Received-SPF: pass (google.com: domain of linux-kernel+bounces-77892-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Date: Fri, 23 Feb 2024 00:03:01 -0800
From: Christoph Hellwig <hch@infradead.org>
To: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>,
	Maxime Coquelin <maxime.coquelin@redhat.com>, jasowang@redhat.com,
	xuanzhuo@linux.alibaba.com, xieyongji@bytedance.com,
	axboe@kernel.dk, gregkh@linuxfoundation.org, brauner@kernel.org,
	lstoakes@gmail.com, virtualization@lists.linux.dev,
	linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
	david.marchand@redhat.com
Subject: Re: [PATCH] vduse: implement DMA sync callbacks
Message-ID: <ZdhRNeJRo1UaZt2F@infradead.org>
References: <20240219170606.587290-1-maxime.coquelin@redhat.com>
 <ZdRqcIRmDD-70ap3@infradead.org>
 <20240222152541-mutt-send-email-mst@kernel.org>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20240222152541-mutt-send-email-mst@kernel.org>

On Thu, Feb 22, 2024 at 03:29:10PM -0500, Michael S. Tsirkin wrote:
> In a sense ... but on the other hand, the "fake DMA" metaphor seems to
> work surprisingly well, like in this instance - internal bounce buffer
> looks a bit like non-coherent DMA.  A way to make this all prettier
> would I guess be to actually wrap all of DMA with virtio wrappers which
> would all go if () dma_... else vduse_...; or something to this end.  A
> lot of work for sure, and is it really worth it? if the only crazy
> driver is vduse I'd maybe rather keep the crazy hacks local there ...

Well, vduse is the only driver that does this hack - we had a few more
and we got rid of it.  It basically is the only thing preventing us
from doing direct calls into the iommu code and compile out dma_ops
entirely for non-Xen builds on the common architectures.

So yes, I'd really like to see it gone rather sooner than later.