1 files changed, 121 insertions, 71 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index f55a40db065f..4b9ff41ca603 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -207,6 +207,8 @@ static u16 have_exit_callback __read_mostly;
 static u16 have_release_callback __read_mostly;
 static u16 have_canfork_callback __read_mostly;
 
+static bool have_favordynmods __ro_after_init = IS_ENABLED(CONFIG_CGROUP_FAVOR_DYNMODS);
+
 /* cgroup namespace for init task */
 struct cgroup_namespace init_cgroup_ns = {
 	.ns.count	= REFCOUNT_INIT(2),
@@ -493,28 +495,6 @@ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
 }
 
 /**
- * cgroup_tryget_css - try to get a cgroup's css for the specified subsystem
- * @cgrp: the cgroup of interest
- * @ss: the subsystem of interest
- *
- * Find and get @cgrp's css associated with @ss.  If the css doesn't exist
- * or is offline, %NULL is returned.
- */
-static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp,
-						     struct cgroup_subsys *ss)
-{
-	struct cgroup_subsys_state *css;
-
-	rcu_read_lock();
-	css = cgroup_css(cgrp, ss);
-	if (css && !css_tryget_online(css))
-		css = NULL;
-	rcu_read_unlock();
-
-	return css;
-}
-
-/**
  * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss
  * @cgrp: the cgroup of interest
  * @ss: the subsystem of interest (%NULL returns @cgrp->self)
@@ -679,7 +659,7 @@ EXPORT_SYMBOL_GPL(of_css);
  * @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.
+ * Should be called under cgroup_mutex.
  */
 #define for_each_css(css, ssid, cgrp)					\
 	for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++)	\
@@ -929,7 +909,7 @@ static void css_set_move_task(struct task_struct *task,
 #define CSS_SET_HASH_BITS	7
 static DEFINE_HASHTABLE(css_set_table, CSS_SET_HASH_BITS);
 
-static unsigned long css_set_hash(struct cgroup_subsys_state *css[])
+static unsigned long css_set_hash(struct cgroup_subsys_state **css)
 {
 	unsigned long key = 0UL;
 	struct cgroup_subsys *ss;
@@ -1070,7 +1050,7 @@ static bool compare_css_sets(struct css_set *cset,
  */
 static struct css_set *find_existing_css_set(struct css_set *old_cset,
 					struct cgroup *cgrp,
-					struct cgroup_subsys_state *template[])
+					struct cgroup_subsys_state **template)
 {
 	struct cgroup_root *root = cgrp->root;
 	struct cgroup_subsys *ss;
@@ -1372,7 +1352,9 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 		cgroup_root_count--;
 	}
 
-	cgroup_favor_dynmods(root, false);
+	if (!have_favordynmods)
+		cgroup_favor_dynmods(root, false);
+
 	cgroup_exit_root_id(root);
 
 	cgroup_unlock();
@@ -1736,25 +1718,27 @@ static int css_populate_dir(struct cgroup_subsys_state *css)
 	struct cftype *cfts, *failed_cfts;
 	int ret;
 
-	if ((css->flags & CSS_VISIBLE) || !cgrp->kn)
+	if (css->flags & CSS_VISIBLE)
 		return 0;
 
 	if (!css->ss) {
 		if (cgroup_on_dfl(cgrp)) {
-			ret = cgroup_addrm_files(&cgrp->self, cgrp,
+			ret = cgroup_addrm_files(css, cgrp,
 						 cgroup_base_files, true);
 			if (ret < 0)
 				return ret;
 
 			if (cgroup_psi_enabled()) {
-				ret = cgroup_addrm_files(&cgrp->self, cgrp,
+				ret = cgroup_addrm_files(css, cgrp,
 							 cgroup_psi_files, true);
 				if (ret < 0)
 					return ret;
 			}
 		} else {
-			cgroup_addrm_files(css, cgrp,
-					   cgroup1_base_files, true);
+			ret = cgroup_addrm_files(css, cgrp,
+						 cgroup1_base_files, true);
+			if (ret < 0)
+				return ret;
 		}
 	} else {
 		list_for_each_entry(cfts, &css->ss->cfts, node) {
@@ -1924,6 +1908,7 @@ enum cgroup2_param {
 	Opt_favordynmods,
 	Opt_memory_localevents,
 	Opt_memory_recursiveprot,
+	Opt_memory_hugetlb_accounting,
 	nr__cgroup2_params
 };
 
