1 files changed, 148 insertions, 215 deletions

diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 31f60a2535e..bef3376bfaf 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1,25 +1,29 @@
 #include "builtin.h"
 #include "perf.h"
 
+#include "util/evlist.h"
+#include "util/evsel.h"
 #include "util/util.h"
 #include "util/cache.h"
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/header.h"
 #include "util/session.h"
+#include "util/tool.h"
 
 #include "util/parse-options.h"
 #include "util/trace-event.h"
+#include "util/data.h"
+#include "util/cpumap.h"
 
 #include "util/debug.h"
 
 #include <linux/rbtree.h>
+#include <linux/string.h>
 
 struct alloc_stat;
 typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *);
 
-static char const		*input_name = "perf.data";
-
 static int			alloc_flag;
 static int			caller_flag;
 
@@ -28,11 +32,6 @@ static int			caller_lines = -1;
 
 static bool			raw_ip;
 
-static char			default_sort_order[] = "frag,hit,bytes";
-
-static int			*cpunode_map;
-static int			max_cpu_num;
-
 struct alloc_stat {
 	u64	call_site;
 	u64	ptr;
@@ -54,64 +53,8 @@ static struct rb_root root_caller_sorted;
 static unsigned long total_requested, total_allocated;
 static unsigned long nr_allocs, nr_cross_allocs;
 
-#define PATH_SYS_NODE	"/sys/devices/system/node"
-
-static void init_cpunode_map(void)
-{
-	FILE *fp;
-	int i;
-
-	fp = fopen("/sys/devices/system/cpu/kernel_max", "r");
-	if (!fp) {
-		max_cpu_num = 4096;
-		return;
-	}
-
-	if (fscanf(fp, "%d", &max_cpu_num) < 1)
-		die("Failed to read 'kernel_max' from sysfs");
-	max_cpu_num++;
-
-	cpunode_map = calloc(max_cpu_num, sizeof(int));
-	if (!cpunode_map)
-		die("calloc");
-	for (i = 0; i < max_cpu_num; i++)
-		cpunode_map[i] = -1;
-	fclose(fp);
-}
-
-static void setup_cpunode_map(void)
-{
-	struct dirent *dent1, *dent2;
-	DIR *dir1, *dir2;
-	unsigned int cpu, mem;
-	char buf[PATH_MAX];
-
-	init_cpunode_map();
-
-	dir1 = opendir(PATH_SYS_NODE);
-	if (!dir1)
-		return;
-
-	while ((dent1 = readdir(dir1)) != NULL) {
-		if (dent1->d_type != DT_DIR ||
-		    sscanf(dent1->d_name, "node%u", &mem) < 1)
-			continue;
-
-		snprintf(buf, PATH_MAX, "%s/%s", PATH_SYS_NODE, dent1->d_name);
-		dir2 = opendir(buf);
-		if (!dir2)
-			continue;
-		while ((dent2 = readdir(dir2)) != NULL) {
-			if (dent2->d_type != DT_LNK ||
-			    sscanf(dent2->d_name, "cpu%u", &cpu) < 1)
-				continue;
-			cpunode_map[cpu] = mem;
-		}
-	}
-}
-
-static void insert_alloc_stat(unsigned long call_site, unsigned long ptr,
-			      int bytes_req, int bytes_alloc, int cpu)
+static int insert_alloc_stat(unsigned long call_site, unsigned long ptr,
+			     int bytes_req, int bytes_alloc, int cpu)
 {
 	struct rb_node **node = &root_alloc_stat.rb_node;
 	struct rb_node *parent = NULL;
@@ -135,8 +78,10 @@ static void insert_alloc_stat(unsigned long call_site, unsigned long ptr,
 		data->bytes_alloc += bytes_alloc;
 	} else {
 		data = malloc(sizeof(*data));
-		if (!data)
-			die("malloc");
+		if (!data) {
+			pr_err("%s: malloc failed\n", __func__);
+			return -1;
+		}
 		data->ptr = ptr;
 		data->pingpong = 0;
 		data->hit = 1;
@@ -148,9 +93,10 @@ static void insert_alloc_stat(unsigned long call_site, unsigned long ptr,
 	}
 	data->call_site = call_site;
 	data->alloc_cpu = cpu;
+	return 0;
 }
 
