From mboxrd@z Thu Jan 1 00:00:00 1970 From: Nick Piggin Subject: Re: [patch 2/2] lockless get_user_pages Date: Thu, 29 May 2008 05:43:59 +0200 Message-ID: <20080529034359.GI3258@wotan.suse.de> References: <20080527095519.4676.KOSAKI.MOTOHIRO@jp.fujitsu.com> <20080527022801.GB21578@wotan.suse.de> <20080527114350.4679.KOSAKI.MOTOHIRO@jp.fujitsu.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from cantor2.suse.de ([195.135.220.15]:35687 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753007AbYE2DoC (ORCPT ); Wed, 28 May 2008 23:44:02 -0400 Content-Disposition: inline In-Reply-To: <20080527114350.4679.KOSAKI.MOTOHIRO@jp.fujitsu.com> Sender: linux-arch-owner@vger.kernel.org List-ID: To: KOSAKI Motohiro Cc: Johannes Weiner , Andrew Morton , shaggy@austin.ibm.com, jens.axboe@oracle.com, torvalds@linux-foundation.org, linux-mm@kvack.org, linux-arch@vger.kernel.org, apw@shadowen.org On Tue, May 27, 2008 at 11:46:27AM +0900, KOSAKI Motohiro wrote: > > Aw, nobody likes fast_gup? ;) > > Ah, I misunderstood your intention. > I thought you disklike fast_gup.. > > I don't dislike it :() > > > > > Technically get_user_pages_lockless is wrong: the implementation may > > not be lockless so one cannot assume it will not take mmap sem and > > ptls. > > agreed. > > > > But I do like to make it clear that it is related to get_user_pages. > > get_current_user_pages(), maybe? Hmm, that's harder to grep for > > both then I guess. get_user_pages_current? > > Yeah, good name. Hmm, although now that I think about it more, fast_gup is not _quite_ just a get_user_pages for "current". In particular it requires a bit of thought as to whether the pages are likely to require page faults or not... so I've called it get_user_pages_fast()