Merge commit 'v2.6.34-rc1' into perf/urgent

Conflicts:
	tools/perf/util/probe-event.c

Merge reason: Pick up -rc1 and resolve the conflict as well.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

15 files changed, 410 insertions, 228 deletions

diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index 39fba37f702..b110d97fb92 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -13,9 +13,10 @@ obj-$(CONFIG_X86_VISWS)		+= visws.o
 
 obj-$(CONFIG_X86_NUMAQ)		+= numaq_32.o
 
+obj-$(CONFIG_X86_MRST)		+= mrst.o
+
 obj-y				+= common.o early.o
-obj-y				+= amd_bus.o
-obj-$(CONFIG_X86_64)		+= bus_numa.o
+obj-y				+= amd_bus.o bus_numa.o
 
 ifeq ($(CONFIG_PCI_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 959e548a703..6e22454bfaa 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -15,6 +15,51 @@ struct pci_root_info {
 	int busnum;
 };
 
+static bool pci_use_crs = true;
+
+static int __init set_use_crs(const struct dmi_system_id *id)
+{
+	pci_use_crs = true;
+	return 0;
+}
+
+static const struct dmi_system_id pci_use_crs_table[] __initconst = {
+	/* http://bugzilla.kernel.org/show_bug.cgi?id=14183 */
+	{
+		.callback = set_use_crs,
+		.ident = "IBM System x3800",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "x3800"),
+		},
+	},
+	{}
+};
+
+void __init pci_acpi_crs_quirks(void)
+{
+	int year;
+
+	if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008)
+		pci_use_crs = false;
+
+	dmi_check_system(pci_use_crs_table);
+
+	/*
+	 * If the user specifies "pci=use_crs" or "pci=nocrs" explicitly, that
+	 * takes precedence over anything we figured out above.
+	 */
+	if (pci_probe & PCI_ROOT_NO_CRS)
+		pci_use_crs = false;
+	else if (pci_probe & PCI_USE__CRS)
+		pci_use_crs = true;
+
+	printk(KERN_INFO "PCI: %s host bridge windows from ACPI; "
+	       "if necessary, use \"pci=%s\" and report a bug\n",
+	       pci_use_crs ? "Using" : "Ignoring",
+	       pci_use_crs ? "nocrs" : "use_crs");
+}
+
 static acpi_status
 resource_to_addr(struct acpi_resource *resource,
 			struct acpi_resource_address64 *addr)
@@ -45,20 +90,6 @@ count_resource(struct acpi_resource *acpi_res, void *data)
 	return AE_OK;
 }
 
-static int
-bus_has_transparent_bridge(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	list_for_each_entry(dev, &bus->devices, bus_list) {
-		u16 class = dev->class >> 8;
-
-		if (class == PCI_CLASS_BRIDGE_PCI && dev->transparent)
-			return true;
-	}
-	return false;
-}
-
 static void
 align_resource(struct acpi_device *bridge, struct resource *res)
 {
@@ -92,12 +123,8 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	acpi_status status;
 	unsigned long flags;
 	struct resource *root;
-	int max_root_bus_resources = PCI_BUS_NUM_RESOURCES;
 	u64 start, end;
 
-	if (bus_has_transparent_bridge(info->bus))
-		max_root_bus_resources -= 3;
-
 	status = resource_to_addr(acpi_res, &addr);
 	if (!ACPI_SUCCESS(status))
 		return AE_OK;
@@ -115,15 +142,6 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 
 	start = addr.minimum + addr.translation_offset;
 	end = start + addr.address_length - 1;
-	if (info->res_num >= 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;
-	}
 
 	res = &info->res[info->res_num];
 	res->name = info->name;
@@ -133,7 +151,7 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	res->child = NULL;
 	align_resource(info->bridge, res);
 
-	if (!(pci_probe & PCI_USE__CRS)) {
+	if (!pci_use_crs) {
 		dev_printk(KERN_DEBUG, &info->bridge->dev,
 			   "host bridge window %pR (ignored)\n", res);
 		return AE_OK;
@@ -143,7 +161,7 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 		dev_err(&info->bridge->dev,
 			"can't allocate host bridge window %pR\n", res);
 	} else {
-		info->bus->resource[info->res_num] = res;
+		pci_bus_add_resource(info->bus, res, 0);
 		info->res_num++;
 		if (addr.translation_offset)
 			dev_info(&info->bridge->dev, "host bridge window %pR "
@@ -164,10 +182,8 @@ get_current_resources(struct acpi_device *device, int busnum,
 	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");
+	if (pci_use_crs)
+		pci_bus_remove_resources(bus);
 
 	info.bridge = device;
 	info.bus = bus;
@@ -282,17 +298,14 @@ int __init pci_acpi_init(void)
 {
 	struct pci_dev *dev = NULL;
 
-	if (pcibios_scanned)
-		return 0;
-
 	if (acpi_noirq)
-		return 0;
+		return -ENODEV;
 
 	printk(KERN_INFO "PCI: Using ACPI for IRQ routing\n");
 	acpi_irq_penalty_init();
-	pcibios_scanned++;
 	pcibios_enable_irq = acpi_pci_irq_enable;
 	pcibios_disable_irq = acpi_pci_irq_disable;
+	x86_init.pci.init_irq = x86_init_noop;
 
 	if (pci_routeirq) {
 		/*
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 95ecbd49595..fc1e8fe07e5 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -2,11 +2,11 @@
 #include <linux/pci.h>
 #include <linux/topology.h>
 #include <linux/cpu.h>
+#include <linux/range.h>
+
 #include <asm/pci_x86.h>
 
-#ifdef CONFIG_X86_64
 #include <asm/pci-direct.h>
-#endif
 
 #include "bus_numa.h"
 
@@ -15,60 +15,6 @@
  * also get peer root bus resource for io,mmio
  */
 
-#ifdef CONFIG_X86_64
-
-#define RANGE_NUM 16
-
-struct res_range {
-	size_t start;
-	size_t end;
-};
-
-static void __init update_range(struct res_range *range, size_t start,
-				size_t end)
-{
-	int i;
-	int j;
-
-	for (j = 0; j < RANGE_NUM; j++) {
-		if (!range[j].end)
-			continue;
-
-		if (start <= range[j].start && end >= range[j].end) {
-			range[j].start = 0;
-			range[j].end = 0;
-			continue;
-		}
-
-		if (start <= range[j].start && end < range[j].end && range[j].start < end + 1) {
-			range[j].start = end + 1;
-			continue;
-		}
-
-
-		if (start > range[j].start && end >= range[j].end && range[j].end > start - 1) {
-			range[j].end = start - 1;
-			continue;
-		}
-
-		if (start > range[j].start && end < range[j].end) {
-			/* find the new spare */
-			for (i = 0; i < RANGE_NUM; i++) {
-				if (range[i].end == 0)
-					break;
-			}
-			if (i < RANGE_NUM) {
-				range[i].end = range[j].end;
-				range[i].start = end + 1;
-			} else {
-				printk(KERN_ERR "run of slot in ranges\n");
-			}
-			range[j].end = start - 1;
-			continue;
-		}
-	}
-}
-
 struct pci_hostbridge_probe {
 	u32 bus;
 	u32 slot;
@@ -111,6 +57,8 @@ static void __init get_pci_mmcfg_amd_fam10h_range(void)
 	fam10h_mmconf_end = base + (1ULL<<(segn_busn_bits + 20)) - 1;
 }
 
+#define RANGE_NUM 16
+
 /**
  * early_fill_mp_bus_to_node()
  * called before pcibios_scan_root and pci_scan_bus
@@ -130,16 +78,17 @@ static int __init early_fill_mp_bus_info(void)
 	struct pci_root_info *info;
 	u32 reg;
 	struct resource *res;
-	size_t start;
-	size_t end;
-	struct res_range range[RANGE_NUM];
+	u64 start;
+	u64 end;
+	struct range range[RANGE_NUM];
 	u64 val;
 	u32 address;
+	bool found;
 
 	if (!early_pci_allowed())
 		return -1;
 
-	found_all_numa_early = 0;
+	found = false;
 	for (i = 0; i < ARRAY_SIZE(pci_probes); i++) {
 		u32 id;
 		u16 device;
@@ -153,12 +102,12 @@ static int __init early_fill_mp_bus_info(void)
 		device = (id>>16) & 0xffff;
 		if (pci_probes[i].vendor == vendor &&
 		    pci_probes[i].device == device) {
-			found_all_numa_early = 1;
+			found = true;
 			break;
 		}
 	}
 
-	if (!found_all_numa_early)
+	if (!found)
 		return 0;
 
 	pci_root_num = 0;
@@ -196,7 +145,7 @@ static int __init early_fill_mp_bus_info(void)
 	def_link = (reg >> 8) & 0x03;
 
 	memset(range, 0, sizeof(range));
-	range[0].end = 0xffff;
+	add_range(range, RANGE_NUM, 0, 0, 0xffff + 1);
 	/* io port resource */
 	for (i = 0; i < 4; i++) {
 		reg = read_pci_config(bus, slot, 1, 0xc0 + (i << 3));
@@ -220,13 +169,13 @@ static int __init early_fill_mp_bus_info(void)
 
 		info = &pci_root_info[j];
 		printk(KERN_DEBUG "node %d link %d: io port [%llx, %llx]\n",
-		       node, link, (u64)start, (u64)end);
+		       node, link, start, end);
 
