[PATCH v9 00/26] powerpc/powernv: PCI hotplug preparation

@@ -17,33 +17,34 @@ struct device_node;
  * PCI controller operations
  */
 struct pci_controller_ops {
-	void		(*dma_dev_setup)(struct pci_dev *dev);
+	void		(*dma_dev_setup)(struct pci_dev *pdev);
 	void		(*dma_bus_setup)(struct pci_bus *bus);
 
-	int		(*probe_mode)(struct pci_bus *);
+	int		(*probe_mode)(struct pci_bus *bus);
 
 	/* Called when pci_enable_device() is called. Returns true to
 	 * allow assignment/enabling of the device. */
-	bool		(*enable_device_hook)(struct pci_dev *);
+	bool		(*enable_device_hook)(struct pci_dev *pdev);
 
-	void		(*disable_device)(struct pci_dev *);
+	void		(*disable_device)(struct pci_dev *pdev);
 
-	void		(*release_device)(struct pci_dev *);
+	void		(*release_device)(struct pci_dev *pdev);
 
 	/* Called during PCI resource reassignment */
-	resource_size_t (*window_alignment)(struct pci_bus *, unsigned long type);
-	void		(*reset_secondary_bus)(struct pci_dev *dev);
+	resource_size_t (*window_alignment)(struct pci_bus *bus,
+					    unsigned long type);
+	void		(*reset_secondary_bus)(struct pci_dev *pdev);
 
 #ifdef CONFIG_PCI_MSI
-	int		(*setup_msi_irqs)(struct pci_dev *dev,
+	int		(*setup_msi_irqs)(struct pci_dev *pdev,
 					  int nvec, int type);
-	void		(*teardown_msi_irqs)(struct pci_dev *dev);
+	void		(*teardown_msi_irqs)(struct pci_dev *pdev);
 #endif
 
-	int             (*dma_set_mask)(struct pci_dev *dev, u64 dma_mask);
-	u64		(*dma_get_required_mask)(struct pci_dev *dev);
+	int             (*dma_set_mask)(struct pci_dev *pdev, u64 dma_mask);
+	u64		(*dma_get_required_mask)(struct pci_dev *pdev);
 
-	void		(*shutdown)(struct pci_controller *);
+	void		(*shutdown)(struct pci_controller *hose);
 };
 
 /*

@@ -3195,12 +3195,6 @@ static bool pnv_pci_enable_device_hook(struct pci_dev *dev)
 	return true;
 }
 
-static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus,
-			       u32 devfn)
-{
-	return phb->ioda.pe_rmap[(bus->number << 8) | devfn];
-}
-
 static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
 {
 	struct pnv_phb *phb = hose->private_data;

@@ -3377,9 +3371,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	phb->freeze_pe = pnv_ioda_freeze_pe;
 	phb->unfreeze_pe = pnv_ioda_unfreeze_pe;
 
-	/* Setup RID -> PE mapping function */
-	phb->bdfn_to_pe = pnv_ioda_bdfn_to_pe;
-
 	/* Setup TCEs */
 	phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
 

@@ -110,7 +110,6 @@ struct pnv_phb {
 			 unsigned int is_64, struct msi_msg *msg);
 	void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
 	void (*fixup_phb)(struct pci_controller *hose);
-	u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
 	int (*init_m64)(struct pnv_phb *phb);
 	void (*reserve_m64_pe)(struct pci_bus *bus,
 			       unsigned long *pe_bitmap, bool all);

@@ -140,15 +140,14 @@ struct pnv_phb {
 		unsigned int		io_segsize;
 		unsigned int		io_pci_base;
 
-		/* PE allocation bitmap */
-		unsigned long		*pe_alloc;
-		/* PE allocation mutex */
+		/* PE allocation */
 		struct mutex		pe_alloc_mutex;
+		unsigned long		*pe_alloc;
+		struct pnv_ioda_pe	*pe_array;
 
 		/* M32 & IO segment maps */
 		unsigned int		*m32_segmap;
 		unsigned int		*io_segmap;
-		struct pnv_ioda_pe	*pe_array;
 
 		/* IRQ chip */
 		int			irq_chip_init;

@@ -2993,7 +2993,7 @@ static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe,
  */
 static void pnv_ioda_setup_pe_seg(struct pnv_ioda_pe *pe)
 {
-	struct resource *res;
+	struct pci_dev *pdev;
 	int i;
 
 	/*

@@ -3003,8 +3003,21 @@ static void pnv_ioda_setup_pe_seg(struct pnv_ioda_pe *pe)
 	 */
 	BUG_ON(!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)));
 
