1 files changed, 81 insertions, 18 deletions

diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 83044312bc41..a9e029b570c8 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -10,6 +10,7 @@
 #include <linux/sched/task.h>
 #include <linux/magic.h>
 #include <linux/slab.h>
+#include <linux/string.h>
 #include <linux/vmalloc.h>
 #include <linux/delayacct.h>
 #include <linux/pid_namespace.h>
@@ -32,6 +33,9 @@ static u16 cgroup_no_v1_mask;
 /* disable named v1 mounts */
 static bool cgroup_no_v1_named;
 
+/* Show unavailable controllers in /proc/cgroups */
+static bool proc_show_all;
+
 /*
  * pidlist destructions need to be flushed on cgroup destruction.  Use a
  * separate workqueue as flush domain.
@@ -46,6 +50,12 @@ bool cgroup1_ssid_disabled(int ssid)
 	return cgroup_no_v1_mask & (1 << ssid);
 }
 
+static bool cgroup1_subsys_absent(struct cgroup_subsys *ss)
+{
+	/* Check also dfl_cftypes for file-less controllers, i.e. perf_event */
+	return ss->legacy_cftypes == NULL && ss->dfl_cftypes;
+}
+
 /**
  * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from'
  * @from: attach to all cgroups of a given task
@@ -59,7 +69,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 	int retval = 0;
 
 	cgroup_lock();
-	cgroup_attach_lock(true);
+	cgroup_attach_lock(CGRP_ATTACH_LOCK_GLOBAL, NULL);
 	for_each_root(root) {
 		struct cgroup *from_cgrp;
 
@@ -71,7 +81,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 		if (retval)
 			break;
 	}
-	cgroup_attach_unlock(true);
+	cgroup_attach_unlock(CGRP_ATTACH_LOCK_GLOBAL, NULL);
 	cgroup_unlock();
 
 	return retval;
@@ -108,7 +118,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 
 	cgroup_lock();
 
-	cgroup_attach_lock(true);
+	cgroup_attach_lock(CGRP_ATTACH_LOCK_GLOBAL, NULL);
 
 	/* all tasks in @from are being moved, all csets are source */
 	spin_lock_irq(&css_set_lock);
@@ -144,7 +154,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 	} while (task && !ret);
 out_err:
 	cgroup_migrate_finish(&mgctx);
-	cgroup_attach_unlock(true);
+	cgroup_attach_unlock(CGRP_ATTACH_LOCK_GLOBAL, NULL);
 	cgroup_unlock();
 	return ret;
 }
@@ -360,10 +370,9 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 	}
 	css_task_iter_end(&it);
 	length = n;
-	/* now sort & (if procs) strip out duplicates */
+	/* now sort & strip out duplicates (tgids or recycled thread PIDs) */
 	sort(array, length, sizeof(pid_t), cmppid, NULL);
-	if (type == CGROUP_FILE_PROCS)
-		length = pidlist_uniq(array, length);
+	length = pidlist_uniq(array, length);
 
 	l = cgroup_pidlist_find_create(cgrp, type);
 	if (!l) {
@@ -431,7 +440,7 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
 			if (l->list[mid] == pid) {
 				index = mid;
 				break;
-			} else if (l->list[mid] <= pid)
+			} else if (l->list[mid] < pid)
 				index = mid + 1;
 			else
 				end = mid;
@@ -494,13 +503,13 @@ static ssize_t __cgroup1_procs_write(struct kernfs_open_file *of,
 	struct task_struct *task;
 	const struct cred *cred, *tcred;
 	ssize_t ret;
-	bool locked;
+	enum cgroup_attach_lock_mode lock_mode;
 
 	cgrp = cgroup_kn_lock_live(of->kn, false);
 	if (!cgrp)
 		return -ENODEV;
 
-	task = cgroup_procs_write_start(buf, threadgroup, &locked);
+	task = cgroup_procs_write_start(buf, threadgroup, &lock_mode);
 	ret = PTR_ERR_OR_ZERO(task);
 	if (ret)
 		goto out_unlock;
@@ -523,7 +532,7 @@ static ssize_t __cgroup1_procs_write(struct kernfs_open_file *of,
 	ret = cgroup_attach_task(cgrp, task, threadgroup);
 
 out_finish:
-	cgroup_procs_write_finish(task, locked);
+	cgroup_procs_write_finish(task, lock_mode);
 out_unlock:
 	cgroup_kn_unlock(of->kn);
 
@@ -668,6 +677,7 @@ struct cftype cgroup1_base_files[] = {
 int proc_cgroupstats_show(struct seq_file *m, void *v)
 {
 	struct cgroup_subsys *ss;
+	bool cgrp_v1_visible = false;
 	int i;
 
 	seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n");
@@ -676,11 +686,21 @@ int proc_cgroupstats_show(struct seq_file *m, void *v)
 	 * cgroup_mutex contention.
 	 */
 
