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:   Thu, 12 Dec 2019 16:07:56 -0800 (PST)
From:   David Rientjes <rientjes@google.com>
To:     Christoph Hellwig <hch@lst.de>
cc:     "Lendacky, Thomas" <Thomas.Lendacky@amd.com>,
        Keith Busch <kbusch@kernel.org>, Jens Axboe <axboe@kernel.dk>,
        "Singh, Brijesh" <brijesh.singh@amd.com>,
        Ming Lei <ming.lei@redhat.com>,
        Peter Gonda <pgonda@google.com>,
        Jianxiong Gao <jxgao@google.com>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "x86@kernel.org" <x86@kernel.org>,
        "iommu@lists.linux-foundation.org" <iommu@lists.linux-foundation.org>
Subject: Re: [bug] __blk_mq_run_hw_queue suspicious rcu usage
In-Reply-To: <20191128064056.GA19822@lst.de>
Message-ID: <alpine.DEB.2.21.1912121550230.148507@chino.kir.corp.google.com>
References: <alpine.DEB.2.21.1909041434580.160038@chino.kir.corp.google.com> <20190905060627.GA1753@lst.de> <alpine.DEB.2.21.1909051534050.245316@chino.kir.corp.google.com> <alpine.DEB.2.21.1909161641320.9200@chino.kir.corp.google.com>
 <alpine.DEB.2.21.1909171121300.151243@chino.kir.corp.google.com> <1d74607e-37f7-56ca-aba3-5a3bd7a68561@amd.com> <20190918132242.GA16133@lst.de> <alpine.DEB.2.21.1911271359000.135363@chino.kir.corp.google.com> <20191128064056.GA19822@lst.de>
User-Agent: Alpine 2.21 (DEB 202 2017-01-01)
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Thu, 28 Nov 2019, Christoph Hellwig wrote:

> > So we're left with making dma_pool_alloc(GFP_ATOMIC) actually be atomic 
> > even when the DMA needs to be unencrypted for SEV.  Christoph's suggestion 
> > was to wire up dmapool in kernel/dma/remap.c for this.  Is that necessary 
> > to be done for all devices that need to do dma_pool_alloc(GFP_ATOMIC) or 
> > can we do it within the DMA API itself so it's transparent to the driver?
> 
> It needs to be transparent to the driver.  Lots of drivers use GFP_ATOMIC
> dma allocations, and all of them are broken on SEV setups currently.
> 

Not my area, so bear with me.

Since all DMA must be unencrypted in this case, what happens if all 
dma_direct_alloc_pages() calls go through the DMA pool in 
kernel/dma/remap.c when force_dma_unencrypted(dev) == true since 
__PAGE_ENC is cleared for these ptes?  (Ignoring for a moment that this 
special pool should likely be a separate dma pool.)

I assume a general depletion of that atomic pool so 
DEFAULT_DMA_COHERENT_POOL_SIZE becomes insufficient.  I'm not sure what 
size any DMA pool wired up for this specific purpose would need to be 
sized at, so I assume dynamic resizing is required.

It shouldn't be *that* difficult to supplement kernel/dma/remap.c with the 
ability to do background expansion of the atomic pool when nearing its 
capacity for this purpose?  I imagine that if we just can't allocate pages 
within the DMA mask that it's the only blocker to dynamic expansion and we 
don't oom kill for lowmem.  But perhaps vm.lowmem_reserve_ratio is good 
enough protection?

Beyond that, I'm not sure what sizing would be appropriate if this is to 
be a generic solution in the DMA API for all devices that may require 
unecrypted memory.