Merge branch 'linus' into release

52 files changed, 2646 insertions, 1320 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 92673b43858d..8d1a419df35d 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -17,6 +17,7 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_cputable.o = -pg -mno-sched-epilog
 CFLAGS_REMOVE_prom_init.o = -pg -mno-sched-epilog
 CFLAGS_REMOVE_btext.o = -pg -mno-sched-epilog
+CFLAGS_REMOVE_prom.o = -pg -mno-sched-epilog
 
 ifdef CONFIG_DYNAMIC_FTRACE
 # dynamic ftrace setup.
@@ -28,7 +29,7 @@ endif
 obj-y				:= cputable.o ptrace.o syscalls.o \
 				   irq.o align.o signal_32.o pmc.o vdso.o \
 				   init_task.o process.o systbl.o idle.o \
-				   signal.o sysfs.o
+				   signal.o sysfs.o cacheinfo.o
 obj-y				+= vdso32/
 obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   signal_64.o ptrace32.o \
@@ -102,6 +103,10 @@ endif
 
 obj-$(CONFIG_PPC64)		+= $(obj64-y)
 
+ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
+obj-y				+= ppc_save_regs.o
+endif
+
 extra-$(CONFIG_PPC_FPU)		+= fpu.o
 extra-$(CONFIG_PPC64)		+= entry_64.o
 
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 75c5dd0138fd..9937fe44555f 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -23,9 +23,6 @@
 #include <linux/mm.h>
 #include <linux/suspend.h>
 #include <linux/hrtimer.h>
-#ifdef CONFIG_KVM
-#include <linux/kvm_host.h>
-#endif
 #ifdef CONFIG_PPC64
 #include <linux/time.h>
 #include <linux/hardirq.h>
@@ -51,6 +48,9 @@
 #ifdef CONFIG_PPC_ISERIES
 #include <asm/iseries/alpaca.h>
 #endif
+#ifdef CONFIG_KVM
+#include <asm/kvm_44x.h>
+#endif
 
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
 #include "head_booke.h"
@@ -60,6 +60,7 @@ int main(void)
 {
 	DEFINE(THREAD, offsetof(struct task_struct, thread));
 	DEFINE(MM, offsetof(struct task_struct, mm));
+	DEFINE(MMCONTEXTID, offsetof(struct mm_struct, context.id));
 #ifdef CONFIG_PPC64
 	DEFINE(AUDITCONTEXT, offsetof(struct task_struct, audit_context));
 #else
@@ -306,6 +307,7 @@ int main(void)
 	DEFINE(CFG_SYSCALL_MAP32, offsetof(struct vdso_data, syscall_map_32));
 	DEFINE(WTOM_CLOCK_SEC, offsetof(struct vdso_data, wtom_clock_sec));
 	DEFINE(WTOM_CLOCK_NSEC, offsetof(struct vdso_data, wtom_clock_nsec));
+	DEFINE(STAMP_XTIME, offsetof(struct vdso_data, stamp_xtime));
 	DEFINE(CFG_ICACHE_BLOCKSZ, offsetof(struct vdso_data, icache_block_size));
 	DEFINE(CFG_DCACHE_BLOCKSZ, offsetof(struct vdso_data, dcache_block_size));
 	DEFINE(CFG_ICACHE_LOGBLOCKSZ, offsetof(struct vdso_data, icache_log_block_size));
@@ -355,12 +357,10 @@ int main(void)
 	DEFINE(PTE_SIZE, sizeof(pte_t));
 
 #ifdef CONFIG_KVM
-	DEFINE(TLBE_BYTES, sizeof(struct tlbe));
+	DEFINE(TLBE_BYTES, sizeof(struct kvmppc_44x_tlbe));
 
 	DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack));
 	DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
-	DEFINE(VCPU_SHADOW_TLB, offsetof(struct kvm_vcpu, arch.shadow_tlb));
-	DEFINE(VCPU_SHADOW_MOD, offsetof(struct kvm_vcpu, arch.shadow_tlb_mod));
 	DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
 	DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
 	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
@@ -378,6 +378,21 @@ int main(void)
 	DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
 	DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
 #endif
+#ifdef CONFIG_44x
+	DEFINE(PGD_T_LOG2, PGD_T_LOG2);
+	DEFINE(PTE_T_LOG2, PTE_T_LOG2);
+#endif
+
+#ifdef CONFIG_KVM_EXIT_TIMING
+	DEFINE(VCPU_TIMING_EXIT_TBU, offsetof(struct kvm_vcpu,
+						arch.timing_exit.tv32.tbu));
+	DEFINE(VCPU_TIMING_EXIT_TBL, offsetof(struct kvm_vcpu,
+						arch.timing_exit.tv32.tbl));
+	DEFINE(VCPU_TIMING_LAST_ENTER_TBU, offsetof(struct kvm_vcpu,
+					arch.timing_last_enter.tv32.tbu));
+	DEFINE(VCPU_TIMING_LAST_ENTER_TBL, offsetof(struct kvm_vcpu,
+					arch.timing_last_enter.tv32.tbl));
+#endif
 
 	return 0;
 }
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
new file mode 100644
index 000000000000..b33f0417a4bf
--- /dev/null
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -0,0 +1,837 @@
+/*
+ * Processor cache information made available to userspace via sysfs;
+ * intended to be compatible with x86 intel_cacheinfo implementation.
+ *
+ * Copyright 2008 IBM Corporation
+ * Author: Nathan Lynch
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/list.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/percpu.h>
+#include <asm/prom.h>
+
+#include "cacheinfo.h"
+
+/* per-cpu object for tracking:
+ * - a "cache" kobject for the top-level directory
+ * - a list of "index" objects representing the cpu's local cache hierarchy
+ */
+struct cache_dir {
+	struct kobject *kobj; /* bare (not embedded) kobject for cache
+			       * directory */
+	struct cache_index_dir *index; /* list of index objects */
+};
+
+/* "index" object: each cpu's cache directory has an index
+ * subdirectory corresponding to a cache object associated with the
+ * cpu.  This object's lifetime is managed via the embedded kobject.
+ */
+struct cache_index_dir {
+	struct kobject kobj;
+	struct cache_index_dir *next; /* next index in parent directory */
+	struct cache *cache;
+};
+
+/* Template for determining which OF properties to query for a given
+ * cache type */
+struct cache_type_info {
+	const char *name;
+	const char *size_prop;
+
+	/* Allow for both [di]-cache-line-size and
+	 * [di]-cache-block-size properties.  According to the PowerPC
+	 * Processor binding, -line-size should be provided if it
+	 * differs from the cache block size (that which is operated
+	 * on by cache instructions), so we look for -line-size first.
+	 * See cache_get_line_size(). */
+
+	const char *line_size_props[2];
+	const char *nr_sets_prop;
+};
+
+/* These are used to index the cache_type_info array. */
+#define CACHE_TYPE_UNIFIED     0
+#define CACHE_TYPE_INSTRUCTION 1
+#define CACHE_TYPE_DATA        2
+
+static const struct cache_type_info cache_type_info[] = {
+	{
+		/* PowerPC Processor binding says the [di]-cache-*
+		 * must be equal on unified caches, so just use
+		 * d-cache properties. */
+		.name            = "Unified",
+		.size_prop       = "d-cache-size",
+		.line_size_props = { "d-cache-line-size",
+				     "d-cache-block-size", },
+		.nr_sets_prop    = "d-cache-sets",
+	},
+	{
+		.name            = "Instruction",
+		.size_prop       = "i-cache-size",
+		.line_size_props = { "i-cache-line-size",
+				     "i-cache-block-size", },
+		.nr_sets_prop    = "i-cache-sets",
+	},
+	{
+		.name            = "Data",
+		.size_prop       = "d-cache-size",
+		.line_size_props = { "d-cache-line-size",
+				     "d-cache-block-size", },
+		.nr_sets_prop    = "d-cache-sets",
+	},
+};
+
+/* Cache object: each instance of this corresponds to a distinct cache
+ * in the system.  There are separate objects for Harvard caches: one
+ * each for instruction and data, and each refers to the same OF node.
+ * The refcount of the OF node is elevated for the lifetime of the
+ * cache object.  A cache object is released when its shared_cpu_map
+ * is cleared (see cache_cpu_clear).
+ *
+ * A cache object is on two lists: an unsorted global list
+ * (cache_list) of cache objects; and a singly-linked list
+ * representing the local cache hierarchy, which is ordered by level
+ * (e.g. L1d -> L1i -> L2 -> L3).
+ */
+struct cache {
+	struct device_node *ofnode;    /* OF node for this cache, may be cpu */
+	struct cpumask shared_cpu_map; /* online CPUs using this cache */
+	int type;                      /* split cache disambiguation */
+	int level;                     /* level not explicit in device tree */
+	struct list_head list;         /* global list of cache objects */
+	struct cache *next_local;      /* next cache of >= level */
+};
+
+static DEFINE_PER_CPU(struct cache_dir *, cache_dir);
+
+/* traversal/modification of this list occurs only at cpu hotplug time;
+ * access is serialized by cpu hotplug locking
+ */
+static LIST_HEAD(cache_list);
+
+static struct cache_index_dir *kobj_to_cache_index_dir(struct kobject *k)
+{
+	return container_of(k, struct cache_index_dir, kobj);
+}
+
+static const char *cache_type_string(const struct cache *cache)
+{
+	return cache_type_info[cache->type].name;
+}
+
+static void __cpuinit cache_init(struct cache *cache, int type, int level, struct device_node *ofnode)
+{
+	cache->type = type;
+	cache->level = level;
+	cache->ofnode = of_node_get(ofnode);
+	INIT_LIST_HEAD(&cache->list);
+	list_add(&cache->list, &cache_list);
+}
+
+static struct cache *__cpuinit new_cache(int type, int level, struct device_node *ofnode)
+{
+	struct cache *cache;
+
+	cache = kzalloc(sizeof(*cache), GFP_KERNEL);
+	if (cache)
+		cache_init(cache, type, level, ofnode);
+
+	return cache;
+}
+
+static void release_cache_debugcheck(struct cache *cache)
+{
+	struct cache *iter;
+
+	list_for_each_entry(iter, &cache_list, list)
+		WARN_ONCE(iter->next_local == cache,
+			  "cache for %s(%s) refers to cache for %s(%s)\n",
+			  iter->ofnode->full_name,
+			  cache_type_string(iter),
+			  cache->ofnode->full_name,
+			  cache_type_string(cache));
+}
+
+static void release_cache(struct cache *cache)
+{
+	if (!cache)
+		return;
+
+	pr_debug("freeing L%d %s cache for %s\n", cache->level,
+		 cache_type_string(cache), cache->ofnode->full_name);
+
+	release_cache_debugcheck(cache);
+	list_del(&cache->list);
+	of_node_put(cache->ofnode);
+	kfree(cache);
+}
+
+static void cache_cpu_set(struct cache *cache, int cpu)
+{
+	struct cache *next = cache;
+
+	while (next) {
+		WARN_ONCE(cpumask_test_cpu(cpu, &next->shared_cpu_map),
+			  "CPU %i already accounted in %s(%s)\n",
+			  cpu, next->ofnode->full_name,
+			  cache_type_string(next));
+		cpumask_set_cpu(cpu, &next->shared_cpu_map);
+		next = next->next_local;
+	}
+}
+
+static int cache_size(const struct cache *cache, unsigned int *ret)
+{
+	const char *propname;
+	const u32 *cache_size;
+
+	propname = cache_type_info[cache->type].size_prop;
+
+	cache_size = of_get_property(cache->ofnode, propname, NULL);
+	if (!cache_size)
+		return -ENODEV;
+
+	*ret = *cache_size;
+	return 0;
+}
+
+static int cache_size_kb(const struct cache *cache, unsigned int *ret)
+{
+	unsigned int size;
+
+	if (cache_size(cache, &size))
+		return -ENODEV;
+
+	*ret = size / 1024;
+	return 0;
+}
+
+/* not cache_line_size() because that's a macro in include/linux/cache.h */
+static int cache_get_line_size(const struct cache *cache, unsigned int *ret)
+{
+	const u32 *line_size;
+	int i, lim;
+
+	lim = ARRAY_SIZE(cache_type_info[cache->type].line_size_props);
+
+	for (i = 0; i < lim; i++) {
+		const char *propname;
+
+		propname = cache_type_info[cache->type].line_size_props[i];
+		line_size = of_get_property(cache->ofnode, propname, NULL);
+		if (line_size)
+			break;
+	}
+
+	if (!line_size)
+		return -ENODEV;
+
+	*ret = *line_size;
+	return 0;
+}
+
+static int cache_nr_sets(const struct cache *cache, unsigned int *ret)
+{
+	const char *propname;
+	const u32 *nr_sets;
+
+	propname = cache_type_info[cache->type].nr_sets_prop;
+
+	nr_sets = of_get_property(cache->ofnode, propname, NULL);
+	if (!nr_sets)
+		return -ENODEV;
+
+	*ret = *nr_sets;
+	return 0;
+}
+
+static int cache_associativity(const struct cache *cache, unsigned int *ret)
+{
+	unsigned int line_size;
+	unsigned int nr_sets;
+	unsigned int size;
+
+	if (cache_nr_sets(cache, &nr_sets))
+		goto err;
+
+	/* If the cache is fully associative, there is no need to
+	 * check the other properties.
+	 */
+	if (nr_sets == 1) {
+		*ret = 0;
+		return 0;
+	}
+
+	if (cache_get_line_size(cache, &line_size))
+		goto err;
+	if (cache_size(cache, &size))
+		goto err;
+
+	if (!(nr_sets > 0 && size > 0 && line_size > 0))
+		goto err;
+
+	*ret = (size / nr_sets) / line_size;
+	return 0;
+err:
+	return -ENODEV;
+}
+
+/* helper for dealing with split caches */
+static struct cache *cache_find_first_sibling(struct cache *cache)
+{
+	struct cache *iter;
+
+	if (cache->type == CACHE_TYPE_UNIFIED)
+		return cache;
+
+	list_for_each_entry(iter, &cache_list, list)
+		if (iter->ofnode == cache->ofnode && iter->next_local == cache)
+			return iter;
+
+	return cache;
+}
+
+/* return the first cache on a local list matching node */
+static struct cache *cache_lookup_by_node(const struct device_node *node)
+{
+	struct cache *cache = NULL;
+	struct cache *iter;
+
+	list_for_each_entry(iter, &cache_list, list) {
+		if (iter->ofnode != node)
+			continue;
+		cache = cache_find_first_sibling(iter);
+		break;
+	}
+
+	return cache;
+}
+
+static bool cache_node_is_unified(const struct device_node *np)
+{
+	return of_get_property(np, "cache-unified", NULL);
+}
+
+static struct cache *__cpuinit cache_do_one_devnode_unified(struct device_node *node, int level)
+{
+	struct cache *cache;
+
+	pr_debug("creating L%d ucache for %s\n", level, node->full_name);
+
+	cache = new_cache(CACHE_TYPE_UNIFIED, level, node);
+
+	return cache;
+}
+
+static struct cache *__cpuinit cache_do_one_devnode_split(struct device_node *node, int level)
+{
+	struct cache *dcache, *icache;
+
+	pr_debug("creating L%d dcache and icache for %s\n", level,
+		 node->full_name);
+
+	dcache = new_cache(CACHE_TYPE_DATA, level, node);
+	icache = new_cache(CACHE_TYPE_INSTRUCTION, level, node);
+
+	if (!dcache || !icache)
+		goto err;
+
+	dcache->next_local = icache;
+
+	return dcache;
+err:
+	release_cache(dcache);
+	release_cache(icache);
+	return NULL;
+}
+
+static struct cache *__cpuinit cache_do_one_devnode(struct device_node *node, int level)
+{
+	struct cache *cache;
+
+	if (cache_node_is_unified(node))
+		cache = cache_do_one_devnode_unified(node, level);
+	else
+		cache = cache_do_one_devnode_split(node, level);
+
+	return cache;
+}
+
+static struct cache *__cpuinit cache_lookup_or_instantiate(struct device_node *node, int level)
+{
+	struct cache *cache;
+
+	cache = cache_lookup_by_node(node);
+
+	WARN_ONCE(cache && cache->level != level,
+		  "cache level mismatch on lookup (got %d, expected %d)\n",
+		  cache->level, level);
+
+	if (!cache)
+		cache = cache_do_one_devnode(node, level);
+
+	return cache;
+}
+
+static void __cpuinit link_cache_lists(struct cache *smaller, struct cache *bigger)
+{
+	while (smaller->next_local) {
+		if (smaller->next_local == bigger)
+			return; /* already linked */
+		smaller = smaller->next_local;
+	}
+
+	smaller->next_local = bigger;
+}
+
+static void __cpuinit do_subsidiary_caches_debugcheck(struct cache *cache)
+{
+	WARN_ON_ONCE(cache->level != 1);
+	WARN_ON_ONCE(strcmp(cache->ofnode->type, "cpu"));
+}
+
+static void __cpuinit do_subsidiary_caches(struct cache *cache)
+{
+	struct device_node *subcache_node;
+	int level = cache->level;
+
+	do_subsidiary_caches_debugcheck(cache);
+
+	while ((subcache_node = of_find_next_cache_node(cache->ofnode))) {
+		struct cache *subcache;
+
+		level++;
+		subcache = cache_lookup_or_instantiate(subcache_node, level);
+		of_node_put(subcache_node);
+		if (!subcache)
+			break;
+
+		link_cache_lists(cache, subcache);
+		cache = subcache;
+	}
+}
+
+static struct cache *__cpuinit cache_chain_instantiate(unsigned int cpu_id)
+{
+	struct device_node *cpu_node;
+	struct cache *cpu_cache = NULL;
+
+	pr_debug("creating cache object(s) for CPU %i\n", cpu_id);
+
+	cpu_node = of_get_cpu_node(cpu_id, NULL);
+	WARN_ONCE(!cpu_node, "no OF node found for CPU %i\n", cpu_id);
+	if (!cpu_node)
+		goto out;
+
+	cpu_cache = cache_lookup_or_instantiate(cpu_node, 1);
+	if (!cpu_cache)
+		goto out;
+
+	do_subsidiary_caches(cpu_cache);
+
+	cache_cpu_set(cpu_cache, cpu_id);
+out:
+	of_node_put(cpu_node);
+
+	return cpu_cache;
+}
+
+static struct cache_dir *__cpuinit cacheinfo_create_cache_dir(unsigned int cpu_id)
+{
+	struct cache_dir *cache_dir;
+	struct sys_device *sysdev;
+	struct kobject *kobj = NULL;
+
+	sysdev = get_cpu_sysdev(cpu_id);
+	WARN_ONCE(!sysdev, "no sysdev for CPU %i\n", cpu_id);
+	if (!sysdev)
+		goto err;
+
+	kobj = kobject_create_and_add("cache", &sysdev->kobj);
+	if (!kobj)
+		goto err;
+
+	cache_dir = kzalloc(sizeof(*cache_dir), GFP_KERNEL);
+	if (!cache_dir)
+		goto err;
+
+	cache_dir->kobj = kobj;
+
+	WARN_ON_ONCE(per_cpu(cache_dir, cpu_id) != NULL);
+
+	per_cpu(cache_dir, cpu_id) = cache_dir;
+
+	return cache_dir;
+err:
+	kobject_put(kobj);
+	return NULL;
+}
+
+static void cache_index_release(struct kobject *kobj)
+{
+	struct cache_index_dir *index;
+
+	index = kobj_to_cache_index_dir(kobj);
+
+	pr_debug("freeing index directory for L%d %s cache\n",
+		 index->cache->level, cache_type_string(index->cache));
+
+	kfree(index);
+}
+
+static ssize_t cache_index_show(struct kobject *k, struct attribute *attr, char *buf)
+{
+	struct kobj_attribute *kobj_attr;
+
+	kobj_attr = container_of(attr, struct kobj_attribute, attr);
+
+	return kobj_attr->show(k, kobj_attr, buf);
+}
+
+static struct cache *index_kobj_to_cache(struct kobject *k)
+{
+	struct cache_index_dir *index;
+
+	index = kobj_to_cache_index_dir(k);
+
+	return index->cache;
+}
+
+static ssize_t size_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+	unsigned int size_kb;
+	struct cache *cache;
+
+	cache = index_kobj_to_cache(k);
+
+	if (cache_size_kb(cache, &size_kb))
+		return -ENODEV;
+
+	return sprintf(buf, "%uK\n", size_kb);
+}
+
+static struct kobj_attribute cache_size_attr =
+	__ATTR(size, 0444, size_show, NULL);
+
+
+static ssize_t line_size_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+	unsigned int line_size;
+	struct cache *cache;
+
+	cache = index_kobj_to_cache(k);
+
+	if (cache_get_line_size(cache, &line_size))
+		return -ENODEV;
+
+	return sprintf(buf, "%u\n", line_size);
+}
+
+static struct kobj_attribute cache_line_size_attr =
+	__ATTR(coherency_line_size, 0444, line_size_show, NULL);
+
+static ssize_t nr_sets_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+	unsigned int nr_sets;
+	struct cache *cache;
+
+	cache = index_kobj_to_cache(k);
+
+	if (cache_nr_sets(cache, &nr_sets))
+		return -ENODEV;
+
+	return sprintf(buf, "%u\n", nr_sets);
+}
+
+static struct kobj_attribute cache_nr_sets_attr =
+	__ATTR(number_of_sets, 0444, nr_sets_show, NULL);
+
+static ssize_t associativity_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+	unsigned int associativity;
+	struct cache *cache;
+
+	cache = index_kobj_to_cache(k);
+
+	if (cache_associativity(cache, &associativity))
+		return -ENODEV;
+
+	return sprintf(buf, "%u\n", associativity);
+}
+
+static struct kobj_attribute cache_assoc_attr =
+	__ATTR(ways_of_associativity, 0444, associativity_show, NULL);
+
+static ssize_t type_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+	struct cache *cache;
+
+	cache = index_kobj_to_cache(k);
+
+	return sprintf(buf, "%s\n", cache_type_string(cache));
+}
+
+static struct kobj_attribute cache_type_attr =
+	__ATTR(type, 0444, type_show, NULL);
+
+static ssize_t level_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+	struct cache_index_dir *index;
+	struct cache *cache;
+
+	index = kobj_to_cache_index_dir(k);
+	cache = index->cache;
+
+	return sprintf(buf, "%d\n", cache->level);
+}
+
+static struct kobj_attribute cache_level_attr =
+	__ATTR(level, 0444, level_show, NULL);
+
+static ssize_t shared_cpu_map_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+	struct cache_index_dir *index;
+	struct cache *cache;
+	int len;
+	int n = 0;
+
+	index = kobj_to_cache_index_dir(k);
+	cache = index->cache;
+	len = PAGE_SIZE - 2;
+
+	if (len > 1) {
+		n = cpumask_scnprintf(buf, len, &cache->shared_cpu_map);
+		buf[n++] = '\n';
+		buf[n] = '\0';
+	}
+	return n;
+}
+
+static struct kobj_attribute cache_shared_cpu_map_attr =
+	__ATTR(shared_cpu_map, 0444, shared_cpu_map_show, NULL);
+
+/* Attributes which should always be created -- the kobject/sysfs core
+ * does this automatically via kobj_type->default_attrs.  This is the
+ * minimum data required to uniquely identify a cache.
+ */
+static struct attribute *cache_index_default_attrs[] = {
+	&cache_type_attr.attr,
+	&cache_level_attr.attr,
+	&cache_shared_cpu_map_attr.attr,
+	NULL,
+};
+
+/* Attributes which should be created if the cache device node has the
+ * right properties -- see cacheinfo_create_index_opt_attrs
+ */
+static struct kobj_attribute *cache_index_opt_attrs[] = {
+	&cache_size_attr,
+	&cache_line_size_attr,
+	&cache_nr_sets_attr,
+	&cache_assoc_attr,
+};
+
+static struct sysfs_ops cache_index_ops = {
+	.show = cache_index_show,
+};
+
+static struct kobj_type cache_index_type = {
+	.release = cache_index_release,
+	.sysfs_ops = &cache_index_ops,
+	.default_attrs = cache_index_default_attrs,
+};
+
+static void __cpuinit cacheinfo_create_index_opt_attrs(struct cache_index_dir *dir)
+{
+	const char *cache_name;
+	const char *cache_type;
+	struct cache *cache;
+	char *buf;
+	int i;
+
+	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!buf)
+		return;
+
+	cache = dir->cache;
+	cache_name = cache->ofnode->full_name;
+	cache_type = cache_type_string(cache);
+
+	/* We don't want to create an attribute that can't provide a
+	 * meaningful value.  Check the return value of each optional
+	 * attribute's ->show method before registering the
+	 * attribute.
+	 */
+	for (i = 0; i < ARRAY_SIZE(cache_index_opt_attrs); i++) {
+		struct kobj_attribute *attr;
+		ssize_t rc;
+
+		attr = cache_index_opt_attrs[i];
+
+		rc = attr->show(&dir->kobj, attr, buf);
+		if (rc <= 0) {
+			pr_debug("not creating %s attribute for "
+				 "%s(%s) (rc = %zd)\n",
+				 attr->attr.name, cache_name,
+				 cache_type, rc);
+			continue;
+		}
+		if (sysfs_create_file(&dir->kobj, &attr->attr))
+			pr_debug("could not create %s attribute for %s(%s)\n",
+				 attr->attr.name, cache_name, cache_type);
+	}
+
+	kfree(buf);
+}
+
+static void __cpuinit cacheinfo_create_index_dir(struct cache *cache, int index, struct cache_dir *cache_dir)
+{
+	struct cache_index_dir *index_dir;
+	int rc;
+
+	index_dir = kzalloc(sizeof(*index_dir), GFP_KERNEL);
+	if (!index_dir)
+		goto err;
+
+	index_dir->cache = cache;
+
+	rc = kobject_init_and_add(&index_dir->kobj, &cache_index_type,
+				  cache_dir->kobj, "index%d", index);
+	if (rc)
+		goto err;
+
+	index_dir->next = cache_dir->index;
+	cache_dir->index = index_dir;
+
+	cacheinfo_create_index_opt_attrs(index_dir);
+
+	return;
+err:
+	kfree(index_dir);
+}
+
+static void __cpuinit cacheinfo_sysfs_populate(unsigned int cpu_id, struct cache *cache_list)
+{
+	struct cache_dir *cache_dir;
+	struct cache *cache;
+	int index = 0;
+
+	cache_dir = cacheinfo_create_cache_dir(cpu_id);
+	if (!cache_dir)
+		return;
+
+	cache = cache_list;
+	while (cache) {
+		cacheinfo_create_index_dir(cache, index, cache_dir);
+		index++;
+		cache = cache->next_local;
+	}
+}
+
+void __cpuinit cacheinfo_cpu_online(unsigned int cpu_id)
+{
+	struct cache *cache;
+
+	cache = cache_chain_instantiate(cpu_id);
+	if (!cache)
+		return;
+
+	cacheinfo_sysfs_populate(cpu_id, cache);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU /* functions needed for cpu offline */
+
+static struct cache *cache_lookup_by_cpu(unsigned int cpu_id)
+{
+	struct device_node *cpu_node;
+	struct cache *cache;
+
+	cpu_node = of_get_cpu_node(cpu_id, NULL);
+	WARN_ONCE(!cpu_node, "no OF node found for CPU %i\n", cpu_id);
+	if (!cpu_node)
+		return NULL;
+
+	cache = cache_lookup_by_node(cpu_node);
+	of_node_put(cpu_node);
+
+	return cache;
+}
+
+static void remove_index_dirs(struct cache_dir *cache_dir)
+{
+	struct cache_index_dir *index;
+
+	index = cache_dir->index;
+
+	while (index) {
+		struct cache_index_dir *next;
+
+		next = index->next;
+		kobject_put(&index->kobj);
+		index = next;
+	}
+}
+
+static void remove_cache_dir(struct cache_dir *cache_dir)
+{
+	remove_index_dirs(cache_dir);
+
+	kobject_put(cache_dir->kobj);
+
+	kfree(cache_dir);
+}
+
+static void cache_cpu_clear(struct cache *cache, int cpu)
+{
+	while (cache) {
+		struct cache *next = cache->next_local;
+
+		WARN_ONCE(!cpumask_test_cpu(cpu, &cache->shared_cpu_map),
+			  "CPU %i not accounted in %s(%s)\n",
+			  cpu, cache->ofnode->full_name,
+			  cache_type_string(cache));
+
+		cpumask_clear_cpu(cpu, &cache->shared_cpu_map);
+
+		/* Release the cache object if all the cpus using it
+		 * are offline */
+		if (cpumask_empty(&cache->shared_cpu_map))
+			release_cache(cache);
+
+		cache = next;
+	}
+}
+
+void cacheinfo_cpu_offline(unsigned int cpu_id)
+{
+	struct cache_dir *cache_dir;
+	struct cache *cache;
+
+	/* Prevent userspace from seeing inconsistent state - remove
+	 * the sysfs hierarchy first */
+	cache_dir = per_cpu(cache_dir, cpu_id);
+
+	/* careful, sysfs population may have failed */
+	if (cache_dir)
+		remove_cache_dir(cache_dir);
+
+	per_cpu(cache_dir, cpu_id) = NULL;
+
+	/* clear the CPU's bit in its cache chain, possibly freeing
+	 * cache objects */
+	cache = cache_lookup_by_cpu(cpu_id);
+	if (cache)
+		cache_cpu_clear(cache, cpu_id);
+}
+#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/powerpc/kernel/cacheinfo.h b/arch/powerpc/kernel/cacheinfo.h
new file mode 100644
index 000000000000..a7b74d36acd7
--- /dev/null
+++ b/arch/powerpc/kernel/cacheinfo.h
@@ -0,0 +1,8 @@
+#ifndef _PPC_CACHEINFO_H
+#define _PPC_CACHEINFO_H
+
+/* These are just hooks for sysfs.c to use. */
+extern void cacheinfo_cpu_online(unsigned int cpu_id);
+extern void cacheinfo_cpu_offline(unsigned int cpu_id);
+
+#endif /* _PPC_CACHEINFO_H */
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 7e8719504f39..923f87aff20a 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -19,6 +19,7 @@
 #include <asm/oprofile_impl.h>
 #include <asm/cputable.h>
 #include <asm/prom.h>		/* for PTRRELOC on ARCH=ppc */
+#include <asm/mmu.h>
 
