mm: add support for discard of unused ptes

In a virtualized environment and given an appropriate interface the guest
can mark pages as unused while they are free (for the s390 implementation
see git commit 45e576b1c3d00206 "guest page hinting light"). For the host
the unused state is a property of the pte.

This patch adds the primitive 'pte_unused' and code to the host swap out
handler so that pages marked as unused by all mappers are not swapped out
but discarded instead, thus saving one IO for swap out and potentially
another one for swap in.

[ Martin Schwidefsky: patch reordering and simplification ]

Signed-off-by: Konstantin Weitz <konstantin.weitz@gmail.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

2 files changed, 23 insertions, 0 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 34c7bdc..1ec08c1 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -193,6 +193,19 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b)
 }
 #endif
 
+#ifndef __HAVE_ARCH_PTE_UNUSED
+/*
+ * Some architectures provide facilities to virtualization guests
+ * so that they can flag allocated pages as unused. This allows the
+ * host to transparently reclaim unused pages. This function returns
+ * whether the pte's page is unused.
+ */
+static inline int pte_unused(pte_t pte)
+{
+	return 0;
+}
+#endif
+
 #ifndef __HAVE_ARCH_PMD_SAME
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
diff --git a/mm/rmap.c b/mm/rmap.c
index d9d4231..9056a1f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1165,6 +1165,16 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		}
 		set_pte_at(mm, address, pte,
 			   swp_entry_to_pte(make_hwpoison_entry(page)));
+	} else if (pte_unused(pteval)) {
+		/*
+		 * The guest indicated that the page content is of no
+		 * interest anymore. Simply discard the pte, vmscan
+		 * will take care of the rest.
+		 */
+		if (PageAnon(page))
+			dec_mm_counter(mm, MM_ANONPAGES);
+		else
+			dec_mm_counter(mm, MM_FILEPAGES);
 	} else if (PageAnon(page)) {
 		swp_entry_t entry = { .val = page_private(page) };
 		pte_t swp_pte;