1 files changed, 180 insertions, 145 deletions

diff --git a/mm/gup.c b/mm/gup.c
index ef7d2da9f03f..3ded6a5f26b2 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -87,11 +87,12 @@ __maybe_unused struct page *try_grab_compound_head(struct page *page,
 		int orig_refs = refs;
 
 		/*
-		 * Can't do FOLL_LONGTERM + FOLL_PIN with CMA in the gup fast
-		 * path, so fail and let the caller fall back to the slow path.
+		 * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a
+		 * right zone, so fail and let the caller fall back to the slow
+		 * path.
 		 */
-		if (unlikely(flags & FOLL_LONGTERM) &&
-				is_migrate_cma_page(page))
+		if (unlikely((flags & FOLL_LONGTERM) &&
+			     !is_pinnable_page(page)))
 			return NULL;
 
 		/*
@@ -213,6 +214,58 @@ void unpin_user_page(struct page *page)
 }
 EXPORT_SYMBOL(unpin_user_page);
 
+static inline void compound_range_next(unsigned long i, unsigned long npages,
+				       struct page **list, struct page **head,
+				       unsigned int *ntails)
+{
+	struct page *next, *page;
+	unsigned int nr = 1;
+
+	if (i >= npages)
+		return;
+
+	next = *list + i;
+	page = compound_head(next);
+	if (PageCompound(page) && compound_order(page) >= 1)
+		nr = min_t(unsigned int,
+			   page + compound_nr(page) - next, npages - i);
+
+	*head = page;
+	*ntails = nr;
+}
+
+#define for_each_compound_range(__i, __list, __npages, __head, __ntails) \
+	for (__i = 0, \
+	     compound_range_next(__i, __npages, __list, &(__head), &(__ntails)); \
+	     __i < __npages; __i += __ntails, \
+	     compound_range_next(__i, __npages, __list, &(__head), &(__ntails)))
+
+static inline void compound_next(unsigned long i, unsigned long npages,
+				 struct page **list, struct page **head,
+				 unsigned int *ntails)
+{
+	struct page *page;
+	unsigned int nr;
+
+	if (i >= npages)
+		return;
+
+	page = compound_head(list[i]);
+	for (nr = i + 1; nr < npages; nr++) {
+		if (compound_head(list[nr]) != page)
+			break;
+	}
+
+	*head = page;
+	*ntails = nr - i;
+}
+
+#define for_each_compound_head(__i, __list, __npages, __head, __ntails) \
+	for (__i = 0, \
+	     compound_next(__i, __npages, __list, &(__head), &(__ntails)); \
+	     __i < __npages; __i += __ntails, \
+	     compound_next(__i, __npages, __list, &(__head), &(__ntails)))
+
 /**
  * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
  * @pages:  array of pages to be maybe marked dirty, and definitely released.
@@ -239,20 +292,15 @@ void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 				 bool make_dirty)
 {
 	unsigned long index;
-
-	/*
-	 * TODO: this can be optimized for huge pages: if a series of pages is
-	 * physically contiguous and part of the same compound page, then a
-	 * single operation to the head page should suffice.
-	 */
+	struct page *head;
+	unsigned int ntails;
 
 	if (!make_dirty) {
 		unpin_user_pages(pages, npages);
 		return;
 	}
 
-	for (index = 0; index < npages; index++) {
-		struct page *page = compound_head(pages[index]);
+	for_each_compound_head(index, pages, npages, head, ntails) {
 		/*
 		 * Checking PageDirty at this point may race with
 		 * clear_page_dirty_for_io(), but that's OK. Two key
@@ -273,14 +321,50 @@ void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 		 * written back, so it gets written back again in the
 		 * next writeback cycle. This is harmless.
 		 */
-		if (!PageDirty(page))
-			set_page_dirty_lock(page);
-		unpin_user_page(page);
+		if (!PageDirty(head))
+			set_page_dirty_lock(head);
+		put_compound_head(head, ntails, FOLL_PIN);
 	}
 }
 EXPORT_SYMBOL(unpin_user_pages_dirty_lock);
 
