Merge commit 'v2.6.38-rc1' into kbuild/packaging

75 files changed, 5368 insertions, 1879 deletions

diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index b1ecefa2a23d..a9523fdc6911 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -19,18 +19,7 @@ config PCI_MSI
            by using the 'pci=nomsi' option.  This disables MSI for the
            entire system.
 
-           If you don't know what to do here, say N.
-
-config PCI_LEGACY
-        bool "Enable deprecated pci_find_* API"
-        depends on PCI
-        default y
-        help
-          Say Y here if you want to include support for the deprecated
-          pci_find_device() API.  Most drivers have been converted over
-          to using the proper hotplug APIs, so this option serves to
-          include/exclude only a few drivers that are still using this
-          API.
+           If you don't know what to do here, say Y.
 
 config PCI_DEBUG
         bool "PCI Debugging"
@@ -51,6 +40,28 @@ config PCI_STUB
 
           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
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index 4df48d58eaa6..98e6fdf34d30 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -2,14 +2,13 @@
 # Makefile for the PCI bus specific drivers.
 #
 
-obj-y           += access.o bus.o probe.o remove.o pci.o quirks.o \
+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
+                        irq.o vpd.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_SYSFS) += slot.o
 
-obj-$(CONFIG_PCI_LEGACY) += legacy.o
-CFLAGS_legacy.o += -Wno-deprecated-declarations
+obj-$(CONFIG_PCI_QUIRKS) += quirks.o
 
 # Build PCI Express stuff if needed
 obj-$(CONFIG_PCIEPORTBUS) += pcie/
@@ -49,12 +48,17 @@ obj-$(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
 
 #
 # ACPI Related PCI FW Functions
 #
 obj-$(CONFIG_ACPI)    += pci-acpi.o
 
+# SMBIOS provided firmware instance and labels
+obj-$(CONFIG_DMI)    += pci-label.o
+
 # Cardbus & CompactPCI use setup-bus
 obj-$(CONFIG_HOTPLUG) += setup-bus.o
 
@@ -62,6 +66,6 @@ obj-$(CONFIG_PCI_SYSCALL) += syscall.o
 
 obj-$(CONFIG_PCI_STUB) += pci-stub.o
 
-ifeq ($(CONFIG_PCI_DEBUG),y)
-EXTRA_CFLAGS += -DDEBUG
-endif
+obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o
+
+ccflags-$(CONFIG_PCI_DEBUG) := -DDEBUG
diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index db23200c4874..531bc697d800 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -2,6 +2,7 @@
 #include <linux/pci.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/ioport.h>
 #include <linux/wait.h>
 
@@ -12,7 +13,7 @@
  * configuration space.
  */
 
-static DEFINE_SPINLOCK(pci_lock);
+static DEFINE_RAW_SPINLOCK(pci_lock);
 
 /*
  *  Wrappers for all PCI configuration access functions.  They just check
@@ -32,10 +33,10 @@ int pci_bus_read_config_##size \
         unsigned long flags;                                            \
         u32 data = 0;                                                   \
         if (PCI_##size##_BAD) return PCIBIOS_BAD_REGISTER_NUMBER;       \
-        spin_lock_irqsave(&pci_lock, flags);                            \
+        raw_spin_lock_irqsave(&pci_lock, flags);                        \
         res = bus->ops->read(bus, devfn, pos, len, &data);              \
         *value = (type)data;                                            \
-        spin_unlock_irqrestore(&pci_lock, flags);                       \
+        raw_spin_unlock_irqrestore(&pci_lock, flags);           \
         return res;                                                     \
 }
 
@@ -46,9 +47,9 @@ int pci_bus_write_config_##size \
         int res;                                                        \
         unsigned long flags;                                            \
         if (PCI_##size##_BAD) return PCIBIOS_BAD_REGISTER_NUMBER;       \
-        spin_lock_irqsave(&pci_lock, flags);                            \
+        raw_spin_lock_irqsave(&pci_lock, flags);                        \
         res = bus->ops->write(bus, devfn, pos, len, value);             \
-        spin_unlock_irqrestore(&pci_lock, flags);                       \
+        raw_spin_unlock_irqrestore(&pci_lock, flags);           \
         return res;                                                     \
 }
 
@@ -78,10 +79,10 @@ struct pci_ops *pci_bus_set_ops(struct pci_bus *bus, struct pci_ops *ops)
         struct pci_ops *old_ops;
         unsigned long flags;
 
-        spin_lock_irqsave(&pci_lock, flags);
+        raw_spin_lock_irqsave(&pci_lock, flags);
         old_ops = bus->ops;
         bus->ops = ops;
-        spin_unlock_irqrestore(&pci_lock, flags);
+        raw_spin_unlock_irqrestore(&pci_lock, flags);
         return old_ops;
 }
 EXPORT_SYMBOL(pci_bus_set_ops);
@@ -135,9 +136,9 @@ static noinline void pci_wait_ucfg(struct pci_dev *dev)
         __add_wait_queue(&pci_ucfg_wait, &wait);
         do {
                 set_current_state(TASK_UNINTERRUPTIBLE);
-                spin_unlock_irq(&pci_lock);
+                raw_spin_unlock_irq(&pci_lock);
                 schedule();
-                spin_lock_irq(&pci_lock);
+                raw_spin_lock_irq(&pci_lock);
         } while (dev->block_ucfg_access);
         __remove_wait_queue(&pci_ucfg_wait, &wait);
 }
@@ -149,11 +150,11 @@ int pci_user_read_config_##size						\
         int ret = 0;                                                    \
         u32 data = -1;                                                  \
         if (PCI_##size##_BAD) return PCIBIOS_BAD_REGISTER_NUMBER;       \
-        spin_lock_irq(&pci_lock);                                       \
+        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);      \
-        spin_unlock_irq(&pci_lock);                                     \
+        raw_spin_unlock_irq(&pci_lock);                         \
         *val = (type)data;                                              \
         return ret;                                                     \
 }
@@ -164,11 +165,11 @@ int pci_user_write_config_##size					\
 {                                                                       \
         int ret = -EIO;                                                 \
         if (PCI_##size##_BAD) return PCIBIOS_BAD_REGISTER_NUMBER;       \
-        spin_lock_irq(&pci_lock);                                       \
+        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);        \
-        spin_unlock_irq(&pci_lock);                                     \
+        raw_spin_unlock_irq(&pci_lock);                         \
         return ret;                                                     \
 }
 
@@ -219,8 +220,13 @@ static int pci_vpd_pci22_wait(struct pci_dev *dev)
                         return 0;
                 }
 
-                if (time_after(jiffies, timeout))
+                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())
@@ -395,10 +401,10 @@ void pci_block_user_cfg_access(struct pci_dev *dev)
         unsigned long flags;
         int was_blocked;
 
-        spin_lock_irqsave(&pci_lock, flags);
+        raw_spin_lock_irqsave(&pci_lock, flags);
         was_blocked = dev->block_ucfg_access;
         dev->block_ucfg_access = 1;
-        spin_unlock_irqrestore(&pci_lock, flags);
+        raw_spin_unlock_irqrestore(&pci_lock, flags);
 
         /* If we BUG() inside the pci_lock, we're guaranteed to hose
          * the machine */
@@ -416,7 +422,7 @@ void pci_unblock_user_cfg_access(struct pci_dev *dev)
 {
         unsigned long flags;
 
-        spin_lock_irqsave(&pci_lock, 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. */
@@ -424,6 +430,6 @@ void pci_unblock_user_cfg_access(struct pci_dev *dev)
 
         dev->block_ucfg_access = 0;
         wake_up_all(&pci_ucfg_wait);
-        spin_unlock_irqrestore(&pci_lock, flags);
+        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
index cef28a79103f..69546e9213dd 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -14,9 +14,56 @@
 #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
@@ -36,11 +83,14 @@ 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,
-                void (*alignf)(void *, struct resource *, resource_size_t,
-                                resource_size_t),
+                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;
@@ -49,8 +99,7 @@ pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res,
         if (!(res->flags & IORESOURCE_MEM_64))
                 max = PCIBIOS_MAX_MEM_32;
 
-        for (i = 0; i < PCI_BUS_NUM_RESOURCES; i++) {
-                struct resource *r = bus->resource[i];
+        pci_bus_for_each_resource(bus, r, i) {
                 if (!r)
                         continue;
 
@@ -191,6 +240,8 @@ void pci_enable_bridges(struct pci_bus *bus)
                 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);
@@ -240,14 +291,15 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
                         next = dev->bus_list.next;
 
                 /* Run device routines with the device locked */
-                down(&dev->dev.sem);
+                device_lock(&dev->dev);
                 retval = cb(dev, userdata);
-                up(&dev->dev.sem);
+                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);
diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index 83aae4747594..09933eb9126b 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -35,6 +35,8 @@
 #include <linux/interrupt.h>
 #include <linux/tboot.h>
 #include <linux/dmi.h>
+#include <linux/slab.h>
+#include <asm/iommu_table.h>
 
 #define PREFIX "DMAR: "
 
@@ -130,9 +132,10 @@ static int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
                 if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT ||
                     scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE)
                         (*cnt)++;
-                else
+                else if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_IOAPIC) {
                         printk(KERN_WARNING PREFIX
-                                "Unsupported device scope\n");
+                               "Unsupported device scope\n");
+                }
                 start += scope->length;
         }
         if (*cnt == 0)
@@ -308,6 +311,8 @@ int dmar_find_matched_atsr_unit(struct pci_dev *dev)
         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))
@@ -357,12 +362,14 @@ dmar_parse_one_rhsa(struct acpi_dmar_header *header)
                         return 0;
                 }
         }
-        WARN(1, "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));
+        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;
 }
@@ -506,7 +513,7 @@ parse_dmar_table(void)
         return ret;
 }
 
-int dmar_pci_device_match(struct pci_dev *devices[], int cnt,
+static int dmar_pci_device_match(struct pci_dev *devices[], int cnt,
                           struct pci_dev *dev)
 {
         int index;
@@ -529,6 +536,8 @@ 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,
@@ -613,7 +622,17 @@ int __init dmar_table_init(void)
         return 0;
 }
 
-static int bios_warned;
+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)
 {
@@ -639,13 +658,7 @@ int __init check_zero_address(void)
 
                         drhd = (void *)entry_header;
                         if (!drhd->address) {
-                                /* Promote an attitude of violence to a BIOS engineer today */
-                                WARN(1, "Your BIOS is broken; DMAR reported at address zero!\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));
-                                bios_warned = 1;
+                                warn_invalid_dmar(0, "");
                                 goto failed;
                         }
 
@@ -658,14 +671,8 @@ int __init check_zero_address(void)
                         ecap = dmar_readq(addr + DMAR_ECAP_REG);
                         early_iounmap(addr, VTD_PAGE_SIZE);
                         if (cap == (uint64_t)-1 && ecap == (uint64_t)-1) {
-                                /* Promote an attitude of violence to a BIOS engineer today */
-                                WARN(1, "Your BIOS is broken; DMAR reported at address %llx returns all ones!\n"
-                                     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
-                                      drhd->address,
-                                      dmi_get_system_info(DMI_BIOS_VENDOR),
-                                      dmi_get_system_info(DMI_BIOS_VERSION),
-                                      dmi_get_system_info(DMI_PRODUCT_VERSION));
-                                bios_warned = 1;
+                                warn_invalid_dmar(drhd->address,
+                                                  " returns all ones");
                                 goto failed;
                         }
                 }
@@ -681,7 +688,7 @@ failed:
         return 0;
 }
 
-void __init detect_intel_iommu(void)
+int __init detect_intel_iommu(void)
 {
         int ret;
 
@@ -717,6 +724,8 @@ void __init detect_intel_iommu(void)
         }
         early_acpi_os_unmap_memory(dmar_tbl, dmar_tbl_size);
         dmar_tbl = NULL;
+
+        return ret ? 1 : -ENODEV;
 }
 
 
@@ -730,14 +739,7 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
         int msagaw = 0;
 
         if (!drhd->reg_base_addr) {
-                if (!bios_warned) {
-                        WARN(1, "Your BIOS is broken; DMAR reported at address zero!\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));
-                        bios_warned = 1;
-                }
+                warn_invalid_dmar(0, "");
                 return -EINVAL;
         }
 
@@ -757,16 +759,7 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
         iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG);
 
         if (iommu->cap == (uint64_t)-1 && iommu->ecap == (uint64_t)-1) {
-                if (!bios_warned) {
-                        /* Promote an attitude of violence to a BIOS engineer today */
-                        WARN(1, "Your BIOS is broken; DMAR reported at address %llx returns all ones!\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));
-                        bios_warned = 1;
-                }
+                warn_invalid_dmar(drhd->reg_base_addr, " returns all ones");
                 goto err_unmap;
         }
 
@@ -805,7 +798,8 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
         }
 
         ver = readl(iommu->reg + DMAR_VER_REG);
-        pr_info("IOMMU %llx: ver %d:%d cap %llx ecap %llx\n",
+        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,
@@ -1230,9 +1224,9 @@ const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type)
         }
 }
 
-void dmar_msi_unmask(unsigned int irq)
+void dmar_msi_unmask(struct irq_data *data)
 {
-        struct intel_iommu *iommu = get_irq_data(irq);
+        struct intel_iommu *iommu = irq_data_get_irq_data(data);
         unsigned long flag;
 
         /* unmask it */
@@ -1243,10 +1237,10 @@ void dmar_msi_unmask(unsigned int irq)
         spin_unlock_irqrestore(&iommu->register_lock, flag);
 }
 
-void dmar_msi_mask(unsigned int irq)
+void dmar_msi_mask(struct irq_data *data)
 {
         unsigned long flag;
-        struct intel_iommu *iommu = get_irq_data(irq);
+        struct intel_iommu *iommu = irq_data_get_irq_data(data);
 
         /* mask it */
         spin_lock_irqsave(&iommu->register_lock, flag);
@@ -1423,6 +1417,11 @@ int __init enable_drhd_fault_handling(void)
                                (unsigned long long)drhd->reg_base_addr, ret);
                         return -1;
                 }
+
+                /*
+                 * Clear any previous faults.
+                 */
+                dmar_fault(iommu->irq, iommu);
         }
 
         return 0;
@@ -1456,9 +1455,12 @@ int dmar_reenable_qi(struct intel_iommu *iommu)
 /*
  * Check interrupt remapping support in DMAR table description.
  */
-int dmar_ir_support(void)
+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/acpi_pcihp.c b/drivers/pci/hotplug/acpi_pcihp.c
index 3c76fc67cf0e..3bc72d18b121 100644
--- a/drivers/pci/hotplug/acpi_pcihp.c
+++ b/drivers/pci/hotplug/acpi_pcihp.c
@@ -32,6 +32,7 @@
 #include <linux/pci_hotplug.h>
 #include <linux/acpi.h>
 #include <linux/pci-acpi.h>
+#include <linux/slab.h>
 
 #define MY_NAME "acpi_pcihp"
 
@@ -337,9 +338,7 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev, u32 flags)
         acpi_handle chandle, handle;
         struct acpi_buffer string = { ACPI_ALLOCATE_BUFFER, NULL };
 
-        flags &= (OSC_PCI_EXPRESS_NATIVE_HP_CONTROL |
-                  OSC_SHPC_NATIVE_HP_CONTROL |
-                  OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL);
+        flags &= OSC_SHPC_NATIVE_HP_CONTROL;
         if (!flags) {
                 err("Invalid flags %u specified!\n", flags);
                 return -EINVAL;
@@ -359,7 +358,7 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev, u32 flags)
                 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);
+                status = acpi_pci_osc_control_set(handle, &flags, flags);
                 if (ACPI_SUCCESS(status))
                         goto got_one;
                 if (status == AE_SUPPORT)
diff --git a/drivers/pci/hotplug/acpiphp.h b/drivers/pci/hotplug/acpiphp.h
index bab52047baa8..7722108e78df 100644
--- a/drivers/pci/hotplug/acpiphp.h
+++ b/drivers/pci/hotplug/acpiphp.h
@@ -36,7 +36,6 @@
 #define _ACPIPHP_H
 
 #include <linux/acpi.h>
-#include <linux/kobject.h>
 #include <linux/mutex.h>
 #include <linux/pci_hotplug.h>
 
diff --git a/drivers/pci/hotplug/acpiphp_core.c b/drivers/pci/hotplug/acpiphp_core.c
index 4dd7114964ac..efa9f2de51c1 100644
--- a/drivers/pci/hotplug/acpiphp_core.c
+++ b/drivers/pci/hotplug/acpiphp_core.c
@@ -332,8 +332,6 @@ int acpiphp_register_hotplug_slot(struct acpiphp_slot *acpiphp_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);
-        slot->hotplug_slot->info->max_bus_speed = PCI_SPEED_UNKNOWN;
-        slot->hotplug_slot->info->cur_bus_speed = PCI_SPEED_UNKNOWN;
 
         acpiphp_slot->slot = slot;
         snprintf(name, SLOT_NAME_SIZE, "%llu", slot->acpi_slot->sun);
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 8e952fdab764..cb23aa2ebf96 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -47,6 +47,7 @@
 #include <linux/pci_hotplug.h>
 #include <linux/pci-acpi.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 
 #include "../pci.h"
 #include "acpiphp.h"
@@ -720,12 +721,6 @@ static int acpiphp_bus_add(struct acpiphp_func *func)
                         -ret_val);
                 goto acpiphp_bus_add_out;
         }
-        /*
-         * try to start anyway.  We could have failed to add
-         * simply because this bus had previously been added
-         * on another add.  Don't bother with the return value
-         * we just keep going.
-         */
         ret_val = acpi_bus_start(device);
 
 acpiphp_bus_add_out:
@@ -755,6 +750,24 @@ static int acpiphp_bus_trim(acpi_handle handle)
         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
@@ -811,6 +824,7 @@ static int __ref enable_device(struct acpiphp_slot *slot)
         pci_bus_assign_resources(bus);
         acpiphp_sanitize_bus(bus);
         acpiphp_set_hpp_values(bus);
+        acpiphp_set_acpi_region(slot);
         pci_enable_bridges(bus);
         pci_bus_add_devices(bus);
 
diff --git a/drivers/pci/hotplug/acpiphp_ibm.c b/drivers/pci/hotplug/acpiphp_ibm.c
index aa5df485f8cf..e525263210ee 100644
--- a/drivers/pci/hotplug/acpiphp_ibm.c
+++ b/drivers/pci/hotplug/acpiphp_ibm.c
@@ -26,6 +26,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <acpi/acpi_bus.h>
@@ -107,7 +108,7 @@ 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 kobject *kobj,
+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,
@@ -350,6 +351,7 @@ read_table_done:
 
 /**
  * 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
@@ -363,7 +365,7 @@ read_table_done:
  * 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 kobject *kobj,
+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)
 {
diff --git a/drivers/pci/hotplug/cpcihp_generic.c b/drivers/pci/hotplug/cpcihp_generic.c
index 148fb463b81c..fb3f84661bdc 100644
--- a/drivers/pci/hotplug/cpcihp_generic.c
+++ b/drivers/pci/hotplug/cpcihp_generic.c
@@ -162,6 +162,7 @@ static int __init cpcihp_generic_init(void)
         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;
diff --git a/drivers/pci/hotplug/cpqphp.h b/drivers/pci/hotplug/cpqphp.h
index 9c6a9fd26812..d8ffc7366801 100644
--- a/drivers/pci/hotplug/cpqphp.h
+++ b/drivers/pci/hotplug/cpqphp.h
@@ -310,8 +310,6 @@ struct controller {
         u8 first_slot;
         u8 add_support;
         u8 push_flag;
-        enum pci_bus_speed speed;
-        enum pci_bus_speed speed_capability;
         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 */
diff --git a/drivers/pci/hotplug/cpqphp_core.c b/drivers/pci/hotplug/cpqphp_core.c
index 075b4f4b6e0d..4952c3b9379d 100644
--- a/drivers/pci/hotplug/cpqphp_core.c
+++ b/drivers/pci/hotplug/cpqphp_core.c
@@ -583,30 +583,6 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
         return 0;
 }
 
-static int get_max_bus_speed (struct hotplug_slot *hotplug_slot, enum pci_bus_speed *value)
-{
-        struct slot *slot = hotplug_slot->private;
-        struct controller *ctrl = slot->ctrl;
-
-        dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
-
-        *value = ctrl->speed_capability;
-
-        return 0;
-}
-
-static int get_cur_bus_speed (struct hotplug_slot *hotplug_slot, enum pci_bus_speed *value)
-{
-        struct slot *slot = hotplug_slot->private;
-        struct controller *ctrl = slot->ctrl;
-
-        dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
-
-        *value = ctrl->speed;
-
-        return 0;
-}
-
 static struct hotplug_slot_ops cpqphp_hotplug_slot_ops = {
         .set_attention_status = set_attention_status,
         .enable_slot =          process_SI,
@@ -616,8 +592,6 @@ static struct hotplug_slot_ops cpqphp_hotplug_slot_ops = {
         .get_attention_status = get_attention_status,
         .get_latch_status =     get_latch_status,
         .get_adapter_status =   get_adapter_status,
-        .get_max_bus_speed =    get_max_bus_speed,
-        .get_cur_bus_speed =    get_cur_bus_speed,
 };
 
 #define SLOT_NAME_SIZE 10
@@ -629,6 +603,7 @@ static int ctrl_slot_setup(struct controller *ctrl,
         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;
@@ -694,7 +669,7 @@ static int ctrl_slot_setup(struct controller *ctrl,
                         slot->capabilities |= PCISLOT_64_BIT_SUPPORTED;
                 if (is_slot66mhz(slot))
                         slot->capabilities |= PCISLOT_66_MHZ_SUPPORTED;
-                if (ctrl->speed == PCI_SPEED_66MHz)
+                if (bus->cur_bus_speed == PCI_SPEED_66MHz)
                         slot->capabilities |= PCISLOT_66_MHZ_OPERATION;
 
                 ctrl_slot =
@@ -844,6 +819,7 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
         u32 rc;
         struct controller *ctrl;
         struct pci_func *func;
+        struct pci_bus *bus;
         int err;
 
         err = pci_enable_device(pdev);
@@ -853,6 +829,14 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
                 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
          */
@@ -871,7 +855,7 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
                 goto err_disable_device;
         }
 
-        /* Check for the proper subsytem ID's
+        /* 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.
@@ -929,22 +913,22 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
                         pci_read_config_byte(pdev, 0x41, &bus_cap);
                         if (bus_cap & 0x80) {
                                 dbg("bus max supports 133MHz PCI-X\n");
-                                ctrl->speed_capability = PCI_SPEED_133MHz_PCIX;
+                                bus->max_bus_speed = PCI_SPEED_133MHz_PCIX;
                                 break;
                         }
                         if (bus_cap & 0x40) {
                                 dbg("bus max supports 100MHz PCI-X\n");
-                                ctrl->speed_capability = PCI_SPEED_100MHz_PCIX;
+                                bus->max_bus_speed = PCI_SPEED_100MHz_PCIX;
                                 break;
                         }
                         if (bus_cap & 20) {
                                 dbg("bus max supports 66MHz PCI-X\n");
-                                ctrl->speed_capability = PCI_SPEED_66MHz_PCIX;
+                                bus->max_bus_speed = PCI_SPEED_66MHz_PCIX;
                                 break;
                         }
                         if (bus_cap & 10) {
                                 dbg("bus max supports 66MHz PCI\n");
-                                ctrl->speed_capability = PCI_SPEED_66MHz;
+                                bus->max_bus_speed = PCI_SPEED_66MHz;
                                 break;
                         }
 
