<div>Ah! I got your point</div>
<div>thank you very much<br></div>
<div class="gmail_quote">On Thu, Nov 11, 2010 at 6:19 PM, Christoph Hellwig <span dir="ltr"><<a href="mailto:hch@infradead.org">hch@infradead.org</a>></span> wrote:<br>
<blockquote style="BORDER-LEFT: #ccc 1px solid; MARGIN: 0px 0px 0px 0.8ex; PADDING-LEFT: 1ex" class="gmail_quote">
<div class="im">On Thu, Nov 11, 2010 at 11:10:33AM +0530, Ajeet Yadav wrote:<br>> I think mips folks agree with the change. I really wish to have there<br>> comment.<br>><br>> I also wish to know do we really need fix in XFS for virtual indexed<br>
> architecture, I think its generic issue as many architecture now use VIVT or<br>> VIPT caches. Do we want to say XFS is relatively unstable with virtual<br>> indexed architecture ?<br><br></div>The vmap flushing APIs I repeatedly pointed you at are the generic<br>
solution. They've been implement for arm, parisc and sh already, it's<br>just that no one has bothered to do it for mips yet.<br><br>Without the proper flushing anything that uses vmap, which includes<br>XFS is not "relatively unstable" but in fact not usable on systems<br>
with virtually indexed caches.<br></blockquote></div><br>