1 files changed, 126 insertions, 797 deletions

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 73a63efcf855..c9c25fb0783c 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -115,32 +115,13 @@ static int __init pci_reset_phbs_setup(char *str)
 
 early_param("ppc_pci_reset_phbs", pci_reset_phbs_setup);
 
-static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r)
-{
-	/*
-	 * WARNING: We cannot rely on the resource flags. The Linux PCI
-	 * allocation code sometimes decides to put a 64-bit prefetchable
-	 * BAR in the 32-bit window, so we have to compare the addresses.
-	 *
-	 * For simplicity we only test resource start.
-	 */
-	return (r->start >= phb->ioda.m64_base &&
-		r->start < (phb->ioda.m64_base + phb->ioda.m64_size));
-}
-
-static inline bool pnv_pci_is_m64_flags(unsigned long resource_flags)
-{
-	unsigned long flags = (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH);
-
-	return (resource_flags & flags) == flags;
-}
-
 static struct pnv_ioda_pe *pnv_ioda_init_pe(struct pnv_phb *phb, int pe_no)
 {
 	s64 rc;
 
 	phb->ioda.pe_array[pe_no].phb = phb;
 	phb->ioda.pe_array[pe_no].pe_number = pe_no;
+	phb->ioda.pe_array[pe_no].dma_setup_done = false;
 
 	/*
 	 * Clear the PE frozen state as it might be put into frozen state
@@ -164,26 +145,48 @@ static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no)
 		return;
 	}
 
+	mutex_lock(&phb->ioda.pe_alloc_mutex);
 	if (test_and_set_bit(pe_no, phb->ioda.pe_alloc))
 		pr_debug("%s: PE %x was reserved on PHB#%x\n",
 			 __func__, pe_no, phb->hose->global_number);
+	mutex_unlock(&phb->ioda.pe_alloc_mutex);
 
 	pnv_ioda_init_pe(phb, pe_no);
 }
 
-static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb)
+struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb, int count)
 {
-	long pe;
+	struct pnv_ioda_pe *ret = NULL;
+	int run = 0, pe, i;
+
+	mutex_lock(&phb->ioda.pe_alloc_mutex);
 
+	/* scan backwards for a run of @count cleared bits */
 	for (pe = phb->ioda.total_pe_num - 1; pe >= 0; pe--) {
-		if (!test_and_set_bit(pe, phb->ioda.pe_alloc))
-			return pnv_ioda_init_pe(phb, pe);
+		if (test_bit(pe, phb->ioda.pe_alloc)) {
+			run = 0;
+			continue;
+		}
+
+		run++;
+		if (run == count)
+			break;
+	}
+	if (run != count)
+		goto out;
+
+	for (i = pe; i < pe + count; i++) {
+		set_bit(i, phb->ioda.pe_alloc);
+		pnv_ioda_init_pe(phb, i);
 	}
+	ret = &phb->ioda.pe_array[pe];
 
-	return NULL;
+out:
+	mutex_unlock(&phb->ioda.pe_alloc_mutex);
+	return ret;
 }
 
-static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe)
+void pnv_ioda_free_pe(struct pnv_ioda_pe *pe)
 {
 	struct pnv_phb *phb = pe->phb;
 	unsigned int pe_num = pe->pe_number;
@@ -192,7 +195,10 @@ static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe)
 	WARN_ON(pe->npucomp); /* NPUs for nvlink are not supposed to be freed */
 	kfree(pe->npucomp);
 	memset(pe, 0, sizeof(struct pnv_ioda_pe));
+
+	mutex_lock(&phb->ioda.pe_alloc_mutex);
 	clear_bit(pe_num, phb->ioda.pe_alloc);
+	mutex_unlock(&phb->ioda.pe_alloc_mutex);
 }
 
 /* The default M64 BAR is shared by all PEs */
@@ -252,8 +258,7 @@ fail:
 static void pnv_ioda_reserve_dev_m64_pe(struct pci_dev *pdev,
 					 unsigned long *pe_bitmap)
 {
-	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-	struct pnv_phb *phb = hose->private_data;
+	struct pnv_phb *phb = pci_bus_to_pnvhb(pdev->bus);
 	struct resource *r;
 	resource_size_t base, sgsz, start, end;
 	int segno, i;
@@ -311,6 +316,28 @@ static int pnv_ioda1_init_m64(struct pnv_phb *phb)
 		}
 	}
 
+	for (index = 0; index < phb->ioda.total_pe_num; index++) {
+		int64_t rc;
+
+		/*
+		 * P7IOC supports M64DT, which helps mapping M64 segment
+		 * to one particular PE#. However, PHB3 has fixed mapping
+		 * between M64 segment and PE#. In order to have same logic
+		 * for P7IOC and PHB3, we enforce fixed mapping between M64
+		 * segment and PE# on P7IOC.
+		 */
+		rc = opal_pci_map_pe_mmio_window(phb->opal_id,
+				index, OPAL_M64_WINDOW_TYPE,
+				index / PNV_IODA1_M64_SEGS,
+				index % PNV_IODA1_M64_SEGS);
+		if (rc != OPAL_SUCCESS) {
+			pr_warn("%s: Error %lld mapping M64 for PHB#%x-PE#%x\n",
+				__func__, rc, phb->hose->global_number,
+				index);
+			goto fail;
+		}
+	}
+
 	/*
 	 * Exclude the segments for reserved and root bus PE, which
 	 * are first or last two PEs.
@@ -351,8 +378,7 @@ static void pnv_ioda_reserve_m64_pe(struct pci_bus *bus,
 