 struct cpu_spec* cur_cpu_spec = NULL;
 EXPORT_SYMBOL(cur_cpu_spec);
@@ -94,6 +95,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER3 (630)",
 		.cpu_features		= CPU_FTRS_POWER3,
 		.cpu_user_features	= COMMON_USER_PPC64|PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -109,6 +111,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER3 (630+)",
 		.cpu_features		= CPU_FTRS_POWER3,
 		.cpu_user_features	= COMMON_USER_PPC64|PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -124,6 +127,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "RS64-II (northstar)",
 		.cpu_features		= CPU_FTRS_RS64,
 		.cpu_user_features	= COMMON_USER_PPC64,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -139,6 +143,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "RS64-III (pulsar)",
 		.cpu_features		= CPU_FTRS_RS64,
 		.cpu_user_features	= COMMON_USER_PPC64,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -154,6 +159,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "RS64-III (icestar)",
 		.cpu_features		= CPU_FTRS_RS64,
 		.cpu_user_features	= COMMON_USER_PPC64,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -169,6 +175,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "RS64-IV (sstar)",
 		.cpu_features		= CPU_FTRS_RS64,
 		.cpu_user_features	= COMMON_USER_PPC64,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -184,6 +191,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER4 (gp)",
 		.cpu_features		= CPU_FTRS_POWER4,
 		.cpu_user_features	= COMMON_USER_POWER4,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -199,6 +207,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER4+ (gq)",
 		.cpu_features		= CPU_FTRS_POWER4,
 		.cpu_user_features	= COMMON_USER_POWER4,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -215,6 +224,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_PPC970,
 		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -233,6 +243,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_PPC970,
 		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -251,6 +262,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_PPC970,
 		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -269,6 +281,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_PPC970,
 		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -287,6 +300,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_PPC970,
 		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -303,6 +317,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER5 (gr)",
 		.cpu_features		= CPU_FTRS_POWER5,
 		.cpu_user_features	= COMMON_USER_POWER5,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
@@ -323,6 +338,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER5+ (gs)",
 		.cpu_features		= CPU_FTRS_POWER5,
 		.cpu_user_features	= COMMON_USER_POWER5_PLUS,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
@@ -339,6 +355,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER5+ (gs)",
 		.cpu_features		= CPU_FTRS_POWER5,
 		.cpu_user_features	= COMMON_USER_POWER5_PLUS,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
@@ -356,6 +373,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER5+",
 		.cpu_features		= CPU_FTRS_POWER5,
 		.cpu_user_features	= COMMON_USER_POWER5_PLUS,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.machine_check		= machine_check_generic,
@@ -369,6 +387,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_POWER6,
 		.cpu_user_features	= COMMON_USER_POWER6 |
 			PPC_FEATURE_POWER6_EXT,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
@@ -388,6 +407,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER6 (architected)",
 		.cpu_features		= CPU_FTRS_POWER6,
 		.cpu_user_features	= COMMON_USER_POWER6,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.machine_check		= machine_check_generic,
@@ -400,6 +420,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER7 (architected)",
 		.cpu_features		= CPU_FTRS_POWER7,
 		.cpu_user_features	= COMMON_USER_POWER7,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.machine_check		= machine_check_generic,
@@ -412,6 +433,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER7 (raw)",
 		.cpu_features		= CPU_FTRS_POWER7,
 		.cpu_user_features	= COMMON_USER_POWER7,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
@@ -434,6 +456,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_user_features	= COMMON_USER_PPC64 |
 			PPC_FEATURE_CELL | PPC_FEATURE_HAS_ALTIVEC_COMP |
 			PPC_FEATURE_SMT,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 4,
@@ -449,6 +472,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "PA6T",
 		.cpu_features		= CPU_FTRS_PA6T,
 		.cpu_user_features	= COMMON_USER_PA6T,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 64,
 		.dcache_bsize		= 64,
 		.num_pmcs		= 6,
@@ -466,6 +490,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER4 (compatible)",
 		.cpu_features		= CPU_FTRS_COMPATIBLE,
 		.cpu_user_features	= COMMON_USER_PPC64,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
@@ -483,6 +508,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_PPC601,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_601_INSTR |
 			PPC_FEATURE_UNIFIED_CACHE | PPC_FEATURE_NO_TB,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_generic,
@@ -494,6 +520,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "603",
 		.cpu_features		= CPU_FTRS_603,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= 0,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_603,
@@ -506,6 +533,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "603e",
 		.cpu_features		= CPU_FTRS_603,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= 0,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_603,
@@ -518,6 +546,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "603ev",
 		.cpu_features		= CPU_FTRS_603,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= 0,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_603,
@@ -530,6 +559,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "604",
 		.cpu_features		= CPU_FTRS_604,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 2,
@@ -543,6 +573,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "604e",
 		.cpu_features		= CPU_FTRS_604,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -556,6 +587,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "604r",
 		.cpu_features		= CPU_FTRS_604,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -569,6 +601,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "604ev",
 		.cpu_features		= CPU_FTRS_604,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -582,6 +615,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "740/750",
 		.cpu_features		= CPU_FTRS_740_NOTAU,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -595,6 +629,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "750CX",
 		.cpu_features		= CPU_FTRS_750,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -608,6 +643,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "750CX",
 		.cpu_features		= CPU_FTRS_750,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -622,6 +658,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "750CXe",
 		.cpu_features		= CPU_FTRS_750,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -636,6 +673,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "750CXe",
 		.cpu_features		= CPU_FTRS_750,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -650,6 +688,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "750CL",
 		.cpu_features		= CPU_FTRS_750CL,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -664,6 +703,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "745/755",
 		.cpu_features		= CPU_FTRS_750,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -678,6 +718,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "750FX",
 		.cpu_features		= CPU_FTRS_750FX1,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -692,6 +733,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "750FX",
 		.cpu_features		= CPU_FTRS_750FX2,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -706,6 +748,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "750FX",
 		.cpu_features		= CPU_FTRS_750FX,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -720,6 +763,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "750GX",
 		.cpu_features		= CPU_FTRS_750GX,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -734,6 +778,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "740/750",
 		.cpu_features		= CPU_FTRS_740,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -749,6 +794,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_7400_NOTAU,
 		.cpu_user_features	= COMMON_USER |
 			PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -764,6 +810,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_7400,
 		.cpu_user_features	= COMMON_USER |
 			PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -779,6 +826,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_7400,
 		.cpu_user_features	= COMMON_USER |
 			PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -794,6 +842,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_7450_20,
 		.cpu_user_features	= COMMON_USER |
 			PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
@@ -811,6 +860,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_7450_21,
 		.cpu_user_features	= COMMON_USER |
 			PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
@@ -828,6 +878,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_7450_23,
 		.cpu_user_features	= COMMON_USER |
 			PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
@@ -845,6 +896,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_7455_1,
 		.cpu_user_features	= COMMON_USER |
 			PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
@@ -862,6 +914,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_7455_20,
 		.cpu_user_features	= COMMON_USER |
 			PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
@@ -879,6 +932,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_7455,
 		.cpu_user_features	= COMMON_USER |
 			PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
@@ -896,6 +950,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_7447_10,
 		.cpu_user_features	= COMMON_USER |
 			PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
@@ -913,6 +968,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_7447_10,
 		.cpu_user_features	= COMMON_USER |
 			PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
@@ -929,6 +985,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "7447/7457",
 		.cpu_features		= CPU_FTRS_7447,
 		.cpu_user_features	= COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
@@ -946,6 +1003,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_7447A,
 		.cpu_user_features	= COMMON_USER |
 			PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
@@ -963,6 +1021,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_7448,
 		.cpu_user_features	= COMMON_USER |
 			PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE,
+		.mmu_features		= MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
@@ -979,6 +1038,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "82xx",
 		.cpu_features		= CPU_FTRS_82XX,
 		.cpu_user_features	= COMMON_USER,
+		.mmu_features		= 0,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_603,
@@ -991,6 +1051,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "G2_LE",
 		.cpu_features		= CPU_FTRS_G2_LE,
 		.cpu_user_features	= COMMON_USER,
+		.mmu_features		= MMU_FTR_USE_HIGH_BATS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_603,
@@ -1003,6 +1064,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "e300c1",
 		.cpu_features		= CPU_FTRS_E300,
 		.cpu_user_features	= COMMON_USER,
+		.mmu_features		= MMU_FTR_USE_HIGH_BATS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_603,
@@ -1015,6 +1077,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "e300c2",
 		.cpu_features		= CPU_FTRS_E300C2,
 		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+		.mmu_features		= MMU_FTR_USE_HIGH_BATS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_603,
@@ -1027,6 +1090,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "e300c3",
 		.cpu_features		= CPU_FTRS_E300,
 		.cpu_user_features	= COMMON_USER,
+		.mmu_features		= MMU_FTR_USE_HIGH_BATS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_603,
@@ -1041,6 +1105,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "e300c4",
 		.cpu_features		= CPU_FTRS_E300,
 		.cpu_user_features	= COMMON_USER,
+		.mmu_features		= MMU_FTR_USE_HIGH_BATS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_603,
@@ -1056,6 +1121,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "(generic PPC)",
 		.cpu_features		= CPU_FTRS_CLASSIC32,
 		.cpu_user_features	= COMMON_USER,
+		.mmu_features		= MMU_FTR_HPTE_TABLE,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_generic,
@@ -1071,6 +1137,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		 * if the 8xx code is there.... */
 		.cpu_features		= CPU_FTRS_8XX,
 		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+		.mmu_features		= MMU_FTR_TYPE_8xx,
 		.icache_bsize		= 16,
 		.dcache_bsize		= 16,
 		.platform		= "ppc823",
@@ -1083,6 +1150,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "403GC",
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 16,
 		.dcache_bsize		= 16,
 		.machine_check		= machine_check_4xx,
@@ -1095,6 +1163,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 		 	PPC_FEATURE_HAS_MMU | PPC_FEATURE_NO_TB,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 16,
 		.dcache_bsize		= 16,
 		.machine_check		= machine_check_4xx,
@@ -1106,6 +1175,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "403G ??",
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 16,
 		.dcache_bsize		= 16,
 		.machine_check		= machine_check_4xx,
@@ -1118,6 +1188,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1130,6 +1201,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1142,6 +1214,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1154,6 +1227,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1166,6 +1240,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1178,6 +1253,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1190,6 +1266,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1202,6 +1279,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1213,6 +1291,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "405LP",
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1225,6 +1304,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1237,6 +1317,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1249,6 +1330,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1261,6 +1343,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1273,6 +1356,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1286,6 +1370,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1298,6 +1383,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1312,6 +1398,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "440GR Rev. A",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1323,6 +1410,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "440EP Rev. A",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_440ep,
@@ -1335,6 +1423,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "440GR Rev. B",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1346,6 +1435,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "440EP Rev. C",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_440ep,
@@ -1358,6 +1448,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "440EP Rev. B",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_440ep,
@@ -1370,6 +1461,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "440GRX",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_440grx,
@@ -1382,6 +1474,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "440EPX",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_440epx,
@@ -1394,6 +1487,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "440GP Rev. B",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1405,6 +1499,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "440GP Rev. C",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1416,6 +1511,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "440GX Rev. A",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_440gx,
@@ -1428,6 +1524,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "440GX Rev. B",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_440gx,
@@ -1440,6 +1537,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "440GX Rev. C",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_440gx,
@@ -1452,6 +1550,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "440GX Rev. F",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_440gx,
@@ -1464,6 +1563,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "440SP Rev. A",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1475,6 +1575,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name               = "440SPe Rev. A",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features      = COMMON_USER_BOOKE,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize           = 32,
 		.dcache_bsize           = 32,
 		.cpu_setup		= __setup_cpu_440spe,
@@ -1487,6 +1588,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "440SPe Rev. B",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_440spe,
@@ -1499,6 +1601,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "440 in Virtex-5 FXT",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_440x5,
@@ -1509,8 +1612,9 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.pvr_mask		= 0xffff0002,
 		.pvr_value		= 0x13020002,
 		.cpu_name		= "460EX",
-		.cpu_features		= CPU_FTRS_44X,
+		.cpu_features		= CPU_FTRS_440x6,
 		.cpu_user_features	= COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_460ex,
@@ -1521,8 +1625,9 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.pvr_mask		= 0xffff0002,
 		.pvr_value		= 0x13020000,
 		.cpu_name		= "460GT",
-		.cpu_features		= CPU_FTRS_44X,
+		.cpu_features		= CPU_FTRS_440x6,
 		.cpu_user_features	= COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_460gt,
@@ -1535,6 +1640,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "(generic 44x PPC)",
 		.cpu_features		= CPU_FTRS_44X,
 		.cpu_user_features	= COMMON_USER_BOOKE,
+		.mmu_features		= MMU_FTR_TYPE_44x,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_4xx,
@@ -1551,6 +1657,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_user_features	= COMMON_USER_BOOKE |
 			PPC_FEATURE_HAS_EFP_SINGLE |
 			PPC_FEATURE_UNIFIED_CACHE,
+		.mmu_features		= MMU_FTR_TYPE_FSL_E,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_e200,
 		.platform		= "ppc5554",
@@ -1565,6 +1672,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 			PPC_FEATURE_HAS_SPE_COMP |
 			PPC_FEATURE_HAS_EFP_SINGLE_COMP |
 			PPC_FEATURE_UNIFIED_CACHE,
+		.mmu_features		= MMU_FTR_TYPE_FSL_E,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_e200,
 		.platform		= "ppc5554",
@@ -1577,6 +1685,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_user_features	= COMMON_USER_BOOKE |
 			PPC_FEATURE_HAS_EFP_SINGLE |
 			PPC_FEATURE_UNIFIED_CACHE,
+		.mmu_features		= MMU_FTR_TYPE_FSL_E,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_e200,
 		.platform		= "ppc5554",
@@ -1591,6 +1700,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_user_features	= COMMON_USER_BOOKE |
 			PPC_FEATURE_HAS_SPE_COMP |
 			PPC_FEATURE_HAS_EFP_SINGLE_COMP,
+		.mmu_features		= MMU_FTR_TYPE_FSL_E,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -1608,6 +1718,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 			PPC_FEATURE_HAS_SPE_COMP |
 			PPC_FEATURE_HAS_EFP_SINGLE_COMP |
 			PPC_FEATURE_HAS_EFP_DOUBLE_COMP,
+		.mmu_features		= MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
@@ -1622,6 +1733,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "e500mc",
 		.cpu_features		= CPU_FTRS_E500MC,
 		.cpu_user_features	= COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+		.mmu_features		= MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS,
 		.icache_bsize		= 64,
 		.dcache_bsize		= 64,
 		.num_pmcs		= 4,
@@ -1638,6 +1750,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_user_features	= COMMON_USER_BOOKE |
 			PPC_FEATURE_HAS_SPE_COMP |
 			PPC_FEATURE_HAS_EFP_SINGLE_COMP,
+		.mmu_features		= MMU_FTR_TYPE_FSL_E,
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.machine_check		= machine_check_e500,
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 3a6eaa876ee1..1c5c8a6fc129 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -120,6 +120,26 @@ static inline void dma_direct_unmap_page(struct device *dev,
 {
 }
 
+#ifdef CONFIG_NOT_COHERENT_CACHE
+static inline void dma_direct_sync_sg(struct device *dev,
+		struct scatterlist *sgl, int nents,
+		enum dma_data_direction direction)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
+}
+
+static inline void dma_direct_sync_single_range(struct device *dev,
+		dma_addr_t dma_handle, unsigned long offset, size_t size,
+		enum dma_data_direction direction)
+{
+	__dma_sync(bus_to_virt(dma_handle+offset), size, direction);
+}
+#endif
+
 struct dma_mapping_ops dma_direct_ops = {
 	.alloc_coherent	= dma_direct_alloc_coherent,
 	.free_coherent	= dma_direct_free_coherent,
@@ -128,5 +148,11 @@ struct dma_mapping_ops dma_direct_ops = {
 	.dma_supported	= dma_direct_dma_supported,
 	.map_page	= dma_direct_map_page,
 	.unmap_page	= dma_direct_unmap_page,
+#ifdef CONFIG_NOT_COHERENT_CACHE
+	.sync_single_range_for_cpu 	= dma_direct_sync_single_range,
+	.sync_single_range_for_device 	= dma_direct_sync_single_range,
+	.sync_sg_for_cpu 		= dma_direct_sync_sg,
+	.sync_sg_for_device 		= dma_direct_sync_sg,
+#endif
 };
 EXPORT_SYMBOL(dma_direct_ops);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 7ecc0d1855c3..6f7eb7e00c79 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -1162,39 +1162,17 @@ machine_check_in_rtas:
 #ifdef CONFIG_DYNAMIC_FTRACE
 _GLOBAL(mcount)
 _GLOBAL(_mcount)
-	stwu	r1,-48(r1)
-	stw	r3, 12(r1)
-	stw	r4, 16(r1)
-	stw	r5, 20(r1)
-	stw	r6, 24(r1)
-	mflr	r3
-	stw	r7, 28(r1)
-	mfcr	r5
-	stw	r8, 32(r1)
-	stw	r9, 36(r1)
-	stw	r10,40(r1)
-	stw	r3, 44(r1)
-	stw	r5, 8(r1)
-	subi	r3, r3, MCOUNT_INSN_SIZE
-	.globl mcount_call
-mcount_call:
-	bl	ftrace_stub
-	nop
-	lwz	r6, 8(r1)
-	lwz	r0, 44(r1)
-	lwz	r3, 12(r1)
+	/*
+	 * It is required that _mcount on PPC32 must preserve the
+	 * link register. But we have r0 to play with. We use r0
+	 * to push the return address back to the caller of mcount
+	 * into the ctr register, restore the link register and
+	 * then jump back using the ctr register.
+	 */
+	mflr	r0
 	mtctr	r0
-	lwz	r4, 16(r1)
-	mtcr	r6
-	lwz	r5, 20(r1)
-	lwz	r6, 24(r1)
-	lwz	r0, 52(r1)
-	lwz	r7, 28(r1)
-	lwz	r8, 32(r1)
+	lwz	r0, 4(r1)
 	mtlr	r0
-	lwz	r9, 36(r1)
-	lwz	r10,40(r1)
-	addi	r1, r1, 48
 	bctr
 
 _GLOBAL(ftrace_caller)
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index e0bcf9354286..383ed6eb0085 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -894,18 +894,6 @@ _GLOBAL(enter_prom)
 #ifdef CONFIG_DYNAMIC_FTRACE
 _GLOBAL(mcount)
 _GLOBAL(_mcount)
-	/* Taken from output of objdump from lib64/glibc */
-	mflr	r3
-	stdu	r1, -112(r1)
-	std	r3, 128(r1)
-	subi	r3, r3, MCOUNT_INSN_SIZE
-	.globl mcount_call
-mcount_call:
-	bl	ftrace_stub
-	nop
-	ld	r0, 128(r1)
-	mtlr	r0
-	addi	r1, r1, 112
 	blr
 
 _GLOBAL(ftrace_caller)
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index f4b006ed0ab1..5355244c99ff 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -9,22 +9,30 @@
 
 #include <linux/spinlock.h>
 #include <linux/hardirq.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <linux/list.h>
 
 #include <asm/cacheflush.h>
+#include <asm/code-patching.h>
 #include <asm/ftrace.h>
 
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(fmt , ...)	do { } while (0)
+#endif
 
-static unsigned int ftrace_nop = 0x60000000;
+static unsigned int ftrace_nop = PPC_NOP_INSTR;
 
 #ifdef CONFIG_PPC32
 # define GET_ADDR(addr) addr
 #else
 /* PowerPC64's functions are data that points to the functions */
-# define GET_ADDR(addr) *(unsigned long *)addr
+# define GET_ADDR(addr) (*(unsigned long *)addr)
 #endif
 
 
@@ -33,12 +41,12 @@ static unsigned int ftrace_calc_offset(long ip, long addr)
 	return (int)(addr - ip);
 }
 
-unsigned char *ftrace_nop_replace(void)
+static unsigned char *ftrace_nop_replace(void)
 {
 	return (char *)&ftrace_nop;
 }
 
-unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 {
 	static unsigned int op;
 
@@ -68,49 +76,422 @@ unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 # define _ASM_PTR	" .long "
 #endif
 
-int
+static int
 ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 		   unsigned char *new_code)
 {
-	unsigned replaced;
-	unsigned old = *(unsigned *)old_code;
-	unsigned new = *(unsigned *)new_code;
-	int faulted = 0;
+	unsigned char replaced[MCOUNT_INSN_SIZE];
 
