Commit acc02a10 authored by Keith Busch's avatar Keith Busch Committed by Greg Kroah-Hartman

node: Add memory-side caching attributes

System memory may have caches to help improve access speed to frequently
requested address ranges. While the system provided cache is transparent
to the software accessing these memory ranges, applications can optimize
their own access based on cache attributes.

Provide a new API for the kernel to register these memory-side caches
under the memory node that provides it.

The new sysfs representation is modeled from the existing cpu cacheinfo
attributes, as seen from /sys/devices/system/cpu/<cpu>/cache/.  Unlike CPU
cacheinfo though, the node cache level is reported from the view of the
memory. A higher level number is nearer to the CPU, while lower levels
are closer to the last level memory.

The exported attributes are the cache size, the line size, associativity
indexing, and write back policy, and add the attributes for the system
memory caches to sysfs stable documentation.
Signed-off-by: default avatarKeith Busch <keith.busch@intel.com>
Reviewed-by: default avatarRafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: default avatarBrice Goglin <Brice.Goglin@inria.fr>
Tested-by: default avatarBrice Goglin <Brice.Goglin@inria.fr>
Signed-off-by: default avatarGreg Kroah-Hartman <gregkh@linuxfoundation.org>
parent e1cf33aa
......@@ -142,3 +142,37 @@ Contact: Keith Busch <keith.busch@intel.com>
Description:
This node's write latency in nanoseconds when access
from nodes found in this class's linked initiators.
What: /sys/devices/system/node/nodeX/memory_side_cache/indexY/
Date: December 2018
Contact: Keith Busch <keith.busch@intel.com>
Description:
The directory containing attributes for the memory-side cache
level 'Y'.
What: /sys/devices/system/node/nodeX/memory_side_cache/indexY/indexing
Date: December 2018
Contact: Keith Busch <keith.busch@intel.com>
Description:
The caches associativity indexing: 0 for direct mapped,
non-zero if indexed.
What: /sys/devices/system/node/nodeX/memory_side_cache/indexY/line_size
Date: December 2018
Contact: Keith Busch <keith.busch@intel.com>
Description:
The number of bytes accessed from the next cache level on a
cache miss.
What: /sys/devices/system/node/nodeX/memory_side_cache/indexY/size
Date: December 2018
Contact: Keith Busch <keith.busch@intel.com>
Description:
The size of this memory side cache in bytes.
What: /sys/devices/system/node/nodeX/memory_side_cache/indexY/write_policy
Date: December 2018
Contact: Keith Busch <keith.busch@intel.com>
Description:
The cache write policy: 0 for write-back, 1 for write-through,
other or unknown.
......@@ -205,6 +205,155 @@ void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
}
}
}
/**
* struct node_cache_info - Internal tracking for memory node caches
* @dev: Device represeting the cache level
* @node: List element for tracking in the node
* @cache_attrs:Attributes for this cache level
*/
struct node_cache_info {
struct device dev;
struct list_head node;
struct node_cache_attrs cache_attrs;
};
#define to_cache_info(device) container_of(device, struct node_cache_info, dev)
#define CACHE_ATTR(name, fmt) \
static ssize_t name##_show(struct device *dev, \
struct device_attribute *attr, \
char *buf) \
{ \
return sprintf(buf, fmt "\n", to_cache_info(dev)->cache_attrs.name);\
} \
DEVICE_ATTR_RO(name);
CACHE_ATTR(size, "%llu")
CACHE_ATTR(line_size, "%u")
CACHE_ATTR(indexing, "%u")
CACHE_ATTR(write_policy, "%u")
static struct attribute *cache_attrs[] = {
&dev_attr_indexing.attr,
&dev_attr_size.attr,
&dev_attr_line_size.attr,
&dev_attr_write_policy.attr,
NULL,
};
ATTRIBUTE_GROUPS(cache);
static void node_cache_release(struct device *dev)
{
kfree(dev);
}
static void node_cacheinfo_release(struct device *dev)
{
struct node_cache_info *info = to_cache_info(dev);
kfree(info);
}
static void node_init_cache_dev(struct node *node)
{
struct device *dev;
dev = kzalloc(sizeof(*dev), GFP_KERNEL);
