mm/page_owner: keep track of page owners

This is the page owner tracking code which is introduced so far ago. It
is resident on Andrew's tree, though, nobody tried to upstream so it
remain as is. Our company uses this feature actively to debug memory leak
or to find a memory hogger so I decide to upstream this feature.

This functionality help us to know who allocates the page. When
allocating a page, we store some information about allocation in extra
memory. Later, if we need to know status of all pages, we can get and
analyze it from this stored information.

In previous version of this feature, extra memory is statically defined in
struct page, but, in this version, extra memory is allocated outside of
struct page. It enables us to turn on/off this feature at boottime
without considerable memory waste.

Although we already have tracepoint for tracing page allocation/free,
using it to analyze page owner is rather complex. We need to enlarge the
trace buffer for preventing overlapping until userspace program launched.
And, launched program continually dump out the trace buffer for later
analysis and it would change system behaviour with more possibility rather
than just keeping it in memory, so bad for debug.

Moreover, we can use page_owner feature further for various purposes. For
example, we can use it for fragmentation statistics implemented in this
patch. And, I also plan to implement some CMA failure debugging feature
using this interface.

I'd like to give the credit for all developers contributed this feature,
but, it's not easy because I don't know exact history. Sorry about that.
Below is people who has "Signed-off-by" in the patches in Andrew's tree.

Contributor:
Alexander Nyberg <[e-mail]>
Mel Gorman <[e-mail]>
Dave Hansen <[e-mail]>
Minchan Kim <[e-mail]>
Michal Nazarewicz <[e-mail]>
Andrew Morton <[e-mail]>
Jungsoo Son <[e-mail]>

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

Documentation/kernel-parameters.txt

···
 	OSS		[HW,OSS]
 			See Documentation/sound/oss/oss-parameters.txt
 
+	page_owner=	[KNL] Boot-time page_owner enabling option.
+			Storage of the information about who allocated
+			each page is disabled in default. With this switch,
+			we can turn it on.
+			on: enable the feature
+
 	panic=		[KNL] Kernel behaviour on panic: delay <timeout>
 			timeout > 0: seconds before rebooting
 			timeout = 0: wait forever

include/linux/page_ext.h

···
 #ifndef __LINUX_PAGE_EXT_H
 #define __LINUX_PAGE_EXT_H
 
+#include <linux/types.h>
+#include <linux/stacktrace.h>
+
 struct pglist_data;
 struct page_ext_operations {
 	bool (*need)(void);
···
 enum page_ext_flags {
 	PAGE_EXT_DEBUG_POISON,		/* Page is poisoned */
 	PAGE_EXT_DEBUG_GUARD,
+	PAGE_EXT_OWNER,
 };
 
 /*
···
  */
 struct page_ext {
 	unsigned long flags;
+#ifdef CONFIG_PAGE_OWNER
+	unsigned int order;
+	gfp_t gfp_mask;
+	struct stack_trace trace;
+	unsigned long trace_entries[8];
+#endif
 };
 
 extern void pgdat_page_ext_init(struct pglist_data *pgdat);

include/linux/page_owner.h

···
+#ifndef __LINUX_PAGE_OWNER_H
+#define __LINUX_PAGE_OWNER_H
+
+#ifdef CONFIG_PAGE_OWNER
+extern bool page_owner_inited;
+extern struct page_ext_operations page_owner_ops;
+
+extern void __reset_page_owner(struct page *page, unsigned int order);
+extern void __set_page_owner(struct page *page,
+			unsigned int order, gfp_t gfp_mask);
+
+static inline void reset_page_owner(struct page *page, unsigned int order)
+{
+	if (likely(!page_owner_inited))
+		return;
+
+	__reset_page_owner(page, order);
+}
+
+static inline void set_page_owner(struct page *page,
+			unsigned int order, gfp_t gfp_mask)
+{
+	if (likely(!page_owner_inited))
+		return;
+
+	__set_page_owner(page, order, gfp_mask);
+}
+#else
+static inline void reset_page_owner(struct page *page, unsigned int order)
+{
+}
+static inline void set_page_owner(struct page *page,
+			unsigned int order, gfp_t gfp_mask)
+{
+}
+
+#endif /* CONFIG_PAGE_OWNER */
+#endif /* __LINUX_PAGE_OWNER_H */

lib/Kconfig.debug

···
 	  you really need it, and what the merge plan to the mainline kernel for
 	  your module is.
 
