Merge branch 'linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6

* 'linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6: (109 commits)
  PCI: fix coding style issue in pci_save_state()
  PCI: add pci_request_acs
  PCI: fix BUG_ON triggered by logical PCIe root port removal
  PCI: remove ifdefed pci_cleanup_aer_correct_error_status
  PCI: unconditionally clear AER uncorr status register during cleanup
  x86/PCI: claim SR-IOV BARs in pcibios_allocate_resource
  PCI: portdrv: remove redundant definitions
  PCI: portdrv: remove unnecessary struct pcie_port_data
  PCI: portdrv: minor cleanup for pcie_port_device_register
  PCI: portdrv: add missing irq cleanup
  PCI: portdrv: enable device before irq initialization
  PCI: portdrv: cleanup service irqs initialization
  PCI: portdrv: check capabilities first
  PCI: portdrv: move PME capability check
  PCI: portdrv: remove redundant pcie type calculation
  PCI: portdrv: cleanup pcie_device registration
  PCI: portdrv: remove redundant pcie_port_device_probe
  PCI: Always set prefetchable base/limit upper32 registers
  PCI: read-modify-write the pcie device control register when initiating pcie flr
  PCI: show dma_mask bits in /sys
  ...

Fixed up conflicts in:
	arch/x86/kernel/amd_iommu_init.c
	drivers/pci/dmar.c
	drivers/pci/hotplug/acpiphp_glue.c
diff --git a/arch/ia64/include/asm/xen/hypervisor.h b/arch/ia64/include/asm/xen/hypervisor.h
index 88afb54..67455c2 100644
--- a/arch/ia64/include/asm/xen/hypervisor.h
+++ b/arch/ia64/include/asm/xen/hypervisor.h
@@ -37,35 +37,9 @@
 #include <xen/interface/xen.h>
 #include <xen/interface/version.h>	/* to compile feature.c */
 #include <xen/features.h>		/* to comiple xen-netfront.c */
+#include <xen/xen.h>
 #include <asm/xen/hypercall.h>
 
-/* xen_domain_type is set before executing any C code by early_xen_setup */
-enum xen_domain_type {
-	XEN_NATIVE,	/* running on bare hardware */
-	XEN_PV_DOMAIN,	/* running in a PV domain */
-	XEN_HVM_DOMAIN,	/* running in a Xen hvm domain*/
-};
-
-#ifdef CONFIG_XEN
-extern enum xen_domain_type xen_domain_type;
-#else
-#define xen_domain_type		XEN_NATIVE
-#endif
-
-#define xen_domain()		(xen_domain_type != XEN_NATIVE)
-#define xen_pv_domain()		(xen_domain() &&			\
-				 xen_domain_type == XEN_PV_DOMAIN)
-#define xen_hvm_domain()	(xen_domain() &&			\
-				 xen_domain_type == XEN_HVM_DOMAIN)
-
-#ifdef CONFIG_XEN_DOM0
-#define xen_initial_domain()	(xen_pv_domain() &&			\
-				 (xen_start_info->flags & SIF_INITDOMAIN))
-#else
-#define xen_initial_domain()	(0)
-#endif
-
-
 #ifdef CONFIG_XEN
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index c0fca2c..df639db7 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -131,6 +131,7 @@
 }
 
 struct pci_root_info {
+	struct acpi_device *bridge;
 	struct pci_controller *controller;
 	char *name;
 };
@@ -297,9 +298,20 @@
 	window->offset = offset;
 
 	if (insert_resource(root, &window->resource)) {
-		printk(KERN_ERR "alloc 0x%llx-0x%llx from %s for %s failed\n",
-			window->resource.start, window->resource.end,
-			root->name, info->name);
+		dev_err(&info->bridge->dev,
+			"can't allocate host bridge window %pR\n",
+			&window->resource);
+	} else {
+		if (offset)
+			dev_info(&info->bridge->dev, "host bridge window %pR "
+				 "(PCI address [%#llx-%#llx])\n",
+				 &window->resource,
+				 window->resource.start - offset,
+				 window->resource.end - offset);
+		else
+			dev_info(&info->bridge->dev,
+				 "host bridge window %pR\n",
+				 &window->resource);
 	}
 
 	return AE_OK;
@@ -319,8 +331,9 @@
 		    (res->end - res->start < 16))
 			continue;
 		if (j >= PCI_BUS_NUM_RESOURCES) {
-			printk("Ignoring range [%#llx-%#llx] (%lx)\n",
-					res->start, res->end, res->flags);
+			dev_warn(&bus->dev,
+				 "ignoring host bridge window %pR (no space)\n",
+				 res);
 			continue;
 		}
 		bus->resource[j++] = res;
@@ -364,6 +377,7 @@
 			goto out3;
 
 		sprintf(name, "PCI Bus %04x:%02x", domain, bus);
+		info.bridge = device;
 		info.controller = controller;
 		info.name = name;
 		acpi_walk_resources(device->handle, METHOD_NAME__CRS,
@@ -720,9 +734,6 @@
 	return ret;
 }
 
-/* It's defined in drivers/pci/pci.c */
-extern u8 pci_cache_line_size;
-
 /**
  * set_pci_cacheline_size - determine cacheline size for PCI devices
  *
@@ -731,7 +742,7 @@
  *
  * Code mostly taken from arch/ia64/kernel/palinfo.c:cache_info().
  */
-static void __init set_pci_cacheline_size(void)
+static void __init set_pci_dfl_cacheline_size(void)
 {
 	unsigned long levels, unique_caches;
 	long status;
@@ -751,7 +762,7 @@
 			"(status=%ld)\n", __func__, status);
 		return;
 	}
-	pci_cache_line_size = (1 << cci.pcci_line_size) / 4;
+	pci_dfl_cache_line_size = (1 << cci.pcci_line_size) / 4;
 }
 
 u64 ia64_dma_get_required_mask(struct device *dev)
@@ -782,7 +793,7 @@
 
 static int __init pcibios_init(void)
 {
-	set_pci_cacheline_size();
+	set_pci_dfl_cacheline_size();
 	return 0;
 }
 
diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h
index b63e51c..b0576df 100644
--- a/arch/sparc/include/asm/pci_64.h
+++ b/arch/sparc/include/asm/pci_64.h
@@ -16,8 +16,6 @@
 
 #define PCI_IRQ_NONE		0xffffffff
 
-#define PCI_CACHE_LINE_BYTES	64
-
 static inline void pcibios_set_master(struct pci_dev *dev)
 {
 	/* No special bus mastering setup handling */
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index c686486..b85374f 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -1081,3 +1081,10 @@
 	*start = rp->start - offset;
 	*end = rp->end - offset;
 }
+
+static int __init pcibios_init(void)
+{
+	pci_dfl_cache_line_size = 64 >> 2;
+	return 0;
+}
+subsys_initcall(pcibios_init);
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index b399988..b4bf9a9 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -118,11 +118,27 @@
 
 /* pci-mmconfig.c */
 
+/* "PCI MMCONFIG %04x [bus %02x-%02x]" */
+#define PCI_MMCFG_RESOURCE_NAME_LEN (22 + 4 + 2 + 2)
+
+struct pci_mmcfg_region {
+	struct list_head list;
+	struct resource res;
+	u64 address;
+	char __iomem *virt;
+	u16 segment;
+	u8 start_bus;
+	u8 end_bus;
+	char name[PCI_MMCFG_RESOURCE_NAME_LEN];
+};
+
 extern int __init pci_mmcfg_arch_init(void);
 extern void __init pci_mmcfg_arch_free(void);
+extern struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus);
 
-extern struct acpi_mcfg_allocation *pci_mmcfg_config;
-extern int pci_mmcfg_config_num;
+extern struct list_head pci_mmcfg_list;
+
+#define PCI_MMCFG_BUS_OFFSET(bus)      ((bus) << 20)
 
