kernel, oom: fix potential pgd_lock deadlock from __mmdrop

Lockdep complains that __mmdrop is not safe from the softirq context:

  =================================
  [ INFO: inconsistent lock state ]
  4.6.0-oomfortification2-00011-geeb3eadeab96-dirty #949 Tainted: G        W
  ---------------------------------
  inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
  swapper/1/0 [HC0[0]:SC1[1]:HE1:SE0] takes:
   (pgd_lock){+.?...}, at: pgd_free+0x19/0x6b
  {SOFTIRQ-ON-W} state was registered at:
     __lock_acquire+0xa06/0x196e
     lock_acquire+0x139/0x1e1
     _raw_spin_lock+0x32/0x41
     __change_page_attr_set_clr+0x2a5/0xacd
     change_page_attr_set_clr+0x16f/0x32c
     set_memory_nx+0x37/0x3a
     free_init_pages+0x9e/0xc7
     alternative_instructions+0xa2/0xb3
     check_bugs+0xe/0x2d
     start_kernel+0x3ce/0x3ea
     x86_64_start_reservations+0x2a/0x2c
     x86_64_start_kernel+0x17a/0x18d
  irq event stamp: 105916
  hardirqs last  enabled at (105916): free_hot_cold_page+0x37e/0x390
  hardirqs last disabled at (105915): free_hot_cold_page+0x2c1/0x390
  softirqs last  enabled at (105878): _local_bh_enable+0x42/0x44
  softirqs last disabled at (105879): irq_exit+0x6f/0xd1

  other info that might help us debug this:
   Possible unsafe locking scenario:

         CPU0
         ----
    lock(pgd_lock);
    <Interrupt>
      lock(pgd_lock);

   *** DEADLOCK ***

  1 lock held by swapper/1/0:
   #0:  (rcu_callback){......}, at: rcu_process_callbacks+0x390/0x800

  stack backtrace:
  CPU: 1 PID: 0 Comm: swapper/1 Tainted: G        W       4.6.0-oomfortification2-00011-geeb3eadeab96-dirty #949
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Debian-1.8.2-1 04/01/2014
  Call Trace:
   <IRQ>
    print_usage_bug.part.25+0x259/0x268
    mark_lock+0x381/0x567
    __lock_acquire+0x993/0x196e
    lock_acquire+0x139/0x1e1
    _raw_spin_lock+0x32/0x41
    pgd_free+0x19/0x6b
    __mmdrop+0x25/0xb9
    __put_task_struct+0x103/0x11e
    delayed_put_task_struct+0x157/0x15e
    rcu_process_callbacks+0x660/0x800
    __do_softirq+0x1ec/0x4d5
    irq_exit+0x6f/0xd1
    smp_apic_timer_interrupt+0x42/0x4d
    apic_timer_interrupt+0x8e/0xa0
   <EOI>
    arch_cpu_idle+0xf/0x11
    default_idle_call+0x32/0x34
    cpu_startup_entry+0x20c/0x399
    start_secondary+0xfe/0x101

More over commit a79e53d85683 ("x86/mm: Fix pgd_lock deadlock") was
explicit about pgd_lock not to be called from the irq context.  This
means that __mmdrop called from free_signal_struct has to be postponed
to a user context.  We already have a similar mechanism for mmput_async
so we can use it here as well.  This is safe because mm_count is pinned
by mm_users.

This fixes bug introduced by "oom: keep mm of the killed task available"

Link: http://lkml.kernel.org/r/1472119394-11342-5-git-send-email-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 19 insertions, 3 deletions

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 903200f4ec41..4a8acedf4b7d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -515,9 +515,7 @@ struct mm_struct {
 #ifdef CONFIG_HUGETLB_PAGE
 	atomic_long_t hugetlb_usage;
 #endif
-#ifdef CONFIG_MMU
 	struct work_struct async_put_work;
-#endif
 };
 
 static inline void mm_init_cpumask(struct mm_struct *mm)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 67ea79610e67..c4b588358296 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2877,6 +2877,20 @@ static inline void mmdrop(struct mm_struct *mm)
 		__mmdrop(mm);
 }
 
+static inline void mmdrop_async_fn(struct work_struct *work)
+{
+	struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work);
+	__mmdrop(mm);
+}
+
+static inline void mmdrop_async(struct mm_struct *mm)
+{
+	if (unlikely(atomic_dec_and_test(&mm->mm_count))) {
+		INIT_WORK(&mm->async_put_work, mmdrop_async_fn);
+		schedule_work(&mm->async_put_work);
+	}
+}
+
 static inline bool mmget_not_zero(struct mm_struct *mm)
 {
 	return atomic_inc_not_zero(&mm->mm_users);
diff --git a/kernel/fork.c b/kernel/fork.c
index 48cafe787b75..5650e35dda43 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -359,8 +359,12 @@ static inline void free_signal_struct(struct signal_struct *sig)
 {
 	taskstats_tgid_free(sig);
 	sched_autogroup_exit(sig);
+	/*
+	 * __mmdrop is not safe to call from softirq context on x86 due to
+	 * pgd_dtor so postpone it to the async context
+	 */
 	if (sig->oom_mm)
-		mmdrop(sig->oom_mm);
+		mmdrop_async(sig->oom_mm);
 	kmem_cache_free(signal_cachep, sig);
 }