-static void insert_caller_stat(unsigned long call_site,
+static int insert_caller_stat(unsigned long call_site,
 			      int bytes_req, int bytes_alloc)
 {
 	struct rb_node **node = &root_caller_stat.rb_node;
@@ -175,8 +121,10 @@ static void insert_caller_stat(unsigned long call_site,
 		data->bytes_alloc += bytes_alloc;
 	} else {
 		data = malloc(sizeof(*data));
-		if (!data)
-			die("malloc");
+		if (!data) {
+			pr_err("%s: malloc failed\n", __func__);
+			return -1;
+		}
 		data->call_site = call_site;
 		data->pingpong = 0;
 		data->hit = 1;
@@ -186,39 +134,43 @@ static void insert_caller_stat(unsigned long call_site,
 		rb_link_node(&data->node, parent, node);
 		rb_insert_color(&data->node, &root_caller_stat);
 	}
+
+	return 0;
 }
 
-static void process_alloc_event(void *data,
-				struct event *event,
-				int cpu,
-				u64 timestamp __used,
-				struct thread *thread __used,
-				int node)
+static int perf_evsel__process_alloc_event(struct perf_evsel *evsel,
+					   struct perf_sample *sample)
 {
-	unsigned long call_site;
-	unsigned long ptr;
-	int bytes_req;
-	int bytes_alloc;
-	int node1, node2;
-
-	ptr = raw_field_value(event, "ptr", data);
-	call_site = raw_field_value(event, "call_site", data);
-	bytes_req = raw_field_value(event, "bytes_req", data);
-	bytes_alloc = raw_field_value(event, "bytes_alloc", data);
+	unsigned long ptr = perf_evsel__intval(evsel, sample, "ptr"),
+		      call_site = perf_evsel__intval(evsel, sample, "call_site");
+	int bytes_req = perf_evsel__intval(evsel, sample, "bytes_req"),
+	    bytes_alloc = perf_evsel__intval(evsel, sample, "bytes_alloc");
 
-	insert_alloc_stat(call_site, ptr, bytes_req, bytes_alloc, cpu);
-	insert_caller_stat(call_site, bytes_req, bytes_alloc);
+	if (insert_alloc_stat(call_site, ptr, bytes_req, bytes_alloc, sample->cpu) ||
+	    insert_caller_stat(call_site, bytes_req, bytes_alloc))
+		return -1;
 
 	total_requested += bytes_req;
 	total_allocated += bytes_alloc;
 
-	if (node) {
-		node1 = cpunode_map[cpu];
-		node2 = raw_field_value(event, "node", data);
+	nr_allocs++;
+	return 0;
+}
+
+static int perf_evsel__process_alloc_node_event(struct perf_evsel *evsel,
+						struct perf_sample *sample)
+{
+	int ret = perf_evsel__process_alloc_event(evsel, sample);
+
+	if (!ret) {
+		int node1 = cpu__get_node(sample->cpu),
+		    node2 = perf_evsel__intval(evsel, sample, "node");
+
 		if (node1 != node2)
 			nr_cross_allocs++;
 	}
-	nr_allocs++;
+
+	return ret;
 }
 
 static int ptr_cmp(struct alloc_stat *, struct alloc_stat *);
@@ -249,95 +201,62 @@ static struct alloc_stat *search_alloc_stat(unsigned long ptr,
 	return NULL;
 }
 
-static void process_free_event(void *data,
-			       struct event *event,
-			       int cpu,
-			       u64 timestamp __used,
-			       struct thread *thread __used)
+static int perf_evsel__process_free_event(struct perf_evsel *evsel,
+					  struct perf_sample *sample)
 {
-	unsigned long ptr;
+	unsigned long ptr = perf_evsel__intval(evsel, sample, "ptr");
 	struct alloc_stat *s_alloc, *s_caller;
 
-	ptr = raw_field_value(event, "ptr", data);
-
 	s_alloc = search_alloc_stat(ptr, 0, &root_alloc_stat, ptr_cmp);
 	if (!s_alloc)
-		return;
+		return 0;
 
