Merge tag 'cgroup-for-6.4-rc5-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:

 - Fix css_set reference leaks on fork failures

 - Fix CPU hotplug locking in cgroup_transfer_tasks() which is used by
   cgroup1 cpuset

 - Doc update

* tag 'cgroup-for-6.4-rc5-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: Documentation: Clarify usage of memory limits
  cgroup: always put cset in cgroup_css_set_put_fork
  cgroup: fix missing cpus_read_{lock,unlock}() in cgroup_transfer_tasks()

Author: torvalds

Documentation/admin-guide/cgroup-v2.rst

@@ -1213,23 +1213,25 @@ PAGE_SIZE multiple when read back.
 	A read-write single value file which exists on non-root
 	cgroups.  The default is "max".
 
-	Memory usage throttle limit.  This is the main mechanism to
-	control memory usage of a cgroup.  If a cgroup's usage goes
+	Memory usage throttle limit.  If a cgroup's usage goes
 	over the high boundary, the processes of the cgroup are
 	throttled and put under heavy reclaim pressure.
 
 	Going over the high limit never invokes the OOM killer and
-	under extreme conditions the limit may be breached.
+	under extreme conditions the limit may be breached. The high
+	limit should be used in scenarios where an external process
+	monitors the limited cgroup to alleviate heavy reclaim
+	pressure.
 
   memory.max
 	A read-write single value file which exists on non-root
 	cgroups.  The default is "max".
 
-	Memory usage hard limit.  This is the final protection
-	mechanism.  If a cgroup's memory usage reaches this limit and
-	can't be reduced, the OOM killer is invoked in the cgroup.
-	Under certain circumstances, the usage may go over the limit
-	temporarily.
+	Memory usage hard limit.  This is the main mechanism to limit
+	memory usage of a cgroup.  If a cgroup's memory usage reaches
+	this limit and can't be reduced, the OOM killer is invoked in
+	the cgroup. Under certain circumstances, the usage may go
+	over the limit temporarily.
 
 	In default configuration regular 0-order allocations always
 	succeed unless OOM killer chooses current task as a victim.
@@ -1238,10 +1240,6 @@ PAGE_SIZE multiple when read back.
 	Caller could retry them differently, return into userspace
 	as -ENOMEM or silently ignore in cases like disk readahead.
 
-	This is the ultimate protection mechanism.  As long as the
-	high limit is used and monitored properly, this limit's
-	utility is limited to providing the final safety net.
-
   memory.reclaim
 	A write-only nested-keyed file which exists for all cgroups.
 

kernel/cgroup/cgroup-v1.c

@@ -108,7 +108,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 
 	cgroup_lock();
 
-	percpu_down_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_lock(true);
 
 	/* all tasks in @from are being moved, all csets are source */
 	spin_lock_irq(&css_set_lock);
@@ -144,7 +144,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 	} while (task && !ret);
 out_err:
 	cgroup_migrate_finish(&mgctx);
-	percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock(true);
 	cgroup_unlock();
 	return ret;
 }

kernel/cgroup/cgroup.c

@@ -6486,19 +6486,18 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 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;