diff options
| -rw-r--r-- | Documentation/admin-guide/cgroup-v1/pids.rst | 3 | ||||
| -rw-r--r-- | Documentation/admin-guide/cgroup-v2.rst | 47 | ||||
| -rw-r--r-- | MAINTAINERS | 1 | ||||
| -rw-r--r-- | include/linux/cgroup-defs.h | 7 | ||||
| -rw-r--r-- | include/linux/misc_cgroup.h | 12 | ||||
| -rw-r--r-- | kernel/cgroup/cgroup.c | 36 | ||||
| -rw-r--r-- | kernel/cgroup/cpuset.c | 197 | ||||
| -rw-r--r-- | kernel/cgroup/misc.c | 80 | ||||
| -rw-r--r-- | kernel/cgroup/pids.c | 129 | ||||
| -rw-r--r-- | kernel/cgroup/rstat.c | 37 | ||||
| -rw-r--r-- | tools/testing/selftests/cgroup/.gitignore | 11 | ||||
| -rw-r--r-- | tools/testing/selftests/cgroup/Makefile | 25 | ||||
| -rwxr-xr-x | tools/testing/selftests/cgroup/test_cpuset_prs.sh | 75 | ||||
| -rw-r--r-- | tools/testing/selftests/cgroup/test_pids.c | 178 |
14 files changed, 679 insertions, 159 deletions
diff --git a/Documentation/admin-guide/cgroup-v1/pids.rst b/Documentation/admin-guide/cgroup-v1/pids.rst index 6acebd9e72c8..0f9f9a7b1f6c 100644 --- a/Documentation/admin-guide/cgroup-v1/pids.rst +++ b/Documentation/admin-guide/cgroup-v1/pids.rst @@ -36,7 +36,8 @@ superset of parent/child/pids.current. The pids.events file contains event counters: - - max: Number of times fork failed because limit was hit. + - max: Number of times fork failed in the cgroup because limit was hit in + self or ancestors. Example ------- diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 8fbb0519d556..05862f06ed26 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -239,6 +239,13 @@ cgroup v2 currently supports the following mount options. will not be tracked by the memory controller (even if cgroup v2 is remounted later on). + pids_localevents + The option restores v1-like behavior of pids.events:max, that is only + local (inside cgroup proper) fork failures are counted. Without this + option pids.events.max represents any pids.max enforcemnt across + cgroup's subtree. + + Organizing Processes and Threads -------------------------------- @@ -2205,12 +2212,18 @@ PID Interface Files descendants has ever reached. pids.events - A read-only flat-keyed file which exists on non-root cgroups. The - following entries are defined. Unless specified otherwise, a value - change in this file generates a file modified event. + A read-only flat-keyed file which exists on non-root cgroups. Unless + specified otherwise, a value change in this file generates a file + modified event. The following entries are defined. max - Number of times fork failed because limit was hit. + The number of times the cgroup's total number of processes hit the pids.max + limit (see also pids_localevents). + + pids.events.local + Similar to pids.events but the fields in the file are local + to the cgroup i.e. not hierarchical. The file modified event + generated on this file reflects only the local events. Organisational operations are not blocked by cgroup policies, so it is possible to have pids.current > pids.max. This can be done by either @@ -2346,8 +2359,12 @@ Cpuset Interface Files is always a subset of it. Users can manually set it to a value that is different from - "cpuset.cpus". The only constraint in setting it is that the - list of CPUs must be exclusive with respect to its sibling. + "cpuset.cpus". One constraint in setting it is that the list of + CPUs must be exclusive with respect to "cpuset.cpus.exclusive" + of its sibling. If "cpuset.cpus.exclusive" of a sibling cgroup + isn't set, its "cpuset.cpus" value, if set, cannot be a subset + of it to leave at least one CPU available when the exclusive + CPUs are taken away. For a parent cgroup, any one of its exclusive CPUs can only be distributed to at most one of its child cgroups. Having an @@ -2363,8 +2380,8 @@ Cpuset Interface Files cpuset-enabled cgroups. This file shows the effective set of exclusive CPUs that - can be used to create a partition root. The content of this - file will always be a subset of "cpuset.cpus" and its parent's + can be used to create a partition root. The content + of this file will always be a subset of its parent's "cpuset.cpus.exclusive.effective" if its parent is not the root cgroup. It will also be a subset of "cpuset.cpus.exclusive" if it is set. If "cpuset.cpus.exclusive" is not set, it is @@ -2625,6 +2642,15 @@ Miscellaneous controller provides 3 interface files. If two misc resources (res_ res_a 3 res_b 0 + misc.peak + A read-only flat-keyed file shown in all cgroups. It shows the + historical maximum usage of the resources in the cgroup and its + children.:: + + $ cat misc.peak + res_a 10 + res_b 8 + misc.max A read-write flat-keyed file shown in the non root cgroups. Allowed maximum usage of the resources in the cgroup and its children.:: @@ -2654,6 +2680,11 @@ Miscellaneous controller provides 3 interface files. If two misc resources (res_ The number of times the cgroup's resource usage was about to go over the max boundary. + misc.events.local + Similar to misc.events but the fields in the file are local to the + cgroup i.e. not hierarchical. The file modified event generated on + this file reflects only the local events. + Migration and Ownership ~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/MAINTAINERS b/MAINTAINERS index b1ce34379868..9cae268966e7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5528,6 +5528,7 @@ CONTROL GROUP (CGROUP) M: Tejun Heo <[email protected]> M: Zefan Li <[email protected]> M: Johannes Weiner <[email protected]> +M: Michal Koutný <[email protected]> S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index ea48c861cd36..b36690ca0d3f 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -119,7 +119,12 @@ enum { /* * Enable hugetlb accounting for the memory controller. */ - CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING = (1 << 19), + CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING = (1 << 