-	pci_bus_for_each_resource(pe->pbus, res, i)
-		pnv_ioda_setup_pe_res(pe, res);
+	list_for_each_entry(pdev, &pe->pbus->devices, bus_list) {
+		for (i = 0; i <= PCI_ROM_RESOURCE; i++)
+			pnv_ioda_setup_pe_res(pe, &pdev->resource[i]);
+
+		/*
+		 * If the PE contains all subordinate PCI buses, the
+		 * windows of the child bridges should be mapped to
+		 * the PE as well.
+		 */
+		if (!(pe->flags & PNV_IODA_PE_BUS_ALL) || !pci_is_bridge(pdev))
+			continue;
+		for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++)
+			pnv_ioda_setup_pe_res(pe,
+				&pdev->resource[PCI_BRIDGE_RESOURCES + i]);
+	}
 }
 
 static void pnv_pci_ioda_setup_seg(void)

@@ -209,14 +209,14 @@ struct pci_dn {
 #ifdef CONFIG_EEH
 	struct eeh_dev *edev;		/* eeh device */
 #endif
-#define IODA_INVALID_PE		(-1)
+#define IODA_INVALID_PE		0xFFFFFFFF
 #ifdef CONFIG_PPC_POWERNV
-	int	pe_number;
+	unsigned int pe_number;
 	int     vf_index;		/* VF index in the PF */
 #ifdef CONFIG_PCI_IOV
 	u16     vfs_expanded;		/* number of VFs IOV BAR expanded */
 	u16     num_vfs;		/* number of VFs enabled*/
-	int     *pe_num_map;		/* PE# for the first VF PE or array */
+	unsigned int *pe_num_map;	/* PE# for the first VF PE or array */
 	bool    m64_single_mode;	/* Use M64 BAR in Single Mode */
 #define IODA_INVALID_M64        (-1)
 	int     (*m64_map)[PCI_SRIOV_NUM_BARS];

@@ -138,7 +138,7 @@ static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no)
 	phb->ioda.pe_array[pe_no].pe_number = pe_no;
 }
 
-static int pnv_ioda_alloc_pe(struct pnv_phb *phb)
+static unsigned int pnv_ioda_alloc_pe(struct pnv_phb *phb)
 {
 	unsigned long pe;
 

@@ -261,7 +261,7 @@ static void pnv_ioda2_reserve_m64_pe(struct pci_bus *bus,
 	}
 }
 
-static int pnv_ioda2_pick_m64_pe(struct pci_bus *bus, bool all)
+static unsigned int pnv_ioda2_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;

@@ -919,7 +919,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 	struct pnv_phb *phb = hose->private_data;
 	struct pci_dn *pdn = pci_get_pdn(dev);
 	struct pnv_ioda_pe *pe;
-	int pe_num;
+	unsigned int pe_num;
 
 	if (!pdn) {
 		pr_err("%s: Device tree node not associated properly\n",

@@ -1010,7 +1010,7 @@ static void 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_ioda_pe *pe;
-	int pe_num = IODA_INVALID_PE;
+	unsigned int pe_num = IODA_INVALID_PE;
 
 	/* Check if PE is determined by M64 */
 	if (phb->pick_m64_pe)

@@ -370,7 +370,7 @@ static void pnv_pci_config_check_eeh(struct pci_dn *pdn)
 	struct pnv_phb *phb = pdn->phb->private_data;
 	u8	fstate;
 	__be16	pcierr;
-	int	pe_no;
+	unsigned int pe_no;
 	s64	rc;
 
 	/*

@@ -113,7 +113,7 @@ struct pnv_phb {
 	int (*init_m64)(struct pnv_phb *phb);
 	void (*reserve_m64_pe)(struct pci_bus *bus,
 			       unsigned long *pe_bitmap, bool all);
-	int (*pick_m64_pe)(struct pci_bus *bus, bool all);
+	unsigned int (*pick_m64_pe)(struct pci_bus *bus, bool all);
 	int (*get_pe_state)(struct pnv_phb *phb, int pe_no);
 	void (*freeze_pe)(struct pnv_phb *phb, int pe_no);
 	int (*unfreeze_pe)(struct pnv_phb *phb, int pe_no, int opt);

@@ -120,7 +120,8 @@ void pci_hp_add_devices(struct pci_bus *bus)
 	if (mode == PCI_PROBE_DEVTREE) {
 		/* use ofdt-based probe */
 		of_rescan_bus(dn, bus);
-	} else if (mode == PCI_PROBE_NORMAL) {
+	} else if (mode == PCI_PROBE_NORMAL &&
+		   dn->child && PCI_DN(dn->child)) {
 		/*
 		 * Use legacy probe. In the partial hotplug case, we
 		 * probably have grandchildren devices unplugged. So

