Debugging: Keep track of page owners

diff -puN /dev/null Documentation/page_owner.c
@@ -0,0 +1,141 @@
+/*
+ * 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, FILE *fin)
+{
+	int ret = 0;
+	int hit = 0;
+	char *curr = buf;
+
+	for (;;) {
+		*curr = getc(fin);
+		if (*curr == EOF) return -1;
+
+		ret++;
+		if (*curr == '\n' && hit == 1)
+			return ret - 1;
+		else if (*curr == '\n')
+			hit = 1;
+		else
+			hit = 0;
+		curr++;
+	}
+}
+
+static int compare_txt(struct block_list *l1, struct block_list *l2)
+{
+	return strcmp(l1->txt, l2->txt);
+}
+
+static int compare_num(struct block_list *l1, struct block_list *l2)
+{
+	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);
+	}
+}
+
+int main(int argc, char **argv)
+{
+	FILE *fin, *fout;
+	char buf[1024];
+	int ret, i, count;
+	struct block_list *list2;
+	struct stat st;
+
+	fin = fopen(argv[1], "r");
+	fout = fopen(argv[2], "w");
+	if (!fin || !fout) {
+		printf("Usage: ./program <input> <output>\n");
+		perror("open: ");
+		exit(2);
+	}
+
+	fstat(fileno(fin), &st);
+	max_size = st.st_size / 100; /* hack ... */
+
+	list = malloc(max_size * sizeof(*list));
+
+	for(;;) {
+		ret = read_block(buf, fin);
+		if (ret < 0)
+			break;
+
+		buf[ret] = '\0';
+		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;
+}

diff -puN include/linux/mm_types.h~pageowner include/linux/mm_types.h
@@ -12,6 +12,7 @@
 #include <linux/cpumask.h>
 #include <linux/page-debug-flags.h>
 #include <linux/uprobes.h>
+#include <linux/stacktrace.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
 

@@ -175,6 +176,12 @@ struct page {
 	 */
 	void *shadow;
 #endif
+#ifdef CONFIG_PAGE_OWNER
+	int order;
+	unsigned int gfp_mask;
+	struct stack_trace trace;
+	unsigned long trace_entries[8];
+#endif
 }
 /*
  * The struct page can be forced to be double word aligned so that atomic ops

diff -puN include/linux/stacktrace.h~pageowner include/linux/stacktrace.h
@@ -20,6 +20,8 @@ extern void save_stack_trace_tsk(struct
 				struct stack_trace *trace);
 
 extern void print_stack_trace(struct stack_trace *trace, int spaces);
+extern int  snprint_stack_trace(char *buf, int buf_len,
+				struct stack_trace *trace, int spaces);
 
 #ifdef CONFIG_USER_STACKTRACE_SUPPORT
 extern void save_stack_trace_user(struct stack_trace *trace);

@@ -32,6 +34,7 @@ extern void save_stack_trace_user(struct
 # define save_stack_trace_tsk(tsk, trace)		do { } while (0)
 # define save_stack_trace_user(trace)			do { } while (0)
 # define print_stack_trace(trace, spaces)		do { } while (0)
+# define snprint_stack_trace(buf, len, trace, spaces)	do { } while (0)
 #endif
 
 #endif

diff -puN kernel/stacktrace.c~pageowner kernel/stacktrace.c
@@ -11,6 +11,29 @@
 #include <linux/kallsyms.h>
 #include <linux/stacktrace.h>
 
