perf kmem: Implement page allocation analysis (v6)

The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events.

It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does.

The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only.

If none of these --slab nor --page is specified, --slab is implied.

  # perf kmem stat --page --alloc --line 10

-------------------------------------------------------------------------------
PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags
-------------------------------------------------------------------------------

            4045014 |               16 |        1 |     2 |  RECLAIM |  00285250
            4143980 |               16 |        1 |     2 |  RECLAIM |  00285250
            3938658 |               16 |        1 |     2 |  RECLAIM |  00285250
            4045400 |               16 |        1 |     2 |  RECLAIM |  00285250
            3568708 |               16 |        1 |     2 |  RECLAIM |  00285250
            3729824 |               16 |        1 |     2 |  RECLAIM |  00285250
            3657210 |               16 |        1 |     2 |  RECLAIM |  00285250
            4120750 |               16 |        1 |     2 |  RECLAIM |  00285250
            3678850 |               16 |        1 |     2 |  RECLAIM |  00285250
            3693874 |               16 |        1 |     2 |  RECLAIM |  00285250

... | ... | ... | ... | ... | ...
-------------------------------------------------------------------------------

SUMMARY (page allocator)
========================

  Total allocation requests     :           44,260   [          177,256 KB ]
  Total free requests           :              117   [              468 KB ]

  Total alloc+freed requests    :               49   [              196 KB ]
  Total alloc-only requests     :           44,211   [          177,060 KB ]
  Total free-only requests      :               68   [              272 KB ]

Total allocation failures : 0 [ 0 KB ]

Order Unmovable Reclaimable Movable Reserved CMA/Isolated
----- ------------ ------------ ------------ ------------ ------------

      0            32             .        44,210             .             .
      1             .             .             .             .             .
      2             .            18             .             .             .
      3             .             .             .             .             .
      4             .             .             .             .             .
      5             .             .             .             .             .
      6             .             .             .             .             .
      7             .             .             .             .             .
      8             .             .             .             .             .
      9             .             .             .             .             .
     10             .             .             .             .             .

Signed-off-by Namhyung Kim <[email protected]>

---
 tools/perf/Documentation/perf-kmem.txt |   8 +-
 tools/perf/builtin-kmem.c              | 500 +++++++++++++++++++++++++++++++--
 2 files changed, 491 insertions(+), 17 deletions(-)

tools/perf/Documentation/perf-kmem.txt +7 -1

index 150253cc3c97..23219c65c16f 100644
@@ -3,7 +3,7 @@ perf-kmem(1)
 
 NAME
 ----
-perf-kmem - Tool to trace/measure kernel memory(slab) properties
+perf-kmem - Tool to trace/measure kernel memory properties
 
 SYNOPSIS
 --------

@@ -46,6 +46,12 @@ OPTIONS
 --raw-ip::
 	Print raw ip instead of symbol
 
+--slab::
+	Analyze SLAB allocator events.
+
+--page::
+	Analyze page allocator events
+
 SEE ALSO
 --------
 linkperf:perf-record[1]

tools/perf/builtin-kmem.c +484 -16

index 4ebf65c79434..63ea01349b6e 100644
@@ -22,6 +22,11 @@
 #include <linux/string.h>
 #include <locale.h>
 
+static int	kmem_slab;
+static int	kmem_page;
+
+static long	kmem_page_size;
+
 struct alloc_stat;
 typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *);
 

@@ -226,6 +231,244 @@ static int perf_evsel__process_free_event(struct perf_evsel *evsel,
 	return 0;
 }
 
+static u64 total_page_alloc_bytes;
+static u64 total_page_free_bytes;
+static u64 total_page_nomatch_bytes;
+static u64 total_page_fail_bytes;
+static unsigned long nr_page_allocs;
+static unsigned long nr_page_frees;
+static unsigned long nr_page_fails;
+static unsigned long nr_page_nomatch;
+
+static bool use_pfn;
+
+#define MAX_MIGRATE_TYPES  6
+#define MAX_PAGE_ORDER     11
+
+static int order_stats[MAX_PAGE_ORDER][MAX_MIGRATE_TYPES];
+
+struct page_stat {
+	struct rb_node 	node;
+	u64 		page;
+	int 		order;
+	unsigned 	gfp_flags;
+	unsigned 	migrate_type;
+	u64		alloc_bytes;
+	u64 		free_bytes;
+	int 		nr_alloc;
+	int 		nr_free;
+};
+
+static struct rb_root page_tree;
+static struct rb_root page_alloc_tree;
+static struct rb_root page_alloc_sorted;
+
+static struct page_stat *search_page(unsigned long page, bool create)
+{
+	struct rb_node **node = &page_tree.rb_node;
+	struct rb_node *parent = NULL;
+	struct page_stat *data;
+
+	while (*node) {
+		s64 cmp;
+
+		parent = *node;
+		data = rb_entry(*node, struct page_stat, node);
+
+		cmp = data->page - page;
+		if (cmp < 0)
+			node = &parent->rb_left;
+		else if (cmp > 0)
+			node = &parent->rb_right;
+		else
+			return data;
+	}
+
+	if (!create)
+		return NULL;
+
+	data = zalloc(sizeof(*data));
+	if (data != NULL) {
+		data->page = page;
+
+		rb_link_node(&data->node, parent, node);
+		rb_insert_color(&data->node, &page_tree);
+	}
+
+	return data;
+}
+
+static int page_stat_cmp(struct page_stat *a, struct page_stat *b)
+{
+	if (a->page > b->page)
+		return -1;
+	if (a->page < b->page)
+		return 1;
+	if (a->order > b->order)
+		return -1;
+	if (a->order < b->order)
+		return 1;
+	if (a->migrate_type > b->migrate_type)
+		return -1;
+	if (a->migrate_type < b->migrate_type)
+		return 1;
+	if (a->gfp_flags > b->gfp_flags)
+		return -1;
+	if (a->gfp_flags < b->gfp_flags)
+		return 1;
+	return 0;
+}
+
+static struct page_stat *search_page_alloc_stat(struct page_stat *stat, bool create)
+{
+	struct rb_node **node = &page_alloc_tree.rb_node;
+	struct rb_node *parent = NULL;
+	struct page_stat *data;
+
+	while (*node) {
+		s64 cmp;
+
+		parent = *node;
+		data = rb_entry(*node, struct page_stat, node);
+
+		cmp = page_stat_cmp(data, stat);
+		if (cmp < 0)
+			node = &parent->rb_left;
+		else if (cmp > 0)
+			node = &parent->rb_right;
+		else
+			return data;
+	}
+
+	if (!create)
+		return NULL;
+
+	data = zalloc(sizeof(*data));
+	if (data != NULL) {
+		data->page = stat->page;
+		data->order = stat->order;
+		data->gfp_flags = stat->gfp_flags;
+		data->migrate_type = stat->migrate_type;
+
+		rb_link_node(&data->node, parent, node);
+		rb_insert_color(&data->node, &page_alloc_tree);
+	}
+
+	return data;
+}
+
+static bool valid_page(u64 pfn_or_page)
+{
+	if (use_pfn && pfn_or_page == -1UL)
+		return false;
+	if (!use_pfn && pfn_or_page == 0)
+		return false;
+	return true;
+}
+
+static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
+						struct perf_sample *sample)
+{
+	u64 page;
+	unsigned int order = perf_evsel__intval(evsel, sample, "order");
+	unsigned int gfp_flags = perf_evsel__intval(evsel, sample, "gfp_flags");
+	unsigned int migrate_type = perf_evsel__intval(evsel, sample,
+						       "migratetype");
+	u64 bytes = kmem_page_size << order;
+	struct page_stat *stat;
+	struct page_stat this = {
+		.order = order,
+		.gfp_flags = gfp_flags,
+		.migrate_type = migrate_type,
+	};
+
+	if (use_pfn)
+		page = perf_evsel__intval(evsel, sample, "pfn");
+	else
+		page = perf_evsel__intval(evsel, sample, "page");
+
+	nr_page_allocs++;
+	total_page_alloc_bytes += bytes;
+
+	if (!valid_page(page)) {
+		nr_page_fails++;
+		total_page_fail_bytes += bytes;
+
+		return 0;
+	}
+
+	/*
+	 * This is to find the current page (with correct gfp flags and
+	 * migrate type) at free event.
+	 */
+	stat = search_page(page, true);
+	if (stat == NULL)
+		return -ENOMEM;
+
+	stat->order = order;
+	stat->gfp_flags = gfp_flags;
+	stat->migrate_type = migrate_type;
+
+	this.page = page;
+	stat = search_page_alloc_stat(&this, true);
+	if (stat == NULL)
+		return -ENOMEM;
+
+	stat->nr_alloc++;
+	stat->alloc_bytes += bytes;
+
+	order_stats[order][migrate_type]++;
+
+	return 0;
+}
+
+static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
+						struct perf_sample *sample)
+{
+	u64 page;
+	unsigned int order = perf_evsel__intval(evsel, sample, "order");
+	u64 bytes = kmem_page_size << order;
+	struct page_stat *stat;
+	struct page_stat this = {
+		.order = order,
+	};
+
+	if (use_pfn)
+		page = perf_evsel__intval(evsel, sample, "pfn");
+	else
+		page = perf_evsel__intval(evsel, sample, "page");
+
+	nr_page_frees++;
+	total_page_free_bytes += bytes;
+
+	stat = search_page(page, false);
+	if (stat == NULL) {
+		pr_debug2("missing free at page %"PRIx64" (order: %d)\n",
+			  page, order);
+
+		nr_page_nomatch++;
+		total_page_nomatch_bytes += bytes;
+
+		return 0;
+	}
+
+	this.page = page;
+	this.gfp_flags = stat->gfp_flags;
+	this.migrate_type = stat->migrate_type;
+
+	rb_erase(&stat->node, &page_tree);
+	free(stat);
+
+	stat = search_page_alloc_stat(&this, false);
+	if (stat == NULL)
+		return -ENOENT;
+
+	stat->nr_free++;
+	stat->free_bytes += bytes;
+
+	return 0;
+}
+
 typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
 				  struct perf_sample *sample);
 

