#include "util/symbol.h"
#include "util/color.h"
#include "util/util.h"
-#include "util/rbtree.h"
+#include <linux/rbtree.h>
#include "util/parse-options.h"
#include "util/parse-events.h"
static int default_interval = 100000;
-static __u64 count_filter = 5;
+static u64 count_filter = 5;
static int print_entries = 15;
static int target_pid = -1;
static unsigned int page_size;
static unsigned int mmap_pages = 16;
static int freq = 0;
+static int verbose = 0;
+static char *vmlinux = NULL;
static char *sym_filter;
static unsigned long filter_start;
* Symbols
*/
-static uint64_t min_ip;
-static uint64_t max_ip = -1ll;
+static u64 min_ip;
+static u64 max_ip = -1ll;
struct sym_entry {
struct rb_node rb_node;
100.0 - (100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec)));
if (nr_counters == 1) {
- printf("%Ld", attrs[0].sample_period);
+ printf("%Ld", (u64)attrs[0].sample_period);
if (freq)
printf("Hz ");
else
for (nd = rb_first(&tmp); nd; nd = rb_next(nd)) {
struct sym_entry *syme = rb_entry(nd, struct sym_entry, rb_node);
struct symbol *sym = (struct symbol *)(syme + 1);
- char *color = PERF_COLOR_NORMAL;
double pcnt;
if (++printed > print_entries || syme->snap_count < count_filter)
pcnt = 100.0 - (100.0 * ((sum_ksamples - syme->snap_count) /
sum_ksamples));
- /*
- * We color high-overhead entries in red, low-overhead
- * entries in green - and keep the middle ground normal:
- */
- if (pcnt >= 5.0)
- color = PERF_COLOR_RED;
- if (pcnt < 0.5)
- color = PERF_COLOR_GREEN;
-
if (nr_counters == 1)
printf("%20.2f - ", syme->weight);
else
printf("%9.1f %10ld - ", syme->weight, syme->snap_count);
- color_fprintf(stdout, color, "%4.1f%%", pcnt);
- printf(" - %016llx : %s\n", sym->start, sym->name);
+ percent_color_fprintf(stdout, "%4.1f%%", pcnt);
+ printf(" - %016llx : %s", sym->start, sym->name);
+ if (sym->module)
+ printf("\t[%s]", sym->module->name);
+ printf("\n");
}
}
-static void *display_thread(void *arg)
+static void *display_thread(void *arg __used)
{
struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
int delay_msecs = delay_secs * 1000;
return NULL;
}
+/* Tag samples to be skipped. */
+static const char *skip_symbols[] = {
+ "default_idle",
+ "cpu_idle",
+ "enter_idle",
+ "exit_idle",
+ "mwait_idle",
+ "ppc64_runlatch_off",
+ "pseries_dedicated_idle_sleep",
+ NULL
+};
+
static int symbol_filter(struct dso *self, struct symbol *sym)
{
static int filter_match;
struct sym_entry *syme;
const char *name = sym->name;
+ int i;
+
+ /*
+ * ppc64 uses function descriptors and appends a '.' to the
+ * start of every instruction address. Remove it.
+ */
+ if (name[0] == '.')
+ name++;
if (!strcmp(name, "_text") ||
!strcmp(name, "_etext") ||
return 1;
syme = dso__sym_priv(self, sym);
- /* Tag samples to be skipped. */
- if (!strcmp("default_idle", name) ||
- !strcmp("cpu_idle", name) ||
- !strcmp("enter_idle", name) ||
- !strcmp("exit_idle", name) ||
- !strcmp("mwait_idle", name))
- syme->skip = 1;
+ for (i = 0; skip_symbols[i]; i++) {
+ if (!strcmp(skip_symbols[i], name)) {
+ syme->skip = 1;
+ break;
+ }
+ }
if (filter_match == 1) {
filter_end = sym->start;
{
struct rb_node *node;
struct symbol *sym;
+ int modules = vmlinux ? 1 : 0;
kernel_dso = dso__new("[kernel]", sizeof(struct sym_entry));
if (kernel_dso == NULL)
return -1;
- if (dso__load_kernel(kernel_dso, NULL, symbol_filter, 1) != 0)
+ if (dso__load_kernel(kernel_dso, vmlinux, symbol_filter, verbose, modules) <= 0)
goto out_delete_dso;
node = rb_first(&kernel_dso->syms);
/*
* Binary search in the histogram table and record the hit:
*/
-static void record_ip(uint64_t ip, int counter)
+static void record_ip(u64 ip, int counter)
{
struct symbol *sym = dso__find_symbol(kernel_dso, ip);
samples--;
}
-static void process_event(uint64_t ip, int counter)
+static void process_event(u64 ip, int counter, int user)
{
samples++;
- if (ip < min_ip || ip > max_ip) {
+ if (user) {
userspace_samples++;
return;
}
struct mmap_data {
int counter;
void *base;
- unsigned int mask;
+ int mask;
unsigned int prev;
};
for (; old != head;) {
struct ip_event {
struct perf_event_header header;
- __u64 ip;
- __u32 pid, target_pid;
+ u64 ip;
+ u32 pid, target_pid;
};
struct mmap_event {
struct perf_event_header header;
- __u32 pid, target_pid;
- __u64 start;
- __u64 len;
- __u64 pgoff;
+ u32 pid, target_pid;
+ u64 start;
+ u64 len;
+ u64 pgoff;
char filename[PATH_MAX];
};
old += size;
- if (event->header.misc & PERF_EVENT_MISC_OVERFLOW) {
- if (event->header.type & PERF_SAMPLE_IP)
- process_event(event->ip.ip, md->counter);
+ if (event->header.type == PERF_EVENT_SAMPLE) {
+ int user =
+ (event->header.misc & PERF_EVENT_MISC_CPUMODE_MASK) == PERF_EVENT_MISC_USER;
+ process_event(event->ip.ip, md->counter, user);
}
}
if (fd[i][counter] < 0) {
int err = errno;
- error("sys_perf_counter_open() syscall returned with %d (%s)\n",
- fd[i][counter], strerror(err));
-
if (err == EPERM)
- die(" No permission - are you root?\n");
+ die("No permission - are you root?\n");
/*
* If it's cycles then fall back to hrtimer
* based cpu-clock-tick sw counter, which
* is always available even if no PMU support:
*/
if (attr->type == PERF_TYPE_HARDWARE
- && attr->config == PERF_COUNT_CPU_CYCLES) {
+ && attr->config == PERF_COUNT_HW_CPU_CYCLES) {
+
+ if (verbose)
+ warning(" ... trying to fall back to cpu-clock-ticks\n");
- warning(" ... trying to fall back to cpu-clock-ticks\n");
attr->type = PERF_TYPE_SOFTWARE;
- attr->config = PERF_COUNT_CPU_CLOCK;
+ attr->config = PERF_COUNT_SW_CPU_CLOCK;
goto try_again;
}
+ printf("\n");
+ error("perfcounter syscall returned with %d (%s)\n",
+ fd[i][counter], strerror(err));
+ die("No CONFIG_PERF_COUNTERS=y kernel support configured?\n");
exit(-1);
}
assert(fd[i][counter] >= 0);
"system-wide collection from all CPUs"),
OPT_INTEGER('C', "CPU", &profile_cpu,
"CPU to profile on"),
+ OPT_STRING('k', "vmlinux", &vmlinux, "file", "vmlinux pathname"),
OPT_INTEGER('m', "mmap-pages", &mmap_pages,
"number of mmap data pages"),
OPT_INTEGER('r', "realtime", &realtime_prio,
"put the counters into a counter group"),
OPT_STRING('s', "sym-filter", &sym_filter, "pattern",
"only display symbols matchig this pattern"),
- OPT_BOOLEAN('z', "zero", &group,
+ OPT_BOOLEAN('z', "zero", &zero,
"zero history across updates"),
OPT_INTEGER('F', "freq", &freq,
"profile at this frequency"),
OPT_INTEGER('E', "entries", &print_entries,
"display this many functions"),
+ OPT_BOOLEAN('v', "verbose", &verbose,
+ "be more verbose (show counter open errors, etc)"),
OPT_END()
};
-int cmd_top(int argc, const char **argv, const char *prefix)
+int cmd_top(int argc, const char **argv, const char *prefix __used)
{
int counter;
+ symbol__init();
+
page_size = sysconf(_SC_PAGE_SIZE);
argc = parse_options(argc, argv, options, top_usage, 0);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff