Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

[Baolu Lu]

On 2022/5/20 00:33, Jean-Philippe Brucker wrote:
> > diff --git a/drivers/iommu/iommu-sva-lib.h b/drivers/iommu/iommu-sva-lib.h
> > index 8909ea1094e3..1be21e6b93ec 100644
> > --- a/drivers/iommu/iommu-sva-lib.h
> > +++ b/drivers/iommu/iommu-sva-lib.h
> > @@ -7,6 +7,7 @@
> >   
> >   #include <linux/ioasid.h>
> >   #include <linux/mm_types.h>
> > +#include <linux/iommu.h>
> >   
> >   int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max);
> >   struct mm_struct *iommu_sva_find(ioasid_t pasid);
> > @@ -16,6 +17,20 @@ struct device;
> >   struct iommu_fault;
> >   struct iopf_queue;
> >   
> > +struct iommu_sva_domain {
> > +	struct iommu_domain	domain;
> > +	struct mm_struct	*mm;
> > +};
> > +
> > +#define to_sva_domain(d) container_of_safe(d, struct iommu_sva_domain, domain)
> Is there a reason to use the 'safe' version of container_of()?  Callers of
> to_sva_domain() don't check the return value before dereferencing it so
> they would break anyway if someone passes an error pointer as domain.  I
> think it matters because there is no other user of container_of_safe() in
> the kernel (the only user, lustre, went away in 2018) so someone will want
> to remove it.

Fair enough. I wondered why there's no user in the tree. Thanks for the
explanation. I will replace it with container_of().

> Apart from that
>
> Reviewed-by: Jean-Philippe Brucker<jean-philippe@xxxxxxxxxx>

Thank you!

Best regards,
baolu