cgroup: Make debug controller useful for debugging

index ec47101cb1bf..3bc4196bf217 100644
@@ -166,6 +166,9 @@ struct css_set {
 	/* the default cgroup associated with this css_set */
 	struct cgroup *dfl_cgrp;
 
+	/* internal task count, protected by css_set_lock */
+	int nr_tasks;
+
 	/*
 	 * Lists running through all tasks using this cgroup group.
 	 * mg_tasks lists tasks which belong to this cset but are in the

index 85d75152402d..e9ea5f201fac 100644
@@ -334,10 +334,6 @@ static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp,
 /**
  * cgroup_task_count - count the number of tasks in a cgroup.
  * @cgrp: the cgroup in question
- *
- * Return the number of tasks in the cgroup.  The returned number can be
- * higher than the actual number of tasks due to css_set references from
- * namespace roots and temporary usages.
  */
 static int cgroup_task_count(const struct cgroup *cgrp)
 {

@@ -346,7 +342,7 @@ static int cgroup_task_count(const struct cgroup *cgrp)
 
 	spin_lock_irq(&css_set_lock);
 	list_for_each_entry(link, &cgrp->cset_links, cset_link)
-		count += refcount_read(&link->cset->refcount);
+		count += link->cset->nr_tasks;
 	spin_unlock_irq(&css_set_lock);
 	return count;
 }

index 8d4e85eae42c..dbfd7028b1c6 100644
@@ -573,6 +573,11 @@ static int css_set_count	= 1;	/* 1 for init_css_set */
 /**
  * css_set_populated - does a css_set contain any tasks?
  * @cset: target css_set
+ *
+ * css_set_populated() should be the same as !!cset->nr_tasks at steady
+ * state. However, css_set_populated() can be called while a task is being
+ * added to or removed from the linked list before the nr_tasks is
+ * properly updated. Hence, we can't just look at ->nr_tasks here.
  */
 static bool css_set_populated(struct css_set *cset)
 {

@@ -1598,6 +1603,7 @@ static void cgroup_enable_task_cg_lists(void)
 				css_set_update_populated(cset, true);
 			list_add_tail(&p->cg_list, &cset->tasks);
 			get_css_set(cset);
+			cset->nr_tasks++;
 		}
 		spin_unlock(&p->sighand->siglock);
 	} while_each_thread(g, p);

@@ -2064,8 +2070,10 @@ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx)
 			struct css_set *to_cset = cset->mg_dst_cset;
 
 			get_css_set(to_cset);
+			to_cset->nr_tasks++;
 			css_set_move_task(task, from_cset, to_cset, true);
 			put_css_set_locked(from_cset);
+			from_cset->nr_tasks--;
 		}
 	}
 	spin_unlock_irq(&css_set_lock);

@@ -4789,6 +4797,7 @@ void cgroup_post_fork(struct task_struct *child)
 		cset = task_css_set(current);
 		if (list_empty(&child->cg_list)) {
 			get_css_set(cset);
+			cset->nr_tasks++;
 			css_set_move_task(child, NULL, cset, false);
 		}
 		spin_unlock_irq(&css_set_lock);

@@ -4838,6 +4847,7 @@ void cgroup_exit(struct task_struct *tsk)
 	if (!list_empty(&tsk->cg_list)) {
 		spin_lock_irq(&css_set_lock);
 		css_set_move_task(tsk, cset, NULL, false);
+		cset->nr_tasks--;
 		spin_unlock_irq(&css_set_lock);
 	} else {
 		get_css_set(cset);

index 00f4d6bf048f..793565c05742 100644
@@ -192,6 +192,8 @@ int cgroup_rmdir(struct kernfs_node *kn);
 int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
 		     struct kernfs_root *kf_root);
 
+int cgroup_task_count(const struct cgroup *cgrp);
+
 /*
  * namespace.c
  */

158 lines not on this page · raw message

153 lines not on this page · raw message

index 1c209aa43733..cbe77a2087c5 100644
@@ -1,3 +1,9 @@
+/*
+ * Debug controller
+ *
+ * WARNING: This controller is for cgroup core debugging only.
+ * Its interfaces are unstable and subject to changes at any time.
+ */
 #include <linux/ctype.h>
 #include <linux/mm.h>
 #include <linux/slab.h>

index cbe77a2087c5..057d9b07f461 100644
@@ -36,10 +36,37 @@ static u64 debug_taskcount_read(struct cgroup_subsys_state *css,
 	return cgroup_task_count(css->cgroup);
 }
 
