Merge tag 'for-3.6' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci

Pull PCI changes from Bjorn Helgaas:
 "Host bridge hotplug:
    - Add MMCONFIG support for hot-added host bridges (Jiang Liu)
  Device hotplug:
    - Move fixups from __init to __devinit (Sebastian Andrzej Siewior)
    - Call FINAL fixups for hot-added devices, too (Myron Stowe)
    - Factor out generic code for P2P bridge hot-add (Yinghai Lu)
    - Remove all functions in a slot, not just those with _EJx (Amos
      Kong)
  Dynamic resource management:
    - Track bus number allocation (struct resource tree per domain)
      (Yinghai Lu)
    - Make P2P bridge 1K I/O windows work with resource reassignment
      (Bjorn Helgaas, Yinghai Lu)
    - Disable decoding while updating 64-bit BARs (Bjorn Helgaas)
  Power management:
    - Add PCIe runtime D3cold support (Huang Ying)
  Virtualization:
    - Add VFIO infrastructure (ACS, DMA source ID quirks) (Alex
      Williamson)
    - Add quirks for devices with broken INTx masking (Jan Kiszka)
  Miscellaneous:
    - Fix some PCI Express capability version issues (Myron Stowe)
    - Factor out some arch code with a weak, generic, pcibios_setup()
      (Myron Stowe)"

* tag 'for-3.6' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (122 commits)
  PCI: hotplug: ensure a consistent return value in error case
  PCI: fix undefined reference to 'pci_fixup_final_inited'
  PCI: build resource code for M68K architecture
  PCI: pciehp: remove unused pciehp_get_max_lnk_width(), pciehp_get_cur_lnk_width()
  PCI: reorder __pci_assign_resource() (no change)
  PCI: fix truncation of resource size to 32 bits
  PCI: acpiphp: merge acpiphp_debug and debug
  PCI: acpiphp: remove unused res_lock
  sparc/PCI: replace pci_cfg_fake_ranges() with pci_read_bridge_bases()
  PCI: call final fixups hot-added devices
  PCI: move final fixups from __init to __devinit
  x86/PCI: move final fixups from __init to __devinit
  MIPS/PCI: move final fixups from __init to __devinit
  PCI: support sizing P2P bridge I/O windows with 1K granularity
  PCI: reimplement P2P bridge 1K I/O windows (Intel P64H2)
  PCI: disable MEM decoding while updating 64-bit MEM BARs
  PCI: leave MEM and IO decoding disabled during 64-bit BAR sizing, too
  PCI: never discard enable/suspend/resume_early/resume fixups
  PCI: release temporary reference in __nv_msi_ht_cap_quirk()
  PCI: restructure 'pci_do_fixups()'
  ...

11 files changed, 440 insertions, 168 deletions

diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index 5ad24a89b19b..73e8eeff22ee 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -104,6 +104,7 @@ struct pci_raw_ops {
 extern const struct pci_raw_ops *raw_pci_ops;
 extern const struct pci_raw_ops *raw_pci_ext_ops;
 
+extern const struct pci_raw_ops pci_mmcfg;
 extern const struct pci_raw_ops pci_direct_conf1;
 extern bool port_cf9_safe;
 
@@ -139,6 +140,12 @@ struct pci_mmcfg_region {
 
 extern int __init pci_mmcfg_arch_init(void);
 extern void __init pci_mmcfg_arch_free(void);
+extern int __devinit pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg);
+extern void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg);
+extern int __devinit pci_mmconfig_insert(struct device *dev,
+					 u16 seg, u8 start,
+					 u8 end, phys_addr_t addr);
+extern int pci_mmconfig_delete(u16 seg, u8 start, u8 end);
 extern struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus);
 
 extern struct list_head pci_mmcfg_list;
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 03920a15a632..1b27de563561 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -512,7 +512,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
 
 #if defined(CONFIG_PCI) && defined(CONFIG_NUMA)
 /* Set correct numa_node information for AMD NB functions */
-static void __init quirk_amd_nb_node(struct pci_dev *dev)
+static void __devinit quirk_amd_nb_node(struct pci_dev *dev)
 {
 	struct pci_dev *nb_ht;
 	unsigned int devfn;
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index fc09c2754e08..505acdd6d600 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -12,8 +12,13 @@ struct pci_root_info {
 	char name[16];
 	unsigned int res_num;
 	struct resource *res;
-	int busnum;
 	struct pci_sysdata sd;
+#ifdef	CONFIG_PCI_MMCONFIG
+	bool mcfg_added;
+	u16 segment;
+	u8 start_bus;
+	u8 end_bus;
+#endif
 };
 
 static bool pci_use_crs = true;
@@ -120,6 +125,81 @@ void __init pci_acpi_crs_quirks(void)
 	       pci_use_crs ? "nocrs" : "use_crs");
 }
 
