acpi, hmat: calculate abstract distance with HMAT

A memory tiering abstract distance calculation algorithm based on ACPI
HMAT is implemented.  The basic idea is as follows.

The performance attributes of system default DRAM nodes are recorded as
the base line.  Whose abstract distance is MEMTIER_ADISTANCE_DRAM.  Then,
the ratio of the abstract distance of a memory node (target) to
MEMTIER_ADISTANCE_DRAM is scaled based on the ratio of the performance
attributes of the node to that of the default DRAM nodes.

The functions to record the read/write latency/bandwidth of the default
DRAM nodes and calculate abstract distance according to read/write
latency/bandwidth ratio will be used by CXL CDAT (Coherent Device
Attribute Table) and other memory device drivers.  So, they are put in
memory-tiers.c.

Link: https://lkml.kernel.org/r/20230926060628.265989-4-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Tested-by: Bharata B Rao <bharata@amd.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Alistair Popple <apopple@nvidia.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>

1 files changed, 63 insertions, 2 deletions

diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 2dee0098f1a9..9ef5f1bdcfdb 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -24,6 +24,7 @@
 #include <linux/node.h>
 #include <linux/sysfs.h>
 #include <linux/dax.h>
+#include <linux/memory-tiers.h>
 
 static u8 hmat_revision;
 static int hmat_disable __initdata;
@@ -759,6 +760,61 @@ static int hmat_callback(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
+static int hmat_set_default_dram_perf(void)
+{
+	int rc;
+	int nid, pxm;
+	struct memory_target *target;
+	struct node_hmem_attrs *attrs;
+
+	if (!default_dram_type)
+		return -EIO;
+
+	for_each_node_mask(nid, default_dram_type->nodes) {
+		pxm = node_to_pxm(nid);
+		target = find_mem_target(pxm);
+		if (!target)
+			continue;
+		attrs = &target->hmem_attrs[1];
+		rc = mt_set_default_dram_perf(nid, attrs, "ACPI HMAT");
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int hmat_calculate_adistance(struct notifier_block *self,
+				    unsigned long nid, void *data)
+{
+	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
+	struct memory_target *target;
+	struct node_hmem_attrs *perf;
+	int *adist = data;
+	int pxm;
+
+	pxm = node_to_pxm(nid);
+	target = find_mem_target(pxm);
+	if (!target)
+		return NOTIFY_OK;
+
+	mutex_lock(&target_lock);
+	hmat_update_target_attrs(target, p_nodes, 1);
+	mutex_unlock(&target_lock);
+
+	perf = &target->hmem_attrs[1];
+
+	if (mt_perf_to_adistance(perf, adist))
+		return NOTIFY_OK;
+
+	return NOTIFY_STOP;
+}
+
+static struct notifier_block hmat_adist_nb __meminitdata = {
+	.notifier_call = hmat_calculate_adistance,
+	.priority = 100,
+};
+
 static __init void hmat_free_structures(void)
 {
 	struct memory_target *target, *tnext;
@@ -841,8 +897,13 @@ static __init int hmat_init(void)
 	hmat_register_targets();
 
 	/* Keep the table and structures if the notifier may use them */
-	if (!hotplug_memory_notifier(hmat_callback, HMAT_CALLBACK_PRI))
-		return 0;
+	if (hotplug_memory_notifier(hmat_callback, HMAT_CALLBACK_PRI))
+		goto out_put;
+
+	if (!hmat_set_default_dram_perf())
+		register_mt_adistance_algorithm(&hmat_adist_nb);
+
+	return 0;
 out_put:
 	hmat_free_structures();
 	acpi_put_table(tbl);