diff options
Diffstat (limited to 'kernel/cgroup/cpuset.c')
| -rw-r--r-- | kernel/cgroup/cpuset.c | 275 |
1 files changed, 173 insertions, 102 deletions
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index adb5190c4429..2a9695ccb65f 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -160,6 +160,9 @@ struct cpuset { */ int use_parent_ecpus; int child_ecpus_count; + + /* Handle for cpuset.cpus.partition */ + struct cgroup_file partition_file; }; /* @@ -263,6 +266,16 @@ static inline int is_partition_root(const struct cpuset *cs) return cs->partition_root_state > 0; } +/* + * Send notification event of whenever partition_root_state changes. + */ +static inline void notify_partition_change(struct cpuset *cs, + int old_prs, int new_prs) +{ + if (old_prs != new_prs) + cgroup_file_notify(&cs->partition_file); +} + static struct cpuset top_cpuset = { .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), @@ -298,17 +311,19 @@ static struct cpuset top_cpuset = { if (is_cpuset_online(((des_cs) = css_cs((pos_css))))) /* - * There are two global locks guarding cpuset structures - cpuset_mutex and + * There are two global locks guarding cpuset structures - cpuset_rwsem and * callback_lock. We also require taking task_lock() when dereferencing a * task's cpuset pointer. See "The task_lock() exception", at the end of this - * comment. + * comment. The cpuset code uses only cpuset_rwsem write lock. Other + * kernel subsystems can use cpuset_read_lock()/cpuset_read_unlock() to + * prevent change to cpuset structures. * * A task must hold both locks to modify cpusets. If a task holds - * cpuset_mutex, then it blocks others wanting that mutex, ensuring that it + * cpuset_rwsem, it blocks others wanting that rwsem, 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 + * just holding cpuset_rwsem. 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. @@ -372,18 +387,29 @@ static inline bool is_in_v2_mode(void) } /* - * Return in pmask the portion of a cpusets's cpus_allowed that - * are online. If none are online, walk up the cpuset hierarchy - * until we find one that does have some online cpus. + * Return in pmask the portion of a task's cpusets's cpus_allowed that + * are online and are capable of running the task. If none are found, + * walk up the cpuset hierarchy until we find one that does have some + * appropriate cpus. * * One way or another, we guarantee to return some non-empty subset * of cpu_online_mask. * - * Call with callback_lock or cpuset_mutex held. + * Call with callback_lock or cpuset_rwsem held. */ -static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask) +static void guarantee_online_cpus(struct task_struct *tsk, + struct cpumask *pmask) { - while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) { + const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); + struct cpuset *cs; + + if (WARN_ON(!cpumask_and(pmask, possible_mask, cpu_online_mask))) + cpumask_copy(pmask, cpu_online_mask); + + rcu_read_lock(); + cs = task_cs(tsk); + + while (!cpumask_intersects(cs->effective_cpus, pmask)) { cs = parent_cs(cs); if (unlikely(!cs)) { /* @@ -393,11 +419,13 @@ static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask) * cpuset's effective_cpus is on its way to be * identical to cpu_online_mask. */ - cpumask_copy(pmask, cpu_online_mask); - return; + goto out_unlock; } } - cpumask_and(pmask, cs->effective_cpus, cpu_online_mask); + cpumask_and(pmask, pmask, cs->effective_cpus); + +out_unlock: + rcu_read_unlock(); } /* @@ -409,7 +437,7 @@ static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask) * One way or another, we guarantee to return some non-empty subset * of node_states[N_MEMORY]. * - * Call with callback_lock or cpuset_mutex held. + * Call with callback_lock or cpuset_rwsem held. */ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) { @@ -421,7 +449,7 @@ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) /* * update task's spread flag if cpuset's page/slab spread flag is set * - * Call with callback_lock or cpuset_mutex held. + * Call with callback_lock or cpuset_rwsem held. */ static void cpuset_update_task_spread_flag(struct cpuset *cs, struct task_struct *tsk) @@ -442,7 +470,7 