| To: | "'Arthur Kepner'" <akepner@xxxxxxx>, "'Anton Blanchard'" <anton@xxxxxxxxx> |
|---|---|
| Subject: | RE: [PATCH] s2io: replace readq() with mmiowb() in s2io_xmit() |
| From: | "Ramkrishna Vepa" <ram.vepa@xxxxxxxxxxxx> |
| Date: | Tue, 3 May 2005 09:23:07 -0700 |
| Cc: | "'Leonid Grossman'" <leonid.grossman@xxxxxxxxxxxx>, <muhammad.shafiq@xxxxxxxxxxxx>, <ramkrishna.vepa@xxxxxxxxxxxx>, <netdev@xxxxxxxxxxx>, "'Ravinandan Arakali'" <ravinandan.arakali@xxxxxxxxxxxx> |
| Importance: | Normal |
| In-reply-to: | <Pine.LNX.4.61.0505030750010.16692@linux.site> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
Ordering is all that is required. We can get rid of the flush. Ram > -----Original Message----- > From: Arthur Kepner [mailto:akepner@xxxxxxx] > Sent: Tuesday, May 03, 2005 7:52 AM > To: Anton Blanchard > Cc: Ramkrishna Vepa; 'Leonid Grossman'; muhammad.shafiq@xxxxxxxxxxxx; > ramkrishna.vepa@xxxxxxxxxxxx; netdev@xxxxxxxxxxx; 'Ravinandan Arakali' > Subject: Re: [PATCH] s2io: replace readq() with mmiowb() in s2io_xmit() > > On Tue, 3 May 2005, Anton Blanchard wrote: > > > > > > [Ram] Yes, it is to ensure ordering as well as the flush of the io > that is > > > required in some platforms. > > > > If the flush of the IO is required I cant see how we can remove the > read. > > > > Agreed. Can someone from neterion comment? Is a flush required, or is > ordering all that's required here? > > -- > Arthur |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: IPsec performance, Miika Komu |
|---|---|
| Next by Date: | Re: icmp_unreachable uses wrong ip, Patrick McHardy |
| Previous by Thread: | Re: [PATCH] s2io: replace readq() with mmiowb() in s2io_xmit(), Arthur Kepner |
| Next by Thread: | Re: [PATCH] s2io: replace readq() with mmiowb() in s2io_xmit(), Anton Blanchard |
| Indexes: | [Date] [Thread] [Top] [All Lists] |