Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "10 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  x86/mm: split vmalloc_sync_all()
  mm, slub: prevent kmalloc_node crashes and memory leaks
  mm/mmu_notifier: silence PROVE_RCU_LIST warnings
  epoll: fix possible lost wakeup on epoll_ctl() path
  mm: do not allow MADV_PAGEOUT for CoW pages
  mm, memcg: throttle allocators based on ancestral memory.high
  mm, memcg: fix corruption on 64-bit divisor in memory.high throttling
  page-flags: fix a crash at SetPageError(THP_SWAP)
  mm/hotplug: fix hot remove failure in SPARSEMEM|!VMEMMAP case
  memcg: fix NULL pointer dereference in __mem_cgroup_usage_unregister_event

7 files changed, 130 insertions, 67 deletions

diff --git a/mm/madvise.c b/mm/madvise.c
index 43b47d3fae02..4bb30ed6c8d2 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -335,12 +335,14 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
 		}
 
 		page = pmd_page(orig_pmd);
+
+		/* Do not interfere with other mappings of this page */
+		if (page_mapcount(page) != 1)
+			goto huge_unlock;
+
 		if (next - addr != HPAGE_PMD_SIZE) {
 			int err;
 
-			if (page_mapcount(page) != 1)
-				goto huge_unlock;
-
 			get_page(page);
 			spin_unlock(ptl);
 			lock_page(page);
@@ -426,6 +428,10 @@ regular_page:
 			continue;
 		}
 
+		/* Do not interfere with other mappings of this page */
+		if (page_mapcount(page) != 1)
+			continue;
+
 		VM_BUG_ON_PAGE(PageTransCompound(page), page);
 
 		if (pte_young(ptent)) {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 2058b8da18db..7a4bd8b9adc2 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2297,28 +2297,41 @@ static void high_work_func(struct work_struct *work)
  #define MEMCG_DELAY_SCALING_SHIFT 14
 
 /*
- * Scheduled by try_charge() to be executed from the userland return path
- * and reclaims memory over the high limit.
+ * Get the number of jiffies that we should penalise a mischievous cgroup which
+ * is exceeding its memory.high by checking both it and its ancestors.
  */
-void mem_cgroup_handle_over_high(void)
+static unsigned long calculate_high_delay(struct mem_cgroup *memcg,
+					  unsigned int nr_pages)
 {
-	unsigned long usage, high, clamped_high;
-	unsigned long pflags;
-	unsigned long penalty_jiffies, overage;
-	unsigned int nr_pages = current->memcg_nr_pages_over_high;
-	struct mem_cgroup *memcg;
+	unsigned long penalty_jiffies;
+	u64 max_overage = 0;
 
-	if (likely(!nr_pages))
-		return;
+	do {
+		unsigned long usage, high;
+		u64 overage;
 
-	memcg = get_mem_cgroup_from_mm(current->mm);
-	reclaim_high(memcg, nr_pages, GFP_KERNEL);
-	current->memcg_nr_pages_over_high = 0;
+		usage = page_counter_read(&memcg->memory);
+		high = READ_ONCE(memcg->high);
+
+		/*
+		 * Prevent division by 0 in overage calculation by acting as if
+		 * it was a threshold of 1 page
+		 */
+		high = max(high, 1UL);
+
+		overage = usage - high;
+		overage <<= MEMCG_DELAY_PRECISION_SHIFT;
+		overage = div64_u64(overage, high);
+
+		if (overage > max_overage)
+			max_overage = overage;
+	} while ((memcg = parent_mem_cgroup(memcg)) &&
+		 !mem_cgroup_is_root(memcg));
+
+	if (!max_overage)
+		return 0;
 
