1 files changed, 240 insertions, 6 deletions

diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index ee95937bdaf1..0089dd49b4cb 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -35,6 +35,7 @@
 #include <asm/vio.h>
 #include <asm/tce.h>
 #include <asm/mmu_context.h>
+#include <asm/ppc-pci.h>
 
 #define DBG(...)
 
@@ -1086,7 +1087,7 @@ void iommu_tce_kill(struct iommu_table *tbl,
 }
 EXPORT_SYMBOL_GPL(iommu_tce_kill);
 
-int iommu_take_ownership(struct iommu_table *tbl)
+static int iommu_take_ownership(struct iommu_table *tbl)
 {
 	unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
 	int ret = 0;
@@ -1118,9 +1119,8 @@ int iommu_take_ownership(struct iommu_table *tbl)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(iommu_take_ownership);
 
-void iommu_release_ownership(struct iommu_table *tbl)
+static void iommu_release_ownership(struct iommu_table *tbl)
 {
 	unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
 
@@ -1137,7 +1137,6 @@ void iommu_release_ownership(struct iommu_table *tbl)
 		spin_unlock(&tbl->pools[i].lock);
 	spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
 }
-EXPORT_SYMBOL_GPL(iommu_release_ownership);
 
 int iommu_add_device(struct iommu_table_group *table_group, struct device *dev)
 {
@@ -1158,8 +1157,14 @@ int iommu_add_device(struct iommu_table_group *table_group, struct device *dev)
 
 	pr_debug("%s: Adding %s to iommu group %d\n",
 		 __func__, dev_name(dev),  iommu_group_id(table_group->group));
-
-	return iommu_group_add_device(table_group->group, dev);
+	/*
+	 * This is still not adding devices via the IOMMU bus notifier because
+	 * of pcibios_init() from arch/powerpc/kernel/pci_64.c which calls
+	 * pcibios_scan_phb() first (and this guy adds devices and triggers
+	 * the notifier) and only then it calls pci_bus_add_devices() which
+	 * configures DMA for buses which also creates PEs and IOMMU groups.
+	 */
+	return iommu_probe_device(dev);
 }
 EXPORT_SYMBOL_GPL(iommu_add_device);
 
