Merge tag 'cgroup-for-7.1' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - cgroup_file_notify() locking converted from a global lock to
   per-cgroup_file spinlock with a lockless fast-path when no
   notification is needed

 - Misc changes including exposing cgroup helpers for sched_ext and
   minor fixes

* tag 'cgroup-for-7.1' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup/rdma: fix swapped arguments in pr_warn() format string
  cgroup/dmem: remove region parameter from dmemcg_parse_limit
  cgroup: replace global cgroup_file_kn_lock with per-cgroup_file lock
  cgroup: add lockless fast-path checks to cgroup_file_notify()
  cgroup: reduce cgroup_file_kn_lock hold time in cgroup_file_notify()
  cgroup: Expose some cgroup helpers

Author: torvalds

include/linux/cgroup-defs.h

@@ -167,6 +167,7 @@ struct cgroup_file {
 	struct kernfs_node *kn;
 	unsigned long notified_at;
 	struct timer_list notify_timer;
+	spinlock_t lock;
 };
 
 /*

include/linux/cgroup.h

@@ -42,6 +42,14 @@ struct kernel_clone_args;
 
 #ifdef CONFIG_CGROUPS
 
+/*
+ * To avoid confusing the compiler (and generating warnings) with code
+ * that attempts to access what would be a 0-element array (i.e. sized
+ * to a potentially empty array when CGROUP_SUBSYS_COUNT == 0), this
+ * constant expression can be added.
+ */
+#define CGROUP_HAS_SUBSYS_CONFIG	(CGROUP_SUBSYS_COUNT > 0)
+
 enum css_task_iter_flags {
 	CSS_TASK_ITER_PROCS    = (1U << 0),  /* walk only threadgroup leaders */
 	CSS_TASK_ITER_THREADED = (1U << 1),  /* walk all threaded css_sets in the domain */
@@ -76,6 +84,7 @@ enum cgroup_lifetime_events {
 extern struct file_system_type cgroup_fs_type;
 extern struct cgroup_root cgrp_dfl_root;
 extern struct css_set init_css_set;
+extern struct mutex cgroup_mutex;
 extern spinlock_t css_set_lock;
 extern struct blocking_notifier_head cgroup_lifetime_notifier;
 
@@ -103,6 +112,8 @@ extern struct blocking_notifier_head cgroup_lifetime_notifier;
 #define cgroup_subsys_on_dfl(ss)						\
 	static_branch_likely(&ss ## _on_dfl_key)
 
+bool cgroup_on_dfl(const struct cgroup *cgrp);
+
 bool css_has_online_children(struct cgroup_subsys_state *css);
 struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss);
 struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup,
@@ -274,6 +285,32 @@ void css_task_iter_end(struct css_task_iter *it);
 	for ((pos) = css_next_descendant_post(NULL, (css)); (pos);	\
 	     (pos) = css_next_descendant_post((pos), (css)))
 
+/* iterate over child cgrps, lock should be held throughout iteration */
+#define cgroup_for_each_live_child(child, cgrp)				\
+	list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \
+		if (({ lockdep_assert_held(&cgroup_mutex);		\
+		       cgroup_is_dead(child); }))			\
+			;						\
+		else
+
+/* walk live descendants in pre order */
+#define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp)		\
+	css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL))	\
+		if (({ lockdep_assert_held(&cgroup_mutex);		\
+		       (dsct) = (d_css)->cgroup;			\
+		       cgroup_is_dead(dsct); }))			\
+			;						\
+		else
+
+/* walk live descendants in postorder */
+#define cgroup_for_each_live_descendant_post(dsct, d_css, cgrp)		\
+	css_for_each_descendant_post((d_css), cgroup_css((cgrp), NULL))	\
+		if (({ lockdep_assert_held(&cgroup_mutex);		\
+		       (dsct) = (d_css)->cgroup;			\
+		       cgroup_is_dead(dsct); }))			\
+			;						\
+		else
+
 /**
  * cgroup_taskset_for_each - iterate cgroup_taskset
  * @task: the loop cursor
@@ -336,6 +373,27 @@ static inline u64 cgroup_id(const struct cgroup *cgrp)
 	return cgrp->kn->id;
 }
 
+/**
+ * cgroup_css - obtain a cgroup's css for the specified subsystem
+ * @cgrp: the cgroup of interest
+ * @ss: the subsystem of interest (%NULL returns @cgrp->self)
+ *
+ * Return @cgrp's css (cgroup_subsys_state) associated with @ss.  This
+ * function must be called either under cgroup_mutex or rcu_read_lock() and
+ * the caller is responsible for pinning the returned css if it wants to
+ * keep accessing it outside the said locks.  This function may return
+ * %NULL if @cgrp doesn't have @subsys_id enabled.
+ */
+static inline struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
+						     struct cgroup_subsys *ss)
+{
+	if (CGROUP_HAS_SUBSYS_CONFIG && ss)
+		return rcu_dereference_check(cgrp->subsys[ss->id],
+					lockdep_is_held(&cgroup_mutex));
+	else
+		return &cgrp->self;
+}
+
 /**
  * css_is_dying - test whether the specified css is dying
  * @css: target css
@@ -372,6 +430,11 @@ static inline bool css_is_self(struct cgroup_subsys_state *css)
 	return false;
 }
 