 /**
+ * unpin_user_page_range_dirty_lock() - release and optionally dirty
+ * gup-pinned page range
+ *
+ * @page:  the starting page of a range maybe marked dirty, and definitely released.
+ * @npages: number of consecutive pages to release.
+ * @make_dirty: whether to mark the pages dirty
+ *
+ * "gup-pinned page range" refers to a range of pages that has had one of the
+ * pin_user_pages() variants called on that page.
+ *
+ * For the page ranges defined by [page .. page+npages], make that range (or
+ * its head pages, if a compound page) dirty, if @make_dirty is true, and if the
+ * page range was previously listed as clean.
+ *
+ * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
+ * required, then the caller should a) verify that this is really correct,
+ * because _lock() is usually required, and b) hand code it:
+ * set_page_dirty_lock(), unpin_user_page().
+ *
+ */
+void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages,
+				      bool make_dirty)
+{
+	unsigned long index;
+	struct page *head;
+	unsigned int ntails;
+
+	for_each_compound_range(index, &page, npages, head, ntails) {
+		if (make_dirty && !PageDirty(head))
+			set_page_dirty_lock(head);
+		put_compound_head(head, ntails, FOLL_PIN);
+	}
+}
+EXPORT_SYMBOL(unpin_user_page_range_dirty_lock);
+
+/**
  * unpin_user_pages() - release an array of gup-pinned pages.
  * @pages:  array of pages to be marked dirty and released.
  * @npages: number of pages in the @pages array.
@@ -292,6 +376,8 @@ EXPORT_SYMBOL(unpin_user_pages_dirty_lock);
 void unpin_user_pages(struct page **pages, unsigned long npages)
 {
 	unsigned long index;
+	struct page *head;
+	unsigned int ntails;
 
 	/*
 	 * If this WARN_ON() fires, then the system *might* be leaking pages (by
@@ -300,13 +386,9 @@ void unpin_user_pages(struct page **pages, unsigned long npages)
 	 */
 	if (WARN_ON(IS_ERR_VALUE(npages)))
 		return;
-	/*
-	 * TODO: this can be optimized for huge pages: if a series of pages is
-	 * physically contiguous and part of the same compound page, then a
-	 * single operation to the head page should suffice.
-	 */
-	for (index = 0; index < npages; index++)
-		unpin_user_page(pages[index]);
+
+	for_each_compound_head(index, pages, npages, head, ntails)
+		put_compound_head(head, ntails, FOLL_PIN);
 }
 EXPORT_SYMBOL(unpin_user_pages);
 
@@ -435,18 +517,6 @@ retry:
 		}
 	}
 
-	if (flags & FOLL_SPLIT && PageTransCompound(page)) {
-		get_page(page);
-		pte_unmap_unlock(ptep, ptl);
-		lock_page(page);
-		ret = split_huge_page(page);
-		unlock_page(page);
-		put_page(page);
-		if (ret)
-			return ERR_PTR(ret);
-		goto retry;
-	}
-
 	/* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */
 	if (unlikely(!try_grab_page(page, flags))) {
 		page = ERR_PTR(-ENOMEM);
@@ -591,7 +661,7 @@ retry_locked:
 		spin_unlock(ptl);
 		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
 	}
-	if (flags & (FOLL_SPLIT | FOLL_SPLIT_PMD)) {
+	if (flags & FOLL_SPLIT_PMD) {
 		int ret;
 		page = pmd_page(*pmd);
 		if (is_huge_zero_page(page)) {
@@ -600,19 +670,7 @@ retry_locked:
 			split_huge_pmd(vma, pmd, address);
 			if (pmd_trans_unstable(pmd))
 				ret = -EBUSY;
-		} else if (flags & FOLL_SPLIT) {
-			if (unlikely(!try_get_page(page))) {
-				spin_unlock(ptl);
-				return ERR_PTR(-ENOMEM);
-			}
-			spin_unlock(ptl);
-			lock_page(page);
-			ret = split_huge_page(page);
-			unlock_page(page);
-			put_page(page);
-			if (pmd_none(*pmd))
-				return no_page_table(vma, flags);
-		} else {  /* flags & FOLL_SPLIT_PMD */
+		} else {
 			spin_unlock(ptl);
 			split_huge_pmd(vma, pmd, address);
 			ret = pte_alloc(mm, pmd) ? -ENOMEM : 0;
@@ -1470,7 +1528,7 @@ static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start,
 {
 	struct vm_area_struct *vma;
 	unsigned long vm_flags;
-	int i;
+	long i;
 
