1 files changed, 67 insertions, 23 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 44970b17f4fe..86a5c9852acf 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -66,6 +66,21 @@ DEFINE_SPINLOCK(hugetlb_lock);
 static int num_fault_mutexes;
 struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp;
 
+static inline bool PageHugeFreed(struct page *head)
+{
+	return page_private(head + 4) == -1UL;
+}
+
+static inline void SetPageHugeFreed(struct page *head)
+{
+	set_page_private(head + 4, -1UL);
+}
+
+static inline void ClearPageHugeFreed(struct page *head)
+{
+	set_page_private(head + 4, 0);
+}
+
 /* Forward declaration */
 static int hugetlb_acct_memory(struct hstate *h, long delta);
 
@@ -841,6 +856,7 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
 	list_move(&page->lru, &h->hugepage_freelists[nid]);
 	h->free_huge_pages++;
 	h->free_huge_pages_node[nid]++;
+	SetPageHugeFreed(page);
 }
 
 static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
@@ -858,6 +874,7 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
 		return NULL;
 	list_move(&page->lru, &h->hugepage_activelist);
 	set_page_refcounted(page);
+	ClearPageHugeFreed(page);
 	h->free_huge_pages--;
 	h->free_huge_pages_node[nid]--;
 	return page;
@@ -1142,14 +1159,16 @@ static inline int alloc_fresh_gigantic_page(struct hstate *h,
 static void update_and_free_page(struct hstate *h, struct page *page)
 {
 	int i;
+	struct page *subpage = page;
 
 	if (hstate_is_gigantic(h) && !gigantic_page_supported())
 		return;
 
 	h->nr_huge_pages--;
 	h->nr_huge_pages_node[page_to_nid(page)]--;
-	for (i = 0; i < pages_per_huge_page(h); i++) {
-		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
+	for (i = 0; i < pages_per_huge_page(h);
+	     i++, subpage = mem_map_next(subpage, page, i)) {
+		subpage->flags &= ~(1 << PG_locked | 1 << PG_error |
 				1 << PG_referenced | 1 << PG_dirty |
 				1 << PG_active | 1 << PG_private |
 				1 << PG_writeback);
@@ -1184,12 +1203,11 @@ struct hstate *size_to_hstate(unsigned long size)
  */
 bool page_huge_active(struct page *page)
 {
-	VM_BUG_ON_PAGE(!PageHuge(page), page);
-	return PageHead(page) && PagePrivate(&page[1]);
+	return PageHeadHuge(page) && PagePrivate(&page[1]);
 }
 
 /* never called for tail page */
-static void set_page_huge_active(struct page *page)
+void set_page_huge_active(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
 	SetPagePrivate(&page[1]);
@@ -1267,6 +1285,7 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 	set_hugetlb_cgroup(page, NULL);
 	h->nr_huge_pages++;
 	h->nr_huge_pages_node[nid]++;
+	ClearPageHugeFreed(page);
 	spin_unlock(&hugetlb_lock);
 	put_page(page); /* free it into the hugepage allocator */
 }
@@ -1425,11 +1444,32 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
  */
 static void dissolve_free_huge_page(struct page *page)
 {
+retry:
 	spin_lock(&hugetlb_lock);
 	if (PageHuge(page) && !page_count(page)) {
 		struct page *head = compound_head(page);
 		struct hstate *h = page_hstate(head);
 		int nid = page_to_nid(head);
+
+		/*
+		 * We should make sure that the page is already on the free list
+		 * when it is dissolved.
+		 */
+		if (unlikely(!PageHugeFreed(head))) {
+			spin_unlock(&hugetlb_lock);
+			cond_resched();
+
+			/*
+			 * Theoretically, we should return -EBUSY when we
+			 * encounter this race. In fact, we have a chance
+			 * to successfully dissolve the page if we do a
+			 * retry. Because the race window is quite small.
+			 * If we seize this opportunity, it is an optimization
+			 * for increasing the success rate of dissolving page.
+			 */
+			goto retry;
+		}
+
 		list_del(&head->lru);
 		h->free_huge_pages--;
 		h->free_huge_pages_node[nid]--;
@@ -2486,8 +2526,10 @@ static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent,
 		return -ENOMEM;
 
 	retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group);
-	if (retval)
+	if (retval) {
 		kobject_put(hstate_kobjs[hi]);
+		hstate_kobjs[hi] = NULL;
+	}
 
 	return retval;
 }
@@ -3659,7 +3701,7 @@ retry:
 		 * So we need to block hugepage fault by PG_hwpoison bit check.
 		 */
 		if (unlikely(PageHWPoison(page))) {
-			ret = VM_FAULT_HWPOISON |
+			ret = VM_FAULT_HWPOISON_LARGE |
 				VM_FAULT_SET_HINDEX(hstate_index(h));
 			goto backout_unlocked;
 		}
@@ -3729,7 +3771,7 @@ backout_unlocked:
 
 #ifdef CONFIG_SMP
 u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
-			    pgoff_t idx, unsigned long address)
+			    pgoff_t idx)
 {
 	unsigned long key[2];
 	u32 hash;
@@ -3737,7 +3779,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
 	key[0] = (unsigned long) mapping;
 	key[1] = idx;
 
-	hash = jhash2((u32 *)&key, sizeof(key)/sizeof(u32), 0);
+	hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0);
 
 	return hash & (num_fault_mutexes - 1);
 }
@@ -3747,7 +3789,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
  * return 0 and avoid the hashing overhead.
  */
 u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
-			    pgoff_t idx, unsigned long address)
+			    pgoff_t idx)
 {
 	return 0;
 }
@@ -3792,7 +3834,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * get spurious allocation failures if two CPUs race to instantiate
 	 * the same page in the page cache.
 	 */
-	hash = hugetlb_fault_mutex_hash(h, mapping, idx, address);
+	hash = hugetlb_fault_mutex_hash(h, mapping, idx);
 	mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 	entry = huge_ptep_get(ptep);
@@ -4280,21 +4322,23 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr)
 void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end)
 {
-	unsigned long a_start, a_end;
+	unsigned long v_start = ALIGN(vma->vm_start, PUD_SIZE),
+		v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE);
 
-	if (!(vma->vm_flags & VM_MAYSHARE))
+	/*
+	 * vma need span at least one aligned PUD size and the start,end range
+	 * must at least partialy within it.
+	 */
+	if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) ||
+		(*end <= v_start) || (*start >= v_end))
 		return;
 
 	/* Extend the range to be PUD aligned for a worst case scenario */
-	a_start = ALIGN_DOWN(*start, PUD_SIZE);
-	a_end = ALIGN(*end, PUD_SIZE);
+	if (*start > v_start)
+		*start = ALIGN_DOWN(*start, PUD_SIZE);
 
-	/*
-	 * Intersect the range with the vma range, since pmd sharing won't be
-	 * across vma after all
-	 */
-	*start = max(vma->vm_start, a_start);
-	*end = min(vma->vm_end, a_end);
+	if (*end < v_end)
+		*end = ALIGN(*end, PUD_SIZE);
 }
 
 /*
@@ -4544,9 +4588,9 @@ bool isolate_huge_page(struct page *page, struct list_head *list)
 {
 	bool ret = true;
 
-	VM_BUG_ON_PAGE(!PageHead(page), page);
 	spin_lock(&hugetlb_lock);
-	if (!page_huge_active(page) || !get_page_unless_zero(page)) {
+	if (!PageHeadHuge(page) || !page_huge_active(page) ||
+	    !get_page_unless_zero(page)) {
 		ret = false;
 		goto unlock;
 	}