Merge branch 'x86/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (821 commits)
  x86: make 64bit hpet_set_mapping to use ioremap too, v2
  x86: get x86_phys_bits early
  x86: max_low_pfn_mapped fix #4
  x86: change _node_to_cpumask_ptr to return const ptr
  x86: I/O APIC: remove an IRQ2-mask hack
  x86: fix numaq_tsc_disable calling
  x86, e820: remove end_user_pfn
  x86: max_low_pfn_mapped fix, #3
  x86: max_low_pfn_mapped fix, #2
  x86: max_low_pfn_mapped fix, #1
  x86_64: fix delayed signals
  x86: remove conflicting nx6325 and nx6125 quirks
  x86: Recover timer_ack lost in the merge of the NMI watchdog
  x86: I/O APIC: Never configure IRQ2
  x86: L-APIC: Always fully configure IRQ0
  x86: L-APIC: Set IRQ0 as edge-triggered
  x86: merge dwarf2 headers
  x86: use AS_CFI instead of UNWIND_INFO
  x86: use ignore macro instead of hash comment
  x86: use matching CFI_ENDPROC
  ...

21 files changed, 951 insertions, 138 deletions

diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index c52fca83326..bba867391a8 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -4,8 +4,6 @@
 
 menuconfig ACPI
 	bool "ACPI (Advanced Configuration and Power Interface) Support"
-	depends on !X86_NUMAQ
-	depends on !X86_VISWS
 	depends on !IA64_HP_SIM
 	depends on IA64 || X86
 	depends on PCI
diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c
index 2b4b392dcbc..87a7f1d0257 100644
--- a/drivers/base/power/trace.c
+++ b/drivers/base/power/trace.c
@@ -153,7 +153,7 @@ EXPORT_SYMBOL(set_trace_device);
  * it's not any guarantee, but it's a high _likelihood_ that
  * the match is valid).
  */
-void generate_resume_trace(void *tracedata, unsigned int user)
+void generate_resume_trace(const void *tracedata, unsigned int user)
 {
 	unsigned short lineno = *(unsigned short *)tracedata;
 	const char *file = *(const char **)(tracedata + 2);
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index fdf4044d2e7..1efe162e16d 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -40,6 +40,7 @@ static ssize_t show_##name(struct sys_device *dev, char *buf)	\
 	return sprintf(buf, "%d\n", topology_##name(cpu));	\
 }
 
+#if defined(topology_thread_siblings) || defined(topology_core_siblings)
 static ssize_t show_cpumap(int type, cpumask_t *mask, char *buf)
 {
 	ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf;
@@ -54,21 +55,41 @@ static ssize_t show_cpumap(int type, cpumask_t *mask, char *buf)
 	}
 	return n;
 }
+#endif
 
+#ifdef arch_provides_topology_pointers
 #define define_siblings_show_map(name)					\
-static inline ssize_t show_##name(struct sys_device *dev, char *buf)	\
+static ssize_t show_##name(struct sys_device *dev, char *buf)	\
 {									\
 	unsigned int cpu = dev->id;					\
 	return show_cpumap(0, &(topology_##name(cpu)), buf);		\
 }
 
 #define define_siblings_show_list(name)					\
-static inline ssize_t show_##name##_list(struct sys_device *dev, char *buf) \
+static ssize_t show_##name##_list(struct sys_device *dev, char *buf) \
 {									\
 	unsigned int cpu = dev->id;					\
 	return show_cpumap(1, &(topology_##name(cpu)), buf);		\
 }
 
+#else
+#define define_siblings_show_map(name)					\
+static ssize_t show_##name(struct sys_device *dev, char *buf)	\
+{									\
+	unsigned int cpu = dev->id;					\
+	cpumask_t mask = topology_##name(cpu);				\
+	return show_cpumap(0, &mask, buf);				\
+}
+
+#define define_siblings_show_list(name)					\
+static ssize_t show_##name##_list(struct sys_device *dev, char *buf) \
+{									\
+	unsigned int cpu = dev->id;					\
+	cpumask_t mask = topology_##name(cpu);				\
+	return show_cpumap(1, &mask, buf);				\
+}
+#endif
+
 #define define_siblings_show_func(name)		\
 	define_siblings_show_map(name); define_siblings_show_list(name)
 
diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c
index 13665db363d..481ffe87c71 100644
--- a/drivers/char/agp/amd64-agp.c
+++ b/drivers/char/agp/amd64-agp.c
@@ -16,28 +16,9 @@
 #include <asm/page.h>		/* PAGE_SIZE */
 #include <asm/e820.h>
 #include <asm/k8.h>
+#include <asm/gart.h>
 #include "agp.h"
 
-/* PTE bits. */
-#define GPTE_VALID	1
-#define GPTE_COHERENT	2
-
-/* Aperture control register bits. */
-#define GARTEN		(1<<0)
-#define DISGARTCPU	(1<<4)
-#define DISGARTIO	(1<<5)
-
-/* GART cache control register bits. */
-#define INVGART		(1<<0)
-#define GARTPTEERR	(1<<1)
-
-/* K8 On-cpu GART registers */
-#define AMD64_GARTAPERTURECTL	0x90
-#define AMD64_GARTAPERTUREBASE	0x94
-#define AMD64_GARTTABLEBASE	0x98
-#define AMD64_GARTCACHECTL	0x9c
-#define AMD64_GARTEN		(1<<0)
-
 /* NVIDIA K8 registers */
 #define NVIDIA_X86_64_0_APBASE		0x10
 #define NVIDIA_X86_64_1_APBASE1		0x50
@@ -165,29 +146,18 @@ static int amd64_fetch_size(void)
  * In a multiprocessor x86-64 system, this function gets
  * called once for each CPU.
  */
-static u64 amd64_configure (struct pci_dev *hammer, u64 gatt_table)
+static u64 amd64_configure(struct pci_dev *hammer, u64 gatt_table)
 {
 	u64 aperturebase;
 	u32 tmp;
-	u64 addr, aper_base;
+	u64 aper_base;
 
 	/* Address to map to */
-	pci_read_config_dword (hammer, AMD64_GARTAPERTUREBASE, &tmp);
+	pci_read_config_dword(hammer, AMD64_GARTAPERTUREBASE, &tmp);
 	aperturebase = tmp << 25;
 	aper_base = (aperturebase & PCI_BASE_ADDRESS_MEM_MASK);
 
-	/* address of the mappings table */
-	addr = (u64) gatt_table;
-	addr >>= 12;
-	tmp = (u32) addr<<4;
-	tmp &= ~0xf;
-	pci_write_config_dword (hammer, AMD64_GARTTABLEBASE, tmp);
-
-	/* Enable GART translation for this hammer. */
-	pci_read_config_dword(hammer, AMD64_GARTAPERTURECTL, &tmp);
-	tmp |= GARTEN;
-	tmp &= ~(DISGARTCPU | DISGARTIO);
-	pci_write_config_dword(hammer, AMD64_GARTAPERTURECTL, tmp);
+	enable_gart_translation(hammer, gatt_table);
 
 	return aper_base;
 }
@@ -226,9 +196,9 @@ static void amd64_cleanup(void)
         for (i = 0; i < num_k8_northbridges; i++) {
 		struct pci_dev *dev = k8_northbridges[i];
 		/* disable gart translation */
-		pci_read_config_dword (dev, AMD64_GARTAPERTURECTL, &tmp);
+		pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &tmp);
 		tmp &= ~AMD64_GARTEN;
-		pci_write_config_dword (dev, AMD64_GARTAPERTURECTL, tmp);
+		pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, tmp);
 	}
 }
 
@@ -258,24 +228,10 @@ static const struct agp_bridge_driver amd_8151_driver = {
 };
 
