3.11.10.3 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Steven Capper <redacted>

commit 2a7cfcbc0553365d75716f69ee7b704cac7c9248 upstream.

When given a compound high page, __flush_dcache_page will only flush
the first page of the compound page repeatedly rather than the entire
set of constituent pages.

This error was introduced by:
   0b19f93 ARM: mm: Add support for flushing HugeTLB pages.

This patch corrects the logic such that all constituent pages are now
flushed.

Signed-off-by: Steve Capper <redacted>
Acked-by: Will Deacon <redacted>
Signed-off-by: Russell King <redacted>
Signed-off-by: Luis Henriques <redacted>
---
 arch/arm/mm/flush.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 6d5ba9a..3387e60 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c

@@ -175,16 +175,16 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page)
 		unsigned long i;
 		if (cache_is_vipt_nonaliasing()) {
 			for (i = 0; i < (1 << compound_order(page)); i++) {
-				void *addr = kmap_atomic(page);
+				void *addr = kmap_atomic(page + i);
 				__cpuc_flush_dcache_area(addr, PAGE_SIZE);
 				kunmap_atomic(addr);
 			}
 		} else {
 			for (i = 0; i < (1 << compound_order(page)); i++) {
-				void *addr = kmap_high_get(page);
+				void *addr = kmap_high_get(page + i);
 				if (addr) {
 					__cpuc_flush_dcache_area(addr, PAGE_SIZE);
-					kunmap_high(page);
+					kunmap_high(page + i);
 				}
 			}
 		}

-- 
1.8.3.2