mm/demotion/dax/kmem: set node's abstract distance to MEMTIER_DEFAULT_DAX_ADISTANCE

By default, all nodes are assigned to the default memory tier which is the
memory tier designated for nodes with DRAM

Set dax kmem device node's tier to slower memory tier by assigning
abstract distance to MEMTIER_DEFAULT_DAX_ADISTANCE.  Low-level drivers
like papr_scm or ACPI NFIT can initialize memory device type to a more
accurate value based on device tree details or HMAT.  If the kernel
doesn't find the memory type initialized, a default slower memory type is
assigned by the kmem driver.

[aneesh.kumar@linux.ibm.com: assign correct memory type for multiple dax devices with the same node affinity]
  Link: https://lkml.kernel.org/r/20220826100224.542312-1-aneesh.kumar@linux.ibm.com
Link: https://lkml.kernel.org/r/20220818131042.113280-5-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Wei Xu <weixugc@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Bharata B Rao <bharata@amd.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hesham Almatary <hesham.almatary@huawei.com>
Cc: Jagdish Gediya <jvgediya.oss@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 39 insertions, 3 deletions

diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index a37622060fff..4852a2dbdb27 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -11,9 +11,17 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
+#include <linux/memory-tiers.h>
 #include "dax-private.h"
 #include "bus.h"
 
+/*
+ * Default abstract distance assigned to the NUMA node onlined
+ * by DAX/kmem if the low level platform driver didn't initialize
+ * one for this NUMA node.
+ */
+#define MEMTIER_DEFAULT_DAX_ADISTANCE	(MEMTIER_ADISTANCE_DRAM * 5)
+
 /* Memory resource name used for add_memory_driver_managed(). */
 static const char *kmem_name;
 /* Set if any memory will remain added when the driver will be unloaded. */
@@ -41,6 +49,7 @@ struct dax_kmem_data {
 	struct resource *res[];
 };
 
+static struct memory_dev_type *dax_slowmem_type;
 static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 {
 	struct device *dev = &dev_dax->dev;
@@ -79,11 +88,13 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 		return -EINVAL;
 	}
 
+	init_node_memory_type(numa_node, dax_slowmem_type);
+
+	rc = -ENOMEM;
 	data = kzalloc(struct_size(data, res, dev_dax->nr_range), GFP_KERNEL);
 	if (!data)
-		return -ENOMEM;
+		goto err_dax_kmem_data;
 
-	rc = -ENOMEM;
 	data->res_name = kstrdup(dev_name(dev), GFP_KERNEL);
 	if (!data->res_name)
 		goto err_res_name;
@@ -155,6 +166,8 @@ err_reg_mgid:
 	kfree(data->res_name);
 err_res_name:
 	kfree(data);
+err_dax_kmem_data:
+	clear_node_memory_type(numa_node, dax_slowmem_type);
 	return rc;
 }
 
@@ -162,6 +175,7 @@ err_res_name:
 static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
 {
 	int i, success = 0;
+	int node = dev_dax->target_node;
 	struct device *dev = &dev_dax->dev;
 	struct dax_kmem_data *data = dev_get_drvdata(dev);
 
@@ -198,6 +212,14 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
 		kfree(data->res_name);
 		kfree(data);
 		dev_set_drvdata(dev, NULL);
+		/*
+		 * Clear the memtype association on successful unplug.
+		 * If not, we have memory blocks left which can be
+		 * offlined/onlined later. We need to keep memory_dev_type
+		 * for that. This implies this reference will be around
+		 * till next reboot.
+		 */
+		clear_node_memory_type(node, dax_slowmem_type);
 	}
 }
 #else
@@ -228,9 +250,22 @@ static int __init dax_kmem_init(void)
 	if (!kmem_name)
 		return -ENOMEM;
 
+	dax_slowmem_type = alloc_memory_type(MEMTIER_DEFAULT_DAX_ADISTANCE);
+	if (IS_ERR(dax_slowmem_type)) {
+		rc = PTR_ERR(dax_slowmem_type);
+		goto err_dax_slowmem_type;
+	}
+
 	rc = dax_driver_register(&device_dax_kmem_driver);
 	if (rc)
-		kfree_const(kmem_name);
+		goto error_dax_driver;
+
+	return rc;
+
+error_dax_driver:
+	destroy_memory_type(dax_slowmem_type);
+err_dax_slowmem_type:
+	kfree_const(kmem_name);
 	return rc;
 }
 
@@ -239,6 +274,7 @@ static void __exit dax_kmem_exit(void)
 	dax_driver_unregister(&device_dax_kmem_driver);
 	if (!any_hotremove_failed)
 		kfree_const(kmem_name);
+	destroy_memory_type(dax_slowmem_type);
 }
 
 MODULE_AUTHOR("Intel Corporation");