@@ -1932,6 +1917,7 @@ static const struct fs_parameter_spec cgroup2_fs_parameters[] = {
 	fsparam_flag("favordynmods",		Opt_favordynmods),
 	fsparam_flag("memory_localevents",	Opt_memory_localevents),
 	fsparam_flag("memory_recursiveprot",	Opt_memory_recursiveprot),
+	fsparam_flag("memory_hugetlb_accounting", Opt_memory_hugetlb_accounting),
 	{}
 };
 
@@ -1958,6 +1944,9 @@ static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param
 	case Opt_memory_recursiveprot:
 		ctx->flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT;
 		return 0;
+	case Opt_memory_hugetlb_accounting:
+		ctx->flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
+		return 0;
 	}
 	return -EINVAL;
 }
@@ -1982,6 +1971,11 @@ static void apply_cgroup_root_flags(unsigned int root_flags)
 			cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT;
 		else
 			cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_RECURSIVE_PROT;
+
+		if (root_flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING)
+			cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
+		else
+			cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
 	}
 }
 
@@ -1995,6 +1989,8 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root
 		seq_puts(seq, ",memory_localevents");
 	if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT)
 		seq_puts(seq, ",memory_recursiveprot");
+	if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING)
+		seq_puts(seq, ",memory_hugetlb_accounting");
 	return 0;
 }
 
@@ -2265,9 +2261,9 @@ static int cgroup_init_fs_context(struct fs_context *fc)
 	fc->user_ns = get_user_ns(ctx->ns->user_ns);
 	fc->global = true;
 
-#ifdef CONFIG_CGROUP_FAVOR_DYNMODS
-	ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS;
-#endif
+	if (have_favordynmods)
+		ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS;
+
 	return 0;
 }
 
@@ -2499,7 +2495,7 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
 
 			/*
 			 * This function may be called both before and
-			 * after cgroup_taskset_migrate().  The two cases
+			 * after cgroup_migrate_execute().  The two cases
 			 * can be distinguished by looking at whether @cset
 			 * has its ->mg_dst_cset set.
 			 */
@@ -3654,9 +3650,32 @@ static int cgroup_stat_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int __maybe_unused cgroup_extra_stat_show(struct seq_file *seq,
-						 struct cgroup *cgrp, int ssid)
+#ifdef CONFIG_CGROUP_SCHED
+/**
+ * cgroup_tryget_css - try to get a cgroup's css for the specified subsystem
+ * @cgrp: the cgroup of interest
+ * @ss: the subsystem of interest
+ *
+ * Find and get @cgrp's css associated with @ss.  If the css doesn't exist
+ * or is offline, %NULL is returned.
+ */
+static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp,
+						     struct cgroup_subsys *ss)
+{
+	struct cgroup_subsys_state *css;
+
+	rcu_read_lock();
+	css = cgroup_css(cgrp, ss);
+	if (css && !css_tryget_online(css))
+		css = NULL;
+	rcu_read_unlock();
+
+	return css;
+}
+
+static int cgroup_extra_stat_show(struct seq_file *seq, int ssid)
 {
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
 	struct cgroup_subsys *ss = cgroup_subsys[ssid];
 	struct cgroup_subsys_state *css;
 	int ret;
@@ -3673,14 +3692,44 @@ static int __maybe_unused cgroup_extra_stat_show(struct seq_file *seq,
 	return ret;
 }
 