+#ifdef	CONFIG_PCI_MMCONFIG
+static int __devinit check_segment(u16 seg, struct device *dev, char *estr)
+{
+	if (seg) {
+		dev_err(dev,
+			"%s can't access PCI configuration "
+			"space under this host bridge.\n",
+			estr);
+		return -EIO;
+	}
+
+	/*
+	 * Failure in adding MMCFG information is not fatal,
+	 * just can't access extended configuration space of
+	 * devices under this host bridge.
+	 */
+	dev_warn(dev,
+		 "%s can't access extended PCI configuration "
+		 "space under this bridge.\n",
+		 estr);
+
+	return 0;
+}
+
+static int __devinit setup_mcfg_map(struct pci_root_info *info,
+				    u16 seg, u8 start, u8 end,
+				    phys_addr_t addr)
+{
+	int result;
+	struct device *dev = &info->bridge->dev;
+
+	info->start_bus = start;
+	info->end_bus = end;
+	info->mcfg_added = false;
+
+	/* return success if MMCFG is not in use */
+	if (raw_pci_ext_ops && raw_pci_ext_ops != &pci_mmcfg)
+		return 0;
+
+	if (!(pci_probe & PCI_PROBE_MMCONF))
+		return check_segment(seg, dev, "MMCONFIG is disabled,");
+
+	result = pci_mmconfig_insert(dev, seg, start, end, addr);
+	if (result == 0) {
+		/* enable MMCFG if it hasn't been enabled yet */
+		if (raw_pci_ext_ops == NULL)
+			raw_pci_ext_ops = &pci_mmcfg;
+		info->mcfg_added = true;
+	} else if (result != -EEXIST)
+		return check_segment(seg, dev,
+			 "fail to add MMCONFIG information,");
+
+	return 0;
+}
+
+static void teardown_mcfg_map(struct pci_root_info *info)
+{
+	if (info->mcfg_added) {
+		pci_mmconfig_delete(info->segment, info->start_bus,
+				    info->end_bus);
+		info->mcfg_added = false;
+	}
+}
+#else
+static int __devinit setup_mcfg_map(struct pci_root_info *info,
+				    u16 seg, u8 start, u8 end,
+				    phys_addr_t addr)
+{
+	return 0;
+}
+static void teardown_mcfg_map(struct pci_root_info *info)
+{
+}
+#endif
+
 static acpi_status
 resource_to_addr(struct acpi_resource *resource,
 			struct acpi_resource_address64 *addr)
@@ -234,13 +314,6 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	}
 
 	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;
 }
@@ -332,8 +405,11 @@ static void __release_pci_root_info(struct pci_root_info *info)
 
 	free_pci_root_info_res(info);
 
+	teardown_mcfg_map(info);
+
 	kfree(info);
 }
+
 static void release_pci_root_info(struct pci_host_bridge *bridge)
 {
 	struct pci_root_info *info = bridge->release_data;
@@ -347,7 +423,9 @@ probe_pci_root_info(struct pci_root_info *info, struct acpi_device *device,
 {
 	size_t size;
 
+	sprintf(info->name, "PCI Bus %04x:%02x", domain, busnum);
 	info->bridge = device;
+
 	info->res_num = 0;
 	acpi_walk_resources(device->handle, METHOD_NAME__CRS, count_resource,
 				info);
@@ -360,8 +438,6 @@ probe_pci_root_info(struct pci_root_info *info, struct acpi_device *device,
 	if (!info->res)
 		return;
 
-	sprintf(info->name, "PCI Bus %04x:%02x", domain, busnum);
-
 	acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource,
 				info);
 }
@@ -373,7 +449,7 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
 	int domain = root->segment;
 	int busnum = root->secondary.start;
 	LIST_HEAD(resources);
-	struct pci_bus *bus;
+	struct pci_bus *bus = NULL;
 	struct pci_sysdata *sd;
 	int node;
 #ifdef CONFIG_ACPI_NUMA
@@ -426,6 +502,8 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
 	} else {
 		probe_pci_root_info(info, device, busnum, domain);
 
+		/* insert busn res at first */
+		pci_add_resource(&resources,  &root->secondary);
 		/*
 		 * _CRS with no apertures is normal, so only fall back to
 		 * defaults or native bridge info if we're ignoring _CRS.
@@ -437,10 +515,13 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
 			x86_pci_root_bus_resources(busnum, &resources);
 		}
 
