1 files changed, 289 insertions, 72 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 103f1187043f..924553aa8f78 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -30,6 +30,7 @@
 #include <linux/numa.h>
 #include <linux/llist.h>
 #include <linux/cma.h>
+#include <linux/migrate.h>
 
 #include <asm/page.h>
 #include <asm/pgalloc.h>
@@ -41,6 +42,7 @@
 #include <linux/node.h>
 #include <linux/page_owner.h>
 #include "internal.h"
+#include "hugetlb_vmemmap.h"
 
 int hugetlb_max_hstate __read_mostly;
 unsigned int default_hstate_idx;
@@ -1318,8 +1320,6 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
 	return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask);
 }
 
-static void prep_new_huge_page(struct hstate *h, struct page *page, int nid);
-static void prep_compound_gigantic_page(struct page *page, unsigned int order);
 #else /* !CONFIG_CONTIG_ALLOC */
 static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
 					int nid, nodemask_t *nodemask)
@@ -1375,7 +1375,40 @@ static void remove_hugetlb_page(struct hstate *h, struct page *page,
 	h->nr_huge_pages_node[nid]--;
 }
 
-static void update_and_free_page(struct hstate *h, struct page *page)
+static void add_hugetlb_page(struct hstate *h, struct page *page,
+			     bool adjust_surplus)
+{
+	int zeroed;
+	int nid = page_to_nid(page);
+
+	VM_BUG_ON_PAGE(!HPageVmemmapOptimized(page), page);
+
+	lockdep_assert_held(&hugetlb_lock);
+
+	INIT_LIST_HEAD(&page->lru);
+	h->nr_huge_pages++;
+	h->nr_huge_pages_node[nid]++;
+
+	if (adjust_surplus) {
+		h->surplus_huge_pages++;
+		h->surplus_huge_pages_node[nid]++;
+	}
+
+	set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
+	set_page_private(page, 0);
+	SetHPageVmemmapOptimized(page);
+
+	/*
+	 * This page is now managed by the hugetlb allocator and has
+	 * no users -- drop the last reference.
+	 */
+	zeroed = put_page_testzero(page);
+	VM_BUG_ON_PAGE(!zeroed, page);
+	arch_clear_hugepage_flags(page);
+	enqueue_huge_page(h, page);
+}
+
+static void __update_and_free_page(struct hstate *h, struct page *page)
 {
 	int i;
 	struct page *subpage = page;
@@ -1383,6 +1416,18 @@ static void update_and_free_page(struct hstate *h, struct page *page)
 	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
 		return;
 
+	if (alloc_huge_page_vmemmap(h, page)) {
+		spin_lock_irq(&hugetlb_lock);
+		/*
+		 * If we cannot allocate vmemmap pages, just refuse to free the
+		 * page and put the page back on the hugetlb free list and treat
+		 * as a surplus page.
+		 */
+		add_hugetlb_page(h, page, true);
+		spin_unlock_irq(&hugetlb_lock);
+		return;
+	}
+
 	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 |
@@ -1398,12 +1443,79 @@ static void update_and_free_page(struct hstate *h, struct page *page)
 	}
 }
 
