initial_commit

107 files changed, 61530 insertions, 0 deletions

diff --git a/drivers/pci/.gitignore b/drivers/pci/.gitignore
new file mode 100644
index 00000000..f297ca8d
--- /dev/null
+++ b/drivers/pci/.gitignore
@@ -0,0 +1,4 @@
+classlist.h
+devlist.h
+gen-devlist
+
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
new file mode 100644
index 00000000..565ab525
--- /dev/null
+++ b/drivers/pci/Kconfig
@@ -0,0 +1,95 @@
+#
+# PCI configuration
+#
+config ARCH_SUPPORTS_MSI
+	bool
+	default n
+
+config PCI_MSI
+	bool "Message Signaled Interrupts (MSI and MSI-X)"
+	depends on PCI
+	depends on ARCH_SUPPORTS_MSI
+	help
+	   This allows device drivers to enable MSI (Message Signaled
+	   Interrupts).  Message Signaled Interrupts enable a device to
+	   generate an interrupt using an inbound Memory Write on its
+	   PCI bus instead of asserting a device IRQ pin.
+
+	   Use of PCI MSI interrupts can be disabled at kernel boot time
+	   by using the 'pci=nomsi' option.  This disables MSI for the
+	   entire system.
+
+	   If you don't know what to do here, say Y.
+
+config PCI_DEBUG
+	bool "PCI Debugging"
+	depends on PCI && DEBUG_KERNEL
+	help
+	  Say Y here if you want the PCI core to produce a bunch of debug
+	  messages to the system log.  Select this if you are having a
+	  problem with PCI support and want to see more of what is going on.
+
+	  When in doubt, say N.
+
+config PCI_STUB
+	tristate "PCI Stub driver"
+	depends on PCI
+	help
+	  Say Y or M here if you want be able to reserve a PCI device
+	  when it is going to be assigned to a guest operating system.
+
+	  When in doubt, say N.
+
+config XEN_PCIDEV_FRONTEND
+        tristate "Xen PCI Frontend"
+        depends on PCI && X86 && XEN
+        select HOTPLUG
+        select PCI_XEN
+	select XEN_XENBUS_FRONTEND
+        default y
+        help
+          The PCI device frontend driver allows the kernel to import arbitrary
+          PCI devices from a PCI backend to support PCI driver domains.
+
+config XEN_PCIDEV_FE_DEBUG
+        bool "Xen PCI Frontend debugging"
+        depends on XEN_PCIDEV_FRONTEND && PCI_DEBUG
+	help
+	  Say Y here if you want the Xen PCI frontend to produce a bunch of debug
+	  messages to the system log.  Select this if you are having a
+	  problem with Xen PCI frontend support and want to see more of what is
+	  going on.
+
+	  When in doubt, say N.
+
+config HT_IRQ
+	bool "Interrupts on hypertransport devices"
+	default y
+	depends on PCI && X86_LOCAL_APIC && X86_IO_APIC
+	help
+	   This allows native hypertransport devices to use interrupts.
+
+	   If unsure say Y.
+
+config PCI_IOV
+	bool "PCI IOV support"
+	depends on PCI
+	help
+	  I/O Virtualization is a PCI feature supported by some devices
+	  which allows them to create virtual devices which share their
+	  physical resources.
+
+	  If unsure, say N.
+
+config PCI_IOAPIC
+	bool
+	depends on PCI
+	depends on ACPI
+	depends on HOTPLUG
+	default y
+
+config PCI_LABEL
+	def_bool y if (DMI || ACPI)
+	select NLS
+
+source "drivers/pci/pcie/Kconfig"
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
new file mode 100644
index 00000000..094308e4
--- /dev/null
+++ b/drivers/pci/Makefile
@@ -0,0 +1,74 @@
+#
+# Makefile for the PCI bus specific drivers.
+#
+
+obj-y		+= access.o bus.o probe.o remove.o pci.o \
+			pci-driver.o search.o pci-sysfs.o rom.o setup-res.o \
+			irq.o vpd.o
+obj-$(CONFIG_PROC_FS) += proc.o
+obj-$(CONFIG_SYSFS) += slot.o
+
+obj-$(CONFIG_PCI_QUIRKS) += quirks.o
+
+# Build PCI Express stuff if needed
+obj-$(CONFIG_PCIEPORTBUS) += pcie/
+
+obj-$(CONFIG_PCI_IOAPIC) += ioapic.o
+
+obj-$(CONFIG_HOTPLUG) += hotplug.o
+
+# Build the PCI Hotplug drivers if we were asked to
+obj-$(CONFIG_HOTPLUG_PCI) += hotplug/
+ifdef CONFIG_HOTPLUG_PCI
+obj-y += hotplug-pci.o
+endif
+
+# Build the PCI MSI interrupt support
+obj-$(CONFIG_PCI_MSI) += msi.o
+
+# Build the Hypertransport interrupt support
+obj-$(CONFIG_HT_IRQ) += htirq.o
+
+# Build Intel IOMMU support
+obj-$(CONFIG_DMAR) += dmar.o iova.o intel-iommu.o
+
+obj-$(CONFIG_INTR_REMAP) += dmar.o intr_remapping.o
+
+obj-$(CONFIG_PCI_IOV) += iov.o
+
+#
+# Some architectures use the generic PCI setup functions
+#
+obj-$(CONFIG_X86) += setup-bus.o
+obj-$(CONFIG_ALPHA) += setup-bus.o setup-irq.o
+obj-$(CONFIG_ARM) += setup-bus.o setup-irq.o
+obj-$(CONFIG_UNICORE32) += setup-bus.o setup-irq.o
+obj-$(CONFIG_PARISC) += setup-bus.o
+obj-$(CONFIG_SUPERH) += setup-bus.o setup-irq.o
+obj-$(CONFIG_PPC) += setup-bus.o
+obj-$(CONFIG_MIPS) += setup-bus.o setup-irq.o
+obj-$(CONFIG_X86_VISWS) += setup-irq.o
+obj-$(CONFIG_MN10300) += setup-bus.o
+obj-$(CONFIG_MICROBLAZE) += setup-bus.o
+obj-$(CONFIG_TILE) += setup-bus.o setup-irq.o
+obj-$(CONFIG_SPARC_LEON) += setup-bus.o setup-irq.o
+
+#
+# ACPI Related PCI FW Functions
+# ACPI _DSM provided firmware instance and string name
+#
+obj-$(CONFIG_ACPI)    += pci-acpi.o
+
+# SMBIOS provided firmware instance and labels
+obj-$(CONFIG_PCI_LABEL) += pci-label.o
+
+# Cardbus & CompactPCI use setup-bus
+obj-$(CONFIG_HOTPLUG) += setup-bus.o
+
+obj-$(CONFIG_PCI_SYSCALL) += syscall.o
+
+obj-$(CONFIG_PCI_STUB) += pci-stub.o
+
+obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o
+
+ccflags-$(CONFIG_PCI_DEBUG) := -DDEBUG
diff --git a/drivers/pci/access.c b/drivers/pci/access.c
new file mode 100644
index 00000000..fdaa42aa
--- /dev/null
+++ b/drivers/pci/access.c
@@ -0,0 +1,447 @@
+#include <linux/delay.h>
+#include <linux/pci.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/ioport.h>
+#include <linux/wait.h>
+
+#include "pci.h"
+
+/*
+ * This interrupt-safe spinlock protects all accesses to PCI
+ * configuration space.
+ */
+
+static DEFINE_RAW_SPINLOCK(pci_lock);
+
+/*
+ *  Wrappers for all PCI configuration access functions.  They just check
+ *  alignment, do locking and call the low-level functions pointed to
+ *  by pci_dev->ops.
+ */
+
+#define PCI_byte_BAD 0
+#define PCI_word_BAD (pos & 1)
+#define PCI_dword_BAD (pos & 3)
+
+#define PCI_OP_READ(size,type,len) \
+int pci_bus_read_config_##size \
+	(struct pci_bus *bus, unsigned int devfn, int pos, type *value)	\
+{									\
+	int res;							\
+	unsigned long flags;						\
+	u32 data = 0;							\
+	if (PCI_##size##_BAD) return PCIBIOS_BAD_REGISTER_NUMBER;	\
+	raw_spin_lock_irqsave(&pci_lock, flags);			\
+	res = bus->ops->read(bus, devfn, pos, len, &data);		\
+	*value = (type)data;						\
+	raw_spin_unlock_irqrestore(&pci_lock, flags);		\
+	return res;							\
+}
+
+#define PCI_OP_WRITE(size,type,len) \
+int pci_bus_write_config_##size \
+	(struct pci_bus *bus, unsigned int devfn, int pos, type value)	\
+{									\
+	int res;							\
+	unsigned long flags;						\
+	if (PCI_##size##_BAD) return PCIBIOS_BAD_REGISTER_NUMBER;	\
+	raw_spin_lock_irqsave(&pci_lock, flags);			\
+	res = bus->ops->write(bus, devfn, pos, len, value);		\
+	raw_spin_unlock_irqrestore(&pci_lock, flags);		\
+	return res;							\
+}
+
+PCI_OP_READ(byte, u8, 1)
+PCI_OP_READ(word, u16, 2)
+PCI_OP_READ(dword, u32, 4)
+PCI_OP_WRITE(byte, u8, 1)
+PCI_OP_WRITE(word, u16, 2)
+PCI_OP_WRITE(dword, u32, 4)
+
+EXPORT_SYMBOL(pci_bus_read_config_byte);
+EXPORT_SYMBOL(pci_bus_read_config_word);
+EXPORT_SYMBOL(pci_bus_read_config_dword);
+EXPORT_SYMBOL(pci_bus_write_config_byte);
+EXPORT_SYMBOL(pci_bus_write_config_word);
+EXPORT_SYMBOL(pci_bus_write_config_dword);
+
+/**
+ * pci_bus_set_ops - Set raw operations of pci bus
+ * @bus:	pci bus struct
+ * @ops:	new raw operations
+ *
+ * Return previous raw operations
+ */
+struct pci_ops *pci_bus_set_ops(struct pci_bus *bus, struct pci_ops *ops)
+{
+	struct pci_ops *old_ops;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&pci_lock, flags);
+	old_ops = bus->ops;
+	bus->ops = ops;
+	raw_spin_unlock_irqrestore(&pci_lock, flags);
+	return old_ops;
+}
+EXPORT_SYMBOL(pci_bus_set_ops);
+
+/**
+ * pci_read_vpd - Read one entry from Vital Product Data
+ * @dev:	pci device struct
+ * @pos:	offset in vpd space
+ * @count:	number of bytes to read
+ * @buf:	pointer to where to store result
+ *
+ */
+ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf)
+{
+	if (!dev->vpd || !dev->vpd->ops)
+		return -ENODEV;
+	return dev->vpd->ops->read(dev, pos, count, buf);
+}
+EXPORT_SYMBOL(pci_read_vpd);
+
+/**
+ * pci_write_vpd - Write entry to Vital Product Data
+ * @dev:	pci device struct
+ * @pos:	offset in vpd space
+ * @count:	number of bytes to write
+ * @buf:	buffer containing write data
+ *
+ */
+ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf)
+{
+	if (!dev->vpd || !dev->vpd->ops)
+		return -ENODEV;
+	return dev->vpd->ops->write(dev, pos, count, buf);
+}
+EXPORT_SYMBOL(pci_write_vpd);
+
+/*
+ * The following routines are to prevent the user from accessing PCI config
+ * space when it's unsafe to do so.  Some devices require this during BIST and
+ * we're required to prevent it during D-state transitions.
+ *
+ * We have a bit per device to indicate it's blocked and a global wait queue
+ * for callers to sleep on until devices are unblocked.
+ */
+static DECLARE_WAIT_QUEUE_HEAD(pci_ucfg_wait);
+
+static noinline void pci_wait_ucfg(struct pci_dev *dev)
+{
+	DECLARE_WAITQUEUE(wait, current);
+
+	__add_wait_queue(&pci_ucfg_wait, &wait);
+	do {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		raw_spin_unlock_irq(&pci_lock);
+		schedule();
+		raw_spin_lock_irq(&pci_lock);
+	} while (dev->block_ucfg_access);
+	__remove_wait_queue(&pci_ucfg_wait, &wait);
+}
+
+/* Returns 0 on success, negative values indicate error. */
+#define PCI_USER_READ_CONFIG(size,type)					\
+int pci_user_read_config_##size						\
+	(struct pci_dev *dev, int pos, type *val)			\
+{									\
+	int ret = 0;							\
+	u32 data = -1;							\
+	if (PCI_##size##_BAD)						\
+		return -EINVAL;						\
+	raw_spin_lock_irq(&pci_lock);				\
+	if (unlikely(dev->block_ucfg_access)) pci_wait_ucfg(dev);	\
+	ret = dev->bus->ops->read(dev->bus, dev->devfn,			\
+					pos, sizeof(type), &data);	\
+	raw_spin_unlock_irq(&pci_lock);				\
+	*val = (type)data;						\
+	if (ret > 0)							\
+		ret = -EINVAL;						\
+	return ret;							\
+}
+
+/* Returns 0 on success, negative values indicate error. */
+#define PCI_USER_WRITE_CONFIG(size,type)				\
+int pci_user_write_config_##size					\
+	(struct pci_dev *dev, int pos, type val)			\
+{									\
+	int ret = -EIO;							\
+	if (PCI_##size##_BAD)						\
+		return -EINVAL;						\
+	raw_spin_lock_irq(&pci_lock);				\
+	if (unlikely(dev->block_ucfg_access)) pci_wait_ucfg(dev);	\
+	ret = dev->bus->ops->write(dev->bus, dev->devfn,		\
+					pos, sizeof(type), val);	\
+	raw_spin_unlock_irq(&pci_lock);				\
+	if (ret > 0)							\
+		ret = -EINVAL;						\
+	return ret;							\
+}
+
+PCI_USER_READ_CONFIG(byte, u8)
+PCI_USER_READ_CONFIG(word, u16)
+PCI_USER_READ_CONFIG(dword, u32)
+PCI_USER_WRITE_CONFIG(byte, u8)
+PCI_USER_WRITE_CONFIG(word, u16)
+PCI_USER_WRITE_CONFIG(dword, u32)
+
+/* VPD access through PCI 2.2+ VPD capability */
+
+#define PCI_VPD_PCI22_SIZE (PCI_VPD_ADDR_MASK + 1)
+
+struct pci_vpd_pci22 {
+	struct pci_vpd base;
+	struct mutex lock;
+	u16	flag;
+	bool	busy;
+	u8	cap;
+};
+
+/*
+ * Wait for last operation to complete.
+ * This code has to spin since there is no other notification from the PCI
+ * hardware. Since the VPD is often implemented by serial attachment to an
+ * EEPROM, it may take many milliseconds to complete.
+ *
+ * Returns 0 on success, negative values indicate error.
+ */
+static int pci_vpd_pci22_wait(struct pci_dev *dev)
+{
+	struct pci_vpd_pci22 *vpd =
+		container_of(dev->vpd, struct pci_vpd_pci22, base);
+	unsigned long timeout = jiffies + HZ/20 + 2;
+	u16 status;
+	int ret;
+
+	if (!vpd->busy)
+		return 0;
+
+	for (;;) {
+		ret = pci_user_read_config_word(dev, vpd->cap + PCI_VPD_ADDR,
+						&status);
+		if (ret < 0)
+			return ret;
+
+		if ((status & PCI_VPD_ADDR_F) == vpd->flag) {
+			vpd->busy = false;
+			return 0;
+		}
+
+		if (time_after(jiffies, timeout)) {
+			dev_printk(KERN_DEBUG, &dev->dev,
+				   "vpd r/w failed.  This is likely a firmware "
+				   "bug on this device.  Contact the card "
+				   "vendor for a firmware update.");
+			return -ETIMEDOUT;
+		}
+		if (fatal_signal_pending(current))
+			return -EINTR;
+		if (!cond_resched())
+			udelay(10);
+	}
+}
+
+static ssize_t pci_vpd_pci22_read(struct pci_dev *dev, loff_t pos, size_t count,
+				  void *arg)
+{
+	struct pci_vpd_pci22 *vpd =
+		container_of(dev->vpd, struct pci_vpd_pci22, base);
+	int ret;
+	loff_t end = pos + count;
+	u8 *buf = arg;
+
+	if (pos < 0 || pos > vpd->base.len || end > vpd->base.len)
+		return -EINVAL;
+
+	if (mutex_lock_killable(&vpd->lock))
+		return -EINTR;
+
+	ret = pci_vpd_pci22_wait(dev);
+	if (ret < 0)
+		goto out;
+
+	while (pos < end) {
+		u32 val;
+		unsigned int i, skip;
+
+		ret = pci_user_write_config_word(dev, vpd->cap + PCI_VPD_ADDR,
+						 pos & ~3);
+		if (ret < 0)
+			break;
+		vpd->busy = true;
+		vpd->flag = PCI_VPD_ADDR_F;
+		ret = pci_vpd_pci22_wait(dev);
+		if (ret < 0)
+			break;
+
+		ret = pci_user_read_config_dword(dev, vpd->cap + PCI_VPD_DATA, &val);
+		if (ret < 0)
+			break;
+
+		skip = pos & 3;
+		for (i = 0;  i < sizeof(u32); i++) {
+			if (i >= skip) {
+				*buf++ = val;
+				if (++pos == end)
+					break;
+			}
+			val >>= 8;
+		}
+	}
+out:
+	mutex_unlock(&vpd->lock);
+	return ret ? ret : count;
+}
+
+static ssize_t pci_vpd_pci22_write(struct pci_dev *dev, loff_t pos, size_t count,
+				   const void *arg)
+{
+	struct pci_vpd_pci22 *vpd =
+		container_of(dev->vpd, struct pci_vpd_pci22, base);
+	const u8 *buf = arg;
+	loff_t end = pos + count;
+	int ret = 0;
+
+	if (pos < 0 || (pos & 3) || (count & 3) || end > vpd->base.len)
+		return -EINVAL;
+
+	if (mutex_lock_killable(&vpd->lock))
+		return -EINTR;
+
+	ret = pci_vpd_pci22_wait(dev);
+	if (ret < 0)
+		goto out;
+
+	while (pos < end) {
+		u32 val;
+
+		val = *buf++;
+		val |= *buf++ << 8;
+		val |= *buf++ << 16;
+		val |= *buf++ << 24;
+
+		ret = pci_user_write_config_dword(dev, vpd->cap + PCI_VPD_DATA, val);
+		if (ret < 0)
+			break;
+		ret = pci_user_write_config_word(dev, vpd->cap + PCI_VPD_ADDR,
+						 pos | PCI_VPD_ADDR_F);
+		if (ret < 0)
+			break;
+
+		vpd->busy = true;
+		vpd->flag = 0;
+		ret = pci_vpd_pci22_wait(dev);
+		if (ret < 0)
+			break;
+
+		pos += sizeof(u32);
+	}
+out:
+	mutex_unlock(&vpd->lock);
+	return ret ? ret : count;
+}
+
+static void pci_vpd_pci22_release(struct pci_dev *dev)
+{
+	kfree(container_of(dev->vpd, struct pci_vpd_pci22, base));
+}
+
+static const struct pci_vpd_ops pci_vpd_pci22_ops = {
+	.read = pci_vpd_pci22_read,
+	.write = pci_vpd_pci22_write,
+	.release = pci_vpd_pci22_release,
+};
+
+int pci_vpd_pci22_init(struct pci_dev *dev)
+{
+	struct pci_vpd_pci22 *vpd;
+	u8 cap;
+
+	cap = pci_find_capability(dev, PCI_CAP_ID_VPD);
+	if (!cap)
+		return -ENODEV;
+	vpd = kzalloc(sizeof(*vpd), GFP_ATOMIC);
+	if (!vpd)
+		return -ENOMEM;
+
+	vpd->base.len = PCI_VPD_PCI22_SIZE;
+	vpd->base.ops = &pci_vpd_pci22_ops;
+	mutex_init(&vpd->lock);
+	vpd->cap = cap;
+	vpd->busy = false;
+	dev->vpd = &vpd->base;
+	return 0;
+}
+
+/**
+ * pci_vpd_truncate - Set available Vital Product Data size
+ * @dev:	pci device struct
+ * @size:	available memory in bytes
+ *
+ * Adjust size of available VPD area.
+ */
+int pci_vpd_truncate(struct pci_dev *dev, size_t size)
+{
+	if (!dev->vpd)
+		return -EINVAL;
+
+	/* limited by the access method */
+	if (size > dev->vpd->len)
+		return -EINVAL;
+
+	dev->vpd->len = size;
+	if (dev->vpd->attr)
+		dev->vpd->attr->size = size;
+
+	return 0;
+}
+EXPORT_SYMBOL(pci_vpd_truncate);
+
+/**
+ * pci_block_user_cfg_access - Block userspace PCI config reads/writes
+ * @dev:	pci device struct
+ *
+ * When user access is blocked, any reads or writes to config space will
+ * sleep until access is unblocked again.  We don't allow nesting of
+ * block/unblock calls.
+ */
+void pci_block_user_cfg_access(struct pci_dev *dev)
+{
+	unsigned long flags;
+	int was_blocked;
+
+	raw_spin_lock_irqsave(&pci_lock, flags);
+	was_blocked = dev->block_ucfg_access;
+	dev->block_ucfg_access = 1;
+	raw_spin_unlock_irqrestore(&pci_lock, flags);
+
+	/* If we BUG() inside the pci_lock, we're guaranteed to hose
+	 * the machine */
+	BUG_ON(was_blocked);
+}
+EXPORT_SYMBOL_GPL(pci_block_user_cfg_access);
+
+/**
+ * pci_unblock_user_cfg_access - Unblock userspace PCI config reads/writes
+ * @dev:	pci device struct
+ *
+ * This function allows userspace PCI config accesses to resume.
+ */
+void pci_unblock_user_cfg_access(struct pci_dev *dev)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&pci_lock, flags);
+
+	/* This indicates a problem in the caller, but we don't need
+	 * to kill them, unlike a double-block above. */
+	WARN_ON(!dev->block_ucfg_access);
+
+	dev->block_ucfg_access = 0;
+	wake_up_all(&pci_ucfg_wait);
+	raw_spin_unlock_irqrestore(&pci_lock, flags);
+}
+EXPORT_SYMBOL_GPL(pci_unblock_user_cfg_access);
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
new file mode 100644
index 00000000..1e2ad92a
--- /dev/null
+++ b/drivers/pci/bus.c
@@ -0,0 +1,301 @@
+/*
+ *	drivers/pci/bus.c
+ *
+ * From setup-res.c, by:
+ *	Dave Rusling (david.rusling@reo.mts.dec.com)
+ *	David Mosberger (davidm@cs.arizona.edu)
+ *	David Miller (davem@redhat.com)
+ *	Ivan Kokshaysky (ink@jurassic.park.msu.ru)
+ */
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/errno.h>
+#include <linux/ioport.h>
+#include <linux/proc_fs.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+
+#include "pci.h"
+
+void pci_bus_add_resource(struct pci_bus *bus, struct resource *res,
+			  unsigned int flags)
+{
+	struct pci_bus_resource *bus_res;
+
+	bus_res = kzalloc(sizeof(struct pci_bus_resource), GFP_KERNEL);
+	if (!bus_res) {
+		dev_err(&bus->dev, "can't add %pR resource\n", res);
+		return;
+	}
+
+	bus_res->res = res;
+	bus_res->flags = flags;
+	list_add_tail(&bus_res->list, &bus->resources);
+}
+
+struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n)
+{
+	struct pci_bus_resource *bus_res;
+
+	if (n < PCI_BRIDGE_RESOURCE_NUM)
+		return bus->resource[n];
+
+	n -= PCI_BRIDGE_RESOURCE_NUM;
+	list_for_each_entry(bus_res, &bus->resources, list) {
+		if (n-- == 0)
+			return bus_res->res;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(pci_bus_resource_n);
+
+void pci_bus_remove_resources(struct pci_bus *bus)
+{
+	struct pci_bus_resource *bus_res, *tmp;
+	int i;
+
+	for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++)
+		bus->resource[i] = NULL;
+
+	list_for_each_entry_safe(bus_res, tmp, &bus->resources, list) {
+		list_del(&bus_res->list);
+		kfree(bus_res);
+	}
+}
+
+/**
+ * pci_bus_alloc_resource - allocate a resource from a parent bus
+ * @bus: PCI bus
+ * @res: resource to allocate
+ * @size: size of resource to allocate
+ * @align: alignment of resource to allocate
+ * @min: minimum /proc/iomem address to allocate
+ * @type_mask: IORESOURCE_* type flags
+ * @alignf: resource alignment function
+ * @alignf_data: data argument for resource alignment function
+ *
+ * Given the PCI bus a device resides on, the size, minimum address,
+ * alignment and type, try to find an acceptable resource allocation
+ * for a specific device resource.
+ */
+int
+pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res,
+		resource_size_t size, resource_size_t align,
+		resource_size_t min, unsigned int type_mask,
+		resource_size_t (*alignf)(void *,
+					  const struct resource *,
+					  resource_size_t,
+					  resource_size_t),
+		void *alignf_data)
+{
+	int i, ret = -ENOMEM;
+	struct resource *r;
+	resource_size_t max = -1;
+
+	type_mask |= IORESOURCE_IO | IORESOURCE_MEM;
+
+	/* don't allocate too high if the pref mem doesn't support 64bit*/
+	if (!(res->flags & IORESOURCE_MEM_64))
+		max = PCIBIOS_MAX_MEM_32;
+
+	pci_bus_for_each_resource(bus, r, i) {
+		if (!r)
+			continue;
+
+		/* type_mask must match */
+		if ((res->flags ^ r->flags) & type_mask)
+			continue;
+
+		/* We cannot allocate a non-prefetching resource
+		   from a pre-fetching area */
+		if ((r->flags & IORESOURCE_PREFETCH) &&
+		    !(res->flags & IORESOURCE_PREFETCH))
+			continue;
+
+		/* Ok, try it out.. */
+		ret = allocate_resource(r, res, size,
+					r->start ? : min,
+					max, align,
+					alignf, alignf_data);
+		if (ret == 0)
+			break;
+	}
+	return ret;
+}
+
+/**
+ * pci_bus_add_device - add a single device
+ * @dev: device to add
+ *
+ * This adds a single pci device to the global
+ * device list and adds sysfs and procfs entries
+ */
+int pci_bus_add_device(struct pci_dev *dev)
+{
+	int retval;
+	retval = device_add(&dev->dev);
+	if (retval)
+		return retval;
+
+	dev->is_added = 1;
+	pci_proc_attach_device(dev);
+	pci_create_sysfs_dev_files(dev);
+	return 0;
+}
+
+/**
+ * pci_bus_add_child - add a child bus
+ * @bus: bus to add
+ *
+ * This adds sysfs entries for a single bus
+ */
+int pci_bus_add_child(struct pci_bus *bus)
+{
+	int retval;
+
+	if (bus->bridge)
+		bus->dev.parent = bus->bridge;
+
+	retval = device_register(&bus->dev);
+	if (retval)
+		return retval;
+
+	bus->is_added = 1;
+
+	/* Create legacy_io and legacy_mem files for this bus */
+	pci_create_legacy_files(bus);
+
+	return retval;
+}
+
+/**
+ * pci_bus_add_devices - insert newly discovered PCI devices
+ * @bus: bus to check for new devices
+ *
+ * Add newly discovered PCI devices (which are on the bus->devices
+ * list) to the global PCI device list, add the sysfs and procfs
+ * entries.  Where a bridge is found, add the discovered bus to
+ * the parents list of child buses, and recurse (breadth-first
+ * to be compatible with 2.4)
+ *
+ * Call hotplug for each new devices.
+ */
+void pci_bus_add_devices(const struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+	struct pci_bus *child;
+	int retval;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		/* Skip already-added devices */
+		if (dev->is_added)
+			continue;
+		retval = pci_bus_add_device(dev);
+		if (retval)
+			dev_err(&dev->dev, "Error adding device, continuing\n");
+	}
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		BUG_ON(!dev->is_added);
+
+		child = dev->subordinate;
+		/*
+		 * If there is an unattached subordinate bus, attach
+		 * it and then scan for unattached PCI devices.
+		 */
+		if (!child)
+			continue;
+		if (list_empty(&child->node)) {
+			down_write(&pci_bus_sem);
+			list_add_tail(&child->node, &dev->bus->children);
+			up_write(&pci_bus_sem);
+		}
+		pci_bus_add_devices(child);
+
+		/*
+		 * register the bus with sysfs as the parent is now
+		 * properly registered.
+		 */
+		if (child->is_added)
+			continue;
+		retval = pci_bus_add_child(child);
+		if (retval)
+			dev_err(&dev->dev, "Error adding bus, continuing\n");
+	}
+}
+
+void pci_enable_bridges(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+	int retval;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		if (dev->subordinate) {
+			if (!pci_is_enabled(dev)) {
+				retval = pci_enable_device(dev);
+				if (retval)
+					dev_err(&dev->dev, "Error enabling bridge (%d), continuing\n", retval);
+				pci_set_master(dev);
+			}
+			pci_enable_bridges(dev->subordinate);
+		}
+	}
+}
+
+/** pci_walk_bus - walk devices on/under bus, calling callback.
+ *  @top      bus whose devices should be walked
+ *  @cb       callback to be called for each device found
+ *  @userdata arbitrary pointer to be passed to callback.
+ *
+ *  Walk the given bus, including any bridged devices
+ *  on buses under this bus.  Call the provided callback
+ *  on each device found.
+ *
+ *  We check the return of @cb each time. If it returns anything
+ *  other than 0, we break out.
+ *
+ */
+void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
+		  void *userdata)
+{
+	struct pci_dev *dev;
+	struct pci_bus *bus;
+	struct list_head *next;
+	int retval;
+
+	bus = top;
+	down_read(&pci_bus_sem);
+	next = top->devices.next;
+	for (;;) {
+		if (next == &bus->devices) {
+			/* end of this bus, go up or finish */
+			if (bus == top)
+				break;
+			next = bus->self->bus_list.next;
+			bus = bus->self->bus;
+			continue;
+		}
+		dev = list_entry(next, struct pci_dev, bus_list);
+		if (dev->subordinate) {
+			/* this is a pci-pci bridge, do its devices next */
+			next = dev->subordinate->devices.next;
+			bus = dev->subordinate;
+		} else
+			next = dev->bus_list.next;
+
+		/* Run device routines with the device locked */
+		device_lock(&dev->dev);
+		retval = cb(dev, userdata);
+		device_unlock(&dev->dev);
+		if (retval)
+			break;
+	}
+	up_read(&pci_bus_sem);
+}
+EXPORT_SYMBOL_GPL(pci_walk_bus);
+
+EXPORT_SYMBOL(pci_bus_alloc_resource);
+EXPORT_SYMBOL_GPL(pci_bus_add_device);
+EXPORT_SYMBOL(pci_bus_add_devices);
+EXPORT_SYMBOL(pci_enable_bridges);
diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
new file mode 100644
index 00000000..6dcc7e2d
--- /dev/null
+++ b/drivers/pci/dmar.c
@@ -0,0 +1,1461 @@
+/*
+ * Copyright (c) 2006, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Copyright (C) 2006-2008 Intel Corporation
+ * Author: Ashok Raj <ashok.raj@intel.com>
+ * Author: Shaohua Li <shaohua.li@intel.com>
+ * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
+ *
+ * This file implements early detection/parsing of Remapping Devices
+ * reported to OS through BIOS via DMA remapping reporting (DMAR) ACPI
+ * tables.
+ *
+ * These routines are used by both DMA-remapping and Interrupt-remapping
+ */
+
+#include <linux/pci.h>
+#include <linux/dmar.h>
+#include <linux/iova.h>
+#include <linux/intel-iommu.h>
+#include <linux/timer.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/tboot.h>
+#include <linux/dmi.h>
+#include <linux/slab.h>
+#include <asm/iommu_table.h>
+
+#define PREFIX "DMAR: "
+
+/* No locks are needed as DMA remapping hardware unit
+ * list is constructed at boot time and hotplug of
+ * these units are not supported by the architecture.
+ */
+LIST_HEAD(dmar_drhd_units);
+
+static struct acpi_table_header * __initdata dmar_tbl;
+static acpi_size dmar_tbl_size;
+
+static void __init dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
+{
+	/*
+	 * add INCLUDE_ALL at the tail, so scan the list will find it at
+	 * the very end.
+	 */
+	if (drhd->include_all)
+		list_add_tail(&drhd->list, &dmar_drhd_units);
+	else
+		list_add(&drhd->list, &dmar_drhd_units);
+}
+
+static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope,
+					   struct pci_dev **dev, u16 segment)
+{
+	struct pci_bus *bus;
+	struct pci_dev *pdev = NULL;
+	struct acpi_dmar_pci_path *path;
+	int count;
+
+	bus = pci_find_bus(segment, scope->bus);
+	path = (struct acpi_dmar_pci_path *)(scope + 1);
+	count = (scope->length - sizeof(struct acpi_dmar_device_scope))
+		/ sizeof(struct acpi_dmar_pci_path);
+
+	while (count) {
+		if (pdev)
+			pci_dev_put(pdev);
+		/*
+		 * Some BIOSes list non-exist devices in DMAR table, just
+		 * ignore it
+		 */
+		if (!bus) {
+			printk(KERN_WARNING
+			PREFIX "Device scope bus [%d] not found\n",
+			scope->bus);
+			break;
+		}
+		pdev = pci_get_slot(bus, PCI_DEVFN(path->dev, path->fn));
+		if (!pdev) {
+			printk(KERN_WARNING PREFIX
+			"Device scope device [%04x:%02x:%02x.%02x] not found\n",
+				segment, bus->number, path->dev, path->fn);
+			break;
+		}
+		path ++;
+		count --;
+		bus = pdev->subordinate;
+	}
+	if (!pdev) {
+		printk(KERN_WARNING PREFIX
+		"Device scope device [%04x:%02x:%02x.%02x] not found\n",
+		segment, scope->bus, path->dev, path->fn);
+		*dev = NULL;
+		return 0;
+	}
+	if ((scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT && \
+			pdev->subordinate) || (scope->entry_type == \
+			ACPI_DMAR_SCOPE_TYPE_BRIDGE && !pdev->subordinate)) {
+		pci_dev_put(pdev);
+		printk(KERN_WARNING PREFIX
+			"Device scope type does not match for %s\n",
+			 pci_name(pdev));
+		return -EINVAL;
+	}
+	*dev = pdev;
+	return 0;
+}
+
+static int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
+				       struct pci_dev ***devices, u16 segment)
+{
+	struct acpi_dmar_device_scope *scope;
+	void * tmp = start;
+	int index;
+	int ret;
+
+	*cnt = 0;
+	while (start < end) {
+		scope = start;
+		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT ||
+		    scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE)
+			(*cnt)++;
+		else if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_IOAPIC) {
+			printk(KERN_WARNING PREFIX
+			       "Unsupported device scope\n");
+		}
+		start += scope->length;
+	}
+	if (*cnt == 0)
+		return 0;
+
+	*devices = kcalloc(*cnt, sizeof(struct pci_dev *), GFP_KERNEL);
+	if (!*devices)
+		return -ENOMEM;
+
+	start = tmp;
+	index = 0;
+	while (start < end) {
+		scope = start;
+		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT ||
+		    scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE) {
+			ret = dmar_parse_one_dev_scope(scope,
+				&(*devices)[index], segment);
+			if (ret) {
+				kfree(*devices);
+				return ret;
+			}
+			index ++;
+		}
+		start += scope->length;
+	}
+
+	return 0;
+}
+
+/**
+ * dmar_parse_one_drhd - parses exactly one DMA remapping hardware definition
+ * structure which uniquely represent one DMA remapping hardware unit
+ * present in the platform
+ */
+static int __init
+dmar_parse_one_drhd(struct acpi_dmar_header *header)
+{
+	struct acpi_dmar_hardware_unit *drhd;
+	struct dmar_drhd_unit *dmaru;
+	int ret = 0;
+
+	drhd = (struct acpi_dmar_hardware_unit *)header;
+	dmaru = kzalloc(sizeof(*dmaru), GFP_KERNEL);
+	if (!dmaru)
+		return -ENOMEM;
+
+	dmaru->hdr = header;
+	dmaru->reg_base_addr = drhd->address;
+	dmaru->segment = drhd->segment;
+	dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */
+
+	ret = alloc_iommu(dmaru);
+	if (ret) {
+		kfree(dmaru);
+		return ret;
+	}
+	dmar_register_drhd_unit(dmaru);
+	return 0;
+}
+
+static int __init dmar_parse_dev(struct dmar_drhd_unit *dmaru)
+{
+	struct acpi_dmar_hardware_unit *drhd;
+	int ret = 0;
+
+	drhd = (struct acpi_dmar_hardware_unit *) dmaru->hdr;
+
+	if (dmaru->include_all)
+		return 0;
+
+	ret = dmar_parse_dev_scope((void *)(drhd + 1),
+				((void *)drhd) + drhd->header.length,
+				&dmaru->devices_cnt, &dmaru->devices,
+				drhd->segment);
+	if (ret) {
+		list_del(&dmaru->list);
+		kfree(dmaru);
+	}
+	return ret;
+}
+
+#ifdef CONFIG_DMAR
+LIST_HEAD(dmar_rmrr_units);
+
+static void __init dmar_register_rmrr_unit(struct dmar_rmrr_unit *rmrr)
+{
+	list_add(&rmrr->list, &dmar_rmrr_units);
+}
+
+
+static int __init
+dmar_parse_one_rmrr(struct acpi_dmar_header *header)
+{
+	struct acpi_dmar_reserved_memory *rmrr;
+	struct dmar_rmrr_unit *rmrru;
+
+	rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
+	if (!rmrru)
+		return -ENOMEM;
+
+	rmrru->hdr = header;
+	rmrr = (struct acpi_dmar_reserved_memory *)header;
+	rmrru->base_address = rmrr->base_address;
+	rmrru->end_address = rmrr->end_address;
+
+	dmar_register_rmrr_unit(rmrru);
+	return 0;
+}
+
+static int __init
+rmrr_parse_dev(struct dmar_rmrr_unit *rmrru)
+{
+	struct acpi_dmar_reserved_memory *rmrr;
+	int ret;
+
+	rmrr = (struct acpi_dmar_reserved_memory *) rmrru->hdr;
+	ret = dmar_parse_dev_scope((void *)(rmrr + 1),
+		((void *)rmrr) + rmrr->header.length,
+		&rmrru->devices_cnt, &rmrru->devices, rmrr->segment);
+
+	if (ret || (rmrru->devices_cnt == 0)) {
+		list_del(&rmrru->list);
+		kfree(rmrru);
+	}
+	return ret;
+}
+
+static LIST_HEAD(dmar_atsr_units);
+
+static int __init dmar_parse_one_atsr(struct acpi_dmar_header *hdr)
+{
+	struct acpi_dmar_atsr *atsr;
+	struct dmar_atsr_unit *atsru;
+
+	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
+	atsru = kzalloc(sizeof(*atsru), GFP_KERNEL);
+	if (!atsru)
+		return -ENOMEM;
+
+	atsru->hdr = hdr;
+	atsru->include_all = atsr->flags & 0x1;
+
+	list_add(&atsru->list, &dmar_atsr_units);
+
+	return 0;
+}
+
+static int __init atsr_parse_dev(struct dmar_atsr_unit *atsru)
+{
+	int rc;
+	struct acpi_dmar_atsr *atsr;
+
+	if (atsru->include_all)
+		return 0;
+
+	atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
+	rc = dmar_parse_dev_scope((void *)(atsr + 1),
+				(void *)atsr + atsr->header.length,
+				&atsru->devices_cnt, &atsru->devices,
+				atsr->segment);
+	if (rc || !atsru->devices_cnt) {
+		list_del(&atsru->list);
+		kfree(atsru);
+	}
+
+	return rc;
+}
+
+int dmar_find_matched_atsr_unit(struct pci_dev *dev)
+{
+	int i;
+	struct pci_bus *bus;
+	struct acpi_dmar_atsr *atsr;
+	struct dmar_atsr_unit *atsru;
+
+	dev = pci_physfn(dev);
+
+	list_for_each_entry(atsru, &dmar_atsr_units, list) {
+		atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
+		if (atsr->segment == pci_domain_nr(dev->bus))
+			goto found;
+	}
+
+	return 0;
+
+found:
+	for (bus = dev->bus; bus; bus = bus->parent) {
+		struct pci_dev *bridge = bus->self;
+
+		if (!bridge || !pci_is_pcie(bridge) ||
+		    bridge->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE)
+			return 0;
+
+		if (bridge->pcie_type == PCI_EXP_TYPE_ROOT_PORT) {
+			for (i = 0; i < atsru->devices_cnt; i++)
+				if (atsru->devices[i] == bridge)
+					return 1;
+			break;
+		}
+	}
+
+	if (atsru->include_all)
+		return 1;
+
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_ACPI_NUMA
+static int __init
+dmar_parse_one_rhsa(struct acpi_dmar_header *header)
+{
+	struct acpi_dmar_rhsa *rhsa;
+	struct dmar_drhd_unit *drhd;
+
+	rhsa = (struct acpi_dmar_rhsa *)header;
+	for_each_drhd_unit(drhd) {
+		if (drhd->reg_base_addr == rhsa->base_address) {
+			int node = acpi_map_pxm_to_node(rhsa->proximity_domain);
+
+			if (!node_online(node))
+				node = -1;
+			drhd->iommu->node = node;
+			return 0;
+		}
+	}
+	WARN_TAINT(
+		1, TAINT_FIRMWARE_WORKAROUND,
+		"Your BIOS is broken; RHSA refers to non-existent DMAR unit at %llx\n"
+		"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+		drhd->reg_base_addr,
+		dmi_get_system_info(DMI_BIOS_VENDOR),
+		dmi_get_system_info(DMI_BIOS_VERSION),
+		dmi_get_system_info(DMI_PRODUCT_VERSION));
+
+	return 0;
+}
+#endif
+
+static void __init
+dmar_table_print_dmar_entry(struct acpi_dmar_header *header)
+{
+	struct acpi_dmar_hardware_unit *drhd;
+	struct acpi_dmar_reserved_memory *rmrr;
+	struct acpi_dmar_atsr *atsr;
+	struct acpi_dmar_rhsa *rhsa;
+
+	switch (header->type) {
+	case ACPI_DMAR_TYPE_HARDWARE_UNIT:
+		drhd = container_of(header, struct acpi_dmar_hardware_unit,
+				    header);
+		printk (KERN_INFO PREFIX
+			"DRHD base: %#016Lx flags: %#x\n",
+			(unsigned long long)drhd->address, drhd->flags);
+		break;
+	case ACPI_DMAR_TYPE_RESERVED_MEMORY:
+		rmrr = container_of(header, struct acpi_dmar_reserved_memory,
+				    header);
+		printk (KERN_INFO PREFIX
+			"RMRR base: %#016Lx end: %#016Lx\n",
+			(unsigned long long)rmrr->base_address,
+			(unsigned long long)rmrr->end_address);
+		break;
+	case ACPI_DMAR_TYPE_ATSR:
+		atsr = container_of(header, struct acpi_dmar_atsr, header);
+		printk(KERN_INFO PREFIX "ATSR flags: %#x\n", atsr->flags);
+		break;
+	case ACPI_DMAR_HARDWARE_AFFINITY:
+		rhsa = container_of(header, struct acpi_dmar_rhsa, header);
+		printk(KERN_INFO PREFIX "RHSA base: %#016Lx proximity domain: %#x\n",
+		       (unsigned long long)rhsa->base_address,
+		       rhsa->proximity_domain);
+		break;
+	}
+}
+
+/**
+ * dmar_table_detect - checks to see if the platform supports DMAR devices
+ */
+static int __init dmar_table_detect(void)
+{
+	acpi_status status = AE_OK;
+
+	/* if we could find DMAR table, then there are DMAR devices */
+	status = acpi_get_table_with_size(ACPI_SIG_DMAR, 0,
+				(struct acpi_table_header **)&dmar_tbl,
+				&dmar_tbl_size);
+
+	if (ACPI_SUCCESS(status) && !dmar_tbl) {
+		printk (KERN_WARNING PREFIX "Unable to map DMAR\n");
+		status = AE_NOT_FOUND;
+	}
+
+	return (ACPI_SUCCESS(status) ? 1 : 0);
+}
+
+/**
+ * parse_dmar_table - parses the DMA reporting table
+ */
+static int __init
+parse_dmar_table(void)
+{
+	struct acpi_table_dmar *dmar;
+	struct acpi_dmar_header *entry_header;
+	int ret = 0;
+
+	/*
+	 * Do it again, earlier dmar_tbl mapping could be mapped with
+	 * fixed map.
+	 */
+	dmar_table_detect();
+
+	/*
+	 * ACPI tables may not be DMA protected by tboot, so use DMAR copy
+	 * SINIT saved in SinitMleData in TXT heap (which is DMA protected)
+	 */
+	dmar_tbl = tboot_get_dmar_table(dmar_tbl);
+
+	dmar = (struct acpi_table_dmar *)dmar_tbl;
+	if (!dmar)
+		return -ENODEV;
+
+	if (dmar->width < PAGE_SHIFT - 1) {
+		printk(KERN_WARNING PREFIX "Invalid DMAR haw\n");
+		return -EINVAL;
+	}
+
+	printk (KERN_INFO PREFIX "Host address width %d\n",
+		dmar->width + 1);
+
+	entry_header = (struct acpi_dmar_header *)(dmar + 1);
+	while (((unsigned long)entry_header) <
+			(((unsigned long)dmar) + dmar_tbl->length)) {
+		/* Avoid looping forever on bad ACPI tables */
+		if (entry_header->length == 0) {
+			printk(KERN_WARNING PREFIX
+				"Invalid 0-length structure\n");
+			ret = -EINVAL;
+			break;
+		}
+
+		dmar_table_print_dmar_entry(entry_header);
+
+		switch (entry_header->type) {
+		case ACPI_DMAR_TYPE_HARDWARE_UNIT:
+			ret = dmar_parse_one_drhd(entry_header);
+			break;
+		case ACPI_DMAR_TYPE_RESERVED_MEMORY:
+#ifdef CONFIG_DMAR
+			ret = dmar_parse_one_rmrr(entry_header);
+#endif
+			break;
+		case ACPI_DMAR_TYPE_ATSR:
+#ifdef CONFIG_DMAR
+			ret = dmar_parse_one_atsr(entry_header);
+#endif
+			break;
+		case ACPI_DMAR_HARDWARE_AFFINITY:
+#ifdef CONFIG_ACPI_NUMA
+			ret = dmar_parse_one_rhsa(entry_header);
+#endif
+			break;
+		default:
+			printk(KERN_WARNING PREFIX
+				"Unknown DMAR structure type %d\n",
+				entry_header->type);
+			ret = 0; /* for forward compatibility */
+			break;
+		}
+		if (ret)
+			break;
+
+		entry_header = ((void *)entry_header + entry_header->length);
+	}
+	return ret;
+}
+
+static int dmar_pci_device_match(struct pci_dev *devices[], int cnt,
+			  struct pci_dev *dev)
+{
+	int index;
+
+	while (dev) {
+		for (index = 0; index < cnt; index++)
+			if (dev == devices[index])
+				return 1;
+
+		/* Check our parent */
+		dev = dev->bus->self;
+	}
+
+	return 0;
+}
+
+struct dmar_drhd_unit *
+dmar_find_matched_drhd_unit(struct pci_dev *dev)
+{
+	struct dmar_drhd_unit *dmaru = NULL;
+	struct acpi_dmar_hardware_unit *drhd;
+
+	dev = pci_physfn(dev);
+
+	list_for_each_entry(dmaru, &dmar_drhd_units, list) {
+		drhd = container_of(dmaru->hdr,
+				    struct acpi_dmar_hardware_unit,
+				    header);
+
+		if (dmaru->include_all &&
+		    drhd->segment == pci_domain_nr(dev->bus))
+			return dmaru;
+
+		if (dmar_pci_device_match(dmaru->devices,
+					  dmaru->devices_cnt, dev))
+			return dmaru;
+	}
+
+	return NULL;
+}
+
+int __init dmar_dev_scope_init(void)
+{
+	struct dmar_drhd_unit *drhd, *drhd_n;
+	int ret = -ENODEV;
+
+	list_for_each_entry_safe(drhd, drhd_n, &dmar_drhd_units, list) {
+		ret = dmar_parse_dev(drhd);
+		if (ret)
+			return ret;
+	}
+
+#ifdef CONFIG_DMAR
+	{
+		struct dmar_rmrr_unit *rmrr, *rmrr_n;
+		struct dmar_atsr_unit *atsr, *atsr_n;
+
+		list_for_each_entry_safe(rmrr, rmrr_n, &dmar_rmrr_units, list) {
+			ret = rmrr_parse_dev(rmrr);
+			if (ret)
+				return ret;
+		}
+
+		list_for_each_entry_safe(atsr, atsr_n, &dmar_atsr_units, list) {
+			ret = atsr_parse_dev(atsr);
+			if (ret)
+				return ret;
+		}
+	}
+#endif
+
+	return ret;
+}
+
+
+int __init dmar_table_init(void)
+{
+	static int dmar_table_initialized;
+	int ret;
+
+	if (dmar_table_initialized)
+		return 0;
+
+	dmar_table_initialized = 1;
+
+	ret = parse_dmar_table();
+	if (ret) {
+		if (ret != -ENODEV)
+			printk(KERN_INFO PREFIX "parse DMAR table failure.\n");
+		return ret;
+	}
+
+	if (list_empty(&dmar_drhd_units)) {
+		printk(KERN_INFO PREFIX "No DMAR devices found\n");
+		return -ENODEV;
+	}
+
+#ifdef CONFIG_DMAR
+	if (list_empty(&dmar_rmrr_units))
+		printk(KERN_INFO PREFIX "No RMRR found\n");
+
+	if (list_empty(&dmar_atsr_units))
+		printk(KERN_INFO PREFIX "No ATSR found\n");
+#endif
+
+	return 0;
+}
+
+static void warn_invalid_dmar(u64 addr, const char *message)
+{
+	WARN_TAINT_ONCE(
+		1, TAINT_FIRMWARE_WORKAROUND,
+		"Your BIOS is broken; DMAR reported at address %llx%s!\n"
+		"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+		addr, message,
+		dmi_get_system_info(DMI_BIOS_VENDOR),
+		dmi_get_system_info(DMI_BIOS_VERSION),
+		dmi_get_system_info(DMI_PRODUCT_VERSION));
+}
+
+int __init check_zero_address(void)
+{
+	struct acpi_table_dmar *dmar;
+	struct acpi_dmar_header *entry_header;
+	struct acpi_dmar_hardware_unit *drhd;
+
+	dmar = (struct acpi_table_dmar *)dmar_tbl;
+	entry_header = (struct acpi_dmar_header *)(dmar + 1);
+
+	while (((unsigned long)entry_header) <
+			(((unsigned long)dmar) + dmar_tbl->length)) {
+		/* Avoid looping forever on bad ACPI tables */
+		if (entry_header->length == 0) {
+			printk(KERN_WARNING PREFIX
+				"Invalid 0-length structure\n");
+			return 0;
+		}
+
+		if (entry_header->type == ACPI_DMAR_TYPE_HARDWARE_UNIT) {
+			void __iomem *addr;
+			u64 cap, ecap;
+
+			drhd = (void *)entry_header;
+			if (!drhd->address) {
+				warn_invalid_dmar(0, "");
+				goto failed;
+			}
+
+			addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
+			if (!addr ) {
+				printk("IOMMU: can't validate: %llx\n", drhd->address);
+				goto failed;
+			}
+			cap = dmar_readq(addr + DMAR_CAP_REG);
+			ecap = dmar_readq(addr + DMAR_ECAP_REG);
+			early_iounmap(addr, VTD_PAGE_SIZE);
+			if (cap == (uint64_t)-1 && ecap == (uint64_t)-1) {
+				warn_invalid_dmar(drhd->address,
+						  " returns all ones");
+				goto failed;
+			}
+		}
+
+		entry_header = ((void *)entry_header + entry_header->length);
+	}
+	return 1;
+
+failed:
+#ifdef CONFIG_DMAR
+	dmar_disabled = 1;
+#endif
+	return 0;
+}
+
+int __init detect_intel_iommu(void)
+{
+	int ret;
+
+	ret = dmar_table_detect();
+	if (ret)
+		ret = check_zero_address();
+	{
+#ifdef CONFIG_INTR_REMAP
+		struct acpi_table_dmar *dmar;
+
+		dmar = (struct acpi_table_dmar *) dmar_tbl;
+		if (ret && cpu_has_x2apic && dmar->flags & 0x1)
+			printk(KERN_INFO
+			       "Queued invalidation will be enabled to support "
+			       "x2apic and Intr-remapping.\n");
+#endif
+#ifdef CONFIG_DMAR
+		if (ret && !no_iommu && !iommu_detected && !dmar_disabled) {
+			iommu_detected = 1;
+			/* Make sure ACS will be enabled */
+			pci_request_acs();
+		}
+#endif
+#ifdef CONFIG_X86
+		if (ret)
+			x86_init.iommu.iommu_init = intel_iommu_init;
+#endif
+	}
+	early_acpi_os_unmap_memory(dmar_tbl, dmar_tbl_size);
+	dmar_tbl = NULL;
+
+	return ret ? 1 : -ENODEV;
+}
+
+
+int alloc_iommu(struct dmar_drhd_unit *drhd)
+{
+	struct intel_iommu *iommu;
+	int map_size;
+	u32 ver;
+	static int iommu_allocated = 0;
+	int agaw = 0;
+	int msagaw = 0;
+
+	if (!drhd->reg_base_addr) {
+		warn_invalid_dmar(0, "");
+		return -EINVAL;
+	}
+
+	iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
+	if (!iommu)
+		return -ENOMEM;
+
+	iommu->seq_id = iommu_allocated++;
+	sprintf (iommu->name, "dmar%d", iommu->seq_id);
+
+	iommu->reg = ioremap(drhd->reg_base_addr, VTD_PAGE_SIZE);
+	if (!iommu->reg) {
+		printk(KERN_ERR "IOMMU: can't map the region\n");
+		goto error;
+	}
+	iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG);
+	iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG);
+
+	if (iommu->cap == (uint64_t)-1 && iommu->ecap == (uint64_t)-1) {
+		warn_invalid_dmar(drhd->reg_base_addr, " returns all ones");
+		goto err_unmap;
+	}
+
+#ifdef CONFIG_DMAR
+	agaw = iommu_calculate_agaw(iommu);
+	if (agaw < 0) {
+		printk(KERN_ERR
+		       "Cannot get a valid agaw for iommu (seq_id = %d)\n",
+		       iommu->seq_id);
+		goto err_unmap;
+	}
+	msagaw = iommu_calculate_max_sagaw(iommu);
+	if (msagaw < 0) {
+		printk(KERN_ERR
+			"Cannot get a valid max agaw for iommu (seq_id = %d)\n",
+			iommu->seq_id);
+		goto err_unmap;
+	}
+#endif
+	iommu->agaw = agaw;
+	iommu->msagaw = msagaw;
+
+	iommu->node = -1;
+
+	/* the registers might be more than one page */
+	map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap),
+		cap_max_fault_reg_offset(iommu->cap));
+	map_size = VTD_PAGE_ALIGN(map_size);
+	if (map_size > VTD_PAGE_SIZE) {
+		iounmap(iommu->reg);
+		iommu->reg = ioremap(drhd->reg_base_addr, map_size);
+		if (!iommu->reg) {
+			printk(KERN_ERR "IOMMU: can't map the region\n");
+			goto error;
+		}
+	}
+
+	ver = readl(iommu->reg + DMAR_VER_REG);
+	pr_info("IOMMU %d: reg_base_addr %llx ver %d:%d cap %llx ecap %llx\n",
+		iommu->seq_id,
+		(unsigned long long)drhd->reg_base_addr,
+		DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver),
+		(unsigned long long)iommu->cap,
+		(unsigned long long)iommu->ecap);
+
+	spin_lock_init(&iommu->register_lock);
+
+	drhd->iommu = iommu;
+	return 0;
+
+ err_unmap:
+	iounmap(iommu->reg);
+ error:
+	kfree(iommu);
+	return -1;
+}
+
+void free_iommu(struct intel_iommu *iommu)
+{
+	if (!iommu)
+		return;
+
+#ifdef CONFIG_DMAR
+	free_dmar_iommu(iommu);
+#endif
+
+	if (iommu->reg)
+		iounmap(iommu->reg);
+	kfree(iommu);
+}
+
+/*
+ * Reclaim all the submitted descriptors which have completed its work.
+ */
+static inline void reclaim_free_desc(struct q_inval *qi)
+{
+	while (qi->desc_status[qi->free_tail] == QI_DONE ||
+	       qi->desc_status[qi->free_tail] == QI_ABORT) {
+		qi->desc_status[qi->free_tail] = QI_FREE;
+		qi->free_tail = (qi->free_tail + 1) % QI_LENGTH;
+		qi->free_cnt++;
+	}
+}
+
+static int qi_check_fault(struct intel_iommu *iommu, int index)
+{
+	u32 fault;
+	int head, tail;
+	struct q_inval *qi = iommu->qi;
+	int wait_index = (index + 1) % QI_LENGTH;
+
+	if (qi->desc_status[wait_index] == QI_ABORT)
+		return -EAGAIN;
+
+	fault = readl(iommu->reg + DMAR_FSTS_REG);
+
+	/*
+	 * If IQE happens, the head points to the descriptor associated
+	 * with the error. No new descriptors are fetched until the IQE
+	 * is cleared.
+	 */
+	if (fault & DMA_FSTS_IQE) {
+		head = readl(iommu->reg + DMAR_IQH_REG);
+		if ((head >> DMAR_IQ_SHIFT) == index) {
+			printk(KERN_ERR "VT-d detected invalid descriptor: "
+				"low=%llx, high=%llx\n",
+				(unsigned long long)qi->desc[index].low,
+				(unsigned long long)qi->desc[index].high);
+			memcpy(&qi->desc[index], &qi->desc[wait_index],
+					sizeof(struct qi_desc));
+			__iommu_flush_cache(iommu, &qi->desc[index],
+					sizeof(struct qi_desc));
+			writel(DMA_FSTS_IQE, iommu->reg + DMAR_FSTS_REG);
+			return -EINVAL;
+		}
+	}
+
+	/*
+	 * If ITE happens, all pending wait_desc commands are aborted.
+	 * No new descriptors are fetched until the ITE is cleared.
+	 */
+	if (fault & DMA_FSTS_ITE) {
+		head = readl(iommu->reg + DMAR_IQH_REG);
+		head = ((head >> DMAR_IQ_SHIFT) - 1 + QI_LENGTH) % QI_LENGTH;
+		head |= 1;
+		tail = readl(iommu->reg + DMAR_IQT_REG);
+		tail = ((tail >> DMAR_IQ_SHIFT) - 1 + QI_LENGTH) % QI_LENGTH;
+
+		writel(DMA_FSTS_ITE, iommu->reg + DMAR_FSTS_REG);
+
+		do {
+			if (qi->desc_status[head] == QI_IN_USE)
+				qi->desc_status[head] = QI_ABORT;
+			head = (head - 2 + QI_LENGTH) % QI_LENGTH;
+		} while (head != tail);
+
+		if (qi->desc_status[wait_index] == QI_ABORT)
+			return -EAGAIN;
+	}
+
+	if (fault & DMA_FSTS_ICE)
+		writel(DMA_FSTS_ICE, iommu->reg + DMAR_FSTS_REG);
+
+	return 0;
+}
+
+/*
+ * Submit the queued invalidation descriptor to the remapping
+ * hardware unit and wait for its completion.
+ */
+int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
+{
+	int rc;
+	struct q_inval *qi = iommu->qi;
+	struct qi_desc *hw, wait_desc;
+	int wait_index, index;
+	unsigned long flags;
+
+	if (!qi)
+		return 0;
+
+	hw = qi->desc;
+
+restart:
+	rc = 0;
+
+	spin_lock_irqsave(&qi->q_lock, flags);
+	while (qi->free_cnt < 3) {
+		spin_unlock_irqrestore(&qi->q_lock, flags);
+		cpu_relax();
+		spin_lock_irqsave(&qi->q_lock, flags);
+	}
+
+	index = qi->free_head;
+	wait_index = (index + 1) % QI_LENGTH;
+
+	qi->desc_status[index] = qi->desc_status[wait_index] = QI_IN_USE;
+
+	hw[index] = *desc;
+
+	wait_desc.low = QI_IWD_STATUS_DATA(QI_DONE) |
+			QI_IWD_STATUS_WRITE | QI_IWD_TYPE;
+	wait_desc.high = virt_to_phys(&qi->desc_status[wait_index]);
+
+	hw[wait_index] = wait_desc;
+
+	__iommu_flush_cache(iommu, &hw[index], sizeof(struct qi_desc));
+	__iommu_flush_cache(iommu, &hw[wait_index], sizeof(struct qi_desc));
+
+	qi->free_head = (qi->free_head + 2) % QI_LENGTH;
+	qi->free_cnt -= 2;
+
+	/*
+	 * update the HW tail register indicating the presence of
+	 * new descriptors.
+	 */
+	writel(qi->free_head << DMAR_IQ_SHIFT, iommu->reg + DMAR_IQT_REG);
+
+	while (qi->desc_status[wait_index] != QI_DONE) {
+		/*
+		 * We will leave the interrupts disabled, to prevent interrupt
+		 * context to queue another cmd while a cmd is already submitted
+		 * and waiting for completion on this cpu. This is to avoid
+		 * a deadlock where the interrupt context can wait indefinitely
+		 * for free slots in the queue.
+		 */
+		rc = qi_check_fault(iommu, index);
+		if (rc)
+			break;
+
+		spin_unlock(&qi->q_lock);
+		cpu_relax();
+		spin_lock(&qi->q_lock);
+	}
+
+	qi->desc_status[index] = QI_DONE;
+
+	reclaim_free_desc(qi);
+	spin_unlock_irqrestore(&qi->q_lock, flags);
+
+	if (rc == -EAGAIN)
+		goto restart;
+
+	return rc;
+}
+
+/*
+ * Flush the global interrupt entry cache.
+ */
+void qi_global_iec(struct intel_iommu *iommu)
+{
+	struct qi_desc desc;
+
+	desc.low = QI_IEC_TYPE;
+	desc.high = 0;
+
+	/* should never fail */
+	qi_submit_sync(&desc, iommu);
+}
+
+void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm,
+		      u64 type)
+{
+	struct qi_desc desc;
+
+	desc.low = QI_CC_FM(fm) | QI_CC_SID(sid) | QI_CC_DID(did)
+			| QI_CC_GRAN(type) | QI_CC_TYPE;
+	desc.high = 0;
+
+	qi_submit_sync(&desc, iommu);
+}
+
+void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
+		    unsigned int size_order, u64 type)
+{
+	u8 dw = 0, dr = 0;
+
+	struct qi_desc desc;
+	int ih = 0;
+
+	if (cap_write_drain(iommu->cap))
+		dw = 1;
+
+	if (cap_read_drain(iommu->cap))
+		dr = 1;
+
+	desc.low = QI_IOTLB_DID(did) | QI_IOTLB_DR(dr) | QI_IOTLB_DW(dw)
+		| QI_IOTLB_GRAN(type) | QI_IOTLB_TYPE;
+	desc.high = QI_IOTLB_ADDR(addr) | QI_IOTLB_IH(ih)
+		| QI_IOTLB_AM(size_order);
+
+	qi_submit_sync(&desc, iommu);
+}
+
+void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 qdep,
+			u64 addr, unsigned mask)
+{
+	struct qi_desc desc;
+
+	if (mask) {
+		BUG_ON(addr & ((1 << (VTD_PAGE_SHIFT + mask)) - 1));
+		addr |= (1 << (VTD_PAGE_SHIFT + mask - 1)) - 1;
+		desc.high = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
+	} else
+		desc.high = QI_DEV_IOTLB_ADDR(addr);
+
+	if (qdep >= QI_DEV_IOTLB_MAX_INVS)
+		qdep = 0;
+
+	desc.low = QI_DEV_IOTLB_SID(sid) | QI_DEV_IOTLB_QDEP(qdep) |
+		   QI_DIOTLB_TYPE;
+
+	qi_submit_sync(&desc, iommu);
+}
+
+/*
+ * Disable Queued Invalidation interface.
+ */
+void dmar_disable_qi(struct intel_iommu *iommu)
+{
+	unsigned long flags;
+	u32 sts;
+	cycles_t start_time = get_cycles();
+
+	if (!ecap_qis(iommu->ecap))
+		return;
+
+	spin_lock_irqsave(&iommu->register_lock, flags);
+
+	sts =  dmar_readq(iommu->reg + DMAR_GSTS_REG);
+	if (!(sts & DMA_GSTS_QIES))
+		goto end;
+
+	/*
+	 * Give a chance to HW to complete the pending invalidation requests.
+	 */
+	while ((readl(iommu->reg + DMAR_IQT_REG) !=
+		readl(iommu->reg + DMAR_IQH_REG)) &&
+		(DMAR_OPERATION_TIMEOUT > (get_cycles() - start_time)))
+		cpu_relax();
+
+	iommu->gcmd &= ~DMA_GCMD_QIE;
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, readl,
+		      !(sts & DMA_GSTS_QIES), sts);
+end:
+	spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
+/*
+ * Enable queued invalidation.
+ */
+static void __dmar_enable_qi(struct intel_iommu *iommu)
+{
+	u32 sts;
+	unsigned long flags;
+	struct q_inval *qi = iommu->qi;
+
+	qi->free_head = qi->free_tail = 0;
+	qi->free_cnt = QI_LENGTH;
+
+	spin_lock_irqsave(&iommu->register_lock, flags);
+
+	/* write zero to the tail reg */
+	writel(0, iommu->reg + DMAR_IQT_REG);
+
+	dmar_writeq(iommu->reg + DMAR_IQA_REG, virt_to_phys(qi->desc));
+
+	iommu->gcmd |= DMA_GCMD_QIE;
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	/* Make sure hardware complete it */
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, readl, (sts & DMA_GSTS_QIES), sts);
+
+	spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
+/*
+ * Enable Queued Invalidation interface. This is a must to support
+ * interrupt-remapping. Also used by DMA-remapping, which replaces
+ * register based IOTLB invalidation.
+ */
+int dmar_enable_qi(struct intel_iommu *iommu)
+{
+	struct q_inval *qi;
+	struct page *desc_page;
+
+	if (!ecap_qis(iommu->ecap))
+		return -ENOENT;
+
+	/*
+	 * queued invalidation is already setup and enabled.
+	 */
+	if (iommu->qi)
+		return 0;
+
+	iommu->qi = kmalloc(sizeof(*qi), GFP_ATOMIC);
+	if (!iommu->qi)
+		return -ENOMEM;
+
+	qi = iommu->qi;
+
+
+	desc_page = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO, 0);
+	if (!desc_page) {
+		kfree(qi);
+		iommu->qi = 0;
+		return -ENOMEM;
+	}
+
+	qi->desc = page_address(desc_page);
+
+	qi->desc_status = kmalloc(QI_LENGTH * sizeof(int), GFP_ATOMIC);
+	if (!qi->desc_status) {
+		free_page((unsigned long) qi->desc);
+		kfree(qi);
+		iommu->qi = 0;
+		return -ENOMEM;
+	}
+
+	qi->free_head = qi->free_tail = 0;
+	qi->free_cnt = QI_LENGTH;
+
+	spin_lock_init(&qi->q_lock);
+
+	__dmar_enable_qi(iommu);
+
+	return 0;
+}
+
+/* iommu interrupt handling. Most stuff are MSI-like. */
+
+enum faulttype {
+	DMA_REMAP,
+	INTR_REMAP,
+	UNKNOWN,
+};
+
+static const char *dma_remap_fault_reasons[] =
+{
+	"Software",
+	"Present bit in root entry is clear",
+	"Present bit in context entry is clear",
+	"Invalid context entry",
+	"Access beyond MGAW",
+	"PTE Write access is not set",
+	"PTE Read access is not set",
+	"Next page table ptr is invalid",
+	"Root table address invalid",
+	"Context table ptr is invalid",
+	"non-zero reserved fields in RTP",
+	"non-zero reserved fields in CTP",
+	"non-zero reserved fields in PTE",
+};
+
+static const char *intr_remap_fault_reasons[] =
+{
+	"Detected reserved fields in the decoded interrupt-remapped request",
+	"Interrupt index exceeded the interrupt-remapping table size",
+	"Present field in the IRTE entry is clear",
+	"Error accessing interrupt-remapping table pointed by IRTA_REG",
+	"Detected reserved fields in the IRTE entry",
+	"Blocked a compatibility format interrupt request",
+	"Blocked an interrupt request due to source-id verification failure",
+};
+
+#define MAX_FAULT_REASON_IDX 	(ARRAY_SIZE(fault_reason_strings) - 1)
+
+const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type)
+{
+	if (fault_reason >= 0x20 && (fault_reason <= 0x20 +
+				     ARRAY_SIZE(intr_remap_fault_reasons))) {
+		*fault_type = INTR_REMAP;
+		return intr_remap_fault_reasons[fault_reason - 0x20];
+	} else if (fault_reason < ARRAY_SIZE(dma_remap_fault_reasons)) {
+		*fault_type = DMA_REMAP;
+		return dma_remap_fault_reasons[fault_reason];
+	} else {
+		*fault_type = UNKNOWN;
+		return "Unknown";
+	}
+}
+
+void dmar_msi_unmask(struct irq_data *data)
+{
+	struct intel_iommu *iommu = irq_data_get_irq_handler_data(data);
+	unsigned long flag;
+
+	/* unmask it */
+	spin_lock_irqsave(&iommu->register_lock, flag);
+	writel(0, iommu->reg + DMAR_FECTL_REG);
+	/* Read a reg to force flush the post write */
+	readl(iommu->reg + DMAR_FECTL_REG);
+	spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+void dmar_msi_mask(struct irq_data *data)
+{
+	unsigned long flag;
+	struct intel_iommu *iommu = irq_data_get_irq_handler_data(data);
+
+	/* mask it */
+	spin_lock_irqsave(&iommu->register_lock, flag);
+	writel(DMA_FECTL_IM, iommu->reg + DMAR_FECTL_REG);
+	/* Read a reg to force flush the post write */
+	readl(iommu->reg + DMAR_FECTL_REG);
+	spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+void dmar_msi_write(int irq, struct msi_msg *msg)
+{
+	struct intel_iommu *iommu = irq_get_handler_data(irq);
+	unsigned long flag;
+
+	spin_lock_irqsave(&iommu->register_lock, flag);
+	writel(msg->data, iommu->reg + DMAR_FEDATA_REG);
+	writel(msg->address_lo, iommu->reg + DMAR_FEADDR_REG);
+	writel(msg->address_hi, iommu->reg + DMAR_FEUADDR_REG);
+	spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+void dmar_msi_read(int irq, struct msi_msg *msg)
+{
+	struct intel_iommu *iommu = irq_get_handler_data(irq);
+	unsigned long flag;
+
+	spin_lock_irqsave(&iommu->register_lock, flag);
+	msg->data = readl(iommu->reg + DMAR_FEDATA_REG);
+	msg->address_lo = readl(iommu->reg + DMAR_FEADDR_REG);
+	msg->address_hi = readl(iommu->reg + DMAR_FEUADDR_REG);
+	spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
+		u8 fault_reason, u16 source_id, unsigned long long addr)
+{
+	const char *reason;
+	int fault_type;
+
+	reason = dmar_get_fault_reason(fault_reason, &fault_type);
+
+	if (fault_type == INTR_REMAP)
+		printk(KERN_ERR "INTR-REMAP: Request device [[%02x:%02x.%d] "
+		       "fault index %llx\n"
+			"INTR-REMAP:[fault reason %02d] %s\n",
+			(source_id >> 8), PCI_SLOT(source_id & 0xFF),
+			PCI_FUNC(source_id & 0xFF), addr >> 48,
+			fault_reason, reason);
+	else
+		printk(KERN_ERR
+		       "DMAR:[%s] Request device [%02x:%02x.%d] "
+		       "fault addr %llx \n"
+		       "DMAR:[fault reason %02d] %s\n",
+		       (type ? "DMA Read" : "DMA Write"),
+		       (source_id >> 8), PCI_SLOT(source_id & 0xFF),
+		       PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason);
+	return 0;
+}
+
+#define PRIMARY_FAULT_REG_LEN (16)
+irqreturn_t dmar_fault(int irq, void *dev_id)
+{
+	struct intel_iommu *iommu = dev_id;
+	int reg, fault_index;
+	u32 fault_status;
+	unsigned long flag;
+
+	spin_lock_irqsave(&iommu->register_lock, flag);
+	fault_status = readl(iommu->reg + DMAR_FSTS_REG);
+	if (fault_status)
+		printk(KERN_ERR "DRHD: handling fault status reg %x\n",
+		       fault_status);
+
+	/* TBD: ignore advanced fault log currently */
+	if (!(fault_status & DMA_FSTS_PPF))
+		goto clear_rest;
+
+	fault_index = dma_fsts_fault_record_index(fault_status);
+	reg = cap_fault_reg_offset(iommu->cap);
+	while (1) {
+		u8 fault_reason;
+		u16 source_id;
+		u64 guest_addr;
+		int type;
+		u32 data;
+
+		/* highest 32 bits */
+		data = readl(iommu->reg + reg +
+				fault_index * PRIMARY_FAULT_REG_LEN + 12);
+		if (!(data & DMA_FRCD_F))
+			break;
+
+		fault_reason = dma_frcd_fault_reason(data);
+		type = dma_frcd_type(data);
+
+		data = readl(iommu->reg + reg +
+				fault_index * PRIMARY_FAULT_REG_LEN + 8);
+		source_id = dma_frcd_source_id(data);
+
+		guest_addr = dmar_readq(iommu->reg + reg +
+				fault_index * PRIMARY_FAULT_REG_LEN);
+		guest_addr = dma_frcd_page_addr(guest_addr);
+		/* clear the fault */
+		writel(DMA_FRCD_F, iommu->reg + reg +
+			fault_index * PRIMARY_FAULT_REG_LEN + 12);
+
+		spin_unlock_irqrestore(&iommu->register_lock, flag);
+
+		dmar_fault_do_one(iommu, type, fault_reason,
+				source_id, guest_addr);
+
+		fault_index++;
+		if (fault_index >= cap_num_fault_regs(iommu->cap))
+			fault_index = 0;
+		spin_lock_irqsave(&iommu->register_lock, flag);
+	}
+clear_rest:
+	/* clear all the other faults */
+	fault_status = readl(iommu->reg + DMAR_FSTS_REG);
+	writel(fault_status, iommu->reg + DMAR_FSTS_REG);
+
+	spin_unlock_irqrestore(&iommu->register_lock, flag);
+	return IRQ_HANDLED;
+}
+
+int dmar_set_interrupt(struct intel_iommu *iommu)
+{
+	int irq, ret;
+
+	/*
+	 * Check if the fault interrupt is already initialized.
+	 */
+	if (iommu->irq)
+		return 0;
+
+	irq = create_irq();
+	if (!irq) {
+		printk(KERN_ERR "IOMMU: no free vectors\n");
+		return -EINVAL;
+	}
+
+	irq_set_handler_data(irq, iommu);
+	iommu->irq = irq;
+
+	ret = arch_setup_dmar_msi(irq);
+	if (ret) {
+		irq_set_handler_data(irq, NULL);
+		iommu->irq = 0;
+		destroy_irq(irq);
+		return ret;
+	}
+
+	ret = request_irq(irq, dmar_fault, IRQF_NO_THREAD, iommu->name, iommu);
+	if (ret)
+		printk(KERN_ERR "IOMMU: can't request irq\n");
+	return ret;
+}
+
+int __init enable_drhd_fault_handling(void)
+{
+	struct dmar_drhd_unit *drhd;
+
+	/*
+	 * Enable fault control interrupt.
+	 */
+	for_each_drhd_unit(drhd) {
+		int ret;
+		struct intel_iommu *iommu = drhd->iommu;
+		ret = dmar_set_interrupt(iommu);
+
+		if (ret) {
+			printk(KERN_ERR "DRHD %Lx: failed to enable fault, "
+			       " interrupt, ret %d\n",
+			       (unsigned long long)drhd->reg_base_addr, ret);
+			return -1;
+		}
+
+		/*
+		 * Clear any previous faults.
+		 */
+		dmar_fault(iommu->irq, iommu);
+	}
+
+	return 0;
+}
+
+/*
+ * Re-enable Queued Invalidation interface.
+ */
+int dmar_reenable_qi(struct intel_iommu *iommu)
+{
+	if (!ecap_qis(iommu->ecap))
+		return -ENOENT;
+
+	if (!iommu->qi)
+		return -ENOENT;
+
+	/*
+	 * First disable queued invalidation.
+	 */
+	dmar_disable_qi(iommu);
+	/*
+	 * Then enable queued invalidation again. Since there is no pending
+	 * invalidation requests now, it's safe to re-enable queued
+	 * invalidation.
+	 */
+	__dmar_enable_qi(iommu);
+
+	return 0;
+}
+
+/*
+ * Check interrupt remapping support in DMAR table description.
+ */
+int __init dmar_ir_support(void)
+{
+	struct acpi_table_dmar *dmar;
+	dmar = (struct acpi_table_dmar *)dmar_tbl;
+	if (!dmar)
+		return 0;
+	return dmar->flags & 0x1;
+}
+IOMMU_INIT_POST(detect_intel_iommu);
diff --git a/drivers/pci/hotplug-pci.c b/drivers/pci/hotplug-pci.c
new file mode 100644
index 00000000..4d4a6447
--- /dev/null
+++ b/drivers/pci/hotplug-pci.c
@@ -0,0 +1,20 @@
+/* Core PCI functionality used only by PCI hotplug */
+
+#include <linux/pci.h>
+#include "pci.h"
+
+
+unsigned int __devinit pci_do_scan_bus(struct pci_bus *bus)
+{
+	unsigned int max;
+
+	max = pci_scan_child_bus(bus);
+
+	/*
+	 * Make the discovered devices available.
+	 */
+	pci_bus_add_devices(bus);
+
+	return max;
+}
+EXPORT_SYMBOL(pci_do_scan_bus);
diff --git a/drivers/pci/hotplug.c b/drivers/pci/hotplug.c
new file mode 100644
index 00000000..2b5352a7
--- /dev/null
+++ b/drivers/pci/hotplug.c
@@ -0,0 +1,37 @@
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/module.h>
+#include "pci.h"
+
+int pci_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct pci_dev *pdev;
+
+	if (!dev)
+		return -ENODEV;
+
+	pdev = to_pci_dev(dev);
+	if (!pdev)
+		return -ENODEV;
+
+	if (add_uevent_var(env, "PCI_CLASS=%04X", pdev->class))
+		return -ENOMEM;
+
+	if (add_uevent_var(env, "PCI_ID=%04X:%04X", pdev->vendor, pdev->device))
+		return -ENOMEM;
+
+	if (add_uevent_var(env, "PCI_SUBSYS_ID=%04X:%04X", pdev->subsystem_vendor,
+			   pdev->subsystem_device))
+		return -ENOMEM;
+
+	if (add_uevent_var(env, "PCI_SLOT_NAME=%s", pci_name(pdev)))
+		return -ENOMEM;
+
+	if (add_uevent_var(env, "MODALIAS=pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02x",
+			   pdev->vendor, pdev->device,
+			   pdev->subsystem_vendor, pdev->subsystem_device,
+			   (u8)(pdev->class >> 16), (u8)(pdev->class >> 8),
+			   (u8)(pdev->class)))
+		return -ENOMEM;
+	return 0;
+}
diff --git a/drivers/pci/hotplug/Kconfig b/drivers/pci/hotplug/Kconfig
new file mode 100644
index 00000000..66f29bc0
--- /dev/null
+++ b/drivers/pci/hotplug/Kconfig
@@ -0,0 +1,176 @@
+#
+# PCI Hotplug support
+#
+
+menuconfig HOTPLUG_PCI
+	tristate "Support for PCI Hotplug"
+	depends on PCI && HOTPLUG && SYSFS
+	---help---
+	  Say Y here if you have a motherboard with a PCI Hotplug controller.
+	  This allows you to add and remove PCI cards while the machine is
+	  powered up and running.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called pci_hotplug.
+
+	  When in doubt, say N.
+
+if HOTPLUG_PCI
+
+config HOTPLUG_PCI_FAKE
+	tristate "Fake PCI Hotplug driver"
+	help
+	  Say Y here if you want to use the fake PCI hotplug driver. It can
+	  be used to simulate PCI hotplug events if even if your system is
+	  not PCI hotplug capable.
+
+	  This driver will "emulate" removing PCI devices from the system.
+	  If the "power" file is written to with "0" then the specified PCI
+	  device will be completely removed from the kernel.
+
+	  WARNING, this does NOT turn off the power to the PCI device.
+	  This is a "logical" removal, not a physical or electrical
+	  removal.
+
+	  Use this module at your own risk.  You have been warned!
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called fakephp.
+
+	  When in doubt, say N.
+
+config HOTPLUG_PCI_COMPAQ
+	tristate "Compaq PCI Hotplug driver"
+	depends on X86 && PCI_BIOS
+	help
+	  Say Y here if you have a motherboard with a Compaq PCI Hotplug
+	  controller.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called cpqphp.
+
+	  When in doubt, say N.
+
+config HOTPLUG_PCI_COMPAQ_NVRAM
+	bool "Save configuration into NVRAM on Compaq servers"
+	depends on HOTPLUG_PCI_COMPAQ
+	help
+	  Say Y here if you have a Compaq server that has a PCI Hotplug
+	  controller.  This will allow the PCI Hotplug driver to store the PCI
+	  system configuration options in NVRAM.
+
+	  When in doubt, say N.
+
+config HOTPLUG_PCI_IBM
+	tristate "IBM PCI Hotplug driver"
+	depends on X86_IO_APIC && X86 && PCI_BIOS
+	help
+	  Say Y here if you have a motherboard with a IBM PCI Hotplug
+	  controller.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called ibmphp.
+
+	  When in doubt, say N.
+
+config HOTPLUG_PCI_ACPI
+	tristate "ACPI PCI Hotplug driver"
+	depends on (!ACPI_DOCK && ACPI) || (ACPI_DOCK)
+	help
+	  Say Y here if you have a system that supports PCI Hotplug using
+	  ACPI.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called acpiphp.
+
+	  When in doubt, say N.
+
+config HOTPLUG_PCI_ACPI_IBM
+	tristate "ACPI PCI Hotplug driver IBM extensions"
+	depends on HOTPLUG_PCI_ACPI
+	help
+	  Say Y here if you have an IBM system that supports PCI Hotplug using
+	  ACPI.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called acpiphp_ibm.
+
+	  When in doubt, say N.
+
+config HOTPLUG_PCI_CPCI
+	bool "CompactPCI Hotplug driver"
+	help
+	  Say Y here if you have a CompactPCI system card with CompactPCI
+	  hotswap support per the PICMG 2.1 specification.
+
+	  When in doubt, say N.
+
+config HOTPLUG_PCI_CPCI_ZT5550
+	tristate "Ziatech ZT5550 CompactPCI Hotplug driver"
+	depends on HOTPLUG_PCI_CPCI && X86
+	help
+	  Say Y here if you have an Performance Technologies (formerly Intel,
+          formerly just Ziatech) Ziatech ZT5550 CompactPCI system card.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called cpcihp_zt5550.
+
+	  When in doubt, say N.
+
+config HOTPLUG_PCI_CPCI_GENERIC
+	tristate "Generic port I/O CompactPCI Hotplug driver"
+	depends on HOTPLUG_PCI_CPCI && X86
+	help
+	  Say Y here if you have a CompactPCI system card that exposes the #ENUM
+	  hotswap signal as a bit in a system register that can be read through
+	  standard port I/O.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called cpcihp_generic.
+
+	  When in doubt, say N.
+
+config HOTPLUG_PCI_SHPC
+	tristate "SHPC PCI Hotplug driver"
+	help
+	  Say Y here if you have a motherboard with a SHPC PCI Hotplug
+	  controller.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called shpchp.
+
+	  When in doubt, say N.
+
+config HOTPLUG_PCI_RPA
+	tristate "RPA PCI Hotplug driver"
+	depends on PPC_PSERIES && EEH && !HOTPLUG_PCI_FAKE
+	help
+	  Say Y here if you have a RPA system that supports PCI Hotplug.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called rpaphp.
+
+	  When in doubt, say N.
+
+config HOTPLUG_PCI_RPA_DLPAR
+	tristate "RPA Dynamic Logical Partitioning for I/O slots"
+	depends on HOTPLUG_PCI_RPA
+	help
+	  Say Y here if your system supports Dynamic Logical Partitioning
+	  for I/O slots.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called rpadlpar_io.
+ 
+ 	  When in doubt, say N.
+
+config HOTPLUG_PCI_SGI
+	tristate "SGI PCI Hotplug Support"
+	depends on IA64_SGI_SN2 || IA64_GENERIC
+	help
+	  Say Y here if you want to use the SGI Altix Hotplug
+	  Driver for PCI devices.
+
+	  When in doubt, say N.
+
+endif # HOTPLUG_PCI
diff --git a/drivers/pci/hotplug/Makefile b/drivers/pci/hotplug/Makefile
new file mode 100644
index 00000000..6cd9f3c9
--- /dev/null
+++ b/drivers/pci/hotplug/Makefile
@@ -0,0 +1,74 @@
+#
+# Makefile for the Linux kernel pci hotplug controller drivers.
+#
+
+obj-$(CONFIG_HOTPLUG_PCI)		+= pci_hotplug.o
+obj-$(CONFIG_HOTPLUG_PCI_COMPAQ)	+= cpqphp.o
+obj-$(CONFIG_HOTPLUG_PCI_IBM)		+= ibmphp.o
+
+# native drivers should be linked before acpiphp in order to allow the
+# native driver to attempt to bind first. We can then fall back to
+# generic support.
+
+obj-$(CONFIG_HOTPLUG_PCI_PCIE)		+= pciehp.o
+obj-$(CONFIG_HOTPLUG_PCI_CPCI_ZT5550)	+= cpcihp_zt5550.o
+obj-$(CONFIG_HOTPLUG_PCI_CPCI_GENERIC)	+= cpcihp_generic.o
+obj-$(CONFIG_HOTPLUG_PCI_SHPC)		+= shpchp.o
+obj-$(CONFIG_HOTPLUG_PCI_RPA)		+= rpaphp.o
+obj-$(CONFIG_HOTPLUG_PCI_RPA_DLPAR)	+= rpadlpar_io.o
+obj-$(CONFIG_HOTPLUG_PCI_SGI)		+= sgi_hotplug.o
+obj-$(CONFIG_HOTPLUG_PCI_ACPI)		+= acpiphp.o
+
+# acpiphp_ibm extends acpiphp, so should be linked afterwards.
+
+obj-$(CONFIG_HOTPLUG_PCI_ACPI_IBM)	+= acpiphp_ibm.o
+
+# Link this last so it doesn't claim devices that have a real hotplug driver
+obj-$(CONFIG_HOTPLUG_PCI_FAKE)		+= fakephp.o
+
+pci_hotplug-objs	:=	pci_hotplug_core.o pcihp_slot.o
+
+ifdef CONFIG_HOTPLUG_PCI_CPCI
+pci_hotplug-objs	+=	cpci_hotplug_core.o	\
+				cpci_hotplug_pci.o
+endif
+ifdef CONFIG_ACPI
+pci_hotplug-objs 	+= 	acpi_pcihp.o
+endif
+
+cpqphp-objs		:=	cpqphp_core.o	\
+				cpqphp_ctrl.o	\
+				cpqphp_sysfs.o	\
+				cpqphp_pci.o
+cpqphp-$(CONFIG_HOTPLUG_PCI_COMPAQ_NVRAM) += cpqphp_nvram.o
+cpqphp-objs += $(cpqphp-y)
+
+ibmphp-objs		:=	ibmphp_core.o	\
+				ibmphp_ebda.o	\
+				ibmphp_pci.o	\
+				ibmphp_res.o	\
+				ibmphp_hpc.o
+
+acpiphp-objs		:=	acpiphp_core.o	\
+				acpiphp_glue.o
+
+rpaphp-objs		:=	rpaphp_core.o	\
+				rpaphp_pci.o	\
+				rpaphp_slot.o
+
+rpadlpar_io-objs	:=	rpadlpar_core.o \
+				rpadlpar_sysfs.o
+
+pciehp-objs		:=	pciehp_core.o	\
+				pciehp_ctrl.o	\
+				pciehp_pci.o	\
+				pciehp_hpc.o
+ifdef CONFIG_ACPI
+pciehp-objs		+=	pciehp_acpi.o
+endif
+
+shpchp-objs		:=	shpchp_core.o	\
+				shpchp_ctrl.o	\
+				shpchp_pci.o	\
+				shpchp_sysfs.o	\
+				shpchp_hpc.o
diff --git a/drivers/pci/hotplug/acpi_pcihp.c b/drivers/pci/hotplug/acpi_pcihp.c
new file mode 100644
index 00000000..8f3faf34
--- /dev/null
+++ b/drivers/pci/hotplug/acpi_pcihp.c
@@ -0,0 +1,480 @@
+/*
+ * Common ACPI functions for hot plug platforms
+ *
+ * Copyright (C) 2006 Intel Corporation
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <kristen.c.accardi@intel.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/acpi.h>
+#include <linux/pci-acpi.h>
+#include <linux/slab.h>
+
+#define MY_NAME	"acpi_pcihp"
+
+#define dbg(fmt, arg...) do { if (debug_acpi) printk(KERN_DEBUG "%s: %s: " fmt , MY_NAME , __func__ , ## arg); } while (0)
+#define err(format, arg...) printk(KERN_ERR "%s: " format , MY_NAME , ## arg)
+#define info(format, arg...) printk(KERN_INFO "%s: " format , MY_NAME , ## arg)
+#define warn(format, arg...) printk(KERN_WARNING "%s: " format , MY_NAME , ## arg)
+
+#define	METHOD_NAME__SUN	"_SUN"
+#define	METHOD_NAME_OSHP	"OSHP"
+
+static int debug_acpi;
+
+static acpi_status
+decode_type0_hpx_record(union acpi_object *record, struct hotplug_params *hpx)
+{
+	int i;
+	union acpi_object *fields = record->package.elements;
+	u32 revision = fields[1].integer.value;
+
+	switch (revision) {
+	case 1:
+		if (record->package.count != 6)
+			return AE_ERROR;
+		for (i = 2; i < 6; i++)
+			if (fields[i].type != ACPI_TYPE_INTEGER)
+				return AE_ERROR;
+		hpx->t0 = &hpx->type0_data;
+		hpx->t0->revision        = revision;
+		hpx->t0->cache_line_size = fields[2].integer.value;
+		hpx->t0->latency_timer   = fields[3].integer.value;
+		hpx->t0->enable_serr     = fields[4].integer.value;
+		hpx->t0->enable_perr     = fields[5].integer.value;
+		break;
+	default:
+		printk(KERN_WARNING
+		       "%s: Type 0 Revision %d record not supported\n",
+		       __func__, revision);
+		return AE_ERROR;
+	}
+	return AE_OK;
+}
+
+static acpi_status
+decode_type1_hpx_record(union acpi_object *record, struct hotplug_params *hpx)
+{
+	int i;
+	union acpi_object *fields = record->package.elements;
+	u32 revision = fields[1].integer.value;
+
+	switch (revision) {
+	case 1:
+		if (record->package.count != 5)
+			return AE_ERROR;
+		for (i = 2; i < 5; i++)
+			if (fields[i].type != ACPI_TYPE_INTEGER)
+				return AE_ERROR;
+		hpx->t1 = &hpx->type1_data;
+		hpx->t1->revision      = revision;
+		hpx->t1->max_mem_read  = fields[2].integer.value;
+		hpx->t1->avg_max_split = fields[3].integer.value;
+		hpx->t1->tot_max_split = fields[4].integer.value;
+		break;
+	default:
+		printk(KERN_WARNING
+		       "%s: Type 1 Revision %d record not supported\n",
+		       __func__, revision);
+		return AE_ERROR;
+	}
+	return AE_OK;
+}
+
+static acpi_status
+decode_type2_hpx_record(union acpi_object *record, struct hotplug_params *hpx)
+{
+	int i;
+	union acpi_object *fields = record->package.elements;
+	u32 revision = fields[1].integer.value;
+
+	switch (revision) {
+	case 1:
+		if (record->package.count != 18)
+			return AE_ERROR;
+		for (i = 2; i < 18; i++)
+			if (fields[i].type != ACPI_TYPE_INTEGER)
+				return AE_ERROR;
+		hpx->t2 = &hpx->type2_data;
+		hpx->t2->revision      = revision;
+		hpx->t2->unc_err_mask_and      = fields[2].integer.value;
+		hpx->t2->unc_err_mask_or       = fields[3].integer.value;
+		hpx->t2->unc_err_sever_and     = fields[4].integer.value;
+		hpx->t2->unc_err_sever_or      = fields[5].integer.value;
+		hpx->t2->cor_err_mask_and      = fields[6].integer.value;
+		hpx->t2->cor_err_mask_or       = fields[7].integer.value;
+		hpx->t2->adv_err_cap_and       = fields[8].integer.value;
+		hpx->t2->adv_err_cap_or        = fields[9].integer.value;
+		hpx->t2->pci_exp_devctl_and    = fields[10].integer.value;
+		hpx->t2->pci_exp_devctl_or     = fields[11].integer.value;
+		hpx->t2->pci_exp_lnkctl_and    = fields[12].integer.value;
+		hpx->t2->pci_exp_lnkctl_or     = fields[13].integer.value;
+		hpx->t2->sec_unc_err_sever_and = fields[14].integer.value;
+		hpx->t2->sec_unc_err_sever_or  = fields[15].integer.value;
+		hpx->t2->sec_unc_err_mask_and  = fields[16].integer.value;
+		hpx->t2->sec_unc_err_mask_or   = fields[17].integer.value;
+		break;
+	default:
+		printk(KERN_WARNING
+		       "%s: Type 2 Revision %d record not supported\n",
+		       __func__, revision);
+		return AE_ERROR;
+	}
+	return AE_OK;
+}
+
+static acpi_status
+acpi_run_hpx(acpi_handle handle, struct hotplug_params *hpx)
+{
+	acpi_status status;
+	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
+	union acpi_object *package, *record, *fields;
+	u32 type;
+	int i;
+
+	/* Clear the return buffer with zeros */
+	memset(hpx, 0, sizeof(struct hotplug_params));
+
+	status = acpi_evaluate_object(handle, "_HPX", NULL, &buffer);
+	if (ACPI_FAILURE(status))
+		return status;
+
+	package = (union acpi_object *)buffer.pointer;
+	if (package->type != ACPI_TYPE_PACKAGE) {
+		status = AE_ERROR;
+		goto exit;
+	}
+
+	for (i = 0; i < package->package.count; i++) {
+		record = &package->package.elements[i];
+		if (record->type != ACPI_TYPE_PACKAGE) {
+			status = AE_ERROR;
+			goto exit;
+		}
+
+		fields = record->package.elements;
+		if (fields[0].type != ACPI_TYPE_INTEGER ||
+		    fields[1].type != ACPI_TYPE_INTEGER) {
+			status = AE_ERROR;
+			goto exit;
+		}
+
+		type = fields[0].integer.value;
+		switch (type) {
+		case 0:
+			status = decode_type0_hpx_record(record, hpx);
+			if (ACPI_FAILURE(status))
+				goto exit;
+			break;
+		case 1:
+			status = decode_type1_hpx_record(record, hpx);
+			if (ACPI_FAILURE(status))
+				goto exit;
+			break;
+		case 2:
+			status = decode_type2_hpx_record(record, hpx);
+			if (ACPI_FAILURE(status))
+				goto exit;
+			break;
+		default:
+			printk(KERN_ERR "%s: Type %d record not supported\n",
+			       __func__, type);
+			status = AE_ERROR;
+			goto exit;
+		}
+	}
+ exit:
+	kfree(buffer.pointer);
+	return status;
+}
+
+static acpi_status
+acpi_run_hpp(acpi_handle handle, struct hotplug_params *hpp)
+{
+	acpi_status status;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	union acpi_object *package, *fields;
+	int i;
+
+	memset(hpp, 0, sizeof(struct hotplug_params));
+
+	status = acpi_evaluate_object(handle, "_HPP", NULL, &buffer);
+	if (ACPI_FAILURE(status))
+		return status;
+
+	package = (union acpi_object *) buffer.pointer;
+	if (package->type != ACPI_TYPE_PACKAGE ||
+	    package->package.count != 4) {
+		status = AE_ERROR;
+		goto exit;
+	}
+
+	fields = package->package.elements;
+	for (i = 0; i < 4; i++) {
+		if (fields[i].type != ACPI_TYPE_INTEGER) {
+			status = AE_ERROR;
+			goto exit;
+		}
+	}
+
+	hpp->t0 = &hpp->type0_data;
+	hpp->t0->revision        = 1;
+	hpp->t0->cache_line_size = fields[0].integer.value;
+	hpp->t0->latency_timer   = fields[1].integer.value;
+	hpp->t0->enable_serr     = fields[2].integer.value;
+	hpp->t0->enable_perr     = fields[3].integer.value;
+
+exit:
+	kfree(buffer.pointer);
+	return status;
+}
+
+
+
+/* acpi_run_oshp - get control of hotplug from the firmware
+ *
+ * @handle - the handle of the hotplug controller.
+ */
+static acpi_status acpi_run_oshp(acpi_handle handle)
+{
+	acpi_status		status;
+	struct acpi_buffer	string = { ACPI_ALLOCATE_BUFFER, NULL };
+
+	acpi_get_name(handle, ACPI_FULL_PATHNAME, &string);
+
+	/* run OSHP */
+	status = acpi_evaluate_object(handle, METHOD_NAME_OSHP, NULL, NULL);
+	if (ACPI_FAILURE(status))
+		if (status != AE_NOT_FOUND)
+			printk(KERN_ERR "%s:%s OSHP fails=0x%x\n",
+			       __func__, (char *)string.pointer, status);
+		else
+			dbg("%s:%s OSHP not found\n",
+			    __func__, (char *)string.pointer);
+	else
+		pr_debug("%s:%s OSHP passes\n", __func__,
+			(char *)string.pointer);
+
+	kfree(string.pointer);
+	return status;
+}
+
+/* pci_get_hp_params
+ *
+ * @dev - the pci_dev for which we want parameters
+ * @hpp - allocated by the caller
+ */
+int pci_get_hp_params(struct pci_dev *dev, struct hotplug_params *hpp)
+{
+	acpi_status status;
+	acpi_handle handle, phandle;
+	struct pci_bus *pbus;
+
+	handle = NULL;
+	for (pbus = dev->bus; pbus; pbus = pbus->parent) {
+		handle = acpi_pci_get_bridge_handle(pbus);
+		if (handle)
+			break;
+	}
+
+	/*
+	 * _HPP settings apply to all child buses, until another _HPP is
+	 * encountered. If we don't find an _HPP for the input pci dev,
+	 * look for it in the parent device scope since that would apply to
+	 * this pci dev.
+	 */
+	while (handle) {
+		status = acpi_run_hpx(handle, hpp);
+		if (ACPI_SUCCESS(status))
+			return 0;
+		status = acpi_run_hpp(handle, hpp);
+		if (ACPI_SUCCESS(status))
+			return 0;
+		if (acpi_is_root_bridge(handle))
+			break;
+		status = acpi_get_parent(handle, &phandle);
+		if (ACPI_FAILURE(status))
+			break;
+		handle = phandle;
+	}
+	return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(pci_get_hp_params);
+
+/**
+ * acpi_get_hp_hw_control_from_firmware
+ * @dev: the pci_dev of the bridge that has a hotplug controller
+ * @flags: requested control bits for _OSC
+ *
+ * Attempt to take hotplug control from firmware.
+ */
+int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev, u32 flags)
+{
+	acpi_status status;
+	acpi_handle chandle, handle;
+	struct acpi_buffer string = { ACPI_ALLOCATE_BUFFER, NULL };
+
+	flags &= OSC_SHPC_NATIVE_HP_CONTROL;
+	if (!flags) {
+		err("Invalid flags %u specified!\n", flags);
+		return -EINVAL;
+	}
+
+	/*
+	 * Per PCI firmware specification, we should run the ACPI _OSC
+	 * method to get control of hotplug hardware before using it. If
+	 * an _OSC is missing, we look for an OSHP to do the same thing.
+	 * To handle different BIOS behavior, we look for _OSC on a root
+	 * bridge preferentially (according to PCI fw spec). Later for
+	 * OSHP within the scope of the hotplug controller and its parents,
+	 * up to the host bridge under which this controller exists.
+	 */
+	handle = acpi_find_root_bridge_handle(pdev);
+	if (handle) {
+		acpi_get_name(handle, ACPI_FULL_PATHNAME, &string);
+		dbg("Trying to get hotplug control for %s\n",
+				(char *)string.pointer);
+		status = acpi_pci_osc_control_set(handle, &flags, flags);
+		if (ACPI_SUCCESS(status))
+			goto got_one;
+		if (status == AE_SUPPORT)
+			goto no_control;
+		kfree(string.pointer);
+		string = (struct acpi_buffer){ ACPI_ALLOCATE_BUFFER, NULL };
+	}
+
+	handle = DEVICE_ACPI_HANDLE(&pdev->dev);
+	if (!handle) {
+		/*
+		 * This hotplug controller was not listed in the ACPI name
+		 * space at all. Try to get acpi handle of parent pci bus.
+		 */
+		struct pci_bus *pbus;
+		for (pbus = pdev->bus; pbus; pbus = pbus->parent) {
+			handle = acpi_pci_get_bridge_handle(pbus);
+			if (handle)
+				break;
+		}
+	}
+
+	while (handle) {
+		acpi_get_name(handle, ACPI_FULL_PATHNAME, &string);
+		dbg("Trying to get hotplug control for %s \n",
+		    (char *)string.pointer);
+		status = acpi_run_oshp(handle);
+		if (ACPI_SUCCESS(status))
+			goto got_one;
+		if (acpi_is_root_bridge(handle))
+			break;
+		chandle = handle;
+		status = acpi_get_parent(chandle, &handle);
+		if (ACPI_FAILURE(status))
+			break;
+	}
+no_control:
+	dbg("Cannot get control of hotplug hardware for pci %s\n",
+	    pci_name(pdev));
+	kfree(string.pointer);
+	return -ENODEV;
+got_one:
+	dbg("Gained control for hotplug HW for pci %s (%s)\n",
+	    pci_name(pdev), (char *)string.pointer);
+	kfree(string.pointer);
+	return 0;
+}
+EXPORT_SYMBOL(acpi_get_hp_hw_control_from_firmware);
+
+static int is_ejectable(acpi_handle handle)
+{
+	acpi_status status;
+	acpi_handle tmp;
+	unsigned long long removable;
+	status = acpi_get_handle(handle, "_ADR", &tmp);
+	if (ACPI_FAILURE(status))
+		return 0;
+	status = acpi_get_handle(handle, "_EJ0", &tmp);
+	if (ACPI_SUCCESS(status))
+		return 1;
+	status = acpi_evaluate_integer(handle, "_RMV", NULL, &removable);
+	if (ACPI_SUCCESS(status) && removable)
+		return 1;
+	return 0;
+}
+
+/**
+ * acpi_pcihp_check_ejectable - check if handle is ejectable ACPI PCI slot
+ * @pbus: the PCI bus of the PCI slot corresponding to 'handle'
+ * @handle: ACPI handle to check
+ *
+ * Return 1 if handle is ejectable PCI slot, 0 otherwise.
+ */
+int acpi_pci_check_ejectable(struct pci_bus *pbus, acpi_handle handle)
+{
+	acpi_handle bridge_handle, parent_handle;
+
+	if (!(bridge_handle = acpi_pci_get_bridge_handle(pbus)))
+		return 0;
+	if ((ACPI_FAILURE(acpi_get_parent(handle, &parent_handle))))
+		return 0;
+	if (bridge_handle != parent_handle)
+		return 0;
+	return is_ejectable(handle);
+}
+EXPORT_SYMBOL_GPL(acpi_pci_check_ejectable);
+
+static acpi_status
+check_hotplug(acpi_handle handle, u32 lvl, void *context, void **rv)
+{
+	int *found = (int *)context;
+	if (is_ejectable(handle)) {
+		*found = 1;
+		return AE_CTRL_TERMINATE;
+	}
+	return AE_OK;
+}
+
+/**
+ * acpi_pci_detect_ejectable - check if the PCI bus has ejectable slots
+ * @handle - handle of the PCI bus to scan
+ *
+ * Returns 1 if the PCI bus has ACPI based ejectable slots, 0 otherwise.
+ */
+int acpi_pci_detect_ejectable(acpi_handle handle)
+{
+	int found = 0;
+
+	if (!handle)
+		return found;
+
+	acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1,
+			    check_hotplug, NULL, (void *)&found, NULL);
+	return found;
+}
+EXPORT_SYMBOL_GPL(acpi_pci_detect_ejectable);
+
+module_param(debug_acpi, bool, 0644);
+MODULE_PARM_DESC(debug_acpi, "Debugging mode for ACPI enabled or not");
diff --git a/drivers/pci/hotplug/acpiphp.h b/drivers/pci/hotplug/acpiphp.h
new file mode 100644
index 00000000..7722108e
--- /dev/null
+++ b/drivers/pci/hotplug/acpiphp.h
@@ -0,0 +1,212 @@
+/*
+ * ACPI PCI Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ * Copyright (C) 2002 Hiroshi Aono (h-aono@ap.jp.nec.com)
+ * Copyright (C) 2002,2003 Takayoshi Kochi (t-kochi@bq.jp.nec.com)
+ * Copyright (C) 2002,2003 NEC Corporation
+ * Copyright (C) 2003-2005 Matthew Wilcox (matthew.wilcox@hp.com)
+ * Copyright (C) 2003-2005 Hewlett Packard
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <gregkh@us.ibm.com>,
+ *		    <t-kochi@bq.jp.nec.com>
+ *
+ */
+
+#ifndef _ACPIPHP_H
+#define _ACPIPHP_H
+
+#include <linux/acpi.h>
+#include <linux/mutex.h>
+#include <linux/pci_hotplug.h>
+
+#define dbg(format, arg...)					\
+	do {							\
+		if (acpiphp_debug)				\
+			printk(KERN_DEBUG "%s: " format,	\
+				MY_NAME , ## arg);		\
+	} while (0)
+#define err(format, arg...) printk(KERN_ERR "%s: " format, MY_NAME , ## arg)
+#define info(format, arg...) printk(KERN_INFO "%s: " format, MY_NAME , ## arg)
+#define warn(format, arg...) printk(KERN_WARNING "%s: " format, MY_NAME , ## arg)
+
+struct acpiphp_bridge;
+struct acpiphp_slot;
+
+/*
+ * struct slot - slot information for each *physical* slot
+ */
+struct slot {
+	struct hotplug_slot	*hotplug_slot;
+	struct acpiphp_slot	*acpi_slot;
+	struct hotplug_slot_info info;
+};
+
+static inline const char *slot_name(struct slot *slot)
+{
+	return hotplug_slot_name(slot->hotplug_slot);
+}
+
+/*
+ * struct acpiphp_bridge - PCI bridge information
+ *
+ * for each bridge device in ACPI namespace
+ */
+struct acpiphp_bridge {
+	struct list_head list;
+	acpi_handle handle;
+	struct acpiphp_slot *slots;
+
+	/* Ejectable PCI-to-PCI bridge (PCI bridge and PCI function) */
+	struct acpiphp_func *func;
+
+	int type;
+	int nr_slots;
+
+	u32 flags;
+
+	/* This bus (host bridge) or Secondary bus (PCI-to-PCI bridge) */
+	struct pci_bus *pci_bus;
+
+	/* PCI-to-PCI bridge device */
+	struct pci_dev *pci_dev;
+
+	spinlock_t res_lock;
+};
+
+
+/*
+ * struct acpiphp_slot - PCI slot information
+ *
+ * PCI slot information for each *physical* PCI slot
+ */
+struct acpiphp_slot {
+	struct acpiphp_slot *next;
+	struct acpiphp_bridge *bridge;	/* parent */
+	struct list_head funcs;		/* one slot may have different
+					   objects (i.e. for each function) */
+	struct slot *slot;
+	struct mutex crit_sect;
+
+	u8		device;		/* pci device# */
+
+	unsigned long long sun;		/* ACPI _SUN (slot unique number) */
+	u32		flags;		/* see below */
+};
+
+
+/*
+ * struct acpiphp_func - PCI function information
+ *
+ * PCI function information for each object in ACPI namespace
+ * typically 8 objects per slot (i.e. for each PCI function)
+ */
+struct acpiphp_func {
+	struct acpiphp_slot *slot;	/* parent */
+	struct acpiphp_bridge *bridge;	/* Ejectable PCI-to-PCI bridge */
+
+	struct list_head sibling;
+	struct notifier_block nb;
+	acpi_handle	handle;
+
+	u8		function;	/* pci function# */
+	u32		flags;		/* see below */
+};
+
+/*
+ * struct acpiphp_attention_info - device specific attention registration
+ *
+ * ACPI has no generic method of setting/getting attention status
+ * this allows for device specific driver registration
+ */
+struct acpiphp_attention_info
+{
+	int (*set_attn)(struct hotplug_slot *slot, u8 status);
+	int (*get_attn)(struct hotplug_slot *slot, u8 *status);
+	struct module *owner;
+};
+
+/* PCI bus bridge HID */
+#define ACPI_PCI_HOST_HID		"PNP0A03"
+
+/* PCI BRIDGE type */
+#define BRIDGE_TYPE_HOST		0
+#define BRIDGE_TYPE_P2P			1
+
+/* ACPI _STA method value (ignore bit 4; battery present) */
+#define ACPI_STA_PRESENT		(0x00000001)
+#define ACPI_STA_ENABLED		(0x00000002)
+#define ACPI_STA_SHOW_IN_UI		(0x00000004)
+#define ACPI_STA_FUNCTIONING		(0x00000008)
+#define ACPI_STA_ALL			(0x0000000f)
+
+/* bridge flags */
+#define BRIDGE_HAS_STA		(0x00000001)
+#define BRIDGE_HAS_EJ0		(0x00000002)
+#define BRIDGE_HAS_HPP		(0x00000004)
+#define BRIDGE_HAS_PS0		(0x00000010)
+#define BRIDGE_HAS_PS1		(0x00000020)
+#define BRIDGE_HAS_PS2		(0x00000040)
+#define BRIDGE_HAS_PS3		(0x00000080)
+
+/* slot flags */
+
+#define SLOT_POWEREDON		(0x00000001)
+#define SLOT_ENABLED		(0x00000002)
+#define SLOT_MULTIFUNCTION	(0x00000004)
+
+/* function flags */
+
+#define FUNC_HAS_STA		(0x00000001)
+#define FUNC_HAS_EJ0		(0x00000002)
+#define FUNC_HAS_PS0		(0x00000010)
+#define FUNC_HAS_PS1		(0x00000020)
+#define FUNC_HAS_PS2		(0x00000040)
+#define FUNC_HAS_PS3		(0x00000080)
+#define FUNC_HAS_DCK            (0x00000100)
+
+/* function prototypes */
+
+/* acpiphp_core.c */
+extern int acpiphp_register_attention(struct acpiphp_attention_info*info);
+extern int acpiphp_unregister_attention(struct acpiphp_attention_info *info);
+extern int acpiphp_register_hotplug_slot(struct acpiphp_slot *slot);
+extern void acpiphp_unregister_hotplug_slot(struct acpiphp_slot *slot);
+
+/* acpiphp_glue.c */
+extern int acpiphp_glue_init (void);
+extern void acpiphp_glue_exit (void);
+extern int acpiphp_get_num_slots (void);
+typedef int (*acpiphp_callback)(struct acpiphp_slot *slot, void *data);
+
+extern int acpiphp_enable_slot (struct acpiphp_slot *slot);
+extern int acpiphp_disable_slot (struct acpiphp_slot *slot);
+extern int acpiphp_eject_slot (struct acpiphp_slot *slot);
+extern u8 acpiphp_get_power_status (struct acpiphp_slot *slot);
+extern u8 acpiphp_get_attention_status (struct acpiphp_slot *slot);
+extern u8 acpiphp_get_latch_status (struct acpiphp_slot *slot);
+extern u8 acpiphp_get_adapter_status (struct acpiphp_slot *slot);
+
+/* variables */
+extern int acpiphp_debug;
+
+#endif /* _ACPIPHP_H */
diff --git a/drivers/pci/hotplug/acpiphp_core.c b/drivers/pci/hotplug/acpiphp_core.c
new file mode 100644
index 00000000..efa9f2de
--- /dev/null
+++ b/drivers/pci/hotplug/acpiphp_core.c
@@ -0,0 +1,399 @@
+/*
+ * ACPI PCI Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ * Copyright (C) 2002 Hiroshi Aono (h-aono@ap.jp.nec.com)
+ * Copyright (C) 2002,2003 Takayoshi Kochi (t-kochi@bq.jp.nec.com)
+ * Copyright (C) 2002,2003 NEC Corporation
+ * Copyright (C) 2003-2005 Matthew Wilcox (matthew.wilcox@hp.com)
+ * Copyright (C) 2003-2005 Hewlett Packard
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <kristen.c.accardi@intel.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include "acpiphp.h"
+
+#define MY_NAME	"acpiphp"
+
+/* name size which is used for entries in pcihpfs */
+#define SLOT_NAME_SIZE  21              /* {_SUN} */
+
+static int debug;
+int acpiphp_debug;
+
+/* local variables */
+static int num_slots;
+static struct acpiphp_attention_info *attention_info;
+
+#define DRIVER_VERSION	"0.5"
+#define DRIVER_AUTHOR	"Greg Kroah-Hartman <gregkh@us.ibm.com>, Takayoshi Kochi <t-kochi@bq.jp.nec.com>, Matthew Wilcox <willy@hp.com>"
+#define DRIVER_DESC	"ACPI Hot Plug PCI Controller Driver"
+
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+MODULE_PARM_DESC(debug, "Debugging mode enabled or not");
+module_param(debug, bool, 0644);
+
+/* export the attention callback registration methods */
+EXPORT_SYMBOL_GPL(acpiphp_register_attention);
+EXPORT_SYMBOL_GPL(acpiphp_unregister_attention);
+
+static int enable_slot		(struct hotplug_slot *slot);
+static int disable_slot		(struct hotplug_slot *slot);
+static int set_attention_status (struct hotplug_slot *slot, u8 value);
+static int get_power_status	(struct hotplug_slot *slot, u8 *value);
+static int get_attention_status (struct hotplug_slot *slot, u8 *value);
+static int get_latch_status	(struct hotplug_slot *slot, u8 *value);
+static int get_adapter_status	(struct hotplug_slot *slot, u8 *value);
+
+static struct hotplug_slot_ops acpi_hotplug_slot_ops = {
+	.enable_slot		= enable_slot,
+	.disable_slot		= disable_slot,
+	.set_attention_status	= set_attention_status,
+	.get_power_status	= get_power_status,
+	.get_attention_status	= get_attention_status,
+	.get_latch_status	= get_latch_status,
+	.get_adapter_status	= get_adapter_status,
+};
+
+/**
+ * acpiphp_register_attention - set attention LED callback
+ * @info: must be completely filled with LED callbacks
+ *
+ * Description: This is used to register a hardware specific ACPI
+ * driver that manipulates the attention LED.  All the fields in
+ * info must be set.
+ */
+int acpiphp_register_attention(struct acpiphp_attention_info *info)
+{
+	int retval = -EINVAL;
+
+	if (info && info->owner && info->set_attn &&
+			info->get_attn && !attention_info) {
+		retval = 0;
+		attention_info = info;
+	}
+	return retval;
+}
+
+
+/**
+ * acpiphp_unregister_attention - unset attention LED callback
+ * @info: must match the pointer used to register
+ *
+ * Description: This is used to un-register a hardware specific acpi
+ * driver that manipulates the attention LED.  The pointer to the 
+ * info struct must be the same as the one used to set it.
+ */
+int acpiphp_unregister_attention(struct acpiphp_attention_info *info)
+{
+	int retval = -EINVAL;
+
+	if (info && attention_info == info) {
+		attention_info = NULL;
+		retval = 0;
+	}
+	return retval;
+}
+
+
+/**
+ * enable_slot - power on and enable a slot
+ * @hotplug_slot: slot to enable
+ *
+ * Actual tasks are done in acpiphp_enable_slot()
+ */
+static int enable_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
+
+	/* enable the specified slot */
+	return acpiphp_enable_slot(slot->acpi_slot);
+}
+
+
+/**
+ * disable_slot - disable and power off a slot
+ * @hotplug_slot: slot to disable
+ *
+ * Actual tasks are done in acpiphp_disable_slot()
+ */
+static int disable_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+	int retval;
+
+	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
+
+	/* disable the specified slot */
+	retval = acpiphp_disable_slot(slot->acpi_slot);
+	if (!retval)
+		retval = acpiphp_eject_slot(slot->acpi_slot);
+	return retval;
+}
+
+
+/**
+ * set_attention_status - set attention LED
+ * @hotplug_slot: slot to set attention LED on
+ * @status: value to set attention LED to (0 or 1)
+ *
+ * attention status LED, so we use a callback that
+ * was registered with us.  This allows hardware specific
+ * ACPI implementations to blink the light for us.
+ */
+ static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status)
+ {
+	int retval = -ENODEV;
+
+	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot_name(hotplug_slot));
+ 
+	if (attention_info && try_module_get(attention_info->owner)) {
+		retval = attention_info->set_attn(hotplug_slot, status);
+		module_put(attention_info->owner);
+	} else
+		attention_info = NULL;
+	return retval;
+ }
+ 
+
+/**
+ * get_power_status - get power status of a slot
+ * @hotplug_slot: slot to get status
+ * @value: pointer to store status
+ *
+ * Some platforms may not implement _STA method properly.
+ * In that case, the value returned may not be reliable.
+ */
+static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
+
+	*value = acpiphp_get_power_status(slot->acpi_slot);
+
+	return 0;
+}
+
+
+/**
+ * get_attention_status - get attention LED status
+ * @hotplug_slot: slot to get status from
+ * @value: returns with value of attention LED
+ *
+ * ACPI doesn't have known method to determine the state
+ * of the attention status LED, so we use a callback that
+ * was registered with us.  This allows hardware specific
+ * ACPI implementations to determine its state.
+ */
+static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	int retval = -EINVAL;
+
+	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot_name(hotplug_slot));
+
+	if (attention_info && try_module_get(attention_info->owner)) {
+		retval = attention_info->get_attn(hotplug_slot, value);
+		module_put(attention_info->owner);
+	} else
+		attention_info = NULL;
+	return retval;
+}
+
+
+/**
+ * get_latch_status - get latch status of a slot
+ * @hotplug_slot: slot to get status
+ * @value: pointer to store status
+ *
+ * ACPI doesn't provide any formal means to access latch status.
+ * Instead, we fake latch status from _STA.
+ */
+static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
+
+	*value = acpiphp_get_latch_status(slot->acpi_slot);
+
+	return 0;
+}
+
+
+/**
+ * get_adapter_status - get adapter status of a slot
+ * @hotplug_slot: slot to get status
+ * @value: pointer to store status
+ *
+ * ACPI doesn't provide any formal means to access adapter status.
+ * Instead, we fake adapter status from _STA.
+ */
+static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
+
+	*value = acpiphp_get_adapter_status(slot->acpi_slot);
+
+	return 0;
+}
+
+static int __init init_acpi(void)
+{
+	int retval;
+
+	/* initialize internal data structure etc. */
+	retval = acpiphp_glue_init();
+
+	/* read initial number of slots */
+	if (!retval) {
+		num_slots = acpiphp_get_num_slots();
+		if (num_slots == 0) {
+			acpiphp_glue_exit();
+			retval = -ENODEV;
+		}
+	}
+
+	return retval;
+}
+
+/**
+ * release_slot - free up the memory used by a slot
+ * @hotplug_slot: slot to free
+ */
+static void release_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
+
+	kfree(slot->hotplug_slot);
+	kfree(slot);
+}
+
+/* callback routine to initialize 'struct slot' for each slot */
+int acpiphp_register_hotplug_slot(struct acpiphp_slot *acpiphp_slot)
+{
+	struct slot *slot;
+	int retval = -ENOMEM;
+	char name[SLOT_NAME_SIZE];
+
+	slot = kzalloc(sizeof(*slot), GFP_KERNEL);
+	if (!slot)
+		goto error;
+
+	slot->hotplug_slot = kzalloc(sizeof(*slot->hotplug_slot), GFP_KERNEL);
+	if (!slot->hotplug_slot)
+		goto error_slot;
+
+	slot->hotplug_slot->info = &slot->info;
+
+	slot->hotplug_slot->private = slot;
+	slot->hotplug_slot->release = &release_slot;
+	slot->hotplug_slot->ops = &acpi_hotplug_slot_ops;
+
+	slot->acpi_slot = acpiphp_slot;
+	slot->hotplug_slot->info->power_status = acpiphp_get_power_status(slot->acpi_slot);
+	slot->hotplug_slot->info->attention_status = 0;
+	slot->hotplug_slot->info->latch_status = acpiphp_get_latch_status(slot->acpi_slot);
+	slot->hotplug_slot->info->adapter_status = acpiphp_get_adapter_status(slot->acpi_slot);
+
+	acpiphp_slot->slot = slot;
+	snprintf(name, SLOT_NAME_SIZE, "%llu", slot->acpi_slot->sun);
+
+	retval = pci_hp_register(slot->hotplug_slot,
+					acpiphp_slot->bridge->pci_bus,
+					acpiphp_slot->device,
+					name);
+	if (retval == -EBUSY)
+		goto error_hpslot;
+	if (retval) {
+		err("pci_hp_register failed with error %d\n", retval);
+		goto error_hpslot;
+ 	}
+
+	info("Slot [%s] registered\n", slot_name(slot));
+
+	return 0;
+error_hpslot:
+	kfree(slot->hotplug_slot);
+error_slot:
+	kfree(slot);
+error:
+	return retval;
+}
+
+
+void acpiphp_unregister_hotplug_slot(struct acpiphp_slot *acpiphp_slot)
+{
+	struct slot *slot = acpiphp_slot->slot;
+	int retval = 0;
+
+	info("Slot [%s] unregistered\n", slot_name(slot));
+
+	retval = pci_hp_deregister(slot->hotplug_slot);
+	if (retval)
+		err("pci_hp_deregister failed with error %d\n", retval);
+}
+
+
+static int __init acpiphp_init(void)
+{
+	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
+
+	if (acpi_pci_disabled)
+		return 0;
+
+	acpiphp_debug = debug;
+
+	/* read all the ACPI info from the system */
+	return init_acpi();
+}
+
+
+static void __exit acpiphp_exit(void)
+{
+	if (acpi_pci_disabled)
+		return;
+
+	/* deallocate internal data structures etc. */
+	acpiphp_glue_exit();
+}
+
+module_init(acpiphp_init);
+module_exit(acpiphp_exit);
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
new file mode 100644
index 00000000..a70fa89f
--- /dev/null
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -0,0 +1,1485 @@
+/*
+ * ACPI PCI HotPlug glue functions to ACPI CA subsystem
+ *
+ * Copyright (C) 2002,2003 Takayoshi Kochi (t-kochi@bq.jp.nec.com)
+ * Copyright (C) 2002 Hiroshi Aono (h-aono@ap.jp.nec.com)
+ * Copyright (C) 2002,2003 NEC Corporation
+ * Copyright (C) 2003-2005 Matthew Wilcox (matthew.wilcox@hp.com)
+ * Copyright (C) 2003-2005 Hewlett Packard
+ * Copyright (C) 2005 Rajesh Shah (rajesh.shah@intel.com)
+ * Copyright (C) 2005 Intel Corporation
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <kristen.c.accardi@intel.com>
+ *
+ */
+
+/*
+ * Lifetime rules for pci_dev:
+ *  - The one in acpiphp_bridge has its refcount elevated by pci_get_slot()
+ *    when the bridge is scanned and it loses a refcount when the bridge
+ *    is removed.
+ *  - When a P2P bridge is present, we elevate the refcount on the subordinate
+ *    bus. It loses the refcount when the the driver unloads.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/pci-acpi.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+
+#include "../pci.h"
+#include "acpiphp.h"
+
+static LIST_HEAD(bridge_list);
+
+#define MY_NAME "acpiphp_glue"
+
+static void handle_hotplug_event_bridge (acpi_handle, u32, void *);
+static void acpiphp_sanitize_bus(struct pci_bus *bus);
+static void acpiphp_set_hpp_values(struct pci_bus *bus);
+static void handle_hotplug_event_func(acpi_handle handle, u32 type, void *context);
+
+/* callback routine to check for the existence of a pci dock device */
+static acpi_status
+is_pci_dock_device(acpi_handle handle, u32 lvl, void *context, void **rv)
+{
+	int *count = (int *)context;
+
+	if (is_dock_device(handle)) {
+		(*count)++;
+		return AE_CTRL_TERMINATE;
+	} else {
+		return AE_OK;
+	}
+}
+
+/*
+ * the _DCK method can do funny things... and sometimes not
+ * hah-hah funny.
+ *
+ * TBD - figure out a way to only call fixups for
+ * systems that require them.
+ */
+static int post_dock_fixups(struct notifier_block *nb, unsigned long val,
+	void *v)
+{
+	struct acpiphp_func *func = container_of(nb, struct acpiphp_func, nb);
+	struct pci_bus *bus = func->slot->bridge->pci_bus;
+	u32 buses;
+
+	if (!bus->self)
+		return  NOTIFY_OK;
+
+	/* fixup bad _DCK function that rewrites
+	 * secondary bridge on slot
+	 */
+	pci_read_config_dword(bus->self,
+			PCI_PRIMARY_BUS,
+			&buses);
+
+	if (((buses >> 8) & 0xff) != bus->secondary) {
+		buses = (buses & 0xff000000)
+			| ((unsigned int)(bus->primary)     <<  0)
+			| ((unsigned int)(bus->secondary)   <<  8)
+			| ((unsigned int)(bus->subordinate) << 16);
+		pci_write_config_dword(bus->self, PCI_PRIMARY_BUS, buses);
+	}
+	return NOTIFY_OK;
+}
+
+
+static struct acpi_dock_ops acpiphp_dock_ops = {
+	.handler = handle_hotplug_event_func,
+};
+
+/* callback routine to register each ACPI PCI slot object */
+static acpi_status
+register_slot(acpi_handle handle, u32 lvl, void *context, void **rv)
+{
+	struct acpiphp_bridge *bridge = (struct acpiphp_bridge *)context;
+	struct acpiphp_slot *slot;
+	struct acpiphp_func *newfunc;
+	acpi_handle tmp;
+	acpi_status status = AE_OK;
+	unsigned long long adr, sun;
+	int device, function, retval;
+	struct pci_bus *pbus = bridge->pci_bus;
+	struct pci_dev *pdev;
+
+	if (!acpi_pci_check_ejectable(pbus, handle) && !is_dock_device(handle))
+		return AE_OK;
+
+	acpi_evaluate_integer(handle, "_ADR", NULL, &adr);
+	device = (adr >> 16) & 0xffff;
+	function = adr & 0xffff;
+
+	newfunc = kzalloc(sizeof(struct acpiphp_func), GFP_KERNEL);
+	if (!newfunc)
+		return AE_NO_MEMORY;
+
+	INIT_LIST_HEAD(&newfunc->sibling);
+	newfunc->handle = handle;
+	newfunc->function = function;
+
+	if (ACPI_SUCCESS(acpi_get_handle(handle, "_EJ0", &tmp)))
+		newfunc->flags = FUNC_HAS_EJ0;
+
+	if (ACPI_SUCCESS(acpi_get_handle(handle, "_STA", &tmp)))
+		newfunc->flags |= FUNC_HAS_STA;
+
+	if (ACPI_SUCCESS(acpi_get_handle(handle, "_PS0", &tmp)))
+		newfunc->flags |= FUNC_HAS_PS0;
+
+	if (ACPI_SUCCESS(acpi_get_handle(handle, "_PS3", &tmp)))
+		newfunc->flags |= FUNC_HAS_PS3;
+
+	if (ACPI_SUCCESS(acpi_get_handle(handle, "_DCK", &tmp)))
+		newfunc->flags |= FUNC_HAS_DCK;
+
+	status = acpi_evaluate_integer(handle, "_SUN", NULL, &sun);
+	if (ACPI_FAILURE(status)) {
+		/*
+		 * use the count of the number of slots we've found
+		 * for the number of the slot
+		 */
+		sun = bridge->nr_slots+1;
+	}
+
+	/* search for objects that share the same slot */
+	for (slot = bridge->slots; slot; slot = slot->next)
+		if (slot->device == device) {
+			if (slot->sun != sun)
+				warn("sibling found, but _SUN doesn't match!\n");
+			break;
+		}
+
+	if (!slot) {
+		slot = kzalloc(sizeof(struct acpiphp_slot), GFP_KERNEL);
+		if (!slot) {
+			kfree(newfunc);
+			return AE_NO_MEMORY;
+		}
+
+		slot->bridge = bridge;
+		slot->device = device;
+		slot->sun = sun;
+		INIT_LIST_HEAD(&slot->funcs);
+		mutex_init(&slot->crit_sect);
+
+		slot->next = bridge->slots;
+		bridge->slots = slot;
+
+		bridge->nr_slots++;
+
+		dbg("found ACPI PCI Hotplug slot %llu at PCI %04x:%02x:%02x\n",
+		    slot->sun, pci_domain_nr(pbus), pbus->number, device);
+		retval = acpiphp_register_hotplug_slot(slot);
+		if (retval) {
+			if (retval == -EBUSY)
+				warn("Slot %llu already registered by another "
+					"hotplug driver\n", slot->sun);
+			else
+				warn("acpiphp_register_hotplug_slot failed "
+					"(err code = 0x%x)\n", retval);
+			goto err_exit;
+		}
+	}
+
+	newfunc->slot = slot;
+	list_add_tail(&newfunc->sibling, &slot->funcs);
+
+	pdev = pci_get_slot(pbus, PCI_DEVFN(device, function));
+	if (pdev) {
+		pdev->current_state = PCI_D0;
+		slot->flags |= (SLOT_ENABLED | SLOT_POWEREDON);
+		pci_dev_put(pdev);
+	}
+
+	if (is_dock_device(handle)) {
+		/* we don't want to call this device's _EJ0
+		 * because we want the dock notify handler
+		 * to call it after it calls _DCK
+		 */
+		newfunc->flags &= ~FUNC_HAS_EJ0;
+		if (register_hotplug_dock_device(handle,
+			&acpiphp_dock_ops, newfunc))
+			dbg("failed to register dock device\n");
+
+		/* we need to be notified when dock events happen
+		 * outside of the hotplug operation, since we may
+		 * need to do fixups before we can hotplug.
+		 */
+		newfunc->nb.notifier_call = post_dock_fixups;
+		if (register_dock_notifier(&newfunc->nb))
+			dbg("failed to register a dock notifier");
+	}
+
+	/* install notify handler */
+	if (!(newfunc->flags & FUNC_HAS_DCK)) {
+		status = acpi_install_notify_handler(handle,
+					     ACPI_SYSTEM_NOTIFY,
+					     handle_hotplug_event_func,
+					     newfunc);
+
+		if (ACPI_FAILURE(status))
+			err("failed to register interrupt notify handler\n");
+	} else
+		status = AE_OK;
+
+	return status;
+
+ err_exit:
+	bridge->nr_slots--;
+	bridge->slots = slot->next;
+	kfree(slot);
+	kfree(newfunc);
+
+	return AE_OK;
+}
+
+
+/* see if it's worth looking at this bridge */
+static int detect_ejectable_slots(acpi_handle handle)
+{
+	int found = acpi_pci_detect_ejectable(handle);
+	if (!found) {
+		acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1,
+				    is_pci_dock_device, NULL, (void *)&found, NULL);
+	}
+	return found;
+}
+
+/* initialize miscellaneous stuff for both root and PCI-to-PCI bridge */
+static void init_bridge_misc(struct acpiphp_bridge *bridge)
+{
+	acpi_status status;
+
+	/* must be added to the list prior to calling register_slot */
+	list_add(&bridge->list, &bridge_list);
+
+	/* register all slot objects under this bridge */
+	status = acpi_walk_namespace(ACPI_TYPE_DEVICE, bridge->handle, (u32)1,
+				     register_slot, NULL, bridge, NULL);
+	if (ACPI_FAILURE(status)) {
+		list_del(&bridge->list);
+		return;
+	}
+
+	/* install notify handler */
+	if (bridge->type != BRIDGE_TYPE_HOST) {
+		if ((bridge->flags & BRIDGE_HAS_EJ0) && bridge->func) {
+			status = acpi_remove_notify_handler(bridge->func->handle,
+						ACPI_SYSTEM_NOTIFY,
+						handle_hotplug_event_func);
+			if (ACPI_FAILURE(status))
+				err("failed to remove notify handler\n");
+		}
+		status = acpi_install_notify_handler(bridge->handle,
+					     ACPI_SYSTEM_NOTIFY,
+					     handle_hotplug_event_bridge,
+					     bridge);
+
+		if (ACPI_FAILURE(status)) {
+			err("failed to register interrupt notify handler\n");
+		}
+	}
+}
+
+
+/* find acpiphp_func from acpiphp_bridge */
+static struct acpiphp_func *acpiphp_bridge_handle_to_function(acpi_handle handle)
+{
+	struct acpiphp_bridge *bridge;
+	struct acpiphp_slot *slot;
+	struct acpiphp_func *func;
+
+	list_for_each_entry(bridge, &bridge_list, list) {
+		for (slot = bridge->slots; slot; slot = slot->next) {
+			list_for_each_entry(func, &slot->funcs, sibling) {
+				if (func->handle == handle)
+					return func;
+			}
+		}
+	}
+
+	return NULL;
+}
+
+
+static inline void config_p2p_bridge_flags(struct acpiphp_bridge *bridge)
+{
+	acpi_handle dummy_handle;
+
+	if (ACPI_SUCCESS(acpi_get_handle(bridge->handle,
+					"_STA", &dummy_handle)))
+		bridge->flags |= BRIDGE_HAS_STA;
+
+	if (ACPI_SUCCESS(acpi_get_handle(bridge->handle,
+					"_EJ0", &dummy_handle)))
+		bridge->flags |= BRIDGE_HAS_EJ0;
+
+	if (ACPI_SUCCESS(acpi_get_handle(bridge->handle,
+					"_PS0", &dummy_handle)))
+		bridge->flags |= BRIDGE_HAS_PS0;
+
+	if (ACPI_SUCCESS(acpi_get_handle(bridge->handle,
+					"_PS3", &dummy_handle)))
+		bridge->flags |= BRIDGE_HAS_PS3;
+
+	/* is this ejectable p2p bridge? */
+	if (bridge->flags & BRIDGE_HAS_EJ0) {
+		struct acpiphp_func *func;
+
+		dbg("found ejectable p2p bridge\n");
+
+		/* make link between PCI bridge and PCI function */
+		func = acpiphp_bridge_handle_to_function(bridge->handle);
+		if (!func)
+			return;
+		bridge->func = func;
+		func->bridge = bridge;
+	}
+}
+
+
+/* allocate and initialize host bridge data structure */
+static void add_host_bridge(acpi_handle *handle)
+{
+	struct acpiphp_bridge *bridge;
+	struct acpi_pci_root *root = acpi_pci_find_root(handle);
+
+	bridge = kzalloc(sizeof(struct acpiphp_bridge), GFP_KERNEL);
+	if (bridge == NULL)
+		return;
+
+	bridge->type = BRIDGE_TYPE_HOST;
+	bridge->handle = handle;
+
+	bridge->pci_bus = root->bus;
+
+	spin_lock_init(&bridge->res_lock);
+
+	init_bridge_misc(bridge);
+}
+
+
+/* allocate and initialize PCI-to-PCI bridge data structure */
+static void add_p2p_bridge(acpi_handle *handle)
+{
+	struct acpiphp_bridge *bridge;
+
+	bridge = kzalloc(sizeof(struct acpiphp_bridge), GFP_KERNEL);
+	if (bridge == NULL) {
+		err("out of memory\n");
+		return;
+	}
+
+	bridge->type = BRIDGE_TYPE_P2P;
+	bridge->handle = handle;
+	config_p2p_bridge_flags(bridge);
+
+	bridge->pci_dev = acpi_get_pci_dev(handle);
+	bridge->pci_bus = bridge->pci_dev->subordinate;
+	if (!bridge->pci_bus) {
+		err("This is not a PCI-to-PCI bridge!\n");
+		goto err;
+	}
+
+	/*
+	 * Grab a ref to the subordinate PCI bus in case the bus is
+	 * removed via PCI core logical hotplug. The ref pins the bus
+	 * (which we access during module unload).
+	 */
+	get_device(&bridge->pci_bus->dev);
+	spin_lock_init(&bridge->res_lock);
+
+	init_bridge_misc(bridge);
+	return;
+ err:
+	pci_dev_put(bridge->pci_dev);
+	kfree(bridge);
+	return;
+}
+
+
+/* callback routine to find P2P bridges */
+static acpi_status
+find_p2p_bridge(acpi_handle handle, u32 lvl, void *context, void **rv)
+{
+	acpi_status status;
+	struct pci_dev *dev;
+
+	dev = acpi_get_pci_dev(handle);
+	if (!dev || !dev->subordinate)
+		goto out;
+
+	/* check if this bridge has ejectable slots */
+	if ((detect_ejectable_slots(handle) > 0)) {
+		dbg("found PCI-to-PCI bridge at PCI %s\n", pci_name(dev));
+		add_p2p_bridge(handle);
+	}
+
+	/* search P2P bridges under this p2p bridge */
+	status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1,
+				     find_p2p_bridge, NULL, NULL, NULL);
+	if (ACPI_FAILURE(status))
+		warn("find_p2p_bridge failed (error code = 0x%x)\n", status);
+
+ out:
+	pci_dev_put(dev);
+	return AE_OK;
+}
+
+
+/* find hot-pluggable slots, and then find P2P bridge */
+static int add_bridge(acpi_handle handle)
+{
+	acpi_status status;
+	unsigned long long tmp;
+	acpi_handle dummy_handle;
+
+	/* if the bridge doesn't have _STA, we assume it is always there */
+	status = acpi_get_handle(handle, "_STA", &dummy_handle);
+	if (ACPI_SUCCESS(status)) {
+		status = acpi_evaluate_integer(handle, "_STA", NULL, &tmp);
+		if (ACPI_FAILURE(status)) {
+			dbg("%s: _STA evaluation failure\n", __func__);
+			return 0;
+		}
+		if ((tmp & ACPI_STA_FUNCTIONING) == 0)
+			/* don't register this object */
+			return 0;
+	}
+
+	/* check if this bridge has ejectable slots */
+	if (detect_ejectable_slots(handle) > 0) {
+		dbg("found PCI host-bus bridge with hot-pluggable slots\n");
+		add_host_bridge(handle);
+	}
+
+	/* search P2P bridges under this host bridge */
+	status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1,
+				     find_p2p_bridge, NULL, NULL, NULL);
+
+	if (ACPI_FAILURE(status))
+		warn("find_p2p_bridge failed (error code = 0x%x)\n", status);
+
+	return 0;
+}
+
+static struct acpiphp_bridge *acpiphp_handle_to_bridge(acpi_handle handle)
+{
+	struct acpiphp_bridge *bridge;
+
+	list_for_each_entry(bridge, &bridge_list, list)
+		if (bridge->handle == handle)
+			return bridge;
+
+	return NULL;
+}
+
+static void cleanup_bridge(struct acpiphp_bridge *bridge)
+{
+	struct acpiphp_slot *slot, *next;
+	struct acpiphp_func *func, *tmp;
+	acpi_status status;
+	acpi_handle handle = bridge->handle;
+
+	status = acpi_remove_notify_handler(handle, ACPI_SYSTEM_NOTIFY,
+					    handle_hotplug_event_bridge);
+	if (ACPI_FAILURE(status))
+		err("failed to remove notify handler\n");
+
+	if ((bridge->type != BRIDGE_TYPE_HOST) &&
+	    ((bridge->flags & BRIDGE_HAS_EJ0) && bridge->func)) {
+		status = acpi_install_notify_handler(bridge->func->handle,
+						ACPI_SYSTEM_NOTIFY,
+						handle_hotplug_event_func,
+						bridge->func);
+		if (ACPI_FAILURE(status))
+			err("failed to install interrupt notify handler\n");
+	}
+
+	slot = bridge->slots;
+	while (slot) {
+		next = slot->next;
+		list_for_each_entry_safe(func, tmp, &slot->funcs, sibling) {
+			if (is_dock_device(func->handle)) {
+				unregister_hotplug_dock_device(func->handle);
+				unregister_dock_notifier(&func->nb);
+			}
+			if (!(func->flags & FUNC_HAS_DCK)) {
+				status = acpi_remove_notify_handler(func->handle,
+						ACPI_SYSTEM_NOTIFY,
+						handle_hotplug_event_func);
+				if (ACPI_FAILURE(status))
+					err("failed to remove notify handler\n");
+			}
+			list_del(&func->sibling);
+			kfree(func);
+		}
+		acpiphp_unregister_hotplug_slot(slot);
+		list_del(&slot->funcs);
+		kfree(slot);
+		slot = next;
+	}
+
+	/*
+	 * Only P2P bridges have a pci_dev
+	 */
+	if (bridge->pci_dev)
+		put_device(&bridge->pci_bus->dev);
+
+	pci_dev_put(bridge->pci_dev);
+	list_del(&bridge->list);
+	kfree(bridge);
+}
+
+static acpi_status
+cleanup_p2p_bridge(acpi_handle handle, u32 lvl, void *context, void **rv)
+{
+	struct acpiphp_bridge *bridge;
+
+	/* cleanup p2p bridges under this P2P bridge
+	   in a depth-first manner */
+	acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1,
+				cleanup_p2p_bridge, NULL, NULL, NULL);
+
+	bridge = acpiphp_handle_to_bridge(handle);
+	if (bridge)
+		cleanup_bridge(bridge);
+
+	return AE_OK;
+}
+
+static void remove_bridge(acpi_handle handle)
+{
+	struct acpiphp_bridge *bridge;
+
+	/* cleanup p2p bridges under this host bridge
+	   in a depth-first manner */
+	acpi_walk_namespace(ACPI_TYPE_DEVICE, handle,
+				(u32)1, cleanup_p2p_bridge, NULL, NULL, NULL);
+
+	/*
+	 * On root bridges with hotplug slots directly underneath (ie,
+	 * no p2p bridge between), we call cleanup_bridge(). 
+	 *
+	 * The else clause cleans up root bridges that either had no
+	 * hotplug slots at all, or had a p2p bridge underneath.
+	 */
+	bridge = acpiphp_handle_to_bridge(handle);
+	if (bridge)
+		cleanup_bridge(bridge);
+	else
+		acpi_remove_notify_handler(handle, ACPI_SYSTEM_NOTIFY,
+					   handle_hotplug_event_bridge);
+}
+
+static int power_on_slot(struct acpiphp_slot *slot)
+{
+	acpi_status status;
+	struct acpiphp_func *func;
+	int retval = 0;
+
+	/* if already enabled, just skip */
+	if (slot->flags & SLOT_POWEREDON)
+		goto err_exit;
+
+	list_for_each_entry(func, &slot->funcs, sibling) {
+		if (func->flags & FUNC_HAS_PS0) {
+			dbg("%s: executing _PS0\n", __func__);
+			status = acpi_evaluate_object(func->handle, "_PS0", NULL, NULL);
+			if (ACPI_FAILURE(status)) {
+				warn("%s: _PS0 failed\n", __func__);
+				retval = -1;
+				goto err_exit;
+			} else
+				break;
+		}
+	}
+
+	/* TBD: evaluate _STA to check if the slot is enabled */
+
+	slot->flags |= SLOT_POWEREDON;
+
+ err_exit:
+	return retval;
+}
+
+
+static int power_off_slot(struct acpiphp_slot *slot)
+{
+	acpi_status status;
+	struct acpiphp_func *func;
+
+	int retval = 0;
+
+	/* if already disabled, just skip */
+	if ((slot->flags & SLOT_POWEREDON) == 0)
+		goto err_exit;
+
+	list_for_each_entry(func, &slot->funcs, sibling) {
+		if (func->flags & FUNC_HAS_PS3) {
+			status = acpi_evaluate_object(func->handle, "_PS3", NULL, NULL);
+			if (ACPI_FAILURE(status)) {
+				warn("%s: _PS3 failed\n", __func__);
+				retval = -1;
+				goto err_exit;
+			} else
+				break;
+		}
+	}
+
+	/* TBD: evaluate _STA to check if the slot is disabled */
+
+	slot->flags &= (~SLOT_POWEREDON);
+
+ err_exit:
+	return retval;
+}
+
+
+
+/**
+ * acpiphp_max_busnr - return the highest reserved bus number under the given bus.
+ * @bus: bus to start search with
+ */
+static unsigned char acpiphp_max_busnr(struct pci_bus *bus)
+{
+	struct list_head *tmp;
+	unsigned char max, n;
+
+	/*
+	 * pci_bus_max_busnr will return the highest
+	 * reserved busnr for all these children.
+	 * that is equivalent to the bus->subordinate
+	 * value.  We don't want to use the parent's
+	 * bus->subordinate value because it could have
+	 * padding in it.
+	 */
+	max = bus->secondary;
+
+	list_for_each(tmp, &bus->children) {
+		n = pci_bus_max_busnr(pci_bus_b(tmp));
+		if (n > max)
+			max = n;
+	}
+	return max;
+}
+
+
+/**
+ * acpiphp_bus_add - add a new bus to acpi subsystem
+ * @func: acpiphp_func of the bridge
+ */
+static int acpiphp_bus_add(struct acpiphp_func *func)
+{
+	acpi_handle phandle;
+	struct acpi_device *device, *pdevice;
+	int ret_val;
+
+	acpi_get_parent(func->handle, &phandle);
+	if (acpi_bus_get_device(phandle, &pdevice)) {
+		dbg("no parent device, assuming NULL\n");
+		pdevice = NULL;
+	}
+	if (!acpi_bus_get_device(func->handle, &device)) {
+		dbg("bus exists... trim\n");
+		/* this shouldn't be in here, so remove
+		 * the bus then re-add it...
+		 */
+		ret_val = acpi_bus_trim(device, 1);
+		dbg("acpi_bus_trim return %x\n", ret_val);
+	}
+
+	ret_val = acpi_bus_add(&device, pdevice, func->handle,
+		ACPI_BUS_TYPE_DEVICE);
+	if (ret_val) {
+		dbg("error adding bus, %x\n",
+			-ret_val);
+		goto acpiphp_bus_add_out;
+	}
+	ret_val = acpi_bus_start(device);
+
+acpiphp_bus_add_out:
+	return ret_val;
+}
+
+
+/**
+ * acpiphp_bus_trim - trim a bus from acpi subsystem
+ * @handle: handle to acpi namespace
+ */
+static int acpiphp_bus_trim(acpi_handle handle)
+{
+	struct acpi_device *device;
+	int retval;
+
+	retval = acpi_bus_get_device(handle, &device);
+	if (retval) {
+		dbg("acpi_device not found\n");
+		return retval;
+	}
+
+	retval = acpi_bus_trim(device, 1);
+	if (retval)
+		err("cannot remove from acpi list\n");
+
+	return retval;
+}
+
+static void acpiphp_set_acpi_region(struct acpiphp_slot *slot)
+{
+	struct acpiphp_func *func;
+	union acpi_object params[2];
+	struct acpi_object_list arg_list;
+
+	list_for_each_entry(func, &slot->funcs, sibling) {
+		arg_list.count = 2;
+		arg_list.pointer = params;
+		params[0].type = ACPI_TYPE_INTEGER;
+		params[0].integer.value = ACPI_ADR_SPACE_PCI_CONFIG;
+		params[1].type = ACPI_TYPE_INTEGER;
+		params[1].integer.value = 1;
+		/* _REG is optional, we don't care about if there is failure */
+		acpi_evaluate_object(func->handle, "_REG", &arg_list, NULL);
+	}
+}
+
+/**
+ * enable_device - enable, configure a slot
+ * @slot: slot to be enabled
+ *
+ * This function should be called per *physical slot*,
+ * not per each slot object in ACPI namespace.
+ */
+static int __ref enable_device(struct acpiphp_slot *slot)
+{
+	struct pci_dev *dev;
+	struct pci_bus *bus = slot->bridge->pci_bus;
+	struct acpiphp_func *func;
+	int retval = 0;
+	int num, max, pass;
+	acpi_status status;
+
+	if (slot->flags & SLOT_ENABLED)
+		goto err_exit;
+
+	/* sanity check: dev should be NULL when hot-plugged in */
+	dev = pci_get_slot(bus, PCI_DEVFN(slot->device, 0));
+	if (dev) {
+		/* This case shouldn't happen */
+		err("pci_dev structure already exists.\n");
+		pci_dev_put(dev);
+		retval = -1;
+		goto err_exit;
+	}
+
+	num = pci_scan_slot(bus, PCI_DEVFN(slot->device, 0));
+	if (num == 0) {
+		err("No new device found\n");
+		retval = -1;
+		goto err_exit;
+	}
+
+	max = acpiphp_max_busnr(bus);
+	for (pass = 0; pass < 2; pass++) {
+		list_for_each_entry(dev, &bus->devices, bus_list) {
+			if (PCI_SLOT(dev->devfn) != slot->device)
+				continue;
+			if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE ||
+			    dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) {
+				max = pci_scan_bridge(bus, dev, max, pass);
+				if (pass && dev->subordinate)
+					pci_bus_size_bridges(dev->subordinate);
+			}
+		}
+	}
+
+	list_for_each_entry(func, &slot->funcs, sibling)
+		acpiphp_bus_add(func);
+
+	pci_bus_assign_resources(bus);
+	acpiphp_sanitize_bus(bus);
+	acpiphp_set_hpp_values(bus);
+	acpiphp_set_acpi_region(slot);
+	pci_enable_bridges(bus);
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		/* Assume that newly added devices are powered on already. */
+		if (!dev->is_added)
+			dev->current_state = PCI_D0;
+	}
+
+	pci_bus_add_devices(bus);
+
+	list_for_each_entry(func, &slot->funcs, sibling) {
+		dev = pci_get_slot(bus, PCI_DEVFN(slot->device,
+						  func->function));
+		if (!dev)
+			continue;
+
+		if (dev->hdr_type != PCI_HEADER_TYPE_BRIDGE &&
+		    dev->hdr_type != PCI_HEADER_TYPE_CARDBUS) {
+			pci_dev_put(dev);
+			continue;
+		}
+
+		status = find_p2p_bridge(func->handle, (u32)1, bus, NULL);
+		if (ACPI_FAILURE(status))
+			warn("find_p2p_bridge failed (error code = 0x%x)\n",
+				status);
+		pci_dev_put(dev);
+	}
+
+	slot->flags |= SLOT_ENABLED;
+
+ err_exit:
+	return retval;
+}
+
+static void disable_bridges(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		if (dev->subordinate) {
+			disable_bridges(dev->subordinate);
+			pci_disable_device(dev);
+		}
+	}
+}
+
+/**
+ * disable_device - disable a slot
+ * @slot: ACPI PHP slot
+ */
+static int disable_device(struct acpiphp_slot *slot)
+{
+	struct acpiphp_func *func;
+	struct pci_dev *pdev;
+
+	/* is this slot already disabled? */
+	if (!(slot->flags & SLOT_ENABLED))
+		goto err_exit;
+
+	list_for_each_entry(func, &slot->funcs, sibling) {
+		if (func->bridge) {
+			/* cleanup p2p bridges under this P2P bridge */
+			cleanup_p2p_bridge(func->bridge->handle,
+						(u32)1, NULL, NULL);
+			func->bridge = NULL;
+		}
+
+		pdev = pci_get_slot(slot->bridge->pci_bus,
+				    PCI_DEVFN(slot->device, func->function));
+		if (pdev) {
+			pci_stop_bus_device(pdev);
+			if (pdev->subordinate) {
+				disable_bridges(pdev->subordinate);
+				pci_disable_device(pdev);
+			}
+			pci_remove_bus_device(pdev);
+			pci_dev_put(pdev);
+		}
+	}
+
+	list_for_each_entry(func, &slot->funcs, sibling) {
+		acpiphp_bus_trim(func->handle);
+	}
+
+	slot->flags &= (~SLOT_ENABLED);
+
+err_exit:
+	return 0;
+}
+
+
+/**
+ * get_slot_status - get ACPI slot status
+ * @slot: ACPI PHP slot
+ *
+ * If a slot has _STA for each function and if any one of them
+ * returned non-zero status, return it.
+ *
+ * If a slot doesn't have _STA and if any one of its functions'
+ * configuration space is configured, return 0x0f as a _STA.
+ *
+ * Otherwise return 0.
+ */
+static unsigned int get_slot_status(struct acpiphp_slot *slot)
+{
+	acpi_status status;
+	unsigned long long sta = 0;
+	u32 dvid;
+	struct acpiphp_func *func;
+
+	list_for_each_entry(func, &slot->funcs, sibling) {
+		if (func->flags & FUNC_HAS_STA) {
+			status = acpi_evaluate_integer(func->handle, "_STA", NULL, &sta);
+			if (ACPI_SUCCESS(status) && sta)
+				break;
+		} else {
+			pci_bus_read_config_dword(slot->bridge->pci_bus,
+						  PCI_DEVFN(slot->device,
+							    func->function),
+						  PCI_VENDOR_ID, &dvid);
+			if (dvid != 0xffffffff) {
+				sta = ACPI_STA_ALL;
+				break;
+			}
+		}
+	}
+
+	return (unsigned int)sta;
+}
+
+/**
+ * acpiphp_eject_slot - physically eject the slot
+ * @slot: ACPI PHP slot
+ */
+int acpiphp_eject_slot(struct acpiphp_slot *slot)
+{
+	acpi_status status;
+	struct acpiphp_func *func;
+	struct acpi_object_list arg_list;
+	union acpi_object arg;
+
+	list_for_each_entry(func, &slot->funcs, sibling) {
+		/* We don't want to call _EJ0 on non-existing functions. */
+		if ((func->flags & FUNC_HAS_EJ0)) {
+			/* _EJ0 method take one argument */
+			arg_list.count = 1;
+			arg_list.pointer = &arg;
+			arg.type = ACPI_TYPE_INTEGER;
+			arg.integer.value = 1;
+
+			status = acpi_evaluate_object(func->handle, "_EJ0", &arg_list, NULL);
+			if (ACPI_FAILURE(status)) {
+				warn("%s: _EJ0 failed\n", __func__);
+				return -1;
+			} else
+				break;
+		}
+	}
+	return 0;
+}
+
+/**
+ * acpiphp_check_bridge - re-enumerate devices
+ * @bridge: where to begin re-enumeration
+ *
+ * Iterate over all slots under this bridge and make sure that if a
+ * card is present they are enabled, and if not they are disabled.
+ */
+static int acpiphp_check_bridge(struct acpiphp_bridge *bridge)
+{
+	struct acpiphp_slot *slot;
+	int retval = 0;
+	int enabled, disabled;
+
+	enabled = disabled = 0;
+
+	for (slot = bridge->slots; slot; slot = slot->next) {
+		unsigned int status = get_slot_status(slot);
+		if (slot->flags & SLOT_ENABLED) {
+			if (status == ACPI_STA_ALL)
+				continue;
+			retval = acpiphp_disable_slot(slot);
+			if (retval) {
+				err("Error occurred in disabling\n");
+				goto err_exit;
+			} else {
+				acpiphp_eject_slot(slot);
+			}
+			disabled++;
+		} else {
+			if (status != ACPI_STA_ALL)
+				continue;
+			retval = acpiphp_enable_slot(slot);
+			if (retval) {
+				err("Error occurred in enabling\n");
+				goto err_exit;
+			}
+			enabled++;
+		}
+	}
+
+	dbg("%s: %d enabled, %d disabled\n", __func__, enabled, disabled);
+
+ err_exit:
+	return retval;
+}
+
+static void acpiphp_set_hpp_values(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list)
+		pci_configure_slot(dev);
+}
+
+/*
+ * Remove devices for which we could not assign resources, call
+ * arch specific code to fix-up the bus
+ */
+static void acpiphp_sanitize_bus(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+	int i;
+	unsigned long type_mask = IORESOURCE_IO | IORESOURCE_MEM;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		for (i=0; i<PCI_BRIDGE_RESOURCES; i++) {
+			struct resource *res = &dev->resource[i];
+			if ((res->flags & type_mask) && !res->start &&
+					res->end) {
+				/* Could not assign a required resources
+				 * for this device, remove it */
+				pci_remove_bus_device(dev);
+				break;
+			}
+		}
+	}
+}
+
+/* Program resources in newly inserted bridge */
+static int acpiphp_configure_bridge (acpi_handle handle)
+{
+	struct pci_bus *bus;
+
+	if (acpi_is_root_bridge(handle)) {
+		struct acpi_pci_root *root = acpi_pci_find_root(handle);
+		bus = root->bus;
+	} else {
+		struct pci_dev *pdev = acpi_get_pci_dev(handle);
+		bus = pdev->subordinate;
+		pci_dev_put(pdev);
+	}
+
+	pci_bus_size_bridges(bus);
+	pci_bus_assign_resources(bus);
+	acpiphp_sanitize_bus(bus);
+	acpiphp_set_hpp_values(bus);
+	pci_enable_bridges(bus);
+	return 0;
+}
+
+static void handle_bridge_insertion(acpi_handle handle, u32 type)
+{
+	struct acpi_device *device, *pdevice;
+	acpi_handle phandle;
+
+	if ((type != ACPI_NOTIFY_BUS_CHECK) &&
+			(type != ACPI_NOTIFY_DEVICE_CHECK)) {
+		err("unexpected notification type %d\n", type);
+		return;
+	}
+
+	acpi_get_parent(handle, &phandle);
+	if (acpi_bus_get_device(phandle, &pdevice)) {
+		dbg("no parent device, assuming NULL\n");
+		pdevice = NULL;
+	}
+	if (acpi_bus_add(&device, pdevice, handle, ACPI_BUS_TYPE_DEVICE)) {
+		err("cannot add bridge to acpi list\n");
+		return;
+	}
+	if (!acpiphp_configure_bridge(handle) &&
+		!acpi_bus_start(device))
+		add_bridge(handle);
+	else
+		err("cannot configure and start bridge\n");
+
+}
+
+/*
+ * ACPI event handlers
+ */
+
+static acpi_status
+count_sub_bridges(acpi_handle handle, u32 lvl, void *context, void **rv)
+{
+	int *count = (int *)context;
+	struct acpiphp_bridge *bridge;
+
+	bridge = acpiphp_handle_to_bridge(handle);
+	if (bridge)
+		(*count)++;
+	return AE_OK ;
+}
+
+static acpi_status
+check_sub_bridges(acpi_handle handle, u32 lvl, void *context, void **rv)
+{
+	struct acpiphp_bridge *bridge;
+	char objname[64];
+	struct acpi_buffer buffer = { .length = sizeof(objname),
+				      .pointer = objname };
+
+	bridge = acpiphp_handle_to_bridge(handle);
+	if (bridge) {
+		acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
+		dbg("%s: re-enumerating slots under %s\n",
+			__func__, objname);
+		acpiphp_check_bridge(bridge);
+	}
+	return AE_OK ;
+}
+
+/**
+ * handle_hotplug_event_bridge - handle ACPI event on bridges
+ * @handle: Notify()'ed acpi_handle
+ * @type: Notify code
+ * @context: pointer to acpiphp_bridge structure
+ *
+ * Handles ACPI event notification on {host,p2p} bridges.
+ */
+static void handle_hotplug_event_bridge(acpi_handle handle, u32 type, void *context)
+{
+	struct acpiphp_bridge *bridge;
+	char objname[64];
+	struct acpi_buffer buffer = { .length = sizeof(objname),
+				      .pointer = objname };
+	struct acpi_device *device;
+	int num_sub_bridges = 0;
+
+	if (acpi_bus_get_device(handle, &device)) {
+		/* This bridge must have just been physically inserted */
+		handle_bridge_insertion(handle, type);
+		return;
+	}
+
+	bridge = acpiphp_handle_to_bridge(handle);
+	if (type == ACPI_NOTIFY_BUS_CHECK) {
+		acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, ACPI_UINT32_MAX,
+			count_sub_bridges, NULL, &num_sub_bridges, NULL);
+	}
+
+	if (!bridge && !num_sub_bridges) {
+		err("cannot get bridge info\n");
+		return;
+	}
+
+	acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
+
+	switch (type) {
+	case ACPI_NOTIFY_BUS_CHECK:
+		/* bus re-enumerate */
+		dbg("%s: Bus check notify on %s\n", __func__, objname);
+		if (bridge) {
+			dbg("%s: re-enumerating slots under %s\n",
+				__func__, objname);
+			acpiphp_check_bridge(bridge);
+		}
+		if (num_sub_bridges)
+			acpi_walk_namespace(ACPI_TYPE_DEVICE, handle,
+				ACPI_UINT32_MAX, check_sub_bridges, NULL, NULL, NULL);
+		break;
+
+	case ACPI_NOTIFY_DEVICE_CHECK:
+		/* device check */
+		dbg("%s: Device check notify on %s\n", __func__, objname);
+		acpiphp_check_bridge(bridge);
+		break;
+
+	case ACPI_NOTIFY_DEVICE_WAKE:
+		/* wake event */
+		dbg("%s: Device wake notify on %s\n", __func__, objname);
+		break;
+
+	case ACPI_NOTIFY_EJECT_REQUEST:
+		/* request device eject */
+		dbg("%s: Device eject notify on %s\n", __func__, objname);
+		if ((bridge->type != BRIDGE_TYPE_HOST) &&
+		    (bridge->flags & BRIDGE_HAS_EJ0)) {
+			struct acpiphp_slot *slot;
+			slot = bridge->func->slot;
+			if (!acpiphp_disable_slot(slot))
+				acpiphp_eject_slot(slot);
+		}
+		break;
+
+	case ACPI_NOTIFY_FREQUENCY_MISMATCH:
+		printk(KERN_ERR "Device %s cannot be configured due"
+				" to a frequency mismatch\n", objname);
+		break;
+
+	case ACPI_NOTIFY_BUS_MODE_MISMATCH:
+		printk(KERN_ERR "Device %s cannot be configured due"
+				" to a bus mode mismatch\n", objname);
+		break;
+
+	case ACPI_NOTIFY_POWER_FAULT:
+		printk(KERN_ERR "Device %s has suffered a power fault\n",
+				objname);
+		break;
+
+	default:
+		warn("notify_handler: unknown event type 0x%x for %s\n", type, objname);
+		break;
+	}
+}
+
+/**
+ * handle_hotplug_event_func - handle ACPI event on functions (i.e. slots)
+ * @handle: Notify()'ed acpi_handle
+ * @type: Notify code
+ * @context: pointer to acpiphp_func structure
+ *
+ * Handles ACPI event notification on slots.
+ */
+static void handle_hotplug_event_func(acpi_handle handle, u32 type, void *context)
+{
+	struct acpiphp_func *func;
+	char objname[64];
+	struct acpi_buffer buffer = { .length = sizeof(objname),
+				      .pointer = objname };
+
+	acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
+
+	func = (struct acpiphp_func *)context;
+
+	switch (type) {
+	case ACPI_NOTIFY_BUS_CHECK:
+		/* bus re-enumerate */
+		dbg("%s: Bus check notify on %s\n", __func__, objname);
+		acpiphp_enable_slot(func->slot);
+		break;
+
+	case ACPI_NOTIFY_DEVICE_CHECK:
+		/* device check : re-enumerate from parent bus */
+		dbg("%s: Device check notify on %s\n", __func__, objname);
+		acpiphp_check_bridge(func->slot->bridge);
+		break;
+
+	case ACPI_NOTIFY_DEVICE_WAKE:
+		/* wake event */
+		dbg("%s: Device wake notify on %s\n", __func__, objname);
+		break;
+
+	case ACPI_NOTIFY_EJECT_REQUEST:
+		/* request device eject */
+		dbg("%s: Device eject notify on %s\n", __func__, objname);
+		if (!(acpiphp_disable_slot(func->slot)))
+			acpiphp_eject_slot(func->slot);
+		break;
+
+	default:
+		warn("notify_handler: unknown event type 0x%x for %s\n", type, objname);
+		break;
+	}
+}
+
+
+static acpi_status
+find_root_bridges(acpi_handle handle, u32 lvl, void *context, void **rv)
+{
+	int *count = (int *)context;
+
+	if (acpi_is_root_bridge(handle)) {
+		acpi_install_notify_handler(handle, ACPI_SYSTEM_NOTIFY,
+				handle_hotplug_event_bridge, NULL);
+			(*count)++;
+	}
+	return AE_OK ;
+}
+
+static struct acpi_pci_driver acpi_pci_hp_driver = {
+	.add =		add_bridge,
+	.remove =	remove_bridge,
+};
+
+/**
+ * acpiphp_glue_init - initializes all PCI hotplug - ACPI glue data structures
+ */
+int __init acpiphp_glue_init(void)
+{
+	int num = 0;
+
+	acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT,
+			ACPI_UINT32_MAX, find_root_bridges, NULL, &num, NULL);
+
+	if (num <= 0)
+		return -1;
+	else
+		acpi_pci_register_driver(&acpi_pci_hp_driver);
+
+	return 0;
+}
+
+
+/**
+ * acpiphp_glue_exit - terminates all PCI hotplug - ACPI glue data structures
+ *
+ * This function frees all data allocated in acpiphp_glue_init().
+ */
+void  acpiphp_glue_exit(void)
+{
+	acpi_pci_unregister_driver(&acpi_pci_hp_driver);
+}
+
+
+/**
+ * acpiphp_get_num_slots - count number of slots in a system
+ */
+int __init acpiphp_get_num_slots(void)
+{
+	struct acpiphp_bridge *bridge;
+	int num_slots = 0;
+
+	list_for_each_entry(bridge, &bridge_list, list) {
+		dbg("Bus %04x:%02x has %d slot%s\n",
+				pci_domain_nr(bridge->pci_bus),
+				bridge->pci_bus->number, bridge->nr_slots,
+				bridge->nr_slots == 1 ? "" : "s");
+		num_slots += bridge->nr_slots;
+	}
+
+	dbg("Total %d slots\n", num_slots);
+	return num_slots;
+}
+
+
+#if 0
+/**
+ * acpiphp_for_each_slot - call function for each slot
+ * @fn: callback function
+ * @data: context to be passed to callback function
+ */
+static int acpiphp_for_each_slot(acpiphp_callback fn, void *data)
+{
+	struct list_head *node;
+	struct acpiphp_bridge *bridge;
+	struct acpiphp_slot *slot;
+	int retval = 0;
+
+	list_for_each (node, &bridge_list) {
+		bridge = (struct acpiphp_bridge *)node;
+		for (slot = bridge->slots; slot; slot = slot->next) {
+			retval = fn(slot, data);
+			if (!retval)
+				goto err_exit;
+		}
+	}
+
+ err_exit:
+	return retval;
+}
+#endif
+
+
+/**
+ * acpiphp_enable_slot - power on slot
+ * @slot: ACPI PHP slot
+ */
+int acpiphp_enable_slot(struct acpiphp_slot *slot)
+{
+	int retval;
+
+	mutex_lock(&slot->crit_sect);
+
+	/* wake up all functions */
+	retval = power_on_slot(slot);
+	if (retval)
+		goto err_exit;
+
+	if (get_slot_status(slot) == ACPI_STA_ALL) {
+		/* configure all functions */
+		retval = enable_device(slot);
+		if (retval)
+			power_off_slot(slot);
+	} else {
+		dbg("%s: Slot status is not ACPI_STA_ALL\n", __func__);
+		power_off_slot(slot);
+	}
+
+ err_exit:
+	mutex_unlock(&slot->crit_sect);
+	return retval;
+}
+
+/**
+ * acpiphp_disable_slot - power off slot
+ * @slot: ACPI PHP slot
+ */
+int acpiphp_disable_slot(struct acpiphp_slot *slot)
+{
+	int retval = 0;
+
+	mutex_lock(&slot->crit_sect);
+
+	/* unconfigure all functions */
+	retval = disable_device(slot);
+	if (retval)
+		goto err_exit;
+
+	/* power off all functions */
+	retval = power_off_slot(slot);
+	if (retval)
+		goto err_exit;
+
+ err_exit:
+	mutex_unlock(&slot->crit_sect);
+	return retval;
+}
+
+
+/*
+ * slot enabled:  1
+ * slot disabled: 0
+ */
+u8 acpiphp_get_power_status(struct acpiphp_slot *slot)
+{
+	return (slot->flags & SLOT_POWEREDON);
+}
+
+
+/*
+ * latch   open:  1
+ * latch closed:  0
+ */
+u8 acpiphp_get_latch_status(struct acpiphp_slot *slot)
+{
+	unsigned int sta;
+
+	sta = get_slot_status(slot);
+
+	return (sta & ACPI_STA_SHOW_IN_UI) ? 0 : 1;
+}
+
+
+/*
+ * adapter presence : 1
+ *          absence : 0
+ */
+u8 acpiphp_get_adapter_status(struct acpiphp_slot *slot)
+{
+	unsigned int sta;
+
+	sta = get_slot_status(slot);
+
+	return (sta == 0) ? 0 : 1;
+}
diff --git a/drivers/pci/hotplug/acpiphp_ibm.c b/drivers/pci/hotplug/acpiphp_ibm.c
new file mode 100644
index 00000000..e5252632
--- /dev/null
+++ b/drivers/pci/hotplug/acpiphp_ibm.c
@@ -0,0 +1,499 @@
+/*
+ * ACPI PCI Hot Plug IBM Extension
+ *
+ * Copyright (C) 2004 Vernon Mauery <vernux@us.ibm.com>
+ * Copyright (C) 2004 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <vernux@us.ibm.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <acpi/acpi_bus.h>
+#include <linux/sysfs.h>
+#include <linux/kobject.h>
+#include <asm/uaccess.h>
+#include <linux/moduleparam.h>
+#include <linux/pci.h>
+
+#include "acpiphp.h"
+#include "../pci.h"
+
+#define DRIVER_VERSION	"1.0.1"
+#define DRIVER_AUTHOR	"Irene Zubarev <zubarev@us.ibm.com>, Vernon Mauery <vernux@us.ibm.com>"
+#define DRIVER_DESC	"ACPI Hot Plug PCI Controller Driver IBM extension"
+
+static int debug;
+
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+MODULE_VERSION(DRIVER_VERSION);
+module_param(debug, bool, 0644);
+MODULE_PARM_DESC(debug, " Debugging mode enabled or not");
+#define MY_NAME "acpiphp_ibm"
+
+#undef dbg
+#define dbg(format, arg...)				\
+do {							\
+	if (debug)					\
+		printk(KERN_DEBUG "%s: " format,	\
+				MY_NAME , ## arg);	\
+} while (0)
+
+#define FOUND_APCI 0x61504349
+/* these are the names for the IBM ACPI pseudo-device */
+#define IBM_HARDWARE_ID1 "IBM37D0"
+#define IBM_HARDWARE_ID2 "IBM37D4"
+
+#define hpslot_to_sun(A) (((struct slot *)((A)->private))->acpi_slot->sun)
+
+/* union apci_descriptor - allows access to the
+ * various device descriptors that are embedded in the
+ * aPCI table
+ */
+union apci_descriptor {
+	struct {
+		char sig[4];
+		u8   len;
+	} header;
+	struct {
+		u8  type;
+		u8  len;
+		u16 slot_id;
+		u8  bus_id;
+		u8  dev_num;
+		u8  slot_num;
+		u8  slot_attr[2];
+		u8  attn;
+		u8  status[2];
+		u8  sun;
+		u8  res[3];
+	} slot;
+	struct {
+		u8 type;
+		u8 len;
+	} generic;
+};
+
+/* struct notification - keeps info about the device
+ * that cause the ACPI notification event
+ */
+struct notification {
+	struct acpi_device *device;
+	u8                  event;
+};
+
+static int ibm_set_attention_status(struct hotplug_slot *slot, u8 status);
+static int ibm_get_attention_status(struct hotplug_slot *slot, u8 *status);
+static void ibm_handle_events(acpi_handle handle, u32 event, void *context);
+static int ibm_get_table_from_acpi(char **bufp);
+static ssize_t ibm_read_apci_table(struct file *filp, struct kobject *kobj,
+				   struct bin_attribute *bin_attr,
+				   char *buffer, loff_t pos, size_t size);
+static acpi_status __init ibm_find_acpi_device(acpi_handle handle,
+		u32 lvl, void *context, void **rv);
+static int __init ibm_acpiphp_init(void);
+static void __exit ibm_acpiphp_exit(void);
+
+static acpi_handle ibm_acpi_handle;
+static struct notification ibm_note;
+static struct bin_attribute ibm_apci_table_attr = {
+	    .attr = {
+		    .name = "apci_table",
+		    .mode = S_IRUGO,
+	    },
+	    .read = ibm_read_apci_table,
+	    .write = NULL,
+};
+static struct acpiphp_attention_info ibm_attention_info = 
+{
+	.set_attn = ibm_set_attention_status,
+	.get_attn = ibm_get_attention_status,
+	.owner = THIS_MODULE,
+};
+
+/**
+ * ibm_slot_from_id - workaround for bad ibm hardware
+ * @id: the slot number that linux refers to the slot by
+ *
+ * Description: This method returns the aCPI slot descriptor
+ * corresponding to the Linux slot number.  This descriptor
+ * has info about the aPCI slot id and attention status.
+ * This descriptor must be freed using kfree when done.
+ */
+static union apci_descriptor *ibm_slot_from_id(int id)
+{
+	int ind = 0, size;
+	union apci_descriptor *ret = NULL, *des;
+	char *table;
+
+	size = ibm_get_table_from_acpi(&table);
+	des = (union apci_descriptor *)table;
+	if (memcmp(des->header.sig, "aPCI", 4) != 0)
+		goto ibm_slot_done;
+
+	des = (union apci_descriptor *)&table[ind += des->header.len];
+	while (ind < size && (des->generic.type != 0x82 ||
+			des->slot.slot_num != id)) {
+		des = (union apci_descriptor *)&table[ind += des->generic.len];
+	}
+
+	if (ind < size && des->slot.slot_num == id)
+		ret = des;
+
+ibm_slot_done:
+	if (ret) {
+		ret = kmalloc(sizeof(union apci_descriptor), GFP_KERNEL);
+		memcpy(ret, des, sizeof(union apci_descriptor));
+	}
+	kfree(table);
+	return ret;
+}
+
+/**
+ * ibm_set_attention_status - callback method to set the attention LED
+ * @slot: the hotplug_slot to work with
+ * @status: what to set the LED to (0 or 1)
+ *
+ * Description: This method is registered with the acpiphp module as a
+ * callback to do the device specific task of setting the LED status.
+ */
+static int ibm_set_attention_status(struct hotplug_slot *slot, u8 status)
+{
+	union acpi_object args[2]; 
+	struct acpi_object_list params = { .pointer = args, .count = 2 };
+	acpi_status stat; 
+	unsigned long long rc;
+	union apci_descriptor *ibm_slot;
+
+	ibm_slot = ibm_slot_from_id(hpslot_to_sun(slot));
+
+	dbg("%s: set slot %d (%d) attention status to %d\n", __func__,
+			ibm_slot->slot.slot_num, ibm_slot->slot.slot_id,
+			(status ? 1 : 0));
+
+	args[0].type = ACPI_TYPE_INTEGER;
+	args[0].integer.value = ibm_slot->slot.slot_id;
+	args[1].type = ACPI_TYPE_INTEGER;
+	args[1].integer.value = (status) ? 1 : 0;
+
+	kfree(ibm_slot);
+
+	stat = acpi_evaluate_integer(ibm_acpi_handle, "APLS", &params, &rc);
+	if (ACPI_FAILURE(stat)) {
+		err("APLS evaluation failed:  0x%08x\n", stat);
+		return -ENODEV;
+	} else if (!rc) {
+		err("APLS method failed:  0x%08llx\n", rc);
+		return -ERANGE;
+	}
+	return 0;
+}
+
+/**
+ * ibm_get_attention_status - callback method to get attention LED status
+ * @slot: the hotplug_slot to work with
+ * @status: returns what the LED is set to (0 or 1)
+ *
+ * Description: This method is registered with the acpiphp module as a
+ * callback to do the device specific task of getting the LED status.
+ * 
+ * Because there is no direct method of getting the LED status directly
+ * from an ACPI call, we read the aPCI table and parse out our
+ * slot descriptor to read the status from that.
+ */
+static int ibm_get_attention_status(struct hotplug_slot *slot, u8 *status)
+{
+	union apci_descriptor *ibm_slot;
+
+	ibm_slot = ibm_slot_from_id(hpslot_to_sun(slot));
+
+	if (ibm_slot->slot.attn & 0xa0 || ibm_slot->slot.status[1] & 0x08)
+		*status = 1;
+	else
+		*status = 0;
+
+	dbg("%s: get slot %d (%d) attention status is %d\n", __func__,
+			ibm_slot->slot.slot_num, ibm_slot->slot.slot_id,
+			*status);
+
+	kfree(ibm_slot);
+	return 0;
+}
+
+/**
+ * ibm_handle_events - listens for ACPI events for the IBM37D0 device
+ * @handle: an ACPI handle to the device that caused the event
+ * @event: the event info (device specific)
+ * @context: passed context (our notification struct)
+ *
+ * Description: This method is registered as a callback with the ACPI
+ * subsystem it is called when this device has an event to notify the OS of.
+ *
+ * The events actually come from the device as two events that get
+ * synthesized into one event with data by this function.  The event
+ * ID comes first and then the slot number that caused it.  We report
+ * this as one event to the OS.
+ *
+ * From section 5.6.2.2 of the ACPI 2.0 spec, I understand that the OSPM will
+ * only re-enable the interrupt that causes this event AFTER this method
+ * has returned, thereby enforcing serial access for the notification struct.
+ */
+static void ibm_handle_events(acpi_handle handle, u32 event, void *context)
+{
+	u8 detail = event & 0x0f;
+	u8 subevent = event & 0xf0;
+	struct notification *note = context;
+
+	dbg("%s: Received notification %02x\n", __func__, event);
+
+	if (subevent == 0x80) {
+		dbg("%s: generationg bus event\n", __func__);
+		acpi_bus_generate_proc_event(note->device, note->event, detail);
+		acpi_bus_generate_netlink_event(note->device->pnp.device_class,
+						  dev_name(&note->device->dev),
+						  note->event, detail);
+	} else
+		note->event = event;
+}
+
+/**
+ * ibm_get_table_from_acpi - reads the APLS buffer from ACPI
+ * @bufp: address to pointer to allocate for the table
+ *
+ * Description: This method reads the APLS buffer in from ACPI and
+ * stores the "stripped" table into a single buffer
+ * it allocates and passes the address back in bufp.
+ *
+ * If NULL is passed in as buffer, this method only calculates
+ * the size of the table and returns that without filling
+ * in the buffer.
+ *
+ * Returns < 0 on error or the size of the table on success.
+ */
+static int ibm_get_table_from_acpi(char **bufp)
+{
+	union acpi_object *package;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	acpi_status status;
+	char *lbuf = NULL;
+	int i, size = -EIO;
+
+	status = acpi_evaluate_object(ibm_acpi_handle, "APCI", NULL, &buffer);
+	if (ACPI_FAILURE(status)) {
+		err("%s:  APCI evaluation failed\n", __func__);
+		return -ENODEV;
+	}
+
+	package = (union acpi_object *) buffer.pointer;
+	if (!(package) ||
+			(package->type != ACPI_TYPE_PACKAGE) ||
+			!(package->package.elements)) {
+		err("%s:  Invalid APCI object\n", __func__);
+		goto read_table_done;
+	}
+
+	for(size = 0, i = 0; i < package->package.count; i++) {
+		if (package->package.elements[i].type != ACPI_TYPE_BUFFER) {
+			err("%s:  Invalid APCI element %d\n", __func__, i);
+			goto read_table_done;
+		}
+		size += package->package.elements[i].buffer.length;
+	}
+
+	if (bufp == NULL)
+		goto read_table_done;
+
+	lbuf = kzalloc(size, GFP_KERNEL);
+	dbg("%s: element count: %i, ASL table size: %i, &table = 0x%p\n",
+			__func__, package->package.count, size, lbuf);
+
+	if (lbuf) {
+		*bufp = lbuf;
+	} else {
+		size = -ENOMEM;
+		goto read_table_done;
+	}
+
+	size = 0;
+	for (i=0; i<package->package.count; i++) {
+		memcpy(&lbuf[size],
+				package->package.elements[i].buffer.pointer,
+				package->package.elements[i].buffer.length);
+		size += package->package.elements[i].buffer.length;
+	}
+
+read_table_done:
+	kfree(buffer.pointer);
+	return size;
+}
+
+/**
+ * ibm_read_apci_table - callback for the sysfs apci_table file
+ * @filp: the open sysfs file
+ * @kobj: the kobject this binary attribute is a part of
+ * @bin_attr: struct bin_attribute for this file
+ * @buffer: the kernel space buffer to fill
+ * @pos: the offset into the file
+ * @size: the number of bytes requested
+ *
+ * Description: Gets registered with sysfs as the reader callback
+ * to be executed when /sys/bus/pci/slots/apci_table gets read.
+ *
+ * Since we don't get notified on open and close for this file,
+ * things get really tricky here...
+ * our solution is to only allow reading the table in all at once.
+ */
+static ssize_t ibm_read_apci_table(struct file *filp, struct kobject *kobj,
+				   struct bin_attribute *bin_attr,
+				   char *buffer, loff_t pos, size_t size)
+{
+	int bytes_read = -EINVAL;
+	char *table = NULL;
+	
+	dbg("%s: pos = %d, size = %zd\n", __func__, (int)pos, size);
+
+	if (pos == 0) {
+		bytes_read = ibm_get_table_from_acpi(&table);
+		if (bytes_read > 0 && bytes_read <= size)
+			memcpy(buffer, table, bytes_read);
+		kfree(table);
+	}
+	return bytes_read;
+}
+
+/**
+ * ibm_find_acpi_device - callback to find our ACPI device
+ * @handle: the ACPI handle of the device we are inspecting
+ * @lvl: depth into the namespace tree
+ * @context: a pointer to our handle to fill when we find the device
+ * @rv: a return value to fill if desired
+ *
+ * Description: Used as a callback when calling acpi_walk_namespace
+ * to find our device.  When this method returns non-zero
+ * acpi_walk_namespace quits its search and returns our value.
+ */
+static acpi_status __init ibm_find_acpi_device(acpi_handle handle,
+		u32 lvl, void *context, void **rv)
+{
+	acpi_handle *phandle = (acpi_handle *)context;
+	acpi_status status; 
+	struct acpi_device_info *info;
+	int retval = 0;
+
+	status = acpi_get_object_info(handle, &info);
+	if (ACPI_FAILURE(status)) {
+		err("%s:  Failed to get device information status=0x%x\n",
+			__func__, status);
+		return retval;
+	}
+
+	if (info->current_status && (info->valid & ACPI_VALID_HID) &&
+			(!strcmp(info->hardware_id.string, IBM_HARDWARE_ID1) ||
+			 !strcmp(info->hardware_id.string, IBM_HARDWARE_ID2))) {
+		dbg("found hardware: %s, handle: %p\n",
+			info->hardware_id.string, handle);
+		*phandle = handle;
+		/* returning non-zero causes the search to stop
+		 * and returns this value to the caller of 
+		 * acpi_walk_namespace, but it also causes some warnings
+		 * in the acpi debug code to print...
+		 */
+		retval = FOUND_APCI;
+	}
+	kfree(info);
+	return retval;
+}
+
+static int __init ibm_acpiphp_init(void)
+{
+	int retval = 0;
+	acpi_status status;
+	struct acpi_device *device;
+	struct kobject *sysdir = &pci_slots_kset->kobj;
+
+	dbg("%s\n", __func__);
+
+	if (acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT,
+			ACPI_UINT32_MAX, ibm_find_acpi_device, NULL,
+			&ibm_acpi_handle, NULL) != FOUND_APCI) {
+		err("%s: acpi_walk_namespace failed\n", __func__);
+		retval = -ENODEV;
+		goto init_return;
+	}
+	dbg("%s: found IBM aPCI device\n", __func__);
+	if (acpi_bus_get_device(ibm_acpi_handle, &device)) {
+		err("%s: acpi_bus_get_device failed\n", __func__);
+		retval = -ENODEV;
+		goto init_return;
+	}
+	if (acpiphp_register_attention(&ibm_attention_info)) {
+		retval = -ENODEV;
+		goto init_return;
+	}
+
+	ibm_note.device = device;
+	status = acpi_install_notify_handler(ibm_acpi_handle,
+			ACPI_DEVICE_NOTIFY, ibm_handle_events,
+			&ibm_note);
+	if (ACPI_FAILURE(status)) {
+		err("%s: Failed to register notification handler\n",
+				__func__);
+		retval = -EBUSY;
+		goto init_cleanup;
+	}
+
+	ibm_apci_table_attr.size = ibm_get_table_from_acpi(NULL);
+	retval = sysfs_create_bin_file(sysdir, &ibm_apci_table_attr);
+
+	return retval;
+
+init_cleanup:
+	acpiphp_unregister_attention(&ibm_attention_info);
+init_return:
+	return retval;
+}
+
+static void __exit ibm_acpiphp_exit(void)
+{
+	acpi_status status;
+	struct kobject *sysdir = &pci_slots_kset->kobj;
+
+	dbg("%s\n", __func__);
+
+	if (acpiphp_unregister_attention(&ibm_attention_info))
+		err("%s: attention info deregistration failed", __func__);
+
+	status = acpi_remove_notify_handler(
+			   ibm_acpi_handle,
+			   ACPI_DEVICE_NOTIFY,
+			   ibm_handle_events);
+	if (ACPI_FAILURE(status))
+		err("%s: Notification handler removal failed\n", __func__);
+	/* remove the /sys entries */
+	sysfs_remove_bin_file(sysdir, &ibm_apci_table_attr);
+}
+
+module_init(ibm_acpiphp_init);
+module_exit(ibm_acpiphp_exit);
diff --git a/drivers/pci/hotplug/cpci_hotplug.h b/drivers/pci/hotplug/cpci_hotplug.h
new file mode 100644
index 00000000..9fff878c
--- /dev/null
+++ b/drivers/pci/hotplug/cpci_hotplug.h
@@ -0,0 +1,102 @@
+/*
+ * CompactPCI Hot Plug Core Functions
+ *
+ * Copyright (C) 2002 SOMA Networks, Inc.
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <scottm@somanetworks.com>
+ */
+
+#ifndef _CPCI_HOTPLUG_H
+#define _CPCI_HOTPLUG_H
+
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+
+/* PICMG 2.1 R2.0 HS CSR bits: */
+#define HS_CSR_INS	0x0080
+#define HS_CSR_EXT	0x0040
+#define HS_CSR_PI	0x0030
+#define HS_CSR_LOO	0x0008
+#define HS_CSR_PIE	0x0004
+#define HS_CSR_EIM	0x0002
+#define HS_CSR_DHA	0x0001
+
+struct slot {
+	u8 number;
+	unsigned int devfn;
+	struct pci_bus *bus;
+	struct pci_dev *dev;
+	unsigned int extracting;
+	struct hotplug_slot *hotplug_slot;
+	struct list_head slot_list;
+};
+
+struct cpci_hp_controller_ops {
+	int (*query_enum) (void);
+	int (*enable_irq) (void);
+	int (*disable_irq) (void);
+	int (*check_irq) (void *dev_id);
+	int (*hardware_test) (struct slot* slot, u32 value);
+	u8  (*get_power) (struct slot* slot);
+	int (*set_power) (struct slot* slot, int value);
+};
+
+struct cpci_hp_controller {
+	unsigned int irq;
+	unsigned long irq_flags;
+	char *devname;
+	void *dev_id;
+	char *name;
+	struct cpci_hp_controller_ops *ops;
+};
+
+static inline const char *slot_name(struct slot *slot)
+{
+	return hotplug_slot_name(slot->hotplug_slot);
+}
+
+extern int cpci_hp_register_controller(struct cpci_hp_controller *controller);
+extern int cpci_hp_unregister_controller(struct cpci_hp_controller *controller);
+extern int cpci_hp_register_bus(struct pci_bus *bus, u8 first, u8 last);
+extern int cpci_hp_unregister_bus(struct pci_bus *bus);
+extern int cpci_hp_start(void);
+extern int cpci_hp_stop(void);
+
+/*
+ * Internal function prototypes, these functions should not be used by
+ * board/chassis drivers.
+ */
+extern u8 cpci_get_attention_status(struct slot *slot);
+extern u8 cpci_get_latch_status(struct slot *slot);
+extern u8 cpci_get_adapter_status(struct slot *slot);
+extern u16 cpci_get_hs_csr(struct slot * slot);
+extern int cpci_set_attention_status(struct slot *slot, int status);
+extern int cpci_check_and_clear_ins(struct slot * slot);
+extern int cpci_check_ext(struct slot * slot);
+extern int cpci_clear_ext(struct slot * slot);
+extern int cpci_led_on(struct slot * slot);
+extern int cpci_led_off(struct slot * slot);
+extern int cpci_configure_slot(struct slot *slot);
+extern int cpci_unconfigure_slot(struct slot *slot);
+
+#endif	/* _CPCI_HOTPLUG_H */
diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c
new file mode 100644
index 00000000..d703e73f
--- /dev/null
+++ b/drivers/pci/hotplug/cpci_hotplug_core.c
@@ -0,0 +1,724 @@
+/*
+ * CompactPCI Hot Plug Driver
+ *
+ * Copyright (C) 2002,2005 SOMA Networks, Inc.
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <scottm@somanetworks.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <asm/atomic.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include "cpci_hotplug.h"
+
+#define DRIVER_AUTHOR	"Scott Murray <scottm@somanetworks.com>"
+#define DRIVER_DESC	"CompactPCI Hot Plug Core"
+
+#define MY_NAME	"cpci_hotplug"
+
+#define dbg(format, arg...)					\
+	do {							\
+		if (cpci_debug)					\
+			printk (KERN_DEBUG "%s: " format "\n",	\
+				MY_NAME , ## arg); 		\
+	} while (0)
+#define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
+#define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
+#define warn(format, arg...) printk(KERN_WARNING "%s: " format "\n", MY_NAME , ## arg)
+
+/* local variables */
+static DECLARE_RWSEM(list_rwsem);
+static LIST_HEAD(slot_list);
+static int slots;
+static atomic_t extracting;
+int cpci_debug;
+static struct cpci_hp_controller *controller;
+static struct task_struct *cpci_thread;
+static int thread_finished;
+
+static int enable_slot(struct hotplug_slot *slot);
+static int disable_slot(struct hotplug_slot *slot);
+static int set_attention_status(struct hotplug_slot *slot, u8 value);
+static int get_power_status(struct hotplug_slot *slot, u8 * value);
+static int get_attention_status(struct hotplug_slot *slot, u8 * value);
+static int get_adapter_status(struct hotplug_slot *slot, u8 * value);
+static int get_latch_status(struct hotplug_slot *slot, u8 * value);
+
+static struct hotplug_slot_ops cpci_hotplug_slot_ops = {
+	.enable_slot = enable_slot,
+	.disable_slot = disable_slot,
+	.set_attention_status = set_attention_status,
+	.get_power_status = get_power_status,
+	.get_attention_status = get_attention_status,
+	.get_adapter_status = get_adapter_status,
+	.get_latch_status = get_latch_status,
+};
+
+static int
+update_latch_status(struct hotplug_slot *hotplug_slot, u8 value)
+{
+	struct hotplug_slot_info info;
+
+	memcpy(&info, hotplug_slot->info, sizeof(struct hotplug_slot_info));
+	info.latch_status = value;
+	return pci_hp_change_slot_info(hotplug_slot, &info);
+}
+
+static int
+update_adapter_status(struct hotplug_slot *hotplug_slot, u8 value)
+{
+	struct hotplug_slot_info info;
+
+	memcpy(&info, hotplug_slot->info, sizeof(struct hotplug_slot_info));
+	info.adapter_status = value;
+	return pci_hp_change_slot_info(hotplug_slot, &info);
+}
+
+static int
+enable_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+	int retval = 0;
+
+	dbg("%s - physical_slot = %s", __func__, slot_name(slot));
+
+	if (controller->ops->set_power)
+		retval = controller->ops->set_power(slot, 1);
+	return retval;
+}
+
+static int
+disable_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+	int retval = 0;
+
+	dbg("%s - physical_slot = %s", __func__, slot_name(slot));
+
+	down_write(&list_rwsem);
+
+	/* Unconfigure device */
+	dbg("%s - unconfiguring slot %s", __func__, slot_name(slot));
+	if ((retval = cpci_unconfigure_slot(slot))) {
+		err("%s - could not unconfigure slot %s",
+		    __func__, slot_name(slot));
+		goto disable_error;
+	}
+	dbg("%s - finished unconfiguring slot %s", __func__, slot_name(slot));
+
+	/* Clear EXT (by setting it) */
+	if (cpci_clear_ext(slot)) {
+		err("%s - could not clear EXT for slot %s",
+		    __func__, slot_name(slot));
+		retval = -ENODEV;
+		goto disable_error;
+	}
+	cpci_led_on(slot);
+
+	if (controller->ops->set_power)
+		if ((retval = controller->ops->set_power(slot, 0)))
+			goto disable_error;
+
+	if (update_adapter_status(slot->hotplug_slot, 0))
+		warn("failure to update adapter file");
+
+	if (slot->extracting) {
+		slot->extracting = 0;
+		atomic_dec(&extracting);
+	}
+disable_error:
+	up_write(&list_rwsem);
+	return retval;
+}
+
+static u8
+cpci_get_power_status(struct slot *slot)
+{
+	u8 power = 1;
+
+	if (controller->ops->get_power)
+		power = controller->ops->get_power(slot);
+	return power;
+}
+
+static int
+get_power_status(struct hotplug_slot *hotplug_slot, u8 * value)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	*value = cpci_get_power_status(slot);
+	return 0;
+}
+
+static int
+get_attention_status(struct hotplug_slot *hotplug_slot, u8 * value)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	*value = cpci_get_attention_status(slot);
+	return 0;
+}
+
+static int
+set_attention_status(struct hotplug_slot *hotplug_slot, u8 status)
+{
+	return cpci_set_attention_status(hotplug_slot->private, status);
+}
+
+static int
+get_adapter_status(struct hotplug_slot *hotplug_slot, u8 * value)
+{
+	*value = hotplug_slot->info->adapter_status;
+	return 0;
+}
+
+static int
+get_latch_status(struct hotplug_slot *hotplug_slot, u8 * value)
+{
+	*value = hotplug_slot->info->latch_status;
+	return 0;
+}
+
+static void release_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	kfree(slot->hotplug_slot->info);
+	kfree(slot->hotplug_slot);
+	if (slot->dev)
+		pci_dev_put(slot->dev);
+	kfree(slot);
+}
+
+#define SLOT_NAME_SIZE	6
+
+int
+cpci_hp_register_bus(struct pci_bus *bus, u8 first, u8 last)
+{
+	struct slot *slot;
+	struct hotplug_slot *hotplug_slot;
+	struct hotplug_slot_info *info;
+	char name[SLOT_NAME_SIZE];
+	int status = -ENOMEM;
+	int i;
+
+	if (!(controller && bus))
+		return -ENODEV;
+
+	/*
+	 * Create a structure for each slot, and register that slot
+	 * with the pci_hotplug subsystem.
+	 */
+	for (i = first; i <= last; ++i) {
+		slot = kzalloc(sizeof (struct slot), GFP_KERNEL);
+		if (!slot)
+			goto error;
+
+		hotplug_slot =
+			kzalloc(sizeof (struct hotplug_slot), GFP_KERNEL);
+		if (!hotplug_slot)
+			goto error_slot;
+		slot->hotplug_slot = hotplug_slot;
+
+		info = kzalloc(sizeof (struct hotplug_slot_info), GFP_KERNEL);
+		if (!info)
+			goto error_hpslot;
+		hotplug_slot->info = info;
+
+		slot->bus = bus;
+		slot->number = i;
+		slot->devfn = PCI_DEVFN(i, 0);
+
+		snprintf(name, SLOT_NAME_SIZE, "%02x:%02x", bus->number, i);
+
+		hotplug_slot->private = slot;
+		hotplug_slot->release = &release_slot;
+		hotplug_slot->ops = &cpci_hotplug_slot_ops;
+
+		/*
+		 * Initialize the slot info structure with some known
+		 * good values.
+		 */
+		dbg("initializing slot %s", name);
+		info->power_status = cpci_get_power_status(slot);
+		info->attention_status = cpci_get_attention_status(slot);
+
+		dbg("registering slot %s", name);
+		status = pci_hp_register(slot->hotplug_slot, bus, i, name);
+		if (status) {
+			err("pci_hp_register failed with error %d", status);
+			goto error_info;
+		}
+		dbg("slot registered with name: %s", slot_name(slot));
+
+		/* Add slot to our internal list */
+		down_write(&list_rwsem);
+		list_add(&slot->slot_list, &slot_list);
+		slots++;
+		up_write(&list_rwsem);
+	}
+	return 0;
+error_info:
+	kfree(info);
+error_hpslot:
+	kfree(hotplug_slot);
+error_slot:
+	kfree(slot);
+error:
+	return status;
+}
+
+int
+cpci_hp_unregister_bus(struct pci_bus *bus)
+{
+	struct slot *slot;
+	struct slot *tmp;
+	int status = 0;
+
+	down_write(&list_rwsem);
+	if (!slots) {
+		up_write(&list_rwsem);
+		return -1;
+	}
+	list_for_each_entry_safe(slot, tmp, &slot_list, slot_list) {
+		if (slot->bus == bus) {
+			list_del(&slot->slot_list);
+			slots--;
+
+			dbg("deregistering slot %s", slot_name(slot));
+			status = pci_hp_deregister(slot->hotplug_slot);
+			if (status) {
+				err("pci_hp_deregister failed with error %d",
+				    status);
+				break;
+			}
+		}
+	}
+	up_write(&list_rwsem);
+	return status;
+}
+
+/* This is the interrupt mode interrupt handler */
+static irqreturn_t
+cpci_hp_intr(int irq, void *data)
+{
+	dbg("entered cpci_hp_intr");
+
+	/* Check to see if it was our interrupt */
+	if ((controller->irq_flags & IRQF_SHARED) &&
+	    !controller->ops->check_irq(controller->dev_id)) {
+		dbg("exited cpci_hp_intr, not our interrupt");
+		return IRQ_NONE;
+	}
+
+	/* Disable ENUM interrupt */
+	controller->ops->disable_irq();
+
+	/* Trigger processing by the event thread */
+	wake_up_process(cpci_thread);
+	return IRQ_HANDLED;
+}
+
+/*
+ * According to PICMG 2.1 R2.0, section 6.3.2, upon
+ * initialization, the system driver shall clear the
+ * INS bits of the cold-inserted devices.
+ */
+static int
+init_slots(int clear_ins)
+{
+	struct slot *slot;
+	struct pci_dev* dev;
+
+	dbg("%s - enter", __func__);
+	down_read(&list_rwsem);
+	if (!slots) {
+		up_read(&list_rwsem);
+		return -1;
+	}
+	list_for_each_entry(slot, &slot_list, slot_list) {
+		dbg("%s - looking at slot %s", __func__, slot_name(slot));
+		if (clear_ins && cpci_check_and_clear_ins(slot))
+			dbg("%s - cleared INS for slot %s",
+			    __func__, slot_name(slot));
+		dev = pci_get_slot(slot->bus, PCI_DEVFN(slot->number, 0));
+		if (dev) {
+			if (update_adapter_status(slot->hotplug_slot, 1))
+				warn("failure to update adapter file");
+			if (update_latch_status(slot->hotplug_slot, 1))
+				warn("failure to update latch file");
+			slot->dev = dev;
+		}
+	}
+	up_read(&list_rwsem);
+	dbg("%s - exit", __func__);
+	return 0;
+}
+
+static int
+check_slots(void)
+{
+	struct slot *slot;
+	int extracted;
+	int inserted;
+	u16 hs_csr;
+
+	down_read(&list_rwsem);
+	if (!slots) {
+		up_read(&list_rwsem);
+		err("no slots registered, shutting down");
+		return -1;
+	}
+	extracted = inserted = 0;
+	list_for_each_entry(slot, &slot_list, slot_list) {
+		dbg("%s - looking at slot %s", __func__, slot_name(slot));
+		if (cpci_check_and_clear_ins(slot)) {
+			/*
+			 * Some broken hardware (e.g. PLX 9054AB) asserts
+			 * ENUM# twice...
+			 */
+			if (slot->dev) {
+				warn("slot %s already inserted",
+				     slot_name(slot));
+				inserted++;
+				continue;
+			}
+
+			/* Process insertion */
+			dbg("%s - slot %s inserted", __func__, slot_name(slot));
+
+			/* GSM, debug */
+			hs_csr = cpci_get_hs_csr(slot);
+			dbg("%s - slot %s HS_CSR (1) = %04x",
+			    __func__, slot_name(slot), hs_csr);
+
+			/* Configure device */
+			dbg("%s - configuring slot %s",
+			    __func__, slot_name(slot));
+			if (cpci_configure_slot(slot)) {
+				err("%s - could not configure slot %s",
+				    __func__, slot_name(slot));
+				continue;
+			}
+			dbg("%s - finished configuring slot %s",
+			    __func__, slot_name(slot));
+
+			/* GSM, debug */
+			hs_csr = cpci_get_hs_csr(slot);
+			dbg("%s - slot %s HS_CSR (2) = %04x",
+			    __func__, slot_name(slot), hs_csr);
+
+			if (update_latch_status(slot->hotplug_slot, 1))
+				warn("failure to update latch file");
+
+			if (update_adapter_status(slot->hotplug_slot, 1))
+				warn("failure to update adapter file");
+
+			cpci_led_off(slot);
+
+			/* GSM, debug */
+			hs_csr = cpci_get_hs_csr(slot);
+			dbg("%s - slot %s HS_CSR (3) = %04x",
+			    __func__, slot_name(slot), hs_csr);
+
+			inserted++;
+		} else if (cpci_check_ext(slot)) {
+			/* Process extraction request */
+			dbg("%s - slot %s extracted",
+			    __func__, slot_name(slot));
+
+			/* GSM, debug */
+			hs_csr = cpci_get_hs_csr(slot);
+			dbg("%s - slot %s HS_CSR = %04x",
+			    __func__, slot_name(slot), hs_csr);
+
+			if (!slot->extracting) {
+				if (update_latch_status(slot->hotplug_slot, 0)) {
+					warn("failure to update latch file");
+				}
+				slot->extracting = 1;
+				atomic_inc(&extracting);
+			}
+			extracted++;
+		} else if (slot->extracting) {
+			hs_csr = cpci_get_hs_csr(slot);
+			if (hs_csr == 0xffff) {
+				/*
+				 * Hmmm, we're likely hosed at this point, should we
+				 * bother trying to tell the driver or not?
+				 */
+				err("card in slot %s was improperly removed",
+				    slot_name(slot));
+				if (update_adapter_status(slot->hotplug_slot, 0))
+					warn("failure to update adapter file");
+				slot->extracting = 0;
+				atomic_dec(&extracting);
+			}
+		}
+	}
+	up_read(&list_rwsem);
+	dbg("inserted=%d, extracted=%d, extracting=%d",
+	    inserted, extracted, atomic_read(&extracting));
+	if (inserted || extracted)
+		return extracted;
+	else if (!atomic_read(&extracting)) {
+		err("cannot find ENUM# source, shutting down");
+		return -1;
+	}
+	return 0;
+}
+
+/* This is the interrupt mode worker thread body */
+static int
+event_thread(void *data)
+{
+	int rc;
+
+	dbg("%s - event thread started", __func__);
+	while (1) {
+		dbg("event thread sleeping");
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule();
+		if (kthread_should_stop())
+			break;
+		do {
+			rc = check_slots();
+			if (rc > 0) {
+				/* Give userspace a chance to handle extraction */
+				msleep(500);
+			} else if (rc < 0) {
+				dbg("%s - error checking slots", __func__);
+				thread_finished = 1;
+				goto out;
+			}
+		} while (atomic_read(&extracting) && !kthread_should_stop());
+		if (kthread_should_stop())
+			break;
+
+		/* Re-enable ENUM# interrupt */
+		dbg("%s - re-enabling irq", __func__);
+		controller->ops->enable_irq();
+	}
+ out:
+	return 0;
+}
+
+/* This is the polling mode worker thread body */
+static int
+poll_thread(void *data)
+{
+	int rc;
+
+	while (1) {
+		if (kthread_should_stop() || signal_pending(current))
+			break;
+		if (controller->ops->query_enum()) {
+			do {
+				rc = check_slots();
+				if (rc > 0) {
+					/* Give userspace a chance to handle extraction */
+					msleep(500);
+				} else if (rc < 0) {
+					dbg("%s - error checking slots", __func__);
+					thread_finished = 1;
+					goto out;
+				}
+			} while (atomic_read(&extracting) && !kthread_should_stop());
+		}
+		msleep(100);
+	}
+ out:
+	return 0;
+}
+
+static int
+cpci_start_thread(void)
+{
+	if (controller->irq)
+		cpci_thread = kthread_run(event_thread, NULL, "cpci_hp_eventd");
+	else
+		cpci_thread = kthread_run(poll_thread, NULL, "cpci_hp_polld");
+	if (IS_ERR(cpci_thread)) {
+		err("Can't start up our thread");
+		return PTR_ERR(cpci_thread);
+	}
+	thread_finished = 0;
+	return 0;
+}
+
+static void
+cpci_stop_thread(void)
+{
+	kthread_stop(cpci_thread);
+	thread_finished = 1;
+}
+
+int
+cpci_hp_register_controller(struct cpci_hp_controller *new_controller)
+{
+	int status = 0;
+
+	if (controller)
+		return -1;
+	if (!(new_controller && new_controller->ops))
+		return -EINVAL;
+	if (new_controller->irq) {
+		if (!(new_controller->ops->enable_irq &&
+		     new_controller->ops->disable_irq))
+			status = -EINVAL;
+		if (request_irq(new_controller->irq,
+			       cpci_hp_intr,
+			       new_controller->irq_flags,
+			       MY_NAME,
+			       new_controller->dev_id)) {
+			err("Can't get irq %d for the hotplug cPCI controller",
+			    new_controller->irq);
+			status = -ENODEV;
+		}
+		dbg("%s - acquired controller irq %d",
+		    __func__, new_controller->irq);
+	}
+	if (!status)
+		controller = new_controller;
+	return status;
+}
+
+static void
+cleanup_slots(void)
+{
+	struct slot *slot;
+	struct slot *tmp;
+
+	/*
+	 * Unregister all of our slots with the pci_hotplug subsystem,
+	 * and free up all memory that we had allocated.
+	 */
+	down_write(&list_rwsem);
+	if (!slots)
+		goto cleanup_null;
+	list_for_each_entry_safe(slot, tmp, &slot_list, slot_list) {
+		list_del(&slot->slot_list);
+		pci_hp_deregister(slot->hotplug_slot);
+	}
+cleanup_null:
+	up_write(&list_rwsem);
+	return;
+}
+
+int
+cpci_hp_unregister_controller(struct cpci_hp_controller *old_controller)
+{
+	int status = 0;
+
+	if (controller) {
+		if (!thread_finished)
+			cpci_stop_thread();
+		if (controller->irq)
+			free_irq(controller->irq, controller->dev_id);
+		controller = NULL;
+		cleanup_slots();
+	} else
+		status = -ENODEV;
+	return status;
+}
+
+int
+cpci_hp_start(void)
+{
+	static int first = 1;
+	int status;
+
+	dbg("%s - enter", __func__);
+	if (!controller)
+		return -ENODEV;
+
+	down_read(&list_rwsem);
+	if (list_empty(&slot_list)) {
+		up_read(&list_rwsem);
+		return -ENODEV;
+	}
+	up_read(&list_rwsem);
+
+	status = init_slots(first);
+	if (first)
+		first = 0;
+	if (status)
+		return status;
+
+	status = cpci_start_thread();
+	if (status)
+		return status;
+	dbg("%s - thread started", __func__);
+
+	if (controller->irq) {
+		/* Start enum interrupt processing */
+		dbg("%s - enabling irq", __func__);
+		controller->ops->enable_irq();
+	}
+	dbg("%s - exit", __func__);
+	return 0;
+}
+
+int
+cpci_hp_stop(void)
+{
+	if (!controller)
+		return -ENODEV;
+	if (controller->irq) {
+		/* Stop enum interrupt processing */
+		dbg("%s - disabling irq", __func__);
+		controller->ops->disable_irq();
+	}
+	cpci_stop_thread();
+	return 0;
+}
+
+int __init
+cpci_hotplug_init(int debug)
+{
+	cpci_debug = debug;
+	return 0;
+}
+
+void __exit
+cpci_hotplug_exit(void)
+{
+	/*
+	 * Clean everything up.
+	 */
+	cpci_hp_stop();
+	cpci_hp_unregister_controller(controller);
+}
+
+EXPORT_SYMBOL_GPL(cpci_hp_register_controller);
+EXPORT_SYMBOL_GPL(cpci_hp_unregister_controller);
+EXPORT_SYMBOL_GPL(cpci_hp_register_bus);
+EXPORT_SYMBOL_GPL(cpci_hp_unregister_bus);
+EXPORT_SYMBOL_GPL(cpci_hp_start);
+EXPORT_SYMBOL_GPL(cpci_hp_stop);
diff --git a/drivers/pci/hotplug/cpci_hotplug_pci.c b/drivers/pci/hotplug/cpci_hotplug_pci.c
new file mode 100644
index 00000000..829c327c
--- /dev/null
+++ b/drivers/pci/hotplug/cpci_hotplug_pci.c
@@ -0,0 +1,353 @@
+/*
+ * CompactPCI Hot Plug Driver PCI functions
+ *
+ * Copyright (C) 2002,2005 by SOMA Networks, Inc.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <scottm@somanetworks.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/proc_fs.h>
+#include "../pci.h"
+#include "cpci_hotplug.h"
+
+#define MY_NAME	"cpci_hotplug"
+
+extern int cpci_debug;
+
+#define dbg(format, arg...)					\
+	do {							\
+		if (cpci_debug)					\
+			printk (KERN_DEBUG "%s: " format "\n",	\
+				MY_NAME , ## arg); 		\
+	} while (0)
+#define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
+#define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
+#define warn(format, arg...) printk(KERN_WARNING "%s: " format "\n", MY_NAME , ## arg)
+
+
+u8 cpci_get_attention_status(struct slot* slot)
+{
+	int hs_cap;
+	u16 hs_csr;
+
+	hs_cap = pci_bus_find_capability(slot->bus,
+					 slot->devfn,
+					 PCI_CAP_ID_CHSWP);
+	if (!hs_cap)
+		return 0;
+
+	if (pci_bus_read_config_word(slot->bus,
+				     slot->devfn,
+				     hs_cap + 2,
+				     &hs_csr))
+		return 0;
+
+	return hs_csr & 0x0008 ? 1 : 0;
+}
+
+int cpci_set_attention_status(struct slot* slot, int status)
+{
+	int hs_cap;
+	u16 hs_csr;
+
+	hs_cap = pci_bus_find_capability(slot->bus,
+					 slot->devfn,
+					 PCI_CAP_ID_CHSWP);
+	if (!hs_cap)
+		return 0;
+	if (pci_bus_read_config_word(slot->bus,
+				     slot->devfn,
+				     hs_cap + 2,
+				     &hs_csr))
+		return 0;
+	if (status)
+		hs_csr |= HS_CSR_LOO;
+	else
+		hs_csr &= ~HS_CSR_LOO;
+	if (pci_bus_write_config_word(slot->bus,
+				      slot->devfn,
+				      hs_cap + 2,
+				      hs_csr))
+		return 0;
+	return 1;
+}
+
+u16 cpci_get_hs_csr(struct slot* slot)
+{
+	int hs_cap;
+	u16 hs_csr;
+
+	hs_cap = pci_bus_find_capability(slot->bus,
+					 slot->devfn,
+					 PCI_CAP_ID_CHSWP);
+	if (!hs_cap)
+		return 0xFFFF;
+	if (pci_bus_read_config_word(slot->bus,
+				     slot->devfn,
+				     hs_cap + 2,
+				     &hs_csr))
+		return 0xFFFF;
+	return hs_csr;
+}
+
+int cpci_check_and_clear_ins(struct slot* slot)
+{
+	int hs_cap;
+	u16 hs_csr;
+	int ins = 0;
+
+	hs_cap = pci_bus_find_capability(slot->bus,
+					 slot->devfn,
+					 PCI_CAP_ID_CHSWP);
+	if (!hs_cap)
+		return 0;
+	if (pci_bus_read_config_word(slot->bus,
+				     slot->devfn,
+				     hs_cap + 2,
+				     &hs_csr))
+		return 0;
+	if (hs_csr & HS_CSR_INS) {
+		/* Clear INS (by setting it) */
+		if (pci_bus_write_config_word(slot->bus,
+					      slot->devfn,
+					      hs_cap + 2,
+					      hs_csr))
+			ins = 0;
+		else
+			ins = 1;
+	}
+	return ins;
+}
+
+int cpci_check_ext(struct slot* slot)
+{
+	int hs_cap;
+	u16 hs_csr;
+	int ext = 0;
+
+	hs_cap = pci_bus_find_capability(slot->bus,
+					 slot->devfn,
+					 PCI_CAP_ID_CHSWP);
+	if (!hs_cap)
+		return 0;
+	if (pci_bus_read_config_word(slot->bus,
+				     slot->devfn,
+				     hs_cap + 2,
+				     &hs_csr))
+		return 0;
+	if (hs_csr & HS_CSR_EXT)
+		ext = 1;
+	return ext;
+}
+
+int cpci_clear_ext(struct slot* slot)
+{
+	int hs_cap;
+	u16 hs_csr;
+
+	hs_cap = pci_bus_find_capability(slot->bus,
+					 slot->devfn,
+					 PCI_CAP_ID_CHSWP);
+	if (!hs_cap)
+		return -ENODEV;
+	if (pci_bus_read_config_word(slot->bus,
+				     slot->devfn,
+				     hs_cap + 2,
+				     &hs_csr))
+		return -ENODEV;
+	if (hs_csr & HS_CSR_EXT) {
+		/* Clear EXT (by setting it) */
+		if (pci_bus_write_config_word(slot->bus,
+					      slot->devfn,
+					      hs_cap + 2,
+					      hs_csr))
+			return -ENODEV;
+	}
+	return 0;
+}
+
+int cpci_led_on(struct slot* slot)
+{
+	int hs_cap;
+	u16 hs_csr;
+
+	hs_cap = pci_bus_find_capability(slot->bus,
+					 slot->devfn,
+					 PCI_CAP_ID_CHSWP);
+	if (!hs_cap)
+		return -ENODEV;
+	if (pci_bus_read_config_word(slot->bus,
+				     slot->devfn,
+				     hs_cap + 2,
+				     &hs_csr))
+		return -ENODEV;
+	if ((hs_csr & HS_CSR_LOO) != HS_CSR_LOO) {
+		hs_csr |= HS_CSR_LOO;
+		if (pci_bus_write_config_word(slot->bus,
+					      slot->devfn,
+					      hs_cap + 2,
+					      hs_csr)) {
+			err("Could not set LOO for slot %s",
+			    hotplug_slot_name(slot->hotplug_slot));
+			return -ENODEV;
+		}
+	}
+	return 0;
+}
+
+int cpci_led_off(struct slot* slot)
+{
+	int hs_cap;
+	u16 hs_csr;
+
+	hs_cap = pci_bus_find_capability(slot->bus,
+					 slot->devfn,
+					 PCI_CAP_ID_CHSWP);
+	if (!hs_cap)
+		return -ENODEV;
+	if (pci_bus_read_config_word(slot->bus,
+				     slot->devfn,
+				     hs_cap + 2,
+				     &hs_csr))
+		return -ENODEV;
+	if (hs_csr & HS_CSR_LOO) {
+		hs_csr &= ~HS_CSR_LOO;
+		if (pci_bus_write_config_word(slot->bus,
+					      slot->devfn,
+					      hs_cap + 2,
+					      hs_csr)) {
+			err("Could not clear LOO for slot %s",
+			    hotplug_slot_name(slot->hotplug_slot));
+			return -ENODEV;
+		}
+	}
+	return 0;
+}
+
+
+/*
+ * Device configuration functions
+ */
+
+int __ref cpci_configure_slot(struct slot *slot)
+{
+	struct pci_bus *parent;
+	int fn;
+
+	dbg("%s - enter", __func__);
+
+	if (slot->dev == NULL) {
+		dbg("pci_dev null, finding %02x:%02x:%x",
+		    slot->bus->number, PCI_SLOT(slot->devfn), PCI_FUNC(slot->devfn));
+		slot->dev = pci_get_slot(slot->bus, slot->devfn);
+	}
+
+	/* Still NULL? Well then scan for it! */
+	if (slot->dev == NULL) {
+		int n;
+		dbg("pci_dev still null");
+
+		/*
+		 * This will generate pci_dev structures for all functions, but
+		 * we will only call this case when lookup fails.
+		 */
+		n = pci_scan_slot(slot->bus, slot->devfn);
+		dbg("%s: pci_scan_slot returned %d", __func__, n);
+		slot->dev = pci_get_slot(slot->bus, slot->devfn);
+		if (slot->dev == NULL) {
+			err("Could not find PCI device for slot %02x", slot->number);
+			return -ENODEV;
+		}
+	}
+	parent = slot->dev->bus;
+
+	for (fn = 0; fn < 8; fn++) {
+		struct pci_dev *dev;
+
+		dev = pci_get_slot(parent, PCI_DEVFN(PCI_SLOT(slot->devfn), fn));
+		if (!dev)
+			continue;
+		if ((dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) ||
+		    (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)) {
+			/* Find an unused bus number for the new bridge */
+			struct pci_bus *child;
+			unsigned char busnr, start = parent->secondary;
+			unsigned char end = parent->subordinate;
+
+			for (busnr = start; busnr <= end; busnr++) {
+				if (!pci_find_bus(pci_domain_nr(parent),
+						  busnr))
+					break;
+			}
+			if (busnr >= end) {
+				err("No free bus for hot-added bridge\n");
+				pci_dev_put(dev);
+				continue;
+			}
+			child = pci_add_new_bus(parent, dev, busnr);
+			if (!child) {
+				err("Cannot add new bus for %s\n",
+				    pci_name(dev));
+				pci_dev_put(dev);
+				continue;
+			}
+			child->subordinate = pci_do_scan_bus(child);
+			pci_bus_size_bridges(child);
+		}
+		pci_dev_put(dev);
+	}
+
+	pci_bus_assign_resources(parent);
+	pci_bus_add_devices(parent);
+	pci_enable_bridges(parent);
+
+	dbg("%s - exit", __func__);
+	return 0;
+}
+
+int cpci_unconfigure_slot(struct slot* slot)
+{
+	int i;
+	struct pci_dev *dev;
+
+	dbg("%s - enter", __func__);
+	if (!slot->dev) {
+		err("No device for slot %02x\n", slot->number);
+		return -ENODEV;
+	}
+
+	for (i = 0; i < 8; i++) {
+		dev = pci_get_slot(slot->bus,
+				    PCI_DEVFN(PCI_SLOT(slot->devfn), i));
+		if (dev) {
+			pci_remove_bus_device(dev);
+			pci_dev_put(dev);
+		}
+	}
+	pci_dev_put(slot->dev);
+	slot->dev = NULL;
+
+	dbg("%s - exit", __func__);
+	return 0;
+}
diff --git a/drivers/pci/hotplug/cpcihp_generic.c b/drivers/pci/hotplug/cpcihp_generic.c
new file mode 100644
index 00000000..fb3f8466
--- /dev/null
+++ b/drivers/pci/hotplug/cpcihp_generic.c
@@ -0,0 +1,230 @@
+/*
+ * cpcihp_generic.c
+ *
+ * Generic port I/O CompactPCI driver
+ *
+ * Copyright 2002 SOMA Networks, Inc.
+ * Copyright 2001 Intel San Luis Obispo
+ * Copyright 2000,2001 MontaVista Software Inc.
+ *
+ * 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.
+ *
+ * THIS SOFTWARE IS PROVIDED "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY 
+ * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL 
+ * THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, 
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, 
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 
+ * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 
+ * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING 
+ * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * This generic CompactPCI hotplug driver should allow using the PCI hotplug
+ * mechanism on any CompactPCI board that exposes the #ENUM signal as a bit
+ * in a system register that can be read through standard port I/O.
+ *
+ * Send feedback to <scottm@somanetworks.com>
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+#include "cpci_hotplug.h"
+
+#define DRIVER_VERSION	"0.1"
+#define DRIVER_AUTHOR	"Scott Murray <scottm@somanetworks.com>"
+#define DRIVER_DESC	"Generic port I/O CompactPCI Hot Plug Driver"
+
+#if !defined(MODULE)
+#define MY_NAME	"cpcihp_generic"
+#else
+#define MY_NAME	THIS_MODULE->name
+#endif
+
+#define dbg(format, arg...)					\
+	do {							\
+		if(debug)					\
+			printk (KERN_DEBUG "%s: " format "\n",	\
+				MY_NAME , ## arg); 		\
+	} while(0)
+#define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
+#define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
+#define warn(format, arg...) printk(KERN_WARNING "%s: " format "\n", MY_NAME , ## arg)
+
+/* local variables */
+static int debug;
+static char *bridge;
+static u8 bridge_busnr;
+static u8 bridge_slot;
+static struct pci_bus *bus;
+static u8 first_slot;
+static u8 last_slot;
+static u16 port;
+static unsigned int enum_bit;
+static u8 enum_mask;
+
+static struct cpci_hp_controller_ops generic_hpc_ops;
+static struct cpci_hp_controller generic_hpc;
+
+static int __init validate_parameters(void)
+{
+	char* str;
+	char* p;
+	unsigned long tmp;
+
+	if(!bridge) {
+		info("not configured, disabling.");
+		return -EINVAL;
+	}
+	str = bridge;
+	if(!*str)
+		return -EINVAL;
+
+	tmp = simple_strtoul(str, &p, 16);
+	if(p == str || tmp > 0xff) {
+		err("Invalid hotplug bus bridge device bus number");
+		return -EINVAL;
+	}
+	bridge_busnr = (u8) tmp;
+	dbg("bridge_busnr = 0x%02x", bridge_busnr);
+	if(*p != ':') {
+		err("Invalid hotplug bus bridge device");
+		return -EINVAL;
+	}
+	str = p + 1;
+	tmp = simple_strtoul(str, &p, 16);
+	if(p == str || tmp > 0x1f) {
+		err("Invalid hotplug bus bridge device slot number");
+		return -EINVAL;
+	}
+	bridge_slot = (u8) tmp;
+	dbg("bridge_slot = 0x%02x", bridge_slot);
+
+	dbg("first_slot = 0x%02x", first_slot);
+	dbg("last_slot = 0x%02x", last_slot);
+	if(!(first_slot && last_slot)) {
+		err("Need to specify first_slot and last_slot");
+		return -EINVAL;
+	}
+	if(last_slot < first_slot) {
+		err("first_slot must be less than last_slot");
+		return -EINVAL;
+	}
+
+	dbg("port = 0x%04x", port);
+	dbg("enum_bit = 0x%02x", enum_bit);
+	if(enum_bit > 7) {
+		err("Invalid #ENUM bit");
+		return -EINVAL;
+	}
+	enum_mask = 1 << enum_bit;
+	return 0;
+}
+
+static int query_enum(void)
+{
+	u8 value;
+
+	value = inb_p(port);
+	return ((value & enum_mask) == enum_mask);
+}
+
+static int __init cpcihp_generic_init(void)
+{
+	int status;
+	struct resource* r;
+	struct pci_dev* dev;
+
+	info(DRIVER_DESC " version: " DRIVER_VERSION);
+	status = validate_parameters();
+	if (status)
+		return status;
+
+	r = request_region(port, 1, "#ENUM hotswap signal register");
+	if(!r)
+		return -EBUSY;
+
+	bus = pci_find_bus(0, bridge_busnr);
+	if (!bus) {
+		err("Invalid bus number %d", bridge_busnr);
+		return -EINVAL;
+	}
+	dev = pci_get_slot(bus, PCI_DEVFN(bridge_slot, 0));
+	if(!dev || dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) {
+		err("Invalid bridge device %s", bridge);
+		pci_dev_put(dev);
+		return -EINVAL;
+	}
+	bus = dev->subordinate;
+	pci_dev_put(dev);
+
+	memset(&generic_hpc, 0, sizeof (struct cpci_hp_controller));
+	generic_hpc_ops.query_enum = query_enum;
+	generic_hpc.ops = &generic_hpc_ops;
+
+	status = cpci_hp_register_controller(&generic_hpc);
+	if(status != 0) {
+		err("Could not register cPCI hotplug controller");
+		return -ENODEV;
+	}
+	dbg("registered controller");
+
+	status = cpci_hp_register_bus(bus, first_slot, last_slot);
+	if(status != 0) {
+		err("Could not register cPCI hotplug bus");
+		goto init_bus_register_error;
+	}
+	dbg("registered bus");
+
+	status = cpci_hp_start();
+	if(status != 0) {
+		err("Could not started cPCI hotplug system");
+		goto init_start_error;
+	}
+	dbg("started cpci hp system");
+	return 0;
+init_start_error:
+	cpci_hp_unregister_bus(bus);
+init_bus_register_error:
+	cpci_hp_unregister_controller(&generic_hpc);
+	err("status = %d", status);
+	return status;
+
+}
+
+static void __exit cpcihp_generic_exit(void)
+{
+	cpci_hp_stop();
+	cpci_hp_unregister_bus(bus);
+	cpci_hp_unregister_controller(&generic_hpc);
+	release_region(port, 1);
+}
+
+module_init(cpcihp_generic_init);
+module_exit(cpcihp_generic_exit);
+
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+module_param(debug, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(debug, "Debugging mode enabled or not");
+module_param(bridge, charp, 0);
+MODULE_PARM_DESC(bridge, "Hotswap bus bridge device, <bus>:<slot> (bus and slot are in hexadecimal)");
+module_param(first_slot, byte, 0);
+MODULE_PARM_DESC(first_slot, "Hotswap bus first slot number");
+module_param(last_slot, byte, 0);
+MODULE_PARM_DESC(last_slot, "Hotswap bus last slot number");
+module_param(port, ushort, 0);
+MODULE_PARM_DESC(port, "#ENUM signal I/O port");
+module_param(enum_bit, uint, 0);
+MODULE_PARM_DESC(enum_bit, "#ENUM signal bit (0-7)");
diff --git a/drivers/pci/hotplug/cpcihp_zt5550.c b/drivers/pci/hotplug/cpcihp_zt5550.c
new file mode 100644
index 00000000..41f6a8d7
--- /dev/null
+++ b/drivers/pci/hotplug/cpcihp_zt5550.c
@@ -0,0 +1,328 @@
+/*
+ * cpcihp_zt5550.c
+ *
+ * Intel/Ziatech ZT5550 CompactPCI Host Controller driver
+ *
+ * Copyright 2002 SOMA Networks, Inc.
+ * Copyright 2001 Intel San Luis Obispo
+ * Copyright 2000,2001 MontaVista Software Inc.
+ *
+ * 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.
+ *
+ * THIS SOFTWARE IS PROVIDED "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY 
+ * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL 
+ * THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, 
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, 
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 
+ * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 
+ * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING 
+ * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <scottm@somanetworks.com>
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/signal.h>	/* IRQF_SHARED */
+#include "cpci_hotplug.h"
+#include "cpcihp_zt5550.h"
+
+#define DRIVER_VERSION	"0.2"
+#define DRIVER_AUTHOR	"Scott Murray <scottm@somanetworks.com>"
+#define DRIVER_DESC	"ZT5550 CompactPCI Hot Plug Driver"
+
+#define MY_NAME	"cpcihp_zt5550"
+
+#define dbg(format, arg...)					\
+	do {							\
+		if(debug)					\
+			printk (KERN_DEBUG "%s: " format "\n",	\
+				MY_NAME , ## arg); 		\
+	} while(0)
+#define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
+#define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
+#define warn(format, arg...) printk(KERN_WARNING "%s: " format "\n", MY_NAME , ## arg)
+
+/* local variables */
+static int debug;
+static int poll;
+static struct cpci_hp_controller_ops zt5550_hpc_ops;
+static struct cpci_hp_controller zt5550_hpc;
+
+/* Primary cPCI bus bridge device */
+static struct pci_dev *bus0_dev;
+static struct pci_bus *bus0;
+
+/* Host controller device */
+static struct pci_dev *hc_dev;
+
+/* Host controller register addresses */
+static void __iomem *hc_registers;
+static void __iomem *csr_hc_index;
+static void __iomem *csr_hc_data;
+static void __iomem *csr_int_status;
+static void __iomem *csr_int_mask;
+
+
+static int zt5550_hc_config(struct pci_dev *pdev)
+{
+	int ret;
+
+	/* Since we know that no boards exist with two HC chips, treat it as an error */
+	if(hc_dev) {
+		err("too many host controller devices?");
+		return -EBUSY;
+	}
+
+	ret = pci_enable_device(pdev);
+	if(ret) {
+		err("cannot enable %s\n", pci_name(pdev));
+		return ret;
+	}
+
+	hc_dev = pdev;
+	dbg("hc_dev = %p", hc_dev);
+	dbg("pci resource start %llx", (unsigned long long)pci_resource_start(hc_dev, 1));
+	dbg("pci resource len %llx", (unsigned long long)pci_resource_len(hc_dev, 1));
+
+	if(!request_mem_region(pci_resource_start(hc_dev, 1),
+				pci_resource_len(hc_dev, 1), MY_NAME)) {
+		err("cannot reserve MMIO region");
+		ret = -ENOMEM;
+		goto exit_disable_device;
+	}
+
+	hc_registers =
+	    ioremap(pci_resource_start(hc_dev, 1), pci_resource_len(hc_dev, 1));
+	if(!hc_registers) {
+		err("cannot remap MMIO region %llx @ %llx",
+			(unsigned long long)pci_resource_len(hc_dev, 1),
+			(unsigned long long)pci_resource_start(hc_dev, 1));
+		ret = -ENODEV;
+		goto exit_release_region;
+	}
+
+	csr_hc_index = hc_registers + CSR_HCINDEX;
+	csr_hc_data = hc_registers + CSR_HCDATA;
+	csr_int_status = hc_registers + CSR_INTSTAT;
+	csr_int_mask = hc_registers + CSR_INTMASK;
+
+	/*
+	 * Disable host control, fault and serial interrupts
+	 */
+	dbg("disabling host control, fault and serial interrupts");
+	writeb((u8) HC_INT_MASK_REG, csr_hc_index);
+	writeb((u8) ALL_INDEXED_INTS_MASK, csr_hc_data);
+	dbg("disabled host control, fault and serial interrupts");
+
+	/*
+	 * Disable timer0, timer1 and ENUM interrupts
+	 */
+	dbg("disabling timer0, timer1 and ENUM interrupts");
+	writeb((u8) ALL_DIRECT_INTS_MASK, csr_int_mask);
+	dbg("disabled timer0, timer1 and ENUM interrupts");
+	return 0;
+
+exit_release_region:
+	release_mem_region(pci_resource_start(hc_dev, 1),
+			   pci_resource_len(hc_dev, 1));
+exit_disable_device:
+	pci_disable_device(hc_dev);
+	return ret;
+}
+
+static int zt5550_hc_cleanup(void)
+{
+	if(!hc_dev)
+		return -ENODEV;
+
+	iounmap(hc_registers);
+	release_mem_region(pci_resource_start(hc_dev, 1),
+			   pci_resource_len(hc_dev, 1));
+	pci_disable_device(hc_dev);
+	return 0;
+}
+
+static int zt5550_hc_query_enum(void)
+{
+	u8 value;
+
+	value = inb_p(ENUM_PORT);
+	return ((value & ENUM_MASK) == ENUM_MASK);
+}
+
+static int zt5550_hc_check_irq(void *dev_id)
+{
+	int ret;
+	u8 reg;
+
+	ret = 0;
+	if(dev_id == zt5550_hpc.dev_id) {
+		reg = readb(csr_int_status);
+		if(reg)
+			ret = 1;
+	}
+	return ret;
+}
+
+static int zt5550_hc_enable_irq(void)
+{
+	u8 reg;
+
+	if(hc_dev == NULL) {
+		return -ENODEV;
+	}
+	reg = readb(csr_int_mask);
+	reg = reg & ~ENUM_INT_MASK;
+	writeb(reg, csr_int_mask);
+	return 0;
+}
+
+static int zt5550_hc_disable_irq(void)
+{
+	u8 reg;
+
+	if(hc_dev == NULL) {
+		return -ENODEV;
+	}
+
+	reg = readb(csr_int_mask);
+	reg = reg | ENUM_INT_MASK;
+	writeb(reg, csr_int_mask);
+	return 0;
+}
+
+static int zt5550_hc_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	int status;
+
+	status = zt5550_hc_config(pdev);
+	if(status != 0) {
+		return status;
+	}
+	dbg("returned from zt5550_hc_config");
+
+	memset(&zt5550_hpc, 0, sizeof (struct cpci_hp_controller));
+	zt5550_hpc_ops.query_enum = zt5550_hc_query_enum;
+	zt5550_hpc.ops = &zt5550_hpc_ops;
+	if(!poll) {
+		zt5550_hpc.irq = hc_dev->irq;
+		zt5550_hpc.irq_flags = IRQF_SHARED;
+		zt5550_hpc.dev_id = hc_dev;
+
+		zt5550_hpc_ops.enable_irq = zt5550_hc_enable_irq;
+		zt5550_hpc_ops.disable_irq = zt5550_hc_disable_irq;
+		zt5550_hpc_ops.check_irq = zt5550_hc_check_irq;
+	} else {
+		info("using ENUM# polling mode");
+	}
+
+	status = cpci_hp_register_controller(&zt5550_hpc);
+	if(status != 0) {
+		err("could not register cPCI hotplug controller");
+		goto init_hc_error;
+	}
+	dbg("registered controller");
+
+	/* Look for first device matching cPCI bus's bridge vendor and device IDs */
+	if(!(bus0_dev = pci_get_device(PCI_VENDOR_ID_DEC,
+					 PCI_DEVICE_ID_DEC_21154, NULL))) {
+		status = -ENODEV;
+		goto init_register_error;
+	}
+	bus0 = bus0_dev->subordinate;
+	pci_dev_put(bus0_dev);
+
+	status = cpci_hp_register_bus(bus0, 0x0a, 0x0f);
+	if(status != 0) {
+		err("could not register cPCI hotplug bus");
+		goto init_register_error;
+	}
+	dbg("registered bus");
+
+	status = cpci_hp_start();
+	if(status != 0) {
+		err("could not started cPCI hotplug system");
+		cpci_hp_unregister_bus(bus0);
+		goto init_register_error;
+	}
+	dbg("started cpci hp system");
+
+	return 0;
+init_register_error:
+	cpci_hp_unregister_controller(&zt5550_hpc);
+init_hc_error:
+	err("status = %d", status);
+	zt5550_hc_cleanup();
+	return status;
+
+}
+
+static void __devexit zt5550_hc_remove_one(struct pci_dev *pdev)
+{
+	cpci_hp_stop();
+	cpci_hp_unregister_bus(bus0);
+	cpci_hp_unregister_controller(&zt5550_hpc);
+	zt5550_hc_cleanup();
+}
+
+
+static struct pci_device_id zt5550_hc_pci_tbl[] = {
+	{ PCI_VENDOR_ID_ZIATECH, PCI_DEVICE_ID_ZIATECH_5550_HC, PCI_ANY_ID, PCI_ANY_ID, },
+	{ 0, }
+};
+MODULE_DEVICE_TABLE(pci, zt5550_hc_pci_tbl);
+	
+static struct pci_driver zt5550_hc_driver = {
+	.name		= "zt5550_hc",
+	.id_table	= zt5550_hc_pci_tbl,
+	.probe		= zt5550_hc_init_one,
+	.remove		= __devexit_p(zt5550_hc_remove_one),
+};
+
+static int __init zt5550_init(void)
+{
+	struct resource* r;
+	int rc;
+
+	info(DRIVER_DESC " version: " DRIVER_VERSION);
+	r = request_region(ENUM_PORT, 1, "#ENUM hotswap signal register");
+	if(!r)
+		return -EBUSY;
+
+	rc = pci_register_driver(&zt5550_hc_driver);
+	if(rc < 0)
+		release_region(ENUM_PORT, 1);
+	return rc;
+}
+
+static void __exit
+zt5550_exit(void)
+{
+	pci_unregister_driver(&zt5550_hc_driver);
+	release_region(ENUM_PORT, 1);
+}
+
+module_init(zt5550_init);
+module_exit(zt5550_exit);
+
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+module_param(debug, bool, 0644);
+MODULE_PARM_DESC(debug, "Debugging mode enabled or not");
+module_param(poll, bool, 0644);
+MODULE_PARM_DESC(poll, "#ENUM polling mode enabled or not");
diff --git a/drivers/pci/hotplug/cpcihp_zt5550.h b/drivers/pci/hotplug/cpcihp_zt5550.h
new file mode 100644
index 00000000..bebc6060
--- /dev/null
+++ b/drivers/pci/hotplug/cpcihp_zt5550.h
@@ -0,0 +1,79 @@
+/*
+ * cpcihp_zt5550.h
+ *
+ * Intel/Ziatech ZT5550 CompactPCI Host Controller driver definitions
+ *
+ * Copyright 2002 SOMA Networks, Inc.
+ * Copyright 2001 Intel San Luis Obispo
+ * Copyright 2000,2001 MontaVista Software Inc.
+ *
+ * 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.
+ *
+ * THIS SOFTWARE IS PROVIDED "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY 
+ * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL 
+ * THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, 
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, 
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 
+ * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 
+ * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING 
+ * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <scottm@somanetworks.com>
+ */
+
+#ifndef _CPCIHP_ZT5550_H
+#define _CPCIHP_ZT5550_H
+
+/* Direct registers */
+#define CSR_HCINDEX		0x00
+#define CSR_HCDATA		0x04
+#define CSR_INTSTAT		0x08
+#define CSR_INTMASK		0x09
+#define CSR_CNT0CMD		0x0C
+#define CSR_CNT1CMD		0x0E
+#define CSR_CNT0		0x10
+#define CSR_CNT1		0x14
+
+/* Masks for interrupt bits in CSR_INTMASK direct register */
+#define CNT0_INT_MASK		0x01
+#define CNT1_INT_MASK		0x02
+#define ENUM_INT_MASK		0x04
+#define ALL_DIRECT_INTS_MASK	0x07
+
+/* Indexed registers (through CSR_INDEX, CSR_DATA) */
+#define HC_INT_MASK_REG		0x04
+#define HC_STATUS_REG		0x08
+#define HC_CMD_REG		0x0C
+#define ARB_CONFIG_GNT_REG	0x10
+#define ARB_CONFIG_CFG_REG	0x12
+#define ARB_CONFIG_REG	 	0x10
+#define ISOL_CONFIG_REG		0x18
+#define FAULT_STATUS_REG	0x20
+#define FAULT_CONFIG_REG	0x24
+#define WD_CONFIG_REG		0x2C
+#define HC_DIAG_REG		0x30
+#define SERIAL_COMM_REG		0x34
+#define SERIAL_OUT_REG		0x38
+#define SERIAL_IN_REG		0x3C
+
+/* Masks for interrupt bits in HC_INT_MASK_REG indexed register */
+#define SERIAL_INT_MASK		0x01
+#define FAULT_INT_MASK		0x02
+#define HCF_INT_MASK		0x04
+#define ALL_INDEXED_INTS_MASK	0x07
+
+/* Digital I/O port storing ENUM# */
+#define ENUM_PORT	0xE1
+/* Mask to get to the ENUM# bit on the bus */
+#define ENUM_MASK	0x40
+
+#endif				/* _CPCIHP_ZT5550_H */
diff --git a/drivers/pci/hotplug/cpqphp.h b/drivers/pci/hotplug/cpqphp.h
new file mode 100644
index 00000000..d8ffc736
--- /dev/null
+++ b/drivers/pci/hotplug/cpqphp.h
@@ -0,0 +1,744 @@
+/*
+ * Compaq Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>
+ *
+ */
+#ifndef _CPQPHP_H
+#define _CPQPHP_H
+
+#include <linux/interrupt.h>
+#include <asm/io.h>		/* for read? and write? functions */
+#include <linux/delay.h>	/* for delays */
+#include <linux/mutex.h>
+#include <linux/sched.h>	/* for signal_pending() */
+
+#define MY_NAME	"cpqphp"
+
+#define dbg(fmt, arg...) do { if (cpqhp_debug) printk(KERN_DEBUG "%s: " fmt , MY_NAME , ## arg); } while (0)
+#define err(format, arg...) printk(KERN_ERR "%s: " format , MY_NAME , ## arg)
+#define info(format, arg...) printk(KERN_INFO "%s: " format , MY_NAME , ## arg)
+#define warn(format, arg...) printk(KERN_WARNING "%s: " format , MY_NAME , ## arg)
+
+
+
+struct smbios_system_slot {
+	u8 type;
+	u8 length;
+	u16 handle;
+	u8 name_string_num;
+	u8 slot_type;
+	u8 slot_width;
+	u8 slot_current_usage;
+	u8 slot_length;
+	u16 slot_number;
+	u8 properties1;
+	u8 properties2;
+} __attribute__ ((packed));
+
+/* offsets to the smbios generic type based on the above structure layout */
+enum smbios_system_slot_offsets {
+	SMBIOS_SLOT_GENERIC_TYPE =	offsetof(struct smbios_system_slot, type),
+	SMBIOS_SLOT_GENERIC_LENGTH =	offsetof(struct smbios_system_slot, length),
+	SMBIOS_SLOT_GENERIC_HANDLE =	offsetof(struct smbios_system_slot, handle),
+	SMBIOS_SLOT_NAME_STRING_NUM =	offsetof(struct smbios_system_slot, name_string_num),
+	SMBIOS_SLOT_TYPE =		offsetof(struct smbios_system_slot, slot_type),
+	SMBIOS_SLOT_WIDTH =		offsetof(struct smbios_system_slot, slot_width),
+	SMBIOS_SLOT_CURRENT_USAGE =	offsetof(struct smbios_system_slot, slot_current_usage),
+	SMBIOS_SLOT_LENGTH =		offsetof(struct smbios_system_slot, slot_length),
+	SMBIOS_SLOT_NUMBER =		offsetof(struct smbios_system_slot, slot_number),
+	SMBIOS_SLOT_PROPERTIES1 =	offsetof(struct smbios_system_slot, properties1),
+	SMBIOS_SLOT_PROPERTIES2 =	offsetof(struct smbios_system_slot, properties2),
+};
+
+struct smbios_generic {
+	u8 type;
+	u8 length;
+	u16 handle;
+} __attribute__ ((packed));
+
+/* offsets to the smbios generic type based on the above structure layout */
+enum smbios_generic_offsets {
+	SMBIOS_GENERIC_TYPE =	offsetof(struct smbios_generic, type),
+	SMBIOS_GENERIC_LENGTH =	offsetof(struct smbios_generic, length),
+	SMBIOS_GENERIC_HANDLE =	offsetof(struct smbios_generic, handle),
+};
+
+struct smbios_entry_point {
+	char anchor[4];
+	u8 ep_checksum;
+	u8 ep_length;
+	u8 major_version;
+	u8 minor_version;
+	u16 max_size_entry;
+	u8 ep_rev;
+	u8 reserved[5];
+	char int_anchor[5];
+	u8 int_checksum;
+	u16 st_length;
+	u32 st_address;
+	u16 number_of_entrys;
+	u8 bcd_rev;
+} __attribute__ ((packed));
+
+/* offsets to the smbios entry point based on the above structure layout */
+enum smbios_entry_point_offsets {
+	ANCHOR =		offsetof(struct smbios_entry_point, anchor[0]),
+	EP_CHECKSUM =		offsetof(struct smbios_entry_point, ep_checksum),
+	EP_LENGTH =		offsetof(struct smbios_entry_point, ep_length),
+	MAJOR_VERSION =		offsetof(struct smbios_entry_point, major_version),
+	MINOR_VERSION =		offsetof(struct smbios_entry_point, minor_version),
+	MAX_SIZE_ENTRY =	offsetof(struct smbios_entry_point, max_size_entry),
+	EP_REV =		offsetof(struct smbios_entry_point, ep_rev),
+	INT_ANCHOR =		offsetof(struct smbios_entry_point, int_anchor[0]),
+	INT_CHECKSUM =		offsetof(struct smbios_entry_point, int_checksum),
+	ST_LENGTH =		offsetof(struct smbios_entry_point, st_length),
+	ST_ADDRESS =		offsetof(struct smbios_entry_point, st_address),
+	NUMBER_OF_ENTRYS =	offsetof(struct smbios_entry_point, number_of_entrys),
+	BCD_REV =		offsetof(struct smbios_entry_point, bcd_rev),
+};
+
+struct ctrl_reg {			/* offset */
+	u8	slot_RST;		/* 0x00 */
+	u8	slot_enable;		/* 0x01 */
+	u16	misc;			/* 0x02 */
+	u32	led_control;		/* 0x04 */
+	u32	int_input_clear;	/* 0x08 */
+	u32	int_mask;		/* 0x0a */
+	u8	reserved0;		/* 0x10 */
+	u8	reserved1;		/* 0x11 */
+	u8	reserved2;		/* 0x12 */
+	u8	gen_output_AB;		/* 0x13 */
+	u32	non_int_input;		/* 0x14 */
+	u32	reserved3;		/* 0x18 */
+	u32	reserved4;		/* 0x1a */
+	u32	reserved5;		/* 0x20 */
+	u8	reserved6;		/* 0x24 */
+	u8	reserved7;		/* 0x25 */
+	u16	reserved8;		/* 0x26 */
+	u8	slot_mask;		/* 0x28 */
+	u8	reserved9;		/* 0x29 */
+	u8	reserved10;		/* 0x2a */
+	u8	reserved11;		/* 0x2b */
+	u8	slot_SERR;		/* 0x2c */
+	u8	slot_power;		/* 0x2d */
+	u8	reserved12;		/* 0x2e */
+	u8	reserved13;		/* 0x2f */
+	u8	next_curr_freq;		/* 0x30 */
+	u8	reset_freq_mode;	/* 0x31 */
+} __attribute__ ((packed));
+
+/* offsets to the controller registers based on the above structure layout */
+enum ctrl_offsets {
+	SLOT_RST =		offsetof(struct ctrl_reg, slot_RST),
+	SLOT_ENABLE =		offsetof(struct ctrl_reg, slot_enable),
+	MISC =			offsetof(struct ctrl_reg, misc),
+	LED_CONTROL =		offsetof(struct ctrl_reg, led_control),
+	INT_INPUT_CLEAR =	offsetof(struct ctrl_reg, int_input_clear),
+	INT_MASK =		offsetof(struct ctrl_reg, int_mask),
+	CTRL_RESERVED0 =	offsetof(struct ctrl_reg, reserved0),
+	CTRL_RESERVED1 =	offsetof(struct ctrl_reg, reserved1),
+	CTRL_RESERVED2 =	offsetof(struct ctrl_reg, reserved1),
+	GEN_OUTPUT_AB =		offsetof(struct ctrl_reg, gen_output_AB),
+	NON_INT_INPUT =		offsetof(struct ctrl_reg, non_int_input),
+	CTRL_RESERVED3 =	offsetof(struct ctrl_reg, reserved3),
+	CTRL_RESERVED4 =	offsetof(struct ctrl_reg, reserved4),
+	CTRL_RESERVED5 =	offsetof(struct ctrl_reg, reserved5),
+	CTRL_RESERVED6 =	offsetof(struct ctrl_reg, reserved6),
+	CTRL_RESERVED7 =	offsetof(struct ctrl_reg, reserved7),
+	CTRL_RESERVED8 =	offsetof(struct ctrl_reg, reserved8),
+	SLOT_MASK =		offsetof(struct ctrl_reg, slot_mask),
+	CTRL_RESERVED9 =	offsetof(struct ctrl_reg, reserved9),
+	CTRL_RESERVED10 =	offsetof(struct ctrl_reg, reserved10),
+	CTRL_RESERVED11 =	offsetof(struct ctrl_reg, reserved11),
+	SLOT_SERR =		offsetof(struct ctrl_reg, slot_SERR),
+	SLOT_POWER =		offsetof(struct ctrl_reg, slot_power),
+	NEXT_CURR_FREQ =	offsetof(struct ctrl_reg, next_curr_freq),
+	RESET_FREQ_MODE =	offsetof(struct ctrl_reg, reset_freq_mode),
+};
+
+struct hrt {
+	char sig0;
+	char sig1;
+	char sig2;
+	char sig3;
+	u16 unused_IRQ;
+	u16 PCIIRQ;
+	u8 number_of_entries;
+	u8 revision;
+	u16 reserved1;
+	u32 reserved2;
+} __attribute__ ((packed));
+
+/* offsets to the hotplug resource table registers based on the above
+ * structure layout
+ */
+enum hrt_offsets {
+	SIG0 =			offsetof(struct hrt, sig0),
+	SIG1 =			offsetof(struct hrt, sig1),
+	SIG2 =			offsetof(struct hrt, sig2),
+	SIG3 =			offsetof(struct hrt, sig3),
+	UNUSED_IRQ =		offsetof(struct hrt, unused_IRQ),
+	PCIIRQ =		offsetof(struct hrt, PCIIRQ),
+	NUMBER_OF_ENTRIES =	offsetof(struct hrt, number_of_entries),
+	REVISION =		offsetof(struct hrt, revision),
+	HRT_RESERVED1 =		offsetof(struct hrt, reserved1),
+	HRT_RESERVED2 =		offsetof(struct hrt, reserved2),
+};
+
+struct slot_rt {
+	u8 dev_func;
+	u8 primary_bus;
+	u8 secondary_bus;
+	u8 max_bus;
+	u16 io_base;
+	u16 io_length;
+	u16 mem_base;
+	u16 mem_length;
+	u16 pre_mem_base;
+	u16 pre_mem_length;
+} __attribute__ ((packed));
+
+/* offsets to the hotplug slot resource table registers based on the above
+ * structure layout
+ */
+enum slot_rt_offsets {
+	DEV_FUNC =		offsetof(struct slot_rt, dev_func),
+	PRIMARY_BUS =		offsetof(struct slot_rt, primary_bus),
+	SECONDARY_BUS =		offsetof(struct slot_rt, secondary_bus),
+	MAX_BUS =		offsetof(struct slot_rt, max_bus),
+	IO_BASE =		offsetof(struct slot_rt, io_base),
+	IO_LENGTH =		offsetof(struct slot_rt, io_length),
+	MEM_BASE =		offsetof(struct slot_rt, mem_base),
+	MEM_LENGTH =		offsetof(struct slot_rt, mem_length),
+	PRE_MEM_BASE =		offsetof(struct slot_rt, pre_mem_base),
+	PRE_MEM_LENGTH =	offsetof(struct slot_rt, pre_mem_length),
+};
+
+struct pci_func {
+	struct pci_func *next;
+	u8 bus;
+	u8 device;
+	u8 function;
+	u8 is_a_board;
+	u16 status;
+	u8 configured;
+	u8 switch_save;
+	u8 presence_save;
+	u32 base_length[0x06];
+	u8 base_type[0x06];
+	u16 reserved2;
+	u32 config_space[0x20];
+	struct pci_resource *mem_head;
+	struct pci_resource *p_mem_head;
+	struct pci_resource *io_head;
+	struct pci_resource *bus_head;
+	struct timer_list *p_task_event;
+	struct pci_dev* pci_dev;
+};
+
+struct slot {
+	struct slot *next;
+	u8 bus;
+	u8 device;
+	u8 number;
+	u8 is_a_board;
+	u8 configured;
+	u8 state;
+	u8 switch_save;
+	u8 presence_save;
+	u32 capabilities;
+	u16 reserved2;
+	struct timer_list task_event;
+	u8 hp_slot;
+	struct controller *ctrl;
+	void __iomem *p_sm_slot;
+	struct hotplug_slot *hotplug_slot;
+};
+
+struct pci_resource {
+	struct pci_resource * next;
+	u32 base;
+	u32 length;
+};
+
+struct event_info {
+	u32 event_type;
+	u8 hp_slot;
+};
+
+struct controller {
+	struct controller *next;
+	u32 ctrl_int_comp;
+	struct mutex crit_sect;	/* critical section mutex */
+	void __iomem *hpc_reg;	/* cookie for our pci controller location */
+	struct pci_resource *mem_head;
+	struct pci_resource *p_mem_head;
+	struct pci_resource *io_head;
+	struct pci_resource *bus_head;
+	struct pci_dev *pci_dev;
+	struct pci_bus *pci_bus;
+	struct event_info event_queue[10];
+	struct slot *slot;
+	u8 next_event;
+	u8 interrupt;
+	u8 cfgspc_irq;
+	u8 bus;			/* bus number for the pci hotplug controller */
+	u8 rev;
+	u8 slot_device_offset;
+	u8 first_slot;
+	u8 add_support;
+	u8 push_flag;
+	u8 push_button;			/* 0 = no pushbutton, 1 = pushbutton present */
+	u8 slot_switch_type;		/* 0 = no switch, 1 = switch present */
+	u8 defeature_PHP;		/* 0 = PHP not supported, 1 = PHP supported */
+	u8 alternate_base_address;	/* 0 = not supported, 1 = supported */
+	u8 pci_config_space;		/* Index/data access to working registers 0 = not supported, 1 = supported */
+	u8 pcix_speed_capability;	/* PCI-X */
+	u8 pcix_support;		/* PCI-X */
+	u16 vendor_id;
+	struct work_struct int_task_event;
+	wait_queue_head_t queue;	/* sleep & wake process */
+	struct dentry *dentry;		/* debugfs dentry */
+};
+
+struct irq_mapping {
+	u8 barber_pole;
+	u8 valid_INT;
+	u8 interrupt[4];
+};
+
+struct resource_lists {
+	struct pci_resource *mem_head;
+	struct pci_resource *p_mem_head;
+	struct pci_resource *io_head;
+	struct pci_resource *bus_head;
+	struct irq_mapping *irqs;
+};
+
+#define ROM_PHY_ADDR			0x0F0000
+#define ROM_PHY_LEN			0x00ffff
+
+#define PCI_HPC_ID			0xA0F7
+#define PCI_SUB_HPC_ID			0xA2F7
+#define PCI_SUB_HPC_ID2			0xA2F8
+#define PCI_SUB_HPC_ID3			0xA2F9
+#define PCI_SUB_HPC_ID_INTC		0xA2FA
+#define PCI_SUB_HPC_ID4			0xA2FD
+
+#define INT_BUTTON_IGNORE		0
+#define INT_PRESENCE_ON			1
+#define INT_PRESENCE_OFF		2
+#define INT_SWITCH_CLOSE		3
+#define INT_SWITCH_OPEN			4
+#define INT_POWER_FAULT			5
+#define INT_POWER_FAULT_CLEAR		6
+#define INT_BUTTON_PRESS		7
+#define INT_BUTTON_RELEASE		8
+#define INT_BUTTON_CANCEL		9
+
+#define STATIC_STATE			0
+#define BLINKINGON_STATE		1
+#define BLINKINGOFF_STATE		2
+#define POWERON_STATE			3
+#define POWEROFF_STATE			4
+
+#define PCISLOT_INTERLOCK_CLOSED	0x00000001
+#define PCISLOT_ADAPTER_PRESENT		0x00000002
+#define PCISLOT_POWERED			0x00000004
+#define PCISLOT_66_MHZ_OPERATION	0x00000008
+#define PCISLOT_64_BIT_OPERATION	0x00000010
+#define PCISLOT_REPLACE_SUPPORTED	0x00000020
+#define PCISLOT_ADD_SUPPORTED		0x00000040
+#define PCISLOT_INTERLOCK_SUPPORTED	0x00000080
+#define PCISLOT_66_MHZ_SUPPORTED	0x00000100
+#define PCISLOT_64_BIT_SUPPORTED	0x00000200
+
+#define PCI_TO_PCI_BRIDGE_CLASS		0x00060400
+
+#define INTERLOCK_OPEN			0x00000002
+#define ADD_NOT_SUPPORTED		0x00000003
+#define CARD_FUNCTIONING		0x00000005
+#define ADAPTER_NOT_SAME		0x00000006
+#define NO_ADAPTER_PRESENT		0x00000009
+#define NOT_ENOUGH_RESOURCES		0x0000000B
+#define DEVICE_TYPE_NOT_SUPPORTED	0x0000000C
+#define POWER_FAILURE			0x0000000E
+
+#define REMOVE_NOT_SUPPORTED		0x00000003
+
+
+/*
+ * error Messages
+ */
+#define msg_initialization_err	"Initialization failure, error=%d\n"
+#define msg_HPC_rev_error	"Unsupported revision of the PCI hot plug controller found.\n"
+#define msg_HPC_non_compaq_or_intel	"The PCI hot plug controller is not supported by this driver.\n"
+#define msg_HPC_not_supported	"this system is not supported by this version of cpqphpd. Upgrade to a newer version of cpqphpd\n"
+#define msg_unable_to_save	"unable to store PCI hot plug add resource information. This system must be rebooted before adding any PCI devices.\n"
+#define msg_button_on		"PCI slot #%d - powering on due to button press.\n"
+#define msg_button_off		"PCI slot #%d - powering off due to button press.\n"
+#define msg_button_cancel	"PCI slot #%d - action canceled due to button press.\n"
+#define msg_button_ignore	"PCI slot #%d - button press ignored.  (action in progress...)\n"
+
+
+/* debugfs functions for the hotplug controller info */
+extern void cpqhp_initialize_debugfs(void);
+extern void cpqhp_shutdown_debugfs(void);
+extern void cpqhp_create_debugfs_files(struct controller *ctrl);
+extern void cpqhp_remove_debugfs_files(struct controller *ctrl);
+
+/* controller functions */
+extern void cpqhp_pushbutton_thread(unsigned long event_pointer);
+extern irqreturn_t cpqhp_ctrl_intr(int IRQ, void *data);
+extern int cpqhp_find_available_resources(struct controller *ctrl,
+					  void __iomem *rom_start);
+extern int cpqhp_event_start_thread(void);
+extern void cpqhp_event_stop_thread(void);
+extern struct pci_func *cpqhp_slot_create(unsigned char busnumber);
+extern struct pci_func *cpqhp_slot_find(unsigned char bus, unsigned char device,
+					unsigned char index);
+extern int cpqhp_process_SI(struct controller *ctrl, struct pci_func *func);
+extern int cpqhp_process_SS(struct controller *ctrl, struct pci_func *func);
+extern int cpqhp_hardware_test(struct controller *ctrl, int test_num);
+
+/* resource functions */
+extern int	cpqhp_resource_sort_and_combine	(struct pci_resource **head);
+
+/* pci functions */
+extern int cpqhp_set_irq(u8 bus_num, u8 dev_num, u8 int_pin, u8 irq_num);
+extern int cpqhp_get_bus_dev(struct controller *ctrl, u8 *bus_num, u8 *dev_num,
+			     u8 slot);
+extern int cpqhp_save_config(struct controller *ctrl, int busnumber,
+			     int is_hot_plug);
+extern int cpqhp_save_base_addr_length(struct controller *ctrl,
+				       struct pci_func *func);
+extern int cpqhp_save_used_resources(struct controller *ctrl,
+				     struct pci_func *func);
+extern int cpqhp_configure_board(struct controller *ctrl,
+				 struct pci_func *func);
+extern int cpqhp_save_slot_config(struct controller *ctrl,
+				  struct pci_func *new_slot);
+extern int cpqhp_valid_replace(struct controller *ctrl, struct pci_func *func);
+extern void cpqhp_destroy_board_resources(struct pci_func *func);
+extern int cpqhp_return_board_resources	(struct pci_func *func,
+					 struct resource_lists *resources);
+extern void cpqhp_destroy_resource_list(struct resource_lists *resources);
+extern int cpqhp_configure_device(struct controller *ctrl,
+				  struct pci_func *func);
+extern int cpqhp_unconfigure_device(struct pci_func *func);
+
+/* Global variables */
+extern int cpqhp_debug;
+extern int cpqhp_legacy_mode;
+extern struct controller *cpqhp_ctrl_list;
+extern struct pci_func *cpqhp_slot_list[256];
+extern struct irq_routing_table *cpqhp_routing_table;
+
+/* these can be gotten rid of, but for debugging they are purty */
+extern u8 cpqhp_nic_irq;
+extern u8 cpqhp_disk_irq;
+
+
+/* inline functions */
+
+static inline const char *slot_name(struct slot *slot)
+{
+	return hotplug_slot_name(slot->hotplug_slot);
+}
+
+/*
+ * return_resource
+ *
+ * Puts node back in the resource list pointed to by head
+ */
+static inline void return_resource(struct pci_resource **head,
+				   struct pci_resource *node)
+{
+	if (!node || !head)
+		return;
+	node->next = *head;
+	*head = node;
+}
+
+static inline void set_SOGO(struct controller *ctrl)
+{
+	u16 misc;
+
+	misc = readw(ctrl->hpc_reg + MISC);
+	misc = (misc | 0x0001) & 0xFFFB;
+	writew(misc, ctrl->hpc_reg + MISC);
+}
+
+
+static inline void amber_LED_on(struct controller *ctrl, u8 slot)
+{
+	u32 led_control;
+
+	led_control = readl(ctrl->hpc_reg + LED_CONTROL);
+	led_control |= (0x01010000L << slot);
+	writel(led_control, ctrl->hpc_reg + LED_CONTROL);
+}
+
+
+static inline void amber_LED_off(struct controller *ctrl, u8 slot)
+{
+	u32 led_control;
+
+	led_control = readl(ctrl->hpc_reg + LED_CONTROL);
+	led_control &= ~(0x01010000L << slot);
+	writel(led_control, ctrl->hpc_reg + LED_CONTROL);
+}
+
+
+static inline int read_amber_LED(struct controller *ctrl, u8 slot)
+{
+	u32 led_control;
+
+	led_control = readl(ctrl->hpc_reg + LED_CONTROL);
+	led_control &= (0x01010000L << slot);
+
+	return led_control ? 1 : 0;
+}
+
+
+static inline void green_LED_on(struct controller *ctrl, u8 slot)
+{
+	u32 led_control;
+
+	led_control = readl(ctrl->hpc_reg + LED_CONTROL);
+	led_control |= 0x0101L << slot;
+	writel(led_control, ctrl->hpc_reg + LED_CONTROL);
+}
+
+static inline void green_LED_off(struct controller *ctrl, u8 slot)
+{
+	u32 led_control;
+
+	led_control = readl(ctrl->hpc_reg + LED_CONTROL);
+	led_control &= ~(0x0101L << slot);
+	writel(led_control, ctrl->hpc_reg + LED_CONTROL);
+}
+
+
+static inline void green_LED_blink(struct controller *ctrl, u8 slot)
+{
+	u32 led_control;
+
+	led_control = readl(ctrl->hpc_reg + LED_CONTROL);
+	led_control &= ~(0x0101L << slot);
+	led_control |= (0x0001L << slot);
+	writel(led_control, ctrl->hpc_reg + LED_CONTROL);
+}
+
+
+static inline void slot_disable(struct controller *ctrl, u8 slot)
+{
+	u8 slot_enable;
+
+	slot_enable = readb(ctrl->hpc_reg + SLOT_ENABLE);
+	slot_enable &= ~(0x01 << slot);
+	writeb(slot_enable, ctrl->hpc_reg + SLOT_ENABLE);
+}
+
+
+static inline void slot_enable(struct controller *ctrl, u8 slot)
+{
+	u8 slot_enable;
+
+	slot_enable = readb(ctrl->hpc_reg + SLOT_ENABLE);
+	slot_enable |= (0x01 << slot);
+	writeb(slot_enable, ctrl->hpc_reg + SLOT_ENABLE);
+}
+
+
+static inline u8 is_slot_enabled(struct controller *ctrl, u8 slot)
+{
+	u8 slot_enable;
+
+	slot_enable = readb(ctrl->hpc_reg + SLOT_ENABLE);
+	slot_enable &= (0x01 << slot);
+	return slot_enable ? 1 : 0;
+}
+
+
+static inline u8 read_slot_enable(struct controller *ctrl)
+{
+	return readb(ctrl->hpc_reg + SLOT_ENABLE);
+}
+
+
+/**
+ * get_controller_speed - find the current frequency/mode of controller.
