Merge commit '3728e6a255b5' into patchwork

* commit '3728e6a255b5': (904 commits)
  Linux 4.14-rc5
  x86/microcode: Do the family check first
  locking/lockdep: Disable cross-release features for now
  x86/mm: Flush more aggressively in lazy TLB mode
  mm, swap: use page-cluster as max window of VMA based swap readahead
  mm: page_vma_mapped: ensure pmd is loaded with READ_ONCE outside of lock
  kmemleak: clear stale pointers from task stacks
  fs/binfmt_misc.c: node could be NULL when evicting inode
  fs/mpage.c: fix mpage_writepage() for pages with buffers
  linux/kernel.h: add/correct kernel-doc notation
  tty: fall back to N_NULL if switching to N_TTY fails during hangup
  Revert "vmalloc: back off when the current task is killed"
  mm/cma.c: take __GFP_NOWARN into account in cma_alloc()
  scripts/kallsyms.c: ignore symbol type 'n'
  userfaultfd: selftest: exercise -EEXIST only in background transfer
  mm: only display online cpus of the numa node
  mm: remove unnecessary WARN_ONCE in page_vma_mapped_walk().
  mm/mempolicy: fix NUMA_INTERLEAVE_HIT counter
  include/linux/of.h: provide of_n_{addr,size}_cells wrappers for !CONFIG_OF
  mm/madvise.c: add description for MADV_WIPEONFORK and MADV_KEEPONFORK
  ...

1 files changed, 17 insertions, 6 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 15af3da5af02..d5f3a62887cf 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1777,6 +1777,10 @@ static void drain_local_stock(struct work_struct *dummy)
 	struct memcg_stock_pcp *stock;
 	unsigned long flags;
 
+	/*
+	 * The only protection from memory hotplug vs. drain_stock races is
+	 * that we always operate on local CPU stock here with IRQ disabled
+	 */
 	local_irq_save(flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
@@ -1821,27 +1825,33 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
 	/* If someone's already draining, avoid adding running more workers. */
 	if (!mutex_trylock(&percpu_charge_mutex))
 		return;
-	/* Notify other cpus that system-wide "drain" is running */
-	get_online_cpus();
+	/*
+	 * Notify other cpus that system-wide "drain" is running
+	 * We do not care about races with the cpu hotplug because cpu down
+	 * as well as workers from this path always operate on the local
+	 * per-cpu data. CPU up doesn't touch memcg_stock at all.
+	 */
 	curcpu = get_cpu();
 	for_each_online_cpu(cpu) {
 		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
 		struct mem_cgroup *memcg;
 
 		memcg = stock->cached;
-		if (!memcg || !stock->nr_pages)
+		if (!memcg || !stock->nr_pages || !css_tryget(&memcg->css))
 			continue;
-		if (!mem_cgroup_is_descendant(memcg, root_memcg))
+		if (!mem_cgroup_is_descendant(memcg, root_memcg)) {
+			css_put(&memcg->css);
 			continue;
+		}
 		if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) {
 			if (cpu == curcpu)
 				drain_local_stock(&stock->work);
 			else
 				schedule_work_on(cpu, &stock->work);
 		}
+		css_put(&memcg->css);
 	}
 	put_cpu();
-	put_online_cpus();
 	mutex_unlock(&percpu_charge_mutex);
 }
 
@@ -5648,7 +5658,8 @@ static void uncharge_batch(const struct uncharge_gather *ug)
 static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 {
 	VM_BUG_ON_PAGE(PageLRU(page), page);
-	VM_BUG_ON_PAGE(!PageHWPoison(page) && page_count(page), page);
+	VM_BUG_ON_PAGE(page_count(page) && !is_zone_device_page(page) &&
+			!PageHWPoison(page) , page);
 
 	if (!page->mem_cgroup)
 		return;