From 4d733685148c65eb6aa52aa9b248bc501a604e39 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 2 Jul 2026 17:47:48 -0400 Subject: [PATCH] cgroup/cpuset: Fix node inconsistencies between cpuset_update_tasks_nodemask() and cpuset_attach() Whenever memory node mask is changed, there are 4 places where the node mask has to be updated or used. 1) task's node mask via cpuset_change_task_nodemask() 2) memory policy binding via mpol_rebind_mm() 3) if memory migration is enabled, migrate from old_mems_allowed to the new node mask via cpuset_migrate_mm(). 4) setting old_mems_allowed These memory actions are done in cpuset_update_tasks_nodemask() and cpuset_attach(). However there are inconsistencies in what node masks are being used in these 2 functions. In cpuset_update_tasks_nodemask(), - cpuset_change_task_nodemask(): guarantee_online_mems() - mpol_rebind_mm(): mems_allowed - cpuset_migrate_mm(): guarantee_online_mems() - old_mems_allowed: guarantee_online_mems() In cpuset_attach(), - cpuset_change_task_nodemask(): guarantee_online_mems() - mpol_rebind_mm(): effective_mems - cpuset_migrate_mm(): effective_mems - old_mems_allowed: effective_mems These inconsistencies dates back to quite a long time ago and it is hard to say what should be the correct values. The guarantee_online_mems() function returns a node mask from current or an ancestor cpuset that is a subset of node_states[N_MEMORY]. Nodes in node_states[N_MEMORY] are all online, i.e. in node_states[N_ONLINE]. However, node in node_states[N_ONLINE] may not have memory. So node_states[N_MEMORY] should be a subset of node_states[N_ONLINE]. The guarantee_online_mems() function should mostly be useful for v1 where mems_allowed is the same as effective_mems. With v2, the memory nodes in effective_mems should be a subset of node_states[N_MEMORY] except when a memory hot-unplug operation is in progress and a memory node is removed from node_states[N_MEMORY] but not yet reflected in the effective_mems's as cpuset_handle_hotplug() has not been called from cpuset_track_online_nodes(). Let use the following setup for both of them and make them consistent. - cpuset_change_task_nodemask(): guarantee_online_mems() - mpol_rebind_mm(): effective_mems - cpuset_migrate_mm(): guarantee_online_mems() - old_mems_allowed: guarantee_online_mems() So for v2, it is effectively all effective_mems most of the time. For v1, mpol_rebind_mm() uses mems_allowed which may differ from what guarantee_online_mems() returns, but it conforms to what the cpuset v1 documentation says with respect to setting memory policy. Signed-off-by: Waiman Long Reviewed-by: Ridong Chen Reviewed-by: Gregory Price Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 30 ++++++++++++++++++------------ 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 7c54289edf40..c2a7a3ccc80d 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -489,7 +489,10 @@ static void guarantee_active_cpus(struct task_struct *tsk, * Return in *pmask the portion of a cpusets's mems_allowed that * are online, with memory. If none are online with memory, walk * up the cpuset hierarchy until we find one that does have some - * online mems. The top cpuset always has some mems online. + * online mems. The top cpuset always has some mems online. With v2, + * effective_mems should always contain online memory nodes except + * during the transition period where a memory node hotunplug operation + * is in progress. * * One way or another, we guarantee to return some non-empty subset * of node_states[N_MEMORY]. @@ -2633,6 +2636,14 @@ static void *cpuset_being_rebound; * Iterate through each task of @cs updating its mems_allowed to the * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. + * + * - cpuset_change_task_nodemask(): guarantee_online_mems() + * - mpol_rebind_mm(): effective_mems + * - cpuset_migrate_mm(): guarantee_online_mems() + * - old_mems_allowed: guarantee_online_mems() + * + * For v2, guarantee_online_mems() should return a node mask that is the same + * as the effective_mems of current cpuset. */ void cpuset_update_tasks_nodemask(struct cpuset *cs) { @@ -2641,7 +2652,6 @@ void cpuset_update_tasks_nodemask(struct cpuset *cs) struct task_struct *task; cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ - guarantee_online_mems(cs, &newmems); /* @@ -3159,19 +3169,16 @@ static void cpuset_attach(struct cgroup_taskset *tset) cpus_updated = !cpumask_equal(cs->effective_cpus, oldcs->effective_cpus); mems_updated = !nodes_equal(cs->effective_mems, oldcs->effective_mems); + guarantee_online_mems(cs, &cpuset_attach_nodemask_to); /* * In the default hierarchy, enabling cpuset in the child cgroups - * will trigger a number of cpuset_attach() calls with no change - * in effective cpus and mems. In that case, we can optimize out - * by skipping the task iteration and update. + * will trigger a cpuset_attach() call with no change in effective cpus + * and mems. In that case, we can optimize out by skipping the task + * iteration and update. */ - if (cpuset_v2() && !cpus_updated && !mems_updated) { - cpuset_attach_nodemask_to = cs->effective_mems; + if (cpuset_v2() && !cpus_updated && !mems_updated) goto out; - } - - guarantee_online_mems(cs, &cpuset_attach_nodemask_to); cgroup_taskset_for_each(task, css, tset) cpuset_attach_task(cs, task); @@ -3182,7 +3189,6 @@ static void cpuset_attach(struct cgroup_taskset *tset) * if there is no change in effective_mems and CS_MEMORY_MIGRATE is * not set. */ - cpuset_attach_nodemask_to = cs->effective_mems; if (!is_memory_migrate(cs) && !mems_updated) goto out; @@ -3190,7 +3196,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) struct mm_struct *mm = get_task_mm(leader); if (mm) { - mpol_rebind_mm(mm, &cpuset_attach_nodemask_to); + mpol_rebind_mm(mm, &cs->effective_mems); /* * old_mems_allowed is the same with mems_allowed