cgroup: pids: fix race between cgroup_post_fork() and cgroup_migrate()

If the new child migrates to another cgroup before cgroup_post_fork() calls
subsys->fork(), then both pids_can_attach() and pids_fork() will do the same
pids_uncharge(old_pids) + pids_charge(pids) sequence twice.

Change copy_process() to call threadgroup_change_begin/threadgroup_change_end
unconditionally. percpu_down_read() is cheap and this allows other cleanups,
see the next changes.

Also, this way we can unify cgroup_threadgroup_rwsem and dup_mmap_sem.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Zefan Li <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

2 files changed, 5 insertions, 25 deletions

diff --git a/kernel/cgroup_pids.c b/kernel/cgroup_pids.c
index cdd8df4..15ef2e4 100644
--- a/kernel/cgroup_pids.c
+++ b/kernel/cgroup_pids.c
@@ -243,27 +243,10 @@ static void pids_cancel_fork(struct task_struct *task, void *priv)
 
 static void pids_fork(struct task_struct *task, void *priv)
 {
-	struct cgroup_subsys_state *css;
-	struct cgroup_subsys_state *old_css = priv;
-	struct pids_cgroup *pids;
-	struct pids_cgroup *old_pids = css_pids(old_css);
-
-	css = task_get_css(task, pids_cgrp_id);
-	pids = css_pids(css);
-
-	/*
-	 * If the association has changed, we have to revert and reapply the
-	 * charge/uncharge on the wrong hierarchy to the current one. Since
-	 * the association can only change due to an organisation event, its
-	 * okay for us to ignore the limit in this case.
-	 */
-	if (pids != old_pids) {
-		pids_uncharge(old_pids, 1);
-		pids_charge(pids, 1);
-	}
+	struct cgroup_subsys_state *css = priv;
 
+	WARN_ON(task_css_check(task, pids_cgrp_id, true) != css);
 	css_put(css);
-	css_put(old_css);
 }
 
 static void pids_free(struct task_struct *task)
diff --git a/kernel/fork.c b/kernel/fork.c
index f97f2c4..fce002e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1368,8 +1368,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->real_start_time = ktime_get_boot_ns();
 	p->io_context = NULL;
 	p->audit_context = NULL;
-	if (clone_flags & CLONE_THREAD)
-		threadgroup_change_begin(current);
+	threadgroup_change_begin(current);
 	cgroup_fork(p);
 #ifdef CONFIG_NUMA
 	p->mempolicy = mpol_dup(p->mempolicy);
@@ -1610,8 +1609,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	proc_fork_connector(p);
 	cgroup_post_fork(p, cgrp_ss_priv);
-	if (clone_flags & CLONE_THREAD)
-		threadgroup_change_end(current);
+	threadgroup_change_end(current);
 	perf_event_fork(p);
 
 	trace_task_newtask(p, clone_flags);
@@ -1652,8 +1650,7 @@ bad_fork_cleanup_policy:
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_threadgroup_lock:
 #endif
-	if (clone_flags & CLONE_THREAD)
-		threadgroup_change_end(current);
+	threadgroup_change_end(current);
 	delayacct_tsk_free(p);
 bad_fork_cleanup_count:
 	atomic_dec(&p->cred->user->processes);