Merge branch 'next-sriov' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc into next

Merge Richard's work to support SR-IOV on PowerNV. All generic PCI
patches acked by Bjorn.

Some minor conflicts with Daniel's pci_controller_ops work.

Conflicts:
	arch/powerpc/include/asm/machdep.h
	arch/powerpc/platforms/powernv/pci-ioda.c

3 files changed, 768 insertions, 31 deletions

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 5e917753c672..920c252d1f49 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -44,6 +44,9 @@
 #include "powernv.h"
 #include "pci.h"
 
+/* 256M DMA window, 4K TCE pages, 8 bytes TCE */
+#define TCE32_TABLE_SIZE	((0x10000000 / 0x1000) * 8)
+
 static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 			    const char *fmt, ...)
 {
@@ -56,11 +59,18 @@ static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	if (pe->pdev)
+	if (pe->flags & PNV_IODA_PE_DEV)
 		strlcpy(pfix, dev_name(&pe->pdev->dev), sizeof(pfix));
-	else
+	else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
 		sprintf(pfix, "%04x:%02x     ",
 			pci_domain_nr(pe->pbus), pe->pbus->number);
+#ifdef CONFIG_PCI_IOV
+	else if (pe->flags & PNV_IODA_PE_VF)
+		sprintf(pfix, "%04x:%02x:%2x.%d",
+			pci_domain_nr(pe->parent_dev->bus),
+			(pe->rid & 0xff00) >> 8,
+			PCI_SLOT(pe->rid), PCI_FUNC(pe->rid));
+#endif /* CONFIG_PCI_IOV*/
 
 	printk("%spci %s: [PE# %.3d] %pV",
 	       level, pfix, pe->pe_number, &vaf);
@@ -591,7 +601,7 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb,
 			      bool is_add)
 {
 	struct pnv_ioda_pe *slave;
-	struct pci_dev *pdev;
+	struct pci_dev *pdev = NULL;
 	int ret;
 
 	/*
@@ -630,8 +640,12 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb,
 
 	if (pe->flags & (PNV_IODA_PE_BUS_ALL | PNV_IODA_PE_BUS))
 		pdev = pe->pbus->self;
-	else
+	else if (pe->flags & PNV_IODA_PE_DEV)
 		pdev = pe->pdev->bus->self;
+#ifdef CONFIG_PCI_IOV
+	else if (pe->flags & PNV_IODA_PE_VF)
+		pdev = pe->parent_dev->bus->self;
+#endif /* CONFIG_PCI_IOV */
 	while (pdev) {
 		struct pci_dn *pdn = pci_get_pdn(pdev);
 		struct pnv_ioda_pe *parent;
@@ -649,6 +663,87 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb,
 	return 0;
 }
 
+#ifdef CONFIG_PCI_IOV
+static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
+{
+	struct pci_dev *parent;
+	uint8_t bcomp, dcomp, fcomp;
+	int64_t rc;
+	long rid_end, rid;
+
+	/* Currently, we just deconfigure VF PE. Bus PE will always there.*/
+	if (pe->pbus) {
+		int count;
+
+		dcomp = OPAL_IGNORE_RID_DEVICE_NUMBER;
+		fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER;
+		parent = pe->pbus->self;
+		if (pe->flags & PNV_IODA_PE_BUS_ALL)
+			count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1;
+		else
+			count = 1;
+
+		switch(count) {
+		case  1: bcomp = OpalPciBusAll;         break;
+		case  2: bcomp = OpalPciBus7Bits;       break;
+		case  4: bcomp = OpalPciBus6Bits;       break;
+		case  8: bcomp = OpalPciBus5Bits;       break;
+		case 16: bcomp = OpalPciBus4Bits;       break;
+		case 32: bcomp = OpalPciBus3Bits;       break;
+		default:
+			dev_err(&pe->pbus->dev, "Number of subordinate buses %d unsupported\n",
+			        count);
+			/* Do an exact match only */
+			bcomp = OpalPciBusAll;
+		}
+		rid_end = pe->rid + (count << 8);
+	} else {
+		if (pe->flags & PNV_IODA_PE_VF)
+			parent = pe->parent_dev;
+		else
+			parent = pe->pdev->bus->self;
+		bcomp = OpalPciBusAll;
+		dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER;
+		fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER;
+		rid_end = pe->rid + 1;
+	}
+
+	/* Clear the reverse map */
+	for (rid = pe->rid; rid < rid_end; rid++)
+		phb->ioda.pe_rmap[rid] = 0;
+
+	/* Release from all parents PELT-V */
+	while (parent) {
+		struct pci_dn *pdn = pci_get_pdn(parent);
+		if (pdn && pdn->pe_number != IODA_INVALID_PE) {
+			rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number,
+						pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN);
+			/* XXX What to do in case of error ? */
+		}
+		parent = parent->bus->self;
+	}
+
+	opal_pci_eeh_freeze_set(phb->opal_id, pe->pe_number,
+				  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+
+	/* Disassociate PE in PELT */
+	rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
+				pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN);
+	if (rc)
+		pe_warn(pe, "OPAL error %ld remove self from PELTV\n", rc);
+	rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
+			     bcomp, dcomp, fcomp, OPAL_UNMAP_PE);
+	if (rc)
+		pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc);
+
+	pe->pbus = NULL;
+	pe->pdev = NULL;
+	pe->parent_dev = NULL;
+
+	return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
 static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 {
 	struct pci_dev *parent;
@@ -675,15 +770,19 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 		case 16: bcomp = OpalPciBus4Bits;	break;
 		case 32: bcomp = OpalPciBus3Bits;	break;
 		default:
-			pr_err("%s: Number of subordinate busses %d"
-			       " unsupported\n",
-			       pci_name(pe->pbus->self), count);
+			dev_err(&pe->pbus->dev, "Number of subordinate buses %d unsupported\n",
+			        count);
 			/* Do an exact match only */
 			bcomp = OpalPciBusAll;
 		}
 		rid_end = pe->rid + (count << 8);
 	} else {
-		parent = pe->pdev->bus->self;
+#ifdef CONFIG_PCI_IOV
+		if (pe->flags & PNV_IODA_PE_VF)
+			parent = pe->parent_dev;
+		else
+#endif /* CONFIG_PCI_IOV */
+			parent = pe->pdev->bus->self;
 		bcomp = OpalPciBusAll;
 		dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER;
 		fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER;
@@ -774,6 +873,78 @@ static unsigned int pnv_ioda_dma_weight(struct pci_dev *dev)
 	return 10;
 }
 
+#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;
+
+		if (!pnv_pci_is_mem_pref_64(res->flags))
+			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;
+		}
+	}
+
+	/*
+	 * After doing so, there would be a "hole" in the /proc/iomem when
+	 * offset is a positive value. It looks like the device return some
+	 * mmio back to the system, which actually no one could use it.
+	 */
+	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+		res = &dev->resource[i + PCI_IOV_RESOURCES];
+		if (!res->flags || !res->parent)
+			continue;
+
+		if (!pnv_pci_is_mem_pref_64(res->flags))
+			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 (enabling %d VFs shifted by %d)\n",
+			 i, &res2, res, num_vfs, offset);
+		pci_update_resource(dev, i + PCI_IOV_RESOURCES);
+	}
+	return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
 #if 0
 static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 {
@@ -857,7 +1028,6 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
 				pci_name(dev));
 			continue;
 		}
-		pdn->pcidev = dev;
 		pdn->pe_number = pe->pe_number;
 		pe->dma_weight += pnv_ioda_dma_weight(dev);
 		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
@@ -916,6 +1086,10 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all)
 		return;
 	}
 
