From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from gate.crashing.org (gate.crashing.org [63.228.1.57]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTPS id BBA62100842 for ; Thu, 19 May 2011 07:52:11 +1000 (EST) Subject: Re: [PATCH 1/7] powerpc/mm: 64-bit 4k: use page-sized PMDs From: Benjamin Herrenschmidt To: Scott Wood In-Reply-To: <20110518164645.0ae83ad5@schlenkerla.am.freescale.net> References: <20110518210453.GA29500@schlenkerla.am.freescale.net> <1305754361.7481.2.camel@pasglop> <20110518164645.0ae83ad5@schlenkerla.am.freescale.net> Content-Type: text/plain; charset="UTF-8" Date: Thu, 19 May 2011 07:52:02 +1000 Message-ID: <1305755522.7481.10.camel@pasglop> Mime-Version: 1.0 Cc: linuxppc-dev@lists.ozlabs.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , > > Why do you want to create a virtual page table at the PMD level ? Also, > > you are changing the geometry of the page tables which I think we don't > > want. We chose that geometry so that the levels match the segment sizes > > on server, I think it may have an impact with the hugetlbfs code (check > > with David), it also was meant as a way to implement shared page tables > > on hash64 tho we never published that. > > The number of virtual page table misses were very high on certain loads. > Cutting back to a virtual PMD eliminates most of that for the benchmark I > tested, though it could still be painful for access patterns that are > extremely spread out through the 64-bit address space. I'll try a full > 4-level walk and see what the performance is like; I was aiming for a > compromise between random access and linear/localized access. Let's get more numbers first then :-) > Why does it need to match segment sizes on server? I'm not sure whether we have a dependency with hugetlbfs there, I need to check (remember we have one page size per segment there). For sharing page tables that came from us using the PMD pointer as a base to calculate the VSIDs. But I don't think we have plans to revive those patches in the immediate future. Cheers, Ben. > As for hugetlbfs, it merged easily enough with Becky's patches (you'll have > to ask her when they'll be published). > > -Scott