From: Rakie Kim <rakie.kim@sk.com>

This patch provides a way to set interleave weight information under
sysfs at /sys/kernel/mm/mempolicy/weighted_interleave/nodeN

The sysfs structure is designed as follows.

  $ tree /sys/kernel/mm/mempolicy/
  /sys/kernel/mm/mempolicy/ [1]
  └── weighted_interleave [2]
      ├── node0 [3]
      └── node1

Each file above can be explained as follows.

[1] mm/mempolicy: configuration interface for mempolicy subsystem

[2] weighted_interleave/: config interface for weighted interleave policy

[3] weighted_interleave/nodeN: weight for nodeN

Signed-off-by: Rakie Kim <rakie.kim@sk.com>
Signed-off-by: Honggyu Kim <honggyu.kim@sk.com>
Co-developed-by: Gregory Price <gregory.price@memverge.com>
Signed-off-by: Gregory Price <gregory.price@memverge.com>
Co-developed-by: Hyeongtak Ji <hyeongtak.ji@sk.com>
Signed-off-by: Hyeongtak Ji <hyeongtak.ji@sk.com>
---
 .../ABI/testing/sysfs-kernel-mm-mempolicy     |   4 +
 ...fs-kernel-mm-mempolicy-weighted-interleave |  22 +++
 mm/mempolicy.c                                | 143 ++++++++++++++++++
 3 files changed, 169 insertions(+)
 create mode 100644 Documentation/ABI/testing/sysfs-kernel-mm-mempolicy
 create mode 100644 Documentation/ABI/testing/sysfs-kernel-mm-mempolicy-weighted-interleave

diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-mempolicy b/Documentation/ABI/testing/sysfs-kernel-mm-mempolicy
new file mode 100644
index 000000000000..2dcf24f4384a
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-mempolicy
@@ -0,0 +1,4 @@
+What:		/sys/kernel/mm/mempolicy/
+Date:		December 2023
+Contact:	Linux memory management mailing list <linux-mm@kvack.org>
+Description:	Interface for Mempolicy
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-mempolicy-weighted-interleave b/Documentation/ABI/testing/sysfs-kernel-mm-mempolicy-weighted-interleave
new file mode 100644
index 000000000000..aa27fdf08c19
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-mempolicy-weighted-interleave
@@ -0,0 +1,22 @@
+What:		/sys/kernel/mm/mempolicy/weighted_interleave/
+Date:		December 2023
+Contact:	Linux memory management mailing list <linux-mm@kvack.org>
+Description:	Configuration Interface for the Weighted Interleave policy
+
+What:		/sys/kernel/mm/mempolicy/weighted_interleave/nodeN
+Date:		December 2023
+Contact:	Linux memory management mailing list <linux-mm@kvack.org>
+Description:	Weight configuration interface for nodeN
+
+		The interleave weight for a memory node (N). These weights are
+		utilized by processes which have set their mempolicy to
+		MPOL_WEIGHTED_INTERLEAVE and have opted into global weights by
+		omitting a task-local weight array.
+
+		These weights only affect new allocations, and changes at runtime
+		will not cause migrations on already allocated pages.
+
+		Writing an empty string resets the weight value to 1.
+
+		Minimum weight: 1
+		Maximum weight: 255
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 10a590ee1c89..5310021181ab 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -131,6 +131,8 @@ static struct mempolicy default_policy = {
 
 static struct mempolicy preferred_node_policy[MAX_NUMNODES];
 
