> From: Jason Gunthorpe
> Sent: Monday, November 1, 2021 8:50 PM
>
> On Fri, Oct 29, 2021 at 09:47:27AM +, Liu, Yi L wrote:
> > Hi Jason,
> >
> > > From: Jason Gunthorpe
> > > Sent: Monday, October 25, 2021 8:53 PM
> > >
> > > On Mon, Oct 25, 2021 at 06:28:09AM +, Liu, Yi L wrote:
> > >
Hi Christoph,
I am sorry, fix my typo.
Walter
On Tue, 2021-11-02 at 07:41 +0100, Christoph Hellwig wrote:
> As others pointed out, DMA_ATTR_NO_KERNEL_MAPPING just means the
> caller can't rely on a kernel mapping. So the "fix" here is
> wrong. That being said for cases where we can easily
Hi Cristoph,
On Tue, 2021-11-02 at 07:41 +0100, Christoph Hellwig wrote:
> As others pointed out, DMA_ATTR_NO_KERNEL_MAPPING just means the
> caller can't rely on a kernel mapping. So the "fix" here is
> wrong. That being said for cases where we can easily remove a page
> from the kernel
On Tue, Nov 02, 2021 at 11:21:16AM +0800, Walter Wu wrote:
> Our platform is arch64. We need a dynamic allocated buffer from CMA is
> not to read by CPU peculative execution, so we need to remove its
> kernel mapping.
If your CPU speculates into unused kernel direct mappings your have
a worse
As others pointed out, DMA_ATTR_NO_KERNEL_MAPPING just means the
caller can't rely on a kernel mapping. So the "fix" here is
wrong. That being said for cases where we can easily remove a page
from the kernel mapping it would be nice to do to:
a) improve security
b) as a debug check to see
