Merge tag 'cgroup-for-6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - Whenever cpuset needs to rebuild sched_domain, it walked all tasks
   looking for DEADLINE tasks as they need to be accounted on the new
   domain. Walking all tasks can be expensive and there may not be any
   DEADLINE tasks at all. Task iteration is now omitted if there are no
   DEADLINE tasks

 - Fixes DEADLINE bandwidth misaccounting after task migration failures

 - When no controller is enabled, -Wstringop-overflow warning is
   triggered. The fix patch added an early exit which is too eager and
   got reverted for now. Will fix later

 - Everything else is minor cleanups

* tag 'cgroup-for-6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  Revert "cgroup: Avoid -Wstringop-overflow warnings"
  cgroup/misc: Expose misc.current on cgroup v2 root
  cgroup: Avoid -Wstringop-overflow warnings
  cgroup: remove obsolete comment on cgroup_on_dfl()
  cgroup: remove unused task_cgroup_path()
  cgroup/cpuset: remove unneeded header files
  cgroup: make cgroup_is_threaded() and cgroup_is_thread_root() static
  rdmacg: fix kernel-doc warnings in rdmacg
  cgroup: Replace the css_set call with cgroup_get
  cgroup: remove unused macro for_each_e_css()
  cgroup: Update out-of-date comment in cgroup_migrate()
  cgroup: Replace all non-returning strlcpy with strscpy
  cgroup/cpuset: remove unneeded header files
  cgroup/cpuset: Free DL BW in case can_attach() fails
  sched/deadline: Create DL BW alloc, free & check overflow interface
  cgroup/cpuset: Iterate only if DEADLINE tasks are present
  sched/cpuset: Keep track of SCHED_DEADLINE task in cpusets
  sched/cpuset: Bring back cpuset_mutex
  cgroup/cpuset: Rename functions dealing with DEADLINE accounting

Documentation/admin-guide/cgroup-v2.rst

@@ -2443,7 +2443,7 @@ Miscellaneous controller provides 3 interface files. If two misc resources (res_
 	  res_b 10
 
   misc.current
-        A read-only flat-keyed file shown in the non-root cgroups.  It shows
+        A read-only flat-keyed file shown in the all cgroups.  It shows
         the current usage of the resources in the cgroup and its children.::
 
 	  $ cat misc.current

include/linux/cgroup.h

@@ -118,7 +118,6 @@ 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);
 int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 		     struct pid *pid, struct task_struct *tsk);

include/linux/cpuset.h

@@ -71,8 +71,10 @@ extern void cpuset_init_smp(void);
 extern void cpuset_force_rebuild(void);
 extern void cpuset_update_active_cpus(void);
 extern void cpuset_wait_for_hotplug(void);
-extern void cpuset_read_lock(void);
-extern void cpuset_read_unlock(void);
+extern void inc_dl_tasks_cs(struct task_struct *task);
+extern void dec_dl_tasks_cs(struct task_struct *task);
+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 nodemask_t cpuset_mems_allowed(struct task_struct *p);
@@ -189,8 +191,10 @@ static inline void cpuset_update_active_cpus(void)
 
 static inline void cpuset_wait_for_hotplug(void) { }
 
-static inline void cpuset_read_lock(void) { }
-static inline void cpuset_read_unlock(void) { }
+static inline void inc_dl_tasks_cs(struct task_struct *task) { }
+static inline void dec_dl_tasks_cs(struct task_struct *task) { }
+static inline void cpuset_lock(void) { }
+static inline void cpuset_unlock(void) { }
 
 static inline void cpuset_cpus_allowed(struct task_struct *p,
 				       struct cpumask *mask)

include/linux/sched.h

@@ -1852,7 +1852,9 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags)
 }
 
 extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
-extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_effective_cpus);
+extern int task_can_attach(struct task_struct *p);
+extern int dl_bw_alloc(int cpu, u64 dl_bw);
+extern void dl_bw_free(int cpu, u64 dl_bw);
 #ifdef CONFIG_SMP
 extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
 extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask);

