powerpc/iommu/powernv: Release replaced TCE

At the moment writing new TCE value to the IOMMU table fails with EBUSY
if there is a valid entry already. However PAPR specification allows
the guest to write new TCE value without clearing it first.

Another problem this patch is addressing is the use of pool locks for
external IOMMU users such as VFIO. The pool locks are to protect
DMA page allocator rather than entries and since the host kernel does
not control what pages are in use, there is no point in pool locks and
exchange()+put_page(oldtce) is sufficient to avoid possible races.

This adds an exchange() callback to iommu_table_ops which does the same
thing as set() plus it returns replaced TCE and DMA direction so
the caller can release the pages afterwards. The exchange() receives
a physical address unlike set() which receives linear mapping address;
and returns a physical address as the clear() does.

This implements exchange() for P5IOC2/IODA/IODA2. This adds a requirement
for a platform to have exchange() implemented in order to support VFIO.

This replaces iommu_tce_build() and iommu_clear_tce() with
a single iommu_tce_xchg().

This makes sure that TCE permission bits are not set in TCE passed to
IOMMU API as those are to be calculated by platform code from
DMA direction.

This moves SetPageDirty() to the IOMMU code to make it work for both
VFIO ioctl interface in in-kernel TCE acceleration (when it becomes
available later).

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
[aw: for the vfio related changes]
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

1 files changed, 34 insertions, 0 deletions

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 390863608569..ecbc071a143e 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1738,6 +1738,20 @@ static int pnv_ioda1_tce_build(struct iommu_table *tbl, long index,
 	return ret;
 }
 
+#ifdef CONFIG_IOMMU_API
+static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index,
+		unsigned long *hpa, enum dma_data_direction *direction)
+{
+	long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+
+	if (!ret && (tbl->it_type &
+			(TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE)))
+		pnv_pci_ioda1_tce_invalidate(tbl, index, 1, false);
+
+	return ret;
+}
+#endif
+
 static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index,
 		long npages)
 {
@@ -1749,6 +1763,9 @@ static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index,
 
 static struct iommu_table_ops pnv_ioda1_iommu_ops = {
 	.set = pnv_ioda1_tce_build,
+#ifdef CONFIG_IOMMU_API
+	.exchange = pnv_ioda1_tce_xchg,
+#endif
 	.clear = pnv_ioda1_tce_free,
 	.get = pnv_tce_get,
 };
@@ -1824,6 +1841,20 @@ static int pnv_ioda2_tce_build(struct iommu_table *tbl, long index,
 	return ret;
 }
 
+#ifdef CONFIG_IOMMU_API
+static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index,
+		unsigned long *hpa, enum dma_data_direction *direction)
+{
+	long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+
+	if (!ret && (tbl->it_type &
+			(TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE)))
+		pnv_pci_ioda2_tce_invalidate(tbl, index, 1, false);
+
+	return ret;
+}
+#endif
+
 static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
 		long npages)
 {
@@ -1835,6 +1866,9 @@ static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
 
 static struct iommu_table_ops pnv_ioda2_iommu_ops = {
 	.set = pnv_ioda2_tce_build,
+#ifdef CONFIG_IOMMU_API
+	.exchange = pnv_ioda2_tce_xchg,
+#endif
 	.clear = pnv_ioda2_tce_free,
 	.get = pnv_tce_get,
 };