@@ -237,6 +237,7 @@ extern struct pci_dn *add_dev_pci_data(struct pci_dev *pdev);
 extern void remove_dev_pci_data(struct pci_dev *pdev);
 extern struct pci_dn *pci_add_device_node_info(struct pci_controller *hose,
 					       struct device_node *dn);
+extern void pci_remove_device_node_info(struct device_node *dn);
 
 static inline int pci_device_from_OF_node(struct device_node *np,
 					  u8 *bus, u8 *devfn)

@@ -331,6 +331,29 @@ struct pci_dn *pci_add_device_node_info(struct pci_controller *hose,
 }
 EXPORT_SYMBOL_GPL(pci_add_device_node_info);
 
+void pci_remove_device_node_info(struct device_node *dn)
+{
+	struct pci_dn *pdn = dn ? PCI_DN(dn) : NULL;
+#ifdef CONFIG_EEH
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
+
+	if (edev)
+		edev->pdn = NULL;
+#endif
+
+	if (!pdn)
+		return;
+
+	WARN_ON(!list_empty(&pdn->child_list));
+	list_del(&pdn->list);
+	if (pdn->parent)
+		of_node_put(pdn->parent->node);
+
+	dn->data = NULL;
+	kfree(pdn);
+}
+EXPORT_SYMBOL_GPL(pci_remove_device_node_info);
+
 /*
  * Traverse a device tree stopping each PCI device in the tree.
  * This is done depth first.  As each node is processed, a "pre"

@@ -48,6 +48,9 @@
 #include "powernv.h"
 #include "pci.h"
 
+#define PNV_IODA1_M64_NUM	16	/* Number of M64 BARs	*/
+#define PNV_IODA1_M64_SEGS	8	/* Segments per M64 BAR	*/
+
 /* 256M DMA window, 4K TCE pages, 8 bytes TCE */
 #define TCE32_TABLE_SIZE	((0x10000000 / 0x1000) * 8)
 

@@ -246,6 +249,64 @@ static void pnv_ioda_reserve_dev_m64_pe(struct pci_dev *pdev,
 	}
 }
 
+static int pnv_ioda1_init_m64(struct pnv_phb *phb)
+{
+	struct resource *r;
+	int index;
+
+	/*
+	 * There are 16 M64 BARs, each of which has 8 segments. So
+	 * there are as many M64 segments as the maximum number of
+	 * PEs, which is 128.
+	 */
+	for (index = 0; index < PNV_IODA1_M64_NUM; index++) {
+		unsigned long base, segsz = phb->ioda.m64_segsize;
+		int64_t rc;
+
+		base = phb->ioda.m64_base +
+		       index * PNV_IODA1_M64_SEGS * segsz;
+		rc = opal_pci_set_phb_mem_window(phb->opal_id,
+				OPAL_M64_WINDOW_TYPE, index, base, 0,
+				PNV_IODA1_M64_SEGS * segsz);
+		if (rc != OPAL_SUCCESS) {
+			pr_warn("  Error %lld setting M64 PHB#%d-BAR#%d\n",
+				rc, phb->hose->global_number, index);
+			goto fail;
+		}
+
+		rc = opal_pci_phb_mmio_enable(phb->opal_id,
+				OPAL_M64_WINDOW_TYPE, index,
+				OPAL_ENABLE_M64_SPLIT);
+		if (rc != OPAL_SUCCESS) {
+			pr_warn("  Error %lld enabling M64 PHB#%d-BAR#%d\n",
+				rc, phb->hose->global_number, index);
+			goto fail;
+		}
+	}
+
+	/*
+	 * Exclude the segment used by the reserved PE, which
+	 * is expected to be 0 or last supported PE#.
+	 */
+	r = &phb->hose->mem_resources[1];
+	if (phb->ioda.reserved_pe_idx == 0)
+		r->start += phb->ioda.m64_segsize;
+	else if (phb->ioda.reserved_pe_idx == (phb->ioda.total_pe_num - 1))
+		r->end -= phb->ioda.m64_segsize;
+	else
+		pr_warn("  Cannot cut M64 segment for reserved PE#%d\n",
+			phb->ioda.reserved_pe_idx);
+
+	return 0;
+
+fail:
+	for ( ; index >= 0; index--)
+		opal_pci_phb_mmio_enable(phb->opal_id,
+			OPAL_M64_WINDOW_TYPE, index, OPAL_DISABLE_M64);
+
+	return -EIO;
+}
+
 static void pnv_ioda_reserve_m64_pe(struct pci_bus *bus,
 				    unsigned long *pe_bitmap,
 				    bool all)

@@ -315,6 +376,26 @@ static unsigned int 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#%d-PE#%d\n",
+					__func__, rc, phb->hose->global_number,
+					pe->pe_number);
+		}
 	}
 
 	kfree(pe_alloc);

@@ -329,8 +410,7 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)
 	const u32 *r;
 	u64 pci_addr;
 
