Merge branch 'for-5.17-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:

 - Fix for a subtle bug in the recent release_agent permission check
   update

 - Fix for a long-standing race condition between cpuset and cpu hotplug

 - Comment updates

* 'for-5.17-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cpuset: Fix kernel-doc
  cgroup-v1: Correct privileges check in release_agent writes
  cgroup: clarify cgroup_css_set_fork()
  cgroup/cpuset: Fix a race between cpuset_attach() and cpu hotplug

3 files changed, 25 insertions, 7 deletions

diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 0e877dbcfeea..afc6c0e9c966 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -546,6 +546,7 @@ static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of,
 					  char *buf, size_t nbytes, loff_t off)
 {
 	struct cgroup *cgrp;
+	struct cgroup_file_ctx *ctx;
 
 	BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
 
@@ -553,8 +554,9 @@ static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of,
 	 * Release agent gets called with all capabilities,
 	 * require capabilities to set release agent.
 	 */
-	if ((of->file->f_cred->user_ns != &init_user_ns) ||
-	    !capable(CAP_SYS_ADMIN))
+	ctx = of->priv;
+	if ((ctx->ns->user_ns != &init_user_ns) ||
+	    !file_ns_capable(of->file, &init_user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	cgrp = cgroup_kn_lock_live(of->kn, false);
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 9d05c3ca2d5e..a557eea7166f 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6166,6 +6166,20 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 	if (ret)
 		goto err;
 
+	/*
+	 * Spawning a task directly into a cgroup works by passing a file
+	 * descriptor to the target cgroup directory. This can even be an O_PATH
+	 * file descriptor. But it can never be a cgroup.procs file descriptor.
+	 * This was done on purpose so spawning into a cgroup could be
+	 * conceptualized as an atomic
+	 *
+	 *   fd = openat(dfd_cgroup, "cgroup.procs", ...);
+	 *   write(fd, <child-pid>, ...);
+	 *
+	 * sequence, i.e. it's a shorthand for the caller opening and writing
+	 * cgroup.procs of the cgroup indicated by @dfd_cgroup. This allows us
+	 * to always use the caller's credentials.
+	 */
 	ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb,
 					!(kargs->flags & CLONE_THREAD),
 					current->nsproxy->cgroup_ns);
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 4c7254e8f49a..5de18448016c 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2289,6 +2289,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 	cgroup_taskset_first(tset, &css);
 	cs = css_cs(css);
 
+	cpus_read_lock();
 	percpu_down_write(&cpuset_rwsem);
 
 	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
@@ -2342,6 +2343,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 		wake_up(&cpuset_attach_wq);
 
 	percpu_up_write(&cpuset_rwsem);
+	cpus_read_unlock();
 }
 
 /* The various types of files and directories in a cpuset file system */
@@ -3522,8 +3524,8 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
 	return cs;
 }
 
-/**
- * cpuset_node_allowed - Can we allocate on a memory node?
+/*
+ * __cpuset_node_allowed - Can we allocate on a memory node?
  * @node: is this an allowed node?
  * @gfp_mask: memory allocation flags
  *
@@ -3694,8 +3696,8 @@ void cpuset_print_current_mems_allowed(void)
 
 int cpuset_memory_pressure_enabled __read_mostly;
 
-/**
- * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims.
+/*
+ * __cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims.
  *
  * Keep a running average of the rate of synchronous (direct)
  * page reclaim efforts initiated by tasks in each cpuset.
@@ -3710,7 +3712,7 @@ int cpuset_memory_pressure_enabled __read_mostly;
  * "memory_pressure".  Value displayed is an integer
  * representing the recent rate of entry into the synchronous
  * (direct) page reclaim by any task attached to the cpuset.
- **/
+ */
 
 void __cpuset_memory_pressure_bump(void)
 {