Merge branch 'for-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - The misc controller now reports allocation rejections through
   misc.events instead of printking

 - cgroup_mutex usage is reduced to improve scalability of some
   operations

 - vhost helper threads are now assigned to the right cgroup on cgroup2

 - Bug fixes

* 'for-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: bpf: Move wrapper for __cgroup_bpf_*() to kernel/bpf/cgroup.c
  cgroup: Fix rootcg cpu.stat guest double counting
  cgroup: no need for cgroup_mutex for /proc/cgroups
  cgroup: remove cgroup_mutex from cgroupstats_build
  cgroup: reduce dependency on cgroup_mutex
  cgroup: cgroup-v1: do not exclude cgrp_dfl_root
  cgroup: Make rebind_subsystems() disable v2 controllers all at once
  docs/cgroup: add entry for misc.events
  misc_cgroup: remove error log to avoid log flood
  misc_cgroup: introduce misc.events to count failures

8 files changed, 144 insertions, 116 deletions

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 81d37ac7132c..2aeb7ae8b393 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -2318,6 +2318,16 @@ Miscellaneous controller provides 3 interface files. If two misc resources (res_
         Limits can be set higher than the capacity value in the misc.capacity
         file.
 
+  misc.events
+	A read-only flat-keyed file which exists on non-root cgroups. The
+	following entries are defined. Unless specified otherwise, a value
+	change in this file generates a file modified event. All fields in
+	this file are hierarchical.
+
+	  max
+		The number of times the cgroup's resource usage was
+		about to go over the max boundary.
+
 Migration and Ownership
 ~~~~~~~~~~~~~~~~~~~~~~~
 
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 3536ab432b30..11820a430d6c 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -157,26 +157,6 @@ struct cgroup_bpf {
 int cgroup_bpf_inherit(struct cgroup *cgrp);
 void cgroup_bpf_offline(struct cgroup *cgrp);
 
-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 __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
-			struct bpf_cgroup_link *link,
-			enum bpf_attach_type type);
-int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
-		       union bpf_attr __user *uattr);
-
-/* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */
-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 cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
-		      enum bpf_attach_type type);
-int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
-		     union bpf_attr __user *uattr);
-
 int __cgroup_bpf_run_filter_skb(struct sock *sk,
 				struct sk_buff *skb,
 				enum cgroup_bpf_attach_type atype);
diff --git a/include/linux/misc_cgroup.h b/include/linux/misc_cgroup.h
index da2367e2ac1e..c238207d1615 100644
--- a/include/linux/misc_cgroup.h
+++ b/include/linux/misc_cgroup.h
@@ -36,7 +36,7 @@ struct misc_cg;
 struct misc_res {
 	unsigned long max;
 	atomic_long_t usage;
-	bool failed;
+	atomic_long_t events;
 };
 
 /**
@@ -46,6 +46,10 @@ struct misc_res {
  */
 struct misc_cg {
 	struct cgroup_subsys_state css;
+
+	/* misc.events */
+	struct cgroup_file events_file;
+
 	struct misc_res res[MISC_CG_RES_TYPES];
 };
 
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 03145d45e3d5..2ca643af9a54 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -430,10 +430,10 @@ static struct bpf_prog_list *find_attach_entry(struct list_head *progs,
  * Exactly one of @prog or @link can be non-null.
  * Must be called with cgroup_mutex held.
  */
-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)
+static 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)
 {
 	u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI));
 	struct bpf_prog *old_prog = NULL;
@@ -523,6 +523,20 @@ cleanup:
 	return err;
 }
 
+static 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;
+}
+
 /* Swap updated BPF program for given link in effective program arrays across
  * all descendant cgroups. This function is guaranteed to succeed.
  */
@@ -672,14 +686,14 @@ static struct bpf_prog_list *find_detach_entry(struct list_head *progs,
  *                         propagate the change to descendants
  * @cgrp: The cgroup which descendants to traverse
  * @prog: A program to detach or NULL
- * @prog: A link to detach or NULL
+ * @link: A link to detach or NULL
  * @type: Type of detach operation
  *
  * At most one of @prog or @link can be non-NULL.
  * Must be called with cgroup_mutex held.
  */
-int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
-			struct bpf_cgroup_link *link, enum bpf_attach_type type)
+static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+			       struct bpf_cgroup_link *link, enum bpf_attach_type type)
 {
 	enum cgroup_bpf_attach_type atype;
 	struct bpf_prog *old_prog;
@@ -730,9 +744,20 @@ cleanup:
 	return err;
 }
 
+static 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;
+}
+
 /* Must be called with cgroup_mutex held to avoid races. */
-int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
-		       union bpf_attr __user *uattr)
