#define TP_UINT_FIELD(bits) \
static u64 tp_field__u##bits(struct tp_field *field, struct perf_sample *sample) \
{ \
- return *(u##bits *)(sample->raw_data + field->offset); \
+ u##bits value; \
+ memcpy(&value, sample->raw_data + field->offset, sizeof(value)); \
+ return value; \
}
TP_UINT_FIELD(8);
#define TP_UINT_FIELD__SWAPPED(bits) \
static u64 tp_field__swapped_u##bits(struct tp_field *field, struct perf_sample *sample) \
{ \
- u##bits value = *(u##bits *)(sample->raw_data + field->offset); \
+ u##bits value; \
+ memcpy(&value, sample->raw_data + field->offset, sizeof(value)); \
return bswap_##bits(value);\
}
struct syscall {
struct event_format *tp_format;
+ int nr_args;
+ struct format_field *args;
const char *name;
bool filtered;
bool is_exit;
const char *last_vfs_getname;
struct intlist *tid_list;
struct intlist *pid_list;
+ struct {
+ size_t nr;
+ pid_t *entries;
+ } filter_pids;
double duration_filter;
double runtime_ms;
struct {
bool show_comm;
bool show_tool_stats;
bool trace_syscalls;
+ bool force;
int trace_pgfaults;
};
struct format_field *field;
int idx = 0;
- sc->arg_scnprintf = calloc(sc->tp_format->format.nr_fields - 1, sizeof(void *));
+ sc->arg_scnprintf = calloc(sc->nr_args, sizeof(void *));
if (sc->arg_scnprintf == NULL)
return -1;
if (sc->fmt)
sc->arg_parm = sc->fmt->arg_parm;
- for (field = sc->tp_format->format.fields->next; field; field = field->next) {
+ for (field = sc->args; field; field = field->next) {
if (sc->fmt && sc->fmt->arg_scnprintf[idx])
sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
else if (field->flags & FIELD_IS_POINTER)
if (sc->tp_format == NULL)
return -1;
+ sc->args = sc->tp_format->format.fields;
+ sc->nr_args = sc->tp_format->format.nr_fields;
+ /* drop nr field - not relevant here; does not exist on older kernels */
+ if (sc->args && strcmp(sc->args->name, "nr") == 0) {
+ sc->args = sc->args->next;
+ --sc->nr_args;
+ }
+
sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit");
return syscall__set_arg_fmts(sc);
}
+/*
+ * args is to be interpreted as a series of longs but we need to handle
+ * 8-byte unaligned accesses. args points to raw_data within the event
+ * and raw_data is guaranteed to be 8-byte unaligned because it is
+ * preceded by raw_size which is a u32. So we need to copy args to a temp
+ * variable to read it. Most notably this avoids extended load instructions
+ * on unaligned addresses
+ */
+
static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
- unsigned long *args, struct trace *trace,
+ unsigned char *args, struct trace *trace,
struct thread *thread)
{
size_t printed = 0;
+ unsigned char *p;
+ unsigned long val;
- if (sc->tp_format != NULL) {
+ if (sc->args != NULL) {
struct format_field *field;
u8 bit = 1;
struct syscall_arg arg = {
.thread = thread,
};
- for (field = sc->tp_format->format.fields->next; field;
+ for (field = sc->args; field;
field = field->next, ++arg.idx, bit <<= 1) {
if (arg.mask & bit)
continue;
+
+ /* special care for unaligned accesses */
+ p = args + sizeof(unsigned long) * arg.idx;
+ memcpy(&val, p, sizeof(val));
+
/*
* Suppress this argument if its value is zero and
* and we don't have a string associated in an
* strarray for it.