19), + + /* + * Enable legacy local pids.events. + */ + CGRP_ROOT_PIDS_LOCAL_EVENTS = (1 << 20), }; /* cftype->flags */ diff --git a/include/linux/misc_cgroup.h b/include/linux/misc_cgroup.h index e799b1f8d05b..49eef10c8e59 100644 --- a/include/linux/misc_cgroup.h +++ b/include/linux/misc_cgroup.h @@ -9,15 +9,16 @@ #define _MISC_CGROUP_H_ /** - * Types of misc cgroup entries supported by the host. + * enum misc_res_type - Types of misc cgroup entries supported by the host. */ enum misc_res_type { #ifdef CONFIG_KVM_AMD_SEV - /* AMD SEV ASIDs resource */ + /** @MISC_CG_RES_SEV: AMD SEV ASIDs resource */ MISC_CG_RES_SEV, - /* AMD SEV-ES ASIDs resource */ + /** @MISC_CG_RES_SEV_ES: AMD SEV-ES ASIDs resource */ MISC_CG_RES_SEV_ES, #endif + /** @MISC_CG_RES_TYPES: count of enum misc_res_type constants */ MISC_CG_RES_TYPES }; @@ -30,13 +31,16 @@ struct misc_cg; /** * struct misc_res: Per cgroup per misc type resource * @max: Maximum limit on the resource. + * @watermark: Historical maximum usage of the resource. * @usage: Current usage of the resource. * @events: Number of times, the resource limit exceeded. */ struct misc_res { u64 max; + atomic64_t watermark; atomic64_t usage; atomic64_t events; + atomic64_t events_local; }; /** @@ -50,6 +54,8 @@ struct misc_cg { /* misc.events */ struct cgroup_file events_file; + /* misc.events.local */ + struct cgroup_file events_local_file; struct misc_res res[MISC_CG_RES_TYPES]; }; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index e32b6972c478..c8e4b62b436a 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1744,8 +1744,11 @@ static int css_populate_dir(struct cgroup_subsys_state *css) if (cgroup_psi_enabled()) { ret = cgroup_addrm_files(css, cgrp, cgroup_psi_files, true); - if (ret < 0) + if (ret < 0) { + cgroup_addrm_files(css, cgrp, + cgroup_base_files, false); return ret; + } } } else { ret = cgroup_addrm_files(css, cgrp, @@ -1839,9 +1842,9 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) RCU_INIT_POINTER(scgrp->subsys[ssid], NULL); rcu_assign_pointer(dcgrp->subsys[ssid], css); ss->root = dst_root; - css->cgroup = dcgrp; spin_lock_irq(&css_set_lock); + css->cgroup = dcgrp; WARN_ON(!list_empty(&dcgrp->e_csets[ss->id])); list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id], e_cset_node[ss->id]) { @@ -1922,6 +1925,7 @@ enum cgroup2_param { Opt_memory_localevents, Opt_memory_recursiveprot, Opt_memory_hugetlb_accounting, + Opt_pids_localevents, nr__cgroup2_params }; @@ -1931,6 +1935,7 @@ static const struct fs_parameter_spec cgroup2_fs_parameters[] = { fsparam_flag("memory_localevents", Opt_memory_localevents), fsparam_flag("memory_recursiveprot", Opt_memory_recursiveprot), fsparam_flag("memory_hugetlb_accounting", Opt_memory_hugetlb_accounting), + fsparam_flag("pids_localevents", Opt_pids_localevents), {} }; @@ -1960,6 +1965,9 @@ static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param case Opt_memory_hugetlb_accounting: ctx->flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING; return 0; + case Opt_pids_localevents: + ctx->flags |= CGRP_ROOT_PIDS_LOCAL_EVENTS; + return 0; } return -EINVAL; } @@ -1989,6 +1997,11 @@ static void apply_cgroup_root_flags(unsigned int root_flags) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING; + + if (root_flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) + cgrp_dfl_root.flags |= CGRP_ROOT_PIDS_LOCAL_EVENTS; + else + cgrp_dfl_root.flags &= ~CGRP_ROOT_PIDS_LOCAL_EVENTS; } } @@ -2004,6 +2017,8 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root seq_puts(seq, ",memory_recursiveprot"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING) seq_puts(seq, ",memory_hugetlb_accounting"); + if (cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) + seq_puts(seq, ",pids_localevents"); return 0; } @@ -6686,8 +6701,10 @@ void cgroup_exit(struct task_struct *tsk) WARN_ON_ONCE(list_empty(&tsk->cg_list)); cset = task_css_set(tsk); css_set_move_task(tsk, cset, NULL, false); - list_add_tail(&tsk->cg_list, &cset->dying_tasks); cset->nr_tasks--; + /* matches the signal->live check in css_task_iter_advance() */ + if (thread_group_leader(tsk) && atomic_read(&tsk->signal->live)) + list_add_tail(&tsk->cg_list, &cset->dying_tasks); if (dl_task(tsk)) dec_dl_tasks_cs(tsk); @@ -6714,10 +6731,12 @@ void cgroup_release(struct task_struct *task) ss->release(task); } while_each_subsys_mask(); - spin_lock_irq(&css_set_lock); - css_set_skip_task_iters(task_css_set(task), task); - list_del_init(&task->cg_list); - spin_unlock_irq(&css_set_lock); + if (!list_empty(&task->cg_list)) { + spin_lock_irq(&css_set_lock); + css_set_skip_task_iters(task_css_set(task), task); + list_del_init(&task->cg_list); + spin_unlock_irq(&css_set_lock); + } } void cgroup_free(struct task_struct *task) @@ -7062,7 +7081,8 @@ static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr, "favordynmods\n" "memory_localevents\n" "memory_recursiveprot\n" - "memory_hugetlb_accounting\n"); + "memory_hugetlb_accounting\n" + "pids_localevents\n"); } static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index c12b9fdb22a4..40ec4abaf440 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -21,6 +21,7 @@ * License. See the file COPYING in the main directory of the Linux * distribution for more details. */ +#include "cgroup-internal.h" #include <linux/cpu.h> #include <linux/cpumask.h> @@ -87,7 +88,7 @@ static const char * const perr_strings[] = { [PERR_NOTEXCL] = "Cpu list in cpuset.cpus not exclusive", [PERR_NOCPUS] = "Parent unable to distribute cpu downstream", [PERR_HOTPLUG] = "No cpu available due to hotplug", - [PERR_CPUSEMPTY] = "cpuset.cpus is empty", + [PERR_CPUSEMPTY] = "cpuset.cpus and cpuset.cpus.exclusive are empty", [PERR_HKEEPING] = "partition config conflicts with housekeeping setup", }; @@ -127,19 +128,28 @@ struct cpuset { /* * Exclusive CPUs dedicated to current cgroup (default hierarchy only) * - * This