 /* Some basic sanity checks for the aperture. */
-static int __devinit aperture_valid(u64 aper, u32 size)
+static int __devinit agp_aperture_valid(u64 aper, u32 size)
 {
-	if (aper == 0) {
-		printk(KERN_ERR PFX "No aperture\n");
-		return 0;
-	}
-	if (size < 32*1024*1024) {
-		printk(KERN_ERR PFX "Aperture too small (%d MB)\n", size>>20);
-		return 0;
-	}
-       if ((u64)aper + size > 0x100000000ULL) {
-		printk(KERN_ERR PFX "Aperture out of bounds\n");
+	if (!aperture_valid(aper, size, 32*1024*1024))
 		return 0;
-	}
-	if (e820_any_mapped(aper, aper + size, E820_RAM)) {
-		printk(KERN_ERR PFX "Aperture pointing to RAM\n");
-		return 0;
-	}
 
 	/* Request the Aperture. This catches cases when someone else
 	   already put a mapping in there - happens with some very broken BIOS
@@ -308,11 +264,11 @@ static __devinit int fix_northbridge(struct pci_dev *nb, struct pci_dev *agp,
 	u32 nb_order, nb_base;
 	u16 apsize;
 
-	pci_read_config_dword(nb, 0x90, &nb_order);
+	pci_read_config_dword(nb, AMD64_GARTAPERTURECTL, &nb_order);
 	nb_order = (nb_order >> 1) & 7;
-	pci_read_config_dword(nb, 0x94, &nb_base);
+	pci_read_config_dword(nb, AMD64_GARTAPERTUREBASE, &nb_base);
 	nb_aper = nb_base << 25;
-	if (aperture_valid(nb_aper, (32*1024*1024)<<nb_order)) {
+	if (agp_aperture_valid(nb_aper, (32*1024*1024)<<nb_order)) {
 		return 0;
 	}
 
@@ -331,12 +287,23 @@ static __devinit int fix_northbridge(struct pci_dev *nb, struct pci_dev *agp,
 	pci_read_config_dword(agp, 0x10, &aper_low);
 	pci_read_config_dword(agp, 0x14, &aper_hi);
 	aper = (aper_low & ~((1<<22)-1)) | ((u64)aper_hi << 32);
+
+	/*
+	 * On some sick chips APSIZE is 0. This means it wants 4G
+	 * so let double check that order, and lets trust the AMD NB settings
+	 */
+	if (order >=0 && aper + (32ULL<<(20 + order)) > 0x100000000ULL) {
+		printk(KERN_INFO "Aperture size %u MB is not right, using settings from NB\n",
+				  32 << order);
+		order = nb_order;
+	}
+
 	printk(KERN_INFO PFX "Aperture from AGP @ %Lx size %u MB\n", aper, 32 << order);
-	if (order < 0 || !aperture_valid(aper, (32*1024*1024)<<order))
+	if (order < 0 || !agp_aperture_valid(aper, (32*1024*1024)<<order))
 		return -1;
 
-	pci_write_config_dword(nb, 0x90, order << 1);
-	pci_write_config_dword(nb, 0x94, aper >> 25);
+	pci_write_config_dword(nb, AMD64_GARTAPERTURECTL, order << 1);
+	pci_write_config_dword(nb, AMD64_GARTAPERTUREBASE, aper >> 25);
 
 	return 0;
 }
diff --git a/drivers/char/hvc_xen.c b/drivers/char/hvc_xen.c
index dd68f8541c2..db2ae421627 100644
--- a/drivers/char/hvc_xen.c
+++ b/drivers/char/hvc_xen.c
@@ -39,9 +39,14 @@ static int xencons_irq;
 
 /* ------------------------------------------------------------------ */
 
+static unsigned long console_pfn = ~0ul;
+
 static inline struct xencons_interface *xencons_interface(void)
 {
-	return mfn_to_virt(xen_start_info->console.domU.mfn);
+	if (console_pfn == ~0ul)
+		return mfn_to_virt(xen_start_info->console.domU.mfn);
+	else
+		return __va(console_pfn << PAGE_SHIFT);
 }
 
 static inline void notify_daemon(void)
@@ -101,20 +106,32 @@ static int __init xen_init(void)
 {
 	struct hvc_struct *hp;
 
-	if (!is_running_on_xen())
-		return 0;
+	if (!is_running_on_xen() ||
+	    is_initial_xendomain() ||
+	    !xen_start_info->console.domU.evtchn)
+		return -ENODEV;
 
 	xencons_irq = bind_evtchn_to_irq(xen_start_info->console.domU.evtchn);
 	if (xencons_irq < 0)
-		xencons_irq = 0 /* NO_IRQ */;
+		xencons_irq = 0; /* NO_IRQ */
+
 	hp = hvc_alloc(HVC_COOKIE, xencons_irq, &hvc_ops, 256);
 	if (IS_ERR(hp))
 		return PTR_ERR(hp);
 
 	hvc = hp;
+
+	console_pfn = mfn_to_pfn(xen_start_info->console.domU.mfn);
+
 	return 0;
 }
 
+void xen_console_resume(void)
+{
+	if (xencons_irq)
+		rebind_evtchn_irq(xen_start_info->console.domU.evtchn, xencons_irq);
+}
+
 static void __exit xen_fini(void)
 {
 	if (hvc)
@@ -134,12 +151,28 @@ module_init(xen_init);
 module_exit(xen_fini);
 console_initcall(xen_cons_init);
 
+static void raw_console_write(const char *str, int len)
+{
+	while(len > 0) {
+		int rc = HYPERVISOR_console_io(CONSOLEIO_write, len, (char *)str);
+		if (rc <= 0)
+			break;
+
+		str += rc;
+		len -= rc;
+	}
+}
+
+#ifdef CONFIG_EARLY_PRINTK
 static void xenboot_write_console(struct console *console, const char *string,
 				  unsigned len)
 {
 	unsigned int linelen, off = 0;
 	const char *pos;
 
+	raw_console_write(string, len);
+
+	write_console(0, "(early) ", 8);
 	while (off < len && NULL != (pos = strchr(string+off, '\n'))) {
 		linelen = pos-string+off;
 		if (off + linelen > len)
@@ -155,5 +188,23 @@ static void xenboot_write_console(struct console *console, const char *string,
 struct console xenboot_console = {
 	.name		= "xenboot",
 	.write		= xenboot_write_console,
-	.flags		= CON_PRINTBUFFER | CON_BOOT,
+	.flags		= CON_PRINTBUFFER | CON_BOOT | CON_ANYTIME,
 };
+#endif	/* CONFIG_EARLY_PRINTK */
+
+void xen_raw_console_write(const char *str)
+{
+	raw_console_write(str, strlen(str));
+}
+
+void xen_raw_printk(const char *fmt, ...)
+{
+	static char buf[512];
+	va_list ap;
+
+	va_start(ap, fmt);
+	vsnprintf(buf, sizeof(buf), fmt, ap);
+	va_end(ap);
+
+	xen_raw_console_write(buf);
+}
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index dc2cec6127d..ebb9e51deb0 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -26,6 +26,16 @@ config EDD_OFF
 	  kernel. Say N if you want EDD enabled by default. EDD can be dynamically set
 	  using the kernel parameter 'edd={on|skipmbr|off}'.
 
