Re: [PATCH 2/3] nvme-pci: Add controller memory buffer supported macro

From: Christoph Hellwig <hch@lst.de>
To: Keith Busch <kbusch@kernel.org>
Cc: sagi@grimberg.me, linux-kernel@vger.kernel.org,
	linux-nvme@lists.infradead.org, axboe@fb.com,
	Baolin Wang <baolin.wang@linux.alibaba.com>,
	baolin.wang7@gmail.com, Christoph Hellwig <hch@lst.de>
Subject: Re: [PATCH 2/3] nvme-pci: Add controller memory buffer supported macro
Date: Wed, 24 Jun 2020 07:47:08 +0200	[thread overview]
Message-ID: <20200624054708.GA17008@lst.de> (raw)
In-Reply-To: <20200624025817.GC1291930@dhcp-10-100-145-180.wdl.wdc.com>

On Tue, Jun 23, 2020 at 07:58:17PM -0700, Keith Busch wrote:
> On Tue, Jun 23, 2020 at 06:27:51PM +0200, Christoph Hellwig wrote:
> > On Tue, Jun 23, 2020 at 09:24:33PM +0800, Baolin Wang wrote:
> > > Introduce a new capability macro to indicate if the controller
> > > supports the memory buffer or not, instead of reading the
> > > NVME_REG_CMBSZ register.
> > 
> > This is a complex issue.  The CMBS bit was only added in NVMe 1.4 as
> > a backwards incompatible change, as the CMB addressing scheme can lead
> > to data corruption.  The CMBS was added as part of the horribe hack
> > that also involves the CBA field, which we'll need to see before
> > using it to work around the addressing issue.  At the same time we
> > should also continue supporting the legacy pre-1.4 CMB with a warning
> > (and may reject it if we know we run in a VM).
> 
> Well, a CMB from an emulated controller (like qemu's) can be used within
> a VM. It's only if you direct assign a PCI function that CMB usage
> breaks.

But we have no idea if a controller is assigned or emulated.

_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme