[PATCH] perf tools: Check fallback error and order

[Namhyung Kim]

The perf_event_open might fail due to various reasons, so blindly
reducing precise_ip level might not be the best way to deal with it.

It seems the kernel return -EOPNOTSUPP when PMU doesn't support the
given precise level.  Let's try again with the correct error code.

This caused a problem on AMD, as it stops on precise_ip of 2 for IBS but
user events with exclude_kernel=1 cannot make progress.  Let's add the
evsel__handle_error_quirks() to this case specially.  I plan to work on
the kernel side to improve this situation but it'd still need some
special handling for IBS.

Signed-off-by: Namhyung Kim <namhyung@xxxxxxxxxx>
---
 tools/perf/util/evsel.c | 50 ++++++++++++++++++++++++++++++++++++-----
 1 file changed, 44 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 476658143822c346..2c45c55222c43dd4 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2246,6 +2246,43 @@ static bool evsel__detect_missing_features(struct evsel *evsel)
 	return false;
 }
 
+/*
+ * AMD core PMU forwards some events with precise_ip to IBS implicitly.
+ * This logic matches to the kernel function (core_pmu_ibs_config).
+ */
+static bool evsel__is_implicit_ibs_event(struct evsel *evsel)
+{
+	if (evsel->core.attr.precise_ip == 0 || !x86__is_amd_cpu())
+		return false;
+
+	if (evsel->core.attr.type == PERF_TYPE_HARDWARE &&
+	    evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES)
+		return true;
+
+	if (evsel->core.attr.type == PERF_TYPE_RAW &&
+	    (evsel->core.attr.config == 0x76 || evsel->core.attr.config == 0xc1))
+		return true;
+
+	return false;
+}
+
+static bool evsel__handle_error_quirks(struct evsel *evsel, int error)
+{
+	/*
+	 * AMD IBS doesn't support exclude_kernel, forward it back to the core
+	 * PMU by clearing precise_ip only if it's from precise_max (:P).
+	 */
+	if (error == -EINVAL && evsel__is_implicit_ibs_event(evsel) &&
+	    evsel->core.attr.exclude_kernel && evsel->precise_max) {
+		evsel->core.attr.precise_ip = 0;
+		pr_debug2_peo("removing precise_ip on AMD\n");
+		display_attr(&evsel->core.attr);
+		return true;
+	}
+
+	return false;
+}
+
 static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 		struct perf_thread_map *threads,
 		int start_cpu_map_idx, int end_cpu_map_idx)
@@ -2366,9 +2403,6 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 	return 0;
 
 try_fallback:
-	if (evsel__precise_ip_fallback(evsel))
-		goto retry_open;
-
 	if (evsel__ignore_missing_thread(evsel, perf_cpu_map__nr(cpus),
 					 idx, threads, thread, err)) {
 		/* We just removed 1 thread, so lower the upper nthreads limit. */
@@ -2385,11 +2419,15 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 	if (err == -EMFILE && rlimit__increase_nofile(&set_rlimit))
 		goto retry_open;
 
-	if (err != -EINVAL || idx > 0 || thread > 0)
-		goto out_close;
+	if (err == -EOPNOTSUPP && evsel__precise_ip_fallback(evsel))
+		goto retry_open;
 
-	if (evsel__detect_missing_features(evsel))
+	if (err == -EINVAL && evsel__detect_missing_features(evsel))
 		goto fallback_missing_features;
+
+	if (evsel__handle_error_quirks(evsel, err))
+		goto retry_open;
+
 out_close:
 	if (err)
 		threads->err_thread = thread;
-- 
2.47.0.rc1.288.g06298d1525-goog