-	if (cpu != s_alloc->alloc_cpu) {
+	if ((short)sample->cpu != s_alloc->alloc_cpu) {
 		s_alloc->pingpong++;
 
 		s_caller = search_alloc_stat(0, s_alloc->call_site,
 					     &root_caller_stat, callsite_cmp);
-		assert(s_caller);
+		if (!s_caller)
+			return -1;
 		s_caller->pingpong++;
 	}
 	s_alloc->alloc_cpu = -1;
-}
-
-static void
-process_raw_event(event_t *raw_event __used, void *data,
-		  int cpu, u64 timestamp, struct thread *thread)
-{
-	struct event *event;
-	int type;
-
-	type = trace_parse_common_type(data);
-	event = trace_find_event(type);
-
-	if (!strcmp(event->name, "kmalloc") ||
-	    !strcmp(event->name, "kmem_cache_alloc")) {
-		process_alloc_event(data, event, cpu, timestamp, thread, 0);
-		return;
-	}
 
-	if (!strcmp(event->name, "kmalloc_node") ||
-	    !strcmp(event->name, "kmem_cache_alloc_node")) {
-		process_alloc_event(data, event, cpu, timestamp, thread, 1);
-		return;
-	}
-
-	if (!strcmp(event->name, "kfree") ||
-	    !strcmp(event->name, "kmem_cache_free")) {
-		process_free_event(data, event, cpu, timestamp, thread);
-		return;
-	}
+	return 0;
 }
 
-static int process_sample_event(event_t *event, struct perf_session *session)
-{
-	struct sample_data data;
-	struct thread *thread;
-
-	memset(&data, 0, sizeof(data));
-	data.time = -1;
-	data.cpu = -1;
-	data.period = 1;
+typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
+				  struct perf_sample *sample);
 
-	event__parse_sample(event, session->sample_type, &data);
-
-	dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
-		    data.pid, data.tid, data.ip, data.period);
+static int process_sample_event(struct perf_tool *tool __maybe_unused,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine)
+{
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->tid);
 
-	thread = perf_session__findnew(session, event->ip.pid);
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
 			 event->header.type);
 		return -1;
 	}
 
-	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
 
-	process_raw_event(event, data.raw_data, data.cpu,
-			  data.time, thread);
+	if (evsel->handler != NULL) {
+		tracepoint_handler f = evsel->handler;
+		return f(evsel, sample);
+	}
 
 	return 0;
 }
 
-static struct perf_event_ops event_ops = {
-	.sample			= process_sample_event,
-	.comm			= event__process_comm,
-	.ordered_samples	= true,
+static struct perf_tool perf_kmem = {
+	.sample		 = process_sample_event,
+	.comm		 = perf_event__process_comm,
+	.ordered_samples = true,
 };
 
 static double fragmentation(unsigned long n_req, unsigned long n_alloc)
@@ -352,7 +271,7 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 			   int n_lines, int is_caller)
 {
 	struct rb_node *next;
-	struct machine *machine;
+	struct machine *machine = &session->machines.host;
 
 	printf("%.102s\n", graph_dotted_line);
 	printf(" %-34s |",  is_caller ? "Callsite": "Alloc Ptr");
@@ -361,11 +280,6 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 
 	next = rb_first(root);
 
-	machine = perf_session__find_host_machine(session);
-	if (!machine) {
-		pr_err("__print_result: couldn't find kernel information\n");
-		return;
-	}
 	while (next && n_lines--) {
 		struct alloc_stat *data = rb_entry(next, struct alloc_stat,
 						   node);
@@ -382,10 +296,10 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 			addr = data->ptr;
 
 		if (sym != NULL)
-			snprintf(buf, sizeof(buf), "%s+%Lx", sym->name,
+			snprintf(buf, sizeof(buf), "%s+%" PRIx64 "", sym->name,
 				 addr - map->unmap_ip(map, sym->start));
 		else
-			snprintf(buf, sizeof(buf), "%#Lx", addr);
+			snprintf(buf, sizeof(buf), "%#" PRIx64 "", addr);
 		printf(" %-34s |", buf);
 