@@ -955,7 +939,7 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
                 case PCI_SUB_HPC_ID:
                         /* Original 6500/7000 implementation */
                         ctrl->slot_switch_type = 1;
-                        ctrl->speed_capability = PCI_SPEED_33MHz;
+                        bus->max_bus_speed = PCI_SPEED_33MHz;
                         ctrl->push_button = 0;
                         ctrl->pci_config_space = 1;
                         ctrl->defeature_PHP = 1;
@@ -966,7 +950,7 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
                         /* First Pushbutton implementation */
                         ctrl->push_flag = 1;
                         ctrl->slot_switch_type = 1;
-                        ctrl->speed_capability = PCI_SPEED_33MHz;
+                        bus->max_bus_speed = PCI_SPEED_33MHz;
                         ctrl->push_button = 1;
                         ctrl->pci_config_space = 1;
                         ctrl->defeature_PHP = 1;
@@ -976,7 +960,7 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
                 case PCI_SUB_HPC_ID_INTC:
                         /* Third party (6500/7000) */
                         ctrl->slot_switch_type = 1;
-                        ctrl->speed_capability = PCI_SPEED_33MHz;
+                        bus->max_bus_speed = PCI_SPEED_33MHz;
                         ctrl->push_button = 0;
                         ctrl->pci_config_space = 1;
                         ctrl->defeature_PHP = 1;
@@ -987,7 +971,7 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
                         /* First 66 Mhz implementation */
                         ctrl->push_flag = 1;
                         ctrl->slot_switch_type = 1;
-                        ctrl->speed_capability = PCI_SPEED_66MHz;
+                        bus->max_bus_speed = PCI_SPEED_66MHz;
                         ctrl->push_button = 1;
                         ctrl->pci_config_space = 1;
                         ctrl->defeature_PHP = 1;
@@ -998,7 +982,7 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
                         /* First PCI-X implementation, 100MHz */
                         ctrl->push_flag = 1;
                         ctrl->slot_switch_type = 1;
-                        ctrl->speed_capability = PCI_SPEED_100MHz_PCIX;
+                        bus->max_bus_speed = PCI_SPEED_100MHz_PCIX;
                         ctrl->push_button = 1;
                         ctrl->pci_config_space = 1;
                         ctrl->defeature_PHP = 1;
@@ -1015,9 +999,9 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
         case PCI_VENDOR_ID_INTEL:
                 /* Check for speed capability (0=33, 1=66) */
                 if (subsystem_deviceid & 0x0001)
-                        ctrl->speed_capability = PCI_SPEED_66MHz;
+                        bus->max_bus_speed = PCI_SPEED_66MHz;
                 else
-                        ctrl->speed_capability = PCI_SPEED_33MHz;
+                        bus->max_bus_speed = PCI_SPEED_33MHz;
 
                 /* Check for push button */
                 if (subsystem_deviceid & 0x0002)
@@ -1079,7 +1063,7 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
                                         pdev->bus->number);
 
         dbg("Hotplug controller capabilities:\n");
-        dbg("    speed_capability       %d\n", ctrl->speed_capability);
+        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 ?
@@ -1098,13 +1082,12 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
         /* make our own copy of the pci bus structure,
          * as we like tweaking it a lot */
-        ctrl->pci_bus = kmalloc(sizeof(*ctrl->pci_bus), GFP_KERNEL);
+        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;
         }
-        memcpy(ctrl->pci_bus, pdev->bus, sizeof(*ctrl->pci_bus));
 
         ctrl->bus = pdev->bus->number;
         ctrl->rev = pdev->revision;
@@ -1142,7 +1125,7 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
         }
 
         /* Check for 66Mhz operation */
-        ctrl->speed = get_controller_speed(ctrl);
+        bus->cur_bus_speed = get_controller_speed(ctrl);
 
 
         /********************************************************
diff --git a/drivers/pci/hotplug/cpqphp_ctrl.c b/drivers/pci/hotplug/cpqphp_ctrl.c
index 0ff689afa757..e43908d9b5df 100644
--- a/drivers/pci/hotplug/cpqphp_ctrl.c
+++ b/drivers/pci/hotplug/cpqphp_ctrl.c
@@ -1130,12 +1130,13 @@ static int is_bridge(struct pci_func * func)
 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 (ctrl->speed == adapter_speed)
+        if (bus->cur_bus_speed == adapter_speed)
                 return 0;
 
         /* We don't allow freq/mode changes if we find another adapter running
@@ -1152,7 +1153,7 @@ static u8 set_controller_speed(struct controller *ctrl, u8 adapter_speed, u8 hp_
                  * lower speed/mode, we allow the new adapter to function at
                  * this rate if supported
                  */
-                if (ctrl->speed < adapter_speed)
+                if (bus->cur_bus_speed < adapter_speed)
                         return 0;
 
                 return 1;
@@ -1161,20 +1162,20 @@ static u8 set_controller_speed(struct controller *ctrl, u8 adapter_speed, u8 hp_
         /* If the controller doesn't support freq/mode changes and the
          * controller is running at a higher mode, we bail
          */
-        if ((ctrl->speed > adapter_speed) && (!ctrl->pcix_speed_capability))
+        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 ((ctrl->speed < adapter_speed) && (!ctrl->pcix_speed_capability))
+        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 (ctrl->speed_capability < adapter_speed) {
-                if (ctrl->speed == ctrl->speed_capability)
+        if (bus->max_bus_speed < adapter_speed) {
+                if (bus->cur_bus_speed == bus->max_bus_speed)
                         return 0;
-                adapter_speed = ctrl->speed_capability;
+                adapter_speed = bus->max_bus_speed;
         }
 
         writel(0x0L, ctrl->hpc_reg + LED_CONTROL);
@@ -1229,8 +1230,8 @@ static u8 set_controller_speed(struct controller *ctrl, u8 adapter_speed, u8 hp_
         pci_write_config_byte(ctrl->pci_dev, 0x43, reg);
 
         /* Only if mode change...*/
-        if (((ctrl->speed == PCI_SPEED_66MHz) && (adapter_speed == PCI_SPEED_66MHz_PCIX)) ||
-                ((ctrl->speed == PCI_SPEED_66MHz_PCIX) && (adapter_speed == PCI_SPEED_66MHz))) 
+        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);
@@ -1243,7 +1244,7 @@ static u8 set_controller_speed(struct controller *ctrl, u8 adapter_speed, u8 hp_
         set_SOGO(ctrl);
         wait_for_ctrl_irq(ctrl);
 
-        ctrl->speed = adapter_speed;
+        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",
@@ -1269,6 +1270,7 @@ static u8 set_controller_speed(struct controller *ctrl, u8 adapter_speed, u8 hp_
  */
 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;
@@ -1309,7 +1311,7 @@ static u32 board_replaced(struct pci_func *func, struct controller *ctrl)
                 wait_for_ctrl_irq (ctrl);
 
                 adapter_speed = get_adapter_speed(ctrl, hp_slot);
-                if (ctrl->speed != adapter_speed)
+                if (bus->cur_bus_speed != adapter_speed)
                         if (set_controller_speed(ctrl, adapter_speed, hp_slot))
                                 rc = WRONG_BUS_FREQUENCY;
 
@@ -1426,6 +1428,7 @@ static u32 board_added(struct pci_func *func, struct controller *ctrl)
         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;
 
@@ -1456,7 +1459,7 @@ static u32 board_added(struct pci_func *func, struct controller *ctrl)
         wait_for_ctrl_irq (ctrl);
 
         adapter_speed = get_adapter_speed(ctrl, hp_slot);
-        if (ctrl->speed != adapter_speed)
+        if (bus->cur_bus_speed != adapter_speed)
                 if (set_controller_speed(ctrl, adapter_speed, hp_slot))
                         rc = WRONG_BUS_FREQUENCY;
 
diff --git a/drivers/pci/hotplug/cpqphp_sysfs.c b/drivers/pci/hotplug/cpqphp_sysfs.c
index e6089bdb6e5b..4cb30447a486 100644
--- a/drivers/pci/hotplug/cpqphp_sysfs.c
+++ b/drivers/pci/hotplug/cpqphp_sysfs.c
@@ -28,15 +28,17 @@
 
 #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/smp_lock.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;
@@ -146,7 +148,7 @@ static int open(struct inode *inode, struct file *file)
         struct ctrl_dbg *dbg;
         int retval = -ENOMEM;
 
-        lock_kernel();
+        mutex_lock(&cpqphp_mutex);
         dbg = kmalloc(sizeof(*dbg), GFP_KERNEL);
         if (!dbg)
                 goto exit;
@@ -159,7 +161,7 @@ static int open(struct inode *inode, struct file *file)
         file->private_data = dbg;
         retval = 0;
 exit:
-        unlock_kernel();
+        mutex_unlock(&cpqphp_mutex);
         return retval;
 }
 
@@ -168,7 +170,7 @@ static loff_t lseek(struct file *file, loff_t off, int whence)
         struct ctrl_dbg *dbg;
         loff_t new = -1;
 
-        lock_kernel();
+        mutex_lock(&cpqphp_mutex);
         dbg = file->private_data;
 
         switch (whence) {
@@ -180,10 +182,10 @@ static loff_t lseek(struct file *file, loff_t off, int whence)
                 break;
         }
         if (new < 0 || new > dbg->size) {
-                unlock_kernel();
+                mutex_unlock(&cpqphp_mutex);
                 return -EINVAL;
         }
-        unlock_kernel();
+        mutex_unlock(&cpqphp_mutex);
         return (file->f_pos = new);
 }
 
diff --git a/drivers/pci/hotplug/fakephp.c b/drivers/pci/hotplug/fakephp.c
index 6151389fd903..17d10e2e8fb6 100644
--- a/drivers/pci/hotplug/fakephp.c
+++ b/drivers/pci/hotplug/fakephp.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/pci.h>
 #include <linux/device.h>
+#include <linux/slab.h>
 #include "../pci.h"
 
 struct legacy_slot {
@@ -73,7 +74,7 @@ static void legacy_release(struct kobject *kobj)
 }
 
 static struct kobj_type legacy_ktype = {
-        .sysfs_ops = &(struct sysfs_ops){
+        .sysfs_ops = &(const struct sysfs_ops){
                 .store = legacy_store, .show = legacy_show
         },
         .release = &legacy_release,
@@ -134,7 +135,7 @@ static int __init init_legacy(void)
         struct pci_dev *pdev = NULL;
 
         /* Add existing devices */
-        while ((pdev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, pdev)))
+        for_each_pci_dev(pdev)
                 legacy_add_slot(pdev);
 
         /* Be alerted of any new ones */
diff --git a/drivers/pci/hotplug/ibmphp_core.c b/drivers/pci/hotplug/ibmphp_core.c
index 7485ffda950c..d934dd4fa873 100644
--- a/drivers/pci/hotplug/ibmphp_core.c
+++ b/drivers/pci/hotplug/ibmphp_core.c
@@ -395,89 +395,40 @@ static int get_adapter_present(struct hotplug_slot *hotplug_slot, u8 * value)
         return rc;
 }
 
-static int get_max_bus_speed(struct hotplug_slot *hotplug_slot, enum pci_bus_speed *value)
+static int get_max_bus_speed(struct slot *slot)
 {
-        int rc = -ENODEV;
-        struct slot *pslot;
+        int rc;
         u8 mode = 0;
+        enum pci_bus_speed speed;
+        struct pci_bus *bus = slot->hotplug_slot->pci_slot->bus;
 
-        debug("%s - Entry hotplug_slot[%p] pvalue[%p]\n", __func__,
-                hotplug_slot, value);
+        debug("%s - Entry slot[%p]\n", __func__, slot);
 
         ibmphp_lock_operations();
-
-        if (hotplug_slot) {
-                pslot = hotplug_slot->private;
-                if (pslot) {
-                        rc = 0;
-                        mode = pslot->supported_bus_mode;
-                        *value = pslot->supported_speed; 
-                        switch (*value) {
-                        case BUS_SPEED_33:
-                                break;
-                        case BUS_SPEED_66:
-                                if (mode == BUS_MODE_PCIX) 
-                                        *value += 0x01;
-                                break;
-                        case BUS_SPEED_100:
-                        case BUS_SPEED_133:
-                                *value = pslot->supported_speed + 0x01;
-                                break;
-                        default:
-                                /* Note (will need to change): there would be soon 256, 512 also */
-                                rc = -ENODEV;
-                        }
-                }
-        }
-
+        mode = slot->supported_bus_mode;
+        speed = slot->supported_speed; 
         ibmphp_unlock_operations();
-        debug("%s - Exit rc[%d] value[%x]\n", __func__, rc, *value);
-        return rc;
-}
 
-static int get_cur_bus_speed(struct hotplug_slot *hotplug_slot, enum pci_bus_speed *value)
-{
-        int rc = -ENODEV;
-        struct slot *pslot;
-        u8 mode = 0;
-
-        debug("%s - Entry hotplug_slot[%p] pvalue[%p]\n", __func__,
-                hotplug_slot, value);
-
-        ibmphp_lock_operations();
-
-        if (hotplug_slot) {
-                pslot = hotplug_slot->private;
-                if (pslot) {
-                        rc = get_cur_bus_info(&pslot);
-                        if (!rc) {
-                                mode = pslot->bus_on->current_bus_mode;
-                                *value = pslot->bus_on->current_speed;
-                                switch (*value) {
-                                case BUS_SPEED_33:
-                                        break;
-                                case BUS_SPEED_66:
-                                        if (mode == BUS_MODE_PCIX) 
-                                                *value += 0x01;
-                                        else if (mode == BUS_MODE_PCI)
-                                                ;
-                                        else
-                                                *value = PCI_SPEED_UNKNOWN;
-                                        break;
-                                case BUS_SPEED_100:
-                                case BUS_SPEED_133:
-                                        *value += 0x01;
-                                        break;
-                                default:
-                                        /* Note of change: there would also be 256, 512 soon */
-                                        rc = -ENODEV;
-                                }
-                        }
-                }
+        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;
         }
 
-        ibmphp_unlock_operations();
-        debug("%s - Exit rc[%d] value[%x]\n", __func__, rc, *value);
+        if (!rc)
+                bus->max_bus_speed = speed;
+
+        debug("%s - Exit rc[%d] speed[%x]\n", __func__, rc, speed);
         return rc;
 }
 
@@ -572,6 +523,7 @@ static int __init init_ops(void)
                 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))
@@ -655,6 +607,7 @@ static int validate(struct slot *slot_cur, int opn)
 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;
@@ -700,8 +653,7 @@ int ibmphp_update_slot_info(struct slot *slot_cur)
                         bus_speed = PCI_SPEED_UNKNOWN;
         }
 
-        info->cur_bus_speed = bus_speed;
-        info->max_bus_speed = slot_cur->hotplug_slot->info->max_bus_speed;
+        bus->cur_bus_speed = bus_speed;
         // To do: bus_names 
         
         rc = pci_hp_change_slot_info(slot_cur->hotplug_slot, info);
@@ -1326,8 +1278,6 @@ struct hotplug_slot_ops ibmphp_hotplug_slot_ops = {
         .get_attention_status =         get_attention_status,
         .get_latch_status =             get_latch_status,
         .get_adapter_status =           get_adapter_present,
-        .get_max_bus_speed =            get_max_bus_speed,
-        .get_cur_bus_speed =            get_cur_bus_speed,
 /*      .get_max_adapter_speed =        get_max_adapter_speed,
         .get_bus_name_status =          get_bus_name,
 */
diff --git a/drivers/pci/hotplug/ibmphp_ebda.c b/drivers/pci/hotplug/ibmphp_ebda.c
index c1abac8ab5c3..2850e64dedae 100644
--- a/drivers/pci/hotplug/ibmphp_ebda.c
+++ b/drivers/pci/hotplug/ibmphp_ebda.c
@@ -245,7 +245,7 @@ static void __init print_ebda_hpc (void)
 
 int __init ibmphp_access_ebda (void)
 {
-        u8 format, num_ctlrs, rio_complete, hs_complete;
+        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;
 
@@ -260,13 +260,28 @@ int __init ibmphp_access_ebda (void)
         iounmap (io_mem);
         debug ("returned ebda segment: %x\n", ebda_seg);
         
-        io_mem = ioremap(ebda_seg<<4, 1024);
+        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;
diff --git a/drivers/pci/hotplug/ibmphp_hpc.c b/drivers/pci/hotplug/ibmphp_hpc.c
index c7084f0eca5a..f59ed30512b5 100644
--- a/drivers/pci/hotplug/ibmphp_hpc.c
+++ b/drivers/pci/hotplug/ibmphp_hpc.c
@@ -35,6 +35,7 @@
 #include <linux/init.h>
 #include <linux/mutex.h>
 #include <linux/sched.h>
+#include <linux/semaphore.h>
 #include <linux/kthread.h>
 #include "ibmphp.h"
 
@@ -132,8 +133,8 @@ void __init ibmphp_hpc_initvars (void)
         debug ("%s - Entry\n", __func__);
 
         mutex_init(&sem_hpcaccess);
-        init_MUTEX (&semOperations);
-        init_MUTEX_LOCKED (&sem_exit);
+        sema_init(&semOperations, 1);
+        sema_init(&sem_exit, 0);
         to_debug = 0;
 
         debug ("%s - Exit\n", __func__);
diff --git a/drivers/pci/hotplug/ibmphp_res.c b/drivers/pci/hotplug/ibmphp_res.c
index ec73294d1fa6..e2dc289f767c 100644
--- a/drivers/pci/hotplug/ibmphp_res.c
+++ b/drivers/pci/hotplug/ibmphp_res.c
@@ -40,7 +40,7 @@ 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_range (int type, struct range_node *, 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);
 
@@ -133,7 +133,7 @@ static int __init alloc_bus_range (struct bus_node **new_bus, struct range_node
                 newrange->rangeno = 1;
         else {
                 /* need to insert our range */
-                add_range (flag, newrange, newbus);
+                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);
         }
 
@@ -384,7 +384,7 @@ int __init ibmphp_rsrc_init (void)
  * Input: type of the resource, range to add, current bus
  * Output: 0 or -1, bus and range ptrs 
  ********************************************************************************/
-static int add_range (int type, struct range_node *range, struct bus_node *bus_cur)
+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;
@@ -455,7 +455,7 @@ static int add_range (int type, struct range_node *range, struct bus_node *bus_c
 
 /*******************************************************************************
  * 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_range fnc
+ * 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
  ******************************************************************************/
@@ -1999,7 +1999,7 @@ static int __init update_bridge_ranges (struct bus_node **bus)
 
                                                         if (bus_sec->noIORanges > 0) {
                                                                 if (!range_exists_already (range, bus_sec, IO)) {
-                                                                        add_range (IO, range, bus_sec);
+                                                                        add_bus_range (IO, range, bus_sec);
                                                                         ++bus_sec->noIORanges;
                                                                 } else {
                                                                         kfree (range);
@@ -2048,7 +2048,7 @@ static int __init update_bridge_ranges (struct bus_node **bus)
 
                                                         if (bus_sec->noMemRanges > 0) {
                                                                 if (!range_exists_already (range, bus_sec, MEM)) {
-                                                                        add_range (MEM, range, bus_sec);
+                                                                        add_bus_range (MEM, range, bus_sec);
                                                                         ++bus_sec->noMemRanges;
                                                                 } else {
                                                                         kfree (range);
@@ -2102,7 +2102,7 @@ static int __init update_bridge_ranges (struct bus_node **bus)
 
                                                         if (bus_sec->noPFMemRanges > 0) {
                                                                 if (!range_exists_already (range, bus_sec, PFMEM)) {
-                                                                        add_range (PFMEM, range, bus_sec);
+                                                                        add_bus_range (PFMEM, range, bus_sec);
                                                                         ++bus_sec->noPFMemRanges;
                                                                 } else {
                                                                         kfree (range);
diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c
index 38183a534b65..6d2eea93298f 100644
--- a/drivers/pci/hotplug/pci_hotplug_core.c
+++ b/drivers/pci/hotplug/pci_hotplug_core.c
@@ -33,7 +33,6 @@
 #include <linux/kobject.h>
 #include <linux/sysfs.h>
 #include <linux/pagemap.h>
-#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
@@ -64,32 +63,6 @@ static int debug;
 static LIST_HEAD(pci_hotplug_slot_list);
 static DEFINE_MUTEX(pci_hp_mutex);
 
-/* these strings match up with the values in pci_bus_speed */
-static 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 */
-        NULL,                   /* 0x0c */
-        NULL,                   /* 0x0d */
-        NULL,                   /* 0x0e */
-        NULL,                   /* 0x0f */
-        NULL,                   /* 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 */
-};
-
 #ifdef CONFIG_HOTPLUG_PCI_CPCI
 extern int cpci_hotplug_init(int debug);
 extern void cpci_hotplug_exit(void);
@@ -118,8 +91,6 @@ GET_STATUS(power_status, u8)
 GET_STATUS(attention_status, u8)
 GET_STATUS(latch_status, u8)
 GET_STATUS(adapter_status, u8)
-GET_STATUS(max_bus_speed, enum pci_bus_speed)
-GET_STATUS(cur_bus_speed, enum pci_bus_speed)
 
 static ssize_t power_read_file(struct pci_slot *slot, char *buf)
 {
@@ -263,60 +234,6 @@ static struct pci_slot_attribute hotplug_slot_attr_presence = {
         .show = presence_read_file,
 };
 
-static char *unknown_speed = "Unknown bus speed";
-
-static ssize_t max_bus_speed_read_file(struct pci_slot *slot, char *buf)
-{
-        char *speed_string;
-        int retval;
-        enum pci_bus_speed value;
-        
-        retval = get_max_bus_speed(slot->hotplug, &value);
-        if (retval)
-                goto exit;
-
-        if (value == PCI_SPEED_UNKNOWN)
-                speed_string = unknown_speed;
-        else
-                speed_string = pci_bus_speed_strings[value];
-        
-        retval = sprintf (buf, "%s\n", speed_string);
-
-exit:
-        return retval;
-}
-
-static struct pci_slot_attribute hotplug_slot_attr_max_bus_speed = {
-        .attr = {.name = "max_bus_speed", .mode = S_IFREG | S_IRUGO},
-        .show = max_bus_speed_read_file,
-};
-
-static ssize_t cur_bus_speed_read_file(struct pci_slot *slot, char *buf)
-{
-        char *speed_string;
-        int retval;
-        enum pci_bus_speed value;
-
-        retval = get_cur_bus_speed(slot->hotplug, &value);
-        if (retval)
-                goto exit;
-
-        if (value == PCI_SPEED_UNKNOWN)
-                speed_string = unknown_speed;
-        else
-                speed_string = pci_bus_speed_strings[value];
-        
-        retval = sprintf (buf, "%s\n", speed_string);
-
-exit:
-        return retval;
-}
-
-static struct pci_slot_attribute hotplug_slot_attr_cur_bus_speed = {
-        .attr = {.name = "cur_bus_speed", .mode = S_IFREG | S_IRUGO},
-        .show = cur_bus_speed_read_file,
-};
-
 static ssize_t test_write_file(struct pci_slot *pci_slot, const char *buf,
                 size_t count)
 {
@@ -391,26 +308,6 @@ static bool has_adapter_file(struct pci_slot *pci_slot)
         return false;
 }
 
-static bool has_max_bus_speed_file(struct pci_slot *pci_slot)
-{
-        struct hotplug_slot *slot = pci_slot->hotplug;
-        if ((!slot) || (!slot->ops))
-                return false;
-        if (slot->ops->get_max_bus_speed)
-                return true;
-        return false;
-}
-
-static bool has_cur_bus_speed_file(struct pci_slot *pci_slot)
-{
-        struct hotplug_slot *slot = pci_slot->hotplug;
-        if ((!slot) || (!slot->ops))
-                return false;
-        if (slot->ops->get_cur_bus_speed)
-                return true;
-        return false;
-}
-
 static bool has_test_file(struct pci_slot *pci_slot)
 {
         struct hotplug_slot *slot = pci_slot->hotplug;
@@ -456,20 +353,6 @@ static int fs_add_slot(struct pci_slot *slot)
                         goto exit_adapter;
         }
 
-        if (has_max_bus_speed_file(slot)) {
-                retval = sysfs_create_file(&slot->kobj,
-                                        &hotplug_slot_attr_max_bus_speed.attr);
-                if (retval)
-                        goto exit_max_speed;
-        }
-
-        if (has_cur_bus_speed_file(slot)) {
-                retval = sysfs_create_file(&slot->kobj,
-                                        &hotplug_slot_attr_cur_bus_speed.attr);
-                if (retval)
-                        goto exit_cur_speed;
-        }
-
         if (has_test_file(slot)) {
                 retval = sysfs_create_file(&slot->kobj,
                                            &hotplug_slot_attr_test.attr);
@@ -480,14 +363,6 @@ static int fs_add_slot(struct pci_slot *slot)
         goto exit;
 
 exit_test:
-        if (has_cur_bus_speed_file(slot))
-                sysfs_remove_file(&slot->kobj,
-                                  &hotplug_slot_attr_cur_bus_speed.attr);
-exit_cur_speed:
-        if (has_max_bus_speed_file(slot))
-                sysfs_remove_file(&slot->kobj,
-                                  &hotplug_slot_attr_max_bus_speed.attr);
-exit_max_speed:
         if (has_adapter_file(slot))
                 sysfs_remove_file(&slot->kobj,
                                   &hotplug_slot_attr_presence.attr);
@@ -523,14 +398,6 @@ static void fs_remove_slot(struct pci_slot *slot)
                 sysfs_remove_file(&slot->kobj,
                                   &hotplug_slot_attr_presence.attr);
 
-        if (has_max_bus_speed_file(slot))
-                sysfs_remove_file(&slot->kobj,
-                                  &hotplug_slot_attr_max_bus_speed.attr);
-
-        if (has_cur_bus_speed_file(slot))
-                sysfs_remove_file(&slot->kobj,
-                                  &hotplug_slot_attr_cur_bus_speed.attr);
-
         if (has_test_file(slot))
                 sysfs_remove_file(&slot->kobj, &hotplug_slot_attr_test.attr);
 
diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 4ed76b47b6dc..838f571027b7 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -36,6 +36,7 @@
 #include <linux/sched.h>                /* signal_pending() */
 #include <linux/pcieport_if.h>
 #include <linux/mutex.h>
+#include <linux/workqueue.h>
 
