Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "13 patches.

  Subsystems affected by this patch series: mm (memory-failure, memcg,
  userfaultfd, hugetlbfs, mremap, oom-kill, kasan, hmm), and kcov"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm/mmu_notifier.c: fix race in mmu_interval_notifier_remove()
  kcov: don't generate a warning on vm_insert_page()'s failure
  MAINTAINERS: add Vincenzo Frascino to KASAN reviewers
  oom_kill.c: futex: delay the OOM reaper to allow time for proper futex cleanup
  selftest/vm: add skip support to mremap_test
  selftest/vm: support xfail in mremap_test
  selftest/vm: verify remap destination address in mremap_test
  selftest/vm: verify mmap addr in mremap_test
  mm, hugetlb: allow for "high" userspace addresses
  userfaultfd: mark uffd_wp regardless of VM_WRITE flag
  memcg: sync flush only if periodic flush is delayed
  mm/memory-failure.c: skip huge_zero_page in memory_failure()
  mm/hwpoison: fix race between hugetlb free/demotion and memory_failure_hugetlb()

8 files changed, 200 insertions, 73 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f8ca7cca3c1a..3fc721789743 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6785,6 +6785,16 @@ int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
 	return ret;
 }
 
+int get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+{
+	int ret;
+
+	spin_lock_irq(&hugetlb_lock);
+	ret = __get_huge_page_for_hwpoison(pfn, flags);
+	spin_unlock_irq(&hugetlb_lock);
+	return ret;
+}
+
 void putback_active_hugepage(struct page *page)
 {
 	spin_lock_irq(&hugetlb_lock);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 725f76723220..598fece89e2b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -587,6 +587,9 @@ static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork);
 static DEFINE_SPINLOCK(stats_flush_lock);
 static DEFINE_PER_CPU(unsigned int, stats_updates);
 static atomic_t stats_flush_threshold = ATOMIC_INIT(0);
+static u64 flush_next_time;
+
+#define FLUSH_TIME (2UL*HZ)
 
 /*
  * Accessors to ensure that preemption is disabled on PREEMPT_RT because it can
@@ -637,6 +640,7 @@ static void __mem_cgroup_flush_stats(void)
 	if (!spin_trylock_irqsave(&stats_flush_lock, flag))
 		return;
 
+	flush_next_time = jiffies_64 + 2*FLUSH_TIME;
 	cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup);
 	atomic_set(&stats_flush_threshold, 0);
 	spin_unlock_irqrestore(&stats_flush_lock, flag);
@@ -648,10 +652,16 @@ void mem_cgroup_flush_stats(void)
 		__mem_cgroup_flush_stats();
 }
 
+void mem_cgroup_flush_stats_delayed(void)
+{
+	if (time_after64(jiffies_64, flush_next_time))
+		mem_cgroup_flush_stats();
+}
+
 static void flush_memcg_stats_dwork(struct work_struct *w)
 {
 	__mem_cgroup_flush_stats();
-	queue_delayed_work(system_unbound_wq, &stats_flush_dwork, 2UL*HZ);
+	queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME);
 }
 
 /**
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index dcb6bb9cf731..27760c19bad7 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1498,50 +1498,113 @@ static int try_to_split_thp_page(struct page *page, const char *msg)
 	return 0;
 }
 
-static int memory_failure_hugetlb(unsigned long pfn, int flags)
+/*
+ * Called from hugetlb code with hugetlb_lock held.
+ *
+ * Return values:
+ *   0             - free hugepage
+ *   1             - in-use hugepage
+ *   2             - not a hugepage
+ *   -EBUSY        - the hugepage is busy (try to retry)
+ *   -EHWPOISON    - the hugepage is already hwpoisoned
+ */
+int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+{
+	struct page *page = pfn_to_page(pfn);
+	struct page *head = compound_head(page);
+	int ret = 2;	/* fallback to normal page handling */
+	bool count_increased = false;
+
+	if (!PageHeadHuge(head))
+		goto out;
+
+	if (flags & MF_COUNT_INCREASED) {
+		ret = 1;
+		count_increased = true;
+	} else if (HPageFreed(head) || HPageMigratable(head)) {
+		ret = get_page_unless_zero(head);
+		if (ret)
+			count_increased = true;
+	} else {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	if (TestSetPageHWPoison(head)) {
+		ret = -EHWPOISON;
+		goto out;
+	}
+
+	return ret;
+out:
+	if (count_increased)
+		put_page(head);
+	return ret;
+}
+
+#ifdef CONFIG_HUGETLB_PAGE
+/*
+ * Taking refcount of hugetlb pages needs extra care about race conditions
+ * with basic operations like hugepage allocation/free/demotion.
+ * So some of prechecks for hwpoison (pinning, and testing/setting
+ * PageHWPoison) should be done in single hugetlb_lock range.
+ */
+static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb)
 {
-	struct page *p = pfn_to_page(pfn);
-	struct page *head = compound_head(p);
 	int res;
+	struct page *p = pfn_to_page(pfn);
+	struct page *head;
 	unsigned long page_flags;
+	bool retry = true;
 
