diff options
| -rw-r--r-- | Documentation/admin-guide/cgroup-v2.rst | 33 | ||||
| -rw-r--r-- | include/linux/cgroup-defs.h | 21 | ||||
| -rw-r--r-- | include/linux/cgroup.h | 4 | ||||
| -rw-r--r-- | include/linux/cpuset.h | 6 | ||||
| -rw-r--r-- | include/linux/sched/isolation.h | 4 | ||||
| -rw-r--r-- | include/linux/workqueue.h | 2 | ||||
| -rw-r--r-- | kernel/cgroup/cgroup-internal.h | 4 | ||||
| -rw-r--r-- | kernel/cgroup/cgroup-v1.c | 34 | ||||
| -rw-r--r-- | kernel/cgroup/cgroup.c | 45 | ||||
| -rw-r--r-- | kernel/cgroup/cpuset.c | 297 | ||||
| -rw-r--r-- | kernel/cgroup/rstat.c | 150 | ||||
| -rw-r--r-- | kernel/workqueue.c | 167 | ||||
| -rwxr-xr-x | tools/testing/selftests/cgroup/test_cpuset_prs.sh | 222 | ||||
| -rw-r--r-- | tools/testing/selftests/cgroup/test_freezer.c | 2 |
14 files changed, 708 insertions, 283 deletions
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 3f85254f3cef2c..09e65312d20c1b 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1093,7 +1093,11 @@ All time durations are in microseconds. A read-write single value file which exists on non-root cgroups. The default is "100". - The weight in the range [1, 10000]. + For non idle groups (cpu.idle = 0), the weight is in the + range [1, 10000]. + + If the cgroup has been configured to be SCHED_IDLE (cpu.idle = 1), + then the weight will show as a 0. cpu.weight.nice A read-write single value file which exists on non-root @@ -1157,6 +1161,16 @@ All time durations are in microseconds. values similar to the sched_setattr(2). This maximum utilization value is used to clamp the task specific maximum utilization clamp. + cpu.idle + A read-write single value file which exists on non-root cgroups. + The default is 0. + + This is the cgroup analog of the per-task SCHED_IDLE sched policy. + Setting this value to a 1 will make the scheduling policy of the + cgroup SCHED_IDLE. The threads inside the cgroup will retain their + own relative priorities, but the cgroup itself will be treated as + very low priority relative to its peers. + Memory @@ -2316,6 +2330,13 @@ Cpuset Interface Files treated to have an implicit value of "cpuset.cpus" in the formation of local partition. + cpuset.cpus.isolated + A read-only and root cgroup only multiple values file. + + This file shows the set of all isolated CPUs used in existing + isolated partitions. It will be empty if no isolated partition + is created. + cpuset.cpus.partition A read-write single value file which exists on non-root cpuset-enabled cgroups. This flag is owned by the parent cgroup @@ -2358,11 +2379,11 @@ Cpuset Interface Files partition or scheduling domain. The set of exclusive CPUs is determined by the value of its "cpuset.cpus.exclusive.effective". - When set to "isolated", the CPUs in that partition will - be in an isolated state without any load balancing from the - scheduler. Tasks placed in such a partition with multiple - CPUs should be carefully distributed and bound to each of the - individual CPUs for optimal performance. + When set to "isolated", the CPUs in that partition will be in + an isolated state without any load balancing from the scheduler + and excluded from the unbound workqueues. Tasks placed in such + a partition with multiple CPUs should be carefully distributed + and bound to each of the individual CPUs for optimal performance. A partition root ("root" or "isolated") can be in one of the two possible states - valid or invalid. An invalid partition diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4a6b6b77ccb6c3..ea48c861cd3695 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -496,6 +496,20 @@ struct cgroup { struct cgroup_rstat_cpu __percpu *rstat_cpu; struct list_head rstat_css_list; + /* + * Add padding to separate the read mostly rstat_cpu and + * rstat_css_list into a different cacheline from the following + * rstat_flush_next and *bstat fields which can have frequent updates. + */ + CACHELINE_PADDING(_pad_); + + /* + * A singly-linked list of cgroup structures to be rstat flushed. + * This is a scratch field to be used exclusively by + * cgroup_rstat_flush_locked() and protected by cgroup_rstat_lock. + */ + struct cgroup *rstat_flush_next; + /* cgroup basic resource statistics */ struct cgroup_base_stat last_bstat; struct cgroup_base_stat bstat; @@ -548,6 +562,10 @@ struct cgroup_root { /* Unique id for this hierarchy. */ int hierarchy_id; + /* A list running through the active hierarchies */ + struct list_head root_list; + struct rcu_head rcu; /* Must be near the top */ + /* * The root cgroup. The containing cgroup_root will be destroyed on its * release. cgrp->ancestors[0] will be used overflowing into the @@ -561,9 +579,6 @@ struct cgroup_root { /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ atomic_t nr_cgrps; - /* A list running through the active hierarchies */ - struct list_head root_list; - /* Hierarchy-specific flags */ unsigned int flags; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 0ef0af66080ed0..34aaf0e87def8f 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -69,6 +69,7 @@ struct css_task_iter { extern struct file_system_type cgroup_fs_type; extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; +extern spinlock_t css_set_lock; #define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; #include <linux/cgroup_subsys.h> @@ -386,7 +387,6 @@ static inline void cgroup_unlock(void) * as locks used during the cgroup_subsys::attach() methods. */ #ifdef CONFIG_PROVE_RCU -extern spinlock_t css_set_lock; #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ rcu_read_lock_sched_held() || \ @@ -853,4 +853,6 @@ static inline void cgroup_bpf_put(struct cgroup *cgrp) {} #endif /* CONFIG_CGROUP_BPF */ +struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id); + #endif /* _LINUX_CGROUP_H */ diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index d629094fac6e66..875d12598bd2d4 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -77,6 +77,7 @@ extern void cpuset_lock(void); extern void cpuset_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern bool cpuset_cpus_allowed_fallback(struct task_struct *p); +extern bool cpuset_cpu_is_isolated(int cpu); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); @@ -207,6 +208,11 @@ static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p) return false; } +static inline bool cpuset_cpu_is_isolated(int cpu) +{ + return