+	pe->tce32_table = kzalloc_node(sizeof(struct iommu_table),
+			GFP_KERNEL, hose->node);
+	pe->tce32_table->data = pe;
+
 	/* Associate it with all child devices */
 	pnv_ioda_setup_same_PE(bus, pe);
 
@@ -974,6 +1148,441 @@ static void pnv_pci_ioda_setup_PEs(void)
 	}
 }
 
+#ifdef CONFIG_PCI_IOV
+static int pnv_pci_vf_release_m64(struct pci_dev *pdev)
+{
+	struct pci_bus        *bus;
+	struct pci_controller *hose;
+	struct pnv_phb        *phb;
+	struct pci_dn         *pdn;
+	int                    i, j;
+
+	bus = pdev->bus;
+	hose = pci_bus_to_host(bus);
+	phb = hose->private_data;
+	pdn = pci_get_pdn(pdev);
+
+	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++)
+		for (j = 0; j < M64_PER_IOV; j++) {
+			if (pdn->m64_wins[i][j] == IODA_INVALID_M64)
+				continue;
+			opal_pci_phb_mmio_enable(phb->opal_id,
+				OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 0);
+			clear_bit(pdn->m64_wins[i][j], &phb->ioda.m64_bar_alloc);
+			pdn->m64_wins[i][j] = IODA_INVALID_M64;
+		}
+
+	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                    vf_groups;
+	int                    vf_per_group;
+
+	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);
+
+	/* Initialize the m64_wins to IODA_INVALID_M64 */
+	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++)
+		for (j = 0; j < M64_PER_IOV; j++)
+			pdn->m64_wins[i][j] = IODA_INVALID_M64;
+
+	if (pdn->m64_per_iov == M64_PER_IOV) {
+		vf_groups = (num_vfs <= M64_PER_IOV) ? num_vfs: M64_PER_IOV;
+		vf_per_group = (num_vfs <= M64_PER_IOV)? 1:
+			roundup_pow_of_two(num_vfs) / pdn->m64_per_iov;
+	} else {
+		vf_groups = 1;
+		vf_per_group = 1;
+	}
+
+	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_mem_pref_64(res->flags))
+			continue;
+
+		for (j = 0; j < vf_groups; 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_wins[i][j] = win;
+
+			if (pdn->m64_per_iov == M64_PER_IOV) {
+				size = pci_iov_resource_size(pdev,
+							PCI_IOV_RESOURCES + i);
+				size = size * vf_per_group;
+				start = res->start + size * j;
+			} else {
+				size = resource_size(res);
+				start = res->start;
+			}
+
+			/* Map the M64 here */
+			if (pdn->m64_per_iov == M64_PER_IOV) {
+				pe_num = pdn->offset + j;
+				rc = opal_pci_map_pe_mmio_window(phb->opal_id,
+						pe_num, OPAL_M64_WINDOW_TYPE,
+						pdn->m64_wins[i][j], 0);
+			}
+
+			rc = opal_pci_set_phb_mem_window(phb->opal_id,
+						 OPAL_M64_WINDOW_TYPE,
+						 pdn->m64_wins[i][j],
+						 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_per_iov == M64_PER_IOV)
+				rc = opal_pci_phb_mmio_enable(phb->opal_id,
+				     OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 2);
+			else
+				rc = opal_pci_phb_mmio_enable(phb->opal_id,
+				     OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 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);
+	return -EBUSY;
+}
+
+static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe *pe)
+{
+	struct pci_bus        *bus;
+	struct pci_controller *hose;
+	struct pnv_phb        *phb;
+	struct iommu_table    *tbl;
+	unsigned long         addr;
+	int64_t               rc;
+
+	bus = dev->bus;
+	hose = pci_bus_to_host(bus);
+	phb = hose->private_data;
