struct syscall *table;
struct {
struct perf_evsel *sys_enter,
- *sys_exit;
+ *sys_exit,
+ *augmented;
} events;
} syscalls;
struct record_opts opts;
bool force;
bool vfs_getname;
int trace_pgfaults;
- int open_id;
};
struct tp_field {
TP_UINT_FIELD__SWAPPED(32);
TP_UINT_FIELD__SWAPPED(64);
-static int tp_field__init_uint(struct tp_field *field,
- struct format_field *format_field,
- bool needs_swap)
+static int __tp_field__init_uint(struct tp_field *field, int size, int offset, bool needs_swap)
{
- field->offset = format_field->offset;
+ field->offset = offset;
- switch (format_field->size) {
+ switch (size) {
case 1:
field->integer = tp_field__u8;
break;
return 0;
}
+static int tp_field__init_uint(struct tp_field *field, struct format_field *format_field, bool needs_swap)
+{
+ return __tp_field__init_uint(field, format_field->size, format_field->offset, needs_swap);
+}
+
static void *tp_field__ptr(struct tp_field *field, struct perf_sample *sample)
{
return sample->raw_data + field->offset;
}
-static int tp_field__init_ptr(struct tp_field *field, struct format_field *format_field)
+static int __tp_field__init_ptr(struct tp_field *field, int offset)
{
- field->offset = format_field->offset;
+ field->offset = offset;
field->pointer = tp_field__ptr;
return 0;
}
+static int tp_field__init_ptr(struct tp_field *field, struct format_field *format_field)
+{
+ return __tp_field__init_ptr(field, format_field->offset);
+}
+
struct syscall_tp {
struct tp_field id;
union {
perf_evsel__delete(evsel);
}
-static int perf_evsel__init_syscall_tp(struct perf_evsel *evsel, void *handler)
+static int perf_evsel__init_syscall_tp(struct perf_evsel *evsel)
+{
+ struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp));
+
+ if (evsel->priv != NULL) {
+ if (perf_evsel__init_tp_uint_field(evsel, &sc->id, "__syscall_nr"))
+ goto out_delete;
+ return 0;
+ }
+
+ return -ENOMEM;
+out_delete:
+ zfree(&evsel->priv);
+ return -ENOENT;
+}
+
+static int perf_evsel__init_augmented_syscall_tp(struct perf_evsel *evsel)
+{
+ struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp));
+
+ if (evsel->priv != NULL) { /* field, sizeof_field, offsetof_field */
+ if (__tp_field__init_uint(&sc->id, sizeof(long), sizeof(long long), evsel->needs_swap))
+ goto out_delete;
+
+ return 0;
+ }
+
+ return -ENOMEM;
+out_delete:
+ zfree(&evsel->priv);
+ return -EINVAL;
+}
+
+static int perf_evsel__init_augmented_syscall_tp_args(struct perf_evsel *evsel)
+{
+ struct syscall_tp *sc = evsel->priv;
+
+ return __tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64));
+}
+
+static int perf_evsel__init_raw_syscall_tp(struct perf_evsel *evsel, void *handler)
{
evsel->priv = malloc(sizeof(struct syscall_tp));
if (evsel->priv != NULL) {
return -ENOENT;
}
-static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction, void *handler)
+static struct perf_evsel *perf_evsel__raw_syscall_newtp(const char *direction, void *handler)
{
struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction);
if (IS_ERR(evsel))
return NULL;
- if (perf_evsel__init_syscall_tp(evsel, handler))
+ if (perf_evsel__init_raw_syscall_tp(evsel, handler))
goto out_delete;
return evsel;
{
int idx = val - sa->offset;
- if (idx < 0 || idx >= sa->nr_entries)
+ if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL)
return scnprintf(bf, size, intfmt, val);
return scnprintf(bf, size, "%s", sa->entries[idx]);
.arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
{ .name = "socket",
.arg = { [0] = STRARRAY(family, socket_families),
- [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+ [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+ [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
{ .name = "socketpair",
.arg = { [0] = STRARRAY(family, socket_families),
- [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+ [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+ [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
{ .name = "stat", .alias = "newstat", },
{ .name = "statx",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* fdat */ },
return bsearch(name, syscall_fmts, nmemb, sizeof(struct syscall_fmt), syscall_fmt__cmp);
}
+/*
+ * is_exit: is this "exit" or "exit_group"?
