node: Add heterogenous memory access attributes

Heterogeneous memory systems provide memory nodes with different latency
and bandwidth performance attributes. Provide a new kernel interface
for subsystems to register the attributes under the memory target
node's initiator access class. If the system provides this information,
applications may query these attributes when deciding which node to
request memory.

The following example shows the new sysfs hierarchy for a node exporting
performance attributes:

  # tree -P "read*|write*"/sys/devices/system/node/nodeY/accessZ/initiators/
  /sys/devices/system/node/nodeY/accessZ/initiators/
  |-- read_bandwidth
  |-- read_latency
  |-- write_bandwidth
  `-- write_latency

The bandwidth is exported as MB/s and latency is reported in
nanoseconds. The values are taken from the platform as reported by the
manufacturer.

Memory accesses from an initiator node that is not one of the memory's
access "Z" initiator nodes linked in the same directory may observe
different performance than reported here. When a subsystem makes use
of this interface, initiators of a different access number may not have
the same performance relative to initiators in other access numbers, or
omitted from the any access class' initiators.

Descriptions for memory access initiator performance access attributes
are added to sysfs stable documentation.

Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Tested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Brice Goglin <Brice.Goglin@inria.fr>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

4 files changed, 121 insertions, 0 deletions

diff --git a/Documentation/ABI/stable/sysfs-devices-node b/Documentation/ABI/stable/sysfs-devices-node
index 433bcc04e542..735a40a3f9b2 100644
--- a/Documentation/ABI/stable/sysfs-devices-node
+++ b/Documentation/ABI/stable/sysfs-devices-node
@@ -114,3 +114,31 @@ Contact:	Keith Busch <keith.busch@intel.com>
 Description:
 		The directory containing symlinks to memory targets that
 		this initiator node has class "Y" access.
+
+What:		/sys/devices/system/node/nodeX/accessY/initiators/read_bandwidth
+Date:		December 2018
+Contact:	Keith Busch <keith.busch@intel.com>
+Description:
+		This node's read bandwidth in MB/s when accessed from
+		nodes found in this access class's linked initiators.
+
+What:		/sys/devices/system/node/nodeX/accessY/initiators/read_latency
+Date:		December 2018
+Contact:	Keith Busch <keith.busch@intel.com>
+Description:
+		This node's read latency in nanoseconds when accessed
+		from nodes found in this access class's linked initiators.
+
+What:		/sys/devices/system/node/nodeX/accessY/initiators/write_bandwidth
+Date:		December 2018
+Contact:	Keith Busch <keith.busch@intel.com>
+Description:
+		This node's write bandwidth in MB/s when accessed from
+		found in this access class's linked initiators.
+
+What:		/sys/devices/system/node/nodeX/accessY/initiators/write_latency
+Date:		December 2018
+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.
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 9fb2c4c92340..1d47ab987413 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -148,6 +148,14 @@ config DEBUG_TEST_DRIVER_REMOVE
 	  unusable. You should say N here unless you are explicitly looking to
 	  test this functionality.
 
+config HMEM_REPORTING
+	bool
+	default n
+	depends on NUMA
+	help
+	  Enable reporting for heterogenous memory access attributes under
+	  their non-uniform memory nodes.
+
 source "drivers/base/test/Kconfig"
 
 config SYS_HYPERVISOR
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 6f4097680580..2de546a040a5 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -71,6 +71,9 @@ struct node_access_nodes {
 	struct device		dev;
 	struct list_head	list_node;
 	unsigned		access;
+#ifdef CONFIG_HMEM_REPORTING
+	struct node_hmem_attrs	hmem_attrs;
+#endif
 };
 #define to_access_nodes(dev) container_of(dev, struct node_access_nodes, dev)
 
@@ -148,6 +151,62 @@ free:
 	return NULL;
 }
 
+#ifdef CONFIG_HMEM_REPORTING
+#define ACCESS_ATTR(name) 						   \
+static ssize_t name##_show(struct device *dev,				   \
+			   struct device_attribute *attr,		   \
+			   char *buf)					   \
+{									   \
+	return sprintf(buf, "%u\n", to_access_nodes(dev)->hmem_attrs.name); \
+}									   \
+static DEVICE_ATTR_RO(name);
+
+ACCESS_ATTR(read_bandwidth)
+ACCESS_ATTR(read_latency)
+ACCESS_ATTR(write_bandwidth)
+ACCESS_ATTR(write_latency)
+
+static struct attribute *access_attrs[] = {
+	&dev_attr_read_bandwidth.attr,
+	&dev_attr_read_latency.attr,
+	&dev_attr_write_bandwidth.attr,
+	&dev_attr_write_latency.attr,
+	NULL,
+};
+
+/**
+ * node_set_perf_attrs - Set the performance values for given access class
+ * @nid: Node identifier to be set
+ * @hmem_attrs: Heterogeneous memory performance attributes
+ * @access: The access class the for the given attributes
+ */
+void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
+			 unsigned access)
+{
+	struct node_access_nodes *c;
+	struct node *node;
+	int i;
+
+	if (WARN_ON_ONCE(!node_online(nid)))
+		return;
+
+	node = node_devices[nid];
+	c = node_init_node_access(node, access);
+	if (!c)
+		return;
+
+	c->hmem_attrs = *hmem_attrs;
+	for (i = 0; access_attrs[i] != NULL; i++) {
+		if (sysfs_add_file_to_group(&c->dev.kobj, access_attrs[i],
+					    "initiators")) {
+			pr_info("failed to add performance attribute to node %d\n",
+				nid);
+			break;
+		}
+	}
+}
+#endif
+
 #define K(x) ((x) << (PAGE_SHIFT - 10))
 static ssize_t node_read_meminfo(struct device *dev,
 			struct device_attribute *attr, char *buf)
diff --git a/include/linux/node.h b/include/linux/node.h
index bb288817ed33..4139d728f8b3 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -20,6 +20,32 @@
 #include <linux/list.h>
 #include <linux/workqueue.h>
 
+/**
+ * struct node_hmem_attrs - heterogeneous memory performance attributes
+ *
+ * @read_bandwidth:	Read bandwidth in MB/s
+ * @write_bandwidth:	Write bandwidth in MB/s
+ * @read_latency:	Read latency in nanoseconds
+ * @write_latency:	Write latency in nanoseconds
+ */
+struct node_hmem_attrs {
+	unsigned int read_bandwidth;
+	unsigned int write_bandwidth;
+	unsigned int read_latency;
+	unsigned int write_latency;
+};
+
+#ifdef CONFIG_HMEM_REPORTING
+void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
+			 unsigned access);
+#else
+static inline void node_set_perf_attrs(unsigned int nid,
+				       struct node_hmem_attrs *hmem_attrs,
+				       unsigned access)
+{
+}
+#endif
+
 struct node {
 	struct device	dev;
 	struct list_head access_list;