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

arch/powerpc/include/asm/iommu.h

@@ -79,6 +79,9 @@ struct iommu_table {
 	struct iommu_group *it_group;
 #endif
 	void (*set_bypass)(struct iommu_table *tbl, bool enable);
+#ifdef CONFIG_PPC_POWERNV
+	void           *data;
+#endif
 };
 
 /* Pure 2^n version of get_order */

arch/powerpc/include/asm/machdep.h

@@ -236,6 +236,11 @@ struct machdep_calls {
 	/* Called after scan and before resource survey */
 	void (*pcibios_fixup_phb)(struct pci_controller *hose);
 
+#ifdef CONFIG_PCI_IOV
+	void (*pcibios_fixup_sriov)(struct pci_dev *pdev);
+	resource_size_t (*pcibios_iov_resource_alignment)(struct pci_dev *, int resno);
+#endif /* CONFIG_PCI_IOV */
+
 	/* Called to shutdown machine specific hardware not already controlled
 	 * by other drivers.
 	 */

arch/powerpc/include/asm/pci-bridge.h

@@ -175,6 +175,7 @@ struct iommu_table;
 
 struct pci_dn {
 	int     flags;
+#define PCI_DN_FLAG_IOV_VF	0x01
 
 	int	busno;			/* pci bus number */
 	int	devfn;			/* pci device and function number */
@@ -189,13 +190,21 @@ struct pci_dn {
 
 	int	pci_ext_config_space;	/* for pci devices */
 
-	struct	pci_dev *pcidev;	/* back-pointer to the pci device */
 #ifdef CONFIG_EEH
 	struct eeh_dev *edev;		/* eeh device */
 #endif
 #define IODA_INVALID_PE		(-1)
 #ifdef CONFIG_PPC_POWERNV
 	int	pe_number;
+#ifdef CONFIG_PCI_IOV
+	u16     vfs_expanded;		/* number of VFs IOV BAR expanded */
+	u16     num_vfs;		/* number of VFs enabled*/
+	int     offset;			/* PE# for the first VF PE */
+#define M64_PER_IOV 4
+	int     m64_per_iov;
+#define IODA_INVALID_M64        (-1)
+	int     m64_wins[PCI_SRIOV_NUM_BARS][M64_PER_IOV];
+#endif /* CONFIG_PCI_IOV */
 #endif
 	struct list_head child_list;
 	struct list_head list;
@@ -207,6 +216,8 @@ struct pci_dn {
 extern struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus,
 					   int devfn);
 extern struct pci_dn *pci_get_pdn(struct pci_dev *pdev);
+extern struct pci_dn *add_dev_pci_data(struct pci_dev *pdev);
+extern void remove_dev_pci_data(struct pci_dev *pdev);
 extern void *update_dn_pci_info(struct device_node *dn, void *data);
 
 static inline int pci_device_from_OF_node(struct device_node *np,

arch/powerpc/kernel/pci-common.c

@@ -134,6 +134,16 @@ void pcibios_reset_secondary_bus(struct pci_dev *dev)
 	pci_reset_secondary_bus(dev);
 }
 
+#ifdef CONFIG_PCI_IOV
+resource_size_t pcibios_iov_resource_alignment(struct pci_dev *pdev, int resno)
+{
+	if (ppc_md.pcibios_iov_resource_alignment)
+		return ppc_md.pcibios_iov_resource_alignment(pdev, resno);
+
+	return pci_iov_resource_size(pdev, resno);
+}
+#endif /* CONFIG_PCI_IOV */
+
 static resource_size_t pcibios_io_size(const struct pci_controller *hose)
 {
 #ifdef CONFIG_PPC64
@@ -792,6 +802,10 @@ static void pcibios_fixup_resources(struct pci_dev *dev)
 		       pci_name(dev));
 		return;
 	}
+
+	if (dev->is_virtfn)
+		return;
+
 	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
 		struct resource *res = dev->resource + i;
 		struct pci_bus_region reg;
@@ -995,6 +1009,12 @@ int pcibios_add_device(struct pci_dev *dev)
 	 */
 	if (dev->bus->is_added)
 		pcibios_setup_device(dev);
+
+#ifdef CONFIG_PCI_IOV
+	if (ppc_md.pcibios_fixup_sriov)
+		ppc_md.pcibios_fixup_sriov(dev);
+#endif /* CONFIG_PCI_IOV */
+
 	return 0;
 }
 

