powerpc: Rewrite sysfs processor cache info code

The current code for providing processor cache information in sysfs
has the following deficiencies:
- several complex functions that are hard to understand
- implicit recursion (cache_desc_release -> kobject_put -> cache_desc_release)
- explicit recursion (create_cache_index_info)
- use of two per-cpu arrays when one would suffice
- duplication of work on systems where CPUs share cache

Also, when I looked at implementing support for a shared_cpu_map
attribute, it was pretty much impossible to handle hotplug without
checking every single online CPU's cache_desc list and fixing things
up... not that this is a hot path, but it would have introduced
O(n^2)-ish behavior during boot.  Addressing this involved rethinking
the core data structures used, which didn't lend itself to an
incremental approach.

This implementation maintains a "forest" (potentially more than one
tree) of cache objects which reflects the system's cache topology.
Cache objects are instantiated as needed as CPUs come online.  A
per-cpu array is used mainly for sysfs-related bookkeeping; the
objects in the array just point to the appropriate points in the
forest.

This maintains compatibility with the existing code and includes some
enhancements:
- Implement the shared_cpu_map attribute, which is essential for
  enabling userspace to discover the system's overall cache topology.
- Use cache-block-size properties if cache-line-size is not available.

I chose to place this implementation in a new file since it would have
roughly doubled the size of sysfs.c, which is already kind of messy.

Signed-off-by: Nathan Lynch <ntl@pobox.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

4 files changed, 850 insertions, 297 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 1308a86e907..8d1a419df35 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -29,7 +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 \
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
new file mode 100644
index 00000000000..b33f0417a4b
--- /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 00000000000..a7b74d36acd
--- /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/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 0c64f10087b..4a2ee08af6a 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
  */
@@ -343,283 +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)
-{
-	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 = of_find_next_cache_node(np);
-	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);
@@ -684,25 +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);
@@ -769,7 +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 */