 #define MY_NAME "pciehp"
 
@@ -44,6 +45,7 @@ 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 {                                                                    \
@@ -176,19 +178,11 @@ static inline void pciehp_firmware_init(void)
 {
         pciehp_acpi_slot_detection_init();
 }
-
-static inline int pciehp_get_hp_hw_control_from_firmware(struct pci_dev *dev)
-{
-        int retval;
-        u32 flags = (OSC_PCI_EXPRESS_NATIVE_HP_CONTROL |
-                     OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL);
-        retval = acpi_get_hp_hw_control_from_firmware(dev, flags);
-        if (retval)
-                return retval;
-        return pciehp_acpi_slot_detection_check(dev);
-}
 #else
 #define pciehp_firmware_init()                          do {} while (0)
-#define pciehp_get_hp_hw_control_from_firmware(dev)     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
index b09b083011d6..5f7226223a62 100644
--- a/drivers/pci/hotplug/pciehp_acpi.c
+++ b/drivers/pci/hotplug/pciehp_acpi.c
@@ -26,6 +26,7 @@
 #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)
@@ -84,9 +85,7 @@ static int __init dummy_probe(struct pcie_device *dev)
         acpi_handle handle;
         struct dummy_slot *slot, *tmp;
         struct pci_dev *pdev = dev->port;
-        /* Note: pciehp_detect_mode != PCIEHP_DETECT_ACPI here */
-        if (pciehp_get_hp_hw_control_from_firmware(pdev))
-                return -ENODEV;
+
         pos = pci_pcie_cap(pdev);
         if (!pos)
                 return -ENODEV;
@@ -116,7 +115,8 @@ static struct pcie_port_service_driver __initdata dummy_driver = {
 static int __init select_detection_mode(void)
 {
         struct dummy_slot *slot, *tmp;
-        pcie_port_service_register(&dummy_driver);
+        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);
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 5674b2075bdc..7ac8358df8fd 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -30,6 +30,7 @@
 #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"
@@ -42,6 +43,7 @@ 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>"
@@ -58,7 +60,7 @@ 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 _OSC and OSHP are missing");
+MODULE_PARM_DESC(pciehp_force, "Force pciehp, even if OSHP is missing");
 
 #define PCIE_MODULE_NAME "pciehp"
 
@@ -69,8 +71,6 @@ 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 int get_max_bus_speed    (struct hotplug_slot *slot, enum pci_bus_speed *value);
-static int get_cur_bus_speed    (struct hotplug_slot *slot, enum pci_bus_speed *value);
 
 /**
  * release_slot - free up the memory used by a slot
@@ -113,8 +113,6 @@ static int init_slot(struct controller *ctrl)
         ops->disable_slot = disable_slot;
         ops->get_power_status = get_power_status;
         ops->get_adapter_status = get_adapter_status;
-        ops->get_max_bus_speed = get_max_bus_speed;
-        ops->get_cur_bus_speed = get_cur_bus_speed;
         if (MRL_SENS(ctrl))
                 ops->get_latch_status = get_latch_status;
         if (ATTN_LED(ctrl)) {
@@ -227,27 +225,6 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
         return pciehp_get_adapter_status(slot, value);
 }
 
-static int get_max_bus_speed(struct hotplug_slot *hotplug_slot,
-                                enum pci_bus_speed *value)
-{
-        struct slot *slot = hotplug_slot->private;
-
-        ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
-                 __func__, slot_name(slot));
-
-        return pciehp_get_max_link_speed(slot, value);
-}
-
-static int get_cur_bus_speed(struct hotplug_slot *hotplug_slot, enum pci_bus_speed *value)
-{
-        struct slot *slot = hotplug_slot->private;
-
-        ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
-                 __func__, slot_name(slot));
-
-        return pciehp_get_cur_link_speed(slot, value);
-}
-
 static int pciehp_probe(struct pcie_device *dev)
 {
         int rc;
@@ -259,7 +236,7 @@ static int pciehp_probe(struct pcie_device *dev)
                 dev_info(&dev->device,
                          "Bypassing BIOS check for pciehp use on %s\n",
                          pci_name(dev->port));
-        else if (pciehp_get_hp_hw_control_from_firmware(dev->port))
+        else if (pciehp_acpi_slot_detection_check(dev->port))
                 goto err_out_none;
 
         ctrl = pcie_init(dev);
@@ -364,18 +341,33 @@ 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)
+        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");
 }
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index d6ac1b261dd9..085dbb5fc168 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -30,8 +30,8 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <linux/slab.h>
 #include <linux/pci.h>
-#include <linux/workqueue.h>
 #include "../pci.h"
 #include "pciehp.h"
 
@@ -49,7 +49,7 @@ static int queue_interrupt_event(struct slot *p_slot, u32 event_type)
         info->p_slot = p_slot;
         INIT_WORK(&info->work, interrupt_event_handler);
 
-        schedule_work(&info->work);
+        queue_work(pciehp_wq, &info->work);
 
         return 0;
 }
@@ -341,9 +341,10 @@ void pciehp_queue_pushbutton_work(struct work_struct *work)
                 p_slot->state = POWERON_STATE;
                 break;
         default:
+                kfree(info);
                 goto out;
         }
-        queue_work(pciehp_wq, &info->work);
+        queue_work(pciehp_ordered_wq, &info->work);
  out:
         mutex_unlock(&p_slot->lock);
 }
@@ -376,7 +377,7 @@ static void handle_button_press_event(struct slot *p_slot)
                 if (ATTN_LED(ctrl))
                         pciehp_set_attention_status(p_slot, 0);
 
-                schedule_delayed_work(&p_slot->work, 5*HZ);
+                queue_delayed_work(pciehp_wq, &p_slot->work, 5*HZ);
                 break;
         case BLINKINGOFF_STATE:
         case BLINKINGON_STATE:
@@ -438,7 +439,7 @@ static void handle_surprise_event(struct slot *p_slot)
         else
                 p_slot->state = POWERON_STATE;
 
-        queue_work(pciehp_wq, &info->work);
+        queue_work(pciehp_ordered_wq, &info->work);
 }
 
 static void interrupt_event_handler(struct work_struct *work)
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 10040d58c8ef..50a23da5d24d 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -36,12 +36,11 @@
 #include <linux/pci.h>
 #include <linux/interrupt.h>
 #include <linux/time.h>
+#include <linux/slab.h>
 
 #include "../pci.h"
 #include "pciehp.h"
 
-static atomic_t pciehp_num_controllers = ATOMIC_INIT(0);
-
 static inline int pciehp_readw(struct controller *ctrl, int reg, u16 *value)
 {
         struct pci_dev *dev = ctrl->pcie->port;
@@ -492,6 +491,7 @@ int pciehp_power_on_slot(struct slot * slot)
         u16 slot_cmd;
         u16 cmd_mask;
         u16 slot_status;
+        u16 lnk_status;
         int retval = 0;
 
         /* Clear sticky power-fault bit from previous power failures */
@@ -523,6 +523,14 @@ int pciehp_power_on_slot(struct slot * slot)
         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;
 }
 
@@ -610,37 +618,6 @@ static irqreturn_t pcie_isr(int irq, void *dev_id)
         return IRQ_HANDLED;
 }
 
-int pciehp_get_max_link_speed(struct slot *slot, enum pci_bus_speed *value)
-{
-        struct controller *ctrl = slot->ctrl;
-        enum pcie_link_speed lnk_speed;
-        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 & 0x000F) {
-        case 1:
-                lnk_speed = PCIE_2_5GB;
-                break;
-        case 2:
-                lnk_speed = PCIE_5_0GB;
-                break;
-        default:
-                lnk_speed = PCIE_LNK_SPEED_UNKNOWN;
-                break;
-        }
-
-        *value = lnk_speed;
-        ctrl_dbg(ctrl, "Max link speed = %d\n", lnk_speed);
-
-        return retval;
-}
-
 int pciehp_get_max_lnk_width(struct slot *slot,
                                  enum pcie_link_width *value)
 {
@@ -691,38 +668,6 @@ int pciehp_get_max_lnk_width(struct slot *slot,
         return retval;
 }
 
-int pciehp_get_cur_link_speed(struct slot *slot, enum pci_bus_speed *value)
-{
-        struct controller *ctrl = slot->ctrl;
-        enum pcie_link_speed lnk_speed = PCI_SPEED_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_CLS) {
-        case 1:
-                lnk_speed = PCIE_2_5GB;
-                break;
-        case 2:
-                lnk_speed = PCIE_5_0GB;
-                break;
-        default:
-                lnk_speed = PCIE_LNK_SPEED_UNKNOWN;
-                break;
-        }
-
-        *value = lnk_speed;
-        ctrl_dbg(ctrl, "Current link speed = %d\n", lnk_speed);
-
-        return retval;
-}
-
 int pciehp_get_cur_lnk_width(struct slot *slot,
                                  enum pcie_link_width *value)
 {
@@ -858,8 +803,8 @@ static void pcie_cleanup_slot(struct controller *ctrl)
 {
         struct slot *slot = ctrl->slot;
         cancel_delayed_work(&slot->work);
-        flush_scheduled_work();
         flush_workqueue(pciehp_wq);
+        flush_workqueue(pciehp_ordered_wq);
         kfree(slot);
 }
 
@@ -886,9 +831,8 @@ static inline void dbg_ctrl(struct controller *ctrl)
         for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
                 if (!pci_resource_len(pdev, i))
                         continue;
-                ctrl_info(ctrl, "  PCI resource [%d]     : 0x%llx@0x%llx\n",
-                          i, (unsigned long long)pci_resource_len(pdev, i),
-                          (unsigned long long)pci_resource_start(pdev, i));
+                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));
@@ -966,16 +910,6 @@ struct controller *pcie_init(struct pcie_device *dev)
         /* Disable sotfware notification */
         pcie_disable_notification(ctrl);
 
-        /*
-         * If this is the first controller to be initialized,
-         * initialize the pciehp work queue
-         */
-        if (atomic_add_return(1, &pciehp_num_controllers) == 1) {
-                pciehp_wq = create_singlethread_workqueue("pciehpd");
-                if (!pciehp_wq)
-                        goto abort_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);
@@ -995,11 +929,5 @@ void pciehp_release_ctrl(struct controller *ctrl)
 {
         pcie_shutdown_notification(ctrl);
         pcie_cleanup_slot(ctrl);
-        /*
-         * If this is the last controller to be released, destroy the
-         * pciehp work queue
-         */
-        if (atomic_dec_and_test(&pciehp_num_controllers))
-                destroy_workqueue(pciehp_wq);
         kfree(ctrl);
 }
diff --git a/drivers/pci/hotplug/pciehp_pci.c b/drivers/pci/hotplug/pciehp_pci.c
index 21733108adde..a4031dfe938e 100644
--- a/drivers/pci/hotplug/pciehp_pci.c
+++ b/drivers/pci/hotplug/pciehp_pci.c
@@ -53,17 +53,15 @@ static int __ref pciehp_add_bridge(struct pci_dev *dev)
                 busnr = pci_scan_bridge(parent, dev, busnr, pass);
         if (!dev->subordinate)
                 return -1;
-        pci_bus_size_bridges(dev->subordinate);
-        pci_bus_assign_resources(parent);
-        pci_enable_bridges(parent);
-        pci_bus_add_devices(parent);
+
         return 0;
 }
 
 int pciehp_configure_device(struct slot *p_slot)
 {
         struct pci_dev *dev;
-        struct pci_bus *parent = p_slot->ctrl->pcie->port->subordinate;
+        struct pci_dev *bridge = p_slot->ctrl->pcie->port;
+        struct pci_bus *parent = bridge->subordinate;
         int num, fn;
         struct controller *ctrl = p_slot->ctrl;
 
@@ -86,22 +84,29 @@ int pciehp_configure_device(struct slot *p_slot)
                 dev = pci_get_slot(parent, PCI_DEVFN(0, fn));
                 if (!dev)
                         continue;
-                if ((dev->class >> 16) == PCI_BASE_CLASS_DISPLAY) {
-                        ctrl_err(ctrl, "Cannot hot-add display device %s\n",
-                                 pci_name(dev));
-                        pci_dev_put(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_assign_resources(parent);
         pci_bus_add_devices(parent);
+
         return 0;
 }
 
@@ -122,15 +127,9 @@ int pciehp_unconfigure_device(struct slot *p_slot)
                 presence = 0;
 
         for (j = 0; j < 8; j++) {
-                struct pci_dev* temp = pci_get_slot(parent, PCI_DEVFN(0, j));
+                struct pci_dev *temp = pci_get_slot(parent, PCI_DEVFN(0, j));
                 if (!temp)
                         continue;
-                if ((temp->class >> 16) == PCI_BASE_CLASS_DISPLAY) {
-                        ctrl_err(ctrl, "Cannot remove display device %s\n",
-                                 pci_name(temp));
-                        pci_dev_put(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) {
@@ -138,7 +137,8 @@ int pciehp_unconfigure_device(struct slot *p_slot)
                                          "Cannot remove display device %s\n",
                                          pci_name(temp));
                                 pci_dev_put(temp);
-                                continue;
+                                rc = -EINVAL;
+                                break;
                         }
                 }
                 pci_remove_bus_device(temp);
diff --git a/drivers/pci/hotplug/rpadlpar_core.c b/drivers/pci/hotplug/rpadlpar_core.c
index 4e3e0382c16e..083034710fa6 100644
--- a/drivers/pci/hotplug/rpadlpar_core.c
+++ b/drivers/pci/hotplug/rpadlpar_core.c
@@ -20,6 +20,7 @@
 #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>
@@ -430,6 +431,8 @@ int dlpar_remove_slot(char *drc_name)
                         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);
diff --git a/drivers/pci/hotplug/rpaphp_core.c b/drivers/pci/hotplug/rpaphp_core.c
index c159223389ec..ef7411c660b9 100644
--- a/drivers/pci/hotplug/rpaphp_core.c
+++ b/drivers/pci/hotplug/rpaphp_core.c
@@ -27,9 +27,9 @@
 #include <linux/moduleparam.h>
 #include <linux/pci.h>
 #include <linux/pci_hotplug.h>
-#include <linux/slab.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 */
@@ -130,10 +130,9 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 * value)
         return 0;
 }
 
-static int get_max_bus_speed(struct hotplug_slot *hotplug_slot, enum pci_bus_speed *value)
+static enum pci_bus_speed get_max_bus_speed(struct slot *slot)
 {
-        struct slot *slot = (struct slot *)hotplug_slot->private;
-
+        enum pci_bus_speed speed;
         switch (slot->type) {
         case 1:
         case 2:
@@ -141,30 +140,30 @@ static int get_max_bus_speed(struct hotplug_slot *hotplug_slot, enum pci_bus_spe
         case 4:
         case 5:
         case 6:
-                *value = PCI_SPEED_33MHz;       /* speed for case 1-6 */
+                speed = PCI_SPEED_33MHz;        /* speed for case 1-6 */
                 break;
         case 7:
         case 8:
-                *value = PCI_SPEED_66MHz;
+                speed = PCI_SPEED_66MHz;
                 break;
         case 11:
         case 14:
-                *value = PCI_SPEED_66MHz_PCIX;
+                speed = PCI_SPEED_66MHz_PCIX;
                 break;
         case 12:
         case 15:
-                *value = PCI_SPEED_100MHz_PCIX;
+                speed = PCI_SPEED_100MHz_PCIX;
                 break;
         case 13:
         case 16:
-                *value = PCI_SPEED_133MHz_PCIX;
+                speed = PCI_SPEED_133MHz_PCIX;
                 break;
         default:
-                *value = PCI_SPEED_UNKNOWN;
+                speed = PCI_SPEED_UNKNOWN;
                 break;
-
         }
-        return 0;
+
+        return speed;
 }
 
 static int get_children_props(struct device_node *dn, const int **drc_indexes,
@@ -408,6 +407,8 @@ static int enable_slot(struct hotplug_slot *hotplug_slot)
                 slot->state = NOT_VALID;
                 return -EINVAL;
         }
+
+        slot->bus->max_bus_speed = get_max_bus_speed(slot);
         return 0;
 }
 
@@ -418,6 +419,8 @@ static int disable_slot(struct hotplug_slot *hotplug_slot)
                 return -EINVAL;
 
         pcibios_remove_pci_devices(slot->bus);
+        vm_unmap_aliases();
+
         slot->state = NOT_CONFIGURED;
         return 0;
 }
@@ -429,7 +432,6 @@ struct hotplug_slot_ops rpaphp_hotplug_slot_ops = {
         .get_power_status = get_power_status,
         .get_attention_status = get_attention_status,
         .get_adapter_status = get_adapter_status,
-        .get_max_bus_speed = get_max_bus_speed,
 };
 
 module_init(rpaphp_init);
diff --git a/drivers/pci/hotplug/rpaphp_slot.c b/drivers/pci/hotplug/rpaphp_slot.c
index 2ea9cf1a8d02..b283bbea6d24 100644
--- a/drivers/pci/hotplug/rpaphp_slot.c
+++ b/drivers/pci/hotplug/rpaphp_slot.c
@@ -24,7 +24,6 @@
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/kobject.h>
 #include <linux/sysfs.h>
 #include <linux/pci.h>
 #include <linux/string.h>
diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c
index 8aebe1e9d3d6..72d507b6a2aa 100644
--- a/drivers/pci/hotplug/sgi_hotplug.c
+++ b/drivers/pci/hotplug/sgi_hotplug.c
@@ -15,6 +15,7 @@
 #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>
 
diff --git a/drivers/pci/hotplug/shpchp.h b/drivers/pci/hotplug/shpchp.h
index 8e210cd76e55..e0c90e643b5f 100644
--- a/drivers/pci/hotplug/shpchp.h
+++ b/drivers/pci/hotplug/shpchp.h
@@ -35,6 +35,7 @@
 #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"
@@ -46,6 +47,7 @@ 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 {                                                                    \
@@ -333,8 +335,6 @@ struct hpc_ops {
         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_max_bus_speed)(struct slot *slot, enum pci_bus_speed *speed);
-        int (*get_cur_bus_speed)(struct slot *slot, enum pci_bus_speed *speed);
         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);
diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c
index 8a520a3d0f59..aca972bbfb4c 100644
--- a/drivers/pci/hotplug/shpchp_core.c
+++ b/drivers/pci/hotplug/shpchp_core.c
@@ -31,8 +31,8 @@
 #include <linux/moduleparam.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <linux/slab.h>
 #include <linux/pci.h>
-#include <linux/workqueue.h>
 #include "shpchp.h"
 
 /* Global variables */
@@ -40,6 +40,7 @@ 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>"
@@ -65,8 +66,6 @@ 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 int get_max_bus_speed    (struct hotplug_slot *slot, enum pci_bus_speed *value);
-static int get_cur_bus_speed    (struct hotplug_slot *slot, enum pci_bus_speed *value);
 
 static struct hotplug_slot_ops shpchp_hotplug_slot_ops = {
         .set_attention_status = set_attention_status,
@@ -76,8 +75,6 @@ static struct hotplug_slot_ops shpchp_hotplug_slot_ops = {
         .get_attention_status = get_attention_status,
         .get_latch_status =     get_latch_status,
         .get_adapter_status =   get_adapter_status,
-        .get_max_bus_speed =    get_max_bus_speed,
-        .get_cur_bus_speed =    get_cur_bus_speed,
 };
 
 /**
@@ -177,8 +174,8 @@ void cleanup_slots(struct controller *ctrl)
                 slot = list_entry(tmp, struct slot, slot_list);
                 list_del(&slot->slot_list);
                 cancel_delayed_work(&slot->work);
-                flush_scheduled_work();
                 flush_workqueue(shpchp_wq);
+                flush_workqueue(shpchp_ordered_wq);
                 pci_hp_deregister(slot->hotplug_slot);
         }
 }
@@ -279,37 +276,6 @@ static int get_adapter_status (struct hotplug_slot *hotplug_slot, u8 *value)
         return 0;
 }
 
-static int get_max_bus_speed(struct hotplug_slot *hotplug_slot,
-                                enum pci_bus_speed *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_max_bus_speed(slot, value);
-        if (retval < 0)
-                *value = PCI_SPEED_UNKNOWN;
-
-        return 0;
-}
-
-static int get_cur_bus_speed (struct hotplug_slot *hotplug_slot, enum pci_bus_speed *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_cur_bus_speed(slot, value);
-        if (retval < 0)
-                *value = PCI_SPEED_UNKNOWN;
-
-        return 0;
-}
-
 static int is_shpc_capable(struct pci_dev *dev)
 {
         if ((dev->vendor == PCI_VENDOR_ID_AMD) || (dev->device ==
@@ -394,9 +360,23 @@ 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;
 }
 
@@ -404,6 +384,8 @@ 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");
 }
 
diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c
index b8ab2796e66a..b00b09bdd38a 100644
--- a/drivers/pci/hotplug/shpchp_ctrl.c
+++ b/drivers/pci/hotplug/shpchp_ctrl.c
@@ -30,8 +30,8 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <linux/slab.h>
 #include <linux/pci.h>
-#include <linux/workqueue.h>
 #include "../pci.h"
 #include "shpchp.h"
 
@@ -51,7 +51,7 @@ static int queue_interrupt_event(struct slot *p_slot, u32 event_type)
         info->p_slot = p_slot;
         INIT_WORK(&info->work, interrupt_event_handler);
 
-        schedule_work(&info->work);
+        queue_work(shpchp_wq, &info->work);
 
         return 0;
 }
@@ -285,17 +285,8 @@ static int board_added(struct slot *p_slot)
                 return WRONG_BUS_FREQUENCY;
         }
 
-        rc = p_slot->hpc_ops->get_cur_bus_speed(p_slot, &bsp);
-        if (rc) {
-                ctrl_err(ctrl, "Can't get bus operation speed\n");
-                return WRONG_BUS_FREQUENCY;
-        }
-
-        rc = p_slot->hpc_ops->get_max_bus_speed(p_slot, &msp);
-        if (rc) {
-                ctrl_err(ctrl, "Can't get max bus operation speed\n");
-                msp = bsp;
-        }
+        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))
@@ -462,9 +453,10 @@ void shpchp_queue_pushbutton_work(struct work_struct *work)
                 p_slot->state = POWERON_STATE;
                 break;
         default:
+                kfree(info);
                 goto out;
         }
-        queue_work(shpchp_wq, &info->work);
+        queue_work(shpchp_ordered_wq, &info->work);
  out:
         mutex_unlock(&p_slot->lock);
 }
@@ -512,7 +504,7 @@ static void handle_button_press_event(struct slot *p_slot)
                 p_slot->hpc_ops->green_led_blink(p_slot);
                 p_slot->hpc_ops->set_attention_status(p_slot, 0);
 
-                schedule_delayed_work(&p_slot->work, 5*HZ);
+                queue_delayed_work(shpchp_wq, &p_slot->work, 5*HZ);
                 break;
         case BLINKINGOFF_STATE:
         case BLINKINGON_STATE:
diff --git a/drivers/pci/hotplug/shpchp_hpc.c b/drivers/pci/hotplug/shpchp_hpc.c
index 86dc39847769..36547f0ce305 100644
--- a/drivers/pci/hotplug/shpchp_hpc.c
+++ b/drivers/pci/hotplug/shpchp_hpc.c
@@ -113,7 +113,7 @@
 #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)
+#define SLOT_REG_RSVDZ_MASK     ((1 << 15) | (7 << 21))
 
 /*
  * SHPC Command Code definitnions
@@ -179,8 +179,6 @@
 #define SLOT_EVENT_LATCH        0x2
 #define SLOT_SERR_INT_MASK      0x3
 
-static atomic_t shpchp_num_controllers = ATOMIC_INIT(0);
-
 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);
@@ -614,13 +612,6 @@ static void hpc_release_ctlr(struct controller *ctrl)
 
         iounmap(ctrl->creg);
         release_mem_region(ctrl->mmio_base, ctrl->mmio_size);
-
-        /*
-         * If this is the last controller to be released, destroy the
-         * shpchpd work queue
-         */
-        if (atomic_dec_and_test(&shpchp_num_controllers))
-                destroy_workqueue(shpchp_wq);
 }
 
 static int hpc_power_on_slot(struct slot * slot)
@@ -660,6 +651,75 @@ static int hpc_slot_disable(struct slot * slot)
         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;
@@ -720,6 +780,8 @@ static int hpc_set_bus_speed_mode(struct slot * slot, enum pci_bus_speed value)
         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;
 }
@@ -803,10 +865,10 @@ static irqreturn_t shpc_isr(int irq, void *dev_id)
         return IRQ_HANDLED;
 }
 
