mm, oom: introduce oom reaper

This patch (of 5):

This is based on the idea from Mel Gorman discussed during LSFMM 2015
and independently brought up by Oleg Nesterov.

The OOM killer currently allows to kill only a single task in a good
hope that the task will terminate in a reasonable time and frees up its
memory.  Such a task (oom victim) will get an access to memory reserves
via mark_oom_victim to allow a forward progress should there be a need
for additional memory during exit path.

It has been shown (e.g.  by Tetsuo Handa) that it is not that hard to
construct workloads which break the core assumption mentioned above and
the OOM victim might take unbounded amount of time to exit because it
might be blocked in the uninterruptible state waiting for an event (e.g.
lock) which is blocked by another task looping in the page allocator.

This patch reduces the probability of such a lockup by introducing a
specialized kernel thread (oom_reaper) which tries to reclaim additional
memory by preemptively reaping the anonymous or swapped out memory owned
by the oom victim under an assumption that such a memory won't be needed
when its owner is killed and kicked from the userspace anyway.  There is
one notable exception to this, though, if the OOM victim was in the
process of coredumping the result would be incomplete.  This is
considered a reasonable constrain because the overall system health is
more important than debugability of a particular application.

A kernel thread has been chosen because we need a reliable way of
invocation so workqueue context is not appropriate because all the
workers might be busy (e.g.  allocating memory).  Kswapd which sounds
like another good fit is not appropriate as well because it might get
blocked on locks during reclaim as well.

oom_reaper has to take mmap_sem on the target task for reading so the
solution is not 100% because the semaphore might be held or blocked for
write but the probability is reduced considerably wrt.  basically any
lock blocking forward progress as described above.  In order to prevent
from blocking on the lock without any forward progress we are using only
a trylock and retry 10 times with a short sleep in between.  Users of
mmap_sem which need it for write should be carefully reviewed to use
_killable waiting as much as possible and reduce allocations requests
done with the lock held to absolute minimum to reduce the risk even
further.

The API between oom killer and oom reaper is quite trivial.
wake_oom_reaper updates mm_to_reap with cmpxchg to guarantee only
NULL->mm transition and oom_reaper clear this atomically once it is done
with the work.  This means that only a single mm_struct can be reaped at
the time.  As the operation is potentially disruptive we are trying to
limit it to the ncessary minimum and the reaper blocks any updates while
it operates on an mm.  mm_struct is pinned by mm_count to allow parallel
exit_mmap and a race is detected by atomic_inc_not_zero(mm_users).

Signed-off-by: Michal Hocko <mhocko@suse.com>
Suggested-by: Oleg Nesterov <oleg@redhat.com>
Suggested-by: Mel Gorman <mgorman@suse.de>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Andrea Argangeli <andrea@kernel.org>
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>

include/linux/mm.h

@@ -1132,6 +1132,8 @@ struct zap_details {
 	struct address_space *check_mapping;	/* Check page->mapping if set */
 	pgoff_t	first_index;			/* Lowest page->index to unmap */
 	pgoff_t last_index;			/* Highest page->index to unmap */
+	bool ignore_dirty;			/* Ignore dirty pages */
+	bool check_swap_entries;		/* Check also swap entries */
 };
 
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,

mm/internal.h

@@ -38,6 +38,11 @@
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
 		unsigned long floor, unsigned long ceiling);
 
+void unmap_page_range(struct mmu_gather *tlb,
+			     struct vm_area_struct *vma,
+			     unsigned long addr, unsigned long end,
+			     struct zap_details *details);
+
 extern int __do_page_cache_readahead(struct address_space *mapping,
 		struct file *filp, pgoff_t offset, unsigned long nr_to_read,
 		unsigned long lookahead_size);

mm/memory.c

@@ -1102,6 +1102,12 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 
 			if (!PageAnon(page)) {
 				if (pte_dirty(ptent)) {
+					/*
+					 * oom_reaper cannot tear down dirty
+					 * pages
+					 */
+					if (unlikely(details && details->ignore_dirty))
+						continue;
 					force_flush = 1;
 					set_page_dirty(page);
 				}
@@ -1120,8 +1126,8 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			}
 			continue;
 		}
-		/* If details->check_mapping, we leave swap entries. */
+		/* only check swap_entries if explicitly asked for in details */
-		if (unlikely(details))
+		if (unlikely(details && !details->check_swap_entries))
 			continue;
 
 		entry = pte_to_swp_entry(ptent);
@@ -1226,7 +1232,7 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
 	return addr;
 }
 
