[PATCH v4 1/2] cgroups: read-write lock CLONE_THREAD forking per threadgroup

[Ben Blum <bblum-OM76b2Iv3yLQjUSlxSEPGw@public.gmane.org>]

[-- Attachment #1: cgroup-threadgroup-fork-lock.patch --]
[-- Type: text/plain, Size: 3737 bytes --]

Adds functionality to read/write lock CLONE_THREAD fork()ing per-threadgroup

From: Ben Blum <bblum-OM76b2Iv3yLQjUSlxSEPGw@public.gmane.org>

This patch adds an rwsem that lives in a threadgroup's signal_struct that's
taken for reading in the fork path, under CONFIG_CGROUPS. If another part of
the kernel later wants to use such a locking mechanism, the CONFIG_CGROUPS
ifdefs should be changed to a higher-up flag that CGROUPS and the other system
would both depend on.

This is a pre-patch for cgroups-procs-write.patch.

Signed-off-by: Ben Blum <bblum-OM76b2Iv3yLQjUSlxSEPGw@public.gmane.org>
---
 include/linux/init_task.h |    9 +++++++++
 include/linux/sched.h     |   10 ++++++++++
 kernel/fork.c             |   16 ++++++++++++++++
 3 files changed, 35 insertions(+), 0 deletions(-)

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 1f43fa5..ca46711 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -15,6 +15,14 @@
 extern struct files_struct init_files;
 extern struct fs_struct init_fs;
 
+#ifdef CONFIG_CGROUPS
+#define INIT_THREADGROUP_FORK_LOCK(sig)					\
+	.threadgroup_fork_lock =					\
+		__RWSEM_INITIALIZER(sig.threadgroup_fork_lock),
+#else
+#define INIT_THREADGROUP_FORK_LOCK(sig)
+#endif
+
 #define INIT_SIGNALS(sig) {						\
 	.nr_threads	= 1,						\
 	.wait_chldexit	= __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\
@@ -29,6 +37,7 @@ extern struct fs_struct init_fs;
 		.running = 0,						\
 		.lock = __SPIN_LOCK_UNLOCKED(sig.cputimer.lock),	\
 	},								\
+	INIT_THREADGROUP_FORK_LOCK(sig)					\
 }
 
 extern struct nsproxy init_nsproxy;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ae69716..82b0bcf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -619,6 +619,16 @@ struct signal_struct {
 	unsigned audit_tty;
 	struct tty_audit_buf *tty_audit_buf;
 #endif
+#ifdef CONFIG_CGROUPS
+	/*
+	 * The threadgroup_fork_lock prevents threads from forking with
+	 * CLONE_THREAD while held for writing. Use this for fork-sensitive
+	 * threadgroup-wide operations. It's taken for reading in fork.c in
+	 * copy_process().
+	 * Currently only needed write-side by cgroups.
+	 */
+	struct rw_semaphore threadgroup_fork_lock;
+#endif
 
 	int oom_adj;	/* OOM kill score adjustment (bit shift) */
 };
diff --git a/kernel/fork.c b/kernel/fork.c
index a82a65c..a9bce89 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -898,6 +898,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 
 	tty_audit_fork(sig);
 
+#ifdef CONFIG_CGROUPS
+	init_rwsem(&sig->threadgroup_fork_lock);
+#endif
+
 	sig->oom_adj = current->signal->oom_adj;
 
 	return 0;
@@ -1076,6 +1080,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	monotonic_to_bootbased(&p->real_start_time);
 	p->io_context = NULL;
 	p->audit_context = NULL;
+#ifdef CONFIG_CGROUPS
+	if (clone_flags & CLONE_THREAD)
+		down_read(&current->signal->threadgroup_fork_lock);
+#endif
 	cgroup_fork(p);
 #ifdef CONFIG_NUMA
 	p->mempolicy = mpol_dup(p->mempolicy);
@@ -1283,6 +1291,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	write_unlock_irq(&tasklist_lock);
 	proc_fork_connector(p);
 	cgroup_post_fork(p);
+#ifdef CONFIG_CGROUPS
+	if (clone_flags & CLONE_THREAD)
+		up_read(&current->signal->threadgroup_fork_lock);
+#endif
 	perf_event_fork(p);
 	return p;
 
@@ -1316,6 +1328,10 @@ bad_fork_cleanup_policy:
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_cgroup:
 #endif
+#ifdef CONFIG_CGROUPS
+	if (clone_flags & CLONE_THREAD)
+		up_read(&current->signal->threadgroup_fork_lock);
+#endif
 	cgroup_exit(p, cgroup_callbacks_done);
 	delayacct_tsk_free(p);
 	module_put(task_thread_info(p)->exec_domain->module);