+int snprint_stack_trace(char *buf, int buf_len, struct stack_trace *trace,
+			int spaces)
+{
+	int ret = 0;
+	int i;
+
+	if (WARN_ON(!trace->entries))
+		return 0;
+
+	for (i = 0; i < trace->nr_entries; i++) {
+		unsigned long ip = trace->entries[i];
+		int printed = snprintf(buf, buf_len, "%*c[<%p>] %pS\n",
+				1 + spaces, ' ',
+				(void *) ip, (void *) ip);
+		buf_len -= printed;
+		ret += printed;
+		buf += printed;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(snprint_stack_trace);
+
 void print_stack_trace(struct stack_trace *trace, int spaces)
 {
 	int i;

diff -puN mm/page_alloc.c~pageowner mm/page_alloc.c
@@ -437,6 +437,9 @@ static inline void set_page_order(struct
 {
 	set_page_private(page, order);
 	__SetPageBuddy(page);
+#ifdef CONFIG_PAGE_OWNER
+	page->order = -1;
+#endif
 }
 
 static inline void rmv_page_order(struct page *page)

@@ -2250,6 +2253,22 @@ __perform_reclaim(gfp_t gfp_mask, unsign
 	return progress;
 }
 
+static void set_page_owner(struct page *page, unsigned int order,
+			unsigned int gfp_mask)
+{
+#ifdef CONFIG_PAGE_OWNER
+	struct stack_trace *trace = &page->trace;
+	trace->nr_entries = 0;
+	trace->max_entries = ARRAY_SIZE(page->trace_entries);
+	trace->entries = &page->trace_entries[0];
+	trace->skip = 3;
+	save_stack_trace(&page->trace);
+
+	page->order = (int) order;
+	page->gfp_mask = gfp_mask;
+#endif /* CONFIG_PAGE_OWNER */
+}
+
 /* The really slow allocator path where we enter direct reclaim */
 static inline struct page *
 __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,

@@ -2285,6 +2304,8 @@ retry:
 		goto retry;
 	}
 
+	if (page)
+		set_page_owner(page, order, gfp_mask);
 	return page;
 }
 

@@ -2593,6 +2614,8 @@ nopage:
 	warn_alloc_failed(gfp_mask, order, NULL);
 	return page;
 got_pg:
+	if (page)
+		set_page_owner(page, order, gfp_mask);
 	if (kmemcheck_enabled)
 		kmemcheck_pagealloc_alloc(page, order, gfp_mask);
 

@@ -2665,6 +2688,9 @@ out:
 	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
 		goto retry_cpuset;
 
+	if (page)
+		set_page_owner(page, order, gfp_mask);
+
 	return page;
 }
 EXPORT_SYMBOL(__alloc_pages_nodemask);

@@ -3869,6 +3895,9 @@ void __meminit memmap_init_zone(unsigned
 		if (!is_highmem_idx(zone))
 			set_page_address(page, __va(pfn << PAGE_SHIFT));
 #endif
+#ifdef CONFIG_PAGE_OWNER
+		page->order = -1;
+#endif
 	}
 }
 

163 lines not on this page · raw message

114 lines not on this page · raw message

diff -puN include/linux/mm_types.h~debugging-keep-track-of-page-owners-fix include/linux/mm_types.h
@@ -8,6 +8,7 @@
 #include <linux/spinlock.h>
 #include <linux/rbtree.h>
 #include <linux/rwsem.h>
+#include <linux/stacktrace.h>
 #include <linux/completion.h>
 #include <linux/cpumask.h>
 #include <linux/page-debug-flags.h>

@@ -180,7 +181,8 @@ struct page {
 #ifdef CONFIG_PAGE_OWNER
 	int order;
 	unsigned int gfp_mask;
-	unsigned long trace[8];
+	struct stack_trace trace;
+	unsigned long trace_entries[8];
 #endif
 }
 /*

diff -puN include/linux/stacktrace.h~debugging-keep-track-of-page-owners-fix include/linux/stacktrace.h
@@ -20,6 +20,8 @@ extern void save_stack_trace_tsk(struct 
 				struct stack_trace *trace);
 
 extern void print_stack_trace(struct stack_trace *trace, int spaces);
+extern int  snprint_stack_trace(char *buf, int buf_len,
+				struct stack_trace *trace, int spaces);
 
