summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/bpf/prog_tests
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing/selftests/bpf/prog_tests')
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf_dump.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgroup_hierarchical_stats.c357
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgroup_iter.c224
3 files changed, 583 insertions, 2 deletions
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index 5fce7008d1ff..a1bae92be1fc 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -764,8 +764,8 @@ static void test_btf_dump_struct_data(struct btf *btf, struct btf_dump *d,
/* union with nested struct */
TEST_BTF_DUMP_DATA(btf, d, "union", str, union bpf_iter_link_info, BTF_F_COMPACT,
- "(union bpf_iter_link_info){.map = (struct){.map_fd = (__u32)1,},}",
- { .map = { .map_fd = 1 }});
+ "(union bpf_iter_link_info){.map = (struct){.map_fd = (__u32)1,},.cgroup = (struct){.order = (enum bpf_cgroup_iter_order)BPF_ITER_SELF_ONLY,.cgroup_fd = (__u32)1,},}",
+ { .cgroup = { .order = 1, .cgroup_fd = 1, }});
/* struct skb with nested structs/unions; because type output is so
* complex, we don't do a string comparison, just verify we return
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_hierarchical_stats.c b/tools/testing/selftests/bpf/prog_tests/cgroup_hierarchical_stats.c
new file mode 100644
index 000000000000..101a6d70b863
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_hierarchical_stats.c
@@ -0,0 +1,357 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Functions to manage eBPF programs attached to cgroup subsystems
+ *
+ * Copyright 2022 Google LLC.
+ */
+#include <asm-generic/errno.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include <test_progs.h>
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+
+#include "cgroup_helpers.h"
+#include "cgroup_hierarchical_stats.skel.h"
+
+#define PAGE_SIZE 4096
+#define MB(x) (x << 20)
+
+#define BPFFS_ROOT "/sys/fs/bpf/"
+#define BPFFS_VMSCAN BPFFS_ROOT"vmscan/"
+
+#define CG_ROOT_NAME "root"
+#define CG_ROOT_ID 1
+
+#define CGROUP_PATH(p, n) {.path = p"/"n, .name = n}
+
+static struct {
+ const char *path, *name;
+ unsigned long long id;
+ int fd;
+} cgroups[] = {
+ CGROUP_PATH("/", "test"),
+ CGROUP_PATH("/test", "child1"),
+ CGROUP_PATH("/test", "child2"),
+ CGROUP_PATH("/test/child1", "child1_1"),
+ CGROUP_PATH("/test/child1", "child1_2"),
+ CGROUP_PATH("/test/child2", "child2_1"),
+ CGROUP_PATH("/test/child2", "child2_2"),
+};
+
+#define N_CGROUPS ARRAY_SIZE(cgroups)
+#define N_NON_LEAF_CGROUPS 3
+
+static int root_cgroup_fd;
+static bool mounted_bpffs;
+
+/* reads file at 'path' to 'buf', returns 0 on success. */
+static int read_from_file(const char *path, char *buf, size_t size)
+{
+ int fd, len;
+
+ fd = open(path, O_RDONLY);
+ if (fd < 0)
+ return fd;
+
+ len = read(fd, buf, size);
+ close(fd);
+ if (len < 0)
+ return len;
+
+ buf[len] = 0;
+ return 0;
+}
+
+/* mounts bpffs and mkdir for reading stats, returns 0 on success. */
+static int setup_bpffs(void)
+{
+ int err;
+
+ /* Mount bpffs */
+ err = mount("bpf", BPFFS_ROOT, "bpf", 0, NULL);
+ mounted_bpffs = !err;
+ if (ASSERT_FALSE(err && errno != EBUSY, "mount"))
+ return err;
+
+ /* Create a directory to contain stat files in bpffs */
+ err = mkdir(BPFFS_VMSCAN, 0755);
+ if (!ASSERT_OK(err, "mkdir"))
+ return err;
+
+ return 0;
+}
+
+static void cleanup_bpffs(void)
+{
+ /* Remove created directory in bpffs */
+ ASSERT_OK(rmdir(BPFFS_VMSCAN), "rmdir "BPFFS_VMSCAN);
+
+ /* Unmount bpffs, if it wasn't already mounted when we started */
+ if (mounted_bpffs)
+ return;
+
+ ASSERT_OK(umount(BPFFS_ROOT), "unmount bpffs");
+}
+
+/* sets up cgroups, returns 0 on success. */
+static int setup_cgroups(void)
+{
+ int i, fd, err;
+
+ err = setup_cgroup_environment();
+ if (!ASSERT_OK(err, "setup_cgroup_environment"))
+ return err;
+
+ root_cgroup_fd = get_root_cgroup();
+ if (!ASSERT_GE(root_cgroup_fd, 0, "get_root_cgroup"))
+ return root_cgroup_fd;
+
+ for (i = 0; i < N_CGROUPS; i++) {
+ fd = create_and_get_cgroup(cgroups[i].path);
+ if (!ASSERT_GE(fd, 0, "create_and_get_cgroup"))
+ return fd;
+
+ cgroups[i].fd = fd;
+ cgroups[i].id = get_cgroup_id(cgroups[i].path);
+
+ /*
+ * Enable memcg controller for the entire hierarchy.
