@@ -23,3 +23,39 @@ Description: Weight configuration interface for nodeN
Writing an empty string or `0` will reset the weight to the
system default. The system default may be set by the kernel
or drivers at boot or during hotplug events.
+
+What: /sys/kernel/mm/mempolicy/weighted_interleave/weightiness
+Date: December 2024
+Contact: Linux memory management mailing list <linux-mm@kvack.org>
+Description: Weight limiting / scaling interface
+
+ "Weightiness": a measure of interleave aggression between
+ memory nodes. Higher values lead to less interleaving (255:1),
+ while lower values lead to more interleaving (1:1).
+
+ When this value is updated, all node weights are re-calculated
+ to reflect the new weightiness. These re-calculated values
+ overwrite all existing node weights, including those manually
+ set by writing to the nodeN files.
+
+ Node weight re-calculation is performed by scaling down
+ bandwidth values reported in the ACPI HMAT to the range
+ [1, weightiness]. Note that re-calculation uses only the
+ weightiness parameter and bandwidth values, and ignores all
+ current node weights.
+
+ Minimum weight: 1
+ Default value: 32
+ Maximum weight: 255
+
+ Writing an empty string will set the value to be the default
+ (32). Writing a value outside the valid range will return
+ EINVAL and will not re-trigger a weight scaling.
+
+ If there is no bandwidth data in the ACPI HMAT, then this file
+ will return ENODEV on an attempted write and perform no updates.
+ Furthermore, if there is no bandwidth information available,
+ all nodes' weights will default to 1.
+
+ Setting max_node_weight to 1 is equivalent to unweighted
+ interleave.
@@ -20,6 +20,7 @@
#include <linux/list_sort.h>
#include <linux/memregion.h>
#include <linux/memory.h>
+#include <linux/mempolicy.h>
#include <linux/mutex.h>
#include <linux/node.h>
#include <linux/sysfs.h>
@@ -7,6 +7,7 @@
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/memory.h>
+#include <linux/mempolicy.h>
#include <linux/vmstat.h>
#include <linux/notifier.h>
#include <linux/node.h>
@@ -214,6 +215,12 @@ void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord,
break;
}
}
+
+ /* When setting CPU access coordinates, update mempolicy */
+ if (access == ACCESS_COORDINATE_CPU) {
+ if (mempolicy_set_node_perf(nid, coord))
+ pr_info("failed to set node%d mempolicy attrs\n", nid);
+ }
}
EXPORT_SYMBOL_GPL(node_set_perf_attrs);
@@ -11,6 +11,7 @@
#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/spinlock.h>
+#include <linux/node.h>
#include <linux/nodemask.h>
#include <linux/pagemap.h>
#include <uapi/linux/mempolicy.h>
@@ -177,6 +178,9 @@ static inline bool mpol_is_preferred_many(struct mempolicy *pol)
extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone);
+extern int mempolicy_set_node_perf(unsigned int node,
+ struct access_coordinate *coords);
+
#else
struct mempolicy {};
@@ -109,6 +109,7 @@
#include <linux/mmu_notifier.h>
#include <linux/printk.h>
#include <linux/swapops.h>
+#include <linux/gcd.h>
#include <asm/tlbflush.h>
#include <asm/tlb.h>
@@ -145,17 +146,19 @@ enum {
};
static unsigned int mempolicy_behavior;
+static uint64_t *node_bw_table;
+
/*
- * iw_table is the sysfs-set interleave weight table, a value of 0 denotes
- * system-default value should be used. A NULL iw_table also denotes that
- * system-default values should be used. Until the system-default table
- * is implemented, the system-default is always 1.
+ * iw_table is the interleave weight table, with default values populated
+ * using ACPI-reported bandwidths (if exists) and scaled down to [1,255].
*
* iw_table is RCU protected
*/
static u8 __rcu *iw_table;
static DEFINE_MUTEX(iw_table_lock);
+static int weightiness = 32;
+
static u8 get_il_weight(int node)
{
u8 *table;
@@ -163,14 +166,97 @@ static u8 get_il_weight(int node)
rcu_read_lock();
table = rcu_dereference(iw_table);
- /* if no iw_table, use system default */
weight = table ? table[node] : 1;
- /* if value in iw_table is 0, use system default */
- weight = weight ? weight : 1;
rcu_read_unlock();
return weight;
}
+/*
+ * Convert ACPI-reported bandwidths into weighted interleave weights for
+ * informed page allocation.
+ * Call with iw_table_lock.
+ */
+static void reduce_interleave_weights(uint64_t *bw, u8 *new_iw)
+{
+ uint64_t ttl_bw = 0, ttl_iw = 0, scaling_factor = 1, iw_gcd = 1;
+ unsigned int i = 0;
+
+ /* Recalculate the bandwidth distribution given the new info */
+ for (i = 0; i < nr_node_ids; i++)
+ ttl_bw += bw[i];
+
+ /* If node is not set or has < 1% of total bw, use minimum value of 1 */
+ for (i = 0; i < nr_node_ids; i++) {
+ if (bw[i]) {
+ scaling_factor = 100 * bw[i];
+ new_iw[i] = max(scaling_factor / ttl_bw, 1);
+ } else {
+ new_iw[i] = 1;
+ }
+ ttl_iw += new_iw[i];
+ }
+
+ /*
+ * Scale each node's share of the total bandwidth from percentages
+ * to whole numbers in the range [1, weightiness]
+ */
+ for (i = 0; i < nr_node_ids; i++) {
+ scaling_factor = weightiness * new_iw[i];
+ new_iw[i] = max(scaling_factor / ttl_iw, 1);
+ if (unlikely(i == 0))
+ iw_gcd = new_iw[0];
+ iw_gcd = gcd(iw_gcd, new_iw[i]);
+ }
+
+ /* 1:2 is strictly better than 16:32. Reduce by the weights' GCD. */
+ for (i = 0; i < nr_node_ids; i++)
+ new_iw[i] /= iw_gcd;
+}
+
+int mempolicy_set_node_perf(unsigned int node, struct access_coordinate *coords)
+{
+ uint64_t *old_bw, *new_bw;
+ uint64_t bw_val;
+ u8 *old_iw, *new_iw;
+
+ /*
+ * Bandwidths above this limit causes rounding errors when reducing
+ * weights. This value is ~16 exabytes, which is unreasonable anyways.
+ */
+ bw_val = min(coords->read_bandwidth, coords->write_bandwidth);
+ if (bw_val > (U64_MAX / 10))
+ return -EINVAL;
+
+ new_bw = kcalloc(nr_node_ids, sizeof(uint64_t), GFP_KERNEL);
+ if (!new_bw)
+ return -ENOMEM;
+
+ new_iw = kcalloc(nr_node_ids, sizeof(u8), GFP_KERNEL);
+ if (!new_iw) {
+ kfree(new_bw);
+ return -ENOMEM;
+ }
+
+ mutex_lock(&iw_table_lock);
+ old_bw = node_bw_table;
+ old_iw = rcu_dereference_protected(iw_table,
+ lockdep_is_held(&iw_table_lock));
+
+ if (old_bw)
+ memcpy(new_bw, old_bw, nr_node_ids*sizeof(uint64_t));
+ new_bw[node] = bw_val;
+ node_bw_table = new_bw;
+
+ reduce_interleave_weights(new_bw, new_iw);
+ rcu_assign_pointer(iw_table, new_iw);
+
+ mutex_unlock(&iw_table_lock);
+ synchronize_rcu();
+ kfree(old_bw);
+ kfree(old_iw);
+ return 0;
+}
+
/**
* numa_nearest_node - Find nearest node by state
* @node: Node id to start the search
@@ -2014,10 +2100,7 @@ static unsigned int weighted_interleave_nid(struct mempolicy *pol, pgoff_t ilx)
table = rcu_dereference(iw_table);
/* calculate the total weight */
for_each_node_mask(nid, nodemask) {
- /* detect system default usage */
- weight = table ? table[nid] : 1;
- weight = weight ? weight : 1;
- weight_total += weight;
+ weight_total += table ? table[nid] : 1;
}
/* Calculate the node offset based on totals */
@@ -2026,7 +2109,6 @@ static unsigned int weighted_interleave_nid(struct mempolicy *pol, pgoff_t ilx)
while (target) {
/* detect system default usage */
weight = table ? table[nid] : 1;
- weight = weight ? weight : 1;
if (target < weight)
break;
target -= weight;
@@ -2409,7 +2491,7 @@ static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp,
unsigned long nr_allocated = 0;
unsigned long rounds;
unsigned long node_pages, delta;
- u8 *table, *weights, weight;
+ u8 *weights, weight;
unsigned int weight_total = 0;
unsigned long rem_pages = nr_pages;
nodemask_t nodes;
@@ -2458,16 +2540,8 @@ static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp,
if (!weights)
return total_allocated;
- rcu_read_lock();
- table = rcu_dereference(iw_table);
- if (table)
- memcpy(weights, table, nr_node_ids);
- rcu_read_unlock();
-
- /* calculate total, detect system default usage */
for_each_node_mask(node, nodes) {
- if (!weights[node])
- weights[node] = 1;
+ weights[node] = get_il_weight(node);
weight_total += weights[node];
}
@@ -3397,6 +3471,54 @@ static ssize_t node_store(struct kobject *kobj, struct kobj_attribute *attr,
static struct iw_node_attr **node_attrs;
+static ssize_t weightiness_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sysfs_emit(buf, "%d\n", weightiness);
+}
+
+static ssize_t weightiness_store(struct kobject *kobj,
+ struct kobj_attribute *attr, const char *buf, size_t count)
+{
+ uint64_t *bw;
+ u8 *old_iw, *new_iw;
+ u8 new_weightiness;
+
+ if (count == 0 || sysfs_streq(buf, ""))
+ new_weightiness = 32;
+ else if (kstrtou8(buf, 0, &new_weightiness) || new_weightiness == 0)
+ return -EINVAL;
+
+ new_iw = kzalloc(nr_node_ids, GFP_KERNEL);
+ if (!new_iw)
+ return -ENOMEM;
+
+ mutex_lock(&iw_table_lock);
+ bw = node_bw_table;
+
+ if (!bw) {
+ mutex_unlock(&iw_table_lock);
+ kfree(new_iw);
+ return -ENODEV;
+ }
+
+ weightiness = new_weightiness;
+ old_iw = rcu_dereference_protected(iw_table,
+ lockdep_is_held(&iw_table_lock));
+
+ reduce_interleave_weights(bw, new_iw);
+ rcu_assign_pointer(iw_table, new_iw);
+ mutex_unlock(&iw_table_lock);
+
+ synchronize_rcu();
+ kfree(old_iw);
+
+ return count;
+}
+
+static struct kobj_attribute wi_attr =
+ __ATTR(weightiness, 0664, weightiness_show, weightiness_store);
+
static void sysfs_wi_node_release(struct iw_node_attr *node_attr,
struct kobject *parent)
{
@@ -3413,6 +3535,7 @@ static void sysfs_wi_release(struct kobject *wi_kobj)
for (i = 0; i < nr_node_ids; i++)
sysfs_wi_node_release(node_attrs[i], wi_kobj);
+
kobject_put(wi_kobj);
}
@@ -3454,6 +3577,15 @@ static int add_weight_node(int nid, struct kobject *wi_kobj)
return 0;
}
+static struct attribute *wi_default_attrs[] = {
+ &wi_attr.attr,
+ NULL
+};
+
+static const struct attribute_group wi_attr_group = {
+ .attrs = wi_default_attrs,
+};
+
static int add_weighted_interleave_group(struct kobject *root_kobj)
{
struct kobject *wi_kobj;
@@ -3470,6 +3602,13 @@ static int add_weighted_interleave_group(struct kobject *root_kobj)
return err;
}
+ err = sysfs_create_group(wi_kobj, &wi_attr_group);
+ if (err) {
+ pr_err("failed to add sysfs [weightiness]\n");
+ kobject_put(wi_kobj);
+ return err;
+ }
+
for_each_node_state(nid, N_POSSIBLE) {
err = add_weight_node(nid, wi_kobj);
if (err) {