Each cgroup_iter_memcg subtest touches 1024 pages and expects the matching memcg counter to be non-zero. On a host with many CPUs it reads zero instead: test_anon:FAIL:final anon mapped val: actual 0 <= expected 0 memcg stats are cached per-cpu and only become visible once the periodic flusher runs (FLUSH_TIME, 2s), or once pending updates cross MEMCG_CHARGE_BATCH * num_online_cpus(). That threshold is 512 pages at 8 CPUs but 8192 at 128, so a single pass no longer reaches it and bpf_mem_cgroup_flush_stats() returns without flushing anything. Retry the stat generation, sleeping in between, so that a flusher cycle is always covered. Fixes: 6bce6ddbe634 ("bpf: selftests: selftests for memcg stat kfuncs") Signed-off-by: Andrii Nakryiko --- .../bpf/prog_tests/cgroup_iter_memcg.c | 43 +++++++++++++++++++ 1 file changed, 43 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_iter_memcg.c b/tools/testing/selftests/bpf/prog_tests/cgroup_iter_memcg.c index b7c18d590b99..37e2cf249be8 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_iter_memcg.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_iter_memcg.c @@ -10,6 +10,17 @@ #include "cgroup_iter_memcg.h" #include "cgroup_iter_memcg.skel.h" +/* + * memcg stats are cached per-cpu and only become visible once the periodic + * flusher runs (FLUSH_TIME, 2s), or once pending updates cross + * MEMCG_CHARGE_BATCH * num_online_cpus(). That threshold grows with the CPU + * count, so on a large machine a single pass does not reach it and + * bpf_mem_cgroup_flush_stats() returns without flushing anything. Retry for + * long enough to cover a flusher cycle. + */ +#define MEMCG_STAT_RETRIES 16 +#define MEMCG_STAT_RETRY_DELAY_US (250 * 1000) + static int read_stats(struct bpf_link *link) { int fd, ret = 0; @@ -35,11 +46,13 @@ static int read_stats(struct bpf_link *link) static void test_anon(struct bpf_link *link, struct memcg_query *memcg_query) { + int retries = 0; void *map; size_t len; len = sysconf(_SC_PAGESIZE) * 1024; +retry: /* * Increase memcg anon usage by mapping and writing * to a new anon region. @@ -53,6 +66,12 @@ static void test_anon(struct bpf_link *link, struct memcg_query *memcg_query) if (!ASSERT_OK(read_stats(link), "read stats")) goto cleanup; + if (!memcg_query->nr_anon_mapped && ++retries < MEMCG_STAT_RETRIES) { + munmap(map, len); + usleep(MEMCG_STAT_RETRY_DELAY_US); + goto retry; + } + ASSERT_GT(memcg_query->nr_anon_mapped, 0, "final anon mapped val"); cleanup: @@ -61,6 +80,7 @@ static void test_anon(struct bpf_link *link, struct memcg_query *memcg_query) static void test_file(struct bpf_link *link, struct memcg_query *memcg_query) { + int retries = 0; void *map; size_t len; char *path; @@ -76,6 +96,7 @@ static void test_file(struct bpf_link *link, struct memcg_query *memcg_query) fd = open(path, O_CREAT | O_RDWR, 0644); if (!ASSERT_OK_FD(fd, "open fd")) return; +retry: if (!ASSERT_OK(ftruncate(fd, len), "ftruncate")) goto cleanup_fd; @@ -88,6 +109,13 @@ static void test_file(struct bpf_link *link, struct memcg_query *memcg_query) if (!ASSERT_OK(read_stats(link), "read stats")) goto cleanup_map; + if (!memcg_query->nr_file_pages && !memcg_query->nr_file_mapped && + ++retries < MEMCG_STAT_RETRIES) { + munmap(map, len); + usleep(MEMCG_STAT_RETRY_DELAY_US); + goto retry; + } + ASSERT_GT(memcg_query->nr_file_pages, 0, "final file value"); ASSERT_GT(memcg_query->nr_file_mapped, 0, "final file mapped value"); @@ -100,6 +128,7 @@ static void test_file(struct bpf_link *link, struct memcg_query *memcg_query) static void test_shmem(struct bpf_link *link, struct memcg_query *memcg_query) { + int retries = 0; size_t len; int fd; @@ -113,12 +142,18 @@ static void test_shmem(struct bpf_link *link, struct memcg_query *memcg_query) if (!ASSERT_OK_FD(fd, "memfd_create")) return; +retry: if (!ASSERT_OK(fallocate(fd, 0, 0, len), "fallocate")) goto cleanup; if (!ASSERT_OK(read_stats(link), "read stats")) goto cleanup; + if (!memcg_query->nr_shmem && ++retries < MEMCG_STAT_RETRIES) { + usleep(MEMCG_STAT_RETRY_DELAY_US); + goto retry; + } + ASSERT_GT(memcg_query->nr_shmem, 0, "final shmem value"); cleanup: @@ -127,11 +162,13 @@ static void test_shmem(struct bpf_link *link, struct memcg_query *memcg_query) static void test_pgfault(struct bpf_link *link, struct memcg_query *memcg_query) { + int retries = 0; void *map; size_t len; len = sysconf(_SC_PAGESIZE) * 1024; +retry: /* Create region to use for triggering a page fault. */ map = mmap(NULL, len, PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (!ASSERT_NEQ(map, MAP_FAILED, "mmap anon")) @@ -143,6 +180,12 @@ static void test_pgfault(struct bpf_link *link, struct memcg_query *memcg_query) if (!ASSERT_OK(read_stats(link), "read stats")) goto cleanup; + if (!memcg_query->pgfault && ++retries < MEMCG_STAT_RETRIES) { + munmap(map, len); + usleep(MEMCG_STAT_RETRY_DELAY_US); + goto retry; + } + ASSERT_GT(memcg_query->pgfault, 0, "final pgfault val"); cleanup: -- 2.53.0-Meta