The patch titled
cgroups: read-write lock CLONE_THREAD forking per threadgroup
has been added to the -mm tree. Its filename is
cgroups-read-write-lock-clone_thread-forking-per-threadgroup.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: cgroups: read-write lock CLONE_THREAD forking per threadgroup
From: Ben Blum <bblum@xxxxxxxxxxxxxx>
Adds functionality to read/write lock CLONE_THREAD fork()ing per-threadgroup
Add 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 cgroup-procs-write.patch.
Signed-off-by: Ben Blum <bblum@xxxxxxxxxxxxxx>
Cc: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx>
Cc: Li Zefan <lizf@xxxxxxxxxxxxxx>
Cc: Matt Helsley <matthltc@xxxxxxxxxx>
Cc: Paul Menage <menage@xxxxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Miao Xie <miaox@xxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/init_task.h | 9 +++++++++
include/linux/sched.h | 36 ++++++++++++++++++++++++++++++++++++
kernel/fork.c | 10 ++++++++++
3 files changed, 55 insertions(+)
diff -puN include/linux/init_task.h~cgroups-read-write-lock-clone_thread-forking-per-threadgroup include/linux/init_task.h
--- a/include/linux/init_task.h~cgroups-read-write-lock-clone_thread-forking-per-threadgroup
+++ a/include/linux/init_task.h
@@ -22,6 +22,14 @@
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),\
@@ -38,6 +46,7 @@ extern struct fs_struct init_fs;
}, \
.cred_guard_mutex = \
__MUTEX_INITIALIZER(sig.cred_guard_mutex), \
+ INIT_THREADGROUP_FORK_LOCK(sig) \
}
extern struct nsproxy init_nsproxy;
diff -puN include/linux/sched.h~cgroups-read-write-lock-clone_thread-forking-per-threadgroup include/linux/sched.h
--- a/include/linux/sched.h~cgroups-read-write-lock-clone_thread-forking-per-threadgroup
+++ a/include/linux/sched.h
@@ -514,6 +514,7 @@ struct thread_group_cputimer {
spinlock_t lock;
};
+#include <linux/rwsem.h>
struct autogroup;
/*
@@ -633,6 +634,16 @@ 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) */
int oom_score_adj; /* OOM kill score adjustment */
@@ -2305,6 +2316,31 @@ static inline void unlock_task_sighand(s
spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
}
+/* See the declaration of threadgroup_fork_lock in signal_struct. */
+#ifdef CONFIG_CGROUPS
+static inline void threadgroup_fork_read_lock(struct task_struct *tsk)
+{
+ down_read(&tsk->signal->threadgroup_fork_lock);
+}
+static inline void threadgroup_fork_read_unlock(struct task_struct *tsk)
+{
+ up_read(&tsk->signal->threadgroup_fork_lock);
+}
+static inline void threadgroup_fork_write_lock(struct task_struct *tsk)
+{
+ down_write(&tsk->signal->threadgroup_fork_lock);
+}
+static inline void threadgroup_fork_write_unlock(struct task_struct *tsk)
+{
+ up_write(&tsk->signal->threadgroup_fork_lock);
+}
+#else
+static inline void threadgroup_fork_read_lock(struct task_struct *tsk) {}
+static inline void threadgroup_fork_read_unlock(struct task_struct *tsk) {}
+static inline void threadgroup_fork_write_lock(struct task_struct *tsk) {}
+static inline void threadgroup_fork_write_unlock(struct task_struct *tsk) {}
+#endif
+
#ifndef __HAVE_THREAD_FUNCTIONS
#define task_thread_info(task) ((struct thread_info *)(task)->stack)
diff -puN kernel/fork.c~cgroups-read-write-lock-clone_thread-forking-per-threadgroup kernel/fork.c
--- a/kernel/fork.c~cgroups-read-write-lock-clone_thread-forking-per-threadgroup
+++ a/kernel/fork.c
@@ -927,6 +927,10 @@ static int copy_signal(unsigned long clo
tty_audit_fork(sig);
sched_autogroup_fork(sig);
+#ifdef CONFIG_CGROUPS
+ init_rwsem(&sig->threadgroup_fork_lock);
+#endif
+
sig->oom_adj = current->signal->oom_adj;
sig->oom_score_adj = current->signal->oom_score_adj;
sig->oom_score_adj_min = current->signal->oom_score_adj_min;
@@ -1109,6 +1113,8 @@ static struct task_struct *copy_process(
monotonic_to_bootbased(&p->real_start_time);
p->io_context = NULL;
p->audit_context = NULL;
+ if (clone_flags & CLONE_THREAD)
+ threadgroup_fork_read_lock(current);
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
@@ -1313,6 +1319,8 @@ static struct task_struct *copy_process(
write_unlock_irq(&tasklist_lock);
proc_fork_connector(p);
cgroup_post_fork(p);
+ if (clone_flags & CLONE_THREAD)
+ threadgroup_fork_read_unlock(current);
perf_event_fork(p);
return p;
@@ -1351,6 +1359,8 @@ bad_fork_cleanup_policy:
mpol_put(p->mempolicy);
bad_fork_cleanup_cgroup:
#endif
+ if (clone_flags & CLONE_THREAD)
+ threadgroup_fork_read_unlock(current);
cgroup_exit(p, cgroup_callbacks_done);
delayacct_tsk_free(p);
module_put(task_thread_info(p)->exec_domain->module);
_
Patches currently in -mm which might be from bblum@xxxxxxxxxxxxxx are
cgroups-read-write-lock-clone_thread-forking-per-threadgroup.patch
cgroups-add-per-thread-subsystem-callbacks.patch
cgroups-make-procs-file-writable.patch
cgroups-use-flex_array-in-attach_proc.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
