summaryrefslogtreecommitdiff
path: root/tools/perf
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf')
-rw-r--r--tools/perf/Makefile24
-rw-r--r--tools/perf/builtin-record.c34
-rw-r--r--tools/perf/builtin-stat.c7
-rw-r--r--tools/perf/builtin-test.c12
-rw-r--r--tools/perf/builtin-top.c55
-rw-r--r--tools/perf/util/cgroup.c2
-rw-r--r--tools/perf/util/debug.c10
-rw-r--r--tools/perf/util/debug.h1
-rw-r--r--tools/perf/util/event.c2
-rw-r--r--tools/perf/util/evlist.c157
-rw-r--r--tools/perf/util/evlist.h3
-rw-r--r--tools/perf/util/evsel.c27
-rw-r--r--tools/perf/util/evsel.h6
-rw-r--r--tools/perf/util/probe-event.c19
-rw-r--r--tools/perf/util/probe-finder.c159
-rw-r--r--tools/perf/util/python.c11
-rw-r--r--tools/perf/util/setup.py7
-rw-r--r--tools/perf/util/string.c2
-rw-r--r--tools/perf/util/symbol.c5
-rw-r--r--tools/perf/util/ui/browsers/annotate.c6
-rw-r--r--tools/perf/util/ui/browsers/hists.c2
21 files changed, 359 insertions, 192 deletions
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 158c30e8210c..0c542563ea6c 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -35,15 +35,21 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
-e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
-e s/sh[234].*/sh/ )
+CC = $(CROSS_COMPILE)gcc
+AR = $(CROSS_COMPILE)ar
+
# Additional ARCH settings for x86
ifeq ($(ARCH),i386)
ARCH := x86
endif
ifeq ($(ARCH),x86_64)
- RAW_ARCH := x86_64
- ARCH := x86
- ARCH_CFLAGS := -DARCH_X86_64
- ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
+ ARCH := x86
+ IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -xc - | tail -n 1)
+ ifeq (${IS_X86_64}, 1)
+ RAW_ARCH := x86_64
+ ARCH_CFLAGS := -DARCH_X86_64
+ ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
+ endif
endif
#
@@ -119,8 +125,6 @@ lib = lib
export prefix bindir sharedir sysconfdir
-CC = $(CROSS_COMPILE)gcc
-AR = $(CROSS_COMPILE)ar
RM = rm -f
MKDIR = mkdir
FIND = find
@@ -165,8 +169,12 @@ grep-libs = $(filter -l%,$(1))
strip-libs = $(filter-out -l%,$(1))
$(OUTPUT)python/perf.so: $(PYRF_OBJS)
- $(QUIET_GEN)python util/setup.py --quiet build_ext --build-lib='$(OUTPUT)python' \
- --build-temp='$(OUTPUT)python/temp'
+ $(QUIET_GEN)( \
+ export CFLAGS="$(BASIC_CFLAGS)"; \
+ python util/setup.py --quiet build_ext --build-lib='$(OUTPUT)python' \
+ --build-temp='$(OUTPUT)python/temp' \
+ )
+
#
# No Perl scripts right now:
#
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 6febcc168a8c..0974f957b8fa 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -41,7 +41,7 @@ static u64 user_interval = ULLONG_MAX;
static u64 default_interval = 0;
static unsigned int page_size;
-static unsigned int mmap_pages = 128;
+static unsigned int mmap_pages = UINT_MAX;
static unsigned int user_freq = UINT_MAX;
static int freq = 1000;
static int output;
@@ -163,6 +163,7 @@ static void config_attr(struct perf_evsel *evsel, struct perf_evlist *evlist)
struct perf_event_attr *attr = &evsel->attr;
int track = !evsel->idx; /* only the first counter needs these */
+ attr->inherit = !no_inherit;
attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
PERF_FORMAT_TOTAL_TIME_RUNNING |
PERF_FORMAT_ID;
@@ -251,6 +252,9 @@ static void open_counters(struct perf_evlist *evlist)
{
struct perf_evsel *pos;
+ if (evlist->cpus->map[0] < 0)
+ no_inherit = true;
+
list_for_each_entry(pos, &evlist->entries, node) {
struct perf_event_attr *attr = &pos->attr;
/*
@@ -271,15 +275,13 @@ static void open_counters(struct perf_evlist *evlist)
retry_sample_id:
attr->sample_id_all = sample_id_all_avail ? 1 : 0;
try_again:
- if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group,
- !no_inherit) < 0) {
+ if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group) < 0) {
int err = errno;
- if (err == EPERM || err == EACCES)
- die("Permission error - are you root?\n"
- "\t Consider tweaking"
- " /proc/sys/kernel/perf_event_paranoid.\n");
- else if (err == ENODEV && cpu_list) {
+ if (err == EPERM || err == EACCES) {
+ ui__warning_paranoid();
+ exit(EXIT_FAILURE);
+ } else if (err == ENODEV && cpu_list) {
die("No such device - did you specify"
" an out-of-range profile CPU?\n");
} else if (err == EINVAL && sample_id_all_avail) {
@@ -302,11 +304,19 @@ try_again:
&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
if (verbose)
- warning(" ... trying to fall back to cpu-clock-ticks\n");
+ ui__warning("The cycles event is not supported, "
+ "trying to fall back to cpu-clock-ticks\n");
attr->type = PERF_TYPE_SOFTWARE;
attr->config = PERF_COUNT_SW_CPU_CLOCK;
goto try_again;
}
+
+ if (err == ENOENT) {
+ ui__warning("The %s event is not supported.\n",
+ event_name(pos));
+ exit(EXIT_FAILURE);
+ }
+
printf("\n");
error("sys_perf_event_open() syscall returned with %d (%s). /bin/dmesg may provide additional information.\n",
err, strerror(err));
@@ -417,7 +427,7 @@ static void mmap_read_all(void)
{
int i;
- for (i = 0; i < evsel_list->cpus->nr; i++) {
+ for (i = 0; i < evsel_list->nr_mmaps; i++) {
if (evsel_list->mmap[i].base)
mmap_read(&evsel_list->mmap[i]);
}
@@ -506,6 +516,10 @@ static int __cmd_record(int argc, const char **argv)
if (have_tracepoints(&evsel_list->entries))
perf_header__set_feat(&session->header, HEADER_TRACE_INFO);
+ /* 512 kiB: default amount of unprivileged mlocked memory */
+ if (mmap_pages == UINT_MAX)
+ mmap_pages = (512 * 1024) / page_size;
+
if (forks) {
child_pid = fork();
if (child_pid < 0) {
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e2109f9b43eb..03f0e45f1479 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -167,16 +167,17 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
PERF_FORMAT_TOTAL_TIME_RUNNING;
+ attr->inherit = !no_inherit;
+
if (system_wide)
- return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false, false);
+ return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false);
- attr->inherit = !no_inherit;
if (target_pid == -1 && target_tid == -1) {
attr->disabled = 1;
attr->enable_on_exec = 1;
}
- return perf_evsel__open_per_thread(evsel, evsel_list->threads, false, false);
+ return perf_evsel__open_per_thread(evsel, evsel_list->threads, false);
}
/*
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 1b2106c58f66..2f9a337b182f 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -290,7 +290,7 @@ static int test__open_syscall_event(void)
goto out_thread_map_delete;
}
- if (perf_evsel__open_per_thread(evsel, threads, false, false) < 0) {
+ if (perf_evsel__open_per_thread(evsel, threads, false) < 0) {
pr_debug("failed to open counter: %s, "
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
strerror(errno));
@@ -303,7 +303,7 @@ static int test__open_syscall_event(void)
}
if (perf_evsel__read_on_cpu(evsel, 0, 0) < 0) {
- pr_debug("perf_evsel__open_read_on_cpu\n");
+ pr_debug("perf_evsel__read_on_cpu\n");
goto out_close_fd;
}
@@ -365,7 +365,7 @@ static int test__open_syscall_event_on_all_cpus(void)
goto out_thread_map_delete;
}
- if (perf_evsel__open(evsel, cpus, threads, false, false) < 0) {
+ if (perf_evsel__open(evsel, cpus, threads, false) < 0) {
pr_debug("failed to open counter: %s, "
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
strerror(errno));
@@ -418,7 +418,7 @@ static int test__open_syscall_event_on_all_cpus(void)
continue;
if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
- pr_debug("perf_evsel__open_read_on_cpu\n");
+ pr_debug("perf_evsel__read_on_cpu\n");
err = -1;
break;
}
@@ -529,7 +529,7 @@ static int test__basic_mmap(void)
perf_evlist__add(evlist, evsels[i]);
- if (perf_evsel__open(evsels[i], cpus, threads, false, false) < 0) {
+ if (perf_evsel__open(evsels[i], cpus, threads, false) < 0) {
pr_debug("failed to open counter: %s, "
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
strerror(errno));
@@ -549,7 +549,7 @@ static int test__basic_mmap(void)
++foo;
}
- while ((event = perf_evlist__read_on_cpu(evlist, 0)) != NULL) {
+ while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
struct perf_sample sample;
if (event->header.type != PERF_RECORD_SAMPLE) {
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 676b4fb0070f..ebfc7cf5f63b 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -801,12 +801,12 @@ static void perf_event__process_sample(const union perf_event *event,
}
}
-static void perf_session__mmap_read_cpu(struct perf_session *self, int cpu)
