diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c22cda7..be1d71d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2608,6 +2608,7 @@ static void cgroup_migrate_add_task(struct task_struct *task, mgctx->tset.nr_tasks++; + css_set_skip_task_iters(cset, task); list_move_tail(&task->cg_list, &cset->mg_tasks); if (list_empty(&cset->mg_node)) list_add_tail(&cset->mg_node, diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 9faf343..e200de7 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -62,6 +62,75 @@ static const char * const perr_strings[] = { }; /* + * CPUSET Locking Convention + * ------------------------- + * + * Below are the four global/local locks guarding cpuset structures in lock + * acquisition order: + * - cpuset_top_mutex + * - cpu_hotplug_lock (cpus_read_lock/cpus_write_lock) + * - cpuset_mutex + * - callback_lock (raw spinlock) + * + * As cpuset will now indirectly flush a number of different workqueues in + * housekeeping_update() to update housekeeping cpumasks when the set of + * isolated CPUs is going to be changed, it may be vulnerable to deadlock + * if we hold cpus_read_lock while calling into housekeeping_update(). + * + * The first cpuset_top_mutex will be held except when calling into + * cpuset_handle_hotplug() from the CPU hotplug code where cpus_write_lock + * and cpuset_mutex will be held instead. The main purpose of this mutex + * is to prevent regular cpuset control file write actions from interfering + * with the call to housekeeping_update(), though CPU hotplug operation can + * still happen in parallel. This mutex also provides protection for some + * internal variables. + * + * A task must hold all the remaining three locks to modify externally visible + * or used fields of cpusets, though some of the internally used cpuset fields + * and internal variables can be modified without holding callback_lock. If only + * reliable read access of the externally used fields are needed, a task can + * hold either cpuset_mutex or callback_lock which are exposed to other + * external subsystems. + * + * If a task holds cpu_hotplug_lock and cpuset_mutex, it blocks others, + * ensuring that it is the only task able to also acquire callback_lock and + * be able to modify cpusets. It can perform various checks on the cpuset + * structure first, knowing nothing will change. It can also allocate memory + * without holding callback_lock. While it is performing these checks, various + * callback routines can briefly acquire callback_lock to query cpusets. Once + * it is ready to make the changes, it takes callback_lock, blocking everyone + * else. + * + * Calls to the kernel memory allocator cannot be made while holding + * callback_lock which is a spinlock, as the memory allocator may sleep or + * call back into cpuset code and acquire callback_lock. + * + * Now, the task_struct fields mems_allowed and mempolicy may be changed + * by other task, we use alloc_lock in the task_struct fields to protect + * them. + * + * The cpuset_common_seq_show() handlers only hold callback_lock across + * small pieces of code, such as when reading out possibly multi-word + * cpumasks and nodemasks. + */ + +static DEFINE_MUTEX(cpuset_top_mutex); +static DEFINE_MUTEX(cpuset_mutex); + +/* + * File level internal variables below follow one of the following exclusion + * rules. + * + * RWCS: Read/write-able by holding either cpus_write_lock (and optionally + * cpuset_mutex) or both cpus_read_lock and cpuset_mutex. + * + * CSCB: Readable by holding either cpuset_mutex or callback_lock. Writable + * by holding both cpuset_mutex and callback_lock. + * + * T: Read/write-able by holding the cpuset_top_mutex. + */ + +/* * For local partitions, update to subpartitions_cpus & isolated_cpus is done * in update_parent_effective_cpumask(). For remote partitions, it is done in * the remote_partition_*() and remote_cpus_update() helpers. @@ -70,19 +139,22 @@ static const char * const perr_strings[] = { * Exclusive CPUs distributed out to local or remote sub-partitions of * top_cpuset */ -static cpumask_var_t subpartitions_cpus; +static cpumask_var_t subpartitions_cpus; /* RWCS */ + +/* + * Exclusive CPUs in isolated partitions (shown in cpuset.cpus.isolated) + */ +static cpumask_var_t isolated_cpus; /* CSCB */ /* - * Exclusive CPUs in isolated partitions + * Set if housekeeping cpumasks are