+static int cgroup_local_stat_show(struct seq_file *seq,
+				  struct cgroup *cgrp, int ssid)
+{
+	struct cgroup_subsys *ss = cgroup_subsys[ssid];
+	struct cgroup_subsys_state *css;
+	int ret;
+
+	if (!ss->css_local_stat_show)
+		return 0;
+
+	css = cgroup_tryget_css(cgrp, ss);
+	if (!css)
+		return 0;
+
+	ret = ss->css_local_stat_show(seq, css);
+	css_put(css);
+	return ret;
+}
+#endif
+
 static int cpu_stat_show(struct seq_file *seq, void *v)
 {
-	struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup;
 	int ret = 0;
 
 	cgroup_base_stat_cputime_show(seq);
 #ifdef CONFIG_CGROUP_SCHED
-	ret = cgroup_extra_stat_show(seq, cgrp, cpu_cgrp_id);
+	ret = cgroup_extra_stat_show(seq, cpu_cgrp_id);
+#endif
+	return ret;
+}
+
+static int cpu_local_stat_show(struct seq_file *seq, void *v)
+{
+	struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup;
+	int ret = 0;
+
+#ifdef CONFIG_CGROUP_SCHED
+	ret = cgroup_local_stat_show(seq, cgrp, cpu_cgrp_id);
 #endif
 	return ret;
 }
@@ -3836,14 +3885,6 @@ static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
 	return psi_trigger_poll(&ctx->psi.trigger, of->file, pt);
 }
 
-static int cgroup_pressure_open(struct kernfs_open_file *of)
-{
-	if (of->file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE))
-		return -EPERM;
-
-	return 0;
-}
-
 static void cgroup_pressure_release(struct kernfs_open_file *of)
 {
 	struct cgroup_file_ctx *ctx = of->priv;
@@ -4320,14 +4361,13 @@ static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 	return ret;
 }
 
-static int cgroup_rm_cftypes_locked(struct cftype *cfts)
+static void cgroup_rm_cftypes_locked(struct cftype *cfts)
 {
 	lockdep_assert_held(&cgroup_mutex);
 
 	list_del(&cfts->node);
 	cgroup_apply_cftypes(cfts, false);
 	cgroup_exit_cftypes(cfts);
-	return 0;
 }
 
 /**
@@ -4343,8 +4383,6 @@ static int cgroup_rm_cftypes_locked(struct cftype *cfts)
  */
 int cgroup_rm_cftypes(struct cftype *cfts)
 {
-	int ret;
-
 	if (!cfts || cfts[0].name[0] == '\0')
 		return 0;
 
@@ -4352,9 +4390,9 @@ int cgroup_rm_cftypes(struct cftype *cfts)
 		return -ENOENT;
 
 	cgroup_lock();
-	ret = cgroup_rm_cftypes_locked(cfts);
+	cgroup_rm_cftypes_locked(cfts);
 	cgroup_unlock();
-	return ret;
+	return 0;
 }
 
 /**
@@ -4889,9 +4927,11 @@ repeat:
 void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
 			 struct css_task_iter *it)
 {
+	unsigned long irqflags;
+
 	memset(it, 0, sizeof(*it));
 
-	spin_lock_irq(&css_set_lock);
+	spin_lock_irqsave(&css_set_lock, irqflags);
 
 	it->ss = css->ss;
 	it->flags = flags;
@@ -4905,7 +4945,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
 
 	css_task_iter_advance(it);
 
-	spin_unlock_irq(&css_set_lock);
+	spin_unlock_irqrestore(&css_set_lock, irqflags);
 }
 
 /**
@@ -4918,12 +4958,14 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
  */
 struct task_struct *css_task_iter_next(struct css_task_iter *it)
 {
+	unsigned long irqflags;
+
 	if (it->cur_task) {
 		put_task_struct(it->cur_task);
 		it->cur_task = NULL;
 	}
 
-	spin_lock_irq(&css_set_lock);
+	spin_lock_irqsave(&css_set_lock, irqflags);
 
 	/* @it may be half-advanced by skips, finish advancing */
 	if (it->flags & CSS_TASK_ITER_SKIPPED)
@@ -4936,7 +4978,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
 		css_task_iter_advance(it);
 	}
 