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs, * * One cpuset is a subset of another if all its allowed CPUs and * Memory Nodes are a subset of the other, and its exclusive flags - * are only set if the other's are set. Call holding cpuset_mutex. + * are only set if the other's are set. Call holding cpuset_rwsem. */ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) @@ -551,7 +579,7 @@ static inline void free_cpuset(struct cpuset *cs) * If we replaced the flag and mask values of the current cpuset * (cur) with those values in the trial cpuset (trial), would * our various subset and exclusive rules still be valid? Presumes - * cpuset_mutex held. + * cpuset_rwsem held. * * 'cur' is the address of an actual, in-use cpuset. Operations * such as list traversal that depend on the actual address of the @@ -674,7 +702,7 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr, rcu_read_unlock(); } -/* Must be called with cpuset_mutex held. */ +/* Must be called with cpuset_rwsem held. */ static inline int nr_cpusets(void) { /* jump label reference count + the top-level cpuset */ @@ -700,7 +728,7 @@ static inline int nr_cpusets(void) * domains when operating in the severe memory shortage situations * that could cause allocation failures below. * - * Must be called with cpuset_mutex held. + * Must be called with cpuset_rwsem held. * * The three key local variables below are: * cp - cpuset pointer, used (together with pos_css) to perform a @@ -979,7 +1007,7 @@ partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], * 'cpus' is removed, then call this routine to rebuild the * scheduler's dynamic sched domains. * - * Call with cpuset_mutex held. Takes get_online_cpus(). + * Call with cpuset_rwsem held. Takes cpus_read_lock(). */ static void rebuild_sched_domains_locked(void) { @@ -1040,11 +1068,11 @@ static void rebuild_sched_domains_locked(void) void rebuild_sched_domains(void) { - get_online_cpus(); + cpus_read_lock(); percpu_down_write(&cpuset_rwsem); rebuild_sched_domains_locked(); percpu_up_write(&cpuset_rwsem); - put_online_cpus(); + cpus_read_unlock(); } /** @@ -1052,7 +1080,7 @@ void rebuild_sched_domains(void) * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed * * Iterate through each task of @cs updating its cpus_allowed to the - * effective cpuset's. As this function is called with cpuset_mutex held, + * effective cpuset's. As this function is called with cpuset_rwsem held, * cpuset membership stays stable. */ static void update_tasks_cpumask(struct cpuset *cs) @@ -1114,7 +1142,7 @@ enum subparts_cmd { * cpus_allowed can be granted or an error code will be returned. * * For partcmd_disable, the cpuset is being transofrmed from a partition - * root back to a non-partition root. any CPUs in cpus_allowed that are in + * 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. * @@ -1148,6 +1176,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, struct cpuset *parent = parent_cs(cpuset); int adding; /* Moving cpus from effective_cpus to subparts_cpus */ int deleting; /* Moving cpus from subparts_cpus to effective_cpus */ + int old_prs, new_prs; bool part_error = false; /* Partition error? */ percpu_rwsem_assert_held(&cpuset_rwsem); @@ -1183,6 +1212,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, * A cpumask update cannot make parent's effective_cpus become empty. */ adding = deleting = false; + old_prs = new_prs = cpuset->partition_root_state; if (cmd == partcmd_enable) { cpumask_copy(tmp->addmask, cpuset->cpus_allowed); adding = true; @@ -1225,7 +1255,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, /* * partcmd_update w/o newmask: * - * addmask = cpus_allowed & parent->effectiveb_cpus + * addmask = cpus_allowed & parent->effective_cpus * * Note that parent's subparts_cpus may have been * pre-shrunk in case there is a change in the cpu list. @@ -1247,11 +1277,11 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, switch (cpuset->partition_root_state) { case PRS_ENABLED: if (part_error) - cpuset->partition_root_state = PRS_ERROR; + new_prs = PRS_ERROR; break; case PRS_ERROR: if (!part_error) - cpuset->partition_root_state = PRS_ENABLED; + new_prs = PRS_ENABLED; break; } /* @@ -1260,10 +1290,10 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, part_error = (prev_prs == PRS_ERROR); } - if (!part_error && (cpuset->partition_root_state == PRS_ERROR)) + if (!part_error && (new_prs == PRS_ERROR)) return 0; /* Nothing need to be done */ - if (cpuset->partition_root_state == PRS_ERROR) { + if (new_prs == PRS_ERROR) { /* * Remove all its cpus from parent's subparts_cpus. */ @@ -1272,7 +1302,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, parent->subparts_cpus); } - if (!adding && !deleting) + if (!adding && !deleting && (new_prs == old_prs)) return 0; /* @@ -1299,7 +1329,12 @@ 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; + spin_unlock_irq(&callback_lock); + notify_partition_change(cpuset, old_prs, new_prs); return cmd == partcmd_update; } @@ -1314,13 +1349,14 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, * * On legacy hierarchy, effective_cpus will be the same with cpu_allowed. * - * Called with cpuset_mutex held + * Called with cpuset_rwsem held */ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; bool need_rebuild_sched_domains = false; + int old_prs, new_prs; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { @@ -1360,17 +1396,18 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) * update_tasks_cpumask() again for tasks in the parent * cpuset if the parent's subparts_cpus changes. */ - if ((cp != cs) && cp->partition_root_state) { + old_prs = new_prs = cp->partition_root_state; + if ((cp != cs) && old_prs) { switch (parent->partition_root_state) { case PRS_DISABLED: /* * If parent is not a partition root or an - * invalid partition root, clear the state - * state and the CS_CPU_EXCLUSIVE flag. + * invalid partition root, clear its state + * and its CS_CPU_EXCLUSIVE flag. */ WARN_ON_ONCE(cp->partition_root_state != PRS_ERROR); - cp->partition_root_state = 0; + new_prs = PRS_DISABLED; /* * clear_bit() is an atomic operation and @@ -1391,11 +1428,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) /* * When parent is invalid, it has to be too. */ - cp->partition_root_state = PRS_ERROR; - if (cp->nr_subparts_cpus) { - cp->nr_subparts_cpus = 0; - cpumask_clear(cp->subparts_cpus); - } + new_prs = PRS_ERROR; break; } } @@ -1407,8 +1440,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) spin_lock_irq(&callback_lock); cpumask_copy(cp->effective_cpus, tmp->new_cpus); - if (cp->nr_subparts_cpus && - (cp->partition_root_state != PRS_ENABLED)) { + if (cp->nr_subparts_cpus && (new_prs != PRS_ENABLED)) { cp->nr_subparts_cpus = 0; cpumask_clear(cp->subparts_cpus); } else if (cp->nr_subparts_cpus) { @@ -1435,7 +1467,12 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) = cpumask_weight(cp->subparts_cpus); } } + + if (new_prs != old_prs) + cp->partition_root_state = new_prs; + spin_unlock_irq(&callback_lock); + notify_partition_change(cp, old_prs, new_prs); WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); @@ -1612,6 +1649,11 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, { struct cpuset_migrate_mm_work *mwork; + if (nodes_equal(*from, *to)) { + mmput(mm); + return; + } + mwork = kzalloc(sizeof(*mwork), GFP_KERNEL); if (mwork) { mwork->mm = mm; @@ -1664,12 +1706,12 @@ static void *cpuset_being_rebound; * @cs: the cpuset in which each task's mems_allowed mask needs to be changed * * Iterate through each task of @cs updating its mems_allowed to the - * effective cpuset's. As this function is called with cpuset_mutex held, + * effective cpuset's. As this function is called with cpuset_rwsem held, * cpuset membership stays stable. */ static void update_tasks_nodemask(struct cpuset *cs) { - static nodemask_t newmems; /* protected by cpuset_mutex */ + static nodemask_t newmems; /* protected by cpuset_rwsem */ struct css_task_iter it; struct task_struct *task; @@ -1682,7 +1724,7 @@ static void update_tasks_nodemask(struct cpuset *cs) * take while holding tasklist_lock. Forks can happen - the * mpol_dup() cpuset_being_rebound check will catch such forks, * and rebind their vma mempolicies too. Because we still hold - * the global cpuset_mutex, we know that no other rebind effort + * the global cpuset_rwsem, we know that no other rebind effort * will be contending for the global variable