@@ -270,8 +513,9 @@ static double fragmentation(unsigned long n_req, unsigned long n_alloc)
 		return 100.0 - (100.0 * n_req / n_alloc);
 }
 
-static void __print_result(struct rb_root *root, struct perf_session *session,
-			   int n_lines, int is_caller)
+static void __print_slab_result(struct rb_root *root,
+				struct perf_session *session,
+				int n_lines, int is_caller)
 {
 	struct rb_node *next;
 	struct machine *machine = &session->machines.host;

@@ -323,9 +567,56 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 	printf("%.105s\n", graph_dotted_line);
 }
 
-static void print_summary(void)
+static const char * const migrate_type_str[] = {
+	"UNMOVABL",
+	"RECLAIM",
+	"MOVABLE",
+	"RESERVED",
+	"CMA/ISLT",
+	"UNKNOWN",
+};
+
+static void __print_page_result(struct rb_root *root,
+				struct perf_session *session __maybe_unused,
+				int n_lines)
+{
+	struct rb_node *next = rb_first(root);
+	const char *format;
+
+	printf("\n%.80s\n", graph_dotted_line);
+	printf(" %-16s | Total alloc (KB) | Hits      | Order | Mig.type | GFP flags\n",
+	       use_pfn ? "PFN" : "Page");
+	printf("%.80s\n", graph_dotted_line);
+
+	if (use_pfn)
+		format = " %16llu | %'16llu | %'9d | %5d | %8s |  %08lx\n";
+	else
+		format = " %016llx | %'16llu | %'9d | %5d | %8s |  %08lx\n";
+
+	while (next && n_lines--) {
+		struct page_stat *data;
+
+		data = rb_entry(next, struct page_stat, node);
+
+		printf(format, (unsigned long long)data->page,
+		       (unsigned long long)data->alloc_bytes / 1024,
+		       data->nr_alloc, data->order,
+		       migrate_type_str[data->migrate_type],
+		       (unsigned long)data->gfp_flags);
+
+		next = rb_next(next);
+	}
+
+	if (n_lines == -1)
+		printf(" ...              | ...              | ...       | ...   | ...      | ...     \n");
+
+	printf("%.80s\n", graph_dotted_line);
+}
+
+static void print_slab_summary(void)
 {
-	printf("\nSUMMARY\n=======\n");
+	printf("\nSUMMARY (SLAB allocator)");
+	printf("\n========================\n");
 	printf("Total bytes requested: %'lu\n", total_requested);
 	printf("Total bytes allocated: %'lu\n", total_allocated);
 	printf("Total bytes wasted on internal fragmentation: %'lu\n",

@@ -335,13 +626,73 @@ static void print_summary(void)
 	printf("Cross CPU allocations: %'lu/%'lu\n", nr_cross_allocs, nr_allocs);
 }
 