-static void unmap_page_range(struct mmu_gather *tlb,
+void unmap_page_range(struct mmu_gather *tlb,
 			     struct vm_area_struct *vma,
 			     unsigned long addr, unsigned long end,
 			     struct zap_details *details)
@@ -1234,9 +1240,6 @@ static void unmap_page_range(struct mmu_gather *tlb,
 	pgd_t *pgd;
 	unsigned long next;
 
-	if (details && !details->check_mapping)
-		details = NULL;
-
 	BUG_ON(addr >= end);
 	tlb_start_vma(tlb, vma);
 	pgd = pgd_offset(vma->vm_mm, addr);
@@ -2432,7 +2435,7 @@ static inline void unmap_mapping_range_tree(struct rb_root *root,
 void unmap_mapping_range(struct address_space *mapping,
 		loff_t const holebegin, loff_t const holelen, int even_cows)
 {
-	struct zap_details details;
+	struct zap_details details = { };
 	pgoff_t hba = holebegin >> PAGE_SHIFT;
 	pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
 

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 +410,133 @@ static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait);
 
 bool oom_killer_disabled __read_mostly;
 
+#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 struct mm_struct *mm_to_reap;
+static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait);
+
+static bool __oom_reap_vmas(struct mm_struct *mm)
+{
+	struct mmu_gather tlb;
+	struct vm_area_struct *vma;
+	struct zap_details details = {.check_swap_entries = true,
+				      .ignore_dirty = true};
+	bool ret = true;
+
+	/* We might have raced with exit path */
+	if (!atomic_inc_not_zero(&mm->mm_users))
+		return true;
+
+	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);
+	up_read(&mm->mmap_sem);
+out:
+	mmput(mm);
+	return ret;
+}
+
+static void oom_reap_vmas(struct mm_struct *mm)
+{
+	int attempts = 0;
+
+	/* Retry the down_read_trylock(mmap_sem) a few times */
+	while (attempts++ < 10 && !__oom_reap_vmas(mm))
+		schedule_timeout_idle(HZ/10);
+
+	/* Drop a reference taken by wake_oom_reaper */
+	mmdrop(mm);
+}
+
+static int oom_reaper(void *unused)
+{
+	while (true) {
+		struct mm_struct *mm;
+
+		wait_event_freezable(oom_reaper_wait,
+				     (mm = READ_ONCE(mm_to_reap)));
+		oom_reap_vmas(mm);
+		WRITE_ONCE(mm_to_reap, NULL);
+	}
+
+	return 0;
+}
+
+static void wake_oom_reaper(struct mm_struct *mm)
+{
+	struct mm_struct *old_mm;
+
+	if (!oom_reaper_th)
+		return;
+
+	/*
+	 * Pin the given mm. Use mm_count instead of mm_users because
+	 * we do not want to delay the address space tear down.
+	 */
+	atomic_inc(&mm->mm_count);
+
+	/*
+	 * Make sure that only a single mm is ever queued for the reaper
+	 * because multiple are not necessary and the operation might be
+	 * disruptive so better reduce it to the bare minimum.
+	 */
+	old_mm = cmpxchg(&mm_to_reap, NULL, mm);
+	if (!old_mm)
+		wake_up(&oom_reaper_wait);
+	else
+		mmdrop(mm);
+}
+
+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 mm_struct *mm)
+{
+}
+#endif
+
 /**
  * mark_oom_victim - mark the given task as OOM victim
  * @tsk: task to mark
@@ -510,6 +642,7 @@ 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 +733,23 @@ 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))
+		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;
-		if (is_global_init(p))
+		}
-			continue;
-		if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
-			continue;
-
 		do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
 	}
 	rcu_read_unlock();
 
+	if (can_oom_reap)
+		wake_oom_reaper(mm);
+
 	mmdrop(mm);
 	put_task_struct(victim);
 }