+ * Note that stats are collected for all cgroups in a hierarchy
+ * with memcg enabled anyway, but are only exposed for cgroups
+ * that have memcg enabled.
+ */
+ if (i < N_NON_LEAF_CGROUPS) {
+ err = enable_controllers(cgroups[i].path, "memory");
+ if (!ASSERT_OK(err, "enable_controllers"))
+ return err;
+ }
+ }
+ return 0;
+}
+
+static void cleanup_cgroups(void)
+{
+ close(root_cgroup_fd);
+ for (int i = 0; i < N_CGROUPS; i++)
+ close(cgroups[i].fd);
+ cleanup_cgroup_environment();
+}
+
+/* Sets up cgroup hiearchary, returns 0 on success. */
+static int setup_hierarchy(void)
+{
+ return setup_bpffs() || setup_cgroups();
+}
+
+static void destroy_hierarchy(void)
+{
+ cleanup_cgroups();
+ cleanup_bpffs();
+}
+
+static int reclaimer(const char *cgroup_path, size_t size)
+{
+ static char size_buf[128];
+ char *buf, *ptr;
+ int err;
+
+ /* Join cgroup in the parent process workdir */
+ if (join_parent_cgroup(cgroup_path))
+ return EACCES;
+
+ /* Allocate memory */
+ buf = malloc(size);
+ if (!buf)
+ return ENOMEM;
+
+ /* Write to memory to make sure it's actually allocated */
+ for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+ *ptr = 1;
+
+ /* Try to reclaim memory */
+ snprintf(size_buf, 128, "%lu", size);
+ err = write_cgroup_file_parent(cgroup_path, "memory.reclaim", size_buf);
+
+ free(buf);
+ /* memory.reclaim returns EAGAIN if the amount is not fully reclaimed */
+ if (err && errno != EAGAIN)
+ return errno;
+
+ return 0;
+}
+
+static int induce_vmscan(void)
+{
+ int i, status;
+
+ /*
+ * In every leaf cgroup, run a child process that allocates some memory
+ * and attempts to reclaim some of it.
+ */
+ for (i = N_NON_LEAF_CGROUPS; i < N_CGROUPS; i++) {
+ pid_t pid;
+
+ /* Create reclaimer child */
+ pid = fork();
+ if (pid == 0) {
+ status = reclaimer(cgroups[i].path, MB(5));
+ exit(status);
+ }
+
+ /* Cleanup reclaimer child */
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status), "reclaimer exited");
+ ASSERT_EQ(WEXITSTATUS(status), 0, "reclaim exit code");
+ }
+ return 0;
+}
+
+static unsigned long long
+get_cgroup_vmscan_delay(unsigned long long cgroup_id, const char *file_name)
+{
+ unsigned long long vmscan = 0, id = 0;
+ static char buf[128], path[128];
+
+ /* For every cgroup, read the file generated by cgroup_iter */
+ snprintf(path, 128, "%s%s", BPFFS_VMSCAN, file_name);
+ if (!ASSERT_OK(read_from_file(path, buf, 128), "read cgroup_iter"))
+ return 0;
+
+ /* Check the output file formatting */
+ ASSERT_EQ(sscanf(buf, "cg_id: %llu, total_vmscan_delay: %llu\n",
+ &id, &vmscan), 2, "output format");
+
+ /* Check that the cgroup_id is displayed correctly */
+ ASSERT_EQ(id, cgroup_id, "cgroup_id");
+ /* Check that the vmscan reading is non-zero */
+ ASSERT_GT(vmscan, 0, "vmscan_reading");
+ return vmscan;
+}
+
+static void check_vmscan_stats(void)
+{
+ unsigned long long vmscan_readings[N_CGROUPS], vmscan_root;
+ int i;
+
+ for (i = 0; i < N_CGROUPS; i++) {
+ vmscan_readings[i] = get_cgroup_vmscan_delay(cgroups[i].id,
+ cgroups[i].name);
+ }
+
+ /* Read stats for root too */
+ vmscan_root = get_cgroup_vmscan_delay(CG_ROOT_ID, CG_ROOT_NAME);
+
+ /* Check that child1 == child1_1 + child1_2 */