 		/* kernel only handle 16 bit only */
 		if (end > 0xffff)
 			end = 0xffff;
 		update_res(info, start, end, IORESOURCE_IO, 1);
-		update_range(range, start, end);
+		subtract_range(range, RANGE_NUM, start, end + 1);
 	}
 	/* add left over io port range to def node/link, [0, 0xffff] */
 	/* find the position */
@@ -241,29 +190,32 @@ static int __init early_fill_mp_bus_info(void)
 			if (!range[i].end)
 				continue;
 
-			update_res(info, range[i].start, range[i].end,
+			update_res(info, range[i].start, range[i].end - 1,
 				   IORESOURCE_IO, 1);
 		}
 	}
 
 	memset(range, 0, sizeof(range));
 	/* 0xfd00000000-0xffffffffff for HT */
-	range[0].end = (0xfdULL<<32) - 1;
+	end = cap_resource((0xfdULL<<32) - 1);
+	end++;
+	add_range(range, RANGE_NUM, 0, 0, end);
 
 	/* need to take out [0, TOM) for RAM*/
 	address = MSR_K8_TOP_MEM1;
 	rdmsrl(address, val);
 	end = (val & 0xffffff800000ULL);
-	printk(KERN_INFO "TOM: %016lx aka %ldM\n", end, end>>20);
+	printk(KERN_INFO "TOM: %016llx aka %lldM\n", end, end>>20);
 	if (end < (1ULL<<32))
-		update_range(range, 0, end - 1);
+		subtract_range(range, RANGE_NUM, 0, end);
 
 	/* get mmconfig */
 	get_pci_mmcfg_amd_fam10h_range();
 	/* need to take out mmconf range */
 	if (fam10h_mmconf_end) {
 		printk(KERN_DEBUG "Fam 10h mmconf [%llx, %llx]\n", fam10h_mmconf_start, fam10h_mmconf_end);
-		update_range(range, fam10h_mmconf_start, fam10h_mmconf_end);
+		subtract_range(range, RANGE_NUM, fam10h_mmconf_start,
+				 fam10h_mmconf_end + 1);
 	}
 
 	/* mmio resource */
@@ -293,7 +245,7 @@ static int __init early_fill_mp_bus_info(void)
 		info = &pci_root_info[j];
 
 		printk(KERN_DEBUG "node %d link %d: mmio [%llx, %llx]",
-		       node, link, (u64)start, (u64)end);
+		       node, link, start, end);
 		/*
 		 * some sick allocation would have range overlap with fam10h
 		 * mmconf range, so need to update start and end.
@@ -318,14 +270,15 @@ static int __init early_fill_mp_bus_info(void)
 				/* we got a hole */
 				endx = fam10h_mmconf_start - 1;
 				update_res(info, start, endx, IORESOURCE_MEM, 0);
-				update_range(range, start, endx);
-				printk(KERN_CONT " ==> [%llx, %llx]", (u64)start, endx);
+				subtract_range(range, RANGE_NUM, start,
+						 endx + 1);
+				printk(KERN_CONT " ==> [%llx, %llx]", start, endx);
 				start = fam10h_mmconf_end + 1;
 				changed = 1;
 			}
 			if (changed) {
 				if (start <= end) {
-					printk(KERN_CONT " %s [%llx, %llx]", endx?"and":"==>", (u64)start, (u64)end);
+					printk(KERN_CONT " %s [%llx, %llx]", endx ? "and" : "==>", start, end);
 				} else {
 					printk(KERN_CONT "%s\n", endx?"":" ==> none");
 					continue;
@@ -333,8 +286,9 @@ static int __init early_fill_mp_bus_info(void)
 			}
 		}
 
-		update_res(info, start, end, IORESOURCE_MEM, 1);
-		update_range(range, start, end);
+		update_res(info, cap_resource(start), cap_resource(end),
+				 IORESOURCE_MEM, 1);
+		subtract_range(range, RANGE_NUM, start, end + 1);
 		printk(KERN_CONT "\n");
 	}
 
@@ -348,8 +302,8 @@ static int __init early_fill_mp_bus_info(void)
 		address = MSR_K8_TOP_MEM2;
 		rdmsrl(address, val);
 		end = (val & 0xffffff800000ULL);
-		printk(KERN_INFO "TOM2: %016lx aka %ldM\n", end, end>>20);
-		update_range(range, 1ULL<<32, end - 1);
+		printk(KERN_INFO "TOM2: %016llx aka %lldM\n", end, end>>20);
+		subtract_range(range, RANGE_NUM, 1ULL<<32, end);
 	}
 
 	/*
@@ -368,7 +322,8 @@ static int __init early_fill_mp_bus_info(void)
 			if (!range[i].end)
 				continue;
 