 		printf(" %9llu/%-5lu | %9llu/%-5lu | %8lu | %8lu | %6.3f%%\n",
@@ -492,7 +406,21 @@ static void sort_result(void)
 static int __cmd_kmem(void)
 {
 	int err = -EINVAL;
-	struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false);
+	struct perf_session *session;
+	const struct perf_evsel_str_handler kmem_tracepoints[] = {
+		{ "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, },
+	};
+	struct perf_data_file file = {
+		.path = input_name,
+		.mode = PERF_DATA_MODE_READ,
+	};
+
+	session = perf_session__new(&file, false, &perf_kmem);
 	if (session == NULL)
 		return -ENOMEM;
 
@@ -502,8 +430,13 @@ static int __cmd_kmem(void)
 	if (!perf_session__has_traces(session, "kmem record"))
 		goto out_delete;
 
+	if (perf_session__set_tracepoints_handlers(session, kmem_tracepoints)) {
+		pr_err("Initializing perf session tracepoint handlers failed\n");
+		return -1;
+	}
+
 	setup_pager();
-	err = perf_session__process_events(session, &event_ops);
+	err = perf_session__process_events(session, &perf_kmem);
 	if (err != 0)
 		goto out_delete;
 	sort_result();
@@ -513,11 +446,6 @@ out_delete:
 	return err;
 }
 
-static const char * const kmem_usage[] = {
-	"perf kmem [<options>] {record|stat}",
-	NULL
-};
-
 static int ptr_cmp(struct alloc_stat *l, struct alloc_stat *r)
 {
 	if (l->ptr < r->ptr)
@@ -616,8 +544,7 @@ static struct sort_dimension *avail_sorts[] = {
 	&pingpong_sort_dimension,
 };
 
-#define NUM_AVAIL_SORTS	\
-	(int)(sizeof(avail_sorts) / sizeof(struct sort_dimension *))
+#define NUM_AVAIL_SORTS	((int)ARRAY_SIZE(avail_sorts))
 
 static int sort_dimension__add(const char *tok, struct list_head *list)
 {
@@ -626,10 +553,11 @@ static int sort_dimension__add(const char *tok, struct list_head *list)
 
 	for (i = 0; i < NUM_AVAIL_SORTS; i++) {
 		if (!strcmp(avail_sorts[i]->name, tok)) {
-			sort = malloc(sizeof(*sort));
-			if (!sort)
-				die("malloc");
-			memcpy(sort, avail_sorts[i], sizeof(*sort));
+			sort = memdup(avail_sorts[i], sizeof(*avail_sorts[i]));
+			if (!sort) {
+				pr_err("%s: memdup failed\n", __func__);
+				return -1;
+			}
 			list_add_tail(&sort->list, list);
 			return 0;
 		}
@@ -643,8 +571,10 @@ static int setup_sorting(struct list_head *sort_list, const char *arg)
 	char *tok;
 	char *str = strdup(arg);
 
-	if (!str)
-		die("strdup");
+	if (!str) {
+		pr_err("%s: strdup failed\n", __func__);
+		return -1;
+	}
 
 	while (true) {
 		tok = strsep(&str, ",");
@@ -652,6 +582,7 @@ static int setup_sorting(struct list_head *sort_list, const char *arg)
 			break;
 		if (sort_dimension__add(tok, sort_list) < 0) {
 			error("Unknown --sort key: '%s'", tok);
+			free(str);
 			return -1;
 		}
 	}
@@ -660,8 +591,8 @@ static int setup_sorting(struct list_head *sort_list, const char *arg)
 	return 0;
 }
 
-static int parse_sort_opt(const struct option *opt __used,
-			  const char *arg, int unset __used)
+static int parse_sort_opt(const struct option *opt __maybe_unused,
+			  const char *arg, int unset __maybe_unused)
 {
 	if (!arg)
 		return -1;
@@ -674,22 +605,24 @@ static int parse_sort_opt(const struct option *opt __used,
 	return 0;
 }
 
-static int parse_caller_opt(const struct option *opt __used,
-			  const char *arg __used, int unset __used)
+static int parse_caller_opt(const struct option *opt __maybe_unused,
+			    const char *arg __maybe_unused,
+			    int unset __maybe_unused)
 {
 	caller_flag = (alloc_flag + 1);
 	return 0;
 }
 
