powerpc/powernv: Implement multilevel TCE tables

TCE tables might get too big in case of 4K IOMMU pages and DDW enabled
on huge guests (hundreds of GB of RAM) so the kernel might be unable to
allocate contiguous chunk of physical memory to store the TCE table.

To address this, POWER8 CPU (actually, IODA2) supports multi-level
TCE tables, up to 5 levels which splits the table into a tree of
smaller subtables.

This adds multi-level TCE tables support to
pnv_pci_ioda2_table_alloc_pages() and pnv_pci_ioda2_table_free_pages()
helpers.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

1 files changed, 13 insertions, 0 deletions

diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index d465b9c32388..765d8ed558d0 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -575,6 +575,19 @@ struct pci_ops pnv_pci_ops = {
 static __be64 *pnv_tce(struct iommu_table *tbl, long idx)
 {
 	__be64 *tmp = ((__be64 *)tbl->it_base);
+	int  level = tbl->it_indirect_levels;
+	const long shift = ilog2(tbl->it_level_size);
+	unsigned long mask = (tbl->it_level_size - 1) << (level * shift);
+
+	while (level) {
+		int n = (idx & mask) >> (level * shift);
+		unsigned long tce = be64_to_cpu(tmp[n]);
+
+		tmp = __va(tce & ~(TCE_PCI_READ | TCE_PCI_WRITE));
+		idx &= ~mask;
+		mask >>= shift;
+		--level;
+	}
 
 	return tmp + idx;
 }