* [PATCH v4 04/11] drivers: base: support cpu cache information interface to userspace via sysfs
2014-09-03 17:00 [PATCH v4 00/11] drivers: cacheinfo support Sudeep Holla
@ 2014-09-03 17:00 ` Sudeep Holla
2014-09-17 17:25 ` Sudeep Holla
2014-09-19 22:24 ` Stephen Boyd
2014-09-03 17:00 ` [PATCH v4 05/11] ia64: move cacheinfo sysfs to generic cacheinfo infrastructure Sudeep Holla
1 sibling, 2 replies; 9+ messages in thread
From: Sudeep Holla @ 2014-09-03 17:00 UTC (permalink / raw)
To: LKML
Cc: Sudeep Holla, Heiko Carstens, Lorenzo Pieralisi,
Greg Kroah-Hartman, Stephen Boyd, linux-api, linux390,
linux-arm-kernel, linux-ia64, linuxppc-dev, linux-s390, x86
From: Sudeep Holla <sudeep.holla@arm.com>
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>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Stephen Boyd <sboyd@codeaurora.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..9534044cca79
--- /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_copy_to_buf(list, mask, buf);
+}
+
+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 */
--
1.8.3.2
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH v4 05/11] ia64: move cacheinfo sysfs to generic cacheinfo infrastructure
2014-09-03 17:00 [PATCH v4 00/11] drivers: cacheinfo support Sudeep Holla
2014-09-03 17:00 ` [PATCH v4 04/11] drivers: base: support cpu cache information interface to userspace via sysfs Sudeep Holla
@ 2014-09-03 17:00 ` Sudeep Holla
1 sibling, 0 replies; 9+ messages in thread
From: Sudeep Holla @ 2014-09-03 17:00 UTC (permalink / raw)
To: LKML
Cc: Sudeep Holla, Heiko Carstens, Lorenzo Pieralisi,
Greg Kroah-Hartman, Tony Luck, Fenghua Yu, linux-ia64
From: Sudeep Holla <sudeep.holla@arm.com>
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: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: linux-ia64@vger.kernel.org
---
arch/ia64/kernel/topology.c | 421 ++++++++++++--------------------------------
1 file changed, 111 insertions(+), 310 deletions(-)
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index f295f9abba4b..3d6749cb53ec 100644
--- a/arch/ia64/kernel/topology.c
+++ b/arch/ia64/kernel/topology.c
@@ -13,6 +13,7 @@
* Populate cpu cache entries in sysfs for cpu cache info
*/
+#include <linux/cacheinfo.h>
#include <linux/cpu.h>
#include <linux/kernel.h>
#include <linux/mm.h>
@@ -21,7 +22,6 @@
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/nodemask.h>
-#include <linux/notifier.h>
#include <linux/export.h>
#include <asm/mmzone.h>
#include <asm/numa.h>
@@ -103,60 +103,25 @@ subsys_initcall(topology_init);
/*
* Export cpu cache information through sysfs
*/
-
-/*
- * A bunch of string array to get pretty printing
- */
-static const char *cache_types[] = {
- "", /* not used */
- "Instruction",
- "Data",
- "Unified" /* unified */
-};
-
-static const char *cache_mattrib[]={
- "WriteThrough",
- "WriteBack",
- "", /* reserved */
- "" /* reserved */
-};
-
-struct cache_info {
- pal_cache_config_info_t cci;
- cpumask_t shared_cpu_map;
- int level;
- int type;
- struct kobject kobj;
-};
-
-struct cpu_cache_info {
- struct cache_info *cache_leaves;
- int num_cache_leaves;
- struct kobject kobj;
-};
-
-static struct cpu_cache_info all_cpu_cache_info[NR_CPUS];
-#define LEAF_KOBJECT_PTR(x,y) (&all_cpu_cache_info[x].cache_leaves[y])
-
#ifdef CONFIG_SMP
-static void cache_shared_cpu_map_setup(unsigned int cpu,
- struct cache_info * this_leaf)
+static int __cache_cpumap_setup(unsigned int cpu, struct cacheinfo *this_leaf)
{
pal_cache_shared_info_t csi;
- int num_shared, i = 0;
- unsigned int j;
+ int num_shared, i = 0, j;
+ enum cache_type type = this_leaf->type;
if (cpu_data(cpu)->threads_per_core <= 1 &&
cpu_data(cpu)->cores_per_socket <= 1) {
cpu_set(cpu, this_leaf->shared_cpu_map);
- return;
+ return 0;
}
