Revert "cgroup: simplify threadgroup locking"

This reverts commit b5ba75b5fc0e8404e2c50cb68f39bb6a53fc916f.

d59cfc09c32a ("sched, cgroup: replace signal_struct->group_rwsem with
a global percpu_rwsem") and b5ba75b5fc0e ("cgroup: simplify
threadgroup locking") changed how cgroup synchronizes against task
fork and exits so that it uses global percpu_rwsem instead of
per-process rwsem; unfortunately, the write [un]lock paths of
percpu_rwsem always involve synchronize_rcu_expedited() which turned
out to be too expensive.

Improvements for percpu_rwsem are scheduled to be merged in the coming
v4.4-rc1 merge window which alleviates this issue.  For now, revert
the two commits to restore per-process rwsem.  They will be re-applied
for the v4.4-rc1 merge window.

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/g/55F8097A.7000206@de.ibm.com
Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: stable@vger.kernel.org # v4.2+

1 files changed, 33 insertions, 12 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2cf0f79f1fc9..115091efa889 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2460,13 +2460,14 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
         if (!cgrp)
                 return -ENODEV;
 
-        percpu_down_write(&cgroup_threadgroup_rwsem);
+retry_find_task:
         rcu_read_lock();
         if (pid) {
                 tsk = find_task_by_vpid(pid);
                 if (!tsk) {
+                        rcu_read_unlock();
                         ret = -ESRCH;
-                        goto out_unlock_rcu;
+                        goto out_unlock_cgroup;
                 }
         } else {
                 tsk = current;
@@ -2482,23 +2483,37 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
          */
         if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {
                 ret = -EINVAL;
-                goto out_unlock_rcu;
+                rcu_read_unlock();
+                goto out_unlock_cgroup;
         }
 
         get_task_struct(tsk);
         rcu_read_unlock();
 
+        percpu_down_write(&cgroup_threadgroup_rwsem);
+        if (threadgroup) {
+                if (!thread_group_leader(tsk)) {
+                        /*
+                         * a race with de_thread from another thread's exec()
+                         * may strip us of our leadership, if this happens,
+                         * there is no choice but to throw this task away and
+                         * try again; this is
+                         * "double-double-toil-and-trouble-check locking".
+                         */
+                        percpu_up_write(&cgroup_threadgroup_rwsem);
+                        put_task_struct(tsk);
+                        goto retry_find_task;
+                }
+        }
+
         ret = cgroup_procs_write_permission(tsk, cgrp, of);
         if (!ret)
                 ret = cgroup_attach_task(cgrp, tsk, threadgroup);
 
-        put_task_struct(tsk);
-        goto out_unlock_threadgroup;
-
-out_unlock_rcu:
-        rcu_read_unlock();
-out_unlock_threadgroup:
         percpu_up_write(&cgroup_threadgroup_rwsem);
+
+        put_task_struct(tsk);
+out_unlock_cgroup:
         cgroup_kn_unlock(of->kn);
         return ret ?: nbytes;
 }
@@ -2643,8 +2658,6 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 
         lockdep_assert_held(&cgroup_mutex);
 
-        percpu_down_write(&cgroup_threadgroup_rwsem);
-
         /* look up all csses currently attached to @cgrp's subtree */
         down_read(&css_set_rwsem);
         css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) {
@@ -2700,8 +2713,17 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
                                 goto out_finish;
                         last_task = task;
 
+                        percpu_down_write(&cgroup_threadgroup_rwsem);
+                        /* raced against de_thread() from another thread? */
+                        if (!thread_group_leader(task)) {
+                                percpu_up_write(&cgroup_threadgroup_rwsem);
+                                put_task_struct(task);
+                                continue;
+                        }
+
                         ret = cgroup_migrate(src_cset->dfl_cgrp, task, true);
 
+                        percpu_up_write(&cgroup_threadgroup_rwsem);
                         put_task_struct(task);
 
                         if (WARN(ret, "cgroup: failed to update controllers for the default hierarchy (%d), further operations may crash or hang\n", ret))
@@ -2711,7 +2733,6 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 
 out_finish:
         cgroup_migrate_finish(&preloaded_csets);
-        percpu_up_write(&cgroup_threadgroup_rwsem);
         return ret;
 }