+config FIRMWARE_MEMMAP
+    bool "Add firmware-provided memory map to sysfs" if EMBEDDED
+    default (X86_64 || X86_32)
+    help
+      Add the firmware-provided (unmodified) memory map to /sys/firmware/memmap.
+      That memory map is used for example by kexec to set up parameter area
+      for the next kernel, but can also be used for debugging purposes.
+
+      See also Documentation/ABI/testing/sysfs-firmware-memmap.
+
 config EFI_VARS
 	tristate "EFI Variable Support via sysfs"
 	depends on EFI
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 4c9147154df..1c3c17343db 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -10,3 +10,4 @@ obj-$(CONFIG_DCDBAS)		+= dcdbas.o
 obj-$(CONFIG_DMIID)		+= dmi-id.o
 obj-$(CONFIG_ISCSI_IBFT_FIND)	+= iscsi_ibft_find.o
 obj-$(CONFIG_ISCSI_IBFT)	+= iscsi_ibft.o
+obj-$(CONFIG_FIRMWARE_MEMMAP)	+= memmap.o
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index c5e3ed7e903..455575be356 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -8,6 +8,11 @@
 #include <linux/slab.h>
 #include <asm/dmi.h>
 
+/*
+ * DMI stands for "Desktop Management Interface".  It is part
+ * of and an antecedent to, SMBIOS, which stands for System
+ * Management BIOS.  See further: http://www.dmtf.org/standards
+ */
 static char dmi_empty_string[] = "        ";
 
 static const char * __init dmi_string_nosave(const struct dmi_header *dm, u8 s)
diff --git a/drivers/firmware/memmap.c b/drivers/firmware/memmap.c
new file mode 100644
index 00000000000..e23399c7f77
--- /dev/null
+++ b/drivers/firmware/memmap.c
@@ -0,0 +1,205 @@
+/*
+ * linux/drivers/firmware/memmap.c
+ *  Copyright (C) 2008 SUSE LINUX Products GmbH
+ *  by Bernhard Walle <bwalle@suse.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License v2.0 as published by
+ * the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/string.h>
+#include <linux/firmware-map.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/bootmem.h>
+
+/*
+ * Data types ------------------------------------------------------------------
+ */
+
+/*
+ * Firmware map entry. Because firmware memory maps are flat and not
+ * hierarchical, it's ok to organise them in a linked list. No parent
+ * information is necessary as for the resource tree.
+ */
+struct firmware_map_entry {
+	resource_size_t		start;	/* start of the memory range */
+	resource_size_t		end;	/* end of the memory range (incl.) */
+	const char		*type;	/* type of the memory range */
+	struct list_head	list;	/* entry for the linked list */
+	struct kobject		kobj;   /* kobject for each entry */
+};
+
+/*
+ * Forward declarations --------------------------------------------------------
+ */
+static ssize_t memmap_attr_show(struct kobject *kobj,
+				struct attribute *attr, char *buf);
+static ssize_t start_show(struct firmware_map_entry *entry, char *buf);
+static ssize_t end_show(struct firmware_map_entry *entry, char *buf);
+static ssize_t type_show(struct firmware_map_entry *entry, char *buf);
+
+/*
+ * Static data -----------------------------------------------------------------
+ */
+
+struct memmap_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct firmware_map_entry *entry, char *buf);
+};
+
+struct memmap_attribute memmap_start_attr = __ATTR_RO(start);
+struct memmap_attribute memmap_end_attr   = __ATTR_RO(end);
+struct memmap_attribute memmap_type_attr  = __ATTR_RO(type);
+
+/*
+ * These are default attributes that are added for every memmap entry.
+ */
+static struct attribute *def_attrs[] = {
+	&memmap_start_attr.attr,
+	&memmap_end_attr.attr,
+	&memmap_type_attr.attr,
+	NULL
+};
+
+static struct sysfs_ops memmap_attr_ops = {
+	.show = memmap_attr_show,
+};
+
+static struct kobj_type memmap_ktype = {
+	.sysfs_ops	= &memmap_attr_ops,
+	.default_attrs	= def_attrs,
+};
+
+/*
+ * Registration functions ------------------------------------------------------
+ */
+
+/*
+ * Firmware memory map entries
+ */
+static LIST_HEAD(map_entries);
+
+/**
+ * Common implementation of firmware_map_add() and firmware_map_add_early()
+ * which expects a pre-allocated struct firmware_map_entry.
+ *
+ * @start: Start of the memory range.
+ * @end:   End of the memory range (inclusive).
+ * @type:  Type of the memory range.
+ * @entry: Pre-allocated (either kmalloc() or bootmem allocator), uninitialised
+ *         entry.
+ */
+static int firmware_map_add_entry(resource_size_t start, resource_size_t end,
+				  const char *type,
+				  struct firmware_map_entry *entry)
+{
+	BUG_ON(start > end);
+
+	entry->start = start;
+	entry->end = end;
+	entry->type = type;
+	INIT_LIST_HEAD(&entry->list);
+	kobject_init(&entry->kobj, &memmap_ktype);
+
+	list_add_tail(&entry->list, &map_entries);
+
+	return 0;
+}
+
+/*
+ * See <linux/firmware-map.h> for documentation.
+ */
+int firmware_map_add(resource_size_t start, resource_size_t end,
+		     const char *type)
+{
+	struct firmware_map_entry *entry;
+
+	entry = kmalloc(sizeof(struct firmware_map_entry), GFP_ATOMIC);
+	WARN_ON(!entry);
+	if (!entry)
+		return -ENOMEM;
+
+	return firmware_map_add_entry(start, end, type, entry);
+}
+
+/*
+ * See <linux/firmware-map.h> for documentation.
+ */
+int __init firmware_map_add_early(resource_size_t start, resource_size_t end,
+				  const char *type)
+{
+	struct firmware_map_entry *entry;
+
+	entry = alloc_bootmem_low(sizeof(struct firmware_map_entry));
+	WARN_ON(!entry);
+	if (!entry)
+		return -ENOMEM;
+
+	return firmware_map_add_entry(start, end, type, entry);
+}
+
+/*
+ * Sysfs functions -------------------------------------------------------------
+ */
+
+static ssize_t start_show(struct firmware_map_entry *entry, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "0x%llx\n", entry->start);
+}
+
+static ssize_t end_show(struct firmware_map_entry *entry, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "0x%llx\n", entry->end);
+}
+
+static ssize_t type_show(struct firmware_map_entry *entry, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%s\n", entry->type);
+}
+
+#define to_memmap_attr(_attr) container_of(_attr, struct memmap_attribute, attr)
+#define to_memmap_entry(obj) container_of(obj, struct firmware_map_entry, kobj)
+
+static ssize_t memmap_attr_show(struct kobject *kobj,
+				struct attribute *attr, char *buf)
+{
+	struct firmware_map_entry *entry = to_memmap_entry(kobj);
+	struct memmap_attribute *memmap_attr = to_memmap_attr(attr);
+
+	return memmap_attr->show(entry, buf);
+}
+
+/*
+ * Initialises stuff and adds the entries in the map_entries list to
+ * sysfs. Important is that firmware_map_add() and firmware_map_add_early()
+ * must be called before late_initcall.
+ */
+static int __init memmap_init(void)
+{
+	int i = 0;
+	struct firmware_map_entry *entry;
+	struct kset *memmap_kset;
+
+	memmap_kset = kset_create_and_add("memmap", NULL, firmware_kobj);
+	WARN_ON(!memmap_kset);
+	if (!memmap_kset)
+		return -ENOMEM;
+
+	list_for_each_entry(entry, &map_entries, list) {
+		entry->kobj.kset = memmap_kset;
+		kobject_add(&entry->kobj, NULL, "%d", i++);
+	}
+
+	return 0;
+}
+late_initcall(memmap_init);
+
diff --git a/drivers/input/xen-kbdfront.c b/drivers/input/xen-kbdfront.c
index 0f47f4697cd..9ce3b3baf3a 100644
--- a/drivers/input/xen-kbdfront.c
+++ b/drivers/input/xen-kbdfront.c
@@ -66,6 +66,9 @@ static irqreturn_t input_handler(int rq, void *dev_id)
 		case XENKBD_TYPE_MOTION:
 			input_report_rel(dev, REL_X, event->motion.rel_x);
 			input_report_rel(dev, REL_Y, event->motion.rel_y);
+			if (event->motion.rel_z)
+				input_report_rel(dev, REL_WHEEL,
+						 -event->motion.rel_z);
 			break;
 		case XENKBD_TYPE_KEY:
 			dev = NULL;
@@ -84,6 +87,9 @@ static irqreturn_t input_handler(int rq, void *dev_id)
 		case XENKBD_TYPE_POS:
 			input_report_abs(dev, ABS_X, event->pos.abs_x);
 			input_report_abs(dev, ABS_Y, event->pos.abs_y);
+			if (event->pos.rel_z)
+				input_report_rel(dev, REL_WHEEL,
+						 -event->pos.rel_z);
 			break;
 		}
 		if (dev)
@@ -152,7 +158,7 @@ static int __devinit xenkbd_probe(struct xenbus_device *dev,
 	ptr->evbit[0] = BIT(EV_KEY) | BIT(EV_REL) | BIT(EV_ABS);
 	for (i = BTN_LEFT; i <= BTN_TASK; i++)
 		set_bit(i, ptr->keybit);
-	ptr->relbit[0] = BIT(REL_X) | BIT(REL_Y);
+	ptr->relbit[0] = BIT(REL_X) | BIT(REL_Y) | BIT(REL_WHEEL);
 	input_set_abs_params(ptr, ABS_X, 0, XENFB_WIDTH, 0, 0);
 	input_set_abs_params(ptr, ABS_Y, 0, XENFB_HEIGHT, 0, 0);
 