to be updated. */ -static cpumask_var_t isolated_cpus; +static bool update_housekeeping; /* RWCS */ /* - * isolated_cpus updating flag (protected by cpuset_mutex) - * Set if isolated_cpus is going to be updated in the current - * cpuset_mutex crtical section. + * Copy of isolated_cpus to be passed to housekeeping_update() */ -static bool isolated_cpus_updating; +static cpumask_var_t isolated_hk_cpus; /* T */ /* * A flag to force sched domain rebuild at the end of an operation. @@ -98,7 +170,7 @@ static bool isolated_cpus_updating; * Note that update_relax_domain_level() in cpuset-v1.c can still call * rebuild_sched_domains_locked() directly without using this flag. */ -static bool force_sd_rebuild; +static bool force_sd_rebuild; /* RWCS */ /* * Partition root states: @@ -218,42 +290,6 @@ struct cpuset top_cpuset = { .partition_root_state = PRS_ROOT, }; -/* - * There are two global locks guarding cpuset structures - cpuset_mutex and - * callback_lock. The cpuset code uses only cpuset_mutex. Other kernel - * subsystems can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset - * structures. Note that cpuset_mutex needs to be a mutex as it is used in - * paths that rely on priority inheritance (e.g. scheduler - on RT) for - * correctness. - * - * A task must hold both locks to modify cpusets. If a task holds - * cpuset_mutex, it blocks others, ensuring that it is the only task able to - * also acquire callback_lock and be able to modify cpusets. It can perform - * various checks on the cpuset structure first, knowing nothing will change. - * It can also allocate memory while just holding cpuset_mutex. While it is - * performing these checks, various callback routines can briefly acquire - * callback_lock to query cpusets. Once it is ready to make the changes, it - * takes callback_lock, blocking everyone else. - * - * Calls to the kernel memory allocator can not be made while holding - * callback_lock, as that would risk double tripping on callback_lock - * from one of the callbacks into the cpuset code from within - * __alloc_pages(). - * - * If a task is only holding callback_lock, then it has read-only - * access to cpusets. - * - * Now, the task_struct fields mems_allowed and mempolicy may be changed - * by other task, we use alloc_lock in the task_struct fields to protect - * them. - * - * The cpuset_common_seq_show() handlers only hold callback_lock across - * small pieces of code, such as when reading out possibly multi-word - * cpumasks and nodemasks. - */ - -static DEFINE_MUTEX(cpuset_mutex); - /** * cpuset_lock - Acquire the global cpuset mutex * @@ -283,6 +319,7 @@ void lockdep_assert_cpuset_lock_held(void) */ void cpuset_full_lock(void) { + mutex_lock(&cpuset_top_mutex); cpus_read_lock(); mutex_lock(&cpuset_mutex); } @@ -291,12 +328,14 @@ void cpuset_full_unlock(void) { mutex_unlock(&cpuset_mutex); cpus_read_unlock(); + mutex_unlock(&cpuset_top_mutex); } #ifdef CONFIG_LOCKDEP bool lockdep_is_cpuset_held(void) { - return lockdep_is_held(&cpuset_mutex); + return lockdep_is_held(&cpuset_mutex) || + lockdep_is_held(&cpuset_top_mutex); } #endif @@ -961,7 +1000,7 @@ void rebuild_sched_domains_locked(void) * offline CPUs, a warning is emitted and we return directly to * prevent the panic. */ - for (i = 0; i < ndoms; ++i) { + for (i = 0; doms && i < ndoms; i++) { if (WARN_ON_ONCE(!cpumask_subset(doms[i], cpu_active_mask))) return; } @@ -1161,12 +1200,18 @@ static void reset_partition_data(struct cpuset *cs) static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus) { WARN_ON_ONCE(old_prs == new_prs); - if (new_prs == PRS_ISOLATED) + lockdep_assert_held(&callback_lock); + lockdep_assert_held(&cpuset_mutex); + if (new_prs == PRS_ISOLATED) { + if (cpumask_subset(xcpus, isolated_cpus)) + return; cpumask_or(isolated_cpus, isolated_cpus, xcpus); - else + } else { + if (!cpumask_intersects(xcpus, isolated_cpus)) + return; cpumask_andnot(isolated_cpus, isolated_cpus, xcpus); - - isolated_cpus_updating = true; + } + update_housekeeping = true; } /* @@ -1219,8 +1264,8 @@ static void partition_xcpus_del(int old_prs, struct cpuset *parent, isolated_cpus_update(old_prs, parent->partition_root_state, xcpus); - cpumask_and(xcpus, xcpus, cpu_active_mask); cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus); + cpumask_and(parent->effective_cpus, parent->effective_cpus, cpu_active_mask); } /* @@ -1284,22 +1329,43 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus) } /* - * update_isolation_cpumasks - Update external isolation related CPU masks + * update_hk_sched_domains - Update HK cpumasks & rebuild sched domains * - * The following external CPU masks will be updated if necessary: - * - workqueue unbound cpumask + * Update housekeeping cpumasks and rebuild sched domains if necessary. + * This should be called at the end of cpuset or hotplug actions. */ -static void update_isolation_cpumasks(void) +static void update_hk_sched_domains(void) { - int ret; - - if (!isolated_cpus_updating) - return; + if (update_housekeeping) { + /* Updating HK cpumasks implies rebuild sched domains */ + update_housekeeping = false; + force_sd_rebuild = true; + cpumask_copy(isolated_hk_cpus, isolated_cpus); - ret = housekeeping_update(isolated_cpus); - WARN_ON_ONCE(ret < 0); + /* + * housekeeping_update() is now called without holding + * cpus_read_lock and cpuset_mutex. Only cpuset_top_mutex + * is still being held for mutual exclusion. + */ + mutex_unlock(&cpuset_mutex); + cpus_read_unlock(); + WARN_ON_ONCE(housekeeping_update(isolated_hk_cpus)); + cpus_read_lock(); + mutex_lock(&cpuset_mutex); + } + /* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */ + if (force_sd_rebuild) + rebuild_sched_domains_locked(); +} - isolated_cpus_updating = false; +/* + * Work function to invoke update_hk_sched_domains() + */ +static void hk_sd_workfn(struct work_struct *work) +{ + cpuset_full_lock(); + update_hk_sched_domains(); + cpuset_full_unlock(); } /** @@ -1450,7 +1516,6 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs, cs->remote_partition = true; cpumask_copy(cs->effective_xcpus, tmp->new_cpus); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); cpuset_force_rebuild(); cs->prs_err = 0; @@ -1495,7 +1560,6 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp) compute_excpus(cs, cs->effective_xcpus); reset_partition_data(cs); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); cpuset_force_rebuild(); /* @@ -1566,7 +1630,6 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus, if (xcpus) cpumask_copy(cs->exclusive_cpus, xcpus); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); if (adding || deleting) cpuset_force_rebuild(); @@ -1910,7 +1973,6 @@ write_error: partition_xcpus_add(new_prs, parent, tmp->delmask); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); if ((old_prs != new_prs) && (cmd == partcmd_update)) update_partition_exclusive_flag(cs, new_prs); @@ -2155,7 +2217,7 @@ get_css: WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); - cpuset_update_tasks_cpumask(cp, cp->effective_cpus); + cpuset_update_tasks_cpumask(cp, tmp->new_cpus); /* * On default hierarchy, inherit the CS_SCHED_LOAD_BALANCE @@ -2878,7 +2940,6 @@ out: else if (isolcpus_updated) isolated_cpus_update(old_prs, new_prs, cs->effective_xcpus); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); /* Force update if switching back to member & update effective_xcpus */ update_cpumasks_hier(cs, &tmpmask, !new_prs); @@ -3168,9 +3229,8 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of, } free_cpuset(trialcs); - if (force_sd_rebuild) - rebuild_sched_domains_locked(); out_unlock: + update_hk_sched_domains(); cpuset_full_unlock(); if (of_cft(of)->private == FILE_MEMLIST) schedule_flush_migrate_mm(); @@ -3278,6 +3338,7 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf, cpuset_full_lock(); if (is_cpuset_online(cs)) retval = update_prstate(cs, val); + update_hk_sched_domains(); cpuset_full_unlock(); return retval ?: nbytes; } @@ -3452,6 +3513,7 @@ static void cpuset_css_killed(struct cgroup_subsys_state *css) /* Reset valid partition back to member */ if (is_partition_valid(cs)) update_prstate(cs, PRS_MEMBER); + update_hk_sched_domains(); cpuset_full_unlock(); } @@ -3607,6 +3669,7 @@ int __init cpuset_init(void) BUG_ON(!alloc_cpumask_var(&top_cpuset.exclusive_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&subpartitions_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&isolated_cpus, GFP_KERNEL)); + BUG_ON(!zalloc_cpumask_var(&isolated_hk_cpus, GFP_KERNEL)); cpumask_setall(top_cpuset.cpus_allowed); nodes_setall(top_cpuset.mems_allowed); @@ -3778,6 +3841,7 @@ unlock: */ static void cpuset_handle_hotplug(void) { + static