-static u64 current_css_set_read(struct cgroup_subsys_state *css,
-				struct cftype *cft)
+static int current_css_set_read(struct seq_file *seq, void *v)
 {
-	return (u64)(unsigned long)current->cgroups;
+	struct css_set *cset;
+	struct cgroup_subsys *ss;
+	struct cgroup_subsys_state *css;
+	int i, refcnt;
+
+	mutex_lock(&cgroup_mutex);
+	spin_lock_irq(&css_set_lock);
+	rcu_read_lock();
+	cset = rcu_dereference(current->cgroups);
+	refcnt = refcount_read(&cset->refcount);
+	seq_printf(seq, "css_set %pK %d", cset, refcnt);
+	if (refcnt > cset->nr_tasks)
+		seq_printf(seq, " +%d", refcnt - cset->nr_tasks);
+	seq_puts(seq, "\n");
+
+	/*
+	 * Print the css'es stored in the current css_set.
+	 */
+	for_each_subsys(ss, i) {
+		css = cset->subsys[ss->id];
+		if (!css)
+			continue;
+		seq_printf(seq, "%2d: %-4s\t- %lx[%d]\n", ss->id, ss->name,
+			  (unsigned long)css, css->id);
+	}
+	rcu_read_unlock();
+	spin_unlock_irq(&css_set_lock);
+	mutex_unlock(&cgroup_mutex);
+	return 0;
 }
 
 static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css,

@@ -84,31 +111,126 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
 {
 	struct cgroup_subsys_state *css = seq_css(seq);
 	struct cgrp_cset_link *link;
+	int dead_cnt = 0, extra_refs = 0;
 
 	spin_lock_irq(&css_set_lock);
 	list_for_each_entry(link, &css->cgroup->cset_links, cset_link) {
 		struct css_set *cset = link->cset;
 		struct task_struct *task;
 		int count = 0;
+		int refcnt = refcount_read(&cset->refcount);
 
-		seq_printf(seq, "css_set %pK\n", cset);
+		seq_printf(seq, " %d", refcnt);
+		if (refcnt - cset->nr_tasks > 0) {
+			int extra = refcnt - cset->nr_tasks;
+
+			seq_printf(seq, " +%d", extra);
+			/*
+			 * Take out the one additional reference in
+			 * init_css_set.
+			 */
+			if (cset == &init_css_set)
+				extra--;
+			extra_refs += extra;
+		}
+		seq_puts(seq, "\n");
 
 		list_for_each_entry(task, &cset->tasks, cg_list) {
-			if (count++ > MAX_TASKS_SHOWN_PER_CSS)
-				goto overflow;
-			seq_printf(seq, "  task %d\n", task_pid_vnr(task));
+			if (count++ <= MAX_TASKS_SHOWN_PER_CSS)
+				seq_printf(seq, "  task %d\n",
+					   task_pid_vnr(task));
 		}
 
 		list_for_each_entry(task, &cset->mg_tasks, cg_list) {
-			if (count++ > MAX_TASKS_SHOWN_PER_CSS)
-				goto overflow;
-			seq_printf(seq, "  task %d\n", task_pid_vnr(task));
+			if (count++ <= MAX_TASKS_SHOWN_PER_CSS)
+				seq_printf(seq, "  task %d\n",
+					   task_pid_vnr(task));
 		}
-		continue;
-	overflow:
-		seq_puts(seq, "  ...\n");
+		/* show # of overflowed tasks */
+		if (count > MAX_TASKS_SHOWN_PER_CSS)
+			seq_printf(seq, "  ... (%d)\n",
+				   count - MAX_TASKS_SHOWN_PER_CSS);
+
+		if (cset->dead) {
+			seq_puts(seq, "    [dead]\n");
+			dead_cnt++;
+		}
+
+		WARN_ON(count != cset->nr_tasks);
 	}
 	spin_unlock_irq(&css_set_lock);
+
+	if (!dead_cnt && !extra_refs)
+		return 0;
+
+	seq_puts(seq, "\n");
+	if (extra_refs)
+		seq_printf(seq, "extra references = %d\n", extra_refs);
+	if (dead_cnt)
+		seq_printf(seq, "dead css_sets = %d\n", dead_cnt);
+
+	return 0;
+}
+
+static int cgroup_subsys_states_read(struct seq_file *seq, void *v)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	struct cgroup_subsys *ss;
+	struct cgroup_subsys_state *css;
+	char pbuf[16];
+	int i;
+
+	mutex_lock(&cgroup_mutex);
+	for_each_subsys(ss, i) {
+		css = rcu_dereference_check(cgrp->subsys[ss->id], true);
+		if (!css)
+			continue;
+
+		pbuf[0] = '\0';
+
+		/* Show the parent CSS if applicable*/
+		if (css->parent)
+			snprintf(pbuf, sizeof(pbuf) - 1, " P=%d",
+				 css->parent->id);
+		seq_printf(seq, "%2d: %-4s\t- %lx[%d] %d%s\n", ss->id, ss->name,
+			  (unsigned long)css, css->id,
+			  atomic_read(&css->online_cnt), pbuf);
+	}
+	mutex_unlock(&cgroup_mutex);
+	return 0;
+}
+
+static int cgroup_masks_read(struct seq_file *seq, void *v)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	struct cgroup_subsys *ss;
+	int i, j;
+	struct {
+		u16  *mask;
+		char *name;
+	} mask_list[] = {
+		{ &cgrp->subtree_control,  "subtree_control"  },
+		{ &cgrp->subtree_ss_mask,  "subtree_ss_mask"  },
+	};
+
+	mutex_lock(&cgroup_mutex);
+	for (i = 0; i < ARRAY_SIZE(mask_list); i++) {
+		u16 mask = *mask_list[i].mask;
+		bool first = true;
+
+		seq_printf(seq, "%-17s: ", mask_list[i].name);
+		for_each_subsys(ss, j) {
+			if (!(mask & (1 << ss->id)))
+				continue;
+			if (!first)
+				seq_puts(seq, ", ");
+			seq_puts(seq, ss->name);
+			first = false;
+		}
+		seq_putc(seq, '\n');
+	}
+
+	mutex_unlock(&cgroup_mutex);
 	return 0;
 }
 