-static void print_result(struct perf_session *session)
+static void print_page_summary(void)
+{
+	int o, m;
+	u64 nr_alloc_freed = nr_page_frees - nr_page_nomatch;
+	u64 total_alloc_freed_bytes = total_page_free_bytes - total_page_nomatch_bytes;
+
+	printf("\nSUMMARY (page allocator)");
+	printf("\n========================\n");
+	printf("%-30s: %'16lu   [ %'16"PRIu64" KB ]\n", "Total allocation requests",
+	       nr_page_allocs, total_page_alloc_bytes / 1024);
+	printf("%-30s: %'16lu   [ %'16"PRIu64" KB ]\n", "Total free requests",
+	       nr_page_frees, total_page_free_bytes / 1024);
+	printf("\n");
+
+	printf("%-30s: %'16lu   [ %'16"PRIu64" KB ]\n", "Total alloc+freed requests",
+	       nr_alloc_freed, (total_alloc_freed_bytes) / 1024);
+	printf("%-30s: %'16lu   [ %'16"PRIu64" KB ]\n", "Total alloc-only requests",
+	       nr_page_allocs - nr_alloc_freed,
+	       (total_page_alloc_bytes - total_alloc_freed_bytes) / 1024);
+	printf("%-30s: %'16lu   [ %'16"PRIu64" KB ]\n", "Total free-only requests",
+	       nr_page_nomatch, total_page_nomatch_bytes / 1024);
+	printf("\n");
+
+	printf("%-30s: %'16lu   [ %'16"PRIu64" KB ]\n", "Total allocation failures",
+	       nr_page_fails, total_page_fail_bytes / 1024);
+	printf("\n");
+
+	printf("%5s  %12s  %12s  %12s  %12s  %12s\n", "Order",  "Unmovable",
+	       "Reclaimable", "Movable", "Reserved", "CMA/Isolated");
+	printf("%.5s  %.12s  %.12s  %.12s  %.12s  %.12s\n", graph_dotted_line,
+	       graph_dotted_line, graph_dotted_line, graph_dotted_line,
+	       graph_dotted_line, graph_dotted_line);
+
+	for (o = 0; o < MAX_PAGE_ORDER; o++) {
+		printf("%5d", o);
+		for (m = 0; m < MAX_MIGRATE_TYPES - 1; m++) {
+			if (order_stats[o][m])
+				printf("  %'12d", order_stats[o][m]);
+			else
+				printf("  %12c", '.');
+		}
+		printf("\n");
+	}
+}
+
+static void print_slab_result(struct perf_session *session)
 {
 	if (caller_flag)
-		__print_result(&root_caller_sorted, session, caller_lines, 1);
+		__print_slab_result(&root_caller_sorted, session, caller_lines, 1);
+	if (alloc_flag)
+		__print_slab_result(&root_alloc_sorted, session, alloc_lines, 0);
+	print_slab_summary();
+}
+
+static void print_page_result(struct perf_session *session)
+{
 	if (alloc_flag)
-		__print_result(&root_alloc_sorted, session, alloc_lines, 0);
-	print_summary();
+		__print_page_result(&page_alloc_sorted, session, alloc_lines);
+	print_page_summary();
+}
+
+static void print_result(struct perf_session *session)
+{
+	if (kmem_slab)
+		print_slab_result(session);
+	if (kmem_page)
+		print_page_result(session);
 }
 
 struct sort_dimension {

@@ -353,8 +704,8 @@ struct sort_dimension {
 static LIST_HEAD(caller_sort);
 static LIST_HEAD(alloc_sort);
 
-static void sort_insert(struct rb_root *root, struct alloc_stat *data,
-			struct list_head *sort_list)
+static void sort_slab_insert(struct rb_root *root, struct alloc_stat *data,
+			     struct list_head *sort_list)
 {
 	struct rb_node **new = &(root->rb_node);
 	struct rb_node *parent = NULL;

@@ -383,8 +734,8 @@ static void sort_insert(struct rb_root *root, struct alloc_stat *data,
 	rb_insert_color(&data->node, root);
 }
 
-static void __sort_result(struct rb_root *root, struct rb_root *root_sorted,
-			  struct list_head *sort_list)
+static void __sort_slab_result(struct rb_root *root, struct rb_root *root_sorted,
+			       struct list_head *sort_list)
 {
 	struct rb_node *node;
 	struct alloc_stat *data;

@@ -396,26 +747,79 @@ static void __sort_result(struct rb_root *root, struct rb_root *root_sorted,
 
 		rb_erase(node, root);
 		data = rb_entry(node, struct alloc_stat, node);
-		sort_insert(root_sorted, data, sort_list);
+		sort_slab_insert(root_sorted, data, sort_list);
+	}
+}
+
+static void sort_page_insert(struct rb_root *root, struct page_stat *data)
+{
+	struct rb_node **new = &root->rb_node;
+	struct rb_node *parent = NULL;
+
+	while (*new) {
+		struct page_stat *this;
+		int cmp = 0;
+
+		this = rb_entry(*new, struct page_stat, node);
+		parent = *new;
+
+		/* TODO: support more sort key */
+		cmp = data->alloc_bytes - this->alloc_bytes;
+
+		if (cmp > 0)
+			new = &parent->rb_left;
+		else
+			new = &parent->rb_right;
+	}
+
+	rb_link_node(&data->node, parent, new);
+	rb_insert_color(&data->node, root);
+}
+
+static void __sort_page_result(struct rb_root *root, struct rb_root *root_sorted)
+{
+	struct rb_node *node;
+	struct page_stat *data;
+
+	for (;;) {
+		node = rb_first(root);
+		if (!node)
+			break;
+
+		rb_erase(node, root);
+		data = rb_entry(node, struct page_stat, node);
+		sort_page_insert(root_sorted, data);
 	}
 }
 
 static void sort_result(void)
 {
-	__sort_result(&root_alloc_stat, &root_alloc_sorted, &alloc_sort);
-	__sort_result(&root_caller_stat, &root_caller_sorted, &caller_sort);
+	if (kmem_slab) {
+		__sort_slab_result(&root_alloc_stat, &root_alloc_sorted,
+				   &alloc_sort);
+		__sort_slab_result(&root_caller_stat, &root_caller_sorted,
+				   &caller_sort);
+	}
+	if (kmem_page) {
+		__sort_page_result(&page_alloc_tree, &page_alloc_sorted);
+	}
 }
 
 static int __cmd_kmem(struct perf_session *session)
 {
 	int err = -EINVAL;
+	struct perf_evsel *evsel;
 	const struct perf_evsel_str_handler kmem_tracepoints[] = {
+		/* slab allocator */
 		{ "kmem:kmalloc",		perf_evsel__process_alloc_event, },
     		{ "kmem:kmem_cache_alloc",	perf_evsel__process_alloc_event, },
 		{ "kmem:kmalloc_node",		perf_evsel__process_alloc_node_event, },
     		{ "kmem:kmem_cache_alloc_node", perf_evsel__process_alloc_node_event, },
 		{ "kmem:kfree",			perf_evsel__process_free_event, },
     		{ "kmem:kmem_cache_free",	perf_evsel__process_free_event, },
+		/* page allocator */
+		{ "kmem:mm_page_alloc",		perf_evsel__process_page_alloc_event, },
+		{ "kmem:mm_page_free",		perf_evsel__process_page_free_event, },
 	};
 
 	if (!perf_session__has_traces(session, "kmem record"))

@@ -426,10 +830,20 @@ static int __cmd_kmem(struct perf_session *session)
 		goto out;
 	}
 
+	evlist__for_each(session->evlist, evsel) {
+		if (!strcmp(perf_evsel__name(evsel), "kmem:mm_page_alloc") &&
+		    perf_evsel__field(evsel, "pfn")) {
+			use_pfn = true;
+			break;
+		}
+	}
+
 	setup_pager();
 	err = perf_session__process_events(session);
-	if (err != 0)
+	if (err != 0) {
+		pr_err("error during process events: %d\n", err);
 		goto out;
+	}
 	sort_result();
 	print_result(session);
 out:

@@ -612,6 +1026,22 @@ static int parse_alloc_opt(const struct option *opt __maybe_unused,
 	return 0;
 }
 
+static int parse_slab_opt(const struct option *opt __maybe_unused,
+			  const char *arg __maybe_unused,
+			  int unset __maybe_unused)
+{
+	kmem_slab = (kmem_page + 1);
+	return 0;
+}
+
+static int parse_page_opt(const struct option *opt __maybe_unused,
+			  const char *arg __maybe_unused,
+			  int unset __maybe_unused)
+{
+	kmem_page = (kmem_slab + 1);
+	return 0;
+}
+
 static int parse_line_opt(const struct option *opt __maybe_unused,
 			  const char *arg, int unset __maybe_unused)
 {

