On Mon, 2024-12-16 at 10:29 +0100, Niklas Schnelle wrote:
> On Fri, 2024-12-13 at 17:49 -0500, Matthew Rosato wrote:
> > PCI devices on s390 have a DMA offset that is reported via CLP. In
> > preparation for allowing identity domains, setup the bus_dma_region
> > for all PCI devices using the reported CLP value.
> >
> > Signed-off-by: Matthew Rosato <mjrosato@xxxxxxxxxxxxx>
> > ---
> > arch/s390/pci/pci_bus.c | 18 ++++++++++++++++++
> > 1 file changed, 18 insertions(+)
> >
> > diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c
> > index d5ace00d10f0..14527687d0f2 100644
> > --- a/arch/s390/pci/pci_bus.c
> > +++ b/arch/s390/pci/pci_bus.c
> > @@ -19,6 +19,7 @@
> > #include <linux/jump_label.h>
> > #include <linux/pci.h>
> > #include <linux/printk.h>
> > +#include <linux/dma-direct.h>
> >
> > #include <asm/pci_clp.h>
> > #include <asm/pci_dma.h>
> > @@ -284,10 +285,27 @@ static struct zpci_bus *zpci_bus_alloc(int topo, bool topo_is_tid)
> > return zbus;
> > }
> >
> > +static void pci_dma_range_setup(struct pci_dev *pdev)
> > +{
> > + struct zpci_dev *zdev = to_zpci(pdev);
> > + struct bus_dma_region *map;
> > +
> > + map = kzalloc(sizeof(*map), GFP_KERNEL);
> > + if (!map)
> > + return;
> > +
> > + map->cpu_start = 0;
> > + map->dma_start = PAGE_ALIGN(zdev->start_dma);
> > + map->size = (u64)virt_to_phys(high_memory);
>
> I don't think we should restrict the size here to the size of memory.
> Instead I think it should be zdev->end_dma - zdev->start_dma.
>
> Since we handle the restriction to memory size as reserved regions I
> think that should be compatible. Also I think otherwise this might
> break the admittedly odd s390_iommu_aperture=X kernel parameter on
> LPARs.
Correction, zdev->end_dma - zdev->start_dma + 1 because zdev->end_dma
is inclusive ;-)
>
>
> > + pdev->dev.dma_range_map = map;
> > +}
> > +
> > void pcibios_bus_add_device(struct pci_dev *pdev)
> > {
> > struct zpci_dev *zdev = to_zpci(pdev);
> >
> > + pci_dma_range_setup(pdev);
> > +
> > /*
> > * With pdev->no_vf_scan the common PCI probing code does not
> > * perform PF/VF linking.
>
