perf_counter: tools: update the tools to support process and inherited counters

"perf record":
 - per task counter
 - inherit switch
 - nmi switch

"perf report":
 - userspace/kernel filter

"perf stat":
 - userspace/kernel filter
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
LKML-Reference: <20090505155437.389163017@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

Documentation/perf_counter/builtin-record.c

@@ -46,6 +46,9 @@ static int			output;
 static char 			*output_name			= "output.perf";
 static int			group				= 0;
 static unsigned int		realtime_prio			= 0;
+static int			system_wide			= 0;
+static int			inherit				= 1;
+static int			nmi				= 1;
 
 const unsigned int default_count[] = {
 	1000000,
@@ -167,7 +170,7 @@ static void display_events_help(void)
 static void display_help(void)
 {
 	printf(
-	"Usage: perf-record [<options>]\n"
+	"Usage: perf-record [<options>] <cmd>\n"
 	"perf-record Options (up to %d event types can be specified at once):\n\n",
 		 MAX_COUNTERS);
 
@@ -178,12 +181,13 @@ static void display_help(void)
 	" -m pages  --mmap_pages=<pages> # number of mmap data pages\n"
 	" -o file   --output=<file>      # output file\n"
 	" -r prio   --realtime=<prio>    # use RT prio\n"
+	" -s        --system             # system wide profiling\n"
 	);
 
 	exit(0);
 }
 
-static void process_options(int argc, char *argv[])
+static void process_options(int argc, const char *argv[])
 {
 	int error = 0, counter;
 
@@ -196,9 +200,12 @@ static void process_options(int argc, char *argv[])
 			{"mmap_pages",	required_argument,	NULL, 'm'},
 			{"output",	required_argument,	NULL, 'o'},
 			{"realtime",	required_argument,	NULL, 'r'},
+			{"system",	no_argument,		NULL, 's'},
+			{"inherit",	no_argument,		NULL, 'i'},
+			{"nmi",		no_argument,		NULL, 'n'},
 			{NULL,		0,			NULL,  0 }
 		};
-		int c = getopt_long(argc, argv, "+:c:e:m:o:r:",
+		int c = getopt_long(argc, argv, "+:c:e:m:o:r:sin",
 				    long_options, &option_index);
 		if (c == -1)
 			break;
@@ -209,9 +216,16 @@ static void process_options(int argc, char *argv[])
 		case 'm': mmap_pages			=   atoi(optarg); break;
 		case 'o': output_name			= strdup(optarg); break;
 		case 'r': realtime_prio			=   atoi(optarg); break;
+		case 's': system_wide                   ^=             1; break;
+		case 'i': inherit			^=	       1; break;
+		case 'n': nmi				^=	       1; break;
 		default: error = 1; break;
 		}
 	}
+
+	if (argc - optind == 0)
+		error = 1;
+
 	if (error)
 		display_help();
 
@@ -325,39 +339,27 @@ static void mmap_read(struct mmap_data *md)
 
 static volatile int done = 0;
 
-static void sigchld_handler(int sig)
+static void sig_handler(int sig)
 {
-	if (sig == SIGCHLD)
 	done = 1;
 }
 
-int cmd_record(int argc, char **argv)
-{
-	struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS];
-	struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
-	struct perf_counter_hw_event hw_event;
-	int i, counter, group_fd, nr_poll = 0;
-	pid_t pid;
-	int ret;
-
-	page_size = sysconf(_SC_PAGE_SIZE);
+static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS];
+static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
 
-	process_options(argc, argv);
+static int nr_poll;
+static int nr_cpu;
 
-	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
-	assert(nr_cpus <= MAX_NR_CPUS);
-	assert(nr_cpus >= 0);
-
-	output = open(output_name, O_CREAT|O_RDWR, S_IRWXU);
-	if (output < 0) {
-		perror("failed to create output file");
-		exit(-1);
-	}
+static void open_counters(int cpu)
+{
+	struct perf_counter_hw_event hw_event;
+	int counter, group_fd;
+	int track = 1;
+	pid_t pid = -1;
 
-	argc -= optind;
-	argv += optind;
+	if (cpu < 0)
+		pid = 0;
 
-	for (i = 0; i < nr_cpus; i++) {
 	group_fd = -1;
 	for (counter = 0; counter < nr_counters; counter++) {
 