DECLARE_WORK(hk_sd_work, hk_sd_workfn); static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated, mems_updated; @@ -3859,9 +3923,21 @@ static void cpuset_handle_hotplug(void) rcu_read_unlock(); } - /* rebuild sched domains if necessary */ - if (force_sd_rebuild) - rebuild_sched_domains_cpuslocked(); + + /* + * Queue a work to call housekeeping_update() & rebuild_sched_domains() + * There will be a slight delay before the HK_TYPE_DOMAIN housekeeping + * cpumask can correctly reflect what is in isolated_cpus. + * + * We rely on WORK_STRUCT_PENDING_BIT to not requeue a work item that + * is still pending. Before the pending bit is cleared, the work data + * is copied out and work item dequeued. So it is possible to queue + * the work again before the hk_sd_workfn() is invoked to process the + * previously queued work. Since hk_sd_workfn() doesn't use the work + * item at all, this is not a problem. + */ + if (update_housekeeping || force_sd_rebuild) + queue_work(system_unbound_wq, &hk_sd_work); free_tmpmasks(ptmp); } diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 3b725d3..ef152d4 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -123,8 +123,6 @@ int housekeeping_update(struct cpumask *isol_mask) struct cpumask *trial, *old = NULL; int err; - lockdep_assert_cpus_held(); - trial = kmalloc(cpumask_size(), GFP_KERNEL); if (!trial) return -ENOMEM; @@ -136,7 +134,7 @@ int housekeeping_update(struct cpumask *isol_mask) } if (!housekeeping.flags) - static_branch_enable_cpuslocked(&housekeeping_overridden); + static_branch_enable(&housekeeping_overridden); if (housekeeping.flags & HK_FLAG_DOMAIN) old = housekeeping_cpumask_dereference(HK_TYPE_DOMAIN); diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index c1ed0d5..155eeae 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -1559,8 +1559,6 @@ int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask) cpumask_var_t cpumask __free(free_cpumask_var) = CPUMASK_VAR_NULL; int cpu; - lockdep_assert_cpus_held(); - if (!works) return -ENOMEM; if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) @@ -1570,6 +1568,7 @@ int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask) * First set previously isolated CPUs as available (unisolate). * This cpumask contains only CPUs that switched to available now. */ + guard(cpus_read_lock)(); cpumask_andnot(cpumask, cpu_online_mask, exclude_cpumask); cpumask_andnot(cpumask, cpumask, tmigr_available_cpumask); @@ -1626,7 +1625,6 @@ static int __init tmigr_init_isolation(void) cpumask_andnot(cpumask, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); /* Protect against RCU torture hotplug testing */ - guard(cpus_read_lock)(); return tmigr_isolated_exclude_cpumask(cpumask); } late_initcall(tmigr_init_isolation); diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index 5dff3ad..a56f415 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -196,7 +196,6 @@ test_add_proc() # P = set cpus.partition (0:member, 1:root, 2:isolated) # C = add cpu-list to cpuset.cpus # X = add cpu-list to cpuset.cpus.exclusive -# S

= use prefix in subtree_control # T = put a task into cgroup # CX = add cpu-list to both cpuset.cpus and cpuset.cpus.exclusive # O= = Write to CPU online file of @@ -209,44 +208,46 @@ test_add_proc() # sched-debug matching which includes offline CPUs and single-CPU partitions # while the second one is for matching cpuset.cpus.isolated. # -SETUP_A123_PARTITIONS="C1-3:P1:S+ C2-3:P1:S+ C3:P1" +SETUP_A123_PARTITIONS="C1-3:P1 C2-3:P1 C3:P1" TEST_MATRIX=( # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- - " C0-1 . . C2-3 S+ C4-5 . . 0 A2:0-1" + " C0-1 . . C2-3 . C4-5 . . 0 A2:0-1" " C0-1 . . C2-3 P1 . . . 0 " - " C0-1 . . C2-3 P1:S+ C0-1:P1 . . 0 " - " C0-1 . . C2-3 P1:S+ C1:P1 . . 0 " - " C0-1:S+ . . C2-3 . . . P1 0 " - " C0-1:P1 . . C2-3 S+ C1 . . 0 " - " C0-1:P1 . . C2-3 S+ C1:P1 . . 0 " - " C0-1:P1 . . C2-3 S+ C1:P1 . P1 0 " + " C0-1 . . C2-3 P1 C0-1:P1 . . 0 " + " C0-1 . . C2-3 P1 C1:P1 . . 0 " + " C0-1 . . C2-3 . . . P1 0 " + " C0-1:P1 . . C2-3 . C1 . . 0 " + " C0-1:P1 . . C2-3 . C1:P1 . . 0 " + " C0-1:P1 . . C2-3 . C1:P1 . P1 0 " " C0-1:P1 . . C2-3 C4-5 . . . 0 A1:4-5" - " C0-1:P1 . . C2-3 S+:C4-5 . . . 0 A1:4-5" " C0-1 . . C2-3:P1 . . . C2 0 " " C0-1 . . C2-3:P1 . . . C4-5 0 B1:4-5" - "C0-3:P1:S+ C2-3:P1 . . . . . . 0 A1:0-1|A2:2-3|XA2:2-3" - "C0-3:P1:S+ C2-3:P1 . . C1-3 . . . 0 A1:1|A2:2-3|XA2:2-3" - "C2-3:P1:S+ C3:P1 . . C3 . . . 