|To:||"Jon Fraser [jfraser"@broadcom.com], email@example.com|
|Subject:||Re: [PATCH 2.6.24][MIPS]Work in progress: fix HIGHMEM-enabled dcache flushing on 32-bit processor|
|From:||David VomLehn <firstname.lastname@example.org>|
|Date:||Wed, 02 Apr 2008 14:56:47 -0700|
|Authentication-results:||sj-dkim-1; header.Fromemail@example.com; dkim=pass ( sig from cisco.com/sjdkim1004 verified; );|
|Dkim-signature:||v=1; a=rsa-sha256; q=dns/txt; l=1118; t=1207173418; x=1208037418; c=relaxed/simple; s=sjdkim1004; h=Content-Type:From:Subject:Content-Transfer-Encoding:MIME-Version; d=cisco.com; firstname.lastname@example.org; z=From:=20David=20VomLehn=20<email@example.com> |Subject:=20Re=3A=20[PATCH=202.6.24][MIPS]Work=20in=20progr ess=3A=20fix=20HIGHMEM-enabled=20dcache=0A=20flushing=20on=2 032-bit=20processor |Sender:=20; bh=uOYvlErAfqKD8lrMpRH3pKnur3snz1z8iQ1zzvUcals=; b=LY4psVsAnXhwZ5irV2eOvLCprFnXsorilOAPUJqng7iRlw8wZkyqGzNdC2 EClFNI7A/vLQk111JTCcU9cBEjllmQa8mmYZiu4HEct1bdzU35/4YmS19YnO 6cZ5+43yqZaB6iCAZbwD2XTEwHKEHqWcPP7q3FX9zhsH46KktHxhw=;|
|Illegal-object:||Syntax error in To: address found on lappi.linux-mips.net: To: "Jon Fraser [jfraser"@broadcom.com] ^-missing end of address|
|User-agent:||Thunderbird 188.8.131.52 (Windows/20080213)|
Did this fix your NFS problem? I'm working on discontiguous memory platforms as well. Jon Fraser On Wed, 2008-03-12 at 19:31 -0700, David VomLehn wrote:This patch is a work in progress, per Ralf's suggestion from last week. It is intended to fix dcache flushing issues when using HIGHMEM support. We get much better results with this patch applied, but I would not characterize our 2.6.24 port as stable, yet, so there may be other HIGHMEM-related issues.
Yes, we are able to boot using NFS with this patch. There are some other minor changes that appear necessary for correct cache flushing but which don't seem to be causing any actual issues. (Cache stuff just works that way--you don't know you've got a problem until you get into some obscure corner case). I'll post these as soon as I can get to it.
I can't say whether these are all the changes required for high memory support, but we sure get a lot farther when we use them...
-- David VomLehn, firstname.lastname@example.org The opinions expressed herein are likely mine, but might not be my employer's...
|<Prev in Thread]||Current Thread||[Next in Thread>|
|Previous by Date:||[PATCH] PbAu1200: fix header breakage, Sergei Shtylyov|
|Next by Date:||Re: [PATCH][MIPS][3/6]: AR7: VLYNQ bus, Matteo Croce|
|Previous by Thread:||Re: [PATCH 2.6.24][MIPS]Work in progress: fix HIGHMEM-enabled dcache flushing on 32-bit processor, Jon Fraser|
|Next by Thread:|
|Indexes:||[Date] [Thread] [Top] [All Lists]|