 static struct pnv_ioda_pe *pnv_ioda_pick_m64_pe(struct pci_bus *bus, bool all)
 {
-	struct pci_controller *hose = pci_bus_to_host(bus);
-	struct pnv_phb *phb = hose->private_data;
+	struct pnv_phb *phb = pci_bus_to_pnvhb(bus);
 	struct pnv_ioda_pe *master_pe, *pe;
 	unsigned long size, *pe_alloc;
 	int i;
@@ -403,26 +429,6 @@ static struct pnv_ioda_pe *pnv_ioda_pick_m64_pe(struct pci_bus *bus, bool all)
 			pe->master = master_pe;
 			list_add_tail(&pe->list, &master_pe->slaves);
 		}
-
-		/*
-		 * P7IOC supports M64DT, which helps mapping M64 segment
-		 * to one particular PE#. However, PHB3 has fixed mapping
-		 * between M64 segment and PE#. In order to have same logic
-		 * for P7IOC and PHB3, we enforce fixed mapping between M64
-		 * segment and PE# on P7IOC.
-		 */
-		if (phb->type == PNV_PHB_IODA1) {
-			int64_t rc;
-
-			rc = opal_pci_map_pe_mmio_window(phb->opal_id,
-					pe->pe_number, OPAL_M64_WINDOW_TYPE,
-					pe->pe_number / PNV_IODA1_M64_SEGS,
-					pe->pe_number % PNV_IODA1_M64_SEGS);
-			if (rc != OPAL_SUCCESS)
-				pr_warn("%s: Error %lld mapping M64 for PHB#%x-PE#%x\n",
-					__func__, rc, phb->hose->global_number,
-					pe->pe_number);
-		}
 	}
 
 	kfree(pe_alloc);
@@ -673,8 +679,7 @@ struct pnv_ioda_pe *pnv_pci_bdfn_to_pe(struct pnv_phb *phb, u16 bdfn)
 
 struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev)
 {
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
+	struct pnv_phb *phb = pci_bus_to_pnvhb(dev->bus);
 	struct pci_dn *pdn = pci_get_pdn(dev);
 
 	if (!pdn)
@@ -816,7 +821,7 @@ static void pnv_ioda_unset_peltv(struct pnv_phb *phb,
 		pe_warn(pe, "OPAL error %lld remove self from PELTV\n", rc);
 }
 
-static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
+int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 {
 	struct pci_dev *parent;
 	uint8_t bcomp, dcomp, fcomp;
@@ -887,7 +892,7 @@ static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 	return 0;
 }
 
-static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
+int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 {
 	struct pci_dev *parent;
 	uint8_t bcomp, dcomp, fcomp;
@@ -982,95 +987,9 @@ out:
 	return 0;
 }
 
-#ifdef CONFIG_PCI_IOV
-static int pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset)
-{
-	struct pci_dn *pdn = pci_get_pdn(dev);
-	int i;
-	struct resource *res, res2;
-	resource_size_t size;
-	u16 num_vfs;
-
-	if (!dev->is_physfn)
-		return -EINVAL;
-
-	/*
-	 * "offset" is in VFs.  The M64 windows are sized so that when they
-	 * are segmented, each segment is the same size as the IOV BAR.
-	 * Each segment is in a separate PE, and the high order bits of the
-	 * address are the PE number.  Therefore, each VF's BAR is in a
-	 * separate PE, and changing the IOV BAR start address changes the
-	 * range of PEs the VFs are in.
-	 */
-	num_vfs = pdn->num_vfs;
-	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
-		res = &dev->resource[i + PCI_IOV_RESOURCES];
-		if (!res->flags || !res->parent)
-			continue;
-
-		/*
-		 * The actual IOV BAR range is determined by the start address
-		 * and the actual size for num_vfs VFs BAR.  This check is to
-		 * make sure that after shifting, the range will not overlap
-		 * with another device.
-		 */
-		size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES);
-		res2.flags = res->flags;
-		res2.start = res->start + (size * offset);
-		res2.end = res2.start + (size * num_vfs) - 1;
-
-		if (res2.end > res->end) {
-			dev_err(&dev->dev, "VF BAR%d: %pR would extend past %pR (trying to enable %d VFs shifted by %d)\n",
-				i, &res2, res, num_vfs, offset);
-			return -EBUSY;
-		}
-	}
-
-	/*
-	 * Since M64 BAR shares segments among all possible 256 PEs,
-	 * we have to shift the beginning of PF IOV BAR to make it start from
-	 * the segment which belongs to the PE number assigned to the first VF.
-	 * This creates a "hole" in the /proc/iomem which could be used for
-	 * allocating other resources so we reserve this area below and
-	 * release when IOV is released.
-	 */
-	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
-		res = &dev->resource[i + PCI_IOV_RESOURCES];
-		if (!res->flags || !res->parent)
-			continue;
-
-		size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES);
-		res2 = *res;
-		res->start += size * offset;
-
-		dev_info(&dev->dev, "VF BAR%d: %pR shifted to %pR (%sabling %d VFs shifted by %d)\n",
-			 i, &res2, res, (offset > 0) ? "En" : "Dis",
-			 num_vfs, offset);
-
-		if (offset < 0) {
-			devm_release_resource(&dev->dev, &pdn->holes[i]);
-			memset(&pdn->holes[i], 0, sizeof(pdn->holes[i]));
-		}
-
-		pci_update_resource(dev, i + PCI_IOV_RESOURCES);
-
-		if (offset > 0) {
-			pdn->holes[i].start = res2.start;
-			pdn->holes[i].end = res2.start + size * offset - 1;
-			pdn->holes[i].flags = IORESOURCE_BUS;
-			pdn->holes[i].name = "pnv_iov_reserved";
-			devm_request_resource(&dev->dev, res->parent,
-					&pdn->holes[i]);
-		}
-	}
-	return 0;
-}
-#endif /* CONFIG_PCI_IOV */
-
 static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 {
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
+	struct pnv_phb *phb = pci_bus_to_pnvhb(dev->bus);
 	struct pci_dn *pdn = pci_get_pdn(dev);
 	struct pnv_ioda_pe *pe;
 
@@ -1082,7 +1001,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 	if (pdn->pe_number != IODA_INVALID_PE)
 		return NULL;
 