 	/*
-	 * memory.high is breached and reclaim is unable to keep up. Throttle
-	 * allocators proactively to slow down excessive growth.
-	 *
 	 * We use overage compared to memory.high to calculate the number of
 	 * jiffies to sleep (penalty_jiffies). Ideally this value should be
 	 * fairly lenient on small overages, and increasingly harsh when the
@@ -2326,24 +2339,9 @@ void mem_cgroup_handle_over_high(void)
 	 * its crazy behaviour, so we exponentially increase the delay based on
 	 * overage amount.
 	 */
-
-	usage = page_counter_read(&memcg->memory);
-	high = READ_ONCE(memcg->high);
-
-	if (usage <= high)
-		goto out;
-
-	/*
-	 * Prevent division by 0 in overage calculation by acting as if it was a
-	 * threshold of 1 page
-	 */
-	clamped_high = max(high, 1UL);
-
-	overage = div_u64((u64)(usage - high) << MEMCG_DELAY_PRECISION_SHIFT,
-			  clamped_high);
-
-	penalty_jiffies = ((u64)overage * overage * HZ)
-		>> (MEMCG_DELAY_PRECISION_SHIFT + MEMCG_DELAY_SCALING_SHIFT);
+	penalty_jiffies = max_overage * max_overage * HZ;
+	penalty_jiffies >>= MEMCG_DELAY_PRECISION_SHIFT;
+	penalty_jiffies >>= MEMCG_DELAY_SCALING_SHIFT;
 
 	/*
 	 * Factor in the task's own contribution to the overage, such that four
@@ -2360,7 +2358,32 @@ void mem_cgroup_handle_over_high(void)
 	 * application moving forwards and also permit diagnostics, albeit
 	 * extremely slowly.
 	 */
-	penalty_jiffies = min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES);
+	return min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES);
+}
+
+/*
+ * Scheduled by try_charge() to be executed from the userland return path
+ * and reclaims memory over the high limit.
+ */
+void mem_cgroup_handle_over_high(void)
+{
+	unsigned long penalty_jiffies;
+	unsigned long pflags;
+	unsigned int nr_pages = current->memcg_nr_pages_over_high;
+	struct mem_cgroup *memcg;
+
+	if (likely(!nr_pages))
+		return;
+
+	memcg = get_mem_cgroup_from_mm(current->mm);
+	reclaim_high(memcg, nr_pages, GFP_KERNEL);
+	current->memcg_nr_pages_over_high = 0;
+
+	/*
+	 * memory.high is breached and reclaim is unable to keep up. Throttle
+	 * allocators proactively to slow down excessive growth.
+	 */
+	penalty_jiffies = calculate_high_delay(memcg, nr_pages);
 
 	/*
 	 * Don't sleep if the amount of jiffies this memcg owes us is so low
@@ -4027,7 +4050,7 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
 	struct mem_cgroup_thresholds *thresholds;
 	struct mem_cgroup_threshold_ary *new;
 	unsigned long usage;
-	int i, j, size;
+	int i, j, size, entries;
 
 	mutex_lock(&memcg->thresholds_lock);
 
@@ -4047,14 +4070,20 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
 	__mem_cgroup_threshold(memcg, type == _MEMSWAP);
 
 	/* Calculate new number of threshold */
-	size = 0;
+	size = entries = 0;
 	for (i = 0; i < thresholds->primary->size; i++) {
 		if (thresholds->primary->entries[i].eventfd != eventfd)
 			size++;
+		else
+			entries++;
 	}
 
 	new = thresholds->spare;
 
+	/* If no items related to eventfd have been cleared, nothing to do */
+	if (!entries)
+		goto unlock;
+
 	/* Set thresholds array to NULL if we don't have thresholds */
 	if (!size) {
 		kfree(new);
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index ef3973a5d34a..06852b896fa6 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -307,7 +307,8 @@ static void mn_hlist_release(struct mmu_notifier_subscriptions *subscriptions,
 	 * ->release returns.
 	 */
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist)
+	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist,
+				 srcu_read_lock_held(&srcu))
 		/*
 		 * If ->release runs before mmu_notifier_unregister it must be
 		 * handled, as it's the only way for the driver to flush all
@@ -370,7 +371,8 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
 