+ *
+ * @ctrl: controller to get frequency/mode for.
+ *
+ * Returns controller speed.
+ */
+static inline u8 get_controller_speed(struct controller *ctrl)
+{
+	u8 curr_freq;
+	u16 misc;
+
+	if (ctrl->pcix_support) {
+		curr_freq = readb(ctrl->hpc_reg + NEXT_CURR_FREQ);
+		if ((curr_freq & 0xB0) == 0xB0)
+			return PCI_SPEED_133MHz_PCIX;
+		if ((curr_freq & 0xA0) == 0xA0)
+			return PCI_SPEED_100MHz_PCIX;
+		if ((curr_freq & 0x90) == 0x90)
+			return PCI_SPEED_66MHz_PCIX;
+		if (curr_freq & 0x10)
+			return PCI_SPEED_66MHz;
+
+		return PCI_SPEED_33MHz;
+	}
+
+	misc = readw(ctrl->hpc_reg + MISC);
+	return (misc & 0x0800) ? PCI_SPEED_66MHz : PCI_SPEED_33MHz;
+}
+
+
+/**
+ * get_adapter_speed - find the max supported frequency/mode of adapter.
+ *
+ * @ctrl: hotplug controller.
+ * @hp_slot: hotplug slot where adapter is installed.
+ *
+ * Returns adapter speed.
+ */
+static inline u8 get_adapter_speed(struct controller *ctrl, u8 hp_slot)
+{
+	u32 temp_dword = readl(ctrl->hpc_reg + NON_INT_INPUT);
+	dbg("slot: %d, PCIXCAP: %8x\n", hp_slot, temp_dword);
+	if (ctrl->pcix_support) {
+		if (temp_dword & (0x10000 << hp_slot))
+			return PCI_SPEED_133MHz_PCIX;
+		if (temp_dword & (0x100 << hp_slot))
+			return PCI_SPEED_66MHz_PCIX;
+	}
+
+	if (temp_dword & (0x01 << hp_slot))
+		return PCI_SPEED_66MHz;
+
+	return PCI_SPEED_33MHz;
+}
+
+static inline void enable_slot_power(struct controller *ctrl, u8 slot)
+{
+	u8 slot_power;
+
+	slot_power = readb(ctrl->hpc_reg + SLOT_POWER);
+	slot_power |= (0x01 << slot);
+	writeb(slot_power, ctrl->hpc_reg + SLOT_POWER);
+}
+
+static inline void disable_slot_power(struct controller *ctrl, u8 slot)
+{
+	u8 slot_power;
+
+	slot_power = readb(ctrl->hpc_reg + SLOT_POWER);
+	slot_power &= ~(0x01 << slot);
+	writeb(slot_power, ctrl->hpc_reg + SLOT_POWER);
+}
+
+
+static inline int cpq_get_attention_status(struct controller *ctrl, struct slot *slot)
+{
+	u8 hp_slot;
+
+	hp_slot = slot->device - ctrl->slot_device_offset;
+
+	return read_amber_LED(ctrl, hp_slot);
+}
+
+
+static inline int get_slot_enabled(struct controller *ctrl, struct slot *slot)
+{
+	u8 hp_slot;
+
+	hp_slot = slot->device - ctrl->slot_device_offset;
+
+	return is_slot_enabled(ctrl, hp_slot);
+}
+
+
+static inline int cpq_get_latch_status(struct controller *ctrl,
+				       struct slot *slot)
+{
+	u32 status;
+	u8 hp_slot;
+
+	hp_slot = slot->device - ctrl->slot_device_offset;
+	dbg("%s: slot->device = %d, ctrl->slot_device_offset = %d \n",
+	    __func__, slot->device, ctrl->slot_device_offset);
+
+	status = (readl(ctrl->hpc_reg + INT_INPUT_CLEAR) & (0x01L << hp_slot));
+
+	return(status == 0) ? 1 : 0;
+}
+
+
+static inline int get_presence_status(struct controller *ctrl,
+				      struct slot *slot)
+{
+	int presence_save = 0;
+	u8 hp_slot;
+	u32 tempdword;
+
+	hp_slot = slot->device - ctrl->slot_device_offset;
+
+	tempdword = readl(ctrl->hpc_reg + INT_INPUT_CLEAR);
+	presence_save = (int) ((((~tempdword) >> 23) | ((~tempdword) >> 15))
+				>> hp_slot) & 0x02;
+
+	return presence_save;
+}
+
+static inline int wait_for_ctrl_irq(struct controller *ctrl)
+{
+        DECLARE_WAITQUEUE(wait, current);
+	int retval = 0;
+
+	dbg("%s - start\n", __func__);
+	add_wait_queue(&ctrl->queue, &wait);
+	/* Sleep for up to 1 second to wait for the LED to change. */
+	msleep_interruptible(1000);
+	remove_wait_queue(&ctrl->queue, &wait);
+	if (signal_pending(current))
+		retval =  -EINTR;
+
+	dbg("%s - end\n", __func__);
+	return retval;
+}
+
+#include <asm/pci_x86.h>
+static inline int cpqhp_routing_table_length(void)
+{
+	BUG_ON(cpqhp_routing_table == NULL);
+	return ((cpqhp_routing_table->size - sizeof(struct irq_routing_table)) /
+		sizeof(struct irq_info));
+}
+
+#endif
diff --git a/drivers/pci/hotplug/cpqphp_core.c b/drivers/pci/hotplug/cpqphp_core.c
new file mode 100644
index 00000000..4952c3b9
--- /dev/null
+++ b/drivers/pci/hotplug/cpqphp_core.c
@@ -0,0 +1,1471 @@
+/*
+ * Compaq Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman <greg@kroah.com>
+ * Copyright (C) 2001 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>
+ *
+ * Jan 12, 2003 -	Added 66/100/133MHz PCI-X support,
+ *			Torben Mathiasen <torben.mathiasen@hp.com>
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/proc_fs.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+
+#include <asm/uaccess.h>
+
+#include "cpqphp.h"
+#include "cpqphp_nvram.h"
+
+
+/* Global variables */
+int cpqhp_debug;
+int cpqhp_legacy_mode;
+struct controller *cpqhp_ctrl_list;	/* = NULL */
+struct pci_func *cpqhp_slot_list[256];
+struct irq_routing_table *cpqhp_routing_table;
+
+/* local variables */
+static void __iomem *smbios_table;
+static void __iomem *smbios_start;
+static void __iomem *cpqhp_rom_start;
+static int power_mode;
+static int debug;
+static int initialized;
+
+#define DRIVER_VERSION	"0.9.8"
+#define DRIVER_AUTHOR	"Dan Zink <dan.zink@compaq.com>, Greg Kroah-Hartman <greg@kroah.com>"
+#define DRIVER_DESC	"Compaq Hot Plug PCI Controller Driver"
+
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+
+module_param(power_mode, bool, 0644);
+MODULE_PARM_DESC(power_mode, "Power mode enabled or not");
+
+module_param(debug, bool, 0644);
+MODULE_PARM_DESC(debug, "Debugging mode enabled or not");
+
+#define CPQHPC_MODULE_MINOR 208
+
+static inline int is_slot64bit(struct slot *slot)
+{
+	return (readb(slot->p_sm_slot + SMBIOS_SLOT_WIDTH) == 0x06) ? 1 : 0;
+}
+
+static inline int is_slot66mhz(struct slot *slot)
+{
+	return (readb(slot->p_sm_slot + SMBIOS_SLOT_TYPE) == 0x0E) ? 1 : 0;
+}
+
+/**
+ * detect_SMBIOS_pointer - find the System Management BIOS Table in mem region.
+ * @begin: begin pointer for region to be scanned.
+ * @end: end pointer for region to be scanned.
+ *
+ * Returns pointer to the head of the SMBIOS tables (or %NULL).
+ */
+static void __iomem * detect_SMBIOS_pointer(void __iomem *begin, void __iomem *end)
+{
+	void __iomem *fp;
+	void __iomem *endp;
+	u8 temp1, temp2, temp3, temp4;
+	int status = 0;
+
+	endp = (end - sizeof(u32) + 1);
+
+	for (fp = begin; fp <= endp; fp += 16) {
+		temp1 = readb(fp);
+		temp2 = readb(fp+1);
+		temp3 = readb(fp+2);
+		temp4 = readb(fp+3);
+		if (temp1 == '_' &&
+		    temp2 == 'S' &&
+		    temp3 == 'M' &&
+		    temp4 == '_') {
+			status = 1;
+			break;
+		}
+	}
+
+	if (!status)
+		fp = NULL;
+
+	dbg("Discovered SMBIOS Entry point at %p\n", fp);
+
+	return fp;
+}
+
+/**
+ * init_SERR - Initializes the per slot SERR generation.
+ * @ctrl: controller to use
+ *
+ * For unexpected switch opens
+ */
+static int init_SERR(struct controller * ctrl)
+{
+	u32 tempdword;
+	u32 number_of_slots;
+	u8 physical_slot;
+
+	if (!ctrl)
+		return 1;
+
+	tempdword = ctrl->first_slot;
+
+	number_of_slots = readb(ctrl->hpc_reg + SLOT_MASK) & 0x0F;
+	/* Loop through slots */
+	while (number_of_slots) {
+		physical_slot = tempdword;
+		writeb(0, ctrl->hpc_reg + SLOT_SERR);
+		tempdword++;
+		number_of_slots--;
+	}
+
+	return 0;
+}
+
+static int init_cpqhp_routing_table(void)
+{
+	int len;
+
+	cpqhp_routing_table = pcibios_get_irq_routing_table();
+	if (cpqhp_routing_table == NULL)
+		return -ENOMEM;
+
+	len = cpqhp_routing_table_length();
+	if (len == 0) {
+		kfree(cpqhp_routing_table);
+		cpqhp_routing_table = NULL;
+		return -1;
+	}
+
+	return 0;
+}
+
+/* nice debugging output */
+static void pci_print_IRQ_route(void)
+{
+	int len;
+	int loop;
+	u8 tbus, tdevice, tslot;
+
+	len = cpqhp_routing_table_length();
+
+	dbg("bus dev func slot\n");
+	for (loop = 0; loop < len; ++loop) {
+		tbus = cpqhp_routing_table->slots[loop].bus;
+		tdevice = cpqhp_routing_table->slots[loop].devfn;
+		tslot = cpqhp_routing_table->slots[loop].slot;
+		dbg("%d %d %d %d\n", tbus, tdevice >> 3, tdevice & 0x7, tslot);
+
+	}
+	return;
+}
+
+
+/**
+ * get_subsequent_smbios_entry: get the next entry from bios table.
+ * @smbios_start: where to start in the SMBIOS table
+ * @smbios_table: location of the SMBIOS table
+ * @curr: %NULL or pointer to previously returned structure
+ *
+ * Gets the first entry if previous == NULL;
+ * otherwise, returns the next entry.
+ * Uses global SMBIOS Table pointer.
+ *
+ * Returns a pointer to an SMBIOS structure or NULL if none found.
+ */
+static void __iomem *get_subsequent_smbios_entry(void __iomem *smbios_start,
+						void __iomem *smbios_table,
+						void __iomem *curr)
+{
+	u8 bail = 0;
+	u8 previous_byte = 1;
+	void __iomem *p_temp;
+	void __iomem *p_max;
+
+	if (!smbios_table || !curr)
+		return NULL;
+
+	/* set p_max to the end of the table */
+	p_max = smbios_start + readw(smbios_table + ST_LENGTH);
+
+	p_temp = curr;
+	p_temp += readb(curr + SMBIOS_GENERIC_LENGTH);
+
+	while ((p_temp < p_max) && !bail) {
+		/* Look for the double NULL terminator
+		 * The first condition is the previous byte
+		 * and the second is the curr
+		 */
+		if (!previous_byte && !(readb(p_temp)))
+			bail = 1;
+
+		previous_byte = readb(p_temp);
+		p_temp++;
+	}
+
+	if (p_temp < p_max)
+		return p_temp;
+	else
+		return NULL;
+}
+
+
+/**
+ * get_SMBIOS_entry - return the requested SMBIOS entry or %NULL
+ * @smbios_start: where to start in the SMBIOS table
+ * @smbios_table: location of the SMBIOS table
+ * @type: SMBIOS structure type to be returned
+ * @previous: %NULL or pointer to previously returned structure
+ *
+ * Gets the first entry of the specified type if previous == %NULL;
+ * Otherwise, returns the next entry of the given type.
+ * Uses global SMBIOS Table pointer.
+ * Uses get_subsequent_smbios_entry.
+ *
+ * Returns a pointer to an SMBIOS structure or %NULL if none found.
+ */
+static void __iomem *get_SMBIOS_entry(void __iomem *smbios_start,
+					void __iomem *smbios_table,
+					u8 type,
+					void __iomem *previous)
+{
+	if (!smbios_table)
+		return NULL;
+
+	if (!previous)
+		previous = smbios_start;
+	else
+		previous = get_subsequent_smbios_entry(smbios_start,
+					smbios_table, previous);
+
+	while (previous)
+		if (readb(previous + SMBIOS_GENERIC_TYPE) != type)
+			previous = get_subsequent_smbios_entry(smbios_start,
+						smbios_table, previous);
+		else
+			break;
+
+	return previous;
+}
+
+static void release_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
+
+	kfree(slot->hotplug_slot->info);
+	kfree(slot->hotplug_slot);
+	kfree(slot);
+}
+
+static int ctrl_slot_cleanup (struct controller * ctrl)
+{
+	struct slot *old_slot, *next_slot;
+
+	old_slot = ctrl->slot;
+	ctrl->slot = NULL;
+
+	while (old_slot) {
+		/* memory will be freed by the release_slot callback */
+		next_slot = old_slot->next;
+		pci_hp_deregister (old_slot->hotplug_slot);
+		old_slot = next_slot;
+	}
+
+	cpqhp_remove_debugfs_files(ctrl);
+
+	/* Free IRQ associated with hot plug device */
+	free_irq(ctrl->interrupt, ctrl);
+	/* Unmap the memory */
+	iounmap(ctrl->hpc_reg);
+	/* Finally reclaim PCI mem */
+	release_mem_region(pci_resource_start(ctrl->pci_dev, 0),
+			   pci_resource_len(ctrl->pci_dev, 0));
+
+	return 0;
+}
+
+
+/**
+ * get_slot_mapping - determine logical slot mapping for PCI device
+ *
+ * Won't work for more than one PCI-PCI bridge in a slot.
+ *
+ * @bus_num - bus number of PCI device
+ * @dev_num - device number of PCI device
+ * @slot - Pointer to u8 where slot number will	be returned
+ *
+ * Output:	SUCCESS or FAILURE
+ */
+static int
+get_slot_mapping(struct pci_bus *bus, u8 bus_num, u8 dev_num, u8 *slot)
+{
+	u32 work;
+	long len;
+	long loop;
+
+	u8 tbus, tdevice, tslot, bridgeSlot;
+
+	dbg("%s: %p, %d, %d, %p\n", __func__, bus, bus_num, dev_num, slot);
+
+	bridgeSlot = 0xFF;
+
+	len = cpqhp_routing_table_length();
+	for (loop = 0; loop < len; ++loop) {
+		tbus = cpqhp_routing_table->slots[loop].bus;
+		tdevice = cpqhp_routing_table->slots[loop].devfn >> 3;
+		tslot = cpqhp_routing_table->slots[loop].slot;
+
+		if ((tbus == bus_num) && (tdevice == dev_num)) {
+			*slot = tslot;
+			return 0;
+		} else {
+			/* Did not get a match on the target PCI device. Check
+			 * if the current IRQ table entry is a PCI-to-PCI
+			 * bridge device.  If so, and it's secondary bus
+			 * matches the bus number for the target device, I need
+			 * to save the bridge's slot number.  If I can not find
+			 * an entry for the target device, I will have to
+			 * assume it's on the other side of the bridge, and
+			 * assign it the bridge's slot.
+			 */
+			bus->number = tbus;
+			pci_bus_read_config_dword(bus, PCI_DEVFN(tdevice, 0),
+						PCI_CLASS_REVISION, &work);
+
+			if ((work >> 8) == PCI_TO_PCI_BRIDGE_CLASS) {
+				pci_bus_read_config_dword(bus,
+							PCI_DEVFN(tdevice, 0),
+							PCI_PRIMARY_BUS, &work);
+				// See if bridge's secondary bus matches target bus.
+				if (((work >> 8) & 0x000000FF) == (long) bus_num)
+					bridgeSlot = tslot;
+			}
+		}
+
+	}
+
+	/* If we got here, we didn't find an entry in the IRQ mapping table for
+	 * the target PCI device.  If we did determine that the target device
+	 * is on the other side of a PCI-to-PCI bridge, return the slot number
+	 * for the bridge.
+	 */
+	if (bridgeSlot != 0xFF) {
+		*slot = bridgeSlot;
+		return 0;
+	}
+	/* Couldn't find an entry in the routing table for this PCI device */
+	return -1;
+}
+
+
+/**
+ * cpqhp_set_attention_status - Turns the Amber LED for a slot on or off
+ * @ctrl: struct controller to use
+ * @func: PCI device/function info
+ * @status: LED control flag: 1 = LED on, 0 = LED off
+ */
+static int
+cpqhp_set_attention_status(struct controller *ctrl, struct pci_func *func,
+				u32 status)
+{
+	u8 hp_slot;
+
+	if (func == NULL)
+		return 1;
+
+	hp_slot = func->device - ctrl->slot_device_offset;
+
+	/* Wait for exclusive access to hardware */
+	mutex_lock(&ctrl->crit_sect);
+
+	if (status == 1)
+		amber_LED_on (ctrl, hp_slot);
+	else if (status == 0)
+		amber_LED_off (ctrl, hp_slot);
+	else {
+		/* Done with exclusive hardware access */
+		mutex_unlock(&ctrl->crit_sect);
+		return 1;
+	}
+
+	set_SOGO(ctrl);
+
+	/* Wait for SOBS to be unset */
+	wait_for_ctrl_irq (ctrl);
+
+	/* Done with exclusive hardware access */
+	mutex_unlock(&ctrl->crit_sect);
+
+	return 0;
+}
+
+
+/**
+ * set_attention_status - Turns the Amber LED for a slot on or off
+ * @hotplug_slot: slot to change LED on
+ * @status: LED control flag
+ */
+static int set_attention_status (struct hotplug_slot *hotplug_slot, u8 status)
+{
+	struct pci_func *slot_func;
+	struct slot *slot = hotplug_slot->private;
+	struct controller *ctrl = slot->ctrl;
+	u8 bus;
+	u8 devfn;
+	u8 device;
+	u8 function;
+
+	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
+
+	if (cpqhp_get_bus_dev(ctrl, &bus, &devfn, slot->number) == -1)
+		return -ENODEV;
+
+	device = devfn >> 3;
+	function = devfn & 0x7;
+	dbg("bus, dev, fn = %d, %d, %d\n", bus, device, function);
+
+	slot_func = cpqhp_slot_find(bus, device, function);
+	if (!slot_func)
+		return -ENODEV;
+
+	return cpqhp_set_attention_status(ctrl, slot_func, status);
+}
+
+
+static int process_SI(struct hotplug_slot *hotplug_slot)
+{
+	struct pci_func *slot_func;
+	struct slot *slot = hotplug_slot->private;
+	struct controller *ctrl = slot->ctrl;
+	u8 bus;
+	u8 devfn;
+	u8 device;
+	u8 function;
+
+	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
+
+	if (cpqhp_get_bus_dev(ctrl, &bus, &devfn, slot->number) == -1)
+		return -ENODEV;
+
+	device = devfn >> 3;
+	function = devfn & 0x7;
+	dbg("bus, dev, fn = %d, %d, %d\n", bus, device, function);
+
+	slot_func = cpqhp_slot_find(bus, device, function);
+	if (!slot_func)
+		return -ENODEV;
+
+	slot_func->bus = bus;
+	slot_func->device = device;
+	slot_func->function = function;
+	slot_func->configured = 0;
+	dbg("board_added(%p, %p)\n", slot_func, ctrl);
+	return cpqhp_process_SI(ctrl, slot_func);
+}
+
+
+static int process_SS(struct hotplug_slot *hotplug_slot)
+{
+	struct pci_func *slot_func;
+	struct slot *slot = hotplug_slot->private;
+	struct controller *ctrl = slot->ctrl;
+	u8 bus;
+	u8 devfn;
+	u8 device;
+	u8 function;
+
+	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
+
+	if (cpqhp_get_bus_dev(ctrl, &bus, &devfn, slot->number) == -1)
+		return -ENODEV;
+
+	device = devfn >> 3;
+	function = devfn & 0x7;
+	dbg("bus, dev, fn = %d, %d, %d\n", bus, device, function);
+
+	slot_func = cpqhp_slot_find(bus, device, function);
+	if (!slot_func)
+		return -ENODEV;
+
+	dbg("In %s, slot_func = %p, ctrl = %p\n", __func__, slot_func, ctrl);
+	return cpqhp_process_SS(ctrl, slot_func);
+}
+
+
+static int hardware_test(struct hotplug_slot *hotplug_slot, u32 value)
+{
+	struct slot *slot = hotplug_slot->private;
+	struct controller *ctrl = slot->ctrl;
+
+	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
+
+	return cpqhp_hardware_test(ctrl, value);
+}
+
+
+static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = hotplug_slot->private;
+	struct controller *ctrl = slot->ctrl;
+
+	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
+
+	*value = get_slot_enabled(ctrl, slot);
+	return 0;
+}
+
+static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = hotplug_slot->private;
+	struct controller *ctrl = slot->ctrl;
+
+	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
+
+	*value = cpq_get_attention_status(ctrl, slot);
+	return 0;
+}
+
+static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = hotplug_slot->private;
+	struct controller *ctrl = slot->ctrl;
+
+	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
+
+	*value = cpq_get_latch_status(ctrl, slot);
+
+	return 0;
+}
+
+static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = hotplug_slot->private;
+	struct controller *ctrl = slot->ctrl;
+
+	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
+
+	*value = get_presence_status(ctrl, slot);
+
+	return 0;
+}
+
+static struct hotplug_slot_ops cpqphp_hotplug_slot_ops = {
+	.set_attention_status =	set_attention_status,
+	.enable_slot =		process_SI,
+	.disable_slot =		process_SS,
+	.hardware_test =	hardware_test,
+	.get_power_status =	get_power_status,
+	.get_attention_status =	get_attention_status,
+	.get_latch_status =	get_latch_status,
+	.get_adapter_status =	get_adapter_status,
+};
+
+#define SLOT_NAME_SIZE 10
+
+static int ctrl_slot_setup(struct controller *ctrl,
+			void __iomem *smbios_start,
+			void __iomem *smbios_table)
+{
+	struct slot *slot;
+	struct hotplug_slot *hotplug_slot;
+	struct hotplug_slot_info *hotplug_slot_info;
+	struct pci_bus *bus = ctrl->pci_bus;
+	u8 number_of_slots;
+	u8 slot_device;
+	u8 slot_number;
+	u8 ctrl_slot;
+	u32 tempdword;
+	char name[SLOT_NAME_SIZE];
+	void __iomem *slot_entry= NULL;
+	int result = -ENOMEM;
+
+	dbg("%s\n", __func__);
+
+	tempdword = readl(ctrl->hpc_reg + INT_INPUT_CLEAR);
+
+	number_of_slots = readb(ctrl->hpc_reg + SLOT_MASK) & 0x0F;
+	slot_device = readb(ctrl->hpc_reg + SLOT_MASK) >> 4;
+	slot_number = ctrl->first_slot;
+
+	while (number_of_slots) {
+		slot = kzalloc(sizeof(*slot), GFP_KERNEL);
+		if (!slot)
+			goto error;
+
+		slot->hotplug_slot = kzalloc(sizeof(*(slot->hotplug_slot)),
+						GFP_KERNEL);
+		if (!slot->hotplug_slot)
+			goto error_slot;
+		hotplug_slot = slot->hotplug_slot;
+
+		hotplug_slot->info = kzalloc(sizeof(*(hotplug_slot->info)),
+							GFP_KERNEL);
+		if (!hotplug_slot->info)
+			goto error_hpslot;
+		hotplug_slot_info = hotplug_slot->info;
+
+		slot->ctrl = ctrl;
+		slot->bus = ctrl->bus;
+		slot->device = slot_device;
+		slot->number = slot_number;
+		dbg("slot->number = %u\n", slot->number);
+
+		slot_entry = get_SMBIOS_entry(smbios_start, smbios_table, 9,
+					slot_entry);
+
+		while (slot_entry && (readw(slot_entry + SMBIOS_SLOT_NUMBER) !=
+				slot->number)) {
+			slot_entry = get_SMBIOS_entry(smbios_start,
+						smbios_table, 9, slot_entry);
+		}
+
+		slot->p_sm_slot = slot_entry;
+
+		init_timer(&slot->task_event);
+		slot->task_event.expires = jiffies + 5 * HZ;
+		slot->task_event.function = cpqhp_pushbutton_thread;
+
+		/*FIXME: these capabilities aren't used but if they are
+		 *	 they need to be correctly implemented
+		 */
+		slot->capabilities |= PCISLOT_REPLACE_SUPPORTED;
+		slot->capabilities |= PCISLOT_INTERLOCK_SUPPORTED;
+
+		if (is_slot64bit(slot))
+			slot->capabilities |= PCISLOT_64_BIT_SUPPORTED;
+		if (is_slot66mhz(slot))
+			slot->capabilities |= PCISLOT_66_MHZ_SUPPORTED;
+		if (bus->cur_bus_speed == PCI_SPEED_66MHz)
+			slot->capabilities |= PCISLOT_66_MHZ_OPERATION;
+
+		ctrl_slot =
+			slot_device - (readb(ctrl->hpc_reg + SLOT_MASK) >> 4);
+
+		/* Check presence */
+		slot->capabilities |=
+			((((~tempdword) >> 23) |
+			 ((~tempdword) >> 15)) >> ctrl_slot) & 0x02;
+		/* Check the switch state */
+		slot->capabilities |=
+			((~tempdword & 0xFF) >> ctrl_slot) & 0x01;
+		/* Check the slot enable */
+		slot->capabilities |=
+			((read_slot_enable(ctrl) << 2) >> ctrl_slot) & 0x04;
+
+		/* register this slot with the hotplug pci core */
+		hotplug_slot->release = &release_slot;
+		hotplug_slot->private = slot;
+		snprintf(name, SLOT_NAME_SIZE, "%u", slot->number);
+		hotplug_slot->ops = &cpqphp_hotplug_slot_ops;
+
+		hotplug_slot_info->power_status = get_slot_enabled(ctrl, slot);
+		hotplug_slot_info->attention_status =
+			cpq_get_attention_status(ctrl, slot);
+		hotplug_slot_info->latch_status =
+			cpq_get_latch_status(ctrl, slot);
+		hotplug_slot_info->adapter_status =
+			get_presence_status(ctrl, slot);
+
+		dbg("registering bus %d, dev %d, number %d, "
+				"ctrl->slot_device_offset %d, slot %d\n",
+				slot->bus, slot->device,
+				slot->number, ctrl->slot_device_offset,
+				slot_number);
+		result = pci_hp_register(hotplug_slot,
+					 ctrl->pci_dev->bus,
+					 slot->device,
+					 name);
+		if (result) {
+			err("pci_hp_register failed with error %d\n", result);
+			goto error_info;
+		}
+
+		slot->next = ctrl->slot;
+		ctrl->slot = slot;
+
+		number_of_slots--;
+		slot_device++;
+		slot_number++;
+	}
+
+	return 0;
+error_info:
+	kfree(hotplug_slot_info);
+error_hpslot:
+	kfree(hotplug_slot);
+error_slot:
+	kfree(slot);
+error:
+	return result;
+}
+
+static int one_time_init(void)
+{
+	int loop;
+	int retval = 0;
+
+	if (initialized)
+		return 0;
+
+	power_mode = 0;
+
+	retval = init_cpqhp_routing_table();
+	if (retval)
+		goto error;
+
+	if (cpqhp_debug)
+		pci_print_IRQ_route();
+
+	dbg("Initialize + Start the notification mechanism \n");
+
+	retval = cpqhp_event_start_thread();
+	if (retval)
+		goto error;
+
+	dbg("Initialize slot lists\n");
+	for (loop = 0; loop < 256; loop++)
+		cpqhp_slot_list[loop] = NULL;
+
+	/* FIXME: We also need to hook the NMI handler eventually.
+	 * this also needs to be worked with Christoph
+	 * register_NMI_handler();
+	 */
+	/* Map rom address */
+	cpqhp_rom_start = ioremap(ROM_PHY_ADDR, ROM_PHY_LEN);
+	if (!cpqhp_rom_start) {
+		err ("Could not ioremap memory region for ROM\n");
+		retval = -EIO;
+		goto error;
+	}
+
+	/* Now, map the int15 entry point if we are on compaq specific
+	 * hardware
+	 */
+	compaq_nvram_init(cpqhp_rom_start);
+
+	/* Map smbios table entry point structure */
+	smbios_table = detect_SMBIOS_pointer(cpqhp_rom_start,
+					cpqhp_rom_start + ROM_PHY_LEN);
+	if (!smbios_table) {
+		err ("Could not find the SMBIOS pointer in memory\n");
+		retval = -EIO;
+		goto error_rom_start;
+	}
+
+	smbios_start = ioremap(readl(smbios_table + ST_ADDRESS),
+					readw(smbios_table + ST_LENGTH));
+	if (!smbios_start) {
+		err ("Could not ioremap memory region taken from SMBIOS values\n");
+		retval = -EIO;
+		goto error_smbios_start;
+	}
+
+	initialized = 1;
+
+	return retval;
+
+error_smbios_start:
+	iounmap(smbios_start);
+error_rom_start:
+	iounmap(cpqhp_rom_start);
+error:
+	return retval;
+}
+
+static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	u8 num_of_slots = 0;
+	u8 hp_slot = 0;
+	u8 device;
+	u8 bus_cap;
+	u16 temp_word;
+	u16 vendor_id;
+	u16 subsystem_vid;
+	u16 subsystem_deviceid;
+	u32 rc;
+	struct controller *ctrl;
+	struct pci_func *func;
+	struct pci_bus *bus;
+	int err;
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		printk(KERN_ERR MY_NAME ": cannot enable PCI device %s (%d)\n",
+			pci_name(pdev), err);
+		return err;
+	}
+
+	bus = pdev->subordinate;
+	if (!bus) {
+		dev_notice(&pdev->dev, "the device is not a bridge, "
+				"skipping\n");
+		rc = -ENODEV;
+		goto err_disable_device;
+	}
+
+	/* Need to read VID early b/c it's used to differentiate CPQ and INTC
+	 * discovery
+	 */
+	rc = pci_read_config_word(pdev, PCI_VENDOR_ID, &vendor_id);
+	if (rc || ((vendor_id != PCI_VENDOR_ID_COMPAQ) && (vendor_id != PCI_VENDOR_ID_INTEL))) {
+		err(msg_HPC_non_compaq_or_intel);
+		rc = -ENODEV;
+		goto err_disable_device;
+	}
+	dbg("Vendor ID: %x\n", vendor_id);
+
+	dbg("revision: %d\n", pdev->revision);
+	if ((vendor_id == PCI_VENDOR_ID_COMPAQ) && (!pdev->revision)) {
+		err(msg_HPC_rev_error);
+		rc = -ENODEV;
+		goto err_disable_device;
+	}
+
+	/* Check for the proper subsystem ID's
+	 * Intel uses a different SSID programming model than Compaq.
+	 * For Intel, each SSID bit identifies a PHP capability.
+	 * Also Intel HPC's may have RID=0.
+	 */
+	if ((pdev->revision <= 2) && (vendor_id != PCI_VENDOR_ID_INTEL)) {
+		err(msg_HPC_not_supported);
+		return -ENODEV;
+	}
+
+	/* TODO: This code can be made to support non-Compaq or Intel
+	 * subsystem IDs
+	 */
+	rc = pci_read_config_word(pdev, PCI_SUBSYSTEM_VENDOR_ID, &subsystem_vid);
+	if (rc) {
+		err("%s : pci_read_config_word failed\n", __func__);
+		goto err_disable_device;
+	}
+	dbg("Subsystem Vendor ID: %x\n", subsystem_vid);
+	if ((subsystem_vid != PCI_VENDOR_ID_COMPAQ) && (subsystem_vid != PCI_VENDOR_ID_INTEL)) {
+		err(msg_HPC_non_compaq_or_intel);
+		rc = -ENODEV;
+		goto err_disable_device;
+	}
+
+	ctrl = kzalloc(sizeof(struct controller), GFP_KERNEL);
+	if (!ctrl) {
+		err("%s : out of memory\n", __func__);
+		rc = -ENOMEM;
+		goto err_disable_device;
+	}
+
+	rc = pci_read_config_word(pdev, PCI_SUBSYSTEM_ID, &subsystem_deviceid);
+	if (rc) {
+		err("%s : pci_read_config_word failed\n", __func__);
+		goto err_free_ctrl;
+	}
+
+	info("Hot Plug Subsystem Device ID: %x\n", subsystem_deviceid);
+
+	/* Set Vendor ID, so it can be accessed later from other
+	 * functions
+	 */
+	ctrl->vendor_id = vendor_id;
+
+	switch (subsystem_vid) {
+	case PCI_VENDOR_ID_COMPAQ:
+		if (pdev->revision >= 0x13) { /* CIOBX */
+			ctrl->push_flag = 1;
+			ctrl->slot_switch_type = 1;
+			ctrl->push_button = 1;
+			ctrl->pci_config_space = 1;
+			ctrl->defeature_PHP = 1;
+			ctrl->pcix_support = 1;
+			ctrl->pcix_speed_capability = 1;
+			pci_read_config_byte(pdev, 0x41, &bus_cap);
+			if (bus_cap & 0x80) {
+				dbg("bus max supports 133MHz PCI-X\n");
+				bus->max_bus_speed = PCI_SPEED_133MHz_PCIX;
+				break;
+			}
+			if (bus_cap & 0x40) {
+				dbg("bus max supports 100MHz PCI-X\n");
+				bus->max_bus_speed = PCI_SPEED_100MHz_PCIX;
+				break;
+			}
+			if (bus_cap & 20) {
+				dbg("bus max supports 66MHz PCI-X\n");
+				bus->max_bus_speed = PCI_SPEED_66MHz_PCIX;
+				break;
+			}
+			if (bus_cap & 10) {
+				dbg("bus max supports 66MHz PCI\n");
+				bus->max_bus_speed = PCI_SPEED_66MHz;
+				break;
+			}
+
+			break;
+		}
+
+		switch (subsystem_deviceid) {
+		case PCI_SUB_HPC_ID:
+			/* Original 6500/7000 implementation */
+			ctrl->slot_switch_type = 1;
+			bus->max_bus_speed = PCI_SPEED_33MHz;
+			ctrl->push_button = 0;
+			ctrl->pci_config_space = 1;
+			ctrl->defeature_PHP = 1;
+			ctrl->pcix_support = 0;
+			ctrl->pcix_speed_capability = 0;
+			break;
+		case PCI_SUB_HPC_ID2:
+			/* First Pushbutton implementation */
+			ctrl->push_flag = 1;
+			ctrl->slot_switch_type = 1;
+			bus->max_bus_speed = PCI_SPEED_33MHz;
+			ctrl->push_button = 1;
+			ctrl->pci_config_space = 1;
+			ctrl->defeature_PHP = 1;
+			ctrl->pcix_support = 0;
+			ctrl->pcix_speed_capability = 0;
+			break;
+		case PCI_SUB_HPC_ID_INTC:
+			/* Third party (6500/7000) */
+			ctrl->slot_switch_type = 1;
+			bus->max_bus_speed = PCI_SPEED_33MHz;
+			ctrl->push_button = 0;
+			ctrl->pci_config_space = 1;
+			ctrl->defeature_PHP = 1;
+			ctrl->pcix_support = 0;
+			ctrl->pcix_speed_capability = 0;
+			break;
+		case PCI_SUB_HPC_ID3:
+			/* First 66 Mhz implementation */
+			ctrl->push_flag = 1;
+			ctrl->slot_switch_type = 1;
+			bus->max_bus_speed = PCI_SPEED_66MHz;
+			ctrl->push_button = 1;
+			ctrl->pci_config_space = 1;
+			ctrl->defeature_PHP = 1;
+			ctrl->pcix_support = 0;
+			ctrl->pcix_speed_capability = 0;
+			break;
+		case PCI_SUB_HPC_ID4:
+			/* First PCI-X implementation, 100MHz */
+			ctrl->push_flag = 1;
+			ctrl->slot_switch_type = 1;
+			bus->max_bus_speed = PCI_SPEED_100MHz_PCIX;
+			ctrl->push_button = 1;
+			ctrl->pci_config_space = 1;
+			ctrl->defeature_PHP = 1;
+			ctrl->pcix_support = 1;
+			ctrl->pcix_speed_capability = 0;
+			break;
+		default:
+			err(msg_HPC_not_supported);
+			rc = -ENODEV;
+			goto err_free_ctrl;
+		}
+		break;
+
+	case PCI_VENDOR_ID_INTEL:
+		/* Check for speed capability (0=33, 1=66) */
+		if (subsystem_deviceid & 0x0001)
+			bus->max_bus_speed = PCI_SPEED_66MHz;
+		else
+			bus->max_bus_speed = PCI_SPEED_33MHz;
+
+		/* Check for push button */
+		if (subsystem_deviceid & 0x0002)
+			ctrl->push_button = 0;
+		else
+			ctrl->push_button = 1;
+
+		/* Check for slot switch type (0=mechanical, 1=not mechanical) */
+		if (subsystem_deviceid & 0x0004)
+			ctrl->slot_switch_type = 0;
+		else
+			ctrl->slot_switch_type = 1;
+
+		/* PHP Status (0=De-feature PHP, 1=Normal operation) */
+		if (subsystem_deviceid & 0x0008)
+			ctrl->defeature_PHP = 1;	/* PHP supported */
+		else
+			ctrl->defeature_PHP = 0;	/* PHP not supported */
+
+		/* Alternate Base Address Register Interface
+		 * (0=not supported, 1=supported)
+		 */
+		if (subsystem_deviceid & 0x0010)
+			ctrl->alternate_base_address = 1;
+		else
+			ctrl->alternate_base_address = 0;
+
+		/* PCI Config Space Index (0=not supported, 1=supported) */
+		if (subsystem_deviceid & 0x0020)
+			ctrl->pci_config_space = 1;
+		else
+			ctrl->pci_config_space = 0;
+
+		/* PCI-X support */
+		if (subsystem_deviceid & 0x0080) {
+			ctrl->pcix_support = 1;
+			if (subsystem_deviceid & 0x0040)
+				/* 133MHz PCI-X if bit 7 is 1 */
+				ctrl->pcix_speed_capability = 1;
+			else
+				/* 100MHz PCI-X if bit 7 is 1 and bit 0 is 0, */
+				/* 66MHz PCI-X if bit 7 is 1 and bit 0 is 1 */
+				ctrl->pcix_speed_capability = 0;
+		} else {
+			/* Conventional PCI */
+			ctrl->pcix_support = 0;
+			ctrl->pcix_speed_capability = 0;
+		}
+		break;
+
+	default:
+		err(msg_HPC_not_supported);
+		rc = -ENODEV;
+		goto err_free_ctrl;
+	}
+
+	/* Tell the user that we found one. */
+	info("Initializing the PCI hot plug controller residing on PCI bus %d\n",
+					pdev->bus->number);
+
+	dbg("Hotplug controller capabilities:\n");
+	dbg("    speed_capability       %d\n", bus->max_bus_speed);
+	dbg("    slot_switch_type       %s\n", ctrl->slot_switch_type ?
+					"switch present" : "no switch");
+	dbg("    defeature_PHP          %s\n", ctrl->defeature_PHP ?
+					"PHP supported" : "PHP not supported");
+	dbg("    alternate_base_address %s\n", ctrl->alternate_base_address ?
+					"supported" : "not supported");
+	dbg("    pci_config_space       %s\n", ctrl->pci_config_space ?
+					"supported" : "not supported");
+	dbg("    pcix_speed_capability  %s\n", ctrl->pcix_speed_capability ?
+					"supported" : "not supported");
+	dbg("    pcix_support           %s\n", ctrl->pcix_support ?
+					"supported" : "not supported");
+
+	ctrl->pci_dev = pdev;
+	pci_set_drvdata(pdev, ctrl);
+
+	/* make our own copy of the pci bus structure,
+	 * as we like tweaking it a lot */
+	ctrl->pci_bus = kmemdup(pdev->bus, sizeof(*ctrl->pci_bus), GFP_KERNEL);
+	if (!ctrl->pci_bus) {
+		err("out of memory\n");
+		rc = -ENOMEM;
+		goto err_free_ctrl;
+	}
+
+	ctrl->bus = pdev->bus->number;
+	ctrl->rev = pdev->revision;
+	dbg("bus device function rev: %d %d %d %d\n", ctrl->bus,
+		PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn), ctrl->rev);
+
+	mutex_init(&ctrl->crit_sect);
+	init_waitqueue_head(&ctrl->queue);
+
+	/* initialize our threads if they haven't already been started up */
+	rc = one_time_init();
+	if (rc) {
+		goto err_free_bus;
+	}
+
+	dbg("pdev = %p\n", pdev);
+	dbg("pci resource start %llx\n", (unsigned long long)pci_resource_start(pdev, 0));
+	dbg("pci resource len %llx\n", (unsigned long long)pci_resource_len(pdev, 0));
+
+	if (!request_mem_region(pci_resource_start(pdev, 0),
+				pci_resource_len(pdev, 0), MY_NAME)) {
+		err("cannot reserve MMIO region\n");
+		rc = -ENOMEM;
+		goto err_free_bus;
+	}
+
+	ctrl->hpc_reg = ioremap(pci_resource_start(pdev, 0),
+					pci_resource_len(pdev, 0));
+	if (!ctrl->hpc_reg) {
+		err("cannot remap MMIO region %llx @ %llx\n",
+		    (unsigned long long)pci_resource_len(pdev, 0),
+		    (unsigned long long)pci_resource_start(pdev, 0));
+		rc = -ENODEV;
+		goto err_free_mem_region;
+	}
+
+	/* Check for 66Mhz operation */
+	bus->cur_bus_speed = get_controller_speed(ctrl);
+
+
+	/********************************************************
+	 *
+	 *              Save configuration headers for this and
+	 *              subordinate PCI buses
+	 *
+	 ********************************************************/
+
+	/* find the physical slot number of the first hot plug slot */
+
+	/* Get slot won't work for devices behind bridges, but
+	 * in this case it will always be called for the "base"
+	 * bus/dev/func of a slot.
+	 * CS: this is leveraging the PCIIRQ routing code from the kernel
+	 * (pci-pc.c: get_irq_routing_table) */
+	rc = get_slot_mapping(ctrl->pci_bus, pdev->bus->number,
+				(readb(ctrl->hpc_reg + SLOT_MASK) >> 4),
+				&(ctrl->first_slot));
+	dbg("get_slot_mapping: first_slot = %d, returned = %d\n",
+				ctrl->first_slot, rc);
+	if (rc) {
+		err(msg_initialization_err, rc);
+		goto err_iounmap;
+	}
+
+	/* Store PCI Config Space for all devices on this bus */
+	rc = cpqhp_save_config(ctrl, ctrl->bus, readb(ctrl->hpc_reg + SLOT_MASK));
+	if (rc) {
+		err("%s: unable to save PCI configuration data, error %d\n",
+				__func__, rc);
+		goto err_iounmap;
+	}
+
+	/*
+	 * Get IO, memory, and IRQ resources for new devices
+	 */
+	/* The next line is required for cpqhp_find_available_resources */
+	ctrl->interrupt = pdev->irq;
+	if (ctrl->interrupt < 0x10) {
+		cpqhp_legacy_mode = 1;
+		dbg("System seems to be configured for Full Table Mapped MPS mode\n");
+	}
+
+	ctrl->cfgspc_irq = 0;
+	pci_read_config_byte(pdev, PCI_INTERRUPT_LINE, &ctrl->cfgspc_irq);
+
+	rc = cpqhp_find_available_resources(ctrl, cpqhp_rom_start);
+	ctrl->add_support = !rc;
+	if (rc) {
+		dbg("cpqhp_find_available_resources = 0x%x\n", rc);
+		err("unable to locate PCI configuration resources for hot plug add.\n");
+		goto err_iounmap;
+	}
+
+	/*
+	 * Finish setting up the hot plug ctrl device
+	 */
+	ctrl->slot_device_offset = readb(ctrl->hpc_reg + SLOT_MASK) >> 4;
+	dbg("NumSlots %d \n", ctrl->slot_device_offset);
+
+	ctrl->next_event = 0;
+
+	/* Setup the slot information structures */
+	rc = ctrl_slot_setup(ctrl, smbios_start, smbios_table);
+	if (rc) {
+		err(msg_initialization_err, 6);
+		err("%s: unable to save PCI configuration data, error %d\n",
+			__func__, rc);
+		goto err_iounmap;
+	}
+
+	/* Mask all general input interrupts */
+	writel(0xFFFFFFFFL, ctrl->hpc_reg + INT_MASK);
+
+	/* set up the interrupt */
+	dbg("HPC interrupt = %d \n", ctrl->interrupt);
+	if (request_irq(ctrl->interrupt, cpqhp_ctrl_intr,
+			IRQF_SHARED, MY_NAME, ctrl)) {
+		err("Can't get irq %d for the hotplug pci controller\n",
+			ctrl->interrupt);
+		rc = -ENODEV;
+		goto err_iounmap;
+	}
+
+	/* Enable Shift Out interrupt and clear it, also enable SERR on power
+	 * fault
+	 */
+	temp_word = readw(ctrl->hpc_reg + MISC);
+	temp_word |= 0x4006;
+	writew(temp_word, ctrl->hpc_reg + MISC);
+
+	/* Changed 05/05/97 to clear all interrupts at start */
+	writel(0xFFFFFFFFL, ctrl->hpc_reg + INT_INPUT_CLEAR);
+
+	ctrl->ctrl_int_comp = readl(ctrl->hpc_reg + INT_INPUT_CLEAR);
+
+	writel(0x0L, ctrl->hpc_reg + INT_MASK);
+
+	if (!cpqhp_ctrl_list) {
+		cpqhp_ctrl_list = ctrl;
+		ctrl->next = NULL;
+	} else {
+		ctrl->next = cpqhp_ctrl_list;
+		cpqhp_ctrl_list = ctrl;
+	}
+
+	/* turn off empty slots here unless command line option "ON" set
+	 * Wait for exclusive access to hardware
+	 */
+	mutex_lock(&ctrl->crit_sect);
+
+	num_of_slots = readb(ctrl->hpc_reg + SLOT_MASK) & 0x0F;
+
+	/* find first device number for the ctrl */
+	device = readb(ctrl->hpc_reg + SLOT_MASK) >> 4;
+
+	while (num_of_slots) {
+		dbg("num_of_slots: %d\n", num_of_slots);
+		func = cpqhp_slot_find(ctrl->bus, device, 0);
+		if (!func)
+			break;
+
+		hp_slot = func->device - ctrl->slot_device_offset;
+		dbg("hp_slot: %d\n", hp_slot);
+
+		/* We have to save the presence info for these slots */
+		temp_word = ctrl->ctrl_int_comp >> 16;
+		func->presence_save = (temp_word >> hp_slot) & 0x01;
+		func->presence_save |= (temp_word >> (hp_slot + 7)) & 0x02;
+
+		if (ctrl->ctrl_int_comp & (0x1L << hp_slot))
+			func->switch_save = 0;
+		else
+			func->switch_save = 0x10;
+
+		if (!power_mode)
+			if (!func->is_a_board) {
+				green_LED_off(ctrl, hp_slot);
+				slot_disable(ctrl, hp_slot);
+			}
+
+		device++;
+		num_of_slots--;
+	}
+
+	if (!power_mode) {
+		set_SOGO(ctrl);
+		/* Wait for SOBS to be unset */
+		wait_for_ctrl_irq(ctrl);
+	}
+
+	rc = init_SERR(ctrl);
+	if (rc) {
+		err("init_SERR failed\n");
+		mutex_unlock(&ctrl->crit_sect);
+		goto err_free_irq;
+	}
+
+	/* Done with exclusive hardware access */
+	mutex_unlock(&ctrl->crit_sect);
+
+	cpqhp_create_debugfs_files(ctrl);
+
+	return 0;
+
+err_free_irq:
+	free_irq(ctrl->interrupt, ctrl);
+err_iounmap:
+	iounmap(ctrl->hpc_reg);
+err_free_mem_region:
+	release_mem_region(pci_resource_start(pdev, 0), pci_resource_len(pdev, 0));
+err_free_bus:
+	kfree(ctrl->pci_bus);
+err_free_ctrl:
+	kfree(ctrl);
+err_disable_device:
+	pci_disable_device(pdev);
+	return rc;
+}
+
+static void __exit unload_cpqphpd(void)
+{
+	struct pci_func *next;
+	struct pci_func *TempSlot;
+	int loop;
+	u32 rc;
+	struct controller *ctrl;
+	struct controller *tctrl;
+	struct pci_resource *res;
+	struct pci_resource *tres;
+
+	rc = compaq_nvram_store(cpqhp_rom_start);
+
+	ctrl = cpqhp_ctrl_list;
+
+	while (ctrl) {
+		if (ctrl->hpc_reg) {
+			u16 misc;
+			rc = read_slot_enable (ctrl);
+
+			writeb(0, ctrl->hpc_reg + SLOT_SERR);
+			writel(0xFFFFFFC0L | ~rc, ctrl->hpc_reg + INT_MASK);
+
+			misc = readw(ctrl->hpc_reg + MISC);
+			misc &= 0xFFFD;
+			writew(misc, ctrl->hpc_reg + MISC);
+		}
+
+		ctrl_slot_cleanup(ctrl);
+
+		res = ctrl->io_head;
+		while (res) {
+			tres = res;
+			res = res->next;
+			kfree(tres);
+		}
+
+		res = ctrl->mem_head;
+		while (res) {
+			tres = res;
+			res = res->next;
+			kfree(tres);
+		}
+
+		res = ctrl->p_mem_head;
+		while (res) {
+			tres = res;
+			res = res->next;
+			kfree(tres);
+		}
+
+		res = ctrl->bus_head;
+		while (res) {
+			tres = res;
+			res = res->next;
+			kfree(tres);
+		}
+
+		kfree (ctrl->pci_bus);
+
+		tctrl = ctrl;
+		ctrl = ctrl->next;
+		kfree(tctrl);
+	}
+
+	for (loop = 0; loop < 256; loop++) {
+		next = cpqhp_slot_list[loop];
+		while (next != NULL) {
+			res = next->io_head;
+			while (res) {
+				tres = res;
+				res = res->next;
+				kfree(tres);
+			}
+
+			res = next->mem_head;
+			while (res) {
+				tres = res;
+				res = res->next;
+				kfree(tres);
+			}
+
+			res = next->p_mem_head;
+			while (res) {
+				tres = res;
+				res = res->next;
+				kfree(tres);
+			}
+
+			res = next->bus_head;
+			while (res) {
+				tres = res;
+				res = res->next;
+				kfree(tres);
+			}
+
+			TempSlot = next;
+			next = next->next;
+			kfree(TempSlot);
+		}
+	}
+
+	/* Stop the notification mechanism */
+	if (initialized)
+		cpqhp_event_stop_thread();
+
+	/* unmap the rom address */
+	if (cpqhp_rom_start)
+		iounmap(cpqhp_rom_start);
+	if (smbios_start)
+		iounmap(smbios_start);
+}
+
+static struct pci_device_id hpcd_pci_tbl[] = {
+	{
+	/* handle any PCI Hotplug controller */
+	.class =        ((PCI_CLASS_SYSTEM_PCI_HOTPLUG << 8) | 0x00),
+	.class_mask =   ~0,
+
+	/* no matter who makes it */
+	.vendor =       PCI_ANY_ID,
+	.device =       PCI_ANY_ID,
+	.subvendor =    PCI_ANY_ID,
+	.subdevice =    PCI_ANY_ID,
+
+	}, { /* end: all zeroes */ }
+};
+
+MODULE_DEVICE_TABLE(pci, hpcd_pci_tbl);
+
+static struct pci_driver cpqhpc_driver = {
+	.name =		"compaq_pci_hotplug",
+	.id_table =	hpcd_pci_tbl,
+	.probe =	cpqhpc_probe,
+	/* remove:	cpqhpc_remove_one, */
+};
+
+static int __init cpqhpc_init(void)
+{
+	int result;
+
+	cpqhp_debug = debug;
+
+	info (DRIVER_DESC " version: " DRIVER_VERSION "\n");
+	cpqhp_initialize_debugfs();
+	result = pci_register_driver(&cpqhpc_driver);
+	dbg("pci_register_driver = %d\n", result);
+	return result;
+}
+
+static void __exit cpqhpc_cleanup(void)
+{
+	dbg("unload_cpqphpd()\n");
+	unload_cpqphpd();
+
+	dbg("pci_unregister_driver\n");
+	pci_unregister_driver(&cpqhpc_driver);
+	cpqhp_shutdown_debugfs();
+}
+
+module_init(cpqhpc_init);
+module_exit(cpqhpc_cleanup);
diff --git a/drivers/pci/hotplug/cpqphp_ctrl.c b/drivers/pci/hotplug/cpqphp_ctrl.c
new file mode 100644
index 00000000..e43908d9
--- /dev/null
+++ b/drivers/pci/hotplug/cpqphp_ctrl.c
@@ -0,0 +1,3011 @@
+/*
+ * Compaq Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/wait.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/kthread.h>
+#include "cpqphp.h"
+
+static u32 configure_new_device(struct controller* ctrl, struct pci_func *func,
+			u8 behind_bridge, struct resource_lists *resources);
+static int configure_new_function(struct controller* ctrl, struct pci_func *func,
+			u8 behind_bridge, struct resource_lists *resources);
+static void interrupt_event_handler(struct controller *ctrl);
+
+
+static struct task_struct *cpqhp_event_thread;
+static unsigned long pushbutton_pending;	/* = 0 */
+
+/* delay is in jiffies to wait for */
+static void long_delay(int delay)
+{
+	/*
+	 * XXX(hch): if someone is bored please convert all callers
+	 * to call msleep_interruptible directly.  They really want
+	 * to specify timeouts in natural units and spend a lot of
+	 * effort converting them to jiffies..
+	 */
+	msleep_interruptible(jiffies_to_msecs(delay));
+}
+
+
+/* FIXME: The following line needs to be somewhere else... */
+#define WRONG_BUS_FREQUENCY 0x07
+static u8 handle_switch_change(u8 change, struct controller * ctrl)
+{
+	int hp_slot;
+	u8 rc = 0;
+	u16 temp_word;
+	struct pci_func *func;
+	struct event_info *taskInfo;
+
+	if (!change)
+		return 0;
+
+	/* Switch Change */
+	dbg("cpqsbd:  Switch interrupt received.\n");
+
+	for (hp_slot = 0; hp_slot < 6; hp_slot++) {
+		if (change & (0x1L << hp_slot)) {
+			/*
+			 * this one changed.
+			 */
+			func = cpqhp_slot_find(ctrl->bus,
+				(hp_slot + ctrl->slot_device_offset), 0);
+
+			/* this is the structure that tells the worker thread
+			 * what to do
+			 */
+			taskInfo = &(ctrl->event_queue[ctrl->next_event]);
+			ctrl->next_event = (ctrl->next_event + 1) % 10;
+			taskInfo->hp_slot = hp_slot;
+
+			rc++;
+
+			temp_word = ctrl->ctrl_int_comp >> 16;
+			func->presence_save = (temp_word >> hp_slot) & 0x01;
+			func->presence_save |= (temp_word >> (hp_slot + 7)) & 0x02;
+
+			if (ctrl->ctrl_int_comp & (0x1L << hp_slot)) {
+				/*
+				 * Switch opened
+				 */
+
+				func->switch_save = 0;
+
+				taskInfo->event_type = INT_SWITCH_OPEN;
+			} else {
+				/*
+				 * Switch closed
+				 */
+
+				func->switch_save = 0x10;
+
+				taskInfo->event_type = INT_SWITCH_CLOSE;
+			}
+		}
+	}
+
+	return rc;
+}
+
+/**
+ * cpqhp_find_slot - find the struct slot of given device
+ * @ctrl: scan lots of this controller
+ * @device: the device id to find
+ */
+static struct slot *cpqhp_find_slot(struct controller *ctrl, u8 device)
+{
+	struct slot *slot = ctrl->slot;
+
+	while (slot && (slot->device != device))
+		slot = slot->next;
+
+	return slot;
+}
+
+
+static u8 handle_presence_change(u16 change, struct controller * ctrl)
+{
+	int hp_slot;
+	u8 rc = 0;
+	u8 temp_byte;
+	u16 temp_word;
+	struct pci_func *func;
+	struct event_info *taskInfo;
+	struct slot *p_slot;
+
+	if (!change)
+		return 0;
+
+	/*
+	 * Presence Change
+	 */
+	dbg("cpqsbd:  Presence/Notify input change.\n");
+	dbg("         Changed bits are 0x%4.4x\n", change );
+
+	for (hp_slot = 0; hp_slot < 6; hp_slot++) {
+		if (change & (0x0101 << hp_slot)) {
+			/*
+			 * this one changed.
+			 */
+			func = cpqhp_slot_find(ctrl->bus,
+				(hp_slot + ctrl->slot_device_offset), 0);
+
+			taskInfo = &(ctrl->event_queue[ctrl->next_event]);
+			ctrl->next_event = (ctrl->next_event + 1) % 10;
+			taskInfo->hp_slot = hp_slot;
+
+			rc++;
+
+			p_slot = cpqhp_find_slot(ctrl, hp_slot + (readb(ctrl->hpc_reg + SLOT_MASK) >> 4));
+			if (!p_slot)
+				return 0;
+
+			/* If the switch closed, must be a button
+			 * If not in button mode, nevermind
+			 */
+			if (func->switch_save && (ctrl->push_button == 1)) {
+				temp_word = ctrl->ctrl_int_comp >> 16;
+				temp_byte = (temp_word >> hp_slot) & 0x01;
+				temp_byte |= (temp_word >> (hp_slot + 7)) & 0x02;
+
+				if (temp_byte != func->presence_save) {
+					/*
+					 * button Pressed (doesn't do anything)
+					 */
+					dbg("hp_slot %d button pressed\n", hp_slot);
+					taskInfo->event_type = INT_BUTTON_PRESS;
+				} else {
+					/*
+					 * button Released - TAKE ACTION!!!!
+					 */
+					dbg("hp_slot %d button released\n", hp_slot);
+					taskInfo->event_type = INT_BUTTON_RELEASE;
+
+					/* Cancel if we are still blinking */
+					if ((p_slot->state == BLINKINGON_STATE)
+					    || (p_slot->state == BLINKINGOFF_STATE)) {
+						taskInfo->event_type = INT_BUTTON_CANCEL;
+						dbg("hp_slot %d button cancel\n", hp_slot);
+					} else if ((p_slot->state == POWERON_STATE)
+						   || (p_slot->state == POWEROFF_STATE)) {
+						/* info(msg_button_ignore, p_slot->number); */
+						taskInfo->event_type = INT_BUTTON_IGNORE;
+						dbg("hp_slot %d button ignore\n", hp_slot);
+					}
+				}
+			} else {
+				/* Switch is open, assume a presence change
+				 * Save the presence state
+				 */
+				temp_word = ctrl->ctrl_int_comp >> 16;
+				func->presence_save = (temp_word >> hp_slot) & 0x01;
+				func->presence_save |= (temp_word >> (hp_slot + 7)) & 0x02;
+
+				if ((!(ctrl->ctrl_int_comp & (0x010000 << hp_slot))) ||
+				    (!(ctrl->ctrl_int_comp & (0x01000000 << hp_slot)))) {
+					/* Present */
+					taskInfo->event_type = INT_PRESENCE_ON;
+				} else {
+					/* Not Present */
+					taskInfo->event_type = INT_PRESENCE_OFF;
+				}
+			}
+		}
+	}
+
+	return rc;
+}
+
+
+static u8 handle_power_fault(u8 change, struct controller * ctrl)
+{
+	int hp_slot;
+	u8 rc = 0;
+	struct pci_func *func;
+	struct event_info *taskInfo;
+
+	if (!change)
+		return 0;
+
+	/*
+	 * power fault
+	 */
+
+	info("power fault interrupt\n");
+
+	for (hp_slot = 0; hp_slot < 6; hp_slot++) {
+		if (change & (0x01 << hp_slot)) {
+			/*
+			 * this one changed.
+			 */
+			func = cpqhp_slot_find(ctrl->bus,
+				(hp_slot + ctrl->slot_device_offset), 0);
+
+			taskInfo = &(ctrl->event_queue[ctrl->next_event]);
+			ctrl->next_event = (ctrl->next_event + 1) % 10;
+			taskInfo->hp_slot = hp_slot;
+
+			rc++;
+
+			if (ctrl->ctrl_int_comp & (0x00000100 << hp_slot)) {
+				/*
+				 * power fault Cleared
+				 */
+				func->status = 0x00;
+
+				taskInfo->event_type = INT_POWER_FAULT_CLEAR;
+			} else {
+				/*
+				 * power fault
+				 */
+				taskInfo->event_type = INT_POWER_FAULT;
+
+				if (ctrl->rev < 4) {
+					amber_LED_on (ctrl, hp_slot);
+					green_LED_off (ctrl, hp_slot);
+					set_SOGO (ctrl);
+
+					/* this is a fatal condition, we want
+					 * to crash the machine to protect from
+					 * data corruption. simulated_NMI
+					 * shouldn't ever return */
+					/* FIXME
+					simulated_NMI(hp_slot, ctrl); */
+
+					/* The following code causes a software
+					 * crash just in case simulated_NMI did
+					 * return */
+					/*FIXME
+					panic(msg_power_fault); */
+				} else {
+					/* set power fault status for this board */
+					func->status = 0xFF;
+					info("power fault bit %x set\n", hp_slot);
+				}
+			}
+		}
+	}
+
+	return rc;
+}
+
+
+/**
+ * sort_by_size - sort nodes on the list by their length, smallest first.
+ * @head: list to sort
+ */
+static int sort_by_size(struct pci_resource **head)
+{
+	struct pci_resource *current_res;
+	struct pci_resource *next_res;
+	int out_of_order = 1;
+
+	if (!(*head))
+		return 1;
+
+	if (!((*head)->next))
+		return 0;
+
+	while (out_of_order) {
+		out_of_order = 0;
+
+		/* Special case for swapping list head */
+		if (((*head)->next) &&
+		    ((*head)->length > (*head)->next->length)) {
+			out_of_order++;
+			current_res = *head;
+			*head = (*head)->next;
+			current_res->next = (*head)->next;
+			(*head)->next = current_res;
+		}
+
+		current_res = *head;
+
+		while (current_res->next && current_res->next->next) {
+			if (current_res->next->length > current_res->next->next->length) {
+				out_of_order++;
+				next_res = current_res->next;
+				current_res->next = current_res->next->next;
+				current_res = current_res->next;
+				next_res->next = current_res->next;
+				current_res->next = next_res;
+			} else
+				current_res = current_res->next;
+		}
+	}  /* End of out_of_order loop */
+
+	return 0;
+}
+
+
+/**
+ * sort_by_max_size - sort nodes on the list by their length, largest first.
+ * @head: list to sort
+ */
+static int sort_by_max_size(struct pci_resource **head)
+{
+	struct pci_resource *current_res;
+	struct pci_resource *next_res;
+	int out_of_order = 1;
+
+	if (!(*head))
+		return 1;
+
+	if (!((*head)->next))
+		return 0;
+
+	while (out_of_order) {
+		out_of_order = 0;
+
+		/* Special case for swapping list head */
+		if (((*head)->next) &&
+		    ((*head)->length < (*head)->next->length)) {
+			out_of_order++;
+			current_res = *head;
+			*head = (*head)->next;
+			current_res->next = (*head)->next;
+			(*head)->next = current_res;
+		}
+
+		current_res = *head;
+
+		while (current_res->next && current_res->next->next) {
+			if (current_res->next->length < current_res->next->next->length) {
+				out_of_order++;
+				next_res = current_res->next;
+				current_res->next = current_res->next->next;
+				current_res = current_res->next;
+				next_res->next = current_res->next;
+				current_res->next = next_res;
+			} else
+				current_res = current_res->next;
+		}
+	}  /* End of out_of_order loop */
+
+	return 0;
+}
+
+
+/**
+ * do_pre_bridge_resource_split - find node of resources that are unused
+ * @head: new list head
+ * @orig_head: original list head
+ * @alignment: max node size (?)
+ */
+static struct pci_resource *do_pre_bridge_resource_split(struct pci_resource **head,
+				struct pci_resource **orig_head, u32 alignment)
+{
+	struct pci_resource *prevnode = NULL;
+	struct pci_resource *node;
+	struct pci_resource *split_node;
+	u32 rc;
+	u32 temp_dword;
+	dbg("do_pre_bridge_resource_split\n");
+
+	if (!(*head) || !(*orig_head))
+		return NULL;
+
+	rc = cpqhp_resource_sort_and_combine(head);
+
+	if (rc)
+		return NULL;
+
+	if ((*head)->base != (*orig_head)->base)
+		return NULL;
+
+	if ((*head)->length == (*orig_head)->length)
+		return NULL;
+
+
+	/* If we got here, there the bridge requires some of the resource, but
+	 * we may be able to split some off of the front
+	 */
+
+	node = *head;
+
+	if (node->length & (alignment -1)) {
+		/* this one isn't an aligned length, so we'll make a new entry
+		 * and split it up.
+		 */
+		split_node = kmalloc(sizeof(*split_node), GFP_KERNEL);
+
+		if (!split_node)
+			return NULL;
+
+		temp_dword = (node->length | (alignment-1)) + 1 - alignment;
+
+		split_node->base = node->base;
+		split_node->length = temp_dword;
+
+		node->length -= temp_dword;
+		node->base += split_node->length;
+
+		/* Put it in the list */
+		*head = split_node;
+		split_node->next = node;
+	}
+
+	if (node->length < alignment)
+		return NULL;
+
+	/* Now unlink it */
+	if (*head == node) {
+		*head = node->next;
+	} else {
+		prevnode = *head;
+		while (prevnode->next != node)
+			prevnode = prevnode->next;
+
+		prevnode->next = node->next;
+	}
+	node->next = NULL;
+
+	return node;
+}
+
+
+/**
+ * do_bridge_resource_split - find one node of resources that aren't in use
+ * @head: list head
+ * @alignment: max node size (?)
+ */
+static struct pci_resource *do_bridge_resource_split(struct pci_resource **head, u32 alignment)
+{
+	struct pci_resource *prevnode = NULL;
+	struct pci_resource *node;
+	u32 rc;
+	u32 temp_dword;
+
+	rc = cpqhp_resource_sort_and_combine(head);
+
+	if (rc)
+		return NULL;
+
+	node = *head;
+
+	while (node->next) {
+		prevnode = node;
+		node = node->next;
+		kfree(prevnode);
+	}
+
+	if (node->length < alignment)
+		goto error;
+
+	if (node->base & (alignment - 1)) {
+		/* Short circuit if adjusted size is too small */
+		temp_dword = (node->base | (alignment-1)) + 1;
+		if ((node->length - (temp_dword - node->base)) < alignment)
+			goto error;
+
+		node->length -= (temp_dword - node->base);
+		node->base = temp_dword;
+	}
+
+	if (node->length & (alignment - 1))
+		/* There's stuff in use after this node */
+		goto error;
+
+	return node;
+error:
+	kfree(node);
+	return NULL;
+}
+
+
+/**
+ * get_io_resource - find first node of given size not in ISA aliasing window.
+ * @head: list to search
+ * @size: size of node to find, must be a power of two.
+ *
+ * Description: This function sorts the resource list by size and then returns
+ * returns the first node of "size" length that is not in the ISA aliasing
+ * window.  If it finds a node larger than "size" it will split it up.
+ */
+static struct pci_resource *get_io_resource(struct pci_resource **head, u32 size)
+{
+	struct pci_resource *prevnode;
+	struct pci_resource *node;
+	struct pci_resource *split_node;
+	u32 temp_dword;
+
+	if (!(*head))
+		return NULL;
+
+	if (cpqhp_resource_sort_and_combine(head))
+		return NULL;
+
+	if (sort_by_size(head))
+		return NULL;
+
+	for (node = *head; node; node = node->next) {
+		if (node->length < size)
+			continue;
+
+		if (node->base & (size - 1)) {
+			/* this one isn't base aligned properly
+			 * so we'll make a new entry and split it up
+			 */
+			temp_dword = (node->base | (size-1)) + 1;
+
+			/* Short circuit if adjusted size is too small */
+			if ((node->length - (temp_dword - node->base)) < size)
+				continue;
+
+			split_node = kmalloc(sizeof(*split_node), GFP_KERNEL);
+
+			if (!split_node)
+				return NULL;
+
+			split_node->base = node->base;
+			split_node->length = temp_dword - node->base;
+			node->base = temp_dword;
+			node->length -= split_node->length;
+
+			/* Put it in the list */
+			split_node->next = node->next;
+			node->next = split_node;
+		} /* End of non-aligned base */
+
+		/* Don't need to check if too small since we already did */
+		if (node->length > size) {
+			/* this one is longer than we need
+			 * so we'll make a new entry and split it up
+			 */
+			split_node = kmalloc(sizeof(*split_node), GFP_KERNEL);
+
+			if (!split_node)
+				return NULL;
+
+			split_node->base = node->base + size;
+			split_node->length = node->length - size;
+			node->length = size;
+
+			/* Put it in the list */
+			split_node->next = node->next;
+			node->next = split_node;
+		}  /* End of too big on top end */
+
+		/* For IO make sure it's not in the ISA aliasing space */
+		if (node->base & 0x300L)
+			continue;
+
+		/* If we got here, then it is the right size
+		 * Now take it out of the list and break
+		 */
+		if (*head == node) {
+			*head = node->next;
+		} else {
+			prevnode = *head;
+			while (prevnode->next != node)
+				prevnode = prevnode->next;
+
+			prevnode->next = node->next;
+		}
+		node->next = NULL;
+		break;
+	}
+
+	return node;
+}
+
+
+/**
+ * get_max_resource - get largest node which has at least the given size.
+ * @head: the list to search the node in
+ * @size: the minimum size of the node to find
+ *
+ * Description: Gets the largest node that is at least "size" big from the
+ * list pointed to by head.  It aligns the node on top and bottom
+ * to "size" alignment before returning it.
+ */
+static struct pci_resource *get_max_resource(struct pci_resource **head, u32 size)
+{
+	struct pci_resource *max;
+	struct pci_resource *temp;
+	struct pci_resource *split_node;
+	u32 temp_dword;
+
+	if (cpqhp_resource_sort_and_combine(head))
+		return NULL;
+
+	if (sort_by_max_size(head))
+		return NULL;
+
+	for (max = *head; max; max = max->next) {
+		/* If not big enough we could probably just bail,
+		 * instead we'll continue to the next.
+		 */
+		if (max->length < size)
+			continue;
+
+		if (max->base & (size - 1)) {
+			/* this one isn't base aligned properly
+			 * so we'll make a new entry and split it up
+			 */
+			temp_dword = (max->base | (size-1)) + 1;
+
+			/* Short circuit if adjusted size is too small */
+			if ((max->length - (temp_dword - max->base)) < size)
+				continue;
+
+			split_node = kmalloc(sizeof(*split_node), GFP_KERNEL);
+
+			if (!split_node)
+				return NULL;
+
+			split_node->base = max->base;
+			split_node->length = temp_dword - max->base;
+			max->base = temp_dword;
+			max->length -= split_node->length;
+
+			split_node->next = max->next;
+			max->next = split_node;
+		}
+
+		if ((max->base + max->length) & (size - 1)) {
+			/* this one isn't end aligned properly at the top
+			 * so we'll make a new entry and split it up
+			 */
+			split_node = kmalloc(sizeof(*split_node), GFP_KERNEL);
+
+			if (!split_node)
+				return NULL;
+			temp_dword = ((max->base + max->length) & ~(size - 1));
+			split_node->base = temp_dword;
+			split_node->length = max->length + max->base
+					     - split_node->base;
+			max->length -= split_node->length;
+
+			split_node->next = max->next;
+			max->next = split_node;
+		}
+
+		/* Make sure it didn't shrink too much when we aligned it */
+		if (max->length < size)
+			continue;
+
+		/* Now take it out of the list */
+		temp = *head;
+		if (temp == max) {
+			*head = max->next;
+		} else {
+			while (temp && temp->next != max) {
+				temp = temp->next;
+			}
+
+			temp->next = max->next;
+		}
+
+		max->next = NULL;
+		break;
+	}
+
+	return max;
+}
+
+
+/**
+ * get_resource - find resource of given size and split up larger ones.
+ * @head: the list to search for resources
+ * @size: the size limit to use
+ *
+ * Description: This function sorts the resource list by size and then
+ * returns the first node of "size" length.  If it finds a node
+ * larger than "size" it will split it up.
+ *
+ * size must be a power of two.
+ */
+static struct pci_resource *get_resource(struct pci_resource **head, u32 size)
+{
+	struct pci_resource *prevnode;
+	struct pci_resource *node;
+	struct pci_resource *split_node;
+	u32 temp_dword;
+
+	if (cpqhp_resource_sort_and_combine(head))
+		return NULL;
+
+	if (sort_by_size(head))
+		return NULL;
+
+	for (node = *head; node; node = node->next) {
+		dbg("%s: req_size =%x node=%p, base=%x, length=%x\n",
+		    __func__, size, node, node->base, node->length);
+		if (node->length < size)
+			continue;
+
+		if (node->base & (size - 1)) {
+			dbg("%s: not aligned\n", __func__);
+			/* this one isn't base aligned properly
+			 * so we'll make a new entry and split it up
+			 */
+			temp_dword = (node->base | (size-1)) + 1;
+
+			/* Short circuit if adjusted size is too small */
+			if ((node->length - (temp_dword - node->base)) < size)
+				continue;
+
+			split_node = kmalloc(sizeof(*split_node), GFP_KERNEL);
+
+			if (!split_node)
+				return NULL;
+
+			split_node->base = node->base;
+			split_node->length = temp_dword - node->base;
+			node->base = temp_dword;
+			node->length -= split_node->length;
+
+			split_node->next = node->next;
+			node->next = split_node;
+		} /* End of non-aligned base */
+
+		/* Don't need to check if too small since we already did */
+		if (node->length > size) {
+			dbg("%s: too big\n", __func__);
+			/* this one is longer than we need
+			 * so we'll make a new entry and split it up
+			 */
+			split_node = kmalloc(sizeof(*split_node), GFP_KERNEL);
+
+			if (!split_node)
+				return NULL;
+
+			split_node->base = node->base + size;
+			split_node->length = node->length - size;
+			node->length = size;
+
+			/* Put it in the list */
+			split_node->next = node->next;
+			node->next = split_node;
+		}  /* End of too big on top end */
+
+		dbg("%s: got one!!!\n", __func__);
+		/* If we got here, then it is the right size
+		 * Now take it out of the list */
+		if (*head == node) {
+			*head = node->next;
+		} else {
+			prevnode = *head;
+			while (prevnode->next != node)
+				prevnode = prevnode->next;
+
+			prevnode->next = node->next;
+		}
+		node->next = NULL;
+		break;
+	}
+	return node;
+}
+
+
+/**
+ * cpqhp_resource_sort_and_combine - sort nodes by base addresses and clean up
+ * @head: the list to sort and clean up
+ *
+ * Description: Sorts all of the nodes in the list in ascending order by
+ * their base addresses.  Also does garbage collection by
+ * combining adjacent nodes.
+ *
+ * Returns %0 if success.
+ */
+int cpqhp_resource_sort_and_combine(struct pci_resource **head)
+{
+	struct pci_resource *node1;
+	struct pci_resource *node2;
+	int out_of_order = 1;
+
+	dbg("%s: head = %p, *head = %p\n", __func__, head, *head);
+
+	if (!(*head))
+		return 1;
+
+	dbg("*head->next = %p\n",(*head)->next);
+
+	if (!(*head)->next)
+		return 0;	/* only one item on the list, already sorted! */
+
+	dbg("*head->base = 0x%x\n",(*head)->base);
+	dbg("*head->next->base = 0x%x\n",(*head)->next->base);
+	while (out_of_order) {
+		out_of_order = 0;
+
+		/* Special case for swapping list head */
+		if (((*head)->next) &&
+		    ((*head)->base > (*head)->next->base)) {
+			node1 = *head;
+			(*head) = (*head)->next;
+			node1->next = (*head)->next;
+			(*head)->next = node1;
+			out_of_order++;
+		}
+
+		node1 = (*head);
+
+		while (node1->next && node1->next->next) {
+			if (node1->next->base > node1->next->next->base) {
+				out_of_order++;
+				node2 = node1->next;
+				node1->next = node1->next->next;
+				node1 = node1->next;
+				node2->next = node1->next;
+				node1->next = node2;
+			} else
+				node1 = node1->next;
+		}
+	}  /* End of out_of_order loop */
+
+	node1 = *head;
+
+	while (node1 && node1->next) {
+		if ((node1->base + node1->length) == node1->next->base) {
+			/* Combine */
+			dbg("8..\n");
+			node1->length += node1->next->length;
+			node2 = node1->next;
+			node1->next = node1->next->next;
+			kfree(node2);
+		} else
+			node1 = node1->next;
+	}
+
+	return 0;
+}
+
+
+irqreturn_t cpqhp_ctrl_intr(int IRQ, void *data)
+{
+	struct controller *ctrl = data;
+	u8 schedule_flag = 0;
+	u8 reset;
+	u16 misc;
+	u32 Diff;
+	u32 temp_dword;
+
+
+	misc = readw(ctrl->hpc_reg + MISC);
+	/*
+	 * Check to see if it was our interrupt
+	 */
+	if (!(misc & 0x000C)) {
+		return IRQ_NONE;
+	}
+
+	if (misc & 0x0004) {
+		/*
+		 * Serial Output interrupt Pending
+		 */
+
+		/* Clear the interrupt */
+		misc |= 0x0004;
+		writew(misc, ctrl->hpc_reg + MISC);
+
+		/* Read to clear posted writes */
+		misc = readw(ctrl->hpc_reg + MISC);
+
+		dbg ("%s - waking up\n", __func__);
+		wake_up_interruptible(&ctrl->queue);
+	}
+
+	if (misc & 0x0008) {
+		/* General-interrupt-input interrupt Pending */
+		Diff = readl(ctrl->hpc_reg + INT_INPUT_CLEAR) ^ ctrl->ctrl_int_comp;
+
+		ctrl->ctrl_int_comp = readl(ctrl->hpc_reg + INT_INPUT_CLEAR);
+
+		/* Clear the interrupt */
+		writel(Diff, ctrl->hpc_reg + INT_INPUT_CLEAR);
+
+		/* Read it back to clear any posted writes */
+		temp_dword = readl(ctrl->hpc_reg + INT_INPUT_CLEAR);
+
+		if (!Diff)
+			/* Clear all interrupts */
+			writel(0xFFFFFFFF, ctrl->hpc_reg + INT_INPUT_CLEAR);
+
+		schedule_flag += handle_switch_change((u8)(Diff & 0xFFL), ctrl);
+		schedule_flag += handle_presence_change((u16)((Diff & 0xFFFF0000L) >> 16), ctrl);
+		schedule_flag += handle_power_fault((u8)((Diff & 0xFF00L) >> 8), ctrl);
+	}
+
+	reset = readb(ctrl->hpc_reg + RESET_FREQ_MODE);
+	if (reset & 0x40) {
+		/* Bus reset has completed */
+		reset &= 0xCF;
+		writeb(reset, ctrl->hpc_reg + RESET_FREQ_MODE);
+		reset = readb(ctrl->hpc_reg + RESET_FREQ_MODE);
+		wake_up_interruptible(&ctrl->queue);
+	}
+
+	if (schedule_flag) {
+		wake_up_process(cpqhp_event_thread);
+		dbg("Waking even thread");
+	}
+	return IRQ_HANDLED;
+}
+
+
+/**
+ * cpqhp_slot_create - Creates a node and adds it to the proper bus.
+ * @busnumber: bus where new node is to be located
+ *
+ * Returns pointer to the new node or %NULL if unsuccessful.
+ */
+struct pci_func *cpqhp_slot_create(u8 busnumber)
+{
+	struct pci_func *new_slot;
+	struct pci_func *next;
+
+	new_slot = kzalloc(sizeof(*new_slot), GFP_KERNEL);
+	if (new_slot == NULL)
+		return new_slot;
+
+	new_slot->next = NULL;
+	new_slot->configured = 1;
+
+	if (cpqhp_slot_list[busnumber] == NULL) {
+		cpqhp_slot_list[busnumber] = new_slot;
+	} else {
+		next = cpqhp_slot_list[busnumber];
+		while (next->next != NULL)
+			next = next->next;
+		next->next = new_slot;
+	}
+	return new_slot;
+}
+
+
+/**
+ * slot_remove - Removes a node from the linked list of slots.
+ * @old_slot: slot to remove
+ *
+ * Returns %0 if successful, !0 otherwise.
+ */
+static int slot_remove(struct pci_func * old_slot)
+{
+	struct pci_func *next;
+
+	if (old_slot == NULL)
+		return 1;
+
+	next = cpqhp_slot_list[old_slot->bus];
+	if (next == NULL)
+		return 1;
+
+	if (next == old_slot) {
+		cpqhp_slot_list[old_slot->bus] = old_slot->next;
+		cpqhp_destroy_board_resources(old_slot);
+		kfree(old_slot);
+		return 0;
+	}
+
+	while ((next->next != old_slot) && (next->next != NULL))
+		next = next->next;
+
+	if (next->next == old_slot) {
+		next->next = old_slot->next;
+		cpqhp_destroy_board_resources(old_slot);
+		kfree(old_slot);
+		return 0;
+	} else
+		return 2;
+}
+
+
+/**
+ * bridge_slot_remove - Removes a node from the linked list of slots.
+ * @bridge: bridge to remove
+ *
+ * Returns %0 if successful, !0 otherwise.
+ */
+static int bridge_slot_remove(struct pci_func *bridge)
+{
+	u8 subordinateBus, secondaryBus;
+	u8 tempBus;
+	struct pci_func *next;
+
+	secondaryBus = (bridge->config_space[0x06] >> 8) & 0xFF;
+	subordinateBus = (bridge->config_space[0x06] >> 16) & 0xFF;
+
+	for (tempBus = secondaryBus; tempBus <= subordinateBus; tempBus++) {
+		next = cpqhp_slot_list[tempBus];
+
+		while (!slot_remove(next))
+			next = cpqhp_slot_list[tempBus];
+	}
+
+	next = cpqhp_slot_list[bridge->bus];
+
+	if (next == NULL)
+		return 1;
+
+	if (next == bridge) {
+		cpqhp_slot_list[bridge->bus] = bridge->next;
+		goto out;
+	}
+
+	while ((next->next != bridge) && (next->next != NULL))
+		next = next->next;
+
+	if (next->next != bridge)
+		return 2;
+	next->next = bridge->next;
+out:
+	kfree(bridge);
+	return 0;
+}
+
+
+/**
+ * cpqhp_slot_find - Looks for a node by bus, and device, multiple functions accessed
+ * @bus: bus to find
+ * @device: device to find
+ * @index: is %0 for first function found, %1 for the second...
+ *
+ * Returns pointer to the node if successful, %NULL otherwise.
+ */
+struct pci_func *cpqhp_slot_find(u8 bus, u8 device, u8 index)
+{
+	int found = -1;
+	struct pci_func *func;
+
+	func = cpqhp_slot_list[bus];
+
+	if ((func == NULL) || ((func->device == device) && (index == 0)))
+		return func;
+
+	if (func->device == device)
+		found++;
+
+	while (func->next != NULL) {
+		func = func->next;
+
+		if (func->device == device)
+			found++;
+
+		if (found == index)
+			return func;
+	}
+
+	return NULL;
+}
+
+
+/* DJZ: I don't think is_bridge will work as is.
+ * FIXME */
+static int is_bridge(struct pci_func * func)
+{
+	/* Check the header type */
+	if (((func->config_space[0x03] >> 16) & 0xFF) == 0x01)
+		return 1;
+	else
+		return 0;
+}
+
+
+/**
+ * set_controller_speed - set the frequency and/or mode of a specific controller segment.
+ * @ctrl: controller to change frequency/mode for.
+ * @adapter_speed: the speed of the adapter we want to match.
+ * @hp_slot: the slot number where the adapter is installed.
+ *
+ * Returns %0 if we successfully change frequency and/or mode to match the
+ * adapter speed.
+ */
+static u8 set_controller_speed(struct controller *ctrl, u8 adapter_speed, u8 hp_slot)
+{
+	struct slot *slot;
+	struct pci_bus *bus = ctrl->pci_bus;
+	u8 reg;
+	u8 slot_power = readb(ctrl->hpc_reg + SLOT_POWER);
+	u16 reg16;
+	u32 leds = readl(ctrl->hpc_reg + LED_CONTROL);
+
+	if (bus->cur_bus_speed == adapter_speed)
+		return 0;
+
+	/* We don't allow freq/mode changes if we find another adapter running
+	 * in another slot on this controller
+	 */
+	for(slot = ctrl->slot; slot; slot = slot->next) {
+		if (slot->device == (hp_slot + ctrl->slot_device_offset))
+			continue;
+		if (!slot->hotplug_slot || !slot->hotplug_slot->info)
+			continue;
+		if (slot->hotplug_slot->info->adapter_status == 0)
+			continue;
+		/* If another adapter is running on the same segment but at a
+		 * lower speed/mode, we allow the new adapter to function at
+		 * this rate if supported
+		 */
+		if (bus->cur_bus_speed < adapter_speed)
+			return 0;
+
+		return 1;
+	}
+
+	/* If the controller doesn't support freq/mode changes and the
+	 * controller is running at a higher mode, we bail
+	 */
+	if ((bus->cur_bus_speed > adapter_speed) && (!ctrl->pcix_speed_capability))
+		return 1;
+
+	/* But we allow the adapter to run at a lower rate if possible */
+	if ((bus->cur_bus_speed < adapter_speed) && (!ctrl->pcix_speed_capability))
+		return 0;
+
+	/* We try to set the max speed supported by both the adapter and
+	 * controller
+	 */
+	if (bus->max_bus_speed < adapter_speed) {
+		if (bus->cur_bus_speed == bus->max_bus_speed)
+			return 0;
+		adapter_speed = bus->max_bus_speed;
+	}
+
+	writel(0x0L, ctrl->hpc_reg + LED_CONTROL);
+	writeb(0x00, ctrl->hpc_reg + SLOT_ENABLE);
+
+	set_SOGO(ctrl);
+	wait_for_ctrl_irq(ctrl);
+
+	if (adapter_speed != PCI_SPEED_133MHz_PCIX)
+		reg = 0xF5;
+	else
+		reg = 0xF4;
+	pci_write_config_byte(ctrl->pci_dev, 0x41, reg);
+
+	reg16 = readw(ctrl->hpc_reg + NEXT_CURR_FREQ);
+	reg16 &= ~0x000F;
+	switch(adapter_speed) {
+		case(PCI_SPEED_133MHz_PCIX):
+			reg = 0x75;
+			reg16 |= 0xB;
+			break;
+		case(PCI_SPEED_100MHz_PCIX):
+			reg = 0x74;
+			reg16 |= 0xA;
+			break;
+		case(PCI_SPEED_66MHz_PCIX):
+			reg = 0x73;
+			reg16 |= 0x9;
+			break;
+		case(PCI_SPEED_66MHz):
+			reg = 0x73;
+			reg16 |= 0x1;
+			break;
+		default: /* 33MHz PCI 2.2 */
+			reg = 0x71;
+			break;
+
+	}
+	reg16 |= 0xB << 12;
+	writew(reg16, ctrl->hpc_reg + NEXT_CURR_FREQ);
+
+	mdelay(5);
+
+	/* Reenable interrupts */
+	writel(0, ctrl->hpc_reg + INT_MASK);
+
+	pci_write_config_byte(ctrl->pci_dev, 0x41, reg);
+
+	/* Restart state machine */
+	reg = ~0xF;
+	pci_read_config_byte(ctrl->pci_dev, 0x43, &reg);
+	pci_write_config_byte(ctrl->pci_dev, 0x43, reg);
+
+	/* Only if mode change...*/
+	if (((bus->cur_bus_speed == PCI_SPEED_66MHz) && (adapter_speed == PCI_SPEED_66MHz_PCIX)) ||
+		((bus->cur_bus_speed == PCI_SPEED_66MHz_PCIX) && (adapter_speed == PCI_SPEED_66MHz))) 
+			set_SOGO(ctrl);
+
+	wait_for_ctrl_irq(ctrl);
+	mdelay(1100);
+
+	/* Restore LED/Slot state */
+	writel(leds, ctrl->hpc_reg + LED_CONTROL);
+	writeb(slot_power, ctrl->hpc_reg + SLOT_ENABLE);
+
+	set_SOGO(ctrl);
+	wait_for_ctrl_irq(ctrl);
+
+	bus->cur_bus_speed = adapter_speed;
+	slot = cpqhp_find_slot(ctrl, hp_slot + ctrl->slot_device_offset);
+
+	info("Successfully changed frequency/mode for adapter in slot %d\n",
+			slot->number);
+	return 0;
+}
+
+/* the following routines constitute the bulk of the
+ * hotplug controller logic
+ */
+
+
+/**
+ * board_replaced - Called after a board has been replaced in the system.
+ * @func: PCI device/function information
+ * @ctrl: hotplug controller
+ *
+ * This is only used if we don't have resources for hot add.
+ * Turns power on for the board.
+ * Checks to see if board is the same.
+ * If board is same, reconfigures it.
+ * If board isn't same, turns it back off.
+ */
+static u32 board_replaced(struct pci_func *func, struct controller *ctrl)
+{
+	struct pci_bus *bus = ctrl->pci_bus;
+	u8 hp_slot;
+	u8 temp_byte;
+	u8 adapter_speed;
+	u32 rc = 0;
+
+	hp_slot = func->device - ctrl->slot_device_offset;
+
+	/*
+	 * The switch is open.
+	 */
+	if (readl(ctrl->hpc_reg + INT_INPUT_CLEAR) & (0x01L << hp_slot))
+		rc = INTERLOCK_OPEN;
+	/*
+	 * The board is already on
+	 */
+	else if (is_slot_enabled (ctrl, hp_slot))
+		rc = CARD_FUNCTIONING;
+	else {
+		mutex_lock(&ctrl->crit_sect);
+
+		/* turn on board without attaching to the bus */
+		enable_slot_power (ctrl, hp_slot);
+
+		set_SOGO(ctrl);
+
+		/* Wait for SOBS to be unset */
+		wait_for_ctrl_irq (ctrl);
+
+		/* Change bits in slot power register to force another shift out
+		 * NOTE: this is to work around the timer bug */
+		temp_byte = readb(ctrl->hpc_reg + SLOT_POWER);
+		writeb(0x00, ctrl->hpc_reg + SLOT_POWER);
+		writeb(temp_byte, ctrl->hpc_reg + SLOT_POWER);
+
+		set_SOGO(ctrl);
+
+		/* Wait for SOBS to be unset */
+		wait_for_ctrl_irq (ctrl);
+
+		adapter_speed = get_adapter_speed(ctrl, hp_slot);
+		if (bus->cur_bus_speed != adapter_speed)
+			if (set_controller_speed(ctrl, adapter_speed, hp_slot))
+				rc = WRONG_BUS_FREQUENCY;
+
+		/* turn off board without attaching to the bus */
+		disable_slot_power (ctrl, hp_slot);
+
+		set_SOGO(ctrl);
+
+		/* Wait for SOBS to be unset */
+		wait_for_ctrl_irq (ctrl);
+
+		mutex_unlock(&ctrl->crit_sect);
+
+		if (rc)
+			return rc;
+
+		mutex_lock(&ctrl->crit_sect);
+
+		slot_enable (ctrl, hp_slot);
+		green_LED_blink (ctrl, hp_slot);
+
+		amber_LED_off (ctrl, hp_slot);
+
+		set_SOGO(ctrl);
+
+		/* Wait for SOBS to be unset */
+		wait_for_ctrl_irq (ctrl);
+
+		mutex_unlock(&ctrl->crit_sect);
+
+		/* Wait for ~1 second because of hot plug spec */
+		long_delay(1*HZ);
+
+		/* Check for a power fault */
+		if (func->status == 0xFF) {
+			/* power fault occurred, but it was benign */
+			rc = POWER_FAILURE;
+			func->status = 0;
+		} else
+			rc = cpqhp_valid_replace(ctrl, func);
+
+		if (!rc) {
+			/* It must be the same board */
+
+			rc = cpqhp_configure_board(ctrl, func);
+
+			/* If configuration fails, turn it off
+			 * Get slot won't work for devices behind
+			 * bridges, but in this case it will always be
+			 * called for the "base" bus/dev/func of an
+			 * adapter.
+			 */
+
+			mutex_lock(&ctrl->crit_sect);
+
+			amber_LED_on (ctrl, hp_slot);
+			green_LED_off (ctrl, hp_slot);
+			slot_disable (ctrl, hp_slot);
+
+			set_SOGO(ctrl);
+
+			/* Wait for SOBS to be unset */
+			wait_for_ctrl_irq (ctrl);
+
+			mutex_unlock(&ctrl->crit_sect);
+
+			if (rc)
+				return rc;
+			else
+				return 1;
+
+		} else {
+			/* Something is wrong
+
+			 * Get slot won't work for devices behind bridges, but
+			 * in this case it will always be called for the "base"
+			 * bus/dev/func of an adapter.
+			 */
+
+			mutex_lock(&ctrl->crit_sect);
+
+			amber_LED_on (ctrl, hp_slot);
+			green_LED_off (ctrl, hp_slot);
+			slot_disable (ctrl, hp_slot);
+
+			set_SOGO(ctrl);
+
+			/* Wait for SOBS to be unset */
+			wait_for_ctrl_irq (ctrl);
+
+			mutex_unlock(&ctrl->crit_sect);
+		}
+
+	}
+	return rc;
+
+}
+
+
+/**
+ * board_added - Called after a board has been added to the system.
+ * @func: PCI device/function info
+ * @ctrl: hotplug controller
+ *
+ * Turns power on for the board.
+ * Configures board.
+ */
+static u32 board_added(struct pci_func *func, struct controller *ctrl)
+{
+	u8 hp_slot;
+	u8 temp_byte;
+	u8 adapter_speed;
+	int index;
+	u32 temp_register = 0xFFFFFFFF;
+	u32 rc = 0;
+	struct pci_func *new_slot = NULL;
+	struct pci_bus *bus = ctrl->pci_bus;
+	struct slot *p_slot;
+	struct resource_lists res_lists;
+
+	hp_slot = func->device - ctrl->slot_device_offset;
+	dbg("%s: func->device, slot_offset, hp_slot = %d, %d ,%d\n",
+	    __func__, func->device, ctrl->slot_device_offset, hp_slot);
+
+	mutex_lock(&ctrl->crit_sect);
+
+	/* turn on board without attaching to the bus */
+	enable_slot_power(ctrl, hp_slot);
+
+	set_SOGO(ctrl);
+
+	/* Wait for SOBS to be unset */
+	wait_for_ctrl_irq (ctrl);
+
+	/* Change bits in slot power register to force another shift out
+	 * NOTE: this is to work around the timer bug
+	 */
+	temp_byte = readb(ctrl->hpc_reg + SLOT_POWER);
+	writeb(0x00, ctrl->hpc_reg + SLOT_POWER);
+	writeb(temp_byte, ctrl->hpc_reg + SLOT_POWER);
+
+	set_SOGO(ctrl);
+
+	/* Wait for SOBS to be unset */
+	wait_for_ctrl_irq (ctrl);
+
+	adapter_speed = get_adapter_speed(ctrl, hp_slot);
+	if (bus->cur_bus_speed != adapter_speed)
+		if (set_controller_speed(ctrl, adapter_speed, hp_slot))
+			rc = WRONG_BUS_FREQUENCY;
+
+	/* turn off board without attaching to the bus */
+	disable_slot_power (ctrl, hp_slot);
+
+	set_SOGO(ctrl);
+
+	/* Wait for SOBS to be unset */
+	wait_for_ctrl_irq(ctrl);
+
+	mutex_unlock(&ctrl->crit_sect);
+
+	if (rc)
+		return rc;
+
+	p_slot = cpqhp_find_slot(ctrl, hp_slot + ctrl->slot_device_offset);
+
+	/* turn on board and blink green LED */
+
+	dbg("%s: before down\n", __func__);
+	mutex_lock(&ctrl->crit_sect);
+	dbg("%s: after down\n", __func__);
+
+	dbg("%s: before slot_enable\n", __func__);
+	slot_enable (ctrl, hp_slot);
+
+	dbg("%s: before green_LED_blink\n", __func__);
+	green_LED_blink (ctrl, hp_slot);
+
+	dbg("%s: before amber_LED_blink\n", __func__);
+	amber_LED_off (ctrl, hp_slot);
+
+	dbg("%s: before set_SOGO\n", __func__);
+	set_SOGO(ctrl);
+
+	/* Wait for SOBS to be unset */
+	dbg("%s: before wait_for_ctrl_irq\n", __func__);
+	wait_for_ctrl_irq (ctrl);
+	dbg("%s: after wait_for_ctrl_irq\n", __func__);
+
+	dbg("%s: before up\n", __func__);
+	mutex_unlock(&ctrl->crit_sect);
+	dbg("%s: after up\n", __func__);
+
+	/* Wait for ~1 second because of hot plug spec */
+	dbg("%s: before long_delay\n", __func__);
+	long_delay(1*HZ);
+	dbg("%s: after long_delay\n", __func__);
+
+	dbg("%s: func status = %x\n", __func__, func->status);
+	/* Check for a power fault */
+	if (func->status == 0xFF) {
+		/* power fault occurred, but it was benign */
+		temp_register = 0xFFFFFFFF;
+		dbg("%s: temp register set to %x by power fault\n", __func__, temp_register);
+		rc = POWER_FAILURE;
+		func->status = 0;
+	} else {
+		/* Get vendor/device ID u32 */
+		ctrl->pci_bus->number = func->bus;
+		rc = pci_bus_read_config_dword (ctrl->pci_bus, PCI_DEVFN(func->device, func->function), PCI_VENDOR_ID, &temp_register);
+		dbg("%s: pci_read_config_dword returns %d\n", __func__, rc);
+		dbg("%s: temp_register is %x\n", __func__, temp_register);
+
+		if (rc != 0) {
+			/* Something's wrong here */
+			temp_register = 0xFFFFFFFF;
+			dbg("%s: temp register set to %x by error\n", __func__, temp_register);
+		}
+		/* Preset return code.  It will be changed later if things go okay. */
+		rc = NO_ADAPTER_PRESENT;
+	}
+
+	/* All F's is an empty slot or an invalid board */
+	if (temp_register != 0xFFFFFFFF) {
+		res_lists.io_head = ctrl->io_head;
+		res_lists.mem_head = ctrl->mem_head;
+		res_lists.p_mem_head = ctrl->p_mem_head;
+		res_lists.bus_head = ctrl->bus_head;
+		res_lists.irqs = NULL;
+
+		rc = configure_new_device(ctrl, func, 0, &res_lists);
+
+		dbg("%s: back from configure_new_device\n", __func__);
+		ctrl->io_head = res_lists.io_head;
+		ctrl->mem_head = res_lists.mem_head;
+		ctrl->p_mem_head = res_lists.p_mem_head;
+		ctrl->bus_head = res_lists.bus_head;
+
+		cpqhp_resource_sort_and_combine(&(ctrl->mem_head));
+		cpqhp_resource_sort_and_combine(&(ctrl->p_mem_head));
+		cpqhp_resource_sort_and_combine(&(ctrl->io_head));
+		cpqhp_resource_sort_and_combine(&(ctrl->bus_head));
+
+		if (rc) {
+			mutex_lock(&ctrl->crit_sect);
+
+			amber_LED_on (ctrl, hp_slot);
+			green_LED_off (ctrl, hp_slot);
+			slot_disable (ctrl, hp_slot);
+
+			set_SOGO(ctrl);
+
+			/* Wait for SOBS to be unset */
+			wait_for_ctrl_irq (ctrl);
+
+			mutex_unlock(&ctrl->crit_sect);
+			return rc;
+		} else {
+			cpqhp_save_slot_config(ctrl, func);
+		}
+
+
+		func->status = 0;
+		func->switch_save = 0x10;
+		func->is_a_board = 0x01;
+
+		/* next, we will instantiate the linux pci_dev structures (with
+		 * appropriate driver notification, if already present) */
+		dbg("%s: configure linux pci_dev structure\n", __func__);
+		index = 0;
+		do {
+			new_slot = cpqhp_slot_find(ctrl->bus, func->device, index++);
+			if (new_slot && !new_slot->pci_dev)
+				cpqhp_configure_device(ctrl, new_slot);
+		} while (new_slot);
+
+		mutex_lock(&ctrl->crit_sect);
+
+		green_LED_on (ctrl, hp_slot);
+
+		set_SOGO(ctrl);
+
+		/* Wait for SOBS to be unset */
+		wait_for_ctrl_irq (ctrl);
+
+		mutex_unlock(&ctrl->crit_sect);
+	} else {
+		mutex_lock(&ctrl->crit_sect);
+
+		amber_LED_on (ctrl, hp_slot);
+		green_LED_off (ctrl, hp_slot);
+		slot_disable (ctrl, hp_slot);
+
+		set_SOGO(ctrl);
+
+		/* Wait for SOBS to be unset */
+		wait_for_ctrl_irq (ctrl);
+
+		mutex_unlock(&ctrl->crit_sect);
+
+		return rc;
+	}
+	return 0;
+}
+
+
+/**
+ * remove_board - Turns off slot and LEDs
+ * @func: PCI device/function info
+ * @replace_flag: whether replacing or adding a new device
+ * @ctrl: target controller
+ */
+static u32 remove_board(struct pci_func * func, u32 replace_flag, struct controller * ctrl)
+{
+	int index;
+	u8 skip = 0;
+	u8 device;
+	u8 hp_slot;
+	u8 temp_byte;
+	u32 rc;
+	struct resource_lists res_lists;
+	struct pci_func *temp_func;
+
+	if (cpqhp_unconfigure_device(func))
+		return 1;
+
+	device = func->device;
+
+	hp_slot = func->device - ctrl->slot_device_offset;
+	dbg("In %s, hp_slot = %d\n", __func__, hp_slot);
+
+	/* When we get here, it is safe to change base address registers.
+	 * We will attempt to save the base address register lengths */
+	if (replace_flag || !ctrl->add_support)
+		rc = cpqhp_save_base_addr_length(ctrl, func);
+	else if (!func->bus_head && !func->mem_head &&
+		 !func->p_mem_head && !func->io_head) {
+		/* Here we check to see if we've saved any of the board's
+		 * resources already.  If so, we'll skip the attempt to
+		 * determine what's being used. */
+		index = 0;
+		temp_func = cpqhp_slot_find(func->bus, func->device, index++);
+		while (temp_func) {
+			if (temp_func->bus_head || temp_func->mem_head
+			    || temp_func->p_mem_head || temp_func->io_head) {
+				skip = 1;
+				break;
+			}
+			temp_func = cpqhp_slot_find(temp_func->bus, temp_func->device, index++);
+		}
+
+		if (!skip)
+			rc = cpqhp_save_used_resources(ctrl, func);
+	}
+	/* Change status to shutdown */
+	if (func->is_a_board)
+		func->status = 0x01;
+	func->configured = 0;
+
+	mutex_lock(&ctrl->crit_sect);
+
+	green_LED_off (ctrl, hp_slot);
+	slot_disable (ctrl, hp_slot);
+
+	set_SOGO(ctrl);
+
+	/* turn off SERR for slot */
+	temp_byte = readb(ctrl->hpc_reg + SLOT_SERR);
+	temp_byte &= ~(0x01 << hp_slot);
+	writeb(temp_byte, ctrl->hpc_reg + SLOT_SERR);
+
+	/* Wait for SOBS to be unset */
+	wait_for_ctrl_irq (ctrl);
+
+	mutex_unlock(&ctrl->crit_sect);
+
+	if (!replace_flag && ctrl->add_support) {
+		while (func) {
+			res_lists.io_head = ctrl->io_head;
+			res_lists.mem_head = ctrl->mem_head;
+			res_lists.p_mem_head = ctrl->p_mem_head;
+			res_lists.bus_head = ctrl->bus_head;
+
+			cpqhp_return_board_resources(func, &res_lists);
+
+			ctrl->io_head = res_lists.io_head;
+			ctrl->mem_head = res_lists.mem_head;
+			ctrl->p_mem_head = res_lists.p_mem_head;
+			ctrl->bus_head = res_lists.bus_head;
+
+			cpqhp_resource_sort_and_combine(&(ctrl->mem_head));
+			cpqhp_resource_sort_and_combine(&(ctrl->p_mem_head));
+			cpqhp_resource_sort_and_combine(&(ctrl->io_head));
+			cpqhp_resource_sort_and_combine(&(ctrl->bus_head));
+
+			if (is_bridge(func)) {
+				bridge_slot_remove(func);
+			} else
+				slot_remove(func);
+
+			func = cpqhp_slot_find(ctrl->bus, device, 0);
+		}
+
+		/* Setup slot structure with entry for empty slot */
+		func = cpqhp_slot_create(ctrl->bus);
+
+		if (func == NULL)
+			return 1;
+
+		func->bus = ctrl->bus;
+		func->device = device;
+		func->function = 0;
+		func->configured = 0;
+		func->switch_save = 0x10;
+		func->is_a_board = 0;
+		func->p_task_event = NULL;
+	}
+
+	return 0;
+}
+
+static void pushbutton_helper_thread(unsigned long data)
+{
+	pushbutton_pending = data;
+	wake_up_process(cpqhp_event_thread);
+}
+
+
+/* this is the main worker thread */
+static int event_thread(void* data)
+{
+	struct controller *ctrl;
+
+	while (1) {
+		dbg("!!!!event_thread sleeping\n");
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule();
+
+		if (kthread_should_stop())
+			break;
+		/* Do stuff here */
+		if (pushbutton_pending)
+			cpqhp_pushbutton_thread(pushbutton_pending);
+		else
+			for (ctrl = cpqhp_ctrl_list; ctrl; ctrl=ctrl->next)
+				interrupt_event_handler(ctrl);
+	}
+	dbg("event_thread signals exit\n");
+	return 0;
+}
+
+int cpqhp_event_start_thread(void)
+{
+	cpqhp_event_thread = kthread_run(event_thread, NULL, "phpd_event");
+	if (IS_ERR(cpqhp_event_thread)) {
+		err ("Can't start up our event thread\n");
+		return PTR_ERR(cpqhp_event_thread);
+	}
+
+	return 0;
+}
+
+
+void cpqhp_event_stop_thread(void)
+{
+	kthread_stop(cpqhp_event_thread);
+}
+
+
+static int update_slot_info(struct controller *ctrl, struct slot *slot)
+{
+	struct hotplug_slot_info *info;
+	int result;
+
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->power_status = get_slot_enabled(ctrl, slot);
+	info->attention_status = cpq_get_attention_status(ctrl, slot);
+	info->latch_status = cpq_get_latch_status(ctrl, slot);
+	info->adapter_status = get_presence_status(ctrl, slot);
+	result = pci_hp_change_slot_info(slot->hotplug_slot, info);
+	kfree (info);
+	return result;
+}
+
+static void interrupt_event_handler(struct controller *ctrl)
+{
+	int loop = 0;
+	int change = 1;
+	struct pci_func *func;
+	u8 hp_slot;
+	struct slot *p_slot;
+
+	while (change) {
+		change = 0;
+
+		for (loop = 0; loop < 10; loop++) {
+			/* dbg("loop %d\n", loop); */
+			if (ctrl->event_queue[loop].event_type != 0) {
+				hp_slot = ctrl->event_queue[loop].hp_slot;
+
+				func = cpqhp_slot_find(ctrl->bus, (hp_slot + ctrl->slot_device_offset), 0);
+				if (!func)
+					return;
+
+				p_slot = cpqhp_find_slot(ctrl, hp_slot + ctrl->slot_device_offset);
+				if (!p_slot)
+					return;
+
+				dbg("hp_slot %d, func %p, p_slot %p\n",
+				    hp_slot, func, p_slot);
+
+				if (ctrl->event_queue[loop].event_type == INT_BUTTON_PRESS) {
+					dbg("button pressed\n");
+				} else if (ctrl->event_queue[loop].event_type == 
+					   INT_BUTTON_CANCEL) {
+					dbg("button cancel\n");
+					del_timer(&p_slot->task_event);
+
+					mutex_lock(&ctrl->crit_sect);
+
+					if (p_slot->state == BLINKINGOFF_STATE) {
+						/* slot is on */
+						dbg("turn on green LED\n");
+						green_LED_on (ctrl, hp_slot);
+					} else if (p_slot->state == BLINKINGON_STATE) {
+						/* slot is off */
+						dbg("turn off green LED\n");
+						green_LED_off (ctrl, hp_slot);
+					}
+
+					info(msg_button_cancel, p_slot->number);
+
+					p_slot->state = STATIC_STATE;
+
+					amber_LED_off (ctrl, hp_slot);
+
+					set_SOGO(ctrl);
+
+					/* Wait for SOBS to be unset */
+					wait_for_ctrl_irq (ctrl);
+
+					mutex_unlock(&ctrl->crit_sect);
+				}
+				/*** button Released (No action on press...) */
+				else if (ctrl->event_queue[loop].event_type == INT_BUTTON_RELEASE) {
+					dbg("button release\n");
+
+					if (is_slot_enabled (ctrl, hp_slot)) {
+						dbg("slot is on\n");
+						p_slot->state = BLINKINGOFF_STATE;
+						info(msg_button_off, p_slot->number);
+					} else {
+						dbg("slot is off\n");
+						p_slot->state = BLINKINGON_STATE;
+						info(msg_button_on, p_slot->number);
+					}
+					mutex_lock(&ctrl->crit_sect);
+
+					dbg("blink green LED and turn off amber\n");
+
+					amber_LED_off (ctrl, hp_slot);
+					green_LED_blink (ctrl, hp_slot);
+
+					set_SOGO(ctrl);
+
+					/* Wait for SOBS to be unset */
+					wait_for_ctrl_irq (ctrl);
+
+					mutex_unlock(&ctrl->crit_sect);
+					init_timer(&p_slot->task_event);
+					p_slot->hp_slot = hp_slot;
+					p_slot->ctrl = ctrl;
+/*					p_slot->physical_slot = physical_slot; */
+					p_slot->task_event.expires = jiffies + 5 * HZ;   /* 5 second delay */
+					p_slot->task_event.function = pushbutton_helper_thread;
+					p_slot->task_event.data = (u32) p_slot;
+
+					dbg("add_timer p_slot = %p\n", p_slot);
+					add_timer(&p_slot->task_event);
+				}
+				/***********POWER FAULT */
+				else if (ctrl->event_queue[loop].event_type == INT_POWER_FAULT) {
+					dbg("power fault\n");
+				} else {
+					/* refresh notification */
+					if (p_slot)
+						update_slot_info(ctrl, p_slot);
+				}
+
+				ctrl->event_queue[loop].event_type = 0;
+
+				change = 1;
+			}
+		}		/* End of FOR loop */
+	}
+
+	return;
+}
+
+
+/**
+ * cpqhp_pushbutton_thread - handle pushbutton events
+ * @slot: target slot (struct)
+ *
+ * Scheduled procedure to handle blocking stuff for the pushbuttons.
+ * Handles all pending events and exits.
+ */
+void cpqhp_pushbutton_thread(unsigned long slot)
+{
+	u8 hp_slot;
+	u8 device;
+	struct pci_func *func;
+	struct slot *p_slot = (struct slot *) slot;
+	struct controller *ctrl = (struct controller *) p_slot->ctrl;
+
+	pushbutton_pending = 0;
+	hp_slot = p_slot->hp_slot;
+
+	device = p_slot->device;
+
+	if (is_slot_enabled(ctrl, hp_slot)) {
+		p_slot->state = POWEROFF_STATE;
+		/* power Down board */
+		func = cpqhp_slot_find(p_slot->bus, p_slot->device, 0);
+		dbg("In power_down_board, func = %p, ctrl = %p\n", func, ctrl);
+		if (!func) {
+			dbg("Error! func NULL in %s\n", __func__);
+			return ;
+		}
+
+		if (cpqhp_process_SS(ctrl, func) != 0) {
+			amber_LED_on(ctrl, hp_slot);
+			green_LED_on(ctrl, hp_slot);
+
+			set_SOGO(ctrl);
+
+			/* Wait for SOBS to be unset */
+			wait_for_ctrl_irq(ctrl);
+		}
+
+		p_slot->state = STATIC_STATE;
+	} else {
+		p_slot->state = POWERON_STATE;
+		/* slot is off */
+
+		func = cpqhp_slot_find(p_slot->bus, p_slot->device, 0);
+		dbg("In add_board, func = %p, ctrl = %p\n", func, ctrl);
+		if (!func) {
+			dbg("Error! func NULL in %s\n", __func__);
+			return ;
+		}
+
+		if (ctrl != NULL) {
+			if (cpqhp_process_SI(ctrl, func) != 0) {
+				amber_LED_on(ctrl, hp_slot);
+				green_LED_off(ctrl, hp_slot);
+
+				set_SOGO(ctrl);
+
+				/* Wait for SOBS to be unset */
+				wait_for_ctrl_irq (ctrl);
+			}
+		}
+
+		p_slot->state = STATIC_STATE;
+	}
+
+	return;
+}
+
+
+int cpqhp_process_SI(struct controller *ctrl, struct pci_func *func)
+{
+	u8 device, hp_slot;
+	u16 temp_word;
+	u32 tempdword;
+	int rc;
+	struct slot* p_slot;
+	int physical_slot = 0;
+
+	tempdword = 0;
+
+	device = func->device;
+	hp_slot = device - ctrl->slot_device_offset;
+	p_slot = cpqhp_find_slot(ctrl, device);
+	if (p_slot)
+		physical_slot = p_slot->number;
+
+	/* Check to see if the interlock is closed */
+	tempdword = readl(ctrl->hpc_reg + INT_INPUT_CLEAR);
+
+	if (tempdword & (0x01 << hp_slot)) {
+		return 1;
+	}
+
+	if (func->is_a_board) {
+		rc = board_replaced(func, ctrl);
+	} else {
+		/* add board */
+		slot_remove(func);
+
+		func = cpqhp_slot_create(ctrl->bus);
+		if (func == NULL)
+			return 1;
+
+		func->bus = ctrl->bus;
+		func->device = device;
+		func->function = 0;
+		func->configured = 0;
+		func->is_a_board = 1;
+
+		/* We have to save the presence info for these slots */
+		temp_word = ctrl->ctrl_int_comp >> 16;
+		func->presence_save = (temp_word >> hp_slot) & 0x01;
+		func->presence_save |= (temp_word >> (hp_slot + 7)) & 0x02;
+
+		if (ctrl->ctrl_int_comp & (0x1L << hp_slot)) {
+			func->switch_save = 0;
+		} else {
+			func->switch_save = 0x10;
+		}
+
+		rc = board_added(func, ctrl);
+		if (rc) {
+			if (is_bridge(func)) {
+				bridge_slot_remove(func);
+			} else
+				slot_remove(func);
+
+			/* Setup slot structure with entry for empty slot */
+			func = cpqhp_slot_create(ctrl->bus);
+
+			if (func == NULL)
+				return 1;
+
+			func->bus = ctrl->bus;
+			func->device = device;
+			func->function = 0;
+			func->configured = 0;
+			func->is_a_board = 0;
+
+			/* We have to save the presence info for these slots */
+			temp_word = ctrl->ctrl_int_comp >> 16;
+			func->presence_save = (temp_word >> hp_slot) & 0x01;
+			func->presence_save |=
+			(temp_word >> (hp_slot + 7)) & 0x02;
+
+			if (ctrl->ctrl_int_comp & (0x1L << hp_slot)) {
+				func->switch_save = 0;
+			} else {
+				func->switch_save = 0x10;
+			}
+		}
+	}
+
+	if (rc) {
+		dbg("%s: rc = %d\n", __func__, rc);
+	}
+
+	if (p_slot)
+		update_slot_info(ctrl, p_slot);
+
+	return rc;
+}
+
+
+int cpqhp_process_SS(struct controller *ctrl, struct pci_func *func)
+{
+	u8 device, class_code, header_type, BCR;
+	u8 index = 0;
+	u8 replace_flag;
+	u32 rc = 0;
+	unsigned int devfn;
+	struct slot* p_slot;
+	struct pci_bus *pci_bus = ctrl->pci_bus;
+	int physical_slot=0;
+
+	device = func->device;
+	func = cpqhp_slot_find(ctrl->bus, device, index++);
+	p_slot = cpqhp_find_slot(ctrl, device);
+	if (p_slot) {
+		physical_slot = p_slot->number;
+	}
+
+	/* Make sure there are no video controllers here */
+	while (func && !rc) {
+		pci_bus->number = func->bus;
+		devfn = PCI_DEVFN(func->device, func->function);
+
+		/* Check the Class Code */
+		rc = pci_bus_read_config_byte (pci_bus, devfn, 0x0B, &class_code);
+		if (rc)
+			return rc;
+
+		if (class_code == PCI_BASE_CLASS_DISPLAY) {
+			/* Display/Video adapter (not supported) */
+			rc = REMOVE_NOT_SUPPORTED;
+		} else {
+			/* See if it's a bridge */
+			rc = pci_bus_read_config_byte (pci_bus, devfn, PCI_HEADER_TYPE, &header_type);
+			if (rc)
+				return rc;
+
+			/* If it's a bridge, check the VGA Enable bit */
+			if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE) {
+				rc = pci_bus_read_config_byte (pci_bus, devfn, PCI_BRIDGE_CONTROL, &BCR);
+				if (rc)
+					return rc;
+
+				/* If the VGA Enable bit is set, remove isn't
+				 * supported */
+				if (BCR & PCI_BRIDGE_CTL_VGA)
+					rc = REMOVE_NOT_SUPPORTED;
+			}
+		}
+
+		func = cpqhp_slot_find(ctrl->bus, device, index++);
+	}
+
+	func = cpqhp_slot_find(ctrl->bus, device, 0);
+	if ((func != NULL) && !rc) {
+		/* FIXME: Replace flag should be passed into process_SS */
+		replace_flag = !(ctrl->add_support);
+		rc = remove_board(func, replace_flag, ctrl);
+	} else if (!rc) {
+		rc = 1;
+	}
+
+	if (p_slot)
+		update_slot_info(ctrl, p_slot);
+
+	return rc;
+}
+
+/**
+ * switch_leds - switch the leds, go from one site to the other.
+ * @ctrl: controller to use
+ * @num_of_slots: number of slots to use
+ * @work_LED: LED control value
+ * @direction: 1 to start from the left side, 0 to start right.
+ */
+static void switch_leds(struct controller *ctrl, const int num_of_slots,
+			u32 *work_LED, const int direction)
+{
+	int loop;
+
+	for (loop = 0; loop < num_of_slots; loop++) {
+		if (direction)
+			*work_LED = *work_LED >> 1;
+		else
+			*work_LED = *work_LED << 1;
+		writel(*work_LED, ctrl->hpc_reg + LED_CONTROL);
+
+		set_SOGO(ctrl);
+
+		/* Wait for SOGO interrupt */
+		wait_for_ctrl_irq(ctrl);
+
+		/* Get ready for next iteration */
+		long_delay((2*HZ)/10);
+	}
+}
+
+/**
+ * cpqhp_hardware_test - runs hardware tests
+ * @ctrl: target controller
+ * @test_num: the number written to the "test" file in sysfs.
+ *
+ * For hot plug ctrl folks to play with.
+ */
+int cpqhp_hardware_test(struct controller *ctrl, int test_num)
+{
+	u32 save_LED;
+	u32 work_LED;
+	int loop;
+	int num_of_slots;
+
+	num_of_slots = readb(ctrl->hpc_reg + SLOT_MASK) & 0x0f;
+
+	switch (test_num) {
+	case 1:
+		/* Do stuff here! */
+
+		/* Do that funky LED thing */
+		/* so we can restore them later */
+		save_LED = readl(ctrl->hpc_reg + LED_CONTROL);
+		work_LED = 0x01010101;
+		switch_leds(ctrl, num_of_slots, &work_LED, 0);
+		switch_leds(ctrl, num_of_slots, &work_LED, 1);
+		switch_leds(ctrl, num_of_slots, &work_LED, 0);
+		switch_leds(ctrl, num_of_slots, &work_LED, 1);
+
+		work_LED = 0x01010000;
+		writel(work_LED, ctrl->hpc_reg + LED_CONTROL);
+		switch_leds(ctrl, num_of_slots, &work_LED, 0);
+		switch_leds(ctrl, num_of_slots, &work_LED, 1);
+		work_LED = 0x00000101;
+		writel(work_LED, ctrl->hpc_reg + LED_CONTROL);
+		switch_leds(ctrl, num_of_slots, &work_LED, 0);
+		switch_leds(ctrl, num_of_slots, &work_LED, 1);
+
+		work_LED = 0x01010000;
+		writel(work_LED, ctrl->hpc_reg + LED_CONTROL);
+		for (loop = 0; loop < num_of_slots; loop++) {
+			set_SOGO(ctrl);
+
+			/* Wait for SOGO interrupt */
+			wait_for_ctrl_irq (ctrl);
+
+			/* Get ready for next iteration */
+			long_delay((3*HZ)/10);
+			work_LED = work_LED >> 16;
+			writel(work_LED, ctrl->hpc_reg + LED_CONTROL);
+
+			set_SOGO(ctrl);
+
+			/* Wait for SOGO interrupt */
+			wait_for_ctrl_irq (ctrl);
+
+			/* Get ready for next iteration */
+			long_delay((3*HZ)/10);
+			work_LED = work_LED << 16;
+			writel(work_LED, ctrl->hpc_reg + LED_CONTROL);
+			work_LED = work_LED << 1;
+			writel(work_LED, ctrl->hpc_reg + LED_CONTROL);
+		}
+
+		/* put it back the way it was */
+		writel(save_LED, ctrl->hpc_reg + LED_CONTROL);
+
+		set_SOGO(ctrl);
+
+		/* Wait for SOBS to be unset */
+		wait_for_ctrl_irq (ctrl);
+		break;
+	case 2:
+		/* Do other stuff here! */
+		break;
+	case 3:
+		/* and more... */
+		break;
+	}
+	return 0;
+}
+
+
+/**
+ * configure_new_device - Configures the PCI header information of one board.
+ * @ctrl: pointer to controller structure
+ * @func: pointer to function structure
+ * @behind_bridge: 1 if this is a recursive call, 0 if not
+ * @resources: pointer to set of resource lists
+ *
+ * Returns 0 if success.
+ */
+static u32 configure_new_device(struct controller * ctrl, struct pci_func * func,
+				 u8 behind_bridge, struct resource_lists * resources)
+{
+	u8 temp_byte, function, max_functions, stop_it;
+	int rc;
+	u32 ID;
+	struct pci_func *new_slot;
+	int index;
+
+	new_slot = func;
+
+	dbg("%s\n", __func__);
+	/* Check for Multi-function device */
+	ctrl->pci_bus->number = func->bus;
+	rc = pci_bus_read_config_byte (ctrl->pci_bus, PCI_DEVFN(func->device, func->function), 0x0E, &temp_byte);
+	if (rc) {
+		dbg("%s: rc = %d\n", __func__, rc);
+		return rc;
+	}
+
+	if (temp_byte & 0x80)	/* Multi-function device */
+		max_functions = 8;
+	else
+		max_functions = 1;
+
+	function = 0;
+
+	do {
+		rc = configure_new_function(ctrl, new_slot, behind_bridge, resources);
+
+		if (rc) {
+			dbg("configure_new_function failed %d\n",rc);
+			index = 0;
+
+			while (new_slot) {
+				new_slot = cpqhp_slot_find(new_slot->bus, new_slot->device, index++);
+
+				if (new_slot)
+					cpqhp_return_board_resources(new_slot, resources);
+			}
+
+			return rc;
+		}
+
+		function++;
+
+		stop_it = 0;
+
+		/* The following loop skips to the next present function
+		 * and creates a board structure */
+
+		while ((function < max_functions) && (!stop_it)) {
+			pci_bus_read_config_dword (ctrl->pci_bus, PCI_DEVFN(func->device, function), 0x00, &ID);
+
+			if (ID == 0xFFFFFFFF) {
+				function++;
+			} else {
+				/* Setup slot structure. */
+				new_slot = cpqhp_slot_create(func->bus);
+
+				if (new_slot == NULL)
+					return 1;
+
+				new_slot->bus = func->bus;
+				new_slot->device = func->device;
+				new_slot->function = function;
+				new_slot->is_a_board = 1;
+				new_slot->status = 0;
+
+				stop_it++;
+			}
+		}
+
+	} while (function < max_functions);
+	dbg("returning from configure_new_device\n");
+
+	return 0;
+}
+
+
+/*
+ * Configuration logic that involves the hotplug data structures and
+ * their bookkeeping
+ */
+
+
+/**
+ * configure_new_function - Configures the PCI header information of one device
+ * @ctrl: pointer to controller structure
+ * @func: pointer to function structure
+ * @behind_bridge: 1 if this is a recursive call, 0 if not
+ * @resources: pointer to set of resource lists
+ *
+ * Calls itself recursively for bridged devices.
+ * Returns 0 if success.
+ */
+static int configure_new_function(struct controller *ctrl, struct pci_func *func,
+				   u8 behind_bridge,
+				   struct resource_lists *resources)
+{
+	int cloop;
+	u8 IRQ = 0;
+	u8 temp_byte;
+	u8 device;
+	u8 class_code;
+	u16 command;
+	u16 temp_word;
+	u32 temp_dword;
+	u32 rc;
+	u32 temp_register;
+	u32 base;
+	u32 ID;
+	unsigned int devfn;
+	struct pci_resource *mem_node;
+	struct pci_resource *p_mem_node;
+	struct pci_resource *io_node;
+	struct pci_resource *bus_node;
+	struct pci_resource *hold_mem_node;
+	struct pci_resource *hold_p_mem_node;
+	struct pci_resource *hold_IO_node;
+	struct pci_resource *hold_bus_node;
+	struct irq_mapping irqs;
+	struct pci_func *new_slot;
+	struct pci_bus *pci_bus;
+	struct resource_lists temp_resources;
+
+	pci_bus = ctrl->pci_bus;
+	pci_bus->number = func->bus;
+	devfn = PCI_DEVFN(func->device, func->function);
+
+	/* Check for Bridge */
+	rc = pci_bus_read_config_byte(pci_bus, devfn, PCI_HEADER_TYPE, &temp_byte);
+	if (rc)
+		return rc;
+
+	if ((temp_byte & 0x7F) == PCI_HEADER_TYPE_BRIDGE) {
+		/* set Primary bus */
+		dbg("set Primary bus = %d\n", func->bus);
+		rc = pci_bus_write_config_byte(pci_bus, devfn, PCI_PRIMARY_BUS, func->bus);
+		if (rc)
+			return rc;
+
+		/* find range of busses to use */
+		dbg("find ranges of buses to use\n");
+		bus_node = get_max_resource(&(resources->bus_head), 1);
+
+		/* If we don't have any busses to allocate, we can't continue */
+		if (!bus_node)
+			return -ENOMEM;
+
+		/* set Secondary bus */
+		temp_byte = bus_node->base;
+		dbg("set Secondary bus = %d\n", bus_node->base);
+		rc = pci_bus_write_config_byte(pci_bus, devfn, PCI_SECONDARY_BUS, temp_byte);
+		if (rc)
+			return rc;
+
+		/* set subordinate bus */
+		temp_byte = bus_node->base + bus_node->length - 1;
+		dbg("set subordinate bus = %d\n", bus_node->base + bus_node->length - 1);
+		rc = pci_bus_write_config_byte(pci_bus, devfn, PCI_SUBORDINATE_BUS, temp_byte);
+		if (rc)
+			return rc;
+
+		/* set subordinate Latency Timer and base Latency Timer */
+		temp_byte = 0x40;
+		rc = pci_bus_write_config_byte(pci_bus, devfn, PCI_SEC_LATENCY_TIMER, temp_byte);
+		if (rc)
+			return rc;
+		rc = pci_bus_write_config_byte(pci_bus, devfn, PCI_LATENCY_TIMER, temp_byte);
+		if (rc)
+			return rc;
+
+		/* set Cache Line size */
+		temp_byte = 0x08;
+		rc = pci_bus_write_config_byte(pci_bus, devfn, PCI_CACHE_LINE_SIZE, temp_byte);
+		if (rc)
+			return rc;
+
+		/* Setup the IO, memory, and prefetchable windows */
+		io_node = get_max_resource(&(resources->io_head), 0x1000);
+		if (!io_node)
+			return -ENOMEM;
+		mem_node = get_max_resource(&(resources->mem_head), 0x100000);
+		if (!mem_node)
+			return -ENOMEM;
+		p_mem_node = get_max_resource(&(resources->p_mem_head), 0x100000);
+		if (!p_mem_node)
+			return -ENOMEM;
+		dbg("Setup the IO, memory, and prefetchable windows\n");
+		dbg("io_node\n");
+		dbg("(base, len, next) (%x, %x, %p)\n", io_node->base,
+					io_node->length, io_node->next);
+		dbg("mem_node\n");
+		dbg("(base, len, next) (%x, %x, %p)\n", mem_node->base,
+					mem_node->length, mem_node->next);
+		dbg("p_mem_node\n");
+		dbg("(base, len, next) (%x, %x, %p)\n", p_mem_node->base,
+					p_mem_node->length, p_mem_node->next);
+
+		/* set up the IRQ info */
+		if (!resources->irqs) {
+			irqs.barber_pole = 0;
+			irqs.interrupt[0] = 0;
+			irqs.interrupt[1] = 0;
+			irqs.interrupt[2] = 0;
+			irqs.interrupt[3] = 0;
+			irqs.valid_INT = 0;
+		} else {
+			irqs.barber_pole = resources->irqs->barber_pole;
+			irqs.interrupt[0] = resources->irqs->interrupt[0];
+			irqs.interrupt[1] = resources->irqs->interrupt[1];
+			irqs.interrupt[2] = resources->irqs->interrupt[2];
+			irqs.interrupt[3] = resources->irqs->interrupt[3];
+			irqs.valid_INT = resources->irqs->valid_INT;
+		}
+
+		/* set up resource lists that are now aligned on top and bottom
+		 * for anything behind the bridge. */
+		temp_resources.bus_head = bus_node;
+		temp_resources.io_head = io_node;
+		temp_resources.mem_head = mem_node;
+		temp_resources.p_mem_head = p_mem_node;
+		temp_resources.irqs = &irqs;
+
+		/* Make copies of the nodes we are going to pass down so that
+		 * if there is a problem,we can just use these to free resources
+		 */
+		hold_bus_node = kmalloc(sizeof(*hold_bus_node), GFP_KERNEL);
+		hold_IO_node = kmalloc(sizeof(*hold_IO_node), GFP_KERNEL);
+		hold_mem_node = kmalloc(sizeof(*hold_mem_node), GFP_KERNEL);
+		hold_p_mem_node = kmalloc(sizeof(*hold_p_mem_node), GFP_KERNEL);
+
+		if (!hold_bus_node || !hold_IO_node || !hold_mem_node || !hold_p_mem_node) {
+			kfree(hold_bus_node);
+			kfree(hold_IO_node);
+			kfree(hold_mem_node);
+			kfree(hold_p_mem_node);
+
+			return 1;
+		}
+
+		memcpy(hold_bus_node, bus_node, sizeof(struct pci_resource));
+
+		bus_node->base += 1;
+		bus_node->length -= 1;
+		bus_node->next = NULL;
+
+		/* If we have IO resources copy them and fill in the bridge's
+		 * IO range registers */
+		if (io_node) {
+			memcpy(hold_IO_node, io_node, sizeof(struct pci_resource));
+			io_node->next = NULL;
+
+			/* set IO base and Limit registers */
+			temp_byte = io_node->base >> 8;
+			rc = pci_bus_write_config_byte(pci_bus, devfn, PCI_IO_BASE, temp_byte);
+
+			temp_byte = (io_node->base + io_node->length - 1) >> 8;
+			rc = pci_bus_write_config_byte(pci_bus, devfn, PCI_IO_LIMIT, temp_byte);
+		} else {
+			kfree(hold_IO_node);
+			hold_IO_node = NULL;
+		}
+
+		/* If we have memory resources copy them and fill in the
+		 * bridge's memory range registers.  Otherwise, fill in the
+		 * range registers with values that disable them. */
+		if (mem_node) {
+			memcpy(hold_mem_node, mem_node, sizeof(struct pci_resource));
+			mem_node->next = NULL;
+
+			/* set Mem base and Limit registers */
+			temp_word = mem_node->base >> 16;
+			rc = pci_bus_write_config_word(pci_bus, devfn, PCI_MEMORY_BASE, temp_word);
+
+			temp_word = (mem_node->base + mem_node->length - 1) >> 16;
+			rc = pci_bus_write_config_word(pci_bus, devfn, PCI_MEMORY_LIMIT, temp_word);
+		} else {
+			temp_word = 0xFFFF;
+			rc = pci_bus_write_config_word(pci_bus, devfn, PCI_MEMORY_BASE, temp_word);
+
+			temp_word = 0x0000;
+			rc = pci_bus_write_config_word(pci_bus, devfn, PCI_MEMORY_LIMIT, temp_word);
+
+			kfree(hold_mem_node);
+			hold_mem_node = NULL;
+		}
+
+		memcpy(hold_p_mem_node, p_mem_node, sizeof(struct pci_resource));
+		p_mem_node->next = NULL;
+
+		/* set Pre Mem base and Limit registers */
+		temp_word = p_mem_node->base >> 16;
+		rc = pci_bus_write_config_word (pci_bus, devfn, PCI_PREF_MEMORY_BASE, temp_word);
+
+		temp_word = (p_mem_node->base + p_mem_node->length - 1) >> 16;
+		rc = pci_bus_write_config_word (pci_bus, devfn, PCI_PREF_MEMORY_LIMIT, temp_word);
+
+		/* Adjust this to compensate for extra adjustment in first loop
+		 */
+		irqs.barber_pole--;
+
+		rc = 0;
+
+		/* Here we actually find the devices and configure them */
+		for (device = 0; (device <= 0x1F) && !rc; device++) {
+			irqs.barber_pole = (irqs.barber_pole + 1) & 0x03;
+
+			ID = 0xFFFFFFFF;
+			pci_bus->number = hold_bus_node->base;
+			pci_bus_read_config_dword (pci_bus, PCI_DEVFN(device, 0), 0x00, &ID);
+			pci_bus->number = func->bus;
+
+			if (ID != 0xFFFFFFFF) {	  /*  device present */
+				/* Setup slot structure. */
+				new_slot = cpqhp_slot_create(hold_bus_node->base);
+
+				if (new_slot == NULL) {
+					rc = -ENOMEM;
+					continue;
+				}
+
+				new_slot->bus = hold_bus_node->base;
+				new_slot->device = device;
+				new_slot->function = 0;
+				new_slot->is_a_board = 1;
+				new_slot->status = 0;
+
+				rc = configure_new_device(ctrl, new_slot, 1, &temp_resources);
+				dbg("configure_new_device rc=0x%x\n",rc);
+			}	/* End of IF (device in slot?) */
+		}		/* End of FOR loop */
+
+		if (rc)
+			goto free_and_out;
+		/* save the interrupt routing information */
+		if (resources->irqs) {
+			resources->irqs->interrupt[0] = irqs.interrupt[0];
+			resources->irqs->interrupt[1] = irqs.interrupt[1];
+			resources->irqs->interrupt[2] = irqs.interrupt[2];
+			resources->irqs->interrupt[3] = irqs.interrupt[3];
+			resources->irqs->valid_INT = irqs.valid_INT;
+		} else if (!behind_bridge) {
+			/* We need to hook up the interrupts here */
+			for (cloop = 0; cloop < 4; cloop++) {
+				if (irqs.valid_INT & (0x01 << cloop)) {
+					rc = cpqhp_set_irq(func->bus, func->device,
+							   cloop + 1, irqs.interrupt[cloop]);
+					if (rc)
+						goto free_and_out;
+				}
+			}	/* end of for loop */
+		}
+		/* Return unused bus resources
+		 * First use the temporary node to store information for
+		 * the board */
+		if (hold_bus_node && bus_node && temp_resources.bus_head) {
+			hold_bus_node->length = bus_node->base - hold_bus_node->base;
+
+			hold_bus_node->next = func->bus_head;
+			func->bus_head = hold_bus_node;
+
+			temp_byte = temp_resources.bus_head->base - 1;
+
+			/* set subordinate bus */
+			rc = pci_bus_write_config_byte (pci_bus, devfn, PCI_SUBORDINATE_BUS, temp_byte);
+
+			if (temp_resources.bus_head->length == 0) {
+				kfree(temp_resources.bus_head);
+				temp_resources.bus_head = NULL;
+			} else {
+				return_resource(&(resources->bus_head), temp_resources.bus_head);
+			}
+		}
+
+		/* If we have IO space available and there is some left,
+		 * return the unused portion */
+		if (hold_IO_node && temp_resources.io_head) {
+			io_node = do_pre_bridge_resource_split(&(temp_resources.io_head),
+							       &hold_IO_node, 0x1000);
+
+			/* Check if we were able to split something off */
+			if (io_node) {
+				hold_IO_node->base = io_node->base + io_node->length;
+
+				temp_byte = (hold_IO_node->base) >> 8;
+				rc = pci_bus_write_config_word (pci_bus, devfn, PCI_IO_BASE, temp_byte);
+
+				return_resource(&(resources->io_head), io_node);
+			}
+
+			io_node = do_bridge_resource_split(&(temp_resources.io_head), 0x1000);
+
+			/* Check if we were able to split something off */
+			if (io_node) {
+				/* First use the temporary node to store
+				 * information for the board */
+				hold_IO_node->length = io_node->base - hold_IO_node->base;
+
+				/* If we used any, add it to the board's list */
+				if (hold_IO_node->length) {
+					hold_IO_node->next = func->io_head;
+					func->io_head = hold_IO_node;
+
+					temp_byte = (io_node->base - 1) >> 8;
+					rc = pci_bus_write_config_byte (pci_bus, devfn, PCI_IO_LIMIT, temp_byte);
+
+					return_resource(&(resources->io_head), io_node);
+				} else {
+					/* it doesn't need any IO */
+					temp_word = 0x0000;
+					rc = pci_bus_write_config_word (pci_bus, devfn, PCI_IO_LIMIT, temp_word);
+
+					return_resource(&(resources->io_head), io_node);
+					kfree(hold_IO_node);
+				}
+			} else {
+				/* it used most of the range */
+				hold_IO_node->next = func->io_head;
+				func->io_head = hold_IO_node;
+			}
+		} else if (hold_IO_node) {
+			/* it used the whole range */
+			hold_IO_node->next = func->io_head;
+			func->io_head = hold_IO_node;
+		}
+		/* If we have memory space available and there is some left,
+		 * return the unused portion */
+		if (hold_mem_node && temp_resources.mem_head) {
+			mem_node = do_pre_bridge_resource_split(&(temp_resources.  mem_head),
+								&hold_mem_node, 0x100000);
+
+			/* Check if we were able to split something off */
+			if (mem_node) {
+				hold_mem_node->base = mem_node->base + mem_node->length;
+
+				temp_word = (hold_mem_node->base) >> 16;
+				rc = pci_bus_write_config_word (pci_bus, devfn, PCI_MEMORY_BASE, temp_word);
+
+				return_resource(&(resources->mem_head), mem_node);
+			}
+
+			mem_node = do_bridge_resource_split(&(temp_resources.mem_head), 0x100000);
+
+			/* Check if we were able to split something off */
+			if (mem_node) {
+				/* First use the temporary node to store
+				 * information for the board */
+				hold_mem_node->length = mem_node->base - hold_mem_node->base;
+
+				if (hold_mem_node->length) {
+					hold_mem_node->next = func->mem_head;
+					func->mem_head = hold_mem_node;
+
+					/* configure end address */
+					temp_word = (mem_node->base - 1) >> 16;
+					rc = pci_bus_write_config_word (pci_bus, devfn, PCI_MEMORY_LIMIT, temp_word);
+
+					/* Return unused resources to the pool */
+					return_resource(&(resources->mem_head), mem_node);
+				} else {
+					/* it doesn't need any Mem */
+					temp_word = 0x0000;
+					rc = pci_bus_write_config_word (pci_bus, devfn, PCI_MEMORY_LIMIT, temp_word);
+
+					return_resource(&(resources->mem_head), mem_node);
+					kfree(hold_mem_node);
+				}
+			} else {
+				/* it used most of the range */
+				hold_mem_node->next = func->mem_head;
+				func->mem_head = hold_mem_node;
+			}
+		} else if (hold_mem_node) {
+			/* it used the whole range */
+			hold_mem_node->next = func->mem_head;
+			func->mem_head = hold_mem_node;
+		}
+		/* If we have prefetchable memory space available and there
+		 * is some left at the end, return the unused portion */
+		if (hold_p_mem_node && temp_resources.p_mem_head) {
+			p_mem_node = do_pre_bridge_resource_split(&(temp_resources.p_mem_head),
+								  &hold_p_mem_node, 0x100000);
+
+			/* Check if we were able to split something off */
+			if (p_mem_node) {
+				hold_p_mem_node->base = p_mem_node->base + p_mem_node->length;
+
+				temp_word = (hold_p_mem_node->base) >> 16;
+				rc = pci_bus_write_config_word (pci_bus, devfn, PCI_PREF_MEMORY_BASE, temp_word);
+
+				return_resource(&(resources->p_mem_head), p_mem_node);
+			}
+
+			p_mem_node = do_bridge_resource_split(&(temp_resources.p_mem_head), 0x100000);
+
+			/* Check if we were able to split something off */
+			if (p_mem_node) {
+				/* First use the temporary node to store
+				 * information for the board */
+				hold_p_mem_node->length = p_mem_node->base - hold_p_mem_node->base;
+
+				/* If we used any, add it to the board's list */
+				if (hold_p_mem_node->length) {
+					hold_p_mem_node->next = func->p_mem_head;
+					func->p_mem_head = hold_p_mem_node;
+
+					temp_word = (p_mem_node->base - 1) >> 16;
+					rc = pci_bus_write_config_word (pci_bus, devfn, PCI_PREF_MEMORY_LIMIT, temp_word);
+
+					return_resource(&(resources->p_mem_head), p_mem_node);
+				} else {
+					/* it doesn't need any PMem */
+					temp_word = 0x0000;
+					rc = pci_bus_write_config_word (pci_bus, devfn, PCI_PREF_MEMORY_LIMIT, temp_word);
+
+					return_resource(&(resources->p_mem_head), p_mem_node);
+					kfree(hold_p_mem_node);
+				}
+			} else {
+				/* it used the most of the range */
+				hold_p_mem_node->next = func->p_mem_head;
+				func->p_mem_head = hold_p_mem_node;
+			}
+		} else if (hold_p_mem_node) {
+			/* it used the whole range */
+			hold_p_mem_node->next = func->p_mem_head;
+			func->p_mem_head = hold_p_mem_node;
+		}
+		/* We should be configuring an IRQ and the bridge's base address
+		 * registers if it needs them.  Although we have never seen such
+		 * a device */
+
+		/* enable card */
+		command = 0x0157;	/* = PCI_COMMAND_IO |
+					 *   PCI_COMMAND_MEMORY |
+					 *   PCI_COMMAND_MASTER |
+					 *   PCI_COMMAND_INVALIDATE |
+					 *   PCI_COMMAND_PARITY |
+					 *   PCI_COMMAND_SERR */
+		rc = pci_bus_write_config_word (pci_bus, devfn, PCI_COMMAND, command);
+
+		/* set Bridge Control Register */
+		command = 0x07;		/* = PCI_BRIDGE_CTL_PARITY |
+					 *   PCI_BRIDGE_CTL_SERR |
+					 *   PCI_BRIDGE_CTL_NO_ISA */
+		rc = pci_bus_write_config_word (pci_bus, devfn, PCI_BRIDGE_CONTROL, command);
+	} else if ((temp_byte & 0x7F) == PCI_HEADER_TYPE_NORMAL) {
+		/* Standard device */
+		rc = pci_bus_read_config_byte (pci_bus, devfn, 0x0B, &class_code);
+
+		if (class_code == PCI_BASE_CLASS_DISPLAY) {
+			/* Display (video) adapter (not supported) */
+			return DEVICE_TYPE_NOT_SUPPORTED;
+		}
+		/* Figure out IO and memory needs */
+		for (cloop = 0x10; cloop <= 0x24; cloop += 4) {
+			temp_register = 0xFFFFFFFF;
+
+			dbg("CND: bus=%d, devfn=%d, offset=%d\n", pci_bus->number, devfn, cloop);
+			rc = pci_bus_write_config_dword (pci_bus, devfn, cloop, temp_register);
+
+			rc = pci_bus_read_config_dword (pci_bus, devfn, cloop, &temp_register);
+			dbg("CND: base = 0x%x\n", temp_register);
+
+			if (temp_register) {	  /* If this register is implemented */
+				if ((temp_register & 0x03L) == 0x01) {
+					/* Map IO */
+
+					/* set base = amount of IO space */
+					base = temp_register & 0xFFFFFFFC;
+					base = ~base + 1;
+
+					dbg("CND:      length = 0x%x\n", base);
+					io_node = get_io_resource(&(resources->io_head), base);
+					dbg("Got io_node start = %8.8x, length = %8.8x next (%p)\n",
+					    io_node->base, io_node->length, io_node->next);
+					dbg("func (%p) io_head (%p)\n", func, func->io_head);
+
+					/* allocate the resource to the board */
+					if (io_node) {
+						base = io_node->base;
+
+						io_node->next = func->io_head;
+						func->io_head = io_node;
+					} else
+						return -ENOMEM;
+				} else if ((temp_register & 0x0BL) == 0x08) {
+					/* Map prefetchable memory */
+					base = temp_register & 0xFFFFFFF0;
+					base = ~base + 1;
+
+					dbg("CND:      length = 0x%x\n", base);
+					p_mem_node = get_resource(&(resources->p_mem_head), base);
+
+					/* allocate the resource to the board */
+					if (p_mem_node) {
+						base = p_mem_node->base;
+
+						p_mem_node->next = func->p_mem_head;
+						func->p_mem_head = p_mem_node;
+					} else
+						return -ENOMEM;
+				} else if ((temp_register & 0x0BL) == 0x00) {
+					/* Map memory */
+					base = temp_register & 0xFFFFFFF0;
+					base = ~base + 1;
+
+					dbg("CND:      length = 0x%x\n", base);
+					mem_node = get_resource(&(resources->mem_head), base);
+
+					/* allocate the resource to the board */
+					if (mem_node) {
+						base = mem_node->base;
+
+						mem_node->next = func->mem_head;
+						func->mem_head = mem_node;
+					} else
+						return -ENOMEM;
+				} else if ((temp_register & 0x0BL) == 0x04) {
+					/* Map memory */
+					base = temp_register & 0xFFFFFFF0;
+					base = ~base + 1;
+
+					dbg("CND:      length = 0x%x\n", base);
+					mem_node = get_resource(&(resources->mem_head), base);
+
+					/* allocate the resource to the board */
+					if (mem_node) {
+						base = mem_node->base;
+
+						mem_node->next = func->mem_head;
+						func->mem_head = mem_node;
+					} else
+						return -ENOMEM;
+				} else if ((temp_register & 0x0BL) == 0x06) {
+					/* Those bits are reserved, we can't handle this */
+					return 1;
+				} else {
+					/* Requesting space below 1M */
+					return NOT_ENOUGH_RESOURCES;
+				}
+
+				rc = pci_bus_write_config_dword(pci_bus, devfn, cloop, base);
+
+				/* Check for 64-bit base */
+				if ((temp_register & 0x07L) == 0x04) {
+					cloop += 4;
+
+					/* Upper 32 bits of address always zero
+					 * on today's systems */
+					/* FIXME this is probably not true on
+					 * Alpha and ia64??? */
+					base = 0;
+					rc = pci_bus_write_config_dword(pci_bus, devfn, cloop, base);
+				}
+			}
+		}		/* End of base register loop */
+		if (cpqhp_legacy_mode) {
+			/* Figure out which interrupt pin this function uses */
+			rc = pci_bus_read_config_byte (pci_bus, devfn,
+				PCI_INTERRUPT_PIN, &temp_byte);
+
+			/* If this function needs an interrupt and we are behind
+			 * a bridge and the pin is tied to something that's
+			 * alread mapped, set this one the same */
+			if (temp_byte && resources->irqs &&
+			    (resources->irqs->valid_INT &
+			     (0x01 << ((temp_byte + resources->irqs->barber_pole - 1) & 0x03)))) {
+				/* We have to share with something already set up */
+				IRQ = resources->irqs->interrupt[(temp_byte +
+					resources->irqs->barber_pole - 1) & 0x03];
+			} else {
+				/* Program IRQ based on card type */
+				rc = pci_bus_read_config_byte (pci_bus, devfn, 0x0B, &class_code);
+
+				if (class_code == PCI_BASE_CLASS_STORAGE)
+					IRQ = cpqhp_disk_irq;
+				else
+					IRQ = cpqhp_nic_irq;
+			}
+
+			/* IRQ Line */
+			rc = pci_bus_write_config_byte (pci_bus, devfn, PCI_INTERRUPT_LINE, IRQ);
+		}
+
+		if (!behind_bridge) {
+			rc = cpqhp_set_irq(func->bus, func->device, temp_byte, IRQ);
+			if (rc)
+				return 1;
+		} else {
+			/* TBD - this code may also belong in the other clause
+			 * of this If statement */
+			resources->irqs->interrupt[(temp_byte + resources->irqs->barber_pole - 1) & 0x03] = IRQ;
+			resources->irqs->valid_INT |= 0x01 << (temp_byte + resources->irqs->barber_pole - 1) & 0x03;
+		}
+
+		/* Latency Timer */
+		temp_byte = 0x40;
+		rc = pci_bus_write_config_byte(pci_bus, devfn,
+					PCI_LATENCY_TIMER, temp_byte);
+
+		/* Cache Line size */
+		temp_byte = 0x08;
+		rc = pci_bus_write_config_byte(pci_bus, devfn,
+					PCI_CACHE_LINE_SIZE, temp_byte);
+
+		/* disable ROM base Address */
+		temp_dword = 0x00L;
+		rc = pci_bus_write_config_word(pci_bus, devfn,
+					PCI_ROM_ADDRESS, temp_dword);
+
+		/* enable card */
+		temp_word = 0x0157;	/* = PCI_COMMAND_IO |
+					 *   PCI_COMMAND_MEMORY |
+					 *   PCI_COMMAND_MASTER |
+					 *   PCI_COMMAND_INVALIDATE |
+					 *   PCI_COMMAND_PARITY |
+					 *   PCI_COMMAND_SERR */
+		rc = pci_bus_write_config_word (pci_bus, devfn,
+					PCI_COMMAND, temp_word);
+	} else {		/* End of Not-A-Bridge else */
+		/* It's some strange type of PCI adapter (Cardbus?) */
+		return DEVICE_TYPE_NOT_SUPPORTED;
+	}
+
+	func->configured = 1;
+
+	return 0;
+free_and_out:
+	cpqhp_destroy_resource_list (&temp_resources);
+
+	return_resource(&(resources-> bus_head), hold_bus_node);
+	return_resource(&(resources-> io_head), hold_IO_node);
+	return_resource(&(resources-> mem_head), hold_mem_node);
+	return_resource(&(resources-> p_mem_head), hold_p_mem_node);
+	return rc;
+}
diff --git a/drivers/pci/hotplug/cpqphp_nvram.c b/drivers/pci/hotplug/cpqphp_nvram.c
new file mode 100644
index 00000000..76ba8a1c
--- /dev/null
+++ b/drivers/pci/hotplug/cpqphp_nvram.c
@@ -0,0 +1,671 @@
+/*
+ * Compaq Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/proc_fs.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/init.h>
+#include <asm/uaccess.h>
+#include "cpqphp.h"
+#include "cpqphp_nvram.h"
+
+
+#define ROM_INT15_PHY_ADDR		0x0FF859
+#define READ_EV				0xD8A4
+#define WRITE_EV			0xD8A5
+
+struct register_foo {
+	union {
+		unsigned long lword;		/* eax */
+		unsigned short word;		/* ax */
+
+		struct {
+			unsigned char low;	/* al */
+			unsigned char high;	/* ah */
+		} byte;
+	} data;
+
+	unsigned char opcode;	/* see below */
+	unsigned long length;	/* if the reg. is a pointer, how much data */
+} __attribute__ ((packed));
+
+struct all_reg {
+	struct register_foo eax_reg;
+	struct register_foo ebx_reg;
+	struct register_foo ecx_reg;
+	struct register_foo edx_reg;
+	struct register_foo edi_reg;
+	struct register_foo esi_reg;
+	struct register_foo eflags_reg;
+} __attribute__ ((packed));
+
+
+struct ev_hrt_header {
+	u8 Version;
+	u8 num_of_ctrl;
+	u8 next;
+};
+
+struct ev_hrt_ctrl {
+	u8 bus;
+	u8 device;
+	u8 function;
+	u8 mem_avail;
+	u8 p_mem_avail;
+	u8 io_avail;
+	u8 bus_avail;
+	u8 next;
+};
+
+
+static u8 evbuffer_init;
+static u8 evbuffer_length;
+static u8 evbuffer[1024];
+
+static void __iomem *compaq_int15_entry_point;
+
+/* lock for ordering int15_bios_call() */
+static spinlock_t int15_lock;
+
+
+/* This is a series of function that deals with
+ * setting & getting the hotplug resource table in some environment variable.
+ */
+
+/*
+ * We really shouldn't be doing this unless there is a _very_ good reason to!!!
+ * greg k-h
+ */
+
+
+static u32 add_byte( u32 **p_buffer, u8 value, u32 *used, u32 *avail)
+{
+	u8 **tByte;
+
+	if ((*used + 1) > *avail)
+		return(1);
+
+	*((u8*)*p_buffer) = value;
+	tByte = (u8**)p_buffer;
+	(*tByte)++;
+	*used+=1;
+	return(0);
+}
+
+
+static u32 add_dword( u32 **p_buffer, u32 value, u32 *used, u32 *avail)
+{
+	if ((*used + 4) > *avail)
+		return(1);
+
+	**p_buffer = value;
+	(*p_buffer)++;
+	*used+=4;
+	return(0);
+}
+
+
+/*
+ * check_for_compaq_ROM
+ *
+ * this routine verifies that the ROM OEM string is 'COMPAQ'
+ *
+ * returns 0 for non-Compaq ROM, 1 for Compaq ROM
+ */
+static int check_for_compaq_ROM (void __iomem *rom_start)
+{
+	u8 temp1, temp2, temp3, temp4, temp5, temp6;
+	int result = 0;
+
+	temp1 = readb(rom_start + 0xffea + 0);
+	temp2 = readb(rom_start + 0xffea + 1);
+	temp3 = readb(rom_start + 0xffea + 2);
+	temp4 = readb(rom_start + 0xffea + 3);
+	temp5 = readb(rom_start + 0xffea + 4);
+	temp6 = readb(rom_start + 0xffea + 5);
+	if ((temp1 == 'C') &&
+	    (temp2 == 'O') &&
+	    (temp3 == 'M') &&
+	    (temp4 == 'P') &&
+	    (temp5 == 'A') &&
+	    (temp6 == 'Q')) {
+		result = 1;
+	}
+	dbg ("%s - returned %d\n", __func__, result);
+	return result;
+}
+
+
+static u32 access_EV (u16 operation, u8 *ev_name, u8 *buffer, u32 *buf_size)
+{
+	unsigned long flags;
+	int op = operation;
+	int ret_val;
+
+	if (!compaq_int15_entry_point)
+		return -ENODEV;
+
+	spin_lock_irqsave(&int15_lock, flags);
+	__asm__ (
+		"xorl   %%ebx,%%ebx\n" \
+		"xorl    %%edx,%%edx\n" \
+		"pushf\n" \
+		"push %%cs\n" \
+		"cli\n" \
+		"call *%6\n"
+		: "=c" (*buf_size), "=a" (ret_val)
+		: "a" (op), "c" (*buf_size), "S" (ev_name),
+		"D" (buffer), "m" (compaq_int15_entry_point)
+		: "%ebx", "%edx");
+	spin_unlock_irqrestore(&int15_lock, flags);
+
+	return((ret_val & 0xFF00) >> 8);
+}
+
+
+/*
+ * load_HRT
+ *
+ * Read the hot plug Resource Table from NVRAM
+ */
+static int load_HRT (void __iomem *rom_start)
+{
+	u32 available;
+	u32 temp_dword;
+	u8 temp_byte = 0xFF;
+	u32 rc;
+
+	if (!check_for_compaq_ROM(rom_start)) {
+		return -ENODEV;
+	}
+
+	available = 1024;
+
+	/* Now load the EV */
+	temp_dword = available;
+
+	rc = access_EV(READ_EV, "CQTHPS", evbuffer, &temp_dword);
+
+	evbuffer_length = temp_dword;
+
+	/* We're maintaining the resource lists so write FF to invalidate old
+	 * info
+	 */
+	temp_dword = 1;
+
+	rc = access_EV(WRITE_EV, "CQTHPS", &temp_byte, &temp_dword);
+
+	return rc;
+}
+
+
+/*
+ * store_HRT
+ *
+ * Save the hot plug Resource Table in NVRAM
+ */
+static u32 store_HRT (void __iomem *rom_start)
+{
+	u32 *buffer;
+	u32 *pFill;
+	u32 usedbytes;
+	u32 available;
+	u32 temp_dword;
+	u32 rc;
+	u8 loop;
+	u8 numCtrl = 0;
+	struct controller *ctrl;
+	struct pci_resource *resNode;
+	struct ev_hrt_header *p_EV_header;
+	struct ev_hrt_ctrl *p_ev_ctrl;
+
+	available = 1024;
+
+	if (!check_for_compaq_ROM(rom_start)) {
+		return(1);
+	}
+
+	buffer = (u32*) evbuffer;
+
+	if (!buffer)
+		return(1);
+
+	pFill = buffer;
+	usedbytes = 0;
+
+	p_EV_header = (struct ev_hrt_header *) pFill;
+
+	ctrl = cpqhp_ctrl_list;
+
+	/* The revision of this structure */
+	rc = add_byte( &pFill, 1 + ctrl->push_flag, &usedbytes, &available);
+	if (rc)
+		return(rc);
+
+	/* The number of controllers */
+	rc = add_byte( &pFill, 1, &usedbytes, &available);
+	if (rc)
+		return(rc);
+
+	while (ctrl) {
+		p_ev_ctrl = (struct ev_hrt_ctrl *) pFill;
+
+		numCtrl++;
+
+		/* The bus number */
+		rc = add_byte( &pFill, ctrl->bus, &usedbytes, &available);
+		if (rc)
+			return(rc);
+
+		/* The device Number */
+		rc = add_byte( &pFill, PCI_SLOT(ctrl->pci_dev->devfn), &usedbytes, &available);
+		if (rc)
+			return(rc);
+
+		/* The function Number */
+		rc = add_byte( &pFill, PCI_FUNC(ctrl->pci_dev->devfn), &usedbytes, &available);
+		if (rc)
+			return(rc);
+
+		/* Skip the number of available entries */
+		rc = add_dword( &pFill, 0, &usedbytes, &available);
+		if (rc)
+			return(rc);
+
+		/* Figure out memory Available */
+
+		resNode = ctrl->mem_head;
+
+		loop = 0;
+
+		while (resNode) {
+			loop ++;
+
+			/* base */
+			rc = add_dword( &pFill, resNode->base, &usedbytes, &available);
+			if (rc)
+				return(rc);
+
+			/* length */
+			rc = add_dword( &pFill, resNode->length, &usedbytes, &available);
+			if (rc)
+				return(rc);
+
+			resNode = resNode->next;
+		}
+
+		/* Fill in the number of entries */
+		p_ev_ctrl->mem_avail = loop;
+
+		/* Figure out prefetchable memory Available */
+
+		resNode = ctrl->p_mem_head;
+
+		loop = 0;
+
+		while (resNode) {
+			loop ++;
+
+			/* base */
+			rc = add_dword( &pFill, resNode->base, &usedbytes, &available);
+			if (rc)
+				return(rc);
+
+			/* length */
+			rc = add_dword( &pFill, resNode->length, &usedbytes, &available);
+			if (rc)
+				return(rc);
+
+			resNode = resNode->next;
+		}
+
+		/* Fill in the number of entries */
+		p_ev_ctrl->p_mem_avail = loop;
+
+		/* Figure out IO Available */
+
+		resNode = ctrl->io_head;
+
+		loop = 0;
+
+		while (resNode) {
+			loop ++;
+
+			/* base */
+			rc = add_dword( &pFill, resNode->base, &usedbytes, &available);
+			if (rc)
+				return(rc);
+
+			/* length */
+			rc = add_dword( &pFill, resNode->length, &usedbytes, &available);
+			if (rc)
+				return(rc);
+
+			resNode = resNode->next;
+		}
+
+		/* Fill in the number of entries */
+		p_ev_ctrl->io_avail = loop;
+
+		/* Figure out bus Available */
+
+		resNode = ctrl->bus_head;
+
+		loop = 0;
+
+		while (resNode) {
+			loop ++;
+
+			/* base */
+			rc = add_dword( &pFill, resNode->base, &usedbytes, &available);
+			if (rc)
+				return(rc);
+
+			/* length */
+			rc = add_dword( &pFill, resNode->length, &usedbytes, &available);
+			if (rc)
+				return(rc);
+
+			resNode = resNode->next;
+		}
+
+		/* Fill in the number of entries */
+		p_ev_ctrl->bus_avail = loop;
+
+		ctrl = ctrl->next;
+	}
+
+	p_EV_header->num_of_ctrl = numCtrl;
+
+	/* Now store the EV */
+
+	temp_dword = usedbytes;
+
+	rc = access_EV(WRITE_EV, "CQTHPS", (u8*) buffer, &temp_dword);
+
+	dbg("usedbytes = 0x%x, length = 0x%x\n", usedbytes, temp_dword);
+
+	evbuffer_length = temp_dword;
+
+	if (rc) {
+		err(msg_unable_to_save);
+		return(1);
+	}
+
+	return(0);
+}
+
+
+void compaq_nvram_init (void __iomem *rom_start)
+{
+	if (rom_start) {
+		compaq_int15_entry_point = (rom_start + ROM_INT15_PHY_ADDR - ROM_PHY_ADDR);
+	}
+	dbg("int15 entry  = %p\n", compaq_int15_entry_point);
+
+	/* initialize our int15 lock */
+	spin_lock_init(&int15_lock);
+}
+
+
+int compaq_nvram_load (void __iomem *rom_start, struct controller *ctrl)
+{
+	u8 bus, device, function;
+	u8 nummem, numpmem, numio, numbus;
+	u32 rc;
+	u8 *p_byte;
+	struct pci_resource *mem_node;
+	struct pci_resource *p_mem_node;
+	struct pci_resource *io_node;
+	struct pci_resource *bus_node;
+	struct ev_hrt_ctrl *p_ev_ctrl;
+	struct ev_hrt_header *p_EV_header;
+
+	if (!evbuffer_init) {
+		/* Read the resource list information in from NVRAM */
+		if (load_HRT(rom_start))
+			memset (evbuffer, 0, 1024);
+
+		evbuffer_init = 1;
+	}
+
+	/* If we saved information in NVRAM, use it now */
+	p_EV_header = (struct ev_hrt_header *) evbuffer;
+
+	/* The following code is for systems where version 1.0 of this
+	 * driver has been loaded, but doesn't support the hardware.
+	 * In that case, the driver would incorrectly store something
+	 * in NVRAM.
+	 */
+	if ((p_EV_header->Version == 2) ||
+	    ((p_EV_header->Version == 1) && !ctrl->push_flag)) {
+		p_byte = &(p_EV_header->next);
+
+		p_ev_ctrl = (struct ev_hrt_ctrl *) &(p_EV_header->next);
+
+		p_byte += 3;
+
+		if (p_byte > ((u8*)p_EV_header + evbuffer_length))
+			return 2;
+
+		bus = p_ev_ctrl->bus;
+		device = p_ev_ctrl->device;
+		function = p_ev_ctrl->function;
+
+		while ((bus != ctrl->bus) ||
+		       (device != PCI_SLOT(ctrl->pci_dev->devfn)) ||
+		       (function != PCI_FUNC(ctrl->pci_dev->devfn))) {
+			nummem = p_ev_ctrl->mem_avail;
+			numpmem = p_ev_ctrl->p_mem_avail;
+			numio = p_ev_ctrl->io_avail;
+			numbus = p_ev_ctrl->bus_avail;
+
+			p_byte += 4;
+
+			if (p_byte > ((u8*)p_EV_header + evbuffer_length))
+				return 2;
+
+			/* Skip forward to the next entry */
+			p_byte += (nummem + numpmem + numio + numbus) * 8;
+
+			if (p_byte > ((u8*)p_EV_header + evbuffer_length))
+				return 2;
+
+			p_ev_ctrl = (struct ev_hrt_ctrl *) p_byte;
+
+			p_byte += 3;
+
+			if (p_byte > ((u8*)p_EV_header + evbuffer_length))
+				return 2;
+
+			bus = p_ev_ctrl->bus;
+			device = p_ev_ctrl->device;
+			function = p_ev_ctrl->function;
+		}
+
+		nummem = p_ev_ctrl->mem_avail;
+		numpmem = p_ev_ctrl->p_mem_avail;
+		numio = p_ev_ctrl->io_avail;
+		numbus = p_ev_ctrl->bus_avail;
+
+		p_byte += 4;
+
+		if (p_byte > ((u8*)p_EV_header + evbuffer_length))
+			return 2;
+
+		while (nummem--) {
+			mem_node = kmalloc(sizeof(struct pci_resource), GFP_KERNEL);
+
+			if (!mem_node)
+				break;
+
+			mem_node->base = *(u32*)p_byte;
+			dbg("mem base = %8.8x\n",mem_node->base);
+			p_byte += 4;
+
+			if (p_byte > ((u8*)p_EV_header + evbuffer_length)) {
+				kfree(mem_node);
+				return 2;
+			}
+
+			mem_node->length = *(u32*)p_byte;
+			dbg("mem length = %8.8x\n",mem_node->length);
+			p_byte += 4;
+
+			if (p_byte > ((u8*)p_EV_header + evbuffer_length)) {
+				kfree(mem_node);
+				return 2;
+			}
+
+			mem_node->next = ctrl->mem_head;
+			ctrl->mem_head = mem_node;
+		}
+
+		while (numpmem--) {
+			p_mem_node = kmalloc(sizeof(struct pci_resource), GFP_KERNEL);
+
+			if (!p_mem_node)
+				break;
+
+			p_mem_node->base = *(u32*)p_byte;
+			dbg("pre-mem base = %8.8x\n",p_mem_node->base);
+			p_byte += 4;
+
+			if (p_byte > ((u8*)p_EV_header + evbuffer_length)) {
+				kfree(p_mem_node);
+				return 2;
+			}
+
+			p_mem_node->length = *(u32*)p_byte;
+			dbg("pre-mem length = %8.8x\n",p_mem_node->length);
+			p_byte += 4;
+
+			if (p_byte > ((u8*)p_EV_header + evbuffer_length)) {
+				kfree(p_mem_node);
+				return 2;
+			}
+
+			p_mem_node->next = ctrl->p_mem_head;
+			ctrl->p_mem_head = p_mem_node;
+		}
+
+		while (numio--) {
+			io_node = kmalloc(sizeof(struct pci_resource), GFP_KERNEL);
+
+			if (!io_node)
+				break;
+
+			io_node->base = *(u32*)p_byte;
+			dbg("io base = %8.8x\n",io_node->base);
+			p_byte += 4;
+
+			if (p_byte > ((u8*)p_EV_header + evbuffer_length)) {
+				kfree(io_node);
+				return 2;
+			}
+
+			io_node->length = *(u32*)p_byte;
+			dbg("io length = %8.8x\n",io_node->length);
+			p_byte += 4;
+
+			if (p_byte > ((u8*)p_EV_header + evbuffer_length)) {
+				kfree(io_node);
+				return 2;
+			}
+
+			io_node->next = ctrl->io_head;
+			ctrl->io_head = io_node;
+		}
+
+		while (numbus--) {
+			bus_node = kmalloc(sizeof(struct pci_resource), GFP_KERNEL);
+
+			if (!bus_node)
+				break;
+
+			bus_node->base = *(u32*)p_byte;
+			p_byte += 4;
+
+			if (p_byte > ((u8*)p_EV_header + evbuffer_length)) {
+				kfree(bus_node);
+				return 2;
+			}
+
+			bus_node->length = *(u32*)p_byte;
+			p_byte += 4;
+
+			if (p_byte > ((u8*)p_EV_header + evbuffer_length)) {
+				kfree(bus_node);
+				return 2;
+			}
+
+			bus_node->next = ctrl->bus_head;
+			ctrl->bus_head = bus_node;
+		}
+
+		/* If all of the following fail, we don't have any resources for
+		 * hot plug add
+		 */
+		rc = 1;
+		rc &= cpqhp_resource_sort_and_combine(&(ctrl->mem_head));
+		rc &= cpqhp_resource_sort_and_combine(&(ctrl->p_mem_head));
+		rc &= cpqhp_resource_sort_and_combine(&(ctrl->io_head));
+		rc &= cpqhp_resource_sort_and_combine(&(ctrl->bus_head));
+
+		if (rc)
+			return(rc);
+	} else {
+		if ((evbuffer[0] != 0) && (!ctrl->push_flag))
+			return 1;
+	}
+
+	return 0;
+}
+
+
+int compaq_nvram_store (void __iomem *rom_start)
+{
+	int rc = 1;
+
+	if (rom_start == NULL)
+		return -ENODEV;
+
+	if (evbuffer_init) {
+		rc = store_HRT(rom_start);
+		if (rc) {
+			err(msg_unable_to_save);
+		}
+	}
+	return rc;
+}
+
diff --git a/drivers/pci/hotplug/cpqphp_nvram.h b/drivers/pci/hotplug/cpqphp_nvram.h
new file mode 100644
index 00000000..e89c0702
--- /dev/null
+++ b/drivers/pci/hotplug/cpqphp_nvram.h
@@ -0,0 +1,57 @@
+/*
+ * Compaq Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>
+ *
+ */
+
+#ifndef _CPQPHP_NVRAM_H
+#define _CPQPHP_NVRAM_H
+
+#ifndef CONFIG_HOTPLUG_PCI_COMPAQ_NVRAM
+
+static inline void compaq_nvram_init (void __iomem *rom_start)
+{
+	return;
+}
+
+static inline int compaq_nvram_load (void __iomem *rom_start, struct controller *ctrl)
+{
+	return 0;
+}
+
+static inline int compaq_nvram_store (void __iomem *rom_start)
+{
+	return 0;
+}
+
+#else
+
+extern void compaq_nvram_init	(void __iomem *rom_start);
+extern int compaq_nvram_load	(void __iomem *rom_start, struct controller *ctrl);
+extern int compaq_nvram_store	(void __iomem *rom_start);
+
+#endif
+
+#endif
+
diff --git a/drivers/pci/hotplug/cpqphp_pci.c b/drivers/pci/hotplug/cpqphp_pci.c
new file mode 100644
index 00000000..6173b9a4
--- /dev/null
+++ b/drivers/pci/hotplug/cpqphp_pci.c
@@ -0,0 +1,1559 @@
+/*
+ * Compaq Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+#include <linux/proc_fs.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include "../pci.h"
+#include "cpqphp.h"
+#include "cpqphp_nvram.h"
+
+
+u8 cpqhp_nic_irq;
+u8 cpqhp_disk_irq;
+
+static u16 unused_IRQ;
+
+/*
+ * detect_HRT_floating_pointer
+ *
+ * find the Hot Plug Resource Table in the specified region of memory.
+ *
+ */
+static void __iomem *detect_HRT_floating_pointer(void __iomem *begin, void __iomem *end)
+{
+	void __iomem *fp;
+	void __iomem *endp;
+	u8 temp1, temp2, temp3, temp4;
+	int status = 0;
+
+	endp = (end - sizeof(struct hrt) + 1);
+
+	for (fp = begin; fp <= endp; fp += 16) {
+		temp1 = readb(fp + SIG0);
+		temp2 = readb(fp + SIG1);
+		temp3 = readb(fp + SIG2);
+		temp4 = readb(fp + SIG3);
+		if (temp1 == '$' &&
+		    temp2 == 'H' &&
+		    temp3 == 'R' &&
+		    temp4 == 'T') {
+			status = 1;
+			break;
+		}
+	}
+
+	if (!status)
+		fp = NULL;
+
+	dbg("Discovered Hotplug Resource Table at %p\n", fp);
+	return fp;
+}
+
+
+int cpqhp_configure_device (struct controller* ctrl, struct pci_func* func)
+{
+	unsigned char bus;
+	struct pci_bus *child;
+	int num;
+
+	if (func->pci_dev == NULL)
+		func->pci_dev = pci_get_bus_and_slot(func->bus,PCI_DEVFN(func->device, func->function));
+
+	/* No pci device, we need to create it then */
+	if (func->pci_dev == NULL) {
+		dbg("INFO: pci_dev still null\n");
+
+		num = pci_scan_slot(ctrl->pci_dev->bus, PCI_DEVFN(func->device, func->function));
+		if (num)
+			pci_bus_add_devices(ctrl->pci_dev->bus);
+
+		func->pci_dev = pci_get_bus_and_slot(func->bus, PCI_DEVFN(func->device, func->function));
+		if (func->pci_dev == NULL) {
+			dbg("ERROR: pci_dev still null\n");
+			return 0;
+		}
+	}
+
+	if (func->pci_dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
+		pci_read_config_byte(func->pci_dev, PCI_SECONDARY_BUS, &bus);
+		child = (struct pci_bus*) pci_add_new_bus(func->pci_dev->bus, (func->pci_dev), bus);
+		pci_do_scan_bus(child);
+	}
+
+	pci_dev_put(func->pci_dev);
+
+	return 0;
+}
+
+
+int cpqhp_unconfigure_device(struct pci_func* func)
+{
+	int j;
+
+	dbg("%s: bus/dev/func = %x/%x/%x\n", __func__, func->bus, func->device, func->function);
+
+	for (j=0; j<8 ; j++) {
+		struct pci_dev* temp = pci_get_bus_and_slot(func->bus, PCI_DEVFN(func->device, j));
+		if (temp) {
+			pci_dev_put(temp);
+			pci_remove_bus_device(temp);
+		}
+	}
+	return 0;
+}
+
+static int PCI_RefinedAccessConfig(struct pci_bus *bus, unsigned int devfn, u8 offset, u32 *value)
+{
+	u32 vendID = 0;
+
+	if (pci_bus_read_config_dword (bus, devfn, PCI_VENDOR_ID, &vendID) == -1)
+		return -1;
+	if (vendID == 0xffffffff)
+		return -1;
+	return pci_bus_read_config_dword (bus, devfn, offset, value);
+}
+
+
+/*
+ * cpqhp_set_irq
+ *
+ * @bus_num: bus number of PCI device
+ * @dev_num: device number of PCI device
+ * @slot: pointer to u8 where slot number will be returned
+ */
+int cpqhp_set_irq (u8 bus_num, u8 dev_num, u8 int_pin, u8 irq_num)
+{
+	int rc = 0;
+
+	if (cpqhp_legacy_mode) {
+		struct pci_dev *fakedev;
+		struct pci_bus *fakebus;
+		u16 temp_word;
+
+		fakedev = kmalloc(sizeof(*fakedev), GFP_KERNEL);
+		fakebus = kmalloc(sizeof(*fakebus), GFP_KERNEL);
+		if (!fakedev || !fakebus) {
+			kfree(fakedev);
+			kfree(fakebus);
+			return -ENOMEM;
+		}
+
+		fakedev->devfn = dev_num << 3;
+		fakedev->bus = fakebus;
+		fakebus->number = bus_num;
+		dbg("%s: dev %d, bus %d, pin %d, num %d\n",
+		    __func__, dev_num, bus_num, int_pin, irq_num);
+		rc = pcibios_set_irq_routing(fakedev, int_pin - 1, irq_num);
+		kfree(fakedev);
+		kfree(fakebus);
+		dbg("%s: rc %d\n", __func__, rc);
+		if (!rc)
+			return !rc;
+
+		/* set the Edge Level Control Register (ELCR) */
+		temp_word = inb(0x4d0);
+		temp_word |= inb(0x4d1) << 8;
+
+		temp_word |= 0x01 << irq_num;
+
+		/* This should only be for x86 as it sets the Edge Level
+		 * Control Register
+		 */
+		outb((u8) (temp_word & 0xFF), 0x4d0); outb((u8) ((temp_word &
+		0xFF00) >> 8), 0x4d1); rc = 0; }
+
+	return rc;
+}
+
+
+static int PCI_ScanBusForNonBridge(struct controller *ctrl, u8 bus_num, u8 * dev_num)
+{
+	u16 tdevice;
+	u32 work;
+	u8 tbus;
+
+	ctrl->pci_bus->number = bus_num;
+
+	for (tdevice = 0; tdevice < 0xFF; tdevice++) {
+		/* Scan for access first */
+		if (PCI_RefinedAccessConfig(ctrl->pci_bus, tdevice, 0x08, &work) == -1)
+			continue;
+		dbg("Looking for nonbridge bus_num %d dev_num %d\n", bus_num, tdevice);
+		/* Yep we got one. Not a bridge ? */
+		if ((work >> 8) != PCI_TO_PCI_BRIDGE_CLASS) {
+			*dev_num = tdevice;
+			dbg("found it !\n");
+			return 0;
+		}
+	}
+	for (tdevice = 0; tdevice < 0xFF; tdevice++) {
+		/* Scan for access first */
+		if (PCI_RefinedAccessConfig(ctrl->pci_bus, tdevice, 0x08, &work) == -1)
+			continue;
+		dbg("Looking for bridge bus_num %d dev_num %d\n", bus_num, tdevice);
+		/* Yep we got one. bridge ? */
+		if ((work >> 8) == PCI_TO_PCI_BRIDGE_CLASS) {
+			pci_bus_read_config_byte (ctrl->pci_bus, PCI_DEVFN(tdevice, 0), PCI_SECONDARY_BUS, &tbus);
+			/* XXX: no recursion, wtf? */
+			dbg("Recurse on bus_num %d tdevice %d\n", tbus, tdevice);
+			return 0;
+		}
+	}
+
+	return -1;
+}
+
+
+static int PCI_GetBusDevHelper(struct controller *ctrl, u8 *bus_num, u8 *dev_num, u8 slot, u8 nobridge)
+{
+	int loop, len;
+	u32 work;
+	u8 tbus, tdevice, tslot;
+
+	len = cpqhp_routing_table_length();
+	for (loop = 0; loop < len; ++loop) {
+		tbus = cpqhp_routing_table->slots[loop].bus;
+		tdevice = cpqhp_routing_table->slots[loop].devfn;
+		tslot = cpqhp_routing_table->slots[loop].slot;
+
+		if (tslot == slot) {
+			*bus_num = tbus;
+			*dev_num = tdevice;
+			ctrl->pci_bus->number = tbus;
+			pci_bus_read_config_dword (ctrl->pci_bus, *dev_num, PCI_VENDOR_ID, &work);
+			if (!nobridge || (work == 0xffffffff))
+				return 0;
+
+			dbg("bus_num %d devfn %d\n", *bus_num, *dev_num);
+			pci_bus_read_config_dword (ctrl->pci_bus, *dev_num, PCI_CLASS_REVISION, &work);
+			dbg("work >> 8 (%x) = BRIDGE (%x)\n", work >> 8, PCI_TO_PCI_BRIDGE_CLASS);
+
+			if ((work >> 8) == PCI_TO_PCI_BRIDGE_CLASS) {
+				pci_bus_read_config_byte (ctrl->pci_bus, *dev_num, PCI_SECONDARY_BUS, &tbus);
+				dbg("Scan bus for Non Bridge: bus %d\n", tbus);
+				if (PCI_ScanBusForNonBridge(ctrl, tbus, dev_num) == 0) {
+					*bus_num = tbus;
+					return 0;
+				}
+			} else
+				return 0;
+		}
+	}
+	return -1;
+}
+
+
+int cpqhp_get_bus_dev (struct controller *ctrl, u8 * bus_num, u8 * dev_num, u8 slot)
+{
+	/* plain (bridges allowed) */
+	return PCI_GetBusDevHelper(ctrl, bus_num, dev_num, slot, 0);
+}
+
+
+/* More PCI configuration routines; this time centered around hotplug
+ * controller
+ */
+
+
+/*
+ * cpqhp_save_config
+ *
+ * Reads configuration for all slots in a PCI bus and saves info.
+ *
+ * Note:  For non-hot plug busses, the slot # saved is the device #
+ *
+ * returns 0 if success
+ */
+int cpqhp_save_config(struct controller *ctrl, int busnumber, int is_hot_plug)
+{
+	long rc;
+	u8 class_code;
+	u8 header_type;
+	u32 ID;
+	u8 secondary_bus;
+	struct pci_func *new_slot;
+	int sub_bus;
+	int FirstSupported;
+	int LastSupported;
+	int max_functions;
+	int function;
+	u8 DevError;
+	int device = 0;
+	int cloop = 0;
+	int stop_it;
+	int index;
+
+	/* Decide which slots are supported */
+
+	if (is_hot_plug) {
+		/*
+		 * is_hot_plug is the slot mask
+		 */
+		FirstSupported = is_hot_plug >> 4;
+		LastSupported = FirstSupported + (is_hot_plug & 0x0F) - 1;
+	} else {
+		FirstSupported = 0;
+		LastSupported = 0x1F;
+	}
+
+	/* Save PCI configuration space for all devices in supported slots */
+	ctrl->pci_bus->number = busnumber;
+	for (device = FirstSupported; device <= LastSupported; device++) {
+		ID = 0xFFFFFFFF;
+		rc = pci_bus_read_config_dword(ctrl->pci_bus, PCI_DEVFN(device, 0), PCI_VENDOR_ID, &ID);
+
+		if (ID == 0xFFFFFFFF) {
+			if (is_hot_plug) {
+				/* Setup slot structure with entry for empty
+				 * slot
+				 */
+				new_slot = cpqhp_slot_create(busnumber);
+				if (new_slot == NULL)
+					return 1;
+
+				new_slot->bus = (u8) busnumber;
+				new_slot->device = (u8) device;
+				new_slot->function = 0;
+				new_slot->is_a_board = 0;
+				new_slot->presence_save = 0;
+				new_slot->switch_save = 0;
+			}
+			continue;
+		}
+
+		rc = pci_bus_read_config_byte(ctrl->pci_bus, PCI_DEVFN(device, 0), 0x0B, &class_code);
+		if (rc)
+			return rc;
+
+		rc = pci_bus_read_config_byte(ctrl->pci_bus, PCI_DEVFN(device, 0), PCI_HEADER_TYPE, &header_type);
+		if (rc)
+			return rc;
+
+		/* If multi-function device, set max_functions to 8 */
+		if (header_type & 0x80)
+			max_functions = 8;
+		else
+			max_functions = 1;
+
+		function = 0;
+
+		do {
+			DevError = 0;
+			if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE) {
+				/* Recurse the subordinate bus
+				 * get the subordinate bus number
+				 */
+				rc = pci_bus_read_config_byte(ctrl->pci_bus, PCI_DEVFN(device, function), PCI_SECONDARY_BUS, &secondary_bus);
+				if (rc) {
+					return rc;
+				} else {
+					sub_bus = (int) secondary_bus;
+
+					/* Save secondary bus cfg spc
+					 * with this recursive call.
+					 */
+					rc = cpqhp_save_config(ctrl, sub_bus, 0);
+					if (rc)
+						return rc;
+					ctrl->pci_bus->number = busnumber;
+				}
+			}
+
+			index = 0;
+			new_slot = cpqhp_slot_find(busnumber, device, index++);
+			while (new_slot &&
+			       (new_slot->function != (u8) function))
+				new_slot = cpqhp_slot_find(busnumber, device, index++);
+
+			if (!new_slot) {
+				/* Setup slot structure. */
+				new_slot = cpqhp_slot_create(busnumber);
+				if (new_slot == NULL)
+					return 1;
+			}
+
+			new_slot->bus = (u8) busnumber;
+			new_slot->device = (u8) device;
+			new_slot->function = (u8) function;
+			new_slot->is_a_board = 1;
+			new_slot->switch_save = 0x10;
+			/* In case of unsupported board */
+			new_slot->status = DevError;
+			new_slot->pci_dev = pci_get_bus_and_slot(new_slot->bus, (new_slot->device << 3) | new_slot->function);
+
+			for (cloop = 0; cloop < 0x20; cloop++) {
+				rc = pci_bus_read_config_dword(ctrl->pci_bus, PCI_DEVFN(device, function), cloop << 2, (u32 *) & (new_slot-> config_space [cloop]));
+				if (rc)
+					return rc;
+			}
+
+			pci_dev_put(new_slot->pci_dev);
+
+			function++;
+
+			stop_it = 0;
+
+			/* this loop skips to the next present function
+			 * reading in Class Code and Header type.
+			 */
+			while ((function < max_functions) && (!stop_it)) {
+				rc = pci_bus_read_config_dword(ctrl->pci_bus, PCI_DEVFN(device, function), PCI_VENDOR_ID, &ID);
+				if (ID == 0xFFFFFFFF) {
+					function++;
+					continue;
+				}
+				rc = pci_bus_read_config_byte(ctrl->pci_bus, PCI_DEVFN(device, function), 0x0B, &class_code);
+				if (rc)
+					return rc;
+
+				rc = pci_bus_read_config_byte(ctrl->pci_bus, PCI_DEVFN(device, function), PCI_HEADER_TYPE, &header_type);
+				if (rc)
+					return rc;
+
+				stop_it++;
+			}
+
+		} while (function < max_functions);
+	}			/* End of FOR loop */
+
+	return 0;
+}
+
+
+/*
+ * cpqhp_save_slot_config
+ *
+ * Saves configuration info for all PCI devices in a given slot
+ * including subordinate busses.
+ *
+ * returns 0 if success
+ */
+int cpqhp_save_slot_config (struct controller *ctrl, struct pci_func * new_slot)
+{
+	long rc;
+	u8 class_code;
+	u8 header_type;
+	u32 ID;
+	u8 secondary_bus;
+	int sub_bus;
+	int max_functions;
+	int function = 0;
+	int cloop = 0;
+	int stop_it;
+
+	ID = 0xFFFFFFFF;
+
+	ctrl->pci_bus->number = new_slot->bus;
+	pci_bus_read_config_dword (ctrl->pci_bus, PCI_DEVFN(new_slot->device, 0), PCI_VENDOR_ID, &ID);
+
+	if (ID == 0xFFFFFFFF)
+		return 2;
+
+	pci_bus_read_config_byte(ctrl->pci_bus, PCI_DEVFN(new_slot->device, 0), 0x0B, &class_code);
+	pci_bus_read_config_byte(ctrl->pci_bus, PCI_DEVFN(new_slot->device, 0), PCI_HEADER_TYPE, &header_type);
+
+	if (header_type & 0x80)	/* Multi-function device */
+		max_functions = 8;
+	else
+		max_functions = 1;
+
+	while (function < max_functions) {
+		if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE) {
+			/*  Recurse the subordinate bus */
+			pci_bus_read_config_byte (ctrl->pci_bus, PCI_DEVFN(new_slot->device, function), PCI_SECONDARY_BUS, &secondary_bus);
+
+			sub_bus = (int) secondary_bus;
+
+			/* Save the config headers for the secondary
+			 * bus.
+			 */
+			rc = cpqhp_save_config(ctrl, sub_bus, 0);
+			if (rc)
+				return(rc);
+			ctrl->pci_bus->number = new_slot->bus;
+
+		}
+
+		new_slot->status = 0;
+
+		for (cloop = 0; cloop < 0x20; cloop++)
+			pci_bus_read_config_dword(ctrl->pci_bus, PCI_DEVFN(new_slot->device, function), cloop << 2, (u32 *) & (new_slot-> config_space [cloop]));
+
+		function++;
+
+		stop_it = 0;
+
+		/* this loop skips to the next present function
+		 * reading in the Class Code and the Header type.
+		 */
+		while ((function < max_functions) && (!stop_it)) {
+			pci_bus_read_config_dword(ctrl->pci_bus, PCI_DEVFN(new_slot->device, function), PCI_VENDOR_ID, &ID);
+
+			if (ID == 0xFFFFFFFF)
+				function++;
+			else {
+				pci_bus_read_config_byte(ctrl->pci_bus, PCI_DEVFN(new_slot->device, function), 0x0B, &class_code);
+				pci_bus_read_config_byte(ctrl->pci_bus, PCI_DEVFN(new_slot->device, function), PCI_HEADER_TYPE, &header_type);
+				stop_it++;
+			}
+		}
+
+	}
+
+	return 0;
+}
+
+
+/*
+ * cpqhp_save_base_addr_length
+ *
+ * Saves the length of all base address registers for the
+ * specified slot.  this is for hot plug REPLACE
+ *
+ * returns 0 if success
+ */
+int cpqhp_save_base_addr_length(struct controller *ctrl, struct pci_func * func)
+{
+	u8 cloop;
+	u8 header_type;
+	u8 secondary_bus;
+	u8 type;
+	int sub_bus;
+	u32 temp_register;
+	u32 base;
+	u32 rc;
+	struct pci_func *next;
+	int index = 0;
+	struct pci_bus *pci_bus = ctrl->pci_bus;
+	unsigned int devfn;
+
+	func = cpqhp_slot_find(func->bus, func->device, index++);
+
+	while (func != NULL) {
+		pci_bus->number = func->bus;
+		devfn = PCI_DEVFN(func->device, func->function);
+
+		/* Check for Bridge */
+		pci_bus_read_config_byte (pci_bus, devfn, PCI_HEADER_TYPE, &header_type);
+
+		if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE) {
+			pci_bus_read_config_byte (pci_bus, devfn, PCI_SECONDARY_BUS, &secondary_bus);
+
+			sub_bus = (int) secondary_bus;
+
+			next = cpqhp_slot_list[sub_bus];
+
+			while (next != NULL) {
+				rc = cpqhp_save_base_addr_length(ctrl, next);
+				if (rc)
+					return rc;
+
+				next = next->next;
+			}
+			pci_bus->number = func->bus;
+
+			/* FIXME: this loop is duplicated in the non-bridge
+			 * case.  The two could be rolled together Figure out
+			 * IO and memory base lengths
+			 */
+			for (cloop = 0x10; cloop <= 0x14; cloop += 4) {
+				temp_register = 0xFFFFFFFF;
+				pci_bus_write_config_dword (pci_bus, devfn, cloop, temp_register);
+				pci_bus_read_config_dword (pci_bus, devfn, cloop, &base);
+				/* If this register is implemented */
+				if (base) {
+					if (base & 0x01L) {
+						/* IO base
+						 * set base = amount of IO space
+						 * requested
+						 */
+						base = base & 0xFFFFFFFE;
+						base = (~base) + 1;
+
+						type = 1;
+					} else {
+						/* memory base */
+						base = base & 0xFFFFFFF0;
+						base = (~base) + 1;
+
+						type = 0;
+					}
+				} else {
+					base = 0x0L;
+					type = 0;
+				}
+
+				/* Save information in slot structure */
+				func->base_length[(cloop - 0x10) >> 2] =
+				base;
+				func->base_type[(cloop - 0x10) >> 2] = type;
+
+			}	/* End of base register loop */
+
+		} else if ((header_type & 0x7F) == 0x00) {
+			/* Figure out IO and memory base lengths */
+			for (cloop = 0x10; cloop <= 0x24; cloop += 4) {
+				temp_register = 0xFFFFFFFF;
+				pci_bus_write_config_dword (pci_bus, devfn, cloop, temp_register);
+				pci_bus_read_config_dword (pci_bus, devfn, cloop, &base);
+
+				/* If this register is implemented */
+				if (base) {
+					if (base & 0x01L) {
+						/* IO base
+						 * base = amount of IO space
+						 * requested
+						 */
+						base = base & 0xFFFFFFFE;
+						base = (~base) + 1;
+
+						type = 1;
+					} else {
+						/* memory base
+						 * base = amount of memory
+						 * space requested
+						 */
+						base = base & 0xFFFFFFF0;
+						base = (~base) + 1;
+
+						type = 0;
+					}
+				} else {
+					base = 0x0L;
+					type = 0;
+				}
+
+				/* Save information in slot structure */
+				func->base_length[(cloop - 0x10) >> 2] = base;
+				func->base_type[(cloop - 0x10) >> 2] = type;
+
+			}	/* End of base register loop */
+
+		} else {	  /* Some other unknown header type */
+		}
+
+		/* find the next device in this slot */
+		func = cpqhp_slot_find(func->bus, func->device, index++);
+	}
+
+	return(0);
+}
+
+
+/*
+ * cpqhp_save_used_resources
+ *
+ * Stores used resource information for existing boards.  this is
+ * for boards that were in the system when this driver was loaded.
+ * this function is for hot plug ADD
+ *
+ * returns 0 if success
+ */
+int cpqhp_save_used_resources (struct controller *ctrl, struct pci_func * func)
+{
+	u8 cloop;
+	u8 header_type;
+	u8 secondary_bus;
+	u8 temp_byte;
+	u8 b_base;
+	u8 b_length;
+	u16 command;
+	u16 save_command;
+	u16 w_base;
+	u16 w_length;
+	u32 temp_register;
+	u32 save_base;
+	u32 base;
+	int index = 0;
+	struct pci_resource *mem_node;
+	struct pci_resource *p_mem_node;
+	struct pci_resource *io_node;
+	struct pci_resource *bus_node;
+	struct pci_bus *pci_bus = ctrl->pci_bus;
+	unsigned int devfn;
+
+	func = cpqhp_slot_find(func->bus, func->device, index++);
+
+	while ((func != NULL) && func->is_a_board) {
+		pci_bus->number = func->bus;
+		devfn = PCI_DEVFN(func->device, func->function);
+
+		/* Save the command register */
+		pci_bus_read_config_word(pci_bus, devfn, PCI_COMMAND, &save_command);
+
+		/* disable card */
+		command = 0x00;
+		pci_bus_write_config_word(pci_bus, devfn, PCI_COMMAND, command);
+
+		/* Check for Bridge */
+		pci_bus_read_config_byte(pci_bus, devfn, PCI_HEADER_TYPE, &header_type);
+
+		if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE) {
+			/* Clear Bridge Control Register */
+			command = 0x00;
+			pci_bus_write_config_word(pci_bus, devfn, PCI_BRIDGE_CONTROL, command);
+			pci_bus_read_config_byte(pci_bus, devfn, PCI_SECONDARY_BUS, &secondary_bus);
+			pci_bus_read_config_byte(pci_bus, devfn, PCI_SUBORDINATE_BUS, &temp_byte);
+
+			bus_node = kmalloc(sizeof(*bus_node), GFP_KERNEL);
+			if (!bus_node)
+				return -ENOMEM;
+
+			bus_node->base = secondary_bus;
+			bus_node->length = temp_byte - secondary_bus + 1;
+
+			bus_node->next = func->bus_head;
+			func->bus_head = bus_node;
+
+			/* Save IO base and Limit registers */
+			pci_bus_read_config_byte(pci_bus, devfn, PCI_IO_BASE, &b_base);
+			pci_bus_read_config_byte(pci_bus, devfn, PCI_IO_LIMIT, &b_length);
+
+			if ((b_base <= b_length) && (save_command & 0x01)) {
+				io_node = kmalloc(sizeof(*io_node), GFP_KERNEL);
+				if (!io_node)
+					return -ENOMEM;
+
+				io_node->base = (b_base & 0xF0) << 8;
+				io_node->length = (b_length - b_base + 0x10) << 8;
+
+				io_node->next = func->io_head;
+				func->io_head = io_node;
+			}
+
+			/* Save memory base and Limit registers */
+			pci_bus_read_config_word(pci_bus, devfn, PCI_MEMORY_BASE, &w_base);
+			pci_bus_read_config_word(pci_bus, devfn, PCI_MEMORY_LIMIT, &w_length);
+
+			if ((w_base <= w_length) && (save_command & 0x02)) {
+				mem_node = kmalloc(sizeof(*mem_node), GFP_KERNEL);
+				if (!mem_node)
+					return -ENOMEM;
+
+				mem_node->base = w_base << 16;
+				mem_node->length = (w_length - w_base + 0x10) << 16;
+
+				mem_node->next = func->mem_head;
+				func->mem_head = mem_node;
+			}
+
+			/* Save prefetchable memory base and Limit registers */
+			pci_bus_read_config_word(pci_bus, devfn, PCI_PREF_MEMORY_BASE, &w_base);
+			pci_bus_read_config_word(pci_bus, devfn, PCI_PREF_MEMORY_LIMIT, &w_length);
+
+			if ((w_base <= w_length) && (save_command & 0x02)) {
+				p_mem_node = kmalloc(sizeof(*p_mem_node), GFP_KERNEL);
+				if (!p_mem_node)
+					return -ENOMEM;
+
+				p_mem_node->base = w_base << 16;
+				p_mem_node->length = (w_length - w_base + 0x10) << 16;
+
+				p_mem_node->next = func->p_mem_head;
+				func->p_mem_head = p_mem_node;
+			}
+			/* Figure out IO and memory base lengths */
+			for (cloop = 0x10; cloop <= 0x14; cloop += 4) {
+				pci_bus_read_config_dword (pci_bus, devfn, cloop, &save_base);
+
+				temp_register = 0xFFFFFFFF;
+				pci_bus_write_config_dword(pci_bus, devfn, cloop, temp_register);
+				pci_bus_read_config_dword(pci_bus, devfn, cloop, &base);
+
+				temp_register = base;
+
+				/* If this register is implemented */
+				if (base) {
+					if (((base & 0x03L) == 0x01)
+					    && (save_command & 0x01)) {
+						/* IO base
+						 * set temp_register = amount
+						 * of IO space requested
+						 */
+						temp_register = base & 0xFFFFFFFE;
+						temp_register = (~temp_register) + 1;
+
+						io_node = kmalloc(sizeof(*io_node),
+								GFP_KERNEL);
+						if (!io_node)
+							return -ENOMEM;
+
+						io_node->base =
+						save_base & (~0x03L);
+						io_node->length = temp_register;
+
+						io_node->next = func->io_head;
+						func->io_head = io_node;
+					} else
+						if (((base & 0x0BL) == 0x08)
+						    && (save_command & 0x02)) {
+						/* prefetchable memory base */
+						temp_register = base & 0xFFFFFFF0;
+						temp_register = (~temp_register) + 1;
+
+						p_mem_node = kmalloc(sizeof(*p_mem_node),
+								GFP_KERNEL);
+						if (!p_mem_node)
+							return -ENOMEM;
+
+						p_mem_node->base = save_base & (~0x0FL);
+						p_mem_node->length = temp_register;
+
+						p_mem_node->next = func->p_mem_head;
+						func->p_mem_head = p_mem_node;
+					} else
+						if (((base & 0x0BL) == 0x00)
+						    && (save_command & 0x02)) {
+						/* prefetchable memory base */
+						temp_register = base & 0xFFFFFFF0;
+						temp_register = (~temp_register) + 1;
+
+						mem_node = kmalloc(sizeof(*mem_node),
+								GFP_KERNEL);
+						if (!mem_node)
+							return -ENOMEM;
+
+						mem_node->base = save_base & (~0x0FL);
+						mem_node->length = temp_register;
+
+						mem_node->next = func->mem_head;
+						func->mem_head = mem_node;
+					} else
+						return(1);
+				}
+			}	/* End of base register loop */
+		/* Standard header */
+		} else if ((header_type & 0x7F) == 0x00) {
+			/* Figure out IO and memory base lengths */
+			for (cloop = 0x10; cloop <= 0x24; cloop += 4) {
+				pci_bus_read_config_dword(pci_bus, devfn, cloop, &save_base);
+
+				temp_register = 0xFFFFFFFF;
+				pci_bus_write_config_dword(pci_bus, devfn, cloop, temp_register);
+				pci_bus_read_config_dword(pci_bus, devfn, cloop, &base);
+
+				temp_register = base;
+
+				/* If this register is implemented */
+				if (base) {
+					if (((base & 0x03L) == 0x01)
+					    && (save_command & 0x01)) {
+						/* IO base
+						 * set temp_register = amount
+						 * of IO space requested
+						 */
+						temp_register = base & 0xFFFFFFFE;
+						temp_register = (~temp_register) + 1;
+
+						io_node = kmalloc(sizeof(*io_node),
+								GFP_KERNEL);
+						if (!io_node)
+							return -ENOMEM;
+
+						io_node->base = save_base & (~0x01L);
+						io_node->length = temp_register;
+
+						io_node->next = func->io_head;
+						func->io_head = io_node;
+					} else
+						if (((base & 0x0BL) == 0x08)
+						    && (save_command & 0x02)) {
+						/* prefetchable memory base */
+						temp_register = base & 0xFFFFFFF0;
+						temp_register = (~temp_register) + 1;
+
+						p_mem_node = kmalloc(sizeof(*p_mem_node),
+								GFP_KERNEL);
+						if (!p_mem_node)
+							return -ENOMEM;
+
+						p_mem_node->base = save_base & (~0x0FL);
+						p_mem_node->length = temp_register;
+
+						p_mem_node->next = func->p_mem_head;
+						func->p_mem_head = p_mem_node;
+					} else
+						if (((base & 0x0BL) == 0x00)
+						    && (save_command & 0x02)) {
+						/* prefetchable memory base */
+						temp_register = base & 0xFFFFFFF0;
+						temp_register = (~temp_register) + 1;
+
+						mem_node = kmalloc(sizeof(*mem_node),
+								GFP_KERNEL);
+						if (!mem_node)
+							return -ENOMEM;
+
+						mem_node->base = save_base & (~0x0FL);
+						mem_node->length = temp_register;
+
+						mem_node->next = func->mem_head;
+						func->mem_head = mem_node;
+					} else
+						return(1);
+				}
+			}	/* End of base register loop */
+		}
+
+		/* find the next device in this slot */
+		func = cpqhp_slot_find(func->bus, func->device, index++);
+	}
+
+	return 0;
+}
+
+
+/*
+ * cpqhp_configure_board
+ *
+ * Copies saved configuration information to one slot.
+ * this is called recursively for bridge devices.
+ * this is for hot plug REPLACE!
+ *
+ * returns 0 if success
+ */
+int cpqhp_configure_board(struct controller *ctrl, struct pci_func * func)
+{
+	int cloop;
+	u8 header_type;
+	u8 secondary_bus;
+	int sub_bus;
+	struct pci_func *next;
+	u32 temp;
+	u32 rc;
+	int index = 0;
+	struct pci_bus *pci_bus = ctrl->pci_bus;
+	unsigned int devfn;
+
+	func = cpqhp_slot_find(func->bus, func->device, index++);
+
+	while (func != NULL) {
+		pci_bus->number = func->bus;
+		devfn = PCI_DEVFN(func->device, func->function);
+
+		/* Start at the top of config space so that the control
+		 * registers are programmed last
+		 */
+		for (cloop = 0x3C; cloop > 0; cloop -= 4)
+			pci_bus_write_config_dword (pci_bus, devfn, cloop, func->config_space[cloop >> 2]);
+
+		pci_bus_read_config_byte (pci_bus, devfn, PCI_HEADER_TYPE, &header_type);
+
+		/* If this is a bridge device, restore subordinate devices */
+		if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE) {
+			pci_bus_read_config_byte (pci_bus, devfn, PCI_SECONDARY_BUS, &secondary_bus);
+
+			sub_bus = (int) secondary_bus;
+
+			next = cpqhp_slot_list[sub_bus];
+
+			while (next != NULL) {
+				rc = cpqhp_configure_board(ctrl, next);
+				if (rc)
+					return rc;
+
+				next = next->next;
+			}
+		} else {
+
+			/* Check all the base Address Registers to make sure
+			 * they are the same.  If not, the board is different.
+			 */
+
+			for (cloop = 16; cloop < 40; cloop += 4) {
+				pci_bus_read_config_dword (pci_bus, devfn, cloop, &temp);
+
+				if (temp != func->config_space[cloop >> 2]) {
+					dbg("Config space compare failure!!! offset = %x\n", cloop);
+					dbg("bus = %x, device = %x, function = %x\n", func->bus, func->device, func->function);
+					dbg("temp = %x, config space = %x\n\n", temp, func->config_space[cloop >> 2]);
+					return 1;
+				}
+			}
+		}
+
+		func->configured = 1;
+
+		func = cpqhp_slot_find(func->bus, func->device, index++);
+	}
+
+	return 0;
+}
+
+
+/*
+ * cpqhp_valid_replace
+ *
+ * this function checks to see if a board is the same as the
+ * one it is replacing.  this check will detect if the device's
+ * vendor or device id's are the same
+ *
+ * returns 0 if the board is the same nonzero otherwise
+ */
+int cpqhp_valid_replace(struct controller *ctrl, struct pci_func * func)
+{
+	u8 cloop;
+	u8 header_type;
+	u8 secondary_bus;
+	u8 type;
+	u32 temp_register = 0;
+	u32 base;
+	u32 rc;
+	struct pci_func *next;
+	int index = 0;
+	struct pci_bus *pci_bus = ctrl->pci_bus;
+	unsigned int devfn;
+
+	if (!func->is_a_board)
+		return(ADD_NOT_SUPPORTED);
+
+	func = cpqhp_slot_find(func->bus, func->device, index++);
+
+	while (func != NULL) {
+		pci_bus->number = func->bus;
+		devfn = PCI_DEVFN(func->device, func->function);
+
+		pci_bus_read_config_dword (pci_bus, devfn, PCI_VENDOR_ID, &temp_register);
+
+		/* No adapter present */
+		if (temp_register == 0xFFFFFFFF)
+			return(NO_ADAPTER_PRESENT);
+
+		if (temp_register != func->config_space[0])
+			return(ADAPTER_NOT_SAME);
+
+		/* Check for same revision number and class code */
+		pci_bus_read_config_dword (pci_bus, devfn, PCI_CLASS_REVISION, &temp_register);
+
+		/* Adapter not the same */
+		if (temp_register != func->config_space[0x08 >> 2])
+			return(ADAPTER_NOT_SAME);
+
+		/* Check for Bridge */
+		pci_bus_read_config_byte (pci_bus, devfn, PCI_HEADER_TYPE, &header_type);
+
+		if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE) {
+			/* In order to continue checking, we must program the
+			 * bus registers in the bridge to respond to accesses
+			 * for its subordinate bus(es)
+			 */
+
+			temp_register = func->config_space[0x18 >> 2];
+			pci_bus_write_config_dword (pci_bus, devfn, PCI_PRIMARY_BUS, temp_register);
+
+			secondary_bus = (temp_register >> 8) & 0xFF;
+
+			next = cpqhp_slot_list[secondary_bus];
+
+			while (next != NULL) {
+				rc = cpqhp_valid_replace(ctrl, next);
+				if (rc)
+					return rc;
+
+				next = next->next;
+			}
+
+		}
+		/* Check to see if it is a standard config header */
+		else if ((header_type & 0x7F) == PCI_HEADER_TYPE_NORMAL) {
+			/* Check subsystem vendor and ID */
+			pci_bus_read_config_dword (pci_bus, devfn, PCI_SUBSYSTEM_VENDOR_ID, &temp_register);
+
+			if (temp_register != func->config_space[0x2C >> 2]) {
+				/* If it's a SMART-2 and the register isn't
+				 * filled in, ignore the difference because
+				 * they just have an old rev of the firmware
+				 */
+				if (!((func->config_space[0] == 0xAE100E11)
+				      && (temp_register == 0x00L)))
+					return(ADAPTER_NOT_SAME);
+			}
+			/* Figure out IO and memory base lengths */
+			for (cloop = 0x10; cloop <= 0x24; cloop += 4) {
+				temp_register = 0xFFFFFFFF;
+				pci_bus_write_config_dword (pci_bus, devfn, cloop, temp_register);
+				pci_bus_read_config_dword (pci_bus, devfn, cloop, &base);
+
+				/* If this register is implemented */
+				if (base) {
+					if (base & 0x01L) {
+						/* IO base
+						 * set base = amount of IO
+						 * space requested
+						 */
+						base = base & 0xFFFFFFFE;
+						base = (~base) + 1;
+
+						type = 1;
+					} else {
+						/* memory base */
+						base = base & 0xFFFFFFF0;
+						base = (~base) + 1;
+
+						type = 0;
+					}
+				} else {
+					base = 0x0L;
+					type = 0;
+				}
+
+				/* Check information in slot structure */
+				if (func->base_length[(cloop - 0x10) >> 2] != base)
+					return(ADAPTER_NOT_SAME);
+
+				if (func->base_type[(cloop - 0x10) >> 2] != type)
+					return(ADAPTER_NOT_SAME);
+
+			}	/* End of base register loop */
+
+		}		/* End of (type 0 config space) else */
+		else {
+			/* this is not a type 0 or 1 config space header so
+			 * we don't know how to do it
+			 */
+			return(DEVICE_TYPE_NOT_SUPPORTED);
+		}
+
+		/* Get the next function */
+		func = cpqhp_slot_find(func->bus, func->device, index++);
+	}
+
+
+	return 0;
+}
+
+
+/*
+ * cpqhp_find_available_resources
+ *
+ * Finds available memory, IO, and IRQ resources for programming
+ * devices which may be added to the system
+ * this function is for hot plug ADD!
+ *
+ * returns 0 if success
+ */
+int cpqhp_find_available_resources(struct controller *ctrl, void __iomem *rom_start)
+{
+	u8 temp;
+	u8 populated_slot;
+	u8 bridged_slot;
+	void __iomem *one_slot;
+	void __iomem *rom_resource_table;
+	struct pci_func *func = NULL;
+	int i = 10, index;
+	u32 temp_dword, rc;
+	struct pci_resource *mem_node;
+	struct pci_resource *p_mem_node;
+	struct pci_resource *io_node;
+	struct pci_resource *bus_node;
+
+	rom_resource_table = detect_HRT_floating_pointer(rom_start, rom_start+0xffff);
+	dbg("rom_resource_table = %p\n", rom_resource_table);
+
+	if (rom_resource_table == NULL)
+		return -ENODEV;
+
+	/* Sum all resources and setup resource maps */
+	unused_IRQ = readl(rom_resource_table + UNUSED_IRQ);
+	dbg("unused_IRQ = %x\n", unused_IRQ);
+
+	temp = 0;
+	while (unused_IRQ) {
+		if (unused_IRQ & 1) {
+			cpqhp_disk_irq = temp;
+			break;
+		}
+		unused_IRQ = unused_IRQ >> 1;
+		temp++;
+	}
+
+	dbg("cpqhp_disk_irq= %d\n", cpqhp_disk_irq);
+	unused_IRQ = unused_IRQ >> 1;
+	temp++;
+
+	while (unused_IRQ) {
+		if (unused_IRQ & 1) {
+			cpqhp_nic_irq = temp;
+			break;
+		}
+		unused_IRQ = unused_IRQ >> 1;
+		temp++;
+	}
+
+	dbg("cpqhp_nic_irq= %d\n", cpqhp_nic_irq);
+	unused_IRQ = readl(rom_resource_table + PCIIRQ);
+
+	temp = 0;
+
+	if (!cpqhp_nic_irq)
+		cpqhp_nic_irq = ctrl->cfgspc_irq;
+
+	if (!cpqhp_disk_irq)
+		cpqhp_disk_irq = ctrl->cfgspc_irq;
+
+	dbg("cpqhp_disk_irq, cpqhp_nic_irq= %d, %d\n", cpqhp_disk_irq, cpqhp_nic_irq);
+
+	rc = compaq_nvram_load(rom_start, ctrl);
+	if (rc)
+		return rc;
+
+	one_slot = rom_resource_table + sizeof (struct hrt);
+
+	i = readb(rom_resource_table + NUMBER_OF_ENTRIES);
+	dbg("number_of_entries = %d\n", i);
+
+	if (!readb(one_slot + SECONDARY_BUS))
+		return 1;
+
+	dbg("dev|IO base|length|Mem base|length|Pre base|length|PB SB MB\n");
+
+	while (i && readb(one_slot + SECONDARY_BUS)) {
+		u8 dev_func = readb(one_slot + DEV_FUNC);
+		u8 primary_bus = readb(one_slot + PRIMARY_BUS);
+		u8 secondary_bus = readb(one_slot + SECONDARY_BUS);
+		u8 max_bus = readb(one_slot + MAX_BUS);
+		u16 io_base = readw(one_slot + IO_BASE);
+		u16 io_length = readw(one_slot + IO_LENGTH);
+		u16 mem_base = readw(one_slot + MEM_BASE);
+		u16 mem_length = readw(one_slot + MEM_LENGTH);
+		u16 pre_mem_base = readw(one_slot + PRE_MEM_BASE);
+		u16 pre_mem_length = readw(one_slot + PRE_MEM_LENGTH);
+
+		dbg("%2.2x | %4.4x  | %4.4x | %4.4x   | %4.4x | %4.4x   | %4.4x |%2.2x %2.2x %2.2x\n",
+		    dev_func, io_base, io_length, mem_base, mem_length, pre_mem_base, pre_mem_length,
+		    primary_bus, secondary_bus, max_bus);
+
+		/* If this entry isn't for our controller's bus, ignore it */
+		if (primary_bus != ctrl->bus) {
+			i--;
+			one_slot += sizeof (struct slot_rt);
+			continue;
+		}
+		/* find out if this entry is for an occupied slot */
+		ctrl->pci_bus->number = primary_bus;
+		pci_bus_read_config_dword (ctrl->pci_bus, dev_func, PCI_VENDOR_ID, &temp_dword);
+		dbg("temp_D_word = %x\n", temp_dword);
+
+		if (temp_dword != 0xFFFFFFFF) {
+			index = 0;
+			func = cpqhp_slot_find(primary_bus, dev_func >> 3, 0);
+
+			while (func && (func->function != (dev_func & 0x07))) {
+				dbg("func = %p (bus, dev, fun) = (%d, %d, %d)\n", func, primary_bus, dev_func >> 3, index);
+				func = cpqhp_slot_find(primary_bus, dev_func >> 3, index++);
+			}
+
+			/* If we can't find a match, skip this table entry */
+			if (!func) {
+				i--;
+				one_slot += sizeof (struct slot_rt);
+				continue;
+			}
+			/* this may not work and shouldn't be used */
+			if (secondary_bus != primary_bus)
+				bridged_slot = 1;
+			else
+				bridged_slot = 0;
+
+			populated_slot = 1;
+		} else {
+			populated_slot = 0;
+			bridged_slot = 0;
+		}
+
+
+		/* If we've got a valid IO base, use it */
+
+		temp_dword = io_base + io_length;
+
+		if ((io_base) && (temp_dword < 0x10000)) {
+			io_node = kmalloc(sizeof(*io_node), GFP_KERNEL);
+			if (!io_node)
+				return -ENOMEM;
+
+			io_node->base = io_base;
+			io_node->length = io_length;
+
+			dbg("found io_node(base, length) = %x, %x\n",
+					io_node->base, io_node->length);
+			dbg("populated slot =%d \n", populated_slot);
+			if (!populated_slot) {
+				io_node->next = ctrl->io_head;
+				ctrl->io_head = io_node;
+			} else {
+				io_node->next = func->io_head;
+				func->io_head = io_node;
+			}
+		}
+
+		/* If we've got a valid memory base, use it */
+		temp_dword = mem_base + mem_length;
+		if ((mem_base) && (temp_dword < 0x10000)) {
+			mem_node = kmalloc(sizeof(*mem_node), GFP_KERNEL);
+			if (!mem_node)
+				return -ENOMEM;
+
+			mem_node->base = mem_base << 16;
+
+			mem_node->length = mem_length << 16;
+
+			dbg("found mem_node(base, length) = %x, %x\n",
+					mem_node->base, mem_node->length);
+			dbg("populated slot =%d \n", populated_slot);
+			if (!populated_slot) {
+				mem_node->next = ctrl->mem_head;
+				ctrl->mem_head = mem_node;
+			} else {
+				mem_node->next = func->mem_head;
+				func->mem_head = mem_node;
+			}
+		}
+
+		/* If we've got a valid prefetchable memory base, and
+		 * the base + length isn't greater than 0xFFFF
+		 */
+		temp_dword = pre_mem_base + pre_mem_length;
+		if ((pre_mem_base) && (temp_dword < 0x10000)) {
+			p_mem_node = kmalloc(sizeof(*p_mem_node), GFP_KERNEL);
+			if (!p_mem_node)
+				return -ENOMEM;
+
+			p_mem_node->base = pre_mem_base << 16;
+
+			p_mem_node->length = pre_mem_length << 16;
+			dbg("found p_mem_node(base, length) = %x, %x\n",
+					p_mem_node->base, p_mem_node->length);
+			dbg("populated slot =%d \n", populated_slot);
+
+			if (!populated_slot) {
+				p_mem_node->next = ctrl->p_mem_head;
+				ctrl->p_mem_head = p_mem_node;
+			} else {
+				p_mem_node->next = func->p_mem_head;
+				func->p_mem_head = p_mem_node;
+			}
+		}
+
+		/* If we've got a valid bus number, use it
+		 * The second condition is to ignore bus numbers on
+		 * populated slots that don't have PCI-PCI bridges
+		 */
+		if (secondary_bus && (secondary_bus != primary_bus)) {
+			bus_node = kmalloc(sizeof(*bus_node), GFP_KERNEL);
+			if (!bus_node)
+				return -ENOMEM;
+
+			bus_node->base = secondary_bus;
+			bus_node->length = max_bus - secondary_bus + 1;
+			dbg("found bus_node(base, length) = %x, %x\n",
+					bus_node->base, bus_node->length);
+			dbg("populated slot =%d \n", populated_slot);
+			if (!populated_slot) {
+				bus_node->next = ctrl->bus_head;
+				ctrl->bus_head = bus_node;
+			} else {
+				bus_node->next = func->bus_head;
+				func->bus_head = bus_node;
+			}
+		}
+
+		i--;
+		one_slot += sizeof (struct slot_rt);
+	}
+
+	/* If all of the following fail, we don't have any resources for
+	 * hot plug add
+	 */
+	rc = 1;
+	rc &= cpqhp_resource_sort_and_combine(&(ctrl->mem_head));
+	rc &= cpqhp_resource_sort_and_combine(&(ctrl->p_mem_head));
+	rc &= cpqhp_resource_sort_and_combine(&(ctrl->io_head));
+	rc &= cpqhp_resource_sort_and_combine(&(ctrl->bus_head));
+
+	return rc;
+}
+
+
+/*
+ * cpqhp_return_board_resources
+ *
+ * this routine returns all resources allocated to a board to
+ * the available pool.
+ *
+ * returns 0 if success
+ */
+int cpqhp_return_board_resources(struct pci_func * func, struct resource_lists * resources)
+{
+	int rc = 0;
+	struct pci_resource *node;
+	struct pci_resource *t_node;
+	dbg("%s\n", __func__);
+
+	if (!func)
+		return 1;
+
+	node = func->io_head;
+	func->io_head = NULL;
+	while (node) {
+		t_node = node->next;
+		return_resource(&(resources->io_head), node);
+		node = t_node;
+	}
+
+	node = func->mem_head;
+	func->mem_head = NULL;
+	while (node) {
+		t_node = node->next;
+		return_resource(&(resources->mem_head), node);
+		node = t_node;
+	}
+
+	node = func->p_mem_head;
+	func->p_mem_head = NULL;
+	while (node) {
+		t_node = node->next;
+		return_resource(&(resources->p_mem_head), node);
+		node = t_node;
+	}
+
+	node = func->bus_head;
+	func->bus_head = NULL;
+	while (node) {
+		t_node = node->next;
+		return_resource(&(resources->bus_head), node);
+		node = t_node;
+	}
+
+	rc |= cpqhp_resource_sort_and_combine(&(resources->mem_head));
+	rc |= cpqhp_resource_sort_and_combine(&(resources->p_mem_head));
+	rc |= cpqhp_resource_sort_and_combine(&(resources->io_head));
+	rc |= cpqhp_resource_sort_and_combine(&(resources->bus_head));
+
+	return rc;
+}
+
+
+/*
+ * cpqhp_destroy_resource_list
+ *
+ * Puts node back in the resource list pointed to by head
+ */
+void cpqhp_destroy_resource_list (struct resource_lists * resources)
+{
+	struct pci_resource *res, *tres;
+
+	res = resources->io_head;
+	resources->io_head = NULL;
+
+	while (res) {
+		tres = res;
+		res = res->next;
+		kfree(tres);
+	}
+
+	res = resources->mem_head;
+	resources->mem_head = NULL;
+
+	while (res) {
+		tres = res;
+		res = res->next;
+		kfree(tres);
+	}
+
+	res = resources->p_mem_head;
+	resources->p_mem_head = NULL;
+
+	while (res) {
+		tres = res;
+		res = res->next;
+		kfree(tres);
+	}
+
+	res = resources->bus_head;
+	resources->bus_head = NULL;
+
+	while (res) {
+		tres = res;
+		res = res->next;
+		kfree(tres);
+	}
+}
+
+
+/*
+ * cpqhp_destroy_board_resources
+ *
+ * Puts node back in the resource list pointed to by head
+ */
+void cpqhp_destroy_board_resources (struct pci_func * func)
+{
+	struct pci_resource *res, *tres;
+
+	res = func->io_head;
+	func->io_head = NULL;
+
+	while (res) {
+		tres = res;
+		res = res->next;
+		kfree(tres);
+	}
+
+	res = func->mem_head;
+	func->mem_head = NULL;
+
+	while (res) {
+		tres = res;
+		res = res->next;
+		kfree(tres);
+	}
+
+	res = func->p_mem_head;
+	func->p_mem_head = NULL;
+
+	while (res) {
+		tres = res;
+		res = res->next;
+		kfree(tres);
+	}
+
+	res = func->bus_head;
+	func->bus_head = NULL;
+
+	while (res) {
+		tres = res;
+		res = res->next;
+		kfree(tres);
+	}
+}
+
diff --git a/drivers/pci/hotplug/cpqphp_sysfs.c b/drivers/pci/hotplug/cpqphp_sysfs.c
new file mode 100644
index 00000000..4cb30447
--- /dev/null
+++ b/drivers/pci/hotplug/cpqphp_sysfs.c
@@ -0,0 +1,241 @@
+/*
+ * Compaq Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001,2003 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/proc_fs.h>
+#include <linux/workqueue.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/mutex.h>
+#include <linux/debugfs.h>
+#include "cpqphp.h"
+
+static DEFINE_MUTEX(cpqphp_mutex);
+static int show_ctrl (struct controller *ctrl, char *buf)
+{
+	char *out = buf;
+	int index;
+	struct pci_resource *res;
+
+	out += sprintf(buf, "Free resources: memory\n");
+	index = 11;
+	res = ctrl->mem_head;
+	while (res && index--) {
+		out += sprintf(out, "start = %8.8x, length = %8.8x\n", res->base, res->length);
+		res = res->next;
+	}
+	out += sprintf(out, "Free resources: prefetchable memory\n");
+	index = 11;
+	res = ctrl->p_mem_head;
+	while (res && index--) {
+		out += sprintf(out, "start = %8.8x, length = %8.8x\n", res->base, res->length);
+		res = res->next;
+	}
+	out += sprintf(out, "Free resources: IO\n");
+	index = 11;
+	res = ctrl->io_head;
+	while (res && index--) {
+		out += sprintf(out, "start = %8.8x, length = %8.8x\n", res->base, res->length);
+		res = res->next;
+	}
+	out += sprintf(out, "Free resources: bus numbers\n");
+	index = 11;
+	res = ctrl->bus_head;
+	while (res && index--) {
+		out += sprintf(out, "start = %8.8x, length = %8.8x\n", res->base, res->length);
+		res = res->next;
+	}
+
+	return out - buf;
+}
+
+static int show_dev (struct controller *ctrl, char *buf)
+{
+	char * out = buf;
+	int index;
+	struct pci_resource *res;
+	struct pci_func *new_slot;
+	struct slot *slot;
+
+	slot = ctrl->slot;
+
+	while (slot) {
+		new_slot = cpqhp_slot_find(slot->bus, slot->device, 0);
+		if (!new_slot)
+			break;
+		out += sprintf(out, "assigned resources: memory\n");
+		index = 11;
+		res = new_slot->mem_head;
+		while (res && index--) {
+			out += sprintf(out, "start = %8.8x, length = %8.8x\n", res->base, res->length);
+			res = res->next;
+		}
+		out += sprintf(out, "assigned resources: prefetchable memory\n");
+		index = 11;
+		res = new_slot->p_mem_head;
+		while (res && index--) {
+			out += sprintf(out, "start = %8.8x, length = %8.8x\n", res->base, res->length);
+			res = res->next;
+		}
+		out += sprintf(out, "assigned resources: IO\n");
+		index = 11;
+		res = new_slot->io_head;
+		while (res && index--) {
+			out += sprintf(out, "start = %8.8x, length = %8.8x\n", res->base, res->length);
+			res = res->next;
+		}
+		out += sprintf(out, "assigned resources: bus numbers\n");
+		index = 11;
+		res = new_slot->bus_head;
+		while (res && index--) {
+			out += sprintf(out, "start = %8.8x, length = %8.8x\n", res->base, res->length);
+			res = res->next;
+		}
+		slot=slot->next;
+	}
+
+	return out - buf;
+}
+
+static int spew_debug_info(struct controller *ctrl, char *data, int size)
+{
+	int used;
+
+	used = size - show_ctrl(ctrl, data);
+	used = (size - used) - show_dev(ctrl, &data[used]);
+	return used;
+}
+
+struct ctrl_dbg {
+	int size;
+	char *data;
+	struct controller *ctrl;
+};
+
+#define MAX_OUTPUT	(4*PAGE_SIZE)
+
+static int open(struct inode *inode, struct file *file)
+{
+	struct controller *ctrl = inode->i_private;
+	struct ctrl_dbg *dbg;
+	int retval = -ENOMEM;
+
+	mutex_lock(&cpqphp_mutex);
+	dbg = kmalloc(sizeof(*dbg), GFP_KERNEL);
+	if (!dbg)
+		goto exit;
+	dbg->data = kmalloc(MAX_OUTPUT, GFP_KERNEL);
+	if (!dbg->data) {
+		kfree(dbg);
+		goto exit;
+	}
+	dbg->size = spew_debug_info(ctrl, dbg->data, MAX_OUTPUT);
+	file->private_data = dbg;
+	retval = 0;
+exit:
+	mutex_unlock(&cpqphp_mutex);
+	return retval;
+}
+
+static loff_t lseek(struct file *file, loff_t off, int whence)
+{
+	struct ctrl_dbg *dbg;
+	loff_t new = -1;
+
+	mutex_lock(&cpqphp_mutex);
+	dbg = file->private_data;
+
+	switch (whence) {
+	case 0:
+		new = off;
+		break;
+	case 1:
+		new = file->f_pos + off;
+		break;
+	}
+	if (new < 0 || new > dbg->size) {
+		mutex_unlock(&cpqphp_mutex);
+		return -EINVAL;
+	}
+	mutex_unlock(&cpqphp_mutex);
+	return (file->f_pos = new);
+}
+
+static ssize_t read(struct file *file, char __user *buf,
+		    size_t nbytes, loff_t *ppos)
+{
+	struct ctrl_dbg *dbg = file->private_data;
+	return simple_read_from_buffer(buf, nbytes, ppos, dbg->data, dbg->size);
+}
+
+static int release(struct inode *inode, struct file *file)
+{
+	struct ctrl_dbg *dbg = file->private_data;
+
+	kfree(dbg->data);
+	kfree(dbg);
+	return 0;
+}
+
+static const struct file_operations debug_ops = {
+	.owner = THIS_MODULE,
+	.open = open,
+	.llseek = lseek,
+	.read = read,
+	.release = release,
+};
+
+static struct dentry *root;
+
+void cpqhp_initialize_debugfs(void)
+{
+	if (!root)
+		root = debugfs_create_dir("cpqhp", NULL);
+}
+
+void cpqhp_shutdown_debugfs(void)
+{
+	debugfs_remove(root);
+}
+
+void cpqhp_create_debugfs_files(struct controller *ctrl)
+{
+	ctrl->dentry = debugfs_create_file(dev_name(&ctrl->pci_dev->dev),
+					   S_IRUGO, root, ctrl, &debug_ops);
+}
+
+void cpqhp_remove_debugfs_files(struct controller *ctrl)
+{
+	if (ctrl->dentry)
+		debugfs_remove(ctrl->dentry);
+	ctrl->dentry = NULL;
+}
+
diff --git a/drivers/pci/hotplug/fakephp.c b/drivers/pci/hotplug/fakephp.c
new file mode 100644
index 00000000..17d10e2e
--- /dev/null
+++ b/drivers/pci/hotplug/fakephp.c
@@ -0,0 +1,164 @@
+/* Works like the fakephp driver used to, except a little better.
+ *
+ * - It's possible to remove devices with subordinate busses.
+ * - New PCI devices that appear via any method, not just a fakephp triggered
+ *   rescan, will be noticed.
+ * - Devices that are removed via any method, not just a fakephp triggered
+ *   removal, will also be noticed.
