Re: [RFC PATCH 01/11] mm/mempolicy: implement the sysfs-based weighted_interleave interface

[Davidlohr Bueso]

On Wed, 06 Dec 2023, Gregory Price wrote:

> Signed-off-by: Rakie Kim <rakie.kim@xxxxxx>
> Signed-off-by: Honggyu Kim <honggyu.kim@xxxxxx>
> Co-developed-by: Gregory Price <gregory.price@xxxxxxxxxxxx>
> Signed-off-by: Gregory Price <gregory.price@xxxxxxxxxxxx>
> Co-developed-by: Hyeongtak Ji <hyeongtak.ji@xxxxxx>
> Signed-off-by: Hyeongtak Ji <hyeongtak.ji@xxxxxx>

fyi Rakie's tag needs to be last, per the From.

...

> +What:		/sys/kernel/mm/mempolicy/weighted_interleave/
> +Date:		December 2023
> +Contact:	Linux memory management mailing list <linux-mm@xxxxxxxxx>
> +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@xxxxxxxxx>
> +Description:	Configuration interface for accesses initiated from nodeN
> +
> +		The directory to configure access initiator weights for nodeN.
> +
> +		Possible numa nodes which have not been marked as a CPU node
> +		at boot will not have a nodeN directory made for them at boot.

This could be better rephrased without the negation. ie:

"Only numa nodes with CPUs (compute) will have a nodeN directory."

> +		Hotplug for CPU nodes is not supported.

Can this even happen? Hot-adding a previously offlined CPU won't change/add a
new numa node. So just rm the line altogether?

> +
> +What:		/sys/kernel/mm/mempolicy/weighted_interleave/nodeN/nodeM
> +		/sys/kernel/mm/mempolicy/weighted_interleave/nodeN/nodeM/weight
> +Date:		December 2023
> +Contact:	Linux memory management mailing list <linux-mm@xxxxxxxxx>
> +Description:	Configuration interface for target nodes accessed from nodeNN
> +
> +		The interleave weight for a memory node (M) from initiating
> +		node (N). These weights are utilized by processes which have set
> +		the 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.
> +
> +		If the weight of 0 is desired, the appropriate way to do this is
> +		by removing the node from the weighted interleave nodemask.
> +
> +		Minimum weight: 1
> +		Maximum weight: 255
> diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> index 10a590ee1c89..ce332b5e7a03 100644
> --- a/mm/mempolicy.c
> +++ b/mm/mempolicy.c
> @@ -131,6 +131,11 @@ static struct mempolicy default_policy = {
>
> static struct mempolicy preferred_node_policy[MAX_NUMNODES];
>
> +struct interleave_weight_table {
> +	unsigned char weights[MAX_NUMNODES];
> +};
> +static struct interleave_weight_table *iw_table;
> +
> /**
>  * numa_nearest_node - Find nearest node by state
>  * @node: Node id to start the search
> @@ -3067,3 +3072,224 @@ 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_info {
> +	struct kobject kobj;
> +	int src;
> +	int dst;
> +};
> +
> +static ssize_t node_weight_show(struct kobject *kobj,
> +				struct kobj_attribute *attr, char *buf)
> +{
> +	struct iw_node_info *node_info = container_of(kobj, struct iw_node_info,
> +						      kobj);
> +	return sysfs_emit(buf, "%d\n",
> +			  iw_table[node_info->src].weights[node_info->dst]);
> +}
> +
> +static ssize_t node_weight_store(struct kobject *kobj,
> +				 struct kobj_attribute *attr,
> +				 const char *buf, size_t count)
> +{
> +	unsigned char weight = 0;
> +	struct iw_node_info *node_info = NULL;
> +
> +	node_info = container_of(kobj, struct iw_node_info, kobj);
> +
> +	if (kstrtou8(buf, 0, &weight) || !weight)
> +		return -EINVAL;
> +
> +	iw_table[node_info->src].weights[node_info->dst] = weight;
> +
> +	return count;
> +}

iw_table will need some (basic) form of serialization.

...

> +static int __init mempolicy_sysfs_init(void)
> +{
> +	int err, nid;
> +	int cpunodes = 0;
> +	struct kobject *root_kobj;
> +
> +	for_each_node_state(nid, N_CPU)
> +		cpunodes += 1;
> +	iw_table = kmalloc_array(cpunodes, sizeof(*iw_table), GFP_KERNEL);
> +	if (!iw_table) {
> +		pr_err("failed to create interleave weight table\n");
> +		err = -ENOMEM;
> +		goto fail_obj;

No ref here yet, just return -ENOMEM.

> +	}
> +	memset(iw_table, 1, cpunodes * sizeof(*iw_table));
> +
> +	root_kobj = kzalloc(sizeof(struct kobject), GFP_KERNEL);
> +	if (!root_kobj)
> +		return -ENOMEM;
> +
> +	kobject_init(root_kobj, &mempolicy_kobj_ktype);
> +	err = kobject_add(root_kobj, mm_kobj, "mempolicy");
> +	if (err) {
> +		pr_err("failed to add kobject to the system\n");
> +		goto fail_obj;
> +	}
> +
> +	err = sysfs_create_group(root_kobj, &mempolicy_attr_group);
> +	if (err) {
> +		pr_err("failed to register mempolicy group\n");
> +		goto fail_obj;
> +	}
> +
> +	err = add_weighted_interleave_group(root_kobj);
> +fail_obj:
> +	if (err)
> +		kobject_put(root_kobj);
> +	return err;
> +
> +}
> +late_initcall(mempolicy_sysfs_init);
> --
> 2.39.1