@@ -1179,4 +1184,233 @@ void iommu_del_device(struct device *dev)
 	iommu_group_remove_device(dev);
 }
 EXPORT_SYMBOL_GPL(iommu_del_device);
+
+/*
+ * A simple iommu_table_group_ops which only allows reusing the existing
+ * iommu_table. This handles VFIO for POWER7 or the nested KVM.
+ * The ops does not allow creating windows and only allows reusing the existing
+ * one if it matches table_group->tce32_start/tce32_size/page_shift.
+ */
+static unsigned long spapr_tce_get_table_size(__u32 page_shift,
+					      __u64 window_size, __u32 levels)
+{
+	unsigned long size;
+
+	if (levels > 1)
+		return ~0U;
+	size = window_size >> (page_shift - 3);
+	return size;
+}
+
+static long spapr_tce_create_table(struct iommu_table_group *table_group, int num,
+				   __u32 page_shift, __u64 window_size, __u32 levels,
+				   struct iommu_table **ptbl)
+{
+	struct iommu_table *tbl = table_group->tables[0];
+
+	if (num > 0)
+		return -EPERM;
+
+	if (tbl->it_page_shift != page_shift ||
+	    tbl->it_size != (window_size >> page_shift) ||
+	    tbl->it_indirect_levels != levels - 1)
+		return -EINVAL;
+
+	*ptbl = iommu_tce_table_get(tbl);
+	return 0;
+}
+
+static long spapr_tce_set_window(struct iommu_table_group *table_group,
+				 int num, struct iommu_table *tbl)
+{
+	return tbl == table_group->tables[num] ? 0 : -EPERM;
+}
+
+static long spapr_tce_unset_window(struct iommu_table_group *table_group, int num)
+{
+	return 0;
+}
+
+static long spapr_tce_take_ownership(struct iommu_table_group *table_group)
+{
+	int i, j, rc = 0;
+
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+		struct iommu_table *tbl = table_group->tables[i];
+
+		if (!tbl || !tbl->it_map)
+			continue;
+
+		rc = iommu_take_ownership(tbl);
+		if (!rc)
+			continue;
+
+		for (j = 0; j < i; ++j)
+			iommu_release_ownership(table_group->tables[j]);
+		return rc;
+	}
+	return 0;
+}
+
+static void spapr_tce_release_ownership(struct iommu_table_group *table_group)
+{
+	int i;
+
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+		struct iommu_table *tbl = table_group->tables[i];
+
+		if (!tbl)
+			continue;
+
+		iommu_table_clear(tbl);
+		if (tbl->it_map)
+			iommu_release_ownership(tbl);
+	}
+}
+
+struct iommu_table_group_ops spapr_tce_table_group_ops = {
+	.get_table_size = spapr_tce_get_table_size,
+	.create_table = spapr_tce_create_table,
+	.set_window = spapr_tce_set_window,
+	.unset_window = spapr_tce_unset_window,
+	.take_ownership = spapr_tce_take_ownership,
+	.release_ownership = spapr_tce_release_ownership,
+};
+
+/*
+ * A simple iommu_ops to allow less cruft in generic VFIO code.
+ */
+static int spapr_tce_blocking_iommu_attach_dev(struct iommu_domain *dom,
+					       struct device *dev)
+{
+	struct iommu_group *grp = iommu_group_get(dev);
+	struct iommu_table_group *table_group;
+	int ret = -EINVAL;
+
+	if (!grp)
+		return -ENODEV;
+
+	table_group = iommu_group_get_iommudata(grp);
+	ret = table_group->ops->take_ownership(table_group);
+	iommu_group_put(grp);
+
+	return ret;
+}
+
+static void spapr_tce_blocking_iommu_set_platform_dma(struct device *dev)
+{
+	struct iommu_group *grp = iommu_group_get(dev);
+	struct iommu_table_group *table_group;
+
+	table_group = iommu_group_get_iommudata(grp);
+	table_group->ops->release_ownership(table_group);
+}
+
+static const struct iommu_domain_ops spapr_tce_blocking_domain_ops = {
+	.attach_dev = spapr_tce_blocking_iommu_attach_dev,
+};
+
+static bool spapr_tce_iommu_capable(struct device *dev, enum iommu_cap cap)
+{
+	switch (cap) {
+	case IOMMU_CAP_CACHE_COHERENCY:
+		return true;
+	default:
+		break;
+	}
+
+	return false;
+}
+
+static struct iommu_domain *spapr_tce_iommu_domain_alloc(unsigned int type)
+{
+	struct iommu_domain *dom;
+
+	if (type != IOMMU_DOMAIN_BLOCKED)
+		return NULL;
+
+	dom = kzalloc(sizeof(*dom), GFP_KERNEL);
+	if (!dom)
+		return NULL;
+
+	dom->ops = &spapr_tce_blocking_domain_ops;
+
+	return dom;
+}
+
+static struct iommu_device *spapr_tce_iommu_probe_device(struct device *dev)
+{
+	struct pci_dev *pdev;
+	struct pci_controller *hose;
+
+	if (!dev_is_pci(dev))
+		return ERR_PTR(-EPERM);
+
+	pdev = to_pci_dev(dev);
+	hose = pdev->bus->sysdata;
+
+	return &hose->iommu;
+}
+
+static void spapr_tce_iommu_release_device(struct device *dev)
+{
+}
+
+static struct iommu_group *spapr_tce_iommu_device_group(struct device *dev)
+{
+	struct pci_controller *hose;
+	struct pci_dev *pdev;
+
+	pdev = to_pci_dev(dev);
+	hose = pdev->bus->sysdata;
+
+	if (!hose->controller_ops.device_group)
+		return ERR_PTR(-ENOENT);
+
+	return hose->controller_ops.device_group(hose, pdev);
+}
+
+static const struct iommu_ops spapr_tce_iommu_ops = {
+	.capable = spapr_tce_iommu_capable,
+	.domain_alloc = spapr_tce_iommu_domain_alloc,
+	.probe_device = spapr_tce_iommu_probe_device,
+	.release_device = spapr_tce_iommu_release_device,
+	.device_group = spapr_tce_iommu_device_group,
+	.set_platform_dma_ops = spapr_tce_blocking_iommu_set_platform_dma,
+};
+
+static struct attribute *spapr_tce_iommu_attrs[] = {
+	NULL,
+};
+
+static struct attribute_group spapr_tce_iommu_group = {
+	.name = "spapr-tce-iommu",
+	.attrs = spapr_tce_iommu_attrs,
+};
+
+static const struct attribute_group *spapr_tce_iommu_groups[] = {
+	&spapr_tce_iommu_group,
+	NULL,
+};
+
+/*
+ * This registers IOMMU devices of PHBs. This needs to happen
+ * after core_initcall(iommu_init) + postcore_initcall(pci_driver_init) and
+ * before subsys_initcall(iommu_subsys_init).
+ */
+static int __init spapr_tce_setup_phb_iommus_initcall(void)
+{
+	struct pci_controller *hose;
+
+	list_for_each_entry(hose, &hose_list, list_node) {
+		iommu_device_sysfs_add(&hose->iommu, hose->parent,
+				       spapr_tce_iommu_groups, "iommu-phb%04x",
+				       hose->global_number);
+		iommu_device_register(&hose->iommu, &spapr_tce_iommu_ops,
+				      hose->parent);
+	}
+	return 0;
+}
+postcore_initcall_sync(spapr_tce_setup_phb_iommus_initcall);
+
 #endif /* CONFIG_IOMMU_API */