+	tbl = pe->tce32_table;
+	addr = tbl->it_base;
+
+	opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number,
+				   pe->pe_number << 1, 1, __pa(addr),
+				   0, 0x1000);
+
+	rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
+				        pe->pe_number,
+				        (pe->pe_number << 1) + 1,
+				        pe->tce_bypass_base,
+				        0);
+	if (rc)
+		pe_warn(pe, "OPAL error %ld release DMA window\n", rc);
+
+	iommu_free_table(tbl, of_node_full_name(dev->dev.of_node));
+	free_pages(addr, get_order(TCE32_TABLE_SIZE));
+	pe->tce32_table = NULL;
+}
+
+static void pnv_ioda_release_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, *pe_n;
+	struct pci_dn         *pdn;
+	u16                    vf_index;
+	int64_t                rc;
+
+	bus = pdev->bus;
+	hose = pci_bus_to_host(bus);
+	phb = hose->private_data;
+	pdn = pci_get_pdn(pdev);
+
+	if (!pdev->is_physfn)
+		return;
+
+	if (pdn->m64_per_iov == M64_PER_IOV && num_vfs > M64_PER_IOV) {
+		int   vf_group;
+		int   vf_per_group;
+		int   vf_index1;
+
+		vf_per_group = roundup_pow_of_two(num_vfs) / pdn->m64_per_iov;
+
+		for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++)
+			for (vf_index = vf_group * vf_per_group;
+				vf_index < (vf_group + 1) * vf_per_group &&
+				vf_index < num_vfs;
+				vf_index++)
+				for (vf_index1 = vf_group * vf_per_group;
+					vf_index1 < (vf_group + 1) * vf_per_group &&
+					vf_index1 < num_vfs;
+					vf_index1++){
+
+					rc = opal_pci_set_peltv(phb->opal_id,
+						pdn->offset + vf_index,
+						pdn->offset + vf_index1,
+						OPAL_REMOVE_PE_FROM_DOMAIN);
+
+					if (rc)
+					    dev_warn(&pdev->dev, "%s: Failed to unlink same group PE#%d(%lld)\n",
+						__func__,
+						pdn->offset + vf_index1, rc);
+				}
+	}
+
+	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(phb, pe->pe_number);
+	}
+}
+
+void pnv_pci_sriov_disable(struct pci_dev *pdev)
+{
+	struct pci_bus        *bus;
+	struct pci_controller *hose;
+	struct pnv_phb        *phb;
+	struct pci_dn         *pdn;
+	struct pci_sriov      *iov;
+	u16 num_vfs;
+
+	bus = pdev->bus;
+	hose = pci_bus_to_host(bus);
+	phb = hose->private_data;
+	pdn = pci_get_pdn(pdev);
+	iov = pdev->sriov;
+	num_vfs = pdn->num_vfs;
+
+	/* Release VF PEs */
+	pnv_ioda_release_vf_PE(pdev, num_vfs);
+
+	if (phb->type == PNV_PHB_IODA2) {
+		if (pdn->m64_per_iov == 1)
+			pnv_pci_vf_resource_shift(pdev, -pdn->offset);
+
+		/* Release M64 windows */
+		pnv_pci_vf_release_m64(pdev);
+
+		/* Release PE numbers */
+		bitmap_clear(phb->ioda.pe_alloc, pdn->offset, num_vfs);
+		pdn->offset = 0;
+	}
+}
+
+static void pnv_pci_ioda2_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;
+	int64_t                rc;
+
+	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++) {
+		pe_num = pdn->offset + 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->tce32_seg = -1;
+		pe->mve_number = -1;
+		pe->rid = (pci_iov_virtfn_bus(pdev, vf_index) << 8) |
+			   pci_iov_virtfn_devfn(pdev, vf_index);
+
+		pe_info(pe, "VF %04d:%02d:%02d.%d associated with PE#%d\n",
+			hose->global_number, pdev->bus->number,
+			PCI_SLOT(pci_iov_virtfn_devfn(pdev, vf_index)),
+			PCI_FUNC(pci_iov_virtfn_devfn(pdev, vf_index)), pe_num);