 /*
  * AMD Fam10h CPUs are buggy, and cannot access MMIO config space
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index d5b7e90..396ff4c 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -37,31 +37,4 @@
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
-enum xen_domain_type {
-	XEN_NATIVE,		/* running on bare hardware    */
-	XEN_PV_DOMAIN,		/* running in a PV domain      */
-	XEN_HVM_DOMAIN,		/* running in a Xen hvm domain */
-};
-
-#ifdef CONFIG_XEN
-extern enum xen_domain_type xen_domain_type;
-#else
-#define xen_domain_type		XEN_NATIVE
-#endif
-
-#define xen_domain()		(xen_domain_type != XEN_NATIVE)
-#define xen_pv_domain()		(xen_domain() &&			\
-				 xen_domain_type == XEN_PV_DOMAIN)
-#define xen_hvm_domain()	(xen_domain() &&			\
-				 xen_domain_type == XEN_HVM_DOMAIN)
-
-#ifdef CONFIG_XEN_DOM0
-#include <xen/interface/xen.h>
-
-#define xen_initial_domain()	(xen_pv_domain() && \
-				 xen_start_info->flags & SIF_INITDOMAIN)
-#else  /* !CONFIG_XEN_DOM0 */
-#define xen_initial_domain()	(0)
-#endif	/* CONFIG_XEN_DOM0 */
-
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 7ffc399..9c4a6f7 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -1336,6 +1336,9 @@
 		iommu_detected = 1;
 		amd_iommu_detected = 1;
 		x86_init.iommu.iommu_init = amd_iommu_init;
+
+		/* Make sure ACS will be enabled */
+		pci_request_acs();
 	}
 }
 
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index d49202e..564b008 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -15,3 +15,8 @@
 
 obj-y				+= common.o early.o
 obj-y				+= amd_bus.o
+obj-$(CONFIG_X86_64)		+= bus_numa.o intel_bus.o
+
+ifeq ($(CONFIG_PCI_DEBUG),y)
+EXTRA_CFLAGS += -DDEBUG
+endif
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 1014eb4..959e548 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -7,6 +7,7 @@
 #include <asm/pci_x86.h>
 
 struct pci_root_info {
+	struct acpi_device *bridge;
 	char *name;
 	unsigned int res_num;
 	struct resource *res;
@@ -58,6 +59,30 @@
 	return false;
 }
 
+static void
+align_resource(struct acpi_device *bridge, struct resource *res)
+{
+	int align = (res->flags & IORESOURCE_MEM) ? 16 : 4;
+
+	/*
+	 * Host bridge windows are not BARs, but the decoders on the PCI side
+	 * that claim this address space have starting alignment and length
+	 * constraints, so fix any obvious BIOS goofs.
+	 */
+	if (!IS_ALIGNED(res->start, align)) {
+		dev_printk(KERN_DEBUG, &bridge->dev,
+			   "host bridge window %pR invalid; "
+			   "aligning start to %d-byte boundary\n", res, align);
+		res->start &= ~(align - 1);
+	}
+	if (!IS_ALIGNED(res->end + 1, align)) {
+		dev_printk(KERN_DEBUG, &bridge->dev,
+			   "host bridge window %pR invalid; "
+			   "aligning end to %d-byte boundary\n", res, align);
+		res->end = ALIGN(res->end, align) - 1;
+	}
+}
+
 static acpi_status
 setup_resource(struct acpi_resource *acpi_res, void *data)
 {
@@ -91,11 +116,12 @@
 	start = addr.minimum + addr.translation_offset;
 	end = start + addr.address_length - 1;
 	if (info->res_num >= max_root_bus_resources) {
-		printk(KERN_WARNING "PCI: Failed to allocate 0x%lx-0x%lx "
-			"from %s for %s due to _CRS returning more than "
-			"%d resource descriptors\n", (unsigned long) start,
-			(unsigned long) end, root->name, info->name,
-			max_root_bus_resources);
+		if (pci_probe & PCI_USE__CRS)
+			printk(KERN_WARNING "PCI: Failed to allocate "
+			       "0x%lx-0x%lx from %s for %s due to _CRS "
+			       "returning more than %d resource descriptors\n",
+			       (unsigned long) start, (unsigned long) end,
+			       root->name, info->name, max_root_bus_resources);
 		return AE_OK;
 	}
 
@@ -105,14 +131,28 @@
 	res->start = start;
 	res->end = end;
 	res->child = NULL;
+	align_resource(info->bridge, res);
+
+	if (!(pci_probe & PCI_USE__CRS)) {
+		dev_printk(KERN_DEBUG, &info->bridge->dev,
+			   "host bridge window %pR (ignored)\n", res);
+		return AE_OK;
+	}
 
 	if (insert_resource(root, res)) {
-		printk(KERN_ERR "PCI: Failed to allocate 0x%lx-0x%lx "
-			"from %s for %s\n", (unsigned long) res->start,
-			(unsigned long) res->end, root->name, info->name);
+		dev_err(&info->bridge->dev,
+			"can't allocate host bridge window %pR\n", res);
 	} else {
 		info->bus->resource[info->res_num] = res;
 		info->res_num++;
+		if (addr.translation_offset)
+			dev_info(&info->bridge->dev, "host bridge window %pR "
+				 "(PCI address [%#llx-%#llx])\n",
+				 res, res->start - addr.translation_offset,
+				 res->end - addr.translation_offset);
+		else
+			dev_info(&info->bridge->dev,
+				 "host bridge window %pR\n", res);
 	}
 	return AE_OK;
 }
@@ -124,6 +164,12 @@
 	struct pci_root_info info;
 	size_t size;
 
+	if (!(pci_probe & PCI_USE__CRS))
+		dev_info(&device->dev,
+			 "ignoring host bridge windows from ACPI; "
+			 "boot with \"pci=use_crs\" to use them\n");
+
+	info.bridge = device;
 	info.bus = bus;
 	info.res_num = 0;
 	acpi_walk_resources(device->handle, METHOD_NAME__CRS, count_resource,
@@ -163,8 +209,9 @@
 #endif
 
 	if (domain && !pci_domains_supported) {
-		printk(KERN_WARNING "PCI: Multiple domains not supported "
-		       "(dom %d, bus %d)\n", domain, busnum);
+		printk(KERN_WARNING "pci_bus %04x:%02x: "
+		       "ignored (multiple domains not supported)\n",
+		       domain, busnum);
 		return NULL;
 	}
 
@@ -188,7 +235,8 @@
 	 */
 	sd = kzalloc(sizeof(*sd), GFP_KERNEL);
 	if (!sd) {
-		printk(KERN_ERR "PCI: OOM, not probing PCI bus %02x\n", busnum);
+		printk(KERN_WARNING "pci_bus %04x:%02x: "
+		       "ignored (out of memory)\n", domain, busnum);
 		return NULL;
 	}
 
@@ -209,9 +257,7 @@
 	} else {
 		bus = pci_create_bus(NULL, busnum, &pci_root_ops, sd);
 		if (bus) {
-			if (pci_probe & PCI_USE__CRS)
-				get_current_resources(device, busnum, domain,
-							bus);
+			get_current_resources(device, busnum, domain, bus);
 			bus->subordinate = pci_scan_child_bus(bus);
 		}
 	}
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 572ee97..95ecbd4 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -6,10 +6,10 @@
 
 #ifdef CONFIG_X86_64
 #include <asm/pci-direct.h>
-#include <asm/mpspec.h>
-#include <linux/cpumask.h>
 #endif
 
+#include "bus_numa.h"
+
 /*
  * This discovers the pcibus <-> node mapping on AMD K8.
  * also get peer root bus resource for io,mmio
@@ -17,67 +17,6 @@
 