 	/*
 	 * Note: Due to modules and __init, code can
 	 *  disappear and change, we need to protect against faulting
-	 *  as well as code changing.
+	 *  as well as code changing. We do this by using the
+	 *  probe_kernel_* functions.
 	 *
 	 * No real locking needed, this code is run through
-	 * kstop_machine.
+	 * kstop_machine, or before SMP starts.
 	 */
-	asm volatile (
-		"1: lwz		%1, 0(%2)\n"
-		"   cmpw	%1, %5\n"
-		"   bne		2f\n"
-		"   stwu	%3, 0(%2)\n"
-		"2:\n"
-		".section .fixup, \"ax\"\n"
-		"3:	li %0, 1\n"
-		"	b 2b\n"
-		".previous\n"
-		".section __ex_table,\"a\"\n"
-		_ASM_ALIGN "\n"
-		_ASM_PTR "1b, 3b\n"
-		".previous"
-		: "=r"(faulted), "=r"(replaced)
-		: "r"(ip), "r"(new),
-		  "0"(faulted), "r"(old)
-		: "memory");
-
-	if (replaced != old && replaced != new)
-		faulted = 2;
-
-	if (!faulted)
-		flush_icache_range(ip, ip + 8);
-
-	return faulted;
+
+	/* read the text we want to modify */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure it is what we expect it to be */
+	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
+		return -EINVAL;
+
+	/* replace the text with the new text */
+	if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	flush_icache_range(ip, ip + 8);
+
+	return 0;
+}
+
+/*
+ * Helper functions that are the same for both PPC64 and PPC32.
+ */
+static int test_24bit_addr(unsigned long ip, unsigned long addr)
+{
+
+	/* use the create_branch to verify that this offset can be branched */
+	return create_branch((unsigned int *)ip, addr, 0);
+}
+
+static int is_bl_op(unsigned int op)
+{
+	return (op & 0xfc000003) == 0x48000001;
+}
+
+static unsigned long find_bl_target(unsigned long ip, unsigned int op)
+{
+	static int offset;
+
+	offset = (op & 0x03fffffc);
+	/* make it signed */
+	if (offset & 0x02000000)
+		offset |= 0xfe000000;
+
+	return ip + (long)offset;
+}
+
+#ifdef CONFIG_PPC64
+static int
+__ftrace_make_nop(struct module *mod,
+		  struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned int op;
+	unsigned int jmp[5];
+	unsigned long ptr;
+	unsigned long ip = rec->ip;
+	unsigned long tramp;
+	int offset;
+
+	/* read where this goes */
+	if (probe_kernel_read(&op, (void *)ip, sizeof(int)))
+		return -EFAULT;
+
+	/* Make sure that that this is still a 24bit jump */
+	if (!is_bl_op(op)) {
+		printk(KERN_ERR "Not expected bl: opcode is %x\n", op);
+		return -EINVAL;
+	}
+
+	/* lets find where the pointer goes */
+	tramp = find_bl_target(ip, op);
+
+	/*
+	 * On PPC64 the trampoline looks like:
+	 * 0x3d, 0x82, 0x00, 0x00,    addis   r12,r2, <high>
+	 * 0x39, 0x8c, 0x00, 0x00,    addi    r12,r12, <low>
+	 *   Where the bytes 2,3,6 and 7 make up the 32bit offset
+	 *   to the TOC that holds the pointer.
+	 *   to jump to.
+	 * 0xf8, 0x41, 0x00, 0x28,    std     r2,40(r1)
+	 * 0xe9, 0x6c, 0x00, 0x20,    ld      r11,32(r12)
+	 *   The actually address is 32 bytes from the offset
+	 *   into the TOC.
+	 * 0xe8, 0x4c, 0x00, 0x28,    ld      r2,40(r12)
+	 */
+
+	DEBUGP("ip:%lx jumps to %lx r2: %lx", ip, tramp, mod->arch.toc);
+
+	/* Find where the trampoline jumps to */
+	if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) {
+		printk(KERN_ERR "Failed to read %lx\n", tramp);
+		return -EFAULT;
+	}
+
+	DEBUGP(" %08x %08x", jmp[0], jmp[1]);
+
+	/* verify that this is what we expect it to be */
+	if (((jmp[0] & 0xffff0000) != 0x3d820000) ||
+	    ((jmp[1] & 0xffff0000) != 0x398c0000) ||
+	    (jmp[2] != 0xf8410028) ||
+	    (jmp[3] != 0xe96c0020) ||
+	    (jmp[4] != 0xe84c0028)) {
+		printk(KERN_ERR "Not a trampoline\n");
+		return -EINVAL;
+	}
+
+	offset = (unsigned)((unsigned short)jmp[0]) << 16 |
+		(unsigned)((unsigned short)jmp[1]);
+
+	DEBUGP(" %x ", offset);
+
+	/* get the address this jumps too */
+	tramp = mod->arch.toc + offset + 32;
+	DEBUGP("toc: %lx", tramp);
+
+	if (probe_kernel_read(jmp, (void *)tramp, 8)) {
+		printk(KERN_ERR "Failed to read %lx\n", tramp);
+		return -EFAULT;
+	}
+
+	DEBUGP(" %08x %08x\n", jmp[0], jmp[1]);
+
+	ptr = ((unsigned long)jmp[0] << 32) + jmp[1];
+
+	/* This should match what was called */
+	if (ptr != GET_ADDR(addr)) {
+		printk(KERN_ERR "addr does not match %lx\n", ptr);
+		return -EINVAL;
+	}
+
+	/*
+	 * We want to nop the line, but the next line is
+	 *  0xe8, 0x41, 0x00, 0x28   ld r2,40(r1)
+	 * This needs to be turned to a nop too.
+	 */
+	if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	if (op != 0xe8410028) {
+		printk(KERN_ERR "Next line is not ld! (%08x)\n", op);
+		return -EINVAL;
+	}
+
+	/*
+	 * Milton Miller pointed out that we can not blindly do nops.
+	 * If a task was preempted when calling a trace function,
+	 * the nops will remove the way to restore the TOC in r2
+	 * and the r2 TOC will get corrupted.
+	 */
+
+	/*
+	 * Replace:
+	 *   bl <tramp>  <==== will be replaced with "b 1f"
+	 *   ld r2,40(r1)
+	 *  1:
+	 */
+	op = 0x48000008;	/* b +8 */
+
+	if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+
+	flush_icache_range(ip, ip + 8);
+
+	return 0;
+}
+
+#else /* !PPC64 */
+static int
+__ftrace_make_nop(struct module *mod,
+		  struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned int op;
+	unsigned int jmp[4];
+	unsigned long ip = rec->ip;
+	unsigned long tramp;
+
+	if (probe_kernel_read(&op, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure that that this is still a 24bit jump */
+	if (!is_bl_op(op)) {
+		printk(KERN_ERR "Not expected bl: opcode is %x\n", op);
+		return -EINVAL;
+	}
+
+	/* lets find where the pointer goes */
+	tramp = find_bl_target(ip, op);
+
+	/*
+	 * On PPC32 the trampoline looks like:
+	 *  0x3d, 0x60, 0x00, 0x00  lis r11,sym@ha
+	 *  0x39, 0x6b, 0x00, 0x00  addi r11,r11,sym@l
+	 *  0x7d, 0x69, 0x03, 0xa6  mtctr r11
+	 *  0x4e, 0x80, 0x04, 0x20  bctr
+	 */
+
+	DEBUGP("ip:%lx jumps to %lx", ip, tramp);
+
+	/* Find where the trampoline jumps to */
+	if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) {
+		printk(KERN_ERR "Failed to read %lx\n", tramp);
+		return -EFAULT;
+	}
+
+	DEBUGP(" %08x %08x ", jmp[0], jmp[1]);
+
+	/* verify that this is what we expect it to be */
+	if (((jmp[0] & 0xffff0000) != 0x3d600000) ||
+	    ((jmp[1] & 0xffff0000) != 0x396b0000) ||
+	    (jmp[2] != 0x7d6903a6) ||
+	    (jmp[3] != 0x4e800420)) {
+		printk(KERN_ERR "Not a trampoline\n");
+		return -EINVAL;
+	}
+
+	tramp = (jmp[1] & 0xffff) |
+		((jmp[0] & 0xffff) << 16);
+	if (tramp & 0x8000)
+		tramp -= 0x10000;
+
+	DEBUGP(" %x ", tramp);
+
+	if (tramp != addr) {
+		printk(KERN_ERR
+		       "Trampoline location %08lx does not match addr\n",
+		       tramp);
+		return -EINVAL;
+	}
+
+	op = PPC_NOP_INSTR;
+
+	if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	flush_icache_range(ip, ip + 8);
+
+	return 0;
+}
+#endif /* PPC64 */
+
+int ftrace_make_nop(struct module *mod,
+		    struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char *old, *new;
+	unsigned long ip = rec->ip;
+
+	/*
+	 * If the calling address is more that 24 bits away,
+	 * then we had to use a trampoline to make the call.
+	 * Otherwise just update the call site.
+	 */
+	if (test_24bit_addr(ip, addr)) {
+		/* within range */
+		old = ftrace_call_replace(ip, addr);
+		new = ftrace_nop_replace();
+		return ftrace_modify_code(ip, old, new);
+	}
+
+	/*
+	 * Out of range jumps are called from modules.
+	 * We should either already have a pointer to the module
+	 * or it has been passed in.
+	 */
+	if (!rec->arch.mod) {
+		if (!mod) {
+			printk(KERN_ERR "No module loaded addr=%lx\n",
+			       addr);
+			return -EFAULT;
+		}
+		rec->arch.mod = mod;
+	} else if (mod) {
+		if (mod != rec->arch.mod) {
+			printk(KERN_ERR
+			       "Record mod %p not equal to passed in mod %p\n",
+			       rec->arch.mod, mod);
+			return -EINVAL;
+		}
+		/* nothing to do if mod == rec->arch.mod */
+	} else
+		mod = rec->arch.mod;
+
+	return __ftrace_make_nop(mod, rec, addr);
+
+}
+
+#ifdef CONFIG_PPC64
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned int op[2];
+	unsigned long ip = rec->ip;
+
+	/* read where this goes */
+	if (probe_kernel_read(op, (void *)ip, MCOUNT_INSN_SIZE * 2))
+		return -EFAULT;
+
+	/*
+	 * It should be pointing to two nops or
+	 *  b +8; ld r2,40(r1)
+	 */
+	if (((op[0] != 0x48000008) || (op[1] != 0xe8410028)) &&
+	    ((op[0] != PPC_NOP_INSTR) || (op[1] != PPC_NOP_INSTR))) {
+		printk(KERN_ERR "Expected NOPs but have %x %x\n", op[0], op[1]);
+		return -EINVAL;
+	}
+
+	/* If we never set up a trampoline to ftrace_caller, then bail */
+	if (!rec->arch.mod->arch.tramp) {
+		printk(KERN_ERR "No ftrace trampoline\n");
+		return -EINVAL;
+	}
+
+	/* create the branch to the trampoline */
+	op[0] = create_branch((unsigned int *)ip,
+			      rec->arch.mod->arch.tramp, BRANCH_SET_LINK);
+	if (!op[0]) {
+		printk(KERN_ERR "REL24 out of range!\n");
+		return -EINVAL;
+	}
+
+	/* ld r2,40(r1) */
+	op[1] = 0xe8410028;
+
+	DEBUGP("write to %lx\n", rec->ip);
+
+	if (probe_kernel_write((void *)ip, op, MCOUNT_INSN_SIZE * 2))
+		return -EPERM;
+
+	flush_icache_range(ip, ip + 8);
+
+	return 0;
+}
+#else
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned int op;
+	unsigned long ip = rec->ip;
+
+	/* read where this goes */
+	if (probe_kernel_read(&op, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* It should be pointing to a nop */
+	if (op != PPC_NOP_INSTR) {
+		printk(KERN_ERR "Expected NOP but have %x\n", op);
+		return -EINVAL;
+	}
+
+	/* If we never set up a trampoline to ftrace_caller, then bail */
+	if (!rec->arch.mod->arch.tramp) {
+		printk(KERN_ERR "No ftrace trampoline\n");
+		return -EINVAL;
+	}
+
+	/* create the branch to the trampoline */
+	op = create_branch((unsigned int *)ip,
+			   rec->arch.mod->arch.tramp, BRANCH_SET_LINK);
+	if (!op) {
+		printk(KERN_ERR "REL24 out of range!\n");
+		return -EINVAL;
+	}
+
+	DEBUGP("write to %lx\n", rec->ip);
+
+	if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	flush_icache_range(ip, ip + 8);
+
+	return 0;
+}
+#endif /* CONFIG_PPC64 */
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char *old, *new;
+	unsigned long ip = rec->ip;
+
+	/*
+	 * If the calling address is more that 24 bits away,
+	 * then we had to use a trampoline to make the call.
+	 * Otherwise just update the call site.
+	 */
+	if (test_24bit_addr(ip, addr)) {
+		/* within range */
+		old = ftrace_nop_replace();
+		new = ftrace_call_replace(ip, addr);
+		return ftrace_modify_code(ip, old, new);
+	}
+
+	/*
+	 * Out of range jumps are called from modules.
+	 * Being that we are converting from nop, it had better
+	 * already have a module defined.
+	 */
+	if (!rec->arch.mod) {
+		printk(KERN_ERR "No module loaded\n");
+		return -EINVAL;
+	}
+
+	return __ftrace_make_call(rec, addr);
 }
 
 int ftrace_update_ftrace_func(ftrace_func_t func)
@@ -128,10 +509,10 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 
 int __init ftrace_dyn_arch_init(void *data)
 {
-	/* This is running in kstop_machine */
+	/* caller expects data to be zero */
+	unsigned long *p = data;
 
-	ftrace_mcount_set(data);
+	*p = 0;
 
 	return 0;
 }
-
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 0c326823c6d4..a1c4cfd25ded 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -31,6 +31,7 @@
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
+#include <asm/bug.h>
 
 /* 601 only have IBAT; cr0.eq is set on 601 when using this macro */
 #define LOAD_BAT(n, reg, RA, RB)	\
@@ -182,7 +183,8 @@ __after_mmu_off:
 	bl	reloc_offset
 	mr	r26,r3
 	addis	r4,r3,KERNELBASE@h	/* current address of _start */
-	cmpwi	0,r4,0			/* are we already running at 0? */
+	lis	r5,PHYSICAL_START@h
+	cmplw	0,r4,r5			/* already running at PHYSICAL_START? */
 	bne	relocate_kernel
 /*
  * we now have the 1st 16M of ram mapped with the bats.
@@ -810,13 +812,13 @@ giveup_altivec:
 
 /*
  * This code is jumped to from the startup code to copy
- * the kernel image to physical address 0.
+ * the kernel image to physical address PHYSICAL_START.
  */
 relocate_kernel:
 	addis	r9,r26,klimit@ha	/* fetch klimit */
 	lwz	r25,klimit@l(r9)
 	addis	r25,r25,-KERNELBASE@h
-	li	r3,0			/* Destination base address */
+	lis	r3,PHYSICAL_START@h	/* Destination base address */
 	li	r6,0			/* Destination offset */
 	li	r5,0x4000		/* # bytes of memory to copy */
 	bl	copy_and_flush		/* copy the first 0x4000 bytes */
@@ -989,12 +991,12 @@ load_up_mmu:
 	LOAD_BAT(1,r3,r4,r5)
 	LOAD_BAT(2,r3,r4,r5)
 	LOAD_BAT(3,r3,r4,r5)
-BEGIN_FTR_SECTION
+BEGIN_MMU_FTR_SECTION
 	LOAD_BAT(4,r3,r4,r5)
 	LOAD_BAT(5,r3,r4,r5)
 	LOAD_BAT(6,r3,r4,r5)
 	LOAD_BAT(7,r3,r4,r5)
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
 	blr
 
 /*
@@ -1070,9 +1072,14 @@ start_here:
 	RFI
 
 /*
+ * void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next);
+ *
  * Set up the segment registers for a new context.
  */
-_ENTRY(set_context)
+_ENTRY(switch_mmu_context)
+	lwz	r3,MMCONTEXTID(r4)
+	cmpwi	cr0,r3,0
+	blt-	4f
 	mulli	r3,r3,897	/* multiply context by skew factor */
 	rlwinm	r3,r3,4,8,27	/* VSID = (context & 0xfffff) << 4 */
 	addis	r3,r3,0x6000	/* Set Ks, Ku bits */
@@ -1083,6 +1090,7 @@ _ENTRY(set_context)
 	/* Context switch the PTE pointer for the Abatron BDI2000.
 	 * The PGDIR is passed as second argument.
 	 */
+	lwz	r4,MM_PGD(r4)
 	lis	r5, KERNELBASE@h
 	lwz	r5, 0xf0(r5)
 	stw	r4, 0x4(r5)
@@ -1098,6 +1106,9 @@ _ENTRY(set_context)
 	sync
 	isync
 	blr
+4:	trap
+	EMIT_BUG_ENTRY 4b,__FILE__,__LINE__,0
+	blr
 
 /*
  * An undocumented "feature" of 604e requires that the v bit
@@ -1131,7 +1142,7 @@ clear_bats:
 	mtspr	SPRN_IBAT2L,r10
 	mtspr	SPRN_IBAT3U,r10
 	mtspr	SPRN_IBAT3L,r10
-BEGIN_FTR_SECTION
+BEGIN_MMU_FTR_SECTION
 	/* Here's a tweak: at this point, CPU setup have
 	 * not been called yet, so HIGH_BAT_EN may not be
 	 * set in HID0 for the 745x processors. However, it
@@ -1154,7 +1165,7 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_IBAT6L,r10
 	mtspr	SPRN_IBAT7U,r10
 	mtspr	SPRN_IBAT7L,r10
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
 	blr
 
 flush_tlbs:
@@ -1178,11 +1189,11 @@ mmu_off:
 
 /*
  * Use the first pair of BAT registers to map the 1st 16MB
- * of RAM to KERNELBASE.  From this point on we can't safely
+ * of RAM to PAGE_OFFSET.  From this point on we can't safely
  * call OF any more.
  */
 initial_bats:
-	lis	r11,KERNELBASE@h
+	lis	r11,PAGE_OFFSET@h
 	mfspr	r9,SPRN_PVR
 	rlwinm	r9,r9,16,16,31		/* r9 = 1 for 601, 4 for 604 */
 	cmpwi	0,r9,1
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index f3a1ea9d7fe4..b56fecc93a16 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -69,6 +69,17 @@ _ENTRY(_start);
 	li	r24,0		/* CPU number */
 
 /*
+ * In case the firmware didn't do it, we apply some workarounds
+ * that are good for all 440 core variants here
+ */
+	mfspr	r3,SPRN_CCR0
+	rlwinm	r3,r3,0,0,27	/* disable icache prefetch */
+	isync
+	mtspr	SPRN_CCR0,r3
+	isync
+	sync
+
+/*
  * Set up the initial MMU state
  *
  * We are still executing code at the virtual address
@@ -391,12 +402,14 @@ interrupt_base:
 	rlwimi	r13,r12,10,30,30
 
 	/* Load the PTE */
-	rlwinm 	r12, r10, 13, 19, 29	/* Compute pgdir/pmd offset */
+	/* Compute pgdir/pmd offset */
+	rlwinm  r12, r10, PPC44x_PGD_OFF_SHIFT, PPC44x_PGD_OFF_MASK_BIT, 29
 	lwzx	r11, r12, r11		/* Get pgd/pmd entry */
 	rlwinm.	r12, r11, 0, 0, 20	/* Extract pt base address */
 	beq	2f			/* Bail if no table */
 
-	rlwimi	r12, r10, 23, 20, 28	/* Compute pte address */
+	/* Compute pte address */
+	rlwimi  r12, r10, PPC44x_PTE_ADD_SHIFT, PPC44x_PTE_ADD_MASK_BIT, 28
 	lwz	r11, 0(r12)		/* Get high word of pte entry */
 	lwz	r12, 4(r12)		/* Get low word of pte entry */
 
@@ -485,12 +498,14 @@ tlb_44x_patch_hwater_D:
 	/* Make up the required permissions */
 	li	r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_HWEXEC
 
-	rlwinm	r12, r10, 13, 19, 29	/* Compute pgdir/pmd offset */
+	/* Compute pgdir/pmd offset */
+	rlwinm 	r12, r10, PPC44x_PGD_OFF_SHIFT, PPC44x_PGD_OFF_MASK_BIT, 29
 	lwzx	r11, r12, r11		/* Get pgd/pmd entry */
 	rlwinm.	r12, r11, 0, 0, 20	/* Extract pt base address */
 	beq	2f			/* Bail if no table */
 
-	rlwimi	r12, r10, 23, 20, 28	/* Compute pte address */
+	/* Compute pte address */
+	rlwimi	r12, r10, PPC44x_PTE_ADD_SHIFT, PPC44x_PTE_ADD_MASK_BIT, 28
 	lwz	r11, 0(r12)		/* Get high word of pte entry */
 	lwz	r12, 4(r12)		/* Get low word of pte entry */
 
@@ -554,15 +569,16 @@ tlb_44x_patch_hwater_I:
  */
 finish_tlb_load:
 	/* Combine RPN & ERPN an write WS 0 */
-	rlwimi	r11,r12,0,0,19
+	rlwimi	r11,r12,0,0,31-PAGE_SHIFT
 	tlbwe	r11,r13,PPC44x_TLB_XLAT
 
 	/*
 	 * Create WS1. This is the faulting address (EPN),
 	 * page size, and valid flag.
 	 */
-	li	r11,PPC44x_TLB_VALID | PPC44x_TLB_4K
-	rlwimi	r10,r11,0,20,31			/* Insert valid and page size*/
+	li	r11,PPC44x_TLB_VALID | PPC44x_TLBE_SIZE
+	/* Insert valid and page size */
+	rlwimi	r10,r11,0,PPC44x_PTE_ADD_MASK_BIT,31
 	tlbwe	r10,r13,PPC44x_TLB_PAGEID	/* Write PAGEID */
 
 	/* And WS 2 */
@@ -634,12 +650,12 @@ _GLOBAL(set_context)
  * goes at the beginning of the data segment, which is page-aligned.
  */
 	.data
-	.align	12
+	.align	PAGE_SHIFT
 	.globl	sdata
 sdata:
 	.globl	empty_zero_page
 empty_zero_page:
-	.space	4096
+	.space	PAGE_SIZE
 
 /*
  * To support >32-bit physical addresses, we use an 8KB pgdir.
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 590304c24dad..11b549acc034 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -92,6 +92,7 @@ _ENTRY(_start);
  * if needed
  */
 
+_ENTRY(__early_start)
 /* 1. Find the index of the entry we're executing in */
 	bl	invstr				/* Find our address */
 invstr:	mflr	r6				/* Make it accessible */
@@ -235,36 +236,40 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	tlbivax 0,r9
 	TLBSYNC
 
+/* The mapping only needs to be cache-coherent on SMP */
+#ifdef CONFIG_SMP
+#define M_IF_SMP	MAS2_M
+#else
+#define M_IF_SMP	0
+#endif
+
 /* 6. Setup KERNELBASE mapping in TLB1[0] */
 	lis	r6,0x1000		/* Set MAS0(TLBSEL) = TLB1(1), ESEL = 0 */
 	mtspr	SPRN_MAS0,r6
 	lis	r6,(MAS1_VALID|MAS1_IPROT)@h
 	ori	r6,r6,(MAS1_TSIZE(BOOKE_PAGESZ_64M))@l
 	mtspr	SPRN_MAS1,r6
-	li	r7,0
-	lis	r6,PAGE_OFFSET@h
-	ori	r6,r6,PAGE_OFFSET@l
-	rlwimi	r6,r7,0,20,31
+	lis	r6,MAS2_VAL(PAGE_OFFSET, BOOKE_PAGESZ_64M, M_IF_SMP)@h
+	ori	r6,r6,MAS2_VAL(PAGE_OFFSET, BOOKE_PAGESZ_64M, M_IF_SMP)@l
 	mtspr	SPRN_MAS2,r6
 	mtspr	SPRN_MAS3,r8
 	tlbwe
 
 /* 7. Jump to KERNELBASE mapping */
-	lis	r6,KERNELBASE@h
-	ori	r6,r6,KERNELBASE@l
-	rlwimi	r6,r7,0,20,31
+	lis	r6,(KERNELBASE & ~0xfff)@h
+	ori	r6,r6,(KERNELBASE & ~0xfff)@l
 	lis	r7,MSR_KERNEL@h
 	ori	r7,r7,MSR_KERNEL@l
 	bl	1f			/* Find our address */
 1:	mflr	r9
 	rlwimi	r6,r9,0,20,31
-	addi	r6,r6,24
+	addi	r6,r6,(2f - 1b)
 	mtspr	SPRN_SRR0,r6
 	mtspr	SPRN_SRR1,r7
 	rfi				/* start execution out of TLB1[0] entry */
 
 /* 8. Clear out the temp mapping */
-	lis	r7,0x1000	/* Set MAS0(TLBSEL) = 1 */
+2:	lis	r7,0x1000	/* Set MAS0(TLBSEL) = 1 */
 	rlwimi	r7,r5,16,4,15	/* Setup MAS0 = TLBSEL | ESEL(r5) */
 	mtspr	SPRN_MAS0,r7
 	tlbre
@@ -344,6 +349,15 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	mtspr	SPRN_DBSR,r2
 #endif
 
+#ifdef CONFIG_SMP
+	/* Check to see if we're the second processor, and jump
+	 * to the secondary_start code if so
+	 */
+	mfspr	r24,SPRN_PIR
+	cmpwi	r24,0
+	bne	__secondary_start
+#endif
+
 	/*
 	 * This is where the main kernel code starts.
 	 */
@@ -685,12 +699,13 @@ interrupt_base:
 	/* SPE Floating Point Data */
 #ifdef CONFIG_SPE
 	EXCEPTION(0x2030, SPEFloatingPointData, SPEFloatingPointException, EXC_XFER_EE);
-#else
-	EXCEPTION(0x2040, SPEFloatingPointData, unknown_exception, EXC_XFER_EE)
-#endif /* CONFIG_SPE */
 
 	/* SPE Floating Point Round */
+	EXCEPTION(0x2050, SPEFloatingPointRound, SPEFloatingPointRoundException, EXC_XFER_EE)
+#else
+	EXCEPTION(0x2040, SPEFloatingPointData, unknown_exception, EXC_XFER_EE)
 	EXCEPTION(0x2050, SPEFloatingPointRound, unknown_exception, EXC_XFER_EE)
+#endif /* CONFIG_SPE */
 
 	/* Performance Monitor */
 	EXCEPTION(0x2060, PerformanceMonitor, performance_monitor_exception, EXC_XFER_STD)
@@ -735,6 +750,9 @@ finish_tlb_load:
 #else
 	rlwimi	r12, r11, 26, 27, 31	/* extract WIMGE from pte */
 #endif
+#ifdef CONFIG_SMP
+	ori	r12, r12, MAS2_M
+#endif
 	mtspr	SPRN_MAS2, r12
 
 	li	r10, (_PAGE_HWEXEC | _PAGE_PRESENT)
@@ -746,15 +764,15 @@ finish_tlb_load:
 	iseleq	r12, r12, r10
 	
 #ifdef CONFIG_PTE_64BIT
-2:	rlwimi	r12, r13, 24, 0, 7	/* grab RPN[32:39] */
+	rlwimi	r12, r13, 24, 0, 7	/* grab RPN[32:39] */
 	rlwimi	r12, r11, 24, 8, 19	/* grab RPN[40:51] */
 	mtspr	SPRN_MAS3, r12
-BEGIN_FTR_SECTION
+BEGIN_MMU_FTR_SECTION
 	srwi	r10, r13, 8		/* grab RPN[8:31] */
 	mtspr	SPRN_MAS7, r10
-END_FTR_SECTION_IFSET(CPU_FTR_BIG_PHYS)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS)
 #else
-2:	rlwimi	r11, r12, 0, 20, 31	/* Extract RPN from PTE and merge with perms */
+	rlwimi	r11, r12, 0, 20, 31	/* Extract RPN from PTE and merge with perms */
 	mtspr	SPRN_MAS3, r11
 #endif
 #ifdef CONFIG_E200
@@ -1037,6 +1055,63 @@ _GLOBAL(flush_dcache_L1)
 
 	blr
 
+#ifdef CONFIG_SMP
+/* When we get here, r24 needs to hold the CPU # */
+	.globl __secondary_start
+__secondary_start:
+	lis	r3,__secondary_hold_acknowledge@h
+	ori	r3,r3,__secondary_hold_acknowledge@l
+	stw	r24,0(r3)
+
+	li	r3,0
+	mr	r4,r24		/* Why? */
+	bl	call_setup_cpu
+
+	lis	r3,tlbcam_index@ha
+	lwz	r3,tlbcam_index@l(r3)
+	mtctr	r3
+	li	r26,0		/* r26 safe? */
+
+	/* Load each CAM entry */
+1:	mr	r3,r26
+	bl	loadcam_entry
+	addi	r26,r26,1
+	bdnz	1b
+
+	/* get current_thread_info and current */
+	lis	r1,secondary_ti@ha
+	lwz	r1,secondary_ti@l(r1)
+	lwz	r2,TI_TASK(r1)
+
+	/* stack */
+	addi	r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
+	li	r0,0
+	stw	r0,0(r1)
+
+	/* ptr to current thread */
+	addi	r4,r2,THREAD	/* address of our thread_struct */
+	mtspr	SPRN_SPRG3,r4
+
+	/* Setup the defaults for TLB entries */
+	li	r4,(MAS4_TSIZED(BOOKE_PAGESZ_4K))@l
+	mtspr	SPRN_MAS4,r4
+
+	/* Jump to start_secondary */
+	lis	r4,MSR_KERNEL@h
+	ori	r4,r4,MSR_KERNEL@l
+	lis	r3,start_secondary@h
+	ori	r3,r3,start_secondary@l
+	mtspr	SPRN_SRR0,r3
+	mtspr	SPRN_SRR1,r4
+	sync
+	rfi
+	sync
+
+	.globl __secondary_hold_acknowledge
+__secondary_hold_acknowledge:
+	.long	-1
+#endif
+
 /*
  * We put a few things here that have to be page-aligned. This stuff
  * goes at the beginning of the data segment, which is page-aligned.
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index 64299d28f364..6e3f62493659 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -47,7 +47,7 @@
 #include <asm/abs_addr.h>
 
 static struct device ibmebus_bus_device = { /* fake "parent" device */
-	.bus_id = "ibmebus",
+	.init_name = "ibmebus",
 };
 
 struct bus_type ibmebus_bus_type;
@@ -231,6 +231,7 @@ void ibmebus_free_irq(u32 ist, void *dev_id)
 	unsigned int irq = irq_find_mapping(NULL, ist);
 
 	free_irq(irq, dev_id);
+	irq_dispose_mapping(irq);
 }
 EXPORT_SYMBOL(ibmebus_free_irq);
 
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 31982d05d81a..88d9c1d5e5fb 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -69,10 +69,15 @@ void cpu_idle(void)
 				smp_mb();
 				local_irq_disable();
 
+				/* Don't trace irqs off for idle */
+				stop_critical_timings();
+
 				/* check again after disabling irqs */
 				if (!need_resched() && !cpu_should_die())
 					ppc_md.power_save();
 
