v11: - Fix incorrect spacing in patch 7 and include documentation suggestions by Michal. - Move partition_is_populated() check to the last one in list of conditions to be checked.
v10: - Relax constraints for changes made to "cpuset.cpus" and "cpuset.cpus.partition" as suggested. Now almost all changes are allowed. - Add patch 1 to signal that we may need to do additional work in the future to relax the constraint that tasks' cpumask may need some adjustment if child partitions are present. - Add patch 2 for miscellaneous cleanups.
This patchset include the following enhancements to the cpuset v2 partition code. 1) Allow partitions that have no task to have empty effective cpus. 2) Relax the constraints on what changes are allowed in cpuset.cpus and cpuset.cpus.partition. However, the partition remain invalid until the constraints of a valid partition root is satisfied. 3) Add a new "isolated" partition type for partitions with no load balancing which is available in v1 but not yet in v2. 4) Allow the reading of cpuset.cpus.partition to include a reason string as to why the partition remain invalid.
In addition, the cgroup-v2.rst documentation file is updated and a self test is added to verify the correctness the partition code.
The code diff from v10 is listed below.
Waiman Long (8): cgroup/cpuset: Add top_cpuset check in update_tasks_cpumask() cgroup/cpuset: Miscellaneous cleanups & add helper functions cgroup/cpuset: Allow no-task partition to have empty cpuset.cpus.effective cgroup/cpuset: Relax constraints to partition & cpus changes cgroup/cpuset: Add a new isolated cpus.partition type cgroup/cpuset: Show invalid partition reason string cgroup/cpuset: Update description of cpuset.cpus.partition in cgroup-v2.rst kselftest/cgroup: Add cpuset v2 partition root state test
Documentation/admin-guide/cgroup-v2.rst | 149 ++-- kernel/cgroup/cpuset.c | 718 +++++++++++------- tools/testing/selftests/cgroup/Makefile | 5 +- .../selftests/cgroup/test_cpuset_prs.sh | 674 ++++++++++++++++ tools/testing/selftests/cgroup/wait_inotify.c | 87 +++ 5 files changed, 1304 insertions(+), 329 deletions(-) create mode 100755 tools/testing/selftests/cgroup/test_cpuset_prs.sh create mode 100644 tools/testing/selftests/cgroup/wait_inotify.c
Right now, update_tasks_cpumask() is not supposed to be called with top cpuset. With cpuset partition that takes CPUs away from the top cpuset, we may want to consider adjusting the cpu_allows mask of the tasks in the top cpuset as well. However, we need more investigation to figure out a way to do that without breaking non-cgroup aware applications in the top cpuset. So move the top_cpuset check into update_tasks_cpumask() and add a comment about possible future work.
Signed-off-by: Waiman Long longman@redhat.com --- kernel/cgroup/cpuset.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 9390bfd9f1cd..d90f33b068a3 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1128,6 +1128,14 @@ static void update_tasks_cpumask(struct cpuset *cs) struct css_task_iter it; struct task_struct *task;
+ /* + * TODO: With cpuset partition that takes CPUs away from the top + * cpuset, we may want to properly adjust the cpus_allowed mask of + * tasks in the top cpuset as well. + */ + if (cs == &top_cpuset) + return; + css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) set_cpus_allowed_ptr(task, cs->effective_cpus); @@ -2092,12 +2100,7 @@ static int update_prstate(struct cpuset *cs, int new_prs) update_flag(CS_CPU_EXCLUSIVE, cs, 0); }
- /* - * Update cpumask of parent's tasks except when it is the top - * cpuset as some system daemons cannot be mapped to other CPUs. - */ - if (parent != &top_cpuset) - update_tasks_cpumask(parent); + update_tasks_cpumask(parent);
if (parent->child_ecpus_count) update_sibling_cpumasks(parent, cs, &tmpmask);
The partition root state (PRS) macro names do not currently match the external names. Change them to match the external names and add helper functions to read or change the state.
Shorten the cpuset argument of update_parent_subparts_cpumask() to cs to match other cpuset functions.
Remove the new_prs argument from notify_partition_change() as the cs->partition_root_state has already been set to new_prs before it is called.
There is no functional change.
Signed-off-by: Waiman Long longman@redhat.com --- kernel/cgroup/cpuset.c | 165 +++++++++++++++++++++-------------------- 1 file changed, 86 insertions(+), 79 deletions(-)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index d90f33b068a3..d156a39d7a08 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -175,20 +175,18 @@ struct cpuset { /* * Partition root states: * - * 0 - not a partition root - * + * 0 - member (not a partition root) * 1 - partition root - * * -1 - invalid partition root - * None of the cpus in cpus_allowed can be put into the parent's - * subparts_cpus. In this case, the cpuset is not a real partition - * root anymore. However, the CPU_EXCLUSIVE bit will still be set - * and the cpuset can be restored back to a partition root if the - * parent cpuset can give more CPUs back to this child cpuset. */ -#define PRS_DISABLED 0 -#define PRS_ENABLED 1 -#define PRS_ERROR -1 +#define PRS_MEMBER 0 +#define PRS_ROOT 1 +#define PRS_INVALID_ROOT -1 + +static inline bool is_prs_invalid(int prs_state) +{ + return prs_state < 0; +}
/* * Temporary cpumasks for working with partitions that are passed among @@ -268,25 +266,35 @@ static inline int is_spread_slab(const struct cpuset *cs) return test_bit(CS_SPREAD_SLAB, &cs->flags); }
-static inline int is_partition_root(const struct cpuset *cs) +static inline int is_partition_valid(const struct cpuset *cs) { return cs->partition_root_state > 0; }
+static inline int is_partition_invalid(const struct cpuset *cs) +{ + return cs->partition_root_state < 0; +} + +static inline void set_partition_invalid(struct cpuset *cs) +{ + cs->partition_root_state = PRS_INVALID_ROOT; +} + /* * Send notification event of whenever partition_root_state changes. */ -static inline void notify_partition_change(struct cpuset *cs, - int old_prs, int new_prs) +static inline void notify_partition_change(struct cpuset *cs, int old_prs) { - if (old_prs != new_prs) - cgroup_file_notify(&cs->partition_file); + if (old_prs == cs->partition_root_state) + return; + cgroup_file_notify(&cs->partition_file); }
static struct cpuset top_cpuset = { .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), - .partition_root_state = PRS_ENABLED, + .partition_root_state = PRS_ROOT, };
/** @@ -875,7 +883,7 @@ static int generate_sched_domains(cpumask_var_t **domains, csa[csn++] = cp;
/* skip @cp's subtree if not a partition root */ - if (!is_partition_root(cp)) + if (!is_partition_valid(cp)) pos_css = css_rightmost_descendant(pos_css); } rcu_read_unlock(); @@ -1081,7 +1089,7 @@ static void rebuild_sched_domains_locked(void) if (top_cpuset.nr_subparts_cpus) { rcu_read_lock(); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { - if (!is_partition_root(cs)) { + if (!is_partition_valid(cs)) { pos_css = css_rightmost_descendant(pos_css); continue; } @@ -1215,11 +1223,11 @@ enum subparts_cmd { * cpumask changes that violates the cpu exclusivity rule will not be * permitted when checked by validate_change(). */ -static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, +static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, struct cpumask *newmask, struct tmpmasks *tmp) { - struct cpuset *parent = parent_cs(cpuset); + struct cpuset *parent = parent_cs(cs); int adding; /* Moving cpus from effective_cpus to subparts_cpus */ int deleting; /* Moving cpus from subparts_cpus to effective_cpus */ int old_prs, new_prs; @@ -1232,16 +1240,16 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, * The new cpumask, if present, or the current cpus_allowed must * not be empty. */ - if (!is_partition_root(parent) || + if (!is_partition_valid(parent) || (newmask && cpumask_empty(newmask)) || - (!newmask && cpumask_empty(cpuset->cpus_allowed))) + (!newmask && cpumask_empty(cs->cpus_allowed))) return -EINVAL;
/* * Enabling/disabling partition root is not allowed if there are * online children. */ - if ((cmd != partcmd_update) && css_has_online_children(&cpuset->css)) + if ((cmd != partcmd_update) && css_has_online_children(&cs->css)) return -EBUSY;
/* @@ -1250,20 +1258,20 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, * CPU will be left after that. */ if ((cmd == partcmd_enable) && - (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) || - cpumask_equal(cpuset->cpus_allowed, parent->effective_cpus))) + (!cpumask_subset(cs->cpus_allowed, parent->effective_cpus) || + cpumask_equal(cs->cpus_allowed, parent->effective_cpus))) return -EINVAL;
/* * A cpumask update cannot make parent's effective_cpus become empty. */ adding = deleting = false; - old_prs = new_prs = cpuset->partition_root_state; + old_prs = new_prs = cs->partition_root_state; if (cmd == partcmd_enable) { - cpumask_copy(tmp->addmask, cpuset->cpus_allowed); + cpumask_copy(tmp->addmask, cs->cpus_allowed); adding = true; } else if (cmd == partcmd_disable) { - deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed, + deleting = cpumask_and(tmp->delmask, cs->cpus_allowed, parent->subparts_cpus); } else if (newmask) { /* @@ -1273,7 +1281,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, * addmask = newmask & parent->effective_cpus * & ~parent->subparts_cpus */ - cpumask_andnot(tmp->delmask, cpuset->cpus_allowed, newmask); + cpumask_andnot(tmp->delmask, cs->cpus_allowed, newmask); deleting = cpumask_and(tmp->delmask, tmp->delmask, parent->subparts_cpus);
@@ -1307,44 +1315,44 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, * pre-shrunk in case there is a change in the cpu list. * So no deletion is needed. */ - adding = cpumask_and(tmp->addmask, cpuset->cpus_allowed, + adding = cpumask_and(tmp->addmask, cs->cpus_allowed, parent->effective_cpus); part_error = cpumask_equal(tmp->addmask, parent->effective_cpus); }
if (cmd == partcmd_update) { - int prev_prs = cpuset->partition_root_state; + int prev_prs = cs->partition_root_state;
/* - * Check for possible transition between PRS_ENABLED - * and PRS_ERROR. + * Check for possible transition between PRS_ROOT + * and PRS_INVALID_ROOT. */ - switch (cpuset->partition_root_state) { - case PRS_ENABLED: + switch (cs->partition_root_state) { + case PRS_ROOT: if (part_error) - new_prs = PRS_ERROR; + new_prs = PRS_INVALID_ROOT; break; - case PRS_ERROR: + case PRS_INVALID_ROOT: if (!part_error) - new_prs = PRS_ENABLED; + new_prs = PRS_ROOT; break; } /* * Set part_error if previously in invalid state. */ - part_error = (prev_prs == PRS_ERROR); + part_error = is_prs_invalid(prev_prs); }
- if (!part_error && (new_prs == PRS_ERROR)) + if (!part_error && is_prs_invalid(new_prs)) return 0; /* Nothing need to be done */
- if (new_prs == PRS_ERROR) { + if (is_prs_invalid(new_prs)) { /* * Remove all its cpus from parent's subparts_cpus. */ adding = false; - deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed, + deleting = cpumask_and(tmp->delmask, cs->cpus_allowed, parent->subparts_cpus); }
@@ -1377,10 +1385,10 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus);
if (old_prs != new_prs) - cpuset->partition_root_state = new_prs; + cs->partition_root_state = new_prs;
spin_unlock_irq(&callback_lock); - notify_partition_change(cpuset, old_prs, new_prs); + notify_partition_change(cs, old_prs);
return cmd == partcmd_update; } @@ -1445,15 +1453,14 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) old_prs = new_prs = cp->partition_root_state; if ((cp != cs) && old_prs) { switch (parent->partition_root_state) { - case PRS_DISABLED: + case PRS_MEMBER: /* * If parent is not a partition root or an * invalid partition root, clear its state * and its CS_CPU_EXCLUSIVE flag. */ - WARN_ON_ONCE(cp->partition_root_state - != PRS_ERROR); - new_prs = PRS_DISABLED; + WARN_ON_ONCE(!is_partition_invalid(cp)); + new_prs = PRS_MEMBER;
/* * clear_bit() is an atomic operation and @@ -1465,16 +1472,16 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) clear_bit(CS_CPU_EXCLUSIVE, &cp->flags); break;
- case PRS_ENABLED: + case PRS_ROOT: if (update_parent_subparts_cpumask(cp, partcmd_update, NULL, tmp)) update_tasks_cpumask(parent); break;
- case PRS_ERROR: + case PRS_INVALID_ROOT: /* * When parent is invalid, it has to be too. */ - new_prs = PRS_ERROR; + new_prs = PRS_INVALID_ROOT; break; } } @@ -1486,7 +1493,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) spin_lock_irq(&callback_lock);
cpumask_copy(cp->effective_cpus, tmp->new_cpus); - if (cp->nr_subparts_cpus && (new_prs != PRS_ENABLED)) { + if (cp->nr_subparts_cpus && !is_partition_valid(cp)) { cp->nr_subparts_cpus = 0; cpumask_clear(cp->subparts_cpus); } else if (cp->nr_subparts_cpus) { @@ -1518,7 +1525,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) cp->partition_root_state = new_prs;
spin_unlock_irq(&callback_lock); - notify_partition_change(cp, old_prs, new_prs); + notify_partition_change(cp, old_prs);
WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); @@ -1534,7 +1541,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) if (!cpumask_empty(cp->cpus_allowed) && is_sched_load_balance(cp) && (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || - is_partition_root(cp))) + is_partition_valid(cp))) need_rebuild_sched_domains = true;
rcu_read_lock(); @@ -2034,10 +2041,11 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, return err; }
-/* +/** * update_prstate - update partition_root_state - * cs: the cpuset to update - * new_prs: new partition root state + * @cs: the cpuset to update + * @new_prs: new partition root state + * Return: 0 if successful, < 0 if error * * Call with cpuset_rwsem held. */ @@ -2054,7 +2062,7 @@ static int update_prstate(struct cpuset *cs, int new_prs) * Cannot force a partial or invalid partition root to a full * partition root. */ - if (new_prs && (old_prs == PRS_ERROR)) + if (new_prs && is_prs_invalid(old_prs)) return -EINVAL;
if (alloc_cpumasks(NULL, &tmpmask)) @@ -2085,7 +2093,7 @@ static int update_prstate(struct cpuset *cs, int new_prs) * Turning off partition root will clear the * CS_CPU_EXCLUSIVE bit. */ - if (old_prs == PRS_ERROR) { + if (is_prs_invalid(old_prs)) { update_flag(CS_CPU_EXCLUSIVE, cs, 0); err = 0; goto out; @@ -2111,7 +2119,7 @@ static int update_prstate(struct cpuset *cs, int new_prs) spin_lock_irq(&callback_lock); cs->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); - notify_partition_change(cs, old_prs, new_prs); + notify_partition_change(cs, old_prs); }
free_cpumasks(NULL, &tmpmask); @@ -2604,13 +2612,13 @@ static int sched_partition_show(struct seq_file *seq, void *v) struct cpuset *cs = css_cs(seq_css(seq));
switch (cs->partition_root_state) { - case PRS_ENABLED: + case PRS_ROOT: seq_puts(seq, "root\n"); break; - case PRS_DISABLED: + case PRS_MEMBER: seq_puts(seq, "member\n"); break; - case PRS_ERROR: + case PRS_INVALID_ROOT: seq_puts(seq, "root invalid\n"); break; } @@ -2630,9 +2638,9 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, * Convert "root" to ENABLED, and convert "member" to DISABLED. */ if (!strcmp(buf, "root")) - val = PRS_ENABLED; + val = PRS_ROOT; else if (!strcmp(buf, "member")) - val = PRS_DISABLED; + val = PRS_MEMBER; else return -EINVAL;
@@ -2931,7 +2939,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) cpus_read_lock(); percpu_down_write(&cpuset_rwsem);
- if (is_partition_root(cs)) + if (is_partition_valid(cs)) update_prstate(cs, 0);
if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && @@ -3176,11 +3184,11 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
/* * In the unlikely event that a partition root has empty - * effective_cpus or its parent becomes erroneous, we have to - * transition it to the erroneous state. + * effective_cpus or its parent becomes invalid, we have to + * transition it to the invalid state. */ - if (is_partition_root(cs) && (cpumask_empty(&new_cpus) || - (parent->partition_root_state == PRS_ERROR))) { + if (is_partition_valid(cs) && (cpumask_empty(&new_cpus) || + is_partition_invalid(parent))) { if (cs->nr_subparts_cpus) { spin_lock_irq(&callback_lock); cs->nr_subparts_cpus = 0; @@ -3195,30 +3203,29 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) * the current partition and let the child partitions * fight for available CPUs. */ - if ((parent->partition_root_state == PRS_ERROR) || + if (is_partition_invalid(parent) || cpumask_empty(&new_cpus)) { int old_prs;
update_parent_subparts_cpumask(cs, partcmd_disable, NULL, tmp); old_prs = cs->partition_root_state; - if (old_prs != PRS_ERROR) { + if (!is_prs_invalid(old_prs)) { spin_lock_irq(&callback_lock); - cs->partition_root_state = PRS_ERROR; + set_partition_invalid(cs); spin_unlock_irq(&callback_lock); - notify_partition_change(cs, old_prs, PRS_ERROR); + notify_partition_change(cs, old_prs); } } cpuset_force_rebuild(); }
/* - * On the other hand, an erroneous partition root may be transitioned + * On the other hand, an invalid partition root may be transitioned * back to a regular one or a partition root with no CPU allocated - * from the parent may change to erroneous. + * from the parent may change to invalid. */ - if (is_partition_root(parent) && - ((cs->partition_root_state == PRS_ERROR) || + if (is_partition_valid(parent) && (is_partition_invalid(cs) || !cpumask_intersects(&new_cpus, parent->subparts_cpus)) && update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp)) cpuset_force_rebuild();
Currently, a partition root cannot have empty "cpuset.cpus.effective". As a result, a parent partition root cannot distribute out all its CPUs to child partitions with no CPUs left. However in most cases, there shouldn't be any tasks associated with intermediate nodes of the default hierarchy. So the current rule is too restrictive and can waste valuable CPU resource.
