1 files changed, 129 insertions, 71 deletions

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 0f7a60f1e..e58908066 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -41,11 +41,18 @@
 #include <asm/ppc-pci.h>
 #include <asm/eeh.h>
 
+/* hose_spinlock protects accesses to the the phb_bitmap. */
 static DEFINE_SPINLOCK(hose_spinlock);
 LIST_HEAD(hose_list);
 
-/* XXX kill that some day ... */
-static int global_phb_number;		/* Global phb counter */
+/* For dynamic PHB numbering on get_phb_number(): max number of PHBs. */
+#define MAX_PHBS 0x10000
+
+/*
+ * For dynamic PHB numbering: used/free PHBs tracking bitmap.
+ * Accesses to this bitmap should be protected by hose_spinlock.
+ */
+static DECLARE_BITMAP(phb_bitmap, MAX_PHBS);
 
 /* ISA Memory physical address */
 resource_size_t isa_mem_base;
@@ -64,6 +71,45 @@ struct dma_map_ops *get_pci_dma_ops(void)
 }
 EXPORT_SYMBOL(get_pci_dma_ops);
 
+/*
+ * This function should run under locking protection, specifically
+ * hose_spinlock.
+ */
+static int get_phb_number(struct device_node *dn)
+{
+	int ret, phb_id = -1;
+	u32 prop_32;
+	u64 prop;
+
+	/*
+	 * Try fixed PHB numbering first, by checking archs and reading
+	 * the respective device-tree properties. Firstly, try powernv by
+	 * reading "ibm,opal-phbid", only present in OPAL environment.
+	 */
+	ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop);
+	if (ret) {
+		ret = of_property_read_u32_index(dn, "reg", 1, &prop_32);
+		prop = prop_32;
+	}
+
+	if (!ret)
+		phb_id = (int)(prop & (MAX_PHBS - 1));
+
+	/* We need to be sure to not use the same PHB number twice. */
+	if ((phb_id >= 0) && !test_and_set_bit(phb_id, phb_bitmap))
+		return phb_id;
+
+	/*
+	 * If not pseries nor powernv, or if fixed PHB numbering tried to add
+	 * the same PHB number twice, then fallback to dynamic PHB numbering.
+	 */
+	phb_id = find_first_zero_bit(phb_bitmap, MAX_PHBS);
+	BUG_ON(phb_id >= MAX_PHBS);
+	set_bit(phb_id, phb_bitmap);
+
+	return phb_id;
+}
+
 struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
 {
 	struct pci_controller *phb;
@@ -72,7 +118,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
 	if (phb == NULL)
 		return NULL;
 	spin_lock(&hose_spinlock);
-	phb->global_number = global_phb_number++;
+	phb->global_number = get_phb_number(dev);
 	list_add_tail(&phb->list_node, &hose_list);
 	spin_unlock(&hose_spinlock);
 	phb->dn = dev;
@@ -94,6 +140,11 @@ EXPORT_SYMBOL_GPL(pcibios_alloc_controller);
 void pcibios_free_controller(struct pci_controller *phb)
 {
 	spin_lock(&hose_spinlock);
+
+	/* Clear bit of phb_bitmap to allow reuse of this PHB number. */
+	if (phb->global_number < MAX_PHBS)
+		clear_bit(phb->global_number, phb_bitmap);
+
 	list_del(&phb->list_node);
 	spin_unlock(&hose_spinlock);
 
@@ -103,6 +154,42 @@ void pcibios_free_controller(struct pci_controller *phb)
 EXPORT_SYMBOL_GPL(pcibios_free_controller);
 
 /*
+ * This function is used to call pcibios_free_controller()
+ * in a deferred manner: a callback from the PCI subsystem.
+ *
+ * _*DO NOT*_ call pcibios_free_controller() explicitly if
+ * this is used (or it may access an invalid *phb pointer).
+ *
+ * The callback occurs when all references to the root bus
+ * are dropped (e.g., child buses/devices and their users).
+ *
+ * It's called as .release_fn() of 'struct pci_host_bridge'
+ * which is associated with the 'struct pci_controller.bus'
+ * (root bus) - it expects .release_data to hold a pointer
+ * to 'struct pci_controller'.
+ *
+ * In order to use it, register .release_fn()/release_data
+ * like this:
+ *
+ * pci_set_host_bridge_release(bridge,
+ *                             pcibios_free_controller_deferred
+ *                             (void *) phb);
+ *
+ * e.g. in the pcibios_root_bridge_prepare() callback from
+ * pci_create_root_bus().
+ */
+void pcibios_free_controller_deferred(struct pci_host_bridge *bridge)
+{
+	struct pci_controller *phb = (struct pci_controller *)
+					 bridge->release_data;
+
+	pr_debug("domain %d, dynamic %d\n", phb->global_number, phb->is_dynamic);
+
+	pcibios_free_controller(phb);
+}
+EXPORT_SYMBOL_GPL(pcibios_free_controller_deferred);
+
+/*
  * The function is used to return the minimal alignment
  * for memory or I/O windows of the associated P2P bridge.
  * By default, 4KiB alignment for I/O windows and 1MiB for
@@ -124,6 +211,14 @@ resource_size_t pcibios_window_alignment(struct pci_bus *bus,
 	return 1;
 }
 
+void pcibios_setup_bridge(struct pci_bus *bus, unsigned long type)
+{
+	struct pci_controller *hose = pci_bus_to_host(bus);
+
+	if (hose->controller_ops.setup_bridge)
+		hose->controller_ops.setup_bridge(bus, type);
+}
+
 void pcibios_reset_secondary_bus(struct pci_dev *dev)
 {
 	struct pci_controller *phb = pci_bus_to_host(dev->bus);
@@ -356,36 +451,6 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
 }
 
 /*
- * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci
- * device mapping.
- */
-static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
-				      pgprot_t protection,
-				      enum pci_mmap_state mmap_state,
-				      int write_combine)
-{
-
-	/* Write combine is always 0 on non-memory space mappings. On
-	 * memory space, if the user didn't pass 1, we check for a
-	 * "prefetchable" resource. This is a bit hackish, but we use
-	 * this to workaround the inability of /sysfs to provide a write
-	 * combine bit
-	 */
-	if (mmap_state != pci_mmap_mem)
-		write_combine = 0;
-	else if (write_combine == 0) {
-		if (rp->flags & IORESOURCE_PREFETCH)
-			write_combine = 1;
-	}
-
-	/* XXX would be nice to have a way to ask for write-through */
-	if (write_combine)
-		return pgprot_noncached_wc(protection);
-	else
-		return pgprot_noncached(protection);
-}
-
-/*
  * This one is used by /dev/mem and fbdev who have no clue about the
  * PCI device, it tries to find the PCI device first and calls the
  * above routine
@@ -458,9 +523,10 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 		return -EINVAL;
 
 	vma->vm_pgoff = offset >> PAGE_SHIFT;
-	vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp,
-						  vma->vm_page_prot,
-						  mmap_state, write_combine);
+	if (write_combine)
+		vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot);
+	else
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
 	ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
 			       vma->vm_end - vma->vm_start, vma->vm_page_prot);
@@ -610,39 +676,25 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
 			  const struct resource *rsrc,
 			  resource_size_t *start, resource_size_t *end)
 {
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	resource_size_t offset = 0;
+	struct pci_bus_region region;
 
-	if (hose == NULL)
+	if (rsrc->flags & IORESOURCE_IO) {
+		pcibios_resource_to_bus(dev->bus, &region,
+					(struct resource *) rsrc);
+		*start = region.start;
+		*end = region.end;
 		return;
+	}
 
-	if (rsrc->flags & IORESOURCE_IO)
-		offset = (unsigned long)hose->io_base_virt - _IO_BASE;
-
-	/* We pass a fully fixed up address to userland for MMIO instead of
-	 * a BAR value because X is lame and expects to be able to use that
-	 * to pass to /dev/mem !
-	 *
-	 * That means that we'll have potentially 64 bits values where some
-	 * userland apps only expect 32 (like X itself since it thinks only
-	 * Sparc has 64 bits MMIO) but if we don't do that, we break it on
-	 * 32 bits CHRPs :-(
+	/* We pass a CPU physical address to userland for MMIO instead of a
+	 * BAR value because X is lame and expects to be able to use that
+	 * to pass to /dev/mem!
 	 *
-	 * Hopefully, the sysfs insterface is immune to that gunk. Once X
-	 * has been fixed (and the fix spread enough), we can re-enable the
-	 * 2 lines below and pass down a BAR value to userland. In that case
-	 * we'll also have to re-enable the matching code in
-	 * __pci_mmap_make_offset().
-	 *
-	 * BenH.
+	 * That means we may have 64-bit values where some apps only expect
+	 * 32 (like X itself since it thinks only Sparc has 64-bit MMIO).
 	 */
-#if 0
-	else if (rsrc->flags & IORESOURCE_MEM)
-		offset = hose->pci_mem_offset;
-#endif
-
-	*start = rsrc->start - offset;
-	*end = rsrc->end - offset;
+	*start = rsrc->start;
+	*end = rsrc->end;
 }
 
 /**
@@ -1362,8 +1414,10 @@ void __init pcibios_resource_survey(void)
 	/* Allocate and assign resources */
 	list_for_each_entry(b, &pci_root_buses, node)
 		pcibios_allocate_bus_resources(b);
-	pcibios_allocate_resources(0);
-	pcibios_allocate_resources(1);
+	if (!pci_has_flag(PCI_REASSIGN_ALL_RSRC)) {
+		pcibios_allocate_resources(0);
+		pcibios_allocate_resources(1);
+	}
 
 	/* Before we start assigning unassigned resource, we try to reserve
 	 * the low IO area and the VGA memory area if they intersect the
@@ -1436,8 +1490,12 @@ void pcibios_finish_adding_to_bus(struct pci_bus *bus)
 	/* Allocate bus and devices resources */
 	pcibios_allocate_bus_resources(bus);
 	pcibios_claim_one_bus(bus);
-	if (!pci_has_flag(PCI_PROBE_ONLY))
-		pci_assign_unassigned_bus_resources(bus);
+	if (!pci_has_flag(PCI_PROBE_ONLY)) {
+		if (bus->self)
+			pci_assign_unassigned_bridge_resources(bus->self);
+		else
+			pci_assign_unassigned_bus_resources(bus);
+	}
 
 	/* Fixup EEH */
 	eeh_add_device_tree_late(bus);
@@ -1485,9 +1543,9 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose,
 	res = &hose->io_resource;
 
 	if (!res->flags) {
-		pr_info("PCI: I/O resource not set for host"
-		       " bridge %s (domain %d)\n",
-		       hose->dn->full_name, hose->global_number);
+		pr_debug("PCI: I/O resource not set for host"
+			 " bridge %s (domain %d)\n",
+			 hose->dn->full_name, hose->global_number);
 	} else {
 		offset = pcibios_io_space_offset(hose);