+/*
+ * As update_and_free_page() can be called under any context, so we cannot
+ * use GFP_KERNEL to allocate vmemmap pages. However, we can defer the
+ * actual freeing in a workqueue to prevent from using GFP_ATOMIC to allocate
+ * the vmemmap pages.
+ *
+ * free_hpage_workfn() locklessly retrieves the linked list of pages to be
+ * freed and frees them one-by-one. As the page->mapping pointer is going
+ * to be cleared in free_hpage_workfn() anyway, it is reused as the llist_node
+ * structure of a lockless linked list of huge pages to be freed.
+ */
+static LLIST_HEAD(hpage_freelist);
+
+static void free_hpage_workfn(struct work_struct *work)
+{
+	struct llist_node *node;
+
+	node = llist_del_all(&hpage_freelist);
+
+	while (node) {
+		struct page *page;
+		struct hstate *h;
+
+		page = container_of((struct address_space **)node,
+				     struct page, mapping);
+		node = node->next;
+		page->mapping = NULL;
+		/*
+		 * The VM_BUG_ON_PAGE(!PageHuge(page), page) in page_hstate()
+		 * is going to trigger because a previous call to
+		 * remove_hugetlb_page() will set_compound_page_dtor(page,
+		 * NULL_COMPOUND_DTOR), so do not use page_hstate() directly.
+		 */
+		h = size_to_hstate(page_size(page));
+
+		__update_and_free_page(h, page);
+
+		cond_resched();
+	}
+}
+static DECLARE_WORK(free_hpage_work, free_hpage_workfn);
+
+static inline void flush_free_hpage_work(struct hstate *h)
+{
+	if (free_vmemmap_pages_per_hpage(h))
+		flush_work(&free_hpage_work);
+}
+
+static void update_and_free_page(struct hstate *h, struct page *page,
+				 bool atomic)
+{
+	if (!HPageVmemmapOptimized(page) || !atomic) {
+		__update_and_free_page(h, page);
+		return;
+	}
+
+	/*
+	 * Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap pages.
+	 *
+	 * Only call schedule_work() if hpage_freelist is previously
+	 * empty. Otherwise, schedule_work() had been called but the workfn
+	 * hasn't retrieved the list yet.
+	 */
+	if (llist_add((struct llist_node *)&page->mapping, &hpage_freelist))
+		schedule_work(&free_hpage_work);
+}
+
 static void update_and_free_pages_bulk(struct hstate *h, struct list_head *list)
 {
 	struct page *page, *t_page;
 
 	list_for_each_entry_safe(page, t_page, list, lru) {
-		update_and_free_page(h, page);
+		update_and_free_page(h, page, false);
 		cond_resched();
 	}
 }
@@ -1470,12 +1582,12 @@ void free_huge_page(struct page *page)
 	if (HPageTemporary(page)) {
 		remove_hugetlb_page(h, page, false);
 		spin_unlock_irqrestore(&hugetlb_lock, flags);
-		update_and_free_page(h, page);
+		update_and_free_page(h, page, true);
 	} else if (h->surplus_huge_pages_node[nid]) {
 		/* remove the page from active list */
 		remove_hugetlb_page(h, page, true);
 		spin_unlock_irqrestore(&hugetlb_lock, flags);
-		update_and_free_page(h, page);
+		update_and_free_page(h, page, true);
 	} else {
 		arch_clear_hugepage_flags(page);
 		enqueue_huge_page(h, page);
@@ -1493,8 +1605,9 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid)
 	h->nr_huge_pages_node[nid]++;
 }
 
-static void __prep_new_huge_page(struct page *page)
+static void __prep_new_huge_page(struct hstate *h, struct page *page)
 {
+	free_huge_page_vmemmap(h, page);
 	INIT_LIST_HEAD(&page->lru);
 	set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
 	hugetlb_set_page_subpool(page, NULL);
@@ -1504,15 +1617,15 @@ static void __prep_new_huge_page(struct page *page)
 
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 {
-	__prep_new_huge_page(page);
+	__prep_new_huge_page(h, page);
 	spin_lock_irq(&hugetlb_lock);
 	__prep_account_new_huge_page(h, nid);
 	spin_unlock_irq(&hugetlb_lock);
 }
 
-static void prep_compound_gigantic_page(struct page *page, unsigned int order)
+static bool prep_compound_gigantic_page(struct page *page, unsigned int order)
 {
-	int i;
+	int i, j;
 	int nr_pages = 1 << order;
 	struct page *p = page + 1;
 