+				start_critical_timings();
+
 				local_irq_enable();
 				set_thread_flag(TIF_POLLING_NRFLAG);
 
diff --git a/arch/powerpc/kernel/init_task.c b/arch/powerpc/kernel/init_task.c
index 4c85b8d56478..688b329800bd 100644
--- a/arch/powerpc/kernel/init_task.c
+++ b/arch/powerpc/kernel/init_task.c
@@ -7,7 +7,6 @@
 #include <linux/mqueue.h>
 #include <asm/uaccess.h>
 
-static struct fs_struct init_fs = INIT_FS;
 static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
 static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
 struct mm_struct init_mm = INIT_MM(init_mm);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index ac222d0ab12e..23b8b5e36f98 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -237,7 +237,7 @@ void fixup_irqs(cpumask_t map)
 			mask = map;
 		}
 		if (irq_desc[irq].chip->set_affinity)
-			irq_desc[irq].chip->set_affinity(irq, mask);
+			irq_desc[irq].chip->set_affinity(irq, &mask);
 		else if (irq_desc[irq].action && !(warned++))
 			printk("Cannot set affinity for irq %i\n", irq);
 	}
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index de79915452c8..c9329786073b 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -96,9 +96,10 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p)
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)
 {
-	mutex_lock(&kprobe_mutex);
-	free_insn_slot(p->ainsn.insn, 0);
-	mutex_unlock(&kprobe_mutex);
+	if (p->ainsn.insn) {
+		free_insn_slot(p->ainsn.insn, 0);
+		p->ainsn.insn = NULL;
+	}
 }
 
 static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
@@ -316,7 +317,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	/*
 	 * It is possible to have multiple instances associated with a given
 	 * task either because an multiple functions in the call path
-	 * have a return probe installed on them, and/or more then one return
+	 * have a return probe installed on them, and/or more than one return
 	 * return probe was registered for a target function.
 	 *
 	 * We can handle this because:
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index ac2a21f45c75..b3abebb7ee64 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -13,13 +13,17 @@
 #include <linux/reboot.h>
 #include <linux/threads.h>
 #include <linux/lmb.h>
+#include <linux/of.h>
 #include <asm/machdep.h>
 #include <asm/prom.h>
+#include <asm/sections.h>
 
 void machine_crash_shutdown(struct pt_regs *regs)
 {
 	if (ppc_md.machine_crash_shutdown)
 		ppc_md.machine_crash_shutdown(regs);
+	else
+		default_machine_crash_shutdown(regs);
 }
 
 /*
@@ -31,11 +35,8 @@ int machine_kexec_prepare(struct kimage *image)
 {
 	if (ppc_md.machine_kexec_prepare)
 		return ppc_md.machine_kexec_prepare(image);
-	/*
-	 * Fail if platform doesn't provide its own machine_kexec_prepare
-	 * implementation.
-	 */
-	return -ENOSYS;
+	else
+		return default_machine_kexec_prepare(image);
 }
 
 void machine_kexec_cleanup(struct kimage *image)
@@ -52,13 +53,11 @@ void machine_kexec(struct kimage *image)
 {
 	if (ppc_md.machine_kexec)
 		ppc_md.machine_kexec(image);
-	else {
-		/*
-		 * Fall back to normal restart if platform doesn't provide
-		 * its own kexec function, and user insist to kexec...
-		 */
-		machine_restart(NULL);
-	}
+	else
+		default_machine_kexec(image);
+
+	/* Fall back to normal restart if we're still alive. */
+	machine_restart(NULL);
 	for(;;);
 }
 
@@ -118,3 +117,71 @@ int overlaps_crashkernel(unsigned long start, unsigned long size)
 {
 	return (start + size) > crashk_res.start && start <= crashk_res.end;
 }
+
+/* Values we need to export to the second kernel via the device tree. */
+static unsigned long kernel_end;
+static unsigned long crashk_size;
+
+static struct property kernel_end_prop = {
+	.name = "linux,kernel-end",
+	.length = sizeof(unsigned long),
+	.value = &kernel_end,
+};
+
+static struct property crashk_base_prop = {
+	.name = "linux,crashkernel-base",
+	.length = sizeof(unsigned long),
+	.value = &crashk_res.start,
+};
+
+static struct property crashk_size_prop = {
+	.name = "linux,crashkernel-size",
+	.length = sizeof(unsigned long),
+	.value = &crashk_size,
+};
+
+static void __init export_crashk_values(struct device_node *node)
+{
+	struct property *prop;
+
+	/* There might be existing crash kernel properties, but we can't
+	 * be sure what's in them, so remove them. */
+	prop = of_find_property(node, "linux,crashkernel-base", NULL);
+	if (prop)
+		prom_remove_property(node, prop);
+
+	prop = of_find_property(node, "linux,crashkernel-size", NULL);
+	if (prop)
+		prom_remove_property(node, prop);
+
+	if (crashk_res.start != 0) {
+		prom_add_property(node, &crashk_base_prop);
+		crashk_size = crashk_res.end - crashk_res.start + 1;
+		prom_add_property(node, &crashk_size_prop);
+	}
+}
+
+static int __init kexec_setup(void)
+{
+	struct device_node *node;
+	struct property *prop;
+
+	node = of_find_node_by_path("/chosen");
+	if (!node)
+		return -ENOENT;
+
+	/* remove any stale properties so ours can be found */
+	prop = of_find_property(node, kernel_end_prop.name, NULL);
+	if (prop)
+		prom_remove_property(node, prop);
+
+	/* information needed by userspace when using default_machine_kexec */
+	kernel_end = __pa(_end);
+	prom_add_property(node, &kernel_end_prop);
+
+	export_crashk_values(node);
+
+	of_node_put(node);
+	return 0;
+}
+late_initcall(kexec_setup);
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index 3c4ca046e854..49e705fcee6d 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -289,7 +289,7 @@ void default_machine_kexec(struct kimage *image)
 }
 
 /* Values we need to export to the second kernel via the device tree. */
-static unsigned long htab_base, kernel_end;
+static unsigned long htab_base;
 
 static struct property htab_base_prop = {
 	.name = "linux,htab-base",
@@ -303,25 +303,20 @@ static struct property htab_size_prop = {
 	.value = &htab_size_bytes,
 };
 
-static struct property kernel_end_prop = {
-	.name = "linux,kernel-end",
-	.length = sizeof(unsigned long),
-	.value = &kernel_end,
-};
-
-static void __init export_htab_values(void)
+static int __init export_htab_values(void)
 {
 	struct device_node *node;
 	struct property *prop;
 
+	/* On machines with no htab htab_address is NULL */
+	if (!htab_address)
+		return -ENODEV;
+
 	node = of_find_node_by_path("/chosen");
 	if (!node)
-		return;
+		return -ENODEV;
 
 	/* remove any stale propertys so ours can be found */
-	prop = of_find_property(node, kernel_end_prop.name, NULL);
-	if (prop)
-		prom_remove_property(node, prop);
 	prop = of_find_property(node, htab_base_prop.name, NULL);
 	if (prop)
 		prom_remove_property(node, prop);
@@ -329,68 +324,11 @@ static void __init export_htab_values(void)
 	if (prop)
 		prom_remove_property(node, prop);
 
-	/* information needed by userspace when using default_machine_kexec */
-	kernel_end = __pa(_end);
-	prom_add_property(node, &kernel_end_prop);
-
-	/* On machines with no htab htab_address is NULL */
-	if (NULL == htab_address)
-		goto out;
-
 	htab_base = __pa(htab_address);
 	prom_add_property(node, &htab_base_prop);
 	prom_add_property(node, &htab_size_prop);
 
- out:
-	of_node_put(node);
-}
-
-static struct property crashk_base_prop = {
-	.name = "linux,crashkernel-base",
-	.length = sizeof(unsigned long),
-	.value = &crashk_res.start,
-};
-
-static unsigned long crashk_size;
-
-static struct property crashk_size_prop = {
-	.name = "linux,crashkernel-size",
-	.length = sizeof(unsigned long),
-	.value = &crashk_size,
-};
-
-static void __init export_crashk_values(void)
-{
-	struct device_node *node;
-	struct property *prop;
-
-	node = of_find_node_by_path("/chosen");
-	if (!node)
-		return;
-
-	/* There might be existing crash kernel properties, but we can't
-	 * be sure what's in them, so remove them. */
-	prop = of_find_property(node, "linux,crashkernel-base", NULL);
-	if (prop)
-		prom_remove_property(node, prop);
-
-	prop = of_find_property(node, "linux,crashkernel-size", NULL);
-	if (prop)
-		prom_remove_property(node, prop);
-
-	if (crashk_res.start != 0) {
-		prom_add_property(node, &crashk_base_prop);
-		crashk_size = crashk_res.end - crashk_res.start + 1;
-		prom_add_property(node, &crashk_size_prop);
-	}
-
 	of_node_put(node);
-}
-
-static int __init kexec_setup(void)
-{
-	export_htab_values();
-	export_crashk_values();
 	return 0;
 }
-__initcall(kexec_setup);
+late_initcall(export_htab_values);
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 5c33bc14bd9f..15f28e0de78d 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -29,6 +29,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/processor.h>
 #include <asm/kexec.h>
+#include <asm/bug.h>
 
 	.text
 
@@ -271,231 +272,6 @@ _GLOBAL(real_writeb)
 
 #endif /* CONFIG_40x */
 
-/*
- * Flush MMU TLB
- */
-#ifndef CONFIG_FSL_BOOKE
-_GLOBAL(_tlbil_all)
-_GLOBAL(_tlbil_pid)
-#endif
-_GLOBAL(_tlbia)
-#if defined(CONFIG_40x)
-	sync			/* Flush to memory before changing mapping */
-	tlbia
-	isync			/* Flush shadow TLB */
-#elif defined(CONFIG_44x)
-	li	r3,0
-	sync
-
-	/* Load high watermark */
-	lis	r4,tlb_44x_hwater@ha
-	lwz	r5,tlb_44x_hwater@l(r4)
-
-1:	tlbwe	r3,r3,PPC44x_TLB_PAGEID
-	addi	r3,r3,1
-	cmpw	0,r3,r5
-	ble	1b
-
-	isync
-#elif defined(CONFIG_FSL_BOOKE)
-	/* Invalidate all entries in TLB0 */
-	li	r3, 0x04
-	tlbivax	0,3
-	/* Invalidate all entries in TLB1 */
-	li	r3, 0x0c
-	tlbivax	0,3
-	msync
-#ifdef CONFIG_SMP
-	tlbsync
-#endif /* CONFIG_SMP */
-#else /* !(CONFIG_40x || CONFIG_44x || CONFIG_FSL_BOOKE) */
-#if defined(CONFIG_SMP)
-	rlwinm	r8,r1,0,0,(31-THREAD_SHIFT)
-	lwz	r8,TI_CPU(r8)
-	oris	r8,r8,10
-	mfmsr	r10
-	SYNC
-	rlwinm	r0,r10,0,17,15		/* clear bit 16 (MSR_EE) */
-	rlwinm	r0,r0,0,28,26		/* clear DR */
-	mtmsr	r0
-	SYNC_601
-	isync
-	lis	r9,mmu_hash_lock@h
-	ori	r9,r9,mmu_hash_lock@l
-	tophys(r9,r9)
-10:	lwarx	r7,0,r9
-	cmpwi	0,r7,0
-	bne-	10b
-	stwcx.	r8,0,r9
-	bne-	10b
-	sync
-	tlbia
-	sync
-	TLBSYNC
-	li	r0,0
-	stw	r0,0(r9)		/* clear mmu_hash_lock */
-	mtmsr	r10
-	SYNC_601
-	isync
-#else /* CONFIG_SMP */
-	sync
-	tlbia
-	sync
-#endif /* CONFIG_SMP */
-#endif /* ! defined(CONFIG_40x) */
-	blr
-
-/*
- * Flush MMU TLB for a particular address
- */
-#ifndef CONFIG_FSL_BOOKE
-_GLOBAL(_tlbil_va)
-#endif
-_GLOBAL(_tlbie)
-#if defined(CONFIG_40x)
-	/* We run the search with interrupts disabled because we have to change
-	 * the PID and I don't want to preempt when that happens.
-	 */
-	mfmsr	r5
-	mfspr	r6,SPRN_PID
-	wrteei	0
-	mtspr	SPRN_PID,r4
-	tlbsx.	r3, 0, r3
-	mtspr	SPRN_PID,r6
-	wrtee	r5
-	bne	10f
-	sync
-	/* There are only 64 TLB entries, so r3 < 64, which means bit 25 is clear.
-	 * Since 25 is the V bit in the TLB_TAG, loading this value will invalidate
-	 * the TLB entry. */
-	tlbwe	r3, r3, TLB_TAG
-	isync
-10:
-
-#elif defined(CONFIG_44x)
-	mfspr	r5,SPRN_MMUCR
-	rlwimi	r5,r4,0,24,31			/* Set TID */
-
-	/* We have to run the search with interrupts disabled, even critical
-	 * and debug interrupts (in fact the only critical exceptions we have
-	 * are debug and machine check).  Otherwise  an interrupt which causes
-	 * a TLB miss can clobber the MMUCR between the mtspr and the tlbsx. */
-	mfmsr	r4
-	lis	r6,(MSR_EE|MSR_CE|MSR_ME|MSR_DE)@ha
-	addi	r6,r6,(MSR_EE|MSR_CE|MSR_ME|MSR_DE)@l
-	andc	r6,r4,r6
-	mtmsr	r6
-	mtspr	SPRN_MMUCR,r5
-	tlbsx.	r3, 0, r3
-	mtmsr	r4
-	bne	10f
-	sync
-	/* There are only 64 TLB entries, so r3 < 64,
-	 * which means bit 22, is clear.  Since 22 is
-	 * the V bit in the TLB_PAGEID, loading this
-	 * value will invalidate the TLB entry.
-	 */
-	tlbwe	r3, r3, PPC44x_TLB_PAGEID
-	isync
-10:
-#elif defined(CONFIG_FSL_BOOKE)
-	rlwinm	r4, r3, 0, 0, 19
-	ori	r5, r4, 0x08	/* TLBSEL = 1 */
-	tlbivax	0, r4
-	tlbivax	0, r5
-	msync
-#if defined(CONFIG_SMP)
-	tlbsync
-#endif /* CONFIG_SMP */
-#else /* !(CONFIG_40x || CONFIG_44x || CONFIG_FSL_BOOKE) */
-#if defined(CONFIG_SMP)
-	rlwinm	r8,r1,0,0,(31-THREAD_SHIFT)
-	lwz	r8,TI_CPU(r8)
-	oris	r8,r8,11
-	mfmsr	r10
-	SYNC
-	rlwinm	r0,r10,0,17,15		/* clear bit 16 (MSR_EE) */
-	rlwinm	r0,r0,0,28,26		/* clear DR */
-	mtmsr	r0
-	SYNC_601
-	isync
-	lis	r9,mmu_hash_lock@h
-	ori	r9,r9,mmu_hash_lock@l
-	tophys(r9,r9)
-10:	lwarx	r7,0,r9
-	cmpwi	0,r7,0
-	bne-	10b
-	stwcx.	r8,0,r9
-	bne-	10b
-	eieio
-	tlbie	r3
-	sync
-	TLBSYNC
-	li	r0,0
-	stw	r0,0(r9)		/* clear mmu_hash_lock */
-	mtmsr	r10
-	SYNC_601
-	isync
-#else /* CONFIG_SMP */
-	tlbie	r3
-	sync
-#endif /* CONFIG_SMP */
-#endif /* ! CONFIG_40x */
-	blr
-
-#if defined(CONFIG_FSL_BOOKE)
-/*
- * Flush MMU TLB, but only on the local processor (no broadcast)
- */
-_GLOBAL(_tlbil_all)
-#define MMUCSR0_TLBFI	(MMUCSR0_TLB0FI | MMUCSR0_TLB1FI | \
-			 MMUCSR0_TLB2FI | MMUCSR0_TLB3FI)
-	li	r3,(MMUCSR0_TLBFI)@l
-	mtspr	SPRN_MMUCSR0, r3
-1:
-	mfspr	r3,SPRN_MMUCSR0
-	andi.	r3,r3,MMUCSR0_TLBFI@l
-	bne	1b
-	blr
-
-/*
- * Flush MMU TLB for a particular process id, but only on the local processor
- * (no broadcast)
- */
-_GLOBAL(_tlbil_pid)
-/* we currently do an invalidate all since we don't have per pid invalidate */
-	li	r3,(MMUCSR0_TLBFI)@l
-	mtspr	SPRN_MMUCSR0, r3
-1:
-	mfspr	r3,SPRN_MMUCSR0
-	andi.	r3,r3,MMUCSR0_TLBFI@l
-	bne	1b
-	msync
-	isync
-	blr
-
-/*
- * Flush MMU TLB for a particular address, but only on the local processor
- * (no broadcast)
- */
-_GLOBAL(_tlbil_va)
-	mfmsr	r10
-	wrteei	0
-	slwi	r4,r4,16
-	mtspr	SPRN_MAS6,r4		/* assume AS=0 for now */
-	tlbsx	0,r3
-	mfspr	r4,SPRN_MAS1		/* check valid */
-	andis.	r3,r4,MAS1_VALID@h
-	beq	1f
-	rlwinm	r4,r4,0,1,31
-	mtspr	SPRN_MAS1,r4
-	tlbwe
-	msync
-	isync
-1:	wrtee	r10
-	blr
-#endif /* CONFIG_FSL_BOOKE */
-
 
 /*
  * Flush instruction cache.
@@ -650,8 +426,8 @@ _GLOBAL(__flush_dcache_icache)
 BEGIN_FTR_SECTION
 	blr
 END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
-	rlwinm	r3,r3,0,0,19			/* Get page base address */
-	li	r4,4096/L1_CACHE_BYTES	/* Number of lines in a page */
+	rlwinm	r3,r3,0,0,31-PAGE_SHIFT		/* Get page base address */
+	li	r4,PAGE_SIZE/L1_CACHE_BYTES	/* Number of lines in a page */
 	mtctr	r4
 	mr	r6,r3
 0:	dcbst	0,r3				/* Write line to ram */
@@ -691,8 +467,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 	rlwinm	r0,r10,0,28,26			/* clear DR */
 	mtmsr	r0
 	isync
-	rlwinm	r3,r3,0,0,19			/* Get page base address */
-	li	r4,4096/L1_CACHE_BYTES	/* Number of lines in a page */
+	rlwinm	r3,r3,0,0,31-PAGE_SHIFT		/* Get page base address */
+	li	r4,PAGE_SIZE/L1_CACHE_BYTES	/* Number of lines in a page */
 	mtctr	r4
 	mr	r6,r3
 0:	dcbst	0,r3				/* Write line to ram */
@@ -716,7 +492,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
  * void clear_pages(void *page, int order) ;
  */
 _GLOBAL(clear_pages)
-	li	r0,4096/L1_CACHE_BYTES
+	li	r0,PAGE_SIZE/L1_CACHE_BYTES
 	slw	r0,r0,r4
 	mtctr	r0
 #ifdef CONFIG_8xx
@@ -774,7 +550,7 @@ _GLOBAL(copy_page)
 	dcbt	r5,r4
 	li	r11,L1_CACHE_BYTES+4
 #endif /* MAX_COPY_PREFETCH */
-	li	r0,4096/L1_CACHE_BYTES - MAX_COPY_PREFETCH
+	li	r0,PAGE_SIZE/L1_CACHE_BYTES - MAX_COPY_PREFETCH
 	crclr	4*cr0+eq
 2:
 	mtctr	r0
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index 7ff292475269..43e7e3a7f130 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -78,6 +78,12 @@ int module_finalize(const Elf_Ehdr *hdr,
 				  (void *)sect->sh_addr,
 				  (void *)sect->sh_addr + sect->sh_size);
 
+	sect = find_section(hdr, sechdrs, "__mmu_ftr_fixup");
+	if (sect != NULL)
+		do_feature_fixups(cur_cpu_spec->mmu_features,
+				  (void *)sect->sh_addr,
+				  (void *)sect->sh_addr + sect->sh_size);
+
 #ifdef CONFIG_PPC64
 	sect = find_section(hdr, sechdrs, "__fw_ftr_fixup");
 	if (sect != NULL)
diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c
index 2df91a03462a..f832773fc28e 100644
--- a/arch/powerpc/kernel/module_32.c
+++ b/arch/powerpc/kernel/module_32.c
@@ -22,6 +22,7 @@
 #include <linux/fs.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
+#include <linux/ftrace.h>
 #include <linux/cache.h>
 #include <linux/bug.h>
 #include <linux/sort.h>
@@ -53,6 +54,9 @@ static unsigned int count_relocs(const Elf32_Rela *rela, unsigned int num)
 			r_addend = rela[i].r_addend;
 		}
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	_count_relocs++;	/* add one for ftrace_caller */
+#endif
 	return _count_relocs;
 }
 
@@ -306,5 +310,11 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 			return -ENOEXEC;
 		}
 	}
+#ifdef CONFIG_DYNAMIC_FTRACE
+	module->arch.tramp =
+		do_plt_call(module->module_core,
+			    (unsigned long)ftrace_caller,
+			    sechdrs, module);
+#endif
 	return 0;
 }
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 1af2377e4992..8992b031a7b6 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -20,6 +20,7 @@
 #include <linux/moduleloader.h>
 #include <linux/err.h>
 #include <linux/vmalloc.h>
+#include <linux/ftrace.h>
 #include <linux/bug.h>
 #include <asm/module.h>
 #include <asm/firmware.h>
@@ -163,6 +164,11 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
 		}
 	}
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	/* make the trampoline to the ftrace_caller */
+	relocs++;
+#endif
+
 	DEBUGP("Looks like a total of %lu stubs, max\n", relocs);
 	return relocs * sizeof(struct ppc64_stub_entry);
 }
@@ -441,5 +447,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		}
 	}
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	me->arch.toc = my_r2(sechdrs, me);
+	me->arch.tramp = stub_for_addr(sechdrs,
+				       (unsigned long)ftrace_caller,
+				       me);
+#endif
+
 	return 0;
 }
diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c
index f3c9cae01dd5..fa983a59c4ce 100644
--- a/arch/powerpc/kernel/of_device.c
+++ b/arch/powerpc/kernel/of_device.c
@@ -14,7 +14,6 @@ static void of_device_make_bus_id(struct of_device *dev)
 {
 	static atomic_t bus_no_reg_magic;
 	struct device_node *node = dev->node;
-	char *name = dev->dev.bus_id;
 	const u32 *reg;
 	u64 addr;
 	int magic;
@@ -27,14 +26,12 @@ static void of_device_make_bus_id(struct of_device *dev)
 	reg = of_get_property(node, "dcr-reg", NULL);
 	if (reg) {
 #ifdef CONFIG_PPC_DCR_NATIVE
-		snprintf(name, BUS_ID_SIZE, "d%x.%s",
-			 *reg, node->name);
+		dev_set_name(&dev->dev, "d%x.%s", *reg, node->name);
 #else /* CONFIG_PPC_DCR_NATIVE */
 		addr = of_translate_dcr_address(node, *reg, NULL);
 		if (addr != OF_BAD_ADDR) {
-			snprintf(name, BUS_ID_SIZE,
-				 "D%llx.%s", (unsigned long long)addr,
-				 node->name);
+			dev_set_name(&dev->dev, "D%llx.%s",
+				     (unsigned long long)addr, node->name);
 			return;
 		}
 #endif /* !CONFIG_PPC_DCR_NATIVE */
@@ -48,9 +45,8 @@ static void of_device_make_bus_id(struct of_device *dev)
 	if (reg) {
 		addr = of_translate_address(node, reg);
 		if (addr != OF_BAD_ADDR) {
-			snprintf(name, BUS_ID_SIZE,
-				 "%llx.%s", (unsigned long long)addr,
-				 node->name);
+			dev_set_name(&dev->dev, "%llx.%s",
+				     (unsigned long long)addr, node->name);
 			return;
 		}
 	}
@@ -60,7 +56,7 @@ static void of_device_make_bus_id(struct of_device *dev)
 	 * counter (and pray...)
 	 */
 	magic = atomic_add_return(1, &bus_no_reg_magic);
-	snprintf(name, BUS_ID_SIZE, "%s.%d", node->name, magic - 1);
+	dev_set_name(&dev->dev, "%s.%d", node->name, magic - 1);
 }
 
 struct of_device *of_device_alloc(struct device_node *np,
@@ -80,7 +76,7 @@ struct of_device *of_device_alloc(struct device_node *np,
 	dev->dev.archdata.of_node = np;
 
 	if (bus_id)
-		strlcpy(dev->dev.bus_id, bus_id, BUS_ID_SIZE);
+		dev_set_name(&dev->dev, bus_id);
 	else
 		of_device_make_bus_id(dev);
 
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 48a347133f41..c744b327bcab 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -37,6 +37,7 @@ struct lppaca lppaca[] = {
 		.end_of_quantum = 0xfffffffffffffffful,
 		.slb_count = 64,
 		.vmxregs_in_use = 0,
+		.page_ins = 0,
 	},
 };
 
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index f36936d9fda3..da5a3855a0c4 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -16,7 +16,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#undef DEBUG
+#define DEBUG
 
 #include <linux/kernel.h>
 #include <linux/pci.h>
@@ -37,13 +37,7 @@
 #include <asm/machdep.h>
 #include <asm/ppc-pci.h>
 #include <asm/firmware.h>
-
-#ifdef DEBUG
-#include <asm/udbg.h>
-#define DBG(fmt...) printk(fmt)
-#else
-#define DBG(fmt...)
-#endif
+#include <asm/eeh.h>
 
 static DEFINE_SPINLOCK(hose_spinlock);
 
@@ -53,8 +47,9 @@ static int global_phb_number;		/* Global phb counter */
 /* ISA Memory physical address */
 resource_size_t isa_mem_base;
 
-/* Default PCI flags is 0 */
-unsigned int ppc_pci_flags;
+/* Default PCI flags is 0 on ppc32, modified at boot on ppc64 */
+unsigned int ppc_pci_flags = 0;
+
 
 static struct dma_mapping_ops *pci_dma_ops;
 
@@ -165,8 +160,6 @@ EXPORT_SYMBOL(pci_domain_nr);
  */
 struct pci_controller* pci_find_hose_for_OF_device(struct device_node* node)
 {
-	if (!have_of)
-		return NULL;
 	while(node) {
 		struct pci_controller *hose, *tmp;
 		list_for_each_entry_safe(hose, tmp, &hose_list, list_node)
@@ -208,26 +201,6 @@ char __devinit *pcibios_setup(char *str)
 	return str;
 }
 
-void __devinit pcibios_setup_new_device(struct pci_dev *dev)
-{
-	struct dev_archdata *sd = &dev->dev.archdata;
-
-	sd->of_node = pci_device_to_OF_node(dev);
-
-	DBG("PCI: device %s OF node: %s\n", pci_name(dev),
-	    sd->of_node ? sd->of_node->full_name : "<none>");
-
-	sd->dma_ops = pci_dma_ops;
-#ifdef CONFIG_PPC32
-	sd->dma_data = (void *)PCI_DRAM_OFFSET;
-#endif
-	set_dev_node(&dev->dev, pcibus_to_node(dev->bus));
-
-	if (ppc_md.pci_dma_dev_setup)
-		ppc_md.pci_dma_dev_setup(dev);
-}
-EXPORT_SYMBOL(pcibios_setup_new_device);
-
 /*
  * Reads the interrupt pin to determine if interrupt is use by card.
  * If the interrupt is used, then gets the interrupt line from the
@@ -252,7 +225,7 @@ int pci_read_irq_line(struct pci_dev *pci_dev)
 		return -1;
 #endif
 