exclusive CPUs must be a subset of cpus_allowed. A parent - * cgroup can only grant exclusive CPUs to one of its children. + * The effective_cpus of a valid partition root comes solely from its + * effective_xcpus and some of the effective_xcpus may be distributed + * to sub-partitions below & hence excluded from its effective_cpus. + * For a valid partition root, its effective_cpus have no relationship + * with cpus_allowed unless its exclusive_cpus isn't set. * - * When the cgroup becomes a valid partition root, effective_xcpus - * defaults to cpus_allowed if not set. The effective_cpus of a valid - * partition root comes solely from its effective_xcpus and some of the - * effective_xcpus may be distributed to sub-partitions below & hence - * excluded from its effective_cpus. + * This value will only be set if either exclusive_cpus is set or + * when this cpuset becomes a local partition root. */ cpumask_var_t effective_xcpus; /* * Exclusive CPUs as requested by the user (default hierarchy only) + * + * Its value is independent of cpus_allowed and designates the set of + * CPUs that can be granted to the current cpuset or its children when + * it becomes a valid partition root. The effective set of exclusive + * CPUs granted (effective_xcpus) depends on whether those exclusive + * CPUs are passed down by its ancestors and not yet taken up by + * another sibling partition root along the way. + * + * If its value isn't set, it defaults to cpus_allowed. */ cpumask_var_t exclusive_cpus; @@ -169,7 +179,7 @@ struct cpuset { /* for custom sched domain */ int relax_domain_level; - /* number of valid sub-partitions */ + /* number of valid local child partitions */ int nr_subparts; /* partition root state */ @@ -230,6 +240,17 @@ static struct list_head remote_children; * 2 - partition root without load balancing (isolated) * -1 - invalid partition root * -2 - invalid isolated partition root + * + * There are 2 types of partitions - local or remote. Local partitions are + * those whose parents are partition root themselves. Setting of + * cpuset.cpus.exclusive are optional in setting up local partitions. + * Remote partitions are those whose parents are not partition roots. Passing + * down exclusive CPUs by setting cpuset.cpus.exclusive along its ancestor + * nodes are mandatory in creating a remote partition. + * + * For simplicity, a local partition can be created under a local or remote + * partition but a remote partition cannot have any partition root in its + * ancestor chain except the cgroup root. */ #define PRS_MEMBER 0 #define PRS_ROOT 1 @@ -434,7 +455,7 @@ static struct cpuset top_cpuset = { * by other task, we use alloc_lock in the task_struct fields to protect * them. * - * The cpuset_common_file_read() handlers only hold callback_lock across + * 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. * @@ -709,6 +730,19 @@ static inline void free_cpuset(struct cpuset *cs) kfree(cs); } +/* Return user specified exclusive CPUs */ +static inline struct cpumask *user_xcpus(struct cpuset *cs) +{ + return cpumask_empty(cs->exclusive_cpus) ? cs->cpus_allowed + : cs->exclusive_cpus; +} + +static inline bool xcpus_empty(struct cpuset *cs) +{ + return cpumask_empty(cs->cpus_allowed) && + cpumask_empty(cs->exclusive_cpus); +} + static inline struct cpumask *fetch_xcpus(struct cpuset *cs) { return !cpumask_empty(cs->exclusive_cpus) ? cs->exclusive_cpus : @@ -825,17 +859,41 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial) /* * If either I or some sibling (!= me) is exclusive, we can't - * overlap + * overlap. exclusive_cpus cannot overlap with each other if set. */ ret = -EINVAL; cpuset_for_each_child(c, css, par) { - if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) && - c != cur) { + bool txset, cxset; /* Are exclusive_cpus set? */ + + if (c == cur) + continue; + + txset = !cpumask_empty(trial->exclusive_cpus); + cxset = !cpumask_empty(c->exclusive_cpus); + if (is_cpu_exclusive(trial) || is_cpu_exclusive(c) || + (txset && cxset)) { if (!cpusets_are_exclusive(trial, c)) goto out; + } else if (txset || cxset) { + struct cpumask *xcpus, *acpus; + + /* + * When just one of the exclusive_cpus's is set, + * cpus_allowed of the other cpuset, if set, cannot be + * a subset of it or none of those CPUs will be + * available if these exclusive CPUs are activated. + */ + if (txset) { + xcpus = trial->exclusive_cpus; + acpus = c->cpus_allowed; + } else { + xcpus = c->exclusive_cpus; + acpus = trial->cpus_allowed; + } + if (!cpumask_empty(acpus) && cpumask_subset(acpus, xcpus)) + goto out; } if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) && - c != cur && nodes_intersects(trial->mems_allowed, c->mems_allowed)) goto out; } @@ -957,13 +1015,15 @@ static int generate_sched_domains(cpumask_var_t **domains, int nslot; /* next empty doms[] struct cpumask slot */ struct cgroup_subsys_state *pos_css; bool root_load_balance = is_sched_load_balance(&top_cpuset); + bool cgrpv2 = cgroup_subsys_on_dfl(cpuset_cgrp_subsys); doms = NULL; dattr = NULL; csa = NULL; /* Special case for the 99% of systems with one, full, sched domain */ - if (root_load_balance && !top_cpuset.nr_subparts) { + if (root_load_balance && cpumask_empty(subpartitions_cpus)) { +single_root_domain: ndoms = 1; doms = alloc_sched_domains(ndoms); if (!doms) @@ -991,16 +1051,18 @@ static int generate_sched_domains(cpumask_var_t **domains, cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) { if (cp == &top_cpuset) continue; + + if (cgrpv2) + goto v2; + /* + * v1: * Continue traversing beyond @cp iff @cp has some CPUs and * isn't load balancing. The former is obvious. The * latter: All child cpusets contain a subset of the * parent's cpus, so just skip them, and then we call * update_domain_attr_tree() to calc relax_domain_level of * the corresponding sched domain. - * - * If root is load-balancing, we can skip @cp if it - * is a subset of the root's effective_cpus. */ if (!cpumask_empty(cp->cpus_allowed) && !