[PATCH v5 04/11] drivers: base: support cpu cache information interface to userspace via sysfs

[PATCH v5 04/11] drivers: base: support cpu cache information interface to userspace via sysfs

[Sudeep Holla]

This patch adds initial support for providing processor cache information
to userspace through sysfs interface. This is based on already existing
implementations(x86, ia64, s390 and powerpc) and hence the interface is
intended to be fully compatible.

The main purpose of this generic support is to avoid further code
duplication to support new architectures and also to unify all the existing
different implementations.

This implementation maintains the hierarchy of cache objects which reflects
the system's cache topology. Cache devices are instantiated as needed as
CPUs come online. The cache information is replicated per-cpu even if they are
shared. A per-cpu array of cache information maintained is used mainly for
sysfs-related book keeping.

It also implements the shared_cpu_map attribute, which is essential for
enabling both kernel and user-space to discover the system's overall cache
topology.

This patch also add the missing ABI documentation for the cacheinfo sysfs
interface already, which is well defined and widely used.

Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Tested-by: Stephen Boyd <sboyd@codeaurora.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-api@vger.kernel.org
Cc: linux390@de.ibm.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-ia64@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-s390@vger.kernel.org
Cc: x86@kernel.org
---
 Documentation/ABI/testing/sysfs-devices-system-cpu |  47 ++
 drivers/base/Makefile                              |   2 +-
 drivers/base/cacheinfo.c                           | 541 +++++++++++++++++++++
 include/linux/cacheinfo.h                          | 100 ++++
 4 files changed, 689 insertions(+), 1 deletion(-)
 create mode 100644 drivers/base/cacheinfo.c
 create mode 100644 include/linux/cacheinfo.h

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index acb9bfc89b48..99983e67c13c 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -224,3 +224,50 @@ Description:	Parameters for the Intel P-state driver
 		frequency range.
 