- if (ia64_pal_cache_shared_info(this_leaf->level,
- this_leaf->type,
- 0,
- &csi) != PAL_STATUS_SUCCESS)
- return;
+ if (type = CACHE_TYPE_UNIFIED)
+ type = CACHE_TYPE_DATA;
+
+ if (ia64_pal_cache_shared_info(this_leaf->level, type, 0,
+ &csi) != PAL_STATUS_SUCCESS)
+ return -EIO;
num_shared = (int) csi.num_shared;
do {
@@ -168,305 +133,141 @@ static void cache_shared_cpu_map_setup(unsigned int cpu,
i++;
} while (i < num_shared &&
- ia64_pal_cache_shared_info(this_leaf->level,
- this_leaf->type,
- i,
- &csi) = PAL_STATUS_SUCCESS);
-}
-#else
-static void cache_shared_cpu_map_setup(unsigned int cpu,
- struct cache_info * this_leaf)
-{
- cpu_set(cpu, this_leaf->shared_cpu_map);
- return;
-}
-#endif
-
-static ssize_t show_coherency_line_size(struct cache_info *this_leaf,
- char *buf)
-{
- return sprintf(buf, "%u\n", 1 << this_leaf->cci.pcci_line_size);
+ ia64_pal_cache_shared_info(this_leaf->level, type, i,
+ &csi) = PAL_STATUS_SUCCESS);
+ return 0;
}
-static ssize_t show_ways_of_associativity(struct cache_info *this_leaf,
- char *buf)
+static int cache_shared_cpu_map_setup(unsigned int cpu)
{
- return sprintf(buf, "%u\n", this_leaf->cci.pcci_assoc);
+ unsigned int idx;
+ int ret = 0;
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+ struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+
+ for (idx = 0; idx < this_cpu_ci->num_leaves; idx++, this_leaf++) {
+ ret = __cache_cpumap_setup(cpu, this_leaf);
+ if (ret)
+ break;
+ }
+ return ret;
}
-
-static ssize_t show_attributes(struct cache_info *this_leaf, char *buf)
+#else
+static int cache_shared_cpu_map_setup(unsigned int cpu)
{
- return sprintf(buf,
- "%s\n",
- cache_mattrib[this_leaf->cci.pcci_cache_attr]);
-}
+ int idx;
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+ struct cacheinfo *this_leaf = this_cpu_ci->info_list;
-static ssize_t show_size(struct cache_info *this_leaf, char *buf)
-{
- return sprintf(buf, "%uK\n", this_leaf->cci.pcci_cache_size / 1024);
+ for (idx = 0; idx < this_cpu_ci->num_leaves; idx++, this_leaf++)
+ cpu_set(cpu, this_leaf->shared_cpu_map);
+ return 0;
}
+#endif
-static ssize_t show_number_of_sets(struct cache_info *this_leaf, char *buf)
+static ssize_t attributes_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
- unsigned number_of_sets = this_leaf->cci.pcci_cache_size;
- number_of_sets /= this_leaf->cci.pcci_assoc;
- number_of_sets /= 1 << this_leaf->cci.pcci_line_size;
-
- return sprintf(buf, "%u\n", number_of_sets);
+ 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 ssize_t show_shared_cpu_map(struct cache_info *this_leaf, char *buf)
-{
- ssize_t len;
- cpumask_t shared_cpu_map;
-
- cpumask_and(&shared_cpu_map,
- &this_leaf->shared_cpu_map, cpu_online_mask);
- len = cpumask_scnprintf(buf, NR_CPUS+1, &shared_cpu_map);
- len += sprintf(buf+len, "\n");
- return len;
-}
+static DEVICE_ATTR_RO(attributes);
-static ssize_t show_type(struct cache_info *this_leaf, char *buf)
+static umode_t
+cache_private_attrs_is_visible(struct kobject *kobj,
+ struct attribute *attr, int unused)
{
- int type = this_leaf->type + this_leaf->cci.pcci_unified;
- return sprintf(buf, "%s\n", cache_types[type]);
-}
+ struct device *dev = kobj_to_dev(kobj);
+ struct cacheinfo *this_leaf = dev_get_drvdata(dev);
-static ssize_t show_level(struct cache_info *this_leaf, char *buf)
-{
- return sprintf(buf, "%u\n", this_leaf->level);
+ if ((attr = &dev_attr_attributes.attr) && this_leaf->attributes)
+ return attr->mode;
+ return 0;
}
-struct cache_attr {
- struct attribute attr;
- ssize_t (*show)(struct cache_info *, char *);
- ssize_t (*store)(struct cache_info *, const char *, size_t count);
-};
-
-#ifdef define_one_ro
- #undef define_one_ro
-#endif
-#define define_one_ro(_name) \
- static struct cache_attr _name = \