(is_sched_load_balance(cp) && @@ -1008,20 +1070,39 @@ static int generate_sched_domains(cpumask_var_t **domains, housekeeping_cpumask(HK_TYPE_DOMAIN)))) continue; - if (root_load_balance && - cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus)) - continue; - if (is_sched_load_balance(cp) && !cpumask_empty(cp->effective_cpus)) csa[csn++] = cp; - /* skip @cp's subtree if not a partition root */ - if (!is_partition_valid(cp)) + /* skip @cp's subtree */ + pos_css = css_rightmost_descendant(pos_css); + continue; + +v2: + /* + * Only valid partition roots that are not isolated and with + * non-empty effective_cpus will be saved into csn[]. + */ + if ((cp->partition_root_state == PRS_ROOT) && + !cpumask_empty(cp->effective_cpus)) + csa[csn++] = cp; + + /* + * Skip @cp's subtree if not a partition root and has no + * exclusive CPUs to be granted to child cpusets. + */ + if (!is_partition_valid(cp) && cpumask_empty(cp->exclusive_cpus)) pos_css = css_rightmost_descendant(pos_css); } rcu_read_unlock(); + /* + * If there are only isolated partitions underneath the cgroup root, + * we can optimize out unneeded sched domains scanning. + */ + if (root_load_balance && (csn == 1)) + goto single_root_domain; + for (i = 0; i < csn; i++) csa[i]->pn = i; ndoms = csn; @@ -1064,6 +1145,20 @@ restart: dattr = kmalloc_array(ndoms, sizeof(struct sched_domain_attr), GFP_KERNEL); + /* + * Cgroup v2 doesn't support domain attributes, just set all of them + * to SD_ATTR_INIT. Also non-isolating partition root CPUs are a + * subset of HK_TYPE_DOMAIN housekeeping CPUs. + */ + if (cgrpv2) { + for (i = 0; i < ndoms; i++) { + cpumask_copy(doms[i], csa[i]->effective_cpus); + if (dattr) + dattr[i] = SD_ATTR_INIT; + } + goto done; + } + for (nslot = 0, i = 0; i < csn; i++) { struct cpuset *a = csa[i]; struct cpumask *dp; @@ -1223,7 +1318,7 @@ static void rebuild_sched_domains_locked(void) * root should be only a subset of the active CPUs. Since a CPU in any * partition root could be offlined, all must be checked. */ - if (top_cpuset.nr_subparts) { + if (!cpumask_empty(subpartitions_cpus)) { rcu_read_lock(); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (!is_partition_valid(cs)) { @@ -1338,7 +1433,7 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, */ static int update_partition_exclusive(struct cpuset *cs, int new_prs) { - bool exclusive = (new_prs > 0); + bool exclusive = (new_prs > PRS_MEMBER); if (exclusive && !is_cpu_exclusive(cs)) { if (update_flag(CS_CPU_EXCLUSIVE, cs, 1)) @@ -1532,7 +1627,7 @@ EXPORT_SYMBOL_GPL(cpuset_cpu_is_isolated); * Return: true if xcpus is not empty, false otherwise. * * Starting with exclusive_cpus (cpus_allowed if exclusive_cpus is not set), - * it must be a subset of cpus_allowed and parent's effective_xcpus. + * it must be a subset of parent's effective_xcpus. */ static bool compute_effective_exclusive_cpumask(struct cpuset *cs, struct cpumask *xcpus) @@ -1542,12 +1637,7 @@ static bool compute_effective_exclusive_cpumask(struct cpuset *cs, if (!xcpus) xcpus = cs->effective_xcpus; - if (!cpumask_empty(cs->exclusive_cpus)) - cpumask_and(xcpus, cs->exclusive_cpus, cs->cpus_allowed); - else - cpumask_copy(xcpus, cs->cpus_allowed); - - return cpumask_and(xcpus, xcpus, parent->effective_xcpus); + return cpumask_and(xcpus, user_xcpus(cs), parent->effective_xcpus); } static inline bool is_remote_partition(struct cpuset *cs) @@ -1826,8 +1916,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, */ adding = deleting = false; old_prs = new_prs = cs->partition_root_state; - xcpus = !cpumask_empty(cs->exclusive_cpus) - ? cs->effective_xcpus : cs->cpus_allowed; + xcpus = user_xcpus(cs); if (cmd == partcmd_invalidate) { if (is_prs_invalid(old_prs)) @@ -1855,7 +1944,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, return is_partition_invalid(parent) ? PERR_INVPARENT : PERR_NOTPART; } - if (!newmask && cpumask_empty(cs->cpus_allowed)) + if (!newmask && xcpus_empty(cs)) return PERR_CPUSEMPTY; nocpu = tasks_nocpu_error(parent, cs, xcpus); @@ -2583,8 +2672,6 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs, retval = cpulist_parse(buf, trialcs->exclusive_cpus); if (retval < 0) return retval; - if (!is_cpu_exclusive(cs)) - set_bit(CS_CPU_EXCLUSIVE, &trialcs->flags); } /* Nothing to do if the CPUs didn't change */ @@ -3071,9 +3158,9 @@ static int update_prstate(struct cpuset *cs, int new_prs) ? partcmd_enable : partcmd_enablei; /* - * cpus_allowed cannot be empty. + * cpus_allowed and exclusive_cpus cannot be both empty. */ - if (cpumask_empty(cs->cpus_allowed)) { + if (xcpus_empty(cs)) { err = PERR_CPUSEMPTY; goto out; } @@ -4009,8 +4096,6 @@ cpuset_css_alloc(struct cgroup_subsys_state *parent_css) } __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; INIT_LIST_HEAD(&cs->remote_sibling); @@ -4040,6 +4125,12 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) set_bit(CS_SPREAD_PAGE, &cs->flags); if (is_spread_slab(parent)) set_bit(CS_SPREAD_SLAB, &cs->flags); + /* + * For v2, clear CS_SCHED_LOAD_BALANCE if parent is isolated + */ + if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && + !is_sched_load_balance(parent)) + clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); cpuset_inc(); @@ -4050,14 +4141,6 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) cs->use_parent_ecpus = true; parent->child_ecpus_count++; } - - /* - * For v2, clear CS_SCHED_LOAD_BALANCE if parent is isolated - */ - if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && - !is_sched_load_balance(parent)) - clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); - spin_unlock_irq(&callback_lock); if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) @@ -4571,7 +4654,7 @@ static void cpuset_handle_hotplug(void) * In the rare case that hotplug removes all