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).
Signed-off-by: "Huang, Ying" <[email protected]>
Tested-by: Bharata B Rao <[email protected]>
Cc: Aneesh Kumar K.V <[email protected]>
Cc: Wei Xu <[email protected]>
Cc: Alistair Popple <[email protected]>
Cc: Dan Williams <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Davidlohr Bueso <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Jonathan Cameron <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Yang Shi <[email protected]>
Cc: Dave Jiang <[email protected]>
Cc: Rafael J Wysocki <[email protected]>
---
include/linux/memory-tiers.h | 19 ++++++++++++
mm/memory-tiers.c | 59 ++++++++++++++++++++++++++++++++++++
2 files changed, 78 insertions(+)
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 437441cdf78f..c8382220cced 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -6,6 +6,7 @@
#include <linux/nodemask.h>
#include <linux/kref.h>
#include <linux/mmzone.h>
+#include <linux/notifier.h>
/*
* Each tier cover a abstrace distance chunk size of 128
*/
@@ -36,6 +37,9 @@ struct memory_dev_type *alloc_memory_type(int adistance);
void put_memory_type(struct memory_dev_type *memtype);
void init_node_memory_type(int node, struct memory_dev_type *default_type);
void clear_node_memory_type(int node, struct memory_dev_type *memtype);
+int register_mt_adistance_algorithm(struct notifier_block *nb);
+int unregister_mt_adistance_algorithm(struct notifier_block *nb);
+int mt_calc_adistance(int node, int *adist);
#ifdef CONFIG_MIGRATION
int next_demotion_node(int node);
void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
@@ -97,5 +101,20 @@ static inline bool node_is_toptier(int node)
{
return true;
}
+
+static inline int register_mt_adistance_algorithm(struct notifier_block *nb)
+{
+ return 0;
+}
+
+static inline int unregister_mt_adistance_algorithm(struct notifier_block *nb)
+{
+ return 0;
+}
+
+static inline int mt_calc_adistance(int node, int *adist)
+{
+ return NOTIFY_DONE;
+}
#endif /* CONFIG_NUMA */
#endif /* _LINUX_MEMORY_TIERS_H */
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 37a4f59d9585..76c0ad47a5ad 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)
{
--
2.39.2
On 9/12/23 01:20, Huang Ying wrote:
> 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).
>
> Signed-off-by: "Huang, Ying" <[email protected]>
> Tested-by: Bharata B Rao <[email protected]>
> Cc: Aneesh Kumar K.V <[email protected]>
> Cc: Wei Xu <[email protected]>
> Cc: Alistair Popple <[email protected]>
> Cc: Dan Williams <[email protected]>
> Cc: Dave Hansen <[email protected]>
> Cc: Davidlohr Bueso <[email protected]>
> Cc: Johannes Weiner <[email protected]>
> Cc: Jonathan Cameron <[email protected]>
> Cc: Michal Hocko <[email protected]>
> Cc: Yang Shi <[email protected]>
> Cc: Dave Jiang <[email protected]>
> Cc: Rafael J Wysocki <[email protected]>
Reviewed-by: Dave Jiang <[email protected]>
> ---
> include/linux/memory-tiers.h | 19 ++++++++++++
> mm/memory-tiers.c | 59 ++++++++++++++++++++++++++++++++++++
> 2 files changed, 78 insertions(+)
>
> diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
> index 437441cdf78f..c8382220cced 100644
> --- a/include/linux/memory-tiers.h
> +++ b/include/linux/memory-tiers.h
> @@ -6,6 +6,7 @@
> #include <linux/nodemask.h>
> #include <linux/kref.h>
> #include <linux/mmzone.h>
> +#include <linux/notifier.h>
> /*
> * Each tier cover a abstrace distance chunk size of 128
> */
> @@ -36,6 +37,9 @@ struct memory_dev_type *alloc_memory_type(int adistance);
> void put_memory_type(struct memory_dev_type *memtype);
> void init_node_memory_type(int node, struct memory_dev_type *default_type);
> void clear_node_memory_type(int node, struct memory_dev_type *memtype);
> +int register_mt_adistance_algorithm(struct notifier_block *nb);
> +int unregister_mt_adistance_algorithm(struct notifier_block *nb);
> +int mt_calc_adistance(int node, int *adist);
> #ifdef CONFIG_MIGRATION
> int next_demotion_node(int node);
> void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
> @@ -97,5 +101,20 @@ static inline bool node_is_toptier(int node)
> {
> return true;
> }
> +
> +static inline int register_mt_adistance_algorithm(struct notifier_block *nb)
> +{
> + return 0;
> +}
> +
> +static inline int unregister_mt_adistance_algorithm(struct notifier_block *nb)
> +{
> + return 0;
> +}
> +
> +static inline int mt_calc_adistance(int node, int *adist)
> +{
> + return NOTIFY_DONE;
> +}
> #endif /* CONFIG_NUMA */
> #endif /* _LINUX_MEMORY_TIERS_H */
> diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
> index 37a4f59d9585..76c0ad47a5ad 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)
> {
Reviewed-by: Alistair Popple <[email protected]>
Huang Ying <[email protected]> writes:
> 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).
>
> Signed-off-by: "Huang, Ying" <[email protected]>
> Tested-by: Bharata B Rao <[email protected]>
> Cc: Aneesh Kumar K.V <[email protected]>
> Cc: Wei Xu <[email protected]>
> Cc: Alistair Popple <[email protected]>
> Cc: Dan Williams <[email protected]>
> Cc: Dave Hansen <[email protected]>
> Cc: Davidlohr Bueso <[email protected]>
> Cc: Johannes Weiner <[email protected]>
> Cc: Jonathan Cameron <[email protected]>
> Cc: Michal Hocko <[email protected]>
> Cc: Yang Shi <[email protected]>
> Cc: Dave Jiang <[email protected]>
> Cc: Rafael J Wysocki <[email protected]>
> ---
> include/linux/memory-tiers.h | 19 ++++++++++++
> mm/memory-tiers.c | 59 ++++++++++++++++++++++++++++++++++++
> 2 files changed, 78 insertions(+)
>
> diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
> index 437441cdf78f..c8382220cced 100644
> --- a/include/linux/memory-tiers.h
> +++ b/include/linux/memory-tiers.h
> @@ -6,6 +6,7 @@
> #include <linux/nodemask.h>
> #include <linux/kref.h>
> #include <linux/mmzone.h>
> +#include <linux/notifier.h>
> /*
> * Each tier cover a abstrace distance chunk size of 128
> */
> @@ -36,6 +37,9 @@ struct memory_dev_type *alloc_memory_type(int adistance);
> void put_memory_type(struct memory_dev_type *memtype);
> void init_node_memory_type(int node, struct memory_dev_type *default_type);
> void clear_node_memory_type(int node, struct memory_dev_type *memtype);
> +int register_mt_adistance_algorithm(struct notifier_block *nb);
> +int unregister_mt_adistance_algorithm(struct notifier_block *nb);
> +int mt_calc_adistance(int node, int *adist);
> #ifdef CONFIG_MIGRATION
> int next_demotion_node(int node);
> void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
> @@ -97,5 +101,20 @@ static inline bool node_is_toptier(int node)
> {
> return true;
> }
> +
> +static inline int register_mt_adistance_algorithm(struct notifier_block *nb)
> +{
> + return 0;
> +}
> +
> +static inline int unregister_mt_adistance_algorithm(struct notifier_block *nb)
> +{
> + return 0;
> +}
> +
> +static inline int mt_calc_adistance(int node, int *adist)
> +{
> + return NOTIFY_DONE;
> +}
> #endif /* CONFIG_NUMA */
> #endif /* _LINUX_MEMORY_TIERS_H */
> diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
> index 37a4f59d9585..76c0ad47a5ad 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)
> {