 #ifdef CONFIG_X86_64
 
-/*
- * sub bus (transparent) will use entres from 3 to store extra from root,
- * so need to make sure have enought slot there, increase PCI_BUS_NUM_RESOURCES?
- */
-#define RES_NUM 16
-struct pci_root_info {
-	char name[12];
-	unsigned int res_num;
-	struct resource res[RES_NUM];
-	int bus_min;
-	int bus_max;
-	int node;
-	int link;
-};
-
-/* 4 at this time, it may become to 32 */
-#define PCI_ROOT_NR 4
-static int pci_root_num;
-static struct pci_root_info pci_root_info[PCI_ROOT_NR];
-
-void x86_pci_root_bus_res_quirks(struct pci_bus *b)
-{
-	int i;
-	int j;
-	struct pci_root_info *info;
-
-	/* don't go for it if _CRS is used already */
-	if (b->resource[0] != &ioport_resource ||
-	    b->resource[1] != &iomem_resource)
-		return;
-
-	/* if only one root bus, don't need to anything */
-	if (pci_root_num < 2)
-		return;
-
-	for (i = 0; i < pci_root_num; i++) {
-		if (pci_root_info[i].bus_min == b->number)
-			break;
-	}
-
-	if (i == pci_root_num)
-		return;
-
-	printk(KERN_DEBUG "PCI: peer root bus %02x res updated from pci conf\n",
-			b->number);
-
-	info = &pci_root_info[i];
-	for (j = 0; j < info->res_num; j++) {
-		struct resource *res;
-		struct resource *root;
-
-		res = &info->res[j];
-		b->resource[j] = res;
-		if (res->flags & IORESOURCE_IO)
-			root = &ioport_resource;
-		else
-			root = &iomem_resource;
-		insert_resource(root, res);
-	}
-}
-
 #define RANGE_NUM 16
 
 struct res_range {
@@ -130,52 +69,6 @@
 	}
 }
 
-static void __init update_res(struct pci_root_info *info, size_t start,
-			      size_t end, unsigned long flags, int merge)
-{
-	int i;
-	struct resource *res;
-
-	if (!merge)
-		goto addit;
-
-	/* try to merge it with old one */
-	for (i = 0; i < info->res_num; i++) {
-		size_t final_start, final_end;
-		size_t common_start, common_end;
-
-		res = &info->res[i];
-		if (res->flags != flags)
-			continue;
-
-		common_start = max((size_t)res->start, start);
-		common_end = min((size_t)res->end, end);
-		if (common_start > common_end + 1)
-			continue;
-
-		final_start = min((size_t)res->start, start);
-		final_end = max((size_t)res->end, end);
-
-		res->start = final_start;
-		res->end = final_end;
-		return;
-	}
-
-addit:
-
-	/* need to add that */
-	if (info->res_num >= RES_NUM)
-		return;
-
-	res = &info->res[info->res_num];
-	res->name = info->name;
-	res->flags = flags;
-	res->start = start;
-	res->end = end;
-	res->child = NULL;
-	info->res_num++;
-}
-
 struct pci_hostbridge_probe {
 	u32 bus;
 	u32 slot;
@@ -230,7 +123,6 @@
 	int j;
 	unsigned bus;
 	unsigned slot;
-	int found;
 	int node;
 	int link;
 	int def_node;
@@ -247,7 +139,7 @@
 	if (!early_pci_allowed())
 		return -1;
 
-	found = 0;
+	found_all_numa_early = 0;
 	for (i = 0; i < ARRAY_SIZE(pci_probes); i++) {
 		u32 id;
 		u16 device;
@@ -261,12 +153,12 @@
 		device = (id>>16) & 0xffff;
 		if (pci_probes[i].vendor == vendor &&
 		    pci_probes[i].device == device) {
-			found = 1;
+			found_all_numa_early = 1;
 			break;
 		}
 	}
 
-	if (!found)
+	if (!found_all_numa_early)
 		return 0;
 
 	pci_root_num = 0;
@@ -488,7 +380,7 @@
 		info = &pci_root_info[i];
 		res_num = info->res_num;
 		busnum = info->bus_min;
-		printk(KERN_DEBUG "bus: [%02x,%02x] on node %x link %x\n",
+		printk(KERN_DEBUG "bus: [%02x, %02x] on node %x link %x\n",
 		       info->bus_min, info->bus_max, info->node, info->link);
 		for (j = 0; j < res_num; j++) {
 			res = &info->res[j];
diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c
new file mode 100644
index 0000000..145df00
--- /dev/null
+++ b/arch/x86/pci/bus_numa.c
@@ -0,0 +1,101 @@
+#include <linux/init.h>
+#include <linux/pci.h>
+
+#include "bus_numa.h"
+
+int pci_root_num;
+struct pci_root_info pci_root_info[PCI_ROOT_NR];
+int found_all_numa_early;
+
+void x86_pci_root_bus_res_quirks(struct pci_bus *b)
+{
+	int i;
+	int j;
+	struct pci_root_info *info;
+
+	/* don't go for it if _CRS is used already */
+	if (b->resource[0] != &ioport_resource ||
+	    b->resource[1] != &iomem_resource)
+		return;
+
+	if (!pci_root_num)
+		return;
+
+	/* for amd, if only one root bus, don't need to do anything */
+	if (pci_root_num < 2 && found_all_numa_early)
+		return;
+
+	for (i = 0; i < pci_root_num; i++) {
+		if (pci_root_info[i].bus_min == b->number)
+			break;
+	}
+
+	if (i == pci_root_num)
+		return;
+
+	printk(KERN_DEBUG "PCI: peer root bus %02x res updated from pci conf\n",
+			b->number);
+
+	info = &pci_root_info[i];
+	for (j = 0; j < info->res_num; j++) {
+		struct resource *res;
+		struct resource *root;
+
+		res = &info->res[j];
+		b->resource[j] = res;
+		if (res->flags & IORESOURCE_IO)
+			root = &ioport_resource;
+		else
+			root = &iomem_resource;
+		insert_resource(root, res);
+	}
+}
+
+void __init update_res(struct pci_root_info *info, size_t start,
+			      size_t end, unsigned long flags, int merge)
+{
+	int i;
+	struct resource *res;
+
+	if (start > end)
+		return;
+
+	if (!merge)
+		goto addit;
+
+	/* try to merge it with old one */
+	for (i = 0; i < info->res_num; i++) {
+		size_t final_start, final_end;
+		size_t common_start, common_end;
+
+		res = &info->res[i];
+		if (res->flags != flags)
+			continue;
+
+		common_start = max((size_t)res->start, start);
+		common_end = min((size_t)res->end, end);
+		if (common_start > common_end + 1)
+			continue;
+
+		final_start = min((size_t)res->start, start);
+		final_end = max((size_t)res->end, end);
+
+		res->start = final_start;
+		res->end = final_end;
+		return;
+	}
+
+addit:
+
+	/* need to add that */
+	if (info->res_num >= RES_NUM)
+		return;
+
+	res = &info->res[info->res_num];
+	res->name = info->name;
+	res->flags = flags;
+	res->start = start;
+	res->end = end;
+	res->child = NULL;
+	info->res_num++;
+}
diff --git a/arch/x86/pci/bus_numa.h b/arch/x86/pci/bus_numa.h
new file mode 100644
index 0000000..adbc23fe
--- /dev/null
+++ b/arch/x86/pci/bus_numa.h
@@ -0,0 +1,27 @@
+#ifdef CONFIG_X86_64
+
+/*
+ * sub bus (transparent) will use entres from 3 to store extra from
+ * root, so need to make sure we have enough slot there, Should we
+ * increase PCI_BUS_NUM_RESOURCES?
+ */
+#define RES_NUM 16
+struct pci_root_info {
+	char name[12];
+	unsigned int res_num;
+	struct resource res[RES_NUM];
+	int bus_min;
+	int bus_max;
+	int node;
+	int link;
+};
+
+/* 4 at this time, it may become to 32 */
+#define PCI_ROOT_NR 4
+extern int pci_root_num;
+extern struct pci_root_info pci_root_info[PCI_ROOT_NR];
+extern int found_all_numa_early;
+
+extern void update_res(struct pci_root_info *info, size_t start,
+			      size_t end, unsigned long flags, int merge);
+#endif
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 1331fcf..d2552c6 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -410,8 +410,6 @@
 	return bus;
 }
 
-extern u8 pci_cache_line_size;
-
 int __init pcibios_init(void)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
@@ -422,15 +420,19 @@
 	}
 
