mm, oom_reaper: do not mmput synchronously from the oom reaper context

Tetsuo has properly noted that mmput slow path might get blocked waiting
for another party (e.g.  exit_aio waits for an IO).  If that happens the
oom_reaper would be put out of the way and will not be able to process
next oom victim.  We should strive for making this context as reliable
and independent on other subsystems as much as possible.

Introduce mmput_async which will perform the slow path from an async
(WQ) context.  This will delay the operation but that shouldn't be a
problem because the oom_reaper has reclaimed the victim's address space
for most cases as much as possible and the remaining context shouldn't
bind too much memory anymore.  The only exception is when mmap_sem
trylock has failed which shouldn't happen too often.

The issue is only theoretical but not impossible.

Signed-off-by: Michal Hocko <mhocko@suse.com>
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 35 insertions, 15 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 3e8451527cbe..8fbed7194af1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -699,6 +699,26 @@ void __mmdrop(struct mm_struct *mm)
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
 
+static inline void __mmput(struct mm_struct *mm)
+{
+        VM_BUG_ON(atomic_read(&mm->mm_users));
+
+        uprobe_clear_state(mm);
+        exit_aio(mm);
+        ksm_exit(mm);
+        khugepaged_exit(mm); /* must run before exit_mmap */
+        exit_mmap(mm);
+        set_mm_exe_file(mm, NULL);
+        if (!list_empty(&mm->mmlist)) {
+                spin_lock(&mmlist_lock);
+                list_del(&mm->mmlist);
+                spin_unlock(&mmlist_lock);
+        }
+        if (mm->binfmt)
+                module_put(mm->binfmt->module);
+        mmdrop(mm);
+}
+
 /*
  * Decrement the use count and release all resources for an mm.
  */
@@ -706,24 +726,24 @@ void mmput(struct mm_struct *mm)
 {
         might_sleep();
 
+        if (atomic_dec_and_test(&mm->mm_users))
+                __mmput(mm);
+}
+EXPORT_SYMBOL_GPL(mmput);
+
+static void mmput_async_fn(struct work_struct *work)
+{
+        struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work);
+        __mmput(mm);
+}
+
+void mmput_async(struct mm_struct *mm)
+{
         if (atomic_dec_and_test(&mm->mm_users)) {
-                uprobe_clear_state(mm);
-                exit_aio(mm);
-                ksm_exit(mm);
-                khugepaged_exit(mm); /* must run before exit_mmap */
-                exit_mmap(mm);
-                set_mm_exe_file(mm, NULL);
-                if (!list_empty(&mm->mmlist)) {
-                        spin_lock(&mmlist_lock);
-                        list_del(&mm->mmlist);
-                        spin_unlock(&mmlist_lock);
-                }
-                if (mm->binfmt)
-                        module_put(mm->binfmt->module);
-                mmdrop(mm);
+                INIT_WORK(&mm->async_put_work, mmput_async_fn);
+                schedule_work(&mm->async_put_work);
         }
 }
-EXPORT_SYMBOL_GPL(mmput);
 
 /**
  * set_mm_exe_file - change a reference to the mm's executable file