-		bus = pci_create_root_bus(NULL, busnum, &pci_root_ops, sd,
-					  &resources);
+		if (!setup_mcfg_map(info, domain, (u8)root->secondary.start,
+				    (u8)root->secondary.end, root->mcfg_addr))
+			bus = pci_create_root_bus(NULL, busnum, &pci_root_ops,
+						  sd, &resources);
+
 		if (bus) {
-			bus->subordinate = pci_scan_child_bus(bus);
+			pci_scan_child_bus(bus);
 			pci_set_host_bridge_release(
 				to_pci_host_bridge(bus->bridge),
 				release_pci_root_info, info);
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 5aed49bff058..e9e6ed5cdf94 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -121,7 +121,6 @@ static int __init early_fill_mp_bus_info(void)
 		link = (reg >> 8) & 0x03;
 
 		info = alloc_pci_root_info(min_bus, max_bus, node, link);
-		sprintf(info->name, "PCI Bus #%02x", min_bus);
 	}
 
 	/* get the default node and link for left over res */
@@ -300,9 +299,9 @@ static int __init early_fill_mp_bus_info(void)
 		int busnum;
 		struct pci_root_res *root_res;
 
-		busnum = info->bus_min;
-		printk(KERN_DEBUG "bus: [%02x, %02x] on node %x link %x\n",
-		       info->bus_min, info->bus_max, info->node, info->link);
+		busnum = info->busn.start;
+		printk(KERN_DEBUG "bus: %pR on node %x link %x\n",
+		       &info->busn, info->node, info->link);
 		list_for_each_entry(root_res, &info->resources, list)
 			printk(KERN_DEBUG "bus: %02x %pR\n",
 				       busnum, &root_res->res);
diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c
index 306579f7d0fd..d37e2fec97e5 100644
--- a/arch/x86/pci/bus_numa.c
+++ b/arch/x86/pci/bus_numa.c
@@ -14,7 +14,7 @@ static struct pci_root_info *x86_find_pci_root_info(int bus)
 		return NULL;
 
 	list_for_each_entry(info, &pci_root_infos, list)
-		if (info->bus_min == bus)
+		if (info->busn.start == bus)
 			return info;
 
 	return NULL;
@@ -24,6 +24,8 @@ void x86_pci_root_bus_resources(int bus, struct list_head *resources)
 {
 	struct pci_root_info *info = x86_find_pci_root_info(bus);
 	struct pci_root_res *root_res;
+	struct pci_host_bridge_window *window;
+	bool found = false;
 
 	if (!info)
 		goto default_resources;
@@ -31,6 +33,16 @@ void x86_pci_root_bus_resources(int bus, struct list_head *resources)
 	printk(KERN_DEBUG "PCI: root bus %02x: hardware-probed resources\n",
 	       bus);
 
+	/* already added by acpi ? */
+	list_for_each_entry(window, resources, list)
+		if (window->res->flags & IORESOURCE_BUS) {
+			found = true;
+			break;
+		}
+
+	if (!found)
+		pci_add_resource(resources, &info->busn);
+
 	list_for_each_entry(root_res, &info->resources, list) {
 		struct resource *res;
 		struct resource *root;
@@ -66,9 +78,13 @@ struct pci_root_info __init *alloc_pci_root_info(int bus_min, int bus_max,
 	if (!info)
 		return info;
 
+	sprintf(info->name, "PCI Bus #%02x", bus_min);
+
 	INIT_LIST_HEAD(&info->resources);
-	info->bus_min = bus_min;
-	info->bus_max = bus_max;
+	info->busn.name  = info->name;
+	info->busn.start = bus_min;
+	info->busn.end   = bus_max;
+	info->busn.flags = IORESOURCE_BUS;
 	info->node = node;
 	info->link = link;
 
diff --git a/arch/x86/pci/bus_numa.h b/arch/x86/pci/bus_numa.h
index 226a466b2b2b..ff8f65b04574 100644
--- a/arch/x86/pci/bus_numa.h
+++ b/arch/x86/pci/bus_numa.h
@@ -13,8 +13,7 @@ struct pci_root_info {
 	struct list_head list;
 	char name[12];
 	struct list_head resources;
-	int bus_min;
-	int bus_max;
+	struct resource busn;
 	int node;
 	int link;
 };
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 0ad990a20d4a..720e973fc34a 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -494,7 +494,7 @@ int __init pcibios_init(void)
 	return 0;
 }
 