+config PAGE_OWNER
+	bool "Track page owner"
+	depends on DEBUG_KERNEL && STACKTRACE_SUPPORT
+	select DEBUG_FS
+	select STACKTRACE
+	select PAGE_EXTENSION
+	help
+	  This keeps track of what call chain is the owner of a page, may
+	  help to find bare alloc_page(s) leaks. Even if you include this
+	  feature on your build, it is disabled in default. You should pass
+	  "page_owner=on" to boot parameter in order to enable it. Eats
+	  a fair amount of memory if enabled. See tools/vm/page_owner_sort.c
+	  for user-space helper.
+
+	  If unsure, say N.
+
 config DEBUG_FS
 	bool "Debug Filesystem"
 	help

mm/Makefile

···
 obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
 obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
 obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o
+obj-$(CONFIG_PAGE_OWNER) += page_owner.o
 obj-$(CONFIG_CLEANCACHE) += cleancache.o
 obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o
 obj-$(CONFIG_ZPOOL)	+= zpool.o

mm/page_alloc.c

···
 #include <linux/page_ext.h>
 #include <linux/hugetlb.h>
 #include <linux/sched/rt.h>
+#include <linux/page_owner.h>
 
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
···
 	if (bad)
 		return false;
 
+	reset_page_owner(page, order);
+
 	if (!PageHighMem(page)) {
 		debug_check_no_locks_freed(page_address(page),
 					   PAGE_SIZE << order);
···
 
 	if (order && (gfp_flags & __GFP_COMP))
 		prep_compound_page(page, order);
+
+	set_page_owner(page, order, gfp_flags);
 
 	return 0;
 }
···
 		split_page(virt_to_page(page[0].shadow), order);
 #endif
 
-	for (i = 1; i < (1 << order); i++)
+	set_page_owner(page, 0, 0);
+	for (i = 1; i < (1 << order); i++) {
 		set_page_refcounted(page + i);
+		set_page_owner(page + i, 0, 0);
+	}
 }
 EXPORT_SYMBOL_GPL(split_page);
 
···
 		}
 	}
 
+	set_page_owner(page, order, 0);
 	return 1UL << order;
 }
 

mm/page_ext.c

···
 #include <linux/memory.h>
 #include <linux/vmalloc.h>
 #include <linux/kmemleak.h>
+#include <linux/page_owner.h>
 
 /*
  * struct page extension
···
 	&debug_guardpage_ops,
 #ifdef CONFIG_PAGE_POISONING
 	&page_poisoning_ops,
+#endif
+#ifdef CONFIG_PAGE_OWNER
+	&page_owner_ops,
 #endif
 };
 