To address this issue, we are now allowing a partition to have empty "cpuset.cpus.effective" as long as it has no task. Therefore, a parent partition with no task can now have all its CPUs distributed out to its child partitions. The top cpuset always have some house-keeping tasks running and so its list of effective cpu can't be empty.
Once a partition with empty "cpuset.cpus.effective" is formed, no new task can be moved into it until "cpuset.cpus.effective" becomes non-empty.
Signed-off-by: Waiman Long longman@redhat.com --- kernel/cgroup/cpuset.c | 112 +++++++++++++++++++++++++++++++---------- 1 file changed, 85 insertions(+), 27 deletions(-)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index d156a39d7a08..6c65bcf278cb 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -412,6 +412,41 @@ static inline bool is_in_v2_mode(void) (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE); }
+/** + * partition_is_populated - check if partition has tasks + * @cs: partition root to be checked + * @excluded_child: a child cpuset to be excluded in task checking + * Return: true if there are tasks, false otherwise + * + * It is assumed that @cs is a valid partition root. @excluded_child should + * be non-NULL when this cpuset is going to become a partition itself. + */ +static inline bool partition_is_populated(struct cpuset *cs, + struct cpuset *excluded_child) +{ + struct cgroup_subsys_state *css; + struct cpuset *child; + + if (cs->css.cgroup->nr_populated_csets) + return true; + if (!excluded_child && !cs->nr_subparts_cpus) + return cgroup_is_populated(cs->css.cgroup); + + rcu_read_lock(); + cpuset_for_each_child(child, css, cs) { + if (child == excluded_child) + continue; + if (is_partition_valid(child)) + continue; + if (cgroup_is_populated(child->css.cgroup)) { + rcu_read_unlock(); + return true; + } + } + rcu_read_unlock(); + return false; +} + /* * Return in pmask the portion of a task's cpusets's cpus_allowed that * are online and are capable of running the task. If none are found, @@ -1252,22 +1287,25 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, if ((cmd != partcmd_update) && css_has_online_children(&cs->css)) return -EBUSY;
- /* - * Enabling partition root is not allowed if not all the CPUs - * can be granted from parent's effective_cpus or at least one - * CPU will be left after that. - */ - if ((cmd == partcmd_enable) && - (!cpumask_subset(cs->cpus_allowed, parent->effective_cpus) || - cpumask_equal(cs->cpus_allowed, parent->effective_cpus))) - return -EINVAL; - - /* - * A cpumask update cannot make parent's effective_cpus become empty. - */ adding = deleting = false; old_prs = new_prs = cs->partition_root_state; if (cmd == partcmd_enable) { + /* + * Enabling partition root is not allowed if not all the CPUs + * can be granted from parent's effective_cpus. + */ + if (!cpumask_subset(cs->cpus_allowed, parent->effective_cpus)) + return -EINVAL; + + /* + * A parent can be left with no CPU as long as there is no + * task directly associated with the parent partition. For + * such a parent, no new task can be moved into it. + */ + if (cpumask_equal(cs->cpus_allowed, parent->effective_cpus) && + partition_is_populated(parent, cs)) + return -EINVAL; + cpumask_copy(tmp->addmask, cs->cpus_allowed); adding = true; } else if (cmd == partcmd_disable) { @@ -1289,10 +1327,12 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, adding = cpumask_andnot(tmp->addmask, tmp->addmask, parent->subparts_cpus); /* - * Return error if the new effective_cpus could become empty. + * Return error if the new effective_cpus could become empty + * and there are tasks in the parent. */ if (adding && - cpumask_equal(parent->effective_cpus, tmp->addmask)) { + cpumask_equal(parent->effective_cpus, tmp->addmask) && + partition_is_populated(parent, cs)) { if (!deleting) return -EINVAL; /* @@ -1317,8 +1357,8 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, */ adding = cpumask_and(tmp->addmask, cs->cpus_allowed, parent->effective_cpus); - part_error = cpumask_equal(tmp->addmask, - parent->effective_cpus); + part_error = cpumask_equal(tmp->addmask, parent->effective_cpus) && + partition_is_populated(parent, cs); }
if (cmd == partcmd_update) { @@ -1420,9 +1460,15 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
/* * If it becomes empty, inherit the effective mask of the - * parent, which is guaranteed to have some CPUs. + * parent, which is guaranteed to have some CPUs unless + * it is a partition root that has explicitly distributed + * out all its CPUs. */ if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) { + if (is_partition_valid(cp) && + cpumask_equal(cp->cpus_allowed, cp->subparts_cpus)) + goto update_parent_subparts; + cpumask_copy(tmp->new_cpus, parent->effective_cpus); if (!cp->use_parent_ecpus) { cp->use_parent_ecpus = true; @@ -1444,6 +1490,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) continue; }
+update_parent_subparts: /* * update_parent_subparts_cpumask() should have been called * for cs already in update_cpumask(). We should also call @@ -2249,6 +2296,13 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock;
+ /* + * On default hierarchy, task cannot be moved to a cpuset with empty + * effective cpus. + */ + if (is_in_v2_mode() && cpumask_empty(cs->effective_cpus)) + goto out_unlock; + cgroup_taskset_for_each(task, css, tset) { ret = task_can_attach(task, cs->cpus_allowed); if (ret) @@ -3115,7 +3169,8 @@ hotplug_update_tasks(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { - if (cpumask_empty(new_cpus)) + /* A partition root is allowed to have empty effective cpus */ + if (cpumask_empty(new_cpus) && !is_partition_valid(cs)) cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus); if (nodes_empty(*new_mems)) *new_mems = parent_cs(cs)->effective_mems; @@ -3184,10 +3239,11 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
/* * In the unlikely event that a partition root has empty - * effective_cpus or its parent becomes invalid, we have to - * transition it to the invalid state. + * effective_cpus with tasks or its parent becomes invalid, we + * have to transition it to the invalid state. */ - if (is_partition_valid(cs) && (cpumask_empty(&new_cpus) || + if (is_partition_valid(cs) && + ((cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)) || is_partition_invalid(parent))) { if (cs->nr_subparts_cpus) { spin_lock_irq(&callback_lock); @@ -3198,13 +3254,15 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) }
/* - * If the effective_cpus is empty because the child - * partitions take away all the CPUs, we can keep - * the current partition and let the child partitions - * fight for available CPUs. + * Force the partition to become invalid if either one of + * the following conditions hold: + * 1) empty effective cpus but not valid empty partition. + * 2) parent is invalid or doesn't grant any cpus to child + * partitions. */ if (is_partition_invalid(parent) || - cpumask_empty(&new_cpus)) { + (cpumask_empty(&new_cpus) && + partition_is_populated(cs, NULL))) { int old_prs;
update_parent_subparts_cpumask(cs, partcmd_disable,
Hello,
Sorry about the long delay.
On Tue, May 10, 2022 at 11:34:08AM -0400, Waiman Long wrote:
Once a partition with empty "cpuset.cpus.effective" is formed, no new task can be moved into it until "cpuset.cpus.effective" becomes non-empty.
This is always true due to no-tasks-in-intermediate-cgroups requirement, right?
Thanks.
On Sun, Jun 12, 2022 at 07:40:25AM -1000, Tejun Heo wrote:
Hello,
Sorry about the long delay.
On Tue, May 10, 2022 at 11:34:08AM -0400, Waiman Long wrote:
Once a partition with empty "cpuset.cpus.effective" is formed, no new task can be moved into it until "cpuset.cpus.effective" becomes non-empty.
This is always true due to no-tasks-in-intermediate-cgroups requirement, right?
or rather, I should have asked, why does this need an explicit check?
Thanks.
On 6/12/22 13:41, Tejun Heo wrote:
On Sun, Jun 12, 2022 at 07:40:25AM -1000, Tejun Heo wrote:
Hello,
Sorry about the long delay.
On Tue, May 10, 2022 at 11:34:08AM -0400, Waiman Long wrote:
Once a partition with empty "cpuset.cpus.effective" is formed, no new task can be moved into it until "cpuset.cpus.effective" becomes non-empty.
This is always true due to no-tasks-in-intermediate-cgroups requirement, right?
or rather, I should have asked, why does this need an explicit check?
Without this patch, cpus.effective will never be empty. It just falls back to its parent if it becomes empty. Now with an empty cpus.effective, I am afraid that if a task is somehow moved to such a cpuset, something bad may happen. So I add this check as a safeguard.
Cheers, Longman
On Sun, Jun 12, 2022 at 10:53:53PM -0400, Waiman Long wrote:
Without this patch, cpus.effective will never be empty. It just falls back to its parent if it becomes empty. Now with an empty cpus.effective, I am
Yeah, that part is fine.
afraid that if a task is somehow moved to such a cpuset, something bad may happen. So I add this check as a safeguard.
But how would that happen? A lot of other things would break too if that were to happen.
Thanks.
On 6/12/22 22:55, Tejun Heo wrote:
On Sun, Jun 12, 2022 at 10:53:53PM -0400, Waiman Long wrote:
Without this patch, cpus.effective will never be empty. It just falls back to its parent if it becomes empty. Now with an empty cpus.effective, I am
Yeah, that part is fine.
afraid that if a task is somehow moved to such a cpuset, something bad may happen. So I add this check as a safeguard.
But how would that happen? A lot of other things would break too if that were to happen.
I will perform further check to see if this check is necessary.
Thanks, Longman
On Sun, Jun 12, 2022 at 04:55:13PM -1000, Tejun Heo tj@kernel.org wrote:
But how would that happen? A lot of other things would break too if that were to happen.
cpuset is a threaded controller where the internal-node-constraint does not hold. So the additional condition for cpuset migrations is IMO warranted (and needed if there's no "fall up").
Michal
On 6/13/22 10:02, Michal Koutný wrote:
On Sun, Jun 12, 2022 at 04:55:13PM -1000, Tejun Heo tj@kernel.org wrote:
But how would that happen? A lot of other things would break too if that were to happen.
cpuset is a threaded controller where the internal-node-constraint does not hold. So the additional condition for cpuset migrations is IMO warranted (and needed if there's no "fall up").
Yes, you are right. cpuset is threaded and so it may have tasks even if it is not the leaf node.
Thanks, Longman
Hello,
On Mon, Jun 13, 2022 at 12:47:37PM -0400, Waiman Long wrote:
On 6/13/22 10:02, Michal Koutný wrote:
On Sun, Jun 12, 2022 at 04:55:13PM -1000, Tejun Heo tj@kernel.org wrote:
But how would that happen? A lot of other things would break too if that were to happen.
cpuset is a threaded controller where the internal-node-constraint does not hold. So the additional condition for cpuset migrations is IMO warranted (and needed if there's no "fall up").