+ * is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter.
+ */
struct syscall {
struct event_format *tp_format;
int nr_args;
+ bool is_exit;
+ bool is_open;
struct format_field *args;
const char *name;
- bool is_exit;
struct syscall_fmt *fmt;
struct syscall_arg_fmt *arg_fmt;
};
}
sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit");
+ sc->is_open = !strcmp(name, "open") || !strcmp(name, "openat");
return syscall__set_arg_fmts(sc);
}
return err;
}
+static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ struct thread_trace *ttrace;
+ struct thread *thread;
+ int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
+ struct syscall *sc = trace__syscall_info(trace, evsel, id);
+ char msg[1024];
+ void *args;
+
+ if (sc == NULL)
+ return -1;
+
+ thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+ ttrace = thread__trace(thread, trace->output);
+ /*
+ * We need to get ttrace just to make sure it is there when syscall__scnprintf_args()
+ * and the rest of the beautifiers accessing it via struct syscall_arg touches it.
+ */
+ if (ttrace == NULL)
+ goto out_put;
+
+ args = perf_evsel__sc_tp_ptr(evsel, args, sample);
+ syscall__scnprintf_args(sc, msg, sizeof(msg), args, trace, thread);
+ fprintf(trace->output, "%s", msg);
+ err = 0;
+out_put:
+ thread__put(thread);
+ return err;
+}
+
static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evsel,
struct perf_sample *sample,
struct callchain_cursor *cursor)
ret = perf_evsel__sc_tp_uint(evsel, ret, sample);
- if (id == trace->open_id && ret >= 0 && ttrace->filename.pending_open) {
+ if (sc->is_open && ret >= 0 && ttrace->filename.pending_open) {
trace__set_fd_pathname(thread, ret, ttrace->filename.name);
ttrace->filename.pending_open = false;
++trace->stats.vfs_getname;
fprintf(trace->output, "%s:", evsel->name);
if (perf_evsel__is_bpf_output(evsel)) {
- bpf_output__fprintf(trace, sample);
+ if (evsel == trace->syscalls.events.augmented)
+ trace__fprintf_sys_enter(trace, evsel, sample);
+ else
+ bpf_output__fprintf(trace, sample);
} else if (evsel->tp_format) {
- event_format__fprintf(evsel->tp_format, sample->cpu,
- sample->raw_data, sample->raw_size,
- trace->output);
+ if (strncmp(evsel->tp_format->name, "sys_enter_", 10) ||
+ trace__fprintf_sys_enter(trace, evsel, sample)) {
+ event_format__fprintf(evsel->tp_format, sample->cpu,
+ sample->raw_data, sample->raw_size,
+ trace->output);
+ }
}
fprintf(trace->output, "\n");
struct perf_evlist *evlist = trace->evlist;
struct perf_evsel *sys_enter, *sys_exit;
- sys_enter = perf_evsel__syscall_newtp("sys_enter", trace__sys_enter);
+ sys_enter = perf_evsel__raw_syscall_newtp("sys_enter", trace__sys_enter);
if (sys_enter == NULL)
goto out;
if (perf_evsel__init_sc_tp_ptr_field(sys_enter, args))
goto out_delete_sys_enter;
- sys_exit = perf_evsel__syscall_newtp("sys_exit", trace__sys_exit);
+ sys_exit = perf_evsel__raw_syscall_newtp("sys_exit", trace__sys_exit);
if (sys_exit == NULL)
goto out_delete_sys_enter;
"syscalls:sys_enter");
if (evsel &&
- (perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 ||
+ (perf_evsel__init_raw_syscall_tp(evsel, trace__sys_enter) < 0 ||
perf_evsel__init_sc_tp_ptr_field(evsel, args))) {
pr_err("Error during initialize raw_syscalls:sys_enter event\n");
goto out;
evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