-char * __devinit  pcibios_setup(char *str)
+char * __init pcibios_setup(char *str)
 {
 	if (!strcmp(str, "off")) {
 		pci_probe = 0;
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 301e325992f6..937bcece7006 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -17,6 +17,8 @@
 #include <linux/bitmap.h>
 #include <linux/dmi.h>
 #include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/rculist.h>
 #include <asm/e820.h>
 #include <asm/pci_x86.h>
 #include <asm/acpi.h>
@@ -24,7 +26,9 @@
 #define PREFIX "PCI: "
 
 /* Indicate if the mmcfg resources have been placed into the resource table. */
-static int __initdata pci_mmcfg_resources_inserted;
+static bool pci_mmcfg_running_state;
+static bool pci_mmcfg_arch_init_failed;
+static DEFINE_MUTEX(pci_mmcfg_lock);
 
 LIST_HEAD(pci_mmcfg_list);
 
@@ -45,24 +49,25 @@ static __init void free_all_mmcfg(void)
 		pci_mmconfig_remove(cfg);
 }
 
-static __init void list_add_sorted(struct pci_mmcfg_region *new)
+static __devinit 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) {
+	list_for_each_entry_rcu(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);
+			list_add_tail_rcu(&new->list, &cfg->list);
 			return;
 		}
 	}
-	list_add_tail(&new->list, &pci_mmcfg_list);
+	list_add_tail_rcu(&new->list, &pci_mmcfg_list);
 }
 
-static __init struct pci_mmcfg_region *pci_mmconfig_add(int segment, int start,
-							int end, u64 addr)
+static __devinit struct pci_mmcfg_region *pci_mmconfig_alloc(int segment,
+							     int start,
+							     int end, u64 addr)
 {
 	struct pci_mmcfg_region *new;
 	struct resource *res;
@@ -79,8 +84,6 @@ static __init struct pci_mmcfg_region *pci_mmconfig_add(int segment, int start,
 	new->start_bus = start;
 	new->end_bus = end;
 
-	list_add_sorted(new);
-
 	res = &new->res;
 	res->start = addr + PCI_MMCFG_BUS_OFFSET(start);
 	res->end = addr + PCI_MMCFG_BUS_OFFSET(end + 1) - 1;
@@ -89,9 +92,25 @@ static __init struct pci_mmcfg_region *pci_mmconfig_add(int segment, int start,
 		 "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;
+}
+
+static __init struct pci_mmcfg_region *pci_mmconfig_add(int segment, int start,
+							int end, u64 addr)
+{
+	struct pci_mmcfg_region *new;
+
+	new = pci_mmconfig_alloc(segment, start, end, addr);
+	if (new) {
+		mutex_lock(&pci_mmcfg_lock);
+		list_add_sorted(new);
+		mutex_unlock(&pci_mmcfg_lock);
+
+		pr_info(PREFIX
+		       "MMCONFIG for domain %04x [bus %02x-%02x] at %pR "
+		       "(base %#lx)\n",
+		       segment, start, end, &new->res, (unsigned long)addr);
+	}
 
 	return new;
 }
@@ -100,7 +119,7 @@ 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)
+	list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list)
 		if (cfg->segment == segment &&
 		    cfg->start_bus <= bus && bus <= cfg->end_bus)
 			return cfg;
@@ -343,8 +362,7 @@ static int __init pci_mmcfg_check_hostbridge(void)
 			name = pci_mmcfg_probes[i].probe();
 
 		if (name)
-			printk(KERN_INFO PREFIX "%s with MMCONFIG support\n",
-			       name);
+			pr_info(PREFIX "%s with MMCONFIG support\n", name);
 	}
 
 	/* some end_bus_number is crazy, fix it */
@@ -353,19 +371,8 @@ static int __init pci_mmcfg_check_hostbridge(void)
 	return !list_empty(&pci_mmcfg_list);
 }
 
-static void __init pci_mmcfg_insert_resources(void)
-{
-	struct pci_mmcfg_region *cfg;
-
-	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;
-}
-
-static acpi_status __init check_mcfg_resource(struct acpi_resource *res,
-					      void *data)
+static acpi_status __devinit check_mcfg_resource(struct acpi_resource *res,
+						 void *data)
 {
 	struct resource *mcfg_res = data;
 	struct acpi_resource_address64 address;
@@ -401,8 +408,8 @@ static acpi_status __init check_mcfg_resource(struct acpi_resource *res,
 	return AE_OK;
 }
 
-static acpi_status __init find_mboard_resource(acpi_handle handle, u32 lvl,
-		void *context, void **rv)
+static acpi_status __devinit find_mboard_resource(acpi_handle handle, u32 lvl,
+						  void *context, void **rv)
 {
 	struct resource *mcfg_res = context;
 