 		More details can be found in Documentation/cpu-freq/intel-pstate.txt
+
+What:		/sys/devices/system/cpu/cpu*/cache/index*/<set_of_attributes_mentioned_below>
+Date:		July 2014(documented, existed before August 2008)
+Contact:	Sudeep Holla <sudeep.holla@arm.com>
+		Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Parameters for the CPU cache attributes
+
+		allocation_policy:
+			- WriteAllocate: allocate a memory location to a cache line
+					 on a cache miss because of a write
+			- ReadAllocate: allocate a memory location to a cache line
+					on a cache miss because of a read
+			- ReadWriteAllocate: both writeallocate and readallocate
+
+		attributes: LEGACY used only on IA64 and is same as write_policy
+
+		coherency_line_size: the minimum amount of data in bytes that gets
+				     transferred from memory to cache
+
+		level: the cache hierarcy in the multi-level cache configuration
+
+		number_of_sets: total number of sets in the cache, a set is a
+				collection of cache lines with the same cache index
+
+		physical_line_partition: number of physical cache line per cache tag
+
+		shared_cpu_list: the list of logical cpus sharing the cache
+
+		shared_cpu_map: logical cpu mask containing the list of cpus sharing
+				the cache
+
+		size: the total cache size in kB
+
+		type:
+			- Instruction: cache that only holds instructions
+			- Data: cache that only caches data
+			- Unified: cache that holds both data and instructions
+
+		ways_of_associativity: degree of freedom in placing a particular block
+					of memory in the cache
+
+		write_policy:
+			- WriteThrough: data is written to both the cache line
+					and to the block in the lower-level memory
+			- WriteBack: data is written only to the cache line and
+				     the modified cache line is written to main
+				     memory only when it is replaced
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 4aab26ec0292..f901bc1cffc8 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -4,7 +4,7 @@ obj-y			:= component.o core.o bus.o dd.o syscore.o \
 			   driver.o class.o platform.o \
 			   cpu.o firmware.o init.o map.o devres.o \
 			   attribute_container.o transport_class.o \
-			   topology.o container.o
+			   topology.o container.o cacheinfo.o
 obj-$(CONFIG_DEVTMPFS)	+= devtmpfs.o
 obj-$(CONFIG_DMA_CMA) += dma-contiguous.o
 obj-y			+= power/
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
new file mode 100644
index 000000000000..8ed4ea1f3716
--- /dev/null
+++ b/drivers/base/cacheinfo.c
@@ -0,0 +1,541 @@
+/*
+ * cacheinfo support - processor cache information via sysfs
+ *
+ * Based on arch/x86/kernel/cpu/intel_cacheinfo.c
+ * Author: Sudeep Holla <sudeep.holla@arm.com>
+ *
+ * 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.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/bitops.h>
+#include <linux/cacheinfo.h>
+#include <linux/compiler.h>
+#include <linux/cpu.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/sysfs.h>
+
+/* pointer to per cpu cacheinfo */
+static DEFINE_PER_CPU(struct cpu_cacheinfo, ci_cpu_cacheinfo);
+#define ci_cacheinfo(cpu)	(&per_cpu(ci_cpu_cacheinfo, cpu))
+#define cache_leaves(cpu)	(ci_cacheinfo(cpu)->num_leaves)
+#define per_cpu_cacheinfo(cpu)	(ci_cacheinfo(cpu)->info_list)
+
+struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu)
+{
+	return ci_cacheinfo(cpu);
+}
+
+#ifdef CONFIG_OF
+static int cache_setup_of_node(unsigned int cpu)
+{
+	struct device_node *np;
+	struct cacheinfo *this_leaf;
+	struct device *cpu_dev = get_cpu_device(cpu);
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	unsigned int index = 0;
+
+	/* skip if of_node is already populated */
+	if (this_cpu_ci->info_list->of_node)
+		return 0;
+
+	if (!cpu_dev) {
+		pr_err("No cpu device for CPU %d\n", cpu);
+		return -ENODEV;
+	}
+	np = cpu_dev->of_node;
+	if (!np) {
+		pr_err("Failed to find cpu%d device node\n", cpu);
+		return -ENOENT;
+	}
+
+	while (np && index < cache_leaves(cpu)) {
+		this_leaf = this_cpu_ci->info_list + index;
+		if (this_leaf->level != 1)
+			np = of_find_next_cache_node(np);
+		else
+			np = of_node_get(np);/* cpu node itself */
+		this_leaf->of_node = np;
+		index++;
+	}
+	return 0;
+}
+
+static inline bool cache_leaves_are_shared(struct cacheinfo *this_leaf,
+					   struct cacheinfo *sib_leaf)
+{
+	return sib_leaf->of_node == this_leaf->of_node;
+}
+#else
+static inline int cache_setup_of_node(unsigned int cpu) { return 0; }
+static inline bool cache_leaves_are_shared(struct cacheinfo *this_leaf,
+					   struct cacheinfo *sib_leaf)
+{
+	/*
+	 * For non-DT systems, assume unique level 1 cache, system-wide
+	 * shared caches for all other levels. This will be used only if
+	 * arch specific code has not populated shared_cpu_map
+	 */
+	return !(this_leaf->level == 1);
+}
+#endif
+
+static int cache_shared_cpu_map_setup(unsigned int cpu)
+{
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cacheinfo *this_leaf, *sib_leaf;
+	unsigned int index;
+	int ret;