@@ -1534,11 +1647,48 @@ static void prep_compound_gigantic_page(struct page *page, unsigned int order)
 		 * after get_user_pages().
 		 */
 		__ClearPageReserved(p);
+		/*
+		 * Subtle and very unlikely
+		 *
+		 * Gigantic 'page allocators' such as memblock or cma will
+		 * return a set of pages with each page ref counted.  We need
+		 * to turn this set of pages into a compound page with tail
+		 * page ref counts set to zero.  Code such as speculative page
+		 * cache adding could take a ref on a 'to be' tail page.
+		 * We need to respect any increased ref count, and only set
+		 * the ref count to zero if count is currently 1.  If count
+		 * is not 1, we call synchronize_rcu in the hope that a rcu
+		 * grace period will cause ref count to drop and then retry.
+		 * If count is still inflated on retry we return an error and
+		 * must discard the pages.
+		 */
+		if (!page_ref_freeze(p, 1)) {
+			pr_info("HugeTLB unexpected inflated ref count on freshly allocated page\n");
+			synchronize_rcu();
+			if (!page_ref_freeze(p, 1))
+				goto out_error;
+		}
 		set_page_count(p, 0);
 		set_compound_head(p, page);
 	}
 	atomic_set(compound_mapcount_ptr(page), -1);
 	atomic_set(compound_pincount_ptr(page), 0);
+	return true;
+
+out_error:
+	/* undo tail page modifications made above */
+	p = page + 1;
+	for (j = 1; j < i; j++, p = mem_map_next(p, page, j)) {
+		clear_compound_head(p);
+		set_page_refcounted(p);
+	}
+	/* need to clear PG_reserved on remaining tail pages  */
+	for (; j < nr_pages; j++, p = mem_map_next(p, page, j))
+		__ClearPageReserved(p);
+	set_compound_order(page, 0);
+	page[1].compound_nr = 0;
+	__ClearPageHead(page);
+	return false;
 }
 
 /*
@@ -1658,7 +1808,9 @@ static struct page *alloc_fresh_huge_page(struct hstate *h,
 		nodemask_t *node_alloc_noretry)
 {
 	struct page *page;
+	bool retry = false;
 
+retry:
 	if (hstate_is_gigantic(h))
 		page = alloc_gigantic_page(h, gfp_mask, nid, nmask);
 	else
@@ -1667,8 +1819,21 @@ static struct page *alloc_fresh_huge_page(struct hstate *h,
 	if (!page)
 		return NULL;
 
-	if (hstate_is_gigantic(h))
-		prep_compound_gigantic_page(page, huge_page_order(h));
+	if (hstate_is_gigantic(h)) {
+		if (!prep_compound_gigantic_page(page, huge_page_order(h))) {
+			/*
+			 * Rare failure to convert pages to compound page.
+			 * Free pages and try again - ONCE!
+			 */
+			free_gigantic_page(page, huge_page_order(h));
+			if (!retry) {
+				retry = true;
+				goto retry;
+			}
+			pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n");
+			return NULL;
+		}
+	}
 	prep_new_huge_page(h, page, page_to_nid(page));
 
 	return page;
@@ -1737,10 +1902,14 @@ static struct page *remove_pool_huge_page(struct hstate *h,
  * nothing for in-use hugepages and non-hugepages.
  * This function returns values like below:
  *
- *  -EBUSY: failed to dissolved free hugepages or the hugepage is in-use
- *          (allocated or reserved.)
- *       0: successfully dissolved free hugepages or the page is not a
- *          hugepage (considered as already dissolved)
+ *  -ENOMEM: failed to allocate vmemmap pages to free the freed hugepages
+ *           when the system is under memory pressure and the feature of
+ *           freeing unused vmemmap pages associated with each hugetlb page
+ *           is enabled.
+ *  -EBUSY:  failed to dissolved free hugepages or the hugepage is in-use
+ *           (allocated or reserved.)
+ *       0:  successfully dissolved free hugepages or the page is not a
+ *           hugepage (considered as already dissolved)
  */
 int dissolve_free_huge_page(struct page *page)
 {
@@ -1782,19 +1951,38 @@ retry:
 			goto retry;
 		}
 