+ *
+ * Uses nothing from the pci-hotplug subsystem.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include "../pci.h"
+
+struct legacy_slot {
+	struct kobject		kobj;
+	struct pci_dev		*dev;
+	struct list_head	list;
+};
+
+static LIST_HEAD(legacy_list);
+
+static ssize_t legacy_show(struct kobject *kobj, struct attribute *attr,
+			   char *buf)
+{
+	struct legacy_slot *slot = container_of(kobj, typeof(*slot), kobj);
+	strcpy(buf, "1\n");
+	return 2;
+}
+
+static void remove_callback(void *data)
+{
+	pci_remove_bus_device((struct pci_dev *)data);
+}
+
+static ssize_t legacy_store(struct kobject *kobj, struct attribute *attr,
+			    const char *buf, size_t len)
+{
+	struct legacy_slot *slot = container_of(kobj, typeof(*slot), kobj);
+	unsigned long val;
+
+	if (strict_strtoul(buf, 0, &val) < 0)
+		return -EINVAL;
+
+	if (val)
+		pci_rescan_bus(slot->dev->bus);
+	else
+		sysfs_schedule_callback(&slot->dev->dev.kobj, remove_callback,
+					slot->dev, THIS_MODULE);
+	return len;
+}
+
+static struct attribute *legacy_attrs[] = {
+	&(struct attribute){ .name = "power", .mode = 0644 },
+	NULL,
+};
+
+static void legacy_release(struct kobject *kobj)
+{
+	struct legacy_slot *slot = container_of(kobj, typeof(*slot), kobj);
+
+	pci_dev_put(slot->dev);
+	kfree(slot);
+}
+
+static struct kobj_type legacy_ktype = {
+	.sysfs_ops = &(const struct sysfs_ops){
+		.store = legacy_store, .show = legacy_show
+	},
+	.release = &legacy_release,
+	.default_attrs = legacy_attrs,
+};
+
+static int legacy_add_slot(struct pci_dev *pdev)
+{
+	struct legacy_slot *slot = kzalloc(sizeof(*slot), GFP_KERNEL);
+
+	if (!slot)
+		return -ENOMEM;
+
+	if (kobject_init_and_add(&slot->kobj, &legacy_ktype,
+				 &pci_slots_kset->kobj, "%s",
+				 dev_name(&pdev->dev))) {
+		dev_warn(&pdev->dev, "Failed to created legacy fake slot\n");
+		return -EINVAL;
+	}
+	slot->dev = pci_dev_get(pdev);
+
+	list_add(&slot->list, &legacy_list);
+
+	return 0;
+}
+
+static int legacy_notify(struct notifier_block *nb,
+			 unsigned long action, void *data)
+{
+	struct pci_dev *pdev = to_pci_dev(data);
+
+	if (action == BUS_NOTIFY_ADD_DEVICE) {
+		legacy_add_slot(pdev);
+	} else if (action == BUS_NOTIFY_DEL_DEVICE) {
+		struct legacy_slot *slot;
+
+		list_for_each_entry(slot, &legacy_list, list)
+			if (slot->dev == pdev)
+				goto found;
+
+		dev_warn(&pdev->dev, "Missing legacy fake slot?");
+		return -ENODEV;
+found:
+		kobject_del(&slot->kobj);
+		list_del(&slot->list);
+		kobject_put(&slot->kobj);
+	}
+
+	return 0;
+}
+
+static struct notifier_block legacy_notifier = {
+	.notifier_call = legacy_notify
+};
+
+static int __init init_legacy(void)
+{
+	struct pci_dev *pdev = NULL;
+
+	/* Add existing devices */
+	for_each_pci_dev(pdev)
+		legacy_add_slot(pdev);
+
+	/* Be alerted of any new ones */
+	bus_register_notifier(&pci_bus_type, &legacy_notifier);
+	return 0;
+}
+module_init(init_legacy);
+
+static void __exit remove_legacy(void)
+{
+	struct legacy_slot *slot, *tmp;
+
+	bus_unregister_notifier(&pci_bus_type, &legacy_notifier);
+
+	list_for_each_entry_safe(slot, tmp, &legacy_list, list) {
+		list_del(&slot->list);
+		kobject_del(&slot->kobj);
+		kobject_put(&slot->kobj);
+	}
+}
+module_exit(remove_legacy);
+
+
+MODULE_AUTHOR("Trent Piepho <xyzzy@speakeasy.org>");
+MODULE_DESCRIPTION("Legacy version of the fakephp interface");
+MODULE_LICENSE("GPL");
diff --git a/drivers/pci/hotplug/ibmphp.h b/drivers/pci/hotplug/ibmphp.h
new file mode 100644
index 00000000..a8d391a4
--- /dev/null
+++ b/drivers/pci/hotplug/ibmphp.h
@@ -0,0 +1,760 @@
+#ifndef __IBMPHP_H
+#define __IBMPHP_H
+
+/*
+ * IBM Hot Plug Controller Driver
+ *
+ * Written By: Jyoti Shah, Tong Yu, Irene Zubarev, IBM Corporation
+ *
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001-2003 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <gregkh@us.ibm.com>
+ *
+ */
+
+#include <linux/pci_hotplug.h>
+
+extern int ibmphp_debug;
+
+#if !defined(MODULE)
+	#define MY_NAME "ibmphpd"
+#else
+	#define MY_NAME THIS_MODULE->name
+#endif
+#define debug(fmt, arg...) do { if (ibmphp_debug == 1) printk(KERN_DEBUG "%s: " fmt , MY_NAME , ## arg); } while (0)
+#define debug_pci(fmt, arg...) do { if (ibmphp_debug) printk(KERN_DEBUG "%s: " fmt , MY_NAME , ## arg); } while (0)
+#define err(format, arg...) printk(KERN_ERR "%s: " format , MY_NAME , ## arg)
+#define info(format, arg...) printk(KERN_INFO "%s: " format , MY_NAME , ## arg)
+#define warn(format, arg...) printk(KERN_WARNING "%s: " format , MY_NAME , ## arg)
+
+
+/* EBDA stuff */
+
+/***********************************************************
+* SLOT CAPABILITY                                          *
+***********************************************************/
+
+#define EBDA_SLOT_133_MAX		0x20
+#define EBDA_SLOT_100_MAX		0x10
+#define EBDA_SLOT_66_MAX		0x02
+#define EBDA_SLOT_PCIX_CAP		0x08
+
+
+/************************************************************
+*  RESOURE TYPE                                             *
+************************************************************/
+
+#define EBDA_RSRC_TYPE_MASK		0x03
+#define EBDA_IO_RSRC_TYPE		0x00
+#define EBDA_MEM_RSRC_TYPE		0x01
+#define EBDA_PFM_RSRC_TYPE		0x03
+#define EBDA_RES_RSRC_TYPE		0x02
+
+
+/*************************************************************
+*  IO RESTRICTION TYPE                                       *
+*************************************************************/
+
+#define EBDA_IO_RESTRI_MASK		0x0c
+#define EBDA_NO_RESTRI			0x00
+#define EBDA_AVO_VGA_ADDR		0x04
+#define EBDA_AVO_VGA_ADDR_AND_ALIA	0x08
+#define EBDA_AVO_ISA_ADDR		0x0c
+
+
+/**************************************************************
+*  DEVICE TYPE DEF                                            *
+**************************************************************/
+
+#define EBDA_DEV_TYPE_MASK		0x10
+#define EBDA_PCI_DEV			0x10
+#define EBDA_NON_PCI_DEV		0x00
+
+
+/***************************************************************
+*  PRIMARY DEF DEFINITION                                      *
+***************************************************************/
+
+#define EBDA_PRI_DEF_MASK		0x20
+#define EBDA_PRI_PCI_BUS_INFO		0x20
+#define EBDA_NORM_DEV_RSRC_INFO		0x00
+
+
+//--------------------------------------------------------------
+// RIO TABLE DATA STRUCTURE
+//--------------------------------------------------------------
+
+struct rio_table_hdr {
+	u8 ver_num; 
+	u8 scal_count;
+	u8 riodev_count;
+	u16 offset;
+};
+
+//-------------------------------------------------------------
+// SCALABILITY DETAIL
+//-------------------------------------------------------------
+
+struct scal_detail {
+	u8 node_id;
+	u32 cbar;
+	u8 port0_node_connect;
+	u8 port0_port_connect;
+	u8 port1_node_connect;
+	u8 port1_port_connect;
+	u8 port2_node_connect;
+	u8 port2_port_connect;
+	u8 chassis_num;
+//	struct list_head scal_detail_list;
+};
+
+//--------------------------------------------------------------
+// RIO DETAIL 
+//--------------------------------------------------------------
+
+struct rio_detail {
+	u8 rio_node_id;
+	u32 bbar;
+	u8 rio_type;
+	u8 owner_id;
+	u8 port0_node_connect;
+	u8 port0_port_connect;
+	u8 port1_node_connect;
+	u8 port1_port_connect;
+	u8 first_slot_num;
+	u8 status;
+	u8 wpindex;
+	u8 chassis_num;
+	struct list_head rio_detail_list;
+};
+
+struct opt_rio {
+	u8 rio_type;
+	u8 chassis_num;
+	u8 first_slot_num;
+	u8 middle_num;
+	struct list_head opt_rio_list;
+};	
+
+struct opt_rio_lo {
+	u8 rio_type;
+	u8 chassis_num;
+	u8 first_slot_num;
+	u8 middle_num;
+	u8 pack_count;
+	struct list_head opt_rio_lo_list;
+};	
+
+/****************************************************************
+*  HPC DESCRIPTOR NODE                                          *
+****************************************************************/
+
+struct ebda_hpc_list {
+	u8 format;
+	u16 num_ctlrs;
+	short phys_addr;
+//      struct list_head ebda_hpc_list;
+};
+/*****************************************************************
+*   IN HPC DATA STRUCTURE, THE ASSOCIATED SLOT AND BUS           *
+*   STRUCTURE                                                    *
+*****************************************************************/
+
+struct ebda_hpc_slot {
+	u8 slot_num;
+	u32 slot_bus_num;
+	u8 ctl_index;
+	u8 slot_cap;
+};
+
+struct ebda_hpc_bus {
+	u32 bus_num;
+	u8 slots_at_33_conv;
+	u8 slots_at_66_conv;
+	u8 slots_at_66_pcix;
+	u8 slots_at_100_pcix;
+	u8 slots_at_133_pcix;
+};
+
+
+/********************************************************************
+*   THREE TYPE OF HOT PLUG CONTROLLER                                *
+********************************************************************/
+
+struct isa_ctlr_access {
+	u16 io_start;
+	u16 io_end;
+};
+
+struct pci_ctlr_access {
+	u8 bus;
+	u8 dev_fun;
+};
+
+struct wpeg_i2c_ctlr_access {
+	ulong wpegbbar;
+	u8 i2c_addr;
+};
+
+#define HPC_DEVICE_ID		0x0246
+#define HPC_SUBSYSTEM_ID	0x0247
+#define HPC_PCI_OFFSET		0x40
+/*************************************************************************
+*   RSTC DESCRIPTOR NODE                                                 *
+*************************************************************************/
+
+struct ebda_rsrc_list {
+	u8 format;
+	u16 num_entries;
+	u16 phys_addr;
+	struct ebda_rsrc_list *next;
+};
+
+
+/***************************************************************************
+*   PCI RSRC NODE                                                          *
+***************************************************************************/
+
+struct ebda_pci_rsrc {
+	u8 rsrc_type;
+	u8 bus_num;
+	u8 dev_fun;
+	u32 start_addr;
+	u32 end_addr;
+	u8 marked;	/* for NVRAM */
+	struct list_head ebda_pci_rsrc_list;
+};
+
+
+/***********************************************************
+* BUS_INFO DATE STRUCTURE                                  *
+***********************************************************/
+
+struct bus_info {
+	u8 slot_min;
+	u8 slot_max;
+	u8 slot_count;
+	u8 busno;
+	u8 controller_id;
+	u8 current_speed;
+	u8 current_bus_mode;
+	u8 index;
+	u8 slots_at_33_conv;
+	u8 slots_at_66_conv;
+	u8 slots_at_66_pcix;
+	u8 slots_at_100_pcix;
+	u8 slots_at_133_pcix;
+	struct list_head bus_info_list;
+};
+
+
+/***********************************************************
+* GLOBAL VARIABLES                                         *
+***********************************************************/
+extern struct list_head ibmphp_ebda_pci_rsrc_head;
+extern struct list_head ibmphp_slot_head;
+/***********************************************************
+* FUNCTION PROTOTYPES                                      *
+***********************************************************/
+
+extern void ibmphp_free_ebda_hpc_queue (void);
+extern int ibmphp_access_ebda (void);
+extern struct slot *ibmphp_get_slot_from_physical_num (u8);
+extern int ibmphp_get_total_hp_slots (void);
+extern void ibmphp_free_ibm_slot (struct slot *);
+extern void ibmphp_free_bus_info_queue (void);
+extern void ibmphp_free_ebda_pci_rsrc_queue (void);
+extern struct bus_info *ibmphp_find_same_bus_num (u32);
+extern int ibmphp_get_bus_index (u8);
+extern u16 ibmphp_get_total_controllers (void);
+extern int ibmphp_register_pci (void);
+
+/* passed parameters */
+#define MEM		0
+#define IO		1
+#define PFMEM		2
+
+/* bit masks */
+#define RESTYPE		0x03
+#define IOMASK		0x00	/* will need to take its complement */
+#define MMASK		0x01
+#define PFMASK		0x03
+#define PCIDEVMASK	0x10	/* we should always have PCI devices */
+#define PRIMARYBUSMASK	0x20
+
+/* pci specific defines */
+#define PCI_VENDOR_ID_NOTVALID		0xFFFF
+#define PCI_HEADER_TYPE_MULTIDEVICE	0x80
+#define PCI_HEADER_TYPE_MULTIBRIDGE	0x81
+
+#define LATENCY		0x64
+#define CACHE		64
+#define DEVICEENABLE	0x015F		/* CPQ has 0x0157 */
+
+#define IOBRIDGE	0x1000		/* 4k */
+#define MEMBRIDGE	0x100000	/* 1M */
+
+/* irqs */
+#define SCSI_IRQ	0x09
+#define LAN_IRQ		0x0A
+#define OTHER_IRQ	0x0B
+
+/* Data Structures */
+
+/* type is of the form x x xx xx
+ *                     | |  |  |_ 00 - I/O, 01 - Memory, 11 - PFMemory
+ *                     | |  - 00 - No Restrictions, 01 - Avoid VGA, 10 - Avoid
+ *                     | |    VGA and their aliases, 11 - Avoid ISA
+ *                     | - 1 - PCI device, 0 - non pci device
+ *                     - 1 - Primary PCI Bus Information (0 if Normal device)
+ * the IO restrictions [2:3] are only for primary buses
+ */
+
+
+/* we need this struct because there could be several resource blocks
+ * allocated per primary bus in the EBDA
+ */
+struct range_node {
+	int rangeno;
+	u32 start;
+	u32 end;
+	struct range_node *next;
+};
+
+struct bus_node {
+	u8 busno;
+	int noIORanges;
+	struct range_node *rangeIO;
+	int noMemRanges;
+	struct range_node *rangeMem;
+	int noPFMemRanges;
+	struct range_node *rangePFMem;
+	int needIOUpdate;
+	int needMemUpdate;
+	int needPFMemUpdate;
+	struct resource_node *firstIO;	/* first IO resource on the Bus */
+	struct resource_node *firstMem;	/* first memory resource on the Bus */
+	struct resource_node *firstPFMem;	/* first prefetchable memory resource on the Bus */
+	struct resource_node *firstPFMemFromMem;	/* when run out of pfmem available, taking from Mem */
+	struct list_head bus_list;
+};
+
+struct resource_node {
+	int rangeno;
+	u8 busno;
+	u8 devfunc;
+	u32 start;
+	u32 end;
+	u32 len;
+	int type;		/* MEM, IO, PFMEM */
+	u8 fromMem;		/* this is to indicate that the range is from
+				 * from the Memory bucket rather than from PFMem */
+	struct resource_node *next;
+	struct resource_node *nextRange;	/* for the other mem range on bus */
+};
+
+struct res_needed {
+	u32 mem;
+	u32 pfmem;
+	u32 io;
+	u8 not_correct;		/* needed for return */
+	int devices[32];	/* for device numbers behind this bridge */
+};
+
+/* functions */
+
+extern int ibmphp_rsrc_init (void);
+extern int ibmphp_add_resource (struct resource_node *);
+extern int ibmphp_remove_resource (struct resource_node *);
+extern int ibmphp_find_resource (struct bus_node *, u32, struct resource_node **, int);
+extern int ibmphp_check_resource (struct resource_node *, u8);
+extern int ibmphp_remove_bus (struct bus_node *, u8);
+extern void ibmphp_free_resources (void);
+extern int ibmphp_add_pfmem_from_mem (struct resource_node *);
+extern struct bus_node *ibmphp_find_res_bus (u8);
+extern void ibmphp_print_test (void);	/* for debugging purposes */
+
+extern void ibmphp_hpc_initvars (void);
+extern int ibmphp_hpc_readslot (struct slot *, u8, u8 *);
+extern int ibmphp_hpc_writeslot (struct slot *, u8);
+extern void ibmphp_lock_operations (void);
+extern void ibmphp_unlock_operations (void);
+extern int ibmphp_hpc_start_poll_thread (void);
+extern void ibmphp_hpc_stop_poll_thread (void);
+
+//----------------------------------------------------------------------------
+
+
+//----------------------------------------------------------------------------
+// HPC return codes
+//----------------------------------------------------------------------------
+#define HPC_ERROR			0xFF
+
+//-----------------------------------------------------------------------------
+// BUS INFO
+//-----------------------------------------------------------------------------
+#define BUS_SPEED			0x30
+#define BUS_MODE			0x40
+#define BUS_MODE_PCIX			0x01
+#define BUS_MODE_PCI			0x00
+#define BUS_SPEED_2			0x20
+#define BUS_SPEED_1			0x10
+#define BUS_SPEED_33			0x00
+#define BUS_SPEED_66			0x01
+#define BUS_SPEED_100			0x02
+#define BUS_SPEED_133			0x03
+#define BUS_SPEED_66PCIX		0x04
+#define BUS_SPEED_66UNKNOWN		0x05
+#define BUS_STATUS_AVAILABLE		0x01
+#define BUS_CONTROL_AVAILABLE		0x02
+#define SLOT_LATCH_REGS_SUPPORTED	0x10
+
+#define PRGM_MODEL_REV_LEVEL		0xF0
+#define MAX_ADAPTER_NONE		0x09
+
+//----------------------------------------------------------------------------
+// HPC 'write' operations/commands
+//----------------------------------------------------------------------------
+//	Command			Code	State	Write to reg
+//					Machine	at index
+//-------------------------	----	-------	------------
+#define HPC_CTLR_ENABLEIRQ	0x00	// N	15
+#define HPC_CTLR_DISABLEIRQ	0x01	// N	15
+#define HPC_SLOT_OFF		0x02	// Y	0-14
+#define HPC_SLOT_ON		0x03	// Y	0-14
+#define HPC_SLOT_ATTNOFF	0x04	// N	0-14
+#define HPC_SLOT_ATTNON		0x05	// N	0-14
+#define HPC_CTLR_CLEARIRQ	0x06	// N	15
+#define HPC_CTLR_RESET		0x07	// Y	15
+#define HPC_CTLR_IRQSTEER	0x08	// N	15
+#define HPC_BUS_33CONVMODE	0x09	// Y	31-34
+#define HPC_BUS_66CONVMODE	0x0A	// Y	31-34
+#define HPC_BUS_66PCIXMODE	0x0B	// Y	31-34
+#define HPC_BUS_100PCIXMODE	0x0C	// Y	31-34
+#define HPC_BUS_133PCIXMODE	0x0D	// Y	31-34
+#define HPC_ALLSLOT_OFF		0x11	// Y	15
+#define HPC_ALLSLOT_ON		0x12	// Y	15
+#define HPC_SLOT_BLINKLED	0x13	// N	0-14
+
+//----------------------------------------------------------------------------
+// read commands
+//----------------------------------------------------------------------------
+#define READ_SLOTSTATUS		0x01
+#define READ_EXTSLOTSTATUS	0x02
+#define READ_BUSSTATUS		0x03
+#define READ_CTLRSTATUS		0x04
+#define READ_ALLSTAT		0x05
+#define READ_ALLSLOT		0x06
+#define READ_SLOTLATCHLOWREG	0x07
+#define READ_REVLEVEL		0x08
+#define READ_HPCOPTIONS		0x09
+//----------------------------------------------------------------------------
+// slot status
+//----------------------------------------------------------------------------
+#define HPC_SLOT_POWER		0x01
+#define HPC_SLOT_CONNECT	0x02
+#define HPC_SLOT_ATTN		0x04
+#define HPC_SLOT_PRSNT2		0x08
+#define HPC_SLOT_PRSNT1		0x10
+#define HPC_SLOT_PWRGD		0x20
+#define HPC_SLOT_BUS_SPEED	0x40
+#define HPC_SLOT_LATCH		0x80
+
+//----------------------------------------------------------------------------
+// HPC_SLOT_POWER status return codes
+//----------------------------------------------------------------------------
+#define HPC_SLOT_POWER_OFF	0x00
+#define HPC_SLOT_POWER_ON	0x01
+
+//----------------------------------------------------------------------------
+// HPC_SLOT_CONNECT status return codes
+//----------------------------------------------------------------------------
+#define HPC_SLOT_CONNECTED	0x00
+#define HPC_SLOT_DISCONNECTED	0x01
+
+//----------------------------------------------------------------------------
+// HPC_SLOT_ATTN status return codes
+//----------------------------------------------------------------------------
+#define HPC_SLOT_ATTN_OFF	0x00
+#define HPC_SLOT_ATTN_ON	0x01
+#define HPC_SLOT_ATTN_BLINK	0x02
+
+//----------------------------------------------------------------------------
+// HPC_SLOT_PRSNT status return codes
+//----------------------------------------------------------------------------
+#define HPC_SLOT_EMPTY		0x00
+#define HPC_SLOT_PRSNT_7	0x01
+#define HPC_SLOT_PRSNT_15	0x02
+#define HPC_SLOT_PRSNT_25	0x03
+
+//----------------------------------------------------------------------------
+// HPC_SLOT_PWRGD status return codes
+//----------------------------------------------------------------------------
+#define HPC_SLOT_PWRGD_FAULT_NONE	0x00
+#define HPC_SLOT_PWRGD_GOOD		0x01
+
+//----------------------------------------------------------------------------
+// HPC_SLOT_BUS_SPEED status return codes
+//----------------------------------------------------------------------------
+#define HPC_SLOT_BUS_SPEED_OK	0x00
+#define HPC_SLOT_BUS_SPEED_MISM	0x01
+
+//----------------------------------------------------------------------------
+// HPC_SLOT_LATCH status return codes
+//----------------------------------------------------------------------------
+#define HPC_SLOT_LATCH_OPEN	0x01	// NOTE : in PCI spec bit off = open
+#define HPC_SLOT_LATCH_CLOSED	0x00	// NOTE : in PCI spec bit on  = closed
+
+
+//----------------------------------------------------------------------------
+// extended slot status
+//----------------------------------------------------------------------------
+#define HPC_SLOT_PCIX		0x01
+#define HPC_SLOT_SPEED1		0x02
+#define HPC_SLOT_SPEED2		0x04
+#define HPC_SLOT_BLINK_ATTN	0x08
+#define HPC_SLOT_RSRVD1		0x10
+#define HPC_SLOT_RSRVD2		0x20
+#define HPC_SLOT_BUS_MODE	0x40
+#define HPC_SLOT_RSRVD3		0x80
+
+//----------------------------------------------------------------------------
+// HPC_XSLOT_PCIX_CAP status return codes
+//----------------------------------------------------------------------------
+#define HPC_SLOT_PCIX_NO	0x00
+#define HPC_SLOT_PCIX_YES	0x01
+
+//----------------------------------------------------------------------------
+// HPC_XSLOT_SPEED status return codes
+//----------------------------------------------------------------------------
+#define HPC_SLOT_SPEED_33	0x00
+#define HPC_SLOT_SPEED_66	0x01
+#define HPC_SLOT_SPEED_133	0x02
+
+//----------------------------------------------------------------------------
+// HPC_XSLOT_ATTN_BLINK status return codes
+//----------------------------------------------------------------------------
+#define HPC_SLOT_ATTN_BLINK_OFF	0x00
+#define HPC_SLOT_ATTN_BLINK_ON	0x01
+
+//----------------------------------------------------------------------------
+// HPC_XSLOT_BUS_MODE status return codes
+//----------------------------------------------------------------------------
+#define HPC_SLOT_BUS_MODE_OK	0x00
+#define HPC_SLOT_BUS_MODE_MISM	0x01
+
+//----------------------------------------------------------------------------
+// Controller status
+//----------------------------------------------------------------------------
+#define HPC_CTLR_WORKING	0x01
+#define HPC_CTLR_FINISHED	0x02
+#define HPC_CTLR_RESULT0	0x04
+#define HPC_CTLR_RESULT1	0x08
+#define HPC_CTLR_RESULE2	0x10
+#define HPC_CTLR_RESULT3	0x20
+#define HPC_CTLR_IRQ_ROUTG	0x40
+#define HPC_CTLR_IRQ_PENDG	0x80
+
+//----------------------------------------------------------------------------
+// HPC_CTLR_WROKING status return codes
+//----------------------------------------------------------------------------
+#define HPC_CTLR_WORKING_NO	0x00
+#define HPC_CTLR_WORKING_YES	0x01
+
+//----------------------------------------------------------------------------
+// HPC_CTLR_FINISHED status return codes
+//----------------------------------------------------------------------------
+#define HPC_CTLR_FINISHED_NO	0x00
+#define HPC_CTLR_FINISHED_YES	0x01
+
+//----------------------------------------------------------------------------
+// HPC_CTLR_RESULT status return codes
+//----------------------------------------------------------------------------
+#define HPC_CTLR_RESULT_SUCCESS	0x00
+#define HPC_CTLR_RESULT_FAILED	0x01
+#define HPC_CTLR_RESULT_RSVD	0x02
+#define HPC_CTLR_RESULT_NORESP	0x03
+
+
+//----------------------------------------------------------------------------
+// macro for slot info
+//----------------------------------------------------------------------------
+#define SLOT_POWER(s)	((u8) ((s & HPC_SLOT_POWER) \
+	? HPC_SLOT_POWER_ON : HPC_SLOT_POWER_OFF))
+
+#define SLOT_CONNECT(s)	((u8) ((s & HPC_SLOT_CONNECT) \
+	? HPC_SLOT_DISCONNECTED : HPC_SLOT_CONNECTED))
+
+#define SLOT_ATTN(s,es)	((u8) ((es & HPC_SLOT_BLINK_ATTN) \
+	? HPC_SLOT_ATTN_BLINK \
+	: ((s & HPC_SLOT_ATTN) ? HPC_SLOT_ATTN_ON : HPC_SLOT_ATTN_OFF)))
+
+#define SLOT_PRESENT(s)	((u8) ((s & HPC_SLOT_PRSNT1) \
+	? ((s & HPC_SLOT_PRSNT2) ? HPC_SLOT_EMPTY : HPC_SLOT_PRSNT_15) \
+	: ((s & HPC_SLOT_PRSNT2) ? HPC_SLOT_PRSNT_25 : HPC_SLOT_PRSNT_7)))
+
+#define SLOT_PWRGD(s)	((u8) ((s & HPC_SLOT_PWRGD) \
+	? HPC_SLOT_PWRGD_GOOD : HPC_SLOT_PWRGD_FAULT_NONE))
+
+#define SLOT_BUS_SPEED(s)	((u8) ((s & HPC_SLOT_BUS_SPEED) \
+	? HPC_SLOT_BUS_SPEED_MISM : HPC_SLOT_BUS_SPEED_OK))
+
+#define SLOT_LATCH(s)	((u8) ((s & HPC_SLOT_LATCH) \
+	? HPC_SLOT_LATCH_CLOSED : HPC_SLOT_LATCH_OPEN))
+
+#define SLOT_PCIX(es)	((u8) ((es & HPC_SLOT_PCIX) \
+	? HPC_SLOT_PCIX_YES : HPC_SLOT_PCIX_NO))
+
+#define SLOT_SPEED(es)	((u8) ((es & HPC_SLOT_SPEED2) \
+	? ((es & HPC_SLOT_SPEED1) ? HPC_SLOT_SPEED_133   \
+				: HPC_SLOT_SPEED_66)   \
+	: HPC_SLOT_SPEED_33))
+
+#define SLOT_BUS_MODE(es)	((u8) ((es & HPC_SLOT_BUS_MODE) \
+	? HPC_SLOT_BUS_MODE_MISM : HPC_SLOT_BUS_MODE_OK))
+
+//--------------------------------------------------------------------------
+// macro for bus info
+//---------------------------------------------------------------------------
+#define CURRENT_BUS_SPEED(s)	((u8) (s & BUS_SPEED_2) \
+	? ((s & BUS_SPEED_1) ? BUS_SPEED_133 : BUS_SPEED_100) \
+	: ((s & BUS_SPEED_1) ? BUS_SPEED_66 : BUS_SPEED_33))
+
+#define CURRENT_BUS_MODE(s)	((u8) (s & BUS_MODE) ? BUS_MODE_PCIX : BUS_MODE_PCI)
+
+#define READ_BUS_STATUS(s)	((u8) (s->options & BUS_STATUS_AVAILABLE))
+
+#define READ_BUS_MODE(s)	((s->revision & PRGM_MODEL_REV_LEVEL) >= 0x20)
+
+#define SET_BUS_STATUS(s)	((u8) (s->options & BUS_CONTROL_AVAILABLE))
+
+#define READ_SLOT_LATCH(s)	((u8) (s->options & SLOT_LATCH_REGS_SUPPORTED))
+
+//----------------------------------------------------------------------------
+// macro for controller info
+//----------------------------------------------------------------------------
+#define CTLR_WORKING(c) ((u8) ((c & HPC_CTLR_WORKING) \
+	? HPC_CTLR_WORKING_YES : HPC_CTLR_WORKING_NO))
+#define CTLR_FINISHED(c) ((u8) ((c & HPC_CTLR_FINISHED) \
+	? HPC_CTLR_FINISHED_YES : HPC_CTLR_FINISHED_NO))
+#define CTLR_RESULT(c) ((u8) ((c & HPC_CTLR_RESULT1)  \
+	? ((c & HPC_CTLR_RESULT0) ? HPC_CTLR_RESULT_NORESP \
+				: HPC_CTLR_RESULT_RSVD)  \
+	: ((c & HPC_CTLR_RESULT0) ? HPC_CTLR_RESULT_FAILED \
+				: HPC_CTLR_RESULT_SUCCESS)))
+
+// command that affect the state machine of HPC
+#define NEEDTOCHECK_CMDSTATUS(c) ((c == HPC_SLOT_OFF)        || \
+				  (c == HPC_SLOT_ON)         || \
+				  (c == HPC_CTLR_RESET)      || \
+				  (c == HPC_BUS_33CONVMODE)  || \
+				  (c == HPC_BUS_66CONVMODE)  || \
+				  (c == HPC_BUS_66PCIXMODE)  || \
+				  (c == HPC_BUS_100PCIXMODE) || \
+				  (c == HPC_BUS_133PCIXMODE) || \
+				  (c == HPC_ALLSLOT_OFF)     || \
+				  (c == HPC_ALLSLOT_ON))
+
+
+/* Core part of the driver */
+
+#define ENABLE		1
+#define DISABLE		0
+
+#define CARD_INFO	0x07
+#define PCIX133		0x07
+#define PCIX66		0x05
+#define PCI66		0x04
+
+extern struct pci_bus *ibmphp_pci_bus;
+
+/* Variables */
+
+struct pci_func {
+	struct pci_dev *dev;	/* from the OS */
+	u8 busno;
+	u8 device;
+	u8 function;
+	struct resource_node *io[6];
+	struct resource_node *mem[6];
+	struct resource_node *pfmem[6];
+	struct pci_func *next;
+	int devices[32];	/* for bridge config */
+	u8 irq[4];		/* for interrupt config */
+	u8 bus;			/* flag for unconfiguring, to say if PPB */
+};
+
+struct slot {
+	u8 bus;
+	u8 device;
+	u8 number;
+	u8 real_physical_slot_num;
+	u32 capabilities;
+	u8 supported_speed;
+	u8 supported_bus_mode;
+	u8 flag;		/* this is for disable slot and polling */
+	u8 ctlr_index;
+	struct hotplug_slot *hotplug_slot;
+	struct controller *ctrl;
+	struct pci_func *func;
+	u8 irq[4];
+	int bit_mode;		/* 0 = 32, 1 = 64 */
+	struct bus_info *bus_on;
+	struct list_head ibm_slot_list;
+	u8 status;
+	u8 ext_status;
+	u8 busstatus;
+};
+
+struct controller {
+	struct ebda_hpc_slot *slots;
+	struct ebda_hpc_bus *buses;
+	struct pci_dev *ctrl_dev; /* in case where controller is PCI */
+	u8 starting_slot_num;	/* starting and ending slot #'s this ctrl controls*/
+	u8 ending_slot_num;
+	u8 revision;
+	u8 options;		/* which options HPC supports */
+	u8 status;
+	u8 ctlr_id;
+	u8 slot_count;
+	u8 bus_count;
+	u8 ctlr_relative_id;
+	u32 irq;
+	union {
+		struct isa_ctlr_access isa_ctlr;
+		struct pci_ctlr_access pci_ctlr;
+		struct wpeg_i2c_ctlr_access wpeg_ctlr;
+	} u;
+	u8 ctlr_type;
+	struct list_head ebda_hpc_list;
+};
+
+/* Functions */
+
+extern int ibmphp_init_devno (struct slot **);	/* This function is called from EBDA, so we need it not be static */
+extern int ibmphp_do_disable_slot (struct slot *slot_cur);
+extern int ibmphp_update_slot_info (struct slot *);	/* This function is called from HPC, so we need it to not be be static */
+extern int ibmphp_configure_card (struct pci_func *, u8);
+extern int ibmphp_unconfigure_card (struct slot **, int);
+extern struct hotplug_slot_ops ibmphp_hotplug_slot_ops;
+
+#endif				//__IBMPHP_H
+
diff --git a/drivers/pci/hotplug/ibmphp_core.c b/drivers/pci/hotplug/ibmphp_core.c
new file mode 100644
index 00000000..d934dd4f
--- /dev/null
+++ b/drivers/pci/hotplug/ibmphp_core.c
@@ -0,0 +1,1373 @@
+/*
+ * IBM Hot Plug Controller Driver
+ *
+ * Written By: Chuck Cole, Jyoti Shah, Tong Yu, Irene Zubarev, IBM Corporation
+ *
+ * Copyright (C) 2001,2003 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001-2003 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <gregkh@us.ibm.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/wait.h>
+#include "../pci.h"
+#include <asm/pci_x86.h>		/* for struct irq_routing_table */
+#include "ibmphp.h"
+
+#define attn_on(sl)  ibmphp_hpc_writeslot (sl, HPC_SLOT_ATTNON)
+#define attn_off(sl) ibmphp_hpc_writeslot (sl, HPC_SLOT_ATTNOFF)
+#define attn_LED_blink(sl) ibmphp_hpc_writeslot (sl, HPC_SLOT_BLINKLED)
+#define get_ctrl_revision(sl, rev) ibmphp_hpc_readslot (sl, READ_REVLEVEL, rev)
+#define get_hpc_options(sl, opt) ibmphp_hpc_readslot (sl, READ_HPCOPTIONS, opt)
+
+#define DRIVER_VERSION	"0.6"
+#define DRIVER_DESC	"IBM Hot Plug PCI Controller Driver"
+
+int ibmphp_debug;
+
+static int debug;
+module_param(debug, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC (debug, "Debugging mode enabled or not");
+MODULE_LICENSE ("GPL");
+MODULE_DESCRIPTION (DRIVER_DESC);
+
+struct pci_bus *ibmphp_pci_bus;
+static int max_slots;
+
+static int irqs[16];    /* PIC mode IRQ's we're using so far (in case MPS
+			 * tables don't provide default info for empty slots */
+
+static int init_flag;
+
+/*
+static int get_max_adapter_speed_1 (struct hotplug_slot *, u8 *, u8);
+
+static inline int get_max_adapter_speed (struct hotplug_slot *hs, u8 *value)
+{
+	return get_max_adapter_speed_1 (hs, value, 1);
+}
+*/
+static inline int get_cur_bus_info(struct slot **sl) 
+{
+	int rc = 1;
+	struct slot * slot_cur = *sl;
+
+	debug("options = %x\n", slot_cur->ctrl->options);
+	debug("revision = %x\n", slot_cur->ctrl->revision);	
+
+	if (READ_BUS_STATUS(slot_cur->ctrl)) 
+		rc = ibmphp_hpc_readslot(slot_cur, READ_BUSSTATUS, NULL);
+	
+	if (rc) 
+		return rc;
+	  
+	slot_cur->bus_on->current_speed = CURRENT_BUS_SPEED(slot_cur->busstatus);
+	if (READ_BUS_MODE(slot_cur->ctrl))
+		slot_cur->bus_on->current_bus_mode =
+				CURRENT_BUS_MODE(slot_cur->busstatus);
+	else
+		slot_cur->bus_on->current_bus_mode = 0xFF;
+
+	debug("busstatus = %x, bus_speed = %x, bus_mode = %x\n",
+			slot_cur->busstatus,
+			slot_cur->bus_on->current_speed,
+			slot_cur->bus_on->current_bus_mode);
+	
+	*sl = slot_cur;
+	return 0;
+}
+
+static inline int slot_update(struct slot **sl)
+{
+	int rc;
+ 	rc = ibmphp_hpc_readslot(*sl, READ_ALLSTAT, NULL);
+	if (rc) 
+		return rc;
+	if (!init_flag)
+		rc = get_cur_bus_info(sl);
+	return rc;
+}
+
+static int __init get_max_slots (void)
+{
+	struct slot * slot_cur;
+	struct list_head * tmp;
+	u8 slot_count = 0;
+
+	list_for_each(tmp, &ibmphp_slot_head) {
+		slot_cur = list_entry(tmp, struct slot, ibm_slot_list);
+		/* sometimes the hot-pluggable slots start with 4 (not always from 1) */
+		slot_count = max(slot_count, slot_cur->number);
+	}
+	return slot_count;
+}
+
+/* This routine will put the correct slot->device information per slot.  It's
+ * called from initialization of the slot structures. It will also assign
+ * interrupt numbers per each slot.
+ * Parameters: struct slot
+ * Returns 0 or errors
+ */
+int ibmphp_init_devno(struct slot **cur_slot)
+{
+	struct irq_routing_table *rtable;
+	int len;
+	int loop;
+	int i;
+
+	rtable = pcibios_get_irq_routing_table();
+	if (!rtable) {
+		err("no BIOS routing table...\n");
+		return -ENOMEM;
+	}
+
+	len = (rtable->size - sizeof(struct irq_routing_table)) /
+			sizeof(struct irq_info);
+
+	if (!len) {
+		kfree(rtable);
+		return -1;
+	}
+	for (loop = 0; loop < len; loop++) {
+		if ((*cur_slot)->number == rtable->slots[loop].slot &&
+		    (*cur_slot)->bus == rtable->slots[loop].bus) {
+			struct io_apic_irq_attr irq_attr;
+
+			(*cur_slot)->device = PCI_SLOT(rtable->slots[loop].devfn);
+			for (i = 0; i < 4; i++)
+				(*cur_slot)->irq[i] = IO_APIC_get_PCI_irq_vector((int) (*cur_slot)->bus,
+						(int) (*cur_slot)->device, i,
+						&irq_attr);
+
+			debug("(*cur_slot)->irq[0] = %x\n",
+					(*cur_slot)->irq[0]);
+			debug("(*cur_slot)->irq[1] = %x\n",
+					(*cur_slot)->irq[1]);
+			debug("(*cur_slot)->irq[2] = %x\n",
+					(*cur_slot)->irq[2]);
+			debug("(*cur_slot)->irq[3] = %x\n",
+					(*cur_slot)->irq[3]);
+
+			debug("rtable->exlusive_irqs = %x\n",
+					rtable->exclusive_irqs);
+			debug("rtable->slots[loop].irq[0].bitmap = %x\n",
+					rtable->slots[loop].irq[0].bitmap);
+			debug("rtable->slots[loop].irq[1].bitmap = %x\n",
+					rtable->slots[loop].irq[1].bitmap);
+			debug("rtable->slots[loop].irq[2].bitmap = %x\n",
+					rtable->slots[loop].irq[2].bitmap);
+			debug("rtable->slots[loop].irq[3].bitmap = %x\n",
+					rtable->slots[loop].irq[3].bitmap);
+
+			debug("rtable->slots[loop].irq[0].link = %x\n",
+					rtable->slots[loop].irq[0].link);
+			debug("rtable->slots[loop].irq[1].link = %x\n",
+					rtable->slots[loop].irq[1].link);
+			debug("rtable->slots[loop].irq[2].link = %x\n",
+					rtable->slots[loop].irq[2].link);
+			debug("rtable->slots[loop].irq[3].link = %x\n",
+					rtable->slots[loop].irq[3].link);
+			debug("end of init_devno\n");
+			kfree(rtable);
+			return 0;
+		}
+	}
+
+	kfree(rtable);
+	return -1;
+}
+
+static inline int power_on(struct slot *slot_cur)
+{
+	u8 cmd = HPC_SLOT_ON;
+	int retval;
+
+	retval = ibmphp_hpc_writeslot(slot_cur, cmd);
+	if (retval) {
+		err("power on failed\n");
+		return retval;
+	}
+	if (CTLR_RESULT(slot_cur->ctrl->status)) {
+		err("command not completed successfully in power_on\n");
+		return -EIO;
+	}
+	msleep(3000);	/* For ServeRAID cards, and some 66 PCI */
+	return 0;
+}
+
+static inline int power_off(struct slot *slot_cur)
+{
+	u8 cmd = HPC_SLOT_OFF;
+	int retval;
+
+	retval = ibmphp_hpc_writeslot(slot_cur, cmd);
+	if (retval) {
+		err("power off failed\n");
+		return retval;
+	}
+	if (CTLR_RESULT(slot_cur->ctrl->status)) {
+		err("command not completed successfully in power_off\n");
+		retval = -EIO;
+	}
+	return retval;
+}
+
+static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 value)
+{
+	int rc = 0;
+	struct slot *pslot;
+	u8 cmd = 0x00;     /* avoid compiler warning */
+
+	debug("set_attention_status - Entry hotplug_slot[%lx] value[%x]\n",
+			(ulong) hotplug_slot, value);
+	ibmphp_lock_operations();
+
+
+	if (hotplug_slot) {
+		switch (value) {
+		case HPC_SLOT_ATTN_OFF:
+			cmd = HPC_SLOT_ATTNOFF;
+			break;
+		case HPC_SLOT_ATTN_ON:
+			cmd = HPC_SLOT_ATTNON;
+			break;
+		case HPC_SLOT_ATTN_BLINK:
+			cmd = HPC_SLOT_BLINKLED;
+			break;
+		default:
+			rc = -ENODEV;
+			err("set_attention_status - Error : invalid input [%x]\n",
+					value);
+			break;
+		}
+		if (rc == 0) {
+			pslot = hotplug_slot->private;
+			if (pslot)
+				rc = ibmphp_hpc_writeslot(pslot, cmd);
+			else
+				rc = -ENODEV;
+		}
+	} else	
+		rc = -ENODEV;
+
+	ibmphp_unlock_operations();
+
+	debug("set_attention_status - Exit rc[%d]\n", rc);
+	return rc;
+}
+
+static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 * value)
+{
+	int rc = -ENODEV;
+	struct slot *pslot;
+	struct slot myslot;
+
+	debug("get_attention_status - Entry hotplug_slot[%lx] pvalue[%lx]\n",
+					(ulong) hotplug_slot, (ulong) value);
+        
+	ibmphp_lock_operations();
+	if (hotplug_slot) {
+		pslot = hotplug_slot->private;
+		if (pslot) {
+			memcpy(&myslot, pslot, sizeof(struct slot));
+			rc = ibmphp_hpc_readslot(pslot, READ_SLOTSTATUS,
+						&(myslot.status));
+			if (!rc)
+				rc = ibmphp_hpc_readslot(pslot,
+						READ_EXTSLOTSTATUS,
+						&(myslot.ext_status));
+			if (!rc)
+				*value = SLOT_ATTN(myslot.status,
+						myslot.ext_status);
+		}
+	}
+
+	ibmphp_unlock_operations();
+	debug("get_attention_status - Exit rc[%d] value[%x]\n", rc, *value);
+	return rc;
+}
+
+static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 * value)
+{
+	int rc = -ENODEV;
+	struct slot *pslot;
+	struct slot myslot;
+
+	debug("get_latch_status - Entry hotplug_slot[%lx] pvalue[%lx]\n",
+					(ulong) hotplug_slot, (ulong) value);
+	ibmphp_lock_operations();
+	if (hotplug_slot) {
+		pslot = hotplug_slot->private;
+		if (pslot) {
+			memcpy(&myslot, pslot, sizeof(struct slot));
+			rc = ibmphp_hpc_readslot(pslot, READ_SLOTSTATUS,
+						&(myslot.status));
+			if (!rc)
+				*value = SLOT_LATCH(myslot.status);
+		}
+	}
+
+	ibmphp_unlock_operations();
+	debug("get_latch_status - Exit rc[%d] rc[%x] value[%x]\n",
+			rc, rc, *value);
+	return rc;
+}
+
+
+static int get_power_status(struct hotplug_slot *hotplug_slot, u8 * value)
+{
+	int rc = -ENODEV;
+	struct slot *pslot;
+	struct slot myslot;
+
+	debug("get_power_status - Entry hotplug_slot[%lx] pvalue[%lx]\n",
+					(ulong) hotplug_slot, (ulong) value);
+	ibmphp_lock_operations();
+	if (hotplug_slot) {
+		pslot = hotplug_slot->private;
+		if (pslot) {
+			memcpy(&myslot, pslot, sizeof(struct slot));
+			rc = ibmphp_hpc_readslot(pslot, READ_SLOTSTATUS,
+						&(myslot.status));
+			if (!rc)
+				*value = SLOT_PWRGD(myslot.status);
+		}
+	}
+
+	ibmphp_unlock_operations();
+	debug("get_power_status - Exit rc[%d] rc[%x] value[%x]\n",
+			rc, rc, *value);
+	return rc;
+}
+
+static int get_adapter_present(struct hotplug_slot *hotplug_slot, u8 * value)
+{
+	int rc = -ENODEV;
+	struct slot *pslot;
+	u8 present;
+	struct slot myslot;
+
+	debug("get_adapter_status - Entry hotplug_slot[%lx] pvalue[%lx]\n",
+					(ulong) hotplug_slot, (ulong) value);
+	ibmphp_lock_operations();
+	if (hotplug_slot) {
+		pslot = hotplug_slot->private;
+		if (pslot) {
+			memcpy(&myslot, pslot, sizeof(struct slot));
+			rc = ibmphp_hpc_readslot(pslot, READ_SLOTSTATUS,
+						&(myslot.status));
+			if (!rc) {
+				present = SLOT_PRESENT(myslot.status);
+				if (present == HPC_SLOT_EMPTY)
+					*value = 0;
+				else
+					*value = 1;
+			}
+		}
+	}
+
+	ibmphp_unlock_operations();
+	debug("get_adapter_present - Exit rc[%d] value[%x]\n", rc, *value);
+	return rc;
+}
+
+static int get_max_bus_speed(struct slot *slot)
+{
+	int rc;
+	u8 mode = 0;
+	enum pci_bus_speed speed;
+	struct pci_bus *bus = slot->hotplug_slot->pci_slot->bus;
+
+	debug("%s - Entry slot[%p]\n", __func__, slot);
+
+	ibmphp_lock_operations();
+	mode = slot->supported_bus_mode;
+	speed = slot->supported_speed; 
+	ibmphp_unlock_operations();
+
+	switch (speed) {
+	case BUS_SPEED_33:
+		break;
+	case BUS_SPEED_66:
+		if (mode == BUS_MODE_PCIX) 
+			speed += 0x01;
+		break;
+	case BUS_SPEED_100:
+	case BUS_SPEED_133:
+		speed += 0x01;
+		break;
+	default:
+		/* Note (will need to change): there would be soon 256, 512 also */
+		rc = -ENODEV;
+	}
+
+	if (!rc)
+		bus->max_bus_speed = speed;
+
+	debug("%s - Exit rc[%d] speed[%x]\n", __func__, rc, speed);
+	return rc;
+}
+
+/*
+static int get_max_adapter_speed_1(struct hotplug_slot *hotplug_slot, u8 * value, u8 flag)
+{
+	int rc = -ENODEV;
+	struct slot *pslot;
+	struct slot myslot;
+
+	debug("get_max_adapter_speed_1 - Entry hotplug_slot[%lx] pvalue[%lx]\n",
+						(ulong)hotplug_slot, (ulong) value);
+
+	if (flag)
+		ibmphp_lock_operations();
+
+	if (hotplug_slot && value) {
+		pslot = hotplug_slot->private;
+		if (pslot) {
+			memcpy(&myslot, pslot, sizeof(struct slot));
+			rc = ibmphp_hpc_readslot(pslot, READ_SLOTSTATUS,
+						&(myslot.status));
+
+			if (!(SLOT_LATCH (myslot.status)) &&
+					(SLOT_PRESENT (myslot.status))) {
+				rc = ibmphp_hpc_readslot(pslot,
+						READ_EXTSLOTSTATUS,
+						&(myslot.ext_status));
+				if (!rc)
+					*value = SLOT_SPEED(myslot.ext_status);
+			} else
+				*value = MAX_ADAPTER_NONE;
+                }
+	}
+
+	if (flag)
+		ibmphp_unlock_operations();
+
+	debug("get_max_adapter_speed_1 - Exit rc[%d] value[%x]\n", rc, *value);
+	return rc;
+}
+
+static int get_bus_name(struct hotplug_slot *hotplug_slot, char * value)
+{
+	int rc = -ENODEV;
+	struct slot *pslot = NULL;
+
+	debug("get_bus_name - Entry hotplug_slot[%lx]\n", (ulong)hotplug_slot);
+
+	ibmphp_lock_operations();
+
+	if (hotplug_slot) {
+		pslot = hotplug_slot->private;
+		if (pslot) {
+			rc = 0;
+			snprintf(value, 100, "Bus %x", pslot->bus);
+		}
+	} else
+		rc = -ENODEV;
+
+	ibmphp_unlock_operations();
+	debug("get_bus_name - Exit rc[%d] value[%x]\n", rc, *value);
+	return rc;
+}
+*/
+
+/****************************************************************************
+ * This routine will initialize the ops data structure used in the validate
+ * function. It will also power off empty slots that are powered on since BIOS
+ * leaves those on, albeit disconnected
+ ****************************************************************************/
+static int __init init_ops(void)
+{
+	struct slot *slot_cur;
+	struct list_head *tmp;
+	int retval;
+	int rc;
+
+	list_for_each(tmp, &ibmphp_slot_head) {
+		slot_cur = list_entry(tmp, struct slot, ibm_slot_list);
+
+		if (!slot_cur)
+			return -ENODEV;
+
+		debug("BEFORE GETTING SLOT STATUS, slot # %x\n",
+							slot_cur->number);
+		if (slot_cur->ctrl->revision == 0xFF) 
+			if (get_ctrl_revision(slot_cur,
+						&slot_cur->ctrl->revision))
+				return -1;
+
+		if (slot_cur->bus_on->current_speed == 0xFF) 
+			if (get_cur_bus_info(&slot_cur)) 
+				return -1;
+		get_max_bus_speed(slot_cur);
+
+		if (slot_cur->ctrl->options == 0xFF)
+			if (get_hpc_options(slot_cur, &slot_cur->ctrl->options))
+				return -1;
+
+		retval = slot_update(&slot_cur);
+		if (retval)
+			return retval;
+
+		debug("status = %x\n", slot_cur->status);
+		debug("ext_status = %x\n", slot_cur->ext_status);
+		debug("SLOT_POWER = %x\n", SLOT_POWER(slot_cur->status));
+		debug("SLOT_PRESENT = %x\n", SLOT_PRESENT(slot_cur->status));
+		debug("SLOT_LATCH = %x\n", SLOT_LATCH(slot_cur->status));
+
+		if ((SLOT_PWRGD(slot_cur->status)) && 
+		    !(SLOT_PRESENT(slot_cur->status)) && 
+		    !(SLOT_LATCH(slot_cur->status))) {
+			debug("BEFORE POWER OFF COMMAND\n");
+				rc = power_off(slot_cur);
+				if (rc)
+					return rc;
+
+	/*		retval = slot_update(&slot_cur);
+	 *		if (retval)
+	 *			return retval;
+	 *		ibmphp_update_slot_info(slot_cur);
+	 */
+		}
+	}
+	init_flag = 0;
+	return 0;
+}
+
+/* This operation will check whether the slot is within the bounds and
+ * the operation is valid to perform on that slot
+ * Parameters: slot, operation
+ * Returns: 0 or error codes
+ */
+static int validate(struct slot *slot_cur, int opn)
+{
+	int number;
+	int retval;
+
+	if (!slot_cur)
+		return -ENODEV;
+	number = slot_cur->number;
+	if ((number > max_slots) || (number < 0))
+		return -EBADSLT;
+	debug("slot_number in validate is %d\n", slot_cur->number);
+
+	retval = slot_update(&slot_cur);
+	if (retval)
+		return retval;
+
+	switch (opn) {
+		case ENABLE:
+			if (!(SLOT_PWRGD(slot_cur->status)) && 
+			     (SLOT_PRESENT(slot_cur->status)) && 
+			     !(SLOT_LATCH(slot_cur->status)))
+				return 0;
+			break;
+		case DISABLE:
+			if ((SLOT_PWRGD(slot_cur->status)) && 
+			    (SLOT_PRESENT(slot_cur->status)) &&
+			    !(SLOT_LATCH(slot_cur->status)))
+				return 0;
+			break;
+		default:
+			break;
+	}
+	err("validate failed....\n");
+	return -EINVAL;
+}
+
+/****************************************************************************
+ * This routine is for updating the data structures in the hotplug core
+ * Parameters: struct slot
+ * Returns: 0 or error
+ ****************************************************************************/
+int ibmphp_update_slot_info(struct slot *slot_cur)
+{
+	struct hotplug_slot_info *info;
+	struct pci_bus *bus = slot_cur->hotplug_slot->pci_slot->bus;
+	int rc;
+	u8 bus_speed;
+	u8 mode;
+
+	info = kmalloc(sizeof(struct hotplug_slot_info), GFP_KERNEL);
+	if (!info) {
+		err("out of system memory\n");
+		return -ENOMEM;
+	}
+        
+	info->power_status = SLOT_PWRGD(slot_cur->status);
+	info->attention_status = SLOT_ATTN(slot_cur->status,
+						slot_cur->ext_status);
+	info->latch_status = SLOT_LATCH(slot_cur->status);
+        if (!SLOT_PRESENT(slot_cur->status)) {
+                info->adapter_status = 0;
+/*		info->max_adapter_speed_status = MAX_ADAPTER_NONE; */
+	} else {
+                info->adapter_status = 1;
+/*		get_max_adapter_speed_1(slot_cur->hotplug_slot,
+					&info->max_adapter_speed_status, 0); */
+	}
+
+	bus_speed = slot_cur->bus_on->current_speed;
+	mode = slot_cur->bus_on->current_bus_mode;
+
+	switch (bus_speed) {
+		case BUS_SPEED_33:
+			break;
+		case BUS_SPEED_66:
+			if (mode == BUS_MODE_PCIX) 
+				bus_speed += 0x01;
+			else if (mode == BUS_MODE_PCI)
+				;
+			else
+				bus_speed = PCI_SPEED_UNKNOWN;
+			break;
+		case BUS_SPEED_100:
+		case BUS_SPEED_133:
+			bus_speed += 0x01;
+			break;
+		default:
+			bus_speed = PCI_SPEED_UNKNOWN;
+	}
+
+	bus->cur_bus_speed = bus_speed;
+	// To do: bus_names 
+	
+	rc = pci_hp_change_slot_info(slot_cur->hotplug_slot, info);
+	kfree(info);
+	return rc;
+}
+
+
+/******************************************************************************
+ * This function will return the pci_func, given bus and devfunc, or NULL.  It
+ * is called from visit routines
+ ******************************************************************************/
+
+static struct pci_func *ibm_slot_find(u8 busno, u8 device, u8 function)
+{
+	struct pci_func *func_cur;
+	struct slot *slot_cur;
+	struct list_head * tmp;
+	list_for_each(tmp, &ibmphp_slot_head) {
+		slot_cur = list_entry(tmp, struct slot, ibm_slot_list);
+		if (slot_cur->func) {
+			func_cur = slot_cur->func;
+			while (func_cur) {
+				if ((func_cur->busno == busno) &&
+						(func_cur->device == device) &&
+						(func_cur->function == function))
+					return func_cur;
+				func_cur = func_cur->next;
+			}
+		}
+	}
+	return NULL;
+}
+
+/*************************************************************
+ * This routine frees up memory used by struct slot, including
+ * the pointers to pci_func, bus, hotplug_slot, controller,
+ * and deregistering from the hotplug core
+ *************************************************************/
+static void free_slots(void)
+{
+	struct slot *slot_cur;
+	struct list_head * tmp;
+	struct list_head * next;
+
+	debug("%s -- enter\n", __func__);
+
+	list_for_each_safe(tmp, next, &ibmphp_slot_head) {
+		slot_cur = list_entry(tmp, struct slot, ibm_slot_list);
+		pci_hp_deregister(slot_cur->hotplug_slot);
+	}
+	debug("%s -- exit\n", __func__);
+}
+
+static void ibm_unconfigure_device(struct pci_func *func)
+{
+	struct pci_dev *temp;
+	u8 j;
+
+	debug("inside %s\n", __func__);
+	debug("func->device = %x, func->function = %x\n",
+					func->device, func->function);
+	debug("func->device << 3 | 0x0  = %x\n", func->device << 3 | 0x0);
+
+	for (j = 0; j < 0x08; j++) {
+		temp = pci_get_bus_and_slot(func->busno, (func->device << 3) | j);
+		if (temp) {
+			pci_remove_bus_device(temp);
+			pci_dev_put(temp);
+		}
+	}
+	pci_dev_put(func->dev);
+}
+
+/*
+ * The following function is to fix kernel bug regarding 
+ * getting bus entries, here we manually add those primary 
+ * bus entries to kernel bus structure whenever apply
+ */
+static u8 bus_structure_fixup(u8 busno)
+{
+	struct pci_bus *bus;
+	struct pci_dev *dev;
+	u16 l;
+
+	if (pci_find_bus(0, busno) || !(ibmphp_find_same_bus_num(busno)))
+		return 1;
+
+	bus = kmalloc(sizeof(*bus), GFP_KERNEL);
+	if (!bus) {
+		err("%s - out of memory\n", __func__);
+		return 1;
+	}
+	dev = kmalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev) {
+		kfree(bus);
+		err("%s - out of memory\n", __func__);
+		return 1;
+	}
+
+	bus->number = busno;
+	bus->ops = ibmphp_pci_bus->ops;
+	dev->bus = bus;
+	for (dev->devfn = 0; dev->devfn < 256; dev->devfn += 8) {
+		if (!pci_read_config_word(dev, PCI_VENDOR_ID, &l) &&
+					(l != 0x0000) && (l != 0xffff)) {
+			debug("%s - Inside bus_struture_fixup()\n",
+							__func__);
+			pci_scan_bus(busno, ibmphp_pci_bus->ops, NULL);
+			break;
+		}
+	}
+
+	kfree(dev);
+	kfree(bus);
+
+	return 0;
+}
+
+static int ibm_configure_device(struct pci_func *func)
+{
+	unsigned char bus;
+	struct pci_bus *child;
+	int num;
+	int flag = 0;	/* this is to make sure we don't double scan the bus,
+					for bridged devices primarily */
+
+	if (!(bus_structure_fixup(func->busno)))
+		flag = 1;
+	if (func->dev == NULL)
+		func->dev = pci_get_bus_and_slot(func->busno,
+				PCI_DEVFN(func->device, func->function));
+
+	if (func->dev == NULL) {
+		struct pci_bus *bus = pci_find_bus(0, func->busno);
+		if (!bus)
+			return 0;
+
+		num = pci_scan_slot(bus,
+				PCI_DEVFN(func->device, func->function));
+		if (num)
+			pci_bus_add_devices(bus);
+
+		func->dev = pci_get_bus_and_slot(func->busno,
+				PCI_DEVFN(func->device, func->function));
+		if (func->dev == NULL) {
+			err("ERROR... : pci_dev still NULL\n");
+			return 0;
+		}
+	}
+	if (!(flag) && (func->dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)) {
+		pci_read_config_byte(func->dev, PCI_SECONDARY_BUS, &bus);
+		child = pci_add_new_bus(func->dev->bus, func->dev, bus);
+		pci_do_scan_bus(child);
+	}
+
+	return 0;
+}
+
+/*******************************************************
+ * Returns whether the bus is empty or not 
+ *******************************************************/
+static int is_bus_empty(struct slot * slot_cur)
+{
+	int rc;
+	struct slot * tmp_slot;
+	u8 i = slot_cur->bus_on->slot_min;
+
+	while (i <= slot_cur->bus_on->slot_max) {
+		if (i == slot_cur->number) {
+			i++;
+			continue;
+		}
+		tmp_slot = ibmphp_get_slot_from_physical_num(i);
+		if (!tmp_slot)
+			return 0;
+		rc = slot_update(&tmp_slot);
+		if (rc)
+			return 0;
+		if (SLOT_PRESENT(tmp_slot->status) &&
+					SLOT_PWRGD(tmp_slot->status))
+			return 0;
+		i++;
+	}
+	return 1;
+}
+
+/***********************************************************
+ * If the HPC permits and the bus currently empty, tries to set the 
+ * bus speed and mode at the maximum card and bus capability
+ * Parameters: slot
+ * Returns: bus is set (0) or error code
+ ***********************************************************/
+static int set_bus(struct slot * slot_cur)
+{
+	int rc;
+	u8 speed;
+	u8 cmd = 0x0;
+	int retval;
+	static struct pci_device_id ciobx[] = {
+		{ PCI_DEVICE(PCI_VENDOR_ID_SERVERWORKS, 0x0101) },
+	        { },
+	};	
+
+	debug("%s - entry slot # %d\n", __func__, slot_cur->number);
+	if (SET_BUS_STATUS(slot_cur->ctrl) && is_bus_empty(slot_cur)) {
+		rc = slot_update(&slot_cur);
+		if (rc)
+			return rc;
+		speed = SLOT_SPEED(slot_cur->ext_status);
+		debug("ext_status = %x, speed = %x\n", slot_cur->ext_status, speed);
+		switch (speed) {
+		case HPC_SLOT_SPEED_33:
+			cmd = HPC_BUS_33CONVMODE;
+			break;
+		case HPC_SLOT_SPEED_66:
+			if (SLOT_PCIX(slot_cur->ext_status)) {
+				if ((slot_cur->supported_speed >= BUS_SPEED_66) &&
+						(slot_cur->supported_bus_mode == BUS_MODE_PCIX))
+					cmd = HPC_BUS_66PCIXMODE;
+				else if (!SLOT_BUS_MODE(slot_cur->ext_status))
+					/* if max slot/bus capability is 66 pci
+					and there's no bus mode mismatch, then
+					the adapter supports 66 pci */ 
+					cmd = HPC_BUS_66CONVMODE;
+				else
+					cmd = HPC_BUS_33CONVMODE;
+			} else {
+				if (slot_cur->supported_speed >= BUS_SPEED_66)
+					cmd = HPC_BUS_66CONVMODE;
+				else
+					cmd = HPC_BUS_33CONVMODE;
+			}
+			break;
+		case HPC_SLOT_SPEED_133:
+			switch (slot_cur->supported_speed) {
+			case BUS_SPEED_33:
+				cmd = HPC_BUS_33CONVMODE;
+				break;
+			case BUS_SPEED_66:
+				if (slot_cur->supported_bus_mode == BUS_MODE_PCIX)
+					cmd = HPC_BUS_66PCIXMODE;
+				else
+					cmd = HPC_BUS_66CONVMODE;
+				break;
+			case BUS_SPEED_100:
+				cmd = HPC_BUS_100PCIXMODE;
+				break;
+			case BUS_SPEED_133:
+				/* This is to take care of the bug in CIOBX chip */
+				if (pci_dev_present(ciobx))
+					ibmphp_hpc_writeslot(slot_cur,
+							HPC_BUS_100PCIXMODE);
+				cmd = HPC_BUS_133PCIXMODE;
+				break;
+			default:
+				err("Wrong bus speed\n");
+				return -ENODEV;
+			}
+			break;
+		default:
+			err("wrong slot speed\n");
+			return -ENODEV;
+		}
+		debug("setting bus speed for slot %d, cmd %x\n",
+						slot_cur->number, cmd);
+		retval = ibmphp_hpc_writeslot(slot_cur, cmd);
+		if (retval) {
+			err("setting bus speed failed\n");
+			return retval;
+		}
+		if (CTLR_RESULT(slot_cur->ctrl->status)) {
+			err("command not completed successfully in set_bus\n");
+			return -EIO;
+		}
+	}
+	/* This is for x440, once Brandon fixes the firmware, 
+	will not need this delay */
+	msleep(1000);
+	debug("%s -Exit\n", __func__);
+	return 0;
+}
+
+/* This routine checks the bus limitations that the slot is on from the BIOS.
+ * This is used in deciding whether or not to power up the slot.  
+ * (electrical/spec limitations. For example, >1 133 MHz or >2 66 PCI cards on
+ * same bus) 
+ * Parameters: slot
+ * Returns: 0 = no limitations, -EINVAL = exceeded limitations on the bus
+ */
+static int check_limitations(struct slot *slot_cur)
+{
+	u8 i;
+	struct slot * tmp_slot;
+	u8 count = 0;
+	u8 limitation = 0;
+
+	for (i = slot_cur->bus_on->slot_min; i <= slot_cur->bus_on->slot_max; i++) {
+		tmp_slot = ibmphp_get_slot_from_physical_num(i);
+		if (!tmp_slot)
+			return -ENODEV;
+		if ((SLOT_PWRGD(tmp_slot->status)) &&
+					!(SLOT_CONNECT(tmp_slot->status)))
+			count++;
+	}
+	get_cur_bus_info(&slot_cur);
+	switch (slot_cur->bus_on->current_speed) {
+	case BUS_SPEED_33:
+		limitation = slot_cur->bus_on->slots_at_33_conv;
+		break;
+	case BUS_SPEED_66:
+		if (slot_cur->bus_on->current_bus_mode == BUS_MODE_PCIX)
+			limitation = slot_cur->bus_on->slots_at_66_pcix;
+		else
+			limitation = slot_cur->bus_on->slots_at_66_conv;
+		break;
+	case BUS_SPEED_100:
+		limitation = slot_cur->bus_on->slots_at_100_pcix;
+		break;
+	case BUS_SPEED_133:
+		limitation = slot_cur->bus_on->slots_at_133_pcix;
+		break;
+	}
+
+	if ((count + 1) > limitation)
+		return -EINVAL;
+	return 0;
+}
+
+static inline void print_card_capability(struct slot *slot_cur)
+{
+	info("capability of the card is ");
+	if ((slot_cur->ext_status & CARD_INFO) == PCIX133) 
+		info("   133 MHz PCI-X\n");
+	else if ((slot_cur->ext_status & CARD_INFO) == PCIX66)
+		info("    66 MHz PCI-X\n");
+	else if ((slot_cur->ext_status & CARD_INFO) == PCI66)
+		info("    66 MHz PCI\n");
+	else
+		info("    33 MHz PCI\n");
+
+}
+
+/* This routine will power on the slot, configure the device(s) and find the
+ * drivers for them.
+ * Parameters: hotplug_slot
+ * Returns: 0 or failure codes
+ */
+static int enable_slot(struct hotplug_slot *hs)
+{
+	int rc, i, rcpr;
+	struct slot *slot_cur;
+	u8 function;
+	struct pci_func *tmp_func;
+
+	ibmphp_lock_operations();
+
+	debug("ENABLING SLOT........\n");
+	slot_cur = hs->private;
+
+	if ((rc = validate(slot_cur, ENABLE))) {
+		err("validate function failed\n");
+		goto error_nopower;
+	}
+
+	attn_LED_blink(slot_cur);
+	
+	rc = set_bus(slot_cur);
+	if (rc) {
+		err("was not able to set the bus\n");
+		goto error_nopower;
+	}
+
+	/*-----------------debugging------------------------------*/
+	get_cur_bus_info(&slot_cur);
+	debug("the current bus speed right after set_bus = %x\n",
+					slot_cur->bus_on->current_speed);
+	/*----------------------------------------------------------*/
+
+	rc = check_limitations(slot_cur);
+	if (rc) {
+		err("Adding this card exceeds the limitations of this bus.\n");
+		err("(i.e., >1 133MHz cards running on same bus, or "
+		     ">2 66 PCI cards running on same bus.\n");
+		err("Try hot-adding into another bus\n");
+		rc = -EINVAL;
+		goto error_nopower;
+	}
+
+	rc = power_on(slot_cur);
+
+	if (rc) {
+		err("something wrong when powering up... please see below for details\n");
+		/* need to turn off before on, otherwise, blinking overwrites */
+		attn_off(slot_cur);
+		attn_on(slot_cur);
+		if (slot_update(&slot_cur)) {
+			attn_off(slot_cur);
+			attn_on(slot_cur);
+			rc = -ENODEV;
+			goto exit;
+		}
+		/* Check to see the error of why it failed */
+		if ((SLOT_POWER(slot_cur->status)) &&
+					!(SLOT_PWRGD(slot_cur->status)))
+			err("power fault occurred trying to power up\n");
+		else if (SLOT_BUS_SPEED(slot_cur->status)) {
+			err("bus speed mismatch occurred.  please check "
+				"current bus speed and card capability\n");
+			print_card_capability(slot_cur);
+		} else if (SLOT_BUS_MODE(slot_cur->ext_status)) {
+			err("bus mode mismatch occurred.  please check "
+				"current bus mode and card capability\n");
+			print_card_capability(slot_cur);
+		}
+		ibmphp_update_slot_info(slot_cur);
+		goto exit;
+	}
+	debug("after power_on\n");
+	/*-----------------------debugging---------------------------*/
+	get_cur_bus_info(&slot_cur);
+	debug("the current bus speed right after power_on = %x\n",
+					slot_cur->bus_on->current_speed);
+	/*----------------------------------------------------------*/
+
+	rc = slot_update(&slot_cur);
+	if (rc)
+		goto error_power;
+	
+	rc = -EINVAL;
+	if (SLOT_POWER(slot_cur->status) && !(SLOT_PWRGD(slot_cur->status))) {
+		err("power fault occurred trying to power up...\n");
+		goto error_power;
+	}
+	if (SLOT_POWER(slot_cur->status) && (SLOT_BUS_SPEED(slot_cur->status))) {
+		err("bus speed mismatch occurred.  please check current bus "
+					"speed and card capability\n");
+		print_card_capability(slot_cur);
+		goto error_power;
+	} 
+	/* Don't think this case will happen after above checks...
+	 * but just in case, for paranoia sake */
+	if (!(SLOT_POWER(slot_cur->status))) {
+		err("power on failed...\n");
+		goto error_power;
+	}
+
+	slot_cur->func = kzalloc(sizeof(struct pci_func), GFP_KERNEL);
+	if (!slot_cur->func) {
+		/* We cannot do update_slot_info here, since no memory for
+		 * kmalloc n.e.ways, and update_slot_info allocates some */
+		err("out of system memory\n");
+		rc = -ENOMEM;
+		goto error_power;
+	}
+	slot_cur->func->busno = slot_cur->bus;
+	slot_cur->func->device = slot_cur->device;
+	for (i = 0; i < 4; i++)
+		slot_cur->func->irq[i] = slot_cur->irq[i];
+
+	debug("b4 configure_card, slot_cur->bus = %x, slot_cur->device = %x\n",
+					slot_cur->bus, slot_cur->device);
+
+	if (ibmphp_configure_card(slot_cur->func, slot_cur->number)) {
+		err("configure_card was unsuccessful...\n");
+		/* true because don't need to actually deallocate resources,
+		 * just remove references */
+		ibmphp_unconfigure_card(&slot_cur, 1);
+		debug("after unconfigure_card\n");
+		slot_cur->func = NULL;
+		rc = -ENOMEM;
+		goto error_power;
+	}
+
+	function = 0x00;
+	do {
+		tmp_func = ibm_slot_find(slot_cur->bus, slot_cur->func->device,
+							function++);
+		if (tmp_func && !(tmp_func->dev))
+			ibm_configure_device(tmp_func);
+	} while (tmp_func);
+
+	attn_off(slot_cur);
+	if (slot_update(&slot_cur)) {
+		rc = -EFAULT;
+		goto exit;
+	}
+	ibmphp_print_test();
+	rc = ibmphp_update_slot_info(slot_cur);
+exit:
+	ibmphp_unlock_operations(); 
+	return rc;
+
+error_nopower:
+	attn_off(slot_cur);	/* need to turn off if was blinking b4 */
+	attn_on(slot_cur);
+error_cont:
+	rcpr = slot_update(&slot_cur);
+	if (rcpr) {
+		rc = rcpr;
+		goto exit;
+	}
+	ibmphp_update_slot_info(slot_cur);
+	goto exit;
+
+error_power:
+	attn_off(slot_cur);	/* need to turn off if was blinking b4 */
+	attn_on(slot_cur);
+	rcpr = power_off(slot_cur);
+	if (rcpr) {
+		rc = rcpr;
+		goto exit;
+	}
+	goto error_cont;
+}
+
+/**************************************************************
+* HOT REMOVING ADAPTER CARD                                   *
+* INPUT: POINTER TO THE HOTPLUG SLOT STRUCTURE                *
+* OUTPUT: SUCCESS 0 ; FAILURE: UNCONFIGURE , VALIDATE         *
+          DISABLE POWER ,                                    *
+**************************************************************/
+static int ibmphp_disable_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+	int rc;
+	
+	ibmphp_lock_operations();
+	rc = ibmphp_do_disable_slot(slot);
+	ibmphp_unlock_operations();
+	return rc;
+}
+
+int ibmphp_do_disable_slot(struct slot *slot_cur)
+{
+	int rc;
+	u8 flag;
+
+	debug("DISABLING SLOT...\n"); 
+		
+	if ((slot_cur == NULL) || (slot_cur->ctrl == NULL)) {
+		return -ENODEV;
+	}
+	
+	flag = slot_cur->flag;
+	slot_cur->flag = 1;
+
+	if (flag == 1) {
+		rc = validate(slot_cur, DISABLE);
+			/* checking if powered off already & valid slot # */
+		if (rc)
+			goto error;
+	}
+	attn_LED_blink(slot_cur);
+
+	if (slot_cur->func == NULL) {
+		/* We need this for fncs's that were there on bootup */
+		slot_cur->func = kzalloc(sizeof(struct pci_func), GFP_KERNEL);
+		if (!slot_cur->func) {
+			err("out of system memory\n");
+			rc = -ENOMEM;
+			goto error;
+		}
+		slot_cur->func->busno = slot_cur->bus;
+		slot_cur->func->device = slot_cur->device;
+	}
+
+	ibm_unconfigure_device(slot_cur->func);
+        
+	/* If we got here from latch suddenly opening on operating card or 
+	a power fault, there's no power to the card, so cannot
+	read from it to determine what resources it occupied.  This operation
+	is forbidden anyhow.  The best we can do is remove it from kernel
+	lists at least */
+
+	if (!flag) {
+		attn_off(slot_cur);
+		return 0;
+	}
+
+	rc = ibmphp_unconfigure_card(&slot_cur, 0);
+	slot_cur->func = NULL;
+	debug("in disable_slot. after unconfigure_card\n");
+	if (rc) {
+		err("could not unconfigure card.\n");
+		goto error;
+	}
+
+	rc = ibmphp_hpc_writeslot(slot_cur, HPC_SLOT_OFF);
+	if (rc)
+		goto error;
+
+	attn_off(slot_cur);
+	rc = slot_update(&slot_cur);
+	if (rc)
+		goto exit;
+
+	rc = ibmphp_update_slot_info(slot_cur);
+	ibmphp_print_test();
+exit:
+	return rc;
+
+error:
+	/*  Need to turn off if was blinking b4 */
+	attn_off(slot_cur);
+	attn_on(slot_cur);
+	if (slot_update(&slot_cur)) {
+		rc = -EFAULT;
+		goto exit;
+	}
+	if (flag)		
+		ibmphp_update_slot_info(slot_cur);
+	goto exit;
+}
+
+struct hotplug_slot_ops ibmphp_hotplug_slot_ops = {
+	.set_attention_status =		set_attention_status,
+	.enable_slot =			enable_slot,
+	.disable_slot =			ibmphp_disable_slot,
+	.hardware_test =		NULL,
+	.get_power_status =		get_power_status,
+	.get_attention_status =		get_attention_status,
+	.get_latch_status =		get_latch_status,
+	.get_adapter_status =		get_adapter_present,
+/*	.get_max_adapter_speed =	get_max_adapter_speed,
+	.get_bus_name_status =		get_bus_name,
+*/
+};
+
+static void ibmphp_unload(void)
+{
+	free_slots();
+	debug("after slots\n");
+	ibmphp_free_resources();
+	debug("after resources\n");
+	ibmphp_free_bus_info_queue();
+	debug("after bus info\n");
+	ibmphp_free_ebda_hpc_queue();
+	debug("after ebda hpc\n");
+	ibmphp_free_ebda_pci_rsrc_queue();
+	debug("after ebda pci rsrc\n");
+	kfree(ibmphp_pci_bus);
+}
+
+static int __init ibmphp_init(void)
+{
+	struct pci_bus *bus;
+	int i = 0;
+	int rc = 0;
+
+	init_flag = 1;
+
+	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
+
+	ibmphp_pci_bus = kmalloc(sizeof(*ibmphp_pci_bus), GFP_KERNEL);
+	if (!ibmphp_pci_bus) {
+		err("out of memory\n");
+		rc = -ENOMEM;
+		goto exit;
+	}
+
+	bus = pci_find_bus(0, 0);
+	if (!bus) {
+		err("Can't find the root pci bus, can not continue\n");
+		rc = -ENODEV;
+		goto error;
+	}
+	memcpy(ibmphp_pci_bus, bus, sizeof(*ibmphp_pci_bus));
+
+	ibmphp_debug = debug;
+
+	ibmphp_hpc_initvars();
+
+	for (i = 0; i < 16; i++)
+		irqs[i] = 0;
+
+	if ((rc = ibmphp_access_ebda()))
+		goto error;
+	debug("after ibmphp_access_ebda()\n");
+
+	if ((rc = ibmphp_rsrc_init()))
+		goto error;
+	debug("AFTER Resource & EBDA INITIALIZATIONS\n");
+
+	max_slots = get_max_slots();
+	
+	if ((rc = ibmphp_register_pci()))
+		goto error;
+
+	if (init_ops()) {
+		rc = -ENODEV;
+		goto error;
+	}
+
+	ibmphp_print_test();
+	if ((rc = ibmphp_hpc_start_poll_thread())) {
+		goto error;
+	}
+
+exit:
+	return rc;
+
+error:
+	ibmphp_unload();
+	goto exit;
+}
+
+static void __exit ibmphp_exit(void)
+{
+	ibmphp_hpc_stop_poll_thread();
+	debug("after polling\n");
+	ibmphp_unload();
+	debug("done\n");
+}
+
+module_init(ibmphp_init);
+module_exit(ibmphp_exit);
diff --git a/drivers/pci/hotplug/ibmphp_ebda.c b/drivers/pci/hotplug/ibmphp_ebda.c
new file mode 100644
index 00000000..2850e64d
--- /dev/null
+++ b/drivers/pci/hotplug/ibmphp_ebda.c
@@ -0,0 +1,1211 @@
+/*
+ * IBM Hot Plug Controller Driver
+ *
+ * Written By: Tong Yu, IBM Corporation
+ *
+ * Copyright (C) 2001,2003 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001-2003 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <gregkh@us.ibm.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/list.h>
+#include <linux/init.h>
+#include "ibmphp.h"
+
+/*
+ * POST builds data blocks(in this data block definition, a char-1
+ * byte, short(or word)-2 byte, long(dword)-4 byte) in the Extended
+ * BIOS Data Area which describe the configuration of the hot-plug
+ * controllers and resources used by the PCI Hot-Plug devices.
+ *
+ * This file walks EBDA, maps data block from physical addr,
+ * reconstruct linked lists about all system resource(MEM, PFM, IO)
+ * already assigned by POST, as well as linked lists about hot plug
+ * controllers (ctlr#, slot#, bus&slot features...)
+ */
+
+/* Global lists */
+LIST_HEAD (ibmphp_ebda_pci_rsrc_head);
+LIST_HEAD (ibmphp_slot_head);
+
+/* Local variables */
+static struct ebda_hpc_list *hpc_list_ptr;
+static struct ebda_rsrc_list *rsrc_list_ptr;
+static struct rio_table_hdr *rio_table_ptr = NULL;
+static LIST_HEAD (ebda_hpc_head);
+static LIST_HEAD (bus_info_head);
+static LIST_HEAD (rio_vg_head);
+static LIST_HEAD (rio_lo_head);
+static LIST_HEAD (opt_vg_head);
+static LIST_HEAD (opt_lo_head);
+static void __iomem *io_mem;
+
+/* Local functions */
+static int ebda_rsrc_controller (void);
+static int ebda_rsrc_rsrc (void);
+static int ebda_rio_table (void);
+
+static struct ebda_hpc_list * __init alloc_ebda_hpc_list (void)
+{
+	return kzalloc(sizeof(struct ebda_hpc_list), GFP_KERNEL);
+}
+
+static struct controller *alloc_ebda_hpc (u32 slot_count, u32 bus_count)
+{
+	struct controller *controller;
+	struct ebda_hpc_slot *slots;
+	struct ebda_hpc_bus *buses;
+
+	controller = kzalloc(sizeof(struct controller), GFP_KERNEL);
+	if (!controller)
+		goto error;
+
+	slots = kcalloc(slot_count, sizeof(struct ebda_hpc_slot), GFP_KERNEL);
+	if (!slots)
+		goto error_contr;
+	controller->slots = slots;
+
+	buses = kcalloc(bus_count, sizeof(struct ebda_hpc_bus), GFP_KERNEL);
+	if (!buses)
+		goto error_slots;
+	controller->buses = buses;
+
+	return controller;
+error_slots:
+	kfree(controller->slots);
+error_contr:
+	kfree(controller);
+error:
+	return NULL;
+}
+
+static void free_ebda_hpc (struct controller *controller)
+{
+	kfree (controller->slots);
+	kfree (controller->buses);
+	kfree (controller);
+}
+
+static struct ebda_rsrc_list * __init alloc_ebda_rsrc_list (void)
+{
+	return kzalloc(sizeof(struct ebda_rsrc_list), GFP_KERNEL);
+}
+
+static struct ebda_pci_rsrc *alloc_ebda_pci_rsrc (void)
+{
+	return kzalloc(sizeof(struct ebda_pci_rsrc), GFP_KERNEL);
+}
+
+static void __init print_bus_info (void)
+{
+	struct bus_info *ptr;
+	
+	list_for_each_entry(ptr, &bus_info_head, bus_info_list) {
+		debug ("%s - slot_min = %x\n", __func__, ptr->slot_min);
+		debug ("%s - slot_max = %x\n", __func__, ptr->slot_max);
+		debug ("%s - slot_count = %x\n", __func__, ptr->slot_count);
+		debug ("%s - bus# = %x\n", __func__, ptr->busno);
+		debug ("%s - current_speed = %x\n", __func__, ptr->current_speed);
+		debug ("%s - controller_id = %x\n", __func__, ptr->controller_id);
+		
+		debug ("%s - slots_at_33_conv = %x\n", __func__, ptr->slots_at_33_conv);
+		debug ("%s - slots_at_66_conv = %x\n", __func__, ptr->slots_at_66_conv);
+		debug ("%s - slots_at_66_pcix = %x\n", __func__, ptr->slots_at_66_pcix);
+		debug ("%s - slots_at_100_pcix = %x\n", __func__, ptr->slots_at_100_pcix);
+		debug ("%s - slots_at_133_pcix = %x\n", __func__, ptr->slots_at_133_pcix);
+
+	}
+}
+
+static void print_lo_info (void)
+{
+	struct rio_detail *ptr;
+	debug ("print_lo_info ----\n");	
+	list_for_each_entry(ptr, &rio_lo_head, rio_detail_list) {
+		debug ("%s - rio_node_id = %x\n", __func__, ptr->rio_node_id);
+		debug ("%s - rio_type = %x\n", __func__, ptr->rio_type);
+		debug ("%s - owner_id = %x\n", __func__, ptr->owner_id);
+		debug ("%s - first_slot_num = %x\n", __func__, ptr->first_slot_num);
+		debug ("%s - wpindex = %x\n", __func__, ptr->wpindex);
+		debug ("%s - chassis_num = %x\n", __func__, ptr->chassis_num);
+
+	}
+}
+
+static void print_vg_info (void)
+{
+	struct rio_detail *ptr;
+	debug ("%s ---\n", __func__);
+	list_for_each_entry(ptr, &rio_vg_head, rio_detail_list) {
+		debug ("%s - rio_node_id = %x\n", __func__, ptr->rio_node_id);
+		debug ("%s - rio_type = %x\n", __func__, ptr->rio_type);
+		debug ("%s - owner_id = %x\n", __func__, ptr->owner_id);
+		debug ("%s - first_slot_num = %x\n", __func__, ptr->first_slot_num);
+		debug ("%s - wpindex = %x\n", __func__, ptr->wpindex);
+		debug ("%s - chassis_num = %x\n", __func__, ptr->chassis_num);
+
+	}
+}
+
+static void __init print_ebda_pci_rsrc (void)
+{
+	struct ebda_pci_rsrc *ptr;
+
+	list_for_each_entry(ptr, &ibmphp_ebda_pci_rsrc_head, ebda_pci_rsrc_list) {
+		debug ("%s - rsrc type: %x bus#: %x dev_func: %x start addr: %x end addr: %x\n", 
+			__func__, ptr->rsrc_type ,ptr->bus_num, ptr->dev_fun,ptr->start_addr, ptr->end_addr);
+	}
+}
+
+static void __init print_ibm_slot (void)
+{
+	struct slot *ptr;
+
+	list_for_each_entry(ptr, &ibmphp_slot_head, ibm_slot_list) {
+		debug ("%s - slot_number: %x\n", __func__, ptr->number);
+	}
+}
+
+static void __init print_opt_vg (void)
+{
+	struct opt_rio *ptr;
+	debug ("%s ---\n", __func__);
+	list_for_each_entry(ptr, &opt_vg_head, opt_rio_list) {
+		debug ("%s - rio_type %x\n", __func__, ptr->rio_type);
+		debug ("%s - chassis_num: %x\n", __func__, ptr->chassis_num);
+		debug ("%s - first_slot_num: %x\n", __func__, ptr->first_slot_num);
+		debug ("%s - middle_num: %x\n", __func__, ptr->middle_num);
+	}
+}
+
+static void __init print_ebda_hpc (void)
+{
+	struct controller *hpc_ptr;
+	u16 index;
+
+	list_for_each_entry(hpc_ptr, &ebda_hpc_head, ebda_hpc_list) {
+		for (index = 0; index < hpc_ptr->slot_count; index++) {
+			debug ("%s - physical slot#: %x\n", __func__, hpc_ptr->slots[index].slot_num);
+			debug ("%s - pci bus# of the slot: %x\n", __func__, hpc_ptr->slots[index].slot_bus_num);
+			debug ("%s - index into ctlr addr: %x\n", __func__, hpc_ptr->slots[index].ctl_index);
+			debug ("%s - cap of the slot: %x\n", __func__, hpc_ptr->slots[index].slot_cap);
+		}
+
+		for (index = 0; index < hpc_ptr->bus_count; index++) {
+			debug ("%s - bus# of each bus controlled by this ctlr: %x\n", __func__, hpc_ptr->buses[index].bus_num);
+		}
+
+		debug ("%s - type of hpc: %x\n", __func__, hpc_ptr->ctlr_type);
+		switch (hpc_ptr->ctlr_type) {
+		case 1:
+			debug ("%s - bus: %x\n", __func__, hpc_ptr->u.pci_ctlr.bus);
+			debug ("%s - dev_fun: %x\n", __func__, hpc_ptr->u.pci_ctlr.dev_fun);
+			debug ("%s - irq: %x\n", __func__, hpc_ptr->irq);
+			break;
+
+		case 0:
+			debug ("%s - io_start: %x\n", __func__, hpc_ptr->u.isa_ctlr.io_start);
+			debug ("%s - io_end: %x\n", __func__, hpc_ptr->u.isa_ctlr.io_end);
+			debug ("%s - irq: %x\n", __func__, hpc_ptr->irq);
+			break;
+
+		case 2:
+		case 4:
+			debug ("%s - wpegbbar: %lx\n", __func__, hpc_ptr->u.wpeg_ctlr.wpegbbar);
+			debug ("%s - i2c_addr: %x\n", __func__, hpc_ptr->u.wpeg_ctlr.i2c_addr);
+			debug ("%s - irq: %x\n", __func__, hpc_ptr->irq);
+			break;
+		}
+	}
+}
+
+int __init ibmphp_access_ebda (void)
+{
+	u8 format, num_ctlrs, rio_complete, hs_complete, ebda_sz;
+	u16 ebda_seg, num_entries, next_offset, offset, blk_id, sub_addr, re, rc_id, re_id, base;
+	int rc = 0;
+
+
+	rio_complete = 0;
+	hs_complete = 0;
+
+	io_mem = ioremap ((0x40 << 4) + 0x0e, 2);
+	if (!io_mem )
+		return -ENOMEM;
+	ebda_seg = readw (io_mem);
+	iounmap (io_mem);
+	debug ("returned ebda segment: %x\n", ebda_seg);
+	
+	io_mem = ioremap(ebda_seg<<4, 1);
+	if (!io_mem)
+		return -ENOMEM;
+	ebda_sz = readb(io_mem);
+	iounmap(io_mem);
+	debug("ebda size: %d(KiB)\n", ebda_sz);
+	if (ebda_sz == 0)
+		return -ENOMEM;
+
+	io_mem = ioremap(ebda_seg<<4, (ebda_sz * 1024));
+	if (!io_mem )
+		return -ENOMEM;
+	next_offset = 0x180;
+
+	for (;;) {
+		offset = next_offset;
+
+		/* Make sure what we read is still in the mapped section */
+		if (WARN(offset > (ebda_sz * 1024 - 4),
+			 "ibmphp_ebda: next read is beyond ebda_sz\n"))
+			break;
+
+		next_offset = readw (io_mem + offset);	/* offset of next blk */
+
+		offset += 2;
+		if (next_offset == 0)	/* 0 indicate it's last blk */
+			break;
+		blk_id = readw (io_mem + offset);	/* this blk id */
+
+		offset += 2;
+		/* check if it is hot swap block or rio block */
+		if (blk_id != 0x4853 && blk_id != 0x4752)
+			continue;
+		/* found hs table */
+		if (blk_id == 0x4853) {
+			debug ("now enter hot swap block---\n");
+			debug ("hot blk id: %x\n", blk_id);
+			format = readb (io_mem + offset);
+
+			offset += 1;
+			if (format != 4)
+				goto error_nodev;
+			debug ("hot blk format: %x\n", format);
+			/* hot swap sub blk */
+			base = offset;
+
+			sub_addr = base;
+			re = readw (io_mem + sub_addr);	/* next sub blk */
+
+			sub_addr += 2;
+			rc_id = readw (io_mem + sub_addr); 	/* sub blk id */
+
+			sub_addr += 2;
+			if (rc_id != 0x5243)
+				goto error_nodev;
+			/* rc sub blk signature  */
+			num_ctlrs = readb (io_mem + sub_addr);
+
+			sub_addr += 1;
+			hpc_list_ptr = alloc_ebda_hpc_list ();
+			if (!hpc_list_ptr) {
+				rc = -ENOMEM;
+				goto out;
+			}
+			hpc_list_ptr->format = format;
+			hpc_list_ptr->num_ctlrs = num_ctlrs;
+			hpc_list_ptr->phys_addr = sub_addr;	/*  offset of RSRC_CONTROLLER blk */
+			debug ("info about hpc descriptor---\n");
+			debug ("hot blk format: %x\n", format);
+			debug ("num of controller: %x\n", num_ctlrs);
+			debug ("offset of hpc data structure enteries: %x\n ", sub_addr);
+
+			sub_addr = base + re;	/* re sub blk */
+			/* FIXME: rc is never used/checked */
+			rc = readw (io_mem + sub_addr);	/* next sub blk */
+
+			sub_addr += 2;
+			re_id = readw (io_mem + sub_addr);	/* sub blk id */
+
+			sub_addr += 2;
+			if (re_id != 0x5245)
+				goto error_nodev;
+
+			/* signature of re */
+			num_entries = readw (io_mem + sub_addr);
+
+			sub_addr += 2;	/* offset of RSRC_ENTRIES blk */
+			rsrc_list_ptr = alloc_ebda_rsrc_list ();
+			if (!rsrc_list_ptr ) {
+				rc = -ENOMEM;
+				goto out;
+			}
+			rsrc_list_ptr->format = format;
+			rsrc_list_ptr->num_entries = num_entries;
+			rsrc_list_ptr->phys_addr = sub_addr;
+
+			debug ("info about rsrc descriptor---\n");
+			debug ("format: %x\n", format);
+			debug ("num of rsrc: %x\n", num_entries);
+			debug ("offset of rsrc data structure enteries: %x\n ", sub_addr);
+
+			hs_complete = 1;
+		} else {
+		/* found rio table, blk_id == 0x4752 */
+			debug ("now enter io table ---\n");
+			debug ("rio blk id: %x\n", blk_id);
+
+			rio_table_ptr = kzalloc(sizeof(struct rio_table_hdr), GFP_KERNEL);
+			if (!rio_table_ptr)
+				return -ENOMEM; 
+			rio_table_ptr->ver_num = readb (io_mem + offset);
+			rio_table_ptr->scal_count = readb (io_mem + offset + 1);
+			rio_table_ptr->riodev_count = readb (io_mem + offset + 2);
+			rio_table_ptr->offset = offset +3 ;
+			
+			debug("info about rio table hdr ---\n");
+			debug("ver_num: %x\nscal_count: %x\nriodev_count: %x\noffset of rio table: %x\n ",
+				rio_table_ptr->ver_num, rio_table_ptr->scal_count,
+				rio_table_ptr->riodev_count, rio_table_ptr->offset);
+
+			rio_complete = 1;
+		}
+	}
+
+	if (!hs_complete && !rio_complete)
+		goto error_nodev;
+
+	if (rio_table_ptr) {
+		if (rio_complete && rio_table_ptr->ver_num == 3) {
+			rc = ebda_rio_table ();
+			if (rc)
+				goto out;
+		}
+	}
+	rc = ebda_rsrc_controller ();
+	if (rc)
+		goto out;
+
+	rc = ebda_rsrc_rsrc ();
+	goto out;
+error_nodev:
+	rc = -ENODEV;
+out:
+	iounmap (io_mem);
+	return rc;
+}
+
+/*
+ * map info of scalability details and rio details from physical address
+ */
+static int __init ebda_rio_table (void)
+{
+	u16 offset;
+	u8 i;
+	struct rio_detail *rio_detail_ptr;
+
+	offset = rio_table_ptr->offset;
+	offset += 12 * rio_table_ptr->scal_count;
+
+	// we do concern about rio details
+	for (i = 0; i < rio_table_ptr->riodev_count; i++) {
+		rio_detail_ptr = kzalloc(sizeof(struct rio_detail), GFP_KERNEL);
+		if (!rio_detail_ptr)
+			return -ENOMEM;
+		rio_detail_ptr->rio_node_id = readb (io_mem + offset);
+		rio_detail_ptr->bbar = readl (io_mem + offset + 1);
+		rio_detail_ptr->rio_type = readb (io_mem + offset + 5);
+		rio_detail_ptr->owner_id = readb (io_mem + offset + 6);
+		rio_detail_ptr->port0_node_connect = readb (io_mem + offset + 7);
+		rio_detail_ptr->port0_port_connect = readb (io_mem + offset + 8);
+		rio_detail_ptr->port1_node_connect = readb (io_mem + offset + 9);
+		rio_detail_ptr->port1_port_connect = readb (io_mem + offset + 10);
+		rio_detail_ptr->first_slot_num = readb (io_mem + offset + 11);
+		rio_detail_ptr->status = readb (io_mem + offset + 12);
+		rio_detail_ptr->wpindex = readb (io_mem + offset + 13);
+		rio_detail_ptr->chassis_num = readb (io_mem + offset + 14);
+//		debug ("rio_node_id: %x\nbbar: %x\nrio_type: %x\nowner_id: %x\nport0_node: %x\nport0_port: %x\nport1_node: %x\nport1_port: %x\nfirst_slot_num: %x\nstatus: %x\n", rio_detail_ptr->rio_node_id, rio_detail_ptr->bbar, rio_detail_ptr->rio_type, rio_detail_ptr->owner_id, rio_detail_ptr->port0_node_connect, rio_detail_ptr->port0_port_connect, rio_detail_ptr->port1_node_connect, rio_detail_ptr->port1_port_connect, rio_detail_ptr->first_slot_num, rio_detail_ptr->status);
+		//create linked list of chassis
+		if (rio_detail_ptr->rio_type == 4 || rio_detail_ptr->rio_type == 5) 
+			list_add (&rio_detail_ptr->rio_detail_list, &rio_vg_head);
+		//create linked list of expansion box				
+		else if (rio_detail_ptr->rio_type == 6 || rio_detail_ptr->rio_type == 7) 
+			list_add (&rio_detail_ptr->rio_detail_list, &rio_lo_head);
+		else 
+			// not in my concern
+			kfree (rio_detail_ptr);
+		offset += 15;
+	}
+	print_lo_info ();
+	print_vg_info ();
+	return 0;
+}
+
+/*
+ * reorganizing linked list of chassis	 
+ */
+static struct opt_rio *search_opt_vg (u8 chassis_num)
+{
+	struct opt_rio *ptr;
+	list_for_each_entry(ptr, &opt_vg_head, opt_rio_list) {
+		if (ptr->chassis_num == chassis_num)
+			return ptr;
+	}		
+	return NULL;
+}
+
+static int __init combine_wpg_for_chassis (void)
+{
+	struct opt_rio *opt_rio_ptr = NULL;
+	struct rio_detail *rio_detail_ptr = NULL;
+	
+	list_for_each_entry(rio_detail_ptr, &rio_vg_head, rio_detail_list) {
+		opt_rio_ptr = search_opt_vg (rio_detail_ptr->chassis_num);
+		if (!opt_rio_ptr) {
+			opt_rio_ptr = kzalloc(sizeof(struct opt_rio), GFP_KERNEL);
+			if (!opt_rio_ptr)
+				return -ENOMEM;
+			opt_rio_ptr->rio_type = rio_detail_ptr->rio_type;
+			opt_rio_ptr->chassis_num = rio_detail_ptr->chassis_num;
+			opt_rio_ptr->first_slot_num = rio_detail_ptr->first_slot_num;
+			opt_rio_ptr->middle_num = rio_detail_ptr->first_slot_num;
+			list_add (&opt_rio_ptr->opt_rio_list, &opt_vg_head);
+		} else {	
+			opt_rio_ptr->first_slot_num = min (opt_rio_ptr->first_slot_num, rio_detail_ptr->first_slot_num);
+			opt_rio_ptr->middle_num = max (opt_rio_ptr->middle_num, rio_detail_ptr->first_slot_num);
+		}	
+	}
+	print_opt_vg ();
+	return 0;	
+}	
+
+/*
+ * reorganizing linked list of expansion box
+ */
+static struct opt_rio_lo *search_opt_lo (u8 chassis_num)
+{
+	struct opt_rio_lo *ptr;
+	list_for_each_entry(ptr, &opt_lo_head, opt_rio_lo_list) {
+		if (ptr->chassis_num == chassis_num)
+			return ptr;
+	}		
+	return NULL;
+}
+
+static int combine_wpg_for_expansion (void)
+{
+	struct opt_rio_lo *opt_rio_lo_ptr = NULL;
+	struct rio_detail *rio_detail_ptr = NULL;
+	
+	list_for_each_entry(rio_detail_ptr, &rio_lo_head, rio_detail_list) {
+		opt_rio_lo_ptr = search_opt_lo (rio_detail_ptr->chassis_num);
+		if (!opt_rio_lo_ptr) {
+			opt_rio_lo_ptr = kzalloc(sizeof(struct opt_rio_lo), GFP_KERNEL);
+			if (!opt_rio_lo_ptr)
+				return -ENOMEM;
+			opt_rio_lo_ptr->rio_type = rio_detail_ptr->rio_type;
+			opt_rio_lo_ptr->chassis_num = rio_detail_ptr->chassis_num;
+			opt_rio_lo_ptr->first_slot_num = rio_detail_ptr->first_slot_num;
+			opt_rio_lo_ptr->middle_num = rio_detail_ptr->first_slot_num;
+			opt_rio_lo_ptr->pack_count = 1;
+			
+			list_add (&opt_rio_lo_ptr->opt_rio_lo_list, &opt_lo_head);
+		} else {	
+			opt_rio_lo_ptr->first_slot_num = min (opt_rio_lo_ptr->first_slot_num, rio_detail_ptr->first_slot_num);
+			opt_rio_lo_ptr->middle_num = max (opt_rio_lo_ptr->middle_num, rio_detail_ptr->first_slot_num);
+			opt_rio_lo_ptr->pack_count = 2;
+		}	
+	}
+	return 0;	
+}
+	
+
+/* Since we don't know the max slot number per each chassis, hence go
+ * through the list of all chassis to find out the range
+ * Arguments: slot_num, 1st slot number of the chassis we think we are on, 
+ * var (0 = chassis, 1 = expansion box) 
+ */
+static int first_slot_num (u8 slot_num, u8 first_slot, u8 var)
+{
+	struct opt_rio *opt_vg_ptr = NULL;
+	struct opt_rio_lo *opt_lo_ptr = NULL;
+	int rc = 0;
+
+	if (!var) {
+		list_for_each_entry(opt_vg_ptr, &opt_vg_head, opt_rio_list) {
+			if ((first_slot < opt_vg_ptr->first_slot_num) && (slot_num >= opt_vg_ptr->first_slot_num)) { 
+				rc = -ENODEV;
+				break;
+			}
+		}
+	} else {
+		list_for_each_entry(opt_lo_ptr, &opt_lo_head, opt_rio_lo_list) {
+			if ((first_slot < opt_lo_ptr->first_slot_num) && (slot_num >= opt_lo_ptr->first_slot_num)) {
+				rc = -ENODEV;
+				break;
+			}
+		}
+	}
+	return rc;
+}
+
+static struct opt_rio_lo * find_rxe_num (u8 slot_num)
+{
+	struct opt_rio_lo *opt_lo_ptr;
+
+	list_for_each_entry(opt_lo_ptr, &opt_lo_head, opt_rio_lo_list) {
+		//check to see if this slot_num belongs to expansion box
+		if ((slot_num >= opt_lo_ptr->first_slot_num) && (!first_slot_num (slot_num, opt_lo_ptr->first_slot_num, 1))) 
+			return opt_lo_ptr;
+	}
+	return NULL;
+}
+
+static struct opt_rio * find_chassis_num (u8 slot_num)
+{
+	struct opt_rio *opt_vg_ptr;
+
+	list_for_each_entry(opt_vg_ptr, &opt_vg_head, opt_rio_list) {
+		//check to see if this slot_num belongs to chassis 
+		if ((slot_num >= opt_vg_ptr->first_slot_num) && (!first_slot_num (slot_num, opt_vg_ptr->first_slot_num, 0))) 
+			return opt_vg_ptr;
+	}
+	return NULL;
+}
+
+/* This routine will find out how many slots are in the chassis, so that
+ * the slot numbers for rxe100 would start from 1, and not from 7, or 6 etc
+ */
+static u8 calculate_first_slot (u8 slot_num)
+{
+	u8 first_slot = 1;
+	struct slot * slot_cur;
+	
+	list_for_each_entry(slot_cur, &ibmphp_slot_head, ibm_slot_list) {
+		if (slot_cur->ctrl) {
+			if ((slot_cur->ctrl->ctlr_type != 4) && (slot_cur->ctrl->ending_slot_num > first_slot) && (slot_num > slot_cur->ctrl->ending_slot_num)) 
+				first_slot = slot_cur->ctrl->ending_slot_num;
+		}
+	}			
+	return first_slot + 1;
+
+}
+
+#define SLOT_NAME_SIZE 30
+
+static char *create_file_name (struct slot * slot_cur)
+{
+	struct opt_rio *opt_vg_ptr = NULL;
+	struct opt_rio_lo *opt_lo_ptr = NULL;
+	static char str[SLOT_NAME_SIZE];
+	int which = 0; /* rxe = 1, chassis = 0 */
+	u8 number = 1; /* either chassis or rxe # */
+	u8 first_slot = 1;
+	u8 slot_num;
+	u8 flag = 0;
+
+	if (!slot_cur) {
+		err ("Structure passed is empty\n");
+		return NULL;
+	}
+	
+	slot_num = slot_cur->number;
+
+	memset (str, 0, sizeof(str));
+	
+	if (rio_table_ptr) {
+		if (rio_table_ptr->ver_num == 3) {
+			opt_vg_ptr = find_chassis_num (slot_num);
+			opt_lo_ptr = find_rxe_num (slot_num);
+		}
+	}
+	if (opt_vg_ptr) {
+		if (opt_lo_ptr) {
+			if ((slot_num - opt_vg_ptr->first_slot_num) > (slot_num - opt_lo_ptr->first_slot_num)) {
+				number = opt_lo_ptr->chassis_num;
+				first_slot = opt_lo_ptr->first_slot_num;
+				which = 1; /* it is RXE */
+			} else {
+				first_slot = opt_vg_ptr->first_slot_num;
+				number = opt_vg_ptr->chassis_num;
+				which = 0;
+			}
+		} else {
+			first_slot = opt_vg_ptr->first_slot_num;
+			number = opt_vg_ptr->chassis_num;
+			which = 0;
+		}
+		++flag;
+	} else if (opt_lo_ptr) {
+		number = opt_lo_ptr->chassis_num;
+		first_slot = opt_lo_ptr->first_slot_num;
+		which = 1;
+		++flag;
+	} else if (rio_table_ptr) {
+		if (rio_table_ptr->ver_num == 3) {
+			/* if both NULL and we DO have correct RIO table in BIOS */
+			return NULL;
+		}
+	} 
+	if (!flag) {
+		if (slot_cur->ctrl->ctlr_type == 4) {
+			first_slot = calculate_first_slot (slot_num);
+			which = 1;
+		} else {
+			which = 0;
+		}
+	}
+
+	sprintf(str, "%s%dslot%d",
+		which == 0 ? "chassis" : "rxe",
+		number, slot_num - first_slot + 1);
+	return str;
+}
+
+static int fillslotinfo(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot;
+	int rc = 0;
+
+	if (!hotplug_slot || !hotplug_slot->private)
+		return -EINVAL;
+
+	slot = hotplug_slot->private;
+	rc = ibmphp_hpc_readslot(slot, READ_ALLSTAT, NULL);
+	if (rc)
+		return rc;
+
+	// power - enabled:1  not:0
+	hotplug_slot->info->power_status = SLOT_POWER(slot->status);
+
+	// attention - off:0, on:1, blinking:2
+	hotplug_slot->info->attention_status = SLOT_ATTN(slot->status, slot->ext_status);
+
+	// latch - open:1 closed:0
+	hotplug_slot->info->latch_status = SLOT_LATCH(slot->status);
+
+	// pci board - present:1 not:0
+	if (SLOT_PRESENT (slot->status))
+		hotplug_slot->info->adapter_status = 1;
+	else
+		hotplug_slot->info->adapter_status = 0;
+/*
+	if (slot->bus_on->supported_bus_mode
+		&& (slot->bus_on->supported_speed == BUS_SPEED_66))
+		hotplug_slot->info->max_bus_speed_status = BUS_SPEED_66PCIX;
+	else
+		hotplug_slot->info->max_bus_speed_status = slot->bus_on->supported_speed;
+*/
+
+	return rc;
+}
+
+static void release_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot;
+
+	if (!hotplug_slot || !hotplug_slot->private)
+		return;
+
+	slot = hotplug_slot->private;
+	kfree(slot->hotplug_slot->info);
+	kfree(slot->hotplug_slot);
+	slot->ctrl = NULL;
+	slot->bus_on = NULL;
+
+	/* we don't want to actually remove the resources, since free_resources will do just that */
+	ibmphp_unconfigure_card(&slot, -1);
+
+	kfree (slot);
+}
+
+static struct pci_driver ibmphp_driver;
+
+/*
+ * map info (ctlr-id, slot count, slot#.. bus count, bus#, ctlr type...) of
+ * each hpc from physical address to a list of hot plug controllers based on
+ * hpc descriptors.
+ */
+static int __init ebda_rsrc_controller (void)
+{
+	u16 addr, addr_slot, addr_bus;
+	u8 ctlr_id, temp, bus_index;
+	u16 ctlr, slot, bus;
+	u16 slot_num, bus_num, index;
+	struct hotplug_slot *hp_slot_ptr;
+	struct controller *hpc_ptr;
+	struct ebda_hpc_bus *bus_ptr;
+	struct ebda_hpc_slot *slot_ptr;
+	struct bus_info *bus_info_ptr1, *bus_info_ptr2;
+	int rc;
+	struct slot *tmp_slot;
+	char name[SLOT_NAME_SIZE];
+
+	addr = hpc_list_ptr->phys_addr;
+	for (ctlr = 0; ctlr < hpc_list_ptr->num_ctlrs; ctlr++) {
+		bus_index = 1;
+		ctlr_id = readb (io_mem + addr);
+		addr += 1;
+		slot_num = readb (io_mem + addr);
+
+		addr += 1;
+		addr_slot = addr;	/* offset of slot structure */
+		addr += (slot_num * 4);
+
+		bus_num = readb (io_mem + addr);
+
+		addr += 1;
+		addr_bus = addr;	/* offset of bus */
+		addr += (bus_num * 9);	/* offset of ctlr_type */
+		temp = readb (io_mem + addr);
+
+		addr += 1;
+		/* init hpc structure */
+		hpc_ptr = alloc_ebda_hpc (slot_num, bus_num);
+		if (!hpc_ptr ) {
+			rc = -ENOMEM;
+			goto error_no_hpc;
+		}
+		hpc_ptr->ctlr_id = ctlr_id;
+		hpc_ptr->ctlr_relative_id = ctlr;
+		hpc_ptr->slot_count = slot_num;
+		hpc_ptr->bus_count = bus_num;
+		debug ("now enter ctlr data struture ---\n");
+		debug ("ctlr id: %x\n", ctlr_id);
+		debug ("ctlr_relative_id: %x\n", hpc_ptr->ctlr_relative_id);
+		debug ("count of slots controlled by this ctlr: %x\n", slot_num);
+		debug ("count of buses controlled by this ctlr: %x\n", bus_num);
+
+		/* init slot structure, fetch slot, bus, cap... */
+		slot_ptr = hpc_ptr->slots;
+		for (slot = 0; slot < slot_num; slot++) {
+			slot_ptr->slot_num = readb (io_mem + addr_slot);
+			slot_ptr->slot_bus_num = readb (io_mem + addr_slot + slot_num);
+			slot_ptr->ctl_index = readb (io_mem + addr_slot + 2*slot_num);
+			slot_ptr->slot_cap = readb (io_mem + addr_slot + 3*slot_num);
+
+			// create bus_info lined list --- if only one slot per bus: slot_min = slot_max 
+
+			bus_info_ptr2 = ibmphp_find_same_bus_num (slot_ptr->slot_bus_num);
+			if (!bus_info_ptr2) {
+				bus_info_ptr1 = kzalloc(sizeof(struct bus_info), GFP_KERNEL);
+				if (!bus_info_ptr1) {
+					rc = -ENOMEM;
+					goto error_no_hp_slot;
+				}
+				bus_info_ptr1->slot_min = slot_ptr->slot_num;
+				bus_info_ptr1->slot_max = slot_ptr->slot_num;
+				bus_info_ptr1->slot_count += 1;
+				bus_info_ptr1->busno = slot_ptr->slot_bus_num;
+				bus_info_ptr1->index = bus_index++;
+				bus_info_ptr1->current_speed = 0xff;
+				bus_info_ptr1->current_bus_mode = 0xff;
+				
+				bus_info_ptr1->controller_id = hpc_ptr->ctlr_id;
+				
+				list_add_tail (&bus_info_ptr1->bus_info_list, &bus_info_head);
+
+			} else {
+				bus_info_ptr2->slot_min = min (bus_info_ptr2->slot_min, slot_ptr->slot_num);
+				bus_info_ptr2->slot_max = max (bus_info_ptr2->slot_max, slot_ptr->slot_num);
+				bus_info_ptr2->slot_count += 1;
+
+			}
+
+			// end of creating the bus_info linked list
+
+			slot_ptr++;
+			addr_slot += 1;
+		}
+
+		/* init bus structure */
+		bus_ptr = hpc_ptr->buses;
+		for (bus = 0; bus < bus_num; bus++) {
+			bus_ptr->bus_num = readb (io_mem + addr_bus + bus);
+			bus_ptr->slots_at_33_conv = readb (io_mem + addr_bus + bus_num + 8 * bus);
+			bus_ptr->slots_at_66_conv = readb (io_mem + addr_bus + bus_num + 8 * bus + 1);
+
+			bus_ptr->slots_at_66_pcix = readb (io_mem + addr_bus + bus_num + 8 * bus + 2);
+
+			bus_ptr->slots_at_100_pcix = readb (io_mem + addr_bus + bus_num + 8 * bus + 3);
+
+			bus_ptr->slots_at_133_pcix = readb (io_mem + addr_bus + bus_num + 8 * bus + 4);
+
+			bus_info_ptr2 = ibmphp_find_same_bus_num (bus_ptr->bus_num);
+			if (bus_info_ptr2) {
+				bus_info_ptr2->slots_at_33_conv = bus_ptr->slots_at_33_conv;
+				bus_info_ptr2->slots_at_66_conv = bus_ptr->slots_at_66_conv;
+				bus_info_ptr2->slots_at_66_pcix = bus_ptr->slots_at_66_pcix;
+				bus_info_ptr2->slots_at_100_pcix = bus_ptr->slots_at_100_pcix;
+				bus_info_ptr2->slots_at_133_pcix = bus_ptr->slots_at_133_pcix; 
+			}
+			bus_ptr++;
+		}
+
+		hpc_ptr->ctlr_type = temp;
+
+		switch (hpc_ptr->ctlr_type) {
+			case 1:
+				hpc_ptr->u.pci_ctlr.bus = readb (io_mem + addr);
+				hpc_ptr->u.pci_ctlr.dev_fun = readb (io_mem + addr + 1);
+				hpc_ptr->irq = readb (io_mem + addr + 2);
+				addr += 3;
+				debug ("ctrl bus = %x, ctlr devfun = %x, irq = %x\n", 
+					hpc_ptr->u.pci_ctlr.bus,
+					hpc_ptr->u.pci_ctlr.dev_fun, hpc_ptr->irq);
+				break;
+
+			case 0:
+				hpc_ptr->u.isa_ctlr.io_start = readw (io_mem + addr);
+				hpc_ptr->u.isa_ctlr.io_end = readw (io_mem + addr + 2);
+				if (!request_region (hpc_ptr->u.isa_ctlr.io_start,
+						     (hpc_ptr->u.isa_ctlr.io_end - hpc_ptr->u.isa_ctlr.io_start + 1),
+						     "ibmphp")) {
+					rc = -ENODEV;
+					goto error_no_hp_slot;
+				}
+				hpc_ptr->irq = readb (io_mem + addr + 4);
+				addr += 5;
+				break;
+
+			case 2:
+			case 4:
+				hpc_ptr->u.wpeg_ctlr.wpegbbar = readl (io_mem + addr);
+				hpc_ptr->u.wpeg_ctlr.i2c_addr = readb (io_mem + addr + 4);
+				hpc_ptr->irq = readb (io_mem + addr + 5);
+				addr += 6;
+				break;
+			default:
+				rc = -ENODEV;
+				goto error_no_hp_slot;
+		}
+
+		//reorganize chassis' linked list
+		combine_wpg_for_chassis ();
+		combine_wpg_for_expansion ();
+		hpc_ptr->revision = 0xff;
+		hpc_ptr->options = 0xff;
+		hpc_ptr->starting_slot_num = hpc_ptr->slots[0].slot_num;
+		hpc_ptr->ending_slot_num = hpc_ptr->slots[slot_num-1].slot_num;
+
+		// register slots with hpc core as well as create linked list of ibm slot
+		for (index = 0; index < hpc_ptr->slot_count; index++) {
+
+			hp_slot_ptr = kzalloc(sizeof(*hp_slot_ptr), GFP_KERNEL);
+			if (!hp_slot_ptr) {
+				rc = -ENOMEM;
+				goto error_no_hp_slot;
+			}
+
+			hp_slot_ptr->info = kzalloc(sizeof(struct hotplug_slot_info), GFP_KERNEL);
+			if (!hp_slot_ptr->info) {
+				rc = -ENOMEM;
+				goto error_no_hp_info;
+			}
+
+			tmp_slot = kzalloc(sizeof(*tmp_slot), GFP_KERNEL);
+			if (!tmp_slot) {
+				rc = -ENOMEM;
+				goto error_no_slot;
+			}
+
+			tmp_slot->flag = 1;
+
+			tmp_slot->capabilities = hpc_ptr->slots[index].slot_cap;
+			if ((hpc_ptr->slots[index].slot_cap & EBDA_SLOT_133_MAX) == EBDA_SLOT_133_MAX)
+				tmp_slot->supported_speed =  3;
+			else if ((hpc_ptr->slots[index].slot_cap & EBDA_SLOT_100_MAX) == EBDA_SLOT_100_MAX)
+				tmp_slot->supported_speed =  2;
+			else if ((hpc_ptr->slots[index].slot_cap & EBDA_SLOT_66_MAX) == EBDA_SLOT_66_MAX)
+				tmp_slot->supported_speed =  1;
+				
+			if ((hpc_ptr->slots[index].slot_cap & EBDA_SLOT_PCIX_CAP) == EBDA_SLOT_PCIX_CAP)
+				tmp_slot->supported_bus_mode = 1;
+			else
+				tmp_slot->supported_bus_mode = 0;
+
+
+			tmp_slot->bus = hpc_ptr->slots[index].slot_bus_num;
+
+			bus_info_ptr1 = ibmphp_find_same_bus_num (hpc_ptr->slots[index].slot_bus_num);
+			if (!bus_info_ptr1) {
+				kfree(tmp_slot);
+				rc = -ENODEV;
+				goto error;
+			}
+			tmp_slot->bus_on = bus_info_ptr1;
+			bus_info_ptr1 = NULL;
+			tmp_slot->ctrl = hpc_ptr;
+
+			tmp_slot->ctlr_index = hpc_ptr->slots[index].ctl_index;
+			tmp_slot->number = hpc_ptr->slots[index].slot_num;
+			tmp_slot->hotplug_slot = hp_slot_ptr;
+
+			hp_slot_ptr->private = tmp_slot;
+			hp_slot_ptr->release = release_slot;
+
+			rc = fillslotinfo(hp_slot_ptr);
+			if (rc)
+				goto error;
+
+			rc = ibmphp_init_devno ((struct slot **) &hp_slot_ptr->private);
+			if (rc)
+				goto error;
+			hp_slot_ptr->ops = &ibmphp_hotplug_slot_ops;
+
+			// end of registering ibm slot with hotplug core
+
+			list_add (& ((struct slot *)(hp_slot_ptr->private))->ibm_slot_list, &ibmphp_slot_head);
+		}
+
+		print_bus_info ();
+		list_add (&hpc_ptr->ebda_hpc_list, &ebda_hpc_head );
+
+	}			/* each hpc  */
+
+	list_for_each_entry(tmp_slot, &ibmphp_slot_head, ibm_slot_list) {
+		snprintf(name, SLOT_NAME_SIZE, "%s", create_file_name(tmp_slot));
+		pci_hp_register(tmp_slot->hotplug_slot,
+			pci_find_bus(0, tmp_slot->bus), tmp_slot->device, name);
+	}
+
+	print_ebda_hpc ();
+	print_ibm_slot ();
+	return 0;
+
+error:
+	kfree (hp_slot_ptr->private);
+error_no_slot:
+	kfree (hp_slot_ptr->info);
+error_no_hp_info:
+	kfree (hp_slot_ptr);
+error_no_hp_slot:
+	free_ebda_hpc (hpc_ptr);
+error_no_hpc:
+	iounmap (io_mem);
+	return rc;
+}
+
+/* 
+ * map info (bus, devfun, start addr, end addr..) of i/o, memory,
+ * pfm from the physical addr to a list of resource.
+ */
+static int __init ebda_rsrc_rsrc (void)
+{
+	u16 addr;
+	short rsrc;
+	u8 type, rsrc_type;
+	struct ebda_pci_rsrc *rsrc_ptr;
+
+	addr = rsrc_list_ptr->phys_addr;
+	debug ("now entering rsrc land\n");
+	debug ("offset of rsrc: %x\n", rsrc_list_ptr->phys_addr);
+
+	for (rsrc = 0; rsrc < rsrc_list_ptr->num_entries; rsrc++) {
+		type = readb (io_mem + addr);
+
+		addr += 1;
+		rsrc_type = type & EBDA_RSRC_TYPE_MASK;
+
+		if (rsrc_type == EBDA_IO_RSRC_TYPE) {
+			rsrc_ptr = alloc_ebda_pci_rsrc ();
+			if (!rsrc_ptr) {
+				iounmap (io_mem);
+				return -ENOMEM;
+			}
+			rsrc_ptr->rsrc_type = type;
+
+			rsrc_ptr->bus_num = readb (io_mem + addr);
+			rsrc_ptr->dev_fun = readb (io_mem + addr + 1);
+			rsrc_ptr->start_addr = readw (io_mem + addr + 2);
+			rsrc_ptr->end_addr = readw (io_mem + addr + 4);
+			addr += 6;
+
+			debug ("rsrc from io type ----\n");
+			debug ("rsrc type: %x bus#: %x dev_func: %x start addr: %x end addr: %x\n",
+				rsrc_ptr->rsrc_type, rsrc_ptr->bus_num, rsrc_ptr->dev_fun, rsrc_ptr->start_addr, rsrc_ptr->end_addr);
+
+			list_add (&rsrc_ptr->ebda_pci_rsrc_list, &ibmphp_ebda_pci_rsrc_head);
+		}
+
+		if (rsrc_type == EBDA_MEM_RSRC_TYPE || rsrc_type == EBDA_PFM_RSRC_TYPE) {
+			rsrc_ptr = alloc_ebda_pci_rsrc ();
+			if (!rsrc_ptr ) {
+				iounmap (io_mem);
+				return -ENOMEM;
+			}
+			rsrc_ptr->rsrc_type = type;
+
+			rsrc_ptr->bus_num = readb (io_mem + addr);
+			rsrc_ptr->dev_fun = readb (io_mem + addr + 1);
+			rsrc_ptr->start_addr = readl (io_mem + addr + 2);
+			rsrc_ptr->end_addr = readl (io_mem + addr + 6);
+			addr += 10;
+
+			debug ("rsrc from mem or pfm ---\n");
+			debug ("rsrc type: %x bus#: %x dev_func: %x start addr: %x end addr: %x\n", 
+				rsrc_ptr->rsrc_type, rsrc_ptr->bus_num, rsrc_ptr->dev_fun, rsrc_ptr->start_addr, rsrc_ptr->end_addr);
+
+			list_add (&rsrc_ptr->ebda_pci_rsrc_list, &ibmphp_ebda_pci_rsrc_head);
+		}
+	}
+	kfree (rsrc_list_ptr);
+	rsrc_list_ptr = NULL;
+	print_ebda_pci_rsrc ();
+	return 0;
+}
+
+u16 ibmphp_get_total_controllers (void)
+{
+	return hpc_list_ptr->num_ctlrs;
+}
+
+struct slot *ibmphp_get_slot_from_physical_num (u8 physical_num)
+{
+	struct slot *slot;
+
+	list_for_each_entry(slot, &ibmphp_slot_head, ibm_slot_list) {
+		if (slot->number == physical_num)
+			return slot;
+	}
+	return NULL;
+}
+
+/* To find:
+ *	- the smallest slot number
+ *	- the largest slot number
+ *	- the total number of the slots based on each bus
+ *	  (if only one slot per bus slot_min = slot_max )
+ */
+struct bus_info *ibmphp_find_same_bus_num (u32 num)
+{
+	struct bus_info *ptr;
+
+	list_for_each_entry(ptr, &bus_info_head, bus_info_list) {
+		if (ptr->busno == num) 
+			 return ptr;
+	}
+	return NULL;
+}
+
+/*  Finding relative bus number, in order to map corresponding
+ *  bus register
+ */
+int ibmphp_get_bus_index (u8 num)
+{
+	struct bus_info *ptr;
+
+	list_for_each_entry(ptr, &bus_info_head, bus_info_list) {
+		if (ptr->busno == num)  
+			return ptr->index;
+	}
+	return -ENODEV;
+}
+
+void ibmphp_free_bus_info_queue (void)
+{
+	struct bus_info *bus_info;
+	struct list_head *list;
+	struct list_head *next;
+
+	list_for_each_safe (list, next, &bus_info_head ) {
+		bus_info = list_entry (list, struct bus_info, bus_info_list);
+		kfree (bus_info);
+	}
+}
+
+void ibmphp_free_ebda_hpc_queue (void)
+{
+	struct controller *controller = NULL;
+	struct list_head *list;
+	struct list_head *next;
+	int pci_flag = 0;
+
+	list_for_each_safe (list, next, &ebda_hpc_head) {
+		controller = list_entry (list, struct controller, ebda_hpc_list);
+		if (controller->ctlr_type == 0)
+			release_region (controller->u.isa_ctlr.io_start, (controller->u.isa_ctlr.io_end - controller->u.isa_ctlr.io_start + 1));
+		else if ((controller->ctlr_type == 1) && (!pci_flag)) {
+			++pci_flag;
+			pci_unregister_driver (&ibmphp_driver);
+		}
+		free_ebda_hpc (controller);
+	}
+}
+
+void ibmphp_free_ebda_pci_rsrc_queue (void)
+{
+	struct ebda_pci_rsrc *resource;
+	struct list_head *list;
+	struct list_head *next;
+
+	list_for_each_safe (list, next, &ibmphp_ebda_pci_rsrc_head) {
+		resource = list_entry (list, struct ebda_pci_rsrc, ebda_pci_rsrc_list);
+		kfree (resource);
+		resource = NULL;
+	}
+}
+
+static struct pci_device_id id_table[] = {
+	{
+		.vendor		= PCI_VENDOR_ID_IBM,
+		.device		= HPC_DEVICE_ID,
+		.subvendor	= PCI_VENDOR_ID_IBM,
+		.subdevice	= HPC_SUBSYSTEM_ID,
+		.class		= ((PCI_CLASS_SYSTEM_PCI_HOTPLUG << 8) | 0x00),
+	}, {}
+};		
+
+MODULE_DEVICE_TABLE(pci, id_table);
+
+static int ibmphp_probe (struct pci_dev *, const struct pci_device_id *);
+static struct pci_driver ibmphp_driver = {
+	.name		= "ibmphp",
+	.id_table	= id_table,
+	.probe		= ibmphp_probe,
+};
+
+int ibmphp_register_pci (void)
+{
+	struct controller *ctrl;
+	int rc = 0;
+
+	list_for_each_entry(ctrl, &ebda_hpc_head, ebda_hpc_list) {
+		if (ctrl->ctlr_type == 1) {
+			rc = pci_register_driver(&ibmphp_driver);
+			break;
+		}
+	}
+	return rc;
+}
+static int ibmphp_probe (struct pci_dev * dev, const struct pci_device_id *ids)
+{
+	struct controller *ctrl;
+
+	debug ("inside ibmphp_probe\n");
+	
+	list_for_each_entry(ctrl, &ebda_hpc_head, ebda_hpc_list) {
+		if (ctrl->ctlr_type == 1) {
+			if ((dev->devfn == ctrl->u.pci_ctlr.dev_fun) && (dev->bus->number == ctrl->u.pci_ctlr.bus)) {
+				ctrl->ctrl_dev = dev;
+				debug ("found device!!!\n");
+				debug ("dev->device = %x, dev->subsystem_device = %x\n", dev->device, dev->subsystem_device);
+				return 0;
+			}
+		}
+	}
+	return -ENODEV;
+}
+
diff --git a/drivers/pci/hotplug/ibmphp_hpc.c b/drivers/pci/hotplug/ibmphp_hpc.c
new file mode 100644
index 00000000..f59ed305
--- /dev/null
+++ b/drivers/pci/hotplug/ibmphp_hpc.c
@@ -0,0 +1,1132 @@
+/*
+ * IBM Hot Plug Controller Driver
+ *
+ * Written By: Jyoti Shah, IBM Corporation
+ *
+ * Copyright (C) 2001-2003 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <gregkh@us.ibm.com>
+ *                  <jshah@us.ibm.com>
+ *
+ */
+
+#include <linux/wait.h>
+#include <linux/time.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/semaphore.h>
+#include <linux/kthread.h>
+#include "ibmphp.h"
+
+static int to_debug = 0;
+#define debug_polling(fmt, arg...)	do { if (to_debug) debug (fmt, arg); } while (0)
+
+//----------------------------------------------------------------------------
+// timeout values
+//----------------------------------------------------------------------------
+#define CMD_COMPLETE_TOUT_SEC	60	// give HPC 60 sec to finish cmd
+#define HPC_CTLR_WORKING_TOUT	60	// give HPC 60 sec to finish cmd
+#define HPC_GETACCESS_TIMEOUT	60	// seconds
+#define POLL_INTERVAL_SEC	2	// poll HPC every 2 seconds
+#define POLL_LATCH_CNT		5	// poll latch 5 times, then poll slots
+
+//----------------------------------------------------------------------------
+// Winnipeg Architected Register Offsets
+//----------------------------------------------------------------------------
+#define WPG_I2CMBUFL_OFFSET	0x08	// I2C Message Buffer Low
+#define WPG_I2CMOSUP_OFFSET	0x10	// I2C Master Operation Setup Reg
+#define WPG_I2CMCNTL_OFFSET	0x20	// I2C Master Control Register
+#define WPG_I2CPARM_OFFSET	0x40	// I2C Parameter Register
+#define WPG_I2CSTAT_OFFSET	0x70	// I2C Status Register
+
+//----------------------------------------------------------------------------
+// Winnipeg Store Type commands (Add this commands to the register offset)
+//----------------------------------------------------------------------------
+#define WPG_I2C_AND		0x1000	// I2C AND operation
+#define WPG_I2C_OR		0x2000	// I2C OR operation
+
+//----------------------------------------------------------------------------
+// Command set for I2C Master Operation Setup Register
+//----------------------------------------------------------------------------
+#define WPG_READATADDR_MASK	0x00010000	// read,bytes,I2C shifted,index
+#define WPG_WRITEATADDR_MASK	0x40010000	// write,bytes,I2C shifted,index
+#define WPG_READDIRECT_MASK	0x10010000
+#define WPG_WRITEDIRECT_MASK	0x60010000
+
+
+//----------------------------------------------------------------------------
+// bit masks for I2C Master Control Register
+//----------------------------------------------------------------------------
+#define WPG_I2CMCNTL_STARTOP_MASK	0x00000002	// Start the Operation
+
+//----------------------------------------------------------------------------
+//
+//----------------------------------------------------------------------------
+#define WPG_I2C_IOREMAP_SIZE	0x2044	// size of linear address interval
+
+//----------------------------------------------------------------------------
+// command index
+//----------------------------------------------------------------------------
+#define WPG_1ST_SLOT_INDEX	0x01	// index - 1st slot for ctlr
+#define WPG_CTLR_INDEX		0x0F	// index - ctlr
+#define WPG_1ST_EXTSLOT_INDEX	0x10	// index - 1st ext slot for ctlr
+#define WPG_1ST_BUS_INDEX	0x1F	// index - 1st bus for ctlr
+
+//----------------------------------------------------------------------------
+// macro utilities
+//----------------------------------------------------------------------------
+// if bits 20,22,25,26,27,29,30 are OFF return 1
+#define HPC_I2CSTATUS_CHECK(s)	((u8)((s & 0x00000A76) ? 0 : 1))
+
+//----------------------------------------------------------------------------
+// global variables
+//----------------------------------------------------------------------------
+static struct mutex sem_hpcaccess;	// lock access to HPC
+static struct semaphore semOperations;	// lock all operations and
+					// access to data structures
+static struct semaphore sem_exit;	// make sure polling thread goes away
+static struct task_struct *ibmphp_poll_thread;
+//----------------------------------------------------------------------------
+// local function prototypes
+//----------------------------------------------------------------------------
+static u8 i2c_ctrl_read (struct controller *, void __iomem *, u8);
+static u8 i2c_ctrl_write (struct controller *, void __iomem *, u8, u8);
+static u8 hpc_writecmdtoindex (u8, u8);
+static u8 hpc_readcmdtoindex (u8, u8);
+static void get_hpc_access (void);
+static void free_hpc_access (void);
+static int poll_hpc(void *data);
+static int process_changeinstatus (struct slot *, struct slot *);
+static int process_changeinlatch (u8, u8, struct controller *);
+static int hpc_wait_ctlr_notworking (int, struct controller *, void __iomem *, u8 *);
+//----------------------------------------------------------------------------
+
+
+/*----------------------------------------------------------------------
+* Name:    ibmphp_hpc_initvars
+*
+* Action:  initialize semaphores and variables
+*---------------------------------------------------------------------*/
+void __init ibmphp_hpc_initvars (void)
+{
+	debug ("%s - Entry\n", __func__);
+
+	mutex_init(&sem_hpcaccess);
+	sema_init(&semOperations, 1);
+	sema_init(&sem_exit, 0);
+	to_debug = 0;
+
+	debug ("%s - Exit\n", __func__);
+}
+
+/*----------------------------------------------------------------------
+* Name:    i2c_ctrl_read
+*
+* Action:  read from HPC over I2C
+*
+*---------------------------------------------------------------------*/
+static u8 i2c_ctrl_read (struct controller *ctlr_ptr, void __iomem *WPGBbar, u8 index)
+{
+	u8 status;
+	int i;
+	void __iomem *wpg_addr;	// base addr + offset
+	unsigned long wpg_data;	// data to/from WPG LOHI format
+	unsigned long ultemp;
+	unsigned long data;	// actual data HILO format
+
+	debug_polling ("%s - Entry WPGBbar[%p] index[%x] \n", __func__, WPGBbar, index);
+
+	//--------------------------------------------------------------------
+	// READ - step 1
+	// read at address, byte length, I2C address (shifted), index
+	// or read direct, byte length, index
+	if (ctlr_ptr->ctlr_type == 0x02) {
+		data = WPG_READATADDR_MASK;
+		// fill in I2C address
+		ultemp = (unsigned long)ctlr_ptr->u.wpeg_ctlr.i2c_addr;
+		ultemp = ultemp >> 1;
+		data |= (ultemp << 8);
+
+		// fill in index
+		data |= (unsigned long)index;
+	} else if (ctlr_ptr->ctlr_type == 0x04) {
+		data = WPG_READDIRECT_MASK;
+
+		// fill in index
+		ultemp = (unsigned long)index;
+		ultemp = ultemp << 8;
+		data |= ultemp;
+	} else {
+		err ("this controller type is not supported \n");
+		return HPC_ERROR;
+	}
+
+	wpg_data = swab32 (data);	// swap data before writing
+	wpg_addr = WPGBbar + WPG_I2CMOSUP_OFFSET;
+	writel (wpg_data, wpg_addr);
+
+	//--------------------------------------------------------------------
+	// READ - step 2 : clear the message buffer
+	data = 0x00000000;
+	wpg_data = swab32 (data);
+	wpg_addr = WPGBbar + WPG_I2CMBUFL_OFFSET;
+	writel (wpg_data, wpg_addr);
+
+	//--------------------------------------------------------------------
+	// READ - step 3 : issue start operation, I2C master control bit 30:ON
+	//                 2020 : [20] OR operation at [20] offset 0x20
+	data = WPG_I2CMCNTL_STARTOP_MASK;
+	wpg_data = swab32 (data);
+	wpg_addr = WPGBbar + WPG_I2CMCNTL_OFFSET + WPG_I2C_OR;
+	writel (wpg_data, wpg_addr);
+
+	//--------------------------------------------------------------------
+	// READ - step 4 : wait until start operation bit clears
+	i = CMD_COMPLETE_TOUT_SEC;
+	while (i) {
+		msleep(10);
+		wpg_addr = WPGBbar + WPG_I2CMCNTL_OFFSET;
+		wpg_data = readl (wpg_addr);
+		data = swab32 (wpg_data);
+		if (!(data & WPG_I2CMCNTL_STARTOP_MASK))
+			break;
+		i--;
+	}
+	if (i == 0) {
+		debug ("%s - Error : WPG timeout\n", __func__);
+		return HPC_ERROR;
+	}
+	//--------------------------------------------------------------------
+	// READ - step 5 : read I2C status register
+	i = CMD_COMPLETE_TOUT_SEC;
+	while (i) {
+		msleep(10);
+		wpg_addr = WPGBbar + WPG_I2CSTAT_OFFSET;
+		wpg_data = readl (wpg_addr);
+		data = swab32 (wpg_data);
+		if (HPC_I2CSTATUS_CHECK (data))
+			break;
+		i--;
+	}
+	if (i == 0) {
+		debug ("ctrl_read - Exit Error:I2C timeout\n");
+		return HPC_ERROR;
+	}
+
+	//--------------------------------------------------------------------
+	// READ - step 6 : get DATA
+	wpg_addr = WPGBbar + WPG_I2CMBUFL_OFFSET;
+	wpg_data = readl (wpg_addr);
+	data = swab32 (wpg_data);
+
+	status = (u8) data;
+
+	debug_polling ("%s - Exit index[%x] status[%x]\n", __func__, index, status);
+
+	return (status);
+}
+
+/*----------------------------------------------------------------------
+* Name:    i2c_ctrl_write
+*
+* Action:  write to HPC over I2C
+*
+* Return   0 or error codes
+*---------------------------------------------------------------------*/
+static u8 i2c_ctrl_write (struct controller *ctlr_ptr, void __iomem *WPGBbar, u8 index, u8 cmd)
+{
+	u8 rc;
+	void __iomem *wpg_addr;	// base addr + offset
+	unsigned long wpg_data;	// data to/from WPG LOHI format 
+	unsigned long ultemp;
+	unsigned long data;	// actual data HILO format
+	int i;
+
+	debug_polling ("%s - Entry WPGBbar[%p] index[%x] cmd[%x]\n", __func__, WPGBbar, index, cmd);
+
+	rc = 0;
+	//--------------------------------------------------------------------
+	// WRITE - step 1
+	// write at address, byte length, I2C address (shifted), index
+	// or write direct, byte length, index
+	data = 0x00000000;
+
+	if (ctlr_ptr->ctlr_type == 0x02) {
+		data = WPG_WRITEATADDR_MASK;
+		// fill in I2C address
+		ultemp = (unsigned long)ctlr_ptr->u.wpeg_ctlr.i2c_addr;
+		ultemp = ultemp >> 1;
+		data |= (ultemp << 8);
+
+		// fill in index
+		data |= (unsigned long)index;
+	} else if (ctlr_ptr->ctlr_type == 0x04) {
+		data = WPG_WRITEDIRECT_MASK;
+
+		// fill in index
+		ultemp = (unsigned long)index;
+		ultemp = ultemp << 8;
+		data |= ultemp;
+	} else {
+		err ("this controller type is not supported \n");
+		return HPC_ERROR;
+	}
+
+	wpg_data = swab32 (data);	// swap data before writing
+	wpg_addr = WPGBbar + WPG_I2CMOSUP_OFFSET;
+	writel (wpg_data, wpg_addr);
+
+	//--------------------------------------------------------------------
+	// WRITE - step 2 : clear the message buffer
+	data = 0x00000000 | (unsigned long)cmd;
+	wpg_data = swab32 (data);
+	wpg_addr = WPGBbar + WPG_I2CMBUFL_OFFSET;
+	writel (wpg_data, wpg_addr);
+
+	//--------------------------------------------------------------------
+	// WRITE - step 3 : issue start operation,I2C master control bit 30:ON
+	//                 2020 : [20] OR operation at [20] offset 0x20
+	data = WPG_I2CMCNTL_STARTOP_MASK;
+	wpg_data = swab32 (data);
+	wpg_addr = WPGBbar + WPG_I2CMCNTL_OFFSET + WPG_I2C_OR;
+	writel (wpg_data, wpg_addr);
+
+	//--------------------------------------------------------------------
+	// WRITE - step 4 : wait until start operation bit clears
+	i = CMD_COMPLETE_TOUT_SEC;
+	while (i) {
+		msleep(10);
+		wpg_addr = WPGBbar + WPG_I2CMCNTL_OFFSET;
+		wpg_data = readl (wpg_addr);
+		data = swab32 (wpg_data);
+		if (!(data & WPG_I2CMCNTL_STARTOP_MASK))
+			break;
+		i--;
+	}
+	if (i == 0) {
+		debug ("%s - Exit Error:WPG timeout\n", __func__);
+		rc = HPC_ERROR;
+	}
+
+	//--------------------------------------------------------------------
+	// WRITE - step 5 : read I2C status register
+	i = CMD_COMPLETE_TOUT_SEC;
+	while (i) {
+		msleep(10);
+		wpg_addr = WPGBbar + WPG_I2CSTAT_OFFSET;
+		wpg_data = readl (wpg_addr);
+		data = swab32 (wpg_data);
+		if (HPC_I2CSTATUS_CHECK (data))
+			break;
+		i--;
+	}
+	if (i == 0) {
+		debug ("ctrl_read - Error : I2C timeout\n");
+		rc = HPC_ERROR;
+	}
+
+	debug_polling ("%s Exit rc[%x]\n", __func__, rc);
+	return (rc);
+}
+
+//------------------------------------------------------------
+//  Read from ISA type HPC 
+//------------------------------------------------------------
+static u8 isa_ctrl_read (struct controller *ctlr_ptr, u8 offset)
+{
+	u16 start_address;
+	u16 end_address;
+	u8 data;
+
+	start_address = ctlr_ptr->u.isa_ctlr.io_start;
+	end_address = ctlr_ptr->u.isa_ctlr.io_end;
+	data = inb (start_address + offset);
+	return data;
+}
+
+//--------------------------------------------------------------
+// Write to ISA type HPC
+//--------------------------------------------------------------
+static void isa_ctrl_write (struct controller *ctlr_ptr, u8 offset, u8 data)
+{
+	u16 start_address;
+	u16 port_address;
+	
+	start_address = ctlr_ptr->u.isa_ctlr.io_start;
+	port_address = start_address + (u16) offset;
+	outb (data, port_address);
+}
+
+static u8 pci_ctrl_read (struct controller *ctrl, u8 offset)
+{
+	u8 data = 0x00;
+	debug ("inside pci_ctrl_read\n");
+	if (ctrl->ctrl_dev)
+		pci_read_config_byte (ctrl->ctrl_dev, HPC_PCI_OFFSET + offset, &data);
+	return data;
+}
+
+static u8 pci_ctrl_write (struct controller *ctrl, u8 offset, u8 data)
+{
+	u8 rc = -ENODEV;
+	debug ("inside pci_ctrl_write\n");
+	if (ctrl->ctrl_dev) {
+		pci_write_config_byte (ctrl->ctrl_dev, HPC_PCI_OFFSET + offset, data);
+		rc = 0;
+	}
+	return rc;
+}
+
+static u8 ctrl_read (struct controller *ctlr, void __iomem *base, u8 offset)
+{
+	u8 rc;
+	switch (ctlr->ctlr_type) {
+	case 0:
+		rc = isa_ctrl_read (ctlr, offset);
+		break;
+	case 1:
+		rc = pci_ctrl_read (ctlr, offset);
+		break;
+	case 2:
+	case 4:
+		rc = i2c_ctrl_read (ctlr, base, offset);
+		break;
+	default:
+		return -ENODEV;
+	}
+	return rc;
+}
+
+static u8 ctrl_write (struct controller *ctlr, void __iomem *base, u8 offset, u8 data)
+{
+	u8 rc = 0;
+	switch (ctlr->ctlr_type) {
+	case 0:
+		isa_ctrl_write(ctlr, offset, data);
+		break;
+	case 1:
+		rc = pci_ctrl_write (ctlr, offset, data);
+		break;
+	case 2:
+	case 4:
+		rc = i2c_ctrl_write(ctlr, base, offset, data);
+		break;
+	default:
+		return -ENODEV;
+	}
+	return rc;
+}
+/*----------------------------------------------------------------------
+* Name:    hpc_writecmdtoindex()
+*
+* Action:  convert a write command to proper index within a controller
+*
+* Return   index, HPC_ERROR
+*---------------------------------------------------------------------*/
+static u8 hpc_writecmdtoindex (u8 cmd, u8 index)
+{
+	u8 rc;
+
+	switch (cmd) {
+	case HPC_CTLR_ENABLEIRQ:	// 0x00.N.15
+	case HPC_CTLR_CLEARIRQ:	// 0x06.N.15
+	case HPC_CTLR_RESET:	// 0x07.N.15
+	case HPC_CTLR_IRQSTEER:	// 0x08.N.15
+	case HPC_CTLR_DISABLEIRQ:	// 0x01.N.15
+	case HPC_ALLSLOT_ON:	// 0x11.N.15
+	case HPC_ALLSLOT_OFF:	// 0x12.N.15
+		rc = 0x0F;
+		break;
+
+	case HPC_SLOT_OFF:	// 0x02.Y.0-14
+	case HPC_SLOT_ON:	// 0x03.Y.0-14
+	case HPC_SLOT_ATTNOFF:	// 0x04.N.0-14
+	case HPC_SLOT_ATTNON:	// 0x05.N.0-14
+	case HPC_SLOT_BLINKLED:	// 0x13.N.0-14
+		rc = index;
+		break;
+
+	case HPC_BUS_33CONVMODE:
+	case HPC_BUS_66CONVMODE:
+	case HPC_BUS_66PCIXMODE:
+	case HPC_BUS_100PCIXMODE:
+	case HPC_BUS_133PCIXMODE:
+		rc = index + WPG_1ST_BUS_INDEX - 1;
+		break;
+
+	default:
+		err ("hpc_writecmdtoindex - Error invalid cmd[%x]\n", cmd);
+		rc = HPC_ERROR;
+	}
+
+	return rc;
+}
+
+/*----------------------------------------------------------------------
+* Name:    hpc_readcmdtoindex()
+*
+* Action:  convert a read command to proper index within a controller
+*
+* Return   index, HPC_ERROR
+*---------------------------------------------------------------------*/
+static u8 hpc_readcmdtoindex (u8 cmd, u8 index)
+{
+	u8 rc;
+
+	switch (cmd) {
+	case READ_CTLRSTATUS:
+		rc = 0x0F;
+		break;
+	case READ_SLOTSTATUS:
+	case READ_ALLSTAT:
+		rc = index;
+		break;
+	case READ_EXTSLOTSTATUS:
+		rc = index + WPG_1ST_EXTSLOT_INDEX;
+		break;
+	case READ_BUSSTATUS:
+		rc = index + WPG_1ST_BUS_INDEX - 1;
+		break;
+	case READ_SLOTLATCHLOWREG:
+		rc = 0x28;
+		break;
+	case READ_REVLEVEL:
+		rc = 0x25;
+		break;
+	case READ_HPCOPTIONS:
+		rc = 0x27;
+		break;
+	default:
+		rc = HPC_ERROR;
+	}
+	return rc;
+}
+
+/*----------------------------------------------------------------------
+* Name:    HPCreadslot()
+*
+* Action:  issue a READ command to HPC
+*
+* Input:   pslot   - cannot be NULL for READ_ALLSTAT
+*          pstatus - can be NULL for READ_ALLSTAT
+*
+* Return   0 or error codes
+*---------------------------------------------------------------------*/
+int ibmphp_hpc_readslot (struct slot * pslot, u8 cmd, u8 * pstatus)
+{
+	void __iomem *wpg_bbar = NULL;
+	struct controller *ctlr_ptr;
+	struct list_head *pslotlist;
+	u8 index, status;
+	int rc = 0;
+	int busindex;
+
+	debug_polling ("%s - Entry pslot[%p] cmd[%x] pstatus[%p]\n", __func__, pslot, cmd, pstatus);
+
+	if ((pslot == NULL)
+	    || ((pstatus == NULL) && (cmd != READ_ALLSTAT) && (cmd != READ_BUSSTATUS))) {
+		rc = -EINVAL;
+		err ("%s - Error invalid pointer, rc[%d]\n", __func__, rc);
+		return rc;
+	}
+
+	if (cmd == READ_BUSSTATUS) {
+		busindex = ibmphp_get_bus_index (pslot->bus);
+		if (busindex < 0) {
+			rc = -EINVAL;
+			err ("%s - Exit Error:invalid bus, rc[%d]\n", __func__, rc);
+			return rc;
+		} else
+			index = (u8) busindex;
+	} else
+		index = pslot->ctlr_index;
+
+	index = hpc_readcmdtoindex (cmd, index);
+
+	if (index == HPC_ERROR) {
+		rc = -EINVAL;
+		err ("%s - Exit Error:invalid index, rc[%d]\n", __func__, rc);
+		return rc;
+	}
+
+	ctlr_ptr = pslot->ctrl;
+
+	get_hpc_access ();
+
+	//--------------------------------------------------------------------
+	// map physical address to logical address
+	//--------------------------------------------------------------------
+	if ((ctlr_ptr->ctlr_type == 2) || (ctlr_ptr->ctlr_type == 4))
+		wpg_bbar = ioremap (ctlr_ptr->u.wpeg_ctlr.wpegbbar, WPG_I2C_IOREMAP_SIZE);
+
+	//--------------------------------------------------------------------
+	// check controller status before reading
+	//--------------------------------------------------------------------
+	rc = hpc_wait_ctlr_notworking (HPC_CTLR_WORKING_TOUT, ctlr_ptr, wpg_bbar, &status);
+	if (!rc) {
+		switch (cmd) {
+		case READ_ALLSTAT:
+			// update the slot structure
+			pslot->ctrl->status = status;
+			pslot->status = ctrl_read (ctlr_ptr, wpg_bbar, index);
+			rc = hpc_wait_ctlr_notworking (HPC_CTLR_WORKING_TOUT, ctlr_ptr, wpg_bbar,
+						       &status);
+			if (!rc)
+				pslot->ext_status = ctrl_read (ctlr_ptr, wpg_bbar, index + WPG_1ST_EXTSLOT_INDEX);
+
+			break;
+
+		case READ_SLOTSTATUS:
+			// DO NOT update the slot structure
+			*pstatus = ctrl_read (ctlr_ptr, wpg_bbar, index);
+			break;
+
+		case READ_EXTSLOTSTATUS:
+			// DO NOT update the slot structure
+			*pstatus = ctrl_read (ctlr_ptr, wpg_bbar, index);
+			break;
+
+		case READ_CTLRSTATUS:
+			// DO NOT update the slot structure
+			*pstatus = status;
+			break;
+
+		case READ_BUSSTATUS:
+			pslot->busstatus = ctrl_read (ctlr_ptr, wpg_bbar, index);
+			break;
+		case READ_REVLEVEL:
+			*pstatus = ctrl_read (ctlr_ptr, wpg_bbar, index);
+			break;
+		case READ_HPCOPTIONS:
+			*pstatus = ctrl_read (ctlr_ptr, wpg_bbar, index);
+			break;
+		case READ_SLOTLATCHLOWREG:
+			// DO NOT update the slot structure
+			*pstatus = ctrl_read (ctlr_ptr, wpg_bbar, index);
+			break;
+
+			// Not used
+		case READ_ALLSLOT:
+			list_for_each (pslotlist, &ibmphp_slot_head) {
+				pslot = list_entry (pslotlist, struct slot, ibm_slot_list);
+				index = pslot->ctlr_index;
+				rc = hpc_wait_ctlr_notworking (HPC_CTLR_WORKING_TOUT, ctlr_ptr,
+								wpg_bbar, &status);
+				if (!rc) {
+					pslot->status = ctrl_read (ctlr_ptr, wpg_bbar, index);
+					rc = hpc_wait_ctlr_notworking (HPC_CTLR_WORKING_TOUT,
+									ctlr_ptr, wpg_bbar, &status);
+					if (!rc)
+						pslot->ext_status =
+						    ctrl_read (ctlr_ptr, wpg_bbar,
+								index + WPG_1ST_EXTSLOT_INDEX);
+				} else {
+					err ("%s - Error ctrl_read failed\n", __func__);
+					rc = -EINVAL;
+					break;
+				}
+			}
+			break;
+		default:
+			rc = -EINVAL;
+			break;
+		}
+	}
+	//--------------------------------------------------------------------
+	// cleanup
+	//--------------------------------------------------------------------
+	
+	// remove physical to logical address mapping
+	if ((ctlr_ptr->ctlr_type == 2) || (ctlr_ptr->ctlr_type == 4))
+		iounmap (wpg_bbar);
+	
+	free_hpc_access ();
+
+	debug_polling ("%s - Exit rc[%d]\n", __func__, rc);
+	return rc;
+}
+
+/*----------------------------------------------------------------------
+* Name:    ibmphp_hpc_writeslot()
+*
+* Action: issue a WRITE command to HPC
+*---------------------------------------------------------------------*/
+int ibmphp_hpc_writeslot (struct slot * pslot, u8 cmd)
+{
+	void __iomem *wpg_bbar = NULL;
+	struct controller *ctlr_ptr;
+	u8 index, status;
+	int busindex;
+	u8 done;
+	int rc = 0;
+	int timeout;
+
+	debug_polling ("%s - Entry pslot[%p] cmd[%x]\n", __func__, pslot, cmd);
+	if (pslot == NULL) {
+		rc = -EINVAL;
+		err ("%s - Error Exit rc[%d]\n", __func__, rc);
+		return rc;
+	}
+
+	if ((cmd == HPC_BUS_33CONVMODE) || (cmd == HPC_BUS_66CONVMODE) ||
+		(cmd == HPC_BUS_66PCIXMODE) || (cmd == HPC_BUS_100PCIXMODE) ||
+		(cmd == HPC_BUS_133PCIXMODE)) {
+		busindex = ibmphp_get_bus_index (pslot->bus);
+		if (busindex < 0) {
+			rc = -EINVAL;
+			err ("%s - Exit Error:invalid bus, rc[%d]\n", __func__, rc);
+			return rc;
+		} else
+			index = (u8) busindex;
+	} else
+		index = pslot->ctlr_index;
+
+	index = hpc_writecmdtoindex (cmd, index);
+
+	if (index == HPC_ERROR) {
+		rc = -EINVAL;
+		err ("%s - Error Exit rc[%d]\n", __func__, rc);
+		return rc;
+	}
+
+	ctlr_ptr = pslot->ctrl;
+
+	get_hpc_access ();
+
+	//--------------------------------------------------------------------
+	// map physical address to logical address
+	//--------------------------------------------------------------------
+	if ((ctlr_ptr->ctlr_type == 2) || (ctlr_ptr->ctlr_type == 4)) {
+		wpg_bbar = ioremap (ctlr_ptr->u.wpeg_ctlr.wpegbbar, WPG_I2C_IOREMAP_SIZE);
+
+		debug ("%s - ctlr id[%x] physical[%lx] logical[%lx] i2c[%x]\n", __func__,
+		ctlr_ptr->ctlr_id, (ulong) (ctlr_ptr->u.wpeg_ctlr.wpegbbar), (ulong) wpg_bbar,
+		ctlr_ptr->u.wpeg_ctlr.i2c_addr);
+	}
+	//--------------------------------------------------------------------
+	// check controller status before writing
+	//--------------------------------------------------------------------
+	rc = hpc_wait_ctlr_notworking (HPC_CTLR_WORKING_TOUT, ctlr_ptr, wpg_bbar, &status);
+	if (!rc) {
+
+		ctrl_write (ctlr_ptr, wpg_bbar, index, cmd);
+
+		//--------------------------------------------------------------------
+		// check controller is still not working on the command
+		//--------------------------------------------------------------------
+		timeout = CMD_COMPLETE_TOUT_SEC;
+		done = 0;
+		while (!done) {
+			rc = hpc_wait_ctlr_notworking (HPC_CTLR_WORKING_TOUT, ctlr_ptr, wpg_bbar,
+							&status);
+			if (!rc) {
+				if (NEEDTOCHECK_CMDSTATUS (cmd)) {
+					if (CTLR_FINISHED (status) == HPC_CTLR_FINISHED_YES)
+						done = 1;
+				} else
+					done = 1;
+			}
+			if (!done) {
+				msleep(1000);
+				if (timeout < 1) {
+					done = 1;
+					err ("%s - Error command complete timeout\n", __func__);
+					rc = -EFAULT;
+				} else
+					timeout--;
+			}
+		}
+		ctlr_ptr->status = status;
+	}
+	// cleanup
+
+	// remove physical to logical address mapping
+	if ((ctlr_ptr->ctlr_type == 2) || (ctlr_ptr->ctlr_type == 4))
+		iounmap (wpg_bbar);
+	free_hpc_access ();
+
+	debug_polling ("%s - Exit rc[%d]\n", __func__, rc);
+	return rc;
+}
+
+/*----------------------------------------------------------------------
+* Name:    get_hpc_access()
+*
+* Action: make sure only one process can access HPC at one time
+*---------------------------------------------------------------------*/
+static void get_hpc_access (void)
+{
+	mutex_lock(&sem_hpcaccess);
+}
+
+/*----------------------------------------------------------------------
+* Name:    free_hpc_access()
+*---------------------------------------------------------------------*/
+void free_hpc_access (void)
+{
+	mutex_unlock(&sem_hpcaccess);
+}
+
+/*----------------------------------------------------------------------
+* Name:    ibmphp_lock_operations()
+*
+* Action: make sure only one process can change the data structure
+*---------------------------------------------------------------------*/
+void ibmphp_lock_operations (void)
+{
+	down (&semOperations);
+	to_debug = 1;
+}
+
+/*----------------------------------------------------------------------
+* Name:    ibmphp_unlock_operations()
+*---------------------------------------------------------------------*/
+void ibmphp_unlock_operations (void)
+{
+	debug ("%s - Entry\n", __func__);
+	up (&semOperations);
+	to_debug = 0;
+	debug ("%s - Exit\n", __func__);
+}
+
+/*----------------------------------------------------------------------
+* Name:    poll_hpc()
+*---------------------------------------------------------------------*/
+#define POLL_LATCH_REGISTER	0
+#define POLL_SLOTS		1
+#define POLL_SLEEP		2
+static int poll_hpc(void *data)
+{
+	struct slot myslot;
+	struct slot *pslot = NULL;
+	struct list_head *pslotlist;
+	int rc;
+	int poll_state = POLL_LATCH_REGISTER;
+	u8 oldlatchlow = 0x00;
+	u8 curlatchlow = 0x00;
+	int poll_count = 0;
+	u8 ctrl_count = 0x00;
+
+	debug ("%s - Entry\n", __func__);
+
+	while (!kthread_should_stop()) {
+		/* try to get the lock to do some kind of hardware access */
+		down (&semOperations);
+
+		switch (poll_state) {
+		case POLL_LATCH_REGISTER: 
+			oldlatchlow = curlatchlow;
+			ctrl_count = 0x00;
+			list_for_each (pslotlist, &ibmphp_slot_head) {
+				if (ctrl_count >= ibmphp_get_total_controllers())
+					break;
+				pslot = list_entry (pslotlist, struct slot, ibm_slot_list);
+				if (pslot->ctrl->ctlr_relative_id == ctrl_count) {
+					ctrl_count++;
+					if (READ_SLOT_LATCH (pslot->ctrl)) {
+						rc = ibmphp_hpc_readslot (pslot,
+									  READ_SLOTLATCHLOWREG,
+									  &curlatchlow);
+						if (oldlatchlow != curlatchlow)
+							process_changeinlatch (oldlatchlow,
+									       curlatchlow,
+									       pslot->ctrl);
+					}
+				}
+			}
+			++poll_count;
+			poll_state = POLL_SLEEP;
+			break;
+		case POLL_SLOTS:
+			list_for_each (pslotlist, &ibmphp_slot_head) {
+				pslot = list_entry (pslotlist, struct slot, ibm_slot_list);
+				// make a copy of the old status
+				memcpy ((void *) &myslot, (void *) pslot,
+					sizeof (struct slot));
+				rc = ibmphp_hpc_readslot (pslot, READ_ALLSTAT, NULL);
+				if ((myslot.status != pslot->status)
+				    || (myslot.ext_status != pslot->ext_status))
+					process_changeinstatus (pslot, &myslot);
+			}
+			ctrl_count = 0x00;
+			list_for_each (pslotlist, &ibmphp_slot_head) {
+				if (ctrl_count >= ibmphp_get_total_controllers())
+					break;
+				pslot = list_entry (pslotlist, struct slot, ibm_slot_list);
+				if (pslot->ctrl->ctlr_relative_id == ctrl_count) {
+					ctrl_count++;
+					if (READ_SLOT_LATCH (pslot->ctrl))
+						rc = ibmphp_hpc_readslot (pslot,
+									  READ_SLOTLATCHLOWREG,
+									  &curlatchlow);
+				}
+			}
+			++poll_count;
+			poll_state = POLL_SLEEP;
+			break;
+		case POLL_SLEEP:
+			/* don't sleep with a lock on the hardware */
+			up (&semOperations);
+			msleep(POLL_INTERVAL_SEC * 1000);
+
+			if (kthread_should_stop())
+				goto out_sleep;
+			
+			down (&semOperations);
+			
+			if (poll_count >= POLL_LATCH_CNT) {
+				poll_count = 0;
+				poll_state = POLL_SLOTS;
+			} else
+				poll_state = POLL_LATCH_REGISTER;
+			break;
+		}	
+		/* give up the hardware semaphore */
+		up (&semOperations);
+		/* sleep for a short time just for good measure */
+out_sleep:
+		msleep(100);
+	}
+	up (&sem_exit);
+	debug ("%s - Exit\n", __func__);
+	return 0;
+}
+
+
+/*----------------------------------------------------------------------
+* Name:    process_changeinstatus
+*
+* Action:  compare old and new slot status, process the change in status
+*
+* Input:   pointer to slot struct, old slot struct
+*
+* Return   0 or error codes
+* Value:
+*
+* Side
+* Effects: None.
+*
+* Notes:
+*---------------------------------------------------------------------*/
+static int process_changeinstatus (struct slot *pslot, struct slot *poldslot)
+{
+	u8 status;
+	int rc = 0;
+	u8 disable = 0;
+	u8 update = 0;
+
+	debug ("process_changeinstatus - Entry pslot[%p], poldslot[%p]\n", pslot, poldslot);
+
+	// bit 0 - HPC_SLOT_POWER
+	if ((pslot->status & 0x01) != (poldslot->status & 0x01))
+		update = 1;
+
+	// bit 1 - HPC_SLOT_CONNECT
+	// ignore
+
+	// bit 2 - HPC_SLOT_ATTN
+	if ((pslot->status & 0x04) != (poldslot->status & 0x04))
+		update = 1;
+
+	// bit 3 - HPC_SLOT_PRSNT2
+	// bit 4 - HPC_SLOT_PRSNT1
+	if (((pslot->status & 0x08) != (poldslot->status & 0x08))
+		|| ((pslot->status & 0x10) != (poldslot->status & 0x10)))
+		update = 1;
+
+	// bit 5 - HPC_SLOT_PWRGD
+	if ((pslot->status & 0x20) != (poldslot->status & 0x20))
+		// OFF -> ON: ignore, ON -> OFF: disable slot
+		if ((poldslot->status & 0x20) && (SLOT_CONNECT (poldslot->status) == HPC_SLOT_CONNECTED) && (SLOT_PRESENT (poldslot->status))) 
+			disable = 1;
+
+	// bit 6 - HPC_SLOT_BUS_SPEED
+	// ignore
+
+	// bit 7 - HPC_SLOT_LATCH
+	if ((pslot->status & 0x80) != (poldslot->status & 0x80)) {
+		update = 1;
+		// OPEN -> CLOSE
+		if (pslot->status & 0x80) {
+			if (SLOT_PWRGD (pslot->status)) {
+				// power goes on and off after closing latch
+				// check again to make sure power is still ON
+				msleep(1000);
+				rc = ibmphp_hpc_readslot (pslot, READ_SLOTSTATUS, &status);
+				if (SLOT_PWRGD (status))
+					update = 1;
+				else	// overwrite power in pslot to OFF
+					pslot->status &= ~HPC_SLOT_POWER;
+			}
+		}
+		// CLOSE -> OPEN 
+		else if ((SLOT_PWRGD (poldslot->status) == HPC_SLOT_PWRGD_GOOD)
+			&& (SLOT_CONNECT (poldslot->status) == HPC_SLOT_CONNECTED) && (SLOT_PRESENT (poldslot->status))) {
+			disable = 1;
+		}
+		// else - ignore
+	}
+	// bit 4 - HPC_SLOT_BLINK_ATTN
+	if ((pslot->ext_status & 0x08) != (poldslot->ext_status & 0x08))
+		update = 1;
+
+	if (disable) {
+		debug ("process_changeinstatus - disable slot\n");
+		pslot->flag = 0;
+		rc = ibmphp_do_disable_slot (pslot);
+	}
+
+	if (update || disable) {
+		ibmphp_update_slot_info (pslot);
+	}
+
+	debug ("%s - Exit rc[%d] disable[%x] update[%x]\n", __func__, rc, disable, update);
+
+	return rc;
+}
+
+/*----------------------------------------------------------------------
+* Name:    process_changeinlatch
+*
+* Action:  compare old and new latch reg status, process the change
+*
+* Input:   old and current latch register status
+*
+* Return   0 or error codes
+* Value:
+*---------------------------------------------------------------------*/
+static int process_changeinlatch (u8 old, u8 new, struct controller *ctrl)
+{
+	struct slot myslot, *pslot;
+	u8 i;
+	u8 mask;
+	int rc = 0;
+
+	debug ("%s - Entry old[%x], new[%x]\n", __func__, old, new);
+	// bit 0 reserved, 0 is LSB, check bit 1-6 for 6 slots
+
+	for (i = ctrl->starting_slot_num; i <= ctrl->ending_slot_num; i++) {
+		mask = 0x01 << i;
+		if ((mask & old) != (mask & new)) {
+			pslot = ibmphp_get_slot_from_physical_num (i);
+			if (pslot) {
+				memcpy ((void *) &myslot, (void *) pslot, sizeof (struct slot));
+				rc = ibmphp_hpc_readslot (pslot, READ_ALLSTAT, NULL);
+				debug ("%s - call process_changeinstatus for slot[%d]\n", __func__, i);
+				process_changeinstatus (pslot, &myslot);
+			} else {
+				rc = -EINVAL;
+				err ("%s - Error bad pointer for slot[%d]\n", __func__, i);
+			}
+		}
+	}
+	debug ("%s - Exit rc[%d]\n", __func__, rc);
+	return rc;
+}
+
+/*----------------------------------------------------------------------
+* Name:    ibmphp_hpc_start_poll_thread
+*
+* Action:  start polling thread
+*---------------------------------------------------------------------*/
+int __init ibmphp_hpc_start_poll_thread (void)
+{
+	debug ("%s - Entry\n", __func__);
+
+	ibmphp_poll_thread = kthread_run(poll_hpc, NULL, "hpc_poll");
+	if (IS_ERR(ibmphp_poll_thread)) {
+		err ("%s - Error, thread not started\n", __func__);
+		return PTR_ERR(ibmphp_poll_thread);
+	}
+	return 0;
+}
+
+/*----------------------------------------------------------------------
+* Name:    ibmphp_hpc_stop_poll_thread
+*
+* Action:  stop polling thread and cleanup
+*---------------------------------------------------------------------*/
+void __exit ibmphp_hpc_stop_poll_thread (void)
+{
+	debug ("%s - Entry\n", __func__);
+
+	kthread_stop(ibmphp_poll_thread);
+	debug ("before locking operations \n");
+	ibmphp_lock_operations ();
+	debug ("after locking operations \n");
+	
+	// wait for poll thread to exit
+	debug ("before sem_exit down \n");
+	down (&sem_exit);
+	debug ("after sem_exit down \n");
+
+	// cleanup
+	debug ("before free_hpc_access \n");
+	free_hpc_access ();
+	debug ("after free_hpc_access \n");
+	ibmphp_unlock_operations ();
+	debug ("after unlock operations \n");
+	up (&sem_exit);
+	debug ("after sem exit up\n");
+
+	debug ("%s - Exit\n", __func__);
+}
+
+/*----------------------------------------------------------------------
+* Name:    hpc_wait_ctlr_notworking
+*
+* Action:  wait until the controller is in a not working state
+*
+* Return   0, HPC_ERROR
+* Value:
+*---------------------------------------------------------------------*/
+static int hpc_wait_ctlr_notworking (int timeout, struct controller *ctlr_ptr, void __iomem *wpg_bbar,
+				    u8 * pstatus)
+{
+	int rc = 0;
+	u8 done = 0;
+
+	debug_polling ("hpc_wait_ctlr_notworking - Entry timeout[%d]\n", timeout);
+
+	while (!done) {
+		*pstatus = ctrl_read (ctlr_ptr, wpg_bbar, WPG_CTLR_INDEX);
+		if (*pstatus == HPC_ERROR) {
+			rc = HPC_ERROR;
+			done = 1;
+		}
+		if (CTLR_WORKING (*pstatus) == HPC_CTLR_WORKING_NO)
+			done = 1;
+		if (!done) {
+			msleep(1000);
+			if (timeout < 1) {
+				done = 1;
+				err ("HPCreadslot - Error ctlr timeout\n");
+				rc = HPC_ERROR;
+			} else
+				timeout--;
+		}
+	}
+	debug_polling ("hpc_wait_ctlr_notworking - Exit rc[%x] status[%x]\n", rc, *pstatus);
+	return rc;
+}
diff --git a/drivers/pci/hotplug/ibmphp_pci.c b/drivers/pci/hotplug/ibmphp_pci.c
new file mode 100644
index 00000000..7b09e161
--- /dev/null
+++ b/drivers/pci/hotplug/ibmphp_pci.c
@@ -0,0 +1,1729 @@
+/*
+ * IBM Hot Plug Controller Driver
+ * 
+ * Written By: Irene Zubarev, IBM Corporation
+ * 
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001,2002 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <gregkh@us.ibm.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/list.h>
+#include "ibmphp.h"
+
+
+static int configure_device(struct pci_func *);
+static int configure_bridge(struct pci_func **, u8);
+static struct res_needed *scan_behind_bridge(struct pci_func *, u8);
+static int add_new_bus (struct bus_node *, struct resource_node *, struct resource_node *, struct resource_node *, u8);
+static u8 find_sec_number (u8 primary_busno, u8 slotno);
+
+/*
+ * NOTE..... If BIOS doesn't provide default routing, we assign:
+ * 9 for SCSI, 10 for LAN adapters, and 11 for everything else. 
+ * If adapter is bridged, then we assign 11 to it and devices behind it.
+ * We also assign the same irq numbers for multi function devices.
+ * These are PIC mode, so shouldn't matter n.e.ways (hopefully)
+ */
+static void assign_alt_irq (struct pci_func * cur_func, u8 class_code)
+{
+	int j;
+	for (j = 0; j < 4; j++) {
+		if (cur_func->irq[j] == 0xff) {
+			switch (class_code) {
+				case PCI_BASE_CLASS_STORAGE:
+					cur_func->irq[j] = SCSI_IRQ;
+					break;
+				case PCI_BASE_CLASS_NETWORK:
+					cur_func->irq[j] = LAN_IRQ;
+					break;
+				default:
+					cur_func->irq[j] = OTHER_IRQ;
+					break;
+			}
+		}
+	}
+}
+
+/*
+ * Configures the device to be added (will allocate needed resources if it
+ * can), the device can be a bridge or a regular pci device, can also be
+ * multi-functional
+ * 
+ * Input: function to be added
+ * 
+ * TO DO:  The error case with Multifunction device or multi function bridge,
+ * if there is an error, will need to go through all previous functions and 
+ * unconfigure....or can add some code into unconfigure_card....
+ */
+int ibmphp_configure_card (struct pci_func *func, u8 slotno)
+{
+	u16 vendor_id;
+	u32 class;
+	u8 class_code;
+	u8 hdr_type, device, sec_number;
+	u8 function;
+	struct pci_func *newfunc;	/* for multi devices */
+	struct pci_func *cur_func, *prev_func;
+	int rc, i, j;
+	int cleanup_count;
+	u8 flag;
+	u8 valid_device = 0x00; /* to see if we are able to read from card any device info at all */
+
+	debug ("inside configure_card, func->busno = %x\n", func->busno);
+
+	device = func->device;
+	cur_func = func;
+
+	/* We only get bus and device from IRQ routing table.  So at this point,
+	 * func->busno is correct, and func->device contains only device (at the 5 
+	 * highest bits)
+	 */
+
+	/* For every function on the card */
+	for (function = 0x00; function < 0x08; function++) {
+		unsigned int devfn = PCI_DEVFN(device, function);
+		ibmphp_pci_bus->number = cur_func->busno;
+
+		cur_func->function = function;
+
+		debug ("inside the loop, cur_func->busno = %x, cur_func->device = %x, cur_func->funcion = %x\n",
+			cur_func->busno, cur_func->device, cur_func->function);
+
+		pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_VENDOR_ID, &vendor_id);
+
+		debug ("vendor_id is %x\n", vendor_id);
+		if (vendor_id != PCI_VENDOR_ID_NOTVALID) {
+			/* found correct device!!! */
+			debug ("found valid device, vendor_id = %x\n", vendor_id);
+
+			++valid_device;
+
+			/* header: x x x x x x x x
+			 *         | |___________|=> 1=PPB bridge, 0=normal device, 2=CardBus Bridge
+			 *         |_=> 0 = single function device, 1 = multi-function device
+			 */
+
+			pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_HEADER_TYPE, &hdr_type);
+			pci_bus_read_config_dword (ibmphp_pci_bus, devfn, PCI_CLASS_REVISION, &class);
+
+			class_code = class >> 24;
+			debug ("hrd_type = %x, class = %x, class_code %x\n", hdr_type, class, class_code);
+			class >>= 8;	/* to take revision out, class = class.subclass.prog i/f */
+			if (class == PCI_CLASS_NOT_DEFINED_VGA) {
+				err ("The device %x is VGA compatible and as is not supported for hot plugging. "
+				     "Please choose another device.\n", cur_func->device);
+				return -ENODEV;
+			} else if (class == PCI_CLASS_DISPLAY_VGA) {
+				err ("The device %x is not supported for hot plugging. "
+				     "Please choose another device.\n", cur_func->device);
+				return -ENODEV;
+			}
+			switch (hdr_type) {
+				case PCI_HEADER_TYPE_NORMAL:
+					debug ("single device case.... vendor id = %x, hdr_type = %x, class = %x\n", vendor_id, hdr_type, class);
+					assign_alt_irq (cur_func, class_code);
+					if ((rc = configure_device (cur_func)) < 0) {
+						/* We need to do this in case some other BARs were properly inserted */
+						err ("was not able to configure devfunc %x on bus %x.\n",
+						     cur_func->device, cur_func->busno);
+						cleanup_count = 6;
+						goto error;
+					}	
+					cur_func->next = NULL;
+					function = 0x8;
+					break;
+				case PCI_HEADER_TYPE_MULTIDEVICE:
+					assign_alt_irq (cur_func, class_code);
+					if ((rc = configure_device (cur_func)) < 0) {
+						/* We need to do this in case some other BARs were properly inserted */
+						err ("was not able to configure devfunc %x on bus %x...bailing out\n",
+						     cur_func->device, cur_func->busno);
+						cleanup_count = 6;
+						goto error;
+					}
+					newfunc = kzalloc(sizeof(*newfunc), GFP_KERNEL);
+					if (!newfunc) {
+						err ("out of system memory\n");
+						return -ENOMEM;
+					}
+					newfunc->busno = cur_func->busno;
+					newfunc->device = device;
+					cur_func->next = newfunc;
+					cur_func = newfunc;
+					for (j = 0; j < 4; j++)
+						newfunc->irq[j] = cur_func->irq[j];
+					break;
+				case PCI_HEADER_TYPE_MULTIBRIDGE:
+					class >>= 8;
+					if (class != PCI_CLASS_BRIDGE_PCI) {
+						err ("This %x is not PCI-to-PCI bridge, and as is not supported for hot-plugging. "
+						     "Please insert another card.\n", cur_func->device);
+						return -ENODEV;
+					}
+					assign_alt_irq (cur_func, class_code);
+					rc = configure_bridge (&cur_func, slotno);
+					if (rc == -ENODEV) {
+						err ("You chose to insert Single Bridge, or nested bridges, this is not supported...\n");
+						err ("Bus %x, devfunc %x\n", cur_func->busno, cur_func->device);
+						return rc;
+					}
+					if (rc) {
+						/* We need to do this in case some other BARs were properly inserted */
+						err ("was not able to hot-add PPB properly.\n");
+						func->bus = 1; /* To indicate to the unconfigure function that this is a PPB */
+						cleanup_count = 2;
+						goto error;
+					}
+
+					pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_SECONDARY_BUS, &sec_number);
+					flag = 0;
+					for (i = 0; i < 32; i++) {
+						if (func->devices[i]) {
+							newfunc = kzalloc(sizeof(*newfunc), GFP_KERNEL);
+							if (!newfunc) {
+								err ("out of system memory\n");
+								return -ENOMEM;
+							}
+							newfunc->busno = sec_number;
+							newfunc->device = (u8) i;
+							for (j = 0; j < 4; j++)
+								newfunc->irq[j] = cur_func->irq[j];
+
+							if (flag) {
+								for (prev_func = cur_func; prev_func->next; prev_func = prev_func->next) ;
+								prev_func->next = newfunc;
+							} else
+								cur_func->next = newfunc;
+
+							rc = ibmphp_configure_card (newfunc, slotno);
+							/* This could only happen if kmalloc failed */
+							if (rc) {
+								/* We need to do this in case bridge itself got configured properly, but devices behind it failed */
+								func->bus = 1; /* To indicate to the unconfigure function that this is a PPB */
+								cleanup_count = 2;
+								goto error;
+							}
+							flag = 1;
+						}
+					}
+
+					newfunc = kzalloc(sizeof(*newfunc), GFP_KERNEL);
+					if (!newfunc) {
+						err ("out of system memory\n");
+						return -ENOMEM;
+					}
+					newfunc->busno = cur_func->busno;
+					newfunc->device = device;
+					for (j = 0; j < 4; j++)
+						newfunc->irq[j] = cur_func->irq[j];
+					for (prev_func = cur_func; prev_func->next; prev_func = prev_func->next) ;
+					prev_func->next = newfunc;
+					cur_func = newfunc;
+					break;
+				case PCI_HEADER_TYPE_BRIDGE:
+					class >>= 8;
+					debug ("class now is %x\n", class);
+					if (class != PCI_CLASS_BRIDGE_PCI) {
+						err ("This %x is not PCI-to-PCI bridge, and as is not supported for hot-plugging. "
+						     "Please insert another card.\n", cur_func->device);
+						return -ENODEV;
+					}
+
+					assign_alt_irq (cur_func, class_code);
+
+					debug ("cur_func->busno b4 configure_bridge is %x\n", cur_func->busno);
+					rc = configure_bridge (&cur_func, slotno);
+					if (rc == -ENODEV) {
+						err ("You chose to insert Single Bridge, or nested bridges, this is not supported...\n");
+						err ("Bus %x, devfunc %x\n", cur_func->busno, cur_func->device);
+						return rc;
+					}
+					if (rc) {
+						/* We need to do this in case some other BARs were properly inserted */
+						func->bus = 1; /* To indicate to the unconfigure function that this is a PPB */
+						err ("was not able to hot-add PPB properly.\n");
+						cleanup_count = 2;
+						goto error;
+					}
+					debug ("cur_func->busno = %x, device = %x, function = %x\n",
+						cur_func->busno, device, function);
+					pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_SECONDARY_BUS, &sec_number);
+					debug ("after configuring bridge..., sec_number = %x\n", sec_number);
+					flag = 0;
+					for (i = 0; i < 32; i++) {
+						if (func->devices[i]) {
+							debug ("inside for loop, device is %x\n", i);
+							newfunc = kzalloc(sizeof(*newfunc), GFP_KERNEL);
+							if (!newfunc) {
+								err (" out of system memory\n");
+								return -ENOMEM;
+							}
+							newfunc->busno = sec_number;
+							newfunc->device = (u8) i;
+							for (j = 0; j < 4; j++)
+								newfunc->irq[j] = cur_func->irq[j];
+
+							if (flag) {
+								for (prev_func = cur_func; prev_func->next; prev_func = prev_func->next) ;
+								prev_func->next = newfunc;
+							} else
+								cur_func->next = newfunc;
+
+							rc = ibmphp_configure_card (newfunc, slotno);
+
+							/* Again, this case should not happen... For complete paranoia, will need to call remove_bus */
+							if (rc) {
+								/* We need to do this in case some other BARs were properly inserted */
+								func->bus = 1; /* To indicate to the unconfigure function that this is a PPB */
+								cleanup_count = 2;
+								goto error;
+							}
+							flag = 1;
+						}
+					}
+
+					function = 0x8;
+					break;
+				default:
+					err ("MAJOR PROBLEM!!!!, header type not supported? %x\n", hdr_type);
+					return -ENXIO;
+					break;
+			}	/* end of switch */
+		}	/* end of valid device */
+	}	/* end of for */
+
+	if (!valid_device) {
+		err ("Cannot find any valid devices on the card.  Or unable to read from card.\n");
+		return -ENODEV;
+	}
+
+	return 0;
+
+error:
+	for (i = 0; i < cleanup_count; i++) {
+		if (cur_func->io[i]) {
+			ibmphp_remove_resource (cur_func->io[i]);
+			cur_func->io[i] = NULL;
+		} else if (cur_func->pfmem[i]) {
+			ibmphp_remove_resource (cur_func->pfmem[i]);
+			cur_func->pfmem[i] = NULL;
+		} else if (cur_func->mem[i]) {
+			ibmphp_remove_resource (cur_func->mem[i]);
+			cur_func->mem[i] = NULL;
+		}
+	}
+	return rc;
+}
+
+/*
+ * This function configures the pci BARs of a single device.  
+ * Input: pointer to the pci_func
+ * Output: configured PCI, 0, or error
+ */
+static int configure_device (struct pci_func *func)
+{
+	u32 bar[6];
+	u32 address[] = {
+		PCI_BASE_ADDRESS_0,
+		PCI_BASE_ADDRESS_1,
+		PCI_BASE_ADDRESS_2,
+		PCI_BASE_ADDRESS_3,
+		PCI_BASE_ADDRESS_4,
+		PCI_BASE_ADDRESS_5,
+		0
+	};
+	u8 irq;
+	int count;
+	int len[6];
+	struct resource_node *io[6];
+	struct resource_node *mem[6];
+	struct resource_node *mem_tmp;
+	struct resource_node *pfmem[6];
+	unsigned int devfn;
+
+	debug ("%s - inside\n", __func__);
+
+	devfn = PCI_DEVFN(func->device, func->function);
+	ibmphp_pci_bus->number = func->busno;
+
+	for (count = 0; address[count]; count++) {	/* for 6 BARs */
+
+		/* not sure if i need this.  per scott, said maybe need smth like this
+		   if devices don't adhere 100% to the spec, so don't want to write
+		   to the reserved bits
+
+		pcibios_read_config_byte(cur_func->busno, cur_func->device, 
+		PCI_BASE_ADDRESS_0 + 4 * count, &tmp);
+		if (tmp & 0x01) // IO
+			pcibios_write_config_dword(cur_func->busno, cur_func->device, 
+			PCI_BASE_ADDRESS_0 + 4 * count, 0xFFFFFFFD);
+		else  // Memory
+			pcibios_write_config_dword(cur_func->busno, cur_func->device, 
+			PCI_BASE_ADDRESS_0 + 4 * count, 0xFFFFFFFF);
+		 */
+		pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], 0xFFFFFFFF);
+		pci_bus_read_config_dword (ibmphp_pci_bus, devfn, address[count], &bar[count]);
+
+		if (!bar[count])	/* This BAR is not implemented */
+			continue;
+
+		debug ("Device %x BAR %d wants %x\n", func->device, count, bar[count]);
+
+		if (bar[count] & PCI_BASE_ADDRESS_SPACE_IO) {
+			/* This is IO */
+			debug ("inside IO SPACE\n");
+
+			len[count] = bar[count] & 0xFFFFFFFC;
+			len[count] = ~len[count] + 1;
+
+			debug ("len[count] in IO %x, count %d\n", len[count], count);
+
+			io[count] = kzalloc(sizeof(struct resource_node), GFP_KERNEL);
+
+			if (!io[count]) {
+				err ("out of system memory\n");
+				return -ENOMEM;
+			}
+			io[count]->type = IO;
+			io[count]->busno = func->busno;
+			io[count]->devfunc = PCI_DEVFN(func->device, func->function);
+			io[count]->len = len[count];
+			if (ibmphp_check_resource(io[count], 0) == 0) {
+				ibmphp_add_resource (io[count]);
+				func->io[count] = io[count];
+			} else {
+				err ("cannot allocate requested io for bus %x device %x function %x len %x\n",
+				     func->busno, func->device, func->function, len[count]);
+				kfree (io[count]);
+				return -EIO;
+			}
+			pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], func->io[count]->start);
+	
+			/* _______________This is for debugging purposes only_____________________ */ 
+			debug ("b4 writing, the IO address is %x\n", func->io[count]->start);
+			pci_bus_read_config_dword (ibmphp_pci_bus, devfn, address[count], &bar[count]);
+			debug ("after writing.... the start address is %x\n", bar[count]);
+			/* _________________________________________________________________________*/
+
+		} else {
+			/* This is Memory */
+			if (bar[count] & PCI_BASE_ADDRESS_MEM_PREFETCH) {
+				/* pfmem */
+				debug ("PFMEM SPACE\n");
+
+				len[count] = bar[count] & 0xFFFFFFF0;
+				len[count] = ~len[count] + 1;
+
+				debug ("len[count] in PFMEM %x, count %d\n", len[count], count);
+
+				pfmem[count] = kzalloc(sizeof(struct resource_node), GFP_KERNEL);
+				if (!pfmem[count]) {
+					err ("out of system memory\n");
+					return -ENOMEM;
+				}
+				pfmem[count]->type = PFMEM;
+				pfmem[count]->busno = func->busno;
+				pfmem[count]->devfunc = PCI_DEVFN(func->device,
+							func->function);
+				pfmem[count]->len = len[count];
+				pfmem[count]->fromMem = 0;
+				if (ibmphp_check_resource (pfmem[count], 0) == 0) {
+					ibmphp_add_resource (pfmem[count]);
+					func->pfmem[count] = pfmem[count];
+				} else {
+					mem_tmp = kzalloc(sizeof(*mem_tmp), GFP_KERNEL);
+					if (!mem_tmp) {
+						err ("out of system memory\n");
+						kfree (pfmem[count]);
+						return -ENOMEM;
+					}
+					mem_tmp->type = MEM;
+					mem_tmp->busno = pfmem[count]->busno;
+					mem_tmp->devfunc = pfmem[count]->devfunc;
+					mem_tmp->len = pfmem[count]->len;
+					debug ("there's no pfmem... going into mem.\n");
+					if (ibmphp_check_resource (mem_tmp, 0) == 0) {
+						ibmphp_add_resource (mem_tmp);
+						pfmem[count]->fromMem = 1;
+						pfmem[count]->rangeno = mem_tmp->rangeno;
+						pfmem[count]->start = mem_tmp->start;
+						pfmem[count]->end = mem_tmp->end;
+						ibmphp_add_pfmem_from_mem (pfmem[count]);
+						func->pfmem[count] = pfmem[count];
+					} else {
+						err ("cannot allocate requested pfmem for bus %x, device %x, len %x\n",
+						     func->busno, func->device, len[count]);
+						kfree (mem_tmp);
+						kfree (pfmem[count]);
+						return -EIO;
+					}
+				}
+
+				pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], func->pfmem[count]->start);
+
+				/*_______________This is for debugging purposes only______________________________*/				
+				debug ("b4 writing, start address is %x\n", func->pfmem[count]->start);
+				pci_bus_read_config_dword (ibmphp_pci_bus, devfn, address[count], &bar[count]);
+				debug ("after writing, start address is %x\n", bar[count]);
+				/*_________________________________________________________________________________*/
+
+				if (bar[count] & PCI_BASE_ADDRESS_MEM_TYPE_64) {	/* takes up another dword */
+					debug ("inside the mem 64 case, count %d\n", count);
+					count += 1;
+					/* on the 2nd dword, write all 0s, since we can't handle them n.e.ways */
+					pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], 0x00000000);
+				}
+			} else {
+				/* regular memory */
+				debug ("REGULAR MEM SPACE\n");
+
+				len[count] = bar[count] & 0xFFFFFFF0;
+				len[count] = ~len[count] + 1;
+
+				debug ("len[count] in Mem %x, count %d\n", len[count], count);
+
+				mem[count] = kzalloc(sizeof(struct resource_node), GFP_KERNEL);
+				if (!mem[count]) {
+					err ("out of system memory\n");
+					return -ENOMEM;
+				}
+				mem[count]->type = MEM;
+				mem[count]->busno = func->busno;
+				mem[count]->devfunc = PCI_DEVFN(func->device,
+							func->function);
+				mem[count]->len = len[count];
+				if (ibmphp_check_resource (mem[count], 0) == 0) {
+					ibmphp_add_resource (mem[count]);
+					func->mem[count] = mem[count];
+				} else {
+					err ("cannot allocate requested mem for bus %x, device %x, len %x\n",
+					     func->busno, func->device, len[count]);
+					kfree (mem[count]);
+					return -EIO;
+				}
+				pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], func->mem[count]->start);
+				/* _______________________This is for debugging purposes only _______________________*/
+				debug ("b4 writing, start address is %x\n", func->mem[count]->start);
+				pci_bus_read_config_dword (ibmphp_pci_bus, devfn, address[count], &bar[count]);
+				debug ("after writing, the address is %x\n", bar[count]);
+				/* __________________________________________________________________________________*/
+
+				if (bar[count] & PCI_BASE_ADDRESS_MEM_TYPE_64) {
+					/* takes up another dword */
+					debug ("inside mem 64 case, reg. mem, count %d\n", count);
+					count += 1;
+					/* on the 2nd dword, write all 0s, since we can't handle them n.e.ways */
+					pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], 0x00000000);
+				}
+			}
+		}		/* end of mem */
+	}			/* end of for */
+
+	func->bus = 0;		/* To indicate that this is not a PPB */
+	pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_INTERRUPT_PIN, &irq);
+	if ((irq > 0x00) && (irq < 0x05))
+		pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_INTERRUPT_LINE, func->irq[irq - 1]);
+
+	pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_CACHE_LINE_SIZE, CACHE);
+	pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_LATENCY_TIMER, LATENCY);
+
+	pci_bus_write_config_dword (ibmphp_pci_bus, devfn, PCI_ROM_ADDRESS, 0x00L);
+	pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_COMMAND, DEVICEENABLE);
+
+	return 0;
+}
+
+/******************************************************************************
+ * This routine configures a PCI-2-PCI bridge and the functions behind it
+ * Parameters: pci_func
+ * Returns: 
+ ******************************************************************************/
+static int configure_bridge (struct pci_func **func_passed, u8 slotno)
+{
+	int count;
+	int i;
+	int rc;
+	u8 sec_number;
+	u8 io_base;
+	u16 pfmem_base;
+	u32 bar[2];
+	u32 len[2];
+	u8 flag_io = 0;
+	u8 flag_mem = 0;
+	u8 flag_pfmem = 0;
+	u8 need_io_upper = 0;
+	u8 need_pfmem_upper = 0;
+	struct res_needed *amount_needed = NULL;
+	struct resource_node *io = NULL;
+	struct resource_node *bus_io[2] = {NULL, NULL};
+	struct resource_node *mem = NULL;
+	struct resource_node *bus_mem[2] = {NULL, NULL};
+	struct resource_node *mem_tmp = NULL;
+	struct resource_node *pfmem = NULL;
+	struct resource_node *bus_pfmem[2] = {NULL, NULL};
+	struct bus_node *bus;
+	u32 address[] = {
+		PCI_BASE_ADDRESS_0,
+		PCI_BASE_ADDRESS_1,
+		0
+	};
+	struct pci_func *func = *func_passed;
+	unsigned int devfn;
+	u8 irq;
+	int retval;
+
+	debug ("%s - enter\n", __func__);
+
+	devfn = PCI_DEVFN(func->function, func->device);
+	ibmphp_pci_bus->number = func->busno;
+
+	/* Configuring necessary info for the bridge so that we could see the devices
+	 * behind it
+	 */
+
+	pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_PRIMARY_BUS, func->busno);
+
+	/* _____________________For debugging purposes only __________________________
+	pci_bus_config_byte (ibmphp_pci_bus, devfn, PCI_PRIMARY_BUS, &pri_number);
+	debug ("primary # written into the bridge is %x\n", pri_number);
+	 ___________________________________________________________________________*/
+
+	/* in EBDA, only get allocated 1 additional bus # per slot */
+	sec_number = find_sec_number (func->busno, slotno);
+	if (sec_number == 0xff) {
+		err ("cannot allocate secondary bus number for the bridged device\n");
+		return -EINVAL;
+	}
+
+	debug ("after find_sec_number, the number we got is %x\n", sec_number);
+	debug ("AFTER FIND_SEC_NUMBER, func->busno IS %x\n", func->busno);
+
+	pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_SECONDARY_BUS, sec_number);
+	
+	/* __________________For debugging purposes only __________________________________
+	pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_SECONDARY_BUS, &sec_number);
+	debug ("sec_number after write/read is %x\n", sec_number);
+	 ________________________________________________________________________________*/
+
+	pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_SUBORDINATE_BUS, sec_number);
+
+	/* __________________For debugging purposes only ____________________________________
+	pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_SUBORDINATE_BUS, &sec_number);
+	debug ("subordinate number after write/read is %x\n", sec_number);
+	 __________________________________________________________________________________*/
+
+	pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_CACHE_LINE_SIZE, CACHE);
+	pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_LATENCY_TIMER, LATENCY);
+	pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_SEC_LATENCY_TIMER, LATENCY);
+
+	debug ("func->busno is %x\n", func->busno);
+	debug ("sec_number after writing is %x\n", sec_number);
+
+
+	/* !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
+	   !!!!!!!!!!!!!!!NEED TO ADD!!!  FAST BACK-TO-BACK ENABLE!!!!!!!!!!!!!!!!!!!! 
+	   !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!*/
+
+
+	/* First we need to allocate mem/io for the bridge itself in case it needs it */
+	for (count = 0; address[count]; count++) {	/* for 2 BARs */
+		pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], 0xFFFFFFFF);
+		pci_bus_read_config_dword (ibmphp_pci_bus, devfn, address[count], &bar[count]);
+
+		if (!bar[count]) {
+			/* This BAR is not implemented */
+			debug ("so we come here then, eh?, count = %d\n", count);
+			continue;
+		}
+		//  tmp_bar = bar[count];
+
+		debug ("Bar %d wants %x\n", count, bar[count]);
+
+		if (bar[count] & PCI_BASE_ADDRESS_SPACE_IO) {
+			/* This is IO */
+			len[count] = bar[count] & 0xFFFFFFFC;
+			len[count] = ~len[count] + 1;
+
+			debug ("len[count] in IO = %x\n", len[count]);
+
+			bus_io[count] = kzalloc(sizeof(struct resource_node), GFP_KERNEL);
+		
+			if (!bus_io[count]) {
+				err ("out of system memory\n");
+				retval = -ENOMEM;
+				goto error;
+			}
+			bus_io[count]->type = IO;
+			bus_io[count]->busno = func->busno;
+			bus_io[count]->devfunc = PCI_DEVFN(func->device,
+							func->function);
+			bus_io[count]->len = len[count];
+			if (ibmphp_check_resource (bus_io[count], 0) == 0) {
+				ibmphp_add_resource (bus_io[count]);
+				func->io[count] = bus_io[count];
+			} else {
+				err ("cannot allocate requested io for bus %x, device %x, len %x\n",
+				     func->busno, func->device, len[count]);
+				kfree (bus_io[count]);
+				return -EIO;
+			}
+
+			pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], func->io[count]->start);
+
+		} else {
+			/* This is Memory */
+			if (bar[count] & PCI_BASE_ADDRESS_MEM_PREFETCH) {
+				/* pfmem */
+				len[count] = bar[count] & 0xFFFFFFF0;
+				len[count] = ~len[count] + 1;
+
+				debug ("len[count] in PFMEM = %x\n", len[count]);
+
+				bus_pfmem[count] = kzalloc(sizeof(struct resource_node), GFP_KERNEL);
+				if (!bus_pfmem[count]) {
+					err ("out of system memory\n");
+					retval = -ENOMEM;
+					goto error;
+				}
+				bus_pfmem[count]->type = PFMEM;
+				bus_pfmem[count]->busno = func->busno;
+				bus_pfmem[count]->devfunc = PCI_DEVFN(func->device,
+							func->function);
+				bus_pfmem[count]->len = len[count];
+				bus_pfmem[count]->fromMem = 0;
+				if (ibmphp_check_resource (bus_pfmem[count], 0) == 0) {
+					ibmphp_add_resource (bus_pfmem[count]);
+					func->pfmem[count] = bus_pfmem[count];
+				} else {
+					mem_tmp = kzalloc(sizeof(*mem_tmp), GFP_KERNEL);
+					if (!mem_tmp) {
+						err ("out of system memory\n");
+						retval = -ENOMEM;
+						goto error;
+					}
+					mem_tmp->type = MEM;
+					mem_tmp->busno = bus_pfmem[count]->busno;
+					mem_tmp->devfunc = bus_pfmem[count]->devfunc;
+					mem_tmp->len = bus_pfmem[count]->len;
+					if (ibmphp_check_resource (mem_tmp, 0) == 0) {
+						ibmphp_add_resource (mem_tmp);
+						bus_pfmem[count]->fromMem = 1;
+						bus_pfmem[count]->rangeno = mem_tmp->rangeno;
+						ibmphp_add_pfmem_from_mem (bus_pfmem[count]);
+						func->pfmem[count] = bus_pfmem[count];
+					} else {
+						err ("cannot allocate requested pfmem for bus %x, device %x, len %x\n", 
+						     func->busno, func->device, len[count]);
+						kfree (mem_tmp);
+						kfree (bus_pfmem[count]);
+						return -EIO;
+					}
+				}
+
+				pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], func->pfmem[count]->start);
+
+				if (bar[count] & PCI_BASE_ADDRESS_MEM_TYPE_64) {
+					/* takes up another dword */
+					count += 1;
+					/* on the 2nd dword, write all 0s, since we can't handle them n.e.ways */
+					pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], 0x00000000);
+
+				}
+			} else {
+				/* regular memory */
+				len[count] = bar[count] & 0xFFFFFFF0;
+				len[count] = ~len[count] + 1;
+
+				debug ("len[count] in Memory is %x\n", len[count]);
+
+				bus_mem[count] = kzalloc(sizeof(struct resource_node), GFP_KERNEL);
+				if (!bus_mem[count]) {
+					err ("out of system memory\n");
+					retval = -ENOMEM;
+					goto error;
+				}
+				bus_mem[count]->type = MEM;
+				bus_mem[count]->busno = func->busno;
+				bus_mem[count]->devfunc = PCI_DEVFN(func->device,
+							func->function);
+				bus_mem[count]->len = len[count];
+				if (ibmphp_check_resource (bus_mem[count], 0) == 0) {
+					ibmphp_add_resource (bus_mem[count]);
+					func->mem[count] = bus_mem[count];
+				} else {
+					err ("cannot allocate requested mem for bus %x, device %x, len %x\n",
+					     func->busno, func->device, len[count]);
+					kfree (bus_mem[count]);
+					return -EIO;
+				}
+
+				pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], func->mem[count]->start);
+
+				if (bar[count] & PCI_BASE_ADDRESS_MEM_TYPE_64) {
+					/* takes up another dword */
+					count += 1;
+					/* on the 2nd dword, write all 0s, since we can't handle them n.e.ways */
+					pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], 0x00000000);
+
+				}
+			}
+		}		/* end of mem */
+	}			/* end of for  */
+
+	/* Now need to see how much space the devices behind the bridge needed */
+	amount_needed = scan_behind_bridge (func, sec_number);
+	if (amount_needed == NULL)
+		return -ENOMEM;
+
+	ibmphp_pci_bus->number = func->busno;
+	debug ("after coming back from scan_behind_bridge\n");
+	debug ("amount_needed->not_correct = %x\n", amount_needed->not_correct);
+	debug ("amount_needed->io = %x\n", amount_needed->io);
+	debug ("amount_needed->mem = %x\n", amount_needed->mem);
+	debug ("amount_needed->pfmem =  %x\n", amount_needed->pfmem);
+
+	if (amount_needed->not_correct) {		
+		debug ("amount_needed is not correct\n");
+		for (count = 0; address[count]; count++) {
+			/* for 2 BARs */
+			if (bus_io[count]) {
+				ibmphp_remove_resource (bus_io[count]);
+				func->io[count] = NULL;
+			} else if (bus_pfmem[count]) {
+				ibmphp_remove_resource (bus_pfmem[count]);
+				func->pfmem[count] = NULL;
+			} else if (bus_mem[count]) {
+				ibmphp_remove_resource (bus_mem[count]);
+				func->mem[count] = NULL;
+			}
+		}
+		kfree (amount_needed);
+		return -ENODEV;
+	}
+
+	if (!amount_needed->io) {
+		debug ("it doesn't want IO?\n");
+		flag_io = 1;
+	} else {
+		debug ("it wants %x IO behind the bridge\n", amount_needed->io);
+		io = kzalloc(sizeof(*io), GFP_KERNEL);
+		
+		if (!io) {
+			err ("out of system memory\n");
+			retval = -ENOMEM;
+			goto error;
+		}
+		io->type = IO;
+		io->busno = func->busno;
+		io->devfunc = PCI_DEVFN(func->device, func->function);
+		io->len = amount_needed->io;
+		if (ibmphp_check_resource (io, 1) == 0) {
+			debug ("were we able to add io\n");
+			ibmphp_add_resource (io);
+			flag_io = 1;
+		}
+	}
+
+	if (!amount_needed->mem) {
+		debug ("it doesn't want n.e.memory?\n");
+		flag_mem = 1;
+	} else {
+		debug ("it wants %x memory behind the bridge\n", amount_needed->mem);
+		mem = kzalloc(sizeof(*mem), GFP_KERNEL);
+		if (!mem) {
+			err ("out of system memory\n");
+			retval = -ENOMEM;
+			goto error;
+		}
+		mem->type = MEM;
+		mem->busno = func->busno;
+		mem->devfunc = PCI_DEVFN(func->device, func->function);
+		mem->len = amount_needed->mem;
+		if (ibmphp_check_resource (mem, 1) == 0) {
+			ibmphp_add_resource (mem);
+			flag_mem = 1;
+			debug ("were we able to add mem\n");
+		}
+	}
+
+	if (!amount_needed->pfmem) {
+		debug ("it doesn't want n.e.pfmem mem?\n");
+		flag_pfmem = 1;
+	} else {
+		debug ("it wants %x pfmemory behind the bridge\n", amount_needed->pfmem);
+		pfmem = kzalloc(sizeof(*pfmem), GFP_KERNEL);
+		if (!pfmem) {
+			err ("out of system memory\n");
+			retval = -ENOMEM;
+			goto error;
+		}
+		pfmem->type = PFMEM;
+		pfmem->busno = func->busno;
+		pfmem->devfunc = PCI_DEVFN(func->device, func->function);
+		pfmem->len = amount_needed->pfmem;
+		pfmem->fromMem = 0;
+		if (ibmphp_check_resource (pfmem, 1) == 0) {
+			ibmphp_add_resource (pfmem);
+			flag_pfmem = 1;
+		} else {
+			mem_tmp = kzalloc(sizeof(*mem_tmp), GFP_KERNEL);
+			if (!mem_tmp) {
+				err ("out of system memory\n");
+				retval = -ENOMEM;
+				goto error;
+			}
+			mem_tmp->type = MEM;
+			mem_tmp->busno = pfmem->busno;
+			mem_tmp->devfunc = pfmem->devfunc;
+			mem_tmp->len = pfmem->len;
+			if (ibmphp_check_resource (mem_tmp, 1) == 0) {
+				ibmphp_add_resource (mem_tmp);
+				pfmem->fromMem = 1;
+				pfmem->rangeno = mem_tmp->rangeno;
+				ibmphp_add_pfmem_from_mem (pfmem);
+				flag_pfmem = 1;
+			}
+		}
+	}
+
+	debug ("b4 if (flag_io && flag_mem && flag_pfmem)\n");
+	debug ("flag_io = %x, flag_mem = %x, flag_pfmem = %x\n", flag_io, flag_mem, flag_pfmem);
+
+	if (flag_io && flag_mem && flag_pfmem) {
+		/* If on bootup, there was a bridged card in this slot,
+		 * then card was removed and ibmphp got unloaded and loaded
+		 * back again, there's no way for us to remove the bus
+		 * struct, so no need to kmalloc, can use existing node
+		 */
+		bus = ibmphp_find_res_bus (sec_number);
+		if (!bus) {
+			bus = kzalloc(sizeof(*bus), GFP_KERNEL);
+			if (!bus) {
+				err ("out of system memory\n");
+				retval = -ENOMEM;
+				goto error;
+			}
+			bus->busno = sec_number;
+			debug ("b4 adding new bus\n");
+			rc = add_new_bus (bus, io, mem, pfmem, func->busno);
+		} else if (!(bus->rangeIO) && !(bus->rangeMem) && !(bus->rangePFMem))
+			rc = add_new_bus (bus, io, mem, pfmem, 0xFF);
+		else {
+			err ("expected bus structure not empty?\n");
+			retval = -EIO;
+			goto error;
+		}
+		if (rc) {
+			if (rc == -ENOMEM) {
+				ibmphp_remove_bus (bus, func->busno);
+				kfree (amount_needed);
+				return rc;
+			}
+			retval = rc;
+			goto error;
+		}
+		pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_IO_BASE, &io_base);
+		pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_PREF_MEMORY_BASE, &pfmem_base);
+
+		if ((io_base & PCI_IO_RANGE_TYPE_MASK) == PCI_IO_RANGE_TYPE_32) {
+			debug ("io 32\n");
+			need_io_upper = 1;
+		}
+		if ((pfmem_base & PCI_PREF_RANGE_TYPE_MASK) == PCI_PREF_RANGE_TYPE_64) {
+			debug ("pfmem 64\n");
+			need_pfmem_upper = 1;
+		}
+
+		if (bus->noIORanges) {
+			pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_IO_BASE, 0x00 | bus->rangeIO->start >> 8);
+			pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_IO_LIMIT, 0x00 | bus->rangeIO->end >> 8);	
+
+			/* _______________This is for debugging purposes only ____________________
+			pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_IO_BASE, &temp);
+			debug ("io_base = %x\n", (temp & PCI_IO_RANGE_TYPE_MASK) << 8);
+			pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_IO_LIMIT, &temp);
+			debug ("io_limit = %x\n", (temp & PCI_IO_RANGE_TYPE_MASK) << 8);
+			 ________________________________________________________________________*/
+
+			if (need_io_upper) {	/* since can't support n.e.ways */
+				pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_IO_BASE_UPPER16, 0x0000);
+				pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_IO_LIMIT_UPPER16, 0x0000);
+			}
+		} else {
+			pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_IO_BASE, 0x00);
+			pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_IO_LIMIT, 0x00);
+		}
+
+		if (bus->noMemRanges) {
+			pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_BASE, 0x0000 | bus->rangeMem->start >> 16);
+			pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_LIMIT, 0x0000 | bus->rangeMem->end >> 16);
+			
+			/* ____________________This is for debugging purposes only ________________________
+			pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_BASE, &temp);
+			debug ("mem_base = %x\n", (temp & PCI_MEMORY_RANGE_TYPE_MASK) << 16);
+			pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_LIMIT, &temp);
+			debug ("mem_limit = %x\n", (temp & PCI_MEMORY_RANGE_TYPE_MASK) << 16);
+			 __________________________________________________________________________________*/
+
+		} else {
+			pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_BASE, 0xffff);
+			pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_LIMIT, 0x0000);
+		}
+		if (bus->noPFMemRanges) {
+			pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_PREF_MEMORY_BASE, 0x0000 | bus->rangePFMem->start >> 16);
+			pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_PREF_MEMORY_LIMIT, 0x0000 | bus->rangePFMem->end >> 16);
+
+			/* __________________________This is for debugging purposes only _______________________
+			pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_PREF_MEMORY_BASE, &temp);
+			debug ("pfmem_base = %x", (temp & PCI_MEMORY_RANGE_TYPE_MASK) << 16);
+			pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_PREF_MEMORY_LIMIT, &temp);
+			debug ("pfmem_limit = %x\n", (temp & PCI_MEMORY_RANGE_TYPE_MASK) << 16);
+			 ______________________________________________________________________________________*/
+
+			if (need_pfmem_upper) {	/* since can't support n.e.ways */
+				pci_bus_write_config_dword (ibmphp_pci_bus, devfn, PCI_PREF_BASE_UPPER32, 0x00000000);
+				pci_bus_write_config_dword (ibmphp_pci_bus, devfn, PCI_PREF_LIMIT_UPPER32, 0x00000000);
+			}
+		} else {
+			pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_PREF_MEMORY_BASE, 0xffff);
+			pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_PREF_MEMORY_LIMIT, 0x0000);
+		}
+
+		debug ("b4 writing control information\n");
+
+		pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_INTERRUPT_PIN, &irq);
+		if ((irq > 0x00) && (irq < 0x05))
+			pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_INTERRUPT_LINE, func->irq[irq - 1]);
+		/*    
+		pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_BRIDGE_CONTROL, ctrl);
+		pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_BRIDGE_CONTROL, PCI_BRIDGE_CTL_PARITY);
+		pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_BRIDGE_CONTROL, PCI_BRIDGE_CTL_SERR);
+		 */
+
+		pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_COMMAND, DEVICEENABLE);
+		pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_BRIDGE_CONTROL, 0x07);
+		for (i = 0; i < 32; i++) {
+			if (amount_needed->devices[i]) {
+				debug ("device where devices[i] is 1 = %x\n", i);
+				func->devices[i] = 1;
+			}
+		}
+		func->bus = 1;	/* For unconfiguring, to indicate it's PPB */
+		func_passed = &func;
+		debug ("func->busno b4 returning is %x\n", func->busno);
+		debug ("func->busno b4 returning in the other structure is %x\n", (*func_passed)->busno);
+		kfree (amount_needed);
+		return 0;
+	} else {
+		err ("Configuring bridge was unsuccessful...\n");
+		mem_tmp = NULL;
+		retval = -EIO;
+		goto error;
+	}
+
+error:
+	kfree(amount_needed);
+	if (pfmem)
+		ibmphp_remove_resource (pfmem);
+	if (io)
+		ibmphp_remove_resource (io);
+	if (mem)
+		ibmphp_remove_resource (mem);
+	for (i = 0; i < 2; i++) {	/* for 2 BARs */
+		if (bus_io[i]) {
+			ibmphp_remove_resource (bus_io[i]);
+			func->io[i] = NULL;
+		} else if (bus_pfmem[i]) {
+			ibmphp_remove_resource (bus_pfmem[i]);
+			func->pfmem[i] = NULL;
+		} else if (bus_mem[i]) {
+			ibmphp_remove_resource (bus_mem[i]);
+			func->mem[i] = NULL;
+		}
+	}
+	return retval;
+}
+
+/*****************************************************************************
+ * This function adds up the amount of resources needed behind the PPB bridge
+ * and passes it to the configure_bridge function
+ * Input: bridge function
+ * Ouput: amount of resources needed
+ *****************************************************************************/
+static struct res_needed *scan_behind_bridge (struct pci_func * func, u8 busno)
+{
+	int count, len[6];
+	u16 vendor_id;
+	u8 hdr_type;
+	u8 device, function;
+	unsigned int devfn;
+	int howmany = 0;	/*this is to see if there are any devices behind the bridge */
+
+	u32 bar[6], class;
+	u32 address[] = {
+		PCI_BASE_ADDRESS_0,
+		PCI_BASE_ADDRESS_1,
+		PCI_BASE_ADDRESS_2,
+		PCI_BASE_ADDRESS_3,
+		PCI_BASE_ADDRESS_4,
+		PCI_BASE_ADDRESS_5,
+		0
+	};
+	struct res_needed *amount;
+
+	amount = kzalloc(sizeof(*amount), GFP_KERNEL);
+	if (amount == NULL)
+		return NULL;
+
+	ibmphp_pci_bus->number = busno;
+
+	debug ("the bus_no behind the bridge is %x\n", busno);
+	debug ("scanning devices behind the bridge...\n");
+	for (device = 0; device < 32; device++) {
+		amount->devices[device] = 0;
+		for (function = 0; function < 8; function++) {
+			devfn = PCI_DEVFN(device, function);
+
+			pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_VENDOR_ID, &vendor_id);
+
+			if (vendor_id != PCI_VENDOR_ID_NOTVALID) {
+				/* found correct device!!! */
+				howmany++;
+
+				pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_HEADER_TYPE, &hdr_type);
+				pci_bus_read_config_dword (ibmphp_pci_bus, devfn, PCI_CLASS_REVISION, &class);
+
+				debug ("hdr_type behind the bridge is %x\n", hdr_type);
+				if (hdr_type & PCI_HEADER_TYPE_BRIDGE) {
+					err ("embedded bridges not supported for hot-plugging.\n");
+					amount->not_correct = 1;
+					return amount;
+				}
+
+				class >>= 8;	/* to take revision out, class = class.subclass.prog i/f */
+				if (class == PCI_CLASS_NOT_DEFINED_VGA) {
+					err ("The device %x is VGA compatible and as is not supported for hot plugging. "
+					     "Please choose another device.\n", device);
+					amount->not_correct = 1;
+					return amount;
+				} else if (class == PCI_CLASS_DISPLAY_VGA) {
+					err ("The device %x is not supported for hot plugging. "
+					     "Please choose another device.\n", device);
+					amount->not_correct = 1;
+					return amount;
+				}
+
+				amount->devices[device] = 1;
+
+				for (count = 0; address[count]; count++) {
+					/* for 6 BARs */
+					/*
+					pci_bus_read_config_byte (ibmphp_pci_bus, devfn, address[count], &tmp);
+					if (tmp & 0x01) // IO
+						pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], 0xFFFFFFFD);
+					else // MEMORY
+						pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], 0xFFFFFFFF);
+					*/
+					pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], 0xFFFFFFFF);
+					pci_bus_read_config_dword (ibmphp_pci_bus, devfn, address[count], &bar[count]);
+
+					debug ("what is bar[count]? %x, count = %d\n", bar[count], count);
+
+					if (!bar[count])	/* This BAR is not implemented */
+						continue;
+
+					//tmp_bar = bar[count];
+
+					debug ("count %d device %x function %x wants %x resources\n", count, device, function, bar[count]);
+
+					if (bar[count] & PCI_BASE_ADDRESS_SPACE_IO) {
+						/* This is IO */
+						len[count] = bar[count] & 0xFFFFFFFC;
+						len[count] = ~len[count] + 1;
+						amount->io += len[count];
+					} else {
+						/* This is Memory */
+						if (bar[count] & PCI_BASE_ADDRESS_MEM_PREFETCH) {
+							/* pfmem */
+							len[count] = bar[count] & 0xFFFFFFF0;
+							len[count] = ~len[count] + 1;
+							amount->pfmem += len[count];
+							if (bar[count] & PCI_BASE_ADDRESS_MEM_TYPE_64)
+								/* takes up another dword */
+								count += 1;
+
+						} else {
+							/* regular memory */
+							len[count] = bar[count] & 0xFFFFFFF0;
+							len[count] = ~len[count] + 1;
+							amount->mem += len[count];
+							if (bar[count] & PCI_BASE_ADDRESS_MEM_TYPE_64) {
+								/* takes up another dword */
+								count += 1;
+							}
+						}
+					}
+				}	/* end for */
+			}	/* end if (valid) */
+		}	/* end for */
+	}	/* end for */
+
+	if (!howmany)
+		amount->not_correct = 1;
+	else
+		amount->not_correct = 0;
+	if ((amount->io) && (amount->io < IOBRIDGE))
+		amount->io = IOBRIDGE;
+	if ((amount->mem) && (amount->mem < MEMBRIDGE))
+		amount->mem = MEMBRIDGE;
+	if ((amount->pfmem) && (amount->pfmem < MEMBRIDGE))
+		amount->pfmem = MEMBRIDGE;
+	return amount;
+}
+
+/* The following 3 unconfigure_boot_ routines deal with the case when we had the card 
+ * upon bootup in the system, since we don't allocate func to such case, we need to read 
+ * the start addresses from pci config space and then find the corresponding entries in 
+ * our resource lists.  The functions return either 0, -ENODEV, or -1 (general failure)
+ * Change: we also call these functions even if we configured the card ourselves (i.e., not
+ * the bootup case), since it should work same way
+ */
+static int unconfigure_boot_device (u8 busno, u8 device, u8 function)
+{
+	u32 start_address;
+	u32 address[] = {
+		PCI_BASE_ADDRESS_0,
+		PCI_BASE_ADDRESS_1,
+		PCI_BASE_ADDRESS_2,
+		PCI_BASE_ADDRESS_3,
+		PCI_BASE_ADDRESS_4,
+		PCI_BASE_ADDRESS_5,
+		0
+	};
+	int count;
+	struct resource_node *io;
+	struct resource_node *mem;
+	struct resource_node *pfmem;
+	struct bus_node *bus;
+	u32 end_address;
+	u32 temp_end;
+	u32 size;
+	u32 tmp_address;
+	unsigned int devfn;
+
+	debug ("%s - enter\n", __func__);
+
+	bus = ibmphp_find_res_bus (busno);
+	if (!bus) {
+		debug ("cannot find corresponding bus.\n");
+		return -EINVAL;
+	}
+
+	devfn = PCI_DEVFN(device, function);
+	ibmphp_pci_bus->number = busno;
+	for (count = 0; address[count]; count++) {	/* for 6 BARs */
+		pci_bus_read_config_dword (ibmphp_pci_bus, devfn, address[count], &start_address);
+
+		/* We can do this here, b/c by that time the device driver of the card has been stopped */
+
+		pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], 0xFFFFFFFF);
+		pci_bus_read_config_dword (ibmphp_pci_bus, devfn, address[count], &size);
+		pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], start_address);
+
+		debug ("start_address is %x\n", start_address);
+		debug ("busno, device, function %x %x %x\n", busno, device, function);
+		if (!size) {
+			/* This BAR is not implemented */
+			debug ("is this bar no implemented?, count = %d\n", count);
+			continue;
+		}
+		tmp_address = start_address;
+		if (start_address & PCI_BASE_ADDRESS_SPACE_IO) {
+			/* This is IO */
+			start_address &= PCI_BASE_ADDRESS_IO_MASK;
+			size = size & 0xFFFFFFFC;
+			size = ~size + 1;
+			end_address = start_address + size - 1;
+			if (ibmphp_find_resource (bus, start_address, &io, IO) < 0) {
+				err ("cannot find corresponding IO resource to remove\n");
+				return -EIO;
+			}
+			debug ("io->start = %x\n", io->start);
+			temp_end = io->end;
+			start_address = io->end + 1;
+			ibmphp_remove_resource (io);
+			/* This is needed b/c of the old I/O restrictions in the BIOS */
+			while (temp_end < end_address) {
+				if (ibmphp_find_resource (bus, start_address, &io, IO) < 0) {
+					err ("cannot find corresponding IO resource to remove\n");
+					return -EIO;
+				}
+				debug ("io->start = %x\n", io->start);
+				temp_end = io->end;
+				start_address = io->end + 1;
+				ibmphp_remove_resource (io);
+			}
+
+			/* ????????? DO WE NEED TO WRITE ANYTHING INTO THE PCI CONFIG SPACE BACK ?????????? */
+		} else {
+			/* This is Memory */
+			if (start_address & PCI_BASE_ADDRESS_MEM_PREFETCH) {
+				/* pfmem */
+				debug ("start address of pfmem is %x\n", start_address);
+				start_address &= PCI_BASE_ADDRESS_MEM_MASK;
+
+				if (ibmphp_find_resource (bus, start_address, &pfmem, PFMEM) < 0) {
+					err ("cannot find corresponding PFMEM resource to remove\n");
+					return -EIO;
+				}
+				if (pfmem) {
+					debug ("pfmem->start = %x\n", pfmem->start);
+
+					ibmphp_remove_resource(pfmem);
+				}
+			} else {
+				/* regular memory */
+				debug ("start address of mem is %x\n", start_address);
+				start_address &= PCI_BASE_ADDRESS_MEM_MASK;
+
+				if (ibmphp_find_resource (bus, start_address, &mem, MEM) < 0) {
+					err ("cannot find corresponding MEM resource to remove\n");
+					return -EIO;
+				}
+				if (mem) {
+					debug ("mem->start = %x\n", mem->start);
+
+					ibmphp_remove_resource(mem);
+				}
+			}
+			if (tmp_address & PCI_BASE_ADDRESS_MEM_TYPE_64) {
+				/* takes up another dword */
+				count += 1;
+			}
+		}	/* end of mem */
+	}	/* end of for */
+
+	return 0;
+}
+
+static int unconfigure_boot_bridge (u8 busno, u8 device, u8 function)
+{
+	int count;
+	int bus_no, pri_no, sub_no, sec_no = 0;
+	u32 start_address, tmp_address;
+	u8 sec_number, sub_number, pri_number;
+	struct resource_node *io = NULL;
+	struct resource_node *mem = NULL;
+	struct resource_node *pfmem = NULL;
+	struct bus_node *bus;
+	u32 address[] = {
+		PCI_BASE_ADDRESS_0,
+		PCI_BASE_ADDRESS_1,
+		0
+	};
+	unsigned int devfn;
+
+	devfn = PCI_DEVFN(device, function);
+	ibmphp_pci_bus->number = busno;
+	bus_no = (int) busno;
+	debug ("busno is %x\n", busno);
+	pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_PRIMARY_BUS, &pri_number);
+	debug ("%s - busno = %x, primary_number = %x\n", __func__, busno, pri_number);
+
+	pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_SECONDARY_BUS, &sec_number);
+	debug ("sec_number is %x\n", sec_number);
+	sec_no = (int) sec_number;
+	pri_no = (int) pri_number;
+	if (pri_no != bus_no) {
+		err ("primary numbers in our structures and pci config space don't match.\n");
+		return -EINVAL;
+	}
+
+	pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_SUBORDINATE_BUS, &sub_number);
+	sub_no = (int) sub_number;
+	debug ("sub_no is %d, sec_no is %d\n", sub_no, sec_no);
+	if (sec_no != sub_number) {
+		err ("there're more buses behind this bridge.  Hot removal is not supported.  Please choose another card\n");
+		return -ENODEV;
+	}
+
+	bus = ibmphp_find_res_bus (sec_number);
+	if (!bus) {
+		err ("cannot find Bus structure for the bridged device\n");
+		return -EINVAL;
+	}
+	debug("bus->busno is %x\n", bus->busno);
+	debug("sec_number is %x\n", sec_number);
+
+	ibmphp_remove_bus (bus, busno);
+
+	for (count = 0; address[count]; count++) {
+		/* for 2 BARs */
+		pci_bus_read_config_dword (ibmphp_pci_bus, devfn, address[count], &start_address);
+
+		if (!start_address) {
+			/* This BAR is not implemented */
+			continue;
+		}
+
+		tmp_address = start_address;
+
+		if (start_address & PCI_BASE_ADDRESS_SPACE_IO) {
+			/* This is IO */
+			start_address &= PCI_BASE_ADDRESS_IO_MASK;
+			if (ibmphp_find_resource (bus, start_address, &io, IO) < 0) {
+				err ("cannot find corresponding IO resource to remove\n");
+				return -EIO;
+			}
+			if (io)
+				debug ("io->start = %x\n", io->start);
+
+			ibmphp_remove_resource (io);
+
+			/* ????????? DO WE NEED TO WRITE ANYTHING INTO THE PCI CONFIG SPACE BACK ?????????? */
+		} else {
+			/* This is Memory */
+			if (start_address & PCI_BASE_ADDRESS_MEM_PREFETCH) {
+				/* pfmem */
+				start_address &= PCI_BASE_ADDRESS_MEM_MASK;
+				if (ibmphp_find_resource (bus, start_address, &pfmem, PFMEM) < 0) {
+					err ("cannot find corresponding PFMEM resource to remove\n");
+					return -EINVAL;
+				}
+				if (pfmem) {
+					debug ("pfmem->start = %x\n", pfmem->start);
+
+					ibmphp_remove_resource(pfmem);
+				}
+			} else {
+				/* regular memory */
+				start_address &= PCI_BASE_ADDRESS_MEM_MASK;
+				if (ibmphp_find_resource (bus, start_address, &mem, MEM) < 0) {
+					err ("cannot find corresponding MEM resource to remove\n");
+					return -EINVAL;
+				}
+				if (mem) {
+					debug ("mem->start = %x\n", mem->start);
+
+					ibmphp_remove_resource(mem);
+				}
+			}
+			if (tmp_address & PCI_BASE_ADDRESS_MEM_TYPE_64) {
+				/* takes up another dword */
+				count += 1;
+			}
+		}	/* end of mem */
+	}	/* end of for */
+	debug ("%s - exiting, returning success\n", __func__);
+	return 0;
+}
+
+static int unconfigure_boot_card (struct slot *slot_cur)
+{
+	u16 vendor_id;
+	u32 class;
+	u8 hdr_type;
+	u8 device;
+	u8 busno;
+	u8 function;
+	int rc;
+	unsigned int devfn;
+	u8 valid_device = 0x00; /* To see if we are ever able to find valid device and read it */
+
+	debug ("%s - enter\n", __func__);
+
+	device = slot_cur->device;
+	busno = slot_cur->bus;
+
+	debug ("b4 for loop, device is %x\n", device);
+	/* For every function on the card */
+	for (function = 0x0; function < 0x08; function++) {
+		devfn = PCI_DEVFN(device, function);
+		ibmphp_pci_bus->number = busno;
+
+		pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_VENDOR_ID, &vendor_id);
+
+		if (vendor_id != PCI_VENDOR_ID_NOTVALID) {
+			/* found correct device!!! */
+			++valid_device;
+
+			debug ("%s - found correct device\n", __func__);
+
+			/* header: x x x x x x x x
+			 *         | |___________|=> 1=PPB bridge, 0=normal device, 2=CardBus Bridge
+			 *         |_=> 0 = single function device, 1 = multi-function device
+			 */
+
+			pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_HEADER_TYPE, &hdr_type);
+			pci_bus_read_config_dword (ibmphp_pci_bus, devfn, PCI_CLASS_REVISION, &class);
+
+			debug ("hdr_type %x, class %x\n", hdr_type, class);
+			class >>= 8;	/* to take revision out, class = class.subclass.prog i/f */
+			if (class == PCI_CLASS_NOT_DEFINED_VGA) {
+				err ("The device %x function %x is VGA compatible and is not supported for hot removing. "
+				     "Please choose another device.\n", device, function);
+				return -ENODEV;
+			} else if (class == PCI_CLASS_DISPLAY_VGA) {
+				err ("The device %x function %x is not supported for hot removing. "
+				     "Please choose another device.\n", device, function);
+				return -ENODEV;
+			}
+
+			switch (hdr_type) {
+				case PCI_HEADER_TYPE_NORMAL:
+					rc = unconfigure_boot_device (busno, device, function);
+					if (rc) {
+						err ("was not able to unconfigure device %x func %x on bus %x. bailing out...\n",
+						     device, function, busno);
+						return rc;
+					}
+					function = 0x8;
+					break;
+				case PCI_HEADER_TYPE_MULTIDEVICE:
+					rc = unconfigure_boot_device (busno, device, function);
+					if (rc) {
+						err ("was not able to unconfigure device %x func %x on bus %x. bailing out...\n",
+						     device, function, busno);
+						return rc;
+					}
+					break;
+				case PCI_HEADER_TYPE_BRIDGE:
+					class >>= 8;
+					if (class != PCI_CLASS_BRIDGE_PCI) {
+						err ("This device %x function %x is not PCI-to-PCI bridge, "
+						     "and is not supported for hot-removing. "
+						     "Please try another card.\n", device, function);
+						return -ENODEV;
+					}
+					rc = unconfigure_boot_bridge (busno, device, function);
+					if (rc != 0) {
+						err ("was not able to hot-remove PPB properly.\n");
+						return rc;
+					}
+
+					function = 0x8;
+					break;
+				case PCI_HEADER_TYPE_MULTIBRIDGE:
+					class >>= 8;
+					if (class != PCI_CLASS_BRIDGE_PCI) {
+						err ("This device %x function %x is not PCI-to-PCI bridge, "
+						     "and is not supported for hot-removing. "
+						     "Please try another card.\n", device, function);
+						return -ENODEV;
+					}
+					rc = unconfigure_boot_bridge (busno, device, function);
+					if (rc != 0) {
+						err ("was not able to hot-remove PPB properly.\n");
+						return rc;
+					}
+					break;
+				default:
+					err ("MAJOR PROBLEM!!!! Cannot read device's header\n");
+					return -1;
+					break;
+			}	/* end of switch */
+		}	/* end of valid device */
+	}	/* end of for */
+
+	if (!valid_device) {
+		err ("Could not find device to unconfigure.  Or could not read the card.\n");
+		return -1;
+	}
+	return 0;
+}
+
+/*
+ * free the resources of the card (multi, single, or bridged)
+ * Parameters: slot, flag to say if this is for removing entire module or just
+ * unconfiguring the device
+ * TO DO:  will probably need to add some code in case there was some resource,
+ * to remove it... this is from when we have errors in the configure_card...
+ * 			!!!!!!!!!!!!!!!!!!!!!!!!!FOR BUSES!!!!!!!!!!!!
+ * Returns: 0, -1, -ENODEV 
+ */
+int ibmphp_unconfigure_card (struct slot **slot_cur, int the_end)
+{
+	int i;
+	int count;
+	int rc;
+	struct slot *sl = *slot_cur;
+	struct pci_func *cur_func = NULL;
+	struct pci_func *temp_func;
+
+	debug ("%s - enter\n", __func__);
+
+	if (!the_end) {
+		/* Need to unconfigure the card */
+		rc = unconfigure_boot_card (sl);
+		if ((rc == -ENODEV) || (rc == -EIO) || (rc == -EINVAL)) {
+			/* In all other cases, will still need to get rid of func structure if it exists */
+			return rc;
+		}
+	}
+
+	if (sl->func) {
+		cur_func = sl->func;
+		while (cur_func) {
+			/* TO DO: WILL MOST LIKELY NEED TO GET RID OF THE BUS STRUCTURE FROM RESOURCES AS WELL */
+			if (cur_func->bus) {
+				/* in other words, it's a PPB */
+				count = 2;
+			} else {
+				count = 6;
+			}
+
+			for (i = 0; i < count; i++) {
+				if (cur_func->io[i]) {
+					debug ("io[%d] exists\n", i);
+					if (the_end > 0)
+						ibmphp_remove_resource (cur_func->io[i]);
+					cur_func->io[i] = NULL;
+				}
+				if (cur_func->mem[i]) {
+					debug ("mem[%d] exists\n", i);
+					if (the_end > 0)
+						ibmphp_remove_resource (cur_func->mem[i]);
+					cur_func->mem[i] = NULL;
+				}
+				if (cur_func->pfmem[i]) {
+					debug ("pfmem[%d] exists\n", i);
+					if (the_end > 0)
+						ibmphp_remove_resource (cur_func->pfmem[i]);
+					cur_func->pfmem[i] = NULL;
+				}
+			}
+
+			temp_func = cur_func->next;
+			kfree (cur_func);
+			cur_func = temp_func;
+		}
+	}
+
+	sl->func = NULL;
+	*slot_cur = sl;
+	debug ("%s - exit\n", __func__);
+	return 0;
+}
+
+/*
+ * add a new bus resulting from hot-plugging a PPB bridge with devices
+ *
+ * Input: bus and the amount of resources needed (we know we can assign those,
+ *        since they've been checked already
+ * Output: bus added to the correct spot
+ *         0, -1, error 
+ */
+static int add_new_bus (struct bus_node *bus, struct resource_node *io, struct resource_node *mem, struct resource_node *pfmem, u8 parent_busno)
+{
+	struct range_node *io_range = NULL;
+	struct range_node *mem_range = NULL;
+	struct range_node *pfmem_range = NULL;
+	struct bus_node *cur_bus = NULL;
+
+	/* Trying to find the parent bus number */
+	if (parent_busno != 0xFF) {
+		cur_bus	= ibmphp_find_res_bus (parent_busno);
+		if (!cur_bus) {
+			err ("strange, cannot find bus which is supposed to be at the system... something is terribly wrong...\n");
+			return -ENODEV;
+		}
+	
+		list_add (&bus->bus_list, &cur_bus->bus_list);
+	}
+	if (io) {
+		io_range = kzalloc(sizeof(*io_range), GFP_KERNEL);
+		if (!io_range) {
+			err ("out of system memory\n");
+			return -ENOMEM;
+		}
+		io_range->start = io->start;
+		io_range->end = io->end;
+		io_range->rangeno = 1;
+		bus->noIORanges = 1;
+		bus->rangeIO = io_range;
+	}
+	if (mem) {
+		mem_range = kzalloc(sizeof(*mem_range), GFP_KERNEL);
+		if (!mem_range) {
+			err ("out of system memory\n");
+			return -ENOMEM;
+		}
+		mem_range->start = mem->start;
+		mem_range->end = mem->end;
+		mem_range->rangeno = 1;
+		bus->noMemRanges = 1;
+		bus->rangeMem = mem_range;
+	}
+	if (pfmem) {
+		pfmem_range = kzalloc(sizeof(*pfmem_range), GFP_KERNEL);
+		if (!pfmem_range) {	
+			err ("out of system memory\n");
+			return -ENOMEM;
+		}
+		pfmem_range->start = pfmem->start;
+		pfmem_range->end = pfmem->end;
+		pfmem_range->rangeno = 1;
+		bus->noPFMemRanges = 1;
+		bus->rangePFMem = pfmem_range;
+	}
+	return 0;
+}
+
+/*
+ * find the 1st available bus number for PPB to set as its secondary bus
+ * Parameters: bus_number of the primary bus
+ * Returns: bus_number of the secondary bus or 0xff in case of failure
+ */
+static u8 find_sec_number (u8 primary_busno, u8 slotno)
+{
+	int min, max;
+	u8 busno;
+	struct bus_info *bus;
+	struct bus_node *bus_cur;
+
+	bus = ibmphp_find_same_bus_num (primary_busno);
+	if (!bus) {
+		err ("cannot get slot range of the bus from the BIOS\n");
+		return 0xff;
+	}
+	max = bus->slot_max;
+	min = bus->slot_min;
+	if ((slotno > max) || (slotno < min)) {
+		err ("got the wrong range\n");
+		return 0xff;
+	}
+	busno = (u8) (slotno - (u8) min);
+	busno += primary_busno + 0x01;
+	bus_cur = ibmphp_find_res_bus (busno);
+	/* either there is no such bus number, or there are no ranges, which
+	 * can only happen if we removed the bridged device in previous load
+	 * of the driver, and now only have the skeleton bus struct
+	 */
+	if ((!bus_cur) || (!(bus_cur->rangeIO) && !(bus_cur->rangeMem) && !(bus_cur->rangePFMem)))
+		return busno;
+	return 0xff;
+}
+
diff --git a/drivers/pci/hotplug/ibmphp_res.c b/drivers/pci/hotplug/ibmphp_res.c
new file mode 100644
index 00000000..e2dc289f
--- /dev/null
+++ b/drivers/pci/hotplug/ibmphp_res.c
@@ -0,0 +1,2145 @@
+/*
+ * IBM Hot Plug Controller Driver
+ *
+ * Written By: Irene Zubarev, IBM Corporation
+ *
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001,2002 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <gregkh@us.ibm.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/list.h>
+#include <linux/init.h>
+#include "ibmphp.h"
+
+static int flags = 0;		/* for testing */
+
+static void update_resources (struct bus_node *bus_cur, int type, int rangeno);
+static int once_over (void);
+static int remove_ranges (struct bus_node *, struct bus_node *);
+static int update_bridge_ranges (struct bus_node **);
+static int add_bus_range (int type, struct range_node *, struct bus_node *);
+static void fix_resources (struct bus_node *);
+static struct bus_node *find_bus_wprev (u8, struct bus_node **, u8);
+
+static LIST_HEAD(gbuses);
+
+static struct bus_node * __init alloc_error_bus (struct ebda_pci_rsrc * curr, u8 busno, int flag)
+{
+	struct bus_node * newbus;
+
+	if (!(curr) && !(flag)) {
+		err ("NULL pointer passed\n");
+		return NULL;
+	}
+
+	newbus = kzalloc(sizeof(struct bus_node), GFP_KERNEL);
+	if (!newbus) {
+		err ("out of system memory\n");
+		return NULL;
+	}
+
+	if (flag)
+		newbus->busno = busno;
+	else
+		newbus->busno = curr->bus_num;
+	list_add_tail (&newbus->bus_list, &gbuses);
+	return newbus;
+}
+
+static struct resource_node * __init alloc_resources (struct ebda_pci_rsrc * curr)
+{
+	struct resource_node *rs;
+	
+	if (!curr) {
+		err ("NULL passed to allocate\n");
+		return NULL;
+	}
+
+	rs = kzalloc(sizeof(struct resource_node), GFP_KERNEL);
+	if (!rs) {
+		err ("out of system memory\n");
+		return NULL;
+	}
+	rs->busno = curr->bus_num;
+	rs->devfunc = curr->dev_fun;
+	rs->start = curr->start_addr;
+	rs->end = curr->end_addr;
+	rs->len = curr->end_addr - curr->start_addr + 1;
+	return rs;
+}
+
+static int __init alloc_bus_range (struct bus_node **new_bus, struct range_node **new_range, struct ebda_pci_rsrc *curr, int flag, u8 first_bus)
+{
+	struct bus_node * newbus;
+	struct range_node *newrange;
+	u8 num_ranges = 0;
+
+	if (first_bus) {
+		newbus = kzalloc(sizeof(struct bus_node), GFP_KERNEL);
+		if (!newbus) {
+			err ("out of system memory.\n");
+			return -ENOMEM;
+		}
+		newbus->busno = curr->bus_num;
+	} else {
+		newbus = *new_bus;
+		switch (flag) {
+			case MEM:
+				num_ranges = newbus->noMemRanges;
+				break;
+			case PFMEM:
+				num_ranges = newbus->noPFMemRanges;
+				break;
+			case IO:
+				num_ranges = newbus->noIORanges;
+				break;
+		}
+	}
+
+	newrange = kzalloc(sizeof(struct range_node), GFP_KERNEL);
+	if (!newrange) {
+		if (first_bus)
+			kfree (newbus);
+		err ("out of system memory\n");
+		return -ENOMEM;
+	}
+	newrange->start = curr->start_addr;
+	newrange->end = curr->end_addr;
+		
+	if (first_bus || (!num_ranges))
+		newrange->rangeno = 1;
+	else {
+		/* need to insert our range */
+		add_bus_range (flag, newrange, newbus);
+		debug ("%d resource Primary Bus inserted on bus %x [%x - %x]\n", flag, newbus->busno, newrange->start, newrange->end);
+	}
+
+	switch (flag) {
+		case MEM:
+			newbus->rangeMem = newrange;
+			if (first_bus)
+				newbus->noMemRanges = 1;
+			else {
+				debug ("First Memory Primary on bus %x, [%x - %x]\n", newbus->busno, newrange->start, newrange->end);
+				++newbus->noMemRanges;
+				fix_resources (newbus);
+			}
+			break;
+		case IO:
+			newbus->rangeIO = newrange;
+			if (first_bus)
+				newbus->noIORanges = 1;
+			else {
+				debug ("First IO Primary on bus %x, [%x - %x]\n", newbus->busno, newrange->start, newrange->end);
+				++newbus->noIORanges;
+				fix_resources (newbus);
+			}
+			break;
+		case PFMEM:
+			newbus->rangePFMem = newrange;
+			if (first_bus)
+				newbus->noPFMemRanges = 1;
+			else {	
+				debug ("1st PFMemory Primary on Bus %x [%x - %x]\n", newbus->busno, newrange->start, newrange->end);
+				++newbus->noPFMemRanges;
+				fix_resources (newbus);
+			}
+
+			break;
+	}
+
+	*new_bus = newbus;
+	*new_range = newrange;
+	return 0;
+}
+
+
+/* Notes:
+ * 1. The ranges are ordered.  The buses are not ordered.  (First come)
+ *
+ * 2. If cannot allocate out of PFMem range, allocate from Mem ranges.  PFmemFromMem
+ * are not sorted. (no need since use mem node). To not change the entire code, we
+ * also add mem node whenever this case happens so as not to change
+ * ibmphp_check_mem_resource etc (and since it really is taking Mem resource)
+ */
+
+/*****************************************************************************
+ * This is the Resource Management initialization function.  It will go through
+ * the Resource list taken from EBDA and fill in this module's data structures
+ *
+ * THIS IS NOT TAKING INTO CONSIDERATION IO RESTRICTIONS OF PRIMARY BUSES, 
+ * SINCE WE'RE GOING TO ASSUME FOR NOW WE DON'T HAVE THOSE ON OUR BUSES FOR NOW
+ *
+ * Input: ptr to the head of the resource list from EBDA
+ * Output: 0, -1 or error codes
+ ***************************************************************************/
+int __init ibmphp_rsrc_init (void)
+{
+	struct ebda_pci_rsrc *curr;
+	struct range_node *newrange = NULL;
+	struct bus_node *newbus = NULL;
+	struct bus_node *bus_cur;
+	struct bus_node *bus_prev;
+	struct list_head *tmp;
+	struct resource_node *new_io = NULL;
+	struct resource_node *new_mem = NULL;
+	struct resource_node *new_pfmem = NULL;
+	int rc;
+	struct list_head *tmp_ebda;
+
+	list_for_each (tmp_ebda, &ibmphp_ebda_pci_rsrc_head) {
+		curr = list_entry (tmp_ebda, struct ebda_pci_rsrc, ebda_pci_rsrc_list);
+		if (!(curr->rsrc_type & PCIDEVMASK)) {
+			/* EBDA still lists non PCI devices, so ignore... */
+			debug ("this is not a PCI DEVICE in rsrc_init, please take care\n");
+			// continue;
+		}
+
+		/* this is a primary bus resource */
+		if (curr->rsrc_type & PRIMARYBUSMASK) {
+			/* memory */
+			if ((curr->rsrc_type & RESTYPE) == MMASK) {
+				/* no bus structure exists in place yet */
+				if (list_empty (&gbuses)) {
+					if ((rc = alloc_bus_range (&newbus, &newrange, curr, MEM, 1)))
+						return rc;
+					list_add_tail (&newbus->bus_list, &gbuses);
+					debug ("gbuses = NULL, Memory Primary Bus %x [%x - %x]\n", newbus->busno, newrange->start, newrange->end);
+				} else {
+					bus_cur = find_bus_wprev (curr->bus_num, &bus_prev, 1);
+					/* found our bus */
+					if (bus_cur) {
+						rc = alloc_bus_range (&bus_cur, &newrange, curr, MEM, 0);
+						if (rc)
+							return rc;
+					} else {
+						/* went through all the buses and didn't find ours, need to create a new bus node */
+						if ((rc = alloc_bus_range (&newbus, &newrange, curr, MEM, 1)))
+							return rc;
+
+						list_add_tail (&newbus->bus_list, &gbuses);
+						debug ("New Bus, Memory Primary Bus %x [%x - %x]\n", newbus->busno, newrange->start, newrange->end);
+					}
+				}
+			} else if ((curr->rsrc_type & RESTYPE) == PFMASK) {
+				/* prefetchable memory */
+				if (list_empty (&gbuses)) {
+					/* no bus structure exists in place yet */
+					if ((rc = alloc_bus_range (&newbus, &newrange, curr, PFMEM, 1)))
+						return rc;
+					list_add_tail (&newbus->bus_list, &gbuses);
+					debug ("gbuses = NULL, PFMemory Primary Bus %x [%x - %x]\n", newbus->busno, newrange->start, newrange->end);
+				} else {
+					bus_cur = find_bus_wprev (curr->bus_num, &bus_prev, 1);
+					if (bus_cur) {
+						/* found our bus */
+						rc = alloc_bus_range (&bus_cur, &newrange, curr, PFMEM, 0);
+						if (rc)
+							return rc;
+					} else {
+						/* went through all the buses and didn't find ours, need to create a new bus node */
+						if ((rc = alloc_bus_range (&newbus, &newrange, curr, PFMEM, 1)))
+							return rc;
+						list_add_tail (&newbus->bus_list, &gbuses);
+						debug ("1st Bus, PFMemory Primary Bus %x [%x - %x]\n", newbus->busno, newrange->start, newrange->end);
+					}
+				}
+			} else if ((curr->rsrc_type & RESTYPE) == IOMASK) {
+				/* IO */
+				if (list_empty (&gbuses)) {
+					/* no bus structure exists in place yet */
+					if ((rc = alloc_bus_range (&newbus, &newrange, curr, IO, 1)))
+						return rc;
+					list_add_tail (&newbus->bus_list, &gbuses);
+					debug ("gbuses = NULL, IO Primary Bus %x [%x - %x]\n", newbus->busno, newrange->start, newrange->end);
+				} else {
+					bus_cur = find_bus_wprev (curr->bus_num, &bus_prev, 1);
+					if (bus_cur) {
+						rc = alloc_bus_range (&bus_cur, &newrange, curr, IO, 0);
+						if (rc)
+							return rc;
+					} else {
+						/* went through all the buses and didn't find ours, need to create a new bus node */
+						if ((rc = alloc_bus_range (&newbus, &newrange, curr, IO, 1)))
+							return rc;
+						list_add_tail (&newbus->bus_list, &gbuses);
+						debug ("1st Bus, IO Primary Bus %x [%x - %x]\n", newbus->busno, newrange->start, newrange->end);
+					}
+				}
+
+			} else {
+				;	/* type is reserved  WHAT TO DO IN THIS CASE???
+					   NOTHING TO DO??? */
+			}
+		} else {
+			/* regular pci device resource */
+			if ((curr->rsrc_type & RESTYPE) == MMASK) {
+				/* Memory resource */
+				new_mem = alloc_resources (curr);
+				if (!new_mem)
+					return -ENOMEM;
+				new_mem->type = MEM;
+				/*
+				 * if it didn't find the bus, means PCI dev
+				 * came b4 the Primary Bus info, so need to
+				 * create a bus rangeno becomes a problem...
+				 * assign a -1 and then update once the range
+				 * actually appears...
+				 */
+				if (ibmphp_add_resource (new_mem) < 0) {
+					newbus = alloc_error_bus (curr, 0, 0);
+					if (!newbus)
+						return -ENOMEM;
+					newbus->firstMem = new_mem;
+					++newbus->needMemUpdate;
+					new_mem->rangeno = -1;
+				}
+				debug ("Memory resource for device %x, bus %x, [%x - %x]\n", new_mem->devfunc, new_mem->busno, new_mem->start, new_mem->end);
+
+			} else if ((curr->rsrc_type & RESTYPE) == PFMASK) {
+				/* PFMemory resource */
+				new_pfmem = alloc_resources (curr);
+				if (!new_pfmem)
+					return -ENOMEM;
+				new_pfmem->type = PFMEM;
+				new_pfmem->fromMem = 0;
+				if (ibmphp_add_resource (new_pfmem) < 0) {
+					newbus = alloc_error_bus (curr, 0, 0);
+					if (!newbus)
+						return -ENOMEM;
+					newbus->firstPFMem = new_pfmem;
+					++newbus->needPFMemUpdate;
+					new_pfmem->rangeno = -1;
+				}
+
+				debug ("PFMemory resource for device %x, bus %x, [%x - %x]\n", new_pfmem->devfunc, new_pfmem->busno, new_pfmem->start, new_pfmem->end);
+			} else if ((curr->rsrc_type & RESTYPE) == IOMASK) {
+				/* IO resource */
+				new_io = alloc_resources (curr);
+				if (!new_io)
+					return -ENOMEM;
+				new_io->type = IO;
+
+				/*
+				 * if it didn't find the bus, means PCI dev
+				 * came b4 the Primary Bus info, so need to
+				 * create a bus rangeno becomes a problem...
+				 * Can assign a -1 and then update once the
+				 * range actually appears...
+				 */
+				if (ibmphp_add_resource (new_io) < 0) {
+					newbus = alloc_error_bus (curr, 0, 0);
+					if (!newbus)
+						return -ENOMEM;
+					newbus->firstIO = new_io;
+					++newbus->needIOUpdate;
+					new_io->rangeno = -1;
+				}
+				debug ("IO resource for device %x, bus %x, [%x - %x]\n", new_io->devfunc, new_io->busno, new_io->start, new_io->end);
+			}
+		}
+	}
+
+	list_for_each (tmp, &gbuses) {
+		bus_cur = list_entry (tmp, struct bus_node, bus_list);
+		/* This is to get info about PPB resources, since EBDA doesn't put this info into the primary bus info */
+		rc = update_bridge_ranges (&bus_cur);
+		if (rc)
+			return rc;
+	}
+	rc = once_over ();  /* This is to align ranges (so no -1) */
+	if (rc)
+		return rc;
+	return 0;
+}
+
+/********************************************************************************
+ * This function adds a range into a sorted list of ranges per bus for a particular
+ * range type, it then calls another routine to update the range numbers on the
+ * pci devices' resources for the appropriate resource
+ *
+ * Input: type of the resource, range to add, current bus
+ * Output: 0 or -1, bus and range ptrs 
+ ********************************************************************************/
+static int add_bus_range (int type, struct range_node *range, struct bus_node *bus_cur)
+{
+	struct range_node *range_cur = NULL;
+	struct range_node *range_prev;
+	int count = 0, i_init;
+	int noRanges = 0;
+
+	switch (type) {
+		case MEM:
+			range_cur = bus_cur->rangeMem;
+			noRanges = bus_cur->noMemRanges;
+			break;
+		case PFMEM:
+			range_cur = bus_cur->rangePFMem;
+			noRanges = bus_cur->noPFMemRanges;
+			break;
+		case IO:
+			range_cur = bus_cur->rangeIO;
+			noRanges = bus_cur->noIORanges;
+			break;
+	}
+
+	range_prev = NULL;
+	while (range_cur) {
+		if (range->start < range_cur->start)
+			break;
+		range_prev = range_cur;
+		range_cur = range_cur->next;
+		count = count + 1;
+	}
+	if (!count) {
+		/* our range will go at the beginning of the list */
+		switch (type) {
+			case MEM:
+				bus_cur->rangeMem = range;
+				break;
+			case PFMEM:
+				bus_cur->rangePFMem = range;
+				break;
+			case IO:
+				bus_cur->rangeIO = range;
+				break;
+		}
+		range->next = range_cur;
+		range->rangeno = 1;
+		i_init = 0;
+	} else if (!range_cur) {
+		/* our range will go at the end of the list */
+		range->next = NULL;
+		range_prev->next = range;
+		range->rangeno = range_prev->rangeno + 1;
+		return 0;
+	} else {
+		/* the range is in the middle */
+		range_prev->next = range;
+		range->next = range_cur;
+		range->rangeno = range_cur->rangeno;
+		i_init = range_prev->rangeno;
+	}
+
+	for (count = i_init; count < noRanges; ++count) {
+		++range_cur->rangeno;
+		range_cur = range_cur->next;
+	}
+
+	update_resources (bus_cur, type, i_init + 1);
+	return 0;
+}
+
+/*******************************************************************************
+ * This routine goes through the list of resources of type 'type' and updates
+ * the range numbers that they correspond to.  It was called from add_bus_range fnc
+ *
+ * Input: bus, type of the resource, the rangeno starting from which to update
+ ******************************************************************************/
+static void update_resources (struct bus_node *bus_cur, int type, int rangeno)
+{
+	struct resource_node *res = NULL;
+	u8 eol = 0;	/* end of list indicator */
+
+	switch (type) {
+		case MEM:
+			if (bus_cur->firstMem) 
+				res = bus_cur->firstMem;
+			break;
+		case PFMEM:
+			if (bus_cur->firstPFMem)
+				res = bus_cur->firstPFMem;
+			break;
+		case IO:
+			if (bus_cur->firstIO)
+				res = bus_cur->firstIO;
+			break;
+	}
+
+	if (res) {
+		while (res) {
+			if (res->rangeno == rangeno)
+				break;
+			if (res->next)
+				res = res->next;
+			else if (res->nextRange)
+				res = res->nextRange;
+			else {
+				eol = 1;
+				break;
+			}
+		}
+
+		if (!eol) {
+			/* found the range */
+			while (res) {
+				++res->rangeno;
+				res = res->next;
+			}
+		}
+	}
+}
+
+static void fix_me (struct resource_node *res, struct bus_node *bus_cur, struct range_node *range)
+{
+	char * str = "";
+	switch (res->type) {
+		case IO:
+			str = "io";
+			break;
+		case MEM:
+			str = "mem";
+			break;
+		case PFMEM:
+			str = "pfmem";
+			break;
+	}
+
+	while (res) {
+		if (res->rangeno == -1) {
+			while (range) {
+				if ((res->start >= range->start) && (res->end <= range->end)) {
+					res->rangeno = range->rangeno;
+					debug ("%s->rangeno in fix_resources is %d\n", str, res->rangeno);
+					switch (res->type) {
+						case IO:
+							--bus_cur->needIOUpdate;
+							break;
+						case MEM:
+							--bus_cur->needMemUpdate;
+							break;
+						case PFMEM:
+							--bus_cur->needPFMemUpdate;
+							break;
+					}
+					break;
+				}
+				range = range->next;
+			}
+		}
+		if (res->next)
+			res = res->next;
+		else
+			res = res->nextRange;
+	}
+
+}
+
+/*****************************************************************************
+ * This routine reassigns the range numbers to the resources that had a -1
+ * This case can happen only if upon initialization, resources taken by pci dev
+ * appear in EBDA before the resources allocated for that bus, since we don't
+ * know the range, we assign -1, and this routine is called after a new range
+ * is assigned to see the resources with unknown range belong to the added range
+ *
+ * Input: current bus
+ * Output: none, list of resources for that bus are fixed if can be
+ *******************************************************************************/
+static void fix_resources (struct bus_node *bus_cur)
+{
+	struct range_node *range;
+	struct resource_node *res;
+
+	debug ("%s - bus_cur->busno = %d\n", __func__, bus_cur->busno);
+
+	if (bus_cur->needIOUpdate) {
+		res = bus_cur->firstIO;
+		range = bus_cur->rangeIO;
+		fix_me (res, bus_cur, range);
+	}
+	if (bus_cur->needMemUpdate) {
+		res = bus_cur->firstMem;
+		range = bus_cur->rangeMem;
+		fix_me (res, bus_cur, range);
+	}
+	if (bus_cur->needPFMemUpdate) {
+		res = bus_cur->firstPFMem;
+		range = bus_cur->rangePFMem;
+		fix_me (res, bus_cur, range);
+	}
+}
+
+/*******************************************************************************
+ * This routine adds a resource to the list of resources to the appropriate bus 
+ * based on their resource type and sorted by their starting addresses.  It assigns
+ * the ptrs to next and nextRange if needed.
+ *
+ * Input: resource ptr
+ * Output: ptrs assigned (to the node)
+ * 0 or -1
+ *******************************************************************************/
+int ibmphp_add_resource (struct resource_node *res)
+{
+	struct resource_node *res_cur;
+	struct resource_node *res_prev;
+	struct bus_node *bus_cur;
+	struct range_node *range_cur = NULL;
+	struct resource_node *res_start = NULL;
+
+	debug ("%s - enter\n", __func__);
+
+	if (!res) {
+		err ("NULL passed to add\n");
+		return -ENODEV;
+	}
+	
+	bus_cur = find_bus_wprev (res->busno, NULL, 0);
+	
+	if (!bus_cur) {
+		/* didn't find a bus, smth's wrong!!! */
+		debug ("no bus in the system, either pci_dev's wrong or allocation failed\n");
+		return -ENODEV;
+	}
+
+	/* Normal case */
+	switch (res->type) {
+		case IO:
+			range_cur = bus_cur->rangeIO;
+			res_start = bus_cur->firstIO;
+			break;
+		case MEM:
+			range_cur = bus_cur->rangeMem;
+			res_start = bus_cur->firstMem;
+			break;
+		case PFMEM:
+			range_cur = bus_cur->rangePFMem;
+			res_start = bus_cur->firstPFMem;
+			break;
+		default:
+			err ("cannot read the type of the resource to add... problem\n");
+			return -EINVAL;
+	}
+	while (range_cur) {
+		if ((res->start >= range_cur->start) && (res->end <= range_cur->end)) {
+			res->rangeno = range_cur->rangeno;
+			break;
+		}
+		range_cur = range_cur->next;
+	}
+
+	/* !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
+	 * this is again the case of rangeno = -1
+	 * !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
+	 */
+
+	if (!range_cur) {
+		switch (res->type) {
+			case IO:
+				++bus_cur->needIOUpdate;					
+				break;
+			case MEM:
+				++bus_cur->needMemUpdate;
+				break;
+			case PFMEM:
+				++bus_cur->needPFMemUpdate;
+				break;
+		}
+		res->rangeno = -1;
+	}
+	
+	debug ("The range is %d\n", res->rangeno);
+	if (!res_start) {
+		/* no first{IO,Mem,Pfmem} on the bus, 1st IO/Mem/Pfmem resource ever */
+		switch (res->type) {
+			case IO:
+				bus_cur->firstIO = res;					
+				break;
+			case MEM:
+				bus_cur->firstMem = res;
+				break;
+			case PFMEM:
+				bus_cur->firstPFMem = res;
+				break;
+		}	
+		res->next = NULL;
+		res->nextRange = NULL;
+	} else {
+		res_cur = res_start;
+		res_prev = NULL;
+
+		debug ("res_cur->rangeno is %d\n", res_cur->rangeno);
+
+		while (res_cur) {
+			if (res_cur->rangeno >= res->rangeno)
+				break;
+			res_prev = res_cur;
+			if (res_cur->next)
+				res_cur = res_cur->next;
+			else
+				res_cur = res_cur->nextRange;
+		}
+
+		if (!res_cur) {
+			/* at the end of the resource list */
+			debug ("i should be here, [%x - %x]\n", res->start, res->end);
+			res_prev->nextRange = res;
+			res->next = NULL;
+			res->nextRange = NULL;
+		} else if (res_cur->rangeno == res->rangeno) {
+			/* in the same range */
+			while (res_cur) {
+				if (res->start < res_cur->start)
+					break;
+				res_prev = res_cur;
+				res_cur = res_cur->next;
+			}
+			if (!res_cur) {
+				/* the last resource in this range */
+				res_prev->next = res;
+				res->next = NULL;
+				res->nextRange = res_prev->nextRange;
+				res_prev->nextRange = NULL;
+			} else if (res->start < res_cur->start) {
+				/* at the beginning or middle of the range */
+				if (!res_prev)	{
+					switch (res->type) {
+						case IO:
+							bus_cur->firstIO = res;
+							break;
+						case MEM:
+							bus_cur->firstMem = res;
+							break;
+						case PFMEM:
+							bus_cur->firstPFMem = res;
+							break;
+					}
+				} else if (res_prev->rangeno == res_cur->rangeno)
+					res_prev->next = res;
+				else
+					res_prev->nextRange = res;
+
+				res->next = res_cur;
+				res->nextRange = NULL;
+			}
+		} else {
+			/* this is the case where it is 1st occurrence of the range */
+			if (!res_prev) {
+				/* at the beginning of the resource list */
+				res->next = NULL;
+				switch (res->type) {
+					case IO:
+						res->nextRange = bus_cur->firstIO;
+						bus_cur->firstIO = res;
+						break;
+					case MEM:
+						res->nextRange = bus_cur->firstMem;
+						bus_cur->firstMem = res;
+						break;
+					case PFMEM:
+						res->nextRange = bus_cur->firstPFMem;
+						bus_cur->firstPFMem = res;
+						break;
+				}
+			} else if (res_cur->rangeno > res->rangeno) {
+				/* in the middle of the resource list */
+				res_prev->nextRange = res;
+				res->next = NULL;
+				res->nextRange = res_cur;
+			}
+		}
+	}
+
+	debug ("%s - exit\n", __func__);
+	return 0;
+}
+
+/****************************************************************************
+ * This routine will remove the resource from the list of resources
+ *
+ * Input: io, mem, and/or pfmem resource to be deleted
+ * Ouput: modified resource list
+ *        0 or error code
+ ****************************************************************************/
+int ibmphp_remove_resource (struct resource_node *res)
+{
+	struct bus_node *bus_cur;
+	struct resource_node *res_cur = NULL;
+	struct resource_node *res_prev;
+	struct resource_node *mem_cur;
+	char * type = "";
+
+	if (!res)  {
+		err ("resource to remove is NULL\n");
+		return -ENODEV;
+	}
+
+	bus_cur = find_bus_wprev (res->busno, NULL, 0);
+
+	if (!bus_cur) {
+		err ("cannot find corresponding bus of the io resource to remove  "
+			"bailing out...\n");
+		return -ENODEV;
+	}
+
+	switch (res->type) {
+		case IO:
+			res_cur = bus_cur->firstIO;
+			type = "io";
+			break;
+		case MEM:
+			res_cur = bus_cur->firstMem;
+			type = "mem";
+			break;
+		case PFMEM:
+			res_cur = bus_cur->firstPFMem;
+			type = "pfmem";
+			break;
+		default:
+			err ("unknown type for resource to remove\n");
+			return -EINVAL;
+	}
+	res_prev = NULL;
+
+	while (res_cur) {
+		if ((res_cur->start == res->start) && (res_cur->end == res->end))
+			break;
+		res_prev = res_cur;
+		if (res_cur->next)
+			res_cur = res_cur->next;
+		else
+			res_cur = res_cur->nextRange;
+	}
+
+	if (!res_cur) {
+		if (res->type == PFMEM) {
+			/* 
+			 * case where pfmem might be in the PFMemFromMem list
+			 * so will also need to remove the corresponding mem
+			 * entry
+			 */
+			res_cur = bus_cur->firstPFMemFromMem;
+			res_prev = NULL;
+
+			while (res_cur) {
+				if ((res_cur->start == res->start) && (res_cur->end == res->end)) {
+					mem_cur = bus_cur->firstMem;
+					while (mem_cur) {
+						if ((mem_cur->start == res_cur->start)
+						    && (mem_cur->end == res_cur->end))
+							break;
+						if (mem_cur->next)
+							mem_cur = mem_cur->next;
+						else
+							mem_cur = mem_cur->nextRange;
+					}
+					if (!mem_cur) {
+						err ("cannot find corresponding mem node for pfmem...\n");
+						return -EINVAL;
+					}
+
+					ibmphp_remove_resource (mem_cur);
+					if (!res_prev)
+						bus_cur->firstPFMemFromMem = res_cur->next;
+					else
+						res_prev->next = res_cur->next;
+					kfree (res_cur);
+					return 0;
+				}
+				res_prev = res_cur;
+				if (res_cur->next)
+					res_cur = res_cur->next;
+				else
+					res_cur = res_cur->nextRange;
+			}
+			if (!res_cur) {
+				err ("cannot find pfmem to delete...\n");
+				return -EINVAL;
+			}
+		} else {
+			err ("the %s resource is not in the list to be deleted...\n", type);
+			return -EINVAL;
+		}
+	}
+	if (!res_prev) {
+		/* first device to be deleted */
+		if (res_cur->next) {
+			switch (res->type) {
+				case IO:
+					bus_cur->firstIO = res_cur->next;
+					break;
+				case MEM:
+					bus_cur->firstMem = res_cur->next;
+					break;
+				case PFMEM:
+					bus_cur->firstPFMem = res_cur->next;
+					break;
+			}
+		} else if (res_cur->nextRange) {
+			switch (res->type) {
+				case IO:
+					bus_cur->firstIO = res_cur->nextRange;
+					break;
+				case MEM:
+					bus_cur->firstMem = res_cur->nextRange;
+					break;
+				case PFMEM:
+					bus_cur->firstPFMem = res_cur->nextRange;
+					break;
+			}
+		} else {
+			switch (res->type) {
+				case IO:
+					bus_cur->firstIO = NULL;
+					break;
+				case MEM:
+					bus_cur->firstMem = NULL;
+					break;
+				case PFMEM:
+					bus_cur->firstPFMem = NULL;
+					break;
+			}
+		}
+		kfree (res_cur);
+		return 0;
+	} else {
+		if (res_cur->next) {
+			if (res_prev->rangeno == res_cur->rangeno)
+				res_prev->next = res_cur->next;
+			else
+				res_prev->nextRange = res_cur->next;
+		} else if (res_cur->nextRange) {
+			res_prev->next = NULL;
+			res_prev->nextRange = res_cur->nextRange;
+		} else {
+			res_prev->next = NULL;
+			res_prev->nextRange = NULL;
+		}
+		kfree (res_cur);
+		return 0;
+	}
+
+	return 0;
+}
+
+static struct range_node * find_range (struct bus_node *bus_cur, struct resource_node * res)
+{
+	struct range_node * range = NULL;
+
+	switch (res->type) {
+		case IO:
+			range = bus_cur->rangeIO;
+			break;
+		case MEM:
+			range = bus_cur->rangeMem;
+			break;
+		case PFMEM:
+			range = bus_cur->rangePFMem;
+			break;
+		default:
+			err ("cannot read resource type in find_range\n");
+	}
+
+	while (range) {
+		if (res->rangeno == range->rangeno)
+			break;
+		range = range->next;
+	}
+	return range;
+}
+
+/*****************************************************************************
+ * This routine will check to make sure the io/mem/pfmem->len that the device asked for 
+ * can fit w/i our list of available IO/MEM/PFMEM resources.  If cannot, returns -EINVAL,
+ * otherwise, returns 0
+ *
+ * Input: resource
+ * Ouput: the correct start and end address are inputted into the resource node,
+ *        0 or -EINVAL
+ *****************************************************************************/
+int ibmphp_check_resource (struct resource_node *res, u8 bridge)
+{
+	struct bus_node *bus_cur;
+	struct range_node *range = NULL;
+	struct resource_node *res_prev;
+	struct resource_node *res_cur = NULL;
+	u32 len_cur = 0, start_cur = 0, len_tmp = 0;
+	int noranges = 0;
+	u32 tmp_start;		/* this is to make sure start address is divisible by the length needed */
+	u32 tmp_divide;
+	u8 flag = 0;
+
+	if (!res)
+		return -EINVAL;
+
+	if (bridge) {
+		/* The rules for bridges are different, 4K divisible for IO, 1M for (pf)mem*/
+		if (res->type == IO)
+			tmp_divide = IOBRIDGE;
+		else
+			tmp_divide = MEMBRIDGE;
+	} else
+		tmp_divide = res->len;
+
+	bus_cur = find_bus_wprev (res->busno, NULL, 0);
+
+	if (!bus_cur) {
+		/* didn't find a bus, smth's wrong!!! */
+		debug ("no bus in the system, either pci_dev's wrong or allocation failed\n");
+		return -EINVAL;
+	}
+
+	debug ("%s - enter\n", __func__);
+	debug ("bus_cur->busno is %d\n", bus_cur->busno);
+
+	/* This is a quick fix to not mess up with the code very much.  i.e.,
+	 * 2000-2fff, len = 1000, but when we compare, we need it to be fff */
+	res->len -= 1;
+
+	switch (res->type) {
+		case IO:
+			res_cur = bus_cur->firstIO;
+			noranges = bus_cur->noIORanges;
+			break;
+		case MEM:
+			res_cur = bus_cur->firstMem;
+			noranges = bus_cur->noMemRanges;
+			break;
+		case PFMEM:
+			res_cur = bus_cur->firstPFMem;
+			noranges = bus_cur->noPFMemRanges;
+			break;
+		default:
+			err ("wrong type of resource to check\n");
+			return -EINVAL;
+	}
+	res_prev = NULL;
+
+	while (res_cur) {
+		range = find_range (bus_cur, res_cur);
+		debug ("%s - rangeno = %d\n", __func__, res_cur->rangeno);
+
+		if (!range) {
+			err ("no range for the device exists... bailing out...\n");
+			return -EINVAL;
+		}
+
+		/* found our range */
+		if (!res_prev) {
+			/* first time in the loop */
+			if ((res_cur->start != range->start) && ((len_tmp = res_cur->start - 1 - range->start) >= res->len)) {
+				debug ("len_tmp = %x\n", len_tmp);
+
+				if ((len_tmp < len_cur) || (len_cur == 0)) {
+
+					if ((range->start % tmp_divide) == 0) {
+						/* just perfect, starting address is divisible by length */
+						flag = 1;
+						len_cur = len_tmp;
+						start_cur = range->start;
+					} else {
+						/* Needs adjusting */
+						tmp_start = range->start;
+						flag = 0;
+
+						while ((len_tmp = res_cur->start - 1 - tmp_start) >= res->len) {
+							if ((tmp_start % tmp_divide) == 0) {
+								flag = 1;
+								len_cur = len_tmp;
+								start_cur = tmp_start;
+								break;
+							}
+							tmp_start += tmp_divide - tmp_start % tmp_divide;
+							if (tmp_start >= res_cur->start - 1)
+								break;
+						}
+					}
+			
+					if (flag && len_cur == res->len) {
+						debug ("but we are not here, right?\n");
+						res->start = start_cur;
+						res->len += 1; /* To restore the balance */
+						res->end = res->start + res->len - 1;
+						return 0;
+					}
+				}
+			}
+		}
+		if (!res_cur->next) {
+			/* last device on the range */
+			if ((range->end != res_cur->end) && ((len_tmp = range->end - (res_cur->end + 1)) >= res->len)) {
+				debug ("len_tmp = %x\n", len_tmp);
+				if ((len_tmp < len_cur) || (len_cur == 0)) {
+
+					if (((res_cur->end + 1) % tmp_divide) == 0) {
+						/* just perfect, starting address is divisible by length */
+						flag = 1;
+						len_cur = len_tmp;
+						start_cur = res_cur->end + 1;
+					} else {
+						/* Needs adjusting */
+						tmp_start = res_cur->end + 1;
+						flag = 0;
+
+						while ((len_tmp = range->end - tmp_start) >= res->len) {
+							if ((tmp_start % tmp_divide) == 0) {
+								flag = 1;
+								len_cur = len_tmp;
+								start_cur = tmp_start;
+								break;
+							}
+							tmp_start += tmp_divide - tmp_start % tmp_divide;
+							if (tmp_start >= range->end)
+								break;
+						}
+					}
+					if (flag && len_cur == res->len) {
+						res->start = start_cur;
+						res->len += 1; /* To restore the balance */
+						res->end = res->start + res->len - 1;
+						return 0;
+					}
+				}
+			}
+		}
+
+		if (res_prev) {
+			if (res_prev->rangeno != res_cur->rangeno) {
+				/* 1st device on this range */
+				if ((res_cur->start != range->start) && 
+					((len_tmp = res_cur->start - 1 - range->start) >= res->len)) {
+					if ((len_tmp < len_cur) || (len_cur == 0)) {
+						if ((range->start % tmp_divide) == 0) {	
+							/* just perfect, starting address is divisible by length */
+							flag = 1;
+							len_cur = len_tmp;
+							start_cur = range->start;
+						} else {
+							/* Needs adjusting */
+							tmp_start = range->start;
+							flag = 0;
+
+							while ((len_tmp = res_cur->start - 1 - tmp_start) >= res->len) {
+								if ((tmp_start % tmp_divide) == 0) {
+									flag = 1;
+									len_cur = len_tmp;
+									start_cur = tmp_start;
+									break;
+								}
+								tmp_start += tmp_divide - tmp_start % tmp_divide;
+								if (tmp_start >= res_cur->start - 1)
+									break;
+							}
+						}
+
+						if (flag && len_cur == res->len) {
+							res->start = start_cur;
+							res->len += 1; /* To restore the balance */
+							res->end = res->start + res->len - 1;
+							return 0;
+						}
+					}
+				}
+			} else {
+				/* in the same range */
+				if ((len_tmp = res_cur->start - 1 - res_prev->end - 1) >= res->len) {
+					if ((len_tmp < len_cur) || (len_cur == 0)) {
+						if (((res_prev->end + 1) % tmp_divide) == 0) {
+							/* just perfect, starting address's divisible by length */
+							flag = 1;
+							len_cur = len_tmp;
+							start_cur = res_prev->end + 1;
+						} else {
+							/* Needs adjusting */
+							tmp_start = res_prev->end + 1;
+							flag = 0;
+
+							while ((len_tmp = res_cur->start - 1 - tmp_start) >= res->len) {
+								if ((tmp_start % tmp_divide) == 0) {
+									flag = 1;
+									len_cur = len_tmp;
+									start_cur = tmp_start;
+									break;
+								}
+								tmp_start += tmp_divide - tmp_start % tmp_divide;
+								if (tmp_start >= res_cur->start - 1)
+									break;
+							}
+						}
+
+						if (flag && len_cur == res->len) {
+							res->start = start_cur;
+							res->len += 1; /* To restore the balance */
+							res->end = res->start + res->len - 1;
+							return 0;
+						}
+					}
+				}
+			}
+		}
+		/* end if (res_prev) */
+		res_prev = res_cur;
+		if (res_cur->next)
+			res_cur = res_cur->next;
+		else
+			res_cur = res_cur->nextRange;
+	}	/* end of while */
+
+
+	if (!res_prev) {
+		/* 1st device ever */
+		/* need to find appropriate range */
+		switch (res->type) {
+			case IO:
+				range = bus_cur->rangeIO;
+				break;
+			case MEM:
+				range = bus_cur->rangeMem;
+				break;
+			case PFMEM:
+				range = bus_cur->rangePFMem;
+				break;
+		}
+		while (range) {
+			if ((len_tmp = range->end - range->start) >= res->len) {
+				if ((len_tmp < len_cur) || (len_cur == 0)) {
+					if ((range->start % tmp_divide) == 0) {
+						/* just perfect, starting address's divisible by length */
+						flag = 1;
+						len_cur = len_tmp;
+						start_cur = range->start;
+					} else {
+						/* Needs adjusting */
+						tmp_start = range->start;
+						flag = 0;
+
+						while ((len_tmp = range->end - tmp_start) >= res->len) {
+							if ((tmp_start % tmp_divide) == 0) {
+								flag = 1;
+								len_cur = len_tmp;
+								start_cur = tmp_start;
+								break;
+							}
+							tmp_start += tmp_divide - tmp_start % tmp_divide;
+							if (tmp_start >= range->end)
+								break;
+						}
+					}
+
+					if (flag && len_cur == res->len) {
+						res->start = start_cur;
+						res->len += 1; /* To restore the balance */
+						res->end = res->start + res->len - 1;
+						return 0;
+					}
+				}
+			}
+			range = range->next;
+		}		/* end of while */
+
+		if ((!range) && (len_cur == 0)) {
+			/* have gone through the list of devices and ranges and haven't found n.e.thing */
+			err ("no appropriate range.. bailing out...\n");
+			return -EINVAL;
+		} else if (len_cur) {
+			res->start = start_cur;
+			res->len += 1; /* To restore the balance */
+			res->end = res->start + res->len - 1;
+			return 0;
+		}
+	}
+
+	if (!res_cur) {
+		debug ("prev->rangeno = %d, noranges = %d\n", res_prev->rangeno, noranges);
+		if (res_prev->rangeno < noranges) {
+			/* if there're more ranges out there to check */
+			switch (res->type) {
+				case IO:
+					range = bus_cur->rangeIO;
+					break;
+				case MEM:
+					range = bus_cur->rangeMem;
+					break;
+				case PFMEM:
+					range = bus_cur->rangePFMem;
+					break;
+			}
+			while (range) {
+				if ((len_tmp = range->end - range->start) >= res->len) {
+					if ((len_tmp < len_cur) || (len_cur == 0)) {
+						if ((range->start % tmp_divide) == 0) {
+							/* just perfect, starting address's divisible by length */
+							flag = 1;
+							len_cur = len_tmp;
+							start_cur = range->start;
+						} else {
+							/* Needs adjusting */
+							tmp_start = range->start;
+							flag = 0;
+
+							while ((len_tmp = range->end - tmp_start) >= res->len) {
+								if ((tmp_start % tmp_divide) == 0) {
+									flag = 1;
+									len_cur = len_tmp;
+									start_cur = tmp_start;
+									break;
+								}
+								tmp_start += tmp_divide - tmp_start % tmp_divide;
+								if (tmp_start >= range->end)
+									break;
+							}
+						}
+
+						if (flag && len_cur == res->len) {
+							res->start = start_cur;
+							res->len += 1; /* To restore the balance */
+							res->end = res->start + res->len - 1;
+							return 0;
+						}
+					}
+				}
+				range = range->next;
+			}	/* end of while */
+
+			if ((!range) && (len_cur == 0)) {
+				/* have gone through the list of devices and ranges and haven't found n.e.thing */
+				err ("no appropriate range.. bailing out...\n");
+				return -EINVAL;
+			} else if (len_cur) {
+				res->start = start_cur;
+				res->len += 1; /* To restore the balance */
+				res->end = res->start + res->len - 1;
+				return 0;
+			}
+		} else {
+			/* no more ranges to check on */
+			if (len_cur) {
+				res->start = start_cur;
+				res->len += 1; /* To restore the balance */
+				res->end = res->start + res->len - 1;
+				return 0;
+			} else {
+				/* have gone through the list of devices and haven't found n.e.thing */
+				err ("no appropriate range.. bailing out...\n");
+				return -EINVAL;
+			}
+		}
+	}	/* end if(!res_cur) */
+	return -EINVAL;
+}
+
+/********************************************************************************
+ * This routine is called from remove_card if the card contained PPB.
