[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Y8AKcnFsdu3+8Cjt@nvidia.com>
Date: Thu, 12 Jan 2023 09:26:10 -0400
From: Jason Gunthorpe <jgg@...dia.com>
To: Baolu Lu <baolu.lu@...ux.intel.com>
Cc: Bjorn Helgaas <bhelgaas@...gle.com>,
Joerg Roedel <jroedel@...e.de>,
Christian König <christian.koenig@....com>,
Kevin Tian <kevin.tian@...el.com>,
Vasant Hegde <vasant.hegde@....com>,
Tony Zhu <tony.zhu@...el.com>, linux-pci@...r.kernel.org,
iommu@...ts.linux.dev, linux-kernel@...r.kernel.org,
Matt Fagnani <matt.fagnani@...l.net>
Subject: Re: [PATCH 1/1] PCI: Add translated request only opt-in for
pci_enable_pasid()
On Thu, Jan 12, 2023 at 09:25:25PM +0800, Baolu Lu wrote:
> On 2023/1/12 20:38, Jason Gunthorpe wrote:
> > On Thu, Jan 12, 2023 at 04:46:29PM +0800, Lu Baolu wrote:
> >
> > > -int pci_enable_pasid(struct pci_dev *pdev, int features);
> > > +int pci_enable_pasid(struct pci_dev *pdev, int features, bool
> > > transled_only);
> >
> > Please use a named flag so we can grep for it..
>
> Sure. What do you think of this naming?
>
> + * @flags: device-specific flags
> + * - PCI_PASID_TRANSLED_REQ_ONLY: The PCI device only issues PASID
> + * memory requests of translated type.
Yes
> > Discuss in the commit message that this is a temporary step and that
> > pci_enable_pasid() needs to be moved to the drivers
>
> I will add below in commit message:
>
> At present, it is a common practice to enable/disable PCI PASID in the
> iommu drivers. Considering that the device driver knows more about the
> specific device, we will follow up by moving pci_enable_pasid() into
> the specific device drivers.
Yes
Jason
Powered by blists - more mailing lists