+
+	ret = cache_setup_of_node(cpu);
+	if (ret)
+		return ret;
+
+	for (index = 0; index < cache_leaves(cpu); index++) {
+		unsigned int i;
+
+		this_leaf = this_cpu_ci->info_list + index;
+		/* skip if shared_cpu_map is already populated */
+		if (!cpumask_empty(&this_leaf->shared_cpu_map))
+			continue;
+
+		cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map);
+		for_each_online_cpu(i) {
+			struct cpu_cacheinfo *sib_cpu_ci = get_cpu_cacheinfo(i);
+
+			if (i == cpu || !sib_cpu_ci->info_list)
+				continue;/* skip if itself or no cacheinfo */
+			sib_leaf = sib_cpu_ci->info_list + index;
+			if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
+				cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map);
+				cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
+			}
+		}
+	}
+
+	return 0;
+}
+
+static void cache_shared_cpu_map_remove(unsigned int cpu)
+{
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cacheinfo *this_leaf, *sib_leaf;
+	unsigned int sibling, index;
+
+	for (index = 0; index < cache_leaves(cpu); index++) {
+		this_leaf = this_cpu_ci->info_list + index;
+		for_each_cpu(sibling, &this_leaf->shared_cpu_map) {
+			struct cpu_cacheinfo *sib_cpu_ci;
+
+			if (sibling == cpu) /* skip itself */
+				continue;
+			sib_cpu_ci = get_cpu_cacheinfo(sibling);
+			sib_leaf = sib_cpu_ci->info_list + index;
+			cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
+			cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
+		}
+		of_node_put(this_leaf->of_node);
+	}
+}
+
+static void free_cache_attributes(unsigned int cpu)
+{
+	cache_shared_cpu_map_remove(cpu);
+
+	kfree(per_cpu_cacheinfo(cpu));
+	per_cpu_cacheinfo(cpu) = NULL;
+}
+
+int __weak init_cache_level(unsigned int cpu)
+{
+	return -ENOENT;
+}
+
+int __weak populate_cache_leaves(unsigned int cpu)
+{
+	return -ENOENT;
+}
+
+static int detect_cache_attributes(unsigned int cpu)
+{
+	int ret;
+
+	if (init_cache_level(cpu))
+		return -ENOENT;
+
+	per_cpu_cacheinfo(cpu) = kcalloc(cache_leaves(cpu),
+					 sizeof(struct cacheinfo), GFP_KERNEL);
+	if (per_cpu_cacheinfo(cpu) == NULL)
+		return -ENOMEM;
+
+	ret = populate_cache_leaves(cpu);
+	if (ret)
+		goto free_ci;
+	/*
+	 * For systems using DT for cache hierarcy, of_node and shared_cpu_map
+	 * will be set up here only if they are not populated already
+	 */
+	ret = cache_shared_cpu_map_setup(cpu);
+	if (ret)
+		goto free_ci;
+	return 0;
+
+free_ci:
+	free_cache_attributes(cpu);
+	return ret;
+}
+
+/* pointer to cpuX/cache device */
+static DEFINE_PER_CPU(struct device *, ci_cache_dev);
+#define per_cpu_cache_dev(cpu)	(per_cpu(ci_cache_dev, cpu))
+
+static cpumask_t cache_dev_map;
+
+/* pointer to array of devices for cpuX/cache/indexY */
+static DEFINE_PER_CPU(struct device **, ci_index_dev);
+#define per_cpu_index_dev(cpu)	(per_cpu(ci_index_dev, cpu))
+#define per_cache_index_dev(cpu, idx)	((per_cpu_index_dev(cpu))[idx])
+
+#define show_one(file_name, object)				\
+static ssize_t file_name##_show(struct device *dev,		\
+		struct device_attribute *attr, char *buf)	\
+{								\
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);	\
+	return sprintf(buf, "%u\n", this_leaf->object);		\
+}
+
+show_one(level, level);
+show_one(coherency_line_size, coherency_line_size);
+show_one(number_of_sets, number_of_sets);
+show_one(physical_line_partition, physical_line_partition);
+show_one(ways_of_associativity, ways_of_associativity);
+
+static ssize_t size_show(struct device *dev,
+			 struct device_attribute *attr, char *buf)
+{
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%uK\n", this_leaf->size >> 10);
+}
+
+static ssize_t shared_cpumap_show_func(struct device *dev, bool list, char *buf)
+{
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+	const struct cpumask *mask = &this_leaf->shared_cpu_map;
+
+	return cpumap_print_to_pagebuf(list, buf, mask);
+}
+
+static ssize_t shared_cpu_map_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	return shared_cpumap_show_func(dev, false, buf);
+}
+
+static ssize_t shared_cpu_list_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	return shared_cpumap_show_func(dev, true, buf);
+}
+
+static ssize_t type_show(struct device *dev,
+			 struct device_attribute *attr, char *buf)
+{
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+
+	switch (this_leaf->type) {
+	case CACHE_TYPE_DATA:
+		return sprintf(buf, "Data\n");
+	case CACHE_TYPE_INST:
+		return sprintf(buf, "Instruction\n");
+	case CACHE_TYPE_UNIFIED:
+		return sprintf(buf, "Unified\n");
+	default:
+		return -EINVAL;
+	}
+}
+
+static ssize_t allocation_policy_show(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+	unsigned int ci_attr = this_leaf->attributes;
+	int n = 0;
+
+	if ((ci_attr & CACHE_READ_ALLOCATE) && (ci_attr & CACHE_WRITE_ALLOCATE))
+		n = sprintf(buf, "ReadWriteAllocate\n");
+	else if (ci_attr & CACHE_READ_ALLOCATE)
+		n = sprintf(buf, "ReadAllocate\n");
+	else if (ci_attr & CACHE_WRITE_ALLOCATE)
+		n = sprintf(buf, "WriteAllocate\n");
