powerpc/powernv/ioda2: Create bigger default window with 64k IOMMU pages

At the moment we create a small window only for 32bit devices, the window
maps 0..2GB of the PCI space only. For other devices we either use
a sketchy bypass or hardware bypass but the former can only work if
the amount of RAM is no bigger than the device's DMA mask and the latter
requires devices to support at least 59bit DMA.

This extends the default DMA window to the maximum size possible to allow
a wider DMA mask than just 32bit. The default window size is now limited
by the the iommu_table::it_map allocation bitmap which is a contiguous
array, 1 bit per an IOMMU page.

This increases the default IOMMU page size from hard coded 4K to
the system page size to allow wider DMA masks.

This increases the level number to not exceed the max order allocation
limit per TCE level. By the same time, this keeps minimal levels number
as 2 in order to save memory.

As the extended window now overlaps the 32bit MMIO region, this adds
an area reservation to iommu_init_table().

After this change the default window size is 0x80000000000==1<<43 so
devices limited to DMA mask smaller than the amount of system RAM can
still use more than just 2GB of memory for DMA.

This is an optimization and not a bug fix for DMA API usage.

With the on-demand allocation of indirect TCE table levels enabled and
2 levels, the first TCE level size is just
1<<ceil((log2(0x7ffffffffff+1)-16)/2)=16384 TCEs or 2 system pages.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190718051139.74787-5-aik@ozlabs.ru

2 files changed, 5 insertions, 5 deletions

diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 889dc2e44b89..42fb03253334 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -609,7 +609,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 
 	iommu_table_setparms(pci->phb, dn, tbl);
 	tbl->it_ops = &iommu_table_pseries_ops;
-	iommu_init_table(tbl, pci->phb->node);
+	iommu_init_table(tbl, pci->phb->node, 0, 0);
 
 	/* Divide the rest (1.75GB) among the children */
 	pci->phb->dma_window_size = 0x80000000ul;
@@ -690,7 +690,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 		iommu_table_setparms_lpar(ppci->phb, pdn, tbl,
 				ppci->table_group, dma_window);
 		tbl->it_ops = &iommu_table_lpar_multi_ops;
-		iommu_init_table(tbl, ppci->phb->node);
+		iommu_init_table(tbl, ppci->phb->node, 0, 0);
 		iommu_register_group(ppci->table_group,
 				pci_domain_nr(bus), 0);
 		pr_debug("  created table: %p\n", ppci->table_group);
@@ -719,7 +719,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 		tbl = PCI_DN(dn)->table_group->tables[0];
 		iommu_table_setparms(phb, dn, tbl);
 		tbl->it_ops = &iommu_table_pseries_ops;
-		iommu_init_table(tbl, phb->node);
+		iommu_init_table(tbl, phb->node, 0, 0);
 		set_iommu_table_base(&dev->dev, tbl);
 		return;
 	}
@@ -1169,7 +1169,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 		iommu_table_setparms_lpar(pci->phb, pdn, tbl,
 				pci->table_group, dma_window);
 		tbl->it_ops = &iommu_table_lpar_multi_ops;
-		iommu_init_table(tbl, pci->phb->node);
+		iommu_init_table(tbl, pci->phb->node, 0, 0);
 		iommu_register_group(pci->table_group,
 				pci_domain_nr(pci->phb->bus), 0);
 		pr_debug("  created table: %p\n", pci->table_group);
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 6601b9d404dc..115934f83935 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -1191,7 +1191,7 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
 	else
 		tbl->it_ops = &iommu_table_pseries_ops;
 
-	return iommu_init_table(tbl, -1);
+	return iommu_init_table(tbl, -1, 0, 0);
 }
 
 /**