+
+		if (pnv_ioda_configure_pe(phb, pe)) {
+			/* XXX What do we do here ? */
+			if (pe_num)
+				pnv_ioda_free_pe(phb, pe_num);
+			pe->pdev = NULL;
+			continue;
+		}
+
+		pe->tce32_table = kzalloc_node(sizeof(struct iommu_table),
+				GFP_KERNEL, hose->node);
+		pe->tce32_table->data = pe;
+
+		/* 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);
+
+		pnv_pci_ioda2_setup_dma_pe(phb, pe);
+	}
+
+	if (pdn->m64_per_iov == M64_PER_IOV && num_vfs > M64_PER_IOV) {
+		int   vf_group;
+		int   vf_per_group;
+		int   vf_index1;
+
+		vf_per_group = roundup_pow_of_two(num_vfs) / pdn->m64_per_iov;
+
+		for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++) {
+			for (vf_index = vf_group * vf_per_group;
+			     vf_index < (vf_group + 1) * vf_per_group &&
+			     vf_index < num_vfs;
+			     vf_index++) {
+				for (vf_index1 = vf_group * vf_per_group;
+				     vf_index1 < (vf_group + 1) * vf_per_group &&
+				     vf_index1 < num_vfs;
+				     vf_index1++) {
+
+					rc = opal_pci_set_peltv(phb->opal_id,
+						pdn->offset + vf_index,
+						pdn->offset + vf_index1,
+						OPAL_ADD_PE_TO_DOMAIN);
+
+					if (rc)
+					    dev_warn(&pdev->dev, "%s: Failed to link same group PE#%d(%lld)\n",
+						__func__,
+						pdn->offset + vf_index1, rc);
+				}
+			}
+		}
+	}
+}
+
+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 pci_dn         *pdn;
+	int                    ret;
+
+	bus = pdev->bus;
+	hose = pci_bus_to_host(bus);
+	phb = hose->private_data;
+	pdn = pci_get_pdn(pdev);
+
+	if (phb->type == PNV_PHB_IODA2) {
+		/* Calculate available PE for required VFs */
+		mutex_lock(&phb->ioda.pe_alloc_mutex);
+		pdn->offset = bitmap_find_next_zero_area(
+			phb->ioda.pe_alloc, phb->ioda.total_pe,
+			0, num_vfs, 0);
+		if (pdn->offset >= phb->ioda.total_pe) {
+			mutex_unlock(&phb->ioda.pe_alloc_mutex);
+			dev_info(&pdev->dev, "Failed to enable VF%d\n", num_vfs);
+			pdn->offset = 0;
+			return -EBUSY;
+		}
+		bitmap_set(phb->ioda.pe_alloc, pdn->offset, num_vfs);
+		pdn->num_vfs = num_vfs;
+		mutex_unlock(&phb->ioda.pe_alloc_mutex);
+
+		/* 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_per_iov == 1) {
+			ret = pnv_pci_vf_resource_shift(pdev, pdn->offset);
+			if (ret)
+				goto m64_failed;
+		}
+	}
+
+	/* Setup VF PEs */
+	pnv_ioda_setup_vf_PE(pdev, num_vfs);
+
+	return 0;
+
+m64_failed:
+	bitmap_clear(phb->ioda.pe_alloc, pdn->offset, num_vfs);
+	pdn->offset = 0;
+
+	return ret;
+}
+
+int pcibios_sriov_disable(struct pci_dev *pdev)
+{
+	pnv_pci_sriov_disable(pdev);
+
+	/* Release PCI data */
+	remove_dev_pci_data(pdev);
+	return 0;
+}
+
+int pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
+{
+	/* Allocate PCI data */
+	add_dev_pci_data(pdev);
+
+	pnv_pci_sriov_enable(pdev, num_vfs);
+	return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
 static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev)
 {
 	struct pci_dn *pdn = pci_get_pdn(pdev);
@@ -989,7 +1598,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
 	WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
-	set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table);
+	set_iommu_table_base_and_group(&pdev->dev, pe->tce32_table);
 }
 
