vfio: powerpc/spapr: powerpc/powernv/ioda: Define and implement DMA windows API

This extends iommu_table_group_ops by a set of callbacks to support
dynamic DMA windows management.

create_table() creates a TCE table with specific parameters.
it receives iommu_table_group to know nodeid in order to allocate
TCE table memory closer to the PHB. The exact format of allocated
multi-level table might be also specific to the PHB model (not
the case now though).
This callback calculated the DMA window offset on a PCI bus from @num
and stores it in a just created table.

set_window() sets the window at specified TVT index + @num on PHB.

unset_window() unsets the window from specified TVT.

This adds a free() callback to iommu_table_ops to free the memory
(potentially a tree of tables) allocated for the TCE table.

create_table() and free() are supposed to be called once per
VFIO container and set_window()/unset_window() are supposed to be
called for every group in a container.

This adds IOMMU capabilities to iommu_table_group such as default
32bit window parameters and others. This makes use of new values in
vfio_iommu_spapr_tce. IODA1/P5IOC2 do not support DDW so they do not
advertise pagemasks to the userspace.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
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, 11 insertions, 8 deletions

diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index a9e2d13c03c0..6d919eb4251f 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -135,7 +135,6 @@ static int tce_iommu_enable(struct tce_container *container)
 {
 	int ret = 0;
 	unsigned long locked;
-	struct iommu_table *tbl;
 	struct iommu_table_group *table_group;
 
 	if (!container->grp)
@@ -171,13 +170,19 @@ static int tce_iommu_enable(struct tce_container *container)
 	 * this is that we cannot tell here the amount of RAM used by the guest
 	 * as this information is only available from KVM and VFIO is
 	 * KVM agnostic.
+	 *
+	 * So we do not allow enabling a container without a group attached
+	 * as there is no way to know how much we should increment
+	 * the locked_vm counter.
 	 */
 	table_group = iommu_group_get_iommudata(container->grp);
 	if (!table_group)
 		return -ENODEV;
 
-	tbl = table_group->tables[0];
-	locked = (tbl->it_size << tbl->it_page_shift) >> PAGE_SHIFT;
+	if (!table_group->tce32_size)
+		return -EPERM;
+
+	locked = table_group->tce32_size >> PAGE_SHIFT;
 	ret = try_increment_locked_vm(locked);
 	if (ret)
 		return ret;
@@ -350,7 +355,6 @@ static long tce_iommu_ioctl(void *iommu_data,
 
 	case VFIO_IOMMU_SPAPR_TCE_GET_INFO: {
 		struct vfio_iommu_spapr_tce_info info;
-		struct iommu_table *tbl;
 		struct iommu_table_group *table_group;
 
 		if (WARN_ON(!container->grp))
@@ -358,8 +362,7 @@ static long tce_iommu_ioctl(void *iommu_data,
 
 		table_group = iommu_group_get_iommudata(container->grp);
 
-		tbl = table_group->tables[0];
-		if (WARN_ON_ONCE(!tbl))
+		if (!table_group)
 			return -ENXIO;
 
 		minsz = offsetofend(struct vfio_iommu_spapr_tce_info,
@@ -371,8 +374,8 @@ static long tce_iommu_ioctl(void *iommu_data,
 		if (info.argsz < minsz)
 			return -EINVAL;
 
-		info.dma32_window_start = tbl->it_offset << tbl->it_page_shift;
-		info.dma32_window_size = tbl->it_size << tbl->it_page_shift;
+		info.dma32_window_start = table_group->tce32_start;
+		info.dma32_window_size = table_group->tce32_size;
 		info.flags = 0;
 
 		if (copy_to_user((void __user *)arg, &info, minsz))