-	DBG("Try to map irq for %s...\n", pci_name(pci_dev));
+	pr_debug("PCI: Try to map irq for %s...\n", pci_name(pci_dev));
 
 #ifdef DEBUG
 	memset(&oirq, 0xff, sizeof(oirq));
@@ -276,26 +249,26 @@ int pci_read_irq_line(struct pci_dev *pci_dev)
 		    line == 0xff || line == 0) {
 			return -1;
 		}
-		DBG(" -> no map ! Using line %d (pin %d) from PCI config\n",
-		    line, pin);
+		pr_debug(" No map ! Using line %d (pin %d) from PCI config\n",
+			 line, pin);
 
 		virq = irq_create_mapping(NULL, line);
 		if (virq != NO_IRQ)
 			set_irq_type(virq, IRQ_TYPE_LEVEL_LOW);
 	} else {
-		DBG(" -> got one, spec %d cells (0x%08x 0x%08x...) on %s\n",
-		    oirq.size, oirq.specifier[0], oirq.specifier[1],
+		pr_debug(" Got one, spec %d cells (0x%08x 0x%08x...) on %s\n",
+			 oirq.size, oirq.specifier[0], oirq.specifier[1],
 		    oirq.controller->full_name);
 
 		virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
 					     oirq.size);
 	}
 	if(virq == NO_IRQ) {
-		DBG(" -> failed to map !\n");
+		pr_debug(" Failed to map !\n");
 		return -1;
 	}
 
-	DBG(" -> mapped to linux irq %d\n", virq);
+	pr_debug(" Mapped to linux irq %d\n", virq);
 
 	pci_dev->irq = virq;
 
@@ -397,13 +370,10 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
 	}
 
 	/* XXX would be nice to have a way to ask for write-through */
-	prot |= _PAGE_NO_CACHE;
 	if (write_combine)
-		prot &= ~_PAGE_GUARDED;
+		return pgprot_noncached_wc(prot);
 	else
-		prot |= _PAGE_GUARDED;
-
-	return __pgprot(prot);
+		return pgprot_noncached(prot);
 }
 
 /*
@@ -414,19 +384,17 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
 pgprot_t pci_phys_mem_access_prot(struct file *file,
 				  unsigned long pfn,
 				  unsigned long size,
-				  pgprot_t protection)
+				  pgprot_t prot)
 {
 	struct pci_dev *pdev = NULL;
 	struct resource *found = NULL;
-	unsigned long prot = pgprot_val(protection);
 	resource_size_t offset = ((resource_size_t)pfn) << PAGE_SHIFT;
 	int i;
 
 	if (page_is_ram(pfn))
-		return __pgprot(prot);
-
-	prot |= _PAGE_NO_CACHE | _PAGE_GUARDED;
+		return prot;
 
+	prot = pgprot_noncached(prot);
 	for_each_pci_dev(pdev) {
 		for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
 			struct resource *rp = &pdev->resource[i];
@@ -447,14 +415,14 @@ pgprot_t pci_phys_mem_access_prot(struct file *file,
 	}
 	if (found) {
 		if (found->flags & IORESOURCE_PREFETCH)
-			prot &= ~_PAGE_GUARDED;
+			prot = pgprot_noncached_wc(prot);
 		pci_dev_put(pdev);
 	}
 
-	DBG("non-PCI map for %llx, prot: %lx\n",
-	    (unsigned long long)offset, prot);
+	pr_debug("PCI: Non-PCI map for %llx, prot: %lx\n",
+		 (unsigned long long)offset, pgprot_val(prot));
 
-	return __pgprot(prot);
+	return prot;
 }
 
 
@@ -610,8 +578,7 @@ int pci_mmap_legacy_page_range(struct pci_bus *bus,
 	pr_debug(" -> mapping phys %llx\n", (unsigned long long)offset);
 
 	vma->vm_pgoff = offset >> PAGE_SHIFT;
-	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
-				     | _PAGE_NO_CACHE | _PAGE_GUARDED);
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
 			       vma->vm_end - vma->vm_start,
 			       vma->vm_page_prot);
@@ -853,15 +820,12 @@ void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose,
 int pci_proc_domain(struct pci_bus *bus)
 {
 	struct pci_controller *hose = pci_bus_to_host(bus);
-#ifdef CONFIG_PPC64
-	return hose->buid != 0;
-#else
+
 	if (!(ppc_pci_flags & PPC_PCI_ENABLE_PROC_DOMAINS))
 		return 0;
 	if (ppc_pci_flags & PPC_PCI_COMPAT_DOMAIN_0)
 		return hose->global_number != 0;
 	return 1;
-#endif
 }
 
 void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region,
@@ -1083,27 +1047,50 @@ static void __devinit pcibios_fixup_bridge(struct pci_bus *bus)
 	}
 }
 
-static void __devinit __pcibios_fixup_bus(struct pci_bus *bus)
+void __devinit pcibios_setup_bus_self(struct pci_bus *bus)
 {
-	struct pci_dev *dev = bus->self;
-
-	pr_debug("PCI: Fixup bus %d (%s)\n", bus->number, dev ? pci_name(dev) : "PHB");
-
-	/* Fixup PCI<->PCI bridges. Host bridges are handled separately, for
-	 * now differently between 32 and 64 bits.
-	 */
-	if (dev != NULL)
+	/* Fix up the bus resources for P2P bridges */
+	if (bus->self != NULL)
 		pcibios_fixup_bridge(bus);
 
-	/* Additional setup that is different between 32 and 64 bits for now */
-	pcibios_do_bus_setup(bus);
-
-	/* Platform specific bus fixups */
+	/* Platform specific bus fixups. This is currently only used
+	 * by fsl_pci and I'm hoping to get rid of it at some point
+	 */
 	if (ppc_md.pcibios_fixup_bus)
 		ppc_md.pcibios_fixup_bus(bus);
 
-	/* Read default IRQs and fixup if necessary */
+	/* Setup bus DMA mappings */
+	if (ppc_md.pci_dma_bus_setup)
+		ppc_md.pci_dma_bus_setup(bus);
+}
+
+void __devinit pcibios_setup_bus_devices(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	pr_debug("PCI: Fixup bus devices %d (%s)\n",
+		 bus->number, bus->self ? pci_name(bus->self) : "PHB");
+
 	list_for_each_entry(dev, &bus->devices, bus_list) {
+		struct dev_archdata *sd = &dev->dev.archdata;
+
+		/* Setup OF node pointer in archdata */
+		sd->of_node = pci_device_to_OF_node(dev);
+
+		/* Fixup NUMA node as it may not be setup yet by the generic
+		 * code and is needed by the DMA init
+		 */
+		set_dev_node(&dev->dev, pcibus_to_node(dev->bus));
+
+		/* Hook up default DMA ops */
+		sd->dma_ops = pci_dma_ops;
+		sd->dma_data = (void *)PCI_DRAM_OFFSET;
+
+		/* Additional platform DMA/iommu setup */
+		if (ppc_md.pci_dma_dev_setup)
+			ppc_md.pci_dma_dev_setup(dev);
+
+		/* Read default IRQs and fixup if necessary */
 		pci_read_irq_line(dev);
 		if (ppc_md.pci_irq_fixup)
 			ppc_md.pci_irq_fixup(dev);
@@ -1113,22 +1100,19 @@ static void __devinit __pcibios_fixup_bus(struct pci_bus *bus)
 void __devinit pcibios_fixup_bus(struct pci_bus *bus)
 {
 	/* When called from the generic PCI probe, read PCI<->PCI bridge
-	 * bases before proceeding
+	 * bases. This is -not- called when generating the PCI tree from
+	 * the OF device-tree.
 	 */
 	if (bus->self != NULL)
 		pci_read_bridge_bases(bus);
-	__pcibios_fixup_bus(bus);
-}
-EXPORT_SYMBOL(pcibios_fixup_bus);
 
-/* When building a bus from the OF tree rather than probing, we need a
- * slightly different version of the fixup which doesn't read the
- * bridge bases using config space accesses
- */
-void __devinit pcibios_fixup_of_probed_bus(struct pci_bus *bus)
-{
-	__pcibios_fixup_bus(bus);
+	/* Now fixup the bus bus */
+	pcibios_setup_bus_self(bus);
+
+	/* Now fixup devices on that bus */
+	pcibios_setup_bus_devices(bus);
 }
+EXPORT_SYMBOL(pcibios_fixup_bus);
 
 static int skip_isa_ioresource_align(struct pci_dev *dev)
 {
@@ -1198,10 +1182,10 @@ static int __init reparent_resources(struct resource *parent,
 	*pp = NULL;
 	for (p = res->child; p != NULL; p = p->sibling) {
 		p->parent = res;
-		DBG(KERN_INFO "PCI: reparented %s [%llx..%llx] under %s\n",
-		    p->name,
-		    (unsigned long long)p->start,
-		    (unsigned long long)p->end, res->name);
+		pr_debug("PCI: Reparented %s [%llx..%llx] under %s\n",
+			 p->name,
+			 (unsigned long long)p->start,
+			 (unsigned long long)p->end, res->name);
 	}
 	return 0;
 }
@@ -1245,9 +1229,12 @@ void pcibios_allocate_bus_resources(struct pci_bus *bus)
 	int i;
 	struct resource *res, *pr;
 
+	pr_debug("PCI: Allocating bus resources for %04x:%02x...\n",
+		 pci_domain_nr(bus), bus->number);
+
 	for (i = 0; i < PCI_BUS_NUM_RESOURCES; ++i) {
 		if ((res = bus->resource[i]) == NULL || !res->flags
-		    || res->start > res->end)
+		    || res->start > res->end || res->parent)
 			continue;
 		if (bus->parent == NULL)
 			pr = (res->flags & IORESOURCE_IO) ?
@@ -1271,14 +1258,14 @@ void pcibios_allocate_bus_resources(struct pci_bus *bus)
 			}
 		}
 
-		DBG("PCI: %s (bus %d) bridge rsrc %d: %016llx-%016llx "
-		    "[0x%x], parent %p (%s)\n",
-		    bus->self ? pci_name(bus->self) : "PHB",
-		    bus->number, i,
-		    (unsigned long long)res->start,
-		    (unsigned long long)res->end,
-		    (unsigned int)res->flags,
-		    pr, (pr && pr->name) ? pr->name : "nil");
+		pr_debug("PCI: %s (bus %d) bridge rsrc %d: %016llx-%016llx "
+			 "[0x%x], parent %p (%s)\n",
+			 bus->self ? pci_name(bus->self) : "PHB",
+			 bus->number, i,
+			 (unsigned long long)res->start,
+			 (unsigned long long)res->end,
+			 (unsigned int)res->flags,
+			 pr, (pr && pr->name) ? pr->name : "nil");
 
 		if (pr && !(pr->flags & IORESOURCE_UNSET)) {
 			if (request_resource(pr, res) == 0)
@@ -1305,11 +1292,11 @@ static inline void __devinit alloc_resource(struct pci_dev *dev, int idx)
 {
 	struct resource *pr, *r = &dev->resource[idx];
 
-	DBG("PCI: Allocating %s: Resource %d: %016llx..%016llx [%x]\n",
-	    pci_name(dev), idx,
-	    (unsigned long long)r->start,
-	    (unsigned long long)r->end,
-	    (unsigned int)r->flags);
+	pr_debug("PCI: Allocating %s: Resource %d: %016llx..%016llx [%x]\n",
+		 pci_name(dev), idx,
+		 (unsigned long long)r->start,
+		 (unsigned long long)r->end,
+		 (unsigned int)r->flags);
 
 	pr = pci_find_parent_resource(dev, r);
 	if (!pr || (pr->flags & IORESOURCE_UNSET) ||
@@ -1317,10 +1304,11 @@ static inline void __devinit alloc_resource(struct pci_dev *dev, int idx)
 		printk(KERN_WARNING "PCI: Cannot allocate resource region %d"
 		       " of device %s, will remap\n", idx, pci_name(dev));
 		if (pr)
-			DBG("PCI:  parent is %p: %016llx-%016llx [%x]\n", pr,
-			    (unsigned long long)pr->start,
-			    (unsigned long long)pr->end,
-			    (unsigned int)pr->flags);
+			pr_debug("PCI:  parent is %p: %016llx-%016llx [%x]\n",
+				 pr,
+				 (unsigned long long)pr->start,
+				 (unsigned long long)pr->end,
+				 (unsigned int)pr->flags);
 		/* We'll assign a new address later */
 		r->flags |= IORESOURCE_UNSET;
 		r->end -= r->start;
@@ -1358,7 +1346,8 @@ static void __init pcibios_allocate_resources(int pass)
 			 * but keep it unregistered.
 			 */
 			u32 reg;
-			DBG("PCI: Switching off ROM of %s\n", pci_name(dev));
+			pr_debug("PCI: Switching off ROM of %s\n",
+				 pci_name(dev));
 			r->flags &= ~IORESOURCE_ROM_ENABLE;
 			pci_read_config_dword(dev, dev->rom_base_reg, &reg);
 			pci_write_config_dword(dev, dev->rom_base_reg,
@@ -1367,6 +1356,63 @@ static void __init pcibios_allocate_resources(int pass)
 	}
 }
 
+static void __init pcibios_reserve_legacy_regions(struct pci_bus *bus)
+{
+	struct pci_controller *hose = pci_bus_to_host(bus);
+	resource_size_t	offset;
+	struct resource *res, *pres;
+	int i;
+
+	pr_debug("Reserving legacy ranges for domain %04x\n", pci_domain_nr(bus));
+
+	/* Check for IO */
+	if (!(hose->io_resource.flags & IORESOURCE_IO))
+		goto no_io;
+	offset = (unsigned long)hose->io_base_virt - _IO_BASE;
+	res = kzalloc(sizeof(struct resource), GFP_KERNEL);
+	BUG_ON(res == NULL);
+	res->name = "Legacy IO";
+	res->flags = IORESOURCE_IO;
+	res->start = offset;
+	res->end = (offset + 0xfff) & 0xfffffffful;
+	pr_debug("Candidate legacy IO: %pR\n", res);
+	if (request_resource(&hose->io_resource, res)) {
+		printk(KERN_DEBUG
+		       "PCI %04x:%02x Cannot reserve Legacy IO %pR\n",
+		       pci_domain_nr(bus), bus->number, res);
+		kfree(res);
+	}
+
+ no_io:
+	/* Check for memory */
+	offset = hose->pci_mem_offset;
+	pr_debug("hose mem offset: %016llx\n", (unsigned long long)offset);
+	for (i = 0; i < 3; i++) {
+		pres = &hose->mem_resources[i];
+		if (!(pres->flags & IORESOURCE_MEM))
+			continue;
+		pr_debug("hose mem res: %pR\n", pres);
+		if ((pres->start - offset) <= 0xa0000 &&
+		    (pres->end - offset) >= 0xbffff)
+			break;
+	}
+	if (i >= 3)
+		return;
+	res = kzalloc(sizeof(struct resource), GFP_KERNEL);
+	BUG_ON(res == NULL);
+	res->name = "Legacy VGA memory";
+	res->flags = IORESOURCE_MEM;
+	res->start = 0xa0000 + offset;
+	res->end = 0xbffff + offset;
+	pr_debug("Candidate VGA memory: %pR\n", res);
+	if (request_resource(pres, res)) {
+		printk(KERN_DEBUG
+		       "PCI %04x:%02x Cannot reserve VGA memory %pR\n",
+		       pci_domain_nr(bus), bus->number, res);
+		kfree(res);
+	}
+}
+
 void __init pcibios_resource_survey(void)
 {
 	struct pci_bus *b;
@@ -1382,8 +1428,20 @@ void __init pcibios_resource_survey(void)
 		pcibios_allocate_resources(1);
 	}
 
+	/* Before we start assigning unassigned resource, we try to reserve
+	 * the low IO area and the VGA memory area if they intersect the
+	 * bus available resources to avoid allocating things on top of them
+	 */
 	if (!(ppc_pci_flags & PPC_PCI_PROBE_ONLY)) {
-		DBG("PCI: Assigning unassigned resouces...\n");
+		list_for_each_entry(b, &pci_root_buses, node)
+			pcibios_reserve_legacy_regions(b);
+	}
+
+	/* Now, if the platform didn't decide to blindly trust the firmware,
+	 * we proceed to assigning things that were left unassigned
+	 */
+	if (!(ppc_pci_flags & PPC_PCI_PROBE_ONLY)) {
+		pr_debug("PCI: Assigning unassigned resouces...\n");
 		pci_assign_unassigned_resources();
 	}
 
@@ -1393,9 +1451,11 @@ void __init pcibios_resource_survey(void)
 }
 
 #ifdef CONFIG_HOTPLUG
-/* This is used by the pSeries hotplug driver to allocate resource
+
+/* This is used by the PCI hotplug driver to allocate resource
  * of newly plugged busses. We can try to consolidate with the
- * rest of the code later, for now, keep it as-is
+ * rest of the code later, for now, keep it as-is as our main
+ * resource allocation function doesn't deal with sub-trees yet.
  */
 void __devinit pcibios_claim_one_bus(struct pci_bus *bus)
 {
@@ -1410,6 +1470,14 @@ void __devinit pcibios_claim_one_bus(struct pci_bus *bus)
 
 			if (r->parent || !r->start || !r->flags)
 				continue;
+
+			pr_debug("PCI: Claiming %s: "
+				 "Resource %d: %016llx..%016llx [%x]\n",
+				 pci_name(dev), i,
+				 (unsigned long long)r->start,
+				 (unsigned long long)r->end,
+				 (unsigned int)r->flags);
+
 			pci_claim_resource(dev, i);
 		}
 	}
@@ -1418,6 +1486,31 @@ void __devinit pcibios_claim_one_bus(struct pci_bus *bus)
 		pcibios_claim_one_bus(child_bus);
 }
 EXPORT_SYMBOL_GPL(pcibios_claim_one_bus);
+
+
+/* pcibios_finish_adding_to_bus
+ *
+ * This is to be called by the hotplug code after devices have been
+ * added to a bus, this include calling it for a PHB that is just
+ * being added
+ */
+void pcibios_finish_adding_to_bus(struct pci_bus *bus)
+{
+	pr_debug("PCI: Finishing adding to hotplug bus %04x:%02x\n",
+		 pci_domain_nr(bus), bus->number);
+
+	/* Allocate bus and devices resources */
+	pcibios_allocate_bus_resources(bus);
+	pcibios_claim_one_bus(bus);
+
+	/* Add new devices to global lists.  Register in proc, sysfs. */
+	pci_bus_add_devices(bus);
+
+	/* Fixup EEH */
+	eeh_add_device_tree_late(bus);
+}
+EXPORT_SYMBOL_GPL(pcibios_finish_adding_to_bus);
+
 #endif /* CONFIG_HOTPLUG */
 
 int pcibios_enable_device(struct pci_dev *dev, int mask)
@@ -1428,3 +1521,61 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 
 	return pci_enable_resources(dev, mask);
 }
+
+void __devinit pcibios_setup_phb_resources(struct pci_controller *hose)
+{
+	struct pci_bus *bus = hose->bus;
+	struct resource *res;
+	int i;
+
+	/* Hookup PHB IO resource */
+	bus->resource[0] = res = &hose->io_resource;
+
+	if (!res->flags) {
+		printk(KERN_WARNING "PCI: I/O resource not set for host"
+		       " bridge %s (domain %d)\n",
+		       hose->dn->full_name, hose->global_number);
+#ifdef CONFIG_PPC32
+		/* Workaround for lack of IO resource only on 32-bit */
+		res->start = (unsigned long)hose->io_base_virt - isa_io_base;
+		res->end = res->start + IO_SPACE_LIMIT;
+		res->flags = IORESOURCE_IO;
+#endif /* CONFIG_PPC32 */
+	}
+
+	pr_debug("PCI: PHB IO resource    = %016llx-%016llx [%lx]\n",
+		 (unsigned long long)res->start,
+		 (unsigned long long)res->end,
+		 (unsigned long)res->flags);
+
+	/* Hookup PHB Memory resources */
+	for (i = 0; i < 3; ++i) {
+		res = &hose->mem_resources[i];
+		if (!res->flags) {
+			if (i > 0)
+				continue;
+			printk(KERN_ERR "PCI: Memory resource 0 not set for "
+			       "host bridge %s (domain %d)\n",
+			       hose->dn->full_name, hose->global_number);
+#ifdef CONFIG_PPC32
+			/* Workaround for lack of MEM resource only on 32-bit */
+			res->start = hose->pci_mem_offset;
+			res->end = (resource_size_t)-1LL;
+			res->flags = IORESOURCE_MEM;
+#endif /* CONFIG_PPC32 */
+		}
+		bus->resource[i+1] = res;
+
+		pr_debug("PCI: PHB MEM resource %d = %016llx-%016llx [%lx]\n", i,
+			 (unsigned long long)res->start,
+			 (unsigned long long)res->end,
+			 (unsigned long)res->flags);
+	}
+
+	pr_debug("PCI: PHB MEM offset     = %016llx\n",
+		 (unsigned long long)hose->pci_mem_offset);
+	pr_debug("PCI: PHB IO  offset     = %08lx\n",
+		 (unsigned long)hose->io_base_virt - _IO_BASE);
+
+}
+
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 131b1dfa68c6..132cd80afa21 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -26,12 +26,6 @@
 
 #undef DEBUG
 
-#ifdef DEBUG
-#define DBG(x...) printk(x)
-#else
-#define DBG(x...)
-#endif
-
 unsigned long isa_io_base     = 0;
 unsigned long pci_dram_offset = 0;
 int pcibios_assign_bus_offset = 1;
@@ -272,17 +266,14 @@ pci_busdev_to_OF_node(struct pci_bus *bus, int devfn)
 {
 	struct device_node *parent, *np;
 
-	if (!have_of)
-		return NULL;
-
-	DBG("pci_busdev_to_OF_node(%d,0x%x)\n", bus->number, devfn);
+	pr_debug("pci_busdev_to_OF_node(%d,0x%x)\n", bus->number, devfn);
 	parent = scan_OF_for_pci_bus(bus);
 	if (parent == NULL)
 		return NULL;
-	DBG(" parent is %s\n", parent ? parent->full_name : "<NULL>");
+	pr_debug(" parent is %s\n", parent ? parent->full_name : "<NULL>");
 	np = scan_OF_for_pci_dev(parent, devfn);
 	of_node_put(parent);
-	DBG(" result is %s\n", np ? np->full_name : "<NULL>");
+	pr_debug(" result is %s\n", np ? np->full_name : "<NULL>");
 
 	/* XXX most callers don't release the returned node
 	 * mostly because ppc64 doesn't increase the refcount,
@@ -315,8 +306,6 @@ pci_device_from_OF_node(struct device_node* node, u8* bus, u8* devfn)
 	struct pci_controller* hose;
 	struct pci_dev* dev = NULL;
 	
-	if (!have_of)
-		return -ENODEV;
 	/* Make sure it's really a PCI device */
 	hose = pci_find_hose_for_OF_device(node);
 	if (!hose || !hose->dn)
@@ -379,10 +368,41 @@ void pcibios_make_OF_bus_map(void)
 }
 #endif /* CONFIG_PPC_OF */
 
+static void __devinit pcibios_scan_phb(struct pci_controller *hose)
+{
+	struct pci_bus *bus;
+	struct device_node *node = hose->dn;
+	unsigned long io_offset;
+	struct resource *res = &hose->io_resource;
+
+	pr_debug("PCI: Scanning PHB %s\n",
+		 node ? node->full_name : "<NO NAME>");
+
+	/* Create an empty bus for the toplevel */
+	bus = pci_create_bus(hose->parent, hose->first_busno, hose->ops, hose);
+	if (bus == NULL) {
+		printk(KERN_ERR "Failed to create bus for PCI domain %04x\n",
+		       hose->global_number);
+		return;
+	}
+	bus->secondary = hose->first_busno;
+	hose->bus = bus;
+
+	/* Fixup IO space offset */
+	io_offset = (unsigned long)hose->io_base_virt - isa_io_base;
+	res->start = (res->start + io_offset) & 0xffffffffu;
+	res->end = (res->end + io_offset) & 0xffffffffu;
+
+	/* Wire up PHB bus resources */
+	pcibios_setup_phb_resources(hose);
+
+	/* Scan children */
+	hose->last_busno = bus->subordinate = pci_scan_child_bus(bus);
+}
+
 static int __init pcibios_init(void)
 {
 	struct pci_controller *hose, *tmp;
-	struct pci_bus *bus;
 	int next_busno = 0;
 
 	printk(KERN_INFO "PCI: Probing PCI hardware\n");
@@ -395,12 +415,8 @@ static int __init pcibios_init(void)
 		if (pci_assign_all_buses)
 			hose->first_busno = next_busno;
 		hose->last_busno = 0xff;
-		bus = pci_scan_bus_parented(hose->parent, hose->first_busno,
-					    hose->ops, hose);
-		if (bus) {
-			pci_bus_add_devices(bus);
-			hose->last_busno = bus->subordinate;
-		}
+		pcibios_scan_phb(hose);
+		pci_bus_add_devices(hose->bus);
 		if (pci_assign_all_buses || next_busno <= hose->last_busno)
 			next_busno = hose->last_busno + pcibios_assign_bus_offset;
 	}
@@ -410,7 +426,7 @@ static int __init pcibios_init(void)
 	 * numbers vs. kernel bus numbers since we may have to
 	 * remap them.
 	 */
-	if (pci_assign_all_buses && have_of)
+	if (pci_assign_all_buses)
 		pcibios_make_OF_bus_map();
 
 	/* Call common code to handle resource allocation */
@@ -425,54 +441,6 @@ static int __init pcibios_init(void)
 
 subsys_initcall(pcibios_init);
 
-void __devinit pcibios_do_bus_setup(struct pci_bus *bus)
-{
-	struct pci_controller *hose = (struct pci_controller *) bus->sysdata;
-	unsigned long io_offset;
-	struct resource *res;
-	int i;
-	struct pci_dev *dev;
-
-	/* Hookup PHB resources */
-	io_offset = (unsigned long)hose->io_base_virt - isa_io_base;
-	if (bus->parent == NULL) {
-		/* This is a host bridge - fill in its resources */
-		hose->bus = bus;
-
-		bus->resource[0] = res = &hose->io_resource;
-		if (!res->flags) {
-			if (io_offset)
-				printk(KERN_ERR "I/O resource not set for host"
-				       " bridge %d\n", hose->global_number);
-			res->start = 0;
-			res->end = IO_SPACE_LIMIT;
-			res->flags = IORESOURCE_IO;
-		}
-		res->start = (res->start + io_offset) & 0xffffffffu;
-		res->end = (res->end + io_offset) & 0xffffffffu;
-
-		for (i = 0; i < 3; ++i) {
-			res = &hose->mem_resources[i];
-			if (!res->flags) {
-				if (i > 0)
-					continue;
-				printk(KERN_ERR "Memory resource not set for "
-				       "host bridge %d\n", hose->global_number);
-				res->start = hose->pci_mem_offset;
-				res->end = ~0U;
-				res->flags = IORESOURCE_MEM;
-			}
-			bus->resource[i+1] = res;
-		}
-	}
-
-	if (ppc_md.pci_dma_bus_setup)
-		ppc_md.pci_dma_bus_setup(bus);
-
-	list_for_each_entry(dev, &bus->devices, bus_list)
-		pcibios_setup_new_device(dev);
-}
-
 /* the next one is stolen from the alpha port... */
 void __init
 pcibios_update_irq(struct pci_dev *dev, int irq)
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 3502b9101e6b..586962f65c2a 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -32,13 +32,6 @@
 #include <asm/machdep.h>
 #include <asm/ppc-pci.h>
 