+static char iw_table[MAX_NUMNODES];
+
 /**
  * numa_nearest_node - Find nearest node by state
  * @node: Node id to start the search
@@ -3067,3 +3069,144 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 		p += scnprintf(p, buffer + maxlen - p, ":%*pbl",
 			       nodemask_pr_args(&nodes));
 }
+
+struct iw_node_attr {
+	struct kobj_attribute kobj_attr;
+	int nid;
+};
+
+static ssize_t node_show(struct kobject *kobj, struct kobj_attribute *attr,
+			 char *buf)
+{
+	struct iw_node_attr *node_attr;
+
+	node_attr = container_of(attr, struct iw_node_attr, kobj_attr);
+	return sysfs_emit(buf, "%d\n", iw_table[node_attr->nid]);
+}
+
+static ssize_t node_store(struct kobject *kobj, struct kobj_attribute *attr,
+			  const char *buf, size_t count)
+{
+	struct iw_node_attr *node_attr;
+	unsigned char weight = 0;
+
+	node_attr = container_of(attr, struct iw_node_attr, kobj_attr);
+	/* If no input, set default weight to 1 */
+	if (count == 0 || sysfs_streq(buf, ""))
+		weight = 1;
+	else if (kstrtou8(buf, 0, &weight) || !weight)
+		return -EINVAL;
+
+	iw_table[node_attr->nid] = weight;
+	return count;
+}
+
+static struct iw_node_attr *node_attrs[MAX_NUMNODES];
+
+static void sysfs_wi_node_release(struct iw_node_attr *node_attr,
+				  struct kobject *parent)
+{
+	if (!node_attr)
+		return;
+	sysfs_remove_file(parent, &node_attr->kobj_attr.attr);
+	kfree(node_attr->kobj_attr.attr.name);
+	kfree(node_attr);
+}
+
+static void sysfs_mempolicy_release(struct kobject *mempolicy_kobj)
+{
+	int i;
+
+	for (i = 0; i < MAX_NUMNODES; i++)
+		sysfs_wi_node_release(node_attrs[i], mempolicy_kobj);
+	kobject_put(mempolicy_kobj);
+}
+
+static const struct kobj_type mempolicy_ktype = {
+	.sysfs_ops = &kobj_sysfs_ops,
+	.release = sysfs_mempolicy_release,
+};
+
+static int add_weight_node(int nid, struct kobject *wi_kobj)
+{
+	struct iw_node_attr *node_attr;
+	char *name;
+
+	node_attr = kzalloc(sizeof(*node_attr), GFP_KERNEL);
+	if (!node_attr)
+		return -ENOMEM;
+
+	name = kasprintf(GFP_KERNEL, "node%d", nid);
+	if (!name) {
+		kfree(node_attr);
+		return -ENOMEM;
+	}
+
+	sysfs_attr_init(&node_attr->attr);
+	node_attr->kobj_attr.attr.name = name;
+	node_attr->kobj_attr.attr.mode = 0644;
+	node_attr->kobj_attr.show = node_show;
+	node_attr->kobj_attr.store = node_store;
+	node_attr->nid = nid;
+
+	if (sysfs_create_file(wi_kobj, &node_attr->kobj_attr.attr)) {
+		kfree(node_attr->kobj_attr.attr.name);
+		kfree(node_attr);
+		pr_err("failed to add attribute to weighted_interleave\n");
+		return -ENOMEM;
+	}
+
+	node_attrs[nid] = node_attr;
+	return 0;
+}
+
+static int add_weighted_interleave_group(struct kobject *root_kobj)
+{
+	struct kobject *wi_kobj;
+	int nid, err;
+
+	wi_kobj = kzalloc(sizeof(struct kobject), GFP_KERNEL);
+	if (!wi_kobj)
+		return -ENOMEM;
+
+	err = kobject_init_and_add(wi_kobj, &mempolicy_ktype, root_kobj,
+				   "weighted_interleave");
+	if (err) {
+		kfree(wi_kobj);
+		return err;
+	}
+
+	memset(node_attrs, 0, sizeof(node_attrs));
+	for_each_node_state(nid, N_POSSIBLE) {
+		err = add_weight_node(nid, wi_kobj);
+		if (err) {
+			pr_err("failed to add sysfs [node%d]\n", nid);
+			break;
+		}
+	}
+	if (err)
+		kobject_put(wi_kobj);
+	return 0;
+}
+
+static int __init mempolicy_sysfs_init(void)
+{
+	int err;
+	struct kobject *root_kobj;
+
+	memset(&iw_table, 1, sizeof(iw_table));
+
+	root_kobj = kobject_create_and_add("mempolicy", mm_kobj);
+	if (!root_kobj) {
+		pr_err("failed to add mempolicy kobject to the system\n");
+		return -ENOMEM;
+	}
+
+	err = add_weighted_interleave_group(root_kobj);
+
+	if (err)
+		kobject_put(root_kobj);
+	return err;
+
+}
+late_initcall(mempolicy_sysfs_init);
-- 
2.39.1