@@ -415,7 +422,7 @@ static acpi_status __init find_mboard_resource(acpi_handle handle, u32 lvl,
 	return AE_OK;
 }
 
-static int __init is_acpi_reserved(u64 start, u64 end, unsigned not_used)
+static int __devinit is_acpi_reserved(u64 start, u64 end, unsigned not_used)
 {
 	struct resource mcfg_res;
 
@@ -434,13 +441,15 @@ static int __init is_acpi_reserved(u64 start, u64 end, unsigned not_used)
 
 typedef int (*check_reserved_t)(u64 start, u64 end, unsigned type);
 
-static int __init is_mmconf_reserved(check_reserved_t is_reserved,
-				    struct pci_mmcfg_region *cfg, int with_e820)
+static int __ref is_mmconf_reserved(check_reserved_t is_reserved,
+				    struct pci_mmcfg_region *cfg,
+				    struct device *dev, int with_e820)
 {
 	u64 addr = cfg->res.start;
 	u64 size = resource_size(&cfg->res);
 	u64 old_size = size;
-	int valid = 0, num_buses;
+	int num_buses;
+	char *method = with_e820 ? "E820" : "ACPI motherboard resources";
 
 	while (!is_reserved(addr, addr + size, E820_RESERVED)) {
 		size >>= 1;
@@ -448,30 +457,76 @@ static int __init is_mmconf_reserved(check_reserved_t is_reserved,
 			break;
 	}
 
-	if (size >= (16UL<<20) || size == old_size) {
-		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 */
-			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);
-		}
+	if (size < (16UL<<20) && size != old_size)
+		return 0;
+
+	if (dev)
+		dev_info(dev, "MMCONFIG at %pR reserved in %s\n",
+			 &cfg->res, method);
+	else
+		pr_info(PREFIX "MMCONFIG at %pR reserved in %s\n",
+		       &cfg->res, method);
+
+	if (old_size != size) {
+		/* 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);
+
+		if (dev)
+			dev_info(dev,
+				"MMCONFIG "
+				"at %pR (base %#lx) (size reduced!)\n",
+				&cfg->res, (unsigned long) cfg->address);
+		else
+			pr_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);
 	}
 
-	return valid;
+	return 1;
+}
+
+static int __ref pci_mmcfg_check_reserved(struct device *dev,
+		  struct pci_mmcfg_region *cfg, int early)
+{
+	if (!early && !acpi_disabled) {
+		if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, 0))
+			return 1;
+
+		if (dev)
+			dev_info(dev, FW_INFO
+				 "MMCONFIG at %pR not reserved in "
+				 "ACPI motherboard resources\n",
+				 &cfg->res);
+		else
+			pr_info(FW_INFO PREFIX
+			       "MMCONFIG at %pR not reserved in "
+			       "ACPI motherboard resources\n",
+			       &cfg->res);
+	}
+
+	/*
+	 * e820_all_mapped() is marked as __init.
+	 * All entries from ACPI MCFG table have been checked at boot time.
+	 * For MCFG information constructed from hotpluggable host bridge's
+	 * _CBA method, just assume it's reserved.
+	 */
+	if (pci_mmcfg_running_state)
+		return 1;
+
+	/* Don't try to do this check unless configuration
+	   type 1 is available. how about type 2 ?*/
+	if (raw_pci_ops)
+		return is_mmconf_reserved(e820_all_mapped, cfg, dev, 1);
+
+	return 0;
 }
 
 static void __init pci_mmcfg_reject_broken(int early)
@@ -479,38 +534,14 @@ static void __init pci_mmcfg_reject_broken(int early)
 	struct pci_mmcfg_region *cfg;
 
 	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
-		int valid = 0;
-
-		if (!early && !acpi_disabled) {
-			valid = is_mmconf_reserved(is_acpi_reserved, cfg, 0);
-
-			if (valid)
-				continue;
-			else
-				printk(KERN_ERR FW_BUG PREFIX
-				       "MMCONFIG at %pR not reserved in "
-				       "ACPI motherboard resources\n",
-				       &cfg->res);
+		if (pci_mmcfg_check_reserved(NULL, cfg, early) == 0) {
+			pr_info(PREFIX "not using MMCONFIG\n");
+			free_all_mmcfg();
+			return;
 		}
-
-		/* 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, cfg, 1);
-
-		if (!valid)
-			goto reject;
 	}
-
-	return;
-
-reject:
-	printk(KERN_INFO PREFIX "not using MMCONFIG\n");
-	free_all_mmcfg();
 }
 
