<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html;charset=ISO-8859-1" http-equiv="Content-Type">
</head>
<body bgcolor="#ffffff" text="#000000">
ron minnich wrote:
<blockquote
cite="mid:13426df10711081447o688550a4jc01be2d7f06209e0@mail.gmail.com"
type="cite">
<meta http-equiv="Content-Type" content="text/html; ">
<meta name="Generator"
content="MS Exchange Server version 6.5.7652.24">
<title>Re: [Lguest] [PATCH] virtio config_ops refactoring</title>
<!-- Converted from text/plain format -->
<p><font size="2">Hi, I'm sorry, I've been stuck on other things (NFS
RDMA anyone?) and<br>
missed part of this discussion.<br>
<br>
Is it really the case that operations on virtio devices will involve<br>
outl/inl etc.?<br>
</font></p>
</blockquote>
What's the problem with them?<br>
Except for the kick event it's not performance critical and the
difference between pio vmexit<br>
and hypercall exit is very small.<br>
I don't know about problems in other architectures, maybe mmio is
better?<br>
Dor.<br>
<blockquote
cite="mid:13426df10711081447o688550a4jc01be2d7f06209e0@mail.gmail.com"
type="cite">
<p><font size="2"><br>
Apologies in advance for my failure to pay attention.<br>
<br>
thanks<br>
<br>
ron<br>
_______________________________________________<br>
Lguest mailing list<br>
<a class="moz-txt-link-abbreviated" href="mailto:Lguest@ozlabs.org">Lguest@ozlabs.org</a><br>
<a moz-do-not-send="true"
href="https://ozlabs.org/mailman/listinfo/lguest">https://ozlabs.org/mailman/listinfo/lguest</a><br>
</font>
</p>
</blockquote>
<br>
</body>
</html>