-			update_res(info, range[i].start, range[i].end,
+			update_res(info, cap_resource(range[i].start),
+				   cap_resource(range[i].end - 1),
 				   IORESOURCE_MEM, 1);
 		}
 	}
@@ -384,24 +339,14 @@ static int __init early_fill_mp_bus_info(void)
 		       info->bus_min, info->bus_max, info->node, info->link);
 		for (j = 0; j < res_num; j++) {
 			res = &info->res[j];
-			printk(KERN_DEBUG "bus: %02x index %x %s: [%llx, %llx]\n",
-			       busnum, j,
-			       (res->flags & IORESOURCE_IO)?"io port":"mmio",
-			       res->start, res->end);
+			printk(KERN_DEBUG "bus: %02x index %x %pR\n",
+				       busnum, j, res);
 		}
 	}
 
 	return 0;
 }
 
-#else  /* !CONFIG_X86_64 */
-
-static int __init early_fill_mp_bus_info(void) { return 0; }
-
-#endif /* !CONFIG_X86_64 */
-
-/* common 32/64 bit code */
-
 #define ENABLE_CF8_EXT_CFG      (1ULL << 46)
 
 static void enable_pci_io_ecs(void *unused)
diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c
index f939d603adf..64a12288389 100644
--- a/arch/x86/pci/bus_numa.c
+++ b/arch/x86/pci/bus_numa.c
@@ -1,11 +1,11 @@
 #include <linux/init.h>
 #include <linux/pci.h>
+#include <linux/range.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)
 {
@@ -21,10 +21,6 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b)
 	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;
@@ -36,13 +32,14 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b)
 	printk(KERN_DEBUG "PCI: peer root bus %02x res updated from pci conf\n",
 			b->number);
 
+	pci_bus_remove_resources(b);
 	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;
+		pci_bus_add_resource(b, res, 0);
 		if (res->flags & IORESOURCE_IO)
 			root = &ioport_resource;
 		else
@@ -51,8 +48,8 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b)
 	}
 }
 
-void __devinit update_res(struct pci_root_info *info, size_t start,
-			      size_t end, unsigned long flags, int merge)
+void __devinit update_res(struct pci_root_info *info, resource_size_t start,
+			  resource_size_t end, unsigned long flags, int merge)
 {
 	int i;
 	struct resource *res;
@@ -60,25 +57,28 @@ void __devinit update_res(struct pci_root_info *info, size_t start,
 	if (start > end)
 		return;
 
+	if (start == MAX_RESOURCE)
+		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;
+		resource_size_t final_start, final_end;
+		resource_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);
+		common_start = max(res->start, start);
+		common_end = min(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);
+		final_start = min(res->start, start);
+		final_end = max(res->end, end);
 
 		res->start = final_start;
 		res->end = final_end;
diff --git a/arch/x86/pci/bus_numa.h b/arch/x86/pci/bus_numa.h
index adbc23fe82a..804a4b40c31 100644
--- a/arch/x86/pci/bus_numa.h
+++ b/arch/x86/pci/bus_numa.h
@@ -1,9 +1,8 @@
-#ifdef CONFIG_X86_64
-
+#ifndef __BUS_NUMA_H
+#define __BUS_NUMA_H
 /*
  * 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?
+ * root, so need to make sure we have enough slot there.
  */
 #define RES_NUM 16
 struct pci_root_info {
@@ -20,8 +19,7 @@ struct pci_root_info {
 #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);
+extern void update_res(struct pci_root_info *info, resource_size_t start,
+		      resource_size_t end, unsigned long flags, int merge);
 #endif
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index d2552c68e94..294e10cb11e 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -72,12 +72,6 @@ struct pci_ops pci_root_ops = {
 };
 
 /*
- * legacy, numa, and acpi all want to call pcibios_scan_root
- * from their initcalls. This flag prevents that.
- */
-int pcibios_scanned;
-
-/*
  * This interrupt-safe spinlock protects all accesses to PCI
  * configuration space.
  */
@@ -520,6 +514,9 @@ char * __devinit  pcibios_setup(char *str)
 	} else if (!strcmp(str, "use_crs")) {
 		pci_probe |= PCI_USE__CRS;
 		return NULL;
+	} else if (!strcmp(str, "nocrs")) {
+		pci_probe |= PCI_ROOT_NO_CRS;
+		return NULL;
 	} else if (!strcmp(str, "earlydump")) {
 		pci_early_dump_regs = 1;
 		return NULL;
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 5dc9e8c63fc..dece3eb9c90 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -60,22 +60,20 @@ skip_isa_ioresource_align(struct pci_dev *dev) {
  * but we want to try to avoid allocating at 0x2900-0x2bff
  * which might have be mirrored at 0x0100-0x03ff..
  */
-void
-pcibios_align_resource(void *data, struct resource *res,
+resource_size_t
+pcibios_align_resource(void *data, const struct resource *res,
 			resource_size_t size, resource_size_t align)
 {
 	struct pci_dev *dev = data;
+	resource_size_t start = res->start;
 
 	if (res->flags & IORESOURCE_IO) {
-		resource_size_t start = res->start;
-
 		if (skip_isa_ioresource_align(dev))
-			return;
-		if (start & 0x300) {
+			return start;
+		if (start & 0x300)
 			start = (start + 0x3ff) & ~0x3ff;
-			res->start = start;
-		}
 	}
+	return start;
 }
 EXPORT_SYMBOL(pcibios_align_resource);
 