kernel/cgroup/cgroup-internal.h

@@ -220,8 +220,6 @@ static inline void get_css_set(struct css_set *cset)
 
 bool cgroup_ssid_enabled(int ssid);
 bool cgroup_on_dfl(const struct cgroup *cgrp);
-bool cgroup_is_thread_root(struct cgroup *cgrp);
-bool cgroup_is_threaded(struct cgroup *cgrp);
 
 struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root);
 struct cgroup *task_cgroup_from_root(struct task_struct *task,

kernel/cgroup/cgroup-v1.c

@@ -563,7 +563,7 @@ static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of,
 	if (!cgrp)
 		return -ENODEV;
 	spin_lock(&release_agent_path_lock);
-	strlcpy(cgrp->root->release_agent_path, strstrip(buf),
+	strscpy(cgrp->root->release_agent_path, strstrip(buf),
 		sizeof(cgrp->root->release_agent_path));
 	spin_unlock(&release_agent_path_lock);
 	cgroup_kn_unlock(of->kn);
@@ -797,7 +797,7 @@ void cgroup1_release_agent(struct work_struct *work)
 		goto out_free;
 
 	spin_lock(&release_agent_path_lock);
-	strlcpy(agentbuf, cgrp->root->release_agent_path, PATH_MAX);
+	strscpy(agentbuf, cgrp->root->release_agent_path, PATH_MAX);
 	spin_unlock(&release_agent_path_lock);
 	if (!agentbuf[0])
 		goto out_free;

kernel/cgroup/cgroup.c

@@ -57,6 +57,7 @@
 #include <linux/file.h>
 #include <linux/fs_parser.h>
 #include <linux/sched/cputime.h>
+#include <linux/sched/deadline.h>
 #include <linux/psi.h>
 #include <net/sock.h>
 
@@ -312,8 +313,6 @@ bool cgroup_ssid_enabled(int ssid)
  *   masks of ancestors.
  *
  * - blkcg: blk-throttle becomes properly hierarchical.
- *
- * - debug: disallowed on the default hierarchy.
  */
 bool cgroup_on_dfl(const struct cgroup *cgrp)
 {
@@ -356,7 +355,7 @@ static bool cgroup_has_tasks(struct cgroup *cgrp)
 	return cgrp->nr_populated_csets;
 }
 
-bool cgroup_is_threaded(struct cgroup *cgrp)
+static bool cgroup_is_threaded(struct cgroup *cgrp)
 {
 	return cgrp->dom_cgrp != cgrp;
 }
@@ -395,7 +394,7 @@ static bool cgroup_can_be_thread_root(struct cgroup *cgrp)
 }
 
 /* is @cgrp root of a threaded subtree? */
-bool cgroup_is_thread_root(struct cgroup *cgrp)
+static bool cgroup_is_thread_root(struct cgroup *cgrp)
 {
 	/* thread root should be a domain */
 	if (cgroup_is_threaded(cgrp))
@@ -618,7 +617,7 @@ EXPORT_SYMBOL_GPL(cgroup_get_e_css);
 static void cgroup_get_live(struct cgroup *cgrp)
 {
 	WARN_ON_ONCE(cgroup_is_dead(cgrp));
-	css_get(&cgrp->self);
+	cgroup_get(cgrp);
 }
 
 /**
@@ -689,21 +688,6 @@ EXPORT_SYMBOL_GPL(of_css);
 				lockdep_is_held(&cgroup_mutex)))) { }	\
 		else
 