-__ATTR(_name, 0444, show_##_name, NULL)
-
-define_one_ro(level);
-define_one_ro(type);
-define_one_ro(coherency_line_size);
-define_one_ro(ways_of_associativity);
-define_one_ro(size);
-define_one_ro(number_of_sets);
-define_one_ro(shared_cpu_map);
-define_one_ro(attributes);
-
-static struct attribute * cache_default_attrs[] = {
- &type.attr,
- &level.attr,
- &coherency_line_size.attr,
- &ways_of_associativity.attr,
- &attributes.attr,
- &size.attr,
- &number_of_sets.attr,
- &shared_cpu_map.attr,
+static struct attribute *cache_priv_attrs[] = {
+ &dev_attr_attributes.attr,
NULL
};
-#define to_object(k) container_of(k, struct cache_info, kobj)
-#define to_attr(a) container_of(a, struct cache_attr, attr)
-
-static ssize_t ia64_cache_show(struct kobject * kobj, struct attribute * attr, char * buf)
-{
- struct cache_attr *fattr = to_attr(attr);
- struct cache_info *this_leaf = to_object(kobj);
- ssize_t ret;
-
- ret = fattr->show ? fattr->show(this_leaf, buf) : 0;
- return ret;
-}
-
-static const struct sysfs_ops cache_sysfs_ops = {
- .show = ia64_cache_show
-};
-
-static struct kobj_type cache_ktype = {
- .sysfs_ops = &cache_sysfs_ops,
- .default_attrs = cache_default_attrs,
+static struct attribute_group cache_private_group = {
+ .attrs = cache_priv_attrs,
+ .is_visible = cache_private_attrs_is_visible,
};
-static struct kobj_type cache_ktype_percpu_entry = {
- .sysfs_ops = &cache_sysfs_ops,
-};
-
-static void cpu_cache_sysfs_exit(unsigned int cpu)
+const struct attribute_group *
+cache_get_priv_group(struct cacheinfo *this_leaf)
{
- kfree(all_cpu_cache_info[cpu].cache_leaves);
- all_cpu_cache_info[cpu].cache_leaves = NULL;
- all_cpu_cache_info[cpu].num_cache_leaves = 0;
- memset(&all_cpu_cache_info[cpu].kobj, 0, sizeof(struct kobject));
- return;
-}
-
-static int cpu_cache_sysfs_init(unsigned int cpu)
-{
- unsigned long i, levels, unique_caches;
- pal_cache_config_info_t cci;
- int j;
- long status;
- struct cache_info *this_cache;
- int num_cache_leaves = 0;
-
- if ((status = ia64_pal_cache_summary(&levels, &unique_caches)) != 0) {
- printk(KERN_ERR "ia64_pal_cache_summary=%ld\n", status);
- return -1;
- }
-
- this_cache=kzalloc(sizeof(struct cache_info)*unique_caches,
- GFP_KERNEL);
- if (this_cache = NULL)
- return -ENOMEM;
-
- for (i=0; i < levels; i++) {
- for (j=2; j >0 ; j--) {
- if ((status=ia64_pal_cache_config_info(i,j, &cci)) !- PAL_STATUS_SUCCESS)
- continue;
-
- this_cache[num_cache_leaves].cci = cci;
- this_cache[num_cache_leaves].level = i + 1;
- this_cache[num_cache_leaves].type = j;
-
- cache_shared_cpu_map_setup(cpu,
- &this_cache[num_cache_leaves]);
- num_cache_leaves ++;
- }
- }
-
- all_cpu_cache_info[cpu].cache_leaves = this_cache;
- all_cpu_cache_info[cpu].num_cache_leaves = num_cache_leaves;
-
- memset(&all_cpu_cache_info[cpu].kobj, 0, sizeof(struct kobject));
-
- return 0;
+ return &cache_private_group;
}
-/* Add cache interface for CPU device */
-static int cache_add_dev(struct device *sys_dev)
+static void ci_leaf_init(struct cacheinfo *this_leaf,
+ pal_cache_config_info_t *cci,
+ enum cache_type type, unsigned int level)
{
- unsigned int cpu = sys_dev->id;
- unsigned long i, j;
- struct cache_info *this_object;
- int retval = 0;
- cpumask_t oldmask;
-
- if (all_cpu_cache_info[cpu].kobj.parent)
- return 0;
-
- oldmask = current->cpus_allowed;
- retval = set_cpus_allowed_ptr(current, cpumask_of(cpu));
- if (unlikely(retval))
- return retval;
-
- retval = cpu_cache_sysfs_init(cpu);
- set_cpus_allowed_ptr(current, &oldmask);
- if (unlikely(retval < 0))
- return retval;
-
- retval = kobject_init_and_add(&all_cpu_cache_info[cpu].kobj,
- &cache_ktype_percpu_entry, &sys_dev->kobj,
- "%s", "cache");
- if (unlikely(retval < 0)) {
- cpu_cache_sysfs_exit(cpu);
- return retval;
- }
-