+ ASSERT_EQ(vmscan_readings[1], vmscan_readings[3] + vmscan_readings[4],
+ "child1_vmscan");
+ /* Check that child2 == child2_1 + child2_2 */
+ ASSERT_EQ(vmscan_readings[2], vmscan_readings[5] + vmscan_readings[6],
+ "child2_vmscan");
+ /* Check that test == child1 + child2 */
+ ASSERT_EQ(vmscan_readings[0], vmscan_readings[1] + vmscan_readings[2],
+ "test_vmscan");
+ /* Check that root >= test */
+ ASSERT_GE(vmscan_root, vmscan_readings[1], "root_vmscan");
+}
+
+/* Creates iter link and pins in bpffs, returns 0 on success, -errno on failure.
+ */
+static int setup_cgroup_iter(struct cgroup_hierarchical_stats *obj,
+ int cgroup_fd, const char *file_name)
+{
+ DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+ union bpf_iter_link_info linfo = {};
+ struct bpf_link *link;
+ static char path[128];
+ int err;
+
+ /*
+ * Create an iter link, parameterized by cgroup_fd. We only want to
+ * traverse one cgroup, so set the traversal order to "self".
+ */
+ linfo.cgroup.cgroup_fd = cgroup_fd;
+ linfo.cgroup.order = BPF_ITER_SELF_ONLY;
+ opts.link_info = &linfo;
+ opts.link_info_len = sizeof(linfo);
+ link = bpf_program__attach_iter(obj->progs.dump_vmscan, &opts);
+ if (!ASSERT_OK_PTR(link, "attach_iter"))
+ return -EFAULT;
+
+ /* Pin the link to a bpffs file */
+ snprintf(path, 128, "%s%s", BPFFS_VMSCAN, file_name);
+ err = bpf_link__pin(link, path);
+ ASSERT_OK(err, "pin cgroup_iter");
+
+ /* Remove the link, leaving only the ref held by the pinned file */
+ bpf_link__destroy(link);
+ return err;
+}
+
+/* Sets up programs for collecting stats, returns 0 on success. */
+static int setup_progs(struct cgroup_hierarchical_stats **skel)
+{
+ int i, err;
+
+ *skel = cgroup_hierarchical_stats__open_and_load();
+ if (!ASSERT_OK_PTR(*skel, "open_and_load"))
+ return 1;
+
+ /* Attach cgroup_iter program that will dump the stats to cgroups */
+ for (i = 0; i < N_CGROUPS; i++) {
+ err = setup_cgroup_iter(*skel, cgroups[i].fd, cgroups[i].name);
+ if (!ASSERT_OK(err, "setup_cgroup_iter"))
+ return err;
+ }
+
+ /* Also dump stats for root */
+ err = setup_cgroup_iter(*skel, root_cgroup_fd, CG_ROOT_NAME);
+ if (!ASSERT_OK(err, "setup_cgroup_iter"))
+ return err;
+
+ bpf_program__set_autoattach((*skel)->progs.dump_vmscan, false);
+ err = cgroup_hierarchical_stats__attach(*skel);
+ if (!ASSERT_OK(err, "attach"))
+ return err;
+
+ return 0;
+}
+
+static void destroy_progs(struct cgroup_hierarchical_stats *skel)
+{
+ static char path[128];
+ int i;
+
+ for (i = 0; i < N_CGROUPS; i++) {
+ /* Delete files in bpffs that cgroup_iters are pinned in */
+ snprintf(path, 128, "%s%s", BPFFS_VMSCAN,
+ cgroups[i].name);
+ ASSERT_OK(remove(path), "remove cgroup_iter pin");
+ }
+
+ /* Delete root file in bpffs */
+ snprintf(path, 128, "%s%s", BPFFS_VMSCAN, CG_ROOT_NAME);
+ ASSERT_OK(remove(path), "remove cgroup_iter root pin");
+ cgroup_hierarchical_stats__destroy(skel);
+}
+
+void test_cgroup_hierarchical_stats(void)
+{
+ struct cgroup_hierarchical_stats *skel = NULL;
+
+ if (setup_hierarchy())
+ goto hierarchy_cleanup;
+ if (setup_progs(&skel))
+ goto cleanup;
+ if (induce_vmscan())
+ goto cleanup;
+ check_vmscan_stats();