*/
- if (args[arg.idx] == 0 &&
+ if (val == 0 &&
!(sc->arg_scnprintf &&
sc->arg_scnprintf[arg.idx] == SCA_STRARRAY &&
sc->arg_parm[arg.idx]))
printed += scnprintf(bf + printed, size - printed,
"%s%s: ", printed ? ", " : "", field->name);
if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) {
- arg.val = args[arg.idx];
+ arg.val = val;
if (sc->arg_parm)
arg.parm = sc->arg_parm[arg.idx];
printed += sc->arg_scnprintf[arg.idx](bf + printed,
size - printed, &arg);
} else {
printed += scnprintf(bf + printed, size - printed,
- "%ld", args[arg.idx]);
+ "%ld", val);
}
}
} else {
int i = 0;
while (i < 6) {
+ /* special care for unaligned accesses */
+ p = args + sizeof(unsigned long) * i;
+ memcpy(&val, p, sizeof(val));
printed += scnprintf(bf + printed, size - printed,
"%sarg%d: %ld",
- printed ? ", " : "", i, args[i]);
+ printed ? ", " : "", i, val);
++i;
}
}
return -1;
}
- printed += trace__printf_interrupted_entry(trace, sample);
+ if (!trace->summary_only)
+ trace__printf_interrupted_entry(trace, sample);
ttrace->entry_time = sample->time;
msg = ttrace->entry_str;
} else
ttrace->entry_pending = true;
- trace->current = thread;
+ if (trace->current != thread) {
+ thread__put(trace->current);
+ trace->current = thread__get(thread);
+ }
return 0;
}
return 0;
}
+static void trace__handle_event(struct trace *trace, union perf_event *event, struct perf_sample *sample)
+{
+ const u32 type = event->header.type;
+ struct perf_evsel *evsel;
+
+ if (!trace->full_time && trace->base_time == 0)
+ trace->base_time = sample->time;
+
+ if (type != PERF_RECORD_SAMPLE) {
+ trace__process_event(trace, trace->host, event, sample);
+ return;
+ }
+
+ evsel = perf_evlist__id2evsel(trace->evlist, sample->id);
+ if (evsel == NULL) {
+ fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample->id);
+ return;
+ }
+
+ if (evsel->attr.type == PERF_TYPE_TRACEPOINT &&
+ sample->raw_data == NULL) {
+ fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
+ perf_evsel__name(evsel), sample->tid,
+ sample->cpu, sample->raw_size);
+ } else {
+ tracepoint_handler handler = evsel->handler;
+ handler(trace, evsel, event, sample);
+ }
+}
+
static int trace__run(struct trace *trace, int argc, const char **argv)
{
struct perf_evlist *evlist = trace->evlist;
- struct perf_evsel *evsel;
int err = -1, i;
unsigned long before;
const bool forks = argc > 0;
* workload was, and in that case we will fill in the thread_map when
* we fork the workload in perf_evlist__prepare_workload.
*/
- if (evlist->threads->map[0] == -1)
- perf_evlist__set_filter_pid(evlist, getpid());
+ if (trace->filter_pids.nr > 0)
+ err = perf_evlist__set_filter_pids(evlist, trace->filter_pids.nr, trace->filter_pids.entries);
+ else if (evlist->threads->map[0] == -1)
+ err = perf_evlist__set_filter_pid(evlist, getpid());
+
+ if (err < 0) {
+ printf("err=%d,%s\n", -err, strerror(-err));
+ exit(1);
+ }
err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
if (err < 0)
goto out_error_mmap;
+ if (!target__none(&trace->opts.target))
+ perf_evlist__enable(evlist);
+
if (forks)
perf_evlist__start_workload(evlist);
- else
- perf_evlist__enable(evlist);
trace->multiple_threads = evlist->threads->map[0] == -1 ||
evlist->threads->nr > 1 ||
union perf_event *event;
while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
- const u32 type = event->header.type;
- tracepoint_handler handler;
struct perf_sample sample;
++trace->nr_events;
goto next_event;
}
- if (!trace->full_time && trace->base_time == 0)
- trace->base_time = sample.time;
-
- if (type != PERF_RECORD_SAMPLE) {