+	return n;
+}
+
+static ssize_t write_policy_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+	unsigned int ci_attr = this_leaf->attributes;
+	int n = 0;
+
+	if (ci_attr & CACHE_WRITE_THROUGH)
+		n = sprintf(buf, "WriteThrough\n");
+	else if (ci_attr & CACHE_WRITE_BACK)
+		n = sprintf(buf, "WriteBack\n");
+	return n;
+}
+
+static DEVICE_ATTR_RO(level);
+static DEVICE_ATTR_RO(type);
+static DEVICE_ATTR_RO(coherency_line_size);
+static DEVICE_ATTR_RO(ways_of_associativity);
+static DEVICE_ATTR_RO(number_of_sets);
+static DEVICE_ATTR_RO(size);
+static DEVICE_ATTR_RO(allocation_policy);
+static DEVICE_ATTR_RO(write_policy);
+static DEVICE_ATTR_RO(shared_cpu_map);
+static DEVICE_ATTR_RO(shared_cpu_list);
+static DEVICE_ATTR_RO(physical_line_partition);
+
+static struct attribute *cache_default_attrs[] = {
+	&dev_attr_type.attr,
+	&dev_attr_level.attr,
+	&dev_attr_shared_cpu_map.attr,
+	&dev_attr_shared_cpu_list.attr,
+	&dev_attr_coherency_line_size.attr,
+	&dev_attr_ways_of_associativity.attr,
+	&dev_attr_number_of_sets.attr,
+	&dev_attr_size.attr,
+	&dev_attr_allocation_policy.attr,
+	&dev_attr_write_policy.attr,
+	&dev_attr_physical_line_partition.attr,
+	NULL
+};
+
+static umode_t
+cache_default_attrs_is_visible(struct kobject *kobj,
+			       struct attribute *attr, int unused)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+	const struct cpumask *mask = &this_leaf->shared_cpu_map;
+	umode_t mode = attr->mode;
+
+	if ((attr == &dev_attr_type.attr) && this_leaf->type)
+		return mode;
+	if ((attr == &dev_attr_level.attr) && this_leaf->level)
+		return mode;
+	if ((attr == &dev_attr_shared_cpu_map.attr) && !cpumask_empty(mask))
+		return mode;
+	if ((attr == &dev_attr_shared_cpu_list.attr) && !cpumask_empty(mask))
+		return mode;
+	if ((attr == &dev_attr_coherency_line_size.attr) &&
+	    this_leaf->coherency_line_size)
+		return mode;
+	if ((attr == &dev_attr_ways_of_associativity.attr) &&
+	    this_leaf->size) /* allow 0 = full associativity */
+		return mode;
+	if ((attr == &dev_attr_number_of_sets.attr) &&
+	    this_leaf->number_of_sets)
+		return mode;
+	if ((attr == &dev_attr_size.attr) && this_leaf->size)
+		return mode;
+	if ((attr == &dev_attr_write_policy.attr) &&
+	    (this_leaf->attributes & CACHE_WRITE_POLICY_MASK))
+		return mode;
+	if ((attr == &dev_attr_allocation_policy.attr) &&
+	    (this_leaf->attributes & CACHE_ALLOCATE_POLICY_MASK))
+		return mode;
+	if ((attr == &dev_attr_physical_line_partition.attr) &&
+	    this_leaf->physical_line_partition)
+		return mode;
+
+	return 0;
+}
+
+static const struct attribute_group cache_default_group = {
+	.attrs = cache_default_attrs,
+	.is_visible = cache_default_attrs_is_visible,
+};
+
+static const struct attribute_group *cache_default_groups[] = {
+	&cache_default_group,
+	NULL,
+};
+
+static const struct attribute_group *cache_private_groups[] = {
+	&cache_default_group,
+	NULL, /* Place holder for private group */
+	NULL,
+};
+
+const struct attribute_group *
+__weak cache_get_priv_group(struct cacheinfo *this_leaf)
+{
+	return NULL;
+}
+
+static const struct attribute_group **
+cache_get_attribute_groups(struct cacheinfo *this_leaf)
+{
+	const struct attribute_group *priv_group =
+			cache_get_priv_group(this_leaf);
+
+	if (!priv_group)
+		return cache_default_groups;
+
+	if (!cache_private_groups[1])
+		cache_private_groups[1] = priv_group;
+
+	return cache_private_groups;
+}
+
+/* Add/Remove cache interface for CPU device */
+static void cpu_cache_sysfs_exit(unsigned int cpu)
+{
+	int i;
+	struct device *ci_dev;
+
+	if (per_cpu_index_dev(cpu)) {
+		for (i = 0; i < cache_leaves(cpu); i++) {
+			ci_dev = per_cache_index_dev(cpu, i);
+			if (!ci_dev)
+				continue;
+			device_unregister(ci_dev);
+		}
+		kfree(per_cpu_index_dev(cpu));
+		per_cpu_index_dev(cpu) = NULL;
+	}
+	device_unregister(per_cpu_cache_dev(cpu));
+	per_cpu_cache_dev(cpu) = NULL;
+}
+
+static int cpu_cache_sysfs_init(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	if (per_cpu_cacheinfo(cpu) == NULL)
+		return -ENOENT;
+
+	per_cpu_cache_dev(cpu) = cpu_device_create(dev, NULL, NULL, "cache");
+	if (IS_ERR(per_cpu_cache_dev(cpu)))
+		return PTR_ERR(per_cpu_cache_dev(cpu));
+
+	/* Allocate all required memory */
+	per_cpu_index_dev(cpu) = kcalloc(cache_leaves(cpu),
+					 sizeof(struct device *), GFP_KERNEL);
+	if (unlikely(per_cpu_index_dev(cpu) == NULL))
+		goto err_out;
+
+	return 0;
+
+err_out:
+	cpu_cache_sysfs_exit(cpu);
+	return -ENOMEM;
+}
+
+static int cache_add_dev(unsigned int cpu)
+{
+	unsigned int i;
+	int rc;
+	struct device *ci_dev, *parent;
+	struct cacheinfo *this_leaf;
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	const struct attribute_group **cache_groups;
+
+	rc = cpu_cache_sysfs_init(cpu);
+	if (unlikely(rc < 0))
+		return rc;
+
+	parent = per_cpu_cache_dev(cpu);
+	for (i = 0; i < cache_leaves(cpu); i++) {
+		this_leaf = this_cpu_ci->info_list + i;
+		if (this_leaf->disable_sysfs)
