Revert "sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem"

commit 0c986253b939cc14c69d4adbe2b4121bdf4aa220 upstream.

This reverts commit d59cfc09c32a2ae31f1c3bc2983a0cd79afb3f14.

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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 22 insertions, 25 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 93755a629299..430c876ad717 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -463,31 +463,8 @@ struct cgroup_subsys {
 	unsigned int depends_on;
 };
 
-extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
-
-/**
- * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups
- * @tsk: target task
- *
- * Called from threadgroup_change_begin() and allows cgroup operations to
- * synchronize against threadgroup changes using a percpu_rw_semaphore.
- */
-static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk)
-{
-	percpu_down_read(&cgroup_threadgroup_rwsem);
-}
-
-/**
- * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups
- * @tsk: target task
- *
- * Called from threadgroup_change_end().  Counterpart of
- * cgroup_threadcgroup_change_begin().
- */
-static inline void cgroup_threadgroup_change_end(struct task_struct *tsk)
-{
-	percpu_up_read(&cgroup_threadgroup_rwsem);
-}
+void cgroup_threadgroup_change_begin(struct task_struct *tsk);
+void cgroup_threadgroup_change_end(struct task_struct *tsk);
 
 #else	/* CONFIG_CGROUPS */
 
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index e8493fee8160..bb9b075f0eb0 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -25,6 +25,13 @@
 extern struct files_struct init_files;
 extern struct fs_struct init_fs;
 
+#ifdef CONFIG_CGROUPS
+#define INIT_GROUP_RWSEM(sig)						\
+	.group_rwsem = __RWSEM_INITIALIZER(sig.group_rwsem),
+#else
+#define INIT_GROUP_RWSEM(sig)
+#endif
+
 #ifdef CONFIG_CPUSETS
 #define INIT_CPUSET_SEQ(tsk)							\
 	.mems_allowed_seq = SEQCNT_ZERO(tsk.mems_allowed_seq),
@@ -48,6 +55,7 @@ extern struct fs_struct init_fs;
 	},								\
 	.cred_guard_mutex =						\
 		 __MUTEX_INITIALIZER(sig.cred_guard_mutex),		\
+	INIT_GROUP_RWSEM(sig)						\
 }
 
 extern struct nsproxy init_nsproxy;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 04b5ada460b4..532e0bdaa012 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -754,6 +754,18 @@ struct signal_struct {
 	unsigned audit_tty_log_passwd;
 	struct tty_audit_buf *tty_audit_buf;
 #endif
+#ifdef CONFIG_CGROUPS
+	/*
+	 * group_rwsem prevents new tasks from entering the threadgroup and
+	 * member tasks from exiting,a more specifically, setting of
+	 * PF_EXITING.  fork and exit paths are protected with this rwsem
+	 * using threadgroup_change_begin/end().  Users which require
+	 * threadgroup to remain stable should use threadgroup_[un]lock()
+	 * which also takes care of exec path.  Currently, cgroup is the
+	 * only user.
+	 */
+	struct rw_semaphore group_rwsem;
+#endif
 
 	oom_flags_t oom_flags;
 	short oom_score_adj;		/* OOM kill score adjustment */