the cpus in * subpartitions_cpus, we assumed that cpus are updated. */ - if (!cpus_updated && top_cpuset.nr_subparts) + if (!cpus_updated && !cpumask_empty(subpartitions_cpus)) cpus_updated = true; /* For v1, synchronize cpus_allowed to cpu_active_mask */ @@ -5051,10 +5134,14 @@ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, if (!buf) goto out; - css = task_get_css(tsk, cpuset_cgrp_id); - retval = cgroup_path_ns(css->cgroup, buf, PATH_MAX, - current->nsproxy->cgroup_ns); - css_put(css); + rcu_read_lock(); + spin_lock_irq(&css_set_lock); + css = task_css(tsk, cpuset_cgrp_id); + retval = cgroup_path_ns_locked(css->cgroup, buf, PATH_MAX, + current->nsproxy->cgroup_ns); + spin_unlock_irq(&css_set_lock); + rcu_read_unlock(); + if (retval == -E2BIG) retval = -ENAMETOOLONG; if (retval < 0) diff --git a/kernel/cgroup/misc.c b/kernel/cgroup/misc.c index 79a3717a5803..0e26068995a6 100644 --- a/kernel/cgroup/misc.c +++ b/kernel/cgroup/misc.c @@ -121,6 +121,30 @@ static void misc_cg_cancel_charge(enum misc_res_type type, struct misc_cg *cg, misc_res_name[type]); } +static void misc_cg_update_watermark(struct misc_res *res, u64 new_usage) +{ + u64 old; + + while (true) { + old = atomic64_read(&res->watermark); + if (new_usage <= old) + break; + if (atomic64_cmpxchg(&res->watermark, old, new_usage) == old) + break; + } +} + +static void misc_cg_event(enum misc_res_type type, struct misc_cg *cg) +{ + atomic64_inc(&cg->res[type].events_local); + cgroup_file_notify(&cg->events_local_file); + + for (; parent_misc(cg); cg = parent_misc(cg)) { + atomic64_inc(&cg->res[type].events); + cgroup_file_notify(&cg->events_file); + } +} + /** * misc_cg_try_charge() - Try charging the misc cgroup. * @type: Misc res type to charge. @@ -159,14 +183,12 @@ int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg, u64 amount) ret = -EBUSY; goto err_charge; } + misc_cg_update_watermark(res, new_usage); } return 0; err_charge: - for (j = i; j; j = parent_misc(j)) { - atomic64_inc(&j->res[type].events); - cgroup_file_notify(&j->events_file); - } + misc_cg_event(type, i); for (j = cg; j != i; j = parent_misc(j)) misc_cg_cancel_charge(type, j, amount); @@ -308,6 +330,29 @@ static int misc_cg_current_show(struct seq_file *sf, void *v) } /** + * misc_cg_peak_show() - Show the peak usage of the misc cgroup. + * @sf: Interface file + * @v: Arguments passed + * + * Context: Any context. + * Return: 0 to denote successful print. + */ +static int misc_cg_peak_show(struct seq_file *sf, void *v) +{ + int i; + u64 watermark; + struct misc_cg *cg = css_misc(seq_css(sf)); + + for (i = 0; i < MISC_CG_RES_TYPES; i++) { + watermark = atomic64_read(&cg->res[i].watermark); + if (READ_ONCE(misc_res_capacity[i]) || watermark) + seq_printf(sf, "%s %llu\n", misc_res_name[i], watermark); + } + + return 0; +} + +/** * misc_cg_capacity_show() - Show the total capacity of misc res on the host. * @sf: Interface file * @v: Arguments passed @@ -331,20 +376,33 @@ static int misc_cg_capacity_show(struct seq_file *sf, void *v) return 0; } -static int misc_events_show(struct seq_file *sf, void *v) +static int __misc_events_show(struct seq_file *sf, bool local) { struct misc_cg *cg = css_misc(seq_css(sf)); u64 events; int i; for (i = 0; i < MISC_CG_RES_TYPES; i++) { - events = atomic64_read(&cg->res[i].events); + if (local) + events = atomic64_read(&cg->res[i].events_local); + else + events = atomic64_read(&cg->res[i].events); if (READ_ONCE(misc_res_capacity[i]) || events) seq_printf(sf, "%s.max %llu\n", misc_res_name[i], events); } return 0; } +static int misc_events_show(struct seq_file *sf, void *v) +{ + return __misc_events_show(sf, false); +} + +static int misc_events_local_show(struct seq_file *sf, void *v) +{ + return __misc_events_show(sf, true); +} + /* Misc cgroup interface files */ static struct cftype misc_cg_files[] = { { @@ -358,6 +416,10 @@ static struct cftype misc_cg_files[] = { .seq_show = misc_cg_current_show, }, { + .name = "peak", + .seq_show = misc_cg_peak_show, + }, + { .name = "capacity", .seq_show = misc_cg_capacity_show, .flags = CFTYPE_ONLY_ON_ROOT, @@ -368,6 +430,12 @@ static struct cftype misc_cg_files[] = { .file_offset = offsetof(struct misc_cg, events_file), .seq_show = misc_events_show, }, + { + .name = "events.local", + .flags = CFTYPE_NOT_ON_ROOT, + .file_offset = offsetof(struct misc_cg, events_local_file), + .seq_show = misc_events_local_show, + }, {} }; diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c index 0e5ec7d59b4d..f5cb0ec45b9d 100644 --- a/kernel/cgroup/pids.c +++ b/kernel/cgroup/pids.c @@ -38,6 +38,14 @@ #define PIDS_MAX (PID_MAX_LIMIT + 1ULL) #define PIDS_MAX_STR "max" +enum pidcg_event { + /* Fork failed in subtree because this pids_cgroup limit was hit. */ + PIDCG_MAX, + /* Fork failed in this pids_cgroup because ancestor limit was hit. */ + PIDCG_FORKFAIL, + NR_PIDCG_EVENTS, +}; + struct pids_cgroup { struct cgroup_subsys_state css; @@ -49,11 +57,12 @@ struct pids_cgroup { atomic64_t limit; int64_t watermark; - /* Handle for "pids.events" */ + /* Handles for pids.events[.local] */ struct cgroup_file events_file; + struct cgroup_file events_local_file; - /* Number of times fork failed because limit was hit. */ - atomic64_t events_limit; + atomic64_t events[NR_PIDCG_EVENTS]; + atomic64_t events_local[NR_PIDCG_EVENTS]; }; static struct pids_cgroup *css_pids(struct cgroup_subsys_state *css) @@ -148,12 +157,13 @@ static void pids_charge(struct pids_cgroup *pids, int num) * pids_try_charge - hierarchically try to charge the pid count * @pids: the pid cgroup state * @num: the number of pids to charge + * @fail: storage of pid cgroup causing the fail * * This function follows the set limit. It will fail if the charge would cause * the new value to exceed the hierarchical limit. Returns 0 if the charge * succeeded, otherwise -EAGAIN. */ -static int pids_try_charge(struct pids_cgroup *pids, int num) +static int pids_try_charge(struct pids_cgroup *pids, int num, struct pids_cgroup **fail) { struct pids_cgroup *p, *q; @@ -166,9 +176,10 @@ static int pids_try_charge(struct pids_cgroup *pids, int num) * p->limit is %PIDS_MAX then we know that this test will never * fail. */ - if (new > limit) + if (new > limit) { + *fail = p; goto revert; - + } /* * Not technically accurate if we go over limit somewhere up * the hierarchy, but that's tolerable for the watermark. @@ -229,6 +240,36 @@ static void pids_cancel_attach(struct cgroup_taskset *tset) } } +static void pids_event(struct pids_cgroup *pids_forking, + struct pids_cgroup *pids_over_limit) +{ + struct pids_cgroup *p = pids_forking; + bool limit = false; + + /* Only log the first time limit is hit. */ + if (atomic64_inc_return(&p->events_local[PIDCG_FORKFAIL]) == 1) { + pr_info("cgroup: fork rejected by pids controller in "); + pr_cont_cgroup_path(p->css.cgroup); + pr_cont("\n"); + } + cgroup_file_notify(&p->events_local_file); + if (!cgroup_subsys_on_dfl(pids_cgrp_subsys) || + cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) + return; + + for (; parent_pids(p); p = parent_pids(p)) { + if (p == pids_over_limit) { + limit = true; + atomic64_inc(&p->events_local[PIDCG_MAX]); + cgroup_file_notify(&p->events_local_file); + } + if (limit) + atomic64_inc(&p->events[PIDCG_MAX]); + + cgroup_file_notify(&p->events_file); + } +} + /* * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies * on cgroup_threadgroup_change_begin() held by the copy_process(). @@ -236,7 +277,7 @@ static void pids_cancel_attach(struct cgroup_taskset *tset) static int pids_can_fork(struct task_struct *task, struct css_set *cset) { struct cgroup_subsys_state *css; - struct pids_cgroup *pids; + struct pids_cgroup *pids, *pids_over_limit; int err; if (cset) @@ -244,16 +285,10 @@ static int pids_can_fork(struct task_struct *task, struct css_set *cset) else css = task_css_check(current, pids_cgrp_id, true); pids = css_pids(css); - err = pids_try_charge(pids, 1); - if (err) { - /* Only log the first time events_limit is incremented. */ - if (atomic64_inc_return(&pids->events_limit) == 1) { - pr_info("cgroup: fork rejected by pids controller in "); - pr_cont_cgroup_path(css->cgroup); - pr_cont("\n"); - } - cgroup_file_notify(&pids->events_file); - } + err = pids_try_charge(pids, 1, &pids_over_limit); + if (err) + pids_event(pids, pids_over_limit); + return err; } @@ -337,11 +372,32 @@ static s64 pids_peak_read(struct cgroup_subsys_state *css, return READ_ONCE(pids->watermark); } -static int pids_events_show(struct seq_file *sf, void *v) +static int __pids_events_show(struct seq_file *sf, bool local) { struct pids_cgroup *pids = css_pids(seq_css(sf)); + enum pidcg_event pe = PIDCG_MAX; + atomic64_t *events; + + if (!cgroup_subsys_on_dfl(pids_cgrp_subsys) || + cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) { + pe = PIDCG_FORKFAIL; + local = true; + } + events = local ? pids->events_local : pids->events; + + seq_printf(sf, "max %lld\n", (s64)atomic64_read(&events[pe])); + return 0; +} - seq_printf(sf, "max %lld\n", (s64)atomic64_read(&pids->events_limit)); +static int pids_events_show(struct seq_file *sf, void *v) +{ + __pids_events_show(sf, false); + return 0; +} + +static int pids_events_local_show(struct seq_file *sf, void *v) +{ + __pids_events_show(sf, true); return 0; } @@ -368,9 +424,42 @@ static struct cftype pids_files[] = { .file_offset = offsetof(struct pids_cgroup, events_file), .flags = CFTYPE_NOT_ON_ROOT, }, + { + .name = "events.local", + .seq_show = pids_events_local_show, + .file_offset = offsetof(struct pids_cgroup, events_local_file), + .flags = CFTYPE_NOT_ON_ROOT, + }, + { } /* terminate */ +}; + +static struct cftype pids_files_legacy[] = { + { + .name = "max", + .write = pids_max_write, + .seq_show = pids_max_show, + .flags = CFTYPE_NOT_ON_ROOT, + }, + { + .name = "current", + .read_s64 = pids_current_read, + .flags = CFTYPE_NOT_ON_ROOT, + }, + { + .name = "peak", + .flags = CFTYPE_NOT_ON_ROOT, + .read_s64 = pids_peak_read, + }, + { + .name = "events", + .seq_show = pids_events_show, + .file_offset = offsetof(struct pids_cgroup, events_file), + .flags = CFTYPE_NOT_ON_ROOT, + }, { } /* terminate */ }; + struct cgroup_subsys pids_cgrp_subsys = { .css_alloc = pids_css_alloc, .css_free = pids_css_free, @@ -379,7 +468,7 @@ struct cgroup_subsys pids_cgrp_subsys = { .can_fork = pids_can_fork, .cancel_fork = pids_cancel_fork, .release = pids_release, - .legacy_cftypes = pids_files, + .legacy_cftypes = pids_files_legacy, .dfl_cftypes = pids_files, .threaded = true, }; diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index fb8b49437573..a06b45272411 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -594,49 +594,46 @@ static void root_cgroup_cputime(struct cgroup_base_stat *bstat) } } + +static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat *bstat) +{ +#ifdef CONFIG_SCHED_CORE + u64 forceidle_time = bstat->forceidle_sum; + + do_div(forceidle_time, NSEC_PER_USEC); + seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time); +#endif +} + void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; u64 usage, utime, stime; - struct cgroup_base_stat bstat; -#ifdef CONFIG_SCHED_CORE - u64 forceidle_time; -#endif if (cgroup_parent(cgrp)) { cgroup_rstat_flush_hold(cgrp); usage = cgrp->bstat.cputime.sum_exec_runtime; cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime); -#ifdef CONFIG_SCHED_CORE - forceidle_time = cgrp->bstat.forceidle_sum; -#endif cgroup_rstat_flush_release(cgrp); } else { - root_cgroup_cputime(&bstat); - usage = bstat.cputime.sum_exec_runtime; - utime = bstat.cputime.utime; - stime = bstat.cputime.stime; -#ifdef CONFIG_SCHED_CORE - forceidle_time = bstat.forceidle_sum; -#endif + /* cgrp->bstat of root is not actually used, reuse it */ + root_cgroup_cputime(&cgrp->bstat); + usage = cgrp->bstat.cputime.sum_exec_runtime; + utime = cgrp->bstat.cputime.utime; + stime = cgrp->bstat.cputime.stime; } do_div(usage, NSEC_PER_USEC); do_div(utime, NSEC_PER_USEC); do_div(stime, NSEC_PER_USEC); -#ifdef CONFIG_SCHED_CORE - do_div(forceidle_time, NSEC_PER_USEC); -#endif seq_printf(seq, "usage_usec %llu\n" "user_usec %llu\n" "system_usec %llu\n", usage, utime, stime); -#ifdef CONFIG_SCHED_CORE - seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time); -#endif + cgroup_force_idle_show(seq, &cgrp->bstat); } /* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */ diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore index 2732e0b29271..952e4448bf07 100644 --- a/tools/testing/selftests/cgroup/.gitignore +++ b/tools/testing/selftests/cgroup/.gitignore @@ -1,11 +1,12 @@ # SPDX-License-Identifier: GPL-2.0-only -test_memcontrol test_core -test_freezer -test_kmem -test_kill test_cpu test_cpuset -test_zswap +test_freezer test_hugetlb_memcg +test_kill +test_kmem +test_memcontrol +test_pids +test_zswap wait_inotify diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile index 16461dc0ffdf..1b897152bab6 100644 --- a/tools/testing/selftests/cgroup/Makefile +++ b/tools/testing/selftests/cgroup/Makefile @@ -6,26 +6,29 @@ all: ${HELPER_PROGS} TEST_FILES := with_stress.sh TEST_PROGS := test_stress.sh test_cpuset_prs.sh test_cpuset_v1_hp.sh TEST_GEN_FILES := wait_inotify -TEST_GEN_PROGS = test_memcontrol -TEST_GEN_PROGS += test_kmem -TEST_GEN_PROGS += test_core -TEST_GEN_PROGS += test_freezer -TEST_GEN_PROGS += test_kill +# Keep the lists lexicographically sorted +TEST_GEN_PROGS = test_core TEST_GEN_PROGS += test_cpu TEST_GEN_PROGS += test_cpuset -TEST_GEN_PROGS += test_zswap +TEST_GEN_PROGS += test_freezer TEST_GEN_PROGS += test_hugetlb_memcg +TEST_GEN_PROGS += test_kill +TEST_GEN_PROGS += test_kmem +TEST_GEN_PROGS += test_memcontrol +TEST_GEN_PROGS += test_pids +TEST_GEN_PROGS += test_zswap LOCAL_HDRS += $(selfdir)/clone3/clone3_selftests.h $(selfdir)/pidfd/pidfd.h include ../lib.mk -$(OUTPUT)/test_memcontrol: cgroup_util.c -$(OUTPUT)/test_kmem: cgroup_util.c $(OUTPUT)/test_core: cgroup_util.c -$(OUTPUT)/test_freezer: cgroup_util.c -$(OUTPUT)/test_kill: cgroup_util.c $(OUTPUT)/test_cpu: cgroup_util.c $(OUTPUT)/test_cpuset: cgroup_util.c -$(OUTPUT)/test_zswap: cgroup_util.c +$(OUTPUT)/test_freezer: cgroup_util.c $(OUTPUT)/test_hugetlb_memcg: cgroup_util.c +$(OUTPUT)/test_kill: cgroup_util.c +$(OUTPUT)/test_kmem: cgroup_util.c +$(OUTPUT)/test_memcontrol: cgroup_util.c +$(OUTPUT)/test_pids: cgroup_util.c +$(OUTPUT)/test_zswap: cgroup_util.c diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index b5eb1be2248c..7c08cc153367 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -28,6 +28,14 @@ CPULIST=$(cat $CGROUP2/cpuset.cpus.effective) NR_CPUS=$(lscpu | grep "^CPU(s):" | sed -e "s/.*:[[:space:]]*//") [[ $NR_CPUS -lt 8 ]] && skip_test "Test needs at least 8 cpus available!" +# Check to see if /dev/console exists and is writable +if [[ -c /dev/console && -w /dev/console ]] +then + CONSOLE=/dev/console +else + CONSOLE=/dev/null +fi + # Set verbose flag and delay factor PROG=$1 VERBOSE=0 @@ -103,8 +111,8 @@ console_msg() { MSG=$1 echo "$MSG" - echo "" > /dev/console - echo "$MSG" > /dev/console + echo "" > $CONSOLE + echo "$MSG" > $CONSOLE pause 0.01 } @@ -161,6 +169,14 @@ test_add_proc() # T = put a task into cgroup # O<c>=<v> = Write <v> to CPU online file of <c> # +# ECPUs - effective CPUs of cpusets +# Pstate - partition root state +# ISOLCPUS - isolated CPUs (<icpus>[,<icpus2>]) +# +# Note that if there are 2 fields in ISOLCPUS, the first one is for +# 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" TEST_MATRIX=( # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS @@ -220,23 +236,29 @@ TEST_MATRIX=( " 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 A1:0-2,A2:1-2,A3:3 A1:P0,A3:P2 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 A1:0-3,A2:1-3,A3:2-3,B1:2-3 A1:P0,A3:P0,B1:P-2" " 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" # 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 \ 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 2-4,2-3" + " 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 \ + 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 \ 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 2-4,2-3" + " 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 \ + A1:P0,A2:P2,A3:P1 2" " 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" @@ -262,8 +284,8 @@ TEST_MATRIX=( . . 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 C2-3:X1:P2 . . . . . . 0 A1:1-3,XA1:1-3,A2:2-3:XA2: A1:P2,A2:P-2 1-3" - " C1-3:S+:P2 C2-3:X1:P2 . . . X3:P2 . . 0 A1:1-2,XA1:1-3,A2:3:XA2:3 A1:P2,A2:P2 1-3" + " 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,B1:4-6 A1:P-2,B1:P0" " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3,B1:4-6 A1:P2,B1:P0 0-3" " C0-3:P2 . . C3-5:C4-5 . . . . 0 A1:0-3,B1:4-5 A1:P2,B1:P0 0-3" @@ -274,32 +296,26 @@ TEST_MATRIX=( " C0-3:X1-3:S+:P2 C1-3:X2-3:S+: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 \ - . . C4 . . 0 A1:1-3,A2:1-3,A3:2-3,XA2:,XA3: A1:P2,A2:P-2,A3:P-2 1-3" + . . 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" # 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 \ + . 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 \ . 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 \ - . . C3 P2 . 0 A1:0-2,A2:0-2,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 \ . . 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 \ . . X3 . . 0 A1:0-3,A2:1-3,XA2:3,XA3:3,A3:2-3 \ 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" - " 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 \ + . X4 . . . 0 A1:0-3,A2:1-3,A3:2-3,XA1:4,XA2:,XA3 \ 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 @@ -346,6 +362,9 @@ TEST_MATRIX=( " C0-1:P1 . . P1:C2-3 C0-2 . . . 