-		/*
-		 * Move PageHWPoison flag from head page to the raw error page,
-		 * which makes any subpages rather than the error page reusable.
-		 */
-		if (PageHWPoison(head) && page != head) {
-			SetPageHWPoison(page);
-			ClearPageHWPoison(head);
-		}
 		remove_hugetlb_page(h, head, false);
 		h->max_huge_pages--;
 		spin_unlock_irq(&hugetlb_lock);
-		update_and_free_page(h, head);
-		return 0;
+
+		/*
+		 * Normally update_and_free_page will allocate required vmemmmap
+		 * before freeing the page.  update_and_free_page will fail to
+		 * free the page if it can not allocate required vmemmap.  We
+		 * need to adjust max_huge_pages if the page is not freed.
+		 * Attempt to allocate vmemmmap here so that we can take
+		 * appropriate action on failure.
+		 */
+		rc = alloc_huge_page_vmemmap(h, head);
+		if (!rc) {
+			/*
+			 * Move PageHWPoison flag from head page to the raw
+			 * error page, which makes any subpages rather than
+			 * the error page reusable.
+			 */
+			if (PageHWPoison(head) && page != head) {
+				SetPageHWPoison(page);
+				ClearPageHWPoison(head);
+			}
+			update_and_free_page(h, head, false);
+		} else {
+			spin_lock_irq(&hugetlb_lock);
+			add_hugetlb_page(h, head, false);
+			h->max_huge_pages++;
+			spin_unlock_irq(&hugetlb_lock);
+		}
+
+		return rc;
 	}
 out:
 	spin_unlock_irq(&hugetlb_lock);
@@ -2351,14 +2539,15 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page,
 
 	/*
 	 * Before dissolving the page, we need to allocate a new one for the
-	 * pool to remain stable. Using alloc_buddy_huge_page() allows us to
-	 * not having to deal with prep_new_huge_page() and avoids dealing of any
-	 * counters. This simplifies and let us do the whole thing under the
-	 * lock.
+	 * pool to remain stable.  Here, we allocate the page and 'prep' it
+	 * by doing everything but actually updating counters and adding to
+	 * the pool.  This simplifies and let us do most of the processing
+	 * under the lock.
 	 */
 	new_page = alloc_buddy_huge_page(h, gfp_mask, nid, NULL, NULL);
 	if (!new_page)
 		return -ENOMEM;
+	__prep_new_huge_page(h, new_page);
 
 retry:
 	spin_lock_irq(&hugetlb_lock);
@@ -2397,14 +2586,9 @@ retry:
 		remove_hugetlb_page(h, old_page, false);
 
 		/*
-		 * new_page needs to be initialized with the standard hugetlb
-		 * state. This is normally done by prep_new_huge_page() but
-		 * that takes hugetlb_lock which is already held so we need to
-		 * open code it here.
 		 * Reference count trick is needed because allocator gives us
 		 * referenced page but the pool requires pages with 0 refcount.
 		 */
-		__prep_new_huge_page(new_page);
 		__prep_account_new_huge_page(h, nid);
 		page_ref_dec(new_page);
 		enqueue_huge_page(h, new_page);
@@ -2413,14 +2597,14 @@ retry:
 		 * Pages have been replaced, we can safely free the old one.
 		 */
 		spin_unlock_irq(&hugetlb_lock);
-		update_and_free_page(h, old_page);
+		update_and_free_page(h, old_page, false);
 	}
 
 	return ret;
 
 free_new:
 	spin_unlock_irq(&hugetlb_lock);
-	__free_pages(new_page, huge_page_order(h));
+	update_and_free_page(h, new_page, false);
 