-	spin_unlock_irq(&css_set_lock);
+	spin_unlock_irqrestore(&css_set_lock, irqflags);
 
 	return it->cur_task;
 }
@@ -4949,11 +4991,13 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
  */
 void css_task_iter_end(struct css_task_iter *it)
 {
+	unsigned long irqflags;
+
 	if (it->cur_cset) {
-		spin_lock_irq(&css_set_lock);
+		spin_lock_irqsave(&css_set_lock, irqflags);
 		list_del(&it->iters_node);
 		put_css_set_locked(it->cur_cset);
-		spin_unlock_irq(&css_set_lock);
+		spin_unlock_irqrestore(&css_set_lock, irqflags);
 	}
 
 	if (it->cur_dcset)
@@ -5235,6 +5279,10 @@ static struct cftype cgroup_base_files[] = {
 		.name = "cpu.stat",
 		.seq_show = cpu_stat_show,
 	},
+	{
+		.name = "cpu.stat.local",
+		.seq_show = cpu_local_stat_show,
+	},
 	{ }	/* terminate */
 };
 
@@ -5243,7 +5291,6 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "io.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_IO]),
-		.open = cgroup_pressure_open,
 		.seq_show = cgroup_io_pressure_show,
 		.write = cgroup_io_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5252,7 +5299,6 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "memory.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]),
-		.open = cgroup_pressure_open,
 		.seq_show = cgroup_memory_pressure_show,
 		.write = cgroup_memory_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5261,7 +5307,6 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "cpu.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]),
-		.open = cgroup_pressure_open,
 		.seq_show = cgroup_cpu_pressure_show,
 		.write = cgroup_cpu_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5271,7 +5316,6 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "irq.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]),
-		.open = cgroup_pressure_open,
 		.seq_show = cgroup_irq_pressure_show,
 		.write = cgroup_irq_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5303,7 +5347,7 @@ static struct cftype cgroup_psi_files[] = {
  *    RCU callback.
  *
  * 4. After the grace period, the css can be freed.  Implemented in
- *    css_free_work_fn().
+ *    css_free_rwork_fn().
  *
  * It is actually hairier because both step 2 and 4 require process context
  * and thus involve punting to css->destroy_work adding two additional
@@ -5547,8 +5591,7 @@ err_free_css:
 
 /*
  * The returned cgroup is fully initialized including its control mask, but
- * it isn't associated with its kernfs_node and doesn't have the control
- * mask applied.
+ * it doesn't have the control mask applied.
  */
 static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 				    umode_t mode)
@@ -5874,7 +5917,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	/*
 	 * Mark @cgrp and the associated csets dead.  The former prevents
 	 * further task migration and child creation by disabling
-	 * cgroup_lock_live_group().  The latter makes the csets ignored by
+	 * cgroup_kn_lock_live().  The latter makes the csets ignored by
 	 * the migration path.
 	 */
 	cgrp->self.flags &= ~CSS_ONLINE;
@@ -5896,7 +5939,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 		parent->nr_threaded_children--;
 
 	spin_lock_irq(&css_set_lock);
-	for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) {
+	for (tcgrp = parent; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
 		tcgrp->nr_descendants--;
 		tcgrp->nr_dying_descendants++;
 		/*
@@ -6089,8 +6132,8 @@ int __init cgroup_init(void)
 			continue;
 
 		if (cgroup1_ssid_disabled(ssid))
-			printk(KERN_INFO "Disabling %s control group subsystem in v1 mounts\n",
-			       ss->name);
+			pr_info("Disabling %s control group subsystem in v1 mounts\n",
+				ss->legacy_name);
 
 		cgrp_dfl_root.subsys_mask |= 1 << ss->id;
 
@@ -6733,6 +6776,12 @@ static int __init enable_cgroup_debug(char *str)
 }
 __setup("cgroup_debug", enable_cgroup_debug);
 
+static int __init cgroup_favordynmods_setup(char *str)
+{
+	return (kstrtobool(str, &have_favordynmods) == 0);
+}
+__setup("cgroup_favordynmods=", cgroup_favordynmods_setup);
+
 /**
  * css_tryget_online_from_dir - get corresponding css from a cgroup dentry
  * @dentry: directory dentry of interest
@@ -7019,7 +7068,8 @@ static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr,
 			"nsdelegate\n"
 			"favordynmods\n"
 			"memory_localevents\n"
-			"memory_recursiveprot\n");
+			"memory_recursiveprot\n"
+			"memory_hugetlb_accounting\n");
 }
 static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features);