1 files changed, 178 insertions, 72 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0a9ac6c26832..271e4432734c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -61,6 +61,9 @@ DEFINE_SPINLOCK(hugetlb_lock);
 static int num_fault_mutexes;
 static struct mutex *htlb_fault_mutex_table ____cacheline_aligned_in_smp;
 
+/* Forward declaration */
+static int hugetlb_acct_memory(struct hstate *h, long delta);
+
 static inline void unlock_or_release_subpool(struct hugepage_subpool *spool)
 {
 	bool free = (spool->count == 0) && (spool->used_hpages == 0);
@@ -68,23 +71,36 @@ static inline void unlock_or_release_subpool(struct hugepage_subpool *spool)
 	spin_unlock(&spool->lock);
 
 	/* If no pages are used, and no other handles to the subpool
-	 * remain, free the subpool the subpool remain */
-	if (free)
+	 * remain, give up any reservations mased on minimum size and
+	 * free the subpool */
+	if (free) {
+		if (spool->min_hpages != -1)
+			hugetlb_acct_memory(spool->hstate,
+						-spool->min_hpages);
 		kfree(spool);
+	}
 }
 
-struct hugepage_subpool *hugepage_new_subpool(long nr_blocks)
+struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
+						long min_hpages)
 {
 	struct hugepage_subpool *spool;
 
-	spool = kmalloc(sizeof(*spool), GFP_KERNEL);
+	spool = kzalloc(sizeof(*spool), GFP_KERNEL);
 	if (!spool)
 		return NULL;
 
 	spin_lock_init(&spool->lock);
 	spool->count = 1;
-	spool->max_hpages = nr_blocks;
-	spool->used_hpages = 0;
+	spool->max_hpages = max_hpages;
+	spool->hstate = h;
+	spool->min_hpages = min_hpages;
+
+	if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) {
+		kfree(spool);
+		return NULL;
+	}
+	spool->rsv_hpages = min_hpages;
 
 	return spool;
 }
@@ -97,36 +113,89 @@ void hugepage_put_subpool(struct hugepage_subpool *spool)
 	unlock_or_release_subpool(spool);
 }
 
-static int hugepage_subpool_get_pages(struct hugepage_subpool *spool,
+/*
+ * Subpool accounting for allocating and reserving pages.
+ * Return -ENOMEM if there are not enough resources to satisfy the
+ * the request.  Otherwise, return the number of pages by which the
+ * global pools must be adjusted (upward).  The returned value may
+ * only be different than the passed value (delta) in the case where
+ * a subpool minimum size must be manitained.
+ */
+static long hugepage_subpool_get_pages(struct hugepage_subpool *spool,
 				      long delta)
 {
-	int ret = 0;
+	long ret = delta;
 
 	if (!spool)
-		return 0;
+		return ret;
 
 	spin_lock(&spool->lock);
-	if ((spool->used_hpages + delta) <= spool->max_hpages) {
-		spool->used_hpages += delta;
-	} else {
-		ret = -ENOMEM;
+
+	if (spool->max_hpages != -1) {		/* maximum size accounting */
+		if ((spool->used_hpages + delta) <= spool->max_hpages)
+			spool->used_hpages += delta;
+		else {
+			ret = -ENOMEM;
+			goto unlock_ret;
+		}
 	}
-	spin_unlock(&spool->lock);
 
+	if (spool->min_hpages != -1) {		/* minimum size accounting */
+		if (delta > spool->rsv_hpages) {
+			/*
+			 * Asking for more reserves than those already taken on
+			 * behalf of subpool.  Return difference.
+			 */
+			ret = delta - spool->rsv_hpages;
+			spool->rsv_hpages = 0;
+		} else {
+			ret = 0;	/* reserves already accounted for */
+			spool->rsv_hpages -= delta;
+		}
+	}
+
+unlock_ret:
+	spin_unlock(&spool->lock);
 	return ret;
 }
 