@@ -257,10 +255,6 @@ void __init pcibios_resource_survey(void)
  */
 fs_initcall(pcibios_assign_resources);
 
-void __weak x86_pci_root_bus_res_quirks(struct pci_bus *b)
-{
-}
-
 /*
  *  If we set up a device for bus mastering, we need to check the latency
  *  timer as certain crappy BIOSes forget to set it properly.
diff --git a/arch/x86/pci/init.c b/arch/x86/pci/init.c
index 25a1f8efed4..adb62aaa7ec 100644
--- a/arch/x86/pci/init.c
+++ b/arch/x86/pci/init.c
@@ -1,6 +1,7 @@
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <asm/pci_x86.h>
+#include <asm/x86_init.h>
 
 /* arch_initcall has too random ordering, so call the initializers
    in the right sequence from here. */
@@ -15,10 +16,9 @@ static __init int pci_arch_init(void)
 	if (!(pci_probe & PCI_PROBE_NOEARLY))
 		pci_mmcfg_early_init();
 
-#ifdef CONFIG_PCI_OLPC
-	if (!pci_olpc_init())
-		return 0;	/* skip additional checks if it's an XO */
-#endif
+	if (x86_init.pci.arch_init && !x86_init.pci.arch_init())
+		return 0;
+
 #ifdef CONFIG_PCI_BIOS
 	pci_pcbios_init();
 #endif
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 0696d506c4a..8b107521d24 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -53,7 +53,7 @@ struct irq_router_handler {
 	int (*probe)(struct irq_router *r, struct pci_dev *router, u16 device);
 };
 
-int (*pcibios_enable_irq)(struct pci_dev *dev) = NULL;
+int (*pcibios_enable_irq)(struct pci_dev *dev) = pirq_enable_irq;
 void (*pcibios_disable_irq)(struct pci_dev *dev) = NULL;
 
 /*
@@ -590,6 +590,8 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route
 	case PCI_DEVICE_ID_INTEL_ICH10_1:
 	case PCI_DEVICE_ID_INTEL_ICH10_2:
 	case PCI_DEVICE_ID_INTEL_ICH10_3:
+	case PCI_DEVICE_ID_INTEL_CPT_LPC1:
+	case PCI_DEVICE_ID_INTEL_CPT_LPC2:
 		r->name = "PIIX/ICH";
 		r->get = pirq_piix_get;
 		r->set = pirq_piix_set;
@@ -1016,7 +1018,7 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 	return 1;
 }
 
-static void __init pcibios_fixup_irqs(void)
+void __init pcibios_fixup_irqs(void)
 {
 	struct pci_dev *dev = NULL;
 	u8 pin;
@@ -1110,12 +1112,12 @@ static struct dmi_system_id __initdata pciirq_dmi_table[] = {
 	{ }
 };
 
-int __init pcibios_irq_init(void)
+void __init pcibios_irq_init(void)
 {
 	DBG(KERN_DEBUG "PCI: IRQ init\n");
 
-	if (pcibios_enable_irq || raw_pci_ops == NULL)
-		return 0;
+	if (raw_pci_ops == NULL)
+		return;
 
 	dmi_check_system(pciirq_dmi_table);
 
@@ -1142,9 +1144,7 @@ int __init pcibios_irq_init(void)
 			pirq_table = NULL;
 	}
 
-	pcibios_enable_irq = pirq_enable_irq;
-
-	pcibios_fixup_irqs();
+	x86_init.pci.fixup_irqs();
 
 	if (io_apic_assign_pci_irqs && pci_routeirq) {
 		struct pci_dev *dev = NULL;
@@ -1157,8 +1157,6 @@ int __init pcibios_irq_init(void)
 		for_each_pci_dev(dev)
 			pirq_enable_irq(dev);
 	}
-
-	return 0;
 }
 
 static void pirq_penalize_isa_irq(int irq, int active)
diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c
index 4061bb0f267..0db5eaf5456 100644
--- a/arch/x86/pci/legacy.c
+++ b/arch/x86/pci/legacy.c
@@ -35,16 +35,13 @@ static void __devinit pcibios_fixup_peer_bridges(void)
 	}
 }
 
-static int __init pci_legacy_init(void)
+int __init pci_legacy_init(void)
 {
 	if (!raw_pci_ops) {
 		printk("PCI: System does not support PCI\n");
 		return 0;
 	}
 