-static int hpc_get_max_bus_speed (struct slot *slot, enum pci_bus_speed *value)
+static int shpc_get_max_bus_speed(struct controller *ctrl)
 {
         int retval = 0;
-        struct controller *ctrl = slot->ctrl;
+        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);
@@ -842,79 +904,12 @@ static int hpc_get_max_bus_speed (struct slot *slot, enum pci_bus_speed *value)
                         retval = -ENODEV;
         }
 
-        *value = bus_speed;
+        bus->max_bus_speed = bus_speed;
         ctrl_dbg(ctrl, "Max bus speed = %d\n", bus_speed);
 
         return retval;
 }
 
-static int hpc_get_cur_bus_speed (struct slot *slot, enum pci_bus_speed *value)
-{
-        int retval = 0;
-        struct controller *ctrl = slot->ctrl;
-        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)) {
-                *value = PCI_SPEED_UNKNOWN;
-                return -ENODEV;
-        }
-
-        switch (speed_mode) {
-        case 0x0:
-                *value = PCI_SPEED_33MHz;
-                break;
-        case 0x1:
-                *value = PCI_SPEED_66MHz;
-                break;
-        case 0x2:
-                *value = PCI_SPEED_66MHz_PCIX;
-                break;
-        case 0x3:
-                *value = PCI_SPEED_100MHz_PCIX;
-                break;
-        case 0x4:
-                *value = PCI_SPEED_133MHz_PCIX;
-                break;
-        case 0x5:
-                *value = PCI_SPEED_66MHz_PCIX_ECC;
-                break;
-        case 0x6:
-                *value = PCI_SPEED_100MHz_PCIX_ECC;
-                break;
-        case 0x7:
-                *value = PCI_SPEED_133MHz_PCIX_ECC;
-                break;
-        case 0x8:
-                *value = PCI_SPEED_66MHz_PCIX_266;
-                break;
-        case 0x9:
-                *value = PCI_SPEED_100MHz_PCIX_266;
-                break;
-        case 0xa:
-                *value = PCI_SPEED_133MHz_PCIX_266;
-                break;
-        case 0xb:
-                *value = PCI_SPEED_66MHz_PCIX_533;
-                break;
-        case 0xc:
-                *value = PCI_SPEED_100MHz_PCIX_533;
-                break;
-        case 0xd:
-                *value = PCI_SPEED_133MHz_PCIX_533;
-                break;
-        default:
-                *value = PCI_SPEED_UNKNOWN;
-                retval = -ENODEV;
-                break;
-        }
-
-        ctrl_dbg(ctrl, "Current 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,
@@ -926,8 +921,6 @@ static struct hpc_ops shpchp_hpc_ops = {
         .get_latch_status               = hpc_get_latch_status,
         .get_adapter_status             = hpc_get_adapter_status,
 
-        .get_max_bus_speed              = hpc_get_max_bus_speed,
-        .get_cur_bus_speed              = hpc_get_cur_bus_speed,
         .get_adapter_speed              = hpc_get_adapter_speed,
         .get_mode1_ECC_cap              = hpc_get_mode1_ECC_cap,
         .get_prog_int                   = hpc_get_prog_int,
@@ -1075,9 +1068,8 @@ int shpc_init(struct controller *ctrl, struct pci_dev *pdev)
 
                 rc = request_irq(ctrl->pci_dev->irq, shpc_isr, IRQF_SHARED,
                                  MY_NAME, (void *)ctrl);
-                ctrl_dbg(ctrl, "request_irq %d for hpc%d (returns %d)\n",
-                         ctrl->pci_dev->irq,
-                    atomic_read(&shpchp_num_controllers), rc);
+                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);
@@ -1086,17 +1078,8 @@ int shpc_init(struct controller *ctrl, struct pci_dev *pdev)
         }
         ctrl_dbg(ctrl, "HPC at %s irq=%x\n", pci_name(pdev), pdev->irq);
 
-        /*
-         * If this is the first controller to be initialized,
-         * initialize the shpchpd work queue
-         */
-        if (atomic_add_return(1, &shpchp_num_controllers) == 1) {
-                shpchp_wq = create_singlethread_workqueue("shpchpd");
-                if (!shpchp_wq) {
-                        rc = -ENOMEM;
-                        goto abort_iounmap;
-                }
-        }
+        shpc_get_max_bus_speed(ctrl);
+        shpc_get_cur_bus_speed(ctrl);
 
         /*
          * Unmask all event interrupts of all slots
diff --git a/drivers/pci/hotplug/shpchp_pci.c b/drivers/pci/hotplug/shpchp_pci.c
index 8c3d3219f227..a2ccfcd3c298 100644
--- a/drivers/pci/hotplug/shpchp_pci.c
+++ b/drivers/pci/hotplug/shpchp_pci.c
@@ -60,12 +60,6 @@ int __ref shpchp_configure_device(struct slot *p_slot)
                 dev = pci_get_slot(parent, PCI_DEVFN(p_slot->device, fn));
                 if (!dev)
                         continue;
-                if ((dev->class >> 16) == PCI_BASE_CLASS_DISPLAY) {
-                        ctrl_err(ctrl, "Cannot hot-add display device %s\n",
-                                 pci_name(dev));
-                        pci_dev_put(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 */
@@ -114,17 +108,11 @@ int shpchp_unconfigure_device(struct slot *p_slot)
         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,
+        for (j = 0; j < 8 ; j++) {
+                struct pci_dev *temp = pci_get_slot(parent,
                                 (p_slot->device << 3) | j);
                 if (!temp)
                         continue;
-                if ((temp->class >> 16) == PCI_BASE_CLASS_DISPLAY) {
-                        ctrl_err(ctrl, "Cannot remove display device %s\n",
-                                 pci_name(temp));
-                        pci_dev_put(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) {
@@ -132,7 +120,8 @@ int shpchp_unconfigure_device(struct slot *p_slot)
                                          "Cannot remove display device %s\n",
                                          pci_name(temp));
                                 pci_dev_put(temp);
-                                continue;
+                                rc = -EINVAL;
+                                break;
                         }
                 }
                 pci_remove_bus_device(temp);
diff --git a/drivers/pci/hotplug/shpchp_sysfs.c b/drivers/pci/hotplug/shpchp_sysfs.c
index 29fa9d26adae..071b7dc0094b 100644
--- a/drivers/pci/hotplug/shpchp_sysfs.c
+++ b/drivers/pci/hotplug/shpchp_sysfs.c
@@ -47,8 +47,7 @@ static ssize_t show_ctrl (struct device *dev, struct device_attribute *attr, cha
         bus = pdev->subordinate;
 
         out += sprintf(buf, "Free resources: memory\n");
-        for (index = 0; index < PCI_BUS_NUM_RESOURCES; index++) {
-                res = bus->resource[index];
+        pci_bus_for_each_resource(bus, res, index) {
                 if (res && (res->flags & IORESOURCE_MEM) &&
                                 !(res->flags & IORESOURCE_PREFETCH)) {
                         out += sprintf(out, "start = %8.8llx, "
@@ -58,8 +57,7 @@ static ssize_t show_ctrl (struct device *dev, struct device_attribute *attr, cha
                 }
         }
         out += sprintf(out, "Free resources: prefetchable memory\n");
-        for (index = 0; index < PCI_BUS_NUM_RESOURCES; index++) {
-                res = bus->resource[index];
+        pci_bus_for_each_resource(bus, res, index) {
                 if (res && (res->flags & IORESOURCE_MEM) &&
                                (res->flags & IORESOURCE_PREFETCH)) {
                         out += sprintf(out, "start = %8.8llx, "
@@ -69,8 +67,7 @@ static ssize_t show_ctrl (struct device *dev, struct device_attribute *attr, cha
                 }
         }
         out += sprintf(out, "Free resources: IO\n");
-        for (index = 0; index < PCI_BUS_NUM_RESOURCES; index++) {
-                res = bus->resource[index];
+        pci_bus_for_each_resource(bus, res, index) {
                 if (res && (res->flags & IORESOURCE_IO)) {
                         out += sprintf(out, "start = %8.8llx, "
                                         "length = %8.8llx\n",
diff --git a/drivers/pci/htirq.c b/drivers/pci/htirq.c
index 737a1c44b07a..834842aa5bbf 100644
--- a/drivers/pci/htirq.c
+++ b/drivers/pci/htirq.c
@@ -10,7 +10,6 @@
 #include <linux/pci.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
-#include <linux/gfp.h>
 #include <linux/htirq.h>
 
 /* Global ht irq lock.
@@ -58,28 +57,22 @@ void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg)
         *msg = cfg->msg;
 }
 
-void mask_ht_irq(unsigned int irq)
+void mask_ht_irq(struct irq_data *data)
 {
-        struct ht_irq_cfg *cfg;
-        struct ht_irq_msg msg;
-
-        cfg = get_irq_data(irq);
+        struct ht_irq_cfg *cfg = irq_data_get_irq_data(data);
+        struct ht_irq_msg msg = cfg->msg;
 
-        msg = cfg->msg;
         msg.address_lo |= 1;
-        write_ht_irq_msg(irq, &msg);
+        write_ht_irq_msg(data->irq, &msg);
 }
 
-void unmask_ht_irq(unsigned int irq)
+void unmask_ht_irq(struct irq_data *data)
 {
-        struct ht_irq_cfg *cfg;
-        struct ht_irq_msg msg;
-
-        cfg = get_irq_data(irq);
+        struct ht_irq_cfg *cfg = irq_data_get_irq_data(data);
+        struct ht_irq_msg msg = cfg->msg;
 
-        msg = cfg->msg;
         msg.address_lo &= ~1;
-        write_ht_irq_msg(irq, &msg);
+        write_ht_irq_msg(data->irq, &msg);
 }
 
 /**
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index 417312528ddf..4789f8e8bf7a 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -71,6 +71,49 @@
 #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);
+}
 
 /* VT-d pages must always be _smaller_ than MM pages. Otherwise things
    are never going to work. */
@@ -236,7 +279,7 @@ static inline u64 dma_pte_addr(struct dma_pte *pte)
         return pte->val & VTD_PAGE_MASK;
 #else
         /* Must have a full atomic 64-bit read */
-        return  __cmpxchg64(pte, 0ULL, 0ULL) & VTD_PAGE_MASK;
+        return  __cmpxchg64(&pte->val, 0ULL, 0ULL) & VTD_PAGE_MASK;
 #endif
 }
 
@@ -340,7 +383,7 @@ int dmar_disabled = 0;
 int dmar_disabled = 1;
 #endif /*CONFIG_DMAR_DEFAULT_ON*/
 
-static int __initdata dmar_map_gfx = 1;
+static int dmar_map_gfx = 1;
 static int dmar_forcedac;
 static int intel_iommu_strict;
 
@@ -434,8 +477,6 @@ void free_iova_mem(struct iova *iova)
 }
 
 
-static inline int width_to_agaw(int width);
-
 static int __iommu_calculate_agaw(struct intel_iommu *iommu, int max_gaw)
 {
         unsigned long sagaw;
@@ -491,13 +532,11 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain)
 
         domain->iommu_coherency = 1;
 
-        i = find_first_bit(&domain->iommu_bmp, g_num_of_iommus);
-        for (; i < g_num_of_iommus; ) {
+        for_each_set_bit(i, &domain->iommu_bmp, g_num_of_iommus) {
                 if (!ecap_coherent(g_iommus[i]->ecap)) {
                         domain->iommu_coherency = 0;
                         break;
                 }
-                i = find_next_bit(&domain->iommu_bmp, g_num_of_iommus, i+1);
         }
 }
 
@@ -507,13 +546,11 @@ static void domain_update_iommu_snooping(struct dmar_domain *domain)
 
         domain->iommu_snooping = 1;
 
-        i = find_first_bit(&domain->iommu_bmp, g_num_of_iommus);
-        for (; i < g_num_of_iommus; ) {
+        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;
                 }
-                i = find_next_bit(&domain->iommu_bmp, g_num_of_iommus, i+1);
         }
 }
 
@@ -650,51 +687,6 @@ out:
         spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
-/* 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 struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
                                       unsigned long pfn)
 {
@@ -1068,7 +1060,7 @@ static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
 }
 
 static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
-                                  unsigned long pfn, unsigned int pages)
+                                  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;
@@ -1089,10 +1081,10 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
                                                 DMA_TLB_PSI_FLUSH);
 
         /*
-         * In caching mode, domain ID 0 is reserved for non-present to present
-         * mapping flush. Device IOTLB doesn't need to be flushed in this case.
+         * 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) || did)
+        if (!cap_caching_mode(iommu->cap) || !map)
                 iommu_flush_dev_iotlb(iommu->domains[did], addr, mask);
 }
 
@@ -1154,7 +1146,8 @@ static int iommu_init_domains(struct intel_iommu *iommu)
         unsigned long nlongs;
 
         ndomains = cap_ndoms(iommu->cap);
-        pr_debug("Number of Domains supportd <%ld>\n", ndomains);
+        pr_debug("IOMMU %d: Number of Domains supportd <%ld>\n", iommu->seq_id,
+                        ndomains);
         nlongs = BITS_TO_LONGS(ndomains);
 
         spin_lock_init(&iommu->lock);
@@ -1194,8 +1187,7 @@ void free_dmar_iommu(struct intel_iommu *iommu)
         unsigned long flags;
 
         if ((iommu->domains) && (iommu->domain_ids)) {
-                i = find_first_bit(iommu->domain_ids, cap_ndoms(iommu->cap));
-                for (; i < cap_ndoms(iommu->cap); ) {
+                for_each_set_bit(i, iommu->domain_ids, cap_ndoms(iommu->cap)) {
                         domain = iommu->domains[i];
                         clear_bit(i, iommu->domain_ids);
 
@@ -1207,9 +1199,6 @@ void free_dmar_iommu(struct intel_iommu *iommu)
                                         domain_exit(domain);
                         }
                         spin_unlock_irqrestore(&domain->iommu_lock, flags);
-
-                        i = find_next_bit(iommu->domain_ids,
-                                cap_ndoms(iommu->cap), i+1);
                 }
         }
 
@@ -1292,14 +1281,11 @@ static void iommu_detach_domain(struct dmar_domain *domain,
 
         spin_lock_irqsave(&iommu->lock, flags);
         ndomains = cap_ndoms(iommu->cap);
-        num = find_first_bit(iommu->domain_ids, ndomains);
-        for (; num < ndomains; ) {
+        for_each_set_bit(num, iommu->domain_ids, ndomains) {
                 if (iommu->domains[num] == domain) {
                         found = 1;
                         break;
                 }
-                num = find_next_bit(iommu->domain_ids,
-                                    cap_ndoms(iommu->cap), num+1);
         }
 
         if (found) {
@@ -1485,15 +1471,12 @@ static int domain_context_mapping_one(struct dmar_domain *domain, int segment,
 
                 /* find an available domain id for this device in iommu */
                 ndomains = cap_ndoms(iommu->cap);
-                num = find_first_bit(iommu->domain_ids, ndomains);
-                for (; num < ndomains; ) {
+                for_each_set_bit(num, iommu->domain_ids, ndomains) {
                         if (iommu->domains[num] == domain) {
                                 id = num;
                                 found = 1;
                                 break;
                         }
-                        num = find_next_bit(iommu->domain_ids,
-                                            cap_ndoms(iommu->cap), num+1);
                 }
 
                 if (found == 0) {
@@ -1558,7 +1541,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain, int segment,
                                            (((u16)bus) << 8) | devfn,
                                            DMA_CCMD_MASK_NOBIT,
                                            DMA_CCMD_DEVICE_INVL);
-                iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_DSI_FLUSH);
+                iommu->flush.flush_iotlb(iommu, domain->id, 0, 0, DMA_TLB_DSI_FLUSH);
         } else {
                 iommu_flush_write_buffer(iommu);
         }
@@ -1887,14 +1870,15 @@ static struct dmar_domain *get_domain_for_dev(struct pci_dev *pdev, int gaw)
                         }
                 }
                 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);
                 }
-                spin_unlock_irqrestore(&device_domain_lock, flags);
         }
 
 found_domain:
@@ -2333,14 +2317,16 @@ int __init init_dmars(void)
                          */
                         iommu->flush.flush_context = __iommu_flush_context;
                         iommu->flush.flush_iotlb = __iommu_flush_iotlb;
-                        printk(KERN_INFO "IOMMU 0x%Lx: using Register based "
+                        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 0x%Lx: using Queued "
+                        printk(KERN_INFO "IOMMU %d 0x%Lx: using Queued "
                                "invalidation\n",
+                                iommu->seq_id,
                                (unsigned long long)drhd->reg_base_addr);
                 }
         }
@@ -2621,7 +2607,7 @@ static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr,
 
         /* it's a non-present to present mapping. Only flush if caching mode */
         if (cap_caching_mode(iommu->cap))
-                iommu_flush_iotlb_psi(iommu, 0, mm_to_dma_pfn(iova->pfn_lo), size);
+                iommu_flush_iotlb_psi(iommu, domain->id, mm_to_dma_pfn(iova->pfn_lo), size, 1);
         else
                 iommu_flush_write_buffer(iommu);
 
@@ -2661,15 +2647,24 @@ static void flush_unmaps(void)
                 if (!deferred_flush[i].next)
                         continue;
 
-                iommu->flush.flush_iotlb(iommu, 0, 0, 0,
+                /* 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];
-
-                        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);
+                        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;
@@ -2750,7 +2745,7 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
 
         if (intel_iommu_strict) {
                 iommu_flush_iotlb_psi(iommu, domain->id, start_pfn,
-                                      last_pfn - start_pfn + 1);
+                                      last_pfn - start_pfn + 1, 0);
                 /* free iova */
                 __free_iova(&domain->iovad, iova);
         } else {
@@ -2840,7 +2835,7 @@ static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,
 
         if (intel_iommu_strict) {
                 iommu_flush_iotlb_psi(iommu, domain->id, start_pfn,
-                                      last_pfn - start_pfn + 1);
+                                      last_pfn - start_pfn + 1, 0);
                 /* free iova */
                 __free_iova(&domain->iovad, iova);
         } else {
@@ -2874,7 +2869,6 @@ static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int ne
         struct dmar_domain *domain;
         size_t size = 0;
         int prot = 0;
-        size_t offset_pfn = 0;
         struct iova *iova = NULL;
         int ret;
         struct scatterlist *sg;
@@ -2928,7 +2922,7 @@ static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int ne
 
         /* it's a non-present to present mapping. Only flush if caching mode */
         if (cap_caching_mode(iommu->cap))
-                iommu_flush_iotlb_psi(iommu, 0, start_vpfn, offset_pfn);
+                iommu_flush_iotlb_psi(iommu, domain->id, start_vpfn, size, 1);
         else
                 iommu_flush_write_buffer(iommu);
 
@@ -3032,6 +3026,34 @@ static void __init iommu_exit_mempool(void)
 
 }
 
+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;
@@ -3436,22 +3458,6 @@ static void vm_domain_remove_all_dev_info(struct dmar_domain *domain)
 /* domain id for virtual machine, it won't be set in context */
 static unsigned long vm_domid;
 
-static int vm_domain_min_agaw(struct dmar_domain *domain)
-{
-        int i;
-        int min_agaw = domain->agaw;
-
-        i = find_first_bit(&domain->iommu_bmp, g_num_of_iommus);
-        for (; i < g_num_of_iommus; ) {
-                if (min_agaw > g_iommus[i]->agaw)
-                        min_agaw = g_iommus[i]->agaw;
-
-                i = find_next_bit(&domain->iommu_bmp, g_num_of_iommus, i+1);
-        }
-
-        return min_agaw;
-}
-
 static struct dmar_domain *iommu_alloc_vm_domain(void)
 {
         struct dmar_domain *domain;
@@ -3512,8 +3518,7 @@ static void iommu_free_vm_domain(struct dmar_domain *domain)
                 iommu = drhd->iommu;
 
                 ndomains = cap_ndoms(iommu->cap);
-                i = find_first_bit(iommu->domain_ids, ndomains);
-                for (; i < ndomains; ) {
+                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);
@@ -3521,7 +3526,6 @@ static void iommu_free_vm_domain(struct dmar_domain *domain)
                                 spin_unlock_irqrestore(&iommu->lock, flags);
                                 break;
                         }
-                        i = find_next_bit(iommu->domain_ids, ndomains, i+1);
                 }
         }
 }
@@ -3582,7 +3586,6 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
         struct pci_dev *pdev = to_pci_dev(dev);
         struct intel_iommu *iommu;
         int addr_width;
-        u64 end;
 
         /* normally pdev is not mapped */
         if (unlikely(domain_context_mapped(pdev))) {
@@ -3605,14 +3608,31 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 
         /* check if this iommu agaw is sufficient for max mapped address */
         addr_width = agaw_to_width(iommu->agaw);
-        end = DOMAIN_MAX_ADDR(addr_width);
-        end = end & VTD_PAGE_MASK;
-        if (end < dmar_domain->max_addr) {
-                printk(KERN_ERR "%s: iommu agaw (%d) is not "
+        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__, iommu->agaw, dmar_domain->max_addr);
+                       __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)) {
+                        free_pgtable_page(dmar_domain->pgd);
+                        dmar_domain->pgd = (struct dma_pte *)
+                                phys_to_virt(dma_pte_addr(pte));
+                }
+                dmar_domain->agaw--;
+        }
 
         return domain_add_dev_info(dmar_domain, pdev, CONTEXT_TT_MULTI_LEVEL);
 }
@@ -3626,14 +3646,14 @@ static void intel_iommu_detach_device(struct iommu_domain *domain,
         domain_remove_one_dev_info(dmar_domain, pdev);
 }
 
-static int intel_iommu_map_range(struct iommu_domain *domain,
-                                 unsigned long iova, phys_addr_t hpa,
-                                 size_t size, int iommu_prot)
+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 addr_width;
         int prot = 0;
+        size_t size;
         int ret;
 
         if (iommu_prot & IOMMU_READ)
@@ -3643,20 +3663,17 @@ static int intel_iommu_map_range(struct iommu_domain *domain,
         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) {
-                int min_agaw;
                 u64 end;
 
                 /* check if minimum agaw is sufficient for mapped address */
-                min_agaw = vm_domain_min_agaw(dmar_domain);
-                addr_width = agaw_to_width(min_agaw);
-                end = DOMAIN_MAX_ADDR(addr_width);
-                end = end & VTD_PAGE_MASK;
+                end = __DOMAIN_MAX_ADDR(dmar_domain->gaw) + 1;
                 if (end < max_addr) {
-                        printk(KERN_ERR "%s: iommu agaw (%d) is not "
+                        printk(KERN_ERR "%s: iommu width (%d) is not "
                                "sufficient for the mapped address (%llx)\n",
-                               __func__, min_agaw, max_addr);
+                               __func__, dmar_domain->gaw, max_addr);
                         return -EFAULT;
                 }
                 dmar_domain->max_addr = max_addr;
@@ -3669,19 +3686,19 @@ static int intel_iommu_map_range(struct iommu_domain *domain,
         return ret;
 }
 
-static void intel_iommu_unmap_range(struct iommu_domain *domain,
-                                    unsigned long iova, size_t size)
+static int intel_iommu_unmap(struct iommu_domain *domain,
+                             unsigned long iova, int gfp_order)
 {
         struct dmar_domain *dmar_domain = domain->priv;
-
-        if (!size)
-                return;
+        size_t size = PAGE_SIZE << gfp_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 gfp_order;
 }
 
 static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
@@ -3705,6 +3722,8 @@ static int intel_iommu_domain_has_cap(struct iommu_domain *domain,
 
         if (cap == IOMMU_CAP_CACHE_COHERENCY)
                 return dmar_domain->iommu_snooping;
+        if (cap == IOMMU_CAP_INTR_REMAP)
+                return intr_remapping_enabled;
 
         return 0;
 }
@@ -3714,8 +3733,8 @@ static struct iommu_ops intel_iommu_ops = {
         .domain_destroy = intel_iommu_domain_destroy,
         .attach_dev     = intel_iommu_attach_device,
         .detach_dev     = intel_iommu_detach_device,
-        .map            = intel_iommu_map_range,
-        .unmap          = intel_iommu_unmap_range,
+        .map            = intel_iommu_map,
+        .unmap          = intel_iommu_unmap,
         .iova_to_phys   = intel_iommu_iova_to_phys,
         .domain_has_cap = intel_iommu_domain_has_cap,
 };
@@ -3728,10 +3747,43 @@ static void __devinit quirk_iommu_rwbf(struct pci_dev *dev)
          */
         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
diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index 95b849130ad4..ec87cd66f3eb 100644
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -1,6 +1,7 @@
 #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>
@@ -20,6 +21,8 @@ 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;
@@ -27,109 +30,40 @@ static __init int setup_nointremap(char *str)
 }
 early_param("nointremap", setup_nointremap);
 