0 A1:|A2:3|XA2:3 A1:P1|A2:P1" - "C2-3:P1:S+ C3:P1 . . C3 P0 . . 0 A1:3|A2:3 A1:P1|A2:P0" - "C2-3:P1:S+ C2:P1 . . C2-4 . . . 0 A1:3-4|A2:2" - "C2-3:P1:S+ C3:P1 . . C3 . . C0-2 0 A1:|B1:0-2 A1:P1|A2:P1" + " C0-3:P1 C2-3:P1 . . . . . . 0 A1:0-1|A2:2-3|XA2:2-3" + " C0-3:P1 C2-3:P1 . . C1-3 . . . 0 A1:1|A2:2-3|XA2:2-3" + " C2-3:P1 C3:P1 . . C3 . . . 0 A1:|A2:3|XA2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . C3 P0 . . 0 A1:3|A2:3 A1:P1|A2:P0" + " C2-3:P1 C2:P1 . . C2-4 . . . 0 A1:3-4|A2:2" + " C2-3:P1 C3:P1 . . C3 . . C0-2 0 A1:|B1:0-2 A1:P1|A2:P1" "$SETUP_A123_PARTITIONS . C2-3 . . . 0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1" # CPU offlining cases: - " C0-1 . . C2-3 S+ C4-5 . O2=0 0 A1:0-1|B1:3" - "C0-3:P1:S+ C2-3:P1 . . O2=0 . . . 0 A1:0-1|A2:3" - "C0-3:P1:S+ C2-3:P1 . . O2=0 O2=1 . . 0 A1:0-1|A2:2-3" - "C0-3:P1:S+ C2-3:P1 . . O1=0 . . . 0 A1:0|A2:2-3" - "C0-3:P1:S+ C2-3:P1 . . O1=0 O1=1 . . 0 A1:0-1|A2:2-3" - "C2-3:P1:S+ C3:P1 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P1" - "C2-3:P1:S+ C3:P2 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P2" - "C2-3:P1:S+ C3:P1 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P1" - "C2-3:P1:S+ C3:P2 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P2" - "C2-3:P1:S+ C3:P1 . . O2=0 . . . 0 A1:|A2:3 A1:P1|A2:P1" - "C2-3:P1:S+ C3:P1 . . O3=0 . . . 0 A1:2|A2: A1:P1|A2:P1" - "C2-3:P1:S+ C3:P1 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-1" - "C2-3:P1:S+ C3:P1 . . . T:O3=0 . . 0 A1:2|A2:2 A1:P1|A2:P-1" + " C0-1 . . C2-3 . C4-5 . O2=0 0 A1:0-1|B1:3" + " C0-3:P1 C2-3:P1 . . O2=0 . . . 0 A1:0-1|A2:3" + " C0-3:P1 C2-3:P1 . . O2=0 O2=1 . . 0 A1:0-1|A2:2-3" + " C0-3:P1 C2-3:P1 . . O1=0 . . . 0 A1:0|A2:2-3" + " C0-3:P1 C2-3:P1 . . O1=0 O1=1 . . 0 A1:0-1|A2:2-3" + " C2-3:P1 C3:P1 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P2 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P2" + " C2-3:P1 C3:P1 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P2 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P2" + " C2-3:P1 C3:P1 . . O2=0 . . . 0 A1:|A2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . O3=0 . . . 0 A1:2|A2: A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-1" + " C2-3:P1 C3:P1 . . . T:O3=0 . . 0 A1:2|A2:2 A1:P1|A2:P-1" + " C2-3:P1 C3:P2 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-2" + " C1-3:P1 C3:P2 . . . T:O3=0 . . 0 A1:1-2|A2:1-2 A1:P1|A2:P-2 3|" + " C1-3:P1 C3:P2 . . . T:O3=0 O3=1 . 0 A1:1-2|A2:3 A1:P1|A2:P2 3" "$SETUP_A123_PARTITIONS . O1=0 . . . 0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1" "$SETUP_A123_PARTITIONS . O2=0 . . . 0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1" "$SETUP_A123_PARTITIONS . O3=0 . . . 0 A1:1|A2:2|A3: A1:P1|A2:P1|A3:P1" @@ -264,88 +265,87 @@ TEST_MATRIX=( # # Remote partition and cpuset.cpus.exclusive tests # - " C0-3:S+ C1-3:S+ C2-3 . X2-3 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3:P2 . . 0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X3:P2 . . 0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 C2-3 . . . P2 0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2" - " C0-3:S+ C1-3:S+ C2-3 C4-5 . . . P2 0 B1:4-5 B1:P2 4-5" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2:C1-3 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" - " C0-3:S+ C1-3:S+ C2-3 C4 X1-3 X1-3:P2 P2 . 0 A2:1|A3:2-3 A2:P2|A3:P2 1-3" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5" - " C4:X0-3:S+ X1-3:S+ X2-3 . . P2 . . 0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3" - " C4:X0-3:S+ X1-3:S+ X2-3 . . . P2 . 0 A1:4|A2:4|A3:2-3 A3:P2 2-3" + " C0-3 C1-3 C2-3 . X2-3 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3" + " C0-3 C1-3 C2-3 . X2-3 X2-3:P2 . . 0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3" + " C0-3 C1-3 C2-3 . X2-3 X3:P2 . . 0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3" + " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" + " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" + " C0-3 C1-3 C2-3 C2-3 . . . P2 0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2" + " C0-3 C1-3 C2-3 C4-5 . . . P2 0 B1:4-5 B1:P2 4-5" + " C0-3 C1-3 C2-3 C4 X2-3 X2-3 X2-3:P2 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" + " C0-3 C1-3 C2-3 C4 X2-3 X2-3 X2-3:P2:C1-3 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" + " C0-3 C1-3 C2-3 C4 X1-3 X1-3:P2 P2 . 