perf evsel: Fix max perf_event_attr.precise_ip detection

Commit-ID:  4e8a5c1551370ebc0fbdb8f5c33dad13e45bdc99
Gitweb:     https://git.kernel.org/tip/4e8a5c1551370ebc0fbdb8f5c33dad13e45bdc99
Author:     Jiri Olsa <[email protected]>
AuthorDate: Thu, 14 Mar 2019 15:00:10 +0100
Committer:  Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Thu, 28 Mar 2019 14:31:56 -0300

perf evsel: Fix max perf_event_attr.precise_ip detection

After a discussion with Andi, move the perf_event_attr.precise_ip detection for maximum precise config (via :P modifier or for default cycles event) to perf_evsel__open().

The current detection in perf_event_attr__set_max_precise_ip() is tricky, because precise_ip config is specific for given event and it currently checks only hw cycles.

We now check for valid precise_ip value right after failing sys_perf_event_open() for specific event, before any of the perf_event_attr fallback code gets executed.

This way we get the proper config in perf_event_attr together with allowed precise_ip settings.

We can see that code activity with -vv, like:

  $ perf record -vv ls
  ...
  ------------------------------------------------------------
  perf_event_attr:
    size                             112
    { sample_period, sample_freq }   4000
    ...
    precise_ip                       3
    sample_id_all                    1
    exclude_guest                    1
    mmap2                            1
    comm_exec                        1
    ksymbol                          1
  ------------------------------------------------------------
  sys_perf_event_open: pid 9926  cpu 0  group_fd -1  flags 0x8
  sys_perf_event_open failed, error -95
  decreasing precise_ip by one (2)
  ------------------------------------------------------------
  perf_event_attr:
    size                             112
    { sample_period, sample_freq }   4000
    ...
    precise_ip                       2
    sample_id_all                    1
    exclude_guest                    1
    mmap2                            1
    comm_exec                        1
    ksymbol                          1
  ------------------------------------------------------------
  sys_perf_event_open: pid 9926  cpu 0  group_fd -1  flags 0x8 = 4
  ...

---
 tools/perf/util/evlist.c | 29 -------------------
 tools/perf/util/evlist.h |  2 --
 tools/perf/util/evsel.c  | 72 +++++++++++++++++++++++++++++++++++++++---------
 3 files changed, 59 insertions(+), 44 deletions(-)

index ec78e93085de..6689378ee577 100644
@@ -231,35 +231,6 @@ void perf_evlist__set_leader(struct perf_evlist *evlist)
 	}
 }
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *pattr)
-{
-	struct perf_event_attr attr = {
-		.type		= PERF_TYPE_HARDWARE,
-		.config		= PERF_COUNT_HW_CPU_CYCLES,
-		.exclude_kernel	= 1,
-		.precise_ip	= 3,
-	};
-
-	event_attr_init(&attr);
-
-	/*
-	 * Unnamed union member, not supported as struct member named
-	 * initializer in older compilers such as gcc 4.4.7
-	 */
-	attr.sample_period = 1;
-
-	while (attr.precise_ip != 0) {
-		int fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
-		if (fd != -1) {
-			close(fd);
-			break;
-		}
-		--attr.precise_ip;
-	}
-
-	pattr->precise_ip = attr.precise_ip;
-}
-
 int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise)
 {
 	struct perf_evsel *evsel = perf_evsel__new_cycles(precise);

index dcb68f34d2cd..6a94785b9100 100644
@@ -315,8 +315,6 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
-
 struct perf_evsel *
 perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);