+			continue;
+		cache_groups = cache_get_attribute_groups(this_leaf);
+		ci_dev = cpu_device_create(parent, this_leaf, cache_groups,
+					   "index%1u", i);
+		if (IS_ERR(ci_dev)) {
+			rc = PTR_ERR(ci_dev);
+			goto err;
+		}
+		per_cache_index_dev(cpu, i) = ci_dev;
+	}
+	cpumask_set_cpu(cpu, &cache_dev_map);
+
+	return 0;
+err:
+	cpu_cache_sysfs_exit(cpu);
+	return rc;
+}
+
+static void cache_remove_dev(unsigned int cpu)
+{
+	if (!cpumask_test_cpu(cpu, &cache_dev_map))
+		return;
+	cpumask_clear_cpu(cpu, &cache_dev_map);
+
+	cpu_cache_sysfs_exit(cpu);
+}
+
+static int cacheinfo_cpu_callback(struct notifier_block *nfb,
+				  unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (unsigned long)hcpu;
+	int rc = 0;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_ONLINE:
+		rc = detect_cache_attributes(cpu);
+		if (!rc)
+			rc = cache_add_dev(cpu);
+		break;
+	case CPU_DEAD:
+		cache_remove_dev(cpu);
+		if (per_cpu_cacheinfo(cpu))
+			free_cache_attributes(cpu);
+		break;
+	}
+	return notifier_from_errno(rc);
+}
+
+static int __init cacheinfo_sysfs_init(void)
+{
+	int cpu, rc = 0;
+
+	cpu_notifier_register_begin();
+
+	for_each_online_cpu(cpu) {
+		rc = detect_cache_attributes(cpu);
+		if (rc) {
+			pr_err("error detecting cacheinfo..cpu%d\n", cpu);
+			goto out;
+		}
+		rc = cache_add_dev(cpu);
+		if (rc) {
+			free_cache_attributes(cpu);
+			pr_err("error populating cacheinfo..cpu%d\n", cpu);
+			goto out;
+		}
+	}
+	__hotcpu_notifier(cacheinfo_cpu_callback, 0);
+
+out:
+	cpu_notifier_register_done();
+	return rc;
+}
+
+device_initcall(cacheinfo_sysfs_init);
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h
new file mode 100644
index 000000000000..3daf5ed392c9
--- /dev/null
+++ b/include/linux/cacheinfo.h
@@ -0,0 +1,100 @@
+#ifndef _LINUX_CACHEINFO_H
+#define _LINUX_CACHEINFO_H
+
+#include <linux/bitops.h>
+#include <linux/cpumask.h>
+#include <linux/smp.h>
+
+struct device_node;
+struct attribute;
+
+enum cache_type {
+	CACHE_TYPE_NOCACHE = 0,
+	CACHE_TYPE_INST = BIT(0),
+	CACHE_TYPE_DATA = BIT(1),
+	CACHE_TYPE_SEPARATE = CACHE_TYPE_INST | CACHE_TYPE_DATA,
+	CACHE_TYPE_UNIFIED = BIT(2),
+};
+
+/**
+ * struct cacheinfo - represent a cache leaf node
+ * @type: type of the cache - data, inst or unified
+ * @level: represents the hierarcy in the multi-level cache
+ * @coherency_line_size: size of each cache line usually representing
+ *	the minimum amount of data that gets transferred from memory
+ * @number_of_sets: total number of sets, a set is a collection of cache
+ *	lines sharing the same index
+ * @ways_of_associativity: number of ways in which a particular memory
+ *	block can be placed in the cache
+ * @physical_line_partition: number of physical cache lines sharing the
+ *	same cachetag
+ * @size: Total size of the cache
+ * @shared_cpu_map: logical cpumask representing all the cpus sharing
+ *	this cache node
+ * @attributes: bitfield representing various cache attributes
+ * @of_node: if devicetree is used, this represents either the cpu node in
+ *	case there's no explicit cache node or the cache node itself in the
+ *	device tree
+ * @disable_sysfs: indicates whether this node is visible to the user via
+ *	sysfs or not
+ * @priv: pointer to any private data structure specific to particular
+ *	cache design
+ *
+ * While @of_node, @disable_sysfs and @priv are used for internal book
+ * keeping, the remaining members form the core properties of the cache
+ */
+struct cacheinfo {
+	enum cache_type type;
+	unsigned int level;
+	unsigned int coherency_line_size;
+	unsigned int number_of_sets;
+	unsigned int ways_of_associativity;
+	unsigned int physical_line_partition;
+	unsigned int size;
+	cpumask_t shared_cpu_map;
+	unsigned int attributes;
+#define CACHE_WRITE_THROUGH	BIT(0)
+#define CACHE_WRITE_BACK	BIT(1)
+#define CACHE_WRITE_POLICY_MASK		\
+	(CACHE_WRITE_THROUGH | CACHE_WRITE_BACK)
+#define CACHE_READ_ALLOCATE	BIT(2)
+#define CACHE_WRITE_ALLOCATE	BIT(3)
+#define CACHE_ALLOCATE_POLICY_MASK	\
+	(CACHE_READ_ALLOCATE | CACHE_WRITE_ALLOCATE)
+
+	struct device_node *of_node;
+	bool disable_sysfs;
+	void *priv;
+};
+
+struct cpu_cacheinfo {
+	struct cacheinfo *info_list;
+	unsigned int num_levels;
+	unsigned int num_leaves;
+};
+
+/*
+ * Helpers to make sure "func" is executed on the cpu whose cache
+ * attributes are being detected
+ */
+#define DEFINE_SMP_CALL_CACHE_FUNCTION(func)			\
+static inline void _##func(void *ret)				\
+{								\
+	int cpu = smp_processor_id();				\
+	*(int *)ret = __##func(cpu);				\
+}								\
+								\
+int func(unsigned int cpu)					\
+{								\
+	int ret;						\
+	smp_call_function_single(cpu, _##func, &ret, true);	\
+	return ret;						\
+}
+
+struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu);
+int init_cache_level(unsigned int cpu);
+int populate_cache_leaves(unsigned int cpu);
+
+const struct attribute_group *cache_get_priv_group(struct cacheinfo *this_leaf);
+
+#endif /* _LINUX_CACHEINFO_H */
-- 
1.9.1