-/**
- * for_each_e_css - iterate all effective css's of a cgroup
- * @css: the iteration cursor
- * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end
- * @cgrp: the target cgroup to iterate css's of
- *
- * Should be called under cgroup_[tree_]mutex.
- */
-#define for_each_e_css(css, ssid, cgrp)					    \
-	for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++)	    \
-		if (!((css) = cgroup_e_css_by_mask(cgrp,		    \
-						   cgroup_subsys[(ssid)]))) \
-			;						    \
-		else
-
 /**
  * do_each_subsys_mask - filter for_each_subsys with a bitmask
  * @ss: the iteration cursor
@@ -2392,45 +2376,6 @@ int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
 }
 EXPORT_SYMBOL_GPL(cgroup_path_ns);
 
-/**
- * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
- * @task: target task
- * @buf: the buffer to write the path into
- * @buflen: the length of the buffer
- *
- * Determine @task's cgroup on the first (the one with the lowest non-zero
- * hierarchy_id) cgroup hierarchy and copy its path into @buf.  This
- * function grabs cgroup_mutex and shouldn't be used inside locks used by
- * cgroup controller callbacks.
- *
- * Return value is the same as kernfs_path().
- */
-int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
-{
-	struct cgroup_root *root;
-	struct cgroup *cgrp;
-	int hierarchy_id = 1;
-	int ret;
-
-	cgroup_lock();
-	spin_lock_irq(&css_set_lock);
-
-	root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id);
-
-	if (root) {
-		cgrp = task_cgroup_from_root(task, root);
-		ret = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns);
-	} else {
-		/* if no hierarchy exists, everyone is in "/" */
-		ret = strscpy(buf, "/", buflen);
-	}
-
-	spin_unlock_irq(&css_set_lock);
-	cgroup_unlock();
-	return ret;
-}
-EXPORT_SYMBOL_GPL(task_cgroup_path);
-
 /**
  * cgroup_attach_lock - Lock for ->attach()
  * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem
@@ -2885,9 +2830,9 @@ int cgroup_migrate(struct task_struct *leader, bool threadgroup,
 	struct task_struct *task;
 
 	/*
-	 * Prevent freeing of tasks while we take a snapshot. Tasks that are
-	 * already PF_EXITING could be freed from underneath us unless we
-	 * take an rcu_read_lock.
+	 * The following thread iteration should be inside an RCU critical
+	 * section to prevent tasks from being freed while taking the snapshot.
+	 * spin_lock_irq() implies RCU critical section here.
 	 */
 	spin_lock_irq(&css_set_lock);
 	task = leader;
@@ -6708,6 +6653,9 @@ void cgroup_exit(struct task_struct *tsk)
 	list_add_tail(&tsk->cg_list, &cset->dying_tasks);
 	cset->nr_tasks--;
 
+	if (dl_task(tsk))
+		dec_dl_tasks_cs(tsk);
+
 	WARN_ON_ONCE(cgroup_task_frozen(tsk));
 	if (unlikely(!(tsk->flags & PF_KTHREAD) &&
 		     test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags)))

kernel/cgroup/misc.c

@@ -357,7 +357,6 @@ static struct cftype misc_cg_files[] = {
 	{
 		.name = "current",
 		.seq_show = misc_cg_current_show,
-		.flags = CFTYPE_NOT_ON_ROOT,
 	},
 	{
 		.name = "capacity",

kernel/cgroup/rdma.c

@@ -197,6 +197,7 @@ uncharge_cg_locked(struct rdma_cgroup *cg,
 
 /**
  * rdmacg_uncharge_hierarchy - hierarchically uncharge rdma resource count
+ * @cg: pointer to cg to uncharge and all parents in hierarchy
  * @device: pointer to rdmacg device
  * @stop_cg: while traversing hirerchy, when meet with stop_cg cgroup
  *           stop uncharging
@@ -221,6 +222,7 @@ static void rdmacg_uncharge_hierarchy(struct rdma_cgroup *cg,
 
