From mboxrd@z Thu Jan 1 00:00:00 1970 From: santosh.shilimkar@ti.com (Santosh Shilimkar) Date: Tue, 22 May 2012 14:52:48 +0530 Subject: [PATCH v2] RFC: ARM: cache-l2x0: update workaround for PL310 errata 727915 In-Reply-To: <20120522085256.GA7286@mudshark.cambridge.arm.com> References: <1337546505-24660-1-git-send-email-linus.walleij@stericsson.com> <20120522085256.GA7286@mudshark.cambridge.arm.com> Message-ID: <4FBB5AE8.4000801@ti.com> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On Tuesday 22 May 2012 02:22 PM, Will Deacon wrote: > Hi Santosh, > > On Mon, May 21, 2012 at 07:04:21AM +0100, Shilimkar, Santosh wrote: >> On Mon, May 21, 2012 at 2:11 AM, Linus Walleij >> wrote: >>> From: Colin Cross >>> >>> ARM errata 727915 for PL310 has been updated to include a new >>> workaround required for PL310 r2p0 for l2x0_flush_all, which also >>> affects l2x0_clean_all in my testing. For r2p0, clean or flush >>> each set/way individually. For r3p0 or greater, use the debug >>> register for cleaning and flushing. >>> >>> Requires exporting the cache_id, sets and ways detected in the >>> init function for later use. >>> >>> Cc: Will Deacon >>> Cc: Santosh Shilimkar >>> Cc: Per Fransson >>> Signed-off-by: Colin Cross >>> Signed-off-by: Linus Walleij >>> --- >>> I found this thing in the Android tree, it looks like it could >>> be pretty serious so I'm mailing it out. If it is correct I >>> guess it should even be tagged for -stable? >>> >>> v2: what about actually git commit --amend in the rebase changes >>> for -rc7? Sorry for the screwup... >>> --- >> This was observed on OMAP4460 devices. Though the errata >> document doesn't support it, the issue seen with l2 clean was >> indeed fixed $subject fix. > > I'm not sure I follow. Which version of the PL310 is in OMAP4460? Are you > saying that the current workaround didn't work but the one in this patch > did? Do you have a testcase? > It's r3p1. IIRC, the errata fix I did(debug register) was only for flush (clean & inv) but Colin found in his testing that it's needed for clean_all as well. I don't have testcase. Colin might be able to suggest one. Regards santosh