1 files changed, 187 insertions, 9 deletions

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 06f7e17..b34d279 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -35,6 +35,11 @@
 #include <linux/freezer.h>
 #include <linux/ftrace.h>
 #include <linux/ratelimit.h>
+#include <linux/kthread.h>
+#include <linux/init.h>
+
+#include <asm/tlb.h>
+#include "internal.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/oom.h>
@@ -405,6 +410,172 @@ static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait);
 
 bool oom_killer_disabled __read_mostly;
 
+#define K(x) ((x) << (PAGE_SHIFT-10))
+
+#ifdef CONFIG_MMU
+/*
+ * OOM Reaper kernel thread which tries to reap the memory used by the OOM
+ * victim (if that is possible) to help the OOM killer to move on.
+ */
+static struct task_struct *oom_reaper_th;
+static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait);
+static struct task_struct *oom_reaper_list;
+static DEFINE_SPINLOCK(oom_reaper_lock);
+
+
+static bool __oom_reap_task(struct task_struct *tsk)
+{
+	struct mmu_gather tlb;
+	struct vm_area_struct *vma;
+	struct mm_struct *mm;
+	struct task_struct *p;
+	struct zap_details details = {.check_swap_entries = true,
+				      .ignore_dirty = true};
+	bool ret = true;
+
+	/*
+	 * Make sure we find the associated mm_struct even when the particular
+	 * thread has already terminated and cleared its mm.
+	 * We might have race with exit path so consider our work done if there
+	 * is no mm.
+	 */
+	p = find_lock_task_mm(tsk);
+	if (!p)
+		return true;
+
+	mm = p->mm;
+	if (!atomic_inc_not_zero(&mm->mm_users)) {
+		task_unlock(p);
+		return true;
+	}
+
+	task_unlock(p);
+
+	if (!down_read_trylock(&mm->mmap_sem)) {
+		ret = false;
+		goto out;
+	}
+
+	tlb_gather_mmu(&tlb, mm, 0, -1);
+	for (vma = mm->mmap ; vma; vma = vma->vm_next) {
+		if (is_vm_hugetlb_page(vma))
+			continue;
+
+		/*
+		 * mlocked VMAs require explicit munlocking before unmap.
+		 * Let's keep it simple here and skip such VMAs.
+		 */
+		if (vma->vm_flags & VM_LOCKED)
+			continue;
+
+		/*
+		 * Only anonymous pages have a good chance to be dropped
+		 * without additional steps which we cannot afford as we
+		 * are OOM already.
+		 *
+		 * We do not even care about fs backed pages because all
+		 * which are reclaimable have already been reclaimed and
+		 * we do not want to block exit_mmap by keeping mm ref
+		 * count elevated without a good reason.
+		 */
+		if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED))
+			unmap_page_range(&tlb, vma, vma->vm_start, vma->vm_end,
+					 &details);
+	}
+	tlb_finish_mmu(&tlb, 0, -1);
+	pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
+			task_pid_nr(tsk), tsk->comm,
+			K(get_mm_counter(mm, MM_ANONPAGES)),
+			K(get_mm_counter(mm, MM_FILEPAGES)),
+			K(get_mm_counter(mm, MM_SHMEMPAGES)));
+	up_read(&mm->mmap_sem);
+
+	/*
+	 * Clear TIF_MEMDIE because the task shouldn't be sitting on a
+	 * reasonably reclaimable memory anymore. OOM killer can continue
+	 * by selecting other victim if unmapping hasn't led to any
+	 * improvements. This also means that selecting this task doesn't
+	 * make any sense.
+	 */
+	tsk->signal->oom_score_adj = OOM_SCORE_ADJ_MIN;
+	exit_oom_victim(tsk);
+out:
+	mmput(mm);
+	return ret;
+}
+
+#define MAX_OOM_REAP_RETRIES 10
+static void oom_reap_task(struct task_struct *tsk)
+{
+	int attempts = 0;
+
+	/* Retry the down_read_trylock(mmap_sem) a few times */
+	while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task(tsk))
+		schedule_timeout_idle(HZ/10);
+
+	if (attempts > MAX_OOM_REAP_RETRIES) {
+		pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
+				task_pid_nr(tsk), tsk->comm);
+		debug_show_all_locks();
+	}
+
+	/* Drop a reference taken by wake_oom_reaper */
+	put_task_struct(tsk);
+}
+
+static int oom_reaper(void *unused)
+{
+	set_freezable();
+
+	while (true) {
+		struct task_struct *tsk = NULL;
+
+		wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL);
+		spin_lock(&oom_reaper_lock);
+		if (oom_reaper_list != NULL) {
+			tsk = oom_reaper_list;
+			oom_reaper_list = tsk->oom_reaper_list;
+		}
+		spin_unlock(&oom_reaper_lock);
+
+		if (tsk)
+			oom_reap_task(tsk);
+	}
+
+	return 0;
+}
+
+static void wake_oom_reaper(struct task_struct *tsk)
+{
+	if (!oom_reaper_th || tsk->oom_reaper_list)
+		return;
+
+	get_task_struct(tsk);
+
+	spin_lock(&oom_reaper_lock);
+	tsk->oom_reaper_list = oom_reaper_list;
+	oom_reaper_list = tsk;
+	spin_unlock(&oom_reaper_lock);
+	wake_up(&oom_reaper_wait);
+}
+
+static int __init oom_init(void)
+{
+	oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper");
+	if (IS_ERR(oom_reaper_th)) {
+		pr_err("Unable to start OOM reaper %ld. Continuing regardless\n",
+				PTR_ERR(oom_reaper_th));
+		oom_reaper_th = NULL;
+	}
+	return 0;
+}
+subsys_initcall(oom_init)
+#else
+static void wake_oom_reaper(struct task_struct *tsk)
+{
+}
+#endif
+
 /**
  * mark_oom_victim - mark the given task as OOM victim
  * @tsk: task to mark
@@ -431,9 +602,10 @@ void mark_oom_victim(struct task_struct *tsk)
 /**
  * exit_oom_victim - note the exit of an OOM victim
  */
-void exit_oom_victim(void)
+void exit_oom_victim(struct task_struct *tsk)
 {
-	clear_thread_flag(TIF_MEMDIE);
+	if (!test_and_clear_tsk_thread_flag(tsk, TIF_MEMDIE))
+		return;
 