 	/*
-	 * Assume PCI cacheline size of 32 bytes for all x86s except K7/K8
-	 * and P4. It's also good for 386/486s (which actually have 16)
+	 * Set PCI cacheline size to that of the CPU if the CPU has reported it.
+	 * (For older CPUs that don't support cpuid, we se it to 32 bytes
+	 * It's also good for 386/486s (which actually have 16)
 	 * as quite a few PCI devices do not support smaller values.
 	 */
-	pci_cache_line_size = 32 >> 2;
-	if (c->x86 >= 6 && c->x86_vendor == X86_VENDOR_AMD)
-		pci_cache_line_size = 64 >> 2;	/* K7 & K8 */
-	else if (c->x86 > 6 && c->x86_vendor == X86_VENDOR_INTEL)
-		pci_cache_line_size = 128 >> 2;	/* P4 */
+	if (c->x86_clflush_size > 0) {
+		pci_dfl_cache_line_size = c->x86_clflush_size >> 2;
+		printk(KERN_DEBUG "PCI: pci_cache_line_size set to %d bytes\n",
+			pci_dfl_cache_line_size << 2);
+	} else {
+ 		pci_dfl_cache_line_size = 32 >> 2;
+		printk(KERN_DEBUG "PCI: Unknown cacheline size. Setting to 32 bytes\n");
+	}
 
 	pcibios_resource_survey();
 
diff --git a/arch/x86/pci/early.c b/arch/x86/pci/early.c
index aaf26ae..d1067d5 100644
--- a/arch/x86/pci/early.c
+++ b/arch/x86/pci/early.c
@@ -12,8 +12,6 @@
 	u32 v;
 	outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8);
 	v = inl(0xcfc);
-	if (v != 0xffffffff)
-		pr_debug("%x reading 4 from %x: %x\n", slot, offset, v);
 	return v;
 }
 
@@ -22,7 +20,6 @@
 	u8 v;
 	outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8);
 	v = inb(0xcfc + (offset&3));
-	pr_debug("%x reading 1 from %x: %x\n", slot, offset, v);
 	return v;
 }
 
@@ -31,28 +28,24 @@
 	u16 v;
 	outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8);
 	v = inw(0xcfc + (offset&2));
-	pr_debug("%x reading 2 from %x: %x\n", slot, offset, v);
 	return v;
 }
 
 void write_pci_config(u8 bus, u8 slot, u8 func, u8 offset,
 				    u32 val)
 {
-	pr_debug("%x writing to %x: %x\n", slot, offset, val);
 	outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8);
 	outl(val, 0xcfc);
 }
 
 void write_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset, u8 val)
 {
-	pr_debug("%x writing to %x: %x\n", slot, offset, val);
 	outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8);
 	outb(val, 0xcfc + (offset&3));
 }
 
 void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val)
 {
-	pr_debug("%x writing to %x: %x\n", slot, offset, val);
 	outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8);
 	outw(val, 0xcfc + (offset&2));
 }
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index b22d13b..5dc9e8c 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -129,7 +129,9 @@
 					continue;
 				if (!r->start ||
 				    pci_claim_resource(dev, idx) < 0) {
-					dev_info(&dev->dev, "BAR %d: can't allocate resource\n", idx);
+					dev_info(&dev->dev,
+						 "can't reserve window %pR\n",
+						 r);
 					/*
 					 * Something is wrong with the region.
 					 * Invalidate the resource to prevent
@@ -144,16 +146,29 @@
 	}
 }
 
+struct pci_check_idx_range {
+	int start;
+	int end;
+};
+
 static void __init pcibios_allocate_resources(int pass)
 {
 	struct pci_dev *dev = NULL;
-	int idx, disabled;
+	int idx, disabled, i;
 	u16 command;
 	struct resource *r;
 
+	struct pci_check_idx_range idx_range[] = {
+		{ PCI_STD_RESOURCES, PCI_STD_RESOURCE_END },
+#ifdef CONFIG_PCI_IOV
+		{ PCI_IOV_RESOURCES, PCI_IOV_RESOURCE_END },
+#endif
+	};
+
 	for_each_pci_dev(dev) {
 		pci_read_config_word(dev, PCI_COMMAND, &command);
-		for (idx = 0; idx < PCI_ROM_RESOURCE; idx++) {
+		for (i = 0; i < ARRAY_SIZE(idx_range); i++)
+		for (idx = idx_range[i].start; idx <= idx_range[i].end; idx++) {
 			r = &dev->resource[idx];
 			if (r->parent)		/* Already allocated */
 				continue;
@@ -164,12 +179,12 @@
 			else
 				disabled = !(command & PCI_COMMAND_MEMORY);
 			if (pass == disabled) {
-				dev_dbg(&dev->dev, "resource %#08llx-%#08llx (f=%lx, d=%d, p=%d)\n",
-					(unsigned long long) r->start,
-					(unsigned long long) r->end,
-					r->flags, disabled, pass);
+				dev_dbg(&dev->dev,
+					"BAR %d: reserving %pr (d=%d, p=%d)\n",
+					idx, r, disabled, pass);
 				if (pci_claim_resource(dev, idx) < 0) {
-					dev_info(&dev->dev, "BAR %d: can't allocate resource\n", idx);
+					dev_info(&dev->dev,
+						 "can't reserve %pR\n", r);
 					/* We'll assign a new address later */
 					r->end -= r->start;
 					r->start = 0;
@@ -182,7 +197,7 @@
 				/* Turn the ROM off, leave the resource region,
 				 * but keep it unregistered. */
 				u32 reg;
-				dev_dbg(&dev->dev, "disabling ROM\n");
+				dev_dbg(&dev->dev, "disabling ROM %pR\n", r);
 				r->flags &= ~IORESOURCE_ROM_ENABLE;
 				pci_read_config_dword(dev,
 						dev->rom_base_reg, &reg);
@@ -282,6 +297,15 @@
 		return -EINVAL;
 
