1 files changed, 105 insertions, 44 deletions

diff --git a/mm/gup.c b/mm/gup.c
index e40579624f10..71e546e279fc 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -213,6 +213,58 @@ 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 +291,15 @@ 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 +320,50 @@ 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 +375,8 @@ 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 +385,9 @@ 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 +516,6 @@ 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 +660,7 @@ 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 +669,7 @@ 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;
@@ -1535,6 +1592,10 @@ 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 */