@@ -126,17 +248,20 @@ static struct cftype debug_files[] =  {
 
 	{
 		.name = "current_css_set",
-		.read_u64 = current_css_set_read,
+		.seq_show = current_css_set_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
 	},
 
 	{
 		.name = "current_css_set_refcount",
 		.read_u64 = current_css_set_refcount_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
 	},
 
 	{
 		.name = "current_css_set_cg_links",
 		.seq_show = current_css_set_cg_links_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
 	},
 
 	{

@@ -145,6 +270,16 @@ static struct cftype debug_files[] =  {
 	},
 
 	{
+		.name = "cgroup_subsys_states",
+		.seq_show = cgroup_subsys_states_read,
+	},
+
+	{
+		.name = "cgroup_masks",
+		.seq_show = cgroup_masks_read,
+	},
+
+	{
 		.name = "releasable",
 		.read_u64 = releasable_read,
 	},

@@ -153,7 +288,8 @@ static struct cftype debug_files[] =  {
 };
 
 struct cgroup_subsys debug_cgrp_subsys = {
-	.css_alloc = debug_css_alloc,
-	.css_free = debug_css_free,
-	.legacy_cftypes = debug_files,
+	.css_alloc	= debug_css_alloc,
+	.css_free	= debug_css_free,
+	.legacy_cftypes	= debug_files,
+	.dfl_cftypes	= debug_files,
 };

index 057d9b07f461..d61e692a5338 100644
@@ -240,7 +240,7 @@ static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft)
 		!css_has_online_children(&css->cgroup->self));
 }
 
-static struct cftype debug_files[] =  {
+static struct cftype debug_legacy_files[] =  {
 	{
 		.name = "taskcount",
 		.read_u64 = debug_taskcount_read,

@@ -287,9 +287,62 @@ static struct cftype debug_files[] =  {
 	{ }	/* terminate */
 };
 
+static struct cftype debug_files[] =  {
+	{
+		.name = "taskcount",
+		.read_u64 = debug_taskcount_read,
+	},
+
+	{
+		.name = "current_css_set",
+		.seq_show = current_css_set_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
+	{
+		.name = "current_css_set_refcount",
+		.read_u64 = current_css_set_refcount_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
+	{
+		.name = "current_css_set_cg_links",
+		.seq_show = current_css_set_cg_links_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
+	{
+		.name = "css_links",
+		.seq_show = cgroup_css_links_read,
+	},
+
+	{
+		.name = "csses",
+		.seq_show = cgroup_subsys_states_read,
+	},
+
+	{
+		.name = "masks",
+		.seq_show = cgroup_masks_read,
+	},
+
+	{ }	/* terminate */
+};
+
 struct cgroup_subsys debug_cgrp_subsys = {
 	.css_alloc	= debug_css_alloc,
 	.css_free	= debug_css_free,
-	.legacy_cftypes	= debug_files,
-	.dfl_cftypes	= debug_files,
+	.legacy_cftypes	= debug_legacy_files,
 };
+
+/*
+ * On v2, debug is an implicit controller enabled by "cgroup_debug" boot
+ * parameter.
+ */
+static int __init enable_cgroup_debug(char *str)
+{
+	debug_cgrp_subsys.dfl_cftypes = debug_files;
+	debug_cgrp_subsys.implicit_on_dfl = true;
+	return 1;
+}
+__setup("cgroup_debug", enable_cgroup_debug);

index d61e692a5338..163fdbd7adf6 100644
@@ -200,36 +200,32 @@ static int cgroup_subsys_states_read(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int cgroup_masks_read(struct seq_file *seq, void *v)
+static void cgroup_masks_read_one(struct seq_file *seq, const char *name,
+				  u16 mask)
 {
-	struct cgroup *cgrp = seq_css(seq)->cgroup;
 	struct cgroup_subsys *ss;
-	int i, j;
-	struct {
-		u16  *mask;
-		char *name;
-	} mask_list[] = {
-		{ &cgrp->subtree_control,  "subtree_control"  },
-		{ &cgrp->subtree_ss_mask,  "subtree_ss_mask"  },
-	};
+	int ssid;
+	bool first = true;
 