0 A1:0-2,B1:2-3 A1:P-1,B1:P-1" " C0-1 . . P1:C2-3 C0-2 . . . 0 A1:0-2,B1:2-3 A1:P0,B1:P-1" + # cpuset.cpus can overlap with sibling cpuset.cpus.exclusive but not subsumed by it + " C0-3 . . C4-5 X5 . . . 0 A1:0-3,B1:4-5" + # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- # Failure cases: @@ -355,6 +374,9 @@ TEST_MATRIX=( # 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" + + # cpuset.cpus cannot be a subset of sibling cpuset.cpus.exclusive + " C0-3 . . C4-5 X3-5 . . . 1 A1:0-3,B1:4-5" ) # @@ -556,14 +578,15 @@ check_cgroup_states() do set -- $(echo $CHK | sed -e "s/:/ /g") CGRP=$1 + CGRP_DIR=$CGRP STATE=$2 FILE= EVAL=$(expr substr $STATE 2 2) - [[ $CGRP = A2 ]] && CGRP=A1/A2 - [[ $CGRP = A3 ]] && CGRP=A1/A2/A3 + [[ $CGRP = A2 ]] && CGRP_DIR=A1/A2 + [[ $CGRP = A3 ]] && CGRP_DIR=A1/A2/A3 case $STATE in - P*) FILE=$CGRP/cpuset.cpus.partition + P*) FILE=$CGRP_DIR/cpuset.cpus.partition ;; *) echo "Unknown state: $STATE!" exit 1 @@ -587,6 +610,16 @@ check_cgroup_states() ;; esac [[ $EVAL != $VAL ]] && return 1 + + # + # For root partition, dump sched-domains info to console if + # verbose mode set for manual comparison with sched debug info. + # + [[ $VAL -eq 1 && $VERBOSE -gt 0 ]] && { + DOMS=$(cat $CGRP_DIR/cpuset.cpus.effective) + [[ -n "$DOMS" ]] && + echo " [$CGRP] sched-domain: $DOMS" > $CONSOLE + } done return 0 } @@ -694,9 +727,9 @@ null_isolcpus_check() [[ $VERBOSE -gt 0 ]] || return 0 # Retry a few times before printing error RETRY=0 - while [[ $RETRY -lt 5 ]] + while [[ $RETRY -lt 8 ]] do - pause 0.01 + pause 0.02 check_isolcpus "." [[ $? -eq 0 ]] && return 0 ((RETRY++)) @@ -726,7 +759,7 @@ run_state_test() while [[ $I -lt $CNT ]] do - echo "Running test $I ..." > /dev/console + echo "Running test $I ..." > $CONSOLE [[ $VERBOSE -gt 1 ]] && { echo "" eval echo \${$TEST[$I]} @@ -783,7 +816,7 @@ run_state_test() while [[ $NEWLIST != $CPULIST && $RETRY -lt 8 ]] do # Wait a bit longer & recheck a few times - pause 0.01 + pause 0.02 ((RETRY++)) NEWLIST=$(cat cpuset.cpus.effective) done diff --git a/tools/testing/selftests/cgroup/test_pids.c b/tools/testing/selftests/cgroup/test_pids.c new file mode 100644 index 000000000000..9ecb83c6cc5c --- /dev/null +++ b/tools/testing/selftests/cgroup/test_pids.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <errno.h> +#include <linux/limits.h> +#include <signal.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> + +#include "../kselftest.h" +#include "cgroup_util.h" + +static int run_success(const char *cgroup, void *arg) +{ + return 0; +} + +static int run_pause(const char *cgroup, void *arg) +{ + return pause(); +} + +/* + * This test checks that pids.max prevents forking new children above the + * specified limit in the cgroup. + */ +static int test_pids_max(const char *root) +{ + int ret = KSFT_FAIL; + char *cg_pids; + int pid; + + cg_pids = cg_name(root, "pids_test"); + if (!cg_pids) + goto cleanup; + + if (cg_create(cg_pids)) + goto cleanup; + + if (cg_read_strcmp(cg_pids, "pids.max", "max\n")) + goto cleanup; + + if (cg_write(cg_pids, "pids.max", "2")) + goto cleanup; + + if (cg_enter_current(cg_pids)) + goto cleanup; + + pid = cg_run_nowait(cg_pids, run_pause, NULL); + if (pid < 0) + goto cleanup; + + if (cg_run_nowait(cg_pids, run_success, NULL) != -1 || errno != EAGAIN) + goto cleanup; + + if (kill(pid, SIGINT)) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + cg_enter_current(root); + cg_destroy(cg_pids); + free(cg_pids); + + return ret; +} + +/* + * This test checks that pids.events are counted in cgroup associated with pids.max + */ +static int test_pids_events(const char *root) +{ + int ret = KSFT_FAIL; + char *cg_parent = NULL, *cg_child = NULL; + int pid; + + cg_parent = cg_name(root, "pids_parent"); + cg_child = cg_name(cg_parent, "pids_child"); + if (!cg_parent || !cg_child) + goto cleanup; + + if (cg_create(cg_parent)) + goto cleanup; + if (cg_write(cg_parent, "cgroup.subtree_control", "+pids")) + goto cleanup; + if (cg_create(cg_child)) + goto cleanup; + + if (cg_write(cg_parent, "pids.max", "2")) + goto cleanup; + + if (cg_read_strcmp(cg_child, "pids.max", "max\n")) + goto cleanup; + + if (cg_enter_current(cg_child)) + goto cleanup; + + pid = cg_run_nowait(cg_child, run_pause, NULL); + if (pid < 0) + goto cleanup; + + if (cg_run_nowait(cg_child, run_success, NULL) != -1 || errno != EAGAIN) + goto cleanup; + + if (kill(pid, SIGINT)) + goto cleanup; + + if (cg_read_key_long(cg_child, "pids.events", "max ") != 0) + goto cleanup; + if (cg_read_key_long(cg_parent, "pids.events", "max ") != 1) + goto cleanup; + + + ret = KSFT_PASS; + +cleanup: + cg_enter_current(root); + if (cg_child) + cg_destroy(cg_child); + if (cg_parent) + cg_destroy(cg_parent); + free(cg_child); + free(cg_parent); + + return ret; +} + + + +#define T(x) { x, #x } +struct pids_test { + int (*fn)(const char *root); + const char *name; +} tests[] = { + T(test_pids_max), + T(test_pids_events), +}; +#undef T + +int main(int argc, char **argv) +{ + char root[PATH_MAX]; + + ksft_print_header(); + ksft_set_plan(ARRAY_SIZE(tests)); + if (cg_find_unified_root(root, sizeof(root), NULL)) + ksft_exit_skip("cgroup v2 isn't mounted\n"); + + /* + * Check that pids controller is available: + * pids is listed in cgroup.controllers + */ + if (cg_read_strstr(root, "cgroup.controllers", "pids")) + ksft_exit_skip("pids controller isn't available\n"); + + if (cg_read_strstr(root, "cgroup.subtree_control", "pids")) + if (cg_write(root, "cgroup.subtree_control", "+pids")) + ksft_exit_skip("Failed to set pids controller\n"); + + for (int i = 0; i < ARRAY_SIZE(tests); i++) { + switch (tests[i].fn(root)) { + case KSFT_PASS: + ksft_test_result_pass("%s\n", tests[i].name); + break; + case KSFT_SKIP: + ksft_test_result_skip("%s\n", tests[i].name); + break; + default: + ksft_test_result_fail("%s\n", tests[i].name); + break; + } + } + + ksft_finished(); +} |