 	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(subscription,
-				 &mm->notifier_subscriptions->list, hlist) {
+				 &mm->notifier_subscriptions->list, hlist,
+				 srcu_read_lock_held(&srcu)) {
 		if (subscription->ops->clear_flush_young)
 			young |= subscription->ops->clear_flush_young(
 				subscription, mm, start, end);
@@ -389,7 +391,8 @@ int __mmu_notifier_clear_young(struct mm_struct *mm,
 
 	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(subscription,
-				 &mm->notifier_subscriptions->list, hlist) {
+				 &mm->notifier_subscriptions->list, hlist,
+				 srcu_read_lock_held(&srcu)) {
 		if (subscription->ops->clear_young)
 			young |= subscription->ops->clear_young(subscription,
 								mm, start, end);
@@ -407,7 +410,8 @@ int __mmu_notifier_test_young(struct mm_struct *mm,
 
 	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(subscription,
-				 &mm->notifier_subscriptions->list, hlist) {
+				 &mm->notifier_subscriptions->list, hlist,
+				 srcu_read_lock_held(&srcu)) {
 		if (subscription->ops->test_young) {
 			young = subscription->ops->test_young(subscription, mm,
 							      address);
@@ -428,7 +432,8 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
 
 	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(subscription,
-				 &mm->notifier_subscriptions->list, hlist) {
+				 &mm->notifier_subscriptions->list, hlist,
+				 srcu_read_lock_held(&srcu)) {
 		if (subscription->ops->change_pte)
 			subscription->ops->change_pte(subscription, mm, address,
 						      pte);
@@ -476,7 +481,8 @@ static int mn_hlist_invalidate_range_start(
 	int id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist) {
+	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist,
+				 srcu_read_lock_held(&srcu)) {
 		const struct mmu_notifier_ops *ops = subscription->ops;
 
 		if (ops->invalidate_range_start) {
@@ -528,7 +534,8 @@ mn_hlist_invalidate_end(struct mmu_notifier_subscriptions *subscriptions,
 	int id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist) {
+	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist,
+				 srcu_read_lock_held(&srcu)) {
 		/*
 		 * Call invalidate_range here too to avoid the need for the
 		 * subsystem of having to register an invalidate_range_end
@@ -582,7 +589,8 @@ void __mmu_notifier_invalidate_range(struct mm_struct *mm,
 
 	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(subscription,
-				 &mm->notifier_subscriptions->list, hlist) {
+				 &mm->notifier_subscriptions->list, hlist,
+				 srcu_read_lock_held(&srcu)) {
 		if (subscription->ops->invalidate_range)
 			subscription->ops->invalidate_range(subscription, mm,
 							    start, end);
@@ -714,7 +722,8 @@ find_get_mmu_notifier(struct mm_struct *mm, const struct mmu_notifier_ops *ops)
 
 	spin_lock(&mm->notifier_subscriptions->lock);
 	hlist_for_each_entry_rcu(subscription,
-				 &mm->notifier_subscriptions->list, hlist) {
+				 &mm->notifier_subscriptions->list, hlist,
+				 lockdep_is_held(&mm->notifier_subscriptions->lock)) {
 		if (subscription->ops != ops)
 			continue;
 
diff --git a/mm/nommu.c b/mm/nommu.c
index bd2b4e5ef144..318df4e236c9 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -370,10 +370,14 @@ void vm_unmap_aliases(void)
 EXPORT_SYMBOL_GPL(vm_unmap_aliases);
 
