| To: | Anton Blanchard <anton@xxxxxxxxx> |
|---|---|
| Subject: | Re: [PATCH] s2io: replace readq() with mmiowb() in s2io_xmit() |
| From: | Arthur Kepner <akepner@xxxxxxx> |
| Date: | Mon, 2 May 2005 19:11:53 -0700 (PDT) |
| Cc: | Leonid Grossman <leonid.grossman@xxxxxxxxxxxx>, muhammad.shafiq@xxxxxxxxxxxx, ramkrishna.vepa@xxxxxxxxxxxx, netdev@xxxxxxxxxxx |
| In-reply-to: | <20050503014034.GC12682@krispykreme> |
| References: | <200504051836.j35IanDD005402@guinness.s2io.com> <Pine.LNX.4.61.0505021459240.16692@linux.site> <20050503014034.GC12682@krispykreme> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Tue, 3 May 2005, Anton Blanchard wrote: > > I didnt know mmiowb is supposed to be a replacement for PCI write > posting. Most architectures define mmiowb as nothing and so will be > broken with your change. > I thought that an arch was supposed to define mmiowb() if it needs it. In this case, the readq() is only being used for the side-effect of ordering the previous writes (the neterion folks can correct me if I'm wrong). -- Arthur |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: [PATCH] s2io: replace readq() with mmiowb() in s2io_xmit(), Anton Blanchard |
|---|---|
| Next by Date: | RE: [PATCH] s2io: replace readq() with mmiowb() in s2io_xmit(), Ramkrishna Vepa |
| Previous by Thread: | Re: [PATCH] s2io: replace readq() with mmiowb() in s2io_xmit(), Anton Blanchard |
| Next by Thread: | RE: [PATCH] s2io: replace readq() with mmiowb() in s2io_xmit(), Ramkrishna Vepa |
| Indexes: | [Date] [Thread] [Top] [All Lists] |