+ * It will remove all the resources on the bus as well as the bus itself
+ * Input: Bus
+ * Ouput: 0, -ENODEV
+ ********************************************************************************/
+int ibmphp_remove_bus (struct bus_node *bus, u8 parent_busno)
+{
+	struct resource_node *res_cur;
+	struct resource_node *res_tmp;
+	struct bus_node *prev_bus;
+	int rc;
+
+	prev_bus = find_bus_wprev (parent_busno, NULL, 0);	
+
+	if (!prev_bus) {
+		debug ("something terribly wrong. Cannot find parent bus to the one to remove\n");
+		return -ENODEV;
+	}
+
+	debug ("In ibmphp_remove_bus... prev_bus->busno is %x\n", prev_bus->busno);
+
+	rc = remove_ranges (bus, prev_bus);
+	if (rc)
+		return rc;
+
+	if (bus->firstIO) {
+		res_cur = bus->firstIO;
+		while (res_cur) {
+			res_tmp = res_cur;
+			if (res_cur->next)
+				res_cur = res_cur->next;
+			else
+				res_cur = res_cur->nextRange;
+			kfree (res_tmp);
+			res_tmp = NULL;
+		}
+		bus->firstIO = NULL;
+	}
+	if (bus->firstMem) {
+		res_cur = bus->firstMem;
+		while (res_cur) {
+			res_tmp = res_cur;
+			if (res_cur->next)
+				res_cur = res_cur->next;
+			else
+				res_cur = res_cur->nextRange;
+			kfree (res_tmp);
+			res_tmp = NULL;
+		}
+		bus->firstMem = NULL;
+	}
+	if (bus->firstPFMem) {
+		res_cur = bus->firstPFMem;
+		while (res_cur) {
+			res_tmp = res_cur;
+			if (res_cur->next)
+				res_cur = res_cur->next;
+			else
+				res_cur = res_cur->nextRange;
+			kfree (res_tmp);
+			res_tmp = NULL;
+		}
+		bus->firstPFMem = NULL;
+	}
+
+	if (bus->firstPFMemFromMem) {
+		res_cur = bus->firstPFMemFromMem;
+		while (res_cur) {
+			res_tmp = res_cur;
+			res_cur = res_cur->next;
+
+			kfree (res_tmp);
+			res_tmp = NULL;
+		}
+		bus->firstPFMemFromMem = NULL;
+	}
+
+	list_del (&bus->bus_list);
+	kfree (bus);
+	return 0;
+}
+
+/******************************************************************************
+ * This routine deletes the ranges from a given bus, and the entries from the 
+ * parent's bus in the resources
+ * Input: current bus, previous bus
+ * Output: 0, -EINVAL
+ ******************************************************************************/
+static int remove_ranges (struct bus_node *bus_cur, struct bus_node *bus_prev)
+{
+	struct range_node *range_cur;
+	struct range_node *range_tmp;
+	int i;
+	struct resource_node *res = NULL;
+
+	if (bus_cur->noIORanges) {
+		range_cur = bus_cur->rangeIO;
+		for (i = 0; i < bus_cur->noIORanges; i++) {
+			if (ibmphp_find_resource (bus_prev, range_cur->start, &res, IO) < 0)
+				return -EINVAL;
+			ibmphp_remove_resource (res);
+
+			range_tmp = range_cur;
+			range_cur = range_cur->next;
+			kfree (range_tmp);
+			range_tmp = NULL;
+		}
+		bus_cur->rangeIO = NULL;
+	}
+	if (bus_cur->noMemRanges) {
+		range_cur = bus_cur->rangeMem;
+		for (i = 0; i < bus_cur->noMemRanges; i++) {
+			if (ibmphp_find_resource (bus_prev, range_cur->start, &res, MEM) < 0) 
+				return -EINVAL;
+
+			ibmphp_remove_resource (res);
+			range_tmp = range_cur;
+			range_cur = range_cur->next;
+			kfree (range_tmp);
+			range_tmp = NULL;
+		}
+		bus_cur->rangeMem = NULL;
+	}
+	if (bus_cur->noPFMemRanges) {
+		range_cur = bus_cur->rangePFMem;
+		for (i = 0; i < bus_cur->noPFMemRanges; i++) {
+			if (ibmphp_find_resource (bus_prev, range_cur->start, &res, PFMEM) < 0) 
+				return -EINVAL;
+
+			ibmphp_remove_resource (res);
+			range_tmp = range_cur;
+			range_cur = range_cur->next;
+			kfree (range_tmp);
+			range_tmp = NULL;
+		}
+		bus_cur->rangePFMem = NULL;
+	}
+	return 0;
+}
+
+/*
+ * find the resource node in the bus 
+ * Input: Resource needed, start address of the resource, type of resource
+ */
+int ibmphp_find_resource (struct bus_node *bus, u32 start_address, struct resource_node **res, int flag)
+{
+	struct resource_node *res_cur = NULL;
+	char * type = "";
+
+	if (!bus) {
+		err ("The bus passed in NULL to find resource\n");
+		return -ENODEV;
+	}
+
+	switch (flag) {
+		case IO:
+			res_cur = bus->firstIO;
+			type = "io";
+			break;
+		case MEM:
+			res_cur = bus->firstMem;
+			type = "mem";
+			break;
+		case PFMEM:
+			res_cur = bus->firstPFMem;
+			type = "pfmem";
+			break;
+		default:
+			err ("wrong type of flag\n");
+			return -EINVAL;
+	}
+	
+	while (res_cur) {
+		if (res_cur->start == start_address) {
+			*res = res_cur;
+			break;
+		}
+		if (res_cur->next)
+			res_cur = res_cur->next;
+		else
+			res_cur = res_cur->nextRange;
+	}
+
+	if (!res_cur) {
+		if (flag == PFMEM) {
+			res_cur = bus->firstPFMemFromMem;
+			while (res_cur) {
+				if (res_cur->start == start_address) {
+					*res = res_cur;
+					break;
+				}
+				res_cur = res_cur->next;
+			}
+			if (!res_cur) {
+				debug ("SOS...cannot find %s resource in the bus.\n", type);
+				return -EINVAL;
+			}
+		} else {
+			debug ("SOS... cannot find %s resource in the bus.\n", type);
+			return -EINVAL;
+		}
+	}
+
+	if (*res)
+		debug ("*res->start = %x\n", (*res)->start);
+
+	return 0;
+}
+
+/***********************************************************************
+ * This routine will free the resource structures used by the
+ * system.  It is called from cleanup routine for the module
+ * Parameters: none
+ * Returns: none
+ ***********************************************************************/
+void ibmphp_free_resources (void)
+{
+	struct bus_node *bus_cur = NULL;
+	struct bus_node *bus_tmp;
+	struct range_node *range_cur;
+	struct range_node *range_tmp;
+	struct resource_node *res_cur;
+	struct resource_node *res_tmp;
+	struct list_head *tmp;
+	struct list_head *next;
+	int i = 0;
+	flags = 1;
+
+	list_for_each_safe (tmp, next, &gbuses) {
+		bus_cur = list_entry (tmp, struct bus_node, bus_list);
+		if (bus_cur->noIORanges) {
+			range_cur = bus_cur->rangeIO;
+			for (i = 0; i < bus_cur->noIORanges; i++) {
+				if (!range_cur)
+					break;
+				range_tmp = range_cur;
+				range_cur = range_cur->next;
+				kfree (range_tmp);
+				range_tmp = NULL;
+			}
+		}
+		if (bus_cur->noMemRanges) {
+			range_cur = bus_cur->rangeMem;
+			for (i = 0; i < bus_cur->noMemRanges; i++) {
+				if (!range_cur)
+					break;
+				range_tmp = range_cur;
+				range_cur = range_cur->next;
+				kfree (range_tmp);
+				range_tmp = NULL;
+			}
+		}
+		if (bus_cur->noPFMemRanges) {
+			range_cur = bus_cur->rangePFMem;
+			for (i = 0; i < bus_cur->noPFMemRanges; i++) {
+				if (!range_cur)
+					break;
+				range_tmp = range_cur;
+				range_cur = range_cur->next;
+				kfree (range_tmp);
+				range_tmp = NULL;
+			}
+		}
+
+		if (bus_cur->firstIO) {
+			res_cur = bus_cur->firstIO;
+			while (res_cur) {
+				res_tmp = res_cur;
+				if (res_cur->next)
+					res_cur = res_cur->next;
+				else
+					res_cur = res_cur->nextRange;
+				kfree (res_tmp);
+				res_tmp = NULL;
+			}
+			bus_cur->firstIO = NULL;
+		}
+		if (bus_cur->firstMem) {
+			res_cur = bus_cur->firstMem;
+			while (res_cur) {
+				res_tmp = res_cur;
+				if (res_cur->next)
+					res_cur = res_cur->next;
+				else
+					res_cur = res_cur->nextRange;
+				kfree (res_tmp);
+				res_tmp = NULL;
+			}
+			bus_cur->firstMem = NULL;
+		}
+		if (bus_cur->firstPFMem) {
+			res_cur = bus_cur->firstPFMem;
+			while (res_cur) {
+				res_tmp = res_cur;
+				if (res_cur->next)
+					res_cur = res_cur->next;
+				else
+					res_cur = res_cur->nextRange;
+				kfree (res_tmp);
+				res_tmp = NULL;
+			}
+			bus_cur->firstPFMem = NULL;
+		}
+
+		if (bus_cur->firstPFMemFromMem) {
+			res_cur = bus_cur->firstPFMemFromMem;
+			while (res_cur) {
+				res_tmp = res_cur;
+				res_cur = res_cur->next;
+
+				kfree (res_tmp);
+				res_tmp = NULL;
+			}
+			bus_cur->firstPFMemFromMem = NULL;
+		}
+
+		bus_tmp = bus_cur;
+		list_del (&bus_cur->bus_list);
+		kfree (bus_tmp);
+		bus_tmp = NULL;
+	}
+}
+
+/*********************************************************************************
+ * This function will go over the PFmem resources to check if the EBDA allocated
+ * pfmem out of memory buckets of the bus.  If so, it will change the range numbers
+ * and a flag to indicate that this resource is out of memory. It will also move the
+ * Pfmem out of the pfmem resource list to the PFMemFromMem list, and will create
+ * a new Mem node
+ * This routine is called right after initialization
+ *******************************************************************************/
+static int __init once_over (void)
+{
+	struct resource_node *pfmem_cur;
+	struct resource_node *pfmem_prev;
+	struct resource_node *mem;
+	struct bus_node *bus_cur;
+	struct list_head *tmp;
+
+	list_for_each (tmp, &gbuses) {
+		bus_cur = list_entry (tmp, struct bus_node, bus_list);
+		if ((!bus_cur->rangePFMem) && (bus_cur->firstPFMem)) {
+			for (pfmem_cur = bus_cur->firstPFMem, pfmem_prev = NULL; pfmem_cur; pfmem_prev = pfmem_cur, pfmem_cur = pfmem_cur->next) {
+				pfmem_cur->fromMem = 1;
+				if (pfmem_prev)
+					pfmem_prev->next = pfmem_cur->next;
+				else
+					bus_cur->firstPFMem = pfmem_cur->next;
+
+				if (!bus_cur->firstPFMemFromMem)
+					pfmem_cur->next = NULL;
+				else
+					/* we don't need to sort PFMemFromMem since we're using mem node for
+					   all the real work anyways, so just insert at the beginning of the
+					   list
+					 */
+					pfmem_cur->next = bus_cur->firstPFMemFromMem;
+
+				bus_cur->firstPFMemFromMem = pfmem_cur;
+
+				mem = kzalloc(sizeof(struct resource_node), GFP_KERNEL);
+				if (!mem) {
+					err ("out of system memory\n");
+					return -ENOMEM;
+				}
+				mem->type = MEM;
+				mem->busno = pfmem_cur->busno;
+				mem->devfunc = pfmem_cur->devfunc;
+				mem->start = pfmem_cur->start;
+				mem->end = pfmem_cur->end;
+				mem->len = pfmem_cur->len;
+				if (ibmphp_add_resource (mem) < 0)
+					err ("Trouble...trouble... EBDA allocated pfmem from mem, but system doesn't display it has this space... unless not PCI device...\n");
+				pfmem_cur->rangeno = mem->rangeno;
+			}	/* end for pfmem */
+		}	/* end if */
+	}	/* end list_for_each bus */
+	return 0; 
+}
+
+int ibmphp_add_pfmem_from_mem (struct resource_node *pfmem)
+{
+	struct bus_node *bus_cur = find_bus_wprev (pfmem->busno, NULL, 0);
+
+	if (!bus_cur) {
+		err ("cannot find bus of pfmem to add...\n");
+		return -ENODEV;
+	}
+
+	if (bus_cur->firstPFMemFromMem)
+		pfmem->next = bus_cur->firstPFMemFromMem;
+	else
+		pfmem->next = NULL;
+
+	bus_cur->firstPFMemFromMem = pfmem;
+
+	return 0;
+}
+
+/* This routine just goes through the buses to see if the bus already exists.
+ * It is called from ibmphp_find_sec_number, to find out a secondary bus number for
+ * bridged cards
+ * Parameters: bus_number
+ * Returns: Bus pointer or NULL
+ */
+struct bus_node *ibmphp_find_res_bus (u8 bus_number)
+{
+	return find_bus_wprev (bus_number, NULL, 0);
+}
+
+static struct bus_node *find_bus_wprev (u8 bus_number, struct bus_node **prev, u8 flag)
+{
+	struct bus_node *bus_cur;
+	struct list_head *tmp;
+	struct list_head *tmp_prev;
+
+	list_for_each (tmp, &gbuses) {
+		tmp_prev = tmp->prev;
+		bus_cur = list_entry (tmp, struct bus_node, bus_list);
+		if (flag) 
+			*prev = list_entry (tmp_prev, struct bus_node, bus_list);
+		if (bus_cur->busno == bus_number) 
+			return bus_cur;
+	}
+
+	return NULL;
+}
+
+void ibmphp_print_test (void)
+{
+	int i = 0;
+	struct bus_node *bus_cur = NULL;
+	struct range_node *range;
+	struct resource_node *res;
+	struct list_head *tmp;
+	
+	debug_pci ("*****************START**********************\n");
+
+	if ((!list_empty(&gbuses)) && flags) {
+		err ("The GBUSES is not NULL?!?!?!?!?\n");
+		return;
+	}
+
+	list_for_each (tmp, &gbuses) {
+		bus_cur = list_entry (tmp, struct bus_node, bus_list);
+		debug_pci ("This is bus # %d.  There are\n", bus_cur->busno);
+		debug_pci ("IORanges = %d\t", bus_cur->noIORanges);
+		debug_pci ("MemRanges = %d\t", bus_cur->noMemRanges);
+		debug_pci ("PFMemRanges = %d\n", bus_cur->noPFMemRanges);
+		debug_pci ("The IO Ranges are as follows:\n");
+		if (bus_cur->rangeIO) {
+			range = bus_cur->rangeIO;
+			for (i = 0; i < bus_cur->noIORanges; i++) {
+				debug_pci ("rangeno is %d\n", range->rangeno);
+				debug_pci ("[%x - %x]\n", range->start, range->end);
+				range = range->next;
+			}
+		}
+
+		debug_pci ("The Mem Ranges are as follows:\n");
+		if (bus_cur->rangeMem) {
+			range = bus_cur->rangeMem;
+			for (i = 0; i < bus_cur->noMemRanges; i++) {
+				debug_pci ("rangeno is %d\n", range->rangeno);
+				debug_pci ("[%x - %x]\n", range->start, range->end);
+				range = range->next;
+			}
+		}
+
+		debug_pci ("The PFMem Ranges are as follows:\n");
+
+		if (bus_cur->rangePFMem) {
+			range = bus_cur->rangePFMem;
+			for (i = 0; i < bus_cur->noPFMemRanges; i++) {
+				debug_pci ("rangeno is %d\n", range->rangeno);
+				debug_pci ("[%x - %x]\n", range->start, range->end);
+				range = range->next;
+			}
+		}
+
+		debug_pci ("The resources on this bus are as follows\n");
+
+		debug_pci ("IO...\n");
+		if (bus_cur->firstIO) {
+			res = bus_cur->firstIO;
+			while (res) {
+				debug_pci ("The range # is %d\n", res->rangeno);
+				debug_pci ("The bus, devfnc is %d, %x\n", res->busno, res->devfunc);
+				debug_pci ("[%x - %x], len=%x\n", res->start, res->end, res->len);
+				if (res->next)
+					res = res->next;
+				else if (res->nextRange)
+					res = res->nextRange;
+				else
+					break;
+			}
+		}
+		debug_pci ("Mem...\n");
+		if (bus_cur->firstMem) {
+			res = bus_cur->firstMem;
+			while (res) {
+				debug_pci ("The range # is %d\n", res->rangeno);
+				debug_pci ("The bus, devfnc is %d, %x\n", res->busno, res->devfunc);
+				debug_pci ("[%x - %x], len=%x\n", res->start, res->end, res->len);
+				if (res->next)
+					res = res->next;
+				else if (res->nextRange)
+					res = res->nextRange;
+				else
+					break;
+			}
+		}
+		debug_pci ("PFMem...\n");
+		if (bus_cur->firstPFMem) {
+			res = bus_cur->firstPFMem;
+			while (res) {
+				debug_pci ("The range # is %d\n", res->rangeno);
+				debug_pci ("The bus, devfnc is %d, %x\n", res->busno, res->devfunc);
+				debug_pci ("[%x - %x], len=%x\n", res->start, res->end, res->len);
+				if (res->next)
+					res = res->next;
+				else if (res->nextRange)
+					res = res->nextRange;
+				else
+					break;
+			}
+		}
+
+		debug_pci ("PFMemFromMem...\n");
+		if (bus_cur->firstPFMemFromMem) {
+			res = bus_cur->firstPFMemFromMem;
+			while (res) {
+				debug_pci ("The range # is %d\n", res->rangeno);
+				debug_pci ("The bus, devfnc is %d, %x\n", res->busno, res->devfunc);
+				debug_pci ("[%x - %x], len=%x\n", res->start, res->end, res->len);
+				res = res->next;
+			}
+		}
+	}
+	debug_pci ("***********************END***********************\n");
+}
+
+static int range_exists_already (struct range_node * range, struct bus_node * bus_cur, u8 type)
+{
+	struct range_node * range_cur = NULL;
+	switch (type) {
+		case IO:
+			range_cur = bus_cur->rangeIO;
+			break;
+		case MEM:
+			range_cur = bus_cur->rangeMem;
+			break;
+		case PFMEM:
+			range_cur = bus_cur->rangePFMem;
+			break;
+		default:
+			err ("wrong type passed to find out if range already exists\n");
+			return -ENODEV;
+	}
+
+	while (range_cur) {
+		if ((range_cur->start == range->start) && (range_cur->end == range->end))
+			return 1;
+		range_cur = range_cur->next;
+	}
+	
+	return 0;
+}
+
+/* This routine will read the windows for any PPB we have and update the
+ * range info for the secondary bus, and will also input this info into
+ * primary bus, since BIOS doesn't. This is for PPB that are in the system
+ * on bootup.  For bridged cards that were added during previous load of the
+ * driver, only the ranges and the bus structure are added, the devices are
+ * added from NVRAM
+ * Input: primary busno
+ * Returns: none
+ * Note: this function doesn't take into account IO restrictions etc,
+ *	 so will only work for bridges with no video/ISA devices behind them It
+ *	 also will not work for onboard PPB's that can have more than 1 *bus
+ *	 behind them All these are TO DO.
+ *	 Also need to add more error checkings... (from fnc returns etc)
+ */
+static int __init update_bridge_ranges (struct bus_node **bus)
+{
+	u8 sec_busno, device, function, hdr_type, start_io_address, end_io_address;
+	u16 vendor_id, upper_io_start, upper_io_end, start_mem_address, end_mem_address;
+	u32 start_address, end_address, upper_start, upper_end;
+	struct bus_node *bus_sec;
+	struct bus_node *bus_cur;
+	struct resource_node *io;
+	struct resource_node *mem;
+	struct resource_node *pfmem;
+	struct range_node *range;
+	unsigned int devfn;
+
+	bus_cur = *bus;
+	if (!bus_cur)
+		return -ENODEV;
+	ibmphp_pci_bus->number = bus_cur->busno;
+
+	debug ("inside %s\n", __func__);
+	debug ("bus_cur->busno = %x\n", bus_cur->busno);
+
+	for (device = 0; device < 32; device++) {
+		for (function = 0x00; function < 0x08; function++) {
+			devfn = PCI_DEVFN(device, function);
+			pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_VENDOR_ID, &vendor_id);
+
+			if (vendor_id != PCI_VENDOR_ID_NOTVALID) {
+				/* found correct device!!! */
+				pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_HEADER_TYPE, &hdr_type);
+
+				switch (hdr_type) {
+					case PCI_HEADER_TYPE_NORMAL:
+						function = 0x8;
+						break;
+					case PCI_HEADER_TYPE_MULTIDEVICE:
+						break;
+					case PCI_HEADER_TYPE_BRIDGE:
+						function = 0x8;
+					case PCI_HEADER_TYPE_MULTIBRIDGE:
+						/* We assume here that only 1 bus behind the bridge 
+						   TO DO: add functionality for several:
+						   temp = secondary;
+						   while (temp < subordinate) {
+						   ...
+						   temp++;
+						   }
+						 */
+						pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_SECONDARY_BUS, &sec_busno);
+						bus_sec = find_bus_wprev (sec_busno, NULL, 0); 
+						/* this bus structure doesn't exist yet, PPB was configured during previous loading of ibmphp */
+						if (!bus_sec) {
+							bus_sec = alloc_error_bus (NULL, sec_busno, 1);
+							/* the rest will be populated during NVRAM call */
+							return 0;
+						}
+						pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_IO_BASE, &start_io_address);
+						pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_IO_LIMIT, &end_io_address);
+						pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_IO_BASE_UPPER16, &upper_io_start);
+						pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_IO_LIMIT_UPPER16, &upper_io_end);
+						start_address = (start_io_address & PCI_IO_RANGE_MASK) << 8;
+						start_address |= (upper_io_start << 16);
+						end_address = (end_io_address & PCI_IO_RANGE_MASK) << 8;
+						end_address |= (upper_io_end << 16);
+
+						if ((start_address) && (start_address <= end_address)) {
+							range = kzalloc(sizeof(struct range_node), GFP_KERNEL);
+							if (!range) {
+								err ("out of system memory\n");
+								return -ENOMEM;
+							}
+							range->start = start_address;
+							range->end = end_address + 0xfff;
+
+							if (bus_sec->noIORanges > 0) {
+								if (!range_exists_already (range, bus_sec, IO)) {
+									add_bus_range (IO, range, bus_sec);
+									++bus_sec->noIORanges;
+								} else {
+									kfree (range);
+									range = NULL;
+								}
+							} else {
+								/* 1st IO Range on the bus */
+								range->rangeno = 1;
+								bus_sec->rangeIO = range;
+								++bus_sec->noIORanges;
+							}
+							fix_resources (bus_sec);
+
+							if (ibmphp_find_resource (bus_cur, start_address, &io, IO)) {
+								io = kzalloc(sizeof(struct resource_node), GFP_KERNEL);
+								if (!io) {
+									kfree (range);
+									err ("out of system memory\n");
+									return -ENOMEM;
+								}
+								io->type = IO;
+								io->busno = bus_cur->busno;
+								io->devfunc = ((device << 3) | (function & 0x7));
+								io->start = start_address;
+								io->end = end_address + 0xfff;
+								io->len = io->end - io->start + 1;
+								ibmphp_add_resource (io);
+							}
+						}	
+
+						pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_BASE, &start_mem_address);
+						pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_LIMIT, &end_mem_address);
+
+						start_address = 0x00000000 | (start_mem_address & PCI_MEMORY_RANGE_MASK) << 16;
+						end_address = 0x00000000 | (end_mem_address & PCI_MEMORY_RANGE_MASK) << 16;
+
+						if ((start_address) && (start_address <= end_address)) {
+
+							range = kzalloc(sizeof(struct range_node), GFP_KERNEL);
+							if (!range) {
+								err ("out of system memory\n");
+								return -ENOMEM;
+							}
+							range->start = start_address;
+							range->end = end_address + 0xfffff;
+
+							if (bus_sec->noMemRanges > 0) {
+								if (!range_exists_already (range, bus_sec, MEM)) {
+									add_bus_range (MEM, range, bus_sec);
+									++bus_sec->noMemRanges;
+								} else {
+									kfree (range);
+									range = NULL;
+								}
+							} else {
+								/* 1st Mem Range on the bus */
+								range->rangeno = 1;
+								bus_sec->rangeMem = range;
+								++bus_sec->noMemRanges;
+							}
+
+							fix_resources (bus_sec);
+
+							if (ibmphp_find_resource (bus_cur, start_address, &mem, MEM)) {
+								mem = kzalloc(sizeof(struct resource_node), GFP_KERNEL);
+								if (!mem) {
+									kfree (range);
+									err ("out of system memory\n");
+									return -ENOMEM;
+								}
+								mem->type = MEM;
+								mem->busno = bus_cur->busno;
+								mem->devfunc = ((device << 3) | (function & 0x7));
+								mem->start = start_address;
+								mem->end = end_address + 0xfffff;
+								mem->len = mem->end - mem->start + 1;
+								ibmphp_add_resource (mem);
+							}
+						}
+						pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_PREF_MEMORY_BASE, &start_mem_address);
+						pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_PREF_MEMORY_LIMIT, &end_mem_address);
+						pci_bus_read_config_dword (ibmphp_pci_bus, devfn, PCI_PREF_BASE_UPPER32, &upper_start);
+						pci_bus_read_config_dword (ibmphp_pci_bus, devfn, PCI_PREF_LIMIT_UPPER32, &upper_end);
+						start_address = 0x00000000 | (start_mem_address & PCI_MEMORY_RANGE_MASK) << 16;
+						end_address = 0x00000000 | (end_mem_address & PCI_MEMORY_RANGE_MASK) << 16;
+#if BITS_PER_LONG == 64
+						start_address |= ((long) upper_start) << 32;
+						end_address |= ((long) upper_end) << 32;
+#endif
+
+						if ((start_address) && (start_address <= end_address)) {
+
+							range = kzalloc(sizeof(struct range_node), GFP_KERNEL);
+							if (!range) {
+								err ("out of system memory\n");
+								return -ENOMEM;
+							}
+							range->start = start_address;
+							range->end = end_address + 0xfffff;
+
+							if (bus_sec->noPFMemRanges > 0) {
+								if (!range_exists_already (range, bus_sec, PFMEM)) {
+									add_bus_range (PFMEM, range, bus_sec);
+									++bus_sec->noPFMemRanges;
+								} else {
+									kfree (range);
+									range = NULL;
+								}
+							} else {
+								/* 1st PFMem Range on the bus */
+								range->rangeno = 1;
+								bus_sec->rangePFMem = range;
+								++bus_sec->noPFMemRanges;
+							}
+
+							fix_resources (bus_sec);
+							if (ibmphp_find_resource (bus_cur, start_address, &pfmem, PFMEM)) {
+								pfmem = kzalloc(sizeof(struct resource_node), GFP_KERNEL);
+								if (!pfmem) {
+									kfree (range);
+									err ("out of system memory\n");
+									return -ENOMEM;
+								}
+								pfmem->type = PFMEM;
+								pfmem->busno = bus_cur->busno;
+								pfmem->devfunc = ((device << 3) | (function & 0x7));
+								pfmem->start = start_address;
+								pfmem->end = end_address + 0xfffff;
+								pfmem->len = pfmem->end - pfmem->start + 1;
+								pfmem->fromMem = 0;
+
+								ibmphp_add_resource (pfmem);
+							}
+						}
+						break;
+				}	/* end of switch */
+			}	/* end if vendor */
+		}	/* end for function */
+	}	/* end for device */
+
+	bus = &bus_cur;
+	return 0;
+}
diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c
new file mode 100644
index 00000000..6d2eea93
--- /dev/null
+++ b/drivers/pci/hotplug/pci_hotplug_core.c
@@ -0,0 +1,572 @@
+/*
+ * PCI HotPlug Controller Core
+ *
+ * Copyright (C) 2001-2002 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001-2002 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <kristen.c.accardi@intel.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/pagemap.h>
+#include <linux/init.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <asm/uaccess.h>
+#include "../pci.h"
+
+#define MY_NAME	"pci_hotplug"
+
+#define dbg(fmt, arg...) do { if (debug) printk(KERN_DEBUG "%s: %s: " fmt , MY_NAME , __func__ , ## arg); } while (0)
+#define err(format, arg...) printk(KERN_ERR "%s: " format , MY_NAME , ## arg)
+#define info(format, arg...) printk(KERN_INFO "%s: " format , MY_NAME , ## arg)
+#define warn(format, arg...) printk(KERN_WARNING "%s: " format , MY_NAME , ## arg)
+
+
+/* local variables */
+static int debug;
+
+#define DRIVER_VERSION	"0.5"
+#define DRIVER_AUTHOR	"Greg Kroah-Hartman <greg@kroah.com>, Scott Murray <scottm@somanetworks.com>"
+#define DRIVER_DESC	"PCI Hot Plug PCI Core"
+
+
+//////////////////////////////////////////////////////////////////
+
+static LIST_HEAD(pci_hotplug_slot_list);
+static DEFINE_MUTEX(pci_hp_mutex);
+
+#ifdef CONFIG_HOTPLUG_PCI_CPCI
+extern int cpci_hotplug_init(int debug);
+extern void cpci_hotplug_exit(void);
+#else
+static inline int cpci_hotplug_init(int debug) { return 0; }
+static inline void cpci_hotplug_exit(void) { }
+#endif
+
+/* Weee, fun with macros... */
+#define GET_STATUS(name,type)	\
+static int get_##name (struct hotplug_slot *slot, type *value)		\
+{									\
+	struct hotplug_slot_ops *ops = slot->ops;			\
+	int retval = 0;							\
+	if (!try_module_get(ops->owner))				\
+		return -ENODEV;						\
+	if (ops->get_##name)						\
+		retval = ops->get_##name(slot, value);			\
+	else								\
+		*value = slot->info->name;				\
+	module_put(ops->owner);						\
+	return retval;							\
+}
+
+GET_STATUS(power_status, u8)
+GET_STATUS(attention_status, u8)
+GET_STATUS(latch_status, u8)
+GET_STATUS(adapter_status, u8)
+
+static ssize_t power_read_file(struct pci_slot *slot, char *buf)
+{
+	int retval;
+	u8 value;
+
+	retval = get_power_status(slot->hotplug, &value);
+	if (retval)
+		goto exit;
+	retval = sprintf (buf, "%d\n", value);
+exit:
+	return retval;
+}
+
+static ssize_t power_write_file(struct pci_slot *pci_slot, const char *buf,
+		size_t count)
+{
+	struct hotplug_slot *slot = pci_slot->hotplug;
+	unsigned long lpower;
+	u8 power;
+	int retval = 0;
+
+	lpower = simple_strtoul (buf, NULL, 10);
+	power = (u8)(lpower & 0xff);
+	dbg ("power = %d\n", power);
+
+	if (!try_module_get(slot->ops->owner)) {
+		retval = -ENODEV;
+		goto exit;
+	}
+	switch (power) {
+		case 0:
+			if (slot->ops->disable_slot)
+				retval = slot->ops->disable_slot(slot);
+			break;
+
+		case 1:
+			if (slot->ops->enable_slot)
+				retval = slot->ops->enable_slot(slot);
+			break;
+
+		default:
+			err ("Illegal value specified for power\n");
+			retval = -EINVAL;
+	}
+	module_put(slot->ops->owner);
+
+exit:	
+	if (retval)
+		return retval;
+	return count;
+}
+
+static struct pci_slot_attribute hotplug_slot_attr_power = {
+	.attr = {.name = "power", .mode = S_IFREG | S_IRUGO | S_IWUSR},
+	.show = power_read_file,
+	.store = power_write_file
+};
+
+static ssize_t attention_read_file(struct pci_slot *slot, char *buf)
+{
+	int retval;
+	u8 value;
+
+	retval = get_attention_status(slot->hotplug, &value);
+	if (retval)
+		goto exit;
+	retval = sprintf(buf, "%d\n", value);
+
+exit:
+	return retval;
+}
+
+static ssize_t attention_write_file(struct pci_slot *slot, const char *buf,
+		size_t count)
+{
+	struct hotplug_slot_ops *ops = slot->hotplug->ops;
+	unsigned long lattention;
+	u8 attention;
+	int retval = 0;
+
+	lattention = simple_strtoul (buf, NULL, 10);
+	attention = (u8)(lattention & 0xff);
+	dbg (" - attention = %d\n", attention);
+
+	if (!try_module_get(ops->owner)) {
+		retval = -ENODEV;
+		goto exit;
+	}
+	if (ops->set_attention_status)
+		retval = ops->set_attention_status(slot->hotplug, attention);
+	module_put(ops->owner);
+
+exit:	
+	if (retval)
+		return retval;
+	return count;
+}
+
+static struct pci_slot_attribute hotplug_slot_attr_attention = {
+	.attr = {.name = "attention", .mode = S_IFREG | S_IRUGO | S_IWUSR},
+	.show = attention_read_file,
+	.store = attention_write_file
+};
+
+static ssize_t latch_read_file(struct pci_slot *slot, char *buf)
+{
+	int retval;
+	u8 value;
+
+	retval = get_latch_status(slot->hotplug, &value);
+	if (retval)
+		goto exit;
+	retval = sprintf (buf, "%d\n", value);
+
+exit:
+	return retval;
+}
+
+static struct pci_slot_attribute hotplug_slot_attr_latch = {
+	.attr = {.name = "latch", .mode = S_IFREG | S_IRUGO},
+	.show = latch_read_file,
+};
+
+static ssize_t presence_read_file(struct pci_slot *slot, char *buf)
+{
+	int retval;
+	u8 value;
+
+	retval = get_adapter_status(slot->hotplug, &value);
+	if (retval)
+		goto exit;
+	retval = sprintf (buf, "%d\n", value);
+
+exit:
+	return retval;
+}
+
+static struct pci_slot_attribute hotplug_slot_attr_presence = {
+	.attr = {.name = "adapter", .mode = S_IFREG | S_IRUGO},
+	.show = presence_read_file,
+};
+
+static ssize_t test_write_file(struct pci_slot *pci_slot, const char *buf,
+		size_t count)
+{
+	struct hotplug_slot *slot = pci_slot->hotplug;
+	unsigned long ltest;
+	u32 test;
+	int retval = 0;
+
+	ltest = simple_strtoul (buf, NULL, 10);
+	test = (u32)(ltest & 0xffffffff);
+	dbg ("test = %d\n", test);
+
+	if (!try_module_get(slot->ops->owner)) {
+		retval = -ENODEV;
+		goto exit;
+	}
+	if (slot->ops->hardware_test)
+		retval = slot->ops->hardware_test(slot, test);
+	module_put(slot->ops->owner);
+
+exit:	
+	if (retval)
+		return retval;
+	return count;
+}
+
+static struct pci_slot_attribute hotplug_slot_attr_test = {
+	.attr = {.name = "test", .mode = S_IFREG | S_IRUGO | S_IWUSR},
+	.store = test_write_file
+};
+
+static bool has_power_file(struct pci_slot *pci_slot)
+{
+	struct hotplug_slot *slot = pci_slot->hotplug;
+	if ((!slot) || (!slot->ops))
+		return false;
+	if ((slot->ops->enable_slot) ||
+	    (slot->ops->disable_slot) ||
+	    (slot->ops->get_power_status))
+		return true;
+	return false;
+}
+
+static bool has_attention_file(struct pci_slot *pci_slot)
+{
+	struct hotplug_slot *slot = pci_slot->hotplug;
+	if ((!slot) || (!slot->ops))
+		return false;
+	if ((slot->ops->set_attention_status) ||
+	    (slot->ops->get_attention_status))
+		return true;
+	return false;
+}
+
+static bool has_latch_file(struct pci_slot *pci_slot)
+{
+	struct hotplug_slot *slot = pci_slot->hotplug;
+	if ((!slot) || (!slot->ops))
+		return false;
+	if (slot->ops->get_latch_status)
+		return true;
+	return false;
+}
+
+static bool has_adapter_file(struct pci_slot *pci_slot)
+{
+	struct hotplug_slot *slot = pci_slot->hotplug;
+	if ((!slot) || (!slot->ops))
+		return false;
+	if (slot->ops->get_adapter_status)
+		return true;
+	return false;
+}
+
+static bool has_test_file(struct pci_slot *pci_slot)
+{
+	struct hotplug_slot *slot = pci_slot->hotplug;
+	if ((!slot) || (!slot->ops))
+		return false;
+	if (slot->ops->hardware_test)
+		return true;
+	return false;
+}
+
+static int fs_add_slot(struct pci_slot *slot)
+{
+	int retval = 0;
+
+	/* Create symbolic link to the hotplug driver module */
+	pci_hp_create_module_link(slot);
+
+	if (has_power_file(slot)) {
+		retval = sysfs_create_file(&slot->kobj,
+					   &hotplug_slot_attr_power.attr);
+		if (retval)
+			goto exit_power;
+	}
+
+	if (has_attention_file(slot)) {
+		retval = sysfs_create_file(&slot->kobj,
+					   &hotplug_slot_attr_attention.attr);
+		if (retval)
+			goto exit_attention;
+	}
+
+	if (has_latch_file(slot)) {
+		retval = sysfs_create_file(&slot->kobj,
+					   &hotplug_slot_attr_latch.attr);
+		if (retval)
+			goto exit_latch;
+	}
+
+	if (has_adapter_file(slot)) {
+		retval = sysfs_create_file(&slot->kobj,
+					   &hotplug_slot_attr_presence.attr);
+		if (retval)
+			goto exit_adapter;
+	}
+
+	if (has_test_file(slot)) {
+		retval = sysfs_create_file(&slot->kobj,
+					   &hotplug_slot_attr_test.attr);
+		if (retval)
+			goto exit_test;
+	}
+
+	goto exit;
+
+exit_test:
+	if (has_adapter_file(slot))
+		sysfs_remove_file(&slot->kobj,
+				  &hotplug_slot_attr_presence.attr);
+exit_adapter:
+	if (has_latch_file(slot))
+		sysfs_remove_file(&slot->kobj, &hotplug_slot_attr_latch.attr);
+exit_latch:
+	if (has_attention_file(slot))
+		sysfs_remove_file(&slot->kobj,
+				  &hotplug_slot_attr_attention.attr);
+exit_attention:
+	if (has_power_file(slot))
+		sysfs_remove_file(&slot->kobj, &hotplug_slot_attr_power.attr);
+exit_power:
+	pci_hp_remove_module_link(slot);
+exit:
+	return retval;
+}
+
+static void fs_remove_slot(struct pci_slot *slot)
+{
+	if (has_power_file(slot))
+		sysfs_remove_file(&slot->kobj, &hotplug_slot_attr_power.attr);
+
+	if (has_attention_file(slot))
+		sysfs_remove_file(&slot->kobj,
+				  &hotplug_slot_attr_attention.attr);
+
+	if (has_latch_file(slot))
+		sysfs_remove_file(&slot->kobj, &hotplug_slot_attr_latch.attr);
+
+	if (has_adapter_file(slot))
+		sysfs_remove_file(&slot->kobj,
+				  &hotplug_slot_attr_presence.attr);
+
+	if (has_test_file(slot))
+		sysfs_remove_file(&slot->kobj, &hotplug_slot_attr_test.attr);
+
+	pci_hp_remove_module_link(slot);
+}
+
+static struct hotplug_slot *get_slot_from_name (const char *name)
+{
+	struct hotplug_slot *slot;
+	struct list_head *tmp;
+
+	list_for_each (tmp, &pci_hotplug_slot_list) {
+		slot = list_entry (tmp, struct hotplug_slot, slot_list);
+		if (strcmp(hotplug_slot_name(slot), name) == 0)
+			return slot;
+	}
+	return NULL;
+}
+
+/**
+ * __pci_hp_register - register a hotplug_slot with the PCI hotplug subsystem
+ * @bus: bus this slot is on
+ * @slot: pointer to the &struct hotplug_slot to register
+ * @devnr: device number
+ * @name: name registered with kobject core
+ * @owner: caller module owner
+ * @mod_name: caller module name
+ *
+ * Registers a hotplug slot with the pci hotplug subsystem, which will allow
+ * userspace interaction to the slot.
+ *
+ * Returns 0 if successful, anything else for an error.
+ */
+int __pci_hp_register(struct hotplug_slot *slot, struct pci_bus *bus,
+		      int devnr, const char *name,
+		      struct module *owner, const char *mod_name)
+{
+	int result;
+	struct pci_slot *pci_slot;
+
+	if (slot == NULL)
+		return -ENODEV;
+	if ((slot->info == NULL) || (slot->ops == NULL))
+		return -EINVAL;
+	if (slot->release == NULL) {
+		dbg("Why are you trying to register a hotplug slot "
+		    "without a proper release function?\n");
+		return -EINVAL;
+	}
+
+	slot->ops->owner = owner;
+	slot->ops->mod_name = mod_name;
+
+	mutex_lock(&pci_hp_mutex);
+	/*
+	 * No problems if we call this interface from both ACPI_PCI_SLOT
+	 * driver and call it here again. If we've already created the
+	 * pci_slot, the interface will simply bump the refcount.
+	 */
+	pci_slot = pci_create_slot(bus, devnr, name, slot);
+	if (IS_ERR(pci_slot)) {
+		result = PTR_ERR(pci_slot);
+		goto out;
+	}
+
+	slot->pci_slot = pci_slot;
+	pci_slot->hotplug = slot;
+
+	list_add(&slot->slot_list, &pci_hotplug_slot_list);
+
+	result = fs_add_slot(pci_slot);
+	kobject_uevent(&pci_slot->kobj, KOBJ_ADD);
+	dbg("Added slot %s to the list\n", name);
+out:
+	mutex_unlock(&pci_hp_mutex);
+	return result;
+}
+
+/**
+ * pci_hp_deregister - deregister a hotplug_slot with the PCI hotplug subsystem
+ * @hotplug: pointer to the &struct hotplug_slot to deregister
+ *
+ * The @slot must have been registered with the pci hotplug subsystem
+ * previously with a call to pci_hp_register().
+ *
+ * Returns 0 if successful, anything else for an error.
+ */
+int pci_hp_deregister(struct hotplug_slot *hotplug)
+{
+	struct hotplug_slot *temp;
+	struct pci_slot *slot;
+
+	if (!hotplug)
+		return -ENODEV;
+
+	mutex_lock(&pci_hp_mutex);
+	temp = get_slot_from_name(hotplug_slot_name(hotplug));
+	if (temp != hotplug) {
+		mutex_unlock(&pci_hp_mutex);
+		return -ENODEV;
+	}
+
+	list_del(&hotplug->slot_list);
+
+	slot = hotplug->pci_slot;
+	fs_remove_slot(slot);
+	dbg("Removed slot %s from the list\n", hotplug_slot_name(hotplug));
+
+	hotplug->release(hotplug);
+	slot->hotplug = NULL;
+	pci_destroy_slot(slot);
+	mutex_unlock(&pci_hp_mutex);
+
+	return 0;
+}
+
+/**
+ * pci_hp_change_slot_info - changes the slot's information structure in the core
+ * @hotplug: pointer to the slot whose info has changed
+ * @info: pointer to the info copy into the slot's info structure
+ *
+ * @slot must have been registered with the pci 
+ * hotplug subsystem previously with a call to pci_hp_register().
+ *
+ * Returns 0 if successful, anything else for an error.
+ */
+int __must_check pci_hp_change_slot_info(struct hotplug_slot *hotplug,
+					 struct hotplug_slot_info *info)
+{
+	struct pci_slot *slot;
+	if (!hotplug || !info)
+		return -ENODEV;
+	slot = hotplug->pci_slot;
+
+	memcpy(hotplug->info, info, sizeof(struct hotplug_slot_info));
+
+	return 0;
+}
+
+static int __init pci_hotplug_init (void)
+{
+	int result;
+
+	result = cpci_hotplug_init(debug);
+	if (result) {
+		err ("cpci_hotplug_init with error %d\n", result);
+		goto err_cpci;
+	}
+
+	info (DRIVER_DESC " version: " DRIVER_VERSION "\n");
+
+err_cpci:
+	return result;
+}
+
+static void __exit pci_hotplug_exit (void)
+{
+	cpci_hotplug_exit();
+}
+
+module_init(pci_hotplug_init);
+module_exit(pci_hotplug_exit);
+
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+module_param(debug, bool, 0644);
+MODULE_PARM_DESC(debug, "Debugging mode enabled or not");
+
+EXPORT_SYMBOL_GPL(__pci_hp_register);
+EXPORT_SYMBOL_GPL(pci_hp_deregister);
+EXPORT_SYMBOL_GPL(pci_hp_change_slot_info);
diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
new file mode 100644
index 00000000..838f5710
--- /dev/null
+++ b/drivers/pci/hotplug/pciehp.h
@@ -0,0 +1,188 @@
+/*
+ * PCI Express Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ * Copyright (C) 2003-2004 Intel Corporation
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>, <kristen.c.accardi@intel.com>
+ *
+ */
+#ifndef _PCIEHP_H
+#define _PCIEHP_H
+
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/delay.h>
+#include <linux/sched.h>		/* signal_pending() */
+#include <linux/pcieport_if.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+
+#define MY_NAME	"pciehp"
+
+extern int pciehp_poll_mode;
+extern int pciehp_poll_time;
+extern int pciehp_debug;
+extern int pciehp_force;
+extern struct workqueue_struct *pciehp_wq;
+extern struct workqueue_struct *pciehp_ordered_wq;
+
+#define dbg(format, arg...)						\
+do {									\
+	if (pciehp_debug)						\
+		printk(KERN_DEBUG "%s: " format, MY_NAME , ## arg);	\
+} while (0)
+#define err(format, arg...)						\
+	printk(KERN_ERR "%s: " format, MY_NAME , ## arg)
+#define info(format, arg...)						\
+	printk(KERN_INFO "%s: " format, MY_NAME , ## arg)
+#define warn(format, arg...)						\
+	printk(KERN_WARNING "%s: " format, MY_NAME , ## arg)
+
+#define ctrl_dbg(ctrl, format, arg...)					\
+	do {								\
+		if (pciehp_debug)					\
+			dev_printk(KERN_DEBUG, &ctrl->pcie->device,	\
+					format, ## arg);		\
+	} while (0)
+#define ctrl_err(ctrl, format, arg...)					\
+	dev_err(&ctrl->pcie->device, format, ## arg)
+#define ctrl_info(ctrl, format, arg...)					\
+	dev_info(&ctrl->pcie->device, format, ## arg)
+#define ctrl_warn(ctrl, format, arg...)					\
+	dev_warn(&ctrl->pcie->device, format, ## arg)
+
+#define SLOT_NAME_SIZE 10
+struct slot {
+	u8 state;
+	struct controller *ctrl;
+	struct hotplug_slot *hotplug_slot;
+	struct delayed_work work;	/* work for button event */
+	struct mutex lock;
+};
+
+struct event_info {
+	u32 event_type;
+	struct slot *p_slot;
+	struct work_struct work;
+};
+
+struct controller {
+	struct mutex ctrl_lock;		/* controller lock */
+	struct pcie_device *pcie;	/* PCI Express port service */
+	struct slot *slot;
+	wait_queue_head_t queue;	/* sleep & wake process */
+	u32 slot_cap;
+	struct timer_list poll_timer;
+	unsigned int cmd_busy:1;
+	unsigned int no_cmd_complete:1;
+	unsigned int link_active_reporting:1;
+	unsigned int notification_enabled:1;
+	unsigned int power_fault_detected;
+};
+
+#define INT_BUTTON_IGNORE		0
+#define INT_PRESENCE_ON			1
+#define INT_PRESENCE_OFF		2
+#define INT_SWITCH_CLOSE		3
+#define INT_SWITCH_OPEN			4
+#define INT_POWER_FAULT			5
+#define INT_POWER_FAULT_CLEAR		6
+#define INT_BUTTON_PRESS		7
+#define INT_BUTTON_RELEASE		8
+#define INT_BUTTON_CANCEL		9
+
+#define STATIC_STATE			0
+#define BLINKINGON_STATE		1
+#define BLINKINGOFF_STATE		2
+#define POWERON_STATE			3
+#define POWEROFF_STATE			4
+
+#define ATTN_BUTTN(ctrl)	((ctrl)->slot_cap & PCI_EXP_SLTCAP_ABP)
+#define POWER_CTRL(ctrl)	((ctrl)->slot_cap & PCI_EXP_SLTCAP_PCP)
+#define MRL_SENS(ctrl)		((ctrl)->slot_cap & PCI_EXP_SLTCAP_MRLSP)
+#define ATTN_LED(ctrl)		((ctrl)->slot_cap & PCI_EXP_SLTCAP_AIP)
+#define PWR_LED(ctrl)		((ctrl)->slot_cap & PCI_EXP_SLTCAP_PIP)
+#define HP_SUPR_RM(ctrl)	((ctrl)->slot_cap & PCI_EXP_SLTCAP_HPS)
+#define EMI(ctrl)		((ctrl)->slot_cap & PCI_EXP_SLTCAP_EIP)
+#define NO_CMD_CMPL(ctrl)	((ctrl)->slot_cap & PCI_EXP_SLTCAP_NCCS)
+#define PSN(ctrl)		((ctrl)->slot_cap >> 19)
+
+extern int pciehp_sysfs_enable_slot(struct slot *slot);
+extern int pciehp_sysfs_disable_slot(struct slot *slot);
+extern u8 pciehp_handle_attention_button(struct slot *p_slot);
+extern u8 pciehp_handle_switch_change(struct slot *p_slot);
+extern u8 pciehp_handle_presence_change(struct slot *p_slot);
+extern u8 pciehp_handle_power_fault(struct slot *p_slot);
+extern int pciehp_configure_device(struct slot *p_slot);
+extern int pciehp_unconfigure_device(struct slot *p_slot);
+extern void pciehp_queue_pushbutton_work(struct work_struct *work);
+struct controller *pcie_init(struct pcie_device *dev);
+int pcie_init_notification(struct controller *ctrl);
+int pciehp_enable_slot(struct slot *p_slot);
+int pciehp_disable_slot(struct slot *p_slot);
+int pcie_enable_notification(struct controller *ctrl);
+int pciehp_power_on_slot(struct slot *slot);
+int pciehp_power_off_slot(struct slot *slot);
+int pciehp_get_power_status(struct slot *slot, u8 *status);
+int pciehp_get_attention_status(struct slot *slot, u8 *status);
+
+int pciehp_set_attention_status(struct slot *slot, u8 status);
+int pciehp_get_latch_status(struct slot *slot, u8 *status);
+int pciehp_get_adapter_status(struct slot *slot, u8 *status);
+int pciehp_get_max_link_speed(struct slot *slot, enum pci_bus_speed *speed);
+int pciehp_get_max_link_width(struct slot *slot, enum pcie_link_width *val);
+int pciehp_get_cur_link_speed(struct slot *slot, enum pci_bus_speed *speed);
+int pciehp_get_cur_link_width(struct slot *slot, enum pcie_link_width *val);
+int pciehp_query_power_fault(struct slot *slot);
+void pciehp_green_led_on(struct slot *slot);
+void pciehp_green_led_off(struct slot *slot);
+void pciehp_green_led_blink(struct slot *slot);
+int pciehp_check_link_status(struct controller *ctrl);
+void pciehp_release_ctrl(struct controller *ctrl);
+
+static inline const char *slot_name(struct slot *slot)
+{
+	return hotplug_slot_name(slot->hotplug_slot);
+}
+
+#ifdef CONFIG_ACPI
+#include <acpi/acpi.h>
+#include <acpi/acpi_bus.h>
+#include <linux/pci-acpi.h>
+
+extern void __init pciehp_acpi_slot_detection_init(void);
+extern int pciehp_acpi_slot_detection_check(struct pci_dev *dev);
+
+static inline void pciehp_firmware_init(void)
+{
+	pciehp_acpi_slot_detection_init();
+}
+#else
+#define pciehp_firmware_init()				do {} while (0)
+static inline int pciehp_acpi_slot_detection_check(struct pci_dev *dev)
+{
+	return 0;
+}
+#endif 				/* CONFIG_ACPI */
+#endif				/* _PCIEHP_H */
diff --git a/drivers/pci/hotplug/pciehp_acpi.c b/drivers/pci/hotplug/pciehp_acpi.c
new file mode 100644
index 00000000..5f722622
--- /dev/null
+++ b/drivers/pci/hotplug/pciehp_acpi.c
@@ -0,0 +1,139 @@
+/*
+ * ACPI related functions for PCI Express Hot Plug driver.
+ *
+ * Copyright (C) 2008 Kenji Kaneshige
+ * Copyright (C) 2008 Fujitsu Limited.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ */
+
+#include <linux/acpi.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/slab.h>
+#include "pciehp.h"
+
+#define PCIEHP_DETECT_PCIE	(0)
+#define PCIEHP_DETECT_ACPI	(1)
+#define PCIEHP_DETECT_AUTO	(2)
+#define PCIEHP_DETECT_DEFAULT	PCIEHP_DETECT_AUTO
+
+struct dummy_slot {
+	u32 number;
+	struct list_head list;
+};
+
+static int slot_detection_mode;
+static char *pciehp_detect_mode;
+module_param(pciehp_detect_mode, charp, 0444);
+MODULE_PARM_DESC(pciehp_detect_mode,
+	 "Slot detection mode: pcie, acpi, auto\n"
+	 "  pcie          - Use PCIe based slot detection\n"
+	 "  acpi          - Use ACPI for slot detection\n"
+	 "  auto(default) - Auto select mode. Use acpi option if duplicate\n"
+	 "                  slot ids are found. Otherwise, use pcie option\n");
+
+int pciehp_acpi_slot_detection_check(struct pci_dev *dev)
+{
+	if (slot_detection_mode != PCIEHP_DETECT_ACPI)
+		return 0;
+	if (acpi_pci_detect_ejectable(DEVICE_ACPI_HANDLE(&dev->dev)))
+		return 0;
+	return -ENODEV;
+}
+
+static int __init parse_detect_mode(void)
+{
+	if (!pciehp_detect_mode)
+		return PCIEHP_DETECT_DEFAULT;
+	if (!strcmp(pciehp_detect_mode, "pcie"))
+		return PCIEHP_DETECT_PCIE;
+	if (!strcmp(pciehp_detect_mode, "acpi"))
+		return PCIEHP_DETECT_ACPI;
+	if (!strcmp(pciehp_detect_mode, "auto"))
+		return PCIEHP_DETECT_AUTO;
+	warn("bad specifier '%s' for pciehp_detect_mode. Use default\n",
+	     pciehp_detect_mode);
+	return PCIEHP_DETECT_DEFAULT;
+}
+
+static int __initdata dup_slot_id;
+static int __initdata acpi_slot_detected;
+static struct list_head __initdata dummy_slots = LIST_HEAD_INIT(dummy_slots);
+
+/* Dummy driver for dumplicate name detection */
+static int __init dummy_probe(struct pcie_device *dev)
+{
+	int pos;
+	u32 slot_cap;
+	acpi_handle handle;
+	struct dummy_slot *slot, *tmp;
+	struct pci_dev *pdev = dev->port;
+
+	pos = pci_pcie_cap(pdev);
+	if (!pos)
+		return -ENODEV;
+	pci_read_config_dword(pdev, pos + PCI_EXP_SLTCAP, &slot_cap);
+	slot = kzalloc(sizeof(*slot), GFP_KERNEL);
+	if (!slot)
+		return -ENOMEM;
+	slot->number = slot_cap >> 19;
+	list_for_each_entry(tmp, &dummy_slots, list) {
+		if (tmp->number == slot->number)
+			dup_slot_id++;
+	}
+	list_add_tail(&slot->list, &dummy_slots);
+	handle = DEVICE_ACPI_HANDLE(&pdev->dev);
+	if (!acpi_slot_detected && acpi_pci_detect_ejectable(handle))
+		acpi_slot_detected = 1;
+	return -ENODEV;         /* dummy driver always returns error */
+}
+
+static struct pcie_port_service_driver __initdata dummy_driver = {
+        .name           = "pciehp_dummy",
+	.port_type	= PCIE_ANY_PORT,
+	.service	= PCIE_PORT_SERVICE_HP,
+        .probe          = dummy_probe,
+};
+
+static int __init select_detection_mode(void)
+{
+	struct dummy_slot *slot, *tmp;
+	if (pcie_port_service_register(&dummy_driver))
+		return PCIEHP_DETECT_ACPI;
+	pcie_port_service_unregister(&dummy_driver);
+	list_for_each_entry_safe(slot, tmp, &dummy_slots, list) {
+		list_del(&slot->list);
+		kfree(slot);
+	}
+	if (acpi_slot_detected && dup_slot_id)
+		return PCIEHP_DETECT_ACPI;
+	return PCIEHP_DETECT_PCIE;
+}
+
+void __init pciehp_acpi_slot_detection_init(void)
+{
+	slot_detection_mode = parse_detect_mode();
+	if (slot_detection_mode != PCIEHP_DETECT_AUTO)
+		goto out;
+	slot_detection_mode = select_detection_mode();
+out:
+	if (slot_detection_mode == PCIEHP_DETECT_ACPI)
+		info("Using ACPI for slot detection.\n");
+}
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
new file mode 100644
index 00000000..7ac8358d
--- /dev/null
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -0,0 +1,376 @@
+/*
+ * PCI Express Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ * Copyright (C) 2003-2004 Intel Corporation
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>, <kristen.c.accardi@intel.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include "pciehp.h"
+#include <linux/interrupt.h>
+#include <linux/time.h>
+
+/* Global variables */
+int pciehp_debug;
+int pciehp_poll_mode;
+int pciehp_poll_time;
+int pciehp_force;
+struct workqueue_struct *pciehp_wq;
+struct workqueue_struct *pciehp_ordered_wq;
+
+#define DRIVER_VERSION	"0.4"
+#define DRIVER_AUTHOR	"Dan Zink <dan.zink@compaq.com>, Greg Kroah-Hartman <greg@kroah.com>, Dely Sy <dely.l.sy@intel.com>"
+#define DRIVER_DESC	"PCI Express Hot Plug Controller Driver"
+
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+
+module_param(pciehp_debug, bool, 0644);
+module_param(pciehp_poll_mode, bool, 0644);
+module_param(pciehp_poll_time, int, 0644);
+module_param(pciehp_force, bool, 0644);
+MODULE_PARM_DESC(pciehp_debug, "Debugging mode enabled or not");
+MODULE_PARM_DESC(pciehp_poll_mode, "Using polling mechanism for hot-plug events or not");
+MODULE_PARM_DESC(pciehp_poll_time, "Polling mechanism frequency, in seconds");
+MODULE_PARM_DESC(pciehp_force, "Force pciehp, even if OSHP is missing");
+
+#define PCIE_MODULE_NAME "pciehp"
+
+static int set_attention_status (struct hotplug_slot *slot, u8 value);
+static int enable_slot		(struct hotplug_slot *slot);
+static int disable_slot		(struct hotplug_slot *slot);
+static int get_power_status	(struct hotplug_slot *slot, u8 *value);
+static int get_attention_status	(struct hotplug_slot *slot, u8 *value);
+static int get_latch_status	(struct hotplug_slot *slot, u8 *value);
+static int get_adapter_status	(struct hotplug_slot *slot, u8 *value);
+
+/**
+ * release_slot - free up the memory used by a slot
+ * @hotplug_slot: slot to free
+ */
+static void release_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
+		 __func__, hotplug_slot_name(hotplug_slot));
+
+	kfree(hotplug_slot->ops);
+	kfree(hotplug_slot->info);
+	kfree(hotplug_slot);
+}
+
+static int init_slot(struct controller *ctrl)
+{
+	struct slot *slot = ctrl->slot;
+	struct hotplug_slot *hotplug = NULL;
+	struct hotplug_slot_info *info = NULL;
+	struct hotplug_slot_ops *ops = NULL;
+	char name[SLOT_NAME_SIZE];
+	int retval = -ENOMEM;
+
+	hotplug = kzalloc(sizeof(*hotplug), GFP_KERNEL);
+	if (!hotplug)
+		goto out;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		goto out;
+
+	/* Setup hotplug slot ops */
+	ops = kzalloc(sizeof(*ops), GFP_KERNEL);
+	if (!ops)
+		goto out;
+	ops->enable_slot = enable_slot;
+	ops->disable_slot = disable_slot;
+	ops->get_power_status = get_power_status;
+	ops->get_adapter_status = get_adapter_status;
+	if (MRL_SENS(ctrl))
+		ops->get_latch_status = get_latch_status;
+	if (ATTN_LED(ctrl)) {
+		ops->get_attention_status = get_attention_status;
+		ops->set_attention_status = set_attention_status;
+	}
+
+	/* register this slot with the hotplug pci core */
+	hotplug->info = info;
+	hotplug->private = slot;
+	hotplug->release = &release_slot;
+	hotplug->ops = ops;
+	slot->hotplug_slot = hotplug;
+	snprintf(name, SLOT_NAME_SIZE, "%u", PSN(ctrl));
+
+	ctrl_dbg(ctrl, "Registering domain:bus:dev=%04x:%02x:00 sun=%x\n",
+		 pci_domain_nr(ctrl->pcie->port->subordinate),
+		 ctrl->pcie->port->subordinate->number, PSN(ctrl));
+	retval = pci_hp_register(hotplug,
+				 ctrl->pcie->port->subordinate, 0, name);
+	if (retval)
+		ctrl_err(ctrl,
+			 "pci_hp_register failed with error %d\n", retval);
+out:
+	if (retval) {
+		kfree(ops);
+		kfree(info);
+		kfree(hotplug);
+	}
+	return retval;
+}
+
+static void cleanup_slot(struct controller *ctrl)
+{
+	pci_hp_deregister(ctrl->slot->hotplug_slot);
+}
+
+/*
+ * set_attention_status - Turns the Amber LED for a slot on, off or blink
+ */
+static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
+		  __func__, slot_name(slot));
+
+	return pciehp_set_attention_status(slot, status);
+}
+
+
+static int enable_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
+		 __func__, slot_name(slot));
+
+	return pciehp_sysfs_enable_slot(slot);
+}
+
+
+static int disable_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
+		  __func__, slot_name(slot));
+
+	return pciehp_sysfs_disable_slot(slot);
+}
+
+static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
+		  __func__, slot_name(slot));
+
+	return pciehp_get_power_status(slot, value);
+}
+
+static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
+		  __func__, slot_name(slot));
+
+	return pciehp_get_attention_status(slot, value);
+}
+
+static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
+		 __func__, slot_name(slot));
+
+	return pciehp_get_latch_status(slot, value);
+}
+
+static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
+		 __func__, slot_name(slot));
+
+	return pciehp_get_adapter_status(slot, value);
+}
+
+static int pciehp_probe(struct pcie_device *dev)
+{
+	int rc;
+	struct controller *ctrl;
+	struct slot *slot;
+	u8 occupied, poweron;
+
+	if (pciehp_force)
+		dev_info(&dev->device,
+			 "Bypassing BIOS check for pciehp use on %s\n",
+			 pci_name(dev->port));
+	else if (pciehp_acpi_slot_detection_check(dev->port))
+		goto err_out_none;
+
+	ctrl = pcie_init(dev);
+	if (!ctrl) {
+		dev_err(&dev->device, "Controller initialization failed\n");
+		goto err_out_none;
+	}
+	set_service_data(dev, ctrl);
+
+	/* Setup the slot information structures */
+	rc = init_slot(ctrl);
+	if (rc) {
+		if (rc == -EBUSY)
+			ctrl_warn(ctrl, "Slot already registered by another "
+				  "hotplug driver\n");
+		else
+			ctrl_err(ctrl, "Slot initialization failed\n");
+		goto err_out_release_ctlr;
+	}
+
+	/* Enable events after we have setup the data structures */
+	rc = pcie_init_notification(ctrl);
+	if (rc) {
+		ctrl_err(ctrl, "Notification initialization failed\n");
+		goto err_out_free_ctrl_slot;
+	}
+
+	/* Check if slot is occupied */
+	slot = ctrl->slot;
+	pciehp_get_adapter_status(slot, &occupied);
+	pciehp_get_power_status(slot, &poweron);
+	if (occupied && pciehp_force)
+		pciehp_enable_slot(slot);
+	/* If empty slot's power status is on, turn power off */
+	if (!occupied && poweron && POWER_CTRL(ctrl))
+		pciehp_power_off_slot(slot);
+
+	return 0;
+
+err_out_free_ctrl_slot:
+	cleanup_slot(ctrl);
+err_out_release_ctlr:
+	pciehp_release_ctrl(ctrl);
+err_out_none:
+	return -ENODEV;
+}
+
+static void pciehp_remove(struct pcie_device *dev)
+{
+	struct controller *ctrl = get_service_data(dev);
+
+	cleanup_slot(ctrl);
+	pciehp_release_ctrl(ctrl);
+}
+
+#ifdef CONFIG_PM
+static int pciehp_suspend (struct pcie_device *dev)
+{
+	dev_info(&dev->device, "%s ENTRY\n", __func__);
+	return 0;
+}
+
+static int pciehp_resume (struct pcie_device *dev)
+{
+	dev_info(&dev->device, "%s ENTRY\n", __func__);
+	if (pciehp_force) {
+		struct controller *ctrl = get_service_data(dev);
+		struct slot *slot;
+		u8 status;
+
+		/* reinitialize the chipset's event detection logic */
+		pcie_enable_notification(ctrl);
+
+		slot = ctrl->slot;
+
+		/* Check if slot is occupied */
+		pciehp_get_adapter_status(slot, &status);
+		if (status)
+			pciehp_enable_slot(slot);
+		else
+			pciehp_disable_slot(slot);
+	}
+	return 0;
+}
+#endif /* PM */
+
+static struct pcie_port_service_driver hpdriver_portdrv = {
+	.name		= PCIE_MODULE_NAME,
+	.port_type	= PCIE_ANY_PORT,
+	.service	= PCIE_PORT_SERVICE_HP,
+
+	.probe		= pciehp_probe,
+	.remove		= pciehp_remove,
+
+#ifdef	CONFIG_PM
+	.suspend	= pciehp_suspend,
+	.resume		= pciehp_resume,
+#endif	/* PM */
+};
+
+static int __init pcied_init(void)
+{
+	int retval = 0;
+
+	pciehp_wq = alloc_workqueue("pciehp", 0, 0);
+	if (!pciehp_wq)
+		return -ENOMEM;
+
+	pciehp_ordered_wq = alloc_ordered_workqueue("pciehp_ordered", 0);
+	if (!pciehp_ordered_wq) {
+		destroy_workqueue(pciehp_wq);
+		return -ENOMEM;
+	}
+
+	pciehp_firmware_init();
+	retval = pcie_port_service_register(&hpdriver_portdrv);
+ 	dbg("pcie_port_service_register = %d\n", retval);
+  	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
+ 	if (retval) {
+		destroy_workqueue(pciehp_ordered_wq);
+		destroy_workqueue(pciehp_wq);
+		dbg("Failure to register service\n");
+	}
+	return retval;
+}
+
+static void __exit pcied_cleanup(void)
+{
+	dbg("unload_pciehpd()\n");
+	destroy_workqueue(pciehp_ordered_wq);
+	destroy_workqueue(pciehp_wq);
+	pcie_port_service_unregister(&hpdriver_portdrv);
+	info(DRIVER_DESC " version: " DRIVER_VERSION " unloaded\n");
+}
+
+module_init(pcied_init);
+module_exit(pcied_cleanup);
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
new file mode 100644
index 00000000..085dbb5f
--- /dev/null
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -0,0 +1,625 @@
+/*
+ * PCI Express Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ * Copyright (C) 2003-2004 Intel Corporation
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>, <kristen.c.accardi@intel.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include "../pci.h"
+#include "pciehp.h"
+
+static void interrupt_event_handler(struct work_struct *work);
+
+static int queue_interrupt_event(struct slot *p_slot, u32 event_type)
+{
+	struct event_info *info;
+
+	info = kmalloc(sizeof(*info), GFP_ATOMIC);
+	if (!info)
+		return -ENOMEM;
+
+	info->event_type = event_type;
+	info->p_slot = p_slot;
+	INIT_WORK(&info->work, interrupt_event_handler);
+
+	queue_work(pciehp_wq, &info->work);
+
+	return 0;
+}
+
+u8 pciehp_handle_attention_button(struct slot *p_slot)
+{
+	u32 event_type;
+	struct controller *ctrl = p_slot->ctrl;
+
+	/* Attention Button Change */
+	ctrl_dbg(ctrl, "Attention button interrupt received\n");
+
+	/*
+	 *  Button pressed - See if need to TAKE ACTION!!!
+	 */
+	ctrl_info(ctrl, "Button pressed on Slot(%s)\n", slot_name(p_slot));
+	event_type = INT_BUTTON_PRESS;
+
+	queue_interrupt_event(p_slot, event_type);
+
+	return 0;
+}
+
+u8 pciehp_handle_switch_change(struct slot *p_slot)
+{
+	u8 getstatus;
+	u32 event_type;
+	struct controller *ctrl = p_slot->ctrl;
+
+	/* Switch Change */
+	ctrl_dbg(ctrl, "Switch interrupt received\n");
+
+	pciehp_get_latch_status(p_slot, &getstatus);
+	if (getstatus) {
+		/*
+		 * Switch opened
+		 */
+		ctrl_info(ctrl, "Latch open on Slot(%s)\n", slot_name(p_slot));
+		event_type = INT_SWITCH_OPEN;
+	} else {
+		/*
+		 *  Switch closed
+		 */
+		ctrl_info(ctrl, "Latch close on Slot(%s)\n", slot_name(p_slot));
+		event_type = INT_SWITCH_CLOSE;
+	}
+
+	queue_interrupt_event(p_slot, event_type);
+
+	return 1;
+}
+
+u8 pciehp_handle_presence_change(struct slot *p_slot)
+{
+	u32 event_type;
+	u8 presence_save;
+	struct controller *ctrl = p_slot->ctrl;
+
+	/* Presence Change */
+	ctrl_dbg(ctrl, "Presence/Notify input change\n");
+
+	/* Switch is open, assume a presence change
+	 * Save the presence state
+	 */
+	pciehp_get_adapter_status(p_slot, &presence_save);
+	if (presence_save) {
+		/*
+		 * Card Present
+		 */
+		ctrl_info(ctrl, "Card present on Slot(%s)\n", slot_name(p_slot));
+		event_type = INT_PRESENCE_ON;
+	} else {
+		/*
+		 * Not Present
+		 */
+		ctrl_info(ctrl, "Card not present on Slot(%s)\n",
+			  slot_name(p_slot));
+		event_type = INT_PRESENCE_OFF;
+	}
+
+	queue_interrupt_event(p_slot, event_type);
+
+	return 1;
+}
+
+u8 pciehp_handle_power_fault(struct slot *p_slot)
+{
+	u32 event_type;
+	struct controller *ctrl = p_slot->ctrl;
+
+	/* power fault */
+	ctrl_dbg(ctrl, "Power fault interrupt received\n");
+	ctrl_err(ctrl, "Power fault on slot %s\n", slot_name(p_slot));
+	event_type = INT_POWER_FAULT;
+	ctrl_info(ctrl, "Power fault bit %x set\n", 0);
+	queue_interrupt_event(p_slot, event_type);
+
+	return 1;
+}
+
+/* The following routines constitute the bulk of the
+   hotplug controller logic
+ */
+
+static void set_slot_off(struct controller *ctrl, struct slot * pslot)
+{
+	/* turn off slot, turn on Amber LED, turn off Green LED if supported*/
+	if (POWER_CTRL(ctrl)) {
+		if (pciehp_power_off_slot(pslot)) {
+			ctrl_err(ctrl,
+				 "Issue of Slot Power Off command failed\n");
+			return;
+		}
+		/*
+		 * After turning power off, we must wait for at least 1 second
+		 * before taking any action that relies on power having been
+		 * removed from the slot/adapter.
+		 */
+		msleep(1000);
+	}
+
+	if (PWR_LED(ctrl))
+		pciehp_green_led_off(pslot);
+
+	if (ATTN_LED(ctrl)) {
+		if (pciehp_set_attention_status(pslot, 1)) {
+			ctrl_err(ctrl,
+				 "Issue of Set Attention Led command failed\n");
+			return;
+		}
+	}
+}
+
+/**
+ * board_added - Called after a board has been added to the system.
+ * @p_slot: &slot where board is added
+ *
+ * Turns power on for the board.
+ * Configures board.
+ */
+static int board_added(struct slot *p_slot)
+{
+	int retval = 0;
+	struct controller *ctrl = p_slot->ctrl;
+	struct pci_bus *parent = ctrl->pcie->port->subordinate;
+
+	if (POWER_CTRL(ctrl)) {
+		/* Power on slot */
+		retval = pciehp_power_on_slot(p_slot);
+		if (retval)
+			return retval;
+	}
+
+	if (PWR_LED(ctrl))
+		pciehp_green_led_blink(p_slot);
+
+	/* Check link training status */
+	retval = pciehp_check_link_status(ctrl);
+	if (retval) {
+		ctrl_err(ctrl, "Failed to check link status\n");
+		goto err_exit;
+	}
+
+	/* Check for a power fault */
+	if (ctrl->power_fault_detected || pciehp_query_power_fault(p_slot)) {
+		ctrl_err(ctrl, "Power fault on slot %s\n", slot_name(p_slot));
+		retval = -EIO;
+		goto err_exit;
+	}
+
+	retval = pciehp_configure_device(p_slot);
+	if (retval) {
+		ctrl_err(ctrl, "Cannot add device at %04x:%02x:00\n",
+			 pci_domain_nr(parent), parent->number);
+		goto err_exit;
+	}
+
+	if (PWR_LED(ctrl))
+		pciehp_green_led_on(p_slot);
+
+	return 0;
+
+err_exit:
+	set_slot_off(ctrl, p_slot);
+	return retval;
+}
+
+/**
+ * remove_board - Turns off slot and LEDs
+ * @p_slot: slot where board is being removed
+ */
+static int remove_board(struct slot *p_slot)
+{
+	int retval = 0;
+	struct controller *ctrl = p_slot->ctrl;
+
+	retval = pciehp_unconfigure_device(p_slot);
+	if (retval)
+		return retval;
+
+	if (POWER_CTRL(ctrl)) {
+		/* power off slot */
+		retval = pciehp_power_off_slot(p_slot);
+		if (retval) {
+			ctrl_err(ctrl,
+				 "Issue of Slot Disable command failed\n");
+			return retval;
+		}
+		/*
+		 * After turning power off, we must wait for at least 1 second
+		 * before taking any action that relies on power having been
+		 * removed from the slot/adapter.
+		 */
+		msleep(1000);
+	}
+
+	/* turn off Green LED */
+	if (PWR_LED(ctrl))
+		pciehp_green_led_off(p_slot);
+
+	return 0;
+}
+
+struct power_work_info {
+	struct slot *p_slot;
+	struct work_struct work;
+};
+
+/**
+ * pciehp_power_thread - handle pushbutton events
+ * @work: &struct work_struct describing work to be done
+ *
+ * Scheduled procedure to handle blocking stuff for the pushbuttons.
+ * Handles all pending events and exits.
+ */
+static void pciehp_power_thread(struct work_struct *work)
+{
+	struct power_work_info *info =
+		container_of(work, struct power_work_info, work);
+	struct slot *p_slot = info->p_slot;
+
+	mutex_lock(&p_slot->lock);
+	switch (p_slot->state) {
+	case POWEROFF_STATE:
+		mutex_unlock(&p_slot->lock);
+		ctrl_dbg(p_slot->ctrl,
+			 "Disabling domain:bus:device=%04x:%02x:00\n",
+			 pci_domain_nr(p_slot->ctrl->pcie->port->subordinate),
+			 p_slot->ctrl->pcie->port->subordinate->number);
+		pciehp_disable_slot(p_slot);
+		mutex_lock(&p_slot->lock);
+		p_slot->state = STATIC_STATE;
+		break;
+	case POWERON_STATE:
+		mutex_unlock(&p_slot->lock);
+		if (pciehp_enable_slot(p_slot) && PWR_LED(p_slot->ctrl))
+			pciehp_green_led_off(p_slot);
+		mutex_lock(&p_slot->lock);
+		p_slot->state = STATIC_STATE;
+		break;
+	default:
+		break;
+	}
+	mutex_unlock(&p_slot->lock);
+
+	kfree(info);
+}
+
+void pciehp_queue_pushbutton_work(struct work_struct *work)
+{
+	struct slot *p_slot = container_of(work, struct slot, work.work);
+	struct power_work_info *info;
+
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info) {
+		ctrl_err(p_slot->ctrl, "%s: Cannot allocate memory\n",
+			 __func__);
+		return;
+	}
+	info->p_slot = p_slot;
+	INIT_WORK(&info->work, pciehp_power_thread);
+
+	mutex_lock(&p_slot->lock);
+	switch (p_slot->state) {
+	case BLINKINGOFF_STATE:
+		p_slot->state = POWEROFF_STATE;
+		break;
+	case BLINKINGON_STATE:
+		p_slot->state = POWERON_STATE;
+		break;
+	default:
+		kfree(info);
+		goto out;
+	}
+	queue_work(pciehp_ordered_wq, &info->work);
+ out:
+	mutex_unlock(&p_slot->lock);
+}
+
+/*
+ * Note: This function must be called with slot->lock held
+ */
+static void handle_button_press_event(struct slot *p_slot)
+{
+	struct controller *ctrl = p_slot->ctrl;
+	u8 getstatus;
+
+	switch (p_slot->state) {
+	case STATIC_STATE:
+		pciehp_get_power_status(p_slot, &getstatus);
+		if (getstatus) {
+			p_slot->state = BLINKINGOFF_STATE;
+			ctrl_info(ctrl,
+				  "PCI slot #%s - powering off due to button "
+				  "press.\n", slot_name(p_slot));
+		} else {
+			p_slot->state = BLINKINGON_STATE;
+			ctrl_info(ctrl,
+				  "PCI slot #%s - powering on due to button "
+				  "press.\n", slot_name(p_slot));
+		}
+		/* blink green LED and turn off amber */
+		if (PWR_LED(ctrl))
+			pciehp_green_led_blink(p_slot);
+		if (ATTN_LED(ctrl))
+			pciehp_set_attention_status(p_slot, 0);
+
+		queue_delayed_work(pciehp_wq, &p_slot->work, 5*HZ);
+		break;
+	case BLINKINGOFF_STATE:
+	case BLINKINGON_STATE:
+		/*
+		 * Cancel if we are still blinking; this means that we
+		 * press the attention again before the 5 sec. limit
+		 * expires to cancel hot-add or hot-remove
+		 */
+		ctrl_info(ctrl, "Button cancel on Slot(%s)\n", slot_name(p_slot));
+		cancel_delayed_work(&p_slot->work);
+		if (p_slot->state == BLINKINGOFF_STATE) {
+			if (PWR_LED(ctrl))
+				pciehp_green_led_on(p_slot);
+		} else {
+			if (PWR_LED(ctrl))
+				pciehp_green_led_off(p_slot);
+		}
+		if (ATTN_LED(ctrl))
+			pciehp_set_attention_status(p_slot, 0);
+		ctrl_info(ctrl, "PCI slot #%s - action canceled "
+			  "due to button press\n", slot_name(p_slot));
+		p_slot->state = STATIC_STATE;
+		break;
+	case POWEROFF_STATE:
+	case POWERON_STATE:
+		/*
+		 * Ignore if the slot is on power-on or power-off state;
+		 * this means that the previous attention button action
+		 * to hot-add or hot-remove is undergoing
+		 */
+		ctrl_info(ctrl, "Button ignore on Slot(%s)\n", slot_name(p_slot));
+		break;
+	default:
+		ctrl_warn(ctrl, "Not a valid state\n");
+		break;
+	}
+}
+
+/*
+ * Note: This function must be called with slot->lock held
+ */
+static void handle_surprise_event(struct slot *p_slot)
+{
+	u8 getstatus;
+	struct power_work_info *info;
+
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info) {
+		ctrl_err(p_slot->ctrl, "%s: Cannot allocate memory\n",
+			 __func__);
+		return;
+	}
+	info->p_slot = p_slot;
+	INIT_WORK(&info->work, pciehp_power_thread);
+
+	pciehp_get_adapter_status(p_slot, &getstatus);
+	if (!getstatus)
+		p_slot->state = POWEROFF_STATE;
+	else
+		p_slot->state = POWERON_STATE;
+
+	queue_work(pciehp_ordered_wq, &info->work);
+}
+
+static void interrupt_event_handler(struct work_struct *work)
+{
+	struct event_info *info = container_of(work, struct event_info, work);
+	struct slot *p_slot = info->p_slot;
+	struct controller *ctrl = p_slot->ctrl;
+
+	mutex_lock(&p_slot->lock);
+	switch (info->event_type) {
+	case INT_BUTTON_PRESS:
+		handle_button_press_event(p_slot);
+		break;
+	case INT_POWER_FAULT:
+		if (!POWER_CTRL(ctrl))
+			break;
+		if (ATTN_LED(ctrl))
+			pciehp_set_attention_status(p_slot, 1);
+		if (PWR_LED(ctrl))
+			pciehp_green_led_off(p_slot);
+		break;
+	case INT_PRESENCE_ON:
+	case INT_PRESENCE_OFF:
+		if (!HP_SUPR_RM(ctrl))
+			break;
+		ctrl_dbg(ctrl, "Surprise Removal\n");
+		handle_surprise_event(p_slot);
+		break;
+	default:
+		break;
+	}
+	mutex_unlock(&p_slot->lock);
+
+	kfree(info);
+}
+
+int pciehp_enable_slot(struct slot *p_slot)
+{
+	u8 getstatus = 0;
+	int rc;
+	struct controller *ctrl = p_slot->ctrl;
+
+	rc = pciehp_get_adapter_status(p_slot, &getstatus);
+	if (rc || !getstatus) {
+		ctrl_info(ctrl, "No adapter on slot(%s)\n", slot_name(p_slot));
+		return -ENODEV;
+	}
+	if (MRL_SENS(p_slot->ctrl)) {
+		rc = pciehp_get_latch_status(p_slot, &getstatus);
+		if (rc || getstatus) {
+			ctrl_info(ctrl, "Latch open on slot(%s)\n",
+				  slot_name(p_slot));
+			return -ENODEV;
+		}
+	}
+
+	if (POWER_CTRL(p_slot->ctrl)) {
+		rc = pciehp_get_power_status(p_slot, &getstatus);
+		if (rc || getstatus) {
+			ctrl_info(ctrl, "Already enabled on slot(%s)\n",
+				  slot_name(p_slot));
+			return -EINVAL;
+		}
+	}
+
+	pciehp_get_latch_status(p_slot, &getstatus);
+
+	rc = board_added(p_slot);
+	if (rc) {
+		pciehp_get_latch_status(p_slot, &getstatus);
+	}
+	return rc;
+}
+
+
+int pciehp_disable_slot(struct slot *p_slot)
+{
+	u8 getstatus = 0;
+	int ret = 0;
+	struct controller *ctrl = p_slot->ctrl;
+
+	if (!p_slot->ctrl)
+		return 1;
+
+	if (!HP_SUPR_RM(p_slot->ctrl)) {
+		ret = pciehp_get_adapter_status(p_slot, &getstatus);
+		if (ret || !getstatus) {
+			ctrl_info(ctrl, "No adapter on slot(%s)\n",
+				  slot_name(p_slot));
+			return -ENODEV;
+		}
+	}
+
+	if (MRL_SENS(p_slot->ctrl)) {
+		ret = pciehp_get_latch_status(p_slot, &getstatus);
+		if (ret || getstatus) {
+			ctrl_info(ctrl, "Latch open on slot(%s)\n",
+				  slot_name(p_slot));
+			return -ENODEV;
+		}
+	}
+
+	if (POWER_CTRL(p_slot->ctrl)) {
+		ret = pciehp_get_power_status(p_slot, &getstatus);
+		if (ret || !getstatus) {
+			ctrl_info(ctrl, "Already disabled on slot(%s)\n",
+				  slot_name(p_slot));
+			return -EINVAL;
+		}
+	}
+
+	return remove_board(p_slot);
+}
+
+int pciehp_sysfs_enable_slot(struct slot *p_slot)
+{
+	int retval = -ENODEV;
+	struct controller *ctrl = p_slot->ctrl;
+
+	mutex_lock(&p_slot->lock);
+	switch (p_slot->state) {
+	case BLINKINGON_STATE:
+		cancel_delayed_work(&p_slot->work);
+	case STATIC_STATE:
+		p_slot->state = POWERON_STATE;
+		mutex_unlock(&p_slot->lock);
+		retval = pciehp_enable_slot(p_slot);
+		mutex_lock(&p_slot->lock);
+		p_slot->state = STATIC_STATE;
+		break;
+	case POWERON_STATE:
+		ctrl_info(ctrl, "Slot %s is already in powering on state\n",
+			  slot_name(p_slot));
+		break;
+	case BLINKINGOFF_STATE:
+	case POWEROFF_STATE:
+		ctrl_info(ctrl, "Already enabled on slot %s\n",
+			  slot_name(p_slot));
+		break;
+	default:
+		ctrl_err(ctrl, "Not a valid state on slot %s\n",
+			 slot_name(p_slot));
+		break;
+	}
+	mutex_unlock(&p_slot->lock);
+
+	return retval;
+}
+
+int pciehp_sysfs_disable_slot(struct slot *p_slot)
+{
+	int retval = -ENODEV;
+	struct controller *ctrl = p_slot->ctrl;
+
+	mutex_lock(&p_slot->lock);
+	switch (p_slot->state) {
+	case BLINKINGOFF_STATE:
+		cancel_delayed_work(&p_slot->work);
+	case STATIC_STATE:
+		p_slot->state = POWEROFF_STATE;
+		mutex_unlock(&p_slot->lock);
+		retval = pciehp_disable_slot(p_slot);
+		mutex_lock(&p_slot->lock);
+		p_slot->state = STATIC_STATE;
+		break;
+	case POWEROFF_STATE:
+		ctrl_info(ctrl, "Slot %s is already in powering off state\n",
+			  slot_name(p_slot));
+		break;
+	case BLINKINGON_STATE:
+	case POWERON_STATE:
+		ctrl_info(ctrl, "Already disabled on slot %s\n",
+			  slot_name(p_slot));
+		break;
+	default:
+		ctrl_err(ctrl, "Not a valid state on slot %s\n",
+			 slot_name(p_slot));
+		break;
+	}
+	mutex_unlock(&p_slot->lock);
+
+	return retval;
+}
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
new file mode 100644
index 00000000..50a23da5
--- /dev/null
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -0,0 +1,933 @@
+/*
+ * PCI Express PCI Hot Plug Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ * Copyright (C) 2003-2004 Intel Corporation
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>,<kristen.c.accardi@intel.com>
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/signal.h>
+#include <linux/jiffies.h>
+#include <linux/timer.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/time.h>
+#include <linux/slab.h>
+
+#include "../pci.h"
+#include "pciehp.h"
+
+static inline int pciehp_readw(struct controller *ctrl, int reg, u16 *value)
+{
+	struct pci_dev *dev = ctrl->pcie->port;
+	return pci_read_config_word(dev, pci_pcie_cap(dev) + reg, value);
+}
+
+static inline int pciehp_readl(struct controller *ctrl, int reg, u32 *value)
+{
+	struct pci_dev *dev = ctrl->pcie->port;
+	return pci_read_config_dword(dev, pci_pcie_cap(dev) + reg, value);
+}
+
+static inline int pciehp_writew(struct controller *ctrl, int reg, u16 value)
+{
+	struct pci_dev *dev = ctrl->pcie->port;
+	return pci_write_config_word(dev, pci_pcie_cap(dev) + reg, value);
+}
+
+static inline int pciehp_writel(struct controller *ctrl, int reg, u32 value)
+{
+	struct pci_dev *dev = ctrl->pcie->port;
+	return pci_write_config_dword(dev, pci_pcie_cap(dev) + reg, value);
+}
+
+/* Power Control Command */
+#define POWER_ON	0
+#define POWER_OFF	PCI_EXP_SLTCTL_PCC
+
+static irqreturn_t pcie_isr(int irq, void *dev_id);
+static void start_int_poll_timer(struct controller *ctrl, int sec);
+
+/* This is the interrupt polling timeout function. */
+static void int_poll_timeout(unsigned long data)
+{
+	struct controller *ctrl = (struct controller *)data;
+
+	/* Poll for interrupt events.  regs == NULL => polling */
+	pcie_isr(0, ctrl);
+
+	init_timer(&ctrl->poll_timer);
+	if (!pciehp_poll_time)
+		pciehp_poll_time = 2; /* default polling interval is 2 sec */
+
+	start_int_poll_timer(ctrl, pciehp_poll_time);
+}
+
+/* This function starts the interrupt polling timer. */
+static void start_int_poll_timer(struct controller *ctrl, int sec)
+{
+	/* Clamp to sane value */
+	if ((sec <= 0) || (sec > 60))
+        	sec = 2;
+
+	ctrl->poll_timer.function = &int_poll_timeout;
+	ctrl->poll_timer.data = (unsigned long)ctrl;
+	ctrl->poll_timer.expires = jiffies + sec * HZ;
+	add_timer(&ctrl->poll_timer);
+}
+
+static inline int pciehp_request_irq(struct controller *ctrl)
+{
+	int retval, irq = ctrl->pcie->irq;
+
+	/* Install interrupt polling timer. Start with 10 sec delay */
+	if (pciehp_poll_mode) {
+		init_timer(&ctrl->poll_timer);
+		start_int_poll_timer(ctrl, 10);
+		return 0;
+	}
+
+	/* Installs the interrupt handler */
+	retval = request_irq(irq, pcie_isr, IRQF_SHARED, MY_NAME, ctrl);
+	if (retval)
+		ctrl_err(ctrl, "Cannot get irq %d for the hotplug controller\n",
+			 irq);
+	return retval;
+}
+
+static inline void pciehp_free_irq(struct controller *ctrl)
+{
+	if (pciehp_poll_mode)
+		del_timer_sync(&ctrl->poll_timer);
+	else
+		free_irq(ctrl->pcie->irq, ctrl);
+}
+
+static int pcie_poll_cmd(struct controller *ctrl)
+{
+	u16 slot_status;
+	int err, timeout = 1000;
+
+	err = pciehp_readw(ctrl, PCI_EXP_SLTSTA, &slot_status);
+	if (!err && (slot_status & PCI_EXP_SLTSTA_CC)) {
+		pciehp_writew(ctrl, PCI_EXP_SLTSTA, PCI_EXP_SLTSTA_CC);
+		return 1;
+	}
+	while (timeout > 0) {
+		msleep(10);
+		timeout -= 10;
+		err = pciehp_readw(ctrl, PCI_EXP_SLTSTA, &slot_status);
+		if (!err && (slot_status & PCI_EXP_SLTSTA_CC)) {
+			pciehp_writew(ctrl, PCI_EXP_SLTSTA, PCI_EXP_SLTSTA_CC);
+			return 1;
+		}
+	}
+	return 0;	/* timeout */
+}
+
+static void pcie_wait_cmd(struct controller *ctrl, int poll)
+{
+	unsigned int msecs = pciehp_poll_mode ? 2500 : 1000;
+	unsigned long timeout = msecs_to_jiffies(msecs);
+	int rc;
+
+	if (poll)
+		rc = pcie_poll_cmd(ctrl);
+	else
+		rc = wait_event_timeout(ctrl->queue, !ctrl->cmd_busy, timeout);
+	if (!rc)
+		ctrl_dbg(ctrl, "Command not completed in 1000 msec\n");
+}
+
+/**
+ * pcie_write_cmd - Issue controller command
+ * @ctrl: controller to which the command is issued
+ * @cmd:  command value written to slot control register
+ * @mask: bitmask of slot control register to be modified
+ */
+static int pcie_write_cmd(struct controller *ctrl, u16 cmd, u16 mask)
+{
+	int retval = 0;
+	u16 slot_status;
+	u16 slot_ctrl;
+
+	mutex_lock(&ctrl->ctrl_lock);
+
+	retval = pciehp_readw(ctrl, PCI_EXP_SLTSTA, &slot_status);
+	if (retval) {
+		ctrl_err(ctrl, "%s: Cannot read SLOTSTATUS register\n",
+			 __func__);
+		goto out;
+	}
+
+	if (slot_status & PCI_EXP_SLTSTA_CC) {
+		if (!ctrl->no_cmd_complete) {
+			/*
+			 * After 1 sec and CMD_COMPLETED still not set, just
+			 * proceed forward to issue the next command according
+			 * to spec. Just print out the error message.
+			 */
+			ctrl_dbg(ctrl, "CMD_COMPLETED not clear after 1 sec\n");
+		} else if (!NO_CMD_CMPL(ctrl)) {
+			/*
+			 * This controller semms to notify of command completed
+			 * event even though it supports none of power
+			 * controller, attention led, power led and EMI.
+			 */
+			ctrl_dbg(ctrl, "Unexpected CMD_COMPLETED. Need to "
+				 "wait for command completed event.\n");
+			ctrl->no_cmd_complete = 0;
+		} else {
+			ctrl_dbg(ctrl, "Unexpected CMD_COMPLETED. Maybe "
+				 "the controller is broken.\n");
+		}
+	}
+
+	retval = pciehp_readw(ctrl, PCI_EXP_SLTCTL, &slot_ctrl);
+	if (retval) {
+		ctrl_err(ctrl, "%s: Cannot read SLOTCTRL register\n", __func__);
+		goto out;
+	}
+
+	slot_ctrl &= ~mask;
+	slot_ctrl |= (cmd & mask);
+	ctrl->cmd_busy = 1;
+	smp_mb();
+	retval = pciehp_writew(ctrl, PCI_EXP_SLTCTL, slot_ctrl);
+	if (retval)
+		ctrl_err(ctrl, "Cannot write to SLOTCTRL register\n");
+
+	/*
+	 * Wait for command completion.
+	 */
+	if (!retval && !ctrl->no_cmd_complete) {
+		int poll = 0;
+		/*
+		 * if hotplug interrupt is not enabled or command
+		 * completed interrupt is not enabled, we need to poll
+		 * command completed event.
+		 */
+		if (!(slot_ctrl & PCI_EXP_SLTCTL_HPIE) ||
+		    !(slot_ctrl & PCI_EXP_SLTCTL_CCIE))
+			poll = 1;
+                pcie_wait_cmd(ctrl, poll);
+	}
+ out:
+	mutex_unlock(&ctrl->ctrl_lock);
+	return retval;
+}
+
+static inline int check_link_active(struct controller *ctrl)
+{
+	u16 link_status;
+
+	if (pciehp_readw(ctrl, PCI_EXP_LNKSTA, &link_status))
+		return 0;
+	return !!(link_status & PCI_EXP_LNKSTA_DLLLA);
+}
+
+static void pcie_wait_link_active(struct controller *ctrl)
+{
+	int timeout = 1000;
+
+	if (check_link_active(ctrl))
+		return;
+	while (timeout > 0) {
+		msleep(10);
+		timeout -= 10;
+		if (check_link_active(ctrl))
+			return;
+	}
+	ctrl_dbg(ctrl, "Data Link Layer Link Active not set in 1000 msec\n");
+}
+
+int pciehp_check_link_status(struct controller *ctrl)
+{
+	u16 lnk_status;
+	int retval = 0;
+
+        /*
+         * Data Link Layer Link Active Reporting must be capable for
+         * hot-plug capable downstream port. But old controller might
+         * not implement it. In this case, we wait for 1000 ms.
+         */
+        if (ctrl->link_active_reporting){
+                /* Wait for Data Link Layer Link Active bit to be set */
+                pcie_wait_link_active(ctrl);
+                /*
+                 * We must wait for 100 ms after the Data Link Layer
+                 * Link Active bit reads 1b before initiating a
+                 * configuration access to the hot added device.
+                 */
+                msleep(100);
+        } else
+                msleep(1000);
+
+	retval = pciehp_readw(ctrl, PCI_EXP_LNKSTA, &lnk_status);
+	if (retval) {
+		ctrl_err(ctrl, "Cannot read LNKSTATUS register\n");
+		return retval;
+	}
+
+	ctrl_dbg(ctrl, "%s: lnk_status = %x\n", __func__, lnk_status);
+	if ((lnk_status & PCI_EXP_LNKSTA_LT) ||
+	    !(lnk_status & PCI_EXP_LNKSTA_NLW)) {
+		ctrl_err(ctrl, "Link Training Error occurs \n");
+		retval = -1;
+		return retval;
+	}
+
+	return retval;
+}
+
+int pciehp_get_attention_status(struct slot *slot, u8 *status)
+{
+	struct controller *ctrl = slot->ctrl;
+	u16 slot_ctrl;
+	u8 atten_led_state;
+	int retval = 0;
+
+	retval = pciehp_readw(ctrl, PCI_EXP_SLTCTL, &slot_ctrl);
+	if (retval) {
+		ctrl_err(ctrl, "%s: Cannot read SLOTCTRL register\n", __func__);
+		return retval;
+	}
+
+	ctrl_dbg(ctrl, "%s: SLOTCTRL %x, value read %x\n", __func__,
+		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_ctrl);
+
+	atten_led_state = (slot_ctrl & PCI_EXP_SLTCTL_AIC) >> 6;
+
+	switch (atten_led_state) {
+	case 0:
+		*status = 0xFF;	/* Reserved */
+		break;
+	case 1:
+		*status = 1;	/* On */
+		break;
+	case 2:
+		*status = 2;	/* Blink */
+		break;
+	case 3:
+		*status = 0;	/* Off */
+		break;
+	default:
+		*status = 0xFF;
+		break;
+	}
+
+	return 0;
+}
+
+int pciehp_get_power_status(struct slot *slot, u8 *status)
+{
+	struct controller *ctrl = slot->ctrl;
+	u16 slot_ctrl;
+	u8 pwr_state;
+	int	retval = 0;
+
+	retval = pciehp_readw(ctrl, PCI_EXP_SLTCTL, &slot_ctrl);
+	if (retval) {
+		ctrl_err(ctrl, "%s: Cannot read SLOTCTRL register\n", __func__);
+		return retval;
+	}
+	ctrl_dbg(ctrl, "%s: SLOTCTRL %x value read %x\n", __func__,
+		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_ctrl);
+
+	pwr_state = (slot_ctrl & PCI_EXP_SLTCTL_PCC) >> 10;
+
+	switch (pwr_state) {
+	case 0:
+		*status = 1;
+		break;
+	case 1:
+		*status = 0;
+		break;
+	default:
+		*status = 0xFF;
+		break;
+	}
+
+	return retval;
+}
+
+int pciehp_get_latch_status(struct slot *slot, u8 *status)
+{
+	struct controller *ctrl = slot->ctrl;
+	u16 slot_status;
+	int retval;
+
+	retval = pciehp_readw(ctrl, PCI_EXP_SLTSTA, &slot_status);
+	if (retval) {
+		ctrl_err(ctrl, "%s: Cannot read SLOTSTATUS register\n",
+			 __func__);
+		return retval;
+	}
+	*status = !!(slot_status & PCI_EXP_SLTSTA_MRLSS);
+	return 0;
+}
+
+int pciehp_get_adapter_status(struct slot *slot, u8 *status)
+{
+	struct controller *ctrl = slot->ctrl;
+	u16 slot_status;
+	int retval;
+
+	retval = pciehp_readw(ctrl, PCI_EXP_SLTSTA, &slot_status);
+	if (retval) {
+		ctrl_err(ctrl, "%s: Cannot read SLOTSTATUS register\n",
+			 __func__);
+		return retval;
+	}
+	*status = !!(slot_status & PCI_EXP_SLTSTA_PDS);
+	return 0;
+}
+
+int pciehp_query_power_fault(struct slot *slot)
+{
+	struct controller *ctrl = slot->ctrl;
+	u16 slot_status;
+	int retval;
+
+	retval = pciehp_readw(ctrl, PCI_EXP_SLTSTA, &slot_status);
+	if (retval) {
+		ctrl_err(ctrl, "Cannot check for power fault\n");
+		return retval;
+	}
+	return !!(slot_status & PCI_EXP_SLTSTA_PFD);
+}
+
+int pciehp_set_attention_status(struct slot *slot, u8 value)
+{
+	struct controller *ctrl = slot->ctrl;
+	u16 slot_cmd;
+	u16 cmd_mask;
+
+	cmd_mask = PCI_EXP_SLTCTL_AIC;
+	switch (value) {
+	case 0 :	/* turn off */
+		slot_cmd = 0x00C0;
+		break;
+	case 1:		/* turn on */
+		slot_cmd = 0x0040;
+		break;
+	case 2:		/* turn blink */
+		slot_cmd = 0x0080;
+		break;
+	default:
+		return -EINVAL;
+	}
+	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
+		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_cmd);
+	return pcie_write_cmd(ctrl, slot_cmd, cmd_mask);
+}
+
+void pciehp_green_led_on(struct slot *slot)
+{
+	struct controller *ctrl = slot->ctrl;
+	u16 slot_cmd;
+	u16 cmd_mask;
+
+	slot_cmd = 0x0100;
+	cmd_mask = PCI_EXP_SLTCTL_PIC;
+	pcie_write_cmd(ctrl, slot_cmd, cmd_mask);
+	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
+		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_cmd);
+}
+
+void pciehp_green_led_off(struct slot *slot)
+{
+	struct controller *ctrl = slot->ctrl;
+	u16 slot_cmd;
+	u16 cmd_mask;
+
+	slot_cmd = 0x0300;
+	cmd_mask = PCI_EXP_SLTCTL_PIC;
+	pcie_write_cmd(ctrl, slot_cmd, cmd_mask);
+	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
+		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_cmd);
+}
+
+void pciehp_green_led_blink(struct slot *slot)
+{
+	struct controller *ctrl = slot->ctrl;
+	u16 slot_cmd;
+	u16 cmd_mask;
+
+	slot_cmd = 0x0200;
+	cmd_mask = PCI_EXP_SLTCTL_PIC;
+	pcie_write_cmd(ctrl, slot_cmd, cmd_mask);
+	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
+		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_cmd);
+}
+
+int pciehp_power_on_slot(struct slot * slot)
+{
+	struct controller *ctrl = slot->ctrl;
+	u16 slot_cmd;
+	u16 cmd_mask;
+	u16 slot_status;
+	u16 lnk_status;
+	int retval = 0;
+
+	/* Clear sticky power-fault bit from previous power failures */
+	retval = pciehp_readw(ctrl, PCI_EXP_SLTSTA, &slot_status);
+	if (retval) {
+		ctrl_err(ctrl, "%s: Cannot read SLOTSTATUS register\n",
+			 __func__);
+		return retval;
+	}
+	slot_status &= PCI_EXP_SLTSTA_PFD;
+	if (slot_status) {
+		retval = pciehp_writew(ctrl, PCI_EXP_SLTSTA, slot_status);
+		if (retval) {
+			ctrl_err(ctrl,
+				 "%s: Cannot write to SLOTSTATUS register\n",
+				 __func__);
+			return retval;
+		}
+	}
+	ctrl->power_fault_detected = 0;
+
+	slot_cmd = POWER_ON;
+	cmd_mask = PCI_EXP_SLTCTL_PCC;
+	retval = pcie_write_cmd(ctrl, slot_cmd, cmd_mask);
+	if (retval) {
+		ctrl_err(ctrl, "Write %x command failed!\n", slot_cmd);
+		return retval;
+	}
+	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
+		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_cmd);
+
+	retval = pciehp_readw(ctrl, PCI_EXP_LNKSTA, &lnk_status);
+	if (retval) {
+		ctrl_err(ctrl, "%s: Cannot read LNKSTA register\n",
+				__func__);
+		return retval;
+	}
+	pcie_update_link_speed(ctrl->pcie->port->subordinate, lnk_status);
+
+	return retval;
+}
+
+int pciehp_power_off_slot(struct slot * slot)
+{
+	struct controller *ctrl = slot->ctrl;
+	u16 slot_cmd;
+	u16 cmd_mask;
+	int retval;
+
+	slot_cmd = POWER_OFF;
+	cmd_mask = PCI_EXP_SLTCTL_PCC;
+	retval = pcie_write_cmd(ctrl, slot_cmd, cmd_mask);
+	if (retval) {
+		ctrl_err(ctrl, "Write command failed!\n");
+		return retval;
+	}
+	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
+		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_cmd);
+	return 0;
+}
+
+static irqreturn_t pcie_isr(int irq, void *dev_id)
+{
+	struct controller *ctrl = (struct controller *)dev_id;
+	struct slot *slot = ctrl->slot;
+	u16 detected, intr_loc;
+
+	/*
+	 * In order to guarantee that all interrupt events are
+	 * serviced, we need to re-inspect Slot Status register after
+	 * clearing what is presumed to be the last pending interrupt.
+	 */
+	intr_loc = 0;
+	do {
+		if (pciehp_readw(ctrl, PCI_EXP_SLTSTA, &detected)) {
+			ctrl_err(ctrl, "%s: Cannot read SLOTSTATUS\n",
+				 __func__);
+			return IRQ_NONE;
+		}
+
+		detected &= (PCI_EXP_SLTSTA_ABP | PCI_EXP_SLTSTA_PFD |
+			     PCI_EXP_SLTSTA_MRLSC | PCI_EXP_SLTSTA_PDC |
+			     PCI_EXP_SLTSTA_CC);
+		detected &= ~intr_loc;
+		intr_loc |= detected;
+		if (!intr_loc)
+			return IRQ_NONE;
+		if (detected && pciehp_writew(ctrl, PCI_EXP_SLTSTA, intr_loc)) {
+			ctrl_err(ctrl, "%s: Cannot write to SLOTSTATUS\n",
+				 __func__);
+			return IRQ_NONE;
+		}
+	} while (detected);
+
+	ctrl_dbg(ctrl, "%s: intr_loc %x\n", __func__, intr_loc);
+
+	/* Check Command Complete Interrupt Pending */
+	if (intr_loc & PCI_EXP_SLTSTA_CC) {
+		ctrl->cmd_busy = 0;
+		smp_mb();
+		wake_up(&ctrl->queue);
+	}
+
+	if (!(intr_loc & ~PCI_EXP_SLTSTA_CC))
+		return IRQ_HANDLED;
+
+	/* Check MRL Sensor Changed */
+	if (intr_loc & PCI_EXP_SLTSTA_MRLSC)
+		pciehp_handle_switch_change(slot);
+
+	/* Check Attention Button Pressed */
+	if (intr_loc & PCI_EXP_SLTSTA_ABP)
+		pciehp_handle_attention_button(slot);
+
+	/* Check Presence Detect Changed */
+	if (intr_loc & PCI_EXP_SLTSTA_PDC)
+		pciehp_handle_presence_change(slot);
+
+	/* Check Power Fault Detected */
+	if ((intr_loc & PCI_EXP_SLTSTA_PFD) && !ctrl->power_fault_detected) {
+		ctrl->power_fault_detected = 1;
+		pciehp_handle_power_fault(slot);
+	}
+	return IRQ_HANDLED;
+}
+
+int pciehp_get_max_lnk_width(struct slot *slot,
+				 enum pcie_link_width *value)
+{
+	struct controller *ctrl = slot->ctrl;
+	enum pcie_link_width lnk_wdth;
+	u32	lnk_cap;
+	int retval = 0;
+
+	retval = pciehp_readl(ctrl, PCI_EXP_LNKCAP, &lnk_cap);
+	if (retval) {
+		ctrl_err(ctrl, "%s: Cannot read LNKCAP register\n", __func__);
+		return retval;
+	}
+
+	switch ((lnk_cap & PCI_EXP_LNKSTA_NLW) >> 4){
+	case 0:
+		lnk_wdth = PCIE_LNK_WIDTH_RESRV;
+		break;
+	case 1:
+		lnk_wdth = PCIE_LNK_X1;
+		break;
+	case 2:
+		lnk_wdth = PCIE_LNK_X2;
+		break;
+	case 4:
+		lnk_wdth = PCIE_LNK_X4;
+		break;
+	case 8:
+		lnk_wdth = PCIE_LNK_X8;
+		break;
+	case 12:
+		lnk_wdth = PCIE_LNK_X12;
+		break;
+	case 16:
+		lnk_wdth = PCIE_LNK_X16;
+		break;
+	case 32:
+		lnk_wdth = PCIE_LNK_X32;
+		break;
+	default:
+		lnk_wdth = PCIE_LNK_WIDTH_UNKNOWN;
+		break;
+	}
+
+	*value = lnk_wdth;
+	ctrl_dbg(ctrl, "Max link width = %d\n", lnk_wdth);
+
+	return retval;
+}
+
+int pciehp_get_cur_lnk_width(struct slot *slot,
+				 enum pcie_link_width *value)
+{
+	struct controller *ctrl = slot->ctrl;
+	enum pcie_link_width lnk_wdth = PCIE_LNK_WIDTH_UNKNOWN;
+	int retval = 0;
+	u16 lnk_status;
+
+	retval = pciehp_readw(ctrl, PCI_EXP_LNKSTA, &lnk_status);
+	if (retval) {
+		ctrl_err(ctrl, "%s: Cannot read LNKSTATUS register\n",
+			 __func__);
+		return retval;
+	}
+
+	switch ((lnk_status & PCI_EXP_LNKSTA_NLW) >> 4){
+	case 0:
+		lnk_wdth = PCIE_LNK_WIDTH_RESRV;
+		break;
+	case 1:
+		lnk_wdth = PCIE_LNK_X1;
+		break;
+	case 2:
+		lnk_wdth = PCIE_LNK_X2;
+		break;
+	case 4:
+		lnk_wdth = PCIE_LNK_X4;
+		break;
+	case 8:
+		lnk_wdth = PCIE_LNK_X8;
+		break;
+	case 12:
+		lnk_wdth = PCIE_LNK_X12;
+		break;
+	case 16:
+		lnk_wdth = PCIE_LNK_X16;
+		break;
+	case 32:
+		lnk_wdth = PCIE_LNK_X32;
+		break;
+	default:
+		lnk_wdth = PCIE_LNK_WIDTH_UNKNOWN;
+		break;
+	}
+
+	*value = lnk_wdth;
+	ctrl_dbg(ctrl, "Current link width = %d\n", lnk_wdth);
+
+	return retval;
+}
+
+int pcie_enable_notification(struct controller *ctrl)
+{
+	u16 cmd, mask;
+
+	/*
+	 * TBD: Power fault detected software notification support.
+	 *
+	 * Power fault detected software notification is not enabled
+	 * now, because it caused power fault detected interrupt storm
+	 * on some machines. On those machines, power fault detected
+	 * bit in the slot status register was set again immediately
+	 * when it is cleared in the interrupt service routine, and
+	 * next power fault detected interrupt was notified again.
+	 */
+	cmd = PCI_EXP_SLTCTL_PDCE;
+	if (ATTN_BUTTN(ctrl))
+		cmd |= PCI_EXP_SLTCTL_ABPE;
+	if (MRL_SENS(ctrl))
+		cmd |= PCI_EXP_SLTCTL_MRLSCE;
+	if (!pciehp_poll_mode)
+		cmd |= PCI_EXP_SLTCTL_HPIE | PCI_EXP_SLTCTL_CCIE;
+
+	mask = (PCI_EXP_SLTCTL_PDCE | PCI_EXP_SLTCTL_ABPE |
+		PCI_EXP_SLTCTL_MRLSCE | PCI_EXP_SLTCTL_PFDE |
+		PCI_EXP_SLTCTL_HPIE | PCI_EXP_SLTCTL_CCIE);
+
+	if (pcie_write_cmd(ctrl, cmd, mask)) {
+		ctrl_err(ctrl, "Cannot enable software notification\n");
+		return -1;
+	}
+	return 0;
+}
+
+static void pcie_disable_notification(struct controller *ctrl)
+{
+	u16 mask;
+	mask = (PCI_EXP_SLTCTL_PDCE | PCI_EXP_SLTCTL_ABPE |
+		PCI_EXP_SLTCTL_MRLSCE | PCI_EXP_SLTCTL_PFDE |
+		PCI_EXP_SLTCTL_HPIE | PCI_EXP_SLTCTL_CCIE |
+		PCI_EXP_SLTCTL_DLLSCE);
+	if (pcie_write_cmd(ctrl, 0, mask))
+		ctrl_warn(ctrl, "Cannot disable software notification\n");
+}
+
+int pcie_init_notification(struct controller *ctrl)
+{
+	if (pciehp_request_irq(ctrl))
+		return -1;
+	if (pcie_enable_notification(ctrl)) {
+		pciehp_free_irq(ctrl);
+		return -1;
+	}
+	ctrl->notification_enabled = 1;
+	return 0;
+}
+
+static void pcie_shutdown_notification(struct controller *ctrl)
+{
+	if (ctrl->notification_enabled) {
+		pcie_disable_notification(ctrl);
+		pciehp_free_irq(ctrl);
+		ctrl->notification_enabled = 0;
+	}
+}
+
+static int pcie_init_slot(struct controller *ctrl)
+{
+	struct slot *slot;
+
+	slot = kzalloc(sizeof(*slot), GFP_KERNEL);
+	if (!slot)
+		return -ENOMEM;
+
+	slot->ctrl = ctrl;
+	mutex_init(&slot->lock);
+	INIT_DELAYED_WORK(&slot->work, pciehp_queue_pushbutton_work);
+	ctrl->slot = slot;
+	return 0;
+}
+
+static void pcie_cleanup_slot(struct controller *ctrl)
+{
+	struct slot *slot = ctrl->slot;
+	cancel_delayed_work(&slot->work);
+	flush_workqueue(pciehp_wq);
+	flush_workqueue(pciehp_ordered_wq);
+	kfree(slot);
+}
+
+static inline void dbg_ctrl(struct controller *ctrl)
+{
+	int i;
+	u16 reg16;
+	struct pci_dev *pdev = ctrl->pcie->port;
+
+	if (!pciehp_debug)
+		return;
+
+	ctrl_info(ctrl, "Hotplug Controller:\n");
+	ctrl_info(ctrl, "  Seg/Bus/Dev/Func/IRQ : %s IRQ %d\n",
+		  pci_name(pdev), pdev->irq);
+	ctrl_info(ctrl, "  Vendor ID            : 0x%04x\n", pdev->vendor);
+	ctrl_info(ctrl, "  Device ID            : 0x%04x\n", pdev->device);
+	ctrl_info(ctrl, "  Subsystem ID         : 0x%04x\n",
+		  pdev->subsystem_device);
+	ctrl_info(ctrl, "  Subsystem Vendor ID  : 0x%04x\n",
+		  pdev->subsystem_vendor);
+	ctrl_info(ctrl, "  PCIe Cap offset      : 0x%02x\n",
+		  pci_pcie_cap(pdev));
+	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+		if (!pci_resource_len(pdev, i))
+			continue;
+		ctrl_info(ctrl, "  PCI resource [%d]     : %pR\n",
+			  i, &pdev->resource[i]);
+	}
+	ctrl_info(ctrl, "Slot Capabilities      : 0x%08x\n", ctrl->slot_cap);
+	ctrl_info(ctrl, "  Physical Slot Number : %d\n", PSN(ctrl));
+	ctrl_info(ctrl, "  Attention Button     : %3s\n",
+		  ATTN_BUTTN(ctrl) ? "yes" : "no");
+	ctrl_info(ctrl, "  Power Controller     : %3s\n",
+		  POWER_CTRL(ctrl) ? "yes" : "no");
+	ctrl_info(ctrl, "  MRL Sensor           : %3s\n",
+		  MRL_SENS(ctrl)   ? "yes" : "no");
+	ctrl_info(ctrl, "  Attention Indicator  : %3s\n",
+		  ATTN_LED(ctrl)   ? "yes" : "no");
+	ctrl_info(ctrl, "  Power Indicator      : %3s\n",
+		  PWR_LED(ctrl)    ? "yes" : "no");
+	ctrl_info(ctrl, "  Hot-Plug Surprise    : %3s\n",
+		  HP_SUPR_RM(ctrl) ? "yes" : "no");
+	ctrl_info(ctrl, "  EMI Present          : %3s\n",
+		  EMI(ctrl)        ? "yes" : "no");
+	ctrl_info(ctrl, "  Command Completed    : %3s\n",
+		  NO_CMD_CMPL(ctrl) ? "no" : "yes");
+	pciehp_readw(ctrl, PCI_EXP_SLTSTA, &reg16);
+	ctrl_info(ctrl, "Slot Status            : 0x%04x\n", reg16);
+	pciehp_readw(ctrl, PCI_EXP_SLTCTL, &reg16);
+	ctrl_info(ctrl, "Slot Control           : 0x%04x\n", reg16);
+}
+
+struct controller *pcie_init(struct pcie_device *dev)
+{
+	struct controller *ctrl;
+	u32 slot_cap, link_cap;
+	struct pci_dev *pdev = dev->port;
+
+	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
+	if (!ctrl) {
+		dev_err(&dev->device, "%s: Out of memory\n", __func__);
+		goto abort;
+	}
+	ctrl->pcie = dev;
+	if (!pci_pcie_cap(pdev)) {
+		ctrl_err(ctrl, "Cannot find PCI Express capability\n");
+		goto abort_ctrl;
+	}
+	if (pciehp_readl(ctrl, PCI_EXP_SLTCAP, &slot_cap)) {
+		ctrl_err(ctrl, "Cannot read SLOTCAP register\n");
+		goto abort_ctrl;
+	}
+
+	ctrl->slot_cap = slot_cap;
+	mutex_init(&ctrl->ctrl_lock);
+	init_waitqueue_head(&ctrl->queue);
+	dbg_ctrl(ctrl);
+	/*
+	 * Controller doesn't notify of command completion if the "No
+	 * Command Completed Support" bit is set in Slot Capability
+	 * register or the controller supports none of power
+	 * controller, attention led, power led and EMI.
+	 */
+	if (NO_CMD_CMPL(ctrl) ||
+	    !(POWER_CTRL(ctrl) | ATTN_LED(ctrl) | PWR_LED(ctrl) | EMI(ctrl)))
+	    ctrl->no_cmd_complete = 1;
+
+        /* Check if Data Link Layer Link Active Reporting is implemented */
+        if (pciehp_readl(ctrl, PCI_EXP_LNKCAP, &link_cap)) {
+                ctrl_err(ctrl, "%s: Cannot read LNKCAP register\n", __func__);
+                goto abort_ctrl;
+        }
+        if (link_cap & PCI_EXP_LNKCAP_DLLLARC) {
+                ctrl_dbg(ctrl, "Link Active Reporting supported\n");
+                ctrl->link_active_reporting = 1;
+        }
+
+	/* Clear all remaining event bits in Slot Status register */
+	if (pciehp_writew(ctrl, PCI_EXP_SLTSTA, 0x1f))
+		goto abort_ctrl;
+
+	/* Disable sotfware notification */
+	pcie_disable_notification(ctrl);
+
+	ctrl_info(ctrl, "HPC vendor_id %x device_id %x ss_vid %x ss_did %x\n",
+		  pdev->vendor, pdev->device, pdev->subsystem_vendor,
+		  pdev->subsystem_device);
+
+	if (pcie_init_slot(ctrl))
+		goto abort_ctrl;
+
+	return ctrl;
+
+abort_ctrl:
+	kfree(ctrl);
+abort:
+	return NULL;
+}
+
+void pciehp_release_ctrl(struct controller *ctrl)
+{
+	pcie_shutdown_notification(ctrl);
+	pcie_cleanup_slot(ctrl);
+	kfree(ctrl);
+}
diff --git a/drivers/pci/hotplug/pciehp_pci.c b/drivers/pci/hotplug/pciehp_pci.c
new file mode 100644
index 00000000..a4031dfe
--- /dev/null
+++ b/drivers/pci/hotplug/pciehp_pci.c
@@ -0,0 +1,159 @@
+/*
+ * PCI Express Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ * Copyright (C) 2003-2004 Intel Corporation
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>, <kristen.c.accardi@intel.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include "../pci.h"
+#include "pciehp.h"
+
+static int __ref pciehp_add_bridge(struct pci_dev *dev)
+{
+	struct pci_bus *parent = dev->bus;
+	int pass, busnr, start = parent->secondary;
+	int end = parent->subordinate;
+
+	for (busnr = start; busnr <= end; busnr++) {
+		if (!pci_find_bus(pci_domain_nr(parent), busnr))
+			break;
+	}
+	if (busnr-- > end) {
+		err("No bus number available for hot-added bridge %s\n",
+				pci_name(dev));
+		return -1;
+	}
+	for (pass = 0; pass < 2; pass++)
+		busnr = pci_scan_bridge(parent, dev, busnr, pass);
+	if (!dev->subordinate)
+		return -1;
+
+	return 0;
+}
+
+int pciehp_configure_device(struct slot *p_slot)
+{
+	struct pci_dev *dev;
+	struct pci_dev *bridge = p_slot->ctrl->pcie->port;
+	struct pci_bus *parent = bridge->subordinate;
+	int num, fn;
+	struct controller *ctrl = p_slot->ctrl;
+
+	dev = pci_get_slot(parent, PCI_DEVFN(0, 0));
+	if (dev) {
+		ctrl_err(ctrl, "Device %s already exists "
+			 "at %04x:%02x:00, cannot hot-add\n", pci_name(dev),
+			 pci_domain_nr(parent), parent->number);
+		pci_dev_put(dev);
+		return -EINVAL;
+	}
+
+	num = pci_scan_slot(parent, PCI_DEVFN(0, 0));
+	if (num == 0) {
+		ctrl_err(ctrl, "No new device found\n");
+		return -ENODEV;
+	}
+
+	for (fn = 0; fn < 8; fn++) {
+		dev = pci_get_slot(parent, PCI_DEVFN(0, fn));
+		if (!dev)
+			continue;
+		if ((dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) ||
+				(dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)) {
+			pciehp_add_bridge(dev);
+		}
+		pci_dev_put(dev);
+	}
+
+	pci_assign_unassigned_bridge_resources(bridge);
+
+	for (fn = 0; fn < 8; fn++) {
+		dev = pci_get_slot(parent, PCI_DEVFN(0, fn));
+		if (!dev)
+			continue;
+		if ((dev->class >> 16) == PCI_BASE_CLASS_DISPLAY) {
+			pci_dev_put(dev);
+			continue;
+		}
+		pci_configure_slot(dev);
+		pci_dev_put(dev);
+	}
+
+	pci_bus_add_devices(parent);
+
+	return 0;
+}
+
+int pciehp_unconfigure_device(struct slot *p_slot)
+{
+	int ret, rc = 0;
+	int j;
+	u8 bctl = 0;
+	u8 presence = 0;
+	struct pci_bus *parent = p_slot->ctrl->pcie->port->subordinate;
+	u16 command;
+	struct controller *ctrl = p_slot->ctrl;
+
+	ctrl_dbg(ctrl, "%s: domain:bus:dev = %04x:%02x:00\n",
+		 __func__, pci_domain_nr(parent), parent->number);
+	ret = pciehp_get_adapter_status(p_slot, &presence);
+	if (ret)
+		presence = 0;
+
+	for (j = 0; j < 8; j++) {
+		struct pci_dev *temp = pci_get_slot(parent, PCI_DEVFN(0, j));
+		if (!temp)
+			continue;
+		if (temp->hdr_type == PCI_HEADER_TYPE_BRIDGE && presence) {
+			pci_read_config_byte(temp, PCI_BRIDGE_CONTROL, &bctl);
+			if (bctl & PCI_BRIDGE_CTL_VGA) {
+				ctrl_err(ctrl,
+					 "Cannot remove display device %s\n",
+					 pci_name(temp));
+				pci_dev_put(temp);
+				rc = -EINVAL;
+				break;
+			}
+		}
+		pci_remove_bus_device(temp);
+		/*
+		 * Ensure that no new Requests will be generated from
+		 * the device.
+		 */
+		if (presence) {
+			pci_read_config_word(temp, PCI_COMMAND, &command);
+			command &= ~(PCI_COMMAND_MASTER | PCI_COMMAND_SERR);
+			command |= PCI_COMMAND_INTX_DISABLE;
+			pci_write_config_word(temp, PCI_COMMAND, command);
+		}
+		pci_dev_put(temp);
+	}
+
+	return rc;
+}
diff --git a/drivers/pci/hotplug/pcihp_skeleton.c b/drivers/pci/hotplug/pcihp_skeleton.c
new file mode 100644
index 00000000..5175d9b2
--- /dev/null
+++ b/drivers/pci/hotplug/pcihp_skeleton.c
@@ -0,0 +1,359 @@
+/*
+ * PCI Hot Plug Controller Skeleton Driver - 0.3
+ *
+ * Copyright (C) 2001,2003 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001,2003 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * This driver is to be used as a skeleton driver to show how to interface
+ * with the pci hotplug core easily.
+ *
+ * Send feedback to <greg@kroah.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/init.h>
+
+#define SLOT_NAME_SIZE	10
+struct slot {
+	u8 number;
+	struct hotplug_slot *hotplug_slot;
+	struct list_head slot_list;
+	char name[SLOT_NAME_SIZE];
+};
+
+static LIST_HEAD(slot_list);
+
+#define MY_NAME	"pcihp_skeleton"
+
+#define dbg(format, arg...)					\
+	do {							\
+		if (debug)					\
+			printk (KERN_DEBUG "%s: " format "\n",	\
+				MY_NAME , ## arg); 		\
+	} while (0)
+#define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
+#define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
+#define warn(format, arg...) printk(KERN_WARNING "%s: " format "\n", MY_NAME , ## arg)
+
+/* local variables */
+static int debug;
+static int num_slots;
+
+#define DRIVER_VERSION	"0.3"
+#define DRIVER_AUTHOR	"Greg Kroah-Hartman <greg@kroah.com>"
+#define DRIVER_DESC	"Hot Plug PCI Controller Skeleton Driver"
+
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+module_param(debug, bool, 0644);
+MODULE_PARM_DESC(debug, "Debugging mode enabled or not");
+
+static int enable_slot		(struct hotplug_slot *slot);
+static int disable_slot		(struct hotplug_slot *slot);
+static int set_attention_status (struct hotplug_slot *slot, u8 value);
+static int hardware_test	(struct hotplug_slot *slot, u32 value);
+static int get_power_status	(struct hotplug_slot *slot, u8 *value);
+static int get_attention_status	(struct hotplug_slot *slot, u8 *value);
+static int get_latch_status	(struct hotplug_slot *slot, u8 *value);
+static int get_adapter_status	(struct hotplug_slot *slot, u8 *value);
+
+static struct hotplug_slot_ops skel_hotplug_slot_ops = {
+	.enable_slot =		enable_slot,
+	.disable_slot =		disable_slot,
+	.set_attention_status =	set_attention_status,
+	.hardware_test =	hardware_test,
+	.get_power_status =	get_power_status,
+	.get_attention_status =	get_attention_status,
+	.get_latch_status =	get_latch_status,
+	.get_adapter_status =	get_adapter_status,
+};
+
+static int enable_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+	int retval = 0;
+
+	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
+
+	/*
+	 * Fill in code here to enable the specified slot
+	 */
+
+	return retval;
+}
+
+static int disable_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+	int retval = 0;
+
+	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
+
+	/*
+	 * Fill in code here to disable the specified slot
+	 */
+
+	return retval;
+}
+
+static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status)
+{
+	struct slot *slot = hotplug_slot->private;
+	int retval = 0;
+
+	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
+
+	switch (status) {
+		case 0:
+			/*
+			 * Fill in code here to turn light off
+			 */
+			break;
+
+		case 1:
+		default:
+			/*
+			 * Fill in code here to turn light on
+			 */
+			break;
+	}
+
+	return retval;
+}
+
+static int hardware_test(struct hotplug_slot *hotplug_slot, u32 value)
+{
+	struct slot *slot = hotplug_slot->private;
+	int retval = 0;
+
+	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
+
+	switch (value) {
+		case 0:
+			/* Specify a test here */
+			break;
+		case 1:
+			/* Specify another test here */
+			break;
+	}
+
+	return retval;
+}
+
+static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = hotplug_slot->private;
+	int retval = 0;
+
+	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
+
+	/*
+	 * Fill in logic to get the current power status of the specific
+	 * slot and store it in the *value location.
+	 */
+
+	return retval;
+}
+
+static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = hotplug_slot->private;
+	int retval = 0;
+
+	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
+
+	/*
+	 * Fill in logic to get the current attention status of the specific
+	 * slot and store it in the *value location.
+	 */
+
+	return retval;
+}
+
+static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = hotplug_slot->private;
+	int retval = 0;
+
+	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
+
+	/*
+	 * Fill in logic to get the current latch status of the specific
+	 * slot and store it in the *value location.
+	 */
+
+	return retval;
+}
+
+static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = hotplug_slot->private;
+	int retval = 0;
+
+	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
+
+	/*
+	 * Fill in logic to get the current adapter status of the specific
+	 * slot and store it in the *value location.
+	 */
+
+	return retval;
+}
+
+static void release_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
+	kfree(slot->hotplug_slot->info);
+	kfree(slot->hotplug_slot);
+	kfree(slot);
+}
+
+static void make_slot_name(struct slot *slot)
+{
+	/*
+	 * Stupid way to make a filename out of the slot name.
+	 * replace this if your hardware provides a better way to name slots.
+	 */
+	snprintf(slot->hotplug_slot->name, SLOT_NAME_SIZE, "%d", slot->number);
+}
+
+/**
+ * init_slots - initialize 'struct slot' structures for each slot
+ *
+ */
+static int __init init_slots(void)
+{
+	struct slot *slot;
+	struct hotplug_slot *hotplug_slot;
+	struct hotplug_slot_info *info;
+	int retval = -ENOMEM;
+	int i;
+
+	/*
+	 * Create a structure for each slot, and register that slot
+	 * with the pci_hotplug subsystem.
+	 */
+	for (i = 0; i < num_slots; ++i) {
+		slot = kzalloc(sizeof(*slot), GFP_KERNEL);
+		if (!slot)
+			goto error;
+
+		hotplug_slot = kzalloc(sizeof(*hotplug_slot), GFP_KERNEL);
+		if (!hotplug_slot)
+			goto error_slot;
+		slot->hotplug_slot = hotplug_slot;
+
+		info = kzalloc(sizeof(*info), GFP_KERNEL);
+		if (!info)
+			goto error_hpslot;
+		hotplug_slot->info = info;
+
+		slot->number = i;
+
+		hotplug_slot->name = slot->name;
+		hotplug_slot->private = slot;
+		hotplug_slot->release = &release_slot;
+		make_slot_name(slot);
+		hotplug_slot->ops = &skel_hotplug_slot_ops;
+		
+		/*
+		 * Initialize the slot info structure with some known
+		 * good values.
+		 */
+		get_power_status(hotplug_slot, &info->power_status);
+		get_attention_status(hotplug_slot, &info->attention_status);
+		get_latch_status(hotplug_slot, &info->latch_status);
+		get_adapter_status(hotplug_slot, &info->adapter_status);
+		
+		dbg("registering slot %d\n", i);
+		retval = pci_hp_register(slot->hotplug_slot);
+		if (retval) {
+			err("pci_hp_register failed with error %d\n", retval);
+			goto error_info;
+		}
+
+		/* add slot to our internal list */
+		list_add(&slot->slot_list, &slot_list);
+	}
+
+	return 0;
+error_info:
+	kfree(info);
+error_hpslot:
+	kfree(hotplug_slot);
+error_slot:
+	kfree(slot);
+error:
+	return retval;
+}
+
+static void __exit cleanup_slots(void)
+{
+	struct list_head *tmp;
+	struct list_head *next;
+	struct slot *slot;
+
+	/*
+	 * Unregister all of our slots with the pci_hotplug subsystem.
+	 * Memory will be freed in release_slot() callback after slot's
+	 * lifespan is finished.
+	 */
+	list_for_each_safe(tmp, next, &slot_list) {
+		slot = list_entry(tmp, struct slot, slot_list);
+		list_del(&slot->slot_list);
+		pci_hp_deregister(slot->hotplug_slot);
+	}
+}
+		
+static int __init pcihp_skel_init(void)
+{
+	int retval;
+
+	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
+	/*
+	 * Do specific initialization stuff for your driver here
+	 * like initializing your controller hardware (if any) and
+	 * determining the number of slots you have in the system
+	 * right now.
+	 */
+	num_slots = 5;
+
+	return init_slots();
+}
+
+static void __exit pcihp_skel_exit(void)
+{
+	/*
+	 * Clean everything up.
+	 */
+	cleanup_slots();
+}
+
+module_init(pcihp_skel_init);
+module_exit(pcihp_skel_exit);
diff --git a/drivers/pci/hotplug/pcihp_slot.c b/drivers/pci/hotplug/pcihp_slot.c
new file mode 100644
index 00000000..749fdf07
--- /dev/null
+++ b/drivers/pci/hotplug/pcihp_slot.c
@@ -0,0 +1,232 @@
+/*
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ * Copyright (C) 2003-2004 Intel Corporation
+ * (c) Copyright 2009 Hewlett-Packard Development Company, L.P.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+
+static struct hpp_type0 pci_default_type0 = {
+	.revision = 1,
+	.cache_line_size = 8,
+	.latency_timer = 0x40,
+	.enable_serr = 0,
+	.enable_perr = 0,
+};
+
+static void program_hpp_type0(struct pci_dev *dev, struct hpp_type0 *hpp)
+{
+	u16 pci_cmd, pci_bctl;
+
+	if (!hpp) {
+		/*
+		 * Perhaps we *should* use default settings for PCIe, but
+		 * pciehp didn't, so we won't either.
+		 */
+		if (pci_is_pcie(dev))
+			return;
+		dev_info(&dev->dev, "using default PCI settings\n");
+		hpp = &pci_default_type0;
+	}
+
+	if (hpp->revision > 1) {
+		dev_warn(&dev->dev,
+			 "PCI settings rev %d not supported; using defaults\n",
+			 hpp->revision);
+		hpp = &pci_default_type0;
+	}
+
+	pci_write_config_byte(dev, PCI_CACHE_LINE_SIZE, hpp->cache_line_size);
+	pci_write_config_byte(dev, PCI_LATENCY_TIMER, hpp->latency_timer);
+	pci_read_config_word(dev, PCI_COMMAND, &pci_cmd);
+	if (hpp->enable_serr)
+		pci_cmd |= PCI_COMMAND_SERR;
+	else
+		pci_cmd &= ~PCI_COMMAND_SERR;
+	if (hpp->enable_perr)
+		pci_cmd |= PCI_COMMAND_PARITY;
+	else
+		pci_cmd &= ~PCI_COMMAND_PARITY;
+	pci_write_config_word(dev, PCI_COMMAND, pci_cmd);
+
+	/* Program bridge control value */
+	if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) {
+		pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER,
+				      hpp->latency_timer);
+		pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &pci_bctl);
+		if (hpp->enable_serr)
+			pci_bctl |= PCI_BRIDGE_CTL_SERR;
+		else
+			pci_bctl &= ~PCI_BRIDGE_CTL_SERR;
+		if (hpp->enable_perr)
+			pci_bctl |= PCI_BRIDGE_CTL_PARITY;
+		else
+			pci_bctl &= ~PCI_BRIDGE_CTL_PARITY;
+		pci_write_config_word(dev, PCI_BRIDGE_CONTROL, pci_bctl);
+	}
+}
+
+static void program_hpp_type1(struct pci_dev *dev, struct hpp_type1 *hpp)
+{
+	if (hpp)
+		dev_warn(&dev->dev, "PCI-X settings not supported\n");
+}
+
+static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp)
+{
+	int pos;
+	u16 reg16;
+	u32 reg32;
+
+	if (!hpp)
+		return;
+
+	/* Find PCI Express capability */
+	pos = pci_pcie_cap(dev);
+	if (!pos)
+		return;
+
+	if (hpp->revision > 1) {
+		dev_warn(&dev->dev, "PCIe settings rev %d not supported\n",
+			 hpp->revision);
+		return;
+	}
+
+	/* Initialize Device Control Register */
+	pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &reg16);
+	reg16 = (reg16 & hpp->pci_exp_devctl_and) | hpp->pci_exp_devctl_or;
+	pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, reg16);
+
+	/* Initialize Link Control Register */
+	if (dev->subordinate) {
+		pci_read_config_word(dev, pos + PCI_EXP_LNKCTL, &reg16);
+		reg16 = (reg16 & hpp->pci_exp_lnkctl_and)
+			| hpp->pci_exp_lnkctl_or;
+		pci_write_config_word(dev, pos + PCI_EXP_LNKCTL, reg16);
+	}
+
+	/* Find Advanced Error Reporting Enhanced Capability */
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	if (!pos)
+		return;
+
+	/* Initialize Uncorrectable Error Mask Register */
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, &reg32);
+	reg32 = (reg32 & hpp->unc_err_mask_and) | hpp->unc_err_mask_or;
+	pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, reg32);
+
+	/* Initialize Uncorrectable Error Severity Register */
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &reg32);
+	reg32 = (reg32 & hpp->unc_err_sever_and) | hpp->unc_err_sever_or;
+	pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, reg32);
+
+	/* Initialize Correctable Error Mask Register */
+	pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, &reg32);
+	reg32 = (reg32 & hpp->cor_err_mask_and) | hpp->cor_err_mask_or;
+	pci_write_config_dword(dev, pos + PCI_ERR_COR_MASK, reg32);
+
+	/* Initialize Advanced Error Capabilities and Control Register */
+	pci_read_config_dword(dev, pos + PCI_ERR_CAP, &reg32);
+	reg32 = (reg32 & hpp->adv_err_cap_and) | hpp->adv_err_cap_or;
+	pci_write_config_dword(dev, pos + PCI_ERR_CAP, reg32);
+
+	/*
+	 * FIXME: The following two registers are not supported yet.
+	 *
+	 *   o Secondary Uncorrectable Error Severity Register
+	 *   o Secondary Uncorrectable Error Mask Register
+	 */
+}
+
+/* Program PCIE MaxPayload setting on device: ensure parent maxpayload <= device */
+static int pci_set_payload(struct pci_dev *dev)
+{
+       int pos, ppos;
+       u16 pctl, psz;
+       u16 dctl, dsz, dcap, dmax;
+       struct pci_dev *parent;
+
+       parent = dev->bus->self;
+       pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
+       if (!pos)
+               return 0;
+
+       /* Read Device MaxPayload capability and setting */
+       pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &dctl);
+       pci_read_config_word(dev, pos + PCI_EXP_DEVCAP, &dcap);
+       dsz = (dctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5;
+       dmax = (dcap & PCI_EXP_DEVCAP_PAYLOAD);
+
+       /* Read Parent MaxPayload setting */
+       ppos = pci_find_capability(parent, PCI_CAP_ID_EXP);
+       if (!ppos)
+               return 0;
+       pci_read_config_word(parent, ppos + PCI_EXP_DEVCTL, &pctl);
+       psz = (pctl &  PCI_EXP_DEVCTL_PAYLOAD) >> 5;
+
+       /* If parent payload > device max payload -> error
+        * If parent payload > device payload -> set speed
+        * If parent payload <= device payload -> do nothing
+        */
+       if (psz > dmax)
+               return -1;
+       else if (psz > dsz) {
+               dev_info(&dev->dev, "Setting MaxPayload to %d\n", 128 << psz);
+               pci_write_config_word(dev, pos + PCI_EXP_DEVCTL,
+                                     (dctl & ~PCI_EXP_DEVCTL_PAYLOAD) +
+                                     (psz << 5));
+       }
+       return 0;
+}
+
+void pci_configure_slot(struct pci_dev *dev)
+{
+	struct pci_dev *cdev;
+	struct hotplug_params hpp;
+	int ret;
+
+	if (!(dev->hdr_type == PCI_HEADER_TYPE_NORMAL ||
+			(dev->hdr_type == PCI_HEADER_TYPE_BRIDGE &&
+			(dev->class >> 8) == PCI_CLASS_BRIDGE_PCI)))
+		return;
+
+       ret = pci_set_payload(dev);
+       if (ret)
+               dev_warn(&dev->dev, "could not set device max payload\n");
+
+	memset(&hpp, 0, sizeof(hpp));
+	ret = pci_get_hp_params(dev, &hpp);
+	if (ret)
+		dev_warn(&dev->dev, "no hotplug settings from platform\n");
+
+	program_hpp_type2(dev, hpp.t2);
+	program_hpp_type1(dev, hpp.t1);
+	program_hpp_type0(dev, hpp.t0);
+
+	if (dev->subordinate) {
+		list_for_each_entry(cdev, &dev->subordinate->devices,
+				    bus_list)
+			pci_configure_slot(cdev);
+	}
+}
+EXPORT_SYMBOL_GPL(pci_configure_slot);
diff --git a/drivers/pci/hotplug/rpadlpar.h b/drivers/pci/hotplug/rpadlpar.h
new file mode 100644
index 00000000..4a0a59b8
--- /dev/null
+++ b/drivers/pci/hotplug/rpadlpar.h
@@ -0,0 +1,24 @@
+/*
+ * Interface for Dynamic Logical Partitioning of I/O Slots on
+ * RPA-compliant PPC64 platform.
+ *
+ * John Rose <johnrose@austin.ibm.com>
+ * October 2003
+ *
+ * Copyright (C) 2003 IBM.
+ *
+ *      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.
+ */
+#ifndef _RPADLPAR_IO_H_
+#define _RPADLPAR_IO_H_
+
+extern int dlpar_sysfs_init(void);
+extern void dlpar_sysfs_exit(void);
+
+extern int dlpar_add_slot(char *drc_name);
+extern int dlpar_remove_slot(char *drc_name);
+
+#endif
diff --git a/drivers/pci/hotplug/rpadlpar_core.c b/drivers/pci/hotplug/rpadlpar_core.c
new file mode 100644
index 00000000..08303471
--- /dev/null
+++ b/drivers/pci/hotplug/rpadlpar_core.c
@@ -0,0 +1,471 @@
+/*
+ * Interface for Dynamic Logical Partitioning of I/O Slots on
+ * RPA-compliant PPC64 platform.
+ *
+ * John Rose <johnrose@austin.ibm.com>
+ * Linda Xie <lxie@us.ibm.com>
+ *
+ * October 2003
+ *
+ * Copyright (C) 2003 IBM.
+ *
+ *      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/init.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
+
+#include <asm/pci-bridge.h>
+#include <linux/mutex.h>
+#include <asm/rtas.h>
+#include <asm/vio.h>
+
+#include "../pci.h"
+#include "rpaphp.h"
+#include "rpadlpar.h"
+
+static DEFINE_MUTEX(rpadlpar_mutex);
+
+#define DLPAR_MODULE_NAME "rpadlpar_io"
+
+#define NODE_TYPE_VIO  1
+#define NODE_TYPE_SLOT 2
+#define NODE_TYPE_PHB  3
+
+static struct device_node *find_vio_slot_node(char *drc_name)
+{
+	struct device_node *parent = of_find_node_by_name(NULL, "vdevice");
+	struct device_node *dn = NULL;
+	char *name;
+	int rc;
+
+	if (!parent)
+		return NULL;
+
+	while ((dn = of_get_next_child(parent, dn))) {
+		rc = rpaphp_get_drc_props(dn, NULL, &name, NULL, NULL);
+		if ((rc == 0) && (!strcmp(drc_name, name)))
+			break;
+	}
+
+	return dn;
+}
+
+/* Find dlpar-capable pci node that contains the specified name and type */
+static struct device_node *find_php_slot_pci_node(char *drc_name,
+						  char *drc_type)
+{
+	struct device_node *np = NULL;
+	char *name;
+	char *type;
+	int rc;
+
+	while ((np = of_find_node_by_name(np, "pci"))) {
+		rc = rpaphp_get_drc_props(np, NULL, &name, &type, NULL);
+		if (rc == 0)
+			if (!strcmp(drc_name, name) && !strcmp(drc_type, type))
+				break;
+	}
+
+	return np;
+}
+
+static struct device_node *find_dlpar_node(char *drc_name, int *node_type)
+{
+	struct device_node *dn;
+
+	dn = find_php_slot_pci_node(drc_name, "SLOT");
+	if (dn) {
+		*node_type = NODE_TYPE_SLOT;
+		return dn;
+	}
+
+	dn = find_php_slot_pci_node(drc_name, "PHB");
+	if (dn) {
+		*node_type = NODE_TYPE_PHB;
+		return dn;
+	}
+
+	dn = find_vio_slot_node(drc_name);
+	if (dn) {
+		*node_type = NODE_TYPE_VIO;
+		return dn;
+	}
+
+	return NULL;
+}
+
+/**
+ * find_php_slot - return hotplug slot structure for device node
+ * @dn: target &device_node
+ *
+ * This routine will return the hotplug slot structure
+ * for a given device node. Note that built-in PCI slots
+ * may be dlpar-able, but not hot-pluggable, so this routine
+ * will return NULL for built-in PCI slots.
+ */
+static struct slot *find_php_slot(struct device_node *dn)
+{
+	struct list_head *tmp, *n;
+	struct slot *slot;
+
+	list_for_each_safe(tmp, n, &rpaphp_slot_head) {
+		slot = list_entry(tmp, struct slot, rpaphp_slot_list);
+		if (slot->dn == dn)
+			return slot;
+	}
+
+	return NULL;
+}
+
+static struct pci_dev *dlpar_find_new_dev(struct pci_bus *parent,
+					struct device_node *dev_dn)
+{
+	struct pci_dev *tmp = NULL;
+	struct device_node *child_dn;
+
+	list_for_each_entry(tmp, &parent->devices, bus_list) {
+		child_dn = pci_device_to_OF_node(tmp);
+		if (child_dn == dev_dn)
+			return tmp;
+	}
+	return NULL;
+}
+
+static void dlpar_pci_add_bus(struct device_node *dn)
+{
+	struct pci_dn *pdn = PCI_DN(dn);
+	struct pci_controller *phb = pdn->phb;
+	struct pci_dev *dev = NULL;
+
+	eeh_add_device_tree_early(dn);
+
+	/* Add EADS device to PHB bus, adding new entry to bus->devices */
+	dev = of_create_pci_dev(dn, phb->bus, pdn->devfn);
+	if (!dev) {
+		printk(KERN_ERR "%s: failed to create pci dev for %s\n",
+				__func__, dn->full_name);
+		return;
+	}
+
+	/* Scan below the new bridge */
+	if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE ||
+	    dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)
+		of_scan_pci_bridge(dn, dev);
+
+	/* Map IO space for child bus, which may or may not succeed */
+	pcibios_map_io_space(dev->subordinate);
+
+	/* Finish adding it : resource allocation, adding devices, etc...
+	 * Note that we need to perform the finish pass on the -parent-
+	 * bus of the EADS bridge so the bridge device itself gets
+	 * properly added
+	 */
+	pcibios_finish_adding_to_bus(phb->bus);
+}
+
+static int dlpar_add_pci_slot(char *drc_name, struct device_node *dn)
+{
+	struct pci_dev *dev;
+	struct pci_controller *phb;
+
+	if (pcibios_find_pci_bus(dn))
+		return -EINVAL;
+
+	/* Add pci bus */
+	dlpar_pci_add_bus(dn);
+
+	/* Confirm new bridge dev was created */
+	phb = PCI_DN(dn)->phb;
+	dev = dlpar_find_new_dev(phb->bus, dn);
+
+	if (!dev) {
+		printk(KERN_ERR "%s: unable to add bus %s\n", __func__,
+			drc_name);
+		return -EIO;
+	}
+
+	if (dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) {
+		printk(KERN_ERR "%s: unexpected header type %d, unable to add bus %s\n",
+			__func__, dev->hdr_type, drc_name);
+		return -EIO;
+	}
+
+	/* Add hotplug slot */
+	if (rpaphp_add_slot(dn)) {
+		printk(KERN_ERR "%s: unable to add hotplug slot %s\n",
+			__func__, drc_name);
+		return -EIO;
+	}
+	return 0;
+}
+
+static int dlpar_remove_phb(char *drc_name, struct device_node *dn)
+{
+	struct slot *slot;
+	struct pci_dn *pdn;
+	int rc = 0;
+
+	if (!pcibios_find_pci_bus(dn))
+		return -EINVAL;
+
+	/* If pci slot is hotplugable, use hotplug to remove it */
+	slot = find_php_slot(dn);
+	if (slot && rpaphp_deregister_slot(slot)) {
+		printk(KERN_ERR "%s: unable to remove hotplug slot %s\n",
+		       __func__, drc_name);
+		return -EIO;
+	}
+
+	pdn = dn->data;
+	BUG_ON(!pdn || !pdn->phb);
+	rc = remove_phb_dynamic(pdn->phb);
+	if (rc < 0)
+		return rc;
+
+	pdn->phb = NULL;
+
+	return 0;
+}
+
+static int dlpar_add_phb(char *drc_name, struct device_node *dn)
+{
+	struct pci_controller *phb;
+
+	if (PCI_DN(dn) && PCI_DN(dn)->phb) {
+		/* PHB already exists */
+		return -EINVAL;
+	}
+
+	phb = init_phb_dynamic(dn);
+	if (!phb)
+		return -EIO;
+
+	if (rpaphp_add_slot(dn)) {
+		printk(KERN_ERR "%s: unable to add hotplug slot %s\n",
+			__func__, drc_name);
+		return -EIO;
+	}
+	return 0;
+}
+
+static int dlpar_add_vio_slot(char *drc_name, struct device_node *dn)
+{
+	if (vio_find_node(dn))
+		return -EINVAL;
+
+	if (!vio_register_device_node(dn)) {
+		printk(KERN_ERR
+			"%s: failed to register vio node %s\n",
+			__func__, drc_name);
+		return -EIO;
+	}
+	return 0;
+}
+
+/**
+ * dlpar_add_slot - DLPAR add an I/O Slot
+ * @drc_name: drc-name of newly added slot
+ *
+ * Make the hotplug module and the kernel aware of a newly added I/O Slot.
+ * Return Codes:
+ * 0			Success
+ * -ENODEV		Not a valid drc_name
+ * -EINVAL		Slot already added
+ * -ERESTARTSYS		Signalled before obtaining lock
+ * -EIO			Internal PCI Error
+ */
+int dlpar_add_slot(char *drc_name)
+{
+	struct device_node *dn = NULL;
+	int node_type;
+	int rc = -EIO;
+
+	if (mutex_lock_interruptible(&rpadlpar_mutex))
+		return -ERESTARTSYS;
+
+	/* Find newly added node */
+	dn = find_dlpar_node(drc_name, &node_type);
+	if (!dn) {
+		rc = -ENODEV;
+		goto exit;
+	}
+
+	switch (node_type) {
+		case NODE_TYPE_VIO:
+			rc = dlpar_add_vio_slot(drc_name, dn);
+			break;
+		case NODE_TYPE_SLOT:
+			rc = dlpar_add_pci_slot(drc_name, dn);
+			break;
+		case NODE_TYPE_PHB:
+			rc = dlpar_add_phb(drc_name, dn);
+			break;
+	}
+
+	printk(KERN_INFO "%s: slot %s added\n", DLPAR_MODULE_NAME, drc_name);
+exit:
+	mutex_unlock(&rpadlpar_mutex);
+	return rc;
+}
+
+/**
+ * dlpar_remove_vio_slot - DLPAR remove a virtual I/O Slot
+ * @drc_name: drc-name of newly added slot
+ * @dn: &device_node
+ *
+ * Remove the kernel and hotplug representations of an I/O Slot.
+ * Return Codes:
+ * 0			Success
+ * -EINVAL		Vio dev doesn't exist
+ */
+static int dlpar_remove_vio_slot(char *drc_name, struct device_node *dn)
+{
+	struct vio_dev *vio_dev;
+
+	vio_dev = vio_find_node(dn);
+	if (!vio_dev)
+		return -EINVAL;
+
+	vio_unregister_device(vio_dev);
+	return 0;
+}
+
+/**
+ * dlpar_remove_pci_slot - DLPAR remove a PCI I/O Slot
+ * @drc_name: drc-name of newly added slot
+ * @dn: &device_node
+ *
+ * Remove the kernel and hotplug representations of a PCI I/O Slot.
+ * Return Codes:
+ * 0			Success
+ * -ENODEV		Not a valid drc_name
+ * -EIO			Internal PCI Error
+ */
+int dlpar_remove_pci_slot(char *drc_name, struct device_node *dn)
+{
+	struct pci_bus *bus;
+	struct slot *slot;
+
+	bus = pcibios_find_pci_bus(dn);
+	if (!bus)
+		return -EINVAL;
+
+	pr_debug("PCI: Removing PCI slot below EADS bridge %s\n",
+		 bus->self ? pci_name(bus->self) : "<!PHB!>");
+
+	slot = find_php_slot(dn);
+	if (slot) {
+		pr_debug("PCI: Removing hotplug slot for %04x:%02x...\n",
+			 pci_domain_nr(bus), bus->number);
+
+		if (rpaphp_deregister_slot(slot)) {
+			printk(KERN_ERR
+				"%s: unable to remove hotplug slot %s\n",
+				__func__, drc_name);
+			return -EIO;
+		}
+	}
+
+	/* Remove all devices below slot */
+	pcibios_remove_pci_devices(bus);
+
+	/* Unmap PCI IO space */
+	if (pcibios_unmap_io_space(bus)) {
+		printk(KERN_ERR "%s: failed to unmap bus range\n",
+			__func__);
+		return -ERANGE;
+	}
+
+	/* Remove the EADS bridge device itself */
+	BUG_ON(!bus->self);
+	pr_debug("PCI: Now removing bridge device %s\n", pci_name(bus->self));
+	eeh_remove_bus_device(bus->self);
+	pci_remove_bus_device(bus->self);
+
+	return 0;
+}
+
+/**
+ * dlpar_remove_slot - DLPAR remove an I/O Slot
+ * @drc_name: drc-name of newly added slot
+ *
+ * Remove the kernel and hotplug representations of an I/O Slot.
+ * Return Codes:
+ * 0			Success
+ * -ENODEV		Not a valid drc_name
+ * -EINVAL		Slot already removed
+ * -ERESTARTSYS		Signalled before obtaining lock
+ * -EIO			Internal Error
+ */
+int dlpar_remove_slot(char *drc_name)
+{
+	struct device_node *dn;
+	int node_type;
+	int rc = 0;
+
+	if (mutex_lock_interruptible(&rpadlpar_mutex))
+		return -ERESTARTSYS;
+
+	dn = find_dlpar_node(drc_name, &node_type);
+	if (!dn) {
+		rc = -ENODEV;
+		goto exit;
+	}
+
+	switch (node_type) {
+		case NODE_TYPE_VIO:
+			rc = dlpar_remove_vio_slot(drc_name, dn);
+			break;
+		case NODE_TYPE_PHB:
+			rc = dlpar_remove_phb(drc_name, dn);
+			break;
+		case NODE_TYPE_SLOT:
+			rc = dlpar_remove_pci_slot(drc_name, dn);
+			break;
+	}
+	vm_unmap_aliases();
+
+	printk(KERN_INFO "%s: slot %s removed\n", DLPAR_MODULE_NAME, drc_name);
+exit:
+	mutex_unlock(&rpadlpar_mutex);
+	return rc;
+}
+
+static inline int is_dlpar_capable(void)
+{
+	int rc = rtas_token("ibm,configure-connector");
+
+	return (int) (rc != RTAS_UNKNOWN_SERVICE);
+}
+
+int __init rpadlpar_io_init(void)
+{
+	int rc = 0;
+
+	if (!is_dlpar_capable()) {
+		printk(KERN_WARNING "%s: partition not DLPAR capable\n",
+			__func__);
+		return -EPERM;
+	}
+
+	rc = dlpar_sysfs_init();
+	return rc;
+}
+
+void rpadlpar_io_exit(void)
+{
+	dlpar_sysfs_exit();
+	return;
+}
+
+module_init(rpadlpar_io_init);
+module_exit(rpadlpar_io_exit);
+MODULE_LICENSE("GPL");
diff --git a/drivers/pci/hotplug/rpadlpar_sysfs.c b/drivers/pci/hotplug/rpadlpar_sysfs.c
new file mode 100644
index 00000000..a796301e
--- /dev/null
+++ b/drivers/pci/hotplug/rpadlpar_sysfs.c
@@ -0,0 +1,130 @@
+/*
+ * Interface for Dynamic Logical Partitioning of I/O Slots on
+ * RPA-compliant PPC64 platform.
+ *
+ * John Rose <johnrose@austin.ibm.com>
+ * October 2003
+ *
+ * Copyright (C) 2003 IBM.
+ *
+ *      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.
+ */
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include "rpadlpar.h"
+#include "../pci.h"
+
+#define DLPAR_KOBJ_NAME       "control"
+
+/* Those two have no quotes because they are passed to __ATTR() which
+ * stringifies the argument (yuck !)
+ */
+#define ADD_SLOT_ATTR_NAME    add_slot
+#define REMOVE_SLOT_ATTR_NAME remove_slot
+
+#define MAX_DRC_NAME_LEN 64
+
+static ssize_t add_slot_store(struct kobject *kobj, struct kobj_attribute *attr,
+			      const char *buf, size_t nbytes)
+{
+	char drc_name[MAX_DRC_NAME_LEN];
+	char *end;
+	int rc;
+
+	if (nbytes >= MAX_DRC_NAME_LEN)
+		return 0;
+
+	memcpy(drc_name, buf, nbytes);
+
+	end = strchr(drc_name, '\n');
+	if (!end)
+		end = &drc_name[nbytes];
+	*end = '\0';
+
+	rc = dlpar_add_slot(drc_name);
+	if (rc)
+		return rc;
+
+	return nbytes;
+}
+
+static ssize_t add_slot_show(struct kobject *kobj,
+			     struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "0\n");
+}
+
+static ssize_t remove_slot_store(struct kobject *kobj,
+				 struct kobj_attribute *attr,
+				 const char *buf, size_t nbytes)
+{
+	char drc_name[MAX_DRC_NAME_LEN];
+	int rc;
+	char *end;
+
+	if (nbytes >= MAX_DRC_NAME_LEN)
+		return 0;
+
+	memcpy(drc_name, buf, nbytes);
+
+	end = strchr(drc_name, '\n');
+	if (!end)
+		end = &drc_name[nbytes];
+	*end = '\0';
+
+	rc = dlpar_remove_slot(drc_name);
+	if (rc)
+		return rc;
+
+	return nbytes;
+}
+
+static ssize_t remove_slot_show(struct kobject *kobj,
+				struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "0\n");
+}
+
+static struct kobj_attribute add_slot_attr =
+	__ATTR(ADD_SLOT_ATTR_NAME, 0644, add_slot_show, add_slot_store);
+
+static struct kobj_attribute remove_slot_attr =
+	__ATTR(REMOVE_SLOT_ATTR_NAME, 0644, remove_slot_show, remove_slot_store);
+
+static struct attribute *default_attrs[] = {
+	&add_slot_attr.attr,
+	&remove_slot_attr.attr,
+	NULL,
+};
+
+static struct attribute_group dlpar_attr_group = {
+	.attrs = default_attrs,
+};
+
+static struct kobject *dlpar_kobj;
+
+int dlpar_sysfs_init(void)
+{
+	int error;
+
+	dlpar_kobj = kobject_create_and_add(DLPAR_KOBJ_NAME,
+					    &pci_slots_kset->kobj);
+	if (!dlpar_kobj)
+		return -EINVAL;
+
+	error = sysfs_create_group(dlpar_kobj, &dlpar_attr_group);
+	if (error)
+		kobject_put(dlpar_kobj);
+	return error;
+}
+
+void dlpar_sysfs_exit(void)
+{
+	sysfs_remove_group(dlpar_kobj, &dlpar_attr_group);
+	kobject_put(dlpar_kobj);
+}
diff --git a/drivers/pci/hotplug/rpaphp.h b/drivers/pci/hotplug/rpaphp.h
new file mode 100644
index 00000000..419919a8
--- /dev/null
+++ b/drivers/pci/hotplug/rpaphp.h
@@ -0,0 +1,103 @@
+/*
+ * PCI Hot Plug Controller Driver for RPA-compliant PPC64 platform.
+ *
+ * Copyright (C) 2003 Linda Xie <lxie@us.ibm.com>
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <lxie@us.ibm.com>,
+ *
+ */
+
+#ifndef _PPC64PHP_H
+#define _PPC64PHP_H
+
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+
+#define DR_INDICATOR 9002
+#define DR_ENTITY_SENSE 9003
+
+#define POWER_ON	100
+#define POWER_OFF	0
+
+#define LED_OFF		0
+#define LED_ON		1	/* continuous on */
+#define LED_ID		2	/* slow blinking */
+#define LED_ACTION	3	/* fast blinking */
+
+/* Sensor values from rtas_get-sensor */
+#define EMPTY           0	/* No card in slot */
+#define PRESENT         1	/* Card in slot */
+
+#define MY_NAME "rpaphp"
+extern int rpaphp_debug;
+#define dbg(format, arg...)					\
+	do {							\
+		if (rpaphp_debug)					\
+			printk(KERN_DEBUG "%s: " format,	\
+				MY_NAME , ## arg); 		\
+	} while (0)
+#define err(format, arg...) printk(KERN_ERR "%s: " format, MY_NAME , ## arg)
+#define info(format, arg...) printk(KERN_INFO "%s: " format, MY_NAME , ## arg)
+#define warn(format, arg...) printk(KERN_WARNING "%s: " format, MY_NAME , ## arg)
+
+/* slot states */
+
+#define	NOT_VALID	3
+#define	NOT_CONFIGURED	2
+#define	CONFIGURED	1
+#define	EMPTY		0
+
+/*
+ * struct slot - slot information for each *physical* slot
+ */
+struct slot {
+	struct list_head rpaphp_slot_list;
+	int state;
+	u32 index;
+	u32 type;
+	u32 power_domain;
+	char *name;
+	struct device_node *dn;
+	struct pci_bus *bus;
+	struct list_head *pci_devs;
+	struct hotplug_slot *hotplug_slot;
+};
+
+extern struct hotplug_slot_ops rpaphp_hotplug_slot_ops;
+extern struct list_head rpaphp_slot_head;
+
+/* function prototypes */
+
+/* rpaphp_pci.c */
+extern int rpaphp_enable_slot(struct slot *slot);
+extern int rpaphp_get_sensor_state(struct slot *slot, int *state);
+
+/* rpaphp_core.c */
+extern int rpaphp_add_slot(struct device_node *dn);
+extern int rpaphp_get_drc_props(struct device_node *dn, int *drc_index,
+		char **drc_name, char **drc_type, int *drc_power_domain);
+
+/* rpaphp_slot.c */
+extern void dealloc_slot_struct(struct slot *slot);
+extern struct slot *alloc_slot_struct(struct device_node *dn, int drc_index, char *drc_name, int power_domain);
+extern int rpaphp_register_slot(struct slot *slot);
+extern int rpaphp_deregister_slot(struct slot *slot);
+	
+#endif				/* _PPC64PHP_H */
diff --git a/drivers/pci/hotplug/rpaphp_core.c b/drivers/pci/hotplug/rpaphp_core.c
new file mode 100644
index 00000000..758adb5f
--- /dev/null
+++ b/drivers/pci/hotplug/rpaphp_core.c
@@ -0,0 +1,442 @@
+/*
+ * PCI Hot Plug Controller Driver for RPA-compliant PPC64 platform.
+ * Copyright (C) 2003 Linda Xie <lxie@us.ibm.com>
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <lxie@us.ibm.com>
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/vmalloc.h>
+#include <asm/eeh.h>       /* for eeh_add_device() */
+#include <asm/rtas.h>		/* rtas_call */
+#include <asm/pci-bridge.h>	/* for pci_controller */
+#include "../pci.h"		/* for pci_add_new_bus */
+				/* and pci_do_scan_bus */
+#include "rpaphp.h"
+
+int rpaphp_debug;
+LIST_HEAD(rpaphp_slot_head);
+
+#define DRIVER_VERSION	"0.1"
+#define DRIVER_AUTHOR	"Linda Xie <lxie@us.ibm.com>"
+#define DRIVER_DESC	"RPA HOT Plug PCI Controller Driver"
+
+#define MAX_LOC_CODE 128
+
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+
+module_param_named(debug, rpaphp_debug, bool, 0644);
+
+/**
+ * set_attention_status - set attention LED
+ * @hotplug_slot: target &hotplug_slot
+ * @value: LED control value
+ *
+ * echo 0 > attention -- set LED OFF
+ * echo 1 > attention -- set LED ON
+ * echo 2 > attention -- set LED ID(identify, light is blinking)
+ */
+static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 value)
+{
+	int rc;
+	struct slot *slot = (struct slot *)hotplug_slot->private;
+
+	switch (value) {
+	case 0:
+	case 1:
+	case 2:
+		break;
+	default:
+		value = 1;
+		break;
+	}
+
+	rc = rtas_set_indicator(DR_INDICATOR, slot->index, value);
+	if (!rc)
+		hotplug_slot->info->attention_status = value;
+
+	return rc;
+}
+
+/**
+ * get_power_status - get power status of a slot
+ * @hotplug_slot: slot to get status
+ * @value: pointer to store status
+ */
+static int get_power_status(struct hotplug_slot *hotplug_slot, u8 * value)
+{
+	int retval, level;
+	struct slot *slot = (struct slot *)hotplug_slot->private;
+
+	retval = rtas_get_power_level (slot->power_domain, &level);
+	if (!retval)
+		*value = level;
+	return retval;
+}
+
+/**
+ * get_attention_status - get attention LED status
+ * @hotplug_slot: slot to get status
+ * @value: pointer to store status
+ */
+static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 * value)
+{
+	struct slot *slot = (struct slot *)hotplug_slot->private;
+	*value = slot->hotplug_slot->info->attention_status;
+	return 0;
+}
+
+static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 * value)
+{
+	struct slot *slot = (struct slot *)hotplug_slot->private;
+	int rc, state;
+
+	rc = rpaphp_get_sensor_state(slot, &state);
+
+	*value = NOT_VALID;
+	if (rc)
+		return rc;
+
+	if (state == EMPTY)
+		*value = EMPTY;
+	else if (state == PRESENT)
+		*value = slot->state;
+
+	return 0;
+}
+
+static enum pci_bus_speed get_max_bus_speed(struct slot *slot)
+{
+	enum pci_bus_speed speed;
+	switch (slot->type) {
+	case 1:
+	case 2:
+	case 3:
+	case 4:
+	case 5:
+	case 6:
+		speed = PCI_SPEED_33MHz;	/* speed for case 1-6 */
+		break;
+	case 7:
+	case 8:
+		speed = PCI_SPEED_66MHz;
+		break;
+	case 11:
+	case 14:
+		speed = PCI_SPEED_66MHz_PCIX;
+		break;
+	case 12:
+	case 15:
+		speed = PCI_SPEED_100MHz_PCIX;
+		break;
+	case 13:
+	case 16:
+		speed = PCI_SPEED_133MHz_PCIX;
+		break;
+	default:
+		speed = PCI_SPEED_UNKNOWN;
+		break;
+	}
+
+	return speed;
+}
+
+static int get_children_props(struct device_node *dn, const int **drc_indexes,
+		const int **drc_names, const int **drc_types,
+		const int **drc_power_domains)
+{
+	const int *indexes, *names, *types, *domains;
+
+	indexes = of_get_property(dn, "ibm,drc-indexes", NULL);
+	names = of_get_property(dn, "ibm,drc-names", NULL);
+	types = of_get_property(dn, "ibm,drc-types", NULL);
+	domains = of_get_property(dn, "ibm,drc-power-domains", NULL);
+
+	if (!indexes || !names || !types || !domains) {
+		/* Slot does not have dynamically-removable children */
+		return -EINVAL;
+	}
+	if (drc_indexes)
+		*drc_indexes = indexes;
+	if (drc_names)
+		/* &drc_names[1] contains NULL terminated slot names */
+		*drc_names = names;
+	if (drc_types)
+		/* &drc_types[1] contains NULL terminated slot types */
+		*drc_types = types;
+	if (drc_power_domains)
+		*drc_power_domains = domains;
+
+	return 0;
+}
+
+/* To get the DRC props describing the current node, first obtain it's
+ * my-drc-index property.  Next obtain the DRC list from it's parent.  Use
+ * the my-drc-index for correlation, and obtain the requested properties.
+ */
+int rpaphp_get_drc_props(struct device_node *dn, int *drc_index,
+		char **drc_name, char **drc_type, int *drc_power_domain)
+{
+	const int *indexes, *names;
+	const int *types, *domains;
+	const unsigned int *my_index;
+	char *name_tmp, *type_tmp;
+	int i, rc;
+
+	my_index = of_get_property(dn, "ibm,my-drc-index", NULL);
+	if (!my_index) {
+		/* Node isn't DLPAR/hotplug capable */
+		return -EINVAL;
+	}
+
+	rc = get_children_props(dn->parent, &indexes, &names, &types, &domains);
+	if (rc < 0) {
+		return -EINVAL;
+	}
+
+	name_tmp = (char *) &names[1];
+	type_tmp = (char *) &types[1];
+
+	/* Iterate through parent properties, looking for my-drc-index */
+	for (i = 0; i < indexes[0]; i++) {
+		if ((unsigned int) indexes[i + 1] == *my_index) {
+			if (drc_name)
+                		*drc_name = name_tmp;
+			if (drc_type)
+				*drc_type = type_tmp;
+			if (drc_index)
+				*drc_index = *my_index;
+			if (drc_power_domain)
+				*drc_power_domain = domains[i+1];
+			return 0;
+		}
+		name_tmp += (strlen(name_tmp) + 1);
+		type_tmp += (strlen(type_tmp) + 1);
+	}
+
+	return -EINVAL;
+}
+
+static int is_php_type(char *drc_type)
+{
+	unsigned long value;
+	char *endptr;
+
+	/* PCI Hotplug nodes have an integer for drc_type */
+	value = simple_strtoul(drc_type, &endptr, 10);
+	if (endptr == drc_type)
+		return 0;
+
+	return 1;
+}
+
+/**
+ * is_php_dn() - return 1 if this is a hotpluggable pci slot, else 0
+ * @dn: target &device_node
+ * @indexes: passed to get_children_props()
+ * @names: passed to get_children_props()
+ * @types: returned from get_children_props()
+ * @power_domains:
+ *
+ * This routine will return true only if the device node is
+ * a hotpluggable slot. This routine will return false
+ * for built-in pci slots (even when the built-in slots are
+ * dlparable.)
+ */
+static int is_php_dn(struct device_node *dn, const int **indexes,
+		const int **names, const int **types, const int **power_domains)
+{
+	const int *drc_types;
+	int rc;
+
+	rc = get_children_props(dn, indexes, names, &drc_types, power_domains);
+	if (rc < 0)
+		return 0;
+
+	if (!is_php_type((char *) &drc_types[1]))
+		return 0;
+
+	*types = drc_types;
+	return 1;
+}
+
+/**
+ * rpaphp_add_slot -- declare a hotplug slot to the hotplug subsystem.
+ * @dn: device node of slot
+ *
+ * This subroutine will register a hotplugable slot with the
+ * PCI hotplug infrastructure. This routine is typically called
+ * during boot time, if the hotplug slots are present at boot time,
+ * or is called later, by the dlpar add code, if the slot is
+ * being dynamically added during runtime.
+ *
+ * If the device node points at an embedded (built-in) slot, this
+ * routine will just return without doing anything, since embedded
+ * slots cannot be hotplugged.
+ *
+ * To remove a slot, it suffices to call rpaphp_deregister_slot().
+ */
+int rpaphp_add_slot(struct device_node *dn)
+{
+	struct slot *slot;
+	int retval = 0;
+	int i;
+	const int *indexes, *names, *types, *power_domains;
+	char *name, *type;
+
+	if (!dn->name || strcmp(dn->name, "pci"))
+		return 0;
+
+	/* If this is not a hotplug slot, return without doing anything. */
+	if (!is_php_dn(dn, &indexes, &names, &types, &power_domains))
+		return 0;
+
+	dbg("Entry %s: dn->full_name=%s\n", __func__, dn->full_name);
+
+	/* register PCI devices */
+	name = (char *) &names[1];
+	type = (char *) &types[1];
+	for (i = 0; i < indexes[0]; i++) {
+
+		slot = alloc_slot_struct(dn, indexes[i + 1], name, power_domains[i + 1]);
+		if (!slot)
+			return -ENOMEM;
+
+		slot->type = simple_strtoul(type, NULL, 10);
+				
+		dbg("Found drc-index:0x%x drc-name:%s drc-type:%s\n",
+				indexes[i + 1], name, type);
+
+		retval = rpaphp_enable_slot(slot);
+		if (!retval)
+			retval = rpaphp_register_slot(slot);
+
+		if (retval)
+			dealloc_slot_struct(slot);
+
+		name += strlen(name) + 1;
+		type += strlen(type) + 1;
+	}
+	dbg("%s - Exit: rc[%d]\n", __func__, retval);
+
+	/* XXX FIXME: reports a failure only if last entry in loop failed */
+	return retval;
+}
+
+static void __exit cleanup_slots(void)
+{
+	struct list_head *tmp, *n;
+	struct slot *slot;
+
+	/*
+	 * Unregister all of our slots with the pci_hotplug subsystem,
+	 * and free up all memory that we had allocated.
+	 * memory will be freed in release_slot callback. 
+	 */
+
+	list_for_each_safe(tmp, n, &rpaphp_slot_head) {
+		slot = list_entry(tmp, struct slot, rpaphp_slot_list);
+		list_del(&slot->rpaphp_slot_list);
+		pci_hp_deregister(slot->hotplug_slot);
+	}
+	return;
+}
+
+static int __init rpaphp_init(void)
+{
+	struct device_node *dn = NULL;
+
+	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
+
+	while ((dn = of_find_node_by_name(dn, "pci")))
+		rpaphp_add_slot(dn);
+
+	return 0;
+}
+
+static void __exit rpaphp_exit(void)
+{
+	cleanup_slots();
+}
+
+static int enable_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = (struct slot *)hotplug_slot->private;
+	int state;
+	int retval;
+
+	if (slot->state == CONFIGURED)
+		return 0;
+
+	retval = rpaphp_get_sensor_state(slot, &state);
+	if (retval)
+		return retval;
+
+	if (state == PRESENT) {
+		pcibios_add_pci_devices(slot->bus);
+		slot->state = CONFIGURED;
+	} else if (state == EMPTY) {
+		slot->state = EMPTY;
+	} else {
+		err("%s: slot[%s] is in invalid state\n", __func__, slot->name);
+		slot->state = NOT_VALID;
+		return -EINVAL;
+	}
+
+	slot->bus->max_bus_speed = get_max_bus_speed(slot);
+	return 0;
+}
+
+static int disable_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = (struct slot *)hotplug_slot->private;
+	if (slot->state == NOT_CONFIGURED)
+		return -EINVAL;
+
+	pcibios_remove_pci_devices(slot->bus);
+	vm_unmap_aliases();
+
+	slot->state = NOT_CONFIGURED;
+	return 0;
+}
+
+struct hotplug_slot_ops rpaphp_hotplug_slot_ops = {
+	.enable_slot = enable_slot,
+	.disable_slot = disable_slot,
+	.set_attention_status = set_attention_status,
+	.get_power_status = get_power_status,
+	.get_attention_status = get_attention_status,
+	.get_adapter_status = get_adapter_status,
+};
+
+module_init(rpaphp_init);
+module_exit(rpaphp_exit);
+
+EXPORT_SYMBOL_GPL(rpaphp_add_slot);
+EXPORT_SYMBOL_GPL(rpaphp_slot_head);
+EXPORT_SYMBOL_GPL(rpaphp_get_drc_props);
diff --git a/drivers/pci/hotplug/rpaphp_pci.c b/drivers/pci/hotplug/rpaphp_pci.c
new file mode 100644
index 00000000..513e1e28
--- /dev/null
+++ b/drivers/pci/hotplug/rpaphp_pci.c
@@ -0,0 +1,136 @@
+/*
+ * PCI Hot Plug Controller Driver for RPA-compliant PPC64 platform.
+ * Copyright (C) 2003 Linda Xie <lxie@us.ibm.com>
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <lxie@us.ibm.com>
+ *
+ */
+#include <linux/pci.h>
+#include <linux/string.h>
+
+#include <asm/pci-bridge.h>
+#include <asm/rtas.h>
+#include <asm/machdep.h>
+
+#include "../pci.h"		/* for pci_add_new_bus */
+#include "rpaphp.h"
+
+int rpaphp_get_sensor_state(struct slot *slot, int *state)
+{
+	int rc;
+	int setlevel;
+
+	rc = rtas_get_sensor(DR_ENTITY_SENSE, slot->index, state);
+
+	if (rc < 0) {
+		if (rc == -EFAULT || rc == -EEXIST) {
+			dbg("%s: slot must be power up to get sensor-state\n",
+			    __func__);
+
+			/* some slots have to be powered up 
+			 * before get-sensor will succeed.
+			 */
+			rc = rtas_set_power_level(slot->power_domain, POWER_ON,
+						  &setlevel);
+			if (rc < 0) {
+				dbg("%s: power on slot[%s] failed rc=%d.\n",
+				    __func__, slot->name, rc);
+			} else {
+				rc = rtas_get_sensor(DR_ENTITY_SENSE,
+						     slot->index, state);
+			}
+		} else if (rc == -ENODEV)
+			info("%s: slot is unusable\n", __func__);
+		else
+			err("%s failed to get sensor state\n", __func__);
+	}
+	return rc;
+}
+
+/**
+ * rpaphp_enable_slot - record slot state, config pci device
+ * @slot: target &slot
+ *
+ * Initialize values in the slot, and the hotplug_slot info
+ * structures to indicate if there is a pci card plugged into
+ * the slot. If the slot is not empty, run the pcibios routine
+ * to get pcibios stuff correctly set up.
+ */
+int rpaphp_enable_slot(struct slot *slot)
+{
+	int rc, level, state;
+	struct pci_bus *bus;
+	struct hotplug_slot_info *info = slot->hotplug_slot->info;
+
+	info->adapter_status = NOT_VALID;
+	slot->state = EMPTY;
+
+	/* Find out if the power is turned on for the slot */
+	rc = rtas_get_power_level(slot->power_domain, &level);
+	if (rc)
+		return rc;
+	info->power_status = level;
+
+	/* Figure out if there is an adapter in the slot */
+	rc = rpaphp_get_sensor_state(slot, &state);
+	if (rc)
+		return rc;
+
+	bus = pcibios_find_pci_bus(slot->dn);
+	if (!bus) {
+		err("%s: no pci_bus for dn %s\n", __func__, slot->dn->full_name);
+		return -EINVAL;
+	}
+
+	info->adapter_status = EMPTY;
+	slot->bus = bus;
+	slot->pci_devs = &bus->devices;
+
+	/* if there's an adapter in the slot, go add the pci devices */
+	if (state == PRESENT) {
+		info->adapter_status = NOT_CONFIGURED;
+		slot->state = NOT_CONFIGURED;
+
+		/* non-empty slot has to have child */
+		if (!slot->dn->child) {
+			err("%s: slot[%s]'s device_node doesn't have child for adapter\n",
+			    __func__, slot->name);
+			return -EINVAL;
+		}
+
+		if (list_empty(&bus->devices))
+			pcibios_add_pci_devices(bus);
+
+		if (!list_empty(&bus->devices)) {
+			info->adapter_status = CONFIGURED;
+			slot->state = CONFIGURED;
+		}
+
+		if (rpaphp_debug) {
+			struct pci_dev *dev;
+			dbg("%s: pci_devs of slot[%s]\n", __func__, slot->dn->full_name);
+			list_for_each_entry (dev, &bus->devices, bus_list)
+				dbg("\t%s\n", pci_name(dev));
+		}
+	}
+
+	return 0;
+}
+
diff --git a/drivers/pci/hotplug/rpaphp_slot.c b/drivers/pci/hotplug/rpaphp_slot.c
new file mode 100644
index 00000000..b283bbea
--- /dev/null
+++ b/drivers/pci/hotplug/rpaphp_slot.c
@@ -0,0 +1,148 @@
+/*
+ * RPA Virtual I/O device functions 
+ * Copyright (C) 2004 Linda Xie <lxie@us.ibm.com>
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <lxie@us.ibm.com>
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sysfs.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+
+#include <asm/rtas.h>
+#include "rpaphp.h"
+
+/* free up the memory used by a slot */
+static void rpaphp_release_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = (struct slot *) hotplug_slot->private;
+	dealloc_slot_struct(slot);
+}
+
+void dealloc_slot_struct(struct slot *slot)
+{
+	kfree(slot->hotplug_slot->info);
+	kfree(slot->name);
+	kfree(slot->hotplug_slot);
+	kfree(slot);
+}
+
+struct slot *alloc_slot_struct(struct device_node *dn,
+                       int drc_index, char *drc_name, int power_domain)
+{
+	struct slot *slot;
+	
+	slot = kzalloc(sizeof(struct slot), GFP_KERNEL);
+	if (!slot)
+		goto error_nomem;
+	slot->hotplug_slot = kzalloc(sizeof(struct hotplug_slot), GFP_KERNEL);
+	if (!slot->hotplug_slot)
+		goto error_slot;	
+	slot->hotplug_slot->info = kzalloc(sizeof(struct hotplug_slot_info),
+					   GFP_KERNEL);
+	if (!slot->hotplug_slot->info)
+		goto error_hpslot;
+	slot->name = kstrdup(drc_name, GFP_KERNEL);
+	if (!slot->name)
+		goto error_info;	
+	slot->dn = dn;
+	slot->index = drc_index;
+	slot->power_domain = power_domain;
+	slot->hotplug_slot->private = slot;
+	slot->hotplug_slot->ops = &rpaphp_hotplug_slot_ops;
+	slot->hotplug_slot->release = &rpaphp_release_slot;
+	
+	return (slot);
+
+error_info:
+	kfree(slot->hotplug_slot->info);
+error_hpslot:
+	kfree(slot->hotplug_slot);
+error_slot:
+	kfree(slot);
+error_nomem:
+	return NULL;
+}
+
+static int is_registered(struct slot *slot)
+{
+	struct slot *tmp_slot;
+
+	list_for_each_entry(tmp_slot, &rpaphp_slot_head, rpaphp_slot_list) {
+		if (!strcmp(tmp_slot->name, slot->name))
+			return 1;
+	}	
+	return 0;
+}
+
+int rpaphp_deregister_slot(struct slot *slot)
+{
+	int retval = 0;
+	struct hotplug_slot *php_slot = slot->hotplug_slot;
+
+	 dbg("%s - Entry: deregistering slot=%s\n",
+		__func__, slot->name);
+
+	list_del(&slot->rpaphp_slot_list);
+	
+	retval = pci_hp_deregister(php_slot);
+	if (retval)
+		err("Problem unregistering a slot %s\n", slot->name);
+
+	dbg("%s - Exit: rc[%d]\n", __func__, retval);
+	return retval;
+}
+EXPORT_SYMBOL_GPL(rpaphp_deregister_slot);
+
+int rpaphp_register_slot(struct slot *slot)
+{
+	struct hotplug_slot *php_slot = slot->hotplug_slot;
+	int retval;
+	int slotno;
+
+	dbg("%s registering slot:path[%s] index[%x], name[%s] pdomain[%x] type[%d]\n", 
+		__func__, slot->dn->full_name, slot->index, slot->name,
+		slot->power_domain, slot->type);
+
+	/* should not try to register the same slot twice */
+	if (is_registered(slot)) {
+		err("rpaphp_register_slot: slot[%s] is already registered\n", slot->name);
+		return -EAGAIN;
+	}	
+
+	if (slot->dn->child)
+		slotno = PCI_SLOT(PCI_DN(slot->dn->child)->devfn);
+	else
+		slotno = -1;
+	retval = pci_hp_register(php_slot, slot->bus, slotno, slot->name);
+	if (retval) {
+		err("pci_hp_register failed with error %d\n", retval);
+		return retval;
+	}
+
+	/* add slot to our internal list */
+	list_add(&slot->rpaphp_slot_list, &rpaphp_slot_head);
+	info("Slot [%s] registered\n", slot->name);
+	return 0;
+}
+
diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c
new file mode 100644
index 00000000..72d507b6
--- /dev/null
+++ b/drivers/pci/hotplug/sgi_hotplug.c
@@ -0,0 +1,730 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2005-2006 Silicon Graphics, Inc. All rights reserved.
+ *
+ * This work was based on the 2.4/2.6 kernel development by Dick Reigner.
+ * Work to add BIOS PROM support was completed by Mike Habeck.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/proc_fs.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/mutex.h>
+
+#include <asm/sn/addrs.h>
+#include <asm/sn/geo.h>
+#include <asm/sn/l1.h>
+#include <asm/sn/module.h>
+#include <asm/sn/pcibr_provider.h>
+#include <asm/sn/pcibus_provider_defs.h>
+#include <asm/sn/pcidev.h>
+#include <asm/sn/sn_feature_sets.h>
+#include <asm/sn/sn_sal.h>
+#include <asm/sn/types.h>
+#include <linux/acpi.h>
+#include <asm/sn/acpi.h>
+
+#include "../pci.h"
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("SGI (prarit@sgi.com, dickie@sgi.com, habeck@sgi.com)");
+MODULE_DESCRIPTION("SGI Altix Hot Plug PCI Controller Driver");
+
+
+/* SAL call error codes. Keep in sync with prom header io/include/pcibr.h */
+#define PCI_SLOT_ALREADY_UP		2	/* slot already up */
+#define PCI_SLOT_ALREADY_DOWN		3	/* slot already down */
+#define PCI_L1_ERR			7	/* L1 console command error */
+#define PCI_EMPTY_33MHZ			15	/* empty 33 MHz bus */
+
+
+#define PCIIO_ASIC_TYPE_TIOCA		4
+#define PCI_L1_QSIZE			128	/* our L1 message buffer size */
+#define SN_MAX_HP_SLOTS			32	/* max hotplug slots */
+#define SN_SLOT_NAME_SIZE		33	/* size of name string */
+
+/* internal list head */
+static struct list_head sn_hp_list;
+
+/* hotplug_slot struct's private pointer */
+struct slot {
+	int device_num;
+	struct pci_bus *pci_bus;
+	/* this struct for glue internal only */
+	struct hotplug_slot *hotplug_slot;
+	struct list_head hp_list;
+	char physical_path[SN_SLOT_NAME_SIZE];
+};
+
+struct pcibr_slot_enable_resp {
+	int resp_sub_errno;
+	char resp_l1_msg[PCI_L1_QSIZE + 1];
+};
+
+struct pcibr_slot_disable_resp {
+	int resp_sub_errno;
+	char resp_l1_msg[PCI_L1_QSIZE + 1];
+};
+
+enum sn_pci_req_e {
+	PCI_REQ_SLOT_ELIGIBLE,
+	PCI_REQ_SLOT_DISABLE
+};
+
+static int enable_slot(struct hotplug_slot *slot);
+static int disable_slot(struct hotplug_slot *slot);
+static inline int get_power_status(struct hotplug_slot *slot, u8 *value);
+
+static struct hotplug_slot_ops sn_hotplug_slot_ops = {
+	.enable_slot            = enable_slot,
+	.disable_slot           = disable_slot,
+	.get_power_status       = get_power_status,
+};
+
+static DEFINE_MUTEX(sn_hotplug_mutex);
+
+static ssize_t path_show(struct pci_slot *pci_slot, char *buf)
+{
+	int retval = -ENOENT;
+	struct slot *slot = pci_slot->hotplug->private;
+
+	if (!slot)
+		return retval;
+
+	retval = sprintf (buf, "%s\n", slot->physical_path);
+	return retval;
+}
+
+static struct pci_slot_attribute sn_slot_path_attr = __ATTR_RO(path);
+
+static int sn_pci_slot_valid(struct pci_bus *pci_bus, int device)
+{
+	struct pcibus_info *pcibus_info;
+	u16 busnum, segment, ioboard_type;
+
+	pcibus_info = SN_PCIBUS_BUSSOFT_INFO(pci_bus);
+
+	/* Check to see if this is a valid slot on 'pci_bus' */
+	if (!(pcibus_info->pbi_valid_devices & (1 << device)))
+		return -EPERM;
+
+	ioboard_type = sn_ioboard_to_pci_bus(pci_bus);
+	busnum = pcibus_info->pbi_buscommon.bs_persist_busnum;
+	segment = pci_domain_nr(pci_bus) & 0xf;
+
+	/* Do not allow hotplug operations on base I/O cards */
+	if ((ioboard_type == L1_BRICKTYPE_IX ||
+	     ioboard_type == L1_BRICKTYPE_IA) &&
+	    (segment == 1 && busnum == 0 && device != 1))
+		return -EPERM;
+
+	return 1;
+}
+
+static int sn_pci_bus_valid(struct pci_bus *pci_bus)
+{
+	struct pcibus_info *pcibus_info;
+	u32 asic_type;
+	u16 ioboard_type;
+
+	/* Don't register slots hanging off the TIOCA bus */
+	pcibus_info = SN_PCIBUS_BUSSOFT_INFO(pci_bus);
+	asic_type = pcibus_info->pbi_buscommon.bs_asic_type;
+	if (asic_type == PCIIO_ASIC_TYPE_TIOCA)
+		return -EPERM;
+
+	/* Only register slots in I/O Bricks that support hotplug */
+	ioboard_type = sn_ioboard_to_pci_bus(pci_bus);
+	switch (ioboard_type) {
+		case L1_BRICKTYPE_IX:
+		case L1_BRICKTYPE_PX:
+		case L1_BRICKTYPE_IA:
+		case L1_BRICKTYPE_PA:
+		case L1_BOARDTYPE_PCIX3SLOT:
+			return 1;
+			break;
+		default:
+			return -EPERM;
+			break;
+	}
+
+	return -EIO;
+}
+
+static int sn_hp_slot_private_alloc(struct hotplug_slot *bss_hotplug_slot,
+				    struct pci_bus *pci_bus, int device,
+				    char *name)
+{
+	struct pcibus_info *pcibus_info;
+	struct slot *slot;
+
+	pcibus_info = SN_PCIBUS_BUSSOFT_INFO(pci_bus);
+
+	slot = kzalloc(sizeof(*slot), GFP_KERNEL);
+	if (!slot)
+		return -ENOMEM;
+	bss_hotplug_slot->private = slot;
+
+	slot->device_num = device;
+	slot->pci_bus = pci_bus;
+	sprintf(name, "%04x:%02x:%02x",
+		pci_domain_nr(pci_bus),
+		((u16)pcibus_info->pbi_buscommon.bs_persist_busnum),
+		device + 1);
+
+	sn_generate_path(pci_bus, slot->physical_path);
+
+	slot->hotplug_slot = bss_hotplug_slot;
+	list_add(&slot->hp_list, &sn_hp_list);
+
+	return 0;
+}
+
+static struct hotplug_slot * sn_hp_destroy(void)
+{
+	struct slot *slot;
+	struct pci_slot *pci_slot;
+	struct hotplug_slot *bss_hotplug_slot = NULL;
+
+	list_for_each_entry(slot, &sn_hp_list, hp_list) {
+		bss_hotplug_slot = slot->hotplug_slot;
+		pci_slot = bss_hotplug_slot->pci_slot;
+		list_del(&((struct slot *)bss_hotplug_slot->private)->
+			 hp_list);
+		sysfs_remove_file(&pci_slot->kobj,
+				  &sn_slot_path_attr.attr);
+		break;
+	}
+	return bss_hotplug_slot;
+}
+
+static void sn_bus_free_data(struct pci_dev *dev)
+{
+	struct pci_bus *subordinate_bus;
+	struct pci_dev *child;
+
+	/* Recursively clean up sn_irq_info structs */
+	if (dev->subordinate) {
+		subordinate_bus = dev->subordinate;
+		list_for_each_entry(child, &subordinate_bus->devices, bus_list)
+			sn_bus_free_data(child);
+	}
+	/*
+	 * Some drivers may use dma accesses during the
+	 * driver remove function. We release the sysdata
+	 * areas after the driver remove functions have
+	 * been called.
+	 */
+	sn_bus_store_sysdata(dev);
+	sn_pci_unfixup_slot(dev);
+}
+
+static int sn_slot_enable(struct hotplug_slot *bss_hotplug_slot,
+			  int device_num, char **ssdt)
+{
+	struct slot *slot = bss_hotplug_slot->private;
+	struct pcibus_info *pcibus_info;
+	struct pcibr_slot_enable_resp resp;
+	int rc;
+
+	pcibus_info = SN_PCIBUS_BUSSOFT_INFO(slot->pci_bus);
+
+	/*
+	 * Power-on and initialize the slot in the SN
+	 * PCI infrastructure.
+	 */
+	rc = sal_pcibr_slot_enable(pcibus_info, device_num, &resp, ssdt);
+
+
+	if (rc == PCI_SLOT_ALREADY_UP) {
+		dev_dbg(&slot->pci_bus->self->dev, "is already active\n");
+		return 1; /* return 1 to user */
+	}
+
+	if (rc == PCI_L1_ERR) {
+		dev_dbg(&slot->pci_bus->self->dev,
+			"L1 failure %d with message: %s",
+			resp.resp_sub_errno, resp.resp_l1_msg);
+		return -EPERM;
+	}
+
+	if (rc) {
+		dev_dbg(&slot->pci_bus->self->dev,
+			"insert failed with error %d sub-error %d\n",
+			rc, resp.resp_sub_errno);
+		return -EIO;
+	}
+
+	pcibus_info = SN_PCIBUS_BUSSOFT_INFO(slot->pci_bus);
+	pcibus_info->pbi_enabled_devices |= (1 << device_num);
+
+	return 0;
+}
+
+static int sn_slot_disable(struct hotplug_slot *bss_hotplug_slot,
+			   int device_num, int action)
+{
+	struct slot *slot = bss_hotplug_slot->private;
+	struct pcibus_info *pcibus_info;
+	struct pcibr_slot_disable_resp resp;
+	int rc;
+
+	pcibus_info = SN_PCIBUS_BUSSOFT_INFO(slot->pci_bus);
+
+	rc = sal_pcibr_slot_disable(pcibus_info, device_num, action, &resp);
+
+	if ((action == PCI_REQ_SLOT_ELIGIBLE) &&
+	    (rc == PCI_SLOT_ALREADY_DOWN)) {
+		dev_dbg(&slot->pci_bus->self->dev, "Slot %s already inactive\n", slot->physical_path);
+		return 1; /* return 1 to user */
+	}
+
+	if ((action == PCI_REQ_SLOT_ELIGIBLE) && (rc == PCI_EMPTY_33MHZ)) {
+		dev_dbg(&slot->pci_bus->self->dev,
+			"Cannot remove last 33MHz card\n");
+		return -EPERM;
+	}
+
+	if ((action == PCI_REQ_SLOT_ELIGIBLE) && (rc == PCI_L1_ERR)) {
+		dev_dbg(&slot->pci_bus->self->dev,
+			"L1 failure %d with message \n%s\n",
+			resp.resp_sub_errno, resp.resp_l1_msg);
+		return -EPERM;
+	}
+
+	if ((action == PCI_REQ_SLOT_ELIGIBLE) && rc) {
+		dev_dbg(&slot->pci_bus->self->dev,
+			"remove failed with error %d sub-error %d\n",
+			rc, resp.resp_sub_errno);
+		return -EIO;
+	}
+
+	if ((action == PCI_REQ_SLOT_ELIGIBLE) && !rc)
+		return 0;
+
+	if ((action == PCI_REQ_SLOT_DISABLE) && !rc) {
+		pcibus_info = SN_PCIBUS_BUSSOFT_INFO(slot->pci_bus);
+		pcibus_info->pbi_enabled_devices &= ~(1 << device_num);
+		dev_dbg(&slot->pci_bus->self->dev, "remove successful\n");
+		return 0;
+	}
+
+	if ((action == PCI_REQ_SLOT_DISABLE) && rc) {
+		dev_dbg(&slot->pci_bus->self->dev,"remove failed rc = %d\n", rc);
+	}
+
+	return rc;
+}
+
+/*
+ * Power up and configure the slot via a SAL call to PROM.
+ * Scan slot (and any children), do any platform specific fixup,
+ * and find device driver.
+ */
+static int enable_slot(struct hotplug_slot *bss_hotplug_slot)
+{
+	struct slot *slot = bss_hotplug_slot->private;
+	struct pci_bus *new_bus = NULL;
+	struct pci_dev *dev;
+	int func, num_funcs;
+	int new_ppb = 0;
+	int rc;
+	char *ssdt = NULL;
+	void pcibios_fixup_device_resources(struct pci_dev *);
+
+	/* Serialize the Linux PCI infrastructure */
+	mutex_lock(&sn_hotplug_mutex);
+
+	/*
+	 * Power-on and initialize the slot in the SN
+	 * PCI infrastructure. Also, retrieve the ACPI SSDT
+	 * table for the slot (if ACPI capable PROM).
+	 */
+	rc = sn_slot_enable(bss_hotplug_slot, slot->device_num, &ssdt);
+	if (rc) {
+		mutex_unlock(&sn_hotplug_mutex);
+		return rc;
+	}
+
+	if (ssdt)
+		ssdt = __va(ssdt);
+	/* Add the new SSDT for the slot to the ACPI namespace */
+	if (SN_ACPI_BASE_SUPPORT() && ssdt) {
+		acpi_status ret;
+
+		ret = acpi_load_table((struct acpi_table_header *)ssdt);
+		if (ACPI_FAILURE(ret)) {
+			printk(KERN_ERR "%s: acpi_load_table failed (0x%x)\n",
+			       __func__, ret);
+			/* try to continue on */
+		}
+	}
+
+	num_funcs = pci_scan_slot(slot->pci_bus,
+				  PCI_DEVFN(slot->device_num + 1, 0));
+	if (!num_funcs) {
+		dev_dbg(&slot->pci_bus->self->dev, "no device in slot\n");
+		mutex_unlock(&sn_hotplug_mutex);
+		return -ENODEV;
+	}
+
+	/*
+	 * Map SN resources for all functions on the card
+	 * to the Linux PCI interface and tell the drivers
+	 * about them.
+	 */
+	for (func = 0; func < num_funcs;  func++) {
+		dev = pci_get_slot(slot->pci_bus,
+				   PCI_DEVFN(slot->device_num + 1,
+					     PCI_FUNC(func)));
+		if (dev) {
+			/* Need to do slot fixup on PPB before fixup of children
+			 * (PPB's pcidev_info needs to be in pcidev_info list
+			 * before child's SN_PCIDEV_INFO() call to setup
+			 * pdi_host_pcidev_info).
+			 */
+			pcibios_fixup_device_resources(dev);
+			if (SN_ACPI_BASE_SUPPORT())
+				sn_acpi_slot_fixup(dev);
+			else
+				sn_io_slot_fixup(dev);
+			if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
+				unsigned char sec_bus;
+				pci_read_config_byte(dev, PCI_SECONDARY_BUS,
+						     &sec_bus);
+				new_bus = pci_add_new_bus(dev->bus, dev,
+							  sec_bus);
+				pci_scan_child_bus(new_bus);
+				new_ppb = 1;
+			}
+			pci_dev_put(dev);
+		}
+	}
+
+	/*
+	 * Add the slot's devices to the ACPI infrastructure */
+	if (SN_ACPI_BASE_SUPPORT() && ssdt) {
+		unsigned long long adr;
+		struct acpi_device *pdevice;
+		struct acpi_device *device;
+		acpi_handle phandle;
+		acpi_handle chandle = NULL;
+		acpi_handle rethandle;
+		acpi_status ret;
+
+		phandle = PCI_CONTROLLER(slot->pci_bus)->acpi_handle;
+
+		if (acpi_bus_get_device(phandle, &pdevice)) {
+			dev_dbg(&slot->pci_bus->self->dev,
+				"no parent device, assuming NULL\n");
+			pdevice = NULL;
+		}
+
+		/*
+		 * Walk the rootbus node's immediate children looking for
+		 * the slot's device node(s). There can be more than
+		 * one for multifunction devices.
+		 */
+		for (;;) {
+			rethandle = NULL;
+			ret = acpi_get_next_object(ACPI_TYPE_DEVICE,
+						   phandle, chandle,
+						   &rethandle);
+
+			if (ret == AE_NOT_FOUND || rethandle == NULL)
+				break;
+
+			chandle = rethandle;
+
+			ret = acpi_evaluate_integer(chandle, METHOD_NAME__ADR,
+						    NULL, &adr);
+
+			if (ACPI_SUCCESS(ret) &&
+			    (adr>>16) == (slot->device_num + 1)) {
+
+				ret = acpi_bus_add(&device, pdevice, chandle,
+						   ACPI_BUS_TYPE_DEVICE);
+				if (ACPI_FAILURE(ret)) {
+					printk(KERN_ERR "%s: acpi_bus_add "
+					       "failed (0x%x) for slot %d "
+					       "func %d\n", __func__,
+					       ret, (int)(adr>>16),
+					       (int)(adr&0xffff));
+					/* try to continue on */
+				} else {
+					acpi_bus_start(device);
+				}
+			}
+		}
+	}
+
+	/* Call the driver for the new device */
+	pci_bus_add_devices(slot->pci_bus);
+	/* Call the drivers for the new devices subordinate to PPB */
+	if (new_ppb)
+		pci_bus_add_devices(new_bus);
+
+	mutex_unlock(&sn_hotplug_mutex);
+
+	if (rc == 0)
+		dev_dbg(&slot->pci_bus->self->dev,
+			"insert operation successful\n");
+	else
+		dev_dbg(&slot->pci_bus->self->dev,
+			"insert operation failed rc = %d\n", rc);
+
+	return rc;
+}
+
+static int disable_slot(struct hotplug_slot *bss_hotplug_slot)
+{
+	struct slot *slot = bss_hotplug_slot->private;
+	struct pci_dev *dev;
+	int func;
+	int rc;
+	acpi_owner_id ssdt_id = 0;
+
+	/* Acquire update access to the bus */
+	mutex_lock(&sn_hotplug_mutex);
+
+	/* is it okay to bring this slot down? */
+	rc = sn_slot_disable(bss_hotplug_slot, slot->device_num,
+			     PCI_REQ_SLOT_ELIGIBLE);
+	if (rc)
+		goto leaving;
+
+	/* free the ACPI resources for the slot */
+	if (SN_ACPI_BASE_SUPPORT() &&
+            PCI_CONTROLLER(slot->pci_bus)->acpi_handle) {
+		unsigned long long adr;
+		struct acpi_device *device;
+		acpi_handle phandle;
+		acpi_handle chandle = NULL;
+		acpi_handle rethandle;
+		acpi_status ret;
+
+		/* Get the rootbus node pointer */
+		phandle = PCI_CONTROLLER(slot->pci_bus)->acpi_handle;
+
+		/*
+		 * Walk the rootbus node's immediate children looking for
+		 * the slot's device node(s). There can be more than
+		 * one for multifunction devices.
+		 */
+		for (;;) {
+			rethandle = NULL;
+			ret = acpi_get_next_object(ACPI_TYPE_DEVICE,
+						   phandle, chandle,
+						   &rethandle);
+
+			if (ret == AE_NOT_FOUND || rethandle == NULL)
+				break;
+
+			chandle = rethandle;
+
+			ret = acpi_evaluate_integer(chandle,
+						    METHOD_NAME__ADR,
+						    NULL, &adr);
+			if (ACPI_SUCCESS(ret) &&
+			    (adr>>16) == (slot->device_num + 1)) {
+				/* retain the owner id */
+				acpi_get_id(chandle, &ssdt_id);
+
+				ret = acpi_bus_get_device(chandle,
+							  &device);
+				if (ACPI_SUCCESS(ret))
+					acpi_bus_trim(device, 1);
+			}
+		}
+
+	}
+
+	/* Free the SN resources assigned to the Linux device.*/
+	for (func = 0; func < 8;  func++) {
+		dev = pci_get_slot(slot->pci_bus,
+				   PCI_DEVFN(slot->device_num + 1,
+				   	     PCI_FUNC(func)));
+		if (dev) {
+			sn_bus_free_data(dev);
+			pci_remove_bus_device(dev);
+			pci_dev_put(dev);
+		}
+	}
+
+	/* Remove the SSDT for the slot from the ACPI namespace */
+	if (SN_ACPI_BASE_SUPPORT() && ssdt_id) {
+		acpi_status ret;
+		ret = acpi_unload_table_id(ssdt_id);
+		if (ACPI_FAILURE(ret)) {
+			printk(KERN_ERR "%s: acpi_unload_table_id "
+			       "failed (0x%x) for id %d\n",
+			       __func__, ret, ssdt_id);
+			/* try to continue on */
+		}
+	}
+
+	/* free the collected sysdata pointers */
+	sn_bus_free_sysdata();
+
+	/* Deactivate slot */
+	rc = sn_slot_disable(bss_hotplug_slot, slot->device_num,
+			     PCI_REQ_SLOT_DISABLE);
+ leaving:
+	/* Release the bus lock */
+	mutex_unlock(&sn_hotplug_mutex);
+
+	return rc;
+}
+
+static inline int get_power_status(struct hotplug_slot *bss_hotplug_slot,
+				   u8 *value)
+{
+	struct slot *slot = bss_hotplug_slot->private;
+	struct pcibus_info *pcibus_info;
+	u32 power;
+
+	pcibus_info = SN_PCIBUS_BUSSOFT_INFO(slot->pci_bus);
+	mutex_lock(&sn_hotplug_mutex);
+	power = pcibus_info->pbi_enabled_devices & (1 << slot->device_num);
+	*value = power ? 1 : 0;
+	mutex_unlock(&sn_hotplug_mutex);
+	return 0;
+}
+
+static void sn_release_slot(struct hotplug_slot *bss_hotplug_slot)
+{
+	kfree(bss_hotplug_slot->info);
+	kfree(bss_hotplug_slot->private);
+	kfree(bss_hotplug_slot);
+}
+
+static int sn_hotplug_slot_register(struct pci_bus *pci_bus)
+{
+	int device;
+	struct pci_slot *pci_slot;
+	struct hotplug_slot *bss_hotplug_slot;
+	char name[SN_SLOT_NAME_SIZE];
+	int rc = 0;
+
+	/*
+	 * Currently only four devices are supported,
+	 * in the future there maybe more -- up to 32.
+	 */
+
+	for (device = 0; device < SN_MAX_HP_SLOTS ; device++) {
+		if (sn_pci_slot_valid(pci_bus, device) != 1)
+			continue;
+
+		bss_hotplug_slot = kzalloc(sizeof(*bss_hotplug_slot),
+					   GFP_KERNEL);
+		if (!bss_hotplug_slot) {
+			rc = -ENOMEM;
+			goto alloc_err;
+		}
+
+		bss_hotplug_slot->info =
+			kzalloc(sizeof(struct hotplug_slot_info),
+				GFP_KERNEL);
+		if (!bss_hotplug_slot->info) {
+			rc = -ENOMEM;
+			goto alloc_err;
+		}
+
+		if (sn_hp_slot_private_alloc(bss_hotplug_slot,
+					     pci_bus, device, name)) {
+			rc = -ENOMEM;
+			goto alloc_err;
+		}
+		bss_hotplug_slot->ops = &sn_hotplug_slot_ops;
+		bss_hotplug_slot->release = &sn_release_slot;
+
+		rc = pci_hp_register(bss_hotplug_slot, pci_bus, device, name);
+		if (rc)
+			goto register_err;
+
+		pci_slot = bss_hotplug_slot->pci_slot;
+		rc = sysfs_create_file(&pci_slot->kobj,
+				       &sn_slot_path_attr.attr);
+		if (rc)
+			goto register_err;
+	}
+	dev_dbg(&pci_bus->self->dev, "Registered bus with hotplug\n");
+	return rc;
+
+register_err:
+	dev_dbg(&pci_bus->self->dev, "bus failed to register with err = %d\n",
+		rc);
+
+alloc_err:
+	if (rc == -ENOMEM)
+		dev_dbg(&pci_bus->self->dev, "Memory allocation error\n");
+
+	/* destroy THIS element */
+	if (bss_hotplug_slot)
+		sn_release_slot(bss_hotplug_slot);
+
+	/* destroy anything else on the list */
+	while ((bss_hotplug_slot = sn_hp_destroy()))
+		pci_hp_deregister(bss_hotplug_slot);
+
+	return rc;
+}
+
+static int __init sn_pci_hotplug_init(void)
+{
+	struct pci_bus *pci_bus = NULL;
+	int rc;
+	int registered = 0;
+
+	if (!sn_prom_feature_available(PRF_HOTPLUG_SUPPORT)) {
+		printk(KERN_ERR "%s: PROM version does not support hotplug.\n",
+		       __func__);
+		return -EPERM;
+	}
+
+	INIT_LIST_HEAD(&sn_hp_list);
+
+	while ((pci_bus = pci_find_next_bus(pci_bus))) {
+		if (!pci_bus->sysdata)
+			continue;
+
+		rc = sn_pci_bus_valid(pci_bus);
+		if (rc != 1) {
+			dev_dbg(&pci_bus->self->dev, "not a valid hotplug bus\n");
+			continue;
+		}
+		dev_dbg(&pci_bus->self->dev, "valid hotplug bus\n");
+
+		rc = sn_hotplug_slot_register(pci_bus);
+		if (!rc) {
+			registered = 1;
+		} else {
+			registered = 0;
+			break;
+		}
+	}
+
+	return registered == 1 ? 0 : -ENODEV;
+}
+
+static void __exit sn_pci_hotplug_exit(void)
+{
+	struct hotplug_slot *bss_hotplug_slot;
+
+	while ((bss_hotplug_slot = sn_hp_destroy()))
+		pci_hp_deregister(bss_hotplug_slot);
+
+	if (!list_empty(&sn_hp_list))
+		printk(KERN_ERR "%s: internal list is not empty\n", __FILE__);
+}
+
+module_init(sn_pci_hotplug_init);
+module_exit(sn_pci_hotplug_exit);
diff --git a/drivers/pci/hotplug/shpchp.h b/drivers/pci/hotplug/shpchp.h
new file mode 100644
index 00000000..e0c90e64
--- /dev/null
+++ b/drivers/pci/hotplug/shpchp.h
@@ -0,0 +1,349 @@
+/*
+ * Standard Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM
+ * Copyright (C) 2003-2004 Intel Corporation
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>,<kristen.c.accardi@intel.com>
+ *
+ */
+#ifndef _SHPCHP_H
+#define _SHPCHP_H
+
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/delay.h>
+#include <linux/sched.h>	/* signal_pending(), struct timer_list */
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+
+#if !defined(MODULE)
+	#define MY_NAME	"shpchp"
+#else
+	#define MY_NAME	THIS_MODULE->name
+#endif
+
+extern int shpchp_poll_mode;
+extern int shpchp_poll_time;
+extern int shpchp_debug;
+extern struct workqueue_struct *shpchp_wq;
+extern struct workqueue_struct *shpchp_ordered_wq;
+
+#define dbg(format, arg...)						\
+do {									\
+	if (shpchp_debug)						\
+		printk(KERN_DEBUG "%s: " format, MY_NAME , ## arg);	\
+} while (0)
+#define err(format, arg...)						\
+	printk(KERN_ERR "%s: " format, MY_NAME , ## arg)
+#define info(format, arg...)						\
+	printk(KERN_INFO "%s: " format, MY_NAME , ## arg)
+#define warn(format, arg...)						\
+	printk(KERN_WARNING "%s: " format, MY_NAME , ## arg)
+
+#define ctrl_dbg(ctrl, format, arg...)					\
+	do {								\
+		if (shpchp_debug)					\
+			dev_printk(KERN_DEBUG, &ctrl->pci_dev->dev,	\
+					format, ## arg);		\
+	} while (0)
+#define ctrl_err(ctrl, format, arg...)					\
+	dev_err(&ctrl->pci_dev->dev, format, ## arg)
+#define ctrl_info(ctrl, format, arg...)					\
+	dev_info(&ctrl->pci_dev->dev, format, ## arg)
+#define ctrl_warn(ctrl, format, arg...)					\
+	dev_warn(&ctrl->pci_dev->dev, format, ## arg)
+
+
+#define SLOT_NAME_SIZE 10
+struct slot {
+	u8 bus;
+	u8 device;
+	u16 status;
+	u32 number;
+	u8 is_a_board;
+	u8 state;
+	u8 presence_save;
+	u8 pwr_save;
+	struct controller *ctrl;
+	struct hpc_ops *hpc_ops;
+	struct hotplug_slot *hotplug_slot;
+	struct list_head	slot_list;
+	struct delayed_work work;	/* work for button event */
+	struct mutex lock;
+	u8 hp_slot;
+};
+
+struct event_info {
+	u32 event_type;
+	struct slot *p_slot;
+	struct work_struct work;
+};
+
+struct controller {
+	struct mutex crit_sect;		/* critical section mutex */
+	struct mutex cmd_lock;		/* command lock */
+	int num_slots;			/* Number of slots on ctlr */
+	int slot_num_inc;		/* 1 or -1 */
+	struct pci_dev *pci_dev;
+	struct list_head slot_list;
+	struct hpc_ops *hpc_ops;
+	wait_queue_head_t queue;	/* sleep & wake process */
+	u8 slot_device_offset;
+	u32 pcix_misc2_reg;	/* for amd pogo errata */
+	u32 first_slot;		/* First physical slot number */
+	u32 cap_offset;
+	unsigned long mmio_base;
+	unsigned long mmio_size;
+	void __iomem *creg;
+	struct timer_list poll_timer;
+};
+
+/* Define AMD SHPC ID  */
+#define PCI_DEVICE_ID_AMD_GOLAM_7450	0x7450
+#define PCI_DEVICE_ID_AMD_POGO_7458	0x7458
+
+/* AMD PCI-X bridge registers */
+#define PCIX_MEM_BASE_LIMIT_OFFSET	0x1C
+#define PCIX_MISCII_OFFSET		0x48
+#define PCIX_MISC_BRIDGE_ERRORS_OFFSET	0x80
+
+/* AMD PCIX_MISCII masks and offsets */
+#define PERRNONFATALENABLE_MASK		0x00040000
+#define PERRFATALENABLE_MASK		0x00080000
+#define PERRFLOODENABLE_MASK		0x00100000
+#define SERRNONFATALENABLE_MASK		0x00200000
+#define SERRFATALENABLE_MASK		0x00400000
+
+/* AMD PCIX_MISC_BRIDGE_ERRORS masks and offsets */
+#define PERR_OBSERVED_MASK		0x00000001
+
+/* AMD PCIX_MEM_BASE_LIMIT masks */
+#define RSE_MASK			0x40000000
+
+#define INT_BUTTON_IGNORE		0
+#define INT_PRESENCE_ON			1
+#define INT_PRESENCE_OFF		2
+#define INT_SWITCH_CLOSE		3
+#define INT_SWITCH_OPEN			4
+#define INT_POWER_FAULT			5
+#define INT_POWER_FAULT_CLEAR		6
+#define INT_BUTTON_PRESS		7
+#define INT_BUTTON_RELEASE		8
+#define INT_BUTTON_CANCEL		9
+
+#define STATIC_STATE			0
+#define BLINKINGON_STATE		1
+#define BLINKINGOFF_STATE		2
+#define POWERON_STATE			3
+#define POWEROFF_STATE			4
+
+/* Error messages */
+#define INTERLOCK_OPEN			0x00000002
+#define ADD_NOT_SUPPORTED		0x00000003
+#define CARD_FUNCTIONING		0x00000005
+#define ADAPTER_NOT_SAME		0x00000006
+#define NO_ADAPTER_PRESENT		0x00000009
+#define NOT_ENOUGH_RESOURCES		0x0000000B
+#define DEVICE_TYPE_NOT_SUPPORTED	0x0000000C
+#define WRONG_BUS_FREQUENCY		0x0000000D
+#define POWER_FAILURE			0x0000000E
+
+extern int __must_check shpchp_create_ctrl_files(struct controller *ctrl);
+extern void shpchp_remove_ctrl_files(struct controller *ctrl);
+extern int shpchp_sysfs_enable_slot(struct slot *slot);
+extern int shpchp_sysfs_disable_slot(struct slot *slot);
+extern u8 shpchp_handle_attention_button(u8 hp_slot, struct controller *ctrl);
+extern u8 shpchp_handle_switch_change(u8 hp_slot, struct controller *ctrl);
+extern u8 shpchp_handle_presence_change(u8 hp_slot, struct controller *ctrl);
+extern u8 shpchp_handle_power_fault(u8 hp_slot, struct controller *ctrl);
+extern int shpchp_configure_device(struct slot *p_slot);
+extern int shpchp_unconfigure_device(struct slot *p_slot);
+extern void cleanup_slots(struct controller *ctrl);
+extern void shpchp_queue_pushbutton_work(struct work_struct *work);
+extern int shpc_init( struct controller *ctrl, struct pci_dev *pdev);
+
+static inline const char *slot_name(struct slot *slot)
+{
+	return hotplug_slot_name(slot->hotplug_slot);
+}
+
+#ifdef CONFIG_ACPI
+#include <linux/pci-acpi.h>
+static inline int get_hp_hw_control_from_firmware(struct pci_dev *dev)
+{
+	u32 flags = OSC_SHPC_NATIVE_HP_CONTROL;
+	return acpi_get_hp_hw_control_from_firmware(dev, flags);
+}
+#else
+#define get_hp_hw_control_from_firmware(dev) (0)
+#endif
+
+struct ctrl_reg {
+	volatile u32 base_offset;
+	volatile u32 slot_avail1;
+	volatile u32 slot_avail2;
+	volatile u32 slot_config;
+	volatile u16 sec_bus_config;
+	volatile u8  msi_ctrl;
+	volatile u8  prog_interface;
+	volatile u16 cmd;
+	volatile u16 cmd_status;
+	volatile u32 intr_loc;
+	volatile u32 serr_loc;
+	volatile u32 serr_intr_enable;
+	volatile u32 slot1;
+} __attribute__ ((packed));
+
+/* offsets to the controller registers based on the above structure layout */
+enum ctrl_offsets {
+	BASE_OFFSET 	 = offsetof(struct ctrl_reg, base_offset),
+	SLOT_AVAIL1 	 = offsetof(struct ctrl_reg, slot_avail1),
+	SLOT_AVAIL2	 = offsetof(struct ctrl_reg, slot_avail2),
+	SLOT_CONFIG 	 = offsetof(struct ctrl_reg, slot_config),
+	SEC_BUS_CONFIG	 = offsetof(struct ctrl_reg, sec_bus_config),
+	MSI_CTRL	 = offsetof(struct ctrl_reg, msi_ctrl),
+	PROG_INTERFACE 	 = offsetof(struct ctrl_reg, prog_interface),
+	CMD		 = offsetof(struct ctrl_reg, cmd),
+	CMD_STATUS	 = offsetof(struct ctrl_reg, cmd_status),
+	INTR_LOC	 = offsetof(struct ctrl_reg, intr_loc),
+	SERR_LOC	 = offsetof(struct ctrl_reg, serr_loc),
+	SERR_INTR_ENABLE = offsetof(struct ctrl_reg, serr_intr_enable),
+	SLOT1		 = offsetof(struct ctrl_reg, slot1),
+};
+
+static inline struct slot *get_slot(struct hotplug_slot *hotplug_slot)
+{
+	return hotplug_slot->private;
+}
+
+static inline struct slot *shpchp_find_slot(struct controller *ctrl, u8 device)
+{
+	struct slot *slot;
+
+	list_for_each_entry(slot, &ctrl->slot_list, slot_list) {
+		if (slot->device == device)
+			return slot;
+	}
+
+	ctrl_err(ctrl, "Slot (device=0x%02x) not found\n", device);
+	return NULL;
+}
+
+static inline void amd_pogo_errata_save_misc_reg(struct slot *p_slot)
+{
+	u32 pcix_misc2_temp;
+
+	/* save MiscII register */
+	pci_read_config_dword(p_slot->ctrl->pci_dev, PCIX_MISCII_OFFSET, &pcix_misc2_temp);
+
+	p_slot->ctrl->pcix_misc2_reg = pcix_misc2_temp;
+
+	/* clear SERR/PERR enable bits */
+	pcix_misc2_temp &= ~SERRFATALENABLE_MASK;
+	pcix_misc2_temp &= ~SERRNONFATALENABLE_MASK;
+	pcix_misc2_temp &= ~PERRFLOODENABLE_MASK;
+	pcix_misc2_temp &= ~PERRFATALENABLE_MASK;
+	pcix_misc2_temp &= ~PERRNONFATALENABLE_MASK;
+	pci_write_config_dword(p_slot->ctrl->pci_dev, PCIX_MISCII_OFFSET, pcix_misc2_temp);
+}
+
+static inline void amd_pogo_errata_restore_misc_reg(struct slot *p_slot)
+{
+	u32 pcix_misc2_temp;
+	u32 pcix_bridge_errors_reg;
+	u32 pcix_mem_base_reg;
+	u8  perr_set;
+	u8  rse_set;
+
+	/* write-one-to-clear Bridge_Errors[ PERR_OBSERVED ] */
+	pci_read_config_dword(p_slot->ctrl->pci_dev, PCIX_MISC_BRIDGE_ERRORS_OFFSET, &pcix_bridge_errors_reg);
+	perr_set = pcix_bridge_errors_reg & PERR_OBSERVED_MASK;
+	if (perr_set) {
+		ctrl_dbg(p_slot->ctrl,
+			 "Bridge_Errors[ PERR_OBSERVED = %08X] (W1C)\n",
+			 perr_set);
+
+		pci_write_config_dword(p_slot->ctrl->pci_dev, PCIX_MISC_BRIDGE_ERRORS_OFFSET, perr_set);
+	}
+
+	/* write-one-to-clear Memory_Base_Limit[ RSE ] */
+	pci_read_config_dword(p_slot->ctrl->pci_dev, PCIX_MEM_BASE_LIMIT_OFFSET, &pcix_mem_base_reg);
+	rse_set = pcix_mem_base_reg & RSE_MASK;
+	if (rse_set) {
+		ctrl_dbg(p_slot->ctrl, "Memory_Base_Limit[ RSE ] (W1C)\n");
+
+		pci_write_config_dword(p_slot->ctrl->pci_dev, PCIX_MEM_BASE_LIMIT_OFFSET, rse_set);
+	}
+	/* restore MiscII register */
+	pci_read_config_dword( p_slot->ctrl->pci_dev, PCIX_MISCII_OFFSET, &pcix_misc2_temp );
+
+	if (p_slot->ctrl->pcix_misc2_reg & SERRFATALENABLE_MASK)
+		pcix_misc2_temp |= SERRFATALENABLE_MASK;
+	else
+		pcix_misc2_temp &= ~SERRFATALENABLE_MASK;
+
+	if (p_slot->ctrl->pcix_misc2_reg & SERRNONFATALENABLE_MASK)
+		pcix_misc2_temp |= SERRNONFATALENABLE_MASK;
+	else
+		pcix_misc2_temp &= ~SERRNONFATALENABLE_MASK;
+
+	if (p_slot->ctrl->pcix_misc2_reg & PERRFLOODENABLE_MASK)
+		pcix_misc2_temp |= PERRFLOODENABLE_MASK;
+	else
+		pcix_misc2_temp &= ~PERRFLOODENABLE_MASK;
+
+	if (p_slot->ctrl->pcix_misc2_reg & PERRFATALENABLE_MASK)
+		pcix_misc2_temp |= PERRFATALENABLE_MASK;
+	else
+		pcix_misc2_temp &= ~PERRFATALENABLE_MASK;
+
+	if (p_slot->ctrl->pcix_misc2_reg & PERRNONFATALENABLE_MASK)
+		pcix_misc2_temp |= PERRNONFATALENABLE_MASK;
+	else
+		pcix_misc2_temp &= ~PERRNONFATALENABLE_MASK;
+	pci_write_config_dword(p_slot->ctrl->pci_dev, PCIX_MISCII_OFFSET, pcix_misc2_temp);
+}
+
+struct hpc_ops {
+	int (*power_on_slot)(struct slot *slot);
+	int (*slot_enable)(struct slot *slot);
+	int (*slot_disable)(struct slot *slot);
+	int (*set_bus_speed_mode)(struct slot *slot, enum pci_bus_speed speed);
+	int (*get_power_status)(struct slot *slot, u8 *status);
+	int (*get_attention_status)(struct slot *slot, u8 *status);
+	int (*set_attention_status)(struct slot *slot, u8 status);
+	int (*get_latch_status)(struct slot *slot, u8 *status);
+	int (*get_adapter_status)(struct slot *slot, u8 *status);
+	int (*get_adapter_speed)(struct slot *slot, enum pci_bus_speed *speed);
+	int (*get_mode1_ECC_cap)(struct slot *slot, u8 *mode);
+	int (*get_prog_int)(struct slot *slot, u8 *prog_int);
+	int (*query_power_fault)(struct slot *slot);
+	void (*green_led_on)(struct slot *slot);
+	void (*green_led_off)(struct slot *slot);
+	void (*green_led_blink)(struct slot *slot);
+	void (*release_ctlr)(struct controller *ctrl);
+	int (*check_cmd_status)(struct controller *ctrl);
+};
+
+#endif				/* _SHPCHP_H */
diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c
new file mode 100644
index 00000000..dd7e0c51
--- /dev/null
+++ b/drivers/pci/hotplug/shpchp_core.c
@@ -0,0 +1,393 @@
+/*
+ * Standard Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ * Copyright (C) 2003-2004 Intel Corporation
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>, <kristen.c.accardi@intel.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include "shpchp.h"
+
+/* Global variables */
+int shpchp_debug;
+int shpchp_poll_mode;
+int shpchp_poll_time;
+struct workqueue_struct *shpchp_wq;
+struct workqueue_struct *shpchp_ordered_wq;
+
+#define DRIVER_VERSION	"0.4"
+#define DRIVER_AUTHOR	"Dan Zink <dan.zink@compaq.com>, Greg Kroah-Hartman <greg@kroah.com>, Dely Sy <dely.l.sy@intel.com>"
+#define DRIVER_DESC	"Standard Hot Plug PCI Controller Driver"
+
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+
+module_param(shpchp_debug, bool, 0644);
+module_param(shpchp_poll_mode, bool, 0644);
+module_param(shpchp_poll_time, int, 0644);
+MODULE_PARM_DESC(shpchp_debug, "Debugging mode enabled or not");
+MODULE_PARM_DESC(shpchp_poll_mode, "Using polling mechanism for hot-plug events or not");
+MODULE_PARM_DESC(shpchp_poll_time, "Polling mechanism frequency, in seconds");
+
+#define SHPC_MODULE_NAME "shpchp"
+
+static int set_attention_status (struct hotplug_slot *slot, u8 value);
+static int enable_slot		(struct hotplug_slot *slot);
+static int disable_slot		(struct hotplug_slot *slot);
+static int get_power_status	(struct hotplug_slot *slot, u8 *value);
+static int get_attention_status	(struct hotplug_slot *slot, u8 *value);
+static int get_latch_status	(struct hotplug_slot *slot, u8 *value);
+static int get_adapter_status	(struct hotplug_slot *slot, u8 *value);
+
+static struct hotplug_slot_ops shpchp_hotplug_slot_ops = {
+	.set_attention_status =	set_attention_status,
+	.enable_slot =		enable_slot,
+	.disable_slot =		disable_slot,
+	.get_power_status =	get_power_status,
+	.get_attention_status =	get_attention_status,
+	.get_latch_status =	get_latch_status,
+	.get_adapter_status =	get_adapter_status,
+};
+
+/**
+ * release_slot - free up the memory used by a slot
+ * @hotplug_slot: slot to free
+ */
+static void release_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
+		 __func__, slot_name(slot));
+
+	kfree(slot->hotplug_slot->info);
+	kfree(slot->hotplug_slot);
+	kfree(slot);
+}
+
+static int init_slots(struct controller *ctrl)
+{
+	struct slot *slot;
+	struct hotplug_slot *hotplug_slot;
+	struct hotplug_slot_info *info;
+	char name[SLOT_NAME_SIZE];
+	int retval = -ENOMEM;
+	int i;
+
+	for (i = 0; i < ctrl->num_slots; i++) {
+		slot = kzalloc(sizeof(*slot), GFP_KERNEL);
+		if (!slot)
+			goto error;
+
+		hotplug_slot = kzalloc(sizeof(*hotplug_slot), GFP_KERNEL);
+		if (!hotplug_slot)
+			goto error_slot;
+		slot->hotplug_slot = hotplug_slot;
+
+		info = kzalloc(sizeof(*info), GFP_KERNEL);
+		if (!info)
+			goto error_hpslot;
+		hotplug_slot->info = info;
+
+		slot->hp_slot = i;
+		slot->ctrl = ctrl;
+		slot->bus = ctrl->pci_dev->subordinate->number;
+		slot->device = ctrl->slot_device_offset + i;
+		slot->hpc_ops = ctrl->hpc_ops;
+		slot->number = ctrl->first_slot + (ctrl->slot_num_inc * i);
+		mutex_init(&slot->lock);
+		INIT_DELAYED_WORK(&slot->work, shpchp_queue_pushbutton_work);
+
+		/* register this slot with the hotplug pci core */
+		hotplug_slot->private = slot;
+		hotplug_slot->release = &release_slot;
+		snprintf(name, SLOT_NAME_SIZE, "%d", slot->number);
+		hotplug_slot->ops = &shpchp_hotplug_slot_ops;
+
+ 		ctrl_dbg(ctrl, "Registering domain:bus:dev=%04x:%02x:%02x "
+ 			 "hp_slot=%x sun=%x slot_device_offset=%x\n",
+ 			 pci_domain_nr(ctrl->pci_dev->subordinate),
+ 			 slot->bus, slot->device, slot->hp_slot, slot->number,
+ 			 ctrl->slot_device_offset);
+		retval = pci_hp_register(slot->hotplug_slot,
+				ctrl->pci_dev->subordinate, slot->device, name);
+		if (retval) {
+			ctrl_err(ctrl, "pci_hp_register failed with error %d\n",
+				 retval);
+			goto error_info;
+		}
+
+		get_power_status(hotplug_slot, &info->power_status);
+		get_attention_status(hotplug_slot, &info->attention_status);
+		get_latch_status(hotplug_slot, &info->latch_status);
+		get_adapter_status(hotplug_slot, &info->adapter_status);
+
+		list_add(&slot->slot_list, &ctrl->slot_list);
+	}
+
+	return 0;
+error_info:
+	kfree(info);
+error_hpslot:
+	kfree(hotplug_slot);
+error_slot:
+	kfree(slot);
+error:
+	return retval;
+}
+
+void cleanup_slots(struct controller *ctrl)
+{
+	struct list_head *tmp;
+	struct list_head *next;
+	struct slot *slot;
+
+	list_for_each_safe(tmp, next, &ctrl->slot_list) {
+		slot = list_entry(tmp, struct slot, slot_list);
+		list_del(&slot->slot_list);
+		cancel_delayed_work(&slot->work);
+		flush_workqueue(shpchp_wq);
+		flush_workqueue(shpchp_ordered_wq);
+		pci_hp_deregister(slot->hotplug_slot);
+	}
+}
+
+/*
+ * set_attention_status - Turns the Amber LED for a slot on, off or blink
+ */
+static int set_attention_status (struct hotplug_slot *hotplug_slot, u8 status)
+{
+	struct slot *slot = get_slot(hotplug_slot);
+
+	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
+		 __func__, slot_name(slot));
+
+	hotplug_slot->info->attention_status = status;
+	slot->hpc_ops->set_attention_status(slot, status);
+
+	return 0;
+}
+
+static int enable_slot (struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = get_slot(hotplug_slot);
+
+	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
+		 __func__, slot_name(slot));
+
+	return shpchp_sysfs_enable_slot(slot);
+}
+
+static int disable_slot (struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = get_slot(hotplug_slot);
+
+	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
+		 __func__, slot_name(slot));
+
+	return shpchp_sysfs_disable_slot(slot);
+}
+
+static int get_power_status (struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = get_slot(hotplug_slot);
+	int retval;
+
+	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
+		 __func__, slot_name(slot));
+
+	retval = slot->hpc_ops->get_power_status(slot, value);
+	if (retval < 0)
+		*value = hotplug_slot->info->power_status;
+
+	return 0;
+}
+
+static int get_attention_status (struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = get_slot(hotplug_slot);
+	int retval;
+
+	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
+		 __func__, slot_name(slot));
+
+	retval = slot->hpc_ops->get_attention_status(slot, value);
+	if (retval < 0)
+		*value = hotplug_slot->info->attention_status;
+
+	return 0;
+}
+
+static int get_latch_status (struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = get_slot(hotplug_slot);
+	int retval;
+
+	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
+		 __func__, slot_name(slot));
+
+	retval = slot->hpc_ops->get_latch_status(slot, value);
+	if (retval < 0)
+		*value = hotplug_slot->info->latch_status;
+
+	return 0;
+}
+
+static int get_adapter_status (struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = get_slot(hotplug_slot);
+	int retval;
+
+	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
+		 __func__, slot_name(slot));
+
+	retval = slot->hpc_ops->get_adapter_status(slot, value);
+	if (retval < 0)
+		*value = hotplug_slot->info->adapter_status;
+
+	return 0;
+}
+
+static int is_shpc_capable(struct pci_dev *dev)
+{
+	if (dev->vendor == PCI_VENDOR_ID_AMD &&
+	    dev->device == PCI_DEVICE_ID_AMD_GOLAM_7450)
+		return 1;
+	if (!pci_find_capability(dev, PCI_CAP_ID_SHPC))
+		return 0;
+	if (get_hp_hw_control_from_firmware(dev))
+		return 0;
+	return 1;
+}
+
+static int shpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	int rc;
+	struct controller *ctrl;
+
+	if (!is_shpc_capable(pdev))
+		return -ENODEV;
+
+	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
+	if (!ctrl) {
+		dev_err(&pdev->dev, "%s: Out of memory\n", __func__);
+		goto err_out_none;
+	}
+	INIT_LIST_HEAD(&ctrl->slot_list);
+
+	rc = shpc_init(ctrl, pdev);
+	if (rc) {
+		ctrl_dbg(ctrl, "Controller initialization failed\n");
+		goto err_out_free_ctrl;
+	}
+
+	pci_set_drvdata(pdev, ctrl);
+
+	/* Setup the slot information structures */
+	rc = init_slots(ctrl);
+	if (rc) {
+		ctrl_err(ctrl, "Slot initialization failed\n");
+		goto err_out_release_ctlr;
+	}
+
+	rc = shpchp_create_ctrl_files(ctrl);
+	if (rc)
+		goto err_cleanup_slots;
+
+	return 0;
+
+err_cleanup_slots:
+	cleanup_slots(ctrl);
+err_out_release_ctlr:
+	ctrl->hpc_ops->release_ctlr(ctrl);
+err_out_free_ctrl:
+	kfree(ctrl);
+err_out_none:
+	return -ENODEV;
+}
+
+static void shpc_remove(struct pci_dev *dev)
+{
+	struct controller *ctrl = pci_get_drvdata(dev);
+
+	shpchp_remove_ctrl_files(ctrl);
+	ctrl->hpc_ops->release_ctlr(ctrl);
+	kfree(ctrl);
+}
+
+static struct pci_device_id shpcd_pci_tbl[] = {
+	{PCI_DEVICE_CLASS(((PCI_CLASS_BRIDGE_PCI << 8) | 0x00), ~0)},
+	{ /* end: all zeroes */ }
+};
+MODULE_DEVICE_TABLE(pci, shpcd_pci_tbl);
+
+static struct pci_driver shpc_driver = {
+	.name =		SHPC_MODULE_NAME,
+	.id_table =	shpcd_pci_tbl,
+	.probe =	shpc_probe,
+	.remove =	shpc_remove,
+};
+
+static int __init shpcd_init(void)
+{
+	int retval = 0;
+
+	shpchp_wq = alloc_ordered_workqueue("shpchp", 0);
+	if (!shpchp_wq)
+		return -ENOMEM;
+
+	shpchp_ordered_wq = alloc_ordered_workqueue("shpchp_ordered", 0);
+	if (!shpchp_ordered_wq) {
+		destroy_workqueue(shpchp_wq);
+		return -ENOMEM;
+	}
+
+	retval = pci_register_driver(&shpc_driver);
+	dbg("%s: pci_register_driver = %d\n", __func__, retval);
+	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
+	if (retval) {
+		destroy_workqueue(shpchp_ordered_wq);
+		destroy_workqueue(shpchp_wq);
+	}
+	return retval;
+}
+
+static void __exit shpcd_cleanup(void)
+{
+	dbg("unload_shpchpd()\n");
+	pci_unregister_driver(&shpc_driver);
+	destroy_workqueue(shpchp_ordered_wq);
+	destroy_workqueue(shpchp_wq);
+	info(DRIVER_DESC " version: " DRIVER_VERSION " unloaded\n");
+}
+
+module_init(shpcd_init);
+module_exit(shpcd_cleanup);
diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c
new file mode 100644
index 00000000..b00b09bd
--- /dev/null
+++ b/drivers/pci/hotplug/shpchp_ctrl.c
@@ -0,0 +1,731 @@
+/*
+ * Standard Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ * Copyright (C) 2003-2004 Intel Corporation
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>, <kristen.c.accardi@intel.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include "../pci.h"
+#include "shpchp.h"
+
+static void interrupt_event_handler(struct work_struct *work);
+static int shpchp_enable_slot(struct slot *p_slot);
+static int shpchp_disable_slot(struct slot *p_slot);
+
+static int queue_interrupt_event(struct slot *p_slot, u32 event_type)
+{
+	struct event_info *info;
+
+	info = kmalloc(sizeof(*info), GFP_ATOMIC);
+	if (!info)
+		return -ENOMEM;
+
+	info->event_type = event_type;
+	info->p_slot = p_slot;
+	INIT_WORK(&info->work, interrupt_event_handler);
+
+	queue_work(shpchp_wq, &info->work);
+
+	return 0;
+}
+
+u8 shpchp_handle_attention_button(u8 hp_slot, struct controller *ctrl)
+{
+	struct slot *p_slot;
+	u32 event_type;
+
+	/* Attention Button Change */
+	ctrl_dbg(ctrl, "Attention button interrupt received\n");
+
+	p_slot = shpchp_find_slot(ctrl, hp_slot + ctrl->slot_device_offset);
+	p_slot->hpc_ops->get_adapter_status(p_slot, &(p_slot->presence_save));
+
+	/*
+	 *  Button pressed - See if need to TAKE ACTION!!!
+	 */
+	ctrl_info(ctrl, "Button pressed on Slot(%s)\n", slot_name(p_slot));
+	event_type = INT_BUTTON_PRESS;
+
+	queue_interrupt_event(p_slot, event_type);
+
+	return 0;
+
+}
+
+u8 shpchp_handle_switch_change(u8 hp_slot, struct controller *ctrl)
+{
+	struct slot *p_slot;
+	u8 getstatus;
+	u32 event_type;
+
+	/* Switch Change */
+	ctrl_dbg(ctrl, "Switch interrupt received\n");
+
+	p_slot = shpchp_find_slot(ctrl, hp_slot + ctrl->slot_device_offset);
+	p_slot->hpc_ops->get_adapter_status(p_slot, &(p_slot->presence_save));
+	p_slot->hpc_ops->get_latch_status(p_slot, &getstatus);
+	ctrl_dbg(ctrl, "Card present %x Power status %x\n",
+		 p_slot->presence_save, p_slot->pwr_save);
+
+	if (getstatus) {
+		/*
+		 * Switch opened
+		 */
+		ctrl_info(ctrl, "Latch open on Slot(%s)\n", slot_name(p_slot));
+		event_type = INT_SWITCH_OPEN;
+		if (p_slot->pwr_save && p_slot->presence_save) {
+			event_type = INT_POWER_FAULT;
+			ctrl_err(ctrl, "Surprise Removal of card\n");
+		}
+	} else {
+		/*
+		 *  Switch closed
+		 */
+		ctrl_info(ctrl, "Latch close on Slot(%s)\n", slot_name(p_slot));
+		event_type = INT_SWITCH_CLOSE;
+	}
+
+	queue_interrupt_event(p_slot, event_type);
+
+	return 1;
+}
+
+u8 shpchp_handle_presence_change(u8 hp_slot, struct controller *ctrl)
+{
+	struct slot *p_slot;
+	u32 event_type;
+
+	/* Presence Change */
+	ctrl_dbg(ctrl, "Presence/Notify input change\n");
+
+	p_slot = shpchp_find_slot(ctrl, hp_slot + ctrl->slot_device_offset);
+
+	/*
+	 * Save the presence state
+	 */
+	p_slot->hpc_ops->get_adapter_status(p_slot, &(p_slot->presence_save));
+	if (p_slot->presence_save) {
+		/*
+		 * Card Present
+		 */
+		ctrl_info(ctrl, "Card present on Slot(%s)\n",
+			  slot_name(p_slot));
+		event_type = INT_PRESENCE_ON;
+	} else {
+		/*
+		 * Not Present
+		 */
+		ctrl_info(ctrl, "Card not present on Slot(%s)\n",
+			  slot_name(p_slot));
+		event_type = INT_PRESENCE_OFF;
+	}
+
+	queue_interrupt_event(p_slot, event_type);
+
+	return 1;
+}
+
+u8 shpchp_handle_power_fault(u8 hp_slot, struct controller *ctrl)
+{
+	struct slot *p_slot;
+	u32 event_type;
+
+	/* Power fault */
+	ctrl_dbg(ctrl, "Power fault interrupt received\n");
+
+	p_slot = shpchp_find_slot(ctrl, hp_slot + ctrl->slot_device_offset);
+
+	if ( !(p_slot->hpc_ops->query_power_fault(p_slot))) {
+		/*
+		 * Power fault Cleared
+		 */
+		ctrl_info(ctrl, "Power fault cleared on Slot(%s)\n",
+			  slot_name(p_slot));
+		p_slot->status = 0x00;
+		event_type = INT_POWER_FAULT_CLEAR;
+	} else {
+		/*
+		 *   Power fault
+		 */
+		ctrl_info(ctrl, "Power fault on Slot(%s)\n", slot_name(p_slot));
+		event_type = INT_POWER_FAULT;
+		/* set power fault status for this board */
+		p_slot->status = 0xFF;
+		ctrl_info(ctrl, "Power fault bit %x set\n", hp_slot);
+	}
+
+	queue_interrupt_event(p_slot, event_type);
+
+	return 1;
+}
+
+/* The following routines constitute the bulk of the
+   hotplug controller logic
+ */
+static int change_bus_speed(struct controller *ctrl, struct slot *p_slot,
+		enum pci_bus_speed speed)
+{
+	int rc = 0;
+
+	ctrl_dbg(ctrl, "Change speed to %d\n", speed);
+	if ((rc = p_slot->hpc_ops->set_bus_speed_mode(p_slot, speed))) {
+		ctrl_err(ctrl, "%s: Issue of set bus speed mode command "
+			 "failed\n", __func__);
+		return WRONG_BUS_FREQUENCY;
+	}
+	return rc;
+}
+
+static int fix_bus_speed(struct controller *ctrl, struct slot *pslot,
+		u8 flag, enum pci_bus_speed asp, enum pci_bus_speed bsp,
+		enum pci_bus_speed msp)
+{
+	int rc = 0;
+
+	/*
+	 * If other slots on the same bus are occupied, we cannot
+	 * change the bus speed.
+	 */
+	if (flag) {
+		if (asp < bsp) {
+			ctrl_err(ctrl, "Speed of bus %x and adapter %x "
+				 "mismatch\n", bsp, asp);
+			rc = WRONG_BUS_FREQUENCY;
+		}
+		return rc;
+	}
+
+	if (asp < msp) {
+		if (bsp != asp)
+			rc = change_bus_speed(ctrl, pslot, asp);
+	} else {
+		if (bsp != msp)
+			rc = change_bus_speed(ctrl, pslot, msp);
+	}
+	return rc;
+}
+
+/**
+ * board_added - Called after a board has been added to the system.
+ * @p_slot: target &slot
+ *
+ * Turns power on for the board.
+ * Configures board.
+ */
+static int board_added(struct slot *p_slot)
+{
+	u8 hp_slot;
+	u8 slots_not_empty = 0;
+	int rc = 0;
+	enum pci_bus_speed asp, bsp, msp;
+	struct controller *ctrl = p_slot->ctrl;
+	struct pci_bus *parent = ctrl->pci_dev->subordinate;
+
+	hp_slot = p_slot->device - ctrl->slot_device_offset;
+
+	ctrl_dbg(ctrl,
+		 "%s: p_slot->device, slot_offset, hp_slot = %d, %d ,%d\n",
+		 __func__, p_slot->device, ctrl->slot_device_offset, hp_slot);
+
+	/* Power on slot without connecting to bus */
+	rc = p_slot->hpc_ops->power_on_slot(p_slot);
+	if (rc) {
+		ctrl_err(ctrl, "Failed to power on slot\n");
+		return -1;
+	}
+
+	if ((ctrl->pci_dev->vendor == 0x8086) && (ctrl->pci_dev->device == 0x0332)) {
+		if (slots_not_empty)
+			return WRONG_BUS_FREQUENCY;
+
+		if ((rc = p_slot->hpc_ops->set_bus_speed_mode(p_slot, PCI_SPEED_33MHz))) {
+			ctrl_err(ctrl, "%s: Issue of set bus speed mode command"
+				 " failed\n", __func__);
+			return WRONG_BUS_FREQUENCY;
+		}
+
+		/* turn on board, blink green LED, turn off Amber LED */
+		if ((rc = p_slot->hpc_ops->slot_enable(p_slot))) {
+			ctrl_err(ctrl, "Issue of Slot Enable command failed\n");
+			return rc;
+		}
+	}
+
+	rc = p_slot->hpc_ops->get_adapter_speed(p_slot, &asp);
+	if (rc) {
+		ctrl_err(ctrl, "Can't get adapter speed or "
+			 "bus mode mismatch\n");
+		return WRONG_BUS_FREQUENCY;
+	}
+
+	bsp = ctrl->pci_dev->bus->cur_bus_speed;
+	msp = ctrl->pci_dev->bus->max_bus_speed;
+
+	/* Check if there are other slots or devices on the same bus */
+	if (!list_empty(&ctrl->pci_dev->subordinate->devices))
+		slots_not_empty = 1;
+
+	ctrl_dbg(ctrl, "%s: slots_not_empty %d, adapter_speed %d, bus_speed %d,"
+		 " max_bus_speed %d\n", __func__, slots_not_empty, asp,
+		 bsp, msp);
+
+	rc = fix_bus_speed(ctrl, p_slot, slots_not_empty, asp, bsp, msp);
+	if (rc)
+		return rc;
+
+	/* turn on board, blink green LED, turn off Amber LED */
+	if ((rc = p_slot->hpc_ops->slot_enable(p_slot))) {
+		ctrl_err(ctrl, "Issue of Slot Enable command failed\n");
+		return rc;
+	}
+
+	/* Wait for ~1 second */
+	msleep(1000);
+
+	ctrl_dbg(ctrl, "%s: slot status = %x\n", __func__, p_slot->status);
+	/* Check for a power fault */
+	if (p_slot->status == 0xFF) {
+		/* power fault occurred, but it was benign */
+		ctrl_dbg(ctrl, "%s: Power fault\n", __func__);
+		rc = POWER_FAILURE;
+		p_slot->status = 0;
+		goto err_exit;
+	}
+
+	if (shpchp_configure_device(p_slot)) {
+		ctrl_err(ctrl, "Cannot add device at %04x:%02x:%02x\n",
+			 pci_domain_nr(parent), p_slot->bus, p_slot->device);
+		goto err_exit;
+	}
+
+	p_slot->status = 0;
+	p_slot->is_a_board = 0x01;
+	p_slot->pwr_save = 1;
+
+	p_slot->hpc_ops->green_led_on(p_slot);
+
+	return 0;
+
+err_exit:
+	/* turn off slot, turn on Amber LED, turn off Green LED */
+	rc = p_slot->hpc_ops->slot_disable(p_slot);
+	if (rc) {
+		ctrl_err(ctrl, "%s: Issue of Slot Disable command failed\n",
+			 __func__);
+		return rc;
+	}
+
+	return(rc);
+}
+
+
+/**
+ * remove_board - Turns off slot and LEDs
+ * @p_slot: target &slot
+ */
+static int remove_board(struct slot *p_slot)
+{
+	struct controller *ctrl = p_slot->ctrl;
+	u8 hp_slot;
+	int rc;
+
+	if (shpchp_unconfigure_device(p_slot))
+		return(1);
+
+	hp_slot = p_slot->device - ctrl->slot_device_offset;
+	p_slot = shpchp_find_slot(ctrl, hp_slot + ctrl->slot_device_offset);
+
+	ctrl_dbg(ctrl, "%s: hp_slot = %d\n", __func__, hp_slot);
+
+	/* Change status to shutdown */
+	if (p_slot->is_a_board)
+		p_slot->status = 0x01;
+
+	/* turn off slot, turn on Amber LED, turn off Green LED */
+	rc = p_slot->hpc_ops->slot_disable(p_slot);
+	if (rc) {
+		ctrl_err(ctrl, "%s: Issue of Slot Disable command failed\n",
+			 __func__);
+		return rc;
+	}
+
+	rc = p_slot->hpc_ops->set_attention_status(p_slot, 0);
+	if (rc) {
+		ctrl_err(ctrl, "Issue of Set Attention command failed\n");
+		return rc;
+	}
+
+	p_slot->pwr_save = 0;
+	p_slot->is_a_board = 0;
+
+	return 0;
+}
+
+
+struct pushbutton_work_info {
+	struct slot *p_slot;
+	struct work_struct work;
+};
+
+/**
+ * shpchp_pushbutton_thread - handle pushbutton events
+ * @work: &struct work_struct to be handled
+ *
+ * Scheduled procedure to handle blocking stuff for the pushbuttons.
+ * Handles all pending events and exits.