Hi Gregory,

kernel test robot noticed the following build errors:

[auto build test ERROR on akpm-mm/mm-everything]
[also build test ERROR on geert-m68k/for-next geert-m68k/for-linus deller-parisc/for-next powerpc/next powerpc/fixes s390/features jcmvbkbc-xtensa/xtensa-for-next arnd-asm-generic/master linus/master tip/x86/asm v6.7-rc5 next-20231214]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Gregory-Price/mm-mempolicy-implement-the-sysfs-based-weighted_interleave-interface/20231214-064236
base:   https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-everything
patch link:    https://lore.kernel.org/r/20231213224118.1949-2-gregory.price%40memverge.com
patch subject: [PATCH v3 01/11] mm/mempolicy: implement the sysfs-based weighted_interleave interface
config: x86_64-randconfig-161-20231214 (https://download.01.org/0day-ci/archive/20231214/202312141733.PALHOosm-lkp@intel.com/config)
compiler: gcc-9 (Debian 9.3.0-22) 9.3.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20231214/202312141733.PALHOosm-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202312141733.PALHOosm-lkp@intel.com/

All errors (new ones prefixed by >>):

   In file included from include/linux/kobject.h:20,
                    from include/linux/energy_model.h:7,
                    from include/linux/device.h:16,
                    from include/linux/node.h:18,
                    from include/linux/cpu.h:17,
                    from include/linux/static_call.h:135,
                    from include/linux/tracepoint.h:22,
                    from include/trace/events/tlb.h:9,
                    from arch/x86/include/asm/mmu_context.h:10,
                    from include/linux/mmu_context.h:5,
                    from include/linux/cpuset.h:18,
                    from mm/mempolicy.c:83:
   mm/mempolicy.c: In function 'add_weight_node':
>> mm/mempolicy.c:3145:28: error: 'struct iw_node_attr' has no member named 'attr'
    3145 |  sysfs_attr_init(&node_attr->attr);
         |                            ^~
   include/linux/sysfs.h:55:3: note: in definition of macro 'sysfs_attr_init'
      55 |  (attr)->key = &__key;    \
         |   ^~~~

Kconfig warnings: (for reference only)
   WARNING: unmet direct dependencies detected for DRM_I915_DEBUG_GEM
   Depends on [n]: HAS_IOMEM [=y] && DRM_I915 [=m] && EXPERT [=y] && DRM_I915_WERROR [=n]
   Selected by [m]:
   - DRM_I915_DEBUG [=y] && HAS_IOMEM [=y] && DRM_I915 [=m] && EXPERT [=y] && !COMPILE_TEST [=n]


vim +3145 mm/mempolicy.c

  3129	
  3130	static int add_weight_node(int nid, struct kobject *wi_kobj)
  3131	{
  3132		struct iw_node_attr *node_attr;
  3133		char *name;
  3134	
  3135		node_attr = kzalloc(sizeof(*node_attr), GFP_KERNEL);
  3136		if (!node_attr)
  3137			return -ENOMEM;
  3138	
  3139		name = kasprintf(GFP_KERNEL, "node%d", nid);
  3140		if (!name) {
  3141			kfree(node_attr);
  3142			return -ENOMEM;
  3143		}
  3144	
> 3145		sysfs_attr_init(&node_attr->attr);
  3146		node_attr->kobj_attr.attr.name = name;
  3147		node_attr->kobj_attr.attr.mode = 0644;
  3148		node_attr->kobj_attr.show = node_show;
  3149		node_attr->kobj_attr.store = node_store;
  3150		node_attr->nid = nid;
  3151	
  3152		if (sysfs_create_file(wi_kobj, &node_attr->kobj_attr.attr)) {
  3153			kfree(node_attr->kobj_attr.attr.name);
  3154			kfree(node_attr);
  3155			pr_err("failed to add attribute to weighted_interleave\n");
  3156			return -ENOMEM;
  3157		}
  3158	
  3159		node_attrs[nid] = node_attr;
  3160		return 0;
  3161	}
  3162	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki