[PATCH 05/22] mm/mempolicy: keep interleave and tmpfs mount policies on common memory
From: Gregory Price (Meta)
Date: Sat Nov 14 2026 - 02:10:55 EST
Use N_MEMORY_COMMON for boot mempolicy calculations and their per-node
sysfs entries (weighted interleave weights).
Restrict the node set mpol_set_nodemask() applies to set_mempolicy()
and mbind() masks to N_MEMORY_COMMON nodes.
Later when an N_MEMORY node is omitted frmo the N_MEMORY_COMMON set,
they will be stripped from mempolicy nodemasks as they're not eligible
(similar to memoryless nodes today).
All memory is common at this point, no behavior change at this point.
Signed-off-by: Gregory Price (Meta) <gourry@xxxxxxxxxx>
---
mm/mempolicy.c | 28 ++++++++++++++--------------
1 file changed, 14 insertions(+), 14 deletions(-)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index b10c098e9c2a3..662ab420fe03c 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -213,10 +213,10 @@ static void reduce_interleave_weights(unsigned int *bw, u8 *new_iw)
int nid;
/*
- * N_MEMORY can change while wi_state_lock is held. Remember the
- * nodes contributing to sum_bw so all passes use the same set.
+ * N_MEMORY_COMMON can change while wi_state_lock is held. Remember
+ * the nodes contributing to sum_bw so all passes use the same set.
*/
- for_each_node_state(nid, N_MEMORY) {
+ for_each_node_state(nid, N_MEMORY_COMMON) {
node_set(nid, nodes);
sum_bw += bw[nid];
}
@@ -439,9 +439,9 @@ static int mpol_set_nodemask(struct mempolicy *pol,
if (!pol || pol->mode == MPOL_LOCAL)
return 0;
- /* Check N_MEMORY */
+ /* Check N_MEMORY_COMMON */
nodes_and(nsc->mask1,
- cpuset_current_mems_allowed, node_states[N_MEMORY]);
+ cpuset_current_mems_allowed, node_states[N_MEMORY_COMMON]);
VM_BUG_ON(!nodes);
@@ -3400,11 +3400,11 @@ void __init numa_policy_init(void)
/*
* Set interleaving policy for system init. Interleaving is only
- * enabled across suitably sized nodes (default is >= 16MB), or
- * fall back to the largest node if they're all smaller.
+ * enabled across suitably sized common memory nodes (default is
+ * >= 16MB), or fall back to the largest node if they're all smaller.
*/
nodes_clear(interleave_nodes);
- for_each_node_state(nid, N_MEMORY) {
+ for_each_node_state(nid, N_MEMORY_COMMON) {
unsigned long total_pages = node_present_pages(nid);
/* Preserve the largest node */
@@ -3476,7 +3476,7 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
*nodelist++ = '\0';
if (nodelist_parse(nodelist, nodes))
goto out;
- if (!nodes_subset(nodes, node_states[N_MEMORY]))
+ if (!nodes_subset(nodes, node_states[N_MEMORY_COMMON]))
goto out;
} else
nodes_clear(nodes);
@@ -3508,7 +3508,7 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
* Default to online nodes with memory if no nodelist
*/
if (!nodelist)
- nodes = node_states[N_MEMORY];
+ nodes = node_states[N_MEMORY_COMMON];
break;
case MPOL_LOCAL:
/*
@@ -3903,6 +3903,9 @@ static int wi_node_notifier(struct notifier_block *nb,
switch (action) {
case NODE_ADDED_FIRST_MEMORY:
+ /* Weighted interleave spans only common memory. */
+ if (!node_state(nid, N_MEMORY_COMMON))
+ break;
err = sysfs_wi_node_add(nid);
if (err)
pr_err("failed to add sysfs for node%d during hotplug: %d\n",
@@ -3934,10 +3937,7 @@ static int __init add_weighted_interleave_group(struct kobject *mempolicy_kobj)
if (err)
goto err_put_kobj;
- for_each_online_node(nid) {
- if (!node_state(nid, N_MEMORY))
- continue;
-
+ for_each_node_state(nid, N_MEMORY_COMMON) {
err = sysfs_wi_node_add(nid);
if (err) {
pr_err("failed to add sysfs for node%d during init: %d\n",
--
2.53.1-Meta