-struct irq_2_iommu {
-        struct intel_iommu *iommu;
-        u16 irte_index;
-        u16 sub_handle;
-        u8  irte_mask;
-};
-
-#ifdef CONFIG_GENERIC_HARDIRQS
-static struct irq_2_iommu *get_one_free_irq_2_iommu(int node)
-{
-        struct irq_2_iommu *iommu;
-
-        iommu = kzalloc_node(sizeof(*iommu), GFP_ATOMIC, node);
-        printk(KERN_DEBUG "alloc irq_2_iommu on node %d\n", node);
-
-        return iommu;
-}
-
-static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
-{
-        struct irq_desc *desc;
-
-        desc = irq_to_desc(irq);
-
-        if (WARN_ON_ONCE(!desc))
-                return NULL;
-
-        return desc->irq_2_iommu;
-}
-
-static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
+static __init int setup_intremap(char *str)
 {
-        struct irq_desc *desc;
-        struct irq_2_iommu *irq_iommu;
-
-        desc = irq_to_desc(irq);
-        if (!desc) {
-                printk(KERN_INFO "can not get irq_desc for %d\n", irq);
-                return NULL;
-        }
+        if (!str)
+                return -EINVAL;
 
-        irq_iommu = desc->irq_2_iommu;
-
-        if (!irq_iommu)
-                desc->irq_2_iommu = get_one_free_irq_2_iommu(irq_node(irq));
-
-        return desc->irq_2_iommu;
-}
+        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;
 
-#else /* !CONFIG_SPARSE_IRQ */
-
-static struct irq_2_iommu irq_2_iommuX[NR_IRQS];
-
-static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
-{
-        if (irq < nr_irqs)
-                return &irq_2_iommuX[irq];
-
-        return NULL;
-}
-static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
-{
-        return irq_2_iommu(irq);
+        return 0;
 }
-#endif
+early_param("intremap", setup_intremap);
 
 static DEFINE_SPINLOCK(irq_2_ir_lock);
 
-static struct irq_2_iommu *valid_irq_2_iommu(unsigned int irq)
-{
-        struct irq_2_iommu *irq_iommu;
-
-        irq_iommu = irq_2_iommu(irq);
-
-        if (!irq_iommu)
-                return NULL;
-
-        if (!irq_iommu->iommu)
-                return NULL;
-
-        return irq_iommu;
-}
-
-int irq_remapped(int irq)
+static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
 {
-        return valid_irq_2_iommu(irq) != NULL;
+        struct irq_cfg *cfg = get_irq_chip_data(irq);
+        return cfg ? &cfg->irq_2_iommu : NULL;
 }
 
 int get_irte(int irq, struct irte *entry)
 {
-        int index;
-        struct irq_2_iommu *irq_iommu;
+        struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
         unsigned long flags;
+        int index;
 
-        if (!entry)
+        if (!entry || !irq_iommu)
                 return -1;
 
         spin_lock_irqsave(&irq_2_ir_lock, flags);
-        irq_iommu = valid_irq_2_iommu(irq);
-        if (!irq_iommu) {
-                spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-                return -1;
-        }
 
         index = irq_iommu->irte_index + irq_iommu->sub_handle;
         *entry = *(irq_iommu->iommu->ir_table->base + index);
@@ -141,20 +75,14 @@ int get_irte(int irq, struct irte *entry)
 int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 {
         struct ir_table *table = iommu->ir_table;
-        struct irq_2_iommu *irq_iommu;
+        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)
-                return -1;
-
-#ifndef CONFIG_SPARSE_IRQ
-        /* protect irq_2_iommu_alloc later */
-        if (irq >= nr_irqs)
+        if (!count || !irq_iommu)
                 return -1;
-#endif
 
         /*
          * start the IRTE search from index 0.
@@ -195,13 +123,6 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
         for (i = index; i < index + count; i++)
                 table->base[i].present = 1;
 
-        irq_iommu = irq_2_iommu_alloc(irq);
-        if (!irq_iommu) {
-                spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-                printk(KERN_ERR "can't allocate irq_2_iommu\n");
-                return -1;
-        }
-
         irq_iommu->iommu = iommu;
         irq_iommu->irte_index =  index;
         irq_iommu->sub_handle = 0;
@@ -225,17 +146,14 @@ static int qi_flush_iec(struct intel_iommu *iommu, int index, int mask)
 
 int map_irq_to_irte_handle(int irq, u16 *sub_handle)
 {
-        int index;
-        struct irq_2_iommu *irq_iommu;
+        struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
         unsigned long flags;
+        int index;
 
-        spin_lock_irqsave(&irq_2_ir_lock, flags);
-        irq_iommu = valid_irq_2_iommu(irq);
-        if (!irq_iommu) {
-                spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+        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);
@@ -244,18 +162,13 @@ int map_irq_to_irte_handle(int irq, u16 *sub_handle)
 
 int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
 {
-        struct irq_2_iommu *irq_iommu;
+        struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
         unsigned long flags;
 
-        spin_lock_irqsave(&irq_2_ir_lock, flags);
-
-        irq_iommu = irq_2_iommu_alloc(irq);
-
-        if (!irq_iommu) {
-                spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-                printk(KERN_ERR "can't allocate irq_2_iommu\n");
+        if (!irq_iommu)
                 return -1;
-        }
+
+        spin_lock_irqsave(&irq_2_ir_lock, flags);
 
         irq_iommu->iommu = iommu;
         irq_iommu->irte_index = index;
@@ -267,51 +180,26 @@ int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
         return 0;
 }
 
-int clear_irte_irq(int irq, struct intel_iommu *iommu, u16 index)
-{
-        struct irq_2_iommu *irq_iommu;
-        unsigned long flags;
-
-        spin_lock_irqsave(&irq_2_ir_lock, flags);
-        irq_iommu = valid_irq_2_iommu(irq);
-        if (!irq_iommu) {
-                spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-                return -1;
-        }
-
-        irq_iommu->iommu = NULL;
-        irq_iommu->irte_index = 0;
-        irq_iommu->sub_handle = 0;
-        irq_2_iommu(irq)->irte_mask = 0;
-
-        spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-
-        return 0;
-}
-
 int modify_irte(int irq, struct irte *irte_modified)
 {
-        int rc;
-        int index;
-        struct irte *irte;
+        struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
         struct intel_iommu *iommu;
-        struct irq_2_iommu *irq_iommu;
         unsigned long flags;
+        struct irte *irte;
+        int rc, index;
 
-        spin_lock_irqsave(&irq_2_ir_lock, flags);
-        irq_iommu = valid_irq_2_iommu(irq);
-        if (!irq_iommu) {
-                spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+        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((unsigned long *)&irte->low, irte_modified->low);
-        set_64bit((unsigned long *)&irte->high, irte_modified->high);
+        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);
@@ -320,31 +208,6 @@ int modify_irte(int irq, struct irte *irte_modified)
         return rc;
 }
 
-int flush_irte(int irq)
-{
-        int rc;
-        int index;
-        struct intel_iommu *iommu;
-        struct irq_2_iommu *irq_iommu;
-        unsigned long flags;
-
-        spin_lock_irqsave(&irq_2_ir_lock, flags);
-        irq_iommu = valid_irq_2_iommu(irq);
-        if (!irq_iommu) {
-                spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-                return -1;
-        }
-
-        iommu = irq_iommu->iommu;
-
-        index = irq_iommu->irte_index + irq_iommu->sub_handle;
-
-        rc = qi_flush_iec(iommu, index, irq_iommu->irte_mask);
-        spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-
-        return rc;
-}
-
 struct intel_iommu *map_hpet_to_ir(u8 hpet_id)
 {
         int i;
@@ -392,8 +255,8 @@ static int clear_entries(struct irq_2_iommu *irq_iommu)
         end = start + (1 << irq_iommu->irte_mask);
 
         for (entry = start; entry < end; entry++) {
-                set_64bit((unsigned long *)&entry->low, 0);
-                set_64bit((unsigned long *)&entry->high, 0);
+                set_64bit(&entry->low, 0);
+                set_64bit(&entry->high, 0);
         }
 
         return qi_flush_iec(iommu, index, irq_iommu->irte_mask);
@@ -401,16 +264,14 @@ static int clear_entries(struct irq_2_iommu *irq_iommu)
 
 int free_irte(int irq)
 {
-        int rc = 0;
-        struct irq_2_iommu *irq_iommu;
+        struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
         unsigned long flags;
+        int rc;
 
-        spin_lock_irqsave(&irq_2_ir_lock, flags);
-        irq_iommu = valid_irq_2_iommu(irq);
-        if (!irq_iommu) {
-                spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+        if (!irq_iommu)
                 return -1;
-        }
+
+        spin_lock_irqsave(&irq_2_ir_lock, flags);
 
         rc = clear_entries(irq_iommu);
 
@@ -452,6 +313,8 @@ int free_irte(int irq)
 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;
@@ -831,9 +694,9 @@ static int ir_parse_ioapic_hpet_scope(struct acpi_dmar_header *header,
                                 return -1;
                         }
 
-                        printk(KERN_INFO "IOAPIC id %d under DRHD base"
-                               " 0x%Lx\n", scope->enumeration_id,
-                               drhd->address);
+                        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) {
diff --git a/drivers/pci/ioapic.c b/drivers/pci/ioapic.c
index 3e0d7b5dd1b9..203508b227b7 100644
--- a/drivers/pci/ioapic.c
+++ b/drivers/pci/ioapic.c
@@ -18,6 +18,7 @@
 
 #include <linux/pci.h>
 #include <linux/acpi.h>
+#include <linux/slab.h>
 #include <acpi/acpi_bus.h>
 
 struct ioapic {
@@ -31,9 +32,9 @@ static int ioapic_probe(struct pci_dev *dev, const struct pci_device_id *ent)
         acpi_status status;
         unsigned long long gsb;
         struct ioapic *ioapic;
-        u64 addr;
         int ret;
         char *type;
+        struct resource *res;
 
         handle = DEVICE_ACPI_HANDLE(&dev->dev);
         if (!handle)
@@ -69,13 +70,12 @@ static int ioapic_probe(struct pci_dev *dev, const struct pci_device_id *ent)
         if (pci_request_region(dev, 0, type))
                 goto exit_disable;
 
-        addr = pci_resource_start(dev, 0);
-        if (acpi_register_ioapic(ioapic->handle, addr, ioapic->gsi_base))
+        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 %#llx, GSI %u\n", type, addr,
-                 ioapic->gsi_base);
+        dev_info(&dev->dev, "%s at %pR, GSI %u\n", type, res, ioapic->gsi_base);
         return 0;
 
 exit_release:
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index b2a448e19fe6..553d8ee55c1c 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/pci.h>
+#include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/string.h>
 #include <linux/delay.h>
@@ -607,7 +608,7 @@ int pci_iov_resource_bar(struct pci_dev *dev, int resno,
  * the VF BAR size multiplied by the number of VFs.  The alignment
  * is just the VF BAR size.
  */
-int pci_sriov_resource_alignment(struct pci_dev *dev, int resno)
+resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno)
 {
         struct resource tmp;
         enum pci_bar_type type;
@@ -706,6 +707,21 @@ irqreturn_t pci_sriov_migration(struct pci_dev *dev)
 }
 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;
diff --git a/drivers/pci/legacy.c b/drivers/pci/legacy.c
deleted file mode 100644
index 871f65c15936..000000000000
--- a/drivers/pci/legacy.c
+++ /dev/null
@@ -1,34 +0,0 @@
-#include <linux/init.h>
-#include <linux/pci.h>
-#include <linux/module.h>
-#include <linux/interrupt.h>
-#include "pci.h"
-
-/**
- * pci_find_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, 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.
- *
- * NOTE: Do not use this function any more; use pci_get_device() instead, as
- * the PCI device returned by this function can disappear at any moment in
- * time.
- */
-struct pci_dev *pci_find_device(unsigned int vendor, unsigned int device,
-                                struct pci_dev *from)
-{
-        struct pci_dev *pdev;
-
-        pci_dev_get(from);
-        pdev = pci_get_subsys(vendor, device, PCI_ANY_ID, PCI_ANY_ID, from);
-        pci_dev_put(pdev);
-        return pdev;
-}
-EXPORT_SYMBOL(pci_find_device);
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index f9cf3173b23d..44b0aeee83e5 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -18,6 +18,7 @@
 #include <linux/smp.h>
 #include <linux/errno.h>
 #include <linux/io.h>
+#include <linux/slab.h>
 
 #include "pci.h"
 #include "msi.h"
@@ -34,7 +35,12 @@ int arch_msi_check_device(struct pci_dev *dev, int nvec, int type)
 #endif
 
 #ifndef arch_setup_msi_irqs
-int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+# 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;
@@ -59,7 +65,12 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 #endif
 
 #ifndef arch_teardown_msi_irqs
-void arch_teardown_msi_irqs(struct pci_dev *dev)
+# 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;
 
@@ -157,8 +168,9 @@ 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 &= ~1;
-        mask_bits |= flag;
+        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;
@@ -169,32 +181,33 @@ static void msix_mask_irq(struct msi_desc *desc, u32 flag)
         desc->masked = __msix_mask_irq(desc, flag);
 }
 
-static void msi_set_mask_bit(unsigned irq, u32 flag)
+static void msi_set_mask_bit(struct irq_data *data, u32 flag)
 {
-        struct msi_desc *desc = get_irq_msi(irq);
+        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 = irq - desc->dev->irq;
+                unsigned offset = data->irq - desc->dev->irq;
                 msi_mask_irq(desc, 1 << offset, flag << offset);
         }
 }
 
-void mask_msi_irq(unsigned int irq)
+void mask_msi_irq(struct irq_data *data)
 {
-        msi_set_mask_bit(irq, 1);
+        msi_set_mask_bit(data, 1);
 }
 
-void unmask_msi_irq(unsigned int irq)
+void unmask_msi_irq(struct irq_data *data)
 {
-        msi_set_mask_bit(irq, 0);
+        msi_set_mask_bit(data, 0);
 }
 
-void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
+void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
-        struct msi_desc *entry = get_irq_desc_msi(desc);
+        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;
@@ -223,15 +236,33 @@ void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
 
 void read_msi_msg(unsigned int irq, struct msi_msg *msg)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
+        struct msi_desc *entry = get_irq_msi(irq);
 
-        read_msi_msg_desc(desc, msg);
+        __read_msi_msg(entry, msg);
 }
 
-void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
+void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
-        struct msi_desc *entry = get_irq_desc_msi(desc);
-        if (entry->msi_attrib.is_msix) {
+        /* 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 = get_irq_msi(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;
@@ -266,9 +297,9 @@ void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
 
 void write_msi_msg(unsigned int irq, struct msi_msg *msg)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
+        struct msi_desc *entry = get_irq_msi(irq);
 
-        write_msi_msg_desc(desc, msg);
+        __write_msi_msg(entry, msg);
 }
 
 static void free_msi_irqs(struct pci_dev *dev)
@@ -434,7 +465,7 @@ static int msi_capability_init(struct pci_dev *dev, int nvec)
 static void __iomem *msix_map_region(struct pci_dev *dev, unsigned pos,
                                                         unsigned nr_entries)
 {
-        unsigned long phys_addr;
+        resource_size_t phys_addr;
         u32 table_offset;
         u8 bir;
 
diff --git a/drivers/pci/msi.h b/drivers/pci/msi.h
index de27c1cb5a2b..65c42f80f23e 100644
--- a/drivers/pci/msi.h
+++ b/drivers/pci/msi.h
@@ -6,12 +6,6 @@
 #ifndef MSI_H
 #define MSI_H
 
-#define PCI_MSIX_ENTRY_SIZE             16
-#define  PCI_MSIX_ENTRY_LOWER_ADDR      0
-#define  PCI_MSIX_ENTRY_UPPER_ADDR      4
-#define  PCI_MSIX_ENTRY_DATA            8
-#define  PCI_MSIX_ENTRY_VECTOR_CTRL     12
-
 #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)
@@ -22,8 +16,8 @@
 #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 + 0x04)
-#define msix_pba_offset_reg(base)       (base + 0x08)
+#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))
 
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 7e2829538a4c..6fe0772e0e7d 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -16,8 +16,145 @@
 #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".
@@ -131,19 +268,92 @@ static int acpi_pci_sleep_wake(struct pci_dev *dev, bool 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) {
+                if (!dev->wakeup.run_wake_count++) {
+                        acpi_enable_wakeup_device_power(dev, ACPI_STATE_S0);
+                        acpi_enable_gpe(dev->wakeup.gpe_device,
+                                        dev->wakeup.gpe_number);
+                }
+        } else if (dev->wakeup.run_wake_count > 0) {
+                if (!--dev->wakeup.run_wake_count) {
+                        acpi_disable_gpe(dev->wakeup.gpe_device,
+                                         dev->wakeup.gpe_number);
+                        acpi_disable_wakeup_device_power(dev);
+                }
+        } else {
+                error = -EALREADY;
+        }
+
+        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;
-        acpi_integer    addr;
+        u64     addr;
 
         pci_dev = to_pci_dev(dev);
         /* Please ref to ACPI spec for the syntax of _ADR */
@@ -189,6 +399,7 @@ static int __init acpi_pci_init(void)
 
         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_clear_aspm();
                 pcie_no_aspm();
         }
 
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index e5d47be3c6d7..88246dd46452 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/cpu.h>
+#include <linux/pm_runtime.h>
 #include "pci.h"
 
 struct pci_dynid {
@@ -288,8 +289,26 @@ struct drv_dev_and_id {
 static long local_pci_probe(void *_ddi)
 {
         struct drv_dev_and_id *ddi = _ddi;
-
-        return ddi->drv->probe(ddi->dev, ddi->id);
+        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,
@@ -319,7 +338,7 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
 }
 
 /**
- * __pci_device_probe()
+ * __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
  * 
@@ -368,11 +387,19 @@ static int pci_device_remove(struct device * dev)
         struct pci_driver * drv = pci_dev->driver;
 
         if (drv) {
-                if (drv->remove)
+                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.
@@ -404,6 +431,36 @@ static void pci_device_shutdown(struct device *dev)
         pci_msix_shutdown(pci_dev);
 }
 
+#ifdef CONFIG_PM_OPS
+
+/* 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
 
 /*
@@ -520,29 +577,6 @@ static int pci_legacy_resume(struct device *dev)
 
 /* Auxiliary functions used by the new power management framework */
 
-/**
- * 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;
-        }
-
-        return pci_restore_state(pci_dev);
-}
-
-static void pci_pm_default_resume_noirq(struct pci_dev *pci_dev)
-{
-        pci_restore_standard_config(pci_dev);
-        pci_fixup_device(pci_fixup_resume_early, pci_dev);
-}
-
 static void pci_pm_default_resume(struct pci_dev *pci_dev)
 {
         pci_fixup_device(pci_fixup_resume, pci_dev);
@@ -581,6 +615,17 @@ 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_resume(dev);
+
         if (drv && drv->pm && drv->pm->prepare)
                 error = drv->pm->prepare(dev);
 
@@ -595,6 +640,13 @@ static void pci_pm_complete(struct device *dev)
                 drv->pm->complete(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)
@@ -681,7 +733,7 @@ static int pci_pm_resume_noirq(struct device *dev)
         struct device_driver *drv = dev->driver;
         int error = 0;
 
-        pci_pm_default_resume_noirq(pci_dev);
+        pci_pm_default_resume_early(pci_dev);
 
         if (pci_has_legacy_pm_support(pci_dev))
                 return pci_legacy_resume_early(dev);
@@ -879,7 +931,7 @@ static int pci_pm_restore_noirq(struct device *dev)
         struct device_driver *drv = dev->driver;
         int error = 0;
 
-        pci_pm_default_resume_noirq(pci_dev);
+        pci_pm_default_resume_early(pci_dev);
 
         if (pci_has_legacy_pm_support(pci_dev))
                 return pci_legacy_resume_early(dev);
@@ -931,6 +983,84 @@ static int pci_pm_restore(struct device *dev)
 
 #endif /* !CONFIG_HIBERNATION */
 
+#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_OPS
+
 const struct dev_pm_ops pci_dev_pm_ops = {
         .prepare = pci_pm_prepare,
         .complete = pci_pm_complete,
@@ -946,15 +1076,18 @@ const struct dev_pm_ops pci_dev_pm_ops = {
         .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 /* !CONFIG_PM_SLEEP */
+#else /* !COMFIG_PM_OPS */
 
 #define PCI_PM_OPS_PTR  NULL
 
-#endif /* !CONFIG_PM_SLEEP */
+#endif /* !COMFIG_PM_OPS */
 
 /**
  * __pci_register_driver - register a new pci driver
diff --git a/drivers/pci/pci-label.c b/drivers/pci/pci-label.c
new file mode 100644
index 000000000000..90c0a729cd3a
--- /dev/null
+++ b/drivers/pci/pci-label.c
@@ -0,0 +1,143 @@
+/*
+ * 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>
+ *
+ * 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 "pci.h"
+
+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)
+{
+        if (!sysfs_create_group(&pdev->dev.kobj, &smbios_attr_group))
+                return 0;
+        return -ENODEV;
+}
+
+static void
+pci_remove_smbiosname_file(struct pci_dev *pdev)
+{
+        sysfs_remove_group(&pdev->dev.kobj, &smbios_attr_group);
+}
+
+void pci_create_firmware_label_files(struct pci_dev *pdev)
+{
+        if (!pci_create_smbiosname_file(pdev))
+                ;
+}
+
+void pci_remove_firmware_label_files(struct pci_dev *pdev)
+{
+        pci_remove_smbiosname_file(pdev);
+}
diff --git a/drivers/pci/pci-stub.c b/drivers/pci/pci-stub.c
index f7b68ca6cc98..775e933c2225 100644
--- a/drivers/pci/pci-stub.c
+++ b/drivers/pci/pci-stub.c
@@ -47,6 +47,10 @@ static int __init pci_stub_init(void)
         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, ","))) {
@@ -54,6 +58,9 @@ static int __init pci_stub_init(void)
                         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);
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 807224ec8351..8ecaac983923 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -21,8 +21,10 @@
 #include <linux/stat.h>
 #include <linux/topology.h>
 #include <linux/mm.h>
+#include <linux/fs.h>
 #include <linux/capability.h>
 #include <linux/pci-aspm.h>
+#include <linux/slab.h>
 #include "pci.h"
 
 static int sysfs_initialized;   /* = 0 */
@@ -356,7 +358,8 @@ boot_vga_show(struct device *dev, struct device_attribute *attr, char *buf)
 struct device_attribute vga_attr = __ATTR_RO(boot_vga);
 
 static ssize_t
-pci_read_config(struct kobject *kobj, struct bin_attribute *bin_attr,
+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));
@@ -365,7 +368,7 @@ pci_read_config(struct kobject *kobj, struct bin_attribute *bin_attr,
         u8 *data = (u8*) buf;
 
         /* Several chips lock up trying to read undefined config space */
-        if (capable(CAP_SYS_ADMIN)) {
+        if (cap_raised(filp->f_cred->cap_effective, CAP_SYS_ADMIN)) {
                 size = dev->cfg_size;
         } else if (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) {
                 size = 128;
@@ -429,7 +432,8 @@ pci_read_config(struct kobject *kobj, struct bin_attribute *bin_attr,
 }
 
 static ssize_t
-pci_write_config(struct kobject *kobj, struct bin_attribute *bin_attr,
+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));
@@ -486,7 +490,8 @@ pci_write_config(struct kobject *kobj, struct bin_attribute *bin_attr,
 }
 
 static ssize_t
-read_vpd_attr(struct kobject *kobj, struct bin_attribute *bin_attr,
+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 =
@@ -501,7 +506,8 @@ read_vpd_attr(struct kobject *kobj, struct bin_attribute *bin_attr,
 }
 
 static ssize_t
-write_vpd_attr(struct kobject *kobj, struct bin_attribute *bin_attr,
+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 =
@@ -518,6 +524,7 @@ write_vpd_attr(struct kobject *kobj, struct bin_attribute *bin_attr,
 #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
@@ -528,7 +535,8 @@ write_vpd_attr(struct kobject *kobj, struct bin_attribute *bin_attr,
  * callback routine (pci_legacy_read).
  */
 static ssize_t
-pci_read_legacy_io(struct kobject *kobj, struct bin_attribute *bin_attr,
+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,
@@ -544,6 +552,7 @@ pci_read_legacy_io(struct kobject *kobj, struct bin_attribute *bin_attr,
 
 /**
  * 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
@@ -554,7 +563,8 @@ pci_read_legacy_io(struct kobject *kobj, struct bin_attribute *bin_attr,
  * callback routine (pci_legacy_write).
  */
 static ssize_t
-pci_write_legacy_io(struct kobject *kobj, struct bin_attribute *bin_attr,
+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,
@@ -569,6 +579,7 @@ pci_write_legacy_io(struct kobject *kobj, struct bin_attribute *bin_attr,
 
 /**
  * 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
@@ -578,7 +589,8 @@ pci_write_legacy_io(struct kobject *kobj, struct bin_attribute *bin_attr,
  * memory space.
  */
 static int
-pci_mmap_legacy_mem(struct kobject *kobj, struct bin_attribute *attr,
+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,
@@ -590,6 +602,7 @@ pci_mmap_legacy_mem(struct kobject *kobj, struct bin_attribute *attr,
 
 /**
  * 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
@@ -599,7 +612,8 @@ pci_mmap_legacy_mem(struct kobject *kobj, struct bin_attribute *attr,
  * memory space. Returns -ENOSYS if the operation isn't supported
  */
 static int
-pci_mmap_legacy_io(struct kobject *kobj, struct bin_attribute *attr,
+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,
@@ -642,6 +656,7 @@ void pci_create_legacy_files(struct pci_bus *b)
         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;
@@ -655,6 +670,7 @@ void pci_create_legacy_files(struct pci_bus *b)
 
         /* 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;
@@ -689,17 +705,21 @@ void pci_remove_legacy_files(struct pci_bus *b)
 
 #ifdef HAVE_PCI_MMAP
 
-int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vma)
+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;
+        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;
-        if (start < size && size - start >= nr)
+        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;
-        WARN(1, "process \"%s\" tried to map 0x%08lx-0x%08lx on %s BAR %d (size 0x%08lx)\n",
-                current->comm, start, start+nr, pci_name(pdev), resno, size);
         return 0;
 }
 
@@ -718,7 +738,7 @@ pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
 {
         struct pci_dev *pdev = to_pci_dev(container_of(kobj,
                                                        struct device, kobj));
-        struct resource *res = (struct resource *)attr->private;
+        struct resource *res = attr->private;
         enum pci_mmap_state mmap_type;
         resource_size_t start, end;
         int i;
@@ -729,8 +749,15 @@ pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
         if (i >= PCI_ROM_RESOURCE)
                 return -ENODEV;
 
-        if (!pci_mmap_fits(pdev, i, vma))
+        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
@@ -747,19 +774,85 @@ pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
 }
 
 static int
-pci_mmap_resource_uc(struct kobject *kobj, struct bin_attribute *attr,
+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 kobject *kobj, struct bin_attribute *attr,
+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
@@ -800,6 +893,7 @@ static int pci_create_attr(struct pci_dev *pdev, int num, int write_combine)
         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);
@@ -809,6 +903,10 @@ static int pci_create_attr(struct pci_dev *pdev, int num, int write_combine)
                         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);
@@ -857,6 +955,7 @@ void __weak pci_remove_resource_files(struct pci_dev *dev) { return; }
 
 /**
  * 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
@@ -866,7 +965,8 @@ void __weak pci_remove_resource_files(struct pci_dev *dev) { return; }
  * writing anything except 0 enables it
  */
 static ssize_t
-pci_write_rom(struct kobject *kobj, struct bin_attribute *bin_attr,
+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));
@@ -881,6 +981,7 @@ pci_write_rom(struct kobject *kobj, struct bin_attribute *bin_attr,
 
 /**
  * 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
@@ -891,7 +992,8 @@ pci_write_rom(struct kobject *kobj, struct bin_attribute *bin_attr,
  * device corresponding to @kobj.
  */
 static ssize_t
-pci_read_rom(struct kobject *kobj, struct bin_attribute *bin_attr,
+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));
@@ -956,7 +1058,12 @@ static ssize_t reset_store(struct device *dev,
 
         if (val != 1)
                 return -EINVAL;
-        return pci_reset_function(pdev);
+
+        result = pci_reset_function(pdev);
+        if (result < 0)
+                return result;
+
+        return count;
 }
 
 static struct device_attribute reset_attr = __ATTR(reset, 0200, NULL, reset_store);
@@ -972,6 +1079,7 @@ static int pci_create_capabilities_sysfs(struct pci_dev *dev)
                 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;
@@ -1038,9 +1146,10 @@ int __must_check pci_create_sysfs_dev_files (struct pci_dev *pdev)
                         retval = -ENOMEM;
                         goto err_resource_files;
                 }
+                sysfs_bin_attr_init(attr);
                 attr->size = rom_size;
                 attr->attr.name = "rom";
-                attr->attr.mode = S_IRUSR;
+                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);
@@ -1067,6 +1176,8 @@ int __must_check pci_create_sysfs_dev_files (struct pci_dev *pdev)
         if (retval)
                 goto err_vga_file;
 
+        pci_create_firmware_label_files(pdev);
+
         return 0;
 
 err_vga_file:
@@ -1134,6 +1245,9 @@ void pci_remove_sysfs_dev_files(struct pci_dev *pdev)
                 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)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 315fea47e784..b714d787bddd 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -12,6 +12,7 @@
 #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>
@@ -19,8 +20,8 @@
 #include <linux/pci-aspm.h>
 #include <linux/pm_wakeup.h>
 #include <linux/interrupt.h>
-#include <asm/dma.h>    /* isa_dma_bridge_buggy */
 #include <linux/device.h>
+#include <linux/pm_runtime.h>
 #include <asm/setup.h>
 #include "pci.h"
 
@@ -29,8 +30,27 @@ const char *pci_power_names[] = {
 };
 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;
@@ -297,6 +317,49 @@ int pci_find_ext_capability(struct pci_dev *dev, int cap)
 }
 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;
@@ -380,10 +443,9 @@ 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;
+        struct resource *best = NULL, *r;
 
-        for(i = 0; i < PCI_BUS_NUM_RESOURCES; i++) {
-                struct resource *r = bus->resource[i];
+        pci_bus_for_each_resource(bus, r, i) {
                 if (!r)
                         continue;
                 if (res->start && !(res->start >= r->start && res->end <= r->end))
@@ -457,6 +519,12 @@ static inline int platform_pci_sleep_wake(struct pci_dev *dev, bool enable)
                         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
@@ -624,7 +692,7 @@ static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state)
  */
 int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state)
 {
-        return state > PCI_D0 ?
+        return state >= PCI_D0 ?
                         pci_platform_power_transition(dev, state) : -EINVAL;
 }
 EXPORT_SYMBOL_GPL(__pci_complete_power_transition);
@@ -661,10 +729,6 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
                  */
                 return 0;
 
-        /* Check if we're already there */
-        if (dev->current_state == state)
-                return 0;
-
         __pci_start_power_transition(dev, state);
 
         /* This device is quirked not to be put into D3, so
@@ -873,14 +937,13 @@ pci_save_state(struct pci_dev *dev)
  * pci_restore_state - Restore the saved state of a PCI device
  * @dev: - PCI device that we're dealing with
  */
-int 
-pci_restore_state(struct pci_dev *dev)
+void pci_restore_state(struct pci_dev *dev)
 {
         int i;
         u32 val;
 
         if (!dev->state_saved)
-                return 0;
+                return;
 
         /* PCI Express register must be restored first */
         pci_restore_pcie_state(dev);
@@ -904,8 +967,6 @@ pci_restore_state(struct pci_dev *dev)
         pci_restore_iov_state(dev);
 
         dev->state_saved = false;
-
-        return 0;
 }
 
 static int do_pci_enable_device(struct pci_dev *dev, int bars)
@@ -943,6 +1004,18 @@ static int __pci_enable_device_flags(struct pci_dev *dev,
         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 */
 
@@ -1142,7 +1215,7 @@ void pci_disable_enabled_device(struct pci_dev *dev)
  * anymore.  This only involves disabling PCI bus-mastering, if active.
  *
  * Note we don't actually disable the device until all callers of
- * pci_device_enable() have called pci_device_disable().
+ * pci_enable_device() have called pci_disable_device().
  */
 void
 pci_disable_device(struct pci_dev *dev)
@@ -1190,6 +1263,68 @@ int pci_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state 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#.
@@ -1202,6 +1337,32 @@ bool pci_pme_capable(struct pci_dev *dev, pci_power_t state)
         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.
@@ -1225,14 +1386,53 @@ void pci_pme_active(struct pci_dev *dev, bool 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
+ * __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.
@@ -1248,11 +1448,12 @@ void pci_pme_active(struct pci_dev *dev, bool enable)
  * 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 enable)
+int __pci_enable_wake(struct pci_dev *dev, pci_power_t state,
+                      bool runtime, bool enable)
 {
         int ret = 0;
 
-        if (enable && !device_may_wakeup(&dev->dev))
+        if (enable && !runtime && !device_may_wakeup(&dev->dev))
                 return -EINVAL;
 
         /* Don't do the same thing twice in a row for one device. */
@@ -1272,19 +1473,24 @@ int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable)
                         pci_pme_active(dev, true);
                 else
                         ret = 1;
-                error = platform_pci_sleep_wake(dev, true);
+                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 {
-                platform_pci_sleep_wake(dev, false);
+                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
@@ -1385,7 +1591,7 @@ int pci_prepare_to_sleep(struct pci_dev *dev)
  * pci_back_from_sleep - turn PCI device on during system-wide transition into working state
  * @dev: Device to handle.
  *
- * Disable device's sytem wake-up capability and put it into D0.
+ * Disable device's system wake-up capability and put it into D0.
  */
 int pci_back_from_sleep(struct pci_dev *dev)
 {
@@ -1394,6 +1600,66 @@ int pci_back_from_sleep(struct pci_dev *dev)
 }
 
 /**
+ * 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.
  */
@@ -1402,7 +1668,10 @@ 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 */
@@ -1450,7 +1719,6 @@ void pci_pm_init(struct pci_dev *dev)
                  * let the user space enable it to wake up the system as needed.
                  */
                 device_set_wakeup_capable(&dev->dev, true);
-                device_set_wakeup_enable(&dev->dev, false);
                 /* Disable the PME# generation functionality */
                 pci_pme_active(dev, false);
         } else {
@@ -1474,7 +1742,6 @@ void platform_pci_wakeup_init(struct pci_dev *dev)
                 return;
 
         device_set_wakeup_capable(&dev->dev, true);
-        device_set_wakeup_enable(&dev->dev, false);
         platform_pci_sleep_wake(dev, false);
 }
 
@@ -2113,51 +2380,19 @@ void pci_msi_off(struct pci_dev *dev)
                 pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
         }
 }
+EXPORT_SYMBOL_GPL(pci_msi_off);
 
-#ifndef HAVE_ARCH_PCI_SET_DMA_MASK
-/*
- * These can be overridden by arch-specific implementations
- */
-int
-pci_set_dma_mask(struct pci_dev *dev, u64 mask)
-{
-        if (!pci_dma_supported(dev, mask))
-                return -EIO;
-
-        dev->dma_mask = mask;
-        dev_dbg(&dev->dev, "using %dbit DMA mask\n", fls64(mask));
-
-        return 0;
-}
-    
-int
-pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask)
-{
-        if (!pci_dma_supported(dev, mask))
-                return -EIO;
-
-        dev->dev.coherent_dma_mask = mask;
-        dev_dbg(&dev->dev, "using %dbit consistent DMA mask\n", fls64(mask));
-
-        return 0;
-}
-#endif
-
-#ifndef HAVE_ARCH_PCI_SET_DMA_MAX_SEGMENT_SIZE
 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);
-#endif
 
-#ifndef HAVE_ARCH_PCI_SET_DMA_SEGMENT_BOUNDARY
 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);
-#endif
 
 static int pcie_flr(struct pci_dev *dev, int probe)
 {
@@ -2304,7 +2539,7 @@ static int pci_dev_reset(struct pci_dev *dev, int probe)
         if (!probe) {
                 pci_block_user_cfg_access(dev);
                 /* block PM suspend, driver probe, etc. */
-                down(&dev->dev.sem);
+                device_lock(&dev->dev);
         }
 
         rc = pci_dev_specific_reset(dev, probe);
@@ -2326,7 +2561,7 @@ static int pci_dev_reset(struct pci_dev *dev, int probe)
         rc = pci_parent_bus_reset(dev, probe);
 done:
         if (!probe) {
-                up(&dev->dev.sem);
+                device_unlock(&dev->dev);
                 pci_unblock_user_cfg_access(dev);
         }
 
@@ -2421,18 +2656,17 @@ EXPORT_SYMBOL_GPL(pci_reset_function);
  */
 int pcix_get_max_mmrbc(struct pci_dev *dev)
 {
-        int err, cap;
+        int cap;
         u32 stat;
 
         cap = pci_find_capability(dev, PCI_CAP_ID_PCIX);
         if (!cap)
                 return -EINVAL;
 
-        err = pci_read_config_dword(dev, cap + PCI_X_STATUS, &stat);
-        if (err)
+        if (pci_read_config_dword(dev, cap + PCI_X_STATUS, &stat))
                 return -EINVAL;
 
-        return (stat & PCI_X_STATUS_MAX_READ) >> 12;
+        return 512 << ((stat & PCI_X_STATUS_MAX_READ) >> 21);
 }
 EXPORT_SYMBOL(pcix_get_max_mmrbc);
 
@@ -2445,18 +2679,17 @@ EXPORT_SYMBOL(pcix_get_max_mmrbc);
  */
 int pcix_get_mmrbc(struct pci_dev *dev)
 {
-        int ret, cap;
-        u32 cmd;
+        int cap;
+        u16 cmd;
 
         cap = pci_find_capability(dev, PCI_CAP_ID_PCIX);
         if (!cap)
                 return -EINVAL;
 
-        ret = pci_read_config_dword(dev, cap + PCI_X_CMD, &cmd);
-        if (!ret)
-                ret = 512 << ((cmd & PCI_X_CMD_MAX_READ) >> 2);
+        if (pci_read_config_word(dev, cap + PCI_X_CMD, &cmd))
+                return -EINVAL;
 
-        return ret;
+        return 512 << ((cmd & PCI_X_CMD_MAX_READ) >> 2);
 }
 EXPORT_SYMBOL(pcix_get_mmrbc);
 
@@ -2471,28 +2704,27 @@ EXPORT_SYMBOL(pcix_get_mmrbc);
  */
 int pcix_set_mmrbc(struct pci_dev *dev, int mmrbc)
 {
-        int cap, err = -EINVAL;
-        u32 stat, cmd, v, o;
+        int cap;
+        u32 stat, v, o;
+        u16 cmd;
 
         if (mmrbc < 512 || mmrbc > 4096 || !is_power_of_2(mmrbc))
-                goto out;
+                return -EINVAL;
 
         v = ffs(mmrbc) - 10;
 
         cap = pci_find_capability(dev, PCI_CAP_ID_PCIX);
         if (!cap)
-                goto out;
+                return -EINVAL;
 
-        err = pci_read_config_dword(dev, cap + PCI_X_STATUS, &stat);
-        if (err)
-                goto out;
+        if (pci_read_config_dword(dev, cap + PCI_X_STATUS, &stat))
+                return -EINVAL;
 
         if (v > (stat & PCI_X_STATUS_MAX_READ) >> 21)
                 return -E2BIG;
 
-        err = pci_read_config_dword(dev, cap + PCI_X_CMD, &cmd);
-        if (err)
-                goto out;
+        if (pci_read_config_word(dev, cap + PCI_X_CMD, &cmd))
+                return -EINVAL;
 
         o = (cmd & PCI_X_CMD_MAX_READ) >> 2;
         if (o != v) {
@@ -2502,10 +2734,10 @@ int pcix_set_mmrbc(struct pci_dev *dev, int mmrbc)
 
                 cmd &= ~PCI_X_CMD_MAX_READ;
                 cmd |= v << 2;
-                err = pci_write_config_dword(dev, cap + PCI_X_CMD, cmd);
+                if (pci_write_config_word(dev, cap + PCI_X_CMD, cmd))
+                        return -EIO;
         }
-out:
-        return err;
+        return 0;
 }
 EXPORT_SYMBOL(pcix_set_mmrbc);
 
@@ -2527,7 +2759,7 @@ int pcie_get_readrq(struct pci_dev *dev)
 
         ret = pci_read_config_word(dev, cap + PCI_EXP_DEVCTL, &ctl);
         if (!ret)
-        ret = 128 << ((ctl & PCI_EXP_DEVCTL_READRQ) >> 12);
+                ret = 128 << ((ctl & PCI_EXP_DEVCTL_READRQ) >> 12);
 
         return ret;
 }
@@ -2615,6 +2847,23 @@ int pci_resource_bar(struct pci_dev *dev, int resno, enum pci_bar_type *type)
         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, bool change_bridge)
+{
+        if (arch_set_vga_state)
+                return arch_set_vga_state(dev, decode, command_bits,
+                                                change_bridge);
+        return 0;
+}
+
 /**
  * pci_set_vga_state - set VGA decode state on device and parents if requested
  * @dev: the PCI device
@@ -2628,9 +2877,15 @@ int pci_set_vga_state(struct pci_dev *dev, bool decode,
         struct pci_bus *bus;
         struct pci_dev *bridge;
         u16 cmd;
+        int rc;
 
         WARN_ON(command_bits & ~(PCI_COMMAND_IO|PCI_COMMAND_MEMORY));
 
+        /* ARCH specific VGA enables */
+        rc = pci_set_vga_state_arch(dev, decode, command_bits, change_bridge);
+        if (rc)
+                return rc;
+
         pci_read_config_word(dev, PCI_COMMAND, &cmd);
         if (decode == true)
                 cmd |= command_bits;
@@ -2860,8 +3115,6 @@ EXPORT_SYMBOL(pci_set_mwi);
 EXPORT_SYMBOL(pci_try_set_mwi);
 EXPORT_SYMBOL(pci_clear_mwi);
 EXPORT_SYMBOL_GPL(pci_intx);
-EXPORT_SYMBOL(pci_set_dma_mask);
-EXPORT_SYMBOL(pci_set_consistent_dma_mask);
 EXPORT_SYMBOL(pci_assign_resource);
 EXPORT_SYMBOL(pci_find_parent_resource);
 EXPORT_SYMBOL(pci_select_bars);
@@ -2871,10 +3124,8 @@ EXPORT_SYMBOL(pci_save_state);
 EXPORT_SYMBOL(pci_restore_state);
 EXPORT_SYMBOL(pci_pme_capable);
 EXPORT_SYMBOL(pci_pme_active);
-EXPORT_SYMBOL(pci_enable_wake);
 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
index fbd0e3adbca3..f69d6e0fda75 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -11,10 +11,24 @@
 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);
+#ifndef CONFIG_DMI
+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 *vma);
+                         struct vm_area_struct *vmai,
+                         enum pci_mmap_api mmap_api);
 #endif
 int pci_probe_reset_function(struct pci_dev *dev);
 
@@ -35,6 +49,10 @@ int pci_probe_reset_function(struct pci_dev *dev);
  *
  * @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.
  */
@@ -44,15 +62,24 @@ struct pci_platform_pm_ops {
         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);
@@ -119,12 +146,6 @@ static inline void pci_no_msi(void) { }
 static inline void pci_msi_init_pci_dev(struct pci_dev *dev) { }
 #endif
 
-#ifdef CONFIG_PCIEAER
-void pci_no_aer(void);
-#else
-static inline void pci_no_aer(void) { }
-#endif
-
 static inline int pci_no_d1d2(struct pci_dev *dev)
 {
         unsigned int parent_dstates = 0;
@@ -235,7 +256,7 @@ struct pci_ats {
         int stu;        /* Smallest Translation Unit */
         int qdep;       /* Invalidate Queue Depth */
         int ref_cnt;    /* Physical Function reference count */
-        int is_enabled:1;       /* Enable bit is set */
+        unsigned int is_enabled:1;      /* Enable bit is set */
 };
 
 #ifdef CONFIG_PCI_IOV
@@ -243,7 +264,8 @@ 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 int pci_sriov_resource_alignment(struct pci_dev *dev, int resno);
+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);
 
@@ -299,7 +321,7 @@ static inline int pci_ats_enabled(struct pci_dev *dev)
 }
 #endif /* CONFIG_PCI_IOV */
 
-static inline int pci_resource_alignment(struct pci_dev *dev,
+static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,
                                          struct resource *res)
 {
 #ifdef CONFIG_PCI_IOV
@@ -319,6 +341,13 @@ struct pci_dev_reset_methods {
         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
index 5a0c6ad53f8e..dda70981b7a6 100644
--- a/drivers/pci/pcie/Kconfig
+++ b/drivers/pci/pcie/Kconfig
@@ -31,14 +31,22 @@ source "drivers/pci/pcie/aer/Kconfig"
 # PCI Express ASPM
 #
 config PCIEASPM
-        bool "PCI Express ASPM support(Experimental)"
-        depends on PCI && EXPERIMENTAL && PCIEPORTBUS
-        default n
+        bool "PCI Express ASPM control" if EMBEDDED
+        depends on PCI && PCIEPORTBUS
+        default y
         help
-          This enables PCI Express ASPM (Active State Power Management) and
-          Clock Power Management. ASPM supports state L0/L0s/L1.
+          This enables OS control over PCI Express ASPM (Active State
+          Power Management) and Clock Power Management. ASPM supports
+          state L0/L0s/L1.
 
-          When in doubt, say N.
+          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
@@ -46,3 +54,7 @@ config PCIEASPM_DEBUG
         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
index 11f6bb1eae24..00c62df5a9fc 100644
--- a/drivers/pci/pcie/Makefile
+++ b/drivers/pci/pcie/Makefile
@@ -6,8 +6,11 @@
 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/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c
index 223052b73563..b3cf6223f63a 100644
--- a/drivers/pci/pcie/aer/aer_inject.c
+++ b/drivers/pci/pcie/aer/aer_inject.c
@@ -21,6 +21,7 @@
 #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>
@@ -167,7 +168,7 @@ static u32 *find_pci_config_dword(struct aer_error *err, int where,
                 target = &err->root_status;
                 rw1cs = 1;
                 break;
-        case PCI_ERR_ROOT_COR_SRC:
+        case PCI_ERR_ROOT_ERR_SRC:
                 target = &err->source_id;
                 break;
         }
@@ -471,6 +472,7 @@ static ssize_t aer_inject_write(struct file *filp, const char __user *ubuf,
 static const struct file_operations aer_inject_fops = {
         .write = aer_inject_write,
         .owner = THIS_MODULE,
+        .llseek = noop_llseek,
 };
 
 static struct miscdevice aer_inject_device = {
diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c
index 21f215f4daa3..58ad7917553c 100644
--- a/drivers/pci/pcie/aer/aerdrv.c
+++ b/drivers/pci/pcie/aer/aerdrv.c
@@ -17,6 +17,7 @@
 
 #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>
@@ -25,6 +26,7 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/pcieport_if.h>
+#include <linux/slab.h>
 
 #include "aerdrv.h"
 #include "../../pci.h"
@@ -71,13 +73,125 @@ 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;
@@ -96,13 +210,13 @@ irqreturn_t aer_irq(int irq, void *context)
 
         /* Read error status */
         pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, &status);
-        if (!(status & ROOT_ERR_STATUS_MASKS)) {
+        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_COR_SRC, &id);
+        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 */
@@ -134,7 +248,7 @@ EXPORT_SYMBOL_GPL(aer_irq);
  * @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;
@@ -143,15 +257,11 @@ static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev)
         if (!rpc)
                 return NULL;
 
-        /*
-         * Initialize Root lock access, e_lock, to Root Error Status Reg,
-         * Root Error ID Reg, and Root error producer/consumer index.
-         */
+        /* 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);
-        rpc->prod_idx = rpc->cons_idx = 0;
         mutex_init(&rpc->rpc_mutex);
         init_waitqueue_head(&rpc->wait_release);
 
@@ -166,7 +276,7 @@ static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev)
  * @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);
@@ -178,7 +288,8 @@ static void aer_remove(struct pcie_device *dev)
 
                 wait_event(rpc->wait_release, rpc->prod_idx == rpc->cons_idx);
 
-                aer_delete_rootport(rpc);
+                aer_disable_rootport(rpc);
+                kfree(rpc);
                 set_service_data(dev, NULL);
         }
 }
@@ -189,7 +300,7 @@ static void aer_remove(struct pcie_device *dev)
  * @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;
@@ -229,41 +340,30 @@ static int __devinit aer_probe(struct pcie_device *dev)
  * @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)
 {
-        u16 p2p_ctrl;
-        u32 status;
+        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_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, 0);
+        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);
 