cpuset_being_rebound. * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. @@ -1728,7 +1770,7 @@ static void update_tasks_nodemask(struct cpuset *cs) * * On legacy hierarchy, effective_mems will be the same with mems_allowed. * - * Called with cpuset_mutex held + * Called with cpuset_rwsem held */ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) { @@ -1781,7 +1823,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) * mempolicies and if the cpuset is marked 'memory_migrate', * migrate the tasks pages to the new memory. * - * Call with cpuset_mutex held. May take callback_lock during call. + * Call with cpuset_rwsem held. May take callback_lock during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, * lock each such tasks mm->mmap_lock, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. @@ -1871,7 +1913,7 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) * @cs: the cpuset in which each task's spread flags needs to be changed * * Iterate through each task of @cs updating its spread flags. As this - * function is called with cpuset_mutex held, cpuset membership stays + * function is called with cpuset_rwsem held, cpuset membership stays * stable. */ static void update_tasks_flags(struct cpuset *cs) @@ -1891,7 +1933,7 @@ static void update_tasks_flags(struct cpuset *cs) * cs: the cpuset to update * turning_on: whether the flag is being set or cleared * - * Call with cpuset_mutex held. + * Call with cpuset_rwsem held. */ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, @@ -1937,34 +1979,32 @@ out: /* * update_prstate - update partititon_root_state - * cs: the cpuset to update - * val: 0 - disabled, 1 - enabled + * cs: the cpuset to update + * new_prs: new partition root state * - * Call with cpuset_mutex held. + * Call with cpuset_rwsem held. */ -static int update_prstate(struct cpuset *cs, int val) +static int update_prstate(struct cpuset *cs, int new_prs) { - int err; + int err, old_prs = cs->partition_root_state; struct cpuset *parent = parent_cs(cs); - struct tmpmasks tmp; + struct tmpmasks tmpmask; - if ((val != 0) && (val != 1)) - return -EINVAL; - if (val == cs->partition_root_state) + if (old_prs == new_prs) return 0; /* * Cannot force a partial or invalid partition root to a full * partition root. */ - if (val && cs->partition_root_state) + if (new_prs && (old_prs == PRS_ERROR)) return -EINVAL; - if (alloc_cpumasks(NULL, &tmp)) + if (alloc_cpumasks(NULL, &tmpmask)) return -ENOMEM; err = -EINVAL; - if (!cs->partition_root_state) { + if (!old_prs) { /* * Turning on partition root requires setting the * CS_CPU_EXCLUSIVE bit implicitly as well and cpus_allowed @@ -1978,31 +2018,27 @@ static int update_prstate(struct cpuset *cs, int val) goto out; err = update_parent_subparts_cpumask(cs, partcmd_enable, - NULL, &tmp); + NULL, &tmpmask); if (err) { update_flag(CS_CPU_EXCLUSIVE, cs, 0); goto out; } - cs->partition_root_state = PRS_ENABLED; } else { /* * Turning off partition root will clear the * CS_CPU_EXCLUSIVE bit. */ - if (cs->partition_root_state == PRS_ERROR) { - cs->partition_root_state = 0; + if (old_prs == PRS_ERROR) { update_flag(CS_CPU_EXCLUSIVE, cs, 0); err = 0; goto out; } err = update_parent_subparts_cpumask(cs, partcmd_disable, - NULL, &tmp); + NULL, &tmpmask); if (err) goto out; - cs->partition_root_state = 0; - /* Turning off CS_CPU_EXCLUSIVE will not return error */ update_flag(CS_CPU_EXCLUSIVE, cs, 0); } @@ -2015,11 +2051,18 @@ static int update_prstate(struct cpuset *cs, int val) update_tasks_cpumask(parent); if (parent->child_ecpus_count) - update_sibling_cpumasks(parent, cs, &tmp); + update_sibling_cpumasks(parent, cs, &tmpmask); rebuild_sched_domains_locked(); out: - free_cpumasks(NULL, &tmp); + if (!err) { + spin_lock_irq(&callback_lock); + cs->partition_root_state = new_prs; + spin_unlock_irq(&callback_lock); + notify_partition_change(cs, old_prs, new_prs); + } + + free_cpumasks(NULL, &tmpmask); return err; } @@ -2126,7 +2169,7 @@ static int fmeter_getrate(struct fmeter *fmp) static struct cpuset *cpuset_attach_old_cs; -/* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ +/* Called by cgroups to determine if a cpuset is usable; cpuset_rwsem held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; @@ -2178,7 +2221,7 