 	prot = pgprot_val(vma->vm_page_prot);
+
+	/*
+ 	 * Return error if pat is not enabled and write_combine is requested.
+ 	 * Caller can followup with UC MINUS request and add a WC mtrr if there
+ 	 * is a free mtrr slot.
+ 	 */
+	if (!pat_enabled && write_combine)
+		return -EINVAL;
+
 	if (pat_enabled && write_combine)
 		prot |= _PAGE_CACHE_WC;
 	else if (pat_enabled || boot_cpu_data.x86 > 3)
diff --git a/arch/x86/pci/intel_bus.c b/arch/x86/pci/intel_bus.c
new file mode 100644
index 0000000..b7a55dc
--- /dev/null
+++ b/arch/x86/pci/intel_bus.c
@@ -0,0 +1,90 @@
+/*
+ * to read io range from IOH pci conf, need to do it after mmconfig is there
+ */
+
+#include <linux/delay.h>
+#include <linux/dmi.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <asm/pci_x86.h>
+
+#include "bus_numa.h"
+
+static inline void print_ioh_resources(struct pci_root_info *info)
+{
+	int res_num;
+	int busnum;
+	int i;
+
+	printk(KERN_DEBUG "IOH bus: [%02x, %02x]\n",
+			info->bus_min, info->bus_max);
+	res_num = info->res_num;
+	busnum = info->bus_min;
+	for (i = 0; i < res_num; i++) {
+		struct resource *res;
+
+		res = &info->res[i];
+		printk(KERN_DEBUG "IOH bus: %02x index %x %s: [%llx, %llx]\n",
+			busnum, i,
+			(res->flags & IORESOURCE_IO) ? "io port" :
+							"mmio",
+			res->start, res->end);
+	}
+}
+
+#define IOH_LIO			0x108
+#define IOH_LMMIOL		0x10c
+#define IOH_LMMIOH		0x110
+#define IOH_LMMIOH_BASEU	0x114
+#define IOH_LMMIOH_LIMITU	0x118
+#define IOH_LCFGBUS		0x11c
+
+static void __devinit pci_root_bus_res(struct pci_dev *dev)
+{
+	u16 word;
+	u32 dword;
+	struct pci_root_info *info;
+	u16 io_base, io_end;
+	u32 mmiol_base, mmiol_end;
+	u64 mmioh_base, mmioh_end;
+	int bus_base, bus_end;
+
+	if (pci_root_num >= PCI_ROOT_NR) {
+		printk(KERN_DEBUG "intel_bus.c: PCI_ROOT_NR is too small\n");
+		return;
+	}
+
+	info = &pci_root_info[pci_root_num];
+	pci_root_num++;
+
+	pci_read_config_word(dev, IOH_LCFGBUS, &word);
+	bus_base = (word & 0xff);
+	bus_end = (word & 0xff00) >> 8;
+	sprintf(info->name, "PCI Bus #%02x", bus_base);
+	info->bus_min = bus_base;
+	info->bus_max = bus_end;
+
+	pci_read_config_word(dev, IOH_LIO, &word);
+	io_base = (word & 0xf0) << (12 - 4);
+	io_end = (word & 0xf000) | 0xfff;
+	update_res(info, io_base, io_end, IORESOURCE_IO, 0);
+
+	pci_read_config_dword(dev, IOH_LMMIOL, &dword);
+	mmiol_base = (dword & 0xff00) << (24 - 8);
+	mmiol_end = (dword & 0xff000000) | 0xffffff;
+	update_res(info, mmiol_base, mmiol_end, IORESOURCE_MEM, 0);
+
+	pci_read_config_dword(dev, IOH_LMMIOH, &dword);
+	mmioh_base = ((u64)(dword & 0xfc00)) << (26 - 10);
+	mmioh_end = ((u64)(dword & 0xfc000000) | 0x3ffffff);
+	pci_read_config_dword(dev, IOH_LMMIOH_BASEU, &dword);
+	mmioh_base |= ((u64)(dword & 0x7ffff)) << 32;
+	pci_read_config_dword(dev, IOH_LMMIOH_LIMITU, &dword);
+	mmioh_end |= ((u64)(dword & 0x7ffff)) << 32;
+	update_res(info, mmioh_base, mmioh_end, IORESOURCE_MEM, 0);
+
+	print_ioh_resources(info);
+}
+
+/* intel IOH */
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x342e, pci_root_bus_res);
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 602c172d..b19d1e5 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -15,48 +15,98 @@
 #include <linux/acpi.h>
 #include <linux/sfi_acpi.h>
 #include <linux/bitmap.h>
-#include <linux/sort.h>
+#include <linux/dmi.h>
 #include <asm/e820.h>
 #include <asm/pci_x86.h>
 #include <asm/acpi.h>
 
 #define PREFIX "PCI: "
 
-/* aperture is up to 256MB but BIOS may reserve less */
-#define MMCONFIG_APER_MIN	(2 * 1024*1024)
-#define MMCONFIG_APER_MAX	(256 * 1024*1024)
-
 /* Indicate if the mmcfg resources have been placed into the resource table. */
 static int __initdata pci_mmcfg_resources_inserted;
 
-static __init int extend_mmcfg(int num)
+LIST_HEAD(pci_mmcfg_list);
+
+static __init void pci_mmconfig_remove(struct pci_mmcfg_region *cfg)
 {
-	struct acpi_mcfg_allocation *new;
-	int new_num = pci_mmcfg_config_num + num;
-
-	new = kzalloc(sizeof(pci_mmcfg_config[0]) * new_num, GFP_KERNEL);
-	if (!new)
-		return -1;
-
-	if (pci_mmcfg_config) {
-		memcpy(new, pci_mmcfg_config,
-			 sizeof(pci_mmcfg_config[0]) * new_num);
-		kfree(pci_mmcfg_config);
-	}
-	pci_mmcfg_config = new;
-
-	return 0;
+	if (cfg->res.parent)
+		release_resource(&cfg->res);
+	list_del(&cfg->list);
+	kfree(cfg);
 }
 
-static __init void fill_one_mmcfg(u64 addr, int segment, int start, int end)
+static __init void free_all_mmcfg(void)
 {
-	int i = pci_mmcfg_config_num;
+	struct pci_mmcfg_region *cfg, *tmp;
 
-	pci_mmcfg_config_num++;
-	pci_mmcfg_config[i].address = addr;
-	pci_mmcfg_config[i].pci_segment = segment;
-	pci_mmcfg_config[i].start_bus_number = start;
-	pci_mmcfg_config[i].end_bus_number = end;
+	pci_mmcfg_arch_free();
+	list_for_each_entry_safe(cfg, tmp, &pci_mmcfg_list, list)
+		pci_mmconfig_remove(cfg);
+}
+
+static __init void list_add_sorted(struct pci_mmcfg_region *new)
+{
+	struct pci_mmcfg_region *cfg;
+
+	/* keep list sorted by segment and starting bus number */
+	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
+		if (cfg->segment > new->segment ||
+		    (cfg->segment == new->segment &&
+		     cfg->start_bus >= new->start_bus)) {
+			list_add_tail(&new->list, &cfg->list);
+			return;
+		}
+	}
+	list_add_tail(&new->list, &pci_mmcfg_list);
+}
+
+static __init struct pci_mmcfg_region *pci_mmconfig_add(int segment, int start,
+							int end, u64 addr)
+{
+	struct pci_mmcfg_region *new;
+	int num_buses;
+	struct resource *res;
+
+	if (addr == 0)
+		return NULL;
+
+	new = kzalloc(sizeof(*new), GFP_KERNEL);
+	if (!new)
+		return NULL;
+
+	new->address = addr;
+	new->segment = segment;
+	new->start_bus = start;
+	new->end_bus = end;
+
+	list_add_sorted(new);
+
+	num_buses = end - start + 1;
+	res = &new->res;
+	res->start = addr + PCI_MMCFG_BUS_OFFSET(start);
+	res->end = addr + PCI_MMCFG_BUS_OFFSET(num_buses) - 1;
+	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	snprintf(new->name, PCI_MMCFG_RESOURCE_NAME_LEN,
+		 "PCI MMCONFIG %04x [bus %02x-%02x]", segment, start, end);
+	res->name = new->name;
+
+	printk(KERN_INFO PREFIX "MMCONFIG for domain %04x [bus %02x-%02x] at "
+	       "%pR (base %#lx)\n", segment, start, end, &new->res,
+	       (unsigned long) addr);
+
+	return new;
+}
+
+struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus)
+{
+	struct pci_mmcfg_region *cfg;
+
+	list_for_each_entry(cfg, &pci_mmcfg_list, list)
+		if (cfg->segment == segment &&
+		    cfg->start_bus <= bus && bus <= cfg->end_bus)
+			return cfg;
+
+	return NULL;
 }
 
 static const char __init *pci_mmcfg_e7520(void)
@@ -68,11 +118,9 @@
 	if (win == 0x0000 || win == 0xf000)
 		return NULL;
 
-	if (extend_mmcfg(1) == -1)
+	if (pci_mmconfig_add(0, 0, 255, win << 16) == NULL)
 		return NULL;
 
-	fill_one_mmcfg(win << 16, 0, 0, 255);
-
 	return "Intel Corporation E7520 Memory Controller Hub";
 }
 
@@ -114,11 +162,9 @@
 	if ((pciexbar & mask) >= 0xf0000000U)
 		return NULL;
 
-	if (extend_mmcfg(1) == -1)
+	if (pci_mmconfig_add(0, 0, (len >> 20) - 1, pciexbar & mask) == NULL)
 		return NULL;
 
-	fill_one_mmcfg(pciexbar & mask, 0, 0, (len >> 20) - 1);
-
 	return "Intel Corporation 945G/GZ/P/PL Express Memory Controller Hub";
 }
 
@@ -127,7 +173,7 @@
 	u32 low, high, address;
 	u64 base, msr;
 	int i;
-	unsigned segnbits = 0, busnbits;
+	unsigned segnbits = 0, busnbits, end_bus;
 
 	if (!(pci_probe & PCI_CHECK_ENABLE_AMD_MMCONF))
 		return NULL;
@@ -161,11 +207,13 @@
 		busnbits = 8;
 	}
 
