diff options
Diffstat (limited to 'kernel/cgroup')
| -rw-r--r-- | kernel/cgroup/cgroup.c | 37 | ||||
| -rw-r--r-- | kernel/cgroup/cpuset.c | 4 | ||||
| -rw-r--r-- | kernel/cgroup/namespace.c | 5 | ||||
| -rw-r--r-- | kernel/cgroup/rstat.c | 76 |
4 files changed, 61 insertions, 61 deletions
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 06b5ea9d899d..1ea181a58465 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -153,11 +153,7 @@ static struct static_key_true *cgroup_subsys_on_dfl_key[] = { static DEFINE_PER_CPU(struct cgroup_rstat_cpu, cgrp_dfl_root_rstat_cpu); -/* - * The default hierarchy, reserved for the subsystems that are otherwise - * unattached - it never has more than a single cgroup, and all tasks are - * part of that cgroup. - */ +/* the default hierarchy */ struct cgroup_root cgrp_dfl_root = { .cgrp.rstat_cpu = &cgrp_dfl_root_rstat_cpu }; EXPORT_SYMBOL_GPL(cgrp_dfl_root); @@ -251,9 +247,6 @@ bool cgroup_ssid_enabled(int ssid) * cases where a subsystem should behave differnetly depending on the * interface version. * - * The set of behaviors which change on the default hierarchy are still - * being determined and the mount option is prefixed with __DEVEL__. - * * List of changed behaviors: * * - Mount options "noprefix", "xattr", "clone_children", "release_agent" @@ -4881,7 +4874,6 @@ static struct cftype cgroup_base_files[] = { }, { .name = "cpu.stat", - .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cpu_stat_show, }, #ifdef CONFIG_PSI @@ -6508,33 +6500,6 @@ int cgroup_bpf_attach(struct cgroup *cgrp, return ret; } -int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *old_prog, - struct bpf_prog *new_prog) -{ - struct bpf_cgroup_link *cg_link; - int ret; - - if (link->ops != &bpf_cgroup_link_lops) - return -EINVAL; - - cg_link = container_of(link, struct bpf_cgroup_link, link); - - mutex_lock(&cgroup_mutex); - /* link might have been auto-released by dying cgroup, so fail */ - if (!cg_link->cgroup) { - ret = -EINVAL; - goto out_unlock; - } - if (old_prog && link->prog != old_prog) { - ret = -EPERM; - goto out_unlock; - } - ret = __cgroup_bpf_replace(cg_link->cgroup, cg_link, new_prog); -out_unlock: - mutex_unlock(&cgroup_mutex); - return ret; -} - int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type) { diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 729d3a5c772e..642415b8c3c9 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1655,7 +1655,7 @@ static void update_tasks_nodemask(struct cpuset *cs) guarantee_online_mems(cs, &newmems); /* - * The mpol_rebind_mm() call takes mmap_sem, which we couldn't + * The mpol_rebind_mm() call takes mmap_lock, which we couldn't * take while holding tasklist_lock. Forks can happen - the * mpol_dup() cpuset_being_rebound check will catch such forks, * and rebind their vma mempolicies too. Because we still hold @@ -1760,7 +1760,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) * * Call with cpuset_mutex held. May take callback_lock during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, - * lock each such tasks mm->mmap_sem, scan its vma's and rebind + * lock each such tasks mm->mmap_lock, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. */ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c index b05f1dd58a62..812a61afd538 100644 --- a/kernel/cgroup/namespace.c +++ b/kernel/cgroup/namespace.c @@ -95,11 +95,12 @@ static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns) return container_of(ns, struct cgroup_namespace, ns); } -static int cgroupns_install(struct nsproxy *nsproxy, struct ns_common *ns) +static int cgroupns_install(struct nsset *nsset, struct ns_common *ns) { + struct nsproxy *nsproxy = nsset->nsproxy; struct cgroup_namespace *cgroup_ns = to_cg_ns(ns); - if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN) || + if (!ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN) || !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 6f87352f8219..b6397a186ce9 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -33,12 +33,9 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) return; /* - * Paired with the one in cgroup_rstat_cpu_pop_updated(). Either we - * see NULL updated_next or they see our updated stat. - */ - smp_mb(); - - /* + * Speculative already-on-list test. This may race leading to + * temporary inaccuracies, which is fine. + * * Because @parent's updated_children is terminated with @parent * instead of NULL, we can tell whether @cgrp is on the list by * testing the next pointer for NULL. @@ -134,13 +131,6 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, *nextp = rstatc->updated_next; rstatc->updated_next = NULL; - /* - * Paired with the one in cgroup_rstat_cpu_updated(). - * Either they see NULL updated_next or we see their - * updated stat. - */ - smp_mb(); - return pos; } @@ -399,18 +389,62 @@ void __cgroup_account_cputime_field(struct cgroup *cgrp, cgroup_base_stat_cputime_account_end(cgrp, rstatc); } +/* + * compute the cputime for the root cgroup by getting the per cpu data + * at a global level, then categorizing the fields in a manner consistent + * with how it is done by __cgroup_account_cputime_field for each bit of + * cpu time attributed to a cgroup. + */ +static void root_cgroup_cputime(struct task_cputime *cputime) +{ + int i; + + cputime->stime = 0; + cputime->utime = 0; + cputime->sum_exec_runtime = 0; + for_each_possible_cpu(i) { + struct kernel_cpustat kcpustat; + u64 *cpustat = kcpustat.cpustat; + u64 user = 0; + u64 sys = 0; + + kcpustat_cpu_fetch(&kcpustat, i); + + user += cpustat[CPUTIME_USER]; + user += cpustat[CPUTIME_NICE]; + cputime->utime += user; + + sys += cpustat[CPUTIME_SYSTEM]; + sys += cpustat[CPUTIME_IRQ]; + sys += cpustat[CPUTIME_SOFTIRQ]; + cputime->stime += sys; + + cputime->sum_exec_runtime += user; + cputime->sum_exec_runtime += sys; + cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL]; + cputime->sum_exec_runtime += cpustat[CPUTIME_GUEST]; + cputime->sum_exec_runtime += cpustat[CPUTIME_GUEST_NICE]; + } +} + void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; u64 usage, utime, stime; - - if (!cgroup_parent(cgrp)) - return; - - cgroup_rstat_flush_hold(cgrp); - usage = cgrp->bstat.cputime.sum_exec_runtime; - cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime); - cgroup_rstat_flush_release(); + struct task_cputime cputime; + + 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); + cgroup_rstat_flush_release(); + } else { + root_cgroup_cputime(&cputime); + usage = cputime.sum_exec_runtime; + utime = cputime.utime; + stime = cputime.stime; + } do_div(usage, NSEC_PER_USEC); do_div(utime, NSEC_PER_USEC); |