diff options
authorOleg Nesterov <oleg@redhat.com>2014-01-21 15:49:56 -0800
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2014-10-05 14:54:15 -0700
commit641bc58deb5e9c1064db00e80acea791eef90622 (patch)
parentbeed61068fba1c90dc4cd553726c8b68a252a68f (diff)
introduce for_each_thread() to replace the buggy while_each_thread()
commit 0c740d0afc3bff0a097ad03a1c8df92757516f5c upstream. while_each_thread() and next_thread() should die, almost every lockless usage is wrong. 1. Unless g == current, the lockless while_each_thread() is not safe. while_each_thread(g, t) can loop forever if g exits, next_thread() can't reach the unhashed thread in this case. Note that this can happen even if g is the group leader, it can exec. 2. Even if while_each_thread() itself was correct, people often use it wrongly. It was never safe to just take rcu_read_lock() and loop unless you verify that pid_alive(g) == T, even the first next_thread() can point to the already freed/reused memory. This patch adds signal_struct->thread_head and task->thread_node to create the normal rcu-safe list with the stable head. The new for_each_thread(g, t) helper is always safe under rcu_read_lock() as long as this task_struct can't go away. Note: of course it is ugly to have both task_struct->thread_node and the old task_struct->thread_group, we will kill it later, after we change the users of while_each_thread() to use for_each_thread(). Perhaps we can kill it even before we convert all users, we can reimplement next_thread(t) using the new thread_head/thread_node. But we can't do this right now because this will lead to subtle behavioural changes. For example, do/while_each_thread() always sees at least one task, while for_each_thread() can do nothing if the whole thread group has died. Or thread_group_empty(), currently its semantics is not clear unless thread_group_leader(p) and we need to audit the callers before we can change it. So this patch adds the new interface which has to coexist with the old one for some time, hopefully the next changes will be more or less straightforward and the old one will go away soon. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Reviewed-by: Sergey Dyasly <dserrg@gmail.com> Tested-by: Sergey Dyasly <dserrg@gmail.com> Reviewed-by: Sameer Nanda <snanda@chromium.org> Acked-by: David Rientjes <rientjes@google.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mandeep Singh Baines <msb@chromium.org> Cc: "Ma, Xindong" <xindong.ma@intel.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: "Tu, Xiaobing" <xiaobing.tu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Li Zefan <lizefan@huawei.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
4 files changed, 22 insertions, 0 deletions
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 5cd0f0949927..998f4dfedecf 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -40,6 +40,7 @@ extern struct fs_struct init_fs;
#define INIT_SIGNALS(sig) { \
.nr_threads = 1, \
+ .thread_head = LIST_HEAD_INIT(init_task.thread_node), \
.wait_chldexit = __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\
.shared_pending = { \
.list = LIST_HEAD_INIT(sig.shared_pending.list), \
@@ -213,6 +214,7 @@ extern struct task_group root_task_group;
}, \
.thread_group = LIST_HEAD_INIT(tsk.thread_group), \
+ .thread_node = LIST_HEAD_INIT(init_signals.thread_head), \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 597c8ab005a0..8293545ac9b7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -480,6 +480,7 @@ struct signal_struct {
atomic_t sigcnt;
atomic_t live;
int nr_threads;
+ struct list_head thread_head;
wait_queue_head_t wait_chldexit; /* for wait4() */
@@ -1160,6 +1161,7 @@ struct task_struct {
/* PID/PID hash table linkage. */
struct pid_link pids[PIDTYPE_MAX];
struct list_head thread_group;
+ struct list_head thread_node;
struct completion *vfork_done; /* for vfork() */
int __user *set_child_tid; /* CLONE_CHILD_SETTID */
@@ -2167,6 +2169,16 @@ extern bool current_is_single_threaded(void);
#define while_each_thread(g, t) \
while ((t = next_thread(t)) != g)
+#define __for_each_thread(signal, t) \
+ list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node)
+#define for_each_thread(p, t) \
+ __for_each_thread((p)->signal, t)
+/* Careful: this is a double loop, 'break' won't work as expected. */
+#define for_each_process_thread(p, t) \
+ for_each_process(p) for_each_thread(p, t)
static inline int get_nr_threads(struct task_struct *tsk)
return tsk->signal->nr_threads;
diff --git a/kernel/exit.c b/kernel/exit.c
index 6682b2ea5b11..717efbd7cb72 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -74,6 +74,7 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
+ list_del_rcu(&p->thread_node);
diff --git a/kernel/fork.c b/kernel/fork.c
index c271467da4f9..2c76e11ba939 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1045,6 +1045,11 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
sig->nr_threads = 1;
atomic_set(&sig->live, 1);
atomic_set(&sig->sigcnt, 1);
+ /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */
+ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node);
+ tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head);
sig->curr_target = tsk;
@@ -1471,6 +1476,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
p->group_leader = current->group_leader;
+ list_add_tail_rcu(&p->thread_node,
+ &p->signal->thread_head);
attach_pid(p, PIDTYPE_PID, pid);