Merge tag 'v4.9.67' into linux-linaro-lsk-v4.9

 This is the 4.9.67 stable release

5 files changed, 29 insertions, 19 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8258e9eee806..3cae1dcf069c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -745,20 +745,15 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
 
 static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd)
+		pmd_t *pmd, int flags)
 {
 	pmd_t _pmd;
 
-	/*
-	 * We should set the dirty bit only for FOLL_WRITE but for now
-	 * the dirty bit in the pmd is meaningless.  And if the dirty
-	 * bit will become meaningful and we'll only set it with
-	 * FOLL_WRITE, an atomic set_bit will be required on the pmd to
-	 * set the young bit, instead of the current set_pmd_at.
-	 */
-	_pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
+	_pmd = pmd_mkyoung(*pmd);
+	if (flags & FOLL_WRITE)
+		_pmd = pmd_mkdirty(_pmd);
 	if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
-				pmd, _pmd,  1))
+				pmd, _pmd, flags & FOLL_WRITE))
 		update_mmu_cache_pmd(vma, addr, pmd);
 }
 
@@ -787,7 +782,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
 		return NULL;
 
 	if (flags & FOLL_TOUCH)
-		touch_pmd(vma, addr, pmd);
+		touch_pmd(vma, addr, pmd, flags);
 
 	/*
 	 * device mapped pages can only be returned if the
@@ -1158,7 +1153,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	page = pmd_page(*pmd);
 	VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
 	if (flags & FOLL_TOUCH)
-		touch_pmd(vma, addr, pmd);
+		touch_pmd(vma, addr, pmd, flags);
 	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
 		/*
 		 * We don't mlock() pte-mapped THPs. This way we can avoid
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 65c36acf8a6b..6ff65c405243 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3135,6 +3135,13 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 	}
 }
 
+static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr)
+{
+	if (addr & ~(huge_page_mask(hstate_vma(vma))))
+		return -EINVAL;
+	return 0;
+}
+
 /*
  * We cannot handle pagefaults against hugetlb pages at all.  They cause
  * handle_mm_fault() to try to instantiate regular-sized pages in the
@@ -3151,6 +3158,7 @@ const struct vm_operations_struct hugetlb_vm_ops = {
 	.fault = hugetlb_vm_op_fault,
 	.open = hugetlb_vm_op_open,
 	.close = hugetlb_vm_op_close,
+	.split = hugetlb_vm_op_split,
 };
 
 static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
diff --git a/mm/madvise.c b/mm/madvise.c
index 55f30ec32e5b..a49afe08698b 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -228,15 +228,14 @@ static long madvise_willneed(struct vm_area_struct *vma,
 {
 	struct file *file = vma->vm_file;
 
+	*prev = vma;
 #ifdef CONFIG_SWAP
 	if (!file) {
-		*prev = vma;
 		force_swapin_readahead(vma, start, end);
 		return 0;
 	}
 
 	if (shmem_mapping(file->f_mapping)) {
-		*prev = vma;
 		force_shm_swapin_readahead(vma, start, end,
 					file->f_mapping);
 		return 0;
@@ -251,7 +250,6 @@ static long madvise_willneed(struct vm_area_struct *vma,
 		return 0;
 	}
 
-	*prev = vma;
 	start = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 	if (end > vma->vm_end)
 		end = vma->vm_end;
diff --git a/mm/mmap.c b/mm/mmap.c
index 75d263bd8739..5b48adb4aa56 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2538,9 +2538,11 @@ static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct vm_area_struct *new;
 	int err;
 
-	if (is_vm_hugetlb_page(vma) && (addr &
-					~(huge_page_mask(hstate_vma(vma)))))
-		return -EINVAL;
+	if (vma->vm_ops && vma->vm_ops->split) {
+		err = vma->vm_ops->split(vma, addr);
+		if (err)
+			return err;
+	}
 
 	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
 	if (!new)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4a044134ce84..ef5ee56095e8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7309,11 +7309,18 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 
 	/*
 	 * In case of -EBUSY, we'd like to know which page causes problem.
-	 * So, just fall through. We will check it in test_pages_isolated().
+	 * So, just fall through. test_pages_isolated() has a tracepoint
+	 * which will report the busy page.
+	 *
+	 * It is possible that busy pages could become available before
+	 * the call to test_pages_isolated, and the range will actually be
+	 * allocated.  So, if we fall through be sure to clear ret so that
+	 * -EBUSY is not accidentally used or returned to caller.
 	 */
 	ret = __alloc_contig_migrate_range(&cc, start, end);
 	if (ret && ret != -EBUSY)
 		goto done;
+	ret =0;
 
 	/*
 	 * Pages from [start, end) are within a MAX_ORDER_NR_PAGES