PPC: POWERNV: move iommu_add_device earlier

The current implementation of IOMMU on sPAPR does not use iommu_ops
and therefore does not call IOMMU API's bus_set_iommu() which
1) sets iommu_ops for a bus
2) registers a bus notifier
Instead, PCI devices are added to IOMMU groups from
subsys_initcall_sync(tce_iommu_init) which does basically the same
thing without using iommu_ops callbacks.

However Freescale PAMU driver (https://lkml.org/lkml/2013/7/1/158)
implements iommu_ops and when tce_iommu_init is called, every PCI device
is already added to some group so there is a conflict.

This patch does 2 things:
1. removes the loop in which PCI devices were added to groups and
adds explicit iommu_add_device() calls to add devices as soon as they get
the iommu_table pointer assigned to them.
2. moves a bus notifier to powernv code in order to avoid conflict with
the notifier from Freescale driver.

iommu_add_device() and iommu_del_device() are public now.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

4 files changed, 42 insertions, 9 deletions

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 084cdfa..614356c 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -460,7 +460,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 		return;
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
-	set_iommu_table_base(&pdev->dev, &pe->tce32_table);
+	set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table);
 }
 
 static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
@@ -468,7 +468,7 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
 	struct pci_dev *dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
-		set_iommu_table_base(&dev->dev, &pe->tce32_table);
+		set_iommu_table_base_and_group(&dev->dev, &pe->tce32_table);
 		if (dev->subordinate)
 			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
 	}
@@ -644,7 +644,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 	iommu_register_group(tbl, pci_domain_nr(pe->pbus), pe->pe_number);
 
 	if (pe->pdev)
-		set_iommu_table_base(&pe->pdev->dev, tbl);
+		set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
 	else
 		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 
@@ -722,7 +722,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 	iommu_init_table(tbl, phb->hose->node);
 
 	if (pe->pdev)
-		set_iommu_table_base(&pe->pdev->dev, tbl);
+		set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
 	else
 		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 
diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
index f8b4bd8..e3807d6 100644
--- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c
+++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
@@ -92,7 +92,7 @@ static void pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb,
 				pci_domain_nr(phb->hose->bus), phb->opal_id);
 	}
 
-	set_iommu_table_base(&pdev->dev, &phb->p5ioc2.iommu_table);
+	set_iommu_table_base_and_group(&pdev->dev, &phb->p5ioc2.iommu_table);
 }
 
 static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 4eb33a9..6f3d49c 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -536,7 +536,7 @@ static void pnv_pci_dma_fallback_setup(struct pci_controller *hose,
 		pdn->iommu_table = pnv_pci_setup_bml_iommu(hose);
 	if (!pdn->iommu_table)
 		return;
-	set_iommu_table_base(&pdev->dev, pdn->iommu_table);
+	set_iommu_table_base_and_group(&pdev->dev, pdn->iommu_table);
 }
 
 static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
@@ -657,3 +657,34 @@ void __init pnv_pci_init(void)
 	ppc_md.teardown_msi_irqs = pnv_teardown_msi_irqs;
 #endif
 }
+
+static int tce_iommu_bus_notifier(struct notifier_block *nb,
+		unsigned long action, void *data)
+{
+	struct device *dev = data;
+
+	switch (action) {
+	case BUS_NOTIFY_ADD_DEVICE:
+		return iommu_add_device(dev);
+	case BUS_NOTIFY_DEL_DEVICE:
+		if (dev->iommu_group)
+			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)
+{
+	BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE);
+
+	bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
+	return 0;
+}
+
+subsys_initcall_sync(tce_iommu_bus_notifier_init);
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index f253361..a80af6c 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -687,7 +687,8 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 		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(&dev->dev, PCI_DN(dn)->iommu_table);
+		set_iommu_table_base_and_group(&dev->dev,
+					       PCI_DN(dn)->iommu_table);
 		return;
 	}
 
@@ -699,7 +700,8 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 		dn = dn->parent;
 
 	if (dn && PCI_DN(dn))
-		set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table);
+		set_iommu_table_base_and_group(&dev->dev,
+					       PCI_DN(dn)->iommu_table);
 	else
 		printk(KERN_WARNING "iommu: Device %s has no iommu table\n",
 		       pci_name(dev));
@@ -1193,7 +1195,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 		pr_debug("  found DMA window, table: %p\n", pci->iommu_table);
 	}
 
-	set_iommu_table_base(&dev->dev, pci->iommu_table);
+	set_iommu_table_base_and_group(&dev->dev, pci->iommu_table);
 }
 
 static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)