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, 35 insertions, 0 deletions

diff --git a/fs/exec.c b/fs/exec.c
index 6d2b6f936858..3aa75b8888a1 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -54,6 +54,7 @@
 #include <linux/fsnotify.h>
 #include <linux/fs_struct.h>
 #include <linux/pipe_fs_i.h>
+#include <linux/oom.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -759,6 +760,10 @@ static int exec_mmap(struct mm_struct *mm)
 	tsk->mm = mm;
 	tsk->active_mm = mm;
 	activate_mm(active_mm, mm);
+	if (old_mm && tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+		atomic_dec(&old_mm->oom_disable_count);
+		atomic_inc(&tsk->mm->oom_disable_count);
+	}
 	task_unlock(tsk);
 	arch_pick_mmap_layout(mm);
 	if (old_mm) {
diff --git a/fs/proc/base.c b/fs/proc/base.c
index dc5d5f51f3fe..6e50c8e65513 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1047,6 +1047,21 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
 		return -EACCES;
 	}
 
+	task_lock(task);
+	if (!task->mm) {
+		task_unlock(task);
+		unlock_task_sighand(task, &flags);
+		put_task_struct(task);
+		return -EINVAL;
+	}
+
+	if (oom_adjust != task->signal->oom_adj) {
+		if (oom_adjust == OOM_DISABLE)
+			atomic_inc(&task->mm->oom_disable_count);
+		if (task->signal->oom_adj == OOM_DISABLE)
+			atomic_dec(&task->mm->oom_disable_count);
+	}
+
 	/*
 	 * Warn that /proc/pid/oom_adj is deprecated, see
 	 * Documentation/feature-removal-schedule.txt.
@@ -1065,6 +1080,7 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
 	else
 		task->signal->oom_score_adj = (oom_adjust * OOM_SCORE_ADJ_MAX) /
 								-OOM_DISABLE;
+	task_unlock(task);
 	unlock_task_sighand(task, &flags);
 	put_task_struct(task);
 
@@ -1133,6 +1149,19 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
 		return -EACCES;
 	}
 
+	task_lock(task);
+	if (!task->mm) {
+		task_unlock(task);
+		unlock_task_sighand(task, &flags);
+		put_task_struct(task);
+		return -EINVAL;
+	}
+	if (oom_score_adj != task->signal->oom_score_adj) {
+		if (oom_score_adj == OOM_SCORE_ADJ_MIN)
+			atomic_inc(&task->mm->oom_disable_count);
+		if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+			atomic_dec(&task->mm->oom_disable_count);
+	}
 	task->signal->oom_score_adj = oom_score_adj;
 	/*
 	 * Scale /proc/pid/oom_adj appropriately ensuring that OOM_DISABLE is
@@ -1143,6 +1172,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
 	else
 		task->signal->oom_adj = (oom_score_adj * OOM_ADJUST_MAX) /
 							OOM_SCORE_ADJ_MAX;
+	task_unlock(task);
 	unlock_task_sighand(task, &flags);
 	put_task_struct(task);
 	return count;