 	if (!atomic_dec_return(&oom_victims))
 		wake_up_all(&oom_victims_wait);
@@ -494,7 +666,6 @@ static bool process_shares_mm(struct task_struct *p, struct mm_struct *mm)
 	return false;
 }
 
-#define K(x) ((x) << (PAGE_SHIFT-10))
 /*
  * Must be called while holding a reference to p, which will be released upon
  * returning.
@@ -510,6 +681,7 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p,
 	unsigned int victim_points = 0;
 	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
 					      DEFAULT_RATELIMIT_BURST);
+	bool can_oom_reap = true;
 
 	/*
 	 * If the task is already exiting, don't alarm the sysadmin or kill
@@ -600,17 +772,23 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p,
 			continue;
 		if (same_thread_group(p, victim))
 			continue;
-		if (unlikely(p->flags & PF_KTHREAD))
-			continue;
-		if (is_global_init(p))
-			continue;
-		if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+		if (unlikely(p->flags & PF_KTHREAD) || is_global_init(p) ||
+		    p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+			/*
+			 * We cannot use oom_reaper for the mm shared by this
+			 * process because it wouldn't get killed and so the
+			 * memory might be still used.
+			 */
+			can_oom_reap = false;
 			continue;
-
+		}
 		do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
 	}
 	rcu_read_unlock();
 
+	if (can_oom_reap)
+		wake_oom_reaper(victim);
+
 	mmdrop(mm);
 	put_task_struct(victim);
 }