From patchwork Sun Apr 29 05:28:15 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yonghong Song X-Patchwork-Id: 906252 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=pass (p=none dis=none) header.from=fb.com Authentication-Results: ozlabs.org; dkim=pass (1024-bit key; unprotected) header.d=fb.com header.i=@fb.com header.b="qvPfCGfx"; dkim-atps=neutral Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 40Ybn64dyQz9s06 for ; Sun, 29 Apr 2018 15:28:42 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752706AbeD2F2i (ORCPT ); Sun, 29 Apr 2018 01:28:38 -0400 Received: from mx0a-00082601.pphosted.com ([67.231.145.42]:46936 "EHLO mx0a-00082601.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752566AbeD2F2Y (ORCPT ); Sun, 29 Apr 2018 01:28:24 -0400 Received: from pps.filterd (m0044012.ppops.net [127.0.0.1]) by mx0a-00082601.pphosted.com (8.16.0.22/8.16.0.22) with SMTP id w3T5OLWW004504 for ; Sat, 28 Apr 2018 22:28:24 -0700 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=fb.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-type; s=facebook; bh=S1fVtw9bGSYqTvdeh1tlxw9T3fLFtK6X/1+6rNOCfeE=; b=qvPfCGfx3DTD5iBb2sL6zVNKpogLB4cTOwRhCcffSR2XcJBCsx4XvW1IkBrnlvj+hPCV q7VSLLUVn6TUMAZNkiLcxzANd54UINGw9vPWCNqYxf9UiqUv7ORt+Lyszf724qDnR8Ef NCKIX95QJ8V4FUjy7ZkvB3XBY+18CACbIs0= Received: from mail.thefacebook.com ([199.201.64.23]) by mx0a-00082601.pphosted.com with ESMTP id 2hmpnh19q7-4 (version=TLSv1 cipher=ECDHE-RSA-AES256-SHA bits=256 verify=NOT) for ; Sat, 28 Apr 2018 22:28:24 -0700 Received: from mx-out.facebook.com (192.168.52.123) by PRN-CHUB01.TheFacebook.com (192.168.16.11) with Microsoft SMTP Server id 14.3.361.1; Sat, 28 Apr 2018 22:28:18 -0700 Received: by devbig474.prn1.facebook.com (Postfix, from userid 128203) id AE4B7E416DD; Sat, 28 Apr 2018 22:28:17 -0700 (PDT) Smtp-Origin-Hostprefix: devbig From: Yonghong Song Smtp-Origin-Hostname: devbig474.prn1.facebook.com To: , , CC: Smtp-Origin-Cluster: prn1c29 Subject: [PATCH bpf-next v9 09/10] tools/bpf: add a test for bpf_get_stack with raw tracepoint prog Date: Sat, 28 Apr 2018 22:28:15 -0700 Message-ID: <20180429052816.2882032-10-yhs@fb.com> X-Mailer: git-send-email 2.9.5 In-Reply-To: <20180429052816.2882032-1-yhs@fb.com> References: <20180429052816.2882032-1-yhs@fb.com> X-FB-Internal: Safe MIME-Version: 1.0 X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:, , definitions=2018-04-29_02:, , signatures=0 X-Proofpoint-Spam-Reason: safe X-FB-Internal: Safe Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org The test attached a raw_tracepoint program to raw_syscalls/sys_enter. It tested to get stack for user space, kernel space and user space with build_id request. It also tested to get user and kernel stack into the same buffer with back-to-back bpf_get_stack helper calls. If jit is not enabled, the user space application will check to ensure that the kernel function for raw_tracepoint ___bpf_prog_run is part of the stack. If jit is enabled, we did not have a reliable way to verify the kernel stack, so just assume the kernel stack is good when the kernel stack size is greater than 0. Signed-off-by: Yonghong Song --- tools/testing/selftests/bpf/Makefile | 4 +- tools/testing/selftests/bpf/test_get_stack_rawtp.c | 102 ++++++++++++ tools/testing/selftests/bpf/test_progs.c | 172 +++++++++++++++++++-- 3 files changed, 266 insertions(+), 12 deletions(-) create mode 100644 tools/testing/selftests/bpf/test_get_stack_rawtp.c diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index b64a7a3..9d76218 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -32,7 +32,8 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \ sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \ sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \ - test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o + test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \ + test_get_stack_rawtp.o # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ @@ -58,6 +59,7 @@ $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c $(OUTPUT)/test_sock: cgroup_helpers.c $(OUTPUT)/test_sock_addr: cgroup_helpers.c $(OUTPUT)/test_sockmap: cgroup_helpers.c +$(OUTPUT)/test_progs: trace_helpers.c .PHONY: force diff --git a/tools/testing/selftests/bpf/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/test_get_stack_rawtp.c new file mode 100644 index 0000000..f6d9f23 --- /dev/null +++ b/tools/testing/selftests/bpf/test_get_stack_rawtp.