false; +} + static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) { return node_possible_map; diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index fe1a46f30d2409..2b461129d1fad0 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -2,6 +2,7 @@ #define _LINUX_SCHED_ISOLATION_H #include <linux/cpumask.h> +#include <linux/cpuset.h> #include <linux/init.h> #include <linux/tick.h> @@ -67,7 +68,8 @@ static inline bool housekeeping_cpu(int cpu, enum hk_type type) static inline bool cpu_is_isolated(int cpu) { return !housekeeping_test_cpu(cpu, HK_TYPE_DOMAIN) || - !housekeeping_test_cpu(cpu, HK_TYPE_TICK); + !housekeeping_test_cpu(cpu, HK_TYPE_TICK) || + cpuset_cpu_is_isolated(cpu); } #endif /* _LINUX_SCHED_ISOLATION_H */ diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 24b1e5070f4d43..b0b9604b76b88a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -491,7 +491,7 @@ struct workqueue_attrs *alloc_workqueue_attrs(void); void free_workqueue_attrs(struct workqueue_attrs *attrs); int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs); -int workqueue_set_unbound_cpumask(cpumask_var_t cpumask); +extern int workqueue_unbound_exclude_cpumask(cpumask_var_t cpumask); extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index c56071f150f2ae..520b90dd97ecae 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -164,13 +164,13 @@ struct cgroup_mgctx { #define DEFINE_CGROUP_MGCTX(name) \ struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name) -extern spinlock_t css_set_lock; extern struct cgroup_subsys *cgroup_subsys[]; extern struct list_head cgroup_roots; /* iterate across the hierarchies */ #define for_each_root(root) \ - list_for_each_entry((root), &cgroup_roots, root_list) + list_for_each_entry_rcu((root), &cgroup_roots, root_list, \ + lockdep_is_held(&cgroup_mutex)) /** * for_each_subsys - iterate all enabled cgroup subsystems diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 76db6c67e39a92..04d11a7dd95f9b 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -1262,6 +1262,40 @@ int cgroup1_get_tree(struct fs_context *fc) return ret; } +/** + * task_get_cgroup1 - Acquires the associated cgroup of a task within a + * specific cgroup1 hierarchy. The cgroup1 hierarchy is identified by its + * hierarchy ID. + * @tsk: The target task + * @hierarchy_id: The ID of a cgroup1 hierarchy + * + * On success, the cgroup is returned. On failure, ERR_PTR is returned. + * We limit it to cgroup1 only. + */ +struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id) +{ + struct cgroup *cgrp = ERR_PTR(-ENOENT); + struct cgroup_root *root; + unsigned long flags; + + rcu_read_lock(); + for_each_root(root) { + /* cgroup1 only*/ + if (root == &cgrp_dfl_root) + continue; + if (root->hierarchy_id != hierarchy_id) + continue; + spin_lock_irqsave(&css_set_lock, flags); + cgrp = task_cgroup_from_root(tsk, root); + if (!cgrp || !cgroup_tryget(cgrp)) + cgrp = ERR_PTR(-ENOENT); + spin_unlock_irqrestore(&css_set_lock, flags); + break; + } + rcu_read_unlock(); + return cgrp; +} + static int __init cgroup1_wq_init(void) { /* diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 4b9ff41ca603a3..8f3cef1a4d8a74 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1315,7 +1315,7 @@ static void cgroup_exit_root_id(struct cgroup_root *root) void cgroup_free_root(struct cgroup_root *root) { - kfree(root); + kfree_rcu(root, rcu); } static void cgroup_destroy_root(struct cgroup_root *root) @@ -1347,10 +1347,9 @@ static void cgroup_destroy_root(struct cgroup_root *root) spin_unlock_irq(&css_set_lock); - if (!list_empty(&root->root_list)) { - list_del(&root->root_list); - cgroup_root_count--; - } + WARN_ON_ONCE(list_empty(&root->root_list)); + list_del_rcu(&root->root_list); + cgroup_root_count--; if (!have_favordynmods) cgroup_favor_dynmods(root, false); @@ -1390,7 +1389,15 @@ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset, } } - BUG_ON(!res_cgroup); + /* + * If cgroup_mutex is not held, the cgrp_cset_link will be freed + * before we remove the cgroup root from the root_list. Consequently, + * when accessing a cgroup root, the cset_link may have already been + * freed, resulting in a NULL res_cgroup. However, by holding the + * cgroup_mutex, we ensure that res_cgroup can't be NULL. + * If we don't hold cgroup_mutex in the caller, we must do the NULL + * check. + */ return res_cgroup; } @@ -1413,6 +1420,11 @@ current_cgns_cgroup_from_root(struct cgroup_root *root) rcu_read_unlock(); + /* + * The namespace_sem is held by current, so the root cgroup can't + * be umounted. Therefore, we can ensure that the res is non-NULL. + */ + WARN_ON_ONCE(!res); return res; } @@ -1449,7 +1461,6 @@ static struct cgroup *current_cgns_cgroup_dfl(void) static struct cgroup *cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { - lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock); return __cset_cgroup_from_root(cset, root); @@ -1457,7 +1468,9 @@ static struct cgroup *cset_cgroup_from_root(struct css_set *cset, /* * Return the cgroup for "task" from the given hierarchy. Must be - * called with cgroup_mutex and css_set_lock held. + * called with css_set_lock held to prevent task's groups from being modified. + * Must be called with either cgroup_mutex or rcu read lock to prevent the + * cgroup root from being destroyed. */ struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroup_root *root) @@ -2032,7 +2045,7 @@ void init_cgroup_root(struct cgroup_fs_context *ctx) struct cgroup_root *root = ctx->root; struct cgroup *cgrp = &root->cgrp; - INIT_LIST_HEAD(&root->root_list); + INIT_LIST_HEAD_RCU(&root->root_list); atomic_set(&root->nr_cgrps, 1); cgrp->root = root; init_cgroup_housekeeping(cgrp); @@ -2115,7 +2128,7 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) * care of subsystems' refcounts, which are explicitly dropped in * the failure exit path. */ - list_add(&root->root_list, &cgroup_roots); + list_add_rcu(&root->root_list, &cgroup_roots); cgroup_root_count++; /* @@ -6265,7 +6278,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, if (!buf) goto out; - cgroup_lock(); + rcu_read_lock(); spin_lock_irq(&css_set_lock); for_each_root(root) { @@ -6276,6 +6289,11 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, if (root == &cgrp_dfl_root && !READ_ONCE(cgrp_dfl_visible)) continue; + cgrp = task_cgroup_from_root(tsk, root); + /* The root has already been unmounted. */ + if (!cgrp) + continue; + seq_printf(m, "%d:", root->hierarchy_id); if (root != &cgrp_dfl_root) for_each_subsys(ss, ssid) @@ -6286,9 +6304,6 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, seq_printf(m, "%sname=%s", count ? "," : "", root->name); seq_putc(m, ':'); - - cgrp = task_cgroup_from_root(tsk, root); - /* * On traditional hierarchies, all zombie tasks show up as * belonging to the root cgroup. On the default hierarchy, @@ -6320,7 +6335,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, retval = 0; out_unlock: spin_unlock_irq(&css_set_lock); - cgroup_unlock(); + rcu_read_unlock(); kfree(buf); out: return retval; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 615daaf87f1fc8..dfbb16aca9f415 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -25,6 +25,7 @@ #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/cpuset.h> +#include <linux/delay.