The cpuset fields that manage partition root state do not strictly follow the cpuset locking rule that update to cpuset has to be done with both the callback_lock and cpuset_mutex held. This is now fixed by making sure that the locking rule is upheld.

Fixes: 3881b86128d0 ("cpuset: Add an error state to cpuset.sched.partition") Fixes: 4b842da276a8 ("cpuset: Make CPU hotplug work with partition) Signed-off-by: Waiman Long longman@redhat.com --- kernel/cgroup/cpuset.c | 58 +++++++++++++++++++++++++----------------- 1 file changed, 35 insertions(+), 23 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index b00982e6f6d8..04a6951abe2a 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1148,6 +1148,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, struct cpuset *parent = parent_cs(cpuset); int adding; /* Moving cpus from effective_cpus to subparts_cpus */ int deleting; /* Moving cpus from subparts_cpus to effective_cpus */ + int new_prs; bool part_error = false; /* Partition error? */

percpu_rwsem_assert_held(&cpuset_rwsem); @@ -1183,6 +1184,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, * A cpumask update cannot make parent's effective_cpus become empty. */ adding = deleting = false; + new_prs = cpuset->partition_root_state; if (cmd == partcmd_enable) { cpumask_copy(tmp->addmask, cpuset->cpus_allowed); adding = true; @@ -1247,11 +1249,11 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, switch (cpuset->partition_root_state) { case PRS_ENABLED: if (part_error) - cpuset->partition_root_state = PRS_ERROR; + new_prs = PRS_ERROR; break; case PRS_ERROR: if (!part_error) - cpuset->partition_root_state = PRS_ENABLED; + new_prs = PRS_ENABLED; break; } /* @@ -1260,10 +1262,10 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, part_error = (prev_prs == PRS_ERROR); }

- if (!part_error && (cpuset->partition_root_state == PRS_ERROR)) + if (!part_error && (new_prs == PRS_ERROR)) return 0; /* Nothing need to be done */

- if (cpuset->partition_root_state == PRS_ERROR) { + if (new_prs == PRS_ERROR) { /* * Remove all its cpus from parent's subparts_cpus. */ @@ -1272,7 +1274,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, parent->subparts_cpus); }

- if (!adding && !deleting) + if (!adding && !deleting && (new_prs == cpuset->partition_root_state)) return 0;

/* @@ -1299,6 +1301,9 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, }

parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus); + + if (cpuset->partition_root_state != new_prs) + cpuset->partition_root_state = new_prs; spin_unlock_irq(&callback_lock);

return cmd == partcmd_update; @@ -1321,6 +1326,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) struct cpuset *cp; struct cgroup_subsys_state *pos_css; bool need_rebuild_sched_domains = false; + int new_prs;

rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { @@ -1360,7 +1366,8 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) * update_tasks_cpumask() again for tasks in the parent * cpuset if the parent's subparts_cpus changes. */ - if ((cp != cs) && cp->partition_root_state) { + new_prs = cp->partition_root_state; + if ((cp != cs) && new_prs) { switch (parent->partition_root_state) { case PRS_DISABLED: /* @@ -1370,7 +1377,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) */ WARN_ON_ONCE(cp->partition_root_state != PRS_ERROR); - cp->partition_root_state = PRS_DISABLED; + new_prs = PRS_DISABLED;

/* * clear_bit() is an atomic operation and @@ -1391,11 +1398,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) /* * When parent is invalid, it has to be too. */ - cp->partition_root_state = PRS_ERROR; - if (cp->nr_subparts_cpus) { - cp->nr_subparts_cpus = 0; - cpumask_clear(cp->subparts_cpus); - } + new_prs = PRS_ERROR; break; } } @@ -1407,8 +1410,7 @@ 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 && - (cp->partition_root_state != PRS_ENABLED)) { + if (cp->nr_subparts_cpus && (new_prs != PRS_ENABLED)) { cp->nr_subparts_cpus = 0; cpumask_clear(cp->subparts_cpus); } else if (cp->nr_subparts_cpus) { @@ -1435,6 +1437,10 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) = cpumask_weight(cp->subparts_cpus); } } + + if (new_prs != cp->partition_root_state) + cp->partition_root_state = new_prs; + spin_unlock_irq(&callback_lock);

