[PATCH] coredump: don't take tasklist_lock

This patch removes tasklist_lock from zap_threads().
This is safe wrt:

	do_exit:
		The caller holds mm->mmap_sem. This means that task which
		shares the same ->mm can't pass exit_mm(), so it can't be
		unhashed from init_task.tasks or ->thread_group lists.

	fork:
		None of sub-threads can fork after zap_process(leader). All
		processes which were created before this point should be
		visible to zap_threads() because copy_process() adds the new
		process to the tail of init_task.tasks list, and ->siglock
		lock/unlock provides a memory barrier.

	de_thread:
		It does list_replace_rcu(&leader->tasks, &current->tasks).
		So zap_threads() will see either old or new leader, it does
		not matter. However, it can change p->sighand, so we should
		use lock_task_sighand() in zap_process().

Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/fs/exec.c b/fs/exec.c
index b58ba7d..49fa012 100644 (file)
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1373,7 +1373,11 @@ static void zap_process(struct task_struct *start)
        struct task_struct *t;
        unsigned long flags;
 
-       spin_lock_irqsave(&start->sighand->siglock, flags);
+       /*
+        * start->sighand can't disappear, but may be
+        * changed by de_thread()
+        */
+       lock_task_sighand(start, &flags);
        start->signal->flags = SIGNAL_GROUP_EXIT;
        start->signal->group_stop_count = 0;
 
@@ -1386,7 +1390,7 @@ static void zap_process(struct task_struct *start)
                }
        } while ((t = next_thread(t)) != start);
 
-       spin_unlock_irqrestore(&start->sighand->siglock, flags);
+       unlock_task_sighand(start, &flags);
 }
 
 static void zap_threads(struct mm_struct *mm)
@@ -1404,7 +1408,7 @@ static void zap_threads(struct mm_struct *mm)
                complete(vfork_done);
        }
 
-       read_lock(&tasklist_lock);
+       rcu_read_lock();
        for_each_process(g) {
                p = g;
                do {
@@ -1415,7 +1419,7 @@ static void zap_threads(struct mm_struct *mm)
                        }
                } while ((p = next_thread(p)) != g);
        }
-       read_unlock(&tasklist_lock);
+       rcu_read_unlock();
 }
 
 static void coredump_wait(struct mm_struct *mm)