 12:23:43 +1000 |
| Cc: | Jesse Barnes <jbarnes@xxxxxxxxxxxx>, akpm@xxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, Jeremy Higdon <jeremy@xxxxxxx>, John Partridge <johnip@xxxxxxx>, Linux Network Development list <netdev@xxxxxxxxxxx> |
| In-reply-to: | <20040929135029.38444afd.davem@davemloft.net> |
| Organization: | Silicon Graphics Inc, Australian Software Group. |
| References: | <200409271103.39913.jbarnes@engr.sgi.com> <20040929103646.GA4682@sgi.com> <20040929133500.59d78765.davem@davemloft.net> <200409291343.55863.jbarnes@engr.sgi.com> <20040929135029.38444afd.davem@davemloft.net> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Thu, 2004-09-30 at 06:50, David S. Miller wrote: > On Wed, 29 Sep 2004 13:43:55 -0700 > Jesse Barnes <jbarnes@xxxxxxxxxxxx> wrote: > > > The patch that actually implements mmiowb() already does this, I think Greg > > just used his patch for testing. Yes, that hunk will be unnecessary when Jesse's patch goes in. > The proper way to do it of course is to > > just use mmiowb() where needed in tg3 after the write barrier patch gets in. > > Perfect, please send me a tg3 patch once the mmiowb() bits > go into the tree. Will do. Greg. -- Greg Banks, R&D Software Engineer, SGI Australian Software Group. I don't speak for SGI. |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Survey on Open Source, Mike Chan |
|---|---|
| Next by Date: | Re: bad TSO performance in 2.6.9-rc2-BK, David S. Miller |
| Previous by Thread: | Re: [PATCH] I/O space write barrier, David S. Miller |
| Next by Thread: | Please route new work through -mm tree?, Stephen Hemminger |
| Indexes: | [Date] [Thread] [Top] [All Lists] |