Yes, you are right. cpuset is threaded and so it may have tasks even if it is not the leaf node.
And we had this same exchange the last time. Can you please add a comment? We might also already have had this exchange before too but is it necessary to allow threaded cgroups to be isolated roots? The interaction between being threaded and isolated is cleaner at that layer as it's interactions between two explicit mode changes.
Thanks.
On 6/12/22 13:40, Tejun Heo wrote:
Hello,
Sorry about the long delay.
On Tue, May 10, 2022 at 11:34:08AM -0400, Waiman Long wrote:
Once a partition with empty "cpuset.cpus.effective" is formed, no new task can be moved into it until "cpuset.cpus.effective" becomes non-empty.
This is always true due to no-tasks-in-intermediate-cgroups requirement, right?
I seems to remember there are corner cases where a task can be moved to an intermediate cgroup under circumstances. I need to dig further to find out what it is.
Cheers, Longman
Currently, enabling a partition root is only allowed if all the constraints of a valid partition are satisfied. Even changes to "cpuset.cpus" may not be allowed in some cases. Moreover, there are limits to changes made to a parent cpuset if it is a valid partition root. This is contrary to the general cgroup v2 philosophy.
This patch relaxes the constraints of changing the state of "cpuset.cpus" and "cpuset.cpus.partition". Now all valid changes ("member" or "root") to "cpuset.cpus.partition" are allowed even if there are child cpusets underneath it.
Trying to make a cpuset a partition root, however, will cause its state to become invalid if the following constraints of a valid partition root are not satisfied.
1) The "cpuset.cpus" is non-empty and exclusive. 2) The parent cpuset is a valid partition root. 3) The "cpuset.cpus" overlaps parent's "cpuset.cpus".
Similarly, almost all changes to "cpuset.cpus" are allowed with the exception that if the underlying CS_CPU_EXCLUSIVE flag is set, the exclusivity rule will still apply.
Signed-off-by: Waiman Long longman@redhat.com --- kernel/cgroup/cpuset.c | 407 +++++++++++++++++++++-------------------- 1 file changed, 213 insertions(+), 194 deletions(-)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 6c65bcf278cb..ed17b14b6c09 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1218,13 +1218,15 @@ enum subparts_cmd { partcmd_update, /* Update parent's subparts_cpus */ };
+static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, + int turning_on); /** * update_parent_subparts_cpumask - update subparts_cpus mask of parent cpuset * @cpuset: The cpuset that requests change in partition root state * @cmd: Partition root state change command * @newmask: Optional new cpumask for partcmd_update * @tmp: Temporary addmask and delmask - * Return: 0, 1 or an error code + * Return: 0 or -1 (error) * * For partcmd_enable, the cpuset is being transformed from a non-partition * root to a partition root. The cpus_allowed mask of the given cpuset will @@ -1235,28 +1237,22 @@ enum subparts_cmd { * For partcmd_disable, the cpuset is being transformed from a partition * root back to a non-partition root. Any CPUs in cpus_allowed that are in * parent's subparts_cpus will be taken away from that cpumask and put back - * into parent's effective_cpus. 0 should always be returned. + * into parent's effective_cpus. 0 will always be returned. * - * For partcmd_update, if the optional newmask is specified, the cpu - * list is to be changed from cpus_allowed to newmask. Otherwise, - * cpus_allowed is assumed to remain the same. The cpuset should either - * be a partition root or an invalid partition root. The partition root - * state may change if newmask is NULL and none of the requested CPUs can - * be granted by the parent. The function will return 1 if changes to - * parent's subparts_cpus and effective_cpus happen or 0 otherwise. - * Error code should only be returned when newmask is non-NULL. + * For partcmd_update, if the optional newmask is specified, the cpu list is + * to be changed from cpus_allowed to newmask. Otherwise, cpus_allowed is + * assumed to remain the same. The cpuset should either be a valid or invalid + * partition root. The partition root state may change from valid to invalid + * or vice versa. An error code will only be returned if transitioning from + * 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. - * - * The checking is more strict when enabling partition root than the - * other two commands. + * update_prstate(). An error code may be returned and the caller will check + * for error. * - * Because of the implicit cpu exclusive nature of a partition root, - * cpumask changes that violates the cpu exclusivity rule will not be - * permitted when checked by validate_change(). + * 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 will be updated directly. */ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, struct cpumask *newmask, @@ -1278,92 +1274,104 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, if (!is_partition_valid(parent) || (newmask && cpumask_empty(newmask)) || (!newmask && cpumask_empty(cs->cpus_allowed))) - return -EINVAL; - - /* - * Enabling/disabling partition root is not allowed if there are - * online children. - */ - if ((cmd != partcmd_update) && css_has_online_children(&cs->css)) - return -EBUSY; + return -1;
adding = deleting = false; old_prs = new_prs = cs->partition_root_state; if (cmd == partcmd_enable) { /* - * Enabling partition root is not allowed if not all the CPUs - * can be granted from parent's effective_cpus. + * Enabling partition root is not allowed if cpus_allowed + * doesn't overlap parent's cpus_allowed. */ - if (!cpumask_subset(cs->cpus_allowed, parent->effective_cpus)) - return -EINVAL; + if (!cpumask_intersects(cs->cpus_allowed, parent->cpus_allowed)) + return -1;
/* * A parent can be left with no CPU as long as there is no - * task directly associated with the parent partition. For - * such a parent, no new task can be moved into it. + * task directly associated with the parent partition. */ - if (cpumask_equal(cs->cpus_allowed, parent->effective_cpus) && + if (!cpumask_intersects(cs->cpus_allowed, parent->effective_cpus) && partition_is_populated(parent, cs)) - return -EINVAL; + return -1;
cpumask_copy(tmp->addmask, cs->cpus_allowed); adding = true; } else if (cmd == partcmd_disable) { - deleting = cpumask_and(tmp->delmask, cs->cpus_allowed, + /* + * Need to remove cpus from parent's subparts_cpus for valid + * partition root. + */ + deleting = !is_prs_invalid(old_prs) && + cpumask_and(tmp->delmask, cs->cpus_allowed, parent->subparts_cpus); } else if (newmask) { /* * partcmd_update with newmask: * + * Compute add/delete mask to/from subparts_cpus + * * delmask = cpus_allowed & ~newmask & parent->subparts_cpus - * addmask = newmask & parent->effective_cpus + * addmask = newmask & parent->cpus_allowed * & ~parent->subparts_cpus */ cpumask_andnot(tmp->delmask, cs->cpus_allowed, newmask); deleting = cpumask_and(tmp->delmask, tmp->delmask, parent->subparts_cpus);
- cpumask_and(tmp->addmask, newmask, parent->effective_cpus); + cpumask_and(tmp->addmask, newmask, parent->cpus_allowed); adding = cpumask_andnot(tmp->addmask, tmp->addmask, parent->subparts_cpus); /* - * Return error if the new effective_cpus could become empty - * and there are tasks in the parent. + * Make partition invalid if parent's effective_cpus could + * become empty and there are tasks in the parent. */ if (adding && - cpumask_equal(parent->effective_cpus, tmp->addmask) && + cpumask_subset(parent->effective_cpus, tmp->addmask) && + !cpumask_intersects(tmp->delmask, cpu_active_mask) && partition_is_populated(parent, cs)) { - if (!deleting) - return -EINVAL; - /* - * As some of the CPUs in subparts_cpus might have - * been offlined, we need to compute the real delmask - * to confirm that. - */ - if (!cpumask_and(tmp->addmask, tmp->delmask, - cpu_active_mask)) - return -EINVAL; - cpumask_copy(tmp->addmask, parent->effective_cpus); + part_error = true; + adding = false; + deleting = cpumask_and(tmp->delmask, cs->cpus_allowed, + parent->subparts_cpus); } } else { /* * partcmd_update w/o newmask: * - * addmask = cpus_allowed & parent->effective_cpus + * delmask = cpus_allowed & parent->subparts_cpus + * addmask = cpus_allowed & parent->cpus_allowed + * & ~parent->subparts_cpus * - * Note that parent's subparts_cpus may have been - * pre-shrunk in case there is a change in the cpu list. - * So no deletion is needed. + * This gets invoked either due to a hotplug event or from + * update_cpumasks_hier(). This can cause the state of a + * partition root to transition from valid to invalid or vice + * versa. So we still need to compute the addmask and delmask. + + * A partition error happens when: + * 1) Cpuset is valid partition, but parent does not distribute + * out any CPUs. + * 2) Parent has tasks and all its effective CPUs will have + * to be distributed out. */ - adding = cpumask_and(tmp->addmask, cs->cpus_allowed, - parent->effective_cpus); - part_error = cpumask_equal(tmp->addmask, parent->effective_cpus) && - partition_is_populated(parent, cs); + cpumask_and(tmp->addmask, cs->cpus_allowed, + parent->cpus_allowed); + adding = cpumask_andnot(tmp->addmask, tmp->addmask, + parent->subparts_cpus); + if ((is_partition_valid(cs) && !parent->nr_subparts_cpus) || + (adding && + cpumask_subset(parent->effective_cpus, tmp->addmask) && + partition_is_populated(parent, cs))) { + part_error = true; + adding = false; + } + + if (part_error && is_partition_valid(cs) && + parent->nr_subparts_cpus) + deleting = cpumask_and(tmp->delmask, cs->cpus_allowed, + parent->subparts_cpus); }
if (cmd == partcmd_update) { - int prev_prs = cs->partition_root_state; - /* * Check for possible transition between PRS_ROOT * and PRS_INVALID_ROOT. @@ -1378,27 +1386,21 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, new_prs = PRS_ROOT; break; } - /* - * Set part_error if previously in invalid state. - */ - part_error = is_prs_invalid(prev_prs); - } - - if (!part_error && is_prs_invalid(new_prs)) - return 0; /* Nothing need to be done */ - - if (is_prs_invalid(new_prs)) { - /* - * Remove all its cpus from parent's subparts_cpus. - */ - adding = false; - deleting = cpumask_and(tmp->delmask, cs->cpus_allowed, - parent->subparts_cpus); }
if (!adding && !deleting && (new_prs == old_prs)) return 0;
+ /* + * Transitioning from invalid to valid (partcmd_update) may require + * setting CS_CPU_EXCLUSIVE. + */ + if ((old_prs != new_prs) && is_prs_invalid(old_prs)) { + if (!is_cpu_exclusive(cs) && + (update_flag(CS_CPU_EXCLUSIVE, cs, 1) < 0)) + return -1; + } + /* * Change the parent's subparts_cpus. * Newly added CPUs will be removed from effective_cpus and @@ -1428,15 +1430,20 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, cs->partition_root_state = new_prs;
spin_unlock_irq(&callback_lock); + + if (adding || deleting) + update_tasks_cpumask(parent); + notify_partition_change(cs, old_prs);
- return cmd == partcmd_update; + return 0; }
/* * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree * @cs: the cpuset to consider * @tmp: temp variables for calculating effective_cpus & partition setup + * @force: don't skip any descendant cpusets if set * * When configured cpumask is changed, the effective cpumasks of this cpuset * and all its descendants need to be updated. @@ -1445,7 +1452,8 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, * * Called with cpuset_rwsem held */ -static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) +static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp, + bool force) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; @@ -1455,6 +1463,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { struct cpuset *parent = parent_cs(cp); + bool update_parent = false;
compute_effective_cpumask(tmp->new_cpus, cp, parent);
@@ -1482,9 +1491,9 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
/* * Skip the whole subtree if the cpumask remains the same - * and has no partition root state. + * and has no partition root state and force flag not set. */ - if (!cp->partition_root_state && + if (!cp->partition_root_state && !force && cpumask_equal(tmp->new_cpus, cp->effective_cpus)) { pos_css = css_rightmost_descendant(pos_css); continue; @@ -1500,33 +1509,15 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) old_prs = new_prs = cp->partition_root_state; if ((cp != cs) && old_prs) { switch (parent->partition_root_state) { - case PRS_MEMBER: - /* - * If parent is not a partition root or an - * invalid partition root, clear its state - * and its CS_CPU_EXCLUSIVE flag. - */ - WARN_ON_ONCE(!is_partition_invalid(cp)); - new_prs = PRS_MEMBER; - - /* - * clear_bit() is an atomic operation and - * readers aren't interested in the state - * of CS_CPU_EXCLUSIVE anyway. So we can - * just update the flag without holding - * the callback_lock. - */ - clear_bit(CS_CPU_EXCLUSIVE, &cp->flags); - break; - case PRS_ROOT: - if (update_parent_subparts_cpumask(cp, partcmd_update, NULL, tmp)) - update_tasks_cpumask(parent); + update_parent = true; break;
- case PRS_INVALID_ROOT: + default: /* - * When parent is invalid, it has to be too. + * When parent is not a partition root or is + * invalid, child partition roots become + * invalid too. */ new_prs = PRS_INVALID_ROOT; break; @@ -1537,41 +1528,43 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) continue; rcu_read_unlock();
+ if (update_parent) { + update_parent_subparts_cpumask(cp, partcmd_update, NULL, + tmp); + /* + * The cpuset partition_root_state may become + * invalid. Capture it. + */ + new_prs = cp->partition_root_state; + } + spin_lock_irq(&callback_lock);
- cpumask_copy(cp->effective_cpus, tmp->new_cpus); if (cp->nr_subparts_cpus && !is_partition_valid(cp)) { + /* + * Put all active subparts_cpus back to effective_cpus. + */ + cpumask_or(tmp->new_cpus, tmp->new_cpus, + cp->subparts_cpus); + cpumask_and(tmp->new_cpus, tmp->new_cpus, + cpu_active_mask); cp->nr_subparts_cpus = 0; cpumask_clear(cp->subparts_cpus); - } else if (cp->nr_subparts_cpus) { + } + + cpumask_copy(cp->effective_cpus, tmp->new_cpus); + if (cp->nr_subparts_cpus) { /* * Make sure that effective_cpus & subparts_cpus * are mutually exclusive. - * - * In the unlikely event that effective_cpus - * becomes empty. we clear cp->nr_subparts_cpus and - * let its child partition roots to compete for - * CPUs again. */ cpumask_andnot(cp->effective_cpus, cp->effective_cpus, cp->subparts_cpus); - if (cpumask_empty(cp->effective_cpus)) { - cpumask_copy(cp->effective_cpus, tmp->new_cpus); - cpumask_clear(cp->subparts_cpus); - cp->nr_subparts_cpus = 0; - } else if (!cpumask_subset(cp->subparts_cpus, - tmp->new_cpus)) { - cpumask_andnot(cp->subparts_cpus, - cp->subparts_cpus, tmp->new_cpus); - cp->nr_subparts_cpus - = cpumask_weight(cp->subparts_cpus); - } }