+ */
+static void shpchp_pushbutton_thread(struct work_struct *work)
+{
+	struct pushbutton_work_info *info =
+		container_of(work, struct pushbutton_work_info, work);
+	struct slot *p_slot = info->p_slot;
+
+	mutex_lock(&p_slot->lock);
+	switch (p_slot->state) {
+	case POWEROFF_STATE:
+		mutex_unlock(&p_slot->lock);
+		shpchp_disable_slot(p_slot);
+		mutex_lock(&p_slot->lock);
+		p_slot->state = STATIC_STATE;
+		break;
+	case POWERON_STATE:
+		mutex_unlock(&p_slot->lock);
+		if (shpchp_enable_slot(p_slot))
+			p_slot->hpc_ops->green_led_off(p_slot);
+		mutex_lock(&p_slot->lock);
+		p_slot->state = STATIC_STATE;
+		break;
+	default:
+		break;
+	}
+	mutex_unlock(&p_slot->lock);
+
+	kfree(info);
+}
+
+void shpchp_queue_pushbutton_work(struct work_struct *work)
+{
+	struct slot *p_slot = container_of(work, struct slot, work.work);
+	struct pushbutton_work_info *info;
+
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info) {
+		ctrl_err(p_slot->ctrl, "%s: Cannot allocate memory\n",
+			 __func__);
+		return;
+	}
+	info->p_slot = p_slot;
+	INIT_WORK(&info->work, shpchp_pushbutton_thread);
+
+	mutex_lock(&p_slot->lock);
+	switch (p_slot->state) {
+	case BLINKINGOFF_STATE:
+		p_slot->state = POWEROFF_STATE;
+		break;
+	case BLINKINGON_STATE:
+		p_slot->state = POWERON_STATE;
+		break;
+	default:
+		kfree(info);
+		goto out;
+	}
+	queue_work(shpchp_ordered_wq, &info->work);
+ out:
+	mutex_unlock(&p_slot->lock);
+}
+
+static int update_slot_info (struct slot *slot)
+{
+	struct hotplug_slot_info *info;
+	int result;
+
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	slot->hpc_ops->get_power_status(slot, &(info->power_status));
+	slot->hpc_ops->get_attention_status(slot, &(info->attention_status));
+	slot->hpc_ops->get_latch_status(slot, &(info->latch_status));
+	slot->hpc_ops->get_adapter_status(slot, &(info->adapter_status));
+
+	result = pci_hp_change_slot_info(slot->hotplug_slot, info);
+	kfree (info);
+	return result;
+}
+
+/*
+ * Note: This function must be called with slot->lock held
+ */
+static void handle_button_press_event(struct slot *p_slot)
+{
+	u8 getstatus;
+	struct controller *ctrl = p_slot->ctrl;
+
+	switch (p_slot->state) {
+	case STATIC_STATE:
+		p_slot->hpc_ops->get_power_status(p_slot, &getstatus);
+		if (getstatus) {
+			p_slot->state = BLINKINGOFF_STATE;
+			ctrl_info(ctrl, "PCI slot #%s - powering off due to "
+				  "button press.\n", slot_name(p_slot));
+		} else {
+			p_slot->state = BLINKINGON_STATE;
+			ctrl_info(ctrl, "PCI slot #%s - powering on due to "
+				  "button press.\n", slot_name(p_slot));
+		}
+		/* blink green LED and turn off amber */
+		p_slot->hpc_ops->green_led_blink(p_slot);
+		p_slot->hpc_ops->set_attention_status(p_slot, 0);
+
+		queue_delayed_work(shpchp_wq, &p_slot->work, 5*HZ);
+		break;
+	case BLINKINGOFF_STATE:
+	case BLINKINGON_STATE:
+		/*
+		 * Cancel if we are still blinking; this means that we
+		 * press the attention again before the 5 sec. limit
+		 * expires to cancel hot-add or hot-remove
+		 */
+		ctrl_info(ctrl, "Button cancel on Slot(%s)\n",
+			  slot_name(p_slot));
+		cancel_delayed_work(&p_slot->work);
+		if (p_slot->state == BLINKINGOFF_STATE)
+			p_slot->hpc_ops->green_led_on(p_slot);
+		else
+			p_slot->hpc_ops->green_led_off(p_slot);
+		p_slot->hpc_ops->set_attention_status(p_slot, 0);
+		ctrl_info(ctrl, "PCI slot #%s - action canceled due to "
+			  "button press\n", slot_name(p_slot));
+		p_slot->state = STATIC_STATE;
+		break;
+	case POWEROFF_STATE:
+	case POWERON_STATE:
+		/*
+		 * Ignore if the slot is on power-on or power-off state;
+		 * this means that the previous attention button action
+		 * to hot-add or hot-remove is undergoing
+		 */
+		ctrl_info(ctrl, "Button ignore on Slot(%s)\n",
+			  slot_name(p_slot));
+		update_slot_info(p_slot);
+		break;
+	default:
+		ctrl_warn(ctrl, "Not a valid state\n");
+		break;
+	}
+}
+
+static void interrupt_event_handler(struct work_struct *work)
+{
+	struct event_info *info = container_of(work, struct event_info, work);
+	struct slot *p_slot = info->p_slot;
+
+	mutex_lock(&p_slot->lock);
+	switch (info->event_type) {
+	case INT_BUTTON_PRESS:
+		handle_button_press_event(p_slot);
+		break;
+	case INT_POWER_FAULT:
+		ctrl_dbg(p_slot->ctrl, "%s: Power fault\n", __func__);
+		p_slot->hpc_ops->set_attention_status(p_slot, 1);
+		p_slot->hpc_ops->green_led_off(p_slot);
+		break;
+	default:
+		update_slot_info(p_slot);
+		break;
+	}
+	mutex_unlock(&p_slot->lock);
+
+	kfree(info);
+}
+
+
+static int shpchp_enable_slot (struct slot *p_slot)
+{
+	u8 getstatus = 0;
+	int rc, retval = -ENODEV;
+	struct controller *ctrl = p_slot->ctrl;
+
+	/* Check to see if (latch closed, card present, power off) */
+	mutex_lock(&p_slot->ctrl->crit_sect);
+	rc = p_slot->hpc_ops->get_adapter_status(p_slot, &getstatus);
+	if (rc || !getstatus) {
+		ctrl_info(ctrl, "No adapter on slot(%s)\n", slot_name(p_slot));
+		goto out;
+	}
+	rc = p_slot->hpc_ops->get_latch_status(p_slot, &getstatus);
+	if (rc || getstatus) {
+		ctrl_info(ctrl, "Latch open on slot(%s)\n", slot_name(p_slot));
+		goto out;
+	}
+	rc = p_slot->hpc_ops->get_power_status(p_slot, &getstatus);
+	if (rc || getstatus) {
+		ctrl_info(ctrl, "Already enabled on slot(%s)\n",
+			  slot_name(p_slot));
+		goto out;
+	}
+
+	p_slot->is_a_board = 1;
+
+	/* We have to save the presence info for these slots */
+	p_slot->hpc_ops->get_adapter_status(p_slot, &(p_slot->presence_save));
+	p_slot->hpc_ops->get_power_status(p_slot, &(p_slot->pwr_save));
+	ctrl_dbg(ctrl, "%s: p_slot->pwr_save %x\n", __func__, p_slot->pwr_save);
+	p_slot->hpc_ops->get_latch_status(p_slot, &getstatus);
+
+	if(((p_slot->ctrl->pci_dev->vendor == PCI_VENDOR_ID_AMD) ||
+	    (p_slot->ctrl->pci_dev->device == PCI_DEVICE_ID_AMD_POGO_7458))
+	     && p_slot->ctrl->num_slots == 1) {
+		/* handle amd pogo errata; this must be done before enable  */
+		amd_pogo_errata_save_misc_reg(p_slot);
+		retval = board_added(p_slot);
+		/* handle amd pogo errata; this must be done after enable  */
+		amd_pogo_errata_restore_misc_reg(p_slot);
+	} else
+		retval = board_added(p_slot);
+
+	if (retval) {
+		p_slot->hpc_ops->get_adapter_status(p_slot,
+				&(p_slot->presence_save));
+		p_slot->hpc_ops->get_latch_status(p_slot, &getstatus);
+	}
+
+	update_slot_info(p_slot);
+ out:
+	mutex_unlock(&p_slot->ctrl->crit_sect);
+	return retval;
+}
+
+
+static int shpchp_disable_slot (struct slot *p_slot)
+{
+	u8 getstatus = 0;
+	int rc, retval = -ENODEV;
+	struct controller *ctrl = p_slot->ctrl;
+
+	if (!p_slot->ctrl)
+		return -ENODEV;
+
+	/* Check to see if (latch closed, card present, power on) */
+	mutex_lock(&p_slot->ctrl->crit_sect);
+
+	rc = p_slot->hpc_ops->get_adapter_status(p_slot, &getstatus);
+	if (rc || !getstatus) {
+		ctrl_info(ctrl, "No adapter on slot(%s)\n", slot_name(p_slot));
+		goto out;
+	}
+	rc = p_slot->hpc_ops->get_latch_status(p_slot, &getstatus);
+	if (rc || getstatus) {
+		ctrl_info(ctrl, "Latch open on slot(%s)\n", slot_name(p_slot));
+		goto out;
+	}
+	rc = p_slot->hpc_ops->get_power_status(p_slot, &getstatus);
+	if (rc || !getstatus) {
+		ctrl_info(ctrl, "Already disabled on slot(%s)\n",
+			  slot_name(p_slot));
+		goto out;
+	}
+
+	retval = remove_board(p_slot);
+	update_slot_info(p_slot);
+ out:
+	mutex_unlock(&p_slot->ctrl->crit_sect);
+	return retval;
+}
+
+int shpchp_sysfs_enable_slot(struct slot *p_slot)
+{
+	int retval = -ENODEV;
+	struct controller *ctrl = p_slot->ctrl;
+
+	mutex_lock(&p_slot->lock);
+	switch (p_slot->state) {
+	case BLINKINGON_STATE:
+		cancel_delayed_work(&p_slot->work);
+	case STATIC_STATE:
+		p_slot->state = POWERON_STATE;
+		mutex_unlock(&p_slot->lock);
+		retval = shpchp_enable_slot(p_slot);
+		mutex_lock(&p_slot->lock);
+		p_slot->state = STATIC_STATE;
+		break;
+	case POWERON_STATE:
+		ctrl_info(ctrl, "Slot %s is already in powering on state\n",
+			  slot_name(p_slot));
+		break;
+	case BLINKINGOFF_STATE:
+	case POWEROFF_STATE:
+		ctrl_info(ctrl, "Already enabled on slot %s\n",
+			  slot_name(p_slot));
+		break;
+	default:
+		ctrl_err(ctrl, "Not a valid state on slot %s\n",
+			 slot_name(p_slot));
+		break;
+	}
+	mutex_unlock(&p_slot->lock);
+
+	return retval;
+}
+
+int shpchp_sysfs_disable_slot(struct slot *p_slot)
+{
+	int retval = -ENODEV;
+	struct controller *ctrl = p_slot->ctrl;
+
+	mutex_lock(&p_slot->lock);
+	switch (p_slot->state) {
+	case BLINKINGOFF_STATE:
+		cancel_delayed_work(&p_slot->work);
+	case STATIC_STATE:
+		p_slot->state = POWEROFF_STATE;
+		mutex_unlock(&p_slot->lock);
+		retval = shpchp_disable_slot(p_slot);
+		mutex_lock(&p_slot->lock);
+		p_slot->state = STATIC_STATE;
+		break;
+	case POWEROFF_STATE:
+		ctrl_info(ctrl, "Slot %s is already in powering off state\n",
+			  slot_name(p_slot));
+		break;
+	case BLINKINGON_STATE:
+	case POWERON_STATE:
+		ctrl_info(ctrl, "Already disabled on slot %s\n",
+			  slot_name(p_slot));
+		break;
+	default:
+		ctrl_err(ctrl, "Not a valid state on slot %s\n",
+			 slot_name(p_slot));
+		break;
+	}
+	mutex_unlock(&p_slot->lock);
+
+	return retval;
+}
diff --git a/drivers/pci/hotplug/shpchp_hpc.c b/drivers/pci/hotplug/shpchp_hpc.c
new file mode 100644
index 00000000..75ba2311
--- /dev/null
+++ b/drivers/pci/hotplug/shpchp_hpc.c
@@ -0,0 +1,1113 @@
+/*
+ * Standard PCI Hot Plug Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ * Copyright (C) 2003-2004 Intel Corporation
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>,<kristen.c.accardi@intel.com>
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+
+#include "shpchp.h"
+
+/* Slot Available Register I field definition */
+#define SLOT_33MHZ		0x0000001f
+#define SLOT_66MHZ_PCIX		0x00001f00
+#define SLOT_100MHZ_PCIX	0x001f0000
+#define SLOT_133MHZ_PCIX	0x1f000000
+
+/* Slot Available Register II field definition */
+#define SLOT_66MHZ		0x0000001f
+#define SLOT_66MHZ_PCIX_266	0x00000f00
+#define SLOT_100MHZ_PCIX_266	0x0000f000
+#define SLOT_133MHZ_PCIX_266	0x000f0000
+#define SLOT_66MHZ_PCIX_533	0x00f00000
+#define SLOT_100MHZ_PCIX_533	0x0f000000
+#define SLOT_133MHZ_PCIX_533	0xf0000000
+
+/* Slot Configuration */
+#define SLOT_NUM		0x0000001F
+#define	FIRST_DEV_NUM		0x00001F00
+#define PSN			0x07FF0000
+#define	UPDOWN			0x20000000
+#define	MRLSENSOR		0x40000000
+#define ATTN_BUTTON		0x80000000
+
+/*
+ * Interrupt Locator Register definitions
+ */
+#define CMD_INTR_PENDING	(1 << 0)
+#define SLOT_INTR_PENDING(i)	(1 << (i + 1))
+
+/*
+ * Controller SERR-INT Register
+ */
+#define GLOBAL_INTR_MASK	(1 << 0)
+#define GLOBAL_SERR_MASK	(1 << 1)
+#define COMMAND_INTR_MASK	(1 << 2)
+#define ARBITER_SERR_MASK	(1 << 3)
+#define COMMAND_DETECTED	(1 << 16)
+#define ARBITER_DETECTED	(1 << 17)
+#define SERR_INTR_RSVDZ_MASK	0xfffc0000
+
+/*
+ * Logical Slot Register definitions
+ */
+#define SLOT_REG(i)		(SLOT1 + (4 * i))
+
+#define SLOT_STATE_SHIFT	(0)
+#define SLOT_STATE_MASK		(3 << 0)
+#define SLOT_STATE_PWRONLY	(1)
+#define SLOT_STATE_ENABLED	(2)
+#define SLOT_STATE_DISABLED	(3)
+#define PWR_LED_STATE_SHIFT	(2)
+#define PWR_LED_STATE_MASK	(3 << 2)
+#define ATN_LED_STATE_SHIFT	(4)
+#define ATN_LED_STATE_MASK	(3 << 4)
+#define ATN_LED_STATE_ON	(1)
+#define ATN_LED_STATE_BLINK	(2)
+#define ATN_LED_STATE_OFF	(3)
+#define POWER_FAULT		(1 << 6)
+#define ATN_BUTTON		(1 << 7)
+#define MRL_SENSOR		(1 << 8)
+#define MHZ66_CAP		(1 << 9)
+#define PRSNT_SHIFT		(10)
+#define PRSNT_MASK		(3 << 10)
+#define PCIX_CAP_SHIFT		(12)
+#define PCIX_CAP_MASK_PI1	(3 << 12)
+#define PCIX_CAP_MASK_PI2	(7 << 12)
+#define PRSNT_CHANGE_DETECTED	(1 << 16)
+#define ISO_PFAULT_DETECTED	(1 << 17)
+#define BUTTON_PRESS_DETECTED	(1 << 18)
+#define MRL_CHANGE_DETECTED	(1 << 19)
+#define CON_PFAULT_DETECTED	(1 << 20)
+#define PRSNT_CHANGE_INTR_MASK	(1 << 24)
+#define ISO_PFAULT_INTR_MASK	(1 << 25)
+#define BUTTON_PRESS_INTR_MASK	(1 << 26)
+#define MRL_CHANGE_INTR_MASK	(1 << 27)
+#define CON_PFAULT_INTR_MASK	(1 << 28)
+#define MRL_CHANGE_SERR_MASK	(1 << 29)
+#define CON_PFAULT_SERR_MASK	(1 << 30)
+#define SLOT_REG_RSVDZ_MASK	((1 << 15) | (7 << 21))
+
+/*
+ * SHPC Command Code definitnions
+ *
+ *     Slot Operation				00h - 3Fh
+ *     Set Bus Segment Speed/Mode A		40h - 47h
+ *     Power-Only All Slots			48h
+ *     Enable All Slots				49h
+ *     Set Bus Segment Speed/Mode B (PI=2)	50h - 5Fh
+ *     Reserved Command Codes			60h - BFh
+ *     Vendor Specific Commands			C0h - FFh
+ */
+#define SET_SLOT_PWR		0x01	/* Slot Operation */
+#define SET_SLOT_ENABLE		0x02
+#define SET_SLOT_DISABLE	0x03
+#define SET_PWR_ON		0x04
+#define SET_PWR_BLINK		0x08
+#define SET_PWR_OFF		0x0c
+#define SET_ATTN_ON		0x10
+#define SET_ATTN_BLINK		0x20
+#define SET_ATTN_OFF		0x30
+#define SETA_PCI_33MHZ		0x40	/* Set Bus Segment Speed/Mode A */
+#define SETA_PCI_66MHZ		0x41
+#define SETA_PCIX_66MHZ		0x42
+#define SETA_PCIX_100MHZ	0x43
+#define SETA_PCIX_133MHZ	0x44
+#define SETA_RESERVED1		0x45
+#define SETA_RESERVED2		0x46
+#define SETA_RESERVED3		0x47
+#define SET_PWR_ONLY_ALL	0x48	/* Power-Only All Slots */
+#define SET_ENABLE_ALL		0x49	/* Enable All Slots */
+#define	SETB_PCI_33MHZ		0x50	/* Set Bus Segment Speed/Mode B */
+#define SETB_PCI_66MHZ		0x51
+#define SETB_PCIX_66MHZ_PM	0x52
+#define SETB_PCIX_100MHZ_PM	0x53
+#define SETB_PCIX_133MHZ_PM	0x54
+#define SETB_PCIX_66MHZ_EM	0x55
+#define SETB_PCIX_100MHZ_EM	0x56
+#define SETB_PCIX_133MHZ_EM	0x57
+#define SETB_PCIX_66MHZ_266	0x58
+#define SETB_PCIX_100MHZ_266	0x59
+#define SETB_PCIX_133MHZ_266	0x5a
+#define SETB_PCIX_66MHZ_533	0x5b
+#define SETB_PCIX_100MHZ_533	0x5c
+#define SETB_PCIX_133MHZ_533	0x5d
+#define SETB_RESERVED1		0x5e
+#define SETB_RESERVED2		0x5f
+
+/*
+ * SHPC controller command error code
+ */
+#define SWITCH_OPEN		0x1
+#define INVALID_CMD		0x2
+#define INVALID_SPEED_MODE	0x4
+
+/*
+ * For accessing SHPC Working Register Set via PCI Configuration Space
+ */
+#define DWORD_SELECT		0x2
+#define DWORD_DATA		0x4
+
+/* Field Offset in Logical Slot Register - byte boundary */
+#define SLOT_EVENT_LATCH	0x2
+#define SLOT_SERR_INT_MASK	0x3
+
+static irqreturn_t shpc_isr(int irq, void *dev_id);
+static void start_int_poll_timer(struct controller *ctrl, int sec);
+static int hpc_check_cmd_status(struct controller *ctrl);
+
+static inline u8 shpc_readb(struct controller *ctrl, int reg)
+{
+	return readb(ctrl->creg + reg);
+}
+
+static inline void shpc_writeb(struct controller *ctrl, int reg, u8 val)
+{
+	writeb(val, ctrl->creg + reg);
+}
+
+static inline u16 shpc_readw(struct controller *ctrl, int reg)
+{
+	return readw(ctrl->creg + reg);
+}
+
+static inline void shpc_writew(struct controller *ctrl, int reg, u16 val)
+{
+	writew(val, ctrl->creg + reg);
+}
+
+static inline u32 shpc_readl(struct controller *ctrl, int reg)
+{
+	return readl(ctrl->creg + reg);
+}
+
+static inline void shpc_writel(struct controller *ctrl, int reg, u32 val)
+{
+	writel(val, ctrl->creg + reg);
+}
+
+static inline int shpc_indirect_read(struct controller *ctrl, int index,
+				     u32 *value)
+{
+	int rc;
+	u32 cap_offset = ctrl->cap_offset;
+	struct pci_dev *pdev = ctrl->pci_dev;
+
+	rc = pci_write_config_byte(pdev, cap_offset + DWORD_SELECT, index);
+	if (rc)
+		return rc;
+	return pci_read_config_dword(pdev, cap_offset + DWORD_DATA, value);
+}
+
+/*
+ * This is the interrupt polling timeout function.
+ */
+static void int_poll_timeout(unsigned long data)
+{
+	struct controller *ctrl = (struct controller *)data;
+
+	/* Poll for interrupt events.  regs == NULL => polling */
+	shpc_isr(0, ctrl);
+
+	init_timer(&ctrl->poll_timer);
+	if (!shpchp_poll_time)
+		shpchp_poll_time = 2; /* default polling interval is 2 sec */
+
+	start_int_poll_timer(ctrl, shpchp_poll_time);
+}
+
+/*
+ * This function starts the interrupt polling timer.
+ */
+static void start_int_poll_timer(struct controller *ctrl, int sec)
+{
+	/* Clamp to sane value */
+	if ((sec <= 0) || (sec > 60))
+		sec = 2;
+
+	ctrl->poll_timer.function = &int_poll_timeout;
+	ctrl->poll_timer.data = (unsigned long)ctrl;
+	ctrl->poll_timer.expires = jiffies + sec * HZ;
+	add_timer(&ctrl->poll_timer);
+}
+
+static inline int is_ctrl_busy(struct controller *ctrl)
+{
+	u16 cmd_status = shpc_readw(ctrl, CMD_STATUS);
+	return cmd_status & 0x1;
+}
+
+/*
+ * Returns 1 if SHPC finishes executing a command within 1 sec,
+ * otherwise returns 0.
+ */
+static inline int shpc_poll_ctrl_busy(struct controller *ctrl)
+{
+	int i;
+
+	if (!is_ctrl_busy(ctrl))
+		return 1;
+
+	/* Check every 0.1 sec for a total of 1 sec */
+	for (i = 0; i < 10; i++) {
+		msleep(100);
+		if (!is_ctrl_busy(ctrl))
+			return 1;
+	}
+
+	return 0;
+}
+
+static inline int shpc_wait_cmd(struct controller *ctrl)
+{
+	int retval = 0;
+	unsigned long timeout = msecs_to_jiffies(1000);
+	int rc;
+
+	if (shpchp_poll_mode)
+		rc = shpc_poll_ctrl_busy(ctrl);
+	else
+		rc = wait_event_interruptible_timeout(ctrl->queue,
+						!is_ctrl_busy(ctrl), timeout);
+	if (!rc && is_ctrl_busy(ctrl)) {
+		retval = -EIO;
+		ctrl_err(ctrl, "Command not completed in 1000 msec\n");
+	} else if (rc < 0) {
+		retval = -EINTR;
+		ctrl_info(ctrl, "Command was interrupted by a signal\n");
+	}
+
+	return retval;
+}
+
+static int shpc_write_cmd(struct slot *slot, u8 t_slot, u8 cmd)
+{
+	struct controller *ctrl = slot->ctrl;
+	u16 cmd_status;
+	int retval = 0;
+	u16 temp_word;
+
+	mutex_lock(&slot->ctrl->cmd_lock);
+
+	if (!shpc_poll_ctrl_busy(ctrl)) {
+		/* After 1 sec and and the controller is still busy */
+		ctrl_err(ctrl, "Controller is still busy after 1 sec\n");
+		retval = -EBUSY;
+		goto out;
+	}
+
+	++t_slot;
+	temp_word =  (t_slot << 8) | (cmd & 0xFF);
+	ctrl_dbg(ctrl, "%s: t_slot %x cmd %x\n", __func__, t_slot, cmd);
+
+	/* To make sure the Controller Busy bit is 0 before we send out the
+	 * command.
+	 */
+	shpc_writew(ctrl, CMD, temp_word);
+
+	/*
+	 * Wait for command completion.
+	 */
+	retval = shpc_wait_cmd(slot->ctrl);
+	if (retval)
+		goto out;
+
+	cmd_status = hpc_check_cmd_status(slot->ctrl);
+	if (cmd_status) {
+		ctrl_err(ctrl,
+			 "Failed to issued command 0x%x (error code = %d)\n",
+			 cmd, cmd_status);
+		retval = -EIO;
+	}
+ out:
+	mutex_unlock(&slot->ctrl->cmd_lock);
+	return retval;
+}
+
+static int hpc_check_cmd_status(struct controller *ctrl)
+{
+	int retval = 0;
+	u16 cmd_status = shpc_readw(ctrl, CMD_STATUS) & 0x000F;
+
+	switch (cmd_status >> 1) {
+	case 0:
+		retval = 0;
+		break;
+	case 1:
+		retval = SWITCH_OPEN;
+		ctrl_err(ctrl, "Switch opened!\n");
+		break;
+	case 2:
+		retval = INVALID_CMD;
+		ctrl_err(ctrl, "Invalid HPC command!\n");
+		break;
+	case 4:
+		retval = INVALID_SPEED_MODE;
+		ctrl_err(ctrl, "Invalid bus speed/mode!\n");
+		break;
+	default:
+		retval = cmd_status;
+	}
+
+	return retval;
+}
+
+
+static int hpc_get_attention_status(struct slot *slot, u8 *status)
+{
+	struct controller *ctrl = slot->ctrl;
+	u32 slot_reg = shpc_readl(ctrl, SLOT_REG(slot->hp_slot));
+	u8 state = (slot_reg & ATN_LED_STATE_MASK) >> ATN_LED_STATE_SHIFT;
+
+	switch (state) {
+	case ATN_LED_STATE_ON:
+		*status = 1;	/* On */
+		break;
+	case ATN_LED_STATE_BLINK:
+		*status = 2;	/* Blink */
+		break;
+	case ATN_LED_STATE_OFF:
+		*status = 0;	/* Off */
+		break;
+	default:
+		*status = 0xFF;	/* Reserved */
+		break;
+	}
+
+	return 0;
+}
+
+static int hpc_get_power_status(struct slot * slot, u8 *status)
+{
+	struct controller *ctrl = slot->ctrl;
+	u32 slot_reg = shpc_readl(ctrl, SLOT_REG(slot->hp_slot));
+	u8 state = (slot_reg & SLOT_STATE_MASK) >> SLOT_STATE_SHIFT;
+
+	switch (state) {
+	case SLOT_STATE_PWRONLY:
+		*status = 2;	/* Powered only */
+		break;
+	case SLOT_STATE_ENABLED:
+		*status = 1;	/* Enabled */
+		break;
+	case SLOT_STATE_DISABLED:
+		*status = 0;	/* Disabled */
+		break;
+	default:
+		*status = 0xFF;	/* Reserved */
+		break;
+	}
+
+	return 0;
+}
+
+
+static int hpc_get_latch_status(struct slot *slot, u8 *status)
+{
+	struct controller *ctrl = slot->ctrl;
+	u32 slot_reg = shpc_readl(ctrl, SLOT_REG(slot->hp_slot));
+
+	*status = !!(slot_reg & MRL_SENSOR);	/* 0 -> close; 1 -> open */
+
+	return 0;
+}
+
+static int hpc_get_adapter_status(struct slot *slot, u8 *status)
+{
+	struct controller *ctrl = slot->ctrl;
+	u32 slot_reg = shpc_readl(ctrl, SLOT_REG(slot->hp_slot));
+	u8 state = (slot_reg & PRSNT_MASK) >> PRSNT_SHIFT;
+
+	*status = (state != 0x3) ? 1 : 0;
+
+	return 0;
+}
+
+static int hpc_get_prog_int(struct slot *slot, u8 *prog_int)
+{
+	struct controller *ctrl = slot->ctrl;
+
+	*prog_int = shpc_readb(ctrl, PROG_INTERFACE);
+
+	return 0;
+}
+
+static int hpc_get_adapter_speed(struct slot *slot, enum pci_bus_speed *value)
+{
+	int retval = 0;
+	struct controller *ctrl = slot->ctrl;
+	u32 slot_reg = shpc_readl(ctrl, SLOT_REG(slot->hp_slot));
+	u8 m66_cap  = !!(slot_reg & MHZ66_CAP);
+	u8 pi, pcix_cap;
+
+	if ((retval = hpc_get_prog_int(slot, &pi)))
+		return retval;
+
+	switch (pi) {
+	case 1:
+		pcix_cap = (slot_reg & PCIX_CAP_MASK_PI1) >> PCIX_CAP_SHIFT;
+		break;
+	case 2:
+		pcix_cap = (slot_reg & PCIX_CAP_MASK_PI2) >> PCIX_CAP_SHIFT;
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	ctrl_dbg(ctrl, "%s: slot_reg = %x, pcix_cap = %x, m66_cap = %x\n",
+		 __func__, slot_reg, pcix_cap, m66_cap);
+
+	switch (pcix_cap) {
+	case 0x0:
+		*value = m66_cap ? PCI_SPEED_66MHz : PCI_SPEED_33MHz;
+		break;
+	case 0x1:
+		*value = PCI_SPEED_66MHz_PCIX;
+		break;
+	case 0x3:
+		*value = PCI_SPEED_133MHz_PCIX;
+		break;
+	case 0x4:
+		*value = PCI_SPEED_133MHz_PCIX_266;
+		break;
+	case 0x5:
+		*value = PCI_SPEED_133MHz_PCIX_533;
+		break;
+	case 0x2:
+	default:
+		*value = PCI_SPEED_UNKNOWN;
+		retval = -ENODEV;
+		break;
+	}
+
+	ctrl_dbg(ctrl, "Adapter speed = %d\n", *value);
+	return retval;
+}
+
+static int hpc_get_mode1_ECC_cap(struct slot *slot, u8 *mode)
+{
+	int retval = 0;
+	struct controller *ctrl = slot->ctrl;
+	u16 sec_bus_status = shpc_readw(ctrl, SEC_BUS_CONFIG);
+	u8 pi = shpc_readb(ctrl, PROG_INTERFACE);
+
+	if (pi == 2) {
+		*mode = (sec_bus_status & 0x0100) >> 8;
+	} else {
+		retval = -1;
+	}
+
+	ctrl_dbg(ctrl, "Mode 1 ECC cap = %d\n", *mode);
+	return retval;
+}
+
+static int hpc_query_power_fault(struct slot * slot)
+{
+	struct controller *ctrl = slot->ctrl;
+	u32 slot_reg = shpc_readl(ctrl, SLOT_REG(slot->hp_slot));
+
+	/* Note: Logic 0 => fault */
+	return !(slot_reg & POWER_FAULT);
+}
+
+static int hpc_set_attention_status(struct slot *slot, u8 value)
+{
+	u8 slot_cmd = 0;
+
+	switch (value) {
+		case 0 :
+			slot_cmd = SET_ATTN_OFF;	/* OFF */
+			break;
+		case 1:
+			slot_cmd = SET_ATTN_ON;		/* ON */
+			break;
+		case 2:
+			slot_cmd = SET_ATTN_BLINK;	/* BLINK */
+			break;
+		default:
+			return -1;
+	}
+
+	return shpc_write_cmd(slot, slot->hp_slot, slot_cmd);
+}
+
+
+static void hpc_set_green_led_on(struct slot *slot)
+{
+	shpc_write_cmd(slot, slot->hp_slot, SET_PWR_ON);
+}
+
+static void hpc_set_green_led_off(struct slot *slot)
+{
+	shpc_write_cmd(slot, slot->hp_slot, SET_PWR_OFF);
+}
+
+static void hpc_set_green_led_blink(struct slot *slot)
+{
+	shpc_write_cmd(slot, slot->hp_slot, SET_PWR_BLINK);
+}
+
+static void hpc_release_ctlr(struct controller *ctrl)
+{
+	int i;
+	u32 slot_reg, serr_int;
+
+	/*
+	 * Mask event interrupts and SERRs of all slots
+	 */
+	for (i = 0; i < ctrl->num_slots; i++) {
+		slot_reg = shpc_readl(ctrl, SLOT_REG(i));
+		slot_reg |= (PRSNT_CHANGE_INTR_MASK | ISO_PFAULT_INTR_MASK |
+			     BUTTON_PRESS_INTR_MASK | MRL_CHANGE_INTR_MASK |
+			     CON_PFAULT_INTR_MASK   | MRL_CHANGE_SERR_MASK |
+			     CON_PFAULT_SERR_MASK);
+		slot_reg &= ~SLOT_REG_RSVDZ_MASK;
+		shpc_writel(ctrl, SLOT_REG(i), slot_reg);
+	}
+
+	cleanup_slots(ctrl);
+
+	/*
+	 * Mask SERR and System Interrupt generation
+	 */
+	serr_int = shpc_readl(ctrl, SERR_INTR_ENABLE);
+	serr_int |= (GLOBAL_INTR_MASK  | GLOBAL_SERR_MASK |
+		     COMMAND_INTR_MASK | ARBITER_SERR_MASK);
+	serr_int &= ~SERR_INTR_RSVDZ_MASK;
+	shpc_writel(ctrl, SERR_INTR_ENABLE, serr_int);
+
+	if (shpchp_poll_mode)
+		del_timer(&ctrl->poll_timer);
+	else {
+		free_irq(ctrl->pci_dev->irq, ctrl);
+		pci_disable_msi(ctrl->pci_dev);
+	}
+
+	iounmap(ctrl->creg);
+	release_mem_region(ctrl->mmio_base, ctrl->mmio_size);
+}
+
+static int hpc_power_on_slot(struct slot * slot)
+{
+	int retval;
+
+	retval = shpc_write_cmd(slot, slot->hp_slot, SET_SLOT_PWR);
+	if (retval)
+		ctrl_err(slot->ctrl, "%s: Write command failed!\n", __func__);
+
+	return retval;
+}
+
+static int hpc_slot_enable(struct slot * slot)
+{
+	int retval;
+
+	/* Slot - Enable, Power Indicator - Blink, Attention Indicator - Off */
+	retval = shpc_write_cmd(slot, slot->hp_slot,
+			SET_SLOT_ENABLE | SET_PWR_BLINK | SET_ATTN_OFF);
+	if (retval)
+		ctrl_err(slot->ctrl, "%s: Write command failed!\n", __func__);
+
+	return retval;
+}
+
+static int hpc_slot_disable(struct slot * slot)
+{
+	int retval;
+
+	/* Slot - Disable, Power Indicator - Off, Attention Indicator - On */
+	retval = shpc_write_cmd(slot, slot->hp_slot,
+			SET_SLOT_DISABLE | SET_PWR_OFF | SET_ATTN_ON);
+	if (retval)
+		ctrl_err(slot->ctrl, "%s: Write command failed!\n", __func__);
+
+	return retval;
+}
+
+static int shpc_get_cur_bus_speed(struct controller *ctrl)
+{
+	int retval = 0;
+	struct pci_bus *bus = ctrl->pci_dev->subordinate;
+	enum pci_bus_speed bus_speed = PCI_SPEED_UNKNOWN;
+	u16 sec_bus_reg = shpc_readw(ctrl, SEC_BUS_CONFIG);
+	u8 pi = shpc_readb(ctrl, PROG_INTERFACE);
+	u8 speed_mode = (pi == 2) ? (sec_bus_reg & 0xF) : (sec_bus_reg & 0x7);
+
+	if ((pi == 1) && (speed_mode > 4)) {
+		retval = -ENODEV;
+		goto out;
+	}
+
+	switch (speed_mode) {
+	case 0x0:
+		bus_speed = PCI_SPEED_33MHz;
+		break;
+	case 0x1:
+		bus_speed = PCI_SPEED_66MHz;
+		break;
+	case 0x2:
+		bus_speed = PCI_SPEED_66MHz_PCIX;
+		break;
+	case 0x3:
+		bus_speed = PCI_SPEED_100MHz_PCIX;
+		break;
+	case 0x4:
+		bus_speed = PCI_SPEED_133MHz_PCIX;
+		break;
+	case 0x5:
+		bus_speed = PCI_SPEED_66MHz_PCIX_ECC;
+		break;
+	case 0x6:
+		bus_speed = PCI_SPEED_100MHz_PCIX_ECC;
+		break;
+	case 0x7:
+		bus_speed = PCI_SPEED_133MHz_PCIX_ECC;
+		break;
+	case 0x8:
+		bus_speed = PCI_SPEED_66MHz_PCIX_266;
+		break;
+	case 0x9:
+		bus_speed = PCI_SPEED_100MHz_PCIX_266;
+		break;
+	case 0xa:
+		bus_speed = PCI_SPEED_133MHz_PCIX_266;
+		break;
+	case 0xb:
+		bus_speed = PCI_SPEED_66MHz_PCIX_533;
+		break;
+	case 0xc:
+		bus_speed = PCI_SPEED_100MHz_PCIX_533;
+		break;
+	case 0xd:
+		bus_speed = PCI_SPEED_133MHz_PCIX_533;
+		break;
+	default:
+		retval = -ENODEV;
+		break;
+	}
+
+ out:
+	bus->cur_bus_speed = bus_speed;
+	dbg("Current bus speed = %d\n", bus_speed);
+	return retval;
+}
+
+
+static int hpc_set_bus_speed_mode(struct slot * slot, enum pci_bus_speed value)
+{
+	int retval;
+	struct controller *ctrl = slot->ctrl;
+	u8 pi, cmd;
+
+	pi = shpc_readb(ctrl, PROG_INTERFACE);
+	if ((pi == 1) && (value > PCI_SPEED_133MHz_PCIX))
+		return -EINVAL;
+
+	switch (value) {
+	case PCI_SPEED_33MHz:
+		cmd = SETA_PCI_33MHZ;
+		break;
+	case PCI_SPEED_66MHz:
+		cmd = SETA_PCI_66MHZ;
+		break;
+	case PCI_SPEED_66MHz_PCIX:
+		cmd = SETA_PCIX_66MHZ;
+		break;
+	case PCI_SPEED_100MHz_PCIX:
+		cmd = SETA_PCIX_100MHZ;
+		break;
+	case PCI_SPEED_133MHz_PCIX:
+		cmd = SETA_PCIX_133MHZ;
+		break;
+	case PCI_SPEED_66MHz_PCIX_ECC:
+		cmd = SETB_PCIX_66MHZ_EM;
+		break;
+	case PCI_SPEED_100MHz_PCIX_ECC:
+		cmd = SETB_PCIX_100MHZ_EM;
+		break;
+	case PCI_SPEED_133MHz_PCIX_ECC:
+		cmd = SETB_PCIX_133MHZ_EM;
+		break;
+	case PCI_SPEED_66MHz_PCIX_266:
+		cmd = SETB_PCIX_66MHZ_266;
+		break;
+	case PCI_SPEED_100MHz_PCIX_266:
+		cmd = SETB_PCIX_100MHZ_266;
+		break;
+	case PCI_SPEED_133MHz_PCIX_266:
+		cmd = SETB_PCIX_133MHZ_266;
+		break;
+	case PCI_SPEED_66MHz_PCIX_533:
+		cmd = SETB_PCIX_66MHZ_533;
+		break;
+	case PCI_SPEED_100MHz_PCIX_533:
+		cmd = SETB_PCIX_100MHZ_533;
+		break;
+	case PCI_SPEED_133MHz_PCIX_533:
+		cmd = SETB_PCIX_133MHZ_533;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	retval = shpc_write_cmd(slot, 0, cmd);
+	if (retval)
+		ctrl_err(ctrl, "%s: Write command failed!\n", __func__);
+	else
+		shpc_get_cur_bus_speed(ctrl);
+
+	return retval;
+}
+
+static irqreturn_t shpc_isr(int irq, void *dev_id)
+{
+	struct controller *ctrl = (struct controller *)dev_id;
+	u32 serr_int, slot_reg, intr_loc, intr_loc2;
+	int hp_slot;
+
+	/* Check to see if it was our interrupt */
+	intr_loc = shpc_readl(ctrl, INTR_LOC);
+	if (!intr_loc)
+		return IRQ_NONE;
+
+	ctrl_dbg(ctrl, "%s: intr_loc = %x\n", __func__, intr_loc);
+
+	if(!shpchp_poll_mode) {
+		/*
+		 * Mask Global Interrupt Mask - see implementation
+		 * note on p. 139 of SHPC spec rev 1.0
+		 */
+		serr_int = shpc_readl(ctrl, SERR_INTR_ENABLE);
+		serr_int |= GLOBAL_INTR_MASK;
+		serr_int &= ~SERR_INTR_RSVDZ_MASK;
+		shpc_writel(ctrl, SERR_INTR_ENABLE, serr_int);
+
+		intr_loc2 = shpc_readl(ctrl, INTR_LOC);
+		ctrl_dbg(ctrl, "%s: intr_loc2 = %x\n", __func__, intr_loc2);
+	}
+
+	if (intr_loc & CMD_INTR_PENDING) {
+		/*
+		 * Command Complete Interrupt Pending
+		 * RO only - clear by writing 1 to the Command Completion
+		 * Detect bit in Controller SERR-INT register
+		 */
+		serr_int = shpc_readl(ctrl, SERR_INTR_ENABLE);
+		serr_int &= ~SERR_INTR_RSVDZ_MASK;
+		shpc_writel(ctrl, SERR_INTR_ENABLE, serr_int);
+
+		wake_up_interruptible(&ctrl->queue);
+	}
+
+	if (!(intr_loc & ~CMD_INTR_PENDING))
+		goto out;
+
+	for (hp_slot = 0; hp_slot < ctrl->num_slots; hp_slot++) {
+		/* To find out which slot has interrupt pending */
+		if (!(intr_loc & SLOT_INTR_PENDING(hp_slot)))
+			continue;
+
+		slot_reg = shpc_readl(ctrl, SLOT_REG(hp_slot));
+		ctrl_dbg(ctrl, "Slot %x with intr, slot register = %x\n",
+			 hp_slot, slot_reg);
+
+		if (slot_reg & MRL_CHANGE_DETECTED)
+			shpchp_handle_switch_change(hp_slot, ctrl);
+
+		if (slot_reg & BUTTON_PRESS_DETECTED)
+			shpchp_handle_attention_button(hp_slot, ctrl);
+
+		if (slot_reg & PRSNT_CHANGE_DETECTED)
+			shpchp_handle_presence_change(hp_slot, ctrl);
+
+		if (slot_reg & (ISO_PFAULT_DETECTED | CON_PFAULT_DETECTED))
+			shpchp_handle_power_fault(hp_slot, ctrl);
+
+		/* Clear all slot events */
+		slot_reg &= ~SLOT_REG_RSVDZ_MASK;
+		shpc_writel(ctrl, SLOT_REG(hp_slot), slot_reg);
+	}
+ out:
+	if (!shpchp_poll_mode) {
+		/* Unmask Global Interrupt Mask */
+		serr_int = shpc_readl(ctrl, SERR_INTR_ENABLE);
+		serr_int &= ~(GLOBAL_INTR_MASK | SERR_INTR_RSVDZ_MASK);
+		shpc_writel(ctrl, SERR_INTR_ENABLE, serr_int);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int shpc_get_max_bus_speed(struct controller *ctrl)
+{
+	int retval = 0;
+	struct pci_bus *bus = ctrl->pci_dev->subordinate;
+	enum pci_bus_speed bus_speed = PCI_SPEED_UNKNOWN;
+	u8 pi = shpc_readb(ctrl, PROG_INTERFACE);
+	u32 slot_avail1 = shpc_readl(ctrl, SLOT_AVAIL1);
+	u32 slot_avail2 = shpc_readl(ctrl, SLOT_AVAIL2);
+
+	if (pi == 2) {
+		if (slot_avail2 & SLOT_133MHZ_PCIX_533)
+			bus_speed = PCI_SPEED_133MHz_PCIX_533;
+		else if (slot_avail2 & SLOT_100MHZ_PCIX_533)
+			bus_speed = PCI_SPEED_100MHz_PCIX_533;
+		else if (slot_avail2 & SLOT_66MHZ_PCIX_533)
+			bus_speed = PCI_SPEED_66MHz_PCIX_533;
+		else if (slot_avail2 & SLOT_133MHZ_PCIX_266)
+			bus_speed = PCI_SPEED_133MHz_PCIX_266;
+		else if (slot_avail2 & SLOT_100MHZ_PCIX_266)
+			bus_speed = PCI_SPEED_100MHz_PCIX_266;
+		else if (slot_avail2 & SLOT_66MHZ_PCIX_266)
+			bus_speed = PCI_SPEED_66MHz_PCIX_266;
+	}
+
+	if (bus_speed == PCI_SPEED_UNKNOWN) {
+		if (slot_avail1 & SLOT_133MHZ_PCIX)
+			bus_speed = PCI_SPEED_133MHz_PCIX;
+		else if (slot_avail1 & SLOT_100MHZ_PCIX)
+			bus_speed = PCI_SPEED_100MHz_PCIX;
+		else if (slot_avail1 & SLOT_66MHZ_PCIX)
+			bus_speed = PCI_SPEED_66MHz_PCIX;
+		else if (slot_avail2 & SLOT_66MHZ)
+			bus_speed = PCI_SPEED_66MHz;
+		else if (slot_avail1 & SLOT_33MHZ)
+			bus_speed = PCI_SPEED_33MHz;
+		else
+			retval = -ENODEV;
+	}
+
+	bus->max_bus_speed = bus_speed;
+	ctrl_dbg(ctrl, "Max bus speed = %d\n", bus_speed);
+
+	return retval;
+}
+
+static struct hpc_ops shpchp_hpc_ops = {
+	.power_on_slot			= hpc_power_on_slot,
+	.slot_enable			= hpc_slot_enable,
+	.slot_disable			= hpc_slot_disable,
+	.set_bus_speed_mode		= hpc_set_bus_speed_mode,
+	.set_attention_status	= hpc_set_attention_status,
+	.get_power_status		= hpc_get_power_status,
+	.get_attention_status	= hpc_get_attention_status,
+	.get_latch_status		= hpc_get_latch_status,
+	.get_adapter_status		= hpc_get_adapter_status,
+
+	.get_adapter_speed		= hpc_get_adapter_speed,
+	.get_mode1_ECC_cap		= hpc_get_mode1_ECC_cap,
+	.get_prog_int			= hpc_get_prog_int,
+
+	.query_power_fault		= hpc_query_power_fault,
+	.green_led_on			= hpc_set_green_led_on,
+	.green_led_off			= hpc_set_green_led_off,
+	.green_led_blink		= hpc_set_green_led_blink,
+
+	.release_ctlr			= hpc_release_ctlr,
+};
+
+int shpc_init(struct controller *ctrl, struct pci_dev *pdev)
+{
+	int rc = -1, num_slots = 0;
+	u8 hp_slot;
+	u32 shpc_base_offset;
+	u32 tempdword, slot_reg, slot_config;
+	u8 i;
+
+	ctrl->pci_dev = pdev;  /* pci_dev of the P2P bridge */
+	ctrl_dbg(ctrl, "Hotplug Controller:\n");
+
+	if (pdev->vendor == PCI_VENDOR_ID_AMD &&
+	    pdev->device == PCI_DEVICE_ID_AMD_GOLAM_7450) {
+		/* amd shpc driver doesn't use Base Offset; assume 0 */
+		ctrl->mmio_base = pci_resource_start(pdev, 0);
+		ctrl->mmio_size = pci_resource_len(pdev, 0);
+	} else {
+		ctrl->cap_offset = pci_find_capability(pdev, PCI_CAP_ID_SHPC);
+		if (!ctrl->cap_offset) {
+			ctrl_err(ctrl, "Cannot find PCI capability\n");
+			goto abort;
+		}
+		ctrl_dbg(ctrl, " cap_offset = %x\n", ctrl->cap_offset);
+
+		rc = shpc_indirect_read(ctrl, 0, &shpc_base_offset);
+		if (rc) {
+			ctrl_err(ctrl, "Cannot read base_offset\n");
+			goto abort;
+		}
+
+		rc = shpc_indirect_read(ctrl, 3, &tempdword);
+		if (rc) {
+			ctrl_err(ctrl, "Cannot read slot config\n");
+			goto abort;
+		}
+		num_slots = tempdword & SLOT_NUM;
+		ctrl_dbg(ctrl, " num_slots (indirect) %x\n", num_slots);
+
+		for (i = 0; i < 9 + num_slots; i++) {
+			rc = shpc_indirect_read(ctrl, i, &tempdword);
+			if (rc) {
+				ctrl_err(ctrl,
+					 "Cannot read creg (index = %d)\n", i);
+				goto abort;
+			}
+			ctrl_dbg(ctrl, " offset %d: value %x\n", i, tempdword);
+		}
+
+		ctrl->mmio_base =
+			pci_resource_start(pdev, 0) + shpc_base_offset;
+		ctrl->mmio_size = 0x24 + 0x4 * num_slots;
+	}
+
+	ctrl_info(ctrl, "HPC vendor_id %x device_id %x ss_vid %x ss_did %x\n",
+		  pdev->vendor, pdev->device, pdev->subsystem_vendor,
+		  pdev->subsystem_device);
+
+	rc = pci_enable_device(pdev);
+	if (rc) {
+		ctrl_err(ctrl, "pci_enable_device failed\n");
+		goto abort;
+	}
+
+	if (!request_mem_region(ctrl->mmio_base, ctrl->mmio_size, MY_NAME)) {
+		ctrl_err(ctrl, "Cannot reserve MMIO region\n");
+		rc = -1;
+		goto abort;
+	}
+
+	ctrl->creg = ioremap(ctrl->mmio_base, ctrl->mmio_size);
+	if (!ctrl->creg) {
+		ctrl_err(ctrl, "Cannot remap MMIO region %lx @ %lx\n",
+			 ctrl->mmio_size, ctrl->mmio_base);
+		release_mem_region(ctrl->mmio_base, ctrl->mmio_size);
+		rc = -1;
+		goto abort;
+	}
+	ctrl_dbg(ctrl, "ctrl->creg %p\n", ctrl->creg);
+
+	mutex_init(&ctrl->crit_sect);
+	mutex_init(&ctrl->cmd_lock);
+
+	/* Setup wait queue */
+	init_waitqueue_head(&ctrl->queue);
+
+	ctrl->hpc_ops = &shpchp_hpc_ops;
+
+	/* Return PCI Controller Info */
+	slot_config = shpc_readl(ctrl, SLOT_CONFIG);
+	ctrl->slot_device_offset = (slot_config & FIRST_DEV_NUM) >> 8;
+	ctrl->num_slots = slot_config & SLOT_NUM;
+	ctrl->first_slot = (slot_config & PSN) >> 16;
+	ctrl->slot_num_inc = ((slot_config & UPDOWN) >> 29) ? 1 : -1;
+
+	/* Mask Global Interrupt Mask & Command Complete Interrupt Mask */
+	tempdword = shpc_readl(ctrl, SERR_INTR_ENABLE);
+	ctrl_dbg(ctrl, "SERR_INTR_ENABLE = %x\n", tempdword);
+	tempdword |= (GLOBAL_INTR_MASK  | GLOBAL_SERR_MASK |
+		      COMMAND_INTR_MASK | ARBITER_SERR_MASK);
+	tempdword &= ~SERR_INTR_RSVDZ_MASK;
+	shpc_writel(ctrl, SERR_INTR_ENABLE, tempdword);
+	tempdword = shpc_readl(ctrl, SERR_INTR_ENABLE);
+	ctrl_dbg(ctrl, "SERR_INTR_ENABLE = %x\n", tempdword);
+
+	/* Mask the MRL sensor SERR Mask of individual slot in
+	 * Slot SERR-INT Mask & clear all the existing event if any
+	 */
+	for (hp_slot = 0; hp_slot < ctrl->num_slots; hp_slot++) {
+		slot_reg = shpc_readl(ctrl, SLOT_REG(hp_slot));
+		ctrl_dbg(ctrl, "Default Logical Slot Register %d value %x\n",
+			 hp_slot, slot_reg);
+		slot_reg |= (PRSNT_CHANGE_INTR_MASK | ISO_PFAULT_INTR_MASK |
+			     BUTTON_PRESS_INTR_MASK | MRL_CHANGE_INTR_MASK |
+			     CON_PFAULT_INTR_MASK   | MRL_CHANGE_SERR_MASK |
+			     CON_PFAULT_SERR_MASK);
+		slot_reg &= ~SLOT_REG_RSVDZ_MASK;
+		shpc_writel(ctrl, SLOT_REG(hp_slot), slot_reg);
+	}
+
+	if (shpchp_poll_mode) {
+		/* Install interrupt polling timer. Start with 10 sec delay */
+		init_timer(&ctrl->poll_timer);
+		start_int_poll_timer(ctrl, 10);
+	} else {
+		/* Installs the interrupt handler */
+		rc = pci_enable_msi(pdev);
+		if (rc) {
+			ctrl_info(ctrl,
+				  "Can't get msi for the hotplug controller\n");
+			ctrl_info(ctrl,
+				  "Use INTx for the hotplug controller\n");
+		}
+
+		rc = request_irq(ctrl->pci_dev->irq, shpc_isr, IRQF_SHARED,
+				 MY_NAME, (void *)ctrl);
+		ctrl_dbg(ctrl, "request_irq %d (returns %d)\n",
+			 ctrl->pci_dev->irq, rc);
+		if (rc) {
+			ctrl_err(ctrl, "Can't get irq %d for the hotplug "
+				 "controller\n", ctrl->pci_dev->irq);
+			goto abort_iounmap;
+		}
+	}
+	ctrl_dbg(ctrl, "HPC at %s irq=%x\n", pci_name(pdev), pdev->irq);
+
+	shpc_get_max_bus_speed(ctrl);
+	shpc_get_cur_bus_speed(ctrl);
+
+	/*
+	 * Unmask all event interrupts of all slots
+	 */
+	for (hp_slot = 0; hp_slot < ctrl->num_slots; hp_slot++) {
+		slot_reg = shpc_readl(ctrl, SLOT_REG(hp_slot));
+		ctrl_dbg(ctrl, "Default Logical Slot Register %d value %x\n",
+			 hp_slot, slot_reg);
+		slot_reg &= ~(PRSNT_CHANGE_INTR_MASK | ISO_PFAULT_INTR_MASK |
+			      BUTTON_PRESS_INTR_MASK | MRL_CHANGE_INTR_MASK |
+			      CON_PFAULT_INTR_MASK | SLOT_REG_RSVDZ_MASK);
+		shpc_writel(ctrl, SLOT_REG(hp_slot), slot_reg);
+	}
+	if (!shpchp_poll_mode) {
+		/* Unmask all general input interrupts and SERR */
+		tempdword = shpc_readl(ctrl, SERR_INTR_ENABLE);
+		tempdword &= ~(GLOBAL_INTR_MASK | COMMAND_INTR_MASK |
+			       SERR_INTR_RSVDZ_MASK);
+		shpc_writel(ctrl, SERR_INTR_ENABLE, tempdword);
+		tempdword = shpc_readl(ctrl, SERR_INTR_ENABLE);
+		ctrl_dbg(ctrl, "SERR_INTR_ENABLE = %x\n", tempdword);
+	}
+
+	return 0;
+
+	/* We end up here for the many possible ways to fail this API.  */
+abort_iounmap:
+	iounmap(ctrl->creg);
+abort:
+	return rc;
+}
diff --git a/drivers/pci/hotplug/shpchp_pci.c b/drivers/pci/hotplug/shpchp_pci.c
new file mode 100644
index 00000000..a2ccfcd3
--- /dev/null
+++ b/drivers/pci/hotplug/shpchp_pci.c
@@ -0,0 +1,132 @@
+/*
+ * Standard Hot Plug Controller Driver
+ *
+ * Copyright (C) 1995,2001 Compaq Computer Corporation
+ * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (C) 2001 IBM Corp.
+ * Copyright (C) 2003-2004 Intel Corporation
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>, <kristen.c.accardi@intel.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include "../pci.h"
+#include "shpchp.h"
+
+int __ref shpchp_configure_device(struct slot *p_slot)
+{
+	struct pci_dev *dev;
+	struct pci_bus *parent = p_slot->ctrl->pci_dev->subordinate;
+	int num, fn;
+	struct controller *ctrl = p_slot->ctrl;
+
+	dev = pci_get_slot(parent, PCI_DEVFN(p_slot->device, 0));
+	if (dev) {
+		ctrl_err(ctrl, "Device %s already exists "
+			 "at %04x:%02x:%02x, cannot hot-add\n", pci_name(dev),
+			 pci_domain_nr(parent), p_slot->bus, p_slot->device);
+		pci_dev_put(dev);
+		return -EINVAL;
+	}
+
+	num = pci_scan_slot(parent, PCI_DEVFN(p_slot->device, 0));
+	if (num == 0) {
+		ctrl_err(ctrl, "No new device found\n");
+		return -ENODEV;
+	}
+
+	for (fn = 0; fn < 8; fn++) {
+		dev = pci_get_slot(parent, PCI_DEVFN(p_slot->device, fn));
+		if (!dev)
+			continue;
+		if ((dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) ||
+				(dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)) {
+			/* Find an unused bus number for the new bridge */
+			struct pci_bus *child;
+			unsigned char busnr, start = parent->secondary;
+			unsigned char end = parent->subordinate;
+			for (busnr = start; busnr <= end; busnr++) {
+				if (!pci_find_bus(pci_domain_nr(parent),
+							busnr))
+					break;
+			}
+			if (busnr > end) {
+				ctrl_err(ctrl,
+					 "No free bus for hot-added bridge\n");
+				pci_dev_put(dev);
+				continue;
+			}
+			child = pci_add_new_bus(parent, dev, busnr);
+			if (!child) {
+				ctrl_err(ctrl, "Cannot add new bus for %s\n",
+					 pci_name(dev));
+				pci_dev_put(dev);
+				continue;
+			}
+			child->subordinate = pci_do_scan_bus(child);
+			pci_bus_size_bridges(child);
+		}
+		pci_configure_slot(dev);
+		pci_dev_put(dev);
+	}
+
+	pci_bus_assign_resources(parent);
+	pci_bus_add_devices(parent);
+	pci_enable_bridges(parent);
+	return 0;
+}
+
+int shpchp_unconfigure_device(struct slot *p_slot)
+{
+	int rc = 0;
+	int j;
+	u8 bctl = 0;
+	struct pci_bus *parent = p_slot->ctrl->pci_dev->subordinate;
+	struct controller *ctrl = p_slot->ctrl;
+
+	ctrl_dbg(ctrl, "%s: domain:bus:dev = %04x:%02x:%02x\n",
+		 __func__, pci_domain_nr(parent), p_slot->bus, p_slot->device);
+
+	for (j = 0; j < 8 ; j++) {
+		struct pci_dev *temp = pci_get_slot(parent,
+				(p_slot->device << 3) | j);
+		if (!temp)
+			continue;
+		if (temp->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
+			pci_read_config_byte(temp, PCI_BRIDGE_CONTROL, &bctl);
+			if (bctl & PCI_BRIDGE_CTL_VGA) {
+				ctrl_err(ctrl,
+					 "Cannot remove display device %s\n",
+					 pci_name(temp));
+				pci_dev_put(temp);
+				rc = -EINVAL;
+				break;
+			}
+		}
+		pci_remove_bus_device(temp);
+		pci_dev_put(temp);
+	}
+	return rc;
+}
+
diff --git a/drivers/pci/hotplug/shpchp_sysfs.c b/drivers/pci/hotplug/shpchp_sysfs.c
new file mode 100644
index 00000000..071b7dc0
--- /dev/null
+++ b/drivers/pci/hotplug/shpchp_sysfs.c
@@ -0,0 +1,99 @@
+/*
+ * Compaq Hot Plug Controller Driver
+ *
+ * Copyright (c) 1995,2001 Compaq Computer Corporation
+ * Copyright (c) 2001,2003 Greg Kroah-Hartman (greg@kroah.com)
+ * Copyright (c) 2001 IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <greg@kroah.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include "shpchp.h"
+
+
+/* A few routines that create sysfs entries for the hot plug controller */
+
+static ssize_t show_ctrl (struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct pci_dev *pdev;
+	char * out = buf;
+	int index, busnr;
+	struct resource *res;
+	struct pci_bus *bus;
+
+	pdev = container_of (dev, struct pci_dev, dev);
+	bus = pdev->subordinate;
+
+	out += sprintf(buf, "Free resources: memory\n");
+	pci_bus_for_each_resource(bus, res, index) {
+		if (res && (res->flags & IORESOURCE_MEM) &&
+				!(res->flags & IORESOURCE_PREFETCH)) {
+			out += sprintf(out, "start = %8.8llx, "
+					"length = %8.8llx\n",
+					(unsigned long long)res->start,
+					(unsigned long long)(res->end - res->start));
+		}
+	}
+	out += sprintf(out, "Free resources: prefetchable memory\n");
+	pci_bus_for_each_resource(bus, res, index) {
+		if (res && (res->flags & IORESOURCE_MEM) &&
+			       (res->flags & IORESOURCE_PREFETCH)) {
+			out += sprintf(out, "start = %8.8llx, "
+					"length = %8.8llx\n",
+					(unsigned long long)res->start,
+					(unsigned long long)(res->end - res->start));
+		}
+	}
+	out += sprintf(out, "Free resources: IO\n");
+	pci_bus_for_each_resource(bus, res, index) {
+		if (res && (res->flags & IORESOURCE_IO)) {
+			out += sprintf(out, "start = %8.8llx, "
+					"length = %8.8llx\n",
+					(unsigned long long)res->start,
+					(unsigned long long)(res->end - res->start));
+		}
+	}
+	out += sprintf(out, "Free resources: bus numbers\n");
+	for (busnr = bus->secondary; busnr <= bus->subordinate; busnr++) {
+		if (!pci_find_bus(pci_domain_nr(bus), busnr))
+			break;
+	}
+	if (busnr < bus->subordinate)
+		out += sprintf(out, "start = %8.8x, length = %8.8x\n",
+				busnr, (bus->subordinate - busnr));
+
+	return out - buf;
+}
+static DEVICE_ATTR (ctrl, S_IRUGO, show_ctrl, NULL);
+
+int __must_check shpchp_create_ctrl_files (struct controller *ctrl)
+{
+	return device_create_file (&ctrl->pci_dev->dev, &dev_attr_ctrl);
+}
+
+void shpchp_remove_ctrl_files(struct controller *ctrl)
+{
+	device_remove_file(&ctrl->pci_dev->dev, &dev_attr_ctrl);
+}
diff --git a/drivers/pci/htirq.c b/drivers/pci/htirq.c
new file mode 100644
index 00000000..db057b6f
--- /dev/null
+++ b/drivers/pci/htirq.c
@@ -0,0 +1,175 @@
+/*
+ * File:	htirq.c
+ * Purpose:	Hypertransport Interrupt Capability
+ *
+ * Copyright (C) 2006 Linux Networx
+ * Copyright (C) Eric Biederman <ebiederman@lnxi.com>
+ */
+
+#include <linux/irq.h>
+#include <linux/pci.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/htirq.h>
+
+/* Global ht irq lock.
+ *
+ * This is needed to serialize access to the data port in hypertransport
+ * irq capability.
+ *
+ * With multiple simultaneous hypertransport irq devices it might pay
+ * to make this more fine grained.  But start with simple, stupid, and correct.
+ */
+static DEFINE_SPINLOCK(ht_irq_lock);
+
+struct ht_irq_cfg {
+	struct pci_dev *dev;
+	 /* Update callback used to cope with buggy hardware */
+	ht_irq_update_t *update;
+	unsigned pos;
+	unsigned idx;
+	struct ht_irq_msg msg;
+};
+
+
+void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg)
+{
+	struct ht_irq_cfg *cfg = irq_get_handler_data(irq);
+	unsigned long flags;
+	spin_lock_irqsave(&ht_irq_lock, flags);
+	if (cfg->msg.address_lo != msg->address_lo) {
+		pci_write_config_byte(cfg->dev, cfg->pos + 2, cfg->idx);
+		pci_write_config_dword(cfg->dev, cfg->pos + 4, msg->address_lo);
+	}
+	if (cfg->msg.address_hi != msg->address_hi) {
+		pci_write_config_byte(cfg->dev, cfg->pos + 2, cfg->idx + 1);
+		pci_write_config_dword(cfg->dev, cfg->pos + 4, msg->address_hi);
+	}
+	if (cfg->update)
+		cfg->update(cfg->dev, irq, msg);
+	spin_unlock_irqrestore(&ht_irq_lock, flags);
+	cfg->msg = *msg;
+}
+
+void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg)
+{
+	struct ht_irq_cfg *cfg = irq_get_handler_data(irq);
+	*msg = cfg->msg;
+}
+
+void mask_ht_irq(struct irq_data *data)
+{
+	struct ht_irq_cfg *cfg = irq_data_get_irq_handler_data(data);
+	struct ht_irq_msg msg = cfg->msg;
+
+	msg.address_lo |= 1;
+	write_ht_irq_msg(data->irq, &msg);
+}
+
+void unmask_ht_irq(struct irq_data *data)
+{
+	struct ht_irq_cfg *cfg = irq_data_get_irq_handler_data(data);
+	struct ht_irq_msg msg = cfg->msg;
+
+	msg.address_lo &= ~1;
+	write_ht_irq_msg(data->irq, &msg);
+}
+
+/**
+ * __ht_create_irq - create an irq and attach it to a device.
+ * @dev: The hypertransport device to find the irq capability on.
+ * @idx: Which of the possible irqs to attach to.
+ * @update: Function to be called when changing the htirq message
+ *
+ * The irq number of the new irq or a negative error value is returned.
+ */
+int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
+{
+	struct ht_irq_cfg *cfg;
+	unsigned long flags;
+	u32 data;
+	int max_irq;
+	int pos;
+	int irq;
+	int node;
+
+	pos = pci_find_ht_capability(dev, HT_CAPTYPE_IRQ);
+	if (!pos)
+		return -EINVAL;
+
+	/* Verify the idx I want to use is in range */
+	spin_lock_irqsave(&ht_irq_lock, flags);
+	pci_write_config_byte(dev, pos + 2, 1);
+	pci_read_config_dword(dev, pos + 4, &data);
+	spin_unlock_irqrestore(&ht_irq_lock, flags);
+
+	max_irq = (data >> 16) & 0xff;
+	if ( idx > max_irq)
+		return -EINVAL;
+
+	cfg = kmalloc(sizeof(*cfg), GFP_KERNEL);
+	if (!cfg)
+		return -ENOMEM;
+
+	cfg->dev = dev;
+	cfg->update = update;
+	cfg->pos = pos;
+	cfg->idx = 0x10 + (idx * 2);
+	/* Initialize msg to a value that will never match the first write. */
+	cfg->msg.address_lo = 0xffffffff;
+	cfg->msg.address_hi = 0xffffffff;
+
+	node = dev_to_node(&dev->dev);
+	irq = create_irq_nr(0, node);
+
+	if (irq <= 0) {
+		kfree(cfg);
+		return -EBUSY;
+	}
+	irq_set_handler_data(irq, cfg);
+
+	if (arch_setup_ht_irq(irq, dev) < 0) {
+		ht_destroy_irq(irq);
+		return -EBUSY;
+	}
+
+	return irq;
+}
+
+/**
+ * ht_create_irq - create an irq and attach it to a device.
+ * @dev: The hypertransport device to find the irq capability on.
+ * @idx: Which of the possible irqs to attach to.
+ *
+ * ht_create_irq needs to be called for all hypertransport devices
+ * that generate irqs.
+ *
+ * The irq number of the new irq or a negative error value is returned.
+ */
+int ht_create_irq(struct pci_dev *dev, int idx)
+{
+	return __ht_create_irq(dev, idx, NULL);
+}
+
+/**
+ * ht_destroy_irq - destroy an irq created with ht_create_irq
+ * @irq: irq to be destroyed
+ *
+ * This reverses ht_create_irq removing the specified irq from
+ * existence.  The irq should be free before this happens.
+ */
+void ht_destroy_irq(unsigned int irq)
+{
+	struct ht_irq_cfg *cfg;
+
+	cfg = irq_get_handler_data(irq);
+	irq_set_chip(irq, NULL);
+	irq_set_handler_data(irq, NULL);
+	destroy_irq(irq);
+
+	kfree(cfg);
+}
+
+EXPORT_SYMBOL(__ht_create_irq);
+EXPORT_SYMBOL(ht_create_irq);
+EXPORT_SYMBOL(ht_destroy_irq);
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
new file mode 100644
index 00000000..0ec8930f
--- /dev/null
+++ b/drivers/pci/intel-iommu.c
@@ -0,0 +1,4023 @@
+/*
+ * Copyright (c) 2006, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Copyright (C) 2006-2008 Intel Corporation
+ * Author: Ashok Raj <ashok.raj@intel.com>
+ * Author: Shaohua Li <shaohua.li@intel.com>
+ * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
+ * Author: Fenghua Yu <fenghua.yu@intel.com>
+ */
+
+#include <linux/init.h>
+#include <linux/bitmap.h>
+#include <linux/debugfs.h>
+#include <linux/slab.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/dmar.h>
+#include <linux/dma-mapping.h>
+#include <linux/mempool.h>
+#include <linux/timer.h>
+#include <linux/iova.h>
+#include <linux/iommu.h>
+#include <linux/intel-iommu.h>
+#include <linux/syscore_ops.h>
+#include <linux/tboot.h>
+#include <linux/dmi.h>
+#include <linux/pci-ats.h>
+#include <asm/cacheflush.h>
+#include <asm/iommu.h>
+#include "pci.h"
+
+#define ROOT_SIZE		VTD_PAGE_SIZE
+#define CONTEXT_SIZE		VTD_PAGE_SIZE
+
+#define IS_BRIDGE_HOST_DEVICE(pdev) \
+			    ((pdev->class >> 8) == PCI_CLASS_BRIDGE_HOST)
+#define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY)
+#define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA)
+#define IS_AZALIA(pdev) ((pdev)->vendor == 0x8086 && (pdev)->device == 0x3a3e)
+
+#define IOAPIC_RANGE_START	(0xfee00000)
+#define IOAPIC_RANGE_END	(0xfeefffff)
+#define IOVA_START_ADDR		(0x1000)
+
+#define DEFAULT_DOMAIN_ADDRESS_WIDTH 48
+
+#define MAX_AGAW_WIDTH 64
+
+#define __DOMAIN_MAX_PFN(gaw)  ((((uint64_t)1) << (gaw-VTD_PAGE_SHIFT)) - 1)
+#define __DOMAIN_MAX_ADDR(gaw) ((((uint64_t)1) << gaw) - 1)
+
+/* We limit DOMAIN_MAX_PFN to fit in an unsigned long, and DOMAIN_MAX_ADDR
+   to match. That way, we can use 'unsigned long' for PFNs with impunity. */
+#define DOMAIN_MAX_PFN(gaw)	((unsigned long) min_t(uint64_t, \
+				__DOMAIN_MAX_PFN(gaw), (unsigned long)-1))
+#define DOMAIN_MAX_ADDR(gaw)	(((uint64_t)__DOMAIN_MAX_PFN(gaw)) << VTD_PAGE_SHIFT)
+
+#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
+#define DMA_32BIT_PFN		IOVA_PFN(DMA_BIT_MASK(32))
+#define DMA_64BIT_PFN		IOVA_PFN(DMA_BIT_MASK(64))
+
+/* page table handling */
+#define LEVEL_STRIDE		(9)
+#define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)
+
+static inline int agaw_to_level(int agaw)
+{
+	return agaw + 2;
+}
+
+static inline int agaw_to_width(int agaw)
+{
+	return 30 + agaw * LEVEL_STRIDE;
+}
+
+static inline int width_to_agaw(int width)
+{
+	return (width - 30) / LEVEL_STRIDE;
+}
+
+static inline unsigned int level_to_offset_bits(int level)
+{
+	return (level - 1) * LEVEL_STRIDE;
+}
+
+static inline int pfn_level_offset(unsigned long pfn, int level)
+{
+	return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK;
+}
+
+static inline unsigned long level_mask(int level)
+{
+	return -1UL << level_to_offset_bits(level);
+}
+
+static inline unsigned long level_size(int level)
+{
+	return 1UL << level_to_offset_bits(level);
+}
+
+static inline unsigned long align_to_level(unsigned long pfn, int level)
+{
+	return (pfn + level_size(level) - 1) & level_mask(level);
+}
+
+static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
+{
+	return  1 << ((lvl - 1) * LEVEL_STRIDE);
+}
+
+/* VT-d pages must always be _smaller_ than MM pages. Otherwise things
+   are never going to work. */
+static inline unsigned long dma_to_mm_pfn(unsigned long dma_pfn)
+{
+	return dma_pfn >> (PAGE_SHIFT - VTD_PAGE_SHIFT);
+}
+
+static inline unsigned long mm_to_dma_pfn(unsigned long mm_pfn)
+{
+	return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT);
+}
+static inline unsigned long page_to_dma_pfn(struct page *pg)
+{
+	return mm_to_dma_pfn(page_to_pfn(pg));
+}
+static inline unsigned long virt_to_dma_pfn(void *p)
+{
+	return page_to_dma_pfn(virt_to_page(p));
+}
+
+/* global iommu list, set NULL for ignored DMAR units */
+static struct intel_iommu **g_iommus;
+
+static void __init check_tylersburg_isoch(void);
+static int rwbf_quirk;
+
+/*
+ * set to 1 to panic kernel if can't successfully enable VT-d
+ * (used when kernel is launched w/ TXT)
+ */
+static int force_on = 0;
+
+/*
+ * 0: Present
+ * 1-11: Reserved
+ * 12-63: Context Ptr (12 - (haw-1))
+ * 64-127: Reserved
+ */
+struct root_entry {
+	u64	val;
+	u64	rsvd1;
+};
+#define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry))
+static inline bool root_present(struct root_entry *root)
+{
+	return (root->val & 1);
+}
+static inline void set_root_present(struct root_entry *root)
+{
+	root->val |= 1;
+}
+static inline void set_root_value(struct root_entry *root, unsigned long value)
+{
+	root->val |= value & VTD_PAGE_MASK;
+}
+
+static inline struct context_entry *
+get_context_addr_from_root(struct root_entry *root)
+{
+	return (struct context_entry *)
+		(root_present(root)?phys_to_virt(
+		root->val & VTD_PAGE_MASK) :
+		NULL);
+}
+
+/*
+ * low 64 bits:
+ * 0: present
+ * 1: fault processing disable
+ * 2-3: translation type
+ * 12-63: address space root
+ * high 64 bits:
+ * 0-2: address width
+ * 3-6: aval
+ * 8-23: domain id
+ */
+struct context_entry {
+	u64 lo;
+	u64 hi;
+};
+
+static inline bool context_present(struct context_entry *context)
+{
+	return (context->lo & 1);
+}
+static inline void context_set_present(struct context_entry *context)
+{
+	context->lo |= 1;
+}
+
+static inline void context_set_fault_enable(struct context_entry *context)
+{
+	context->lo &= (((u64)-1) << 2) | 1;
+}
+
+static inline void context_set_translation_type(struct context_entry *context,
+						unsigned long value)
+{
+	context->lo &= (((u64)-1) << 4) | 3;
+	context->lo |= (value & 3) << 2;
+}
+
+static inline void context_set_address_root(struct context_entry *context,
+					    unsigned long value)
+{
+	context->lo |= value & VTD_PAGE_MASK;
+}
+
+static inline void context_set_address_width(struct context_entry *context,
+					     unsigned long value)
+{
+	context->hi |= value & 7;
+}
+
+static inline void context_set_domain_id(struct context_entry *context,
+					 unsigned long value)
+{
+	context->hi |= (value & ((1 << 16) - 1)) << 8;
+}
+
+static inline void context_clear_entry(struct context_entry *context)
+{
+	context->lo = 0;
+	context->hi = 0;
+}
+
+/*
+ * 0: readable
+ * 1: writable
+ * 2-6: reserved
+ * 7: super page
+ * 8-10: available
+ * 11: snoop behavior
+ * 12-63: Host physcial address
+ */
+struct dma_pte {
+	u64 val;
+};
+
+static inline void dma_clear_pte(struct dma_pte *pte)
+{
+	pte->val = 0;
+}
+
+static inline void dma_set_pte_readable(struct dma_pte *pte)
+{
+	pte->val |= DMA_PTE_READ;
+}
+
+static inline void dma_set_pte_writable(struct dma_pte *pte)
+{
+	pte->val |= DMA_PTE_WRITE;
+}
+
+static inline void dma_set_pte_snp(struct dma_pte *pte)
+{
+	pte->val |= DMA_PTE_SNP;
+}
+
+static inline void dma_set_pte_prot(struct dma_pte *pte, unsigned long prot)
+{
+	pte->val = (pte->val & ~3) | (prot & 3);
+}
+
+static inline u64 dma_pte_addr(struct dma_pte *pte)
+{
+#ifdef CONFIG_64BIT
+	return pte->val & VTD_PAGE_MASK;
+#else
+	/* Must have a full atomic 64-bit read */
+	return  __cmpxchg64(&pte->val, 0ULL, 0ULL) & VTD_PAGE_MASK;
+#endif
+}
+
+static inline void dma_set_pte_pfn(struct dma_pte *pte, unsigned long pfn)
+{
+	pte->val |= (uint64_t)pfn << VTD_PAGE_SHIFT;
+}
+
+static inline bool dma_pte_present(struct dma_pte *pte)
+{
+	return (pte->val & 3) != 0;
+}
+
+static inline bool dma_pte_superpage(struct dma_pte *pte)
+{
+	return (pte->val & (1 << 7));
+}
+
+static inline int first_pte_in_page(struct dma_pte *pte)
+{
+	return !((unsigned long)pte & ~VTD_PAGE_MASK);
+}
+
+/*
+ * This domain is a statically identity mapping domain.
+ *	1. This domain creats a static 1:1 mapping to all usable memory.
+ * 	2. It maps to each iommu if successful.
+ *	3. Each iommu mapps to this domain if successful.
+ */
+static struct dmar_domain *si_domain;
+static int hw_pass_through = 1;
+
+/* devices under the same p2p bridge are owned in one domain */
+#define DOMAIN_FLAG_P2P_MULTIPLE_DEVICES (1 << 0)
+
+/* domain represents a virtual machine, more than one devices
+ * across iommus may be owned in one domain, e.g. kvm guest.
+ */
+#define DOMAIN_FLAG_VIRTUAL_MACHINE	(1 << 1)
+
+/* si_domain contains mulitple devices */
+#define DOMAIN_FLAG_STATIC_IDENTITY	(1 << 2)
+
+struct dmar_domain {
+	int	id;			/* domain id */
+	int	nid;			/* node id */
+	unsigned long iommu_bmp;	/* bitmap of iommus this domain uses*/
+
+	struct list_head devices; 	/* all devices' list */
+	struct iova_domain iovad;	/* iova's that belong to this domain */
+
+	struct dma_pte	*pgd;		/* virtual address */
+	int		gaw;		/* max guest address width */
+
+	/* adjusted guest address width, 0 is level 2 30-bit */
+	int		agaw;
+
+	int		flags;		/* flags to find out type of domain */
+
+	int		iommu_coherency;/* indicate coherency of iommu access */
+	int		iommu_snooping; /* indicate snooping control feature*/
+	int		iommu_count;	/* reference count of iommu */
+	int		iommu_superpage;/* Level of superpages supported:
+					   0 == 4KiB (no superpages), 1 == 2MiB,
+					   2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
+	spinlock_t	iommu_lock;	/* protect iommu set in domain */
+	u64		max_addr;	/* maximum mapped address */
+};
+
+/* PCI domain-device relationship */
+struct device_domain_info {
+	struct list_head link;	/* link to domain siblings */
+	struct list_head global; /* link to global list */
+	int segment;		/* PCI domain */
+	u8 bus;			/* PCI bus number */
+	u8 devfn;		/* PCI devfn number */
+	struct pci_dev *dev; /* it's NULL for PCIe-to-PCI bridge */
+	struct intel_iommu *iommu; /* IOMMU used by this device */
+	struct dmar_domain *domain; /* pointer to domain */
+};
+
+static void flush_unmaps_timeout(unsigned long data);
+
+DEFINE_TIMER(unmap_timer,  flush_unmaps_timeout, 0, 0);
+
+#define HIGH_WATER_MARK 250
+struct deferred_flush_tables {
+	int next;
+	struct iova *iova[HIGH_WATER_MARK];
+	struct dmar_domain *domain[HIGH_WATER_MARK];
+};
+
+static struct deferred_flush_tables *deferred_flush;
+
+/* bitmap for indexing intel_iommus */
+static int g_num_of_iommus;
+
+static DEFINE_SPINLOCK(async_umap_flush_lock);
+static LIST_HEAD(unmaps_to_do);
+
+static int timer_on;
+static long list_size;
+
+static void domain_remove_dev_info(struct dmar_domain *domain);
+
+#ifdef CONFIG_DMAR_DEFAULT_ON
+int dmar_disabled = 0;
+#else
+int dmar_disabled = 1;
+#endif /*CONFIG_DMAR_DEFAULT_ON*/
+
+static int dmar_map_gfx = 1;
+static int dmar_forcedac;
+static int intel_iommu_strict;
+static int intel_iommu_superpage = 1;
+
+#define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1))
+static DEFINE_SPINLOCK(device_domain_lock);
+static LIST_HEAD(device_domain_list);
+
+static struct iommu_ops intel_iommu_ops;
+
+static int __init intel_iommu_setup(char *str)
+{
+	if (!str)
+		return -EINVAL;
+	while (*str) {
+		if (!strncmp(str, "on", 2)) {
+			dmar_disabled = 0;
+			printk(KERN_INFO "Intel-IOMMU: enabled\n");
+		} else if (!strncmp(str, "off", 3)) {
+			dmar_disabled = 1;
+			printk(KERN_INFO "Intel-IOMMU: disabled\n");
+		} else if (!strncmp(str, "igfx_off", 8)) {
+			dmar_map_gfx = 0;
+			printk(KERN_INFO
+				"Intel-IOMMU: disable GFX device mapping\n");
+		} else if (!strncmp(str, "forcedac", 8)) {
+			printk(KERN_INFO
+				"Intel-IOMMU: Forcing DAC for PCI devices\n");
+			dmar_forcedac = 1;
+		} else if (!strncmp(str, "strict", 6)) {
+			printk(KERN_INFO
+				"Intel-IOMMU: disable batched IOTLB flush\n");
+			intel_iommu_strict = 1;
+		} else if (!strncmp(str, "sp_off", 6)) {
+			printk(KERN_INFO
+				"Intel-IOMMU: disable supported super page\n");
+			intel_iommu_superpage = 0;
+		}
+
+		str += strcspn(str, ",");
+		while (*str == ',')
+			str++;
+	}
+	return 0;
+}
+__setup("intel_iommu=", intel_iommu_setup);
+
+static struct kmem_cache *iommu_domain_cache;
+static struct kmem_cache *iommu_devinfo_cache;
+static struct kmem_cache *iommu_iova_cache;
+
+static inline void *alloc_pgtable_page(int node)
+{
+	struct page *page;
+	void *vaddr = NULL;
+
+	page = alloc_pages_node(node, GFP_ATOMIC | __GFP_ZERO, 0);
+	if (page)
+		vaddr = page_address(page);
+	return vaddr;
+}
+
+static inline void free_pgtable_page(void *vaddr)
+{
+	free_page((unsigned long)vaddr);
+}
+
+static inline void *alloc_domain_mem(void)
+{
+	return kmem_cache_alloc(iommu_domain_cache, GFP_ATOMIC);
+}
+
+static void free_domain_mem(void *vaddr)
+{
+	kmem_cache_free(iommu_domain_cache, vaddr);
+}
+
+static inline void * alloc_devinfo_mem(void)
+{
+	return kmem_cache_alloc(iommu_devinfo_cache, GFP_ATOMIC);
+}
+
+static inline void free_devinfo_mem(void *vaddr)
+{
+	kmem_cache_free(iommu_devinfo_cache, vaddr);
+}
+
+struct iova *alloc_iova_mem(void)
+{
+	return kmem_cache_alloc(iommu_iova_cache, GFP_ATOMIC);
+}
+
+void free_iova_mem(struct iova *iova)
+{
+	kmem_cache_free(iommu_iova_cache, iova);
+}
+
+
+static int __iommu_calculate_agaw(struct intel_iommu *iommu, int max_gaw)
+{
+	unsigned long sagaw;
+	int agaw = -1;
+
+	sagaw = cap_sagaw(iommu->cap);
+	for (agaw = width_to_agaw(max_gaw);
+	     agaw >= 0; agaw--) {
+		if (test_bit(agaw, &sagaw))
+			break;
+	}
+
+	return agaw;
+}
+
+/*
+ * Calculate max SAGAW for each iommu.
+ */
+int iommu_calculate_max_sagaw(struct intel_iommu *iommu)
+{
+	return __iommu_calculate_agaw(iommu, MAX_AGAW_WIDTH);
+}
+
+/*
+ * calculate agaw for each iommu.
+ * "SAGAW" may be different across iommus, use a default agaw, and
+ * get a supported less agaw for iommus that don't support the default agaw.
+ */
+int iommu_calculate_agaw(struct intel_iommu *iommu)
+{
+	return __iommu_calculate_agaw(iommu, DEFAULT_DOMAIN_ADDRESS_WIDTH);
+}
+
+/* This functionin only returns single iommu in a domain */
+static struct intel_iommu *domain_get_iommu(struct dmar_domain *domain)
+{
+	int iommu_id;
+
+	/* si_domain and vm domain should not get here. */
+	BUG_ON(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE);
+	BUG_ON(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY);
+
+	iommu_id = find_first_bit(&domain->iommu_bmp, g_num_of_iommus);
+	if (iommu_id < 0 || iommu_id >= g_num_of_iommus)
+		return NULL;
+
+	return g_iommus[iommu_id];
+}
+
+static void domain_update_iommu_coherency(struct dmar_domain *domain)
+{
+	int i;
+
+	domain->iommu_coherency = 1;
+
+	for_each_set_bit(i, &domain->iommu_bmp, g_num_of_iommus) {
+		if (!ecap_coherent(g_iommus[i]->ecap)) {
+			domain->iommu_coherency = 0;
+			break;
+		}
+	}
+}
+
+static void domain_update_iommu_snooping(struct dmar_domain *domain)
+{
+	int i;
+
+	domain->iommu_snooping = 1;
+
+	for_each_set_bit(i, &domain->iommu_bmp, g_num_of_iommus) {
+		if (!ecap_sc_support(g_iommus[i]->ecap)) {
+			domain->iommu_snooping = 0;
+			break;
+		}
+	}
+}
+
+static void domain_update_iommu_superpage(struct dmar_domain *domain)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+	int mask = 0xf;
+
+	if (!intel_iommu_superpage) {
+		domain->iommu_superpage = 0;
+		return;
+	}
+
+	/* set iommu_superpage to the smallest common denominator */
+	for_each_active_iommu(iommu, drhd) {
+		mask &= cap_super_page_val(iommu->cap);
+		if (!mask) {
+			break;
+		}
+	}
+	domain->iommu_superpage = fls(mask);
+}
+
+/* Some capabilities may be different across iommus */
+static void domain_update_iommu_cap(struct dmar_domain *domain)
+{
+	domain_update_iommu_coherency(domain);
+	domain_update_iommu_snooping(domain);
+	domain_update_iommu_superpage(domain);
+}
+
+static struct intel_iommu *device_to_iommu(int segment, u8 bus, u8 devfn)
+{
+	struct dmar_drhd_unit *drhd = NULL;
+	int i;
+
+	for_each_drhd_unit(drhd) {
+		if (drhd->ignored)
+			continue;
+		if (segment != drhd->segment)
+			continue;
+
+		for (i = 0; i < drhd->devices_cnt; i++) {
+			if (drhd->devices[i] &&
+			    drhd->devices[i]->bus->number == bus &&
+			    drhd->devices[i]->devfn == devfn)
+				return drhd->iommu;
+			if (drhd->devices[i] &&
+			    drhd->devices[i]->subordinate &&
+			    drhd->devices[i]->subordinate->number <= bus &&
+			    drhd->devices[i]->subordinate->subordinate >= bus)
+				return drhd->iommu;
+		}
+
+		if (drhd->include_all)
+			return drhd->iommu;
+	}
+
+	return NULL;
+}
+
+static void domain_flush_cache(struct dmar_domain *domain,
+			       void *addr, int size)
+{
+	if (!domain->iommu_coherency)
+		clflush_cache_range(addr, size);
+}
+
+/* Gets context entry for a given bus and devfn */
+static struct context_entry * device_to_context_entry(struct intel_iommu *iommu,
+		u8 bus, u8 devfn)
+{
+	struct root_entry *root;
+	struct context_entry *context;
+	unsigned long phy_addr;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	root = &iommu->root_entry[bus];
+	context = get_context_addr_from_root(root);
+	if (!context) {
+		context = (struct context_entry *)
+				alloc_pgtable_page(iommu->node);
+		if (!context) {
+			spin_unlock_irqrestore(&iommu->lock, flags);
+			return NULL;
+		}
+		__iommu_flush_cache(iommu, (void *)context, CONTEXT_SIZE);
+		phy_addr = virt_to_phys((void *)context);
+		set_root_value(root, phy_addr);
+		set_root_present(root);
+		__iommu_flush_cache(iommu, root, sizeof(*root));
+	}
+	spin_unlock_irqrestore(&iommu->lock, flags);
+	return &context[devfn];
+}
+
+static int device_context_mapped(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	struct root_entry *root;
+	struct context_entry *context;
+	int ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	root = &iommu->root_entry[bus];
+	context = get_context_addr_from_root(root);
+	if (!context) {
+		ret = 0;
+		goto out;
+	}
+	ret = context_present(&context[devfn]);
+out:
+	spin_unlock_irqrestore(&iommu->lock, flags);
+	return ret;
+}
+
+static void clear_context_table(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	struct root_entry *root;
+	struct context_entry *context;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	root = &iommu->root_entry[bus];
+	context = get_context_addr_from_root(root);
+	if (context) {
+		context_clear_entry(&context[devfn]);
+		__iommu_flush_cache(iommu, &context[devfn], \
+			sizeof(*context));
+	}
+	spin_unlock_irqrestore(&iommu->lock, flags);
+}
+
+static void free_context_table(struct intel_iommu *iommu)
+{
+	struct root_entry *root;
+	int i;
+	unsigned long flags;
+	struct context_entry *context;
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	if (!iommu->root_entry) {
+		goto out;
+	}
+	for (i = 0; i < ROOT_ENTRY_NR; i++) {
+		root = &iommu->root_entry[i];
+		context = get_context_addr_from_root(root);
+		if (context)
+			free_pgtable_page(context);
+	}
+	free_pgtable_page(iommu->root_entry);
+	iommu->root_entry = NULL;
+out:
+	spin_unlock_irqrestore(&iommu->lock, flags);
+}
+
+static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
+				      unsigned long pfn, int target_level)
+{
+	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
+	struct dma_pte *parent, *pte = NULL;
+	int level = agaw_to_level(domain->agaw);
+	int offset;
+
+	BUG_ON(!domain->pgd);
+	BUG_ON(addr_width < BITS_PER_LONG && pfn >> addr_width);
+	parent = domain->pgd;
+
+	while (level > 0) {
+		void *tmp_page;
+
+		offset = pfn_level_offset(pfn, level);
+		pte = &parent[offset];
+		if (!target_level && (dma_pte_superpage(pte) || !dma_pte_present(pte)))
+			break;
+		if (level == target_level)
+			break;
+
+		if (!dma_pte_present(pte)) {
+			uint64_t pteval;
+
+			tmp_page = alloc_pgtable_page(domain->nid);
+
+			if (!tmp_page)
+				return NULL;
+
+			domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE);
+			pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE;
+			if (cmpxchg64(&pte->val, 0ULL, pteval)) {
+				/* Someone else set it while we were thinking; use theirs. */
+				free_pgtable_page(tmp_page);
+			} else {
+				dma_pte_addr(pte);
+				domain_flush_cache(domain, pte, sizeof(*pte));
+			}
+		}
+		parent = phys_to_virt(dma_pte_addr(pte));
+		level--;
+	}
+
+	return pte;
+}
+
+
+/* return address's pte at specific level */
+static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain,
+					 unsigned long pfn,
+					 int level, int *large_page)
+{
+	struct dma_pte *parent, *pte = NULL;
+	int total = agaw_to_level(domain->agaw);
+	int offset;
+
+	parent = domain->pgd;
+	while (level <= total) {
+		offset = pfn_level_offset(pfn, total);
+		pte = &parent[offset];
+		if (level == total)
+			return pte;
+
+		if (!dma_pte_present(pte)) {
+			*large_page = total;
+			break;
+		}
+
+		if (pte->val & DMA_PTE_LARGE_PAGE) {
+			*large_page = total;
+			return pte;
+		}
+
+		parent = phys_to_virt(dma_pte_addr(pte));
+		total--;
+	}
+	return NULL;
+}
+
+/* clear last level pte, a tlb flush should be followed */
+static int dma_pte_clear_range(struct dmar_domain *domain,
+				unsigned long start_pfn,
+				unsigned long last_pfn)
+{
+	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
+	unsigned int large_page = 1;
+	struct dma_pte *first_pte, *pte;
+	int order;
+
+	BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width);
+	BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width);
+	BUG_ON(start_pfn > last_pfn);
+
+	/* we don't need lock here; nobody else touches the iova range */
+	do {
+		large_page = 1;
+		first_pte = pte = dma_pfn_level_pte(domain, start_pfn, 1, &large_page);
+		if (!pte) {
+			start_pfn = align_to_level(start_pfn + 1, large_page + 1);
+			continue;
+		}
+		do {
+			dma_clear_pte(pte);
+			start_pfn += lvl_to_nr_pages(large_page);
+			pte++;
+		} while (start_pfn <= last_pfn && !first_pte_in_page(pte));
+
+		domain_flush_cache(domain, first_pte,
+				   (void *)pte - (void *)first_pte);
+
+	} while (start_pfn && start_pfn <= last_pfn);
+
+	order = (large_page - 1) * 9;
+	return order;
+}
+
+/* free page table pages. last level pte should already be cleared */
+static void dma_pte_free_pagetable(struct dmar_domain *domain,
+				   unsigned long start_pfn,
+				   unsigned long last_pfn)
+{
+	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
+	struct dma_pte *first_pte, *pte;
+	int total = agaw_to_level(domain->agaw);
+	int level;
+	unsigned long tmp;
+	int large_page = 2;
+
+	BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width);
+	BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width);
+	BUG_ON(start_pfn > last_pfn);
+
+	/* We don't need lock here; nobody else touches the iova range */
+	level = 2;
+	while (level <= total) {
+		tmp = align_to_level(start_pfn, level);
+
+		/* If we can't even clear one PTE at this level, we're done */
+		if (tmp + level_size(level) - 1 > last_pfn)
+			return;
+
+		do {
+			large_page = level;
+			first_pte = pte = dma_pfn_level_pte(domain, tmp, level, &large_page);
+			if (large_page > level)
+				level = large_page + 1;
+			if (!pte) {
+				tmp = align_to_level(tmp + 1, level + 1);
+				continue;
+			}
+			do {
+				if (dma_pte_present(pte)) {
+					free_pgtable_page(phys_to_virt(dma_pte_addr(pte)));
+					dma_clear_pte(pte);
+				}
+				pte++;
+				tmp += level_size(level);
+			} while (!first_pte_in_page(pte) &&
+				 tmp + level_size(level) - 1 <= last_pfn);
+
+			domain_flush_cache(domain, first_pte,
+					   (void *)pte - (void *)first_pte);
+			
+		} while (tmp && tmp + level_size(level) - 1 <= last_pfn);
+		level++;
+	}
+	/* free pgd */
+	if (start_pfn == 0 && last_pfn == DOMAIN_MAX_PFN(domain->gaw)) {
+		free_pgtable_page(domain->pgd);
+		domain->pgd = NULL;
+	}
+}
+
+/* iommu handling */
+static int iommu_alloc_root_entry(struct intel_iommu *iommu)
+{
+	struct root_entry *root;
+	unsigned long flags;
+
+	root = (struct root_entry *)alloc_pgtable_page(iommu->node);
+	if (!root)
+		return -ENOMEM;
+
+	__iommu_flush_cache(iommu, root, ROOT_SIZE);
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	iommu->root_entry = root;
+	spin_unlock_irqrestore(&iommu->lock, flags);
+
+	return 0;
+}
+
+static void iommu_set_root_entry(struct intel_iommu *iommu)
+{
+	void *addr;
+	u32 sts;
+	unsigned long flag;
+
+	addr = iommu->root_entry;
+
+	spin_lock_irqsave(&iommu->register_lock, flag);
+	dmar_writeq(iommu->reg + DMAR_RTADDR_REG, virt_to_phys(addr));
+
+	writel(iommu->gcmd | DMA_GCMD_SRTP, iommu->reg + DMAR_GCMD_REG);
+
+	/* Make sure hardware complete it */
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, (sts & DMA_GSTS_RTPS), sts);
+
+	spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+static void iommu_flush_write_buffer(struct intel_iommu *iommu)
+{
+	u32 val;
+	unsigned long flag;
+
+	if (!rwbf_quirk && !cap_rwbf(iommu->cap))
+		return;
+
+	spin_lock_irqsave(&iommu->register_lock, flag);
+	writel(iommu->gcmd | DMA_GCMD_WBF, iommu->reg + DMAR_GCMD_REG);
+
+	/* Make sure hardware complete it */
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, (!(val & DMA_GSTS_WBFS)), val);
+
+	spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+/* return value determine if we need a write buffer flush */
+static void __iommu_flush_context(struct intel_iommu *iommu,
+				  u16 did, u16 source_id, u8 function_mask,
+				  u64 type)
+{
+	u64 val = 0;
+	unsigned long flag;
+
+	switch (type) {
+	case DMA_CCMD_GLOBAL_INVL:
+		val = DMA_CCMD_GLOBAL_INVL;
+		break;
+	case DMA_CCMD_DOMAIN_INVL:
+		val = DMA_CCMD_DOMAIN_INVL|DMA_CCMD_DID(did);
+		break;
+	case DMA_CCMD_DEVICE_INVL:
+		val = DMA_CCMD_DEVICE_INVL|DMA_CCMD_DID(did)
+			| DMA_CCMD_SID(source_id) | DMA_CCMD_FM(function_mask);
+		break;
+	default:
+		BUG();
+	}
+	val |= DMA_CCMD_ICC;
+
+	spin_lock_irqsave(&iommu->register_lock, flag);
+	dmar_writeq(iommu->reg + DMAR_CCMD_REG, val);
+
+	/* Make sure hardware complete it */
+	IOMMU_WAIT_OP(iommu, DMAR_CCMD_REG,
+		dmar_readq, (!(val & DMA_CCMD_ICC)), val);
+
+	spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+/* return value determine if we need a write buffer flush */
+static void __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did,
+				u64 addr, unsigned int size_order, u64 type)
+{
+	int tlb_offset = ecap_iotlb_offset(iommu->ecap);
+	u64 val = 0, val_iva = 0;
+	unsigned long flag;
+
+	switch (type) {
+	case DMA_TLB_GLOBAL_FLUSH:
+		/* global flush doesn't need set IVA_REG */
+		val = DMA_TLB_GLOBAL_FLUSH|DMA_TLB_IVT;
+		break;
+	case DMA_TLB_DSI_FLUSH:
+		val = DMA_TLB_DSI_FLUSH|DMA_TLB_IVT|DMA_TLB_DID(did);
+		break;
+	case DMA_TLB_PSI_FLUSH:
+		val = DMA_TLB_PSI_FLUSH|DMA_TLB_IVT|DMA_TLB_DID(did);
+		/* Note: always flush non-leaf currently */
+		val_iva = size_order | addr;
+		break;
+	default:
+		BUG();
+	}
+	/* Note: set drain read/write */
+#if 0
+	/*
+	 * This is probably to be super secure.. Looks like we can
+	 * ignore it without any impact.
+	 */
+	if (cap_read_drain(iommu->cap))
+		val |= DMA_TLB_READ_DRAIN;
+#endif
+	if (cap_write_drain(iommu->cap))
+		val |= DMA_TLB_WRITE_DRAIN;
+
+	spin_lock_irqsave(&iommu->register_lock, flag);
+	/* Note: Only uses first TLB reg currently */
+	if (val_iva)
+		dmar_writeq(iommu->reg + tlb_offset, val_iva);
+	dmar_writeq(iommu->reg + tlb_offset + 8, val);
+
+	/* Make sure hardware complete it */
+	IOMMU_WAIT_OP(iommu, tlb_offset + 8,
+		dmar_readq, (!(val & DMA_TLB_IVT)), val);
+
+	spin_unlock_irqrestore(&iommu->register_lock, flag);
+
+	/* check IOTLB invalidation granularity */
+	if (DMA_TLB_IAIG(val) == 0)
+		printk(KERN_ERR"IOMMU: flush IOTLB failed\n");
+	if (DMA_TLB_IAIG(val) != DMA_TLB_IIRG(type))
+		pr_debug("IOMMU: tlb flush request %Lx, actual %Lx\n",
+			(unsigned long long)DMA_TLB_IIRG(type),
+			(unsigned long long)DMA_TLB_IAIG(val));
+}
+
+static struct device_domain_info *iommu_support_dev_iotlb(
+	struct dmar_domain *domain, int segment, u8 bus, u8 devfn)
+{
+	int found = 0;
+	unsigned long flags;
+	struct device_domain_info *info;
+	struct intel_iommu *iommu = device_to_iommu(segment, bus, devfn);
+
+	if (!ecap_dev_iotlb_support(iommu->ecap))
+		return NULL;
+
+	if (!iommu->qi)
+		return NULL;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	list_for_each_entry(info, &domain->devices, link)
+		if (info->bus == bus && info->devfn == devfn) {
+			found = 1;
+			break;
+		}
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	if (!found || !info->dev)
+		return NULL;
+
+	if (!pci_find_ext_capability(info->dev, PCI_EXT_CAP_ID_ATS))
+		return NULL;
+
+	if (!dmar_find_matched_atsr_unit(info->dev))
+		return NULL;
+
+	info->iommu = iommu;
+
+	return info;
+}
+
+static void iommu_enable_dev_iotlb(struct device_domain_info *info)
+{
+	if (!info)
+		return;
+
+	pci_enable_ats(info->dev, VTD_PAGE_SHIFT);
+}
+
+static void iommu_disable_dev_iotlb(struct device_domain_info *info)
+{
+	if (!info->dev || !pci_ats_enabled(info->dev))
+		return;
+
+	pci_disable_ats(info->dev);
+}
+
+static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
+				  u64 addr, unsigned mask)
+{
+	u16 sid, qdep;
+	unsigned long flags;
+	struct device_domain_info *info;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	list_for_each_entry(info, &domain->devices, link) {
+		if (!info->dev || !pci_ats_enabled(info->dev))
+			continue;
+
+		sid = info->bus << 8 | info->devfn;
+		qdep = pci_ats_queue_depth(info->dev);
+		qi_flush_dev_iotlb(info->iommu, sid, qdep, addr, mask);
+	}
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+}
+
+static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
+				  unsigned long pfn, unsigned int pages, int map)
+{
+	unsigned int mask = ilog2(__roundup_pow_of_two(pages));
+	uint64_t addr = (uint64_t)pfn << VTD_PAGE_SHIFT;
+
+	BUG_ON(pages == 0);
+
+	/*
+	 * Fallback to domain selective flush if no PSI support or the size is
+	 * too big.
+	 * PSI requires page size to be 2 ^ x, and the base address is naturally
+	 * aligned to the size
+	 */
+	if (!cap_pgsel_inv(iommu->cap) || mask > cap_max_amask_val(iommu->cap))
+		iommu->flush.flush_iotlb(iommu, did, 0, 0,
+						DMA_TLB_DSI_FLUSH);
+	else
+		iommu->flush.flush_iotlb(iommu, did, addr, mask,
+						DMA_TLB_PSI_FLUSH);
+
+	/*
+	 * In caching mode, changes of pages from non-present to present require
+	 * flush. However, device IOTLB doesn't need to be flushed in this case.
+	 */
+	if (!cap_caching_mode(iommu->cap) || !map)
+		iommu_flush_dev_iotlb(iommu->domains[did], addr, mask);
+}
+
+static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu)
+{
+	u32 pmen;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iommu->register_lock, flags);
+	pmen = readl(iommu->reg + DMAR_PMEN_REG);
+	pmen &= ~DMA_PMEN_EPM;
+	writel(pmen, iommu->reg + DMAR_PMEN_REG);
+
+	/* wait for the protected region status bit to clear */
+	IOMMU_WAIT_OP(iommu, DMAR_PMEN_REG,
+		readl, !(pmen & DMA_PMEN_PRS), pmen);
+
+	spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
+static int iommu_enable_translation(struct intel_iommu *iommu)
+{
+	u32 sts;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iommu->register_lock, flags);
+	iommu->gcmd |= DMA_GCMD_TE;
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	/* Make sure hardware complete it */
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, (sts & DMA_GSTS_TES), sts);
+
+	spin_unlock_irqrestore(&iommu->register_lock, flags);
+	return 0;
+}
+
+static int iommu_disable_translation(struct intel_iommu *iommu)
+{
+	u32 sts;
+	unsigned long flag;
+
+	spin_lock_irqsave(&iommu->register_lock, flag);
+	iommu->gcmd &= ~DMA_GCMD_TE;
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	/* Make sure hardware complete it */
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, (!(sts & DMA_GSTS_TES)), sts);
+
+	spin_unlock_irqrestore(&iommu->register_lock, flag);
+	return 0;
+}
+
+
+static int iommu_init_domains(struct intel_iommu *iommu)
+{
+	unsigned long ndomains;
+	unsigned long nlongs;
+
+	ndomains = cap_ndoms(iommu->cap);
+	pr_debug("IOMMU %d: Number of Domains supportd <%ld>\n", iommu->seq_id,
+			ndomains);
+	nlongs = BITS_TO_LONGS(ndomains);
+
+	spin_lock_init(&iommu->lock);
+
+	/* TBD: there might be 64K domains,
+	 * consider other allocation for future chip
+	 */
+	iommu->domain_ids = kcalloc(nlongs, sizeof(unsigned long), GFP_KERNEL);
+	if (!iommu->domain_ids) {
+		printk(KERN_ERR "Allocating domain id array failed\n");
+		return -ENOMEM;
+	}
+	iommu->domains = kcalloc(ndomains, sizeof(struct dmar_domain *),
+			GFP_KERNEL);
+	if (!iommu->domains) {
+		printk(KERN_ERR "Allocating domain array failed\n");
+		return -ENOMEM;
+	}
+
+	/*
+	 * if Caching mode is set, then invalid translations are tagged
+	 * with domainid 0. Hence we need to pre-allocate it.
+	 */
+	if (cap_caching_mode(iommu->cap))
+		set_bit(0, iommu->domain_ids);
+	return 0;
+}
+
+
+static void domain_exit(struct dmar_domain *domain);
+static void vm_domain_exit(struct dmar_domain *domain);
+
+void free_dmar_iommu(struct intel_iommu *iommu)
+{
+	struct dmar_domain *domain;
+	int i;
+	unsigned long flags;
+
+	if ((iommu->domains) && (iommu->domain_ids)) {
+		for_each_set_bit(i, iommu->domain_ids, cap_ndoms(iommu->cap)) {
+			domain = iommu->domains[i];
+			clear_bit(i, iommu->domain_ids);
+
+			spin_lock_irqsave(&domain->iommu_lock, flags);
+			if (--domain->iommu_count == 0) {
+				if (domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE)
+					vm_domain_exit(domain);
+				else
+					domain_exit(domain);
+			}
+			spin_unlock_irqrestore(&domain->iommu_lock, flags);
+		}
+	}
+
+	if (iommu->gcmd & DMA_GCMD_TE)
+		iommu_disable_translation(iommu);
+
+	if (iommu->irq) {
+		irq_set_handler_data(iommu->irq, NULL);
+		/* This will mask the irq */
+		free_irq(iommu->irq, iommu);
+		destroy_irq(iommu->irq);
+	}
+
+	kfree(iommu->domains);
+	kfree(iommu->domain_ids);
+
+	g_iommus[iommu->seq_id] = NULL;
+
+	/* if all iommus are freed, free g_iommus */
+	for (i = 0; i < g_num_of_iommus; i++) {
+		if (g_iommus[i])
+			break;
+	}
+
+	if (i == g_num_of_iommus)
+		kfree(g_iommus);
+
+	/* free context mapping */
+	free_context_table(iommu);
+}
+
+static struct dmar_domain *alloc_domain(void)
+{
+	struct dmar_domain *domain;
+
+	domain = alloc_domain_mem();
+	if (!domain)
+		return NULL;
+
+	domain->nid = -1;
+	memset(&domain->iommu_bmp, 0, sizeof(unsigned long));
+	domain->flags = 0;
+
+	return domain;
+}
+
+static int iommu_attach_domain(struct dmar_domain *domain,
+			       struct intel_iommu *iommu)
+{
+	int num;
+	unsigned long ndomains;
+	unsigned long flags;
+
+	ndomains = cap_ndoms(iommu->cap);
+
+	spin_lock_irqsave(&iommu->lock, flags);
+
+	num = find_first_zero_bit(iommu->domain_ids, ndomains);
+	if (num >= ndomains) {
+		spin_unlock_irqrestore(&iommu->lock, flags);
+		printk(KERN_ERR "IOMMU: no free domain ids\n");
+		return -ENOMEM;
+	}
+
+	domain->id = num;
+	set_bit(num, iommu->domain_ids);
+	set_bit(iommu->seq_id, &domain->iommu_bmp);
+	iommu->domains[num] = domain;
+	spin_unlock_irqrestore(&iommu->lock, flags);
+
+	return 0;
+}
+
+static void iommu_detach_domain(struct dmar_domain *domain,
+				struct intel_iommu *iommu)
+{
+	unsigned long flags;
+	int num, ndomains;
+	int found = 0;
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	ndomains = cap_ndoms(iommu->cap);
+	for_each_set_bit(num, iommu->domain_ids, ndomains) {
+		if (iommu->domains[num] == domain) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (found) {
+		clear_bit(num, iommu->domain_ids);
+		clear_bit(iommu->seq_id, &domain->iommu_bmp);
+		iommu->domains[num] = NULL;
+	}
+	spin_unlock_irqrestore(&iommu->lock, flags);
+}
+
+static struct iova_domain reserved_iova_list;
+static struct lock_class_key reserved_rbtree_key;
+
+static int dmar_init_reserved_ranges(void)
+{
+	struct pci_dev *pdev = NULL;
+	struct iova *iova;
+	int i;
+
+	init_iova_domain(&reserved_iova_list, DMA_32BIT_PFN);
+
+	lockdep_set_class(&reserved_iova_list.iova_rbtree_lock,
+		&reserved_rbtree_key);
+
+	/* IOAPIC ranges shouldn't be accessed by DMA */
+	iova = reserve_iova(&reserved_iova_list, IOVA_PFN(IOAPIC_RANGE_START),
+		IOVA_PFN(IOAPIC_RANGE_END));
+	if (!iova) {
+		printk(KERN_ERR "Reserve IOAPIC range failed\n");
+		return -ENODEV;
+	}
+
+	/* Reserve all PCI MMIO to avoid peer-to-peer access */
+	for_each_pci_dev(pdev) {
+		struct resource *r;
+
+		for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+			r = &pdev->resource[i];
+			if (!r->flags || !(r->flags & IORESOURCE_MEM))
+				continue;
+			iova = reserve_iova(&reserved_iova_list,
+					    IOVA_PFN(r->start),
+					    IOVA_PFN(r->end));
+			if (!iova) {
+				printk(KERN_ERR "Reserve iova failed\n");
+				return -ENODEV;
+			}
+		}
+	}
+	return 0;
+}
+
+static void domain_reserve_special_ranges(struct dmar_domain *domain)
+{
+	copy_reserved_iova(&reserved_iova_list, &domain->iovad);
+}
+
+static inline int guestwidth_to_adjustwidth(int gaw)
+{
+	int agaw;
+	int r = (gaw - 12) % 9;
+
+	if (r == 0)
+		agaw = gaw;
+	else
+		agaw = gaw + 9 - r;
+	if (agaw > 64)
+		agaw = 64;
+	return agaw;
+}
+
+static int domain_init(struct dmar_domain *domain, int guest_width)
+{
+	struct intel_iommu *iommu;
+	int adjust_width, agaw;
+	unsigned long sagaw;
+
+	init_iova_domain(&domain->iovad, DMA_32BIT_PFN);
+	spin_lock_init(&domain->iommu_lock);
+
+	domain_reserve_special_ranges(domain);
+
+	/* calculate AGAW */
+	iommu = domain_get_iommu(domain);
+	if (guest_width > cap_mgaw(iommu->cap))
+		guest_width = cap_mgaw(iommu->cap);
+	domain->gaw = guest_width;
+	adjust_width = guestwidth_to_adjustwidth(guest_width);
+	agaw = width_to_agaw(adjust_width);
+	sagaw = cap_sagaw(iommu->cap);
+	if (!test_bit(agaw, &sagaw)) {
+		/* hardware doesn't support it, choose a bigger one */
+		pr_debug("IOMMU: hardware doesn't support agaw %d\n", agaw);
+		agaw = find_next_bit(&sagaw, 5, agaw);
+		if (agaw >= 5)
+			return -ENODEV;
+	}
+	domain->agaw = agaw;
+	INIT_LIST_HEAD(&domain->devices);
+
+	if (ecap_coherent(iommu->ecap))
+		domain->iommu_coherency = 1;
+	else
+		domain->iommu_coherency = 0;
+
+	if (ecap_sc_support(iommu->ecap))
+		domain->iommu_snooping = 1;
+	else
+		domain->iommu_snooping = 0;
+
+	domain->iommu_superpage = fls(cap_super_page_val(iommu->cap));
+	domain->iommu_count = 1;
+	domain->nid = iommu->node;
+
+	/* always allocate the top pgd */
+	domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid);
+	if (!domain->pgd)
+		return -ENOMEM;
+	__iommu_flush_cache(iommu, domain->pgd, PAGE_SIZE);
+	return 0;
+}
+
+static void domain_exit(struct dmar_domain *domain)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+
+	/* Domain 0 is reserved, so dont process it */
+	if (!domain)
+		return;
+
+	/* Flush any lazy unmaps that may reference this domain */
+	if (!intel_iommu_strict)
+		flush_unmaps_timeout(0);
+
+	domain_remove_dev_info(domain);
+	/* destroy iovas */
+	put_iova_domain(&domain->iovad);
+
+	/* clear ptes */
+	dma_pte_clear_range(domain, 0, DOMAIN_MAX_PFN(domain->gaw));
+
+	/* free page tables */
+	dma_pte_free_pagetable(domain, 0, DOMAIN_MAX_PFN(domain->gaw));
+
+	for_each_active_iommu(iommu, drhd)
+		if (test_bit(iommu->seq_id, &domain->iommu_bmp))
+			iommu_detach_domain(domain, iommu);
+
+	free_domain_mem(domain);
+}
+
+static int domain_context_mapping_one(struct dmar_domain *domain, int segment,
+				 u8 bus, u8 devfn, int translation)
+{
+	struct context_entry *context;
+	unsigned long flags;
+	struct intel_iommu *iommu;
+	struct dma_pte *pgd;
+	unsigned long num;
+	unsigned long ndomains;
+	int id;
+	int agaw;
+	struct device_domain_info *info = NULL;
+
+	pr_debug("Set context mapping for %02x:%02x.%d\n",
+		bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
+
+	BUG_ON(!domain->pgd);
+	BUG_ON(translation != CONTEXT_TT_PASS_THROUGH &&
+	       translation != CONTEXT_TT_MULTI_LEVEL);
+
+	iommu = device_to_iommu(segment, bus, devfn);
+	if (!iommu)
+		return -ENODEV;
+
+	context = device_to_context_entry(iommu, bus, devfn);
+	if (!context)
+		return -ENOMEM;
+	spin_lock_irqsave(&iommu->lock, flags);
+	if (context_present(context)) {
+		spin_unlock_irqrestore(&iommu->lock, flags);
+		return 0;
+	}
+
+	id = domain->id;
+	pgd = domain->pgd;
+
+	if (domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE ||
+	    domain->flags & DOMAIN_FLAG_STATIC_IDENTITY) {
+		int found = 0;
+
+		/* find an available domain id for this device in iommu */
+		ndomains = cap_ndoms(iommu->cap);
+		for_each_set_bit(num, iommu->domain_ids, ndomains) {
+			if (iommu->domains[num] == domain) {
+				id = num;
+				found = 1;
+				break;
+			}
+		}
+
+		if (found == 0) {
+			num = find_first_zero_bit(iommu->domain_ids, ndomains);
+			if (num >= ndomains) {
+				spin_unlock_irqrestore(&iommu->lock, flags);
+				printk(KERN_ERR "IOMMU: no free domain ids\n");
+				return -EFAULT;
+			}
+
+			set_bit(num, iommu->domain_ids);
+			iommu->domains[num] = domain;
+			id = num;
+		}
+
+		/* Skip top levels of page tables for
+		 * iommu which has less agaw than default.
+		 * Unnecessary for PT mode.
+		 */
+		if (translation != CONTEXT_TT_PASS_THROUGH) {
+			for (agaw = domain->agaw; agaw != iommu->agaw; agaw--) {
+				pgd = phys_to_virt(dma_pte_addr(pgd));
+				if (!dma_pte_present(pgd)) {
+					spin_unlock_irqrestore(&iommu->lock, flags);
+					return -ENOMEM;
+				}
+			}
+		}
+	}
+
+	context_set_domain_id(context, id);
+
+	if (translation != CONTEXT_TT_PASS_THROUGH) {
+		info = iommu_support_dev_iotlb(domain, segment, bus, devfn);
+		translation = info ? CONTEXT_TT_DEV_IOTLB :
+				     CONTEXT_TT_MULTI_LEVEL;
+	}
+	/*
+	 * In pass through mode, AW must be programmed to indicate the largest
+	 * AGAW value supported by hardware. And ASR is ignored by hardware.
+	 */
+	if (unlikely(translation == CONTEXT_TT_PASS_THROUGH))
+		context_set_address_width(context, iommu->msagaw);
+	else {
+		context_set_address_root(context, virt_to_phys(pgd));
+		context_set_address_width(context, iommu->agaw);
+	}
+
+	context_set_translation_type(context, translation);
+	context_set_fault_enable(context);
+	context_set_present(context);
+	domain_flush_cache(domain, context, sizeof(*context));
+
+	/*
+	 * It's a non-present to present mapping. If hardware doesn't cache
+	 * non-present entry we only need to flush the write-buffer. If the
+	 * _does_ cache non-present entries, then it does so in the special
+	 * domain #0, which we have to flush:
+	 */
+	if (cap_caching_mode(iommu->cap)) {
+		iommu->flush.flush_context(iommu, 0,
+					   (((u16)bus) << 8) | devfn,
+					   DMA_CCMD_MASK_NOBIT,
+					   DMA_CCMD_DEVICE_INVL);
+		iommu->flush.flush_iotlb(iommu, domain->id, 0, 0, DMA_TLB_DSI_FLUSH);
+	} else {
+		iommu_flush_write_buffer(iommu);
+	}
+	iommu_enable_dev_iotlb(info);
+	spin_unlock_irqrestore(&iommu->lock, flags);
+
+	spin_lock_irqsave(&domain->iommu_lock, flags);
+	if (!test_and_set_bit(iommu->seq_id, &domain->iommu_bmp)) {
+		domain->iommu_count++;
+		if (domain->iommu_count == 1)
+			domain->nid = iommu->node;
+		domain_update_iommu_cap(domain);
+	}
+	spin_unlock_irqrestore(&domain->iommu_lock, flags);
+	return 0;
+}
+
+static int
+domain_context_mapping(struct dmar_domain *domain, struct pci_dev *pdev,
+			int translation)
+{
+	int ret;
+	struct pci_dev *tmp, *parent;
+
+	ret = domain_context_mapping_one(domain, pci_domain_nr(pdev->bus),
+					 pdev->bus->number, pdev->devfn,
+					 translation);
+	if (ret)
+		return ret;
+
+	/* dependent device mapping */
+	tmp = pci_find_upstream_pcie_bridge(pdev);
+	if (!tmp)
+		return 0;
+	/* Secondary interface's bus number and devfn 0 */
+	parent = pdev->bus->self;
+	while (parent != tmp) {
+		ret = domain_context_mapping_one(domain,
+						 pci_domain_nr(parent->bus),
+						 parent->bus->number,
+						 parent->devfn, translation);
+		if (ret)
+			return ret;
+		parent = parent->bus->self;
+	}
+	if (pci_is_pcie(tmp)) /* this is a PCIe-to-PCI bridge */
+		return domain_context_mapping_one(domain,
+					pci_domain_nr(tmp->subordinate),
+					tmp->subordinate->number, 0,
+					translation);
+	else /* this is a legacy PCI bridge */
+		return domain_context_mapping_one(domain,
+						  pci_domain_nr(tmp->bus),
+						  tmp->bus->number,
+						  tmp->devfn,
+						  translation);
+}
+
+static int domain_context_mapped(struct pci_dev *pdev)
+{
+	int ret;
+	struct pci_dev *tmp, *parent;
+	struct intel_iommu *iommu;
+
+	iommu = device_to_iommu(pci_domain_nr(pdev->bus), pdev->bus->number,
+				pdev->devfn);
+	if (!iommu)
+		return -ENODEV;
+
+	ret = device_context_mapped(iommu, pdev->bus->number, pdev->devfn);
+	if (!ret)
+		return ret;
+	/* dependent device mapping */
+	tmp = pci_find_upstream_pcie_bridge(pdev);
+	if (!tmp)
+		return ret;
+	/* Secondary interface's bus number and devfn 0 */
+	parent = pdev->bus->self;
+	while (parent != tmp) {
+		ret = device_context_mapped(iommu, parent->bus->number,
+					    parent->devfn);
+		if (!ret)
+			return ret;
+		parent = parent->bus->self;
+	}
+	if (pci_is_pcie(tmp))
+		return device_context_mapped(iommu, tmp->subordinate->number,
+					     0);
+	else
+		return device_context_mapped(iommu, tmp->bus->number,
+					     tmp->devfn);
+}
+
+/* Returns a number of VTD pages, but aligned to MM page size */
+static inline unsigned long aligned_nrpages(unsigned long host_addr,
+					    size_t size)
+{
+	host_addr &= ~PAGE_MASK;
+	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
+}
+
+/* Return largest possible superpage level for a given mapping */
+static inline int hardware_largepage_caps(struct dmar_domain *domain,
+					  unsigned long iov_pfn,
+					  unsigned long phy_pfn,
+					  unsigned long pages)
+{
+	int support, level = 1;
+	unsigned long pfnmerge;
+
+	support = domain->iommu_superpage;
+
+	/* To use a large page, the virtual *and* physical addresses
+	   must be aligned to 2MiB/1GiB/etc. Lower bits set in either
+	   of them will mean we have to use smaller pages. So just
+	   merge them and check both at once. */
+	pfnmerge = iov_pfn | phy_pfn;
+
+	while (support && !(pfnmerge & ~VTD_STRIDE_MASK)) {
+		pages >>= VTD_STRIDE_SHIFT;
+		if (!pages)
+			break;
+		pfnmerge >>= VTD_STRIDE_SHIFT;
+		level++;
+		support--;
+	}
+	return level;
+}
+
+static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
+			    struct scatterlist *sg, unsigned long phys_pfn,
+			    unsigned long nr_pages, int prot)
+{
+	struct dma_pte *first_pte = NULL, *pte = NULL;
+	phys_addr_t uninitialized_var(pteval);
+	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
+	unsigned long sg_res;
+	unsigned int largepage_lvl = 0;
+	unsigned long lvl_pages = 0;
+
+	BUG_ON(addr_width < BITS_PER_LONG && (iov_pfn + nr_pages - 1) >> addr_width);
+
+	if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0)
+		return -EINVAL;
+
+	prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP;
+
+	if (sg)
+		sg_res = 0;
+	else {
+		sg_res = nr_pages + 1;
+		pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
+	}
+
+	while (nr_pages > 0) {
+		uint64_t tmp;
+
+		if (!sg_res) {
+			sg_res = aligned_nrpages(sg->offset, sg->length);
+			sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + sg->offset;
+			sg->dma_length = sg->length;
+			pteval = page_to_phys(sg_page(sg)) | prot;
+			phys_pfn = pteval >> VTD_PAGE_SHIFT;
+		}
+
+		if (!pte) {
+			largepage_lvl = hardware_largepage_caps(domain, iov_pfn, phys_pfn, sg_res);
+
+			first_pte = pte = pfn_to_dma_pte(domain, iov_pfn, largepage_lvl);
+			if (!pte)
+				return -ENOMEM;
+			/* It is large page*/
+			if (largepage_lvl > 1)
+				pteval |= DMA_PTE_LARGE_PAGE;
+			else
+				pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE;
+
+		}
+		/* We don't need lock here, nobody else
+		 * touches the iova range
+		 */
+		tmp = cmpxchg64_local(&pte->val, 0ULL, pteval);
+		if (tmp) {
+			static int dumps = 5;
+			printk(KERN_CRIT "ERROR: DMA PTE for vPFN 0x%lx already set (to %llx not %llx)\n",
+			       iov_pfn, tmp, (unsigned long long)pteval);
+			if (dumps) {
+				dumps--;
+				debug_dma_dump_mappings(NULL);
+			}
+			WARN_ON(1);
+		}
+
+		lvl_pages = lvl_to_nr_pages(largepage_lvl);
+
+		BUG_ON(nr_pages < lvl_pages);
+		BUG_ON(sg_res < lvl_pages);
+
+		nr_pages -= lvl_pages;
+		iov_pfn += lvl_pages;
+		phys_pfn += lvl_pages;
+		pteval += lvl_pages * VTD_PAGE_SIZE;
+		sg_res -= lvl_pages;
+
+		/* If the next PTE would be the first in a new page, then we
+		   need to flush the cache on the entries we've just written.
+		   And then we'll need to recalculate 'pte', so clear it and
+		   let it get set again in the if (!pte) block above.
+
+		   If we're done (!nr_pages) we need to flush the cache too.
+
+		   Also if we've been setting superpages, we may need to
+		   recalculate 'pte' and switch back to smaller pages for the
+		   end of the mapping, if the trailing size is not enough to
+		   use another superpage (i.e. sg_res < lvl_pages). */
+		pte++;
+		if (!nr_pages || first_pte_in_page(pte) ||
+		    (largepage_lvl > 1 && sg_res < lvl_pages)) {
+			domain_flush_cache(domain, first_pte,
+					   (void *)pte - (void *)first_pte);
+			pte = NULL;
+		}
+
+		if (!sg_res && nr_pages)
+			sg = sg_next(sg);
+	}
+	return 0;
+}
+
+static inline int domain_sg_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
+				    struct scatterlist *sg, unsigned long nr_pages,
+				    int prot)
+{
+	return __domain_mapping(domain, iov_pfn, sg, 0, nr_pages, prot);
+}
+
+static inline int domain_pfn_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
+				     unsigned long phys_pfn, unsigned long nr_pages,
+				     int prot)
+{
+	return __domain_mapping(domain, iov_pfn, NULL, phys_pfn, nr_pages, prot);
+}
+
+static void iommu_detach_dev(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	if (!iommu)
+		return;
+
+	clear_context_table(iommu, bus, devfn);
+	iommu->flush.flush_context(iommu, 0, 0, 0,
+					   DMA_CCMD_GLOBAL_INVL);
+	iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
+}
+
+static void domain_remove_dev_info(struct dmar_domain *domain)
+{
+	struct device_domain_info *info;
+	unsigned long flags;
+	struct intel_iommu *iommu;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	while (!list_empty(&domain->devices)) {
+		info = list_entry(domain->devices.next,
+			struct device_domain_info, link);
+		list_del(&info->link);
+		list_del(&info->global);
+		if (info->dev)
+			info->dev->dev.archdata.iommu = NULL;
+		spin_unlock_irqrestore(&device_domain_lock, flags);
+
+		iommu_disable_dev_iotlb(info);
+		iommu = device_to_iommu(info->segment, info->bus, info->devfn);
+		iommu_detach_dev(iommu, info->bus, info->devfn);
+		free_devinfo_mem(info);
+
+		spin_lock_irqsave(&device_domain_lock, flags);
+	}
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+}
+
+/*
+ * find_domain
+ * Note: we use struct pci_dev->dev.archdata.iommu stores the info
+ */
+static struct dmar_domain *
+find_domain(struct pci_dev *pdev)
+{
+	struct device_domain_info *info;
+
+	/* No lock here, assumes no domain exit in normal case */
+	info = pdev->dev.archdata.iommu;
+	if (info)
+		return info->domain;
+	return NULL;
+}
+
+/* domain is initialized */
+static struct dmar_domain *get_domain_for_dev(struct pci_dev *pdev, int gaw)
+{
+	struct dmar_domain *domain, *found = NULL;
+	struct intel_iommu *iommu;
+	struct dmar_drhd_unit *drhd;
+	struct device_domain_info *info, *tmp;
+	struct pci_dev *dev_tmp;
+	unsigned long flags;
+	int bus = 0, devfn = 0;
+	int segment;
+	int ret;
+
+	domain = find_domain(pdev);
+	if (domain)
+		return domain;
+
+	segment = pci_domain_nr(pdev->bus);
+
+	dev_tmp = pci_find_upstream_pcie_bridge(pdev);
+	if (dev_tmp) {
+		if (pci_is_pcie(dev_tmp)) {
+			bus = dev_tmp->subordinate->number;
+			devfn = 0;
+		} else {
+			bus = dev_tmp->bus->number;
+			devfn = dev_tmp->devfn;
+		}
+		spin_lock_irqsave(&device_domain_lock, flags);
+		list_for_each_entry(info, &device_domain_list, global) {
+			if (info->segment == segment &&
+			    info->bus == bus && info->devfn == devfn) {
+				found = info->domain;
+				break;
+			}
+		}
+		spin_unlock_irqrestore(&device_domain_lock, flags);
+		/* pcie-pci bridge already has a domain, uses it */
+		if (found) {
+			domain = found;
+			goto found_domain;
+		}
+	}
+
+	domain = alloc_domain();
+	if (!domain)
+		goto error;
+
+	/* Allocate new domain for the device */
+	drhd = dmar_find_matched_drhd_unit(pdev);
+	if (!drhd) {
+		printk(KERN_ERR "IOMMU: can't find DMAR for device %s\n",
+			pci_name(pdev));
+		return NULL;
+	}
+	iommu = drhd->iommu;
+
+	ret = iommu_attach_domain(domain, iommu);
+	if (ret) {
+		free_domain_mem(domain);
+		goto error;
+	}
+
+	if (domain_init(domain, gaw)) {
+		domain_exit(domain);
+		goto error;
+	}
+
+	/* register pcie-to-pci device */
+	if (dev_tmp) {
+		info = alloc_devinfo_mem();
+		if (!info) {
+			domain_exit(domain);
+			goto error;
+		}
+		info->segment = segment;
+		info->bus = bus;
+		info->devfn = devfn;
+		info->dev = NULL;
+		info->domain = domain;
+		/* This domain is shared by devices under p2p bridge */
+		domain->flags |= DOMAIN_FLAG_P2P_MULTIPLE_DEVICES;
+
+		/* pcie-to-pci bridge already has a domain, uses it */
+		found = NULL;
+		spin_lock_irqsave(&device_domain_lock, flags);
+		list_for_each_entry(tmp, &device_domain_list, global) {
+			if (tmp->segment == segment &&
+			    tmp->bus == bus && tmp->devfn == devfn) {
+				found = tmp->domain;
+				break;
+			}
+		}
+		if (found) {
+			spin_unlock_irqrestore(&device_domain_lock, flags);
+			free_devinfo_mem(info);
+			domain_exit(domain);
+			domain = found;
+		} else {
+			list_add(&info->link, &domain->devices);
+			list_add(&info->global, &device_domain_list);
+			spin_unlock_irqrestore(&device_domain_lock, flags);
+		}
+	}
+
+found_domain:
+	info = alloc_devinfo_mem();
+	if (!info)
+		goto error;
+	info->segment = segment;
+	info->bus = pdev->bus->number;
+	info->devfn = pdev->devfn;
+	info->dev = pdev;
+	info->domain = domain;
+	spin_lock_irqsave(&device_domain_lock, flags);
+	/* somebody is fast */
+	found = find_domain(pdev);
+	if (found != NULL) {
+		spin_unlock_irqrestore(&device_domain_lock, flags);
+		if (found != domain) {
+			domain_exit(domain);
+			domain = found;
+		}
+		free_devinfo_mem(info);
+		return domain;
+	}
+	list_add(&info->link, &domain->devices);
+	list_add(&info->global, &device_domain_list);
+	pdev->dev.archdata.iommu = info;
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+	return domain;
+error:
+	/* recheck it here, maybe others set it */
+	return find_domain(pdev);
+}
+
+static int iommu_identity_mapping;
+#define IDENTMAP_ALL		1
+#define IDENTMAP_GFX		2
+#define IDENTMAP_AZALIA		4
+
+static int iommu_domain_identity_map(struct dmar_domain *domain,
+				     unsigned long long start,
+				     unsigned long long end)
+{
+	unsigned long first_vpfn = start >> VTD_PAGE_SHIFT;
+	unsigned long last_vpfn = end >> VTD_PAGE_SHIFT;
+
+	if (!reserve_iova(&domain->iovad, dma_to_mm_pfn(first_vpfn),
+			  dma_to_mm_pfn(last_vpfn))) {
+		printk(KERN_ERR "IOMMU: reserve iova failed\n");
+		return -ENOMEM;
+	}
+
+	pr_debug("Mapping reserved region %llx-%llx for domain %d\n",
+		 start, end, domain->id);
+	/*
+	 * RMRR range might have overlap with physical memory range,
+	 * clear it first
+	 */
+	dma_pte_clear_range(domain, first_vpfn, last_vpfn);
+
+	return domain_pfn_mapping(domain, first_vpfn, first_vpfn,
+				  last_vpfn - first_vpfn + 1,
+				  DMA_PTE_READ|DMA_PTE_WRITE);
+}
+
+static int iommu_prepare_identity_map(struct pci_dev *pdev,
+				      unsigned long long start,
+				      unsigned long long end)
+{
+	struct dmar_domain *domain;
+	int ret;
+
+	domain = get_domain_for_dev(pdev, DEFAULT_DOMAIN_ADDRESS_WIDTH);
+	if (!domain)
+		return -ENOMEM;
+
+	/* For _hardware_ passthrough, don't bother. But for software
+	   passthrough, we do it anyway -- it may indicate a memory
+	   range which is reserved in E820, so which didn't get set
+	   up to start with in si_domain */
+	if (domain == si_domain && hw_pass_through) {
+		printk("Ignoring identity map for HW passthrough device %s [0x%Lx - 0x%Lx]\n",
+		       pci_name(pdev), start, end);
+		return 0;
+	}
+
+	printk(KERN_INFO
+	       "IOMMU: Setting identity map for device %s [0x%Lx - 0x%Lx]\n",
+	       pci_name(pdev), start, end);
+	
+	if (end < start) {
+		WARN(1, "Your BIOS is broken; RMRR ends before it starts!\n"
+			"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+			dmi_get_system_info(DMI_BIOS_VENDOR),
+			dmi_get_system_info(DMI_BIOS_VERSION),
+		     dmi_get_system_info(DMI_PRODUCT_VERSION));
+		ret = -EIO;
+		goto error;
+	}
+
+	if (end >> agaw_to_width(domain->agaw)) {
+		WARN(1, "Your BIOS is broken; RMRR exceeds permitted address width (%d bits)\n"
+		     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+		     agaw_to_width(domain->agaw),
+		     dmi_get_system_info(DMI_BIOS_VENDOR),
+		     dmi_get_system_info(DMI_BIOS_VERSION),
+		     dmi_get_system_info(DMI_PRODUCT_VERSION));
+		ret = -EIO;
+		goto error;
+	}
+
+	ret = iommu_domain_identity_map(domain, start, end);
+	if (ret)
+		goto error;
+
+	/* context entry init */
+	ret = domain_context_mapping(domain, pdev, CONTEXT_TT_MULTI_LEVEL);
+	if (ret)
+		goto error;
+
+	return 0;
+
+ error:
+	domain_exit(domain);
+	return ret;
+}
+
+static inline int iommu_prepare_rmrr_dev(struct dmar_rmrr_unit *rmrr,
+	struct pci_dev *pdev)
+{
+	if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)
+		return 0;
+	return iommu_prepare_identity_map(pdev, rmrr->base_address,
+		rmrr->end_address);
+}
+
+#ifdef CONFIG_DMAR_FLOPPY_WA
+static inline void iommu_prepare_isa(void)
+{
+	struct pci_dev *pdev;
+	int ret;
+
+	pdev = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, NULL);
+	if (!pdev)
+		return;
+
+	printk(KERN_INFO "IOMMU: Prepare 0-16MiB unity mapping for LPC\n");
+	ret = iommu_prepare_identity_map(pdev, 0, 16*1024*1024 - 1);
+
+	if (ret)
+		printk(KERN_ERR "IOMMU: Failed to create 0-16MiB identity map; "
+		       "floppy might not work\n");
+
+}
+#else
+static inline void iommu_prepare_isa(void)
+{
+	return;
+}
+#endif /* !CONFIG_DMAR_FLPY_WA */
+
+static int md_domain_init(struct dmar_domain *domain, int guest_width);
+
+static int __init si_domain_work_fn(unsigned long start_pfn,
+				    unsigned long end_pfn, void *datax)
+{
+	int *ret = datax;
+
+	*ret = iommu_domain_identity_map(si_domain,
+					 (uint64_t)start_pfn << PAGE_SHIFT,
+					 (uint64_t)end_pfn << PAGE_SHIFT);
+	return *ret;
+
+}
+
+static int __init si_domain_init(int hw)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	int nid, ret = 0;
+
+	si_domain = alloc_domain();
+	if (!si_domain)
+		return -EFAULT;
+
+	pr_debug("Identity mapping domain is domain %d\n", si_domain->id);
+
+	for_each_active_iommu(iommu, drhd) {
+		ret = iommu_attach_domain(si_domain, iommu);
+		if (ret) {
+			domain_exit(si_domain);
+			return -EFAULT;
+		}
+	}
+
+	if (md_domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
+		domain_exit(si_domain);
+		return -EFAULT;
+	}
+
+	si_domain->flags = DOMAIN_FLAG_STATIC_IDENTITY;
+
+	if (hw)
+		return 0;
+
+	for_each_online_node(nid) {
+		work_with_active_regions(nid, si_domain_work_fn, &ret);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void domain_remove_one_dev_info(struct dmar_domain *domain,
+					  struct pci_dev *pdev);
+static int identity_mapping(struct pci_dev *pdev)
+{
+	struct device_domain_info *info;
+
+	if (likely(!iommu_identity_mapping))
+		return 0;
+
+	info = pdev->dev.archdata.iommu;
+	if (info && info != DUMMY_DEVICE_DOMAIN_INFO)
+		return (info->domain == si_domain);
+
+	return 0;
+}
+
+static int domain_add_dev_info(struct dmar_domain *domain,
+			       struct pci_dev *pdev,
+			       int translation)
+{
+	struct device_domain_info *info;
+	unsigned long flags;
+	int ret;
+
+	info = alloc_devinfo_mem();
+	if (!info)
+		return -ENOMEM;
+
+	ret = domain_context_mapping(domain, pdev, translation);
+	if (ret) {
+		free_devinfo_mem(info);
+		return ret;
+	}
+
+	info->segment = pci_domain_nr(pdev->bus);
+	info->bus = pdev->bus->number;
+	info->devfn = pdev->devfn;
+	info->dev = pdev;
+	info->domain = domain;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	list_add(&info->link, &domain->devices);
+	list_add(&info->global, &device_domain_list);
+	pdev->dev.archdata.iommu = info;
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	return 0;
+}
+
+static int iommu_should_identity_map(struct pci_dev *pdev, int startup)
+{
+	if ((iommu_identity_mapping & IDENTMAP_AZALIA) && IS_AZALIA(pdev))
+		return 1;
+
+	if ((iommu_identity_mapping & IDENTMAP_GFX) && IS_GFX_DEVICE(pdev))
+		return 1;
+
+	if (!(iommu_identity_mapping & IDENTMAP_ALL))
+		return 0;
+
+	/*
+	 * We want to start off with all devices in the 1:1 domain, and
+	 * take them out later if we find they can't access all of memory.
+	 *
+	 * However, we can't do this for PCI devices behind bridges,
+	 * because all PCI devices behind the same bridge will end up
+	 * with the same source-id on their transactions.
+	 *
+	 * Practically speaking, we can't change things around for these
+	 * devices at run-time, because we can't be sure there'll be no
+	 * DMA transactions in flight for any of their siblings.
+	 * 
+	 * So PCI devices (unless they're on the root bus) as well as
+	 * their parent PCI-PCI or PCIe-PCI bridges must be left _out_ of
+	 * the 1:1 domain, just in _case_ one of their siblings turns out
+	 * not to be able to map all of memory.
+	 */
+	if (!pci_is_pcie(pdev)) {
+		if (!pci_is_root_bus(pdev->bus))
+			return 0;
+		if (pdev->class >> 8 == PCI_CLASS_BRIDGE_PCI)
+			return 0;
+	} else if (pdev->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE)
+		return 0;
+
+	/* 
+	 * At boot time, we don't yet know if devices will be 64-bit capable.
+	 * Assume that they will -- if they turn out not to be, then we can 
+	 * take them out of the 1:1 domain later.
+	 */
+	if (!startup) {
+		/*
+		 * If the device's dma_mask is less than the system's memory
+		 * size then this is not a candidate for identity mapping.
+		 */
+		u64 dma_mask = pdev->dma_mask;
+
+		if (pdev->dev.coherent_dma_mask &&
+		    pdev->dev.coherent_dma_mask < dma_mask)
+			dma_mask = pdev->dev.coherent_dma_mask;
+
+		return dma_mask >= dma_get_required_mask(&pdev->dev);
+	}
+
+	return 1;
+}
+
+static int __init iommu_prepare_static_identity_mapping(int hw)
+{
+	struct pci_dev *pdev = NULL;
+	int ret;
+
+	ret = si_domain_init(hw);
+	if (ret)
+		return -EFAULT;
+
+	for_each_pci_dev(pdev) {
+		/* Skip Host/PCI Bridge devices */
+		if (IS_BRIDGE_HOST_DEVICE(pdev))
+			continue;
+		if (iommu_should_identity_map(pdev, 1)) {
+			printk(KERN_INFO "IOMMU: %s identity mapping for device %s\n",
+			       hw ? "hardware" : "software", pci_name(pdev));
+
+			ret = domain_add_dev_info(si_domain, pdev,
+						     hw ? CONTEXT_TT_PASS_THROUGH :
+						     CONTEXT_TT_MULTI_LEVEL);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int __init init_dmars(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct dmar_rmrr_unit *rmrr;
+	struct pci_dev *pdev;
+	struct intel_iommu *iommu;
+	int i, ret;
+
+	/*
+	 * for each drhd
+	 *    allocate root
+	 *    initialize and program root entry to not present
+	 * endfor
+	 */
+	for_each_drhd_unit(drhd) {
+		g_num_of_iommus++;
+		/*
+		 * lock not needed as this is only incremented in the single
+		 * threaded kernel __init code path all other access are read
+		 * only
+		 */
+	}
+
+	g_iommus = kcalloc(g_num_of_iommus, sizeof(struct intel_iommu *),
+			GFP_KERNEL);
+	if (!g_iommus) {
+		printk(KERN_ERR "Allocating global iommu array failed\n");
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	deferred_flush = kzalloc(g_num_of_iommus *
+		sizeof(struct deferred_flush_tables), GFP_KERNEL);
+	if (!deferred_flush) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	for_each_drhd_unit(drhd) {
+		if (drhd->ignored)
+			continue;
+
+		iommu = drhd->iommu;
+		g_iommus[iommu->seq_id] = iommu;
+
+		ret = iommu_init_domains(iommu);
+		if (ret)
+			goto error;
+
+		/*
+		 * TBD:
+		 * we could share the same root & context tables
+		 * among all IOMMU's. Need to Split it later.
+		 */
+		ret = iommu_alloc_root_entry(iommu);
+		if (ret) {
+			printk(KERN_ERR "IOMMU: allocate root entry failed\n");
+			goto error;
+		}
+		if (!ecap_pass_through(iommu->ecap))
+			hw_pass_through = 0;
+	}
+
+	/*
+	 * Start from the sane iommu hardware state.
+	 */
+	for_each_drhd_unit(drhd) {
+		if (drhd->ignored)
+			continue;
+
+		iommu = drhd->iommu;
+
+		/*
+		 * If the queued invalidation is already initialized by us
+		 * (for example, while enabling interrupt-remapping) then
+		 * we got the things already rolling from a sane state.
+		 */
+		if (iommu->qi)
+			continue;
+
+		/*
+		 * Clear any previous faults.
+		 */
+		dmar_fault(-1, iommu);
+		/*
+		 * Disable queued invalidation if supported and already enabled
+		 * before OS handover.
+		 */
+		dmar_disable_qi(iommu);
+	}
+
+	for_each_drhd_unit(drhd) {
+		if (drhd->ignored)
+			continue;
+
+		iommu = drhd->iommu;
+
+		if (dmar_enable_qi(iommu)) {
+			/*
+			 * Queued Invalidate not enabled, use Register Based
+			 * Invalidate
+			 */
+			iommu->flush.flush_context = __iommu_flush_context;
+			iommu->flush.flush_iotlb = __iommu_flush_iotlb;
+			printk(KERN_INFO "IOMMU %d 0x%Lx: using Register based "
+			       "invalidation\n",
+				iommu->seq_id,
+			       (unsigned long long)drhd->reg_base_addr);
+		} else {
+			iommu->flush.flush_context = qi_flush_context;
+			iommu->flush.flush_iotlb = qi_flush_iotlb;
+			printk(KERN_INFO "IOMMU %d 0x%Lx: using Queued "
+			       "invalidation\n",
+				iommu->seq_id,
+			       (unsigned long long)drhd->reg_base_addr);
+		}
+	}
+
+	if (iommu_pass_through)
+		iommu_identity_mapping |= IDENTMAP_ALL;
+
+#ifdef CONFIG_DMAR_BROKEN_GFX_WA
+	iommu_identity_mapping |= IDENTMAP_GFX;
+#endif
+
+	check_tylersburg_isoch();
+
+	/*
+	 * If pass through is not set or not enabled, setup context entries for
+	 * identity mappings for rmrr, gfx, and isa and may fall back to static
+	 * identity mapping if iommu_identity_mapping is set.
+	 */
+	if (iommu_identity_mapping) {
+		ret = iommu_prepare_static_identity_mapping(hw_pass_through);
+		if (ret) {
+			printk(KERN_CRIT "Failed to setup IOMMU pass-through\n");
+			goto error;
+		}
+	}
+	/*
+	 * For each rmrr
+	 *   for each dev attached to rmrr
+	 *   do
+	 *     locate drhd for dev, alloc domain for dev
+	 *     allocate free domain
+	 *     allocate page table entries for rmrr
+	 *     if context not allocated for bus
+	 *           allocate and init context
+	 *           set present in root table for this bus
+	 *     init context with domain, translation etc
+	 *    endfor
+	 * endfor
+	 */
+	printk(KERN_INFO "IOMMU: Setting RMRR:\n");
+	for_each_rmrr_units(rmrr) {
+		for (i = 0; i < rmrr->devices_cnt; i++) {
+			pdev = rmrr->devices[i];
+			/*
+			 * some BIOS lists non-exist devices in DMAR
+			 * table.
+			 */
+			if (!pdev)
+				continue;
+			ret = iommu_prepare_rmrr_dev(rmrr, pdev);
+			if (ret)
+				printk(KERN_ERR
+				       "IOMMU: mapping reserved region failed\n");
+		}
+	}
+
+	iommu_prepare_isa();
+
+	/*
+	 * for each drhd
+	 *   enable fault log
+	 *   global invalidate context cache
+	 *   global invalidate iotlb
+	 *   enable translation
+	 */
+	for_each_drhd_unit(drhd) {
+		if (drhd->ignored) {
+			/*
+			 * we always have to disable PMRs or DMA may fail on
+			 * this device
+			 */
+			if (force_on)
+				iommu_disable_protect_mem_regions(drhd->iommu);
+			continue;
+		}
+		iommu = drhd->iommu;
+
+		iommu_flush_write_buffer(iommu);
+
+		ret = dmar_set_interrupt(iommu);
+		if (ret)
+			goto error;
+
+		iommu_set_root_entry(iommu);
+
+		iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
+		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
+
+		ret = iommu_enable_translation(iommu);
+		if (ret)
+			goto error;
+
+		iommu_disable_protect_mem_regions(iommu);
+	}
+
+	return 0;
+error:
+	for_each_drhd_unit(drhd) {
+		if (drhd->ignored)
+			continue;
+		iommu = drhd->iommu;
+		free_iommu(iommu);
+	}
+	kfree(g_iommus);
+	return ret;
+}
+
+/* This takes a number of _MM_ pages, not VTD pages */
+static struct iova *intel_alloc_iova(struct device *dev,
+				     struct dmar_domain *domain,
+				     unsigned long nrpages, uint64_t dma_mask)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct iova *iova = NULL;
+
+	/* Restrict dma_mask to the width that the iommu can handle */
+	dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw), dma_mask);
+
+	if (!dmar_forcedac && dma_mask > DMA_BIT_MASK(32)) {
+		/*
+		 * First try to allocate an io virtual address in
+		 * DMA_BIT_MASK(32) and if that fails then try allocating
+		 * from higher range
+		 */
+		iova = alloc_iova(&domain->iovad, nrpages,
+				  IOVA_PFN(DMA_BIT_MASK(32)), 1);
+		if (iova)
+			return iova;
+	}
+	iova = alloc_iova(&domain->iovad, nrpages, IOVA_PFN(dma_mask), 1);
+	if (unlikely(!iova)) {
+		printk(KERN_ERR "Allocating %ld-page iova for %s failed",
+		       nrpages, pci_name(pdev));
+		return NULL;
+	}
+
+	return iova;
+}
+
+static struct dmar_domain *__get_valid_domain_for_dev(struct pci_dev *pdev)
+{
+	struct dmar_domain *domain;
+	int ret;
+
+	domain = get_domain_for_dev(pdev,
+			DEFAULT_DOMAIN_ADDRESS_WIDTH);
+	if (!domain) {
+		printk(KERN_ERR
+			"Allocating domain for %s failed", pci_name(pdev));
+		return NULL;
+	}
+
+	/* make sure context mapping is ok */
+	if (unlikely(!domain_context_mapped(pdev))) {
+		ret = domain_context_mapping(domain, pdev,
+					     CONTEXT_TT_MULTI_LEVEL);
+		if (ret) {
+			printk(KERN_ERR
+				"Domain context map for %s failed",
+				pci_name(pdev));
+			return NULL;
+		}
+	}
+
+	return domain;
+}
+
+static inline struct dmar_domain *get_valid_domain_for_dev(struct pci_dev *dev)
+{
+	struct device_domain_info *info;
+
+	/* No lock here, assumes no domain exit in normal case */
+	info = dev->dev.archdata.iommu;
+	if (likely(info))
+		return info->domain;
+
+	return __get_valid_domain_for_dev(dev);
+}
+
+static int iommu_dummy(struct pci_dev *pdev)
+{
+	return pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO;
+}
+
+/* Check if the pdev needs to go through non-identity map and unmap process.*/
+static int iommu_no_mapping(struct device *dev)
+{
+	struct pci_dev *pdev;
+	int found;
+
+	if (unlikely(dev->bus != &pci_bus_type))
+		return 1;
+
+	pdev = to_pci_dev(dev);
+	if (iommu_dummy(pdev))
+		return 1;
+
+	if (!iommu_identity_mapping)
+		return 0;
+
+	found = identity_mapping(pdev);
+	if (found) {
+		if (iommu_should_identity_map(pdev, 0))
+			return 1;
+		else {
+			/*
+			 * 32 bit DMA is removed from si_domain and fall back
+			 * to non-identity mapping.
+			 */
+			domain_remove_one_dev_info(si_domain, pdev);
+			printk(KERN_INFO "32bit %s uses non-identity mapping\n",
+			       pci_name(pdev));
+			return 0;
+		}
+	} else {
+		/*
+		 * In case of a detached 64 bit DMA device from vm, the device
+		 * is put into si_domain for identity mapping.
+		 */
+		if (iommu_should_identity_map(pdev, 0)) {
+			int ret;
+			ret = domain_add_dev_info(si_domain, pdev,
+						  hw_pass_through ?
+						  CONTEXT_TT_PASS_THROUGH :
+						  CONTEXT_TT_MULTI_LEVEL);
+			if (!ret) {
+				printk(KERN_INFO "64bit %s uses identity mapping\n",
+				       pci_name(pdev));
+				return 1;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr,
+				     size_t size, int dir, u64 dma_mask)
+{
+	struct pci_dev *pdev = to_pci_dev(hwdev);
+	struct dmar_domain *domain;
+	phys_addr_t start_paddr;
+	struct iova *iova;
+	int prot = 0;
+	int ret;
+	struct intel_iommu *iommu;
+	unsigned long paddr_pfn = paddr >> PAGE_SHIFT;
+
+	BUG_ON(dir == DMA_NONE);
+
+	if (iommu_no_mapping(hwdev))
+		return paddr;
+
+	domain = get_valid_domain_for_dev(pdev);
+	if (!domain)
+		return 0;
+
+	iommu = domain_get_iommu(domain);
+	size = aligned_nrpages(paddr, size);
+
+	iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size), dma_mask);
+	if (!iova)
+		goto error;
+
+	/*
+	 * Check if DMAR supports zero-length reads on write only
+	 * mappings..
+	 */
+	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL || \
+			!cap_zlr(iommu->cap))
+		prot |= DMA_PTE_READ;
+	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
+		prot |= DMA_PTE_WRITE;
+	/*
+	 * paddr - (paddr + size) might be partial page, we should map the whole
+	 * page.  Note: if two part of one page are separately mapped, we
+	 * might have two guest_addr mapping to the same host paddr, but this
+	 * is not a big problem
+	 */
+	ret = domain_pfn_mapping(domain, mm_to_dma_pfn(iova->pfn_lo),
+				 mm_to_dma_pfn(paddr_pfn), size, prot);
+	if (ret)
+		goto error;
+
+	/* it's a non-present to present mapping. Only flush if caching mode */
+	if (cap_caching_mode(iommu->cap))
+		iommu_flush_iotlb_psi(iommu, domain->id, mm_to_dma_pfn(iova->pfn_lo), size, 1);
+	else
+		iommu_flush_write_buffer(iommu);
+
+	start_paddr = (phys_addr_t)iova->pfn_lo << PAGE_SHIFT;
+	start_paddr += paddr & ~PAGE_MASK;
+	return start_paddr;
+
+error:
+	if (iova)
+		__free_iova(&domain->iovad, iova);
+	printk(KERN_ERR"Device %s request: %zx@%llx dir %d --- failed\n",
+		pci_name(pdev), size, (unsigned long long)paddr, dir);
+	return 0;
+}
+
+static dma_addr_t intel_map_page(struct device *dev, struct page *page,
+				 unsigned long offset, size_t size,
+				 enum dma_data_direction dir,
+				 struct dma_attrs *attrs)
+{
+	return __intel_map_single(dev, page_to_phys(page) + offset, size,
+				  dir, to_pci_dev(dev)->dma_mask);
+}
+
+static void flush_unmaps(void)
+{
+	int i, j;
+
+	timer_on = 0;
+
+	/* just flush them all */
+	for (i = 0; i < g_num_of_iommus; i++) {
+		struct intel_iommu *iommu = g_iommus[i];
+		if (!iommu)
+			continue;
+
+		if (!deferred_flush[i].next)
+			continue;
+
+		/* In caching mode, global flushes turn emulation expensive */
+		if (!cap_caching_mode(iommu->cap))
+			iommu->flush.flush_iotlb(iommu, 0, 0, 0,
+					 DMA_TLB_GLOBAL_FLUSH);
+		for (j = 0; j < deferred_flush[i].next; j++) {
+			unsigned long mask;
+			struct iova *iova = deferred_flush[i].iova[j];
+			struct dmar_domain *domain = deferred_flush[i].domain[j];
+
+			/* On real hardware multiple invalidations are expensive */
+			if (cap_caching_mode(iommu->cap))
+				iommu_flush_iotlb_psi(iommu, domain->id,
+				iova->pfn_lo, iova->pfn_hi - iova->pfn_lo + 1, 0);
+			else {
+				mask = ilog2(mm_to_dma_pfn(iova->pfn_hi - iova->pfn_lo + 1));
+				iommu_flush_dev_iotlb(deferred_flush[i].domain[j],
+						(uint64_t)iova->pfn_lo << PAGE_SHIFT, mask);
+			}
+			__free_iova(&deferred_flush[i].domain[j]->iovad, iova);
+		}
+		deferred_flush[i].next = 0;
+	}
+
+	list_size = 0;
+}
+
+static void flush_unmaps_timeout(unsigned long data)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&async_umap_flush_lock, flags);
+	flush_unmaps();
+	spin_unlock_irqrestore(&async_umap_flush_lock, flags);
+}
+
+static void add_unmap(struct dmar_domain *dom, struct iova *iova)
+{
+	unsigned long flags;
+	int next, iommu_id;
+	struct intel_iommu *iommu;
+
+	spin_lock_irqsave(&async_umap_flush_lock, flags);
+	if (list_size == HIGH_WATER_MARK)
+		flush_unmaps();
+
+	iommu = domain_get_iommu(dom);
+	iommu_id = iommu->seq_id;
+
+	next = deferred_flush[iommu_id].next;
+	deferred_flush[iommu_id].domain[next] = dom;
+	deferred_flush[iommu_id].iova[next] = iova;
+	deferred_flush[iommu_id].next++;
+
+	if (!timer_on) {
+		mod_timer(&unmap_timer, jiffies + msecs_to_jiffies(10));
+		timer_on = 1;
+	}
+	list_size++;
+	spin_unlock_irqrestore(&async_umap_flush_lock, flags);
+}
+
+static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
+			     size_t size, enum dma_data_direction dir,
+			     struct dma_attrs *attrs)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct dmar_domain *domain;
+	unsigned long start_pfn, last_pfn;
+	struct iova *iova;
+	struct intel_iommu *iommu;
+
+	if (iommu_no_mapping(dev))
+		return;
+
+	domain = find_domain(pdev);
+	BUG_ON(!domain);
+
+	iommu = domain_get_iommu(domain);
+
+	iova = find_iova(&domain->iovad, IOVA_PFN(dev_addr));
+	if (WARN_ONCE(!iova, "Driver unmaps unmatched page at PFN %llx\n",
+		      (unsigned long long)dev_addr))
+		return;
+
+	start_pfn = mm_to_dma_pfn(iova->pfn_lo);
+	last_pfn = mm_to_dma_pfn(iova->pfn_hi + 1) - 1;
+
+	pr_debug("Device %s unmapping: pfn %lx-%lx\n",
+		 pci_name(pdev), start_pfn, last_pfn);
+
+	/*  clear the whole page */
+	dma_pte_clear_range(domain, start_pfn, last_pfn);
+
+	/* free page tables */
+	dma_pte_free_pagetable(domain, start_pfn, last_pfn);
+
+	if (intel_iommu_strict) {
+		iommu_flush_iotlb_psi(iommu, domain->id, start_pfn,
+				      last_pfn - start_pfn + 1, 0);
+		/* free iova */
+		__free_iova(&domain->iovad, iova);
+	} else {
+		add_unmap(domain, iova);
+		/*
+		 * queue up the release of the unmap to save the 1/6th of the
+		 * cpu used up by the iotlb flush operation...
+		 */
+	}
+}
+
+static void *intel_alloc_coherent(struct device *hwdev, size_t size,
+				  dma_addr_t *dma_handle, gfp_t flags)
+{
+	void *vaddr;
+	int order;
+
+	size = PAGE_ALIGN(size);
+	order = get_order(size);
+
+	if (!iommu_no_mapping(hwdev))
+		flags &= ~(GFP_DMA | GFP_DMA32);
+	else if (hwdev->coherent_dma_mask < dma_get_required_mask(hwdev)) {
+		if (hwdev->coherent_dma_mask < DMA_BIT_MASK(32))
+			flags |= GFP_DMA;
+		else
+			flags |= GFP_DMA32;
+	}
+
+	vaddr = (void *)__get_free_pages(flags, order);
+	if (!vaddr)
+		return NULL;
+	memset(vaddr, 0, size);
+
+	*dma_handle = __intel_map_single(hwdev, virt_to_bus(vaddr), size,
+					 DMA_BIDIRECTIONAL,
+					 hwdev->coherent_dma_mask);
+	if (*dma_handle)
+		return vaddr;
+	free_pages((unsigned long)vaddr, order);
+	return NULL;
+}
+
+static void intel_free_coherent(struct device *hwdev, size_t size, void *vaddr,
+				dma_addr_t dma_handle)
+{
+	int order;
+
+	size = PAGE_ALIGN(size);
+	order = get_order(size);
+
+	intel_unmap_page(hwdev, dma_handle, size, DMA_BIDIRECTIONAL, NULL);
+	free_pages((unsigned long)vaddr, order);
+}
+
+static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,
+			   int nelems, enum dma_data_direction dir,
+			   struct dma_attrs *attrs)
+{
+	struct pci_dev *pdev = to_pci_dev(hwdev);
+	struct dmar_domain *domain;
+	unsigned long start_pfn, last_pfn;
+	struct iova *iova;
+	struct intel_iommu *iommu;
+
+	if (iommu_no_mapping(hwdev))
+		return;
+
+	domain = find_domain(pdev);
+	BUG_ON(!domain);
+
+	iommu = domain_get_iommu(domain);
+
+	iova = find_iova(&domain->iovad, IOVA_PFN(sglist[0].dma_address));
+	if (WARN_ONCE(!iova, "Driver unmaps unmatched sglist at PFN %llx\n",
+		      (unsigned long long)sglist[0].dma_address))
+		return;
+
+	start_pfn = mm_to_dma_pfn(iova->pfn_lo);
+	last_pfn = mm_to_dma_pfn(iova->pfn_hi + 1) - 1;
+
+	/*  clear the whole page */
+	dma_pte_clear_range(domain, start_pfn, last_pfn);
+
+	/* free page tables */
+	dma_pte_free_pagetable(domain, start_pfn, last_pfn);
+
+	if (intel_iommu_strict) {
+		iommu_flush_iotlb_psi(iommu, domain->id, start_pfn,
+				      last_pfn - start_pfn + 1, 0);
+		/* free iova */
+		__free_iova(&domain->iovad, iova);
+	} else {
+		add_unmap(domain, iova);
+		/*
+		 * queue up the release of the unmap to save the 1/6th of the
+		 * cpu used up by the iotlb flush operation...
+		 */
+	}
+}
+
+static int intel_nontranslate_map_sg(struct device *hddev,
+	struct scatterlist *sglist, int nelems, int dir)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nelems, i) {
+		BUG_ON(!sg_page(sg));
+		sg->dma_address = page_to_phys(sg_page(sg)) + sg->offset;
+		sg->dma_length = sg->length;
+	}
+	return nelems;
+}
+
+static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int nelems,
+			enum dma_data_direction dir, struct dma_attrs *attrs)
+{
+	int i;
+	struct pci_dev *pdev = to_pci_dev(hwdev);
+	struct dmar_domain *domain;
+	size_t size = 0;
+	int prot = 0;
+	struct iova *iova = NULL;
+	int ret;
+	struct scatterlist *sg;
+	unsigned long start_vpfn;
+	struct intel_iommu *iommu;
+
+	BUG_ON(dir == DMA_NONE);
+	if (iommu_no_mapping(hwdev))
+		return intel_nontranslate_map_sg(hwdev, sglist, nelems, dir);
+
+	domain = get_valid_domain_for_dev(pdev);
+	if (!domain)
+		return 0;
+
+	iommu = domain_get_iommu(domain);
+
+	for_each_sg(sglist, sg, nelems, i)
+		size += aligned_nrpages(sg->offset, sg->length);
+
+	iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size),
+				pdev->dma_mask);
+	if (!iova) {
+		sglist->dma_length = 0;
+		return 0;
+	}
+
+	/*
+	 * Check if DMAR supports zero-length reads on write only
+	 * mappings..
+	 */
+	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL || \
+			!cap_zlr(iommu->cap))
+		prot |= DMA_PTE_READ;
+	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
+		prot |= DMA_PTE_WRITE;
+
+	start_vpfn = mm_to_dma_pfn(iova->pfn_lo);
+
+	ret = domain_sg_mapping(domain, start_vpfn, sglist, size, prot);
+	if (unlikely(ret)) {
+		/*  clear the page */
+		dma_pte_clear_range(domain, start_vpfn,
+				    start_vpfn + size - 1);
+		/* free page tables */
+		dma_pte_free_pagetable(domain, start_vpfn,
+				       start_vpfn + size - 1);
+		/* free iova */
+		__free_iova(&domain->iovad, iova);
+		return 0;
+	}
+
+	/* it's a non-present to present mapping. Only flush if caching mode */
+	if (cap_caching_mode(iommu->cap))
+		iommu_flush_iotlb_psi(iommu, domain->id, start_vpfn, size, 1);
+	else
+		iommu_flush_write_buffer(iommu);
+
+	return nelems;
+}
+
+static int intel_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return !dma_addr;
+}
+
+struct dma_map_ops intel_dma_ops = {
+	.alloc_coherent = intel_alloc_coherent,
+	.free_coherent = intel_free_coherent,
+	.map_sg = intel_map_sg,
+	.unmap_sg = intel_unmap_sg,
+	.map_page = intel_map_page,
+	.unmap_page = intel_unmap_page,
+	.mapping_error = intel_mapping_error,
+};
+
+static inline int iommu_domain_cache_init(void)
+{
+	int ret = 0;
+
+	iommu_domain_cache = kmem_cache_create("iommu_domain",
+					 sizeof(struct dmar_domain),
+					 0,
+					 SLAB_HWCACHE_ALIGN,
+
+					 NULL);
+	if (!iommu_domain_cache) {
+		printk(KERN_ERR "Couldn't create iommu_domain cache\n");
+		ret = -ENOMEM;
+	}
+
+	return ret;
+}
+
+static inline int iommu_devinfo_cache_init(void)
+{
+	int ret = 0;
+
+	iommu_devinfo_cache = kmem_cache_create("iommu_devinfo",
+					 sizeof(struct device_domain_info),
+					 0,
+					 SLAB_HWCACHE_ALIGN,
+					 NULL);
+	if (!iommu_devinfo_cache) {
+		printk(KERN_ERR "Couldn't create devinfo cache\n");
+		ret = -ENOMEM;
+	}
+
+	return ret;
+}
+
+static inline int iommu_iova_cache_init(void)
+{
+	int ret = 0;
+
+	iommu_iova_cache = kmem_cache_create("iommu_iova",
+					 sizeof(struct iova),
+					 0,
+					 SLAB_HWCACHE_ALIGN,
+					 NULL);
+	if (!iommu_iova_cache) {
+		printk(KERN_ERR "Couldn't create iova cache\n");
+		ret = -ENOMEM;
+	}
+
+	return ret;
+}
+
+static int __init iommu_init_mempool(void)
+{
+	int ret;
+	ret = iommu_iova_cache_init();
+	if (ret)
+		return ret;
+
+	ret = iommu_domain_cache_init();
+	if (ret)
+		goto domain_error;
+
+	ret = iommu_devinfo_cache_init();
+	if (!ret)
+		return ret;
+
+	kmem_cache_destroy(iommu_domain_cache);
+domain_error:
+	kmem_cache_destroy(iommu_iova_cache);
+
+	return -ENOMEM;
+}
+
+static void __init iommu_exit_mempool(void)
+{
+	kmem_cache_destroy(iommu_devinfo_cache);
+	kmem_cache_destroy(iommu_domain_cache);
+	kmem_cache_destroy(iommu_iova_cache);
+
+}
+
+static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
+{
+	struct dmar_drhd_unit *drhd;
+	u32 vtbar;
+	int rc;
+
+	/* We know that this device on this chipset has its own IOMMU.
+	 * If we find it under a different IOMMU, then the BIOS is lying
+	 * to us. Hope that the IOMMU for this device is actually
+	 * disabled, and it needs no translation...
+	 */
+	rc = pci_bus_read_config_dword(pdev->bus, PCI_DEVFN(0, 0), 0xb0, &vtbar);
+	if (rc) {
+		/* "can't" happen */
+		dev_info(&pdev->dev, "failed to run vt-d quirk\n");
+		return;
+	}
+	vtbar &= 0xffff0000;
+
+	/* we know that the this iommu should be at offset 0xa000 from vtbar */
+	drhd = dmar_find_matched_drhd_unit(pdev);
+	if (WARN_TAINT_ONCE(!drhd || drhd->reg_base_addr - vtbar != 0xa000,
+			    TAINT_FIRMWARE_WORKAROUND,
+			    "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n"))
+		pdev->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO;
+}
+DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB, quirk_ioat_snb_local_iommu);
+
+static void __init init_no_remapping_devices(void)
+{
+	struct dmar_drhd_unit *drhd;
+
+	for_each_drhd_unit(drhd) {
+		if (!drhd->include_all) {
+			int i;
+			for (i = 0; i < drhd->devices_cnt; i++)
+				if (drhd->devices[i] != NULL)
+					break;
+			/* ignore DMAR unit if no pci devices exist */
+			if (i == drhd->devices_cnt)
+				drhd->ignored = 1;
+		}
+	}
+
+	if (dmar_map_gfx)
+		return;
+
+	for_each_drhd_unit(drhd) {
+		int i;
+		if (drhd->ignored || drhd->include_all)
+			continue;
+
+		for (i = 0; i < drhd->devices_cnt; i++)
+			if (drhd->devices[i] &&
+				!IS_GFX_DEVICE(drhd->devices[i]))
+				break;
+
+		if (i < drhd->devices_cnt)
+			continue;
+
+		/* bypass IOMMU if it is just for gfx devices */
+		drhd->ignored = 1;
+		for (i = 0; i < drhd->devices_cnt; i++) {
+			if (!drhd->devices[i])
+				continue;
+			drhd->devices[i]->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO;
+		}
+	}
+}
+
+#ifdef CONFIG_SUSPEND
+static int init_iommu_hw(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+
+	for_each_active_iommu(iommu, drhd)
+		if (iommu->qi)
+			dmar_reenable_qi(iommu);
+
+	for_each_iommu(iommu, drhd) {
+		if (drhd->ignored) {
+			/*
+			 * we always have to disable PMRs or DMA may fail on
+			 * this device
+			 */
+			if (force_on)
+				iommu_disable_protect_mem_regions(iommu);
+			continue;
+		}
+	
+		iommu_flush_write_buffer(iommu);
+
+		iommu_set_root_entry(iommu);
+
+		iommu->flush.flush_context(iommu, 0, 0, 0,
+					   DMA_CCMD_GLOBAL_INVL);
+		iommu->flush.flush_iotlb(iommu, 0, 0, 0,
+					 DMA_TLB_GLOBAL_FLUSH);
+		if (iommu_enable_translation(iommu))
+			return 1;
+		iommu_disable_protect_mem_regions(iommu);
+	}
+
+	return 0;
+}
+
+static void iommu_flush_all(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+
+	for_each_active_iommu(iommu, drhd) {
+		iommu->flush.flush_context(iommu, 0, 0, 0,
+					   DMA_CCMD_GLOBAL_INVL);
+		iommu->flush.flush_iotlb(iommu, 0, 0, 0,
+					 DMA_TLB_GLOBAL_FLUSH);
+	}
+}
+
+static int iommu_suspend(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+	unsigned long flag;
+
+	for_each_active_iommu(iommu, drhd) {
+		iommu->iommu_state = kzalloc(sizeof(u32) * MAX_SR_DMAR_REGS,
+						 GFP_ATOMIC);
+		if (!iommu->iommu_state)
+			goto nomem;
+	}
+
+	iommu_flush_all();
+
+	for_each_active_iommu(iommu, drhd) {
+		iommu_disable_translation(iommu);
+
+		spin_lock_irqsave(&iommu->register_lock, flag);
+
+		iommu->iommu_state[SR_DMAR_FECTL_REG] =
+			readl(iommu->reg + DMAR_FECTL_REG);
+		iommu->iommu_state[SR_DMAR_FEDATA_REG] =
+			readl(iommu->reg + DMAR_FEDATA_REG);
+		iommu->iommu_state[SR_DMAR_FEADDR_REG] =
+			readl(iommu->reg + DMAR_FEADDR_REG);
+		iommu->iommu_state[SR_DMAR_FEUADDR_REG] =
+			readl(iommu->reg + DMAR_FEUADDR_REG);
+
+		spin_unlock_irqrestore(&iommu->register_lock, flag);
+	}
+	return 0;
+
+nomem:
+	for_each_active_iommu(iommu, drhd)
+		kfree(iommu->iommu_state);
+
+	return -ENOMEM;
+}
+
+static void iommu_resume(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+	unsigned long flag;
+
+	if (init_iommu_hw()) {
+		if (force_on)
+			panic("tboot: IOMMU setup failed, DMAR can not resume!\n");
+		else
+			WARN(1, "IOMMU setup failed, DMAR can not resume!\n");
+		return;
+	}
+
+	for_each_active_iommu(iommu, drhd) {
+
+		spin_lock_irqsave(&iommu->register_lock, flag);
+
+		writel(iommu->iommu_state[SR_DMAR_FECTL_REG],
+			iommu->reg + DMAR_FECTL_REG);
+		writel(iommu->iommu_state[SR_DMAR_FEDATA_REG],
+			iommu->reg + DMAR_FEDATA_REG);
+		writel(iommu->iommu_state[SR_DMAR_FEADDR_REG],
+			iommu->reg + DMAR_FEADDR_REG);
+		writel(iommu->iommu_state[SR_DMAR_FEUADDR_REG],
+			iommu->reg + DMAR_FEUADDR_REG);
+
+		spin_unlock_irqrestore(&iommu->register_lock, flag);
+	}
+
+	for_each_active_iommu(iommu, drhd)
+		kfree(iommu->iommu_state);
+}
+
+static struct syscore_ops iommu_syscore_ops = {
+	.resume		= iommu_resume,
+	.suspend	= iommu_suspend,
+};
+
+static void __init init_iommu_pm_ops(void)
+{
+	register_syscore_ops(&iommu_syscore_ops);
+}
+
+#else
+static inline void init_iommu_pm_ops(void) {}
+#endif	/* CONFIG_PM */
+
+/*
+ * Here we only respond to action of unbound device from driver.
+ *
+ * Added device is not attached to its DMAR domain here yet. That will happen
+ * when mapping the device to iova.
+ */
+static int device_notifier(struct notifier_block *nb,
+				  unsigned long action, void *data)
+{
+	struct device *dev = data;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct dmar_domain *domain;
+
+	if (iommu_no_mapping(dev))
+		return 0;
+
+	domain = find_domain(pdev);
+	if (!domain)
+		return 0;
+
+	if (action == BUS_NOTIFY_UNBOUND_DRIVER && !iommu_pass_through) {
+		domain_remove_one_dev_info(domain, pdev);
+
+		if (!(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) &&
+		    !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY) &&
+		    list_empty(&domain->devices))
+			domain_exit(domain);
+	}
+
+	return 0;
+}
+
+static struct notifier_block device_nb = {
+	.notifier_call = device_notifier,
+};
+
+int __init intel_iommu_init(void)
+{
+	int ret = 0;
+
+	/* VT-d is required for a TXT/tboot launch, so enforce that */
+	force_on = tboot_force_iommu();
+
+	if (dmar_table_init()) {
+		if (force_on)
+			panic("tboot: Failed to initialize DMAR table\n");
+		return 	-ENODEV;
+	}
+
+	if (dmar_dev_scope_init()) {
+		if (force_on)
+			panic("tboot: Failed to initialize DMAR device scope\n");
+		return 	-ENODEV;
+	}
+
+	/*
+	 * Check the need for DMA-remapping initialization now.
+	 * Above initialization will also be used by Interrupt-remapping.
+	 */
+	if (no_iommu || dmar_disabled)
+		return -ENODEV;
+
+	if (iommu_init_mempool()) {
+		if (force_on)
+			panic("tboot: Failed to initialize iommu memory\n");
+		return 	-ENODEV;
+	}
+
+	if (dmar_init_reserved_ranges()) {
+		if (force_on)
+			panic("tboot: Failed to reserve iommu ranges\n");
+		return 	-ENODEV;
+	}
+
+	init_no_remapping_devices();
+
+	ret = init_dmars();
+	if (ret) {
+		if (force_on)
+			panic("tboot: Failed to initialize DMARs\n");
+		printk(KERN_ERR "IOMMU: dmar init failed\n");
+		put_iova_domain(&reserved_iova_list);
+		iommu_exit_mempool();
+		return ret;
+	}
+	printk(KERN_INFO
+	"PCI-DMA: Intel(R) Virtualization Technology for Directed I/O\n");
+
+	init_timer(&unmap_timer);
+#ifdef CONFIG_SWIOTLB
+	swiotlb = 0;
+#endif
+	dma_ops = &intel_dma_ops;
+
+	init_iommu_pm_ops();
+
+	register_iommu(&intel_iommu_ops);
+
+	bus_register_notifier(&pci_bus_type, &device_nb);
+
+	return 0;
+}
+
+static void iommu_detach_dependent_devices(struct intel_iommu *iommu,
+					   struct pci_dev *pdev)
+{
+	struct pci_dev *tmp, *parent;
+
+	if (!iommu || !pdev)
+		return;
+
+	/* dependent device detach */
+	tmp = pci_find_upstream_pcie_bridge(pdev);
+	/* Secondary interface's bus number and devfn 0 */
+	if (tmp) {
+		parent = pdev->bus->self;
+		while (parent != tmp) {
+			iommu_detach_dev(iommu, parent->bus->number,
+					 parent->devfn);
+			parent = parent->bus->self;
+		}
+		if (pci_is_pcie(tmp)) /* this is a PCIe-to-PCI bridge */
+			iommu_detach_dev(iommu,
+				tmp->subordinate->number, 0);
+		else /* this is a legacy PCI bridge */
+			iommu_detach_dev(iommu, tmp->bus->number,
+					 tmp->devfn);
+	}
+}
+
+static void domain_remove_one_dev_info(struct dmar_domain *domain,
+					  struct pci_dev *pdev)
+{
+	struct device_domain_info *info;
+	struct intel_iommu *iommu;
+	unsigned long flags;
+	int found = 0;
+	struct list_head *entry, *tmp;
+
+	iommu = device_to_iommu(pci_domain_nr(pdev->bus), pdev->bus->number,
+				pdev->devfn);
+	if (!iommu)
+		return;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	list_for_each_safe(entry, tmp, &domain->devices) {
+		info = list_entry(entry, struct device_domain_info, link);
+		if (info->segment == pci_domain_nr(pdev->bus) &&
+		    info->bus == pdev->bus->number &&
+		    info->devfn == pdev->devfn) {
+			list_del(&info->link);
+			list_del(&info->global);
+			if (info->dev)
+				info->dev->dev.archdata.iommu = NULL;
+			spin_unlock_irqrestore(&device_domain_lock, flags);
+
+			iommu_disable_dev_iotlb(info);
+			iommu_detach_dev(iommu, info->bus, info->devfn);
+			iommu_detach_dependent_devices(iommu, pdev);
+			free_devinfo_mem(info);
+
+			spin_lock_irqsave(&device_domain_lock, flags);
+
+			if (found)
+				break;
+			else
+				continue;
+		}
+
+		/* if there is no other devices under the same iommu
+		 * owned by this domain, clear this iommu in iommu_bmp
+		 * update iommu count and coherency
+		 */
+		if (iommu == device_to_iommu(info->segment, info->bus,
+					    info->devfn))
+			found = 1;
+	}
+
+	if (found == 0) {
+		unsigned long tmp_flags;
+		spin_lock_irqsave(&domain->iommu_lock, tmp_flags);
+		clear_bit(iommu->seq_id, &domain->iommu_bmp);
+		domain->iommu_count--;
+		domain_update_iommu_cap(domain);
+		spin_unlock_irqrestore(&domain->iommu_lock, tmp_flags);
+
+		if (!(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) &&
+		    !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY)) {
+			spin_lock_irqsave(&iommu->lock, tmp_flags);
+			clear_bit(domain->id, iommu->domain_ids);
+			iommu->domains[domain->id] = NULL;
+			spin_unlock_irqrestore(&iommu->lock, tmp_flags);
+		}
+	}
+
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+}
+
+static void vm_domain_remove_all_dev_info(struct dmar_domain *domain)
+{
+	struct device_domain_info *info;
+	struct intel_iommu *iommu;
+	unsigned long flags1, flags2;
+
+	spin_lock_irqsave(&device_domain_lock, flags1);
+	while (!list_empty(&domain->devices)) {
+		info = list_entry(domain->devices.next,
+			struct device_domain_info, link);
+		list_del(&info->link);
+		list_del(&info->global);
+		if (info->dev)
+			info->dev->dev.archdata.iommu = NULL;
+
+		spin_unlock_irqrestore(&device_domain_lock, flags1);
+
+		iommu_disable_dev_iotlb(info);
+		iommu = device_to_iommu(info->segment, info->bus, info->devfn);
+		iommu_detach_dev(iommu, info->bus, info->devfn);
+		iommu_detach_dependent_devices(iommu, info->dev);
+
+		/* clear this iommu in iommu_bmp, update iommu count
+		 * and capabilities
+		 */
+		spin_lock_irqsave(&domain->iommu_lock, flags2);
+		if (test_and_clear_bit(iommu->seq_id,
+				       &domain->iommu_bmp)) {
+			domain->iommu_count--;
+			domain_update_iommu_cap(domain);
+		}
+		spin_unlock_irqrestore(&domain->iommu_lock, flags2);
+
+		free_devinfo_mem(info);
+		spin_lock_irqsave(&device_domain_lock, flags1);
+	}
+	spin_unlock_irqrestore(&device_domain_lock, flags1);
+}
+
+/* domain id for virtual machine, it won't be set in context */
+static unsigned long vm_domid;
+
+static struct dmar_domain *iommu_alloc_vm_domain(void)
+{
+	struct dmar_domain *domain;
+
+	domain = alloc_domain_mem();
+	if (!domain)
+		return NULL;
+
+	domain->id = vm_domid++;
+	domain->nid = -1;
+	memset(&domain->iommu_bmp, 0, sizeof(unsigned long));
+	domain->flags = DOMAIN_FLAG_VIRTUAL_MACHINE;
+
+	return domain;
+}
+
+static int md_domain_init(struct dmar_domain *domain, int guest_width)
+{
+	int adjust_width;
+
+	init_iova_domain(&domain->iovad, DMA_32BIT_PFN);
+	spin_lock_init(&domain->iommu_lock);
+
+	domain_reserve_special_ranges(domain);
+
+	/* calculate AGAW */
+	domain->gaw = guest_width;
+	adjust_width = guestwidth_to_adjustwidth(guest_width);
+	domain->agaw = width_to_agaw(adjust_width);
+
+	INIT_LIST_HEAD(&domain->devices);
+
+	domain->iommu_count = 0;
+	domain->iommu_coherency = 0;
+	domain->iommu_snooping = 0;
+	domain->iommu_superpage = 0;
+	domain->max_addr = 0;
+	domain->nid = -1;
+
+	/* always allocate the top pgd */
+	domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid);
+	if (!domain->pgd)
+		return -ENOMEM;
+	domain_flush_cache(domain, domain->pgd, PAGE_SIZE);
+	return 0;
+}
+
+static void iommu_free_vm_domain(struct dmar_domain *domain)
+{
+	unsigned long flags;
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	unsigned long i;
+	unsigned long ndomains;
+
+	for_each_drhd_unit(drhd) {
+		if (drhd->ignored)
+			continue;
+		iommu = drhd->iommu;
+
+		ndomains = cap_ndoms(iommu->cap);
+		for_each_set_bit(i, iommu->domain_ids, ndomains) {
+			if (iommu->domains[i] == domain) {
+				spin_lock_irqsave(&iommu->lock, flags);
+				clear_bit(i, iommu->domain_ids);
+				iommu->domains[i] = NULL;
+				spin_unlock_irqrestore(&iommu->lock, flags);
+				break;
+			}
+		}
+	}
+}
+
+static void vm_domain_exit(struct dmar_domain *domain)
+{
+	/* Domain 0 is reserved, so dont process it */
+	if (!domain)
+		return;
+
+	vm_domain_remove_all_dev_info(domain);
+	/* destroy iovas */
+	put_iova_domain(&domain->iovad);
+
+	/* clear ptes */
+	dma_pte_clear_range(domain, 0, DOMAIN_MAX_PFN(domain->gaw));
+
+	/* free page tables */
+	dma_pte_free_pagetable(domain, 0, DOMAIN_MAX_PFN(domain->gaw));
+
+	iommu_free_vm_domain(domain);
+	free_domain_mem(domain);
+}
+
+static int intel_iommu_domain_init(struct iommu_domain *domain)
+{
+	struct dmar_domain *dmar_domain;
+
+	dmar_domain = iommu_alloc_vm_domain();
+	if (!dmar_domain) {
+		printk(KERN_ERR
+			"intel_iommu_domain_init: dmar_domain == NULL\n");
+		return -ENOMEM;
+	}
+	if (md_domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
+		printk(KERN_ERR
+			"intel_iommu_domain_init() failed\n");
+		vm_domain_exit(dmar_domain);
+		return -ENOMEM;
+	}
+	domain_update_iommu_cap(dmar_domain);
+	domain->priv = dmar_domain;
+
+	return 0;
+}
+
+static void intel_iommu_domain_destroy(struct iommu_domain *domain)
+{
+	struct dmar_domain *dmar_domain = domain->priv;
+
+	domain->priv = NULL;
+	vm_domain_exit(dmar_domain);
+}
+
+static int intel_iommu_attach_device(struct iommu_domain *domain,
+				     struct device *dev)
+{
+	struct dmar_domain *dmar_domain = domain->priv;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct intel_iommu *iommu;
+	int addr_width;
+
+	/* normally pdev is not mapped */
+	if (unlikely(domain_context_mapped(pdev))) {
+		struct dmar_domain *old_domain;
+
+		old_domain = find_domain(pdev);
+		if (old_domain) {
+			if (dmar_domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE ||
+			    dmar_domain->flags & DOMAIN_FLAG_STATIC_IDENTITY)
+				domain_remove_one_dev_info(old_domain, pdev);
+			else
+				domain_remove_dev_info(old_domain);
+		}
+	}
+
+	iommu = device_to_iommu(pci_domain_nr(pdev->bus), pdev->bus->number,
+				pdev->devfn);
+	if (!iommu)
+		return -ENODEV;
+
+	/* check if this iommu agaw is sufficient for max mapped address */
+	addr_width = agaw_to_width(iommu->agaw);
+	if (addr_width > cap_mgaw(iommu->cap))
+		addr_width = cap_mgaw(iommu->cap);
+
+	if (dmar_domain->max_addr > (1LL << addr_width)) {
+		printk(KERN_ERR "%s: iommu width (%d) is not "
+		       "sufficient for the mapped address (%llx)\n",
+		       __func__, addr_width, dmar_domain->max_addr);
+		return -EFAULT;
+	}
+	dmar_domain->gaw = addr_width;
+
+	/*
+	 * Knock out extra levels of page tables if necessary
+	 */
+	while (iommu->agaw < dmar_domain->agaw) {
+		struct dma_pte *pte;
+
+		pte = dmar_domain->pgd;
+		if (dma_pte_present(pte)) {
+			dmar_domain->pgd = (struct dma_pte *)
+				phys_to_virt(dma_pte_addr(pte));
+			free_pgtable_page(pte);
+		}
+		dmar_domain->agaw--;
+	}
+
+	return domain_add_dev_info(dmar_domain, pdev, CONTEXT_TT_MULTI_LEVEL);
+}
+
+static void intel_iommu_detach_device(struct iommu_domain *domain,
+				      struct device *dev)
+{
+	struct dmar_domain *dmar_domain = domain->priv;
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	domain_remove_one_dev_info(dmar_domain, pdev);
+}
+
+static int intel_iommu_map(struct iommu_domain *domain,
+			   unsigned long iova, phys_addr_t hpa,
+			   int gfp_order, int iommu_prot)
+{
+	struct dmar_domain *dmar_domain = domain->priv;
+	u64 max_addr;
+	int prot = 0;
+	size_t size;
+	int ret;
+
+	if (iommu_prot & IOMMU_READ)
+		prot |= DMA_PTE_READ;
+	if (iommu_prot & IOMMU_WRITE)
+		prot |= DMA_PTE_WRITE;
+	if ((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping)
+		prot |= DMA_PTE_SNP;
+
+	size     = PAGE_SIZE << gfp_order;
+	max_addr = iova + size;
+	if (dmar_domain->max_addr < max_addr) {
+		u64 end;
+
+		/* check if minimum agaw is sufficient for mapped address */
+		end = __DOMAIN_MAX_ADDR(dmar_domain->gaw) + 1;
+		if (end < max_addr) {
+			printk(KERN_ERR "%s: iommu width (%d) is not "
+			       "sufficient for the mapped address (%llx)\n",
+			       __func__, dmar_domain->gaw, max_addr);
+			return -EFAULT;
+		}
+		dmar_domain->max_addr = max_addr;
+	}
+	/* Round up size to next multiple of PAGE_SIZE, if it and
+	   the low bits of hpa would take us onto the next page */
+	size = aligned_nrpages(hpa, size);
+	ret = domain_pfn_mapping(dmar_domain, iova >> VTD_PAGE_SHIFT,
+				 hpa >> VTD_PAGE_SHIFT, size, prot);
+	return ret;
+}
+
+static int intel_iommu_unmap(struct iommu_domain *domain,
+			     unsigned long iova, int gfp_order)
+{
+	struct dmar_domain *dmar_domain = domain->priv;
+	size_t size = PAGE_SIZE << gfp_order;
+	int order;
+
+	order = dma_pte_clear_range(dmar_domain, iova >> VTD_PAGE_SHIFT,
+			    (iova + size - 1) >> VTD_PAGE_SHIFT);
+
+	if (dmar_domain->max_addr == iova + size)
+		dmar_domain->max_addr = iova;
+
+	return order;
+}
+
+static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
+					    unsigned long iova)
+{
+	struct dmar_domain *dmar_domain = domain->priv;
+	struct dma_pte *pte;
+	u64 phys = 0;
+
+	pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, 0);
+	if (pte)
+		phys = dma_pte_addr(pte);
+
+	return phys;
+}
+
+static int intel_iommu_domain_has_cap(struct iommu_domain *domain,
+				      unsigned long cap)
+{
+	struct dmar_domain *dmar_domain = domain->priv;
+
+	if (cap == IOMMU_CAP_CACHE_COHERENCY)
+		return dmar_domain->iommu_snooping;
+	if (cap == IOMMU_CAP_INTR_REMAP)
+		return intr_remapping_enabled;
+
+	return 0;
+}
+
+static struct iommu_ops intel_iommu_ops = {
+	.domain_init	= intel_iommu_domain_init,
+	.domain_destroy = intel_iommu_domain_destroy,
+	.attach_dev	= intel_iommu_attach_device,
+	.detach_dev	= intel_iommu_detach_device,
+	.map		= intel_iommu_map,
+	.unmap		= intel_iommu_unmap,
+	.iova_to_phys	= intel_iommu_iova_to_phys,
+	.domain_has_cap = intel_iommu_domain_has_cap,
+};
+
+static void __devinit quirk_iommu_rwbf(struct pci_dev *dev)
+{
+	/*
+	 * Mobile 4 Series Chipset neglects to set RWBF capability,
+	 * but needs it:
+	 */
+	printk(KERN_INFO "DMAR: Forcing write-buffer flush capability\n");
+	rwbf_quirk = 1;
+
+	/* https://bugzilla.redhat.com/show_bug.cgi?id=538163 */
+	if (dev->revision == 0x07) {
+		printk(KERN_INFO "DMAR: Disabling IOMMU for graphics on this chipset\n");
+		dmar_map_gfx = 0;
+	}
+}
+
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_rwbf);
+
+#define GGC 0x52
+#define GGC_MEMORY_SIZE_MASK	(0xf << 8)
+#define GGC_MEMORY_SIZE_NONE	(0x0 << 8)
+#define GGC_MEMORY_SIZE_1M	(0x1 << 8)
+#define GGC_MEMORY_SIZE_2M	(0x3 << 8)
+#define GGC_MEMORY_VT_ENABLED	(0x8 << 8)
+#define GGC_MEMORY_SIZE_2M_VT	(0x9 << 8)
+#define GGC_MEMORY_SIZE_3M_VT	(0xa << 8)
+#define GGC_MEMORY_SIZE_4M_VT	(0xb << 8)
+
+static void __devinit quirk_calpella_no_shadow_gtt(struct pci_dev *dev)
+{
+	unsigned short ggc;
+
+	if (pci_read_config_word(dev, GGC, &ggc))
+		return;
+
+	if (!(ggc & GGC_MEMORY_VT_ENABLED)) {
+		printk(KERN_INFO "DMAR: BIOS has allocated no shadow GTT; disabling IOMMU for graphics\n");
+		dmar_map_gfx = 0;
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0040, quirk_calpella_no_shadow_gtt);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_calpella_no_shadow_gtt);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0062, quirk_calpella_no_shadow_gtt);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x006a, quirk_calpella_no_shadow_gtt);
+
+/* On Tylersburg chipsets, some BIOSes have been known to enable the
+   ISOCH DMAR unit for the Azalia sound device, but not give it any
+   TLB entries, which causes it to deadlock. Check for that.  We do
+   this in a function called from init_dmars(), instead of in a PCI
+   quirk, because we don't want to print the obnoxious "BIOS broken"
+   message if VT-d is actually disabled.
+*/
+static void __init check_tylersburg_isoch(void)
+{
+	struct pci_dev *pdev;
+	uint32_t vtisochctrl;
+
+	/* If there's no Azalia in the system anyway, forget it. */
+	pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x3a3e, NULL);
+	if (!pdev)
+		return;
+	pci_dev_put(pdev);
+
+	/* System Management Registers. Might be hidden, in which case
+	   we can't do the sanity check. But that's OK, because the
+	   known-broken BIOSes _don't_ actually hide it, so far. */
+	pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x342e, NULL);
+	if (!pdev)
+		return;
+
+	if (pci_read_config_dword(pdev, 0x188, &vtisochctrl)) {
+		pci_dev_put(pdev);
+		return;
+	}
+
+	pci_dev_put(pdev);
+
+	/* If Azalia DMA is routed to the non-isoch DMAR unit, fine. */
+	if (vtisochctrl & 1)
+		return;
+
+	/* Drop all bits other than the number of TLB entries */
+	vtisochctrl &= 0x1c;
+
+	/* If we have the recommended number of TLB entries (16), fine. */
+	if (vtisochctrl == 0x10)
+		return;
+
+	/* Zero TLB entries? You get to ride the short bus to school. */
+	if (!vtisochctrl) {
+		WARN(1, "Your BIOS is broken; DMA routed to ISOCH DMAR unit but no TLB space.\n"
+		     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+		     dmi_get_system_info(DMI_BIOS_VENDOR),
+		     dmi_get_system_info(DMI_BIOS_VERSION),
+		     dmi_get_system_info(DMI_PRODUCT_VERSION));
+		iommu_identity_mapping |= IDENTMAP_AZALIA;
+		return;
+	}
+	
+	printk(KERN_WARNING "DMAR: Recommended TLB entries for ISOCH unit is 16; your BIOS set %d\n",
+	       vtisochctrl);
+}
diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
new file mode 100644
index 00000000..3607faf2
--- /dev/null
+++ b/drivers/pci/intr_remapping.c
@@ -0,0 +1,798 @@
+#include <linux/interrupt.h>
+#include <linux/dmar.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/jiffies.h>
+#include <linux/hpet.h>
+#include <linux/pci.h>
+#include <linux/irq.h>
+#include <asm/io_apic.h>
+#include <asm/smp.h>
+#include <asm/cpu.h>
+#include <linux/intel-iommu.h>
+#include "intr_remapping.h"
+#include <acpi/acpi.h>
+#include <asm/pci-direct.h>
+#include "pci.h"
+
+static struct ioapic_scope ir_ioapic[MAX_IO_APICS];
+static struct hpet_scope ir_hpet[MAX_HPET_TBS];
+static int ir_ioapic_num, ir_hpet_num;
+int intr_remapping_enabled;
+
+static int disable_intremap;
+static int disable_sourceid_checking;
+
+static __init int setup_nointremap(char *str)
+{
+	disable_intremap = 1;
+	return 0;
+}
+early_param("nointremap", setup_nointremap);
+
+static __init int setup_intremap(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!strncmp(str, "on", 2))
+		disable_intremap = 0;
+	else if (!strncmp(str, "off", 3))
+		disable_intremap = 1;
+	else if (!strncmp(str, "nosid", 5))
+		disable_sourceid_checking = 1;
+
+	return 0;
+}
+early_param("intremap", setup_intremap);
+
+static DEFINE_SPINLOCK(irq_2_ir_lock);
+
+static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
+{
+	struct irq_cfg *cfg = irq_get_chip_data(irq);
+	return cfg ? &cfg->irq_2_iommu : NULL;
+}
+
+int get_irte(int irq, struct irte *entry)
+{
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	unsigned long flags;
+	int index;
+
+	if (!entry || !irq_iommu)
+		return -1;
+
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
+
+	index = irq_iommu->irte_index + irq_iommu->sub_handle;
+	*entry = *(irq_iommu->iommu->ir_table->base + index);
+
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+	return 0;
+}
+
+int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
+{
+	struct ir_table *table = iommu->ir_table;
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	u16 index, start_index;
+	unsigned int mask = 0;
+	unsigned long flags;
+	int i;
+
+	if (!count || !irq_iommu)
+		return -1;
+
+	/*
+	 * start the IRTE search from index 0.
+	 */
+	index = start_index = 0;
+
+	if (count > 1) {
+		count = __roundup_pow_of_two(count);
+		mask = ilog2(count);
+	}
+
+	if (mask > ecap_max_handle_mask(iommu->ecap)) {
+		printk(KERN_ERR
+		       "Requested mask %x exceeds the max invalidation handle"
+		       " mask value %Lx\n", mask,
+		       ecap_max_handle_mask(iommu->ecap));
+		return -1;
+	}
+
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
+	do {
+		for (i = index; i < index + count; i++)
+			if  (table->base[i].present)
+				break;
+		/* empty index found */
+		if (i == index + count)
+			break;
+
+		index = (index + count) % INTR_REMAP_TABLE_ENTRIES;
+
+		if (index == start_index) {
+			spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+			printk(KERN_ERR "can't allocate an IRTE\n");
+			return -1;
+		}
+	} while (1);
+
+	for (i = index; i < index + count; i++)
+		table->base[i].present = 1;
+
+	irq_iommu->iommu = iommu;
+	irq_iommu->irte_index =  index;
+	irq_iommu->sub_handle = 0;
+	irq_iommu->irte_mask = mask;
+
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+
+	return index;
+}
+
+static int qi_flush_iec(struct intel_iommu *iommu, int index, int mask)
+{
+	struct qi_desc desc;
+
+	desc.low = QI_IEC_IIDEX(index) | QI_IEC_TYPE | QI_IEC_IM(mask)
+		   | QI_IEC_SELECTIVE;
+	desc.high = 0;
+
+	return qi_submit_sync(&desc, iommu);
+}
+
+int map_irq_to_irte_handle(int irq, u16 *sub_handle)
+{
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	unsigned long flags;
+	int index;
+
+	if (!irq_iommu)
+		return -1;
+
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
+	*sub_handle = irq_iommu->sub_handle;
+	index = irq_iommu->irte_index;
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+	return index;
+}
+
+int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
+{
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	unsigned long flags;
+
+	if (!irq_iommu)
+		return -1;
+
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
+
+	irq_iommu->iommu = iommu;
+	irq_iommu->irte_index = index;
+	irq_iommu->sub_handle = subhandle;
+	irq_iommu->irte_mask = 0;
+
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+
+	return 0;
+}
+
+int modify_irte(int irq, struct irte *irte_modified)
+{
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	struct intel_iommu *iommu;
+	unsigned long flags;
+	struct irte *irte;
+	int rc, index;
+
+	if (!irq_iommu)
+		return -1;
+
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
+
+	iommu = irq_iommu->iommu;
+
+	index = irq_iommu->irte_index + irq_iommu->sub_handle;
+	irte = &iommu->ir_table->base[index];
+
+	set_64bit(&irte->low, irte_modified->low);
+	set_64bit(&irte->high, irte_modified->high);
+	__iommu_flush_cache(iommu, irte, sizeof(*irte));
+
+	rc = qi_flush_iec(iommu, index, 0);
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+
+	return rc;
+}
+
+struct intel_iommu *map_hpet_to_ir(u8 hpet_id)
+{
+	int i;
+
+	for (i = 0; i < MAX_HPET_TBS; i++)
+		if (ir_hpet[i].id == hpet_id)
+			return ir_hpet[i].iommu;
+	return NULL;
+}
+
+struct intel_iommu *map_ioapic_to_ir(int apic)
+{
+	int i;
+
+	for (i = 0; i < MAX_IO_APICS; i++)
+		if (ir_ioapic[i].id == apic)
+			return ir_ioapic[i].iommu;
+	return NULL;
+}
+
+struct intel_iommu *map_dev_to_ir(struct pci_dev *dev)
+{
+	struct dmar_drhd_unit *drhd;
+
+	drhd = dmar_find_matched_drhd_unit(dev);
+	if (!drhd)
+		return NULL;
+
+	return drhd->iommu;
+}
+
+static int clear_entries(struct irq_2_iommu *irq_iommu)
+{
+	struct irte *start, *entry, *end;
+	struct intel_iommu *iommu;
+	int index;
+
+	if (irq_iommu->sub_handle)
+		return 0;
+
+	iommu = irq_iommu->iommu;
+	index = irq_iommu->irte_index + irq_iommu->sub_handle;
+
+	start = iommu->ir_table->base + index;
+	end = start + (1 << irq_iommu->irte_mask);
+
+	for (entry = start; entry < end; entry++) {
+		set_64bit(&entry->low, 0);
+		set_64bit(&entry->high, 0);
+	}
+
+	return qi_flush_iec(iommu, index, irq_iommu->irte_mask);
+}
+
+int free_irte(int irq)
+{
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	unsigned long flags;
+	int rc;
+
+	if (!irq_iommu)
+		return -1;
+
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
+
+	rc = clear_entries(irq_iommu);
+
+	irq_iommu->iommu = NULL;
+	irq_iommu->irte_index = 0;
+	irq_iommu->sub_handle = 0;
+	irq_iommu->irte_mask = 0;
+
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+
+	return rc;
+}
+
+/*
+ * source validation type
+ */
+#define SVT_NO_VERIFY		0x0  /* no verification is required */
+#define SVT_VERIFY_SID_SQ	0x1  /* verify using SID and SQ fields */
+#define SVT_VERIFY_BUS		0x2  /* verify bus of request-id */
+
+/*
+ * source-id qualifier
+ */
+#define SQ_ALL_16	0x0  /* verify all 16 bits of request-id */
+#define SQ_13_IGNORE_1	0x1  /* verify most significant 13 bits, ignore
+			      * the third least significant bit
+			      */
+#define SQ_13_IGNORE_2	0x2  /* verify most significant 13 bits, ignore
+			      * the second and third least significant bits
+			      */
+#define SQ_13_IGNORE_3	0x3  /* verify most significant 13 bits, ignore
+			      * the least three significant bits
+			      */
+
+/*
+ * set SVT, SQ and SID fields of irte to verify
+ * source ids of interrupt requests
+ */
+static void set_irte_sid(struct irte *irte, unsigned int svt,
+			 unsigned int sq, unsigned int sid)
+{
+	if (disable_sourceid_checking)
+		svt = SVT_NO_VERIFY;
+	irte->svt = svt;
+	irte->sq = sq;
+	irte->sid = sid;
+}
+
+int set_ioapic_sid(struct irte *irte, int apic)
+{
+	int i;
+	u16 sid = 0;
+
+	if (!irte)
+		return -1;
+
+	for (i = 0; i < MAX_IO_APICS; i++) {
+		if (ir_ioapic[i].id == apic) {
+			sid = (ir_ioapic[i].bus << 8) | ir_ioapic[i].devfn;
+			break;
+		}
+	}
+
+	if (sid == 0) {
+		pr_warning("Failed to set source-id of IOAPIC (%d)\n", apic);
+		return -1;
+	}
+
+	set_irte_sid(irte, 1, 0, sid);
+
+	return 0;
+}
+
+int set_hpet_sid(struct irte *irte, u8 id)
+{
+	int i;
+	u16 sid = 0;
+
+	if (!irte)
+		return -1;
+
+	for (i = 0; i < MAX_HPET_TBS; i++) {
+		if (ir_hpet[i].id == id) {
+			sid = (ir_hpet[i].bus << 8) | ir_hpet[i].devfn;
+			break;
+		}
+	}
+
+	if (sid == 0) {
+		pr_warning("Failed to set source-id of HPET block (%d)\n", id);
+		return -1;
+	}
+
+	/*
+	 * Should really use SQ_ALL_16. Some platforms are broken.
+	 * While we figure out the right quirks for these broken platforms, use
+	 * SQ_13_IGNORE_3 for now.
+	 */
+	set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_13_IGNORE_3, sid);
+
+	return 0;
+}
+
+int set_msi_sid(struct irte *irte, struct pci_dev *dev)
+{
+	struct pci_dev *bridge;
+
+	if (!irte || !dev)
+		return -1;
+
+	/* PCIe device or Root Complex integrated PCI device */
+	if (pci_is_pcie(dev) || !dev->bus->parent) {
+		set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16,
+			     (dev->bus->number << 8) | dev->devfn);
+		return 0;
+	}
+
+	bridge = pci_find_upstream_pcie_bridge(dev);
+	if (bridge) {
+		if (pci_is_pcie(bridge))/* this is a PCIe-to-PCI/PCIX bridge */
+			set_irte_sid(irte, SVT_VERIFY_BUS, SQ_ALL_16,
+				(bridge->bus->number << 8) | dev->bus->number);
+		else /* this is a legacy PCI bridge */
+			set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16,
+				(bridge->bus->number << 8) | bridge->devfn);
+	}
+
+	return 0;
+}
+
+static void iommu_set_intr_remapping(struct intel_iommu *iommu, int mode)
+{
+	u64 addr;
+	u32 sts;
+	unsigned long flags;
+
+	addr = virt_to_phys((void *)iommu->ir_table->base);
+
+	spin_lock_irqsave(&iommu->register_lock, flags);
+
+	dmar_writeq(iommu->reg + DMAR_IRTA_REG,
+		    (addr) | IR_X2APIC_MODE(mode) | INTR_REMAP_TABLE_REG_SIZE);
+
+	/* Set interrupt-remapping table pointer */
+	iommu->gcmd |= DMA_GCMD_SIRTP;
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, (sts & DMA_GSTS_IRTPS), sts);
+	spin_unlock_irqrestore(&iommu->register_lock, flags);
+
+	/*
+	 * global invalidation of interrupt entry cache before enabling
+	 * interrupt-remapping.
+	 */
+	qi_global_iec(iommu);
+
+	spin_lock_irqsave(&iommu->register_lock, flags);
+
+	/* Enable interrupt-remapping */
+	iommu->gcmd |= DMA_GCMD_IRE;
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, (sts & DMA_GSTS_IRES), sts);
+
+	spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
+
+static int setup_intr_remapping(struct intel_iommu *iommu, int mode)
+{
+	struct ir_table *ir_table;
+	struct page *pages;
+
+	ir_table = iommu->ir_table = kzalloc(sizeof(struct ir_table),
+					     GFP_ATOMIC);
+
+	if (!iommu->ir_table)
+		return -ENOMEM;
+
+	pages = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO,
+				 INTR_REMAP_PAGE_ORDER);
+
+	if (!pages) {
+		printk(KERN_ERR "failed to allocate pages of order %d\n",
+		       INTR_REMAP_PAGE_ORDER);
+		kfree(iommu->ir_table);
+		return -ENOMEM;
+	}
+
+	ir_table->base = page_address(pages);
+
+	iommu_set_intr_remapping(iommu, mode);
+	return 0;
+}
+
+/*
+ * Disable Interrupt Remapping.
+ */
+static void iommu_disable_intr_remapping(struct intel_iommu *iommu)
+{
+	unsigned long flags;
+	u32 sts;
+
+	if (!ecap_ir_support(iommu->ecap))
+		return;
+
+	/*
+	 * global invalidation of interrupt entry cache before disabling
+	 * interrupt-remapping.
+	 */
+	qi_global_iec(iommu);
+
+	spin_lock_irqsave(&iommu->register_lock, flags);
+
+	sts = dmar_readq(iommu->reg + DMAR_GSTS_REG);
+	if (!(sts & DMA_GSTS_IRES))
+		goto end;
+
+	iommu->gcmd &= ~DMA_GCMD_IRE;
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, !(sts & DMA_GSTS_IRES), sts);
+
+end:
+	spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
+int __init intr_remapping_supported(void)
+{
+	struct dmar_drhd_unit *drhd;
+
+	if (disable_intremap)
+		return 0;
+
+	if (!dmar_ir_support())
+		return 0;
+
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		if (!ecap_ir_support(iommu->ecap))
+			return 0;
+	}
+
+	return 1;
+}
+
+int __init enable_intr_remapping(int eim)
+{
+	struct dmar_drhd_unit *drhd;
+	int setup = 0;
+
+	if (parse_ioapics_under_ir() != 1) {
+		printk(KERN_INFO "Not enable interrupt remapping\n");
+		return -1;
+	}
+
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		/*
+		 * If the queued invalidation is already initialized,
+		 * shouldn't disable it.
+		 */
+		if (iommu->qi)
+			continue;
+
+		/*
+		 * Clear previous faults.
+		 */
+		dmar_fault(-1, iommu);
+
+		/*
+		 * Disable intr remapping and queued invalidation, if already
+		 * enabled prior to OS handover.
+		 */
+		iommu_disable_intr_remapping(iommu);
+
+		dmar_disable_qi(iommu);
+	}
+
+	/*
+	 * check for the Interrupt-remapping support
+	 */
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		if (eim && !ecap_eim_support(iommu->ecap)) {
+			printk(KERN_INFO "DRHD %Lx: EIM not supported by DRHD, "
+			       " ecap %Lx\n", drhd->reg_base_addr, iommu->ecap);
+			return -1;
+		}
+	}
+
+	/*
+	 * Enable queued invalidation for all the DRHD's.
+	 */
+	for_each_drhd_unit(drhd) {
+		int ret;
+		struct intel_iommu *iommu = drhd->iommu;
+		ret = dmar_enable_qi(iommu);
+
+		if (ret) {
+			printk(KERN_ERR "DRHD %Lx: failed to enable queued, "
+			       " invalidation, ecap %Lx, ret %d\n",
+			       drhd->reg_base_addr, iommu->ecap, ret);
+			return -1;
+		}
+	}
+
+	/*
+	 * Setup Interrupt-remapping for all the DRHD's now.
+	 */
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		if (setup_intr_remapping(iommu, eim))
+			goto error;
+
+		setup = 1;
+	}
+
+	if (!setup)
+		goto error;
+
+	intr_remapping_enabled = 1;
+
+	return 0;
+
+error:
+	/*
+	 * handle error condition gracefully here!
+	 */
+	return -1;
+}
+
+static void ir_parse_one_hpet_scope(struct acpi_dmar_device_scope *scope,
+				      struct intel_iommu *iommu)
+{
+	struct acpi_dmar_pci_path *path;
+	u8 bus;
+	int count;
+
+	bus = scope->bus;
+	path = (struct acpi_dmar_pci_path *)(scope + 1);
+	count = (scope->length - sizeof(struct acpi_dmar_device_scope))
+		/ sizeof(struct acpi_dmar_pci_path);
+
+	while (--count > 0) {
+		/*
+		 * Access PCI directly due to the PCI
+		 * subsystem isn't initialized yet.
+		 */
+		bus = read_pci_config_byte(bus, path->dev, path->fn,
+					   PCI_SECONDARY_BUS);
+		path++;
+	}
+	ir_hpet[ir_hpet_num].bus   = bus;
+	ir_hpet[ir_hpet_num].devfn = PCI_DEVFN(path->dev, path->fn);
+	ir_hpet[ir_hpet_num].iommu = iommu;
+	ir_hpet[ir_hpet_num].id    = scope->enumeration_id;
+	ir_hpet_num++;
+}
+
+static void ir_parse_one_ioapic_scope(struct acpi_dmar_device_scope *scope,
+				      struct intel_iommu *iommu)
+{
+	struct acpi_dmar_pci_path *path;
+	u8 bus;
+	int count;
+
+	bus = scope->bus;
+	path = (struct acpi_dmar_pci_path *)(scope + 1);
+	count = (scope->length - sizeof(struct acpi_dmar_device_scope))
+		/ sizeof(struct acpi_dmar_pci_path);
+
+	while (--count > 0) {
+		/*
+		 * Access PCI directly due to the PCI
+		 * subsystem isn't initialized yet.
+		 */
+		bus = read_pci_config_byte(bus, path->dev, path->fn,
+					   PCI_SECONDARY_BUS);
+		path++;
+	}
+
+	ir_ioapic[ir_ioapic_num].bus   = bus;
+	ir_ioapic[ir_ioapic_num].devfn = PCI_DEVFN(path->dev, path->fn);
+	ir_ioapic[ir_ioapic_num].iommu = iommu;
+	ir_ioapic[ir_ioapic_num].id    = scope->enumeration_id;
+	ir_ioapic_num++;
+}
+
+static int ir_parse_ioapic_hpet_scope(struct acpi_dmar_header *header,
+				      struct intel_iommu *iommu)
+{
+	struct acpi_dmar_hardware_unit *drhd;
+	struct acpi_dmar_device_scope *scope;
+	void *start, *end;
+
+	drhd = (struct acpi_dmar_hardware_unit *)header;
+
+	start = (void *)(drhd + 1);
+	end = ((void *)drhd) + header->length;
+
+	while (start < end) {
+		scope = start;
+		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_IOAPIC) {
+			if (ir_ioapic_num == MAX_IO_APICS) {
+				printk(KERN_WARNING "Exceeded Max IO APICS\n");
+				return -1;
+			}
+
+			printk(KERN_INFO "IOAPIC id %d under DRHD base "
+			       " 0x%Lx IOMMU %d\n", scope->enumeration_id,
+			       drhd->address, iommu->seq_id);
+
+			ir_parse_one_ioapic_scope(scope, iommu);
+		} else if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_HPET) {
+			if (ir_hpet_num == MAX_HPET_TBS) {
+				printk(KERN_WARNING "Exceeded Max HPET blocks\n");
+				return -1;
+			}
+
+			printk(KERN_INFO "HPET id %d under DRHD base"
+			       " 0x%Lx\n", scope->enumeration_id,
+			       drhd->address);
+
+			ir_parse_one_hpet_scope(scope, iommu);
+		}
+		start += scope->length;
+	}
+
+	return 0;
+}
+
+/*
+ * Finds the assocaition between IOAPIC's and its Interrupt-remapping
+ * hardware unit.
+ */
+int __init parse_ioapics_under_ir(void)
+{
+	struct dmar_drhd_unit *drhd;
+	int ir_supported = 0;
+
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		if (ecap_ir_support(iommu->ecap)) {
+			if (ir_parse_ioapic_hpet_scope(drhd->hdr, iommu))
+				return -1;
+
+			ir_supported = 1;
+		}
+	}
+
+	if (ir_supported && ir_ioapic_num != nr_ioapics) {
+		printk(KERN_WARNING
+		       "Not all IO-APIC's listed under remapping hardware\n");
+		return -1;
+	}
+
+	return ir_supported;
+}
+
+void disable_intr_remapping(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+
+	/*
+	 * Disable Interrupt-remapping for all the DRHD's now.
+	 */
+	for_each_iommu(iommu, drhd) {
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		iommu_disable_intr_remapping(iommu);
+	}
+}
+
+int reenable_intr_remapping(int eim)
+{
+	struct dmar_drhd_unit *drhd;
+	int setup = 0;
+	struct intel_iommu *iommu = NULL;
+
+	for_each_iommu(iommu, drhd)
+		if (iommu->qi)
+			dmar_reenable_qi(iommu);
+
+	/*
+	 * Setup Interrupt-remapping for all the DRHD's now.
+	 */
+	for_each_iommu(iommu, drhd) {
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		/* Set up interrupt remapping for iommu.*/
+		iommu_set_intr_remapping(iommu, eim);
+		setup = 1;
+	}
+
+	if (!setup)
+		goto error;
+
+	return 0;
+
+error:
+	/*
+	 * handle error condition gracefully here!
+	 */
+	return -1;
+}
+
diff --git a/drivers/pci/intr_remapping.h b/drivers/pci/intr_remapping.h
new file mode 100644
index 00000000..5662fecf
--- /dev/null
+++ b/drivers/pci/intr_remapping.h
@@ -0,0 +1,17 @@
+#include <linux/intel-iommu.h>
+
+struct ioapic_scope {
+	struct intel_iommu *iommu;
+	unsigned int id;
+	unsigned int bus;	/* PCI bus number */
+	unsigned int devfn;	/* PCI devfn number */
+};
+
+struct hpet_scope {
+	struct intel_iommu *iommu;
+	u8 id;
+	unsigned int bus;
+	unsigned int devfn;
+};
+
+#define IR_X2APIC_MODE(mode) (mode ? (1 << 11) : 0)
diff --git a/drivers/pci/ioapic.c b/drivers/pci/ioapic.c
new file mode 100644
index 00000000..203508b2
--- /dev/null
+++ b/drivers/pci/ioapic.c
@@ -0,0 +1,127 @@
+/*
+ * IOAPIC/IOxAPIC/IOSAPIC driver
+ *
+ * Copyright (C) 2009 Fujitsu Limited.
+ * (c) Copyright 2009 Hewlett-Packard Development Company, L.P.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * This driver manages PCI I/O APICs added by hotplug after boot.  We try to
+ * claim all I/O APIC PCI devices, but those present at boot were registered
+ * when we parsed the ACPI MADT, so we'll fail when we try to re-register
+ * them.
+ */
+
+#include <linux/pci.h>
+#include <linux/acpi.h>
+#include <linux/slab.h>
+#include <acpi/acpi_bus.h>
+
+struct ioapic {
+	acpi_handle	handle;
+	u32		gsi_base;
+};
+
+static int ioapic_probe(struct pci_dev *dev, const struct pci_device_id *ent)
+{
+	acpi_handle handle;
+	acpi_status status;
+	unsigned long long gsb;
+	struct ioapic *ioapic;
+	int ret;
+	char *type;
+	struct resource *res;
+
+	handle = DEVICE_ACPI_HANDLE(&dev->dev);
+	if (!handle)
+		return -EINVAL;
+
+	status = acpi_evaluate_integer(handle, "_GSB", NULL, &gsb);
+	if (ACPI_FAILURE(status))
+		return -EINVAL;
+
+	/*
+	 * The previous code in acpiphp evaluated _MAT if _GSB failed, but
+	 * ACPI spec 4.0 sec 6.2.2 requires _GSB for hot-pluggable I/O APICs.
+	 */
+
+	ioapic = kzalloc(sizeof(*ioapic), GFP_KERNEL);
+	if (!ioapic)
+		return -ENOMEM;
+
+	ioapic->handle = handle;
+	ioapic->gsi_base = (u32) gsb;
+
+	if (dev->class == PCI_CLASS_SYSTEM_PIC_IOAPIC)
+		type = "IOAPIC";
+	else
+		type = "IOxAPIC";
+
+	ret = pci_enable_device(dev);
+	if (ret < 0)
+		goto exit_free;
+
+	pci_set_master(dev);
+
+	if (pci_request_region(dev, 0, type))
+		goto exit_disable;
+
+	res = &dev->resource[0];
+	if (acpi_register_ioapic(ioapic->handle, res->start, ioapic->gsi_base))
+		goto exit_release;
+
+	pci_set_drvdata(dev, ioapic);
+	dev_info(&dev->dev, "%s at %pR, GSI %u\n", type, res, ioapic->gsi_base);
+	return 0;
+
+exit_release:
+	pci_release_region(dev, 0);
+exit_disable:
+	pci_disable_device(dev);
+exit_free:
+	kfree(ioapic);
+	return -ENODEV;
+}
+
+static void ioapic_remove(struct pci_dev *dev)
+{
+	struct ioapic *ioapic = pci_get_drvdata(dev);
+
+	acpi_unregister_ioapic(ioapic->handle, ioapic->gsi_base);
+	pci_release_region(dev, 0);
+	pci_disable_device(dev);
+	kfree(ioapic);
+}
+
+
+static struct pci_device_id ioapic_devices[] = {
+	{ PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
+	  PCI_CLASS_SYSTEM_PIC_IOAPIC << 8, 0xffff00, },
+	{ PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
+	  PCI_CLASS_SYSTEM_PIC_IOXAPIC << 8, 0xffff00, },
+	{ }
+};
+
+static struct pci_driver ioapic_driver = {
+	.name		= "ioapic",
+	.id_table	= ioapic_devices,
+	.probe		= ioapic_probe,
+	.remove		= __devexit_p(ioapic_remove),
+};
+
+static int __init ioapic_init(void)
+{
+	return pci_register_driver(&ioapic_driver);
+}
+
+static void __exit ioapic_exit(void)
+{
+	pci_unregister_driver(&ioapic_driver);
+}
+
+module_init(ioapic_init);
+module_exit(ioapic_exit);
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
new file mode 100644
index 00000000..42fae477
--- /dev/null
+++ b/drivers/pci/iov.c
@@ -0,0 +1,866 @@
+/*
+ * drivers/pci/iov.c
+ *
+ * Copyright (C) 2009 Intel Corporation, Yu Zhao <yu.zhao@intel.com>
+ *
+ * PCI Express I/O Virtualization (IOV) support.
+ *   Single Root IOV 1.0
+ *   Address Translation Service 1.0
+ */
+
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <linux/pci-ats.h>
+#include "pci.h"
+
+#define VIRTFN_ID_LEN	16
+
+static inline u8 virtfn_bus(struct pci_dev *dev, int id)
+{
+	return dev->bus->number + ((dev->devfn + dev->sriov->offset +
+				    dev->sriov->stride * id) >> 8);
+}
+
+static inline u8 virtfn_devfn(struct pci_dev *dev, int id)
+{
+	return (dev->devfn + dev->sriov->offset +
+		dev->sriov->stride * id) & 0xff;
+}
+
+static struct pci_bus *virtfn_add_bus(struct pci_bus *bus, int busnr)
+{
+	int rc;
+	struct pci_bus *child;
+
+	if (bus->number == busnr)
+		return bus;
+
+	child = pci_find_bus(pci_domain_nr(bus), busnr);
+	if (child)
+		return child;
+
+	child = pci_add_new_bus(bus, NULL, busnr);
+	if (!child)
+		return NULL;
+
+	child->subordinate = busnr;
+	child->dev.parent = bus->bridge;
+	rc = pci_bus_add_child(child);
+	if (rc) {
+		pci_remove_bus(child);
+		return NULL;
+	}
+
+	return child;
+}
+
+static void virtfn_remove_bus(struct pci_bus *bus, int busnr)
+{
+	struct pci_bus *child;
+
+	if (bus->number == busnr)
+		return;
+
+	child = pci_find_bus(pci_domain_nr(bus), busnr);
+	BUG_ON(!child);
+
+	if (list_empty(&child->devices))
+		pci_remove_bus(child);
+}
+
+static int virtfn_add(struct pci_dev *dev, int id, int reset)
+{
+	int i;
+	int rc;
+	u64 size;
+	char buf[VIRTFN_ID_LEN];
+	struct pci_dev *virtfn;
+	struct resource *res;
+	struct pci_sriov *iov = dev->sriov;
+
+	virtfn = alloc_pci_dev();
+	if (!virtfn)
+		return -ENOMEM;
+
+	mutex_lock(&iov->dev->sriov->lock);
+	virtfn->bus = virtfn_add_bus(dev->bus, virtfn_bus(dev, id));
+	if (!virtfn->bus) {
+		kfree(virtfn);
+		mutex_unlock(&iov->dev->sriov->lock);
+		return -ENOMEM;
+	}
+	virtfn->devfn = virtfn_devfn(dev, id);
+	virtfn->vendor = dev->vendor;
+	pci_read_config_word(dev, iov->pos + PCI_SRIOV_VF_DID, &virtfn->device);
+	pci_setup_device(virtfn);
+	virtfn->dev.parent = dev->dev.parent;
+
+	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+		res = dev->resource + PCI_IOV_RESOURCES + i;
+		if (!res->parent)
+			continue;
+		virtfn->resource[i].name = pci_name(virtfn);
+		virtfn->resource[i].flags = res->flags;
+		size = resource_size(res);
+		do_div(size, iov->total);
+		virtfn->resource[i].start = res->start + size * id;
+		virtfn->resource[i].end = virtfn->resource[i].start + size - 1;
+		rc = request_resource(res, &virtfn->resource[i]);
+		BUG_ON(rc);
+	}
+
+	if (reset)
+		__pci_reset_function(virtfn);
+
+	pci_device_add(virtfn, virtfn->bus);
+	mutex_unlock(&iov->dev->sriov->lock);
+
+	virtfn->physfn = pci_dev_get(dev);
+	virtfn->is_virtfn = 1;
+
+	rc = pci_bus_add_device(virtfn);
+	if (rc)
+		goto failed1;
+	sprintf(buf, "virtfn%u", id);
+	rc = sysfs_create_link(&dev->dev.kobj, &virtfn->dev.kobj, buf);
+	if (rc)
+		goto failed1;
+	rc = sysfs_create_link(&virtfn->dev.kobj, &dev->dev.kobj, "physfn");
+	if (rc)
+		goto failed2;
+
+	kobject_uevent(&virtfn->dev.kobj, KOBJ_CHANGE);
+
+	return 0;
+
+failed2:
+	sysfs_remove_link(&dev->dev.kobj, buf);
+failed1:
+	pci_dev_put(dev);
+	mutex_lock(&iov->dev->sriov->lock);
+	pci_remove_bus_device(virtfn);
+	virtfn_remove_bus(dev->bus, virtfn_bus(dev, id));
+	mutex_unlock(&iov->dev->sriov->lock);
+
+	return rc;
+}
+
+static void virtfn_remove(struct pci_dev *dev, int id, int reset)
+{
+	char buf[VIRTFN_ID_LEN];
+	struct pci_bus *bus;
+	struct pci_dev *virtfn;
+	struct pci_sriov *iov = dev->sriov;
+
+	bus = pci_find_bus(pci_domain_nr(dev->bus), virtfn_bus(dev, id));
+	if (!bus)
+		return;
+
+	virtfn = pci_get_slot(bus, virtfn_devfn(dev, id));
+	if (!virtfn)
+		return;
+
+	pci_dev_put(virtfn);
+
+	if (reset) {
+		device_release_driver(&virtfn->dev);
+		__pci_reset_function(virtfn);
+	}
+
+	sprintf(buf, "virtfn%u", id);
+	sysfs_remove_link(&dev->dev.kobj, buf);
+	sysfs_remove_link(&virtfn->dev.kobj, "physfn");
+
+	mutex_lock(&iov->dev->sriov->lock);
+	pci_remove_bus_device(virtfn);
+	virtfn_remove_bus(dev->bus, virtfn_bus(dev, id));
+	mutex_unlock(&iov->dev->sriov->lock);
+
+	pci_dev_put(dev);
+}
+
+static int sriov_migration(struct pci_dev *dev)
+{
+	u16 status;
+	struct pci_sriov *iov = dev->sriov;
+
+	if (!iov->nr_virtfn)
+		return 0;
+
+	if (!(iov->cap & PCI_SRIOV_CAP_VFM))
+		return 0;
+
+	pci_read_config_word(dev, iov->pos + PCI_SRIOV_STATUS, &status);
+	if (!(status & PCI_SRIOV_STATUS_VFM))
+		return 0;
+
+	schedule_work(&iov->mtask);
+
+	return 1;
+}
+
+static void sriov_migration_task(struct work_struct *work)
+{
+	int i;
+	u8 state;
+	u16 status;
+	struct pci_sriov *iov = container_of(work, struct pci_sriov, mtask);
+
+	for (i = iov->initial; i < iov->nr_virtfn; i++) {
+		state = readb(iov->mstate + i);
+		if (state == PCI_SRIOV_VFM_MI) {
+			writeb(PCI_SRIOV_VFM_AV, iov->mstate + i);
+			state = readb(iov->mstate + i);
+			if (state == PCI_SRIOV_VFM_AV)
+				virtfn_add(iov->self, i, 1);
+		} else if (state == PCI_SRIOV_VFM_MO) {
+			virtfn_remove(iov->self, i, 1);
+			writeb(PCI_SRIOV_VFM_UA, iov->mstate + i);
+			state = readb(iov->mstate + i);
+			if (state == PCI_SRIOV_VFM_AV)
+				virtfn_add(iov->self, i, 0);
+		}
+	}
+
+	pci_read_config_word(iov->self, iov->pos + PCI_SRIOV_STATUS, &status);
+	status &= ~PCI_SRIOV_STATUS_VFM;
+	pci_write_config_word(iov->self, iov->pos + PCI_SRIOV_STATUS, status);
+}
+
+static int sriov_enable_migration(struct pci_dev *dev, int nr_virtfn)
+{
+	int bir;
+	u32 table;
+	resource_size_t pa;
+	struct pci_sriov *iov = dev->sriov;
+
+	if (nr_virtfn <= iov->initial)
+		return 0;
+
+	pci_read_config_dword(dev, iov->pos + PCI_SRIOV_VFM, &table);
+	bir = PCI_SRIOV_VFM_BIR(table);
+	if (bir > PCI_STD_RESOURCE_END)
+		return -EIO;
+
+	table = PCI_SRIOV_VFM_OFFSET(table);
+	if (table + nr_virtfn > pci_resource_len(dev, bir))
+		return -EIO;
+
+	pa = pci_resource_start(dev, bir) + table;
+	iov->mstate = ioremap(pa, nr_virtfn);
+	if (!iov->mstate)
+		return -ENOMEM;
+
+	INIT_WORK(&iov->mtask, sriov_migration_task);
+
+	iov->ctrl |= PCI_SRIOV_CTRL_VFM | PCI_SRIOV_CTRL_INTR;
+	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
+
+	return 0;
+}
+
+static void sriov_disable_migration(struct pci_dev *dev)
+{
+	struct pci_sriov *iov = dev->sriov;
+
+	iov->ctrl &= ~(PCI_SRIOV_CTRL_VFM | PCI_SRIOV_CTRL_INTR);
+	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
+
+	cancel_work_sync(&iov->mtask);
+	iounmap(iov->mstate);
+}
+
+static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
+{
+	int rc;
+	int i, j;
+	int nres;
+	u16 offset, stride, initial;
+	struct resource *res;
+	struct pci_dev *pdev;
+	struct pci_sriov *iov = dev->sriov;
+
+	if (!nr_virtfn)
+		return 0;
+
+	if (iov->nr_virtfn)
+		return -EINVAL;
+
+	pci_read_config_word(dev, iov->pos + PCI_SRIOV_INITIAL_VF, &initial);
+	if (initial > iov->total ||
+	    (!(iov->cap & PCI_SRIOV_CAP_VFM) && (initial != iov->total)))
+		return -EIO;
+
+	if (nr_virtfn < 0 || nr_virtfn > iov->total ||
+	    (!(iov->cap & PCI_SRIOV_CAP_VFM) && (nr_virtfn > initial)))
+		return -EINVAL;
+
+	pci_write_config_word(dev, iov->pos + PCI_SRIOV_NUM_VF, nr_virtfn);
+	pci_read_config_word(dev, iov->pos + PCI_SRIOV_VF_OFFSET, &offset);
+	pci_read_config_word(dev, iov->pos + PCI_SRIOV_VF_STRIDE, &stride);
+	if (!offset || (nr_virtfn > 1 && !stride))
+		return -EIO;
+
+	nres = 0;
+	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+		res = dev->resource + PCI_IOV_RESOURCES + i;
+		if (res->parent)
+			nres++;
+	}
+	if (nres != iov->nres) {
+		dev_err(&dev->dev, "not enough MMIO resources for SR-IOV\n");
+		return -ENOMEM;
+	}
+
+	iov->offset = offset;
+	iov->stride = stride;
+
+	if (virtfn_bus(dev, nr_virtfn - 1) > dev->bus->subordinate) {
+		dev_err(&dev->dev, "SR-IOV: bus number out of range\n");
+		return -ENOMEM;
+	}
+
+	if (iov->link != dev->devfn) {
+		pdev = pci_get_slot(dev->bus, iov->link);
+		if (!pdev)
+			return -ENODEV;
+
+		pci_dev_put(pdev);
+
+		if (!pdev->is_physfn)
+			return -ENODEV;
+
+		rc = sysfs_create_link(&dev->dev.kobj,
+					&pdev->dev.kobj, "dep_link");
+		if (rc)
+			return rc;
+	}
+
+	iov->ctrl |= PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE;
+	pci_block_user_cfg_access(dev);
+	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
+	msleep(100);
+	pci_unblock_user_cfg_access(dev);
+
+	iov->initial = initial;
+	if (nr_virtfn < initial)
+		initial = nr_virtfn;
+
+	for (i = 0; i < initial; i++) {
+		rc = virtfn_add(dev, i, 0);
+		if (rc)
+			goto failed;
+	}
+
+	if (iov->cap & PCI_SRIOV_CAP_VFM) {
+		rc = sriov_enable_migration(dev, nr_virtfn);
+		if (rc)
+			goto failed;
+	}
+
+	kobject_uevent(&dev->dev.kobj, KOBJ_CHANGE);
+	iov->nr_virtfn = nr_virtfn;
+
+	return 0;
+
+failed:
+	for (j = 0; j < i; j++)
+		virtfn_remove(dev, j, 0);
+
+	iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE);
+	pci_block_user_cfg_access(dev);
+	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
+	ssleep(1);
+	pci_unblock_user_cfg_access(dev);
+
+	if (iov->link != dev->devfn)
+		sysfs_remove_link(&dev->dev.kobj, "dep_link");
+
+	return rc;
+}
+
+static void sriov_disable(struct pci_dev *dev)
+{
+	int i;
+	struct pci_sriov *iov = dev->sriov;
+
+	if (!iov->nr_virtfn)
+		return;
+
+	if (iov->cap & PCI_SRIOV_CAP_VFM)
+		sriov_disable_migration(dev);
+
+	for (i = 0; i < iov->nr_virtfn; i++)
+		virtfn_remove(dev, i, 0);
+
+	iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE);
+	pci_block_user_cfg_access(dev);
+	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
+	ssleep(1);
+	pci_unblock_user_cfg_access(dev);
+
+	if (iov->link != dev->devfn)
+		sysfs_remove_link(&dev->dev.kobj, "dep_link");
+
+	iov->nr_virtfn = 0;
+}
+
+static int sriov_init(struct pci_dev *dev, int pos)
+{
+	int i;
+	int rc;
+	int nres;
+	u32 pgsz;
+	u16 ctrl, total, offset, stride;
+	struct pci_sriov *iov;
+	struct resource *res;
+	struct pci_dev *pdev;
+
+	if (dev->pcie_type != PCI_EXP_TYPE_RC_END &&
+	    dev->pcie_type != PCI_EXP_TYPE_ENDPOINT)
+		return -ENODEV;
+
+	pci_read_config_word(dev, pos + PCI_SRIOV_CTRL, &ctrl);
+	if (ctrl & PCI_SRIOV_CTRL_VFE) {
+		pci_write_config_word(dev, pos + PCI_SRIOV_CTRL, 0);
+		ssleep(1);
+	}
+
+	pci_read_config_word(dev, pos + PCI_SRIOV_TOTAL_VF, &total);
+	if (!total)
+		return 0;
+
+	ctrl = 0;
+	list_for_each_entry(pdev, &dev->bus->devices, bus_list)
+		if (pdev->is_physfn)
+			goto found;
+
+	pdev = NULL;
+	if (pci_ari_enabled(dev->bus))
+		ctrl |= PCI_SRIOV_CTRL_ARI;
+
+found:
+	pci_write_config_word(dev, pos + PCI_SRIOV_CTRL, ctrl);
+	pci_write_config_word(dev, pos + PCI_SRIOV_NUM_VF, total);
+	pci_read_config_word(dev, pos + PCI_SRIOV_VF_OFFSET, &offset);
+	pci_read_config_word(dev, pos + PCI_SRIOV_VF_STRIDE, &stride);
+	if (!offset || (total > 1 && !stride))
+		return -EIO;
+
+	pci_read_config_dword(dev, pos + PCI_SRIOV_SUP_PGSIZE, &pgsz);
+	i = PAGE_SHIFT > 12 ? PAGE_SHIFT - 12 : 0;
+	pgsz &= ~((1 << i) - 1);
+	if (!pgsz)
+		return -EIO;
+
+	pgsz &= ~(pgsz - 1);
+	pci_write_config_dword(dev, pos + PCI_SRIOV_SYS_PGSIZE, pgsz);
+
+	nres = 0;
+	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+		res = dev->resource + PCI_IOV_RESOURCES + i;
+		i += __pci_read_base(dev, pci_bar_unknown, res,
+				     pos + PCI_SRIOV_BAR + i * 4);
+		if (!res->flags)
+			continue;
+		if (resource_size(res) & (PAGE_SIZE - 1)) {
+			rc = -EIO;
+			goto failed;
+		}
+		res->end = res->start + resource_size(res) * total - 1;
+		nres++;
+	}
+
+	iov = kzalloc(sizeof(*iov), GFP_KERNEL);
+	if (!iov) {
+		rc = -ENOMEM;
+		goto failed;
+	}
+
+	iov->pos = pos;
+	iov->nres = nres;
+	iov->ctrl = ctrl;
+	iov->total = total;
+	iov->offset = offset;
+	iov->stride = stride;
+	iov->pgsz = pgsz;
+	iov->self = dev;
+	pci_read_config_dword(dev, pos + PCI_SRIOV_CAP, &iov->cap);
+	pci_read_config_byte(dev, pos + PCI_SRIOV_FUNC_LINK, &iov->link);
+	if (dev->pcie_type == PCI_EXP_TYPE_RC_END)
+		iov->link = PCI_DEVFN(PCI_SLOT(dev->devfn), iov->link);
+
+	if (pdev)
+		iov->dev = pci_dev_get(pdev);
+	else
+		iov->dev = dev;
+
+	mutex_init(&iov->lock);
+
+	dev->sriov = iov;
+	dev->is_physfn = 1;
+
+	return 0;
+
+failed:
+	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+		res = dev->resource + PCI_IOV_RESOURCES + i;
+		res->flags = 0;
+	}
+
+	return rc;
+}
+
+static void sriov_release(struct pci_dev *dev)
+{
+	BUG_ON(dev->sriov->nr_virtfn);
+
+	if (dev != dev->sriov->dev)
+		pci_dev_put(dev->sriov->dev);
+
+	mutex_destroy(&dev->sriov->lock);
+
+	kfree(dev->sriov);
+	dev->sriov = NULL;
+}
+
+static void sriov_restore_state(struct pci_dev *dev)
+{
+	int i;
+	u16 ctrl;
+	struct pci_sriov *iov = dev->sriov;
+
+	pci_read_config_word(dev, iov->pos + PCI_SRIOV_CTRL, &ctrl);
+	if (ctrl & PCI_SRIOV_CTRL_VFE)
+		return;
+
+	for (i = PCI_IOV_RESOURCES; i <= PCI_IOV_RESOURCE_END; i++)
+		pci_update_resource(dev, i);
+
+	pci_write_config_dword(dev, iov->pos + PCI_SRIOV_SYS_PGSIZE, iov->pgsz);
+	pci_write_config_word(dev, iov->pos + PCI_SRIOV_NUM_VF, iov->nr_virtfn);
+	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
+	if (iov->ctrl & PCI_SRIOV_CTRL_VFE)
+		msleep(100);
+}
+
+/**
+ * pci_iov_init - initialize the IOV capability
+ * @dev: the PCI device
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+int pci_iov_init(struct pci_dev *dev)
+{
+	int pos;
+
+	if (!pci_is_pcie(dev))
+		return -ENODEV;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_SRIOV);
+	if (pos)
+		return sriov_init(dev, pos);
+
+	return -ENODEV;
+}
+
+/**
+ * pci_iov_release - release resources used by the IOV capability
+ * @dev: the PCI device
+ */
+void pci_iov_release(struct pci_dev *dev)
+{
+	if (dev->is_physfn)
+		sriov_release(dev);
+}
+
+/**
+ * pci_iov_resource_bar - get position of the SR-IOV BAR
+ * @dev: the PCI device
+ * @resno: the resource number
+ * @type: the BAR type to be filled in
+ *
+ * Returns position of the BAR encapsulated in the SR-IOV capability.
+ */
+int pci_iov_resource_bar(struct pci_dev *dev, int resno,
+			 enum pci_bar_type *type)
+{
+	if (resno < PCI_IOV_RESOURCES || resno > PCI_IOV_RESOURCE_END)
+		return 0;
+
+	BUG_ON(!dev->is_physfn);
+
+	*type = pci_bar_unknown;
+
+	return dev->sriov->pos + PCI_SRIOV_BAR +
+		4 * (resno - PCI_IOV_RESOURCES);
+}
+
+/**
+ * pci_sriov_resource_alignment - get resource alignment for VF BAR
+ * @dev: the PCI device
+ * @resno: the resource number
+ *
+ * Returns the alignment of the VF BAR found in the SR-IOV capability.
+ * This is not the same as the resource size which is defined as
+ * the VF BAR size multiplied by the number of VFs.  The alignment
+ * is just the VF BAR size.
+ */
+resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno)
+{
+	struct resource tmp;
+	enum pci_bar_type type;
+	int reg = pci_iov_resource_bar(dev, resno, &type);
+	
+	if (!reg)
+		return 0;
+
+	 __pci_read_base(dev, type, &tmp, reg);
+	return resource_alignment(&tmp);
+}
+
+/**
+ * pci_restore_iov_state - restore the state of the IOV capability
+ * @dev: the PCI device
+ */
+void pci_restore_iov_state(struct pci_dev *dev)
+{
+	if (dev->is_physfn)
+		sriov_restore_state(dev);
+}
+
+/**
+ * pci_iov_bus_range - find bus range used by Virtual Function
+ * @bus: the PCI bus
+ *
+ * Returns max number of buses (exclude current one) used by Virtual
+ * Functions.
+ */
+int pci_iov_bus_range(struct pci_bus *bus)
+{
+	int max = 0;
+	u8 busnr;
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		if (!dev->is_physfn)
+			continue;
+		busnr = virtfn_bus(dev, dev->sriov->total - 1);
+		if (busnr > max)
+			max = busnr;
+	}
+
+	return max ? max - bus->number : 0;
+}
+
+/**
+ * pci_enable_sriov - enable the SR-IOV capability
+ * @dev: the PCI device
+ * @nr_virtfn: number of virtual functions to enable
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn)
+{
+	might_sleep();
+
+	if (!dev->is_physfn)
+		return -ENODEV;
+
+	return sriov_enable(dev, nr_virtfn);
+}
+EXPORT_SYMBOL_GPL(pci_enable_sriov);
+
+/**
+ * pci_disable_sriov - disable the SR-IOV capability
+ * @dev: the PCI device
+ */
+void pci_disable_sriov(struct pci_dev *dev)
+{
+	might_sleep();
+
+	if (!dev->is_physfn)
+		return;
+
+	sriov_disable(dev);
+}
+EXPORT_SYMBOL_GPL(pci_disable_sriov);
+
+/**
+ * pci_sriov_migration - notify SR-IOV core of Virtual Function Migration
+ * @dev: the PCI device
+ *
+ * Returns IRQ_HANDLED if the IRQ is handled, or IRQ_NONE if not.
+ *
+ * Physical Function driver is responsible to register IRQ handler using
+ * VF Migration Interrupt Message Number, and call this function when the
+ * interrupt is generated by the hardware.
+ */
+irqreturn_t pci_sriov_migration(struct pci_dev *dev)
+{
+	if (!dev->is_physfn)
+		return IRQ_NONE;
+
+	return sriov_migration(dev) ? IRQ_HANDLED : IRQ_NONE;
+}
+EXPORT_SYMBOL_GPL(pci_sriov_migration);
+
+/**
+ * pci_num_vf - return number of VFs associated with a PF device_release_driver
+ * @dev: the PCI device
+ *
+ * Returns number of VFs, or 0 if SR-IOV is not enabled.
+ */
+int pci_num_vf(struct pci_dev *dev)
+{
+	if (!dev || !dev->is_physfn)
+		return 0;
+	else
+		return dev->sriov->nr_virtfn;
+}
+EXPORT_SYMBOL_GPL(pci_num_vf);
+
+static int ats_alloc_one(struct pci_dev *dev, int ps)
+{
+	int pos;
+	u16 cap;
+	struct pci_ats *ats;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ATS);
+	if (!pos)
+		return -ENODEV;
+
+	ats = kzalloc(sizeof(*ats), GFP_KERNEL);
+	if (!ats)
+		return -ENOMEM;
+
+	ats->pos = pos;
+	ats->stu = ps;
+	pci_read_config_word(dev, pos + PCI_ATS_CAP, &cap);
+	ats->qdep = PCI_ATS_CAP_QDEP(cap) ? PCI_ATS_CAP_QDEP(cap) :
+					    PCI_ATS_MAX_QDEP;
+	dev->ats = ats;
+
+	return 0;
+}
+
+static void ats_free_one(struct pci_dev *dev)
+{
+	kfree(dev->ats);
+	dev->ats = NULL;
+}
+
+/**
+ * pci_enable_ats - enable the ATS capability
+ * @dev: the PCI device
+ * @ps: the IOMMU page shift
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+int pci_enable_ats(struct pci_dev *dev, int ps)
+{
+	int rc;
+	u16 ctrl;
+
+	BUG_ON(dev->ats && dev->ats->is_enabled);
+
+	if (ps < PCI_ATS_MIN_STU)
+		return -EINVAL;
+
+	if (dev->is_physfn || dev->is_virtfn) {
+		struct pci_dev *pdev = dev->is_physfn ? dev : dev->physfn;
+
+		mutex_lock(&pdev->sriov->lock);
+		if (pdev->ats)
+			rc = pdev->ats->stu == ps ? 0 : -EINVAL;
+		else
+			rc = ats_alloc_one(pdev, ps);
+
+		if (!rc)
+			pdev->ats->ref_cnt++;
+		mutex_unlock(&pdev->sriov->lock);
+		if (rc)
+			return rc;
+	}
+
+	if (!dev->is_physfn) {
+		rc = ats_alloc_one(dev, ps);
+		if (rc)
+			return rc;
+	}
+
+	ctrl = PCI_ATS_CTRL_ENABLE;
+	if (!dev->is_virtfn)
+		ctrl |= PCI_ATS_CTRL_STU(ps - PCI_ATS_MIN_STU);
+	pci_write_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, ctrl);
+
+	dev->ats->is_enabled = 1;
+
+	return 0;
+}
+
+/**
+ * pci_disable_ats - disable the ATS capability
+ * @dev: the PCI device
+ */
+void pci_disable_ats(struct pci_dev *dev)
+{
+	u16 ctrl;
+
+	BUG_ON(!dev->ats || !dev->ats->is_enabled);
+
+	pci_read_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, &ctrl);
+	ctrl &= ~PCI_ATS_CTRL_ENABLE;
+	pci_write_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, ctrl);
+
+	dev->ats->is_enabled = 0;
+
+	if (dev->is_physfn || dev->is_virtfn) {
+		struct pci_dev *pdev = dev->is_physfn ? dev : dev->physfn;
+
+		mutex_lock(&pdev->sriov->lock);
+		pdev->ats->ref_cnt--;
+		if (!pdev->ats->ref_cnt)
+			ats_free_one(pdev);
+		mutex_unlock(&pdev->sriov->lock);
+	}
+
+	if (!dev->is_physfn)
+		ats_free_one(dev);
+}
+
+/**
+ * pci_ats_queue_depth - query the ATS Invalidate Queue Depth
+ * @dev: the PCI device
+ *
+ * Returns the queue depth on success, or negative on failure.
+ *
+ * The ATS spec uses 0 in the Invalidate Queue Depth field to
+ * indicate that the function can accept 32 Invalidate Request.
+ * But here we use the `real' values (i.e. 1~32) for the Queue
+ * Depth; and 0 indicates the function shares the Queue with
+ * other functions (doesn't exclusively own a Queue).
+ */
+int pci_ats_queue_depth(struct pci_dev *dev)
+{
+	int pos;
+	u16 cap;
+
+	if (dev->is_virtfn)
+		return 0;
+
+	if (dev->ats)
+		return dev->ats->qdep;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ATS);
+	if (!pos)
+		return -ENODEV;
+
+	pci_read_config_word(dev, pos + PCI_ATS_CAP, &cap);
+
+	return PCI_ATS_CAP_QDEP(cap) ? PCI_ATS_CAP_QDEP(cap) :
+				       PCI_ATS_MAX_QDEP;
+}
diff --git a/drivers/pci/iova.c b/drivers/pci/iova.c
new file mode 100644
index 00000000..c5c274ab
--- /dev/null
+++ b/drivers/pci/iova.c
@@ -0,0 +1,435 @@
+/*
+ * Copyright © 2006-2009, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
+ */
+
+#include <linux/iova.h>
+
+void
+init_iova_domain(struct iova_domain *iovad, unsigned long pfn_32bit)
+{
+	spin_lock_init(&iovad->iova_rbtree_lock);
+	iovad->rbroot = RB_ROOT;
+	iovad->cached32_node = NULL;
+	iovad->dma_32bit_pfn = pfn_32bit;
+}
+
+static struct rb_node *
+__get_cached_rbnode(struct iova_domain *iovad, unsigned long *limit_pfn)
+{
+	if ((*limit_pfn != iovad->dma_32bit_pfn) ||
+		(iovad->cached32_node == NULL))
+		return rb_last(&iovad->rbroot);
+	else {
+		struct rb_node *prev_node = rb_prev(iovad->cached32_node);
+		struct iova *curr_iova =
+			container_of(iovad->cached32_node, struct iova, node);
+		*limit_pfn = curr_iova->pfn_lo - 1;
+		return prev_node;
+	}
+}
+
+static void
+__cached_rbnode_insert_update(struct iova_domain *iovad,
+	unsigned long limit_pfn, struct iova *new)
+{
+	if (limit_pfn != iovad->dma_32bit_pfn)
+		return;
+	iovad->cached32_node = &new->node;
+}
+
+static void
+__cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
+{
+	struct iova *cached_iova;
+	struct rb_node *curr;
+
+	if (!iovad->cached32_node)
+		return;
+	curr = iovad->cached32_node;
+	cached_iova = container_of(curr, struct iova, node);
+
+	if (free->pfn_lo >= cached_iova->pfn_lo) {
+		struct rb_node *node = rb_next(&free->node);
+		struct iova *iova = container_of(node, struct iova, node);
+
+		/* only cache if it's below 32bit pfn */
+		if (node && iova->pfn_lo < iovad->dma_32bit_pfn)
+			iovad->cached32_node = node;
+		else
+			iovad->cached32_node = NULL;
+	}
+}
+
+/* Computes the padding size required, to make the
+ * the start address naturally aligned on its size
+ */
+static int
+iova_get_pad_size(int size, unsigned int limit_pfn)
+{
+	unsigned int pad_size = 0;
+	unsigned int order = ilog2(size);
+
+	if (order)
+		pad_size = (limit_pfn + 1) % (1 << order);
+
+	return pad_size;
+}
+
+static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
+		unsigned long size, unsigned long limit_pfn,
+			struct iova *new, bool size_aligned)
+{
+	struct rb_node *prev, *curr = NULL;
+	unsigned long flags;
+	unsigned long saved_pfn;
+	unsigned int pad_size = 0;
+
+	/* Walk the tree backwards */
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	saved_pfn = limit_pfn;
+	curr = __get_cached_rbnode(iovad, &limit_pfn);
+	prev = curr;
+	while (curr) {
+		struct iova *curr_iova = container_of(curr, struct iova, node);
+
+		if (limit_pfn < curr_iova->pfn_lo)
+			goto move_left;
+		else if (limit_pfn < curr_iova->pfn_hi)
+			goto adjust_limit_pfn;
+		else {
+			if (size_aligned)
+				pad_size = iova_get_pad_size(size, limit_pfn);
+			if ((curr_iova->pfn_hi + size + pad_size) <= limit_pfn)
+				break;	/* found a free slot */
+		}
+adjust_limit_pfn:
+		limit_pfn = curr_iova->pfn_lo - 1;
+move_left:
+		prev = curr;
+		curr = rb_prev(curr);
+	}
+
+	if (!curr) {
+		if (size_aligned)
+			pad_size = iova_get_pad_size(size, limit_pfn);
+		if ((IOVA_START_PFN + size + pad_size) > limit_pfn) {
+			spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+			return -ENOMEM;
+		}
+	}
+
+	/* pfn_lo will point to size aligned address if size_aligned is set */
+	new->pfn_lo = limit_pfn - (size + pad_size) + 1;
+	new->pfn_hi = new->pfn_lo + size - 1;
+
+	/* Insert the new_iova into domain rbtree by holding writer lock */
+	/* Add new node and rebalance tree. */
+	{
+		struct rb_node **entry, *parent = NULL;
+
+		/* If we have 'prev', it's a valid place to start the
+		   insertion. Otherwise, start from the root. */
+		if (prev)
+			entry = &prev;
+		else
+			entry = &iovad->rbroot.rb_node;
+
+		/* Figure out where to put new node */
+		while (*entry) {
+			struct iova *this = container_of(*entry,
+							struct iova, node);
+			parent = *entry;
+
+			if (new->pfn_lo < this->pfn_lo)
+				entry = &((*entry)->rb_left);
+			else if (new->pfn_lo > this->pfn_lo)
+				entry = &((*entry)->rb_right);
+			else
+				BUG(); /* this should not happen */
+		}
+
+		/* Add new node and rebalance tree. */
+		rb_link_node(&new->node, parent, entry);
+		rb_insert_color(&new->node, &iovad->rbroot);
+	}
+	__cached_rbnode_insert_update(iovad, saved_pfn, new);
+
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+
+
+	return 0;
+}
+
+static void
+iova_insert_rbtree(struct rb_root *root, struct iova *iova)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	/* Figure out where to put new node */
+	while (*new) {
+		struct iova *this = container_of(*new, struct iova, node);
+		parent = *new;
+
+		if (iova->pfn_lo < this->pfn_lo)
+			new = &((*new)->rb_left);
+		else if (iova->pfn_lo > this->pfn_lo)
+			new = &((*new)->rb_right);
+		else
+			BUG(); /* this should not happen */
+	}
+	/* Add new node and rebalance tree. */
+	rb_link_node(&iova->node, parent, new);
+	rb_insert_color(&iova->node, root);
+}
+
+/**
+ * alloc_iova - allocates an iova
+ * @iovad - iova domain in question
+ * @size - size of page frames to allocate
+ * @limit_pfn - max limit address
+ * @size_aligned - set if size_aligned address range is required
+ * This function allocates an iova in the range limit_pfn to IOVA_START_PFN
+ * looking from limit_pfn instead from IOVA_START_PFN. If the size_aligned
+ * flag is set then the allocated address iova->pfn_lo will be naturally
+ * aligned on roundup_power_of_two(size).
+ */
+struct iova *
+alloc_iova(struct iova_domain *iovad, unsigned long size,
+	unsigned long limit_pfn,
+	bool size_aligned)
+{
+	struct iova *new_iova;
+	int ret;
+
+	new_iova = alloc_iova_mem();
+	if (!new_iova)
+		return NULL;
+
+	/* If size aligned is set then round the size to
+	 * to next power of two.
+	 */
+	if (size_aligned)
+		size = __roundup_pow_of_two(size);
+
+	ret = __alloc_and_insert_iova_range(iovad, size, limit_pfn,
+			new_iova, size_aligned);
+
+	if (ret) {
+		free_iova_mem(new_iova);
+		return NULL;
+	}
+
+	return new_iova;
+}
+
+/**
+ * find_iova - find's an iova for a given pfn
+ * @iovad - iova domain in question.
+ * pfn - page frame number
+ * This function finds and returns an iova belonging to the
+ * given doamin which matches the given pfn.
+ */
+struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn)
+{
+	unsigned long flags;
+	struct rb_node *node;
+
+	/* Take the lock so that no other thread is manipulating the rbtree */
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	node = iovad->rbroot.rb_node;
+	while (node) {
+		struct iova *iova = container_of(node, struct iova, node);
+
+		/* If pfn falls within iova's range, return iova */
+		if ((pfn >= iova->pfn_lo) && (pfn <= iova->pfn_hi)) {
+			spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+			/* We are not holding the lock while this iova
+			 * is referenced by the caller as the same thread
+			 * which called this function also calls __free_iova()
+			 * and it is by desing that only one thread can possibly
+			 * reference a particular iova and hence no conflict.
+			 */
+			return iova;
+		}
+
+		if (pfn < iova->pfn_lo)
+			node = node->rb_left;
+		else if (pfn > iova->pfn_lo)
+			node = node->rb_right;
+	}
+
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	return NULL;
+}
+
+/**
+ * __free_iova - frees the given iova
+ * @iovad: iova domain in question.
+ * @iova: iova in question.
+ * Frees the given iova belonging to the giving domain
+ */
+void
+__free_iova(struct iova_domain *iovad, struct iova *iova)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	__cached_rbnode_delete_update(iovad, iova);
+	rb_erase(&iova->node, &iovad->rbroot);
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	free_iova_mem(iova);
+}
+
+/**
+ * free_iova - finds and frees the iova for a given pfn
+ * @iovad: - iova domain in question.
+ * @pfn: - pfn that is allocated previously
+ * This functions finds an iova for a given pfn and then
+ * frees the iova from that domain.