mm/page_owner.c

···
+#include <linux/debugfs.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/bootmem.h>
+#include <linux/stacktrace.h>
+#include <linux/page_owner.h>
+#include "internal.h"
+
+static bool page_owner_disabled = true;
+bool page_owner_inited __read_mostly;
+
+static int early_page_owner_param(char *buf)
+{
+	if (!buf)
+		return -EINVAL;
+
+	if (strcmp(buf, "on") == 0)
+		page_owner_disabled = false;
+
+	return 0;
+}
+early_param("page_owner", early_page_owner_param);
+
+static bool need_page_owner(void)
+{
+	if (page_owner_disabled)
+		return false;
+
+	return true;
+}
+
+static void init_page_owner(void)
+{
+	if (page_owner_disabled)
+		return;
+
+	page_owner_inited = true;
+}
+
+struct page_ext_operations page_owner_ops = {
+	.need = need_page_owner,
+	.init = init_page_owner,
+};
+
+void __reset_page_owner(struct page *page, unsigned int order)
+{
+	int i;
+	struct page_ext *page_ext;
+
+	for (i = 0; i < (1 << order); i++) {
+		page_ext = lookup_page_ext(page + i);
+		__clear_bit(PAGE_EXT_OWNER, &page_ext->flags);
+	}
+}
+
+void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
+{
+	struct page_ext *page_ext;
+	struct stack_trace *trace;
+
+	page_ext = lookup_page_ext(page);
+
+	trace = &page_ext->trace;
+	trace->nr_entries = 0;
+	trace->max_entries = ARRAY_SIZE(page_ext->trace_entries);
+	trace->entries = &page_ext->trace_entries[0];
+	trace->skip = 3;
+	save_stack_trace(&page_ext->trace);
+
+	page_ext->order = order;
+	page_ext->gfp_mask = gfp_mask;
+
+	__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
+}
+
+static ssize_t
+print_page_owner(char __user *buf, size_t count, unsigned long pfn,
+		struct page *page, struct page_ext *page_ext)
+{
+	int ret;
+	int pageblock_mt, page_mt;
+	char *kbuf;
+
+	kbuf = kmalloc(count, GFP_KERNEL);
+	if (!kbuf)
+		return -ENOMEM;
+
+	ret = snprintf(kbuf, count,
+			"Page allocated via order %u, mask 0x%x\n",
+			page_ext->order, page_ext->gfp_mask);
+
+	if (ret >= count)
+		goto err;
+
+	/* Print information relevant to grouping pages by mobility */
+	pageblock_mt = get_pfnblock_migratetype(page, pfn);
+	page_mt  = gfpflags_to_migratetype(page_ext->gfp_mask);
+	ret += snprintf(kbuf + ret, count - ret,
+			"PFN %lu Block %lu type %d %s Flags %s%s%s%s%s%s%s%s%s%s%s%s\n",
+			pfn,
+			pfn >> pageblock_order,
+			pageblock_mt,
+			pageblock_mt != page_mt ? "Fallback" : "        ",
+			PageLocked(page)	? "K" : " ",
+			PageError(page)		? "E" : " ",
+			PageReferenced(page)	? "R" : " ",
+			PageUptodate(page)	? "U" : " ",
+			PageDirty(page)		? "D" : " ",
+			PageLRU(page)		? "L" : " ",
+			PageActive(page)	? "A" : " ",
+			PageSlab(page)		? "S" : " ",
+			PageWriteback(page)	? "W" : " ",
+			PageCompound(page)	? "C" : " ",
+			PageSwapCache(page)	? "B" : " ",
+			PageMappedToDisk(page)	? "M" : " ");
+
+	if (ret >= count)
+		goto err;
+
+	ret += snprint_stack_trace(kbuf + ret, count - ret,
+					&page_ext->trace, 0);
+	if (ret >= count)
+		goto err;
+
+	ret += snprintf(kbuf + ret, count - ret, "\n");
+	if (ret >= count)
+		goto err;
+
+	if (copy_to_user(buf, kbuf, ret))
+		ret = -EFAULT;
+
+	kfree(kbuf);
+	return ret;
+
+err:
+	kfree(kbuf);
+	return -ENOMEM;
+}
+
+static ssize_t
+read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+	unsigned long pfn;
+	struct page *page;
+	struct page_ext *page_ext;
+
+	if (!page_owner_inited)
+		return -EINVAL;
+
+	page = NULL;
+	pfn = min_low_pfn + *ppos;
+
+	/* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */
+	while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0)
+		pfn++;
+
+	drain_all_pages(NULL);
+
+	/* Find an allocated page */
+	for (; pfn < max_pfn; pfn++) {
+		/*
+		 * If the new page is in a new MAX_ORDER_NR_PAGES area,
+		 * validate the area as existing, skip it if not
+		 */
+		if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0 && !pfn_valid(pfn)) {
+			pfn += MAX_ORDER_NR_PAGES - 1;
+			continue;
+		}
+
+		/* Check for holes within a MAX_ORDER area */
+		if (!pfn_valid_within(pfn))
+			continue;
+
+		page = pfn_to_page(pfn);
+		if (PageBuddy(page)) {
+			unsigned long freepage_order = page_order_unsafe(page);
+
+			if (freepage_order < MAX_ORDER)
+				pfn += (1UL << freepage_order) - 1;
+			continue;
+		}
+
+		page_ext = lookup_page_ext(page);
+
+		/*
+		 * Pages allocated before initialization of page_owner are
+		 * non-buddy and have no page_owner info.
+		 */
+		if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
+			continue;
+
+		/* Record the next PFN to read in the file offset */
+		*ppos = (pfn - min_low_pfn) + 1;
+
+		return print_page_owner(buf, count, pfn, page, page_ext);
+	}
+
+	return 0;
+}
+
+static const struct file_operations proc_page_owner_operations = {
+	.read		= read_page_owner,
+};
+
+static int __init pageowner_init(void)
+{
+	struct dentry *dentry;
+
+	if (!page_owner_inited) {
+		pr_info("page_owner is disabled\n");
+		return 0;
+	}
+
+	dentry = debugfs_create_file("page_owner", S_IRUSR, NULL,
+			NULL, &proc_page_owner_operations);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	return 0;
+}
+module_init(pageowner_init)

mm/vmstat.c

···
 #include <linux/writeback.h>
 #include <linux/compaction.h>
 #include <linux/mm_inline.h>
+#include <linux/page_ext.h>
+#include <linux/page_owner.h>
 