-	if (pcibios_scanned++)
-		return 0;
-
 	printk("PCI: Probing PCI hardware\n");
 	pci_root_bus = pcibios_scan_root(0);
 	if (pci_root_bus)
@@ -55,18 +52,15 @@ static int __init pci_legacy_init(void)
 
 int __init pci_subsys_init(void)
 {
-#ifdef CONFIG_X86_NUMAQ
-	pci_numaq_init();
-#endif
-#ifdef CONFIG_ACPI
-	pci_acpi_init();
-#endif
-#ifdef CONFIG_X86_VISWS
-	pci_visws_init();
-#endif
-	pci_legacy_init();
+	/*
+	 * The init function returns an non zero value when
+	 * pci_legacy_init should be invoked.
+	 */
+	if (x86_init.pci.init())
+		pci_legacy_init();
+
 	pcibios_fixup_peer_bridges();
-	pcibios_irq_init();
+	x86_init.pci.init_irq();
 	pcibios_init();
 
 	return 0;
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index b19d1e54201..8f3f9a50b1e 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -303,22 +303,17 @@ static void __init pci_mmcfg_check_end_bus_number(void)
 {
 	struct pci_mmcfg_region *cfg, *cfgx;
 
-	/* last one*/
-	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 */
+	/* Fixup overlaps */
 	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
 		if (cfg->end_bus < cfg->start_bus)
 			cfg->end_bus = 255;
 