-static void hugepage_subpool_put_pages(struct hugepage_subpool *spool,
+/*
+ * Subpool accounting for freeing and unreserving pages.
+ * Return the number of global page reservations that must be dropped.
+ * The return value may only be different than the passed value (delta)
+ * in the case where a subpool minimum size must be maintained.
+ */
+static long hugepage_subpool_put_pages(struct hugepage_subpool *spool,
 				       long delta)
 {
+	long ret = delta;
+
 	if (!spool)
-		return;
+		return delta;
 
 	spin_lock(&spool->lock);
-	spool->used_hpages -= delta;
-	/* If hugetlbfs_put_super couldn't free spool due to
-	* an outstanding quota reference, free it now. */
+
+	if (spool->max_hpages != -1)		/* maximum size accounting */
+		spool->used_hpages -= delta;
+
+	if (spool->min_hpages != -1) {		/* minimum size accounting */
+		if (spool->rsv_hpages + delta <= spool->min_hpages)
+			ret = 0;
+		else
+			ret = spool->rsv_hpages + delta - spool->min_hpages;
+
+		spool->rsv_hpages += delta;
+		if (spool->rsv_hpages > spool->min_hpages)
+			spool->rsv_hpages = spool->min_hpages;
+	}
+
+	/*
+	 * If hugetlbfs_put_super couldn't free spool due to an outstanding
+	 * quota reference, free it now.
+	 */
 	unlock_or_release_subpool(spool);
+
+	return ret;
 }
 
 static inline struct hugepage_subpool *subpool_inode(struct inode *inode)
@@ -855,6 +924,31 @@ struct hstate *size_to_hstate(unsigned long size)
 	return NULL;
 }
 
+/*
+ * Test to determine whether the hugepage is "active/in-use" (i.e. being linked
+ * to hstate->hugepage_activelist.)
+ *
+ * This function can be called for tail pages, but never returns true for them.
+ */
+bool page_huge_active(struct page *page)
+{
+	VM_BUG_ON_PAGE(!PageHuge(page), page);
+	return PageHead(page) && PagePrivate(&page[1]);
+}
+
+/* never called for tail page */
+static void set_page_huge_active(struct page *page)
+{
+	VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
+	SetPagePrivate(&page[1]);
+}
+
+static void clear_page_huge_active(struct page *page)
+{
+	VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
+	ClearPagePrivate(&page[1]);
+}
+
 void free_huge_page(struct page *page)
 {
 	/*
@@ -874,7 +968,16 @@ void free_huge_page(struct page *page)
 	restore_reserve = PagePrivate(page);
 	ClearPagePrivate(page);
 
+	/*
+	 * A return code of zero implies that the subpool will be under its
+	 * minimum size if the reservation is not restored after page is free.
+	 * Therefore, force restore_reserve operation.
+	 */
+	if (hugepage_subpool_put_pages(spool, 1) == 0)
+		restore_reserve = true;
+
 	spin_lock(&hugetlb_lock);
+	clear_page_huge_active(page);
 	hugetlb_cgroup_uncharge_page(hstate_index(h),
 				     pages_per_huge_page(h), page);
 	if (restore_reserve)
@@ -891,7 +994,6 @@ void free_huge_page(struct page *page)
 		enqueue_huge_page(h, page);
 	}
 	spin_unlock(&hugetlb_lock);
-	hugepage_subpool_put_pages(spool, 1);
 }
 
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
@@ -917,7 +1019,6 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
 	__SetPageHead(page);
 	__ClearPageReserved(page);
 	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
-		__SetPageTail(p);
 		/*
 		 * For gigantic hugepages allocated through bootmem at
 		 * boot, it's safer to be consistent with the not-gigantic
@@ -933,6 +1034,9 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
 		__ClearPageReserved(p);
 		set_page_count(p, 0);
 		p->first_page = page;
+		/* Make sure p->first_page is always valid for PageTail() */
+		smp_wmb();
+		__SetPageTail(p);
 	}
 }
 