@@ -365,46 +367,81 @@ int cmd_record(int argc, char **argv)
 		hw_event.config		= event_id[counter];
 		hw_event.irq_period	= event_count[counter];
 		hw_event.record_type	= PERF_RECORD_IP | PERF_RECORD_TID;
-			hw_event.nmi		= 1;
-			hw_event.mmap		= 1;
-			hw_event.comm		= 1;
+		hw_event.nmi		= nmi;
+		hw_event.mmap		= track;
+		hw_event.comm		= track;
+		hw_event.inherit	= (cpu < 0) && inherit;
+
+		track = 0; // only the first counter needs these
 
-			fd[i][counter] = sys_perf_counter_open(&hw_event, -1, i, group_fd, 0);
-			if (fd[i][counter] < 0) {
+		fd[nr_cpu][counter] =
+			sys_perf_counter_open(&hw_event, pid, cpu, group_fd, 0);
+
+		if (fd[nr_cpu][counter] < 0) {
 			int err = errno;
 			printf("kerneltop error: syscall returned with %d (%s)\n",
-					fd[i][counter], strerror(err));
+					fd[nr_cpu][counter], strerror(err));
 			if (err == EPERM)
 				printf("Are you root?\n");
 			exit(-1);
 		}
-			assert(fd[i][counter] >= 0);
-			fcntl(fd[i][counter], F_SETFL, O_NONBLOCK);
+		assert(fd[nr_cpu][counter] >= 0);
+		fcntl(fd[nr_cpu][counter], F_SETFL, O_NONBLOCK);
 
 		/*
 		 * First counter acts as the group leader:
 		 */
 		if (group && group_fd == -1)
-				group_fd = fd[i][counter];
+			group_fd = fd[nr_cpu][counter];
 
-			event_array[nr_poll].fd = fd[i][counter];
+		event_array[nr_poll].fd = fd[nr_cpu][counter];
 		event_array[nr_poll].events = POLLIN;
 		nr_poll++;
 
-			mmap_array[i][counter].counter = counter;
-			mmap_array[i][counter].prev = 0;
-			mmap_array[i][counter].mask = mmap_pages*page_size - 1;
-			mmap_array[i][counter].base = mmap(NULL, (mmap_pages+1)*page_size,
-					PROT_READ, MAP_SHARED, fd[i][counter], 0);
-			if (mmap_array[i][counter].base == MAP_FAILED) {
+		mmap_array[nr_cpu][counter].counter = counter;
+		mmap_array[nr_cpu][counter].prev = 0;
+		mmap_array[nr_cpu][counter].mask = mmap_pages*page_size - 1;
+		mmap_array[nr_cpu][counter].base = mmap(NULL, (mmap_pages+1)*page_size,
+				PROT_READ, MAP_SHARED, fd[nr_cpu][counter], 0);
+		if (mmap_array[nr_cpu][counter].base == MAP_FAILED) {
 			printf("kerneltop error: failed to mmap with %d (%s)\n",
 					errno, strerror(errno));
 			exit(-1);
 		}
 	}
+	nr_cpu++;
+}
+
+int cmd_record(int argc, const char **argv)
+{
+	int i, counter;
+	pid_t pid;
+	int ret;
+
+	page_size = sysconf(_SC_PAGE_SIZE);
+
+	process_options(argc, argv);
+
+	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+	assert(nr_cpus <= MAX_NR_CPUS);
+	assert(nr_cpus >= 0);
+
+	output = open(output_name, O_CREAT|O_RDWR, S_IRWXU);
+	if (output < 0) {
+		perror("failed to create output file");
+		exit(-1);
 	}
 
-	signal(SIGCHLD, sigchld_handler);
+	argc -= optind;
+	argv += optind;
+
+	if (!system_wide)
+		open_counters(-1);
+	else for (i = 0; i < nr_cpus; i++)
+		open_counters(i);
+
+	signal(SIGCHLD, sig_handler);
+	signal(SIGINT, sig_handler);
 
 	pid = fork();
 	if (pid < 0)
@@ -434,7 +471,7 @@ int cmd_record(int argc, char **argv)
 	while (!done) {
 		int hits = events;
 
-		for (i = 0; i < nr_cpus; i++) {
+		for (i = 0; i < nr_cpu; i++) {
 			for (counter = 0; counter < nr_counters; counter++)
 				mmap_read(&mmap_array[i][counter]);
 		}

Documentation/perf_counter/builtin-stat.c

@@ -87,6 +87,9 @@
 
 #include "perf.h"
 