-	if (extend_mmcfg(1 << segnbits) == -1)
-		return NULL;
-
+	end_bus = (1 << busnbits) - 1;
 	for (i = 0; i < (1 << segnbits); i++)
-		fill_one_mmcfg(base + (1<<28) * i, i, 0, (1 << busnbits) - 1);
+		if (pci_mmconfig_add(i, 0, end_bus,
+				     base + (1<<28) * i) == NULL) {
+			free_all_mmcfg();
+			return NULL;
+		}
 
 	return "AMD Family 10h NB";
 }
@@ -190,7 +238,7 @@
 	/*
 	 * do check if amd fam10h already took over
 	 */
-	if (!acpi_disabled || pci_mmcfg_config_num || mcp55_checked)
+	if (!acpi_disabled || !list_empty(&pci_mmcfg_list) || mcp55_checked)
 		return NULL;
 
 	mcp55_checked = true;
@@ -213,16 +261,14 @@
 		if (!(extcfg & extcfg_enable_mask))
 			continue;
 
-		if (extend_mmcfg(1) == -1)
-			continue;
-
 		size_index = (extcfg & extcfg_size_mask) >> extcfg_size_shift;
 		base = extcfg & extcfg_base_mask[size_index];
 		/* base could > 4G */
 		base <<= extcfg_base_lshift;
 		start = (extcfg & extcfg_start_mask) >> extcfg_start_shift;
 		end = start + extcfg_sizebus[size_index] - 1;
-		fill_one_mmcfg(base, 0, start, end);
+		if (pci_mmconfig_add(0, start, end, base) == NULL)
+			continue;
 		mcp55_mmconf_found++;
 	}
 
@@ -253,45 +299,27 @@
 	  0x0369, pci_mmcfg_nvidia_mcp55 },
 };
 
-static int __init cmp_mmcfg(const void *x1, const void *x2)
-{
-	const typeof(pci_mmcfg_config[0]) *m1 = x1;
-	const typeof(pci_mmcfg_config[0]) *m2 = x2;
-	int start1, start2;
-
-	start1 = m1->start_bus_number;
-	start2 = m2->start_bus_number;
-
-	return start1 - start2;
-}
-
 static void __init pci_mmcfg_check_end_bus_number(void)
 {
-	int i;
-	typeof(pci_mmcfg_config[0]) *cfg, *cfgx;
-
-	/* sort them at first */
-	sort(pci_mmcfg_config, pci_mmcfg_config_num,
-		 sizeof(pci_mmcfg_config[0]), cmp_mmcfg, NULL);
+	struct pci_mmcfg_region *cfg, *cfgx;
 
 	/* last one*/
-	if (pci_mmcfg_config_num > 0) {
-		i = pci_mmcfg_config_num - 1;
-		cfg = &pci_mmcfg_config[i];
-		if (cfg->end_bus_number < cfg->start_bus_number)
-			cfg->end_bus_number = 255;
-	}
+	cfg = list_entry(pci_mmcfg_list.prev, typeof(*cfg), list);
+	if (cfg)
+		if (cfg->end_bus < cfg->start_bus)
+			cfg->end_bus = 255;
+
+	if (list_is_singular(&pci_mmcfg_list))
+		return;
 
 	/* don't overlap please */
-	for (i = 0; i < pci_mmcfg_config_num - 1; i++) {
-		cfg = &pci_mmcfg_config[i];
-		cfgx = &pci_mmcfg_config[i+1];
+	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
+		if (cfg->end_bus < cfg->start_bus)
+			cfg->end_bus = 255;
 
-		if (cfg->end_bus_number < cfg->start_bus_number)
-			cfg->end_bus_number = 255;
-
-		if (cfg->end_bus_number >= cfgx->start_bus_number)
-			cfg->end_bus_number = cfgx->start_bus_number - 1;
+		cfgx = list_entry(cfg->list.next, typeof(*cfg), list);
+		if (cfg != cfgx && cfg->end_bus >= cfgx->start_bus)
+			cfg->end_bus = cfgx->start_bus - 1;
 	}
 }
 
@@ -306,8 +334,7 @@
 	if (!raw_pci_ops)
 		return 0;
 
-	pci_mmcfg_config_num = 0;
-	pci_mmcfg_config = NULL;
+	free_all_mmcfg();
 
 	for (i = 0; i < ARRAY_SIZE(pci_mmcfg_probes); i++) {
 		bus =  pci_mmcfg_probes[i].bus;
@@ -322,45 +349,22 @@
 			name = pci_mmcfg_probes[i].probe();
 
 		if (name)
-			printk(KERN_INFO "PCI: Found %s with MMCONFIG support.\n",
+			printk(KERN_INFO PREFIX "%s with MMCONFIG support\n",
 			       name);
 	}
 
 	/* some end_bus_number is crazy, fix it */
 	pci_mmcfg_check_end_bus_number();
 
-	return pci_mmcfg_config_num != 0;
+	return !list_empty(&pci_mmcfg_list);
 }
 
 static void __init pci_mmcfg_insert_resources(void)
 {
-#define PCI_MMCFG_RESOURCE_NAME_LEN 24
-	int i;
-	struct resource *res;
-	char *names;
-	unsigned num_buses;
+	struct pci_mmcfg_region *cfg;
 
-	res = kcalloc(PCI_MMCFG_RESOURCE_NAME_LEN + sizeof(*res),
-			pci_mmcfg_config_num, GFP_KERNEL);
-	if (!res) {
-		printk(KERN_ERR "PCI: Unable to allocate MMCONFIG resources\n");
-		return;
-	}
-
-	names = (void *)&res[pci_mmcfg_config_num];
-	for (i = 0; i < pci_mmcfg_config_num; i++, res++) {
-		struct acpi_mcfg_allocation *cfg = &pci_mmcfg_config[i];
-		num_buses = cfg->end_bus_number - cfg->start_bus_number + 1;
-		res->name = names;
-		snprintf(names, PCI_MMCFG_RESOURCE_NAME_LEN,
-			 "PCI MMCONFIG %u [%02x-%02x]", cfg->pci_segment,
-			 cfg->start_bus_number, cfg->end_bus_number);
-		res->start = cfg->address + (cfg->start_bus_number << 20);
-		res->end = res->start + (num_buses << 20) - 1;
-		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
-		insert_resource(&iomem_resource, res);
-		names += PCI_MMCFG_RESOURCE_NAME_LEN;
-	}
+	list_for_each_entry(cfg, &pci_mmcfg_list, list)
+		insert_resource(&iomem_resource, &cfg->res);
 
 	/* Mark that the resources have been inserted. */
 	pci_mmcfg_resources_inserted = 1;
@@ -437,11 +441,12 @@
 typedef int (*check_reserved_t)(u64 start, u64 end, unsigned type);
 
 static int __init is_mmconf_reserved(check_reserved_t is_reserved,
-		u64 addr, u64 size, int i,
-		typeof(pci_mmcfg_config[0]) *cfg, int with_e820)
+				    struct pci_mmcfg_region *cfg, int with_e820)
 {
+	u64 addr = cfg->res.start;
+	u64 size = resource_size(&cfg->res);
 	u64 old_size = size;
-	int valid = 0;
+	int valid = 0, num_buses;
 
 	while (!is_reserved(addr, addr + size, E820_RESERVED)) {
 		size >>= 1;
@@ -450,19 +455,25 @@
 	}
 
 	if (size >= (16UL<<20) || size == old_size) {
-		printk(KERN_NOTICE
-		       "PCI: MCFG area at %Lx reserved in %s\n",
-			addr, with_e820?"E820":"ACPI motherboard resources");
+		printk(KERN_INFO PREFIX "MMCONFIG at %pR reserved in %s\n",
+		       &cfg->res,
+		       with_e820 ? "E820" : "ACPI motherboard resources");
 		valid = 1;
 