+ */
+void
+free_iova(struct iova_domain *iovad, unsigned long pfn)
+{
+	struct iova *iova = find_iova(iovad, pfn);
+	if (iova)
+		__free_iova(iovad, iova);
+
+}
+
+/**
+ * put_iova_domain - destroys the iova doamin
+ * @iovad: - iova domain in question.
+ * All the iova's in that domain are destroyed.
+ */
+void put_iova_domain(struct iova_domain *iovad)
+{
+	struct rb_node *node;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	node = rb_first(&iovad->rbroot);
+	while (node) {
+		struct iova *iova = container_of(node, struct iova, node);
+		rb_erase(node, &iovad->rbroot);
+		free_iova_mem(iova);
+		node = rb_first(&iovad->rbroot);
+	}
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+}
+
+static int
+__is_range_overlap(struct rb_node *node,
+	unsigned long pfn_lo, unsigned long pfn_hi)
+{
+	struct iova *iova = container_of(node, struct iova, node);
+
+	if ((pfn_lo <= iova->pfn_hi) && (pfn_hi >= iova->pfn_lo))
+		return 1;
+	return 0;
+}
+
+static struct iova *
+__insert_new_range(struct iova_domain *iovad,
+	unsigned long pfn_lo, unsigned long pfn_hi)
+{
+	struct iova *iova;
+
+	iova = alloc_iova_mem();
+	if (!iova)
+		return iova;
+
+	iova->pfn_hi = pfn_hi;
+	iova->pfn_lo = pfn_lo;
+	iova_insert_rbtree(&iovad->rbroot, iova);
+	return iova;
+}
+
+static void
+__adjust_overlap_range(struct iova *iova,
+	unsigned long *pfn_lo, unsigned long *pfn_hi)
+{
+	if (*pfn_lo < iova->pfn_lo)
+		iova->pfn_lo = *pfn_lo;
+	if (*pfn_hi > iova->pfn_hi)
+		*pfn_lo = iova->pfn_hi + 1;
+}
+
+/**
+ * reserve_iova - reserves an iova in the given range
+ * @iovad: - iova domain pointer
+ * @pfn_lo: - lower page frame address
+ * @pfn_hi:- higher pfn adderss
+ * This function allocates reserves the address range from pfn_lo to pfn_hi so
+ * that this address is not dished out as part of alloc_iova.
+ */
+struct iova *
+reserve_iova(struct iova_domain *iovad,
+	unsigned long pfn_lo, unsigned long pfn_hi)
+{
+	struct rb_node *node;
+	unsigned long flags;
+	struct iova *iova;
+	unsigned int overlap = 0;
+
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	for (node = rb_first(&iovad->rbroot); node; node = rb_next(node)) {
+		if (__is_range_overlap(node, pfn_lo, pfn_hi)) {
+			iova = container_of(node, struct iova, node);
+			__adjust_overlap_range(iova, &pfn_lo, &pfn_hi);
+			if ((pfn_lo >= iova->pfn_lo) &&
+				(pfn_hi <= iova->pfn_hi))
+				goto finish;
+			overlap = 1;
+
+		} else if (overlap)
+				break;
+	}
+
+	/* We are here either because this is the first reserver node
+	 * or need to insert remaining non overlap addr range
+	 */
+	iova = __insert_new_range(iovad, pfn_lo, pfn_hi);
+finish:
+
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	return iova;
+}
+
+/**
+ * copy_reserved_iova - copies the reserved between domains
+ * @from: - source doamin from where to copy
+ * @to: - destination domin where to copy
+ * This function copies reserved iova's from one doamin to
+ * other.
+ */
+void
+copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
+{
+	unsigned long flags;
+	struct rb_node *node;
+
+	spin_lock_irqsave(&from->iova_rbtree_lock, flags);
+	for (node = rb_first(&from->rbroot); node; node = rb_next(node)) {
+		struct iova *iova = container_of(node, struct iova, node);
+		struct iova *new_iova;
+		new_iova = reserve_iova(to, iova->pfn_lo, iova->pfn_hi);
+		if (!new_iova)
+			printk(KERN_ERR "Reserve iova range %lx@%lx failed\n",
+				iova->pfn_lo, iova->pfn_lo);
+	}
+	spin_unlock_irqrestore(&from->iova_rbtree_lock, flags);
+}
diff --git a/drivers/pci/irq.c b/drivers/pci/irq.c
new file mode 100644
index 00000000..de01174a
--- /dev/null
+++ b/drivers/pci/irq.c
@@ -0,0 +1,60 @@
+/*
+ * PCI IRQ failure handing code
+ *
+ * Copyright (c) 2008 James Bottomley <James.Bottomley@HansenPartnership.com>
+ */
+
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+
+static void pci_note_irq_problem(struct pci_dev *pdev, const char *reason)
+{
+	struct pci_dev *parent = to_pci_dev(pdev->dev.parent);
+
+	dev_printk(KERN_ERR, &pdev->dev,
+		   "Potentially misrouted IRQ (Bridge %s %04x:%04x)\n",
+		   dev_name(&parent->dev), parent->vendor, parent->device);
+	dev_printk(KERN_ERR, &pdev->dev, "%s\n", reason);
+	dev_printk(KERN_ERR, &pdev->dev, "Please report to linux-kernel@vger.kernel.org\n");
+	WARN_ON(1);
+}
+
+/**
+ * pci_lost_interrupt - reports a lost PCI interrupt
+ * @pdev:	device whose interrupt is lost
+ * 
+ * The primary function of this routine is to report a lost interrupt
+ * in a standard way which users can recognise (instead of blaming the
+ * driver).
+ *
+ * Returns:
+ *  a suggestion for fixing it (although the driver is not required to
+ * act on this).
+ */
+enum pci_lost_interrupt_reason pci_lost_interrupt(struct pci_dev *pdev)
+{
+	if (pdev->msi_enabled || pdev->msix_enabled) {
+		enum pci_lost_interrupt_reason ret;
+
+		if (pdev->msix_enabled) {
+			pci_note_irq_problem(pdev, "MSIX routing failure");
+			ret = PCI_LOST_IRQ_DISABLE_MSIX;
+		} else {
+			pci_note_irq_problem(pdev, "MSI routing failure");
+			ret = PCI_LOST_IRQ_DISABLE_MSI;
+		}
+		return ret;
+	}
+#ifdef CONFIG_ACPI
+	if (!(acpi_disabled || acpi_noirq)) {
+		pci_note_irq_problem(pdev, "Potential ACPI misrouting please reboot with acpi=noirq");
+		/* currently no way to fix acpi on the fly */
+		return PCI_LOST_IRQ_DISABLE_ACPI;
+	}
+#endif
+	pci_note_irq_problem(pdev, "unknown cause (not MSI or ACPI)");
+	return PCI_LOST_IRQ_NO_INFORMATION;
+}
+EXPORT_SYMBOL(pci_lost_interrupt);
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
new file mode 100644
index 00000000..e1749825
--- /dev/null
+++ b/drivers/pci/msi.c
@@ -0,0 +1,883 @@
+/*
+ * File:	msi.c
+ * Purpose:	PCI Message Signaled Interrupt (MSI)
+ *
+ * Copyright (C) 2003-2004 Intel
+ * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
+ */
+
+#include <linux/err.h>
+#include <linux/mm.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/pci.h>
+#include <linux/proc_fs.h>
+#include <linux/msi.h>
+#include <linux/smp.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+
+#include "pci.h"
+#include "msi.h"
+
+static int pci_msi_enable = 1;
+
+/* Arch hooks */
+
+#ifndef arch_msi_check_device
+int arch_msi_check_device(struct pci_dev *dev, int nvec, int type)
+{
+	return 0;
+}
+#endif
+
+#ifndef arch_setup_msi_irqs
+# define arch_setup_msi_irqs default_setup_msi_irqs
+# define HAVE_DEFAULT_MSI_SETUP_IRQS
+#endif
+
+#ifdef HAVE_DEFAULT_MSI_SETUP_IRQS
+int default_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	struct msi_desc *entry;
+	int ret;
+
+	/*
+	 * If an architecture wants to support multiple MSI, it needs to
+	 * override arch_setup_msi_irqs()
+	 */
+	if (type == PCI_CAP_ID_MSI && nvec > 1)
+		return 1;
+
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		ret = arch_setup_msi_irq(dev, entry);
+		if (ret < 0)
+			return ret;
+		if (ret > 0)
+			return -ENOSPC;
+	}
+
+	return 0;
+}
+#endif
+
+#ifndef arch_teardown_msi_irqs
+# define arch_teardown_msi_irqs default_teardown_msi_irqs
+# define HAVE_DEFAULT_MSI_TEARDOWN_IRQS
+#endif
+
+#ifdef HAVE_DEFAULT_MSI_TEARDOWN_IRQS
+void default_teardown_msi_irqs(struct pci_dev *dev)
+{
+	struct msi_desc *entry;
+
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		int i, nvec;
+		if (entry->irq == 0)
+			continue;
+		nvec = 1 << entry->msi_attrib.multiple;
+		for (i = 0; i < nvec; i++)
+			arch_teardown_msi_irq(entry->irq + i);
+	}
+}
+#endif
+
+static void msi_set_enable(struct pci_dev *dev, int pos, int enable)
+{
+	u16 control;
+
+	BUG_ON(!pos);
+
+	pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &control);
+	control &= ~PCI_MSI_FLAGS_ENABLE;
+	if (enable)
+		control |= PCI_MSI_FLAGS_ENABLE;
+	pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control);
+}
+
+static void msix_set_enable(struct pci_dev *dev, int enable)
+{
+	int pos;
+	u16 control;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+	if (pos) {
+		pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control);
+		control &= ~PCI_MSIX_FLAGS_ENABLE;
+		if (enable)
+			control |= PCI_MSIX_FLAGS_ENABLE;
+		pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
+	}
+}
+
+static inline __attribute_const__ u32 msi_mask(unsigned x)
+{
+	/* Don't shift by >= width of type */
+	if (x >= 5)
+		return 0xffffffff;
+	return (1 << (1 << x)) - 1;
+}
+
+static inline __attribute_const__ u32 msi_capable_mask(u16 control)
+{
+	return msi_mask((control >> 1) & 7);
+}
+
+static inline __attribute_const__ u32 msi_enabled_mask(u16 control)
+{
+	return msi_mask((control >> 4) & 7);
+}
+
+/*
+ * PCI 2.3 does not specify mask bits for each MSI interrupt.  Attempting to
+ * mask all MSI interrupts by clearing the MSI enable bit does not work
+ * reliably as devices without an INTx disable bit will then generate a
+ * level IRQ which will never be cleared.
+ */
+static u32 __msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
+{
+	u32 mask_bits = desc->masked;
+
+	if (!desc->msi_attrib.maskbit)
+		return 0;
+
+	mask_bits &= ~mask;
+	mask_bits |= flag;
+	pci_write_config_dword(desc->dev, desc->mask_pos, mask_bits);
+
+	return mask_bits;
+}
+
+static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
+{
+	desc->masked = __msi_mask_irq(desc, mask, flag);
+}
+
+/*
+ * This internal function does not flush PCI writes to the device.
+ * All users must ensure that they read from the device before either
+ * assuming that the device state is up to date, or returning out of this
+ * file.  This saves a few milliseconds when initialising devices with lots
+ * of MSI-X interrupts.
+ */
+static u32 __msix_mask_irq(struct msi_desc *desc, u32 flag)
+{
+	u32 mask_bits = desc->masked;
+	unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
+						PCI_MSIX_ENTRY_VECTOR_CTRL;
+	mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
+	if (flag)
+		mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
+	writel(mask_bits, desc->mask_base + offset);
+
+	return mask_bits;
+}
+
+static void msix_mask_irq(struct msi_desc *desc, u32 flag)
+{
+	desc->masked = __msix_mask_irq(desc, flag);
+}
+
+static void msi_set_mask_bit(struct irq_data *data, u32 flag)
+{
+	struct msi_desc *desc = irq_data_get_msi(data);
+
+	if (desc->msi_attrib.is_msix) {
+		msix_mask_irq(desc, flag);
+		readl(desc->mask_base);		/* Flush write to device */
+	} else {
+		unsigned offset = data->irq - desc->dev->irq;
+		msi_mask_irq(desc, 1 << offset, flag << offset);
+	}
+}
+
+void mask_msi_irq(struct irq_data *data)
+{
+	msi_set_mask_bit(data, 1);
+}
+
+void unmask_msi_irq(struct irq_data *data)
+{
+	msi_set_mask_bit(data, 0);
+}
+
+void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
+{
+	BUG_ON(entry->dev->current_state != PCI_D0);
+
+	if (entry->msi_attrib.is_msix) {
+		void __iomem *base = entry->mask_base +
+			entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
+
+		msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR);
+		msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR);
+		msg->data = readl(base + PCI_MSIX_ENTRY_DATA);
+	} else {
+		struct pci_dev *dev = entry->dev;
+		int pos = entry->msi_attrib.pos;
+		u16 data;
+
+		pci_read_config_dword(dev, msi_lower_address_reg(pos),
+					&msg->address_lo);
+		if (entry->msi_attrib.is_64) {
+			pci_read_config_dword(dev, msi_upper_address_reg(pos),
+						&msg->address_hi);
+			pci_read_config_word(dev, msi_data_reg(pos, 1), &data);
+		} else {
+			msg->address_hi = 0;
+			pci_read_config_word(dev, msi_data_reg(pos, 0), &data);
+		}
+		msg->data = data;
+	}
+}
+
+void read_msi_msg(unsigned int irq, struct msi_msg *msg)
+{
+	struct msi_desc *entry = irq_get_msi_desc(irq);
+
+	__read_msi_msg(entry, msg);
+}
+
+void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
+{
+	/* Assert that the cache is valid, assuming that
+	 * valid messages are not all-zeroes. */
+	BUG_ON(!(entry->msg.address_hi | entry->msg.address_lo |
+		 entry->msg.data));
+
+	*msg = entry->msg;
+}
+
+void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg)
+{
+	struct msi_desc *entry = irq_get_msi_desc(irq);
+
+	__get_cached_msi_msg(entry, msg);
+}
+
+void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
+{
+	if (entry->dev->current_state != PCI_D0) {
+		/* Don't touch the hardware now */
+	} else if (entry->msi_attrib.is_msix) {
+		void __iomem *base;
+		base = entry->mask_base +
+			entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
+
+		writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR);
+		writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR);
+		writel(msg->data, base + PCI_MSIX_ENTRY_DATA);
+	} else {
+		struct pci_dev *dev = entry->dev;
+		int pos = entry->msi_attrib.pos;
+		u16 msgctl;
+
+		pci_read_config_word(dev, msi_control_reg(pos), &msgctl);
+		msgctl &= ~PCI_MSI_FLAGS_QSIZE;
+		msgctl |= entry->msi_attrib.multiple << 4;
+		pci_write_config_word(dev, msi_control_reg(pos), msgctl);
+
+		pci_write_config_dword(dev, msi_lower_address_reg(pos),
+					msg->address_lo);
+		if (entry->msi_attrib.is_64) {
+			pci_write_config_dword(dev, msi_upper_address_reg(pos),
+						msg->address_hi);
+			pci_write_config_word(dev, msi_data_reg(pos, 1),
+						msg->data);
+		} else {
+			pci_write_config_word(dev, msi_data_reg(pos, 0),
+						msg->data);
+		}
+	}
+	entry->msg = *msg;
+}
+
+void write_msi_msg(unsigned int irq, struct msi_msg *msg)
+{
+	struct msi_desc *entry = irq_get_msi_desc(irq);
+
+	__write_msi_msg(entry, msg);
+}
+
+static void free_msi_irqs(struct pci_dev *dev)
+{
+	struct msi_desc *entry, *tmp;
+
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		int i, nvec;
+		if (!entry->irq)
+			continue;
+		nvec = 1 << entry->msi_attrib.multiple;
+		for (i = 0; i < nvec; i++)
+			BUG_ON(irq_has_action(entry->irq + i));
+	}
+
+	arch_teardown_msi_irqs(dev);
+
+	list_for_each_entry_safe(entry, tmp, &dev->msi_list, list) {
+		if (entry->msi_attrib.is_msix) {
+			if (list_is_last(&entry->list, &dev->msi_list))
+				iounmap(entry->mask_base);
+		}
+		list_del(&entry->list);
+		kfree(entry);
+	}
+}
+
+static struct msi_desc *alloc_msi_entry(struct pci_dev *dev)
+{
+	struct msi_desc *desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return NULL;
+
+	INIT_LIST_HEAD(&desc->list);
+	desc->dev = dev;
+
+	return desc;
+}
+
+static void pci_intx_for_msi(struct pci_dev *dev, int enable)
+{
+	if (!(dev->dev_flags & PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG))
+		pci_intx(dev, enable);
+}
+
+static void __pci_restore_msi_state(struct pci_dev *dev)
+{
+	int pos;
+	u16 control;
+	struct msi_desc *entry;
+
+	if (!dev->msi_enabled)
+		return;
+
+	entry = irq_get_msi_desc(dev->irq);
+	pos = entry->msi_attrib.pos;
+
+	pci_intx_for_msi(dev, 0);
+	msi_set_enable(dev, pos, 0);
+	write_msi_msg(dev->irq, &entry->msg);
+
+	pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &control);
+	msi_mask_irq(entry, msi_capable_mask(control), entry->masked);
+	control &= ~PCI_MSI_FLAGS_QSIZE;
+	control |= (entry->msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE;
+	pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control);
+}
+
+static void __pci_restore_msix_state(struct pci_dev *dev)
+{
+	int pos;
+	struct msi_desc *entry;
+	u16 control;
+
+	if (!dev->msix_enabled)
+		return;
+	BUG_ON(list_empty(&dev->msi_list));
+	entry = list_first_entry(&dev->msi_list, struct msi_desc, list);
+	pos = entry->msi_attrib.pos;
+	pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control);
+
+	/* route the table */
+	pci_intx_for_msi(dev, 0);
+	control |= PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL;
+	pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
+
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		write_msi_msg(entry->irq, &entry->msg);
+		msix_mask_irq(entry, entry->masked);
+	}
+
+	control &= ~PCI_MSIX_FLAGS_MASKALL;
+	pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
+}
+
+void pci_restore_msi_state(struct pci_dev *dev)
+{
+	__pci_restore_msi_state(dev);
+	__pci_restore_msix_state(dev);
+}
+EXPORT_SYMBOL_GPL(pci_restore_msi_state);
+
+/**
+ * msi_capability_init - configure device's MSI capability structure
+ * @dev: pointer to the pci_dev data structure of MSI device function
+ * @nvec: number of interrupts to allocate
+ *
+ * Setup the MSI capability structure of the device with the requested
+ * number of interrupts.  A return value of zero indicates the successful
+ * setup of an entry with the new MSI irq.  A negative return value indicates
+ * an error, and a positive return value indicates the number of interrupts
+ * which could have been allocated.
+ */
+static int msi_capability_init(struct pci_dev *dev, int nvec)
+{
+	struct msi_desc *entry;
+	int pos, ret;
+	u16 control;
+	unsigned mask;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	msi_set_enable(dev, pos, 0);	/* Disable MSI during set up */
+
+	pci_read_config_word(dev, msi_control_reg(pos), &control);
+	/* MSI Entry Initialization */
+	entry = alloc_msi_entry(dev);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->msi_attrib.is_msix	= 0;
+	entry->msi_attrib.is_64		= is_64bit_address(control);
+	entry->msi_attrib.entry_nr	= 0;
+	entry->msi_attrib.maskbit	= is_mask_bit_support(control);
+	entry->msi_attrib.default_irq	= dev->irq;	/* Save IOAPIC IRQ */
+	entry->msi_attrib.pos		= pos;
+
+	entry->mask_pos = msi_mask_reg(pos, entry->msi_attrib.is_64);
+	/* All MSIs are unmasked by default, Mask them all */
+	if (entry->msi_attrib.maskbit)
+		pci_read_config_dword(dev, entry->mask_pos, &entry->masked);
+	mask = msi_capable_mask(control);
+	msi_mask_irq(entry, mask, mask);
+
+	list_add_tail(&entry->list, &dev->msi_list);
+
+	/* Configure MSI capability structure */
+	ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI);
+	if (ret) {
+		msi_mask_irq(entry, mask, ~mask);
+		free_msi_irqs(dev);
+		return ret;
+	}
+
+	/* Set MSI enabled bits	 */
+	pci_intx_for_msi(dev, 0);
+	msi_set_enable(dev, pos, 1);
+	dev->msi_enabled = 1;
+
+	dev->irq = entry->irq;
+	return 0;
+}
+
+static void __iomem *msix_map_region(struct pci_dev *dev, unsigned pos,
+							unsigned nr_entries)
+{
+	resource_size_t phys_addr;
+	u32 table_offset;
+	u8 bir;
+
+	pci_read_config_dword(dev, msix_table_offset_reg(pos), &table_offset);
+	bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
+	table_offset &= ~PCI_MSIX_FLAGS_BIRMASK;
+	phys_addr = pci_resource_start(dev, bir) + table_offset;
+
+	return ioremap_nocache(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE);
+}
+
+static int msix_setup_entries(struct pci_dev *dev, unsigned pos,
+				void __iomem *base, struct msix_entry *entries,
+				int nvec)
+{
+	struct msi_desc *entry;
+	int i;
+
+	for (i = 0; i < nvec; i++) {
+		entry = alloc_msi_entry(dev);
+		if (!entry) {
+			if (!i)
+				iounmap(base);
+			else
+				free_msi_irqs(dev);
+			/* No enough memory. Don't try again */
+			return -ENOMEM;
+		}
+
+		entry->msi_attrib.is_msix	= 1;
+		entry->msi_attrib.is_64		= 1;
+		entry->msi_attrib.entry_nr	= entries[i].entry;
+		entry->msi_attrib.default_irq	= dev->irq;
+		entry->msi_attrib.pos		= pos;
+		entry->mask_base		= base;
+
+		list_add_tail(&entry->list, &dev->msi_list);
+	}
+
+	return 0;
+}
+
+static void msix_program_entries(struct pci_dev *dev,
+					struct msix_entry *entries)
+{
+	struct msi_desc *entry;
+	int i = 0;
+
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		int offset = entries[i].entry * PCI_MSIX_ENTRY_SIZE +
+						PCI_MSIX_ENTRY_VECTOR_CTRL;
+
+		entries[i].vector = entry->irq;
+		irq_set_msi_desc(entry->irq, entry);
+		entry->masked = readl(entry->mask_base + offset);
+		msix_mask_irq(entry, 1);
+		i++;
+	}
+}
+
+/**
+ * msix_capability_init - configure device's MSI-X capability
+ * @dev: pointer to the pci_dev data structure of MSI-X device function
+ * @entries: pointer to an array of struct msix_entry entries
+ * @nvec: number of @entries
+ *
+ * Setup the MSI-X capability structure of device function with a
+ * single MSI-X irq. A return of zero indicates the successful setup of
+ * requested MSI-X entries with allocated irqs or non-zero for otherwise.
+ **/
+static int msix_capability_init(struct pci_dev *dev,
+				struct msix_entry *entries, int nvec)
+{
+	int pos, ret;
+	u16 control;
+	void __iomem *base;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+	pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control);
+
+	/* Ensure MSI-X is disabled while it is set up */
+	control &= ~PCI_MSIX_FLAGS_ENABLE;
+	pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
+
+	/* Request & Map MSI-X table region */
+	base = msix_map_region(dev, pos, multi_msix_capable(control));
+	if (!base)
+		return -ENOMEM;
+
+	ret = msix_setup_entries(dev, pos, base, entries, nvec);
+	if (ret)
+		return ret;
+
+	ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX);
+	if (ret)
+		goto error;
+
+	/*
+	 * Some devices require MSI-X to be enabled before we can touch the
+	 * MSI-X registers.  We need to mask all the vectors to prevent
+	 * interrupts coming in before they're fully set up.
+	 */
+	control |= PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE;
+	pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
+
+	msix_program_entries(dev, entries);
+
+	/* Set MSI-X enabled bits and unmask the function */
+	pci_intx_for_msi(dev, 0);
+	dev->msix_enabled = 1;
+
+	control &= ~PCI_MSIX_FLAGS_MASKALL;
+	pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
+
+	return 0;
+
+error:
+	if (ret < 0) {
+		/*
+		 * If we had some success, report the number of irqs
+		 * we succeeded in setting up.
+		 */
+		struct msi_desc *entry;
+		int avail = 0;
+
+		list_for_each_entry(entry, &dev->msi_list, list) {
+			if (entry->irq != 0)
+				avail++;
+		}
+		if (avail != 0)
+			ret = avail;
+	}
+
+	free_msi_irqs(dev);
+
+	return ret;
+}
+
+/**
+ * pci_msi_check_device - check whether MSI may be enabled on a device
+ * @dev: pointer to the pci_dev data structure of MSI device function
+ * @nvec: how many MSIs have been requested ?
+ * @type: are we checking for MSI or MSI-X ?
+ *
+ * Look at global flags, the device itself, and its parent busses
+ * to determine if MSI/-X are supported for the device. If MSI/-X is
+ * supported return 0, else return an error code.
+ **/
+static int pci_msi_check_device(struct pci_dev *dev, int nvec, int type)
+{
+	struct pci_bus *bus;
+	int ret;
+
+	/* MSI must be globally enabled and supported by the device */
+	if (!pci_msi_enable || !dev || dev->no_msi)
+		return -EINVAL;
+
+	/*
+	 * You can't ask to have 0 or less MSIs configured.
+	 *  a) it's stupid ..
+	 *  b) the list manipulation code assumes nvec >= 1.
+	 */
+	if (nvec < 1)
+		return -ERANGE;
+
+	/*
+	 * Any bridge which does NOT route MSI transactions from its
+	 * secondary bus to its primary bus must set NO_MSI flag on
+	 * the secondary pci_bus.
+	 * We expect only arch-specific PCI host bus controller driver
+	 * or quirks for specific PCI bridges to be setting NO_MSI.
+	 */
+	for (bus = dev->bus; bus; bus = bus->parent)
+		if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI)
+			return -EINVAL;
+
+	ret = arch_msi_check_device(dev, nvec, type);
+	if (ret)
+		return ret;
+
+	if (!pci_find_capability(dev, type))
+		return -EINVAL;
+
+	return 0;
+}
+
+/**
+ * pci_enable_msi_block - configure device's MSI capability structure
+ * @dev: device to configure
+ * @nvec: number of interrupts to configure
+ *
+ * Allocate IRQs for a device with the MSI capability.
+ * This function returns a negative errno if an error occurs.  If it
+ * is unable to allocate the number of interrupts requested, it returns
+ * the number of interrupts it might be able to allocate.  If it successfully
+ * allocates at least the number of interrupts requested, it returns 0 and
+ * updates the @dev's irq member to the lowest new interrupt number; the
+ * other interrupt numbers allocated to this device are consecutive.
+ */
+int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec)
+{
+	int status, pos, maxvec;
+	u16 msgctl;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	if (!pos)
+		return -EINVAL;
+	pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl);
+	maxvec = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1);
+	if (nvec > maxvec)
+		return maxvec;
+
+	status = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSI);
+	if (status)
+		return status;
+
+	WARN_ON(!!dev->msi_enabled);
+
+	/* Check whether driver already requested MSI-X irqs */
+	if (dev->msix_enabled) {
+		dev_info(&dev->dev, "can't enable MSI "
+			 "(MSI-X already enabled)\n");
+		return -EINVAL;
+	}
+
+	status = msi_capability_init(dev, nvec);
+	return status;
+}
+EXPORT_SYMBOL(pci_enable_msi_block);
+
+void pci_msi_shutdown(struct pci_dev *dev)
+{
+	struct msi_desc *desc;
+	u32 mask;
+	u16 ctrl;
+	unsigned pos;
+
+	if (!pci_msi_enable || !dev || !dev->msi_enabled)
+		return;
+
+	BUG_ON(list_empty(&dev->msi_list));
+	desc = list_first_entry(&dev->msi_list, struct msi_desc, list);
+	pos = desc->msi_attrib.pos;
+
+	msi_set_enable(dev, pos, 0);
+	pci_intx_for_msi(dev, 1);
+	dev->msi_enabled = 0;
+
+	/* Return the device with MSI unmasked as initial states */
+	pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &ctrl);
+	mask = msi_capable_mask(ctrl);
+	/* Keep cached state to be restored */
+	__msi_mask_irq(desc, mask, ~mask);
+
+	/* Restore dev->irq to its default pin-assertion irq */
+	dev->irq = desc->msi_attrib.default_irq;
+}
+
+void pci_disable_msi(struct pci_dev *dev)
+{
+	if (!pci_msi_enable || !dev || !dev->msi_enabled)
+		return;
+
+	pci_msi_shutdown(dev);
+	free_msi_irqs(dev);
+}
+EXPORT_SYMBOL(pci_disable_msi);
+
+/**
+ * pci_msix_table_size - return the number of device's MSI-X table entries
+ * @dev: pointer to the pci_dev data structure of MSI-X device function
+ */
+int pci_msix_table_size(struct pci_dev *dev)
+{
+	int pos;
+	u16 control;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+	if (!pos)
+		return 0;
+
+	pci_read_config_word(dev, msi_control_reg(pos), &control);
+	return multi_msix_capable(control);
+}
+
+/**
+ * pci_enable_msix - configure device's MSI-X capability structure
+ * @dev: pointer to the pci_dev data structure of MSI-X device function
+ * @entries: pointer to an array of MSI-X entries
+ * @nvec: number of MSI-X irqs requested for allocation by device driver
+ *
+ * Setup the MSI-X capability structure of device function with the number
+ * of requested irqs upon its software driver call to request for
+ * MSI-X mode enabled on its hardware device function. A return of zero
+ * indicates the successful configuration of MSI-X capability structure
+ * with new allocated MSI-X irqs. A return of < 0 indicates a failure.
+ * Or a return of > 0 indicates that driver request is exceeding the number
+ * of irqs or MSI-X vectors available. Driver should use the returned value to
+ * re-send its request.
+ **/
+int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec)
+{
+	int status, nr_entries;
+	int i, j;
+
+	if (!entries)
+		return -EINVAL;
+
+	status = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSIX);
+	if (status)
+		return status;
+
+	nr_entries = pci_msix_table_size(dev);
+	if (nvec > nr_entries)
+		return nr_entries;
+
+	/* Check for any invalid entries */
+	for (i = 0; i < nvec; i++) {
+		if (entries[i].entry >= nr_entries)
+			return -EINVAL;		/* invalid entry */
+		for (j = i + 1; j < nvec; j++) {
+			if (entries[i].entry == entries[j].entry)
+				return -EINVAL;	/* duplicate entry */
+		}
+	}
+	WARN_ON(!!dev->msix_enabled);
+
+	/* Check whether driver already requested for MSI irq */
+	if (dev->msi_enabled) {
+		dev_info(&dev->dev, "can't enable MSI-X "
+		       "(MSI IRQ already assigned)\n");
+		return -EINVAL;
+	}
+	status = msix_capability_init(dev, entries, nvec);
+	return status;
+}
+EXPORT_SYMBOL(pci_enable_msix);
+
+void pci_msix_shutdown(struct pci_dev *dev)
+{
+	struct msi_desc *entry;
+
+	if (!pci_msi_enable || !dev || !dev->msix_enabled)
+		return;
+
+	/* Return the device with MSI-X masked as initial states */
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		/* Keep cached states to be restored */
+		__msix_mask_irq(entry, 1);
+	}
+
+	msix_set_enable(dev, 0);
+	pci_intx_for_msi(dev, 1);
+	dev->msix_enabled = 0;
+}
+
+void pci_disable_msix(struct pci_dev *dev)
+{
+	if (!pci_msi_enable || !dev || !dev->msix_enabled)
+		return;
+
+	pci_msix_shutdown(dev);
+	free_msi_irqs(dev);
+}
+EXPORT_SYMBOL(pci_disable_msix);
+
+/**
+ * msi_remove_pci_irq_vectors - reclaim MSI(X) irqs to unused state
+ * @dev: pointer to the pci_dev data structure of MSI(X) device function
+ *
+ * Being called during hotplug remove, from which the device function
+ * is hot-removed. All previous assigned MSI/MSI-X irqs, if
+ * allocated for this device function, are reclaimed to unused state,
+ * which may be used later on.
+ **/
+void msi_remove_pci_irq_vectors(struct pci_dev *dev)
+{
+	if (!pci_msi_enable || !dev)
+		return;
+
+	if (dev->msi_enabled || dev->msix_enabled)
+		free_msi_irqs(dev);
+}
+
+void pci_no_msi(void)
+{
+	pci_msi_enable = 0;
+}
+
+/**
+ * pci_msi_enabled - is MSI enabled?
+ *
+ * Returns true if MSI has not been disabled by the command-line option
+ * pci=nomsi.
+ **/
+int pci_msi_enabled(void)
+{
+	return pci_msi_enable;
+}
+EXPORT_SYMBOL(pci_msi_enabled);
+
+void pci_msi_init_pci_dev(struct pci_dev *dev)
+{
+	int pos;
+	INIT_LIST_HEAD(&dev->msi_list);
+
+	/* Disable the msi hardware to avoid screaming interrupts
+	 * during boot.  This is the power on reset default so
+	 * usually this should be a noop.
+	 */
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	if (pos)
+		msi_set_enable(dev, pos, 0);
+	msix_set_enable(dev, 0);
+}
diff --git a/drivers/pci/msi.h b/drivers/pci/msi.h
new file mode 100644
index 00000000..65c42f80
--- /dev/null
+++ b/drivers/pci/msi.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2003-2004 Intel
+ * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
+ */
+
+#ifndef MSI_H
+#define MSI_H
+
+#define msi_control_reg(base)		(base + PCI_MSI_FLAGS)
+#define msi_lower_address_reg(base)	(base + PCI_MSI_ADDRESS_LO)
+#define msi_upper_address_reg(base)	(base + PCI_MSI_ADDRESS_HI)
+#define msi_data_reg(base, is64bit)	\
+	(base + ((is64bit == 1) ? PCI_MSI_DATA_64 : PCI_MSI_DATA_32))
+#define msi_mask_reg(base, is64bit)	\
+	(base + ((is64bit == 1) ? PCI_MSI_MASK_64 : PCI_MSI_MASK_32))
+#define is_64bit_address(control)	(!!(control & PCI_MSI_FLAGS_64BIT))
+#define is_mask_bit_support(control)	(!!(control & PCI_MSI_FLAGS_MASKBIT))
+
+#define msix_table_offset_reg(base)	(base + PCI_MSIX_TABLE)
+#define msix_pba_offset_reg(base)	(base + PCI_MSIX_PBA)
+#define msix_table_size(control) 	((control & PCI_MSIX_FLAGS_QSIZE)+1)
+#define multi_msix_capable(control)	msix_table_size((control))
+
+#endif /* MSI_H */
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
new file mode 100644
index 00000000..56b04bc8
--- /dev/null
+++ b/drivers/pci/pci-acpi.c
@@ -0,0 +1,405 @@
+/*
+ * File:	pci-acpi.c
+ * Purpose:	Provide PCI support in ACPI
+ *
+ * Copyright (C) 2005 David Shaohua Li <shaohua.li@intel.com>
+ * Copyright (C) 2004 Tom Long Nguyen <tom.l.nguyen@intel.com>
+ * Copyright (C) 2004 Intel Corp.
+ */
+
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/module.h>
+#include <linux/pci-aspm.h>
+#include <acpi/acpi.h>
+#include <acpi/acpi_bus.h>
+
+#include <linux/pci-acpi.h>
+#include <linux/pm_runtime.h>
+#include "pci.h"
+
+static DEFINE_MUTEX(pci_acpi_pm_notify_mtx);
+
+/**
+ * pci_acpi_wake_bus - Wake-up notification handler for root buses.
+ * @handle: ACPI handle of a device the notification is for.
+ * @event: Type of the signaled event.
+ * @context: PCI root bus to wake up devices on.
+ */
+static void pci_acpi_wake_bus(acpi_handle handle, u32 event, void *context)
+{
+	struct pci_bus *pci_bus = context;
+
+	if (event == ACPI_NOTIFY_DEVICE_WAKE && pci_bus)
+		pci_pme_wakeup_bus(pci_bus);
+}
+
+/**
+ * pci_acpi_wake_dev - Wake-up notification handler for PCI devices.
+ * @handle: ACPI handle of a device the notification is for.
+ * @event: Type of the signaled event.
+ * @context: PCI device object to wake up.
+ */
+static void pci_acpi_wake_dev(acpi_handle handle, u32 event, void *context)
+{
+	struct pci_dev *pci_dev = context;
+
+	if (event == ACPI_NOTIFY_DEVICE_WAKE && pci_dev) {
+		pci_wakeup_event(pci_dev);
+		pci_check_pme_status(pci_dev);
+		pm_runtime_resume(&pci_dev->dev);
+		if (pci_dev->subordinate)
+			pci_pme_wakeup_bus(pci_dev->subordinate);
+	}
+}
+
+/**
+ * add_pm_notifier - Register PM notifier for given ACPI device.
+ * @dev: ACPI device to add the notifier for.
+ * @context: PCI device or bus to check for PME status if an event is signaled.
+ *
+ * NOTE: @dev need not be a run-wake or wake-up device to be a valid source of
+ * PM wake-up events.  For example, wake-up events may be generated for bridges
+ * if one of the devices below the bridge is signaling PME, even if the bridge
+ * itself doesn't have a wake-up GPE associated with it.
+ */
+static acpi_status add_pm_notifier(struct acpi_device *dev,
+				   acpi_notify_handler handler,
+				   void *context)
+{
+	acpi_status status = AE_ALREADY_EXISTS;
+
+	mutex_lock(&pci_acpi_pm_notify_mtx);
+
+	if (dev->wakeup.flags.notifier_present)
+		goto out;
+
+	status = acpi_install_notify_handler(dev->handle,
+					     ACPI_SYSTEM_NOTIFY,
+					     handler, context);
+	if (ACPI_FAILURE(status))
+		goto out;
+
+	dev->wakeup.flags.notifier_present = true;
+
+ out:
+	mutex_unlock(&pci_acpi_pm_notify_mtx);
+	return status;
+}
+
+/**
+ * remove_pm_notifier - Unregister PM notifier from given ACPI device.
+ * @dev: ACPI device to remove the notifier from.
+ */
+static acpi_status remove_pm_notifier(struct acpi_device *dev,
+				      acpi_notify_handler handler)
+{
+	acpi_status status = AE_BAD_PARAMETER;
+
+	mutex_lock(&pci_acpi_pm_notify_mtx);
+
+	if (!dev->wakeup.flags.notifier_present)
+		goto out;
+
+	status = acpi_remove_notify_handler(dev->handle,
+					    ACPI_SYSTEM_NOTIFY,
+					    handler);
+	if (ACPI_FAILURE(status))
+		goto out;
+
+	dev->wakeup.flags.notifier_present = false;
+
+ out:
+	mutex_unlock(&pci_acpi_pm_notify_mtx);
+	return status;
+}
+
+/**
+ * pci_acpi_add_bus_pm_notifier - Register PM notifier for given PCI bus.
+ * @dev: ACPI device to add the notifier for.
+ * @pci_bus: PCI bus to walk checking for PME status if an event is signaled.
+ */
+acpi_status pci_acpi_add_bus_pm_notifier(struct acpi_device *dev,
+					 struct pci_bus *pci_bus)
+{
+	return add_pm_notifier(dev, pci_acpi_wake_bus, pci_bus);
+}
+
+/**
+ * pci_acpi_remove_bus_pm_notifier - Unregister PCI bus PM notifier.
+ * @dev: ACPI device to remove the notifier from.
+ */
+acpi_status pci_acpi_remove_bus_pm_notifier(struct acpi_device *dev)
+{
+	return remove_pm_notifier(dev, pci_acpi_wake_bus);
+}
+
+/**
+ * pci_acpi_add_pm_notifier - Register PM notifier for given PCI device.
+ * @dev: ACPI device to add the notifier for.
+ * @pci_dev: PCI device to check for the PME status if an event is signaled.
+ */
+acpi_status pci_acpi_add_pm_notifier(struct acpi_device *dev,
+				     struct pci_dev *pci_dev)
+{
+	return add_pm_notifier(dev, pci_acpi_wake_dev, pci_dev);
+}
+
+/**
+ * pci_acpi_remove_pm_notifier - Unregister PCI device PM notifier.
+ * @dev: ACPI device to remove the notifier from.
+ */
+acpi_status pci_acpi_remove_pm_notifier(struct acpi_device *dev)
+{
+	return remove_pm_notifier(dev, pci_acpi_wake_dev);
+}
+
+/*
+ * _SxD returns the D-state with the highest power
+ * (lowest D-state number) supported in the S-state "x".
+ *
+ * If the devices does not have a _PRW
+ * (Power Resources for Wake) supporting system wakeup from "x"
+ * then the OS is free to choose a lower power (higher number
+ * D-state) than the return value from _SxD.
+ *
+ * But if _PRW is enabled at S-state "x", the OS
+ * must not choose a power lower than _SxD --
+ * unless the device has an _SxW method specifying
+ * the lowest power (highest D-state number) the device
+ * may enter while still able to wake the system.
+ *
+ * ie. depending on global OS policy:
+ *
+ * if (_PRW at S-state x)
+ *	choose from highest power _SxD to lowest power _SxW
+ * else // no _PRW at S-state x
+ * 	choose highest power _SxD or any lower power
+ */
+
+static pci_power_t acpi_pci_choose_state(struct pci_dev *pdev)
+{
+	int acpi_state;
+
+	acpi_state = acpi_pm_device_sleep_state(&pdev->dev, NULL);
+	if (acpi_state < 0)
+		return PCI_POWER_ERROR;
+
+	switch (acpi_state) {
+	case ACPI_STATE_D0:
+		return PCI_D0;
+	case ACPI_STATE_D1:
+		return PCI_D1;
+	case ACPI_STATE_D2:
+		return PCI_D2;
+	case ACPI_STATE_D3:
+		return PCI_D3hot;
+	case ACPI_STATE_D3_COLD:
+		return PCI_D3cold;
+	}
+	return PCI_POWER_ERROR;
+}
+
+static bool acpi_pci_power_manageable(struct pci_dev *dev)
+{
+	acpi_handle handle = DEVICE_ACPI_HANDLE(&dev->dev);
+
+	return handle ? acpi_bus_power_manageable(handle) : false;
+}
+
+static int acpi_pci_set_power_state(struct pci_dev *dev, pci_power_t state)
+{
+	acpi_handle handle = DEVICE_ACPI_HANDLE(&dev->dev);
+	acpi_handle tmp;
+	static const u8 state_conv[] = {
+		[PCI_D0] = ACPI_STATE_D0,
+		[PCI_D1] = ACPI_STATE_D1,
+		[PCI_D2] = ACPI_STATE_D2,
+		[PCI_D3hot] = ACPI_STATE_D3,
+		[PCI_D3cold] = ACPI_STATE_D3
+	};
+	int error = -EINVAL;
+
+	/* If the ACPI device has _EJ0, ignore the device */
+	if (!handle || ACPI_SUCCESS(acpi_get_handle(handle, "_EJ0", &tmp)))
+		return -ENODEV;
+
+	switch (state) {
+	case PCI_D0:
+	case PCI_D1:
+	case PCI_D2:
+	case PCI_D3hot:
+	case PCI_D3cold:
+		error = acpi_bus_set_power(handle, state_conv[state]);
+	}
+
+	if (!error)
+		dev_printk(KERN_INFO, &dev->dev,
+				"power state changed by ACPI to D%d\n", state);
+
+	return error;
+}
+
+static bool acpi_pci_can_wakeup(struct pci_dev *dev)
+{
+	acpi_handle handle = DEVICE_ACPI_HANDLE(&dev->dev);
+
+	return handle ? acpi_bus_can_wakeup(handle) : false;
+}
+
+static void acpi_pci_propagate_wakeup_enable(struct pci_bus *bus, bool enable)
+{
+	while (bus->parent) {
+		if (!acpi_pm_device_sleep_wake(&bus->self->dev, enable))
+			return;
+		bus = bus->parent;
+	}
+
+	/* We have reached the root bus. */
+	if (bus->bridge)
+		acpi_pm_device_sleep_wake(bus->bridge, enable);
+}
+
+static int acpi_pci_sleep_wake(struct pci_dev *dev, bool enable)
+{
+	if (acpi_pci_can_wakeup(dev))
+		return acpi_pm_device_sleep_wake(&dev->dev, enable);
+
+	acpi_pci_propagate_wakeup_enable(dev->bus, enable);
+	return 0;
+}
+
+/**
+ * acpi_dev_run_wake - Enable/disable wake-up for given device.
+ * @phys_dev: Device to enable/disable the platform to wake-up the system for.
+ * @enable: Whether enable or disable the wake-up functionality.
+ *
+ * Find the ACPI device object corresponding to @pci_dev and try to
+ * enable/disable the GPE associated with it.
+ */
+static int acpi_dev_run_wake(struct device *phys_dev, bool enable)
+{
+	struct acpi_device *dev;
+	acpi_handle handle;
+	int error = -ENODEV;
+
+	if (!device_run_wake(phys_dev))
+		return -EINVAL;
+
+	handle = DEVICE_ACPI_HANDLE(phys_dev);
+	if (!handle || ACPI_FAILURE(acpi_bus_get_device(handle, &dev))) {
+		dev_dbg(phys_dev, "ACPI handle has no context in %s!\n",
+			__func__);
+		return -ENODEV;
+	}
+
+	if (enable) {
+		acpi_enable_wakeup_device_power(dev, ACPI_STATE_S0);
+		acpi_enable_gpe(dev->wakeup.gpe_device, dev->wakeup.gpe_number);
+	} else {
+		acpi_disable_gpe(dev->wakeup.gpe_device, dev->wakeup.gpe_number);
+		acpi_disable_wakeup_device_power(dev);
+	}
+
+	return error;
+}
+
+static void acpi_pci_propagate_run_wake(struct pci_bus *bus, bool enable)
+{
+	while (bus->parent) {
+		struct pci_dev *bridge = bus->self;
+
+		if (bridge->pme_interrupt)
+			return;
+		if (!acpi_dev_run_wake(&bridge->dev, enable))
+			return;
+		bus = bus->parent;
+	}
+
+	/* We have reached the root bus. */
+	if (bus->bridge)
+		acpi_dev_run_wake(bus->bridge, enable);
+}
+
+static int acpi_pci_run_wake(struct pci_dev *dev, bool enable)
+{
+	if (dev->pme_interrupt)
+		return 0;
+
+	if (!acpi_dev_run_wake(&dev->dev, enable))
+		return 0;
+
+	acpi_pci_propagate_run_wake(dev->bus, enable);
+	return 0;
+}
+
+static struct pci_platform_pm_ops acpi_pci_platform_pm = {
+	.is_manageable = acpi_pci_power_manageable,
+	.set_state = acpi_pci_set_power_state,
+	.choose_state = acpi_pci_choose_state,
+	.can_wakeup = acpi_pci_can_wakeup,
+	.sleep_wake = acpi_pci_sleep_wake,
+	.run_wake = acpi_pci_run_wake,
+};
+
+/* ACPI bus type */
+static int acpi_pci_find_device(struct device *dev, acpi_handle *handle)
+{
+	struct pci_dev * pci_dev;
+	u64	addr;
+
+	pci_dev = to_pci_dev(dev);
+	/* Please ref to ACPI spec for the syntax of _ADR */
+	addr = (PCI_SLOT(pci_dev->devfn) << 16) | PCI_FUNC(pci_dev->devfn);
+	*handle = acpi_get_child(DEVICE_ACPI_HANDLE(dev->parent), addr);
+	if (!*handle)
+		return -ENODEV;
+	return 0;
+}
+
+static int acpi_pci_find_root_bridge(struct device *dev, acpi_handle *handle)
+{
+	int num;
+	unsigned int seg, bus;
+
+	/*
+	 * The string should be the same as root bridge's name
+	 * Please look at 'pci_scan_bus_parented'
+	 */
+	num = sscanf(dev_name(dev), "pci%04x:%02x", &seg, &bus);
+	if (num != 2)
+		return -ENODEV;
+	*handle = acpi_get_pci_rootbridge_handle(seg, bus);
+	if (!*handle)
+		return -ENODEV;
+	return 0;
+}
+
+static struct acpi_bus_type acpi_pci_bus = {
+	.bus = &pci_bus_type,
+	.find_device = acpi_pci_find_device,
+	.find_bridge = acpi_pci_find_root_bridge,
+};
+
+static int __init acpi_pci_init(void)
+{
+	int ret;
+
+	if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_MSI) {
+		printk(KERN_INFO"ACPI FADT declares the system doesn't support MSI, so disable it\n");
+		pci_no_msi();
+	}
+
+	if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_ASPM) {
+		printk(KERN_INFO"ACPI FADT declares the system doesn't support PCIe ASPM, so disable it\n");
+		pcie_no_aspm();
+	}
+
+	ret = register_acpi_bus_type(&acpi_pci_bus);
+	if (ret)
+		return 0;
+	pci_set_platform_pm(&acpi_pci_platform_pm);
+	return 0;
+}
+arch_initcall(acpi_pci_init);
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
new file mode 100644
index 00000000..46767c53
--- /dev/null
+++ b/drivers/pci/pci-driver.c
@@ -0,0 +1,1272 @@
+/*
+ * drivers/pci/pci-driver.c
+ *
+ * (C) Copyright 2002-2004, 2007 Greg Kroah-Hartman <greg@kroah.com>
+ * (C) Copyright 2007 Novell Inc.
+ *
+ * Released under the GPL v2 only.
+ *
+ */
+
+#include <linux/pci.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/mempolicy.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/cpu.h>
+#include <linux/pm_runtime.h>
+#include "pci.h"
+
+struct pci_dynid {
+	struct list_head node;
+	struct pci_device_id id;
+};
+
+/**
+ * pci_add_dynid - add a new PCI device ID to this driver and re-probe devices
+ * @drv: target pci driver
+ * @vendor: PCI vendor ID
+ * @device: PCI device ID
+ * @subvendor: PCI subvendor ID
+ * @subdevice: PCI subdevice ID
+ * @class: PCI class
+ * @class_mask: PCI class mask
+ * @driver_data: private driver data
+ *
+ * Adds a new dynamic pci device ID to this driver and causes the
+ * driver to probe for all devices again.  @drv must have been
+ * registered prior to calling this function.
+ *
+ * CONTEXT:
+ * Does GFP_KERNEL allocation.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int pci_add_dynid(struct pci_driver *drv,
+		  unsigned int vendor, unsigned int device,
+		  unsigned int subvendor, unsigned int subdevice,
+		  unsigned int class, unsigned int class_mask,
+		  unsigned long driver_data)
+{
+	struct pci_dynid *dynid;
+	int retval;
+
+	dynid = kzalloc(sizeof(*dynid), GFP_KERNEL);
+	if (!dynid)
+		return -ENOMEM;
+
+	dynid->id.vendor = vendor;
+	dynid->id.device = device;
+	dynid->id.subvendor = subvendor;
+	dynid->id.subdevice = subdevice;
+	dynid->id.class = class;
+	dynid->id.class_mask = class_mask;
+	dynid->id.driver_data = driver_data;
+
+	spin_lock(&drv->dynids.lock);
+	list_add_tail(&dynid->node, &drv->dynids.list);
+	spin_unlock(&drv->dynids.lock);
+
+	get_driver(&drv->driver);
+	retval = driver_attach(&drv->driver);
+	put_driver(&drv->driver);
+
+	return retval;
+}
+
+static void pci_free_dynids(struct pci_driver *drv)
+{
+	struct pci_dynid *dynid, *n;
+
+	spin_lock(&drv->dynids.lock);
+	list_for_each_entry_safe(dynid, n, &drv->dynids.list, node) {
+		list_del(&dynid->node);
+		kfree(dynid);
+	}
+	spin_unlock(&drv->dynids.lock);
+}
+
+/*
+ * Dynamic device ID manipulation via sysfs is disabled for !CONFIG_HOTPLUG
+ */
+#ifdef CONFIG_HOTPLUG
+/**
+ * store_new_id - sysfs frontend to pci_add_dynid()
+ * @driver: target device driver
+ * @buf: buffer for scanning device ID data
+ * @count: input size
+ *
+ * Allow PCI IDs to be added to an existing driver via sysfs.
+ */
+static ssize_t
+store_new_id(struct device_driver *driver, const char *buf, size_t count)
+{
+	struct pci_driver *pdrv = to_pci_driver(driver);
+	const struct pci_device_id *ids = pdrv->id_table;
+	__u32 vendor, device, subvendor=PCI_ANY_ID,
+		subdevice=PCI_ANY_ID, class=0, class_mask=0;
+	unsigned long driver_data=0;
+	int fields=0;
+	int retval;
+
+	fields = sscanf(buf, "%x %x %x %x %x %x %lx",
+			&vendor, &device, &subvendor, &subdevice,
+			&class, &class_mask, &driver_data);
+	if (fields < 2)
+		return -EINVAL;
+
+	/* Only accept driver_data values that match an existing id_table
+	   entry */
+	if (ids) {
+		retval = -EINVAL;
+		while (ids->vendor || ids->subvendor || ids->class_mask) {
+			if (driver_data == ids->driver_data) {
+				retval = 0;
+				break;
+			}
+			ids++;
+		}
+		if (retval)	/* No match */
+			return retval;
+	}
+
+	retval = pci_add_dynid(pdrv, vendor, device, subvendor, subdevice,
+			       class, class_mask, driver_data);
+	if (retval)
+		return retval;
+	return count;
+}
+static DRIVER_ATTR(new_id, S_IWUSR, NULL, store_new_id);
+
+/**
+ * store_remove_id - remove a PCI device ID from this driver
+ * @driver: target device driver
+ * @buf: buffer for scanning device ID data
+ * @count: input size
+ *
+ * Removes a dynamic pci device ID to this driver.
+ */
+static ssize_t
+store_remove_id(struct device_driver *driver, const char *buf, size_t count)
+{
+	struct pci_dynid *dynid, *n;
+	struct pci_driver *pdrv = to_pci_driver(driver);
+	__u32 vendor, device, subvendor = PCI_ANY_ID,
+		subdevice = PCI_ANY_ID, class = 0, class_mask = 0;
+	int fields = 0;
+	int retval = -ENODEV;
+
+	fields = sscanf(buf, "%x %x %x %x %x %x",
+			&vendor, &device, &subvendor, &subdevice,
+			&class, &class_mask);
+	if (fields < 2)
+		return -EINVAL;
+
+	spin_lock(&pdrv->dynids.lock);
+	list_for_each_entry_safe(dynid, n, &pdrv->dynids.list, node) {
+		struct pci_device_id *id = &dynid->id;
+		if ((id->vendor == vendor) &&
+		    (id->device == device) &&
+		    (subvendor == PCI_ANY_ID || id->subvendor == subvendor) &&
+		    (subdevice == PCI_ANY_ID || id->subdevice == subdevice) &&
+		    !((id->class ^ class) & class_mask)) {
+			list_del(&dynid->node);
+			kfree(dynid);
+			retval = 0;
+			break;
+		}
+	}
+	spin_unlock(&pdrv->dynids.lock);
+
+	if (retval)
+		return retval;
+	return count;
+}
+static DRIVER_ATTR(remove_id, S_IWUSR, NULL, store_remove_id);
+
+static int
+pci_create_newid_file(struct pci_driver *drv)
+{
+	int error = 0;
+	if (drv->probe != NULL)
+		error = driver_create_file(&drv->driver, &driver_attr_new_id);
+	return error;
+}
+
+static void pci_remove_newid_file(struct pci_driver *drv)
+{
+	driver_remove_file(&drv->driver, &driver_attr_new_id);
+}
+
+static int
+pci_create_removeid_file(struct pci_driver *drv)
+{
+	int error = 0;
+	if (drv->probe != NULL)
+		error = driver_create_file(&drv->driver,&driver_attr_remove_id);
+	return error;
+}
+
+static void pci_remove_removeid_file(struct pci_driver *drv)
+{
+	driver_remove_file(&drv->driver, &driver_attr_remove_id);
+}
+#else /* !CONFIG_HOTPLUG */
+static inline int pci_create_newid_file(struct pci_driver *drv)
+{
+	return 0;
+}
+static inline void pci_remove_newid_file(struct pci_driver *drv) {}
+static inline int pci_create_removeid_file(struct pci_driver *drv)
+{
+	return 0;
+}
+static inline void pci_remove_removeid_file(struct pci_driver *drv) {}
+#endif
+
+/**
+ * pci_match_id - See if a pci device matches a given pci_id table
+ * @ids: array of PCI device id structures to search in
+ * @dev: the PCI device structure to match against.
+ *
+ * Used by a driver to check whether a PCI device present in the
+ * system is in its list of supported devices.  Returns the matching
+ * pci_device_id structure or %NULL if there is no match.
+ *
+ * Deprecated, don't use this as it will not catch any dynamic ids
+ * that a driver might want to check for.
+ */
+const struct pci_device_id *pci_match_id(const struct pci_device_id *ids,
+					 struct pci_dev *dev)
+{
+	if (ids) {
+		while (ids->vendor || ids->subvendor || ids->class_mask) {
+			if (pci_match_one_device(ids, dev))
+				return ids;
+			ids++;
+		}
+	}
+	return NULL;
+}
+
+/**
+ * pci_match_device - Tell if a PCI device structure has a matching PCI device id structure
+ * @drv: the PCI driver to match against
+ * @dev: the PCI device structure to match against
+ *
+ * Used by a driver to check whether a PCI device present in the
+ * system is in its list of supported devices.  Returns the matching
+ * pci_device_id structure or %NULL if there is no match.
+ */
+static const struct pci_device_id *pci_match_device(struct pci_driver *drv,
+						    struct pci_dev *dev)
+{
+	struct pci_dynid *dynid;
+
+	/* Look at the dynamic ids first, before the static ones */
+	spin_lock(&drv->dynids.lock);
+	list_for_each_entry(dynid, &drv->dynids.list, node) {
+		if (pci_match_one_device(&dynid->id, dev)) {
+			spin_unlock(&drv->dynids.lock);
+			return &dynid->id;
+		}
+	}
+	spin_unlock(&drv->dynids.lock);
+
+	return pci_match_id(drv->id_table, dev);
+}
+
+struct drv_dev_and_id {
+	struct pci_driver *drv;
+	struct pci_dev *dev;
+	const struct pci_device_id *id;
+};
+
+static long local_pci_probe(void *_ddi)
+{
+	struct drv_dev_and_id *ddi = _ddi;
+	struct device *dev = &ddi->dev->dev;
+	int rc;
+
+	/* Unbound PCI devices are always set to disabled and suspended.
+	 * During probe, the device is set to enabled and active and the
+	 * usage count is incremented.  If the driver supports runtime PM,
+	 * it should call pm_runtime_put_noidle() in its probe routine and
+	 * pm_runtime_get_noresume() in its remove routine.
+	 */
+	pm_runtime_get_noresume(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
+	rc = ddi->drv->probe(ddi->dev, ddi->id);
+	if (rc) {
+		pm_runtime_disable(dev);
+		pm_runtime_set_suspended(dev);
+		pm_runtime_put_noidle(dev);
+	}
+	return rc;
+}
+
+static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
+			  const struct pci_device_id *id)
+{
+	int error, node;
+	struct drv_dev_and_id ddi = { drv, dev, id };
+
+	/* Execute driver initialization on node where the device's
+	   bus is attached to.  This way the driver likely allocates
+	   its local memory on the right node without any need to
+	   change it. */
+	node = dev_to_node(&dev->dev);
+	if (node >= 0) {
+		int cpu;
+
+		get_online_cpus();
+		cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask);
+		if (cpu < nr_cpu_ids)
+			error = work_on_cpu(cpu, local_pci_probe, &ddi);
+		else
+			error = local_pci_probe(&ddi);
+		put_online_cpus();
+	} else
+		error = local_pci_probe(&ddi);
+	return error;
+}
+
+/**
+ * __pci_device_probe - check if a driver wants to claim a specific PCI device
+ * @drv: driver to call to check if it wants the PCI device
+ * @pci_dev: PCI device being probed
+ * 
+ * returns 0 on success, else error.
+ * side-effect: pci_dev->driver is set to drv when drv claims pci_dev.
+ */
+static int
+__pci_device_probe(struct pci_driver *drv, struct pci_dev *pci_dev)
+{
+	const struct pci_device_id *id;
+	int error = 0;
+
+	if (!pci_dev->driver && drv->probe) {
+		error = -ENODEV;
+
+		id = pci_match_device(drv, pci_dev);
+		if (id)
+			error = pci_call_probe(drv, pci_dev, id);
+		if (error >= 0) {
+			pci_dev->driver = drv;
+			error = 0;
+		}
+	}
+	return error;
+}
+
+static int pci_device_probe(struct device * dev)
+{
+	int error = 0;
+	struct pci_driver *drv;
+	struct pci_dev *pci_dev;
+
+	drv = to_pci_driver(dev->driver);
+	pci_dev = to_pci_dev(dev);
+	pci_dev_get(pci_dev);
+	error = __pci_device_probe(drv, pci_dev);
+	if (error)
+		pci_dev_put(pci_dev);
+
+	return error;
+}
+
+static int pci_device_remove(struct device * dev)
+{
+	struct pci_dev * pci_dev = to_pci_dev(dev);
+	struct pci_driver * drv = pci_dev->driver;
+
+	if (drv) {
+		if (drv->remove) {
+			pm_runtime_get_sync(dev);
+			drv->remove(pci_dev);
+			pm_runtime_put_noidle(dev);
+		}
+		pci_dev->driver = NULL;
+	}
+
+	/* Undo the runtime PM settings in local_pci_probe() */
+	pm_runtime_disable(dev);
+	pm_runtime_set_suspended(dev);
+	pm_runtime_put_noidle(dev);
+
+	/*
+	 * If the device is still on, set the power state as "unknown",
+	 * since it might change by the next time we load the driver.
+	 */
+	if (pci_dev->current_state == PCI_D0)
+		pci_dev->current_state = PCI_UNKNOWN;
+
+	/*
+	 * We would love to complain here if pci_dev->is_enabled is set, that
+	 * the driver should have called pci_disable_device(), but the
+	 * unfortunate fact is there are too many odd BIOS and bridge setups
+	 * that don't like drivers doing that all of the time.  
+	 * Oh well, we can dream of sane hardware when we sleep, no matter how
+	 * horrible the crap we have to deal with is when we are awake...
+	 */
+
+	pci_dev_put(pci_dev);
+	return 0;
+}
+
+static void pci_device_shutdown(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct pci_driver *drv = pci_dev->driver;
+
+	if (drv && drv->shutdown)
+		drv->shutdown(pci_dev);
+	pci_msi_shutdown(pci_dev);
+	pci_msix_shutdown(pci_dev);
+}
+
+#ifdef CONFIG_PM
+
+/* Auxiliary functions used for system resume and run-time resume. */
+
+/**
+ * pci_restore_standard_config - restore standard config registers of PCI device
+ * @pci_dev: PCI device to handle
+ */
+static int pci_restore_standard_config(struct pci_dev *pci_dev)
+{
+	pci_update_current_state(pci_dev, PCI_UNKNOWN);
+
+	if (pci_dev->current_state != PCI_D0) {
+		int error = pci_set_power_state(pci_dev, PCI_D0);
+		if (error)
+			return error;
+	}
+
+	pci_restore_state(pci_dev);
+	return 0;
+}
+
+static void pci_pm_default_resume_early(struct pci_dev *pci_dev)
+{
+	pci_restore_standard_config(pci_dev);
+	pci_fixup_device(pci_fixup_resume_early, pci_dev);
+}
+
+#endif
+
+#ifdef CONFIG_PM_SLEEP
+
+/*
+ * Default "suspend" method for devices that have no driver provided suspend,
+ * or not even a driver at all (second part).
+ */
+static void pci_pm_set_unknown_state(struct pci_dev *pci_dev)
+{
+	/*
+	 * mark its power state as "unknown", since we don't know if
+	 * e.g. the BIOS will change its device state when we suspend.
+	 */
+	if (pci_dev->current_state == PCI_D0)
+		pci_dev->current_state = PCI_UNKNOWN;
+}
+
+/*
+ * Default "resume" method for devices that have no driver provided resume,
+ * or not even a driver at all (second part).
+ */
+static int pci_pm_reenable_device(struct pci_dev *pci_dev)
+{
+	int retval;
+
+	/* if the device was enabled before suspend, reenable */
+	retval = pci_reenable_device(pci_dev);
+	/*
+	 * if the device was busmaster before the suspend, make it busmaster
+	 * again
+	 */
+	if (pci_dev->is_busmaster)
+		pci_set_master(pci_dev);
+
+	return retval;
+}
+
+static int pci_legacy_suspend(struct device *dev, pm_message_t state)
+{
+	struct pci_dev * pci_dev = to_pci_dev(dev);
+	struct pci_driver * drv = pci_dev->driver;
+
+	if (drv && drv->suspend) {
+		pci_power_t prev = pci_dev->current_state;
+		int error;
+
+		error = drv->suspend(pci_dev, state);
+		suspend_report_result(drv->suspend, error);
+		if (error)
+			return error;
+
+		if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
+		    && pci_dev->current_state != PCI_UNKNOWN) {
+			WARN_ONCE(pci_dev->current_state != prev,
+				"PCI PM: Device state not saved by %pF\n",
+				drv->suspend);
+		}
+	}
+
+	pci_fixup_device(pci_fixup_suspend, pci_dev);
+
+	return 0;
+}
+
+static int pci_legacy_suspend_late(struct device *dev, pm_message_t state)
+{
+	struct pci_dev * pci_dev = to_pci_dev(dev);
+	struct pci_driver * drv = pci_dev->driver;
+
+	if (drv && drv->suspend_late) {
+		pci_power_t prev = pci_dev->current_state;
+		int error;
+
+		error = drv->suspend_late(pci_dev, state);
+		suspend_report_result(drv->suspend_late, error);
+		if (error)
+			return error;
+
+		if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
+		    && pci_dev->current_state != PCI_UNKNOWN) {
+			WARN_ONCE(pci_dev->current_state != prev,
+				"PCI PM: Device state not saved by %pF\n",
+				drv->suspend_late);
+			return 0;
+		}
+	}
+
+	if (!pci_dev->state_saved)
+		pci_save_state(pci_dev);
+
+	pci_pm_set_unknown_state(pci_dev);
+
+	return 0;
+}
+
+static int pci_legacy_resume_early(struct device *dev)
+{
+	struct pci_dev * pci_dev = to_pci_dev(dev);
+	struct pci_driver * drv = pci_dev->driver;
+
+	return drv && drv->resume_early ?
+			drv->resume_early(pci_dev) : 0;
+}
+
+static int pci_legacy_resume(struct device *dev)
+{
+	struct pci_dev * pci_dev = to_pci_dev(dev);
+	struct pci_driver * drv = pci_dev->driver;
+
+	pci_fixup_device(pci_fixup_resume, pci_dev);
+
+	return drv && drv->resume ?
+			drv->resume(pci_dev) : pci_pm_reenable_device(pci_dev);
+}
+
+/* Auxiliary functions used by the new power management framework */
+
+static void pci_pm_default_resume(struct pci_dev *pci_dev)
+{
+	pci_fixup_device(pci_fixup_resume, pci_dev);
+
+	if (!pci_is_bridge(pci_dev))
+		pci_enable_wake(pci_dev, PCI_D0, false);
+}
+
+static void pci_pm_default_suspend(struct pci_dev *pci_dev)
+{
+	/* Disable non-bridge devices without PM support */
+	if (!pci_is_bridge(pci_dev))
+		pci_disable_enabled_device(pci_dev);
+}
+
+static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev)
+{
+	struct pci_driver *drv = pci_dev->driver;
+	bool ret = drv && (drv->suspend || drv->suspend_late || drv->resume
+		|| drv->resume_early);
+
+	/*
+	 * Legacy PM support is used by default, so warn if the new framework is
+	 * supported as well.  Drivers are supposed to support either the
+	 * former, or the latter, but not both at the same time.
+	 */
+	WARN_ON(ret && drv->driver.pm);
+
+	return ret;
+}
+
+/* New power management framework */
+
+static int pci_pm_prepare(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int error = 0;
+
+	/*
+	 * PCI devices suspended at run time need to be resumed at this
+	 * point, because in general it is necessary to reconfigure them for
+	 * system suspend.  Namely, if the device is supposed to wake up the
+	 * system from the sleep state, we may need to reconfigure it for this
+	 * purpose.  In turn, if the device is not supposed to wake up the
+	 * system from the sleep state, we'll have to prevent it from signaling
+	 * wake-up.
+	 */
+	pm_runtime_get_sync(dev);
+
+	if (drv && drv->pm && drv->pm->prepare)
+		error = drv->pm->prepare(dev);
+
+	return error;
+}
+
+static void pci_pm_complete(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+
+	if (drv && drv->pm && drv->pm->complete)
+		drv->pm->complete(dev);
+
+	pm_runtime_put_sync(dev);
+}
+
+#else /* !CONFIG_PM_SLEEP */
+
+#define pci_pm_prepare	NULL
+#define pci_pm_complete	NULL
+
+#endif /* !CONFIG_PM_SLEEP */
+
+#ifdef CONFIG_SUSPEND
+
+static int pci_pm_suspend(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	if (pci_has_legacy_pm_support(pci_dev))
+		return pci_legacy_suspend(dev, PMSG_SUSPEND);
+
+	if (!pm) {
+		pci_pm_default_suspend(pci_dev);
+		goto Fixup;
+	}
+
+	if (pm->suspend) {
+		pci_power_t prev = pci_dev->current_state;
+		int error;
+
+		error = pm->suspend(dev);
+		suspend_report_result(pm->suspend, error);
+		if (error)
+			return error;
+
+		if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
+		    && pci_dev->current_state != PCI_UNKNOWN) {
+			WARN_ONCE(pci_dev->current_state != prev,
+				"PCI PM: State of device not saved by %pF\n",
+				pm->suspend);
+		}
+	}
+
+ Fixup:
+	pci_fixup_device(pci_fixup_suspend, pci_dev);
+
+	return 0;
+}
+
+static int pci_pm_suspend_noirq(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	if (pci_has_legacy_pm_support(pci_dev))
+		return pci_legacy_suspend_late(dev, PMSG_SUSPEND);
+
+	if (!pm) {
+		pci_save_state(pci_dev);
+		return 0;
+	}
+
+	if (pm->suspend_noirq) {
+		pci_power_t prev = pci_dev->current_state;
+		int error;
+
+		error = pm->suspend_noirq(dev);
+		suspend_report_result(pm->suspend_noirq, error);
+		if (error)
+			return error;
+
+		if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
+		    && pci_dev->current_state != PCI_UNKNOWN) {
+			WARN_ONCE(pci_dev->current_state != prev,
+				"PCI PM: State of device not saved by %pF\n",
+				pm->suspend_noirq);
+			return 0;
+		}
+	}
+
+	if (!pci_dev->state_saved) {
+		pci_save_state(pci_dev);
+		if (!pci_is_bridge(pci_dev))
+			pci_prepare_to_sleep(pci_dev);
+	}
+
+	pci_pm_set_unknown_state(pci_dev);
+
+	return 0;
+}
+
+static int pci_pm_resume_noirq(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct device_driver *drv = dev->driver;
+	int error = 0;
+
+	pci_pm_default_resume_early(pci_dev);
+
+	if (pci_has_legacy_pm_support(pci_dev))
+		return pci_legacy_resume_early(dev);
+
+	if (drv && drv->pm && drv->pm->resume_noirq)
+		error = drv->pm->resume_noirq(dev);
+
+	return error;
+}
+
+static int pci_pm_resume(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+	int error = 0;
+
+	/*
+	 * This is necessary for the suspend error path in which resume is
+	 * called without restoring the standard config registers of the device.
+	 */
+	if (pci_dev->state_saved)
+		pci_restore_standard_config(pci_dev);
+
+	if (pci_has_legacy_pm_support(pci_dev))
+		return pci_legacy_resume(dev);
+
+	pci_pm_default_resume(pci_dev);
+
+	if (pm) {
+		if (pm->resume)
+			error = pm->resume(dev);
+	} else {
+		pci_pm_reenable_device(pci_dev);
+	}
+
+	return error;
+}
+
+#else /* !CONFIG_SUSPEND */
+
+#define pci_pm_suspend		NULL
+#define pci_pm_suspend_noirq	NULL
+#define pci_pm_resume		NULL
+#define pci_pm_resume_noirq	NULL
+
+#endif /* !CONFIG_SUSPEND */
+
+#ifdef CONFIG_HIBERNATE_CALLBACKS
+
+static int pci_pm_freeze(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	if (pci_has_legacy_pm_support(pci_dev))
+		return pci_legacy_suspend(dev, PMSG_FREEZE);
+
+	if (!pm) {
+		pci_pm_default_suspend(pci_dev);
+		return 0;
+	}
+
+	if (pm->freeze) {
+		int error;
+
+		error = pm->freeze(dev);
+		suspend_report_result(pm->freeze, error);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+static int pci_pm_freeze_noirq(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct device_driver *drv = dev->driver;
+
+	if (pci_has_legacy_pm_support(pci_dev))
+		return pci_legacy_suspend_late(dev, PMSG_FREEZE);
+
+	if (drv && drv->pm && drv->pm->freeze_noirq) {
+		int error;
+
+		error = drv->pm->freeze_noirq(dev);
+		suspend_report_result(drv->pm->freeze_noirq, error);
+		if (error)
+			return error;
+	}
+
+	if (!pci_dev->state_saved)
+		pci_save_state(pci_dev);
+
+	pci_pm_set_unknown_state(pci_dev);
+
+	return 0;
+}
+
+static int pci_pm_thaw_noirq(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct device_driver *drv = dev->driver;
+	int error = 0;
+
+	if (pci_has_legacy_pm_support(pci_dev))
+		return pci_legacy_resume_early(dev);
+
+	pci_update_current_state(pci_dev, PCI_D0);
+
+	if (drv && drv->pm && drv->pm->thaw_noirq)
+		error = drv->pm->thaw_noirq(dev);
+
+	return error;
+}
+
+static int pci_pm_thaw(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+	int error = 0;
+
+	if (pci_has_legacy_pm_support(pci_dev))
+		return pci_legacy_resume(dev);
+
+	if (pm) {
+		if (pm->thaw)
+			error = pm->thaw(dev);
+	} else {
+		pci_pm_reenable_device(pci_dev);
+	}
+
+	pci_dev->state_saved = false;
+
+	return error;
+}
+
+static int pci_pm_poweroff(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	if (pci_has_legacy_pm_support(pci_dev))
+		return pci_legacy_suspend(dev, PMSG_HIBERNATE);
+
+	if (!pm) {
+		pci_pm_default_suspend(pci_dev);
+		goto Fixup;
+	}
+
+	if (pm->poweroff) {
+		int error;
+
+		error = pm->poweroff(dev);
+		suspend_report_result(pm->poweroff, error);
+		if (error)
+			return error;
+	}
+
+ Fixup:
+	pci_fixup_device(pci_fixup_suspend, pci_dev);
+
+	return 0;
+}
+
+static int pci_pm_poweroff_noirq(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct device_driver *drv = dev->driver;
+
+	if (pci_has_legacy_pm_support(to_pci_dev(dev)))
+		return pci_legacy_suspend_late(dev, PMSG_HIBERNATE);
+
+	if (!drv || !drv->pm)
+		return 0;
+
+	if (drv->pm->poweroff_noirq) {
+		int error;
+
+		error = drv->pm->poweroff_noirq(dev);
+		suspend_report_result(drv->pm->poweroff_noirq, error);
+		if (error)
+			return error;
+	}
+
+	if (!pci_dev->state_saved && !pci_is_bridge(pci_dev))
+		pci_prepare_to_sleep(pci_dev);
+
+	return 0;
+}
+
+static int pci_pm_restore_noirq(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct device_driver *drv = dev->driver;
+	int error = 0;
+
+	pci_pm_default_resume_early(pci_dev);
+
+	if (pci_has_legacy_pm_support(pci_dev))
+		return pci_legacy_resume_early(dev);
+
+	if (drv && drv->pm && drv->pm->restore_noirq)
+		error = drv->pm->restore_noirq(dev);
+
+	return error;
+}
+
+static int pci_pm_restore(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+	int error = 0;
+
+	/*
+	 * This is necessary for the hibernation error path in which restore is
+	 * called without restoring the standard config registers of the device.
+	 */
+	if (pci_dev->state_saved)
+		pci_restore_standard_config(pci_dev);
+
+	if (pci_has_legacy_pm_support(pci_dev))
+		return pci_legacy_resume(dev);
+
+	pci_pm_default_resume(pci_dev);
+
+	if (pm) {
+		if (pm->restore)
+			error = pm->restore(dev);
+	} else {
+		pci_pm_reenable_device(pci_dev);
+	}
+
+	return error;
+}
+
+#else /* !CONFIG_HIBERNATE_CALLBACKS */
+
+#define pci_pm_freeze		NULL
+#define pci_pm_freeze_noirq	NULL
+#define pci_pm_thaw		NULL
+#define pci_pm_thaw_noirq	NULL
+#define pci_pm_poweroff		NULL
+#define pci_pm_poweroff_noirq	NULL
+#define pci_pm_restore		NULL
+#define pci_pm_restore_noirq	NULL
+
+#endif /* !CONFIG_HIBERNATE_CALLBACKS */
+
+#ifdef CONFIG_PM_RUNTIME
+
+static int pci_pm_runtime_suspend(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+	pci_power_t prev = pci_dev->current_state;
+	int error;
+
+	if (!pm || !pm->runtime_suspend)
+		return -ENOSYS;
+
+	error = pm->runtime_suspend(dev);
+	suspend_report_result(pm->runtime_suspend, error);
+	if (error)
+		return error;
+
+	pci_fixup_device(pci_fixup_suspend, pci_dev);
+
+	if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
+	    && pci_dev->current_state != PCI_UNKNOWN) {
+		WARN_ONCE(pci_dev->current_state != prev,
+			"PCI PM: State of device not saved by %pF\n",
+			pm->runtime_suspend);
+		return 0;
+	}
+
+	if (!pci_dev->state_saved)
+		pci_save_state(pci_dev);
+
+	pci_finish_runtime_suspend(pci_dev);
+
+	return 0;
+}
+
+static int pci_pm_runtime_resume(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	if (!pm || !pm->runtime_resume)
+		return -ENOSYS;
+
+	pci_pm_default_resume_early(pci_dev);
+	__pci_enable_wake(pci_dev, PCI_D0, true, false);
+	pci_fixup_device(pci_fixup_resume, pci_dev);
+
+	return pm->runtime_resume(dev);
+}
+
+static int pci_pm_runtime_idle(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	if (!pm)
+		return -ENOSYS;
+
+	if (pm->runtime_idle) {
+		int ret = pm->runtime_idle(dev);
+		if (ret)
+			return ret;
+	}
+
+	pm_runtime_suspend(dev);
+
+	return 0;
+}
+
+#else /* !CONFIG_PM_RUNTIME */
+
+#define pci_pm_runtime_suspend	NULL
+#define pci_pm_runtime_resume	NULL
+#define pci_pm_runtime_idle	NULL
+
+#endif /* !CONFIG_PM_RUNTIME */
+
+#ifdef CONFIG_PM
+
+const struct dev_pm_ops pci_dev_pm_ops = {
+	.prepare = pci_pm_prepare,
+	.complete = pci_pm_complete,
+	.suspend = pci_pm_suspend,
+	.resume = pci_pm_resume,
+	.freeze = pci_pm_freeze,
+	.thaw = pci_pm_thaw,
+	.poweroff = pci_pm_poweroff,
+	.restore = pci_pm_restore,
+	.suspend_noirq = pci_pm_suspend_noirq,
+	.resume_noirq = pci_pm_resume_noirq,
+	.freeze_noirq = pci_pm_freeze_noirq,
+	.thaw_noirq = pci_pm_thaw_noirq,
+	.poweroff_noirq = pci_pm_poweroff_noirq,
+	.restore_noirq = pci_pm_restore_noirq,
+	.runtime_suspend = pci_pm_runtime_suspend,
+	.runtime_resume = pci_pm_runtime_resume,
+	.runtime_idle = pci_pm_runtime_idle,
+};
+
+#define PCI_PM_OPS_PTR	(&pci_dev_pm_ops)
+
+#else /* !COMFIG_PM_OPS */
+
+#define PCI_PM_OPS_PTR	NULL
+
+#endif /* !COMFIG_PM_OPS */
+
+/**
+ * __pci_register_driver - register a new pci driver
+ * @drv: the driver structure to register
+ * @owner: owner module of drv
+ * @mod_name: module name string
+ * 
+ * Adds the driver structure to the list of registered drivers.
+ * Returns a negative value on error, otherwise 0. 
+ * If no error occurred, the driver remains registered even if 
+ * no device was claimed during registration.
+ */
+int __pci_register_driver(struct pci_driver *drv, struct module *owner,
+			  const char *mod_name)
+{
+	int error;
+
+	/* initialize common driver fields */
+	drv->driver.name = drv->name;
+	drv->driver.bus = &pci_bus_type;
+	drv->driver.owner = owner;
+	drv->driver.mod_name = mod_name;
+
+	spin_lock_init(&drv->dynids.lock);
+	INIT_LIST_HEAD(&drv->dynids.list);
+
+	/* register with core */
+	error = driver_register(&drv->driver);
+	if (error)
+		goto out;
+
+	error = pci_create_newid_file(drv);
+	if (error)
+		goto out_newid;
+
+	error = pci_create_removeid_file(drv);
+	if (error)
+		goto out_removeid;
+out:
+	return error;
+
+out_removeid:
+	pci_remove_newid_file(drv);
+out_newid:
+	driver_unregister(&drv->driver);
+	goto out;
+}
+
+/**
+ * pci_unregister_driver - unregister a pci driver
+ * @drv: the driver structure to unregister
+ * 
+ * Deletes the driver structure from the list of registered PCI drivers,
+ * gives it a chance to clean up by calling its remove() function for
+ * each device it was responsible for, and marks those devices as
+ * driverless.
+ */
+
+void
+pci_unregister_driver(struct pci_driver *drv)
+{
+	pci_remove_removeid_file(drv);
+	pci_remove_newid_file(drv);
+	driver_unregister(&drv->driver);
+	pci_free_dynids(drv);
+}
+
+static struct pci_driver pci_compat_driver = {
+	.name = "compat"
+};
+
+/**
+ * pci_dev_driver - get the pci_driver of a device
+ * @dev: the device to query
+ *
+ * Returns the appropriate pci_driver structure or %NULL if there is no 
+ * registered driver for the device.
+ */
+struct pci_driver *
+pci_dev_driver(const struct pci_dev *dev)
+{
+	if (dev->driver)
+		return dev->driver;
+	else {
+		int i;
+		for(i=0; i<=PCI_ROM_RESOURCE; i++)
+			if (dev->resource[i].flags & IORESOURCE_BUSY)
+				return &pci_compat_driver;
+	}
+	return NULL;
+}
+
+/**
+ * pci_bus_match - Tell if a PCI device structure has a matching PCI device id structure
+ * @dev: the PCI device structure to match against
+ * @drv: the device driver to search for matching PCI device id structures
+ * 
+ * Used by a driver to check whether a PCI device present in the
+ * system is in its list of supported devices. Returns the matching
+ * pci_device_id structure or %NULL if there is no match.
+ */
+static int pci_bus_match(struct device *dev, struct device_driver *drv)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct pci_driver *pci_drv = to_pci_driver(drv);
+	const struct pci_device_id *found_id;
+
+	found_id = pci_match_device(pci_drv, pci_dev);
+	if (found_id)
+		return 1;
+
+	return 0;
+}
+
+/**
+ * pci_dev_get - increments the reference count of the pci device structure
+ * @dev: the device being referenced
+ *
+ * Each live reference to a device should be refcounted.
+ *
+ * Drivers for PCI devices should normally record such references in
+ * their probe() methods, when they bind to a device, and release
+ * them by calling pci_dev_put(), in their disconnect() methods.
+ *
+ * A pointer to the device with the incremented reference counter is returned.
+ */
+struct pci_dev *pci_dev_get(struct pci_dev *dev)
+{
+	if (dev)
+		get_device(&dev->dev);
+	return dev;
+}
+
+/**
+ * pci_dev_put - release a use of the pci device structure
+ * @dev: device that's been disconnected
+ *
+ * Must be called when a user of a device is finished with it.  When the last
+ * user of the device calls this function, the memory of the device is freed.
+ */
+void pci_dev_put(struct pci_dev *dev)
+{
+	if (dev)
+		put_device(&dev->dev);
+}
+
+#ifndef CONFIG_HOTPLUG
+int pci_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	return -ENODEV;
+}
+#endif
+
+struct bus_type pci_bus_type = {
+	.name		= "pci",
+	.match		= pci_bus_match,
+	.uevent		= pci_uevent,
+	.probe		= pci_device_probe,
+	.remove		= pci_device_remove,
+	.shutdown	= pci_device_shutdown,
+	.dev_attrs	= pci_dev_attrs,
+	.bus_attrs	= pci_bus_attrs,
+	.pm		= PCI_PM_OPS_PTR,
+};
+
+static int __init pci_driver_init(void)
+{
+	return bus_register(&pci_bus_type);
+}
+
+postcore_initcall(pci_driver_init);
+
+EXPORT_SYMBOL_GPL(pci_add_dynid);
+EXPORT_SYMBOL(pci_match_id);
+EXPORT_SYMBOL(__pci_register_driver);
+EXPORT_SYMBOL(pci_unregister_driver);
+EXPORT_SYMBOL(pci_dev_driver);
+EXPORT_SYMBOL(pci_bus_type);
+EXPORT_SYMBOL(pci_dev_get);
+EXPORT_SYMBOL(pci_dev_put);
diff --git a/drivers/pci/pci-label.c b/drivers/pci/pci-label.c
new file mode 100644
index 00000000..77cb2a14
--- /dev/null
+++ b/drivers/pci/pci-label.c
@@ -0,0 +1,383 @@
+/*
+ * Purpose: Export the firmware instance and label associated with
+ * a pci device to sysfs
+ * Copyright (C) 2010 Dell Inc.
+ * by Narendra K <Narendra_K@dell.com>,
+ * Jordan Hargrave <Jordan_Hargrave@dell.com>
+ *
+ * PCI Firmware Specification Revision 3.1 section 4.6.7 (DSM for Naming a
+ * PCI or PCI Express Device Under Operating Systems) defines an instance
+ * number and string name. This code retrieves them and exports them to sysfs.
+ * If the system firmware does not provide the ACPI _DSM (Device Specific
+ * Method), then the SMBIOS type 41 instance number and string is exported to
+ * sysfs.
+ *
+ * SMBIOS defines type 41 for onboard pci devices. This code retrieves
+ * the instance number and string from the type 41 record and exports
+ * it to sysfs.
+ *
+ * Please see http://linux.dell.com/wiki/index.php/Oss/libnetdevname for more
+ * information.
+ */
+
+#include <linux/dmi.h>
+#include <linux/sysfs.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/nls.h>
+#include <linux/acpi.h>
+#include <linux/pci-acpi.h>
+#include <acpi/acpi_bus.h>
+#include "pci.h"
+
+#define	DEVICE_LABEL_DSM	0x07
+
+#ifndef CONFIG_DMI
+
+static inline int
+pci_create_smbiosname_file(struct pci_dev *pdev)
+{
+	return -1;
+}
+
+static inline void
+pci_remove_smbiosname_file(struct pci_dev *pdev)
+{
+}
+
+#else
+
+enum smbios_attr_enum {
+	SMBIOS_ATTR_NONE = 0,
+	SMBIOS_ATTR_LABEL_SHOW,
+	SMBIOS_ATTR_INSTANCE_SHOW,
+};
+
+static mode_t
+find_smbios_instance_string(struct pci_dev *pdev, char *buf,
+			    enum smbios_attr_enum attribute)
+{
+	const struct dmi_device *dmi;
+	struct dmi_dev_onboard *donboard;
+	int bus;
+	int devfn;
+
+	bus = pdev->bus->number;
+	devfn = pdev->devfn;
+
+	dmi = NULL;
+	while ((dmi = dmi_find_device(DMI_DEV_TYPE_DEV_ONBOARD,
+				      NULL, dmi)) != NULL) {
+		donboard = dmi->device_data;
+		if (donboard && donboard->bus == bus &&
+					donboard->devfn == devfn) {
+			if (buf) {
+				if (attribute == SMBIOS_ATTR_INSTANCE_SHOW)
+					return scnprintf(buf, PAGE_SIZE,
+							 "%d\n",
+							 donboard->instance);
+				else if (attribute == SMBIOS_ATTR_LABEL_SHOW)
+					return scnprintf(buf, PAGE_SIZE,
+							 "%s\n",
+							 dmi->name);
+			}
+			return strlen(dmi->name);
+		}
+	}
+	return 0;
+}
+
+static mode_t
+smbios_instance_string_exist(struct kobject *kobj, struct attribute *attr,
+			     int n)
+{
+	struct device *dev;
+	struct pci_dev *pdev;
+
+	dev = container_of(kobj, struct device, kobj);
+	pdev = to_pci_dev(dev);
+
+	return find_smbios_instance_string(pdev, NULL, SMBIOS_ATTR_NONE) ?
+					   S_IRUGO : 0;
+}
+
+static ssize_t
+smbioslabel_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct pci_dev *pdev;
+	pdev = to_pci_dev(dev);
+
+	return find_smbios_instance_string(pdev, buf,
+					   SMBIOS_ATTR_LABEL_SHOW);
+}
+
+static ssize_t
+smbiosinstance_show(struct device *dev,
+		    struct device_attribute *attr, char *buf)
+{
+	struct pci_dev *pdev;
+	pdev = to_pci_dev(dev);
+
+	return find_smbios_instance_string(pdev, buf,
+					   SMBIOS_ATTR_INSTANCE_SHOW);
+}
+
+static struct device_attribute smbios_attr_label = {
+	.attr = {.name = "label", .mode = 0444},
+	.show = smbioslabel_show,
+};
+
+static struct device_attribute smbios_attr_instance = {
+	.attr = {.name = "index", .mode = 0444},
+	.show = smbiosinstance_show,
+};
+
+static struct attribute *smbios_attributes[] = {
+	&smbios_attr_label.attr,
+	&smbios_attr_instance.attr,
+	NULL,
+};
+
+static struct attribute_group smbios_attr_group = {
+	.attrs = smbios_attributes,
+	.is_visible = smbios_instance_string_exist,
+};
+
+static int
+pci_create_smbiosname_file(struct pci_dev *pdev)
+{
+	return sysfs_create_group(&pdev->dev.kobj, &smbios_attr_group);
+}
+
+static void
+pci_remove_smbiosname_file(struct pci_dev *pdev)
+{
+	sysfs_remove_group(&pdev->dev.kobj, &smbios_attr_group);
+}
+
+#endif
+
+#ifndef CONFIG_ACPI
+
+static inline int
+pci_create_acpi_index_label_files(struct pci_dev *pdev)
+{
+	return -1;
+}
+
+static inline int
+pci_remove_acpi_index_label_files(struct pci_dev *pdev)
+{
+	return -1;
+}
+
+static inline bool
+device_has_dsm(struct device *dev)
+{
+	return false;
+}
+
+#else
+
+static const char device_label_dsm_uuid[] = {
+	0xD0, 0x37, 0xC9, 0xE5, 0x53, 0x35, 0x7A, 0x4D,
+	0x91, 0x17, 0xEA, 0x4D, 0x19, 0xC3, 0x43, 0x4D
+};
+
+enum acpi_attr_enum {
+	ACPI_ATTR_NONE = 0,
+	ACPI_ATTR_LABEL_SHOW,
+	ACPI_ATTR_INDEX_SHOW,
+};
+
+static void dsm_label_utf16s_to_utf8s(union acpi_object *obj, char *buf)
+{
+	int len;
+	len = utf16s_to_utf8s((const wchar_t *)obj->
+			      package.elements[1].string.pointer,
+			      obj->package.elements[1].string.length,
+			      UTF16_LITTLE_ENDIAN,
+			      buf, PAGE_SIZE);
+	buf[len] = '\n';
+}
+
+static int
+dsm_get_label(acpi_handle handle, int func,
+	      struct acpi_buffer *output,
+	      char *buf, enum acpi_attr_enum attribute)
+{
+	struct acpi_object_list input;
+	union acpi_object params[4];
+	union acpi_object *obj;
+	int len = 0;
+
+	int err;
+
+	input.count = 4;
+	input.pointer = params;
+	params[0].type = ACPI_TYPE_BUFFER;
+	params[0].buffer.length = sizeof(device_label_dsm_uuid);
+	params[0].buffer.pointer = (char *)device_label_dsm_uuid;
+	params[1].type = ACPI_TYPE_INTEGER;
+	params[1].integer.value = 0x02;
+	params[2].type = ACPI_TYPE_INTEGER;
+	params[2].integer.value = func;
+	params[3].type = ACPI_TYPE_PACKAGE;
+	params[3].package.count = 0;
+	params[3].package.elements = NULL;
+
+	err = acpi_evaluate_object(handle, "_DSM", &input, output);
+	if (err)
+		return -1;
+
+	obj = (union acpi_object *)output->pointer;
+
+	switch (obj->type) {
+	case ACPI_TYPE_PACKAGE:
+		if (obj->package.count != 2)
+			break;
+		len = obj->package.elements[0].integer.value;
+		if (buf) {
+			if (attribute == ACPI_ATTR_INDEX_SHOW)
+				scnprintf(buf, PAGE_SIZE, "%llu\n",
+				obj->package.elements[0].integer.value);
+			else if (attribute == ACPI_ATTR_LABEL_SHOW)
+				dsm_label_utf16s_to_utf8s(obj, buf);
+			kfree(output->pointer);
+			return strlen(buf);
+		}
+		kfree(output->pointer);
+		return len;
+	break;
+	default:
+		kfree(output->pointer);
+	}
+	return -1;
+}
+
+static bool
+device_has_dsm(struct device *dev)
+{
+	acpi_handle handle;
+	struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
+
+	handle = DEVICE_ACPI_HANDLE(dev);
+
+	if (!handle)
+		return FALSE;
+
+	if (dsm_get_label(handle, DEVICE_LABEL_DSM, &output, NULL,
+			  ACPI_ATTR_NONE) > 0)
+		return TRUE;
+
+	return FALSE;
+}
+
+static mode_t
+acpi_index_string_exist(struct kobject *kobj, struct attribute *attr, int n)
+{
+	struct device *dev;
+
+	dev = container_of(kobj, struct device, kobj);
+
+	if (device_has_dsm(dev))
+		return S_IRUGO;
+
+	return 0;
+}
+
+static ssize_t
+acpilabel_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
+	acpi_handle handle;
+	int length;
+
+	handle = DEVICE_ACPI_HANDLE(dev);
+
+	if (!handle)
+		return -1;
+
+	length = dsm_get_label(handle, DEVICE_LABEL_DSM,
+			       &output, buf, ACPI_ATTR_LABEL_SHOW);
+
+	if (length < 1)
+		return -1;
+
+	return length;
+}
+
+static ssize_t
+acpiindex_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
+	acpi_handle handle;
+	int length;
+
+	handle = DEVICE_ACPI_HANDLE(dev);
+
+	if (!handle)
+		return -1;
+
+	length = dsm_get_label(handle, DEVICE_LABEL_DSM,
+			       &output, buf, ACPI_ATTR_INDEX_SHOW);
+
+	if (length < 0)
+		return -1;
+
+	return length;
+
+}
+
+static struct device_attribute acpi_attr_label = {
+	.attr = {.name = "label", .mode = 0444},
+	.show = acpilabel_show,
+};
+
+static struct device_attribute acpi_attr_index = {
+	.attr = {.name = "acpi_index", .mode = 0444},
+	.show = acpiindex_show,
+};
+
+static struct attribute *acpi_attributes[] = {
+	&acpi_attr_label.attr,
+	&acpi_attr_index.attr,
+	NULL,
+};
+
+static struct attribute_group acpi_attr_group = {
+	.attrs = acpi_attributes,
+	.is_visible = acpi_index_string_exist,
+};
+
+static int
+pci_create_acpi_index_label_files(struct pci_dev *pdev)
+{
+	return sysfs_create_group(&pdev->dev.kobj, &acpi_attr_group);
+}
+
+static int
+pci_remove_acpi_index_label_files(struct pci_dev *pdev)
+{
+	sysfs_remove_group(&pdev->dev.kobj, &acpi_attr_group);
+	return 0;
+}
+#endif
+
+void pci_create_firmware_label_files(struct pci_dev *pdev)
+{
+	if (device_has_dsm(&pdev->dev))
+		pci_create_acpi_index_label_files(pdev);
+	else
+		pci_create_smbiosname_file(pdev);
+}
+
+void pci_remove_firmware_label_files(struct pci_dev *pdev)
+{
+	if (device_has_dsm(&pdev->dev))
+		pci_remove_acpi_index_label_files(pdev);
+	else
+		pci_remove_smbiosname_file(pdev);
+}
diff --git a/drivers/pci/pci-stub.c b/drivers/pci/pci-stub.c
new file mode 100644
index 00000000..775e933c
--- /dev/null
+++ b/drivers/pci/pci-stub.c
@@ -0,0 +1,97 @@
+/* pci-stub - simple stub driver to reserve a pci device
+ *
+ * Copyright (C) 2008 Red Hat, Inc.
+ * Author:
+ * 	Chris Wright
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Usage is simple, allocate a new id to the stub driver and bind the
+ * device to it.  For example:
+ * 
+ * # echo "8086 10f5" > /sys/bus/pci/drivers/pci-stub/new_id
+ * # echo -n 0000:00:19.0 > /sys/bus/pci/drivers/e1000e/unbind
+ * # echo -n 0000:00:19.0 > /sys/bus/pci/drivers/pci-stub/bind
+ * # ls -l /sys/bus/pci/devices/0000:00:19.0/driver
+ * .../0000:00:19.0/driver -> ../../../bus/pci/drivers/pci-stub
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+
+static char ids[1024] __initdata;
+
+module_param_string(ids, ids, sizeof(ids), 0);
+MODULE_PARM_DESC(ids, "Initial PCI IDs to add to the stub driver, format is "
+		 "\"vendor:device[:subvendor[:subdevice[:class[:class_mask]]]]\""
+		 " and multiple comma separated entries can be specified");
+
+static int pci_stub_probe(struct pci_dev *dev, const struct pci_device_id *id)
+{
+	dev_printk(KERN_INFO, &dev->dev, "claimed by stub\n");
+	return 0;
+}
+
+static struct pci_driver stub_driver = {
+	.name		= "pci-stub",
+	.id_table	= NULL,	/* only dynamic id's */
+	.probe		= pci_stub_probe,
+};
+
+static int __init pci_stub_init(void)
+{
+	char *p, *id;
+	int rc;
+
+	rc = pci_register_driver(&stub_driver);
+	if (rc)
+		return rc;
+
+	/* no ids passed actually */
+	if (ids[0] == '\0')
+		return 0;
+
+	/* add ids specified in the module parameter */
+	p = ids;
+	while ((id = strsep(&p, ","))) {
+		unsigned int vendor, device, subvendor = PCI_ANY_ID,
+			subdevice = PCI_ANY_ID, class=0, class_mask=0;
+		int fields;
+
+		if (!strlen(id))
+			continue;
+
+		fields = sscanf(id, "%x:%x:%x:%x:%x:%x",
+				&vendor, &device, &subvendor, &subdevice,
+				&class, &class_mask);
+
+		if (fields < 2) {
+			printk(KERN_WARNING
+			       "pci-stub: invalid id string \"%s\"\n", id);
+			continue;
+		}
+
+		printk(KERN_INFO
+		       "pci-stub: add %04X:%04X sub=%04X:%04X cls=%08X/%08X\n",
+		       vendor, device, subvendor, subdevice, class, class_mask);
+
+		rc = pci_add_dynid(&stub_driver, vendor, device,
+				   subvendor, subdevice, class, class_mask, 0);
+		if (rc)
+			printk(KERN_WARNING
+			       "pci-stub: failed to add dynamic id (%d)\n", rc);
+	}
+
+	return 0;
+}
+
+static void __exit pci_stub_exit(void)
+{
+	pci_unregister_driver(&stub_driver);
+}
+
+module_init(pci_stub_init);
+module_exit(pci_stub_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Chris Wright <chrisw@sous-sol.org>");
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
new file mode 100644
index 00000000..7bcf12ad
--- /dev/null
+++ b/drivers/pci/pci-sysfs.c
@@ -0,0 +1,1333 @@
+/*
+ * drivers/pci/pci-sysfs.c
+ *
+ * (C) Copyright 2002-2004 Greg Kroah-Hartman <greg@kroah.com>
+ * (C) Copyright 2002-2004 IBM Corp.
+ * (C) Copyright 2003 Matthew Wilcox
+ * (C) Copyright 2003 Hewlett-Packard
+ * (C) Copyright 2004 Jon Smirl <jonsmirl@yahoo.com>
+ * (C) Copyright 2004 Silicon Graphics, Inc. Jesse Barnes <jbarnes@sgi.com>
+ *
+ * File attributes for PCI devices
+ *
+ * Modeled after usb's driverfs.c 
+ *
+ */
+
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/pci.h>
+#include <linux/stat.h>
+#include <linux/topology.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/capability.h>
+#include <linux/security.h>
+#include <linux/pci-aspm.h>
+#include <linux/slab.h>
+#include "pci.h"
+
+static int sysfs_initialized;	/* = 0 */
+
+/* show configuration fields */
+#define pci_config_attr(field, format_string)				\
+static ssize_t								\
+field##_show(struct device *dev, struct device_attribute *attr, char *buf)				\
+{									\
+	struct pci_dev *pdev;						\
+									\
+	pdev = to_pci_dev (dev);					\
+	return sprintf (buf, format_string, pdev->field);		\
+}
+
+pci_config_attr(vendor, "0x%04x\n");
+pci_config_attr(device, "0x%04x\n");
+pci_config_attr(subsystem_vendor, "0x%04x\n");
+pci_config_attr(subsystem_device, "0x%04x\n");
+pci_config_attr(class, "0x%06x\n");
+pci_config_attr(irq, "%u\n");
+
+static ssize_t broken_parity_status_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	return sprintf (buf, "%u\n", pdev->broken_parity_status);
+}
+
+static ssize_t broken_parity_status_store(struct device *dev,
+					  struct device_attribute *attr,
+					  const char *buf, size_t count)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	unsigned long val;
+
+	if (strict_strtoul(buf, 0, &val) < 0)
+		return -EINVAL;
+
+	pdev->broken_parity_status = !!val;
+
+	return count;
+}
+
+static ssize_t local_cpus_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{		
+	const struct cpumask *mask;
+	int len;
+
+#ifdef CONFIG_NUMA
+	mask = (dev_to_node(dev) == -1) ? cpu_online_mask :
+					  cpumask_of_node(dev_to_node(dev));
+#else
+	mask = cpumask_of_pcibus(to_pci_dev(dev)->bus);
+#endif
+	len = cpumask_scnprintf(buf, PAGE_SIZE-2, mask);
+	buf[len++] = '\n';
+	buf[len] = '\0';
+	return len;
+}
+
+
+static ssize_t local_cpulist_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	const struct cpumask *mask;
+	int len;
+
+#ifdef CONFIG_NUMA
+	mask = (dev_to_node(dev) == -1) ? cpu_online_mask :
+					  cpumask_of_node(dev_to_node(dev));
+#else
+	mask = cpumask_of_pcibus(to_pci_dev(dev)->bus);
+#endif
+	len = cpulist_scnprintf(buf, PAGE_SIZE-2, mask);
+	buf[len++] = '\n';
+	buf[len] = '\0';
+	return len;
+}
+
+/*
+ * PCI Bus Class Devices
+ */
+static ssize_t pci_bus_show_cpuaffinity(struct device *dev,
+					int type,
+					struct device_attribute *attr,
+					char *buf)
+{
+	int ret;
+	const struct cpumask *cpumask;
+
+	cpumask = cpumask_of_pcibus(to_pci_bus(dev));
+	ret = type ?
+		cpulist_scnprintf(buf, PAGE_SIZE-2, cpumask) :
+		cpumask_scnprintf(buf, PAGE_SIZE-2, cpumask);
+	buf[ret++] = '\n';
+	buf[ret] = '\0';
+	return ret;
+}
+
+static inline ssize_t pci_bus_show_cpumaskaffinity(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	return pci_bus_show_cpuaffinity(dev, 0, attr, buf);
+}
+
+static inline ssize_t pci_bus_show_cpulistaffinity(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	return pci_bus_show_cpuaffinity(dev, 1, attr, buf);
+}
+
+/* show resources */
+static ssize_t
+resource_show(struct device * dev, struct device_attribute *attr, char * buf)
+{
+	struct pci_dev * pci_dev = to_pci_dev(dev);
+	char * str = buf;
+	int i;
+	int max;
+	resource_size_t start, end;
+
+	if (pci_dev->subordinate)
+		max = DEVICE_COUNT_RESOURCE;
+	else
+		max = PCI_BRIDGE_RESOURCES;
+
+	for (i = 0; i < max; i++) {
+		struct resource *res =  &pci_dev->resource[i];
+		pci_resource_to_user(pci_dev, i, res, &start, &end);
+		str += sprintf(str,"0x%016llx 0x%016llx 0x%016llx\n",
+			       (unsigned long long)start,
+			       (unsigned long long)end,
+			       (unsigned long long)res->flags);
+	}
+	return (str - buf);
+}
+
+static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+
+	return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02x\n",
+		       pci_dev->vendor, pci_dev->device,
+		       pci_dev->subsystem_vendor, pci_dev->subsystem_device,
+		       (u8)(pci_dev->class >> 16), (u8)(pci_dev->class >> 8),
+		       (u8)(pci_dev->class));
+}
+
+static ssize_t is_enabled_store(struct device *dev,
+				struct device_attribute *attr, const char *buf,
+				size_t count)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	unsigned long val;
+	ssize_t result = strict_strtoul(buf, 0, &val);
+
+	if (result < 0)
+		return result;
+
+	/* this can crash the machine when done on the "wrong" device */
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!val) {
+		if (pci_is_enabled(pdev))
+			pci_disable_device(pdev);
+		else
+			result = -EIO;
+	} else
+		result = pci_enable_device(pdev);
+
+	return result < 0 ? result : count;
+}
+
+static ssize_t is_enabled_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct pci_dev *pdev;
+
+	pdev = to_pci_dev (dev);
+	return sprintf (buf, "%u\n", atomic_read(&pdev->enable_cnt));
+}
+
+#ifdef CONFIG_NUMA
+static ssize_t
+numa_node_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return sprintf (buf, "%d\n", dev->numa_node);
+}
+#endif
+
+static ssize_t
+dma_mask_bits_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	return sprintf (buf, "%d\n", fls64(pdev->dma_mask));
+}
+
+static ssize_t
+consistent_dma_mask_bits_show(struct device *dev, struct device_attribute *attr,
+				 char *buf)
+{
+	return sprintf (buf, "%d\n", fls64(dev->coherent_dma_mask));
+}
+
+static ssize_t
+msi_bus_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	if (!pdev->subordinate)
+		return 0;
+
+	return sprintf (buf, "%u\n",
+			!(pdev->subordinate->bus_flags & PCI_BUS_FLAGS_NO_MSI));
+}
+
+static ssize_t
+msi_bus_store(struct device *dev, struct device_attribute *attr,
+	      const char *buf, size_t count)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	unsigned long val;
+
+	if (strict_strtoul(buf, 0, &val) < 0)
+		return -EINVAL;
+
+	/* bad things may happen if the no_msi flag is changed
+	 * while some drivers are loaded */
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* Maybe pci devices without subordinate busses shouldn't even have this
+	 * attribute in the first place?  */
+	if (!pdev->subordinate)
+		return count;
+
+	/* Is the flag going to change, or keep the value it already had? */
+	if (!(pdev->subordinate->bus_flags & PCI_BUS_FLAGS_NO_MSI) ^
+	    !!val) {
+		pdev->subordinate->bus_flags ^= PCI_BUS_FLAGS_NO_MSI;
+
+		dev_warn(&pdev->dev, "forced subordinate bus to%s support MSI,"
+			 " bad things could happen\n", val ? "" : " not");
+	}
+
+	return count;
+}
+
+#ifdef CONFIG_HOTPLUG
+static DEFINE_MUTEX(pci_remove_rescan_mutex);
+static ssize_t bus_rescan_store(struct bus_type *bus, const char *buf,
+				size_t count)
+{
+	unsigned long val;
+	struct pci_bus *b = NULL;
+
+	if (strict_strtoul(buf, 0, &val) < 0)
+		return -EINVAL;
+
+	if (val) {
+		mutex_lock(&pci_remove_rescan_mutex);
+		while ((b = pci_find_next_bus(b)) != NULL)
+			pci_rescan_bus(b);
+		mutex_unlock(&pci_remove_rescan_mutex);
+	}
+	return count;
+}
+
+struct bus_attribute pci_bus_attrs[] = {
+	__ATTR(rescan, (S_IWUSR|S_IWGRP), NULL, bus_rescan_store),
+	__ATTR_NULL
+};
+
+static ssize_t
+dev_rescan_store(struct device *dev, struct device_attribute *attr,
+		 const char *buf, size_t count)
+{
+	unsigned long val;
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	if (strict_strtoul(buf, 0, &val) < 0)
+		return -EINVAL;
+
+	if (val) {
+		mutex_lock(&pci_remove_rescan_mutex);
+		pci_rescan_bus(pdev->bus);
+		mutex_unlock(&pci_remove_rescan_mutex);
+	}
+	return count;
+}
+
+static void remove_callback(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	mutex_lock(&pci_remove_rescan_mutex);
+	pci_remove_bus_device(pdev);
+	mutex_unlock(&pci_remove_rescan_mutex);
+}
+
+static ssize_t
+remove_store(struct device *dev, struct device_attribute *dummy,
+	     const char *buf, size_t count)
+{
+	int ret = 0;
+	unsigned long val;
+
+	if (strict_strtoul(buf, 0, &val) < 0)
+		return -EINVAL;
+
+	/* An attribute cannot be unregistered by one of its own methods,
+	 * so we have to use this roundabout approach.
+	 */
+	if (val)
+		ret = device_schedule_callback(dev, remove_callback);
+	if (ret)
+		count = ret;
+	return count;
+}
+
+static ssize_t
+dev_bus_rescan_store(struct device *dev, struct device_attribute *attr,
+		 const char *buf, size_t count)
+{
+	unsigned long val;
+	struct pci_bus *bus = to_pci_bus(dev);
+
+	if (strict_strtoul(buf, 0, &val) < 0)
+		return -EINVAL;
+
+	if (val) {
+		mutex_lock(&pci_remove_rescan_mutex);
+		pci_rescan_bus(bus);
+		mutex_unlock(&pci_remove_rescan_mutex);
+	}
+	return count;
+}
+
+#endif
+
+struct device_attribute pci_dev_attrs[] = {
+	__ATTR_RO(resource),
+	__ATTR_RO(vendor),
+	__ATTR_RO(device),
+	__ATTR_RO(subsystem_vendor),
+	__ATTR_RO(subsystem_device),
+	__ATTR_RO(class),
+	__ATTR_RO(irq),
+	__ATTR_RO(local_cpus),
+	__ATTR_RO(local_cpulist),
+	__ATTR_RO(modalias),
+#ifdef CONFIG_NUMA
+	__ATTR_RO(numa_node),
+#endif
+	__ATTR_RO(dma_mask_bits),
+	__ATTR_RO(consistent_dma_mask_bits),
+	__ATTR(enable, 0600, is_enabled_show, is_enabled_store),
+	__ATTR(broken_parity_status,(S_IRUGO|S_IWUSR),
+		broken_parity_status_show,broken_parity_status_store),
+	__ATTR(msi_bus, 0644, msi_bus_show, msi_bus_store),
+#ifdef CONFIG_HOTPLUG
+	__ATTR(remove, (S_IWUSR|S_IWGRP), NULL, remove_store),
+	__ATTR(rescan, (S_IWUSR|S_IWGRP), NULL, dev_rescan_store),
+#endif
+	__ATTR_NULL,
+};
+
+struct device_attribute pcibus_dev_attrs[] = {
+#ifdef CONFIG_HOTPLUG
+	__ATTR(rescan, (S_IWUSR|S_IWGRP), NULL, dev_bus_rescan_store),
+#endif
+	__ATTR(cpuaffinity, S_IRUGO, pci_bus_show_cpumaskaffinity, NULL),
+	__ATTR(cpulistaffinity, S_IRUGO, pci_bus_show_cpulistaffinity, NULL),
+	__ATTR_NULL,
+};
+
+static ssize_t
+boot_vga_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	return sprintf(buf, "%u\n",
+		!!(pdev->resource[PCI_ROM_RESOURCE].flags &
+		   IORESOURCE_ROM_SHADOW));
+}
+struct device_attribute vga_attr = __ATTR_RO(boot_vga);
+
+static ssize_t
+pci_read_config(struct file *filp, struct kobject *kobj,
+		struct bin_attribute *bin_attr,
+		char *buf, loff_t off, size_t count)
+{
+	struct pci_dev *dev = to_pci_dev(container_of(kobj,struct device,kobj));
+	unsigned int size = 64;
+	loff_t init_off = off;
+	u8 *data = (u8*) buf;
+
+	/* Several chips lock up trying to read undefined config space */
+	if (security_capable(&init_user_ns, filp->f_cred, CAP_SYS_ADMIN) == 0) {
+		size = dev->cfg_size;
+	} else if (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) {
+		size = 128;
+	}
+
+	if (off > size)
+		return 0;
+	if (off + count > size) {
+		size -= off;
+		count = size;
+	} else {
+		size = count;
+	}
+
+	if ((off & 1) && size) {
+		u8 val;
+		pci_user_read_config_byte(dev, off, &val);
+		data[off - init_off] = val;
+		off++;
+		size--;
+	}
+
+	if ((off & 3) && size > 2) {
+		u16 val;
+		pci_user_read_config_word(dev, off, &val);
+		data[off - init_off] = val & 0xff;
+		data[off - init_off + 1] = (val >> 8) & 0xff;
+		off += 2;
+		size -= 2;
+	}
+
+	while (size > 3) {
+		u32 val;
+		pci_user_read_config_dword(dev, off, &val);
+		data[off - init_off] = val & 0xff;
+		data[off - init_off + 1] = (val >> 8) & 0xff;
+		data[off - init_off + 2] = (val >> 16) & 0xff;
+		data[off - init_off + 3] = (val >> 24) & 0xff;
+		off += 4;
+		size -= 4;
+	}
+
+	if (size >= 2) {
+		u16 val;
+		pci_user_read_config_word(dev, off, &val);
+		data[off - init_off] = val & 0xff;
+		data[off - init_off + 1] = (val >> 8) & 0xff;
+		off += 2;
+		size -= 2;
+	}
+
+	if (size > 0) {
+		u8 val;
+		pci_user_read_config_byte(dev, off, &val);
+		data[off - init_off] = val;
+		off++;
+		--size;
+	}
+
+	return count;
+}
+
+static ssize_t
+pci_write_config(struct file* filp, struct kobject *kobj,
+		 struct bin_attribute *bin_attr,
+		 char *buf, loff_t off, size_t count)
+{
+	struct pci_dev *dev = to_pci_dev(container_of(kobj,struct device,kobj));
+	unsigned int size = count;
+	loff_t init_off = off;
+	u8 *data = (u8*) buf;
+
+	if (off > dev->cfg_size)
+		return 0;
+	if (off + count > dev->cfg_size) {
+		size = dev->cfg_size - off;
+		count = size;
+	}
+	
+	if ((off & 1) && size) {
+		pci_user_write_config_byte(dev, off, data[off - init_off]);
+		off++;
+		size--;
+	}
+	
+	if ((off & 3) && size > 2) {
+		u16 val = data[off - init_off];
+		val |= (u16) data[off - init_off + 1] << 8;
+                pci_user_write_config_word(dev, off, val);
+                off += 2;
+                size -= 2;
+        }
+
+	while (size > 3) {
+		u32 val = data[off - init_off];
+		val |= (u32) data[off - init_off + 1] << 8;
+		val |= (u32) data[off - init_off + 2] << 16;
+		val |= (u32) data[off - init_off + 3] << 24;
+		pci_user_write_config_dword(dev, off, val);
+		off += 4;
+		size -= 4;
+	}
+	
+	if (size >= 2) {
+		u16 val = data[off - init_off];
+		val |= (u16) data[off - init_off + 1] << 8;
+		pci_user_write_config_word(dev, off, val);
+		off += 2;
+		size -= 2;
+	}
+
+	if (size) {
+		pci_user_write_config_byte(dev, off, data[off - init_off]);
+		off++;
+		--size;
+	}
+
+	return count;
+}
+
+static ssize_t
+read_vpd_attr(struct file *filp, struct kobject *kobj,
+	      struct bin_attribute *bin_attr,
+	      char *buf, loff_t off, size_t count)
+{
+	struct pci_dev *dev =
+		to_pci_dev(container_of(kobj, struct device, kobj));
+
+	if (off > bin_attr->size)
+		count = 0;
+	else if (count > bin_attr->size - off)
+		count = bin_attr->size - off;
+
+	return pci_read_vpd(dev, off, count, buf);
+}
+
+static ssize_t
+write_vpd_attr(struct file *filp, struct kobject *kobj,
+	       struct bin_attribute *bin_attr,
+	       char *buf, loff_t off, size_t count)
+{
+	struct pci_dev *dev =
+		to_pci_dev(container_of(kobj, struct device, kobj));
+
+	if (off > bin_attr->size)
+		count = 0;
+	else if (count > bin_attr->size - off)
+		count = bin_attr->size - off;
+
+	return pci_write_vpd(dev, off, count, buf);
+}
+
+#ifdef HAVE_PCI_LEGACY
+/**
+ * pci_read_legacy_io - read byte(s) from legacy I/O port space
+ * @filp: open sysfs file
+ * @kobj: kobject corresponding to file to read from
+ * @bin_attr: struct bin_attribute for this file
+ * @buf: buffer to store results
+ * @off: offset into legacy I/O port space
+ * @count: number of bytes to read
+ *
+ * Reads 1, 2, or 4 bytes from legacy I/O port space using an arch specific
+ * callback routine (pci_legacy_read).
+ */
+static ssize_t
+pci_read_legacy_io(struct file *filp, struct kobject *kobj,
+		   struct bin_attribute *bin_attr,
+		   char *buf, loff_t off, size_t count)
+{
+        struct pci_bus *bus = to_pci_bus(container_of(kobj,
+                                                      struct device,
+						      kobj));
+
+        /* Only support 1, 2 or 4 byte accesses */
+        if (count != 1 && count != 2 && count != 4)
+                return -EINVAL;
+
+        return pci_legacy_read(bus, off, (u32 *)buf, count);
+}
+
+/**
+ * pci_write_legacy_io - write byte(s) to legacy I/O port space
+ * @filp: open sysfs file
+ * @kobj: kobject corresponding to file to read from
+ * @bin_attr: struct bin_attribute for this file
+ * @buf: buffer containing value to be written
+ * @off: offset into legacy I/O port space
+ * @count: number of bytes to write
+ *
+ * Writes 1, 2, or 4 bytes from legacy I/O port space using an arch specific
+ * callback routine (pci_legacy_write).
+ */
+static ssize_t
+pci_write_legacy_io(struct file *filp, struct kobject *kobj,
+		    struct bin_attribute *bin_attr,
+		    char *buf, loff_t off, size_t count)
+{
+        struct pci_bus *bus = to_pci_bus(container_of(kobj,
+						      struct device,
+						      kobj));
+        /* Only support 1, 2 or 4 byte accesses */
+        if (count != 1 && count != 2 && count != 4)
+                return -EINVAL;
+
+        return pci_legacy_write(bus, off, *(u32 *)buf, count);
+}
+
+/**
+ * pci_mmap_legacy_mem - map legacy PCI memory into user memory space
+ * @filp: open sysfs file
+ * @kobj: kobject corresponding to device to be mapped
+ * @attr: struct bin_attribute for this file
+ * @vma: struct vm_area_struct passed to mmap
+ *
+ * Uses an arch specific callback, pci_mmap_legacy_mem_page_range, to mmap
+ * legacy memory space (first meg of bus space) into application virtual
+ * memory space.
+ */
+static int
+pci_mmap_legacy_mem(struct file *filp, struct kobject *kobj,
+		    struct bin_attribute *attr,
+                    struct vm_area_struct *vma)
+{
+        struct pci_bus *bus = to_pci_bus(container_of(kobj,
+                                                      struct device,
+						      kobj));
+
+        return pci_mmap_legacy_page_range(bus, vma, pci_mmap_mem);
+}
+
+/**
+ * pci_mmap_legacy_io - map legacy PCI IO into user memory space
+ * @filp: open sysfs file
+ * @kobj: kobject corresponding to device to be mapped
+ * @attr: struct bin_attribute for this file
+ * @vma: struct vm_area_struct passed to mmap
+ *
+ * Uses an arch specific callback, pci_mmap_legacy_io_page_range, to mmap
+ * legacy IO space (first meg of bus space) into application virtual
+ * memory space. Returns -ENOSYS if the operation isn't supported
+ */
+static int
+pci_mmap_legacy_io(struct file *filp, struct kobject *kobj,
+		   struct bin_attribute *attr,
+		   struct vm_area_struct *vma)
+{
+        struct pci_bus *bus = to_pci_bus(container_of(kobj,
+                                                      struct device,
+						      kobj));
+
+        return pci_mmap_legacy_page_range(bus, vma, pci_mmap_io);
+}
+
+/**
+ * pci_adjust_legacy_attr - adjustment of legacy file attributes
+ * @b: bus to create files under
+ * @mmap_type: I/O port or memory
+ *
+ * Stub implementation. Can be overridden by arch if necessary.
+ */
+void __weak
+pci_adjust_legacy_attr(struct pci_bus *b, enum pci_mmap_state mmap_type)
+{
+	return;
+}
+
+/**
+ * pci_create_legacy_files - create legacy I/O port and memory files
+ * @b: bus to create files under
+ *
+ * Some platforms allow access to legacy I/O port and ISA memory space on
+ * a per-bus basis.  This routine creates the files and ties them into
+ * their associated read, write and mmap files from pci-sysfs.c
+ *
+ * On error unwind, but don't propagate the error to the caller
+ * as it is ok to set up the PCI bus without these files.
+ */
+void pci_create_legacy_files(struct pci_bus *b)
+{
+	int error;
+
+	b->legacy_io = kzalloc(sizeof(struct bin_attribute) * 2,
+			       GFP_ATOMIC);
+	if (!b->legacy_io)
+		goto kzalloc_err;
+
+	sysfs_bin_attr_init(b->legacy_io);
+	b->legacy_io->attr.name = "legacy_io";
+	b->legacy_io->size = 0xffff;
+	b->legacy_io->attr.mode = S_IRUSR | S_IWUSR;
+	b->legacy_io->read = pci_read_legacy_io;
+	b->legacy_io->write = pci_write_legacy_io;
+	b->legacy_io->mmap = pci_mmap_legacy_io;
+	pci_adjust_legacy_attr(b, pci_mmap_io);
+	error = device_create_bin_file(&b->dev, b->legacy_io);
+	if (error)
+		goto legacy_io_err;
+
+	/* Allocated above after the legacy_io struct */
+	b->legacy_mem = b->legacy_io + 1;
+	sysfs_bin_attr_init(b->legacy_mem);
+	b->legacy_mem->attr.name = "legacy_mem";
+	b->legacy_mem->size = 1024*1024;
+	b->legacy_mem->attr.mode = S_IRUSR | S_IWUSR;
+	b->legacy_mem->mmap = pci_mmap_legacy_mem;
+	pci_adjust_legacy_attr(b, pci_mmap_mem);
+	error = device_create_bin_file(&b->dev, b->legacy_mem);
+	if (error)
+		goto legacy_mem_err;
+
+	return;
+
+legacy_mem_err:
+	device_remove_bin_file(&b->dev, b->legacy_io);
+legacy_io_err:
+	kfree(b->legacy_io);
+	b->legacy_io = NULL;
+kzalloc_err:
+	printk(KERN_WARNING "pci: warning: could not create legacy I/O port "
+	       "and ISA memory resources to sysfs\n");
+	return;
+}
+
+void pci_remove_legacy_files(struct pci_bus *b)
+{
+	if (b->legacy_io) {
+		device_remove_bin_file(&b->dev, b->legacy_io);
+		device_remove_bin_file(&b->dev, b->legacy_mem);
+		kfree(b->legacy_io); /* both are allocated here */
+	}
+}
+#endif /* HAVE_PCI_LEGACY */
+
+#ifdef HAVE_PCI_MMAP
+
+int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vma,
+		  enum pci_mmap_api mmap_api)
+{
+	unsigned long nr, start, size, pci_start;
+
+	if (pci_resource_len(pdev, resno) == 0)
+		return 0;
+	nr = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	start = vma->vm_pgoff;
+	size = ((pci_resource_len(pdev, resno) - 1) >> PAGE_SHIFT) + 1;
+	pci_start = (mmap_api == PCI_MMAP_PROCFS) ?
+			pci_resource_start(pdev, resno) >> PAGE_SHIFT : 0;
+	if (start >= pci_start && start < pci_start + size &&
+			start + nr <= pci_start + size)
+		return 1;
+	return 0;
+}
+
+/**
+ * pci_mmap_resource - map a PCI resource into user memory space
+ * @kobj: kobject for mapping
+ * @attr: struct bin_attribute for the file being mapped
+ * @vma: struct vm_area_struct passed into the mmap
+ * @write_combine: 1 for write_combine mapping
+ *
+ * Use the regular PCI mapping routines to map a PCI resource into userspace.
+ */
+static int
+pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
+		  struct vm_area_struct *vma, int write_combine)
+{
+	struct pci_dev *pdev = to_pci_dev(container_of(kobj,
+						       struct device, kobj));
+	struct resource *res = attr->private;
+	enum pci_mmap_state mmap_type;
+	resource_size_t start, end;
+	int i;
+
+	for (i = 0; i < PCI_ROM_RESOURCE; i++)
+		if (res == &pdev->resource[i])
+			break;
+	if (i >= PCI_ROM_RESOURCE)
+		return -ENODEV;
+
+	if (!pci_mmap_fits(pdev, i, vma, PCI_MMAP_SYSFS)) {
+		WARN(1, "process \"%s\" tried to map 0x%08lx bytes "
+			"at page 0x%08lx on %s BAR %d (start 0x%16Lx, size 0x%16Lx)\n",
+			current->comm, vma->vm_end-vma->vm_start, vma->vm_pgoff,
+			pci_name(pdev), i,
+			(u64)pci_resource_start(pdev, i),
+			(u64)pci_resource_len(pdev, i));
+		return -EINVAL;
+	}
+
+	/* pci_mmap_page_range() expects the same kind of entry as coming
+	 * from /proc/bus/pci/ which is a "user visible" value. If this is
+	 * different from the resource itself, arch will do necessary fixup.
+	 */
+	pci_resource_to_user(pdev, i, res, &start, &end);
+	vma->vm_pgoff += start >> PAGE_SHIFT;
+	mmap_type = res->flags & IORESOURCE_MEM ? pci_mmap_mem : pci_mmap_io;
+
+	if (res->flags & IORESOURCE_MEM && iomem_is_exclusive(start))
+		return -EINVAL;
+
+	return pci_mmap_page_range(pdev, vma, mmap_type, write_combine);
+}
+
+static int
+pci_mmap_resource_uc(struct file *filp, struct kobject *kobj,
+		     struct bin_attribute *attr,
+		     struct vm_area_struct *vma)
+{
+	return pci_mmap_resource(kobj, attr, vma, 0);
+}
+
+static int
+pci_mmap_resource_wc(struct file *filp, struct kobject *kobj,
+		     struct bin_attribute *attr,
+		     struct vm_area_struct *vma)
+{
+	return pci_mmap_resource(kobj, attr, vma, 1);
+}
+
+static ssize_t
+pci_resource_io(struct file *filp, struct kobject *kobj,
+		struct bin_attribute *attr, char *buf,
+		loff_t off, size_t count, bool write)
+{
+	struct pci_dev *pdev = to_pci_dev(container_of(kobj,
+						       struct device, kobj));
+	struct resource *res = attr->private;
+	unsigned long port = off;
+	int i;
+
+	for (i = 0; i < PCI_ROM_RESOURCE; i++)
+		if (res == &pdev->resource[i])
+			break;
+	if (i >= PCI_ROM_RESOURCE)
+		return -ENODEV;
+
+	port += pci_resource_start(pdev, i);
+
+	if (port > pci_resource_end(pdev, i))
+		return 0;
+
+	if (port + count - 1 > pci_resource_end(pdev, i))
+		return -EINVAL;
+
+	switch (count) {
+	case 1:
+		if (write)
+			outb(*(u8 *)buf, port);
+		else
+			*(u8 *)buf = inb(port);
+		return 1;
+	case 2:
+		if (write)
+			outw(*(u16 *)buf, port);
+		else
+			*(u16 *)buf = inw(port);
+		return 2;
+	case 4:
+		if (write)
+			outl(*(u32 *)buf, port);
+		else
+			*(u32 *)buf = inl(port);
+		return 4;
+	}
+	return -EINVAL;
+}
+
+static ssize_t
+pci_read_resource_io(struct file *filp, struct kobject *kobj,
+		     struct bin_attribute *attr, char *buf,
+		     loff_t off, size_t count)
+{
+	return pci_resource_io(filp, kobj, attr, buf, off, count, false);
+}
+
+static ssize_t
+pci_write_resource_io(struct file *filp, struct kobject *kobj,
+		      struct bin_attribute *attr, char *buf,
+		      loff_t off, size_t count)
+{
+	return pci_resource_io(filp, kobj, attr, buf, off, count, true);
+}
+
+/**
+ * pci_remove_resource_files - cleanup resource files
+ * @pdev: dev to cleanup
+ *
+ * If we created resource files for @pdev, remove them from sysfs and
+ * free their resources.
+ */
+static void
+pci_remove_resource_files(struct pci_dev *pdev)
+{
+	int i;
+
+	for (i = 0; i < PCI_ROM_RESOURCE; i++) {
+		struct bin_attribute *res_attr;
+
+		res_attr = pdev->res_attr[i];
+		if (res_attr) {
+			sysfs_remove_bin_file(&pdev->dev.kobj, res_attr);
+			kfree(res_attr);
+		}
+
+		res_attr = pdev->res_attr_wc[i];
+		if (res_attr) {
+			sysfs_remove_bin_file(&pdev->dev.kobj, res_attr);
+			kfree(res_attr);
+		}
+	}
+}
+
+static int pci_create_attr(struct pci_dev *pdev, int num, int write_combine)
+{
+	/* allocate attribute structure, piggyback attribute name */
+	int name_len = write_combine ? 13 : 10;
+	struct bin_attribute *res_attr;
+	int retval;
+
+	res_attr = kzalloc(sizeof(*res_attr) + name_len, GFP_ATOMIC);
+	if (res_attr) {
+		char *res_attr_name = (char *)(res_attr + 1);
+
+		sysfs_bin_attr_init(res_attr);
+		if (write_combine) {
+			pdev->res_attr_wc[num] = res_attr;
+			sprintf(res_attr_name, "resource%d_wc", num);
+			res_attr->mmap = pci_mmap_resource_wc;
+		} else {
+			pdev->res_attr[num] = res_attr;
+			sprintf(res_attr_name, "resource%d", num);
+			res_attr->mmap = pci_mmap_resource_uc;
+		}
+		if (pci_resource_flags(pdev, num) & IORESOURCE_IO) {
+			res_attr->read = pci_read_resource_io;
+			res_attr->write = pci_write_resource_io;
+		}
+		res_attr->attr.name = res_attr_name;
+		res_attr->attr.mode = S_IRUSR | S_IWUSR;
+		res_attr->size = pci_resource_len(pdev, num);
+		res_attr->private = &pdev->resource[num];
+		retval = sysfs_create_bin_file(&pdev->dev.kobj, res_attr);
+	} else
+		retval = -ENOMEM;
+
+	return retval;
+}
+
+/**
+ * pci_create_resource_files - create resource files in sysfs for @dev
+ * @pdev: dev in question
+ *
+ * Walk the resources in @pdev creating files for each resource available.
+ */
+static int pci_create_resource_files(struct pci_dev *pdev)
+{
+	int i;
+	int retval;
+
+	/* Expose the PCI resources from this device as files */
+	for (i = 0; i < PCI_ROM_RESOURCE; i++) {
+
+		/* skip empty resources */
+		if (!pci_resource_len(pdev, i))
+			continue;
+
+		retval = pci_create_attr(pdev, i, 0);
+		/* for prefetchable resources, create a WC mappable file */
+		if (!retval && pdev->resource[i].flags & IORESOURCE_PREFETCH)
+			retval = pci_create_attr(pdev, i, 1);
+
+		if (retval) {
+			pci_remove_resource_files(pdev);
+			return retval;
+		}
+	}
+	return 0;
+}
+#else /* !HAVE_PCI_MMAP */
+int __weak pci_create_resource_files(struct pci_dev *dev) { return 0; }
+void __weak pci_remove_resource_files(struct pci_dev *dev) { return; }
+#endif /* HAVE_PCI_MMAP */
+
+/**
+ * pci_write_rom - used to enable access to the PCI ROM display
+ * @filp: sysfs file
+ * @kobj: kernel object handle
+ * @bin_attr: struct bin_attribute for this file
+ * @buf: user input
+ * @off: file offset
+ * @count: number of byte in input
+ *
+ * writing anything except 0 enables it
+ */
+static ssize_t
+pci_write_rom(struct file *filp, struct kobject *kobj,
+	      struct bin_attribute *bin_attr,
+	      char *buf, loff_t off, size_t count)
+{
+	struct pci_dev *pdev = to_pci_dev(container_of(kobj, struct device, kobj));
+
+	if ((off ==  0) && (*buf == '0') && (count == 2))
+		pdev->rom_attr_enabled = 0;
+	else
+		pdev->rom_attr_enabled = 1;
+
+	return count;
+}
+
+/**
+ * pci_read_rom - read a PCI ROM
+ * @filp: sysfs file
+ * @kobj: kernel object handle
+ * @bin_attr: struct bin_attribute for this file
+ * @buf: where to put the data we read from the ROM
+ * @off: file offset
+ * @count: number of bytes to read
+ *
+ * Put @count bytes starting at @off into @buf from the ROM in the PCI
+ * device corresponding to @kobj.
+ */
+static ssize_t
+pci_read_rom(struct file *filp, struct kobject *kobj,
+	     struct bin_attribute *bin_attr,
+	     char *buf, loff_t off, size_t count)
+{
+	struct pci_dev *pdev = to_pci_dev(container_of(kobj, struct device, kobj));
+	void __iomem *rom;
+	size_t size;
+
+	if (!pdev->rom_attr_enabled)
+		return -EINVAL;
+	
+	rom = pci_map_rom(pdev, &size);	/* size starts out as PCI window size */
+	if (!rom || !size)
+		return -EIO;
+		
+	if (off >= size)
+		count = 0;
+	else {
+		if (off + count > size)
+			count = size - off;
+		
+		memcpy_fromio(buf, rom + off, count);
+	}
+	pci_unmap_rom(pdev, rom);
+		
+	return count;
+}
+
+static struct bin_attribute pci_config_attr = {
+	.attr =	{
+		.name = "config",
+		.mode = S_IRUGO | S_IWUSR,
+	},
+	.size = PCI_CFG_SPACE_SIZE,
+	.read = pci_read_config,
+	.write = pci_write_config,
+};
+
+static struct bin_attribute pcie_config_attr = {
+	.attr =	{
+		.name = "config",
+		.mode = S_IRUGO | S_IWUSR,
+	},
+	.size = PCI_CFG_SPACE_EXP_SIZE,
+	.read = pci_read_config,
+	.write = pci_write_config,
+};
+
+int __attribute__ ((weak)) pcibios_add_platform_entries(struct pci_dev *dev)
+{
+	return 0;
+}
+
+static ssize_t reset_store(struct device *dev,
+			   struct device_attribute *attr, const char *buf,
+			   size_t count)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	unsigned long val;
+	ssize_t result = strict_strtoul(buf, 0, &val);
+
+	if (result < 0)
+		return result;
+
+	if (val != 1)
+		return -EINVAL;
+
+	result = pci_reset_function(pdev);
+	if (result < 0)
+		return result;
+
+	return count;
+}
+
+static struct device_attribute reset_attr = __ATTR(reset, 0200, NULL, reset_store);
+
+static int pci_create_capabilities_sysfs(struct pci_dev *dev)
+{
+	int retval;
+	struct bin_attribute *attr;
+
+	/* If the device has VPD, try to expose it in sysfs. */
+	if (dev->vpd) {
+		attr = kzalloc(sizeof(*attr), GFP_ATOMIC);
+		if (!attr)
+			return -ENOMEM;
+
+		sysfs_bin_attr_init(attr);
+		attr->size = dev->vpd->len;
+		attr->attr.name = "vpd";
+		attr->attr.mode = S_IRUSR | S_IWUSR;
+		attr->read = read_vpd_attr;
+		attr->write = write_vpd_attr;
+		retval = sysfs_create_bin_file(&dev->dev.kobj, attr);
+		if (retval) {
+			kfree(attr);
+			return retval;
+		}
+		dev->vpd->attr = attr;
+	}
+
+	/* Active State Power Management */
+	pcie_aspm_create_sysfs_dev_files(dev);
+
+	if (!pci_probe_reset_function(dev)) {
+		retval = device_create_file(&dev->dev, &reset_attr);
+		if (retval)
+			goto error;
+		dev->reset_fn = 1;
+	}
+	return 0;
+
+error:
+	pcie_aspm_remove_sysfs_dev_files(dev);
+	if (dev->vpd && dev->vpd->attr) {
+		sysfs_remove_bin_file(&dev->dev.kobj, dev->vpd->attr);
+		kfree(dev->vpd->attr);
+	}
+
+	return retval;
+}
+
+int __must_check pci_create_sysfs_dev_files (struct pci_dev *pdev)
+{
+	int retval;
+	int rom_size = 0;
+	struct bin_attribute *attr;
+
+	if (!sysfs_initialized)
+		return -EACCES;
+
+	if (pdev->cfg_size < PCI_CFG_SPACE_EXP_SIZE)
+		retval = sysfs_create_bin_file(&pdev->dev.kobj, &pci_config_attr);
+	else
+		retval = sysfs_create_bin_file(&pdev->dev.kobj, &pcie_config_attr);
+	if (retval)
+		goto err;
+
+	retval = pci_create_resource_files(pdev);
+	if (retval)
+		goto err_config_file;
+
+	if (pci_resource_len(pdev, PCI_ROM_RESOURCE))
+		rom_size = pci_resource_len(pdev, PCI_ROM_RESOURCE);
+	else if (pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW)
+		rom_size = 0x20000;
+
+	/* If the device has a ROM, try to expose it in sysfs. */
+	if (rom_size) {
+		attr = kzalloc(sizeof(*attr), GFP_ATOMIC);
+		if (!attr) {
+			retval = -ENOMEM;
+			goto err_resource_files;
+		}
+		sysfs_bin_attr_init(attr);
+		attr->size = rom_size;
+		attr->attr.name = "rom";
+		attr->attr.mode = S_IRUSR | S_IWUSR;
+		attr->read = pci_read_rom;
+		attr->write = pci_write_rom;
+		retval = sysfs_create_bin_file(&pdev->dev.kobj, attr);
+		if (retval) {
+			kfree(attr);
+			goto err_resource_files;
+		}
+		pdev->rom_attr = attr;
+	}
+
+	if ((pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA) {
+		retval = device_create_file(&pdev->dev, &vga_attr);
+		if (retval)
+			goto err_rom_file;
+	}
+
+	/* add platform-specific attributes */
+	retval = pcibios_add_platform_entries(pdev);
+	if (retval)
+		goto err_vga_file;
+
+	/* add sysfs entries for various capabilities */
+	retval = pci_create_capabilities_sysfs(pdev);
+	if (retval)
+		goto err_vga_file;
+
+	pci_create_firmware_label_files(pdev);
+
+	return 0;
+
+err_vga_file:
+	if ((pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA)
+		device_remove_file(&pdev->dev, &vga_attr);
+err_rom_file:
+	if (rom_size) {
+		sysfs_remove_bin_file(&pdev->dev.kobj, pdev->rom_attr);
+		kfree(pdev->rom_attr);
+		pdev->rom_attr = NULL;
+	}
+err_resource_files:
+	pci_remove_resource_files(pdev);
+err_config_file:
+	if (pdev->cfg_size < PCI_CFG_SPACE_EXP_SIZE)
+		sysfs_remove_bin_file(&pdev->dev.kobj, &pci_config_attr);
+	else
+		sysfs_remove_bin_file(&pdev->dev.kobj, &pcie_config_attr);
+err:
+	return retval;
+}
+
+static void pci_remove_capabilities_sysfs(struct pci_dev *dev)
+{
+	if (dev->vpd && dev->vpd->attr) {
+		sysfs_remove_bin_file(&dev->dev.kobj, dev->vpd->attr);
+		kfree(dev->vpd->attr);
+	}
+
+	pcie_aspm_remove_sysfs_dev_files(dev);
+	if (dev->reset_fn) {
+		device_remove_file(&dev->dev, &reset_attr);
+		dev->reset_fn = 0;
+	}
+}
+
+/**
+ * pci_remove_sysfs_dev_files - cleanup PCI specific sysfs files
+ * @pdev: device whose entries we should free
+ *
+ * Cleanup when @pdev is removed from sysfs.
+ */
+void pci_remove_sysfs_dev_files(struct pci_dev *pdev)
+{
+	int rom_size = 0;
+
+	if (!sysfs_initialized)
+		return;
+
+	pci_remove_capabilities_sysfs(pdev);
+
+	if (pdev->cfg_size < PCI_CFG_SPACE_EXP_SIZE)
+		sysfs_remove_bin_file(&pdev->dev.kobj, &pci_config_attr);
+	else
+		sysfs_remove_bin_file(&pdev->dev.kobj, &pcie_config_attr);
+
+	pci_remove_resource_files(pdev);
+
+	if (pci_resource_len(pdev, PCI_ROM_RESOURCE))
+		rom_size = pci_resource_len(pdev, PCI_ROM_RESOURCE);
+	else if (pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW)
+		rom_size = 0x20000;
+
+	if (rom_size && pdev->rom_attr) {
+		sysfs_remove_bin_file(&pdev->dev.kobj, pdev->rom_attr);
+		kfree(pdev->rom_attr);
+	}
+
+	pci_remove_firmware_label_files(pdev);
+
+}
+
+static int __init pci_sysfs_init(void)
+{
+	struct pci_dev *pdev = NULL;
+	int retval;
+
+	sysfs_initialized = 1;
+	for_each_pci_dev(pdev) {
+		retval = pci_create_sysfs_dev_files(pdev);
+		if (retval) {
+			pci_dev_put(pdev);
+			return retval;
+		}
+	}
+
+	return 0;
+}
+
+late_initcall(pci_sysfs_init);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
new file mode 100644
index 00000000..d549bbc9
--- /dev/null
+++ b/drivers/pci/pci.c
@@ -0,0 +1,3556 @@
+/*
+ *	PCI Bus Services, see include/linux/pci.h for further explanation.
+ *
+ *	Copyright 1993 -- 1997 Drew Eckhardt, Frederic Potter,
+ *	David Mosberger-Tang
+ *
+ *	Copyright 1997 -- 2000 Martin Mares <mj@ucw.cz>
+ */
+
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/pm.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/log2.h>
+#include <linux/pci-aspm.h>
+#include <linux/pm_wakeup.h>
+#include <linux/interrupt.h>
+#include <linux/device.h>
+#include <linux/pm_runtime.h>
+#include <asm/setup.h>
+#include "pci.h"
+
+const char *pci_power_names[] = {
+	"error", "D0", "D1", "D2", "D3hot", "D3cold", "unknown",
+};
+EXPORT_SYMBOL_GPL(pci_power_names);
+
+int isa_dma_bridge_buggy;
+EXPORT_SYMBOL(isa_dma_bridge_buggy);
+
+int pci_pci_problems;
+EXPORT_SYMBOL(pci_pci_problems);
+
+unsigned int pci_pm_d3_delay;
+
+static void pci_pme_list_scan(struct work_struct *work);
+
+static LIST_HEAD(pci_pme_list);
+static DEFINE_MUTEX(pci_pme_list_mutex);
+static DECLARE_DELAYED_WORK(pci_pme_work, pci_pme_list_scan);
+
+struct pci_pme_device {
+	struct list_head list;
+	struct pci_dev *dev;
+};
+
+#define PME_TIMEOUT 1000 /* How long between PME checks */
+
+static void pci_dev_d3_sleep(struct pci_dev *dev)
+{
+	unsigned int delay = dev->d3_delay;
+
+	if (delay < pci_pm_d3_delay)
+		delay = pci_pm_d3_delay;
+
+	msleep(delay);
+}
+
+#ifdef CONFIG_PCI_DOMAINS
+int pci_domains_supported = 1;
+#endif
+
+#define DEFAULT_CARDBUS_IO_SIZE		(256)
+#define DEFAULT_CARDBUS_MEM_SIZE	(64*1024*1024)
+/* pci=cbmemsize=nnM,cbiosize=nn can override this */
+unsigned long pci_cardbus_io_size = DEFAULT_CARDBUS_IO_SIZE;
+unsigned long pci_cardbus_mem_size = DEFAULT_CARDBUS_MEM_SIZE;
+
+#define DEFAULT_HOTPLUG_IO_SIZE		(256)
+#define DEFAULT_HOTPLUG_MEM_SIZE	(2*1024*1024)
+/* pci=hpmemsize=nnM,hpiosize=nn can override this */
+unsigned long pci_hotplug_io_size  = DEFAULT_HOTPLUG_IO_SIZE;
+unsigned long pci_hotplug_mem_size = DEFAULT_HOTPLUG_MEM_SIZE;
+
+/*
+ * The default CLS is used if arch didn't set CLS explicitly and not
+ * all pci devices agree on the same value.  Arch can override either
+ * the dfl or actual value as it sees fit.  Don't forget this is
+ * measured in 32-bit words, not bytes.
+ */
+u8 pci_dfl_cache_line_size __devinitdata = L1_CACHE_BYTES >> 2;
+u8 pci_cache_line_size;
+
+/**
+ * pci_bus_max_busnr - returns maximum PCI bus number of given bus' children
+ * @bus: pointer to PCI bus structure to search
+ *
+ * Given a PCI bus, returns the highest PCI bus number present in the set
+ * including the given PCI bus and its list of child PCI buses.
+ */
+unsigned char pci_bus_max_busnr(struct pci_bus* bus)
+{
+	struct list_head *tmp;
+	unsigned char max, n;
+
+	max = bus->subordinate;
+	list_for_each(tmp, &bus->children) {
+		n = pci_bus_max_busnr(pci_bus_b(tmp));
+		if(n > max)
+			max = n;
+	}
+	return max;
+}
+EXPORT_SYMBOL_GPL(pci_bus_max_busnr);
+
+#ifdef CONFIG_HAS_IOMEM
+void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar)
+{
+	/*
+	 * Make sure the BAR is actually a memory resource, not an IO resource
+	 */
+	if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) {
+		WARN_ON(1);
+		return NULL;
+	}
+	return ioremap_nocache(pci_resource_start(pdev, bar),
+				     pci_resource_len(pdev, bar));
+}
+EXPORT_SYMBOL_GPL(pci_ioremap_bar);
+#endif
+
+#if 0
+/**
+ * pci_max_busnr - returns maximum PCI bus number
+ *
+ * Returns the highest PCI bus number present in the system global list of
+ * PCI buses.
+ */
+unsigned char __devinit
+pci_max_busnr(void)
+{
+	struct pci_bus *bus = NULL;
+	unsigned char max, n;
+
+	max = 0;
+	while ((bus = pci_find_next_bus(bus)) != NULL) {
+		n = pci_bus_max_busnr(bus);
+		if(n > max)
+			max = n;
+	}
+	return max;
+}
+
+#endif  /*  0  */
+
+#define PCI_FIND_CAP_TTL	48
+
+static int __pci_find_next_cap_ttl(struct pci_bus *bus, unsigned int devfn,
+				   u8 pos, int cap, int *ttl)
+{
+	u8 id;
+
+	while ((*ttl)--) {
+		pci_bus_read_config_byte(bus, devfn, pos, &pos);
+		if (pos < 0x40)
+			break;
+		pos &= ~3;
+		pci_bus_read_config_byte(bus, devfn, pos + PCI_CAP_LIST_ID,
+					 &id);
+		if (id == 0xff)
+			break;
+		if (id == cap)
+			return pos;
+		pos += PCI_CAP_LIST_NEXT;
+	}
+	return 0;
+}
+
+static int __pci_find_next_cap(struct pci_bus *bus, unsigned int devfn,
+			       u8 pos, int cap)
+{
+	int ttl = PCI_FIND_CAP_TTL;
+
+	return __pci_find_next_cap_ttl(bus, devfn, pos, cap, &ttl);
+}
+
+int pci_find_next_capability(struct pci_dev *dev, u8 pos, int cap)
+{
+	return __pci_find_next_cap(dev->bus, dev->devfn,
+				   pos + PCI_CAP_LIST_NEXT, cap);
+}
+EXPORT_SYMBOL_GPL(pci_find_next_capability);
+
+static int __pci_bus_find_cap_start(struct pci_bus *bus,
+				    unsigned int devfn, u8 hdr_type)
+{
+	u16 status;
+
+	pci_bus_read_config_word(bus, devfn, PCI_STATUS, &status);
+	if (!(status & PCI_STATUS_CAP_LIST))
+		return 0;
+
+	switch (hdr_type) {
+	case PCI_HEADER_TYPE_NORMAL:
+	case PCI_HEADER_TYPE_BRIDGE:
+		return PCI_CAPABILITY_LIST;
+	case PCI_HEADER_TYPE_CARDBUS:
+		return PCI_CB_CAPABILITY_LIST;
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
+/**
+ * pci_find_capability - query for devices' capabilities 
+ * @dev: PCI device to query
+ * @cap: capability code
+ *
+ * Tell if a device supports a given PCI capability.
+ * Returns the address of the requested capability structure within the
+ * device's PCI configuration space or 0 in case the device does not
+ * support it.  Possible values for @cap:
+ *
+ *  %PCI_CAP_ID_PM           Power Management 
+ *  %PCI_CAP_ID_AGP          Accelerated Graphics Port 
+ *  %PCI_CAP_ID_VPD          Vital Product Data 
+ *  %PCI_CAP_ID_SLOTID       Slot Identification 
+ *  %PCI_CAP_ID_MSI          Message Signalled Interrupts
+ *  %PCI_CAP_ID_CHSWP        CompactPCI HotSwap 
+ *  %PCI_CAP_ID_PCIX         PCI-X
+ *  %PCI_CAP_ID_EXP          PCI Express
+ */
+int pci_find_capability(struct pci_dev *dev, int cap)
+{
+	int pos;
+
+	pos = __pci_bus_find_cap_start(dev->bus, dev->devfn, dev->hdr_type);
+	if (pos)
+		pos = __pci_find_next_cap(dev->bus, dev->devfn, pos, cap);
+
+	return pos;
+}
+
+/**
+ * pci_bus_find_capability - query for devices' capabilities 
+ * @bus:   the PCI bus to query
+ * @devfn: PCI device to query
+ * @cap:   capability code
+ *
+ * Like pci_find_capability() but works for pci devices that do not have a
+ * pci_dev structure set up yet. 
+ *
+ * Returns the address of the requested capability structure within the
+ * device's PCI configuration space or 0 in case the device does not
+ * support it.
+ */
+int pci_bus_find_capability(struct pci_bus *bus, unsigned int devfn, int cap)
+{
+	int pos;
+	u8 hdr_type;
+
+	pci_bus_read_config_byte(bus, devfn, PCI_HEADER_TYPE, &hdr_type);
+
+	pos = __pci_bus_find_cap_start(bus, devfn, hdr_type & 0x7f);
+	if (pos)
+		pos = __pci_find_next_cap(bus, devfn, pos, cap);
+
+	return pos;
+}
+
+/**
+ * pci_find_ext_capability - Find an extended capability
+ * @dev: PCI device to query
+ * @cap: capability code
+ *
+ * Returns the address of the requested extended capability structure
+ * within the device's PCI configuration space or 0 if the device does
+ * not support it.  Possible values for @cap:
+ *
+ *  %PCI_EXT_CAP_ID_ERR		Advanced Error Reporting
+ *  %PCI_EXT_CAP_ID_VC		Virtual Channel
+ *  %PCI_EXT_CAP_ID_DSN		Device Serial Number
+ *  %PCI_EXT_CAP_ID_PWR		Power Budgeting
+ */
+int pci_find_ext_capability(struct pci_dev *dev, int cap)
+{
+	u32 header;
+	int ttl;
+	int pos = PCI_CFG_SPACE_SIZE;
+
+	/* minimum 8 bytes per capability */
+	ttl = (PCI_CFG_SPACE_EXP_SIZE - PCI_CFG_SPACE_SIZE) / 8;
+
+	if (dev->cfg_size <= PCI_CFG_SPACE_SIZE)
+		return 0;
+
+	if (pci_read_config_dword(dev, pos, &header) != PCIBIOS_SUCCESSFUL)
+		return 0;
+
+	/*
+	 * If we have no capabilities, this is indicated by cap ID,
+	 * cap version and next pointer all being 0.
+	 */
+	if (header == 0)
+		return 0;
+
+	while (ttl-- > 0) {
+		if (PCI_EXT_CAP_ID(header) == cap)
+			return pos;
+
+		pos = PCI_EXT_CAP_NEXT(header);
+		if (pos < PCI_CFG_SPACE_SIZE)
+			break;
+
+		if (pci_read_config_dword(dev, pos, &header) != PCIBIOS_SUCCESSFUL)
+			break;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_find_ext_capability);
+
+/**
+ * pci_bus_find_ext_capability - find an extended capability
+ * @bus:   the PCI bus to query
+ * @devfn: PCI device to query
+ * @cap:   capability code
+ *
+ * Like pci_find_ext_capability() but works for pci devices that do not have a
+ * pci_dev structure set up yet.
+ *
+ * Returns the address of the requested capability structure within the
+ * device's PCI configuration space or 0 in case the device does not
+ * support it.
+ */
+int pci_bus_find_ext_capability(struct pci_bus *bus, unsigned int devfn,
+				int cap)
+{
+	u32 header;
+	int ttl;
+	int pos = PCI_CFG_SPACE_SIZE;
+
+	/* minimum 8 bytes per capability */
+	ttl = (PCI_CFG_SPACE_EXP_SIZE - PCI_CFG_SPACE_SIZE) / 8;
+
+	if (!pci_bus_read_config_dword(bus, devfn, pos, &header))
+		return 0;
+	if (header == 0xffffffff || header == 0)
+		return 0;
+
+	while (ttl-- > 0) {
+		if (PCI_EXT_CAP_ID(header) == cap)
+			return pos;
+
+		pos = PCI_EXT_CAP_NEXT(header);
+		if (pos < PCI_CFG_SPACE_SIZE)
+			break;
+
+		if (!pci_bus_read_config_dword(bus, devfn, pos, &header))
+			break;
+	}
+
+	return 0;
+}
+
+static int __pci_find_next_ht_cap(struct pci_dev *dev, int pos, int ht_cap)
+{
+	int rc, ttl = PCI_FIND_CAP_TTL;
+	u8 cap, mask;
+
+	if (ht_cap == HT_CAPTYPE_SLAVE || ht_cap == HT_CAPTYPE_HOST)
+		mask = HT_3BIT_CAP_MASK;
+	else
+		mask = HT_5BIT_CAP_MASK;
+
+	pos = __pci_find_next_cap_ttl(dev->bus, dev->devfn, pos,
+				      PCI_CAP_ID_HT, &ttl);
+	while (pos) {
+		rc = pci_read_config_byte(dev, pos + 3, &cap);
+		if (rc != PCIBIOS_SUCCESSFUL)
+			return 0;
+
+		if ((cap & mask) == ht_cap)
+			return pos;
+
+		pos = __pci_find_next_cap_ttl(dev->bus, dev->devfn,
+					      pos + PCI_CAP_LIST_NEXT,
+					      PCI_CAP_ID_HT, &ttl);
+	}
+
+	return 0;
+}
+/**
+ * pci_find_next_ht_capability - query a device's Hypertransport capabilities
+ * @dev: PCI device to query
+ * @pos: Position from which to continue searching
+ * @ht_cap: Hypertransport capability code
+ *
+ * To be used in conjunction with pci_find_ht_capability() to search for
+ * all capabilities matching @ht_cap. @pos should always be a value returned
+ * from pci_find_ht_capability().
+ *
+ * NB. To be 100% safe against broken PCI devices, the caller should take
+ * steps to avoid an infinite loop.
+ */
+int pci_find_next_ht_capability(struct pci_dev *dev, int pos, int ht_cap)
+{
+	return __pci_find_next_ht_cap(dev, pos + PCI_CAP_LIST_NEXT, ht_cap);
+}
+EXPORT_SYMBOL_GPL(pci_find_next_ht_capability);
+
+/**
+ * pci_find_ht_capability - query a device's Hypertransport capabilities
+ * @dev: PCI device to query
+ * @ht_cap: Hypertransport capability code
+ *
+ * Tell if a device supports a given Hypertransport capability.
+ * Returns an address within the device's PCI configuration space
+ * or 0 in case the device does not support the request capability.
+ * The address points to the PCI capability, of type PCI_CAP_ID_HT,
+ * which has a Hypertransport capability matching @ht_cap.
+ */
+int pci_find_ht_capability(struct pci_dev *dev, int ht_cap)
+{
+	int pos;
+
+	pos = __pci_bus_find_cap_start(dev->bus, dev->devfn, dev->hdr_type);
+	if (pos)
+		pos = __pci_find_next_ht_cap(dev, pos, ht_cap);
+
+	return pos;
+}
+EXPORT_SYMBOL_GPL(pci_find_ht_capability);
+
+/**
+ * pci_find_parent_resource - return resource region of parent bus of given region
+ * @dev: PCI device structure contains resources to be searched
+ * @res: child resource record for which parent is sought
+ *
+ *  For given resource region of given device, return the resource
+ *  region of parent bus the given region is contained in or where
+ *  it should be allocated from.
+ */
+struct resource *
+pci_find_parent_resource(const struct pci_dev *dev, struct resource *res)
+{
+	const struct pci_bus *bus = dev->bus;
+	int i;
+	struct resource *best = NULL, *r;
+
+	pci_bus_for_each_resource(bus, r, i) {
+		if (!r)
+			continue;
+		if (res->start && !(res->start >= r->start && res->end <= r->end))
+			continue;	/* Not contained */
+		if ((res->flags ^ r->flags) & (IORESOURCE_IO | IORESOURCE_MEM))
+			continue;	/* Wrong type */
+		if (!((res->flags ^ r->flags) & IORESOURCE_PREFETCH))
+			return r;	/* Exact match */
+		/* We can't insert a non-prefetch resource inside a prefetchable parent .. */
+		if (r->flags & IORESOURCE_PREFETCH)
+			continue;
+		/* .. but we can put a prefetchable resource inside a non-prefetchable one */
+		if (!best)
+			best = r;
+	}
+	return best;
+}
+
+/**
+ * pci_restore_bars - restore a devices BAR values (e.g. after wake-up)
+ * @dev: PCI device to have its BARs restored
+ *
+ * Restore the BAR values for a given device, so as to make it
+ * accessible by its driver.
+ */
+static void
+pci_restore_bars(struct pci_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < PCI_BRIDGE_RESOURCES; i++)
+		pci_update_resource(dev, i);
+}
+
+static struct pci_platform_pm_ops *pci_platform_pm;
+
+int pci_set_platform_pm(struct pci_platform_pm_ops *ops)
+{
+	if (!ops->is_manageable || !ops->set_state || !ops->choose_state
+	    || !ops->sleep_wake || !ops->can_wakeup)
+		return -EINVAL;
+	pci_platform_pm = ops;
+	return 0;
+}
+
+static inline bool platform_pci_power_manageable(struct pci_dev *dev)
+{
+	return pci_platform_pm ? pci_platform_pm->is_manageable(dev) : false;
+}
+
+static inline int platform_pci_set_power_state(struct pci_dev *dev,
+                                                pci_power_t t)
+{
+	return pci_platform_pm ? pci_platform_pm->set_state(dev, t) : -ENOSYS;
+}
+
+static inline pci_power_t platform_pci_choose_state(struct pci_dev *dev)
+{
+	return pci_platform_pm ?
+			pci_platform_pm->choose_state(dev) : PCI_POWER_ERROR;
+}
+
+static inline bool platform_pci_can_wakeup(struct pci_dev *dev)
+{
+	return pci_platform_pm ? pci_platform_pm->can_wakeup(dev) : false;
+}
+
+static inline int platform_pci_sleep_wake(struct pci_dev *dev, bool enable)
+{
+	return pci_platform_pm ?
+			pci_platform_pm->sleep_wake(dev, enable) : -ENODEV;
+}
+
+static inline int platform_pci_run_wake(struct pci_dev *dev, bool enable)
+{
+	return pci_platform_pm ?
+			pci_platform_pm->run_wake(dev, enable) : -ENODEV;
+}
+
+/**
+ * pci_raw_set_power_state - Use PCI PM registers to set the power state of
+ *                           given PCI device
+ * @dev: PCI device to handle.
+ * @state: PCI power state (D0, D1, D2, D3hot) to put the device into.
+ *
+ * RETURN VALUE:
+ * -EINVAL if the requested state is invalid.
+ * -EIO if device does not support PCI PM or its PM capabilities register has a
+ * wrong version, or device doesn't support the requested state.
+ * 0 if device already is in the requested state.
+ * 0 if device's power state has been successfully changed.
+ */
+static int pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state)
+{
+	u16 pmcsr;
+	bool need_restore = false;
+
+	/* Check if we're already there */
+	if (dev->current_state == state)
+		return 0;
+
+	if (!dev->pm_cap)
+		return -EIO;
+
+	if (state < PCI_D0 || state > PCI_D3hot)
+		return -EINVAL;
+
+	/* Validate current state:
+	 * Can enter D0 from any state, but if we can only go deeper 
+	 * to sleep if we're already in a low power state
+	 */
+	if (state != PCI_D0 && dev->current_state <= PCI_D3cold
+	    && dev->current_state > state) {
+		dev_err(&dev->dev, "invalid power transition "
+			"(from state %d to %d)\n", dev->current_state, state);
+		return -EINVAL;
+	}
+
+	/* check if this device supports the desired state */
+	if ((state == PCI_D1 && !dev->d1_support)
+	   || (state == PCI_D2 && !dev->d2_support))
+		return -EIO;
+
+	pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
+
+	/* If we're (effectively) in D3, force entire word to 0.
+	 * This doesn't affect PME_Status, disables PME_En, and
+	 * sets PowerState to 0.
+	 */
+	switch (dev->current_state) {
+	case PCI_D0:
+	case PCI_D1:
+	case PCI_D2:
+		pmcsr &= ~PCI_PM_CTRL_STATE_MASK;
+		pmcsr |= state;
+		break;
+	case PCI_D3hot:
+	case PCI_D3cold:
+	case PCI_UNKNOWN: /* Boot-up */
+		if ((pmcsr & PCI_PM_CTRL_STATE_MASK) == PCI_D3hot
+		 && !(pmcsr & PCI_PM_CTRL_NO_SOFT_RESET))
+			need_restore = true;
+		/* Fall-through: force to D0 */
+	default:
+		pmcsr = 0;
+		break;
+	}
+
+	/* enter specified state */
+	pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, pmcsr);
+
+	/* Mandatory power management transition delays */
+	/* see PCI PM 1.1 5.6.1 table 18 */
+	if (state == PCI_D3hot || dev->current_state == PCI_D3hot)
+		pci_dev_d3_sleep(dev);
+	else if (state == PCI_D2 || dev->current_state == PCI_D2)
+		udelay(PCI_PM_D2_DELAY);
+
+	pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
+	dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK);
+	if (dev->current_state != state && printk_ratelimit())
+		dev_info(&dev->dev, "Refused to change power state, "
+			"currently in D%d\n", dev->current_state);
+
+	/* According to section 5.4.1 of the "PCI BUS POWER MANAGEMENT
+	 * INTERFACE SPECIFICATION, REV. 1.2", a device transitioning
+	 * from D3hot to D0 _may_ perform an internal reset, thereby
+	 * going to "D0 Uninitialized" rather than "D0 Initialized".
+	 * For example, at least some versions of the 3c905B and the
+	 * 3c556B exhibit this behaviour.
+	 *
+	 * At least some laptop BIOSen (e.g. the Thinkpad T21) leave
+	 * devices in a D3hot state at boot.  Consequently, we need to
+	 * restore at least the BARs so that the device will be
+	 * accessible to its driver.
+	 */
+	if (need_restore)
+		pci_restore_bars(dev);
+
+	if (dev->bus->self)
+		pcie_aspm_pm_state_change(dev->bus->self);
+
+	return 0;
+}
+
+/**
+ * pci_update_current_state - Read PCI power state of given device from its
+ *                            PCI PM registers and cache it
+ * @dev: PCI device to handle.
+ * @state: State to cache in case the device doesn't have the PM capability
+ */
+void pci_update_current_state(struct pci_dev *dev, pci_power_t state)
+{
+	if (dev->pm_cap) {
+		u16 pmcsr;
+
+		pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
+		dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK);
+	} else {
+		dev->current_state = state;
+	}
+}
+
+/**
+ * pci_platform_power_transition - Use platform to change device power state
+ * @dev: PCI device to handle.
+ * @state: State to put the device into.
+ */
+static int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state)
+{
+	int error;
+
+	if (platform_pci_power_manageable(dev)) {
+		error = platform_pci_set_power_state(dev, state);
+		if (!error)
+			pci_update_current_state(dev, state);
+	} else {
+		error = -ENODEV;
+		/* Fall back to PCI_D0 if native PM is not supported */
+		if (!dev->pm_cap)
+			dev->current_state = PCI_D0;
+	}
+
+	return error;
+}
+
+/**
+ * __pci_start_power_transition - Start power transition of a PCI device
+ * @dev: PCI device to handle.
+ * @state: State to put the device into.
+ */
+static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state)
+{
+	if (state == PCI_D0)
+		pci_platform_power_transition(dev, PCI_D0);
+}
+
+/**
+ * __pci_complete_power_transition - Complete power transition of a PCI device
+ * @dev: PCI device to handle.
+ * @state: State to put the device into.
+ *
+ * This function should not be called directly by device drivers.
+ */
+int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state)
+{
+	return state >= PCI_D0 ?
+			pci_platform_power_transition(dev, state) : -EINVAL;
+}
+EXPORT_SYMBOL_GPL(__pci_complete_power_transition);
+
+/**
+ * pci_set_power_state - Set the power state of a PCI device
+ * @dev: PCI device to handle.
+ * @state: PCI power state (D0, D1, D2, D3hot) to put the device into.
+ *
+ * Transition a device to a new power state, using the platform firmware and/or
+ * the device's PCI PM registers.
+ *
+ * RETURN VALUE:
+ * -EINVAL if the requested state is invalid.
+ * -EIO if device does not support PCI PM or its PM capabilities register has a
+ * wrong version, or device doesn't support the requested state.
+ * 0 if device already is in the requested state.
+ * 0 if device's power state has been successfully changed.
+ */
+int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
+{
+	int error;
+
+	/* bound the state we're entering */
+	if (state > PCI_D3hot)
+		state = PCI_D3hot;
+	else if (state < PCI_D0)
+		state = PCI_D0;
+	else if ((state == PCI_D1 || state == PCI_D2) && pci_no_d1d2(dev))
+		/*
+		 * If the device or the parent bridge do not support PCI PM,
+		 * ignore the request if we're doing anything other than putting
+		 * it into D0 (which would only happen on boot).
+		 */
+		return 0;
+
+	__pci_start_power_transition(dev, state);
+
+	/* This device is quirked not to be put into D3, so
+	   don't put it in D3 */
+	if (state == PCI_D3hot && (dev->dev_flags & PCI_DEV_FLAGS_NO_D3))
+		return 0;
+
+	error = pci_raw_set_power_state(dev, state);
+
+	if (!__pci_complete_power_transition(dev, state))
+		error = 0;
+	/*
+	 * When aspm_policy is "powersave" this call ensures
+	 * that ASPM is configured.
+	 */
+	if (!error && dev->bus->self)
+		pcie_aspm_powersave_config_link(dev->bus->self);
+
+	return error;
+}
+
+/**
+ * pci_choose_state - Choose the power state of a PCI device
+ * @dev: PCI device to be suspended
+ * @state: target sleep state for the whole system. This is the value
+ *	that is passed to suspend() function.
+ *
+ * Returns PCI power state suitable for given device and given system
+ * message.
+ */
+
+pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state)
+{
+	pci_power_t ret;
+
+	if (!pci_find_capability(dev, PCI_CAP_ID_PM))
+		return PCI_D0;
+
+	ret = platform_pci_choose_state(dev);
+	if (ret != PCI_POWER_ERROR)
+		return ret;
+
+	switch (state.event) {
+	case PM_EVENT_ON:
+		return PCI_D0;
+	case PM_EVENT_FREEZE:
+	case PM_EVENT_PRETHAW:
+		/* REVISIT both freeze and pre-thaw "should" use D0 */
+	case PM_EVENT_SUSPEND:
+	case PM_EVENT_HIBERNATE:
+		return PCI_D3hot;
+	default:
+		dev_info(&dev->dev, "unrecognized suspend event %d\n",
+			 state.event);
+		BUG();
+	}
+	return PCI_D0;
+}
+
+EXPORT_SYMBOL(pci_choose_state);
+
+#define PCI_EXP_SAVE_REGS	7
+
+#define pcie_cap_has_devctl(type, flags)	1
+#define pcie_cap_has_lnkctl(type, flags)		\
+		((flags & PCI_EXP_FLAGS_VERS) > 1 ||	\
+		 (type == PCI_EXP_TYPE_ROOT_PORT ||	\
+		  type == PCI_EXP_TYPE_ENDPOINT ||	\
+		  type == PCI_EXP_TYPE_LEG_END))
+#define pcie_cap_has_sltctl(type, flags)		\
+		((flags & PCI_EXP_FLAGS_VERS) > 1 ||	\
+		 ((type == PCI_EXP_TYPE_ROOT_PORT) ||	\
+		  (type == PCI_EXP_TYPE_DOWNSTREAM &&	\
+		   (flags & PCI_EXP_FLAGS_SLOT))))
+#define pcie_cap_has_rtctl(type, flags)			\
+		((flags & PCI_EXP_FLAGS_VERS) > 1 ||	\
+		 (type == PCI_EXP_TYPE_ROOT_PORT ||	\
+		  type == PCI_EXP_TYPE_RC_EC))
+#define pcie_cap_has_devctl2(type, flags)		\
+		((flags & PCI_EXP_FLAGS_VERS) > 1)
+#define pcie_cap_has_lnkctl2(type, flags)		\
+		((flags & PCI_EXP_FLAGS_VERS) > 1)
+#define pcie_cap_has_sltctl2(type, flags)		\
+		((flags & PCI_EXP_FLAGS_VERS) > 1)
+
+static int pci_save_pcie_state(struct pci_dev *dev)
+{
+	int pos, i = 0;
+	struct pci_cap_saved_state *save_state;
+	u16 *cap;
+	u16 flags;
+
+	pos = pci_pcie_cap(dev);
+	if (!pos)
+		return 0;
+
+	save_state = pci_find_saved_cap(dev, PCI_CAP_ID_EXP);
+	if (!save_state) {
+		dev_err(&dev->dev, "buffer not found in %s\n", __func__);
+		return -ENOMEM;
+	}
+	cap = (u16 *)&save_state->cap.data[0];
+
+	pci_read_config_word(dev, pos + PCI_EXP_FLAGS, &flags);
+
+	if (pcie_cap_has_devctl(dev->pcie_type, flags))
+		pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &cap[i++]);
+	if (pcie_cap_has_lnkctl(dev->pcie_type, flags))
+		pci_read_config_word(dev, pos + PCI_EXP_LNKCTL, &cap[i++]);
+	if (pcie_cap_has_sltctl(dev->pcie_type, flags))
+		pci_read_config_word(dev, pos + PCI_EXP_SLTCTL, &cap[i++]);
+	if (pcie_cap_has_rtctl(dev->pcie_type, flags))
+		pci_read_config_word(dev, pos + PCI_EXP_RTCTL, &cap[i++]);
+	if (pcie_cap_has_devctl2(dev->pcie_type, flags))
+		pci_read_config_word(dev, pos + PCI_EXP_DEVCTL2, &cap[i++]);
+	if (pcie_cap_has_lnkctl2(dev->pcie_type, flags))
+		pci_read_config_word(dev, pos + PCI_EXP_LNKCTL2, &cap[i++]);
+	if (pcie_cap_has_sltctl2(dev->pcie_type, flags))
+		pci_read_config_word(dev, pos + PCI_EXP_SLTCTL2, &cap[i++]);
+
+	return 0;
+}
+
+static void pci_restore_pcie_state(struct pci_dev *dev)
+{
+	int i = 0, pos;
+	struct pci_cap_saved_state *save_state;
+	u16 *cap;
+	u16 flags;
+
+	save_state = pci_find_saved_cap(dev, PCI_CAP_ID_EXP);
+	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
+	if (!save_state || pos <= 0)
+		return;
+	cap = (u16 *)&save_state->cap.data[0];
+
+	pci_read_config_word(dev, pos + PCI_EXP_FLAGS, &flags);
+
+	if (pcie_cap_has_devctl(dev->pcie_type, flags))
+		pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, cap[i++]);
+	if (pcie_cap_has_lnkctl(dev->pcie_type, flags))
+		pci_write_config_word(dev, pos + PCI_EXP_LNKCTL, cap[i++]);
+	if (pcie_cap_has_sltctl(dev->pcie_type, flags))
+		pci_write_config_word(dev, pos + PCI_EXP_SLTCTL, cap[i++]);
+	if (pcie_cap_has_rtctl(dev->pcie_type, flags))
+		pci_write_config_word(dev, pos + PCI_EXP_RTCTL, cap[i++]);
+	if (pcie_cap_has_devctl2(dev->pcie_type, flags))
+		pci_write_config_word(dev, pos + PCI_EXP_DEVCTL2, cap[i++]);
+	if (pcie_cap_has_lnkctl2(dev->pcie_type, flags))
+		pci_write_config_word(dev, pos + PCI_EXP_LNKCTL2, cap[i++]);
+	if (pcie_cap_has_sltctl2(dev->pcie_type, flags))
+		pci_write_config_word(dev, pos + PCI_EXP_SLTCTL2, cap[i++]);
+}
+
+
+static int pci_save_pcix_state(struct pci_dev *dev)
+{
+	int pos;
+	struct pci_cap_saved_state *save_state;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_PCIX);
+	if (pos <= 0)
+		return 0;
+
+	save_state = pci_find_saved_cap(dev, PCI_CAP_ID_PCIX);
+	if (!save_state) {
+		dev_err(&dev->dev, "buffer not found in %s\n", __func__);
+		return -ENOMEM;
+	}
+
+	pci_read_config_word(dev, pos + PCI_X_CMD,
+			     (u16 *)save_state->cap.data);
+
+	return 0;
+}
+
+static void pci_restore_pcix_state(struct pci_dev *dev)
+{
+	int i = 0, pos;
+	struct pci_cap_saved_state *save_state;
+	u16 *cap;
+
+	save_state = pci_find_saved_cap(dev, PCI_CAP_ID_PCIX);
+	pos = pci_find_capability(dev, PCI_CAP_ID_PCIX);
+	if (!save_state || pos <= 0)
+		return;
+	cap = (u16 *)&save_state->cap.data[0];
+
+	pci_write_config_word(dev, pos + PCI_X_CMD, cap[i++]);
+}
+
+
+/**
+ * pci_save_state - save the PCI configuration space of a device before suspending
+ * @dev: - PCI device that we're dealing with
+ */
+int
+pci_save_state(struct pci_dev *dev)
+{
+	int i;
+	/* XXX: 100% dword access ok here? */
+	for (i = 0; i < 16; i++)
+		pci_read_config_dword(dev, i * 4, &dev->saved_config_space[i]);
+	dev->state_saved = true;
+	if ((i = pci_save_pcie_state(dev)) != 0)
+		return i;
+	if ((i = pci_save_pcix_state(dev)) != 0)
+		return i;
+	return 0;
+}
+
+/** 
+ * pci_restore_state - Restore the saved state of a PCI device
+ * @dev: - PCI device that we're dealing with
+ */
+void pci_restore_state(struct pci_dev *dev)
+{
+	int i;
+	u32 val;
+
+	if (!dev->state_saved)
+		return;
+
+	/* PCI Express register must be restored first */
+	pci_restore_pcie_state(dev);
+
+	/*
+	 * The Base Address register should be programmed before the command
+	 * register(s)
+	 */
+	for (i = 15; i >= 0; i--) {
+		pci_read_config_dword(dev, i * 4, &val);
+		if (val != dev->saved_config_space[i]) {
+			dev_printk(KERN_DEBUG, &dev->dev, "restoring config "
+				"space at offset %#x (was %#x, writing %#x)\n",
+				i, val, (int)dev->saved_config_space[i]);
+			pci_write_config_dword(dev,i * 4,
+				dev->saved_config_space[i]);
+		}
+	}
+	pci_restore_pcix_state(dev);
+	pci_restore_msi_state(dev);
+	pci_restore_iov_state(dev);
+
+	dev->state_saved = false;
+}
+
+struct pci_saved_state {
+	u32 config_space[16];
+	struct pci_cap_saved_data cap[0];
+};
+
+/**
+ * pci_store_saved_state - Allocate and return an opaque struct containing
+ *			   the device saved state.
+ * @dev: PCI device that we're dealing with
+ *
+ * Rerturn NULL if no state or error.
+ */
+struct pci_saved_state *pci_store_saved_state(struct pci_dev *dev)
+{
+	struct pci_saved_state *state;
+	struct pci_cap_saved_state *tmp;
+	struct pci_cap_saved_data *cap;
+	struct hlist_node *pos;
+	size_t size;
+
+	if (!dev->state_saved)
+		return NULL;
+
+	size = sizeof(*state) + sizeof(struct pci_cap_saved_data);
+
+	hlist_for_each_entry(tmp, pos, &dev->saved_cap_space, next)
+		size += sizeof(struct pci_cap_saved_data) + tmp->cap.size;
+
+	state = kzalloc(size, GFP_KERNEL);
+	if (!state)
+		return NULL;
+
+	memcpy(state->config_space, dev->saved_config_space,
+	       sizeof(state->config_space));
+
+	cap = state->cap;
+	hlist_for_each_entry(tmp, pos, &dev->saved_cap_space, next) {
+		size_t len = sizeof(struct pci_cap_saved_data) + tmp->cap.size;
+		memcpy(cap, &tmp->cap, len);
+		cap = (struct pci_cap_saved_data *)((u8 *)cap + len);
+	}
+	/* Empty cap_save terminates list */
+
+	return state;
+}
+EXPORT_SYMBOL_GPL(pci_store_saved_state);
+
+/**
+ * pci_load_saved_state - Reload the provided save state into struct pci_dev.
+ * @dev: PCI device that we're dealing with
+ * @state: Saved state returned from pci_store_saved_state()
+ */
+int pci_load_saved_state(struct pci_dev *dev, struct pci_saved_state *state)
+{
+	struct pci_cap_saved_data *cap;
+
+	dev->state_saved = false;
+
+	if (!state)
+		return 0;
+
+	memcpy(dev->saved_config_space, state->config_space,
+	       sizeof(state->config_space));
+
+	cap = state->cap;
+	while (cap->size) {
+		struct pci_cap_saved_state *tmp;
+
+		tmp = pci_find_saved_cap(dev, cap->cap_nr);
+		if (!tmp || tmp->cap.size != cap->size)
+			return -EINVAL;
+
+		memcpy(tmp->cap.data, cap->data, tmp->cap.size);
+		cap = (struct pci_cap_saved_data *)((u8 *)cap +
+		       sizeof(struct pci_cap_saved_data) + cap->size);
+	}
+
+	dev->state_saved = true;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_load_saved_state);
+
+/**
+ * pci_load_and_free_saved_state - Reload the save state pointed to by state,
+ *				   and free the memory allocated for it.
+ * @dev: PCI device that we're dealing with
+ * @state: Pointer to saved state returned from pci_store_saved_state()
+ */
+int pci_load_and_free_saved_state(struct pci_dev *dev,
+				  struct pci_saved_state **state)
+{
+	int ret = pci_load_saved_state(dev, *state);
+	kfree(*state);
+	*state = NULL;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pci_load_and_free_saved_state);
+
+static int do_pci_enable_device(struct pci_dev *dev, int bars)
+{
+	int err;
+
+	err = pci_set_power_state(dev, PCI_D0);
+	if (err < 0 && err != -EIO)
+		return err;
+	err = pcibios_enable_device(dev, bars);
+	if (err < 0)
+		return err;
+	pci_fixup_device(pci_fixup_enable, dev);
+
+	return 0;
+}
+
+/**
+ * pci_reenable_device - Resume abandoned device
+ * @dev: PCI device to be resumed
+ *
+ *  Note this function is a backend of pci_default_resume and is not supposed
+ *  to be called by normal code, write proper resume handler and use it instead.
+ */
+int pci_reenable_device(struct pci_dev *dev)
+{
+	if (pci_is_enabled(dev))
+		return do_pci_enable_device(dev, (1 << PCI_NUM_RESOURCES) - 1);
+	return 0;
+}
+
+static int __pci_enable_device_flags(struct pci_dev *dev,
+				     resource_size_t flags)
+{
+	int err;
+	int i, bars = 0;
+
+	/*
+	 * Power state could be unknown at this point, either due to a fresh
+	 * boot or a device removal call.  So get the current power state
+	 * so that things like MSI message writing will behave as expected
+	 * (e.g. if the device really is in D0 at enable time).
+	 */
+	if (dev->pm_cap) {
+		u16 pmcsr;
+		pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
+		dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK);
+	}
+
+	if (atomic_add_return(1, &dev->enable_cnt) > 1)
+		return 0;		/* already enabled */
+
+	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++)
+		if (dev->resource[i].flags & flags)
+			bars |= (1 << i);
+
+	err = do_pci_enable_device(dev, bars);
+	if (err < 0)
+		atomic_dec(&dev->enable_cnt);
+	return err;
+}
+
+/**
+ * pci_enable_device_io - Initialize a device for use with IO space
+ * @dev: PCI device to be initialized
+ *
+ *  Initialize device before it's used by a driver. Ask low-level code
+ *  to enable I/O resources. Wake up the device if it was suspended.
+ *  Beware, this function can fail.
+ */
+int pci_enable_device_io(struct pci_dev *dev)
+{
+	return __pci_enable_device_flags(dev, IORESOURCE_IO);
+}
+
+/**
+ * pci_enable_device_mem - Initialize a device for use with Memory space
+ * @dev: PCI device to be initialized
+ *
+ *  Initialize device before it's used by a driver. Ask low-level code
+ *  to enable Memory resources. Wake up the device if it was suspended.
+ *  Beware, this function can fail.
+ */
+int pci_enable_device_mem(struct pci_dev *dev)
+{
+	return __pci_enable_device_flags(dev, IORESOURCE_MEM);
+}
+
+/**
+ * pci_enable_device - Initialize device before it's used by a driver.
+ * @dev: PCI device to be initialized
+ *
+ *  Initialize device before it's used by a driver. Ask low-level code
+ *  to enable I/O and memory. Wake up the device if it was suspended.
+ *  Beware, this function can fail.
+ *
+ *  Note we don't actually enable the device many times if we call
+ *  this function repeatedly (we just increment the count).
+ */
+int pci_enable_device(struct pci_dev *dev)
+{
+	return __pci_enable_device_flags(dev, IORESOURCE_MEM | IORESOURCE_IO);
+}
+
+/*
+ * Managed PCI resources.  This manages device on/off, intx/msi/msix
+ * on/off and BAR regions.  pci_dev itself records msi/msix status, so
+ * there's no need to track it separately.  pci_devres is initialized
+ * when a device is enabled using managed PCI device enable interface.
+ */
+struct pci_devres {
+	unsigned int enabled:1;
+	unsigned int pinned:1;
+	unsigned int orig_intx:1;
+	unsigned int restore_intx:1;
+	u32 region_mask;
+};
+
+static void pcim_release(struct device *gendev, void *res)
+{
+	struct pci_dev *dev = container_of(gendev, struct pci_dev, dev);
+	struct pci_devres *this = res;
+	int i;
+
+	if (dev->msi_enabled)
+		pci_disable_msi(dev);
+	if (dev->msix_enabled)
+		pci_disable_msix(dev);
+
+	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++)
+		if (this->region_mask & (1 << i))
+			pci_release_region(dev, i);
+
+	if (this->restore_intx)
+		pci_intx(dev, this->orig_intx);
+
+	if (this->enabled && !this->pinned)
+		pci_disable_device(dev);
+}
+
+static struct pci_devres * get_pci_dr(struct pci_dev *pdev)
+{
+	struct pci_devres *dr, *new_dr;
+
+	dr = devres_find(&pdev->dev, pcim_release, NULL, NULL);
+	if (dr)
+		return dr;
+
+	new_dr = devres_alloc(pcim_release, sizeof(*new_dr), GFP_KERNEL);
+	if (!new_dr)
+		return NULL;
+	return devres_get(&pdev->dev, new_dr, NULL, NULL);
+}
+
+static struct pci_devres * find_pci_dr(struct pci_dev *pdev)
+{
+	if (pci_is_managed(pdev))
+		return devres_find(&pdev->dev, pcim_release, NULL, NULL);
+	return NULL;
+}
+
+/**
+ * pcim_enable_device - Managed pci_enable_device()
+ * @pdev: PCI device to be initialized
+ *
+ * Managed pci_enable_device().
+ */
+int pcim_enable_device(struct pci_dev *pdev)
+{
+	struct pci_devres *dr;
+	int rc;
+
+	dr = get_pci_dr(pdev);
+	if (unlikely(!dr))
+		return -ENOMEM;
+	if (dr->enabled)
+		return 0;
+
+	rc = pci_enable_device(pdev);
+	if (!rc) {
+		pdev->is_managed = 1;
+		dr->enabled = 1;
+	}
+	return rc;
+}
+
+/**
+ * pcim_pin_device - Pin managed PCI device
+ * @pdev: PCI device to pin
+ *
+ * Pin managed PCI device @pdev.  Pinned device won't be disabled on
+ * driver detach.  @pdev must have been enabled with
+ * pcim_enable_device().
+ */
+void pcim_pin_device(struct pci_dev *pdev)
+{
+	struct pci_devres *dr;
+
+	dr = find_pci_dr(pdev);
+	WARN_ON(!dr || !dr->enabled);
+	if (dr)
+		dr->pinned = 1;
+}
+
+/**
+ * pcibios_disable_device - disable arch specific PCI resources for device dev
+ * @dev: the PCI device to disable
+ *
+ * Disables architecture specific PCI resources for the device. This
+ * is the default implementation. Architecture implementations can
+ * override this.
+ */
+void __attribute__ ((weak)) pcibios_disable_device (struct pci_dev *dev) {}
+
+static void do_pci_disable_device(struct pci_dev *dev)
+{
+	u16 pci_command;
+
+	pci_read_config_word(dev, PCI_COMMAND, &pci_command);
+	if (pci_command & PCI_COMMAND_MASTER) {
+		pci_command &= ~PCI_COMMAND_MASTER;
+		pci_write_config_word(dev, PCI_COMMAND, pci_command);
+	}
+
+	pcibios_disable_device(dev);
+}
+
+/**
+ * pci_disable_enabled_device - Disable device without updating enable_cnt
+ * @dev: PCI device to disable
+ *
+ * NOTE: This function is a backend of PCI power management routines and is
+ * not supposed to be called drivers.
+ */
+void pci_disable_enabled_device(struct pci_dev *dev)
+{
+	if (pci_is_enabled(dev))
+		do_pci_disable_device(dev);
+}
+
+/**
+ * pci_disable_device - Disable PCI device after use
+ * @dev: PCI device to be disabled
+ *
+ * Signal to the system that the PCI device is not in use by the system
+ * anymore.  This only involves disabling PCI bus-mastering, if active.
+ *
+ * Note we don't actually disable the device until all callers of
+ * pci_enable_device() have called pci_disable_device().
+ */
+void
+pci_disable_device(struct pci_dev *dev)
+{
+	struct pci_devres *dr;
+
+	dr = find_pci_dr(dev);
+	if (dr)
+		dr->enabled = 0;
+
+	if (atomic_sub_return(1, &dev->enable_cnt) != 0)
+		return;
+
+	do_pci_disable_device(dev);
+
+	dev->is_busmaster = 0;
+}
+
+/**
+ * pcibios_set_pcie_reset_state - set reset state for device dev
+ * @dev: the PCIe device reset
+ * @state: Reset state to enter into
+ *
+ *
+ * Sets the PCIe reset state for the device. This is the default
+ * implementation. Architecture implementations can override this.
+ */
+int __attribute__ ((weak)) pcibios_set_pcie_reset_state(struct pci_dev *dev,
+							enum pcie_reset_state state)
+{
+	return -EINVAL;
+}
+
+/**
+ * pci_set_pcie_reset_state - set reset state for device dev
+ * @dev: the PCIe device reset
+ * @state: Reset state to enter into
+ *
+ *
+ * Sets the PCI reset state for the device.
+ */
+int pci_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state)
+{
+	return pcibios_set_pcie_reset_state(dev, state);
+}
+
+/**
+ * pci_check_pme_status - Check if given device has generated PME.
+ * @dev: Device to check.
+ *
+ * Check the PME status of the device and if set, clear it and clear PME enable
+ * (if set).  Return 'true' if PME status and PME enable were both set or
+ * 'false' otherwise.
+ */
+bool pci_check_pme_status(struct pci_dev *dev)
+{
+	int pmcsr_pos;
+	u16 pmcsr;
+	bool ret = false;
+
+	if (!dev->pm_cap)
+		return false;
+
+	pmcsr_pos = dev->pm_cap + PCI_PM_CTRL;
+	pci_read_config_word(dev, pmcsr_pos, &pmcsr);
+	if (!(pmcsr & PCI_PM_CTRL_PME_STATUS))
+		return false;
+
+	/* Clear PME status. */
+	pmcsr |= PCI_PM_CTRL_PME_STATUS;
+	if (pmcsr & PCI_PM_CTRL_PME_ENABLE) {
+		/* Disable PME to avoid interrupt flood. */
+		pmcsr &= ~PCI_PM_CTRL_PME_ENABLE;
+		ret = true;
+	}
+
+	pci_write_config_word(dev, pmcsr_pos, pmcsr);
+
+	return ret;
+}
+
+/**
+ * pci_pme_wakeup - Wake up a PCI device if its PME Status bit is set.
+ * @dev: Device to handle.
+ * @ign: Ignored.
+ *
+ * Check if @dev has generated PME and queue a resume request for it in that
+ * case.
+ */
+static int pci_pme_wakeup(struct pci_dev *dev, void *ign)
+{
+	if (pci_check_pme_status(dev)) {
+		pci_wakeup_event(dev);
+		pm_request_resume(&dev->dev);
+	}
+	return 0;
+}
+
+/**
+ * pci_pme_wakeup_bus - Walk given bus and wake up devices on it, if necessary.
+ * @bus: Top bus of the subtree to walk.
+ */
+void pci_pme_wakeup_bus(struct pci_bus *bus)
+{
+	if (bus)
+		pci_walk_bus(bus, pci_pme_wakeup, NULL);
+}
+
+/**
+ * pci_pme_capable - check the capability of PCI device to generate PME#
+ * @dev: PCI device to handle.
+ * @state: PCI state from which device will issue PME#.
+ */
+bool pci_pme_capable(struct pci_dev *dev, pci_power_t state)
+{
+	if (!dev->pm_cap)
+		return false;
+
+	return !!(dev->pme_support & (1 << state));
+}
+
+static void pci_pme_list_scan(struct work_struct *work)
+{
+	struct pci_pme_device *pme_dev;
+
+	mutex_lock(&pci_pme_list_mutex);
+	if (!list_empty(&pci_pme_list)) {
+		list_for_each_entry(pme_dev, &pci_pme_list, list)
+			pci_pme_wakeup(pme_dev->dev, NULL);
+		schedule_delayed_work(&pci_pme_work, msecs_to_jiffies(PME_TIMEOUT));
+	}
+	mutex_unlock(&pci_pme_list_mutex);
+}
+
+/**
+ * pci_external_pme - is a device an external PCI PME source?
+ * @dev: PCI device to check
+ *
+ */
+
+static bool pci_external_pme(struct pci_dev *dev)
+{
+	if (pci_is_pcie(dev) || dev->bus->number == 0)
+		return false;
+	return true;
+}
+
+/**
+ * pci_pme_active - enable or disable PCI device's PME# function
+ * @dev: PCI device to handle.
+ * @enable: 'true' to enable PME# generation; 'false' to disable it.
+ *
+ * The caller must verify that the device is capable of generating PME# before
+ * calling this function with @enable equal to 'true'.
+ */
+void pci_pme_active(struct pci_dev *dev, bool enable)
+{
+	u16 pmcsr;
+
+	if (!dev->pm_cap)
+		return;
+
+	pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
+	/* Clear PME_Status by writing 1 to it and enable PME# */
+	pmcsr |= PCI_PM_CTRL_PME_STATUS | PCI_PM_CTRL_PME_ENABLE;
+	if (!enable)
+		pmcsr &= ~PCI_PM_CTRL_PME_ENABLE;
+
+	pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, pmcsr);
+
+	/* PCI (as opposed to PCIe) PME requires that the device have
+	   its PME# line hooked up correctly. Not all hardware vendors
+	   do this, so the PME never gets delivered and the device
+	   remains asleep. The easiest way around this is to
+	   periodically walk the list of suspended devices and check
+	   whether any have their PME flag set. The assumption is that
+	   we'll wake up often enough anyway that this won't be a huge
+	   hit, and the power savings from the devices will still be a
+	   win. */
+
+	if (pci_external_pme(dev)) {
+		struct pci_pme_device *pme_dev;
+		if (enable) {
+			pme_dev = kmalloc(sizeof(struct pci_pme_device),
+					  GFP_KERNEL);
+			if (!pme_dev)
+				goto out;
+			pme_dev->dev = dev;
+			mutex_lock(&pci_pme_list_mutex);
+			list_add(&pme_dev->list, &pci_pme_list);
+			if (list_is_singular(&pci_pme_list))
+				schedule_delayed_work(&pci_pme_work,
+						      msecs_to_jiffies(PME_TIMEOUT));
+			mutex_unlock(&pci_pme_list_mutex);
+		} else {
+			mutex_lock(&pci_pme_list_mutex);
+			list_for_each_entry(pme_dev, &pci_pme_list, list) {
+				if (pme_dev->dev == dev) {
+					list_del(&pme_dev->list);
+					kfree(pme_dev);
+					break;
+				}
+			}
+			mutex_unlock(&pci_pme_list_mutex);
+		}
+	}
+
+out:
+	dev_printk(KERN_DEBUG, &dev->dev, "PME# %s\n",
+			enable ? "enabled" : "disabled");
+}
+
+/**
+ * __pci_enable_wake - enable PCI device as wakeup event source
+ * @dev: PCI device affected
+ * @state: PCI state from which device will issue wakeup events
+ * @runtime: True if the events are to be generated at run time
+ * @enable: True to enable event generation; false to disable
+ *
+ * This enables the device as a wakeup event source, or disables it.
+ * When such events involves platform-specific hooks, those hooks are
+ * called automatically by this routine.
+ *
+ * Devices with legacy power management (no standard PCI PM capabilities)
+ * always require such platform hooks.
+ *
+ * RETURN VALUE:
+ * 0 is returned on success
+ * -EINVAL is returned if device is not supposed to wake up the system
+ * Error code depending on the platform is returned if both the platform and
+ * the native mechanism fail to enable the generation of wake-up events
+ */
+int __pci_enable_wake(struct pci_dev *dev, pci_power_t state,
+		      bool runtime, bool enable)
+{
+	int ret = 0;
+
+	if (enable && !runtime && !device_may_wakeup(&dev->dev))
+		return -EINVAL;
+
+	/* Don't do the same thing twice in a row for one device. */
+	if (!!enable == !!dev->wakeup_prepared)
+		return 0;
+
+	/*
+	 * According to "PCI System Architecture" 4th ed. by Tom Shanley & Don
+	 * Anderson we should be doing PME# wake enable followed by ACPI wake
+	 * enable.  To disable wake-up we call the platform first, for symmetry.
+	 */
+
+	if (enable) {
+		int error;
+
+		if (pci_pme_capable(dev, state))
+			pci_pme_active(dev, true);
+		else
+			ret = 1;
+		error = runtime ? platform_pci_run_wake(dev, true) :
+					platform_pci_sleep_wake(dev, true);
+		if (ret)
+			ret = error;
+		if (!ret)
+			dev->wakeup_prepared = true;
+	} else {
+		if (runtime)
+			platform_pci_run_wake(dev, false);
+		else
+			platform_pci_sleep_wake(dev, false);
+		pci_pme_active(dev, false);
+		dev->wakeup_prepared = false;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(__pci_enable_wake);
+
+/**
+ * pci_wake_from_d3 - enable/disable device to wake up from D3_hot or D3_cold
+ * @dev: PCI device to prepare
+ * @enable: True to enable wake-up event generation; false to disable
+ *
+ * Many drivers want the device to wake up the system from D3_hot or D3_cold
+ * and this function allows them to set that up cleanly - pci_enable_wake()
+ * should not be called twice in a row to enable wake-up due to PCI PM vs ACPI
+ * ordering constraints.
+ *
+ * This function only returns error code if the device is not capable of
+ * generating PME# from both D3_hot and D3_cold, and the platform is unable to
+ * enable wake-up power for it.
+ */
+int pci_wake_from_d3(struct pci_dev *dev, bool enable)
+{
+	return pci_pme_capable(dev, PCI_D3cold) ?
+			pci_enable_wake(dev, PCI_D3cold, enable) :
+			pci_enable_wake(dev, PCI_D3hot, enable);
+}
+
+/**
+ * pci_target_state - find an appropriate low power state for a given PCI dev
+ * @dev: PCI device
+ *
+ * Use underlying platform code to find a supported low power state for @dev.
+ * If the platform can't manage @dev, return the deepest state from which it
+ * can generate wake events, based on any available PME info.
+ */
+pci_power_t pci_target_state(struct pci_dev *dev)
+{
+	pci_power_t target_state = PCI_D3hot;
+
+	if (platform_pci_power_manageable(dev)) {
+		/*
+		 * Call the platform to choose the target state of the device
+		 * and enable wake-up from this state if supported.
+		 */
+		pci_power_t state = platform_pci_choose_state(dev);
+
+		switch (state) {
+		case PCI_POWER_ERROR:
+		case PCI_UNKNOWN:
+			break;
+		case PCI_D1:
+		case PCI_D2:
+			if (pci_no_d1d2(dev))
+				break;
+		default:
+			target_state = state;
+		}
+	} else if (!dev->pm_cap) {
+		target_state = PCI_D0;
+	} else if (device_may_wakeup(&dev->dev)) {
+		/*
+		 * Find the deepest state from which the device can generate
+		 * wake-up events, make it the target state and enable device
+		 * to generate PME#.
+		 */
+		if (dev->pme_support) {
+			while (target_state
+			      && !(dev->pme_support & (1 << target_state)))
+				target_state--;
+		}
+	}
+
+	return target_state;
+}
+
+/**
+ * pci_prepare_to_sleep - prepare PCI device for system-wide transition into a sleep state
+ * @dev: Device to handle.
+ *
+ * Choose the power state appropriate for the device depending on whether
+ * it can wake up the system and/or is power manageable by the platform
+ * (PCI_D3hot is the default) and put the device into that state.
+ */
+int pci_prepare_to_sleep(struct pci_dev *dev)
+{
+	pci_power_t target_state = pci_target_state(dev);
+	int error;
+
+	if (target_state == PCI_POWER_ERROR)
+		return -EIO;
+
+	pci_enable_wake(dev, target_state, device_may_wakeup(&dev->dev));
+
+	error = pci_set_power_state(dev, target_state);
+
+	if (error)
+		pci_enable_wake(dev, target_state, false);
+
+	return error;
+}
+
+/**
+ * pci_back_from_sleep - turn PCI device on during system-wide transition into working state
+ * @dev: Device to handle.
+ *
+ * Disable device's system wake-up capability and put it into D0.
+ */
+int pci_back_from_sleep(struct pci_dev *dev)
+{
+	pci_enable_wake(dev, PCI_D0, false);
+	return pci_set_power_state(dev, PCI_D0);
+}
+
+/**
+ * pci_finish_runtime_suspend - Carry out PCI-specific part of runtime suspend.
+ * @dev: PCI device being suspended.
+ *
+ * Prepare @dev to generate wake-up events at run time and put it into a low
+ * power state.
+ */
+int pci_finish_runtime_suspend(struct pci_dev *dev)
+{
+	pci_power_t target_state = pci_target_state(dev);
+	int error;
+
+	if (target_state == PCI_POWER_ERROR)
+		return -EIO;
+
+	__pci_enable_wake(dev, target_state, true, pci_dev_run_wake(dev));
+
+	error = pci_set_power_state(dev, target_state);
+
+	if (error)
+		__pci_enable_wake(dev, target_state, true, false);
+
+	return error;
+}
+
+/**
+ * pci_dev_run_wake - Check if device can generate run-time wake-up events.
+ * @dev: Device to check.
+ *
+ * Return true if the device itself is cabable of generating wake-up events
+ * (through the platform or using the native PCIe PME) or if the device supports
+ * PME and one of its upstream bridges can generate wake-up events.
+ */
+bool pci_dev_run_wake(struct pci_dev *dev)
+{
+	struct pci_bus *bus = dev->bus;
+
+	if (device_run_wake(&dev->dev))
+		return true;
+
+	if (!dev->pme_support)
+		return false;
+
+	while (bus->parent) {
+		struct pci_dev *bridge = bus->self;
+
+		if (device_run_wake(&bridge->dev))
+			return true;
+
+		bus = bus->parent;
+	}
+
+	/* We have reached the root bus. */
+	if (bus->bridge)
+		return device_run_wake(bus->bridge);
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(pci_dev_run_wake);
+
+/**
+ * pci_pm_init - Initialize PM functions of given PCI device
+ * @dev: PCI device to handle.
+ */
+void pci_pm_init(struct pci_dev *dev)
+{
+	int pm;
+	u16 pmc;
+
+	pm_runtime_forbid(&dev->dev);
+	device_enable_async_suspend(&dev->dev);
+	dev->wakeup_prepared = false;
+
+	dev->pm_cap = 0;
+
+	/* find PCI PM capability in list */
+	pm = pci_find_capability(dev, PCI_CAP_ID_PM);
+	if (!pm)
+		return;
+	/* Check device's ability to generate PME# */
+	pci_read_config_word(dev, pm + PCI_PM_PMC, &pmc);
+
+	if ((pmc & PCI_PM_CAP_VER_MASK) > 3) {
+		dev_err(&dev->dev, "unsupported PM cap regs version (%u)\n",
+			pmc & PCI_PM_CAP_VER_MASK);
+		return;
+	}
+
+	dev->pm_cap = pm;
+	dev->d3_delay = PCI_PM_D3_WAIT;
+
+	dev->d1_support = false;
+	dev->d2_support = false;
+	if (!pci_no_d1d2(dev)) {
+		if (pmc & PCI_PM_CAP_D1)
+			dev->d1_support = true;
+		if (pmc & PCI_PM_CAP_D2)
+			dev->d2_support = true;
+
+		if (dev->d1_support || dev->d2_support)
+			dev_printk(KERN_DEBUG, &dev->dev, "supports%s%s\n",
+				   dev->d1_support ? " D1" : "",
+				   dev->d2_support ? " D2" : "");
+	}
+
+	pmc &= PCI_PM_CAP_PME_MASK;
+	if (pmc) {
+		dev_printk(KERN_DEBUG, &dev->dev,
+			 "PME# supported from%s%s%s%s%s\n",
+			 (pmc & PCI_PM_CAP_PME_D0) ? " D0" : "",
+			 (pmc & PCI_PM_CAP_PME_D1) ? " D1" : "",
+			 (pmc & PCI_PM_CAP_PME_D2) ? " D2" : "",
+			 (pmc & PCI_PM_CAP_PME_D3) ? " D3hot" : "",
+			 (pmc & PCI_PM_CAP_PME_D3cold) ? " D3cold" : "");
+		dev->pme_support = pmc >> PCI_PM_CAP_PME_SHIFT;
+		/*
+		 * Make device's PM flags reflect the wake-up capability, but
+		 * let the user space enable it to wake up the system as needed.
+		 */
+		device_set_wakeup_capable(&dev->dev, true);
+		/* Disable the PME# generation functionality */
+		pci_pme_active(dev, false);
+	} else {
+		dev->pme_support = 0;
+	}
+}
+
+/**
+ * platform_pci_wakeup_init - init platform wakeup if present
+ * @dev: PCI device
+ *
+ * Some devices don't have PCI PM caps but can still generate wakeup
+ * events through platform methods (like ACPI events).  If @dev supports
+ * platform wakeup events, set the device flag to indicate as much.  This
+ * may be redundant if the device also supports PCI PM caps, but double
+ * initialization should be safe in that case.
+ */
+void platform_pci_wakeup_init(struct pci_dev *dev)
+{
+	if (!platform_pci_can_wakeup(dev))
+		return;
+
+	device_set_wakeup_capable(&dev->dev, true);
+	platform_pci_sleep_wake(dev, false);
+}
+
+/**
+ * pci_add_save_buffer - allocate buffer for saving given capability registers
+ * @dev: the PCI device
+ * @cap: the capability to allocate the buffer for
+ * @size: requested size of the buffer
+ */
+static int pci_add_cap_save_buffer(
+	struct pci_dev *dev, char cap, unsigned int size)
+{
+	int pos;
+	struct pci_cap_saved_state *save_state;
+
+	pos = pci_find_capability(dev, cap);
+	if (pos <= 0)
+		return 0;
+
+	save_state = kzalloc(sizeof(*save_state) + size, GFP_KERNEL);
+	if (!save_state)
+		return -ENOMEM;
+
+	save_state->cap.cap_nr = cap;
+	save_state->cap.size = size;
+	pci_add_saved_cap(dev, save_state);
+
+	return 0;
+}
+
+/**
+ * pci_allocate_cap_save_buffers - allocate buffers for saving capabilities
+ * @dev: the PCI device
+ */
+void pci_allocate_cap_save_buffers(struct pci_dev *dev)
+{
+	int error;
+
+	error = pci_add_cap_save_buffer(dev, PCI_CAP_ID_EXP,
+					PCI_EXP_SAVE_REGS * sizeof(u16));
+	if (error)
+		dev_err(&dev->dev,
+			"unable to preallocate PCI Express save buffer\n");
+
+	error = pci_add_cap_save_buffer(dev, PCI_CAP_ID_PCIX, sizeof(u16));
+	if (error)
+		dev_err(&dev->dev,
+			"unable to preallocate PCI-X save buffer\n");
+}
+
+/**
+ * pci_enable_ari - enable ARI forwarding if hardware support it
+ * @dev: the PCI device
+ */
+void pci_enable_ari(struct pci_dev *dev)
+{
+	int pos;
+	u32 cap;
+	u16 flags, ctrl;
+	struct pci_dev *bridge;
+
+	if (!pci_is_pcie(dev) || dev->devfn)
+		return;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ARI);
+	if (!pos)
+		return;
+
+	bridge = dev->bus->self;
+	if (!bridge || !pci_is_pcie(bridge))
+		return;
+
+	pos = pci_pcie_cap(bridge);
+	if (!pos)
+		return;
+
+	/* ARI is a PCIe v2 feature */
+	pci_read_config_word(bridge, pos + PCI_EXP_FLAGS, &flags);
+	if ((flags & PCI_EXP_FLAGS_VERS) < 2)
+		return;
+
+	pci_read_config_dword(bridge, pos + PCI_EXP_DEVCAP2, &cap);
+	if (!(cap & PCI_EXP_DEVCAP2_ARI))
+		return;
+
+	pci_read_config_word(bridge, pos + PCI_EXP_DEVCTL2, &ctrl);
+	ctrl |= PCI_EXP_DEVCTL2_ARI;
+	pci_write_config_word(bridge, pos + PCI_EXP_DEVCTL2, ctrl);
+
+	bridge->ari_enabled = 1;
+}
+
+/**
+ * pci_enable_ido - enable ID-based ordering on a device
+ * @dev: the PCI device
+ * @type: which types of IDO to enable
+ *
+ * Enable ID-based ordering on @dev.  @type can contain the bits
+ * %PCI_EXP_IDO_REQUEST and/or %PCI_EXP_IDO_COMPLETION to indicate
+ * which types of transactions are allowed to be re-ordered.
+ */
+void pci_enable_ido(struct pci_dev *dev, unsigned long type)
+{
+	int pos;
+	u16 ctrl;
+
+	pos = pci_pcie_cap(dev);
+	if (!pos)
+		return;
+
+	pci_read_config_word(dev, pos + PCI_EXP_DEVCTL2, &ctrl);
+	if (type & PCI_EXP_IDO_REQUEST)
+		ctrl |= PCI_EXP_IDO_REQ_EN;
+	if (type & PCI_EXP_IDO_COMPLETION)
+		ctrl |= PCI_EXP_IDO_CMP_EN;
+	pci_write_config_word(dev, pos + PCI_EXP_DEVCTL2, ctrl);
+}
+EXPORT_SYMBOL(pci_enable_ido);
+
+/**
+ * pci_disable_ido - disable ID-based ordering on a device
+ * @dev: the PCI device
+ * @type: which types of IDO to disable
+ */
+void pci_disable_ido(struct pci_dev *dev, unsigned long type)
+{
+	int pos;
+	u16 ctrl;
+
+	if (!pci_is_pcie(dev))
+		return;
+
+	pos = pci_pcie_cap(dev);
+	if (!pos)
+		return;
+
+	pci_read_config_word(dev, pos + PCI_EXP_DEVCTL2, &ctrl);
+	if (type & PCI_EXP_IDO_REQUEST)
+		ctrl &= ~PCI_EXP_IDO_REQ_EN;
+	if (type & PCI_EXP_IDO_COMPLETION)
+		ctrl &= ~PCI_EXP_IDO_CMP_EN;
+	pci_write_config_word(dev, pos + PCI_EXP_DEVCTL2, ctrl);
+}
+EXPORT_SYMBOL(pci_disable_ido);
+
+/**
+ * pci_enable_obff - enable optimized buffer flush/fill
+ * @dev: PCI device
+ * @type: type of signaling to use
+ *
+ * Try to enable @type OBFF signaling on @dev.  It will try using WAKE#
+ * signaling if possible, falling back to message signaling only if
+ * WAKE# isn't supported.  @type should indicate whether the PCIe link
+ * be brought out of L0s or L1 to send the message.  It should be either
+ * %PCI_EXP_OBFF_SIGNAL_ALWAYS or %PCI_OBFF_SIGNAL_L0.
+ *
+ * If your device can benefit from receiving all messages, even at the
+ * power cost of bringing the link back up from a low power state, use
+ * %PCI_EXP_OBFF_SIGNAL_ALWAYS.  Otherwise, use %PCI_OBFF_SIGNAL_L0 (the
+ * preferred type).
+ *
+ * RETURNS:
+ * Zero on success, appropriate error number on failure.
+ */
+int pci_enable_obff(struct pci_dev *dev, enum pci_obff_signal_type type)
+{
+	int pos;
+	u32 cap;
+	u16 ctrl;
+	int ret;
+
+	if (!pci_is_pcie(dev))
+		return -ENOTSUPP;
+
+	pos = pci_pcie_cap(dev);
+	if (!pos)
+		return -ENOTSUPP;
+
+	pci_read_config_dword(dev, pos + PCI_EXP_DEVCAP2, &cap);
+	if (!(cap & PCI_EXP_OBFF_MASK))
+		return -ENOTSUPP; /* no OBFF support at all */
+
+	/* Make sure the topology supports OBFF as well */
+	if (dev->bus) {
+		ret = pci_enable_obff(dev->bus->self, type);
+		if (ret)
+			return ret;
+	}
+
+	pci_read_config_word(dev, pos + PCI_EXP_DEVCTL2, &ctrl);
+	if (cap & PCI_EXP_OBFF_WAKE)
+		ctrl |= PCI_EXP_OBFF_WAKE_EN;
+	else {
+		switch (type) {
+		case PCI_EXP_OBFF_SIGNAL_L0:
+			if (!(ctrl & PCI_EXP_OBFF_WAKE_EN))
+				ctrl |= PCI_EXP_OBFF_MSGA_EN;
+			break;
+		case PCI_EXP_OBFF_SIGNAL_ALWAYS:
+			ctrl &= ~PCI_EXP_OBFF_WAKE_EN;
+			ctrl |= PCI_EXP_OBFF_MSGB_EN;
+			break;
+		default:
+			WARN(1, "bad OBFF signal type\n");
+			return -ENOTSUPP;
+		}
+	}
+	pci_write_config_word(dev, pos + PCI_EXP_DEVCTL2, ctrl);
+
+	return 0;
+}
+EXPORT_SYMBOL(pci_enable_obff);
+
+/**
+ * pci_disable_obff - disable optimized buffer flush/fill
+ * @dev: PCI device
+ *
+ * Disable OBFF on @dev.
+ */
+void pci_disable_obff(struct pci_dev *dev)
+{
+	int pos;
+	u16 ctrl;
+
+	if (!pci_is_pcie(dev))
+		return;
+
+	pos = pci_pcie_cap(dev);
+	if (!pos)
+		return;
+
+	pci_read_config_word(dev, pos + PCI_EXP_DEVCTL2, &ctrl);
+	ctrl &= ~PCI_EXP_OBFF_WAKE_EN;
+	pci_write_config_word(dev, pos + PCI_EXP_DEVCTL2, ctrl);
+}
+EXPORT_SYMBOL(pci_disable_obff);
+
+/**
+ * pci_ltr_supported - check whether a device supports LTR
+ * @dev: PCI device
+ *
+ * RETURNS:
+ * True if @dev supports latency tolerance reporting, false otherwise.
+ */
+bool pci_ltr_supported(struct pci_dev *dev)
+{
+	int pos;
+	u32 cap;
+
+	if (!pci_is_pcie(dev))
+		return false;
+
+	pos = pci_pcie_cap(dev);
+	if (!pos)
+		return false;
+
+	pci_read_config_dword(dev, pos + PCI_EXP_DEVCAP2, &cap);
+
+	return cap & PCI_EXP_DEVCAP2_LTR;
+}
+EXPORT_SYMBOL(pci_ltr_supported);
+
+/**
+ * pci_enable_ltr - enable latency tolerance reporting
+ * @dev: PCI device
+ *
+ * Enable LTR on @dev if possible, which means enabling it first on
+ * upstream ports.
+ *
+ * RETURNS:
+ * Zero on success, errno on failure.
+ */
+int pci_enable_ltr(struct pci_dev *dev)
+{
+	int pos;
+	u16 ctrl;
+	int ret;
+
+	if (!pci_ltr_supported(dev))
+		return -ENOTSUPP;
+
+	pos = pci_pcie_cap(dev);
+	if (!pos)
+		return -ENOTSUPP;
+
+	/* Only primary function can enable/disable LTR */
+	if (PCI_FUNC(dev->devfn) != 0)
+		return -EINVAL;
+
+	/* Enable upstream ports first */
+	if (dev->bus) {
+		ret = pci_enable_ltr(dev->bus->self);
+		if (ret)
+			return ret;
+	}
+
+	pci_read_config_word(dev, pos + PCI_EXP_DEVCTL2, &ctrl);
+	ctrl |= PCI_EXP_LTR_EN;
+	pci_write_config_word(dev, pos + PCI_EXP_DEVCTL2, ctrl);
+
+	return 0;
+}
+EXPORT_SYMBOL(pci_enable_ltr);
+
+/**
+ * pci_disable_ltr - disable latency tolerance reporting
+ * @dev: PCI device
+ */
+void pci_disable_ltr(struct pci_dev *dev)
+{
+	int pos;
+	u16 ctrl;
+
+	if (!pci_ltr_supported(dev))
+		return;
+
+	pos = pci_pcie_cap(dev);
+	if (!pos)
+		return;
+
+	/* Only primary function can enable/disable LTR */
+	if (PCI_FUNC(dev->devfn) != 0)
+		return;
+
+	pci_read_config_word(dev, pos + PCI_EXP_DEVCTL2, &ctrl);
+	ctrl &= ~PCI_EXP_LTR_EN;
+	pci_write_config_word(dev, pos + PCI_EXP_DEVCTL2, ctrl);
+}
+EXPORT_SYMBOL(pci_disable_ltr);
+
+static int __pci_ltr_scale(int *val)
+{
+	int scale = 0;
+
+	while (*val > 1023) {
+		*val = (*val + 31) / 32;
+		scale++;
+	}
+	return scale;
+}
+
+/**
+ * pci_set_ltr - set LTR latency values
+ * @dev: PCI device
+ * @snoop_lat_ns: snoop latency in nanoseconds
+ * @nosnoop_lat_ns: nosnoop latency in nanoseconds
+ *
+ * Figure out the scale and set the LTR values accordingly.
+ */
+int pci_set_ltr(struct pci_dev *dev, int snoop_lat_ns, int nosnoop_lat_ns)
+{
+	int pos, ret, snoop_scale, nosnoop_scale;
+	u16 val;
+
+	if (!pci_ltr_supported(dev))
+		return -ENOTSUPP;
+
+	snoop_scale = __pci_ltr_scale(&snoop_lat_ns);
+	nosnoop_scale = __pci_ltr_scale(&nosnoop_lat_ns);
+
+	if (snoop_lat_ns > PCI_LTR_VALUE_MASK ||
+	    nosnoop_lat_ns > PCI_LTR_VALUE_MASK)
+		return -EINVAL;
+
+	if ((snoop_scale > (PCI_LTR_SCALE_MASK >> PCI_LTR_SCALE_SHIFT)) ||
+	    (nosnoop_scale > (PCI_LTR_SCALE_MASK >> PCI_LTR_SCALE_SHIFT)))
+		return -EINVAL;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_LTR);
+	if (!pos)
+		return -ENOTSUPP;
+
+	val = (snoop_scale << PCI_LTR_SCALE_SHIFT) | snoop_lat_ns;
+	ret = pci_write_config_word(dev, pos + PCI_LTR_MAX_SNOOP_LAT, val);
+	if (ret != 4)
+		return -EIO;
+
+	val = (nosnoop_scale << PCI_LTR_SCALE_SHIFT) | nosnoop_lat_ns;
+	ret = pci_write_config_word(dev, pos + PCI_LTR_MAX_NOSNOOP_LAT, val);
+	if (ret != 4)
+		return -EIO;
+
+	return 0;
+}
+EXPORT_SYMBOL(pci_set_ltr);
+
+static int pci_acs_enable;
+
+/**
+ * pci_request_acs - ask for ACS to be enabled if supported
+ */
+void pci_request_acs(void)
+{
+	pci_acs_enable = 1;
+}
+
+/**
+ * pci_enable_acs - enable ACS if hardware support it
+ * @dev: the PCI device
+ */
+void pci_enable_acs(struct pci_dev *dev)
+{
+	int pos;
+	u16 cap;
+	u16 ctrl;
+
+	if (!pci_acs_enable)
+		return;
+
+	if (!pci_is_pcie(dev))
+		return;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
+	if (!pos)
+		return;
+
+	pci_read_config_word(dev, pos + PCI_ACS_CAP, &cap);
+	pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl);
+
+	/* Source Validation */
+	ctrl |= (cap & PCI_ACS_SV);
+
+	/* P2P Request Redirect */
+	ctrl |= (cap & PCI_ACS_RR);
+
+	/* P2P Completion Redirect */
+	ctrl |= (cap & PCI_ACS_CR);
+
+	/* Upstream Forwarding */
+	ctrl |= (cap & PCI_ACS_UF);
+
+	pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl);
+}
+
+/**
+ * pci_swizzle_interrupt_pin - swizzle INTx for device behind bridge
+ * @dev: the PCI device
+ * @pin: the INTx pin (1=INTA, 2=INTB, 3=INTD, 4=INTD)
+ *
+ * Perform INTx swizzling for a device behind one level of bridge.  This is
+ * required by section 9.1 of the PCI-to-PCI bridge specification for devices
+ * behind bridges on add-in cards.  For devices with ARI enabled, the slot
+ * number is always 0 (see the Implementation Note in section 2.2.8.1 of
+ * the PCI Express Base Specification, Revision 2.1)
+ */
+u8 pci_swizzle_interrupt_pin(struct pci_dev *dev, u8 pin)
+{
+	int slot;
+
+	if (pci_ari_enabled(dev->bus))
+		slot = 0;
+	else
+		slot = PCI_SLOT(dev->devfn);
+
+	return (((pin - 1) + slot) % 4) + 1;
+}
+
+int
+pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge)
+{
+	u8 pin;
+
+	pin = dev->pin;
+	if (!pin)
+		return -1;
+
+	while (!pci_is_root_bus(dev->bus)) {
+		pin = pci_swizzle_interrupt_pin(dev, pin);
+		dev = dev->bus->self;
+	}
+	*bridge = dev;
+	return pin;
+}
+
+/**
+ * pci_common_swizzle - swizzle INTx all the way to root bridge
+ * @dev: the PCI device
+ * @pinp: pointer to the INTx pin value (1=INTA, 2=INTB, 3=INTD, 4=INTD)
+ *
+ * Perform INTx swizzling for a device.  This traverses through all PCI-to-PCI
+ * bridges all the way up to a PCI root bus.
+ */
+u8 pci_common_swizzle(struct pci_dev *dev, u8 *pinp)
+{
+	u8 pin = *pinp;
+
+	while (!pci_is_root_bus(dev->bus)) {
+		pin = pci_swizzle_interrupt_pin(dev, pin);
+		dev = dev->bus->self;
+	}
+	*pinp = pin;
+	return PCI_SLOT(dev->devfn);
+}
+
+/**
+ *	pci_release_region - Release a PCI bar
+ *	@pdev: PCI device whose resources were previously reserved by pci_request_region
+ *	@bar: BAR to release
+ *
+ *	Releases the PCI I/O and memory resources previously reserved by a
+ *	successful call to pci_request_region.  Call this function only
+ *	after all use of the PCI regions has ceased.
+ */
+void pci_release_region(struct pci_dev *pdev, int bar)
+{
+	struct pci_devres *dr;
+
+	if (pci_resource_len(pdev, bar) == 0)
+		return;
+	if (pci_resource_flags(pdev, bar) & IORESOURCE_IO)
+		release_region(pci_resource_start(pdev, bar),
+				pci_resource_len(pdev, bar));
+	else if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM)
+		release_mem_region(pci_resource_start(pdev, bar),
+				pci_resource_len(pdev, bar));
+
+	dr = find_pci_dr(pdev);
+	if (dr)
+		dr->region_mask &= ~(1 << bar);
+}
+
+/**
+ *	__pci_request_region - Reserved PCI I/O and memory resource
+ *	@pdev: PCI device whose resources are to be reserved
+ *	@bar: BAR to be reserved
+ *	@res_name: Name to be associated with resource.
+ *	@exclusive: whether the region access is exclusive or not
+ *
+ *	Mark the PCI region associated with PCI device @pdev BR @bar as
+ *	being reserved by owner @res_name.  Do not access any
+ *	address inside the PCI regions unless this call returns
+ *	successfully.
+ *
+ *	If @exclusive is set, then the region is marked so that userspace
+ *	is explicitly not allowed to map the resource via /dev/mem or
+ * 	sysfs MMIO access.
+ *
+ *	Returns 0 on success, or %EBUSY on error.  A warning
+ *	message is also printed on failure.
+ */
+static int __pci_request_region(struct pci_dev *pdev, int bar, const char *res_name,
+									int exclusive)
+{
+	struct pci_devres *dr;
+
+	if (pci_resource_len(pdev, bar) == 0)
+		return 0;
+		
+	if (pci_resource_flags(pdev, bar) & IORESOURCE_IO) {
+		if (!request_region(pci_resource_start(pdev, bar),
+			    pci_resource_len(pdev, bar), res_name))
+			goto err_out;
+	}
+	else if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) {
+		if (!__request_mem_region(pci_resource_start(pdev, bar),
+					pci_resource_len(pdev, bar), res_name,
+					exclusive))
+			goto err_out;
+	}
+
+	dr = find_pci_dr(pdev);
+	if (dr)
+		dr->region_mask |= 1 << bar;
+
+	return 0;
+
+err_out:
+	dev_warn(&pdev->dev, "BAR %d: can't reserve %pR\n", bar,
+		 &pdev->resource[bar]);
+	return -EBUSY;
+}
+
+/**
+ *	pci_request_region - Reserve PCI I/O and memory resource
+ *	@pdev: PCI device whose resources are to be reserved
+ *	@bar: BAR to be reserved
+ *	@res_name: Name to be associated with resource
+ *
+ *	Mark the PCI region associated with PCI device @pdev BAR @bar as
+ *	being reserved by owner @res_name.  Do not access any
+ *	address inside the PCI regions unless this call returns
+ *	successfully.
+ *
+ *	Returns 0 on success, or %EBUSY on error.  A warning
+ *	message is also printed on failure.
+ */
+int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name)
+{
+	return __pci_request_region(pdev, bar, res_name, 0);
+}
+
+/**
+ *	pci_request_region_exclusive - Reserved PCI I/O and memory resource
+ *	@pdev: PCI device whose resources are to be reserved
+ *	@bar: BAR to be reserved
+ *	@res_name: Name to be associated with resource.
+ *
+ *	Mark the PCI region associated with PCI device @pdev BR @bar as
+ *	being reserved by owner @res_name.  Do not access any
+ *	address inside the PCI regions unless this call returns
+ *	successfully.
+ *
+ *	Returns 0 on success, or %EBUSY on error.  A warning
+ *	message is also printed on failure.
+ *
+ *	The key difference that _exclusive makes it that userspace is
+ *	explicitly not allowed to map the resource via /dev/mem or
+ * 	sysfs.
+ */
+int pci_request_region_exclusive(struct pci_dev *pdev, int bar, const char *res_name)
+{
+	return __pci_request_region(pdev, bar, res_name, IORESOURCE_EXCLUSIVE);
+}
+/**
+ * pci_release_selected_regions - Release selected PCI I/O and memory resources
+ * @pdev: PCI device whose resources were previously reserved
+ * @bars: Bitmask of BARs to be released
+ *
+ * Release selected PCI I/O and memory resources previously reserved.
+ * Call this function only after all use of the PCI regions has ceased.
+ */
+void pci_release_selected_regions(struct pci_dev *pdev, int bars)
+{
+	int i;
+
+	for (i = 0; i < 6; i++)
+		if (bars & (1 << i))
+			pci_release_region(pdev, i);
+}
+
+int __pci_request_selected_regions(struct pci_dev *pdev, int bars,
+				 const char *res_name, int excl)
+{
+	int i;
+
+	for (i = 0; i < 6; i++)
+		if (bars & (1 << i))
+			if (__pci_request_region(pdev, i, res_name, excl))
+				goto err_out;
+	return 0;
+
+err_out:
+	while(--i >= 0)
+		if (bars & (1 << i))
+			pci_release_region(pdev, i);
+
+	return -EBUSY;
+}
+
+
+/**
+ * pci_request_selected_regions - Reserve selected PCI I/O and memory resources
+ * @pdev: PCI device whose resources are to be reserved
+ * @bars: Bitmask of BARs to be requested
+ * @res_name: Name to be associated with resource
+ */
+int pci_request_selected_regions(struct pci_dev *pdev, int bars,
+				 const char *res_name)
+{
+	return __pci_request_selected_regions(pdev, bars, res_name, 0);
+}
+
+int pci_request_selected_regions_exclusive(struct pci_dev *pdev,
+				 int bars, const char *res_name)
+{
+	return __pci_request_selected_regions(pdev, bars, res_name,
+			IORESOURCE_EXCLUSIVE);
+}
+
+/**
+ *	pci_release_regions - Release reserved PCI I/O and memory resources
+ *	@pdev: PCI device whose resources were previously reserved by pci_request_regions
+ *
+ *	Releases all PCI I/O and memory resources previously reserved by a
+ *	successful call to pci_request_regions.  Call this function only
+ *	after all use of the PCI regions has ceased.
+ */
+
+void pci_release_regions(struct pci_dev *pdev)
+{
+	pci_release_selected_regions(pdev, (1 << 6) - 1);
+}
+
+/**
+ *	pci_request_regions - Reserved PCI I/O and memory resources
+ *	@pdev: PCI device whose resources are to be reserved
+ *	@res_name: Name to be associated with resource.
+ *
+ *	Mark all PCI regions associated with PCI device @pdev as
+ *	being reserved by owner @res_name.  Do not access any
+ *	address inside the PCI regions unless this call returns
+ *	successfully.
+ *
+ *	Returns 0 on success, or %EBUSY on error.  A warning
+ *	message is also printed on failure.
+ */
+int pci_request_regions(struct pci_dev *pdev, const char *res_name)
+{
+	return pci_request_selected_regions(pdev, ((1 << 6) - 1), res_name);
+}
+
+/**
+ *	pci_request_regions_exclusive - Reserved PCI I/O and memory resources
+ *	@pdev: PCI device whose resources are to be reserved
+ *	@res_name: Name to be associated with resource.
+ *
+ *	Mark all PCI regions associated with PCI device @pdev as
+ *	being reserved by owner @res_name.  Do not access any
+ *	address inside the PCI regions unless this call returns
+ *	successfully.
+ *
+ *	pci_request_regions_exclusive() will mark the region so that
+ * 	/dev/mem and the sysfs MMIO access will not be allowed.
+ *
+ *	Returns 0 on success, or %EBUSY on error.  A warning
+ *	message is also printed on failure.
+ */
+int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name)
+{
+	return pci_request_selected_regions_exclusive(pdev,
+					((1 << 6) - 1), res_name);
+}
+
+static void __pci_set_master(struct pci_dev *dev, bool enable)
+{
+	u16 old_cmd, cmd;
+
+	pci_read_config_word(dev, PCI_COMMAND, &old_cmd);
+	if (enable)
+		cmd = old_cmd | PCI_COMMAND_MASTER;
+	else
+		cmd = old_cmd & ~PCI_COMMAND_MASTER;
+	if (cmd != old_cmd) {
+		dev_dbg(&dev->dev, "%s bus mastering\n",
+			enable ? "enabling" : "disabling");
+		pci_write_config_word(dev, PCI_COMMAND, cmd);
+	}
+	dev->is_busmaster = enable;
+}
+
+/**
+ * pci_set_master - enables bus-mastering for device dev
+ * @dev: the PCI device to enable
+ *
+ * Enables bus-mastering on the device and calls pcibios_set_master()
+ * to do the needed arch specific settings.
+ */
+void pci_set_master(struct pci_dev *dev)
+{
+	__pci_set_master(dev, true);
+	pcibios_set_master(dev);
+}
+
+/**
+ * pci_clear_master - disables bus-mastering for device dev
+ * @dev: the PCI device to disable
+ */
+void pci_clear_master(struct pci_dev *dev)
+{
+	__pci_set_master(dev, false);
+}
+
+/**
+ * pci_set_cacheline_size - ensure the CACHE_LINE_SIZE register is programmed
+ * @dev: the PCI device for which MWI is to be enabled
+ *
+ * Helper function for pci_set_mwi.
+ * Originally copied from drivers/net/acenic.c.
+ * Copyright 1998-2001 by Jes Sorensen, <jes@trained-monkey.org>.
+ *
+ * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
+ */
+int pci_set_cacheline_size(struct pci_dev *dev)
+{
+	u8 cacheline_size;
+
+	if (!pci_cache_line_size)
+		return -EINVAL;
+
+	/* Validate current setting: the PCI_CACHE_LINE_SIZE must be
+	   equal to or multiple of the right value. */
+	pci_read_config_byte(dev, PCI_CACHE_LINE_SIZE, &cacheline_size);
+	if (cacheline_size >= pci_cache_line_size &&
+	    (cacheline_size % pci_cache_line_size) == 0)
+		return 0;
+
+	/* Write the correct value. */
+	pci_write_config_byte(dev, PCI_CACHE_LINE_SIZE, pci_cache_line_size);
+	/* Read it back. */
+	pci_read_config_byte(dev, PCI_CACHE_LINE_SIZE, &cacheline_size);
+	if (cacheline_size == pci_cache_line_size)
+		return 0;
+
+	dev_printk(KERN_DEBUG, &dev->dev, "cache line size of %d is not "
+		   "supported\n", pci_cache_line_size << 2);
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(pci_set_cacheline_size);
+
+#ifdef PCI_DISABLE_MWI
+int pci_set_mwi(struct pci_dev *dev)
+{
+	return 0;
+}
+
+int pci_try_set_mwi(struct pci_dev *dev)
+{
+	return 0;
+}
+
+void pci_clear_mwi(struct pci_dev *dev)
+{
+}
+
+#else
+
+/**
+ * pci_set_mwi - enables memory-write-invalidate PCI transaction
+ * @dev: the PCI device for which MWI is enabled
+ *
+ * Enables the Memory-Write-Invalidate transaction in %PCI_COMMAND.
+ *
+ * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
+ */
+int
+pci_set_mwi(struct pci_dev *dev)
+{
+	int rc;
+	u16 cmd;
+
+	rc = pci_set_cacheline_size(dev);
+	if (rc)
+		return rc;
+
+	pci_read_config_word(dev, PCI_COMMAND, &cmd);
+	if (! (cmd & PCI_COMMAND_INVALIDATE)) {
+		dev_dbg(&dev->dev, "enabling Mem-Wr-Inval\n");
+		cmd |= PCI_COMMAND_INVALIDATE;
+		pci_write_config_word(dev, PCI_COMMAND, cmd);
+	}
+	
+	return 0;
+}
+
+/**
+ * pci_try_set_mwi - enables memory-write-invalidate PCI transaction
+ * @dev: the PCI device for which MWI is enabled
+ *
+ * Enables the Memory-Write-Invalidate transaction in %PCI_COMMAND.
+ * Callers are not required to check the return value.
+ *
+ * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
+ */
+int pci_try_set_mwi(struct pci_dev *dev)
+{
+	int rc = pci_set_mwi(dev);
+	return rc;
+}
+
+/**
+ * pci_clear_mwi - disables Memory-Write-Invalidate for device dev
+ * @dev: the PCI device to disable
+ *
+ * Disables PCI Memory-Write-Invalidate transaction on the device
+ */
+void
+pci_clear_mwi(struct pci_dev *dev)
+{
+	u16 cmd;
+
+	pci_read_config_word(dev, PCI_COMMAND, &cmd);
+	if (cmd & PCI_COMMAND_INVALIDATE) {
+		cmd &= ~PCI_COMMAND_INVALIDATE;
+		pci_write_config_word(dev, PCI_COMMAND, cmd);
+	}
+}
+#endif /* ! PCI_DISABLE_MWI */
+
+/**
+ * pci_intx - enables/disables PCI INTx for device dev
+ * @pdev: the PCI device to operate on
+ * @enable: boolean: whether to enable or disable PCI INTx
+ *
+ * Enables/disables PCI INTx for device dev
+ */
+void
+pci_intx(struct pci_dev *pdev, int enable)
+{
+	u16 pci_command, new;
+
+	pci_read_config_word(pdev, PCI_COMMAND, &pci_command);
+
+	if (enable) {
+		new = pci_command & ~PCI_COMMAND_INTX_DISABLE;
+	} else {
+		new = pci_command | PCI_COMMAND_INTX_DISABLE;
+	}
+
+	if (new != pci_command) {
+		struct pci_devres *dr;
+
+		pci_write_config_word(pdev, PCI_COMMAND, new);
+
+		dr = find_pci_dr(pdev);
+		if (dr && !dr->restore_intx) {
+			dr->restore_intx = 1;
+			dr->orig_intx = !enable;
+		}
+	}
+}
+
+/**
+ * pci_msi_off - disables any msi or msix capabilities
+ * @dev: the PCI device to operate on
+ *
+ * If you want to use msi see pci_enable_msi and friends.
+ * This is a lower level primitive that allows us to disable
+ * msi operation at the device level.
+ */
+void pci_msi_off(struct pci_dev *dev)
+{
+	int pos;
+	u16 control;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	if (pos) {
+		pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &control);
+		control &= ~PCI_MSI_FLAGS_ENABLE;
+		pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control);
+	}
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+	if (pos) {
+		pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control);
+		control &= ~PCI_MSIX_FLAGS_ENABLE;
+		pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
+	}
+}
+EXPORT_SYMBOL_GPL(pci_msi_off);
+
+int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size)
+{
+	return dma_set_max_seg_size(&dev->dev, size);
+}
+EXPORT_SYMBOL(pci_set_dma_max_seg_size);
+
+int pci_set_dma_seg_boundary(struct pci_dev *dev, unsigned long mask)
+{
+	return dma_set_seg_boundary(&dev->dev, mask);
+}
+EXPORT_SYMBOL(pci_set_dma_seg_boundary);
+
+static int pcie_flr(struct pci_dev *dev, int probe)
+{
+	int i;
+	int pos;
+	u32 cap;
+	u16 status, control;
+
+	pos = pci_pcie_cap(dev);
+	if (!pos)
+		return -ENOTTY;
+
+	pci_read_config_dword(dev, pos + PCI_EXP_DEVCAP, &cap);
+	if (!(cap & PCI_EXP_DEVCAP_FLR))
+		return -ENOTTY;
+
+	if (probe)
+		return 0;
+
+	/* Wait for Transaction Pending bit clean */
+	for (i = 0; i < 4; i++) {
+		if (i)
+			msleep((1 << (i - 1)) * 100);
+
+		pci_read_config_word(dev, pos + PCI_EXP_DEVSTA, &status);
+		if (!(status & PCI_EXP_DEVSTA_TRPND))
+			goto clear;
+	}
+
+	dev_err(&dev->dev, "transaction is not cleared; "
+			"proceeding with reset anyway\n");
+
+clear:
+	pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &control);
+	control |= PCI_EXP_DEVCTL_BCR_FLR;
+	pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, control);
+
+	msleep(100);
+
+	return 0;
+}
+
+static int pci_af_flr(struct pci_dev *dev, int probe)
+{
+	int i;
+	int pos;
+	u8 cap;
+	u8 status;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_AF);
+	if (!pos)
+		return -ENOTTY;
+
+	pci_read_config_byte(dev, pos + PCI_AF_CAP, &cap);
+	if (!(cap & PCI_AF_CAP_TP) || !(cap & PCI_AF_CAP_FLR))
+		return -ENOTTY;
+
+	if (probe)
+		return 0;
+
+	/* Wait for Transaction Pending bit clean */
+	for (i = 0; i < 4; i++) {
+		if (i)
+			msleep((1 << (i - 1)) * 100);
+
+		pci_read_config_byte(dev, pos + PCI_AF_STATUS, &status);
+		if (!(status & PCI_AF_STATUS_TP))
+			goto clear;
+	}
+
+	dev_err(&dev->dev, "transaction is not cleared; "
+			"proceeding with reset anyway\n");
+
+clear:
+	pci_write_config_byte(dev, pos + PCI_AF_CTRL, PCI_AF_CTRL_FLR);
+	msleep(100);
+
+	return 0;
+}
+
+/**
+ * pci_pm_reset - Put device into PCI_D3 and back into PCI_D0.
+ * @dev: Device to reset.
+ * @probe: If set, only check if the device can be reset this way.
+ *
+ * If @dev supports native PCI PM and its PCI_PM_CTRL_NO_SOFT_RESET flag is
+ * unset, it will be reinitialized internally when going from PCI_D3hot to
+ * PCI_D0.  If that's the case and the device is not in a low-power state
+ * already, force it into PCI_D3hot and back to PCI_D0, causing it to be reset.
+ *
+ * NOTE: This causes the caller to sleep for twice the device power transition
+ * cooldown period, which for the D0->D3hot and D3hot->D0 transitions is 10 ms
+ * by devault (i.e. unless the @dev's d3_delay field has a different value).
+ * Moreover, only devices in D0 can be reset by this function.
+ */
+static int pci_pm_reset(struct pci_dev *dev, int probe)
+{
+	u16 csr;
+
+	if (!dev->pm_cap)
+		return -ENOTTY;
+
+	pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &csr);
+	if (csr & PCI_PM_CTRL_NO_SOFT_RESET)
+		return -ENOTTY;
+
+	if (probe)
+		return 0;
+
+	if (dev->current_state != PCI_D0)
+		return -EINVAL;
+
+	csr &= ~PCI_PM_CTRL_STATE_MASK;
+	csr |= PCI_D3hot;
+	pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, csr);
+	pci_dev_d3_sleep(dev);
+
+	csr &= ~PCI_PM_CTRL_STATE_MASK;
+	csr |= PCI_D0;
+	pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, csr);
+	pci_dev_d3_sleep(dev);
+
+	return 0;
+}
+
+static int pci_parent_bus_reset(struct pci_dev *dev, int probe)
+{
+	u16 ctrl;
+	struct pci_dev *pdev;
+
+	if (pci_is_root_bus(dev->bus) || dev->subordinate || !dev->bus->self)
+		return -ENOTTY;
+
+	list_for_each_entry(pdev, &dev->bus->devices, bus_list)
+		if (pdev != dev)
+			return -ENOTTY;
+
+	if (probe)
+		return 0;
+
+	pci_read_config_word(dev->bus->self, PCI_BRIDGE_CONTROL, &ctrl);
+	ctrl |= PCI_BRIDGE_CTL_BUS_RESET;
+	pci_write_config_word(dev->bus->self, PCI_BRIDGE_CONTROL, ctrl);
+	msleep(100);
+
+	ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET;
+	pci_write_config_word(dev->bus->self, PCI_BRIDGE_CONTROL, ctrl);
+	msleep(100);
+
+	return 0;
+}
+
+static int pci_dev_reset(struct pci_dev *dev, int probe)
+{
+	int rc;
+
+	might_sleep();
+
+	if (!probe) {
+		pci_block_user_cfg_access(dev);
+		/* block PM suspend, driver probe, etc. */
+		device_lock(&dev->dev);
+	}
+
+	rc = pci_dev_specific_reset(dev, probe);
+	if (rc != -ENOTTY)
+		goto done;
+
+	rc = pcie_flr(dev, probe);
+	if (rc != -ENOTTY)
+		goto done;
+
+	rc = pci_af_flr(dev, probe);
+	if (rc != -ENOTTY)
+		goto done;
+
+	rc = pci_pm_reset(dev, probe);
+	if (rc != -ENOTTY)
+		goto done;
+
+	rc = pci_parent_bus_reset(dev, probe);
+done:
+	if (!probe) {
+		device_unlock(&dev->dev);
+		pci_unblock_user_cfg_access(dev);
+	}
+
+	return rc;
+}
+
+/**
+ * __pci_reset_function - reset a PCI device function
+ * @dev: PCI device to reset
+ *
+ * Some devices allow an individual function to be reset without affecting
+ * other functions in the same device.  The PCI device must be responsive
+ * to PCI config space in order to use this function.
+ *
+ * The device function is presumed to be unused when this function is called.
+ * Resetting the device will make the contents of PCI configuration space
+ * random, so any caller of this must be prepared to reinitialise the
+ * device including MSI, bus mastering, BARs, decoding IO and memory spaces,
+ * etc.
+ *
+ * Returns 0 if the device function was successfully reset or negative if the
+ * device doesn't support resetting a single function.
+ */
+int __pci_reset_function(struct pci_dev *dev)
+{
+	return pci_dev_reset(dev, 0);
+}
+EXPORT_SYMBOL_GPL(__pci_reset_function);
+
+/**
+ * pci_probe_reset_function - check whether the device can be safely reset
+ * @dev: PCI device to reset
+ *
+ * Some devices allow an individual function to be reset without affecting
+ * other functions in the same device.  The PCI device must be responsive
+ * to PCI config space in order to use this function.
+ *
+ * Returns 0 if the device function can be reset or negative if the
+ * device doesn't support resetting a single function.
+ */
+int pci_probe_reset_function(struct pci_dev *dev)
+{
+	return pci_dev_reset(dev, 1);
+}
+
+/**
+ * pci_reset_function - quiesce and reset a PCI device function
+ * @dev: PCI device to reset
+ *
+ * Some devices allow an individual function to be reset without affecting
+ * other functions in the same device.  The PCI device must be responsive
+ * to PCI config space in order to use this function.
+ *
+ * This function does not just reset the PCI portion of a device, but
+ * clears all the state associated with the device.  This function differs
+ * from __pci_reset_function in that it saves and restores device state
+ * over the reset.
+ *
+ * Returns 0 if the device function was successfully reset or negative if the
+ * device doesn't support resetting a single function.
+ */
+int pci_reset_function(struct pci_dev *dev)
+{
+	int rc;
+
+	rc = pci_dev_reset(dev, 1);
+	if (rc)
+		return rc;
+
+	pci_save_state(dev);
+
+	/*
+	 * both INTx and MSI are disabled after the Interrupt Disable bit
+	 * is set and the Bus Master bit is cleared.
+	 */
+	pci_write_config_word(dev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
+
+	rc = pci_dev_reset(dev, 0);
+
+	pci_restore_state(dev);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(pci_reset_function);
+
+/**
+ * pcix_get_max_mmrbc - get PCI-X maximum designed memory read byte count
+ * @dev: PCI device to query
+ *
+ * Returns mmrbc: maximum designed memory read count in bytes
+ *    or appropriate error value.
+ */
+int pcix_get_max_mmrbc(struct pci_dev *dev)
+{
+	int cap;
+	u32 stat;
+
+	cap = pci_find_capability(dev, PCI_CAP_ID_PCIX);
+	if (!cap)
+		return -EINVAL;
+
+	if (pci_read_config_dword(dev, cap + PCI_X_STATUS, &stat))
+		return -EINVAL;
+
+	return 512 << ((stat & PCI_X_STATUS_MAX_READ) >> 21);
+}
+EXPORT_SYMBOL(pcix_get_max_mmrbc);
+
+/**
+ * pcix_get_mmrbc - get PCI-X maximum memory read byte count
+ * @dev: PCI device to query
+ *
+ * Returns mmrbc: maximum memory read count in bytes
+ *    or appropriate error value.
+ */
+int pcix_get_mmrbc(struct pci_dev *dev)
+{
+	int cap;
+	u16 cmd;
+
+	cap = pci_find_capability(dev, PCI_CAP_ID_PCIX);
+	if (!cap)
+		return -EINVAL;
+
+	if (pci_read_config_word(dev, cap + PCI_X_CMD, &cmd))
+		return -EINVAL;
+
+	return 512 << ((cmd & PCI_X_CMD_MAX_READ) >> 2);
+}
+EXPORT_SYMBOL(pcix_get_mmrbc);
+
+/**
+ * pcix_set_mmrbc - set PCI-X maximum memory read byte count
+ * @dev: PCI device to query
+ * @mmrbc: maximum memory read count in bytes
+ *    valid values are 512, 1024, 2048, 4096
+ *
+ * If possible sets maximum memory read byte count, some bridges have erratas
+ * that prevent this.
+ */
+int pcix_set_mmrbc(struct pci_dev *dev, int mmrbc)
+{
+	int cap;
+	u32 stat, v, o;
+	u16 cmd;
+
+	if (mmrbc < 512 || mmrbc > 4096 || !is_power_of_2(mmrbc))
+		return -EINVAL;
+
+	v = ffs(mmrbc) - 10;
+
+	cap = pci_find_capability(dev, PCI_CAP_ID_PCIX);
+	if (!cap)
+		return -EINVAL;
+
+	if (pci_read_config_dword(dev, cap + PCI_X_STATUS, &stat))
+		return -EINVAL;
+
+	if (v > (stat & PCI_X_STATUS_MAX_READ) >> 21)
+		return -E2BIG;
+
+	if (pci_read_config_word(dev, cap + PCI_X_CMD, &cmd))
+		return -EINVAL;
+
+	o = (cmd & PCI_X_CMD_MAX_READ) >> 2;
+	if (o != v) {
+		if (v > o && dev->bus &&
+		   (dev->bus->bus_flags & PCI_BUS_FLAGS_NO_MMRBC))
+			return -EIO;
+
+		cmd &= ~PCI_X_CMD_MAX_READ;
+		cmd |= v << 2;
+		if (pci_write_config_word(dev, cap + PCI_X_CMD, cmd))
+			return -EIO;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(pcix_set_mmrbc);
+
+/**
+ * pcie_get_readrq - get PCI Express read request size
+ * @dev: PCI device to query
+ *
+ * Returns maximum memory read request in bytes
+ *    or appropriate error value.
+ */
+int pcie_get_readrq(struct pci_dev *dev)
+{
+	int ret, cap;
+	u16 ctl;
+
+	cap = pci_pcie_cap(dev);
+	if (!cap)
+		return -EINVAL;
+
+	ret = pci_read_config_word(dev, cap + PCI_EXP_DEVCTL, &ctl);
+	if (!ret)
+		ret = 128 << ((ctl & PCI_EXP_DEVCTL_READRQ) >> 12);
+
+	return ret;
+}
+EXPORT_SYMBOL(pcie_get_readrq);
+
+/**
+ * pcie_set_readrq - set PCI Express maximum memory read request
+ * @dev: PCI device to query
+ * @rq: maximum memory read count in bytes
+ *    valid values are 128, 256, 512, 1024, 2048, 4096
+ *
+ * If possible sets maximum read byte count
+ */
+int pcie_set_readrq(struct pci_dev *dev, int rq)
+{
+	int cap, err = -EINVAL;
+	u16 ctl, v;
+
+	if (rq < 128 || rq > 4096 || !is_power_of_2(rq))
+		goto out;
+
+	v = (ffs(rq) - 8) << 12;
+
+	cap = pci_pcie_cap(dev);
+	if (!cap)
+		goto out;
+
+	err = pci_read_config_word(dev, cap + PCI_EXP_DEVCTL, &ctl);
+	if (err)
+		goto out;
+
+	if ((ctl & PCI_EXP_DEVCTL_READRQ) != v) {
+		ctl &= ~PCI_EXP_DEVCTL_READRQ;
+		ctl |= v;
+		err = pci_write_config_dword(dev, cap + PCI_EXP_DEVCTL, ctl);
+	}
+
+out:
+	return err;
+}
+EXPORT_SYMBOL(pcie_set_readrq);
+
+/**
+ * pci_select_bars - Make BAR mask from the type of resource
+ * @dev: the PCI device for which BAR mask is made
+ * @flags: resource type mask to be selected
+ *
+ * This helper routine makes bar mask from the type of resource.
+ */
+int pci_select_bars(struct pci_dev *dev, unsigned long flags)
+{
+	int i, bars = 0;
+	for (i = 0; i < PCI_NUM_RESOURCES; i++)
+		if (pci_resource_flags(dev, i) & flags)
+			bars |= (1 << i);
+	return bars;
+}
+
+/**
+ * pci_resource_bar - get position of the BAR associated with a resource
+ * @dev: the PCI device
+ * @resno: the resource number
+ * @type: the BAR type to be filled in
+ *
+ * Returns BAR position in config space, or 0 if the BAR is invalid.
+ */
+int pci_resource_bar(struct pci_dev *dev, int resno, enum pci_bar_type *type)
+{
+	int reg;
+
+	if (resno < PCI_ROM_RESOURCE) {
+		*type = pci_bar_unknown;
+		return PCI_BASE_ADDRESS_0 + 4 * resno;
+	} else if (resno == PCI_ROM_RESOURCE) {
+		*type = pci_bar_mem32;
+		return dev->rom_base_reg;
+	} else if (resno < PCI_BRIDGE_RESOURCES) {
+		/* device specific resource */
+		reg = pci_iov_resource_bar(dev, resno, type);
+		if (reg)
+			return reg;
+	}
+
+	dev_err(&dev->dev, "BAR %d: invalid resource\n", resno);
+	return 0;
+}
+
+/* Some architectures require additional programming to enable VGA */
+static arch_set_vga_state_t arch_set_vga_state;
+
+void __init pci_register_set_vga_state(arch_set_vga_state_t func)
+{
+	arch_set_vga_state = func;	/* NULL disables */
+}
+
+static int pci_set_vga_state_arch(struct pci_dev *dev, bool decode,
+		      unsigned int command_bits, u32 flags)
+{
+	if (arch_set_vga_state)
+		return arch_set_vga_state(dev, decode, command_bits,
+						flags);
+	return 0;
+}
+
+/**
+ * pci_set_vga_state - set VGA decode state on device and parents if requested
+ * @dev: the PCI device
+ * @decode: true = enable decoding, false = disable decoding
+ * @command_bits: PCI_COMMAND_IO and/or PCI_COMMAND_MEMORY
+ * @flags: traverse ancestors and change bridges
+ * CHANGE_BRIDGE_ONLY / CHANGE_BRIDGE
+ */
+int pci_set_vga_state(struct pci_dev *dev, bool decode,
+		      unsigned int command_bits, u32 flags)
+{
+	struct pci_bus *bus;
+	struct pci_dev *bridge;
+	u16 cmd;
+	int rc;
+
+	WARN_ON((flags & PCI_VGA_STATE_CHANGE_DECODES) & (command_bits & ~(PCI_COMMAND_IO|PCI_COMMAND_MEMORY)));
+
+	/* ARCH specific VGA enables */
+	rc = pci_set_vga_state_arch(dev, decode, command_bits, flags);
+	if (rc)
+		return rc;
+
+	if (flags & PCI_VGA_STATE_CHANGE_DECODES) {
+		pci_read_config_word(dev, PCI_COMMAND, &cmd);
+		if (decode == true)
+			cmd |= command_bits;
+		else
+			cmd &= ~command_bits;
+		pci_write_config_word(dev, PCI_COMMAND, cmd);
+	}
+
+	if (!(flags & PCI_VGA_STATE_CHANGE_BRIDGE))
+		return 0;
+
+	bus = dev->bus;
+	while (bus) {
+		bridge = bus->self;
+		if (bridge) {
+			pci_read_config_word(bridge, PCI_BRIDGE_CONTROL,
+					     &cmd);
+			if (decode == true)
+				cmd |= PCI_BRIDGE_CTL_VGA;
+			else
+				cmd &= ~PCI_BRIDGE_CTL_VGA;
+			pci_write_config_word(bridge, PCI_BRIDGE_CONTROL,
+					      cmd);
+		}
+		bus = bus->parent;
+	}
+	return 0;
+}
+
+#define RESOURCE_ALIGNMENT_PARAM_SIZE COMMAND_LINE_SIZE
+static char resource_alignment_param[RESOURCE_ALIGNMENT_PARAM_SIZE] = {0};
+static DEFINE_SPINLOCK(resource_alignment_lock);
+
+/**
+ * pci_specified_resource_alignment - get resource alignment specified by user.
+ * @dev: the PCI device to get
+ *
+ * RETURNS: Resource alignment if it is specified.
+ *          Zero if it is not specified.
+ */
+resource_size_t pci_specified_resource_alignment(struct pci_dev *dev)
+{
+	int seg, bus, slot, func, align_order, count;
+	resource_size_t align = 0;
+	char *p;
+
+	spin_lock(&resource_alignment_lock);
+	p = resource_alignment_param;
+	while (*p) {
+		count = 0;
+		if (sscanf(p, "%d%n", &align_order, &count) == 1 &&
+							p[count] == '@') {
+			p += count + 1;
+		} else {
+			align_order = -1;
+		}
+		if (sscanf(p, "%x:%x:%x.%x%n",
+			&seg, &bus, &slot, &func, &count) != 4) {
+			seg = 0;
+			if (sscanf(p, "%x:%x.%x%n",
+					&bus, &slot, &func, &count) != 3) {
+				/* Invalid format */
+				printk(KERN_ERR "PCI: Can't parse resource_alignment parameter: %s\n",
+					p);
+				break;
+			}
+		}
+		p += count;
+		if (seg == pci_domain_nr(dev->bus) &&
+			bus == dev->bus->number &&
+			slot == PCI_SLOT(dev->devfn) &&
+			func == PCI_FUNC(dev->devfn)) {
+			if (align_order == -1) {
+				align = PAGE_SIZE;
+			} else {
+				align = 1 << align_order;
+			}
+			/* Found */
+			break;
+		}
+		if (*p != ';' && *p != ',') {
+			/* End of param or invalid format */
+			break;
+		}
+		p++;
+	}
+	spin_unlock(&resource_alignment_lock);
+	return align;
+}
+
+/**
+ * pci_is_reassigndev - check if specified PCI is target device to reassign
+ * @dev: the PCI device to check
+ *
+ * RETURNS: non-zero for PCI device is a target device to reassign,
+ *          or zero is not.
