Merge branch 'for-2.6.23' into merge

1 files changed, 454 insertions, 0 deletions

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
new file mode 100644
index 00000000000..faf5ef3e90d
--- /dev/null
+++ b/arch/powerpc/kernel/pci-common.c
@@ -0,0 +1,454 @@
+/*
+ * Contains common pci routines for ALL ppc platform
+ * (based on pci_32.c and pci_64.c)
+ *
+ * Port for PPC64 David Engebretsen, IBM Corp.
+ * Contains common pci routines for ppc64 platform, pSeries and iSeries brands.
+ *
+ * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM
+ *   Rework, based on alpha PCI code.
+ *
+ * Common pmac/prep/chrp pci routines. -- Cort
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/mm.h>
+#include <linux/list.h>
+#include <linux/syscalls.h>
+#include <linux/irq.h>
+#include <linux/vmalloc.h>
+
+#include <asm/processor.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/pci-bridge.h>
+#include <asm/byteorder.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+#include <asm/firmware.h>
+
+#ifdef DEBUG
+#include <asm/udbg.h>
+#define DBG(fmt...) printk(fmt)
+#else
+#define DBG(fmt...)
+#endif
+
+static DEFINE_SPINLOCK(hose_spinlock);
+
+/* XXX kill that some day ... */
+int global_phb_number;		/* Global phb counter */
+
+extern struct list_head hose_list;
+
+/*
+ * pci_controller(phb) initialized common variables.
+ */
+static void __devinit pci_setup_pci_controller(struct pci_controller *hose)
+{
+	memset(hose, 0, sizeof(struct pci_controller));
+
+	spin_lock(&hose_spinlock);
+	hose->global_number = global_phb_number++;
+	list_add_tail(&hose->list_node, &hose_list);
+	spin_unlock(&hose_spinlock);
+}
+
+struct pci_controller * pcibios_alloc_controller(struct device_node *dev)
+{
+	struct pci_controller *phb;
+
+	if (mem_init_done)
+		phb = kmalloc(sizeof(struct pci_controller), GFP_KERNEL);
+	else
+		phb = alloc_bootmem(sizeof (struct pci_controller));
+	if (phb == NULL)
+		return NULL;
+	pci_setup_pci_controller(phb);
+	phb->arch_data = dev;
+	phb->is_dynamic = mem_init_done;
+#ifdef CONFIG_PPC64
+	if (dev) {
+		int nid = of_node_to_nid(dev);
+
+		if (nid < 0 || !node_online(nid))
+			nid = -1;
+
+		PHB_SET_NODE(phb, nid);
+	}
+#endif
+	return phb;
+}
+
+void pcibios_free_controller(struct pci_controller *phb)
+{
+	spin_lock(&hose_spinlock);
+	list_del(&phb->list_node);
+	spin_unlock(&hose_spinlock);
+
+	if (phb->is_dynamic)
+		kfree(phb);
+}
+
+/*
+ * Return the domain number for this bus.
+ */
+int pci_domain_nr(struct pci_bus *bus)
+{
+	if (firmware_has_feature(FW_FEATURE_ISERIES))
+		return 0;
+	else {
+		struct pci_controller *hose = pci_bus_to_host(bus);
+
+		return hose->global_number;
+	}
+}
+
+EXPORT_SYMBOL(pci_domain_nr);
+
+#ifdef CONFIG_PPC_OF
+
+/* This routine is meant to be used early during boot, when the
+ * PCI bus numbers have not yet been assigned, and you need to
+ * issue PCI config cycles to an OF device.
+ * It could also be used to "fix" RTAS config cycles if you want
+ * to set pci_assign_all_buses to 1 and still use RTAS for PCI
+ * config cycles.
