1 files changed, 118 insertions, 43 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 4c1cf0969a80..eef24a25bda7 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -55,6 +55,7 @@
 #include <linux/nsproxy.h>
 #include <linux/file.h>
 #include <linux/sched/cputime.h>
+#include <linux/psi.h>
 #include <net/sock.h>
 
 #define CREATE_TRACE_POINTS
@@ -85,6 +86,7 @@ EXPORT_SYMBOL_GPL(css_set_lock);
 
 DEFINE_SPINLOCK(trace_cgroup_path_lock);
 char trace_cgroup_path[TRACE_CGROUP_PATH_LEN];
+bool cgroup_debug __read_mostly;
 
 /*
  * Protects cgroup_idr and css_idr so that IDs can be released without
@@ -195,7 +197,7 @@ static u64 css_serial_nr_next = 1;
  */
 static u16 have_fork_callback __read_mostly;
 static u16 have_exit_callback __read_mostly;
-static u16 have_free_callback __read_mostly;
+static u16 have_release_callback __read_mostly;
 static u16 have_canfork_callback __read_mostly;
 
 /* cgroup namespace for init task */
@@ -862,7 +864,7 @@ static void css_set_move_task(struct task_struct *task,
 		 */
 		WARN_ON_ONCE(task->flags & PF_EXITING);
 
-		rcu_assign_pointer(task->cgroups, to_cset);
+		cgroup_move_task(task, to_cset);
 		list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks :
 							     &to_cset->tasks);
 	}
@@ -1428,12 +1430,15 @@ static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
 	struct cgroup_subsys *ss = cft->ss;
 
 	if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) &&
-	    !(cgrp->root->flags & CGRP_ROOT_NOPREFIX))
-		snprintf(buf, CGROUP_FILE_NAME_MAX, "%s.%s",
-			 cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name,
+	    !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) {
+		const char *dbg = (cft->flags & CFTYPE_DEBUG) ? ".__DEBUG__." : "";
+
+		snprintf(buf, CGROUP_FILE_NAME_MAX, "%s%s.%s",
+			 dbg, cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name,
 			 cft->name);
-	else
+	} else {
 		strscpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
+	}
 	return buf;
 }
 
@@ -1773,7 +1778,7 @@ static int parse_cgroup_root_flags(char *data, unsigned int *root_flags)
 
 	*root_flags = 0;
 
-	if (!data)
+	if (!data || *data == '\0')
 		return 0;
 
 	while ((token = strsep(&data, ",")) != NULL) {
@@ -1922,7 +1927,7 @@ void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts)
 		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
 }
 
-int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags)
+int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 {
 	LIST_HEAD(tmp_links);
 	struct cgroup *root_cgrp = &root->cgrp;
@@ -1939,7 +1944,7 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags)
 	root_cgrp->ancestor_ids[0] = ret;
 
 	ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release,
-			      ref_flags, GFP_KERNEL);
+			      0, GFP_KERNEL);
 	if (ret)
 		goto out;
 
@@ -2028,7 +2033,7 @@ struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
 			       struct cgroup_namespace *ns)
 {
 	struct dentry *dentry;
-	bool new_sb;
+	bool new_sb = false;
 
 	dentry = kernfs_mount(fs_type, flags, root->kf_root, magic, &new_sb);
 
@@ -2038,6 +2043,7 @@ struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
 	 */
 	if (!IS_ERR(dentry) && ns != &init_cgroup_ns) {
 		struct dentry *nsdentry;
+		struct super_block *sb = dentry->d_sb;
 		struct cgroup *cgrp;
 
 		mutex_lock(&cgroup_mutex);
@@ -2048,12 +2054,14 @@ struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
 		spin_unlock_irq(&css_set_lock);
 		mutex_unlock(&cgroup_mutex);
 
-		nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb);
+		nsdentry = kernfs_node_dentry(cgrp->kn, sb);
 		dput(dentry);
+		if (IS_ERR(nsdentry))
+			deactivate_locked_super(sb);
 		dentry = nsdentry;
 	}
 
-	if (IS_ERR(dentry) || !new_sb)
+	if (!new_sb)
 		cgroup_put(&root->cgrp);
 
 	return dentry;
@@ -2113,18 +2121,16 @@ static void cgroup_kill_sb(struct super_block *sb)
 	struct cgroup_root *root = cgroup_root_from_kf(kf_root);
 