-	/* FIXME: Support M64 for P7IOC */
-	if (phb->type != PNV_PHB_IODA2) {
+	if (phb->type != PNV_PHB_IODA1 && phb->type != PNV_PHB_IODA2) {
 		pr_info("  Not support M64 window\n");
 		return;
 	}

@@ -364,7 +444,10 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)
 
 	/* Use last M64 BAR to cover M64 window */
 	phb->ioda.m64_bar_idx = 15;
-	phb->init_m64 = pnv_ioda2_init_m64;
+	if (phb->type == PNV_PHB_IODA1)
+		phb->init_m64 = pnv_ioda1_init_m64;
+	else
+		phb->init_m64 = pnv_ioda2_init_m64;
 	phb->reserve_m64_pe = pnv_ioda_reserve_m64_pe;
 	phb->pick_m64_pe = pnv_ioda_pick_m64_pe;
 }

@@ -219,7 +219,7 @@ fail:
 	return -EIO;
 }
 
-static void pnv_ioda2_reserve_dev_m64_pe(struct pci_dev *pdev,
+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);

@@ -246,22 +246,22 @@ static void pnv_ioda2_reserve_dev_m64_pe(struct pci_dev *pdev,
 	}
 }
 
-static void pnv_ioda2_reserve_m64_pe(struct pci_bus *bus,
-				     unsigned long *pe_bitmap,
-				     bool all)
+static void pnv_ioda_reserve_m64_pe(struct pci_bus *bus,
+				    unsigned long *pe_bitmap,
+				    bool all)
 {
 	struct pci_dev *pdev;
 
 	list_for_each_entry(pdev, &bus->devices, bus_list) {
-		pnv_ioda2_reserve_dev_m64_pe(pdev, pe_bitmap);
+		pnv_ioda_reserve_dev_m64_pe(pdev, pe_bitmap);
 
 		if (all && pdev->subordinate)
-			pnv_ioda2_reserve_m64_pe(pdev->subordinate,
-						 pe_bitmap, all);
+			pnv_ioda_reserve_m64_pe(pdev->subordinate,
+						pe_bitmap, all);
 	}
 }
 
-static unsigned int pnv_ioda2_pick_m64_pe(struct pci_bus *bus, bool all)
+static unsigned int 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;

@@ -283,7 +283,7 @@ static unsigned int pnv_ioda2_pick_m64_pe(struct pci_bus *bus, bool all)
 	}
 
 	/* Figure out reserved PE numbers by the PE */
-	pnv_ioda2_reserve_m64_pe(bus, pe_alloc, all);
+	pnv_ioda_reserve_m64_pe(bus, pe_alloc, all);
 
 	/*
 	 * the current bus might not own M64 window and that's all

@@ -365,8 +365,8 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)
 	/* Use last M64 BAR to cover M64 window */
 	phb->ioda.m64_bar_idx = 15;
 	phb->init_m64 = pnv_ioda2_init_m64;
-	phb->reserve_m64_pe = pnv_ioda2_reserve_m64_pe;
-	phb->pick_m64_pe = pnv_ioda2_pick_m64_pe;
+	phb->reserve_m64_pe = pnv_ioda_reserve_m64_pe;
+	phb->pick_m64_pe = pnv_ioda_pick_m64_pe;
 }
 
 static void pnv_ioda_freeze_pe(struct pnv_phb *phb, int pe_no)

@@ -123,6 +123,14 @@ static inline bool pnv_pci_is_mem_pref_64(unsigned long flags)
 		(IORESOURCE_MEM_64 | IORESOURCE_PREFETCH));
 }
 
+static struct pnv_ioda_pe *pnv_ioda_init_pe(struct pnv_phb *phb, int pe_no)
+{
+	phb->ioda.pe_array[pe_no].phb = phb;
+	phb->ioda.pe_array[pe_no].pe_number = pe_no;
+
+	return &phb->ioda.pe_array[pe_no];
+}
+
 static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no)
 {
 	if (!(pe_no >= 0 && pe_no < phb->ioda.total_pe_num)) {

@@ -135,11 +143,10 @@ static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no)
 		pr_debug("%s: PE %d was reserved on PHB#%x\n",
 			 __func__, pe_no, phb->hose->global_number);
 
-	phb->ioda.pe_array[pe_no].phb = phb;
-	phb->ioda.pe_array[pe_no].pe_number = pe_no;
+	pnv_ioda_init_pe(phb, pe_no);
 }
 
-static unsigned int pnv_ioda_alloc_pe(struct pnv_phb *phb)
+static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb)
 {
 	unsigned long pe;
 