 		if (old_size != size) {
-			/* update end_bus_number */
-			cfg->end_bus_number = cfg->start_bus_number + ((size>>20) - 1);
-			printk(KERN_NOTICE "PCI: updated MCFG configuration %d: base %lx "
-			       "segment %hu buses %u - %u\n",
-			       i, (unsigned long)cfg->address, cfg->pci_segment,
-			       (unsigned int)cfg->start_bus_number,
-			       (unsigned int)cfg->end_bus_number);
+			/* update end_bus */
+			cfg->end_bus = cfg->start_bus + ((size>>20) - 1);
+			num_buses = cfg->end_bus - cfg->start_bus + 1;
+			cfg->res.end = cfg->res.start +
+			    PCI_MMCFG_BUS_OFFSET(num_buses) - 1;
+			snprintf(cfg->name, PCI_MMCFG_RESOURCE_NAME_LEN,
+				 "PCI MMCONFIG %04x [bus %02x-%02x]",
+				 cfg->segment, cfg->start_bus, cfg->end_bus);
+			printk(KERN_INFO PREFIX
+			       "MMCONFIG for %04x [bus%02x-%02x] "
+			       "at %pR (base %#lx) (size reduced!)\n",
+			       cfg->segment, cfg->start_bus, cfg->end_bus,
+			       &cfg->res, (unsigned long) cfg->address);
 		}
 	}
 
@@ -471,45 +482,26 @@
 
 static void __init pci_mmcfg_reject_broken(int early)
 {
-	typeof(pci_mmcfg_config[0]) *cfg;
-	int i;
+	struct pci_mmcfg_region *cfg;
 
-	if ((pci_mmcfg_config_num == 0) ||
-	    (pci_mmcfg_config == NULL) ||
-	    (pci_mmcfg_config[0].address == 0))
-		return;
-
-	for (i = 0; i < pci_mmcfg_config_num; i++) {
+	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
 		int valid = 0;
-		u64 addr, size;
-
-		cfg = &pci_mmcfg_config[i];
-		addr = cfg->start_bus_number;
-		addr <<= 20;
-		addr += cfg->address;
-		size = cfg->end_bus_number + 1 - cfg->start_bus_number;
-		size <<= 20;
-		printk(KERN_NOTICE "PCI: MCFG configuration %d: base %lx "
-		       "segment %hu buses %u - %u\n",
-		       i, (unsigned long)cfg->address, cfg->pci_segment,
-		       (unsigned int)cfg->start_bus_number,
-		       (unsigned int)cfg->end_bus_number);
 
 		if (!early && !acpi_disabled)
-			valid = is_mmconf_reserved(is_acpi_reserved, addr, size, i, cfg, 0);
+			valid = is_mmconf_reserved(is_acpi_reserved, cfg, 0);
 
 		if (valid)
 			continue;
 
 		if (!early)
-			printk(KERN_ERR "PCI: BIOS Bug: MCFG area at %Lx is not"
-			       " reserved in ACPI motherboard resources\n",
-			       cfg->address);
+			printk(KERN_ERR FW_BUG PREFIX
+			       "MMCONFIG at %pR not reserved in "
+			       "ACPI motherboard resources\n", &cfg->res);
 
 		/* Don't try to do this check unless configuration
 		   type 1 is available. how about type 2 ?*/
 		if (raw_pci_ops)
-			valid = is_mmconf_reserved(e820_all_mapped, addr, size, i, cfg, 1);
+			valid = is_mmconf_reserved(e820_all_mapped, cfg, 1);
 
 		if (!valid)
 			goto reject;
@@ -518,34 +510,41 @@
 	return;
 
 reject:
-	printk(KERN_INFO "PCI: Not using MMCONFIG.\n");
-	pci_mmcfg_arch_free();
-	kfree(pci_mmcfg_config);
-	pci_mmcfg_config = NULL;
-	pci_mmcfg_config_num = 0;
+	printk(KERN_INFO PREFIX "not using MMCONFIG\n");
+	free_all_mmcfg();
 }
 
 static int __initdata known_bridge;
 
-static int acpi_mcfg_64bit_base_addr __initdata = FALSE;
-
-/* The physical address of the MMCONFIG aperture.  Set from ACPI tables. */
-struct acpi_mcfg_allocation *pci_mmcfg_config;
-int pci_mmcfg_config_num;
-
-static int __init acpi_mcfg_oem_check(struct acpi_table_mcfg *mcfg)
+static int __init acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg,
+					struct acpi_mcfg_allocation *cfg)
 {
-	if (!strcmp(mcfg->header.oem_id, "SGI"))
-		acpi_mcfg_64bit_base_addr = TRUE;
+	int year;
 
-	return 0;
+	if (cfg->address < 0xFFFFFFFF)
+		return 0;
+
+	if (!strcmp(mcfg->header.oem_id, "SGI"))
+		return 0;
+
+	if (mcfg->header.revision >= 1) {
+		if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) &&
+		    year >= 2010)
+			return 0;
+	}
+
+	printk(KERN_ERR PREFIX "MCFG region for %04x [bus %02x-%02x] at %#llx "
+	       "is above 4GB, ignored\n", cfg->pci_segment,
+	       cfg->start_bus_number, cfg->end_bus_number, cfg->address);
+	return -EINVAL;
 }
 
 static int __init pci_parse_mcfg(struct acpi_table_header *header)
 {
 	struct acpi_table_mcfg *mcfg;
+	struct acpi_mcfg_allocation *cfg_table, *cfg;
 	unsigned long i;
-	int config_size;
+	int entries;
 
 	if (!header)
 		return -EINVAL;
@@ -553,38 +552,33 @@
 	mcfg = (struct acpi_table_mcfg *)header;
 
 	/* how many config structures do we have */
-	pci_mmcfg_config_num = 0;
+	free_all_mmcfg();
+	entries = 0;
 	i = header->length - sizeof(struct acpi_table_mcfg);
 	while (i >= sizeof(struct acpi_mcfg_allocation)) {
-		++pci_mmcfg_config_num;
+		entries++;
 		i -= sizeof(struct acpi_mcfg_allocation);
 	};
-	if (pci_mmcfg_config_num == 0) {
+	if (entries == 0) {
 		printk(KERN_ERR PREFIX "MMCONFIG has no entries\n");
 		return -ENODEV;
 	}
 
-	config_size = pci_mmcfg_config_num * sizeof(*pci_mmcfg_config);
-	pci_mmcfg_config = kmalloc(config_size, GFP_KERNEL);
-	if (!pci_mmcfg_config) {
-		printk(KERN_WARNING PREFIX
-		       "No memory for MCFG config tables\n");
-		return -ENOMEM;
-	}
-
-	memcpy(pci_mmcfg_config, &mcfg[1], config_size);
-
-	acpi_mcfg_oem_check(mcfg);
-
-	for (i = 0; i < pci_mmcfg_config_num; ++i) {
-		if ((pci_mmcfg_config[i].address > 0xFFFFFFFF) &&
-		    !acpi_mcfg_64bit_base_addr) {
-			printk(KERN_ERR PREFIX
-			       "MMCONFIG not in low 4GB of memory\n");
-			kfree(pci_mmcfg_config);
-			pci_mmcfg_config_num = 0;
+	cfg_table = (struct acpi_mcfg_allocation *) &mcfg[1];
+	for (i = 0; i < entries; i++) {
+		cfg = &cfg_table[i];
+		if (acpi_mcfg_check_entry(mcfg, cfg)) {
+			free_all_mmcfg();
 			return -ENODEV;
 		}
+
+		if (pci_mmconfig_add(cfg->pci_segment, cfg->start_bus_number,
+				   cfg->end_bus_number, cfg->address) == NULL) {
+			printk(KERN_WARNING PREFIX
+			       "no memory for MCFG entries\n");
+			free_all_mmcfg();
+			return -ENOMEM;
+		}
 	}
 
 	return 0;
@@ -614,9 +608,7 @@
 
 	pci_mmcfg_reject_broken(early);
 