 	/*
-	 * If @root doesn't have any mounts or children, start killing it.
+	 * If @root doesn't have any children, start killing it.
 	 * This prevents new mounts by disabling percpu_ref_tryget_live().
 	 * cgroup_mount() may wait for @root's release.
 	 *
 	 * And don't kill the default root.
 	 */
-	if (!list_empty(&root->cgrp.self.children) ||
-	    root == &cgrp_dfl_root)
-		cgroup_put(&root->cgrp);
-	else
+	if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root &&
+	    !percpu_ref_is_dying(&root->cgrp.self.refcnt))
 		percpu_ref_kill(&root->cgrp.self.refcnt);
-
+	cgroup_put(&root->cgrp);
 	kernfs_kill_sb(sb);
 }
 
@@ -3446,6 +3452,21 @@ static int cpu_stat_show(struct seq_file *seq, void *v)
 	return ret;
 }
 
+#ifdef CONFIG_PSI
+static int cgroup_io_pressure_show(struct seq_file *seq, void *v)
+{
+	return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_IO);
+}
+static int cgroup_memory_pressure_show(struct seq_file *seq, void *v)
+{
+	return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_MEM);
+}
+static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
+{
+	return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_CPU);
+}
+#endif
+
 static int cgroup_file_open(struct kernfs_open_file *of)
 {
 	struct cftype *cft = of->kn->priv;
@@ -3513,6 +3534,16 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 	return ret ?: nbytes;
 }
 
+static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt)
+{
+	struct cftype *cft = of->kn->priv;
+
+	if (cft->poll)
+		return cft->poll(of, pt);
+
+	return kernfs_generic_poll(of, pt);
+}
+
 static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos)
 {
 	return seq_cft(seq)->seq_start(seq, ppos);
@@ -3551,6 +3582,7 @@ static struct kernfs_ops cgroup_kf_single_ops = {
 	.open			= cgroup_file_open,
 	.release		= cgroup_file_release,
 	.write			= cgroup_file_write,
+	.poll			= cgroup_file_poll,
 	.seq_show		= cgroup_seqfile_show,
 };
 
@@ -3559,6 +3591,7 @@ static struct kernfs_ops cgroup_kf_ops = {
 	.open			= cgroup_file_open,
 	.release		= cgroup_file_release,
 	.write			= cgroup_file_write,
+	.poll			= cgroup_file_poll,
 	.seq_start		= cgroup_seqfile_start,
 	.seq_next		= cgroup_seqfile_next,
 	.seq_stop		= cgroup_seqfile_stop,
@@ -3653,7 +3686,8 @@ restart:
 			continue;
 		if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgroup_parent(cgrp))
 			continue;
-
+		if ((cft->flags & CFTYPE_DEBUG) && !cgroup_debug)
+			continue;
 		if (is_add) {
 			ret = cgroup_add_file(css, cgrp, cft);
 			if (ret) {
@@ -4216,20 +4250,25 @@ static void css_task_iter_advance(struct css_task_iter *it)
 
 	lockdep_assert_held(&css_set_lock);
 repeat:
-	/*
-	 * Advance iterator to find next entry.  cset->tasks is consumed
-	 * first and then ->mg_tasks.  After ->mg_tasks, we move onto the
-	 * next cset.
-	 */
-	next = it->task_pos->next;
+	if (it->task_pos) {
+		/*
+		 * Advance iterator to find next entry.  cset->tasks is
+		 * consumed first and then ->mg_tasks.  After ->mg_tasks,
+		 * we move onto the next cset.
+		 */
+		next = it->task_pos->next;
 
-	if (next == it->tasks_head)
-		next = it->mg_tasks_head->next;
+		if (next == it->tasks_head)
+			next = it->mg_tasks_head->next;
 
-	if (next == it->mg_tasks_head)
+		if (next == it->mg_tasks_head)
+			css_task_iter_advance_css_set(it);
+		else
+			it->task_pos = next;
+	} else {
+		/* called from start, proceed to the first cset */
 		css_task_iter_advance_css_set(it);
-	else
-		it->task_pos = next;
+	}
 
 	/* if PROCS, skip over tasks which aren't group leaders */
 	if ((it->flags & CSS_TASK_ITER_PROCS) && it->task_pos &&
@@ -4269,7 +4308,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
 
 	it->cset_head = it->cset_pos;
 
-	css_task_iter_advance_css_set(it);
+	css_task_iter_advance(it);
 
 	spin_unlock_irq(&css_set_lock);
 }
@@ -4576,6 +4615,23 @@ static struct cftype cgroup_base_files[] = {
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = cpu_stat_show,
 	},
+#ifdef CONFIG_PSI
+	{
+		.name = "io.pressure",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = cgroup_io_pressure_show,
+	},
+	{
+		.name = "memory.pressure",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = cgroup_memory_pressure_show,
+	},
+	{
+		.name = "cpu.pressure",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = cgroup_cpu_pressure_show,
+	},
+#endif
 	{ }	/* terminate */
 };
 