WARN_ON(!is_in_v2_mode() && @@ -1944,25 +1950,25 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, */ static int update_prstate(struct cpuset *cs, int new_prs) { - int err; + int err, old_prs = cs->partition_root_state; struct cpuset *parent = parent_cs(cs); struct tmpmasks tmpmask;

- if (new_prs == cs->partition_root_state) + if (old_prs == new_prs) return 0;

/* * Cannot force a partial or invalid partition root to a full * partition root. */ - if (new_prs && (cs->partition_root_state < 0)) + if (new_prs && (old_prs == PRS_ERROR)) return -EINVAL;

if (alloc_cpumasks(NULL, &tmpmask)) return -ENOMEM;

err = -EINVAL; - if (!cs->partition_root_state) { + if (!old_prs) { /* * Turning on partition root requires setting the * CS_CPU_EXCLUSIVE bit implicitly as well and cpus_allowed @@ -1981,14 +1987,12 @@ static int update_prstate(struct cpuset *cs, int new_prs) update_flag(CS_CPU_EXCLUSIVE, cs, 0); goto out; } - cs->partition_root_state = PRS_ENABLED; } else { /* * Turning off partition root will clear the * CS_CPU_EXCLUSIVE bit. */ - if (cs->partition_root_state == PRS_ERROR) { - cs->partition_root_state = PRS_DISABLED; + if (old_prs == PRS_ERROR) { update_flag(CS_CPU_EXCLUSIVE, cs, 0); err = 0; goto out; @@ -1999,8 +2003,6 @@ static int update_prstate(struct cpuset *cs, int new_prs) if (err) goto out;

- cs->partition_root_state = PRS_DISABLED; - /* Turning off CS_CPU_EXCLUSIVE will not return error */ update_flag(CS_CPU_EXCLUSIVE, cs, 0); } @@ -2017,6 +2019,12 @@ 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); + } + free_cpumasks(NULL, &tmpmask); return err; } @@ -3080,8 +3088,10 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) if (is_partition_root(cs) && (cpumask_empty(&new_cpus) || (parent->partition_root_state == PRS_ERROR))) { if (cs->nr_subparts_cpus) { + 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); }

@@ -3095,7 +3105,9 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) cpumask_empty(&new_cpus)) { update_parent_subparts_cpumask(cs, partcmd_disable, NULL, tmp); + spin_lock_irq(&callback_lock); cs->partition_root_state = PRS_ERROR; + spin_unlock_irq(&callback_lock); } cpuset_force_rebuild(); }

A valid cpuset partition can become invalid if all its CPUs are offlined or somehow removed. This can happen through external events without "cpuset.cpus.partition" being touched at all.

Users that rely on the property of a partition being present do not currently have a simple way to get such an event notified other than constant periodic polling which is both inefficient and cumbersome.

To make life easier for those users, event notification is now enabled for "cpuset.cpus.partition" when it goes into or out of an invalid partition state.

Suggested-by: Tejun Heo tj@kernel.org Signed-off-by: Waiman Long longman@redhat.com --- kernel/cgroup/cpuset.c | 49 ++++++++++++++++++++++++++++++++---------- 1 file changed, 38 insertions(+), 11 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 04a6951abe2a..2e34fc5b76f0 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -160,6 +160,9 @@ struct cpuset { */ int use_parent_ecpus; int child_ecpus_count; + + /* Handle for cpuset.cpus.partition */ + struct cgroup_file partition_file; };

/* @@ -263,6 +266,19 @@ static inline int is_partition_root(const struct cpuset *cs) return cs->partition_root_state > 0; }