@@ -634,6 +1064,8 @@ static int __cmd_record(int argc, const char **argv)
 {
 	const char * const record_args[] = {
 	"record", "-a", "-R", "-c", "1",
+	};
+	const char * const slab_events[] = {
 	"-e", "kmem:kmalloc",
 	"-e", "kmem:kmalloc_node",
 	"-e", "kmem:kfree",

@@ -641,10 +1073,19 @@ static int __cmd_record(int argc, const char **argv)
 	"-e", "kmem:kmem_cache_alloc_node",
 	"-e", "kmem:kmem_cache_free",
 	};
+	const char * const page_events[] = {
+	"-e", "kmem:mm_page_alloc",
+	"-e", "kmem:mm_page_free",
+	};
 	unsigned int rec_argc, i, j;
 	const char **rec_argv;
 
 	rec_argc = ARRAY_SIZE(record_args) + argc - 1;
+	if (kmem_slab)
+		rec_argc += ARRAY_SIZE(slab_events);
+	if (kmem_page)
+		rec_argc += ARRAY_SIZE(page_events);
+
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
 	if (rec_argv == NULL)

@@ -653,6 +1094,15 @@ static int __cmd_record(int argc, const char **argv)
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = strdup(record_args[i]);
 
+	if (kmem_slab) {
+		for (j = 0; j < ARRAY_SIZE(slab_events); j++, i++)
+			rec_argv[i] = strdup(slab_events[j]);
+	}
+	if (kmem_page) {
+		for (j = 0; j < ARRAY_SIZE(page_events); j++, i++)
+			rec_argv[i] = strdup(page_events[j]);
+	}
+
 	for (j = 1; j < (unsigned int)argc; j++, i++)
 		rec_argv[i] = argv[j];
 

@@ -679,6 +1129,10 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK('l', "line", NULL, "num", "show n lines", parse_line_opt),
 	OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"),
 	OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+	OPT_CALLBACK_NOOPT(0, "slab", NULL, NULL, "Analyze slab allocator",
+			   parse_slab_opt),
+	OPT_CALLBACK_NOOPT(0, "page", NULL, NULL, "Analyze page allocator",
+			   parse_page_opt),
 	OPT_END()
 	};
 	const char *const kmem_subcommands[] = { "record", "stat", NULL };

@@ -695,6 +1149,9 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (!argc)
 		usage_with_options(kmem_usage, kmem_options);
 
+	if (kmem_slab == 0 && kmem_page == 0)
+		kmem_slab = 1;  /* for backward compatibility */
+
 	if (!strncmp(argv[0], "rec", 3)) {
 		symbol__init(NULL);
 		return __cmd_record(argc, argv);

@@ -706,6 +1163,17 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (session == NULL)
 		return -1;
 
+	if (kmem_page) {
+		struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+		if (evsel == NULL || evsel->tp_format == NULL) {
+			pr_err("invalid event found.. aborting\n");
+			return -1;
+		}
+
+		kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent);
+	}
+
 	symbol__init(&session->header.env);
 
 	if (!strcmp(argv[0], "stat")) {

Signature · 1 line

2.3.2

Em Mon, Apr 06, 2015 at 02:36:10PM +0900, Namhyung Kim escreveu:

Quoted 7 lines

The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events.

It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does.

Quoted 7 lines

The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only.

If none of these --slab nor --page is specified, --slab is implied.

  # perf kmem stat --page --alloc --line 10

Hi, applied the first patch, the kernel one, reboot with that kernel:

[root@ssdandy ~]#

What am I missing?

Em Fri, Apr 10, 2015 at 06:06:29PM -0300, Arnaldo Carvalho de Melo escreveu:

Quoted 17 lines

Em Mon, Apr 06, 2015 at 02:36:10PM +0900, Namhyung Kim escreveu:

Quoted 7 lines

The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events.

It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does.

Quoted 7 lines

The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only.

If none of these --slab nor --page is specified, --slab is implied.

  # perf kmem stat --page --alloc --line 10

Hi, applied the first patch, the kernel one, reboot with that kernel:

<SNIP>

Quoted 2 lines

[root@ssdandy ~]#

Quoted 1 line

What am I missing?

Argh, I was expecting to read just what is in that cset and be able to reproduce the results, had to go back to the [PATCH 0/0] cover letter to figure out that I need to run:

perf kmem record --page sleep 5

With that I get:

[root@ssdandy ~]# perf kmem stat --page --alloc --line 20

--------------------------------------------------------------------------------
PFN | Total alloc (KB) | Hits | Order | Mig.type | GFP flags
--------------------------------------------------------------------------------

          3487838 |               12 |         3 |     0 | UNMOVABL |  00020010
          3493414 |                8 |         2 |     0 | UNMOVABL |  000284d0
          3487761 |                4 |         1 |     0 | UNMOVABL |  000202d0
          3487764 |                4 |         1 |     0 | UNMOVABL |  000202d0
          3487982 |                4 |         1 |     0 | UNMOVABL |  000202d0
          3487991 |                4 |         1 |     0 | UNMOVABL |  000284d0
          3488046 |                4 |         1 |     0 | UNMOVABL |  002284d0
          3488057 |                4 |         1 |     0 | UNMOVABL |  000200d0
          3488191 |                4 |         1 |     0 | UNMOVABL |  002284d0
          3488203 |                4 |         1 |     0 | UNMOVABL |  000202d0
          3488206 |                4 |         1 |     0 | UNMOVABL |  000202d0
          3488210 |                4 |         1 |     0 | UNMOVABL |  000202d0
          3488211 |                4 |         1 |     0 | UNMOVABL |  000202d0
          3488213 |                4 |         1 |     0 | UNMOVABL |  000202d0
          3488215 |                4 |         1 |     0 | UNMOVABL |  000202d0
          3488298 |                4 |         1 |     0 | UNMOVABL |  000202d0
          3488325 |                4 |         1 |     0 | UNMOVABL |  000202d0
          3488326 |                4 |         1 |     0 | UNMOVABL |  000202d0
          3488327 |                4 |         1 |     0 | UNMOVABL |  000202d0
          3488329 |                4 |         1 |     0 | UNMOVABL |  000202d0
 ...              | ...              | ...       | ...   | ...      | ...     

--------------------------------------------------------------------------------

SUMMARY (page allocator)
========================

Total allocation requests     :              166   [              664 KB ]
Total free requests           :              239   [              956 KB ]

Total alloc+freed requests    :               49   [              196 KB ]
Total alloc-only requests     :              117   [              468 KB ]
Total free-only requests      :              190   [              760 KB ]

Total allocation failures : 0 [ 0 KB ]

Order Unmovable Reclaimable Movable Reserved CMA/Isolated
----- ------------ ------------ ------------ ------------ ------------

    0           143             .            23             .             .
    1             .             .             .             .             .
    2             .             .             .             .             .
    3             .             .             .             .             .
    4             .             .             .             .             .
    5             .             .             .             .             .
    6             .             .             .             .             .
    7             .             .             .             .             .
    8             .             .             .             .             .
    9             .             .             .             .             .
   10             .             .             .             .             .