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/kernel.h> @@ -43,6 +44,7 @@ #include <linux/sched/isolation.h> #include <linux/cgroup.h> #include <linux/wait.h> +#include <linux/workqueue.h> DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key); DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key); @@ -204,6 +206,11 @@ struct cpuset { */ static cpumask_var_t subpartitions_cpus; +/* + * Exclusive CPUs in isolated partitions + */ +static cpumask_var_t isolated_cpus; + /* List of remote partition root children */ static struct list_head remote_children; @@ -1317,6 +1324,7 @@ static void compute_effective_cpumask(struct cpumask *new_cpus, */ enum partition_cmd { partcmd_enable, /* Enable partition root */ + partcmd_enablei, /* Enable isolated partition root */ partcmd_disable, /* Disable partition root */ partcmd_update, /* Update parent's effective_cpus */ partcmd_invalidate, /* Make partition invalid */ @@ -1419,6 +1427,109 @@ static void reset_partition_data(struct cpuset *cs) } /* + * partition_xcpus_newstate - Exclusive CPUs state change + * @old_prs: old partition_root_state + * @new_prs: new partition_root_state + * @xcpus: exclusive CPUs with state change + */ +static void partition_xcpus_newstate(int old_prs, int new_prs, struct cpumask *xcpus) +{ + WARN_ON_ONCE(old_prs == new_prs); + if (new_prs == PRS_ISOLATED) + cpumask_or(isolated_cpus, isolated_cpus, xcpus); + else + cpumask_andnot(isolated_cpus, isolated_cpus, xcpus); +} + +/* + * partition_xcpus_add - Add new exclusive CPUs to partition + * @new_prs: new partition_root_state + * @parent: parent cpuset + * @xcpus: exclusive CPUs to be added + * Return: true if isolated_cpus modified, false otherwise + * + * Remote partition if parent == NULL + */ +static bool partition_xcpus_add(int new_prs, struct cpuset *parent, + struct cpumask *xcpus) +{ + bool isolcpus_updated; + + WARN_ON_ONCE(new_prs < 0); + lockdep_assert_held(&callback_lock); + if (!parent) + parent = &top_cpuset; + + + if (parent == &top_cpuset) + cpumask_or(subpartitions_cpus, subpartitions_cpus, xcpus); + + isolcpus_updated = (new_prs != parent->partition_root_state); + if (isolcpus_updated) + partition_xcpus_newstate(parent->partition_root_state, new_prs, + xcpus); + + cpumask_andnot(parent->effective_cpus, parent->effective_cpus, xcpus); + return isolcpus_updated; +} + +/* + * partition_xcpus_del - Remove exclusive CPUs from partition + * @old_prs: old partition_root_state + * @parent: parent cpuset + * @xcpus: exclusive CPUs to be removed + * Return: true if isolated_cpus modified, false otherwise + * + * Remote partition if parent == NULL + */ +static bool partition_xcpus_del(int old_prs, struct cpuset *parent, + struct cpumask *xcpus) +{ + bool isolcpus_updated; + + WARN_ON_ONCE(old_prs < 0); + lockdep_assert_held(&callback_lock); + if (!parent) + parent = &top_cpuset; + + if (parent == &top_cpuset) + cpumask_andnot(subpartitions_cpus, subpartitions_cpus, xcpus); + + isolcpus_updated = (old_prs != parent->partition_root_state); + if (isolcpus_updated) + partition_xcpus_newstate(old_prs, parent->partition_root_state, + xcpus); + + cpumask_and(xcpus, xcpus, cpu_active_mask); + cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus); + return isolcpus_updated; +} + +static void update_unbound_workqueue_cpumask(bool isolcpus_updated) +{ + int ret; + + lockdep_assert_cpus_held(); + + if (!isolcpus_updated) + return; + + ret = workqueue_unbound_exclude_cpumask(isolated_cpus); + WARN_ON_ONCE(ret < 0); +} + +/** + * cpuset_cpu_is_isolated - Check if the given CPU is isolated + * @cpu: the CPU number to be checked + * Return: true if CPU is used in an isolated partition, false otherwise + */ +bool cpuset_cpu_is_isolated(int cpu) +{ + return cpumask_test_cpu(cpu, isolated_cpus); +} +EXPORT_SYMBOL_GPL(cpuset_cpu_is_isolated); + +/* * compute_effective_exclusive_cpumask - compute effective exclusive CPUs * @cs: cpuset * @xcpus: effective exclusive CPUs value to be set @@ -1456,14 +1567,18 @@ static inline bool is_local_partition(struct cpuset *cs) /* * remote_partition_enable - Enable current cpuset as a remote partition root * @cs: the cpuset to update + * @new_prs: new partition_root_state * @tmp: temparary masks * Return: 1 if successful, 0 if error * * Enable the current cpuset to become a remote partition root taking CPUs * directly from the top cpuset. cpuset_mutex must be held by the caller. */ -static int remote_partition_enable(struct cpuset *cs, struct tmpmasks *tmp) +static int remote_partition_enable(struct cpuset *cs, int new_prs, + struct tmpmasks *tmp) { + bool isolcpus_updated; + /* * The user must have sysadmin privilege. */ @@ -1485,26 +1600,22 @@ static int remote_partition_enable(struct cpuset *cs, struct tmpmasks *tmp) return 0; spin_lock_irq(&callback_lock); - cpumask_andnot(top_cpuset.effective_cpus, - top_cpuset.effective_cpus, tmp->new_cpus); - cpumask_or(subpartitions_cpus, - subpartitions_cpus, tmp->new_cpus); - + isolcpus_updated = partition_xcpus_add(new_prs, NULL, tmp->new_cpus); + list_add(&cs->remote_sibling, &remote_children); if (cs->use_parent_ecpus) { struct cpuset *parent = parent_cs(cs); cs->use_parent_ecpus = false; parent->child_ecpus_count--; } - list_add(&cs->remote_sibling, &remote_children); spin_unlock_irq(&callback_lock); + update_unbound_workqueue_cpumask(isolcpus_updated); /* * Proprogate changes in top_cpuset's effective_cpus down the hierarchy. */ update_tasks_cpumask(&top_cpuset, tmp->new_cpus); update_sibling_cpumasks(&top_cpuset, NULL, tmp); - return 1; } @@ -1519,23 +1630,22 @@ static int remote_partition_enable(struct cpuset *cs, struct tmpmasks *tmp) */ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp) { + bool isolcpus_updated; + compute_effective_exclusive_cpumask(cs, tmp->new_cpus); WARN_ON_ONCE(!is_remote_partition(cs)); WARN_ON_ONCE(!cpumask_subset(tmp->new_cpus, subpartitions_cpus)); spin_lock_irq(&callback_lock); - cpumask_andnot(subpartitions_cpus, - subpartitions_cpus, tmp->new_cpus); - cpumask_and(tmp->new_cpus, - tmp->new_cpus, cpu_active_mask); - cpumask_or(top_cpuset.effective_cpus, - top_cpuset.effective_cpus, tmp->new_cpus); list_del_init(&cs->remote_sibling); + isolcpus_updated = partition_xcpus_del(cs->partition_root_state, + NULL, tmp->new_cpus); cs->partition_root_state = -cs->partition_root_state; if (!cs->prs_err) cs->prs_err = PERR_INVCPUS; reset_partition_data(cs); spin_unlock_irq(&callback_lock); + update_unbound_workqueue_cpumask(isolcpus_updated); /* * Proprogate changes in top_cpuset's effective_cpus down the hierarchy. @@ -1557,6 +1667,8 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask, struct tmpmasks *tmp) { bool adding, deleting; + int prs = cs->partition_root_state; + int isolcpus_updated = 0; if (WARN_ON_ONCE(!is_remote_partition(cs))) return; @@ -1580,21 +1692,12 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *newmask, goto invalidate; spin_lock_irq(&callback_lock); - if (adding) { - cpumask_or(subpartitions_cpus, - subpartitions_cpus, tmp->addmask); - cpumask_andnot(top_cpuset.effective_cpus, - top_cpuset.effective_cpus, tmp->addmask); - } - if (deleting) { - cpumask_andnot(subpartitions_cpus, - subpartitions_cpus, tmp->delmask); - cpumask_and(tmp->delmask, - tmp->delmask, cpu_active_mask); - cpumask_or(top_cpuset.effective_cpus, - top_cpuset.effective_cpus, tmp->delmask); - } + if (adding) + isolcpus_updated += partition_xcpus_add(prs, NULL, tmp->addmask); + if (deleting) + isolcpus_updated += partition_xcpus_del(prs, NULL, tmp->delmask); spin_unlock_irq(&callback_lock); + update_unbound_workqueue_cpumask(isolcpus_updated); /* * Proprogate changes in top_cpuset's effective_cpus down the hierarchy. @@ -1676,11 +1779,11 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus) * @tmp: Temporary addmask and delmask * 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 effective_xcpus (cpus_allowed if effective_xcpus - * not set) mask of the given cpuset will be taken away from parent's - * effective_cpus. The function will return 0 if all the CPUs listed in - * effective_xcpus can be granted or an error code will be returned. + * For partcmd_enable*, the cpuset is being transformed from a non-partition + * root to a partition root. The effective_xcpus (cpus_allowed if + * effective_xcpus not set) mask of the given cpuset will be taken away from + * parent's effective_cpus. The function will return 0 if all the CPUs listed + * in effective_xcpus can be granted or an error code will be returned. * * For partcmd_disable, the cpuset is being transformed from a partition * root back to a non-partition root. Any CPUs in effective_xcpus will be @@ -1695,7 +1798,7 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus) * * For partcmd_invalidate, the current partition will be made invalid. * - * The partcmd_enable and partcmd_disable commands are used by + * The partcmd_enable* and partcmd_disable commands are used by * update_prstate(). An error code may be returned and the caller will check * for error. * @@ -1716,6 +1819,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, int part_error = PERR_NONE; /* Partition error? */ int subparts_delta = 0; struct cpumask *xcpus; /* cs effective_xcpus */ + int isolcpus_updated = 0; bool nocpu; lockdep_assert_held(&cpuset_mutex); @@ -1760,7 +1864,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, nocpu = tasks_nocpu_error(parent, cs, xcpus); - if (cmd == partcmd_enable) { + if ((cmd == partcmd_enable) || (cmd == partcmd_enablei)) { /* * Enabling partition root is not allowed if its * effective_xcpus is empty or doesn't overlap with @@ -1783,6 +1887,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, cpumask_copy(tmp->delmask, xcpus); deleting = true; subparts_delta++; + new_prs = (cmd == partcmd_enable) ? PRS_ROOT : PRS_ISOLATED; } else if (cmd == partcmd_disable) { /* * May need to add cpus to parent's effective_cpus for @@ -1792,6 +1897,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, cpumask_and(tmp->addmask, xcpus, parent->effective_xcpus); if (adding) subparts_delta--; + new_prs = PRS_MEMBER; } else if (newmask) { /* * Empty cpumask is not allowed @@ -1940,38 +2046,28 @@ write_error: * newly deleted ones will be added back to effective_cpus. */ spin_lock_irq(&callback_lock); - if (adding) { - if (parent == &top_cpuset) - cpumask_andnot(subpartitions_cpus, - subpartitions_cpus, tmp->addmask); - /* - * Some of the CPUs in effective_xcpus might have been offlined. - */ - cpumask_or(parent->effective_cpus, - parent->effective_cpus, tmp->addmask); - cpumask_and(parent->effective_cpus, - parent->effective_cpus, cpu_active_mask); - } - if (deleting) { - if (parent == &top_cpuset) - cpumask_or(subpartitions_cpus, - subpartitions_cpus, tmp->delmask); - cpumask_andnot(parent->effective_cpus, - parent->effective_cpus, tmp->delmask); - } - - if (is_partition_valid(parent)) { - parent->nr_subparts += subparts_delta; - WARN_ON_ONCE(parent->nr_subparts < 0); - } - if (old_prs != new_prs) { cs->partition_root_state = new_prs; if (new_prs <= 0) cs->nr_subparts = 0; } + /* + * Adding to parent's effective_cpus means deletion CPUs from cs + * and vice versa. + */ + if (adding) + isolcpus_updated += partition_xcpus_del(old_prs, parent, + tmp->addmask); + if (deleting) + isolcpus_updated += partition_xcpus_add(new_prs, parent, + tmp->delmask); + if (is_partition_valid(parent)) { + parent->nr_subparts += subparts_delta; + WARN_ON_ONCE(parent->nr_subparts < 0); + } spin_unlock_irq(&callback_lock); + update_unbound_workqueue_cpumask(isolcpus_updated); if ((old_prs != new_prs) && (cmd == partcmd_update)) update_partition_exclusive(cs, new_prs); @@ -2948,6 +3044,7 @@ static int update_prstate(struct cpuset *cs, int new_prs) int err = PERR_NONE, old_prs = cs->partition_root_state; struct cpuset *parent = parent_cs(cs); struct tmpmasks tmpmask; + bool new_xcpus_state = false; if (old_prs == new_prs) return 0; @@ -2977,6 +3074,9 @@ static int update_prstate(struct cpuset *cs, int new_prs) goto out; if (!old_prs) { + enum partition_cmd cmd = (new_prs == PRS_ROOT) + ? partcmd_enable : partcmd_enablei; + /* * cpus_allowed cannot be empty. */ @@ -2985,19 +3085,18 @@ static int update_prstate(struct cpuset *cs, int new_prs) goto out; } - err = update_parent_effective_cpumask(cs, partcmd_enable, - NULL, &tmpmask); + err = update_parent_effective_cpumask(cs, cmd, NULL, &tmpmask); /* * If an attempt to become local partition root fails, * try to become a remote partition root instead. */ - if (err && remote_partition_enable(cs, &tmpmask)) + if (err && remote_partition_enable(cs, new_prs, &tmpmask)) err = 0; } else if (old_prs && new_prs) { /* * A change in load balance state only, no change in cpumasks. */ - ; + new_xcpus_state = true; } else { /* * Switching back to member is always allowed even if it @@ -3029,7 +3128,10 @@ out: WRITE_ONCE(cs->prs_err, err); if (!is_partition_valid(cs)) reset_partition_data(cs); + else if (new_xcpus_state) + partition_xcpus_newstate(old_prs, new_prs, cs->effective_xcpus); spin_unlock_irq(&callback_lock); + update_unbound_workqueue_cpumask(new_xcpus_state); /* Force update if switching back to member */ update_cpumasks_hier(cs, &tmpmask, !new_prs ? HIER_CHECKALL : 0); @@ -3386,6 +3488,7 @@ typedef enum { FILE_SUBPARTS_CPULIST, FILE_EXCLUSIVE_CPULIST, FILE_EFFECTIVE_XCPULIST, + FILE_ISOLATED_CPULIST, FILE_CPU_EXCLUSIVE, FILE_MEM_EXCLUSIVE, FILE_MEM_HARDWALL, @@ -3582,6 +3685,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v) case FILE_SUBPARTS_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(subpartitions_cpus)); break; + case FILE_ISOLATED_CPULIST: + seq_printf(sf, "%*pbl\n", cpumask_pr_args(isolated_cpus)); + break; default: ret = -EINVAL; } @@ -3875,6 +3981,13 @@ static struct cftype dfl_files[] = { .flags = CFTYPE_ONLY_ON_ROOT | CFTYPE_DEBUG, }, + { + .name = "cpus.isolated", + .seq_show = cpuset_common_seq_show, + .private = FILE_ISOLATED_CPULIST, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + { } /* terminate */ }; @@ -4194,6 +4307,7 @@ int __init cpuset_init(void) BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_xcpus, GFP_KERNEL)); 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)); cpumask_setall(top_cpuset.cpus_allowed); nodes_setall(top_cpuset.mems_allowed); @@ -4306,6 +4420,30 @@ void cpuset_force_rebuild(void) force_rebuild = true; } +/* + * Attempt to acquire a cpus_read_lock while a hotplug operation may be in + * progress. + * Return: true if successful, false otherwise + * + * To avoid circular lock dependency between cpuset_mutex and cpus_read_lock, + * cpus_read_trylock() is used here to acquire the lock. + */ +static bool cpuset_hotplug_cpus_read_trylock(void) +{ + int retries = 0; + + while (!cpus_read_trylock()) { + /* + * CPU hotplug still in progress. Retry 5 times + * with a 10ms wait before bailing out. + */ + if (++retries > 5) + return false; + msleep(10); + } + return true; +} + /** * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug * @cs: cpuset in interest @@ -4322,6 +4460,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) bool cpus_updated; bool mems_updated; bool remote; + int partcmd = -1; struct cpuset *parent; retry: wait_event(cpuset_attach_wq, cs->attach_in_progress == 0); @@ -4353,11 +4492,13 @@ retry: compute_partition_effective_cpumask(cs, &new_cpus); if (remote && cpumask_empty(&new_cpus) && - partition_is_populated(cs, NULL)) { + partition_is_populated(cs, NULL) && + cpuset_hotplug_cpus_read_trylock()) { remote_partition_disable(cs, tmp); compute_effective_cpumask(&new_cpus, cs, parent); remote = false; cpuset_force_rebuild(); + cpus_read_unlock(); } /* @@ -4368,18 +4509,28 @@ retry: * partitions. */ if (is_local_partition(cs) && (!is_partition_valid(parent) || - tasks_nocpu_error(parent, cs, &new_cpus))) { - update_parent_effective_cpumask(cs, partcmd_invalidate, NULL, tmp); - compute_effective_cpumask(&new_cpus, cs, parent); - cpuset_force_rebuild(); - } + tasks_nocpu_error(parent, cs, &new_cpus))) + partcmd = partcmd_invalidate; /* * On the other hand, an invalid partition root may be transitioned * back to a regular one. */ - else if (is_partition_valid(parent) && is_partition_invalid(cs)) { - update_parent_effective_cpumask(cs, partcmd_update, NULL, tmp); - if (is_partition_valid(cs)) { + else if (is_partition_valid(parent) && is_partition_invalid(cs)) + partcmd = partcmd_update; + + /* + * cpus_read_lock needs to be held before calling + * update_parent_effective_cpumask(). To avoid circular lock + * dependency between cpuset_mutex and cpus_read_lock, + * cpus_read_trylock() is used here to acquire the lock. + */ + if (partcmd >= 0) { + if (!cpuset_hotplug_cpus_read_trylock()) + goto update_tasks; + + update_parent_effective_cpumask(cs, partcmd, NULL, tmp); + cpus_read_unlock(); + if ((partcmd == partcmd_invalidate) || is_partition_valid(cs)) { compute_partition_effective_cpumask(cs, &new_cpus); cpuset_force_rebuild(); } diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index c0adb7254b45ae..a8350d2d63e6b1 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -74,64 +74,109 @@ __bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) } /** - * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree - * @pos: current position - * @root: root of the tree to traversal + * cgroup_rstat_push_children - push children cgroups into the given list + * @head: current head of the list (= subtree root) + * @child: first child of the root * @cpu: target cpu + * Return: A new singly linked list of cgroups to be flush * - * Walks the updated rstat_cpu tree on @cpu from @root. %NULL @pos starts - * the traversal and %NULL return indicates the end. During traversal, - * each returned cgroup is unlinked from the tree. Must be called with the - * matching cgroup_rstat_cpu_lock held. + * Iteratively traverse down the cgroup_rstat_cpu updated tree level by + * level and push all the parents first before their next level children + * into a singly linked list built from the tail backward like "pushing" + * cgroups into a stack. The root is pushed by the caller. + */ +static struct cgroup *cgroup_rstat_push_children(struct cgroup *head, + struct cgroup *child, int cpu) +{ + struct cgroup *chead = child; /* Head of child cgroup level */ + struct cgroup *ghead = NULL; /* Head of grandchild cgroup level */ + struct cgroup *parent, *grandchild; + struct