 #ifdef CONFIG_USER_STACKTRACE_SUPPORT
 extern void save_stack_trace_user(struct stack_trace *trace);

@@ -32,6 +34,7 @@ extern void save_stack_trace_user(struct
 # define save_stack_trace_tsk(tsk, trace)		do { } while (0)
 # define save_stack_trace_user(trace)			do { } while (0)
 # define print_stack_trace(trace, spaces)		do { } while (0)
+# define snprint_stack_trace(buf, len, trace, spaces)	do { } while (0)
 #endif
 
 #endif

diff -puN kernel/stacktrace.c~debugging-keep-track-of-page-owners-fix kernel/stacktrace.c
@@ -11,6 +11,29 @@
 #include <linux/kallsyms.h>
 #include <linux/stacktrace.h>
 
+int snprint_stack_trace(char *buf, int buf_len, struct stack_trace *trace,
+			int spaces)
+{
+	int ret = 0;
+	int i;
+
+	if (WARN_ON(!trace->entries))
+		return 0;
+
+	for (i = 0; i < trace->nr_entries; i++) {
+		unsigned long ip = trace->entries[i];
+		int printed = snprintf(buf, buf_len, "%*c[<%p>] %pS\n",
+				1 + spaces, ' ',
+				(void *) ip, (void *) ip);
+		buf_len -= printed;
+		ret += printed;
+		buf += printed;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(snprint_stack_trace);
+
 void print_stack_trace(struct stack_trace *trace, int spaces)
 {
 	int i;

101 lines not on this page · raw message

diff -puN mm/pageowner.c~debugging-keep-track-of-page-owners-fix mm/pageowner.c
@@ -26,12 +26,8 @@ read_page_owner(struct file *file, char 
 {
 	unsigned long pfn;
 	struct page *page;
-	char *kbuf, *modname;
-	const char *symname;
+	char *kbuf;
 	int ret = 0;
-	char namebuf[128];
-	unsigned long offset = 0, symsize;
-	int i;
 	ssize_t num_written = 0;
 	int blocktype = 0, pagetype = 0;
 

@@ -67,7 +63,7 @@ read_page_owner(struct file *file, char 
 				pfn);
 
 		/* Stop search if page is allocated and has trace info */
-		if (page->order >= 0 && page->trace[0]) {
+		if (page->order >= 0 && page->trace.nr_entries) {
 			//intk("stopped search at pfn: %ld\n", pfn);
 			break;
 		}

@@ -126,20 +122,13 @@ read_page_owner(struct file *file, char 
 
 	num_written = ret;
 
-	for (i = 0; i < 8; i++) {
-		if (!page->trace[i])
-			break;
-		symname = kallsyms_lookup(page->trace[i], &symsize, &offset,
-					&modname, namebuf);
-		ret = snprintf(kbuf + num_written, count - num_written,
-				"[0x%lx] %s+%lu\n",
-				page->trace[i], namebuf, offset);
-		if (ret >= count - num_written) {
-			ret = -ENOMEM;
-			goto out;
-		}
-		num_written += ret;
+	ret = snprint_stack_trace(kbuf + num_written, count - num_written,
+				  &page->trace, 0);
+	if (ret >= count - num_written) {
+		ret = -ENOMEM;
+		goto out;
 	}
+	num_written += ret;
 
 	ret = snprintf(kbuf + num_written, count - num_written, "\n");
 	if (ret >= count - num_written) {

diff -puN mm/vmstat.c~debugging-keep-track-of-page-owners-fix mm/vmstat.c
@@ -985,7 +985,10 @@ static void pagetypeinfo_showmixedcount_
 
 			pagetype = allocflags_to_migratetype(page->gfp_mask);
 			if (pagetype != mtype) {
-				count[mtype]++;
+				if (is_migrate_cma(pagetype))
+					count[MIGRATE_MOVABLE]++;
+				else
+					count[mtype]++;
 				break;
 			}