-	pe = pnv_ioda_alloc_pe(phb);
+	pe = pnv_ioda_alloc_pe(phb, 1);
 	if (!pe) {
 		pr_warn("%s: Not enough PE# available, disabling device\n",
 			pci_name(dev));
@@ -1129,8 +1048,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
  */
 static struct pnv_ioda_pe *pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all)
 {
-	struct pci_controller *hose = pci_bus_to_host(bus);
-	struct pnv_phb *phb = hose->private_data;
+	struct pnv_phb *phb = pci_bus_to_pnvhb(bus);
 	struct pnv_ioda_pe *pe = NULL;
 	unsigned int pe_num;
 
@@ -1154,7 +1072,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all)
 
 	/* The PE number isn't pinned by M64 */
 	if (!pe)
-		pe = pnv_ioda_alloc_pe(phb);
+		pe = pnv_ioda_alloc_pe(phb, 1);
 
 	if (!pe) {
 		pr_warn("%s: Not enough PE# available for PCI bus %04x:%02x\n",
@@ -1196,8 +1114,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)
 	struct pnv_ioda_pe *pe;
 	struct pci_dev *gpu_pdev;
 	struct pci_dn *npu_pdn;
-	struct pci_controller *hose = pci_bus_to_host(npu_pdev->bus);
-	struct pnv_phb *phb = hose->private_data;
+	struct pnv_phb *phb = pci_bus_to_pnvhb(npu_pdev->bus);
 
 	/*
 	 * Intentionally leak a reference on the npu device (for
@@ -1297,446 +1214,12 @@ static void pnv_pci_ioda_setup_nvlink(void)
 #endif
 }
 