0 A2:1|A3:2-3 A2:P2|A3:P2 1-3" + " C0-3 C1-3 C2-3 C4 X2-3 X2-3 X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5" + " C4:X0-3 X1-3 X2-3 . . P2 . . 0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3" + " C4:X0-3 X1-3 X2-3 . . . P2 . 0 A1:4|A2:4|A3:2-3 A3:P2 2-3" # Nested remote/local partition tests - " C0-3:S+ C1-3:S+ C2-3 C4-5 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4-5 \ + " C0-3 C1-3 C2-3 C4-5 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4-5 \ A1:P0|A2:P1|A3:P2|B1:P1 2-3" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4 \ + " C0-3 C1-3 C2-3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4 \ A1:P0|A2:P1|A3:P2|B1:P1 2-4|2-3" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 . P1 0 A1:0-1|A2:2-3|A3:2-3|B1:4 \ + " C0-3 C1-3 C2-3 C4 X2-3 X2-3:P1 . P1 0 A1:0-1|A2:2-3|A3:2-3|B1:4 \ A1:P0|A2:P1|A3:P0|B1:P1" - " C0-3:S+ C1-3:S+ C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:2|A3:3|B1:4 \ + " C0-3 C1-3 C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:2|A3:3|B1:4 \ A1:P0|A2:P1|A3:P2|B1:P1 2-4|3" - " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1|A2:2-3|A3:4 \ + " C0-4 C1-4 C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1|A2:2-3|A3:4 \ A1:P0|A2:P2|A3:P1 2-4|2-3" - " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1|A2:2|A3:3-4 \ + " C0-4 C1-4 C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1|A2:2|A3:3-4 \ A1:P0|A2:P2|A3:P1 2" - " C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \ + " C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \ . . X5 . . 0 A1:0-4|A2:1-4|A3:2-4 \ A1:P0|A2:P-2|A3:P-1 ." - " C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \ + " C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \ . . . X1 . 0 A1:0-1|A2:2-4|A3:2-4 \ A1:P0|A2:P2|A3:P-1 2-4" # Remote partition offline tests - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 . 0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 P2:O3=0 . 0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3" - " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 T:P2:O3=0 . 0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|" + " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2:O2=0 . 0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3" + " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" + " C0-3 C1-3 C3 . X2-3 X2-3 P2:O3=0 . 0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3" + " C0-3 C1-3 C3 . X2-3 X2-3 T:P2:O3=0 . 0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|" # An invalidated remote partition cannot self-recover from hotplug - " C0-3:S+ C1-3:S+ C2 . X2-3 X2-3 T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ." + " C0-3 C1-3 C2 . X2-3 X2-3 T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ." # cpus.exclusive.effective clearing test - " C0-3:S+ C1-3:S+ C2 . X2-3:X . . . 0 A1:0-3|A2:1-3|A3:2|XA1:" + " C0-3 C1-3 C2 . X2-3:X . . . 0 A1:0-3|A2:1-3|A3:2|XA1:" # Invalid to valid remote partition transition test - " C0-3:S+ C1-3 . . . X3:P2 . . 0 A1:0-3|A2:1-3|XA2: A2:P-2 ." - " C0-3:S+ C1-3:X3:P2 - . . X2-3 P2 . . 0 A1:0-2|A2:3|XA2:3 A2:P2 3" + " C0-3 C1-3 . . . X3:P2 . . 0 A1:0-3|A2:1-3|XA2: A2:P-2 ." + " C0-3 C1-3:X3:P2 . . X2-3 P2 . . 0 A1:0-2|A2:3|XA2:3 A2:P2 3" # Invalid to valid local partition direct transition tests - " C1-3:S+:P2 X4:P2 . . . . . . 0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3" - " C1-3:S+:P2 X4:P2 . . . X3:P2 . . 0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3" - " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4|B1:5-6 A1:P2|B1:P0" - " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3" + " C1-3:P2 X4:P2 . . . . . . 0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3" + " C1-3:P2 X4:P2 . . . X3:P2 . . 0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3" + " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4|B1:5-6 A1:P2|B1:P0" + " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3" # Local partition invalidation tests - " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \ + " C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \ . . . . . 0 A1:1|A2:2|A3:3 A1:P2|A2:P2|A3:P2 1-3" - " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \ + " C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \ . . X4 . . 0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3" - " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \ + " C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \ . . C4:X . . 