1 files changed, 47 insertions, 74 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 625d7483951c..bfe3cd8ccf36 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -57,6 +57,7 @@
 #include <linux/file.h>
 #include <linux/fs_parser.h>
 #include <linux/sched/cputime.h>
+#include <linux/sched/deadline.h>
 #include <linux/psi.h>
 #include <net/sock.h>
 
@@ -312,8 +313,6 @@ bool cgroup_ssid_enabled(int ssid)
  *   masks of ancestors.
  *
  * - blkcg: blk-throttle becomes properly hierarchical.
- *
- * - debug: disallowed on the default hierarchy.
  */
 bool cgroup_on_dfl(const struct cgroup *cgrp)
 {
@@ -356,7 +355,7 @@ static bool cgroup_has_tasks(struct cgroup *cgrp)
 	return cgrp->nr_populated_csets;
 }
 
-bool cgroup_is_threaded(struct cgroup *cgrp)
+static bool cgroup_is_threaded(struct cgroup *cgrp)
 {
 	return cgrp->dom_cgrp != cgrp;
 }
@@ -395,7 +394,7 @@ static bool cgroup_can_be_thread_root(struct cgroup *cgrp)
 }
 
 /* is @cgrp root of a threaded subtree? */
-bool cgroup_is_thread_root(struct cgroup *cgrp)
+static bool cgroup_is_thread_root(struct cgroup *cgrp)
 {
 	/* thread root should be a domain */
 	if (cgroup_is_threaded(cgrp))
@@ -618,7 +617,7 @@ EXPORT_SYMBOL_GPL(cgroup_get_e_css);
 static void cgroup_get_live(struct cgroup *cgrp)
 {
 	WARN_ON_ONCE(cgroup_is_dead(cgrp));
-	css_get(&cgrp->self);
+	cgroup_get(cgrp);
 }
 
 /**
@@ -690,21 +689,6 @@ EXPORT_SYMBOL_GPL(of_css);
 		else
 
 /**
- * for_each_e_css - iterate all effective css's of a cgroup
- * @css: the iteration cursor
- * @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.
- */
-#define for_each_e_css(css, ssid, cgrp)					    \
-	for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++)	    \
-		if (!((css) = cgroup_e_css_by_mask(cgrp,		    \
-						   cgroup_subsys[(ssid)]))) \
-			;						    \
-		else
-
-/**
  * do_each_subsys_mask - filter for_each_subsys with a bitmask
  * @ss: the iteration cursor
  * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
@@ -1798,7 +1782,7 @@ 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;
+	int ssid, ret;
 	u16 dfl_disable_ss_mask = 0;
 
 	lockdep_assert_held(&cgroup_mutex);
@@ -1842,7 +1826,8 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 		struct cgroup_root *src_root = ss->root;
 		struct cgroup *scgrp = &src_root->cgrp;
 		struct cgroup_subsys_state *css = cgroup_css(scgrp, ss);
-		struct css_set *cset;
+		struct css_set *cset, *cset_pos;
+		struct css_task_iter *it;
 
 		WARN_ON(!css || cgroup_css(dcgrp, ss));
 
@@ -1860,9 +1845,22 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 		css->cgroup = dcgrp;
 
 		spin_lock_irq(&css_set_lock);
-		hash_for_each(css_set_table, i, cset, hlist)
+		WARN_ON(!list_empty(&dcgrp->e_csets[ss->id]));
+		list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id],
+					 e_cset_node[ss->id]) {
 			list_move_tail(&cset->e_cset_node[ss->id],
 				       &dcgrp->e_csets[ss->id]);
+			/*
+			 * all css_sets of scgrp together in same order to dcgrp,
+			 * patch in-flight iterators to preserve correct iteration.
+			 * since the iterator is always advanced right away and
+			 * finished when it->cset_pos meets it->cset_head, so only
+			 * update it->cset_head is enough here.
+			 */
+			list_for_each_entry(it, &cset->task_iters, iters_node)
+				if (it->cset_head == &scgrp->e_csets[ss->id])
+					it->cset_head = &dcgrp->e_csets[ss->id];
+		}
 		spin_unlock_irq(&css_set_lock);
 
 		if (ss->css_rstat_flush) {
@@ -2379,45 +2377,6 @@ int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
 EXPORT_SYMBOL_GPL(cgroup_path_ns);
 