 /**
  * rdmacg_uncharge - hierarchically uncharge rdma resource count
+ * @cg: pointer to cg to uncharge and all parents in hierarchy
  * @device: pointer to rdmacg device
  * @index: index of the resource to uncharge in cgroup in given resource pool
  */

kernel/sched/core.c

@@ -7631,6 +7631,7 @@ static int __sched_setscheduler(struct task_struct *p,
 	int reset_on_fork;
 	int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 	struct rq *rq;
+	bool cpuset_locked = false;
 
 	/* The pi code expects interrupts enabled */
 	BUG_ON(pi && in_interrupt());
@@ -7680,8 +7681,14 @@ static int __sched_setscheduler(struct task_struct *p,
 			return retval;
 	}
 
-	if (pi)
-		cpuset_read_lock();
+	/*
+	 * SCHED_DEADLINE bandwidth accounting relies on stable cpusets
+	 * information.
+	 */
+	if (dl_policy(policy) || dl_policy(p->policy)) {
+		cpuset_locked = true;
+		cpuset_lock();
+	}
 
 	/*
 	 * Make sure no PI-waiters arrive (or leave) while we are
@@ -7757,8 +7764,8 @@ static int __sched_setscheduler(struct task_struct *p,
 	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
 		policy = oldpolicy = -1;
 		task_rq_unlock(rq, p, &rf);
-		if (pi)
-			cpuset_read_unlock();
+		if (cpuset_locked)
+			cpuset_unlock();
 		goto recheck;
 	}
 
@@ -7825,7 +7832,8 @@ static int __sched_setscheduler(struct task_struct *p,
 	task_rq_unlock(rq, p, &rf);
 
 	if (pi) {
-		cpuset_read_unlock();
+		if (cpuset_locked)
+			cpuset_unlock();
 		rt_mutex_adjust_pi(p);
 	}
 
@@ -7837,8 +7845,8 @@ static int __sched_setscheduler(struct task_struct *p,
 
 unlock:
 	task_rq_unlock(rq, p, &rf);
-	if (pi)
-		cpuset_read_unlock();
+	if (cpuset_locked)
+		cpuset_unlock();
 	return retval;
 }
 
@@ -9327,8 +9335,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur,
 	return ret;
 }
 
-int task_can_attach(struct task_struct *p,
-		    const struct cpumask *cs_effective_cpus)
+int task_can_attach(struct task_struct *p)
 {
 	int ret = 0;
 
@@ -9341,21 +9348,9 @@ int task_can_attach(struct task_struct *p,
 	 * success of set_cpus_allowed_ptr() on all attached tasks
 	 * before cpus_mask may be changed.
 	 */
-	if (p->flags & PF_NO_SETAFFINITY) {
+	if (p->flags & PF_NO_SETAFFINITY)
 		ret = -EINVAL;
-		goto out;
-	}
 
-	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
-					      cs_effective_cpus)) {
-		int cpu = cpumask_any_and(cpu_active_mask, cs_effective_cpus);
-
-		if (unlikely(cpu >= nr_cpu_ids))
-			return -EINVAL;
-		ret = dl_cpu_busy(cpu, p);
-	}
-
-out:
 	return ret;
 }
 
@@ -9638,7 +9633,7 @@ static void cpuset_cpu_active(void)
 static int cpuset_cpu_inactive(unsigned int cpu)
 {
 	if (!cpuhp_tasks_frozen) {
-		int ret = dl_cpu_busy(cpu, NULL);
+		int ret = dl_bw_check_overflow(cpu);
 
 		if (ret)
 			return ret;

kernel/sched/deadline.c

@@ -16,6 +16,8 @@
  *                    Fabio Checconi <fchecconi@gmail.com>
  */
 
+#include <linux/cpuset.h>
+
 /*
  * Default limits for DL period; on the top end we guard against small util
  * tasks still getting ridiculously long effective runtimes, on the bottom end we
@@ -2585,6 +2587,12 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
 	if (task_on_rq_queued(p) && p->dl.dl_runtime)
 		task_non_contending(p);
 