+static void perf_session__mmap_read_idx(struct perf_session *self, int idx)
{
struct perf_sample sample;
union perf_event *event;
- while ((event = perf_evlist__read_on_cpu(top.evlist, cpu)) != NULL) {
+ while ((event = perf_evlist__mmap_read(top.evlist, idx)) != NULL) {
perf_session__parse_sample(self, event, &sample);
if (event->header.type == PERF_RECORD_SAMPLE)
@@ -820,8 +820,8 @@ static void perf_session__mmap_read(struct perf_session *self)
{
int i;
- for (i = 0; i < top.evlist->cpus->nr; i++)
- perf_session__mmap_read_cpu(self, i);
+ for (i = 0; i < top.evlist->nr_mmaps; i++)
+ perf_session__mmap_read_idx(self, i);
}
static void start_counters(struct perf_evlist *evlist)
@@ -845,15 +845,16 @@ static void start_counters(struct perf_evlist *evlist)
}
attr->mmap = 1;
+ attr->inherit = inherit;
try_again:
if (perf_evsel__open(counter, top.evlist->cpus,
- top.evlist->threads, group, inherit) < 0) {
+ top.evlist->threads, group) < 0) {
int err = errno;
- if (err == EPERM || err == EACCES)
- die("Permission error - are you root?\n"
- "\t Consider tweaking"
- " /proc/sys/kernel/perf_event_paranoid.\n");
+ if (err == EPERM || err == EACCES) {
+ ui__warning_paranoid();
+ goto out_err;
+ }
/*
* If it's cycles then fall back to hrtimer
* based cpu-clock-tick sw counter, which
@@ -861,25 +862,41 @@ try_again:
*/
if (attr->type == PERF_TYPE_HARDWARE &&
attr->config == PERF_COUNT_HW_CPU_CYCLES) {
-
if (verbose)
- warning(" ... trying to fall back to cpu-clock-ticks\n");
+ ui__warning("Cycles event not supported,\n"
+ "trying to fall back to cpu-clock-ticks\n");
attr->type = PERF_TYPE_SOFTWARE;
attr->config = PERF_COUNT_SW_CPU_CLOCK;
goto try_again;
}
- printf("\n");
- error("sys_perf_event_open() syscall returned with %d "
- "(%s). /bin/dmesg may provide additional information.\n",
- err, strerror(err));
- die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
- exit(-1);
+
+ if (err == ENOENT) {
+ ui__warning("The %s event is not supported.\n",
+ event_name(counter));
+ goto out_err;
+ }
+
+ ui__warning("The sys_perf_event_open() syscall "
+ "returned with %d (%s). /bin/dmesg "
+ "may provide additional information.\n"
+ "No CONFIG_PERF_EVENTS=y kernel support "
+ "configured?\n", err, strerror(err));
+ goto out_err;
}
}
- if (perf_evlist__mmap(evlist, mmap_pages, false) < 0)
- die("failed to mmap with %d (%s)\n", errno, strerror(errno));
+ if (perf_evlist__mmap(evlist, mmap_pages, false) < 0) {
+ ui__warning("Failed to mmap with %d (%s)\n",
+ errno, strerror(errno));
+ goto out_err;
+ }
+
+ return;
+
+out_err:
+ exit_browser(0);
+ exit(0);
}
static int __cmd_top(void)
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 9fea75535221..96bee5c46008 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -13,7 +13,7 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen)
{
FILE *fp;
char mountpoint[MAX_PATH+1], tokens[MAX_PATH+1], type[MAX_PATH+1];
- char *token, *saved_ptr;
+ char *token, *saved_ptr = NULL;
int found = 0;
fp = fopen("/proc/mounts", "r");
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index d4536a9e0d8c..155749d74350 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -57,6 +57,16 @@ void ui__warning(const char *format, ...)
}
#endif
+void ui__warning_paranoid(void)
+{
+ ui__warning("Permission error - are you root?\n"
+ "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
+ " -1 - Not paranoid at all\n"
+ " 0 - Disallow raw tracepoint access for unpriv\n"
+ " 1 - Disallow cpu events for unpriv\n"
+ " 2 - Disallow kernel profiling for unpriv\n");
+}
+
void trace_event(union perf_event *event)
{
unsigned char *raw_event = (void *)event;
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 93516cf4682c..fd53db47e3de 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -36,5 +36,6 @@ int ui_helpline__show_help(const char *format, va_list ap);
#endif
void ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
+void ui__warning_paranoid(void);
#endif /* __PERF_DEBUG_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 2b15c362ef56..1023f67633a4 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -710,7 +710,7 @@ try_again:
* in the whole kernel symbol list.