+static inline bool cgroup_is_dead(const struct cgroup *cgrp)
+{
+	return !(cgrp->self.flags & CSS_ONLINE);
+}
+
 static inline void cgroup_get(struct cgroup *cgrp)
 {
 	css_get(&cgrp->self);
@@ -387,8 +450,6 @@ 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);

kernel/cgroup/cgroup-internal.h

@@ -184,11 +184,6 @@ extern bool cgrp_dfl_visible;
 	for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT &&		\
 	     (((ss) = cgroup_subsys[ssid]) || true); (ssid)++)
 
-static inline bool cgroup_is_dead(const struct cgroup *cgrp)
-{
-	return !(cgrp->self.flags & CSS_ONLINE);
-}
-
 static inline bool notify_on_release(const struct cgroup *cgrp)
 {
 	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
@@ -222,7 +217,6 @@ static inline void get_css_set(struct css_set *cset)
 }
 
 bool cgroup_ssid_enabled(int ssid);
-bool cgroup_on_dfl(const struct cgroup *cgrp);
 
 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.c

@@ -68,14 +68,6 @@
 /* let's not notify more than 100 times per second */
 #define CGROUP_FILE_NOTIFY_MIN_INTV	DIV_ROUND_UP(HZ, 100)
 
-/*
- * To avoid confusing the compiler (and generating warnings) with code
- * that attempts to access what would be a 0-element array (i.e. sized
- * to a potentially empty array when CGROUP_SUBSYS_COUNT == 0), this
- * constant expression can be added.
- */
-#define CGROUP_HAS_SUBSYS_CONFIG	(CGROUP_SUBSYS_COUNT > 0)
-
 /*
  * cgroup_mutex is the master lock.  Any modification to cgroup or its
  * hierarchy must be performed while holding it.
@@ -107,12 +99,6 @@ static bool cgroup_debug __read_mostly;
  */
 static DEFINE_SPINLOCK(cgroup_idr_lock);
 
-/*
- * Protects cgroup_file->kn for !self csses.  It synchronizes notifications
- * against file removal/re-creation across css hiding.
- */
-static DEFINE_SPINLOCK(cgroup_file_kn_lock);
-
 DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem);
 
 #define cgroup_assert_mutex_or_rcu_locked()				\
@@ -509,27 +495,6 @@ static u32 cgroup_ss_mask(struct cgroup *cgrp)
 	return cgrp->root->subsys_mask;
 }
 
-/**
- * cgroup_css - obtain a cgroup's css for the specified subsystem
- * @cgrp: the cgroup of interest
- * @ss: the subsystem of interest (%NULL returns @cgrp->self)
- *
- * Return @cgrp's css (cgroup_subsys_state) associated with @ss.  This
- * function must be called either under cgroup_mutex or rcu_read_lock() and
- * the caller is responsible for pinning the returned css if it wants to
- * keep accessing it outside the said locks.  This function may return
- * %NULL if @cgrp doesn't have @subsys_id enabled.
- */
-static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
-					      struct cgroup_subsys *ss)
-{
-	if (CGROUP_HAS_SUBSYS_CONFIG && ss)
-		return rcu_dereference_check(cgrp->subsys[ss->id],
-					lockdep_is_held(&cgroup_mutex));
-	else
-		return &cgrp->self;
-}
-
 /**
  * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss
  * @cgrp: the cgroup of interest
@@ -741,32 +706,6 @@ EXPORT_SYMBOL_GPL(of_css);
 	}								\
 } while (false)
 
-/* iterate over child cgrps, lock should be held throughout iteration */
-#define cgroup_for_each_live_child(child, cgrp)				\
-	list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \
-		if (({ lockdep_assert_held(&cgroup_mutex);		\
-		       cgroup_is_dead(child); }))			\
-			;						\
-		else
-
-/* walk live descendants in pre order */
-#define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp)		\
-	css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL))	\
-		if (({ lockdep_assert_held(&cgroup_mutex);		\
-		       (dsct) = (d_css)->cgroup;			\
-		       cgroup_is_dead(dsct); }))			\
-			;						\
-		else
-
-/* walk live descendants in postorder */
-#define cgroup_for_each_live_descendant_post(dsct, d_css, cgrp)		\
-	css_for_each_descendant_post((d_css), cgroup_css((cgrp), NULL))	\
-		if (({ lockdep_assert_held(&cgroup_mutex);		\
-		       (dsct) = (d_css)->cgroup;			\
-		       cgroup_is_dead(dsct); }))			\
-			;						\
-		else
-
 /*
  * The default css_set - used by init and its children prior to any
  * hierarchies being mounted. It contains a pointer to the root state
@@ -1748,9 +1687,9 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
 		struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss);
 		struct cgroup_file *cfile = (void *)css + cft->file_offset;
 