[root@ssdandy ~]#

- Arnaldo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Quoted 13 lines

Em Fri, Apr 10, 2015 at 06:06:29PM -0300, Arnaldo Carvalho de Melo escreveu:

Quoted 6 lines

Em Mon, Apr 06, 2015 at 02:36:10PM +0900, Namhyung Kim escreveu:

Quoted 3 lines

If none of these --slab nor --page is specified, --slab is implied.

  # perf kmem stat --page --alloc --line 10

Hi, applied the first patch, the kernel one, reboot with that kernel:

<SNIP>

Quoted 3 lines

[root@ssdandy ~]#

What am I missing?

Quoted 5 lines

Argh, I was expecting to read just what is in that cset and be able to reproduce the results, had to go back to the [PATCH 0/0] cover letter to figure out that I need to run:

perf kmem record --page sleep 5

Right. Maybe I need to change to print warning if no events found with option.

Hmm.. looks like you ran some old version. Please check v6! :)

The perf kmem command records and analyze kernel memory allocation only for SLAB objects. This patch implement a simple page allocator analyzer using kmem:mm_page_alloc and kmem:mm_page_free events.

It adds two new options of --slab and --page. The --slab option is for analyzing SLAB allocator and that's what perf kmem currently does.

The new --page option enables page allocator events and analyze kernel memory usage in page unit. Currently, 'stat --alloc' subcommand is implemented only.

If none of these --slab nor --page is specified, --slab is implied.

  # perf kmem stat --page --alloc --line 10

It perf kmem support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info.

Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions:

^_?_?(alloc|get_free|get_zeroed)_pages?

This gave me a following list of functions:

  # perf kmem record --page sleep 3
  # perf kmem stat --page -v
  ...
  alloc func: __get_free_pages
  alloc func: get_zeroed_page
  alloc func: alloc_pages_exact
  alloc func: __alloc_pages_direct_compact
  alloc func: __alloc_pages_nodemask
  alloc func: alloc_page_interleave
  alloc func: alloc_pages_current
  alloc func: alloc_pages_vma
  alloc func: alloc_page_buffers
  alloc func: alloc_pages_exact_nid
  ...

The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite.

---------------------------------------------------------------------------------------------
Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite
---------------------------------------------------------------------------------------------

              1,064 |       266 |     0 | UNMOVABL |  000000d0 | __pollwait
                 52 |        13 |     0 | UNMOVABL |  002084d0 | pte_alloc_one
                 44 |        11 |     0 |  MOVABLE |  000280da | handle_mm_fault
                 20 |         5 |     0 |  MOVABLE |  000200da | do_cow_fault
                 20 |         5 |     0 |  MOVABLE |  000200da | do_wp_page
                 16 |         4 |     0 | UNMOVABL |  000084d0 | __pmd_alloc
                 16 |         4 |     0 | UNMOVABL |  00000200 | __tlb_remove_page
                 12 |         3 |     0 | UNMOVABL |  000084d0 | __pud_alloc
                  8 |         2 |     0 | UNMOVABL |  00000010 | bio_copy_user_iov
                  4 |         1 |     0 | UNMOVABL |  000200d2 | pipe_write
                  4 |         1 |     0 |  MOVABLE |  000280da | do_wp_page
                  4 |         1 |     0 | UNMOVABL |  002084d0 | pgd_alloc

---------------------------------------------------------------------------------------------

Signed-off-by Namhyung Kim <[email protected]>

---
 tools/perf/builtin-kmem.c | 279 +++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 263 insertions(+), 16 deletions(-)

tools/perf/builtin-kmem.c +39 -1

index 63ea01349b6e..5b3ed17c293a 100644
@@ -10,6 +10,7 @@
 #include "util/header.h"
 #include "util/session.h"
 #include "util/tool.h"
+#include "util/callchain.h"
 
 #include "util/parse-options.h"
 #include "util/trace-event.h"

@@ -21,6 +22,7 @@
 #include <linux/rbtree.h>
 #include <linux/string.h>
 #include <locale.h>
+#include <regex.h>
 
 static int	kmem_slab;
 static int	kmem_page;

@@ -241,6 +243,7 @@ static unsigned long nr_page_fails;
 static unsigned long nr_page_nomatch;
 
 static bool use_pfn;
+static struct perf_session *kmem_session;
 
 #define MAX_MIGRATE_TYPES  6
 #define MAX_PAGE_ORDER     11

@@ -250,6 +253,7 @@ static int order_stats[MAX_PAGE_ORDER][MAX_MIGRATE_TYPES];
 struct page_stat {
 	struct rb_node 	node;
 	u64 		page;
+	u64 		callsite;
 	int 		order;
 	unsigned 	gfp_flags;
 	unsigned 	migrate_type;

@@ -262,8 +266,138 @@ struct page_stat {
 static struct rb_root page_tree;
 static struct rb_root page_alloc_tree;
 static struct rb_root page_alloc_sorted;
+static struct rb_root page_caller_tree;
+static struct rb_root page_caller_sorted;
 
-static struct page_stat *search_page(unsigned long page, bool create)
+struct alloc_func {
+	u64 start;
+	u64 end;
+	char *name;
+};
+
+static int nr_alloc_funcs;
+static struct alloc_func *alloc_func_list;
+
+static int funcmp(const void *a, const void *b)
+{
+	const struct alloc_func *fa = a;
+	const struct alloc_func *fb = b;
+
+	if (fa->start > fb->start)
+		return 1;
+	else
+		return -1;
+}
+
+static int callcmp(const void *a, const void *b)
+{
+	const struct alloc_func *fa = a;
+	const struct alloc_func *fb = b;
+
+	if (fb->start <= fa->start && fa->end < fb->end)
+		return 0;
+
+	if (fa->start > fb->start)
+		return 1;
+	else
+		return -1;
+}

tools/perf/builtin-kmem.c +4 -0

+	regex_t alloc_func_regex;
+	const char pattern[] = "^_?_?(alloc|get_free|get_zeroed)_pages?";
+
+	ret = regcomp(&alloc_func_regex, pattern, REG_EXTENDED);