[PATCH v5 08/11] powerpc: move cacheinfo sysfs to generic cacheinfo infrastructure

[Sudeep Holla]

This patch removes the redundant sysfs cacheinfo code by making use of
the newly introduced generic cacheinfo infrastructure.

Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: linuxppc-dev@lists.ozlabs.org
---
 arch/powerpc/kernel/cacheinfo.c | 812 +++++-----------------------------------
 arch/powerpc/kernel/cacheinfo.h |   8 -
 arch/powerpc/kernel/sysfs.c     |  12 +-
 3 files changed, 90 insertions(+), 742 deletions(-)
 delete mode 100644 arch/powerpc/kernel/cacheinfo.h

diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index 40198d50b4c2..6845eb7fcc18 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -10,38 +10,10 @@
  * 2 as published by the Free Software Foundation.
  */
 
+#include <linux/cacheinfo.h>
 #include <linux/cpu.h>
-#include <linux/cpumask.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 <linux/slab.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 */
@@ -60,11 +32,6 @@ struct cache_type_info {
 	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-*
@@ -92,231 +59,82 @@ static const struct cache_type_info cache_type_info[] = {
 	},
 };
 
-/* 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_pcpu);
-
-/* 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)
+static inline int get_cacheinfo_idx(enum cache_type type)
 {
-	return cache_type_info[cache->type].name;
-}
-
-static void 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 *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;
-	}
+	if (type == CACHE_TYPE_UNIFIED)
+		return 0;
+	return type;
 }
 
-static int cache_size(const struct cache *cache, unsigned int *ret)
+static void cache_size(struct cacheinfo *this_leaf)
 {
 	const char *propname;
 	const __be32 *cache_size;
+	int ct_idx;
 
-	propname = cache_type_info[cache->type].size_prop;
+	ct_idx = get_cacheinfo_idx(this_leaf->type);
+	propname = cache_type_info[ct_idx].size_prop;
 