-#ifdef CONFIG_PCI_IOV
-static int pnv_pci_vf_release_m64(struct pci_dev *pdev, u16 num_vfs)
-{
-	struct pci_bus        *bus;
-	struct pci_controller *hose;
-	struct pnv_phb        *phb;
-	struct pci_dn         *pdn;
-	int                    i, j;
-	int                    m64_bars;
-
-	bus = pdev->bus;
-	hose = pci_bus_to_host(bus);
-	phb = hose->private_data;
-	pdn = pci_get_pdn(pdev);
-
-	if (pdn->m64_single_mode)
-		m64_bars = num_vfs;
-	else
-		m64_bars = 1;
-
-	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++)
-		for (j = 0; j < m64_bars; j++) {
-			if (pdn->m64_map[j][i] == IODA_INVALID_M64)
-				continue;
-			opal_pci_phb_mmio_enable(phb->opal_id,
-				OPAL_M64_WINDOW_TYPE, pdn->m64_map[j][i], 0);
-			clear_bit(pdn->m64_map[j][i], &phb->ioda.m64_bar_alloc);
-			pdn->m64_map[j][i] = IODA_INVALID_M64;
-		}
-
-	kfree(pdn->m64_map);
-	return 0;
-}
-
-static int pnv_pci_vf_assign_m64(struct pci_dev *pdev, u16 num_vfs)
-{
-	struct pci_bus        *bus;
-	struct pci_controller *hose;
-	struct pnv_phb        *phb;
-	struct pci_dn         *pdn;
-	unsigned int           win;
-	struct resource       *res;
-	int                    i, j;
-	int64_t                rc;
-	int                    total_vfs;
-	resource_size_t        size, start;
-	int                    pe_num;
-	int                    m64_bars;
-
-	bus = pdev->bus;
-	hose = pci_bus_to_host(bus);
-	phb = hose->private_data;
-	pdn = pci_get_pdn(pdev);
-	total_vfs = pci_sriov_get_totalvfs(pdev);
-
-	if (pdn->m64_single_mode)
-		m64_bars = num_vfs;
-	else
-		m64_bars = 1;
-
-	pdn->m64_map = kmalloc_array(m64_bars,
-				     sizeof(*pdn->m64_map),
-				     GFP_KERNEL);
-	if (!pdn->m64_map)
-		return -ENOMEM;
-	/* Initialize the m64_map to IODA_INVALID_M64 */
-	for (i = 0; i < m64_bars ; i++)
-		for (j = 0; j < PCI_SRIOV_NUM_BARS; j++)
-			pdn->m64_map[i][j] = IODA_INVALID_M64;
-
-
-	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
-		res = &pdev->resource[i + PCI_IOV_RESOURCES];
-		if (!res->flags || !res->parent)
-			continue;
-
-		for (j = 0; j < m64_bars; j++) {
-			do {
-				win = find_next_zero_bit(&phb->ioda.m64_bar_alloc,
-						phb->ioda.m64_bar_idx + 1, 0);
-
-				if (win >= phb->ioda.m64_bar_idx + 1)
-					goto m64_failed;
-			} while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc));
-
-			pdn->m64_map[j][i] = win;
-
-			if (pdn->m64_single_mode) {
-				size = pci_iov_resource_size(pdev,
-							PCI_IOV_RESOURCES + i);
-				start = res->start + size * j;
-			} else {
-				size = resource_size(res);
-				start = res->start;
-			}
-
-			/* Map the M64 here */
-			if (pdn->m64_single_mode) {
-				pe_num = pdn->pe_num_map[j];
-				rc = opal_pci_map_pe_mmio_window(phb->opal_id,
-						pe_num, OPAL_M64_WINDOW_TYPE,
-						pdn->m64_map[j][i], 0);
-			}
-
-			rc = opal_pci_set_phb_mem_window(phb->opal_id,
-						 OPAL_M64_WINDOW_TYPE,
-						 pdn->m64_map[j][i],
-						 start,
-						 0, /* unused */
-						 size);
-
-
-			if (rc != OPAL_SUCCESS) {
-				dev_err(&pdev->dev, "Failed to map M64 window #%d: %lld\n",
-					win, rc);
-				goto m64_failed;
-			}
-
-			if (pdn->m64_single_mode)
-				rc = opal_pci_phb_mmio_enable(phb->opal_id,
-				     OPAL_M64_WINDOW_TYPE, pdn->m64_map[j][i], 2);
-			else
-				rc = opal_pci_phb_mmio_enable(phb->opal_id,
-				     OPAL_M64_WINDOW_TYPE, pdn->m64_map[j][i], 1);
-
-			if (rc != OPAL_SUCCESS) {
-				dev_err(&pdev->dev, "Failed to enable M64 window #%d: %llx\n",
-					win, rc);
-				goto m64_failed;
-			}
-		}
-	}
-	return 0;
-
-m64_failed:
-	pnv_pci_vf_release_m64(pdev, num_vfs);
-	return -EBUSY;
-}
-
-static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group,
-		int num);
-
-static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe *pe)
-{
-	struct iommu_table    *tbl;
-	int64_t               rc;
-
-	tbl = pe->table_group.tables[0];
-	rc = pnv_pci_ioda2_unset_window(&pe->table_group, 0);
-	if (rc)
-		pe_warn(pe, "OPAL error %lld release DMA window\n", rc);
-
-	pnv_pci_ioda2_set_bypass(pe, false);
-	if (pe->table_group.group) {
-		iommu_group_put(pe->table_group.group);
-		BUG_ON(pe->table_group.group);
-	}
-	iommu_tce_table_put(tbl);
-}
-
-static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
-{
-	struct pci_bus        *bus;
-	struct pci_controller *hose;
-	struct pnv_phb        *phb;
-	struct pnv_ioda_pe    *pe, *pe_n;
-	struct pci_dn         *pdn;
-
-	bus = pdev->bus;
-	hose = pci_bus_to_host(bus);
-	phb = hose->private_data;
-	pdn = pci_get_pdn(pdev);
-
-	if (!pdev->is_physfn)
-		return;
-
-	list_for_each_entry_safe(pe, pe_n, &phb->ioda.pe_list, list) {
-		if (pe->parent_dev != pdev)
-			continue;
-
-		pnv_pci_ioda2_release_dma_pe(pdev, pe);
-
-		/* Remove from list */
-		mutex_lock(&phb->ioda.pe_list_mutex);
-		list_del(&pe->list);
-		mutex_unlock(&phb->ioda.pe_list_mutex);
-
-		pnv_ioda_deconfigure_pe(phb, pe);
-
-		pnv_ioda_free_pe(pe);
-	}
-}
-
-void pnv_pci_sriov_disable(struct pci_dev *pdev)
-{
-	struct pci_bus        *bus;
-	struct pci_controller *hose;
-	struct pnv_phb        *phb;
-	struct pnv_ioda_pe    *pe;
-	struct pci_dn         *pdn;
-	u16                    num_vfs, i;
-
-	bus = pdev->bus;
-	hose = pci_bus_to_host(bus);
-	phb = hose->private_data;
-	pdn = pci_get_pdn(pdev);
-	num_vfs = pdn->num_vfs;
-
-	/* Release VF PEs */
-	pnv_ioda_release_vf_PE(pdev);
-
-	if (phb->type == PNV_PHB_IODA2) {
-		if (!pdn->m64_single_mode)
-			pnv_pci_vf_resource_shift(pdev, -*pdn->pe_num_map);
-
-		/* Release M64 windows */
-		pnv_pci_vf_release_m64(pdev, num_vfs);
-
-		/* Release PE numbers */
-		if (pdn->m64_single_mode) {
-			for (i = 0; i < num_vfs; i++) {
