Re: [PATCH v5 6/6] iommu/s390: Implement map_pages()/unmap_pages() instead of map()/unmap()

[Niklas Schnelle <schnelle@linux.ibm.com>]

On Thu, 2022-10-06 at 17:03 -0400, Matthew Rosato wrote:
> On 10/6/22 10:47 AM, Niklas Schnelle wrote:
> > While s390-iommu currently implements the map_page()/unmap_page()
> > operations which only map/unmap a single page at a time the internal
> > s390_iommu_update_trans() API already supports mapping/unmapping a range
> > of pages at once. Take advantage of this by implementing the
> > map_pages()/unmap_pages() operations instead thus allowing users of the
> > IOMMU drivers to map multiple pages in a single call followed by
> > a single I/O TLB flush if needed.
> > 
> > Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
> > ---
> >  drivers/iommu/s390-iommu.c | 48 +++++++++++++++++++++++++-------------
> >  1 file changed, 32 insertions(+), 16 deletions(-)
> > 
> > diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c
> > index ac200f0b81fa..7b92855135ac 100644
> > --- a/drivers/iommu/s390-iommu.c
> > +++ b/drivers/iommu/s390-iommu.c
> > @@ -189,20 +189,15 @@ static void s390_iommu_release_device(struct device *dev)
> >  
> >  static int s390_iommu_update_trans(struct s390_domain *s390_domain,
> >  				   phys_addr_t pa, dma_addr_t dma_addr,
> > -				   size_t size, int flags)
> > +				   unsigned long nr_pages, int flags)
> >  {
> >  	phys_addr_t page_addr = pa & PAGE_MASK;
> >  	dma_addr_t start_dma_addr = dma_addr;
> > -	unsigned long irq_flags, nr_pages, i;
> > +	unsigned long irq_flags, i;
> >  	struct zpci_dev *zdev;
> >  	unsigned long *entry;
> >  	int rc = 0;
> >  
> > -	if (dma_addr < s390_domain->domain.geometry.aperture_start ||
> > -	    (dma_addr + size - 1) > s390_domain->domain.geometry.aperture_end)
> > -		return -EINVAL;
> > -
> > -	nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
> >  	if (!nr_pages)
> >  		return 0;
> >  
> > @@ -245,11 +240,24 @@ static int s390_iommu_update_trans(struct s390_domain *s390_domain,
> >  	return rc;
> >  }
> >  
> > -static int s390_iommu_map(struct iommu_domain *domain, unsigned long iova,
> > -			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
> > +static int s390_iommu_map_pages(struct iommu_domain *domain,
> > +				unsigned long iova, phys_addr_t paddr,
> > +				size_t pgsize, size_t pgcount,
> > +				int prot, gfp_t gfp, size_t *mapped)
> >  {
> >  	struct s390_domain *s390_domain = to_s390_domain(domain);
> >  	int flags = ZPCI_PTE_VALID, rc = 0;
> > +	size_t size = pgcount << __ffs(pgsize);
> > +
> > +	if (pgsize != SZ_4K)
> > +		return -EINVAL;
> > +
> > +	if (iova < s390_domain->domain.geometry.aperture_start ||
> > +	    (iova + size - 1) > s390_domain->domain.geometry.aperture_end)
> > +		return -EINVAL;
> > +
> > +	if (!IS_ALIGNED(iova | paddr, pgsize))
> > +		return -EINVAL;
> >  
> >  	if (!(prot & IOMMU_READ))
> >  		return -EINVAL;
> > @@ -258,7 +266,9 @@ static int s390_iommu_map(struct iommu_domain *domain, unsigned long iova,
> >  		flags |= ZPCI_TABLE_PROTECTED;
> >  
> >  	rc = s390_iommu_update_trans(s390_domain, paddr, iova,
> > -				     size, flags);
> > +				     pgcount, flags);
> > +	if (!rc)
> > +		*mapped = size;
> >  
> >  	return rc;
> >  }
> > @@ -294,21 +304,27 @@ static phys_addr_t s390_iommu_iova_to_phys(struct iommu_domain *domain,
> >  	return phys;
> >  }
> >  
> > -static size_t s390_iommu_unmap(struct iommu_domain *domain,
> > -			       unsigned long iova, size_t size,
> > -			       struct iommu_iotlb_gather *gather)
> > +static size_t s390_iommu_unmap_pages(struct iommu_domain *domain,
> > +				     unsigned long iova,
> > +				     size_t pgsize, size_t pgcount,
> > +				     struct iommu_iotlb_gather *gather)
> >  {
> >  	struct s390_domain *s390_domain = to_s390_domain(domain);
> > +	size_t size = pgcount << __ffs(pgsize);
> >  	int flags = ZPCI_PTE_INVALID;
> >  	phys_addr_t paddr;
> >  	int rc;
> >  
> > +	if (iova < s390_domain->domain.geometry.aperture_start ||
> > +	    (iova + size - 1) > s390_domain->domain.geometry.aperture_end)
> > +		return 0;
> > +
> 
> Overall this LGTM and runs well with my testing.  But I'm curious why we silently ignore an egregiously bad unmap request here?  We've already done an -EINVAL for an attempt to map_pages() something outside of the aperture.  If something still tries to unmap_pages() outside of the aperture, that seems like a bug?  Maybe this should be surrounded by a if (WARN_ON(... || ...) to signify the unexpected behavior and then still return 0?
> 

Well, the problem here is that .unmap_pages() returns size_t so
0 is kind of the only invalid value.But yes, a WARN_ON() seems
warranted.

> Otherwise:
> Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
> 
> >  	paddr = s390_iommu_iova_to_phys(domain, iova);
> >  	if (!paddr)
> >  		return 0;
> >  
> >  	rc = s390_iommu_update_trans(s390_domain, paddr, iova,
> > -				     size, flags);
> > +				     pgcount, flags);
> >  	if (rc)
> >  		return 0;
> >  
> > @@ -354,8 +370,8 @@ static const struct iommu_ops s390_iommu_ops = {
> >  	.default_domain_ops = &(const struct iommu_domain_ops) {
> >  		.attach_dev	= s390_iommu_attach_device,
> >  		.detach_dev	= s390_iommu_detach_device,
> > -		.map		= s390_iommu_map,
> > -		.unmap		= s390_iommu_unmap,
> > +		.map_pages	= s390_iommu_map_pages,
> > +		.unmap_pages	= s390_iommu_unmap_pages,
> >  		.iova_to_phys	= s390_iommu_iova_to_phys,
> >  		.free		= s390_domain_free,
> >  	}