+ */
+int pci_is_reassigndev(struct pci_dev *dev)
+{
+	return (pci_specified_resource_alignment(dev) != 0);
+}
+
+ssize_t pci_set_resource_alignment_param(const char *buf, size_t count)
+{
+	if (count > RESOURCE_ALIGNMENT_PARAM_SIZE - 1)
+		count = RESOURCE_ALIGNMENT_PARAM_SIZE - 1;
+	spin_lock(&resource_alignment_lock);
+	strncpy(resource_alignment_param, buf, count);
+	resource_alignment_param[count] = '\0';
+	spin_unlock(&resource_alignment_lock);
+	return count;
+}
+
+ssize_t pci_get_resource_alignment_param(char *buf, size_t size)
+{
+	size_t count;
+	spin_lock(&resource_alignment_lock);
+	count = snprintf(buf, size, "%s", resource_alignment_param);
+	spin_unlock(&resource_alignment_lock);
+	return count;
+}
+
+static ssize_t pci_resource_alignment_show(struct bus_type *bus, char *buf)
+{
+	return pci_get_resource_alignment_param(buf, PAGE_SIZE);
+}
+
+static ssize_t pci_resource_alignment_store(struct bus_type *bus,
+					const char *buf, size_t count)
+{
+	return pci_set_resource_alignment_param(buf, count);
+}
+
+BUS_ATTR(resource_alignment, 0644, pci_resource_alignment_show,
+					pci_resource_alignment_store);
+
+static int __init pci_resource_alignment_sysfs_init(void)
+{
+	return bus_create_file(&pci_bus_type,
+					&bus_attr_resource_alignment);
+}
+
+late_initcall(pci_resource_alignment_sysfs_init);
+
+static void __devinit pci_no_domains(void)
+{
+#ifdef CONFIG_PCI_DOMAINS
+	pci_domains_supported = 0;
+#endif
+}
+
+/**
+ * pci_ext_cfg_enabled - can we access extended PCI config space?
+ * @dev: The PCI device of the root bridge.
+ *
+ * Returns 1 if we can access PCI extended config space (offsets
+ * greater than 0xff). This is the default implementation. Architecture
+ * implementations can override this.
+ */
+int __attribute__ ((weak)) pci_ext_cfg_avail(struct pci_dev *dev)
+{
+	return 1;
+}
+
+void __weak pci_fixup_cardbus(struct pci_bus *bus)
+{
+}
+EXPORT_SYMBOL(pci_fixup_cardbus);
+
+static int __init pci_setup(char *str)
+{
+	while (str) {
+		char *k = strchr(str, ',');
+		if (k)
+			*k++ = 0;
+		if (*str && (str = pcibios_setup(str)) && *str) {
+			if (!strcmp(str, "nomsi")) {
+				pci_no_msi();
+			} else if (!strcmp(str, "noaer")) {
+				pci_no_aer();
+			} else if (!strncmp(str, "realloc", 7)) {
+				pci_realloc();
+			} else if (!strcmp(str, "nodomains")) {
+				pci_no_domains();
+			} else if (!strncmp(str, "cbiosize=", 9)) {
+				pci_cardbus_io_size = memparse(str + 9, &str);
+			} else if (!strncmp(str, "cbmemsize=", 10)) {
+				pci_cardbus_mem_size = memparse(str + 10, &str);
+			} else if (!strncmp(str, "resource_alignment=", 19)) {
+				pci_set_resource_alignment_param(str + 19,
+							strlen(str + 19));
+			} else if (!strncmp(str, "ecrc=", 5)) {
+				pcie_ecrc_get_policy(str + 5);
+			} else if (!strncmp(str, "hpiosize=", 9)) {
+				pci_hotplug_io_size = memparse(str + 9, &str);
+			} else if (!strncmp(str, "hpmemsize=", 10)) {
+				pci_hotplug_mem_size = memparse(str + 10, &str);
+			} else {
+				printk(KERN_ERR "PCI: Unknown option `%s'\n",
+						str);
+			}
+		}
+		str = k;
+	}
+	return 0;
+}
+early_param("pci", pci_setup);
+
+EXPORT_SYMBOL(pci_reenable_device);
+EXPORT_SYMBOL(pci_enable_device_io);
+EXPORT_SYMBOL(pci_enable_device_mem);
+EXPORT_SYMBOL(pci_enable_device);
+EXPORT_SYMBOL(pcim_enable_device);
+EXPORT_SYMBOL(pcim_pin_device);
+EXPORT_SYMBOL(pci_disable_device);
+EXPORT_SYMBOL(pci_find_capability);
+EXPORT_SYMBOL(pci_bus_find_capability);
+EXPORT_SYMBOL(pci_release_regions);
+EXPORT_SYMBOL(pci_request_regions);
+EXPORT_SYMBOL(pci_request_regions_exclusive);
+EXPORT_SYMBOL(pci_release_region);
+EXPORT_SYMBOL(pci_request_region);
+EXPORT_SYMBOL(pci_request_region_exclusive);
+EXPORT_SYMBOL(pci_release_selected_regions);
+EXPORT_SYMBOL(pci_request_selected_regions);
+EXPORT_SYMBOL(pci_request_selected_regions_exclusive);
+EXPORT_SYMBOL(pci_set_master);
+EXPORT_SYMBOL(pci_clear_master);
+EXPORT_SYMBOL(pci_set_mwi);
+EXPORT_SYMBOL(pci_try_set_mwi);
+EXPORT_SYMBOL(pci_clear_mwi);
+EXPORT_SYMBOL_GPL(pci_intx);
+EXPORT_SYMBOL(pci_assign_resource);
+EXPORT_SYMBOL(pci_find_parent_resource);
+EXPORT_SYMBOL(pci_select_bars);
+
+EXPORT_SYMBOL(pci_set_power_state);
+EXPORT_SYMBOL(pci_save_state);
+EXPORT_SYMBOL(pci_restore_state);
+EXPORT_SYMBOL(pci_pme_capable);
+EXPORT_SYMBOL(pci_pme_active);
+EXPORT_SYMBOL(pci_wake_from_d3);
+EXPORT_SYMBOL(pci_target_state);
+EXPORT_SYMBOL(pci_prepare_to_sleep);
+EXPORT_SYMBOL(pci_back_from_sleep);
+EXPORT_SYMBOL_GPL(pci_set_pcie_reset_state);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
new file mode 100644
index 00000000..3a39bf1f
--- /dev/null
+++ b/drivers/pci/pci.h
@@ -0,0 +1,317 @@
+#ifndef DRIVERS_PCI_H
+#define DRIVERS_PCI_H
+
+#include <linux/workqueue.h>
+
+#define PCI_CFG_SPACE_SIZE	256
+#define PCI_CFG_SPACE_EXP_SIZE	4096
+
+/* Functions internal to the PCI core code */
+
+extern int pci_uevent(struct device *dev, struct kobj_uevent_env *env);
+extern int pci_create_sysfs_dev_files(struct pci_dev *pdev);
+extern void pci_remove_sysfs_dev_files(struct pci_dev *pdev);
+#if !defined(CONFIG_DMI) && !defined(CONFIG_ACPI)
+static inline void pci_create_firmware_label_files(struct pci_dev *pdev)
+{ return; }
+static inline void pci_remove_firmware_label_files(struct pci_dev *pdev)
+{ return; }
+#else
+extern void pci_create_firmware_label_files(struct pci_dev *pdev);
+extern void pci_remove_firmware_label_files(struct pci_dev *pdev);
+#endif
+extern void pci_cleanup_rom(struct pci_dev *dev);
+#ifdef HAVE_PCI_MMAP
+enum pci_mmap_api {
+	PCI_MMAP_SYSFS,	/* mmap on /sys/bus/pci/devices/<BDF>/resource<N> */
+	PCI_MMAP_PROCFS	/* mmap on /proc/bus/pci/<BDF> */
+};
+extern int pci_mmap_fits(struct pci_dev *pdev, int resno,
+			 struct vm_area_struct *vmai,
+			 enum pci_mmap_api mmap_api);
+#endif
+int pci_probe_reset_function(struct pci_dev *dev);
+
+/**
+ * struct pci_platform_pm_ops - Firmware PM callbacks
+ *
+ * @is_manageable: returns 'true' if given device is power manageable by the
+ *                 platform firmware
+ *
+ * @set_state: invokes the platform firmware to set the device's power state
+ *
+ * @choose_state: returns PCI power state of given device preferred by the
+ *                platform; to be used during system-wide transitions from a
+ *                sleeping state to the working state and vice versa
+ *
+ * @can_wakeup: returns 'true' if given device is capable of waking up the
+ *              system from a sleeping state
+ *
+ * @sleep_wake: enables/disables the system wake up capability of given device
+ *
+ * @run_wake: enables/disables the platform to generate run-time wake-up events
+ *		for given device (the device's wake-up capability has to be
+ *		enabled by @sleep_wake for this feature to work)
+ *
+ * If given platform is generally capable of power managing PCI devices, all of
+ * these callbacks are mandatory.
+ */
+struct pci_platform_pm_ops {
+	bool (*is_manageable)(struct pci_dev *dev);
+	int (*set_state)(struct pci_dev *dev, pci_power_t state);
+	pci_power_t (*choose_state)(struct pci_dev *dev);
+	bool (*can_wakeup)(struct pci_dev *dev);
+	int (*sleep_wake)(struct pci_dev *dev, bool enable);
+	int (*run_wake)(struct pci_dev *dev, bool enable);
+};
+
+extern int pci_set_platform_pm(struct pci_platform_pm_ops *ops);
+extern void pci_update_current_state(struct pci_dev *dev, pci_power_t state);
+extern void pci_disable_enabled_device(struct pci_dev *dev);
+extern int pci_finish_runtime_suspend(struct pci_dev *dev);
+extern int __pci_pme_wakeup(struct pci_dev *dev, void *ign);
+extern void pci_pm_init(struct pci_dev *dev);
+extern void platform_pci_wakeup_init(struct pci_dev *dev);
+extern void pci_allocate_cap_save_buffers(struct pci_dev *dev);
+
+static inline void pci_wakeup_event(struct pci_dev *dev)
+{
+	/* Wait 100 ms before the system can be put into a sleep state. */
+	pm_wakeup_event(&dev->dev, 100);
+}
+
+static inline bool pci_is_bridge(struct pci_dev *pci_dev)
+{
+	return !!(pci_dev->subordinate);
+}
+
+extern int pci_user_read_config_byte(struct pci_dev *dev, int where, u8 *val);
+extern int pci_user_read_config_word(struct pci_dev *dev, int where, u16 *val);
+extern int pci_user_read_config_dword(struct pci_dev *dev, int where, u32 *val);
+extern int pci_user_write_config_byte(struct pci_dev *dev, int where, u8 val);
+extern int pci_user_write_config_word(struct pci_dev *dev, int where, u16 val);
+extern int pci_user_write_config_dword(struct pci_dev *dev, int where, u32 val);
+
+struct pci_vpd_ops {
+	ssize_t (*read)(struct pci_dev *dev, loff_t pos, size_t count, void *buf);
+	ssize_t (*write)(struct pci_dev *dev, loff_t pos, size_t count, const void *buf);
+	void (*release)(struct pci_dev *dev);
+};
+
+struct pci_vpd {
+	unsigned int len;
+	const struct pci_vpd_ops *ops;
+	struct bin_attribute *attr; /* descriptor for sysfs VPD entry */
+};
+
+extern int pci_vpd_pci22_init(struct pci_dev *dev);
+static inline void pci_vpd_release(struct pci_dev *dev)
+{
+	if (dev->vpd)
+		dev->vpd->ops->release(dev);
+}
+
+/* PCI /proc functions */
+#ifdef CONFIG_PROC_FS
+extern int pci_proc_attach_device(struct pci_dev *dev);
+extern int pci_proc_detach_device(struct pci_dev *dev);
+extern int pci_proc_detach_bus(struct pci_bus *bus);
+#else
+static inline int pci_proc_attach_device(struct pci_dev *dev) { return 0; }
+static inline int pci_proc_detach_device(struct pci_dev *dev) { return 0; }
+static inline int pci_proc_detach_bus(struct pci_bus *bus) { return 0; }
+#endif
+
+/* Functions for PCI Hotplug drivers to use */
+extern unsigned int pci_do_scan_bus(struct pci_bus *bus);
+
+#ifdef HAVE_PCI_LEGACY
+extern void pci_create_legacy_files(struct pci_bus *bus);
+extern void pci_remove_legacy_files(struct pci_bus *bus);
+#else
+static inline void pci_create_legacy_files(struct pci_bus *bus) { return; }
+static inline void pci_remove_legacy_files(struct pci_bus *bus) { return; }
+#endif
+
+/* Lock for read/write access to pci device and bus lists */
+extern struct rw_semaphore pci_bus_sem;
+
+extern unsigned int pci_pm_d3_delay;
+
+#ifdef CONFIG_PCI_MSI
+void pci_no_msi(void);
+extern void pci_msi_init_pci_dev(struct pci_dev *dev);
+#else
+static inline void pci_no_msi(void) { }
+static inline void pci_msi_init_pci_dev(struct pci_dev *dev) { }
+#endif
+
+extern void pci_realloc(void);
+
+static inline int pci_no_d1d2(struct pci_dev *dev)
+{
+	unsigned int parent_dstates = 0;
+
+	if (dev->bus->self)
+		parent_dstates = dev->bus->self->no_d1d2;
+	return (dev->no_d1d2 || parent_dstates);
+
+}
+extern struct device_attribute pci_dev_attrs[];
+extern struct device_attribute pcibus_dev_attrs[];
+#ifdef CONFIG_HOTPLUG
+extern struct bus_attribute pci_bus_attrs[];
+#else
+#define pci_bus_attrs	NULL
+#endif
+
+
+/**
+ * pci_match_one_device - Tell if a PCI device structure has a matching
+ *                        PCI device id structure
+ * @id: single PCI device id structure to match
+ * @dev: the PCI device structure to match against
+ *
+ * Returns the matching pci_device_id structure or %NULL if there is no match.
+ */
+static inline const struct pci_device_id *
+pci_match_one_device(const struct pci_device_id *id, const struct pci_dev *dev)
+{
+	if ((id->vendor == PCI_ANY_ID || id->vendor == dev->vendor) &&
+	    (id->device == PCI_ANY_ID || id->device == dev->device) &&
+	    (id->subvendor == PCI_ANY_ID || id->subvendor == dev->subsystem_vendor) &&
+	    (id->subdevice == PCI_ANY_ID || id->subdevice == dev->subsystem_device) &&
+	    !((id->class ^ dev->class) & id->class_mask))
+		return id;
+	return NULL;
+}
+
+struct pci_dev *pci_find_upstream_pcie_bridge(struct pci_dev *pdev);
+
+/* PCI slot sysfs helper code */
+#define to_pci_slot(s) container_of(s, struct pci_slot, kobj)
+
+extern struct kset *pci_slots_kset;
+
+struct pci_slot_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct pci_slot *, char *);
+	ssize_t (*store)(struct pci_slot *, const char *, size_t);
+};
+#define to_pci_slot_attr(s) container_of(s, struct pci_slot_attribute, attr)
+
+enum pci_bar_type {
+	pci_bar_unknown,	/* Standard PCI BAR probe */
+	pci_bar_io,		/* An io port BAR */
+	pci_bar_mem32,		/* A 32-bit memory BAR */
+	pci_bar_mem64,		/* A 64-bit memory BAR */
+};
+
+extern int pci_setup_device(struct pci_dev *dev);
+extern int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
+				struct resource *res, unsigned int reg);
+extern int pci_resource_bar(struct pci_dev *dev, int resno,
+			    enum pci_bar_type *type);
+extern int pci_bus_add_child(struct pci_bus *bus);
+extern void pci_enable_ari(struct pci_dev *dev);
+/**
+ * pci_ari_enabled - query ARI forwarding status
+ * @bus: the PCI bus
+ *
+ * Returns 1 if ARI forwarding is enabled, or 0 if not enabled;
+ */
+static inline int pci_ari_enabled(struct pci_bus *bus)
+{
+	return bus->self && bus->self->ari_enabled;
+}
+
+#ifdef CONFIG_PCI_QUIRKS
+extern int pci_is_reassigndev(struct pci_dev *dev);
+resource_size_t pci_specified_resource_alignment(struct pci_dev *dev);
+extern void pci_disable_bridge_window(struct pci_dev *dev);
+#endif
+
+/* Single Root I/O Virtualization */
+struct pci_sriov {
+	int pos;		/* capability position */
+	int nres;		/* number of resources */
+	u32 cap;		/* SR-IOV Capabilities */
+	u16 ctrl;		/* SR-IOV Control */
+	u16 total;		/* total VFs associated with the PF */
+	u16 initial;		/* initial VFs associated with the PF */
+	u16 nr_virtfn;		/* number of VFs available */
+	u16 offset;		/* first VF Routing ID offset */
+	u16 stride;		/* following VF stride */
+	u32 pgsz;		/* page size for BAR alignment */
+	u8 link;		/* Function Dependency Link */
+	struct pci_dev *dev;	/* lowest numbered PF */
+	struct pci_dev *self;	/* this PF */
+	struct mutex lock;	/* lock for VF bus */
+	struct work_struct mtask; /* VF Migration task */
+	u8 __iomem *mstate;	/* VF Migration State Array */
+};
+
+#ifdef CONFIG_PCI_IOV
+extern int pci_iov_init(struct pci_dev *dev);
+extern void pci_iov_release(struct pci_dev *dev);
+extern int pci_iov_resource_bar(struct pci_dev *dev, int resno,
+				enum pci_bar_type *type);
+extern resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev,
+						    int resno);
+extern void pci_restore_iov_state(struct pci_dev *dev);
+extern int pci_iov_bus_range(struct pci_bus *bus);
+
+#else
+static inline int pci_iov_init(struct pci_dev *dev)
+{
+	return -ENODEV;
+}
+static inline void pci_iov_release(struct pci_dev *dev)
+
+{
+}
+static inline int pci_iov_resource_bar(struct pci_dev *dev, int resno,
+				       enum pci_bar_type *type)
+{
+	return 0;
+}
+static inline void pci_restore_iov_state(struct pci_dev *dev)
+{
+}
+static inline int pci_iov_bus_range(struct pci_bus *bus)
+{
+	return 0;
+}
+
+#endif /* CONFIG_PCI_IOV */
+
+static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,
+					 struct resource *res)
+{
+#ifdef CONFIG_PCI_IOV
+	int resno = res - dev->resource;
+
+	if (resno >= PCI_IOV_RESOURCES && resno <= PCI_IOV_RESOURCE_END)
+		return pci_sriov_resource_alignment(dev, resno);
+#endif
+	return resource_alignment(res);
+}
+
+extern void pci_enable_acs(struct pci_dev *dev);
+
+struct pci_dev_reset_methods {
+	u16 vendor;
+	u16 device;
+	int (*reset)(struct pci_dev *dev, int probe);
+};
+
+#ifdef CONFIG_PCI_QUIRKS
+extern int pci_dev_specific_reset(struct pci_dev *dev, int probe);
+#else
+static inline int pci_dev_specific_reset(struct pci_dev *dev, int probe)
+{
+	return -ENOTTY;
+}
+#endif
+
+#endif /* DRIVERS_PCI_H */
diff --git a/drivers/pci/pcie/Kconfig b/drivers/pci/pcie/Kconfig
new file mode 100644
index 00000000..dc293482
--- /dev/null
+++ b/drivers/pci/pcie/Kconfig
@@ -0,0 +1,60 @@
+#
+# PCI Express Port Bus Configuration
+#
+config PCIEPORTBUS
+	bool "PCI Express support"
+	depends on PCI
+	help
+	  This automatically enables PCI Express Port Bus support. Users can
+	  choose Native Hot-Plug support, Advanced Error Reporting support,
+	  Power Management Event support and Virtual Channel support to run
+	  on PCI Express Ports (Root or Switch).
+
+#
+# Include service Kconfig here
+#
+config HOTPLUG_PCI_PCIE
+	tristate "PCI Express Hotplug driver"
+	depends on HOTPLUG_PCI && PCIEPORTBUS
+	help
+	  Say Y here if you have a motherboard that supports PCI Express Native
+	  Hotplug
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called pciehp.
+
+	  When in doubt, say N.
+
+source "drivers/pci/pcie/aer/Kconfig"
+
+#
+# PCI Express ASPM
+#
+config PCIEASPM
+	bool "PCI Express ASPM control" if EXPERT
+	depends on PCI && PCIEPORTBUS
+	default y
+	help
+	  This enables OS control over PCI Express ASPM (Active State
+	  Power Management) and Clock Power Management. ASPM supports
+	  state L0/L0s/L1.
+
+	  ASPM is initially set up the the firmware. With this option enabled,
+	  Linux can modify this state in order to disable ASPM on known-bad
+	  hardware or configurations and enable it when known-safe.
+
+	  ASPM can be disabled or enabled at runtime via
+	  /sys/module/pcie_aspm/parameters/policy
+
+	  When in doubt, say Y.
+config PCIEASPM_DEBUG
+	bool "Debug PCI Express ASPM"
+	depends on PCIEASPM
+	default n
+	help
+	  This enables PCI Express ASPM debug support. It will add per-device
+	  interface to control ASPM.
+
+config PCIE_PME
+	def_bool y
+	depends on PCIEPORTBUS && PM_RUNTIME && EXPERIMENTAL && ACPI
diff --git a/drivers/pci/pcie/Makefile b/drivers/pci/pcie/Makefile
new file mode 100644
index 00000000..00c62df5
--- /dev/null
+++ b/drivers/pci/pcie/Makefile
@@ -0,0 +1,16 @@
+#
+# Makefile for PCI-Express PORT Driver
+#
+
+# Build PCI Express ASPM if needed
+obj-$(CONFIG_PCIEASPM)		+= aspm.o
+
+pcieportdrv-y			:= portdrv_core.o portdrv_pci.o portdrv_bus.o
+pcieportdrv-$(CONFIG_ACPI)	+= portdrv_acpi.o
+
+obj-$(CONFIG_PCIEPORTBUS)	+= pcieportdrv.o
+
+# Build PCI Express AER if needed
+obj-$(CONFIG_PCIEAER)		+= aer/
+
+obj-$(CONFIG_PCIE_PME) += pme.o
diff --git a/drivers/pci/pcie/aer/Kconfig b/drivers/pci/pcie/aer/Kconfig
new file mode 100644
index 00000000..50e94e02
--- /dev/null
+++ b/drivers/pci/pcie/aer/Kconfig
@@ -0,0 +1,27 @@
+#
+# PCI Express Root Port Device AER Configuration
+#
+
+config PCIEAER
+	boolean "Root Port Advanced Error Reporting support"
+	depends on PCIEPORTBUS
+	default y
+	help
+	  This enables PCI Express Root Port Advanced Error Reporting
+	  (AER) driver support. Error reporting messages sent to Root
+	  Port will be handled by PCI Express AER driver.
+
+
+#
+# PCI Express ECRC
+#
+config PCIE_ECRC
+	bool "PCI Express ECRC settings control"
+	depends on PCIEAER
+	help
+	  Used to override firmware/bios settings for PCI Express ECRC
+	  (transaction layer end-to-end CRC checking).
+
+	  When in doubt, say N.
+
+source "drivers/pci/pcie/aer/Kconfig.debug"
diff --git a/drivers/pci/pcie/aer/Kconfig.debug b/drivers/pci/pcie/aer/Kconfig.debug
new file mode 100644
index 00000000..91429497
--- /dev/null
+++ b/drivers/pci/pcie/aer/Kconfig.debug
@@ -0,0 +1,18 @@
+#
+# PCI Express Root Port Device AER Debug Configuration
+#
+
+config PCIEAER_INJECT
+	tristate "PCIe AER error injector support"
+	depends on PCIEAER
+	default n
+	help
+	  This enables PCI Express Root Port Advanced Error Reporting
+	  (AER) software error injector.
+
+	  Debugging PCIe AER code is quite difficult because it is hard
+	  to trigger various real hardware errors. Software based
+	  error injection can fake almost all kinds of errors with the
+	  help of a user space helper tool aer-inject, which can be
+	  gotten from:
+	     http://www.kernel.org/pub/linux/utils/pci/aer-inject/
diff --git a/drivers/pci/pcie/aer/Makefile b/drivers/pci/pcie/aer/Makefile
new file mode 100644
index 00000000..2cba6751
--- /dev/null
+++ b/drivers/pci/pcie/aer/Makefile
@@ -0,0 +1,12 @@
+#
+# Makefile for PCI-Express Root Port Advanced Error Reporting Driver
+#
+
+obj-$(CONFIG_PCIEAER) += aerdriver.o
+
+obj-$(CONFIG_PCIE_ECRC)	+= ecrc.o
+
+aerdriver-objs := aerdrv_errprint.o aerdrv_core.o aerdrv.o
+aerdriver-$(CONFIG_ACPI) += aerdrv_acpi.o
+
+obj-$(CONFIG_PCIEAER_INJECT) += aer_inject.o
diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c
new file mode 100644
index 00000000..95489cd9
--- /dev/null
+++ b/drivers/pci/pcie/aer/aer_inject.c
@@ -0,0 +1,539 @@
+/*
+ * PCIe AER software error injection support.
+ *
+ * Debuging PCIe AER code is quite difficult because it is hard to
+ * trigger various real hardware errors. Software based error
+ * injection can fake almost all kinds of errors with the help of a
+ * user space helper tool aer-inject, which can be gotten from:
+ *   http://www.kernel.org/pub/linux/utils/pci/aer-inject/
+ *
+ * Copyright 2009 Intel Corporation.
+ *     Huang Ying <ying.huang@intel.com>
+ *
+ * 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; version 2
+ * of the License.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/miscdevice.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+#include <linux/stddef.h>
+#include "aerdrv.h"
+
+/* Override the existing corrected and uncorrected error masks */
+static int aer_mask_override;
+module_param(aer_mask_override, bool, 0);
+
+struct aer_error_inj {
+	u8 bus;
+	u8 dev;
+	u8 fn;
+	u32 uncor_status;
+	u32 cor_status;
+	u32 header_log0;
+	u32 header_log1;
+	u32 header_log2;
+	u32 header_log3;
+	u16 domain;
+};
+
+struct aer_error {
+	struct list_head list;
+	u16 domain;
+	unsigned int bus;
+	unsigned int devfn;
+	int pos_cap_err;
+
+	u32 uncor_status;
+	u32 cor_status;
+	u32 header_log0;
+	u32 header_log1;
+	u32 header_log2;
+	u32 header_log3;
+	u32 root_status;
+	u32 source_id;
+};
+
+struct pci_bus_ops {
+	struct list_head list;
+	struct pci_bus *bus;
+	struct pci_ops *ops;
+};
+
+static LIST_HEAD(einjected);
+
+static LIST_HEAD(pci_bus_ops_list);
+
+/* Protect einjected and pci_bus_ops_list */
+static DEFINE_SPINLOCK(inject_lock);
+
+static void aer_error_init(struct aer_error *err, u16 domain,
+			   unsigned int bus, unsigned int devfn,
+			   int pos_cap_err)
+{
+	INIT_LIST_HEAD(&err->list);
+	err->domain = domain;
+	err->bus = bus;
+	err->devfn = devfn;
+	err->pos_cap_err = pos_cap_err;
+}
+
+/* inject_lock must be held before calling */
+static struct aer_error *__find_aer_error(u16 domain, unsigned int bus,
+					  unsigned int devfn)
+{
+	struct aer_error *err;
+
+	list_for_each_entry(err, &einjected, list) {
+		if (domain == err->domain &&
+		    bus == err->bus &&
+		    devfn == err->devfn)
+			return err;
+	}
+	return NULL;
+}
+
+/* inject_lock must be held before calling */
+static struct aer_error *__find_aer_error_by_dev(struct pci_dev *dev)
+{
+	int domain = pci_domain_nr(dev->bus);
+	if (domain < 0)
+		return NULL;
+	return __find_aer_error((u16)domain, dev->bus->number, dev->devfn);
+}
+
+/* inject_lock must be held before calling */
+static struct pci_ops *__find_pci_bus_ops(struct pci_bus *bus)
+{
+	struct pci_bus_ops *bus_ops;
+
+	list_for_each_entry(bus_ops, &pci_bus_ops_list, list) {
+		if (bus_ops->bus == bus)
+			return bus_ops->ops;
+	}
+	return NULL;
+}
+
+static struct pci_bus_ops *pci_bus_ops_pop(void)
+{
+	unsigned long flags;
+	struct pci_bus_ops *bus_ops = NULL;
+
+	spin_lock_irqsave(&inject_lock, flags);
+	if (list_empty(&pci_bus_ops_list))
+		bus_ops = NULL;
+	else {
+		struct list_head *lh = pci_bus_ops_list.next;
+		list_del(lh);
+		bus_ops = list_entry(lh, struct pci_bus_ops, list);
+	}
+	spin_unlock_irqrestore(&inject_lock, flags);
+	return bus_ops;
+}
+
+static u32 *find_pci_config_dword(struct aer_error *err, int where,
+				  int *prw1cs)
+{
+	int rw1cs = 0;
+	u32 *target = NULL;
+
+	if (err->pos_cap_err == -1)
+		return NULL;
+
+	switch (where - err->pos_cap_err) {
+	case PCI_ERR_UNCOR_STATUS:
+		target = &err->uncor_status;
+		rw1cs = 1;
+		break;
+	case PCI_ERR_COR_STATUS:
+		target = &err->cor_status;
+		rw1cs = 1;
+		break;
+	case PCI_ERR_HEADER_LOG:
+		target = &err->header_log0;
+		break;
+	case PCI_ERR_HEADER_LOG+4:
+		target = &err->header_log1;
+		break;
+	case PCI_ERR_HEADER_LOG+8:
+		target = &err->header_log2;
+		break;
+	case PCI_ERR_HEADER_LOG+12:
+		target = &err->header_log3;
+		break;
+	case PCI_ERR_ROOT_STATUS:
+		target = &err->root_status;
+		rw1cs = 1;
+		break;
+	case PCI_ERR_ROOT_ERR_SRC:
+		target = &err->source_id;
+		break;
+	}
+	if (prw1cs)
+		*prw1cs = rw1cs;
+	return target;
+}
+
+static int pci_read_aer(struct pci_bus *bus, unsigned int devfn, int where,
+			int size, u32 *val)
+{
+	u32 *sim;
+	struct aer_error *err;
+	unsigned long flags;
+	struct pci_ops *ops;
+	int domain;
+
+	spin_lock_irqsave(&inject_lock, flags);
+	if (size != sizeof(u32))
+		goto out;
+	domain = pci_domain_nr(bus);
+	if (domain < 0)
+		goto out;
+	err = __find_aer_error((u16)domain, bus->number, devfn);
+	if (!err)
+		goto out;
+
+	sim = find_pci_config_dword(err, where, NULL);
+	if (sim) {
+		*val = *sim;
+		spin_unlock_irqrestore(&inject_lock, flags);
+		return 0;
+	}
+out:
+	ops = __find_pci_bus_ops(bus);
+	spin_unlock_irqrestore(&inject_lock, flags);
+	return ops->read(bus, devfn, where, size, val);
+}
+
+int pci_write_aer(struct pci_bus *bus, unsigned int devfn, int where, int size,
+		  u32 val)
+{
+	u32 *sim;
+	struct aer_error *err;
+	unsigned long flags;
+	int rw1cs;
+	struct pci_ops *ops;
+	int domain;
+
+	spin_lock_irqsave(&inject_lock, flags);
+	if (size != sizeof(u32))
+		goto out;
+	domain = pci_domain_nr(bus);
+	if (domain < 0)
+		goto out;
+	err = __find_aer_error((u16)domain, bus->number, devfn);
+	if (!err)
+		goto out;
+
+	sim = find_pci_config_dword(err, where, &rw1cs);
+	if (sim) {
+		if (rw1cs)
+			*sim ^= val;
+		else
+			*sim = val;
+		spin_unlock_irqrestore(&inject_lock, flags);
+		return 0;
+	}
+out:
+	ops = __find_pci_bus_ops(bus);
+	spin_unlock_irqrestore(&inject_lock, flags);
+	return ops->write(bus, devfn, where, size, val);
+}
+
+static struct pci_ops pci_ops_aer = {
+	.read = pci_read_aer,
+	.write = pci_write_aer,
+};
+
+static void pci_bus_ops_init(struct pci_bus_ops *bus_ops,
+			     struct pci_bus *bus,
+			     struct pci_ops *ops)
+{
+	INIT_LIST_HEAD(&bus_ops->list);
+	bus_ops->bus = bus;
+	bus_ops->ops = ops;
+}
+
+static int pci_bus_set_aer_ops(struct pci_bus *bus)
+{
+	struct pci_ops *ops;
+	struct pci_bus_ops *bus_ops;
+	unsigned long flags;
+
+	bus_ops = kmalloc(sizeof(*bus_ops), GFP_KERNEL);
+	if (!bus_ops)
+		return -ENOMEM;
+	ops = pci_bus_set_ops(bus, &pci_ops_aer);
+	spin_lock_irqsave(&inject_lock, flags);
+	if (ops == &pci_ops_aer)
+		goto out;
+	pci_bus_ops_init(bus_ops, bus, ops);
+	list_add(&bus_ops->list, &pci_bus_ops_list);
+	bus_ops = NULL;
+out:
+	spin_unlock_irqrestore(&inject_lock, flags);
+	kfree(bus_ops);
+	return 0;
+}
+
+static struct pci_dev *pcie_find_root_port(struct pci_dev *dev)
+{
+	while (1) {
+		if (!pci_is_pcie(dev))
+			break;
+		if (dev->pcie_type == PCI_EXP_TYPE_ROOT_PORT)
+			return dev;
+		if (!dev->bus->self)
+			break;
+		dev = dev->bus->self;
+	}
+	return NULL;
+}
+
+static int find_aer_device_iter(struct device *device, void *data)
+{
+	struct pcie_device **result = data;
+	struct pcie_device *pcie_dev;
+
+	if (device->bus == &pcie_port_bus_type) {
+		pcie_dev = to_pcie_device(device);
+		if (pcie_dev->service & PCIE_PORT_SERVICE_AER) {
+			*result = pcie_dev;
+			return 1;
+		}
+	}
+	return 0;
+}
+
+static int find_aer_device(struct pci_dev *dev, struct pcie_device **result)
+{
+	return device_for_each_child(&dev->dev, result, find_aer_device_iter);
+}
+
+static int aer_inject(struct aer_error_inj *einj)
+{
+	struct aer_error *err, *rperr;
+	struct aer_error *err_alloc = NULL, *rperr_alloc = NULL;
+	struct pci_dev *dev, *rpdev;
+	struct pcie_device *edev;
+	unsigned long flags;
+	unsigned int devfn = PCI_DEVFN(einj->dev, einj->fn);
+	int pos_cap_err, rp_pos_cap_err;
+	u32 sever, cor_mask, uncor_mask, cor_mask_orig = 0, uncor_mask_orig = 0;
+	int ret = 0;
+
+	dev = pci_get_domain_bus_and_slot((int)einj->domain, einj->bus, devfn);
+	if (!dev)
+		return -ENODEV;
+	rpdev = pcie_find_root_port(dev);
+	if (!rpdev) {
+		ret = -ENOTTY;
+		goto out_put;
+	}
+
+	pos_cap_err = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	if (!pos_cap_err) {
+		ret = -ENOTTY;
+		goto out_put;
+	}
+	pci_read_config_dword(dev, pos_cap_err + PCI_ERR_UNCOR_SEVER, &sever);
+	pci_read_config_dword(dev, pos_cap_err + PCI_ERR_COR_MASK, &cor_mask);
+	pci_read_config_dword(dev, pos_cap_err + PCI_ERR_UNCOR_MASK,
+			      &uncor_mask);
+
+	rp_pos_cap_err = pci_find_ext_capability(rpdev, PCI_EXT_CAP_ID_ERR);
+	if (!rp_pos_cap_err) {
+		ret = -ENOTTY;
+		goto out_put;
+	}
+
+	err_alloc =  kzalloc(sizeof(struct aer_error), GFP_KERNEL);
+	if (!err_alloc) {
+		ret = -ENOMEM;
+		goto out_put;
+	}
+	rperr_alloc =  kzalloc(sizeof(struct aer_error), GFP_KERNEL);
+	if (!rperr_alloc) {
+		ret = -ENOMEM;
+		goto out_put;
+	}
+
+	if (aer_mask_override) {
+		cor_mask_orig = cor_mask;
+		cor_mask &= !(einj->cor_status);
+		pci_write_config_dword(dev, pos_cap_err + PCI_ERR_COR_MASK,
+				       cor_mask);
+
+		uncor_mask_orig = uncor_mask;
+		uncor_mask &= !(einj->uncor_status);
+		pci_write_config_dword(dev, pos_cap_err + PCI_ERR_UNCOR_MASK,
+				       uncor_mask);
+	}
+
+	spin_lock_irqsave(&inject_lock, flags);
+
+	err = __find_aer_error_by_dev(dev);
+	if (!err) {
+		err = err_alloc;
+		err_alloc = NULL;
+		aer_error_init(err, einj->domain, einj->bus, devfn,
+			       pos_cap_err);
+		list_add(&err->list, &einjected);
+	}
+	err->uncor_status |= einj->uncor_status;
+	err->cor_status |= einj->cor_status;
+	err->header_log0 = einj->header_log0;
+	err->header_log1 = einj->header_log1;
+	err->header_log2 = einj->header_log2;
+	err->header_log3 = einj->header_log3;
+
+	if (!aer_mask_override && einj->cor_status &&
+	    !(einj->cor_status & ~cor_mask)) {
+		ret = -EINVAL;
+		printk(KERN_WARNING "The correctable error(s) is masked "
+				"by device\n");
+		spin_unlock_irqrestore(&inject_lock, flags);
+		goto out_put;
+	}
+	if (!aer_mask_override && einj->uncor_status &&
+	    !(einj->uncor_status & ~uncor_mask)) {
+		ret = -EINVAL;
+		printk(KERN_WARNING "The uncorrectable error(s) is masked "
+				"by device\n");
+		spin_unlock_irqrestore(&inject_lock, flags);
+		goto out_put;
+	}
+
+	rperr = __find_aer_error_by_dev(rpdev);
+	if (!rperr) {
+		rperr = rperr_alloc;
+		rperr_alloc = NULL;
+		aer_error_init(rperr, pci_domain_nr(rpdev->bus),
+			       rpdev->bus->number, rpdev->devfn,
+			       rp_pos_cap_err);
+		list_add(&rperr->list, &einjected);
+	}
+	if (einj->cor_status) {
+		if (rperr->root_status & PCI_ERR_ROOT_COR_RCV)
+			rperr->root_status |= PCI_ERR_ROOT_MULTI_COR_RCV;
+		else
+			rperr->root_status |= PCI_ERR_ROOT_COR_RCV;
+		rperr->source_id &= 0xffff0000;
+		rperr->source_id |= (einj->bus << 8) | devfn;
+	}
+	if (einj->uncor_status) {
+		if (rperr->root_status & PCI_ERR_ROOT_UNCOR_RCV)
+			rperr->root_status |= PCI_ERR_ROOT_MULTI_UNCOR_RCV;
+		if (sever & einj->uncor_status) {
+			rperr->root_status |= PCI_ERR_ROOT_FATAL_RCV;
+			if (!(rperr->root_status & PCI_ERR_ROOT_UNCOR_RCV))
+				rperr->root_status |= PCI_ERR_ROOT_FIRST_FATAL;
+		} else
+			rperr->root_status |= PCI_ERR_ROOT_NONFATAL_RCV;
+		rperr->root_status |= PCI_ERR_ROOT_UNCOR_RCV;
+		rperr->source_id &= 0x0000ffff;
+		rperr->source_id |= ((einj->bus << 8) | devfn) << 16;
+	}
+	spin_unlock_irqrestore(&inject_lock, flags);
+
+	if (aer_mask_override) {
+		pci_write_config_dword(dev, pos_cap_err + PCI_ERR_COR_MASK,
+				       cor_mask_orig);
+		pci_write_config_dword(dev, pos_cap_err + PCI_ERR_UNCOR_MASK,
+				       uncor_mask_orig);
+	}
+
+	ret = pci_bus_set_aer_ops(dev->bus);
+	if (ret)
+		goto out_put;
+	ret = pci_bus_set_aer_ops(rpdev->bus);
+	if (ret)
+		goto out_put;
+
+	if (find_aer_device(rpdev, &edev)) {
+		if (!get_service_data(edev)) {
+			printk(KERN_WARNING "AER service is not initialized\n");
+			ret = -EINVAL;
+			goto out_put;
+		}
+		aer_irq(-1, edev);
+	}
+	else
+		ret = -EINVAL;
+out_put:
+	kfree(err_alloc);
+	kfree(rperr_alloc);
+	pci_dev_put(dev);
+	return ret;
+}
+
+static ssize_t aer_inject_write(struct file *filp, const char __user *ubuf,
+				size_t usize, loff_t *off)
+{
+	struct aer_error_inj einj;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	if (usize < offsetof(struct aer_error_inj, domain) ||
+	    usize > sizeof(einj))
+		return -EINVAL;
+
+	memset(&einj, 0, sizeof(einj));
+	if (copy_from_user(&einj, ubuf, usize))
+		return -EFAULT;
+
+	ret = aer_inject(&einj);
+	return ret ? ret : usize;
+}
+
+static const struct file_operations aer_inject_fops = {
+	.write = aer_inject_write,
+	.owner = THIS_MODULE,
+	.llseek = noop_llseek,
+};
+
+static struct miscdevice aer_inject_device = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "aer_inject",
+	.fops = &aer_inject_fops,
+};
+
+static int __init aer_inject_init(void)
+{
+	return misc_register(&aer_inject_device);
+}
+
+static void __exit aer_inject_exit(void)
+{
+	struct aer_error *err, *err_next;
+	unsigned long flags;
+	struct pci_bus_ops *bus_ops;
+
+	misc_deregister(&aer_inject_device);
+
+	while ((bus_ops = pci_bus_ops_pop())) {
+		pci_bus_set_ops(bus_ops->bus, bus_ops->ops);
+		kfree(bus_ops);
+	}
+
+	spin_lock_irqsave(&inject_lock, flags);
+	list_for_each_entry_safe(err, err_next, &einjected, list) {
+		list_del(&err->list);
+		kfree(err);
+	}
+	spin_unlock_irqrestore(&inject_lock, flags);
+}
+
+module_init(aer_inject_init);
+module_exit(aer_inject_exit);
+
+MODULE_DESCRIPTION("PCIe AER software error injector");
+MODULE_LICENSE("GPL");
diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c
new file mode 100644
index 00000000..58ad7917
--- /dev/null
+++ b/drivers/pci/pcie/aer/aerdrv.c
@@ -0,0 +1,436 @@
+/*
+ * drivers/pci/pcie/aer/aerdrv.c
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * This file implements the AER root port service driver. The driver will
+ * register an irq handler. When root port triggers an AER interrupt, the irq
+ * handler will collect root port status and schedule a work.
+ *
+ * Copyright (C) 2006 Intel Corp.
+ *	Tom Long Nguyen (tom.l.nguyen@intel.com)
+ *	Zhang Yanmin (yanmin.zhang@intel.com)
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/pci-acpi.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/pm.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/pcieport_if.h>
+#include <linux/slab.h>
+
+#include "aerdrv.h"
+#include "../../pci.h"
+
+/*
+ * Version Information
+ */
+#define DRIVER_VERSION "v1.0"
+#define DRIVER_AUTHOR "tom.l.nguyen@intel.com"
+#define DRIVER_DESC "Root Port Advanced Error Reporting Driver"
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+
+static int __devinit aer_probe(struct pcie_device *dev);
+static void aer_remove(struct pcie_device *dev);
+static pci_ers_result_t aer_error_detected(struct pci_dev *dev,
+	enum pci_channel_state error);
+static void aer_error_resume(struct pci_dev *dev);
+static pci_ers_result_t aer_root_reset(struct pci_dev *dev);
+
+static struct pci_error_handlers aer_error_handlers = {
+	.error_detected = aer_error_detected,
+	.resume		= aer_error_resume,
+};
+
+static struct pcie_port_service_driver aerdriver = {
+	.name		= "aer",
+	.port_type	= PCI_EXP_TYPE_ROOT_PORT,
+	.service	= PCIE_PORT_SERVICE_AER,
+
+	.probe		= aer_probe,
+	.remove		= aer_remove,
+
+	.err_handler	= &aer_error_handlers,
+
+	.reset_link	= aer_root_reset,
+};
+
+static int pcie_aer_disable;
+
+void pci_no_aer(void)
+{
+	pcie_aer_disable = 1;	/* has priority over 'forceload' */
+}
+
+bool pci_aer_available(void)
+{
+	return !pcie_aer_disable && pci_msi_enabled();
+}
+
+static int set_device_error_reporting(struct pci_dev *dev, void *data)
+{
+	bool enable = *((bool *)data);
+
+	if ((dev->pcie_type == PCI_EXP_TYPE_ROOT_PORT) ||
+	    (dev->pcie_type == PCI_EXP_TYPE_UPSTREAM) ||
+	    (dev->pcie_type == PCI_EXP_TYPE_DOWNSTREAM)) {
+		if (enable)
+			pci_enable_pcie_error_reporting(dev);
+		else
+			pci_disable_pcie_error_reporting(dev);
+	}
+
+	if (enable)
+		pcie_set_ecrc_checking(dev);
+
+	return 0;
+}
+
+/**
+ * set_downstream_devices_error_reporting - enable/disable the error reporting  bits on the root port and its downstream ports.
+ * @dev: pointer to root port's pci_dev data structure
+ * @enable: true = enable error reporting, false = disable error reporting.
+ */
+static void set_downstream_devices_error_reporting(struct pci_dev *dev,
+						   bool enable)
+{
+	set_device_error_reporting(dev, &enable);
+
+	if (!dev->subordinate)
+		return;
+	pci_walk_bus(dev->subordinate, set_device_error_reporting, &enable);
+}
+
+/**
+ * aer_enable_rootport - enable Root Port's interrupts when receiving messages
+ * @rpc: pointer to a Root Port data structure
+ *
+ * Invoked when PCIe bus loads AER service driver.
+ */
+static void aer_enable_rootport(struct aer_rpc *rpc)
+{
+	struct pci_dev *pdev = rpc->rpd->port;
+	int pos, aer_pos;
+	u16 reg16;
+	u32 reg32;
+
+	pos = pci_pcie_cap(pdev);
+	/* Clear PCIe Capability's Device Status */
+	pci_read_config_word(pdev, pos+PCI_EXP_DEVSTA, &reg16);
+	pci_write_config_word(pdev, pos+PCI_EXP_DEVSTA, reg16);
+
+	/* Disable system error generation in response to error messages */
+	pci_read_config_word(pdev, pos + PCI_EXP_RTCTL, &reg16);
+	reg16 &= ~(SYSTEM_ERROR_INTR_ON_MESG_MASK);
+	pci_write_config_word(pdev, pos + PCI_EXP_RTCTL, reg16);
+
+	aer_pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
+	/* Clear error status */
+	pci_read_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, &reg32);
+	pci_write_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, reg32);
+	pci_read_config_dword(pdev, aer_pos + PCI_ERR_COR_STATUS, &reg32);
+	pci_write_config_dword(pdev, aer_pos + PCI_ERR_COR_STATUS, reg32);
+	pci_read_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, &reg32);
+	pci_write_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, reg32);
+
+	/*
+	 * Enable error reporting for the root port device and downstream port
+	 * devices.
+	 */
+	set_downstream_devices_error_reporting(pdev, true);
+
+	/* Enable Root Port's interrupt in response to error messages */
+	pci_read_config_dword(pdev, aer_pos + PCI_ERR_ROOT_COMMAND, &reg32);
+	reg32 |= ROOT_PORT_INTR_ON_MESG_MASK;
+	pci_write_config_dword(pdev, aer_pos + PCI_ERR_ROOT_COMMAND, reg32);
+}
+
+/**
+ * aer_disable_rootport - disable Root Port's interrupts when receiving messages
+ * @rpc: pointer to a Root Port data structure
+ *
+ * Invoked when PCIe bus unloads AER service driver.
+ */
+static void aer_disable_rootport(struct aer_rpc *rpc)
+{
+	struct pci_dev *pdev = rpc->rpd->port;
+	u32 reg32;
+	int pos;
+
+	/*
+	 * Disable error reporting for the root port device and downstream port
+	 * devices.
+	 */
+	set_downstream_devices_error_reporting(pdev, false);
+
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
+	/* Disable Root's interrupt in response to error messages */
+	pci_read_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, &reg32);
+	reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
+	pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, reg32);
+
+	/* Clear Root's error status reg */
+	pci_read_config_dword(pdev, pos + PCI_ERR_ROOT_STATUS, &reg32);
+	pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_STATUS, reg32);
+}
+
+/**
+ * aer_irq - Root Port's ISR
+ * @irq: IRQ assigned to Root Port
+ * @context: pointer to Root Port data structure
+ *
+ * Invoked when Root Port detects AER messages.
+ */
+irqreturn_t aer_irq(int irq, void *context)
+{
+	unsigned int status, id;
+	struct pcie_device *pdev = (struct pcie_device *)context;
+	struct aer_rpc *rpc = get_service_data(pdev);
+	int next_prod_idx;
+	unsigned long flags;
+	int pos;
+
+	pos = pci_find_ext_capability(pdev->port, PCI_EXT_CAP_ID_ERR);
+	/*
+	 * Must lock access to Root Error Status Reg, Root Error ID Reg,
+	 * and Root error producer/consumer index
+	 */
+	spin_lock_irqsave(&rpc->e_lock, flags);
+
+	/* Read error status */
+	pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, &status);
+	if (!(status & (PCI_ERR_ROOT_UNCOR_RCV|PCI_ERR_ROOT_COR_RCV))) {
+		spin_unlock_irqrestore(&rpc->e_lock, flags);
+		return IRQ_NONE;
+	}
+
+	/* Read error source and clear error status */
+	pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_ERR_SRC, &id);
+	pci_write_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, status);
+
+	/* Store error source for later DPC handler */
+	next_prod_idx = rpc->prod_idx + 1;
+	if (next_prod_idx == AER_ERROR_SOURCES_MAX)
+		next_prod_idx = 0;
+	if (next_prod_idx == rpc->cons_idx) {
+		/*
+		 * Error Storm Condition - possibly the same error occurred.
+		 * Drop the error.
+		 */
+		spin_unlock_irqrestore(&rpc->e_lock, flags);
+		return IRQ_HANDLED;
+	}
+	rpc->e_sources[rpc->prod_idx].status =  status;
+	rpc->e_sources[rpc->prod_idx].id = id;
+	rpc->prod_idx = next_prod_idx;
+	spin_unlock_irqrestore(&rpc->e_lock, flags);
+
+	/*  Invoke DPC handler */
+	schedule_work(&rpc->dpc_handler);
+
+	return IRQ_HANDLED;
+}
+EXPORT_SYMBOL_GPL(aer_irq);
+
+/**
+ * aer_alloc_rpc - allocate Root Port data structure
+ * @dev: pointer to the pcie_dev data structure
+ *
+ * Invoked when Root Port's AER service is loaded.
+ */
+static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev)
+{
+	struct aer_rpc *rpc;
+
+	rpc = kzalloc(sizeof(struct aer_rpc), GFP_KERNEL);
+	if (!rpc)
+		return NULL;
+
+	/* Initialize Root lock access, e_lock, to Root Error Status Reg */
+	spin_lock_init(&rpc->e_lock);
+
+	rpc->rpd = dev;
+	INIT_WORK(&rpc->dpc_handler, aer_isr);
+	mutex_init(&rpc->rpc_mutex);
+	init_waitqueue_head(&rpc->wait_release);
+
+	/* Use PCIe bus function to store rpc into PCIe device */
+	set_service_data(dev, rpc);
+
+	return rpc;
+}
+
+/**
+ * aer_remove - clean up resources
+ * @dev: pointer to the pcie_dev data structure
+ *
+ * Invoked when PCI Express bus unloads or AER probe fails.
+ */
+static void aer_remove(struct pcie_device *dev)
+{
+	struct aer_rpc *rpc = get_service_data(dev);
+
+	if (rpc) {
+		/* If register interrupt service, it must be free. */
+		if (rpc->isr)
+			free_irq(dev->irq, dev);
+
+		wait_event(rpc->wait_release, rpc->prod_idx == rpc->cons_idx);
+
+		aer_disable_rootport(rpc);
+		kfree(rpc);
+		set_service_data(dev, NULL);
+	}
+}
+
+/**
+ * aer_probe - initialize resources
+ * @dev: pointer to the pcie_dev data structure
+ * @id: pointer to the service id data structure
+ *
+ * Invoked when PCI Express bus loads AER service driver.
+ */
+static int __devinit aer_probe(struct pcie_device *dev)
+{
+	int status;
+	struct aer_rpc *rpc;
+	struct device *device = &dev->device;
+
+	/* Init */
+	status = aer_init(dev);
+	if (status)
+		return status;
+
+	/* Alloc rpc data structure */
+	rpc = aer_alloc_rpc(dev);
+	if (!rpc) {
+		dev_printk(KERN_DEBUG, device, "alloc rpc failed\n");
+		aer_remove(dev);
+		return -ENOMEM;
+	}
+
+	/* Request IRQ ISR */
+	status = request_irq(dev->irq, aer_irq, IRQF_SHARED, "aerdrv", dev);
+	if (status) {
+		dev_printk(KERN_DEBUG, device, "request IRQ failed\n");
+		aer_remove(dev);
+		return status;
+	}
+
+	rpc->isr = 1;
+
+	aer_enable_rootport(rpc);
+
+	return status;
+}
+
+/**
+ * aer_root_reset - reset link on Root Port
+ * @dev: pointer to Root Port's pci_dev data structure
+ *
+ * Invoked by Port Bus driver when performing link reset at Root Port.
+ */
+static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
+{
+	u32 reg32;
+	int pos;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+
+	/* Disable Root's interrupt in response to error messages */
+	pci_read_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, &reg32);
+	reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
+	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
+
+	aer_do_secondary_bus_reset(dev);
+	dev_printk(KERN_DEBUG, &dev->dev, "Root Port link has been reset\n");
+
+	/* Clear Root Error Status */
+	pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &reg32);
+	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, reg32);
+
+	/* Enable Root Port's interrupt in response to error messages */
+	pci_read_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, &reg32);
+	reg32 |= ROOT_PORT_INTR_ON_MESG_MASK;
+	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
+
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
+/**
+ * aer_error_detected - update severity status
+ * @dev: pointer to Root Port's pci_dev data structure
+ * @error: error severity being notified by port bus
+ *
+ * Invoked by Port Bus driver during error recovery.
+ */
+static pci_ers_result_t aer_error_detected(struct pci_dev *dev,
+			enum pci_channel_state error)
+{
+	/* Root Port has no impact. Always recovers. */
+	return PCI_ERS_RESULT_CAN_RECOVER;
+}
+
+/**
+ * aer_error_resume - clean up corresponding error status bits
+ * @dev: pointer to Root Port's pci_dev data structure
+ *
+ * Invoked by Port Bus driver during nonfatal recovery.
+ */
+static void aer_error_resume(struct pci_dev *dev)
+{
+	int pos;
+	u32 status, mask;
+	u16 reg16;
+
+	/* Clean up Root device status */
+	pos = pci_pcie_cap(dev);
+	pci_read_config_word(dev, pos + PCI_EXP_DEVSTA, &reg16);
+	pci_write_config_word(dev, pos + PCI_EXP_DEVSTA, reg16);
+
+	/* Clean AER Root Error Status */
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &mask);
+	if (dev->error_state == pci_channel_io_normal)
+		status &= ~mask; /* Clear corresponding nonfatal bits */
+	else
+		status &= mask; /* Clear corresponding fatal bits */
+	pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
+}
+
+/**
+ * aer_service_init - register AER root service driver
+ *
+ * Invoked when AER root service driver is loaded.
+ */
+static int __init aer_service_init(void)
+{
+	if (!pci_aer_available() || aer_acpi_firmware_first())
+		return -ENXIO;
+	return pcie_port_service_register(&aerdriver);
+}
+
+/**
+ * aer_service_exit - unregister AER root service driver
+ *
+ * Invoked when AER root service driver is unloaded.
+ */
+static void __exit aer_service_exit(void)
+{
+	pcie_port_service_unregister(&aerdriver);
+}
+
+module_init(aer_service_init);
+module_exit(aer_service_exit);
diff --git a/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h
new file mode 100644
index 00000000..94a7598e
--- /dev/null
+++ b/drivers/pci/pcie/aer/aerdrv.h
@@ -0,0 +1,134 @@
+/*
+ * Copyright (C) 2006 Intel Corp.
+ *	Tom Long Nguyen (tom.l.nguyen@intel.com)
+ *	Zhang Yanmin (yanmin.zhang@intel.com)
+ *
+ */
+
+#ifndef _AERDRV_H_
+#define _AERDRV_H_
+
+#include <linux/workqueue.h>
+#include <linux/pcieport_if.h>
+#include <linux/aer.h>
+#include <linux/interrupt.h>
+
+#define AER_NONFATAL			0
+#define AER_FATAL			1
+#define AER_CORRECTABLE			2
+
+#define SYSTEM_ERROR_INTR_ON_MESG_MASK	(PCI_EXP_RTCTL_SECEE|	\
+					PCI_EXP_RTCTL_SENFEE|	\
+					PCI_EXP_RTCTL_SEFEE)
+#define ROOT_PORT_INTR_ON_MESG_MASK	(PCI_ERR_ROOT_CMD_COR_EN|	\
+					PCI_ERR_ROOT_CMD_NONFATAL_EN|	\
+					PCI_ERR_ROOT_CMD_FATAL_EN)
+#define ERR_COR_ID(d)			(d & 0xffff)
+#define ERR_UNCOR_ID(d)			(d >> 16)
+
+#define AER_ERROR_SOURCES_MAX		100
+
+#define AER_LOG_TLP_MASKS		(PCI_ERR_UNC_POISON_TLP|	\
+					PCI_ERR_UNC_ECRC|		\
+					PCI_ERR_UNC_UNSUP|		\
+					PCI_ERR_UNC_COMP_ABORT|		\
+					PCI_ERR_UNC_UNX_COMP|		\
+					PCI_ERR_UNC_MALF_TLP)
+
+#define AER_MAX_MULTI_ERR_DEVICES	5	/* Not likely to have more */
+struct aer_err_info {
+	struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES];
+	int error_dev_num;
+
+	unsigned int id:16;
+
+	unsigned int severity:2;	/* 0:NONFATAL | 1:FATAL | 2:COR */
+	unsigned int __pad1:5;
+	unsigned int multi_error_valid:1;
+
+	unsigned int first_error:5;
+	unsigned int __pad2:2;
+	unsigned int tlp_header_valid:1;
+
+	unsigned int status;		/* COR/UNCOR Error Status */
+	unsigned int mask;		/* COR/UNCOR Error Mask */
+	struct aer_header_log_regs tlp;	/* TLP Header */
+};
+
+struct aer_err_source {
+	unsigned int status;
+	unsigned int id;
+};
+
+struct aer_rpc {
+	struct pcie_device *rpd;	/* Root Port device */
+	struct work_struct dpc_handler;
+	struct aer_err_source e_sources[AER_ERROR_SOURCES_MAX];
+	unsigned short prod_idx;	/* Error Producer Index */
+	unsigned short cons_idx;	/* Error Consumer Index */
+	int isr;
+	spinlock_t e_lock;		/*
+					 * Lock access to Error Status/ID Regs
+					 * and error producer/consumer index
+					 */
+	struct mutex rpc_mutex;		/*
+					 * only one thread could do
+					 * recovery on the same
+					 * root port hierarchy
+					 */
+	wait_queue_head_t wait_release;
+};
+
+struct aer_broadcast_data {
+	enum pci_channel_state state;
+	enum pci_ers_result result;
+};
+
+static inline pci_ers_result_t merge_result(enum pci_ers_result orig,
+		enum pci_ers_result new)
+{
+	if (new == PCI_ERS_RESULT_NONE)
+		return orig;
+
+	switch (orig) {
+	case PCI_ERS_RESULT_CAN_RECOVER:
+	case PCI_ERS_RESULT_RECOVERED:
+		orig = new;
+		break;
+	case PCI_ERS_RESULT_DISCONNECT:
+		if (new == PCI_ERS_RESULT_NEED_RESET)
+			orig = new;
+		break;
+	default:
+		break;
+	}
+
+	return orig;
+}
+
+extern struct bus_type pcie_port_bus_type;
+extern void aer_do_secondary_bus_reset(struct pci_dev *dev);
+extern int aer_init(struct pcie_device *dev);
+extern void aer_isr(struct work_struct *work);
+extern void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);
+extern void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info);
+extern irqreturn_t aer_irq(int irq, void *context);
+
+#ifdef CONFIG_ACPI_APEI
+extern int pcie_aer_get_firmware_first(struct pci_dev *pci_dev);
+#else
+static inline int pcie_aer_get_firmware_first(struct pci_dev *pci_dev)
+{
+	if (pci_dev->__aer_firmware_first_valid)
+		return pci_dev->__aer_firmware_first;
+	return 0;
+}
+#endif
+
+static inline void pcie_aer_force_firmware_first(struct pci_dev *pci_dev,
+						 int enable)
+{
+	pci_dev->__aer_firmware_first = !!enable;
+	pci_dev->__aer_firmware_first_valid = 1;
+}
+#endif /* _AERDRV_H_ */
diff --git a/drivers/pci/pcie/aer/aerdrv_acpi.c b/drivers/pci/pcie/aer/aerdrv_acpi.c
new file mode 100644
index 00000000..275bf158
--- /dev/null
+++ b/drivers/pci/pcie/aer/aerdrv_acpi.c
@@ -0,0 +1,130 @@
+/*
+ * Access ACPI _OSC method
+ *
+ * Copyright (C) 2006 Intel Corp.
+ *	Tom Long Nguyen (tom.l.nguyen@intel.com)
+ *	Zhang Yanmin (yanmin.zhang@intel.com)
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/pm.h>
+#include <linux/suspend.h>
+#include <linux/acpi.h>
+#include <linux/pci-acpi.h>
+#include <linux/delay.h>
+#include <acpi/apei.h>
+#include "aerdrv.h"
+
+#ifdef CONFIG_ACPI_APEI
+static inline int hest_match_pci(struct acpi_hest_aer_common *p,
+				 struct pci_dev *pci)
+{
+	return	(0           == pci_domain_nr(pci->bus) &&
+		 p->bus      == pci->bus->number &&
+		 p->device   == PCI_SLOT(pci->devfn) &&
+		 p->function == PCI_FUNC(pci->devfn));
+}
+
+struct aer_hest_parse_info {
+	struct pci_dev *pci_dev;
+	int firmware_first;
+};
+
+static int aer_hest_parse(struct acpi_hest_header *hest_hdr, void *data)
+{
+	struct aer_hest_parse_info *info = data;
+	struct acpi_hest_aer_common *p;
+	u8 pcie_type = 0;
+	u8 bridge = 0;
+	int ff = 0;
+
+	switch (hest_hdr->type) {
+	case ACPI_HEST_TYPE_AER_ROOT_PORT:
+		pcie_type = PCI_EXP_TYPE_ROOT_PORT;
+		break;
+	case ACPI_HEST_TYPE_AER_ENDPOINT:
+		pcie_type = PCI_EXP_TYPE_ENDPOINT;
+		break;
+	case ACPI_HEST_TYPE_AER_BRIDGE:
+		if ((info->pci_dev->class >> 16) == PCI_BASE_CLASS_BRIDGE)
+			bridge = 1;
+		break;
+	default:
+		return 0;
+	}
+
+	p = (struct acpi_hest_aer_common *)(hest_hdr + 1);
+	if (p->flags & ACPI_HEST_GLOBAL) {
+		if ((info->pci_dev->is_pcie &&
+		     info->pci_dev->pcie_type == pcie_type) || bridge)
+			ff = !!(p->flags & ACPI_HEST_FIRMWARE_FIRST);
+	} else
+		if (hest_match_pci(p, info->pci_dev))
+			ff = !!(p->flags & ACPI_HEST_FIRMWARE_FIRST);
+	info->firmware_first = ff;
+
+	return 0;
+}
+
+static void aer_set_firmware_first(struct pci_dev *pci_dev)
+{
+	int rc;
+	struct aer_hest_parse_info info = {
+		.pci_dev	= pci_dev,
+		.firmware_first	= 0,
+	};
+
+	rc = apei_hest_parse(aer_hest_parse, &info);
+
+	if (rc)
+		pci_dev->__aer_firmware_first = 0;
+	else
+		pci_dev->__aer_firmware_first = info.firmware_first;
+	pci_dev->__aer_firmware_first_valid = 1;
+}
+
+int pcie_aer_get_firmware_first(struct pci_dev *dev)
+{
+	if (!dev->__aer_firmware_first_valid)
+		aer_set_firmware_first(dev);
+	return dev->__aer_firmware_first;
+}
+
+static bool aer_firmware_first;
+
+static int aer_hest_parse_aff(struct acpi_hest_header *hest_hdr, void *data)
+{
+	struct acpi_hest_aer_common *p;
+
+	if (aer_firmware_first)
+		return 0;
+
+	switch (hest_hdr->type) {
+	case ACPI_HEST_TYPE_AER_ROOT_PORT:
+	case ACPI_HEST_TYPE_AER_ENDPOINT:
+	case ACPI_HEST_TYPE_AER_BRIDGE:
+		p = (struct acpi_hest_aer_common *)(hest_hdr + 1);
+		aer_firmware_first = !!(p->flags & ACPI_HEST_FIRMWARE_FIRST);
+	default:
+		return 0;
+	}
+}
+
+/**
+ * aer_acpi_firmware_first - Check if APEI should control AER.
+ */
+bool aer_acpi_firmware_first(void)
+{
+	static bool parsed = false;
+
+	if (!parsed) {
+		apei_hest_parse(aer_hest_parse_aff, NULL);
+		parsed = true;
+	}
+	return aer_firmware_first;
+}
+#endif
diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
new file mode 100644
index 00000000..43421fbe
--- /dev/null
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -0,0 +1,781 @@
+/*
+ * drivers/pci/pcie/aer/aerdrv_core.c
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * This file implements the core part of PCI-Express AER. When an pci-express
+ * error is delivered, an error message will be collected and printed to
+ * console, then, an error recovery procedure will be executed by following
+ * the pci error recovery rules.
+ *
+ * Copyright (C) 2006 Intel Corp.
+ *	Tom Long Nguyen (tom.l.nguyen@intel.com)
+ *	Zhang Yanmin (yanmin.zhang@intel.com)
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/pm.h>
+#include <linux/suspend.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include "aerdrv.h"
+
+static int forceload;
+static int nosourceid;
+module_param(forceload, bool, 0);
+module_param(nosourceid, bool, 0);
+
+int pci_enable_pcie_error_reporting(struct pci_dev *dev)
+{
+	u16 reg16 = 0;
+	int pos;
+
+	if (pcie_aer_get_firmware_first(dev))
+		return -EIO;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	if (!pos)
+		return -EIO;
+
+	pos = pci_pcie_cap(dev);
+	if (!pos)
+		return -EIO;
+
+	pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &reg16);
+	reg16 |= (PCI_EXP_DEVCTL_CERE |
+		PCI_EXP_DEVCTL_NFERE |
+		PCI_EXP_DEVCTL_FERE |
+		PCI_EXP_DEVCTL_URRE);
+	pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, reg16);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_enable_pcie_error_reporting);
+
+int pci_disable_pcie_error_reporting(struct pci_dev *dev)
+{
+	u16 reg16 = 0;
+	int pos;
+
+	if (pcie_aer_get_firmware_first(dev))
+		return -EIO;
+
+	pos = pci_pcie_cap(dev);
+	if (!pos)
+		return -EIO;
+
+	pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &reg16);
+	reg16 &= ~(PCI_EXP_DEVCTL_CERE |
+		PCI_EXP_DEVCTL_NFERE |
+		PCI_EXP_DEVCTL_FERE |
+		PCI_EXP_DEVCTL_URRE);
+	pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, reg16);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting);
+
+int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
+{
+	int pos;
+	u32 status;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	if (!pos)
+		return -EIO;
+
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
+	if (status)
+		pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status);
+
+/**
+ * add_error_device - list device to be handled
+ * @e_info: pointer to error info
+ * @dev: pointer to pci_dev to be added
+ */
+static int add_error_device(struct aer_err_info *e_info, struct pci_dev *dev)
+{
+	if (e_info->error_dev_num < AER_MAX_MULTI_ERR_DEVICES) {
+		e_info->dev[e_info->error_dev_num] = dev;
+		e_info->error_dev_num++;
+		return 0;
+	}
+	return -ENOSPC;
+}
+
+#define	PCI_BUS(x)	(((x) >> 8) & 0xff)
+
+/**
+ * is_error_source - check whether the device is source of reported error
+ * @dev: pointer to pci_dev to be checked
+ * @e_info: pointer to reported error info
+ */
+static bool is_error_source(struct pci_dev *dev, struct aer_err_info *e_info)
+{
+	int pos;
+	u32 status, mask;
+	u16 reg16;
+
+	/*
+	 * When bus id is equal to 0, it might be a bad id
+	 * reported by root port.
+	 */
+	if (!nosourceid && (PCI_BUS(e_info->id) != 0)) {
+		/* Device ID match? */
+		if (e_info->id == ((dev->bus->number << 8) | dev->devfn))
+			return true;
+
+		/* Continue id comparing if there is no multiple error */
+		if (!e_info->multi_error_valid)
+			return false;
+	}
+
+	/*
+	 * When either
+	 *      1) nosourceid==y;
+	 *      2) bus id is equal to 0. Some ports might lose the bus
+	 *              id of error source id;
+	 *      3) There are multiple errors and prior id comparing fails;
+	 * We check AER status registers to find possible reporter.
+	 */
+	if (atomic_read(&dev->enable_cnt) == 0)
+		return false;
+	pos = pci_pcie_cap(dev);
+	if (!pos)
+		return false;
+
+	/* Check if AER is enabled */
+	pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &reg16);
+	if (!(reg16 & (
+		PCI_EXP_DEVCTL_CERE |
+		PCI_EXP_DEVCTL_NFERE |
+		PCI_EXP_DEVCTL_FERE |
+		PCI_EXP_DEVCTL_URRE)))
+		return false;
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	if (!pos)
+		return false;
+
+	/* Check if error is recorded */
+	if (e_info->severity == AER_CORRECTABLE) {
+		pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS, &status);
+		pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, &mask);
+	} else {
+		pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
+		pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, &mask);
+	}
+	if (status & ~mask)
+		return true;
+
+	return false;
+}
+
+static int find_device_iter(struct pci_dev *dev, void *data)
+{
+	struct aer_err_info *e_info = (struct aer_err_info *)data;
+
+	if (is_error_source(dev, e_info)) {
+		/* List this device */
+		if (add_error_device(e_info, dev)) {
+			/* We cannot handle more... Stop iteration */
+			/* TODO: Should print error message here? */
+			return 1;
+		}
+
+		/* If there is only a single error, stop iteration */
+		if (!e_info->multi_error_valid)
+			return 1;
+	}
+	return 0;
+}
+
+/**
+ * find_source_device - search through device hierarchy for source device
+ * @parent: pointer to Root Port pci_dev data structure
+ * @e_info: including detailed error information such like id
+ *
+ * Return true if found.
+ *
+ * Invoked by DPC when error is detected at the Root Port.
+ * Caller of this function must set id, severity, and multi_error_valid of
+ * struct aer_err_info pointed by @e_info properly.  This function must fill
+ * e_info->error_dev_num and e_info->dev[], based on the given information.
+ */
+static bool find_source_device(struct pci_dev *parent,
+		struct aer_err_info *e_info)
+{
+	struct pci_dev *dev = parent;
+	int result;
+
+	/* Must reset in this function */
+	e_info->error_dev_num = 0;
+
+	/* Is Root Port an agent that sends error message? */
+	result = find_device_iter(dev, e_info);
+	if (result)
+		return true;
+
+	pci_walk_bus(parent->subordinate, find_device_iter, e_info);
+
+	if (!e_info->error_dev_num) {
+		dev_printk(KERN_DEBUG, &parent->dev,
+				"can't find device of ID%04x\n",
+				e_info->id);
+		return false;
+	}
+	return true;
+}
+
+static int report_error_detected(struct pci_dev *dev, void *data)
+{
+	pci_ers_result_t vote;
+	struct pci_error_handlers *err_handler;
+	struct aer_broadcast_data *result_data;
+	result_data = (struct aer_broadcast_data *) data;
+
+	dev->error_state = result_data->state;
+
+	if (!dev->driver ||
+		!dev->driver->err_handler ||
+		!dev->driver->err_handler->error_detected) {
+		if (result_data->state == pci_channel_io_frozen &&
+			!(dev->hdr_type & PCI_HEADER_TYPE_BRIDGE)) {
+			/*
+			 * In case of fatal recovery, if one of down-
+			 * stream device has no driver. We might be
+			 * unable to recover because a later insmod
+			 * of a driver for this device is unaware of
+			 * its hw state.
+			 */
+			dev_printk(KERN_DEBUG, &dev->dev, "device has %s\n",
+				   dev->driver ?
+				   "no AER-aware driver" : "no driver");
+		}
+		return 0;
+	}
+
+	err_handler = dev->driver->err_handler;
+	vote = err_handler->error_detected(dev, result_data->state);
+	result_data->result = merge_result(result_data->result, vote);
+	return 0;
+}
+
+static int report_mmio_enabled(struct pci_dev *dev, void *data)
+{
+	pci_ers_result_t vote;
+	struct pci_error_handlers *err_handler;
+	struct aer_broadcast_data *result_data;
+	result_data = (struct aer_broadcast_data *) data;
+
+	if (!dev->driver ||
+		!dev->driver->err_handler ||
+		!dev->driver->err_handler->mmio_enabled)
+		return 0;
+
+	err_handler = dev->driver->err_handler;
+	vote = err_handler->mmio_enabled(dev);
+	result_data->result = merge_result(result_data->result, vote);
+	return 0;
+}
+
+static int report_slot_reset(struct pci_dev *dev, void *data)
+{
+	pci_ers_result_t vote;
+	struct pci_error_handlers *err_handler;
+	struct aer_broadcast_data *result_data;
+	result_data = (struct aer_broadcast_data *) data;
+
+	if (!dev->driver ||
+		!dev->driver->err_handler ||
+		!dev->driver->err_handler->slot_reset)
+		return 0;
+
+	err_handler = dev->driver->err_handler;
+	vote = err_handler->slot_reset(dev);
+	result_data->result = merge_result(result_data->result, vote);
+	return 0;
+}
+
+static int report_resume(struct pci_dev *dev, void *data)
+{
+	struct pci_error_handlers *err_handler;
+
+	dev->error_state = pci_channel_io_normal;
+
+	if (!dev->driver ||
+		!dev->driver->err_handler ||
+		!dev->driver->err_handler->resume)
+		return 0;
+
+	err_handler = dev->driver->err_handler;
+	err_handler->resume(dev);
+	return 0;
+}
+
+/**
+ * broadcast_error_message - handle message broadcast to downstream drivers
+ * @dev: pointer to from where in a hierarchy message is broadcasted down
+ * @state: error state
+ * @error_mesg: message to print
+ * @cb: callback to be broadcasted
+ *
+ * Invoked during error recovery process. Once being invoked, the content
+ * of error severity will be broadcasted to all downstream drivers in a
+ * hierarchy in question.
+ */
+static pci_ers_result_t broadcast_error_message(struct pci_dev *dev,
+	enum pci_channel_state state,
+	char *error_mesg,
+	int (*cb)(struct pci_dev *, void *))
+{
+	struct aer_broadcast_data result_data;
+
+	dev_printk(KERN_DEBUG, &dev->dev, "broadcast %s message\n", error_mesg);
+	result_data.state = state;
+	if (cb == report_error_detected)
+		result_data.result = PCI_ERS_RESULT_CAN_RECOVER;
+	else
+		result_data.result = PCI_ERS_RESULT_RECOVERED;
+
+	if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE) {
+		/*
+		 * If the error is reported by a bridge, we think this error
+		 * is related to the downstream link of the bridge, so we
+		 * do error recovery on all subordinates of the bridge instead
+		 * of the bridge and clear the error status of the bridge.
+		 */
+		if (cb == report_error_detected)
+			dev->error_state = state;
+		pci_walk_bus(dev->subordinate, cb, &result_data);
+		if (cb == report_resume) {
+			pci_cleanup_aer_uncorrect_error_status(dev);
+			dev->error_state = pci_channel_io_normal;
+		}
+	} else {
+		/*
+		 * If the error is reported by an end point, we think this
+		 * error is related to the upstream link of the end point.
+		 */
+		pci_walk_bus(dev->bus, cb, &result_data);
+	}
+
+	return result_data.result;
+}
+
+/**
+ * aer_do_secondary_bus_reset - perform secondary bus reset
+ * @dev: pointer to bridge's pci_dev data structure
+ *
+ * Invoked when performing link reset at Root Port or Downstream Port.
+ */
+void aer_do_secondary_bus_reset(struct pci_dev *dev)
+{
+	u16 p2p_ctrl;
+
+	/* Assert Secondary Bus Reset */
+	pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &p2p_ctrl);
+	p2p_ctrl |= PCI_BRIDGE_CTL_BUS_RESET;
+	pci_write_config_word(dev, PCI_BRIDGE_CONTROL, p2p_ctrl);
+
+	/*
+	 * we should send hot reset message for 2ms to allow it time to
+	 * propagate to all downstream ports
+	 */
+	msleep(2);
+
+	/* De-assert Secondary Bus Reset */
+	p2p_ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET;
+	pci_write_config_word(dev, PCI_BRIDGE_CONTROL, p2p_ctrl);
+
+	/*
+	 * System software must wait for at least 100ms from the end
+	 * of a reset of one or more device before it is permitted
+	 * to issue Configuration Requests to those devices.
+	 */
+	msleep(200);
+}
+
+/**
+ * default_downstream_reset_link - default reset function for Downstream Port
+ * @dev: pointer to downstream port's pci_dev data structure
+ *
+ * Invoked when performing link reset at Downstream Port w/ no aer driver.
+ */
+static pci_ers_result_t default_downstream_reset_link(struct pci_dev *dev)
+{
+	aer_do_secondary_bus_reset(dev);
+	dev_printk(KERN_DEBUG, &dev->dev,
+		"Downstream Port link has been reset\n");
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
+static int find_aer_service_iter(struct device *device, void *data)
+{
+	struct pcie_port_service_driver *service_driver, **drv;
+
+	drv = (struct pcie_port_service_driver **) data;
+
+	if (device->bus == &pcie_port_bus_type && device->driver) {
+		service_driver = to_service_driver(device->driver);
+		if (service_driver->service == PCIE_PORT_SERVICE_AER) {
+			*drv = service_driver;
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static struct pcie_port_service_driver *find_aer_service(struct pci_dev *dev)
+{
+	struct pcie_port_service_driver *drv = NULL;
+
+	device_for_each_child(&dev->dev, &drv, find_aer_service_iter);
+
+	return drv;
+}
+
+static pci_ers_result_t reset_link(struct pcie_device *aerdev,
+		struct pci_dev *dev)
+{
+	struct pci_dev *udev;
+	pci_ers_result_t status;
+	struct pcie_port_service_driver *driver;
+
+	if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE) {
+		/* Reset this port for all subordinates */
+		udev = dev;
+	} else {
+		/* Reset the upstream component (likely downstream port) */
+		udev = dev->bus->self;
+	}
+
+	/* Use the aer driver of the component firstly */
+	driver = find_aer_service(udev);
+
+	if (driver && driver->reset_link) {
+		status = driver->reset_link(udev);
+	} else if (udev->pcie_type == PCI_EXP_TYPE_DOWNSTREAM) {
+		status = default_downstream_reset_link(udev);
+	} else {
+		dev_printk(KERN_DEBUG, &dev->dev,
+			"no link-reset support at upstream device %s\n",
+			pci_name(udev));
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	if (status != PCI_ERS_RESULT_RECOVERED) {
+		dev_printk(KERN_DEBUG, &dev->dev,
+			"link reset at upstream device %s failed\n",
+			pci_name(udev));
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	return status;
+}
+
+/**
+ * do_recovery - handle nonfatal/fatal error recovery process
+ * @aerdev: pointer to a pcie_device data structure of root port
+ * @dev: pointer to a pci_dev data structure of agent detecting an error
+ * @severity: error severity type
+ *
+ * Invoked when an error is nonfatal/fatal. Once being invoked, broadcast
+ * error detected message to all downstream drivers within a hierarchy in
+ * question and return the returned code.
+ */
+static void do_recovery(struct pcie_device *aerdev, struct pci_dev *dev,
+		int severity)
+{
+	pci_ers_result_t status, result = PCI_ERS_RESULT_RECOVERED;
+	enum pci_channel_state state;
+
+	if (severity == AER_FATAL)
+		state = pci_channel_io_frozen;
+	else
+		state = pci_channel_io_normal;
+
+	status = broadcast_error_message(dev,
+			state,
+			"error_detected",
+			report_error_detected);
+
+	if (severity == AER_FATAL) {
+		result = reset_link(aerdev, dev);
+		if (result != PCI_ERS_RESULT_RECOVERED)
+			goto failed;
+	}
+
+	if (status == PCI_ERS_RESULT_CAN_RECOVER)
+		status = broadcast_error_message(dev,
+				state,
+				"mmio_enabled",
+				report_mmio_enabled);
+
+	if (status == PCI_ERS_RESULT_NEED_RESET) {
+		/*
+		 * TODO: Should call platform-specific
+		 * functions to reset slot before calling
+		 * drivers' slot_reset callbacks?
+		 */
+		status = broadcast_error_message(dev,
+				state,
+				"slot_reset",
+				report_slot_reset);
+	}
+
+	if (status != PCI_ERS_RESULT_RECOVERED)
+		goto failed;
+
+	broadcast_error_message(dev,
+				state,
+				"resume",
+				report_resume);
+
+	dev_printk(KERN_DEBUG, &dev->dev,
+		"AER driver successfully recovered\n");
+	return;
+
+failed:
+	/* TODO: Should kernel panic here? */
+	dev_printk(KERN_DEBUG, &dev->dev,
+		"AER driver didn't recover\n");
+}
+
+/**
+ * handle_error_source - handle logging error into an event log
+ * @aerdev: pointer to pcie_device data structure of the root port
+ * @dev: pointer to pci_dev data structure of error source device
+ * @info: comprehensive error information
+ *
+ * Invoked when an error being detected by Root Port.
+ */
+static void handle_error_source(struct pcie_device *aerdev,
+	struct pci_dev *dev,
+	struct aer_err_info *info)
+{
+	int pos;
+
+	if (info->severity == AER_CORRECTABLE) {
+		/*
+		 * Correctable error does not need software intevention.
+		 * No need to go through error recovery process.
+		 */
+		pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+		if (pos)
+			pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS,
+					info->status);
+	} else
+		do_recovery(aerdev, dev, info->severity);
+}
+
+/**
+ * get_device_error_info - read error status from dev and store it to info
+ * @dev: pointer to the device expected to have a error record
+ * @info: pointer to structure to store the error record
+ *
+ * Return 1 on success, 0 on error.
+ *
+ * Note that @info is reused among all error devices. Clear fields properly.
+ */
+static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
+{
+	int pos, temp;
+
+	/* Must reset in this function */
+	info->status = 0;
+	info->tlp_header_valid = 0;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+
+	/* The device might not support AER */
+	if (!pos)
+		return 1;
+
+	if (info->severity == AER_CORRECTABLE) {
+		pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS,
+			&info->status);
+		pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK,
+			&info->mask);
+		if (!(info->status & ~info->mask))
+			return 0;
+	} else if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE ||
+		info->severity == AER_NONFATAL) {
+
+		/* Link is still healthy for IO reads */
+		pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS,
+			&info->status);
+		pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK,
+			&info->mask);
+		if (!(info->status & ~info->mask))
+			return 0;
+
+		/* Get First Error Pointer */
+		pci_read_config_dword(dev, pos + PCI_ERR_CAP, &temp);
+		info->first_error = PCI_ERR_CAP_FEP(temp);
+
+		if (info->status & AER_LOG_TLP_MASKS) {
+			info->tlp_header_valid = 1;
+			pci_read_config_dword(dev,
+				pos + PCI_ERR_HEADER_LOG, &info->tlp.dw0);
+			pci_read_config_dword(dev,
+				pos + PCI_ERR_HEADER_LOG + 4, &info->tlp.dw1);
+			pci_read_config_dword(dev,
+				pos + PCI_ERR_HEADER_LOG + 8, &info->tlp.dw2);
+			pci_read_config_dword(dev,
+				pos + PCI_ERR_HEADER_LOG + 12, &info->tlp.dw3);
+		}
+	}
+
+	return 1;
+}
+
+static inline void aer_process_err_devices(struct pcie_device *p_device,
+			struct aer_err_info *e_info)
+{
+	int i;
+
+	/* Report all before handle them, not to lost records by reset etc. */
+	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
+		if (get_device_error_info(e_info->dev[i], e_info))
+			aer_print_error(e_info->dev[i], e_info);
+	}
+	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
+		if (get_device_error_info(e_info->dev[i], e_info))
+			handle_error_source(p_device, e_info->dev[i], e_info);
+	}
+}
+
+/**
+ * aer_isr_one_error - consume an error detected by root port
+ * @p_device: pointer to error root port service device
+ * @e_src: pointer to an error source
+ */
+static void aer_isr_one_error(struct pcie_device *p_device,
+		struct aer_err_source *e_src)
+{
+	struct aer_err_info *e_info;
+
+	/* struct aer_err_info might be big, so we allocate it with slab */
+	e_info = kmalloc(sizeof(struct aer_err_info), GFP_KERNEL);
+	if (!e_info) {
+		dev_printk(KERN_DEBUG, &p_device->port->dev,
+			"Can't allocate mem when processing AER errors\n");
+		return;
+	}
+
+	/*
+	 * There is a possibility that both correctable error and
+	 * uncorrectable error being logged. Report correctable error first.
+	 */
+	if (e_src->status & PCI_ERR_ROOT_COR_RCV) {
+		e_info->id = ERR_COR_ID(e_src->id);
+		e_info->severity = AER_CORRECTABLE;
+
+		if (e_src->status & PCI_ERR_ROOT_MULTI_COR_RCV)
+			e_info->multi_error_valid = 1;
+		else
+			e_info->multi_error_valid = 0;
+
+		aer_print_port_info(p_device->port, e_info);
+
+		if (find_source_device(p_device->port, e_info))
+			aer_process_err_devices(p_device, e_info);
+	}
+
+	if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
+		e_info->id = ERR_UNCOR_ID(e_src->id);
+
+		if (e_src->status & PCI_ERR_ROOT_FATAL_RCV)
+			e_info->severity = AER_FATAL;
+		else
+			e_info->severity = AER_NONFATAL;
+
+		if (e_src->status & PCI_ERR_ROOT_MULTI_UNCOR_RCV)
+			e_info->multi_error_valid = 1;
+		else
+			e_info->multi_error_valid = 0;
+
+		aer_print_port_info(p_device->port, e_info);
+
+		if (find_source_device(p_device->port, e_info))
+			aer_process_err_devices(p_device, e_info);
+	}
+
+	kfree(e_info);
+}
+
+/**
+ * get_e_source - retrieve an error source
+ * @rpc: pointer to the root port which holds an error
+ * @e_src: pointer to store retrieved error source
+ *
+ * Return 1 if an error source is retrieved, otherwise 0.
+ *
+ * Invoked by DPC handler to consume an error.
+ */
+static int get_e_source(struct aer_rpc *rpc, struct aer_err_source *e_src)
+{
+	unsigned long flags;
+
+	/* Lock access to Root error producer/consumer index */
+	spin_lock_irqsave(&rpc->e_lock, flags);
+	if (rpc->prod_idx == rpc->cons_idx) {
+		spin_unlock_irqrestore(&rpc->e_lock, flags);
+		return 0;
+	}
+
+	*e_src = rpc->e_sources[rpc->cons_idx];
+	rpc->cons_idx++;
+	if (rpc->cons_idx == AER_ERROR_SOURCES_MAX)
+		rpc->cons_idx = 0;
+	spin_unlock_irqrestore(&rpc->e_lock, flags);
+
+	return 1;
+}
+
+/**
+ * aer_isr - consume errors detected by root port
+ * @work: definition of this work item
+ *
+ * Invoked, as DPC, when root port records new detected error
+ */
+void aer_isr(struct work_struct *work)
+{
+	struct aer_rpc *rpc = container_of(work, struct aer_rpc, dpc_handler);
+	struct pcie_device *p_device = rpc->rpd;
+	struct aer_err_source uninitialized_var(e_src);
+
+	mutex_lock(&rpc->rpc_mutex);
+	while (get_e_source(rpc, &e_src))
+		aer_isr_one_error(p_device, &e_src);
+	mutex_unlock(&rpc->rpc_mutex);
+
+	wake_up(&rpc->wait_release);
+}
+
+/**
+ * aer_init - provide AER initialization
+ * @dev: pointer to AER pcie device
+ *
+ * Invoked when AER service driver is loaded.
+ */
+int aer_init(struct pcie_device *dev)
+{
+	if (forceload) {
+		dev_printk(KERN_DEBUG, &dev->device,
+			   "aerdrv forceload requested.\n");
+		pcie_aer_force_firmware_first(dev->port, 0);
+	}
+	return 0;
+}
diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c
new file mode 100644
index 00000000..b07a42e0
--- /dev/null
+++ b/drivers/pci/pcie/aer/aerdrv_errprint.c
@@ -0,0 +1,262 @@
+/*
+ * drivers/pci/pcie/aer/aerdrv_errprint.c
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Format error messages and print them to console.
+ *
+ * Copyright (C) 2006 Intel Corp.
+ *	Tom Long Nguyen (tom.l.nguyen@intel.com)
+ *	Zhang Yanmin (yanmin.zhang@intel.com)
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/pm.h>
+#include <linux/suspend.h>
+#include <linux/cper.h>
+
+#include "aerdrv.h"
+
+#define AER_AGENT_RECEIVER		0
+#define AER_AGENT_REQUESTER		1
+#define AER_AGENT_COMPLETER		2
+#define AER_AGENT_TRANSMITTER		3
+
+#define AER_AGENT_REQUESTER_MASK(t)	((t == AER_CORRECTABLE) ?	\
+	0 : (PCI_ERR_UNC_COMP_TIME|PCI_ERR_UNC_UNSUP))
+#define AER_AGENT_COMPLETER_MASK(t)	((t == AER_CORRECTABLE) ?	\
+	0 : PCI_ERR_UNC_COMP_ABORT)
+#define AER_AGENT_TRANSMITTER_MASK(t)	((t == AER_CORRECTABLE) ?	\
+	(PCI_ERR_COR_REP_ROLL|PCI_ERR_COR_REP_TIMER) : 0)
+
+#define AER_GET_AGENT(t, e)						\
+	((e & AER_AGENT_COMPLETER_MASK(t)) ? AER_AGENT_COMPLETER :	\
+	(e & AER_AGENT_REQUESTER_MASK(t)) ? AER_AGENT_REQUESTER :	\
+	(e & AER_AGENT_TRANSMITTER_MASK(t)) ? AER_AGENT_TRANSMITTER :	\
+	AER_AGENT_RECEIVER)
+
+#define AER_PHYSICAL_LAYER_ERROR	0
+#define AER_DATA_LINK_LAYER_ERROR	1
+#define AER_TRANSACTION_LAYER_ERROR	2
+
+#define AER_PHYSICAL_LAYER_ERROR_MASK(t) ((t == AER_CORRECTABLE) ?	\
+	PCI_ERR_COR_RCVR : 0)
+#define AER_DATA_LINK_LAYER_ERROR_MASK(t) ((t == AER_CORRECTABLE) ?	\
+	(PCI_ERR_COR_BAD_TLP|						\
+	PCI_ERR_COR_BAD_DLLP|						\
+	PCI_ERR_COR_REP_ROLL|						\
+	PCI_ERR_COR_REP_TIMER) : PCI_ERR_UNC_DLP)
+
+#define AER_GET_LAYER_ERROR(t, e)					\
+	((e & AER_PHYSICAL_LAYER_ERROR_MASK(t)) ? AER_PHYSICAL_LAYER_ERROR : \
+	(e & AER_DATA_LINK_LAYER_ERROR_MASK(t)) ? AER_DATA_LINK_LAYER_ERROR : \
+	AER_TRANSACTION_LAYER_ERROR)
+
+/*
+ * AER error strings
+ */
+static const char *aer_error_severity_string[] = {
+	"Uncorrected (Non-Fatal)",
+	"Uncorrected (Fatal)",
+	"Corrected"
+};
+
+static const char *aer_error_layer[] = {
+	"Physical Layer",
+	"Data Link Layer",
+	"Transaction Layer"
+};
+
+static const char *aer_correctable_error_string[] = {
+	"Receiver Error",		/* Bit Position 0	*/
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	"Bad TLP",			/* Bit Position 6	*/
+	"Bad DLLP",			/* Bit Position 7	*/
+	"RELAY_NUM Rollover",		/* Bit Position 8	*/
+	NULL,
+	NULL,
+	NULL,
+	"Replay Timer Timeout",		/* Bit Position 12	*/
+	"Advisory Non-Fatal",		/* Bit Position 13	*/
+};
+
+static const char *aer_uncorrectable_error_string[] = {
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	"Data Link Protocol",		/* Bit Position 4	*/
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	NULL,
+	"Poisoned TLP",			/* Bit Position 12	*/
+	"Flow Control Protocol",	/* Bit Position 13	*/
+	"Completion Timeout",		/* Bit Position 14	*/
+	"Completer Abort",		/* Bit Position 15	*/
+	"Unexpected Completion",	/* Bit Position 16	*/
+	"Receiver Overflow",		/* Bit Position 17	*/
+	"Malformed TLP",		/* Bit Position 18	*/
+	"ECRC",				/* Bit Position 19	*/
+	"Unsupported Request",		/* Bit Position 20	*/
+};
+
+static const char *aer_agent_string[] = {
+	"Receiver ID",
+	"Requester ID",
+	"Completer ID",
+	"Transmitter ID"
+};
+
+static void __aer_print_error(const char *prefix,
+			      struct aer_err_info *info)
+{
+	int i, status;
+	const char *errmsg = NULL;
+
+	status = (info->status & ~info->mask);
+
+	for (i = 0; i < 32; i++) {
+		if (!(status & (1 << i)))
+			continue;
+
+		if (info->severity == AER_CORRECTABLE)
+			errmsg = i < ARRAY_SIZE(aer_correctable_error_string) ?
+				aer_correctable_error_string[i] : NULL;
+		else
+			errmsg = i < ARRAY_SIZE(aer_uncorrectable_error_string) ?
+				aer_uncorrectable_error_string[i] : NULL;
+
+		if (errmsg)
+			printk("%s""   [%2d] %-22s%s\n", prefix, i, errmsg,
+				info->first_error == i ? " (First)" : "");
+		else
+			printk("%s""   [%2d] Unknown Error Bit%s\n", prefix, i,
+				info->first_error == i ? " (First)" : "");
+	}
+}
+
+void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
+{
+	int id = ((dev->bus->number << 8) | dev->devfn);
+	char prefix[44];
+
+	snprintf(prefix, sizeof(prefix), "%s%s %s: ",
+		 (info->severity == AER_CORRECTABLE) ? KERN_WARNING : KERN_ERR,
+		 dev_driver_string(&dev->dev), dev_name(&dev->dev));
+
+	if (info->status == 0) {
+		printk("%s""PCIe Bus Error: severity=%s, type=Unaccessible, "
+			"id=%04x(Unregistered Agent ID)\n", prefix,
+			aer_error_severity_string[info->severity], id);
+	} else {
+		int layer, agent;
+
+		layer = AER_GET_LAYER_ERROR(info->severity, info->status);
+		agent = AER_GET_AGENT(info->severity, info->status);
+
+		printk("%s""PCIe Bus Error: severity=%s, type=%s, id=%04x(%s)\n",
+			prefix, aer_error_severity_string[info->severity],
+			aer_error_layer[layer], id, aer_agent_string[agent]);
+
+		printk("%s""  device [%04x:%04x] error status/mask=%08x/%08x\n",
+			prefix, dev->vendor, dev->device,
+			info->status, info->mask);
+
+		__aer_print_error(prefix, info);
+
+		if (info->tlp_header_valid) {
+			unsigned char *tlp = (unsigned char *) &info->tlp;
+			printk("%s""  TLP Header:"
+				" %02x%02x%02x%02x %02x%02x%02x%02x"
+				" %02x%02x%02x%02x %02x%02x%02x%02x\n",
+				prefix, *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp,
+				*(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4),
+				*(tlp + 11), *(tlp + 10), *(tlp + 9),
+				*(tlp + 8), *(tlp + 15), *(tlp + 14),
+				*(tlp + 13), *(tlp + 12));
+		}
+	}
+
+	if (info->id && info->error_dev_num > 1 && info->id == id)
+		printk("%s""  Error of this Agent(%04x) is reported first\n",
+			prefix, id);
+}
+
+void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info)
+{
+	dev_info(&dev->dev, "AER: %s%s error received: id=%04x\n",
+		info->multi_error_valid ? "Multiple " : "",
+		aer_error_severity_string[info->severity], info->id);
+}
+
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+static int cper_severity_to_aer(int cper_severity)
+{
+	switch (cper_severity) {
+	case CPER_SEV_RECOVERABLE:
+		return AER_NONFATAL;
+	case CPER_SEV_FATAL:
+		return AER_FATAL;
+	default:
+		return AER_CORRECTABLE;
+	}
+}
+
+void cper_print_aer(const char *prefix, int cper_severity,
+		    struct aer_capability_regs *aer)
+{
+	int aer_severity, layer, agent, status_strs_size, tlp_header_valid = 0;
+	u32 status, mask;
+	const char **status_strs;
+
+	aer_severity = cper_severity_to_aer(cper_severity);
+	if (aer_severity == AER_CORRECTABLE) {
+		status = aer->cor_status;
+		mask = aer->cor_mask;
+		status_strs = aer_correctable_error_string;
+		status_strs_size = ARRAY_SIZE(aer_correctable_error_string);
+	} else {
+		status = aer->uncor_status;
+		mask = aer->uncor_mask;
+		status_strs = aer_uncorrectable_error_string;
+		status_strs_size = ARRAY_SIZE(aer_uncorrectable_error_string);
+		tlp_header_valid = status & AER_LOG_TLP_MASKS;
+	}
+	layer = AER_GET_LAYER_ERROR(aer_severity, status);
+	agent = AER_GET_AGENT(aer_severity, status);
+	printk("%s""aer_status: 0x%08x, aer_mask: 0x%08x\n",
+	       prefix, status, mask);
+	cper_print_bits(prefix, status, status_strs, status_strs_size);
+	printk("%s""aer_layer=%s, aer_agent=%s\n", prefix,
+	       aer_error_layer[layer], aer_agent_string[agent]);
+	if (aer_severity != AER_CORRECTABLE)
+		printk("%s""aer_uncor_severity: 0x%08x\n",
+		       prefix, aer->uncor_severity);
+	if (tlp_header_valid) {
+		const unsigned char *tlp;
+		tlp = (const unsigned char *)&aer->header_log;
+		printk("%s""aer_tlp_header:"
+			" %02x%02x%02x%02x %02x%02x%02x%02x"
+			" %02x%02x%02x%02x %02x%02x%02x%02x\n",
+			prefix, *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp,
+			*(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4),
+			*(tlp + 11), *(tlp + 10), *(tlp + 9),
+			*(tlp + 8), *(tlp + 15), *(tlp + 14),
+			*(tlp + 13), *(tlp + 12));
+	}
+}
+#endif
diff --git a/drivers/pci/pcie/aer/ecrc.c b/drivers/pci/pcie/aer/ecrc.c
new file mode 100644
index 00000000..a2747a66
--- /dev/null
+++ b/drivers/pci/pcie/aer/ecrc.c
@@ -0,0 +1,131 @@
+/*
+ *    Enables/disables PCIe ECRC checking.
+ *
+ *    (C) Copyright 2009 Hewlett-Packard Development Company, L.P.
+ *    Andrew Patterson <andrew.patterson@hp.com>
+ *
+ *    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; version 2 of the License.
+ *
+ *    This program is distributed in the hope that it will be useful,
+ *    but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *    MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ *    General Public License for more details.
+ *
+ *    You should have received a copy of the GNU General Public License
+ *    along with this program; if not, write to the Free Software
+ *    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
+ *    02111-1307, USA.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/pci.h>
+#include <linux/pci_regs.h>
+#include <linux/errno.h>
+#include "../../pci.h"
+
+#define ECRC_POLICY_DEFAULT 0		/* ECRC set by BIOS */
+#define ECRC_POLICY_OFF     1		/* ECRC off for performance */
+#define ECRC_POLICY_ON      2		/* ECRC on for data integrity */
+
+static int ecrc_policy = ECRC_POLICY_DEFAULT;
+
+static const char *ecrc_policy_str[] = {
+	[ECRC_POLICY_DEFAULT] = "bios",
+	[ECRC_POLICY_OFF] = "off",
+	[ECRC_POLICY_ON] = "on"
+};
+
+/**
+ * enable_ercr_checking - enable PCIe ECRC checking for a device
+ * @dev: the PCI device
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+static int enable_ecrc_checking(struct pci_dev *dev)
+{
+	int pos;
+	u32 reg32;
+
+	if (!pci_is_pcie(dev))
+		return -ENODEV;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	if (!pos)
+		return -ENODEV;
+
+	pci_read_config_dword(dev, pos + PCI_ERR_CAP, &reg32);
+	if (reg32 & PCI_ERR_CAP_ECRC_GENC)
+		reg32 |= PCI_ERR_CAP_ECRC_GENE;
+	if (reg32 & PCI_ERR_CAP_ECRC_CHKC)
+		reg32 |= PCI_ERR_CAP_ECRC_CHKE;
+	pci_write_config_dword(dev, pos + PCI_ERR_CAP, reg32);
+
+	return 0;
+}
+
+/**
+ * disable_ercr_checking - disables PCIe ECRC checking for a device
+ * @dev: the PCI device
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+static int disable_ecrc_checking(struct pci_dev *dev)
+{
+	int pos;
+	u32 reg32;
+
+	if (!pci_is_pcie(dev))
+		return -ENODEV;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	if (!pos)
+		return -ENODEV;
+
+	pci_read_config_dword(dev, pos + PCI_ERR_CAP, &reg32);
+	reg32 &= ~(PCI_ERR_CAP_ECRC_GENE | PCI_ERR_CAP_ECRC_CHKE);
+	pci_write_config_dword(dev, pos + PCI_ERR_CAP, reg32);
+
+	return 0;
+}
+
+/**
+ * pcie_set_ecrc_checking - set/unset PCIe ECRC checking for a device based on global policy
+ * @dev: the PCI device
+ */
+void pcie_set_ecrc_checking(struct pci_dev *dev)
+{
+	switch (ecrc_policy) {
+	case ECRC_POLICY_DEFAULT:
+		return;
+	case ECRC_POLICY_OFF:
+		disable_ecrc_checking(dev);
+		break;
+	case ECRC_POLICY_ON:
+		enable_ecrc_checking(dev);
+		break;
+	default:
+		return;
+	}
+}
+
+/**
+ * pcie_ecrc_get_policy - parse kernel command-line ecrc option
+ */
+void pcie_ecrc_get_policy(char *str)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ecrc_policy_str); i++)
+		if (!strncmp(str, ecrc_policy_str[i],
+			     strlen(ecrc_policy_str[i])))
+			break;
+	if (i >= ARRAY_SIZE(ecrc_policy_str))
+		return;
+
+	ecrc_policy = i;
+}
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
new file mode 100644
index 00000000..0ff0182f
--- /dev/null
+++ b/drivers/pci/pcie/aspm.c
@@ -0,0 +1,1004 @@
+/*
+ * File:	drivers/pci/pcie/aspm.c
+ * Enabling PCIe link L0s/L1 state and Clock Power Management
+ *
+ * Copyright (C) 2007 Intel
+ * Copyright (C) Zhang Yanmin (yanmin.zhang@intel.com)
+ * Copyright (C) Shaohua Li (shaohua.li@intel.com)
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/pci.h>
+#include <linux/pci_regs.h>
+#include <linux/errno.h>
+#include <linux/pm.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/jiffies.h>
+#include <linux/delay.h>
+#include <linux/pci-aspm.h>
+#include "../pci.h"
+
+#ifdef MODULE_PARAM_PREFIX
+#undef MODULE_PARAM_PREFIX
+#endif
+#define MODULE_PARAM_PREFIX "pcie_aspm."
+
+/* Note: those are not register definitions */
+#define ASPM_STATE_L0S_UP	(1)	/* Upstream direction L0s state */
+#define ASPM_STATE_L0S_DW	(2)	/* Downstream direction L0s state */
+#define ASPM_STATE_L1		(4)	/* L1 state */
+#define ASPM_STATE_L0S		(ASPM_STATE_L0S_UP | ASPM_STATE_L0S_DW)
+#define ASPM_STATE_ALL		(ASPM_STATE_L0S | ASPM_STATE_L1)
+
+struct aspm_latency {
+	u32 l0s;			/* L0s latency (nsec) */
+	u32 l1;				/* L1 latency (nsec) */
+};
+
+struct pcie_link_state {
+	struct pci_dev *pdev;		/* Upstream component of the Link */
+	struct pcie_link_state *root;	/* pointer to the root port link */
+	struct pcie_link_state *parent;	/* pointer to the parent Link state */
+	struct list_head sibling;	/* node in link_list */
+	struct list_head children;	/* list of child link states */
+	struct list_head link;		/* node in parent's children list */
+
+	/* ASPM state */
+	u32 aspm_support:3;		/* Supported ASPM state */
+	u32 aspm_enabled:3;		/* Enabled ASPM state */
+	u32 aspm_capable:3;		/* Capable ASPM state with latency */
+	u32 aspm_default:3;		/* Default ASPM state by BIOS */
+	u32 aspm_disable:3;		/* Disabled ASPM state */
+
+	/* Clock PM state */
+	u32 clkpm_capable:1;		/* Clock PM capable? */
+	u32 clkpm_enabled:1;		/* Current Clock PM state */
+	u32 clkpm_default:1;		/* Default Clock PM state by BIOS */
+
+	/* Exit latencies */
+	struct aspm_latency latency_up;	/* Upstream direction exit latency */
+	struct aspm_latency latency_dw;	/* Downstream direction exit latency */
+	/*
+	 * Endpoint acceptable latencies. A pcie downstream port only
+	 * has one slot under it, so at most there are 8 functions.
+	 */
+	struct aspm_latency acceptable[8];
+};
+
+static int aspm_disabled, aspm_force;
+static bool aspm_support_enabled = true;
+static DEFINE_MUTEX(aspm_lock);
+static LIST_HEAD(link_list);
+
+#define POLICY_DEFAULT 0	/* BIOS default setting */
+#define POLICY_PERFORMANCE 1	/* high performance */
+#define POLICY_POWERSAVE 2	/* high power saving */
+static int aspm_policy;
+static const char *policy_str[] = {
+	[POLICY_DEFAULT] = "default",
+	[POLICY_PERFORMANCE] = "performance",
+	[POLICY_POWERSAVE] = "powersave"
+};
+
+#define LINK_RETRAIN_TIMEOUT HZ
+
+static int policy_to_aspm_state(struct pcie_link_state *link)
+{
+	switch (aspm_policy) {
+	case POLICY_PERFORMANCE:
+		/* Disable ASPM and Clock PM */
+		return 0;
+	case POLICY_POWERSAVE:
+		/* Enable ASPM L0s/L1 */
+		return ASPM_STATE_ALL;
+	case POLICY_DEFAULT:
+		return link->aspm_default;
+	}
+	return 0;
+}
+
+static int policy_to_clkpm_state(struct pcie_link_state *link)
+{
+	switch (aspm_policy) {
+	case POLICY_PERFORMANCE:
+		/* Disable ASPM and Clock PM */
+		return 0;
+	case POLICY_POWERSAVE:
+		/* Disable Clock PM */
+		return 1;
+	case POLICY_DEFAULT:
+		return link->clkpm_default;
+	}
+	return 0;
+}
+
+static void pcie_set_clkpm_nocheck(struct pcie_link_state *link, int enable)
+{
+	int pos;
+	u16 reg16;
+	struct pci_dev *child;
+	struct pci_bus *linkbus = link->pdev->subordinate;
+
+	list_for_each_entry(child, &linkbus->devices, bus_list) {
+		pos = pci_pcie_cap(child);
+		if (!pos)
+			return;
+		pci_read_config_word(child, pos + PCI_EXP_LNKCTL, &reg16);
+		if (enable)
+			reg16 |= PCI_EXP_LNKCTL_CLKREQ_EN;
+		else
+			reg16 &= ~PCI_EXP_LNKCTL_CLKREQ_EN;
+		pci_write_config_word(child, pos + PCI_EXP_LNKCTL, reg16);
+	}
+	link->clkpm_enabled = !!enable;
+}
+
+static void pcie_set_clkpm(struct pcie_link_state *link, int enable)
+{
+	/* Don't enable Clock PM if the link is not Clock PM capable */
+	if (!link->clkpm_capable && enable)
+		enable = 0;
+	/* Need nothing if the specified equals to current state */
+	if (link->clkpm_enabled == enable)
+		return;
+	pcie_set_clkpm_nocheck(link, enable);
+}
+
+static void pcie_clkpm_cap_init(struct pcie_link_state *link, int blacklist)
+{
+	int pos, capable = 1, enabled = 1;
+	u32 reg32;
+	u16 reg16;
+	struct pci_dev *child;
+	struct pci_bus *linkbus = link->pdev->subordinate;
+
+	/* All functions should have the same cap and state, take the worst */
+	list_for_each_entry(child, &linkbus->devices, bus_list) {
+		pos = pci_pcie_cap(child);
+		if (!pos)
+			return;
+		pci_read_config_dword(child, pos + PCI_EXP_LNKCAP, &reg32);
+		if (!(reg32 & PCI_EXP_LNKCAP_CLKPM)) {
+			capable = 0;
+			enabled = 0;
+			break;
+		}
+		pci_read_config_word(child, pos + PCI_EXP_LNKCTL, &reg16);
+		if (!(reg16 & PCI_EXP_LNKCTL_CLKREQ_EN))
+			enabled = 0;
+	}
+	link->clkpm_enabled = enabled;
+	link->clkpm_default = enabled;
+	link->clkpm_capable = (blacklist) ? 0 : capable;
+}
+
+/*
+ * pcie_aspm_configure_common_clock: check if the 2 ends of a link
+ *   could use common clock. If they are, configure them to use the
+ *   common clock. That will reduce the ASPM state exit latency.
+ */
+static void pcie_aspm_configure_common_clock(struct pcie_link_state *link)
+{
+	int ppos, cpos, same_clock = 1;
+	u16 reg16, parent_reg, child_reg[8];
+	unsigned long start_jiffies;
+	struct pci_dev *child, *parent = link->pdev;
+	struct pci_bus *linkbus = parent->subordinate;
+	/*
+	 * All functions of a slot should have the same Slot Clock
+	 * Configuration, so just check one function
+	 */
+	child = list_entry(linkbus->devices.next, struct pci_dev, bus_list);
+	BUG_ON(!pci_is_pcie(child));
+
+	/* Check downstream component if bit Slot Clock Configuration is 1 */
+	cpos = pci_pcie_cap(child);
+	pci_read_config_word(child, cpos + PCI_EXP_LNKSTA, &reg16);
+	if (!(reg16 & PCI_EXP_LNKSTA_SLC))
+		same_clock = 0;
+
+	/* Check upstream component if bit Slot Clock Configuration is 1 */
+	ppos = pci_pcie_cap(parent);
+	pci_read_config_word(parent, ppos + PCI_EXP_LNKSTA, &reg16);
+	if (!(reg16 & PCI_EXP_LNKSTA_SLC))
+		same_clock = 0;
+
+	/* Configure downstream component, all functions */
+	list_for_each_entry(child, &linkbus->devices, bus_list) {
+		cpos = pci_pcie_cap(child);
+		pci_read_config_word(child, cpos + PCI_EXP_LNKCTL, &reg16);
+		child_reg[PCI_FUNC(child->devfn)] = reg16;
+		if (same_clock)
+			reg16 |= PCI_EXP_LNKCTL_CCC;
+		else
+			reg16 &= ~PCI_EXP_LNKCTL_CCC;
+		pci_write_config_word(child, cpos + PCI_EXP_LNKCTL, reg16);
+	}
+
+	/* Configure upstream component */
+	pci_read_config_word(parent, ppos + PCI_EXP_LNKCTL, &reg16);
+	parent_reg = reg16;
+	if (same_clock)
+		reg16 |= PCI_EXP_LNKCTL_CCC;
+	else
+		reg16 &= ~PCI_EXP_LNKCTL_CCC;
+	pci_write_config_word(parent, ppos + PCI_EXP_LNKCTL, reg16);
+
+	/* Retrain link */
+	reg16 |= PCI_EXP_LNKCTL_RL;
+	pci_write_config_word(parent, ppos + PCI_EXP_LNKCTL, reg16);
+
+	/* Wait for link training end. Break out after waiting for timeout */
+	start_jiffies = jiffies;
+	for (;;) {
+		pci_read_config_word(parent, ppos + PCI_EXP_LNKSTA, &reg16);
+		if (!(reg16 & PCI_EXP_LNKSTA_LT))
+			break;
+		if (time_after(jiffies, start_jiffies + LINK_RETRAIN_TIMEOUT))
+			break;
+		msleep(1);
+	}
+	if (!(reg16 & PCI_EXP_LNKSTA_LT))
+		return;
+
+	/* Training failed. Restore common clock configurations */
+	dev_printk(KERN_ERR, &parent->dev,
+		   "ASPM: Could not configure common clock\n");
+	list_for_each_entry(child, &linkbus->devices, bus_list) {
+		cpos = pci_pcie_cap(child);
+		pci_write_config_word(child, cpos + PCI_EXP_LNKCTL,
+				      child_reg[PCI_FUNC(child->devfn)]);
+	}
+	pci_write_config_word(parent, ppos + PCI_EXP_LNKCTL, parent_reg);
+}
+
+/* Convert L0s latency encoding to ns */
+static u32 calc_l0s_latency(u32 encoding)
+{
+	if (encoding == 0x7)
+		return (5 * 1000);	/* > 4us */
+	return (64 << encoding);
+}
+
+/* Convert L0s acceptable latency encoding to ns */
+static u32 calc_l0s_acceptable(u32 encoding)
+{
+	if (encoding == 0x7)
+		return -1U;
+	return (64 << encoding);
+}
+
+/* Convert L1 latency encoding to ns */
+static u32 calc_l1_latency(u32 encoding)
+{
+	if (encoding == 0x7)
+		return (65 * 1000);	/* > 64us */
+	return (1000 << encoding);
+}
+
+/* Convert L1 acceptable latency encoding to ns */
+static u32 calc_l1_acceptable(u32 encoding)
+{
+	if (encoding == 0x7)
+		return -1U;
+	return (1000 << encoding);
+}
+
+struct aspm_register_info {
+	u32 support:2;
+	u32 enabled:2;
+	u32 latency_encoding_l0s;
+	u32 latency_encoding_l1;
+};
+
+static void pcie_get_aspm_reg(struct pci_dev *pdev,
+			      struct aspm_register_info *info)
+{
+	int pos;
+	u16 reg16;
+	u32 reg32;
+
+	pos = pci_pcie_cap(pdev);
+	pci_read_config_dword(pdev, pos + PCI_EXP_LNKCAP, &reg32);
+	info->support = (reg32 & PCI_EXP_LNKCAP_ASPMS) >> 10;
+	info->latency_encoding_l0s = (reg32 & PCI_EXP_LNKCAP_L0SEL) >> 12;
+	info->latency_encoding_l1  = (reg32 & PCI_EXP_LNKCAP_L1EL) >> 15;
+	pci_read_config_word(pdev, pos + PCI_EXP_LNKCTL, &reg16);
+	info->enabled = reg16 & PCI_EXP_LNKCTL_ASPMC;
+}
+
+static void pcie_aspm_check_latency(struct pci_dev *endpoint)
+{
+	u32 latency, l1_switch_latency = 0;
+	struct aspm_latency *acceptable;
+	struct pcie_link_state *link;
+
+	/* Device not in D0 doesn't need latency check */
+	if ((endpoint->current_state != PCI_D0) &&
+	    (endpoint->current_state != PCI_UNKNOWN))
+		return;
+
+	link = endpoint->bus->self->link_state;
+	acceptable = &link->acceptable[PCI_FUNC(endpoint->devfn)];
+
+	while (link) {
+		/* Check upstream direction L0s latency */
+		if ((link->aspm_capable & ASPM_STATE_L0S_UP) &&
+		    (link->latency_up.l0s > acceptable->l0s))
+			link->aspm_capable &= ~ASPM_STATE_L0S_UP;
+
+		/* Check downstream direction L0s latency */
+		if ((link->aspm_capable & ASPM_STATE_L0S_DW) &&
+		    (link->latency_dw.l0s > acceptable->l0s))
+			link->aspm_capable &= ~ASPM_STATE_L0S_DW;
+		/*
+		 * Check L1 latency.
+		 * Every switch on the path to root complex need 1
+		 * more microsecond for L1. Spec doesn't mention L0s.
+		 */
+		latency = max_t(u32, link->latency_up.l1, link->latency_dw.l1);
+		if ((link->aspm_capable & ASPM_STATE_L1) &&
+		    (latency + l1_switch_latency > acceptable->l1))
+			link->aspm_capable &= ~ASPM_STATE_L1;
+		l1_switch_latency += 1000;
+
+		link = link->parent;
+	}
+}
+
+static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
+{
+	struct pci_dev *child, *parent = link->pdev;
+	struct pci_bus *linkbus = parent->subordinate;
+	struct aspm_register_info upreg, dwreg;
+
+	if (blacklist) {
+		/* Set enabled/disable so that we will disable ASPM later */
+		link->aspm_enabled = ASPM_STATE_ALL;
+		link->aspm_disable = ASPM_STATE_ALL;
+		return;
+	}
+
+	/* Configure common clock before checking latencies */
+	pcie_aspm_configure_common_clock(link);
+
+	/* Get upstream/downstream components' register state */
+	pcie_get_aspm_reg(parent, &upreg);
+	child = list_entry(linkbus->devices.next, struct pci_dev, bus_list);
+	pcie_get_aspm_reg(child, &dwreg);
+
+	/*
+	 * Setup L0s state
+	 *
+	 * Note that we must not enable L0s in either direction on a
+	 * given link unless components on both sides of the link each
+	 * support L0s.
+	 */
+	if (dwreg.support & upreg.support & PCIE_LINK_STATE_L0S)
+		link->aspm_support |= ASPM_STATE_L0S;
+	if (dwreg.enabled & PCIE_LINK_STATE_L0S)
+		link->aspm_enabled |= ASPM_STATE_L0S_UP;
+	if (upreg.enabled & PCIE_LINK_STATE_L0S)
+		link->aspm_enabled |= ASPM_STATE_L0S_DW;
+	link->latency_up.l0s = calc_l0s_latency(upreg.latency_encoding_l0s);
+	link->latency_dw.l0s = calc_l0s_latency(dwreg.latency_encoding_l0s);
+
+	/* Setup L1 state */
+	if (upreg.support & dwreg.support & PCIE_LINK_STATE_L1)
+		link->aspm_support |= ASPM_STATE_L1;
+	if (upreg.enabled & dwreg.enabled & PCIE_LINK_STATE_L1)
+		link->aspm_enabled |= ASPM_STATE_L1;
+	link->latency_up.l1 = calc_l1_latency(upreg.latency_encoding_l1);
+	link->latency_dw.l1 = calc_l1_latency(dwreg.latency_encoding_l1);
+
+	/* Save default state */
+	link->aspm_default = link->aspm_enabled;
+
+	/* Setup initial capable state. Will be updated later */
+	link->aspm_capable = link->aspm_support;
+	/*
+	 * If the downstream component has pci bridge function, don't
+	 * do ASPM for now.
+	 */
+	list_for_each_entry(child, &linkbus->devices, bus_list) {
+		if (child->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) {
+			link->aspm_disable = ASPM_STATE_ALL;
+			break;
+		}
+	}
+
+	/* Get and check endpoint acceptable latencies */
+	list_for_each_entry(child, &linkbus->devices, bus_list) {
+		int pos;
+		u32 reg32, encoding;
+		struct aspm_latency *acceptable =
+			&link->acceptable[PCI_FUNC(child->devfn)];
+
+		if (child->pcie_type != PCI_EXP_TYPE_ENDPOINT &&
+		    child->pcie_type != PCI_EXP_TYPE_LEG_END)
+			continue;
+
+		pos = pci_pcie_cap(child);
+		pci_read_config_dword(child, pos + PCI_EXP_DEVCAP, &reg32);
+		/* Calculate endpoint L0s acceptable latency */
+		encoding = (reg32 & PCI_EXP_DEVCAP_L0S) >> 6;
+		acceptable->l0s = calc_l0s_acceptable(encoding);
+		/* Calculate endpoint L1 acceptable latency */
+		encoding = (reg32 & PCI_EXP_DEVCAP_L1) >> 9;
+		acceptable->l1 = calc_l1_acceptable(encoding);
+
+		pcie_aspm_check_latency(child);
+	}
+}
+
+static void pcie_config_aspm_dev(struct pci_dev *pdev, u32 val)
+{
+	u16 reg16;
+	int pos = pci_pcie_cap(pdev);
+
+	pci_read_config_word(pdev, pos + PCI_EXP_LNKCTL, &reg16);
+	reg16 &= ~0x3;
+	reg16 |= val;
+	pci_write_config_word(pdev, pos + PCI_EXP_LNKCTL, reg16);
+}
+
+static void pcie_config_aspm_link(struct pcie_link_state *link, u32 state)
+{
+	u32 upstream = 0, dwstream = 0;
+	struct pci_dev *child, *parent = link->pdev;
+	struct pci_bus *linkbus = parent->subordinate;
+
+	/* Nothing to do if the link is already in the requested state */
+	state &= (link->aspm_capable & ~link->aspm_disable);
+	if (link->aspm_enabled == state)
+		return;
+	/* Convert ASPM state to upstream/downstream ASPM register state */
+	if (state & ASPM_STATE_L0S_UP)
+		dwstream |= PCIE_LINK_STATE_L0S;
+	if (state & ASPM_STATE_L0S_DW)
+		upstream |= PCIE_LINK_STATE_L0S;
+	if (state & ASPM_STATE_L1) {
+		upstream |= PCIE_LINK_STATE_L1;
+		dwstream |= PCIE_LINK_STATE_L1;
+	}
+	/*
+	 * Spec 2.0 suggests all functions should be configured the
+	 * same setting for ASPM. Enabling ASPM L1 should be done in
+	 * upstream component first and then downstream, and vice
+	 * versa for disabling ASPM L1. Spec doesn't mention L0S.
+	 */
+	if (state & ASPM_STATE_L1)
+		pcie_config_aspm_dev(parent, upstream);
+	list_for_each_entry(child, &linkbus->devices, bus_list)
+		pcie_config_aspm_dev(child, dwstream);
+	if (!(state & ASPM_STATE_L1))
+		pcie_config_aspm_dev(parent, upstream);
+
+	link->aspm_enabled = state;
+}
+
+static void pcie_config_aspm_path(struct pcie_link_state *link)
+{
+	while (link) {
+		pcie_config_aspm_link(link, policy_to_aspm_state(link));
+		link = link->parent;
+	}
+}
+
+static void free_link_state(struct pcie_link_state *link)
+{
+	link->pdev->link_state = NULL;
+	kfree(link);
+}
+
+static int pcie_aspm_sanity_check(struct pci_dev *pdev)
+{
+	struct pci_dev *child;
+	int pos;
+	u32 reg32;
+
+	/*
+	 * Some functions in a slot might not all be PCIe functions,
+	 * very strange. Disable ASPM for the whole slot
+	 */
+	list_for_each_entry(child, &pdev->subordinate->devices, bus_list) {
+		pos = pci_pcie_cap(child);
+		if (!pos)
+			return -EINVAL;
+
+		/*
+		 * If ASPM is disabled then we're not going to change
+		 * the BIOS state. It's safe to continue even if it's a
+		 * pre-1.1 device
+		 */
+
+		if (aspm_disabled)
+			continue;
+
+		/*
+		 * Disable ASPM for pre-1.1 PCIe device, we follow MS to use
+		 * RBER bit to determine if a function is 1.1 version device
+		 */
+		pci_read_config_dword(child, pos + PCI_EXP_DEVCAP, &reg32);
+		if (!(reg32 & PCI_EXP_DEVCAP_RBER) && !aspm_force) {
+			dev_printk(KERN_INFO, &child->dev, "disabling ASPM"
+				" on pre-1.1 PCIe device.  You can enable it"
+				" with 'pcie_aspm=force'\n");
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev)
+{
+	struct pcie_link_state *link;
+
+	link = kzalloc(sizeof(*link), GFP_KERNEL);
+	if (!link)
+		return NULL;
+	INIT_LIST_HEAD(&link->sibling);
+	INIT_LIST_HEAD(&link->children);
+	INIT_LIST_HEAD(&link->link);
+	link->pdev = pdev;
+	if (pdev->pcie_type == PCI_EXP_TYPE_DOWNSTREAM) {
+		struct pcie_link_state *parent;
+		parent = pdev->bus->parent->self->link_state;
+		if (!parent) {
+			kfree(link);
+			return NULL;
+		}
+		link->parent = parent;
+		list_add(&link->link, &parent->children);
+	}
+	/* Setup a pointer to the root port link */
+	if (!link->parent)
+		link->root = link;
+	else
+		link->root = link->parent->root;
+
+	list_add(&link->sibling, &link_list);
+	pdev->link_state = link;
+	return link;
+}
+
+/*
+ * pcie_aspm_init_link_state: Initiate PCI express link state.
+ * It is called after the pcie and its children devices are scaned.
+ * @pdev: the root port or switch downstream port
+ */
+void pcie_aspm_init_link_state(struct pci_dev *pdev)
+{
+	struct pcie_link_state *link;
+	int blacklist = !!pcie_aspm_sanity_check(pdev);
+
+	if (!pci_is_pcie(pdev) || pdev->link_state)
+		return;
+	if (pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT &&
+	    pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM)
+		return;
+
+	/* VIA has a strange chipset, root port is under a bridge */
+	if (pdev->pcie_type == PCI_EXP_TYPE_ROOT_PORT &&
+	    pdev->bus->self)
+		return;
+
+	down_read(&pci_bus_sem);
+	if (list_empty(&pdev->subordinate->devices))
+		goto out;
+
+	mutex_lock(&aspm_lock);
+	link = alloc_pcie_link_state(pdev);
+	if (!link)
+		goto unlock;
+	/*
+	 * Setup initial ASPM state. Note that we need to configure
+	 * upstream links also because capable state of them can be
+	 * update through pcie_aspm_cap_init().
+	 */
+	pcie_aspm_cap_init(link, blacklist);
+
+	/* Setup initial Clock PM state */
+	pcie_clkpm_cap_init(link, blacklist);
+
+	/*
+	 * At this stage drivers haven't had an opportunity to change the
+	 * link policy setting. Enabling ASPM on broken hardware can cripple
+	 * it even before the driver has had a chance to disable ASPM, so
+	 * default to a safe level right now. If we're enabling ASPM beyond
+	 * the BIOS's expectation, we'll do so once pci_enable_device() is
+	 * called.
+	 */
+	if (aspm_policy != POLICY_POWERSAVE) {
+		pcie_config_aspm_path(link);
+		pcie_set_clkpm(link, policy_to_clkpm_state(link));
+	}
+
+unlock:
+	mutex_unlock(&aspm_lock);
+out:
+	up_read(&pci_bus_sem);
+}
+
+/* Recheck latencies and update aspm_capable for links under the root */
+static void pcie_update_aspm_capable(struct pcie_link_state *root)
+{
+	struct pcie_link_state *link;
+	BUG_ON(root->parent);
+	list_for_each_entry(link, &link_list, sibling) {
+		if (link->root != root)
+			continue;
+		link->aspm_capable = link->aspm_support;
+	}
+	list_for_each_entry(link, &link_list, sibling) {
+		struct pci_dev *child;
+		struct pci_bus *linkbus = link->pdev->subordinate;
+		if (link->root != root)
+			continue;
+		list_for_each_entry(child, &linkbus->devices, bus_list) {
+			if ((child->pcie_type != PCI_EXP_TYPE_ENDPOINT) &&
+			    (child->pcie_type != PCI_EXP_TYPE_LEG_END))
+				continue;
+			pcie_aspm_check_latency(child);
+		}
+	}
+}
+
+/* @pdev: the endpoint device */
+void pcie_aspm_exit_link_state(struct pci_dev *pdev)
+{
+	struct pci_dev *parent = pdev->bus->self;
+	struct pcie_link_state *link, *root, *parent_link;
+
+	if (!pci_is_pcie(pdev) || !parent || !parent->link_state)
+		return;
+	if ((parent->pcie_type != PCI_EXP_TYPE_ROOT_PORT) &&
+	    (parent->pcie_type != PCI_EXP_TYPE_DOWNSTREAM))
+		return;
+
+	down_read(&pci_bus_sem);
+	mutex_lock(&aspm_lock);
+	/*
+	 * All PCIe functions are in one slot, remove one function will remove
+	 * the whole slot, so just wait until we are the last function left.
+	 */
+	if (!list_is_last(&pdev->bus_list, &parent->subordinate->devices))
+		goto out;
+
+	link = parent->link_state;
+	root = link->root;
+	parent_link = link->parent;
+
+	/* All functions are removed, so just disable ASPM for the link */
+	pcie_config_aspm_link(link, 0);
+	list_del(&link->sibling);
+	list_del(&link->link);
+	/* Clock PM is for endpoint device */
+	free_link_state(link);
+
+	/* Recheck latencies and configure upstream links */
+	if (parent_link) {
+		pcie_update_aspm_capable(root);
+		pcie_config_aspm_path(parent_link);
+	}
+out:
+	mutex_unlock(&aspm_lock);
+	up_read(&pci_bus_sem);
+}
+
+/* @pdev: the root port or switch downstream port */
+void pcie_aspm_pm_state_change(struct pci_dev *pdev)
+{
+	struct pcie_link_state *link = pdev->link_state;
+
+	if (aspm_disabled || !pci_is_pcie(pdev) || !link)
+		return;
+	if ((pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT) &&
+	    (pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM))
+		return;
+	/*
+	 * Devices changed PM state, we should recheck if latency
+	 * meets all functions' requirement
+	 */
+	down_read(&pci_bus_sem);
+	mutex_lock(&aspm_lock);
+	pcie_update_aspm_capable(link->root);
+	pcie_config_aspm_path(link);
+	mutex_unlock(&aspm_lock);
+	up_read(&pci_bus_sem);
+}
+
+void pcie_aspm_powersave_config_link(struct pci_dev *pdev)
+{
+	struct pcie_link_state *link = pdev->link_state;
+
+	if (aspm_disabled || !pci_is_pcie(pdev) || !link)
+		return;
+
+	if (aspm_policy != POLICY_POWERSAVE)
+		return;
+
+	if ((pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT) &&
+	    (pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM))
+		return;
+
+	down_read(&pci_bus_sem);
+	mutex_lock(&aspm_lock);
+	pcie_config_aspm_path(link);
+	pcie_set_clkpm(link, policy_to_clkpm_state(link));
+	mutex_unlock(&aspm_lock);
+	up_read(&pci_bus_sem);
+}
+
+/*
+ * pci_disable_link_state - disable pci device's link state, so the link will
+ * never enter specific states
+ */
+static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem,
+				     bool force)
+{
+	struct pci_dev *parent = pdev->bus->self;
+	struct pcie_link_state *link;
+
+	if (aspm_disabled && !force)
+		return;
+
+	if (!pci_is_pcie(pdev))
+		return;
+
+	if (pdev->pcie_type == PCI_EXP_TYPE_ROOT_PORT ||
+	    pdev->pcie_type == PCI_EXP_TYPE_DOWNSTREAM)
+		parent = pdev;
+	if (!parent || !parent->link_state)
+		return;
+
+	if (sem)
+		down_read(&pci_bus_sem);
+	mutex_lock(&aspm_lock);
+	link = parent->link_state;
+	if (state & PCIE_LINK_STATE_L0S)
+		link->aspm_disable |= ASPM_STATE_L0S;
+	if (state & PCIE_LINK_STATE_L1)
+		link->aspm_disable |= ASPM_STATE_L1;
+	pcie_config_aspm_link(link, policy_to_aspm_state(link));
+
+	if (state & PCIE_LINK_STATE_CLKPM) {
+		link->clkpm_capable = 0;
+		pcie_set_clkpm(link, 0);
+	}
+	mutex_unlock(&aspm_lock);
+	if (sem)
+		up_read(&pci_bus_sem);
+}
+
+void pci_disable_link_state_locked(struct pci_dev *pdev, int state)
+{
+	__pci_disable_link_state(pdev, state, false, false);
+}
+EXPORT_SYMBOL(pci_disable_link_state_locked);
+
+void pci_disable_link_state(struct pci_dev *pdev, int state)
+{
+	__pci_disable_link_state(pdev, state, true, false);
+}
+EXPORT_SYMBOL(pci_disable_link_state);
+
+void pcie_clear_aspm(struct pci_bus *bus)
+{
+	struct pci_dev *child;
+
+	/*
+	 * Clear any ASPM setup that the firmware has carried out on this bus
+	 */
+	list_for_each_entry(child, &bus->devices, bus_list) {
+		__pci_disable_link_state(child, PCIE_LINK_STATE_L0S |
+					 PCIE_LINK_STATE_L1 |
+					 PCIE_LINK_STATE_CLKPM,
+					 false, true);
+	}
+}
+
+static int pcie_aspm_set_policy(const char *val, struct kernel_param *kp)
+{
+	int i;
+	struct pcie_link_state *link;
+
+	if (aspm_disabled)
+		return -EPERM;
+	for (i = 0; i < ARRAY_SIZE(policy_str); i++)
+		if (!strncmp(val, policy_str[i], strlen(policy_str[i])))
+			break;
+	if (i >= ARRAY_SIZE(policy_str))
+		return -EINVAL;
+	if (i == aspm_policy)
+		return 0;
+
+	down_read(&pci_bus_sem);
+	mutex_lock(&aspm_lock);
+	aspm_policy = i;
+	list_for_each_entry(link, &link_list, sibling) {
+		pcie_config_aspm_link(link, policy_to_aspm_state(link));
+		pcie_set_clkpm(link, policy_to_clkpm_state(link));
+	}
+	mutex_unlock(&aspm_lock);
+	up_read(&pci_bus_sem);
+	return 0;
+}
+
+static int pcie_aspm_get_policy(char *buffer, struct kernel_param *kp)
+{
+	int i, cnt = 0;
+	for (i = 0; i < ARRAY_SIZE(policy_str); i++)
+		if (i == aspm_policy)
+			cnt += sprintf(buffer + cnt, "[%s] ", policy_str[i]);
+		else
+			cnt += sprintf(buffer + cnt, "%s ", policy_str[i]);
+	return cnt;
+}
+
+module_param_call(policy, pcie_aspm_set_policy, pcie_aspm_get_policy,
+	NULL, 0644);
+
+#ifdef CONFIG_PCIEASPM_DEBUG
+static ssize_t link_state_show(struct device *dev,
+		struct device_attribute *attr,
+		char *buf)
+{
+	struct pci_dev *pci_device = to_pci_dev(dev);
+	struct pcie_link_state *link_state = pci_device->link_state;
+
+	return sprintf(buf, "%d\n", link_state->aspm_enabled);
+}
+
+static ssize_t link_state_store(struct device *dev,
+		struct device_attribute *attr,
+		const char *buf,
+		size_t n)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pcie_link_state *link, *root = pdev->link_state->root;
+	u32 val = buf[0] - '0', state = 0;
+
+	if (aspm_disabled)
+		return -EPERM;
+	if (n < 1 || val > 3)
+		return -EINVAL;
+
+	/* Convert requested state to ASPM state */
+	if (val & PCIE_LINK_STATE_L0S)
+		state |= ASPM_STATE_L0S;
+	if (val & PCIE_LINK_STATE_L1)
+		state |= ASPM_STATE_L1;
+
+	down_read(&pci_bus_sem);
+	mutex_lock(&aspm_lock);
+	list_for_each_entry(link, &link_list, sibling) {
+		if (link->root != root)
+			continue;
+		pcie_config_aspm_link(link, state);
+	}
+	mutex_unlock(&aspm_lock);
+	up_read(&pci_bus_sem);
+	return n;
+}
+
+static ssize_t clk_ctl_show(struct device *dev,
+		struct device_attribute *attr,
+		char *buf)
+{
+	struct pci_dev *pci_device = to_pci_dev(dev);
+	struct pcie_link_state *link_state = pci_device->link_state;
+
+	return sprintf(buf, "%d\n", link_state->clkpm_enabled);
+}
+
+static ssize_t clk_ctl_store(struct device *dev,
+		struct device_attribute *attr,
+		const char *buf,
+		size_t n)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int state;
+
+	if (n < 1)
+		return -EINVAL;
+	state = buf[0]-'0';
+
+	down_read(&pci_bus_sem);
+	mutex_lock(&aspm_lock);
+	pcie_set_clkpm_nocheck(pdev->link_state, !!state);
+	mutex_unlock(&aspm_lock);
+	up_read(&pci_bus_sem);
+
+	return n;
+}
+
+static DEVICE_ATTR(link_state, 0644, link_state_show, link_state_store);
+static DEVICE_ATTR(clk_ctl, 0644, clk_ctl_show, clk_ctl_store);
+
+static char power_group[] = "power";
+void pcie_aspm_create_sysfs_dev_files(struct pci_dev *pdev)
+{
+	struct pcie_link_state *link_state = pdev->link_state;
+
+	if (!pci_is_pcie(pdev) ||
+	    (pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT &&
+	     pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM) || !link_state)
+		return;
+
+	if (link_state->aspm_support)
+		sysfs_add_file_to_group(&pdev->dev.kobj,
+			&dev_attr_link_state.attr, power_group);
+	if (link_state->clkpm_capable)
+		sysfs_add_file_to_group(&pdev->dev.kobj,
+			&dev_attr_clk_ctl.attr, power_group);
+}
+
+void pcie_aspm_remove_sysfs_dev_files(struct pci_dev *pdev)
+{
+	struct pcie_link_state *link_state = pdev->link_state;
+
+	if (!pci_is_pcie(pdev) ||
+	    (pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT &&
+	     pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM) || !link_state)
+		return;
+
+	if (link_state->aspm_support)
+		sysfs_remove_file_from_group(&pdev->dev.kobj,
+			&dev_attr_link_state.attr, power_group);
+	if (link_state->clkpm_capable)
+		sysfs_remove_file_from_group(&pdev->dev.kobj,
+			&dev_attr_clk_ctl.attr, power_group);
+}
+#endif
+
+static int __init pcie_aspm_disable(char *str)
+{
+	if (!strcmp(str, "off")) {
+		aspm_policy = POLICY_DEFAULT;
+		aspm_disabled = 1;
+		aspm_support_enabled = false;
+		printk(KERN_INFO "PCIe ASPM is disabled\n");
+	} else if (!strcmp(str, "force")) {
+		aspm_force = 1;
+		printk(KERN_INFO "PCIe ASPM is forcedly enabled\n");
+	}
+	return 1;
+}
+
+__setup("pcie_aspm=", pcie_aspm_disable);
+
+void pcie_no_aspm(void)
+{
+	/*
+	 * Disabling ASPM is intended to prevent the kernel from modifying
+	 * existing hardware state, not to clear existing state. To that end:
+	 * (a) set policy to POLICY_DEFAULT in order to avoid changing state
+	 * (b) prevent userspace from changing policy
+	 */
+	if (!aspm_force) {
+		aspm_policy = POLICY_DEFAULT;
+		aspm_disabled = 1;
+	}
+}
+
+/**
+ * pcie_aspm_enabled - is PCIe ASPM enabled?
+ *
+ * Returns true if ASPM has not been disabled by the command-line option
+ * pcie_aspm=off.
+ **/
+int pcie_aspm_enabled(void)
+{
+       return !aspm_disabled;
+}
+EXPORT_SYMBOL(pcie_aspm_enabled);
+
+bool pcie_aspm_support_enabled(void)
+{
+	return aspm_support_enabled;
+}
+EXPORT_SYMBOL(pcie_aspm_support_enabled);
diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
new file mode 100644
index 00000000..0057344a
--- /dev/null
+++ b/drivers/pci/pcie/pme.c
@@ -0,0 +1,443 @@
+/*
+ * PCIe Native PME support
+ *
+ * Copyright (C) 2007 - 2009 Intel Corp
+ * Copyright (C) 2007 - 2009 Shaohua Li <shaohua.li@intel.com>
+ * Copyright (C) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License V2.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/device.h>
+#include <linux/pcieport_if.h>
+#include <linux/acpi.h>
+#include <linux/pci-acpi.h>
+#include <linux/pm_runtime.h>
+
+#include "../pci.h"
+#include "portdrv.h"
+
+/*
+ * If this switch is set, MSI will not be used for PCIe PME signaling.  This
+ * causes the PCIe port driver to use INTx interrupts only, but it turns out
+ * that using MSI for PCIe PME signaling doesn't play well with PCIe PME-based
+ * wake-up from system sleep states.
+ */
+bool pcie_pme_msi_disabled;
+
+static int __init pcie_pme_setup(char *str)
+{
+	if (!strncmp(str, "nomsi", 5))
+		pcie_pme_msi_disabled = true;
+
+	return 1;
+}
+__setup("pcie_pme=", pcie_pme_setup);
+
+struct pcie_pme_service_data {
+	spinlock_t lock;
+	struct pcie_device *srv;
+	struct work_struct work;
+	bool noirq; /* Don't enable the PME interrupt used by this service. */
+};
+
+/**
+ * pcie_pme_interrupt_enable - Enable/disable PCIe PME interrupt generation.
+ * @dev: PCIe root port or event collector.
+ * @enable: Enable or disable the interrupt.
+ */
+void pcie_pme_interrupt_enable(struct pci_dev *dev, bool enable)
+{
+	int rtctl_pos;
+	u16 rtctl;
+
+	rtctl_pos = pci_pcie_cap(dev) + PCI_EXP_RTCTL;
+
+	pci_read_config_word(dev, rtctl_pos, &rtctl);
+	if (enable)
+		rtctl |= PCI_EXP_RTCTL_PMEIE;
+	else
+		rtctl &= ~PCI_EXP_RTCTL_PMEIE;
+	pci_write_config_word(dev, rtctl_pos, rtctl);
+}
+
+/**
+ * pcie_pme_walk_bus - Scan a PCI bus for devices asserting PME#.
+ * @bus: PCI bus to scan.
+ *
+ * Scan given PCI bus and all buses under it for devices asserting PME#.
+ */
+static bool pcie_pme_walk_bus(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+	bool ret = false;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		/* Skip PCIe devices in case we started from a root port. */
+		if (!pci_is_pcie(dev) && pci_check_pme_status(dev)) {
+			pci_wakeup_event(dev);
+			pm_request_resume(&dev->dev);
+			ret = true;
+		}
+
+		if (dev->subordinate && pcie_pme_walk_bus(dev->subordinate))
+			ret = true;
+	}
+
+	return ret;
+}
+
+/**
+ * pcie_pme_from_pci_bridge - Check if PCIe-PCI bridge generated a PME.
+ * @bus: Secondary bus of the bridge.
+ * @devfn: Device/function number to check.
+ *
+ * PME from PCI devices under a PCIe-PCI bridge may be converted to an in-band
+ * PCIe PME message.  In such that case the bridge should use the Requester ID
+ * of device/function number 0 on its secondary bus.
+ */
+static bool pcie_pme_from_pci_bridge(struct pci_bus *bus, u8 devfn)
+{
+	struct pci_dev *dev;
+	bool found = false;
+
+	if (devfn)
+		return false;
+
+	dev = pci_dev_get(bus->self);
+	if (!dev)
+		return false;
+
+	if (pci_is_pcie(dev) && dev->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) {
+		down_read(&pci_bus_sem);
+		if (pcie_pme_walk_bus(bus))
+			found = true;
+		up_read(&pci_bus_sem);
+	}
+
+	pci_dev_put(dev);
+	return found;
+}
+
+/**
+ * pcie_pme_handle_request - Find device that generated PME and handle it.
+ * @port: Root port or event collector that generated the PME interrupt.
+ * @req_id: PCIe Requester ID of the device that generated the PME.
+ */
+static void pcie_pme_handle_request(struct pci_dev *port, u16 req_id)
+{
+	u8 busnr = req_id >> 8, devfn = req_id & 0xff;
+	struct pci_bus *bus;
+	struct pci_dev *dev;
+	bool found = false;
+
+	/* First, check if the PME is from the root port itself. */
+	if (port->devfn == devfn && port->bus->number == busnr) {
+		if (pci_check_pme_status(port)) {
+			pm_request_resume(&port->dev);
+			found = true;
+		} else {
+			/*
+			 * Apparently, the root port generated the PME on behalf
+			 * of a non-PCIe device downstream.  If this is done by
+			 * a root port, the Requester ID field in its status
+			 * register may contain either the root port's, or the
+			 * source device's information (PCI Express Base
+			 * Specification, Rev. 2.0, Section 6.1.9).
+			 */
+			down_read(&pci_bus_sem);
+			found = pcie_pme_walk_bus(port->subordinate);
+			up_read(&pci_bus_sem);
+		}
+		goto out;
+	}
+
+	/* Second, find the bus the source device is on. */
+	bus = pci_find_bus(pci_domain_nr(port->bus), busnr);
+	if (!bus)
+		goto out;
+
+	/* Next, check if the PME is from a PCIe-PCI bridge. */
+	found = pcie_pme_from_pci_bridge(bus, devfn);
+	if (found)
+		goto out;
+
+	/* Finally, try to find the PME source on the bus. */
+	down_read(&pci_bus_sem);
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		pci_dev_get(dev);
+		if (dev->devfn == devfn) {
+			found = true;
+			break;
+		}
+		pci_dev_put(dev);
+	}
+	up_read(&pci_bus_sem);
+
+	if (found) {
+		/* The device is there, but we have to check its PME status. */
+		found = pci_check_pme_status(dev);
+		if (found) {
+			pci_wakeup_event(dev);
+			pm_request_resume(&dev->dev);
+		}
+		pci_dev_put(dev);
+	} else if (devfn) {
+		/*
+		 * The device is not there, but we can still try to recover by
+		 * assuming that the PME was reported by a PCIe-PCI bridge that
+		 * used devfn different from zero.
+		 */
+		dev_dbg(&port->dev, "PME interrupt generated for "
+			"non-existent device %02x:%02x.%d\n",
+			busnr, PCI_SLOT(devfn), PCI_FUNC(devfn));
+		found = pcie_pme_from_pci_bridge(bus, 0);
+	}
+
+ out:
+	if (!found)
+		dev_dbg(&port->dev, "Spurious native PME interrupt!\n");
+}
+
+/**
+ * pcie_pme_work_fn - Work handler for PCIe PME interrupt.
+ * @work: Work structure giving access to service data.
+ */
+static void pcie_pme_work_fn(struct work_struct *work)
+{
+	struct pcie_pme_service_data *data =
+			container_of(work, struct pcie_pme_service_data, work);
+	struct pci_dev *port = data->srv->port;
+	int rtsta_pos;
+	u32 rtsta;
+
+	rtsta_pos = pci_pcie_cap(port) + PCI_EXP_RTSTA;
+
+	spin_lock_irq(&data->lock);
+
+	for (;;) {
+		if (data->noirq)
+			break;
+
+		pci_read_config_dword(port, rtsta_pos, &rtsta);
+		if (rtsta & PCI_EXP_RTSTA_PME) {
+			/*
+			 * Clear PME status of the port.  If there are other
+			 * pending PMEs, the status will be set again.
+			 */
+			pcie_clear_root_pme_status(port);
+
+			spin_unlock_irq(&data->lock);
+			pcie_pme_handle_request(port, rtsta & 0xffff);
+			spin_lock_irq(&data->lock);
+
+			continue;
+		}
+
+		/* No need to loop if there are no more PMEs pending. */
+		if (!(rtsta & PCI_EXP_RTSTA_PENDING))
+			break;
+
+		spin_unlock_irq(&data->lock);
+		cpu_relax();
+		spin_lock_irq(&data->lock);
+	}
+
+	if (!data->noirq)
+		pcie_pme_interrupt_enable(port, true);
+
+	spin_unlock_irq(&data->lock);
+}
+
+/**
+ * pcie_pme_irq - Interrupt handler for PCIe root port PME interrupt.
+ * @irq: Interrupt vector.
+ * @context: Interrupt context pointer.
+ */
+static irqreturn_t pcie_pme_irq(int irq, void *context)
+{
+	struct pci_dev *port;
+	struct pcie_pme_service_data *data;
+	int rtsta_pos;
+	u32 rtsta;
+	unsigned long flags;
+
+	port = ((struct pcie_device *)context)->port;
+	data = get_service_data((struct pcie_device *)context);
+
+	rtsta_pos = pci_pcie_cap(port) + PCI_EXP_RTSTA;
+
+	spin_lock_irqsave(&data->lock, flags);
+	pci_read_config_dword(port, rtsta_pos, &rtsta);
+
+	if (!(rtsta & PCI_EXP_RTSTA_PME)) {
+		spin_unlock_irqrestore(&data->lock, flags);
+		return IRQ_NONE;
+	}
+
+	pcie_pme_interrupt_enable(port, false);
+	spin_unlock_irqrestore(&data->lock, flags);
+
+	/* We don't use pm_wq, because it's freezable. */
+	schedule_work(&data->work);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * pcie_pme_set_native - Set the PME interrupt flag for given device.
+ * @dev: PCI device to handle.
+ * @ign: Ignored.
+ */
+static int pcie_pme_set_native(struct pci_dev *dev, void *ign)
+{
+	dev_info(&dev->dev, "Signaling PME through PCIe PME interrupt\n");
+
+	device_set_run_wake(&dev->dev, true);
+	dev->pme_interrupt = true;
+	return 0;
+}
+
+/**
+ * pcie_pme_mark_devices - Set the PME interrupt flag for devices below a port.
+ * @port: PCIe root port or event collector to handle.
+ *
+ * For each device below given root port, including the port itself (or for each
+ * root complex integrated endpoint if @port is a root complex event collector)
+ * set the flag indicating that it can signal run-time wake-up events via PCIe
+ * PME interrupts.
+ */
+static void pcie_pme_mark_devices(struct pci_dev *port)
+{
+	pcie_pme_set_native(port, NULL);
+	if (port->subordinate) {
+		pci_walk_bus(port->subordinate, pcie_pme_set_native, NULL);
+	} else {
+		struct pci_bus *bus = port->bus;
+		struct pci_dev *dev;
+
+		/* Check if this is a root port event collector. */
+		if (port->pcie_type != PCI_EXP_TYPE_RC_EC || !bus)
+			return;
+
+		down_read(&pci_bus_sem);
+		list_for_each_entry(dev, &bus->devices, bus_list)
+			if (pci_is_pcie(dev)
+			    && dev->pcie_type == PCI_EXP_TYPE_RC_END)
+				pcie_pme_set_native(dev, NULL);
+		up_read(&pci_bus_sem);
+	}
+}
+
+/**
+ * pcie_pme_probe - Initialize PCIe PME service for given root port.
+ * @srv: PCIe service to initialize.
+ */
+static int pcie_pme_probe(struct pcie_device *srv)
+{
+	struct pci_dev *port;
+	struct pcie_pme_service_data *data;
+	int ret;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	spin_lock_init(&data->lock);
+	INIT_WORK(&data->work, pcie_pme_work_fn);
+	data->srv = srv;
+	set_service_data(srv, data);
+
+	port = srv->port;
+	pcie_pme_interrupt_enable(port, false);
+	pcie_clear_root_pme_status(port);
+
+	ret = request_irq(srv->irq, pcie_pme_irq, IRQF_SHARED, "PCIe PME", srv);
+	if (ret) {
+		kfree(data);
+	} else {
+		pcie_pme_mark_devices(port);
+		pcie_pme_interrupt_enable(port, true);
+	}
+
+	return ret;
+}
+
+/**
+ * pcie_pme_suspend - Suspend PCIe PME service device.
+ * @srv: PCIe service device to suspend.
+ */
+static int pcie_pme_suspend(struct pcie_device *srv)
+{
+	struct pcie_pme_service_data *data = get_service_data(srv);
+	struct pci_dev *port = srv->port;
+
+	spin_lock_irq(&data->lock);
+	pcie_pme_interrupt_enable(port, false);
+	pcie_clear_root_pme_status(port);
+	data->noirq = true;
+	spin_unlock_irq(&data->lock);
+
+	synchronize_irq(srv->irq);
+
+	return 0;
+}
+
+/**
+ * pcie_pme_resume - Resume PCIe PME service device.
+ * @srv - PCIe service device to resume.
+ */
+static int pcie_pme_resume(struct pcie_device *srv)
+{
+	struct pcie_pme_service_data *data = get_service_data(srv);
+	struct pci_dev *port = srv->port;
+
+	spin_lock_irq(&data->lock);
+	data->noirq = false;
+	pcie_clear_root_pme_status(port);
+	pcie_pme_interrupt_enable(port, true);
+	spin_unlock_irq(&data->lock);
+
+	return 0;
+}
+
+/**
+ * pcie_pme_remove - Prepare PCIe PME service device for removal.
+ * @srv - PCIe service device to resume.
+ */
+static void pcie_pme_remove(struct pcie_device *srv)
+{
+	pcie_pme_suspend(srv);
+	free_irq(srv->irq, srv);
+	kfree(get_service_data(srv));
+}
+
+static struct pcie_port_service_driver pcie_pme_driver = {
+	.name		= "pcie_pme",
+	.port_type 	= PCI_EXP_TYPE_ROOT_PORT,
+	.service 	= PCIE_PORT_SERVICE_PME,
+
+	.probe		= pcie_pme_probe,
+	.suspend	= pcie_pme_suspend,
+	.resume		= pcie_pme_resume,
+	.remove		= pcie_pme_remove,
+};
+
+/**
+ * pcie_pme_service_init - Register the PCIe PME service driver.
+ */
+static int __init pcie_pme_service_init(void)
+{
+	return pcie_port_service_register(&pcie_pme_driver);
+}
+
+module_init(pcie_pme_service_init);
diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h
new file mode 100644
index 00000000..bd00a01a
--- /dev/null
+++ b/drivers/pci/pcie/portdrv.h
@@ -0,0 +1,71 @@
+/*
+ * File:	portdrv.h
+ * Purpose:	PCI Express Port Bus Driver's Internal Data Structures
+ *
+ * Copyright (C) 2004 Intel
+ * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
+ */
+
+#ifndef _PORTDRV_H_
+#define _PORTDRV_H_
+
+#include <linux/compiler.h>
+
+#define PCIE_PORT_DEVICE_MAXSERVICES   4
+/*
+ * According to the PCI Express Base Specification 2.0, the indices of
+ * the MSI-X table entires used by port services must not exceed 31
+ */
+#define PCIE_PORT_MAX_MSIX_ENTRIES	32
+
+#define get_descriptor_id(type, service) (((type - 4) << 4) | service)
+
+extern struct bus_type pcie_port_bus_type;
+extern int pcie_port_device_register(struct pci_dev *dev);
+#ifdef CONFIG_PM
+extern int pcie_port_device_suspend(struct device *dev);
+extern int pcie_port_device_resume(struct device *dev);
+#endif
+extern void pcie_port_device_remove(struct pci_dev *dev);
+extern int __must_check pcie_port_bus_register(void);
+extern void pcie_port_bus_unregister(void);
+
+struct pci_dev;
+
+extern void pcie_clear_root_pme_status(struct pci_dev *dev);
+
+#ifdef CONFIG_PCIE_PME
+extern bool pcie_pme_msi_disabled;
+
+static inline void pcie_pme_disable_msi(void)
+{
+	pcie_pme_msi_disabled = true;
+}
+
+static inline bool pcie_pme_no_msi(void)
+{
+	return pcie_pme_msi_disabled;
+}
+
+extern void pcie_pme_interrupt_enable(struct pci_dev *dev, bool enable);
+#else /* !CONFIG_PCIE_PME */
+static inline void pcie_pme_disable_msi(void) {}
+static inline bool pcie_pme_no_msi(void) { return false; }
+static inline void pcie_pme_interrupt_enable(struct pci_dev *dev, bool en) {}
+#endif /* !CONFIG_PCIE_PME */
+
+#ifdef CONFIG_ACPI
+extern int pcie_port_acpi_setup(struct pci_dev *port, int *mask);
+
+static inline int pcie_port_platform_notify(struct pci_dev *port, int *mask)
+{
+	return pcie_port_acpi_setup(port, mask);
+}
+#else /* !CONFIG_ACPI */
+static inline int pcie_port_platform_notify(struct pci_dev *port, int *mask)
+{
+	return 0;
+}
+#endif /* !CONFIG_ACPI */
+
+#endif /* _PORTDRV_H_ */
diff --git a/drivers/pci/pcie/portdrv_acpi.c b/drivers/pci/pcie/portdrv_acpi.c
new file mode 100644
index 00000000..a86b56e5
--- /dev/null
+++ b/drivers/pci/pcie/portdrv_acpi.c
@@ -0,0 +1,62 @@
+/*
+ * PCIe Port Native Services Support, ACPI-Related Part
+ *
+ * Copyright (C) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License V2.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/acpi.h>
+#include <linux/pci-acpi.h>
+#include <linux/pcieport_if.h>
+
+#include "aer/aerdrv.h"
+#include "../pci.h"
+
+/**
+ * pcie_port_acpi_setup - Request the BIOS to release control of PCIe services.
+ * @port: PCIe Port service for a root port or event collector.
+ * @srv_mask: Bit mask of services that can be enabled for @port.
+ *
+ * Invoked when @port is identified as a PCIe port device.  To avoid conflicts
+ * with the BIOS PCIe port native services support requires the BIOS to yield
+ * control of these services to the kernel.  The mask of services that the BIOS
+ * allows to be enabled for @port is written to @srv_mask.
+ *
+ * NOTE: It turns out that we cannot do that for individual port services
+ * separately, because that would make some systems work incorrectly.
+ */
+int pcie_port_acpi_setup(struct pci_dev *port, int *srv_mask)
+{
+	struct acpi_pci_root *root;
+	acpi_handle handle;
+	u32 flags;
+
+	if (acpi_pci_disabled)
+		return 0;
+
+	handle = acpi_find_root_bridge_handle(port);
+	if (!handle)
+		return -EINVAL;
+
+	root = acpi_pci_find_root(handle);
+	if (!root)
+		return -ENODEV;
+
+	flags = root->osc_control_set;
+
+	*srv_mask = PCIE_PORT_SERVICE_VC;
+	if (flags & OSC_PCI_EXPRESS_NATIVE_HP_CONTROL)
+		*srv_mask |= PCIE_PORT_SERVICE_HP;
+	if (flags & OSC_PCI_EXPRESS_PME_CONTROL)
+		*srv_mask |= PCIE_PORT_SERVICE_PME;
+	if (flags & OSC_PCI_EXPRESS_AER_CONTROL)
+		*srv_mask |= PCIE_PORT_SERVICE_AER;
+
+	return 0;
+}
diff --git a/drivers/pci/pcie/portdrv_bus.c b/drivers/pci/pcie/portdrv_bus.c
new file mode 100644
index 00000000..18bf90f7
--- /dev/null
+++ b/drivers/pci/pcie/portdrv_bus.c
@@ -0,0 +1,55 @@
+/*
+ * File:	portdrv_bus.c
+ * Purpose:	PCI Express Port Bus Driver's Bus Overloading Functions
+ *
+ * Copyright (C) 2004 Intel
+ * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/pm.h>
+
+#include <linux/pcieport_if.h>
+#include "portdrv.h"
+
+static int pcie_port_bus_match(struct device *dev, struct device_driver *drv);
+
+struct bus_type pcie_port_bus_type = {
+	.name 		= "pci_express",
+	.match 		= pcie_port_bus_match,
+};
+EXPORT_SYMBOL_GPL(pcie_port_bus_type);
+
+static int pcie_port_bus_match(struct device *dev, struct device_driver *drv)
+{
+	struct pcie_device *pciedev;
+	struct pcie_port_service_driver *driver;
+
+	if (drv->bus != &pcie_port_bus_type || dev->bus != &pcie_port_bus_type)
+		return 0;
+
+	pciedev = to_pcie_device(dev);
+	driver = to_service_driver(drv);
+
+	if (driver->service != pciedev->service)
+		return 0;
+
+	if ((driver->port_type != PCIE_ANY_PORT) &&
+	    (driver->port_type != pciedev->port->pcie_type))
+		return 0;
+
+	return 1;
+}
+
+int pcie_port_bus_register(void)
+{
+	return bus_register(&pcie_port_bus_type);
+}
+
+void pcie_port_bus_unregister(void)
+{
+	bus_unregister(&pcie_port_bus_type);
+}
diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c
new file mode 100644
index 00000000..595654a1
--- /dev/null
+++ b/drivers/pci/pcie/portdrv_core.c
@@ -0,0 +1,560 @@
+/*
+ * File:	portdrv_core.c
+ * Purpose:	PCI Express Port Bus Driver's Core Functions
+ *
+ * Copyright (C) 2004 Intel
+ * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/pm.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/pcieport_if.h>
+#include <linux/aer.h>
+
+#include "../pci.h"
+#include "portdrv.h"
+
+/**
+ * release_pcie_device - free PCI Express port service device structure
+ * @dev: Port service device to release
+ *
+ * Invoked automatically when device is being removed in response to
+ * device_unregister(dev).  Release all resources being claimed.
+ */
+static void release_pcie_device(struct device *dev)
+{
+	kfree(to_pcie_device(dev));
+}
+
+/**
+ * pcie_port_msix_add_entry - add entry to given array of MSI-X entries
+ * @entries: Array of MSI-X entries
+ * @new_entry: Index of the entry to add to the array
+ * @nr_entries: Number of entries aleady in the array
+ *
+ * Return value: Position of the added entry in the array
+ */
+static int pcie_port_msix_add_entry(
+	struct msix_entry *entries, int new_entry, int nr_entries)
+{
+	int j;
+
+	for (j = 0; j < nr_entries; j++)
+		if (entries[j].entry == new_entry)
+			return j;
+
+	entries[j].entry = new_entry;
+	return j;
+}
+
+/**
+ * pcie_port_enable_msix - try to set up MSI-X as interrupt mode for given port
+ * @dev: PCI Express port to handle
+ * @vectors: Array of interrupt vectors to populate
+ * @mask: Bitmask of port capabilities returned by get_port_device_capability()
+ *
+ * Return value: 0 on success, error code on failure
+ */
+static int pcie_port_enable_msix(struct pci_dev *dev, int *vectors, int mask)
+{
+	struct msix_entry *msix_entries;
+	int idx[PCIE_PORT_DEVICE_MAXSERVICES];
+	int nr_entries, status, pos, i, nvec;
+	u16 reg16;
+	u32 reg32;
+
+	nr_entries = pci_msix_table_size(dev);
+	if (!nr_entries)
+		return -EINVAL;
+	if (nr_entries > PCIE_PORT_MAX_MSIX_ENTRIES)
+		nr_entries = PCIE_PORT_MAX_MSIX_ENTRIES;
+
+	msix_entries = kzalloc(sizeof(*msix_entries) * nr_entries, GFP_KERNEL);
+	if (!msix_entries)
+		return -ENOMEM;
+
+	/*
+	 * Allocate as many entries as the port wants, so that we can check
+	 * which of them will be useful.  Moreover, if nr_entries is correctly
+	 * equal to the number of entries this port actually uses, we'll happily
+	 * go through without any tricks.
+	 */
+	for (i = 0; i < nr_entries; i++)
+		msix_entries[i].entry = i;
+
+	status = pci_enable_msix(dev, msix_entries, nr_entries);
+	if (status)
+		goto Exit;
+
+	for (i = 0; i < PCIE_PORT_DEVICE_MAXSERVICES; i++)
+		idx[i] = -1;
+	status = -EIO;
+	nvec = 0;
+
+	if (mask & (PCIE_PORT_SERVICE_PME | PCIE_PORT_SERVICE_HP)) {
+		int entry;
+
+		/*
+		 * The code below follows the PCI Express Base Specification 2.0
+		 * stating in Section 6.1.6 that "PME and Hot-Plug Event
+		 * interrupts (when both are implemented) always share the same
+		 * MSI or MSI-X vector, as indicated by the Interrupt Message
+		 * Number field in the PCI Express Capabilities register", where
+		 * according to Section 7.8.2 of the specification "For MSI-X,
+		 * the value in this field indicates which MSI-X Table entry is
+		 * used to generate the interrupt message."
+		 */
+		pos = pci_pcie_cap(dev);
+		pci_read_config_word(dev, pos + PCI_EXP_FLAGS, &reg16);
+		entry = (reg16 & PCI_EXP_FLAGS_IRQ) >> 9;
+		if (entry >= nr_entries)
+			goto Error;
+
+		i = pcie_port_msix_add_entry(msix_entries, entry, nvec);
+		if (i == nvec)
+			nvec++;
+
+		idx[PCIE_PORT_SERVICE_PME_SHIFT] = i;
+		idx[PCIE_PORT_SERVICE_HP_SHIFT] = i;
+	}
+
+	if (mask & PCIE_PORT_SERVICE_AER) {
+		int entry;
+
+		/*
+		 * The code below follows Section 7.10.10 of the PCI Express
+		 * Base Specification 2.0 stating that bits 31-27 of the Root
+		 * Error Status Register contain a value indicating which of the
+		 * MSI/MSI-X vectors assigned to the port is going to be used
+		 * for AER, where "For MSI-X, the value in this register
+		 * indicates which MSI-X Table entry is used to generate the
+		 * interrupt message."
+		 */
+		pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+		pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &reg32);
+		entry = reg32 >> 27;
+		if (entry >= nr_entries)
+			goto Error;
+
+		i = pcie_port_msix_add_entry(msix_entries, entry, nvec);
+		if (i == nvec)
+			nvec++;
+
+		idx[PCIE_PORT_SERVICE_AER_SHIFT] = i;
+	}
+
+	/*
+	 * If nvec is equal to the allocated number of entries, we can just use
+	 * what we have.  Otherwise, the port has some extra entries not for the
+	 * services we know and we need to work around that.
+	 */
+	if (nvec == nr_entries) {
+		status = 0;
+	} else {
+		/* Drop the temporary MSI-X setup */
+		pci_disable_msix(dev);
+
+		/* Now allocate the MSI-X vectors for real */
+		status = pci_enable_msix(dev, msix_entries, nvec);
+		if (status)
+			goto Exit;
+	}
+
+	for (i = 0; i < PCIE_PORT_DEVICE_MAXSERVICES; i++)
+		vectors[i] = idx[i] >= 0 ? msix_entries[idx[i]].vector : -1;
+
+ Exit:
+	kfree(msix_entries);
+	return status;
+
+ Error:
+	pci_disable_msix(dev);
+	goto Exit;
+}
+
+/**
+ * init_service_irqs - initialize irqs for PCI Express port services
+ * @dev: PCI Express port to handle
+ * @irqs: Array of irqs to populate
+ * @mask: Bitmask of port capabilities returned by get_port_device_capability()
+ *
+ * Return value: Interrupt mode associated with the port
+ */
+static int init_service_irqs(struct pci_dev *dev, int *irqs, int mask)
+{
+	int i, irq = -1;
+
+	/* We have to use INTx if MSI cannot be used for PCIe PME. */
+	if ((mask & PCIE_PORT_SERVICE_PME) && pcie_pme_no_msi()) {
+		if (dev->pin)
+			irq = dev->irq;
+		goto no_msi;
+	}
+
+	/* Try to use MSI-X if supported */
+	if (!pcie_port_enable_msix(dev, irqs, mask))
+		return 0;
+
+	/* We're not going to use MSI-X, so try MSI and fall back to INTx */
+	if (!pci_enable_msi(dev) || dev->pin)
+		irq = dev->irq;
+
+ no_msi:
+	for (i = 0; i < PCIE_PORT_DEVICE_MAXSERVICES; i++)
+		irqs[i] = irq;
+	irqs[PCIE_PORT_SERVICE_VC_SHIFT] = -1;
+
+	if (irq < 0)
+		return -ENODEV;
+	return 0;
+}
+
+static void cleanup_service_irqs(struct pci_dev *dev)
+{
+	if (dev->msix_enabled)
+		pci_disable_msix(dev);
+	else if (dev->msi_enabled)
+		pci_disable_msi(dev);
+}
+
+/**
+ * get_port_device_capability - discover capabilities of a PCI Express port
+ * @dev: PCI Express port to examine
+ *
+ * The capabilities are read from the port's PCI Express configuration registers
+ * as described in PCI Express Base Specification 1.0a sections 7.8.2, 7.8.9 and
+ * 7.9 - 7.11.
+ *
+ * Return value: Bitmask of discovered port capabilities
+ */
+static int get_port_device_capability(struct pci_dev *dev)
+{
+	int services = 0, pos;
+	u16 reg16;
+	u32 reg32;
+	int cap_mask;
+	int err;
+
+	if (pcie_ports_disabled)
+		return 0;
+
+	err = pcie_port_platform_notify(dev, &cap_mask);
+	if (!pcie_ports_auto) {
+		cap_mask = PCIE_PORT_SERVICE_PME | PCIE_PORT_SERVICE_HP
+				| PCIE_PORT_SERVICE_VC;
+		if (pci_aer_available())
+			cap_mask |= PCIE_PORT_SERVICE_AER;
+	} else if (err) {
+			return 0;
+	}
+
+	pos = pci_pcie_cap(dev);
+	pci_read_config_word(dev, pos + PCI_EXP_FLAGS, &reg16);
+	/* Hot-Plug Capable */
+	if ((cap_mask & PCIE_PORT_SERVICE_HP) && (reg16 & PCI_EXP_FLAGS_SLOT)) {
+		pci_read_config_dword(dev, pos + PCI_EXP_SLTCAP, &reg32);
+		if (reg32 & PCI_EXP_SLTCAP_HPC) {
+			services |= PCIE_PORT_SERVICE_HP;
+			/*
+			 * Disable hot-plug interrupts in case they have been
+			 * enabled by the BIOS and the hot-plug service driver
+			 * is not loaded.
+			 */
+			pos += PCI_EXP_SLTCTL;
+			pci_read_config_word(dev, pos, &reg16);
+			reg16 &= ~(PCI_EXP_SLTCTL_CCIE | PCI_EXP_SLTCTL_HPIE);
+			pci_write_config_word(dev, pos, reg16);
+		}
+	}
+	/* AER capable */
+	if ((cap_mask & PCIE_PORT_SERVICE_AER)
+	    && pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR)) {
+		services |= PCIE_PORT_SERVICE_AER;
+		/*
+		 * Disable AER on this port in case it's been enabled by the
+		 * BIOS (the AER service driver will enable it when necessary).
+		 */
+		pci_disable_pcie_error_reporting(dev);
+	}
+	/* VC support */
+	if (pci_find_ext_capability(dev, PCI_EXT_CAP_ID_VC))
+		services |= PCIE_PORT_SERVICE_VC;
+	/* Root ports are capable of generating PME too */
+	if ((cap_mask & PCIE_PORT_SERVICE_PME)
+	    && dev->pcie_type == PCI_EXP_TYPE_ROOT_PORT) {
+		services |= PCIE_PORT_SERVICE_PME;
+		/*
+		 * Disable PME interrupt on this port in case it's been enabled
+		 * by the BIOS (the PME service driver will enable it when
+		 * necessary).
+		 */
+		pcie_pme_interrupt_enable(dev, false);
+	}
+
+	return services;
+}
+
+/**
+ * pcie_device_init - allocate and initialize PCI Express port service device
+ * @pdev: PCI Express port to associate the service device with
+ * @service: Type of service to associate with the service device
+ * @irq: Interrupt vector to associate with the service device
+ */
+static int pcie_device_init(struct pci_dev *pdev, int service, int irq)
+{
+	int retval;
+	struct pcie_device *pcie;
+	struct device *device;
+
+	pcie = kzalloc(sizeof(*pcie), GFP_KERNEL);
+	if (!pcie)
+		return -ENOMEM;
+	pcie->port = pdev;
+	pcie->irq = irq;
+	pcie->service = service;
+
+	/* Initialize generic device interface */
+	device = &pcie->device;
+	device->bus = &pcie_port_bus_type;
+	device->release = release_pcie_device;	/* callback to free pcie dev */
+	dev_set_name(device, "%s:pcie%02x",
+		     pci_name(pdev),
+		     get_descriptor_id(pdev->pcie_type, service));
+	device->parent = &pdev->dev;
+	device_enable_async_suspend(device);
+
+	retval = device_register(device);
+	if (retval)
+		kfree(pcie);
+	else
+		get_device(device);
+	return retval;
+}
+
+/**
+ * pcie_port_device_register - register PCI Express port
+ * @dev: PCI Express port to register
+ *
+ * Allocate the port extension structure and register services associated with
+ * the port.
+ */
+int pcie_port_device_register(struct pci_dev *dev)
+{
+	int status, capabilities, i, nr_service;
+	int irqs[PCIE_PORT_DEVICE_MAXSERVICES];
+
+	/* Enable PCI Express port device */
+	status = pci_enable_device(dev);
+	if (status)
+		return status;
+
+	/* Get and check PCI Express port services */
+	capabilities = get_port_device_capability(dev);
+	if (!capabilities)
+		return 0;
+
+	pci_set_master(dev);
+	/*
+	 * Initialize service irqs. Don't use service devices that
+	 * require interrupts if there is no way to generate them.
+	 */
+	status = init_service_irqs(dev, irqs, capabilities);
+	if (status) {
+		capabilities &= PCIE_PORT_SERVICE_VC;
+		if (!capabilities)
+			goto error_disable;
+	}
+
+	/* Allocate child services if any */
+	status = -ENODEV;
+	nr_service = 0;
+	for (i = 0; i < PCIE_PORT_DEVICE_MAXSERVICES; i++) {
+		int service = 1 << i;
+		if (!(capabilities & service))
+			continue;
+		if (!pcie_device_init(dev, service, irqs[i]))
+			nr_service++;
+	}
+	if (!nr_service)
+		goto error_cleanup_irqs;
+
+	return 0;
+
+error_cleanup_irqs:
+	cleanup_service_irqs(dev);
+error_disable:
+	pci_disable_device(dev);
+	return status;
+}
+
+#ifdef CONFIG_PM
+static int suspend_iter(struct device *dev, void *data)
+{
+	struct pcie_port_service_driver *service_driver;
+
+	if ((dev->bus == &pcie_port_bus_type) && dev->driver) {
+		service_driver = to_service_driver(dev->driver);
+		if (service_driver->suspend)
+			service_driver->suspend(to_pcie_device(dev));
+	}
+	return 0;
+}
+
+/**
+ * pcie_port_device_suspend - suspend port services associated with a PCIe port
+ * @dev: PCI Express port to handle
+ */
+int pcie_port_device_suspend(struct device *dev)
+{
+	return device_for_each_child(dev, NULL, suspend_iter);
+}
+
+static int resume_iter(struct device *dev, void *data)
+{
+	struct pcie_port_service_driver *service_driver;
+
+	if ((dev->bus == &pcie_port_bus_type) &&
+	    (dev->driver)) {
+		service_driver = to_service_driver(dev->driver);
+		if (service_driver->resume)
+			service_driver->resume(to_pcie_device(dev));
+	}
+	return 0;
+}
+
+/**
+ * pcie_port_device_suspend - resume port services associated with a PCIe port
+ * @dev: PCI Express port to handle
+ */
+int pcie_port_device_resume(struct device *dev)
+{
+	return device_for_each_child(dev, NULL, resume_iter);
+}
+#endif /* PM */
+
+static int remove_iter(struct device *dev, void *data)
+{
+	if (dev->bus == &pcie_port_bus_type) {
+		put_device(dev);
+		device_unregister(dev);
+	}
+	return 0;
+}
+
+/**
+ * pcie_port_device_remove - unregister PCI Express port service devices
+ * @dev: PCI Express port the service devices to unregister are associated with
+ *
+ * Remove PCI Express port service devices associated with given port and
+ * disable MSI-X or MSI for the port.
+ */
+void pcie_port_device_remove(struct pci_dev *dev)
+{
+	device_for_each_child(&dev->dev, NULL, remove_iter);
+	cleanup_service_irqs(dev);
+	pci_disable_device(dev);
+}
+
+/**
+ * pcie_port_probe_service - probe driver for given PCI Express port service
+ * @dev: PCI Express port service device to probe against
+ *
+ * If PCI Express port service driver is registered with
+ * pcie_port_service_register(), this function will be called by the driver core
+ * whenever match is found between the driver and a port service device.
+ */
+static int pcie_port_probe_service(struct device *dev)
+{
+	struct pcie_device *pciedev;
+	struct pcie_port_service_driver *driver;
+	int status;
+
+	if (!dev || !dev->driver)
+		return -ENODEV;
+
+	driver = to_service_driver(dev->driver);
+	if (!driver || !driver->probe)
+		return -ENODEV;
+
+	pciedev = to_pcie_device(dev);
+	status = driver->probe(pciedev);
+	if (!status) {
+		dev_printk(KERN_DEBUG, dev, "service driver %s loaded\n",
+			driver->name);
+		get_device(dev);
+	}
+	return status;
+}
+
+/**
+ * pcie_port_remove_service - detach driver from given PCI Express port service
+ * @dev: PCI Express port service device to handle
+ *
+ * If PCI Express port service driver is registered with
+ * pcie_port_service_register(), this function will be called by the driver core
+ * when device_unregister() is called for the port service device associated
+ * with the driver.
+ */
+static int pcie_port_remove_service(struct device *dev)
+{
+	struct pcie_device *pciedev;
+	struct pcie_port_service_driver *driver;
+
+	if (!dev || !dev->driver)
+		return 0;
+
+	pciedev = to_pcie_device(dev);
+	driver = to_service_driver(dev->driver);
+	if (driver && driver->remove) {
+		dev_printk(KERN_DEBUG, dev, "unloading service driver %s\n",
+			driver->name);
+		driver->remove(pciedev);
+		put_device(dev);
+	}
+	return 0;
+}
+
+/**
+ * pcie_port_shutdown_service - shut down given PCI Express port service
+ * @dev: PCI Express port service device to handle
+ *
+ * If PCI Express port service driver is registered with
+ * pcie_port_service_register(), this function will be called by the driver core
+ * when device_shutdown() is called for the port service device associated
+ * with the driver.
+ */
+static void pcie_port_shutdown_service(struct device *dev) {}
+
+/**
+ * pcie_port_service_register - register PCI Express port service driver
+ * @new: PCI Express port service driver to register
+ */
+int pcie_port_service_register(struct pcie_port_service_driver *new)
+{
+	if (pcie_ports_disabled)
+		return -ENODEV;
+
+	new->driver.name = (char *)new->name;
+	new->driver.bus = &pcie_port_bus_type;
+	new->driver.probe = pcie_port_probe_service;
+	new->driver.remove = pcie_port_remove_service;
+	new->driver.shutdown = pcie_port_shutdown_service;
+
+	return driver_register(&new->driver);
+}
+EXPORT_SYMBOL(pcie_port_service_register);
+
+/**
+ * pcie_port_service_unregister - unregister PCI Express port service driver
+ * @drv: PCI Express port service driver to unregister
+ */
+void pcie_port_service_unregister(struct pcie_port_service_driver *drv)
+{
+	driver_unregister(&drv->driver);
+}
+EXPORT_SYMBOL(pcie_port_service_unregister);
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
new file mode 100644
index 00000000..e0610bda
--- /dev/null
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -0,0 +1,378 @@
+/*
+ * File:	portdrv_pci.c
+ * Purpose:	PCI Express Port Bus Driver
+ *
+ * Copyright (C) 2004 Intel
+ * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/pm.h>
+#include <linux/init.h>
+#include <linux/pcieport_if.h>
+#include <linux/aer.h>
+#include <linux/dmi.h>
+#include <linux/pci-aspm.h>
+
+#include "portdrv.h"
+#include "aer/aerdrv.h"
+
+/*
+ * Version Information
+ */
+#define DRIVER_VERSION "v1.0"
+#define DRIVER_AUTHOR "tom.l.nguyen@intel.com"
+#define DRIVER_DESC "PCIe Port Bus Driver"
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+
+/* If this switch is set, PCIe port native services should not be enabled. */
+bool pcie_ports_disabled;
+
+/*
+ * If this switch is set, ACPI _OSC will be used to determine whether or not to
+ * enable PCIe port native services.
+ */
+bool pcie_ports_auto = true;
+
+static int __init pcie_port_setup(char *str)
+{
+	if (!strncmp(str, "compat", 6)) {
+		pcie_ports_disabled = true;
+	} else if (!strncmp(str, "native", 6)) {
+		pcie_ports_disabled = false;
+		pcie_ports_auto = false;
+	} else if (!strncmp(str, "auto", 4)) {
+		pcie_ports_disabled = false;
+		pcie_ports_auto = true;
+	}
+
+	return 1;
+}
+__setup("pcie_ports=", pcie_port_setup);
+
+/* global data */
+
+/**
+ * pcie_clear_root_pme_status - Clear root port PME interrupt status.
+ * @dev: PCIe root port or event collector.
+ */
+void pcie_clear_root_pme_status(struct pci_dev *dev)
+{
+	int rtsta_pos;
+	u32 rtsta;
+
+	rtsta_pos = pci_pcie_cap(dev) + PCI_EXP_RTSTA;
+
+	pci_read_config_dword(dev, rtsta_pos, &rtsta);
+	rtsta |= PCI_EXP_RTSTA_PME;
+	pci_write_config_dword(dev, rtsta_pos, rtsta);
+}
+
+static int pcie_portdrv_restore_config(struct pci_dev *dev)
+{
+	int retval;
+
+	retval = pci_enable_device(dev);
+	if (retval)
+		return retval;
+	pci_set_master(dev);
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int pcie_port_resume_noirq(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	/*
+	 * Some BIOSes forget to clear Root PME Status bits after system wakeup
+	 * which breaks ACPI-based runtime wakeup on PCI Express, so clear those
+	 * bits now just in case (shouldn't hurt).
+	 */
+	if(pdev->pcie_type == PCI_EXP_TYPE_ROOT_PORT)
+		pcie_clear_root_pme_status(pdev);
+	return 0;
+}
+
+static const struct dev_pm_ops pcie_portdrv_pm_ops = {
+	.suspend	= pcie_port_device_suspend,
+	.resume		= pcie_port_device_resume,
+	.freeze		= pcie_port_device_suspend,
+	.thaw		= pcie_port_device_resume,
+	.poweroff	= pcie_port_device_suspend,
+	.restore	= pcie_port_device_resume,
+	.resume_noirq	= pcie_port_resume_noirq,
+};
+
+#define PCIE_PORTDRV_PM_OPS	(&pcie_portdrv_pm_ops)
+
+#else /* !PM */
+
+#define PCIE_PORTDRV_PM_OPS	NULL
+#endif /* !PM */
+
+/*
+ * pcie_portdrv_probe - Probe PCI-Express port devices
+ * @dev: PCI-Express port device being probed
+ *
+ * If detected invokes the pcie_port_device_register() method for
+ * this port device.
+ *
+ */
+static int __devinit pcie_portdrv_probe(struct pci_dev *dev,
+					const struct pci_device_id *id)
+{
+	int status;
+
+	if (!pci_is_pcie(dev) ||
+	    ((dev->pcie_type != PCI_EXP_TYPE_ROOT_PORT) &&
+	     (dev->pcie_type != PCI_EXP_TYPE_UPSTREAM) &&
+	     (dev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM)))
+		return -ENODEV;
+
+	if (!dev->irq && dev->pin) {
+		dev_warn(&dev->dev, "device [%04x:%04x] has invalid IRQ; "
+			 "check vendor BIOS\n", dev->vendor, dev->device);
+	}
+	status = pcie_port_device_register(dev);
+	if (status)
+		return status;
+
+	pci_save_state(dev);
+
+	return 0;
+}
+
+static void pcie_portdrv_remove(struct pci_dev *dev)
+{
+	pcie_port_device_remove(dev);
+	pci_disable_device(dev);
+}
+
+static int error_detected_iter(struct device *device, void *data)
+{
+	struct pcie_device *pcie_device;
+	struct pcie_port_service_driver *driver;
+	struct aer_broadcast_data *result_data;
+	pci_ers_result_t status;
+
+	result_data = (struct aer_broadcast_data *) data;
+
+	if (device->bus == &pcie_port_bus_type && device->driver) {
+		driver = to_service_driver(device->driver);
+		if (!driver ||
+			!driver->err_handler ||
+			!driver->err_handler->error_detected)
+			return 0;
+
+		pcie_device = to_pcie_device(device);
+
+		/* Forward error detected message to service drivers */
+		status = driver->err_handler->error_detected(
+			pcie_device->port,
+			result_data->state);
+		result_data->result =
+			merge_result(result_data->result, status);
+	}
+
+	return 0;
+}
+
+static pci_ers_result_t pcie_portdrv_error_detected(struct pci_dev *dev,
+					enum pci_channel_state error)
+{
+	struct aer_broadcast_data data = {error, PCI_ERS_RESULT_CAN_RECOVER};
+	int ret;
+
+	/* can not fail */
+	ret = device_for_each_child(&dev->dev, &data, error_detected_iter);
+
+	return data.result;
+}
+
+static int mmio_enabled_iter(struct device *device, void *data)
+{
+	struct pcie_device *pcie_device;
+	struct pcie_port_service_driver *driver;
+	pci_ers_result_t status, *result;
+
+	result = (pci_ers_result_t *) data;
+
+	if (device->bus == &pcie_port_bus_type && device->driver) {
+		driver = to_service_driver(device->driver);
+		if (driver &&
+			driver->err_handler &&
+			driver->err_handler->mmio_enabled) {
+			pcie_device = to_pcie_device(device);
+
+			/* Forward error message to service drivers */
+			status = driver->err_handler->mmio_enabled(
+					pcie_device->port);
+			*result = merge_result(*result, status);
+		}
+	}
+
+	return 0;
+}
+
+static pci_ers_result_t pcie_portdrv_mmio_enabled(struct pci_dev *dev)
+{
+	pci_ers_result_t status = PCI_ERS_RESULT_RECOVERED;
+	int retval;
+
+	/* get true return value from &status */
+	retval = device_for_each_child(&dev->dev, &status, mmio_enabled_iter);
+	return status;
+}
+
+static int slot_reset_iter(struct device *device, void *data)
+{
+	struct pcie_device *pcie_device;
+	struct pcie_port_service_driver *driver;
+	pci_ers_result_t status, *result;
+
+	result = (pci_ers_result_t *) data;
+
+	if (device->bus == &pcie_port_bus_type && device->driver) {
+		driver = to_service_driver(device->driver);
+		if (driver &&
+			driver->err_handler &&
+			driver->err_handler->slot_reset) {
+			pcie_device = to_pcie_device(device);
+
+			/* Forward error message to service drivers */
+			status = driver->err_handler->slot_reset(
+					pcie_device->port);
+			*result = merge_result(*result, status);
+		}
+	}
+
+	return 0;
+}
+
+static pci_ers_result_t pcie_portdrv_slot_reset(struct pci_dev *dev)
+{
+	pci_ers_result_t status = PCI_ERS_RESULT_RECOVERED;
+	int retval;
+
+	/* If fatal, restore cfg space for possible link reset at upstream */
+	if (dev->error_state == pci_channel_io_frozen) {
+		dev->state_saved = true;
+		pci_restore_state(dev);
+		pcie_portdrv_restore_config(dev);
+		pci_enable_pcie_error_reporting(dev);
+	}
+
+	/* get true return value from &status */
+	retval = device_for_each_child(&dev->dev, &status, slot_reset_iter);
+
+	return status;
+}
+
+static int resume_iter(struct device *device, void *data)
+{
+	struct pcie_device *pcie_device;
+	struct pcie_port_service_driver *driver;
+
+	if (device->bus == &pcie_port_bus_type && device->driver) {
+		driver = to_service_driver(device->driver);
+		if (driver &&
+			driver->err_handler &&
+			driver->err_handler->resume) {
+			pcie_device = to_pcie_device(device);
+
+			/* Forward error message to service drivers */
+			driver->err_handler->resume(pcie_device->port);
+		}
+	}
+
+	return 0;
+}
+
+static void pcie_portdrv_err_resume(struct pci_dev *dev)
+{
+	int retval;
+	/* nothing to do with error value, if it ever happens */
+	retval = device_for_each_child(&dev->dev, NULL, resume_iter);
+}
+
+/*
+ * LINUX Device Driver Model
+ */
+static const struct pci_device_id port_pci_ids[] = { {
+	/* handle any PCI-Express port */
+	PCI_DEVICE_CLASS(((PCI_CLASS_BRIDGE_PCI << 8) | 0x00), ~0),
+	}, { /* end: all zeroes */ }
+};
+MODULE_DEVICE_TABLE(pci, port_pci_ids);
+
+static struct pci_error_handlers pcie_portdrv_err_handler = {
+		.error_detected = pcie_portdrv_error_detected,
+		.mmio_enabled = pcie_portdrv_mmio_enabled,
+		.slot_reset = pcie_portdrv_slot_reset,
+		.resume = pcie_portdrv_err_resume,
+};
+
+static struct pci_driver pcie_portdriver = {
+	.name		= "pcieport",
+	.id_table	= &port_pci_ids[0],
+
+	.probe		= pcie_portdrv_probe,
+	.remove		= pcie_portdrv_remove,
+
+	.err_handler 	= &pcie_portdrv_err_handler,
+
+	.driver.pm 	= PCIE_PORTDRV_PM_OPS,
+};
+
+static int __init dmi_pcie_pme_disable_msi(const struct dmi_system_id *d)
+{
+	pr_notice("%s detected: will not use MSI for PCIe PME signaling\n",
+			d->ident);
+	pcie_pme_disable_msi();
+	return 0;
+}
+
+static struct dmi_system_id __initdata pcie_portdrv_dmi_table[] = {
+	/*
+	 * Boxes that should not use MSI for PCIe PME signaling.
+	 */
+	{
+	 .callback = dmi_pcie_pme_disable_msi,
+	 .ident = "MSI Wind U-100",
+	 .matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR,
+		     		"MICRO-STAR INTERNATIONAL CO., LTD"),
+		     DMI_MATCH(DMI_PRODUCT_NAME, "U-100"),
+		     },
+	 },
+	 {}
+};
+
+static int __init pcie_portdrv_init(void)
+{
+	int retval;
+
+	if (pcie_ports_disabled)
+		return pci_register_driver(&pcie_portdriver);
+
+	dmi_check_system(pcie_portdrv_dmi_table);
+
+	retval = pcie_port_bus_register();
+	if (retval) {
+		printk(KERN_WARNING "PCIE: bus_register error: %d\n", retval);
+		goto out;
+	}
+	retval = pci_register_driver(&pcie_portdriver);
+	if (retval)
+		pcie_port_bus_unregister();
+ out:
+	return retval;
+}
+
+module_init(pcie_portdrv_init);
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
new file mode 100644
index 00000000..5b3771a7
--- /dev/null
+++ b/drivers/pci/probe.c
@@ -0,0 +1,1520 @@
+/*
+ * probe.c - PCI detection and setup code
+ */
+
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/cpumask.h>
+#include <linux/pci-aspm.h>
+#include "pci.h"
+
+#define CARDBUS_LATENCY_TIMER	176	/* secondary latency timer */
+#define CARDBUS_RESERVE_BUSNR	3
+
+/* Ugh.  Need to stop exporting this to modules. */
+LIST_HEAD(pci_root_buses);
+EXPORT_SYMBOL(pci_root_buses);
+
+
+static int find_anything(struct device *dev, void *data)
+{
+	return 1;
+}
+
+/*
+ * Some device drivers need know if pci is initiated.
+ * Basically, we think pci is not initiated when there
+ * is no device to be found on the pci_bus_type.
+ */
+int no_pci_devices(void)
+{
+	struct device *dev;
+	int no_devices;
+
+	dev = bus_find_device(&pci_bus_type, NULL, NULL, find_anything);
+	no_devices = (dev == NULL);
+	put_device(dev);
+	return no_devices;
+}
+EXPORT_SYMBOL(no_pci_devices);
+
+/*
+ * PCI Bus Class
+ */
+static void release_pcibus_dev(struct device *dev)
+{
+	struct pci_bus *pci_bus = to_pci_bus(dev);
+
+	if (pci_bus->bridge)
+		put_device(pci_bus->bridge);
+	pci_bus_remove_resources(pci_bus);
+	kfree(pci_bus);
+}
+
+static struct class pcibus_class = {
+	.name		= "pci_bus",
+	.dev_release	= &release_pcibus_dev,
+	.dev_attrs	= pcibus_dev_attrs,
+};
+
+static int __init pcibus_class_init(void)
+{
+	return class_register(&pcibus_class);
+}
+postcore_initcall(pcibus_class_init);
+
+/*
+ * Translate the low bits of the PCI base
+ * to the resource type
+ */
+static inline unsigned int pci_calc_resource_flags(unsigned int flags)
+{
+	if (flags & PCI_BASE_ADDRESS_SPACE_IO)
+		return IORESOURCE_IO;
+
+	if (flags & PCI_BASE_ADDRESS_MEM_PREFETCH)
+		return IORESOURCE_MEM | IORESOURCE_PREFETCH;
+
+	return IORESOURCE_MEM;
+}
+
+static u64 pci_size(u64 base, u64 maxbase, u64 mask)
+{
+	u64 size = mask & maxbase;	/* Find the significant bits */
+	if (!size)
+		return 0;
+
+	/* Get the lowest of them to find the decode size, and
+	   from that the extent.  */
+	size = (size & ~(size-1)) - 1;
+
+	/* base == maxbase can be valid only if the BAR has
+	   already been programmed with all 1s.  */
+	if (base == maxbase && ((base | size) & mask) != mask)
+		return 0;
+
+	return size;
+}
+
+static inline enum pci_bar_type decode_bar(struct resource *res, u32 bar)
+{
+	if ((bar & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) {
+		res->flags = bar & ~PCI_BASE_ADDRESS_IO_MASK;
+		return pci_bar_io;
+	}
+
+	res->flags = bar & ~PCI_BASE_ADDRESS_MEM_MASK;
+
+	if (res->flags & PCI_BASE_ADDRESS_MEM_TYPE_64)
+		return pci_bar_mem64;
+	return pci_bar_mem32;
+}
+
+/**
+ * pci_read_base - read a PCI BAR
+ * @dev: the PCI device
+ * @type: type of the BAR
+ * @res: resource buffer to be filled in
+ * @pos: BAR position in the config space
+ *
+ * Returns 1 if the BAR is 64-bit, or 0 if 32-bit.
+ */
+int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
+			struct resource *res, unsigned int pos)
+{
+	u32 l, sz, mask;
+	u16 orig_cmd;
+
+	mask = type ? PCI_ROM_ADDRESS_MASK : ~0;
+
+	if (!dev->mmio_always_on) {
+		pci_read_config_word(dev, PCI_COMMAND, &orig_cmd);
+		pci_write_config_word(dev, PCI_COMMAND,
+			orig_cmd & ~(PCI_COMMAND_MEMORY | PCI_COMMAND_IO));
+	}
+
+	res->name = pci_name(dev);
+
+	pci_read_config_dword(dev, pos, &l);
+	pci_write_config_dword(dev, pos, l | mask);
+	pci_read_config_dword(dev, pos, &sz);
+	pci_write_config_dword(dev, pos, l);
+
+	if (!dev->mmio_always_on)
+		pci_write_config_word(dev, PCI_COMMAND, orig_cmd);
+
+	/*
+	 * All bits set in sz means the device isn't working properly.
+	 * If the BAR isn't implemented, all bits must be 0.  If it's a
+	 * memory BAR or a ROM, bit 0 must be clear; if it's an io BAR, bit
+	 * 1 must be clear.
+	 */
+	if (!sz || sz == 0xffffffff)
+		goto fail;
+
+	/*
+	 * I don't know how l can have all bits set.  Copied from old code.
+	 * Maybe it fixes a bug on some ancient platform.
+	 */
+	if (l == 0xffffffff)
+		l = 0;
+
+	if (type == pci_bar_unknown) {
+		type = decode_bar(res, l);
+		res->flags |= pci_calc_resource_flags(l) | IORESOURCE_SIZEALIGN;
+		if (type == pci_bar_io) {
+			l &= PCI_BASE_ADDRESS_IO_MASK;
+			mask = PCI_BASE_ADDRESS_IO_MASK & (u32) IO_SPACE_LIMIT;
+		} else {
+			l &= PCI_BASE_ADDRESS_MEM_MASK;
+			mask = (u32)PCI_BASE_ADDRESS_MEM_MASK;
+		}
+	} else {
+		res->flags |= (l & IORESOURCE_ROM_ENABLE);
+		l &= PCI_ROM_ADDRESS_MASK;
+		mask = (u32)PCI_ROM_ADDRESS_MASK;
+	}
+
+	if (type == pci_bar_mem64) {
+		u64 l64 = l;
+		u64 sz64 = sz;
+		u64 mask64 = mask | (u64)~0 << 32;
+
+		pci_read_config_dword(dev, pos + 4, &l);
+		pci_write_config_dword(dev, pos + 4, ~0);
+		pci_read_config_dword(dev, pos + 4, &sz);
+		pci_write_config_dword(dev, pos + 4, l);
+
+		l64 |= ((u64)l << 32);
+		sz64 |= ((u64)sz << 32);
+
+		sz64 = pci_size(l64, sz64, mask64);
+
+		if (!sz64)
+			goto fail;
+
+		if ((sizeof(resource_size_t) < 8) && (sz64 > 0x100000000ULL)) {
+			dev_err(&dev->dev, "reg %x: can't handle 64-bit BAR\n",
+				pos);
+			goto fail;
+		}
+
+		res->flags |= IORESOURCE_MEM_64;
+		if ((sizeof(resource_size_t) < 8) && l) {
+			/* Address above 32-bit boundary; disable the BAR */
+			pci_write_config_dword(dev, pos, 0);
+			pci_write_config_dword(dev, pos + 4, 0);
+			res->start = 0;
+			res->end = sz64;
+		} else {
+			res->start = l64;
+			res->end = l64 + sz64;
+			dev_printk(KERN_DEBUG, &dev->dev, "reg %x: %pR\n",
+				   pos, res);
+		}
+	} else {
+		sz = pci_size(l, sz, mask);
+
+		if (!sz)
+			goto fail;
+
+		res->start = l;
+		res->end = l + sz;
+
+		dev_printk(KERN_DEBUG, &dev->dev, "reg %x: %pR\n", pos, res);
+	}
+
+ out:
+	return (type == pci_bar_mem64) ? 1 : 0;
+ fail:
+	res->flags = 0;
+	goto out;
+}
+
+static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom)
+{
+	unsigned int pos, reg;
+
+	for (pos = 0; pos < howmany; pos++) {
+		struct resource *res = &dev->resource[pos];
+		reg = PCI_BASE_ADDRESS_0 + (pos << 2);
+		pos += __pci_read_base(dev, pci_bar_unknown, res, reg);
+	}
+
+	if (rom) {
+		struct resource *res = &dev->resource[PCI_ROM_RESOURCE];
+		dev->rom_base_reg = rom;
+		res->flags = IORESOURCE_MEM | IORESOURCE_PREFETCH |
+				IORESOURCE_READONLY | IORESOURCE_CACHEABLE |
+				IORESOURCE_SIZEALIGN;
+		__pci_read_base(dev, pci_bar_mem32, res, rom);
+	}
+}
+
+static void __devinit pci_read_bridge_io(struct pci_bus *child)
+{
+	struct pci_dev *dev = child->self;
+	u8 io_base_lo, io_limit_lo;
+	unsigned long base, limit;
+	struct resource *res;
+
+	res = child->resource[0];
+	pci_read_config_byte(dev, PCI_IO_BASE, &io_base_lo);
+	pci_read_config_byte(dev, PCI_IO_LIMIT, &io_limit_lo);
+	base = (io_base_lo & PCI_IO_RANGE_MASK) << 8;
+	limit = (io_limit_lo & PCI_IO_RANGE_MASK) << 8;
+
+	if ((io_base_lo & PCI_IO_RANGE_TYPE_MASK) == PCI_IO_RANGE_TYPE_32) {
+		u16 io_base_hi, io_limit_hi;
+		pci_read_config_word(dev, PCI_IO_BASE_UPPER16, &io_base_hi);
+		pci_read_config_word(dev, PCI_IO_LIMIT_UPPER16, &io_limit_hi);
+		base |= (io_base_hi << 16);
+		limit |= (io_limit_hi << 16);
+	}
+
+	if (base && base <= limit) {
+		res->flags = (io_base_lo & PCI_IO_RANGE_TYPE_MASK) | IORESOURCE_IO;
+		if (!res->start)
+			res->start = base;
+		if (!res->end)
+			res->end = limit + 0xfff;
+		dev_printk(KERN_DEBUG, &dev->dev, "  bridge window %pR\n", res);
+	} else {
+		dev_printk(KERN_DEBUG, &dev->dev,
+			 "  bridge window [io  %#06lx-%#06lx] (disabled)\n",
+				 base, limit);
+	}
+}
+
+static void __devinit pci_read_bridge_mmio(struct pci_bus *child)
+{
+	struct pci_dev *dev = child->self;
+	u16 mem_base_lo, mem_limit_lo;
+	unsigned long base, limit;
+	struct resource *res;
+
+	res = child->resource[1];
+	pci_read_config_word(dev, PCI_MEMORY_BASE, &mem_base_lo);
+	pci_read_config_word(dev, PCI_MEMORY_LIMIT, &mem_limit_lo);
+	base = (mem_base_lo & PCI_MEMORY_RANGE_MASK) << 16;
+	limit = (mem_limit_lo & PCI_MEMORY_RANGE_MASK) << 16;
+	if (base && base <= limit) {
+		res->flags = (mem_base_lo & PCI_MEMORY_RANGE_TYPE_MASK) | IORESOURCE_MEM;
+		res->start = base;
+		res->end = limit + 0xfffff;
+		dev_printk(KERN_DEBUG, &dev->dev, "  bridge window %pR\n", res);
+	} else {
+		dev_printk(KERN_DEBUG, &dev->dev,
+			"  bridge window [mem %#010lx-%#010lx] (disabled)\n",
+					 base, limit + 0xfffff);
+	}
+}
+
+static void __devinit pci_read_bridge_mmio_pref(struct pci_bus *child)
+{
+	struct pci_dev *dev = child->self;
+	u16 mem_base_lo, mem_limit_lo;
+	unsigned long base, limit;
+	struct resource *res;
+
+	res = child->resource[2];
+	pci_read_config_word(dev, PCI_PREF_MEMORY_BASE, &mem_base_lo);
+	pci_read_config_word(dev, PCI_PREF_MEMORY_LIMIT, &mem_limit_lo);
+	base = (mem_base_lo & PCI_PREF_RANGE_MASK) << 16;
+	limit = (mem_limit_lo & PCI_PREF_RANGE_MASK) << 16;
+
+	if ((mem_base_lo & PCI_PREF_RANGE_TYPE_MASK) == PCI_PREF_RANGE_TYPE_64) {
+		u32 mem_base_hi, mem_limit_hi;
+		pci_read_config_dword(dev, PCI_PREF_BASE_UPPER32, &mem_base_hi);
+		pci_read_config_dword(dev, PCI_PREF_LIMIT_UPPER32, &mem_limit_hi);
+
+		/*
+		 * Some bridges set the base > limit by default, and some
+		 * (broken) BIOSes do not initialize them.  If we find
+		 * this, just assume they are not being used.
+		 */
+		if (mem_base_hi <= mem_limit_hi) {
+#if BITS_PER_LONG == 64
+			base |= ((long) mem_base_hi) << 32;
+			limit |= ((long) mem_limit_hi) << 32;
+#else
+			if (mem_base_hi || mem_limit_hi) {
+				dev_err(&dev->dev, "can't handle 64-bit "
+					"address space for bridge\n");
+				return;
+			}
+#endif
+		}
+	}
+	if (base && base <= limit) {
+		res->flags = (mem_base_lo & PCI_PREF_RANGE_TYPE_MASK) |
+					 IORESOURCE_MEM | IORESOURCE_PREFETCH;
+		if (res->flags & PCI_PREF_RANGE_TYPE_64)
+			res->flags |= IORESOURCE_MEM_64;
+		res->start = base;
+		res->end = limit + 0xfffff;
+		dev_printk(KERN_DEBUG, &dev->dev, "  bridge window %pR\n", res);
+	} else {
+		dev_printk(KERN_DEBUG, &dev->dev,
+		     "  bridge window [mem %#010lx-%#010lx pref] (disabled)\n",
+					 base, limit + 0xfffff);
+	}
+}
+
+void __devinit pci_read_bridge_bases(struct pci_bus *child)
+{
+	struct pci_dev *dev = child->self;
+	struct resource *res;
+	int i;
+
+	if (pci_is_root_bus(child))	/* It's a host bus, nothing to read */
+		return;
+
+	dev_info(&dev->dev, "PCI bridge to [bus %02x-%02x]%s\n",
+		 child->secondary, child->subordinate,
+		 dev->transparent ? " (subtractive decode)" : "");
+
+	pci_bus_remove_resources(child);
+	for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++)
+		child->resource[i] = &dev->resource[PCI_BRIDGE_RESOURCES+i];
+
+	pci_read_bridge_io(child);
+	pci_read_bridge_mmio(child);
+	pci_read_bridge_mmio_pref(child);
+
+	if (dev->transparent) {
+		pci_bus_for_each_resource(child->parent, res, i) {
+			if (res) {
+				pci_bus_add_resource(child, res,
+						     PCI_SUBTRACTIVE_DECODE);
+				dev_printk(KERN_DEBUG, &dev->dev,
+					   "  bridge window %pR (subtractive decode)\n",
+					   res);
+			}
+		}
+	}
+}
+
+static struct pci_bus * pci_alloc_bus(void)
+{
+	struct pci_bus *b;
+
+	b = kzalloc(sizeof(*b), GFP_KERNEL);
+	if (b) {
+		INIT_LIST_HEAD(&b->node);
+		INIT_LIST_HEAD(&b->children);
+		INIT_LIST_HEAD(&b->devices);
+		INIT_LIST_HEAD(&b->slots);
+		INIT_LIST_HEAD(&b->resources);
+		b->max_bus_speed = PCI_SPEED_UNKNOWN;
+		b->cur_bus_speed = PCI_SPEED_UNKNOWN;
+	}
+	return b;
+}
+
+static unsigned char pcix_bus_speed[] = {
+	PCI_SPEED_UNKNOWN,		/* 0 */
+	PCI_SPEED_66MHz_PCIX,		/* 1 */
+	PCI_SPEED_100MHz_PCIX,		/* 2 */
+	PCI_SPEED_133MHz_PCIX,		/* 3 */
+	PCI_SPEED_UNKNOWN,		/* 4 */
+	PCI_SPEED_66MHz_PCIX_ECC,	/* 5 */
+	PCI_SPEED_100MHz_PCIX_ECC,	/* 6 */
+	PCI_SPEED_133MHz_PCIX_ECC,	/* 7 */
+	PCI_SPEED_UNKNOWN,		/* 8 */
+	PCI_SPEED_66MHz_PCIX_266,	/* 9 */
+	PCI_SPEED_100MHz_PCIX_266,	/* A */
+	PCI_SPEED_133MHz_PCIX_266,	/* B */
+	PCI_SPEED_UNKNOWN,		/* C */
+	PCI_SPEED_66MHz_PCIX_533,	/* D */
+	PCI_SPEED_100MHz_PCIX_533,	/* E */
+	PCI_SPEED_133MHz_PCIX_533	/* F */
+};
+
+static unsigned char pcie_link_speed[] = {
+	PCI_SPEED_UNKNOWN,		/* 0 */
+	PCIE_SPEED_2_5GT,		/* 1 */
+	PCIE_SPEED_5_0GT,		/* 2 */
+	PCIE_SPEED_8_0GT,		/* 3 */
+	PCI_SPEED_UNKNOWN,		/* 4 */
+	PCI_SPEED_UNKNOWN,		/* 5 */
+	PCI_SPEED_UNKNOWN,		/* 6 */
+	PCI_SPEED_UNKNOWN,		/* 7 */
+	PCI_SPEED_UNKNOWN,		/* 8 */
+	PCI_SPEED_UNKNOWN,		/* 9 */
+	PCI_SPEED_UNKNOWN,		/* A */
+	PCI_SPEED_UNKNOWN,		/* B */
+	PCI_SPEED_UNKNOWN,		/* C */
+	PCI_SPEED_UNKNOWN,		/* D */
+	PCI_SPEED_UNKNOWN,		/* E */
+	PCI_SPEED_UNKNOWN		/* F */
+};
+
+void pcie_update_link_speed(struct pci_bus *bus, u16 linksta)
+{
+	bus->cur_bus_speed = pcie_link_speed[linksta & 0xf];
+}
+EXPORT_SYMBOL_GPL(pcie_update_link_speed);
+
+static unsigned char agp_speeds[] = {
+	AGP_UNKNOWN,
+	AGP_1X,
+	AGP_2X,
+	AGP_4X,
+	AGP_8X
+};
+
+static enum pci_bus_speed agp_speed(int agp3, int agpstat)
+{
+	int index = 0;
+
+	if (agpstat & 4)
+		index = 3;
+	else if (agpstat & 2)
+		index = 2;
+	else if (agpstat & 1)
+		index = 1;
+	else
+		goto out;
+	
+	if (agp3) {
+		index += 2;
+		if (index == 5)
+			index = 0;
+	}
+
+ out:
+	return agp_speeds[index];
+}
+
+
+static void pci_set_bus_speed(struct pci_bus *bus)
+{
+	struct pci_dev *bridge = bus->self;
+	int pos;
+
+	pos = pci_find_capability(bridge, PCI_CAP_ID_AGP);
+	if (!pos)
+		pos = pci_find_capability(bridge, PCI_CAP_ID_AGP3);
+	if (pos) {
+		u32 agpstat, agpcmd;
+
+		pci_read_config_dword(bridge, pos + PCI_AGP_STATUS, &agpstat);
+		bus->max_bus_speed = agp_speed(agpstat & 8, agpstat & 7);
+
+		pci_read_config_dword(bridge, pos + PCI_AGP_COMMAND, &agpcmd);
+		bus->cur_bus_speed = agp_speed(agpstat & 8, agpcmd & 7);
+	}
+
+	pos = pci_find_capability(bridge, PCI_CAP_ID_PCIX);
+	if (pos) {
+		u16 status;
+		enum pci_bus_speed max;
+		pci_read_config_word(bridge, pos + 2, &status);
+
+		if (status & 0x8000) {
+			max = PCI_SPEED_133MHz_PCIX_533;
+		} else if (status & 0x4000) {
+			max = PCI_SPEED_133MHz_PCIX_266;
+		} else if (status & 0x0002) {
+			if (((status >> 12) & 0x3) == 2) {
+				max = PCI_SPEED_133MHz_PCIX_ECC;
+			} else {
+				max = PCI_SPEED_133MHz_PCIX;
+			}
+		} else {
+			max = PCI_SPEED_66MHz_PCIX;
+		}
+
+		bus->max_bus_speed = max;
+		bus->cur_bus_speed = pcix_bus_speed[(status >> 6) & 0xf];
+
+		return;
+	}
+
+	pos = pci_find_capability(bridge, PCI_CAP_ID_EXP);
+	if (pos) {
+		u32 linkcap;
+		u16 linksta;
+
+		pci_read_config_dword(bridge, pos + PCI_EXP_LNKCAP, &linkcap);
+		bus->max_bus_speed = pcie_link_speed[linkcap & 0xf];
+
+		pci_read_config_word(bridge, pos + PCI_EXP_LNKSTA, &linksta);
+		pcie_update_link_speed(bus, linksta);
+	}
+}
+
+
+static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent,
+					   struct pci_dev *bridge, int busnr)
+{
+	struct pci_bus *child;
+	int i;
+
+	/*
+	 * Allocate a new bus, and inherit stuff from the parent..
+	 */
+	child = pci_alloc_bus();
+	if (!child)
+		return NULL;
+
+	child->parent = parent;
+	child->ops = parent->ops;
+	child->sysdata = parent->sysdata;
+	child->bus_flags = parent->bus_flags;
+
+	/* initialize some portions of the bus device, but don't register it
+	 * now as the parent is not properly set up yet.  This device will get
+	 * registered later in pci_bus_add_devices()
+	 */
+	child->dev.class = &pcibus_class;
+	dev_set_name(&child->dev, "%04x:%02x", pci_domain_nr(child), busnr);
+
+	/*
+	 * Set up the primary, secondary and subordinate
+	 * bus numbers.
+	 */
+	child->number = child->secondary = busnr;
+	child->primary = parent->secondary;
+	child->subordinate = 0xff;
+
+	if (!bridge)
+		return child;
+
+	child->self = bridge;
+	child->bridge = get_device(&bridge->dev);
+
+	pci_set_bus_speed(child);
+
+	/* Set up default resource pointers and names.. */
+	for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++) {
+		child->resource[i] = &bridge->resource[PCI_BRIDGE_RESOURCES+i];
+		child->resource[i]->name = child->name;
+	}
+	bridge->subordinate = child;
+
+	return child;
+}
+
+struct pci_bus *__ref pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev, int busnr)
+{
+	struct pci_bus *child;
+
+	child = pci_alloc_child_bus(parent, dev, busnr);
+	if (child) {
+		down_write(&pci_bus_sem);
+		list_add_tail(&child->node, &parent->children);
+		up_write(&pci_bus_sem);
+	}
+	return child;
+}
+
+static void pci_fixup_parent_subordinate_busnr(struct pci_bus *child, int max)
+{
+	struct pci_bus *parent = child->parent;
+
+	/* Attempts to fix that up are really dangerous unless
+	   we're going to re-assign all bus numbers. */
+	if (!pcibios_assign_all_busses())
+		return;
+
+	while (parent->parent && parent->subordinate < max) {
+		parent->subordinate = max;
+		pci_write_config_byte(parent->self, PCI_SUBORDINATE_BUS, max);
+		parent = parent->parent;
+	}
+}
+
+/*
+ * If it's a bridge, configure it and scan the bus behind it.
+ * For CardBus bridges, we don't scan behind as the devices will
+ * be handled by the bridge driver itself.
+ *
+ * We need to process bridges in two passes -- first we scan those
+ * already configured by the BIOS and after we are done with all of
+ * them, we proceed to assigning numbers to the remaining buses in
+ * order to avoid overlaps between old and new bus numbers.
+ */
+int __devinit pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass)
+{
+	struct pci_bus *child;
+	int is_cardbus = (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS);
+	u32 buses, i, j = 0;
+	u16 bctl;
+	u8 primary, secondary, subordinate;
+	int broken = 0;
+
+	pci_read_config_dword(dev, PCI_PRIMARY_BUS, &buses);
+	primary = buses & 0xFF;
+	secondary = (buses >> 8) & 0xFF;
+	subordinate = (buses >> 16) & 0xFF;
+
+	dev_dbg(&dev->dev, "scanning [bus %02x-%02x] behind bridge, pass %d\n",
+		secondary, subordinate, pass);
+
+	if (!primary && (primary != bus->number) && secondary && subordinate) {
+		dev_warn(&dev->dev, "Primary bus is hard wired to 0\n");
+		primary = bus->number;
+	}
+
+	/* Check if setup is sensible at all */
+	if (!pass &&
+	    (primary != bus->number || secondary <= bus->number)) {
+		dev_dbg(&dev->dev, "bus configuration invalid, reconfiguring\n");
+		broken = 1;
+	}
+
+	/* Disable MasterAbortMode during probing to avoid reporting
+	   of bus errors (in some architectures) */ 
+	pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &bctl);
+	pci_write_config_word(dev, PCI_BRIDGE_CONTROL,
+			      bctl & ~PCI_BRIDGE_CTL_MASTER_ABORT);
+
+	if ((secondary || subordinate) && !pcibios_assign_all_busses() &&
+	    !is_cardbus && !broken) {
+		unsigned int cmax;
+		/*
+		 * Bus already configured by firmware, process it in the first
+		 * pass and just note the configuration.
+		 */
+		if (pass)
+			goto out;
+
+		/*
+		 * If we already got to this bus through a different bridge,
+		 * don't re-add it. This can happen with the i450NX chipset.
+		 *
+		 * However, we continue to descend down the hierarchy and
+		 * scan remaining child buses.
+		 */
+		child = pci_find_bus(pci_domain_nr(bus), secondary);
+		if (!child) {
+			child = pci_add_new_bus(bus, dev, secondary);
+			if (!child)
+				goto out;
+			child->primary = primary;
+			child->subordinate = subordinate;
+			child->bridge_ctl = bctl;
+		}
+
+		cmax = pci_scan_child_bus(child);
+		if (cmax > max)
+			max = cmax;
+		if (child->subordinate > max)
+			max = child->subordinate;
+	} else {
+		/*
+		 * We need to assign a number to this bus which we always
+		 * do in the second pass.
+		 */
+		if (!pass) {
+			if (pcibios_assign_all_busses() || broken)
+				/* Temporarily disable forwarding of the
+				   configuration cycles on all bridges in
+				   this bus segment to avoid possible
+				   conflicts in the second pass between two
+				   bridges programmed with overlapping
+				   bus ranges. */
+				pci_write_config_dword(dev, PCI_PRIMARY_BUS,
+						       buses & ~0xffffff);
+			goto out;
+		}
+
+		/* Clear errors */
+		pci_write_config_word(dev, PCI_STATUS, 0xffff);
+
+		/* Prevent assigning a bus number that already exists.
+		 * This can happen when a bridge is hot-plugged */
+		if (pci_find_bus(pci_domain_nr(bus), max+1))
+			goto out;
+		child = pci_add_new_bus(bus, dev, ++max);
+		if (!child)
+			goto out;
+		buses = (buses & 0xff000000)
+		      | ((unsigned int)(child->primary)     <<  0)
+		      | ((unsigned int)(child->secondary)   <<  8)
+		      | ((unsigned int)(child->subordinate) << 16);
+
+		/*
+		 * yenta.c forces a secondary latency timer of 176.
+		 * Copy that behaviour here.
+		 */
+		if (is_cardbus) {
+			buses &= ~0xff000000;
+			buses |= CARDBUS_LATENCY_TIMER << 24;
+		}
+
+		/*
+		 * We need to blast all three values with a single write.
+		 */
+		pci_write_config_dword(dev, PCI_PRIMARY_BUS, buses);
+
+		if (!is_cardbus) {
+			child->bridge_ctl = bctl;
+			/*
+			 * Adjust subordinate busnr in parent buses.
+			 * We do this before scanning for children because
+			 * some devices may not be detected if the bios
+			 * was lazy.
+			 */
+			pci_fixup_parent_subordinate_busnr(child, max);
+			/* Now we can scan all subordinate buses... */
+			max = pci_scan_child_bus(child);
+			/*
+			 * now fix it up again since we have found
+			 * the real value of max.
+			 */
+			pci_fixup_parent_subordinate_busnr(child, max);
+		} else {
+			/*
+			 * For CardBus bridges, we leave 4 bus numbers
+			 * as cards with a PCI-to-PCI bridge can be
+			 * inserted later.
+			 */
+			for (i=0; i<CARDBUS_RESERVE_BUSNR; i++) {
+				struct pci_bus *parent = bus;
+				if (pci_find_bus(pci_domain_nr(bus),
+							max+i+1))
+					break;
+				while (parent->parent) {
+					if ((!pcibios_assign_all_busses()) &&
+					    (parent->subordinate > max) &&
+					    (parent->subordinate <= max+i)) {
+						j = 1;
+					}
+					parent = parent->parent;
+				}
+				if (j) {
+					/*
+					 * Often, there are two cardbus bridges
+					 * -- try to leave one valid bus number
+					 * for each one.
+					 */
+					i /= 2;
+					break;
+				}
+			}
+			max += i;
+			pci_fixup_parent_subordinate_busnr(child, max);
+		}
+		/*
+		 * Set the subordinate bus number to its real value.
+		 */
+		child->subordinate = max;
+		pci_write_config_byte(dev, PCI_SUBORDINATE_BUS, max);
+	}
+
+	sprintf(child->name,
+		(is_cardbus ? "PCI CardBus %04x:%02x" : "PCI Bus %04x:%02x"),
+		pci_domain_nr(bus), child->number);
+
+	/* Has only triggered on CardBus, fixup is in yenta_socket */
+	while (bus->parent) {
+		if ((child->subordinate > bus->subordinate) ||
+		    (child->number > bus->subordinate) ||
+		    (child->number < bus->number) ||
+		    (child->subordinate < bus->number)) {
+			dev_info(&child->dev, "[bus %02x-%02x] %s "
+				"hidden behind%s bridge %s [bus %02x-%02x]\n",
+				child->number, child->subordinate,
+				(bus->number > child->subordinate &&
+				 bus->subordinate < child->number) ?
+					"wholly" : "partially",
+				bus->self->transparent ? " transparent" : "",
+				dev_name(&bus->dev),
+				bus->number, bus->subordinate);
+		}
+		bus = bus->parent;
+	}
+
+out:
+	pci_write_config_word(dev, PCI_BRIDGE_CONTROL, bctl);
+
+	return max;
+}
+
+/*
+ * Read interrupt line and base address registers.
+ * The architecture-dependent code can tweak these, of course.
+ */
+static void pci_read_irq(struct pci_dev *dev)
+{
+	unsigned char irq;
+
+	pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &irq);
+	dev->pin = irq;
+	if (irq)
+		pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &irq);
+	dev->irq = irq;
+}
+
+void set_pcie_port_type(struct pci_dev *pdev)
+{
+	int pos;
+	u16 reg16;
+
+	pos = pci_find_capability(pdev, PCI_CAP_ID_EXP);
+	if (!pos)
+		return;
+	pdev->is_pcie = 1;
+	pdev->pcie_cap = pos;
+	pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, &reg16);
+	pdev->pcie_type = (reg16 & PCI_EXP_FLAGS_TYPE) >> 4;
+}
+
+void set_pcie_hotplug_bridge(struct pci_dev *pdev)
+{
+	int pos;
+	u16 reg16;
+	u32 reg32;
+
+	pos = pci_pcie_cap(pdev);
+	if (!pos)
+		return;
+	pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, &reg16);
+	if (!(reg16 & PCI_EXP_FLAGS_SLOT))
+		return;
+	pci_read_config_dword(pdev, pos + PCI_EXP_SLTCAP, &reg32);
+	if (reg32 & PCI_EXP_SLTCAP_HPC)
+		pdev->is_hotplug_bridge = 1;
+}
+
+#define LEGACY_IO_RESOURCE	(IORESOURCE_IO | IORESOURCE_PCI_FIXED)
+
+/**
+ * pci_setup_device - fill in class and map information of a device
+ * @dev: the device structure to fill
+ *
+ * Initialize the device structure with information about the device's 
+ * vendor,class,memory and IO-space addresses,IRQ lines etc.
+ * Called at initialisation of the PCI subsystem and by CardBus services.
+ * Returns 0 on success and negative if unknown type of device (not normal,
+ * bridge or CardBus).
+ */
+int pci_setup_device(struct pci_dev *dev)
+{
+	u32 class;
+	u8 hdr_type;
+	struct pci_slot *slot;
+	int pos = 0;
+
+	if (pci_read_config_byte(dev, PCI_HEADER_TYPE, &hdr_type))
+		return -EIO;
+
+	dev->sysdata = dev->bus->sysdata;
+	dev->dev.parent = dev->bus->bridge;
+	dev->dev.bus = &pci_bus_type;
+	dev->hdr_type = hdr_type & 0x7f;
+	dev->multifunction = !!(hdr_type & 0x80);
+	dev->error_state = pci_channel_io_normal;
+	set_pcie_port_type(dev);
+
+	list_for_each_entry(slot, &dev->bus->slots, list)
+		if (PCI_SLOT(dev->devfn) == slot->number)
+			dev->slot = slot;
+
+	/* Assume 32-bit PCI; let 64-bit PCI cards (which are far rarer)
+	   set this higher, assuming the system even supports it.  */
+	dev->dma_mask = 0xffffffff;
+
+	dev_set_name(&dev->dev, "%04x:%02x:%02x.%d", pci_domain_nr(dev->bus),
+		     dev->bus->number, PCI_SLOT(dev->devfn),
+		     PCI_FUNC(dev->devfn));
+
+	pci_read_config_dword(dev, PCI_CLASS_REVISION, &class);
+	dev->revision = class & 0xff;
+	class >>= 8;				    /* upper 3 bytes */
+	dev->class = class;
+	class >>= 8;
+
+	dev_printk(KERN_DEBUG, &dev->dev, "[%04x:%04x] type %d class %#08x\n",
+		   dev->vendor, dev->device, dev->hdr_type, class);
+
+	/* need to have dev->class ready */
+	dev->cfg_size = pci_cfg_space_size(dev);
+
+	/* "Unknown power state" */
+	dev->current_state = PCI_UNKNOWN;
+
+	/* Early fixups, before probing the BARs */
+	pci_fixup_device(pci_fixup_early, dev);
+	/* device class may be changed after fixup */
+	class = dev->class >> 8;
+
+	switch (dev->hdr_type) {		    /* header type */
+	case PCI_HEADER_TYPE_NORMAL:		    /* standard header */
+		if (class == PCI_CLASS_BRIDGE_PCI)
+			goto bad;
+		pci_read_irq(dev);
+		pci_read_bases(dev, 6, PCI_ROM_ADDRESS);
+		pci_read_config_word(dev, PCI_SUBSYSTEM_VENDOR_ID, &dev->subsystem_vendor);
+		pci_read_config_word(dev, PCI_SUBSYSTEM_ID, &dev->subsystem_device);
+
+		/*
+		 *	Do the ugly legacy mode stuff here rather than broken chip
+		 *	quirk code. Legacy mode ATA controllers have fixed
+		 *	addresses. These are not always echoed in BAR0-3, and
+		 *	BAR0-3 in a few cases contain junk!
+		 */
+		if (class == PCI_CLASS_STORAGE_IDE) {
+			u8 progif;
+			pci_read_config_byte(dev, PCI_CLASS_PROG, &progif);
+			if ((progif & 1) == 0) {
+				dev->resource[0].start = 0x1F0;
+				dev->resource[0].end = 0x1F7;
+				dev->resource[0].flags = LEGACY_IO_RESOURCE;
+				dev->resource[1].start = 0x3F6;
+				dev->resource[1].end = 0x3F6;
+				dev->resource[1].flags = LEGACY_IO_RESOURCE;
+			}
+			if ((progif & 4) == 0) {
+				dev->resource[2].start = 0x170;
+				dev->resource[2].end = 0x177;
+				dev->resource[2].flags = LEGACY_IO_RESOURCE;
+				dev->resource[3].start = 0x376;
+				dev->resource[3].end = 0x376;
+				dev->resource[3].flags = LEGACY_IO_RESOURCE;
+			}
+		}
+		break;
+
+	case PCI_HEADER_TYPE_BRIDGE:		    /* bridge header */
+		if (class != PCI_CLASS_BRIDGE_PCI)
+			goto bad;
+		/* The PCI-to-PCI bridge spec requires that subtractive
+		   decoding (i.e. transparent) bridge must have programming
+		   interface code of 0x01. */ 
+		pci_read_irq(dev);
+		dev->transparent = ((dev->class & 0xff) == 1);
+		pci_read_bases(dev, 2, PCI_ROM_ADDRESS1);
+		set_pcie_hotplug_bridge(dev);
+		pos = pci_find_capability(dev, PCI_CAP_ID_SSVID);
+		if (pos) {
+			pci_read_config_word(dev, pos + PCI_SSVID_VENDOR_ID, &dev->subsystem_vendor);
+			pci_read_config_word(dev, pos + PCI_SSVID_DEVICE_ID, &dev->subsystem_device);
+		}
+		break;
+
+	case PCI_HEADER_TYPE_CARDBUS:		    /* CardBus bridge header */
+		if (class != PCI_CLASS_BRIDGE_CARDBUS)
+			goto bad;
+		pci_read_irq(dev);
+		pci_read_bases(dev, 1, 0);
+		pci_read_config_word(dev, PCI_CB_SUBSYSTEM_VENDOR_ID, &dev->subsystem_vendor);
+		pci_read_config_word(dev, PCI_CB_SUBSYSTEM_ID, &dev->subsystem_device);
+		break;
+
+	default:				    /* unknown header */
+		dev_err(&dev->dev, "unknown header type %02x, "
+			"ignoring device\n", dev->hdr_type);
+		return -EIO;
+
+	bad:
+		dev_err(&dev->dev, "ignoring class %02x (doesn't match header "
+			"type %02x)\n", class, dev->hdr_type);
+		dev->class = PCI_CLASS_NOT_DEFINED;
+	}
+
+	/* We found a fine healthy device, go go go... */
+	return 0;
+}
+
+static void pci_release_capabilities(struct pci_dev *dev)
+{
+	pci_vpd_release(dev);
+	pci_iov_release(dev);
+}
+
+/**
+ * pci_release_dev - free a pci device structure when all users of it are finished.
+ * @dev: device that's been disconnected
+ *
+ * Will be called only by the device core when all users of this pci device are
+ * done.
+ */
+static void pci_release_dev(struct device *dev)
+{
+	struct pci_dev *pci_dev;
+
+	pci_dev = to_pci_dev(dev);
+	pci_release_capabilities(pci_dev);
+	kfree(pci_dev);
+}
+
+/**
+ * pci_cfg_space_size - get the configuration space size of the PCI device.
+ * @dev: PCI device
+ *
+ * Regular PCI devices have 256 bytes, but PCI-X 2 and PCI Express devices
+ * have 4096 bytes.  Even if the device is capable, that doesn't mean we can
+ * access it.  Maybe we don't have a way to generate extended config space
+ * accesses, or the device is behind a reverse Express bridge.  So we try
+ * reading the dword at 0x100 which must either be 0 or a valid extended
+ * capability header.
+ */
+int pci_cfg_space_size_ext(struct pci_dev *dev)
+{
+	u32 status;
+	int pos = PCI_CFG_SPACE_SIZE;
+
+	if (pci_read_config_dword(dev, pos, &status) != PCIBIOS_SUCCESSFUL)
+		goto fail;
+	if (status == 0xffffffff)
+		goto fail;
+
+	return PCI_CFG_SPACE_EXP_SIZE;
+
+ fail:
+	return PCI_CFG_SPACE_SIZE;
+}
+
+int pci_cfg_space_size(struct pci_dev *dev)
+{
+	int pos;
+	u32 status;
+	u16 class;
+
+	class = dev->class >> 8;
+	if (class == PCI_CLASS_BRIDGE_HOST)
+		return pci_cfg_space_size_ext(dev);
+
+	pos = pci_pcie_cap(dev);
+	if (!pos) {
+		pos = pci_find_capability(dev, PCI_CAP_ID_PCIX);
+		if (!pos)
+			goto fail;
+
+		pci_read_config_dword(dev, pos + PCI_X_STATUS, &status);
+		if (!(status & (PCI_X_STATUS_266MHZ | PCI_X_STATUS_533MHZ)))
+			goto fail;
+	}
+
+	return pci_cfg_space_size_ext(dev);
+
+ fail:
+	return PCI_CFG_SPACE_SIZE;
+}
+
+static void pci_release_bus_bridge_dev(struct device *dev)
+{
+	kfree(dev);
+}
+
+struct pci_dev *alloc_pci_dev(void)
+{
+	struct pci_dev *dev;
+
+	dev = kzalloc(sizeof(struct pci_dev), GFP_KERNEL);
+	if (!dev)
+		return NULL;
+
+	INIT_LIST_HEAD(&dev->bus_list);
+
+	return dev;
+}
+EXPORT_SYMBOL(alloc_pci_dev);
+
+/*
+ * Read the config data for a PCI device, sanity-check it
+ * and fill in the dev structure...
+ */
+static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn)
+{
+	struct pci_dev *dev;
+	u32 l;
+	int delay = 1;
+
+	if (pci_bus_read_config_dword(bus, devfn, PCI_VENDOR_ID, &l))
+		return NULL;
+
+	/* some broken boards return 0 or ~0 if a slot is empty: */
+	if (l == 0xffffffff || l == 0x00000000 ||
+	    l == 0x0000ffff || l == 0xffff0000)
+		return NULL;
+
+	/* Configuration request Retry Status */
+	while (l == 0xffff0001) {
+		msleep(delay);
+		delay *= 2;
+		if (pci_bus_read_config_dword(bus, devfn, PCI_VENDOR_ID, &l))
+			return NULL;
+		/* Card hasn't responded in 60 seconds?  Must be stuck. */
+		if (delay > 60 * 1000) {
+			printk(KERN_WARNING "pci %04x:%02x:%02x.%d: not "
+					"responding\n", pci_domain_nr(bus),
+					bus->number, PCI_SLOT(devfn),
+					PCI_FUNC(devfn));
+			return NULL;
+		}
+	}
+
+	dev = alloc_pci_dev();
+	if (!dev)
+		return NULL;
+
+	dev->bus = bus;
+	dev->devfn = devfn;
+	dev->vendor = l & 0xffff;
+	dev->device = (l >> 16) & 0xffff;
+
+	if (pci_setup_device(dev)) {
+		kfree(dev);
+		return NULL;
+	}
+
+	return dev;
+}
+
+static void pci_init_capabilities(struct pci_dev *dev)
+{
+	/* MSI/MSI-X list */
+	pci_msi_init_pci_dev(dev);
+
+	/* Buffers for saving PCIe and PCI-X capabilities */
+	pci_allocate_cap_save_buffers(dev);
+
+	/* Power Management */
+	pci_pm_init(dev);
+	platform_pci_wakeup_init(dev);
+
+	/* Vital Product Data */
+	pci_vpd_pci22_init(dev);
+
+	/* Alternative Routing-ID Forwarding */
+	pci_enable_ari(dev);
+
+	/* Single Root I/O Virtualization */
+	pci_iov_init(dev);
+
+	/* Enable ACS P2P upstream forwarding */
+	pci_enable_acs(dev);
+}
+
+void pci_device_add(struct pci_dev *dev, struct pci_bus *bus)
+{
+	device_initialize(&dev->dev);
+	dev->dev.release = pci_release_dev;
+	pci_dev_get(dev);
+
+	dev->dev.dma_mask = &dev->dma_mask;
+	dev->dev.dma_parms = &dev->dma_parms;
+	dev->dev.coherent_dma_mask = 0xffffffffull;
+
+	pci_set_dma_max_seg_size(dev, 65536);
+	pci_set_dma_seg_boundary(dev, 0xffffffff);
+
+	/* Fix up broken headers */
+	pci_fixup_device(pci_fixup_header, dev);
+
+	/* Clear the state_saved flag. */
+	dev->state_saved = false;
+
+	/* Initialize various capabilities */
+	pci_init_capabilities(dev);
+
+	/*
+	 * Add the device to our list of discovered devices
+	 * and the bus list for fixup functions, etc.
+	 */
+	down_write(&pci_bus_sem);
+	list_add_tail(&dev->bus_list, &bus->devices);
+	up_write(&pci_bus_sem);
+}
+
+struct pci_dev *__ref pci_scan_single_device(struct pci_bus *bus, int devfn)
+{
+	struct pci_dev *dev;
+
+	dev = pci_get_slot(bus, devfn);
+	if (dev) {
+		pci_dev_put(dev);
+		return dev;
+	}
+
+	dev = pci_scan_device(bus, devfn);
+	if (!dev)
+		return NULL;
+
+	pci_device_add(dev, bus);
+
+	return dev;
+}
+EXPORT_SYMBOL(pci_scan_single_device);
+
+static unsigned next_ari_fn(struct pci_dev *dev, unsigned fn)
+{
+	u16 cap;
+	unsigned pos, next_fn;
+
+	if (!dev)
+		return 0;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ARI);
+	if (!pos)
+		return 0;
+	pci_read_config_word(dev, pos + 4, &cap);
+	next_fn = cap >> 8;
+	if (next_fn <= fn)
+		return 0;
+	return next_fn;
+}
+
+static unsigned next_trad_fn(struct pci_dev *dev, unsigned fn)
+{
+	return (fn + 1) % 8;
+}
+
+static unsigned no_next_fn(struct pci_dev *dev, unsigned fn)
+{
+	return 0;
+}
+
+static int only_one_child(struct pci_bus *bus)
+{
+	struct pci_dev *parent = bus->self;
+	if (!parent || !pci_is_pcie(parent))
+		return 0;
+	if (parent->pcie_type == PCI_EXP_TYPE_ROOT_PORT ||
+	    parent->pcie_type == PCI_EXP_TYPE_DOWNSTREAM)
+		return 1;
+	return 0;
+}
+
+/**
+ * pci_scan_slot - scan a PCI slot on a bus for devices.
+ * @bus: PCI bus to scan
+ * @devfn: slot number to scan (must have zero function.)
+ *
+ * Scan a PCI slot on the specified PCI bus for devices, adding
+ * discovered devices to the @bus->devices list.  New devices
+ * will not have is_added set.
+ *
+ * Returns the number of new devices found.
+ */
+int pci_scan_slot(struct pci_bus *bus, int devfn)
+{
+	unsigned fn, nr = 0;
+	struct pci_dev *dev;
+	unsigned (*next_fn)(struct pci_dev *, unsigned) = no_next_fn;
+
+	if (only_one_child(bus) && (devfn > 0))
+		return 0; /* Already scanned the entire slot */
+
+	dev = pci_scan_single_device(bus, devfn);
+	if (!dev)
+		return 0;
+	if (!dev->is_added)
+		nr++;
+
+	if (pci_ari_enabled(bus))
+		next_fn = next_ari_fn;
+	else if (dev->multifunction)
+		next_fn = next_trad_fn;
+
+	for (fn = next_fn(dev, 0); fn > 0; fn = next_fn(dev, fn)) {
+		dev = pci_scan_single_device(bus, devfn + fn);
+		if (dev) {
+			if (!dev->is_added)
+				nr++;
+			dev->multifunction = 1;
+		}
+	}
+
+	/* only one slot has pcie device */
+	if (bus->self && nr)
+		pcie_aspm_init_link_state(bus->self);
+
+	return nr;
+}
+
+unsigned int __devinit pci_scan_child_bus(struct pci_bus *bus)
+{
+	unsigned int devfn, pass, max = bus->secondary;
+	struct pci_dev *dev;
+
+	dev_dbg(&bus->dev, "scanning bus\n");
+
+	/* Go find them, Rover! */
+	for (devfn = 0; devfn < 0x100; devfn += 8)
+		pci_scan_slot(bus, devfn);
+
+	/* Reserve buses for SR-IOV capability. */
+	max += pci_iov_bus_range(bus);
+
+	/*
+	 * After performing arch-dependent fixup of the bus, look behind
+	 * all PCI-to-PCI bridges on this bus.
+	 */
+	if (!bus->is_added) {
+		dev_dbg(&bus->dev, "fixups for bus\n");
+		pcibios_fixup_bus(bus);
+		if (pci_is_root_bus(bus))
+			bus->is_added = 1;
+	}
+
+	for (pass=0; pass < 2; pass++)
+		list_for_each_entry(dev, &bus->devices, bus_list) {
+			if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE ||
+			    dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)
+				max = pci_scan_bridge(bus, dev, max, pass);
+		}
+
+	/*
+	 * We've scanned the bus and so we know all about what's on
+	 * the other side of any bridges that may be on this bus plus
+	 * any devices.
+	 *
+	 * Return how far we've got finding sub-buses.
+	 */
+	dev_dbg(&bus->dev, "bus scan returning with max=%02x\n", max);
+	return max;
+}
+
+struct pci_bus * pci_create_bus(struct device *parent,
+		int bus, struct pci_ops *ops, void *sysdata)
+{
+	int error;
+	struct pci_bus *b, *b2;
+	struct device *dev;
+
+	b = pci_alloc_bus();
+	if (!b)
+		return NULL;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev){
+		kfree(b);
+		return NULL;
+	}
+
+	b->sysdata = sysdata;
+	b->ops = ops;
+
+	b2 = pci_find_bus(pci_domain_nr(b), bus);
+	if (b2) {
+		/* If we already got to this bus through a different bridge, ignore it */
+		dev_dbg(&b2->dev, "bus already known\n");
+		goto err_out;
+	}
+
+	down_write(&pci_bus_sem);
+	list_add_tail(&b->node, &pci_root_buses);
+	up_write(&pci_bus_sem);
+
+	dev->parent = parent;
+	dev->release = pci_release_bus_bridge_dev;
+	dev_set_name(dev, "pci%04x:%02x", pci_domain_nr(b), bus);
+	error = device_register(dev);
+	if (error)
+		goto dev_reg_err;
+	b->bridge = get_device(dev);
+	device_enable_async_suspend(b->bridge);
+
+	if (!parent)
+		set_dev_node(b->bridge, pcibus_to_node(b));
+
+	b->dev.class = &pcibus_class;
+	b->dev.parent = b->bridge;
+	dev_set_name(&b->dev, "%04x:%02x", pci_domain_nr(b), bus);
+	error = device_register(&b->dev);
+	if (error)
+		goto class_dev_reg_err;
+
+	/* Create legacy_io and legacy_mem files for this bus */
+	pci_create_legacy_files(b);
+
+	b->number = b->secondary = bus;
+	b->resource[0] = &ioport_resource;
+	b->resource[1] = &iomem_resource;
+
+	return b;
+
+class_dev_reg_err:
+	device_unregister(dev);
+dev_reg_err:
+	down_write(&pci_bus_sem);
+	list_del(&b->node);
+	up_write(&pci_bus_sem);
+err_out:
+	kfree(dev);
+	kfree(b);
+	return NULL;
+}
+
+struct pci_bus * __devinit pci_scan_bus_parented(struct device *parent,
+		int bus, struct pci_ops *ops, void *sysdata)
+{
+	struct pci_bus *b;
+
+	b = pci_create_bus(parent, bus, ops, sysdata);
+	if (b)
+		b->subordinate = pci_scan_child_bus(b);
+	return b;
+}
+EXPORT_SYMBOL(pci_scan_bus_parented);
+
+#ifdef CONFIG_HOTPLUG
+/**
+ * pci_rescan_bus - scan a PCI bus for devices.
+ * @bus: PCI bus to scan
+ *
+ * Scan a PCI bus and child buses for new devices, adds them,
+ * and enables them.
+ *
+ * Returns the max number of subordinate bus discovered.
+ */
+unsigned int __ref pci_rescan_bus(struct pci_bus *bus)
+{
+	unsigned int max;
+	struct pci_dev *dev;
+
+	max = pci_scan_child_bus(bus);
+
+	down_read(&pci_bus_sem);
+	list_for_each_entry(dev, &bus->devices, bus_list)
+		if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE ||
+		    dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)
+			if (dev->subordinate)
+				pci_bus_size_bridges(dev->subordinate);
+	up_read(&pci_bus_sem);
+
+	pci_bus_assign_resources(bus);
+	pci_enable_bridges(bus);
+	pci_bus_add_devices(bus);
+
+	return max;
+}
+EXPORT_SYMBOL_GPL(pci_rescan_bus);
+
+EXPORT_SYMBOL(pci_add_new_bus);
+EXPORT_SYMBOL(pci_scan_slot);
+EXPORT_SYMBOL(pci_scan_bridge);
+EXPORT_SYMBOL_GPL(pci_scan_child_bus);
+#endif
+
+static int __init pci_sort_bf_cmp(const struct device *d_a, const struct device *d_b)
+{
+	const struct pci_dev *a = to_pci_dev(d_a);
+	const struct pci_dev *b = to_pci_dev(d_b);
+
+	if      (pci_domain_nr(a->bus) < pci_domain_nr(b->bus)) return -1;
+	else if (pci_domain_nr(a->bus) > pci_domain_nr(b->bus)) return  1;
+
+	if      (a->bus->number < b->bus->number) return -1;
+	else if (a->bus->number > b->bus->number) return  1;
+
+	if      (a->devfn < b->devfn) return -1;
+	else if (a->devfn > b->devfn) return  1;
+
+	return 0;
+}
+
+void __init pci_sort_breadthfirst(void)
+{
+	bus_sort_breadthfirst(&pci_bus_type, &pci_sort_bf_cmp);
+}
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
new file mode 100644
index 00000000..27911b55
--- /dev/null
+++ b/drivers/pci/proc.c
@@ -0,0 +1,490 @@
+/*
+ *	Procfs interface for the PCI bus.
+ *
+ *	Copyright (c) 1997--1999 Martin Mares <mj@ucw.cz>
+ */
+
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/capability.h>
+#include <asm/uaccess.h>
+#include <asm/byteorder.h>
+#include "pci.h"
+
+static int proc_initialized;	/* = 0 */
+
+static loff_t
+proc_bus_pci_lseek(struct file *file, loff_t off, int whence)
+{
+	loff_t new = -1;
+	struct inode *inode = file->f_path.dentry->d_inode;
+
+	mutex_lock(&inode->i_mutex);
+	switch (whence) {
+	case 0:
+		new = off;
+		break;
+	case 1:
+		new = file->f_pos + off;
+		break;
+	case 2:
+		new = inode->i_size + off;
+		break;
+	}
+	if (new < 0 || new > inode->i_size)
+		new = -EINVAL;
+	else
+		file->f_pos = new;
+	mutex_unlock(&inode->i_mutex);
+	return new;
+}
+
+static ssize_t
+proc_bus_pci_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
+{
+	const struct inode *ino = file->f_path.dentry->d_inode;
+	const struct proc_dir_entry *dp = PDE(ino);
+	struct pci_dev *dev = dp->data;
+	unsigned int pos = *ppos;
+	unsigned int cnt, size;
+
+	/*
+	 * Normal users can read only the standardized portion of the
+	 * configuration space as several chips lock up when trying to read
+	 * undefined locations (think of Intel PIIX4 as a typical example).
+	 */
+
+	if (capable(CAP_SYS_ADMIN))
+		size = dp->size;
+	else if (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)
+		size = 128;
+	else
+		size = 64;
+
+	if (pos >= size)
+		return 0;
+	if (nbytes >= size)
+		nbytes = size;
+	if (pos + nbytes > size)
+		nbytes = size - pos;
+	cnt = nbytes;
+
+	if (!access_ok(VERIFY_WRITE, buf, cnt))
+		return -EINVAL;
+
+	if ((pos & 1) && cnt) {
+		unsigned char val;
+		pci_user_read_config_byte(dev, pos, &val);
+		__put_user(val, buf);
+		buf++;
+		pos++;
+		cnt--;
+	}
+
+	if ((pos & 3) && cnt > 2) {
+		unsigned short val;
+		pci_user_read_config_word(dev, pos, &val);
+		__put_user(cpu_to_le16(val), (__le16 __user *) buf);
+		buf += 2;
+		pos += 2;
+		cnt -= 2;
+	}
+
+	while (cnt >= 4) {
+		unsigned int val;
+		pci_user_read_config_dword(dev, pos, &val);
+		__put_user(cpu_to_le32(val), (__le32 __user *) buf);
+		buf += 4;
+		pos += 4;
+		cnt -= 4;
+	}
+
+	if (cnt >= 2) {
+		unsigned short val;
+		pci_user_read_config_word(dev, pos, &val);
+		__put_user(cpu_to_le16(val), (__le16 __user *) buf);
+		buf += 2;
+		pos += 2;
+		cnt -= 2;
+	}
+
+	if (cnt) {
+		unsigned char val;
+		pci_user_read_config_byte(dev, pos, &val);
+		__put_user(val, buf);
+		buf++;
+		pos++;
+		cnt--;
+	}
+
+	*ppos = pos;
+	return nbytes;
+}
+
+static ssize_t
+proc_bus_pci_write(struct file *file, const char __user *buf, size_t nbytes, loff_t *ppos)
+{
+	struct inode *ino = file->f_path.dentry->d_inode;
+	const struct proc_dir_entry *dp = PDE(ino);
+	struct pci_dev *dev = dp->data;
+	int pos = *ppos;
+	int size = dp->size;
+	int cnt;
+
+	if (pos >= size)
+		return 0;
+	if (nbytes >= size)
+		nbytes = size;
+	if (pos + nbytes > size)
+		nbytes = size - pos;
+	cnt = nbytes;
+
+	if (!access_ok(VERIFY_READ, buf, cnt))
+		return -EINVAL;
+
+	if ((pos & 1) && cnt) {
+		unsigned char val;
+		__get_user(val, buf);
+		pci_user_write_config_byte(dev, pos, val);
+		buf++;
+		pos++;
+		cnt--;
+	}
+
+	if ((pos & 3) && cnt > 2) {
+		__le16 val;
+		__get_user(val, (__le16 __user *) buf);
+		pci_user_write_config_word(dev, pos, le16_to_cpu(val));
+		buf += 2;
+		pos += 2;
+		cnt -= 2;
+	}
+
+	while (cnt >= 4) {
+		__le32 val;
+		__get_user(val, (__le32 __user *) buf);
+		pci_user_write_config_dword(dev, pos, le32_to_cpu(val));
+		buf += 4;
+		pos += 4;
+		cnt -= 4;
+	}
+
+	if (cnt >= 2) {
+		__le16 val;
+		__get_user(val, (__le16 __user *) buf);
+		pci_user_write_config_word(dev, pos, le16_to_cpu(val));
+		buf += 2;
+		pos += 2;
+		cnt -= 2;
+	}
+
+	if (cnt) {
+		unsigned char val;
+		__get_user(val, buf);
+		pci_user_write_config_byte(dev, pos, val);
+		buf++;
+		pos++;
+		cnt--;
+	}
+
+	*ppos = pos;
+	i_size_write(ino, dp->size);
+	return nbytes;
+}
+
+struct pci_filp_private {
+	enum pci_mmap_state mmap_state;
+	int write_combine;
+};
+
+static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd,
+			       unsigned long arg)
+{
+	const struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode);
+	struct pci_dev *dev = dp->data;
+#ifdef HAVE_PCI_MMAP
+	struct pci_filp_private *fpriv = file->private_data;
+#endif /* HAVE_PCI_MMAP */
+	int ret = 0;
+
+	switch (cmd) {
+	case PCIIOC_CONTROLLER:
+		ret = pci_domain_nr(dev->bus);
+		break;
+
+#ifdef HAVE_PCI_MMAP
+	case PCIIOC_MMAP_IS_IO:
+		fpriv->mmap_state = pci_mmap_io;
+		break;
+
+	case PCIIOC_MMAP_IS_MEM:
+		fpriv->mmap_state = pci_mmap_mem;
+		break;
+
+	case PCIIOC_WRITE_COMBINE:
+		if (arg)
+			fpriv->write_combine = 1;
+		else
+			fpriv->write_combine = 0;
+		break;
+
+#endif /* HAVE_PCI_MMAP */
+
+	default:
+		ret = -EINVAL;
+		break;
+	};
+
+	return ret;
+}
+
+#ifdef HAVE_PCI_MMAP
+static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	const struct proc_dir_entry *dp = PDE(inode);
+	struct pci_dev *dev = dp->data;
+	struct pci_filp_private *fpriv = file->private_data;
+	int i, ret;
+
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	/* Make sure the caller is mapping a real resource for this device */
+	for (i = 0; i < PCI_ROM_RESOURCE; i++) {
+		if (pci_mmap_fits(dev, i, vma,  PCI_MMAP_PROCFS))
+			break;
+	}
+
+	if (i >= PCI_ROM_RESOURCE)
+		return -ENODEV;
+
+	ret = pci_mmap_page_range(dev, vma,
+				  fpriv->mmap_state,
+				  fpriv->write_combine);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int proc_bus_pci_open(struct inode *inode, struct file *file)
+{
+	struct pci_filp_private *fpriv = kmalloc(sizeof(*fpriv), GFP_KERNEL);
+
+	if (!fpriv)
+		return -ENOMEM;
+
+	fpriv->mmap_state = pci_mmap_io;
+	fpriv->write_combine = 0;
+
+	file->private_data = fpriv;
+
+	return 0;
+}
+
+static int proc_bus_pci_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	file->private_data = NULL;
+
+	return 0;
+}
+#endif /* HAVE_PCI_MMAP */
+
+static const struct file_operations proc_bus_pci_operations = {
+	.owner		= THIS_MODULE,
+	.llseek		= proc_bus_pci_lseek,
+	.read		= proc_bus_pci_read,
+	.write		= proc_bus_pci_write,
+	.unlocked_ioctl	= proc_bus_pci_ioctl,
+	.compat_ioctl	= proc_bus_pci_ioctl,
+#ifdef HAVE_PCI_MMAP
+	.open		= proc_bus_pci_open,
+	.release	= proc_bus_pci_release,
+	.mmap		= proc_bus_pci_mmap,
+#ifdef HAVE_ARCH_PCI_GET_UNMAPPED_AREA
+	.get_unmapped_area = get_pci_unmapped_area,
+#endif /* HAVE_ARCH_PCI_GET_UNMAPPED_AREA */
+#endif /* HAVE_PCI_MMAP */
+};
+
+/* iterator */
+static void *pci_seq_start(struct seq_file *m, loff_t *pos)
+{
+	struct pci_dev *dev = NULL;
+	loff_t n = *pos;
+
+	for_each_pci_dev(dev) {
+		if (!n--)
+			break;
+	}
+	return dev;
+}
+
+static void *pci_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct pci_dev *dev = v;
+
+	(*pos)++;
+	dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
+	return dev;
+}
+
+static void pci_seq_stop(struct seq_file *m, void *v)
+{
+	if (v) {
+		struct pci_dev *dev = v;
+		pci_dev_put(dev);
+	}
+}
+
+static int show_device(struct seq_file *m, void *v)
+{
+	const struct pci_dev *dev = v;
+	const struct pci_driver *drv;
+	int i;
+
+	if (dev == NULL)
+		return 0;
+
+	drv = pci_dev_driver(dev);
+	seq_printf(m, "%02x%02x\t%04x%04x\t%x",
+			dev->bus->number,
+			dev->devfn,
+			dev->vendor,
+			dev->device,
+			dev->irq);
+
+	/* only print standard and ROM resources to preserve compatibility */
+	for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
+		resource_size_t start, end;
+		pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
+		seq_printf(m, "\t%16llx",
+			(unsigned long long)(start |
+			(dev->resource[i].flags & PCI_REGION_FLAG_MASK)));
+	}
+	for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
+		resource_size_t start, end;
+		pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
+		seq_printf(m, "\t%16llx",
+			dev->resource[i].start < dev->resource[i].end ?