-				if (pdn->pe_num_map[i] == IODA_INVALID_PE)
-					continue;
-
-				pe = &phb->ioda.pe_array[pdn->pe_num_map[i]];
-				pnv_ioda_free_pe(pe);
-			}
-		} else
-			bitmap_clear(phb->ioda.pe_alloc, *pdn->pe_num_map, num_vfs);
-		/* Releasing pe_num_map */
-		kfree(pdn->pe_num_map);
-	}
-}
-
-static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
+static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
 				       struct pnv_ioda_pe *pe);
-static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
-{
-	struct pci_bus        *bus;
-	struct pci_controller *hose;
-	struct pnv_phb        *phb;
-	struct pnv_ioda_pe    *pe;
-	int                    pe_num;
-	u16                    vf_index;
-	struct pci_dn         *pdn;
-
-	bus = pdev->bus;
-	hose = pci_bus_to_host(bus);
-	phb = hose->private_data;
-	pdn = pci_get_pdn(pdev);
-
-	if (!pdev->is_physfn)
-		return;
-
-	/* Reserve PE for each VF */
-	for (vf_index = 0; vf_index < num_vfs; vf_index++) {
-		int vf_devfn = pci_iov_virtfn_devfn(pdev, vf_index);
-		int vf_bus = pci_iov_virtfn_bus(pdev, vf_index);
-		struct pci_dn *vf_pdn;
-
-		if (pdn->m64_single_mode)
-			pe_num = pdn->pe_num_map[vf_index];
-		else
-			pe_num = *pdn->pe_num_map + vf_index;
-
-		pe = &phb->ioda.pe_array[pe_num];
-		pe->pe_number = pe_num;
-		pe->phb = phb;
-		pe->flags = PNV_IODA_PE_VF;
-		pe->pbus = NULL;
-		pe->parent_dev = pdev;
-		pe->mve_number = -1;
-		pe->rid = (vf_bus << 8) | vf_devfn;
-
-		pe_info(pe, "VF %04d:%02d:%02d.%d associated with PE#%x\n",
-			hose->global_number, pdev->bus->number,
-			PCI_SLOT(vf_devfn), PCI_FUNC(vf_devfn), pe_num);
-
-		if (pnv_ioda_configure_pe(phb, pe)) {
-			/* XXX What do we do here ? */
-			pnv_ioda_free_pe(pe);
-			pe->pdev = NULL;
-			continue;
-		}
-
-		/* Put PE to the list */
-		mutex_lock(&phb->ioda.pe_list_mutex);
-		list_add_tail(&pe->list, &phb->ioda.pe_list);
-		mutex_unlock(&phb->ioda.pe_list_mutex);
-
-		/* associate this pe to it's pdn */
-		list_for_each_entry(vf_pdn, &pdn->parent->child_list, list) {
-			if (vf_pdn->busno == vf_bus &&
-			    vf_pdn->devfn == vf_devfn) {
-				vf_pdn->pe_number = pe_num;
-				break;
-			}
-		}
-
-		pnv_pci_ioda2_setup_dma_pe(phb, pe);
-	}
-}
-
-int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
-{
-	struct pci_bus        *bus;
-	struct pci_controller *hose;
-	struct pnv_phb        *phb;
-	struct pnv_ioda_pe    *pe;
-	struct pci_dn         *pdn;
-	int                    ret;
-	u16                    i;
-
-	bus = pdev->bus;
-	hose = pci_bus_to_host(bus);
-	phb = hose->private_data;
-	pdn = pci_get_pdn(pdev);
-
-	if (phb->type == PNV_PHB_IODA2) {
-		if (!pdn->vfs_expanded) {
-			dev_info(&pdev->dev, "don't support this SRIOV device"
-				" with non 64bit-prefetchable IOV BAR\n");
-			return -ENOSPC;
-		}
-
-		/*
-		 * When M64 BARs functions in Single PE mode, the number of VFs
-		 * could be enabled must be less than the number of M64 BARs.
-		 */
-		if (pdn->m64_single_mode && num_vfs > phb->ioda.m64_bar_idx) {
-			dev_info(&pdev->dev, "Not enough M64 BAR for VFs\n");
-			return -EBUSY;
-		}
-
-		/* Allocating pe_num_map */
-		if (pdn->m64_single_mode)
-			pdn->pe_num_map = kmalloc_array(num_vfs,
-							sizeof(*pdn->pe_num_map),
-							GFP_KERNEL);
-		else
-			pdn->pe_num_map = kmalloc(sizeof(*pdn->pe_num_map), GFP_KERNEL);
-
-		if (!pdn->pe_num_map)
-			return -ENOMEM;
-
-		if (pdn->m64_single_mode)
-			for (i = 0; i < num_vfs; i++)
-				pdn->pe_num_map[i] = IODA_INVALID_PE;
-
-		/* Calculate available PE for required VFs */
-		if (pdn->m64_single_mode) {
-			for (i = 0; i < num_vfs; i++) {
-				pe = pnv_ioda_alloc_pe(phb);
-				if (!pe) {
-					ret = -EBUSY;
-					goto m64_failed;
-				}
-
-				pdn->pe_num_map[i] = pe->pe_number;
-			}
-		} else {
-			mutex_lock(&phb->ioda.pe_alloc_mutex);
-			*pdn->pe_num_map = bitmap_find_next_zero_area(
-				phb->ioda.pe_alloc, phb->ioda.total_pe_num,
-				0, num_vfs, 0);
-			if (*pdn->pe_num_map >= phb->ioda.total_pe_num) {
-				mutex_unlock(&phb->ioda.pe_alloc_mutex);
-				dev_info(&pdev->dev, "Failed to enable VF%d\n", num_vfs);
-				kfree(pdn->pe_num_map);
-				return -EBUSY;
-			}
-			bitmap_set(phb->ioda.pe_alloc, *pdn->pe_num_map, num_vfs);
-			mutex_unlock(&phb->ioda.pe_alloc_mutex);
-		}
-		pdn->num_vfs = num_vfs;
-
-		/* Assign M64 window accordingly */
-		ret = pnv_pci_vf_assign_m64(pdev, num_vfs);
-		if (ret) {
-			dev_info(&pdev->dev, "Not enough M64 window resources\n");
-			goto m64_failed;
-		}
-
-		/*
-		 * When using one M64 BAR to map one IOV BAR, we need to shift
-		 * the IOV BAR according to the PE# allocated to the VFs.
-		 * Otherwise, the PE# for the VF will conflict with others.
-		 */
-		if (!pdn->m64_single_mode) {
-			ret = pnv_pci_vf_resource_shift(pdev, *pdn->pe_num_map);
-			if (ret)
-				goto m64_failed;
-		}
-	}
-
-	/* Setup VF PEs */
-	pnv_ioda_setup_vf_PE(pdev, num_vfs);
-
-	return 0;
-
-m64_failed:
-	if (pdn->m64_single_mode) {
-		for (i = 0; i < num_vfs; i++) {
-			if (pdn->pe_num_map[i] == IODA_INVALID_PE)
-				continue;
-
-			pe = &phb->ioda.pe_array[pdn->pe_num_map[i]];
-			pnv_ioda_free_pe(pe);
-		}
-	} else
-		bitmap_clear(phb->ioda.pe_alloc, *pdn->pe_num_map, num_vfs);
-
-	/* Releasing pe_num_map */
-	kfree(pdn->pe_num_map);
-
-	return ret;
-}
-
-int pnv_pcibios_sriov_disable(struct pci_dev *pdev)
-{
-	pnv_pci_sriov_disable(pdev);
-
-	/* Release PCI data */
-	remove_sriov_vf_pdns(pdev);
-	return 0;
-}
-
-int pnv_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
-{
-	/* Allocate PCI data */
-	add_sriov_vf_pdns(pdev);
-
-	return pnv_pci_sriov_enable(pdev, num_vfs);
-}
-#endif /* CONFIG_PCI_IOV */
 
