[PATCH v11 0/8] cgroup/cpuset: cpu partition code enhancements

-- diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 94e1e3771830..9184a09e0fc9 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -2130,10 +2130,10 @@ Cpuset Interface Files CPUs should be carefully distributed and bound to each of the individual CPUs for optimal performance. - The value shown in "cpuset.cpus.effective" of a partition root is - the CPUs that the parent partition root can dedicate to the new - partition root. They are subtracted from "cpuset.cpus.effective" - of the parent and may be different from "cpuset.cpus" + The value shown in "cpuset.cpus.effective" of a partition root + is the CPUs that the partition root can dedicate to a potential + new child partition root. The new child subtracts available + CPUs from its parent "cpuset.cpus.effective". A partition root ("root" or "isolated") can be in one of the two possible states - valid or invalid. An invalid partition @@ -2165,24 +2165,28 @@ Cpuset Interface Files 2) The parent cgroup is a valid partition root. 3) The "cpuset.cpus" is not empty and must contain at least one of the CPUs from parent's "cpuset.cpus", i.e. they overlap. - 4) The "cpuset.cpus.effective" must be a subset of "cpuset.cpus" - and cannot be empty unless there is no task associated with - this partition. + 4) The "cpuset.cpus.effective" must be a subset of "cpuset.cpus" + and cannot be empty unless there is no task associated with + this partition. External events like hotplug or changes to "cpuset.cpus" can cause a valid partition root to become invalid and vice versa. Note that a task cannot be moved to a cgroup with empty "cpuset.cpus.effective". - For a valid partition root or an invalid partition root with - the exclusivity rule enabled, changes made to "cpuset.cpus" - that violate the exclusivity rule will not be allowed. + For a valid partition root or an invalid partition root with + the exclusivity rule enabled, changes made to "cpuset.cpus" + that violate the exclusivity rule will not be allowed. A valid non-root parent partition may distribute out all its CPUs to its child partitions when there is no task associated with it. - Care must be taken to change a valid partition root to "member" - as all its child partitions, if present, will become invalid. + Care must be taken to change a valid partition root to + "member" as all its child partitions, if present, will become + invalid causing disruption to tasks running in those child + partitions. These inactivated partitions could be recovered if + their parent is switched back to a partition root with a proper + set of "cpuset.cpus". Poll and inotify events are triggered whenever the state of "cpuset.cpus.partition" changes. That includes changes caused diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 90ee0e4d8d7e..261974f5bb3c 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1283,9 +1283,12 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, * invalid to valid violates the exclusivity rule. * * The partcmd_enable and partcmd_disable commands are used by - * update_prstate(). The partcmd_update command is used by - * update_cpumasks_hier() with newmask NULL and update_cpumask() with - * newmask set. + * update_prstate(). An error code may be returned and the caller will check + * for error. + * + * The partcmd_update command is used by update_cpumasks_hier() with newmask + * NULL and update_cpumask() with newmask set. The callers won't check for + * error and so partition_root_state and prs_error will be updated directly. */ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, struct cpumask *newmask, @@ -1326,8 +1329,8 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, * A parent can be left with no CPU as long as there is no * task directly associated with the parent partition. */ - if (partition_is_populated(parent, cs) && - !cpumask_intersects(cs->cpus_allowed, parent->effective_cpus)) + if (!cpumask_intersects(cs->cpus_allowed, parent->effective_cpus) && + partition_is_populated(parent, cs)) return PERR_NOCPUS; cpumask_copy(tmp->addmask, cs->cpus_allowed); @@ -1361,9 +1364,10 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, * Make partition invalid if parent's effective_cpus could * become empty and there are tasks in the parent. */ - if (adding && partition_is_populated(parent, cs) && + if (adding && cpumask_subset(parent->effective_cpus, tmp->addmask) && - !cpumask_intersects(tmp->delmask, cpu_active_mask)) { + !cpumask_intersects(tmp->delmask, cpu_active_mask) && + partition_is_populated(parent, cs)) { part_error = PERR_NOCPUS; adding = false; deleting = cpumask_and(tmp->delmask, cs->cpus_allowed, @@ -1749,13 +1753,13 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, /* * Make sure that subparts_cpus, if not empty, is a subset of - * cpus_allowed. Clear subparts_cpus if there is an error or + * cpus_allowed. Clear subparts_cpus if partition not valid or * empty effective cpus with tasks. */ if (cs->nr_subparts_cpus) { - if (cs->prs_err || - (partition_is_populated(cs, NULL) && - cpumask_subset(trialcs->effective_cpus, cs->subparts_cpus))) { + if (!is_partition_valid(cs) || + (cpumask_subset(trialcs->effective_cpus, cs->subparts_cpus) && + partition_is_populated(cs, NULL))) { cs->nr_subparts_cpus = 0; cpumask_clear(cs->subparts_cpus); } else {