1 files changed, 129 insertions, 50 deletions

diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 61d5a17f45c0..10510dea16b3 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -36,6 +36,8 @@
 #include <linux/crash_dump.h>
 #include <linux/memory.h>
 #include <linux/of.h>
+#include <linux/iommu.h>
+#include <linux/rculist.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/rtas.h>
@@ -51,6 +53,73 @@
 
 #include "pseries.h"
 
+static struct iommu_table_group *iommu_pseries_alloc_group(int node)
+{
+	struct iommu_table_group *table_group = NULL;
+	struct iommu_table *tbl = NULL;
+	struct iommu_table_group_link *tgl = NULL;
+
+	table_group = kzalloc_node(sizeof(struct iommu_table_group), GFP_KERNEL,
+			   node);
+	if (!table_group)
+		goto fail_exit;
+
+	tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, node);
+	if (!tbl)
+		goto fail_exit;
+
+	tgl = kzalloc_node(sizeof(struct iommu_table_group_link), GFP_KERNEL,
+			node);
+	if (!tgl)
+		goto fail_exit;
+
+	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+	tgl->table_group = table_group;
+	list_add_rcu(&tgl->next, &tbl->it_group_list);
+
+	table_group->tables[0] = tbl;
+
+	return table_group;
+
+fail_exit:
+	kfree(tgl);
+	kfree(table_group);
+	kfree(tbl);
+
+	return NULL;
+}
+
+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);
+	}
+#endif
+	iommu_free_table(tbl, node_name);
+
+	kfree(table_group);
+}
+
 static void tce_invalidate_pSeries_sw(struct iommu_table *tbl,
 				      __be64 *startp, __be64 *endp)
 {
@@ -193,7 +262,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	int ret = 0;
 	unsigned long flags;
 
-	if (npages == 1) {
+	if ((npages == 1) || !firmware_has_feature(FW_FEATURE_MULTITCE)) {
 		return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
 		                           direction, attrs);
 	}
@@ -285,6 +354,9 @@ static void tce_freemulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long n
 {
 	u64 rc;
 
+	if (!firmware_has_feature(FW_FEATURE_MULTITCE))
+		return tce_free_pSeriesLP(tbl, tcenum, npages);
+
 	rc = plpar_tce_stuff((u64)tbl->it_index, (u64)tcenum << 12, 0, npages);
 
 	if (rc && printk_ratelimit()) {
@@ -460,7 +532,6 @@ static int tce_setrange_multi_pSeriesLP_walk(unsigned long start_pfn,
 	return tce_setrange_multi_pSeriesLP(start_pfn, num_pfn, arg);
 }
 
-
 #ifdef CONFIG_PCI
 static void iommu_table_setparms(struct pci_controller *phb,
 				 struct device_node *dn,
@@ -546,6 +617,12 @@ static void iommu_table_setparms_lpar(struct pci_controller *phb,
 	tbl->it_size = size >> tbl->it_page_shift;
 }
 
+struct iommu_table_ops iommu_table_pseries_ops = {
+	.set = tce_build_pSeries,
+	.clear = tce_free_pSeries,
+	.get = tce_get_pseries
+};
+
 static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 {
 	struct device_node *dn;
@@ -610,12 +687,13 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 	pci->phb->dma_window_size = 0x8000000ul;
 	pci->phb->dma_window_base_cur = 0x8000000ul;
 
-	tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
-			   pci->phb->node);
+	pci->table_group = iommu_pseries_alloc_group(pci->phb->node);
+	tbl = pci->table_group->tables[0];
 
 	iommu_table_setparms(pci->phb, dn, tbl);
-	pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
-	iommu_register_group(tbl, pci_domain_nr(bus), 0);
+	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;
@@ -625,6 +703,11 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 	pr_debug("ISA/IDE, window size is 0x%llx\n", pci->phb->dma_window_size);
 }
 
+struct iommu_table_ops iommu_table_lpar_multi_ops = {
+	.set = tce_buildmulti_pSeriesLP,
+	.clear = tce_freemulti_pSeriesLP,
+	.get = tce_get_pSeriesLP
+};
 
 static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 {
@@ -653,15 +736,17 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 	ppci = PCI_DN(pdn);
 
 	pr_debug("  parent is %s, iommu_table: 0x%p\n",
-		 pdn->full_name, ppci->iommu_table);
+		 pdn->full_name, ppci->table_group);
 
-	if (!ppci->iommu_table) {
-		tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
-				   ppci->phb->node);
+	if (!ppci->table_group) {
+		ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node);
+		tbl = ppci->table_group->tables[0];
 		iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window);
-		ppci->iommu_table = iommu_init_table(tbl, ppci->phb->node);
-		iommu_register_group(tbl, pci_domain_nr(bus), 0);
-		pr_debug("  created table: %p\n", ppci->iommu_table);
+		tbl->it_ops = &iommu_table_lpar_multi_ops;
+		iommu_init_table(tbl, ppci->phb->node);
+		iommu_register_group(ppci->table_group,
+				pci_domain_nr(bus), 0);
+		pr_debug("  created table: %p\n", ppci->table_group);
 	}
 }
 
@@ -683,13 +768,15 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 		struct pci_controller *phb = PCI_DN(dn)->phb;
 
 		pr_debug(" --> first child, no bridge. Allocating iommu table.\n");
-		tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
-				   phb->node);
+		PCI_DN(dn)->table_group = iommu_pseries_alloc_group(phb->node);
+		tbl = PCI_DN(dn)->table_group->tables[0];
 		iommu_table_setparms(phb, dn, tbl);
-		PCI_DN(dn)->iommu_table = iommu_init_table(tbl, phb->node);
-		iommu_register_group(tbl, pci_domain_nr(phb->bus), 0);
-		set_iommu_table_base_and_group(&dev->dev,
-					       PCI_DN(dn)->iommu_table);
+		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;
 	}
 