@@ -147,20 +154,20 @@ static unsigned int pnv_ioda_alloc_pe(struct pnv_phb *phb)
 		pe = find_next_zero_bit(phb->ioda.pe_alloc,
 					phb->ioda.total_pe_num, 0);
 		if (pe >= phb->ioda.total_pe_num)
-			return IODA_INVALID_PE;
+			return NULL;
 	} while(test_and_set_bit(pe, phb->ioda.pe_alloc));
 
-	phb->ioda.pe_array[pe].phb = phb;
-	phb->ioda.pe_array[pe].pe_number = pe;
-	return pe;
+	return pnv_ioda_init_pe(phb, pe);
 }
 
-static void pnv_ioda_free_pe(struct pnv_phb *phb, int pe)
+static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe)
 {
-	WARN_ON(phb->ioda.pe_array[pe].pdev);
+	struct pnv_phb *phb = pe->phb;
 
-	memset(&phb->ioda.pe_array[pe], 0, sizeof(struct pnv_ioda_pe));
-	clear_bit(pe, phb->ioda.pe_alloc);
+	WARN_ON(pe->pdev);
+
+	memset(pe, 0, sizeof(struct pnv_ioda_pe));
+	clear_bit(pe->pe_number, phb->ioda.pe_alloc);
 }
 
 /* The default M64 BAR is shared by all PEs */

@@ -320,7 +327,7 @@ static void pnv_ioda_reserve_m64_pe(struct pci_bus *bus,
 	}
 }
 
-static unsigned int pnv_ioda_pick_m64_pe(struct pci_bus *bus, bool all)
+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;

@@ -330,7 +337,7 @@ static unsigned int pnv_ioda_pick_m64_pe(struct pci_bus *bus, bool all)
 
 	/* Root bus shouldn't use M64 */
 	if (pci_is_root_bus(bus))
-		return IODA_INVALID_PE;
+		return NULL;
 
 	/* Allocate bitmap */
 	size = _ALIGN_UP(phb->ioda.total_pe_num / 8, sizeof(unsigned long));

@@ -338,7 +345,7 @@ static unsigned int pnv_ioda_pick_m64_pe(struct pci_bus *bus, bool all)
 	if (!pe_alloc) {
 		pr_warn("%s: Out of memory !\n",
 			__func__);
-		return IODA_INVALID_PE;
+		return NULL;
 	}
 
 	/* Figure out reserved PE numbers by the PE */

@@ -351,7 +358,7 @@ static unsigned int pnv_ioda_pick_m64_pe(struct pci_bus *bus, bool all)
 	 */
 	if (bitmap_empty(pe_alloc, phb->ioda.total_pe_num)) {
 		kfree(pe_alloc);
-		return IODA_INVALID_PE;
+		return NULL;
 	}
 
 	/*

@@ -397,7 +404,7 @@ static unsigned int pnv_ioda_pick_m64_pe(struct pci_bus *bus, bool all)
 	}
 
 	kfree(pe_alloc);
-	return master_pe->pe_number;
+	return master_pe;
 }
 
 static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)

@@ -963,7 +970,6 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 	struct pnv_phb *phb = hose->private_data;
 	struct pci_dn *pdn = pci_get_pdn(dev);
 	struct pnv_ioda_pe *pe;
-	unsigned int pe_num;
 
 	if (!pdn) {
 		pr_err("%s: Device tree node not associated properly\n",

@@ -973,8 +979,8 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 	if (pdn->pe_number != IODA_INVALID_PE)
 		return NULL;
 
-	pe_num = pnv_ioda_alloc_pe(phb);
-	if (pe_num == IODA_INVALID_PE) {
+	pe = pnv_ioda_alloc_pe(phb);
+	if (!pe) {
 		pr_warning("%s: Not enough PE# available, disabling device\n",
 			   pci_name(dev));
 		return NULL;

@@ -987,10 +993,9 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 	 *
 	 * At some point we want to remove the PDN completely anyways
 	 */
-	pe = &phb->ioda.pe_array[pe_num];
 	pci_dev_get(dev);
 	pdn->pcidev = dev;
-	pdn->pe_number = pe_num;
+	pdn->pe_number = pe->pe_number;
 	pe->flags = PNV_IODA_PE_DEV;
 	pe->pdev = dev;
 	pe->pbus = NULL;

@@ -1001,8 +1006,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 
 	if (pnv_ioda_configure_pe(phb, pe)) {
 		/* XXX What do we do here ? */
-		if (pe_num)
-			pnv_ioda_free_pe(phb, pe_num);
+		pnv_ioda_free_pe(pe);
 		pdn->pe_number = IODA_INVALID_PE;
 		pe->pdev = NULL;
 		pci_dev_put(dev);

@@ -1037,28 +1041,26 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
  * subordinate PCI devices and buses. The second type of PE is normally
  * orgiriated by PCIe-to-PCI bridge or PLX switch downstream ports.
  */
-static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all)
+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_ioda_pe *pe;
-	unsigned int pe_num = IODA_INVALID_PE;
+	struct pnv_ioda_pe *pe = NULL;
 
 	/* Check if PE is determined by M64 */
 	if (phb->pick_m64_pe)
-		pe_num = phb->pick_m64_pe(bus, all);
+		pe = phb->pick_m64_pe(bus, all);
 
 	/* The PE number isn't pinned by M64 */
-	if (pe_num == IODA_INVALID_PE)
-		pe_num = pnv_ioda_alloc_pe(phb);
+	if (!pe)
+		pe = pnv_ioda_alloc_pe(phb);
 
-	if (pe_num == IODA_INVALID_PE) {
+	if (!pe) {
 		pr_warning("%s: Not enough PE# available for PCI bus %04x:%02x\n",
 			__func__, pci_domain_nr(bus), bus->number);
-		return;
+		return NULL;
 	}
 
-	pe = &phb->ioda.pe_array[pe_num];
 	pe->flags |= (all ? PNV_IODA_PE_BUS_ALL : PNV_IODA_PE_BUS);
 	pe->pbus = bus;
 	pe->pdev = NULL;

@@ -1067,17 +1069,16 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all)
 
 	if (all)
 		pe_info(pe, "Secondary bus %d..%d associated with PE#%d\n",
-			bus->busn_res.start, bus->busn_res.end, pe_num);
+			bus->busn_res.start, bus->busn_res.end, pe->pe_number);
 	else
 		pe_info(pe, "Secondary bus %d associated with PE#%d\n",
-			bus->busn_res.start, pe_num);
+			bus->busn_res.start, pe->pe_number);
 
 	if (pnv_ioda_configure_pe(phb, pe)) {
 		/* XXX What do we do here ? */
-		if (pe_num)
-			pnv_ioda_free_pe(phb, pe_num);
+		pnv_ioda_free_pe(pe);
 		pe->pbus = NULL;
-		return;
+		return NULL;
 	}
 
 	/* Associate it with all child devices */

@@ -1085,6 +1086,8 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all)
 
 	/* Put PE to the list */
 	list_add_tail(&pe->list, &phb->ioda.pe_list);
+
+	return pe;
 }
 
 static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)

@@ -1396,7 +1399,7 @@ static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
 
 		pnv_ioda_deconfigure_pe(phb, pe);
 
-		pnv_ioda_free_pe(phb, pe->pe_number);
+		pnv_ioda_free_pe(pe);
 	}
 }
 

@@ -1405,6 +1408,7 @@ 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;
 	struct pci_sriov      *iov;
 	u16                    num_vfs, i;

@@ -1429,8 +1433,11 @@ void pnv_pci_sriov_disable(struct pci_dev *pdev)
 		/* Release PE numbers */
 		if (pdn->m64_single_mode) {
 			for (i = 0; i < num_vfs; i++) {
-				if (pdn->pe_num_map[i] != IODA_INVALID_PE)
-					pnv_ioda_free_pe(phb, pdn->pe_num_map[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);

@@ -1483,8 +1490,7 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 
 		if (pnv_ioda_configure_pe(phb, pe)) {
 			/* XXX What do we do here ? */
-			if (pe_num)
-				pnv_ioda_free_pe(phb, pe_num);
+			pnv_ioda_free_pe(pe);
 			pe->pdev = NULL;
 			continue;
 		}

@@ -1503,6 +1509,7 @@ 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;

@@ -1545,11 +1552,13 @@ int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
 		/* Calculate available PE for required VFs */
 		if (pdn->m64_single_mode) {
 			for (i = 0; i < num_vfs; i++) {
-				pdn->pe_num_map[i] = pnv_ioda_alloc_pe(phb);
-				if (pdn->pe_num_map[i] == IODA_INVALID_PE) {
+				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);

@@ -1594,8 +1603,11 @@ int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
 m64_failed:
 	if (pdn->m64_single_mode) {
 		for (i = 0; i < num_vfs; i++) {
-			if (pdn->pe_num_map[i] != IODA_INVALID_PE)
-				pnv_ioda_free_pe(phb, pdn->pe_num_map[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);

@@ -105,7 +105,7 @@ struct pnv_phb {
 	int (*init_m64)(struct pnv_phb *phb);
 	void (*reserve_m64_pe)(struct pci_bus *bus,
 			       unsigned long *pe_bitmap, bool all);
-	unsigned int (*pick_m64_pe)(struct pci_bus *bus, bool all);
+	struct pnv_ioda_pe *(*pick_m64_pe)(struct pci_bus *bus, bool all);
 	int (*get_pe_state)(struct pnv_phb *phb, int pe_no);
 	void (*freeze_pe)(struct pnv_phb *phb, int pe_no);
 	int (*unfreeze_pe)(struct pnv_phb *phb, int pe_no, int opt);

