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, 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 | 400 +++++++++++++++++++++-------------------- 1 file changed, 208 insertions(+), 192 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 7d9abd50a1b9..1f1d76013046 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 +1237,19 @@ 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. - * - * 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(). */ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, struct cpumask *newmask, @@ -1278,91 +1271,103 @@ 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 (partition_is_populated(parent, cs) && - cpumask_equal(cs->cpus_allowed, parent->effective_cpus)) - return -EINVAL; + !cpumask_intersects(cs->cpus_allowed, parent->effective_cpus)) + 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 && partition_is_populated(parent, cs) && - cpumask_equal(parent->effective_cpus, tmp->addmask)) { - 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); + cpumask_subset(parent->effective_cpus, tmp->addmask) && + !cpumask_intersects(tmp->delmask, cpu_active_mask)) { + 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. @@ -1377,27 +1382,21 @@ 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 @@ -1427,15 +1426,20 @@ 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. @@ -1444,7 +1448,8 @@ 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; @@ -1454,6 +1459,7 @@ 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);

@@ -1481,9 +1487,9 @@ 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; @@ -1499,33 +1505,15 @@ 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; @@ -1536,41 +1524,43 @@ 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() && @@ -1631,7 +1621,7 @@ 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); } @@ -1691,27 +1681,36 @@ 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 there is an error 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 (cs->prs_err || + (partition_is_populated(cs, NULL) && + cpumask_subset(trialcs->effective_cpus, cs->subparts_cpus))) { + 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); @@ -2097,7 +2096,7 @@ 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;

@@ -2105,24 +2104,25 @@ 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) @@ -2136,19 +2136,22 @@ 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); @@ -2161,15 +2164,24 @@ 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; }

/* @@ -3238,12 +3250,31 @@ 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; @@ -3252,40 +3283,25 @@ 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);

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 | 91 ++++++++++++++++++++++++++++++++++-------- 1 file changed, 74 insertions(+), 17 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 073db69ac8fc..90ee0e4d8d7e 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 @@ -1264,7 +1295,7 @@ 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);

@@ -1273,10 +1304,13 @@ 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; @@ -1286,7 +1320,7 @@ 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 @@ -1294,7 +1328,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, */ if (partition_is_populated(parent, cs) && !cpumask_intersects(cs->cpus_allowed, parent->effective_cpus)) - return -1; + return PERR_NOCPUS;

cpumask_copy(tmp->addmask, cs->cpus_allowed); adding = true; @@ -1330,7 +1364,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, if (adding && partition_is_populated(parent, cs) && cpumask_subset(parent->effective_cpus, tmp->addmask) && !cpumask_intersects(tmp->delmask, cpu_active_mask)) { - part_error = true; + part_error = PERR_NOCPUS; adding = false; deleting = cpumask_and(tmp->delmask, cs->cpus_allowed, parent->subparts_cpus); @@ -1362,7 +1396,7 @@ 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; }

@@ -1371,6 +1405,8 @@ 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) { /* @@ -1401,7 +1437,7 @@ 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; }

/* @@ -1534,6 +1570,9 @@ 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; } } @@ -2108,13 +2147,13 @@ 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; @@ -2141,13 +2180,15 @@ 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); @@ -2719,6 +2760,7 @@ 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: @@ -2731,9 +2773,17 @@ 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; } @@ -3324,7 +3374,7 @@ 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) { @@ -3336,10 +3386,17 @@ 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();

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; +}