*/
if ((long long)al->addr < 0 &&
- cpumode == PERF_RECORD_MISC_KERNEL &&
+ cpumode == PERF_RECORD_MISC_USER &&
machine && mg != &machine->kmaps) {
mg = &machine->kmaps;
goto try_again;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d852cefa20de..23eb22b05d27 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -12,6 +12,7 @@
#include "evlist.h"
#include "evsel.h"
#include "util.h"
+#include "debug.h"
#include <sys/mman.h>
@@ -165,11 +166,11 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
return NULL;
}
-union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu)
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
{
/* XXX Move this to perf.c, making it generally available */
unsigned int page_size = sysconf(_SC_PAGE_SIZE);
- struct perf_mmap *md = &evlist->mmap[cpu];
+ struct perf_mmap *md = &evlist->mmap[idx];
unsigned int head = perf_mmap__read_head(md);
unsigned int old = md->prev;
unsigned char *data = md->base + page_size;
@@ -234,36 +235,126 @@ union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu)
void perf_evlist__munmap(struct perf_evlist *evlist)
{
- int cpu;
+ int i;
- for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
- if (evlist->mmap[cpu].base != NULL) {
- munmap(evlist->mmap[cpu].base, evlist->mmap_len);
- evlist->mmap[cpu].base = NULL;
+ for (i = 0; i < evlist->nr_mmaps; i++) {
+ if (evlist->mmap[i].base != NULL) {
+ munmap(evlist->mmap[i].base, evlist->mmap_len);
+ evlist->mmap[i].base = NULL;
}
}
+
+ free(evlist->mmap);
+ evlist->mmap = NULL;
}
int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
{
- evlist->mmap = zalloc(evlist->cpus->nr * sizeof(struct perf_mmap));
+ evlist->nr_mmaps = evlist->cpus->nr;
+ if (evlist->cpus->map[0] == -1)
+ evlist->nr_mmaps = evlist->threads->nr;
+ evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
return evlist->mmap != NULL ? 0 : -ENOMEM;
}
-static int __perf_evlist__mmap(struct perf_evlist *evlist, int cpu, int prot,
- int mask, int fd)
+static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *evsel,
+ int idx, int prot, int mask, int fd)
{
- evlist->mmap[cpu].prev = 0;
- evlist->mmap[cpu].mask = mask;
- evlist->mmap[cpu].base = mmap(NULL, evlist->mmap_len, prot,
+ evlist->mmap[idx].prev = 0;
+ evlist->mmap[idx].mask = mask;
+ evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
MAP_SHARED, fd, 0);
- if (evlist->mmap[cpu].base == MAP_FAILED)
+ if (evlist->mmap[idx].base == MAP_FAILED) {
+ if (evlist->cpus->map[idx] == -1 && evsel->attr.inherit)
+ ui__warning("Inherit is not allowed on per-task "
+ "events using mmap.\n");
return -1;
+ }
perf_evlist__add_pollfd(evlist, fd);
return 0;
}
+static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int mask)
+{
+ struct perf_evsel *evsel;
+ int cpu, thread;
+
+ for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+ int output = -1;
+
+ for (thread = 0; thread < evlist->threads->nr; thread++) {
+ list_for_each_entry(evsel, &evlist->entries, node) {
+ int fd = FD(evsel, cpu, thread);
+
+ if (output == -1) {
+ output = fd;
+ if (__perf_evlist__mmap(evlist, evsel, cpu,
+ prot, mask, output) < 0)
+ goto out_unmap;
+ } else {
+ if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
+ goto out_unmap;
+ }
+
+ if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+ perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
+ goto out_unmap;
+ }
+ }
+ }
+
+ return 0;
+
+out_unmap:
+ for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+ if (evlist->mmap[cpu].base != NULL) {
+ munmap(evlist->mmap[cpu].base, evlist->mmap_len);
+ evlist->mmap[cpu].base = NULL;
+ }
+ }
+ return -1;
+}
+
+static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, int mask)
+{
+ struct perf_evsel *evsel;
+ int thread;
+
+ for (thread = 0; thread < evlist->threads->nr; thread++) {
+ int output = -1;
+
+ list_for_each_entry(evsel, &evlist->entries, node) {
+ int fd = FD(evsel, 0, thread);
+
+ if (output == -1) {
+ output = fd;
+ if (__perf_evlist__mmap(evlist, evsel, thread,
+ prot, mask, output) < 0)
+ goto out_unmap;
+ } else {
+ if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
+ goto out_unmap;
+ }
+
+ if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+ perf_evlist__id_add_fd(evlist, evsel, 0, thread, fd) < 0)