cgroup_rstat_cpu *crstatc; + + child->rstat_flush_next = NULL; + +next_level: + while (chead) { + child = chead; + chead = child->rstat_flush_next; + parent = cgroup_parent(child); + + /* updated_next is parent cgroup terminated */ + while (child != parent) { + child->rstat_flush_next = head; + head = child; + crstatc = cgroup_rstat_cpu(child, cpu); + grandchild = crstatc->updated_children; + if (grandchild != child) { + /* Push the grand child to the next level */ + crstatc->updated_children = child; + grandchild->rstat_flush_next = ghead; + ghead = grandchild; + } + child = crstatc->updated_next; + crstatc->updated_next = NULL; + } + } + + if (ghead) { + chead = ghead; + ghead = NULL; + goto next_level; + } + return head; +} + +/** + * cgroup_rstat_updated_list - return a list of updated cgroups to be flushed + * @root: root of the cgroup subtree to traverse + * @cpu: target cpu + * Return: A singly linked list of cgroups to be flushed + * + * Walks the updated rstat_cpu tree on @cpu from @root. During traversal, + * each returned cgroup is unlinked from the updated tree. * * The only ordering guarantee is that, for a parent and a child pair - * covered by a given traversal, if a child is visited, its parent is - * guaranteed to be visited afterwards. + * covered by a given traversal, the child is before its parent in + * the list. + * + * Note that updated_children is self terminated and points to a list of + * child cgroups if not empty. Whereas updated_next is like a sibling link + * within the children list and terminated by the parent cgroup. An exception + * here is the cgroup root whose updated_next can be self terminated. */ -static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, - struct cgroup *root, int cpu) +static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu) { - struct cgroup_rstat_cpu *rstatc; - struct cgroup *parent; - - if (pos == root) - return NULL; + raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); + struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(root, cpu); + struct cgroup *head = NULL, *parent, *child; + unsigned long flags; /* - * We're gonna walk down to the first leaf and visit/remove it. We - * can pick whatever unvisited node as the starting point. + * The _irqsave() is needed because cgroup_rstat_lock is + * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring + * this lock with the _irq() suffix only disables interrupts on + * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables + * interrupts on both configurations. The _irqsave() ensures + * that interrupts are always disabled and later restored. */ - if (!pos) { - pos = root; - /* return NULL if this subtree is not on-list */ - if (!cgroup_rstat_cpu(pos, cpu)->updated_next) - return NULL; - } else { - pos = cgroup_parent(pos); - } + raw_spin_lock_irqsave(cpu_lock, flags); - /* walk down to the first leaf */ - while (true) { - rstatc = cgroup_rstat_cpu(pos, cpu); - if (rstatc->updated_children == pos) - break; - pos = rstatc->updated_children; - } + /* Return NULL if this subtree is not on-list */ + if (!rstatc->updated_next) + goto unlock_ret; /* - * Unlink @pos from the tree. As the updated_children list is + * Unlink @root from its parent. As the updated_children list is * singly linked, we have to walk it to find the removal point. - * However, due to the way we traverse, @pos will be the first - * child in most cases. The only exception is @root. */ - parent = cgroup_parent(pos); + parent = cgroup_parent(root); if (parent) { struct cgroup_rstat_cpu *prstatc; struct cgroup **nextp; prstatc = cgroup_rstat_cpu(parent, cpu); nextp = &prstatc->updated_children; - while (*nextp != pos) { + while (*nextp != root) { struct cgroup_rstat_cpu *nrstatc; nrstatc = cgroup_rstat_cpu(*nextp, cpu); @@ -142,7 +187,17 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, } rstatc->updated_next = NULL; - return pos; + + /* Push @root to the list first before pushing the children */ + head = root; + root->rstat_flush_next = NULL; + child = rstatc->updated_children; + rstatc->updated_children = root; + if (child != root) + head = cgroup_rstat_push_children(head, child, cpu); +unlock_ret: + raw_spin_unlock_irqrestore(cpu_lock, flags); + return head; } /* @@ -176,21 +231,9 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp) lockdep_assert_held(&cgroup_rstat_lock); for_each_possible_cpu(cpu) { - raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, - cpu); - struct cgroup *pos = NULL; - unsigned long flags; + struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu); - /* - * The _irqsave() is needed because cgroup_rstat_lock is - * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring - * this lock with the _irq() suffix only disables interrupts on - * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables - * interrupts on both configurations. The _irqsave() ensures - * that interrupts are always disabled and later restored. - */ - raw_spin_lock_irqsave(cpu_lock, flags); - while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) { + for (; pos; pos = pos->rstat_flush_next) { struct cgroup_subsys_state *css; cgroup_base_stat_flush(pos, cpu); @@ -202,7 +245,6 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp) css->ss->css_rstat_flush(css, cpu); rcu_read_unlock(); } - raw_spin_unlock_irqrestore(cpu_lock, flags); /* play nice and yield if necessary */ if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) { diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 2989b57e154a76..76e60faed89235 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -381,6 +381,12 @@ static bool workqueue_freezing; /* PL: have wqs started freezing? */ /* PL&A: allowable cpus for unbound wqs and work items */ static cpumask_var_t wq_unbound_cpumask; +/* PL: user requested unbound cpumask via sysfs */ +static cpumask_var_t wq_requested_unbound_cpumask; + +/* PL: isolated cpumask to be excluded from unbound cpumask */ +static cpumask_var_t wq_isolated_cpumask; + /* for further constrain wq_unbound_cpumask by cmdline parameter*/ static struct cpumask wq_cmdline_cpumask __initdata; @@ -4408,19 +4414,6 @@ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx) mutex_unlock(&ctx->wq->mutex); } -static void apply_wqattrs_lock(void) -{ - /* CPUs should stay stable across pwq creations and installations */ - cpus_read_lock(); - mutex_lock(&wq_pool_mutex); -} - -static void apply_wqattrs_unlock(void) -{ - mutex_unlock(&wq_pool_mutex); - cpus_read_unlock(); -} - static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { @@ -5825,39 +5818,40 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) } /** - * workqueue_set_unbound_cpumask - Set the low-level unbound cpumask - * @cpumask: the cpumask to set - * - * The low-level workqueues cpumask is a global cpumask that limits - * the affinity of all unbound workqueues. This function check the @cpumask - * and apply it to all unbound workqueues and updates all pwqs of them. + * workqueue_unbound_exclude_cpumask - Exclude given CPUs from unbound cpumask + * @exclude_cpumask: the cpumask to be excluded from wq_unbound_cpumask * - * Return: 0 - Success - * -EINVAL - Invalid @cpumask - * -ENOMEM - Failed to allocate memory for attrs or pwqs. + * This function can be called from cpuset code to provide a set of isolated + * CPUs that should be excluded from wq_unbound_cpumask. The caller must hold + * either cpus_read_lock or cpus_write_lock. */ -int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) +int workqueue_unbound_exclude_cpumask(cpumask_var_t exclude_cpumask) { - int ret = -EINVAL; + cpumask_var_t cpumask; + int ret = 0; + + if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) + return -ENOMEM; + + lockdep_assert_cpus_held(); + mutex_lock(&wq_pool_mutex); + + /* Save the current isolated cpumask & export it via sysfs */ + cpumask_copy(wq_isolated_cpumask, exclude_cpumask); /* - * Not excluding isolated cpus on purpose. - * If the user wishes to include them, we allow that. + * If the operation fails, it will fall back to + * wq_requested_unbound_cpumask which is initially set to + * (HK_TYPE_WQ ∩ HK_TYPE_DOMAIN) house keeping mask and rewritten + * by any subsequent write to workqueue/cpumask sysfs file. */ - cpumask_and(cpumask, cpumask, cpu_possible_mask); - if (!cpumask_empty(cpumask)) { - apply_wqattrs_lock(); - if (cpumask_equal(cpumask, wq_unbound_cpumask)) { - ret = 0; - goto out_unlock; - } - + if (!cpumask_andnot(cpumask, wq_requested_unbound_cpumask, exclude_cpumask)) + cpumask_copy(cpumask, wq_requested_unbound_cpumask); + if (!cpumask_equal(cpumask, wq_unbound_cpumask)) ret = workqueue_apply_unbound_cpumask(cpumask); -out_unlock: - apply_wqattrs_unlock(); - } - + mutex_unlock(&wq_pool_mutex); + free_cpumask_var(cpumask); return ret; } @@ -5979,6 +5973,19 @@ static struct attribute *wq_sysfs_attrs[] = { }; ATTRIBUTE_GROUPS(wq_sysfs); +static void apply_wqattrs_lock(void) +{ + /* CPUs should stay stable across pwq creations and installations */ + cpus_read_lock(); + mutex_lock(&wq_pool_mutex); +} + +static void apply_wqattrs_unlock(void) +{ + mutex_unlock(&wq_pool_mutex); + cpus_read_unlock(); +} + static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -6155,19 +6162,74 @@ static struct bus_type wq_subsys = { .dev_groups = wq_sysfs_groups, }; -static ssize_t wq_unbound_cpumask_show(struct device *dev, - struct device_attribute *attr, char *buf) +/** + * workqueue_set_unbound_cpumask - Set the low-level unbound cpumask + * @cpumask: the cpumask to set + * + * The low-level workqueues cpumask is a global cpumask that limits + * the affinity of all unbound workqueues. This function check the @cpumask + * and apply it to all unbound workqueues and updates all pwqs of them. + * + * Return: 0 - Success + * -EINVAL - Invalid @cpumask + * -ENOMEM - Failed to allocate memory for attrs or pwqs. + */ +static int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) +{ + int ret = -EINVAL; + + /* + * Not excluding isolated cpus on purpose. + * If the user wishes to include them, we allow that. + */ + cpumask_and(cpumask, cpumask, cpu_possible_mask); + if (!cpumask_empty(cpumask)) { + apply_wqattrs_lock(); + cpumask_copy(wq_requested_unbound_cpumask, cpumask); + if (cpumask_equal(cpumask, wq_unbound_cpumask)) { + ret = 0; + goto out_unlock; + } + + ret = workqueue_apply_unbound_cpumask(cpumask); + +out_unlock: + apply_wqattrs_unlock(); + } + + return ret; +} + +static ssize_t __wq_cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf, cpumask_var_t mask) { int written; mutex_lock(&wq_pool_mutex); - written = scnprintf(buf, PAGE_SIZE, "%*pb\n", - cpumask_pr_args(wq_unbound_cpumask)); + written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask)); mutex_unlock(&wq_pool_mutex); return written; } +static ssize_t wq_unbound_cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return __wq_cpumask_show(dev, attr, buf, wq_unbound_cpumask); +} + +static ssize_t wq_requested_cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return __wq_cpumask_show(dev, attr, buf, wq_requested_unbound_cpumask); +} + +static ssize_t wq_isolated_cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return __wq_cpumask_show(dev, attr, buf, wq_isolated_cpumask); +} + static ssize_t wq_unbound_cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { @@ -6185,9 +6247,13 @@ static ssize_t wq_unbound_cpumask_store(struct device *dev, return ret ? ret : count; } -static struct device_attribute wq_sysfs_cpumask_attr = +static struct device_attribute wq_sysfs_cpumask_attrs[] = { __ATTR(cpumask, 0644, wq_unbound_cpumask_show, - wq_unbound_cpumask_store); + wq_unbound_cpumask_store), + __ATTR(cpumask_requested, 0444, wq_requested_cpumask_show, NULL), + __ATTR(cpumask_isolated, 0444, wq_isolated_cpumask_show, NULL), + __ATTR_NULL, +}; static int __init wq_sysfs_init(void) { @@ -6200,7 +6266,13 @@ static int __init wq_sysfs_init(void) dev_root = bus_get_dev_root(&wq_subsys); if (dev_root) { - err = device_create_file(dev_root, &wq_sysfs_cpumask_attr); + struct device_attribute *attr; + + for (attr = wq_sysfs_cpumask_attrs; attr->attr.name; attr++) { + err = device_create_file(dev_root, attr); + if (err) + break; + } put_device(dev_root); } return err; @@ -6542,12 +6614,17 @@ void __init workqueue_init_early(void) BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&wq_requested_unbound_cpumask, GFP_KERNEL)); + BUG_ON(!zalloc_cpumask_var(&wq_isolated_cpumask, GFP_KERNEL)); + cpumask_copy(wq_unbound_cpumask, cpu_possible_mask); restrict_unbound_cpumask("HK_TYPE_WQ", housekeeping_cpumask(HK_TYPE_WQ)); restrict_unbound_cpumask("HK_TYPE_DOMAIN", housekeeping_cpumask(HK_TYPE_DOMAIN)); if (!cpumask_empty(&wq_cmdline_cpumask)) restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask); + cpumask_copy(wq_requested_unbound_cpumask, wq_unbound_cpumask); + pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); wq_update_pod_attrs_buf = alloc_workqueue_attrs(); diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index a6e9848189d62d..b5eb1be2248c24 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -147,71 +147,6 @@ test_add_proc() } # -# Testing the new "isolated" partition root type -# -test_isolated() -{ - cd $CGROUP2/test - echo 2-3 > cpuset.cpus - TYPE=$(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 @@ -297,14 +232,14 @@ TEST_MATRIX=( " 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 \ 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 \ - A1:P0,A2:P1,A3:P2,B1:P1 2-4" + A1:P0,A2:P1,A3:P2,B1:P1 2-4,2-3" " 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 \ - A1:P0,A2:P1,A3:P2,B1:P1 2-4" + 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 \ - A1:P0,A2:P2,A3:P1 2-4" + A1:P0,A2:P2,A3:P1 2-4,2-3" " C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \ . . X5 . . 0 A1:0-4,A2:1-4,A3:2-4 \ - A1:P0,A2:P-2,A3:P-1 ." + A1:P0,A2:P-2,A3:P-1" " C0-4:X2-4:S+ C1-4:X2-4:S+: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" @@ -313,7 +248,7 @@ TEST_MATRIX=( " 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: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," # 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" @@ -347,10 +282,10 @@ TEST_MATRIX=( # cpus_allowed/exclusive_cpus update tests " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ . C4 . P2 . 0 A1:4,A2:4,XA2:,XA3:,A3:4 \ - A1:P0,A3:P-2 ." + A1:P0,A3:P-2" " C0-3:X2-3:S+ C1-3:X2-3:S+ 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 ." + A1:P0,A3:P-2" " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ . . C3 P2 . 0 A1:0-2,A2:0-2,XA2:3,XA3:3,A3:3 \ A1:P0,A3:P2 3" @@ -359,13 +294,13 @@ TEST_MATRIX=( A1:P0,A3:P2 3" " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \ . . X3 . . 0 A1:0-3,A2:1-3,XA2:3,XA3:3,A3:2-3 \ - A1:P0,A3:P-2 ." + A1:P0,A3:P-2" " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \ . . C3 . . 0 A1:0-3,A2:3,XA2:3,XA3:3,A3:3 \ - A1:P0,A3:P-2 ." + A1:P0,A3:P-2" " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \ . C4 . . . 0 A1:4,A2:4,A3:4,XA1:,XA2:,XA3 \ - A1:P0,A3:P-2 ." + A1:P0,A3:P-2" # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- @@ -441,7 +376,7 @@ write_cpu_online() } fi echo $VAL > $CPUFILE - pause 0.01 + pause 0.05 } # @@ -573,12 +508,14 @@ dump_states() XECPUS=$DIR/cpuset.cpus.exclusive.effective PRS=$DIR/cpuset.cpus.partition PCPUS=$DIR/.__DEBUG__.cpuset.cpus.subpartitions + ISCPUS=$DIR/cpuset.cpus.isolated [[ -e $CPUS ]] && echo "$CPUS: $(cat $CPUS)" [[ -e $XCPUS ]] && echo "$XCPUS: $(cat $XCPUS)" [[ -e $ECPUS ]] && echo "$ECPUS: $(cat $ECPUS)" [[ -e $XECPUS ]] && echo "$XECPUS: $(cat $XECPUS)" [[ -e $PRS ]] && echo "$PRS: $(cat $PRS)" [[ -e $PCPUS ]] && echo "$PCPUS: $(cat $PCPUS)" + [[ -e $ISCPUS ]] && echo "$ISCPUS: $(cat $ISCPUS)" done } @@ -656,11 +593,17 @@ check_cgroup_states() # # Get isolated (including offline) CPUs by looking at -# /sys/kernel/debug/sched/domains and compare that with the expected value. +# /sys/kernel/debug/sched/domains and cpuset.cpus.isolated control file, +# if available, and compare that with the expected value. # -# Note that a sched domain of just 1 CPU will be considered isolated. +# Note that isolated CPUs from the sched/domains context include offline +# CPUs as well as CPUs in non-isolated 1-CPU partition. Those CPUs may +# not be included in the cpuset.cpus.isolated control file which contains +# only CPUs in isolated partitions. # -# $1 - expected isolated cpu list +# $1 - expected isolated cpu list(s) <isolcpus1>{,<isolcpus2>} +# <isolcpus1> - expected sched/domains value +# <isolcpus2> - cpuset.cpus.isolated value = <isolcpus1> if not defined # check_isolcpus() { @@ -668,8 +611,38 @@ check_isolcpus() ISOLCPUS= LASTISOLCPU= SCHED_DOMAINS=/sys/kernel/debug/sched/domains + ISCPUS=${CGROUP2}/cpuset.cpus.isolated + if [[ $EXPECT_VAL = . ]] + then + EXPECT_VAL= + EXPECT_VAL2= + elif [[ $(expr $EXPECT_VAL : ".*,.*") > 0 ]] + then + set -- $(echo $EXPECT_VAL | sed -e "s/,/ /g") + EXPECT_VAL=$1 + EXPECT_VAL2=$2 + else + EXPECT_VAL2=$EXPECT_VAL + fi + + # + # Check the debug isolated cpumask, if present + # + [[ -f $ISCPUS ]] && { + ISOLCPUS=$(cat $ISCPUS) + [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && { + # Take a 50ms pause and try again + pause 0.05 + ISOLCPUS=$(cat $ISCPUS) + } + [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && return 1 + ISOLCPUS= + } + + # + # Use the sched domain in debugfs to check isolated CPUs, if available + # [[ -d $SCHED_DOMAINS ]] || return 0 - [[ $EXPECT_VAL = . ]] && EXPECT_VAL= for ((CPU=0; CPU < $NR_CPUS; CPU++)) do @@ -714,6 +687,26 @@ test_fail() } # +# Check to see if there are unexpected isolated CPUs left +# +null_isolcpus_check() +{ + [[ $VERBOSE -gt 0 ]] || return 0 + # Retry a few times before printing error + RETRY=0 + while [[ $RETRY -lt 5 ]] + do + pause 0.01 + check_isolcpus "." + [[ $? -eq 0 ]] && return 0 + ((RETRY++)) + done + echo "Unexpected isolated CPUs: $ISOLCPUS" + dump_states + exit 1 +} + +# # Run cpuset state transition test # $1 - test matrix name # @@ -787,7 +780,7 @@ run_state_test() # NEWLIST=$(cat cpuset.cpus.effective) RETRY=0 - while [[ $NEWLIST != $CPULIST && $RETRY -lt 5 ]] + while [[ $NEWLIST != $CPULIST && $RETRY -lt 8 ]] do # Wait a bit longer & recheck a few times pause 0.01 @@ -798,6 +791,7 @@ run_state_test() echo "Effective cpus changed to $NEWLIST after test $I!" exit 1 } + null_isolcpus_check [[ $VERBOSE -gt 0 ]] && echo "Test $I done." ((I++)) done @@ -805,6 +799,72 @@ run_state_test() } # +# Testing the new "isolated" partition root type +# +test_isolated() +{ + cd $CGROUP2/test + 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 + null_isolcpus_check +} + +# # Wait for inotify event for the given file and read it # $1: cgroup file to wait for # $2: file to store the read result diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c index ff519029f6f433..8845353aca53bb 100644 --- a/tools/testing/selftests/cgroup/test_freezer.c +++ b/tools/testing/selftests/cgroup/test_freezer.c @@ -740,7 +740,7 @@ static int test_cgfreezer_ptraced(const char *root) /* * cg_check_frozen(cgroup, true) will fail here, - * because the task in in the TRACEd state. + * because the task is in the TRACEd state. */ if (cg_freeze_wait(cgroup, false)) goto cleanup; |