+cleanup:
+ destroy_progs(skel);
+hierarchy_cleanup:
+ destroy_hierarchy();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c b/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c
new file mode 100644
index 000000000000..38958c37b9ce
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c
@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Google */
+
+#include <test_progs.h>
+#include <bpf/libbpf.h>
+#include <bpf/btf.h>
+#include "cgroup_iter.skel.h"
+#include "cgroup_helpers.h"
+
+#define ROOT 0
+#define PARENT 1
+#define CHILD1 2
+#define CHILD2 3
+#define NUM_CGROUPS 4
+
+#define PROLOGUE "prologue\n"
+#define EPILOGUE "epilogue\n"
+
+static const char *cg_path[] = {
+ "/", "/parent", "/parent/child1", "/parent/child2"
+};
+
+static int cg_fd[] = {-1, -1, -1, -1};
+static unsigned long long cg_id[] = {0, 0, 0, 0};
+static char expected_output[64];
+
+static int setup_cgroups(void)
+{
+ int fd, i = 0;
+
+ for (i = 0; i < NUM_CGROUPS; i++) {
+ fd = create_and_get_cgroup(cg_path[i]);
+ if (fd < 0)
+ return fd;
+
+ cg_fd[i] = fd;
+ cg_id[i] = get_cgroup_id(cg_path[i]);
+ }
+ return 0;
+}
+
+static void cleanup_cgroups(void)
+{
+ int i;
+
+ for (i = 0; i < NUM_CGROUPS; i++)
+ close(cg_fd[i]);
+}
+
+static void read_from_cgroup_iter(struct bpf_program *prog, int cgroup_fd,
+ int order, const char *testname)
+{
+ DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+ union bpf_iter_link_info linfo;
+ struct bpf_link *link;
+ int len, iter_fd;
+ static char buf[128];
+ size_t left;
+ char *p;
+
+ memset(&linfo, 0, sizeof(linfo));
+ linfo.cgroup.cgroup_fd = cgroup_fd;
+ linfo.cgroup.order = order;
+ opts.link_info = &linfo;
+ opts.link_info_len = sizeof(linfo);
+
+ link = bpf_program__attach_iter(prog, &opts);
+ if (!ASSERT_OK_PTR(link, "attach_iter"))
+ return;
+
+ iter_fd = bpf_iter_create(bpf_link__fd(link));
+ if (iter_fd < 0)
+ goto free_link;
+
+ memset(buf, 0, sizeof(buf));
+ left = ARRAY_SIZE(buf);
+ p = buf;
+ while ((len = read(iter_fd, p, left)) > 0) {
+ p += len;
+ left -= len;
+ }
+
+ ASSERT_STREQ(buf, expected_output, testname);
+
+ /* read() after iter finishes should be ok. */
+ if (len == 0)
+ ASSERT_OK(read(iter_fd, buf, sizeof(buf)), "second_read");
+
+ close(iter_fd);
+free_link:
+ bpf_link__destroy(link);
+}
+
+/* Invalid cgroup. */
+static void test_invalid_cgroup(struct cgroup_iter *skel)
+{
+ DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+ union bpf_iter_link_info linfo;
+ struct bpf_link *link;
+
+ memset(&linfo, 0, sizeof(linfo));
+ linfo.cgroup.cgroup_fd = (__u32)-1;
+ opts.link_info = &linfo;
+ opts.link_info_len = sizeof(linfo);
+
+ link = bpf_program__attach_iter(skel->progs.cgroup_id_printer, &opts);
+ ASSERT_ERR_PTR(link, "attach_iter");
+ bpf_link__destroy(link);
+}
+
+/* Specifying both cgroup_fd and cgroup_id is invalid. */
+static void test_invalid_cgroup_spec(struct cgroup_iter *skel)
+{
+ DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+ union bpf_iter_link_info linfo;
+ struct bpf_link *link;
+
+ memset(&linfo, 0, sizeof(linfo));
+ linfo.cgroup.cgroup_fd = (__u32)cg_fd[PARENT];
+ linfo.cgroup.cgroup_id = (__u64)cg_id[PARENT];
+ opts.link_info = &linfo;
