powerpc/powernv/pseries: Rework device adding to IOMMU groups

The powernv platform registers IOMMU groups and adds devices to them
from the pci_controller_ops::setup_bridge() hook except one case when
virtual functions (SRIOV VFs) are added from a bus notifier.

The pseries platform registers IOMMU groups from
the pci_controller_ops::dma_bus_setup() hook and adds devices from
the pci_controller_ops::dma_dev_setup() hook. The very same bus notifier
used for powernv does not add devices for pseries though as
__of_scan_bus() adds devices first, then it does the bus/dev DMA setup.

Both platforms use iommu_add_device() which takes a device and expects
it to have a valid IOMMU table struct with an iommu_table_group pointer
which in turn points the iommu_group struct (which represents
an IOMMU group). Although the helper seems easy to use, it relies on
some pre-existing device configuration and associated data structures
which it does not really need.

This simplifies iommu_add_device() to take the table_group pointer
directly. Pseries already has a table_group pointer handy and the bus
notified is not used anyway. For powernv, this copies the existing bus
notifier, makes it work for powernv only which means an easy way of
getting to the table_group pointer. This was tested on VFs but should
also support physical PCI hotplug.

Since iommu_add_device() receives the table_group pointer directly,
pseries does not do TCE cache invalidation (the hypervisor does) nor
allow multiple groups per a VFIO container (in other words sharing
an IOMMU table between partitionable endpoints), this removes
iommu_table_group_link from pseries.

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, 24 insertions, 22 deletions

diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 2783cb7f3aef..8fc8fe0b9848 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -57,7 +57,6 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node)
 {
 	struct iommu_table_group *table_group;
 	struct iommu_table *tbl;
-	struct iommu_table_group_link *tgl;
 
 	table_group = kzalloc_node(sizeof(struct iommu_table_group), GFP_KERNEL,
 			   node);
@@ -68,22 +67,13 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node)
 	if (!tbl)
 		goto free_group;
 
-	tgl = kzalloc_node(sizeof(struct iommu_table_group_link), GFP_KERNEL,
-			node);
-	if (!tgl)
-		goto free_table;
-
 	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
 	kref_init(&tbl->it_kref);
-	tgl->table_group = table_group;
-	list_add_rcu(&tgl->next, &tbl->it_group_list);
 
 	table_group->tables[0] = tbl;
 
 	return table_group;
 
-free_table:
-	kfree(tbl);
 free_group:
 	kfree(table_group);
 	return NULL;
@@ -93,23 +83,12 @@ static void iommu_pseries_free_group(struct iommu_table_group *table_group,
 		const char *node_name)
 {
 	struct iommu_table *tbl;
-#ifdef CONFIG_IOMMU_API
-	struct iommu_table_group_link *tgl;
-#endif
 
 	if (!table_group)
 		return;
 
 	tbl = table_group->tables[0];
 #ifdef CONFIG_IOMMU_API
-	tgl = list_first_entry_or_null(&tbl->it_group_list,
-			struct iommu_table_group_link, next);
-
-	WARN_ON_ONCE(!tgl);
-	if (tgl) {
-		list_del_rcu(&tgl->next);
-		kfree(tgl);
-	}
 	if (table_group->group) {
 		iommu_group_put(table_group->group);
 		BUG_ON(table_group->group);
@@ -1216,7 +1195,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	}
 
 	set_iommu_table_base(&dev->dev, pci->table_group->tables[0]);
-	iommu_add_device(&dev->dev);
+	iommu_add_device(pci->table_group, &dev->dev);
 }
 
 static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)
@@ -1421,4 +1400,27 @@ static int __init disable_multitce(char *str)
 
 __setup("multitce=", disable_multitce);
 
+static int tce_iommu_bus_notifier(struct notifier_block *nb,
+		unsigned long action, void *data)
+{
+	struct device *dev = data;
+
+	switch (action) {
+	case BUS_NOTIFY_DEL_DEVICE:
+		iommu_del_device(dev);
+		return 0;
+	default:
+		return 0;
+	}
+}
+
+static struct notifier_block tce_iommu_bus_nb = {
+	.notifier_call = tce_iommu_bus_notifier,
+};
+
+static int __init tce_iommu_bus_notifier_init(void)
+{
+	bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
+	return 0;
+}
 machine_subsys_initcall_sync(pseries, tce_iommu_bus_notifier_init);