 static void pnv_pci_ioda_dma_dev_setup(struct pci_dev *pdev)
 {
-	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-	struct pnv_phb *phb = hose->private_data;
+	struct pnv_phb *phb = pci_bus_to_pnvhb(pdev->bus);
 	struct pci_dn *pdn = pci_get_pdn(pdev);
 	struct pnv_ioda_pe *pe;
 
@@ -1762,6 +1245,24 @@ static void pnv_pci_ioda_dma_dev_setup(struct pci_dev *pdev)
 		pci_info(pdev, "Added to existing PE#%x\n", pe->pe_number);
 	}
 
+	/*
+	 * We assume that bridges *probably* don't need to do any DMA so we can
+	 * skip allocating a TCE table, etc unless we get a non-bridge device.
+	 */
+	if (!pe->dma_setup_done && !pci_is_bridge(pdev)) {
+		switch (phb->type) {
+		case PNV_PHB_IODA1:
+			pnv_pci_ioda1_setup_dma_pe(phb, pe);
+			break;
+		case PNV_PHB_IODA2:
+			pnv_pci_ioda2_setup_dma_pe(phb, pe);
+			break;
+		default:
+			pr_warn("%s: No DMA for PHB#%x (type %d)\n",
+				__func__, phb->hose->global_number, phb->type);
+		}
+	}
+
 	if (pdn)
 		pdn->pe_number = pe->pe_number;
 	pe->device_count++;
@@ -1847,8 +1348,7 @@ err:
 static bool pnv_pci_ioda_iommu_bypass_supported(struct pci_dev *pdev,
 		u64 dma_mask)
 {
-	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-	struct pnv_phb *phb = hose->private_data;
+	struct pnv_phb *phb = pci_bus_to_pnvhb(pdev->bus);
 	struct pci_dn *pdn = pci_get_pdn(pdev);
 	struct pnv_ioda_pe *pe;
 
@@ -1885,19 +1385,6 @@ static bool pnv_pci_ioda_iommu_bypass_supported(struct pci_dev *pdev,
 	return false;
 }
 
-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->table_group.tables[0]);
-		dev->dev.archdata.dma_offset = pe->tce_bypass_base;
-
-		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
-			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
-	}
-}
-
 static inline __be64 __iomem *pnv_ioda_get_inval_reg(struct pnv_phb *phb,
 						     bool real_mode)
 {
@@ -2285,6 +1772,7 @@ found:
 	pe->table_group.tce32_size = tbl->it_size << tbl->it_page_shift;
 	iommu_init_table(tbl, phb->hose->node, 0, 0);
 
+	pe->dma_setup_done = true;
 	return;
  fail:
 	/* XXX Failure: Try to fallback to 64-bit only ? */
@@ -2474,7 +1962,6 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
 	return 0;
 }
 
-#if defined(CONFIG_IOMMU_API) || defined(CONFIG_PCI_IOV)
 static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group,
 		int num)
 {
@@ -2498,7 +1985,6 @@ static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group,
 
 	return ret;
 }
-#endif
 
 #ifdef CONFIG_IOMMU_API
 unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
@@ -2547,6 +2033,19 @@ static long pnv_pci_ioda2_create_table_userspace(
 	return ret;
 }
 
+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->table_group.tables[0]);
+		dev->dev.archdata.dma_offset = pe->tce_bypass_base;
+
+		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
+			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
+	}
+}
+
 static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
 {
 	struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
@@ -2583,14 +2082,11 @@ static struct iommu_table_group_ops pnv_pci_ioda2_ops = {
 };
 #endif
 
-static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
-				       struct pnv_ioda_pe *pe)
+void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
+				struct pnv_ioda_pe *pe)
 {
 	int64_t rc;
 
-	if (!pnv_pci_ioda_pe_dma_weight(pe))
-		return;
-
 	/* TVE #1 is selected by PCI address bit 59 */
 	pe->tce_bypass_base = 1ull << 59;
 
@@ -2615,6 +2111,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 	iommu_register_group(&pe->table_group, phb->hose->global_number,
 			     pe->pe_number);
 #endif
+	pe->dma_setup_done = true;
 }
 
 int64_t pnv_opal_pci_msi_eoi(struct irq_chip *chip, unsigned int hw_irq)
@@ -2763,118 +2260,6 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb)
 		count, phb->msi_base);
 }
 