+		/* Don't access the list head ! */
+		if (cfg->list.next == &pci_mmcfg_list)
+			break;
+
 		cfgx = list_entry(cfg->list.next, typeof(*cfg), list);
-		if (cfg != cfgx && cfg->end_bus >= cfgx->start_bus)
+		if (cfg->end_bus >= cfgx->start_bus)
 			cfg->end_bus = cfgx->start_bus - 1;
 	}
 }
diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c
new file mode 100644
index 00000000000..8bf2fcb88d0
--- /dev/null
+++ b/arch/x86/pci/mrst.c
@@ -0,0 +1,262 @@
+/*
+ * Moorestown PCI support
+ *   Copyright (c) 2008 Intel Corporation
+ *     Jesse Barnes <jesse.barnes@intel.com>
+ *
+ * Moorestown has an interesting PCI implementation:
+ *   - configuration space is memory mapped (as defined by MCFG)
+ *   - Lincroft devices also have a real, type 1 configuration space
+ *   - Early Lincroft silicon has a type 1 access bug that will cause
+ *     a hang if non-existent devices are accessed
+ *   - some devices have the "fixed BAR" capability, which means
+ *     they can't be relocated or modified; check for that during
+ *     BAR sizing
+ *
+ * So, we use the MCFG space for all reads and writes, but also send
+ * Lincroft writes to type 1 space.  But only read/write if the device
+ * actually exists, otherwise return all 1s for reads and bit bucket
+ * the writes.
+ */
+
+#include <linux/sched.h>
+#include <linux/pci.h>
+#include <linux/ioport.h>
+#include <linux/init.h>
+#include <linux/dmi.h>
+
+#include <asm/acpi.h>
+#include <asm/segment.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/pci_x86.h>
+#include <asm/hw_irq.h>
+#include <asm/io_apic.h>
+
+#define PCIE_CAP_OFFSET	0x100
+
+/* Fixed BAR fields */
+#define PCIE_VNDR_CAP_ID_FIXED_BAR 0x00	/* Fixed BAR (TBD) */
+#define PCI_FIXED_BAR_0_SIZE	0x04
+#define PCI_FIXED_BAR_1_SIZE	0x08
+#define PCI_FIXED_BAR_2_SIZE	0x0c
+#define PCI_FIXED_BAR_3_SIZE	0x10
+#define PCI_FIXED_BAR_4_SIZE	0x14
+#define PCI_FIXED_BAR_5_SIZE	0x1c
+
+/**
+ * fixed_bar_cap - return the offset of the fixed BAR cap if found
+ * @bus: PCI bus
+ * @devfn: device in question
+ *
+ * Look for the fixed BAR cap on @bus and @devfn, returning its offset
+ * if found or 0 otherwise.
+ */
+static int fixed_bar_cap(struct pci_bus *bus, unsigned int devfn)
+{
+	int pos;
+	u32 pcie_cap = 0, cap_data;
+
+	pos = PCIE_CAP_OFFSET;
+
+	if (!raw_pci_ext_ops)
+		return 0;
+
+	while (pos) {
+		if (raw_pci_ext_ops->read(pci_domain_nr(bus), bus->number,
+					  devfn, pos, 4, &pcie_cap))
+			return 0;
+
+		if (pcie_cap == 0xffffffff)
+			return 0;
+
+		if (PCI_EXT_CAP_ID(pcie_cap) == PCI_EXT_CAP_ID_VNDR) {
+			raw_pci_ext_ops->read(pci_domain_nr(bus), bus->number,
+					      devfn, pos + 4, 4, &cap_data);
+			if ((cap_data & 0xffff) == PCIE_VNDR_CAP_ID_FIXED_BAR)
+				return pos;
+		}
+
+		pos = pcie_cap >> 20;
+	}
+
+	return 0;
+}
+
+static int pci_device_update_fixed(struct pci_bus *bus, unsigned int devfn,
+				   int reg, int len, u32 val, int offset)
+{
+	u32 size;
+	unsigned int domain, busnum;
+	int bar = (reg - PCI_BASE_ADDRESS_0) >> 2;
+
+	domain = pci_domain_nr(bus);
+	busnum = bus->number;
+
+	if (val == ~0 && len == 4) {
+		unsigned long decode;
+
+		raw_pci_ext_ops->read(domain, busnum, devfn,
+			       offset + 8 + (bar * 4), 4, &size);
+
+		/* Turn the size into a decode pattern for the sizing code */
+		if (size) {
+			decode = size - 1;
+			decode |= decode >> 1;
+			decode |= decode >> 2;
+			decode |= decode >> 4;
+			decode |= decode >> 8;
+			decode |= decode >> 16;
+			decode++;
+			decode = ~(decode - 1);
+		} else {
+			decode = ~0;
+		}
+
+		/*
+		 * If val is all ones, the core code is trying to size the reg,
+		 * so update the mmconfig space with the real size.
+		 *
+		 * Note: this assumes the fixed size we got is a power of two.
+		 */
+		return raw_pci_ext_ops->write(domain, busnum, devfn, reg, 4,
+				       decode);
+	}
+
+	/* This is some other kind of BAR write, so just do it. */
+	return raw_pci_ext_ops->write(domain, busnum, devfn, reg, len, val);
+}
+
+/**
+ * type1_access_ok - check whether to use type 1
+ * @bus: bus number
+ * @devfn: device & function in question
+ *
+ * If the bus is on a Lincroft chip and it exists, or is not on a Lincroft at
+ * all, the we can go ahead with any reads & writes.  If it's on a Lincroft,
+ * but doesn't exist, avoid the access altogether to keep the chip from
+ * hanging.
+ */
+static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg)
+{
+	/* This is a workaround for A0 LNC bug where PCI status register does
+	 * not have new CAP bit set. can not be written by SW either.
+	 *
+	 * PCI header type in real LNC indicates a single function device, this
+	 * will prevent probing other devices under the same function in PCI
+	 * shim. Therefore, use the header type in shim instead.
+	 */
+	if (reg >= 0x100 || reg == PCI_STATUS || reg == PCI_HEADER_TYPE)
+		return 0;
+	if (bus == 0 && (devfn == PCI_DEVFN(2, 0) || devfn == PCI_DEVFN(0, 0)))
+		return 1;
+	return 0; /* langwell on others */
+}
+
+static int pci_read(struct pci_bus *bus, unsigned int devfn, int where,
+		    int size, u32 *value)
+{
+	if (type1_access_ok(bus->number, devfn, where))
+		return pci_direct_conf1.read(pci_domain_nr(bus), bus->number,
+					devfn, where, size, value);
+	return raw_pci_ext_ops->read(pci_domain_nr(bus), bus->number,
+			      devfn, where, size, value);
+}
+
+static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
+		     int size, u32 value)
+{
+	int offset;
+
+	/* On MRST, there is no PCI ROM BAR, this will cause a subsequent read
+	 * to ROM BAR return 0 then being ignored.
+	 */
+	if (where == PCI_ROM_ADDRESS)
+		return 0;
+
+	/*
+	 * Devices with fixed BARs need special handling:
+	 *   - BAR sizing code will save, write ~0, read size, restore
+	 *   - so writes to fixed BARs need special handling
+	 *   - other writes to fixed BAR devices should go through mmconfig
+	 */
+	offset = fixed_bar_cap(bus, devfn);
+	if (offset &&
+	    (where >= PCI_BASE_ADDRESS_0 && where <= PCI_BASE_ADDRESS_5)) {
+		return pci_device_update_fixed(bus, devfn, where, size, value,
+					       offset);
+	}
+
+	/*
+	 * On Moorestown update both real & mmconfig space
+	 * Note: early Lincroft silicon can't handle type 1 accesses to
+	 *       non-existent devices, so just eat the write in that case.
+	 */
+	if (type1_access_ok(bus->number, devfn, where))
+		return pci_direct_conf1.write(pci_domain_nr(bus), bus->number,
+					      devfn, where, size, value);
+	return raw_pci_ext_ops->write(pci_domain_nr(bus), bus->number, devfn,
+			       where, size, value);
+}
+
+static int mrst_pci_irq_enable(struct pci_dev *dev)
+{
+	u8 pin;
+	struct io_apic_irq_attr irq_attr;
+
+	pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+
+	/* MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to
+	 * IOAPIC RTE entries, so we just enable RTE for the device.
+	 */
+	irq_attr.ioapic = mp_find_ioapic(dev->irq);
+	irq_attr.ioapic_pin = dev->irq;
+	irq_attr.trigger = 1; /* level */
+	irq_attr.polarity = 1; /* active low */
+	io_apic_set_pci_routing(&dev->dev, dev->irq, &irq_attr);
+
+	return 0;
+}
+
+struct pci_ops pci_mrst_ops = {
+	.read = pci_read,
+	.write = pci_write,
+};
+
+/**
+ * pci_mrst_init - installs pci_mrst_ops
+ *
+ * Moorestown has an interesting PCI implementation (see above).
+ * Called when the early platform detection installs it.
+ */
+int __init pci_mrst_init(void)
+{
+	printk(KERN_INFO "Moorestown platform detected, using MRST PCI ops\n");
+	pci_mmcfg_late_init();
+	pcibios_enable_irq = mrst_pci_irq_enable;
+	pci_root_ops = pci_mrst_ops;
+	/* Continue with standard init */
+	return 1;
+}
+
+/*
+ * Langwell devices reside at fixed offsets, don't try to move them.
+ */
+static void __devinit pci_fixed_bar_fixup(struct pci_dev *dev)
+{
+	unsigned long offset;
+	u32 size;
+	int i;
+
+	/* Fixup the BAR sizes for fixed BAR devices and make them unmoveable */
+	offset = fixed_bar_cap(dev->bus, dev->devfn);
+	if (!offset || PCI_DEVFN(2, 0) == dev->devfn ||
+	    PCI_DEVFN(2, 2) == dev->devfn)
+		return;
+
+	for (i = 0; i < PCI_ROM_RESOURCE; i++) {
+		pci_read_config_dword(dev, offset + 8 + (i * 4), &size);
+		dev->resource[i].end = dev->resource[i].start + size - 1;
+		dev->resource[i].flags |= IORESOURCE_PCI_FIXED;
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_fixed_bar_fixup);
diff --git a/arch/x86/pci/numaq_32.c b/arch/x86/pci/numaq_32.c
index 8eb295e116f..8223738ad80 100644
--- a/arch/x86/pci/numaq_32.c
+++ b/arch/x86/pci/numaq_32.c
@@ -8,9 +8,7 @@
 #include <asm/apic.h>
 #include <asm/mpspec.h>
 #include <asm/pci_x86.h>
-
-#define XQUAD_PORTIO_BASE 0xfe400000
-#define XQUAD_PORTIO_QUAD 0x40000  /* 256k per quad. */
+#include <asm/numaq.h>
 
