Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id ; Wed, 13 Feb 2002 15:02:45 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id ; Wed, 13 Feb 2002 15:02:35 -0500 Received: from perninha.conectiva.com.br ([200.250.58.156]:36621 "HELO perninha.conectiva.com.br") by vger.kernel.org with SMTP id ; Wed, 13 Feb 2002 15:02:21 -0500 Date: Wed, 13 Feb 2002 16:52:34 -0200 (BRST) From: Marcelo Tosatti To: Hugh Dickins Cc: Linus Torvalds , Andrew Morton , Andrea Arcangeli , Rik van Riel , "David S. Miller" , Benjamin LaHaise , Gerd Knorr , Dave Jones , linux-kernel@vger.kernel.org Subject: Re: [PATCH] __free_pages_ok oops In-Reply-To: Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 12 Feb 2002, Hugh Dickins wrote: > On Sat, 9 Feb 2002, Benjamin LaHaise wrote: > > On Fri, Feb 08, 2002 at 05:46:56PM +0000, Hugh Dickins wrote: > > > Ben, you probably have an AIO opinion here. Is there a circumstance > > > in which AIO can unpin a user page at interrupt time, after the > > > calling task has (exited or) unmapped the page? > > > > If the user unmaps the page, then aio is left holding the last reference > > to the page and will unmap it from irq or bh context (potentially task > > context too). With networked aio, pages from userspace (anonymous or > > page cache pages) will be released by the network stack from bh context. > > Even now, I'm guess that should be possible with the zero copy flag... Hugh. Are you sure we can free a page from IRQ/BH context with _current_ 2.4 ? Please make sure so. - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/