mm/page_ext: resurrect struct page extending code for debugging

When we debug something, we'd like to insert some information to every
page.  For this purpose, we sometimes modify struct page itself.  But,
this has drawbacks.  First, it requires re-compile.  This makes us
hesitate to use the powerful debug feature so development process is
slowed down.  And, second, sometimes it is impossible to rebuild the
kernel due to third party module dependency.  At third, system behaviour
would be largely different after re-compile, because it changes size of
struct page greatly and this structure is accessed by every part of
kernel.  Keeping this as it is would be better to reproduce errornous
situation.

This feature is intended to overcome above mentioned problems.  This
feature allocates memory for extended data per page in certain place
rather than the struct page itself.  This memory can be accessed by the
accessor functions provided by this code.  During the boot process, it
checks whether allocation of huge chunk of memory is needed or not.  If
not, it avoids allocating memory at all.  With this advantage, we can
include this feature into the kernel in default and can avoid rebuild and
solve related problems.

Until now, memcg uses this technique.  But, now, memcg decides to embed
their variable to struct page itself and it's code to extend struct page
has been removed.  I'd like to use this code to develop debug feature, so
this patch resurrect it.

To help these things to work well, this patch introduces two callbacks for
clients.  One is the need callback which is mandatory if user wants to
avoid useless memory allocation at boot-time.  The other is optional, init
callback, which is used to do proper initialization after memory is
allocated.  Detailed explanation about purpose of these functions is in
code comment.  Please refer it.

Others are completely same with previous extension code in memcg.

Signed-off-by: Joonsoo Kim <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Michal Nazarewicz <[email protected]>
Cc: Jungsoo Son <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Joonsoo Kim <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/mmzone.h

@@ -722,6 +722,9 @@ typedef struct pglist_data {
 	int nr_zones;
 #ifdef CONFIG_FLAT_NODE_MEM_MAP	/* means !SPARSEMEM */
 	struct page *node_mem_map;
+#ifdef CONFIG_PAGE_EXTENSION
+	struct page_ext *node_page_ext;
+#endif
 #endif
 #ifndef CONFIG_NO_BOOTMEM
 	struct bootmem_data *bdata;
@@ -1075,6 +1078,7 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn)
 #define SECTION_ALIGN_DOWN(pfn)	((pfn) & PAGE_SECTION_MASK)
 
 struct page;
+struct page_ext;
 struct mem_section {
 	/*
 	 * This is, logically, a pointer to an array of struct
@@ -1092,6 +1096,14 @@ struct mem_section {
 
 	/* See declaration of similar field in struct zone */
 	unsigned long *pageblock_flags;
+#ifdef CONFIG_PAGE_EXTENSION
+	/*
+	 * If !SPARSEMEM, pgdat doesn't have page_ext pointer. We use
+	 * section. (see page_ext.h about this.)
+	 */
+	struct page_ext *page_ext;
+	unsigned long pad;
+#endif
 	/*
 	 * WARNING: mem_section must be a power-of-2 in size for the
 	 * calculation and use of SECTION_ROOT_MASK to make sense.

include/linux/page_ext.h

@@ -0,0 +1,59 @@
+#ifndef __LINUX_PAGE_EXT_H
+#define __LINUX_PAGE_EXT_H
+
+struct pglist_data;
+struct page_ext_operations {
+	bool (*need)(void);
+	void (*init)(void);
+};
+
+#ifdef CONFIG_PAGE_EXTENSION
+
+/*
+ * Page Extension can be considered as an extended mem_map.
+ * A page_ext page is associated with every page descriptor. The
+ * page_ext helps us add more information about the page.
+ * All page_ext are allocated at boot or memory hotplug event,
+ * then the page_ext for pfn always exists.
+ */
+struct page_ext {
+	unsigned long flags;
+};
+
+extern void pgdat_page_ext_init(struct pglist_data *pgdat);
+
+#ifdef CONFIG_SPARSEMEM
+static inline void page_ext_init_flatmem(void)
+{
+}
+extern void page_ext_init(void);
+#else
+extern void page_ext_init_flatmem(void);
+static inline void page_ext_init(void)
+{
+}
+#endif
+
+struct page_ext *lookup_page_ext(struct page *page);
+
+#else /* !CONFIG_PAGE_EXTENSION */
+struct page_ext;
+
+static inline void pgdat_page_ext_init(struct pglist_data *pgdat)
+{
+}
+
+static inline struct page_ext *lookup_page_ext(struct page *page)
+{
+	return NULL;
+}
+
+static inline void page_ext_init(void)
+{
+}
+
+static inline void page_ext_init_flatmem(void)
+{
+}
+#endif /* CONFIG_PAGE_EXTENSION */
+#endif /* __LINUX_PAGE_EXT_H */

init/main.c

@@ -51,6 +51,7 @@
 #include <linux/mempolicy.h>
 #include <linux/key.h>
 #include <linux/buffer_head.h>
+#include <linux/page_ext.h>
 #include <linux/debug_locks.h>
 #include <linux/debugobjects.h>
 #include <linux/lockdep.h>
@@ -484,6 +485,11 @@ void __init __weak thread_info_cache_init(void)
  */
 static void __init mm_init(void)
 {
+	/*
+	 * page_ext requires contiguous pages,
+	 * bigger than MAX_ORDER unless SPARSEMEM.
+	 */
+	page_ext_init_flatmem();
 	mem_init();
 	kmem_cache_init();
 	percpu_init_late();
@@ -621,6 +627,7 @@ asmlinkage __visible void __init start_kernel(void)
 		initrd_start = 0;
 	}
 #endif
+	page_ext_init();
 	debug_objects_mem_init();
 	kmemleak_init();
 	setup_per_cpu_pageset();

mm/Kconfig.debug

@@ -1,3 +1,12 @@
+config PAGE_EXTENSION
+	bool "Extend memmap on extra space for more information on page"
+	---help---
+	  Extend memmap on extra space for more information on page. This
+	  could be used for debugging features that need to insert extra
+	  field for every page. This extension enables us to save memory
+	  by not allocating this extra memory according to boottime
+	  configuration.
+
 config DEBUG_PAGEALLOC
 	bool "Debug page memory allocations"
 	depends on DEBUG_KERNEL

mm/Makefile

@@ -71,3 +71,4 @@ obj-$(CONFIG_ZSMALLOC)	+= zsmalloc.o
 obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o
 obj-$(CONFIG_CMA)	+= cma.o
 obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o
+obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o

mm/page_alloc.c

@@ -48,6 +48,7 @@
 #include <linux/backing-dev.h>
 #include <linux/fault-inject.h>
 #include <linux/page-isolation.h>
+#include <linux/page_ext.h>
 #include <linux/debugobjects.h>
 #include <linux/kmemleak.h>
 #include <linux/compaction.h>
@@ -4856,6 +4857,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 #endif
 	init_waitqueue_head(&pgdat->kswapd_wait);
 	init_waitqueue_head(&pgdat->pfmemalloc_wait);
+	pgdat_page_ext_init(pgdat);
 
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;