- if (new_prs != old_prs) - cp->partition_root_state = new_prs; - + cp->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); + notify_partition_change(cp, old_prs);
WARN_ON(!is_in_v2_mode() && @@ -1632,7 +1625,7 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, continue;
rcu_read_unlock(); - update_cpumasks_hier(sibling, tmp); + update_cpumasks_hier(sibling, tmp, false); rcu_read_lock(); css_put(&sibling->css); } @@ -1692,27 +1685,36 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, #endif
if (cs->partition_root_state) { - /* Cpumask of a partition root cannot be empty */ - if (cpumask_empty(trialcs->cpus_allowed)) - return -EINVAL; - if (update_parent_subparts_cpumask(cs, partcmd_update, - trialcs->cpus_allowed, &tmp) < 0) - return -EINVAL; + update_parent_subparts_cpumask(cs, partcmd_update, + trialcs->cpus_allowed, &tmp); }
+ compute_effective_cpumask(trialcs->effective_cpus, trialcs, + parent_cs(cs)); spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
/* - * Make sure that subparts_cpus is a subset of cpus_allowed. + * Make sure that subparts_cpus, if not empty, is a subset of + * cpus_allowed. Clear subparts_cpus if partition not valid or + * empty effective cpus with tasks. */ if (cs->nr_subparts_cpus) { - cpumask_and(cs->subparts_cpus, cs->subparts_cpus, cs->cpus_allowed); - cs->nr_subparts_cpus = cpumask_weight(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 { + cpumask_and(cs->subparts_cpus, cs->subparts_cpus, + cs->cpus_allowed); + cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus); + } } spin_unlock_irq(&callback_lock);
- update_cpumasks_hier(cs, &tmp); + /* effective_cpus will be updated here */ + update_cpumasks_hier(cs, &tmp, false);
if (cs->partition_root_state) { struct cpuset *parent = parent_cs(cs); @@ -2098,7 +2100,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, */ static int update_prstate(struct cpuset *cs, int new_prs) { - int err, old_prs = cs->partition_root_state; + int err = 0, old_prs = cs->partition_root_state; struct cpuset *parent = parent_cs(cs); struct tmpmasks tmpmask;
@@ -2106,24 +2108,25 @@ static int update_prstate(struct cpuset *cs, int new_prs) return 0;
/* - * Cannot force a partial or invalid partition root to a full - * partition root. + * For a previously invalid partition root, leave it at being + * invalid if new_prs is not "member". */ if (new_prs && is_prs_invalid(old_prs)) - return -EINVAL; + return 0;
if (alloc_cpumasks(NULL, &tmpmask)) return -ENOMEM;
- err = -EINVAL; if (!old_prs) { /* * Turning on partition root requires setting the * CS_CPU_EXCLUSIVE bit implicitly as well and cpus_allowed - * cannot be NULL. + * cannot be empty. */ - if (cpumask_empty(cs->cpus_allowed)) + if (cpumask_empty(cs->cpus_allowed)) { + err = 1; goto out; + }
err = update_flag(CS_CPU_EXCLUSIVE, cs, 1); if (err) @@ -2137,19 +2140,22 @@ static int update_prstate(struct cpuset *cs, int new_prs) } } else { /* - * Turning off partition root will clear the - * CS_CPU_EXCLUSIVE bit. + * Switching back to member is always allowed even if it + * disables child partitions. */ - if (is_prs_invalid(old_prs)) { - update_flag(CS_CPU_EXCLUSIVE, cs, 0); - err = 0; - goto out; - } + update_parent_subparts_cpumask(cs, partcmd_disable, NULL, + &tmpmask);
- err = update_parent_subparts_cpumask(cs, partcmd_disable, - NULL, &tmpmask); - if (err) - goto out; + /* + * If there are child partitions, they will all become invalid. + */ + if (unlikely(cs->nr_subparts_cpus)) { + spin_lock_irq(&callback_lock); + cs->nr_subparts_cpus = 0; + cpumask_clear(cs->subparts_cpus); + compute_effective_cpumask(cs->effective_cpus, cs, parent); + spin_unlock_irq(&callback_lock); + }
/* Turning off CS_CPU_EXCLUSIVE will not return error */ update_flag(CS_CPU_EXCLUSIVE, cs, 0); @@ -2162,15 +2168,24 @@ static int update_prstate(struct cpuset *cs, int new_prs)
rebuild_sched_domains_locked(); out: - if (!err) { - spin_lock_irq(&callback_lock); - cs->partition_root_state = new_prs; - spin_unlock_irq(&callback_lock); - notify_partition_change(cs, old_prs); - } + /* + * Make partition invalid if an error happen + */ + if (err) + new_prs = PRS_INVALID_ROOT; + spin_lock_irq(&callback_lock); + cs->partition_root_state = new_prs; + spin_unlock_irq(&callback_lock); + /* + * Update child cpusets, if present. + * Force update if switching back to member. + */ + if (!list_empty(&cs->css.children)) + update_cpumasks_hier(cs, &tmpmask, !new_prs);
+ notify_partition_change(cs, old_prs); free_cpumasks(NULL, &tmpmask); - return err; + return 0; }
/* @@ -3239,12 +3254,31 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
/* * In the unlikely event that a partition root has empty - * effective_cpus with tasks or its parent becomes invalid, we - * have to transition it to the invalid state. + * effective_cpus with tasks, we will have to invalidate child + * partitions, if present, by setting nr_subparts_cpus to 0 to + * reclaim their cpus. */ - if (is_partition_valid(cs) && - ((cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)) || - is_partition_invalid(parent))) { + if (cs->nr_subparts_cpus && is_partition_valid(cs) && + cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)) { + spin_lock_irq(&callback_lock); + cs->nr_subparts_cpus = 0; + cpumask_clear(cs->subparts_cpus); + spin_unlock_irq(&callback_lock); + compute_effective_cpumask(&new_cpus, cs, parent); + } + + /* + * Force the partition to become invalid if either one of + * the following conditions hold: + * 1) empty effective cpus but not valid empty partition. + * 2) parent is invalid or doesn't grant any cpus to child + * partitions. + */ + if (is_partition_valid(cs) && (!parent->nr_subparts_cpus || + (cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)))) { + int old_prs; + + update_parent_subparts_cpumask(cs, partcmd_disable, NULL, tmp); if (cs->nr_subparts_cpus) { spin_lock_irq(&callback_lock); cs->nr_subparts_cpus = 0; @@ -3253,40 +3287,25 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) compute_effective_cpumask(&new_cpus, cs, parent); }
- /* - * Force the partition to become invalid if either one of - * the following conditions hold: - * 1) empty effective cpus but not valid empty partition. - * 2) parent is invalid or doesn't grant any cpus to child - * partitions. - */ - if (is_partition_invalid(parent) || - (cpumask_empty(&new_cpus) && - partition_is_populated(cs, NULL))) { - int old_prs; - - update_parent_subparts_cpumask(cs, partcmd_disable, - NULL, tmp); - old_prs = cs->partition_root_state; - if (!is_prs_invalid(old_prs)) { - spin_lock_irq(&callback_lock); - set_partition_invalid(cs); - spin_unlock_irq(&callback_lock); - notify_partition_change(cs, old_prs); - } + old_prs = cs->partition_root_state; + if (is_partition_valid(cs)) { + spin_lock_irq(&callback_lock); + set_partition_invalid(cs); + spin_unlock_irq(&callback_lock); + notify_partition_change(cs, old_prs); } cpuset_force_rebuild(); }
/* * On the other hand, an invalid partition root may be transitioned - * back to a regular one or a partition root with no CPU allocated - * from the parent may change to invalid. + * back to a regular one. */ - if (is_partition_valid(parent) && (is_partition_invalid(cs) || - !cpumask_intersects(&new_cpus, parent->subparts_cpus)) && - update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp)) - cpuset_force_rebuild(); + else if (is_partition_valid(parent) && is_partition_invalid(cs)) { + update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp); + if (is_partition_valid(cs)) + cpuset_force_rebuild(); + }
update_tasks: cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
Cpuset v1 uses the sched_load_balance control file to determine if load balancing should be enabled. Cpuset v2 gets rid of sched_load_balance as its use may require disabling load balancing at cgroup root.
For workloads that require very low latency like DPDK, the latency jitters caused by periodic load balancing may exceed the desired latency limit.
When cpuset v2 is in use, the only way to avoid this latency cost is to use the "isolcpus=" kernel boot option to isolate a set of CPUs. After the kernel boot, however, there is no way to add or remove CPUs from this isolated set. For workloads that are more dynamic in nature, that means users have to provision enough CPUs for the worst case situation resulting in excess idle CPUs.
To address this issue for cpuset v2, a new cpuset.cpus.partition type "isolated" is added which allows the creation of a cpuset partition without load balancing. This will allow system administrators to dynamically adjust the size of isolated partition to the current need of the workload without rebooting the system.
Signed-off-by: Waiman Long longman@redhat.com --- kernel/cgroup/cpuset.c | 74 +++++++++++++++++++++++++++++++++++------- 1 file changed, 63 insertions(+), 11 deletions(-)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index ed17b14b6c09..dde45a16deec 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -177,11 +177,15 @@ struct cpuset { * * 0 - member (not a partition root) * 1 - partition root + * 2 - partition root without load balancing (isolated) * -1 - invalid partition root + * -2 - invalid isolated partition root */ #define PRS_MEMBER 0 #define PRS_ROOT 1 +#define PRS_ISOLATED 2 #define PRS_INVALID_ROOT -1 +#define PRS_INVALID_ISOLATED -2
static inline bool is_prs_invalid(int prs_state) { @@ -278,7 +282,8 @@ static inline int is_partition_invalid(const struct cpuset *cs)
static inline void set_partition_invalid(struct cpuset *cs) { - cs->partition_root_state = PRS_INVALID_ROOT; + if (is_partition_valid(cs)) + cs->partition_root_state = -cs->partition_root_state; }
/* @@ -1373,17 +1378,19 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
if (cmd == partcmd_update) { /* - * Check for possible transition between PRS_ROOT - * and PRS_INVALID_ROOT. + * Check for possible transition between valid and invalid + * partition root. */ switch (cs->partition_root_state) { case PRS_ROOT: + case PRS_ISOLATED: if (part_error) - new_prs = PRS_INVALID_ROOT; + new_prs = -old_prs; break; case PRS_INVALID_ROOT: + case PRS_INVALID_ISOLATED: if (!part_error) - new_prs = PRS_ROOT; + new_prs = -old_prs; break; } } @@ -1393,7 +1400,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
/* * Transitioning from invalid to valid (partcmd_update) may require - * setting CS_CPU_EXCLUSIVE. + * setting CS_CPU_EXCLUSIVE and clearing CS_SCHED_LOAD_BALANCE later. */ if ((old_prs != new_prs) && is_prs_invalid(old_prs)) { if (!is_cpu_exclusive(cs) && @@ -1434,8 +1441,17 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, if (adding || deleting) update_tasks_cpumask(parent);
+ /* + * Set or clear CS_SCHED_LOAD_BALANCE when partcmd_update, if necessary. + * rebuild_sched_domains_locked() may be called. + */ + if ((old_prs != new_prs) && (cmd == partcmd_update)) { + if (old_prs == PRS_ISOLATED) + update_flag(CS_SCHED_LOAD_BALANCE, cs, 1); + else if (new_prs == PRS_ISOLATED) + update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); + } notify_partition_change(cs, old_prs); - return 0; }
@@ -1510,6 +1526,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp, if ((cp != cs) && old_prs) { switch (parent->partition_root_state) { case PRS_ROOT: + case PRS_ISOLATED: update_parent = true; break;
@@ -1519,7 +1536,8 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp, * invalid, child partition roots become * invalid too. */ - new_prs = PRS_INVALID_ROOT; + if (is_partition_valid(cp)) + new_prs = -cp->partition_root_state; break; } } @@ -2101,6 +2119,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, static int update_prstate(struct cpuset *cs, int new_prs) { int err = 0, old_prs = cs->partition_root_state; + bool sched_domain_rebuilt = false; struct cpuset *parent = parent_cs(cs); struct tmpmasks tmpmask;
@@ -2111,8 +2130,10 @@ static int update_prstate(struct cpuset *cs, int new_prs) * For a previously invalid partition root, leave it at being * invalid if new_prs is not "member". */ - if (new_prs && is_prs_invalid(old_prs)) + if (new_prs && is_prs_invalid(old_prs)) { + cs->partition_root_state = -new_prs; return 0; + }
if (alloc_cpumasks(NULL, &tmpmask)) return -ENOMEM; @@ -2138,6 +2159,22 @@ static int update_prstate(struct cpuset *cs, int new_prs) update_flag(CS_CPU_EXCLUSIVE, cs, 0); goto out; } + + if (new_prs == PRS_ISOLATED) { + /* + * Disable the load balance flag should not return an + * error unless the system is running out of memory. + */ + update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); + sched_domain_rebuilt = true; + } + } else if (old_prs && new_prs) { + /* + * A change in load balance state only, no change in cpumasks. + */ + update_flag(CS_SCHED_LOAD_BALANCE, cs, (new_prs != PRS_ISOLATED)); + sched_domain_rebuilt = true; + goto out; /* Sched domain is rebuilt in update_flag() */ } else { /* * Switching back to member is always allowed even if it @@ -2159,6 +2196,12 @@ static int update_prstate(struct cpuset *cs, int new_prs)
/* Turning off CS_CPU_EXCLUSIVE will not return error */ update_flag(CS_CPU_EXCLUSIVE, cs, 0); + + if (!is_sched_load_balance(cs)) { + /* Make sure load balance is on */ + update_flag(CS_SCHED_LOAD_BALANCE, cs, 1); + sched_domain_rebuilt = true; + } }
update_tasks_cpumask(parent); @@ -2166,13 +2209,14 @@ static int update_prstate(struct cpuset *cs, int new_prs) if (parent->child_ecpus_count) update_sibling_cpumasks(parent, cs, &tmpmask);
- rebuild_sched_domains_locked(); + if (!sched_domain_rebuilt) + rebuild_sched_domains_locked(); out: /* * Make partition invalid if an error happen */ if (err) - new_prs = PRS_INVALID_ROOT; + new_prs = -new_prs; spin_lock_irq(&callback_lock); cs->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); @@ -2684,12 +2728,18 @@ static int sched_partition_show(struct seq_file *seq, void *v) case PRS_ROOT: seq_puts(seq, "root\n"); break; + case PRS_ISOLATED: + seq_puts(seq, "isolated\n"); + break; case PRS_MEMBER: seq_puts(seq, "member\n"); break; case PRS_INVALID_ROOT: seq_puts(seq, "root invalid\n"); break; + case PRS_INVALID_ISOLATED: + seq_puts(seq, "isolated invalid\n"); + break; } return 0; } @@ -2710,6 +2760,8 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, val = PRS_ROOT; else if (!strcmp(buf, "member")) val = PRS_MEMBER; + else if (!strcmp(buf, "isolated")) + val = PRS_ISOLATED; else return -EINVAL;
There are a number of different reasons which can cause a partition to become invalid. A user seeing an invalid partition may not know exactly why. To help user to get a better understanding of the underlying reason, The cpuset.cpus.partition control file, when read, will now report the reason why a partition become invalid. When a partition does become invalid, reading the control file will show "root invalid (<reason>)" where <reason> is a string that describes why the partition is invalid.
