Skip to contentSkip to conversation

Patch "Revert "sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem"" has been added to the 4.2-stable tree

PATCH [email protected] 1 participant 1 message Oct 13, 2015

Subsystems (5)
lore
Share & tools
lore

[email protected]

author maintainer Applied
#0 lore raw

This is a note to let you know that I've just added the patch titled

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

to the 4.2-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
revert-sched-cgroup-replace-signal_struct-group_rwsem-with-a-global-percpu_rwsem.patch
and it can be found in the queue-4.2 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree, please let <[email protected]> know about it.

Quoted 1 line

From 0c986253b939cc14c69d4adbe2b4121bdf4aa220 Mon Sep 17 00:00:00 2001

From: Tejun Heo <[email protected]>
Date: Wed, 16 Sep 2015 11:51:12 -0400
Subject: Revert "sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem"

From: Tejun Heo <[email protected]>

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.

---
 include/linux/cgroup-defs.h |   27 +--------------
 include/linux/init_task.h   |    8 ++++
 include/linux/sched.h       |   12 ++++++
 kernel/cgroup.c             |   77 ++++++++++++++++++++++++++++++++------------
 kernel/fork.c               |    4 ++
 5 files changed, 83 insertions(+), 45 deletions(-)
include/linux/cgroup-defs.h +2 -25
@@ -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 */
 
include/linux/init_task.h +8 -0
@@ -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;
include/linux/sched.h +12 -0
@@ -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 */
kernel/cgroup.c +57 -20

157 lines not on this page · raw message

kernel/fork.c +4 -0
@@ -1146,6 +1146,10 @@ static int copy_signal(unsigned long clo
 	tty_audit_fork(sig);
 	sched_autogroup_fork(sig);
 
+#ifdef CONFIG_CGROUPS
+	init_rwsem(&sig->group_rwsem);
+#endif
+
 	sig->oom_score_adj = current->signal->oom_score_adj;
 	sig->oom_score_adj_min = current->signal->oom_score_adj_min;
 

Patches currently in stable-queue which might be from [email protected] are

queue-4.2/revert-cgroup-simplify-threadgroup-locking.patch queue-4.2/revert-sched-cgroup-replace-signal_struct-group_rwsem-with-a-global-percpu_rwsem.patch queue-4.2/block-blkg_destroy_all-should-clear-q-root_blkg-and-root_rl.blkg.patch