diff options
Diffstat (limited to 'kernel/cgroup/cgroup.c')
-rw-r--r-- | kernel/cgroup/cgroup.c | 141 |
1 files changed, 71 insertions, 70 deletions
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 8afa8690d288..919194de39c8 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1740,6 +1740,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) struct cgroup *dcgrp = &dst_root->cgrp; struct cgroup_subsys *ss; int ssid, i, ret; + u16 dfl_disable_ss_mask = 0; lockdep_assert_held(&cgroup_mutex); @@ -1756,8 +1757,28 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) /* can't move between two non-dummy roots either */ if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root) return -EBUSY; + + /* + * Collect ssid's that need to be disabled from default + * hierarchy. + */ + if (ss->root == &cgrp_dfl_root) + dfl_disable_ss_mask |= 1 << ssid; + } while_each_subsys_mask(); + if (dfl_disable_ss_mask) { + struct cgroup *scgrp = &cgrp_dfl_root.cgrp; + + /* + * Controllers from default hierarchy that need to be rebound + * are all disabled together in one go. + */ + cgrp_dfl_root.subsys_mask &= ~dfl_disable_ss_mask; + WARN_ON(cgroup_apply_control(scgrp)); + cgroup_finalize_control(scgrp, 0); + } + do_each_subsys_mask(ss, ssid, ss_mask) { struct cgroup_root *src_root = ss->root; struct cgroup *scgrp = &src_root->cgrp; @@ -1766,10 +1787,12 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) WARN_ON(!css || cgroup_css(dcgrp, ss)); - /* disable from the source */ - src_root->subsys_mask &= ~(1 << ssid); - WARN_ON(cgroup_apply_control(scgrp)); - cgroup_finalize_control(scgrp, 0); + if (src_root != &cgrp_dfl_root) { + /* disable from the source */ + src_root->subsys_mask &= ~(1 << ssid); + WARN_ON(cgroup_apply_control(scgrp)); + cgroup_finalize_control(scgrp, 0); + } /* rebind */ RCU_INIT_POINTER(scgrp->subsys[ssid], NULL); @@ -2187,8 +2210,10 @@ static void cgroup_kill_sb(struct super_block *sb) * And don't kill the default root. */ if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root && - !percpu_ref_is_dying(&root->cgrp.self.refcnt)) + !percpu_ref_is_dying(&root->cgrp.self.refcnt)) { + cgroup_bpf_offline(&root->cgrp); percpu_ref_kill(&root->cgrp.self.refcnt); + } cgroup_put(&root->cgrp); kernfs_kill_sb(sb); } @@ -5909,17 +5934,20 @@ struct cgroup *cgroup_get_from_id(u64 id) struct kernfs_node *kn; struct cgroup *cgrp = NULL; - mutex_lock(&cgroup_mutex); kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id); if (!kn) - goto out_unlock; + goto out; + + rcu_read_lock(); - cgrp = kn->priv; - if (cgroup_is_dead(cgrp) || !cgroup_tryget(cgrp)) + cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); + if (cgrp && !cgroup_tryget(cgrp)) cgrp = NULL; + + rcu_read_unlock(); + kernfs_put(kn); -out_unlock: - mutex_unlock(&cgroup_mutex); +out: return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_id); @@ -6472,30 +6500,34 @@ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss) * * Find the cgroup at @path on the default hierarchy, increment its * reference count and return it. Returns pointer to the found cgroup on - * success, ERR_PTR(-ENOENT) if @path doesn't exist and ERR_PTR(-ENOTDIR) - * if @path points to a non-directory. + * success, ERR_PTR(-ENOENT) if @path doesn't exist or if the cgroup has already + * been released and ERR_PTR(-ENOTDIR) if @path points to a non-directory. */ struct cgroup *cgroup_get_from_path(const char *path) { struct kernfs_node *kn; - struct cgroup *cgrp; - - mutex_lock(&cgroup_mutex); + struct cgroup *cgrp = ERR_PTR(-ENOENT); kn = kernfs_walk_and_get(cgrp_dfl_root.cgrp.kn, path); - if (kn) { - if (kernfs_type(kn) == KERNFS_DIR) { - cgrp = kn->priv; - cgroup_get_live(cgrp); - } else { - cgrp = ERR_PTR(-ENOTDIR); - } - kernfs_put(kn); - } else { - cgrp = ERR_PTR(-ENOENT); + if (!kn) + goto out; + + if (kernfs_type(kn) != KERNFS_DIR) { + cgrp = ERR_PTR(-ENOTDIR); + goto out_kernfs; } - mutex_unlock(&cgroup_mutex); + rcu_read_lock(); + + cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); + if (!cgrp || !cgroup_tryget(cgrp)) + cgrp = ERR_PTR(-ENOENT); + + rcu_read_unlock(); + +out_kernfs: + kernfs_put(kn); +out: return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_path); @@ -6574,22 +6606,29 @@ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v) void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { - /* Don't associate the sock with unrelated interrupted task's cgroup. */ - if (in_interrupt()) - return; + struct cgroup *cgroup; rcu_read_lock(); + /* Don't associate the sock with unrelated interrupted task's cgroup. */ + if (in_interrupt()) { + cgroup = &cgrp_dfl_root.cgrp; + cgroup_get(cgroup); + goto out; + } + while (true) { struct css_set *cset; cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { - skcd->cgroup = cset->dfl_cgrp; - cgroup_bpf_get(cset->dfl_cgrp); + cgroup = cset->dfl_cgrp; break; } cpu_relax(); } +out: + skcd->cgroup = cgroup; + cgroup_bpf_get(cgroup); rcu_read_unlock(); } @@ -6616,44 +6655,6 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd) #endif /* CONFIG_SOCK_CGROUP_DATA */ -#ifdef CONFIG_CGROUP_BPF -int cgroup_bpf_attach(struct cgroup *cgrp, - struct bpf_prog *prog, struct bpf_prog *replace_prog, - struct bpf_cgroup_link *link, - enum bpf_attach_type type, - u32 flags) -{ - int ret; - - mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags); - mutex_unlock(&cgroup_mutex); - return ret; -} - -int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type) -{ - int ret; - - mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_detach(cgrp, prog, NULL, type); - mutex_unlock(&cgroup_mutex); - return ret; -} - -int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, - union bpf_attr __user *uattr) -{ - int ret; - - mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_query(cgrp, attr, uattr); - mutex_unlock(&cgroup_mutex); - return ret; -} -#endif /* CONFIG_CGROUP_BPF */ - #ifdef CONFIG_SYSFS static ssize_t show_delegatable_files(struct cftype *files, char *buf, ssize_t size, const char *prefix) |