Signed-off-by: Waiman Long longman@redhat.com --- kernel/cgroup/cpuset.c | 93 ++++++++++++++++++++++++++++++++++-------- 1 file changed, 75 insertions(+), 18 deletions(-)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index dde45a16deec..261974f5bb3c 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -85,6 +85,30 @@ struct fmeter { spinlock_t lock; /* guards read or write of above */ };
+/* + * Invalid partition error code + */ +enum prs_errcode { + PERR_NONE = 0, + PERR_INVCPUS, + PERR_INVPARENT, + PERR_NOTPART, + PERR_NOTEXCL, + PERR_NOCPUS, + PERR_HOTPLUG, + PERR_CPUSEMPTY, +}; + +static const char * const perr_strings[] = { + [PERR_INVCPUS] = "Invalid cpu list in cpuset.cpus", + [PERR_INVPARENT] = "Parent is an invalid partition root", + [PERR_NOTPART] = "Parent is not a partition root", + [PERR_NOTEXCL] = "Cpu list in cpuset.cpus not exclusive", + [PERR_NOCPUS] = "Parent unable to distribute cpu downstream", + [PERR_HOTPLUG] = "No cpu available due to hotplug", + [PERR_CPUSEMPTY] = "cpuset.cpus is empty", +}; + struct cpuset { struct cgroup_subsys_state css;
@@ -168,6 +192,9 @@ struct cpuset { int use_parent_ecpus; int child_ecpus_count;
+ /* Invalid partition error code, not lock protected */ + enum prs_errcode prs_err; + /* Handle for cpuset.cpus.partition */ struct cgroup_file partition_file; }; @@ -294,6 +321,10 @@ static inline void notify_partition_change(struct cpuset *cs, int old_prs) if (old_prs == cs->partition_root_state) return; cgroup_file_notify(&cs->partition_file); + + /* Reset prs_err if not invalid */ + if (is_partition_valid(cs)) + WRITE_ONCE(cs->prs_err, PERR_NONE); }
static struct cpuset top_cpuset = { @@ -1231,7 +1262,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, * @cmd: Partition root state change command * @newmask: Optional new cpumask for partcmd_update * @tmp: Temporary addmask and delmask - * Return: 0 or -1 (error) + * Return: 0 or a partition root state error code * * For partcmd_enable, the cpuset is being transformed from a non-partition * root to a partition root. The cpus_allowed mask of the given cpuset will @@ -1257,7 +1288,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, * * 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 will be updated directly. + * 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, @@ -1267,7 +1298,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, int adding; /* Moving cpus from effective_cpus to subparts_cpus */ int deleting; /* Moving cpus from subparts_cpus to effective_cpus */ int old_prs, new_prs; - bool part_error = false; /* Partition error? */ + int part_error = PERR_NONE; /* Partition error? */
percpu_rwsem_assert_held(&cpuset_rwsem);
@@ -1276,10 +1307,13 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, * The new cpumask, if present, or the current cpus_allowed must * not be empty. */ - if (!is_partition_valid(parent) || - (newmask && cpumask_empty(newmask)) || + if (!is_partition_valid(parent)) { + return is_partition_invalid(parent) + ? PERR_INVPARENT : PERR_NOTPART; + } + if ((newmask && cpumask_empty(newmask)) || (!newmask && cpumask_empty(cs->cpus_allowed))) - return -1; + return PERR_CPUSEMPTY;
adding = deleting = false; old_prs = new_prs = cs->partition_root_state; @@ -1289,7 +1323,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, * doesn't overlap parent's cpus_allowed. */ if (!cpumask_intersects(cs->cpus_allowed, parent->cpus_allowed)) - return -1; + return PERR_INVCPUS;
/* * A parent can be left with no CPU as long as there is no @@ -1297,7 +1331,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, */ if (!cpumask_intersects(cs->cpus_allowed, parent->effective_cpus) && partition_is_populated(parent, cs)) - return -1; + return PERR_NOCPUS;
cpumask_copy(tmp->addmask, cs->cpus_allowed); adding = true; @@ -1334,7 +1368,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, cpumask_subset(parent->effective_cpus, tmp->addmask) && !cpumask_intersects(tmp->delmask, cpu_active_mask) && partition_is_populated(parent, cs)) { - part_error = true; + part_error = PERR_NOCPUS; adding = false; deleting = cpumask_and(tmp->delmask, cs->cpus_allowed, parent->subparts_cpus); @@ -1366,7 +1400,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, (adding && cpumask_subset(parent->effective_cpus, tmp->addmask) && partition_is_populated(parent, cs))) { - part_error = true; + part_error = PERR_NOCPUS; adding = false; }
@@ -1375,6 +1409,8 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, deleting = cpumask_and(tmp->delmask, cs->cpus_allowed, parent->subparts_cpus); } + if (part_error) + WRITE_ONCE(cs->prs_err, part_error);
if (cmd == partcmd_update) { /* @@ -1405,7 +1441,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, if ((old_prs != new_prs) && is_prs_invalid(old_prs)) { if (!is_cpu_exclusive(cs) && (update_flag(CS_CPU_EXCLUSIVE, cs, 1) < 0)) - return -1; + return PERR_NOTEXCL; }
/* @@ -1538,6 +1574,9 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp, */ if (is_partition_valid(cp)) new_prs = -cp->partition_root_state; + WRITE_ONCE(cp->prs_err, + is_partition_invalid(parent) + ? PERR_INVPARENT : PERR_NOTPART); break; } } @@ -2112,13 +2151,13 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, * update_prstate - update partition_root_state * @cs: the cpuset to update * @new_prs: new partition root state - * Return: 0 if successful, < 0 if error + * Return: 0 if successful, != 0 if error * * Call with cpuset_rwsem held. */ static int update_prstate(struct cpuset *cs, int new_prs) { - int err = 0, old_prs = cs->partition_root_state; + int err = PERR_NONE, old_prs = cs->partition_root_state; bool sched_domain_rebuilt = false; struct cpuset *parent = parent_cs(cs); struct tmpmasks tmpmask; @@ -2145,13 +2184,15 @@ static int update_prstate(struct cpuset *cs, int new_prs) * cannot be empty. */ if (cpumask_empty(cs->cpus_allowed)) { - err = 1; + err = PERR_CPUSEMPTY; goto out; }
err = update_flag(CS_CPU_EXCLUSIVE, cs, 1); - if (err) + if (err) { + err = PERR_NOTEXCL; goto out; + }
err = update_parent_subparts_cpumask(cs, partcmd_enable, NULL, &tmpmask); @@ -2723,6 +2764,7 @@ static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) static int sched_partition_show(struct seq_file *seq, void *v) { struct cpuset *cs = css_cs(seq_css(seq)); + const char *err, *type = NULL;
switch (cs->partition_root_state) { case PRS_ROOT: @@ -2735,9 +2777,17 @@ static int sched_partition_show(struct seq_file *seq, void *v) seq_puts(seq, "member\n"); break; case PRS_INVALID_ROOT: - seq_puts(seq, "root invalid\n"); - break; + type = "root"; + fallthrough; case PRS_INVALID_ISOLATED: + if (!type) + type = "isolated"; + err = perr_strings[READ_ONCE(cs->prs_err)]; + if (err) + seq_printf(seq, "%s invalid (%s)\n", type, err); + else + seq_printf(seq, "%s invalid\n", type); + break; seq_puts(seq, "isolated invalid\n"); break; } @@ -3328,7 +3378,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) */ if (is_partition_valid(cs) && (!parent->nr_subparts_cpus || (cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)))) { - int old_prs; + int old_prs, parent_prs;
update_parent_subparts_cpumask(cs, partcmd_disable, NULL, tmp); if (cs->nr_subparts_cpus) { @@ -3340,10 +3390,17 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) }
old_prs = cs->partition_root_state; + parent_prs = parent->partition_root_state; if (is_partition_valid(cs)) { spin_lock_irq(&callback_lock); set_partition_invalid(cs); spin_unlock_irq(&callback_lock); + if (is_prs_invalid(parent_prs)) + WRITE_ONCE(cs->prs_err, PERR_INVPARENT); + else if (!parent_prs) + WRITE_ONCE(cs->prs_err, PERR_NOTPART); + else + WRITE_ONCE(cs->prs_err, PERR_HOTPLUG); notify_partition_change(cs, old_prs); } cpuset_force_rebuild();
Update Documentation/admin-guide/cgroup-v2.rst on the newly introduced "isolated" cpuset partition type as well as other changes made in other cpuset patches.
Signed-off-by: Waiman Long longman@redhat.com --- Documentation/admin-guide/cgroup-v2.rst | 149 +++++++++++++----------- 1 file changed, 83 insertions(+), 66 deletions(-)
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 69d7a6983f78..9184a09e0fc9 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -2110,74 +2110,91 @@ Cpuset Interface Files It accepts only the following input values when written to.
======== ================================ - "root" a partition root - "member" a non-root member of a partition + "member" Non-root member of a partition + "root" Partition root + "isolated" Partition root without load balancing ======== ================================
- When set to be a partition root, the current cgroup is the - root of a new partition or scheduling domain that comprises - itself and all its descendants except those that are separate - partition roots themselves and their descendants. The root - cgroup is always a partition root. - - There are constraints on where a partition root can be set. - It can only be set in a cgroup if all the following conditions - are true. - - 1) The "cpuset.cpus" is not empty and the list of CPUs are - exclusive, i.e. they are not shared by any of its siblings. - 2) The parent cgroup is a partition root. - 3) The "cpuset.cpus" is also a proper subset of the parent's - "cpuset.cpus.effective". - 4) There is no child cgroups with cpuset enabled. This is for - eliminating corner cases that have to be handled if such a - condition is allowed. - - Setting it to partition root will take the CPUs away from the - effective CPUs of the parent cgroup. Once it is set, this - file cannot be reverted back to "member" if there are any child - cgroups with cpuset enabled. - - A parent partition cannot distribute all its CPUs to its - child partitions. There must be at least one cpu left in the - parent partition. - - Once becoming a partition root, changes to "cpuset.cpus" is - generally allowed as long as the first condition above is true, - the change will not take away all the CPUs from the parent - partition and the new "cpuset.cpus" value is a superset of its - children's "cpuset.cpus" values. - - Sometimes, external factors like changes to ancestors' - "cpuset.cpus" or cpu hotplug can cause the state of the partition - root to change. On read, the "cpuset.sched.partition" file - can show the following values. - - ============== ============================== - "member" Non-root member of a partition - "root" Partition root - "root invalid" Invalid partition root - ============== ============================== - - It is a partition root if the first 2 partition root conditions - above are true and at least one CPU from "cpuset.cpus" is - granted by the parent cgroup. - - A partition root can become invalid if none of CPUs requested - in "cpuset.cpus" can be granted by the parent cgroup or the - parent cgroup is no longer a partition root itself. In this - case, it is not a real partition even though the restriction - of the first partition root condition above will still apply. - The cpu affinity of all the tasks in the cgroup will then be - associated with CPUs in the nearest ancestor partition. - - An invalid partition root can be transitioned back to a - real partition root if at least one of the requested CPUs - can now be granted by its parent. In this case, the cpu - affinity of all the tasks in the formerly invalid partition - will be associated to the CPUs of the newly formed partition. - Changing the partition state of an invalid partition root to - "member" is always allowed even if child cpusets are present. + The root cgroup is always a partition root and its state + cannot be changed. All other non-root cgroups start out as + "member". + + When set to "root", the current cgroup is the root of a new + partition or scheduling domain that comprises itself and all + its descendants except those that are separate partition roots + themselves and their descendants. + + When set to "isolated", the CPUs in that partition root will + be in an isolated state without any load balancing from the + scheduler. Tasks placed in such a partition with multiple + 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 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 + root is in a degraded state where some state information may + be retained, but behaves more like a "member". + + All possible state transitions among "member", "root" and + "isolated" are allowed. + + On read, the "cpuset.cpus.partition" file can show the following + values. + + ====================== ============================== + "member" Non-root member of a partition + "root" Partition root + "isolated" Partition root without load balancing + "root invalid (<reason>)" Invalid partition root + "isolated invalid (<reason>)" Invalid isolated partition root + ====================== ============================== + + In the case of an invalid partition root, a descriptive string on + why the partition is invalid is included within parentheses. + + For a partition root to become valid, the following conditions + must be met. + + 1) The "cpuset.cpus" is exclusive, i.e. they are not shared by + any of its siblings (exclusivity rule). + 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. + + 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. + + 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 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 + by write to "cpuset.cpus.partition", cpu hotplug or other + changes that modify the validity status of the partition. + This will allow user space agents to monitor unexpected changes + to "cpuset.cpus.partition" without the need to do continuous + polling.
Device controller
Hello,
On Tue, May 10, 2022 at 11:34:12AM -0400, Waiman Long wrote:
- 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.
My memory is failing but this is the same thing that we were discussing before, right? The point was that the different behaviors re. system events and config actions seemed unncessary and IIRC Michal was of the same opinion (please correct me if I'm misremembering).
- A valid non-root parent partition may distribute out all its CPUs
- to its child partitions when there is no task associated with it.
I'm probably forgetting something. Was this necessary because of threaded cgroup support because otherwise the above condition is superflous?