tools/perf/builtin-kmem.c +72 -0

+
+	map__for_each_symbol(kernel_map, sym, node) {
+		if (regexec(&alloc_func_regex, sym->name, 0, NULL, 0))
+			continue;
+
+		func = realloc(alloc_func_list,
+			       (nr_alloc_funcs + 1) * sizeof(*func));
+		if (func == NULL)
+			return -ENOMEM;
+
+		pr_debug("alloc func: %s\n", sym->name);
+		func[nr_alloc_funcs].start = sym->start;
+		func[nr_alloc_funcs].end   = sym->end;
+		func[nr_alloc_funcs].name  = sym->name;
+
+		alloc_func_list = func;
+		nr_alloc_funcs++;
+	}
+
+	qsort(alloc_func_list, nr_alloc_funcs, sizeof(*func), funcmp);
+
+	regfree(&alloc_func_regex);
+	return 0;
+}
+
+/*
+ * Find first non-memory allocation function from callchain.
+ * The allocation functions are in the 'alloc_func_list'.
+ */
+static u64 find_callsite(struct perf_evsel *evsel, struct perf_sample *sample)
+{
+	struct addr_location al;
+	struct machine *machine = &kmem_session->machines.host;
+	struct callchain_cursor_node *node;
+
+	if (alloc_func_list == NULL)
+		build_alloc_func_list();
+
+	al.thread = machine__findnew_thread(machine, sample->pid, sample->tid);
+	sample__resolve_callchain(sample, NULL, evsel, &al, 16);
+
+	callchain_cursor_commit(&callchain_cursor);
+	while (true) {
+		struct alloc_func key, *caller;
+		u64 addr;
+
+		node = callchain_cursor_current(&callchain_cursor);
+		if (node == NULL)
+			break;
+
+		key.start = key.end = node->ip;
+		caller = bsearch(&key, alloc_func_list, nr_alloc_funcs,
+				 sizeof(key), callcmp);
+		if (!caller) {
+			/* found */
+			if (node->map)
+				addr = map__unmap_ip(node->map, node->ip);
+			else
+				addr = node->ip;
+
+			return addr;
+		} else
+			pr_debug3("skipping alloc function: %s\n", caller->name);
+
+		callchain_cursor_advance(&callchain_cursor);
+	}
+
+	pr_debug2("unknown callsite: %"PRIx64 "\n", sample->ip);
+	return sample->ip;
+}
+
+static struct page_stat *search_page(u64 page, bool create)
 {
 	struct rb_node **node = &page_tree.rb_node;
 	struct rb_node *parent = NULL;

tools/perf/builtin-kmem.c +122 -15

+	while (*node) {
+		s64 cmp;
+
+		parent = *node;
+		data = rb_entry(*node, struct page_stat, node);
+
+		cmp = data->callsite - callsite;
+		if (cmp < 0)
+			node = &parent->rb_left;
+		else if (cmp > 0)
+			node = &parent->rb_right;
+		else
+			return data;
+	}
+
+	if (!create)
+		return NULL;
+
+	data = zalloc(sizeof(*data));
+	if (data != NULL) {
+		data->callsite = callsite;
+
+		rb_link_node(&data->node, parent, node);
+		rb_insert_color(&data->node, &page_caller_tree);
+	}
+
+	return data;
+}
+
 static bool valid_page(u64 pfn_or_page)
 {
 	if (use_pfn && pfn_or_page == -1UL)

@@ -375,6 +544,7 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 	unsigned int migrate_type = perf_evsel__intval(evsel, sample,
 						       "migratetype");
 	u64 bytes = kmem_page_size << order;
+	u64 callsite;
 	struct page_stat *stat;
 	struct page_stat this = {
 		.order = order,

@@ -397,6 +567,8 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 		return 0;
 	}
 
+	callsite = find_callsite(evsel, sample);
+
 	/*
 	 * This is to find the current page (with correct gfp flags and
 	 * migrate type) at free event.

@@ -408,6 +580,7 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 	stat->order = order;
 	stat->gfp_flags = gfp_flags;
 	stat->migrate_type = migrate_type;
+	stat->callsite = callsite;
 
 	this.page = page;
 	stat = search_page_alloc_stat(&this, true);

@@ -416,6 +589,18 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 
 	stat->nr_alloc++;
 	stat->alloc_bytes += bytes;
+	stat->callsite = callsite;
+
+	stat = search_page_caller_stat(callsite, true);
+	if (stat == NULL)
+		return -ENOMEM;
+
+	stat->order = order;
+	stat->gfp_flags = gfp_flags;
+	stat->migrate_type = migrate_type;
+
+	stat->nr_alloc++;
+	stat->alloc_bytes += bytes;
 
 	order_stats[order][migrate_type]++;
 

@@ -455,6 +640,7 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 	this.page = page;
 	this.gfp_flags = stat->gfp_flags;
 	this.migrate_type = stat->migrate_type;
+	this.callsite = stat->callsite;
 
 	rb_erase(&stat->node, &page_tree);
 	free(stat);

@@ -466,6 +652,13 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 	stat->nr_free++;
 	stat->free_bytes += bytes;
 
+	stat = search_page_caller_stat(this.callsite, false);
+	if (stat == NULL)
+		return -ENOENT;
+
+	stat->nr_free++;
+	stat->free_bytes += bytes;
+
 	return 0;
 }
 

@@ -576,41 +769,89 @@ static const char * const migrate_type_str[] = {
 	"UNKNOWN",
 };
 
-static void __print_page_result(struct rb_root *root,
-				struct perf_session *session __maybe_unused,
-				int n_lines)
+static void __print_page_alloc_result(struct perf_session *session, int n_lines)
 {
-	struct rb_node *next = rb_first(root);
+	struct rb_node *next = rb_first(&page_alloc_sorted);
+	struct machine *machine = &session->machines.host;
 	const char *format;
 
-	printf("\n%.80s\n", graph_dotted_line);
-	printf(" %-16s | Total alloc (KB) | Hits      | Order | Mig.type | GFP flags\n",
+	printf("\n%.105s\n", graph_dotted_line);
+	printf(" %-16s | Total alloc (KB) | Hits      | Order | Mig.type | GFP flags | Callsite\n",
 	       use_pfn ? "PFN" : "Page");
-	printf("%.80s\n", graph_dotted_line);
+	printf("%.105s\n", graph_dotted_line);
 
 	if (use_pfn)
-		format = " %16llu | %'16llu | %'9d | %5d | %8s |  %08lx\n";
+		format = " %16llu | %'16llu | %'9d | %5d | %8s |  %08lx | %s\n";
 	else
-		format = " %016llx | %'16llu | %'9d | %5d | %8s |  %08lx\n";
+		format = " %016llx | %'16llu | %'9d | %5d | %8s |  %08lx | %s\n";
 
 	while (next && n_lines--) {
 		struct page_stat *data;
+		struct symbol *sym;
+		struct map *map;
+		char buf[32];
+		char *caller = buf;
 
 		data = rb_entry(next, struct page_stat, node);
+		sym = machine__find_kernel_function(machine, data->callsite,
+						    &map, NULL);
+		if (sym && sym->name)
+			caller = sym->name;
+		else
+			scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
 
 		printf(format, (unsigned long long)data->page,
 		       (unsigned long long)data->alloc_bytes / 1024,
 		       data->nr_alloc, data->order,
 		       migrate_type_str[data->migrate_type],
-		       (unsigned long)data->gfp_flags);
+		       (unsigned long)data->gfp_flags, caller);
+
+		next = rb_next(next);
+	}
+
+	if (n_lines == -1)
+		printf(" ...              | ...              | ...       | ...   | ...      | ...       | ...\n");
+
+	printf("%.105s\n", graph_dotted_line);
+}
+
+static void __print_page_caller_result(struct perf_session *session, int n_lines)
+{
+	struct rb_node *next = rb_first(&page_caller_sorted);
+	struct machine *machine = &session->machines.host;
+
+	printf("\n%.105s\n", graph_dotted_line);
+	printf(" Total alloc (KB) | Hits      | Order | Mig.type | GFP flags | Callsite\n");
+	printf("%.105s\n", graph_dotted_line);
+
+	while (next && n_lines--) {
+		struct page_stat *data;
+		struct symbol *sym;
+		struct map *map;
+		char buf[32];
+		char *caller = buf;
+
+		data = rb_entry(next, struct page_stat, node);
+		sym = machine__find_kernel_function(machine, data->callsite,
+						    &map, NULL);
+		if (sym && sym->name)
+			caller = sym->name;
+		else
+			scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
+
+		printf(" %'16llu | %'9d | %5d | %8s |  %08lx | %s\n",
+		       (unsigned long long)data->alloc_bytes / 1024,
+		       data->nr_alloc, data->order,
+		       migrate_type_str[data->migrate_type],
+		       (unsigned long)data->gfp_flags, caller);
 
 		next = rb_next(next);
 	}
 
 	if (n_lines == -1)
-		printf(" ...              | ...              | ...       | ...   | ...      | ...     \n");
+		printf(" ...              | ...       | ...   | ...      | ...       | ...\n");
 
