1 files changed, 46 insertions, 70 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index e75d2191226b..528bd44b59e2 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -27,10 +27,12 @@
 
 #include <linux/cgroup-defs.h>
 
+struct kernel_clone_args;
+
 #ifdef CONFIG_CGROUPS
 
 /*
- * All weight knobs on the default hierarhcy should use the following min,
+ * All weight knobs on the default hierarchy should use the following min,
  * default and max values.  The default value is the logarithmic center of
  * MIN and MAX and allows 100x to be expressed in both directions.
  */
@@ -58,9 +60,6 @@ struct css_task_iter {
 	struct list_head		*tcset_head;
 
 	struct list_head		*task_pos;
-	struct list_head		*tasks_head;
-	struct list_head		*mg_tasks_head;
-	struct list_head		*dying_tasks_head;
 
 	struct list_head		*cur_tasks_head;
 	struct css_set			*cur_cset;
@@ -107,6 +106,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
 
 struct cgroup *cgroup_get_from_path(const char *path);
 struct cgroup *cgroup_get_from_fd(int fd);
+struct cgroup *cgroup_v1v2_get_from_fd(int fd);
 
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
@@ -115,6 +115,7 @@ int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_rm_cftypes(struct cftype *cfts);
 void cgroup_file_notify(struct cgroup_file *cfile);
+void cgroup_file_show(struct cgroup_file *cfile, bool show);
 
 int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
 int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry);
@@ -122,9 +123,12 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 		     struct pid *pid, struct task_struct *tsk);
 
 void cgroup_fork(struct task_struct *p);
-extern int cgroup_can_fork(struct task_struct *p);
-extern void cgroup_cancel_fork(struct task_struct *p);
-extern void cgroup_post_fork(struct task_struct *p);
+extern int cgroup_can_fork(struct task_struct *p,
+			   struct kernel_clone_args *kargs);
+extern void cgroup_cancel_fork(struct task_struct *p,
+			       struct kernel_clone_args *kargs);
+extern void cgroup_post_fork(struct task_struct *p,
+			     struct kernel_clone_args *kargs);
 void cgroup_exit(struct task_struct *p);
 void cgroup_release(struct task_struct *p);
 void cgroup_free(struct task_struct *p);
@@ -305,7 +309,7 @@ void css_task_iter_end(struct css_task_iter *it);
  * Inline functions.
  */
 
-static inline u64 cgroup_id(struct cgroup *cgrp)
+static inline u64 cgroup_id(const struct cgroup *cgrp)
 {
 	return cgrp->kn->id;
 }
@@ -430,6 +434,18 @@ static inline void cgroup_put(struct cgroup *cgrp)
 	css_put(&cgrp->self);
 }
 
+extern struct mutex cgroup_mutex;
+
+static inline void cgroup_lock(void)
+{
+	mutex_lock(&cgroup_mutex);
+}
+
+static inline void cgroup_unlock(void)
+{
+	mutex_unlock(&cgroup_mutex);
+}
+
 /**
  * task_css_set_check - obtain a task's css_set with extra access conditions
  * @task: the task to obtain css_set for
@@ -444,10 +460,10 @@ static inline void cgroup_put(struct cgroup *cgrp)
  * as locks used during the cgroup_subsys::attach() methods.
  */
 #ifdef CONFIG_PROVE_RCU
-extern struct mutex cgroup_mutex;
 extern spinlock_t css_set_lock;
 #define task_css_set_check(task, __c)					\
 	rcu_dereference_check((task)->cgroups,				\
+		rcu_read_lock_sched_held() ||				\
 		lockdep_is_held(&cgroup_mutex) ||			\
 		lockdep_is_held(&css_set_lock) ||			\
 		((task)->flags & PF_EXITING) || (__c))
@@ -571,7 +587,7 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp,
 {
 	if (cgrp->root != ancestor->root || cgrp->level < ancestor->level)
 		return false;
-	return cgrp->ancestor_ids[ancestor->level] == cgroup_id(ancestor);
+	return cgrp->ancestors[ancestor->level] == ancestor;
 }
 
 /**
@@ -588,11 +604,9 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp,
 static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp,
 					     int ancestor_level)
 {
-	if (cgrp->level < ancestor_level)
+	if (ancestor_level < 0 || ancestor_level > cgrp->level)
 		return NULL;
-	while (cgrp && cgrp->level > ancestor_level)
-		cgrp = cgroup_parent(cgrp);
-	return cgrp;
+	return cgrp->ancestors[ancestor_level];
 }
 
 /**
@@ -669,10 +683,7 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
 	pr_cont_kernfs_path(cgrp->kn);
 }
 
-static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
-{
-	return &cgrp->psi;
-}
+bool cgroup_psi_enabled(void);
 
 static inline void cgroup_init_kthreadd(void)
 {
@@ -694,23 +705,29 @@ static inline void cgroup_kthread_ready(void)
 }
 
 void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen);
+struct cgroup *cgroup_get_from_id(u64 id);
 #else /* !CONFIG_CGROUPS */
 
 struct cgroup_subsys_state;
 struct cgroup;
 