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset) } /* - * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach() + * Protected by cpuset_rwsem. cpus_attach is used only by cpuset_attach() * but we can't allocate it dynamically there. Define it global and * allocate from cpuset_init(). */ @@ -2186,7 +2229,7 @@ static cpumask_var_t cpus_attach; static void cpuset_attach(struct cgroup_taskset *tset) { - /* static buf protected by cpuset_mutex */ + /* static buf protected by cpuset_rwsem */ static nodemask_t cpuset_attach_nodemask_to; struct task_struct *task; struct task_struct *leader; @@ -2199,15 +2242,13 @@ static void cpuset_attach(struct cgroup_taskset *tset) percpu_down_write(&cpuset_rwsem); - /* prepare for attach */ - if (cs == &top_cpuset) - cpumask_copy(cpus_attach, cpu_possible_mask); - else - guarantee_online_cpus(cs, cpus_attach); - guarantee_online_mems(cs, &cpuset_attach_nodemask_to); cgroup_taskset_for_each(task, css, tset) { + if (cs != &top_cpuset) + guarantee_online_cpus(task, cpus_attach); + else + cpumask_copy(cpus_attach, task_cpu_possible_mask(task)); /* * can_attach beforehand should guarantee that this doesn't * fail. TODO: have a better way to handle failure here @@ -2282,7 +2323,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, cpuset_filetype_t type = cft->private; int retval = 0; - get_online_cpus(); + cpus_read_lock(); percpu_down_write(&cpuset_rwsem); if (!is_cpuset_online(cs)) { retval = -ENODEV; @@ -2320,7 +2361,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, } out_unlock: percpu_up_write(&cpuset_rwsem); - put_online_cpus(); + cpus_read_unlock(); return retval; } @@ -2331,7 +2372,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, cpuset_filetype_t type = cft->private; int retval = -ENODEV; - get_online_cpus(); + cpus_read_lock(); percpu_down_write(&cpuset_rwsem); if (!is_cpuset_online(cs)) goto out_unlock; @@ -2346,7 +2387,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, } out_unlock: percpu_up_write(&cpuset_rwsem); - put_online_cpus(); + cpus_read_unlock(); return retval; } @@ -2378,14 +2419,14 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, * operation like this one can lead to a deadlock through kernfs * active_ref protection. Let's break the protection. Losing the * protection is okay as we check whether @cs is online after - * grabbing cpuset_mutex anyway. This only happens on the legacy + * grabbing cpuset_rwsem anyway. This only happens on the legacy * hierarchies. */ css_get(&cs->css); kernfs_break_active_protection(of->kn); flush_work(&cpuset_hotplug_work); - get_online_cpus(); + cpus_read_lock(); percpu_down_write(&cpuset_rwsem); if (!is_cpuset_online(cs)) goto out_unlock; @@ -2411,7 +2452,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, free_cpuset(trialcs); out_unlock: percpu_up_write(&cpuset_rwsem); - put_online_cpus(); + cpus_read_unlock(); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); flush_workqueue(cpuset_migrate_mm_wq); @@ -2542,7 +2583,7 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, return -EINVAL; css_get(&cs->css); - get_online_cpus(); + cpus_read_lock(); percpu_down_write(&cpuset_rwsem); if (!is_cpuset_online(cs)) goto out_unlock; @@ -2550,7 +2591,7 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, retval = update_prstate(cs, val); out_unlock: percpu_up_write(&cpuset_rwsem); - put_online_cpus(); + cpus_read_unlock(); css_put(&cs->css); return retval ?: nbytes; } @@ -2702,6 +2743,7 @@ static struct cftype dfl_files[] = { .write = sched_partition_write, .private = FILE_PARTITION_ROOT, .flags = CFTYPE_NOT_ON_ROOT, + .file_offset = offsetof(struct cpuset, partition_file), }, { @@ -2737,12 +2779,16 @@ cpuset_css_alloc(struct cgroup_subsys_state *parent_css) return ERR_PTR(-ENOMEM); } - set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); + __set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); nodes_clear(cs->mems_allowed); nodes_clear(cs->effective_mems); fmeter_init(&cs->fmeter); cs->relax_domain_level = -1; + /* Set CS_MEMORY_MIGRATE for default hierarchy */ + if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) + __set_bit(CS_MEMORY_MIGRATE, &cs->flags); + return &cs->css; } @@ -2756,7 +2802,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) if (!parent) return 0; - get_online_cpus(); + cpus_read_lock(); percpu_down_write(&cpuset_rwsem); set_bit(CS_ONLINE, &cs->flags); @@ -2809,7 +2855,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) spin_unlock_irq(&callback_lock); out_unlock: percpu_up_write(&cpuset_rwsem); - put_online_cpus(); + cpus_read_unlock(); return 0; } @@ -2828,7 +2874,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); - get_online_cpus(); + cpus_read_lock(); percpu_down_write(&cpuset_rwsem); if (is_partition_root(cs)) @@ -2849,7 +2895,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) clear_bit(CS_ONLINE, &cs->flags); percpu_up_write(&cpuset_rwsem); - put_online_cpus(); + cpus_read_unlock(); } static void cpuset_css_free(struct cgroup_subsys_state *css) @@ -3060,7 +3106,7 @@ retry: goto retry; } - parent = parent_cs(cs); + parent = parent_cs(cs); compute_effective_cpumask(&new_cpus, cs, parent); nodes_and(new_mems, cs->mems_allowed, parent->effective_mems); @@ -3082,8 +3128,10 @@ retry: if (is_partition_root(cs) && (cpumask_empty(&new_cpus) || (parent->partition_root_state == PRS_ERROR))) { if (cs->nr_subparts_cpus) { + spin_lock_irq(&callback_lock); cs->nr_subparts_cpus = 0; cpumask_clear(cs->subparts_cpus); + spin_unlock_irq(&callback_lock); compute_effective_cpumask(&new_cpus, cs, parent); } @@ -3095,9 +3143,17 @@ retry: */ if ((parent->partition_root_state == PRS_ERROR) || cpumask_empty(&new_cpus)) { + int old_prs; + update_parent_subparts_cpumask(cs, partcmd_disable, NULL, tmp); - cs->partition_root_state = PRS_ERROR; + old_prs = cs->partition_root_state; + if (old_prs != PRS_ERROR) { + spin_lock_irq(&callback_lock); + cs->partition_root_state = PRS_ERROR; + spin_unlock_irq(&callback_lock); + notify_partition_change(cs, old_prs, PRS_ERROR); + } } cpuset_force_rebuild(); } @@ -3168,6 +3224,13 @@ static void cpuset_hotplug_workfn(struct work_struct *work) cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus); mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems); + /* + * In the rare case that hotplug removes all the cpus in subparts_cpus, + * we assumed that cpus are updated. + */ + if (!cpus_updated && top_cpuset.nr_subparts_cpus) + cpus_updated = true; + /* synchronize cpus_allowed to cpu_active_mask */ if (cpus_updated) { spin_lock_irq(&callback_lock); @@ -3302,9 +3365,7 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) unsigned long flags; spin_lock_irqsave(&callback_lock, flags); - rcu_read_lock(); - guarantee_online_cpus(task_cs(tsk), pmask); - rcu_read_unlock(); + guarantee_online_cpus(tsk, pmask); spin_unlock_irqrestore(&callback_lock, flags); } @@ -3318,13 +3379,22 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) * which will not contain a sane cpumask during cases such as cpu hotplugging. * This is the absolute last resort for the scheduler and it is only used if * _every_ other avenue has been traveled. + * + * Returns true if the affinity of @tsk was changed, false otherwise. **/ -void cpuset_cpus_allowed_fallback(struct task_struct *tsk) +bool cpuset_cpus_allowed_fallback(struct task_struct *tsk) { + const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); + const struct cpumask *cs_mask; + bool changed = false; + rcu_read_lock(); - do_set_cpus_allowed(tsk, is_in_v2_mode() ? - task_cs(tsk)->cpus_allowed : cpu_possible_mask); + cs_mask = task_cs(tsk)->cpus_allowed; + if (is_in_v2_mode() && cpumask_subset(cs_mask, possible_mask)) { + do_set_cpus_allowed(tsk, cs_mask); + changed = true; + } rcu_read_unlock(); /* @@ -3344,6 +3414,7 @@ void cpuset_cpus_allowed_fallback(struct task_struct *tsk) * select_fallback_rq() will fix things ups and set cpu_possible_mask * if required. */ + return changed; } void __init cpuset_init_current_mems_allowed(void) @@ -3603,7 +3674,7 @@ void __cpuset_memory_pressure_bump(void) * - Used for /proc/<pid>/cpuset. * - No need to task_lock(tsk) on this tsk->cpuset reference, as it * doesn't really matter if tsk->cpuset changes after we read it, - * and we take cpuset_mutex, keeping cpuset_attach() from changing it + * and we take cpuset_rwsem, keeping cpuset_attach() from changing it * anyway. */ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, |