+	/*
+	 * In case a task is setscheduled out from SCHED_DEADLINE we need to
+	 * keep track of that on its cpuset (for correct bandwidth tracking).
+	 */
+	dec_dl_tasks_cs(p);
+
 	if (!task_on_rq_queued(p)) {
 		/*
 		 * Inactive timer is armed. However, p is leaving DEADLINE and
@@ -2625,6 +2633,12 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 	if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1)
 		put_task_struct(p);
 
+	/*
+	 * In case a task is setscheduled to SCHED_DEADLINE we need to keep
+	 * track of that on its cpuset (for correct bandwidth tracking).
+	 */
+	inc_dl_tasks_cs(p);
+
 	/* If p is not queued we will update its parameters at next wakeup. */
 	if (!task_on_rq_queued(p)) {
 		add_rq_bw(&p->dl, &rq->dl);
@@ -3033,26 +3047,38 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
 	return ret;
 }
 
-int dl_cpu_busy(int cpu, struct task_struct *p)
+enum dl_bw_request {
+	dl_bw_req_check_overflow = 0,
+	dl_bw_req_alloc,
+	dl_bw_req_free
+};
+
+static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
 {
-	unsigned long flags, cap;
+	unsigned long flags;
 	struct dl_bw *dl_b;
-	bool overflow;
+	bool overflow = 0;
 
 	rcu_read_lock_sched();
 	dl_b = dl_bw_of(cpu);
 	raw_spin_lock_irqsave(&dl_b->lock, flags);
-	cap = dl_bw_capacity(cpu);
-	overflow = __dl_overflow(dl_b, cap, 0, p ? p->dl.dl_bw : 0);
 
-	if (!overflow && p) {
-		/*
-		 * We reserve space for this task in the destination
-		 * root_domain, as we can't fail after this point.
-		 * We will free resources in the source root_domain
-		 * later on (see set_cpus_allowed_dl()).
-		 */
-		__dl_add(dl_b, p->dl.dl_bw, dl_bw_cpus(cpu));
+	if (req == dl_bw_req_free) {
+		__dl_sub(dl_b, dl_bw, dl_bw_cpus(cpu));
+	} else {
+		unsigned long cap = dl_bw_capacity(cpu);
+
+		overflow = __dl_overflow(dl_b, cap, 0, dl_bw);
+
+		if (req == dl_bw_req_alloc && !overflow) {
+			/*
+			 * We reserve space in the destination
+			 * root_domain, as we can't fail after this point.
+			 * We will free resources in the source root_domain
+			 * later on (see set_cpus_allowed_dl()).
+			 */
+			__dl_add(dl_b, dl_bw, dl_bw_cpus(cpu));
+		}
 	}
 
 	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
@@ -3060,6 +3086,21 @@ int dl_cpu_busy(int cpu, struct task_struct *p)
 
 	return overflow ? -EBUSY : 0;
 }
+
+int dl_bw_check_overflow(int cpu)
+{
+	return dl_bw_manage(dl_bw_req_check_overflow, cpu, 0);
+}
+
+int dl_bw_alloc(int cpu, u64 dl_bw)
+{
+	return dl_bw_manage(dl_bw_req_alloc, cpu, dl_bw);
+}
+
+void dl_bw_free(int cpu, u64 dl_bw)
+{
+	dl_bw_manage(dl_bw_req_free, cpu, dl_bw);
+}
 #endif
 
 #ifdef CONFIG_SCHED_DEBUG

kernel/sched/sched.h

@@ -324,7 +324,7 @@ extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr);
 extern bool __checkparam_dl(const struct sched_attr *attr);
 extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
 extern int  dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
-extern int  dl_cpu_busy(int cpu, struct task_struct *p);
+extern int  dl_bw_check_overflow(int cpu);
 
 #ifdef CONFIG_CGROUP_SCHED