0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3" # Local partition CPU change tests - " C0-5:S+:P2 C4-5:S+:P1 . . . C3-5 . . 0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2" - " C0-5:S+:P2 C4-5:S+:P1 . . C1-5 . . . 0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3" + " C0-5:P2 C4-5:P1 . . . C3-5 . . 0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2" + " C0-5:P2 C4-5:P1 . . C1-5 . . . 0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3" # cpus_allowed/exclusive_cpus update tests - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \ . X:C4 . P2 . 0 A1:4|A2:4|XA2:|XA3:|A3:4 \ A1:P0|A3:P-2 ." - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \ . X1 . P2 . 0 A1:0-3|A2:1-3|XA1:1|XA2:|XA3:|A3:2-3 \ A1:P0|A3:P-2 ." - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \ . . X3 P2 . 0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3 \ A1:P0|A3:P2 3" - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \ . . X3 . . 0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3|XA3:3 \ A1:P0|A3:P2 3" - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \ . X4 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:4|XA2:|XA3 \ A1:P0|A3:P-2" @@ -356,37 +356,37 @@ TEST_MATRIX=( # # Adding CPUs to partition root that are not in parent's # cpuset.cpus is allowed, but those extra CPUs are ignored. - "C2-3:P1:S+ C3:P1 . . . C2-4 . . 0 A1:|A2:2-3 A1:P1|A2:P1" + " C2-3:P1 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. - "C2-3:P1:S+ C3:P1 . . T C2-3 . . 0 A1:2-3|A2:2-3 A1:P1|A2:P-1" - " C3:P1:S+ C3 . . T P1 . . 0 A1:3|A2:3 A1:P1|A2:P-1" + " C2-3:P1 C3:P1 . . T C2-3 . . 0 A1:2-3|A2:2-3 A1:P1|A2:P-1" + " C3:P1 C3 . . T P1 . . 0 A1:3|A2:3 A1:P1|A2:P-1" "$SETUP_A123_PARTITIONS . T:C2-3 . . . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1" "$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 - "C2-3:P1:S+ C3:P1 . . P0 . . . 0 A1:2-3|A2:3 A1:P0|A2:P-1" + " C2-3:P1 C3:P1 . . P0 . . . 0 A1:2-3|A2:3 A1:P0|A2:P-1" "$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. - "C2-3:P1:S+ . . . . C3-4:P1 . . 0 A1:2|A2:3 A1:P1|A2:P1" + " C2-3:P1 . . . . C3-4:P1 . . 0 A1:2|A2:3 A1:P1|A2:P1" # Deletion of CPUs distributed to child cgroup is allowed. - "C0-1:P1:S+ C1 . C2-3 C4-5 . . . 0 A1:4-5|A2:4-5" + " C0-1:P1 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. - " C0-1:P1 . . C2-3 S+ C4-5:P1 . . 0 A1:0-1|A2:0-1 A1:P1|A2:P-1" + " C0-1:P1 . . C2-3 . C4-5:P1 . . 0 A1:0-1|A2:0-1 A1:P1|A2:P-1" # Enabling partition with child cpusets is allowed - " C0-1:S+ C1 . C2-3 P1 . . . 0 A1:0-1|A2:1 A1:P1" + " C0-1 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. - " C0-1:S+ C1 . C2-3 . P2 . . 0 A1:0-1|A2:1 A1:P0|A2:P-2" - " C0-1:S+ C1:P2 . C2-3 P1 . . . 0 A1:0|A2:1 A1:P1|A2:P2 0-1|1" + " C0-1 C1 . C2-3 . P2 . . 0 A1:0-1|A2:1 A1:P0|A2:P-2" + " C0-1 C1:P2 . C2-3 P1 . . . 0 A1:0|A2:1 A1:P1|A2:P2 0-1|1" # A non-exclusive cpuset.cpus change will not invalidate its siblings partition. " C0-1:P1 . . C2-3 C0-2 . . . 0 A1:0-2|B1:3 A1:P1|B1:P0" @@ -398,23 +398,23 @@ TEST_MATRIX=( # Child partition root that try to take all CPUs from parent partition # with tasks will remain invalid. - " C1-4:P1:S+ P1 . . . . . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1" - " C1-4:P1:S+ P1 . . . C1-4 . . 0 A1|A2:1-4 A1:P1|A2:P1" - " C1-4:P1:S+ P1 . . T C1-4 . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1" + " C1-4:P1 P1 . . . . . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1" + " C1-4:P1 P1 . . . C1-4 . . 0 A1|A2:1-4 A1:P1|A2:P1" + " C1-4:P1 P1 . . T C1-4 . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1" # Clearing of cpuset.cpus with a preset cpuset.cpus.exclusive shouldn't # affect cpuset.cpus.exclusive.effective. - " C1-4:X3:S+ C1:X3 . . . C . . 0 A2:1-4|XA2:3" + " C1-4:X3 C1:X3 . . . C . . 0 A2:1-4|XA2:3" # cpuset.cpus can contain CPUs that overlap a sibling cpuset with cpus.exclusive # but creating a local partition out of it is not allowed. Similarly and change # in cpuset.cpus of a local partition that overlaps sibling exclusive CPUs will # invalidate it. - " CX1-4:S+ CX2-4:P2 . C5-6 . . . P1 0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \ + " CX1-4 CX2-4:P2 . C5-6 . . . P1 0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \ A1:P0|A2:P2:B1:P1 2-4" - " CX1-4:S+ CX2-4:P2 . C3-6 . . . P1 0 A1:1|A2:2-4|B1:5-6 \ + " CX1-4 CX2-4:P2 . C3-6 . . . P1 0 A1:1|A2:2-4|B1:5-6 \ A1:P0|A2:P2:B1:P-1 2-4" - " CX1-4:S+ CX2-4:P2 . C5-6 . . . P1:C3-6 0 A1:1|A2:2-4|B1:5-6 \ + " CX1-4 CX2-4:P2 . C5-6 . . . P1:C3-6 0 A1:1|A2:2-4|B1:5-6 \ A1:P0|A2:P2:B1:P-1 2-4" # When multiple partitions with conflicting cpuset.cpus are created, the @@ -426,14 +426,14 @@ TEST_MATRIX=( " C1-3:X1-3 . . C4-5 . . . C1-2 0 A1:1-3|B1:1-2" # cpuset.cpus can become empty with task in it as it inherits parent's effective CPUs - " C1-3:S+ C2 . . . T:C . . 