mm: oom: let oom_reap_task and exit_mmap run concurrently

This is purely required because exit_aio() may block and exit_mmap() may
never start, if the oom_reap_task cannot start running on a mm with
mm_users == 0.

At the same time if the OOM reaper doesn't wait at all for the memory of
the current OOM candidate to be freed by exit_mmap->unmap_vmas, it would
generate a spurious OOM kill.

If it wasn't because of the exit_aio or similar blocking functions in
the last mmput, it would be enough to change the oom_reap_task() in the
case it finds mm_users == 0, to wait for a timeout or to wait for
__mmput to set MMF_OOM_SKIP itself, but it's not just exit_mmap the
problem here so the concurrency of exit_mmap and oom_reap_task is
apparently warranted.

It's a non standard runtime, exit_mmap() runs without mmap_sem, and
oom_reap_task runs with the mmap_sem for reading as usual (kind of
MADV_DONTNEED).

The race between the two is solved with a combination of
tsk_is_oom_victim() (serialized by task_lock) and MMF_OOM_SKIP
(serialized by a dummy down_write/up_write cycle on the same lines of
the ksm_exit method).

If the oom_reap_task() may be running concurrently during exit_mmap,
exit_mmap will wait it to finish in down_write (before taking down mm
structures that would make the oom_reap_task fail with use after free).

If exit_mmap comes first, oom_reap_task() will skip the mm if
MMF_OOM_SKIP is already set and in turn all memory is already freed and
furthermore the mm data structures may already have been taken down by
free_pgtables.

[aarcange@redhat.com: incremental one liner]
  Link: http://lkml.kernel.org/r/20170726164319.GC29716@redhat.com
[rientjes@google.com: remove unused mmput_async]
  Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1708141733130.50317@chino.kir.corp.google.com
[aarcange@redhat.com: microoptimization]
  Link: http://lkml.kernel.org/r/20170817171240.GB5066@redhat.com
Link: http://lkml.kernel.org/r/20170726162912.GA29716@redhat.com
Fixes: 26db62f1 ("oom: keep mm of the killed task available")
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Reported-by: David Rientjes <rientjes@google.com>
Tested-by: David Rientjes <rientjes@google.com>
Reviewed-by: Michal Hocko <mhocko@suse.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/sched/mm.h

@@ -84,12 +84,6 @@ static inline bool mmget_not_zero(struct mm_struct *mm)
 
 /* mmput gets rid of the mappings and all user-space */
 extern void mmput(struct mm_struct *);
-#ifdef CONFIG_MMU
-/* same as above but performs the slow path from the async context. Can
- * be called from the atomic context as well
- */
-extern void mmput_async(struct mm_struct *);
-#endif
 
 /* Grab a reference to a task's mm, if it is not already going away */
 extern struct mm_struct *get_task_mm(struct task_struct *task);

kernel/fork.c

@@ -922,7 +922,6 @@ static inline void __mmput(struct mm_struct *mm)
 	}
 	if (mm->binfmt)
 		module_put(mm->binfmt->module);
-	set_bit(MMF_OOM_SKIP, &mm->flags);
 	mmdrop(mm);
 }
 
@@ -938,22 +937,6 @@ void mmput(struct mm_struct *mm)
 }
 EXPORT_SYMBOL_GPL(mmput);
 
-#ifdef CONFIG_MMU
-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)) {
-		INIT_WORK(&mm->async_put_work, mmput_async_fn);
-		schedule_work(&mm->async_put_work);
-	}
-}
-#endif
-
 /**
  * set_mm_exe_file - change a reference to the mm's executable file
  *

mm/mmap.c

@@ -44,6 +44,7 @@
 #include <linux/userfaultfd_k.h>
 #include <linux/moduleparam.h>
 #include <linux/pkeys.h>
+#include <linux/oom.h>
 
 #include <linux/uaccess.h>
 #include <asm/cacheflush.h>
@@ -3001,6 +3002,23 @@ void exit_mmap(struct mm_struct *mm)
 	/* Use -1 here to ensure all VMAs in the mm are unmapped */
 	unmap_vmas(&tlb, vma, 0, -1);
 
+	set_bit(MMF_OOM_SKIP, &mm->flags);
+	if (unlikely(tsk_is_oom_victim(current))) {
+		/*
+		 * Wait for oom_reap_task() to stop working on this
+		 * mm. Because MMF_OOM_SKIP is already set before
+		 * calling down_read(), oom_reap_task() will not run
+		 * on this "mm" post up_write().
+		 *
+		 * tsk_is_oom_victim() cannot be set from under us
+		 * either because current->mm is already set to NULL
+		 * under task_lock before calling mmput and oom_mm is
+		 * set not NULL by the OOM killer only if current->mm
+		 * is found not NULL while holding the task_lock.
+		 */
+		down_write(&mm->mmap_sem);
+		up_write(&mm->mmap_sem);
+	}
 	free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING);
 	tlb_finish_mmu(&tlb, 0, -1);
 

mm/oom_kill.c

@@ -495,11 +495,12 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 	}
 
 	/*
-	 * increase mm_users only after we know we will reap something so
-	 * that the mmput_async is called only when we have reaped something
-	 * and delayed __mmput doesn't matter that much
+	 * MMF_OOM_SKIP is set by exit_mmap when the OOM reaper can't
+	 * work on the mm anymore. The check for MMF_OOM_SKIP must run
+	 * under mmap_sem for reading because it serializes against the
+	 * down_write();up_write() cycle in exit_mmap().
 	 */
-	if (!mmget_not_zero(mm)) {
+	if (test_bit(MMF_OOM_SKIP, &mm->flags)) {
 		up_read(&mm->mmap_sem);
 		trace_skip_task_reaping(tsk->pid);
 		goto unlock_oom;
@@ -542,12 +543,6 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 			K(get_mm_counter(mm, MM_SHMEMPAGES)));
 	up_read(&mm->mmap_sem);
 
-	/*
-	 * Drop our reference but make sure the mmput slow path is called from a
-	 * different context because we shouldn't risk we get stuck there and
-	 * put the oom_reaper out of the way.
-	 */
-	mmput_async(mm);
 	trace_finish_task_reaping(tsk->pid);
 unlock_oom:
 	mutex_unlock(&oom_lock);