-	printf("%.80s\n", graph_dotted_line);
+	printf("%.105s\n", graph_dotted_line);
 }
 
 static void print_slab_summary(void)

@@ -682,8 +923,10 @@ static void print_slab_result(struct perf_session *session)
 
 static void print_page_result(struct perf_session *session)
 {
+	if (caller_flag)
+		__print_page_caller_result(session, caller_lines);
 	if (alloc_flag)
-		__print_page_result(&page_alloc_sorted, session, alloc_lines);
+		__print_page_alloc_result(session, alloc_lines);
 	print_page_summary();
 }
 

@@ -802,6 +1045,7 @@ static void sort_result(void)
 	}
 	if (kmem_page) {
 		__sort_page_result(&page_alloc_tree, &page_alloc_sorted);
+		__sort_page_result(&page_caller_tree, &page_caller_sorted);
 	}
 }
 

@@ -1084,7 +1328,7 @@ static int __cmd_record(int argc, const char **argv)
 	if (kmem_slab)
 		rec_argc += ARRAY_SIZE(slab_events);
 	if (kmem_page)
-		rec_argc += ARRAY_SIZE(page_events);
+		rec_argc += ARRAY_SIZE(page_events) + 1; /* for -g */
 
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 

@@ -1099,6 +1343,8 @@ static int __cmd_record(int argc, const char **argv)
 			rec_argv[i] = strdup(slab_events[j]);
 	}
 	if (kmem_page) {
+		rec_argv[i++] = strdup("-g");
+
 		for (j = 0; j < ARRAY_SIZE(page_events); j++, i++)
 			rec_argv[i] = strdup(page_events[j]);
 	}

@@ -1159,7 +1405,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	file.path = input_name;
 
-	session = perf_session__new(&file, false, &perf_kmem);
+	kmem_session = session = perf_session__new(&file, false, &perf_kmem);
 	if (session == NULL)
 		return -1;
 

@@ -1172,6 +1418,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 		}
 
 		kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent);
+		symbol_conf.use_callchain = true;
 	}
 
 	symbol__init(&session->header.env);

Signature · 1 line

2.3.2

Em Mon, Apr 06, 2015 at 02:36:11PM +0900, Namhyung Kim escreveu:

tools/perf/builtin-kmem.c struct page_stat { · line 314

Quoted 9 lines

tools/perf/builtin-kmem.c +9 -0

+static int build_alloc_func_list(void)
+{
+	int ret;
+	struct map *kernel_map;
+	struct symbol *sym;
+	struct rb_node *node;
+	struct alloc_func *func;
+	struct machine *machine = &kmem_session->machines.host;
+

Why having a blank like here?

Quoted 5 lines

tools/perf/builtin-kmem.c +4 -0

+	regex_t alloc_func_regex;
+	const char pattern[] = "^_?_?(alloc|get_free|get_zeroed)_pages?";
+
+	ret = regcomp(&alloc_func_regex, pattern, REG_EXTENDED);

tools/perf/builtin-kmem.c struct page_stat { · line 328

Quoted 10 lines

tools/perf/builtin-kmem.c +10 -0

+	if (ret) {
+		char err[BUFSIZ];
+
+		regerror(ret, &alloc_func_regex, err, sizeof(err));
+		pr_err("Invalid regex: %s\n%s", pattern, err);
+		return -EINVAL;
+	}
+
+	kernel_map = machine->vmlinux_maps[MAP__FUNCTION];
+	map__load(kernel_map, NULL);

What if the map can't be loaded?

Quoted 30 lines

tools/perf/builtin-kmem.c +29 -0

+
+	map__for_each_symbol(kernel_map, sym, node) {
+		if (regexec(&alloc_func_regex, sym->name, 0, NULL, 0))
+			continue;
+
+		func = realloc(alloc_func_list,
+			       (nr_alloc_funcs + 1) * sizeof(*func));
+		if (func == NULL)
+			return -ENOMEM;
+
+		pr_debug("alloc func: %s\n", sym->name);
+		func[nr_alloc_funcs].start = sym->start;
+		func[nr_alloc_funcs].end   = sym->end;
+		func[nr_alloc_funcs].name  = sym->name;
+
+		alloc_func_list = func;
+		nr_alloc_funcs++;
+	}
+
+	qsort(alloc_func_list, nr_alloc_funcs, sizeof(*func), funcmp);
+
+	regfree(&alloc_func_regex);
+	return 0;
+}
+
+/*
+ * Find first non-memory allocation function from callchain.
+ * The allocation functions are in the 'alloc_func_list'.
+ */

tools/perf/builtin-kmem.c struct page_stat { · line 365

Quoted 8 lines

tools/perf/builtin-kmem.c +8 -0

+static u64 find_callsite(struct perf_evsel *evsel, struct perf_sample *sample)
+{
+	struct addr_location al;
+	struct machine *machine = &kmem_session->machines.host;
+	struct callchain_cursor_node *node;
+
+	if (alloc_func_list == NULL)
+		build_alloc_func_list();

Quoted 39 lines

tools/perf/builtin-kmem.c +35 -0

+
+	al.thread = machine__findnew_thread(machine, sample->pid, sample->tid);
+	sample__resolve_callchain(sample, NULL, evsel, &al, 16);
+
+	callchain_cursor_commit(&callchain_cursor);
+	while (true) {
+		struct alloc_func key, *caller;
+		u64 addr;
+
+		node = callchain_cursor_current(&callchain_cursor);
+		if (node == NULL)
+			break;
+
+		key.start = key.end = node->ip;
+		caller = bsearch(&key, alloc_func_list, nr_alloc_funcs,
+				 sizeof(key), callcmp);
+		if (!caller) {
+			/* found */
+			if (node->map)
+				addr = map__unmap_ip(node->map, node->ip);
+			else
+				addr = node->ip;
+
+			return addr;
+		} else
+			pr_debug3("skipping alloc function: %s\n", caller->name);
+
+		callchain_cursor_advance(&callchain_cursor);
+	}
+
+	pr_debug2("unknown callsite: %"PRIx64 "\n", sample->ip);
+	return sample->ip;
+}
+
+static struct page_stat *search_page(u64 page, bool create)
 {
 	struct rb_node **node = &page_tree.rb_node;
 	struct rb_node *parent = NULL;

tools/perf/builtin-kmem.c static struct page_stat *search_page_alloc_stat(struct page_stat *stat, bool cre · line 498

Quoted 8 lines

tools/perf/builtin-kmem.c +5 -0

@@ -357,6 +491,41 @@ static struct page_stat *search_page_alloc_stat(struct page_stat *stat, bool cre
 	return data;
 }
 
+static struct page_stat *search_page_caller_stat(u64 callsite, bool create)
+{
+	struct rb_node **node = &page_caller_tree.rb_node;
+	struct rb_node *parent = NULL;
+	struct page_stat *data;

Please use the "findnew" idiom to name this function, looking at only its name one things it searches a tree, a read only operation, but it may insert elements too, a modify operation.