-        /* Assert Secondary Bus Reset */
-        pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &p2p_ctrl);
-        p2p_ctrl |= PCI_CB_BRIDGE_CTL_CB_RESET;
-        pci_write_config_word(dev, PCI_BRIDGE_CONTROL, p2p_ctrl);
-
-        /* De-assert Secondary Bus Reset */
-        p2p_ctrl &= ~PCI_CB_BRIDGE_CTL_CB_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);
+        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_STATUS, &status);
-        pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, status);
-        pci_write_config_dword(dev,
-                pos + PCI_ERR_ROOT_COMMAND,
-                ROOT_PORT_INTR_ON_MESG_MASK);
+        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;
 }
@@ -274,7 +374,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
  * @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)
 {
@@ -287,7 +387,7 @@ static pci_ers_result_t aer_error_detected(struct pci_dev *dev,
  * @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;
@@ -314,12 +414,10 @@ static void aer_error_resume(struct pci_dev *dev)
  * aer_service_init - register AER root service driver
  *
  * Invoked when AER root service driver is loaded.
- **/
+ */
 static int __init aer_service_init(void)
 {
-        if (pcie_aer_disable)
-                return -ENXIO;
-        if (!pci_msi_enabled())
+        if (!pci_aer_available() || aer_acpi_firmware_first())
                 return -ENXIO;
         return pcie_port_service_register(&aerdriver);
 }
@@ -328,7 +426,7 @@ static int __init aer_service_init(void)
  * 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);
diff --git a/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h
index bd833ea3ba49..80c11d131499 100644
--- a/drivers/pci/pcie/aer/aerdrv.h
+++ b/drivers/pci/pcie/aer/aerdrv.h
@@ -17,9 +17,6 @@
 #define AER_FATAL                       1
 #define AER_CORRECTABLE                 2
 
-/* Root Error Status Register Bits */
-#define ROOT_ERR_STATUS_MASKS           0x0f
-
 #define SYSTEM_ERROR_INTR_ON_MESG_MASK  (PCI_EXP_RTCTL_SECEE|   \
                                         PCI_EXP_RTCTL_SENFEE|   \
                                         PCI_EXP_RTCTL_SEFEE)
@@ -117,8 +114,7 @@ static inline pci_ers_result_t merge_result(enum pci_ers_result orig,
 }
 
 extern struct bus_type pcie_port_bus_type;
-extern void aer_enable_rootport(struct aer_rpc *rpc);
-extern void aer_delete_rootport(struct aer_rpc *rpc);
+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);
@@ -134,4 +130,21 @@ static inline int aer_osc_setup(struct pcie_device *pciedev)
 }
 #endif
 
+#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
index 04814087658d..275bf158ffa7 100644
--- a/drivers/pci/pcie/aer/aerdrv_acpi.c
+++ b/drivers/pci/pcie/aer/aerdrv_acpi.c
@@ -16,40 +16,115 @@
 #include <linux/acpi.h>
 #include <linux/pci-acpi.h>
 #include <linux/delay.h>
+#include <acpi/apei.h>
 #include "aerdrv.h"
 
-/**
- * aer_osc_setup - run ACPI _OSC method
- * @pciedev: pcie_device which AER is being enabled on
- *
- * @return: Zero on success. Nonzero otherwise.
- *
- * Invoked when PCIe bus loads AER service driver. To avoid conflict with
- * BIOS AER support requires BIOS to yield AER control to OS native driver.
- **/
-int aer_osc_setup(struct pcie_device *pciedev)
+#ifdef CONFIG_ACPI_APEI
+static inline int hest_match_pci(struct acpi_hest_aer_common *p,
+                                 struct pci_dev *pci)
 {
-        acpi_status status = AE_NOT_FOUND;
-        struct pci_dev *pdev = pciedev->port;
-        acpi_handle handle = NULL;
-
-        if (acpi_pci_disabled)
-                return -1;
-
-        handle = acpi_find_root_bridge_handle(pdev);
-        if (handle) {
-                status = acpi_pci_osc_control_set(handle,
-                                        OSC_PCI_EXPRESS_AER_CONTROL |
-                                        OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL);
-        }
+        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;
 
-        if (ACPI_FAILURE(status)) {
-                dev_printk(KERN_DEBUG, &pciedev->device, "AER service couldn't "
-                           "init device: %s\n",
-                           (status == AE_SUPPORT || status == AE_NOT_FOUND) ?
-                           "no _OSC support" : "_OSC failed");
-                return -1;
+        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
index c843a799814d..43421fbe080a 100644
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -23,6 +23,7 @@
 #include <linux/pm.h>
 #include <linux/suspend.h>
 #include <linux/delay.h>
+#include <linux/slab.h>
 #include "aerdrv.h"
 
 static int forceload;
@@ -35,7 +36,7 @@ int pci_enable_pcie_error_reporting(struct pci_dev *dev)
         u16 reg16 = 0;
         int pos;
 
-        if (dev->aer_firmware_first)
+        if (pcie_aer_get_firmware_first(dev))
                 return -EIO;
 
         pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
@@ -46,13 +47,12 @@ int pci_enable_pcie_error_reporting(struct pci_dev *dev)
         if (!pos)
                 return -EIO;
 
-        pci_read_config_word(dev, pos+PCI_EXP_DEVCTL, &reg16);
-        reg16 = reg16 |
-                PCI_EXP_DEVCTL_CERE |
+        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);
+                PCI_EXP_DEVCTL_URRE);
+        pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, reg16);
 
         return 0;
 }
@@ -63,19 +63,19 @@ int pci_disable_pcie_error_reporting(struct pci_dev *dev)
         u16 reg16 = 0;
         int pos;
 
-        if (dev->aer_firmware_first)
+        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 = 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);
+        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;
 }
@@ -98,99 +98,46 @@ int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status);
 
-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.
+ * add_error_device - list device to be handled
+ * @e_info: pointer to error info
+ * @dev: pointer to pci_dev to be added
  */
-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);
-}
-
-static inline int compare_device_id(struct pci_dev *dev,
-                        struct aer_err_info *e_info)
-{
-        if (e_info->id == ((dev->bus->number << 8) | dev->devfn)) {
-                /*
-                 * Device ID match
-                 */
-                return 1;
-        }
-
-        return 0;
-}
-
 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 1;
+                return 0;
         }
-
-        return 0;
+        return -ENOSPC;
 }
 
-
 #define PCI_BUS(x)      (((x) >> 8) & 0xff)
 
-static int find_device_iter(struct pci_dev *dev, void *data)
+/**
+ * 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;
-        u32 mask;
+        u32 status, mask;
         u16 reg16;
-        int result;
-        struct aer_err_info *e_info = (struct aer_err_info *)data;
 
         /*
          * 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)) {
-                result = compare_device_id(dev, e_info);
-                if (result)
-                        add_error_device(e_info, dev);
+                /* Device ID match? */
+                if (e_info->id == ((dev->bus->number << 8) | dev->devfn))
+                        return true;
 
-                /*
-                 * If there is no multiple error, we stop
-                 * or continue based on the id comparing.
-                 */
+                /* Continue id comparing if there is no multiple error */
                 if (!e_info->multi_error_valid)
-                        return result;
-
-                /*
-                 * If there are multiple errors and id does match,
-                 * We need continue to search other devices under
-                 * the root port. Return 0 means that.
-                 */
-                if (result)
-                        return 0;
+                        return false;
         }
 
         /*
@@ -199,71 +146,94 @@ static int find_device_iter(struct pci_dev *dev, void *data)
          *      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 the initial reporter.
+         * We check AER status registers to find possible reporter.
          */
         if (atomic_read(&dev->enable_cnt) == 0)
-                return 0;
+                return false;
         pos = pci_pcie_cap(dev);
         if (!pos)
-                return 0;
+                return false;
+
         /* Check if AER is enabled */
-        pci_read_config_word(dev, pos+PCI_EXP_DEVCTL, &reg16);
+        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 0;
+                return false;
         pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
         if (!pos)
-                return 0;
+                return false;
 
-        status = 0;
-        mask = 0;
+        /* 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);
-                if (status & ~mask) {
-                        add_error_device(e_info, dev);
-                        goto added;
-                }
         } 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) {
-                        add_error_device(e_info, dev);
-                        goto added;
-                }
         }
+        if (status & ~mask)
+                return true;
 
-        return 0;
+        return false;
+}
 
-added:
-        if (e_info->multi_error_valid)
-                return 0;
-        else
-                return 1;
+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
- * @err_info: including detailed error information such like id
+ * @e_info: including detailed error information such like id
  *
- * Invoked when error is detected at the Root Port.
+ * 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 void find_source_device(struct pci_dev *parent,
+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;
+                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)
@@ -402,43 +372,77 @@ static pci_ers_result_t broadcast_error_message(struct pci_dev *dev,
         return result_data.result;
 }
 
-struct find_aer_service_data {
-        struct pcie_port_service_driver *aer_driver;
-        int is_downstream;
-};
-
-static int find_aer_service_iter(struct device *device, void *data)
+/**
+ * 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)
 {
-        struct device_driver *driver;
-        struct pcie_port_service_driver *service_driver;
-        struct find_aer_service_data *result;
+        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);
 
-        result = (struct find_aer_service_data *) data;
+        /* De-assert Secondary Bus Reset */
+        p2p_ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET;
+        pci_write_config_word(dev, PCI_BRIDGE_CONTROL, p2p_ctrl);
 
-        if (device->bus == &pcie_port_bus_type) {
-                struct pcie_device *pcie = to_pcie_device(device);
+        /*
+         * 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;
+}
 
-                if (pcie->port->pcie_type == PCI_EXP_TYPE_DOWNSTREAM)
-                        result->is_downstream = 1;
+static int find_aer_service_iter(struct device *device, void *data)
+{
+        struct pcie_port_service_driver *service_driver, **drv;
 
-                driver = device->driver;
-                if (driver) {
-                        service_driver = to_service_driver(driver);
-                        if (service_driver->service == PCIE_PORT_SERVICE_AER) {
-                                result->aer_driver = service_driver;
-                                return 1;
-                        }
+        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 void find_aer_service(struct pci_dev *dev,
-                struct find_aer_service_data *data)
+static struct pcie_port_service_driver *find_aer_service(struct pci_dev *dev)
 {
-        int retval;
-        retval = device_for_each_child(&dev->dev, data, find_aer_service_iter);
+        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,
@@ -446,38 +450,34 @@ static pci_ers_result_t reset_link(struct pcie_device *aerdev,
 {
         struct pci_dev *udev;
         pci_ers_result_t status;
-        struct find_aer_service_data data;
+        struct pcie_port_service_driver *driver;
 
-        if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE)
+        if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE) {
+                /* Reset this port for all subordinates */
                 udev = dev;
-        else
+        } else {
+                /* Reset the upstream component (likely downstream port) */
                 udev = dev->bus->self;
+        }
 
-        data.is_downstream = 0;
-        data.aer_driver = NULL;
-        find_aer_service(udev, &data);
+        /* Use the aer driver of the component firstly */
+        driver = find_aer_service(udev);
 
-        /*
-         * Use the aer driver of the error agent firstly.
-         * If it hasn't the aer driver, use the root port's
-         */
-        if (!data.aer_driver || !data.aer_driver->reset_link) {
-                if (data.is_downstream &&
-                        aerdev->device.driver &&
-                        to_service_driver(aerdev->device.driver)->reset_link) {
-                        data.aer_driver =
-                                to_service_driver(aerdev->device.driver);
-                } else {
-                        dev_printk(KERN_DEBUG, &dev->dev, "no link-reset "
-                                   "support\n");
-                        return PCI_ERS_RESULT_DISCONNECT;
-                }
+        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;
         }
 
-        status = data.aer_driver->reset_link(udev);
         if (status != PCI_ERS_RESULT_RECOVERED) {
-                dev_printk(KERN_DEBUG, &dev->dev, "link reset at upstream "
-                           "device %s failed\n", pci_name(udev));
+                dev_printk(KERN_DEBUG, &dev->dev,
+                        "link reset at upstream device %s failed\n",
+                        pci_name(udev));
                 return PCI_ERS_RESULT_DISCONNECT;
         }
 
@@ -494,8 +494,7 @@ static pci_ers_result_t reset_link(struct pcie_device *aerdev,
  * error detected message to all downstream drivers within a hierarchy in
  * question and return the returned code.
  */
-static pci_ers_result_t do_recovery(struct pcie_device *aerdev,
-                struct pci_dev *dev,
+static void do_recovery(struct pcie_device *aerdev, struct pci_dev *dev,
                 int severity)
 {
         pci_ers_result_t status, result = PCI_ERS_RESULT_RECOVERED;
@@ -513,10 +512,8 @@ static pci_ers_result_t do_recovery(struct pcie_device *aerdev,
 
         if (severity == AER_FATAL) {
                 result = reset_link(aerdev, dev);
-                if (result != PCI_ERS_RESULT_RECOVERED) {
-                        /* TODO: Should panic here? */
-                        return result;
-                }
+                if (result != PCI_ERS_RESULT_RECOVERED)
+                        goto failed;
         }
 
         if (status == PCI_ERS_RESULT_CAN_RECOVER)
@@ -537,13 +534,22 @@ static pci_ers_result_t do_recovery(struct pcie_device *aerdev,
                                 report_slot_reset);
         }
 
-        if (status == PCI_ERS_RESULT_RECOVERED)
-                broadcast_error_message(dev,
+        if (status != PCI_ERS_RESULT_RECOVERED)
+                goto failed;
+
+        broadcast_error_message(dev,
                                 state,
                                 "resume",
                                 report_resume);
 
-        return status;
+        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");
 }
 
 /**
@@ -558,7 +564,6 @@ static void handle_error_source(struct pcie_device *aerdev,
         struct pci_dev *dev,
         struct aer_err_info *info)
 {
-        pci_ers_result_t status = 0;
         int pos;
 
         if (info->severity == AER_CORRECTABLE) {
@@ -570,114 +575,8 @@ static void handle_error_source(struct pcie_device *aerdev,
                 if (pos)
                         pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS,
                                         info->status);
-        } else {
-                status = do_recovery(aerdev, dev, info->severity);
-                if (status == PCI_ERS_RESULT_RECOVERED) {
-                        dev_printk(KERN_DEBUG, &dev->dev, "AER driver "
-                                   "successfully recovered\n");
-                } else {
-                        /* TODO: Should kernel panic here? */
-                        dev_printk(KERN_DEBUG, &dev->dev, "AER driver didn't "
-                                   "recover\n");
-                }
-        }
-}
-
-/**
- * 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.
- */
-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_write_config_dword(pdev,
-                aer_pos + PCI_ERR_ROOT_COMMAND,
-                ROOT_PORT_INTR_ON_MESG_MASK);
-}
-
-/**
- * disable_root_aer - 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 disable_root_aer(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_write_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, 0);
-
-        /* 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);
-}
-
-/**
- * get_e_source - retrieve an error source
- * @rpc: pointer to the root port which holds an error
- *
- * Invoked by DPC handler to consume an error.
- */
-static struct aer_err_source *get_e_source(struct aer_rpc *rpc)
-{
-        struct aer_err_source *e_source;
-        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 NULL;
-        }
-        e_source = &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 e_source;
+        } else
+                do_recovery(aerdev, dev, info->severity);
 }
 
 /**
@@ -686,11 +585,14 @@ static struct aer_err_source *get_e_source(struct aer_rpc *rpc)
  * @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;
 
@@ -743,12 +645,6 @@ static inline void aer_process_err_devices(struct pcie_device *p_device,
 {
         int i;
 
-        if (!e_info->dev[0]) {
-                dev_printk(KERN_DEBUG, &p_device->port->dev,
-                                "can't find device of ID%04x\n",
-                                e_info->id);
-        }
-
         /* 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))
@@ -769,11 +665,10 @@ static void aer_isr_one_error(struct pcie_device *p_device,
                 struct aer_err_source *e_src)
 {
         struct aer_err_info *e_info;
-        int i;
 
         /* 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 == NULL) {
+        if (!e_info) {
                 dev_printk(KERN_DEBUG, &p_device->port->dev,
                         "Can't allocate mem when processing AER errors\n");
                 return;
@@ -783,37 +678,73 @@ static void aer_isr_one_error(struct pcie_device *p_device,
          * There is a possibility that both correctable error and
          * uncorrectable error being logged. Report correctable error first.
          */
-        for (i = 1; i & ROOT_ERR_STATUS_MASKS ; i <<= 2) {
-                if (i > 4)
-                        break;
-                if (!(e_src->status & i))
-                        continue;
-
-                memset(e_info, 0, sizeof(struct aer_err_info));
-
-                /* Init comprehensive error information */
-                if (i & PCI_ERR_ROOT_COR_RCV) {
-                        e_info->id = ERR_COR_ID(e_src->id);
-                        e_info->severity = AER_CORRECTABLE;
-                } else {
-                        e_info->id = ERR_UNCOR_ID(e_src->id);
-                        e_info->severity = ((e_src->status >> 6) & 1);
-                }
-                if (e_src->status &
-                        (PCI_ERR_ROOT_MULTI_COR_RCV |
-                         PCI_ERR_ROOT_MULTI_UNCOR_RCV))
+        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);
 
-                find_source_device(p_device->port, e_info);
-                aer_process_err_devices(p_device, 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
  *
@@ -823,34 +754,17 @@ 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 *e_src;
+        struct aer_err_source uninitialized_var(e_src);
 
         mutex_lock(&rpc->rpc_mutex);
-        e_src = get_e_source(rpc);
-        while (e_src) {
-                aer_isr_one_error(p_device, e_src);
-                e_src = get_e_source(rpc);
-        }
+        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_delete_rootport - disable root port aer and delete service data
- * @rpc: pointer to a root port device being deleted
- *
- * Invoked when AER service unloaded on a specific Root Port
- */
-void aer_delete_rootport(struct aer_rpc *rpc)
-{
-        /* Disable root port AER itself */
-        disable_root_aer(rpc);
-
-        kfree(rpc);
-}
-
-/**
  * aer_init - provide AER initialization
  * @dev: pointer to AER pcie device
  *
@@ -858,22 +772,10 @@ void aer_delete_rootport(struct aer_rpc *rpc)
  */
 int aer_init(struct pcie_device *dev)
 {
-        if (dev->port->aer_firmware_first) {
-                dev_printk(KERN_DEBUG, &dev->device,
-                           "PCIe errors handled by platform firmware.\n");
-                goto out;
-        }
-
-        if (aer_osc_setup(dev))
-                goto out;
-
-        return 0;
-out:
         if (forceload) {
                 dev_printk(KERN_DEBUG, &dev->device,
                            "aerdrv forceload requested.\n");
-                dev->port->aer_firmware_first = 0;
-                return 0;
+                pcie_aer_force_firmware_first(dev->port, 0);
         }
-        return -ENXIO;
+        return 0;
 }
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index be53d98fa384..3188cd96b338 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -68,7 +68,7 @@ struct pcie_link_state {
         struct aspm_latency acceptable[8];
 };
 
-static int aspm_disabled, aspm_force;
+static int aspm_disabled, aspm_force, aspm_clear_state;
 static DEFINE_MUTEX(aspm_lock);
 static LIST_HEAD(link_list);
 
@@ -139,7 +139,7 @@ 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)
-                return;
+                enable = 0;
         /* Need nothing if the specified equals to current state */
         if (link->clkpm_enabled == enable)
                 return;
@@ -498,6 +498,10 @@ static int pcie_aspm_sanity_check(struct pci_dev *pdev)
         struct pci_dev *child;
         int pos;
         u32 reg32;
+
+        if (aspm_clear_state)
+                return -EINVAL;
+
         /*
          * Some functions in a slot might not all be PCIe functions,
          * very strange. Disable ASPM for the whole slot
@@ -563,12 +567,15 @@ void pcie_aspm_init_link_state(struct pci_dev *pdev)
         struct pcie_link_state *link;
         int blacklist = !!pcie_aspm_sanity_check(pdev);
 
-        if (aspm_disabled || !pci_is_pcie(pdev) || pdev->link_state)
+        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;
 
+        if (aspm_disabled && !aspm_clear_state)
+                return;
+
         /* VIA has a strange chipset, root port is under a bridge */
         if (pdev->pcie_type == PCI_EXP_TYPE_ROOT_PORT &&
             pdev->bus->self)
@@ -588,11 +595,23 @@ void pcie_aspm_init_link_state(struct pci_dev *pdev)
          * update through pcie_aspm_cap_init().
          */
         pcie_aspm_cap_init(link, blacklist);
-        pcie_config_aspm_path(link);
 
         /* Setup initial Clock PM state */
         pcie_clkpm_cap_init(link, blacklist);
-        pcie_set_clkpm(link, policy_to_clkpm_state(link));
+
+        /*
+         * 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:
@@ -629,7 +648,7 @@ 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 (aspm_disabled || !pci_is_pcie(pdev) ||
+        if ((aspm_disabled && !aspm_clear_state) || !pci_is_pcie(pdev) ||
             !parent || !parent->link_state)
                 return;
         if ((parent->pcie_type != PCI_EXP_TYPE_ROOT_PORT) &&
@@ -887,6 +906,12 @@ static int __init pcie_aspm_disable(char *str)
 
 __setup("pcie_aspm=", pcie_aspm_disable);
 
+void pcie_clear_aspm(void)
+{
+        if (!aspm_force)
+                aspm_clear_state = 1;
+}
+
 void pcie_no_aspm(void)
 {
         if (!aspm_force)
diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
new file mode 100644
index 000000000000..0057344a3fcb
--- /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
index aaeb9d21cba5..bd00a01aef14 100644
--- a/drivers/pci/pcie/portdrv.h
+++ b/drivers/pci/pcie/portdrv.h
@@ -30,4 +30,42 @@ 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 000000000000..a86b56e5f2f2
--- /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_core.c b/drivers/pci/pcie/portdrv_core.c
index b174188ac121..5130d0d22390 100644
--- a/drivers/pci/pcie/portdrv_core.c
+++ b/drivers/pci/pcie/portdrv_core.c
@@ -14,6 +14,8 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/pcieport_if.h>
+#include <linux/aer.h>
+#include <linux/pci-aspm.h>
 
 #include "../pci.h"
 #include "portdrv.h"
@@ -186,16 +188,24 @@ static int pcie_port_enable_msix(struct pci_dev *dev, int *vectors, int mask)
  */
 static int init_service_irqs(struct pci_dev *dev, int *irqs, int mask)
 {
-        int i, irq;
+        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 */
-        irq = -1;
         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;
@@ -228,24 +238,64 @@ 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 (reg16 & PCI_EXP_FLAGS_SLOT) {
+        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)
+                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 (pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR))
+        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 (dev->pcie_type == PCI_EXP_TYPE_ROOT_PORT)
+        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;
 }
@@ -277,6 +327,7 @@ static int pcie_device_init(struct pci_dev *pdev, int service, int irq)
                      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)
@@ -298,15 +349,18 @@ int pcie_port_device_register(struct pci_dev *dev)
         int status, capabilities, i, nr_service;
         int irqs[PCIE_PORT_DEVICE_MAXSERVICES];
 
-        /* Get and check PCI Express port services */
-        capabilities = get_port_device_capability(dev);
-        if (!capabilities)
-                return -ENODEV;
-
         /* 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) {
+                pcie_no_aspm();
+                return 0;
+        }
+
         pci_set_master(dev);
         /*
          * Initialize service irqs. Don't use service devices that
@@ -485,6 +539,9 @@ static void pcie_port_shutdown_service(struct device *dev) {}
  */
 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;
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 13c8972886e6..e0610bda1dea 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -12,9 +12,10 @@
 #include <linux/errno.h>
 #include <linux/pm.h>
 #include <linux/init.h>
-#include <linux/slab.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"
@@ -29,8 +30,49 @@ 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;
@@ -43,6 +85,20 @@ static int pcie_portdrv_restore_config(struct pci_dev *dev)
 }
 
 #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,
@@ -50,6 +106,7 @@ static const struct dev_pm_ops pcie_portdrv_pm_ops = {
         .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)
@@ -273,10 +330,39 @@ static struct pci_driver pcie_portdriver = {
         .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);
@@ -289,11 +375,4 @@ static int __init pcie_portdrv_init(void)
         return retval;
 }
 
-static void __exit pcie_portdrv_exit(void)
-{
-        pci_unregister_driver(&pcie_portdriver);
-        pcie_port_bus_unregister();
-}
-
 module_init(pcie_portdrv_init);
-module_exit(pcie_portdrv_exit);
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 98ffb2de22e9..c84900da3c59 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -10,7 +10,6 @@
 #include <linux/module.h>
 #include <linux/cpumask.h>
 #include <linux/pci-aspm.h>
-#include <acpi/acpi_hest.h>
 #include "pci.h"
 
 #define CARDBUS_LATENCY_TIMER   176     /* secondary latency timer */
@@ -89,6 +88,7 @@ static void release_pcibus_dev(struct device *dev)
 
         if (pci_bus->bridge)
                 put_device(pci_bus->bridge);
+        pci_bus_remove_resources(pci_bus);
         kfree(pci_bus);
 }
 
@@ -163,9 +163,16 @@ 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);
@@ -173,6 +180,9 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
         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
@@ -281,26 +291,12 @@ static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom)
         }
 }
 