@@ -294,6 +300,16 @@ InitWait:
 		 */
 		if (dev->state != XenbusStateConnected)
 			goto InitWait; /* no InitWait seen yet, fudge it */
+
+		/* Set input abs params to match backend screen res */
+		if (xenbus_scanf(XBT_NIL, info->xbdev->otherend,
+				 "width", "%d", &val) > 0)
+			input_set_abs_params(info->ptr, ABS_X, 0, val, 0, 0);
+
+		if (xenbus_scanf(XBT_NIL, info->xbdev->otherend,
+				 "height", "%d", &val) > 0)
+			input_set_abs_params(info->ptr, ABS_Y, 0, val, 0, 0);
+
 		break;
 
 	case XenbusStateClosing:
@@ -337,4 +353,6 @@ static void __exit xenkbd_cleanup(void)
 module_init(xenkbd_init);
 module_exit(xenkbd_cleanup);
 
+MODULE_DESCRIPTION("Xen virtual keyboard/pointer device frontend");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("xen:vkbd");
diff --git a/drivers/lguest/Kconfig b/drivers/lguest/Kconfig
index 6b8dbb9ba73..76f2b36881c 100644
--- a/drivers/lguest/Kconfig
+++ b/drivers/lguest/Kconfig
@@ -1,6 +1,6 @@
 config LGUEST
 	tristate "Linux hypervisor example code"
-	depends on X86_32 && EXPERIMENTAL && !X86_PAE && FUTEX && !(X86_VISWS || X86_VOYAGER)
+	depends on X86_32 && EXPERIMENTAL && !X86_PAE && FUTEX && !X86_VOYAGER
 	select HVC_DRIVER
 	---help---
 	  This is a very simple module which allows you to run
diff --git a/drivers/lguest/lg.h b/drivers/lguest/lg.h
index 005bd045d2e..5faefeaf679 100644
--- a/drivers/lguest/lg.h
+++ b/drivers/lguest/lg.h
@@ -136,7 +136,6 @@ int run_guest(struct lg_cpu *cpu, unsigned long __user *user);
  * first step in the migration to the kernel types.  pte_pfn is already defined
  * in the kernel. */
 #define pgd_flags(x)	(pgd_val(x) & ~PAGE_MASK)
-#define pte_flags(x)	(pte_val(x) & ~PAGE_MASK)
 #define pgd_pfn(x)	(pgd_val(x) >> PAGE_SHIFT)
 
 /* interrupts_and_traps.c: */
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index 66c0fd21894..bb0642318a9 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -1637,12 +1637,43 @@ static inline int iommu_prepare_rmrr_dev(struct dmar_rmrr_unit *rmrr,
 }
 
 #ifdef CONFIG_DMAR_GFX_WA
-extern int arch_get_ram_range(int slot, u64 *addr, u64 *size);
+struct iommu_prepare_data {
+	struct pci_dev *pdev;
+	int ret;
+};
+
+static int __init iommu_prepare_work_fn(unsigned long start_pfn,
+					 unsigned long end_pfn, void *datax)
+{
+	struct iommu_prepare_data *data;
+
+	data = (struct iommu_prepare_data *)datax;
+
+	data->ret = iommu_prepare_identity_map(data->pdev,
+				start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
+	return data->ret;
+
+}
+
+static int __init iommu_prepare_with_active_regions(struct pci_dev *pdev)
+{
+	int nid;
+	struct iommu_prepare_data data;
+
+	data.pdev = pdev;
+	data.ret = 0;
+
+	for_each_online_node(nid) {
+		work_with_active_regions(nid, iommu_prepare_work_fn, &data);
+		if (data.ret)
+			return data.ret;
+	}
+	return data.ret;
+}
+
 static void __init iommu_prepare_gfx_mapping(void)
 {
 	struct pci_dev *pdev = NULL;
-	u64 base, size;
-	int slot;
 	int ret;
 
 	for_each_pci_dev(pdev) {
@@ -1651,17 +1682,9 @@ static void __init iommu_prepare_gfx_mapping(void)
 			continue;
 		printk(KERN_INFO "IOMMU: gfx device %s 1-1 mapping\n",
 			pci_name(pdev));
-		slot = arch_get_ram_range(0, &base, &size);
-		while (slot >= 0) {
-			ret = iommu_prepare_identity_map(pdev,
-					base, base + size);
-			if (ret)
-				goto error;
-			slot = arch_get_ram_range(slot, &base, &size);
-		}
-		continue;
-error:
-		printk(KERN_ERR "IOMMU: mapping reserved region failed\n");
+		ret = iommu_prepare_with_active_regions(pdev);
+		if (ret)
+			printk(KERN_ERR "IOMMU: mapping reserved region failed\n");
 	}
 }
 #endif
diff --git a/drivers/video/sgivwfb.c b/drivers/video/sgivwfb.c
index 4fb16240c04..f5252c2552f 100644
--- a/drivers/video/sgivwfb.c
+++ b/drivers/video/sgivwfb.c
@@ -21,8 +21,7 @@
 
 #include <asm/io.h>
 #include <asm/mtrr.h>
-
-#include <setup_arch.h>
+#include <asm/visws/sgivw.h>
 
 #define INCLUDE_TIMING_TABLE_DATA
 #define DBE_REG_BASE par->regs
diff --git a/drivers/video/xen-fbfront.c b/drivers/video/xen-fbfront.c
index 619a6f8d65a..47ed39b52f9 100644
--- a/drivers/video/xen-fbfront.c
+++ b/drivers/video/xen-fbfront.c
@@ -18,6 +18,7 @@
  * frame buffer.
  */
 
+#include <linux/console.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/fb.h>
@@ -42,37 +43,68 @@ struct xenfb_info {
 	struct xenfb_page	*page;
 	unsigned long 		*mfns;
 	int			update_wanted; /* XENFB_TYPE_UPDATE wanted */
+	int			feature_resize; /* XENFB_TYPE_RESIZE ok */
+	struct xenfb_resize	resize;		/* protected by resize_lock */
+	int			resize_dpy;	/* ditto */
+	spinlock_t		resize_lock;
 
 	struct xenbus_device	*xbdev;
 };
 
-static u32 xenfb_mem_len = XENFB_WIDTH * XENFB_HEIGHT * XENFB_DEPTH / 8;
+#define XENFB_DEFAULT_FB_LEN (XENFB_WIDTH * XENFB_HEIGHT * XENFB_DEPTH / 8)
 