+ opts.link_info_len = sizeof(linfo);
+
+ link = bpf_program__attach_iter(skel->progs.cgroup_id_printer, &opts);
+ ASSERT_ERR_PTR(link, "attach_iter");
+ bpf_link__destroy(link);
+}
+
+/* Preorder walk prints parent and child in order. */
+static void test_walk_preorder(struct cgroup_iter *skel)
+{
+ snprintf(expected_output, sizeof(expected_output),
+ PROLOGUE "%8llu\n%8llu\n%8llu\n" EPILOGUE,
+ cg_id[PARENT], cg_id[CHILD1], cg_id[CHILD2]);
+
+ read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
+ BPF_ITER_DESCENDANTS_PRE, "preorder");
+}
+
+/* Postorder walk prints child and parent in order. */
+static void test_walk_postorder(struct cgroup_iter *skel)
+{
+ snprintf(expected_output, sizeof(expected_output),
+ PROLOGUE "%8llu\n%8llu\n%8llu\n" EPILOGUE,
+ cg_id[CHILD1], cg_id[CHILD2], cg_id[PARENT]);
+
+ read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
+ BPF_ITER_DESCENDANTS_POST, "postorder");
+}
+
+/* Walking parents prints parent and then root. */
+static void test_walk_ancestors_up(struct cgroup_iter *skel)
+{
+ /* terminate the walk when ROOT is met. */
+ skel->bss->terminal_cgroup = cg_id[ROOT];
+
+ snprintf(expected_output, sizeof(expected_output),
+ PROLOGUE "%8llu\n%8llu\n" EPILOGUE,
+ cg_id[PARENT], cg_id[ROOT]);
+
+ read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
+ BPF_ITER_ANCESTORS_UP, "ancestors_up");
+
+ skel->bss->terminal_cgroup = 0;
+}
+
+/* Early termination prints parent only. */
+static void test_early_termination(struct cgroup_iter *skel)
+{
+ /* terminate the walk after the first element is processed. */
+ skel->bss->terminate_early = 1;
+
+ snprintf(expected_output, sizeof(expected_output),
+ PROLOGUE "%8llu\n" EPILOGUE, cg_id[PARENT]);
+
+ read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
+ BPF_ITER_DESCENDANTS_PRE, "early_termination");
+
+ skel->bss->terminate_early = 0;
+}
+
+/* Waling self prints self only. */
+static void test_walk_self_only(struct cgroup_iter *skel)
+{
+ snprintf(expected_output, sizeof(expected_output),
+ PROLOGUE "%8llu\n" EPILOGUE, cg_id[PARENT]);
+
+ read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
+ BPF_ITER_SELF_ONLY, "self_only");
+}
+
+void test_cgroup_iter(void)
+{
+ struct cgroup_iter *skel = NULL;
+
+ if (setup_cgroup_environment())
+ return;
+
+ if (setup_cgroups())
+ goto out;
+
+ skel = cgroup_iter__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "cgroup_iter__open_and_load"))
+ goto out;
+
+ if (test__start_subtest("cgroup_iter__invalid_cgroup"))
+ test_invalid_cgroup(skel);
+ if (test__start_subtest("cgroup_iter__invalid_cgroup_spec"))
+ test_invalid_cgroup_spec(skel);
+ if (test__start_subtest("cgroup_iter__preorder"))
+ test_walk_preorder(skel);
+ if (test__start_subtest("cgroup_iter__postorder"))
+ test_walk_postorder(skel);
+ if (test__start_subtest("cgroup_iter__ancestors_up_walk"))
+ test_walk_ancestors_up(skel);
+ if (test__start_subtest("cgroup_iter__early_termination"))
+ test_early_termination(skel);
+ if (test__start_subtest("cgroup_iter__self_only"))
+ test_walk_self_only(skel);
+out:
+ cgroup_iter__destroy(skel);
+ cleanup_cgroups();
+ cleanup_cgroup_environment();
+}