 /**
- * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
- * @task: target task
- * @buf: the buffer to write the path into
- * @buflen: the length of the buffer
- *
- * Determine @task's cgroup on the first (the one with the lowest non-zero
- * hierarchy_id) cgroup hierarchy and copy its path into @buf.  This
- * function grabs cgroup_mutex and shouldn't be used inside locks used by
- * cgroup controller callbacks.
- *
- * Return value is the same as kernfs_path().
- */
-int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
-{
-	struct cgroup_root *root;
-	struct cgroup *cgrp;
-	int hierarchy_id = 1;
-	int ret;
-
-	cgroup_lock();
-	spin_lock_irq(&css_set_lock);
-
-	root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id);
-
-	if (root) {
-		cgrp = task_cgroup_from_root(task, root);
-		ret = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns);
-	} else {
-		/* if no hierarchy exists, everyone is in "/" */
-		ret = strscpy(buf, "/", buflen);
-	}
-
-	spin_unlock_irq(&css_set_lock);
-	cgroup_unlock();
-	return ret;
-}
-EXPORT_SYMBOL_GPL(task_cgroup_path);
-
-/**
  * cgroup_attach_lock - Lock for ->attach()
  * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem
  *
@@ -2871,9 +2830,9 @@ int cgroup_migrate(struct task_struct *leader, bool threadgroup,
 	struct task_struct *task;
 
 	/*
-	 * Prevent freeing of tasks while we take a snapshot. Tasks that are
-	 * already PF_EXITING could be freed from underneath us unless we
-	 * take an rcu_read_lock.
+	 * The following thread iteration should be inside an RCU critical
+	 * section to prevent tasks from being freed while taking the snapshot.
+	 * spin_lock_irq() implies RCU critical section here.
 	 */
 	spin_lock_irq(&css_set_lock);
 	task = leader;
@@ -3877,6 +3836,14 @@ 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;
@@ -5276,6 +5243,7 @@ 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,
@@ -5284,6 +5252,7 @@ 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,
@@ -5292,6 +5261,7 @@ 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,
@@ -5301,6 +5271,7 @@ 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,
@@ -6486,19 +6457,18 @@ err:
 static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs)
 	__releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex)
 {
+	struct cgroup *cgrp = kargs->cgrp;
+	struct css_set *cset = kargs->cset;
+
 	cgroup_threadgroup_change_end(current);
 
-	if (kargs->flags & CLONE_INTO_CGROUP) {
-		struct cgroup *cgrp = kargs->cgrp;
-		struct css_set *cset = kargs->cset;
+	if (cset) {
+		put_css_set(cset);
+		kargs->cset = NULL;
+	}
 
+	if (kargs->flags & CLONE_INTO_CGROUP) {
 		cgroup_unlock();
-
-		if (cset) {
-			put_css_set(cset);
-			kargs->cset = NULL;
-		}
-
 		if (cgrp) {
 			cgroup_put(cgrp);
 			kargs->cgrp = NULL;
@@ -6683,6 +6653,9 @@ void cgroup_exit(struct task_struct *tsk)
 	list_add_tail(&tsk->cg_list, &cset->dying_tasks);
 	cset->nr_tasks--;
 
+	if (dl_task(tsk))
+		dec_dl_tasks_cs(tsk);
+
 	WARN_ON_ONCE(cgroup_task_frozen(tsk));
 	if (unlikely(!(tsk->flags & PF_KTHREAD) &&
 		     test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags)))