From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1751284AbdAMUIc (ORCPT <rfc822;w@1wt.eu>);
        Fri, 13 Jan 2017 15:08:32 -0500
Received: from zeniv.linux.org.uk ([195.92.253.2]:56000 "EHLO
        ZenIV.linux.org.uk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1751048AbdAMUIa (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Fri, 13 Jan 2017 15:08:30 -0500
Date: Fri, 13 Jan 2017 20:08:27 +0000
From: Al Viro <viro@ZenIV.linux.org.uk>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: "Alan J. Wylie" <alan@wylie.me.uk>,
        Thorsten Leemhuis <regressions@leemhuis.info>,
        linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: 4.9.0 regression in pipe-backed iov_iter with systemd-nspawn
Message-ID: <20170113200826.GP1555@ZenIV.linux.org.uk>
References: <22647.59020.331664.632444@wylie.me.uk>
 <CA+55aFy+sj1SmPrTPAon-=M=DRtiS5ak0DJtQe0TMBU3sMJ0kg@mail.gmail.com>
 <22648.1838.747474.51727@wylie.me.uk>
 <CA+55aFybndhA_RPd6gAPmbYYzOL5Le1tCjb2GYVGgFVU8xoD+g@mail.gmail.com>
 <22648.32903.752857.203733@wylie.me.uk>
 <20170113093359.GJ1555@ZenIV.linux.org.uk>
 <22648.41914.351371.678606@wylie.me.uk>
 <20170113102019.GK1555@ZenIV.linux.org.uk>
 <20170113111842.GL1555@ZenIV.linux.org.uk>
 <CA+55aFw0T1wARr8kLvcuHkA4bDE+YJ18wKtPaxc1vFHWPgfQQg@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CA+55aFw0T1wARr8kLvcuHkA4bDE+YJ18wKtPaxc1vFHWPgfQQg@mail.gmail.com>
User-Agent: Mutt/1.7.1 (2016-10-04)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Fri, Jan 13, 2017 at 11:33:18AM -0800, Linus Torvalds wrote:

> What am I missing?

The fact that we want to free the _tail_, not the beginning of the
damn thing.

> Why is "pipe_advance()" written in that incomprehensible form? Why
> don't we do the pipe_buf_release() as we advance through it, instead
> of doing it at the end?
> 
> Also, the line
> 
>                 buf->len = size;
> 
> in that pipe_advance() function looks buggy. "size" is how much we
> *remove* from buf->len, shouldn't we update buf->len by subtracting
> size?

Because it's "truncate to size", not "throw everything up to that point
out".

We have some amount of data pushed into pipe (in this case - 0) and we
have some buffers allocated by ..._get_pages() past the end of it.
Some of that we want to keep (again, in this case - none) and have the next
copy_to_iter() go after those, the rest we discard.