-static int __initdata known_bridge;
-
 static int __init acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg,
 					struct acpi_mcfg_allocation *cfg)
 {
@@ -529,7 +560,7 @@ static int __init acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg,
 			return 0;
 	}
 
-	printk(KERN_ERR PREFIX "MCFG region for %04x [bus %02x-%02x] at %#llx "
+	pr_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;
@@ -556,7 +587,7 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header)
 		i -= sizeof(struct acpi_mcfg_allocation);
 	};
 	if (entries == 0) {
-		printk(KERN_ERR PREFIX "MMCONFIG has no entries\n");
+		pr_err(PREFIX "MMCONFIG has no entries\n");
 		return -ENODEV;
 	}
 
@@ -570,8 +601,7 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header)
 
 		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");
+			pr_warn(PREFIX "no memory for MCFG entries\n");
 			free_all_mmcfg();
 			return -ENOMEM;
 		}
@@ -582,28 +612,7 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header)
 
 static void __init __pci_mmcfg_init(int early)
 {
-	/* MMCONFIG disabled */
-	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
-		return;
-
-	/* MMCONFIG already enabled */
-	if (!early && !(pci_probe & PCI_PROBE_MASK & ~PCI_PROBE_MMCONF))
-		return;
-
-	/* for late to exit */
-	if (known_bridge)
-		return;
-
-	if (early) {
-		if (pci_mmcfg_check_hostbridge())
-			known_bridge = 1;
-	}
-
-	if (!known_bridge)
-		acpi_sfi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg);
-
 	pci_mmcfg_reject_broken(early);
-
 	if (list_empty(&pci_mmcfg_list))
 		return;
 
@@ -620,33 +629,48 @@ static void __init __pci_mmcfg_init(int early)
 	if (pci_mmcfg_arch_init())
 		pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF;
 	else {
-		/*
-		 * Signal not to attempt to insert mmcfg resources because
-		 * the architecture mmcfg setup could not initialize.
-		 */
-		pci_mmcfg_resources_inserted = 1;
+		free_all_mmcfg();
+		pci_mmcfg_arch_init_failed = true;
 	}
 }
 
+static int __initdata known_bridge;
+
 void __init pci_mmcfg_early_init(void)
 {
-	__pci_mmcfg_init(1);
+	if (pci_probe & PCI_PROBE_MMCONF) {
+		if (pci_mmcfg_check_hostbridge())
+			known_bridge = 1;
+		else
+			acpi_sfi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg);
+		__pci_mmcfg_init(1);
+	}
 }
 
 void __init pci_mmcfg_late_init(void)
 {
-	__pci_mmcfg_init(0);
+	/* MMCONFIG disabled */
+	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
+		return;
+
+	if (known_bridge)
+		return;
+
+	/* MMCONFIG hasn't been enabled yet, try again */
+	if (pci_probe & PCI_PROBE_MASK & ~PCI_PROBE_MMCONF) {
+		acpi_sfi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg);
+		__pci_mmcfg_init(0);
+	}
 }
 
 static int __init pci_mmcfg_late_insert_resources(void)
 {
-	/*
-	 * If resources are already inserted or we are not using MMCONFIG,
-	 * don't insert the resources.
-	 */
-	if ((pci_mmcfg_resources_inserted == 1) ||
-	    (pci_probe & PCI_PROBE_MMCONF) == 0 ||
-	    list_empty(&pci_mmcfg_list))
+	struct pci_mmcfg_region *cfg;
+
+	pci_mmcfg_running_state = true;
+
+	/* If we are not using MMCONFIG, don't insert the resources. */
+	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
 		return 1;
 
 	/*
@@ -654,7 +678,9 @@ static int __init pci_mmcfg_late_insert_resources(void)
 	 * marked so it won't cause request errors when __request_region is
 	 * called.
 	 */
-	pci_mmcfg_insert_resources();
+	list_for_each_entry(cfg, &pci_mmcfg_list, list)
+		if (!cfg->res.parent)
+			insert_resource(&iomem_resource, &cfg->res);
 