+enum { KPARAM_MEM, KPARAM_WIDTH, KPARAM_HEIGHT, KPARAM_CNT };
+static int video[KPARAM_CNT] = { 2, XENFB_WIDTH, XENFB_HEIGHT };
+module_param_array(video, int, NULL, 0);
+MODULE_PARM_DESC(video,
+	"Video memory size in MB, width, height in pixels (default 2,800,600)");
+
+static void xenfb_make_preferred_console(void);
 static int xenfb_remove(struct xenbus_device *);
-static void xenfb_init_shared_page(struct xenfb_info *);
+static void xenfb_init_shared_page(struct xenfb_info *, struct fb_info *);
 static int xenfb_connect_backend(struct xenbus_device *, struct xenfb_info *);
 static void xenfb_disconnect_backend(struct xenfb_info *);
 
+static void xenfb_send_event(struct xenfb_info *info,
+			     union xenfb_out_event *event)
+{
+	u32 prod;
+
+	prod = info->page->out_prod;
+	/* caller ensures !xenfb_queue_full() */
+	mb();			/* ensure ring space available */
+	XENFB_OUT_RING_REF(info->page, prod) = *event;
+	wmb();			/* ensure ring contents visible */
+	info->page->out_prod = prod + 1;
+
+	notify_remote_via_irq(info->irq);
+}
+
 static void xenfb_do_update(struct xenfb_info *info,
 			    int x, int y, int w, int h)
 {
 	union xenfb_out_event event;
-	u32 prod;
 
+	memset(&event, 0, sizeof(event));
 	event.type = XENFB_TYPE_UPDATE;
 	event.update.x = x;
 	event.update.y = y;
 	event.update.width = w;
 	event.update.height = h;
 
-	prod = info->page->out_prod;
 	/* caller ensures !xenfb_queue_full() */
-	mb();			/* ensure ring space available */
-	XENFB_OUT_RING_REF(info->page, prod) = event;
-	wmb();			/* ensure ring contents visible */
-	info->page->out_prod = prod + 1;
+	xenfb_send_event(info, &event);
+}
 
-	notify_remote_via_irq(info->irq);
+static void xenfb_do_resize(struct xenfb_info *info)
+{
+	union xenfb_out_event event;
+
+	memset(&event, 0, sizeof(event));
+	event.resize = info->resize;
+
+	/* caller ensures !xenfb_queue_full() */
+	xenfb_send_event(info, &event);
 }
 
 static int xenfb_queue_full(struct xenfb_info *info)
@@ -84,12 +116,28 @@ static int xenfb_queue_full(struct xenfb_info *info)
 	return prod - cons == XENFB_OUT_RING_LEN;
 }
 
+static void xenfb_handle_resize_dpy(struct xenfb_info *info)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&info->resize_lock, flags);
+	if (info->resize_dpy) {
+		if (!xenfb_queue_full(info)) {
+			info->resize_dpy = 0;
+			xenfb_do_resize(info);
+		}
+	}
+	spin_unlock_irqrestore(&info->resize_lock, flags);
+}
+
 static void xenfb_refresh(struct xenfb_info *info,
 			  int x1, int y1, int w, int h)
 {
 	unsigned long flags;
-	int y2 = y1 + h - 1;
 	int x2 = x1 + w - 1;
+	int y2 = y1 + h - 1;
+
+	xenfb_handle_resize_dpy(info);
 
 	if (!info->update_wanted)
 		return;
@@ -222,6 +270,57 @@ static ssize_t xenfb_write(struct fb_info *p, const char __user *buf,
 	return res;
 }
 
+static int
+xenfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
+{
+	struct xenfb_info *xenfb_info;
+	int required_mem_len;
+
+	xenfb_info = info->par;
+
+	if (!xenfb_info->feature_resize) {
+		if (var->xres == video[KPARAM_WIDTH] &&
+		    var->yres == video[KPARAM_HEIGHT] &&
+		    var->bits_per_pixel == xenfb_info->page->depth) {
+			return 0;
+		}
+		return -EINVAL;
+	}
+
+	/* Can't resize past initial width and height */
+	if (var->xres > video[KPARAM_WIDTH] || var->yres > video[KPARAM_HEIGHT])
+		return -EINVAL;
+
+	required_mem_len = var->xres * var->yres * xenfb_info->page->depth / 8;
+	if (var->bits_per_pixel == xenfb_info->page->depth &&
+	    var->xres <= info->fix.line_length / (XENFB_DEPTH / 8) &&
+	    required_mem_len <= info->fix.smem_len) {
+		var->xres_virtual = var->xres;
+		var->yres_virtual = var->yres;
+		return 0;
+	}
+	return -EINVAL;
+}
+
+static int xenfb_set_par(struct fb_info *info)
+{
+	struct xenfb_info *xenfb_info;
+	unsigned long flags;
+
+	xenfb_info = info->par;
+
+	spin_lock_irqsave(&xenfb_info->resize_lock, flags);
+	xenfb_info->resize.type = XENFB_TYPE_RESIZE;
+	xenfb_info->resize.width = info->var.xres;
+	xenfb_info->resize.height = info->var.yres;
+	xenfb_info->resize.stride = info->fix.line_length;
+	xenfb_info->resize.depth = info->var.bits_per_pixel;
+	xenfb_info->resize.offset = 0;
+	xenfb_info->resize_dpy = 1;
+	spin_unlock_irqrestore(&xenfb_info->resize_lock, flags);
+	return 0;
+}
+
 static struct fb_ops xenfb_fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_read	= fb_sys_read,
@@ -230,6 +329,8 @@ static struct fb_ops xenfb_fb_ops = {
 	.fb_fillrect	= xenfb_fillrect,
 	.fb_copyarea	= xenfb_copyarea,
 	.fb_imageblit	= xenfb_imageblit,
+	.fb_check_var	= xenfb_check_var,
+	.fb_set_par     = xenfb_set_par,
 };
 
 static irqreturn_t xenfb_event_handler(int rq, void *dev_id)
@@ -258,6 +359,8 @@ static int __devinit xenfb_probe(struct xenbus_device *dev,
 {
 	struct xenfb_info *info;
 	struct fb_info *fb_info;
+	int fb_size;
+	int val;
 	int ret;
 
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
@@ -265,18 +368,35 @@ static int __devinit xenfb_probe(struct xenbus_device *dev,
 		xenbus_dev_fatal(dev, -ENOMEM, "allocating info structure");
 		return -ENOMEM;
 	}
+
+	/* Limit kernel param videoram amount to what is in xenstore */
+	if (xenbus_scanf(XBT_NIL, dev->otherend, "videoram", "%d", &val) == 1) {
+		if (val < video[KPARAM_MEM])
+			video[KPARAM_MEM] = val;
+	}
+
+	/* If requested res does not fit in available memory, use default */
+	fb_size = video[KPARAM_MEM] * 1024 * 1024;
+	if (video[KPARAM_WIDTH] * video[KPARAM_HEIGHT] * XENFB_DEPTH / 8
+	    > fb_size) {
+		video[KPARAM_WIDTH] = XENFB_WIDTH;
+		video[KPARAM_HEIGHT] = XENFB_HEIGHT;
+		fb_size = XENFB_DEFAULT_FB_LEN;
+	}
+
 	dev->dev.driver_data = info;
 	info->xbdev = dev;
 	info->irq = -1;
 	info->x1 = info->y1 = INT_MAX;
 	spin_lock_init(&info->dirty_lock);
+	spin_lock_init(&info->resize_lock);
 
-	info->fb = vmalloc(xenfb_mem_len);
+	info->fb = vmalloc(fb_size);
 	if (info->fb == NULL)
 		goto error_nomem;
-	memset(info->fb, 0, xenfb_mem_len);
+	memset(info->fb, 0, fb_size);
 