-	for_each_subsys(ss, i)
+	for_each_subsys(ss, i) {
+		cgrp_v1_visible |= ss->root != &cgrp_dfl_root;
+
+		if (!proc_show_all && cgroup1_subsys_absent(ss))
+			continue;
+
 		seq_printf(m, "%s\t%d\t%d\t%d\n",
 			   ss->legacy_name, ss->root->hierarchy_id,
 			   atomic_read(&ss->root->nr_cgrps),
 			   cgroup_ssid_enabled(i));
+	}
+
+	if (cgrp_dfl_visible && !cgrp_v1_visible)
+		pr_info_once("/proc/cgroups lists only v1 controllers, use cgroup.controllers of root cgroup for v2 info\n");
+
 
 	return 0;
 }
@@ -803,7 +823,7 @@ void cgroup1_release_agent(struct work_struct *work)
 		goto out_free;
 
 	ret = cgroup_path_ns(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns);
-	if (ret < 0 || ret >= PATH_MAX)
+	if (ret < 0)
 		goto out_free;
 
 	argv[0] = agentbuf;
@@ -836,7 +856,7 @@ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent
 
 	if (kernfs_type(kn) != KERNFS_DIR)
 		return -ENOTDIR;
-	if (kn->parent != new_parent)
+	if (rcu_access_pointer(kn->__parent) != new_parent)
 		return -EIO;
 
 	/*
@@ -933,7 +953,8 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		if (ret != -ENOPARAM)
 			return ret;
 		for_each_subsys(ss, i) {
-			if (strcmp(param->key, ss->legacy_name))
+			if (strcmp(param->key, ss->legacy_name) ||
+			    cgroup1_subsys_absent(ss))
 				continue;
 			if (!cgroup_ssid_enabled(i) || cgroup1_ssid_disabled(i))
 				return invalfc(fc, "Disabled controller '%s'",
@@ -1025,7 +1046,8 @@ static int check_cgroupfs_options(struct fs_context *fc)
 	mask = ~((u16)1 << cpuset_cgrp_id);
 #endif
 	for_each_subsys(ss, i)
-		if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i))
+		if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i) &&
+		    !cgroup1_subsys_absent(ss))
 			enabled |= 1 << i;
 
 	ctx->subsys_mask &= enabled;
@@ -1112,7 +1134,7 @@ int cgroup1_reconfigure(struct fs_context *fc)
 
 	if (ctx->release_agent) {
 		spin_lock(&release_agent_path_lock);
-		strcpy(root->release_agent_path, ctx->release_agent);
+		strscpy(root->release_agent_path, ctx->release_agent);
 		spin_unlock(&release_agent_path_lock);
 	}
 
@@ -1263,6 +1285,40 @@ int cgroup1_get_tree(struct fs_context *fc)
 	return ret;
 }
 
+/**
+ * task_get_cgroup1 - Acquires the associated cgroup of a task within a
+ * specific cgroup1 hierarchy. The cgroup1 hierarchy is identified by its
+ * hierarchy ID.
+ * @tsk: The target task
+ * @hierarchy_id: The ID of a cgroup1 hierarchy
+ *
+ * On success, the cgroup is returned. On failure, ERR_PTR is returned.
+ * We limit it to cgroup1 only.
+ */
+struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id)
+{
+	struct cgroup *cgrp = ERR_PTR(-ENOENT);
+	struct cgroup_root *root;
+	unsigned long flags;
+
+	rcu_read_lock();
+	for_each_root(root) {
+		/* cgroup1 only*/
+		if (root == &cgrp_dfl_root)
+			continue;
+		if (root->hierarchy_id != hierarchy_id)
+			continue;
+		spin_lock_irqsave(&css_set_lock, flags);
+		cgrp = task_cgroup_from_root(tsk, root);
+		if (!cgrp || !cgroup_tryget(cgrp))
+			cgrp = ERR_PTR(-ENOENT);
+		spin_unlock_irqrestore(&css_set_lock, flags);
+		break;
+	}
+	rcu_read_unlock();
+	return cgrp;
+}
+
 static int __init cgroup1_wq_init(void)
 {
 	/*
@@ -1270,7 +1326,7 @@ static int __init cgroup1_wq_init(void)
 	 * Cap @max_active to 1 too.
 	 */
 	cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy",
-						    0, 1);
+						    WQ_PERCPU, 1);
 	BUG_ON(!cgroup_pidlist_destroy_wq);
 	return 0;
 }
@@ -1302,8 +1358,15 @@ static int __init cgroup_no_v1(char *str)
 				continue;
 
 			cgroup_no_v1_mask |= 1 << i;
+			break;
 		}
 	}
 	return 1;
 }
 __setup("cgroup_no_v1=", cgroup_no_v1);
+
+static int __init cgroup_v1_proc(char *str)
+{
+	return (kstrtobool(str, &proc_show_all) == 0);
+}
+__setup("cgroup_v1_proc=", cgroup_v1_proc);