 static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
@@ -1016,7 +1625,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
 	} else {
 		dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
 		set_dma_ops(&pdev->dev, &dma_iommu_ops);
-		set_iommu_table_base(&pdev->dev, &pe->tce32_table);
+		set_iommu_table_base(&pdev->dev, pe->tce32_table);
 	}
 	*pdev->dev.dma_mask = dma_mask;
 	return 0;
@@ -1053,9 +1662,9 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		if (add_to_iommu_group)
 			set_iommu_table_base_and_group(&dev->dev,
-						       &pe->tce32_table);
+						       pe->tce32_table);
 		else
-			set_iommu_table_base(&dev->dev, &pe->tce32_table);
+			set_iommu_table_base(&dev->dev, pe->tce32_table);
 
 		if (dev->subordinate)
 			pnv_ioda_setup_bus_dma(pe, dev->subordinate,
@@ -1145,8 +1754,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
 void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
 				 __be64 *startp, __be64 *endp, bool rm)
 {
-	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
-					      tce32_table);
+	struct pnv_ioda_pe *pe = tbl->data;
 	struct pnv_phb *phb = pe->phb;
 
 	if (phb->type == PNV_PHB_IODA1)
@@ -1167,9 +1775,6 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 	int64_t rc;
 	void *addr;
 
-	/* 256M DMA window, 4K TCE pages, 8 bytes TCE */
-#define TCE32_TABLE_SIZE	((0x10000000 / 0x1000) * 8)
-
 	/* XXX FIXME: Handle 64-bit only DMA devices */
 	/* XXX FIXME: Provide 64-bit DMA facilities & non-4K TCE tables etc.. */
 	/* XXX FIXME: Allocate multi-level tables on PHB3 */
@@ -1212,7 +1817,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 	}
 
 	/* Setup linux iommu table */
-	tbl = &pe->tce32_table;
+	tbl = pe->tce32_table;
 	pnv_pci_setup_iommu_table(tbl, addr, TCE32_TABLE_SIZE * segs,
 				  base << 28, IOMMU_PAGE_SHIFT_4K);
 
@@ -1232,12 +1837,19 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 				 TCE_PCI_SWINV_PAIR);
 	}
 	iommu_init_table(tbl, phb->hose->node);
-	iommu_register_group(tbl, phb->hose->global_number, pe->pe_number);
 
-	if (pe->pdev)
+	if (pe->flags & PNV_IODA_PE_DEV) {
+		iommu_register_group(tbl, phb->hose->global_number,
+				     pe->pe_number);
 		set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
-	else
+	} else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) {
+		iommu_register_group(tbl, phb->hose->global_number,
+				     pe->pe_number);
 		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
+	} else if (pe->flags & PNV_IODA_PE_VF) {
+		iommu_register_group(tbl, phb->hose->global_number,
+				     pe->pe_number);
+	}
 
 	return;
  fail:
@@ -1250,8 +1862,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 
 static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
 {
-	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
-					      tce32_table);
+	struct pnv_ioda_pe *pe = tbl->data;
 	uint16_t window_id = (pe->pe_number << 1 ) + 1;
 	int64_t rc;
 
@@ -1296,10 +1907,10 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb,
 	pe->tce_bypass_base = 1ull << 59;
 
 	/* Install set_bypass callback for VFIO */
-	pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass;
+	pe->tce32_table->set_bypass = pnv_pci_ioda2_set_bypass;
 
 	/* Enable bypass by default */
-	pnv_pci_ioda2_set_bypass(&pe->tce32_table, true);
+	pnv_pci_ioda2_set_bypass(pe->tce32_table, true);
 }
 
 static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
@@ -1347,7 +1958,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 	}
 
 	/* Setup linux iommu table */
-	tbl = &pe->tce32_table;
+	tbl = pe->tce32_table;
 	pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0,
 			IOMMU_PAGE_SHIFT_4K);
 