 	return 0;
 }
@@ -665,3 +691,101 @@ static int __init pci_mmcfg_late_insert_resources(void)
  * with other system resources.
  */
 late_initcall(pci_mmcfg_late_insert_resources);
+
+/* Add MMCFG information for host bridges */
+int __devinit pci_mmconfig_insert(struct device *dev,
+				  u16 seg, u8 start, u8 end,
+				  phys_addr_t addr)
+{
+	int rc;
+	struct resource *tmp = NULL;
+	struct pci_mmcfg_region *cfg;
+
+	if (!(pci_probe & PCI_PROBE_MMCONF) || pci_mmcfg_arch_init_failed)
+		return -ENODEV;
+
+	if (start > end)
+		return -EINVAL;
+
+	mutex_lock(&pci_mmcfg_lock);
+	cfg = pci_mmconfig_lookup(seg, start);
+	if (cfg) {
+		if (cfg->end_bus < end)
+			dev_info(dev, FW_INFO
+				 "MMCONFIG for "
+				 "domain %04x [bus %02x-%02x] "
+				 "only partially covers this bridge\n",
+				  cfg->segment, cfg->start_bus, cfg->end_bus);
+		mutex_unlock(&pci_mmcfg_lock);
+		return -EEXIST;
+	}
+
+	if (!addr) {
+		mutex_unlock(&pci_mmcfg_lock);
+		return -EINVAL;
+	}
+
+	rc = -EBUSY;
+	cfg = pci_mmconfig_alloc(seg, start, end, addr);
+	if (cfg == NULL) {
+		dev_warn(dev, "fail to add MMCONFIG (out of memory)\n");
+		rc = -ENOMEM;
+	} else if (!pci_mmcfg_check_reserved(dev, cfg, 0)) {
+		dev_warn(dev, FW_BUG "MMCONFIG %pR isn't reserved\n",
+			 &cfg->res);
+	} else {
+		/* Insert resource if it's not in boot stage */
+		if (pci_mmcfg_running_state)
+			tmp = insert_resource_conflict(&iomem_resource,
+						       &cfg->res);
+
+		if (tmp) {
+			dev_warn(dev,
+				 "MMCONFIG %pR conflicts with "
+				 "%s %pR\n",
+				 &cfg->res, tmp->name, tmp);
+		} else if (pci_mmcfg_arch_map(cfg)) {
+			dev_warn(dev, "fail to map MMCONFIG %pR.\n",
+				 &cfg->res);
+		} else {
+			list_add_sorted(cfg);
+			dev_info(dev, "MMCONFIG at %pR (base %#lx)\n",
+				 &cfg->res, (unsigned long)addr);
+			cfg = NULL;
+			rc = 0;
+		}
+	}
+
+	if (cfg) {
+		if (cfg->res.parent)
+			release_resource(&cfg->res);
+		kfree(cfg);
+	}
+
+	mutex_unlock(&pci_mmcfg_lock);
+
+	return rc;
+}
+
+/* Delete MMCFG information for host bridges */
+int pci_mmconfig_delete(u16 seg, u8 start, u8 end)
+{
+	struct pci_mmcfg_region *cfg;
+
+	mutex_lock(&pci_mmcfg_lock);
+	list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list)
+		if (cfg->segment == seg && cfg->start_bus == start &&
+		    cfg->end_bus == end) {
+			list_del_rcu(&cfg->list);
+			synchronize_rcu();
+			pci_mmcfg_arch_unmap(cfg);
+			if (cfg->res.parent)
+				release_resource(&cfg->res);
+			mutex_unlock(&pci_mmcfg_lock);
+			kfree(cfg);
+			return 0;
+		}
+	mutex_unlock(&pci_mmcfg_lock);
+
+	return -ENOENT;
+}
diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c
index 5372e86834c0..db63ac23e3d9 100644
--- a/arch/x86/pci/mmconfig_32.c
+++ b/arch/x86/pci/mmconfig_32.c
@@ -11,6 +11,7 @@
 
 #include <linux/pci.h>
 #include <linux/init.h>
+#include <linux/rcupdate.h>
 #include <asm/e820.h>
 #include <asm/pci_x86.h>
 #include <acpi/acpi.h>
@@ -60,9 +61,12 @@ err:		*value = -1;
 		return -EINVAL;
 	}
 
+	rcu_read_lock();
 	base = get_base_addr(seg, bus, devfn);
-	if (!base)
+	if (!base) {
+		rcu_read_unlock();
 		goto err;
+	}
 
 	raw_spin_lock_irqsave(&pci_config_lock, flags);
 
@@ -80,6 +84,7 @@ err:		*value = -1;
 		break;
 	}
 	raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+	rcu_read_unlock();
 
 	return 0;
 }
@@ -93,9 +98,12 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus,
 	if ((bus > 255) || (devfn > 255) || (reg > 4095))
 		return -EINVAL;
 
+	rcu_read_lock();
 	base = get_base_addr(seg, bus, devfn);
-	if (!base)
+	if (!base) {
+		rcu_read_unlock();
 		return -EINVAL;
+	}
 
 	raw_spin_lock_irqsave(&pci_config_lock, flags);
 
