While running test_progs in a loop I found out that I'm sometimes hitting
"Didn't find expected build ID from the map" error.
Looking at stack_map_get_build_id_offset() it seems that it is racy (by
design) and can sometimes return BPF_STACK_BUILD_ID_IP (i.e. can't trylock
current->mm->mmap_sem).

Let's retry this test a single time.

Fixes: 13790d1cc72c ("bpf: add selftest for stackmap with build_id in NMI 
context")
Signed-off-by: Stanislav Fomichev <s...@google.com>
---
 tools/testing/selftests/bpf/test_progs.c | 30 ++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/tools/testing/selftests/bpf/test_progs.c 
b/tools/testing/selftests/bpf/test_progs.c
index 126fc624290d..25f0083a9b2e 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1188,7 +1188,9 @@ static void test_stacktrace_build_id(void)
        int i, j;
        struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH];
        int build_id_matches = 0;
+       int retry = 1;
 
+retry:
        err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
        if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
                goto out;
@@ -1301,6 +1303,19 @@ static void test_stacktrace_build_id(void)
                previous_key = key;
        } while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0);
 
+       /* stack_map_get_build_id_offset() is racy and sometimes can return
+        * BPF_STACK_BUILD_ID_IP instead of BPF_STACK_BUILD_ID_VALID;
+        * try it one more time.
+        */
+       if (build_id_matches < 1 && retry--) {
+               ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
+               close(pmu_fd);
+               bpf_object__close(obj);
+               printf("%s:WARN:Didn't find expected build ID from the map, 
retrying\n",
+                      __func__);
+               goto retry;
+       }
+
        if (CHECK(build_id_matches < 1, "build id match",
                  "Didn't find expected build ID from the map\n"))
                goto disable_pmu;
@@ -1341,7 +1356,9 @@ static void test_stacktrace_build_id_nmi(void)
        int i, j;
        struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH];
        int build_id_matches = 0;
+       int retry = 1;
 
+retry:
        err = bpf_prog_load(file, BPF_PROG_TYPE_PERF_EVENT, &obj, &prog_fd);
        if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
                return;
@@ -1436,6 +1453,19 @@ static void test_stacktrace_build_id_nmi(void)
                previous_key = key;
        } while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0);
 
+       /* stack_map_get_build_id_offset() is racy and sometimes can return
+        * BPF_STACK_BUILD_ID_IP instead of BPF_STACK_BUILD_ID_VALID;
+        * try it one more time.
+        */
+       if (build_id_matches < 1 && retry--) {
+               ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
+               close(pmu_fd);
+               bpf_object__close(obj);
+               printf("%s:WARN:Didn't find expected build ID from the map, 
retrying\n",
+                      __func__);
+               goto retry;
+       }
+
        if (CHECK(build_id_matches < 1, "build id match",
                  "Didn't find expected build ID from the map\n"))
                goto disable_pmu;
-- 
2.20.1.97.g81188d93c3-goog

Reply via email to