@@ -1365,12 +1976,19 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 		tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE);
 	}
 	iommu_init_table(tbl, phb->hose->node);
-	iommu_register_group(tbl, phb->hose->global_number, pe->pe_number);
 
-	if (pe->pdev)
+	if (pe->flags & PNV_IODA_PE_DEV) {
+		iommu_register_group(tbl, phb->hose->global_number,
+				     pe->pe_number);
 		set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
-	else
+	} else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) {
+		iommu_register_group(tbl, phb->hose->global_number,
+				     pe->pe_number);
 		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
+	} else if (pe->flags & PNV_IODA_PE_VF) {
+		iommu_register_group(tbl, phb->hose->global_number,
+				     pe->pe_number);
+	}
 
 	/* Also create a bypass window */
 	if (!pnv_iommu_bypass_disabled)
@@ -1731,6 +2349,73 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb)
 static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { }
 #endif /* CONFIG_PCI_MSI */
 
+#ifdef CONFIG_PCI_IOV
+static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
+{
+	struct pci_controller *hose;
+	struct pnv_phb *phb;
+	struct resource *res;
+	int i;
+	resource_size_t size;
+	struct pci_dn *pdn;
+	int mul, total_vfs;
+
+	if (!pdev->is_physfn || pdev->is_added)
+		return;
+
+	hose = pci_bus_to_host(pdev->bus);
+	phb = hose->private_data;
+
+	pdn = pci_get_pdn(pdev);
+	pdn->vfs_expanded = 0;
+
+	total_vfs = pci_sriov_get_totalvfs(pdev);
+	pdn->m64_per_iov = 1;
+	mul = phb->ioda.total_pe;
+
+	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_mem_pref_64(res->flags)) {
+			dev_warn(&pdev->dev, " non M64 VF BAR%d: %pR\n",
+				 i, res);
+			continue;
+		}
+
+		size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES);
+
+		/* bigger than 64M */
+		if (size > (1 << 26)) {
+			dev_info(&pdev->dev, "PowerNV: VF BAR%d: %pR IOV size is bigger than 64M, roundup power2\n",
+				 i, res);
+			pdn->m64_per_iov = M64_PER_IOV;
+			mul = roundup_pow_of_two(total_vfs);
+			break;
+		}
+	}
+
+	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_mem_pref_64(res->flags)) {
+			dev_warn(&pdev->dev, "Skipping expanding VF BAR%d: %pR\n",
+				 i, res);
+			continue;
+		}
+
+		dev_dbg(&pdev->dev, " Fixing VF BAR%d: %pR to\n", i, res);
+		size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES);
+		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;
+}
+#endif /* CONFIG_PCI_IOV */
+
 /*
  * This function is supposed to be called on basis of PE from top
  * to bottom style. So the the I/O or MMIO segment assigned to
@@ -1908,6 +2593,25 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
 	return phb->ioda.io_segsize;
 }
 
+#ifdef CONFIG_PCI_IOV
+static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev,
+						      int resno)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+	resource_size_t align, iov_align;
+
+	iov_align = resource_size(&pdev->resource[resno]);
+	if (iov_align)
+		return iov_align;
+
+	align = pci_iov_resource_size(pdev, resno);
+	if (pdn->vfs_expanded)
+		return pdn->vfs_expanded * align;
+
+	return align;
+}
+#endif /* CONFIG_PCI_IOV */
+
 /* Prevent enabling devices for which we couldn't properly
  * assign a PE
  */
@@ -1993,6 +2697,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	phb->hub_id = hub_id;
 	phb->opal_id = phb_id;
 	phb->type = ioda_type;
+	mutex_init(&phb->ioda.pe_alloc_mutex);
 
 	/* Detect specific models for error handling */
 	if (of_device_is_compatible(np, "ibm,p7ioc-pciex"))
@@ -2052,6 +2757,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 
 	INIT_LIST_HEAD(&phb->ioda.pe_dma_list);
 	INIT_LIST_HEAD(&phb->ioda.pe_list);
+	mutex_init(&phb->ioda.pe_list_mutex);
 