+ goto out_unmap;
+ }
+ }
+
+ return 0;
+
+out_unmap:
+ for (thread = 0; thread < evlist->threads->nr; thread++) {
+ if (evlist->mmap[thread].base != NULL) {
+ munmap(evlist->mmap[thread].base, evlist->mmap_len);
+ evlist->mmap[thread].base = NULL;
+ }
+ }
+ return -1;
+}
+
/** perf_evlist__mmap - Create per cpu maps to receive events
*
* @evlist - list of events
@@ -282,11 +373,11 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int cpu, int prot,
int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
{
unsigned int page_size = sysconf(_SC_PAGE_SIZE);
- int mask = pages * page_size - 1, cpu;
- struct perf_evsel *first_evsel, *evsel;
+ int mask = pages * page_size - 1;
+ struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
const struct thread_map *threads = evlist->threads;
- int thread, prot = PROT_READ | (overwrite ? 0 : PROT_WRITE);
+ int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE);
if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
return -ENOMEM;
@@ -296,42 +387,18 @@ int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
evlist->overwrite = overwrite;
evlist->mmap_len = (pages + 1) * page_size;
- first_evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
list_for_each_entry(evsel, &evlist->entries, node) {
if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
evsel->sample_id == NULL &&
perf_evsel__alloc_id(evsel, cpus->nr, threads->nr) < 0)
return -ENOMEM;
-
- for (cpu = 0; cpu < cpus->nr; cpu++) {
- for (thread = 0; thread < threads->nr; thread++) {
- int fd = FD(evsel, cpu, thread);
-
- if (evsel->idx || thread) {
- if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT,
- FD(first_evsel, cpu, 0)) != 0)
- goto out_unmap;
- } else if (__perf_evlist__mmap(evlist, cpu, prot, mask, fd) < 0)
- goto out_unmap;
-
- if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
- perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
- goto out_unmap;
- }
- }
}
- return 0;
+ if (evlist->cpus->map[0] == -1)
+ return perf_evlist__mmap_per_thread(evlist, prot, mask);
-out_unmap:
- for (cpu = 0; cpu < cpus->nr; cpu++) {
- if (evlist->mmap[cpu].base != NULL) {
- munmap(evlist->mmap[cpu].base, evlist->mmap_len);
- evlist->mmap[cpu].base = NULL;
- }
- }
- return -1;
+ return perf_evlist__mmap_per_cpu(evlist, prot, mask);
}
int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
@@ -342,7 +409,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
if (evlist->threads == NULL)
return -1;
- if (target_tid != -1)
+ if (cpu_list == NULL && target_tid != -1)
evlist->cpus = cpu_map__dummy_new();
else
evlist->cpus = cpu_map__new(cpu_list);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 8b1cb7a4c5f1..7109d7add14e 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -17,6 +17,7 @@ struct perf_evlist {
struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
int nr_entries;
int nr_fds;
+ int nr_mmaps;
int mmap_len;
bool overwrite;
union perf_event event_copy;
@@ -46,7 +47,7 @@ void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
-union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *self, int cpu);
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
int perf_evlist__alloc_mmap(struct perf_evlist *evlist);
int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 662596afd7f1..d6fd59beb860 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -175,7 +175,7 @@ int __perf_evsel__read(struct perf_evsel *evsel,
}
static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
- struct thread_map *threads, bool group, bool inherit)
+ struct thread_map *threads, bool group)
{
int cpu, thread;
unsigned long flags = 0;
@@ -192,19 +192,6 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
for (cpu = 0; cpu < cpus->nr; cpu++) {
int group_fd = -1;
- /*
- * Don't allow mmap() of inherited per-task counters. This
- * would create a performance issue due to all children writing
- * to the same buffer.
- *
- * FIXME:
- * Proper fix is not to pass 'inherit' to perf_evsel__open*,
- * but a 'flags' parameter, with 'group' folded there as well,
- * then introduce a PERF_O_{MMAP,GROUP,INHERIT} enum, and if
- * O_MMAP is set, emit a warning if cpu < 0 and O_INHERIT is
- * set. Lets go for the minimal fix first tho.