+#define EVENT_MASK_KERNEL		1
+#define EVENT_MASK_USER			2
+
 static int			system_wide			=  0;
 
 static int			nr_counters			=  0;
@@ -104,6 +107,7 @@ static __u64			event_id[MAX_COUNTERS]		= {
 static int			default_interval = 100000;
 static int			event_count[MAX_COUNTERS];
 static int			fd[MAX_NR_CPUS][MAX_COUNTERS];
+static int			event_mask[MAX_COUNTERS];
 
 static int			tid				= -1;
 static int			profile_cpu			= -1;
@@ -258,13 +262,24 @@ static __u64 match_event_symbols(char *str)
 	__u64 config, id;
 	int type;
 	unsigned int i;
+	char mask_str[4];
 
 	if (sscanf(str, "r%llx", &config) == 1)
 		return config | PERF_COUNTER_RAW_MASK;
 
-	if (sscanf(str, "%d:%llu", &type, &id) == 2)
+	switch (sscanf(str, "%d:%llu:%2s", &type, &id, mask_str)) {
+		case 3:
+			if (strchr(mask_str, 'u'))
+				event_mask[nr_counters] |= EVENT_MASK_USER;
+			if (strchr(mask_str, 'k'))
+				event_mask[nr_counters] |= EVENT_MASK_KERNEL;
+		case 2:
 			return EID(type, id);
 
+		default:
+			break;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(event_symbols); i++) {
 		if (!strncmp(str, event_symbols[i].symbol,
 			     strlen(event_symbols[i].symbol)))
@@ -313,6 +328,11 @@ static void create_perfstat_counter(int counter)
 	hw_event.config		= event_id[counter];
 	hw_event.record_type	= 0;
 	hw_event.nmi		= 0;
+	hw_event.exclude_kernel = event_mask[counter] & EVENT_MASK_KERNEL;
+	hw_event.exclude_user   = event_mask[counter] & EVENT_MASK_USER;
+
+printf("exclude: %d\n", event_mask[counter]);
+
 	if (scale)
 		hw_event.read_format	= PERF_FORMAT_TOTAL_TIME_ENABLED |
 					  PERF_FORMAT_TOTAL_TIME_RUNNING;

Documentation/perf_counter/perf-report.cc

@@ -33,8 +33,13 @@
 #include <string>
 
 
+#define SHOW_KERNEL	1
+#define SHOW_USER	2
+#define SHOW_HV		4
+
 static char 		const *input_name = "output.perf";
 static int		input;
+static int		show_mask = SHOW_KERNEL | SHOW_USER | SHOW_HV;
 
 static unsigned long	page_size;
 static unsigned long	mmap_window = 32;
@@ -359,15 +364,21 @@ static void process_options(int argc, char *argv[])
 		/** Options for getopt */
 		static struct option long_options[] = {
 			{"input",	required_argument,	NULL, 'i'},
+			{"no-user",	no_argument,		NULL, 'u'},
+			{"no-kernel",	no_argument,		NULL, 'k'},
+			{"no-hv",	no_argument,		NULL, 'h'},
 			{NULL,		0,			NULL,  0 }
 		};
-		int c = getopt_long(argc, argv, "+:i:",
+		int c = getopt_long(argc, argv, "+:i:kuh",
 				    long_options, &option_index);
 		if (c == -1)
 			break;
 
 		switch (c) {
 		case 'i': input_name			= strdup(optarg); break;
+		case 'k': show_mask &= ~SHOW_KERNEL; break;
+		case 'u': show_mask &= ~SHOW_USER; break;
+		case 'h': show_mask &= ~SHOW_HV; break;
 		default: error = 1; break;
 		}
 	}
@@ -443,22 +454,28 @@ more:
 
 	if (event->header.misc & PERF_EVENT_MISC_OVERFLOW) {
 		std::string comm, sym, level;
+		int show = 0;
 		char output[1024];
 
 		if (event->header.misc & PERF_EVENT_MISC_KERNEL) {
+			show |= SHOW_KERNEL;
 			level = " [k] ";
 			sym = resolve_kernel_symbol(event->ip.ip);
 		} else if (event->header.misc & PERF_EVENT_MISC_USER) {
+			show |= SHOW_USER;
 			level = " [.] ";
 			sym = resolve_user_symbol(event->ip.pid, event->ip.ip);
 		} else {
+			show |= SHOW_HV;
 			level = " [H] ";
 		}
-		comm = resolve_comm(event->ip.pid);
 
+		if (show & show_mask) {
+			comm = resolve_comm(event->ip.pid);
 			snprintf(output, sizeof(output), "%16s %s %s",
 					comm.c_str(), level.c_str(), sym.c_str());
 			hist[output]++;
+		}
 
 		total++;