-	if ((pci_mmcfg_config_num == 0) ||
-	    (pci_mmcfg_config == NULL) ||
-	    (pci_mmcfg_config[0].address == 0))
+	if (list_empty(&pci_mmcfg_list))
 		return;
 
 	if (pci_mmcfg_arch_init())
@@ -648,9 +640,7 @@
 	 */
 	if ((pci_mmcfg_resources_inserted == 1) ||
 	    (pci_probe & PCI_PROBE_MMCONF) == 0 ||
-	    (pci_mmcfg_config_num == 0) ||
-	    (pci_mmcfg_config == NULL) ||
-	    (pci_mmcfg_config[0].address == 0))
+	    list_empty(&pci_mmcfg_list))
 		return 1;
 
 	/*
diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c
index f10a7e9..90d5fd47 100644
--- a/arch/x86/pci/mmconfig_32.c
+++ b/arch/x86/pci/mmconfig_32.c
@@ -27,18 +27,10 @@
  */
 static u32 get_base_addr(unsigned int seg, int bus, unsigned devfn)
 {
-	struct acpi_mcfg_allocation *cfg;
-	int cfg_num;
+	struct pci_mmcfg_region *cfg = pci_mmconfig_lookup(seg, bus);
 
-	for (cfg_num = 0; cfg_num < pci_mmcfg_config_num; cfg_num++) {
-		cfg = &pci_mmcfg_config[cfg_num];
-		if (cfg->pci_segment == seg &&
-		    (cfg->start_bus_number <= bus) &&
-		    (cfg->end_bus_number >= bus))
-			return cfg->address;
-	}
-
-	/* Fall back to type 0 */
+	if (cfg)
+		return cfg->address;
 	return 0;
 }
 
@@ -47,7 +39,7 @@
  */
 static void pci_exp_set_dev_base(unsigned int base, int bus, int devfn)
 {
-	u32 dev_base = base | (bus << 20) | (devfn << 12);
+	u32 dev_base = base | PCI_MMCFG_BUS_OFFSET(bus) | (devfn << 12);
 	int cpu = smp_processor_id();
 	if (dev_base != mmcfg_last_accessed_device ||
 	    cpu != mmcfg_last_accessed_cpu) {
diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c
index 94349f8..e783841 100644
--- a/arch/x86/pci/mmconfig_64.c
+++ b/arch/x86/pci/mmconfig_64.c
@@ -12,38 +12,15 @@
 #include <asm/e820.h>
 #include <asm/pci_x86.h>
 
-/* Static virtual mapping of the MMCONFIG aperture */
-struct mmcfg_virt {
-	struct acpi_mcfg_allocation *cfg;
-	char __iomem *virt;
-};
-static struct mmcfg_virt *pci_mmcfg_virt;
-
-static char __iomem *get_virt(unsigned int seg, unsigned bus)
-{
-	struct acpi_mcfg_allocation *cfg;
-	int cfg_num;
-
-	for (cfg_num = 0; cfg_num < pci_mmcfg_config_num; cfg_num++) {
-		cfg = pci_mmcfg_virt[cfg_num].cfg;
-		if (cfg->pci_segment == seg &&
-		    (cfg->start_bus_number <= bus) &&
-		    (cfg->end_bus_number >= bus))
-			return pci_mmcfg_virt[cfg_num].virt;
-	}
-
-	/* Fall back to type 0 */
-	return NULL;
-}
+#define PREFIX "PCI: "
 
 static char __iomem *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn)
 {
-	char __iomem *addr;
+	struct pci_mmcfg_region *cfg = pci_mmconfig_lookup(seg, bus);
 
-	addr = get_virt(seg, bus);
-	if (!addr)
-		return NULL;
- 	return addr + ((bus << 20) | (devfn << 12));
+	if (cfg && cfg->virt)
+		return cfg->virt + (PCI_MMCFG_BUS_OFFSET(bus) | (devfn << 12));
+	return NULL;
 }
 
 static int pci_mmcfg_read(unsigned int seg, unsigned int bus,
@@ -109,42 +86,30 @@
 	.write =	pci_mmcfg_write,
 };
 
-static void __iomem * __init mcfg_ioremap(struct acpi_mcfg_allocation *cfg)
+static void __iomem * __init mcfg_ioremap(struct pci_mmcfg_region *cfg)
 {
 	void __iomem *addr;
 	u64 start, size;
+	int num_buses;
 
-	start = cfg->start_bus_number;
-	start <<= 20;
-	start += cfg->address;
-	size = cfg->end_bus_number + 1 - cfg->start_bus_number;
-	size <<= 20;
+	start = cfg->address + PCI_MMCFG_BUS_OFFSET(cfg->start_bus);
+	num_buses = cfg->end_bus - cfg->start_bus + 1;
+	size = PCI_MMCFG_BUS_OFFSET(num_buses);
 	addr = ioremap_nocache(start, size);
-	if (addr) {
-		printk(KERN_INFO "PCI: Using MMCONFIG at %Lx - %Lx\n",
-		       start, start + size - 1);
-		addr -= cfg->start_bus_number << 20;
-	}
+	if (addr)
+		addr -= PCI_MMCFG_BUS_OFFSET(cfg->start_bus);
 	return addr;
 }
 
 int __init pci_mmcfg_arch_init(void)
 {
-	int i;
-	pci_mmcfg_virt = kzalloc(sizeof(*pci_mmcfg_virt) *
-				 pci_mmcfg_config_num, GFP_KERNEL);
-	if (pci_mmcfg_virt == NULL) {
-		printk(KERN_ERR "PCI: Can not allocate memory for mmconfig structures\n");
-		return 0;
-	}
+	struct pci_mmcfg_region *cfg;
 
-	for (i = 0; i < pci_mmcfg_config_num; ++i) {
-		pci_mmcfg_virt[i].cfg = &pci_mmcfg_config[i];
-		pci_mmcfg_virt[i].virt = mcfg_ioremap(&pci_mmcfg_config[i]);
-		if (!pci_mmcfg_virt[i].virt) {
-			printk(KERN_ERR "PCI: Cannot map mmconfig aperture for "
-					"segment %d\n",
-				pci_mmcfg_config[i].pci_segment);
+	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
+		cfg->virt = mcfg_ioremap(cfg);
+		if (!cfg->virt) {
+			printk(KERN_ERR PREFIX "can't map MMCONFIG at %pR\n",
+			       &cfg->res);
 			pci_mmcfg_arch_free();
 			return 0;
 		}
@@ -155,19 +120,12 @@
 
 void __init pci_mmcfg_arch_free(void)
 {
-	int i;
+	struct pci_mmcfg_region *cfg;
 
-	if (pci_mmcfg_virt == NULL)
-		return;
-
-	for (i = 0; i < pci_mmcfg_config_num; ++i) {
-		if (pci_mmcfg_virt[i].virt) {
-			iounmap(pci_mmcfg_virt[i].virt + (pci_mmcfg_virt[i].cfg->start_bus_number << 20));
-			pci_mmcfg_virt[i].virt = NULL;
-			pci_mmcfg_virt[i].cfg = NULL;
+	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
+		if (cfg->virt) {
+			iounmap(cfg->virt + PCI_MMCFG_BUS_OFFSET(cfg->start_bus));
+			cfg->virt = NULL;
 		}
 	}
-
-	kfree(pci_mmcfg_virt);
-	pci_mmcfg_virt = NULL;
 }
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b8e45f1..2b26dd5 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -27,7 +27,9 @@
 #include <linux/page-flags.h>
 #include <linux/highmem.h>
 #include <linux/console.h>
+#include <linux/pci.h>
 
+#include <xen/xen.h>
 #include <xen/interface/xen.h>
 #include <xen/interface/version.h>
 #include <xen/interface/physdev.h>
@@ -1175,7 +1177,11 @@
 		add_preferred_console("xenboot", 0, NULL);
 		add_preferred_console("tty", 0, NULL);
 		add_preferred_console("hvc", 0, NULL);
+	} else {
+		/* Make sure ACS will be enabled */
+		pci_request_acs();
 	}
+		
 
 	xen_raw_console_write("about to get started...\n");