- */
- evsel->attr.inherit = (cpus->map[cpu] >= 0) && inherit;
for (thread = 0; thread < threads->nr; thread++) {
@@ -253,7 +240,7 @@ static struct {
};
int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
- struct thread_map *threads, bool group, bool inherit)
+ struct thread_map *threads, bool group)
{
if (cpus == NULL) {
/* Work around old compiler warnings about strict aliasing */
@@ -263,19 +250,19 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
if (threads == NULL)
threads = &empty_thread_map.map;
- return __perf_evsel__open(evsel, cpus, threads, group, inherit);
+ return __perf_evsel__open(evsel, cpus, threads, group);
}
int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
- struct cpu_map *cpus, bool group, bool inherit)
+ struct cpu_map *cpus, bool group)
{
- return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group, inherit);
+ return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group);
}
int perf_evsel__open_per_thread(struct perf_evsel *evsel,
- struct thread_map *threads, bool group, bool inherit)
+ struct thread_map *threads, bool group)
{
- return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group, inherit);
+ return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group);
}
static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 6710ab538342..f79bb2c09a6c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -81,11 +81,11 @@ void perf_evsel__free_id(struct perf_evsel *evsel);
void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
- struct cpu_map *cpus, bool group, bool inherit);
+ struct cpu_map *cpus, bool group);
int perf_evsel__open_per_thread(struct perf_evsel *evsel,
- struct thread_map *threads, bool group, bool inherit);
+ struct thread_map *threads, bool group);
int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
- struct thread_map *threads, bool group, bool inherit);
+ struct thread_map *threads, bool group);
#define perf_evsel__match(evsel, t, c) \
(evsel->attr.type == PERF_TYPE_##t && \
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 5ddee66020a7..f0223166e761 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -234,7 +234,6 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
/* Searching trace events corresponding to probe event */
ntevs = find_probe_trace_events(fd, pev, tevs, max_tevs);
- close(fd);
if (ntevs > 0) { /* Succeeded to find trace events */
pr_debug("find %d probe_trace_events.\n", ntevs);
@@ -388,7 +387,6 @@ int show_line_range(struct line_range *lr, const char *module)
}
ret = find_line_range(fd, lr);
- close(fd);
if (ret == 0) {
pr_warning("Specified source line is not found.\n");
return -ENOENT;
@@ -512,19 +510,18 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
if (ret < 0)
return ret;
- fd = open_vmlinux(module);
- if (fd < 0) {
- pr_warning("Failed to open debug information file.\n");
- return fd;
- }
-
setup_pager();
- for (i = 0; i < npevs && ret >= 0; i++)
+ for (i = 0; i < npevs && ret >= 0; i++) {
+ fd = open_vmlinux(module);
+ if (fd < 0) {
+ pr_warning("Failed to open debug information file.\n");
+ ret = fd;
+ break;
+ }
ret = show_available_vars_at(fd, &pevs[i], max_vls, _filter,
externs);
-
- close(fd);
+ }
return ret;
}
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 194f9e2a3285..b7c85ce466a1 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -273,6 +273,25 @@ static const char *cu_get_comp_dir(Dwarf_Die *cu_die)
return dwarf_formstring(&attr);
}
+/* Get a line number and file name for given address */
+static int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
+ const char **fname, int *lineno)
+{
+ Dwarf_Line *line;
+ Dwarf_Addr laddr;
+
+ line = dwarf_getsrc_die(cudie, (Dwarf_Addr)addr);
+ if (line && dwarf_lineaddr(line, &laddr) == 0 &&
+ addr == (unsigned long)laddr && dwarf_lineno(line, lineno) == 0) {
+ *fname = dwarf_linesrc(line, NULL, NULL);
+ if (!*fname)
+ /* line number is useless without filename */
+ *lineno = 0;
+ }
+
+ return *lineno ?: -ENOENT;
+}
+
/* Compare diename and tname */
static bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
{
@@ -497,7 +516,20 @@ static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data)
static Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
Dwarf_Die *die_mem)
{
- return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem);
+ Dwarf_Die tmp_die;
+
+ sp_die = die_find_child(sp_die, __die_find_inline_cb, &addr, &tmp_die);
+ if (!sp_die)
+ return NULL;
+
+ /* Inlined function could be recursive. Trace it until fail */
+ while (sp_die) {
+ memcpy(die_mem, sp_die, sizeof(Dwarf_Die));
+ sp_die = die_find_child(sp_die, __die_find_inline_cb, &addr,
+ &tmp_die);
+ }
+
+ return die_mem;
}
/* Walker on lines (Note: line number will not be sorted) */
@@ -1395,6 +1427,10 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
!die_compare_name(sp_die, pp->function))