+/* + * Send notification event of partition_root_state change when going into + * or out of PRS_ERROR which may be due to an external event like hotplug. + */ +static inline void notify_partition_change(struct cpuset *cs, + int old_prs, int new_prs) +{ + if ((old_prs == new_prs) || + ((old_prs != PRS_ERROR) && (new_prs != PRS_ERROR))) + return; + cgroup_file_notify(&cs->partition_file); +} + static struct cpuset top_cpuset = { .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), @@ -1148,7 +1164,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, struct cpuset *parent = parent_cs(cpuset); int adding; /* Moving cpus from effective_cpus to subparts_cpus */ int deleting; /* Moving cpus from subparts_cpus to effective_cpus */ - int new_prs; + int old_prs, new_prs; bool part_error = false; /* Partition error? */

percpu_rwsem_assert_held(&cpuset_rwsem); @@ -1184,7 +1200,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, * A cpumask update cannot make parent's effective_cpus become empty. */ adding = deleting = false; - new_prs = cpuset->partition_root_state; + old_prs = new_prs = cpuset->partition_root_state; if (cmd == partcmd_enable) { cpumask_copy(tmp->addmask, cpuset->cpus_allowed); adding = true; @@ -1274,7 +1290,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, parent->subparts_cpus); }

- if (!adding && !deleting && (new_prs == cpuset->partition_root_state)) + if (!adding && !deleting && (new_prs == old_prs)) return 0;

/* @@ -1302,9 +1318,11 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,

parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus);

- if (cpuset->partition_root_state != new_prs) + if (old_prs != new_prs) cpuset->partition_root_state = new_prs; + spin_unlock_irq(&callback_lock); + notify_partition_change(cpuset, old_prs, new_prs);

return cmd == partcmd_update; } @@ -1326,7 +1344,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) struct cpuset *cp; struct cgroup_subsys_state *pos_css; bool need_rebuild_sched_domains = false; - int new_prs; + int old_prs, new_prs;

rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { @@ -1366,8 +1384,8 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) * update_tasks_cpumask() again for tasks in the parent * cpuset if the parent's subparts_cpus changes. */ - new_prs = cp->partition_root_state; - if ((cp != cs) && new_prs) { + old_prs = new_prs = cp->partition_root_state; + if ((cp != cs) && old_prs) { switch (parent->partition_root_state) { case PRS_DISABLED: /* @@ -1438,10 +1456,11 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) } }

- if (new_prs != cp->partition_root_state) + if (new_prs != old_prs) cp->partition_root_state = new_prs;

spin_unlock_irq(&callback_lock); + notify_partition_change(cp, old_prs, new_prs);

WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); @@ -2023,6 +2042,7 @@ 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); }

free_cpumasks(NULL, &tmpmask); @@ -2708,6 +2728,7 @@ static struct cftype dfl_files[] = { .write = sched_partition_write, .private = FILE_PARTITION_ROOT, .flags = CFTYPE_NOT_ON_ROOT, + .file_offset = offsetof(struct cpuset, partition_file), },

{ @@ -3103,11 +3124,17 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) */ if ((parent->partition_root_state == PRS_ERROR) || cpumask_empty(&new_cpus)) { + int old_prs; + update_parent_subparts_cpumask(cs, partcmd_disable, NULL, tmp); - spin_lock_irq(&callback_lock); - cs->partition_root_state = PRS_ERROR; - spin_unlock_irq(&callback_lock); + old_prs = cs->partition_root_state; + if (old_prs != PRS_ERROR) { + spin_lock_irq(&callback_lock); + cs->partition_root_state = PRS_ERROR; + spin_unlock_irq(&callback_lock); + notify_partition_change(cs, old_prs, PRS_ERROR); + } } cpuset_force_rebuild(); }

For cpuset partition, the special state of PRS_ERROR (invalid partition root) was originally designed to handle hotplug events. In this state, CPUs allocated to the partition root is released back to the parent but the cpuset exclusive flags remain unchanged.

Since partition root sets the CPU_EXCLUSIVE flag, cpuset.cpus changes that break the cpu exclusivity rule will not be allowed. However, other changes to cpuset.cpus on a partition root may still cause it to become invalid. This is undesriable as we don't want accidental change to cpuset.cpus to invalidate a partition root.

Additional checks are now added to make sure that regular cpuset control file manipulations are not allowed to make a partition root invalid. These additional checks are:

1) A partition root can't be changed to member if it has child partition roots. 2) Removing CPUs from cpuset.cpus that causes it to become invalid is not allowed.

