ksm: check and skip page, if it is already scanned

On system like Android where most of the process are forked
from parent w/o execve, KSM can scan same page multiple times
in one scan cycle. There is no advantage in scanning same page
multiple times for merging. During testing with Android, it was
observed around 60% pages are skipped for each scan cycle.

Change-Id: I0cf01802f0b4d61fcab92558beb9e1c660dc9a77
Link: http://lkml.kernel.org/r/CAMrOTPgBtANS_ryRjan0-dTL97U7eRvtf3dCsss=Kn+Uk89fuA@mail.gmail.com
Signed-off-by: Pradeep Sawlani <sawlani@amazon.com>

Signed-off-by: Paul Reioux <reioux@gmail.com>

include/linux/page-flags.h

@@ -114,8 +114,16 @@ enum pageflags {
 	PG_compound_lock,
 #endif
 	PG_readahead,		/* page in a readahead window */
+#ifdef CONFIG_KSM_CHECK_PAGE
+	PG_ksm_scan0,		/* page has been scanned by even KSM cycle */
+#endif
 	__NR_PAGEFLAGS,
 
+#ifdef CONFIG_KSM_CHECK_PAGE
+	/* page has been scanned by odd KSM cycle */
+	PG_ksm_scan1 = PG_owner_priv_1,
+#endif
+
 	/* Filesystems */
 	PG_checked = PG_owner_priv_1,
 
@@ -215,6 +223,10 @@ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved)
 PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked)
 
 __PAGEFLAG(SlobFree, slob_free)
+#ifdef CONFIG_KSM_CHECK_PAGE
+CLEARPAGEFLAG(KsmScan0, ksm_scan0) TESTSETFLAG(KsmScan0, ksm_scan0)
+CLEARPAGEFLAG(KsmScan1, ksm_scan1) TESTSETFLAG(KsmScan1, ksm_scan1)
+#endif
 
 #ifdef CONFIG_CLEANCACHE
 PAGEFLAG(WasActive, was_active)

mm/Kconfig

@@ -237,6 +237,16 @@ config KSM
 	  until a program has madvised that an area is MADV_MERGEABLE, and
 	  root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
 
+config KSM_CHECK_PAGE
+	bool "Check page before scanning"
+	depends on KSM
+	default n
+	help
+	  If enabled, this will check and skip if page is already scanned in
+	  same KSM scan cycle.
+	  This is useful in situation where you have parent and
+	  child process marking same area for KSM scanning.
+
 config DEFAULT_MMAP_MIN_ADDR
         int "Low address space to protect from user allocation"
 	depends on MMU

mm/ksm.c

@@ -651,7 +651,9 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item)
 		 * than left over from before.
 		 */
 		age = (unsigned char)(ksm_scan.seqnr - rmap_item->address);
+#ifndef CONFIG_KSM_CHECK_PAGE
 		BUG_ON(age > 1);
+#endif
 		if (!age)
 			rb_erase(&rmap_item->node,
 				 root_unstable_tree + NUMA(rmap_item->nid));
@@ -1688,6 +1690,31 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page)
 	return NULL;
 }
 
+static inline int is_page_scanned(struct page *page)
+{
+#ifdef CONFIG_KSM_CHECK_PAGE
+	/* page is already marked as ksm, so this will be simple merge */
+	if (PageKsm(page))
+		return 0;
+
+	if (ksm_scan.seqnr & 0x1) {
+		/* odd cycle */
+		/* clear even cycle bit */
+		ClearPageKsmScan0(page);
+		/* get old value and mark it scanned */
+		return TestSetPageKsmScan1(page);
+	} else {
+		/* even cycle */
+		/* clear odd cycle bit */
+		ClearPageKsmScan1(page);
+		/* get old value and mark it scanned */
+		return TestSetPageKsmScan0(page);
+	}
+#else
+	return 0;
+#endif
+}
+
 /**
  * ksm_do_scan  - the ksm scanner main worker function.
  * @scan_npages - number of pages we want to scan before we return.
@@ -1702,6 +1729,7 @@ static void ksm_do_scan(unsigned int scan_npages)
 		rmap_item = scan_get_next_rmap_item(&page);
 		if (!rmap_item)
 			return;
+		if (!is_page_scanned(page))
 		cmp_and_merge_page(page, rmap_item);
 		put_page(page);
 	}