-void __devinit pci_read_bridge_bases(struct pci_bus *child)
+static void __devinit pci_read_bridge_io(struct pci_bus *child)
 {
         struct pci_dev *dev = child->self;
         u8 io_base_lo, io_limit_lo;
-        u16 mem_base_lo, mem_limit_lo;
         unsigned long base, limit;
         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)": "");
-
-        if (dev->transparent) {
-                for(i = 3; i < PCI_BUS_NUM_RESOURCES; i++)
-                        child->resource[i] = child->parent->resource[i - 3];
-        }
 
         res = child->resource[0];
         pci_read_config_byte(dev, PCI_IO_BASE, &io_base_lo);
@@ -316,26 +312,50 @@ void __devinit pci_read_bridge_bases(struct pci_bus *child)
                 limit |= (io_limit_hi << 16);
         }
 
-        if (base <= limit) {
+        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 <= limit) {
+        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);
@@ -366,7 +386,7 @@ void __devinit pci_read_bridge_bases(struct pci_bus *child)
 #endif
                 }
         }
-        if (base <= limit) {
+        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)
@@ -374,6 +394,44 @@ void __devinit pci_read_bridge_bases(struct pci_bus *child)
                 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);
+                        }
+                }
         }
 }
 
@@ -387,10 +445,147 @@ static struct pci_bus * pci_alloc_bus(void)
                 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)
 {
@@ -430,6 +625,8 @@ static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent,
         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];
@@ -485,16 +682,20 @@ int __devinit pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max,
         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 behind bridge, config %06x, pass %d\n",
-                buses & 0xffffff, pass);
+        dev_dbg(&dev->dev, "scanning [bus %02x-%02x] behind bridge, pass %d\n",
+                secondary, subordinate, pass);
 
         /* Check if setup is sensible at all */
         if (!pass &&
-            ((buses & 0xff) != bus->number || ((buses >> 8) & 0xff) <= bus->number)) {
+            (primary != bus->number || secondary <= bus->number)) {
                 dev_dbg(&dev->dev, "bus configuration invalid, reconfiguring\n");
                 broken = 1;
         }
@@ -505,15 +706,15 @@ int __devinit pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max,
         pci_write_config_word(dev, PCI_BRIDGE_CONTROL,
                               bctl & ~PCI_BRIDGE_CTL_MASTER_ABORT);
 
-        if ((buses & 0xffff00) && !pcibios_assign_all_busses() && !is_cardbus && !broken) {
-                unsigned int cmax, busnr;
+        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;
-                busnr = (buses >> 8) & 0xFF;
 
                 /*
                  * If we already got to this bus through a different bridge,
@@ -522,13 +723,13 @@ int __devinit pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max,
                  * However, we continue to descend down the hierarchy and
                  * scan remaining child buses.
                  */
-                child = pci_find_bus(pci_domain_nr(bus), busnr);
+                child = pci_find_bus(pci_domain_nr(bus), secondary);
                 if (!child) {
-                        child = pci_add_new_bus(bus, dev, busnr);
+                        child = pci_add_new_bus(bus, dev, secondary);
                         if (!child)
                                 goto out;
-                        child->primary = buses & 0xFF;
-                        child->subordinate = (buses >> 16) & 0xFF;
+                        child->primary = primary;
+                        child->subordinate = subordinate;
                         child->bridge_ctl = bctl;
                 }
 
@@ -681,7 +882,7 @@ static void pci_read_irq(struct pci_dev *dev)
         dev->irq = irq;
 }
 
-static void set_pcie_port_type(struct pci_dev *pdev)
+void set_pcie_port_type(struct pci_dev *pdev)
 {
         int pos;
         u16 reg16;
@@ -695,7 +896,7 @@ static void set_pcie_port_type(struct pci_dev *pdev)
         pdev->pcie_type = (reg16 & PCI_EXP_FLAGS_TYPE) >> 4;
 }
 
-static void set_pcie_hotplug_bridge(struct pci_dev *pdev)
+void set_pcie_hotplug_bridge(struct pci_dev *pdev)
 {
         int pos;
         u16 reg16;
@@ -712,12 +913,6 @@ static void set_pcie_hotplug_bridge(struct pci_dev *pdev)
                 pdev->is_hotplug_bridge = 1;
 }
 
-static void set_pci_aer_firmware_first(struct pci_dev *pdev)
-{
-        if (acpi_hest_firmware_first_pci(pdev))
-                pdev->aer_firmware_first = 1;
-}
-
 #define LEGACY_IO_RESOURCE      (IORESOURCE_IO | IORESOURCE_PCI_FIXED)
 
 /**
@@ -747,7 +942,6 @@ int pci_setup_device(struct pci_dev *dev)
         dev->multifunction = !!(hdr_type & 0x80);
         dev->error_state = pci_channel_io_normal;
         set_pcie_port_type(dev);
-        set_pci_aer_firmware_first(dev);
 
         list_for_each_entry(slot, &dev->bus->slots, list)
                 if (PCI_SLOT(dev->devfn) == slot->number)
@@ -767,8 +961,8 @@ int pci_setup_device(struct pci_dev *dev)
         dev->class = class;
         class >>= 8;
 
-        dev_dbg(&dev->dev, "found [%04x:%04x] class %06x header type %02x\n",
-                 dev->vendor, dev->device, class, dev->hdr_type);
+        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);
@@ -1081,6 +1275,45 @@ struct pci_dev *__ref pci_scan_single_device(struct pci_bus *bus, int devfn)
 }
 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
@@ -1094,21 +1327,30 @@ EXPORT_SYMBOL(pci_scan_single_device);
  */
 int pci_scan_slot(struct pci_bus *bus, int devfn)
 {
-        int fn, nr = 0;
+        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 && !dev->is_added)      /* new device? */
+        if (!dev)
+                return 0;
+        if (!dev->is_added)
                 nr++;
 
-        if (dev && dev->multifunction) {
-                for (fn = 1; fn < 8; fn++) {
-                        dev = pci_scan_single_device(bus, devfn + fn);
-                        if (dev) {
-                                if (!dev->is_added)
-                                        nr++;
-                                dev->multifunction = 1;
-                        }
+        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;
                 }
         }
 
@@ -1200,6 +1442,7 @@ struct pci_bus * pci_create_bus(struct device *parent,
         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));
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index 593bb844b8db..27911b55c2a5 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -6,10 +6,10 @@
 
 #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/smp_lock.h>
 #include <linux/capability.h>
 #include <asm/uaccess.h>
 #include <asm/byteorder.h>
@@ -211,8 +211,6 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd,
 #endif /* HAVE_PCI_MMAP */
         int ret = 0;
 
-        lock_kernel();
-
         switch (cmd) {
         case PCIIOC_CONTROLLER:
                 ret = pci_domain_nr(dev->bus);
@@ -241,7 +239,6 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd,
                 break;
         };
 
-        unlock_kernel();
         return ret;
 }
 
@@ -259,7 +256,7 @@ static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma)
 
         /* 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))
+                if (pci_mmap_fits(dev, i, vma,  PCI_MMAP_PROCFS))
                         break;
         }
 
@@ -305,6 +302,7 @@ static const struct file_operations proc_bus_pci_operations = {
         .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,
@@ -430,8 +428,6 @@ int pci_proc_detach_device(struct pci_dev *dev)
         struct proc_dir_entry *e;
 
         if ((e = dev->procent)) {
-                if (atomic_read(&e->count) > 1)
-                        return -EBUSY;
                 remove_proc_entry(e->name, dev->bus->procdir);
                 dev->procent = NULL;
         }
@@ -484,9 +480,9 @@ static int __init pci_proc_init(void)
         proc_create("devices", 0, proc_bus_pci_dir,
                     &proc_bus_pci_dev_operations);
         proc_initialized = 1;
-        while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
+        for_each_pci_dev(dev)
                 pci_proc_attach_device(dev);
-        }
+
         return 0;
 }
 
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index c74694345b6e..53a786fd0d40 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -25,14 +25,9 @@
 #include <linux/dmi.h>
 #include <linux/pci-aspm.h>
 #include <linux/ioport.h>
+#include <asm/dma.h>    /* isa_dma_bridge_buggy */
 #include "pci.h"
 
-int isa_dma_bridge_buggy;
-EXPORT_SYMBOL(isa_dma_bridge_buggy);
-int pci_pci_problems;
-EXPORT_SYMBOL(pci_pci_problems);
-
-#ifdef CONFIG_PCI_QUIRKS
 /*
  * This quirk function disables memory decoding and releases memory resources
  * of the device specified by kernel's boot parameter 'pci=resource_alignment='.
@@ -96,6 +91,19 @@ static void __devinit quirk_resource_alignment(struct pci_dev *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.
@@ -155,6 +163,26 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NEC,	PCI_DEVICE_ID_NEC_CBUS_2,	quirk_isa_d
 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)
@@ -198,6 +226,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82439TX, 	quir
  *      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.
  *
@@ -338,6 +367,23 @@ static void __devinit quirk_s3_64M(struct pci_dev *dev)
 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)
 {
@@ -356,8 +402,9 @@ static void __devinit quirk_io_region(struct pci_dev *dev, unsigned region,
                 bus_region.end = res->end;
                 pcibios_bus_to_resource(dev, res, &bus_region);
 
-                pci_claim_resource(dev, nr);
-                dev_info(&dev->dev, "quirk: %pR claimed by %s\n", res, name);
+                if (pci_claim_resource(dev, nr) == 0)
+                        dev_info(&dev->dev, "quirk: %pR claimed by %s\n",
+                                 res, name);
         }
 }       
 
@@ -970,7 +1017,7 @@ 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/ds/GX for info on what
+ * 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)
@@ -1444,7 +1491,9 @@ static void quirk_jmicron_ata(struct pci_dev *pdev)
         conf5 &= ~(1 << 24);  /* Clear bit 24 */
 
         switch (pdev->device) {
-        case PCI_DEVICE_ID_JMICRON_JMB360:
+        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;
@@ -1456,6 +1505,7 @@ static void quirk_jmicron_ata(struct pci_dev *pdev)
                 /* 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 */
@@ -1480,16 +1530,22 @@ static void quirk_jmicron_ata(struct pci_dev *pdev)
 }
 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
 
@@ -1965,11 +2021,25 @@ 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. The defaults are that these
-         * features are turned off but some BIOSes turn them on.
+         * 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 */
@@ -1996,7 +2066,7 @@ static void __devinit quirk_via_cx700_pci_parking_caching(struct pci_dev *dev)
                 }
         }
 }
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_VIA, 0x324e, quirk_via_cx700_pci_parking_caching);
+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
@@ -2066,6 +2136,24 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82865_HB,
 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
@@ -2085,6 +2173,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_RS480, quirk_disabl
 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)
@@ -2096,6 +2185,28 @@ static void __devinit quirk_disable_msi(struct pci_dev *dev)
         }
 }
 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 */
@@ -2187,15 +2298,16 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SERVERWORKS,
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8132_BRIDGE,
                          ht_enable_msi_mapping);
 
-/* The P5N32-SLI Premium motherboard from Asus has a problem with msi
+/* 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)
 {
-        if (dmi_name_in_vendors("P5N32-SLI PREMIUM")) {
+        if (dmi_name_in_vendors("P5N32-SLI PREMIUM") ||
+            dmi_name_in_vendors("P5N32-E SLI")) {
                 dev_info(&dev->dev,
-                         "Disabling msi for MCP55 NIC on P5N32-SLI Premium\n");
+                         "Disabling msi for MCP55 NIC on P5N32-SLI\n");
                 dev->no_msi = 1;
         }
 }
@@ -2203,6 +2315,40 @@ 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;
@@ -2354,6 +2500,9 @@ static void __devinit __nv_msi_ht_cap_quirk(struct pci_dev *dev, int all)
         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);
 
@@ -2517,9 +2666,131 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10e7, quirk_i82576_sriov);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10e8, quirk_i82576_sriov);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x150a, quirk_i82576_sriov);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x150d, quirk_i82576_sriov);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1518, quirk_i82576_sriov);
 
 #endif  /* CONFIG_PCI_IOV */
 
+/* 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 similiar 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;
+
+        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);
+#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 pci_do_fixups(struct pci_dev *dev, struct pci_fixup *f,
                           struct pci_fixup *end)
 {
@@ -2595,6 +2866,7 @@ void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev)
         }
         pci_do_fixups(dev, start, end);
 }
+EXPORT_SYMBOL(pci_fixup_device);
 
 static int __init pci_apply_final_quirks(void)
 {
@@ -2606,7 +2878,7 @@ static int __init pci_apply_final_quirks(void)
                 printk(KERN_DEBUG "PCI: CLS %u bytes\n",
                        pci_cache_line_size << 2);
 
-        while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
+        for_each_pci_dev(dev) {
                 pci_fixup_device(pci_fixup_final, dev);
                 /*
                  * If arch hasn't set it explicitly yet, use the CLS
@@ -2706,9 +2978,3 @@ int pci_dev_specific_reset(struct pci_dev *dev, int probe)
 
         return -ENOTTY;
 }
-
-#else
-void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev) {}
-int pci_dev_specific_reset(struct pci_dev *dev, int probe) { return -ENOTTY; }
-#endif
-EXPORT_SYMBOL(pci_fixup_device);
diff --git a/drivers/pci/search.c b/drivers/pci/search.c
index 4a471dc4f4b9..9d75dc8ca602 100644
--- a/drivers/pci/search.c
+++ b/drivers/pci/search.c
@@ -9,6 +9,7 @@
 
 #include <linux/init.h>
 #include <linux/pci.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include "pci.h"
@@ -168,7 +169,7 @@ struct pci_dev *pci_get_domain_bus_and_slot(int domain, unsigned int bus,
 {
         struct pci_dev *dev = NULL;
 
-        while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
+        for_each_pci_dev(dev) {
                 if (pci_domain_nr(dev->bus) == domain &&
                     (dev->bus->number == bus && dev->devfn == devfn))
                         return dev;
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index c48cd377b3f5..66cb8f4cc5f4 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -27,37 +27,91 @@
 #include <linux/slab.h>
 #include "pci.h"
 
-static void pbus_assign_resources_sorted(const struct pci_bus *bus)
-{
-        struct pci_dev *dev;
+struct resource_list_x {
+        struct resource_list_x *next;
         struct resource *res;
-        struct resource_list head, *list, *tmp;
-        int idx;
+        struct pci_dev *dev;
+        resource_size_t start;
+        resource_size_t end;
+        unsigned long flags;
+};
 
-        head.next = NULL;
-        list_for_each_entry(dev, &bus->devices, bus_list) {
-                u16 class = dev->class >> 8;
+static void add_to_failed_list(struct resource_list_x *head,
+                                 struct pci_dev *dev, struct resource *res)
+{
+        struct resource_list_x *list = head;
+        struct resource_list_x *ln = list->next;
+        struct resource_list_x *tmp;
 
-                /* Don't touch classless devices or host bridges or ioapics.  */
-                if (class == PCI_CLASS_NOT_DEFINED ||
-                    class == PCI_CLASS_BRIDGE_HOST)
-                        continue;
+        tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
+        if (!tmp) {
+                pr_warning("add_to_failed_list: kmalloc() failed!\n");
+                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))
-                                continue;
-                }
+        tmp->next = ln;
+        tmp->res = res;
+        tmp->dev = dev;
+        tmp->start = res->start;
+        tmp->end = res->end;
+        tmp->flags = res->flags;
+        list->next = tmp;
+}
+
+static void free_failed_list(struct resource_list_x *head)
+{
+        struct resource_list_x *list, *tmp;
 
-                pdev_sort_resources(dev, &head);
+        for (list = head->next; list;) {
+                tmp = list;
+                list = list->next;
+                kfree(tmp);
         }
 
-        for (list = head.next; list;) {
+        head->next = NULL;
+}
+
+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 void __assign_resources_sorted(struct resource_list *head,
+                                 struct resource_list_x *fail_head)
+{
+        struct resource *res;
+        struct resource_list *list, *tmp;
+        int idx;
+
+        for (list = head->next; list;) {
                 res = list->res;
                 idx = res - &list->dev->resource[0];
+
                 if (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);
+                        }
                         res->start = 0;
                         res->end = 0;
                         res->flags = 0;
@@ -68,6 +122,30 @@ static void pbus_assign_resources_sorted(const struct pci_bus *bus)
         }
 }
 
+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, fail_head);
+
+}
+
+static void pbus_assign_resources_sorted(const struct pci_bus *bus,
+                                         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, fail_head);
+}
+
 void pci_setup_cardbus(struct pci_bus *bus)
 {
         struct pci_dev *bridge = bus->self;
@@ -134,18 +212,12 @@ EXPORT_SYMBOL(pci_setup_cardbus);
    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(struct pci_bus *bus)
+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, bu, lu, io_upper16;
-
-        if (pci_is_enabled(bridge))
-                return;
-
-        dev_info(&bridge->dev, "PCI bridge to [bus %02x-%02x]\n",
-                 bus->secondary, bus->subordinate);
+        u32 l, io_upper16;
 
         /* Set up the top and bottom of the PCI I/O segment for this bus. */
         res = bus->resource[0];
@@ -158,8 +230,7 @@ static void pci_setup_bridge(struct pci_bus *bus)
                 /* 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 {
+        } else {
                 /* Clear upper 16 bits of I/O base/limit. */
                 io_upper16 = 0;
                 l = 0x00f0;
@@ -171,21 +242,35 @@ static void pci_setup_bridge(struct pci_bus *bus)
         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);
+}
 
-        /* Set up the top and bottom of the PCI Memory segment
-           for this bus. */
+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 {
+        } 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
@@ -204,8 +289,7 @@ static void pci_setup_bridge(struct pci_bus *bus)
                         lu = upper_32_bits(region.end);
                 }
                 dev_info(&bridge->dev, "  bridge window %pR\n", res);
-        }
-        else {
+        } else {
                 l = 0x0000fff0;
                 dev_info(&bridge->dev, "  bridge window [mem pref disabled]\n");
         }
@@ -214,10 +298,35 @@ static void pci_setup_bridge(struct pci_bus *bus)
         /* 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. */
@@ -253,8 +362,11 @@ static void pci_bridge_check_ranges(struct pci_bus *bus)
         }
         if (pmem) {
                 b_res[2].flags |= IORESOURCE_MEM | IORESOURCE_PREFETCH;
-                if ((pmem & PCI_PREF_RANGE_TYPE_MASK) == PCI_PREF_RANGE_TYPE_64)
+                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 */
@@ -283,8 +395,7 @@ static struct resource *find_free_bus_resource(struct pci_bus *bus, unsigned lon
         unsigned long type_mask = IORESOURCE_IO | IORESOURCE_MEM |
                                   IORESOURCE_PREFETCH;
 
-        for (i = 0; i < PCI_BUS_NUM_RESOURCES; i++) {
-                r = bus->resource[i];
+        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)
@@ -301,7 +412,7 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size)
 {
         struct pci_dev *dev;
         struct resource *b_res = find_free_bus_resource(bus, IORESOURCE_IO);
-        unsigned long size = 0, size1 = 0;
+        unsigned long size = 0, size1 = 0, old_size;
 
         if (!b_res)
                 return;
@@ -326,12 +437,17 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size)
         }
         if (size < min_size)
                 size = min_size;
+        old_size = resource_size(b_res);
+        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, 4096);
+        if (size < old_size)
+                size = old_size;
         if (!size) {
                 if (b_res->start || b_res->end)
                         dev_info(&bus->self->dev, "disabling bridge window "
@@ -352,7 +468,7 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
                          unsigned long type, resource_size_t min_size)
 {
         struct pci_dev *dev;
-        resource_size_t min_align, align, size;
+        resource_size_t min_align, align, size, old_size;
         resource_size_t aligns[12];     /* Alignments from 1Mb to 2Gb */
         int order, max_order;
         struct resource *b_res = find_free_bus_resource(bus, type);
@@ -402,6 +518,11 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
         }
         if (size < min_size)
                 size = min_size;
+        old_size = resource_size(b_res);
+        if (old_size == 1)
+                old_size = 0;
+        if (size < old_size)
+                size = old_size;
 
         align = 0;
         min_align = 0;
@@ -538,23 +659,25 @@ void __ref pci_bus_size_bridges(struct pci_bus *bus)
 }
 EXPORT_SYMBOL(pci_bus_size_bridges);
 
-void __ref pci_bus_assign_resources(const struct pci_bus *bus)
+static void __ref __pci_bus_assign_resources(const struct pci_bus *bus,
+                                         struct resource_list_x *fail_head)
 {
         struct pci_bus *b;
         struct pci_dev *dev;
 
-        pbus_assign_resources_sorted(bus);
+        pbus_assign_resources_sorted(bus, fail_head);
 
         list_for_each_entry(dev, &bus->devices, bus_list) {
                 b = dev->subordinate;
                 if (!b)
                         continue;
 
-                pci_bus_assign_resources(b);
+                __pci_bus_assign_resources(b, fail_head);
 
                 switch (dev->class >> 8) {
                 case PCI_CLASS_BRIDGE_PCI:
-                        pci_setup_bridge(b);
+                        if (!pci_is_enabled(dev))
+                                pci_setup_bridge(b);
                         break;
 
                 case PCI_CLASS_BRIDGE_CARDBUS:
@@ -568,15 +691,130 @@ void __ref pci_bus_assign_resources(const struct pci_bus *bus)
                 }
         }
 }
+
+void __ref pci_bus_assign_resources(const struct pci_bus *bus)
+{
+        __pci_bus_assign_resources(bus, 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, 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)
 {
-        int i;
+        struct resource *res;
+        int i;
 
-        for (i = 0; i < PCI_BUS_NUM_RESOURCES; i++) {
-                struct resource *res = bus->resource[i];
-                if (!res || !res->end)
+        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);
@@ -621,3 +859,67 @@ pci_assign_unassigned_resources(void)
                 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_failed_list(&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_failed_list(&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
index aa795fd428de..eec9738f3492 100644
--- a/drivers/pci/setup-irq.c
+++ b/drivers/pci/setup-irq.c
@@ -59,7 +59,6 @@ pci_fixup_irqs(u8 (*swizzle)(struct pci_dev *, u8 *),
                int (*map_irq)(struct pci_dev *, u8, u8))
 {
         struct pci_dev *dev = NULL;
-        while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, 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
index 7d678bb15ffb..bc0e6eea0fff 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -85,7 +85,7 @@ void pci_update_resource(struct pci_dev *dev, int resno)
                 }
         }
         res->flags &= ~IORESOURCE_UNSET;
-        dev_info(&dev->dev, "BAR %d: set to %pR (PCI address [%#llx-%#llx]\n",
+        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);
 }
@@ -93,22 +93,24 @@ void pci_update_resource(struct pci_dev *dev, int resno)
 int pci_claim_resource(struct pci_dev *dev, int resource)
 {
         struct resource *res = &dev->resource[resource];
-        struct resource *root;
-        int err;
+        struct resource *root, *conflict;
 
         root = pci_find_parent_resource(dev, res);
         if (!root) {
-                dev_err(&dev->dev, "no compatible bridge window for %pR\n",
-                        res);
+                dev_info(&dev->dev, "no compatible bridge window for %pR\n",
+                         res);
                 return -EINVAL;
         }
 
-        err = request_resource(root, res);
-        if (err)
-                dev_err(&dev->dev,
-                        "address space collision: %pR already in use\n", res);
+        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 err;
+        return 0;
 }
 EXPORT_SYMBOL(pci_claim_resource);
 
@@ -154,6 +156,38 @@ static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev,
                                              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);
diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index 8c02b6c53bdb..968cfea04f74 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/kobject.h>
+#include <linux/slab.h>
 #include <linux/pci.h>
 #include <linux/err.h>
 #include "pci.h"
@@ -29,7 +30,7 @@ static ssize_t pci_slot_attr_store(struct kobject *kobj,
         return attribute->store ? attribute->store(slot, buf, len) : -EIO;
 }
 
-static struct sysfs_ops pci_slot_sysfs_ops = {
+static const struct sysfs_ops pci_slot_sysfs_ops = {
         .show = pci_slot_attr_show,
         .store = pci_slot_attr_store,
 };
@@ -47,6 +48,55 @@ static ssize_t address_read_file(struct pci_slot *slot, char *buf)
                                 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;
@@ -66,9 +116,15 @@ static void pci_slot_release(struct kobject *kobj)
 
 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,
 };
 
diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c
new file mode 100644
index 000000000000..a5a5ca17cfe6
--- /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 000000000000..3a5a6fcc0ead
--- /dev/null
+++ b/drivers/pci/xen-pcifront.c
@@ -0,0 +1,1148 @@
+/*
+ * 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++)
+                                *(*vector+i) = op.msix_entries[i].vector;
+                        return 0;
+                } else {
+                        printk(KERN_DEBUG "enable msix get value %x\n",
+                                op.value);
+                        return 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) = op.value;
+        } 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 "
+                                        "giving less than 4GB to domain.\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);
+
+        /*For PCIE_AER error handling job*/
+        flush_scheduled_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");