@@ -4636,6 +4692,7 @@ static void css_free_rwork_fn(struct work_struct *work)
 			 */
 			cgroup_put(cgroup_parent(cgrp));
 			kernfs_put(cgrp->kn);
+			psi_cgroup_free(cgrp);
 			if (cgroup_on_dfl(cgrp))
 				cgroup_rstat_exit(cgrp);
 			kfree(cgrp);
@@ -4892,10 +4949,15 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 	cgrp->self.parent = &parent->self;
 	cgrp->root = root;
 	cgrp->level = level;
-	ret = cgroup_bpf_inherit(cgrp);
+
+	ret = psi_cgroup_alloc(cgrp);
 	if (ret)
 		goto out_idr_free;
 
+	ret = cgroup_bpf_inherit(cgrp);
+	if (ret)
+		goto out_psi_free;
+
 	for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
 		cgrp->ancestor_ids[tcgrp->level] = tcgrp->id;
 
@@ -4933,6 +4995,8 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 
 	return cgrp;
 
+out_psi_free:
+	psi_cgroup_free(cgrp);
 out_idr_free:
 	cgroup_idr_remove(&root->cgroup_idr, cgrp->id);
 out_stat_exit:
@@ -5262,7 +5326,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
 
 	have_fork_callback |= (bool)ss->fork << ss->id;
 	have_exit_callback |= (bool)ss->exit << ss->id;
-	have_free_callback |= (bool)ss->free << ss->id;
+	have_release_callback |= (bool)ss->release << ss->id;
 	have_canfork_callback |= (bool)ss->can_fork << ss->id;
 
 	/* At system boot, before all subsystems have been
@@ -5332,7 +5396,7 @@ int __init cgroup_init(void)
 	cgroup_rstat_boot();
 
 	/*
-	 * The latency of the synchronize_sched() is too high for cgroups,
+	 * The latency of the synchronize_rcu() is too high for cgroups,
 	 * avoid it at the cost of forcing all readers into the slow path.
 	 */
 	rcu_sync_enter_start(&cgroup_threadgroup_rwsem.rss);
@@ -5348,7 +5412,7 @@ int __init cgroup_init(void)
 	hash_add(css_set_table, &init_css_set.hlist,
 		 css_set_hash(init_css_set.subsys));
 
-	BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0, 0));
+	BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
 
 	mutex_unlock(&cgroup_mutex);
 
@@ -5698,16 +5762,19 @@ void cgroup_exit(struct task_struct *tsk)
 	} while_each_subsys_mask();
 }
 
-void cgroup_free(struct task_struct *task)
+void cgroup_release(struct task_struct *task)
 {
-	struct css_set *cset = task_css_set(task);
 	struct cgroup_subsys *ss;
 	int ssid;
 
-	do_each_subsys_mask(ss, ssid, have_free_callback) {
-		ss->free(task);
+	do_each_subsys_mask(ss, ssid, have_release_callback) {
+		ss->release(task);
 	} while_each_subsys_mask();
+}
 
+void cgroup_free(struct task_struct *task)
+{
+	struct css_set *cset = task_css_set(task);
 	put_css_set(cset);
 }
 
@@ -5732,6 +5799,16 @@ static int __init cgroup_disable(char *str)
 }
 __setup("cgroup_disable=", cgroup_disable);
 
+void __init __weak enable_debug_cgroup(void) { }
+
+static int __init enable_cgroup_debug(char *str)
+{
+	cgroup_debug = true;
+	enable_debug_cgroup();
+	return 1;
+}
+__setup("cgroup_debug", enable_cgroup_debug);
+
 /**
  * css_tryget_online_from_dir - get corresponding css from a cgroup dentry
  * @dentry: directory dentry of interest
@@ -5935,7 +6012,7 @@ int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 	int ret;
 
 	mutex_lock(&cgroup_mutex);
-	ret = __cgroup_bpf_detach(cgrp, prog, type, flags);
+	ret = __cgroup_bpf_detach(cgrp, prog, type);
 	mutex_unlock(&cgroup_mutex);
 	return ret;
 }
@@ -5967,10 +6044,8 @@ static ssize_t show_delegatable_files(struct cftype *files, char *buf,
 
 		ret += snprintf(buf + ret, size - ret, "%s\n", cft->name);
 
-		if (unlikely(ret >= size)) {
-			WARN_ON(1);
+		if (WARN_ON(ret >= size))
 			break;
-		}
 	}
 
 	return ret;