Date: Fri, 7 Oct 2016 18:08:42 +0100
From: Al Viro <viro@ZenIV.linux.org.uk>
To: Brian Boylston <brian.boylston@hpe.com>
Cc: linux-nvdimm@ml01.01.org, linux-kernel@vger.kernel.org,
        toshi.kani@hpe.com, oliver.moreno@hpe.com,
        Ross Zwisler <ross.zwisler@linux.intel.com>,
        Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@redhat.com>,
        "H. Peter Anvin" <hpa@zytor.com>, x86@kernel.org,
        Dan Williams <dan.j.williams@intel.com>
Subject: Re: [PATCH] use a nocache copy for bvecs in copy_from_iter_nocache()
Message-ID: <20161007170842.GQ19539@ZenIV.linux.org.uk>
References: <20161007155511.21502-1-brian.boylston@hpe.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20161007155511.21502-1-brian.boylston@hpe.com>
User-Agent: Mutt/1.7.0 (2016-08-17)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 876
Lines: 18

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()