+ */
+struct pci_controller* pci_find_hose_for_OF_device(struct device_node* node)
+{
+	if (!have_of)
+		return NULL;
+	while(node) {
+		struct pci_controller *hose, *tmp;
+		list_for_each_entry_safe(hose, tmp, &hose_list, list_node)
+			if (hose->arch_data == node)
+				return hose;
+		node = node->parent;
+	}
+	return NULL;
+}
+
+static ssize_t pci_show_devspec(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct pci_dev *pdev;
+	struct device_node *np;
+
+	pdev = to_pci_dev (dev);
+	np = pci_device_to_OF_node(pdev);
+	if (np == NULL || np->full_name == NULL)
+		return 0;
+	return sprintf(buf, "%s", np->full_name);
+}
+static DEVICE_ATTR(devspec, S_IRUGO, pci_show_devspec, NULL);
+#endif /* CONFIG_PPC_OF */
+
+/* Add sysfs properties */
+void pcibios_add_platform_entries(struct pci_dev *pdev)
+{
+#ifdef CONFIG_PPC_OF
+	device_create_file(&pdev->dev, &dev_attr_devspec);
+#endif /* CONFIG_PPC_OF */
+}
+
+char __init *pcibios_setup(char *str)
+{
+	return str;
+}
+
+/*
+ * Reads the interrupt pin to determine if interrupt is use by card.
+ * If the interrupt is used, then gets the interrupt line from the
+ * openfirmware and sets it in the pci_dev and pci_config line.
+ */
+int pci_read_irq_line(struct pci_dev *pci_dev)
+{
+	struct of_irq oirq;
+	unsigned int virq;
+
+	DBG("Try to map irq for %s...\n", pci_name(pci_dev));
+
+#ifdef DEBUG
+	memset(&oirq, 0xff, sizeof(oirq));
+#endif
+	/* Try to get a mapping from the device-tree */
+	if (of_irq_map_pci(pci_dev, &oirq)) {
+		u8 line, pin;
+
+		/* If that fails, lets fallback to what is in the config
+		 * space and map that through the default controller. We
+		 * also set the type to level low since that's what PCI
+		 * interrupts are. If your platform does differently, then
+		 * either provide a proper interrupt tree or don't use this
+		 * function.
+		 */
+		if (pci_read_config_byte(pci_dev, PCI_INTERRUPT_PIN, &pin))
+			return -1;
+		if (pin == 0)
+			return -1;
+		if (pci_read_config_byte(pci_dev, PCI_INTERRUPT_LINE, &line) ||
+		    line == 0xff) {
+			return -1;
+		}
+		DBG(" -> no map ! Using irq line %d from PCI config\n", line);
+
+		virq = irq_create_mapping(NULL, line);
+		if (virq != NO_IRQ)
+			set_irq_type(virq, IRQ_TYPE_LEVEL_LOW);
+	} else {
+		DBG(" -> got one, spec %d cells (0x%08x 0x%08x...) on %s\n",
+		    oirq.size, oirq.specifier[0], oirq.specifier[1],
+		    oirq.controller->full_name);
+
+		virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
+					     oirq.size);
+	}
+	if(virq == NO_IRQ) {
+		DBG(" -> failed to map !\n");
+		return -1;
+	}
+
+	DBG(" -> mapped to linux irq %d\n", virq);
+
+	pci_dev->irq = virq;
+
+	return 0;
+}
+EXPORT_SYMBOL(pci_read_irq_line);
+
+/*
+ * Platform support for /proc/bus/pci/X/Y mmap()s,
+ * modelled on the sparc64 implementation by Dave Miller.
+ *  -- paulus.
+ */
+
+/*
+ * Adjust vm_pgoff of VMA such that it is the physical page offset
+ * corresponding to the 32-bit pci bus offset for DEV requested by the user.
+ *
+ * Basically, the user finds the base address for his device which he wishes
+ * to mmap.  They read the 32-bit value from the config space base register,
+ * add whatever PAGE_SIZE multiple offset they wish, and feed this into the
+ * offset parameter of mmap on /proc/bus/pci/XXX for that device.
+ *
+ * Returns negative error code on failure, zero on success.
+ */
+static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
+					       resource_size_t *offset,
+					       enum pci_mmap_state mmap_state)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	unsigned long io_offset = 0;
+	int i, res_bit;
+
+	if (hose == 0)
+		return NULL;		/* should never happen */
+
+	/* If memory, add on the PCI bridge address offset */
+	if (mmap_state == pci_mmap_mem) {
+#if 0 /* See comment in pci_resource_to_user() for why this is disabled */
+		*offset += hose->pci_mem_offset;
+#endif
+		res_bit = IORESOURCE_MEM;
+	} else {
+		io_offset = (unsigned long)hose->io_base_virt - _IO_BASE;
+		*offset += io_offset;
+		res_bit = IORESOURCE_IO;
+	}
+
+	/*
+	 * Check that the offset requested corresponds to one of the
+	 * resources of the device.
+	 */
+	for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
+		struct resource *rp = &dev->resource[i];
+		int flags = rp->flags;
+
+		/* treat ROM as memory (should be already) */
+		if (i == PCI_ROM_RESOURCE)
+			flags |= IORESOURCE_MEM;
+
+		/* Active and same type? */
+		if ((flags & res_bit) == 0)
+			continue;
+
+		/* In the range of this resource? */
+		if (*offset < (rp->start & PAGE_MASK) || *offset > rp->end)
+			continue;
+
+		/* found it! construct the final physical address */
+		if (mmap_state == pci_mmap_io)
+			*offset += hose->io_base_phys - io_offset;
+		return rp;
+	}
+
+	return NULL;
+}
+
+/*
+ * 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)
+{
+	unsigned long prot = pgprot_val(protection);
+
+	/* 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 */
+	prot |= _PAGE_NO_CACHE;
+	if (write_combine)
+		prot &= ~_PAGE_GUARDED;
+	else
+		prot |= _PAGE_GUARDED;
+
+	return __pgprot(prot);
+}
+
+/*
+ * 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
+ */
+pgprot_t pci_phys_mem_access_prot(struct file *file,
+				  unsigned long pfn,
+				  unsigned long size,
+				  pgprot_t protection)
+{
+	struct pci_dev *pdev = NULL;
+	struct resource *found = NULL;
+	unsigned long prot = pgprot_val(protection);
+	unsigned long offset = pfn << PAGE_SHIFT;
+	int i;
+
+	if (page_is_ram(pfn))
+		return __pgprot(prot);
+
+	prot |= _PAGE_NO_CACHE | _PAGE_GUARDED;
+
+	for_each_pci_dev(pdev) {
+		for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
+			struct resource *rp = &pdev->resource[i];
+			int flags = rp->flags;
+
+			/* Active and same type? */
+			if ((flags & IORESOURCE_MEM) == 0)
+				continue;
+			/* In the range of this resource? */
+			if (offset < (rp->start & PAGE_MASK) ||
+			    offset > rp->end)
+				continue;
+			found = rp;
+			break;
+		}
+		if (found)
+			break;
+	}
+	if (found) {
+		if (found->flags & IORESOURCE_PREFETCH)
+			prot &= ~_PAGE_GUARDED;
+		pci_dev_put(pdev);
+	}
+
+	DBG("non-PCI map for %lx, prot: %lx\n", offset, prot);
+
+	return __pgprot(prot);
+}
+
+
+/*
+ * Perform the actual remap of the pages for a PCI device mapping, as
+ * appropriate for this architecture.  The region in the process to map
+ * is described by vm_start and vm_end members of VMA, the base physical
+ * address is found in vm_pgoff.
+ * The pci device structure is provided so that architectures may make mapping
+ * decisions on a per-device or per-bus basis.
+ *
+ * Returns a negative error code on failure, zero on success.
+ */
+int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+			enum pci_mmap_state mmap_state, int write_combine)
+{
+	resource_size_t offset = vma->vm_pgoff << PAGE_SHIFT;
+	struct resource *rp;
+	int ret;
+
+	rp = __pci_mmap_make_offset(dev, &offset, mmap_state);
+	if (rp == NULL)
+		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);
+
+	ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+			       vma->vm_end - vma->vm_start, vma->vm_page_prot);
+
+	return ret;
+}
+
+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;
+
+	if (hose == NULL)
+		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 :-(
+	 *
+	 * 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.
+	 */
+#if 0
+	else if (rsrc->flags & IORESOURCE_MEM)
+		offset = hose->pci_mem_offset;
+#endif
+
+	*start = rsrc->start - offset;
+	*end = rsrc->end - offset;
+}