@@ -113,11 +121,12 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus,
 		break;
 	}
 	raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+	rcu_read_unlock();
 
 	return 0;
 }
 
-static const struct pci_raw_ops pci_mmcfg = {
+const struct pci_raw_ops pci_mmcfg = {
 	.read =		pci_mmcfg_read,
 	.write =	pci_mmcfg_write,
 };
@@ -132,3 +141,18 @@ int __init pci_mmcfg_arch_init(void)
 void __init pci_mmcfg_arch_free(void)
 {
 }
+
+int __devinit pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg)
+{
+	return 0;
+}
+
+void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg)
+{
+	unsigned long flags;
+
+	/* Invalidate the cached mmcfg map entry. */
+	raw_spin_lock_irqsave(&pci_config_lock, flags);
+	mmcfg_last_accessed_device = 0;
+	raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+}
diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c
index 915a493502cb..d4ebd07c306d 100644
--- a/arch/x86/pci/mmconfig_64.c
+++ b/arch/x86/pci/mmconfig_64.c
@@ -9,6 +9,7 @@
 #include <linux/init.h>
 #include <linux/acpi.h>
 #include <linux/bitmap.h>
+#include <linux/rcupdate.h>
 #include <asm/e820.h>
 #include <asm/pci_x86.h>
 
@@ -34,9 +35,12 @@ err:		*value = -1;
 		return -EINVAL;
 	}
 
+	rcu_read_lock();
 	addr = pci_dev_base(seg, bus, devfn);
-	if (!addr)
+	if (!addr) {
+		rcu_read_unlock();
 		goto err;
+	}
 
 	switch (len) {
 	case 1:
@@ -49,6 +53,7 @@ err:		*value = -1;
 		*value = mmio_config_readl(addr + reg);
 		break;
 	}
+	rcu_read_unlock();
 
 	return 0;
 }
@@ -62,9 +67,12 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus,
 	if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095)))
 		return -EINVAL;
 
+	rcu_read_lock();
 	addr = pci_dev_base(seg, bus, devfn);
-	if (!addr)
+	if (!addr) {
+		rcu_read_unlock();
 		return -EINVAL;
+	}
 
 	switch (len) {
 	case 1:
@@ -77,16 +85,17 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus,
 		mmio_config_writel(addr + reg, value);
 		break;
 	}
+	rcu_read_unlock();
 
 	return 0;
 }
 
-static const struct pci_raw_ops pci_mmcfg = {
+const struct pci_raw_ops pci_mmcfg = {
 	.read =		pci_mmcfg_read,
 	.write =	pci_mmcfg_write,
 };
 
-static void __iomem * __init mcfg_ioremap(struct pci_mmcfg_region *cfg)
+static void __iomem * __devinit mcfg_ioremap(struct pci_mmcfg_region *cfg)
 {
 	void __iomem *addr;
 	u64 start, size;
@@ -105,16 +114,14 @@ int __init pci_mmcfg_arch_init(void)
 {
 	struct pci_mmcfg_region *cfg;
 
-	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);
+	list_for_each_entry(cfg, &pci_mmcfg_list, list)
+		if (pci_mmcfg_arch_map(cfg)) {
 			pci_mmcfg_arch_free();
 			return 0;
 		}
-	}
+
 	raw_pci_ext_ops = &pci_mmcfg;
+
 	return 1;
 }
 
@@ -122,10 +129,25 @@ void __init pci_mmcfg_arch_free(void)
 {
 	struct pci_mmcfg_region *cfg;
 
-	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;
-		}
+	list_for_each_entry(cfg, &pci_mmcfg_list, list)
+		pci_mmcfg_arch_unmap(cfg);
+}
+
+int __devinit pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg)
+{
+	cfg->virt = mcfg_ioremap(cfg);
+	if (!cfg->virt) {
+		pr_err(PREFIX "can't map MMCONFIG at %pR\n", &cfg->res);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg)
+{
+	if (cfg && cfg->virt) {
+		iounmap(cfg->virt + PCI_MMCFG_BUS_OFFSET(cfg->start_bus));
+		cfg->virt = NULL;
 	}
 }
diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c
index 140942f66b31..e14a2ff708b5 100644
--- a/arch/x86/pci/mrst.c
+++ b/arch/x86/pci/mrst.c
@@ -264,7 +264,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_d3delay_fixup);
 
 static void __devinit mrst_power_off_unused_dev(struct pci_dev *dev)
 {
-	pci_set_power_state(dev, PCI_D3cold);
+	pci_set_power_state(dev, PCI_D3hot);
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0801, mrst_power_off_unused_dev);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0809, mrst_power_off_unused_dev);