Merge branch 'akpm' (patches from Andrew)

Merge fixes from Andrew Morton:
 "7 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm/memory_hotplug.c: initialize per_cpu_nodestats for hotadded pgdats
  mm, oom: fix uninitialized ret in task_will_free_mem()
  kasan: remove the unnecessary WARN_ONCE from quarantine.c
  mm: memcontrol: fix memcg id ref counter on swap charge move
  mm: memcontrol: fix swap counter leak on swapout from offline cgroup
  proc, meminfo: use correct helpers for calculating LRU sizes in meminfo
  mm/hugetlb: fix incorrect hugepages count during mem hotplug

7 files changed, 64 insertions, 20 deletions

diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 09e18fdf61e5..b9a8c813e5e6 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -46,7 +46,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
                 cached = 0;
 
         for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
-                pages[lru] = global_page_state(NR_LRU_BASE + lru);
+                pages[lru] = global_node_page_state(NR_LRU_BASE + lru);
 
         available = si_mem_available();
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b9aa1b0b38b0..87e11d8ad536 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1448,6 +1448,7 @@ static void dissolve_free_huge_page(struct page *page)
                 list_del(&page->lru);
                 h->free_huge_pages--;
                 h->free_huge_pages_node[nid]--;
+                h->max_huge_pages--;
                 update_and_free_page(h, page);
         }
         spin_unlock(&hugetlb_lock);
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index b6728a33a4ac..baabaad4a4aa 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -217,11 +217,8 @@ void quarantine_reduce(void)
         new_quarantine_size = (READ_ONCE(totalram_pages) << PAGE_SHIFT) /
                 QUARANTINE_FRACTION;
         percpu_quarantines = QUARANTINE_PERCPU_SIZE * num_online_cpus();
-        if (WARN_ONCE(new_quarantine_size < percpu_quarantines,
-                "Too little memory, disabling global KASAN quarantine.\n"))
-                new_quarantine_size = 0;
-        else
-                new_quarantine_size -= percpu_quarantines;
+        new_quarantine_size = (new_quarantine_size < percpu_quarantines) ?
+                0 : new_quarantine_size - percpu_quarantines;
         WRITE_ONCE(quarantine_size, new_quarantine_size);
 
         last = global_quarantine.head;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e74d7080ec9e..2ff0289ad061 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4077,14 +4077,32 @@ static struct cftype mem_cgroup_legacy_files[] = {
 
 static DEFINE_IDR(mem_cgroup_idr);
 
-static void mem_cgroup_id_get(struct mem_cgroup *memcg)
+static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n)
 {
-        atomic_inc(&memcg->id.ref);
+        atomic_add(n, &memcg->id.ref);
 }
 
-static void mem_cgroup_id_put(struct mem_cgroup *memcg)
+static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
 {
-        if (atomic_dec_and_test(&memcg->id.ref)) {
+        while (!atomic_inc_not_zero(&memcg->id.ref)) {
+                /*
+                 * The root cgroup cannot be destroyed, so it's refcount must
+                 * always be >= 1.
+                 */
+                if (WARN_ON_ONCE(memcg == root_mem_cgroup)) {
+                        VM_BUG_ON(1);
+                        break;
+                }
+                memcg = parent_mem_cgroup(memcg);
+                if (!memcg)
+                        memcg = root_mem_cgroup;
+        }
+        return memcg;
+}
+
+static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n)
+{
+        if (atomic_sub_and_test(n, &memcg->id.ref)) {
                 idr_remove(&mem_cgroup_idr, memcg->id.id);
                 memcg->id.id = 0;
 
@@ -4093,6 +4111,16 @@ static void mem_cgroup_id_put(struct mem_cgroup *memcg)
         }
 }
 
+static inline void mem_cgroup_id_get(struct mem_cgroup *memcg)
+{
+        mem_cgroup_id_get_many(memcg, 1);
+}
+
+static inline void mem_cgroup_id_put(struct mem_cgroup *memcg)
+{
+        mem_cgroup_id_put_many(memcg, 1);
+}
+
 /**
  * mem_cgroup_from_id - look up a memcg from a memcg id
  * @id: the memcg id to look up
@@ -4727,6 +4755,8 @@ static void __mem_cgroup_clear_mc(void)
                 if (!mem_cgroup_is_root(mc.from))
                         page_counter_uncharge(&mc.from->memsw, mc.moved_swap);
 