"syscalls:sys_exit");
if (evsel &&
- (perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 ||
+ (perf_evsel__init_raw_syscall_tp(evsel, trace__sys_exit) < 0 ||
perf_evsel__init_sc_tp_uint_field(evsel, ret))) {
pr_err("Error during initialize raw_syscalls:sys_exit event\n");
goto out;
evsel->handler = handler;
}
+static int evlist__set_syscall_tp_fields(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel;
+
+ evlist__for_each_entry(evlist, evsel) {
+ if (evsel->priv || !evsel->tp_format)
+ continue;
+
+ if (strcmp(evsel->tp_format->system, "syscalls"))
+ continue;
+
+ if (perf_evsel__init_syscall_tp(evsel))
+ return -1;
+
+ if (!strncmp(evsel->tp_format->name, "sys_enter_", 10)) {
+ struct syscall_tp *sc = evsel->priv;
+
+ if (__tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64)))
+ return -1;
+ } else if (!strncmp(evsel->tp_format->name, "sys_exit_", 9)) {
+ struct syscall_tp *sc = evsel->priv;
+
+ if (__tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap))
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
/*
* XXX: Hackish, just splitting the combined -e+--event (syscalls
* (raw_syscalls:{sys_{enter,exit}} + events (tracepoints, HW, SW, etc) to use
if (trace__validate_ev_qualifier(trace))
goto out;
+ trace->trace_syscalls = true;
}
err = 0;
},
.output = stderr,
.show_comm = true,
- .trace_syscalls = true,
+ .trace_syscalls = false,
.kernel_syscallchains = false,
.max_stack = UINT_MAX,
};
};
bool __maybe_unused max_stack_user_set = true;
bool mmap_pages_user_set = true;
+ struct perf_evsel *evsel;
const char * const trace_subcommands[] = { "record", NULL };
- int err;
+ int err = -1;
char bf[BUFSIZ];
signal(SIGSEGV, sighandler_dump_stack);
"cgroup monitoring only available in system-wide mode");
}
+ evsel = bpf__setup_output_event(trace.evlist, "__augmented_syscalls__");
+ if (IS_ERR(evsel)) {
+ bpf__strerror_setup_output_event(trace.evlist, PTR_ERR(evsel), bf, sizeof(bf));
+ pr_err("ERROR: Setup trace syscalls enter failed: %s\n", bf);
+ goto out;
+ }
+
+ if (evsel) {
+ if (perf_evsel__init_augmented_syscall_tp(evsel) ||
+ perf_evsel__init_augmented_syscall_tp_args(evsel))
+ goto out;
+ trace.syscalls.events.augmented = evsel;
+ }
+
err = bpf__setup_stdout(trace.evlist);
if (err) {
bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf));
symbol_conf.use_callchain = true;
}
- if (trace.evlist->nr_entries > 0)
+ if (trace.evlist->nr_entries > 0) {
evlist__set_evsel_handler(trace.evlist, trace__event_handler);
+ if (evlist__set_syscall_tp_fields(trace.evlist)) {
+ perror("failed to set syscalls:* tracepoint fields");
+ goto out;
+ }
+ }
if ((argc >= 1) && (strcmp(argv[0], "record") == 0))
return trace__record(&trace, argc-1, &argv[1]);
if (!trace.trace_syscalls && !trace.trace_pgfaults &&
trace.evlist->nr_entries == 0 /* Was --events used? */) {
- pr_err("Please specify something to trace.\n");
- return -1;
- }
-
- if (!trace.trace_syscalls && trace.ev_qualifier) {
- pr_err("The -e option can't be used with --no-syscalls.\n");
- goto out;
+ trace.trace_syscalls = true;
}
if (output_name != NULL) {
}
}
- trace.open_id = syscalltbl__id(trace.sctbl, "open");
-
err = target__validate(&trace.opts.target);
if (err) {
target__strerror(&trace.opts.target, err, bf, sizeof(bf));
projects / linux.git / blobdiff