 	return ret;
 }
@@ -2625,16 +2809,10 @@ found:
 	return 1;
 }
 
-static void __init prep_compound_huge_page(struct page *page,
-		unsigned int order)
-{
-	if (unlikely(order > (MAX_ORDER - 1)))
-		prep_compound_gigantic_page(page, order);
-	else
-		prep_compound_page(page, order);
-}
-
-/* Put bootmem huge pages into the standard lists after mem_map is up */
+/*
+ * Put bootmem huge pages into the standard lists after mem_map is up.
+ * Note: This only applies to gigantic (order > MAX_ORDER) pages.
+ */
 static void __init gather_bootmem_prealloc(void)
 {
 	struct huge_bootmem_page *m;
@@ -2643,20 +2821,23 @@ static void __init gather_bootmem_prealloc(void)
 		struct page *page = virt_to_page(m);
 		struct hstate *h = m->hstate;
 
+		VM_BUG_ON(!hstate_is_gigantic(h));
 		WARN_ON(page_count(page) != 1);
-		prep_compound_huge_page(page, huge_page_order(h));
-		WARN_ON(PageReserved(page));
-		prep_new_huge_page(h, page, page_to_nid(page));
-		put_page(page); /* free it into the hugepage allocator */
+		if (prep_compound_gigantic_page(page, huge_page_order(h))) {
+			WARN_ON(PageReserved(page));
+			prep_new_huge_page(h, page, page_to_nid(page));
+			put_page(page); /* add to the hugepage allocator */
+		} else {
+			free_gigantic_page(page, huge_page_order(h));
+			pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n");
+		}
 
 		/*
-		 * If we had gigantic hugepages allocated at boot time, we need
-		 * to restore the 'stolen' pages to totalram_pages in order to
-		 * fix confusing memory reports from free(1) and another
-		 * side-effects, like CommitLimit going negative.
+		 * We need to restore the 'stolen' pages to totalram_pages
+		 * in order to fix confusing memory reports from free(1) and
+		 * other side-effects, like CommitLimit going negative.
 		 */
-		if (hstate_is_gigantic(h))
-			adjust_managed_page_count(page, pages_per_huge_page(h));
+		adjust_managed_page_count(page, pages_per_huge_page(h));
 		cond_resched();
 	}
 }
@@ -2834,6 +3015,7 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
 	 * pages in hstate via the proc/sysfs interfaces.
 	 */
 	mutex_lock(&h->resize_lock);
+	flush_free_hpage_work(h);
 	spin_lock_irq(&hugetlb_lock);
 
 	/*
@@ -2943,6 +3125,7 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
 	/* free the pages after dropping lock */
 	spin_unlock_irq(&hugetlb_lock);
 	update_and_free_pages_bulk(h, &page_list);
+	flush_free_hpage_work(h);
 	spin_lock_irq(&hugetlb_lock);
 
 	while (count < persistent_huge_pages(h)) {
@@ -3450,6 +3633,7 @@ void __init hugetlb_add_hstate(unsigned int order)
 	h->next_nid_to_free = first_memory_node;
 	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
 					huge_page_size(h)/1024);
+	hugetlb_vmemmap_init(h);
 
 	parsed_hstate = h;
 }
@@ -3924,6 +4108,7 @@ static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
 				int writable)
 {
 	pte_t entry;
+	unsigned int shift = huge_page_shift(hstate_vma(vma));
 
 	if (writable) {
 		entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page,
@@ -3934,7 +4119,7 @@ static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
 	}
 	entry = pte_mkyoung(entry);
 	entry = pte_mkhuge(entry);
-	entry = arch_make_huge_pte(entry, vma, page, writable);
+	entry = arch_make_huge_pte(entry, shift, vma->vm_flags);
 
 	return entry;
 }
@@ -4057,12 +4242,13 @@ again:
 				    is_hugetlb_entry_hwpoisoned(entry))) {
 			swp_entry_t swp_entry = pte_to_swp_entry(entry);
 