return DWARF_CB_OK;
+ /* Check declared file */
+ if (pp->file && strtailcmp(pp->file, dwarf_decl_file(sp_die)))
+ return DWARF_CB_OK;
+
pf->fname = dwarf_decl_file(sp_die);
if (pp->line) { /* Function relative line */
dwarf_decl_line(sp_die, &pf->lno);
@@ -1451,6 +1487,7 @@ static int find_probes(int fd, struct probe_finder *pf)
if (!dbg) {
pr_warning("No debug information found in the vmlinux - "
"please rebuild with CONFIG_DEBUG_INFO=y.\n");
+ close(fd); /* Without dwfl_end(), fd isn't closed. */
return -EBADF;
}
@@ -1686,11 +1723,9 @@ int find_perf_probe_point(unsigned long addr, struct perf_probe_point *ppt)
Dwarf_Die cudie, spdie, indie;
Dwarf *dbg = NULL;
Dwfl *dwfl = NULL;
- Dwarf_Line *line;
- Dwarf_Addr laddr, eaddr, bias = 0;
- const char *tmp;
- int lineno, ret = 0;
- bool found = false;
+ Dwarf_Addr _addr, baseaddr, bias = 0;
+ const char *fname = NULL, *func = NULL, *tmp;
+ int baseline = 0, lineno = 0, ret = 0;
/* Open the live linux kernel */
dbg = dwfl_init_live_kernel_dwarf(addr, &dwfl, &bias);
@@ -1711,68 +1746,79 @@ int find_perf_probe_point(unsigned long addr, struct perf_probe_point *ppt)
goto end;
}
- /* Find a corresponding line */
- line = dwarf_getsrc_die(&cudie, (Dwarf_Addr)addr);
- if (line) {
- if (dwarf_lineaddr(line, &laddr) == 0 &&
- (Dwarf_Addr)addr == laddr &&
- dwarf_lineno(line, &lineno) == 0) {
- tmp = dwarf_linesrc(line, NULL, NULL);
- if (tmp) {
- ppt->line = lineno;
- ppt->file = strdup(tmp);
- if (ppt->file == NULL) {
- ret = -ENOMEM;
- goto end;
- }
- found = true;
- }
- }
- }
+ /* Find a corresponding line (filename and lineno) */
+ cu_find_lineinfo(&cudie, addr, &fname, &lineno);
+ /* Don't care whether it failed or not */
- /* Find a corresponding function */
+ /* Find a corresponding function (name, baseline and baseaddr) */
if (die_find_real_subprogram(&cudie, (Dwarf_Addr)addr, &spdie)) {
+ /* Get function entry information */
tmp = dwarf_diename(&spdie);
- if (!tmp || dwarf_entrypc(&spdie, &eaddr) != 0)
- goto end;
-
- if (ppt->line) {
- if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
- &indie)) {
- /* addr in an inline function */
+ if (!tmp ||
+ dwarf_entrypc(&spdie, &baseaddr) != 0 ||
+ dwarf_decl_line(&spdie, &baseline) != 0)
+ goto post;
+ func = tmp;
+
+ if (addr == (unsigned long)baseaddr)
+ /* Function entry - Relative line number is 0 */
+ lineno = baseline;
+ else if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
+ &indie)) {
+ if (dwarf_entrypc(&indie, &_addr) == 0 &&
+ _addr == addr)
+ /*
+ * addr is at an inline function entry.
+ * In this case, lineno should be the call-site
+ * line number.
+ */
+ lineno = die_get_call_lineno(&indie);
+ else {
+ /*
+ * addr is in an inline function body.
+ * Since lineno points one of the lines
+ * of the inline function, baseline should
+ * be the entry line of the inline function.
+ */
tmp = dwarf_diename(&indie);
- if (!tmp)
- goto end;
- ret = dwarf_decl_line(&indie, &lineno);
- } else {
- if (eaddr == addr) { /* Function entry */
- lineno = ppt->line;
- ret = 0;
- } else
- ret = dwarf_decl_line(&spdie, &lineno);
- }
- if (ret == 0) {
- /* Make a relative line number */
- ppt->line -= lineno;
- goto found;
+ if (tmp &&
+ dwarf_decl_line(&spdie, &baseline) == 0)
+ func = tmp;
}
}
- /* We don't have a line number, let's use offset */
- ppt->offset = addr - (unsigned long)eaddr;
-found:
- ppt->function = strdup(tmp);
+ }
+
+post:
+ /* Make a relative line number or an offset */
+ if (lineno)
+ ppt->line = lineno - baseline;
+ else if (func)
+ ppt->offset = addr - (unsigned long)baseaddr;
+
+ /* Duplicate strings */
+ if (func) {
+ ppt->function = strdup(func);
if (ppt->function == NULL) {
ret = -ENOMEM;
goto end;
}
- found = true;
}
-
+ if (fname) {
+ ppt->file = strdup(fname);
+ if (ppt->file == NULL) {
+ if (ppt->function) {
+ free(ppt->function);
+ ppt->function = NULL;
+ }
+ ret = -ENOMEM;
+ goto end;
+ }
+ }
end:
if (dwfl)
dwfl_end(dwfl);
- if (ret >= 0)
- ret = found ? 1 : 0;
+ if (ret == 0 && (fname || func))
+ ret = 1; /* Found a point */
return ret;
}
@@ -1840,6 +1886,10 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
struct line_finder *lf = param->data;
struct line_range *lr = lf->lr;
+ /* Check declared file */
+ if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die)))
+ return DWARF_CB_OK;
+
if (dwarf_tag(sp_die) == DW_TAG_subprogram &&
die_compare_name(sp_die, lr->function)) {
lf->fname = dwarf_decl_file(sp_die);
@@ -1892,6 +1942,7 @@ int find_line_range(int fd, struct line_range *lr)
if (!dbg) {
pr_warning("No debug information found in the vmlinux - "
"please rebuild with CONFIG_DEBUG_INFO=y.\n");
+ close(fd); /* Without dwfl_end(), fd isn't closed. */
return -EBADF;
}
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index a9f2d7e1204d..99c722672f84 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -498,11 +498,11 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