if (!dev)
return;
dev->parent = &node->dev;
dev->release = node_cache_release;
if (dev_set_name(dev, "memory_side_cache"))
goto free_dev;
if (device_register(dev))
goto free_name;
pm_runtime_no_callbacks(dev);
node->cache_dev = dev;
return;
free_name:
kfree_const(dev->kobj.name);
free_dev:
kfree(dev);
}
/**
* node_add_cache() - add cache attribute to a memory node
* @nid: Node identifier that has new cache attributes
* @cache_attrs: Attributes for the cache being added
*/
void node_add_cache(unsigned int nid, struct node_cache_attrs *cache_attrs)
{
struct node_cache_info *info;
struct device *dev;
struct node *node;
if (!node_online(nid) || !node_devices[nid])
return;
node = node_devices[nid];
list_for_each_entry(info, &node->cache_attrs, node) {
if (info->cache_attrs.level == cache_attrs->level) {
dev_warn(&node->dev,
"attempt to add duplicate cache level:%d\n",
cache_attrs->level);
return;
}
}
if (!node->cache_dev)
node_init_cache_dev(node);
if (!node->cache_dev)
return;
info = kzalloc(sizeof(*info), GFP_KERNEL);
if (!info)
return;
dev = &info->dev;
dev->parent = node->cache_dev;
dev->release = node_cacheinfo_release;
dev->groups = cache_groups;
if (dev_set_name(dev, "index%d", cache_attrs->level))
goto free_cache;
info->cache_attrs = *cache_attrs;
if (device_register(dev)) {
dev_warn(&node->dev, "failed to add cache level:%d\n",
cache_attrs->level);
goto free_name;
}
pm_runtime_no_callbacks(dev);
list_add_tail(&info->node, &node->cache_attrs);
return;
free_name:
kfree_const(dev->kobj.name);
free_cache:
kfree(info);
}
static void node_remove_caches(struct node *node)
{
struct node_cache_info *info, *next;
if (!node->cache_dev)
return;
list_for_each_entry_safe(info, next, &node->cache_attrs, node) {
list_del(&info->node);
device_unregister(&info->dev);
}
device_unregister(node->cache_dev);
}
static void node_init_caches(unsigned int nid)
{
INIT_LIST_HEAD(&node_devices[nid]->cache_attrs);
}
#else
static void node_init_caches(unsigned int nid) { }
static void node_remove_caches(struct node *node) { }
#endif
#define K(x) ((x) << (PAGE_SHIFT - 10))
......@@ -489,6 +638,7 @@ void unregister_node(struct node *node)
{
hugetlb_unregister_node(node); /* no-op, if memoryless node */
node_remove_accesses(node);
node_remove_caches(node);
device_unregister(&node->dev);
}
......@@ -781,6 +931,7 @@ int __register_one_node(int nid)
INIT_LIST_HEAD(&node_devices[nid]->access_list);
/* initialize work queue for memory hot plug */
init_node_hugetlb_work(nid);
node_init_caches(nid);
return error;
}
......
......@@ -35,10 +35,45 @@ struct node_hmem_attrs {
unsigned int write_latency;
};
enum cache_indexing {
NODE_CACHE_DIRECT_MAP,
NODE_CACHE_INDEXED,
NODE_CACHE_OTHER,
};
enum cache_write_policy {
NODE_CACHE_WRITE_BACK,
NODE_CACHE_WRITE_THROUGH,
NODE_CACHE_WRITE_OTHER,
};
/**
* struct node_cache_attrs - system memory caching attributes
*
* @indexing: The ways memory blocks may be placed in cache
* @write_policy: Write back or write through policy
* @size: Total size of cache in bytes
* @line_size: Number of bytes fetched on a cache miss
* @level: The cache hierarchy level
*/
struct node_cache_attrs {
enum cache_indexing indexing;
enum cache_write_policy write_policy;
u64 size;
u16 line_size;
u8 level;
};
#ifdef CONFIG_HMEM_REPORTING
void node_add_cache(unsigned int nid, struct node_cache_attrs *cache_attrs);
void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
unsigned access);
#else
static inline void node_add_cache(unsigned int nid,
struct node_cache_attrs *cache_attrs)
{
}
static inline void node_set_perf_attrs(unsigned int nid,
struct node_hmem_attrs *hmem_attrs,
unsigned access)
......@@ -53,6 +88,10 @@ struct node {
#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HUGETLBFS)
struct work_struct node_work;
#endif
#ifdef CONFIG_HMEM_REPORTING
struct list_head cache_attrs;
struct device *cache_dev;
#endif
};
struct memory_block;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment