blob: ec2b787b23bd0664271881e9c92170835396e793 [file] [log] [blame]
#include "perf.h"
#include "util/util.h"
#include "util/parse-options.h"
#include "util/parse-events.h"
#include <sched.h>
#define ALIGN(x, a) __ALIGN_MASK(x, (typeof(x))(a)-1)
#define __ALIGN_MASK(x, mask) (((x)+(mask))&~(mask))
static int default_interval = 100000;
static int event_count[MAX_COUNTERS];
static int fd[MAX_NR_CPUS][MAX_COUNTERS];
static int nr_cpus = 0;
static unsigned int page_size;
static unsigned int mmap_pages = 16;
static int output;
static const char *output_name = "output.perf";
static int group = 0;
static unsigned int realtime_prio = 0;
static int system_wide = 0;
static pid_t target_pid = -1;
static int inherit = 1;
static int nmi = 1;
const unsigned int default_count[] = {
1000000,
1000000,
10000,
10000,
1000000,
10000,
};
struct mmap_data {
int counter;
void *base;
unsigned int mask;
unsigned int prev;
};
static unsigned int mmap_read_head(struct mmap_data *md)
{
struct perf_counter_mmap_page *pc = md->base;
int head;
head = pc->data_head;
rmb();
return head;
}
static long events;
static struct timeval last_read, this_read;
static void mmap_read(struct mmap_data *md)
{
unsigned int head = mmap_read_head(md);
unsigned int old = md->prev;
unsigned char *data = md->base + page_size;
unsigned long size;
void *buf;
int diff;
gettimeofday(&this_read, NULL);
/*
* If we're further behind than half the buffer, there's a chance
* the writer will bite our tail and screw up the events under us.
*
* If we somehow ended up ahead of the head, we got messed up.
*
* In either case, truncate and restart at head.
*/
diff = head - old;
if (diff > md->mask / 2 || diff < 0) {
struct timeval iv;
unsigned long msecs;
timersub(&this_read, &last_read, &iv);
msecs = iv.tv_sec*1000 + iv.tv_usec/1000;
fprintf(stderr, "WARNING: failed to keep up with mmap data."
" Last read %lu msecs ago.\n", msecs);
/*
* head points to a known good entry, start there.
*/
old = head;
}
last_read = this_read;
if (old != head)
events++;
size = head - old;
if ((old & md->mask) + size != (head & md->mask)) {
buf = &data[old & md->mask];
size = md->mask + 1 - (old & md->mask);
old += size;
while (size) {
int ret = write(output, buf, size);
if (ret < 0) {
perror("failed to write");
exit(-1);
}
size -= ret;
buf += ret;
}
}
buf = &data[old & md->mask];
size = head - old;
old += size;
while (size) {
int ret = write(output, buf, size);
if (ret < 0) {
perror("failed to write");
exit(-1);
}
size -= ret;
buf += ret;
}
md->prev = old;
}
static volatile int done = 0;
static void sig_handler(int sig)
{
done = 1;
}
static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS];
static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
static int nr_poll;
static int nr_cpu;
struct mmap_event {
struct perf_event_header header;
__u32 pid, tid;
__u64 start;
__u64 len;
__u64 pgoff;
char filename[PATH_MAX];
};
struct comm_event {
struct perf_event_header header;
__u32 pid,tid;
char comm[16];
};
static pid_t pid_synthesize_comm_event(pid_t pid)
{
char filename[PATH_MAX];
char bf[BUFSIZ];
struct comm_event comm_ev;
size_t size;
int fd;
snprintf(filename, sizeof(filename), "/proc/%d/stat", pid);
fd = open(filename, O_RDONLY);
if (fd < 0) {
fprintf(stderr, "couldn't open %s\n", filename);
exit(EXIT_FAILURE);
}
if (read(fd, bf, sizeof(bf)) < 0) {
fprintf(stderr, "couldn't read %s\n", filename);
exit(EXIT_FAILURE);
}
close(fd);
pid_t spid, ppid;
char state;
char comm[18];
memset(&comm_ev, 0, sizeof(comm_ev));
int nr = sscanf(bf, "%d %s %c %d %d ",
&spid, comm, &state, &ppid, &comm_ev.pid);
if (nr != 5) {
fprintf(stderr, "couldn't get COMM and pgid, malformed %s\n",
filename);
exit(EXIT_FAILURE);
}
comm_ev.header.type = PERF_EVENT_COMM;
comm_ev.tid = pid;
size = strlen(comm);
comm[--size] = '\0'; /* Remove the ')' at the end */
--size; /* Remove the '(' at the begin */
memcpy(comm_ev.comm, comm + 1, size);
size = ALIGN(size, sizeof(uint64_t));
comm_ev.header.size = sizeof(comm_ev) - (sizeof(comm_ev.comm) - size);
int ret = write(output, &comm_ev, comm_ev.header.size);
if (ret < 0) {
perror("failed to write");
exit(-1);
}
return comm_ev.pid;
}
static void pid_synthesize_mmap_events(pid_t pid, pid_t pgid)
{
char filename[PATH_MAX];
FILE *fp;
snprintf(filename, sizeof(filename), "/proc/%d/maps", pid);
fp = fopen(filename, "r");
if (fp == NULL) {
fprintf(stderr, "couldn't open %s\n", filename);
exit(EXIT_FAILURE);
}
while (1) {
char bf[BUFSIZ];
unsigned char vm_read, vm_write, vm_exec, vm_mayshare;
struct mmap_event mmap_ev = {
.header.type = PERF_EVENT_MMAP,
};
unsigned long ino;
int major, minor;
size_t size;
if (fgets(bf, sizeof(bf), fp) == NULL)
break;
/* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */
sscanf(bf, "%llx-%llx %c%c%c%c %llx %x:%x %lu",
&mmap_ev.start, &mmap_ev.len,
&vm_read, &vm_write, &vm_exec, &vm_mayshare,
&mmap_ev.pgoff, &major, &minor, &ino);
if (vm_exec == 'x') {
char *execname = strrchr(bf, ' ');
if (execname == NULL || execname[1] != '/')
continue;
execname += 1;
size = strlen(execname);
execname[size - 1] = '\0'; /* Remove \n */
memcpy(mmap_ev.filename, execname, size);
size = ALIGN(size, sizeof(uint64_t));
mmap_ev.len -= mmap_ev.start;
mmap_ev.header.size = (sizeof(mmap_ev) -
(sizeof(mmap_ev.filename) - size));
mmap_ev.pid = pgid;
mmap_ev.tid = pid;
if (write(output, &mmap_ev, mmap_ev.header.size) < 0) {
perror("failed to write");
exit(-1);
}
}
}
fclose(fp);
}
static void open_counters(int cpu, pid_t pid)
{
struct perf_counter_hw_event hw_event;
int counter, group_fd;
int track = 1;
if (pid > 0) {
pid_t pgid = pid_synthesize_comm_event(pid);
pid_synthesize_mmap_events(pid, pgid);
}
group_fd = -1;
for (counter = 0; counter < nr_counters; counter++) {
memset(&hw_event, 0, sizeof(hw_event));
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 = nmi;
hw_event.mmap = track;
hw_event.comm = track;
hw_event.inherit = (cpu < 0) && inherit;
track = 0; // only the first counter needs these
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[nr_cpu][counter], strerror(err));
if (err == EPERM)
printf("Are you root?\n");
exit(-1);
}
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[nr_cpu][counter];
event_array[nr_poll].fd = fd[nr_cpu][counter];
event_array[nr_poll].events = POLLIN;
nr_poll++;
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++;
}
static int __cmd_record(int argc, const char **argv)
{
int i, counter;
pid_t pid;
int ret;
page_size = sysconf(_SC_PAGE_SIZE);
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);
}
if (!system_wide) {
open_counters(-1, target_pid != -1 ? target_pid : 0);
} else for (i = 0; i < nr_cpus; i++)
open_counters(i, target_pid);
signal(SIGCHLD, sig_handler);
signal(SIGINT, sig_handler);
if (target_pid == -1) {
pid = fork();
if (pid < 0)
perror("failed to fork");
if (!pid) {
if (execvp(argv[0], (char **)argv)) {
perror(argv[0]);
exit(-1);
}
}
}
if (realtime_prio) {
struct sched_param param;
param.sched_priority = realtime_prio;
if (sched_setscheduler(0, SCHED_FIFO, &param)) {
printf("Could not set realtime priority.\n");
exit(-1);
}
}
/*
* TODO: store the current /proc/$/maps information somewhere
*/
while (!done) {
int hits = events;
for (i = 0; i < nr_cpu; i++) {
for (counter = 0; counter < nr_counters; counter++)
mmap_read(&mmap_array[i][counter]);
}
if (hits == events)
ret = poll(event_array, nr_poll, 100);
}
return 0;
}
static const char * const record_usage[] = {
"perf record [<options>] <command>",
NULL
};
static char events_help_msg[EVENTS_HELP_MAX];
static const struct option options[] = {
OPT_CALLBACK('e', "event", NULL, "event",
events_help_msg, parse_events),
OPT_INTEGER('c', "count", &default_interval,
"event period to sample"),
OPT_INTEGER('m', "mmap-pages", &mmap_pages,
"number of mmap data pages"),
OPT_STRING('o', "output", &output_name, "file",
"output file name"),
OPT_BOOLEAN('i', "inherit", &inherit,
"child tasks inherit counters"),
OPT_INTEGER('p', "pid", &target_pid,
"record events on existing pid"),
OPT_INTEGER('r', "realtime", &realtime_prio,
"collect data with this RT SCHED_FIFO priority"),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
OPT_END()
};
int cmd_record(int argc, const char **argv, const char *prefix)
{
int counter;
create_events_help(events_help_msg);
argc = parse_options(argc, argv, options, record_usage, 0);
if (!argc)
usage_with_options(record_usage, options);
if (!nr_counters) {
nr_counters = 1;
event_id[0] = 0;
}
for (counter = 0; counter < nr_counters; counter++) {
if (event_count[counter])
continue;
event_count[counter] = default_interval;
}
return __cmd_record(argc, argv);
}