arch/powerpc/kernel/pci_dn.c

@@ -136,6 +136,135 @@ struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
 	return NULL;
 }
 
+#ifdef CONFIG_PCI_IOV
+static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
+					   struct pci_dev *pdev,
+					   int busno, int devfn)
+{
+	struct pci_dn *pdn;
+
+	/* Except PHB, we always have the parent */
+	if (!parent)
+		return NULL;
+
+	pdn = kzalloc(sizeof(*pdn), GFP_KERNEL);
+	if (!pdn) {
+		dev_warn(&pdev->dev, "%s: Out of memory!\n", __func__);
+		return NULL;
+	}
+
+	pdn->phb = parent->phb;
+	pdn->parent = parent;
+	pdn->busno = busno;
+	pdn->devfn = devfn;
+#ifdef CONFIG_PPC_POWERNV
+	pdn->pe_number = IODA_INVALID_PE;
+#endif
+	INIT_LIST_HEAD(&pdn->child_list);
+	INIT_LIST_HEAD(&pdn->list);
+	list_add_tail(&pdn->list, &parent->child_list);
+
+	/*
+	 * If we already have PCI device instance, lets
+	 * bind them.
+	 */
+	if (pdev)
+		pdev->dev.archdata.pci_data = pdn;
+
+	return pdn;
+}
+#endif
+
+struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
+{
+#ifdef CONFIG_PCI_IOV
+	struct pci_dn *parent, *pdn;
+	int i;
+
+	/* Only support IOV for now */
+	if (!pdev->is_physfn)
+		return pci_get_pdn(pdev);
+
+	/* Check if VFs have been populated */
+	pdn = pci_get_pdn(pdev);
+	if (!pdn || (pdn->flags & PCI_DN_FLAG_IOV_VF))
+		return NULL;
+
+	pdn->flags |= PCI_DN_FLAG_IOV_VF;
+	parent = pci_bus_to_pdn(pdev->bus);
+	if (!parent)
+		return NULL;
+
+	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
+		pdn = add_one_dev_pci_data(parent, NULL,
+					   pci_iov_virtfn_bus(pdev, i),
+					   pci_iov_virtfn_devfn(pdev, i));
+		if (!pdn) {
+			dev_warn(&pdev->dev, "%s: Cannot create firmware data for VF#%d\n",
+				 __func__, i);
+			return NULL;
+		}
+	}
+#endif /* CONFIG_PCI_IOV */
+
+	return pci_get_pdn(pdev);
+}
+
+void remove_dev_pci_data(struct pci_dev *pdev)
+{
+#ifdef CONFIG_PCI_IOV
+	struct pci_dn *parent;
+	struct pci_dn *pdn, *tmp;
+	int i;
+
+	/*
+	 * VF and VF PE are created/released dynamically, so we need to
+	 * bind/unbind them.  Otherwise the VF and VF PE would be mismatched
+	 * when re-enabling SR-IOV.
+	 */
+	if (pdev->is_virtfn) {
+		pdn = pci_get_pdn(pdev);
+#ifdef CONFIG_PPC_POWERNV
+		pdn->pe_number = IODA_INVALID_PE;
+#endif
+		return;
+	}
+
+	/* Only support IOV PF for now */
+	if (!pdev->is_physfn)
+		return;
+
+	/* Check if VFs have been populated */
+	pdn = pci_get_pdn(pdev);
+	if (!pdn || !(pdn->flags & PCI_DN_FLAG_IOV_VF))
+		return;
+
+	pdn->flags &= ~PCI_DN_FLAG_IOV_VF;
+	parent = pci_bus_to_pdn(pdev->bus);
+	if (!parent)
+		return;
+
+	/*
+	 * We might introduce flag to pci_dn in future
+	 * so that we can release VF's firmware data in
+	 * a batch mode.
+	 */
+	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
+		list_for_each_entry_safe(pdn, tmp,
+			&parent->child_list, list) {
+			if (pdn->busno != pci_iov_virtfn_bus(pdev, i) ||
+			    pdn->devfn != pci_iov_virtfn_devfn(pdev, i))
+				continue;
+
+			if (!list_empty(&pdn->list))
+				list_del(&pdn->list);
+
+			kfree(pdn);
+		}
+	}
+#endif /* CONFIG_PCI_IOV */
+}
+
 /*
  * Traverse_func that inits the PCI fields of the device node.
  * NOTE: this *must* be done before read/write config to the device.

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);

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

drivers/pci/pci.h

@@ -243,10 +243,12 @@ struct pci_sriov {
 	u16 stride;		/* following VF stride */
 	u32 pgsz;		/* page size for BAR alignment */
 	u8 link;		/* Function Dependency Link */
+	u8 max_VF_buses;	/* max buses consumed by VFs */
 	u16 driver_max_VFs;	/* max num VFs driver supports */
 	struct pci_dev *dev;	/* lowest numbered PF */
 	struct pci_dev *self;	/* this PF */
 	struct mutex lock;	/* lock for VF bus */
+	resource_size_t barsz[PCI_SRIOV_NUM_BARS];	/* VF BAR size */
 };
 
 #ifdef CONFIG_PCI_ATS

drivers/pci/setup-bus.c

@@ -99,8 +99,8 @@ static void remove_from_list(struct list_head *head,
 	}
 }
 
-static resource_size_t get_res_add_size(struct list_head *head,
-					struct resource *res)
+static struct pci_dev_resource *res_to_dev_res(struct list_head *head,
+					       struct resource *res)
 {
 	struct pci_dev_resource *dev_res;
 
@@ -109,17 +109,37 @@ static resource_size_t get_res_add_size(struct list_head *head,
 			int idx = res - &dev_res->dev->resource[0];
 
 			dev_printk(KERN_DEBUG, &dev_res->dev->dev,
-				 "res[%d]=%pR get_res_add_size add_size %llx\n",
+				 "res[%d]=%pR res_to_dev_res add_size %llx min_align %llx\n",
 				 idx, dev_res->res,
-				 (unsigned long long)dev_res->add_size);
+				 (unsigned long long)dev_res->add_size,
+				 (unsigned long long)dev_res->min_align);
 
-			return dev_res->add_size;
+			return dev_res;
 		}
 	}
 
-	return 0;
+	return NULL;
 }
 
+static resource_size_t get_res_add_size(struct list_head *head,
+					struct resource *res)
+{
+	struct pci_dev_resource *dev_res;
+
+	dev_res = res_to_dev_res(head, res);
+	return dev_res ? dev_res->add_size : 0;
+}
+
+static resource_size_t get_res_add_align(struct list_head *head,
+					 struct resource *res)
+{
+	struct pci_dev_resource *dev_res;
+
+	dev_res = res_to_dev_res(head, res);
+	return dev_res ? dev_res->min_align : 0;
+}
+
+
 /* Sort resources by alignment */
 static void pdev_sort_resources(struct pci_dev *dev, struct list_head *head)
 {
@@ -215,7 +235,7 @@ static void reassign_resources_sorted(struct list_head *realloc_head,
 	struct resource *res;
 	struct pci_dev_resource *add_res, *tmp;
 	struct pci_dev_resource *dev_res;
-	resource_size_t add_size;
+	resource_size_t add_size, align;
 	int idx;
 
 	list_for_each_entry_safe(add_res, tmp, realloc_head, list) {
@@ -238,13 +258,13 @@ static void reassign_resources_sorted(struct list_head *realloc_head,
 
 		idx = res - &add_res->dev->resource[0];
 		add_size = add_res->add_size;
+		align = add_res->min_align;
 		if (!resource_size(res)) {
-			res->start = add_res->start;
+			res->start = align;
 			res->end = res->start + add_size - 1;
 			if (pci_assign_resource(add_res->dev, idx))
 				reset_resource(res);
 		} else {
-			resource_size_t align = add_res->min_align;
 			res->flags |= add_res->flags &
 				 (IORESOURCE_STARTALIGN|IORESOURCE_SIZEALIGN);
 			if (pci_reassign_resource(add_res->dev, idx,
@@ -368,8 +388,9 @@ static void __assign_resources_sorted(struct list_head *head,
 	LIST_HEAD(save_head);
 	LIST_HEAD(local_fail_head);
 	struct pci_dev_resource *save_res;
-	struct pci_dev_resource *dev_res, *tmp_res;
+	struct pci_dev_resource *dev_res, *tmp_res, *dev_res2;
 	unsigned long fail_type;
+	resource_size_t add_align, align;
 
 	/* Check if optional add_size is there */
 	if (!realloc_head || list_empty(realloc_head))
@@ -384,10 +405,44 @@ static void __assign_resources_sorted(struct list_head *head,
 	}
 
 	/* Update res in head list with add_size in realloc_head list */
-	list_for_each_entry(dev_res, head, list)
+	list_for_each_entry_safe(dev_res, tmp_res, head, list) {
 		dev_res->res->end += get_res_add_size(realloc_head,
 							dev_res->res);
 
+		/*
+		 * There are two kinds of additional resources in the list:
+		 * 1. bridge resource  -- IORESOURCE_STARTALIGN
+		 * 2. SR-IOV resource   -- IORESOURCE_SIZEALIGN
+		 * Here just fix the additional alignment for bridge
+		 */
+		if (!(dev_res->res->flags & IORESOURCE_STARTALIGN))
+			continue;
+
+		add_align = get_res_add_align(realloc_head, dev_res->res);
+
+		/*
+		 * The "head" list is sorted by the alignment to make sure
+		 * resources with bigger alignment will be assigned first.
+		 * After we change the alignment of a dev_res in "head" list,
+		 * we need to reorder the list by alignment to make it
+		 * consistent.
+		 */
+		if (add_align > dev_res->res->start) {
+			dev_res->res->start = add_align;
+			dev_res->res->end = add_align +
+				            resource_size(dev_res->res);
+
+			list_for_each_entry(dev_res2, head, list) {
+				align = pci_resource_alignment(dev_res2->dev,
+							       dev_res2->res);
+				if (add_align > align)
+					list_move_tail(&dev_res->list,
+						       &dev_res2->list);
+			}
+               }
+
+	}
+
 	/* Try updated head list with add_size added */
 	assign_requested_resources_sorted(head, &local_fail_head);
 
@@ -962,6 +1017,8 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 	struct resource *b_res = find_free_bus_resource(bus,
 					mask | IORESOURCE_PREFETCH, type);
 	resource_size_t children_add_size = 0;
+	resource_size_t children_add_align = 0;
+	resource_size_t add_align = 0;
 
 	if (!b_res)
 		return -ENOSPC;
@@ -986,6 +1043,7 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 			/* put SRIOV requested res to the optional list */
 			if (realloc_head && i >= PCI_IOV_RESOURCES &&
 					i <= PCI_IOV_RESOURCE_END) {
+				add_align = max(pci_resource_alignment(dev, r), add_align);
 				r->end = r->start - 1;
 				add_to_list(realloc_head, dev, r, r_size, 0/* don't care */);
 				children_add_size += r_size;
@@ -1016,19 +1074,23 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 			if (order > max_order)
 				max_order = order;
 
-			if (realloc_head)
+			if (realloc_head) {
 				children_add_size += get_res_add_size(realloc_head, r);
+				children_add_align = get_res_add_align(realloc_head, r);
+				add_align = max(add_align, children_add_align);
+			}
 		}
 	}
 
 	min_align = calculate_mem_align(aligns, max_order);
 	min_align = max(min_align, window_alignment(bus, b_res->flags));
 	size0 = calculate_memsize(size, min_size, 0, resource_size(b_res), min_align);
+	add_align = max(min_align, add_align);
 	if (children_add_size > add_size)
 		add_size = children_add_size;
 	size1 = (!realloc_head || (realloc_head && !add_size)) ? size0 :
 		calculate_memsize(size, min_size, add_size,
-				resource_size(b_res), min_align);
+				resource_size(b_res), add_align);
 	if (!size0 && !size1) {
 		if (b_res->start || b_res->end)
 			dev_info(&bus->self->dev, "disabling bridge window %pR to %pR (unused)\n",
@@ -1040,10 +1102,11 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 	b_res->end = size0 + min_align - 1;
 	b_res->flags |= IORESOURCE_STARTALIGN;
 	if (size1 > size0 && realloc_head) {
-		add_to_list(realloc_head, bus->self, b_res, size1-size0, min_align);
-		dev_printk(KERN_DEBUG, &bus->self->dev, "bridge window %pR to %pR add_size %llx\n",
+		add_to_list(realloc_head, bus->self, b_res, size1-size0, add_align);
+		dev_printk(KERN_DEBUG, &bus->self->dev, "bridge window %pR to %pR add_size %llx add_align %llx\n",
 			   b_res, &bus->busn_res,
-			   (unsigned long long)size1-size0);
+			   (unsigned long long) (size1 - size0),
+			   (unsigned long long) add_align);
 	}
 	return 0;
 }

include/linux/pci.h

@@ -1174,6 +1174,7 @@ unsigned char pci_bus_max_busnr(struct pci_bus *bus);
 void pci_setup_bridge(struct pci_bus *bus);
 resource_size_t pcibios_window_alignment(struct pci_bus *bus,
 					 unsigned long type);
+resource_size_t pcibios_iov_resource_alignment(struct pci_dev *dev, int resno);
 
 #define PCI_VGA_STATE_CHANGE_BRIDGE (1 << 0)
 #define PCI_VGA_STATE_CHANGE_DECODES (1 << 1)
@@ -1669,13 +1670,25 @@ int pci_ext_cfg_avail(void);
 void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar);
 
 #ifdef CONFIG_PCI_IOV
+int pci_iov_virtfn_bus(struct pci_dev *dev, int id);
+int pci_iov_virtfn_devfn(struct pci_dev *dev, int id);
+
 int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn);
 void pci_disable_sriov(struct pci_dev *dev);
 int pci_num_vf(struct pci_dev *dev);
 int pci_vfs_assigned(struct pci_dev *dev);
 int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs);
 int pci_sriov_get_totalvfs(struct pci_dev *dev);
+resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno);
 #else
+static inline int pci_iov_virtfn_bus(struct pci_dev *dev, int id)
+{
+	return -ENOSYS;
+}
+static inline int pci_iov_virtfn_devfn(struct pci_dev *dev, int id)
+{
+	return -ENOSYS;
+}
 static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn)
 { return -ENODEV; }
 static inline void pci_disable_sriov(struct pci_dev *dev) { }
@@ -1686,6 +1699,8 @@ static inline int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs)
 { return 0; }
 static inline int pci_sriov_get_totalvfs(struct pci_dev *dev)
 { return 0; }
+static inline resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno)
+{ return 0; }
 #endif
 
 #if defined(CONFIG_HOTPLUG_PCI) || defined(CONFIG_HOTPLUG_PCI_MODULE)