N_MEMORY_PRIVATE node access is gated by per-node capabilities and the zonelist. Isolating by cpuset offers no functionality and creates issues on rebind when a cpuset loses access to that node (in particular: it generates migrations that may not be supported).
Do not partition private nodes via cpuset.mem, instead treat them as globally accessible resources. Do not engage in silent background operations on these nodes due to cpuset.mem membership changing. The result: cpuset operations checking for node validity always allow N_MEMORY_PRIVATE nodes. On hot-unplug, we still need to rebind memory policies if the private node has left N_MEMORY_PRIVATE (i.e. no more memory). Signed-off-by: Gregory Price <[email protected]> --- kernel/cgroup/cpuset.c | 26 ++++++++++++++++++++++---- mm/memcontrol.c | 2 ++ 2 files changed, 24 insertions(+), 4 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index dfd0f827e3b92..05468f95c10bd 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -26,6 +26,7 @@ #include <linux/mempolicy.h> #include <linux/mm.h> #include <linux/memory.h> +#include <linux/node_private.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/sched/deadline.h> @@ -3867,7 +3868,8 @@ static void cpuset_handle_hotplug(void) static DECLARE_WORK(hk_sd_work, hk_sd_workfn); static cpumask_t new_cpus; static nodemask_t new_mems; - bool cpus_updated, mems_updated; + static nodemask_t prev_priv_mems; + bool cpus_updated, mems_updated, priv_shrank; bool on_dfl = is_in_v2_mode(); struct tmpmasks tmp, *ptmp = NULL; @@ -3890,6 +3892,14 @@ static void cpuset_handle_hotplug(void) !cpumask_empty(subpartitions_cpus); mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems); + /* + * Private nodes are not partitioned by cpuset, but if one leaves + * N_MEMORY_PRIVATE we still need to run mpol_rebind_* to clean up + * mempolicies that are binding them. + */ + priv_shrank = !nodes_subset(prev_priv_mems, node_states[N_MEMORY_PRIVATE]); + prev_priv_mems = node_states[N_MEMORY_PRIVATE]; + /* For v1, synchronize cpus_allowed to cpu_active_mask */ if (cpus_updated) { cpuset_force_rebuild(); @@ -3922,9 +3932,12 @@ static void cpuset_handle_hotplug(void) top_cpuset.mems_allowed = new_mems; top_cpuset.effective_mems = new_mems; spin_unlock_irq(&callback_lock); - cpuset_update_tasks_nodemask(&top_cpuset); } + /* Rebind task mempolicies if any memory node changed state */ + if (mems_updated || priv_shrank) + cpuset_update_tasks_nodemask(&top_cpuset); + mutex_unlock(&cpuset_mutex); /* if cpus or mems changed, we need to propagate to descendants */ @@ -4155,11 +4168,13 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk) * cpuset_nodemask_valid_mems_allowed - check nodemask vs. current mems_allowed * @nodemask: the nodemask to be checked * - * Are any of the nodes in the nodemask allowed in current->mems_allowed? + * Are any of the nodes in the nodemask usable? N_MEMORY nodes must be in + * current->mems_allowed, while N_MEMORY_PRIVATE nodes are always valid. */ int cpuset_nodemask_valid_mems_allowed(const nodemask_t *nodemask) { - return nodes_intersects(*nodemask, current->mems_allowed); + return nodes_intersects(*nodemask, current->mems_allowed) || + nodes_intersects(*nodemask, node_states[N_MEMORY_PRIVATE]); } /* @@ -4223,6 +4238,9 @@ bool cpuset_current_node_allowed(int node, gfp_t gfp_mask) if (in_interrupt()) return true; + /* N_MEMORY_PRIVATE nodes are not partitioned by cpusets.mems */ + if (node_is_private(node)) + return true; if (node_isset(node, current->mems_allowed)) return true; /* diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8319ad8c5c23a..f0dde52dc9e0e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6069,6 +6069,8 @@ void mem_cgroup_node_filter_allowed(struct mem_cgroup *memcg, nodemask_t *mask) * mask is acceptable. */ cpuset_nodes_allowed(memcg->css.cgroup, &allowed); + /* N_MEMORY_PRIVATE nodes are not partitioned by cpuset, include them */ + nodes_or(allowed, allowed, node_states[N_MEMORY_PRIVATE]); nodes_and(*mask, *mask, allowed); } -- 2.53.0-Meta