+			(unsigned long long)(end - start) + 1 : 0);
+	}
+	seq_putc(m, '\t');
+	if (drv)
+		seq_printf(m, "%s", drv->name);
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static const struct seq_operations proc_bus_pci_devices_op = {
+	.start	= pci_seq_start,
+	.next	= pci_seq_next,
+	.stop	= pci_seq_stop,
+	.show	= show_device
+};
+
+static struct proc_dir_entry *proc_bus_pci_dir;
+
+int pci_proc_attach_device(struct pci_dev *dev)
+{
+	struct pci_bus *bus = dev->bus;
+	struct proc_dir_entry *e;
+	char name[16];
+
+	if (!proc_initialized)
+		return -EACCES;
+
+	if (!bus->procdir) {
+		if (pci_proc_domain(bus)) {
+			sprintf(name, "%04x:%02x", pci_domain_nr(bus),
+					bus->number);
+		} else {
+			sprintf(name, "%02x", bus->number);
+		}
+		bus->procdir = proc_mkdir(name, proc_bus_pci_dir);
+		if (!bus->procdir)
+			return -ENOMEM;
+	}
+
+	sprintf(name, "%02x.%x", PCI_SLOT(dev->devfn), PCI_FUNC(dev->devfn));
+	e = proc_create_data(name, S_IFREG | S_IRUGO | S_IWUSR, bus->procdir,
+			     &proc_bus_pci_operations, dev);
+	if (!e)
+		return -ENOMEM;
+	e->size = dev->cfg_size;
+	dev->procent = e;
+
+	return 0;
+}
+
+int pci_proc_detach_device(struct pci_dev *dev)
+{
+	struct proc_dir_entry *e;
+
+	if ((e = dev->procent)) {
+		remove_proc_entry(e->name, dev->bus->procdir);
+		dev->procent = NULL;
+	}
+	return 0;
+}
+
+#if 0
+int pci_proc_attach_bus(struct pci_bus* bus)
+{
+	struct proc_dir_entry *de = bus->procdir;
+
+	if (!proc_initialized)
+		return -EACCES;
+
+	if (!de) {
+		char name[16];
+		sprintf(name, "%02x", bus->number);
+		de = bus->procdir = proc_mkdir(name, proc_bus_pci_dir);
+		if (!de)
+			return -ENOMEM;
+	}
+	return 0;
+}
+#endif  /*  0  */
+
+int pci_proc_detach_bus(struct pci_bus* bus)
+{
+	struct proc_dir_entry *de = bus->procdir;
+	if (de)
+		remove_proc_entry(de->name, proc_bus_pci_dir);
+	return 0;
+}
+
+static int proc_bus_pci_dev_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &proc_bus_pci_devices_op);
+}
+static const struct file_operations proc_bus_pci_dev_operations = {
+	.owner		= THIS_MODULE,
+	.open		= proc_bus_pci_dev_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int __init pci_proc_init(void)
+{
+	struct pci_dev *dev = NULL;
+	proc_bus_pci_dir = proc_mkdir("bus/pci", NULL);
+	proc_create("devices", 0, proc_bus_pci_dir,
+		    &proc_bus_pci_dev_operations);
+	proc_initialized = 1;
+	for_each_pci_dev(dev)
+		pci_proc_attach_device(dev);
+
+	return 0;
+}
+
+device_initcall(pci_proc_init);
+
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
new file mode 100644
index 00000000..a6b07dda
--- /dev/null
+++ b/drivers/pci/quirks.c
@@ -0,0 +1,3045 @@
+/*
+ *  This file contains work-arounds for many known PCI hardware
+ *  bugs.  Devices present only on certain architectures (host
+ *  bridges et cetera) should be handled in arch-specific code.
+ *
+ *  Note: any quirks for hotpluggable devices must _NOT_ be declared __init.
+ *
+ *  Copyright (c) 1999 Martin Mares <mj@ucw.cz>
+ *
+ *  Init/reset quirks for USB host controllers should be in the
+ *  USB quirks file, where their drivers can access reuse it.
+ *
+ *  The bridge optimization stuff has been removed. If you really
+ *  have a silly BIOS which is unable to set your host bridge right,
+ *  use the PowerTweak utility (see http://powertweak.sourceforge.net).
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/acpi.h>
+#include <linux/kallsyms.h>
+#include <linux/dmi.h>
+#include <linux/pci-aspm.h>
+#include <linux/ioport.h>
+#include <asm/dma.h>	/* isa_dma_bridge_buggy */
+#include "pci.h"
+
+/*
+ * This quirk function disables memory decoding and releases memory resources
+ * of the device specified by kernel's boot parameter 'pci=resource_alignment='.
+ * It also rounds up size to specified alignment.
+ * Later on, the kernel will assign page-aligned memory resource back
+ * to the device.
+ */
+static void __devinit quirk_resource_alignment(struct pci_dev *dev)
+{
+	int i;
+	struct resource *r;
+	resource_size_t align, size;
+	u16 command;
+
+	if (!pci_is_reassigndev(dev))
+		return;
+
+	if (dev->hdr_type == PCI_HEADER_TYPE_NORMAL &&
+	    (dev->class >> 8) == PCI_CLASS_BRIDGE_HOST) {
+		dev_warn(&dev->dev,
+			"Can't reassign resources to host bridge.\n");
+		return;
+	}
+
+	dev_info(&dev->dev,
+		"Disabling memory decoding and releasing memory resources.\n");
+	pci_read_config_word(dev, PCI_COMMAND, &command);
+	command &= ~PCI_COMMAND_MEMORY;
+	pci_write_config_word(dev, PCI_COMMAND, command);
+
+	align = pci_specified_resource_alignment(dev);
+	for (i=0; i < PCI_BRIDGE_RESOURCES; i++) {
+		r = &dev->resource[i];
+		if (!(r->flags & IORESOURCE_MEM))
+			continue;
+		size = resource_size(r);
+		if (size < align) {
+			size = align;
+			dev_info(&dev->dev,
+				"Rounding up size of resource #%d to %#llx.\n",
+				i, (unsigned long long)size);
+		}
+		r->end = size - 1;
+		r->start = 0;
+	}
+	/* Need to disable bridge's resource window,
+	 * to enable the kernel to reassign new resource
+	 * window later on.
+	 */
+	if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE &&
+	    (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) {
+		for (i = PCI_BRIDGE_RESOURCES; i < PCI_NUM_RESOURCES; i++) {
+			r = &dev->resource[i];
+			if (!(r->flags & IORESOURCE_MEM))
+				continue;
+			r->end = resource_size(r) - 1;
+			r->start = 0;
+		}
+		pci_disable_bridge_window(dev);
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, quirk_resource_alignment);
+
+/*
+ * Decoding should be disabled for a PCI device during BAR sizing to avoid
+ * conflict. But doing so may cause problems on host bridge and perhaps other
+ * key system devices. For devices that need to have mmio decoding always-on,
+ * we need to set the dev->mmio_always_on bit.
+ */
+static void __devinit quirk_mmio_always_on(struct pci_dev *dev)
+{
+	if ((dev->class >> 8) == PCI_CLASS_BRIDGE_HOST)
+		dev->mmio_always_on = 1;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_ANY_ID, PCI_ANY_ID, quirk_mmio_always_on);
+
+/* The Mellanox Tavor device gives false positive parity errors
+ * Mark this device with a broken_parity_status, to allow
+ * PCI scanning code to "skip" this now blacklisted device.
+ */
+static void __devinit quirk_mellanox_tavor(struct pci_dev *dev)
+{
+	dev->broken_parity_status = 1;	/* This device gives false positives */
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MELLANOX,PCI_DEVICE_ID_MELLANOX_TAVOR,quirk_mellanox_tavor);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MELLANOX,PCI_DEVICE_ID_MELLANOX_TAVOR_BRIDGE,quirk_mellanox_tavor);
+
+/* Deal with broken BIOS'es that neglect to enable passive release,
+   which can cause problems in combination with the 82441FX/PPro MTRRs */
+static void quirk_passive_release(struct pci_dev *dev)
+{
+	struct pci_dev *d = NULL;
+	unsigned char dlc;
+
+	/* We have to make sure a particular bit is set in the PIIX3
+	   ISA bridge, so we have to go out and find it. */
+	while ((d = pci_get_device(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371SB_0, d))) {
+		pci_read_config_byte(d, 0x82, &dlc);
+		if (!(dlc & 1<<1)) {
+			dev_info(&d->dev, "PIIX3: Enabling Passive Release\n");
+			dlc |= 1<<1;
+			pci_write_config_byte(d, 0x82, dlc);
+		}
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82441,	quirk_passive_release);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82441,	quirk_passive_release);
+
+/*  The VIA VP2/VP3/MVP3 seem to have some 'features'. There may be a workaround
+    but VIA don't answer queries. If you happen to have good contacts at VIA
+    ask them for me please -- Alan 
+    
+    This appears to be BIOS not version dependent. So presumably there is a 
+    chipset level fix */
+    
+static void __devinit quirk_isa_dma_hangs(struct pci_dev *dev)
+{
+	if (!isa_dma_bridge_buggy) {
+		isa_dma_bridge_buggy=1;
+		dev_info(&dev->dev, "Activating ISA DMA hang workarounds\n");
+	}
+}
+	/*
+	 * Its not totally clear which chipsets are the problematic ones
+	 * We know 82C586 and 82C596 variants are affected.
+	 */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C586_0,	quirk_isa_dma_hangs);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C596,	quirk_isa_dma_hangs);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_82371SB_0,  quirk_isa_dma_hangs);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL,	PCI_DEVICE_ID_AL_M1533, 	quirk_isa_dma_hangs);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NEC,	PCI_DEVICE_ID_NEC_CBUS_1,	quirk_isa_dma_hangs);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NEC,	PCI_DEVICE_ID_NEC_CBUS_2,	quirk_isa_dma_hangs);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NEC,	PCI_DEVICE_ID_NEC_CBUS_3,	quirk_isa_dma_hangs);
+
+/*
+ * Intel NM10 "TigerPoint" LPC PM1a_STS.BM_STS must be clear
+ * for some HT machines to use C4 w/o hanging.
+ */
+static void __devinit quirk_tigerpoint_bm_sts(struct pci_dev *dev)
+{
+	u32 pmbase;
+	u16 pm1a;
+
+	pci_read_config_dword(dev, 0x40, &pmbase);
+	pmbase = pmbase & 0xff80;
+	pm1a = inw(pmbase);
+
+	if (pm1a & 0x10) {
+		dev_info(&dev->dev, FW_BUG "TigerPoint LPC.BM_STS cleared\n");
+		outw(0x10, pmbase);
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGP_LPC, quirk_tigerpoint_bm_sts);
+
+/*
+ *	Chipsets where PCI->PCI transfers vanish or hang
+ */
+static void __devinit quirk_nopcipci(struct pci_dev *dev)
+{
+	if ((pci_pci_problems & PCIPCI_FAIL)==0) {
+		dev_info(&dev->dev, "Disabling direct PCI/PCI transfers\n");
+		pci_pci_problems |= PCIPCI_FAIL;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SI,	PCI_DEVICE_ID_SI_5597,		quirk_nopcipci);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SI,	PCI_DEVICE_ID_SI_496,		quirk_nopcipci);
+
+static void __devinit quirk_nopciamd(struct pci_dev *dev)
+{
+	u8 rev;
+	pci_read_config_byte(dev, 0x08, &rev);
+	if (rev == 0x13) {
+		/* Erratum 24 */
+		dev_info(&dev->dev, "Chipset erratum: Disabling direct PCI/AGP transfers\n");
+		pci_pci_problems |= PCIAGP_FAIL;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD,	PCI_DEVICE_ID_AMD_8151_0,	quirk_nopciamd);
+
+/*
+ *	Triton requires workarounds to be used by the drivers
+ */
+static void __devinit quirk_triton(struct pci_dev *dev)
+{
+	if ((pci_pci_problems&PCIPCI_TRITON)==0) {
+		dev_info(&dev->dev, "Limiting direct PCI/PCI transfers\n");
+		pci_pci_problems |= PCIPCI_TRITON;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82437, 	quirk_triton);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82437VX, 	quirk_triton);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82439, 	quirk_triton);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82439TX, 	quirk_triton);
+
+/*
+ *	VIA Apollo KT133 needs PCI latency patch
+ *	Made according to a windows driver based patch by George E. Breese
+ *	see PCI Latency Adjust on http://www.viahardware.com/download/viatweak.shtm
+ *	and http://www.georgebreese.com/net/software/#PCI
+ *      Also see http://www.au-ja.org/review-kt133a-1-en.phtml for
+ *      the info on which Mr Breese based his work.
+ *
+ *	Updated based on further information from the site and also on
+ *	information provided by VIA 
+ */
+static void quirk_vialatency(struct pci_dev *dev)
+{
+	struct pci_dev *p;
+	u8 busarb;
+	/* Ok we have a potential problem chipset here. Now see if we have
+	   a buggy southbridge */
+	   
+	p = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_82C686, NULL);
+	if (p!=NULL) {
+		/* 0x40 - 0x4f == 686B, 0x10 - 0x2f == 686A; thanks Dan Hollis */
+		/* Check for buggy part revisions */
+		if (p->revision < 0x40 || p->revision > 0x42)
+			goto exit;
+	} else {
+		p = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8231, NULL);
+		if (p==NULL)	/* No problem parts */
+			goto exit;
+		/* Check for buggy part revisions */
+		if (p->revision < 0x10 || p->revision > 0x12)
+			goto exit;
+	}
+	
+	/*
+	 *	Ok we have the problem. Now set the PCI master grant to 
+	 *	occur every master grant. The apparent bug is that under high
+	 *	PCI load (quite common in Linux of course) you can get data
+	 *	loss when the CPU is held off the bus for 3 bus master requests
+	 *	This happens to include the IDE controllers....
+	 *
+	 *	VIA only apply this fix when an SB Live! is present but under
+	 *	both Linux and Windows this isn't enough, and we have seen
+	 *	corruption without SB Live! but with things like 3 UDMA IDE
+	 *	controllers. So we ignore that bit of the VIA recommendation..
+	 */
+
+	pci_read_config_byte(dev, 0x76, &busarb);
+	/* Set bit 4 and bi 5 of byte 76 to 0x01 
+	   "Master priority rotation on every PCI master grant */
+	busarb &= ~(1<<5);
+	busarb |= (1<<4);
+	pci_write_config_byte(dev, 0x76, busarb);
+	dev_info(&dev->dev, "Applying VIA southbridge workaround\n");
+exit:
+	pci_dev_put(p);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8363_0,	quirk_vialatency);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8371_1,	quirk_vialatency);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8361,		quirk_vialatency);
+/* Must restore this on a resume from RAM */
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8363_0,	quirk_vialatency);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8371_1,	quirk_vialatency);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8361,		quirk_vialatency);
+
+/*
+ *	VIA Apollo VP3 needs ETBF on BT848/878
+ */
+static void __devinit quirk_viaetbf(struct pci_dev *dev)
+{
+	if ((pci_pci_problems&PCIPCI_VIAETBF)==0) {
+		dev_info(&dev->dev, "Limiting direct PCI/PCI transfers\n");
+		pci_pci_problems |= PCIPCI_VIAETBF;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C597_0,	quirk_viaetbf);
+
+static void __devinit quirk_vsfx(struct pci_dev *dev)
+{
+	if ((pci_pci_problems&PCIPCI_VSFX)==0) {
+		dev_info(&dev->dev, "Limiting direct PCI/PCI transfers\n");
+		pci_pci_problems |= PCIPCI_VSFX;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C576,	quirk_vsfx);
+
+/*
+ *	Ali Magik requires workarounds to be used by the drivers
+ *	that DMA to AGP space. Latency must be set to 0xA and triton
+ *	workaround applied too
+ *	[Info kindly provided by ALi]
+ */	
+static void __init quirk_alimagik(struct pci_dev *dev)
+{
+	if ((pci_pci_problems&PCIPCI_ALIMAGIK)==0) {
+		dev_info(&dev->dev, "Limiting direct PCI/PCI transfers\n");
+		pci_pci_problems |= PCIPCI_ALIMAGIK|PCIPCI_TRITON;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, 	PCI_DEVICE_ID_AL_M1647, 	quirk_alimagik);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, 	PCI_DEVICE_ID_AL_M1651, 	quirk_alimagik);
+
+/*
+ *	Natoma has some interesting boundary conditions with Zoran stuff
+ *	at least
+ */
+static void __devinit quirk_natoma(struct pci_dev *dev)
+{
+	if ((pci_pci_problems&PCIPCI_NATOMA)==0) {
+		dev_info(&dev->dev, "Limiting direct PCI/PCI transfers\n");
+		pci_pci_problems |= PCIPCI_NATOMA;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82441, 	quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82443LX_0, 	quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82443LX_1, 	quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82443BX_0, 	quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82443BX_1, 	quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82443BX_2, 	quirk_natoma);
+
+/*
+ *  This chip can cause PCI parity errors if config register 0xA0 is read
+ *  while DMAs are occurring.
+ */
+static void __devinit quirk_citrine(struct pci_dev *dev)
+{
+	dev->cfg_size = 0xA0;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM,	PCI_DEVICE_ID_IBM_CITRINE,	quirk_citrine);
+
+/*
+ *  S3 868 and 968 chips report region size equal to 32M, but they decode 64M.
+ *  If it's needed, re-allocate the region.
+ */
+static void __devinit quirk_s3_64M(struct pci_dev *dev)
+{
+	struct resource *r = &dev->resource[0];
+
+	if ((r->start & 0x3ffffff) || r->end != r->start + 0x3ffffff) {
+		r->start = 0;
+		r->end = 0x3ffffff;
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_S3,	PCI_DEVICE_ID_S3_868,		quirk_s3_64M);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_S3,	PCI_DEVICE_ID_S3_968,		quirk_s3_64M);
+
+/*
+ * Some CS5536 BIOSes (for example, the Soekris NET5501 board w/ comBIOS
+ * ver. 1.33  20070103) don't set the correct ISA PCI region header info.
+ * BAR0 should be 8 bytes; instead, it may be set to something like 8k
+ * (which conflicts w/ BAR1's memory range).
+ */
+static void __devinit quirk_cs5536_vsa(struct pci_dev *dev)
+{
+	if (pci_resource_len(dev, 0) != 8) {
+		struct resource *res = &dev->resource[0];
+		res->end = res->start + 8 - 1;
+		dev_info(&dev->dev, "CS5536 ISA bridge bug detected "
+				"(incorrect header); workaround applied.\n");
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA, quirk_cs5536_vsa);
+
+static void __devinit quirk_io_region(struct pci_dev *dev, unsigned region,
+	unsigned size, int nr, const char *name)
+{
+	region &= ~(size-1);
+	if (region) {
+		struct pci_bus_region bus_region;
+		struct resource *res = dev->resource + nr;
+
+		res->name = pci_name(dev);
+		res->start = region;
+		res->end = region + size - 1;
+		res->flags = IORESOURCE_IO;
+
+		/* Convert from PCI bus to resource space.  */
+		bus_region.start = res->start;
+		bus_region.end = res->end;
+		pcibios_bus_to_resource(dev, res, &bus_region);
+
+		if (pci_claim_resource(dev, nr) == 0)
+			dev_info(&dev->dev, "quirk: %pR claimed by %s\n",
+				 res, name);
+	}
+}	
+
+/*
+ *	ATI Northbridge setups MCE the processor if you even
+ *	read somewhere between 0x3b0->0x3bb or read 0x3d3
+ */
+static void __devinit quirk_ati_exploding_mce(struct pci_dev *dev)
+{
+	dev_info(&dev->dev, "ATI Northbridge, reserving I/O ports 0x3b0 to 0x3bb\n");
+	/* Mae rhaid i ni beidio ag edrych ar y lleoliadiau I/O hyn */
+	request_region(0x3b0, 0x0C, "RadeonIGP");
+	request_region(0x3d3, 0x01, "RadeonIGP");
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI,	PCI_DEVICE_ID_ATI_RS100,   quirk_ati_exploding_mce);
+
+/*
+ * Let's make the southbridge information explicit instead
+ * of having to worry about people probing the ACPI areas,
+ * for example.. (Yes, it happens, and if you read the wrong
+ * ACPI register it will put the machine to sleep with no
+ * way of waking it up again. Bummer).
+ *
+ * ALI M7101: Two IO regions pointed to by words at
+ *	0xE0 (64 bytes of ACPI registers)
+ *	0xE2 (32 bytes of SMB registers)
+ */
+static void __devinit quirk_ali7101_acpi(struct pci_dev *dev)
+{
+	u16 region;
+
+	pci_read_config_word(dev, 0xE0, &region);
+	quirk_io_region(dev, region, 64, PCI_BRIDGE_RESOURCES, "ali7101 ACPI");
+	pci_read_config_word(dev, 0xE2, &region);
+	quirk_io_region(dev, region, 32, PCI_BRIDGE_RESOURCES+1, "ali7101 SMB");
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AL,	PCI_DEVICE_ID_AL_M7101,		quirk_ali7101_acpi);
+
+static void piix4_io_quirk(struct pci_dev *dev, const char *name, unsigned int port, unsigned int enable)
+{
+	u32 devres;
+	u32 mask, size, base;
+
+	pci_read_config_dword(dev, port, &devres);
+	if ((devres & enable) != enable)
+		return;
+	mask = (devres >> 16) & 15;
+	base = devres & 0xffff;
+	size = 16;
+	for (;;) {
+		unsigned bit = size >> 1;
+		if ((bit & mask) == bit)
+			break;
+		size = bit;
+	}
+	/*
+	 * For now we only print it out. Eventually we'll want to
+	 * reserve it (at least if it's in the 0x1000+ range), but
+	 * let's get enough confirmation reports first. 
+	 */
+	base &= -size;
+	dev_info(&dev->dev, "%s PIO at %04x-%04x\n", name, base, base + size - 1);
+}
+
+static void piix4_mem_quirk(struct pci_dev *dev, const char *name, unsigned int port, unsigned int enable)
+{
+	u32 devres;
+	u32 mask, size, base;
+
+	pci_read_config_dword(dev, port, &devres);
+	if ((devres & enable) != enable)
+		return;
+	base = devres & 0xffff0000;
+	mask = (devres & 0x3f) << 16;
+	size = 128 << 16;
+	for (;;) {
+		unsigned bit = size >> 1;
+		if ((bit & mask) == bit)
+			break;
+		size = bit;
+	}
+	/*
+	 * For now we only print it out. Eventually we'll want to
+	 * reserve it, but let's get enough confirmation reports first. 
+	 */
+	base &= -size;
+	dev_info(&dev->dev, "%s MMIO at %04x-%04x\n", name, base, base + size - 1);
+}
+
+/*
+ * PIIX4 ACPI: Two IO regions pointed to by longwords at
+ *	0x40 (64 bytes of ACPI registers)
+ *	0x90 (16 bytes of SMB registers)
+ * and a few strange programmable PIIX4 device resources.
+ */
+static void __devinit quirk_piix4_acpi(struct pci_dev *dev)
+{
+	u32 region, res_a;
+
+	pci_read_config_dword(dev, 0x40, &region);
+	quirk_io_region(dev, region, 64, PCI_BRIDGE_RESOURCES, "PIIX4 ACPI");
+	pci_read_config_dword(dev, 0x90, &region);
+	quirk_io_region(dev, region, 16, PCI_BRIDGE_RESOURCES+1, "PIIX4 SMB");
+
+	/* Device resource A has enables for some of the other ones */
+	pci_read_config_dword(dev, 0x5c, &res_a);
+
+	piix4_io_quirk(dev, "PIIX4 devres B", 0x60, 3 << 21);
+	piix4_io_quirk(dev, "PIIX4 devres C", 0x64, 3 << 21);
+
+	/* Device resource D is just bitfields for static resources */
+
+	/* Device 12 enabled? */
+	if (res_a & (1 << 29)) {
+		piix4_io_quirk(dev, "PIIX4 devres E", 0x68, 1 << 20);
+		piix4_mem_quirk(dev, "PIIX4 devres F", 0x6c, 1 << 7);
+	}
+	/* Device 13 enabled? */
+	if (res_a & (1 << 30)) {
+		piix4_io_quirk(dev, "PIIX4 devres G", 0x70, 1 << 20);
+		piix4_mem_quirk(dev, "PIIX4 devres H", 0x74, 1 << 7);
+	}
+	piix4_io_quirk(dev, "PIIX4 devres I", 0x78, 1 << 20);
+	piix4_io_quirk(dev, "PIIX4 devres J", 0x7c, 1 << 20);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82371AB_3,	quirk_piix4_acpi);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82443MX_3,	quirk_piix4_acpi);
+
+#define ICH_PMBASE	0x40
+#define ICH_ACPI_CNTL	0x44
+#define  ICH4_ACPI_EN	0x10
+#define  ICH6_ACPI_EN	0x80
+#define ICH4_GPIOBASE	0x58
+#define ICH4_GPIO_CNTL	0x5c
+#define  ICH4_GPIO_EN	0x10
+#define ICH6_GPIOBASE	0x48
+#define ICH6_GPIO_CNTL	0x4c
+#define  ICH6_GPIO_EN	0x10
+
+/*
+ * ICH4, ICH4-M, ICH5, ICH5-M ACPI: Three IO regions pointed to by longwords at
+ *	0x40 (128 bytes of ACPI, GPIO & TCO registers)
+ *	0x58 (64 bytes of GPIO I/O space)
+ */
+static void __devinit quirk_ich4_lpc_acpi(struct pci_dev *dev)
+{
+	u32 region;
+	u8 enable;
+
+	/*
+	 * The check for PCIBIOS_MIN_IO is to ensure we won't create a conflict
+	 * with low legacy (and fixed) ports. We don't know the decoding
+	 * priority and can't tell whether the legacy device or the one created
+	 * here is really at that address.  This happens on boards with broken
+	 * BIOSes.
+	*/
+
+	pci_read_config_byte(dev, ICH_ACPI_CNTL, &enable);
+	if (enable & ICH4_ACPI_EN) {
+		pci_read_config_dword(dev, ICH_PMBASE, &region);
+		region &= PCI_BASE_ADDRESS_IO_MASK;
+		if (region >= PCIBIOS_MIN_IO)
+			quirk_io_region(dev, region, 128, PCI_BRIDGE_RESOURCES,
+					"ICH4 ACPI/GPIO/TCO");
+	}
+
+	pci_read_config_byte(dev, ICH4_GPIO_CNTL, &enable);
+	if (enable & ICH4_GPIO_EN) {
+		pci_read_config_dword(dev, ICH4_GPIOBASE, &region);
+		region &= PCI_BASE_ADDRESS_IO_MASK;
+		if (region >= PCIBIOS_MIN_IO)
+			quirk_io_region(dev, region, 64,
+					PCI_BRIDGE_RESOURCES + 1, "ICH4 GPIO");
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_82801AA_0,		quirk_ich4_lpc_acpi);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_82801AB_0,		quirk_ich4_lpc_acpi);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_82801BA_0,		quirk_ich4_lpc_acpi);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_82801BA_10,	quirk_ich4_lpc_acpi);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_82801CA_0,		quirk_ich4_lpc_acpi);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_82801CA_12,	quirk_ich4_lpc_acpi);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_82801DB_0,		quirk_ich4_lpc_acpi);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_82801DB_12,	quirk_ich4_lpc_acpi);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_82801EB_0,		quirk_ich4_lpc_acpi);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_ESB_1,		quirk_ich4_lpc_acpi);
+
+static void __devinit ich6_lpc_acpi_gpio(struct pci_dev *dev)
+{
+	u32 region;
+	u8 enable;
+
+	pci_read_config_byte(dev, ICH_ACPI_CNTL, &enable);
+	if (enable & ICH6_ACPI_EN) {
+		pci_read_config_dword(dev, ICH_PMBASE, &region);
+		region &= PCI_BASE_ADDRESS_IO_MASK;
+		if (region >= PCIBIOS_MIN_IO)
+			quirk_io_region(dev, region, 128, PCI_BRIDGE_RESOURCES,
+					"ICH6 ACPI/GPIO/TCO");
+	}
+
+	pci_read_config_byte(dev, ICH6_GPIO_CNTL, &enable);
+	if (enable & ICH6_GPIO_EN) {
+		pci_read_config_dword(dev, ICH6_GPIOBASE, &region);
+		region &= PCI_BASE_ADDRESS_IO_MASK;
+		if (region >= PCIBIOS_MIN_IO)
+			quirk_io_region(dev, region, 64,
+					PCI_BRIDGE_RESOURCES + 1, "ICH6 GPIO");
+	}
+}
+
+static void __devinit ich6_lpc_generic_decode(struct pci_dev *dev, unsigned reg, const char *name, int dynsize)
+{
+	u32 val;
+	u32 size, base;
+
+	pci_read_config_dword(dev, reg, &val);
+
+	/* Enabled? */
+	if (!(val & 1))
+		return;
+	base = val & 0xfffc;
+	if (dynsize) {
+		/*
+		 * This is not correct. It is 16, 32 or 64 bytes depending on
+		 * register D31:F0:ADh bits 5:4.
+		 *
+		 * But this gets us at least _part_ of it.
+		 */
+		size = 16;
+	} else {
+		size = 128;
+	}
+	base &= ~(size-1);
+
+	/* Just print it out for now. We should reserve it after more debugging */
+	dev_info(&dev->dev, "%s PIO at %04x-%04x\n", name, base, base+size-1);
+}
+
+static void __devinit quirk_ich6_lpc(struct pci_dev *dev)
+{
+	/* Shared ACPI/GPIO decode with all ICH6+ */
+	ich6_lpc_acpi_gpio(dev);
+
+	/* ICH6-specific generic IO decode */
+	ich6_lpc_generic_decode(dev, 0x84, "LPC Generic IO decode 1", 0);
+	ich6_lpc_generic_decode(dev, 0x88, "LPC Generic IO decode 2", 1);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH6_0, quirk_ich6_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH6_1, quirk_ich6_lpc);
+
+static void __devinit ich7_lpc_generic_decode(struct pci_dev *dev, unsigned reg, const char *name)
+{
+	u32 val;
+	u32 mask, base;
+
+	pci_read_config_dword(dev, reg, &val);
+
+	/* Enabled? */
+	if (!(val & 1))
+		return;
+
+	/*
+	 * IO base in bits 15:2, mask in bits 23:18, both
+	 * are dword-based
+	 */
+	base = val & 0xfffc;
+	mask = (val >> 16) & 0xfc;
+	mask |= 3;
+
+	/* Just print it out for now. We should reserve it after more debugging */
+	dev_info(&dev->dev, "%s PIO at %04x (mask %04x)\n", name, base, mask);
+}
+
+/* ICH7-10 has the same common LPC generic IO decode registers */
+static void __devinit quirk_ich7_lpc(struct pci_dev *dev)
+{
+	/* We share the common ACPI/GPIO decode with ICH6 */
+	ich6_lpc_acpi_gpio(dev);
+
+	/* And have 4 ICH7+ generic decodes */
+	ich7_lpc_generic_decode(dev, 0x84, "ICH7 LPC Generic IO decode 1");
+	ich7_lpc_generic_decode(dev, 0x88, "ICH7 LPC Generic IO decode 2");
+	ich7_lpc_generic_decode(dev, 0x8c, "ICH7 LPC Generic IO decode 3");
+	ich7_lpc_generic_decode(dev, 0x90, "ICH7 LPC Generic IO decode 4");
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH7_0, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH7_1, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH7_31, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH8_0, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH8_2, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH8_3, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH8_1, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH8_4, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH9_2, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH9_4, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH9_7, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH9_8, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,   PCI_DEVICE_ID_INTEL_ICH10_1, quirk_ich7_lpc);
+
+/*
+ * VIA ACPI: One IO region pointed to by longword at
+ *	0x48 or 0x20 (256 bytes of ACPI registers)
+ */
+static void __devinit quirk_vt82c586_acpi(struct pci_dev *dev)
+{
+	u32 region;
+
+	if (dev->revision & 0x10) {
+		pci_read_config_dword(dev, 0x48, &region);
+		region &= PCI_BASE_ADDRESS_IO_MASK;
+		quirk_io_region(dev, region, 256, PCI_BRIDGE_RESOURCES, "vt82c586 ACPI");
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C586_3,	quirk_vt82c586_acpi);
+
+/*
+ * VIA VT82C686 ACPI: Three IO region pointed to by (long)words at
+ *	0x48 (256 bytes of ACPI registers)
+ *	0x70 (128 bytes of hardware monitoring register)
+ *	0x90 (16 bytes of SMB registers)
+ */
+static void __devinit quirk_vt82c686_acpi(struct pci_dev *dev)
+{
+	u16 hm;
+	u32 smb;
+
+	quirk_vt82c586_acpi(dev);
+
+	pci_read_config_word(dev, 0x70, &hm);
+	hm &= PCI_BASE_ADDRESS_IO_MASK;
+	quirk_io_region(dev, hm, 128, PCI_BRIDGE_RESOURCES + 1, "vt82c686 HW-mon");
+
+	pci_read_config_dword(dev, 0x90, &smb);
+	smb &= PCI_BASE_ADDRESS_IO_MASK;
+	quirk_io_region(dev, smb, 16, PCI_BRIDGE_RESOURCES + 2, "vt82c686 SMB");
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C686_4,	quirk_vt82c686_acpi);
+
+/*
+ * VIA VT8235 ISA Bridge: Two IO regions pointed to by words at
+ *	0x88 (128 bytes of power management registers)
+ *	0xd0 (16 bytes of SMB registers)
+ */
+static void __devinit quirk_vt8235_acpi(struct pci_dev *dev)
+{
+	u16 pm, smb;
+
+	pci_read_config_word(dev, 0x88, &pm);
+	pm &= PCI_BASE_ADDRESS_IO_MASK;
+	quirk_io_region(dev, pm, 128, PCI_BRIDGE_RESOURCES, "vt8235 PM");
+
+	pci_read_config_word(dev, 0xd0, &smb);
+	smb &= PCI_BASE_ADDRESS_IO_MASK;
+	quirk_io_region(dev, smb, 16, PCI_BRIDGE_RESOURCES + 1, "vt8235 SMB");
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8235,	quirk_vt8235_acpi);
+
+/*
+ * TI XIO2000a PCIe-PCI Bridge erroneously reports it supports fast back-to-back:
+ *	Disable fast back-to-back on the secondary bus segment
+ */
+static void __devinit quirk_xio2000a(struct pci_dev *dev)
+{
+	struct pci_dev *pdev;
+	u16 command;
+
+	dev_warn(&dev->dev, "TI XIO2000a quirk detected; "
+		"secondary bus fast back-to-back transfers disabled\n");
+	list_for_each_entry(pdev, &dev->subordinate->devices, bus_list) {
+		pci_read_config_word(pdev, PCI_COMMAND, &command);
+		if (command & PCI_COMMAND_FAST_BACK)
+			pci_write_config_word(pdev, PCI_COMMAND, command & ~PCI_COMMAND_FAST_BACK);
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_TI, PCI_DEVICE_ID_TI_XIO2000A,
+			quirk_xio2000a);
+
+#ifdef CONFIG_X86_IO_APIC 
+
+#include <asm/io_apic.h>
+
+/*
+ * VIA 686A/B: If an IO-APIC is active, we need to route all on-chip
+ * devices to the external APIC.
+ *
+ * TODO: When we have device-specific interrupt routers,
+ * this code will go away from quirks.
+ */
+static void quirk_via_ioapic(struct pci_dev *dev)
+{
+	u8 tmp;
+	
+	if (nr_ioapics < 1)
+		tmp = 0;    /* nothing routed to external APIC */
+	else
+		tmp = 0x1f; /* all known bits (4-0) routed to external APIC */
+		
+	dev_info(&dev->dev, "%sbling VIA external APIC routing\n",
+	       tmp == 0 ? "Disa" : "Ena");
+
+	/* Offset 0x58: External APIC IRQ output control */
+	pci_write_config_byte (dev, 0x58, tmp);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C686,	quirk_via_ioapic);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C686,	quirk_via_ioapic);
+
+/*
+ * VIA 8237: Some BIOSs don't set the 'Bypass APIC De-Assert Message' Bit.
+ * This leads to doubled level interrupt rates.
+ * Set this bit to get rid of cycle wastage.
+ * Otherwise uncritical.
+ */
+static void quirk_via_vt8237_bypass_apic_deassert(struct pci_dev *dev)
+{
+	u8 misc_control2;
+#define BYPASS_APIC_DEASSERT 8
+
+	pci_read_config_byte(dev, 0x5B, &misc_control2);
+	if (!(misc_control2 & BYPASS_APIC_DEASSERT)) {
+		dev_info(&dev->dev, "Bypassing VIA 8237 APIC De-Assert Message\n");
+		pci_write_config_byte(dev, 0x5B, misc_control2|BYPASS_APIC_DEASSERT);
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8237,		quirk_via_vt8237_bypass_apic_deassert);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8237,		quirk_via_vt8237_bypass_apic_deassert);
+
+/*
+ * The AMD io apic can hang the box when an apic irq is masked.
+ * We check all revs >= B0 (yet not in the pre production!) as the bug
+ * is currently marked NoFix
+ *
+ * We have multiple reports of hangs with this chipset that went away with
+ * noapic specified. For the moment we assume it's the erratum. We may be wrong
+ * of course. However the advice is demonstrably good even if so..
+ */
+static void __devinit quirk_amd_ioapic(struct pci_dev *dev)
+{
+	if (dev->revision >= 0x02) {
+		dev_warn(&dev->dev, "I/O APIC: AMD Erratum #22 may be present. In the event of instability try\n");
+		dev_warn(&dev->dev, "        : booting with the \"noapic\" option\n");
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD,	PCI_DEVICE_ID_AMD_VIPER_7410,	quirk_amd_ioapic);
+
+static void __init quirk_ioapic_rmw(struct pci_dev *dev)
+{
+	if (dev->devfn == 0 && dev->bus->number == 0)
+		sis_apic_bug = 1;
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SI,	PCI_ANY_ID,			quirk_ioapic_rmw);
+#endif /* CONFIG_X86_IO_APIC */
+
+/*
+ * Some settings of MMRBC can lead to data corruption so block changes.
+ * See AMD 8131 HyperTransport PCI-X Tunnel Revision Guide
+ */
+static void __init quirk_amd_8131_mmrbc(struct pci_dev *dev)
+{
+	if (dev->subordinate && dev->revision <= 0x12) {
+		dev_info(&dev->dev, "AMD8131 rev %x detected; "
+			"disabling PCI-X MMRBC\n", dev->revision);
+		dev->subordinate->bus_flags |= PCI_BUS_FLAGS_NO_MMRBC;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8131_BRIDGE, quirk_amd_8131_mmrbc);
+
+/*
+ * FIXME: it is questionable that quirk_via_acpi
+ * is needed.  It shows up as an ISA bridge, and does not
+ * support the PCI_INTERRUPT_LINE register at all.  Therefore
+ * it seems like setting the pci_dev's 'irq' to the
+ * value of the ACPI SCI interrupt is only done for convenience.
+ *	-jgarzik
+ */
+static void __devinit quirk_via_acpi(struct pci_dev *d)
+{
+	/*
+	 * VIA ACPI device: SCI IRQ line in PCI config byte 0x42
+	 */
+	u8 irq;
+	pci_read_config_byte(d, 0x42, &irq);
+	irq &= 0xf;
+	if (irq && (irq != 2))
+		d->irq = irq;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C586_3,	quirk_via_acpi);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C686_4,	quirk_via_acpi);
+
+
+/*
+ *	VIA bridges which have VLink
+ */
+
+static int via_vlink_dev_lo = -1, via_vlink_dev_hi = 18;
+
+static void quirk_via_bridge(struct pci_dev *dev)
+{
+	/* See what bridge we have and find the device ranges */
+	switch (dev->device) {
+	case PCI_DEVICE_ID_VIA_82C686:
+		/* The VT82C686 is special, it attaches to PCI and can have
+		   any device number. All its subdevices are functions of
+		   that single device. */
+		via_vlink_dev_lo = PCI_SLOT(dev->devfn);
+		via_vlink_dev_hi = PCI_SLOT(dev->devfn);
+		break;
+	case PCI_DEVICE_ID_VIA_8237:
+	case PCI_DEVICE_ID_VIA_8237A:
+		via_vlink_dev_lo = 15;
+		break;
+	case PCI_DEVICE_ID_VIA_8235:
+		via_vlink_dev_lo = 16;
+		break;
+	case PCI_DEVICE_ID_VIA_8231:
+	case PCI_DEVICE_ID_VIA_8233_0:
+	case PCI_DEVICE_ID_VIA_8233A:
+	case PCI_DEVICE_ID_VIA_8233C_0:
+		via_vlink_dev_lo = 17;
+		break;
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C686,	quirk_via_bridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8231,		quirk_via_bridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8233_0,	quirk_via_bridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8233A,	quirk_via_bridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8233C_0,	quirk_via_bridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8235,		quirk_via_bridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8237,		quirk_via_bridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8237A,	quirk_via_bridge);
+
+/**
+ *	quirk_via_vlink		-	VIA VLink IRQ number update
+ *	@dev: PCI device
+ *
+ *	If the device we are dealing with is on a PIC IRQ we need to
+ *	ensure that the IRQ line register which usually is not relevant
+ *	for PCI cards, is actually written so that interrupts get sent
+ *	to the right place.
+ *	We only do this on systems where a VIA south bridge was detected,
+ *	and only for VIA devices on the motherboard (see quirk_via_bridge
+ *	above).
+ */
+
+static void quirk_via_vlink(struct pci_dev *dev)
+{
+	u8 irq, new_irq;
+
+	/* Check if we have VLink at all */
+	if (via_vlink_dev_lo == -1)
+		return;
+
+	new_irq = dev->irq;
+
+	/* Don't quirk interrupts outside the legacy IRQ range */
+	if (!new_irq || new_irq > 15)
+		return;
+
+	/* Internal device ? */
+	if (dev->bus->number != 0 || PCI_SLOT(dev->devfn) > via_vlink_dev_hi ||
+	    PCI_SLOT(dev->devfn) < via_vlink_dev_lo)
+		return;
+
+	/* This is an internal VLink device on a PIC interrupt. The BIOS
+	   ought to have set this but may not have, so we redo it */
+
+	pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &irq);
+	if (new_irq != irq) {
+		dev_info(&dev->dev, "VIA VLink IRQ fixup, from %d to %d\n",
+			irq, new_irq);
+		udelay(15);	/* unknown if delay really needed */
+		pci_write_config_byte(dev, PCI_INTERRUPT_LINE, new_irq);
+	}
+}
+DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_VIA, PCI_ANY_ID, quirk_via_vlink);
+
+/*
+ * VIA VT82C598 has its device ID settable and many BIOSes
+ * set it to the ID of VT82C597 for backward compatibility.
+ * We need to switch it off to be able to recognize the real
+ * type of the chip.
+ */
+static void __devinit quirk_vt82c598_id(struct pci_dev *dev)
+{
+	pci_write_config_byte(dev, 0xfc, 0);
+	pci_read_config_word(dev, PCI_DEVICE_ID, &dev->device);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C597_0,	quirk_vt82c598_id);
+
+/*
+ * CardBus controllers have a legacy base address that enables them
+ * to respond as i82365 pcmcia controllers.  We don't want them to
+ * do this even if the Linux CardBus driver is not loaded, because
+ * the Linux i82365 driver does not (and should not) handle CardBus.
+ */
+static void quirk_cardbus_legacy(struct pci_dev *dev)
+{
+	if ((PCI_CLASS_BRIDGE_CARDBUS << 8) ^ dev->class)
+		return;
+	pci_write_config_dword(dev, PCI_CB_LEGACY_MODE_BASE, 0);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, quirk_cardbus_legacy);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_ANY_ID, PCI_ANY_ID, quirk_cardbus_legacy);
+
+/*
+ * Following the PCI ordering rules is optional on the AMD762. I'm not
+ * sure what the designers were smoking but let's not inhale...
+ *
+ * To be fair to AMD, it follows the spec by default, its BIOS people
+ * who turn it off!
+ */
+static void quirk_amd_ordering(struct pci_dev *dev)
+{
+	u32 pcic;
+	pci_read_config_dword(dev, 0x4C, &pcic);
+	if ((pcic&6)!=6) {
+		pcic |= 6;
+		dev_warn(&dev->dev, "BIOS failed to enable PCI standards compliance; fixing this error\n");
+		pci_write_config_dword(dev, 0x4C, pcic);
+		pci_read_config_dword(dev, 0x84, &pcic);
+		pcic |= (1<<23);	/* Required in this mode */
+		pci_write_config_dword(dev, 0x84, pcic);
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD,	PCI_DEVICE_ID_AMD_FE_GATE_700C, quirk_amd_ordering);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_AMD,	PCI_DEVICE_ID_AMD_FE_GATE_700C, quirk_amd_ordering);
+
+/*
+ *	DreamWorks provided workaround for Dunord I-3000 problem
+ *
+ *	This card decodes and responds to addresses not apparently
+ *	assigned to it. We force a larger allocation to ensure that
+ *	nothing gets put too close to it.
+ */
+static void __devinit quirk_dunord ( struct pci_dev * dev )
+{
+	struct resource *r = &dev->resource [1];
+	r->start = 0;
+	r->end = 0xffffff;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_DUNORD,	PCI_DEVICE_ID_DUNORD_I3000,	quirk_dunord);
+
+/*
+ * i82380FB mobile docking controller: its PCI-to-PCI bridge
+ * is subtractive decoding (transparent), and does indicate this
+ * in the ProgIf. Unfortunately, the ProgIf value is wrong - 0x80
+ * instead of 0x01.
+ */
+static void __devinit quirk_transparent_bridge(struct pci_dev *dev)
+{
+	dev->transparent = 1;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82380FB,	quirk_transparent_bridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TOSHIBA,	0x605,	quirk_transparent_bridge);
+
+/*
+ * Common misconfiguration of the MediaGX/Geode PCI master that will
+ * reduce PCI bandwidth from 70MB/s to 25MB/s.  See the GXM/GXLV/GX1
+ * datasheets found at http://www.national.com/analog for info on what
+ * these bits do.  <christer@weinigel.se>
+ */
+static void quirk_mediagx_master(struct pci_dev *dev)
+{
+	u8 reg;
+	pci_read_config_byte(dev, 0x41, &reg);
+	if (reg & 2) {
+		reg &= ~2;
+		dev_info(&dev->dev, "Fixup for MediaGX/Geode Slave Disconnect Boundary (0x41=0x%02x)\n", reg);
+                pci_write_config_byte(dev, 0x41, reg);
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CYRIX,	PCI_DEVICE_ID_CYRIX_PCI_MASTER, quirk_mediagx_master);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_CYRIX,	PCI_DEVICE_ID_CYRIX_PCI_MASTER, quirk_mediagx_master);
+
+/*
+ *	Ensure C0 rev restreaming is off. This is normally done by
+ *	the BIOS but in the odd case it is not the results are corruption
+ *	hence the presence of a Linux check
+ */
+static void quirk_disable_pxb(struct pci_dev *pdev)
+{
+	u16 config;
+	
+	if (pdev->revision != 0x04)		/* Only C0 requires this */
+		return;
+	pci_read_config_word(pdev, 0x40, &config);
+	if (config & (1<<6)) {
+		config &= ~(1<<6);
+		pci_write_config_word(pdev, 0x40, config);
+		dev_info(&pdev->dev, "C0 revision 450NX. Disabling PCI restreaming\n");
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82454NX,	quirk_disable_pxb);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82454NX,	quirk_disable_pxb);
+
+static void __devinit quirk_amd_ide_mode(struct pci_dev *pdev)
+{
+	/* set SBX00/Hudson-2 SATA in IDE mode to AHCI mode */
+	u8 tmp;
+
+	pci_read_config_byte(pdev, PCI_CLASS_DEVICE, &tmp);
+	if (tmp == 0x01) {
+		pci_read_config_byte(pdev, 0x40, &tmp);
+		pci_write_config_byte(pdev, 0x40, tmp|1);
+		pci_write_config_byte(pdev, 0x9, 1);
+		pci_write_config_byte(pdev, 0xa, 6);
+		pci_write_config_byte(pdev, 0x40, tmp);
+
+		pdev->class = PCI_CLASS_STORAGE_SATA_AHCI;
+		dev_info(&pdev->dev, "set SATA to AHCI mode\n");
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP600_SATA, quirk_amd_ide_mode);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP600_SATA, quirk_amd_ide_mode);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP700_SATA, quirk_amd_ide_mode);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP700_SATA, quirk_amd_ide_mode);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_HUDSON2_SATA_IDE, quirk_amd_ide_mode);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_HUDSON2_SATA_IDE, quirk_amd_ide_mode);
+
+/*
+ *	Serverworks CSB5 IDE does not fully support native mode
+ */
+static void __devinit quirk_svwks_csb5ide(struct pci_dev *pdev)
+{
+	u8 prog;
+	pci_read_config_byte(pdev, PCI_CLASS_PROG, &prog);
+	if (prog & 5) {
+		prog &= ~5;
+		pdev->class &= ~5;
+		pci_write_config_byte(pdev, PCI_CLASS_PROG, prog);
+		/* PCI layer will sort out resources */
+	}
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_CSB5IDE, quirk_svwks_csb5ide);
+
+/*
+ *	Intel 82801CAM ICH3-M datasheet says IDE modes must be the same
+ */
+static void __init quirk_ide_samemode(struct pci_dev *pdev)
+{
+	u8 prog;
+
+	pci_read_config_byte(pdev, PCI_CLASS_PROG, &prog);
+
+	if (((prog & 1) && !(prog & 4)) || ((prog & 4) && !(prog & 1))) {
+		dev_info(&pdev->dev, "IDE mode mismatch; forcing legacy mode\n");
+		prog &= ~5;
+		pdev->class &= ~5;
+		pci_write_config_byte(pdev, PCI_CLASS_PROG, prog);
+	}
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_10, quirk_ide_samemode);
+
+/*
+ * Some ATA devices break if put into D3
+ */
+
+static void __devinit quirk_no_ata_d3(struct pci_dev *pdev)
+{
+	/* Quirk the legacy ATA devices only. The AHCI ones are ok */
+	if ((pdev->class >> 8) == PCI_CLASS_STORAGE_IDE)
+		pdev->dev_flags |= PCI_DEV_FLAGS_NO_D3;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, PCI_ANY_ID, quirk_no_ata_d3);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_ATI, PCI_ANY_ID, quirk_no_ata_d3);
+/* ALi loses some register settings that we cannot then restore */
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AL, PCI_ANY_ID, quirk_no_ata_d3);
+/* VIA comes back fine but we need to keep it alive or ACPI GTM failures
+   occur when mode detecting */
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_VIA, PCI_ANY_ID, quirk_no_ata_d3);
+
+/* This was originally an Alpha specific thing, but it really fits here.
+ * The i82375 PCI/EISA bridge appears as non-classified. Fix that.
+ */
+static void __init quirk_eisa_bridge(struct pci_dev *dev)
+{
+	dev->class = PCI_CLASS_BRIDGE_EISA << 8;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82375,	quirk_eisa_bridge);
+
+
+/*
+ * On ASUS P4B boards, the SMBus PCI Device within the ICH2/4 southbridge
+ * is not activated. The myth is that Asus said that they do not want the
+ * users to be irritated by just another PCI Device in the Win98 device
+ * manager. (see the file prog/hotplug/README.p4b in the lm_sensors 
+ * package 2.7.0 for details)
+ *
+ * The SMBus PCI Device can be activated by setting a bit in the ICH LPC 
+ * bridge. Unfortunately, this device has no subvendor/subdevice ID. So it 
+ * becomes necessary to do this tweak in two steps -- the chosen trigger
+ * is either the Host bridge (preferred) or on-board VGA controller.
+ *
+ * Note that we used to unhide the SMBus that way on Toshiba laptops
+ * (Satellite A40 and Tecra M2) but then found that the thermal management
+ * was done by SMM code, which could cause unsynchronized concurrent
+ * accesses to the SMBus registers, with potentially bad effects. Thus you
+ * should be very careful when adding new entries: if SMM is accessing the
+ * Intel SMBus, this is a very good reason to leave it hidden.
+ *
+ * Likewise, many recent laptops use ACPI for thermal management. If the
+ * ACPI DSDT code accesses the SMBus, then Linux should not access it
+ * natively, and keeping the SMBus hidden is the right thing to do. If you
+ * are about to add an entry in the table below, please first disassemble
+ * the DSDT and double-check that there is no code accessing the SMBus.
+ */
+static int asus_hides_smbus;
+
+static void __init asus_hides_smbus_hostbridge(struct pci_dev *dev)
+{
+	if (unlikely(dev->subsystem_vendor == PCI_VENDOR_ID_ASUSTEK)) {
+		if (dev->device == PCI_DEVICE_ID_INTEL_82845_HB)
+			switch(dev->subsystem_device) {
+			case 0x8025: /* P4B-LX */
+			case 0x8070: /* P4B */
+			case 0x8088: /* P4B533 */
+			case 0x1626: /* L3C notebook */
+				asus_hides_smbus = 1;
+			}
+		else if (dev->device == PCI_DEVICE_ID_INTEL_82845G_HB)
+			switch(dev->subsystem_device) {
+			case 0x80b1: /* P4GE-V */
+			case 0x80b2: /* P4PE */
+			case 0x8093: /* P4B533-V */
+				asus_hides_smbus = 1;
+			}
+		else if (dev->device == PCI_DEVICE_ID_INTEL_82850_HB)
+			switch(dev->subsystem_device) {
+			case 0x8030: /* P4T533 */
+				asus_hides_smbus = 1;
+			}
+		else if (dev->device == PCI_DEVICE_ID_INTEL_7205_0)
+			switch (dev->subsystem_device) {
+			case 0x8070: /* P4G8X Deluxe */
+				asus_hides_smbus = 1;
+			}
+		else if (dev->device == PCI_DEVICE_ID_INTEL_E7501_MCH)
+			switch (dev->subsystem_device) {
+			case 0x80c9: /* PU-DLS */
+				asus_hides_smbus = 1;
+			}
+		else if (dev->device == PCI_DEVICE_ID_INTEL_82855GM_HB)
+			switch (dev->subsystem_device) {
+			case 0x1751: /* M2N notebook */
+			case 0x1821: /* M5N notebook */
+			case 0x1897: /* A6L notebook */
+				asus_hides_smbus = 1;
+			}
+		else if (dev->device == PCI_DEVICE_ID_INTEL_82855PM_HB)
+			switch (dev->subsystem_device) {
+			case 0x184b: /* W1N notebook */
+			case 0x186a: /* M6Ne notebook */
+				asus_hides_smbus = 1;
+			}
+		else if (dev->device == PCI_DEVICE_ID_INTEL_82865_HB)
+			switch (dev->subsystem_device) {
+			case 0x80f2: /* P4P800-X */
+				asus_hides_smbus = 1;
+			}
+		else if (dev->device == PCI_DEVICE_ID_INTEL_82915GM_HB)
+			switch (dev->subsystem_device) {
+			case 0x1882: /* M6V notebook */
+			case 0x1977: /* A6VA notebook */
+				asus_hides_smbus = 1;
+			}
+	} else if (unlikely(dev->subsystem_vendor == PCI_VENDOR_ID_HP)) {
+		if (dev->device ==  PCI_DEVICE_ID_INTEL_82855PM_HB)
+			switch(dev->subsystem_device) {
+			case 0x088C: /* HP Compaq nc8000 */
+			case 0x0890: /* HP Compaq nc6000 */
+				asus_hides_smbus = 1;
+			}
+		else if (dev->device == PCI_DEVICE_ID_INTEL_82865_HB)
+			switch (dev->subsystem_device) {
+			case 0x12bc: /* HP D330L */
+			case 0x12bd: /* HP D530 */
+			case 0x006a: /* HP Compaq nx9500 */
+				asus_hides_smbus = 1;
+			}
+		else if (dev->device == PCI_DEVICE_ID_INTEL_82875_HB)
+			switch (dev->subsystem_device) {
+			case 0x12bf: /* HP xw4100 */
+				asus_hides_smbus = 1;
+			}
+       } else if (unlikely(dev->subsystem_vendor == PCI_VENDOR_ID_SAMSUNG)) {
+               if (dev->device ==  PCI_DEVICE_ID_INTEL_82855PM_HB)
+                       switch(dev->subsystem_device) {
+                       case 0xC00C: /* Samsung P35 notebook */
+                               asus_hides_smbus = 1;
+                       }
+	} else if (unlikely(dev->subsystem_vendor == PCI_VENDOR_ID_COMPAQ)) {
+		if (dev->device == PCI_DEVICE_ID_INTEL_82855PM_HB)
+			switch(dev->subsystem_device) {
+			case 0x0058: /* Compaq Evo N620c */
+				asus_hides_smbus = 1;
+			}
+		else if (dev->device == PCI_DEVICE_ID_INTEL_82810_IG3)
+			switch(dev->subsystem_device) {
+			case 0xB16C: /* Compaq Deskpro EP 401963-001 (PCA# 010174) */
+				/* Motherboard doesn't have Host bridge
+				 * subvendor/subdevice IDs, therefore checking
+				 * its on-board VGA controller */
+				asus_hides_smbus = 1;
+			}
+		else if (dev->device == PCI_DEVICE_ID_INTEL_82801DB_2)
+			switch(dev->subsystem_device) {
+			case 0x00b8: /* Compaq Evo D510 CMT */
+			case 0x00b9: /* Compaq Evo D510 SFF */
+			case 0x00ba: /* Compaq Evo D510 USDT */
+				/* Motherboard doesn't have Host bridge
+				 * subvendor/subdevice IDs and on-board VGA
+				 * controller is disabled if an AGP card is
+				 * inserted, therefore checking USB UHCI
+				 * Controller #1 */
+				asus_hides_smbus = 1;
+			}
+		else if (dev->device == PCI_DEVICE_ID_INTEL_82815_CGC)
+			switch (dev->subsystem_device) {
+			case 0x001A: /* Compaq Deskpro EN SSF P667 815E */
+				/* Motherboard doesn't have host bridge
+				 * subvendor/subdevice IDs, therefore checking
+				 * its on-board VGA controller */
+				asus_hides_smbus = 1;
+			}
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82845_HB,	asus_hides_smbus_hostbridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82845G_HB,	asus_hides_smbus_hostbridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82850_HB,	asus_hides_smbus_hostbridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82865_HB,	asus_hides_smbus_hostbridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82875_HB,	asus_hides_smbus_hostbridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_7205_0,	asus_hides_smbus_hostbridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7501_MCH,	asus_hides_smbus_hostbridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82855PM_HB,	asus_hides_smbus_hostbridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82855GM_HB,	asus_hides_smbus_hostbridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82915GM_HB, asus_hides_smbus_hostbridge);
+
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82810_IG3,	asus_hides_smbus_hostbridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82801DB_2,	asus_hides_smbus_hostbridge);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82815_CGC,	asus_hides_smbus_hostbridge);
+
+static void asus_hides_smbus_lpc(struct pci_dev *dev)
+{
+	u16 val;
+	
+	if (likely(!asus_hides_smbus))
+		return;
+
+	pci_read_config_word(dev, 0xF2, &val);
+	if (val & 0x8) {
+		pci_write_config_word(dev, 0xF2, val & (~0x8));
+		pci_read_config_word(dev, 0xF2, &val);
+		if (val & 0x8)
+			dev_info(&dev->dev, "i801 SMBus device continues to play 'hide and seek'! 0x%x\n", val);
+		else
+			dev_info(&dev->dev, "Enabled i801 SMBus device\n");
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82801AA_0,	asus_hides_smbus_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82801DB_0,	asus_hides_smbus_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82801BA_0,	asus_hides_smbus_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82801CA_0,	asus_hides_smbus_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82801CA_12,	asus_hides_smbus_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82801DB_12,	asus_hides_smbus_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82801EB_0,	asus_hides_smbus_lpc);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82801AA_0,	asus_hides_smbus_lpc);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82801DB_0,	asus_hides_smbus_lpc);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82801BA_0,	asus_hides_smbus_lpc);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82801CA_0,	asus_hides_smbus_lpc);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82801CA_12,	asus_hides_smbus_lpc);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82801DB_12,	asus_hides_smbus_lpc);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82801EB_0,	asus_hides_smbus_lpc);
+
+/* It appears we just have one such device. If not, we have a warning */
+static void __iomem *asus_rcba_base;
+static void asus_hides_smbus_lpc_ich6_suspend(struct pci_dev *dev)
+{
+	u32 rcba;
+
+	if (likely(!asus_hides_smbus))
+		return;
+	WARN_ON(asus_rcba_base);
+
+	pci_read_config_dword(dev, 0xF0, &rcba);
+	/* use bits 31:14, 16 kB aligned */
+	asus_rcba_base = ioremap_nocache(rcba & 0xFFFFC000, 0x4000);
+	if (asus_rcba_base == NULL)
+		return;
+}
+
+static void asus_hides_smbus_lpc_ich6_resume_early(struct pci_dev *dev)
+{
+	u32 val;
+
+	if (likely(!asus_hides_smbus || !asus_rcba_base))
+		return;
+	/* read the Function Disable register, dword mode only */
+	val = readl(asus_rcba_base + 0x3418);
+	writel(val & 0xFFFFFFF7, asus_rcba_base + 0x3418); /* enable the SMBus device */
+}
+
+static void asus_hides_smbus_lpc_ich6_resume(struct pci_dev *dev)
+{
+	if (likely(!asus_hides_smbus || !asus_rcba_base))
+		return;
+	iounmap(asus_rcba_base);
+	asus_rcba_base = NULL;
+	dev_info(&dev->dev, "Enabled ICH6/i801 SMBus device\n");
+}
+
+static void asus_hides_smbus_lpc_ich6(struct pci_dev *dev)
+{
+	asus_hides_smbus_lpc_ich6_suspend(dev);
+	asus_hides_smbus_lpc_ich6_resume_early(dev);
+	asus_hides_smbus_lpc_ich6_resume(dev);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH6_1,	asus_hides_smbus_lpc_ich6);
+DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH6_1,	asus_hides_smbus_lpc_ich6_suspend);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH6_1,	asus_hides_smbus_lpc_ich6_resume);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH6_1,	asus_hides_smbus_lpc_ich6_resume_early);
+
+/*
+ * SiS 96x south bridge: BIOS typically hides SMBus device...
+ */
+static void quirk_sis_96x_smbus(struct pci_dev *dev)
+{
+	u8 val = 0;
+	pci_read_config_byte(dev, 0x77, &val);
+	if (val & 0x10) {
+		dev_info(&dev->dev, "Enabling SiS 96x SMBus\n");
+		pci_write_config_byte(dev, 0x77, val & ~0x10);
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SI,	PCI_DEVICE_ID_SI_961,		quirk_sis_96x_smbus);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SI,	PCI_DEVICE_ID_SI_962,		quirk_sis_96x_smbus);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SI,	PCI_DEVICE_ID_SI_963,		quirk_sis_96x_smbus);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SI,	PCI_DEVICE_ID_SI_LPC,		quirk_sis_96x_smbus);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_SI,	PCI_DEVICE_ID_SI_961,		quirk_sis_96x_smbus);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_SI,	PCI_DEVICE_ID_SI_962,		quirk_sis_96x_smbus);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_SI,	PCI_DEVICE_ID_SI_963,		quirk_sis_96x_smbus);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_SI,	PCI_DEVICE_ID_SI_LPC,		quirk_sis_96x_smbus);
+
+/*
+ * ... This is further complicated by the fact that some SiS96x south
+ * bridges pretend to be 85C503/5513 instead.  In that case see if we
+ * spotted a compatible north bridge to make sure.
+ * (pci_find_device doesn't work yet)
+ *
+ * We can also enable the sis96x bit in the discovery register..
+ */
+#define SIS_DETECT_REGISTER 0x40
+
+static void quirk_sis_503(struct pci_dev *dev)
+{
+	u8 reg;
+	u16 devid;
+
+	pci_read_config_byte(dev, SIS_DETECT_REGISTER, &reg);
+	pci_write_config_byte(dev, SIS_DETECT_REGISTER, reg | (1 << 6));
+	pci_read_config_word(dev, PCI_DEVICE_ID, &devid);
+	if (((devid & 0xfff0) != 0x0960) && (devid != 0x0018)) {
+		pci_write_config_byte(dev, SIS_DETECT_REGISTER, reg);
+		return;
+	}
+
+	/*
+	 * Ok, it now shows up as a 96x.. run the 96x quirk by
+	 * hand in case it has already been processed.
+	 * (depends on link order, which is apparently not guaranteed)
+	 */
+	dev->device = devid;
+	quirk_sis_96x_smbus(dev);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SI,	PCI_DEVICE_ID_SI_503,		quirk_sis_503);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_SI,	PCI_DEVICE_ID_SI_503,		quirk_sis_503);
+
+
+/*
+ * On ASUS A8V and A8V Deluxe boards, the onboard AC97 audio controller
+ * and MC97 modem controller are disabled when a second PCI soundcard is
+ * present. This patch, tweaking the VT8237 ISA bridge, enables them.
+ * -- bjd
+ */
+static void asus_hides_ac97_lpc(struct pci_dev *dev)
+{
+	u8 val;
+	int asus_hides_ac97 = 0;
+
+	if (likely(dev->subsystem_vendor == PCI_VENDOR_ID_ASUSTEK)) {
+		if (dev->device == PCI_DEVICE_ID_VIA_8237)
+			asus_hides_ac97 = 1;
+	}
+
+	if (!asus_hides_ac97)
+		return;
+
+	pci_read_config_byte(dev, 0x50, &val);
+	if (val & 0xc0) {
+		pci_write_config_byte(dev, 0x50, val & (~0xc0));
+		pci_read_config_byte(dev, 0x50, &val);
+		if (val & 0xc0)
+			dev_info(&dev->dev, "Onboard AC97/MC97 devices continue to play 'hide and seek'! 0x%x\n", val);
+		else
+			dev_info(&dev->dev, "Enabled onboard AC97/MC97 devices\n");
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8237, asus_hides_ac97_lpc);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8237, asus_hides_ac97_lpc);
+
+#if defined(CONFIG_ATA) || defined(CONFIG_ATA_MODULE)
+
+/*
+ *	If we are using libata we can drive this chip properly but must
+ *	do this early on to make the additional device appear during
+ *	the PCI scanning.
+ */
+static void quirk_jmicron_ata(struct pci_dev *pdev)
+{
+	u32 conf1, conf5, class;
+	u8 hdr;
+
+	/* Only poke fn 0 */
+	if (PCI_FUNC(pdev->devfn))
+		return;
+
+	pci_read_config_dword(pdev, 0x40, &conf1);
+	pci_read_config_dword(pdev, 0x80, &conf5);
+
+	conf1 &= ~0x00CFF302; /* Clear bit 1, 8, 9, 12-19, 22, 23 */
+	conf5 &= ~(1 << 24);  /* Clear bit 24 */
+
+	switch (pdev->device) {
+	case PCI_DEVICE_ID_JMICRON_JMB360: /* SATA single port */
+	case PCI_DEVICE_ID_JMICRON_JMB362: /* SATA dual ports */
+	case PCI_DEVICE_ID_JMICRON_JMB364: /* SATA dual ports */
+		/* The controller should be in single function ahci mode */
+		conf1 |= 0x0002A100; /* Set 8, 13, 15, 17 */
+		break;
+
+	case PCI_DEVICE_ID_JMICRON_JMB365:
+	case PCI_DEVICE_ID_JMICRON_JMB366:
+		/* Redirect IDE second PATA port to the right spot */
+		conf5 |= (1 << 24);
+		/* Fall through */
+	case PCI_DEVICE_ID_JMICRON_JMB361:
+	case PCI_DEVICE_ID_JMICRON_JMB363:
+	case PCI_DEVICE_ID_JMICRON_JMB369:
+		/* Enable dual function mode, AHCI on fn 0, IDE fn1 */
+		/* Set the class codes correctly and then direct IDE 0 */
+		conf1 |= 0x00C2A1B3; /* Set 0, 1, 4, 5, 7, 8, 13, 15, 17, 22, 23 */
+		break;
+
+	case PCI_DEVICE_ID_JMICRON_JMB368:
+		/* The controller should be in single function IDE mode */
+		conf1 |= 0x00C00000; /* Set 22, 23 */
+		break;
+	}
+
+	pci_write_config_dword(pdev, 0x40, conf1);
+	pci_write_config_dword(pdev, 0x80, conf5);
+
+	/* Update pdev accordingly */
+	pci_read_config_byte(pdev, PCI_HEADER_TYPE, &hdr);
+	pdev->hdr_type = hdr & 0x7f;
+	pdev->multifunction = !!(hdr & 0x80);
+
+	pci_read_config_dword(pdev, PCI_CLASS_REVISION, &class);
+	pdev->class = class >> 8;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB360, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB361, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB362, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB363, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB364, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB365, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB366, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB368, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB369, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB360, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB361, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB362, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB363, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB364, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB365, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB366, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB368, quirk_jmicron_ata);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB369, quirk_jmicron_ata);
+
+#endif
+
+#ifdef CONFIG_X86_IO_APIC
+static void __init quirk_alder_ioapic(struct pci_dev *pdev)
+{
+	int i;
+
+	if ((pdev->class >> 8) != 0xff00)
+		return;
+
+	/* the first BAR is the location of the IO APIC...we must
+	 * not touch this (and it's already covered by the fixmap), so
+	 * forcibly insert it into the resource tree */
+	if (pci_resource_start(pdev, 0) && pci_resource_len(pdev, 0))
+		insert_resource(&iomem_resource, &pdev->resource[0]);
+
+	/* The next five BARs all seem to be rubbish, so just clean
+	 * them out */
+	for (i=1; i < 6; i++) {
+		memset(&pdev->resource[i], 0, sizeof(pdev->resource[i]));
+	}
+
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_EESSC,	quirk_alder_ioapic);
+#endif
+
+static void __devinit quirk_pcie_mch(struct pci_dev *pdev)
+{
+	pci_msi_off(pdev);
+	pdev->no_msi = 1;
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7520_MCH,	quirk_pcie_mch);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7320_MCH,	quirk_pcie_mch);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7525_MCH,	quirk_pcie_mch);
+
+
+/*
+ * It's possible for the MSI to get corrupted if shpc and acpi
+ * are used together on certain PXH-based systems.
+ */
+static void __devinit quirk_pcie_pxh(struct pci_dev *dev)
+{
+	pci_msi_off(dev);
+	dev->no_msi = 1;
+	dev_warn(&dev->dev, "PXH quirk detected; SHPC device MSI disabled\n");
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXHD_0,	quirk_pcie_pxh);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXHD_1,	quirk_pcie_pxh);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXH_0,	quirk_pcie_pxh);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXH_1,	quirk_pcie_pxh);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXHV,	quirk_pcie_pxh);
+
+/*
+ * Some Intel PCI Express chipsets have trouble with downstream
+ * device power management.
+ */
+static void quirk_intel_pcie_pm(struct pci_dev * dev)
+{
+	pci_pm_d3_delay = 120;
+	dev->no_d1d2 = 1;
+}
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x25e2, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x25e3, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x25e4, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x25e5, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x25e6, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x25e7, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x25f7, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x25f8, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x25f9, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x25fa, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x2601, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x2602, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x2603, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x2604, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x2605, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x2606, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x2607, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x2608, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x2609, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x260a, quirk_intel_pcie_pm);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x260b, quirk_intel_pcie_pm);
+
+#ifdef CONFIG_X86_IO_APIC
+/*
+ * Boot interrupts on some chipsets cannot be turned off. For these chipsets,
+ * remap the original interrupt in the linux kernel to the boot interrupt, so
+ * that a PCI device's interrupt handler is installed on the boot interrupt
+ * line instead.
+ */
+static void quirk_reroute_to_boot_interrupts_intel(struct pci_dev *dev)
+{
+	if (noioapicquirk || noioapicreroute)
+		return;
+
+	dev->irq_reroute_variant = INTEL_IRQ_REROUTE_VARIANT;
+	dev_info(&dev->dev, "rerouting interrupts for [%04x:%04x]\n",
+		 dev->vendor, dev->device);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80333_0,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80333_1,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ESB2_0,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXH_0,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXH_1,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXHV,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80332_0,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80332_1,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80333_0,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80333_1,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ESB2_0,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXH_0,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXH_1,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXHV,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80332_0,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80332_1,	quirk_reroute_to_boot_interrupts_intel);
+
+/*
+ * On some chipsets we can disable the generation of legacy INTx boot
+ * interrupts.
+ */
+
+/*
+ * IO-APIC1 on 6300ESB generates boot interrupts, see intel order no
+ * 300641-004US, section 5.7.3.
+ */
+#define INTEL_6300_IOAPIC_ABAR		0x40
+#define INTEL_6300_DISABLE_BOOT_IRQ	(1<<14)
+
+static void quirk_disable_intel_boot_interrupt(struct pci_dev *dev)
+{
+	u16 pci_config_word;
+
+	if (noioapicquirk)
+		return;
+
+	pci_read_config_word(dev, INTEL_6300_IOAPIC_ABAR, &pci_config_word);
+	pci_config_word |= INTEL_6300_DISABLE_BOOT_IRQ;
+	pci_write_config_word(dev, INTEL_6300_IOAPIC_ABAR, pci_config_word);
+
+	dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n",
+		 dev->vendor, dev->device);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,   PCI_DEVICE_ID_INTEL_ESB_10, 	quirk_disable_intel_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,   PCI_DEVICE_ID_INTEL_ESB_10, 	quirk_disable_intel_boot_interrupt);
+
+/*
+ * disable boot interrupts on HT-1000
+ */
+#define BC_HT1000_FEATURE_REG		0x64
+#define BC_HT1000_PIC_REGS_ENABLE	(1<<0)
+#define BC_HT1000_MAP_IDX		0xC00
+#define BC_HT1000_MAP_DATA		0xC01
+
+static void quirk_disable_broadcom_boot_interrupt(struct pci_dev *dev)
+{
+	u32 pci_config_dword;
+	u8 irq;
+
+	if (noioapicquirk)
+		return;
+
+	pci_read_config_dword(dev, BC_HT1000_FEATURE_REG, &pci_config_dword);
+	pci_write_config_dword(dev, BC_HT1000_FEATURE_REG, pci_config_dword |
+			BC_HT1000_PIC_REGS_ENABLE);
+
+	for (irq = 0x10; irq < 0x10 + 32; irq++) {
+		outb(irq, BC_HT1000_MAP_IDX);
+		outb(0x00, BC_HT1000_MAP_DATA);
+	}
+
+	pci_write_config_dword(dev, BC_HT1000_FEATURE_REG, pci_config_dword);
+
+	dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n",
+		 dev->vendor, dev->device);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SERVERWORKS,   PCI_DEVICE_ID_SERVERWORKS_HT1000SB, 	quirk_disable_broadcom_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_SERVERWORKS,   PCI_DEVICE_ID_SERVERWORKS_HT1000SB, 	quirk_disable_broadcom_boot_interrupt);
+
+/*
+ * disable boot interrupts on AMD and ATI chipsets
+ */
+/*
+ * NOIOAMODE needs to be disabled to disable "boot interrupts". For AMD 8131
+ * rev. A0 and B0, NOIOAMODE needs to be disabled anyway to fix IO-APIC mode
+ * (due to an erratum).
+ */
+#define AMD_813X_MISC			0x40
+#define AMD_813X_NOIOAMODE		(1<<0)
+#define AMD_813X_REV_B1			0x12
+#define AMD_813X_REV_B2			0x13
+
+static void quirk_disable_amd_813x_boot_interrupt(struct pci_dev *dev)
+{
+	u32 pci_config_dword;
+
+	if (noioapicquirk)
+		return;
+	if ((dev->revision == AMD_813X_REV_B1) ||
+	    (dev->revision == AMD_813X_REV_B2))
+		return;
+
+	pci_read_config_dword(dev, AMD_813X_MISC, &pci_config_dword);
+	pci_config_dword &= ~AMD_813X_NOIOAMODE;
+	pci_write_config_dword(dev, AMD_813X_MISC, pci_config_dword);
+
+	dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n",
+		 dev->vendor, dev->device);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD,	PCI_DEVICE_ID_AMD_8131_BRIDGE,	quirk_disable_amd_813x_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD,	PCI_DEVICE_ID_AMD_8131_BRIDGE,	quirk_disable_amd_813x_boot_interrupt);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD,	PCI_DEVICE_ID_AMD_8132_BRIDGE,	quirk_disable_amd_813x_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD,	PCI_DEVICE_ID_AMD_8132_BRIDGE,	quirk_disable_amd_813x_boot_interrupt);
+
+#define AMD_8111_PCI_IRQ_ROUTING	0x56
+
+static void quirk_disable_amd_8111_boot_interrupt(struct pci_dev *dev)
+{
+	u16 pci_config_word;
+
+	if (noioapicquirk)
+		return;
+
+	pci_read_config_word(dev, AMD_8111_PCI_IRQ_ROUTING, &pci_config_word);
+	if (!pci_config_word) {
+		dev_info(&dev->dev, "boot interrupts on device [%04x:%04x] "
+			 "already disabled\n", dev->vendor, dev->device);
+		return;
+	}
+	pci_write_config_word(dev, AMD_8111_PCI_IRQ_ROUTING, 0);
+	dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n",
+		 dev->vendor, dev->device);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD,   PCI_DEVICE_ID_AMD_8111_SMBUS, 	quirk_disable_amd_8111_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD,   PCI_DEVICE_ID_AMD_8111_SMBUS, 	quirk_disable_amd_8111_boot_interrupt);
+#endif /* CONFIG_X86_IO_APIC */
+
+/*
+ * Toshiba TC86C001 IDE controller reports the standard 8-byte BAR0 size
+ * but the PIO transfers won't work if BAR0 falls at the odd 8 bytes.
+ * Re-allocate the region if needed...
+ */
+static void __init quirk_tc86c001_ide(struct pci_dev *dev)
+{
+	struct resource *r = &dev->resource[0];
+
+	if (r->start & 0x8) {
+		r->start = 0;
+		r->end = 0xf;
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TOSHIBA_2,
+			 PCI_DEVICE_ID_TOSHIBA_TC86C001_IDE,
+			 quirk_tc86c001_ide);
+
+static void __devinit quirk_netmos(struct pci_dev *dev)
+{
+	unsigned int num_parallel = (dev->subsystem_device & 0xf0) >> 4;
+	unsigned int num_serial = dev->subsystem_device & 0xf;
+
+	/*
+	 * These Netmos parts are multiport serial devices with optional
+	 * parallel ports.  Even when parallel ports are present, they
+	 * are identified as class SERIAL, which means the serial driver
+	 * will claim them.  To prevent this, mark them as class OTHER.
+	 * These combo devices should be claimed by parport_serial.
+	 *
+	 * The subdevice ID is of the form 0x00PS, where <P> is the number
+	 * of parallel ports and <S> is the number of serial ports.
+	 */
+	switch (dev->device) {
+	case PCI_DEVICE_ID_NETMOS_9835:
+		/* Well, this rule doesn't hold for the following 9835 device */
+		if (dev->subsystem_vendor == PCI_VENDOR_ID_IBM &&
+				dev->subsystem_device == 0x0299)
+			return;
+	case PCI_DEVICE_ID_NETMOS_9735:
+	case PCI_DEVICE_ID_NETMOS_9745:
+	case PCI_DEVICE_ID_NETMOS_9845:
+	case PCI_DEVICE_ID_NETMOS_9855:
+		if ((dev->class >> 8) == PCI_CLASS_COMMUNICATION_SERIAL &&
+		    num_parallel) {
+			dev_info(&dev->dev, "Netmos %04x (%u parallel, "
+				"%u serial); changing class SERIAL to OTHER "
+				"(use parport_serial)\n",
+				dev->device, num_parallel, num_serial);
+			dev->class = (PCI_CLASS_COMMUNICATION_OTHER << 8) |
+			    (dev->class & 0xff);
+		}
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETMOS, PCI_ANY_ID, quirk_netmos);
+
+static void __devinit quirk_e100_interrupt(struct pci_dev *dev)
+{
+	u16 command, pmcsr;
+	u8 __iomem *csr;
+	u8 cmd_hi;
+	int pm;
+
+	switch (dev->device) {
+	/* PCI IDs taken from drivers/net/e100.c */
+	case 0x1029:
+	case 0x1030 ... 0x1034:
+	case 0x1038 ... 0x103E:
+	case 0x1050 ... 0x1057:
+	case 0x1059:
+	case 0x1064 ... 0x106B:
+	case 0x1091 ... 0x1095:
+	case 0x1209:
+	case 0x1229:
+	case 0x2449:
+	case 0x2459:
+	case 0x245D:
+	case 0x27DC:
+		break;
+	default:
+		return;
+	}
+
+	/*
+	 * Some firmware hands off the e100 with interrupts enabled,
+	 * which can cause a flood of interrupts if packets are
+	 * received before the driver attaches to the device.  So
+	 * disable all e100 interrupts here.  The driver will
+	 * re-enable them when it's ready.
+	 */
+	pci_read_config_word(dev, PCI_COMMAND, &command);
+
+	if (!(command & PCI_COMMAND_MEMORY) || !pci_resource_start(dev, 0))
+		return;
+
+	/*
+	 * Check that the device is in the D0 power state. If it's not,
+	 * there is no point to look any further.
+	 */
+	pm = pci_find_capability(dev, PCI_CAP_ID_PM);
+	if (pm) {
+		pci_read_config_word(dev, pm + PCI_PM_CTRL, &pmcsr);
+		if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0)
+			return;
+	}
+
+	/* Convert from PCI bus to resource space.  */
+	csr = ioremap(pci_resource_start(dev, 0), 8);
+	if (!csr) {
+		dev_warn(&dev->dev, "Can't map e100 registers\n");
+		return;
+	}
+
+	cmd_hi = readb(csr + 3);
+	if (cmd_hi == 0) {
+		dev_warn(&dev->dev, "Firmware left e100 interrupts enabled; "
+			"disabling\n");
+		writeb(1, csr + 3);
+	}
+
+	iounmap(csr);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, quirk_e100_interrupt);
+
+/*
+ * The 82575 and 82598 may experience data corruption issues when transitioning
+ * out of L0S.  To prevent this we need to disable L0S on the pci-e link
+ */
+static void __devinit quirk_disable_aspm_l0s(struct pci_dev *dev)
+{
+	dev_info(&dev->dev, "Disabling L0s\n");
+	pci_disable_link_state(dev, PCIE_LINK_STATE_L0S);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10a7, quirk_disable_aspm_l0s);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10a9, quirk_disable_aspm_l0s);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10b6, quirk_disable_aspm_l0s);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10c6, quirk_disable_aspm_l0s);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10c7, quirk_disable_aspm_l0s);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10c8, quirk_disable_aspm_l0s);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10d6, quirk_disable_aspm_l0s);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10db, quirk_disable_aspm_l0s);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10dd, quirk_disable_aspm_l0s);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10e1, quirk_disable_aspm_l0s);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10ec, quirk_disable_aspm_l0s);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f1, quirk_disable_aspm_l0s);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f4, quirk_disable_aspm_l0s);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1508, quirk_disable_aspm_l0s);
+
+static void __devinit fixup_rev1_53c810(struct pci_dev* dev)
+{
+	/* rev 1 ncr53c810 chips don't set the class at all which means
+	 * they don't get their resources remapped. Fix that here.
+	 */
+
+	if (dev->class == PCI_CLASS_NOT_DEFINED) {
+		dev_info(&dev->dev, "NCR 53c810 rev 1 detected; setting PCI class\n");
+		dev->class = PCI_CLASS_STORAGE_SCSI;
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NCR, PCI_DEVICE_ID_NCR_53C810, fixup_rev1_53c810);
+
+/* Enable 1k I/O space granularity on the Intel P64H2 */
+static void __devinit quirk_p64h2_1k_io(struct pci_dev *dev)
+{
+	u16 en1k;
+	u8 io_base_lo, io_limit_lo;
+	unsigned long base, limit;
+	struct resource *res = dev->resource + PCI_BRIDGE_RESOURCES;
+
+	pci_read_config_word(dev, 0x40, &en1k);
+
+	if (en1k & 0x200) {
+		dev_info(&dev->dev, "Enable I/O Space to 1KB granularity\n");
+
+		pci_read_config_byte(dev, PCI_IO_BASE, &io_base_lo);
+		pci_read_config_byte(dev, PCI_IO_LIMIT, &io_limit_lo);
+		base = (io_base_lo & (PCI_IO_RANGE_MASK | 0x0c)) << 8;
+		limit = (io_limit_lo & (PCI_IO_RANGE_MASK | 0x0c)) << 8;
+
+		if (base <= limit) {
+			res->start = base;
+			res->end = limit + 0x3ff;
+		}
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	0x1460,		quirk_p64h2_1k_io);
+
+/* Fix the IOBL_ADR for 1k I/O space granularity on the Intel P64H2
+ * The IOBL_ADR gets re-written to 4k boundaries in pci_setup_bridge()
+ * in drivers/pci/setup-bus.c
+ */
+static void __devinit quirk_p64h2_1k_io_fix_iobl(struct pci_dev *dev)
+{
+	u16 en1k, iobl_adr, iobl_adr_1k;
+	struct resource *res = dev->resource + PCI_BRIDGE_RESOURCES;
+
+	pci_read_config_word(dev, 0x40, &en1k);
+
+	if (en1k & 0x200) {
+		pci_read_config_word(dev, PCI_IO_BASE, &iobl_adr);
+
+		iobl_adr_1k = iobl_adr | (res->start >> 8) | (res->end & 0xfc00);
+
+		if (iobl_adr != iobl_adr_1k) {
+			dev_info(&dev->dev, "Fixing P64H2 IOBL_ADR from 0x%x to 0x%x for 1KB granularity\n",
+				iobl_adr,iobl_adr_1k);
+			pci_write_config_word(dev, PCI_IO_BASE, iobl_adr_1k);
+		}
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x1460,		quirk_p64h2_1k_io_fix_iobl);
+
+/* Under some circumstances, AER is not linked with extended capabilities.
+ * Force it to be linked by setting the corresponding control bit in the
+ * config space.
+ */
+static void quirk_nvidia_ck804_pcie_aer_ext_cap(struct pci_dev *dev)
+{
+	uint8_t b;
+	if (pci_read_config_byte(dev, 0xf41, &b) == 0) {
+		if (!(b & 0x20)) {
+			pci_write_config_byte(dev, 0xf41, b | 0x20);
+			dev_info(&dev->dev,
+			       "Linking AER extended capability\n");
+		}
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA,  PCI_DEVICE_ID_NVIDIA_CK804_PCIE,
+			quirk_nvidia_ck804_pcie_aer_ext_cap);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_NVIDIA,  PCI_DEVICE_ID_NVIDIA_CK804_PCIE,
+			quirk_nvidia_ck804_pcie_aer_ext_cap);
+
+static void __devinit quirk_via_cx700_pci_parking_caching(struct pci_dev *dev)
+{
+	/*
+	 * Disable PCI Bus Parking and PCI Master read caching on CX700
+	 * which causes unspecified timing errors with a VT6212L on the PCI
+	 * bus leading to USB2.0 packet loss.
+	 *
+	 * This quirk is only enabled if a second (on the external PCI bus)
+	 * VT6212L is found -- the CX700 core itself also contains a USB
+	 * host controller with the same PCI ID as the VT6212L.
+	 */
+
+	/* Count VT6212L instances */
+	struct pci_dev *p = pci_get_device(PCI_VENDOR_ID_VIA,
+		PCI_DEVICE_ID_VIA_8235_USB_2, NULL);
+	uint8_t b;
+
+	/* p should contain the first (internal) VT6212L -- see if we have
+	   an external one by searching again */
+	p = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235_USB_2, p);
+	if (!p)
+		return;
+	pci_dev_put(p);
+
+	if (pci_read_config_byte(dev, 0x76, &b) == 0) {
+		if (b & 0x40) {
+			/* Turn off PCI Bus Parking */
+			pci_write_config_byte(dev, 0x76, b ^ 0x40);
+
+			dev_info(&dev->dev,
+				"Disabling VIA CX700 PCI parking\n");
+		}
+	}
+
+	if (pci_read_config_byte(dev, 0x72, &b) == 0) {
+		if (b != 0) {
+			/* Turn off PCI Master read caching */
+			pci_write_config_byte(dev, 0x72, 0x0);
+
+			/* Set PCI Master Bus time-out to "1x16 PCLK" */
+			pci_write_config_byte(dev, 0x75, 0x1);
+
+			/* Disable "Read FIFO Timer" */
+			pci_write_config_byte(dev, 0x77, 0x0);
+
+			dev_info(&dev->dev,
+				"Disabling VIA CX700 PCI caching\n");
+		}
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, 0x324e, quirk_via_cx700_pci_parking_caching);
+
+/*
+ * For Broadcom 5706, 5708, 5709 rev. A nics, any read beyond the
+ * VPD end tag will hang the device.  This problem was initially
+ * observed when a vpd entry was created in sysfs
+ * ('/sys/bus/pci/devices/<id>/vpd').   A read to this sysfs entry
+ * will dump 32k of data.  Reading a full 32k will cause an access
+ * beyond the VPD end tag causing the device to hang.  Once the device
+ * is hung, the bnx2 driver will not be able to reset the device.
+ * We believe that it is legal to read beyond the end tag and
+ * therefore the solution is to limit the read/write length.
+ */
+static void __devinit quirk_brcm_570x_limit_vpd(struct pci_dev *dev)
+{
+	/*
+	 * Only disable the VPD capability for 5706, 5706S, 5708,
+	 * 5708S and 5709 rev. A
+	 */
+	if ((dev->device == PCI_DEVICE_ID_NX2_5706) ||
+	    (dev->device == PCI_DEVICE_ID_NX2_5706S) ||
+	    (dev->device == PCI_DEVICE_ID_NX2_5708) ||
+	    (dev->device == PCI_DEVICE_ID_NX2_5708S) ||
+	    ((dev->device == PCI_DEVICE_ID_NX2_5709) &&
+	     (dev->revision & 0xf0) == 0x0)) {
+		if (dev->vpd)
+			dev->vpd->len = 0x80;
+	}
+}
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_BROADCOM,
+			PCI_DEVICE_ID_NX2_5706,
+			quirk_brcm_570x_limit_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_BROADCOM,
+			PCI_DEVICE_ID_NX2_5706S,
+			quirk_brcm_570x_limit_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_BROADCOM,
+			PCI_DEVICE_ID_NX2_5708,
+			quirk_brcm_570x_limit_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_BROADCOM,
+			PCI_DEVICE_ID_NX2_5708S,
+			quirk_brcm_570x_limit_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_BROADCOM,
+			PCI_DEVICE_ID_NX2_5709,
+			quirk_brcm_570x_limit_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_BROADCOM,
+			PCI_DEVICE_ID_NX2_5709S,
+			quirk_brcm_570x_limit_vpd);
+
+/* Originally in EDAC sources for i82875P:
+ * Intel tells BIOS developers to hide device 6 which
+ * configures the overflow device access containing
+ * the DRBs - this is where we expose device 6.
+ * http://www.x86-secret.com/articles/tweak/pat/patsecrets-2.htm
+ */
+static void __devinit quirk_unhide_mch_dev6(struct pci_dev *dev)
+{
+	u8 reg;
+
+	if (pci_read_config_byte(dev, 0xF4, &reg) == 0 && !(reg & 0x02)) {
+		dev_info(&dev->dev, "Enabling MCH 'Overflow' Device\n");
+		pci_write_config_byte(dev, 0xF4, reg | 0x02);
+	}
+}
+
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82865_HB,
+			quirk_unhide_mch_dev6);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82875_HB,
+			quirk_unhide_mch_dev6);
+
+#ifdef CONFIG_TILE
+/*
+ * The Tilera TILEmpower platform needs to set the link speed
+ * to 2.5GT(Giga-Transfers)/s (Gen 1). The default link speed
+ * setting is 5GT/s (Gen 2). 0x98 is the Link Control2 PCIe
+ * capability register of the PEX8624 PCIe switch. The switch
+ * supports link speed auto negotiation, but falsely sets
+ * the link speed to 5GT/s.
+ */
+static void __devinit quirk_tile_plx_gen1(struct pci_dev *dev)
+{
+	if (tile_plx_gen1) {
+		pci_write_config_dword(dev, 0x98, 0x1);
+		mdelay(50);
+	}
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_PLX, 0x8624, quirk_tile_plx_gen1);
+#endif /* CONFIG_TILE */
+
+#ifdef CONFIG_PCI_MSI
+/* Some chipsets do not support MSI. We cannot easily rely on setting
+ * PCI_BUS_FLAGS_NO_MSI in its bus flags because there are actually
+ * some other busses controlled by the chipset even if Linux is not
+ * aware of it.  Instead of setting the flag on all busses in the
+ * machine, simply disable MSI globally.
+ */
+static void __init quirk_disable_all_msi(struct pci_dev *dev)
+{
+	pci_no_msi();
+	dev_warn(&dev->dev, "MSI quirk detected; MSI disabled\n");
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_GCNB_LE, quirk_disable_all_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_RS400_200, quirk_disable_all_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_RS480, quirk_disable_all_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_VT3336, quirk_disable_all_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_VT3351, quirk_disable_all_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_VT3364, quirk_disable_all_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8380_0, quirk_disable_all_msi);
+
+/* Disable MSI on chipsets that are known to not support it */
+static void __devinit quirk_disable_msi(struct pci_dev *dev)
+{
+	if (dev->subordinate) {
+		dev_warn(&dev->dev, "MSI quirk detected; "
+			"subordinate MSI disabled\n");
+		dev->subordinate->bus_flags |= PCI_BUS_FLAGS_NO_MSI;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8131_BRIDGE, quirk_disable_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, 0xa238, quirk_disable_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x5a3f, quirk_disable_msi);
+
+/*
+ * The APC bridge device in AMD 780 family northbridges has some random
+ * OEM subsystem ID in its vendor ID register (erratum 18), so instead
+ * we use the possible vendor/device IDs of the host bridge for the
+ * declared quirk, and search for the APC bridge by slot number.
+ */
+static void __devinit quirk_amd_780_apc_msi(struct pci_dev *host_bridge)
+{
+	struct pci_dev *apc_bridge;
+
+	apc_bridge = pci_get_slot(host_bridge->bus, PCI_DEVFN(1, 0));
+	if (apc_bridge) {
+		if (apc_bridge->device == 0x9602)
+			quirk_disable_msi(apc_bridge);
+		pci_dev_put(apc_bridge);
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x9600, quirk_amd_780_apc_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x9601, quirk_amd_780_apc_msi);
+
+/* Go through the list of Hypertransport capabilities and
+ * return 1 if a HT MSI capability is found and enabled */
+static int __devinit msi_ht_cap_enabled(struct pci_dev *dev)
+{
+	int pos, ttl = 48;
+
+	pos = pci_find_ht_capability(dev, HT_CAPTYPE_MSI_MAPPING);
+	while (pos && ttl--) {
+		u8 flags;
+
+		if (pci_read_config_byte(dev, pos + HT_MSI_FLAGS,
+					 &flags) == 0)
+		{
+			dev_info(&dev->dev, "Found %s HT MSI Mapping\n",
+				flags & HT_MSI_FLAGS_ENABLE ?
+				"enabled" : "disabled");
+			return (flags & HT_MSI_FLAGS_ENABLE) != 0;
+		}
+
+		pos = pci_find_next_ht_capability(dev, pos,
+						  HT_CAPTYPE_MSI_MAPPING);
+	}
+	return 0;
+}
+
+/* Check the hypertransport MSI mapping to know whether MSI is enabled or not */
+static void __devinit quirk_msi_ht_cap(struct pci_dev *dev)
+{
+	if (dev->subordinate && !msi_ht_cap_enabled(dev)) {
+		dev_warn(&dev->dev, "MSI quirk detected; "
+			"subordinate MSI disabled\n");
+		dev->subordinate->bus_flags |= PCI_BUS_FLAGS_NO_MSI;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_HT2000_PCIE,
+			quirk_msi_ht_cap);
+
+/* The nVidia CK804 chipset may have 2 HT MSI mappings.
+ * MSI are supported if the MSI capability set in any of these mappings.
+ */
+static void __devinit quirk_nvidia_ck804_msi_ht_cap(struct pci_dev *dev)
+{
+	struct pci_dev *pdev;
+
+	if (!dev->subordinate)
+		return;
+
+	/* check HT MSI cap on this chipset and the root one.
+	 * a single one having MSI is enough to be sure that MSI are supported.
+	 */
+	pdev = pci_get_slot(dev->bus, 0);
+	if (!pdev)
+		return;
+	if (!msi_ht_cap_enabled(dev) && !msi_ht_cap_enabled(pdev)) {
+		dev_warn(&dev->dev, "MSI quirk detected; "
+			"subordinate MSI disabled\n");
+		dev->subordinate->bus_flags |= PCI_BUS_FLAGS_NO_MSI;
+	}
+	pci_dev_put(pdev);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_CK804_PCIE,
+			quirk_nvidia_ck804_msi_ht_cap);
+
+/* Force enable MSI mapping capability on HT bridges */
+static void __devinit ht_enable_msi_mapping(struct pci_dev *dev)
+{
+	int pos, ttl = 48;
+
+	pos = pci_find_ht_capability(dev, HT_CAPTYPE_MSI_MAPPING);
+	while (pos && ttl--) {
+		u8 flags;
+
+		if (pci_read_config_byte(dev, pos + HT_MSI_FLAGS,
+					 &flags) == 0) {
+			dev_info(&dev->dev, "Enabling HT MSI Mapping\n");
+
+			pci_write_config_byte(dev, pos + HT_MSI_FLAGS,
+					      flags | HT_MSI_FLAGS_ENABLE);
+		}
+		pos = pci_find_next_ht_capability(dev, pos,
+						  HT_CAPTYPE_MSI_MAPPING);
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SERVERWORKS,
+			 PCI_DEVICE_ID_SERVERWORKS_HT1000_PXB,
+			 ht_enable_msi_mapping);
+
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8132_BRIDGE,
+			 ht_enable_msi_mapping);
+
+/* The P5N32-SLI motherboards from Asus have a problem with msi
+ * for the MCP55 NIC. It is not yet determined whether the msi problem
+ * also affects other devices. As for now, turn off msi for this device.
+ */
+static void __devinit nvenet_msi_disable(struct pci_dev *dev)
+{
+	const char *board_name = dmi_get_system_info(DMI_BOARD_NAME);
+
+	if (board_name &&
+	    (strstr(board_name, "P5N32-SLI PREMIUM") ||
+	     strstr(board_name, "P5N32-E SLI"))) {
+		dev_info(&dev->dev,
+			 "Disabling msi for MCP55 NIC on P5N32-SLI\n");
+		dev->no_msi = 1;
+	}
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA,
+			PCI_DEVICE_ID_NVIDIA_NVENET_15,
+			nvenet_msi_disable);
+
+/*
+ * Some versions of the MCP55 bridge from nvidia have a legacy irq routing
+ * config register.  This register controls the routing of legacy interrupts
+ * from devices that route through the MCP55.  If this register is misprogramed
+ * interrupts are only sent to the bsp, unlike conventional systems where the
+ * irq is broadxast to all online cpus.  Not having this register set
+ * properly prevents kdump from booting up properly, so lets make sure that
+ * we have it set correctly.
+ * Note this is an undocumented register.
+ */
+static void __devinit nvbridge_check_legacy_irq_routing(struct pci_dev *dev)
+{
+	u32 cfg;
+
+	if (!pci_find_capability(dev, PCI_CAP_ID_HT))
+		return;
+
+	pci_read_config_dword(dev, 0x74, &cfg);
+
+	if (cfg & ((1 << 2) | (1 << 15))) {
+		printk(KERN_INFO "Rewriting irq routing register on MCP55\n");
+		cfg &= ~((1 << 2) | (1 << 15));
+		pci_write_config_dword(dev, 0x74, cfg);
+	}
+}
+
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA,
+			PCI_DEVICE_ID_NVIDIA_MCP55_BRIDGE_V0,
+			nvbridge_check_legacy_irq_routing);
+
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA,
+			PCI_DEVICE_ID_NVIDIA_MCP55_BRIDGE_V4,
+			nvbridge_check_legacy_irq_routing);
+
+static int __devinit ht_check_msi_mapping(struct pci_dev *dev)
+{
+	int pos, ttl = 48;
+	int found = 0;
+
+	/* check if there is HT MSI cap or enabled on this device */
+	pos = pci_find_ht_capability(dev, HT_CAPTYPE_MSI_MAPPING);
+	while (pos && ttl--) {
+		u8 flags;
+
+		if (found < 1)
+			found = 1;
+		if (pci_read_config_byte(dev, pos + HT_MSI_FLAGS,
+					 &flags) == 0) {
+			if (flags & HT_MSI_FLAGS_ENABLE) {
+				if (found < 2) {
+					found = 2;
+					break;
+				}
+			}
+		}
+		pos = pci_find_next_ht_capability(dev, pos,
+						  HT_CAPTYPE_MSI_MAPPING);
+	}
+
+	return found;
+}
+
+static int __devinit host_bridge_with_leaf(struct pci_dev *host_bridge)
+{
+	struct pci_dev *dev;
+	int pos;
+	int i, dev_no;
+	int found = 0;
+
+	dev_no = host_bridge->devfn >> 3;
+	for (i = dev_no + 1; i < 0x20; i++) {
+		dev = pci_get_slot(host_bridge->bus, PCI_DEVFN(i, 0));
+		if (!dev)
+			continue;
+
+		/* found next host bridge ?*/
+		pos = pci_find_ht_capability(dev, HT_CAPTYPE_SLAVE);
+		if (pos != 0) {
+			pci_dev_put(dev);
+			break;
+		}
+
+		if (ht_check_msi_mapping(dev)) {
+			found = 1;
+			pci_dev_put(dev);
+			break;
+		}
+		pci_dev_put(dev);
+	}
+
+	return found;
+}
+
+#define PCI_HT_CAP_SLAVE_CTRL0     4    /* link control */
+#define PCI_HT_CAP_SLAVE_CTRL1     8    /* link control to */
+
+static int __devinit is_end_of_ht_chain(struct pci_dev *dev)
+{
+	int pos, ctrl_off;
+	int end = 0;
+	u16 flags, ctrl;
+
+	pos = pci_find_ht_capability(dev, HT_CAPTYPE_SLAVE);
+
+	if (!pos)
+		goto out;
+
+	pci_read_config_word(dev, pos + PCI_CAP_FLAGS, &flags);
+
+	ctrl_off = ((flags >> 10) & 1) ?
+			PCI_HT_CAP_SLAVE_CTRL0 : PCI_HT_CAP_SLAVE_CTRL1;
+	pci_read_config_word(dev, pos + ctrl_off, &ctrl);
+
+	if (ctrl & (1 << 6))
+		end = 1;
+
+out:
+	return end;
+}
+
+static void __devinit nv_ht_enable_msi_mapping(struct pci_dev *dev)
+{
+	struct pci_dev *host_bridge;
+	int pos;
+	int i, dev_no;
+	int found = 0;
+
+	dev_no = dev->devfn >> 3;
+	for (i = dev_no; i >= 0; i--) {
+		host_bridge = pci_get_slot(dev->bus, PCI_DEVFN(i, 0));
+		if (!host_bridge)
+			continue;
+
+		pos = pci_find_ht_capability(host_bridge, HT_CAPTYPE_SLAVE);
+		if (pos != 0) {
+			found = 1;
+			break;
+		}
+		pci_dev_put(host_bridge);
+	}
+
+	if (!found)
+		return;
+
+	/* don't enable end_device/host_bridge with leaf directly here */
+	if (host_bridge == dev && is_end_of_ht_chain(host_bridge) &&
+	    host_bridge_with_leaf(host_bridge))
+		goto out;
+
+	/* root did that ! */
+	if (msi_ht_cap_enabled(host_bridge))
+		goto out;
+
+	ht_enable_msi_mapping(dev);
+
+out:
+	pci_dev_put(host_bridge);
+}
+
+static void __devinit ht_disable_msi_mapping(struct pci_dev *dev)
+{
+	int pos, ttl = 48;
+
+	pos = pci_find_ht_capability(dev, HT_CAPTYPE_MSI_MAPPING);
+	while (pos && ttl--) {
+		u8 flags;
+
+		if (pci_read_config_byte(dev, pos + HT_MSI_FLAGS,
+					 &flags) == 0) {
+			dev_info(&dev->dev, "Disabling HT MSI Mapping\n");
+
+			pci_write_config_byte(dev, pos + HT_MSI_FLAGS,
+					      flags & ~HT_MSI_FLAGS_ENABLE);
+		}
+		pos = pci_find_next_ht_capability(dev, pos,
+						  HT_CAPTYPE_MSI_MAPPING);
+	}
+}
+
+static void __devinit __nv_msi_ht_cap_quirk(struct pci_dev *dev, int all)
+{
+	struct pci_dev *host_bridge;
+	int pos;
+	int found;
+
+	if (!pci_msi_enabled())
+		return;
+
+	/* check if there is HT MSI cap or enabled on this device */
+	found = ht_check_msi_mapping(dev);
+
+	/* no HT MSI CAP */
+	if (found == 0)
+		return;
+
+	/*
+	 * HT MSI mapping should be disabled on devices that are below
+	 * a non-Hypertransport host bridge. Locate the host bridge...
+	 */
+	host_bridge = pci_get_bus_and_slot(0, PCI_DEVFN(0, 0));
+	if (host_bridge == NULL) {
+		dev_warn(&dev->dev,
+			 "nv_msi_ht_cap_quirk didn't locate host bridge\n");
+		return;
+	}
+
+	pos = pci_find_ht_capability(host_bridge, HT_CAPTYPE_SLAVE);
+	if (pos != 0) {
+		/* Host bridge is to HT */
+		if (found == 1) {
+			/* it is not enabled, try to enable it */
+			if (all)
+				ht_enable_msi_mapping(dev);
+			else
+				nv_ht_enable_msi_mapping(dev);
+		}
+		return;
+	}
+
+	/* HT MSI is not enabled */
+	if (found == 1)
+		return;
+
+	/* Host bridge is not to HT, disable HT MSI mapping on this device */
+	ht_disable_msi_mapping(dev);
+}
+
+static void __devinit nv_msi_ht_cap_quirk_all(struct pci_dev *dev)
+{
+	return __nv_msi_ht_cap_quirk(dev, 1);
+}
+
+static void __devinit nv_msi_ht_cap_quirk_leaf(struct pci_dev *dev)
+{
+	return __nv_msi_ht_cap_quirk(dev, 0);
+}
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, nv_msi_ht_cap_quirk_leaf);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, nv_msi_ht_cap_quirk_leaf);
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, PCI_ANY_ID, nv_msi_ht_cap_quirk_all);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_AL, PCI_ANY_ID, nv_msi_ht_cap_quirk_all);
+
+static void __devinit quirk_msi_intx_disable_bug(struct pci_dev *dev)
+{
+	dev->dev_flags |= PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG;
+}
+static void __devinit quirk_msi_intx_disable_ati_bug(struct pci_dev *dev)
+{
+	struct pci_dev *p;
+
+	/* SB700 MSI issue will be fixed at HW level from revision A21,
+	 * we need check PCI REVISION ID of SMBus controller to get SB700
+	 * revision.
+	 */
+	p = pci_get_device(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
+			   NULL);
+	if (!p)
+		return;
+
+	if ((p->revision < 0x3B) && (p->revision >= 0x30))
+		dev->dev_flags |= PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG;
+	pci_dev_put(p);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_BROADCOM,
+			PCI_DEVICE_ID_TIGON3_5780,
+			quirk_msi_intx_disable_bug);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_BROADCOM,
+			PCI_DEVICE_ID_TIGON3_5780S,
+			quirk_msi_intx_disable_bug);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_BROADCOM,
+			PCI_DEVICE_ID_TIGON3_5714,
+			quirk_msi_intx_disable_bug);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_BROADCOM,
+			PCI_DEVICE_ID_TIGON3_5714S,
+			quirk_msi_intx_disable_bug);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_BROADCOM,
+			PCI_DEVICE_ID_TIGON3_5715,
+			quirk_msi_intx_disable_bug);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_BROADCOM,
+			PCI_DEVICE_ID_TIGON3_5715S,
+			quirk_msi_intx_disable_bug);
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x4390,
+			quirk_msi_intx_disable_ati_bug);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x4391,
+			quirk_msi_intx_disable_ati_bug);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x4392,
+			quirk_msi_intx_disable_ati_bug);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x4393,
+			quirk_msi_intx_disable_ati_bug);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x4394,
+			quirk_msi_intx_disable_ati_bug);
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x4373,
+			quirk_msi_intx_disable_bug);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x4374,
+			quirk_msi_intx_disable_bug);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x4375,
+			quirk_msi_intx_disable_bug);
+
+#endif /* CONFIG_PCI_MSI */
+
+/* Allow manual resource allocation for PCI hotplug bridges
+ * via pci=hpmemsize=nnM and pci=hpiosize=nnM parameters. For
+ * some PCI-PCI hotplug bridges, like PLX 6254 (former HINT HB6),
+ * kernel fails to allocate resources when hotplug device is 
+ * inserted and PCI bus is rescanned.
+ */
+static void __devinit quirk_hotplug_bridge(struct pci_dev *dev)
+{
+	dev->is_hotplug_bridge = 1;
+}
+
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HINT, 0x0020, quirk_hotplug_bridge);
+
+/*
+ * This is a quirk for the Ricoh MMC controller found as a part of
+ * some mulifunction chips.
+
+ * This is very similar and based on the ricoh_mmc driver written by
+ * Philip Langdale. Thank you for these magic sequences.
+ *
+ * These chips implement the four main memory card controllers (SD, MMC, MS, xD)
+ * and one or both of cardbus or firewire.
+ *
+ * It happens that they implement SD and MMC
+ * support as separate controllers (and PCI functions). The linux SDHCI
+ * driver supports MMC cards but the chip detects MMC cards in hardware
+ * and directs them to the MMC controller - so the SDHCI driver never sees
+ * them.
+ *
+ * To get around this, we must disable the useless MMC controller.
+ * At that point, the SDHCI controller will start seeing them
+ * It seems to be the case that the relevant PCI registers to deactivate the
+ * MMC controller live on PCI function 0, which might be the cardbus controller
+ * or the firewire controller, depending on the particular chip in question
+ *
+ * This has to be done early, because as soon as we disable the MMC controller
+ * other pci functions shift up one level, e.g. function #2 becomes function
+ * #1, and this will confuse the pci core.
+ */
+
+#ifdef CONFIG_MMC_RICOH_MMC
+static void ricoh_mmc_fixup_rl5c476(struct pci_dev *dev)
+{
+	/* disable via cardbus interface */
+	u8 write_enable;
+	u8 write_target;
+	u8 disable;
+
+	/* disable must be done via function #0 */
+	if (PCI_FUNC(dev->devfn))
+		return;
+
+	pci_read_config_byte(dev, 0xB7, &disable);
+	if (disable & 0x02)
+		return;
+
+	pci_read_config_byte(dev, 0x8E, &write_enable);
+	pci_write_config_byte(dev, 0x8E, 0xAA);
+	pci_read_config_byte(dev, 0x8D, &write_target);
+	pci_write_config_byte(dev, 0x8D, 0xB7);
+	pci_write_config_byte(dev, 0xB7, disable | 0x02);
+	pci_write_config_byte(dev, 0x8E, write_enable);
+	pci_write_config_byte(dev, 0x8D, write_target);
+
+	dev_notice(&dev->dev, "proprietary Ricoh MMC controller disabled (via cardbus function)\n");
+	dev_notice(&dev->dev, "MMC cards are now supported by standard SDHCI controller\n");
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_RL5C476, ricoh_mmc_fixup_rl5c476);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_RL5C476, ricoh_mmc_fixup_rl5c476);
+
+static void ricoh_mmc_fixup_r5c832(struct pci_dev *dev)
+{
+	/* disable via firewire interface */
+	u8 write_enable;
+	u8 disable;
+
+	/* disable must be done via function #0 */
+	if (PCI_FUNC(dev->devfn))
+		return;
+	/*
+	 * RICOH 0xe823 SD/MMC card reader fails to recognize
+	 * certain types of SD/MMC cards. Lowering the SD base
+	 * clock frequency from 200Mhz to 50Mhz fixes this issue.
+	 *
+	 * 0x150 - SD2.0 mode enable for changing base clock
+	 *	   frequency to 50Mhz
+	 * 0xe1  - Base clock frequency
+	 * 0x32  - 50Mhz new clock frequency
+	 * 0xf9  - Key register for 0x150
+	 * 0xfc  - key register for 0xe1
+	 */
+	if (dev->device == PCI_DEVICE_ID_RICOH_R5CE823) {
+		pci_write_config_byte(dev, 0xf9, 0xfc);
+		pci_write_config_byte(dev, 0x150, 0x10);
+		pci_write_config_byte(dev, 0xf9, 0x00);
+		pci_write_config_byte(dev, 0xfc, 0x01);
+		pci_write_config_byte(dev, 0xe1, 0x32);
+		pci_write_config_byte(dev, 0xfc, 0x00);
+
+		dev_notice(&dev->dev, "MMC controller base frequency changed to 50Mhz.\n");
+	}
+
+	pci_read_config_byte(dev, 0xCB, &disable);
+
+	if (disable & 0x02)
+		return;
+
+	pci_read_config_byte(dev, 0xCA, &write_enable);
+	pci_write_config_byte(dev, 0xCA, 0x57);
+	pci_write_config_byte(dev, 0xCB, disable | 0x02);
+	pci_write_config_byte(dev, 0xCA, write_enable);
+
+	dev_notice(&dev->dev, "proprietary Ricoh MMC controller disabled (via firewire function)\n");
+	dev_notice(&dev->dev, "MMC cards are now supported by standard SDHCI controller\n");
+
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5C832, ricoh_mmc_fixup_r5c832);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5C832, ricoh_mmc_fixup_r5c832);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5CE823, ricoh_mmc_fixup_r5c832);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5CE823, ricoh_mmc_fixup_r5c832);
+#endif /*CONFIG_MMC_RICOH_MMC*/
+
+#if defined(CONFIG_DMAR) || defined(CONFIG_INTR_REMAP)
+#define VTUNCERRMSK_REG	0x1ac
+#define VTD_MSK_SPEC_ERRORS	(1 << 31)
+/*
+ * This is a quirk for masking vt-d spec defined errors to platform error
+ * handling logic. With out this, platforms using Intel 7500, 5500 chipsets
+ * (and the derivative chipsets like X58 etc) seem to generate NMI/SMI (based
+ * on the RAS config settings of the platform) when a vt-d fault happens.
+ * The resulting SMI caused the system to hang.
+ *
+ * VT-d spec related errors are already handled by the VT-d OS code, so no
+ * need to report the same error through other channels.
+ */
+static void vtd_mask_spec_errors(struct pci_dev *dev)
+{
+	u32 word;
+
+	pci_read_config_dword(dev, VTUNCERRMSK_REG, &word);
+	pci_write_config_dword(dev, VTUNCERRMSK_REG, word | VTD_MSK_SPEC_ERRORS);
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x342e, vtd_mask_spec_errors);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x3c28, vtd_mask_spec_errors);
+#endif
+
+static void __devinit fixup_ti816x_class(struct pci_dev* dev)
+{
+	/* TI 816x devices do not have class code set when in PCIe boot mode */
+	if (dev->class == PCI_CLASS_NOT_DEFINED) {
+		dev_info(&dev->dev, "Setting PCI class for 816x PCIe device\n");
+		dev->class = PCI_CLASS_MULTIMEDIA_VIDEO;
+	}
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_TI, 0xb800, fixup_ti816x_class);
+
+/*
+ * Some BIOS implementations leave the Intel GPU interrupts enabled,
+ * even though no one is handling them (f.e. i915 driver is never loaded).
+ * Additionally the interrupt destination is not set up properly
+ * and the interrupt ends up -somewhere-.
+ *
+ * These spurious interrupts are "sticky" and the kernel disables
+ * the (shared) interrupt line after 100.000+ generated interrupts.
+ *
+ * Fix it by disabling the still enabled interrupts.
+ * This resolves crashes often seen on monitor unplug.
+ */
+#define I915_DEIER_REG 0x4400c
+static void __devinit disable_igfx_irq(struct pci_dev *dev)
+{
+	void __iomem *regs = pci_iomap(dev, 0, 0);
+	if (regs == NULL) {
+		dev_warn(&dev->dev, "igfx quirk: Can't iomap PCI device\n");
+		return;
+	}
+
+	/* Check if any interrupt line is still enabled */
+	if (readl(regs + I915_DEIER_REG) != 0) {
+		dev_warn(&dev->dev, "BIOS left Intel GPU interrupts enabled; "
+			"disabling\n");
+
+		writel(0, regs + I915_DEIER_REG);
+	}
+
+	pci_iounmap(dev, regs);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0102, disable_igfx_irq);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x010a, disable_igfx_irq);
+
+static void pci_do_fixups(struct pci_dev *dev, struct pci_fixup *f,
+			  struct pci_fixup *end)
+{
+	while (f < end) {
+		if ((f->vendor == dev->vendor || f->vendor == (u16) PCI_ANY_ID) &&
+		    (f->device == dev->device || f->device == (u16) PCI_ANY_ID)) {
+			dev_dbg(&dev->dev, "calling %pF\n", f->hook);
+			f->hook(dev);
+		}
+		f++;
+	}
+}
+
+extern struct pci_fixup __start_pci_fixups_early[];
+extern struct pci_fixup __end_pci_fixups_early[];
+extern struct pci_fixup __start_pci_fixups_header[];
+extern struct pci_fixup __end_pci_fixups_header[];
+extern struct pci_fixup __start_pci_fixups_final[];
+extern struct pci_fixup __end_pci_fixups_final[];
+extern struct pci_fixup __start_pci_fixups_enable[];
+extern struct pci_fixup __end_pci_fixups_enable[];
+extern struct pci_fixup __start_pci_fixups_resume[];
+extern struct pci_fixup __end_pci_fixups_resume[];
+extern struct pci_fixup __start_pci_fixups_resume_early[];
+extern struct pci_fixup __end_pci_fixups_resume_early[];
+extern struct pci_fixup __start_pci_fixups_suspend[];
+extern struct pci_fixup __end_pci_fixups_suspend[];
+
+
+void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev)
+{
+	struct pci_fixup *start, *end;
+
+	switch(pass) {
+	case pci_fixup_early:
+		start = __start_pci_fixups_early;
+		end = __end_pci_fixups_early;
+		break;
+
+	case pci_fixup_header:
+		start = __start_pci_fixups_header;
+		end = __end_pci_fixups_header;
+		break;
+
+	case pci_fixup_final:
+		start = __start_pci_fixups_final;
+		end = __end_pci_fixups_final;
+		break;
+
+	case pci_fixup_enable:
+		start = __start_pci_fixups_enable;
+		end = __end_pci_fixups_enable;
+		break;
+
+	case pci_fixup_resume:
+		start = __start_pci_fixups_resume;
+		end = __end_pci_fixups_resume;
+		break;
+
+	case pci_fixup_resume_early:
+		start = __start_pci_fixups_resume_early;
+		end = __end_pci_fixups_resume_early;
+		break;
+
+	case pci_fixup_suspend:
+		start = __start_pci_fixups_suspend;
+		end = __end_pci_fixups_suspend;
+		break;
+
+	default:
+		/* stupid compiler warning, you would think with an enum... */
+		return;
+	}
+	pci_do_fixups(dev, start, end);
+}
+EXPORT_SYMBOL(pci_fixup_device);
+
+static int __init pci_apply_final_quirks(void)
+{
+	struct pci_dev *dev = NULL;
+	u8 cls = 0;
+	u8 tmp;
+
+	if (pci_cache_line_size)
+		printk(KERN_DEBUG "PCI: CLS %u bytes\n",
+		       pci_cache_line_size << 2);
+
+	for_each_pci_dev(dev) {
+		pci_fixup_device(pci_fixup_final, dev);
+		/*
+		 * If arch hasn't set it explicitly yet, use the CLS
+		 * value shared by all PCI devices.  If there's a
+		 * mismatch, fall back to the default value.
+		 */
+		if (!pci_cache_line_size) {
+			pci_read_config_byte(dev, PCI_CACHE_LINE_SIZE, &tmp);
+			if (!cls)
+				cls = tmp;
+			if (!tmp || cls == tmp)
+				continue;
+
+			printk(KERN_DEBUG "PCI: CLS mismatch (%u != %u), "
+			       "using %u bytes\n", cls << 2, tmp << 2,
+			       pci_dfl_cache_line_size << 2);
+			pci_cache_line_size = pci_dfl_cache_line_size;
+		}
+	}
+	if (!pci_cache_line_size) {
+		printk(KERN_DEBUG "PCI: CLS %u bytes, default %u\n",
+		       cls << 2, pci_dfl_cache_line_size << 2);
+		pci_cache_line_size = cls ? cls : pci_dfl_cache_line_size;
+	}
+
+	return 0;
+}
+
+fs_initcall_sync(pci_apply_final_quirks);
+
+/*
+ * Followings are device-specific reset methods which can be used to
+ * reset a single function if other methods (e.g. FLR, PM D0->D3) are
+ * not available.
+ */
+static int reset_intel_generic_dev(struct pci_dev *dev, int probe)
+{
+	int pos;
+
+	/* only implement PCI_CLASS_SERIAL_USB at present */
+	if (dev->class == PCI_CLASS_SERIAL_USB) {
+		pos = pci_find_capability(dev, PCI_CAP_ID_VNDR);
+		if (!pos)
+			return -ENOTTY;
+
+		if (probe)
+			return 0;
+
+		pci_write_config_byte(dev, pos + 0x4, 1);
+		msleep(100);
+
+		return 0;
+	} else {
+		return -ENOTTY;
+	}
+}
+
+static int reset_intel_82599_sfp_virtfn(struct pci_dev *dev, int probe)
+{
+	int pos;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
+	if (!pos)
+		return -ENOTTY;
+
+	if (probe)
+		return 0;
+
+	pci_write_config_word(dev, pos + PCI_EXP_DEVCTL,
+				PCI_EXP_DEVCTL_BCR_FLR);
+	msleep(100);
+
+	return 0;
+}
+
+#define PCI_DEVICE_ID_INTEL_82599_SFP_VF   0x10ed
+
+static const struct pci_dev_reset_methods pci_dev_reset_methods[] = {
+	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82599_SFP_VF,
+		 reset_intel_82599_sfp_virtfn },
+	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
+		reset_intel_generic_dev },
+	{ 0 }
+};
+
+int pci_dev_specific_reset(struct pci_dev *dev, int probe)
+{
+	const struct pci_dev_reset_methods *i;
+
+	for (i = pci_dev_reset_methods; i->reset; i++) {
+		if ((i->vendor == dev->vendor ||
+		     i->vendor == (u16)PCI_ANY_ID) &&
+		    (i->device == dev->device ||
+		     i->device == (u16)PCI_ANY_ID))
+			return i->reset(dev, probe);
+	}
+
+	return -ENOTTY;
+}
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
new file mode 100644
index 00000000..7f87beed
--- /dev/null
+++ b/drivers/pci/remove.c
@@ -0,0 +1,151 @@
+#include <linux/pci.h>
+#include <linux/module.h>
+#include <linux/pci-aspm.h>
+#include "pci.h"
+
+static void pci_free_resources(struct pci_dev *dev)
+{
+	int i;
+
+ 	msi_remove_pci_irq_vectors(dev);
+
+	pci_cleanup_rom(dev);
+	for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+		struct resource *res = dev->resource + i;
+		if (res->parent)
+			release_resource(res);
+	}
+}
+
+static void pci_stop_dev(struct pci_dev *dev)
+{
+	if (dev->is_added) {
+		pci_proc_detach_device(dev);
+		pci_remove_sysfs_dev_files(dev);
+		device_unregister(&dev->dev);
+		dev->is_added = 0;
+	}
+
+	if (dev->bus->self)
+		pcie_aspm_exit_link_state(dev);
+}
+
+static void pci_destroy_dev(struct pci_dev *dev)
+{
+	/* Remove the device from the device lists, and prevent any further
+	 * list accesses from this device */
+	down_write(&pci_bus_sem);
+	list_del(&dev->bus_list);
+	dev->bus_list.next = dev->bus_list.prev = NULL;
+	up_write(&pci_bus_sem);
+
+	pci_free_resources(dev);
+	pci_dev_put(dev);
+}
+
+/**
+ * pci_remove_device_safe - remove an unused hotplug device
+ * @dev: the device to remove
+ *
+ * Delete the device structure from the device lists and 
+ * notify userspace (/sbin/hotplug), but only if the device
+ * in question is not being used by a driver.
+ * Returns 0 on success.
+ */
+#if 0
+int pci_remove_device_safe(struct pci_dev *dev)
+{
+	if (pci_dev_driver(dev))
+		return -EBUSY;
+	pci_destroy_dev(dev);
+	return 0;
+}
+#endif  /*  0  */
+
+void pci_remove_bus(struct pci_bus *pci_bus)
+{
+	pci_proc_detach_bus(pci_bus);
+
+	down_write(&pci_bus_sem);
+	list_del(&pci_bus->node);
+	up_write(&pci_bus_sem);
+	if (!pci_bus->is_added)
+		return;
+
+	pci_remove_legacy_files(pci_bus);
+	device_unregister(&pci_bus->dev);
+}
+EXPORT_SYMBOL(pci_remove_bus);
+
+/**
+ * pci_remove_bus_device - remove a PCI device and any children
+ * @dev: the device to remove
+ *
+ * Remove a PCI device from the device lists, informing the drivers
+ * that the device has been removed.  We also remove any subordinate
+ * buses and children in a depth-first manner.
+ *
+ * For each device we remove, delete the device structure from the
+ * device lists, remove the /proc entry, and notify userspace
+ * (/sbin/hotplug).
+ */
+void pci_remove_bus_device(struct pci_dev *dev)
+{
+	pci_stop_bus_device(dev);
+	if (dev->subordinate) {
+		struct pci_bus *b = dev->subordinate;
+
+		pci_remove_behind_bridge(dev);
+		pci_remove_bus(b);
+		dev->subordinate = NULL;
+	}
+
+	pci_destroy_dev(dev);
+}
+
+/**
+ * pci_remove_behind_bridge - remove all devices behind a PCI bridge
+ * @dev: PCI bridge device
+ *
+ * Remove all devices on the bus, except for the parent bridge.
+ * This also removes any child buses, and any devices they may
+ * contain in a depth-first manner.
+ */
+void pci_remove_behind_bridge(struct pci_dev *dev)
+{
+	struct list_head *l, *n;
+
+	if (dev->subordinate)
+		list_for_each_safe(l, n, &dev->subordinate->devices)
+			pci_remove_bus_device(pci_dev_b(l));
+}
+
+static void pci_stop_bus_devices(struct pci_bus *bus)
+{
+	struct list_head *l, *n;
+
+	list_for_each_safe(l, n, &bus->devices) {
+		struct pci_dev *dev = pci_dev_b(l);
+		pci_stop_bus_device(dev);
+	}
+}
+
+/**
+ * pci_stop_bus_device - stop a PCI device and any children
+ * @dev: the device to stop
+ *
+ * Stop a PCI device (detach the driver, remove from the global list
+ * and so on). This also stop any subordinate buses and children in a
+ * depth-first manner.
+ */
+void pci_stop_bus_device(struct pci_dev *dev)
+{
+	if (dev->subordinate)
+		pci_stop_bus_devices(dev->subordinate);
+
+	pci_stop_dev(dev);
+}
+
+EXPORT_SYMBOL(pci_remove_bus_device);
+EXPORT_SYMBOL(pci_remove_behind_bridge);
+EXPORT_SYMBOL_GPL(pci_stop_bus_device);
diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
new file mode 100644
index 00000000..36864a93
--- /dev/null
+++ b/drivers/pci/rom.c
@@ -0,0 +1,269 @@
+/*
+ * drivers/pci/rom.c
+ *
+ * (C) Copyright 2004 Jon Smirl <jonsmirl@yahoo.com>
+ * (C) Copyright 2004 Silicon Graphics, Inc. Jesse Barnes <jbarnes@sgi.com>
+ *
+ * PCI ROM access routines
+ */
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+
+#include "pci.h"
+
+/**
+ * pci_enable_rom - enable ROM decoding for a PCI device
+ * @pdev: PCI device to enable
+ *
+ * Enable ROM decoding on @dev.  This involves simply turning on the last
+ * bit of the PCI ROM BAR.  Note that some cards may share address decoders
+ * between the ROM and other resources, so enabling it may disable access
+ * to MMIO registers or other card memory.
+ */
+int pci_enable_rom(struct pci_dev *pdev)
+{
+	struct resource *res = pdev->resource + PCI_ROM_RESOURCE;
+	struct pci_bus_region region;
+	u32 rom_addr;
+
+	if (!res->flags)
+		return -1;
+
+	pcibios_resource_to_bus(pdev, &region, res);
+	pci_read_config_dword(pdev, pdev->rom_base_reg, &rom_addr);
+	rom_addr &= ~PCI_ROM_ADDRESS_MASK;
+	rom_addr |= region.start | PCI_ROM_ADDRESS_ENABLE;
+	pci_write_config_dword(pdev, pdev->rom_base_reg, rom_addr);
+	return 0;
+}
+
+/**
+ * pci_disable_rom - disable ROM decoding for a PCI device
+ * @pdev: PCI device to disable
+ *
+ * Disable ROM decoding on a PCI device by turning off the last bit in the
+ * ROM BAR.
+ */
+void pci_disable_rom(struct pci_dev *pdev)
+{
+	u32 rom_addr;
+	pci_read_config_dword(pdev, pdev->rom_base_reg, &rom_addr);
+	rom_addr &= ~PCI_ROM_ADDRESS_ENABLE;
+	pci_write_config_dword(pdev, pdev->rom_base_reg, rom_addr);
+}
+
+/**
+ * pci_get_rom_size - obtain the actual size of the ROM image
+ * @pdev: target PCI device
+ * @rom: kernel virtual pointer to image of ROM
+ * @size: size of PCI window
+ *  return: size of actual ROM image
+ *
+ * Determine the actual length of the ROM image.
+ * The PCI window size could be much larger than the
+ * actual image size.
+ */
+size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size)
+{
+	void __iomem *image;
+	int last_image;
+
+	image = rom;
+	do {
+		void __iomem *pds;
+		/* Standard PCI ROMs start out with these bytes 55 AA */
+		if (readb(image) != 0x55) {
+			dev_err(&pdev->dev, "Invalid ROM contents\n");
+			break;
+		}
+		if (readb(image + 1) != 0xAA)
+			break;
+		/* get the PCI data structure and check its signature */
+		pds = image + readw(image + 24);
+		if (readb(pds) != 'P')
+			break;
+		if (readb(pds + 1) != 'C')
+			break;
+		if (readb(pds + 2) != 'I')
+			break;
+		if (readb(pds + 3) != 'R')
+			break;
+		last_image = readb(pds + 21) & 0x80;
+		/* this length is reliable */
+		image += readw(pds + 16) * 512;
+	} while (!last_image);
+
+	/* never return a size larger than the PCI resource window */
+	/* there are known ROMs that get the size wrong */
+	return min((size_t)(image - rom), size);
+}
+
+/**
+ * pci_map_rom - map a PCI ROM to kernel space
+ * @pdev: pointer to pci device struct
+ * @size: pointer to receive size of pci window over ROM
+ *
+ * Return: kernel virtual pointer to image of ROM
+ *
+ * Map a PCI ROM into kernel space. If ROM is boot video ROM,
+ * the shadow BIOS copy will be returned instead of the
+ * actual ROM.
+ */
+void __iomem *pci_map_rom(struct pci_dev *pdev, size_t *size)
+{
+	struct resource *res = &pdev->resource[PCI_ROM_RESOURCE];
+	loff_t start;
+	void __iomem *rom;
+
+	/*
+	 * IORESOURCE_ROM_SHADOW set on x86, x86_64 and IA64 supports legacy
+	 * memory map if the VGA enable bit of the Bridge Control register is
+	 * set for embedded VGA.
+	 */
+	if (res->flags & IORESOURCE_ROM_SHADOW) {
+		/* primary video rom always starts here */
+		start = (loff_t)0xC0000;
+		*size = 0x20000; /* cover C000:0 through E000:0 */
+	} else {
+		if (res->flags &
+			(IORESOURCE_ROM_COPY | IORESOURCE_ROM_BIOS_COPY)) {
+			*size = pci_resource_len(pdev, PCI_ROM_RESOURCE);
+			return (void __iomem *)(unsigned long)
+				pci_resource_start(pdev, PCI_ROM_RESOURCE);
+		} else {
+			/* assign the ROM an address if it doesn't have one */
+			if (res->parent == NULL &&
+			    pci_assign_resource(pdev,PCI_ROM_RESOURCE))
+				return NULL;
+			start = pci_resource_start(pdev, PCI_ROM_RESOURCE);
+			*size = pci_resource_len(pdev, PCI_ROM_RESOURCE);
+			if (*size == 0)
+				return NULL;
+
+			/* Enable ROM space decodes */
+			if (pci_enable_rom(pdev))
+				return NULL;
+		}
+	}
+
+	rom = ioremap(start, *size);
+	if (!rom) {
+		/* restore enable if ioremap fails */
+		if (!(res->flags & (IORESOURCE_ROM_ENABLE |
+				    IORESOURCE_ROM_SHADOW |
+				    IORESOURCE_ROM_COPY)))
+			pci_disable_rom(pdev);
+		return NULL;
+	}
+
+	/*
+	 * Try to find the true size of the ROM since sometimes the PCI window
+	 * size is much larger than the actual size of the ROM.
+	 * True size is important if the ROM is going to be copied.
+	 */
+	*size = pci_get_rom_size(pdev, rom, *size);
+	return rom;
+}
+
+#if 0
+/**
+ * pci_map_rom_copy - map a PCI ROM to kernel space, create a copy
+ * @pdev: pointer to pci device struct
+ * @size: pointer to receive size of pci window over ROM
+ *
+ * Return: kernel virtual pointer to image of ROM
+ *
+ * Map a PCI ROM into kernel space. If ROM is boot video ROM,
+ * the shadow BIOS copy will be returned instead of the
+ * actual ROM.
+ */
+void __iomem *pci_map_rom_copy(struct pci_dev *pdev, size_t *size)
+{
+	struct resource *res = &pdev->resource[PCI_ROM_RESOURCE];
+	void __iomem *rom;
+
+	rom = pci_map_rom(pdev, size);
+	if (!rom)
+		return NULL;
+
+	if (res->flags & (IORESOURCE_ROM_COPY | IORESOURCE_ROM_SHADOW |
+			  IORESOURCE_ROM_BIOS_COPY))
+		return rom;
+
+	res->start = (unsigned long)kmalloc(*size, GFP_KERNEL);
+	if (!res->start)
+		return rom;
+
+	res->end = res->start + *size;
+	memcpy_fromio((void*)(unsigned long)res->start, rom, *size);
+	pci_unmap_rom(pdev, rom);
+	res->flags |= IORESOURCE_ROM_COPY;
+
+	return (void __iomem *)(unsigned long)res->start;
+}
+#endif  /*  0  */
+
+/**
+ * pci_unmap_rom - unmap the ROM from kernel space
+ * @pdev: pointer to pci device struct
+ * @rom: virtual address of the previous mapping
+ *
+ * Remove a mapping of a previously mapped ROM
+ */
+void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom)
+{
+	struct resource *res = &pdev->resource[PCI_ROM_RESOURCE];
+
+	if (res->flags & (IORESOURCE_ROM_COPY | IORESOURCE_ROM_BIOS_COPY))
+		return;
+
+	iounmap(rom);
+
+	/* Disable again before continuing, leave enabled if pci=rom */
+	if (!(res->flags & (IORESOURCE_ROM_ENABLE | IORESOURCE_ROM_SHADOW)))
+		pci_disable_rom(pdev);
+}
+
+#if 0
+/**
+ * pci_remove_rom - disable the ROM and remove its sysfs attribute
+ * @pdev: pointer to pci device struct
+ *
+ * Remove the rom file in sysfs and disable ROM decoding.
+ */
+void pci_remove_rom(struct pci_dev *pdev)
+{
+	struct resource *res = &pdev->resource[PCI_ROM_RESOURCE];
+
+	if (pci_resource_len(pdev, PCI_ROM_RESOURCE))
+		sysfs_remove_bin_file(&pdev->dev.kobj, pdev->rom_attr);
+	if (!(res->flags & (IORESOURCE_ROM_ENABLE |
+			    IORESOURCE_ROM_SHADOW |
+			    IORESOURCE_ROM_BIOS_COPY |
+			    IORESOURCE_ROM_COPY)))
+		pci_disable_rom(pdev);
+}
+#endif  /*  0  */
+
+/**
+ * pci_cleanup_rom - free the ROM copy created by pci_map_rom_copy
+ * @pdev: pointer to pci device struct
+ *
+ * Free the copied ROM if we allocated one.
+ */
+void pci_cleanup_rom(struct pci_dev *pdev)
+{
+	struct resource *res = &pdev->resource[PCI_ROM_RESOURCE];
+	if (res->flags & IORESOURCE_ROM_COPY) {
+		kfree((void*)(unsigned long)res->start);
+		res->flags &= ~IORESOURCE_ROM_COPY;
+		res->start = 0;
+		res->end = 0;
+	}
+}
+
+EXPORT_SYMBOL(pci_map_rom);
+EXPORT_SYMBOL(pci_unmap_rom);
+EXPORT_SYMBOL_GPL(pci_enable_rom);
+EXPORT_SYMBOL_GPL(pci_disable_rom);
diff --git a/drivers/pci/search.c b/drivers/pci/search.c
new file mode 100644
index 00000000..9d75dc8c
--- /dev/null
+++ b/drivers/pci/search.c
@@ -0,0 +1,359 @@
+/*
+ * 	PCI searching functions.
+ *
+ *	Copyright (C) 1993 -- 1997 Drew Eckhardt, Frederic Potter,
+ *					David Mosberger-Tang
+ *	Copyright (C) 1997 -- 2000 Martin Mares <mj@ucw.cz>
+ *	Copyright (C) 2003 -- 2004 Greg Kroah-Hartman <greg@kroah.com>
+ */
+
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include "pci.h"
+
+DECLARE_RWSEM(pci_bus_sem);
+/*
+ * find the upstream PCIe-to-PCI bridge of a PCI device
+ * if the device is PCIE, return NULL
+ * if the device isn't connected to a PCIe bridge (that is its parent is a
+ * legacy PCI bridge and the bridge is directly connected to bus 0), return its
+ * parent
+ */
+struct pci_dev *
+pci_find_upstream_pcie_bridge(struct pci_dev *pdev)
+{
+	struct pci_dev *tmp = NULL;
+
+	if (pci_is_pcie(pdev))
+		return NULL;
+	while (1) {
+		if (pci_is_root_bus(pdev->bus))
+			break;
+		pdev = pdev->bus->self;
+		/* a p2p bridge */
+		if (!pci_is_pcie(pdev)) {
+			tmp = pdev;
+			continue;
+		}
+		/* PCI device should connect to a PCIe bridge */
+		if (pdev->pcie_type != PCI_EXP_TYPE_PCI_BRIDGE) {
+			/* Busted hardware? */
+			WARN_ON_ONCE(1);
+			return NULL;
+		}
+		return pdev;
+	}
+
+	return tmp;
+}
+
+static struct pci_bus *pci_do_find_bus(struct pci_bus *bus, unsigned char busnr)
+{
+	struct pci_bus* child;
+	struct list_head *tmp;
+
+	if(bus->number == busnr)
+		return bus;
+
+	list_for_each(tmp, &bus->children) {
+		child = pci_do_find_bus(pci_bus_b(tmp), busnr);
+		if(child)
+			return child;
+	}
+	return NULL;
+}
+
+/**
+ * pci_find_bus - locate PCI bus from a given domain and bus number
+ * @domain: number of PCI domain to search
+ * @busnr: number of desired PCI bus
+ *
+ * Given a PCI bus number and domain number, the desired PCI bus is located
+ * in the global list of PCI buses.  If the bus is found, a pointer to its
+ * data structure is returned.  If no bus is found, %NULL is returned.
+ */
+struct pci_bus * pci_find_bus(int domain, int busnr)
+{
+	struct pci_bus *bus = NULL;
+	struct pci_bus *tmp_bus;
+
+	while ((bus = pci_find_next_bus(bus)) != NULL)  {
+		if (pci_domain_nr(bus) != domain)
+			continue;
+		tmp_bus = pci_do_find_bus(bus, busnr);
+		if (tmp_bus)
+			return tmp_bus;
+	}
+	return NULL;
+}
+
+/**
+ * pci_find_next_bus - begin or continue searching for a PCI bus
+ * @from: Previous PCI bus found, or %NULL for new search.
+ *
+ * Iterates through the list of known PCI busses.  A new search is
+ * initiated by passing %NULL as the @from argument.  Otherwise if
+ * @from is not %NULL, searches continue from next device on the
+ * global list.
+ */
+struct pci_bus * 
+pci_find_next_bus(const struct pci_bus *from)
+{
+	struct list_head *n;
+	struct pci_bus *b = NULL;
+
+	WARN_ON(in_interrupt());
+	down_read(&pci_bus_sem);
+	n = from ? from->node.next : pci_root_buses.next;
+	if (n != &pci_root_buses)
+		b = pci_bus_b(n);
+	up_read(&pci_bus_sem);
+	return b;
+}
+
+/**
+ * pci_get_slot - locate PCI device for a given PCI slot
+ * @bus: PCI bus on which desired PCI device resides
+ * @devfn: encodes number of PCI slot in which the desired PCI 
+ * device resides and the logical device number within that slot 
+ * in case of multi-function devices.
+ *
+ * Given a PCI bus and slot/function number, the desired PCI device 
+ * is located in the list of PCI devices.
+ * If the device is found, its reference count is increased and this
+ * function returns a pointer to its data structure.  The caller must
+ * decrement the reference count by calling pci_dev_put().
+ * If no device is found, %NULL is returned.
+ */
+struct pci_dev * pci_get_slot(struct pci_bus *bus, unsigned int devfn)
+{
+	struct list_head *tmp;
+	struct pci_dev *dev;
+
+	WARN_ON(in_interrupt());
+	down_read(&pci_bus_sem);
+
+	list_for_each(tmp, &bus->devices) {
+		dev = pci_dev_b(tmp);
+		if (dev->devfn == devfn)
+			goto out;
+	}
+
+	dev = NULL;
+ out:
+	pci_dev_get(dev);
+	up_read(&pci_bus_sem);
+	return dev;
+}
+
+/**
+ * pci_get_domain_bus_and_slot - locate PCI device for a given PCI domain (segment), bus, and slot
+ * @domain: PCI domain/segment on which the PCI device resides.
+ * @bus: PCI bus on which desired PCI device resides
+ * @devfn: encodes number of PCI slot in which the desired PCI device
+ * resides and the logical device number within that slot in case of
+ * multi-function devices.
+ *
+ * Given a PCI domain, bus, and slot/function number, the desired PCI
+ * device is located in the list of PCI devices. If the device is
+ * found, its reference count is increased and this function returns a
+ * pointer to its data structure.  The caller must decrement the
+ * reference count by calling pci_dev_put().  If no device is found,
+ * %NULL is returned.
+ */
+struct pci_dev *pci_get_domain_bus_and_slot(int domain, unsigned int bus,
+					    unsigned int devfn)
+{
+	struct pci_dev *dev = NULL;
+
+	for_each_pci_dev(dev) {
+		if (pci_domain_nr(dev->bus) == domain &&
+		    (dev->bus->number == bus && dev->devfn == devfn))
+			return dev;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(pci_get_domain_bus_and_slot);
+
+static int match_pci_dev_by_id(struct device *dev, void *data)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pci_device_id *id = data;
+
+	if (pci_match_one_device(id, pdev))
+		return 1;
+	return 0;
+}
+
+/*
+ * pci_get_dev_by_id - begin or continue searching for a PCI device by id
+ * @id: pointer to struct pci_device_id to match for the device
+ * @from: Previous PCI device found in search, or %NULL for new search.
+ *
+ * Iterates through the list of known PCI devices.  If a PCI device is found
+ * with a matching id a pointer to its device structure is returned, and the
+ * reference count to the device is incremented.  Otherwise, %NULL is returned.
+ * A new search is initiated by passing %NULL as the @from argument.  Otherwise
+ * if @from is not %NULL, searches continue from next device on the global
+ * list.  The reference count for @from is always decremented if it is not
+ * %NULL.
+ *
+ * This is an internal function for use by the other search functions in
+ * this file.
+ */
+static struct pci_dev *pci_get_dev_by_id(const struct pci_device_id *id,
+					 struct pci_dev *from)
+{
+	struct device *dev;
+	struct device *dev_start = NULL;
+	struct pci_dev *pdev = NULL;
+
+	WARN_ON(in_interrupt());
+	if (from)
+		dev_start = &from->dev;
+	dev = bus_find_device(&pci_bus_type, dev_start, (void *)id,
+			      match_pci_dev_by_id);
+	if (dev)
+		pdev = to_pci_dev(dev);
+	if (from)
+		pci_dev_put(from);
+	return pdev;
+}
+
+/**
+ * pci_get_subsys - begin or continue searching for a PCI device by vendor/subvendor/device/subdevice id
+ * @vendor: PCI vendor id to match, or %PCI_ANY_ID to match all vendor ids
+ * @device: PCI device id to match, or %PCI_ANY_ID to match all device ids
+ * @ss_vendor: PCI subsystem vendor id to match, or %PCI_ANY_ID to match all vendor ids
+ * @ss_device: PCI subsystem device id to match, or %PCI_ANY_ID to match all device ids
+ * @from: Previous PCI device found in search, or %NULL for new search.
+ *
+ * Iterates through the list of known PCI devices.  If a PCI device is found
+ * with a matching @vendor, @device, @ss_vendor and @ss_device, a pointer to its
+ * device structure is returned, and the reference count to the device is
+ * incremented.  Otherwise, %NULL is returned.  A new search is initiated by
+ * passing %NULL as the @from argument.  Otherwise if @from is not %NULL,
+ * searches continue from next device on the global list.
+ * The reference count for @from is always decremented if it is not %NULL.
+ */
+struct pci_dev *pci_get_subsys(unsigned int vendor, unsigned int device,
+			       unsigned int ss_vendor, unsigned int ss_device,
+			       struct pci_dev *from)
+{
+	struct pci_dev *pdev;
+	struct pci_device_id *id;
+
+	/*
+	 * pci_find_subsys() can be called on the ide_setup() path,
+	 * super-early in boot.  But the down_read() will enable local
+	 * interrupts, which can cause some machines to crash.  So here we
+	 * detect and flag that situation and bail out early.
+	 */
+	if (unlikely(no_pci_devices()))
+		return NULL;
+
+	id = kzalloc(sizeof(*id), GFP_KERNEL);
+	if (!id)
+		return NULL;
+	id->vendor = vendor;
+	id->device = device;
+	id->subvendor = ss_vendor;
+	id->subdevice = ss_device;
+
+	pdev = pci_get_dev_by_id(id, from);
+	kfree(id);
+
+	return pdev;
+}
+
+/**
+ * pci_get_device - begin or continue searching for a PCI device by vendor/device id
+ * @vendor: PCI vendor id to match, or %PCI_ANY_ID to match all vendor ids
+ * @device: PCI device id to match, or %PCI_ANY_ID to match all device ids
+ * @from: Previous PCI device found in search, or %NULL for new search.
+ *
+ * Iterates through the list of known PCI devices.  If a PCI device is
+ * found with a matching @vendor and @device, the reference count to the
+ * device is incremented and a pointer to its device structure is returned.
+ * Otherwise, %NULL is returned.  A new search is initiated by passing %NULL
+ * as the @from argument.  Otherwise if @from is not %NULL, searches continue
+ * from next device on the global list.  The reference count for @from is
+ * always decremented if it is not %NULL.
+ */
+struct pci_dev *
+pci_get_device(unsigned int vendor, unsigned int device, struct pci_dev *from)
+{
+	return pci_get_subsys(vendor, device, PCI_ANY_ID, PCI_ANY_ID, from);
+}
+
+/**
+ * pci_get_class - begin or continue searching for a PCI device by class
+ * @class: search for a PCI device with this class designation
+ * @from: Previous PCI device found in search, or %NULL for new search.
+ *
+ * Iterates through the list of known PCI devices.  If a PCI device is
+ * found with a matching @class, the reference count to the device is
+ * incremented and a pointer to its device structure is returned.
+ * Otherwise, %NULL is returned.
+ * A new search is initiated by passing %NULL as the @from argument.
+ * Otherwise if @from is not %NULL, searches continue from next device
+ * on the global list.  The reference count for @from is always decremented
+ * if it is not %NULL.
+ */
+struct pci_dev *pci_get_class(unsigned int class, struct pci_dev *from)
+{
+	struct pci_dev *dev;
+	struct pci_device_id *id;
+
+	id = kzalloc(sizeof(*id), GFP_KERNEL);
+	if (!id)
+		return NULL;
+	id->vendor = id->device = id->subvendor = id->subdevice = PCI_ANY_ID;
+	id->class_mask = PCI_ANY_ID;
+	id->class = class;
+
+	dev = pci_get_dev_by_id(id, from);
+	kfree(id);
+	return dev;
+}
+
+/**
+ * pci_dev_present - Returns 1 if device matching the device list is present, 0 if not.
+ * @ids: A pointer to a null terminated list of struct pci_device_id structures
+ * that describe the type of PCI device the caller is trying to find.
+ *
+ * Obvious fact: You do not have a reference to any device that might be found
+ * by this function, so if that device is removed from the system right after
+ * this function is finished, the value will be stale.  Use this function to
+ * find devices that are usually built into a system, or for a general hint as
+ * to if another device happens to be present at this specific moment in time.
+ */
+int pci_dev_present(const struct pci_device_id *ids)
+{
+	struct pci_dev *found = NULL;
+
+	WARN_ON(in_interrupt());
+	while (ids->vendor || ids->subvendor || ids->class_mask) {
+		found = pci_get_dev_by_id(ids, NULL);
+		if (found)
+			goto exit;
+		ids++;
+	}
+exit:
+	if (found)
+		return 1;
+	return 0;
+}
+EXPORT_SYMBOL(pci_dev_present);
+
+/* For boot time work */
+EXPORT_SYMBOL(pci_find_bus);
+EXPORT_SYMBOL(pci_find_next_bus);
+/* For everyone */
+EXPORT_SYMBOL(pci_get_device);
+EXPORT_SYMBOL(pci_get_subsys);
+EXPORT_SYMBOL(pci_get_slot);
+EXPORT_SYMBOL(pci_get_class);
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
new file mode 100644
index 00000000..9995842e
--- /dev/null
+++ b/drivers/pci/setup-bus.c
@@ -0,0 +1,1206 @@
+/*
+ *	drivers/pci/setup-bus.c
+ *
+ * Extruded from code written by
+ *      Dave Rusling (david.rusling@reo.mts.dec.com)
+ *      David Mosberger (davidm@cs.arizona.edu)
+ *	David Miller (davem@redhat.com)
+ *
+ * Support routines for initializing a PCI subsystem.
+ */
+
+/*
+ * Nov 2000, Ivan Kokshaysky <ink@jurassic.park.msu.ru>
+ *	     PCI-PCI bridges cleanup, sorted resource allocation.
+ * Feb 2002, Ivan Kokshaysky <ink@jurassic.park.msu.ru>
+ *	     Converted to allocation in 3 passes, which gives
+ *	     tighter packing. Prefetchable range support.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/errno.h>
+#include <linux/ioport.h>
+#include <linux/cache.h>
+#include <linux/slab.h>
+#include "pci.h"
+
+struct resource_list_x {
+	struct resource_list_x *next;
+	struct resource *res;
+	struct pci_dev *dev;
+	resource_size_t start;
+	resource_size_t end;
+	resource_size_t add_size;
+	unsigned long flags;
+};
+
+#define free_list(type, head) do {                      \
+	struct type *list, *tmp;			\
+	for (list = (head)->next; list;) {		\
+		tmp = list;				\
+		list = list->next;			\
+		kfree(tmp);				\
+	}						\
+	(head)->next = NULL;				\
+} while (0)
+
+int pci_realloc_enable = 0;
+#define pci_realloc_enabled() pci_realloc_enable
+void pci_realloc(void)
+{
+	pci_realloc_enable = 1;
+}
+
+/**
+ * add_to_list() - add a new resource tracker to the list
+ * @head:	Head of the list
+ * @dev:	device corresponding to which the resource
+ *		belongs
+ * @res:	The resource to be tracked
+ * @add_size:	additional size to be optionally added
+ *              to the resource
+ */
+static void add_to_list(struct resource_list_x *head,
+		 struct pci_dev *dev, struct resource *res,
+		 resource_size_t add_size)
+{
+	struct resource_list_x *list = head;
+	struct resource_list_x *ln = list->next;
+	struct resource_list_x *tmp;
+
+	tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp) {
+		pr_warning("add_to_list: kmalloc() failed!\n");
+		return;
+	}
+
+	tmp->next = ln;
+	tmp->res = res;
+	tmp->dev = dev;
+	tmp->start = res->start;
+	tmp->end = res->end;
+	tmp->flags = res->flags;
+	tmp->add_size = add_size;
+	list->next = tmp;
+}
+
+static void add_to_failed_list(struct resource_list_x *head,
+				struct pci_dev *dev, struct resource *res)
+{
+	add_to_list(head, dev, res, 0);
+}
+
+static void __dev_sort_resources(struct pci_dev *dev,
+				 struct resource_list *head)
+{
+	u16 class = dev->class >> 8;
+
+	/* Don't touch classless devices or host bridges or ioapics.  */
+	if (class == PCI_CLASS_NOT_DEFINED || class == PCI_CLASS_BRIDGE_HOST)
+		return;
+
+	/* Don't touch ioapic devices already enabled by firmware */
+	if (class == PCI_CLASS_SYSTEM_PIC) {
+		u16 command;
+		pci_read_config_word(dev, PCI_COMMAND, &command);
+		if (command & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY))
+			return;
+	}
+
+	pdev_sort_resources(dev, head);
+}
+
+static inline void reset_resource(struct resource *res)
+{
+	res->start = 0;
+	res->end = 0;
+	res->flags = 0;
+}
+
+/**
+ * adjust_resources_sorted() - satisfy any additional resource requests
+ *
+ * @add_head : head of the list tracking requests requiring additional
+ *             resources
+ * @head     : head of the list tracking requests with allocated
+ *             resources
+ *
+ * Walk through each element of the add_head and try to procure
+ * additional resources for the element, provided the element
+ * is in the head list.
+ */
+static void adjust_resources_sorted(struct resource_list_x *add_head,
+		struct resource_list *head)
+{
+	struct resource *res;
+	struct resource_list_x *list, *tmp, *prev;
+	struct resource_list *hlist;
+	resource_size_t add_size;
+	int idx;
+
+	prev = add_head;
+	for (list = add_head->next; list;) {
+		res = list->res;
+		/* skip resource that has been reset */
+		if (!res->flags)
+			goto out;
+
+		/* skip this resource if not found in head list */
+		for (hlist = head->next; hlist && hlist->res != res;
+				hlist = hlist->next);
+		if (!hlist) { /* just skip */
+			prev = list;
+			list = list->next;
+			continue;
+		}
+
+		idx = res - &list->dev->resource[0];
+		add_size=list->add_size;
+		if (!resource_size(res) && add_size) {
+			 res->end = res->start + add_size - 1;
+			 if(pci_assign_resource(list->dev, idx))
+				reset_resource(res);
+		} else if (add_size) {
+			adjust_resource(res, res->start,
+				resource_size(res) + add_size);
+		}
+out:
+		tmp = list;
+		prev->next = list = list->next;
+		kfree(tmp);
+	}
+}
+
+/**
+ * assign_requested_resources_sorted() - satisfy resource requests
+ *
+ * @head : head of the list tracking requests for resources
+ * @failed_list : head of the list tracking requests that could
+ *		not be allocated
+ *
+ * Satisfy resource requests of each element in the list. Add
+ * requests that could not satisfied to the failed_list.
+ */
+static void assign_requested_resources_sorted(struct resource_list *head,
+				 struct resource_list_x *fail_head)
+{
+	struct resource *res;
+	struct resource_list *list;
+	int idx;
+
+	for (list = head->next; list; list = list->next) {
+		res = list->res;
+		idx = res - &list->dev->resource[0];
+		if (resource_size(res) && pci_assign_resource(list->dev, idx)) {
+			if (fail_head && !pci_is_root_bus(list->dev->bus)) {
+				/*
+				 * if the failed res is for ROM BAR, and it will
+				 * be enabled later, don't add it to the list
+				 */
+				if (!((idx == PCI_ROM_RESOURCE) &&
+				      (!(res->flags & IORESOURCE_ROM_ENABLE))))
+					add_to_failed_list(fail_head, list->dev, res);
+			}
+			reset_resource(res);
+		}
+	}
+}
+
+static void __assign_resources_sorted(struct resource_list *head,
+				 struct resource_list_x *add_head,
+				 struct resource_list_x *fail_head)
+{
+	/* Satisfy the must-have resource requests */
+	assign_requested_resources_sorted(head, fail_head);
+
+	/* Try to satisfy any additional nice-to-have resource
+		requests */
+	if (add_head)
+		adjust_resources_sorted(add_head, head);
+	free_list(resource_list, head);
+}
+
+static void pdev_assign_resources_sorted(struct pci_dev *dev,
+				 struct resource_list_x *fail_head)
+{
+	struct resource_list head;
+
+	head.next = NULL;
+	__dev_sort_resources(dev, &head);
+	__assign_resources_sorted(&head, NULL, fail_head);
+
+}
+
+static void pbus_assign_resources_sorted(const struct pci_bus *bus,
+					 struct resource_list_x *add_head,
+					 struct resource_list_x *fail_head)
+{
+	struct pci_dev *dev;
+	struct resource_list head;
+
+	head.next = NULL;
+	list_for_each_entry(dev, &bus->devices, bus_list)
+		__dev_sort_resources(dev, &head);
+
+	__assign_resources_sorted(&head, add_head, fail_head);
+}
+
+void pci_setup_cardbus(struct pci_bus *bus)
+{
+	struct pci_dev *bridge = bus->self;
+	struct resource *res;
+	struct pci_bus_region region;
+
+	dev_info(&bridge->dev, "CardBus bridge to [bus %02x-%02x]\n",
+		 bus->secondary, bus->subordinate);
+
+	res = bus->resource[0];
+	pcibios_resource_to_bus(bridge, &region, res);
+	if (res->flags & IORESOURCE_IO) {
+		/*
+		 * The IO resource is allocated a range twice as large as it
+		 * would normally need.  This allows us to set both IO regs.
+		 */
+		dev_info(&bridge->dev, "  bridge window %pR\n", res);
+		pci_write_config_dword(bridge, PCI_CB_IO_BASE_0,
+					region.start);
+		pci_write_config_dword(bridge, PCI_CB_IO_LIMIT_0,
+					region.end);
+	}
+
+	res = bus->resource[1];
+	pcibios_resource_to_bus(bridge, &region, res);
+	if (res->flags & IORESOURCE_IO) {
+		dev_info(&bridge->dev, "  bridge window %pR\n", res);
+		pci_write_config_dword(bridge, PCI_CB_IO_BASE_1,
+					region.start);
+		pci_write_config_dword(bridge, PCI_CB_IO_LIMIT_1,
+					region.end);
+	}
+
+	res = bus->resource[2];
+	pcibios_resource_to_bus(bridge, &region, res);
+	if (res->flags & IORESOURCE_MEM) {
+		dev_info(&bridge->dev, "  bridge window %pR\n", res);
+		pci_write_config_dword(bridge, PCI_CB_MEMORY_BASE_0,
+					region.start);
+		pci_write_config_dword(bridge, PCI_CB_MEMORY_LIMIT_0,
+					region.end);
+	}
+
+	res = bus->resource[3];
+	pcibios_resource_to_bus(bridge, &region, res);
+	if (res->flags & IORESOURCE_MEM) {
+		dev_info(&bridge->dev, "  bridge window %pR\n", res);
+		pci_write_config_dword(bridge, PCI_CB_MEMORY_BASE_1,
+					region.start);
+		pci_write_config_dword(bridge, PCI_CB_MEMORY_LIMIT_1,
+					region.end);
+	}
+}
+EXPORT_SYMBOL(pci_setup_cardbus);
+
+/* Initialize bridges with base/limit values we have collected.
+   PCI-to-PCI Bridge Architecture Specification rev. 1.1 (1998)
+   requires that if there is no I/O ports or memory behind the
+   bridge, corresponding range must be turned off by writing base
+   value greater than limit to the bridge's base/limit registers.
+
+   Note: care must be taken when updating I/O base/limit registers
+   of bridges which support 32-bit I/O. This update requires two
+   config space writes, so it's quite possible that an I/O window of
+   the bridge will have some undesirable address (e.g. 0) after the
+   first write. Ditto 64-bit prefetchable MMIO.  */
+static void pci_setup_bridge_io(struct pci_bus *bus)
+{
+	struct pci_dev *bridge = bus->self;
+	struct resource *res;
+	struct pci_bus_region region;
+	u32 l, io_upper16;
+
+	/* Set up the top and bottom of the PCI I/O segment for this bus. */
+	res = bus->resource[0];
+	pcibios_resource_to_bus(bridge, &region, res);
+	if (res->flags & IORESOURCE_IO) {
+		pci_read_config_dword(bridge, PCI_IO_BASE, &l);
+		l &= 0xffff0000;
+		l |= (region.start >> 8) & 0x00f0;
+		l |= region.end & 0xf000;
+		/* Set up upper 16 bits of I/O base/limit. */
+		io_upper16 = (region.end & 0xffff0000) | (region.start >> 16);
+		dev_info(&bridge->dev, "  bridge window %pR\n", res);
+	} else {
+		/* Clear upper 16 bits of I/O base/limit. */
+		io_upper16 = 0;
+		l = 0x00f0;
+		dev_info(&bridge->dev, "  bridge window [io  disabled]\n");
+	}
+	/* Temporarily disable the I/O range before updating PCI_IO_BASE. */
+	pci_write_config_dword(bridge, PCI_IO_BASE_UPPER16, 0x0000ffff);
+	/* Update lower 16 bits of I/O base/limit. */
+	pci_write_config_dword(bridge, PCI_IO_BASE, l);
+	/* Update upper 16 bits of I/O base/limit. */
+	pci_write_config_dword(bridge, PCI_IO_BASE_UPPER16, io_upper16);
+}
+
+static void pci_setup_bridge_mmio(struct pci_bus *bus)
+{
+	struct pci_dev *bridge = bus->self;
+	struct resource *res;
+	struct pci_bus_region region;
+	u32 l;
+
+	/* Set up the top and bottom of the PCI Memory segment for this bus. */
+	res = bus->resource[1];
+	pcibios_resource_to_bus(bridge, &region, res);
+	if (res->flags & IORESOURCE_MEM) {
+		l = (region.start >> 16) & 0xfff0;
+		l |= region.end & 0xfff00000;
+		dev_info(&bridge->dev, "  bridge window %pR\n", res);
+	} else {
+		l = 0x0000fff0;
+		dev_info(&bridge->dev, "  bridge window [mem disabled]\n");
+	}
+	pci_write_config_dword(bridge, PCI_MEMORY_BASE, l);
+}
+
+static void pci_setup_bridge_mmio_pref(struct pci_bus *bus)
+{
+	struct pci_dev *bridge = bus->self;
+	struct resource *res;
+	struct pci_bus_region region;
+	u32 l, bu, lu;
+
+	/* Clear out the upper 32 bits of PREF limit.
+	   If PCI_PREF_BASE_UPPER32 was non-zero, this temporarily
+	   disables PREF range, which is ok. */
+	pci_write_config_dword(bridge, PCI_PREF_LIMIT_UPPER32, 0);
+
+	/* Set up PREF base/limit. */
+	bu = lu = 0;
+	res = bus->resource[2];
+	pcibios_resource_to_bus(bridge, &region, res);
+	if (res->flags & IORESOURCE_PREFETCH) {
+		l = (region.start >> 16) & 0xfff0;
+		l |= region.end & 0xfff00000;
+		if (res->flags & IORESOURCE_MEM_64) {
+			bu = upper_32_bits(region.start);
+			lu = upper_32_bits(region.end);
+		}
+		dev_info(&bridge->dev, "  bridge window %pR\n", res);
+	} else {
+		l = 0x0000fff0;
+		dev_info(&bridge->dev, "  bridge window [mem pref disabled]\n");
+	}
+	pci_write_config_dword(bridge, PCI_PREF_MEMORY_BASE, l);
+
+	/* Set the upper 32 bits of PREF base & limit. */
+	pci_write_config_dword(bridge, PCI_PREF_BASE_UPPER32, bu);
+	pci_write_config_dword(bridge, PCI_PREF_LIMIT_UPPER32, lu);
+}
+
+static void __pci_setup_bridge(struct pci_bus *bus, unsigned long type)
+{
+	struct pci_dev *bridge = bus->self;
+
+	dev_info(&bridge->dev, "PCI bridge to [bus %02x-%02x]\n",
+		 bus->secondary, bus->subordinate);
+
+	if (type & IORESOURCE_IO)
+		pci_setup_bridge_io(bus);
+
+	if (type & IORESOURCE_MEM)
+		pci_setup_bridge_mmio(bus);
+
+	if (type & IORESOURCE_PREFETCH)
+		pci_setup_bridge_mmio_pref(bus);
+
+	pci_write_config_word(bridge, PCI_BRIDGE_CONTROL, bus->bridge_ctl);
+}
+
+static void pci_setup_bridge(struct pci_bus *bus)
+{
+	unsigned long type = IORESOURCE_IO | IORESOURCE_MEM |
+				  IORESOURCE_PREFETCH;
+
+	__pci_setup_bridge(bus, type);
+}
+
+/* Check whether the bridge supports optional I/O and
+   prefetchable memory ranges. If not, the respective
+   base/limit registers must be read-only and read as 0. */
+static void pci_bridge_check_ranges(struct pci_bus *bus)
+{
+	u16 io;
+	u32 pmem;
+	struct pci_dev *bridge = bus->self;
+	struct resource *b_res;
+
+	b_res = &bridge->resource[PCI_BRIDGE_RESOURCES];
+	b_res[1].flags |= IORESOURCE_MEM;
+
+	pci_read_config_word(bridge, PCI_IO_BASE, &io);
+	if (!io) {
+		pci_write_config_word(bridge, PCI_IO_BASE, 0xf0f0);
+		pci_read_config_word(bridge, PCI_IO_BASE, &io);
+ 		pci_write_config_word(bridge, PCI_IO_BASE, 0x0);
+ 	}
+ 	if (io)
+		b_res[0].flags |= IORESOURCE_IO;
+	/*  DECchip 21050 pass 2 errata: the bridge may miss an address
+	    disconnect boundary by one PCI data phase.
+	    Workaround: do not use prefetching on this device. */
+	if (bridge->vendor == PCI_VENDOR_ID_DEC && bridge->device == 0x0001)
+		return;
+	pci_read_config_dword(bridge, PCI_PREF_MEMORY_BASE, &pmem);
+	if (!pmem) {
+		pci_write_config_dword(bridge, PCI_PREF_MEMORY_BASE,
+					       0xfff0fff0);
+		pci_read_config_dword(bridge, PCI_PREF_MEMORY_BASE, &pmem);
+		pci_write_config_dword(bridge, PCI_PREF_MEMORY_BASE, 0x0);
+	}
+	if (pmem) {
+		b_res[2].flags |= IORESOURCE_MEM | IORESOURCE_PREFETCH;
+		if ((pmem & PCI_PREF_RANGE_TYPE_MASK) ==
+		    PCI_PREF_RANGE_TYPE_64) {
+			b_res[2].flags |= IORESOURCE_MEM_64;
+			b_res[2].flags |= PCI_PREF_RANGE_TYPE_64;
+		}
+	}
+
+	/* double check if bridge does support 64 bit pref */
+	if (b_res[2].flags & IORESOURCE_MEM_64) {
+		u32 mem_base_hi, tmp;
+		pci_read_config_dword(bridge, PCI_PREF_BASE_UPPER32,
+					 &mem_base_hi);
+		pci_write_config_dword(bridge, PCI_PREF_BASE_UPPER32,
+					       0xffffffff);
+		pci_read_config_dword(bridge, PCI_PREF_BASE_UPPER32, &tmp);
+		if (!tmp)
+			b_res[2].flags &= ~IORESOURCE_MEM_64;
+		pci_write_config_dword(bridge, PCI_PREF_BASE_UPPER32,
+				       mem_base_hi);
+	}
+}
+
+/* Helper function for sizing routines: find first available
+   bus resource of a given type. Note: we intentionally skip
+   the bus resources which have already been assigned (that is,
+   have non-NULL parent resource). */
+static struct resource *find_free_bus_resource(struct pci_bus *bus, unsigned long type)
+{
+	int i;
+	struct resource *r;
+	unsigned long type_mask = IORESOURCE_IO | IORESOURCE_MEM |
+				  IORESOURCE_PREFETCH;
+
+	pci_bus_for_each_resource(bus, r, i) {
+		if (r == &ioport_resource || r == &iomem_resource)
+			continue;
+		if (r && (r->flags & type_mask) == type && !r->parent)
+			return r;
+	}
+	return NULL;
+}
+
+static resource_size_t calculate_iosize(resource_size_t size,
+		resource_size_t min_size,
+		resource_size_t size1,
+		resource_size_t old_size,
+		resource_size_t align)
+{
+	if (size < min_size)
+		size = min_size;
+	if (old_size == 1 )
+		old_size = 0;
+	/* To be fixed in 2.5: we should have sort of HAVE_ISA
+	   flag in the struct pci_bus. */
+#if defined(CONFIG_ISA) || defined(CONFIG_EISA)
+	size = (size & 0xff) + ((size & ~0xffUL) << 2);
+#endif
+	size = ALIGN(size + size1, align);
+	if (size < old_size)
+		size = old_size;
+	return size;
+}
+
+static resource_size_t calculate_memsize(resource_size_t size,
+		resource_size_t min_size,
+		resource_size_t size1,
+		resource_size_t old_size,
+		resource_size_t align)
+{
+	if (size < min_size)
+		size = min_size;
+	if (old_size == 1 )
+		old_size = 0;
+	if (size < old_size)
+		size = old_size;
+	size = ALIGN(size + size1, align);
+	return size;
+}
+
+/**
+ * pbus_size_io() - size the io window of a given bus
+ *
+ * @bus : the bus
+ * @min_size : the minimum io window that must to be allocated
+ * @add_size : additional optional io window
+ * @add_head : track the additional io window on this list
+ *
+ * Sizing the IO windows of the PCI-PCI bridge is trivial,
+ * since these windows have 4K granularity and the IO ranges
+ * of non-bridge PCI devices are limited to 256 bytes.
+ * We must be careful with the ISA aliasing though.
+ */
+static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size,
+		resource_size_t add_size, struct resource_list_x *add_head)
+{
+	struct pci_dev *dev;
+	struct resource *b_res = find_free_bus_resource(bus, IORESOURCE_IO);
+	unsigned long size = 0, size0 = 0, size1 = 0;
+
+	if (!b_res)
+ 		return;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		int i;
+
+		for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+			struct resource *r = &dev->resource[i];
+			unsigned long r_size;
+
+			if (r->parent || !(r->flags & IORESOURCE_IO))
+				continue;
+			r_size = resource_size(r);
+
+			if (r_size < 0x400)
+				/* Might be re-aligned for ISA */
+				size += r_size;
+			else
+				size1 += r_size;
+		}
+	}
+	size0 = calculate_iosize(size, min_size, size1,
+			resource_size(b_res), 4096);
+	size1 = (!add_head || (add_head && !add_size)) ? size0 :
+		calculate_iosize(size, min_size+add_size, size1,
+			resource_size(b_res), 4096);
+	if (!size0 && !size1) {
+		if (b_res->start || b_res->end)
+			dev_info(&bus->self->dev, "disabling bridge window "
+				 "%pR to [bus %02x-%02x] (unused)\n", b_res,
+				 bus->secondary, bus->subordinate);
+		b_res->flags = 0;
+		return;
+	}
+	/* Alignment of the IO window is always 4K */
+	b_res->start = 4096;
+	b_res->end = b_res->start + size0 - 1;
+	b_res->flags |= IORESOURCE_STARTALIGN;
+	if (size1 > size0 && add_head)
+		add_to_list(add_head, bus->self, b_res, size1-size0);
+}
+
+/**
+ * pbus_size_mem() - size the memory window of a given bus
+ *
+ * @bus : the bus
+ * @min_size : the minimum memory window that must to be allocated
+ * @add_size : additional optional memory window
+ * @add_head : track the additional memory window on this list
+ *
+ * Calculate the size of the bus and minimal alignment which
+ * guarantees that all child resources fit in this size.
+ */
+static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
+			 unsigned long type, resource_size_t min_size,
+			resource_size_t add_size,
+			struct resource_list_x *add_head)
+{
+	struct pci_dev *dev;
+	resource_size_t min_align, align, size, size0, size1;
+	resource_size_t aligns[12];	/* Alignments from 1Mb to 2Gb */
+	int order, max_order;
+	struct resource *b_res = find_free_bus_resource(bus, type);
+	unsigned int mem64_mask = 0;
+
+	if (!b_res)
+		return 0;
+
+	memset(aligns, 0, sizeof(aligns));
+	max_order = 0;
+	size = 0;
+
+	mem64_mask = b_res->flags & IORESOURCE_MEM_64;
+	b_res->flags &= ~IORESOURCE_MEM_64;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		int i;
+
+		for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+			struct resource *r = &dev->resource[i];
+			resource_size_t r_size;
+
+			if (r->parent || (r->flags & mask) != type)
+				continue;
+			r_size = resource_size(r);
+			/* For bridges size != alignment */
+			align = pci_resource_alignment(dev, r);
+			order = __ffs(align) - 20;
+			if (order > 11) {
+				dev_warn(&dev->dev, "disabling BAR %d: %pR "
+					 "(bad alignment %#llx)\n", i, r,
+					 (unsigned long long) align);
+				r->flags = 0;
+				continue;
+			}
+			size += r_size;
+			if (order < 0)
+				order = 0;
+			/* Exclude ranges with size > align from
+			   calculation of the alignment. */
+			if (r_size == align)
+				aligns[order] += align;
+			if (order > max_order)
+				max_order = order;
+			mem64_mask &= r->flags & IORESOURCE_MEM_64;
+		}
+	}
+	align = 0;
+	min_align = 0;
+	for (order = 0; order <= max_order; order++) {
+		resource_size_t align1 = 1;
+
+		align1 <<= (order + 20);
+
+		if (!align)
+			min_align = align1;
+		else if (ALIGN(align + min_align, min_align) < align1)
+			min_align = align1 >> 1;
+		align += aligns[order];
+	}
+	size0 = calculate_memsize(size, min_size, 0, resource_size(b_res), min_align);
+	size1 = (!add_head || (add_head && !add_size)) ? size0 :
+		calculate_memsize(size, min_size+add_size, 0,
+				resource_size(b_res), min_align);
+	if (!size0 && !size1) {
+		if (b_res->start || b_res->end)
+			dev_info(&bus->self->dev, "disabling bridge window "
+				 "%pR to [bus %02x-%02x] (unused)\n", b_res,
+				 bus->secondary, bus->subordinate);
+		b_res->flags = 0;
+		return 1;
+	}
+	b_res->start = min_align;
+	b_res->end = size0 + min_align - 1;
+	b_res->flags |= IORESOURCE_STARTALIGN | mem64_mask;
+	if (size1 > size0 && add_head)
+		add_to_list(add_head, bus->self, b_res, size1-size0);
+	return 1;
+}
+
+static void pci_bus_size_cardbus(struct pci_bus *bus)
+{
+	struct pci_dev *bridge = bus->self;
+	struct resource *b_res = &bridge->resource[PCI_BRIDGE_RESOURCES];
+	u16 ctrl;
+
+	/*
+	 * Reserve some resources for CardBus.  We reserve
+	 * a fixed amount of bus space for CardBus bridges.
+	 */
+	b_res[0].start = 0;
+	b_res[0].end = pci_cardbus_io_size - 1;
+	b_res[0].flags |= IORESOURCE_IO | IORESOURCE_SIZEALIGN;
+
+	b_res[1].start = 0;
+	b_res[1].end = pci_cardbus_io_size - 1;
+	b_res[1].flags |= IORESOURCE_IO | IORESOURCE_SIZEALIGN;
+
+	/*
+	 * Check whether prefetchable memory is supported
+	 * by this bridge.
+	 */
+	pci_read_config_word(bridge, PCI_CB_BRIDGE_CONTROL, &ctrl);
+	if (!(ctrl & PCI_CB_BRIDGE_CTL_PREFETCH_MEM0)) {
+		ctrl |= PCI_CB_BRIDGE_CTL_PREFETCH_MEM0;
+		pci_write_config_word(bridge, PCI_CB_BRIDGE_CONTROL, ctrl);
+		pci_read_config_word(bridge, PCI_CB_BRIDGE_CONTROL, &ctrl);
+	}
+
+	/*
+	 * If we have prefetchable memory support, allocate
+	 * two regions.  Otherwise, allocate one region of
+	 * twice the size.
+	 */
+	if (ctrl & PCI_CB_BRIDGE_CTL_PREFETCH_MEM0) {
+		b_res[2].start = 0;
+		b_res[2].end = pci_cardbus_mem_size - 1;
+		b_res[2].flags |= IORESOURCE_MEM | IORESOURCE_PREFETCH | IORESOURCE_SIZEALIGN;
+
+		b_res[3].start = 0;
+		b_res[3].end = pci_cardbus_mem_size - 1;
+		b_res[3].flags |= IORESOURCE_MEM | IORESOURCE_SIZEALIGN;
+	} else {
+		b_res[3].start = 0;
+		b_res[3].end = pci_cardbus_mem_size * 2 - 1;
+		b_res[3].flags |= IORESOURCE_MEM | IORESOURCE_SIZEALIGN;
+	}
+}
+
+void __ref __pci_bus_size_bridges(struct pci_bus *bus,
+			struct resource_list_x *add_head)
+{
+	struct pci_dev *dev;
+	unsigned long mask, prefmask;
+	resource_size_t additional_mem_size = 0, additional_io_size = 0;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		struct pci_bus *b = dev->subordinate;
+		if (!b)
+			continue;
+
+		switch (dev->class >> 8) {
+		case PCI_CLASS_BRIDGE_CARDBUS:
+			pci_bus_size_cardbus(b);
+			break;
+
+		case PCI_CLASS_BRIDGE_PCI:
+		default:
+			__pci_bus_size_bridges(b, add_head);
+			break;
+		}
+	}
+
+	/* The root bus? */
+	if (!bus->self)
+		return;
+
+	switch (bus->self->class >> 8) {
+	case PCI_CLASS_BRIDGE_CARDBUS:
+		/* don't size cardbuses yet. */
+		break;
+
+	case PCI_CLASS_BRIDGE_PCI:
+		pci_bridge_check_ranges(bus);
+		if (bus->self->is_hotplug_bridge) {
+			additional_io_size  = pci_hotplug_io_size;
+			additional_mem_size = pci_hotplug_mem_size;
+		}
+		/*
+		 * Follow thru
+		 */
+	default:
+		pbus_size_io(bus, 0, additional_io_size, add_head);
+		/* If the bridge supports prefetchable range, size it
+		   separately. If it doesn't, or its prefetchable window
+		   has already been allocated by arch code, try
+		   non-prefetchable range for both types of PCI memory
+		   resources. */
+		mask = IORESOURCE_MEM;
+		prefmask = IORESOURCE_MEM | IORESOURCE_PREFETCH;
+		if (pbus_size_mem(bus, prefmask, prefmask, 0, additional_mem_size, add_head))
+			mask = prefmask; /* Success, size non-prefetch only. */
+		else
+			additional_mem_size += additional_mem_size;
+		pbus_size_mem(bus, mask, IORESOURCE_MEM, 0, additional_mem_size, add_head);
+		break;
+	}
+}
+
+void __ref pci_bus_size_bridges(struct pci_bus *bus)
+{
+	__pci_bus_size_bridges(bus, NULL);
+}
+EXPORT_SYMBOL(pci_bus_size_bridges);
+
+static void __ref __pci_bus_assign_resources(const struct pci_bus *bus,
+					 struct resource_list_x *add_head,
+					 struct resource_list_x *fail_head)
+{
+	struct pci_bus *b;
+	struct pci_dev *dev;
+
+	pbus_assign_resources_sorted(bus, add_head, fail_head);
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		b = dev->subordinate;
+		if (!b)
+			continue;
+
+		__pci_bus_assign_resources(b, add_head, fail_head);
+
+		switch (dev->class >> 8) {
+		case PCI_CLASS_BRIDGE_PCI:
+			if (!pci_is_enabled(dev))
+				pci_setup_bridge(b);
+			break;
+
+		case PCI_CLASS_BRIDGE_CARDBUS:
+			pci_setup_cardbus(b);
+			break;
+
+		default:
+			dev_info(&dev->dev, "not setting up bridge for bus "
+				 "%04x:%02x\n", pci_domain_nr(b), b->number);
+			break;
+		}
+	}
+}
+
+void __ref pci_bus_assign_resources(const struct pci_bus *bus)
+{
+	__pci_bus_assign_resources(bus, NULL, NULL);
+}
+EXPORT_SYMBOL(pci_bus_assign_resources);
+
+static void __ref __pci_bridge_assign_resources(const struct pci_dev *bridge,
+					 struct resource_list_x *fail_head)
+{
+	struct pci_bus *b;
+
+	pdev_assign_resources_sorted((struct pci_dev *)bridge, fail_head);
+
+	b = bridge->subordinate;
+	if (!b)
+		return;
+
+	__pci_bus_assign_resources(b, NULL, fail_head);
+
+	switch (bridge->class >> 8) {
+	case PCI_CLASS_BRIDGE_PCI:
+		pci_setup_bridge(b);
+		break;
+
+	case PCI_CLASS_BRIDGE_CARDBUS:
+		pci_setup_cardbus(b);
+		break;
+
+	default:
+		dev_info(&bridge->dev, "not setting up bridge for bus "
+			 "%04x:%02x\n", pci_domain_nr(b), b->number);
+		break;
+	}
+}
+static void pci_bridge_release_resources(struct pci_bus *bus,
+					  unsigned long type)
+{
+	int idx;
+	bool changed = false;
+	struct pci_dev *dev;
+	struct resource *r;
+	unsigned long type_mask = IORESOURCE_IO | IORESOURCE_MEM |
+				  IORESOURCE_PREFETCH;
+
+	dev = bus->self;
+	for (idx = PCI_BRIDGE_RESOURCES; idx <= PCI_BRIDGE_RESOURCE_END;
+	     idx++) {
+		r = &dev->resource[idx];
+		if ((r->flags & type_mask) != type)
+			continue;
+		if (!r->parent)
+			continue;
+		/*
+		 * if there are children under that, we should release them
+		 *  all
+		 */
+		release_child_resources(r);
+		if (!release_resource(r)) {
+			dev_printk(KERN_DEBUG, &dev->dev,
+				 "resource %d %pR released\n", idx, r);
+			/* keep the old size */
+			r->end = resource_size(r) - 1;
+			r->start = 0;
+			r->flags = 0;
+			changed = true;
+		}
+	}
+
+	if (changed) {
+		/* avoiding touch the one without PREF */
+		if (type & IORESOURCE_PREFETCH)
+			type = IORESOURCE_PREFETCH;
+		__pci_setup_bridge(bus, type);
+	}
+}
+
+enum release_type {
+	leaf_only,
+	whole_subtree,
+};
+/*
+ * try to release pci bridge resources that is from leaf bridge,
+ * so we can allocate big new one later
+ */
+static void __ref pci_bus_release_bridge_resources(struct pci_bus *bus,
+						   unsigned long type,
+						   enum release_type rel_type)
+{
+	struct pci_dev *dev;
+	bool is_leaf_bridge = true;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		struct pci_bus *b = dev->subordinate;
+		if (!b)
+			continue;
+
+		is_leaf_bridge = false;
+
+		if ((dev->class >> 8) != PCI_CLASS_BRIDGE_PCI)
+			continue;
+
+		if (rel_type == whole_subtree)
+			pci_bus_release_bridge_resources(b, type,
+						 whole_subtree);
+	}
+
+	if (pci_is_root_bus(bus))
+		return;
+
+	if ((bus->self->class >> 8) != PCI_CLASS_BRIDGE_PCI)
+		return;
+
+	if ((rel_type == whole_subtree) || is_leaf_bridge)
+		pci_bridge_release_resources(bus, type);
+}
+
+static void pci_bus_dump_res(struct pci_bus *bus)
+{
+	struct resource *res;
+	int i;
+
+	pci_bus_for_each_resource(bus, res, i) {
+		if (!res || !res->end || !res->flags)
+                        continue;
+
+		dev_printk(KERN_DEBUG, &bus->dev, "resource %d %pR\n", i, res);
+        }
+}
+
+static void pci_bus_dump_resources(struct pci_bus *bus)
+{
+	struct pci_bus *b;
+	struct pci_dev *dev;
+
+
+	pci_bus_dump_res(bus);
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		b = dev->subordinate;
+		if (!b)
+			continue;
+
+		pci_bus_dump_resources(b);
+	}
+}
+
+static int __init pci_bus_get_depth(struct pci_bus *bus)
+{
+	int depth = 0;
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		int ret;
+		struct pci_bus *b = dev->subordinate;
+		if (!b)
+			continue;
+
+		ret = pci_bus_get_depth(b);
+		if (ret + 1 > depth)
+			depth = ret + 1;
+	}
+
+	return depth;
+}
+static int __init pci_get_max_depth(void)
+{
+	int depth = 0;
+	struct pci_bus *bus;
+
+	list_for_each_entry(bus, &pci_root_buses, node) {
+		int ret;
+
+		ret = pci_bus_get_depth(bus);
+		if (ret > depth)
+			depth = ret;
+	}
+
+	return depth;
+}
+
+
+/*
+ * first try will not touch pci bridge res
+ * second  and later try will clear small leaf bridge res
+ * will stop till to the max  deepth if can not find good one
+ */
+void __init
+pci_assign_unassigned_resources(void)
+{
+	struct pci_bus *bus;
+	struct resource_list_x add_list; /* list of resources that
+					want additional resources */
+	int tried_times = 0;
+	enum release_type rel_type = leaf_only;
+	struct resource_list_x head, *list;
+	unsigned long type_mask = IORESOURCE_IO | IORESOURCE_MEM |
+				  IORESOURCE_PREFETCH;
+	unsigned long failed_type;
+	int max_depth = pci_get_max_depth();
+	int pci_try_num;
+
+
+	head.next = NULL;
+	add_list.next = NULL;
+
+	pci_try_num = max_depth + 1;
+	printk(KERN_DEBUG "PCI: max bus depth: %d pci_try_num: %d\n",
+		 max_depth, pci_try_num);
+
+again:
+	/* Depth first, calculate sizes and alignments of all
+	   subordinate buses. */
+	list_for_each_entry(bus, &pci_root_buses, node)
+		__pci_bus_size_bridges(bus, &add_list);
+
+	/* Depth last, allocate resources and update the hardware. */
+	list_for_each_entry(bus, &pci_root_buses, node)
+		__pci_bus_assign_resources(bus, &add_list, &head);
+	BUG_ON(add_list.next);
+	tried_times++;
+
+	/* any device complain? */
+	if (!head.next)
+		goto enable_and_dump;
+
+	/* don't realloc if asked to do so */
+	if (!pci_realloc_enabled()) {
+		free_list(resource_list_x, &head);
+		goto enable_and_dump;
+	}
+
+	failed_type = 0;
+	for (list = head.next; list;) {
+		failed_type |= list->flags;
+		list = list->next;
+	}
+	/*
+	 * io port are tight, don't try extra
+	 * or if reach the limit, don't want to try more
+	 */
+	failed_type &= type_mask;
+	if ((failed_type == IORESOURCE_IO) || (tried_times >= pci_try_num)) {
+		free_list(resource_list_x, &head);
+		goto enable_and_dump;
+	}
+
+	printk(KERN_DEBUG "PCI: No. %d try to assign unassigned res\n",
+			 tried_times + 1);
+
+	/* third times and later will not check if it is leaf */
+	if ((tried_times + 1) > 2)
+		rel_type = whole_subtree;
+
+	/*
+	 * Try to release leaf bridge's resources that doesn't fit resource of
+	 * child device under that bridge
+	 */
+	for (list = head.next; list;) {
+		bus = list->dev->bus;
+		pci_bus_release_bridge_resources(bus, list->flags & type_mask,
+						  rel_type);
+		list = list->next;
+	}
+	/* restore size and flags */
+	for (list = head.next; list;) {
+		struct resource *res = list->res;
+
+		res->start = list->start;
+		res->end = list->end;
+		res->flags = list->flags;
+		if (list->dev->subordinate)
+			res->flags = 0;
+
+		list = list->next;
+	}
+	free_list(resource_list_x, &head);
+
+	goto again;
+
+enable_and_dump:
+	/* Depth last, update the hardware. */
+	list_for_each_entry(bus, &pci_root_buses, node)
+		pci_enable_bridges(bus);
+
+	/* dump the resource on buses */
+	list_for_each_entry(bus, &pci_root_buses, node)
+		pci_bus_dump_resources(bus);
+}
+
+void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge)
+{
+	struct pci_bus *parent = bridge->subordinate;
+	int tried_times = 0;
+	struct resource_list_x head, *list;
+	int retval;
+	unsigned long type_mask = IORESOURCE_IO | IORESOURCE_MEM |
+				  IORESOURCE_PREFETCH;
+
+	head.next = NULL;
+
+again:
+	pci_bus_size_bridges(parent);
+	__pci_bridge_assign_resources(bridge, &head);
+
+	tried_times++;
+
+	if (!head.next)
+		goto enable_all;
+
+	if (tried_times >= 2) {
+		/* still fail, don't need to try more */
+		free_list(resource_list_x, &head);
+		goto enable_all;
+	}
+
+	printk(KERN_DEBUG "PCI: No. %d try to assign unassigned res\n",
+			 tried_times + 1);
+
+	/*
+	 * Try to release leaf bridge's resources that doesn't fit resource of
+	 * child device under that bridge
+	 */
+	for (list = head.next; list;) {
+		struct pci_bus *bus = list->dev->bus;
+		unsigned long flags = list->flags;
+
+		pci_bus_release_bridge_resources(bus, flags & type_mask,
+						 whole_subtree);
+		list = list->next;
+	}
+	/* restore size and flags */
+	for (list = head.next; list;) {
+		struct resource *res = list->res;
+
+		res->start = list->start;
+		res->end = list->end;
+		res->flags = list->flags;
+		if (list->dev->subordinate)
+			res->flags = 0;
+
+		list = list->next;
+	}
+	free_list(resource_list_x, &head);
+
+	goto again;
+
+enable_all:
+	retval = pci_reenable_device(bridge);
+	pci_set_master(bridge);
+	pci_enable_bridges(parent);
+}
+EXPORT_SYMBOL_GPL(pci_assign_unassigned_bridge_resources);
diff --git a/drivers/pci/setup-irq.c b/drivers/pci/setup-irq.c
new file mode 100644
index 00000000..eec9738f
--- /dev/null
+++ b/drivers/pci/setup-irq.c
@@ -0,0 +1,64 @@
+/*
+ *	drivers/pci/setup-irq.c
+ *
+ * Extruded from code written by
+ *      Dave Rusling (david.rusling@reo.mts.dec.com)
+ *      David Mosberger (davidm@cs.arizona.edu)
+ *	David Miller (davem@redhat.com)
+ *
+ * Support routines for initializing a PCI subsystem.
+ */
+
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/errno.h>
+#include <linux/ioport.h>
+#include <linux/cache.h>
+
+
+static void __init
+pdev_fixup_irq(struct pci_dev *dev,
+	       u8 (*swizzle)(struct pci_dev *, u8 *),
+	       int (*map_irq)(struct pci_dev *, u8, u8))
+{
+	u8 pin, slot;
+	int irq = 0;
+
+	/* If this device is not on the primary bus, we need to figure out
+	   which interrupt pin it will come in on.   We know which slot it
+	   will come in on 'cos that slot is where the bridge is.   Each
+	   time the interrupt line passes through a PCI-PCI bridge we must
+	   apply the swizzle function.  */
+
+	pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+	/* Cope with illegal. */
+	if (pin > 4)
+		pin = 1;
+
+	if (pin != 0) {
+		/* Follow the chain of bridges, swizzling as we go.  */
+		slot = (*swizzle)(dev, &pin);
+
+		irq = (*map_irq)(dev, slot, pin);
+		if (irq == -1)
+			irq = 0;
+	}
+	dev->irq = irq;
+
+	dev_dbg(&dev->dev, "fixup irq: got %d\n", dev->irq);
+
+	/* Always tell the device, so the driver knows what is
+	   the real IRQ to use; the device does not use it. */
+	pcibios_update_irq(dev, irq);
+}
+
+void __init
+pci_fixup_irqs(u8 (*swizzle)(struct pci_dev *, u8 *),
+	       int (*map_irq)(struct pci_dev *, u8, u8))
+{
+	struct pci_dev *dev = NULL;
+	for_each_pci_dev(dev)
+		pdev_fixup_irq(dev, swizzle, map_irq);
+}
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
new file mode 100644
index 00000000..bc0e6eea
--- /dev/null
+++ b/drivers/pci/setup-res.c
@@ -0,0 +1,330 @@
+/*
+ *	drivers/pci/setup-res.c
+ *
+ * Extruded from code written by
+ *      Dave Rusling (david.rusling@reo.mts.dec.com)
+ *      David Mosberger (davidm@cs.arizona.edu)
+ *	David Miller (davem@redhat.com)
+ *
+ * Support routines for initializing a PCI subsystem.
+ */
+
+/* fixed for multiple pci buses, 1999 Andrea Arcangeli <andrea@suse.de> */
+
+/*
+ * Nov 2000, Ivan Kokshaysky <ink@jurassic.park.msu.ru>
+ *	     Resource sorting
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/errno.h>
+#include <linux/ioport.h>
+#include <linux/cache.h>
+#include <linux/slab.h>
+#include "pci.h"
+
+
+void pci_update_resource(struct pci_dev *dev, int resno)
+{
+	struct pci_bus_region region;
+	u32 new, check, mask;
+	int reg;
+	enum pci_bar_type type;
+	struct resource *res = dev->resource + resno;
+
+	/*
+	 * Ignore resources for unimplemented BARs and unused resource slots
+	 * for 64 bit BARs.
+	 */
+	if (!res->flags)
+		return;
+
+	/*
+	 * Ignore non-moveable resources.  This might be legacy resources for
+	 * which no functional BAR register exists or another important
+	 * system resource we shouldn't move around.
+	 */
+	if (res->flags & IORESOURCE_PCI_FIXED)
+		return;
+
+	pcibios_resource_to_bus(dev, &region, res);
+
+	new = region.start | (res->flags & PCI_REGION_FLAG_MASK);
+	if (res->flags & IORESOURCE_IO)
+		mask = (u32)PCI_BASE_ADDRESS_IO_MASK;
+	else
+		mask = (u32)PCI_BASE_ADDRESS_MEM_MASK;
+
+	reg = pci_resource_bar(dev, resno, &type);
+	if (!reg)
+		return;
+	if (type != pci_bar_unknown) {
+		if (!(res->flags & IORESOURCE_ROM_ENABLE))
+			return;
+		new |= PCI_ROM_ADDRESS_ENABLE;
+	}
+
+	pci_write_config_dword(dev, reg, new);
+	pci_read_config_dword(dev, reg, &check);
+
+	if ((new ^ check) & mask) {
+		dev_err(&dev->dev, "BAR %d: error updating (%#08x != %#08x)\n",
+			resno, new, check);
+	}
+
+	if ((new & (PCI_BASE_ADDRESS_SPACE|PCI_BASE_ADDRESS_MEM_TYPE_MASK)) ==
+	    (PCI_BASE_ADDRESS_SPACE_MEMORY|PCI_BASE_ADDRESS_MEM_TYPE_64)) {
+		new = region.start >> 16 >> 16;
+		pci_write_config_dword(dev, reg + 4, new);
+		pci_read_config_dword(dev, reg + 4, &check);
+		if (check != new) {
+			dev_err(&dev->dev, "BAR %d: error updating "
+			       "(high %#08x != %#08x)\n", resno, new, check);
+		}
+	}
+	res->flags &= ~IORESOURCE_UNSET;
+	dev_info(&dev->dev, "BAR %d: set to %pR (PCI address [%#llx-%#llx])\n",
+		 resno, res, (unsigned long long)region.start,
+		 (unsigned long long)region.end);
+}
+
+int pci_claim_resource(struct pci_dev *dev, int resource)
+{
+	struct resource *res = &dev->resource[resource];
+	struct resource *root, *conflict;
+
+	root = pci_find_parent_resource(dev, res);
+	if (!root) {
+		dev_info(&dev->dev, "no compatible bridge window for %pR\n",
+			 res);
+		return -EINVAL;
+	}
+
+	conflict = request_resource_conflict(root, res);
+	if (conflict) {
+		dev_info(&dev->dev,
+			 "address space collision: %pR conflicts with %s %pR\n",
+			 res, conflict->name, conflict);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(pci_claim_resource);
+
+#ifdef CONFIG_PCI_QUIRKS
+void pci_disable_bridge_window(struct pci_dev *dev)
+{
+	dev_info(&dev->dev, "disabling bridge mem windows\n");
+
+	/* MMIO Base/Limit */
+	pci_write_config_dword(dev, PCI_MEMORY_BASE, 0x0000fff0);
+
+	/* Prefetchable MMIO Base/Limit */
+	pci_write_config_dword(dev, PCI_PREF_LIMIT_UPPER32, 0);
+	pci_write_config_dword(dev, PCI_PREF_MEMORY_BASE, 0x0000fff0);
+	pci_write_config_dword(dev, PCI_PREF_BASE_UPPER32, 0xffffffff);
+}
+#endif	/* CONFIG_PCI_QUIRKS */
+
+static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev,
+				 int resno)
+{
+	struct resource *res = dev->resource + resno;
+	resource_size_t size, min, align;
+	int ret;
+
+	size = resource_size(res);
+	min = (res->flags & IORESOURCE_IO) ? PCIBIOS_MIN_IO : PCIBIOS_MIN_MEM;
+	align = pci_resource_alignment(dev, res);
+
+	/* First, try exact prefetching match.. */
+	ret = pci_bus_alloc_resource(bus, res, size, align, min,
+				     IORESOURCE_PREFETCH,
+				     pcibios_align_resource, dev);
+
+	if (ret < 0 && (res->flags & IORESOURCE_PREFETCH)) {
+		/*
+		 * That failed.
+		 *
+		 * But a prefetching area can handle a non-prefetching
+		 * window (it will just not perform as well).
+		 */
+		ret = pci_bus_alloc_resource(bus, res, size, align, min, 0,
+					     pcibios_align_resource, dev);
+	}
+
+	if (ret < 0 && dev->fw_addr[resno]) {
+		struct resource *root, *conflict;
+		resource_size_t start, end;
+
+		/*
+		 * If we failed to assign anything, let's try the address
+		 * where firmware left it.  That at least has a chance of
+		 * working, which is better than just leaving it disabled.
+		 */
+
+		if (res->flags & IORESOURCE_IO)
+			root = &ioport_resource;
+		else
+			root = &iomem_resource;
+
+		start = res->start;
+		end = res->end;
+		res->start = dev->fw_addr[resno];
+		res->end = res->start + size - 1;
+		dev_info(&dev->dev, "BAR %d: trying firmware assignment %pR\n",
+			 resno, res);
+		conflict = request_resource_conflict(root, res);
+		if (conflict) {
+			dev_info(&dev->dev,
+				 "BAR %d: %pR conflicts with %s %pR\n", resno,
+				 res, conflict->name, conflict);
+			res->start = start;
+			res->end = end;
+		} else
+			ret = 0;
+	}
+
+	if (!ret) {
+		res->flags &= ~IORESOURCE_STARTALIGN;
+		dev_info(&dev->dev, "BAR %d: assigned %pR\n", resno, res);
+		if (resno < PCI_BRIDGE_RESOURCES)
+			pci_update_resource(dev, resno);
+	}
+
+	return ret;
+}
+
+int pci_assign_resource(struct pci_dev *dev, int resno)
+{
+	struct resource *res = dev->resource + resno;
+	resource_size_t align;
+	struct pci_bus *bus;
+	int ret;
+	char *type;
+
+	align = pci_resource_alignment(dev, res);
+	if (!align) {
+		dev_info(&dev->dev, "BAR %d: can't assign %pR "
+			 "(bogus alignment)\n", resno, res);
+		return -EINVAL;
+	}
+
+	bus = dev->bus;
+	while ((ret = __pci_assign_resource(bus, dev, resno))) {
+		if (bus->parent && bus->self->transparent)
+			bus = bus->parent;
+		else
+			bus = NULL;
+		if (bus)
+			continue;
+		break;
+	}
+
+	if (ret) {
+		if (res->flags & IORESOURCE_MEM)
+			if (res->flags & IORESOURCE_PREFETCH)
+				type = "mem pref";
+			else
+				type = "mem";
+		else if (res->flags & IORESOURCE_IO)
+			type = "io";
+		else
+			type = "unknown";
+		dev_info(&dev->dev,
+			 "BAR %d: can't assign %s (size %#llx)\n",
+			 resno, type, (unsigned long long) resource_size(res));
+	}
+
+	return ret;
+}
+
+/* Sort resources by alignment */
+void pdev_sort_resources(struct pci_dev *dev, struct resource_list *head)
+{
+	int i;
+
+	for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+		struct resource *r;
+		struct resource_list *list, *tmp;
+		resource_size_t r_align;
+
+		r = &dev->resource[i];
+
+		if (r->flags & IORESOURCE_PCI_FIXED)
+			continue;
+
+		if (!(r->flags) || r->parent)
+			continue;
+
+		r_align = pci_resource_alignment(dev, r);
+		if (!r_align) {
+			dev_warn(&dev->dev, "BAR %d: %pR has bogus alignment\n",
+				 i, r);
+			continue;
+		}
+		for (list = head; ; list = list->next) {
+			resource_size_t align = 0;
+			struct resource_list *ln = list->next;
+
+			if (ln)
+				align = pci_resource_alignment(ln->dev, ln->res);
+
+			if (r_align > align) {
+				tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
+				if (!tmp)
+					panic("pdev_sort_resources(): "
+					      "kmalloc() failed!\n");
+				tmp->next = ln;
+				tmp->res = r;
+				tmp->dev = dev;
+				list->next = tmp;
+				break;
+			}
+		}
+	}
+}
+
+int pci_enable_resources(struct pci_dev *dev, int mask)
+{
+	u16 cmd, old_cmd;
+	int i;
+	struct resource *r;
+
+	pci_read_config_word(dev, PCI_COMMAND, &cmd);
+	old_cmd = cmd;
+
+	for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+		if (!(mask & (1 << i)))
+			continue;
+
+		r = &dev->resource[i];
+
+		if (!(r->flags & (IORESOURCE_IO | IORESOURCE_MEM)))
+			continue;
+		if ((i == PCI_ROM_RESOURCE) &&
+				(!(r->flags & IORESOURCE_ROM_ENABLE)))
+			continue;
+
+		if (!r->parent) {
+			dev_err(&dev->dev, "device not available "
+				"(can't reserve %pR)\n", r);
+			return -EINVAL;
+		}
+
+		if (r->flags & IORESOURCE_IO)
+			cmd |= PCI_COMMAND_IO;
+		if (r->flags & IORESOURCE_MEM)
+			cmd |= PCI_COMMAND_MEMORY;
+	}
+
+	if (cmd != old_cmd) {
+		dev_info(&dev->dev, "enabling device (%04x -> %04x)\n",
+			 old_cmd, cmd);
+		pci_write_config_word(dev, PCI_COMMAND, cmd);
+	}
+	return 0;
+}
diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
new file mode 100644
index 00000000..968cfea0
--- /dev/null
+++ b/drivers/pci/slot.c
@@ -0,0 +1,419 @@
+/*
+ * drivers/pci/slot.c
+ * Copyright (C) 2006 Matthew Wilcox <matthew@wil.cx>
+ * Copyright (C) 2006-2009 Hewlett-Packard Development Company, L.P.
+ *	Alex Chiang <achiang@hp.com>
+ */
+
+#include <linux/kobject.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/err.h>
+#include "pci.h"
+
+struct kset *pci_slots_kset;
+EXPORT_SYMBOL_GPL(pci_slots_kset);
+
+static ssize_t pci_slot_attr_show(struct kobject *kobj,
+					struct attribute *attr, char *buf)
+{
+	struct pci_slot *slot = to_pci_slot(kobj);
+	struct pci_slot_attribute *attribute = to_pci_slot_attr(attr);
+	return attribute->show ? attribute->show(slot, buf) : -EIO;
+}
+
+static ssize_t pci_slot_attr_store(struct kobject *kobj,
+			struct attribute *attr, const char *buf, size_t len)
+{
+	struct pci_slot *slot = to_pci_slot(kobj);
+	struct pci_slot_attribute *attribute = to_pci_slot_attr(attr);
+	return attribute->store ? attribute->store(slot, buf, len) : -EIO;
+}
+
+static const struct sysfs_ops pci_slot_sysfs_ops = {
+	.show = pci_slot_attr_show,
+	.store = pci_slot_attr_store,
+};
+
+static ssize_t address_read_file(struct pci_slot *slot, char *buf)
+{
+	if (slot->number == 0xff)
+		return sprintf(buf, "%04x:%02x\n",
+				pci_domain_nr(slot->bus),
+				slot->bus->number);
+	else
+		return sprintf(buf, "%04x:%02x:%02x\n",
+				pci_domain_nr(slot->bus),
+				slot->bus->number,
+				slot->number);
+}
+
+/* these strings match up with the values in pci_bus_speed */
+static const char *pci_bus_speed_strings[] = {
+	"33 MHz PCI",		/* 0x00 */
+	"66 MHz PCI",		/* 0x01 */
+	"66 MHz PCI-X", 	/* 0x02 */
+	"100 MHz PCI-X",	/* 0x03 */
+	"133 MHz PCI-X",	/* 0x04 */
+	NULL,			/* 0x05 */
+	NULL,			/* 0x06 */
+	NULL,			/* 0x07 */
+	NULL,			/* 0x08 */
+	"66 MHz PCI-X 266",	/* 0x09 */
+	"100 MHz PCI-X 266",	/* 0x0a */
+	"133 MHz PCI-X 266",	/* 0x0b */
+	"Unknown AGP",		/* 0x0c */
+	"1x AGP",		/* 0x0d */
+	"2x AGP",		/* 0x0e */
+	"4x AGP",		/* 0x0f */
+	"8x AGP",		/* 0x10 */
+	"66 MHz PCI-X 533",	/* 0x11 */
+	"100 MHz PCI-X 533",	/* 0x12 */
+	"133 MHz PCI-X 533",	/* 0x13 */
+	"2.5 GT/s PCIe",	/* 0x14 */
+	"5.0 GT/s PCIe",	/* 0x15 */
+	"8.0 GT/s PCIe",	/* 0x16 */
+};
+
+static ssize_t bus_speed_read(enum pci_bus_speed speed, char *buf)
+{
+	const char *speed_string;
+
+	if (speed < ARRAY_SIZE(pci_bus_speed_strings))
+		speed_string = pci_bus_speed_strings[speed];
+	else
+		speed_string = "Unknown";
+
+	return sprintf(buf, "%s\n", speed_string);
+}
+
+static ssize_t max_speed_read_file(struct pci_slot *slot, char *buf)
+{
+	return bus_speed_read(slot->bus->max_bus_speed, buf);
+}
+
+static ssize_t cur_speed_read_file(struct pci_slot *slot, char *buf)
+{
+	return bus_speed_read(slot->bus->cur_bus_speed, buf);
+}
+
+static void pci_slot_release(struct kobject *kobj)
+{
+	struct pci_dev *dev;
+	struct pci_slot *slot = to_pci_slot(kobj);
+
+	dev_dbg(&slot->bus->dev, "dev %02x, released physical slot %s\n",
+		slot->number, pci_slot_name(slot));
+
+	list_for_each_entry(dev, &slot->bus->devices, bus_list)
+		if (PCI_SLOT(dev->devfn) == slot->number)
+			dev->slot = NULL;
+
+	list_del(&slot->list);
+
+	kfree(slot);
+}
+
+static struct pci_slot_attribute pci_slot_attr_address =
+	__ATTR(address, (S_IFREG | S_IRUGO), address_read_file, NULL);
+static struct pci_slot_attribute pci_slot_attr_max_speed =
+	__ATTR(max_bus_speed, (S_IFREG | S_IRUGO), max_speed_read_file, NULL);
+static struct pci_slot_attribute pci_slot_attr_cur_speed =
+	__ATTR(cur_bus_speed, (S_IFREG | S_IRUGO), cur_speed_read_file, NULL);
+
+static struct attribute *pci_slot_default_attrs[] = {
+	&pci_slot_attr_address.attr,
+	&pci_slot_attr_max_speed.attr,
+	&pci_slot_attr_cur_speed.attr,
+	NULL,
+};
+
+static struct kobj_type pci_slot_ktype = {
+	.sysfs_ops = &pci_slot_sysfs_ops,
+	.release = &pci_slot_release,
+	.default_attrs = pci_slot_default_attrs,
+};
+
+static char *make_slot_name(const char *name)
+{
+	char *new_name;
+	int len, max, dup;
+
+	new_name = kstrdup(name, GFP_KERNEL);
+	if (!new_name)
+		return NULL;
+
+	/*
+	 * Make sure we hit the realloc case the first time through the
+	 * loop.  'len' will be strlen(name) + 3 at that point which is
+	 * enough space for "name-X" and the trailing NUL.
+	 */
+	len = strlen(name) + 2;
+	max = 1;
+	dup = 1;
+
+	for (;;) {
+		struct kobject *dup_slot;
+		dup_slot = kset_find_obj(pci_slots_kset, new_name);
+		if (!dup_slot)
+			break;
+		kobject_put(dup_slot);
+		if (dup == max) {
+			len++;
+			max *= 10;
+			kfree(new_name);
+			new_name = kmalloc(len, GFP_KERNEL);
+			if (!new_name)
+				break;
+		}
+		sprintf(new_name, "%s-%d", name, dup++);
+	}
+
+	return new_name;
+}
+
+static int rename_slot(struct pci_slot *slot, const char *name)
+{
+	int result = 0;
+	char *slot_name;
+
+	if (strcmp(pci_slot_name(slot), name) == 0)
+		return result;
+
+	slot_name = make_slot_name(name);
+	if (!slot_name)
+		return -ENOMEM;
+
+	result = kobject_rename(&slot->kobj, slot_name);
+	kfree(slot_name);
+
+	return result;
+}
+
+static struct pci_slot *get_slot(struct pci_bus *parent, int slot_nr)
+{
+	struct pci_slot *slot;
+	/*
+	 * We already hold pci_bus_sem so don't worry
+	 */
+	list_for_each_entry(slot, &parent->slots, list)
+		if (slot->number == slot_nr) {
+			kobject_get(&slot->kobj);
+			return slot;
+		}
+
+	return NULL;
+}
+
+/**
+ * pci_create_slot - create or increment refcount for physical PCI slot
+ * @parent: struct pci_bus of parent bridge
+ * @slot_nr: PCI_SLOT(pci_dev->devfn) or -1 for placeholder
+ * @name: user visible string presented in /sys/bus/pci/slots/<name>
+ * @hotplug: set if caller is hotplug driver, NULL otherwise
+ *
+ * PCI slots have first class attributes such as address, speed, width,
+ * and a &struct pci_slot is used to manage them. This interface will
+ * either return a new &struct pci_slot to the caller, or if the pci_slot
+ * already exists, its refcount will be incremented.
+ *
+ * Slots are uniquely identified by a @pci_bus, @slot_nr tuple.
+ *
+ * There are known platforms with broken firmware that assign the same
+ * name to multiple slots. Workaround these broken platforms by renaming
+ * the slots on behalf of the caller. If firmware assigns name N to
+ * multiple slots:
+ *
+ * The first slot is assigned N
+ * The second slot is assigned N-1
+ * The third slot is assigned N-2
+ * etc.
+ *
+ * Placeholder slots:
+ * In most cases, @pci_bus, @slot_nr will be sufficient to uniquely identify
+ * a slot. There is one notable exception - pSeries (rpaphp), where the
+ * @slot_nr cannot be determined until a device is actually inserted into
+ * the slot. In this scenario, the caller may pass -1 for @slot_nr.
+ *
+ * The following semantics are imposed when the caller passes @slot_nr ==
+ * -1. First, we no longer check for an existing %struct pci_slot, as there
+ * may be many slots with @slot_nr of -1.  The other change in semantics is
+ * user-visible, which is the 'address' parameter presented in sysfs will
+ * consist solely of a dddd:bb tuple, where dddd is the PCI domain of the
+ * %struct pci_bus and bb is the bus number. In other words, the devfn of
+ * the 'placeholder' slot will not be displayed.
+ */
+struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
+				 const char *name,
+				 struct hotplug_slot *hotplug)
+{
+	struct pci_dev *dev;
+	struct pci_slot *slot;
+	int err = 0;
+	char *slot_name = NULL;
+
+	down_write(&pci_bus_sem);
+
+	if (slot_nr == -1)
+		goto placeholder;
+
+	/*
+	 * Hotplug drivers are allowed to rename an existing slot,
+	 * but only if not already claimed.
+	 */
+	slot = get_slot(parent, slot_nr);
+	if (slot) {
+		if (hotplug) {
+			if ((err = slot->hotplug ? -EBUSY : 0)
+			     || (err = rename_slot(slot, name))) {
+				kobject_put(&slot->kobj);
+				slot = NULL;
+				goto err;
+			}
+		}
+		goto out;
+	}
+
+placeholder:
+	slot = kzalloc(sizeof(*slot), GFP_KERNEL);
+	if (!slot) {
+		err = -ENOMEM;
+		goto err;
+	}
+
+	slot->bus = parent;
+	slot->number = slot_nr;
+
+	slot->kobj.kset = pci_slots_kset;
+
+	slot_name = make_slot_name(name);
+	if (!slot_name) {
+		err = -ENOMEM;
+		goto err;
+	}
+
+	err = kobject_init_and_add(&slot->kobj, &pci_slot_ktype, NULL,
+				   "%s", slot_name);
+	if (err)
+		goto err;
+
+	INIT_LIST_HEAD(&slot->list);
+	list_add(&slot->list, &parent->slots);
+
+	list_for_each_entry(dev, &parent->devices, bus_list)
+		if (PCI_SLOT(dev->devfn) == slot_nr)
+			dev->slot = slot;
+
+	dev_dbg(&parent->dev, "dev %02x, created physical slot %s\n",
+		slot_nr, pci_slot_name(slot));
+
+out:
+	kfree(slot_name);
+	up_write(&pci_bus_sem);
+	return slot;
+err:
+	kfree(slot);
+	slot = ERR_PTR(err);
+	goto out;
+}
+EXPORT_SYMBOL_GPL(pci_create_slot);
+
+/**
+ * pci_renumber_slot - update %struct pci_slot -> number
+ * @slot: &struct pci_slot to update
+ * @slot_nr: new number for slot
+ *
+ * The primary purpose of this interface is to allow callers who earlier
+ * created a placeholder slot in pci_create_slot() by passing a -1 as
+ * slot_nr, to update their %struct pci_slot with the correct @slot_nr.
+ */
+void pci_renumber_slot(struct pci_slot *slot, int slot_nr)
+{
+	struct pci_slot *tmp;
+
+	down_write(&pci_bus_sem);
+
+	list_for_each_entry(tmp, &slot->bus->slots, list) {
+		WARN_ON(tmp->number == slot_nr);
+		goto out;
+	}
+
+	slot->number = slot_nr;
+out:
+	up_write(&pci_bus_sem);
+}
+EXPORT_SYMBOL_GPL(pci_renumber_slot);
+
+/**
+ * pci_destroy_slot - decrement refcount for physical PCI slot
+ * @slot: struct pci_slot to decrement
+ *
+ * %struct pci_slot is refcounted, so destroying them is really easy; we
+ * just call kobject_put on its kobj and let our release methods do the
+ * rest.
+ */
+void pci_destroy_slot(struct pci_slot *slot)
+{
+	dev_dbg(&slot->bus->dev, "dev %02x, dec refcount to %d\n",
+		slot->number, atomic_read(&slot->kobj.kref.refcount) - 1);
+
+	down_write(&pci_bus_sem);
+	kobject_put(&slot->kobj);
+	up_write(&pci_bus_sem);
+}
+EXPORT_SYMBOL_GPL(pci_destroy_slot);
+
+#if defined(CONFIG_HOTPLUG_PCI) || defined(CONFIG_HOTPLUG_PCI_MODULE)
+#include <linux/pci_hotplug.h>
+/**
+ * pci_hp_create_link - create symbolic link to the hotplug driver module.
+ * @pci_slot: struct pci_slot
+ *
+ * Helper function for pci_hotplug_core.c to create symbolic link to
+ * the hotplug driver module.
+ */
+void pci_hp_create_module_link(struct pci_slot *pci_slot)
+{
+	struct hotplug_slot *slot = pci_slot->hotplug;
+	struct kobject *kobj = NULL;
+	int no_warn;
+
+	if (!slot || !slot->ops)
+		return;
+	kobj = kset_find_obj(module_kset, slot->ops->mod_name);
+	if (!kobj)
+		return;
+	no_warn = sysfs_create_link(&pci_slot->kobj, kobj, "module");
+	kobject_put(kobj);
+}
+EXPORT_SYMBOL_GPL(pci_hp_create_module_link);
+
+/**
+ * pci_hp_remove_link - remove symbolic link to the hotplug driver module.
+ * @pci_slot: struct pci_slot
+ *
+ * Helper function for pci_hotplug_core.c to remove symbolic link to
+ * the hotplug driver module.
+ */
+void pci_hp_remove_module_link(struct pci_slot *pci_slot)
+{
+	sysfs_remove_link(&pci_slot->kobj, "module");
+}
+EXPORT_SYMBOL_GPL(pci_hp_remove_module_link);
+#endif
+
+static int pci_slot_init(void)
+{
+	struct kset *pci_bus_kset;
+
+	pci_bus_kset = bus_get_kset(&pci_bus_type);
+	pci_slots_kset = kset_create_and_add("slots", NULL,
+						&pci_bus_kset->kobj);
+	if (!pci_slots_kset) {
+		printk(KERN_ERR "PCI: Slot initialization failure\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+subsys_initcall(pci_slot_init);
diff --git a/drivers/pci/syscall.c b/drivers/pci/syscall.c
new file mode 100644
index 00000000..e1c1ec54
--- /dev/null
+++ b/drivers/pci/syscall.c
@@ -0,0 +1,136 @@
+/*
+ *	pci_syscall.c
+ *
+ * For architectures where we want to allow direct access
+ * to the PCI config stuff - it would probably be preferable
+ * on PCs too, but there people just do it by hand with the
+ * magic northbridge registers..
+ */
+
+#include <linux/errno.h>
+#include <linux/pci.h>
+#include <linux/syscalls.h>
+#include <asm/uaccess.h>
+#include "pci.h"
+
+SYSCALL_DEFINE5(pciconfig_read, unsigned long, bus, unsigned long, dfn,
+		unsigned long, off, unsigned long, len, void __user *, buf)
+{
+	struct pci_dev *dev;
+	u8 byte;
+	u16 word;
+	u32 dword;
+	long err;
+	long cfg_ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	err = -ENODEV;
+	dev = pci_get_bus_and_slot(bus, dfn);
+	if (!dev)
+		goto error;
+
+	switch (len) {
+	case 1:
+		cfg_ret = pci_user_read_config_byte(dev, off, &byte);
+		break;
+	case 2:
+		cfg_ret = pci_user_read_config_word(dev, off, &word);
+		break;
+	case 4:
+		cfg_ret = pci_user_read_config_dword(dev, off, &dword);
+		break;
+	default:
+		err = -EINVAL;
+		goto error;
+	};
+
+	err = -EIO;
+	if (cfg_ret != PCIBIOS_SUCCESSFUL)
+		goto error;
+
+	switch (len) {
+	case 1:
+		err = put_user(byte, (unsigned char __user *)buf);
+		break;
+	case 2:
+		err = put_user(word, (unsigned short __user *)buf);
+		break;
+	case 4:
+		err = put_user(dword, (unsigned int __user *)buf);
+		break;
+	}
+	pci_dev_put(dev);
+	return err;
+
+error:
+	/* ??? XFree86 doesn't even check the return value.  They
+	   just look for 0xffffffff in the output, since that's what
+	   they get instead of a machine check on x86.  */
+	switch (len) {
+	case 1:
+		put_user(-1, (unsigned char __user *)buf);
+		break;
+	case 2:
+		put_user(-1, (unsigned short __user *)buf);
+		break;
+	case 4:
+		put_user(-1, (unsigned int __user *)buf);
+		break;
+	}
+	pci_dev_put(dev);
+	return err;
+}
+
+SYSCALL_DEFINE5(pciconfig_write, unsigned long, bus, unsigned long, dfn,
+		unsigned long, off, unsigned long, len, void __user *, buf)
+{
+	struct pci_dev *dev;
+	u8 byte;
+	u16 word;
+	u32 dword;
+	int err = 0;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	dev = pci_get_bus_and_slot(bus, dfn);
+	if (!dev)
+		return -ENODEV;
+
+	switch(len) {
+	case 1:
+		err = get_user(byte, (u8 __user *)buf);
+		if (err)
+			break;
+		err = pci_user_write_config_byte(dev, off, byte);
+		if (err != PCIBIOS_SUCCESSFUL)
+			err = -EIO;
+		break;
+
+	case 2:
+		err = get_user(word, (u16 __user *)buf);
+		if (err)
+			break;
+		err = pci_user_write_config_word(dev, off, word);
+		if (err != PCIBIOS_SUCCESSFUL)
+			err = -EIO;
+		break;
+
+	case 4:
+		err = get_user(dword, (u32 __user *)buf);
+		if (err)
+			break;
+		err = pci_user_write_config_dword(dev, off, dword);
+		if (err != PCIBIOS_SUCCESSFUL)
+			err = -EIO;
+		break;
+
+	default:
+		err = -EINVAL;
+		break;
+	}
+	pci_dev_put(dev);
+	return err;
+}
diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c
new file mode 100644
index 00000000..a5a5ca17
--- /dev/null
+++ b/drivers/pci/vpd.c
@@ -0,0 +1,61 @@
+/*
+ * File:	vpd.c
+ * Purpose:	Provide PCI VPD support
+ *
+ * Copyright (C) 2010 Broadcom Corporation.
+ */
+
+#include <linux/pci.h>
+
+int pci_vpd_find_tag(const u8 *buf, unsigned int off, unsigned int len, u8 rdt)
+{
+	int i;
+
+	for (i = off; i < len; ) {
+		u8 val = buf[i];
+
+		if (val & PCI_VPD_LRDT) {
+			/* Don't return success of the tag isn't complete */
+			if (i + PCI_VPD_LRDT_TAG_SIZE > len)
+				break;
+
+			if (val == rdt)
+				return i;
+
+			i += PCI_VPD_LRDT_TAG_SIZE +
+			     pci_vpd_lrdt_size(&buf[i]);
+		} else {
+			u8 tag = val & ~PCI_VPD_SRDT_LEN_MASK;
+
+			if (tag == rdt)
+				return i;
+
+			if (tag == PCI_VPD_SRDT_END)
+				break;
+
+			i += PCI_VPD_SRDT_TAG_SIZE +
+			     pci_vpd_srdt_size(&buf[i]);
+		}
+	}
+
+	return -ENOENT;
+}
+EXPORT_SYMBOL_GPL(pci_vpd_find_tag);
+
+int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off,
+			      unsigned int len, const char *kw)
+{
+	int i;
+
+	for (i = off; i + PCI_VPD_INFO_FLD_HDR_SIZE <= off + len;) {
+		if (buf[i + 0] == kw[0] &&
+		    buf[i + 1] == kw[1])
+			return i;
+
+		i += PCI_VPD_INFO_FLD_HDR_SIZE +
+		     pci_vpd_info_field_size(&buf[i]);
+	}
+
+	return -ENOENT;
+}
+EXPORT_SYMBOL_GPL(pci_vpd_find_info_keyword);
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
new file mode 100644
index 00000000..d4e7a105
--- /dev/null
+++ b/drivers/pci/xen-pcifront.c
@@ -0,0 +1,1158 @@
+/*
+ * Xen PCI Frontend.
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <xen/xenbus.h>
+#include <xen/events.h>
+#include <xen/grant_table.h>
+#include <xen/page.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <xen/interface/io/pciif.h>
+#include <asm/xen/pci.h>
+#include <linux/interrupt.h>
+#include <asm/atomic.h>
+#include <linux/workqueue.h>
+#include <linux/bitops.h>
+#include <linux/time.h>
+
+#define INVALID_GRANT_REF (0)
+#define INVALID_EVTCHN    (-1)
+
+struct pci_bus_entry {
+	struct list_head list;
+	struct pci_bus *bus;
+};
+
+#define _PDEVB_op_active		(0)
+#define PDEVB_op_active			(1 << (_PDEVB_op_active))
+
+struct pcifront_device {
+	struct xenbus_device *xdev;
+	struct list_head root_buses;
+
+	int evtchn;
+	int gnt_ref;
+
+	int irq;
+
+	/* Lock this when doing any operations in sh_info */
+	spinlock_t sh_info_lock;
+	struct xen_pci_sharedinfo *sh_info;
+	struct work_struct op_work;
+	unsigned long flags;
+
+};
+
+struct pcifront_sd {
+	int domain;
+	struct pcifront_device *pdev;
+};
+
+static inline struct pcifront_device *
+pcifront_get_pdev(struct pcifront_sd *sd)
+{
+	return sd->pdev;
+}
+
+static inline void pcifront_init_sd(struct pcifront_sd *sd,
+				    unsigned int domain, unsigned int bus,
+				    struct pcifront_device *pdev)
+{
+	sd->domain = domain;
+	sd->pdev = pdev;
+}
+
+static DEFINE_SPINLOCK(pcifront_dev_lock);
+static struct pcifront_device *pcifront_dev;
+
+static int verbose_request;
+module_param(verbose_request, int, 0644);
+
+static int errno_to_pcibios_err(int errno)
+{
+	switch (errno) {
+	case XEN_PCI_ERR_success:
+		return PCIBIOS_SUCCESSFUL;
+
+	case XEN_PCI_ERR_dev_not_found:
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	case XEN_PCI_ERR_invalid_offset:
+	case XEN_PCI_ERR_op_failed:
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+
+	case XEN_PCI_ERR_not_implemented:
+		return PCIBIOS_FUNC_NOT_SUPPORTED;
+
+	case XEN_PCI_ERR_access_denied:
+		return PCIBIOS_SET_FAILED;
+	}
+	return errno;
+}
+
+static inline void schedule_pcifront_aer_op(struct pcifront_device *pdev)
+{
+	if (test_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags)
+		&& !test_and_set_bit(_PDEVB_op_active, &pdev->flags)) {
+		dev_dbg(&pdev->xdev->dev, "schedule aer frontend job\n");
+		schedule_work(&pdev->op_work);
+	}
+}
+
+static int do_pci_op(struct pcifront_device *pdev, struct xen_pci_op *op)
+{
+	int err = 0;
+	struct xen_pci_op *active_op = &pdev->sh_info->op;
+	unsigned long irq_flags;
+	evtchn_port_t port = pdev->evtchn;
+	unsigned irq = pdev->irq;
+	s64 ns, ns_timeout;
+	struct timeval tv;
+
+	spin_lock_irqsave(&pdev->sh_info_lock, irq_flags);
+
+	memcpy(active_op, op, sizeof(struct xen_pci_op));
+
+	/* Go */
+	wmb();
+	set_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags);
+	notify_remote_via_evtchn(port);
+
+	/*
+	 * We set a poll timeout of 3 seconds but give up on return after
+	 * 2 seconds. It is better to time out too late rather than too early
+	 * (in the latter case we end up continually re-executing poll() with a
+	 * timeout in the past). 1s difference gives plenty of slack for error.
+	 */
+	do_gettimeofday(&tv);
+	ns_timeout = timeval_to_ns(&tv) + 2 * (s64)NSEC_PER_SEC;
+
+	xen_clear_irq_pending(irq);
+
+	while (test_bit(_XEN_PCIF_active,
+			(unsigned long *)&pdev->sh_info->flags)) {
+		xen_poll_irq_timeout(irq, jiffies + 3*HZ);
+		xen_clear_irq_pending(irq);
+		do_gettimeofday(&tv);
+		ns = timeval_to_ns(&tv);
+		if (ns > ns_timeout) {
+			dev_err(&pdev->xdev->dev,
+				"pciback not responding!!!\n");
+			clear_bit(_XEN_PCIF_active,
+				  (unsigned long *)&pdev->sh_info->flags);
+			err = XEN_PCI_ERR_dev_not_found;
+			goto out;
+		}
+	}
+
+	/*
+	* We might lose backend service request since we
+	* reuse same evtchn with pci_conf backend response. So re-schedule
+	* aer pcifront service.
+	*/
+	if (test_bit(_XEN_PCIB_active,
+			(unsigned long *)&pdev->sh_info->flags)) {
+		dev_err(&pdev->xdev->dev,
+			"schedule aer pcifront service\n");
+		schedule_pcifront_aer_op(pdev);
+	}
+
+	memcpy(op, active_op, sizeof(struct xen_pci_op));
+
+	err = op->err;
+out:
+	spin_unlock_irqrestore(&pdev->sh_info_lock, irq_flags);
+	return err;
+}
+
+/* Access to this function is spinlocked in drivers/pci/access.c */
+static int pcifront_bus_read(struct pci_bus *bus, unsigned int devfn,
+			     int where, int size, u32 *val)
+{
+	int err = 0;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_conf_read,
+		.domain = pci_domain_nr(bus),
+		.bus    = bus->number,
+		.devfn  = devfn,
+		.offset = where,
+		.size   = size,
+	};
+	struct pcifront_sd *sd = bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	if (verbose_request)
+		dev_info(&pdev->xdev->dev,
+			 "read dev=%04x:%02x:%02x.%01x - offset %x size %d\n",
+			 pci_domain_nr(bus), bus->number, PCI_SLOT(devfn),
+			 PCI_FUNC(devfn), where, size);
+
+	err = do_pci_op(pdev, &op);
+
+	if (likely(!err)) {
+		if (verbose_request)
+			dev_info(&pdev->xdev->dev, "read got back value %x\n",
+				 op.value);
+
+		*val = op.value;
+	} else if (err == -ENODEV) {
+		/* No device here, pretend that it just returned 0 */
+		err = 0;
+		*val = 0;
+	}
+
+	return errno_to_pcibios_err(err);
+}
+
+/* Access to this function is spinlocked in drivers/pci/access.c */
+static int pcifront_bus_write(struct pci_bus *bus, unsigned int devfn,
+			      int where, int size, u32 val)
+{
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_conf_write,
+		.domain = pci_domain_nr(bus),
+		.bus    = bus->number,
+		.devfn  = devfn,
+		.offset = where,
+		.size   = size,
+		.value  = val,
+	};
+	struct pcifront_sd *sd = bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	if (verbose_request)
+		dev_info(&pdev->xdev->dev,
+			 "write dev=%04x:%02x:%02x.%01x - "
+			 "offset %x size %d val %x\n",
+			 pci_domain_nr(bus), bus->number,
+			 PCI_SLOT(devfn), PCI_FUNC(devfn), where, size, val);
+
+	return errno_to_pcibios_err(do_pci_op(pdev, &op));
+}
+
+struct pci_ops pcifront_bus_ops = {
+	.read = pcifront_bus_read,
+	.write = pcifront_bus_write,
+};
+
+#ifdef CONFIG_PCI_MSI
+static int pci_frontend_enable_msix(struct pci_dev *dev,
+				    int vector[], int nvec)
+{
+	int err;
+	int i;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_enable_msix,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+		.value = nvec,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+	struct msi_desc *entry;
+
+	if (nvec > SH_INFO_MAX_VEC) {
+		dev_err(&dev->dev, "too much vector for pci frontend: %x."
+				   " Increase SH_INFO_MAX_VEC.\n", nvec);
+		return -EINVAL;
+	}
+
+	i = 0;
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		op.msix_entries[i].entry = entry->msi_attrib.entry_nr;
+		/* Vector is useless at this point. */
+		op.msix_entries[i].vector = -1;
+		i++;
+	}
+
+	err = do_pci_op(pdev, &op);
+
+	if (likely(!err)) {
+		if (likely(!op.value)) {
+			/* we get the result */
+			for (i = 0; i < nvec; i++) {
+				if (op.msix_entries[i].vector <= 0) {
+					dev_warn(&dev->dev, "MSI-X entry %d is invalid: %d!\n",
+						i, op.msix_entries[i].vector);
+					err = -EINVAL;
+					vector[i] = -1;
+					continue;
+				}
+				vector[i] = op.msix_entries[i].vector;
+			}
+		} else {
+			printk(KERN_DEBUG "enable msix get value %x\n",
+				op.value);
+		}
+	} else {
+		dev_err(&dev->dev, "enable msix get err %x\n", err);
+	}
+	return err;
+}
+
+static void pci_frontend_disable_msix(struct pci_dev *dev)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_disable_msix,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+
+	/* What should do for error ? */
+	if (err)
+		dev_err(&dev->dev, "pci_disable_msix get err %x\n", err);
+}
+
+static int pci_frontend_enable_msi(struct pci_dev *dev, int vector[])
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_enable_msi,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+	if (likely(!err)) {
+		vector[0] = op.value;
+		if (op.value <= 0) {
+			dev_warn(&dev->dev, "MSI entry is invalid: %d!\n",
+				op.value);
+			err = -EINVAL;
+			vector[0] = -1;
+		}
+	} else {
+		dev_err(&dev->dev, "pci frontend enable msi failed for dev "
+				    "%x:%x\n", op.bus, op.devfn);
+		err = -EINVAL;
+	}
+	return err;
+}
+
+static void pci_frontend_disable_msi(struct pci_dev *dev)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_disable_msi,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+	if (err == XEN_PCI_ERR_dev_not_found) {
+		/* XXX No response from backend, what shall we do? */
+		printk(KERN_DEBUG "get no response from backend for disable MSI\n");
+		return;
+	}
+	if (err)
+		/* how can pciback notify us fail? */
+		printk(KERN_DEBUG "get fake response frombackend\n");
+}
+
+static struct xen_pci_frontend_ops pci_frontend_ops = {
+	.enable_msi = pci_frontend_enable_msi,
+	.disable_msi = pci_frontend_disable_msi,
+	.enable_msix = pci_frontend_enable_msix,
+	.disable_msix = pci_frontend_disable_msix,
+};
+
+static void pci_frontend_registrar(int enable)
+{
+	if (enable)
+		xen_pci_frontend = &pci_frontend_ops;
+	else
+		xen_pci_frontend = NULL;
+};
+#else
+static inline void pci_frontend_registrar(int enable) { };
+#endif /* CONFIG_PCI_MSI */
+
+/* Claim resources for the PCI frontend as-is, backend won't allow changes */
+static int pcifront_claim_resource(struct pci_dev *dev, void *data)
+{
+	struct pcifront_device *pdev = data;
+	int i;
+	struct resource *r;
+
+	for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+		r = &dev->resource[i];
+
+		if (!r->parent && r->start && r->flags) {
+			dev_info(&pdev->xdev->dev, "claiming resource %s/%d\n",
+				pci_name(dev), i);
+			if (pci_claim_resource(dev, i)) {
+				dev_err(&pdev->xdev->dev, "Could not claim resource %s/%d! "
+					"Device offline. Try using e820_host=1 in the guest config.\n",
+					pci_name(dev), i);
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int __devinit pcifront_scan_bus(struct pcifront_device *pdev,
+				unsigned int domain, unsigned int bus,
+				struct pci_bus *b)
+{
+	struct pci_dev *d;
+	unsigned int devfn;
+
+	/* Scan the bus for functions and add.
+	 * We omit handling of PCI bridge attachment because pciback prevents
+	 * bridges from being exported.
+	 */
+	for (devfn = 0; devfn < 0x100; devfn++) {
+		d = pci_get_slot(b, devfn);
+		if (d) {
+			/* Device is already known. */
+			pci_dev_put(d);
+			continue;
+		}
+
+		d = pci_scan_single_device(b, devfn);
+		if (d)
+			dev_info(&pdev->xdev->dev, "New device on "
+				 "%04x:%02x:%02x.%02x found.\n", domain, bus,
+				 PCI_SLOT(devfn), PCI_FUNC(devfn));
+	}
+
+	return 0;
+}
+
+static int __devinit pcifront_scan_root(struct pcifront_device *pdev,
+				 unsigned int domain, unsigned int bus)
+{
+	struct pci_bus *b;
+	struct pcifront_sd *sd = NULL;
+	struct pci_bus_entry *bus_entry = NULL;
+	int err = 0;
+
+#ifndef CONFIG_PCI_DOMAINS
+	if (domain != 0) {
+		dev_err(&pdev->xdev->dev,
+			"PCI Root in non-zero PCI Domain! domain=%d\n", domain);
+		dev_err(&pdev->xdev->dev,
+			"Please compile with CONFIG_PCI_DOMAINS\n");
+		err = -EINVAL;
+		goto err_out;
+	}
+#endif
+
+	dev_info(&pdev->xdev->dev, "Creating PCI Frontend Bus %04x:%02x\n",
+		 domain, bus);
+
+	bus_entry = kmalloc(sizeof(*bus_entry), GFP_KERNEL);
+	sd = kmalloc(sizeof(*sd), GFP_KERNEL);
+	if (!bus_entry || !sd) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+	pcifront_init_sd(sd, domain, bus, pdev);
+
+	b = pci_scan_bus_parented(&pdev->xdev->dev, bus,
+				  &pcifront_bus_ops, sd);
+	if (!b) {
+		dev_err(&pdev->xdev->dev,
+			"Error creating PCI Frontend Bus!\n");
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	bus_entry->bus = b;
+
+	list_add(&bus_entry->list, &pdev->root_buses);
+
+	/* pci_scan_bus_parented skips devices which do not have a have
+	* devfn==0. The pcifront_scan_bus enumerates all devfn. */
+	err = pcifront_scan_bus(pdev, domain, bus, b);
+
+	/* Claim resources before going "live" with our devices */
+	pci_walk_bus(b, pcifront_claim_resource, pdev);
+
+	/* Create SysFS and notify udev of the devices. Aka: "going live" */
+	pci_bus_add_devices(b);
+
+	return err;
+
+err_out:
+	kfree(bus_entry);
+	kfree(sd);
+
+	return err;
+}
+
+static int __devinit pcifront_rescan_root(struct pcifront_device *pdev,
+				   unsigned int domain, unsigned int bus)
+{
+	int err;
+	struct pci_bus *b;
+
+#ifndef CONFIG_PCI_DOMAINS
+	if (domain != 0) {
+		dev_err(&pdev->xdev->dev,
+			"PCI Root in non-zero PCI Domain! domain=%d\n", domain);
+		dev_err(&pdev->xdev->dev,
+			"Please compile with CONFIG_PCI_DOMAINS\n");
+		return -EINVAL;
+	}
+#endif
+
+	dev_info(&pdev->xdev->dev, "Rescanning PCI Frontend Bus %04x:%02x\n",
+		 domain, bus);
+
+	b = pci_find_bus(domain, bus);
+	if (!b)
+		/* If the bus is unknown, create it. */
+		return pcifront_scan_root(pdev, domain, bus);
+
+	err = pcifront_scan_bus(pdev, domain, bus, b);
+
+	/* Claim resources before going "live" with our devices */
+	pci_walk_bus(b, pcifront_claim_resource, pdev);
+
+	/* Create SysFS and notify udev of the devices. Aka: "going live" */
+	pci_bus_add_devices(b);
+
+	return err;
+}
+
+static void free_root_bus_devs(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	while (!list_empty(&bus->devices)) {
+		dev = container_of(bus->devices.next, struct pci_dev,
+				   bus_list);
+		dev_dbg(&dev->dev, "removing device\n");
+		pci_remove_bus_device(dev);
+	}
+}
+
+static void pcifront_free_roots(struct pcifront_device *pdev)
+{
+	struct pci_bus_entry *bus_entry, *t;
+
+	dev_dbg(&pdev->xdev->dev, "cleaning up root buses\n");
+
+	list_for_each_entry_safe(bus_entry, t, &pdev->root_buses, list) {
+		list_del(&bus_entry->list);
+
+		free_root_bus_devs(bus_entry->bus);
+
+		kfree(bus_entry->bus->sysdata);
+
+		device_unregister(bus_entry->bus->bridge);
+		pci_remove_bus(bus_entry->bus);
+
+		kfree(bus_entry);
+	}
+}
+
+static pci_ers_result_t pcifront_common_process(int cmd,
+						struct pcifront_device *pdev,
+						pci_channel_state_t state)
+{
+	pci_ers_result_t result;
+	struct pci_driver *pdrv;
+	int bus = pdev->sh_info->aer_op.bus;
+	int devfn = pdev->sh_info->aer_op.devfn;
+	struct pci_dev *pcidev;
+	int flag = 0;
+
+	dev_dbg(&pdev->xdev->dev,
+		"pcifront AER process: cmd %x (bus:%x, devfn%x)",
+		cmd, bus, devfn);
+	result = PCI_ERS_RESULT_NONE;
+
+	pcidev = pci_get_bus_and_slot(bus, devfn);
+	if (!pcidev || !pcidev->driver) {
+		dev_err(&pdev->xdev->dev, "device or AER driver is NULL\n");
+		if (pcidev)
+			pci_dev_put(pcidev);
+		return result;
+	}
+	pdrv = pcidev->driver;
+
+	if (get_driver(&pdrv->driver)) {
+		if (pdrv->err_handler && pdrv->err_handler->error_detected) {
+			dev_dbg(&pcidev->dev,
+				"trying to call AER service\n");
+			if (pcidev) {
+				flag = 1;
+				switch (cmd) {
+				case XEN_PCI_OP_aer_detected:
+					result = pdrv->err_handler->
+						 error_detected(pcidev, state);
+					break;
+				case XEN_PCI_OP_aer_mmio:
+					result = pdrv->err_handler->
+						 mmio_enabled(pcidev);
+					break;
+				case XEN_PCI_OP_aer_slotreset:
+					result = pdrv->err_handler->
+						 slot_reset(pcidev);
+					break;
+				case XEN_PCI_OP_aer_resume:
+					pdrv->err_handler->resume(pcidev);
+					break;
+				default:
+					dev_err(&pdev->xdev->dev,
+						"bad request in aer recovery "
+						"operation!\n");
+
+				}
+			}
+		}
+		put_driver(&pdrv->driver);
+	}
+	if (!flag)
+		result = PCI_ERS_RESULT_NONE;
+
+	return result;
+}
+
+
+static void pcifront_do_aer(struct work_struct *data)
+{
+	struct pcifront_device *pdev =
+		container_of(data, struct pcifront_device, op_work);
+	int cmd = pdev->sh_info->aer_op.cmd;
+	pci_channel_state_t state =
+		(pci_channel_state_t)pdev->sh_info->aer_op.err;
+
+	/*If a pci_conf op is in progress,
+		we have to wait until it is done before service aer op*/
+	dev_dbg(&pdev->xdev->dev,
+		"pcifront service aer bus %x devfn %x\n",
+		pdev->sh_info->aer_op.bus, pdev->sh_info->aer_op.devfn);
+
+	pdev->sh_info->aer_op.err = pcifront_common_process(cmd, pdev, state);
+
+	/* Post the operation to the guest. */
+	wmb();
+	clear_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags);
+	notify_remote_via_evtchn(pdev->evtchn);
+
+	/*in case of we lost an aer request in four lines time_window*/
+	smp_mb__before_clear_bit();
+	clear_bit(_PDEVB_op_active, &pdev->flags);
+	smp_mb__after_clear_bit();
+
+	schedule_pcifront_aer_op(pdev);
+
+}
+
+static irqreturn_t pcifront_handler_aer(int irq, void *dev)
+{
+	struct pcifront_device *pdev = dev;
+	schedule_pcifront_aer_op(pdev);
+	return IRQ_HANDLED;
+}
+static int pcifront_connect(struct pcifront_device *pdev)
+{
+	int err = 0;
+
+	spin_lock(&pcifront_dev_lock);
+
+	if (!pcifront_dev) {
+		dev_info(&pdev->xdev->dev, "Installing PCI frontend\n");
+		pcifront_dev = pdev;
+	} else {
+		dev_err(&pdev->xdev->dev, "PCI frontend already installed!\n");
+		err = -EEXIST;
+	}
+
+	spin_unlock(&pcifront_dev_lock);
+
+	return err;
+}
+
+static void pcifront_disconnect(struct pcifront_device *pdev)
+{
+	spin_lock(&pcifront_dev_lock);
+
+	if (pdev == pcifront_dev) {
+		dev_info(&pdev->xdev->dev,
+			 "Disconnecting PCI Frontend Buses\n");
+		pcifront_dev = NULL;
+	}
+
+	spin_unlock(&pcifront_dev_lock);
+}
+static struct pcifront_device *alloc_pdev(struct xenbus_device *xdev)
+{
+	struct pcifront_device *pdev;
+
+	pdev = kzalloc(sizeof(struct pcifront_device), GFP_KERNEL);
+	if (pdev == NULL)
+		goto out;
+
+	pdev->sh_info =
+	    (struct xen_pci_sharedinfo *)__get_free_page(GFP_KERNEL);
+	if (pdev->sh_info == NULL) {
+		kfree(pdev);
+		pdev = NULL;
+		goto out;
+	}
+	pdev->sh_info->flags = 0;
+
+	/*Flag for registering PV AER handler*/
+	set_bit(_XEN_PCIB_AERHANDLER, (void *)&pdev->sh_info->flags);
+
+	dev_set_drvdata(&xdev->dev, pdev);
+	pdev->xdev = xdev;
+
+	INIT_LIST_HEAD(&pdev->root_buses);
+
+	spin_lock_init(&pdev->sh_info_lock);
+
+	pdev->evtchn = INVALID_EVTCHN;
+	pdev->gnt_ref = INVALID_GRANT_REF;
+	pdev->irq = -1;
+
+	INIT_WORK(&pdev->op_work, pcifront_do_aer);
+
+	dev_dbg(&xdev->dev, "Allocated pdev @ 0x%p pdev->sh_info @ 0x%p\n",
+		pdev, pdev->sh_info);
+out:
+	return pdev;
+}
+
+static void free_pdev(struct pcifront_device *pdev)
+{
+	dev_dbg(&pdev->xdev->dev, "freeing pdev @ 0x%p\n", pdev);
+
+	pcifront_free_roots(pdev);
+
+	cancel_work_sync(&pdev->op_work);
+
+	if (pdev->irq >= 0)
+		unbind_from_irqhandler(pdev->irq, pdev);
+
+	if (pdev->evtchn != INVALID_EVTCHN)
+		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
+
+	if (pdev->gnt_ref != INVALID_GRANT_REF)
+		gnttab_end_foreign_access(pdev->gnt_ref, 0 /* r/w page */,
+					  (unsigned long)pdev->sh_info);
+	else
+		free_page((unsigned long)pdev->sh_info);
+
+	dev_set_drvdata(&pdev->xdev->dev, NULL);
+
+	kfree(pdev);
+}
+
+static int pcifront_publish_info(struct pcifront_device *pdev)
+{
+	int err = 0;
+	struct xenbus_transaction trans;
+
+	err = xenbus_grant_ring(pdev->xdev, virt_to_mfn(pdev->sh_info));
+	if (err < 0)
+		goto out;
+
+	pdev->gnt_ref = err;
+
+	err = xenbus_alloc_evtchn(pdev->xdev, &pdev->evtchn);
+	if (err)
+		goto out;
+
+	err = bind_evtchn_to_irqhandler(pdev->evtchn, pcifront_handler_aer,
+		0, "pcifront", pdev);
+
+	if (err < 0)
+		return err;
+
+	pdev->irq = err;
+
+do_publish:
+	err = xenbus_transaction_start(&trans);
+	if (err) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error writing configuration for backend "
+				 "(start transaction)");
+		goto out;
+	}
+
+	err = xenbus_printf(trans, pdev->xdev->nodename,
+			    "pci-op-ref", "%u", pdev->gnt_ref);
+	if (!err)
+		err = xenbus_printf(trans, pdev->xdev->nodename,
+				    "event-channel", "%u", pdev->evtchn);
+	if (!err)
+		err = xenbus_printf(trans, pdev->xdev->nodename,
+				    "magic", XEN_PCI_MAGIC);
+
+	if (err) {
+		xenbus_transaction_end(trans, 1);
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error writing configuration for backend");
+		goto out;
+	} else {
+		err = xenbus_transaction_end(trans, 0);
+		if (err == -EAGAIN)
+			goto do_publish;
+		else if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error completing transaction "
+					 "for backend");
+			goto out;
+		}
+	}
+
+	xenbus_switch_state(pdev->xdev, XenbusStateInitialised);
+
+	dev_dbg(&pdev->xdev->dev, "publishing successful!\n");
+
+out:
+	return err;
+}
+
+static int __devinit pcifront_try_connect(struct pcifront_device *pdev)
+{
+	int err = -EFAULT;
+	int i, num_roots, len;
+	char str[64];
+	unsigned int domain, bus;
+
+
+	/* Only connect once */
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateInitialised)
+		goto out;
+
+	err = pcifront_connect(pdev);
+	if (err) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error connecting PCI Frontend");
+		goto out;
+	}
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+			   "root_num", "%d", &num_roots);
+	if (err == -ENOENT) {
+		xenbus_dev_error(pdev->xdev, err,
+				 "No PCI Roots found, trying 0000:00");
+		err = pcifront_scan_root(pdev, 0, 0);
+		num_roots = 0;
+	} else if (err != 1) {
+		if (err == 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI roots");
+		goto out;
+	}
+
+	for (i = 0; i < num_roots; i++) {
+		len = snprintf(str, sizeof(str), "root-%d", i);
+		if (unlikely(len >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x", &domain, &bus);
+		if (err != 2) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI root %d", i);
+			goto out;
+		}
+
+		err = pcifront_scan_root(pdev, domain, bus);
+		if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error scanning PCI root %04x:%02x",
+					 domain, bus);
+			goto out;
+		}
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateConnected);
+
+out:
+	return err;
+}
+
+static int pcifront_try_disconnect(struct pcifront_device *pdev)
+{
+	int err = 0;
+	enum xenbus_state prev_state;
+
+
+	prev_state = xenbus_read_driver_state(pdev->xdev->nodename);
+
+	if (prev_state >= XenbusStateClosing)
+		goto out;
+
+	if (prev_state == XenbusStateConnected) {
+		pcifront_free_roots(pdev);
+		pcifront_disconnect(pdev);
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateClosed);
+
+out:
+
+	return err;
+}
+
+static int __devinit pcifront_attach_devices(struct pcifront_device *pdev)
+{
+	int err = -EFAULT;
+	int i, num_roots, len;
+	unsigned int domain, bus;
+	char str[64];
+
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateReconfiguring)
+		goto out;
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+			   "root_num", "%d", &num_roots);
+	if (err == -ENOENT) {
+		xenbus_dev_error(pdev->xdev, err,
+				 "No PCI Roots found, trying 0000:00");
+		err = pcifront_rescan_root(pdev, 0, 0);
+		num_roots = 0;
+	} else if (err != 1) {
+		if (err == 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI roots");
+		goto out;
+	}
+
+	for (i = 0; i < num_roots; i++) {
+		len = snprintf(str, sizeof(str), "root-%d", i);
+		if (unlikely(len >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x", &domain, &bus);
+		if (err != 2) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI root %d", i);
+			goto out;
+		}
+
+		err = pcifront_rescan_root(pdev, domain, bus);
+		if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error scanning PCI root %04x:%02x",
+					 domain, bus);
+			goto out;
+		}
+	}
+
+	xenbus_switch_state(pdev->xdev, XenbusStateConnected);
+
+out:
+	return err;
+}
+
+static int pcifront_detach_devices(struct pcifront_device *pdev)
+{
+	int err = 0;
+	int i, num_devs;
+	unsigned int domain, bus, slot, func;
+	struct pci_bus *pci_bus;
+	struct pci_dev *pci_dev;
+	char str[64];
+
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateConnected)
+		goto out;
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, "num_devs", "%d",
+			   &num_devs);
+	if (err != 1) {
+		if (err >= 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI devices");
+		goto out;
+	}
+
+	/* Find devices being detached and remove them. */
+	for (i = 0; i < num_devs; i++) {
+		int l, state;
+		l = snprintf(str, sizeof(str), "state-%d", i);
+		if (unlikely(l >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str, "%d",
+				   &state);
+		if (err != 1)
+			state = XenbusStateUnknown;
+
+		if (state != XenbusStateClosing)
+			continue;
+
+		/* Remove device. */
+		l = snprintf(str, sizeof(str), "vdev-%d", i);
+		if (unlikely(l >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x:%x.%x", &domain, &bus, &slot, &func);
+		if (err != 4) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI device %d", i);
+			goto out;
+		}
+
+		pci_bus = pci_find_bus(domain, bus);
+		if (!pci_bus) {
+			dev_dbg(&pdev->xdev->dev, "Cannot get bus %04x:%02x\n",
+				domain, bus);
+			continue;
+		}
+		pci_dev = pci_get_slot(pci_bus, PCI_DEVFN(slot, func));
+		if (!pci_dev) {
+			dev_dbg(&pdev->xdev->dev,
+				"Cannot get PCI device %04x:%02x:%02x.%02x\n",
+				domain, bus, slot, func);
+			continue;
+		}
+		pci_remove_bus_device(pci_dev);
+		pci_dev_put(pci_dev);
+
+		dev_dbg(&pdev->xdev->dev,
+			"PCI device %04x:%02x:%02x.%02x removed.\n",
+			domain, bus, slot, func);
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateReconfiguring);
+
+out:
+	return err;
+}
+
+static void __init_refok pcifront_backend_changed(struct xenbus_device *xdev,
+						  enum xenbus_state be_state)
+{
+	struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
+
+	switch (be_state) {
+	case XenbusStateUnknown:
+	case XenbusStateInitialising:
+	case XenbusStateInitWait:
+	case XenbusStateInitialised:
+	case XenbusStateClosed:
+		break;
+
+	case XenbusStateConnected:
+		pcifront_try_connect(pdev);
+		break;
+
+	case XenbusStateClosing:
+		dev_warn(&xdev->dev, "backend going away!\n");
+		pcifront_try_disconnect(pdev);
+		break;
+
+	case XenbusStateReconfiguring:
+		pcifront_detach_devices(pdev);
+		break;
+
+	case XenbusStateReconfigured:
+		pcifront_attach_devices(pdev);
+		break;
+	}
+}
+
+static int pcifront_xenbus_probe(struct xenbus_device *xdev,
+				 const struct xenbus_device_id *id)
+{
+	int err = 0;
+	struct pcifront_device *pdev = alloc_pdev(xdev);
+
+	if (pdev == NULL) {
+		err = -ENOMEM;
+		xenbus_dev_fatal(xdev, err,
+				 "Error allocating pcifront_device struct");
+		goto out;
+	}
+
+	err = pcifront_publish_info(pdev);
+	if (err)
+		free_pdev(pdev);
+
+out:
+	return err;
+}
+
+static int pcifront_xenbus_remove(struct xenbus_device *xdev)
+{
+	struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
+	if (pdev)
+		free_pdev(pdev);
+
+	return 0;
+}
+
+static const struct xenbus_device_id xenpci_ids[] = {
+	{"pci"},
+	{""},
+};
+
+static struct xenbus_driver xenbus_pcifront_driver = {
+	.name			= "pcifront",
+	.owner			= THIS_MODULE,
+	.ids			= xenpci_ids,
+	.probe			= pcifront_xenbus_probe,
+	.remove			= pcifront_xenbus_remove,
+	.otherend_changed	= pcifront_backend_changed,
+};
+
+static int __init pcifront_init(void)
+{
+	if (!xen_pv_domain() || xen_initial_domain())
+		return -ENODEV;
+
+	pci_frontend_registrar(1 /* enable */);
+
+	return xenbus_register_frontend(&xenbus_pcifront_driver);
+}
+
+static void __exit pcifront_cleanup(void)
+{
+	xenbus_unregister_driver(&xenbus_pcifront_driver);
+	pci_frontend_registrar(0 /* disable */);
+}
+module_init(pcifront_init);
+module_exit(pcifront_cleanup);
+
+MODULE_DESCRIPTION("Xen PCI passthrough frontend.");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("xen:pci");