sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem
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>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 1b8c938..7d83d7f 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -461,8 +461,31 @@
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 696d223..0cc0bbf 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),
@@ -56,7 +49,6 @@
}, \
.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 5ee2900..add524a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -743,18 +743,6 @@
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 */