mm: Add flush_dcache_folio

This is a default implementation which calls flush_dcache_page() on
each page in the folio.  If architectures can do better, they should
implement their own version of it.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>

Documentation/core-api/cachetlb.rst

@@ -325,6 +325,12 @@ maps this page at its virtual address.
 			dirty.  Again, see sparc64 for examples of how
 			to deal with this.
 
+  ``void flush_dcache_folio(struct folio *folio)``
+	This function is called under the same circumstances as
+	flush_dcache_page().  It allows the architecture to
+	optimise for flushing the entire folio of pages instead
+	of flushing one page at a time.
+
   ``void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
   unsigned long user_vaddr, void *dst, void *src, int len)``
   ``void copy_from_user_page(struct vm_area_struct *vma, struct page *page,

include/asm-generic/cacheflush.h

@@ -49,9 +49,22 @@ static inline void flush_cache_page(struct vm_area_struct *vma,
 static inline void flush_dcache_page(struct page *page)
 {
 }
+
+static inline void flush_dcache_folio(struct folio *folio) { }
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
 #endif
 
+#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
+static inline void flush_dcache_folio(struct folio *folio)
+{
+	unsigned int n = folio_nr_pages(folio);
+
+	do {
+		flush_dcache_page(&folio->page[--n]);
+	} while (n);
+}
+#endif
 
 #ifndef flush_dcache_mmap_lock
 static inline void flush_dcache_mmap_lock(struct address_space *mapping)