Since we use the findnew idiom elsewhere for operations that do that, i.e. optimize the "new" part of "findnew" by using the "find" part, please use it here as well.

Currently it ignores operator priority and just sets processed args as a right operand. But it could result in priority inversion in case that the right operand is also a operator arg and its priority is lower.

For example, following print format is from new kmem events.

"page=%p", REC->pfn != -1UL ? (((struct page *)(0xffffea0000000000UL)) + (REC->pfn)) : ((void *)0)

But this was treated as below:

REC->pfn != ((null - 1UL) ? ((struct page *)0xffffea0000000000UL + REC->pfn) : (void *) 0)

In this case, the right arg was '?' operator which has lower priority. But it just sets the whole arg so making the output confusing - page was always 0 or 1 since that's the result of logical operation.

With this patch, it can handle it properly like following:

((REC->pfn != (null - 1UL)) ? ((struct page *)0xffffea0000000000UL + REC->pfn) : (void *) 0)

Cc Steven Rostedt <[email protected]>

Signed-off-by Namhyung Kim <[email protected]>

---
 tools/lib/traceevent/event-parse.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

tools/lib/traceevent/event-parse.c +0 -0

index 6d31b6419d37..604bea5c3fb0 100644

Quoted 12 lines · On Mon, 6 Apr 2015 14:36:16 +0900 Namhyung Kim <[email protected]> wrote:

Currently it ignores operator priority and just sets processed args as a right operand. But it could result in priority inversion in case that the right operand is also a operator arg and its priority is lower.

For example, following print format is from new kmem events.

"page=%p", REC->pfn != -1UL ? (((struct page *)(0xffffea0000000000UL)) + (REC->pfn)) : ((void *)0)

But this was treated as below:

REC->pfn != ((null - 1UL) ? ((struct page *)0xffffea0000000000UL + REC->pfn) : (void *) 0)

Quoted 7 lines

In this case, the right arg was '?' operator which has lower priority. But it just sets the whole arg so making the output confusing - page was always 0 or 1 since that's the result of logical operation.

With this patch, it can handle it properly like following:

((REC->pfn != (null - 1UL)) ? ((struct page *)0xffffea0000000000UL + REC->pfn) : (void *) 0)

Nice catch. One nit.

Quoted 14 lines

Cc Steven Rostedt <[email protected]>

Signed-off-by Namhyung Kim <[email protected]>

---
 tools/lib/traceevent/event-parse.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

tools/lib/traceevent/event-parse.c +0 -0

index 6d31b6419d37..604bea5c3fb0 100644
@@ -1939,7 +1939,22 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 			goto out_warn_free;
 

tools/lib/traceevent/event-parse.c process_op(struct event_format *event, struct print_arg *arg, char **tok) · line 1947

Quoted 8 lines

tools/lib/traceevent/event-parse.c +6 -1

 		type = process_arg_token(event, right, tok, type);
-		arg->op.right = right;
+
+		if (right->type == PRINT_OP &&
+		    get_op_prio(arg->op.op) < get_op_prio(right->op.op)) {
+			struct print_arg tmp;
+
+			/* swap ops according to the priority */

This isn't really a swap. Better term to use is "rotate".

But other than that,

Acked-by Steven Rostedt <[email protected]>

Quoted 12 lines

tools/lib/traceevent/event-parse.c +10 -0

+			arg->op.right = right->op.left;
+
+			tmp = *arg;
+			*arg = *right;
+			*right = tmp;
+
+			arg->op.left = right;
+		} else {
+			arg->op.right = right;
+		}
 

tools/lib/traceevent/event-parse.c process_op(struct event_format *event, struct print_arg *arg, char **tok) · line 1960

Quoted 2 lines

tools/lib/traceevent/event-parse.c +0 -0

 	} else if (strcmp(token, "[") == 0) {
 

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Quoted 10 lines

tools/lib/traceevent/event-parse.c process_op(struct event_format *event, struct print_arg *arg, char **tok) · line 1947

Quoted 8 lines

tools/lib/traceevent/event-parse.c +6 -1

 		type = process_arg_token(event, right, tok, type);
-		arg->op.right = right;
+
+		if (right->type == PRINT_OP &&
+		    get_op_prio(arg->op.op) < get_op_prio(right->op.op)) {
+			struct print_arg tmp;
+
+			/* swap ops according to the priority */

This isn't really a swap. Better term to use is "rotate".

You're right!

Quoted 3 lines

But other than that,

Acked-by Steven Rostedt <[email protected]>

Thanks for the review

Ok, so just doing that s/swap/rotate/g, sticking Rostedt's ack and applying, ok?

Em Tue, Apr 07, 2015 at 04:52:26PM +0900, Namhyung Kim escreveu:

Quoted 13 lines · Steven Rostedt

Quoted 10 lines

tools/lib/traceevent/event-parse.c process_op(struct event_format *event, struct print_arg *arg, char **tok) · line 1947

Quoted 8 lines

tools/lib/traceevent/event-parse.c +6 -1

 		type = process_arg_token(event, right, tok, type);
-		arg->op.right = right;
+
+		if (right->type == PRINT_OP &&
+		    get_op_prio(arg->op.op) < get_op_prio(right->op.op)) {
+			struct print_arg tmp;
+
+			/* swap ops according to the priority */

This isn't really a swap. Better term to use is "rotate".

You're right!

Quoted 5 lines

Quoted 3 lines

But other than that,

Acked-by Steven Rostedt <[email protected]>

Thanks for the review

Ok, so just doing that s/swap/rotate/g, sticking Rostedt's ack and applying, ok?

Currently it ignores operator priority and just sets processed args as a right operand. But it could result in priority inversion in case that the right operand is also a operator arg and its priority is lower.

For example, following print format is from new kmem events.

"page=%p", REC->pfn != -1UL ? (((struct page *)(0xffffea0000000000UL)) + (REC->pfn)) : ((void *)0)

But this was treated as below:

REC->pfn != ((null - 1UL) ? ((struct page *)0xffffea0000000000UL + REC->pfn) : (void *) 0)

In this case, the right arg was '?' operator which has lower priority. But it just sets the whole arg so making the output confusing - page was always 0 or 1 since that's the result of logical operation.

With this patch, it can handle it properly like following:

((REC->pfn != (null - 1UL)) ? ((struct page *)0xffffea0000000000UL + REC->pfn) : (void *) 0)