- trace__process_event(trace, trace->host, event, &sample);
- continue;
- }
-
- evsel = perf_evlist__id2evsel(evlist, sample.id);
- if (evsel == NULL) {
- fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id);
- goto next_event;
- }
-
- if (evsel->attr.type == PERF_TYPE_TRACEPOINT &&
- sample.raw_data == NULL) {
- fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
- perf_evsel__name(evsel), sample.tid,
- sample.cpu, sample.raw_size);
- goto next_event;
- }
-
- handler = evsel->handler;
- handler(trace, evsel, event, &sample);
+ trace__handle_event(trace, event, &sample);
next_event:
perf_evlist__mmap_consume(evlist, i);
if (interrupted)
goto out_disable;
+
+ if (done && !draining) {
+ perf_evlist__disable(evlist);
+ draining = true;
+ }
}
}
}
out_disable:
+ thread__zput(trace->current);
+
perf_evlist__disable(evlist);
if (!err) {
struct perf_data_file file = {
.path = input_name,
.mode = PERF_DATA_MODE_READ,
+ .force = trace->force,
};
struct perf_session *session;
struct perf_evsel *evsel;
setup_pager();
- err = perf_session__process_events(session, &trace->tool);
+ err = perf_session__process_events(session);
if (err)
pr_err("Failed to process events, error %d", err);
return 0;
}
+static int trace__set_filter_pids(const struct option *opt, const char *str,
+ int unset __maybe_unused)
+{
+ int ret = -1;
+ size_t i;
+ struct trace *trace = opt->value;
+ /*
+ * FIXME: introduce a intarray class, plain parse csv and create a
+ * { int nr, int entries[] } struct...
+ */
+ struct intlist *list = intlist__new(str);
+
+ if (list == NULL)
+ return -1;
+
+ i = trace->filter_pids.nr = intlist__nr_entries(list) + 1;
+ trace->filter_pids.entries = calloc(i, sizeof(pid_t));
+
+ if (trace->filter_pids.entries == NULL)
+ goto out;
+
+ trace->filter_pids.entries[0] = getpid();
+
+ for (i = 1; i < trace->filter_pids.nr; ++i)
+ trace->filter_pids.entries[i] = intlist__entry(list, i - 1)->i;
+
+ intlist__delete(list);
+ ret = 0;
+out:
+ return ret;
+}
+
static int trace__open_output(struct trace *trace, const char *filename)
{
struct stat st;
int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
{
- const char * const trace_usage[] = {
+ const char *trace_usage[] = {
"perf trace [<options>] [<command>]",
"perf trace [<options>] -- <command> [<options>]",
"perf trace record [<options>] [<command>]",
"trace events on existing process id"),
OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
"trace events on existing thread id"),
+ OPT_CALLBACK(0, "filter-pids", &trace, "float",
+ "show only events with duration > N.M ms", trace__set_filter_pids),
OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
"system-wide collection from all CPUs"),
OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
OPT_CALLBACK_DEFAULT('F', "pf", &trace.trace_pgfaults, "all|maj|min",
"Trace pagefaults", parse_pagefaults, "maj"),
OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"),
+ OPT_BOOLEAN('f', "force", &trace.force, "don't complain, do it"),
OPT_END()
};
+ const char * const trace_subcommands[] = { "record", NULL };
int err;
char bf[BUFSIZ];
+ signal(SIGSEGV, sighandler_dump_stack);
+ signal(SIGFPE, sighandler_dump_stack);
+
trace.evlist = perf_evlist__new();
if (trace.evlist == NULL)
return -ENOMEM;
goto out;
}
- argc = parse_options(argc, argv, trace_options, trace_usage,
- PARSE_OPT_STOP_AT_NON_OPTION);
+ argc = parse_options_subcommand(argc, argv, trace_options, trace_subcommands,
+ trace_usage, PARSE_OPT_STOP_AT_NON_OPTION);
if (trace.trace_pgfaults) {
trace.opts.sample_address = true;
projects / firefly-linux-kernel-4.4.55.git / blobdiff