-	if (TestSetPageHWPoison(head)) {
-		pr_err("Memory failure: %#lx: already hardware poisoned\n",
-		       pfn);
-		res = -EHWPOISON;
-		if (flags & MF_ACTION_REQUIRED)
+	*hugetlb = 1;
+retry:
+	res = get_huge_page_for_hwpoison(pfn, flags);
+	if (res == 2) { /* fallback to normal page handling */
+		*hugetlb = 0;
+		return 0;
+	} else if (res == -EHWPOISON) {
+		pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn);
+		if (flags & MF_ACTION_REQUIRED) {
+			head = compound_head(p);
 			res = kill_accessing_process(current, page_to_pfn(head), flags);
+		}
+		return res;
+	} else if (res == -EBUSY) {
+		if (retry) {
+			retry = false;
+			goto retry;
+		}
+		action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED);
 		return res;
 	}
 
+	head = compound_head(p);
+	lock_page(head);
+
+	if (hwpoison_filter(p)) {
+		ClearPageHWPoison(head);
+		res = -EOPNOTSUPP;
+		goto out;
+	}
+
 	num_poisoned_pages_inc();
 
-	if (!(flags & MF_COUNT_INCREASED)) {
-		res = get_hwpoison_page(p, flags);
-		if (!res) {
-			lock_page(head);
-			if (hwpoison_filter(p)) {
-				if (TestClearPageHWPoison(head))
-					num_poisoned_pages_dec();
-				unlock_page(head);
-				return -EOPNOTSUPP;
-			}
-			unlock_page(head);
-			res = MF_FAILED;
-			if (__page_handle_poison(p)) {
-				page_ref_inc(p);
-				res = MF_RECOVERED;
-			}
-			action_result(pfn, MF_MSG_FREE_HUGE, res);
-			return res == MF_RECOVERED ? 0 : -EBUSY;
-		} else if (res < 0) {
-			action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED);
-			return -EBUSY;
+	/*
+	 * Handling free hugepage.  The possible race with hugepage allocation
+	 * or demotion can be prevented by PageHWPoison flag.
+	 */
+	if (res == 0) {
+		unlock_page(head);
+		res = MF_FAILED;
+		if (__page_handle_poison(p)) {
+			page_ref_inc(p);
+			res = MF_RECOVERED;
 		}
+		action_result(pfn, MF_MSG_FREE_HUGE, res);
+		return res == MF_RECOVERED ? 0 : -EBUSY;
 	}
 
-	lock_page(head);
-
 	/*
 	 * The page could have changed compound pages due to race window.
 	 * If this happens just bail out.
@@ -1554,14 +1617,6 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
 
 	page_flags = head->flags;
 
-	if (hwpoison_filter(p)) {
-		if (TestClearPageHWPoison(head))
-			num_poisoned_pages_dec();
-		put_page(p);
-		res = -EOPNOTSUPP;
-		goto out;
-	}
-
 	/*
 	 * TODO: hwpoison for pud-sized hugetlb doesn't work right now, so
 	 * simply disable it. In order to make it work properly, we need
@@ -1588,6 +1643,12 @@ out:
 	unlock_page(head);
 	return res;
 }
+#else
+static inline int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb)
+{
+	return 0;
+}
+#endif
 
 static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 		struct dev_pagemap *pgmap)
@@ -1712,6 +1773,7 @@ int memory_failure(unsigned long pfn, int flags)
 	int res = 0;
 	unsigned long page_flags;
 	bool retry = true;
+	int hugetlb = 0;
 
