Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Fri, 20 Dec 2019 21:23:46 +0100
From:   Peter Zijlstra <peterz@infradead.org>
To:     Alexey Brodkin <Alexey.Brodkin@synopsys.com>
Cc:     Robin Murphy <robin.murphy@arm.com>,
        Marc Gonzalez <marc.w.gonzalez@free.fr>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        Rafael Wysocki <rjw@rjwysocki.net>,
        LKML <linux-kernel@vger.kernel.org>,
        Linux ARM <linux-arm-kernel@lists.infradead.org>,
        Dmitry Torokhov <dmitry.torokhov@gmail.com>,
        Will Deacon <will@kernel.org>,
        Russell King <rmk+kernel@armlinux.org.uk>,
        Bjorn Andersson <bjorn.andersson@linaro.org>,
        Tejun Heo <tj@kernel.org>, Mark Brown <broonie@kernel.org>,
        arcml <linux-snps-arc@lists.infradead.org>,
        Vineet Gupta <Vineet.Gupta1@synopsys.com>,
        Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
Subject: Re: [RFC PATCH v1] devres: align devres.data strictly only for
 devm_kmalloc()
Message-ID: <20191220202346.GT2827@hirez.programming.kicks-ass.net>
References: <74ae22cd-08c1-d846-3e1d-cbc38db87442@free.fr>
 <bf020a68-00fd-2bb7-c3b6-00f5befa293a@free.fr>
 <20191220140655.GN2827@hirez.programming.kicks-ass.net>
 <9be1d523-e92c-836b-b79d-37e880d092a0@arm.com>
 <CY4PR1201MB012011E554FC69F7B074B7E2A12D0@CY4PR1201MB0120.namprd12.prod.outlook.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CY4PR1201MB012011E554FC69F7B074B7E2A12D0@CY4PR1201MB0120.namprd12.prod.outlook.com>
User-Agent: Mutt/1.10.1 (2018-07-13)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Fri, Dec 20, 2019 at 07:32:16PM +0000, Alexey Brodkin wrote:

> Well it somehow used to work for quite some time now with the data-buffer
> being allocated with 4 words offset (which is 16 bytes for 32-bit platform

3 words, devres_node is 3 words.

Which is exactly why we had to change it, the odd alignment caused ARC
to explode.

> and 32 for 64-bit which is still much less than mentioned 128 bytes).
> Or we just never managed to identify those rare cases when data corruption
> really happened?

The races are rather rare methinks, you'd have to get a list-op
concurrently with a DMA.

If you get the list corrupted, I'm thinking the crash is fairly likely,
albeit really difficuly to debug.

> > No matter which way round you allocate devres and data, by necessity
> > they're always going to consume the same total amount of memory.
> 
> So then the next option I guess is to separate meta-data from data buffers
> completely. Are there any reasons to not do that

Dunno, should work just fine I think.

> other than the hack we're
> discussing here (meta-data in the beginning of the buffer) used to work OK-ish?

If meta-data at the beginngin used to work, I don't see why meta-data at
the end wouldn't work equally well. They'd be equally broken.

But I'm still flabbergasted at the fact that they're doing non-coherent
DMA to kmalloc memory, I thought we had a DMA api for that, with a
special allocator and everything (but what do I know, I've never used
that).