Re: [RFC PATCH 3/4] iommu/vt-d: Map/unmap domain with mmmap/mmunmap

[Lu Baolu]

Hi,

On 9/25/19 1:00 PM, Tian, Kevin wrote:
> > From: Lu Baolu [mailto:baolu.lu@xxxxxxxxxxxxxxx]
> > Sent: Monday, September 23, 2019 8:25 PM
> >
> > If a dmar domain has DOMAIN_FLAG_FIRST_LEVEL_TRANS bit set
> > in its flags, IOMMU will use the first level page table for
> > translation. Hence, we need to map or unmap addresses in the
> > first level page table.
> >
> > Cc: Ashok Raj <ashok.raj@xxxxxxxxx>
> > Cc: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
> > Cc: Kevin Tian <kevin.tian@xxxxxxxxx>
> > Cc: Liu Yi L <yi.l.liu@xxxxxxxxx>
> > Cc: Yi Sun <yi.y.sun@xxxxxxxxxxxxxxx>
> > Signed-off-by: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
> > ---
> >   drivers/iommu/intel-iommu.c | 94 ++++++++++++++++++++++++++++++++-
> > ----
> >   1 file changed, 82 insertions(+), 12 deletions(-)
> >
> > diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
> > index 9cfe8098d993..103480016010 100644
> > --- a/drivers/iommu/intel-iommu.c
> > +++ b/drivers/iommu/intel-iommu.c
> > @@ -168,6 +168,11 @@ static inline unsigned long virt_to_dma_pfn(void
> > *p)
> >   	return page_to_dma_pfn(virt_to_page(p));
> >   }
> >
> > +static inline unsigned long dma_pfn_to_addr(unsigned long pfn)
> > +{
> > +	return pfn << VTD_PAGE_SHIFT;
> > +}
> > +
> >   /* global iommu list, set NULL for ignored DMAR units */
> >   static struct intel_iommu **g_iommus;
> >
> > @@ -307,6 +312,9 @@ static int hw_pass_through = 1;
> >    */
> >   #define DOMAIN_FLAG_LOSE_CHILDREN		BIT(1)
> >
> > +/* Domain uses first level translation for DMA remapping. */
> > +#define DOMAIN_FLAG_FIRST_LEVEL_TRANS		BIT(2)
> > +
> >   #define for_each_domain_iommu(idx, domain)			\
> >   	for (idx = 0; idx < g_num_of_iommus; idx++)		\
> >   		if (domain->iommu_refcnt[idx])
> > @@ -552,6 +560,11 @@ static inline int domain_type_is_si(struct
> > dmar_domain *domain)
> >   	return domain->flags & DOMAIN_FLAG_STATIC_IDENTITY;
> >   }
> >
> > +static inline int domain_type_is_flt(struct dmar_domain *domain)
> > +{
> > +	return domain->flags & DOMAIN_FLAG_FIRST_LEVEL_TRANS;
> > +}
> > +
> >   static inline int domain_pfn_supported(struct dmar_domain *domain,
> >   				       unsigned long pfn)
> >   {
> > @@ -1147,8 +1160,15 @@ static struct page *domain_unmap(struct
> > dmar_domain *domain,
> >   	BUG_ON(start_pfn > last_pfn);
> >
> >   	/* we don't need lock here; nobody else touches the iova range */
> > -	freelist = dma_pte_clear_level(domain, agaw_to_level(domain-
> > > agaw),
> > -				       domain->pgd, 0, start_pfn, last_pfn,
> > NULL);
> > +	if (domain_type_is_flt(domain))
> > +		freelist = intel_mmunmap_range(domain,
> > +					       dma_pfn_to_addr(start_pfn),
> > +					       dma_pfn_to_addr(last_pfn + 1));
> > +	else
> > +		freelist = dma_pte_clear_level(domain,
> > +					       agaw_to_level(domain->agaw),
> > +					       domain->pgd, 0, start_pfn,
> > +					       last_pfn, NULL);
>
> what about providing an unified interface at the caller side, then having
> the level differentiated within the interface?

Good point! I ever thought about adding some ops in struct dmar_domain,
something like:

diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index ed11ef594378..1dd184f76bfb 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -489,7 +489,14 @@ struct dmar_domain {
        struct list_head auxd;          /* link to device's auxiliary 
list */
        struct iova_domain iovad;       /* iova's that belong to this 
domain */

+       /* per domain page table and manipulation ops */
        struct dma_pte  *pgd;           /* virtual address */
+       int (*map)(struct dmar_domain *domain,
+                  unsigned long addr, unsigned long end,
+                  phys_addr_t phys_addr, int dma_prot);
+       struct page *(*unmap)(struct dmar_domain *domain,
+                             unsigned long addr, unsigned long end);
+
        int             gaw;            /* max guest address width */

        /* adjusted guest address width, 0 is level 2 30-bit */

So that this code could be simply like this:

	freelist = domain->unmap(...);

Best regards,
Baolu