-			if (is_write_migration_entry(swp_entry) && cow) {
+			if (is_writable_migration_entry(swp_entry) && cow) {
 				/*
 				 * COW mappings require pages in both
 				 * parent and child to be set to read.
 				 */
-				make_migration_entry_read(&swp_entry);
+				swp_entry = make_readable_migration_entry(
+							swp_offset(swp_entry));
 				entry = swp_entry_to_pte(swp_entry);
 				set_huge_swap_pte_at(src, addr, src_pte,
 						     entry, sz);
@@ -4939,20 +5125,17 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 			    struct page **pagep)
 {
 	bool is_continue = (mode == MCOPY_ATOMIC_CONTINUE);
-	struct address_space *mapping;
-	pgoff_t idx;
+	struct hstate *h = hstate_vma(dst_vma);
+	struct address_space *mapping = dst_vma->vm_file->f_mapping;
+	pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr);
 	unsigned long size;
 	int vm_shared = dst_vma->vm_flags & VM_SHARED;
-	struct hstate *h = hstate_vma(dst_vma);
 	pte_t _dst_pte;
 	spinlock_t *ptl;
-	int ret;
+	int ret = -ENOMEM;
 	struct page *page;
 	int writable;
 
-	mapping = dst_vma->vm_file->f_mapping;
-	idx = vma_hugecache_offset(h, dst_vma, dst_addr);
-
 	if (is_continue) {
 		ret = -EFAULT;
 		page = find_lock_page(mapping, idx);
@@ -4981,12 +5164,44 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 		/* fallback to copy_from_user outside mmap_lock */
 		if (unlikely(ret)) {
 			ret = -ENOENT;
+			/* Free the allocated page which may have
+			 * consumed a reservation.
+			 */
+			restore_reserve_on_error(h, dst_vma, dst_addr, page);
+			put_page(page);
+
+			/* Allocate a temporary page to hold the copied
+			 * contents.
+			 */
+			page = alloc_huge_page_vma(h, dst_vma, dst_addr);
+			if (!page) {
+				ret = -ENOMEM;
+				goto out;
+			}
 			*pagep = page;
-			/* don't free the page */
+			/* Set the outparam pagep and return to the caller to
+			 * copy the contents outside the lock. Don't free the
+			 * page.
+			 */
 			goto out;
 		}
 	} else {
-		page = *pagep;
+		if (vm_shared &&
+		    hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) {
+			put_page(*pagep);
+			ret = -EEXIST;
+			*pagep = NULL;
+			goto out;
+		}
+
+		page = alloc_huge_page(dst_vma, dst_addr, 0);
+		if (IS_ERR(page)) {
+			ret = -ENOMEM;
+			*pagep = NULL;
+			goto out;
+		}
+		copy_huge_page(page, *pagep);
+		put_page(*pagep);
 		*pagep = NULL;
 	}
 
@@ -5318,10 +5533,11 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		if (unlikely(is_hugetlb_entry_migration(pte))) {
 			swp_entry_t entry = pte_to_swp_entry(pte);
 
-			if (is_write_migration_entry(entry)) {
+			if (is_writable_migration_entry(entry)) {
 				pte_t newpte;
 
-				make_migration_entry_read(&entry);
+				entry = make_readable_migration_entry(
+							swp_offset(entry));
 				newpte = swp_entry_to_pte(entry);
 				set_huge_swap_pte_at(mm, address, ptep,
 						     newpte, huge_page_size(h));
@@ -5332,10 +5548,11 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		}
 		if (!huge_pte_none(pte)) {
 			pte_t old_pte;
+			unsigned int shift = huge_page_shift(hstate_vma(vma));
 
 			old_pte = huge_ptep_modify_prot_start(vma, address, ptep);
 			pte = pte_mkhuge(huge_pte_modify(old_pte, newprot));
-			pte = arch_make_huge_pte(pte, vma, NULL, 0);
+			pte = arch_make_huge_pte(pte, shift, vma->vm_flags);
 			huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte);
 			pages++;
 		}