-static inline u64 cgroup_id(struct cgroup *cgrp) { return 1; }
+static inline u64 cgroup_id(const struct cgroup *cgrp) { return 1; }
 static inline void css_get(struct cgroup_subsys_state *css) {}
 static inline void css_put(struct cgroup_subsys_state *css) {}
+static inline void cgroup_lock(void) {}
+static inline void cgroup_unlock(void) {}
 static inline int cgroup_attach_task_all(struct task_struct *from,
 					 struct task_struct *t) { return 0; }
 static inline int cgroupstats_build(struct cgroupstats *stats,
 				    struct dentry *dentry) { return -EINVAL; }
 
 static inline void cgroup_fork(struct task_struct *p) {}
-static inline int cgroup_can_fork(struct task_struct *p) { return 0; }
-static inline void cgroup_cancel_fork(struct task_struct *p) {}
-static inline void cgroup_post_fork(struct task_struct *p) {}
+static inline int cgroup_can_fork(struct task_struct *p,
+				  struct kernel_clone_args *kargs) { return 0; }
+static inline void cgroup_cancel_fork(struct task_struct *p,
+				      struct kernel_clone_args *kargs) {}
+static inline void cgroup_post_fork(struct task_struct *p,
+				    struct kernel_clone_args *kargs) {}
 static inline void cgroup_exit(struct task_struct *p) {}
 static inline void cgroup_release(struct task_struct *p) {}
 static inline void cgroup_free(struct task_struct *p) {}
@@ -725,9 +742,9 @@ static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
 	return NULL;
 }
 
-static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
+static inline bool cgroup_psi_enabled(void)
 {
-	return NULL;
+	return false;
 }
 
 static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
@@ -773,11 +790,9 @@ static inline void cgroup_account_cputime(struct task_struct *task,
 
 	cpuacct_charge(task, delta_exec);
 
-	rcu_read_lock();
 	cgrp = task_dfl_cgroup(task);
 	if (cgroup_parent(cgrp))
 		__cgroup_account_cputime(cgrp, delta_exec);
-	rcu_read_unlock();
 }
 
 static inline void cgroup_account_cputime_field(struct task_struct *task,
@@ -788,11 +803,9 @@ static inline void cgroup_account_cputime_field(struct task_struct *task,
 
 	cpuacct_account_field(task, index, delta_exec);
 
-	rcu_read_lock();
 	cgrp = task_dfl_cgroup(task);
 	if (cgroup_parent(cgrp))
 		__cgroup_account_cputime_field(cgrp, index, delta_exec);
-	rcu_read_unlock();
 }
 
 #else	/* CONFIG_CGROUPS */
@@ -811,43 +824,24 @@ static inline void cgroup_account_cputime_field(struct task_struct *task,
  */
 #ifdef CONFIG_SOCK_CGROUP_DATA
 
-#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
-extern spinlock_t cgroup_sk_update_lock;
-#endif
-
-void cgroup_sk_alloc_disable(void);
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
+void cgroup_sk_clone(struct sock_cgroup_data *skcd);
 void cgroup_sk_free(struct sock_cgroup_data *skcd);
 
 static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 {
-#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
-	unsigned long v;
-
-	/*
-	 * @skcd->val is 64bit but the following is safe on 32bit too as we
-	 * just need the lower ulong to be written and read atomically.
-	 */
-	v = READ_ONCE(skcd->val);
-
-	if (v & 1)
-		return &cgrp_dfl_root.cgrp;
-
-	return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;
-#else
-	return (struct cgroup *)(unsigned long)skcd->val;
-#endif
+	return skcd->cgroup;
 }
 
 #else	/* CONFIG_CGROUP_DATA */
 
 static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {}
+static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {}
 static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}
 
 #endif	/* CONFIG_CGROUP_DATA */
 
 struct cgroup_namespace {
-	refcount_t		count;
 	struct ns_common	ns;
 	struct user_namespace	*user_ns;
 	struct ucounts		*ucounts;
@@ -882,12 +876,12 @@ copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns,
 static inline void get_cgroup_ns(struct cgroup_namespace *ns)
 {
 	if (ns)
-		refcount_inc(&ns->count);
+		refcount_inc(&ns->ns.count);
 }
 
 static inline void put_cgroup_ns(struct cgroup_namespace *ns)
 {
-	if (ns && refcount_dec_and_test(&ns->count))
+	if (ns && refcount_dec_and_test(&ns->ns.count))
 		free_cgroup_ns(ns);
 }
 
@@ -900,20 +894,6 @@ void cgroup_freeze(struct cgroup *cgrp, bool freeze);
 void cgroup_freezer_migrate_task(struct task_struct *task, struct cgroup *src,
 				 struct cgroup *dst);
 
-static inline bool cgroup_task_freeze(struct task_struct *task)
-{
-	bool ret;
-
-	if (task->flags & PF_KTHREAD)
-		return false;
-
-	rcu_read_lock();
-	ret = test_bit(CGRP_FREEZE, &task_dfl_cgroup(task)->flags);
-	rcu_read_unlock();
-
-	return ret;
-}
-
 static inline bool cgroup_task_frozen(struct task_struct *task)
 {
 	return task->frozen;
@@ -923,10 +903,6 @@ static inline bool cgroup_task_frozen(struct task_struct *task)
 
 static inline void cgroup_enter_frozen(void) { }
 static inline void cgroup_leave_frozen(bool always_leave) { }
-static inline bool cgroup_task_freeze(struct task_struct *task)
-{
-	return false;
-}
 static inline bool cgroup_task_frozen(struct task_struct *task)
 {
 	return false;