-	cache_size = of_get_property(cache->ofnode, propname, NULL);
+	cache_size = of_get_property(this_leaf->of_node, propname, NULL);
 	if (!cache_size)
-		return -ENODEV;
-
-	*ret = of_read_number(cache_size, 1);
-	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;
+		this_leaf->size = 0;
+	else
+		this_leaf->size = of_read_number(cache_size, 1);
 }
 
 /* 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)
+static void cache_get_line_size(struct cacheinfo *this_leaf)
 {
 	const __be32 *line_size;
-	int i, lim;
+	int i, lim, ct_idx;
 
-	lim = ARRAY_SIZE(cache_type_info[cache->type].line_size_props);
+	ct_idx = get_cacheinfo_idx(this_leaf->type);
+	lim = ARRAY_SIZE(cache_type_info[ct_idx].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);
+		propname = cache_type_info[ct_idx].line_size_props[i];
+		line_size = of_get_property(this_leaf->of_node, propname, NULL);
 		if (line_size)
 			break;
 	}
 
 	if (!line_size)
-		return -ENODEV;
-
-	*ret = of_read_number(line_size, 1);
-	return 0;
+		this_leaf->coherency_line_size = 0;
+	else
+		this_leaf->coherency_line_size = of_read_number(line_size, 1);
 }
 
-static int cache_nr_sets(const struct cache *cache, unsigned int *ret)
+static void cache_nr_sets(struct cacheinfo *this_leaf)
 {
 	const char *propname;
 	const __be32 *nr_sets;
+	int ct_idx;
 
-	propname = cache_type_info[cache->type].nr_sets_prop;
+	ct_idx = get_cacheinfo_idx(this_leaf->type);
+	propname = cache_type_info[ct_idx].nr_sets_prop;
 
-	nr_sets = of_get_property(cache->ofnode, propname, NULL);
+	nr_sets = of_get_property(this_leaf->of_node, propname, NULL);
 	if (!nr_sets)
-		return -ENODEV;
-
-	*ret = of_read_number(nr_sets, 1);
-	return 0;
+		this_leaf->number_of_sets = 0;
+	else
+		this_leaf->number_of_sets = of_read_number(nr_sets, 1);
 }
 
-static int cache_associativity(const struct cache *cache, unsigned int *ret)
+static void cache_associativity(struct cacheinfo *this_leaf)
 {
-	unsigned int line_size;
-	unsigned int nr_sets;
-	unsigned int size;
-
-	if (cache_nr_sets(cache, &nr_sets))
-		goto err;
+	unsigned int line_size = this_leaf->coherency_line_size;
+	unsigned int nr_sets = this_leaf->number_of_sets;
+	unsigned int size = this_leaf->size;
 
 	/* 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;
+	if ((nr_sets == 1) || !(nr_sets > 0 && size > 0 && line_size > 0))
+		this_leaf->ways_of_associativity = 0;
+	else
+		this_leaf->ways_of_associativity = (size / nr_sets) / line_size;
 }
 
 static bool cache_node_is_unified(const struct device_node *np)
@@ -324,526 +142,74 @@ static bool cache_node_is_unified(const struct device_node *np)
 	return of_get_property(np, "cache-unified", NULL);
 }
 
-static struct cache *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 *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 *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 *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 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 do_subsidiary_caches_debugcheck(struct cache *cache)
-{
-	WARN_ON_ONCE(cache->level != 1);
-	WARN_ON_ONCE(strcmp(cache->ofnode->type, "cpu"));
-}
-
-static void 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 *cache_chain_instantiate(unsigned int cpu_id)
+static void ci_leaf_init(struct cacheinfo *this_leaf,
+			 enum cache_type type, unsigned int level)
 {
-	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;
+	this_leaf->level = level;
+	this_leaf->type = type;
+	cache_size(this_leaf);
+	cache_get_line_size(this_leaf);
+	cache_nr_sets(this_leaf);
+	cache_associativity(this_leaf);
 }
 
-static struct cache_dir *cacheinfo_create_cache_dir(unsigned int cpu_id)
+int init_cache_level(unsigned int cpu)
 {
-	struct cache_dir *cache_dir;
-	struct device *dev;
-	struct kobject *kobj = NULL;
-
-	dev = get_cpu_device(cpu_id);
-	WARN_ONCE(!dev, "no dev for CPU %i\n", cpu_id);
-	if (!dev)
-		goto err;
-
-	kobj = kobject_create_and_add("cache", &dev->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_pcpu, cpu_id) != NULL);
-
-	per_cpu(cache_dir_pcpu, cpu_id) = cache_dir;
+	struct device_node *np;
+	struct device *cpu_dev = get_cpu_device(cpu);
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	unsigned int level = 0, leaves = 0;
 