-	info->nr_pages = (xenfb_mem_len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	info->nr_pages = (fb_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	info->mfns = vmalloc(sizeof(unsigned long) * info->nr_pages);
 	if (!info->mfns)
@@ -287,8 +407,6 @@ static int __devinit xenfb_probe(struct xenbus_device *dev,
 	if (!info->page)
 		goto error_nomem;
 
-	xenfb_init_shared_page(info);
-
 	/* abusing framebuffer_alloc() to allocate pseudo_palette */
 	fb_info = framebuffer_alloc(sizeof(u32) * 256, NULL);
 	if (fb_info == NULL)
@@ -301,9 +419,9 @@ static int __devinit xenfb_probe(struct xenbus_device *dev,
 	fb_info->screen_base = info->fb;
 
 	fb_info->fbops = &xenfb_fb_ops;
-	fb_info->var.xres_virtual = fb_info->var.xres = info->page->width;
-	fb_info->var.yres_virtual = fb_info->var.yres = info->page->height;
-	fb_info->var.bits_per_pixel = info->page->depth;
+	fb_info->var.xres_virtual = fb_info->var.xres = video[KPARAM_WIDTH];
+	fb_info->var.yres_virtual = fb_info->var.yres = video[KPARAM_HEIGHT];
+	fb_info->var.bits_per_pixel = XENFB_DEPTH;
 
 	fb_info->var.red = (struct fb_bitfield){16, 8, 0};
 	fb_info->var.green = (struct fb_bitfield){8, 8, 0};
@@ -315,9 +433,9 @@ static int __devinit xenfb_probe(struct xenbus_device *dev,
 	fb_info->var.vmode = FB_VMODE_NONINTERLACED;
 
 	fb_info->fix.visual = FB_VISUAL_TRUECOLOR;
-	fb_info->fix.line_length = info->page->line_length;
+	fb_info->fix.line_length = fb_info->var.xres * XENFB_DEPTH / 8;
 	fb_info->fix.smem_start = 0;
-	fb_info->fix.smem_len = xenfb_mem_len;
+	fb_info->fix.smem_len = fb_size;
 	strcpy(fb_info->fix.id, "xen");
 	fb_info->fix.type = FB_TYPE_PACKED_PIXELS;
 	fb_info->fix.accel = FB_ACCEL_NONE;
@@ -334,6 +452,8 @@ static int __devinit xenfb_probe(struct xenbus_device *dev,
 	fb_info->fbdefio = &xenfb_defio;
 	fb_deferred_io_init(fb_info);
 
+	xenfb_init_shared_page(info, fb_info);
+
 	ret = register_framebuffer(fb_info);
 	if (ret) {
 		fb_deferred_io_cleanup(fb_info);
@@ -348,6 +468,7 @@ static int __devinit xenfb_probe(struct xenbus_device *dev,
 	if (ret < 0)
 		goto error;
 
+	xenfb_make_preferred_console();
 	return 0;
 
  error_nomem:
@@ -358,12 +479,34 @@ static int __devinit xenfb_probe(struct xenbus_device *dev,
 	return ret;
 }
 
+static __devinit void
+xenfb_make_preferred_console(void)
+{
+	struct console *c;
+
+	if (console_set_on_cmdline)
+		return;
+
+	acquire_console_sem();
+	for (c = console_drivers; c; c = c->next) {
+		if (!strcmp(c->name, "tty") && c->index == 0)
+			break;
+	}
+	release_console_sem();
+	if (c) {
+		unregister_console(c);
+		c->flags |= CON_CONSDEV;
+		c->flags &= ~CON_PRINTBUFFER; /* don't print again */
+		register_console(c);
+	}
+}
+
 static int xenfb_resume(struct xenbus_device *dev)
 {
 	struct xenfb_info *info = dev->dev.driver_data;
 
 	xenfb_disconnect_backend(info);
-	xenfb_init_shared_page(info);
+	xenfb_init_shared_page(info, info->fb_info);
 	return xenfb_connect_backend(dev, info);
 }
 
@@ -391,20 +534,23 @@ static unsigned long vmalloc_to_mfn(void *address)
 	return pfn_to_mfn(vmalloc_to_pfn(address));
 }
 
-static void xenfb_init_shared_page(struct xenfb_info *info)
+static void xenfb_init_shared_page(struct xenfb_info *info,
+				   struct fb_info *fb_info)
 {
 	int i;
+	int epd = PAGE_SIZE / sizeof(info->mfns[0]);
 
 	for (i = 0; i < info->nr_pages; i++)
 		info->mfns[i] = vmalloc_to_mfn(info->fb + i * PAGE_SIZE);
 
-	info->page->pd[0] = vmalloc_to_mfn(info->mfns);
-	info->page->pd[1] = 0;
-	info->page->width = XENFB_WIDTH;
-	info->page->height = XENFB_HEIGHT;
-	info->page->depth = XENFB_DEPTH;
-	info->page->line_length = (info->page->depth / 8) * info->page->width;
-	info->page->mem_length = xenfb_mem_len;
+	for (i = 0; i * epd < info->nr_pages; i++)
+		info->page->pd[i] = vmalloc_to_mfn(&info->mfns[i * epd]);
+
+	info->page->width = fb_info->var.xres;
+	info->page->height = fb_info->var.yres;
+	info->page->depth = fb_info->var.bits_per_pixel;
+	info->page->line_length = fb_info->fix.line_length;
+	info->page->mem_length = fb_info->fix.smem_len;
 	info->page->in_cons = info->page->in_prod = 0;
 	info->page->out_cons = info->page->out_prod = 0;
 }
@@ -504,6 +650,11 @@ InitWait:
 			val = 0;
 		if (val)
 			info->update_wanted = 1;
+
+		if (xenbus_scanf(XBT_NIL, dev->otherend,
+				 "feature-resize", "%d", &val) < 0)
+			val = 0;
+		info->feature_resize = val;
 		break;
 
 	case XenbusStateClosing:
@@ -547,4 +698,6 @@ static void __exit xenfb_cleanup(void)
 module_init(xenfb_init);
 module_exit(xenfb_cleanup);
 
+MODULE_DESCRIPTION("Xen virtual framebuffer device frontend");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("xen:vfb");
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 37af04f1ffd..363286c5429 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -1,4 +1,4 @@
-obj-y	+= grant-table.o features.o events.o
+obj-y	+= grant-table.o features.o events.o manage.o
 obj-y	+= xenbus/
 obj-$(CONFIG_XEN_XENCOMM)	+= xencomm.o
 obj-$(CONFIG_XEN_BALLOON)	+= balloon.o
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index ab25ba6cbbb..591bc29b55f 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -225,7 +225,7 @@ static int increase_reservation(unsigned long nr_pages)
 		page = balloon_next_page(page);
 	}
 
-	reservation.extent_start = (unsigned long)frame_list;
+	set_xen_guest_handle(reservation.extent_start, frame_list);
 	reservation.nr_extents   = nr_pages;
 	rc = HYPERVISOR_memory_op(
 		XENMEM_populate_physmap, &reservation);
@@ -321,7 +321,7 @@ static int decrease_reservation(unsigned long nr_pages)
 		balloon_append(pfn_to_page(pfn));
 	}
 
-	reservation.extent_start = (unsigned long)frame_list;
+	set_xen_guest_handle(reservation.extent_start, frame_list);
 	reservation.nr_extents   = nr_pages;
 	ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
 	BUG_ON(ret != nr_pages);
@@ -368,7 +368,7 @@ static void balloon_process(struct work_struct *work)
 }
 
