Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "5 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm: correct the comment when reclaimed pages exceed the scanned pages
  userfaultfd: shmem: handle coredumping in handle_userfault()
  mm: numa: avoid waiting on freed migrated pages
  swap: cond_resched in swap_cgroup_prepare()
  mm/memory-failure.c: use compound_head() flags for huge pages

5 files changed, 38 insertions, 13 deletions

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index f7555fc25877..1d622f276e3a 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -340,9 +340,28 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	bool must_wait, return_to_userland;
 	long blocking_state;
 
-	BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
-
 	ret = VM_FAULT_SIGBUS;
+
+	/*
+	 * We don't do userfault handling for the final child pid update.
+	 *
+	 * We also don't do userfault handling during
+	 * coredumping. hugetlbfs has the special
+	 * follow_hugetlb_page() to skip missing pages in the
+	 * FOLL_DUMP case, anon memory also checks for FOLL_DUMP with
+	 * the no_page_table() helper in follow_page_mask(), but the
+	 * shmem_vm_ops->fault method is invoked even during
+	 * coredumping without mmap_sem and it ends up here.
+	 */
+	if (current->flags & (PF_EXITING|PF_DUMPCORE))
+		goto out;
+
+	/*
+	 * Coredumping runs without mmap_sem so we can only check that
+	 * the mmap_sem is held, if PF_DUMPCORE was not set.
+	 */
+	WARN_ON_ONCE(!rwsem_is_locked(&mm->mmap_sem));
+
 	ctx = vmf->vma->vm_userfaultfd_ctx.ctx;
 	if (!ctx)
 		goto out;
@@ -361,12 +380,6 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 		goto out;
 
 	/*
-	 * We don't do userfault handling for the final child pid update.
-	 */
-	if (current->flags & PF_EXITING)
-		goto out;
-
-	/*
 	 * Check that we can return VM_FAULT_RETRY.
 	 *
 	 * NOTE: it should become possible to return VM_FAULT_RETRY
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a84909cf20d3..88c6167f194d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1426,8 +1426,11 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
 	 */
 	if (unlikely(pmd_trans_migrating(*vmf->pmd))) {
 		page = pmd_page(*vmf->pmd);
+		if (!get_page_unless_zero(page))
+			goto out_unlock;
 		spin_unlock(vmf->ptl);
 		wait_on_page_locked(page);
+		put_page(page);
 		goto out;
 	}
 
@@ -1459,9 +1462,12 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
 
 	/* Migration could have started since the pmd_trans_migrating check */
 	if (!page_locked) {
+		page_nid = -1;
+		if (!get_page_unless_zero(page))
+			goto out_unlock;
 		spin_unlock(vmf->ptl);
 		wait_on_page_locked(page);
-		page_nid = -1;
+		put_page(page);
 		goto out;
 	}
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 342fac9ba89b..ecc183fd94f3 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1184,7 +1184,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	 * page_remove_rmap() in try_to_unmap_one(). So to determine page status
 	 * correctly, we save a copy of the page flags at this time.
 	 */
-	page_flags = p->flags;
+	if (PageHuge(p))
+		page_flags = hpage->flags;
+	else
+		page_flags = p->flags;
 
 	/*
 	 * unpoison always clear PG_hwpoison inside page lock
diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c
index ac6318a064d3..3405b4ee1757 100644
--- a/mm/swap_cgroup.c
+++ b/mm/swap_cgroup.c
@@ -48,6 +48,9 @@ static int swap_cgroup_prepare(int type)
 		if (!page)
 			goto not_enough_page;
 		ctrl->map[idx] = page;
+
+		if (!(idx % SWAP_CLUSTER_MAX))
+			cond_resched();
 	}
 	return 0;
 not_enough_page:
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index 6063581f705c..ce0618bfa8d0 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -115,9 +115,9 @@ static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned,
 	unsigned long pressure = 0;
 
 	/*
-	 * reclaimed can be greater than scanned in cases
-	 * like THP, where the scanned is 1 and reclaimed
-	 * could be 512
+	 * reclaimed can be greater than scanned for things such as reclaimed
+	 * slab pages. shrink_node() just adds reclaimed pages without a
+	 * related increment to scanned pages.
 	 */
 	if (reclaimed >= scanned)
 		goto out;