-	mutex_lock(&cgroup_mutex);
-	for (i = 0; i < ARRAY_SIZE(mask_list); i++) {
-		u16 mask = *mask_list[i].mask;
-		bool first = true;
-
-		seq_printf(seq, "%-17s: ", mask_list[i].name);
-		for_each_subsys(ss, j) {
-			if (!(mask & (1 << ss->id)))
-				continue;
-			if (!first)
-				seq_puts(seq, ", ");
-			seq_puts(seq, ss->name);
-			first = false;
-		}
-		seq_putc(seq, '\n');
+	seq_printf(seq, "%-17s: ", name);
+	for_each_subsys(ss, ssid) {
+		if (!(mask & (1 << ssid)))
+			continue;
+		if (!first)
+			seq_puts(seq, ", ");
+		seq_puts(seq, ss->name);
+		first = false;
 	}
+	seq_putc(seq, '\n');
+}
 
+static int cgroup_masks_read(struct seq_file *seq, void *v)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+
+	mutex_lock(&cgroup_mutex);
+	cgroup_masks_read_one(seq, "subtree_control", cgrp->subtree_control);
+	cgroup_masks_read_one(seq, "subtree_ss_mask", cgrp->subtree_ss_mask);
 	mutex_unlock(&cgroup_mutex);
 	return 0;
 }

index 163fdbd7adf6..dac46af22782 100644
@@ -38,12 +38,15 @@ static u64 debug_taskcount_read(struct cgroup_subsys_state *css,
 
 static int current_css_set_read(struct seq_file *seq, void *v)
 {
+	struct kernfs_open_file *of = seq->private;
 	struct css_set *cset;
 	struct cgroup_subsys *ss;
 	struct cgroup_subsys_state *css;
 	int i, refcnt;
 
-	mutex_lock(&cgroup_mutex);
+	if (!cgroup_kn_lock_live(of->kn, false))
+		return -ENODEV;
+
 	spin_lock_irq(&css_set_lock);
 	rcu_read_lock();
 	cset = rcu_dereference(current->cgroups);

@@ -65,7 +68,7 @@ static int current_css_set_read(struct seq_file *seq, void *v)
 	}
 	rcu_read_unlock();
 	spin_unlock_irq(&css_set_lock);
-	mutex_unlock(&cgroup_mutex);
+	cgroup_kn_unlock(of->kn);
 	return 0;
 }
 

@@ -174,13 +177,17 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
 
 static int cgroup_subsys_states_read(struct seq_file *seq, void *v)
 {
-	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	struct kernfs_open_file *of = seq->private;
+	struct cgroup *cgrp;
 	struct cgroup_subsys *ss;
 	struct cgroup_subsys_state *css;
 	char pbuf[16];
 	int i;
 
-	mutex_lock(&cgroup_mutex);
+	cgrp = cgroup_kn_lock_live(of->kn, false);
+	if (!cgrp)
+		return -ENODEV;
+
 	for_each_subsys(ss, i) {
 		css = rcu_dereference_check(cgrp->subsys[ss->id], true);
 		if (!css)

@@ -196,7 +203,8 @@ static int cgroup_subsys_states_read(struct seq_file *seq, void *v)
 			  (unsigned long)css, css->id,
 			  atomic_read(&css->online_cnt), pbuf);
 	}
-	mutex_unlock(&cgroup_mutex);
+
+	cgroup_kn_unlock(of->kn);
 	return 0;
 }
 

@@ -221,12 +229,17 @@ static void cgroup_masks_read_one(struct seq_file *seq, const char *name,
 
 static int cgroup_masks_read(struct seq_file *seq, void *v)
 {
-	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	struct kernfs_open_file *of = seq->private;
+	struct cgroup *cgrp;
+
+	cgrp = cgroup_kn_lock_live(of->kn, false);
+	if (!cgrp)
+		return -ENODEV;
 
-	mutex_lock(&cgroup_mutex);
 	cgroup_masks_read_one(seq, "subtree_control", cgrp->subtree_control);
 	cgroup_masks_read_one(seq, "subtree_ss_mask", cgrp->subtree_ss_mask);
-	mutex_unlock(&cgroup_mutex);
+
+	cgroup_kn_unlock(of->kn);
 	return 0;
 }