perf trace: Use event filters for the event qualifier list

We use raw_syscalls:sys_{enter,exit} events to show the syscalls, but were
using a rather lazy/inneficient way to implement our 'strace -e' equivalent:
filter out after reading the events in the ring buffer.

Deflect more work to the kernel by appending a filter expression for that,
that, together with the pid list, that is always present, if only to filter the
tracer itself, reduces pressure on the ring buffer and otherwise use
infrastructure already in place in the kernel to do early filtering.

If we use it with -v we can see the filter passed to the kernel,
for instance, for this contrieved case:

  # trace -v -e \!open,close,write,poll,recvfrom,select,recvmsg,writev,sendmsg,read,futex,epoll_wait,ioctl,eventfd --filter-pids 2189,2566,1398,2692,4475,4532
<SNIP>
  (common_pid != 2514 && common_pid != 1398 && common_pid != 2189 && common_pid != 2566 && common_pid != 2692 && common_pid != 4475 && common_pid != 4532) && (id != 3 && id != 232 && id != 284 && id != 202 && id != 16 && id != 2 && id != 7 && id != 0 && id != 45 && id != 47 && id != 23 && id != 46 && id != 1 && id != 20)
     0.011 (0.011 ms): caribou/2295 eventfd2(flags: CLOEXEC|NONBLOCK) = 18
    16.946 (0.019 ms): caribou/2295 eventfd2(flags: CLOEXEC|NONBLOCK) = 18
    38.598 (0.167 ms): chronyd/794 socket(family: INET, type: DGRAM ) = 4
    38.603 (0.002 ms): chronyd/794 fcntl(fd: 4<socket:[239307]>, cmd: GETFD) = 0
    38.605 (0.001 ms): chronyd/794 fcntl(fd: 4<socket:[239307]>, cmd: SETFD, arg: 1) = 0
^C
 #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ti2tg18atproqpguc2moinp6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index c02b65a72410b9d140412b40d5350f3699031b9d..0ebf55bf20b356e46b92fb6478a4bac38fad2329 100644 (file)
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1187,7 +1187,6 @@ struct syscall {
        int                 nr_args;
        struct format_field *args;
        const char          *name;
-       bool                filtered;
        bool                is_exit;
        struct syscall_fmt  *fmt;
        size_t              (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
@@ -1550,19 +1549,6 @@ static int trace__read_syscall_info(struct trace *trace, int id)
        sc = trace->syscalls.table + id;
        sc->name = name;
 
-       if (trace->ev_qualifier) {
-               bool in = strlist__find(trace->ev_qualifier, name) != NULL;
-
-               if (!(in ^ trace->not_ev_qualifier)) {
-                       sc->filtered = true;
-                       /*
-                        * No need to do read tracepoint information since this will be
-                        * filtered out.
-                        */
-                       return 0;
-               }
-       }
-
        sc->fmt  = syscall_fmt__find(sc->name);
 
        snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name);
@@ -1823,9 +1809,6 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
        if (sc == NULL)
                return -1;
 
-       if (sc->filtered)
-               return 0;
-
        thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
        ttrace = thread__trace(thread, trace->output);
        if (ttrace == NULL)
@@ -1881,9 +1864,6 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
        if (sc == NULL)
                return -1;
 
-       if (sc->filtered)
-               return 0;
-
        thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
        ttrace = thread__trace(thread, trace->output);
        if (ttrace == NULL)
@@ -2310,6 +2290,26 @@ out_delete_sys_enter:
        goto out;
 }
 
+static int trace__set_ev_qualifier_filter(struct trace *trace)
+{
+       int err = -1;
+       char *filter = asprintf_expr_inout_ints("id", !trace->not_ev_qualifier,
+                                               trace->ev_qualifier_ids.nr,
+                                               trace->ev_qualifier_ids.entries);
+
+       if (filter == NULL)
+               goto out_enomem;
+
+       if (!perf_evsel__append_filter(trace->syscalls.events.sys_enter, "&&", filter))
+               err = perf_evsel__append_filter(trace->syscalls.events.sys_exit, "&&", filter);
+
+       free(filter);
+out:
+       return err;
+out_enomem:
+       errno = ENOMEM;
+       goto out;
+}
 
 static int trace__run(struct trace *trace, int argc, const char **argv)
 {
@@ -2386,6 +2386,14 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
        if (err < 0)
                goto out_error_mem;
 
+       if (trace->ev_qualifier_ids.nr > 0) {
+               err = trace__set_ev_qualifier_filter(trace);
+               if (err < 0)
+                       goto out_errno;
+       }
+
+       pr_debug("%s\n", trace->syscalls.events.sys_exit->filter);
+
        err = perf_evlist__apply_filters(evlist, &evsel);
        if (err < 0)
                goto out_error_apply_filters;
@@ -2502,6 +2510,10 @@ out_error_apply_filters:
 out_error_mem:
        fprintf(trace->output, "Not enough memory to run!\n");
        goto out_delete_evlist;
+
+out_errno:
+       fprintf(trace->output, "errno=%d,%s\n", errno, strerror(errno));
+       goto out_delete_evlist;
 }
 
 static int trace__replay(struct trace *trace)