@@ -260,10 +260,10 @@ static inline struct eeh_dev *pdn_to_eeh_dev(struct pci_dn *pdn)
 extern struct pci_bus *pcibios_find_pci_bus(struct device_node *dn);
 
 /** Remove all of the PCI devices under this bus */
-extern void pcibios_remove_pci_devices(struct pci_bus *bus);
+extern void pci_hp_remove_devices(struct pci_bus *bus);
 
 /** Discover new pci devices under this bus, and add them */
-extern void pcibios_add_pci_devices(struct pci_bus *bus);
+extern void pci_hp_add_devices(struct pci_bus *bus);
 
 
 extern void isa_bridge_find_early(struct pci_controller *hose);

@@ -621,7 +621,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 	 * We don't remove the corresponding PE instances because
 	 * we need the information afterwords. The attached EEH
 	 * devices are expected to be attached soon when calling
-	 * into pcibios_add_pci_devices().
+	 * into pci_hp_add_devices().
 	 */
 	eeh_pe_state_mark(pe, EEH_PE_KEEP);
 	if (bus) {

@@ -630,7 +630,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 		} else {
 			eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 			pci_lock_rescan_remove();
-			pcibios_remove_pci_devices(bus);
+			pci_hp_remove_devices(bus);
 			pci_unlock_rescan_remove();
 		}
 	} else if (frozen_bus) {

@@ -681,7 +681,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 		if (pe->type & EEH_PE_VF)
 			eeh_add_virt_device(edev, NULL);
 		else
-			pcibios_add_pci_devices(bus);
+			pci_hp_add_devices(bus);
 	} else if (frozen_bus && rmv_data->removed) {
 		pr_info("EEH: Sleep 5s ahead of partial hotplug\n");
 		ssleep(5);

@@ -691,7 +691,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 		if (pe->type & EEH_PE_VF)
 			eeh_add_virt_device(edev, NULL);
 		else
-			pcibios_add_pci_devices(frozen_bus);
+			pci_hp_add_devices(frozen_bus);
 	}
 	eeh_pe_state_clear(pe, EEH_PE_KEEP);
 

@@ -896,7 +896,7 @@ perm_error:
 			eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
 
 			pci_lock_rescan_remove();
-			pcibios_remove_pci_devices(frozen_bus);
+			pci_hp_remove_devices(frozen_bus);
 			pci_unlock_rescan_remove();
 		}
 	}

@@ -981,7 +981,7 @@ static void eeh_handle_special_event(void)
 				bus = eeh_pe_bus_get(phb_pe);
 				eeh_pe_dev_traverse(pe,
 					eeh_report_failure, NULL);
-				pcibios_remove_pci_devices(bus);
+				pci_hp_remove_devices(bus);
 			}
 			pci_unlock_rescan_remove();
 		}

@@ -38,20 +38,20 @@ void pcibios_release_device(struct pci_dev *dev)
 }
 
 /**
- * pcibios_remove_pci_devices - remove all devices under this bus
+ * pci_hp_remove_devices - remove all devices under this bus
  * @bus: the indicated PCI bus
  *
  * Remove all of the PCI devices under this bus both from the
  * linux pci device tree, and from the powerpc EEH address cache.
  */
-void pcibios_remove_pci_devices(struct pci_bus *bus)
+void pci_hp_remove_devices(struct pci_bus *bus)
 {
 	struct pci_dev *dev, *tmp;
 	struct pci_bus *child_bus;
 
 	/* First go down child busses */
 	list_for_each_entry(child_bus, &bus->children, node)
-		pcibios_remove_pci_devices(child_bus);
+		pci_hp_remove_devices(child_bus);
 
 	pr_debug("PCI: Removing devices on bus %04x:%02x\n",
 		 pci_domain_nr(bus),  bus->number);

@@ -60,11 +60,10 @@ void pcibios_remove_pci_devices(struct pci_bus *bus)
 		pci_stop_and_remove_bus_device(dev);
 	}
 }
-
-EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices);
+EXPORT_SYMBOL_GPL(pci_hp_remove_devices);
 
 /**
- * pcibios_add_pci_devices - adds new pci devices to bus
+ * pci_hp_add_devices - adds new pci devices to bus
  * @bus: the indicated PCI bus
  *
  * This routine will find and fixup new pci devices under

@@ -74,7 +73,7 @@ EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices);
  * is how this routine differs from other, similar pcibios
  * routines.)
  */
-void pcibios_add_pci_devices(struct pci_bus * bus)
+void pci_hp_add_devices(struct pci_bus *bus)
 {
 	int slotno, mode, pass, max;
 	struct pci_dev *dev;