Thanks.
On 6/12/22 13:49, Tejun Heo wrote:
Hello,
On Tue, May 10, 2022 at 11:34:12AM -0400, Waiman Long wrote:
- 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.
My memory is failing but this is the same thing that we were discussing before, right? The point was that the different behaviors re. system events and config actions seemed unncessary and IIRC Michal was of the same opinion (please correct me if I'm misremembering).
That is the behavior enforced by setting the CPU_EXCLUSIVE bit in cgroup v1. I haven't explicitly change it to make it different in cgroup v2. The major reason is that I don't want change to one cpuset to affect a sibling partition as it may make the code more complicate to validate if a partition is valid.
- A valid non-root parent partition may distribute out all its CPUs
- to its child partitions when there is no task associated with it.
I'm probably forgetting something. Was this necessary because of threaded cgroup support because otherwise the above condition is superflous?
The top cpuset cannot have empty cpus.effective whereas the non-root partition roots can. Maybe I should reword it to make it more clear.
Thanks, Longman
Hello,
On Sun, Jun 12, 2022 at 11:02:38PM -0400, Waiman Long wrote:
That is the behavior enforced by setting the CPU_EXCLUSIVE bit in cgroup v1. I haven't explicitly change it to make it different in cgroup v2. The major reason is that I don't want change to one cpuset to affect a sibling partition as it may make the code more complicate to validate if a partition is valid.
If at all possible, I'd really like to avoid situations where a parent can't withdraw resources due to something that a descendant does.
Thanks.
On 6/12/22 23:12, Tejun Heo wrote:
Hello,
On Sun, Jun 12, 2022 at 11:02:38PM -0400, Waiman Long wrote:
That is the behavior enforced by setting the CPU_EXCLUSIVE bit in cgroup v1. I haven't explicitly change it to make it different in cgroup v2. The major reason is that I don't want change to one cpuset to affect a sibling partition as it may make the code more complicate to validate if a partition is valid.
If at all possible, I'd really like to avoid situations where a parent can't withdraw resources due to something that a descendant does.
No, it doesn't affect parent at all. It just limit whats the siblings can do due to their mutual constraint. If this is what the confusion is about, I will try to reword the doc text.
Cheers, Longman
On 6/13/22 09:18, Waiman Long wrote:
On 6/12/22 23:12, Tejun Heo wrote:
Hello,
On Sun, Jun 12, 2022 at 11:02:38PM -0400, Waiman Long wrote:
That is the behavior enforced by setting the CPU_EXCLUSIVE bit in cgroup v1. I haven't explicitly change it to make it different in cgroup v2. The major reason is that I don't want change to one cpuset to affect a sibling partition as it may make the code more complicate to validate if a partition is valid.
If at all possible, I'd really like to avoid situations where a parent can't withdraw resources due to something that a descendant does.
No, it doesn't affect parent at all. It just limit whats the siblings can do due to their mutual constraint. If this is what the confusion is about, I will try to reword the doc text.
I am planning to make the following change to the documentation patch. Please let me know if that can clarify the confusion, if any.
Thanks, Longman
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guid> index 9184a09e0fc9..9cbfa25dab97 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -2176,7 +2175,8 @@ Cpuset Interface Files
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. + that violate the exclusivity rule with its siblings 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.
On Sun, Jun 12, 2022 at 05:12:51PM -1000, Tejun Heo tj@kernel.org wrote:
Hello,
On Sun, Jun 12, 2022 at 11:02:38PM -0400, Waiman Long wrote:
That is the behavior enforced by setting the CPU_EXCLUSIVE bit in cgroup v1. I haven't explicitly change it to make it different in cgroup v2. The major reason is that I don't want change to one cpuset to affect a sibling partition as it may make the code more complicate to validate if a partition is valid.
If at all possible, I'd really like to avoid situations where a parent can't withdraw resources due to something that a descendant does.
My understanding of the discussed paragraph is that the changes are only disallowed only among siblings on one level (due to exclusivity rule, checked in validate_change()). A change in parent won't affect (non)exclusivity of (valid) children so it's simply allowed.
So the docs (and implementation by a quick look) is sensible.
Michal
Hello,
On Mon, Jun 13, 2022 at 04:24:52PM +0200, Michal Koutný wrote:
On Sun, Jun 12, 2022 at 05:12:51PM -1000, Tejun Heo tj@kernel.org wrote:
On Sun, Jun 12, 2022 at 11:02:38PM -0400, Waiman Long wrote:
That is the behavior enforced by setting the CPU_EXCLUSIVE bit in cgroup v1. I haven't explicitly change it to make it different in cgroup v2. The major reason is that I don't want change to one cpuset to affect a sibling partition as it may make the code more complicate to validate if a partition is valid.
If at all possible, I'd really like to avoid situations where a parent can't withdraw resources due to something that a descendant does.
My understanding of the discussed paragraph is that the changes are only disallowed only among siblings on one level (due to exclusivity rule, checked in validate_change()). A change in parent won't affect (non)exclusivity of (valid) children so it's simply allowed.
So the docs (and implementation by a quick look) is sensible.
I see. Is this part even necessary? All the .cpus files of the siblings are owned by the parent who's responsible for configuring both the mode that the cgroup subtree is gonna be in and their cpumasks. Given that all the other errors it can make are notified through "invalid (REASON)" in the mode file, wouldn't it fit better to notify cpus configuration error the same way too?
Thanks.
On Mon, Jun 13, 2022 at 07:28:25AM -1000, Tejun Heo tj@kernel.org wrote:
I see. Is this part even necessary? All the .cpus files of the siblings are owned by the parent who's responsible for configuring both the mode that the cgroup subtree is gonna be in and their cpumasks.
Do you mean such an example:
parent cpuset.cpus=SET (root) cpuset.cpus.partition=isolated `- child_1 cpuset.cpus=partition_of(SET) (root) cpuset.cpus.partition=isolated `- ... `- child_n cpuset.cpus=partition_of(SET) (root) cpuset.cpus.partition=isolated ?
I don't think child_*/cpuset.cpus must be owned by root. Actually, the root would only configure the parent, i.e. parent/cpuset.cpus (whose changes would be disallowed to the unprivileged tasks) and the distribution among siblings would up to the whatever runs below.
Given that all the other errors it can make are notified through "invalid (REASON)" in the mode file, wouldn't it fit better to notify cpus configuration error the same way too?
Do you suggest that a write into child_*/cpuset.cpus that'd not be exclusive wrt a sibling would result in an error string in parent/cpuset.cpus.partition?
Thanks, Michal
Hello,
On Mon, Jun 13, 2022 at 07:55:49PM +0200, Michal Koutný wrote:
On Mon, Jun 13, 2022 at 07:28:25AM -1000, Tejun Heo tj@kernel.org wrote:
I see. Is this part even necessary? All the .cpus files of the siblings are owned by the parent who's responsible for configuring both the mode that the cgroup subtree is gonna be in and their cpumasks.
Do you mean such an example:
parent cpuset.cpus=SET (root) cpuset.cpus.partition=isolated `- child_1 cpuset.cpus=partition_of(SET) (root) cpuset.cpus.partition=isolated `- ... `- child_n cpuset.cpus=partition_of(SET) (root) cpuset.cpus.partition=isolated?
I don't think child_*/cpuset.cpus must be owned by root.
I meant the parent.
Actually, the root would only configure the parent, i.e. parent/cpuset.cpus (whose changes would be disallowed to the unprivileged tasks) and the distribution among siblings would up to the whatever runs below.
Given that all the other errors it can make are notified through "invalid (REASON)" in the mode file, wouldn't it fit better to notify cpus configuration error the same way too?
Do you suggest that a write into child_*/cpuset.cpus that'd not be exclusive wrt a sibling would result in an error string in parent/cpuset.cpus.partition?
Yeah, I don't know why this part is different from any other errors that the parent can make.
Thanks.
On Mon, Jun 13, 2022 at 08:00:56AM -1000, Tejun Heo tj@kernel.org wrote:
Yeah, I don't know why this part is different from any other errors that the parent can make.
It's different because a write to parent's cpuset.cpus is independent of whether cpuset.cpus of its children are exclusive or not. In an extreme case the children may be non-exclusive
parent cpuset.cpus=0-3 // valid partition `- child_1 cpuset.cpus=0-1 // invalid partition `- child_2 cpuset.cpus=1-2 // invalid partition
but the parent can still be a valid partition (thanks to cpu no. 3 in the example above).
Do I miss anything?
Thanks, Michal
Hello,
On Tue, Jun 14, 2022 at 01:53:45PM +0200, Michal Koutný wrote:
On Mon, Jun 13, 2022 at 08:00:56AM -1000, Tejun Heo tj@kernel.org wrote:
Yeah, I don't know why this part is different from any other errors that the parent can make.
It's different because a write to parent's cpuset.cpus is independent of whether cpuset.cpus of its children are exclusive or not. In an extreme case the children may be non-exclusive
parent cpuset.cpus=0-3 // valid partition `- child_1 cpuset.cpus=0-1 // invalid partition `- child_2 cpuset.cpus=1-2 // invalid partitionbut the parent can still be a valid partition (thanks to cpu no. 3 in the example above).
Do I miss anything?
What I'm trying to say is that cpuset.cpus of child_1 and child_2 are owned by the parent, so a feature which blocks siblings from intersecting each other doesn't make whole lot of sense because all those files are under the control of the parent who would have the power to enable or disable the restrition anyway.
The partition mode file is owned by the parent too, right? So, all these are to be configured by the same entity and the errors can be reported the same way, no?
Thanks.
On Tue, Jun 28, 2022 at 04:10:29AM +0900, Tejun Heo tj@kernel.org wrote:
What I'm trying to say is that cpuset.cpus of child_1 and child_2 are owned by the parent,
Cf
On Mon, Jun 13, 2022 at 08:00:56AM -1000, Tejun Heo tj@kernel.org wrote:
On Mon, Jun 13, 2022 at 07:55:49PM +0200, Michal Koutný wrote:
I don't think child_*/cpuset.cpus must be owned by root.
I meant the parent.
I'm slightly confused.
so a feature which blocks siblings from intersecting each other doesn't make whole lot of sense because all those files are under the control of the parent who would have the power to enable or disable the restrition anyway.
file owner parent/ user (mkdir) `- cpuset.cpus root `- cpuset.cpus.partition root (P) `- child_1/ user ` cpuset.cpus user (*) `- child_2/ user ` cpuset.cpus user (*)
The writes to child cpuset.cpus may/may not invalidate parent's (P) partition validity (whether a cpu is left to it to host possible tasks). child_1 vs child_2 overlap affects only whether the children cgroups are a valid partition.
I think you mean: writes to children cpuset.cpus should be allowed, possible exclusivity violation should be reported in parent/cpuset.cpus.partition.
What I thought was OK: prevent (fail) writes to children cpuset.cpus that'd violate the exclusivity (or would take the last cpu from parent if it's necessary to host a task). IMO, it's similar to failed writes to parent/cgroup.subtree_control in a delegated subtree if the parent still has some tasks (that'd violate internal node constraint).
What I think might still be OK: allow writes to children cpuset.cpus that violate exclusivity and report that in children's cpuset.cpus.partition. Writes that'd take last cpu from parent should still fail (similar to the failing subtree_control writes above).
Hope that clarifies, Michal
Hello,
On Thu, Jun 30, 2022 at 04:32:11PM +0200, Michal Koutný wrote:
file owner parent/ user (mkdir) `- cpuset.cpus root `- cpuset.cpus.partition root (P) `- child_1/ user ` cpuset.cpus user (*) `- child_2/ user ` cpuset.cpus user (*)
The writes to child cpuset.cpus may/may not invalidate parent's (P) partition validity (whether a cpu is left to it to host possible tasks). child_1 vs child_2 overlap affects only whether the children cgroups are a valid partition.
I think you mean: writes to children cpuset.cpus should be allowed, possible exclusivity violation should be reported in parent/cpuset.cpus.partition.
I see.
What I thought was OK: prevent (fail) writes to children cpuset.cpus that'd violate the exclusivity (or would take the last cpu from parent if it's necessary to host a task). IMO, it's similar to failed writes to parent/cgroup.subtree_control in a delegated subtree if the parent still has some tasks (that'd violate internal node constraint).
What I think might still be OK: allow writes to children cpuset.cpus that violate exclusivity and report that in children's cpuset.cpus.partition. Writes that'd take last cpu from parent should still fail (similar to the failing subtree_control writes above).
Yeah, this one.
So, here, one important question is who owns cpuset.cpus.partition file - is it a konb which is owned by the parent like other resource control knobs including cpuset.cpus or is it a knob which is owned by the cgroup itself for selecting its own operation like cgroup.procs or cgroup.subtree_control.
In the former case, the parent being able to say that "my children can't overlap" makes sense although I'm not a big fan of the current interface (again, who owns that knob?). In the latter case, it doesn't really make sense cuz it'd be declaring "I can't make my children overlap" - well, then, don't.
Thanks.
Add a test script test_cpuset_prs.sh with a helper program wait_inotify for exercising the cpuset v2 partition root state code.