-static int parse_alloc_opt(const struct option *opt __used,
-			  const char *arg __used, int unset __used)
+static int parse_alloc_opt(const struct option *opt __maybe_unused,
+			   const char *arg __maybe_unused,
+			   int unset __maybe_unused)
 {
 	alloc_flag = (caller_flag + 1);
 	return 0;
 }
 
-static int parse_line_opt(const struct option *opt __used,
-			  const char *arg, int unset __used)
+static int parse_line_opt(const struct option *opt __maybe_unused,
+			  const char *arg, int unset __maybe_unused)
 {
 	int lines;
 
@@ -706,47 +639,26 @@ static int parse_line_opt(const struct option *opt __used,
 	return 0;
 }
 
-static const struct option kmem_options[] = {
-	OPT_STRING('i', "input", &input_name, "file",
-		   "input file name"),
-	OPT_CALLBACK_NOOPT(0, "caller", NULL, NULL,
-			   "show per-callsite statistics",
-			   parse_caller_opt),
-	OPT_CALLBACK_NOOPT(0, "alloc", NULL, NULL,
-			   "show per-allocation statistics",
-			   parse_alloc_opt),
-	OPT_CALLBACK('s', "sort", NULL, "key[,key2...]",
-		     "sort by keys: ptr, call_site, bytes, hit, pingpong, frag",
-		     parse_sort_opt),
-	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_END()
-};
-
-static const char *record_args[] = {
-	"record",
-	"-a",
-	"-R",
-	"-f",
-	"-c", "1",
+static int __cmd_record(int argc, const char **argv)
+{
+	const char * const record_args[] = {
+	"record", "-a", "-R", "-c", "1",
 	"-e", "kmem:kmalloc",
 	"-e", "kmem:kmalloc_node",
 	"-e", "kmem:kfree",
 	"-e", "kmem:kmem_cache_alloc",
 	"-e", "kmem:kmem_cache_alloc_node",
 	"-e", "kmem:kmem_cache_free",
-};
-
-static int __cmd_record(int argc, const char **argv)
-{
+	};
 	unsigned int rec_argc, i, j;
 	const char **rec_argv;
 
 	rec_argc = ARRAY_SIZE(record_args) + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
+	if (rec_argv == NULL)
+		return -ENOMEM;
+
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = strdup(record_args[i]);
 
@@ -756,9 +668,29 @@ static int __cmd_record(int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
-int cmd_kmem(int argc, const char **argv, const char *prefix __used)
+int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	argc = parse_options(argc, argv, kmem_options, kmem_usage, 0);
+	const char * const default_sort_order = "frag,hit,bytes";
+	const struct option kmem_options[] = {
+	OPT_STRING('i', "input", &input_name, "file", "input file name"),
+	OPT_CALLBACK_NOOPT(0, "caller", NULL, NULL,
+			   "show per-callsite statistics", parse_caller_opt),
+	OPT_CALLBACK_NOOPT(0, "alloc", NULL, NULL,
+			   "show per-allocation statistics", parse_alloc_opt),
+	OPT_CALLBACK('s', "sort", NULL, "key[,key2...]",
+		     "sort by keys: ptr, call_site, bytes, hit, pingpong, frag",
+		     parse_sort_opt),
+	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_END()
+	};
+	const char *const kmem_subcommands[] = { "record", "stat", NULL };
+	const char *kmem_usage[] = {
+		NULL,
+		NULL
+	};
+	argc = parse_options_subcommand(argc, argv, kmem_options,
+					kmem_subcommands, kmem_usage, 0);
 
 	if (!argc)
 		usage_with_options(kmem_usage, kmem_options);
@@ -768,7 +700,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __used)
 	if (!strncmp(argv[0], "rec", 3)) {
 		return __cmd_record(argc, argv);
 	} else if (!strcmp(argv[0], "stat")) {
-		setup_cpunode_map();
+		if (cpu__setup_cpunode_map())
+			return -1;
 
 		if (list_empty(&caller_sort))
 			setup_sorting(&caller_sort, default_sort_order);