-#ifdef DEBUG
-#include <asm/udbg.h>
-#define DBG(fmt...) printk(fmt)
-#else
-#define DBG(fmt...)
-#endif
-
 unsigned long pci_probe_only = 1;
 
 /* pci_io_base -- the base address from which io bars are offsets.
@@ -102,7 +95,7 @@ static void pci_parse_of_addrs(struct device_node *node, struct pci_dev *dev)
 	addrs = of_get_property(node, "assigned-addresses", &proplen);
 	if (!addrs)
 		return;
-	DBG("    parse addresses (%d bytes) @ %p\n", proplen, addrs);
+	pr_debug("    parse addresses (%d bytes) @ %p\n", proplen, addrs);
 	for (; proplen >= 20; proplen -= 20, addrs += 5) {
 		flags = pci_parse_of_flags(addrs[0]);
 		if (!flags)
@@ -112,8 +105,9 @@ static void pci_parse_of_addrs(struct device_node *node, struct pci_dev *dev)
 		if (!size)
 			continue;
 		i = addrs[0] & 0xff;
-		DBG("  base: %llx, size: %llx, i: %x\n",
-		    (unsigned long long)base, (unsigned long long)size, i);
+		pr_debug("  base: %llx, size: %llx, i: %x\n",
+			 (unsigned long long)base,
+			 (unsigned long long)size, i);
 
 		if (PCI_BASE_ADDRESS_0 <= i && i <= PCI_BASE_ADDRESS_5) {
 			res = &dev->resource[(i - PCI_BASE_ADDRESS_0) >> 2];
@@ -144,7 +138,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 	if (type == NULL)
 		type = "";
 
-	DBG("    create device, devfn: %x, type: %s\n", devfn, type);
+	pr_debug("    create device, devfn: %x, type: %s\n", devfn, type);
 
 	dev->bus = bus;
 	dev->sysdata = node;
@@ -165,8 +159,8 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 	dev->class = get_int_prop(node, "class-code", 0);
 	dev->revision = get_int_prop(node, "revision-id", 0);
 
-	DBG("    class: 0x%x\n", dev->class);
-	DBG("    revision: 0x%x\n", dev->revision);
+	pr_debug("    class: 0x%x\n", dev->class);
+	pr_debug("    revision: 0x%x\n", dev->revision);
 
 	dev->current_state = 4;		/* unknown power state */
 	dev->error_state = pci_channel_io_normal;
@@ -187,7 +181,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 
 	pci_parse_of_addrs(node, dev);
 
-	DBG("    adding to system ...\n");
+	pr_debug("    adding to system ...\n");
 
 	pci_device_add(dev, bus);
 
@@ -195,19 +189,20 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 }
 EXPORT_SYMBOL(of_create_pci_dev);
 
-void __devinit of_scan_bus(struct device_node *node,
-			   struct pci_bus *bus)
+static void __devinit __of_scan_bus(struct device_node *node,
+				    struct pci_bus *bus, int rescan_existing)
 {
 	struct device_node *child;
 	const u32 *reg;
 	int reglen, devfn;
 	struct pci_dev *dev;
 
-	DBG("of_scan_bus(%s) bus no %d... \n", node->full_name, bus->number);
+	pr_debug("of_scan_bus(%s) bus no %d... \n",
+		 node->full_name, bus->number);
 
 	/* Scan direct children */
 	for_each_child_of_node(node, child) {
-		DBG("  * %s\n", child->full_name);
+		pr_debug("  * %s\n", child->full_name);
 		reg = of_get_property(child, "reg", &reglen);
 		if (reg == NULL || reglen < 20)
 			continue;
@@ -217,11 +212,15 @@ void __devinit of_scan_bus(struct device_node *node,
 		dev = of_create_pci_dev(child, bus, devfn);
 		if (!dev)
 			continue;
-		DBG("    dev header type: %x\n", dev->hdr_type);
+		pr_debug("    dev header type: %x\n", dev->hdr_type);
 	}
 
-	/* Ally all fixups */
-	pcibios_fixup_of_probed_bus(bus);
+	/* Apply all fixups necessary. We don't fixup the bus "self"
+	 * for an existing bridge that is being rescanned
+	 */
+	if (!rescan_existing)
+		pcibios_setup_bus_self(bus);
+	pcibios_setup_bus_devices(bus);
 
 	/* Now scan child busses */
 	list_for_each_entry(dev, &bus->devices, bus_list) {
@@ -233,7 +232,20 @@ void __devinit of_scan_bus(struct device_node *node,
 		}
 	}
 }
-EXPORT_SYMBOL(of_scan_bus);
+
+void __devinit of_scan_bus(struct device_node *node,
+			   struct pci_bus *bus)
+{
+	__of_scan_bus(node, bus, 0);
+}
+EXPORT_SYMBOL_GPL(of_scan_bus);
+
+void __devinit of_rescan_bus(struct device_node *node,
+			     struct pci_bus *bus)
+{
+	__of_scan_bus(node, bus, 1);
+}
+EXPORT_SYMBOL_GPL(of_rescan_bus);
 
 void __devinit of_scan_pci_bridge(struct device_node *node,
 				  struct pci_dev *dev)
@@ -245,7 +257,7 @@ void __devinit of_scan_pci_bridge(struct device_node *node,
 	unsigned int flags;
 	u64 size;
 
-	DBG("of_scan_pci_bridge(%s)\n", node->full_name);
+	pr_debug("of_scan_pci_bridge(%s)\n", node->full_name);
 
 	/* parse bus-range property */
 	busrange = of_get_property(node, "bus-range", &len);
@@ -309,12 +321,12 @@ void __devinit of_scan_pci_bridge(struct device_node *node,
 	}
 	sprintf(bus->name, "PCI Bus %04x:%02x", pci_domain_nr(bus),
 		bus->number);
-	DBG("    bus name: %s\n", bus->name);
+	pr_debug("    bus name: %s\n", bus->name);
 
 	mode = PCI_PROBE_NORMAL;
 	if (ppc_md.pci_probe_mode)
 		mode = ppc_md.pci_probe_mode(bus);
-	DBG("    probe mode: %d\n", mode);
+	pr_debug("    probe mode: %d\n", mode);
 
 	if (mode == PCI_PROBE_DEVTREE)
 		of_scan_bus(node, bus);
@@ -327,9 +339,10 @@ void __devinit scan_phb(struct pci_controller *hose)
 {
 	struct pci_bus *bus;
 	struct device_node *node = hose->dn;
-	int i, mode;
+	int mode;
 
-	DBG("PCI: Scanning PHB %s\n", node ? node->full_name : "<NO NAME>");
+	pr_debug("PCI: Scanning PHB %s\n",
+		 node ? node->full_name : "<NO NAME>");
 
 	/* Create an empty bus for the toplevel */
 	bus = pci_create_bus(hose->parent, hose->first_busno, hose->ops, node);
@@ -345,26 +358,13 @@ void __devinit scan_phb(struct pci_controller *hose)
 	pcibios_map_io_space(bus);
 
 	/* Wire up PHB bus resources */
-	DBG("PCI: PHB IO resource    = %016lx-%016lx [%lx]\n",
-	    hose->io_resource.start, hose->io_resource.end,
-	    hose->io_resource.flags);
-	bus->resource[0] = &hose->io_resource;
-	for (i = 0; i < 3; ++i) {
-		DBG("PCI: PHB MEM resource %d = %016lx-%016lx [%lx]\n", i,
-		    hose->mem_resources[i].start,
-		    hose->mem_resources[i].end,
-		    hose->mem_resources[i].flags);
-		bus->resource[i+1] = &hose->mem_resources[i];
-	}
-	DBG("PCI: PHB MEM offset     = %016lx\n", hose->pci_mem_offset);
-	DBG("PCI: PHB IO  offset     = %08lx\n",
-	    (unsigned long)hose->io_base_virt - _IO_BASE);
+	pcibios_setup_phb_resources(hose);
 
 	/* Get probe mode and perform scan */
 	mode = PCI_PROBE_NORMAL;
 	if (node && ppc_md.pci_probe_mode)
 		mode = ppc_md.pci_probe_mode(bus);
-	DBG("    probe mode: %d\n", mode);
+	pr_debug("    probe mode: %d\n", mode);
 	if (mode == PCI_PROBE_DEVTREE) {
 		bus->subordinate = hose->last_busno;
 		of_scan_bus(node, bus);
@@ -380,7 +380,7 @@ static int __init pcibios_init(void)
 
 	printk(KERN_INFO "PCI: Probing PCI hardware\n");
 
-	/* For now, override phys_mem_access_prot. If we need it,
+	/* For now, override phys_mem_access_prot. If we need it,g
 	 * later, we may move that initialization to each ppc_md
 	 */
 	ppc_md.phys_mem_access_prot = pci_phys_mem_access_prot;
@@ -388,6 +388,11 @@ static int __init pcibios_init(void)
 	if (pci_probe_only)
 		ppc_pci_flags |= PPC_PCI_PROBE_ONLY;
 
+	/* On ppc64, we always enable PCI domains and we keep domain 0
+	 * backward compatible in /proc for video cards
+	 */
+	ppc_pci_flags |= PPC_PCI_ENABLE_PROC_DOMAINS | PPC_PCI_COMPAT_DOMAIN_0;
+
 	/* Scan all of the recorded PCI controllers.  */
 	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
 		scan_phb(hose);
@@ -422,8 +427,8 @@ int pcibios_unmap_io_space(struct pci_bus *bus)
 	if (bus->self) {
 		struct resource *res = bus->resource[0];
 
-		DBG("IO unmapping for PCI-PCI bridge %s\n",
-		    pci_name(bus->self));
+		pr_debug("IO unmapping for PCI-PCI bridge %s\n",
+			 pci_name(bus->self));
 
 		__flush_hash_table_range(&init_mm, res->start + _IO_BASE,
 					 res->end + _IO_BASE + 1);
@@ -437,8 +442,8 @@ int pcibios_unmap_io_space(struct pci_bus *bus)
 	if (hose->io_base_alloc == 0)
 		return 0;
 
-	DBG("IO unmapping for PHB %s\n", hose->dn->full_name);
-	DBG("  alloc=0x%p\n", hose->io_base_alloc);
+	pr_debug("IO unmapping for PHB %s\n", hose->dn->full_name);
+	pr_debug("  alloc=0x%p\n", hose->io_base_alloc);
 
 	/* This is a PHB, we fully unmap the IO area */
 	vunmap(hose->io_base_alloc);
@@ -463,11 +468,11 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus)
 	 * thus HPTEs will be faulted in when needed
 	 */
 	if (bus->self) {
-		DBG("IO mapping for PCI-PCI bridge %s\n",
-		    pci_name(bus->self));
-		DBG("  virt=0x%016lx...0x%016lx\n",
-		    bus->resource[0]->start + _IO_BASE,
-		    bus->resource[0]->end + _IO_BASE);
+		pr_debug("IO mapping for PCI-PCI bridge %s\n",
+			 pci_name(bus->self));
+		pr_debug("  virt=0x%016lx...0x%016lx\n",
+			 bus->resource[0]->start + _IO_BASE,
+			 bus->resource[0]->end + _IO_BASE);
 		return 0;
 	}
 
@@ -496,11 +501,11 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus)
 	hose->io_base_virt = (void __iomem *)(area->addr +
 					      hose->io_base_phys - phys_page);
 
-	DBG("IO mapping for PHB %s\n", hose->dn->full_name);
-	DBG("  phys=0x%016lx, virt=0x%p (alloc=0x%p)\n",
-	    hose->io_base_phys, hose->io_base_virt, hose->io_base_alloc);
-	DBG("  size=0x%016lx (alloc=0x%016lx)\n",
-	    hose->pci_io_size, size_page);
+	pr_debug("IO mapping for PHB %s\n", hose->dn->full_name);
+	pr_debug("  phys=0x%016lx, virt=0x%p (alloc=0x%p)\n",
+		 hose->io_base_phys, hose->io_base_virt, hose->io_base_alloc);
+	pr_debug("  size=0x%016lx (alloc=0x%016lx)\n",
+		 hose->pci_io_size, size_page);
 
 	/* Establish the mapping */
 	if (__ioremap_at(phys_page, area->addr, size_page,
@@ -512,24 +517,13 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus)
 	hose->io_resource.start += io_virt_offset;
 	hose->io_resource.end += io_virt_offset;
 
-	DBG("  hose->io_resource=0x%016lx...0x%016lx\n",
-	    hose->io_resource.start, hose->io_resource.end);
+	pr_debug("  hose->io_resource=0x%016lx...0x%016lx\n",
+		 hose->io_resource.start, hose->io_resource.end);
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(pcibios_map_io_space);
 
-void __devinit pcibios_do_bus_setup(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	if (ppc_md.pci_dma_bus_setup)
-		ppc_md.pci_dma_bus_setup(bus);
-
-	list_for_each_entry(dev, &bus->devices, bus_list)
-		pcibios_setup_new_device(dev);
-}
-
 unsigned long pci_address_to_pio(phys_addr_t address)
 {
 	struct pci_controller *hose, *tmp;
@@ -566,9 +560,14 @@ long sys_pciconfig_iobase(long which, unsigned long in_bus,
 	 * G5 machines... So when something asks for bus 0 io base
 	 * (bus 0 is HT root), we return the AGP one instead.
 	 */
-	if (machine_is_compatible("MacRISC4"))
-		if (in_bus == 0)
+	if (in_bus == 0 && machine_is_compatible("MacRISC4")) {
+		struct device_node *agp;
+
+		agp = of_find_compatible_node(NULL, NULL, "u3-agp");
+		if (agp)
 			in_bus = 0xf0;
+		of_node_put(agp);
+	}
 
 	/* That syscall isn't quite compatible with PCI domains, but it's
 	 * used on pre-domains setup. We return the first match
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 260089dccfb0..c8b27bb4dbde 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -116,12 +116,6 @@ EXPORT_SYMBOL(giveup_spe);
 
 #ifndef CONFIG_PPC64
 EXPORT_SYMBOL(flush_instruction_cache);
-EXPORT_SYMBOL(flush_tlb_kernel_range);
-EXPORT_SYMBOL(flush_tlb_page);
-EXPORT_SYMBOL(_tlbie);
-#if defined(CONFIG_4xx) || defined(CONFIG_8xx) || defined(CONFIG_FSL_BOOKE)
-EXPORT_SYMBOL(_tlbil_va);
-#endif
 #endif
 EXPORT_SYMBOL(__flush_icache_range);
 EXPORT_SYMBOL(flush_dcache_range);
@@ -171,11 +165,11 @@ EXPORT_SYMBOL(timer_interrupt);
 EXPORT_SYMBOL(irq_desc);
 EXPORT_SYMBOL(tb_ticks_per_jiffy);
 EXPORT_SYMBOL(cacheable_memcpy);
+EXPORT_SYMBOL(cacheable_memzero);
 #endif
 
 #ifdef CONFIG_PPC32
-EXPORT_SYMBOL(next_mmu_context);
-EXPORT_SYMBOL(set_context);
+EXPORT_SYMBOL(switch_mmu_context);
 #endif
 
 #ifdef CONFIG_PPC_STD_MMU_32
diff --git a/arch/powerpc/kernel/ppc_save_regs.S b/arch/powerpc/kernel/ppc_save_regs.S
new file mode 100644
index 000000000000..5113bd2285e1
--- /dev/null
+++ b/arch/powerpc/kernel/ppc_save_regs.S
@@ -0,0 +1,74 @@
+/*
+ * Copyright (C) 1996 Paul Mackerras.
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ *
+ * NOTE: assert(sizeof(buf) > 23 * sizeof(long))
+ */
+#include <asm/processor.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+
+/*
+ * Grab the register values as they are now.
+ * This won't do a particularily good job because we really
+ * want our caller's caller's registers, and our caller has
+ * already executed its prologue.
+ * ToDo: We could reach back into the caller's save area to do
+ * a better job of representing the caller's state (note that
+ * that will be different for 32-bit and 64-bit, because of the
+ * different ABIs, though).
+ */
+_GLOBAL(ppc_save_regs)
+	PPC_STL	r0,0*SZL(r3)
+	PPC_STL	r2,2*SZL(r3)
+	PPC_STL	r3,3*SZL(r3)
+	PPC_STL	r4,4*SZL(r3)
+	PPC_STL	r5,5*SZL(r3)
+	PPC_STL	r6,6*SZL(r3)
+	PPC_STL	r7,7*SZL(r3)
+	PPC_STL	r8,8*SZL(r3)
+	PPC_STL	r9,9*SZL(r3)
+	PPC_STL	r10,10*SZL(r3)
+	PPC_STL	r11,11*SZL(r3)
+	PPC_STL	r12,12*SZL(r3)
+	PPC_STL	r13,13*SZL(r3)
+	PPC_STL	r14,14*SZL(r3)
+	PPC_STL	r15,15*SZL(r3)
+	PPC_STL	r16,16*SZL(r3)
+	PPC_STL	r17,17*SZL(r3)
+	PPC_STL	r18,18*SZL(r3)
+	PPC_STL	r19,19*SZL(r3)
+	PPC_STL	r20,20*SZL(r3)
+	PPC_STL	r21,21*SZL(r3)
+	PPC_STL	r22,22*SZL(r3)
+	PPC_STL	r23,23*SZL(r3)
+	PPC_STL	r24,24*SZL(r3)
+	PPC_STL	r25,25*SZL(r3)
+	PPC_STL	r26,26*SZL(r3)
+	PPC_STL	r27,27*SZL(r3)
+	PPC_STL	r28,28*SZL(r3)
+	PPC_STL	r29,29*SZL(r3)
+	PPC_STL	r30,30*SZL(r3)
+	PPC_STL	r31,31*SZL(r3)
+	/* go up one stack frame for SP */
+	PPC_LL	r4,0(r1)
+	PPC_STL	r4,1*SZL(r3)
+	/* get caller's LR */
+	PPC_LL	r0,LRSAVE(r4)
+	PPC_STL	r0,_NIP-STACK_FRAME_OVERHEAD(r3)
+	PPC_STL	r0,_LINK-STACK_FRAME_OVERHEAD(r3)
+	mfmsr	r0
+	PPC_STL	r0,_MSR-STACK_FRAME_OVERHEAD(r3)
+	mfctr	r0
+	PPC_STL	r0,_CTR-STACK_FRAME_OVERHEAD(r3)
+	mfxer	r0
+	PPC_STL	r0,_XER-STACK_FRAME_OVERHEAD(r3)
+	mfcr	r0
+	PPC_STL	r0,_CCR-STACK_FRAME_OVERHEAD(r3)
+	li	r0,0
+	PPC_STL	r0,_TRAP-STACK_FRAME_OVERHEAD(r3)
+	blr
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 957bded0020d..fb7049c054c0 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -33,6 +33,7 @@
 #include <linux/mqueue.h>
 #include <linux/hardirq.h>
 #include <linux/utsname.h>
+#include <linux/kernel_stat.h>
 
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
@@ -467,6 +468,8 @@ static struct regbit {
 	{MSR_VEC,	"VEC"},
 	{MSR_VSX,	"VSX"},
 	{MSR_ME,	"ME"},
+	{MSR_CE,	"CE"},
+	{MSR_DE,	"DE"},
 	{MSR_IR,	"IR"},
 	{MSR_DR,	"DR"},
 	{0,		NULL}
@@ -998,7 +1001,7 @@ unsigned long get_wchan(struct task_struct *p)
 	return 0;
 }
 
-static int kstack_depth_to_print = 64;
+static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH;
 
 void show_stack(struct task_struct *tsk, unsigned long *stack)
 {
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 3a2dc7e6586a..c09cffafb6ee 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -824,11 +824,11 @@ static int __init early_init_dt_scan_chosen(unsigned long node,
 #endif
 
 #ifdef CONFIG_KEXEC
-	lprop = (u64*)of_get_flat_dt_prop(node, "linux,crashkernel-base", NULL);
+	lprop = of_get_flat_dt_prop(node, "linux,crashkernel-base", NULL);
 	if (lprop)
 		crashk_res.start = *lprop;
 
-	lprop = (u64*)of_get_flat_dt_prop(node, "linux,crashkernel-size", NULL);
+	lprop = of_get_flat_dt_prop(node, "linux,crashkernel-size", NULL);
 	if (lprop)
 		crashk_res.end = crashk_res.start + *lprop - 1;
 #endif
@@ -893,12 +893,12 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 	u64 base, size, lmb_size;
 	unsigned int is_kexec_kdump = 0, rngs;
 
-	ls = (cell_t *)of_get_flat_dt_prop(node, "ibm,lmb-size", &l);
+	ls = of_get_flat_dt_prop(node, "ibm,lmb-size", &l);
 	if (ls == NULL || l < dt_root_size_cells * sizeof(cell_t))
 		return 0;
 	lmb_size = dt_mem_next_cell(dt_root_size_cells, &ls);
 
-	dm = (cell_t *)of_get_flat_dt_prop(node, "ibm,dynamic-memory", &l);
+	dm = of_get_flat_dt_prop(node, "ibm,dynamic-memory", &l);
 	if (dm == NULL || l < sizeof(cell_t))
 		return 0;
 
@@ -907,7 +907,7 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 		return 0;
 
 	/* check if this is a kexec/kdump kernel. */
-	usm = (cell_t *)of_get_flat_dt_prop(node, "linux,drconf-usable-memory",
+	usm = of_get_flat_dt_prop(node, "linux,drconf-usable-memory",
 						 &l);
 	if (usm != NULL)
 		is_kexec_kdump = 1;
@@ -981,9 +981,9 @@ static int __init early_init_dt_scan_memory(unsigned long node,
 	} else if (strcmp(type, "memory") != 0)
 		return 0;
 
-	reg = (cell_t *)of_get_flat_dt_prop(node, "linux,usable-memory", &l);
+	reg = of_get_flat_dt_prop(node, "linux,usable-memory", &l);
 	if (reg == NULL)
-		reg = (cell_t *)of_get_flat_dt_prop(node, "reg", &l);
+		reg = of_get_flat_dt_prop(node, "reg", &l);
 	if (reg == NULL)
 		return 0;
 
@@ -1160,6 +1160,8 @@ static inline void __init phyp_dump_reserve_mem(void) {}
 
 void __init early_init_devtree(void *params)
 {
+	unsigned long limit;
+
 	DBG(" -> early_init_devtree(%p)\n", params);
 
 	/* Setup flat device-tree pointer */
@@ -1200,7 +1202,19 @@ void __init early_init_devtree(void *params)
 	early_reserve_mem();
 	phyp_dump_reserve_mem();
 
-	lmb_enforce_memory_limit(memory_limit);
+	limit = memory_limit;
+	if (! limit) {
+		unsigned long memsize;
+
+		/* Ensure that total memory size is page-aligned, because
+		 * otherwise mark_bootmem() gets upset. */
+		lmb_analyze();
+		memsize = lmb_phys_mem_size();
+		if ((memsize & PAGE_MASK) != memsize)
+			limit = memsize & PAGE_MASK;
+	}
+	lmb_enforce_memory_limit(limit);
+
 	lmb_analyze();
 
 	DBG("Phys. mem: %lx\n", lmb_phys_mem_size());
@@ -1271,6 +1285,37 @@ struct device_node *of_find_node_by_phandle(phandle handle)
 EXPORT_SYMBOL(of_find_node_by_phandle);
 
 /**
+ *	of_find_next_cache_node - Find a node's subsidiary cache
+ *	@np:	node of type "cpu" or "cache"
+ *
+ *	Returns a node pointer with refcount incremented, use
+ *	of_node_put() on it when done.  Caller should hold a reference
+ *	to np.
+ */
+struct device_node *of_find_next_cache_node(struct device_node *np)
+{
+	struct device_node *child;
+	const phandle *handle;
+
+	handle = of_get_property(np, "l2-cache", NULL);
+	if (!handle)
+		handle = of_get_property(np, "next-level-cache", NULL);
+
+	if (handle)
+		return of_find_node_by_phandle(*handle);
+
+	/* OF on pmac has nodes instead of properties named "l2-cache"
+	 * beneath CPU nodes.
+	 */
+	if (!strcmp(np->type, "cpu"))
+		for_each_child_of_node(np, child)
+			if (!strcmp(child->type, "cache"))
+				return child;
+
+	return NULL;
+}
+
+/**
  *	of_find_all_nodes - Get next node in global list
  *	@prev:	Previous node or NULL to start iteration
  *		of_node_put() will be called on it
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 2445945d3761..7f1b33d5e30d 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1210,7 +1210,7 @@ static void __init prom_initialize_tce_table(void)
 		/* Initialize the table to have a one-to-one mapping
 		 * over the allocated size.
 		 */
-		tce_entryp = (unsigned long *)base;
+		tce_entryp = (u64 *)base;
 		for (i = 0; i < (minsize >> 3) ;tce_entryp++, i++) {
 			tce_entry = (i << PAGE_SHIFT);
 			tce_entry |= 0x3;
diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c
index a11d68976dc8..8f0856f312da 100644
--- a/arch/powerpc/kernel/prom_parse.c
+++ b/arch/powerpc/kernel/prom_parse.c
@@ -232,11 +232,6 @@ int of_pci_address_to_resource(struct device_node *dev, int bar,
 }
 EXPORT_SYMBOL_GPL(of_pci_address_to_resource);
 
-static u8 of_irq_pci_swizzle(u8 slot, u8 pin)
-{
-	return (((pin - 1) + slot) % 4) + 1;
-}
-
 int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq)
 {
 	struct device_node *dn, *ppnode;
@@ -306,7 +301,7 @@ int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq)
 		/* We can only get here if we hit a P2P bridge with no node,
 		 * let's do standard swizzling and try again
 		 */
-		lspec = of_irq_pci_swizzle(PCI_SLOT(pdev->devfn), lspec);
+		lspec = pci_swizzle_interrupt_pin(pdev, lspec);
 		pdev = ppdev;
 	}
 
@@ -734,10 +729,7 @@ void of_irq_map_init(unsigned int flags)
 	if (flags & OF_IMAP_NO_PHANDLE) {
 		struct device_node *np;
 
-		for(np = NULL; (np = of_find_all_nodes(np)) != NULL;) {
-			if (of_get_property(np, "interrupt-controller", NULL)
-			    == NULL)
-				continue;
+		for_each_node_with_property(np, "interrupt-controller") {
 			/* Skip /chosen/interrupt-controller */
 			if (strcmp(np->name, "chosen") == 0)
 				continue;
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 1f8505c23548..fdfe14c4bdef 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -566,6 +566,32 @@ int rtas_get_sensor(int sensor, int index, int *state)
 }
 EXPORT_SYMBOL(rtas_get_sensor);
 