- for (i = 0; i < all_cpu_cache_info[cpu].num_cache_leaves; i++) {
- this_object = LEAF_KOBJECT_PTR(cpu,i);
- retval = kobject_init_and_add(&(this_object->kobj),
- &cache_ktype,
- &all_cpu_cache_info[cpu].kobj,
- "index%1lu", i);
- if (unlikely(retval)) {
- for (j = 0; j < i; j++) {
- kobject_put(&(LEAF_KOBJECT_PTR(cpu,j)->kobj));
- }
- kobject_put(&all_cpu_cache_info[cpu].kobj);
- cpu_cache_sysfs_exit(cpu);
- return retval;
- }
- kobject_uevent(&(this_object->kobj), KOBJ_ADD);
- }
- kobject_uevent(&all_cpu_cache_info[cpu].kobj, KOBJ_ADD);
- return retval;
+ unsigned number_of_sets = cci->pcci_cache_size;
+
+ number_of_sets /= cci->pcci_assoc;
+ number_of_sets /= 1 << cci->pcci_line_size;
+ this_leaf->level = level;
+ this_leaf->type = cci->pcci_unified ? CACHE_TYPE_UNIFIED : type;
+ this_leaf->coherency_line_size = cci->pcci_line_size;
+ this_leaf->ways_of_associativity = cci->pcci_assoc;
+ this_leaf->size = cci->pcci_cache_size;
+ this_leaf->attributes = cci->pcci_cache_attr;
+ this_leaf->number_of_sets = number_of_sets;
}
-/* Remove cache interface for CPU device */
-static int cache_remove_dev(struct device *sys_dev)
+int init_cache_level(unsigned int cpu)
{
- unsigned int cpu = sys_dev->id;
- unsigned long i;
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+ unsigned long levels, unique_caches;
+ long status;
- for (i = 0; i < all_cpu_cache_info[cpu].num_cache_leaves; i++)
- kobject_put(&(LEAF_KOBJECT_PTR(cpu,i)->kobj));
+ if (!this_cpu_ci)
+ return -EINVAL;
- if (all_cpu_cache_info[cpu].kobj.parent) {
- kobject_put(&all_cpu_cache_info[cpu].kobj);
- memset(&all_cpu_cache_info[cpu].kobj,
- 0,
- sizeof(struct kobject));
+ status = ia64_pal_cache_summary(&levels, &unique_caches);
+ if (status != PAL_STATUS_SUCCESS) {
+ pr_err("ia64_pal_cache_summary = %ld\n", status);
+ return -EIO;
}
-
- cpu_cache_sysfs_exit(cpu);
+ this_cpu_ci->num_levels = levels;
+ this_cpu_ci->num_leaves = unique_caches;
return 0;
}
-/*
- * When a cpu is hot-plugged, do a check and initiate
- * cache kobject if necessary
- */
-static int cache_cpu_callback(struct notifier_block *nfb,
- unsigned long action, void *hcpu)
-{
- unsigned int cpu = (unsigned long)hcpu;
- struct device *sys_dev;
-
- sys_dev = get_cpu_device(cpu);
- switch (action) {
- case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
- cache_add_dev(sys_dev);
- break;
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- cache_remove_dev(sys_dev);
- break;
- }
- return NOTIFY_OK;
-}
-
-static struct notifier_block cache_cpu_notifier -{
- .notifier_call = cache_cpu_callback
-};
-
-static int __init cache_sysfs_init(void)
+int populate_cache_leaves(unsigned int cpu)
{
- int i;
-
- cpu_notifier_register_begin();
-
- for_each_online_cpu(i) {
- struct device *sys_dev = get_cpu_device((unsigned int)i);
- cache_add_dev(sys_dev);
+ unsigned int level, idx;
+ s64 status;
+ pal_cache_config_info_t cci;
+ enum cache_type type;
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+ struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+
+ for (idx = 0, level = 1; level <= this_cpu_ci->num_levels &&
+ idx < this_cpu_ci->num_leaves; idx++, level++) {
+ if (!this_leaf)
+ return -EINVAL;
+
+ type = CACHE_TYPE_INST;
+ status = ia64_pal_cache_config_info(level - 1, type, &cci);
+ if (status = PAL_STATUS_SUCCESS)
+ ci_leaf_init(this_leaf++, &cci, type, level);
+ type = CACHE_TYPE_DATA;
+ status = ia64_pal_cache_config_info(level - 1, type, &cci);
+ if (status = PAL_STATUS_SUCCESS)
+ ci_leaf_init(this_leaf++, &cci, type, level);
}
-
- __register_hotcpu_notifier(&cache_cpu_notifier);
-
- cpu_notifier_register_done();
-
- return 0;
+ return cache_shared_cpu_map_setup(cpu);
}
-
-device_initcall(cache_sysfs_init);
-
--
1.8.3.2
^ permalink raw reply related [flat|nested] 9+ messages in thread