struct cpu_map *cpus = NULL;
struct thread_map *threads = NULL;
PyObject *pcpus = NULL, *pthreads = NULL;
- int group = 0, overwrite = 0;
- static char *kwlist[] = {"cpus", "threads", "group", "overwrite", NULL, NULL};
+ int group = 0, inherit = 0;
+ static char *kwlist[] = {"cpus", "threads", "group", "inherit", NULL, NULL};
if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist,
- &pcpus, &pthreads, &group, &overwrite))
+ &pcpus, &pthreads, &group, &inherit))
return NULL;
if (pthreads != NULL)
@@ -511,7 +511,8 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
if (pcpus != NULL)
cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
- if (perf_evsel__open(evsel, cpus, threads, group, overwrite) < 0) {
+ evsel->attr.inherit = inherit;
+ if (perf_evsel__open(evsel, cpus, threads, group) < 0) {
PyErr_SetFromErrno(PyExc_OSError);
return NULL;
}
@@ -679,7 +680,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
&cpu, &sample_id_all))
return NULL;
- event = perf_evlist__read_on_cpu(evlist, cpu);
+ event = perf_evlist__mmap_read(evlist, cpu);
if (event != NULL) {
struct perf_evsel *first;
PyObject *pyevent = pyrf_event__new(event);
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index e24ffadb20b2..bbc982f5dd8b 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -1,13 +1,18 @@
#!/usr/bin/python2
from distutils.core import setup, Extension
+from os import getenv
+
+cflags = ['-fno-strict-aliasing', '-Wno-write-strings']
+cflags += getenv('CFLAGS', '').split()
perf = Extension('perf',
sources = ['util/python.c', 'util/ctype.c', 'util/evlist.c',
'util/evsel.c', 'util/cpumap.c', 'util/thread_map.c',
'util/util.c', 'util/xyarray.c', 'util/cgroup.c'],
include_dirs = ['util/include'],
- extra_compile_args = ['-fno-strict-aliasing', '-Wno-write-strings'])
+ extra_compile_args = cflags,
+ )
setup(name='perf',
version='0.1',
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 8fc0bd3a3a4a..b9a985dadd08 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -85,7 +85,7 @@ out:
/*
* Helper function for splitting a string into an argv-like array.
- * originaly copied from lib/argv_split.c
+ * originally copied from lib/argv_split.c
*/
static const char *skip_sep(const char *cp)
{
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 17df793c8924..f06c10f092ba 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1196,6 +1196,8 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
if (curr_dso == NULL)
goto out_elf_end;
curr_dso->kernel = self->kernel;
+ curr_dso->long_name = self->long_name;
+ curr_dso->long_name_len = self->long_name_len;
curr_map = map__new2(start, curr_dso,
map->type);
if (curr_map == NULL) {
@@ -1842,6 +1844,7 @@ int dso__load_vmlinux(struct dso *self, struct map *map,
if (fd < 0)
return -1;
+ dso__set_long_name(self, (char *)vmlinux);
dso__set_loaded(self, map->type);
err = dso__load_sym(self, map, symfs_vmlinux, fd, filter, 0, 0);
close(fd);
@@ -2403,6 +2406,8 @@ int symbol__init(void)
if (symbol_conf.initialized)
return 0;
+ symbol_conf.priv_size = ALIGN(symbol_conf.priv_size, sizeof(u64));
+
elf_version(EV_CURRENT);
if (symbol_conf.sort_by_name)
symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) -
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c
index 8c17a8730e4a..15633d608133 100644
--- a/tools/perf/util/ui/browsers/annotate.c
+++ b/tools/perf/util/ui/browsers/annotate.c
@@ -256,10 +256,9 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
int refresh)
{
struct objdump_line *pos, *n;
- struct annotation *notes = symbol__annotation(sym);
+ struct annotation *notes;
struct annotate_browser browser = {
.b = {
- .entries = &notes->src->source,
.refresh = ui_browser__list_head_refresh,
.seek = ui_browser__list_head_seek,
.write = annotate_browser__write,
@@ -281,6 +280,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
ui_helpline__push("Press <- or ESC to exit");
+ notes = symbol__annotation(sym);
+
list_for_each_entry(pos, &notes->src->source, node) {
struct objdump_line_rb_node *rbpos;
size_t line_len = strlen(pos->line);
@@ -291,6 +292,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
rbpos->idx = browser.b.nr_entries++;
}
+ browser.b.entries = &notes->src->source,
browser.b.width += 18; /* Percentage */
ret = annotate_browser__run(&browser, evidx, refresh);
list_for_each_entry_safe(pos, n, &notes->src->source, node) {
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index 798efdca3ead..5d767c622dfc 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -851,7 +851,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel,
goto out_free_stack;
case 'a':
if (browser->selection == NULL ||
- browser->selection->map == NULL ||
+ browser->selection->sym == NULL ||
browser->selection->map->dso->annotate_warned)
continue;
goto do_annotate;