From 4fe7efdbdfb1c7e7a7f31decfd831c0f31d37091 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@openvz.org>
Date: Wed, 20 Jun 2012 12:53:01 -0700
Subject: mm: correctly synchronize rss-counters at exit/exec
do_exit() and exec_mmap() call sync_mm_rss() before mm_release() does
put_user(clear_child_tid) which can update task->rss_stat and thus make
mm->rss_stat inconsistent. This triggers the "BUG:" printk in check_mm().
Let's fix this bug in the safest way, and optimize/cleanup this later.
Reported-by: Markus Trippelsdorf <markus@trippelsdorf.de>
Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
kernel/exit.c | 1 +
1 file changed, 1 insertion(+)
(limited to 'kernel/exit.c')
diff --git a/kernel/exit.c b/kernel/exit.c
index 34867cc5b42a..c0277d3f1aaa 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -643,6 +643,7 @@ static void exit_mm(struct task_struct * tsk)
mm_release(tsk, mm);
if (!mm)
return;
+ sync_mm_rss(mm);
/*
* Serialize with any possible pending coredump.
* We must hold mmap_sem around checking core_state
--
cgit
From 6347e90091041e34bea625370794c92f4ce71228 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Wed, 20 Jun 2012 12:53:03 -0700
Subject: pidns: guarantee that the pidns init will be the last pidns process
reaped
Today we have a twofold bug. Sometimes release_task on pid == 1 in a pid
namespace can run before other processes in a pid namespace have had
release task called. With the result that pid_ns_release_proc can be
called before the last proc_flus_task() is done using upid->ns->proc_mnt,
resulting in the use of a stale pointer. This same set of circumstances
can lead to waitpid(...) returning for a processes started with
clone(CLONE_NEWPID) before the every process in the pid namespace has
actually exited.
To fix this modify zap_pid_ns_processess wait until all other processes in
the pid namespace have exited, even EXIT_DEAD zombies.
The delay_group_leader and related tests ensure that the thread gruop
leader will be the last thread of a process group to be reaped, or to
become EXIT_DEAD and self reap. With the change to zap_pid_ns_processes
we get the guarantee that pid == 1 in a pid namespace will be the last
task that release_task is called on.
With pid == 1 being the last task to pass through release_task
pid_ns_release_proc can no longer be called too early nor can wait return
before all of the EXIT_DEAD tasks in a pid namespace have exited.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Louis Rilling <louis.rilling@kerlabs.com>
Cc: Mike Galbraith <efault@gmx.de>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Tested-by: Andrew Wagin <avagin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
kernel/exit.c | 14 +++++++++++++-
kernel/pid_namespace.c | 20 ++++++++++++++++++++
2 files changed, 33 insertions(+), 1 deletion(-)
(limited to 'kernel/exit.c')
diff --git a/kernel/exit.c b/kernel/exit.c
index c0277d3f1aaa..a85efd2348bd 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -64,7 +64,6 @@ static void exit_mm(struct task_struct * tsk);
static void __unhash_process(struct task_struct *p, bool group_dead)
{
nr_threads--;
- detach_pid(p, PIDTYPE_PID);
if (group_dead) {
detach_pid(p, PIDTYPE_PGID);
detach_pid(p, PIDTYPE_SID);
@@ -72,7 +71,20 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
list_del_rcu(&p->tasks);
list_del_init(&p->sibling);
__this_cpu_dec(process_counts);
+ /*
+ * If we are the last child process in a pid namespace to be
+ * reaped, notify the reaper sleeping zap_pid_ns_processes().
+ */
+ if (IS_ENABLED(CONFIG_PID_NS)) {
+ struct task_struct *parent = p->real_parent;
+
+ if ((task_active_pid_ns(p)->child_reaper == parent) &&
+ list_empty(&parent->children) &&
+ (parent->flags & PF_EXITING))
+ wake_up_process(parent);
+ }
}
+ detach_pid(p, PIDTYPE_PID);
list_del_rcu(&p->thread_group);
}
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 16b20e38c4a1..b3c7fd554250 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -184,11 +184,31 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
}
read_unlock(&tasklist_lock);
+ /* Firstly reap the EXIT_ZOMBIE children we may have. */
do {
clear_thread_flag(TIF_SIGPENDING);
rc = sys_wait4(-1, NULL, __WALL, NULL);
} while (rc != -ECHILD);
+ /*
+ * sys_wait4() above can't reap the TASK_DEAD children.
+ * Make sure they all go away, see __unhash_process().
+ */
+ for (;;) {
+ bool need_wait = false;
+
+ read_lock(&tasklist_lock);
+ if (!list_empty(¤t->children)) {
+ __set_current_state(TASK_UNINTERRUPTIBLE);
+ need_wait = true;
+ }
+ read_unlock(&tasklist_lock);
+
+ if (!need_wait)
+ break;
+ schedule();
+ }
+
if (pid_ns->reboot)
current->signal->group_exit_code = pid_ns->reboot;
--
cgit
From 50d75f8daead8a1f850c40a3b6c6575ab19b48cf Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Wed, 20 Jun 2012 12:53:04 -0700
Subject: pidns: find_new_reaper() can no longer switch to
init_pid_ns.child_reaper
find_new_reaper() changes pid_ns->child_reaper, see add0d4df ("pid_ns:
zap_pid_ns_processes: fix the ->child_reaper changing").
The original reason has gone away after the previous patch, ->children
list must be empty after zap_pid_ns_processes().
However now we can not switch to init_pid_ns.child_reaper.
__unhash_process() relies on the "->child_reaper == parent" check, but
this check does not work if the last exiting task is also the child
reaper.
As Eric sugested, we can change __unhash_process() to use the parent's
pid_ns and remove this code.
Also, with this change we can move detach_pid(PIDTYPE_PID) back, where it
was before the previous fix.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Louis Rilling <louis.rilling@kerlabs.com>
Cc: Mike Galbraith <efault@gmx.de>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Tested-by: Andrew Wagin <avagin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
kernel/exit.c | 10 ++--------
1 file changed, 2 insertions(+), 8 deletions(-)
(limited to 'kernel/exit.c')
diff --git a/kernel/exit.c b/kernel/exit.c
index a85efd2348bd..2f59cc334516 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -64,6 +64,7 @@ static void exit_mm(struct task_struct * tsk);
static void __unhash_process(struct task_struct *p, bool group_dead)
{
nr_threads--;
+ detach_pid(p, PIDTYPE_PID);
if (group_dead) {
detach_pid(p, PIDTYPE_PGID);
detach_pid(p, PIDTYPE_SID);
@@ -78,13 +79,12 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
if (IS_ENABLED(CONFIG_PID_NS)) {
struct task_struct *parent = p->real_parent;
- if ((task_active_pid_ns(p)->child_reaper == parent) &&
+ if ((task_active_pid_ns(parent)->child_reaper == parent) &&
list_empty(&parent->children) &&
(parent->flags & PF_EXITING))
wake_up_process(parent);
}
}
- detach_pid(p, PIDTYPE_PID);
list_del_rcu(&p->thread_group);
}
@@ -732,12 +732,6 @@ static struct task_struct *find_new_reaper(struct task_struct *father)
zap_pid_ns_processes(pid_ns);
write_lock_irq(&tasklist_lock);
- /*
- * We can not clear ->child_reaper or leave it alone.
- * There may by stealth EXIT_DEAD tasks on ->children,
- * forget_original_parent() must move them somewhere.
- */
- pid_ns->child_reaper = init_pid_ns.child_reaper;
} else if (father->signal->has_child_subreaper) {
struct task_struct *reaper;
--
cgit