 #define BUS2QUAD(global) (mp_bus_id_to_node[global])
 
@@ -18,8 +16,6 @@
 
 #define QUADLOCAL2BUS(quad,local) (quad_local_to_mp_bus_id[quad][local])
 
-#define XQUAD_PORT_ADDR(port, quad) (xquad_portio + (XQUAD_PORTIO_QUAD*quad) + port)
-
 #define PCI_CONF1_MQ_ADDRESS(bus, devfn, reg) \
 	(0x80000000 | (BUS2LOCAL(bus) << 16) | (devfn << 8) | (reg & ~3))
 
@@ -152,14 +148,8 @@ int __init pci_numaq_init(void)
 {
 	int quad;
 
-	if (!found_numaq)
-		return 0;
-
 	raw_pci_ops = &pci_direct_conf1_mq;
 
-	if (pcibios_scanned++)
-		return 0;
-
 	pci_root_bus = pcibios_scan_root(0);
 	if (pci_root_bus)
 		pci_bus_add_devices(pci_root_bus);
diff --git a/arch/x86/pci/olpc.c b/arch/x86/pci/olpc.c
index b889d824f7c..b34815408f5 100644
--- a/arch/x86/pci/olpc.c
+++ b/arch/x86/pci/olpc.c
@@ -304,9 +304,6 @@ static struct pci_raw_ops pci_olpc_conf = {
 
 int __init pci_olpc_init(void)
 {
-	if (!machine_is_olpc() || olpc_has_vsa())
-		return -ENODEV;
-
 	printk(KERN_INFO "PCI: Using configuration type OLPC\n");
 	raw_pci_ops = &pci_olpc_conf;
 	is_lx = is_geode_lx();
diff --git a/arch/x86/pci/visws.c b/arch/x86/pci/visws.c
index bcead7a4687..03008f72eb0 100644
--- a/arch/x86/pci/visws.c
+++ b/arch/x86/pci/visws.c
@@ -69,9 +69,6 @@ void __init pcibios_update_irq(struct pci_dev *dev, int irq)
 
 int __init pci_visws_init(void)
 {
-	if (!is_visws_box())
-		return -1;
-
 	pcibios_enable_irq = &pci_visws_enable_irq;
 	pcibios_disable_irq = &pci_visws_disable_irq;
 
@@ -90,5 +87,6 @@ int __init pci_visws_init(void)
 	pci_scan_bus_with_sysdata(pci_bus1);
 	pci_fixup_irqs(pci_common_swizzle, visws_map_irq);
 	pcibios_resource_survey();
-	return 0;
+	/* Request bus scan */
+	return 1;
 }