@@ -1384,7 +1488,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	if (chg < 0)
 		return ERR_PTR(-ENOMEM);
 	if (chg || avoid_reserve)
-		if (hugepage_subpool_get_pages(spool, 1))
+		if (hugepage_subpool_get_pages(spool, 1) < 0)
 			return ERR_PTR(-ENOSPC);
 
 	ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg);
@@ -2452,6 +2556,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 	struct resv_map *resv = vma_resv_map(vma);
 	struct hugepage_subpool *spool = subpool_vma(vma);
 	unsigned long reserve, start, end;
+	long gbl_reserve;
 
 	if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER))
 		return;
@@ -2464,8 +2569,12 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 	kref_put(&resv->refs, resv_map_release);
 
 	if (reserve) {
-		hugetlb_acct_memory(h, -reserve);
-		hugepage_subpool_put_pages(spool, reserve);
+		/*
+		 * Decrement reserve counts.  The global reserve count may be
+		 * adjusted if the subpool has a minimum size.
+		 */
+		gbl_reserve = hugepage_subpool_put_pages(spool, reserve);
+		hugetlb_acct_memory(h, -gbl_reserve);
 	}
 }
 
@@ -2889,6 +2998,7 @@ retry_avoidcopy:
 	copy_user_huge_page(new_page, old_page, address, vma,
 			    pages_per_huge_page(h));
 	__SetPageUptodate(new_page);
+	set_page_huge_active(new_page);
 
 	mmun_start = address & huge_page_mask(h);
 	mmun_end = mmun_start + huge_page_size(h);
@@ -3001,6 +3111,7 @@ retry:
 		}
 		clear_huge_page(page, address, pages_per_huge_page(h));
 		__SetPageUptodate(page);
+		set_page_huge_active(page);
 
 		if (vma->vm_flags & VM_MAYSHARE) {
 			int err;
@@ -3276,6 +3387,15 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct page *page;
 
 		/*
+		 * If we have a pending SIGKILL, don't keep faulting pages and
+		 * potentially allocating memory.
+		 */
+		if (unlikely(fatal_signal_pending(current))) {
+			remainder = 0;
+			break;
+		}
+
+		/*
 		 * Some archs (sparc64, sh*) have multiple pte_ts to
 		 * each hugepage.  We have to make sure we get the
 		 * first, for the page indexing below to work.
@@ -3436,6 +3556,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 	struct hstate *h = hstate_inode(inode);
 	struct hugepage_subpool *spool = subpool_inode(inode);
 	struct resv_map *resv_map;
+	long gbl_reserve;
 
 	/*
 	 * Only apply hugepage reservation if asked. At fault time, an
@@ -3472,8 +3593,13 @@ int hugetlb_reserve_pages(struct inode *inode,
 		goto out_err;
 	}
 
-	/* There must be enough pages in the subpool for the mapping */
-	if (hugepage_subpool_get_pages(spool, chg)) {
+	/*
+	 * There must be enough pages in the subpool for the mapping. If
+	 * the subpool has a minimum size, there may be some global
+	 * reservations already in place (gbl_reserve).
+	 */
+	gbl_reserve = hugepage_subpool_get_pages(spool, chg);
+	if (gbl_reserve < 0) {
 		ret = -ENOSPC;
 		goto out_err;
 	}
@@ -3482,9 +3608,10 @@ int hugetlb_reserve_pages(struct inode *inode,
 	 * Check enough hugepages are available for the reservation.
 	 * Hand the pages back to the subpool if there are not
 	 */
-	ret = hugetlb_acct_memory(h, chg);
+	ret = hugetlb_acct_memory(h, gbl_reserve);
 	if (ret < 0) {
-		hugepage_subpool_put_pages(spool, chg);
+		/* put back original number of pages, chg */
+		(void)hugepage_subpool_put_pages(spool, chg);
 		goto out_err;
 	}
 
@@ -3514,6 +3641,7 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 	struct resv_map *resv_map = inode_resv_map(inode);
 	long chg = 0;
 	struct hugepage_subpool *spool = subpool_inode(inode);
+	long gbl_reserve;
 
 	if (resv_map)
 		chg = region_truncate(resv_map, offset);
@@ -3521,8 +3649,12 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 	inode->i_blocks -= (blocks_per_huge_page(h) * freed);
 	spin_unlock(&inode->i_lock);
 
-	hugepage_subpool_put_pages(spool, (chg - freed));
-	hugetlb_acct_memory(h, -(chg - freed));
+	/*
+	 * If the subpool has a minimum size, the number of global
+	 * reservations to be released may be adjusted.
+	 */
+	gbl_reserve = hugepage_subpool_put_pages(spool, (chg - freed));
+	hugetlb_acct_memory(h, -gbl_reserve);
 }
 
 #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
@@ -3733,8 +3865,7 @@ retry:
 	if (!pmd_huge(*pmd))
 		goto out;
 	if (pmd_present(*pmd)) {
-		page = pte_page(*(pte_t *)pmd) +
-			((address & ~PMD_MASK) >> PAGE_SHIFT);
+		page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT);
 		if (flags & FOLL_GET)
 			get_page(page);
 	} else {
@@ -3765,20 +3896,6 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address,
 
 #ifdef CONFIG_MEMORY_FAILURE
 
-/* Should be called in hugetlb_lock */
-static int is_hugepage_on_freelist(struct page *hpage)
-{
-	struct page *page;
-	struct page *tmp;
-	struct hstate *h = page_hstate(hpage);
-	int nid = page_to_nid(hpage);
-
-	list_for_each_entry_safe(page, tmp, &h->hugepage_freelists[nid], lru)
-		if (page == hpage)
-			return 1;
-	return 0;
-}
-
 /*
  * This function is called from memory failure code.
  * Assume the caller holds page lock of the head page.
@@ -3790,7 +3907,11 @@ int dequeue_hwpoisoned_huge_page(struct page *hpage)
 	int ret = -EBUSY;
 
 	spin_lock(&hugetlb_lock);
-	if (is_hugepage_on_freelist(hpage)) {
+	/*
+	 * Just checking !page_huge_active is not enough, because that could be
+	 * an isolated/hwpoisoned hugepage (which have >0 refcount).
+	 */
+	if (!page_huge_active(hpage) && !page_count(hpage)) {
 		/*
 		 * Hwpoisoned hugepage isn't linked to activelist or freelist,
 		 * but dangling hpage->lru can trigger list-debug warnings
@@ -3810,42 +3931,27 @@ int dequeue_hwpoisoned_huge_page(struct page *hpage)
 
 bool isolate_huge_page(struct page *page, struct list_head *list)
 {
+	bool ret = true;
+
 	VM_BUG_ON_PAGE(!PageHead(page), page);
-	if (!get_page_unless_zero(page))
-		return false;
 	spin_lock(&hugetlb_lock);
+	if (!page_huge_active(page) || !get_page_unless_zero(page)) {
+		ret = false;
+		goto unlock;
+	}
+	clear_page_huge_active(page);
 	list_move_tail(&page->lru, list);
+unlock:
 	spin_unlock(&hugetlb_lock);
-	return true;
+	return ret;
 }
 
 void putback_active_hugepage(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageHead(page), page);
 	spin_lock(&hugetlb_lock);
+	set_page_huge_active(page);
 	list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist);
 	spin_unlock(&hugetlb_lock);
 	put_page(page);
 }
-
-bool is_hugepage_active(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageHuge(page), page);
-	/*
-	 * This function can be called for a tail page because the caller,
-	 * scan_movable_pages, scans through a given pfn-range which typically
-	 * covers one memory block. In systems using gigantic hugepage (1GB
-	 * for x86_64,) a hugepage is larger than a memory block, and we don't
-	 * support migrating such large hugepages for now, so return false
-	 * when called for tail pages.
-	 */
-	if (PageTail(page))
-		return false;
-	/*
-	 * Refcount of a hwpoisoned hugepages is 1, but they are not active,
-	 * so we should return false for them.
-	 */
-	if (unlikely(PageHWPoison(page)))
-		return false;
-	return page_count(page) > 0;
-}