-		spin_lock_irq(&cgroup_file_kn_lock);
-		cfile->kn = NULL;
-		spin_unlock_irq(&cgroup_file_kn_lock);
+		spin_lock_irq(&cfile->lock);
+		WRITE_ONCE(cfile->kn, NULL);
+		spin_unlock_irq(&cfile->lock);
 
 		timer_delete_sync(&cfile->notify_timer);
 	}
@@ -4429,10 +4368,8 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
 		struct cgroup_file *cfile = (void *)css + cft->file_offset;
 
 		timer_setup(&cfile->notify_timer, cgroup_file_notify_timer, 0);
-
-		spin_lock_irq(&cgroup_file_kn_lock);
+		spin_lock_init(&cfile->lock);
 		cfile->kn = kn;
-		spin_unlock_irq(&cgroup_file_kn_lock);
 	}
 
 	return 0;
@@ -4687,21 +4624,32 @@ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
  */
 void cgroup_file_notify(struct cgroup_file *cfile)
 {
-	unsigned long flags;
+	unsigned long flags, last, next;
+	struct kernfs_node *kn = NULL;
 
-	spin_lock_irqsave(&cgroup_file_kn_lock, flags);
+	if (!READ_ONCE(cfile->kn))
+		return;
+
+	last = READ_ONCE(cfile->notified_at);
+	next = last + CGROUP_FILE_NOTIFY_MIN_INTV;
+	if (time_in_range(jiffies, last, next)) {
+		timer_reduce(&cfile->notify_timer, next);
+		if (timer_pending(&cfile->notify_timer))
+			return;
+	}
+
+	spin_lock_irqsave(&cfile->lock, flags);
 	if (cfile->kn) {
-		unsigned long last = cfile->notified_at;
-		unsigned long next = last + CGROUP_FILE_NOTIFY_MIN_INTV;
+		kn = cfile->kn;
+		kernfs_get(kn);
+		WRITE_ONCE(cfile->notified_at, jiffies);
+	}
+	spin_unlock_irqrestore(&cfile->lock, flags);
 
-		if (time_in_range(jiffies, last, next)) {
-			timer_reduce(&cfile->notify_timer, next);
-		} else {
-			kernfs_notify(cfile->kn);
-			cfile->notified_at = jiffies;
-		}
+	if (kn) {
+		kernfs_notify(kn);
+		kernfs_put(kn);
 	}
-	spin_unlock_irqrestore(&cgroup_file_kn_lock, flags);
 }
 EXPORT_SYMBOL_GPL(cgroup_file_notify);
 
@@ -4714,10 +4662,10 @@ void cgroup_file_show(struct cgroup_file *cfile, bool show)
 {
 	struct kernfs_node *kn;
 
-	spin_lock_irq(&cgroup_file_kn_lock);
+	spin_lock_irq(&cfile->lock);
 	kn = cfile->kn;
 	kernfs_get(kn);
-	spin_unlock_irq(&cgroup_file_kn_lock);
+	spin_unlock_irq(&cfile->lock);
 
 	if (kn)
 		kernfs_show(kn, show);

kernel/cgroup/dmem.c

@@ -707,8 +707,7 @@ static int dmem_cgroup_region_capacity_show(struct seq_file *sf, void *v)
 	return 0;
 }
 
-static int dmemcg_parse_limit(char *options, struct dmem_cgroup_region *region,
-			      u64 *new_limit)
+static int dmemcg_parse_limit(char *options, u64 *new_limit)
 {
 	char *end;
 
@@ -762,7 +761,7 @@ static ssize_t dmemcg_limit_write(struct kernfs_open_file *of,
 		if (!region)
 			return -EINVAL;
 
-		err = dmemcg_parse_limit(options, region, &new_limit);
+		err = dmemcg_parse_limit(options, &new_limit);
 		if (err < 0)
 			goto out_put;
 

kernel/cgroup/rdma.c

@@ -173,7 +173,7 @@ uncharge_cg_locked(struct rdma_cgroup *cg,
 	 * the system.
 	 */
 	if (unlikely(!rpool)) {
-		pr_warn("Invalid device %p or rdma cgroup %p\n", cg, device);
+		pr_warn("Invalid device %p or rdma cgroup %p\n", device, cg);
 		return;
 	}