summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorHuang Ying <ying.huang@intel.com>2023-09-26 14:06:25 +0800
committerAndrew Morton <akpm@linux-foundation.org>2023-10-16 15:44:38 -0700
commit07a8bdd4120ced3490ef9adf51b8086af0aaa8e7 (patch)
treef55a0f62ef20091f05aba87c73bad1685144ce69 /mm
parenta48bf7b4757cd8de3497c2878536f46a8d2da65c (diff)
memory tiering: add abstract distance calculation algorithms management
Patch series "memory tiering: calculate abstract distance based on ACPI HMAT", v4. We have the explicit memory tiers framework to manage systems with multiple types of memory, e.g., DRAM in DIMM slots and CXL memory devices. Where, same kind of memory devices will be grouped into memory types, then put into memory tiers. To describe the performance of a memory type, abstract distance is defined. Which is in direct proportion to the memory latency and inversely proportional to the memory bandwidth. To keep the code as simple as possible, fixed abstract distance is used in dax/kmem to describe slow memory such as Optane DCPMM. To support more memory types, in this series, we added the abstract distance calculation algorithm management mechanism, provided a algorithm implementation based on ACPI HMAT, and used the general abstract distance calculation interface in dax/kmem driver. So, dax/kmem can support HBM (high bandwidth memory) in addition to the original Optane DCPMM. This patch (of 4): The abstract distance may be calculated by various drivers, such as ACPI HMAT, CXL CDAT, etc. While it may be used by various code which hot-add memory node, such as dax/kmem etc. To decouple the algorithm users and the providers, the abstract distance calculation algorithms management mechanism is implemented in this patch. It provides interface for the providers to register the implementation, and interface for the users. Multiple algorithm implementations can cooperate via calculating abstract distance for different memory nodes. The preference of algorithm implementations can be specified via priority (notifier_block.priority). Link: https://lkml.kernel.org/r/20230926060628.265989-1-ying.huang@intel.com Link: https://lkml.kernel.org/r/20230926060628.265989-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Tested-by: Bharata B Rao <bharata@amd.com> Reviewed-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Dave Jiang <dave.jiang@intel.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Wei Xu <weixugc@google.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Rafael J Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/memory-tiers.c59
1 files changed, 59 insertions, 0 deletions
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 876d8a5e210e..4301e7e89223 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -5,6 +5,7 @@
#include <linux/kobject.h>
#include <linux/memory.h>
#include <linux/memory-tiers.h>
+#include <linux/notifier.h>
#include "internal.h"
@@ -105,6 +106,8 @@ static int top_tier_adistance;
static struct demotion_nodes *node_demotion __read_mostly;
#endif /* CONFIG_MIGRATION */
+static BLOCKING_NOTIFIER_HEAD(mt_adistance_algorithms);
+
static inline struct memory_tier *to_memory_tier(struct device *device)
{
return container_of(device, struct memory_tier, dev);
@@ -592,6 +595,62 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype)
}
EXPORT_SYMBOL_GPL(clear_node_memory_type);
+/**
+ * register_mt_adistance_algorithm() - Register memory tiering abstract distance algorithm
+ * @nb: The notifier block which describe the algorithm
+ *
+ * Return: 0 on success, errno on error.
+ *
+ * Every memory tiering abstract distance algorithm provider needs to
+ * register the algorithm with register_mt_adistance_algorithm(). To
+ * calculate the abstract distance for a specified memory node, the
+ * notifier function will be called unless some high priority
+ * algorithm has provided result. The prototype of the notifier
+ * function is as follows,
+ *
+ * int (*algorithm_notifier)(struct notifier_block *nb,
+ * unsigned long nid, void *data);
+ *
+ * Where "nid" specifies the memory node, "data" is the pointer to the
+ * returned abstract distance (that is, "int *adist"). If the
+ * algorithm provides the result, NOTIFY_STOP should be returned.
+ * Otherwise, return_value & %NOTIFY_STOP_MASK == 0 to allow the next
+ * algorithm in the chain to provide the result.
+ */
+int register_mt_adistance_algorithm(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&mt_adistance_algorithms, nb);
+}
+EXPORT_SYMBOL_GPL(register_mt_adistance_algorithm);
+
+/**
+ * unregister_mt_adistance_algorithm() - Unregister memory tiering abstract distance algorithm
+ * @nb: the notifier block which describe the algorithm
+ *
+ * Return: 0 on success, errno on error.
+ */
+int unregister_mt_adistance_algorithm(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_unregister(&mt_adistance_algorithms, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_mt_adistance_algorithm);
+
+/**
+ * mt_calc_adistance() - Calculate abstract distance with registered algorithms
+ * @node: the node to calculate abstract distance for
+ * @adist: the returned abstract distance
+ *
+ * Return: if return_value & %NOTIFY_STOP_MASK != 0, then some
+ * abstract distance algorithm provides the result, and return it via
+ * @adist. Otherwise, no algorithm can provide the result and @adist
+ * will be kept as it is.
+ */
+int mt_calc_adistance(int node, int *adist)
+{
+ return blocking_notifier_call_chain(&mt_adistance_algorithms, node, adist);
+}
+EXPORT_SYMBOL_GPL(mt_calc_adistance);
+
static int __meminit memtier_hotplug_callback(struct notifier_block *self,
unsigned long action, void *_arg)
{