oom: add per-mm oom disable count

It's pointless to kill a task if another thread sharing its mm cannot be
killed to allow future memory freeing.  A subsequent patch will prevent
kills in such cases, but first it's necessary to have a way to flag a task
that shares memory with an OOM_DISABLE task that doesn't incur an
additional tasklist scan, which would make select_bad_process() an O(n^2)
function.

This patch adds an atomic counter to struct mm_struct that follows how
many threads attached to it have an oom_score_adj of OOM_SCORE_ADJ_MIN.
They cannot be killed by the kernel, so their memory cannot be freed in
oom conditions.

This only requires task_lock() on the task that we're operating on, it
does not require mm->mmap_sem since task_lock() pins the mm and the
operation is atomic.

[rientjes@google.com: changelog and sys_unshare() code]
[rientjes@google.com: protect oom_disable_count with task_lock in fork]
[rientjes@google.com: use old_mm for oom_disable_count in exec]
Signed-off-by: Ying Han <yinghan@google.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 17 insertions, 1 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index e2bdf37f9fde..894179a32ec1 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -50,6 +50,7 @@
 #include <linux/perf_event.h>
 #include <trace/events/sched.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/oom.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -687,6 +688,8 @@ static void exit_mm(struct task_struct * tsk)
 	enter_lazy_tlb(mm, current);
 	/* We don't want this task to be frozen prematurely */
 	clear_freeze_flag(tsk);
+	if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+		atomic_dec(&mm->oom_disable_count);
 	task_unlock(tsk);
 	mm_update_next_owner(mm);
 	mmput(mm);
diff --git a/kernel/fork.c b/kernel/fork.c
index c445f8cc408d..e87aaaaf5131 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -65,6 +65,7 @@
 #include <linux/perf_event.h>
 #include <linux/posix-timers.h>
 #include <linux/user-return-notifier.h>
+#include <linux/oom.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -488,6 +489,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 	mm->cached_hole_size = ~0UL;
 	mm_init_aio(mm);
 	mm_init_owner(mm, p);
+	atomic_set(&mm->oom_disable_count, 0);
 
 	if (likely(!mm_alloc_pgd(mm))) {
 		mm->def_flags = 0;
@@ -741,6 +743,8 @@ good_mm:
 	/* Initializing for Swap token stuff */
 	mm->token_priority = 0;
 	mm->last_interval = 0;
+	if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+		atomic_inc(&mm->oom_disable_count);
 
 	tsk->mm = mm;
 	tsk->active_mm = mm;
@@ -1299,8 +1303,13 @@ bad_fork_cleanup_io:
 bad_fork_cleanup_namespaces:
 	exit_task_namespaces(p);
 bad_fork_cleanup_mm:
-	if (p->mm)
+	if (p->mm) {
+		task_lock(p);
+		if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+			atomic_dec(&p->mm->oom_disable_count);
+		task_unlock(p);
 		mmput(p->mm);
+	}
 bad_fork_cleanup_signal:
 	if (!(clone_flags & CLONE_THREAD))
 		free_signal_struct(p->signal);
@@ -1693,6 +1702,10 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 			active_mm = current->active_mm;
 			current->mm = new_mm;
 			current->active_mm = new_mm;
+			if (current->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+				atomic_dec(&mm->oom_disable_count);
+				atomic_inc(&new_mm->oom_disable_count);
+			}
 			activate_mm(active_mm, new_mm);
 			new_mm = mm;
 		}