Comments are also added to clarify that a partition root becomes invalid only when an external event like hotplug that causes all the CPUs allocated to a partition root to become unavailable.

Signed-off-by: Waiman Long longman@redhat.com --- kernel/cgroup/cpuset.c | 144 ++++++++++++++++++++++++----------------- 1 file changed, 86 insertions(+), 58 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 2e34fc5b76f0..c16060b703cc 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -177,7 +177,9 @@ struct cpuset { * 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. + * parent cpuset can give more CPUs back to this child cpuset. A + * partition root becomes invalid when all its cpus become unavailable + * like being offlined. */ #define PRS_DISABLED 0 #define PRS_ENABLED 1 @@ -1211,6 +1213,15 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, /* * partcmd_update with newmask: * + * Return error if newmask isn't a subset of + * (cpus_allowed | parent->effective_cpus). + */ + cpumask_or(tmp->addmask, cpuset->cpus_allowed, + parent->effective_cpus); + if (!cpumask_subset(newmask, tmp->addmask)) + return -EINVAL; + + /* * delmask = cpus_allowed & ~newmask & parent->subparts_cpus * addmask = newmask & parent->effective_cpus * & ~parent->subparts_cpus @@ -1223,7 +1234,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, 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 parent's effective_cpus could become empty. */ if (adding && cpumask_equal(parent->effective_cpus, tmp->addmask)) { @@ -1239,20 +1250,35 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, return -EINVAL; cpumask_copy(tmp->addmask, parent->effective_cpus); } + + /* + * Return error if effective_cpus becomes empty or any CPU + * distributed to child partitions is deleted. + */ + if (deleting && + (cpumask_intersects(tmp->delmask, cpuset->subparts_cpus) || + cpumask_equal(tmp->delmask, cpuset->effective_cpus))) + return -EBUSY; } else { /* * partcmd_update w/o newmask: * * addmask = cpus_allowed & parent->effective_cpus * + * This gets invoked either due to a hotplug event or + * from update_cpumasks_hier() where we can't return an + * error. This can cause a partition root to become invalid + * in the case of a hotplug. + * * 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. */ adding = cpumask_and(tmp->addmask, cpuset->cpus_allowed, parent->effective_cpus); - part_error = cpumask_equal(tmp->addmask, - parent->effective_cpus); + part_error = (is_partition_root(cpuset) && + !parent->nr_subparts_cpus) || + cpumask_equal(tmp->addmask, parent->effective_cpus); }

if (cmd == partcmd_update) { @@ -1427,33 +1453,27 @@ 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)) { + /* + * 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. + * of a partition root are mutually exclusive. */ 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); - } + WARN_ON_ONCE(cpumask_empty(cp->effective_cpus)); }

if (new_prs != old_prs) @@ -1462,7 +1482,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) spin_unlock_irq(&callback_lock); notify_partition_change(cp, old_prs, new_prs);

- WARN_ON(!is_in_v2_mode() && + WARN_ON_ONCE(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus));

update_tasks_cpumask(cp); @@ -1585,8 +1605,8 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, * Make sure that subparts_cpus is a subset of cpus_allowed. */ if (cs->nr_subparts_cpus) { - cpumask_andnot(cs->subparts_cpus, cs->subparts_cpus, - cs->cpus_allowed); + 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); @@ -2008,20 +2028,26 @@ static int update_prstate(struct cpuset *cs, int new_prs) } } else { /* - * Turning off partition root will clear the - * CS_CPU_EXCLUSIVE bit. + * Switch back to member is always allowed if PRS_ERROR. */ if (old_prs == PRS_ERROR) { - update_flag(CS_CPU_EXCLUSIVE, cs, 0); err = 0; - goto out; + goto reset_flag; }

+ /* + * A partition root cannot be reverted to member if some + * CPUs have been distributed to child partition roots. + */ + if (!cpumask_empty(cs->subparts_cpus)) + return -EBUSY; + err = update_parent_subparts_cpumask(cs, partcmd_disable, NULL, &tmpmask); if (err) goto out;