 /*
- * Implement a stub for vmalloc_sync_all() if the architecture chose not to
- * have one.
+ * Implement a stub for vmalloc_sync_[un]mapping() if the architecture
+ * chose not to have one.
  */
-void __weak vmalloc_sync_all(void)
+void __weak vmalloc_sync_mappings(void)
+{
+}
+
+void __weak vmalloc_sync_unmappings(void)
 {
 }
 
diff --git a/mm/slub.c b/mm/slub.c
index 97580b41a24b..6589b41d5a60 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1973,8 +1973,6 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
 
 	if (node == NUMA_NO_NODE)
 		searchnode = numa_mem_id();
-	else if (!node_present_pages(node))
-		searchnode = node_to_mem_node(node);
 
 	object = get_partial_node(s, get_node(s, searchnode), c, flags);
 	if (object || node != NUMA_NO_NODE)
@@ -2563,17 +2561,27 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	struct page *page;
 
 	page = c->page;
-	if (!page)
+	if (!page) {
+		/*
+		 * if the node is not online or has no normal memory, just
+		 * ignore the node constraint
+		 */
+		if (unlikely(node != NUMA_NO_NODE &&
+			     !node_state(node, N_NORMAL_MEMORY)))
+			node = NUMA_NO_NODE;
 		goto new_slab;
+	}
 redo:
 
 	if (unlikely(!node_match(page, node))) {
-		int searchnode = node;
-
-		if (node != NUMA_NO_NODE && !node_present_pages(node))
-			searchnode = node_to_mem_node(node);
-
-		if (unlikely(!node_match(page, searchnode))) {
+		/*
+		 * same as above but node_match() being false already
+		 * implies node != NUMA_NO_NODE
+		 */
+		if (!node_state(node, N_NORMAL_MEMORY)) {
+			node = NUMA_NO_NODE;
+			goto redo;
+		} else {
 			stat(s, ALLOC_NODE_MISMATCH);
 			deactivate_slab(s, page, c->freelist, c);
 			goto new_slab;
diff --git a/mm/sparse.c b/mm/sparse.c
index 596b2a45b100..aadb7298dcef 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -734,6 +734,7 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 	struct mem_section *ms = __pfn_to_section(pfn);
 	bool section_is_early = early_section(ms);
 	struct page *memmap = NULL;
+	bool empty;
 	unsigned long *subsection_map = ms->usage
 		? &ms->usage->subsection_map[0] : NULL;
 
@@ -764,7 +765,8 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 	 * For 2/ and 3/ the SPARSEMEM_VMEMMAP={y,n} cases are unified
 	 */
 	bitmap_xor(subsection_map, map, subsection_map, SUBSECTIONS_PER_SECTION);
-	if (bitmap_empty(subsection_map, SUBSECTIONS_PER_SECTION)) {
+	empty = bitmap_empty(subsection_map, SUBSECTIONS_PER_SECTION);
+	if (empty) {
 		unsigned long section_nr = pfn_to_section_nr(pfn);
 
 		/*
@@ -779,13 +781,15 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 			ms->usage = NULL;
 		}
 		memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
-		ms->section_mem_map = (unsigned long)NULL;
 	}
 
 	if (section_is_early && memmap)
 		free_map_bootmem(memmap);
 	else
 		depopulate_section_memmap(pfn, nr_pages, altmap);
+
+	if (empty)
+		ms->section_mem_map = (unsigned long)NULL;
 }
 
 static struct page * __meminit section_activate(int nid, unsigned long pfn,
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 1f46c3b86f9f..6b8eeb0ecee5 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1295,7 +1295,7 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
 	 * First make sure the mappings are removed from all page-tables
 	 * before they are freed.
 	 */
-	vmalloc_sync_all();
+	vmalloc_sync_unmappings();
 
 	/*
 	 * TODO: to calculate a flush range without looping.
@@ -3128,16 +3128,19 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 EXPORT_SYMBOL(remap_vmalloc_range);
 
 /*
- * Implement a stub for vmalloc_sync_all() if the architecture chose not to
- * have one.
+ * Implement stubs for vmalloc_sync_[un]mappings () if the architecture chose
+ * not to have one.
  *
  * The purpose of this function is to make sure the vmalloc area
  * mappings are identical in all page-tables in the system.
  */
-void __weak vmalloc_sync_all(void)
+void __weak vmalloc_sync_mappings(void)
 {
 }
 
+void __weak vmalloc_sync_unmappings(void)
+{
+}
 
 static int f(pte_t *pte, unsigned long addr, void *data)
 {