[PATCH 02/11] mm: Support THPs in zero_user_segments

["Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>]

We can only kmap() one subpage of a THP at a time, so loop over all
relevant subpages, skipping ones which don't need to be zeroed.  This is
too large to inline when THPs are enabled and we actually need highmem,
so put it in highmem.c.

Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
---
 include/linux/highmem.h | 15 +++++++---
 mm/highmem.c            | 62 +++++++++++++++++++++++++++++++++++++++--
 2 files changed, 71 insertions(+), 6 deletions(-)

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 14e6202ce47f..5390bfd4bdd3 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -284,13 +284,18 @@ static inline void clear_highpage(struct page *page)
 	kunmap_atomic(kaddr);
 }
 
+#if defined(CONFIG_HIGHMEM) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
+void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
+		unsigned start2, unsigned end2);
+#else /* !HIGHMEM || !TRANSPARENT_HUGEPAGE */
 static inline void zero_user_segments(struct page *page,
-	unsigned start1, unsigned end1,
-	unsigned start2, unsigned end2)
+		unsigned start1, unsigned end1,
+		unsigned start2, unsigned end2)
 {
 	void *kaddr = kmap_atomic(page);
+	unsigned int i;
 
-	BUG_ON(end1 > PAGE_SIZE || end2 > PAGE_SIZE);
+	BUG_ON(end1 > thp_size(page) || end2 > thp_size(page));
 
 	if (end1 > start1)
 		memset(kaddr + start1, 0, end1 - start1);
@@ -299,8 +304,10 @@ static inline void zero_user_segments(struct page *page,
 		memset(kaddr + start2, 0, end2 - start2);
 
 	kunmap_atomic(kaddr);
-	flush_dcache_page(page);
+	for (i = 0; i < thp_nr_pages(page); i++)
+		flush_dcache_page(page + i);
 }
+#endif /* !HIGHMEM || !TRANSPARENT_HUGEPAGE */
 
 static inline void zero_user_segment(struct page *page,
 	unsigned start, unsigned end)
diff --git a/mm/highmem.c b/mm/highmem.c
index 64d8dea47dd1..c0f1e389a153 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -367,9 +367,67 @@ void kunmap_high(struct page *page)
 	if (need_wakeup)
 		wake_up(pkmap_map_wait);
 }
-
 EXPORT_SYMBOL(kunmap_high);
-#endif
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
+		unsigned start2, unsigned end2)
+{
+	unsigned int i;
+
+	BUG_ON(end1 > thp_size(page) || end2 > thp_size(page));
+
+	for (i = 0; i < thp_nr_pages(page); i++) {
+		void *kaddr;
+		unsigned this_end;
+
+		if (end1 == 0 && start2 >= PAGE_SIZE) {
+			start2 -= PAGE_SIZE;
+			end2 -= PAGE_SIZE;
+			continue;
+		}
+
+		if (start1 >= PAGE_SIZE) {
+			start1 -= PAGE_SIZE;
+			end1 -= PAGE_SIZE;
+			if (start2) {
+				start2 -= PAGE_SIZE;
+				end2 -= PAGE_SIZE;
+			}
+			continue;
+		}
+
+		kaddr = kmap_atomic(page + i);
+
+		this_end = min_t(unsigned, end1, PAGE_SIZE);
+		if (end1 > start1)
+			memset(kaddr + start1, 0, this_end - start1);
+		end1 -= this_end;
+		start1 = 0;
+
+		if (start2 >= PAGE_SIZE) {
+			start2 -= PAGE_SIZE;
+			end2 -= PAGE_SIZE;
+		} else {
+			this_end = min_t(unsigned, end2, PAGE_SIZE);
+			if (end2 > start2)
+				memset(kaddr + start2, 0, this_end - start2);
+			end2 -= this_end;
+			start2 = 0;
+		}
+
+		kunmap_atomic(kaddr);
+		flush_dcache_page(page + i);
+
+		if (!end1 && !end2)
+			break;
+	}
+
+	BUG_ON((start1 | start2 | end1 | end2) != 0);
+}
+EXPORT_SYMBOL(zero_user_segments);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif /* CONFIG_HIGHMEM */
 
 #if defined(HASHED_PAGE_VIRTUAL)
 
-- 
2.28.0