 	/* Calculate how many 32-bit TCE segments we have */
 	phb->ioda.tce32_count = phb->ioda.m32_pci_base >> 28;
@@ -2106,6 +2812,12 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	pnv_pci_controller_ops.enable_device_hook = pnv_pci_enable_device_hook;
 	pnv_pci_controller_ops.window_alignment = pnv_pci_window_alignment;
 	pnv_pci_controller_ops.reset_secondary_bus = pnv_pci_reset_secondary_bus;
+
+#ifdef CONFIG_PCI_IOV
+	ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources;
+	ppc_md.pcibios_iov_resource_alignment = pnv_pci_iov_resource_alignment;
+#endif
+
 	pci_add_flags(PCI_REASSIGN_ALL_RSRC);
 
 	/* Reset IODA tables to a clean state */
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index fa96aa8aa1e2..bca2aeb6e4b6 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -666,6 +666,24 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
+#ifdef CONFIG_PCI_IOV
+	struct pnv_ioda_pe *pe;
+	struct pci_dn *pdn;
+
+	/* Fix the VF pdn PE number */
+	if (pdev->is_virtfn) {
+		pdn = pci_get_pdn(pdev);
+		WARN_ON(pdn->pe_number != IODA_INVALID_PE);
+		list_for_each_entry(pe, &phb->ioda.pe_list, list) {
+			if (pe->rid == ((pdev->bus->number << 8) |
+			    (pdev->devfn & 0xff))) {
+				pdn->pe_number = pe->pe_number;
+				pe->pdev = pdev;
+				break;
+			}
+		}
+	}
+#endif /* CONFIG_PCI_IOV */
 
 	if (phb && phb->dma_dev_setup)
 		phb->dma_dev_setup(phb, pdev);
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 1f0cb66133a1..070ee888fc95 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -23,6 +23,7 @@ enum pnv_phb_model {
 #define PNV_IODA_PE_BUS_ALL	(1 << 2)	/* PE has subordinate buses	*/
 #define PNV_IODA_PE_MASTER	(1 << 3)	/* Master PE in compound case	*/
 #define PNV_IODA_PE_SLAVE	(1 << 4)	/* Slave PE in compound case	*/
+#define PNV_IODA_PE_VF		(1 << 5)	/* PE for one VF 		*/
 
 /* Data associated with a PE, including IOMMU tracking etc.. */
 struct pnv_phb;
@@ -34,6 +35,9 @@ struct pnv_ioda_pe {
 	 * entire bus (& children). In the former case, pdev
 	 * is populated, in the later case, pbus is.
 	 */
+#ifdef CONFIG_PCI_IOV
+	struct pci_dev          *parent_dev;
+#endif
 	struct pci_dev		*pdev;
 	struct pci_bus		*pbus;
 
@@ -53,7 +57,7 @@ struct pnv_ioda_pe {
 	/* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */
 	int			tce32_seg;
 	int			tce32_segcount;
-	struct iommu_table	tce32_table;
+	struct iommu_table	*tce32_table;
 	phys_addr_t		tce_inval_reg_phys;
 
 	/* 64-bit TCE bypass region */
@@ -145,6 +149,8 @@ struct pnv_phb {
 
 			/* PE allocation bitmap */
 			unsigned long		*pe_alloc;
+			/* PE allocation mutex */
+			struct mutex		pe_alloc_mutex;
 
 			/* M32 & IO segment maps */
 			unsigned int		*m32_segmap;
@@ -159,6 +165,7 @@ struct pnv_phb {
 			 * on the sequence of creation
 			 */
 			struct list_head	pe_list;
+			struct mutex            pe_list_mutex;
 
 			/* Reverse map of PEs, will have to extend if
 			 * we are to support more than 256 PEs, indexed