UPSTREAM: mm: reuse only-pte-mapped KSM page in do_wp_page()

Add an optimization for KSM pages almost in the same way that we have
for ordinary anonymous pages.  If there is a write fault in a page,
which is mapped to an only pte, and it is not related to swap cache; the
page may be reused without copying its content.

[ Note that we do not consider PageSwapCache() pages at least for now,
  since we don't want to complicate __get_ksm_page(), which has nice
  optimization based on this (for the migration case). Currenly it is
  spinning on PageSwapCache() pages, waiting for when they have
  unfreezed counters (i.e., for the migration finish). But we don't want
  to make it also spinning on swap cache pages, which we try to reuse,
  since there is not a very high probability to reuse them. So, for now
  we do not consider PageSwapCache() pages at all. ]

So in reuse_ksm_page() we check for 1) PageSwapCache() and 2)
page_stable_node(), to skip a page, which KSM is currently trying to
link to stable tree.  Then we do page_ref_freeze() to prohibit KSM to
merge one more page into the page, we are reusing.  After that, nobody
can refer to the reusing page: KSM skips !PageSwapCache() pages with
zero refcount; and the protection against of all other participants is
the same as for reused ordinary anon pages pte lock, page lock and
mmap_sem.

[akpm@linux-foundation.org: replace BUG_ON()s with WARN_ON()s]
Link: http://lkml.kernel.org/r/154471491016.31352.1168978849911555609.stgit@localhost.localdomain
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Reviewed-by: Yang Shi <yang.shi@linux.alibaba.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christian Koenig <christian.koenig@amd.com>
Cc: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Change-Id: If32387b1f7c36f0e12fcbb0926bf1b67886ec594

3 files changed, 50 insertions, 4 deletions

diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 481c8c4627ca..febba394f93c 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -62,6 +62,8 @@ struct page *ksm_might_need_to_copy(struct page *page,
 
 int rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc);
 void ksm_migrate_page(struct page *newpage, struct page *oldpage);
+bool reuse_ksm_page(struct page *page,
+			struct vm_area_struct *vma, unsigned long address);
 
 #else  /* !CONFIG_KSM */
 
@@ -102,6 +104,11 @@ static inline int rmap_walk_ksm(struct page *page,
 static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage)
 {
 }
+static inline bool reuse_ksm_page(struct page *page,
+			struct vm_area_struct *vma, unsigned long address)
+{
+	return false;
+}
 #endif /* CONFIG_MMU */
 #endif /* !CONFIG_KSM */
 
diff --git a/mm/ksm.c b/mm/ksm.c
index 2a4ef426b331..bfee36c149e6 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -580,8 +580,9 @@ again:
 	 * case this node is no longer referenced, and should be freed;
 	 * however, it might mean that the page is under page_freeze_refs().
 	 * The __remove_mapping() case is easy, again the node is now stale;
-	 * but if page is swapcache in migrate_page_move_mapping(), it might
-	 * still be our page, in which case it's essential to keep the node.
+	 * the same is in reuse_ksm_page() case; but if page is swapcache
+	 * in migrate_page_move_mapping(), it might still be our page,
+	 * in which case it's essential to keep the node.
 	 */
 	while (!get_page_unless_zero(page)) {
 		/*
@@ -2061,6 +2062,31 @@ out:
 	return ret;
 }
 
+bool reuse_ksm_page(struct page *page,
+		    struct vm_area_struct *vma,
+		    unsigned long address)
+{
+#ifdef CONFIG_DEBUG_VM
+	if (WARN_ON(is_zero_pfn(page_to_pfn(page))) ||
+			WARN_ON(!page_mapped(page)) ||
+			WARN_ON(!PageLocked(page))) {
+		dump_page(page, "reuse_ksm_page");
+		return false;
+	}
+#endif
+
+	if (PageSwapCache(page) || !page_stable_node(page))
+		return false;
+	/* Prohibit parallel get_ksm_page() */
+	if (!page_ref_freeze(page, 1))
+		return false;
+
+	page_move_anon_rmap(page, vma);
+	page->index = linear_page_index(vma, address);
+	page_ref_unfreeze(page, 1);
+
+	return true;
+}
 #ifdef CONFIG_MIGRATION
 void ksm_migrate_page(struct page *newpage, struct page *oldpage)
 {
diff --git a/mm/memory.c b/mm/memory.c
index 09a57fe6ae01..ccb04d3f9bab 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2399,7 +2399,10 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * Take out anonymous pages first, anonymous shared vmas are
 	 * not dirty accountable.
 	 */
-	if (PageAnon(old_page) && !PageKsm(old_page)) {
+	if (PageAnon(old_page)) {
+		if (PageKsm(old_page) && (PageSwapCache(old_page) ||
+					  page_count(old_page) != 1))
+			goto copy;
 		if (!trylock_page(old_page)) {
 			page_cache_get(old_page);
 			pte_unmap_unlock(page_table, ptl);
@@ -2414,6 +2417,16 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			}
 			page_cache_release(old_page);
 		}
+		if (PageKsm(old_page)) {
+			bool reused = reuse_ksm_page(old_page, vma,
+						     address);
+			unlock_page(old_page);
+			if (!reused)
+				goto copy;
+			wp_page_reuse(mm, vma, address, page_table, ptl,
+				      orig_pte, old_page, 0, 0);
+			return VM_FAULT_WRITE;
+		}
 		if (reuse_swap_page(old_page)) {
 			/*
 			 * The page is all ours.  Move it to our anon_vma so
@@ -2431,7 +2444,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		return wp_page_shared(mm, vma, address, page_table, pmd,
 				      ptl, orig_pte, old_page);
 	}
-
+copy:
 	/*
 	 * Ok, we need to copy. Oh, well..
 	 */