-#ifdef CONFIG_PCI_IOV
-static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
-{
-	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	const resource_size_t gate = phb->ioda.m64_segsize >> 2;
-	struct resource *res;
-	int i;
-	resource_size_t size, total_vf_bar_sz;
-	struct pci_dn *pdn;
-	int mul, total_vfs;
-
-	pdn = pci_get_pdn(pdev);
-	pdn->vfs_expanded = 0;
-	pdn->m64_single_mode = false;
-
-	total_vfs = pci_sriov_get_totalvfs(pdev);
-	mul = phb->ioda.total_pe_num;
-	total_vf_bar_sz = 0;
-
-	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
-		res = &pdev->resource[i + PCI_IOV_RESOURCES];
-		if (!res->flags || res->parent)
-			continue;
-		if (!pnv_pci_is_m64_flags(res->flags)) {
-			dev_warn(&pdev->dev, "Don't support SR-IOV with"
-					" non M64 VF BAR%d: %pR. \n",
-				 i, res);
-			goto truncate_iov;
-		}
-
-		total_vf_bar_sz += pci_iov_resource_size(pdev,
-				i + PCI_IOV_RESOURCES);
-
-		/*
-		 * If bigger than quarter of M64 segment size, just round up
-		 * power of two.
-		 *
-		 * Generally, one M64 BAR maps one IOV BAR. To avoid conflict
-		 * with other devices, IOV BAR size is expanded to be
-		 * (total_pe * VF_BAR_size).  When VF_BAR_size is half of M64
-		 * segment size , the expanded size would equal to half of the
-		 * whole M64 space size, which will exhaust the M64 Space and
-		 * limit the system flexibility.  This is a design decision to
-		 * set the boundary to quarter of the M64 segment size.
-		 */
-		if (total_vf_bar_sz > gate) {
-			mul = roundup_pow_of_two(total_vfs);
-			dev_info(&pdev->dev,
-				"VF BAR Total IOV size %llx > %llx, roundup to %d VFs\n",
-				total_vf_bar_sz, gate, mul);
-			pdn->m64_single_mode = true;
-			break;
-		}
-	}
-
-	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
-		res = &pdev->resource[i + PCI_IOV_RESOURCES];
-		if (!res->flags || res->parent)
-			continue;
-
-		size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES);
-		/*
-		 * On PHB3, the minimum size alignment of M64 BAR in single
-		 * mode is 32MB.
-		 */
-		if (pdn->m64_single_mode && (size < SZ_32M))
-			goto truncate_iov;
-		dev_dbg(&pdev->dev, " Fixing VF BAR%d: %pR to\n", i, res);
-		res->end = res->start + size * mul - 1;
-		dev_dbg(&pdev->dev, "                       %pR\n", res);
-		dev_info(&pdev->dev, "VF BAR%d: %pR (expanded to %d VFs for PE alignment)",
-			 i, res, mul);
-	}
-	pdn->vfs_expanded = mul;
-
-	return;
-
-truncate_iov:
-	/* To save MMIO space, IOV BAR is truncated. */
-	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
-		res = &pdev->resource[i + PCI_IOV_RESOURCES];
-		res->flags = 0;
-		res->end = res->start - 1;
-	}
-}
-
-static void pnv_pci_ioda_fixup_iov(struct pci_dev *pdev)
-{
-	if (WARN_ON(pci_dev_is_added(pdev)))
-		return;
-
-	if (pdev->is_virtfn) {
-		struct pnv_ioda_pe *pe = pnv_ioda_get_pe(pdev);
-
-		/*
-		 * VF PEs are single-device PEs so their pdev pointer needs to
-		 * be set. The pdev doesn't exist when the PE is allocated (in
-		 * (pcibios_sriov_enable()) so we fix it up here.
-		 */
-		pe->pdev = pdev;
-		WARN_ON(!(pe->flags & PNV_IODA_PE_VF));
-	} else if (pdev->is_physfn) {
-		/*
-		 * For PFs adjust their allocated IOV resources to match what
-		 * the PHB can support using it's M64 BAR table.
-		 */
-		pnv_pci_ioda_fixup_iov_resources(pdev);
-	}
-}
-#endif /* CONFIG_PCI_IOV */
-
 static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe,
 				  struct resource *res)
 {
@@ -3101,10 +2486,9 @@ static void pnv_pci_ioda_fixup(void)
 static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
 						unsigned long type)
 {
-	struct pci_dev *bridge;
-	struct pci_controller *hose = pci_bus_to_host(bus);
-	struct pnv_phb *phb = hose->private_data;
+	struct pnv_phb *phb = pci_bus_to_pnvhb(bus);
 	int num_pci_bridges = 0;
+	struct pci_dev *bridge;
 
 	bridge = bus->self;
 	while (bridge) {
@@ -3190,8 +2574,6 @@ static void pnv_pci_fixup_bridge_resources(struct pci_bus *bus,
 
 static void pnv_pci_configure_bus(struct pci_bus *bus)
 {
-	struct pci_controller *hose = pci_bus_to_host(bus);
-	struct pnv_phb *phb = hose->private_data;
 	struct pci_dev *bridge = bus->self;
 	struct pnv_ioda_pe *pe;
 	bool all = (bridge && pci_pcie_type(bridge) == PCI_EXP_TYPE_PCI_BRIDGE);
@@ -3215,17 +2597,6 @@ static void pnv_pci_configure_bus(struct pci_bus *bus)
 		return;
 
 	pnv_ioda_setup_pe_seg(pe);
-	switch (phb->type) {
-	case PNV_PHB_IODA1:
-		pnv_pci_ioda1_setup_dma_pe(phb, pe);
-		break;
-	case PNV_PHB_IODA2:
-		pnv_pci_ioda2_setup_dma_pe(phb, pe);
-		break;
-	default:
-		pr_warn("%s: No DMA for PHB#%x (type %d)\n",
-			__func__, phb->hose->global_number, phb->type);
-	}
 }
 
 static resource_size_t pnv_pci_default_alignment(void)
@@ -3233,49 +2604,12 @@ static resource_size_t pnv_pci_default_alignment(void)
 	return PAGE_SIZE;
 }
 
-#ifdef CONFIG_PCI_IOV
-static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev,
-						      int resno)
-{
-	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	struct pci_dn *pdn = pci_get_pdn(pdev);
-	resource_size_t align;
-
-	/*
-	 * On PowerNV platform, IOV BAR is mapped by M64 BAR to enable the
-	 * SR-IOV. While from hardware perspective, the range mapped by M64
-	 * BAR should be size aligned.
-	 *
-	 * When IOV BAR is mapped with M64 BAR in Single PE mode, the extra
-	 * powernv-specific hardware restriction is gone. But if just use the
-	 * VF BAR size as the alignment, PF BAR / VF BAR may be allocated with
-	 * in one segment of M64 #15, which introduces the PE conflict between
-	 * PF and VF. Based on this, the minimum alignment of an IOV BAR is
-	 * m64_segsize.
-	 *
-	 * This function returns the total IOV BAR size if M64 BAR is in
-	 * Shared PE mode or just VF BAR size if not.
-	 * If the M64 BAR is in Single PE mode, return the VF BAR size or
-	 * M64 segment size if IOV BAR size is less.
-	 */
-	align = pci_iov_resource_size(pdev, resno);
-	if (!pdn->vfs_expanded)
-		return align;
-	if (pdn->m64_single_mode)
-		return max(align, (resource_size_t)phb->ioda.m64_segsize);
-
-	return pdn->vfs_expanded * align;
-}
-#endif /* CONFIG_PCI_IOV */
-
 /* Prevent enabling devices for which we couldn't properly
  * assign a PE
  */
 static bool pnv_pci_enable_device_hook(struct pci_dev *dev)
 {
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
+	struct pnv_phb *phb = pci_bus_to_pnvhb(dev->bus);
 	struct pci_dn *pdn;
 
