[PATCH 10/18] mm, hugetlb: call vma_has_reserve() before entering alloc_huge_page()

[Joonsoo Kim]

To implement a graceful failure handling, we need to know whether
allocation request is for reserved pool or not, on higher level.
In this patch, we just move up vma_has_reseve() to caller function
in order to know it. There is no functional change.

Following patches implement a grace failure handling and remove
a hugetlb_instantiation_mutex.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a66226e..5f31ca5 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1123,12 +1123,12 @@ static void vma_commit_reservation(struct hstate *h,
 }
 
 static struct page *alloc_huge_page(struct vm_area_struct *vma,
-				    unsigned long addr, int avoid_reserve)
+				    unsigned long addr, int use_reserve)
 {
 	struct hugepage_subpool *spool = subpool_vma(vma);
 	struct hstate *h = hstate_vma(vma);
 	struct page *page;
-	int ret, idx, use_reserve;
+	int ret, idx;
 	struct hugetlb_cgroup *h_cg;
 
 	idx = hstate_index(h);
@@ -1140,11 +1140,6 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	 * need pages and subpool limit allocated allocated if no reserve
 	 * mapping overlaps.
 	 */
-	use_reserve = vma_has_reserves(h, vma, addr);
-	if (use_reserve < 0)
-		return ERR_PTR(-ENOMEM);
-
-	use_reserve = use_reserve && !avoid_reserve;
 	if (!use_reserve && (hugepage_subpool_get_pages(spool, 1) < 0))
 			return ERR_PTR(-ENOSPC);
 
@@ -2520,7 +2515,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	struct hstate *h = hstate_vma(vma);
 	struct page *old_page, *new_page;
-	int outside_reserve = 0;
+	int use_reserve, outside_reserve = 0;
 	unsigned long mmun_start;	/* For mmu_notifiers */
 	unsigned long mmun_end;		/* For mmu_notifiers */
 
@@ -2553,7 +2548,18 @@ retry_avoidcopy:
 
 	/* Drop page_table_lock as buddy allocator may be called */
 	spin_unlock(&mm->page_table_lock);
-	new_page = alloc_huge_page(vma, address, outside_reserve);
+
+	use_reserve = vma_has_reserves(h, vma, address);
+	if (use_reserve == -ENOMEM) {
+		page_cache_release(old_page);
+
+		/* Caller expects lock to be held */
+		spin_lock(&mm->page_table_lock);
+		return VM_FAULT_OOM;
+	}
+	use_reserve = use_reserve && !outside_reserve;
+
+	new_page = alloc_huge_page(vma, address, use_reserve);
 
 	if (IS_ERR(new_page)) {
 		long err = PTR_ERR(new_page);
@@ -2679,6 +2685,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page;
 	struct address_space *mapping;
 	pte_t new_pte;
+	int use_reserve = 0;
 
 	/*
 	 * Currently, we are forced to kill the process in the event the
@@ -2704,7 +2711,14 @@ retry:
 		size = i_size_read(mapping->host) >> huge_page_shift(h);
 		if (idx >= size)
 			goto out;
-		page = alloc_huge_page(vma, address, 0);
+
+		use_reserve = vma_has_reserves(h, vma, address);
+		if (use_reserve == -ENOMEM) {
+			ret = VM_FAULT_OOM;
+			goto out;
+		}
+
+		page = alloc_huge_page(vma, address, use_reserve);
 		if (IS_ERR(page)) {
 			ret = PTR_ERR(page);
 			if (ret == -ENOMEM)
-- 
1.7.9.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/