1 files changed, 58 insertions, 30 deletions

diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 06f02960b439..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);
@@ -645,7 +624,6 @@ 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_register_group(pci->table_group, pci_domain_nr(bus), 0);
 
 	/* Divide the rest (1.75GB) among the children */
 	pci->phb->dma_window_size = 0x80000000ul;
@@ -756,10 +734,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 		iommu_table_setparms(phb, dn, tbl);
 		tbl->it_ops = &iommu_table_pseries_ops;
 		iommu_init_table(tbl, phb->node);
-		iommu_register_group(PCI_DN(dn)->table_group,
-				pci_domain_nr(phb->bus), 0);
 		set_iommu_table_base(&dev->dev, tbl);
-		iommu_add_device(&dev->dev);
 		return;
 	}
 
@@ -770,11 +745,10 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 	while (dn && PCI_DN(dn) && PCI_DN(dn)->table_group == NULL)
 		dn = dn->parent;
 
-	if (dn && PCI_DN(dn)) {
+	if (dn && PCI_DN(dn))
 		set_iommu_table_base(&dev->dev,
 				PCI_DN(dn)->table_group->tables[0]);
-		iommu_add_device(&dev->dev);
-	} else
+	else
 		printk(KERN_WARNING "iommu: Device %s has no iommu table\n",
 		       pci_name(dev));
 }
@@ -964,6 +938,37 @@ struct failed_ddw_pdn {
 
 static LIST_HEAD(failed_ddw_pdn_list);
 
+static phys_addr_t ddw_memory_hotplug_max(void)
+{
+	phys_addr_t max_addr = memory_hotplug_max();
+	struct device_node *memory;
+
+	for_each_node_by_type(memory, "memory") {
+		unsigned long start, size;
+		int ranges, n_mem_addr_cells, n_mem_size_cells, len;
+		const __be32 *memcell_buf;
+
+		memcell_buf = of_get_property(memory, "reg", &len);
+		if (!memcell_buf || len <= 0)
+			continue;
+
+		n_mem_addr_cells = of_n_addr_cells(memory);
+		n_mem_size_cells = of_n_size_cells(memory);
+
+		/* ranges in cell */
+		ranges = (len >> 2) / (n_mem_addr_cells + n_mem_size_cells);
+
+		start = of_read_number(memcell_buf, n_mem_addr_cells);
+		memcell_buf += n_mem_addr_cells;
+		size = of_read_number(memcell_buf, n_mem_size_cells);
+		memcell_buf += n_mem_size_cells;
+
+		max_addr = max_t(phys_addr_t, max_addr, start + size);
+	}
+
+	return max_addr;
+}
+
 /*
  * If the PE supports dynamic dma windows, and there is space for a table
  * that can map all pages in a linear offset, then setup such a table,
@@ -1053,7 +1058,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	}
 	/* verify the window * number of ptes will map the partition */
 	/* check largest block * page size > max memory hotplug addr */
-	max_addr = memory_hotplug_max();
+	max_addr = ddw_memory_hotplug_max();
 	if (query.largest_available_block < (max_addr >> page_shift)) {
 		dev_dbg(&dev->dev, "can't map partition max 0x%llx with %u "
 			  "%llu-sized pages\n", max_addr,  query.largest_available_block,
@@ -1190,7 +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)
@@ -1395,4 +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);