 #include "internal.h"
 
···
 	return 0;
 }
 
+#ifdef CONFIG_PAGE_OWNER
+static void pagetypeinfo_showmixedcount_print(struct seq_file *m,
+							pg_data_t *pgdat,
+							struct zone *zone)
+{
+	struct page *page;
+	struct page_ext *page_ext;
+	unsigned long pfn = zone->zone_start_pfn, block_end_pfn;
+	unsigned long end_pfn = pfn + zone->spanned_pages;
+	unsigned long count[MIGRATE_TYPES] = { 0, };
+	int pageblock_mt, page_mt;
+	int i;
+
+	/* Scan block by block. First and last block may be incomplete */
+	pfn = zone->zone_start_pfn;
+
+	/*
+	 * Walk the zone in pageblock_nr_pages steps. If a page block spans
+	 * a zone boundary, it will be double counted between zones. This does
+	 * not matter as the mixed block count will still be correct
+	 */
+	for (; pfn < end_pfn; ) {
+		if (!pfn_valid(pfn)) {
+			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
+			continue;
+		}
+
+		block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
+		block_end_pfn = min(block_end_pfn, end_pfn);
+
+		page = pfn_to_page(pfn);
+		pageblock_mt = get_pfnblock_migratetype(page, pfn);
+
+		for (; pfn < block_end_pfn; pfn++) {
+			if (!pfn_valid_within(pfn))
+				continue;
+
+			page = pfn_to_page(pfn);
+			if (PageBuddy(page)) {
+				pfn += (1UL << page_order(page)) - 1;
+				continue;
+			}
+
+			if (PageReserved(page))
+				continue;
+
+			page_ext = lookup_page_ext(page);
+
+			if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
+				continue;
+
+			page_mt = gfpflags_to_migratetype(page_ext->gfp_mask);
+			if (pageblock_mt != page_mt) {
+				if (is_migrate_cma(pageblock_mt))
+					count[MIGRATE_MOVABLE]++;
+				else
+					count[pageblock_mt]++;
+
+				pfn = block_end_pfn;
+				break;
+			}
+			pfn += (1UL << page_ext->order) - 1;
+		}
+	}
+
+	/* Print counts */
+	seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
+	for (i = 0; i < MIGRATE_TYPES; i++)
+		seq_printf(m, "%12lu ", count[i]);
+	seq_putc(m, '\n');
+}
+#endif /* CONFIG_PAGE_OWNER */
+
+/*
+ * Print out the number of pageblocks for each migratetype that contain pages
+ * of other types. This gives an indication of how well fallbacks are being
+ * contained by rmqueue_fallback(). It requires information from PAGE_OWNER
+ * to determine what is going on
+ */
+static void pagetypeinfo_showmixedcount(struct seq_file *m, pg_data_t *pgdat)
+{
+#ifdef CONFIG_PAGE_OWNER
+	int mtype;
+
+	if (!page_owner_inited)
+		return;
+
+	drain_all_pages(NULL);
+
+	seq_printf(m, "\n%-23s", "Number of mixed blocks ");
+	for (mtype = 0; mtype < MIGRATE_TYPES; mtype++)
+		seq_printf(m, "%12s ", migratetype_names[mtype]);
+	seq_putc(m, '\n');
+
+	walk_zones_in_node(m, pgdat, pagetypeinfo_showmixedcount_print);
+#endif /* CONFIG_PAGE_OWNER */
+}
+
 /*
  * This prints out statistics in relation to grouping pages by mobility.
  * It is expensive to collect so do not constantly read the file.
···
 	seq_putc(m, '\n');
 	pagetypeinfo_showfree(m, pgdat);
 	pagetypeinfo_showblockcount(m, pgdat);
+	pagetypeinfo_showmixedcount(m, pgdat);
 
 	return 0;
 }

tools/vm/Makefile

···
 # Makefile for vm tools
 #
-TARGETS=page-types slabinfo
+TARGETS=page-types slabinfo page_owner_sort
 