Signed-off-by: Waiman Long longman@redhat.com --- tools/testing/selftests/cgroup/Makefile | 5 +- .../selftests/cgroup/test_cpuset_prs.sh | 674 ++++++++++++++++++ tools/testing/selftests/cgroup/wait_inotify.c | 87 +++ 3 files changed, 764 insertions(+), 2 deletions(-) create mode 100755 tools/testing/selftests/cgroup/test_cpuset_prs.sh create mode 100644 tools/testing/selftests/cgroup/wait_inotify.c
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile index 745fe25fa0b9..01687418b92f 100644 --- a/tools/testing/selftests/cgroup/Makefile +++ b/tools/testing/selftests/cgroup/Makefile @@ -1,10 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -Wall -pthread
-all: +all: ${HELPER_PROGS}
TEST_FILES := with_stress.sh -TEST_PROGS := test_stress.sh +TEST_PROGS := test_stress.sh test_cpuset_prs.sh +TEST_GEN_FILES := wait_inotify TEST_GEN_PROGS = test_memcontrol TEST_GEN_PROGS += test_kmem TEST_GEN_PROGS += test_core diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh new file mode 100755 index 000000000000..3ee12f8dc752 --- /dev/null +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -0,0 +1,674 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test for cpuset v2 partition root state (PRS) +# +# The sched verbose flag is set, if available, so that the console log +# can be examined for the correct setting of scheduling domain. +# + +skip_test() { + echo "$1" + echo "Test SKIPPED" + exit 0 +} + +[[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!" + +# Set sched verbose flag, if available +[[ -d /sys/kernel/debug/sched ]] && echo Y > /sys/kernel/debug/sched/verbose + +# Get wait_inotify location +WAIT_INOTIFY=$(cd $(dirname $0); pwd)/wait_inotify + +# Find cgroup v2 mount point +CGROUP2=$(mount -t cgroup2 | head -1 | awk -e '{print $3}') +[[ -n "$CGROUP2" ]] || skip_test "Cgroup v2 mount point not found!" + +CPUS=$(lscpu | grep "^CPU(s)" | sed -e "s/.*:[[:space:]]*//") +[[ $CPUS -lt 8 ]] && skip_test "Test needs at least 8 cpus available!" + +# Set verbose flag and delay factor +PROG=$1 +VERBOSE= +DELAY_FACTOR=1 +while [[ "$1" = -* ]] +do + case "$1" in + -v) VERBOSE=1 + break + ;; + -d) DELAY_FACTOR=$2 + shift + break + ;; + *) echo "Usage: $PROG [-v] [-d <delay-factor>" + exit + ;; + esac + shift +done + +cd $CGROUP2 +echo +cpuset > cgroup.subtree_control +[[ -d test ]] || mkdir test +cd test + +# Pause in ms +pause() +{ + DELAY=$1 + LOOP=0 + while [[ $LOOP -lt $DELAY_FACTOR ]] + do + sleep $DELAY + ((LOOP++)) + done + return 0 +} + +console_msg() +{ + MSG=$1 + echo "$MSG" + echo "" > /dev/console + echo "$MSG" > /dev/console + pause 0.01 +} + +test_partition() +{ + EXPECTED_VAL=$1 + echo $EXPECTED_VAL > cpuset.cpus.partition + [[ $? -eq 0 ]] || exit 1 + ACTUAL_VAL=$(cat cpuset.cpus.partition) + [[ $ACTUAL_VAL != $EXPECTED_VAL ]] && { + echo "cpuset.cpus.partition: expect $EXPECTED_VAL, found $EXPECTED_VAL" + echo "Test FAILED" + exit 1 + } +} + +test_effective_cpus() +{ + EXPECTED_VAL=$1 + ACTUAL_VAL=$(cat cpuset.cpus.effective) + [[ "$ACTUAL_VAL" != "$EXPECTED_VAL" ]] && { + echo "cpuset.cpus.effective: expect '$EXPECTED_VAL', found '$EXPECTED_VAL'" + echo "Test FAILED" + exit 1 + } +} + +# Adding current process to cgroup.procs as a test +test_add_proc() +{ + OUTSTR="$1" + ERRMSG=$((echo $$ > cgroup.procs) |& cat) + echo $ERRMSG | grep -q "$OUTSTR" + [[ $? -ne 0 ]] && { + echo "cgroup.procs: expect '$OUTSTR', got '$ERRMSG'" + echo "Test FAILED" + exit 1 + } + echo $$ > $CGROUP2/cgroup.procs # Move out the task +} + +# +# Testing the new "isolated" partition root type +# +test_isolated() +{ + echo 2-3 > cpuset.cpus + TYPE=$(cat cpuset.cpus.partition) + [[ $TYPE = member ]] || echo member > cpuset.cpus.partition + + console_msg "Change from member to root" + test_partition root + + console_msg "Change from root to isolated" + test_partition isolated + + console_msg "Change from isolated to member" + test_partition member + + console_msg "Change from member to isolated" + test_partition isolated + + console_msg "Change from isolated to root" + test_partition root + + console_msg "Change from root to member" + test_partition member + + # + # Testing partition root with no cpu + # + console_msg "Distribute all cpus to child partition" + echo +cpuset > cgroup.subtree_control + test_partition root + + mkdir A1 + cd A1 + echo 2-3 > cpuset.cpus + test_partition root + test_effective_cpus 2-3 + cd .. + test_effective_cpus "" + + console_msg "Moving task to partition test" + test_add_proc "No space left" + cd A1 + test_add_proc "" + cd .. + + console_msg "Shrink and expand child partition" + cd A1 + echo 2 > cpuset.cpus + cd .. + test_effective_cpus 3 + cd A1 + echo 2-3 > cpuset.cpus + cd .. + test_effective_cpus "" + + # Cleaning up + console_msg "Cleaning up" + echo $$ > $CGROUP2/cgroup.procs + [[ -d A1 ]] && rmdir A1 +} + +# +# Cpuset controller state transition test matrix. +# +# Cgroup test hierarchy +# +# test -- A1 -- A2 -- A3 +# - B1 +# +# P<v> = set cpus.partition (0:member, 1:root, 2:isolated, -1:root invalid) +# C<l> = add cpu-list +# S<p> = use prefix in subtree_control +# T = put a task into cgroup +# O<c>-<v> = Write <v> to CPU online file of <c> +# +SETUP_A123_PARTITIONS="C1-3:P1:S+ C2-3:P1:S+ C3:P1" +TEST_MATRIX=( + # test old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate + # ---- ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ + " S+ C0-1 . . C2-3 S+ C4-5 . . 0 A2:0-1" + " S+ C0-1 . . C2-3 P1 . . . 0 " + " S+ C0-1 . . C2-3 P1:S+ C0-1:P1 . . 0 " + " S+ C0-1 . . C2-3 P1:S+ C1:P1 . . 0 " + " S+ C0-1:S+ . . C2-3 . . . P1 0 " + " S+ C0-1:P1 . . C2-3 S+ C1 . . 0 " + " S+ C0-1:P1 . . C2-3 S+ C1:P1 . . 0 " + " S+ C0-1:P1 . . C2-3 S+ C1:P1 . P1 0 " + " S+ C0-1:P1 . . C2-3 C4-5 . . . 0 A1:4-5" + " S+ C0-1:P1 . . C2-3 S+:C4-5 . . . 0 A1:4-5" + " S+ C0-1 . . C2-3:P1 . . . C2 0 " + " S+ C0-1 . . C2-3:P1 . . . C4-5 0 B1:4-5" + " S+ C0-3:P1:S+ C2-3:P1 . . . . . . 0 A1:0-1,A2:2-3" + " S+ C0-3:P1:S+ C2-3:P1 . . C1-3 . . . 0 A1:1,A2:2-3" + " S+ C2-3:P1:S+ C3:P1 . . C3 . . . 0 A1:,A2:3 A1:P1,A2:P1" + " S+ C2-3:P1:S+ C3:P1 . . C3 P0 . . 0 A1:3,A2:3 A1:P1,A2:P0" + " S+ C2-3:P1:S+ C2:P1 . . C2-4 . . . 0 A1:3-4,A2:2" + " S+ C2-3:P1:S+ C3:P1 . . C3 . . C0-2 0 A1:,B1:0-2 A1:P1,A2:P1" + " S+ $SETUP_A123_PARTITIONS . C2-3 . . . 0 A1:,A2:2,A3:3 A1:P1,A2:P1,A3:P1" + + # CPU offlining cases: + " S+ C0-1 . . C2-3 S+ C4-5 . O2-0 0 A1:0-1,B1:3" + " S+ C0-3:P1:S+ C2-3:P1 . . O2-0 . . . 0 A1:0-1,A2:3" + " S+ C0-3:P1:S+ C2-3:P1 . . O2-0 O2-1 . . 0 A1:0-1,A2:2-3" + " S+ C0-3:P1:S+ C2-3:P1 . . O1-0 . . . 0 A1:0,A2:2-3" + " S+ C0-3:P1:S+ C2-3:P1 . . O1-0 O1-1 . . 0 A1:0-1,A2:2-3" + " S+ C2-3:P1:S+ C3:P1 . . O3-0 O3-1 . . 0 A1:2,A2:3 A1:P1,A2:P1" + " S+ C2-3:P1:S+ C3:P2 . . O3-0 O3-1 . . 0 A1:2,A2:3 A1:P1,A2:P2" + " S+ C2-3:P1:S+ C3:P1 . . O2-0 O2-1 . . 0 A1:2,A2:3 A1:P1,A2:P1" + " S+ C2-3:P1:S+ C3:P2 . . O2-0 O2-1 . . 0 A1:2,A2:3 A1:P1,A2:P2" + " S+ C2-3:P1:S+ C3:P1 . . O2-0 . . . 0 A1:,A2:3 A1:P1,A2:P1" + " S+ C2-3:P1:S+ C3:P1 . . O3-0 . . . 0 A1:2,A2: A1:P1,A2:P1" + " S+ C2-3:P1:S+ C3:P1 . . T:O2-0 . . . 0 A1:3,A2:3 A1:P1,A2:P-1" + " S+ C2-3:P1:S+ C3:P1 . . . T:O3-0 . . 0 A1:2,A2:2 A1:P1,A2:P-1" + " S+ $SETUP_A123_PARTITIONS . O1-0 . . . 0 A1:,A2:2,A3:3 A1:P1,A2:P1,A3:P1" + " S+ $SETUP_A123_PARTITIONS . O2-0 . . . 0 A1:1,A2:,A3:3 A1:P1,A2:P1,A3:P1" + " S+ $SETUP_A123_PARTITIONS . O3-0 . . . 0 A1:1,A2:2,A3: A1:P1,A2:P1,A3:P1" + " S+ $SETUP_A123_PARTITIONS . T:O1-0 . . . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1" + " S+ $SETUP_A123_PARTITIONS . . T:O2-0 . . 0 A1:1,A2:3,A3:3 A1:P1,A2:P1,A3:P-1" + " S+ $SETUP_A123_PARTITIONS . . . T:O3-0 . 0 A1:1,A2:2,A3:2 A1:P1,A2:P1,A3:P-1" + " S+ $SETUP_A123_PARTITIONS . T:O1-0 O1-1 . . 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1" + " S+ $SETUP_A123_PARTITIONS . . T:O2-0 O2-1 . 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1" + " S+ $SETUP_A123_PARTITIONS . . . T:O3-0 O3-1 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1" + " S+ $SETUP_A123_PARTITIONS . T:O1-0 O2-0 O1-1 . 0 A1:1,A2:,A3:3 A1:P1,A2:P1,A3:P1" + " S+ $SETUP_A123_PARTITIONS . T:O1-0 O2-0 O2-1 . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1" + + # test old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate + # ---- ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ + # + # Incorrect change to cpuset.cpus invalidates partition root + # + # Adding CPUs to partition root that are not in parent's + # cpuset.cpus is allowed, but those extra CPUs are ignored. + " S+ C2-3:P1:S+ C3:P1 . . . C2-4 . . 0 A1:,A2:2-3 A1:P1,A2:P1" + + # Taking away all CPUs from parent or itself if there are tasks + # will make the partition invalid. + " S+ C2-3:P1:S+ C3:P1 . . T C2-3 . . 0 A1:2-3,A2:2-3 A1:P1,A2:P-1" + " S+ $SETUP_A123_PARTITIONS . T:C2-3 . . . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1" + " S+ $SETUP_A123_PARTITIONS . T:C2-3:C1-3 . . . 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1" + + # Changing a partition root to member makes child partitions invalid + " S+ C2-3:P1:S+ C3:P1 . . P0 . . . 0 A1:2-3,A2:3 A1:P0,A2:P-1" + " S+ $SETUP_A123_PARTITIONS . C2-3 P0 . . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P0,A3:P-1" + + # cpuset.cpus can contains cpus not in parent's cpuset.cpus as long + # as they overlap. + " S+ C2-3:P1:S+ . . . . C3-4:P1 . . 0 A1:2,A2:3 A1:P1,A2:P1" + + # Deletion of CPUs distributed to child cgroup is allowed. + " S+ C0-1:P1:S+ C1 . C2-3 C4-5 . . . 0 A1:4-5,A2:4-5" + + # To become a valid partition root, cpuset.cpus must overlap parent's + # cpuset.cpus. + " S+ C0-1:P1 . . C2-3 S+ C4-5:P1 . . 0 A1:0-1,A2:0-1 A1:P1,A2:P-1" + + # Enabling partition with child cpusets is allowed + " S+ C0-1:S+ C1 . C2-3 P1 . . . 0 A1:0-1,A2:1 A1:P1" + + # A partition root with non-partition root parent is invalid, but it + # can be made valid if its parent becomes a partition root too. + " S+ C0-1:S+ C1 . C2-3 . P2 . . 0 A1:0-1,A2:1 A1:P0,A2:P-2" + " S+ C0-1:S+ C1:P2 . C2-3 P1 . . . 0 A1:0,A2:1 A1:P1,A2:P2" + + # test old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate + # ---- ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ + # Failure cases: + + # Any change to cpuset.cpus of a partition root must be exclusive. + " S+ C0-1:P1 . . C2-3 C0-2 . . . 1 " + " S+ C0-1 . . C2-3:P1 . . . C1 1 " + " S+ C2-3:P1:S+ C2:P1 . C1 C1-3 . . . 1 " + + # A task cannot be added to a partition with no cpu + " S+ C2-3:P1:S+ C3:P1 . . O2-0:T . . . 1 A1:,A2:3 A1:P1,A2:P1" +) + +# +# Write to the cpu online file +# $1 - <c>-<v> where <c> = cpu number, <v> value to be written +# +write_cpu_online() +{ + CPU=${1%-*} + VAL=${1#*-} + CPUFILE=//sys/devices/system/cpu/cpu${CPU}/online + if [[ $VAL -eq 0 ]] + then + OFFLINE_CPUS="$OFFLINE_CPUS $CPU" + else + [[ -n "$OFFLINE_CPUS" ]] && { + OFFLINE_CPUS=$(echo $CPU $CPU $OFFLINE_CPUS | fmt -1 |\ + sort | uniq -u) + } + fi + echo $VAL > $CPUFILE + pause 0.01 +} + +# +# Set controller state +# $1 - cgroup directory +# $2 - state +# $3 - showerr +# +# The presence of ":" in state means transition from one to the next. +# +set_ctrl_state() +{ + TMPMSG=/tmp/.msg_$$ + CGRP=$1 + STATE=$2 + SHOWERR=${3}${VERBOSE} + CTRL=${CTRL:=$CONTROLLER} + HASERR=0 + REDIRECT="2> $TMPMSG" + [[ -z "$STATE" || "$STATE" = '.' ]] && return 0 + + rm -f $TMPMSG + for CMD in $(echo $STATE | sed -e "s/:/ /g") + do + TFILE=$CGRP/cgroup.procs + SFILE=$CGRP/cgroup.subtree_control + PFILE=$CGRP/cpuset.cpus.partition + CFILE=$CGRP/cpuset.cpus + S=$(expr substr $CMD 1 1) + if [[ $S = S ]] + then + PREFIX=${CMD#?} + COMM="echo ${PREFIX}${CTRL} > $SFILE" + eval $COMM $REDIRECT + elif [[ $S = C ]] + then + CPUS=${CMD#?} + COMM="echo $CPUS > $CFILE" + eval $COMM $REDIRECT + elif [[ $S = P ]] + then + VAL=${CMD#?} + case $VAL in + 0) VAL=member + ;; + 1) VAL=root + ;; + 2) VAL=isolated + ;; + *) + echo "Invalid partition state - $VAL" + exit 1 + ;; + esac + COMM="echo $VAL > $PFILE" + eval $COMM $REDIRECT + elif [[ $S = O ]] + then + VAL=${CMD#?} + write_cpu_online $VAL + elif [[ $S = T ]] + then + COMM="echo 0 > $TFILE" + eval $COMM $REDIRECT + fi + RET=$? + [[ $RET -ne 0 ]] && { + [[ -n "$SHOWERR" ]] && { + echo "$COMM" + cat $TMPMSG + } + HASERR=1 + } + pause 0.01 + rm -f $TMPMSG + done + return $HASERR +} + +set_ctrl_state_noerr() +{ + CGRP=$1 + STATE=$2 + [[ -d $CGRP ]] || mkdir $CGRP + set_ctrl_state $CGRP $STATE 1 + [[ $? -ne 0 ]] && { + echo "ERROR: Failed to set $2 to cgroup $1!" + exit 1 + } +} + +online_cpus() +{ + [[ -n "OFFLINE_CPUS" ]] && { + for C in $OFFLINE_CPUS + do + write_cpu_online ${C}-1 + done + } +} + +# +# Return 1 if the list of effective cpus isn't the same as the initial list. +# +reset_cgroup_states() +{ + echo 0 > $CGROUP2/cgroup.procs + online_cpus + rmdir A1/A2/A3 A1/A2 A1 B1 > /dev/null 2>&1 + set_ctrl_state . S- + pause 0.01 +} + +dump_states() +{ + for DIR in A1 A1/A2 A1/A2/A3 B1 + do + ECPUS=$DIR/cpuset.cpus.effective + PRS=$DIR/cpuset.cpus.partition + [[ -e $ECPUS ]] && echo "$ECPUS: $(cat $ECPUS)" + [[ -e $PRS ]] && echo "$PRS: $(cat $PRS)" + done +} + +# +# Check effective cpus +# $1 - check string, format: <cgroup>:<cpu-list>[,<cgroup>:<cpu-list>]* +# +check_effective_cpus() +{ + CHK_STR=$1 + for CHK in $(echo $CHK_STR | sed -e "s/,/ /g") + do + set -- $(echo $CHK | sed -e "s/:/ /g") + CGRP=$1 + CPUS=$2 + [[ $CGRP = A2 ]] && CGRP=A1/A2 + [[ $CGRP = A3 ]] && CGRP=A1/A2/A3 + FILE=$CGRP/cpuset.cpus.effective + [[ -e $FILE ]] || return 1 + [[ $CPUS = $(cat $FILE) ]] || return 1 + done +} + +# +# Check cgroup states +# $1 - check string, format: <cgroup>:<state>[,<cgroup>:<state>]* +# +check_cgroup_states() +{ + CHK_STR=$1 + for CHK in $(echo $CHK_STR | sed -e "s/,/ /g") + do + set -- $(echo $CHK | sed -e "s/:/ /g") + CGRP=$1 + STATE=$2 + FILE= + EVAL=$(expr substr $STATE 2 2) + [[ $CGRP = A2 ]] && CGRP=A1/A2 + [[ $CGRP = A3 ]] && CGRP=A1/A2/A3 + + case $STATE in + P*) FILE=$CGRP/cpuset.cpus.partition + ;; + *) echo "Unknown state: $STATE!" + exit 1 + ;; + esac + VAL=$(cat $FILE) + + case "$VAL" in + member) VAL=0 + ;; + root) VAL=1 + ;; + isolated) + VAL=2 + ;; + "root invalid"*) + VAL=-1 + ;; + "isolated invalid"*) + VAL=-2 + ;; + esac + [[ $EVAL != $VAL ]] && return 1 + done + return 0 +} + +# +# Run cpuset state transition test +# $1 - test matrix name +# +# This test is somewhat fragile as delays (sleep x) are added in various +# places to make sure state changes are fully propagated before the next +# action. These delays may need to be adjusted if running in a slower machine. +# +run_state_test() +{ + TEST=$1 + CONTROLLER=cpuset + CPULIST=0-6 + I=0 + eval CNT="${#$TEST[@]}" + + reset_cgroup_states + echo $CPULIST > cpuset.cpus + echo root > cpuset.cpus.partition + console_msg "Running state transition test ..." + + while [[ $I -lt $CNT ]] + do + echo "Running test $I ..." > /dev/console + eval set -- "${$TEST[$I]}" + ROOT=$1 + OLD_A1=$2 + OLD_A2=$3 + OLD_A3=$4 + OLD_B1=$5 + NEW_A1=$6 + NEW_A2=$7 + NEW_A3=$8 + NEW_B1=$9 + RESULT=${10} + ECPUS=${11} + STATES=${12} + + set_ctrl_state_noerr . $ROOT + set_ctrl_state_noerr A1 $OLD_A1 + set_ctrl_state_noerr A1/A2 $OLD_A2 + set_ctrl_state_noerr A1/A2/A3 $OLD_A3 + set_ctrl_state_noerr B1 $OLD_B1 + RETVAL=0 + set_ctrl_state A1 $NEW_A1; ((RETVAL += $?)) + set_ctrl_state A1/A2 $NEW_A2; ((RETVAL += $?)) + set_ctrl_state A1/A2/A3 $NEW_A3; ((RETVAL += $?)) + set_ctrl_state B1 $NEW_B1; ((RETVAL += $?)) + + [[ $RETVAL -ne $RESULT ]] && { + echo "Test $TEST[$I] failed result check!" + eval echo "${$TEST[$I]}" + dump_states + online_cpus + exit 1 + } + + [[ -n "$ECPUS" && "$ECPUS" != . ]] && { + check_effective_cpus $ECPUS + [[ $? -ne 0 ]] && { + echo "Test $TEST[$I] failed effective CPU check!" + eval echo "${$TEST[$I]}" + echo + dump_states + online_cpus + exit 1 + } + } + + [[ -n "$STATES" ]] && { + check_cgroup_states $STATES + [[ $? -ne 0 ]] && { + echo "FAILED: Test $TEST[$I] failed states check!" + eval echo "${$TEST[$I]}" + echo + dump_states + online_cpus + exit 1 + } + } + + reset_cgroup_states + # + # Check to see if effective cpu list changes + # + pause 0.05 + NEWLIST=$(cat cpuset.cpus.effective) + [[ $NEWLIST != $CPULIST ]] && { + echo "Effective cpus changed to $NEWLIST after test $I!" + exit 1 + } + [[ -n "$VERBOSE" ]] && echo "Test $I done." + ((I++)) + done + echo "All $I tests of $TEST PASSED." + + echo member > cpuset.cpus.partition +} + +# +# Wait for inotify event for the given file and read it +# $1: cgroup file to wait for +# $2: file to store the read result +# +wait_inotify() +{ + CGROUP_FILE=$1 + OUTPUT_FILE=$2 + + $WAIT_INOTIFY $CGROUP_FILE + cat $CGROUP_FILE > $OUTPUT_FILE +} + +# +# Test if inotify events are properly generated when going into and out of +# invalid partition state. +# +test_inotify() +{ + ERR=0 + PRS=/tmp/.prs_$$ + [[ -f $WAIT_INOTIFY ]] || { + echo "wait_inotify not found, inotify test SKIPPED." + return + } + + pause 0.01 + echo 1 > cpuset.cpus + echo 0 > cgroup.procs + echo root > cpuset.cpus.partition + pause 0.01 + rm -f $PRS + wait_inotify $PWD/cpuset.cpus.partition $PRS & + pause 0.01 + set_ctrl_state . "O1-0" + pause 0.01 + check_cgroup_states ".:P-1" + if [[ $? -ne 0 ]] + then + echo "FAILED: Inotify test - partition not invalid" + ERR=1 + elif [[ ! -f $PRS ]] + then + echo "FAILED: Inotify test - event not generated" + ERR=1 + kill %1 + elif [[ $(cat $PRS) != "root invalid"* ]] + then + echo "FAILED: Inotify test - incorrect state" + cat $PRS + ERR=1 + fi + online_cpus + echo member > cpuset.cpus.partition + echo 0 > ../cgroup.procs + if [[ $ERR -ne 0 ]] + then + exit 1 + else + echo "Inotify test PASSED" + fi +} + +run_state_test TEST_MATRIX +test_isolated +test_inotify +echo "All tests PASSED." +cd .. +rmdir test diff --git a/tools/testing/selftests/cgroup/wait_inotify.c b/tools/testing/selftests/cgroup/wait_inotify.c new file mode 100644 index 000000000000..e11b431e1b62 --- /dev/null +++ b/tools/testing/selftests/cgroup/wait_inotify.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Wait until an inotify event on the given cgroup file. + */ +#include <linux/limits.h> +#include <sys/inotify.h> +#include <sys/mman.h> +#include <sys/ptrace.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <errno.h> +#include <fcntl.h> +#include <poll.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +static const char usage[] = "Usage: %s [-v] <cgroup_file>\n"; +static char *file; +static int verbose; + +static inline void fail_message(char *msg) +{ + fprintf(stderr, msg, file); + exit(1); +} + +int main(int argc, char *argv[]) +{ + char *cmd = argv[0]; + int c, fd; + struct pollfd fds = { .events = POLLIN, }; + + while ((c = getopt(argc, argv, "v")) != -1) { + switch (c) { + case 'v': + verbose++; + break; + } + argv++, argc--; + } + + if (argc != 2) { + fprintf(stderr, usage, cmd); + return -1; + } + file = argv[1]; + fd = open(file, O_RDONLY); + if (fd < 0) + fail_message("Cgroup file %s not found!\n"); + close(fd); + + fd = inotify_init(); + if (fd < 0) + fail_message("inotify_init() fails on %s!\n"); + if (inotify_add_watch(fd, file, IN_MODIFY) < 0) + fail_message("inotify_add_watch() fails on %s!\n"); + fds.fd = fd; + + /* + * poll waiting loop + */ + for (;;) { + int ret = poll(&fds, 1, 10000); + + if (ret < 0) { + if (errno == EINTR) + continue; + perror("poll"); + exit(1); + } + if ((ret > 0) && (fds.revents & POLLIN)) + break; + } + if (verbose) { + struct inotify_event events[10]; + long len; + + usleep(1000); + len = read(fd, events, sizeof(events)); + printf("Number of events read = %ld\n", + len/sizeof(struct inotify_event)); + } + close(fd); + return 0; +}
On 5/10/22 8:34 PM, Waiman Long wrote:
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile index 745fe25fa0b9..01687418b92f 100644 --- a/tools/testing/selftests/cgroup/Makefile +++ b/tools/testing/selftests/cgroup/Makefile @@ -1,10 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -Wall -pthread -all: +all: ${HELPER_PROGS} TEST_FILES := with_stress.sh -TEST_PROGS := test_stress.sh +TEST_PROGS := test_stress.sh test_cpuset_prs.sh +TEST_GEN_FILES := wait_inotify
Please add wait_inotify to .gitignore file.
TEST_GEN_PROGS = test_memcontrol TEST_GEN_PROGS += test_kmem TEST_GEN_PROGS += test_core
On 5/21/22 06:24, Muhammad Usama Anjum wrote:
On 5/10/22 8:34 PM, Waiman Long wrote:
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile index 745fe25fa0b9..01687418b92f 100644 --- a/tools/testing/selftests/cgroup/Makefile +++ b/tools/testing/selftests/cgroup/Makefile @@ -1,10 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -Wall -pthread -all: +all: ${HELPER_PROGS} TEST_FILES := with_stress.sh -TEST_PROGS := test_stress.sh +TEST_PROGS := test_stress.sh test_cpuset_prs.sh +TEST_GEN_FILES := wait_inotify
Please add wait_inotify to .gitignore file.
TEST_GEN_PROGS = test_memcontrol TEST_GEN_PROGS += test_kmem TEST_GEN_PROGS += test_core
Right. Sorry for missing that. Will add it to the next version.
Thanks, Longman
On 2022-05-10 11:34:05 [-0400], Waiman Long wrote:
v11:
- Fix incorrect spacing in patch 7 and include documentation suggestions by Michal.
- Move partition_is_populated() check to the last one in list of conditions to be checked.
If I follow this correctly, then this is the latest version of the isolcpus= replacement with cgroup's cpusets, correct?
Sebastian
On 5/20/22 12:00, Sebastian Andrzej Siewior wrote:
On 2022-05-10 11:34:05 [-0400], Waiman Long wrote:
v11:
- Fix incorrect spacing in patch 7 and include documentation suggestions by Michal.
- Move partition_is_populated() check to the last one in list of conditions to be checked.
If I follow this correctly, then this is the latest version of the isolcpus= replacement with cgroup's cpusets, correct?
Sebastian
It is just the beginning, there is still a lot of work to do before isolcpus= can be completely replaced.
Cheers, Longman
On 2022-05-20 12:46:52 [-0400], Waiman Long wrote:
On 5/20/22 12:00, Sebastian Andrzej Siewior wrote:
On 2022-05-10 11:34:05 [-0400], Waiman Long wrote:
v11:
- Fix incorrect spacing in patch 7 and include documentation suggestions by Michal.
- Move partition_is_populated() check to the last one in list of conditions to be checked.
If I follow this correctly, then this is the latest version of the isolcpus= replacement with cgroup's cpusets, correct?
Sebastian
It is just the beginning, there is still a lot of work to do before isolcpus= can be completely replaced.
Okay. Thanks.
Cheers, Longman
Sebastian
linux-kselftest-mirror@lists.linaro.org
-
Michal Koutný -
Muhammad Usama Anjum -
Sebastian Andrzej Siewior -
Tejun Heo -
Waiman Long