0 A1:1-3|A2:1-3" + " C1-3 C2 . . . T:C . . 0 A1:1-3|A2:1-3" # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- # Failure cases: # A task cannot be added to a partition with no cpu - "C2-3:P1:S+ C3:P1 . . O2=0:T . . . 1 A1:|A2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . O2=0:T . . . 1 A1:|A2:3 A1:P1|A2:P1" # Changes to cpuset.cpus.exclusive that violate exclusivity rule is rejected " C0-3 . . C4-5 X0-3 . . X3-5 1 A1:0-3|B1:4-5" @@ -465,31 +465,31 @@ REMOTE_TEST_MATRIX=( # old-p1 old-p2 old-c11 old-c12 old-c21 old-c22 # new-p1 new-p2 new-c11 new-c12 new-c21 new-c22 ECPUs Pstate ISOLCPUS # ------ ------ ------- ------- ------- ------- ----- ------ -------- - " X1-3:S+ X4-6:S+ X1-2 X3 X4-5 X6 \ + " X1-3 X4-6 X1-2 X3 X4-5 X6 \ . . P2 P2 P2 P2 c11:1-2|c12:3|c21:4-5|c22:6 \ c11:P2|c12:P2|c21:P2|c22:P2 1-6" - " CX1-4:S+ . X1-2:P2 C3 . . \ + " CX1-4 . X1-2:P2 C3 . . \ . . . C3-4 . . p1:3-4|c11:1-2|c12:3-4 \ p1:P0|c11:P2|c12:P0 1-2" - " CX1-4:S+ . X1-2:P2 . . . \ + " CX1-4 . X1-2:P2 . . . \ X2-4 . . . . . p1:1,3-4|c11:2 \ p1:P0|c11:P2 2" - " CX1-5:S+ . X1-2:P2 X3-5:P1 . . \ + " CX1-5 . X1-2:P2 X3-5:P1 . . \ X2-4 . . . . . p1:1,5|c11:2|c12:3-4 \ p1:P0|c11:P2|c12:P1 2" - " CX1-4:S+ . X1-2:P2 X3-4:P1 . . \ + " CX1-4 . X1-2:P2 X3-4:P1 . . \ . . X2 . . . p1:1|c11:2|c12:3-4 \ p1:P0|c11:P2|c12:P1 2" # p1 as member, will get its effective CPUs from its parent rtest - " CX1-4:S+ . X1-2:P2 X3-4:P1 . . \ + " CX1-4 . X1-2:P2 X3-4:P1 . . \ . . X1 CX2-4 . . p1:5-7|c11:1|c12:2-4 \ p1:P0|c11:P2|c12:P1 1" - " CX1-4:S+ X5-6:P1:S+ . . . . \ - . . X1-2:P2 X4-5:P1 . X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \ + " CX1-4 X5-6:P1 . . . . \ + . . X1-2:P2 X4-5:P1 . X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \ p1:P0|p2:P1|c11:P2|c12:P1|c22:P2 \ 1-2,4-6|1-2,5-6" # c12 whose cpuset.cpus CPUs are all granted to c11 will become invalid partition - " C1-5:P1:S+ . C1-4:P1 C2-3 . . \ + " C1-5:P1 . C1-4:P1 C2-3 . . \ . . . P1 . . p1:5|c11:1-4|c12:5 \ p1:P1|c11:P1|c12:P-1" ) @@ -530,7 +530,6 @@ set_ctrl_state() CGRP=$1 STATE=$2 SHOWERR=${3} - CTRL=${CTRL:=$CONTROLLER} HASERR=0 REDIRECT="2> $TMPMSG" [[ -z "$STATE" || "$STATE" = '.' ]] && return 0 @@ -540,15 +539,16 @@ set_ctrl_state() 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=$CGRP/cpuset.cpus XFILE=$CGRP/cpuset.cpus.exclusive - case $CMD in - S*) PREFIX=${CMD#?} - COMM="echo ${PREFIX}${CTRL} > $SFILE" + + # Enable cpuset controller if not enabled yet + [[ -f $CFILE ]] || { + COMM="echo +cpuset > $CGRP/../cgroup.subtree_control" eval $COMM $REDIRECT - ;; + } + case $CMD in X*) CPUS=${CMD#?} COMM="echo $CPUS > $XFILE" @@ -764,7 +764,7 @@ check_cgroup_states() # only CPUs in isolated partitions as well as those that are isolated at # boot time. # -# $1 - expected isolated cpu list(s) {,} +# $1 - expected isolated cpu list(s) {|} # - expected sched/domains value # - cpuset.cpus.isolated value = if not defined # @@ -773,6 +773,7 @@ check_isolcpus() EXPECTED_ISOLCPUS=$1 ISCPUS=${CGROUP2}/cpuset.cpus.isolated ISOLCPUS=$(cat $ISCPUS) + HKICPUS=$(cat /sys/devices/system/cpu/isolated) LASTISOLCPU= SCHED_DOMAINS=/sys/kernel/debug/sched/domains if [[ $EXPECTED_ISOLCPUS = . ]] @@ -811,6 +812,11 @@ check_isolcpus() EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN # + # The inverse of HK_TYPE_DOMAIN cpumask in $HKICPUS should match $ISOLCPUS + # + [[ "$ISOLCPUS" != "$HKICPUS" ]] && return 1 + + # # Use the sched domain in debugfs to check isolated CPUs, if available # [[ -d $SCHED_DOMAINS ]] || return 0 @@ -947,7 +953,6 @@ check_test_results() run_state_test() { TEST=$1 - CONTROLLER=cpuset CGROUP_LIST=". A1 A1/A2 A1/A2/A3 B1" RESET_LIST="A1/A2/A3 A1/A2 A1 B1" I=0 @@ -1003,7 +1008,6 @@ run_state_test() run_remote_state_test() { TEST=$1 - CONTROLLER=cpuset [[ -d rtest ]] || mkdir rtest cd rtest echo +cpuset > cgroup.subtree_control