-	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))
+	if (!cpu_dev) {
+		pr_err("No cpu device for CPU %d\n", cpu);
 		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 const 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 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);
+	np = cpu_dev->of_node;
+	if (!np) {
+		pr_err("Failed to find cpu%d device node\n", cpu);
+		return -ENOENT;
 	}
 
-	kfree(buf);
-}
-
-static void 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 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;
+	while (np) {
+		leaves += cache_node_is_unified(np) ? 1 : 2;
+		level++;
+		of_node_put(np);
+		np = of_find_next_cache_node(np);
 	}
-}
+	this_cpu_ci->num_levels = level;
+	this_cpu_ci->num_leaves = leaves;
 
-void 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);
-}
-
-/* functions needed to remove cache entry for cpu offline or suspend/resume */
-
-#if (defined(CONFIG_PPC_PSERIES) && defined(CONFIG_SUSPEND)) || \
-    defined(CONFIG_HOTPLUG_CPU)
-
-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;
+	return 0;
 }
 
-static void remove_index_dirs(struct cache_dir *cache_dir)
+int populate_cache_leaves(unsigned int cpu)
 {
-	struct cache_index_dir *index;
-
-	index = cache_dir->index;
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+	struct device *cpu_dev = get_cpu_device(cpu);
+	struct device_node *np;
+	unsigned int level, idx;
 
-	while (index) {
-		struct cache_index_dir *next;
-
-		next = index->next;
-		kobject_put(&index->kobj);
-		index = next;
+	np = of_node_get(cpu_dev->of_node);
+	if (!np) {
+		pr_err("Failed to find cpu%d device node\n", cpu);
+		return -ENOENT;
 	}
-}
-
-static void remove_cache_dir(struct cache_dir *cache_dir)
-{
-	remove_index_dirs(cache_dir);
 
-	/* Remove cache dir from sysfs */
-	kobject_del(cache_dir->kobj);
-
-	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;
+	for (idx = 0, level = 1; level <= this_cpu_ci->num_levels &&
+	     idx < this_cpu_ci->num_leaves; idx++, level++) {
+		if (!this_leaf)
+			return -EINVAL;
+
+		this_leaf->of_node = np;
+		if (cache_node_is_unified(np)) {
+			ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
+		} else {
+			ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
+			ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
+		}
+		np = of_find_next_cache_node(np);
 	}
+	return 0;
 }
 
-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_pcpu, cpu_id);
-
-	/* careful, sysfs population may have failed */
-	if (cache_dir)
-		remove_cache_dir(cache_dir);
-
-	per_cpu(cache_dir_pcpu, 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_PPC_PSERIES && CONFIG_SUSPEND) || CONFIG_HOTPLUG_CPU */
diff --git a/arch/powerpc/kernel/cacheinfo.h b/arch/powerpc/kernel/cacheinfo.h
deleted file mode 100644
index a7b74d36acd7..000000000000
--- a/arch/powerpc/kernel/cacheinfo.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#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 67fd2fd2620a..6e9c5a8141bb 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -19,8 +19,6 @@
 #include <asm/pmc.h>
 #include <asm/firmware.h>
 
-#include "cacheinfo.h"
-
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 #include <asm/lppaca.h>
@@ -743,7 +741,6 @@ static void register_cpu_online(unsigned int cpu)
 		device_create_file(s, &dev_attr_altivec_idle_wait_time);
 	}
 #endif
-	cacheinfo_cpu_online(cpu);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -824,7 +821,6 @@ static void unregister_cpu_online(unsigned int cpu)
 		device_remove_file(s, &dev_attr_altivec_idle_wait_time);
 	}
 #endif
-	cacheinfo_cpu_offline(cpu);
 }
 
 #ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
@@ -988,8 +984,7 @@ static int __init topology_init(void)
 	int cpu;
 
 	register_nodes();
-
-	cpu_notifier_register_begin();
+	register_cpu_notifier(&sysfs_cpu_nb);
 
 	for_each_possible_cpu(cpu) {
 		struct cpu *c = &per_cpu(cpu_devices, cpu);
@@ -1013,11 +1008,6 @@ static int __init topology_init(void)
 		if (cpu_online(cpu))
 			register_cpu_online(cpu);
 	}
-
-	__register_cpu_notifier(&sysfs_cpu_nb);
-
-	cpu_notifier_register_done();
-
 #ifdef CONFIG_PPC64
 	sysfs_create_dscr_default();
 #endif /* CONFIG_PPC64 */
-- 
1.9.1