+bool rtas_indicator_present(int token, int *maxindex)
+{
+	int proplen, count, i;
+	const struct indicator_elem {
+		u32 token;
+		u32 maxindex;
+	} *indicators;
+
+	indicators = of_get_property(rtas.dev, "rtas-indicators", &proplen);
+	if (!indicators)
+		return false;
+
+	count = proplen / sizeof(struct indicator_elem);
+
+	for (i = 0; i < count; i++) {
+		if (indicators[i].token != token)
+			continue;
+		if (maxindex)
+			*maxindex = indicators[i].maxindex;
+		return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL(rtas_indicator_present);
+
 int rtas_set_indicator(int indicator, int index, int new_value)
 {
 	int token = rtas_token("set-indicator");
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index 589a2797eac2..8869001ab5d7 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -301,51 +301,3 @@ void __init find_and_init_phbs(void)
 #endif /* CONFIG_PPC32 */
 	}
 }
-
-/* RPA-specific bits for removing PHBs */
-int pcibios_remove_root_bus(struct pci_controller *phb)
-{
-	struct pci_bus *b = phb->bus;
-	struct resource *res;
-	int rc, i;
-
-	res = b->resource[0];
-	if (!res->flags) {
-		printk(KERN_ERR "%s: no IO resource for PHB %s\n", __func__,
-				b->name);
-		return 1;
-	}
-
-	rc = pcibios_unmap_io_space(b);
-	if (rc) {
-		printk(KERN_ERR "%s: failed to unmap IO on bus %s\n",
-			__func__, b->name);
-		return 1;
-	}
-
-	if (release_resource(res)) {
-		printk(KERN_ERR "%s: failed to release IO on bus %s\n",
-				__func__, b->name);
-		return 1;
-	}
-
-	for (i = 1; i < 3; ++i) {
-		res = b->resource[i];
-		if (!res->flags && i == 0) {
-			printk(KERN_ERR "%s: no MEM resource for PHB %s\n",
-				__func__, b->name);
-			return 1;
-		}
-		if (res->flags && release_resource(res)) {
-			printk(KERN_ERR
-			       "%s: failed to release IO %d on bus %s\n",
-				__func__, i, b->name);
-			return 1;
-		}
-	}
-
-	pcibios_free_controller(phb);
-
-	return 0;
-}
-EXPORT_SYMBOL(pcibios_remove_root_bus);
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index c1a27626a940..9e1ca745d8f0 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -38,6 +38,7 @@
 #include <asm/time.h>
 #include <asm/serial.h>
 #include <asm/udbg.h>
+#include <asm/mmu_context.h>
 
 #include "setup.h"
 
@@ -49,12 +50,12 @@ int boot_cpuid;
 EXPORT_SYMBOL_GPL(boot_cpuid);
 int boot_cpuid_phys;
 
+int smp_hw_index[NR_CPUS];
+
 unsigned long ISA_DMA_THRESHOLD;
 unsigned int DMA_MODE_READ;
 unsigned int DMA_MODE_WRITE;
 
-int have_of = 1;
-
 #ifdef CONFIG_VGA_CONSOLE
 unsigned long vgacon_remap_base;
 EXPORT_SYMBOL(vgacon_remap_base);
@@ -97,6 +98,10 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
 			  PTRRELOC(&__start___ftr_fixup),
 			  PTRRELOC(&__stop___ftr_fixup));
 
+	do_feature_fixups(spec->mmu_features,
+			  PTRRELOC(&__start___mmu_ftr_fixup),
+			  PTRRELOC(&__stop___mmu_ftr_fixup));
+
 	do_lwsync_fixups(spec->cpu_features,
 			 PTRRELOC(&__start___lwsync_fixup),
 			 PTRRELOC(&__stop___lwsync_fixup));
@@ -121,6 +126,8 @@ notrace void __init machine_init(unsigned long dt_ptr)
 
 	probe_machine();
 
+	setup_kdump_trampoline();
+
 #ifdef CONFIG_6xx
 	if (cpu_has_feature(CPU_FTR_CAN_DOZE) ||
 	    cpu_has_feature(CPU_FTR_CAN_NAP))
@@ -326,4 +333,8 @@ void __init setup_arch(char **cmdline_p)
 	if ( ppc_md.progress ) ppc_md.progress("arch: exit", 0x3eab);
 
 	paging_init();
+
+	/* Initialize the MMU context management stuff */
+	mmu_context_init();
+
 }
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 169d74cef157..d8bd2161e738 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -70,7 +70,6 @@
 #define DBG(fmt...)
 #endif
 
-int have_of = 1;
 int boot_cpuid = 0;
 u64 ppc64_pft_size;
 
@@ -362,6 +361,8 @@ void __init setup_system(void)
 	 */
 	do_feature_fixups(cur_cpu_spec->cpu_features,
 			  &__start___ftr_fixup, &__stop___ftr_fixup);
+	do_feature_fixups(cur_cpu_spec->mmu_features,
+			  &__start___mmu_ftr_fixup, &__stop___mmu_ftr_fixup);
 	do_feature_fixups(powerpc_firmware_features,
 			  &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup);
 	do_lwsync_fixups(cur_cpu_spec->cpu_features,
@@ -606,8 +607,6 @@ void __init setup_per_cpu_areas(void)
 
 	for_each_possible_cpu(i) {
 		ptr = alloc_bootmem_pages_node(NODE_DATA(cpu_to_node(i)), size);
-		if (!ptr)
-			panic("Cannot allocate cpu data for CPU %d\n", i);
 
 		paca[i].data_offset = ptr - __per_cpu_start;
 		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
diff --git a/arch/powerpc/kernel/smp-tbsync.c b/arch/powerpc/kernel/smp-tbsync.c
index bc892e69b4f7..a5e54526403d 100644
--- a/arch/powerpc/kernel/smp-tbsync.c
+++ b/arch/powerpc/kernel/smp-tbsync.c
@@ -113,7 +113,7 @@ void __devinit smp_generic_give_timebase(void)
 {
 	int i, score, score2, old, min=0, max=5000, offset=1000;
 
-	printk("Synchronizing timebase\n");
+	pr_debug("Software timebase sync\n");
 
 	/* if this fails then this kernel won't work anyway... */
 	tbsync = kzalloc( sizeof(*tbsync), GFP_KERNEL );
@@ -123,13 +123,13 @@ void __devinit smp_generic_give_timebase(void)
 	while (!tbsync->ack)
 		barrier();
 
-	printk("Got ack\n");
+	pr_debug("Got ack\n");
 
 	/* binary search */
 	for (old = -1; old != offset ; offset = (min+max) / 2) {
 		score = start_contest(kSetAndTest, offset, NUM_ITER);
 
-		printk("score %d, offset %d\n", score, offset );
+		pr_debug("score %d, offset %d\n", score, offset );
 
 		if( score > 0 )
 			max = offset;
@@ -140,8 +140,8 @@ void __devinit smp_generic_give_timebase(void)
 	score = start_contest(kSetAndTest, min, NUM_ITER);
 	score2 = start_contest(kSetAndTest, max, NUM_ITER);
 
-	printk("Min %d (score %d), Max %d (score %d)\n",
-	       min, score, max, score2);
+	pr_debug("Min %d (score %d), Max %d (score %d)\n",
+		 min, score, max, score2);
 	score = abs(score);
 	score2 = abs(score2);
 	offset = (score < score2) ? min : max;
@@ -155,7 +155,7 @@ void __devinit smp_generic_give_timebase(void)
 		if (score2 <= score || score2 < 20)
 			break;
 	}
-	printk("Final offset: %d (%d/%d)\n", offset, score2, NUM_ITER );
+	pr_debug("Final offset: %d (%d/%d)\n", offset, score2, NUM_ITER );
 
 	/* exiting */
 	tbsync->cmd = kExit;
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index ff9f7010097d..65484b2200b3 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -57,16 +57,11 @@
 #define DBG(fmt...)
 #endif
 
-int smp_hw_index[NR_CPUS];
 struct thread_info *secondary_ti;
 
-cpumask_t cpu_possible_map = CPU_MASK_NONE;
-cpumask_t cpu_online_map = CPU_MASK_NONE;
 DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
 DEFINE_PER_CPU(cpumask_t, cpu_core_map) = CPU_MASK_NONE;
 
-EXPORT_SYMBOL(cpu_online_map);
-EXPORT_SYMBOL(cpu_possible_map);
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 
@@ -123,6 +118,65 @@ void smp_message_recv(int msg)
 	}
 }
 
+static irqreturn_t call_function_action(int irq, void *data)
+{
+	generic_smp_call_function_interrupt();
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t reschedule_action(int irq, void *data)
+{
+	/* we just need the return path side effect of checking need_resched */
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t call_function_single_action(int irq, void *data)
+{
+	generic_smp_call_function_single_interrupt();
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t debug_ipi_action(int irq, void *data)
+{
+	smp_message_recv(PPC_MSG_DEBUGGER_BREAK);
+	return IRQ_HANDLED;
+}
+
+static irq_handler_t smp_ipi_action[] = {
+	[PPC_MSG_CALL_FUNCTION] =  call_function_action,
+	[PPC_MSG_RESCHEDULE] = reschedule_action,
+	[PPC_MSG_CALL_FUNC_SINGLE] = call_function_single_action,
+	[PPC_MSG_DEBUGGER_BREAK] = debug_ipi_action,
+};
+
+const char *smp_ipi_name[] = {
+	[PPC_MSG_CALL_FUNCTION] =  "ipi call function",
+	[PPC_MSG_RESCHEDULE] = "ipi reschedule",
+	[PPC_MSG_CALL_FUNC_SINGLE] = "ipi call function single",
+	[PPC_MSG_DEBUGGER_BREAK] = "ipi debugger",
+};
+
+/* optional function to request ipi, for controllers with >= 4 ipis */
+int smp_request_message_ipi(int virq, int msg)
+{
+	int err;
+
+	if (msg < 0 || msg > PPC_MSG_DEBUGGER_BREAK) {
+		return -EINVAL;
+	}
+#if !defined(CONFIG_DEBUGGER) && !defined(CONFIG_KEXEC)
+	if (msg == PPC_MSG_DEBUGGER_BREAK) {
+		return 1;
+	}
+#endif
+	err = request_irq(virq, smp_ipi_action[msg], IRQF_DISABLED|IRQF_PERCPU,
+			  smp_ipi_name[msg], 0);
+	WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n",
+		virq, smp_ipi_name[msg], err);
+
+	return err;
+}
+
 void smp_send_reschedule(int cpu)
 {
 	if (likely(smp_ops))
@@ -408,8 +462,7 @@ out:
 static struct device_node *cpu_to_l2cache(int cpu)
 {
 	struct device_node *np;
-	const phandle *php;
-	phandle ph;
+	struct device_node *cache;
 
 	if (!cpu_present(cpu))
 		return NULL;
@@ -418,13 +471,11 @@ static struct device_node *cpu_to_l2cache(int cpu)
 	if (np == NULL)
 		return NULL;
 
-	php = of_get_property(np, "l2-cache", NULL);
-	if (php == NULL)
-		return NULL;
-	ph = *php;
+	cache = of_find_next_cache_node(np);
+
 	of_node_put(np);
 
-	return of_find_node_by_phandle(ph);
+	return cache;
 }
 
 /* Activate a secondary processor. */
diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c
index 77b7b34b5955..560c96119501 100644
--- a/arch/powerpc/kernel/swsusp.c
+++ b/arch/powerpc/kernel/swsusp.c
@@ -34,6 +34,6 @@ void save_processor_state(void)
 void restore_processor_state(void)
 {
 #ifdef CONFIG_PPC32
-	set_context(current->active_mm->context.id, current->active_mm->pgd);
+	switch_mmu_context(NULL, current->active_mm);
 #endif
 }
diff --git a/arch/powerpc/kernel/swsusp_32.S b/arch/powerpc/kernel/swsusp_32.S
index 77fc76607ab2..b47d8ceffb52 100644
--- a/arch/powerpc/kernel/swsusp_32.S
+++ b/arch/powerpc/kernel/swsusp_32.S
@@ -5,7 +5,7 @@
 #include <asm/thread_info.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
-
+#include <asm/mmu.h>
 
 /*
  * Structure for storing CPU registers on the save area.
@@ -279,7 +279,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	mtibatl	3,r4
 #endif
 
-BEGIN_FTR_SECTION
+BEGIN_MMU_FTR_SECTION
 	li	r4,0
 	mtspr	SPRN_DBAT4U,r4
 	mtspr	SPRN_DBAT4L,r4
@@ -297,7 +297,7 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_IBAT6L,r4
 	mtspr	SPRN_IBAT7U,r4
 	mtspr	SPRN_IBAT7L,r4
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
 
 	/* Flush all TLBs */
 	lis	r4,0x1000
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 20885a38237a..4a2ee08af6a7 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -18,6 +18,8 @@
 #include <asm/machdep.h>
 #include <asm/smp.h>
 
+#include "cacheinfo.h"
+
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 #include <asm/lppaca.h>
@@ -25,8 +27,6 @@
 
 static DEFINE_PER_CPU(struct cpu, cpu_devices);
 
-static DEFINE_PER_CPU(struct kobject *, cache_toplevel);
-
 /*
  * SMT snooze delay stuff, 64-bit only for now
  */
@@ -343,288 +343,6 @@ static struct sysdev_attribute pa6t_attrs[] = {
 #endif /* HAS_PPC_PMC_PA6T */
 #endif /* HAS_PPC_PMC_CLASSIC */
 
-struct cache_desc {
-	struct kobject kobj;
-	struct cache_desc *next;
-	const char *type;	/* Instruction, Data, or Unified */
-	u32 size;		/* total cache size in KB */
-	u32 line_size;		/* in bytes */
-	u32 nr_sets;		/* number of sets */
-	u32 level;		/* e.g. 1, 2, 3... */
-	u32 associativity;	/* e.g. 8-way... 0 is fully associative */
-};
-
-DEFINE_PER_CPU(struct cache_desc *, cache_desc);
-
-static struct cache_desc *kobj_to_cache_desc(struct kobject *k)
-{
-	return container_of(k, struct cache_desc, kobj);
-}
-
-static void cache_desc_release(struct kobject *k)
-{
-	struct cache_desc *desc = kobj_to_cache_desc(k);
-
-	pr_debug("%s: releasing %s\n", __func__, kobject_name(k));
-
-	if (desc->next)
-		kobject_put(&desc->next->kobj);
-
-	kfree(kobj_to_cache_desc(k));
-}
-
-static ssize_t cache_desc_show(struct kobject *k, struct attribute *attr, char *buf)
-{
-	struct kobj_attribute *kobj_attr;
-
-	kobj_attr = container_of(attr, struct kobj_attribute, attr);
-
-	return kobj_attr->show(k, kobj_attr, buf);
-}
-
-static struct sysfs_ops cache_desc_sysfs_ops = {
-	.show = cache_desc_show,
-};
-
-static struct kobj_type cache_desc_type = {
-	.release = cache_desc_release,
-	.sysfs_ops = &cache_desc_sysfs_ops,
-};
-
-static ssize_t cache_size_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
-{
-	struct cache_desc *cache = kobj_to_cache_desc(k);
-
-	return sprintf(buf, "%uK\n", cache->size);
-}
-
-static struct kobj_attribute cache_size_attr =
-	__ATTR(size, 0444, cache_size_show, NULL);
-
-static ssize_t cache_line_size_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
-{
-	struct cache_desc *cache = kobj_to_cache_desc(k);
-
-	return sprintf(buf, "%u\n", cache->line_size);
-}
-
-static struct kobj_attribute cache_line_size_attr =
-	__ATTR(coherency_line_size, 0444, cache_line_size_show, NULL);
-
-static ssize_t cache_nr_sets_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
-{
-	struct cache_desc *cache = kobj_to_cache_desc(k);
-
-	return sprintf(buf, "%u\n", cache->nr_sets);
-}
-
-static struct kobj_attribute cache_nr_sets_attr =
-	__ATTR(number_of_sets, 0444, cache_nr_sets_show, NULL);
-
-static ssize_t cache_type_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
-{
-	struct cache_desc *cache = kobj_to_cache_desc(k);
-
-	return sprintf(buf, "%s\n", cache->type);
-}
-
-static struct kobj_attribute cache_type_attr =
-	__ATTR(type, 0444, cache_type_show, NULL);
-
-static ssize_t cache_level_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
-{
-	struct cache_desc *cache = kobj_to_cache_desc(k);
-
-	return sprintf(buf, "%u\n", cache->level);
-}
-
-static struct kobj_attribute cache_level_attr =
-	__ATTR(level, 0444, cache_level_show, NULL);
-
-static ssize_t cache_assoc_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
-{
-	struct cache_desc *cache = kobj_to_cache_desc(k);
-
-	return sprintf(buf, "%u\n", cache->associativity);
-}
-
-static struct kobj_attribute cache_assoc_attr =
-	__ATTR(ways_of_associativity, 0444, cache_assoc_show, NULL);
-
-struct cache_desc_info {
-	const char *type;
-	const char *size_prop;
-	const char *line_size_prop;
-	const char *nr_sets_prop;
-};
-
-/* PowerPC Processor binding says the [di]-cache-* must be equal on
- * unified caches, so just use d-cache properties. */
-static struct cache_desc_info ucache_info = {
-	.type = "Unified",
-	.size_prop = "d-cache-size",
-	.line_size_prop = "d-cache-line-size",
-	.nr_sets_prop = "d-cache-sets",
-};
-
-static struct cache_desc_info dcache_info = {
-	.type = "Data",
-	.size_prop = "d-cache-size",
-	.line_size_prop = "d-cache-line-size",
-	.nr_sets_prop = "d-cache-sets",
-};
-
-static struct cache_desc_info icache_info = {
-	.type = "Instruction",
-	.size_prop = "i-cache-size",
-	.line_size_prop = "i-cache-line-size",
-	.nr_sets_prop = "i-cache-sets",
-};
-
-static struct cache_desc * __cpuinit create_cache_desc(struct device_node *np, struct kobject *parent, int index, int level, struct cache_desc_info *info)
-{
-	const u32 *cache_line_size;
-	struct cache_desc *new;
-	const u32 *cache_size;
-	const u32 *nr_sets;
-	int rc;
-
-	new = kzalloc(sizeof(*new), GFP_KERNEL);
-	if (!new)
-		return NULL;
-
-	rc = kobject_init_and_add(&new->kobj, &cache_desc_type, parent,
-				  "index%d", index);
-	if (rc)
-		goto err;
-
-	/* type */
-	new->type = info->type;
-	rc = sysfs_create_file(&new->kobj, &cache_type_attr.attr);
-	WARN_ON(rc);
-
-	/* level */
-	new->level = level;
-	rc = sysfs_create_file(&new->kobj, &cache_level_attr.attr);
-	WARN_ON(rc);
-
-	/* size */
-	cache_size = of_get_property(np, info->size_prop, NULL);
-	if (cache_size) {
-		new->size = *cache_size / 1024;
-		rc = sysfs_create_file(&new->kobj,
-				       &cache_size_attr.attr);
-		WARN_ON(rc);
-	}
-
-	/* coherency_line_size */
-	cache_line_size = of_get_property(np, info->line_size_prop, NULL);
-	if (cache_line_size) {
-		new->line_size = *cache_line_size;
-		rc = sysfs_create_file(&new->kobj,
-				       &cache_line_size_attr.attr);
-		WARN_ON(rc);
-	}
-
-	/* number_of_sets */
-	nr_sets = of_get_property(np, info->nr_sets_prop, NULL);
-	if (nr_sets) {
-		new->nr_sets = *nr_sets;
-		rc = sysfs_create_file(&new->kobj,
-				       &cache_nr_sets_attr.attr);
-		WARN_ON(rc);
-	}
-
-	/* ways_of_associativity */
-	if (new->nr_sets == 1) {
-		/* fully associative */
-		new->associativity = 0;
-		goto create_assoc;
-	}
-
-	if (new->nr_sets && new->size && new->line_size) {
-		/* If we have values for all of these we can derive
-		 * the associativity. */
-		new->associativity =
-			((new->size * 1024) / new->nr_sets) / new->line_size;
-create_assoc:
-		rc = sysfs_create_file(&new->kobj,
-				       &cache_assoc_attr.attr);
-		WARN_ON(rc);
-	}
-
-	return new;
-err:
-	kfree(new);
-	return NULL;
-}
-
-static bool cache_is_unified(struct device_node *np)
-{
-	return of_get_property(np, "cache-unified", NULL);
-}
-
-static struct cache_desc * __cpuinit create_cache_index_info(struct device_node *np, struct kobject *parent, int index, int level)
-{
-	const phandle *next_cache_phandle;
-	struct device_node *next_cache;
-	struct cache_desc *new, **end;
-
-	pr_debug("%s(node = %s, index = %d)\n", __func__, np->full_name, index);
-
-	if (cache_is_unified(np)) {
-		new = create_cache_desc(np, parent, index, level,
-					&ucache_info);
-	} else {
-		new = create_cache_desc(np, parent, index, level,
-					&dcache_info);
-		if (new) {
-			index++;
-			new->next = create_cache_desc(np, parent, index, level,
-						      &icache_info);
-		}
-	}
-	if (!new)
-		return NULL;
-
-	end = &new->next;
-	while (*end)
-		end = &(*end)->next;
-
-	next_cache_phandle = of_get_property(np, "l2-cache", NULL);
-	if (!next_cache_phandle)
-		goto out;
-
-	next_cache = of_find_node_by_phandle(*next_cache_phandle);
-	if (!next_cache)
-		goto out;
-
-	*end = create_cache_index_info(next_cache, parent, ++index, ++level);
-
-	of_node_put(next_cache);
-out:
-	return new;
-}
-
-static void __cpuinit create_cache_info(struct sys_device *sysdev)
-{
-	struct kobject *cache_toplevel;
-	struct device_node *np = NULL;
-	int cpu = sysdev->id;
-
-	cache_toplevel = kobject_create_and_add("cache", &sysdev->kobj);
-	if (!cache_toplevel)
-		return;
-	per_cpu(cache_toplevel, cpu) = cache_toplevel;
-	np = of_get_cpu_node(cpu, NULL);
-	if (np != NULL) {
-		per_cpu(cache_desc, cpu) =
-			create_cache_index_info(np, cache_toplevel, 0, 1);
-		of_node_put(np);
-	}
-	return;
-}
-
 static void __cpuinit register_cpu_online(unsigned int cpu)
 {
 	struct cpu *c = &per_cpu(cpu_devices, cpu);
@@ -689,25 +407,10 @@ static void __cpuinit register_cpu_online(unsigned int cpu)
 		sysdev_create_file(s, &attr_dscr);
 #endif /* CONFIG_PPC64 */
 
-	create_cache_info(s);
+	cacheinfo_cpu_online(cpu);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static void remove_cache_info(struct sys_device *sysdev)
-{
-	struct kobject *cache_toplevel;
-	struct cache_desc *cache_desc;
-	int cpu = sysdev->id;
-
-	cache_desc = per_cpu(cache_desc, cpu);
-	if (cache_desc != NULL)
-		kobject_put(&cache_desc->kobj);
-
-	cache_toplevel = per_cpu(cache_toplevel, cpu);
-	if (cache_toplevel != NULL)
-		kobject_put(cache_toplevel);
-}
-
 static void unregister_cpu_online(unsigned int cpu)
 {
 	struct cpu *c = &per_cpu(cpu_devices, cpu);
@@ -774,7 +477,7 @@ static void unregister_cpu_online(unsigned int cpu)
 		sysdev_remove_file(s, &attr_dscr);
 #endif /* CONFIG_PPC64 */
 
-	remove_cache_info(s);
+	cacheinfo_cpu_offline(cpu);
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index e2ee66b5831d..c9564031a2a9 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -164,8 +164,6 @@ static u64 tb_to_ns_scale __read_mostly;
 static unsigned tb_to_ns_shift __read_mostly;
 static unsigned long boot_tb __read_mostly;
 
-static struct gettimeofday_struct do_gtod;
-
 extern struct timezone sys_tz;
 static long timezone_offset;
 
@@ -258,8 +256,10 @@ void account_system_vtime(struct task_struct *tsk)
 		delta += sys_time;
 		get_paca()->system_time = 0;
 	}
-	account_system_time(tsk, 0, delta);
-	account_system_time_scaled(tsk, deltascaled);
+	if (in_irq() || idle_task(smp_processor_id()) != tsk)
+		account_system_time(tsk, 0, delta, deltascaled);
+	else
+		account_idle_time(delta);
 	per_cpu(cputime_last_delta, smp_processor_id()) = delta;
 	per_cpu(cputime_scaled_last_delta, smp_processor_id()) = deltascaled;
 	local_irq_restore(flags);
@@ -277,10 +277,8 @@ void account_process_tick(struct task_struct *tsk, int user_tick)
 
 	utime = get_paca()->user_time;
 	get_paca()->user_time = 0;
-	account_user_time(tsk, utime);
-
 	utimescaled = cputime_to_scaled(utime);
-	account_user_time_scaled(tsk, utimescaled);
+	account_user_time(tsk, utime, utimescaled);
 }
 
 /*
@@ -340,8 +338,12 @@ void calculate_steal_time(void)
 	tb = mftb();
 	purr = mfspr(SPRN_PURR);
 	stolen = (tb - pme->tb) - (purr - pme->purr);
-	if (stolen > 0)
-		account_steal_time(current, stolen);
+	if (stolen > 0) {
+		if (idle_task(smp_processor_id()) != current)
+			account_steal_time(stolen);
+		else
+			account_idle_time(stolen);
+	}
 	pme->tb = tb;
 	pme->purr = purr;
 }
@@ -415,31 +417,9 @@ void udelay(unsigned long usecs)
 }
 EXPORT_SYMBOL(udelay);
 
-
-/*
- * There are two copies of tb_to_xs and stamp_xsec so that no
- * lock is needed to access and use these values in
- * do_gettimeofday.  We alternate the copies and as long as a
- * reasonable time elapses between changes, there will never
- * be inconsistent values.  ntpd has a minimum of one minute
- * between updates.
- */
 static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec,
 			       u64 new_tb_to_xs)
 {
-	unsigned temp_idx;
-	struct gettimeofday_vars *temp_varp;
-
-	temp_idx = (do_gtod.var_idx == 0);
-	temp_varp = &do_gtod.vars[temp_idx];
-
-	temp_varp->tb_to_xs = new_tb_to_xs;
-	temp_varp->tb_orig_stamp = new_tb_stamp;
-	temp_varp->stamp_xsec = new_stamp_xsec;
-	smp_mb();
-	do_gtod.varp = temp_varp;
-	do_gtod.var_idx = temp_idx;
-
 	/*
 	 * tb_update_count is used to allow the userspace gettimeofday code
 	 * to assure itself that it sees a consistent view of the tb_to_xs and
@@ -456,6 +436,7 @@ static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec,
 	vdso_data->tb_to_xs = new_tb_to_xs;
 	vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec;
 	vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec;
+	vdso_data->stamp_xtime = xtime;
 	smp_wmb();
 	++(vdso_data->tb_update_count);
 }
@@ -514,9 +495,7 @@ static int __init iSeries_tb_recal(void)
 				tb_ticks_per_sec   = new_tb_ticks_per_sec;
 				calc_cputime_factors();
 				div128_by_32( XSEC_PER_SEC, 0, tb_ticks_per_sec, &divres );
-				do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
 				tb_to_xs = divres.result_low;
-				do_gtod.varp->tb_to_xs = tb_to_xs;
 				vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
 				vdso_data->tb_to_xs = tb_to_xs;
 			}
@@ -869,7 +848,7 @@ static void register_decrementer_clockevent(int cpu)
 	struct clock_event_device *dec = &per_cpu(decrementers, cpu).event;
 