+reset_flag: /* Turning off CS_CPU_EXCLUSIVE will not return error */ update_flag(CS_CPU_EXCLUSIVE, cs, 0); } @@ -3103,11 +3129,28 @@ 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, we will have to force any child partitions, + * if present, to become invalid by setting nr_subparts_cpus to 0 + * without causing itself to become invalid. + */ + if (is_partition_root(cs) && cs->nr_subparts_cpus && + cpumask_empty(&new_cpus)) { + cs->nr_subparts_cpus = 0; + cpumask_clear(cs->subparts_cpus); + compute_effective_cpumask(&new_cpus, cs, parent); + } + + /* + * If empty effective_cpus or zero nr_subparts_cpus or its parent + * becomes erroneous, we have to transition it to the erroneous state. */ if (is_partition_root(cs) && (cpumask_empty(&new_cpus) || - (parent->partition_root_state == PRS_ERROR))) { + (parent->partition_root_state == PRS_ERROR) || + !parent->nr_subparts_cpus)) { + 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; @@ -3116,38 +3159,23 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) compute_effective_cpumask(&new_cpus, cs, parent); }

- /* - * 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. - */ - if ((parent->partition_root_state == PRS_ERROR) || - 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) { - spin_lock_irq(&callback_lock); - cs->partition_root_state = PRS_ERROR; - spin_unlock_irq(&callback_lock); - notify_partition_change(cs, old_prs, PRS_ERROR); - } + old_prs = cs->partition_root_state; + if (old_prs != PRS_ERROR) { + spin_lock_irq(&callback_lock); + cs->partition_root_state = PRS_ERROR; + spin_unlock_irq(&callback_lock); + notify_partition_change(cs, old_prs, PRS_ERROR); } cpuset_force_rebuild(); }

/* * On the other hand, an erroneous 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. + * back to a regular one. */ - if (is_partition_root(parent) && - ((cs->partition_root_state == PRS_ERROR) || - !cpumask_intersects(&new_cpus, parent->subparts_cpus)) && - update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp)) + else if (is_partition_root(parent) && + (cs->partition_root_state == PRS_ERROR) && + update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp)) cpuset_force_rebuild();

update_tasks:

Currently, a parent partition root cannot distribute all its CPUs to child partition roots with no CPUs left. However in some use cases, a management application may want to create a parent partition root as a management unit with no task associated with it and has all its CPUs distributed to various child partition roots dynamically according to their needs. Leaving a cpu in the parent partition root in such a case is now a waste.

To accommodate such use cases, a parent partition root can now have all its CPUs distributed to its child partition roots as long as: 1) it is not the top cpuset; and 2) there is no task directly associated with the parent.

Once an empty parent partition root is formed, no new task can be moved into it.

Signed-off-by: Waiman Long longman@redhat.com --- kernel/cgroup/cpuset.c | 90 +++++++++++++++++++++++++++++------------- 1 file changed, 63 insertions(+), 27 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 60562346ecc1..d4d0c091a0d3 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -284,6 +284,11 @@ static inline void notify_partition_change(struct cpuset *cs, cgroup_file_notify(&cs->partition_file); }

+static inline int cpuset_has_tasks(const struct cpuset *cs) +{ + return cs->css.cgroup->nr_populated_csets; +} + static struct cpuset top_cpuset = { .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), @@ -1191,22 +1196,32 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, if ((cmd != partcmd_update) && css_has_online_children(&cpuset->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(cpuset->cpus_allowed, parent->effective_cpus) || - cpumask_equal(cpuset->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; if (cmd == partcmd_enable) { + bool parent_is_top_cpuset = !parent_cs(parent); + bool no_cpu_in_parent = cpumask_equal(cpuset->cpus_allowed, + parent->effective_cpus); + /* + * Enabling partition root is not allowed if not all the CPUs + * can be granted from parent's effective_cpus. If the parent + * is the top cpuset, at least one CPU must be left after that. + */ + if (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) || + (parent_is_top_cpuset && no_cpu_in_parent)) + return -EINVAL; + + /* + * A non-top parent can be left with no CPU as long as there + * is no task directly associated with the parent. For such + * a parent, no new task can be moved into it. + */ + if (no_cpu_in_parent && cpuset_has_tasks(parent)) + return -EINVAL; + cpumask_copy(tmp->addmask, cpuset->cpus_allowed); adding = true; } else if (cmd == partcmd_disable) { @@ -1237,9 +1252,10 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, adding = cpumask_andnot(tmp->addmask, tmp->addmask, parent->subparts_cpus); /* - * Return error if parent's effective_cpus could become empty. + * Return error if parent's effective_cpus could become empty + * and there are tasks in the parent. */ - if (adding && + if (adding && cpuset_has_tasks(parent) && cpumask_equal(parent->effective_cpus, tmp->addmask)) { if (!deleting) return -EINVAL; @@ -1255,12 +1271,13 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, }

/* - * Return error if effective_cpus becomes empty or any CPU - * distributed to child partitions is deleted. + * Return error if effective_cpus becomes empty with tasks + * or any CPU distributed to child partitions is deleted. */ if (deleting && (cpumask_intersects(tmp->delmask, cpuset->subparts_cpus) || - cpumask_equal(tmp->delmask, cpuset->effective_cpus))) + (cpumask_equal(tmp->delmask, cpuset->effective_cpus) && + cpuset_has_tasks(cpuset)))) return -EBUSY; } else { /* @@ -1281,7 +1298,8 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, parent->effective_cpus); part_error = (is_partition_root(cpuset) && !parent->nr_subparts_cpus) || - cpumask_equal(tmp->addmask, parent->effective_cpus); + (cpumask_equal(tmp->addmask, parent->effective_cpus) && + cpuset_has_tasks(parent)); }

if (cmd == partcmd_update) { @@ -1388,9 +1406,15 @@ 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_root(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; @@ -1412,6 +1436,7 @@ 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 @@ -1482,7 +1507,8 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) */ cpumask_andnot(cp->effective_cpus, cp->effective_cpus, cp->subparts_cpus); - WARN_ON_ONCE(cpumask_empty(cp->effective_cpus)); + WARN_ON_ONCE(cpumask_empty(cp->effective_cpus) && + cpuset_has_tasks(cp)); }

if (new_prs != old_prs) @@ -1816,7 +1842,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) cp->effective_mems = *new_mems; spin_unlock_irq(&callback_lock);

- WARN_ON(!is_in_v2_mode() && + WARN_ON_ONCE(!is_in_v2_mode() && !nodes_equal(cp->mems_allowed, cp->effective_mems));

update_tasks_nodemask(cp); @@ -2231,6 +2257,13 @@ 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) @@ -3098,7 +3131,8 @@ 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_root(cs)) cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus); if (nodes_empty(*new_mems)) *new_mems = parent_cs(cs)->effective_mems; @@ -3167,22 +3201,24 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)

/* * In the unlikely event that a partition root has empty - * effective_cpus, we will have to force any child partitions, - * if present, to become invalid by setting nr_subparts_cpus to 0 - * without causing itself to become invalid. + * effective_cpus with tasks, we will have to force any child + * partitions, if present, to become invalid by setting + * nr_subparts_cpus to 0 without causing itself to become invalid. */ if (is_partition_root(cs) && cs->nr_subparts_cpus && - cpumask_empty(&new_cpus)) { + cpumask_empty(&new_cpus) && cpuset_has_tasks(cs)) { cs->nr_subparts_cpus = 0; cpumask_clear(cs->subparts_cpus); compute_effective_cpumask(&new_cpus, cs, parent); }

/* - * If empty effective_cpus or zero nr_subparts_cpus or its parent - * becomes erroneous, we have to transition it to the erroneous state. + * If empty effective_cpus with tasks or zero nr_subparts_cpus or + * its parent becomes erroneous, we have to transition it to the + * erroneous state. */ - if (is_partition_root(cs) && (cpumask_empty(&new_cpus) || + if (is_partition_root(cs) && + ((cpumask_empty(&new_cpus) && cpuset_has_tasks(cs)) || (parent->partition_root_state == PRS_ERROR) || !parent->nr_subparts_cpus)) { int old_prs;

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 | 626 ++++++++++++++++++ tools/testing/selftests/cgroup/wait_inotify.c | 67 ++ 3 files changed, 696 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 59e222460581..3f1fd3f93f41 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..5a99f7048910 --- /dev/null +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -0,0 +1,626 @@ +#!/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 +VERBOSE= +[[ "$1" = -v ]] && VERBOSE=1 + +cd $CGROUP2 +echo +cpuset > cgroup.subtree_control +[[ -d test ]] || mkdir test +cd test + +console_msg() +{ + MSG=$1 + echo "$MSG" + echo "" > /dev/console + echo "$MSG" > /dev/console + sleep 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+ $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 + # ---- ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ + # Failure cases: + + # To become a partition root, cpuset.cpus must be a subset of + # parent's cpuset.cpus.effective. + " S+ C0-1 . . C2-3 S+ C4-5:P1 . . 1 " + + # A cpuset cannot become a partition root if it has child cpusets + # with non-empty cpuset.cpus. + " S+ C0-1:S+ C1 . C2-3 P1 . . . 1 " + + # 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 " + + # Deletion of CPUs distributed to child partition root is not allowed. + " S+ C0-1:P1:S+ C1 . C2-3 C4-5 . . . 1 " + " S+ C0-3:P1:S+ C2-3:P1 . . C0-2 . . . 1 " + + # Adding CPUs to partition root that are not in parent's + # cpuset.cpus.effective is not allowed. + " S+ C2-3:P1:S+ C3:P1 . . . C2-4 . . 1 " + + # Taking away all CPUs from parent or itself is not allowed if there are tasks. + " S+ C2-3:P1:S+ C3:P1 . . T C2-3 . . 1 A1:2,A2:3" + " S+ C1-3:P1:S+ C2-3:P1:S+ + C3:P1 . T:C2-3 . . . 1 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1" + + # A partition root cannot change to member if it has child partition. + " S+ C2-3:P1:S+ C3:P1 . . P0 . . . 1 " + " S+ $SETUP_A123_PARTITIONS . C2-3 P0 . . 1 A1:,A2:2,A3:3 A1:P1,A2:P1,A3:P1" + + # 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" + " S+ C2-3:P1:S+ C3:P1 . . O3-0 T . . 1 A1:2,A2: 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 + sleep 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 partiton 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 + } + sleep 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 > $CGROUP2/cgroup.procs + online_cpus + rmdir A1/A2/A3 A1/A2 A1 B1 > /dev/null 2>&1 + set_ctrl_state . S- + sleep 0.005 # 5ms artificial delay to complete the deletion +} + +dump_states() +{ + for DIR in A1 A1/A2 A1/A2/A3 B1 + do + ECPUS=$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 + ;; + 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=$1 + CONTROLLER=cpuset + I=0 + CPULIST=0-6 + eval CNT="${#$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[$I]}" + online_cpus + exit 1 + } + + [[ -n "$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[$I]}" + echo + dump_states + online_cpus + exit 1 + } + } + + reset_cgroup_states + [[ -n "$VERBOSE" ]] && echo "Test $I done." + ((I++)) + done + echo "All $I tests of $TEST PASSED." + + # + # Check to see if the effective cpu list changes + # + sleep 0.05 + NEWLIST=$(cat cpuset.cpus.effective) + [[ $NEWLIST != $CPULIST ]] && { + echo "Effective cpus changed to $NEWLIST!" + } + 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 + } + + sleep 0.01 + echo 1 > cpuset.cpus + echo 0 > cgroup.procs + echo root > cpuset.cpus.partition + sleep 0.01 + rm -f $PRS + wait_inotify $PWD/cpuset.cpus.partition $PRS & + sleep 0.01 + set_ctrl_state . "O1-0" + sleep 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..a6f80d008b4b --- /dev/null +++ b/tools/testing/selftests/cgroup/wait_inotify.c @@ -0,0 +1,67 @@ +/* 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> + +const char usage[] = "Usage: %s <cgroup_file>\n"; +static char *file; + +static inline void fail_message(char *msg) +{ + fprintf(stderr, msg, file); + exit(1); +} + +int main(int argc, char *argv[]) +{ + char *cmd = argv[0]; + int fd; + struct pollfd fds = { .events = POLLIN, }; + + 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_init() 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; + } + close(fd); + return 0; +}