 	if (!sysctl_memory_failure_recovery)
 		panic("Memory failure on page %lx", pfn);
@@ -1739,10 +1801,9 @@ int memory_failure(unsigned long pfn, int flags)
 	}
 
 try_again:
-	if (PageHuge(p)) {
-		res = memory_failure_hugetlb(pfn, flags);
+	res = try_memory_failure_hugetlb(pfn, flags, &hugetlb);
+	if (hugetlb)
 		goto unlock_mutex;
-	}
 
 	if (TestSetPageHWPoison(p)) {
 		pr_err("Memory failure: %#lx: already hardware poisoned\n",
@@ -1800,6 +1861,19 @@ try_again:
 
 	if (PageTransHuge(hpage)) {
 		/*
+		 * Bail out before SetPageHasHWPoisoned() if hpage is
+		 * huge_zero_page, although PG_has_hwpoisoned is not
+		 * checked in set_huge_zero_page().
+		 *
+		 * TODO: Handle memory failure of huge_zero_page thoroughly.
+		 */
+		if (is_huge_zero_page(hpage)) {
+			action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED);
+			res = -EBUSY;
+			goto unlock_mutex;
+		}
+
+		/*
 		 * The flag must be set after the refcount is bumped
 		 * otherwise it may race with THP split.
 		 * And the flag can't be set in get_hwpoison_page() since
diff --git a/mm/mmap.c b/mm/mmap.c
index 3aa839f81e63..313b57d55a63 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2117,14 +2117,6 @@ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info)
 	return addr;
 }
 
-#ifndef arch_get_mmap_end
-#define arch_get_mmap_end(addr)	(TASK_SIZE)
-#endif
-
-#ifndef arch_get_mmap_base
-#define arch_get_mmap_base(addr, base) (base)
-#endif
-
 /* Get an address range which is currently unmapped.
  * For shmat() with addr=0.
  *
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 459d195d2ff6..f45ff1b7626a 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -1036,6 +1036,18 @@ int mmu_interval_notifier_insert_locked(
 }
 EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert_locked);
 
+static bool
+mmu_interval_seq_released(struct mmu_notifier_subscriptions *subscriptions,
+			  unsigned long seq)
+{
+	bool ret;
+
+	spin_lock(&subscriptions->lock);
+	ret = subscriptions->invalidate_seq != seq;
+	spin_unlock(&subscriptions->lock);
+	return ret;
+}
+
 /**
  * mmu_interval_notifier_remove - Remove a interval notifier
  * @interval_sub: Interval subscription to unregister
@@ -1083,7 +1095,7 @@ void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub)
 	lock_map_release(&__mmu_notifier_invalidate_range_start_map);
 	if (seq)
 		wait_event(subscriptions->wq,
-			   READ_ONCE(subscriptions->invalidate_seq) != seq);
+			   mmu_interval_seq_released(subscriptions, seq));
 
 	/* pairs with mmgrab in mmu_interval_notifier_insert() */
 	mmdrop(mm);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 7ec38194f8e1..49d7df39b02d 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -632,7 +632,7 @@ done:
 	 */
 	set_bit(MMF_OOM_SKIP, &mm->flags);
 
-	/* Drop a reference taken by wake_oom_reaper */
+	/* Drop a reference taken by queue_oom_reaper */
 	put_task_struct(tsk);
 }
 
@@ -644,12 +644,12 @@ static int oom_reaper(void *unused)
 		struct task_struct *tsk = NULL;
 
 		wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL);
-		spin_lock(&oom_reaper_lock);
+		spin_lock_irq(&oom_reaper_lock);
 		if (oom_reaper_list != NULL) {
 			tsk = oom_reaper_list;
 			oom_reaper_list = tsk->oom_reaper_list;
 		}
-		spin_unlock(&oom_reaper_lock);
+		spin_unlock_irq(&oom_reaper_lock);
 
 		if (tsk)
 			oom_reap_task(tsk);
@@ -658,22 +658,48 @@ static int oom_reaper(void *unused)
 	return 0;
 }
 
-static void wake_oom_reaper(struct task_struct *tsk)
+static void wake_oom_reaper(struct timer_list *timer)
 {
-	/* mm is already queued? */
-	if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags))
-		return;
+	struct task_struct *tsk = container_of(timer, struct task_struct,
+			oom_reaper_timer);
+	struct mm_struct *mm = tsk->signal->oom_mm;
+	unsigned long flags;
 