 	/* calculate required read or write permissions.
 	 * If FOLL_FORCE is set, we only require the "MAY" flags.
@@ -1517,7 +1575,7 @@ finish_or_fault:
  * Returns NULL on any kind of failure - a hole must then be inserted into
  * the corefile, to preserve alignment with its headers; and also returns
  * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
- * allowing a hole to be left in the corefile to save diskspace.
+ * allowing a hole to be left in the corefile to save disk space.
  *
  * Called without mmap_lock (takes and releases the mmap_lock by itself).
  */
@@ -1535,120 +1593,96 @@ struct page *get_dump_page(unsigned long addr)
 				      FOLL_FORCE | FOLL_DUMP | FOLL_GET);
 	if (locked)
 		mmap_read_unlock(mm);
-
-	if (ret == 1 && is_page_poisoned(page))
-		return NULL;
-
 	return (ret == 1) ? page : NULL;
 }
 #endif /* CONFIG_ELF_CORE */
 
-#ifdef CONFIG_CMA
-static long check_and_migrate_cma_pages(struct mm_struct *mm,
-					unsigned long start,
-					unsigned long nr_pages,
-					struct page **pages,
-					struct vm_area_struct **vmas,
-					unsigned int gup_flags)
+#ifdef CONFIG_MIGRATION
+/*
+ * Check whether all pages are pinnable, if so return number of pages.  If some
+ * pages are not pinnable, migrate them, and unpin all pages. Return zero if
+ * pages were migrated, or if some pages were not successfully isolated.
+ * Return negative error if migration fails.
+ */
+static long check_and_migrate_movable_pages(unsigned long nr_pages,
+					    struct page **pages,
+					    unsigned int gup_flags)
 {
 	unsigned long i;
-	unsigned long step;
+	unsigned long isolation_error_count = 0;
 	bool drain_allow = true;
-	bool migrate_allow = true;
-	LIST_HEAD(cma_page_list);
-	long ret = nr_pages;
+	LIST_HEAD(movable_page_list);
+	long ret = 0;
+	struct page *prev_head = NULL;
+	struct page *head;
 	struct migration_target_control mtc = {
 		.nid = NUMA_NO_NODE,
-		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_NOWARN,
+		.gfp_mask = GFP_USER | __GFP_NOWARN,
 	};
 
-check_again:
-	for (i = 0; i < nr_pages;) {
-
-		struct page *head = compound_head(pages[i]);
-
-		/*
-		 * gup may start from a tail page. Advance step by the left
-		 * part.
-		 */
-		step = compound_nr(head) - (pages[i] - head);
+	for (i = 0; i < nr_pages; i++) {
+		head = compound_head(pages[i]);
+		if (head == prev_head)
+			continue;
+		prev_head = head;
 		/*
-		 * If we get a page from the CMA zone, since we are going to
-		 * be pinning these entries, we might as well move them out
-		 * of the CMA zone if possible.
+		 * If we get a movable page, since we are going to be pinning
+		 * these entries, try to move them out if possible.
 		 */
-		if (is_migrate_cma_page(head)) {
-			if (PageHuge(head))
-				isolate_huge_page(head, &cma_page_list);
-			else {
+		if (!is_pinnable_page(head)) {
+			if (PageHuge(head)) {
+				if (!isolate_huge_page(head, &movable_page_list))
+					isolation_error_count++;
+			} else {
 				if (!PageLRU(head) && drain_allow) {
 					lru_add_drain_all();
 					drain_allow = false;
 				}
 
-				if (!isolate_lru_page(head)) {
-					list_add_tail(&head->lru, &cma_page_list);
-					mod_node_page_state(page_pgdat(head),
-							    NR_ISOLATED_ANON +
-							    page_is_file_lru(head),
-							    thp_nr_pages(head));
+				if (isolate_lru_page(head)) {
+					isolation_error_count++;
+					continue;
 				}
+				list_add_tail(&head->lru, &movable_page_list);
+				mod_node_page_state(page_pgdat(head),
+						    NR_ISOLATED_ANON +
+						    page_is_file_lru(head),
+						    thp_nr_pages(head));
 			}
 		}
-
-		i += step;
 	}
 
-	if (!list_empty(&cma_page_list)) {
-		/*
-		 * drop the above get_user_pages reference.
-		 */
-		if (gup_flags & FOLL_PIN)
-			unpin_user_pages(pages, nr_pages);
-		else
-			for (i = 0; i < nr_pages; i++)
-				put_page(pages[i]);
-
-		if (migrate_pages(&cma_page_list, alloc_migration_target, NULL,
-			(unsigned long)&mtc, MIGRATE_SYNC, MR_CONTIG_RANGE)) {
-			/*
-			 * some of the pages failed migration. Do get_user_pages
-			 * without migration.
-			 */
-			migrate_allow = false;
+	/*
+	 * If list is empty, and no isolation errors, means that all pages are
+	 * in the correct zone.
+	 */
+	if (list_empty(&movable_page_list) && !isolation_error_count)
+		return nr_pages;
 
-			if (!list_empty(&cma_page_list))
-				putback_movable_pages(&cma_page_list);
-		}
-		/*
-		 * We did migrate all the pages, Try to get the page references
-		 * again migrating any new CMA pages which we failed to isolate
-		 * earlier.
-		 */
-		ret = __get_user_pages_locked(mm, start, nr_pages,
-						   pages, vmas, NULL,
-						   gup_flags);
-
-		if ((ret > 0) && migrate_allow) {
-			nr_pages = ret;
-			drain_allow = true;
-			goto check_again;
-		}
+	if (gup_flags & FOLL_PIN) {
+		unpin_user_pages(pages, nr_pages);
+	} else {
+		for (i = 0; i < nr_pages; i++)
+			put_page(pages[i]);
+	}
+	if (!list_empty(&movable_page_list)) {
+		ret = migrate_pages(&movable_page_list, alloc_migration_target,
+				    NULL, (unsigned long)&mtc, MIGRATE_SYNC,
+				    MR_LONGTERM_PIN);
+		if (ret && !list_empty(&movable_page_list))
+			putback_movable_pages(&movable_page_list);
 	}
 
-	return ret;
+	return ret > 0 ? -ENOMEM : ret;
 }
 #else
-static long check_and_migrate_cma_pages(struct mm_struct *mm,
-					unsigned long start,
-					unsigned long nr_pages,
-					struct page **pages,
-					struct vm_area_struct **vmas,
-					unsigned int gup_flags)
+static long check_and_migrate_movable_pages(unsigned long nr_pages,
+					    struct page **pages,
+					    unsigned int gup_flags)
 {
 	return nr_pages;
 }
-#endif /* CONFIG_CMA */
+#endif /* CONFIG_MIGRATION */
 
 /*
  * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which
@@ -1661,21 +1695,22 @@ static long __gup_longterm_locked(struct mm_struct *mm,
 				  struct vm_area_struct **vmas,
 				  unsigned int gup_flags)
 {
-	unsigned long flags = 0;
+	unsigned int flags;
 	long rc;
 
-	if (gup_flags & FOLL_LONGTERM)
-		flags = memalloc_nocma_save();
-
-	rc = __get_user_pages_locked(mm, start, nr_pages, pages, vmas, NULL,
-				     gup_flags);
+	if (!(gup_flags & FOLL_LONGTERM))
+		return __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
+					       NULL, gup_flags);
+	flags = memalloc_pin_save();
+	do {
+		rc = __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
+					     NULL, gup_flags);
+		if (rc <= 0)
+			break;
+		rc = check_and_migrate_movable_pages(rc, pages, gup_flags);
+	} while (!rc);
+	memalloc_pin_restore(flags);
 
-	if (gup_flags & FOLL_LONGTERM) {
-		if (rc > 0)
-			rc = check_and_migrate_cma_pages(mm, start, rc, pages,
-							 vmas, gup_flags);
-		memalloc_nocma_restore(flags);
-	}
 	return rc;
 }