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

Note: This commit was originally committed as d59cfc09c32a but got
      reverted by 0c986253b939 due to the performance regression from
      the percpu_rwsem write down/up operations added to cgroup task
      migration path.  percpu_rwsem changes which alleviate the
      performance issue are pending for v4.4-rc1 merge window.
      Re-apply.

The cgroup side of threadgroup locking uses signal_struct->group_rwsem
to synchronize against threadgroup changes.  This per-process rwsem
adds small overhead to thread creation, exit and exec paths, forces
cgroup code paths to do lock-verify-unlock-retry dance in a couple
places and makes it impossible to atomically perform operations across
multiple processes.

This patch replaces signal_struct->group_rwsem with a global
percpu_rwsem cgroup_threadgroup_rwsem which is cheaper on the reader
side and contained in cgroups proper.  This patch converts one-to-one.

This does make writer side heavier and lower the granularity; however,
cgroup process migration is a fairly cold path, we do want to optimize
thread operations over it and cgroup migration operations don't take
enough time for the lower granularity to matter.

Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/g/55F8097A.7000206@de.ibm.com
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>

3 files changed, 25 insertions, 22 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 8492721b39be..4d8fcf2187dc 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -473,8 +473,31 @@ struct cgroup_subsys {
 	unsigned int depends_on;
 };
 
-void cgroup_threadgroup_change_begin(struct task_struct *tsk);
-void cgroup_threadgroup_change_end(struct task_struct *tsk);
+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);
+}
 
 #else	/* CONFIG_CGROUPS */
 
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index e38681f4912d..d0b380ee7d67 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -25,13 +25,6 @@
 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),
@@ -64,7 +57,6 @@ 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 b7b9501b41af..a4ab9daa387c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -762,18 +762,6 @@ 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 */