+static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+			      union bpf_attr __user *uattr)
 {
 	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
 	enum bpf_attach_type type = attr->query.attach_type;
@@ -789,6 +814,17 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 	return ret;
 }
 
+static 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;
+}
+
 int cgroup_bpf_prog_attach(const union bpf_attr *attr,
 			   enum bpf_prog_type ptype, struct bpf_prog *prog)
 {
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 35b920328344..81c9e0685948 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -63,9 +63,6 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 	for_each_root(root) {
 		struct cgroup *from_cgrp;
 
-		if (root == &cgrp_dfl_root)
-			continue;
-
 		spin_lock_irq(&css_set_lock);
 		from_cgrp = task_cgroup_from_root(from, root);
 		spin_unlock_irq(&css_set_lock);
@@ -662,11 +659,9 @@ int proc_cgroupstats_show(struct seq_file *m, void *v)
 
 	seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n");
 	/*
-	 * ideally we don't want subsystems moving around while we do this.
-	 * cgroup_mutex is also necessary to guarantee an atomic snapshot of
-	 * subsys/hierarchy state.
+	 * Grab the subsystems state racily. No need to add avenue to
+	 * cgroup_mutex contention.
 	 */
-	mutex_lock(&cgroup_mutex);
 
 	for_each_subsys(ss, i)
 		seq_printf(m, "%s\t%d\t%d\t%d\n",
@@ -674,7 +669,6 @@ int proc_cgroupstats_show(struct seq_file *m, void *v)
 			   atomic_read(&ss->root->nr_cgrps),
 			   cgroup_ssid_enabled(i));
 
-	mutex_unlock(&cgroup_mutex);
 	return 0;
 }
 
@@ -701,8 +695,6 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 	    kernfs_type(kn) != KERNFS_DIR)
 		return -EINVAL;
 
-	mutex_lock(&cgroup_mutex);
-
 	/*
 	 * We aren't being called from kernfs and there's no guarantee on
 	 * @kn->priv's validity.  For this and css_tryget_online_from_dir(),
@@ -710,9 +702,8 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 	 */
 	rcu_read_lock();
 	cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv);
-	if (!cgrp || cgroup_is_dead(cgrp)) {
+	if (!cgrp || !cgroup_tryget(cgrp)) {
 		rcu_read_unlock();
-		mutex_unlock(&cgroup_mutex);
 		return -ENOENT;
 	}
 	rcu_read_unlock();
@@ -740,7 +731,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 	}
 	css_task_iter_end(&it);
 
-	mutex_unlock(&cgroup_mutex);
+	cgroup_put(cgrp);
 	return 0;
 }
 
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index ea08f01d0111..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);
@@ -5911,17 +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;
 
-	cgrp = kn->priv;
-	if (cgroup_is_dead(cgrp) || !cgroup_tryget(cgrp))
+	rcu_read_lock();
+
+	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);
@@ -6474,30 +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);
@@ -6625,44 +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)
diff --git a/kernel/cgroup/misc.c b/kernel/cgroup/misc.c
index ec02d963cad1..fe3e8a0eb7ed 100644
--- a/kernel/cgroup/misc.c
+++ b/kernel/cgroup/misc.c
@@ -157,13 +157,6 @@ int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg,
 		new_usage = atomic_long_add_return(amount, &res->usage);
 		if (new_usage > READ_ONCE(res->max) ||
 		    new_usage > READ_ONCE(misc_res_capacity[type])) {
-			if (!res->failed) {
-				pr_info("cgroup: charge rejected by the misc controller for %s resource in ",
-					misc_res_name[type]);
-				pr_cont_cgroup_path(i->css.cgroup);
-				pr_cont("\n");
-				res->failed = true;
-			}
 			ret = -EBUSY;
 			goto err_charge;
 		}
@@ -171,6 +164,11 @@ int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg,
 	return 0;
 
 err_charge:
+	for (j = i; j; j = parent_misc(j)) {
+		atomic_long_inc(&j->res[type].events);
+		cgroup_file_notify(&j->events_file);
+	}
+
 	for (j = cg; j != i; j = parent_misc(j))
 		misc_cg_cancel_charge(type, j, amount);
 	misc_cg_cancel_charge(type, i, amount);
@@ -335,6 +333,19 @@ static int misc_cg_capacity_show(struct seq_file *sf, void *v)
 	return 0;
 }
 
+static int misc_events_show(struct seq_file *sf, void *v)
+{
+	struct misc_cg *cg = css_misc(seq_css(sf));
+	unsigned long events, i;
+
+	for (i = 0; i < MISC_CG_RES_TYPES; i++) {
+		events = atomic_long_read(&cg->res[i].events);
+		if (READ_ONCE(misc_res_capacity[i]) || events)
+			seq_printf(sf, "%s.max %lu\n", misc_res_name[i], events);
+	}
+	return 0;
+}
+
 /* Misc cgroup interface files */
 static struct cftype misc_cg_files[] = {
 	{
@@ -353,6 +364,12 @@ static struct cftype misc_cg_files[] = {
 		.seq_show = misc_cg_capacity_show,
 		.flags = CFTYPE_ONLY_ON_ROOT,
 	},
+	{
+		.name = "events",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.file_offset = offsetof(struct misc_cg, events_file),
+		.seq_show = misc_events_show,
+	},
 	{}
 };
 
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index b264ab5652ba..1486768f2318 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -433,8 +433,6 @@ static void root_cgroup_cputime(struct task_cputime *cputime)
 		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];
 	}
 }