@@ -114,4 +113,4 @@ void pcibios_add_pci_devices(struct pci_bus * bus)
 	}
 	pcibios_finish_adding_to_bus(bus);
 }
-EXPORT_SYMBOL_GPL(pcibios_add_pci_devices);
+EXPORT_SYMBOL_GPL(pci_hp_add_devices);

@@ -380,7 +380,7 @@ int dlpar_remove_pci_slot(char *drc_name, struct device_node *dn)
 	}
 
 	/* Remove all devices below slot */
-	pcibios_remove_pci_devices(bus);
+	pci_hp_remove_devices(bus);
 
 	/* Unmap PCI IO space */
 	if (pcibios_unmap_io_space(bus)) {

@@ -404,7 +404,7 @@ static int enable_slot(struct hotplug_slot *hotplug_slot)
 
 	if (state == PRESENT) {
 		pci_lock_rescan_remove();
-		pcibios_add_pci_devices(slot->bus);
+		pci_hp_add_devices(slot->bus);
 		pci_unlock_rescan_remove();
 		slot->state = CONFIGURED;
 	} else if (state == EMPTY) {

@@ -426,7 +426,7 @@ static int disable_slot(struct hotplug_slot *hotplug_slot)
 		return -EINVAL;
 
 	pci_lock_rescan_remove();
-	pcibios_remove_pci_devices(slot->bus);
+	pci_hp_remove_devices(slot->bus);
 	pci_unlock_rescan_remove();
 	vm_unmap_aliases();
 

@@ -116,7 +116,7 @@ int rpaphp_enable_slot(struct slot *slot)
 		}
 
 		if (list_empty(&bus->devices))
-			pcibios_add_pci_devices(bus);
+			pci_hp_add_devices(bus);
 
 		if (!list_empty(&bus->devices)) {
 			info->adapter_status = CONFIGURED;

@@ -2929,19 +2929,72 @@ truncate_iov:
 }
 #endif /* CONFIG_PCI_IOV */
 
+static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe,
+				  struct resource *res)
+{
+	struct pnv_phb *phb = pe->phb;
+	struct pci_bus_region region;
+	int index;
+	int64_t rc;
+
+	if (!res || !res->flags || res->start > res->end)
+		return;
+
+	if (res->flags & IORESOURCE_IO) {
+		region.start = res->start - phb->ioda.io_pci_base;
+		region.end   = res->end - phb->ioda.io_pci_base;
+		index = region.start / phb->ioda.io_segsize;
+
+		while (index < phb->ioda.total_pe_num &&
+		       region.start <= region.end) {
+			phb->ioda.io_segmap[index] = pe->pe_number;
+			rc = opal_pci_map_pe_mmio_window(phb->opal_id,
+				pe->pe_number, OPAL_IO_WINDOW_TYPE, 0, index);
+			if (rc != OPAL_SUCCESS) {
+				pr_err("%s: Error %lld mapping IO segment#%d to PE#%d\n",
+				       __func__, rc, index, pe->pe_number);
+				break;
+			}
+
+			region.start += phb->ioda.io_segsize;
+			index++;
+		}
+	} else if ((res->flags & IORESOURCE_MEM) &&
+		   !pnv_pci_is_mem_pref_64(res->flags)) {
+		region.start = res->start -
+			       phb->hose->mem_offset[0] -
+			       phb->ioda.m32_pci_base;
+		region.end   = res->end -
+			       phb->hose->mem_offset[0] -
+			       phb->ioda.m32_pci_base;
+		index = region.start / phb->ioda.m32_segsize;
+
+		while (index < phb->ioda.total_pe_num &&
+		       region.start <= region.end) {
+			phb->ioda.m32_segmap[index] = pe->pe_number;
+			rc = opal_pci_map_pe_mmio_window(phb->opal_id,
+				pe->pe_number, OPAL_M32_WINDOW_TYPE, 0, index);
+			if (rc != OPAL_SUCCESS) {
+				pr_err("%s: Error %lld mapping M32 segment#%d to PE#%d",
+				       __func__, rc, index, pe->pe_number);
+				break;
+			}
+
+			region.start += phb->ioda.m32_segsize;
+			index++;
+		}
+	}
+}
+
 /*
  * 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
  * parent PE could be overrided by its child PEs if necessary.
  */
-static void pnv_ioda_setup_pe_seg(struct pci_controller *hose,
-				  struct pnv_ioda_pe *pe)
+static void pnv_ioda_setup_pe_seg(struct pnv_ioda_pe *pe)
 {
-	struct pnv_phb *phb = hose->private_data;
-	struct pci_bus_region region;
 	struct resource *res;
-	int i, index;
-	int rc;
+	int i;
 
 	/*
 	 * NOTE: We only care PCI bus based PE for now. For PCI