 LIB_DIR = ../lib/api
 LIBS = $(LIB_DIR)/libapikfs.a
···
 	$(CC) $(CFLAGS) -o $@ $< $(LDFLAGS)
 
 clean:
-	$(RM) page-types slabinfo
+	$(RM) page-types slabinfo page_owner_sort
 	make -C $(LIB_DIR) clean

tools/vm/page_owner_sort.c

···
+/*
+ * User-space helper to sort the output of /sys/kernel/debug/page_owner
+ *
+ * Example use:
+ * cat /sys/kernel/debug/page_owner > page_owner_full.txt
+ * grep -v ^PFN page_owner_full.txt > page_owner.txt
+ * ./sort page_owner.txt sorted_page_owner.txt
+*/
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <string.h>
+
+struct block_list {
+	char *txt;
+	int len;
+	int num;
+};
+
+
+static struct block_list *list;
+static int list_size;
+static int max_size;
+
+struct block_list *block_head;
+
+int read_block(char *buf, int buf_size, FILE *fin)
+{
+	char *curr = buf, *const buf_end = buf + buf_size;
+
+	while (buf_end - curr > 1 && fgets(curr, buf_end - curr, fin)) {
+		if (*curr == '\n') /* empty line */
+			return curr - buf;
+		curr += strlen(curr);
+	}
+
+	return -1; /* EOF or no space left in buf. */
+}
+
+static int compare_txt(const void *p1, const void *p2)
+{
+	const struct block_list *l1 = p1, *l2 = p2;
+
+	return strcmp(l1->txt, l2->txt);
+}
+
+static int compare_num(const void *p1, const void *p2)
+{
+	const struct block_list *l1 = p1, *l2 = p2;
+
+	return l2->num - l1->num;
+}
+
+static void add_list(char *buf, int len)
+{
+	if (list_size != 0 &&
+	    len == list[list_size-1].len &&
+	    memcmp(buf, list[list_size-1].txt, len) == 0) {
+		list[list_size-1].num++;
+		return;
+	}
+	if (list_size == max_size) {
+		printf("max_size too small??\n");
+		exit(1);
+	}
+	list[list_size].txt = malloc(len+1);
+	list[list_size].len = len;
+	list[list_size].num = 1;
+	memcpy(list[list_size].txt, buf, len);
+	list[list_size].txt[len] = 0;
+	list_size++;
+	if (list_size % 1000 == 0) {
+		printf("loaded %d\r", list_size);
+		fflush(stdout);
+	}
+}
+
+#define BUF_SIZE	1024
+
+int main(int argc, char **argv)
+{
+	FILE *fin, *fout;
+	char buf[BUF_SIZE];
+	int ret, i, count;
+	struct block_list *list2;
+	struct stat st;
+
+	if (argc < 3) {
+		printf("Usage: ./program <input> <output>\n");
+		perror("open: ");
+		exit(1);
+	}
+
+	fin = fopen(argv[1], "r");
+	fout = fopen(argv[2], "w");
+	if (!fin || !fout) {
+		printf("Usage: ./program <input> <output>\n");
+		perror("open: ");
+		exit(1);
+	}
+
+	fstat(fileno(fin), &st);
+	max_size = st.st_size / 100; /* hack ... */
+
+	list = malloc(max_size * sizeof(*list));
+
+	for ( ; ; ) {
+		ret = read_block(buf, BUF_SIZE, fin);
+		if (ret < 0)
+			break;
+
+		add_list(buf, ret);
+	}
+
+	printf("loaded %d\n", list_size);
+
+	printf("sorting ....\n");
+
+	qsort(list, list_size, sizeof(list[0]), compare_txt);
+
+	list2 = malloc(sizeof(*list) * list_size);
+
+	printf("culling\n");
+
+	for (i = count = 0; i < list_size; i++) {
+		if (count == 0 ||
+		    strcmp(list2[count-1].txt, list[i].txt) != 0) {
+			list2[count++] = list[i];
+		} else {
+			list2[count-1].num += list[i].num;
+		}
+	}
+
+	qsort(list2, count, sizeof(list[0]), compare_num);
+
+	for (i = 0; i < count; i++)
+		fprintf(fout, "%d times:\n%s\n", list2[i].num, list2[i].txt);
+
+	return 0;
+}