 /* Resets the Xen limit, sets new target, and kicks off processing. */
-void balloon_set_new_target(unsigned long target)
+static void balloon_set_new_target(unsigned long target)
 {
 	/* No need for lock. Not read-modify-write updates. */
 	balloon_stats.hard_limit   = ~0UL;
@@ -483,7 +483,7 @@ static int dealloc_pte_fn(
 		.extent_order = 0,
 		.domid        = DOMID_SELF
 	};
-	reservation.extent_start = (unsigned long)&mfn;
+	set_xen_guest_handle(reservation.extent_start, &mfn);
 	set_pte_at(&init_mm, addr, pte, __pte_ma(0ull));
 	set_phys_to_machine(__pa(addr) >> PAGE_SHIFT, INVALID_P2M_ENTRY);
 	ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
@@ -519,7 +519,7 @@ static struct page **alloc_empty_pages_and_pagevec(int nr_pages)
 				.extent_order = 0,
 				.domid        = DOMID_SELF
 			};
-			reservation.extent_start = (unsigned long)&gmfn;
+			set_xen_guest_handle(reservation.extent_start, &gmfn);
 			ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
 						   &reservation);
 			if (ret == 1)
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 76e5b7386af..332dd63750a 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -355,7 +355,7 @@ static void unbind_from_irq(unsigned int irq)
 
 	spin_lock(&irq_mapping_update_lock);
 
-	if (VALID_EVTCHN(evtchn) && (--irq_bindcount[irq] == 0)) {
+	if ((--irq_bindcount[irq] == 0) && VALID_EVTCHN(evtchn)) {
 		close.port = evtchn;
 		if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
 			BUG();
@@ -375,7 +375,7 @@ static void unbind_from_irq(unsigned int irq)
 		evtchn_to_irq[evtchn] = -1;
 		irq_info[irq] = IRQ_UNBOUND;
 
-		dynamic_irq_init(irq);
+		dynamic_irq_cleanup(irq);
 	}
 
 	spin_unlock(&irq_mapping_update_lock);
@@ -557,6 +557,33 @@ out:
 	put_cpu();
 }
 
+/* Rebind a new event channel to an existing irq. */
+void rebind_evtchn_irq(int evtchn, int irq)
+{
+	/* Make sure the irq is masked, since the new event channel
+	   will also be masked. */
+	disable_irq(irq);
+
+	spin_lock(&irq_mapping_update_lock);
+
+	/* After resume the irq<->evtchn mappings are all cleared out */
+	BUG_ON(evtchn_to_irq[evtchn] != -1);
+	/* Expect irq to have been bound before,
+	   so the bindcount should be non-0 */
+	BUG_ON(irq_bindcount[irq] == 0);
+
+	evtchn_to_irq[evtchn] = irq;
+	irq_info[irq] = mk_irq_info(IRQT_EVTCHN, 0, evtchn);
+
+	spin_unlock(&irq_mapping_update_lock);
+
+	/* new event channels are always bound to cpu 0 */
+	irq_set_affinity(irq, cpumask_of_cpu(0));
+
+	/* Unmask the event channel. */
+	enable_irq(irq);
+}
+
 /* Rebind an evtchn so that it gets delivered to a specific cpu */
 static void rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 {
@@ -647,6 +674,89 @@ static int retrigger_dynirq(unsigned int irq)
 	return ret;
 }
 
+static void restore_cpu_virqs(unsigned int cpu)
+{
+	struct evtchn_bind_virq bind_virq;
+	int virq, irq, evtchn;
+
+	for (virq = 0; virq < NR_VIRQS; virq++) {
+		if ((irq = per_cpu(virq_to_irq, cpu)[virq]) == -1)
+			continue;
+
+		BUG_ON(irq_info[irq].type != IRQT_VIRQ);
+		BUG_ON(irq_info[irq].index != virq);
+
+		/* Get a new binding from Xen. */
+		bind_virq.virq = virq;
+		bind_virq.vcpu = cpu;
+		if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
+						&bind_virq) != 0)
+			BUG();
+		evtchn = bind_virq.port;
+
+		/* Record the new mapping. */
+		evtchn_to_irq[evtchn] = irq;
+		irq_info[irq] = mk_irq_info(IRQT_VIRQ, virq, evtchn);
+		bind_evtchn_to_cpu(evtchn, cpu);
+
+		/* Ready for use. */
+		unmask_evtchn(evtchn);
+	}
+}
+
+static void restore_cpu_ipis(unsigned int cpu)
+{
+	struct evtchn_bind_ipi bind_ipi;
+	int ipi, irq, evtchn;
+
+	for (ipi = 0; ipi < XEN_NR_IPIS; ipi++) {
+		if ((irq = per_cpu(ipi_to_irq, cpu)[ipi]) == -1)
+			continue;
+
+		BUG_ON(irq_info[irq].type != IRQT_IPI);
+		BUG_ON(irq_info[irq].index != ipi);
+
+		/* Get a new binding from Xen. */
+		bind_ipi.vcpu = cpu;
+		if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_ipi,
+						&bind_ipi) != 0)
+			BUG();
+		evtchn = bind_ipi.port;
+
+		/* Record the new mapping. */
+		evtchn_to_irq[evtchn] = irq;
+		irq_info[irq] = mk_irq_info(IRQT_IPI, ipi, evtchn);
+		bind_evtchn_to_cpu(evtchn, cpu);
+
+		/* Ready for use. */
+		unmask_evtchn(evtchn);
+
+	}
+}
+
+void xen_irq_resume(void)
+{
+	unsigned int cpu, irq, evtchn;
+
+	init_evtchn_cpu_bindings();
+
+	/* New event-channel space is not 'live' yet. */
+	for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++)
+		mask_evtchn(evtchn);
+
+	/* No IRQ <-> event-channel mappings. */
+	for (irq = 0; irq < NR_IRQS; irq++)
+		irq_info[irq].evtchn = 0; /* zap event-channel binding */
+
+	for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++)
+		evtchn_to_irq[evtchn] = -1;
+
+	for_each_possible_cpu(cpu) {
+		restore_cpu_virqs(cpu);
+		restore_cpu_ipis(cpu);
+	}
+}
+
 static struct irq_chip xen_dynamic_chip __read_mostly = {
 	.name		= "xen-dyn",
 	.mask		= disable_dynirq,
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 52b6b41b909..e9e11168616 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -471,14 +471,14 @@ static int gnttab_map(unsigned int start_idx, unsigned int end_idx)
 	return 0;
 }
 
-static int gnttab_resume(void)
+int gnttab_resume(void)
 {
 	if (max_nr_grant_frames() < nr_grant_frames)
 		return -ENOSYS;
 	return gnttab_map(0, nr_grant_frames - 1);
 }
 