 	*dec = decrementer_clockevent;
-	dec->cpumask = cpumask_of_cpu(cpu);
+	dec->cpumask = cpumask_of(cpu);
 
 	printk(KERN_DEBUG "clockevent: %s mult[%lx] shift[%d] cpu[%d]\n",
 	       dec->name, dec->mult, dec->shift, cpu);
@@ -988,15 +967,6 @@ void __init time_init(void)
 		sys_tz.tz_dsttime = 0;
         }
 
-	do_gtod.varp = &do_gtod.vars[0];
-	do_gtod.var_idx = 0;
-	do_gtod.varp->tb_orig_stamp = tb_last_jiffy;
-	__get_cpu_var(last_jiffy) = tb_last_jiffy;
-	do_gtod.varp->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC;
-	do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
-	do_gtod.varp->tb_to_xs = tb_to_xs;
-	do_gtod.tb_to_us = tb_to_us;
-
 	vdso_data->tb_orig_stamp = tb_last_jiffy;
 	vdso_data->tb_update_count = 0;
 	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index f5def6cf5cd6..5457e9575685 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1160,37 +1160,85 @@ void CacheLockingException(struct pt_regs *regs, unsigned long address,
 #ifdef CONFIG_SPE
 void SPEFloatingPointException(struct pt_regs *regs)
 {
+	extern int do_spe_mathemu(struct pt_regs *regs);
 	unsigned long spefscr;
 	int fpexc_mode;
 	int code = 0;
+	int err;
+
+	preempt_disable();
+	if (regs->msr & MSR_SPE)
+		giveup_spe(current);
+	preempt_enable();
 
 	spefscr = current->thread.spefscr;
 	fpexc_mode = current->thread.fpexc_mode;
 
-	/* Hardware does not neccessarily set sticky
-	 * underflow/overflow/invalid flags */
 	if ((spefscr & SPEFSCR_FOVF) && (fpexc_mode & PR_FP_EXC_OVF)) {
 		code = FPE_FLTOVF;
-		spefscr |= SPEFSCR_FOVFS;
 	}
 	else if ((spefscr & SPEFSCR_FUNF) && (fpexc_mode & PR_FP_EXC_UND)) {
 		code = FPE_FLTUND;
-		spefscr |= SPEFSCR_FUNFS;
 	}
 	else if ((spefscr & SPEFSCR_FDBZ) && (fpexc_mode & PR_FP_EXC_DIV))
 		code = FPE_FLTDIV;
 	else if ((spefscr & SPEFSCR_FINV) && (fpexc_mode & PR_FP_EXC_INV)) {
 		code = FPE_FLTINV;
-		spefscr |= SPEFSCR_FINVS;
 	}
 	else if ((spefscr & (SPEFSCR_FG | SPEFSCR_FX)) && (fpexc_mode & PR_FP_EXC_RES))
 		code = FPE_FLTRES;
 
-	current->thread.spefscr = spefscr;
+	err = do_spe_mathemu(regs);
+	if (err == 0) {
+		regs->nip += 4;		/* skip emulated instruction */
+		emulate_single_step(regs);
+		return;
+	}
+
+	if (err == -EFAULT) {
+		/* got an error reading the instruction */
+		_exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip);
+	} else if (err == -EINVAL) {
+		/* didn't recognize the instruction */
+		printk(KERN_ERR "unrecognized spe instruction "
+		       "in %s at %lx\n", current->comm, regs->nip);
+	} else {
+		_exception(SIGFPE, regs, code, regs->nip);
+	}
 
-	_exception(SIGFPE, regs, code, regs->nip);
 	return;
 }
+
+void SPEFloatingPointRoundException(struct pt_regs *regs)
+{
+	extern int speround_handler(struct pt_regs *regs);
+	int err;
+
+	preempt_disable();
+	if (regs->msr & MSR_SPE)
+		giveup_spe(current);
+	preempt_enable();
+
+	regs->nip -= 4;
+	err = speround_handler(regs);
+	if (err == 0) {
+		regs->nip += 4;		/* skip emulated instruction */
+		emulate_single_step(regs);
+		return;
+	}
+
+	if (err == -EFAULT) {
+		/* got an error reading the instruction */
+		_exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip);
+	} else if (err == -EINVAL) {
+		/* didn't recognize the instruction */
+		printk(KERN_ERR "unrecognized spe instruction "
+		       "in %s at %lx\n", current->comm, regs->nip);
+	} else {
+		_exception(SIGFPE, regs, 0, regs->nip);
+		return;
+	}
+}
 #endif
 
 /*
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 65639a43e644..ad06d5c75b15 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -184,8 +184,7 @@ static void dump_vdso_pages(struct vm_area_struct * vma)
  * This is called from binfmt_elf, we create the special vma for the
  * vDSO and insert it into the mm struct tree
  */
-int arch_setup_additional_pages(struct linux_binprm *bprm,
-				int executable_stack)
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
 	struct page **vdso_pagelist;
@@ -567,6 +566,11 @@ static __init int vdso_fixup_features(struct lib32_elfinfo *v32,
 		do_feature_fixups(cur_cpu_spec->cpu_features,
 				  start64, start64 + size64);
 
+	start64 = find_section64(v64->hdr, "__mmu_ftr_fixup", &size64);
+	if (start64)
+		do_feature_fixups(cur_cpu_spec->mmu_features,
+				  start64, start64 + size64);
+
 	start64 = find_section64(v64->hdr, "__fw_ftr_fixup", &size64);
 	if (start64)
 		do_feature_fixups(powerpc_firmware_features,
@@ -583,6 +587,11 @@ static __init int vdso_fixup_features(struct lib32_elfinfo *v32,
 		do_feature_fixups(cur_cpu_spec->cpu_features,
 				  start32, start32 + size32);
 
+	start32 = find_section32(v32->hdr, "__mmu_ftr_fixup", &size32);
+	if (start32)
+		do_feature_fixups(cur_cpu_spec->mmu_features,
+				  start32, start32 + size32);
+
 #ifdef CONFIG_PPC64
 	start32 = find_section32(v32->hdr, "__fw_ftr_fixup", &size32);
 	if (start32)
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index 72ca26df457e..ee038d4bf252 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -16,6 +16,13 @@
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
 
+/* Offset for the low 32-bit part of a field of long type */
+#ifdef CONFIG_PPC64
+#define LOPART	4
+#else
+#define LOPART	0
+#endif
+
 	.text
 /*
  * Exact prototype of gettimeofday
@@ -90,101 +97,53 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 
 	mflr	r12			/* r12 saves lr */
   .cfi_register lr,r12
-	mr	r10,r3			/* r10 saves id */
 	mr	r11,r4			/* r11 saves tp */
 	bl	__get_datapage@local	/* get data page */
 	mr	r9,r3			/* datapage ptr in r9 */
-	beq	cr1,50f			/* if monotonic -> jump there */
-
-	/*
-	 * CLOCK_REALTIME
-	 */
-
-	bl	__do_get_xsec@local	/* get xsec from tb & kernel */
-	bne-	98f			/* out of line -> do syscall */
-
-	/* seconds are xsec >> 20 */
-	rlwinm	r5,r4,12,20,31
-	rlwimi	r5,r3,12,0,19
-	stw	r5,TSPC32_TV_SEC(r11)
 
-	/* get remaining xsec and convert to nsec. we scale
-	 * up remaining xsec by 12 bits and get the top 32 bits
-	 * of the multiplication, then we multiply by 1000
-	 */
-	rlwinm	r5,r4,12,0,19
-	lis	r6,1000000@h
-	ori	r6,r6,1000000@l
-	mulhwu	r5,r5,r6
-	mulli	r5,r5,1000
-	stw	r5,TSPC32_TV_NSEC(r11)
-	mtlr	r12
-	crclr	cr0*4+so
-	li	r3,0
-	blr
+50:	bl	__do_get_tspec@local	/* get sec/nsec from tb & kernel */
+	bne	cr1,80f			/* not monotonic -> all done */
 
 	/*
 	 * CLOCK_MONOTONIC
 	 */
 
-50:	bl	__do_get_xsec@local	/* get xsec from tb & kernel */
-	bne-	98f			/* out of line -> do syscall */
-
-	/* seconds are xsec >> 20 */
-	rlwinm	r6,r4,12,20,31
-	rlwimi	r6,r3,12,0,19
-
-	/* get remaining xsec and convert to nsec. we scale
-	 * up remaining xsec by 12 bits and get the top 32 bits
-	 * of the multiplication, then we multiply by 1000
-	 */
-	rlwinm	r7,r4,12,0,19
-	lis	r5,1000000@h
-	ori	r5,r5,1000000@l
-	mulhwu	r7,r7,r5
-	mulli	r7,r7,1000
-
 	/* now we must fixup using wall to monotonic. We need to snapshot
 	 * that value and do the counter trick again. Fortunately, we still
 	 * have the counter value in r8 that was returned by __do_get_xsec.
-	 * At this point, r6,r7 contain our sec/nsec values, r3,r4 and r5
-	 * can be used
+	 * At this point, r3,r4 contain our sec/nsec values, r5 and r6
+	 * can be used, r7 contains NSEC_PER_SEC.
 	 */
 
-	lwz	r3,WTOM_CLOCK_SEC(r9)
-	lwz	r4,WTOM_CLOCK_NSEC(r9)
+	lwz	r5,WTOM_CLOCK_SEC(r9)
+	lwz	r6,WTOM_CLOCK_NSEC(r9)
 
-	/* We now have our result in r3,r4. We create a fake dependency
-	 * on that result and re-check the counter
+	/* We now have our offset in r5,r6. We create a fake dependency
+	 * on that value and re-check the counter
 	 */
-	or	r5,r4,r3
-	xor	r0,r5,r5
+	or	r0,r6,r5
+	xor	r0,r0,r0
 	add	r9,r9,r0
-#ifdef CONFIG_PPC64
-	lwz	r0,(CFG_TB_UPDATE_COUNT+4)(r9)
-#else
-	lwz	r0,(CFG_TB_UPDATE_COUNT)(r9)
-#endif
+	lwz	r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
         cmpl    cr0,r8,r0		/* check if updated */
 	bne-	50b
 
-	/* Calculate and store result. Note that this mimmics the C code,
+	/* Calculate and store result. Note that this mimics the C code,
 	 * which may cause funny results if nsec goes negative... is that
 	 * possible at all ?
 	 */
-	add	r3,r3,r6
-	add	r4,r4,r7
-	lis	r5,NSEC_PER_SEC@h
-	ori	r5,r5,NSEC_PER_SEC@l
-	cmpl	cr0,r4,r5
-	cmpli	cr1,r4,0
+	add	r3,r3,r5
+	add	r4,r4,r6
+	cmpw	cr0,r4,r7
+	cmpwi	cr1,r4,0
 	blt	1f
-	subf	r4,r5,r4
+	subf	r4,r7,r4
 	addi	r3,r3,1
-1:	bge	cr1,1f
+1:	bge	cr1,80f
 	addi	r3,r3,-1
-	add	r4,r4,r5
-1:	stw	r3,TSPC32_TV_SEC(r11)
+	add	r4,r4,r7
+
+80:	stw	r3,TSPC32_TV_SEC(r11)
 	stw	r4,TSPC32_TV_NSEC(r11)
 
 	mtlr	r12
@@ -195,10 +154,6 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	/*
 	 * syscall fallback
 	 */
-98:
-	mtlr	r12
-	mr	r3,r10
-	mr	r4,r11
 99:
 	li	r0,__NR_clock_gettime
 	sc
@@ -254,11 +209,7 @@ __do_get_xsec:
 	/* Check for update count & load values. We use the low
 	 * order 32 bits of the update count
 	 */
-#ifdef CONFIG_PPC64
-1:	lwz	r8,(CFG_TB_UPDATE_COUNT+4)(r9)
-#else
-1:	lwz	r8,(CFG_TB_UPDATE_COUNT)(r9)
-#endif
+1:	lwz	r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
 	andi.	r0,r8,1			/* pending update ? loop */
 	bne-	1b
 	xor	r0,r8,r8		/* create dependency */
@@ -305,11 +256,7 @@ __do_get_xsec:
 	or	r6,r4,r3
 	xor	r0,r6,r6
 	add	r9,r9,r0
-#ifdef CONFIG_PPC64
-	lwz	r0,(CFG_TB_UPDATE_COUNT+4)(r9)
-#else
-	lwz	r0,(CFG_TB_UPDATE_COUNT)(r9)
-#endif
+	lwz	r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
         cmpl    cr0,r8,r0		/* check if updated */
 	bne-	1b
 
@@ -322,3 +269,98 @@ __do_get_xsec:
 	 */
 3:	blr
   .cfi_endproc
+
+/*
+ * This is the core of clock_gettime(), it returns the current
+ * time in seconds and nanoseconds in r3 and r4.
+ * It expects the datapage ptr in r9 and doesn't clobber it.
+ * It clobbers r0, r5, r6, r10 and returns NSEC_PER_SEC in r7.
+ * On return, r8 contains the counter value that can be reused.
+ * This clobbers cr0 but not any other cr field.
+ */
+__do_get_tspec:
+  .cfi_startproc
+	/* Check for update count & load values. We use the low
+	 * order 32 bits of the update count
+	 */
+1:	lwz	r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
+	andi.	r0,r8,1			/* pending update ? loop */
+	bne-	1b
+	xor	r0,r8,r8		/* create dependency */
+	add	r9,r9,r0
+
+	/* Load orig stamp (offset to TB) */
+	lwz	r5,CFG_TB_ORIG_STAMP(r9)
+	lwz	r6,(CFG_TB_ORIG_STAMP+4)(r9)
+
+	/* Get a stable TB value */
+2:	mftbu	r3
+	mftbl	r4
+	mftbu	r0
+	cmpl	cr0,r3,r0
+	bne-	2b
+
+	/* Subtract tb orig stamp and shift left 12 bits.
+	 */
+	subfc	r7,r6,r4
+	subfe	r0,r5,r3
+	slwi	r0,r0,12
+	rlwimi.	r0,r7,12,20,31
+	slwi	r7,r7,12
+
+	/* Load scale factor & do multiplication */
+	lwz	r5,CFG_TB_TO_XS(r9)	/* load values */
+	lwz	r6,(CFG_TB_TO_XS+4)(r9)
+	mulhwu	r3,r7,r6
+	mullw	r10,r7,r5
+	mulhwu	r4,r7,r5
+	addc	r10,r3,r10
+	li	r3,0
+
+	beq+	4f			/* skip high part computation if 0 */
+	mulhwu	r3,r0,r5
+	mullw	r7,r0,r5
+	mulhwu	r5,r0,r6
+	mullw	r6,r0,r6
+	adde	r4,r4,r7
+	addze	r3,r3
+	addc	r4,r4,r5
+	addze	r3,r3
+	addc	r10,r10,r6
+
+4:	addze	r4,r4			/* add in carry */
+	lis	r7,NSEC_PER_SEC@h
+	ori	r7,r7,NSEC_PER_SEC@l
+	mulhwu	r4,r4,r7		/* convert to nanoseconds */
+
+	/* At this point, we have seconds & nanoseconds since the xtime
+	 * stamp in r3+CA and r4.  Load & add the xtime stamp.
+	 */
+#ifdef CONFIG_PPC64
+	lwz	r5,STAMP_XTIME+TSPC64_TV_SEC+LOPART(r9)
+	lwz	r6,STAMP_XTIME+TSPC64_TV_NSEC+LOPART(r9)
+#else
+	lwz	r5,STAMP_XTIME+TSPC32_TV_SEC(r9)
+	lwz	r6,STAMP_XTIME+TSPC32_TV_NSEC(r9)
+#endif
+	add	r4,r4,r6
+	adde	r3,r3,r5
+
+	/* We now have our result in r3,r4. We create a fake dependency
+	 * on that result and re-check the counter
+	 */
+	or	r6,r4,r3
+	xor	r0,r6,r6
+	add	r9,r9,r0
+	lwz	r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
+        cmpl    cr0,r8,r0		/* check if updated */
+	bne-	1b
+
+	/* check for nanosecond overflow and adjust if necessary */
+	cmpw	r4,r7
+	bltlr				/* all done if no overflow */
+	subf	r4,r7,r4		/* adjust if overflow */
+	addi	r3,r3,1
+
+	blr
+  .cfi_endproc
diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S
index be3b6a41dc09..904ef1360dd7 100644
--- a/arch/powerpc/kernel/vdso32/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S
@@ -34,6 +34,9 @@ SECTIONS
 	__ftr_fixup	: { *(__ftr_fixup) }
 
 	. = ALIGN(8);
+	__mmu_ftr_fixup	: { *(__mmu_ftr_fixup) }
+
+	. = ALIGN(8);
 	__lwsync_fixup	: { *(__lwsync_fixup) }
 
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index c6401f9e37f1..262cd5857a56 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -75,90 +75,49 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 
 	mflr	r12			/* r12 saves lr */
   .cfi_register lr,r12
-	mr	r10,r3			/* r10 saves id */
 	mr	r11,r4			/* r11 saves tp */
 	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
-	beq	cr1,50f			/* if monotonic -> jump there */
-
-	/*
-	 * CLOCK_REALTIME
-	 */
-
-	bl	V_LOCAL_FUNC(__do_get_xsec)	/* get xsec from tb & kernel */
-
-	lis     r7,15			/* r7 = 1000000 = USEC_PER_SEC */
-	ori     r7,r7,16960
-	rldicl  r5,r4,44,20		/* r5 = sec = xsec / XSEC_PER_SEC */
-	rldicr  r6,r5,20,43		/* r6 = sec * XSEC_PER_SEC */
-	std	r5,TSPC64_TV_SEC(r11)	/* store sec in tv */
-	subf	r0,r6,r4		/* r0 = xsec = (xsec - r6) */
-	mulld   r0,r0,r7		/* usec = (xsec * USEC_PER_SEC) /
-					 * XSEC_PER_SEC
-					 */
-	rldicl  r0,r0,44,20
-	mulli	r0,r0,1000		/* nsec = usec * 1000 */
-	std	r0,TSPC64_TV_NSEC(r11)	/* store nsec in tp */
-
-	mtlr	r12
-	crclr	cr0*4+so
-	li	r3,0
-	blr
+50:	bl	V_LOCAL_FUNC(__do_get_tspec)	/* get time from tb & kernel */
+	bne	cr1,80f			/* if not monotonic, all done */
 
 	/*
 	 * CLOCK_MONOTONIC
 	 */
 
-50:	bl	V_LOCAL_FUNC(__do_get_xsec)	/* get xsec from tb & kernel */
-
-	lis     r7,15			/* r7 = 1000000 = USEC_PER_SEC */
-	ori     r7,r7,16960
-	rldicl  r5,r4,44,20		/* r5 = sec = xsec / XSEC_PER_SEC */
-	rldicr  r6,r5,20,43		/* r6 = sec * XSEC_PER_SEC */
-	subf	r0,r6,r4		/* r0 = xsec = (xsec - r6) */
-	mulld   r0,r0,r7		/* usec = (xsec * USEC_PER_SEC) /
-					 * XSEC_PER_SEC
-					 */
-	rldicl  r6,r0,44,20
-	mulli	r6,r6,1000		/* nsec = usec * 1000 */
-
 	/* now we must fixup using wall to monotonic. We need to snapshot
 	 * that value and do the counter trick again. Fortunately, we still
-	 * have the counter value in r8 that was returned by __do_get_xsec.
-	 * At this point, r5,r6 contain our sec/nsec values.
-	 * can be used
+	 * have the counter value in r8 that was returned by __do_get_tspec.
+	 * At this point, r4,r5 contain our sec/nsec values.
 	 */
 
-	lwa	r4,WTOM_CLOCK_SEC(r3)
-	lwa	r7,WTOM_CLOCK_NSEC(r3)
+	lwa	r6,WTOM_CLOCK_SEC(r3)
+	lwa	r9,WTOM_CLOCK_NSEC(r3)
 
-	/* We now have our result in r4,r7. We create a fake dependency
+	/* We now have our result in r6,r9. We create a fake dependency
 	 * on that result and re-check the counter
 	 */
-	or	r9,r4,r7
-	xor	r0,r9,r9
+	or	r0,r6,r9
+	xor	r0,r0,r0
 	add	r3,r3,r0
 	ld	r0,CFG_TB_UPDATE_COUNT(r3)
         cmpld   cr0,r0,r8		/* check if updated */
 	bne-	50b
 
-	/* Calculate and store result. Note that this mimmics the C code,
-	 * which may cause funny results if nsec goes negative... is that
-	 * possible at all ?
+	/* Add wall->monotonic offset and check for overflow or underflow.
 	 */
-	add	r4,r4,r5
-	add	r7,r7,r6
-	lis	r9,NSEC_PER_SEC@h
-	ori	r9,r9,NSEC_PER_SEC@l
-	cmpl	cr0,r7,r9
-	cmpli	cr1,r7,0
+	add	r4,r4,r6
+	add	r5,r5,r9
+	cmpd	cr0,r5,r7
+	cmpdi	cr1,r5,0
 	blt	1f
-	subf	r7,r9,r7
+	subf	r5,r7,r5
 	addi	r4,r4,1
-1:	bge	cr1,1f
+1:	bge	cr1,80f
 	addi	r4,r4,-1
-	add	r7,r7,r9
-1:	std	r4,TSPC64_TV_SEC(r11)
-	std	r7,TSPC64_TV_NSEC(r11)
+	add	r5,r5,r7
+
+80:	std	r4,TSPC64_TV_SEC(r11)
+	std	r5,TSPC64_TV_NSEC(r11)
 
 	mtlr	r12
 	crclr	cr0*4+so
@@ -168,10 +127,6 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	/*
 	 * syscall fallback
 	 */
-98:
-	mtlr	r12
-	mr	r3,r10
-	mr	r4,r11
 99:
 	li	r0,__NR_clock_gettime
 	sc
@@ -253,3 +208,59 @@ V_FUNCTION_BEGIN(__do_get_xsec)
 	blr
   .cfi_endproc
 V_FUNCTION_END(__do_get_xsec)
+
+/*
+ * This is the core of clock_gettime(), it returns the current
+ * time in seconds and nanoseconds in r4 and r5.
+ * It expects the datapage ptr in r3 and doesn't clobber it.
+ * It clobbers r0 and r6 and returns NSEC_PER_SEC in r7.
+ * On return, r8 contains the counter value that can be reused.
+ * This clobbers cr0 but not any other cr field.
+ */
+V_FUNCTION_BEGIN(__do_get_tspec)
+  .cfi_startproc
+	/* check for update count & load values */
+1:	ld	r8,CFG_TB_UPDATE_COUNT(r3)
+	andi.	r0,r8,1			/* pending update ? loop */
+	bne-	1b
+	xor	r0,r8,r8		/* create dependency */
+	add	r3,r3,r0
+
+	/* Get TB & offset it. We use the MFTB macro which will generate
+	 * workaround code for Cell.
+	 */
+	MFTB(r7)
+	ld	r9,CFG_TB_ORIG_STAMP(r3)
+	subf	r7,r9,r7
+
+	/* Scale result */
+	ld	r5,CFG_TB_TO_XS(r3)
+	sldi	r7,r7,12		/* compute time since stamp_xtime */
+	mulhdu	r6,r7,r5		/* in units of 2^-32 seconds */
+
+	/* Add stamp since epoch */
+	ld	r4,STAMP_XTIME+TSPC64_TV_SEC(r3)
+	ld	r5,STAMP_XTIME+TSPC64_TV_NSEC(r3)
+	or	r0,r4,r5
+	or	r0,r0,r6
+	xor	r0,r0,r0
+	add	r3,r3,r0
+	ld	r0,CFG_TB_UPDATE_COUNT(r3)
+	cmpld   r0,r8			/* check if updated */
+	bne-	1b			/* reload if so */
+
+	/* convert to seconds & nanoseconds and add to stamp */
+	lis	r7,NSEC_PER_SEC@h
+	ori	r7,r7,NSEC_PER_SEC@l
+	mulhwu	r0,r6,r7		/* compute nanoseconds and */
+	srdi	r6,r6,32		/* seconds since stamp_xtime */
+	clrldi	r0,r0,32
+	add	r5,r5,r0		/* add nanoseconds together */
+	cmpd	r5,r7			/* overflow? */
+	add	r4,r4,r6
+	bltlr				/* all done if no overflow */
+	subf	r5,r7,r5		/* if overflow, adjust */
+	addi	r4,r4,1
+	blr
+  .cfi_endproc
+V_FUNCTION_END(__do_get_tspec)
diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S
index d0b2526dd38d..0e615404e247 100644
--- a/arch/powerpc/kernel/vdso64/vdso64.lds.S
+++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S
@@ -35,6 +35,9 @@ SECTIONS
 	__ftr_fixup	: { *(__ftr_fixup) }
 
 	. = ALIGN(8);
+	__mmu_ftr_fixup	: { *(__mmu_ftr_fixup) }
+
+	. = ALIGN(8);
 	__lwsync_fixup	: { *(__lwsync_fixup) }
 
 	. = ALIGN(8);
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index a11e6bc59b30..94aa7b011b27 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -41,9 +41,9 @@
 static struct bus_type vio_bus_type;
 
 static struct vio_dev vio_bus_device  = { /* fake "parent" device */
-	.name = vio_bus_device.dev.bus_id,
+	.name = "vio",
 	.type = "",
-	.dev.bus_id = "vio",
+	.dev.init_name = "vio",
 	.dev.bus = &vio_bus_type,
 };
 
@@ -1216,7 +1216,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 
 	viodev->irq = irq_of_parse_and_map(of_node, 0);
 
-	snprintf(viodev->dev.bus_id, BUS_ID_SIZE, "%x", *unit_address);
+	dev_set_name(&viodev->dev, "%x", *unit_address);
 	viodev->name = of_node->name;
 	viodev->type = of_node->type;
 	viodev->unit_address = *unit_address;
@@ -1243,7 +1243,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 	/* register with generic device framework */
 	if (device_register(&viodev->dev)) {
 		printk(KERN_ERR "%s: failed to register device %s\n",
-				__func__, viodev->dev.bus_id);
+				__func__, dev_name(&viodev->dev));
 		/* XXX free TCE table */
 		kfree(viodev);
 		return NULL;
@@ -1400,13 +1400,13 @@ static struct vio_dev *vio_find_name(const char *name)
 struct vio_dev *vio_find_node(struct device_node *vnode)
 {
 	const uint32_t *unit_address;
-	char kobj_name[BUS_ID_SIZE];
+	char kobj_name[20];
 
 	/* construct the kobject name from the device node */
 	unit_address = of_get_property(vnode, "reg", NULL);
 	if (!unit_address)
 		return NULL;
-	snprintf(kobj_name, BUS_ID_SIZE, "%x", *unit_address);
+	snprintf(kobj_name, sizeof(kobj_name), "%x", *unit_address);
 
 	return vio_find_name(kobj_name);
 }
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 2412c056baa4..47bf15cd2c9e 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -152,6 +152,12 @@ SECTIONS
 		__stop___ftr_fixup = .;
 	}
 	. = ALIGN(8);
+	__mmu_ftr_fixup : AT(ADDR(__mmu_ftr_fixup) - LOAD_OFFSET) {
+		__start___mmu_ftr_fixup = .;
+		*(__mmu_ftr_fixup)
+		__stop___mmu_ftr_fixup = .;
+	}
+	. = ALIGN(8);
 	__lwsync_fixup : AT(ADDR(__lwsync_fixup) - LOAD_OFFSET) {
 		__start___lwsync_fixup = .;
 		*(__lwsync_fixup)