 	/* The function is probably called while the PEs have
@@ -3346,11 +2680,10 @@ static long pnv_pci_ioda1_unset_window(struct iommu_table_group *table_group,
 
 static void pnv_pci_ioda1_release_pe_dma(struct pnv_ioda_pe *pe)
 {
-	unsigned int weight = pnv_pci_ioda_pe_dma_weight(pe);
 	struct iommu_table *tbl = pe->table_group.tables[0];
 	int64_t rc;
 
-	if (!weight)
+	if (!pe->dma_setup_done)
 		return;
 
 	rc = pnv_pci_ioda1_unset_window(&pe->table_group, 0);
@@ -3367,22 +2700,17 @@ static void pnv_pci_ioda1_release_pe_dma(struct pnv_ioda_pe *pe)
 	iommu_tce_table_put(tbl);
 }
 
-static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
+void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
 {
 	struct iommu_table *tbl = pe->table_group.tables[0];
-	unsigned int weight = pnv_pci_ioda_pe_dma_weight(pe);
-#ifdef CONFIG_IOMMU_API
 	int64_t rc;
-#endif
 
-	if (!weight)
+	if (pe->dma_setup_done)
 		return;
 
-#ifdef CONFIG_IOMMU_API
 	rc = pnv_pci_ioda2_unset_window(&pe->table_group, 0);
 	if (rc)
 		pe_warn(pe, "OPAL error %lld release DMA window\n", rc);
-#endif
 
 	pnv_pci_ioda2_set_bypass(pe, false);
 	if (pe->table_group.group) {
@@ -3405,14 +2733,8 @@ static void pnv_ioda_free_pe_seg(struct pnv_ioda_pe *pe,
 		if (map[idx] != pe->pe_number)
 			continue;
 
-		if (win == OPAL_M64_WINDOW_TYPE)
-			rc = opal_pci_map_pe_mmio_window(phb->opal_id,
-					phb->ioda.reserved_pe_idx, win,
-					idx / PNV_IODA1_M64_SEGS,
-					idx % PNV_IODA1_M64_SEGS);
-		else
-			rc = opal_pci_map_pe_mmio_window(phb->opal_id,
-					phb->ioda.reserved_pe_idx, win, 0, idx);
+		rc = opal_pci_map_pe_mmio_window(phb->opal_id,
+				phb->ioda.reserved_pe_idx, win, 0, idx);
 
 		if (rc != OPAL_SUCCESS)
 			pe_warn(pe, "Error %lld unmapping (%d) segment#%d\n",
@@ -3431,8 +2753,7 @@ static void pnv_ioda_release_pe_seg(struct pnv_ioda_pe *pe)
 				     phb->ioda.io_segmap);
 		pnv_ioda_free_pe_seg(pe, OPAL_M32_WINDOW_TYPE,
 				     phb->ioda.m32_segmap);
-		pnv_ioda_free_pe_seg(pe, OPAL_M64_WINDOW_TYPE,
-				     phb->ioda.m64_segmap);
+		/* M64 is pre-configured by pnv_ioda1_init_m64() */
 	} else if (phb->type == PNV_PHB_IODA2) {
 		pnv_ioda_free_pe_seg(pe, OPAL_M32_WINDOW_TYPE,
 				     phb->ioda.m32_segmap);
@@ -3488,17 +2809,27 @@ static void pnv_ioda_release_pe(struct pnv_ioda_pe *pe)
 
 static void pnv_pci_release_device(struct pci_dev *pdev)
 {
-	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-	struct pnv_phb *phb = hose->private_data;
+	struct pnv_phb *phb = pci_bus_to_pnvhb(pdev->bus);
 	struct pci_dn *pdn = pci_get_pdn(pdev);
 	struct pnv_ioda_pe *pe;
 
+	/* The VF PE state is torn down when sriov_disable() is called */
 	if (pdev->is_virtfn)
 		return;
 
 	if (!pdn || pdn->pe_number == IODA_INVALID_PE)
 		return;
 
+#ifdef CONFIG_PCI_IOV
+	/*
+	 * FIXME: Try move this to sriov_disable(). It's here since we allocate
+	 * the iov state at probe time since we need to fiddle with the IOV
+	 * resources.
+	 */
+	if (pdev->is_physfn)
+		kfree(pdev->dev.archdata.iov_data);
+#endif
+
 	/*
 	 * PCI hotplug can happen as part of EEH error recovery. The @pdn
 	 * isn't removed and added afterwards in this scenario. We should
@@ -3534,8 +2865,7 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
 
 static void pnv_pci_ioda_dma_bus_setup(struct pci_bus *bus)
 {
-	struct pci_controller *hose = bus->sysdata;
-	struct pnv_phb *phb = hose->private_data;
+	struct pnv_phb *phb = pci_bus_to_pnvhb(bus);
 	struct pnv_ioda_pe *pe;
 
 	list_for_each_entry(pe, &phb->ioda.pe_list, list) {
@@ -3760,7 +3090,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 		pnv_ioda_reserve_pe(phb, phb->ioda.root_pe_idx);
 	} else {
 		/* otherwise just allocate one */
-		root_pe = pnv_ioda_alloc_pe(phb);
+		root_pe = pnv_ioda_alloc_pe(phb, 1);
 		phb->ioda.root_pe_idx = root_pe->pe_number;
 	}
 
@@ -3873,8 +3203,7 @@ void __init pnv_pci_init_npu2_opencapi_phb(struct device_node *np)
 
 static void pnv_npu2_opencapi_cfg_size_fixup(struct pci_dev *dev)
 {
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
+	struct pnv_phb *phb = pci_bus_to_pnvhb(dev->bus);
 
 	if (!machine_is(powernv))
 		return;