-static int gnttab_suspend(void)
+int gnttab_suspend(void)
 {
 	arch_gnttab_unmap_shared(shared, nr_grant_frames);
 	return 0;
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
new file mode 100644
index 00000000000..5b546e365f0
--- /dev/null
+++ b/drivers/xen/manage.c
@@ -0,0 +1,252 @@
+/*
+ * Handle extern requests for shutdown, reboot and sysrq
+ */
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/reboot.h>
+#include <linux/sysrq.h>
+#include <linux/stop_machine.h>
+#include <linux/freezer.h>
+
+#include <xen/xenbus.h>
+#include <xen/grant_table.h>
+#include <xen/events.h>
+#include <xen/hvc-console.h>
+#include <xen/xen-ops.h>
+
+#include <asm/xen/hypercall.h>
+#include <asm/xen/page.h>
+
+enum shutdown_state {
+	SHUTDOWN_INVALID = -1,
+	SHUTDOWN_POWEROFF = 0,
+	SHUTDOWN_SUSPEND = 2,
+	/* Code 3 is SHUTDOWN_CRASH, which we don't use because the domain can only
+	   report a crash, not be instructed to crash!
+	   HALT is the same as POWEROFF, as far as we're concerned.  The tools use
+	   the distinction when we return the reason code to them.  */
+	 SHUTDOWN_HALT = 4,
+};
+
+/* Ignore multiple shutdown requests. */
+static enum shutdown_state shutting_down = SHUTDOWN_INVALID;
+
+#ifdef CONFIG_PM_SLEEP
+static int xen_suspend(void *data)
+{
+	int *cancelled = data;
+	int err;
+
+	BUG_ON(!irqs_disabled());
+
+	load_cr3(swapper_pg_dir);
+
+	err = device_power_down(PMSG_SUSPEND);
+	if (err) {
+		printk(KERN_ERR "xen_suspend: device_power_down failed: %d\n",
+		       err);
+		return err;
+	}
+
+	xen_mm_pin_all();
+	gnttab_suspend();
+	xen_pre_suspend();
+
+	/*
+	 * This hypercall returns 1 if suspend was cancelled
+	 * or the domain was merely checkpointed, and 0 if it
+	 * is resuming in a new domain.
+	 */
+	*cancelled = HYPERVISOR_suspend(virt_to_mfn(xen_start_info));
+
+	xen_post_suspend(*cancelled);
+	gnttab_resume();
+	xen_mm_unpin_all();
+
+	device_power_up();
+
+	if (!*cancelled) {
+		xen_irq_resume();
+		xen_console_resume();
+	}
+
+	return 0;
+}
+
+static void do_suspend(void)
+{
+	int err;
+	int cancelled = 1;
+
+	shutting_down = SHUTDOWN_SUSPEND;
+
+#ifdef CONFIG_PREEMPT
+	/* If the kernel is preemptible, we need to freeze all the processes
+	   to prevent them from being in the middle of a pagetable update
+	   during suspend. */
+	err = freeze_processes();
+	if (err) {
+		printk(KERN_ERR "xen suspend: freeze failed %d\n", err);
+		return;
+	}
+#endif
+
+	err = device_suspend(PMSG_SUSPEND);
+	if (err) {
+		printk(KERN_ERR "xen suspend: device_suspend %d\n", err);
+		goto out;
+	}
+
+	printk("suspending xenbus...\n");
+	/* XXX use normal device tree? */
+	xenbus_suspend();
+
+	err = stop_machine_run(xen_suspend, &cancelled, 0);
+	if (err) {
+		printk(KERN_ERR "failed to start xen_suspend: %d\n", err);
+		goto out;
+	}
+
+	if (!cancelled)
+		xenbus_resume();
+	else
+		xenbus_suspend_cancel();
+
+	device_resume();
+
+	/* Make sure timer events get retriggered on all CPUs */
+	clock_was_set();
+out:
+#ifdef CONFIG_PREEMPT
+	thaw_processes();
+#endif
+	shutting_down = SHUTDOWN_INVALID;
+}
+#endif	/* CONFIG_PM_SLEEP */
+
+static void shutdown_handler(struct xenbus_watch *watch,
+			     const char **vec, unsigned int len)
+{
+	char *str;
+	struct xenbus_transaction xbt;
+	int err;
+
+	if (shutting_down != SHUTDOWN_INVALID)
+		return;
+
+ again:
+	err = xenbus_transaction_start(&xbt);
+	if (err)
+		return;
+
+	str = (char *)xenbus_read(xbt, "control", "shutdown", NULL);
+	/* Ignore read errors and empty reads. */
+	if (XENBUS_IS_ERR_READ(str)) {
+		xenbus_transaction_end(xbt, 1);
+		return;
+	}
+
+	xenbus_write(xbt, "control", "shutdown", "");
+
+	err = xenbus_transaction_end(xbt, 0);
+	if (err == -EAGAIN) {
+		kfree(str);
+		goto again;
+	}
+
+	if (strcmp(str, "poweroff") == 0 ||
+	    strcmp(str, "halt") == 0) {
+		shutting_down = SHUTDOWN_POWEROFF;
+		orderly_poweroff(false);
+	} else if (strcmp(str, "reboot") == 0) {
+		shutting_down = SHUTDOWN_POWEROFF; /* ? */
+		ctrl_alt_del();
+#ifdef CONFIG_PM_SLEEP
+	} else if (strcmp(str, "suspend") == 0) {
+		do_suspend();
+#endif
+	} else {
+		printk(KERN_INFO "Ignoring shutdown request: %s\n", str);
+		shutting_down = SHUTDOWN_INVALID;
+	}
+
+	kfree(str);
+}
+
+static void sysrq_handler(struct xenbus_watch *watch, const char **vec,
+			  unsigned int len)
+{
+	char sysrq_key = '\0';
+	struct xenbus_transaction xbt;
+	int err;
+
+ again:
+	err = xenbus_transaction_start(&xbt);
+	if (err)
+		return;
+	if (!xenbus_scanf(xbt, "control", "sysrq", "%c", &sysrq_key)) {
+		printk(KERN_ERR "Unable to read sysrq code in "
+		       "control/sysrq\n");
+		xenbus_transaction_end(xbt, 1);
+		return;
+	}
+
+	if (sysrq_key != '\0')
+		xenbus_printf(xbt, "control", "sysrq", "%c", '\0');
+
+	err = xenbus_transaction_end(xbt, 0);
+	if (err == -EAGAIN)
+		goto again;
+
+	if (sysrq_key != '\0')
+		handle_sysrq(sysrq_key, NULL);
+}
+
+static struct xenbus_watch shutdown_watch = {
+	.node = "control/shutdown",
+	.callback = shutdown_handler
+};
+
+static struct xenbus_watch sysrq_watch = {
+	.node = "control/sysrq",
+	.callback = sysrq_handler
+};
+
+static int setup_shutdown_watcher(void)
+{
+	int err;
+
+	err = register_xenbus_watch(&shutdown_watch);
+	if (err) {
+		printk(KERN_ERR "Failed to set shutdown watcher\n");
+		return err;
+	}
+
+	err = register_xenbus_watch(&sysrq_watch);
+	if (err) {
+		printk(KERN_ERR "Failed to set sysrq watcher\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static int shutdown_event(struct notifier_block *notifier,
+			  unsigned long event,
+			  void *data)
+{
+	setup_shutdown_watcher();
+	return NOTIFY_DONE;
+}
+
+static int __init setup_shutdown_event(void)
+{
+	static struct notifier_block xenstore_notifier = {
+		.notifier_call = shutdown_event
+	};
+	register_xenstore_notifier(&xenstore_notifier);
+
+	return 0;
+}
+
+subsys_initcall(setup_shutdown_event);
diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c
index 6efbe3f29ca..090c61ee8fd 100644
--- a/drivers/xen/xenbus/xenbus_comms.c
+++ b/drivers/xen/xenbus/xenbus_comms.c
@@ -203,7 +203,6 @@ int xb_read(void *data, unsigned len)
 int xb_init_comms(void)
 {
 	struct xenstore_domain_interface *intf = xen_store_interface;
-	int err;
 
 	if (intf->req_prod != intf->req_cons)
 		printk(KERN_ERR "XENBUS request ring is not quiescent "
@@ -216,18 +215,20 @@ int xb_init_comms(void)
 		intf->rsp_cons = intf->rsp_prod;
 	}
 
-	if (xenbus_irq)
-		unbind_from_irqhandler(xenbus_irq, &xb_waitq);
+	if (xenbus_irq) {
+		/* Already have an irq; assume we're resuming */
+		rebind_evtchn_irq(xen_store_evtchn, xenbus_irq);
+	} else {
+		int err;
+		err = bind_evtchn_to_irqhandler(xen_store_evtchn, wake_waiting,
+						0, "xenbus", &xb_waitq);
+		if (err <= 0) {
+			printk(KERN_ERR "XENBUS request irq failed %i\n", err);
+			return err;
+		}
 
-	err = bind_evtchn_to_irqhandler(
-		xen_store_evtchn, wake_waiting,
-		0, "xenbus", &xb_waitq);
-	if (err <= 0) {
-		printk(KERN_ERR "XENBUS request irq failed %i\n", err);
-		return err;
+		xenbus_irq = err;
 	}
 
-	xenbus_irq = err;
-
 	return 0;
 }