+                mem_cgroup_id_put_many(mc.from, mc.moved_swap);
+
                 /*
                  * we charged both to->memory and to->memsw, so we
                  * should uncharge to->memory.
@@ -4734,9 +4764,9 @@ static void __mem_cgroup_clear_mc(void)
                 if (!mem_cgroup_is_root(mc.to))
                         page_counter_uncharge(&mc.to->memory, mc.moved_swap);
 
-                css_put_many(&mc.from->css, mc.moved_swap);
+                mem_cgroup_id_get_many(mc.to, mc.moved_swap);
+                css_put_many(&mc.to->css, mc.moved_swap);
 
-                /* we've already done css_get(mc.to) */
                 mc.moved_swap = 0;
         }
         memcg_oom_recover(from);
@@ -5800,7 +5830,7 @@ subsys_initcall(mem_cgroup_init);
  */
 void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 {
-        struct mem_cgroup *memcg;
+        struct mem_cgroup *memcg, *swap_memcg;
         unsigned short oldid;
 
         VM_BUG_ON_PAGE(PageLRU(page), page);
@@ -5815,16 +5845,27 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
         if (!memcg)
                 return;
 
-        mem_cgroup_id_get(memcg);
-        oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
+        /*
+         * In case the memcg owning these pages has been offlined and doesn't
+         * have an ID allocated to it anymore, charge the closest online
+         * ancestor for the swap instead and transfer the memory+swap charge.
+         */
+        swap_memcg = mem_cgroup_id_get_online(memcg);
+        oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg));
         VM_BUG_ON_PAGE(oldid, page);
-        mem_cgroup_swap_statistics(memcg, true);
+        mem_cgroup_swap_statistics(swap_memcg, true);
 
         page->mem_cgroup = NULL;
 
         if (!mem_cgroup_is_root(memcg))
                 page_counter_uncharge(&memcg->memory, 1);
 
+        if (memcg != swap_memcg) {
+                if (!mem_cgroup_is_root(swap_memcg))
+                        page_counter_charge(&swap_memcg->memsw, 1);
+                page_counter_uncharge(&memcg->memsw, 1);
+        }
+
         /*
          * Interrupts should be disabled here because the caller holds the
          * mapping->tree_lock lock which is taken with interrupts-off. It is
@@ -5863,11 +5904,14 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
         if (!memcg)
                 return 0;
 
+        memcg = mem_cgroup_id_get_online(memcg);
+
         if (!mem_cgroup_is_root(memcg) &&
-            !page_counter_try_charge(&memcg->swap, 1, &counter))
+            !page_counter_try_charge(&memcg->swap, 1, &counter)) {
+                mem_cgroup_id_put(memcg);
                 return -ENOMEM;
+        }
 
-        mem_cgroup_id_get(memcg);
         oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
         VM_BUG_ON_PAGE(oldid, page);
         mem_cgroup_swap_statistics(memcg, true);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 3894b65b1555..41266dc29f33 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1219,6 +1219,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 
         /* init node's zones as empty zones, we don't have any present pages.*/
         free_area_init_node(nid, zones_size, start_pfn, zholes_size);
+        pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat);
 
         /*
          * The node we allocated has no zone fallback lists. For avoiding
@@ -1249,6 +1250,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
 {
         arch_refresh_nodedata(nid, NULL);
+        free_percpu(pgdat->per_cpu_nodestats);
         arch_free_nodedata(pgdat);
         return;
 }
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 7d0a275df822..d53a9aa00977 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -764,7 +764,7 @@ bool task_will_free_mem(struct task_struct *task)
 {
         struct mm_struct *mm = task->mm;
         struct task_struct *p;
-        bool ret;
+        bool ret = true;
 
         /*
          * Skip tasks without mm because it might have passed its exit_mm and
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ab2c0ff8c2e6..3fbe73a6fe4b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4060,7 +4060,7 @@ long si_mem_available(void)
         int lru;
 
         for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
-                pages[lru] = global_page_state(NR_LRU_BASE + lru);
+                pages[lru] = global_node_page_state(NR_LRU_BASE + lru);
 
         for_each_zone(zone)
                 wmark_low += zone->watermark[WMARK_LOW];