[PATCH v5 01/27] iommu/arm-smmu-v3: Do not allow a SVA domain to be set on the wrong PASID

[Jason Gunthorpe]

On Fri, Mar 22, 2024 at 05:48:52PM +0000, Mostafa Saleh wrote:
> Hi Jason,
> 
> On Mon, Mar 04, 2024 at 07:43:49PM -0400, Jason Gunthorpe wrote:
> > The SVA code is wired to assume that the SVA is programmed onto the
> > mm->pasid. The current core code always does this, so it is fine.
> > 
> > Add a check for clarity.
> > 
> > Tested-by: Nicolin Chen <nicolinc at nvidia.com>
> > Signed-off-by: Jason Gunthorpe <jgg at nvidia.com>
> > ---
> >  drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 3 +++
> >  1 file changed, 3 insertions(+)
> > 
> > diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
> > index 2610e82c0ecd0d..347c2fdd865c1a 100644
> > --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
> > +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
> > @@ -581,6 +581,9 @@ static int arm_smmu_sva_set_dev_pasid(struct iommu_domain *domain,
> >  	int ret = 0;
> >  	struct mm_struct *mm = domain->mm;
> >  
> > +	if (mm_get_enqcmd_pasid(mm) != id)
> > +		return -EINVAL;
> > +
> I am not sure if that is needed, the only caller in the tree is the IOMMU code
> and it does the right thing, as that check is removed later anyway, I don’t
> think this patch adds much.

It really should be backported, when we get drivers that do other
things it creates a hazard. I've added a fixes line.

Jason