Merge branch 'for-4.3-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:
 "The threadgroup locking changes which went in during 4.2 devel cycle
  added write locking of a percpu_rwsem in cgroup task migration path;
  unfortunately, that involved expedited rcu syncing which turned out to
  be too slow and heavy for certain workloads.  The patchset which is
  dependent on this one didn't get committed during that devel cycle, so
  these two patches can be reverted safely.

  Oleg reworked percpu_rwsem for 4.4 so that the writer path is a lot
  lighter.  The reported issue goes away with Oleg's reworked
  percpu_rwsem and I'll reapply these patches on the for-4.4 branch so
  that they can land together with Oleg's changes"

* 'for-4.3-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  Revert "sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem"
  Revert "cgroup: simplify threadgroup locking"

3 files changed, 22 insertions, 25 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 4d8fcf2187dc..8492721b39be 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -473,31 +473,8 @@ 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 d0b380ee7d67..e38681f4912d 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),
@@ -57,6 +64,7 @@ extern struct fs_struct init_fs;
 	INIT_PREV_CPUTIME(sig)						\
 	.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 a4ab9daa387c..b7b9501b41af 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -762,6 +762,18 @@ 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 */