From: "Kani, Toshimitsu" <toshi.kani@hpe.com>
To: "viro@ZenIV.linux.org.uk" <viro@ZenIV.linux.org.uk>,
        "Boylston, Brian" <brian.boylston@hpe.com>
CC: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "tglx@linutronix.de" <tglx@linutronix.de>,
        "x86@kernel.org" <x86@kernel.org>,
        "dan.j.williams@intel.com" <dan.j.williams@intel.com>,
        "hpa@zytor.com" <hpa@zytor.com>,
        "linux-nvdimm@lists.01.org" <linux-nvdimm@ml01.01.org>,
        "Moreno, Oliver" <oliver.moreno@hpe.com>,
        "mingo@redhat.com" <mingo@redhat.com>,
        "ross.zwisler@linux.intel.com" <ross.zwisler@linux.intel.com>
Subject: Re: [PATCH] use a nocache copy for bvecs in copy_from_iter_nocache()
Thread-Topic: [PATCH] use a nocache copy for bvecs in copy_from_iter_nocache()
Thread-Index: AQHSILN+aItLHflkh0KwEo1pStmsFKCdOYEAgASZ44A=
Date: Mon, 10 Oct 2016 15:26:03 +0000
Message-ID: <1476113071.20881.15.camel@hpe.com>
References: <20161007155511.21502-1-brian.boylston@hpe.com>
         <20161007170842.GQ19539@ZenIV.linux.org.uk>
In-Reply-To: <20161007170842.GQ19539@ZenIV.linux.org.uk>
Accept-Language: en-US
Content-Language: en-US
spamdiagnosticoutput: 1:99
spamdiagnosticmetadata: NSPM
Content-Type: text/plain; charset="utf-8"
Content-ID: <49938475457C2849B27452052CD4DCE6@NAMPRD84.PROD.OUTLOOK.COM>
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-originalarrivaltime: 10 Oct 2016 15:26:03.5545
 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: 105b2061-b669-4b31-92ac-24d304d195dc
X-MS-Exchange-Transport-CrossTenantHeadersStamped: CS1PR84MB0295
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org
Content-Transfer-Encoding: 8bit
X-MIME-Autoconverted: from base64 to 8bit by mail.home.local id u9AH2k6v003982
Content-Length: 1160
Lines: 30

On Fri, 2016-10-07 at 18:08 +0100, Al Viro wrote:
> On Fri, Oct 07, 2016 at 10:55:11AM -0500, Brian Boylston wrote:
> > 
> > copy_from_iter_nocache() is only "nocache" for iovecs.  Enhance it
> > to also use a nocache copy for bvecs.  This improves performance by
> > 2-3X when splice()ing to a file in a DAX-mounted, pmem-backed file
> > system.
> 
> > 
> > +static void memcpy_from_page_nocache(char *to, struct page *page,
> > size_t offset, size_t len)
> > +{
> > +	char *from = kmap_atomic(page);
> > +	__copy_from_user_inatomic_nocache(to, from, len);
> > +	kunmap_atomic(from);
> > +}
> 
> At the very least, it will blow up on any architecture with split
> userland and kernel MMU contexts.  You *can't* feed a kernel pointer
> to things like that and expect it to work.  At the very least, you
> need to add memcpy_nocache() and have it default to memcpy(), with
> non-dummy version on x86.  And use _that_, rather than messing with
> __copy_from_user_inatomic_nocache()

Good point.  I think we can add memcpy_nocache() which calls
__copy_from_user_inatomic_nocache() on x86 and defauts to memcpy() on
other architectures.

Thanks,
-Toshi