@@ -697,13 +784,14 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 	 * an already allocated iommu table is found and use that.
 	 */
 
-	while (dn && PCI_DN(dn) && PCI_DN(dn)->iommu_table == NULL)
+	while (dn && PCI_DN(dn) && PCI_DN(dn)->table_group == NULL)
 		dn = dn->parent;
 
-	if (dn && PCI_DN(dn))
-		set_iommu_table_base_and_group(&dev->dev,
-					       PCI_DN(dn)->iommu_table);
-	else
+	if (dn && PCI_DN(dn)) {
+		set_iommu_table_base(&dev->dev,
+				PCI_DN(dn)->table_group->tables[0]);
+		iommu_add_device(&dev->dev);
+	} else
 		printk(KERN_WARNING "iommu: Device %s has no iommu table\n",
 		       pci_name(dev));
 }
@@ -1088,7 +1176,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	dn = pci_device_to_OF_node(dev);
 	pr_debug("  node is %s\n", dn->full_name);
 
-	for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->iommu_table;
+	for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group;
 	     pdn = pdn->parent) {
 		dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
 		if (dma_window)
@@ -1104,18 +1192,21 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	pr_debug("  parent is %s\n", pdn->full_name);
 
 	pci = PCI_DN(pdn);
-	if (!pci->iommu_table) {
-		tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
-				   pci->phb->node);
+	if (!pci->table_group) {
+		pci->table_group = iommu_pseries_alloc_group(pci->phb->node);
+		tbl = pci->table_group->tables[0];
 		iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window);
-		pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
-		iommu_register_group(tbl, pci_domain_nr(pci->phb->bus), 0);
-		pr_debug("  created table: %p\n", pci->iommu_table);
+		tbl->it_ops = &iommu_table_lpar_multi_ops;
+		iommu_init_table(tbl, pci->phb->node);
+		iommu_register_group(pci->table_group,
+				pci_domain_nr(pci->phb->bus), 0);
+		pr_debug("  created table: %p\n", pci->table_group);
 	} else {
-		pr_debug("  found DMA window, table: %p\n", pci->iommu_table);
+		pr_debug("  found DMA window, table: %p\n", pci->table_group);
 	}
 
-	set_iommu_table_base_and_group(&dev->dev, pci->iommu_table);
+	set_iommu_table_base(&dev->dev, pci->table_group->tables[0]);
+	iommu_add_device(&dev->dev);
 }
 
 static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)
@@ -1145,7 +1236,7 @@ static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)
 		 * search upwards in the tree until we either hit a dma-window
 		 * property, OR find a parent with a table already allocated.
 		 */
-		for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->iommu_table;
+		for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group;
 				pdn = pdn->parent) {
 			dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
 			if (dma_window)
@@ -1189,7 +1280,7 @@ static u64 dma_get_required_mask_pSeriesLP(struct device *dev)
 		dn = pci_device_to_OF_node(pdev);
 
 		/* search upwards for ibm,dma-window */
-		for (; dn && PCI_DN(dn) && !PCI_DN(dn)->iommu_table;
+		for (; dn && PCI_DN(dn) && !PCI_DN(dn)->table_group;
 				dn = dn->parent)
 			if (of_get_property(dn, "ibm,dma-window", NULL))
 				break;
@@ -1269,8 +1360,9 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
 		 * the device node.
 		 */
 		remove_ddw(np, false);
-		if (pci && pci->iommu_table)
-			iommu_free_table(pci->iommu_table, np->full_name);
+		if (pci && pci->table_group)
+			iommu_pseries_free_group(pci->table_group,
+					np->full_name);
 
 		spin_lock(&direct_window_list_lock);
 		list_for_each_entry(window, &direct_window_list, list) {
@@ -1300,22 +1392,11 @@ void iommu_init_early_pSeries(void)
 		return;
 
 	if (firmware_has_feature(FW_FEATURE_LPAR)) {
-		if (firmware_has_feature(FW_FEATURE_MULTITCE)) {
-			ppc_md.tce_build = tce_buildmulti_pSeriesLP;
-			ppc_md.tce_free	 = tce_freemulti_pSeriesLP;
-		} else {
-			ppc_md.tce_build = tce_build_pSeriesLP;
-			ppc_md.tce_free	 = tce_free_pSeriesLP;
-		}
-		ppc_md.tce_get   = tce_get_pSeriesLP;
 		pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeriesLP;
 		pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeriesLP;
 		ppc_md.dma_set_mask = dma_set_mask_pSeriesLP;
 		ppc_md.dma_get_required_mask = dma_get_required_mask_pSeriesLP;
 	} else {
-		ppc_md.tce_build = tce_build_pSeries;
-		ppc_md.tce_free  = tce_free_pSeries;
-		ppc_md.tce_get   = tce_get_pseries;
 		pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeries;
 		pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeries;
 	}
@@ -1333,8 +1414,6 @@ static int __init disable_multitce(char *str)
 	    firmware_has_feature(FW_FEATURE_LPAR) &&
 	    firmware_has_feature(FW_FEATURE_MULTITCE)) {
 		printk(KERN_INFO "Disabling MULTITCE firmware feature\n");
-		ppc_md.tce_build = tce_build_pSeriesLP;
-		ppc_md.tce_free	 = tce_free_pSeriesLP;
 		powerpc_firmware_features &= ~FW_FEATURE_MULTITCE;
 	}
 	return 1;