-	get_task_struct(tsk);
+	/* The victim managed to terminate on its own - see exit_mmap */
+	if (test_bit(MMF_OOM_SKIP, &mm->flags)) {
+		put_task_struct(tsk);
+		return;
+	}
 
-	spin_lock(&oom_reaper_lock);
+	spin_lock_irqsave(&oom_reaper_lock, flags);
 	tsk->oom_reaper_list = oom_reaper_list;
 	oom_reaper_list = tsk;
-	spin_unlock(&oom_reaper_lock);
+	spin_unlock_irqrestore(&oom_reaper_lock, flags);
 	trace_wake_reaper(tsk->pid);
 	wake_up(&oom_reaper_wait);
 }
 
+/*
+ * Give the OOM victim time to exit naturally before invoking the oom_reaping.
+ * The timers timeout is arbitrary... the longer it is, the longer the worst
+ * case scenario for the OOM can take. If it is too small, the oom_reaper can
+ * get in the way and release resources needed by the process exit path.
+ * e.g. The futex robust list can sit in Anon|Private memory that gets reaped
+ * before the exit path is able to wake the futex waiters.
+ */
+#define OOM_REAPER_DELAY (2*HZ)
+static void queue_oom_reaper(struct task_struct *tsk)
+{
+	/* mm is already queued? */
+	if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags))
+		return;
+
+	get_task_struct(tsk);
+	timer_setup(&tsk->oom_reaper_timer, wake_oom_reaper, 0);
+	tsk->oom_reaper_timer.expires = jiffies + OOM_REAPER_DELAY;
+	add_timer(&tsk->oom_reaper_timer);
+}
+
 static int __init oom_init(void)
 {
 	oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper");
@@ -681,7 +707,7 @@ static int __init oom_init(void)
 }
 subsys_initcall(oom_init)
 #else
-static inline void wake_oom_reaper(struct task_struct *tsk)
+static inline void queue_oom_reaper(struct task_struct *tsk)
 {
 }
 #endif /* CONFIG_MMU */
@@ -932,7 +958,7 @@ static void __oom_kill_process(struct task_struct *victim, const char *message)
 	rcu_read_unlock();
 
 	if (can_oom_reap)
-		wake_oom_reaper(victim);
+		queue_oom_reaper(victim);
 
 	mmdrop(mm);
 	put_task_struct(victim);
@@ -968,7 +994,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 	task_lock(victim);
 	if (task_will_free_mem(victim)) {
 		mark_oom_victim(victim);
-		wake_oom_reaper(victim);
+		queue_oom_reaper(victim);
 		task_unlock(victim);
 		put_task_struct(victim);
 		return;
@@ -1067,7 +1093,7 @@ bool out_of_memory(struct oom_control *oc)
 	 */
 	if (task_will_free_mem(current)) {
 		mark_oom_victim(current);
-		wake_oom_reaper(current);
+		queue_oom_reaper(current);
 		return true;
 	}
 
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 0cb8e5ef1713..e9bb6db002aa 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -72,12 +72,15 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
 	_dst_pte = pte_mkdirty(_dst_pte);
 	if (page_in_cache && !vm_shared)
 		writable = false;
-	if (writable) {
-		if (wp_copy)
-			_dst_pte = pte_mkuffd_wp(_dst_pte);
-		else
-			_dst_pte = pte_mkwrite(_dst_pte);
-	}
+
+	/*
+	 * Always mark a PTE as write-protected when needed, regardless of
+	 * VM_WRITE, which the user might change.
+	 */
+	if (wp_copy)
+		_dst_pte = pte_mkuffd_wp(_dst_pte);
+	else if (writable)
+		_dst_pte = pte_mkwrite(_dst_pte);
 
 	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
 
diff --git a/mm/workingset.c b/mm/workingset.c
index 8a3828acc0bf..592569a8974c 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -355,7 +355,7 @@ void workingset_refault(struct folio *folio, void *shadow)
 
 	mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr);
 
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats_delayed();
 	/*
 	 * Compare the distance to the existing workingset size. We
 	 * don't activate pages that couldn't stay resident even if