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include "bpf_helpers.h" + +/* Permit pretty deep stack traces */ +#define MAX_STACK_RAWTP 100 +struct stack_trace_t { + int pid; + int kern_stack_size; + int user_stack_size; + int user_stack_buildid_size; + __u64 kern_stack[MAX_STACK_RAWTP]; + __u64 user_stack[MAX_STACK_RAWTP]; + struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP]; +}; + +struct bpf_map_def SEC("maps") perfmap = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(__u32), + .max_entries = 2, +}; + +struct bpf_map_def SEC("maps") stackdata_map = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct stack_trace_t), + .max_entries = 1, +}; + +/* Allocate per-cpu space twice the needed. For the code below + * usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK); + * if (usize < 0) + * return 0; + * ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); + * + * If we have value_size = MAX_STACK_RAWTP * sizeof(__u64), + * verifier will complain that access "raw_data + usize" + * with size "max_len - usize" may be out of bound. + * The maximum "raw_data + usize" is "raw_data + max_len" + * and the maximum "max_len - usize" is "max_len", verifier + * concludes that the maximum buffer access range is + * "raw_data[0...max_len * 2 - 1]" and hence reject the program. + * + * Doubling the to-be-used max buffer size can fix this verifier + * issue and avoid complicated C programming massaging. + * This is an acceptable workaround since there is one entry here. + */ +struct bpf_map_def SEC("maps") rawdata_map = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = MAX_STACK_RAWTP * sizeof(__u64) * 2, + .max_entries = 1, +}; + +SEC("tracepoint/raw_syscalls/sys_enter") +int bpf_prog1(void *ctx) +{ + int max_len, max_buildid_len, usize, ksize, total_size; + struct stack_trace_t *data; + void *raw_data; + __u32 key = 0; + + data = bpf_map_lookup_elem(&stackdata_map, &key); + if (!data) + return 0; + + max_len = MAX_STACK_RAWTP * sizeof(__u64); + max_buildid_len = MAX_STACK_RAWTP * sizeof(struct bpf_stack_build_id); + data->pid = bpf_get_current_pid_tgid(); + data->kern_stack_size = bpf_get_stack(ctx, data->kern_stack, + max_len, 0); + data->user_stack_size = bpf_get_stack(ctx, data->user_stack, max_len, + BPF_F_USER_STACK); + data->user_stack_buildid_size = bpf_get_stack( + ctx, data->user_stack_buildid, max_buildid_len, + BPF_F_USER_STACK | BPF_F_USER_BUILD_ID); + bpf_perf_event_output(ctx, &perfmap, 0, data, sizeof(*data)); + + /* write both kernel and user stacks to the same buffer */ + raw_data = bpf_map_lookup_elem(&rawdata_map, &key); + if (!raw_data) + return 0; + + usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK); + if (usize < 0) + return 0; + + ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); + if (ksize < 0) + return 0; + + total_size = usize + ksize; + if (total_size > 0 && total_size <= max_len) + bpf_perf_event_output(ctx, &perfmap, 0, raw_data, total_size); + + return 0; +} + +char _license[] SEC("license") = "GPL"; +__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */ diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index eedda98..0ddbf34 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -38,8 +38,10 @@ typedef __u16 __sum16; #include "bpf_util.h" #include "bpf_endian.h" #include "bpf_rlimit.h" +#include "trace_helpers.h" static int error_cnt, pass_cnt; +static bool jit_enabled; #define MAGIC_BYTES 123 @@ -391,13 +393,30 @@ static inline __u64 ptr_to_u64(const void *ptr) return (__u64) (unsigned long) ptr; } +static bool is_jit_enabled(void) +{ + const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable"; + bool enabled = false; + int sysctl_fd; + + sysctl_fd = open(jit_sysctl, 0, O_RDONLY); + if (sysctl_fd != -1) { + char tmpc; + + if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1) + enabled = (tmpc != '0'); + close(sysctl_fd); + } + + return enabled; +} + static void test_bpf_obj_id(void) { const __u64 array_magic_value = 0xfaceb00c; const __u32 array_key = 0; const int nr_iters = 2; const char *file = "./test_obj_id.o"; - const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable"; const char *expected_prog_name = "test_obj_id"; const char *expected_map_name = "test_map_id"; const __u64 nsec_per_sec = 1000000000; @@ -414,20 +433,11 @@ static void test_bpf_obj_id(void) char jited_insns[128], xlated_insns[128], zeros[128]; __u32 i, next_id, info_len, nr_id_found, duration = 0; struct timespec real_time_ts, boot_time_ts; - int sysctl_fd, jit_enabled = 0, err = 0; + int err = 0; __u64 array_value; uid_t my_uid = getuid(); time_t now, load_time; - sysctl_fd = open(jit_sysctl, 0, O_RDONLY); - if (sysctl_fd != -1) { - char tmpc; - - if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1) - jit_enabled = (tmpc != '0'); - close(sysctl_fd); - } - err = bpf_prog_get_fd_by_id(0); CHECK(err >= 0 || errno != ENOENT, "get-fd-by-notexist-prog-id", "err %d errno %d\n", err, errno); @@ -1204,8 +1214,147 @@ static void test_stacktrace_build_id(void) return; } +#define MAX_CNT_RAWTP 10ull +#define MAX_STACK_RAWTP 100 +struct get_stack_trace_t { + int pid; + int kern_stack_size; + int user_stack_size; + int user_stack_buildid_size; + __u64 kern_stack[MAX_STACK_RAWTP]; + __u64 user_stack[MAX_STACK_RAWTP]; + struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP]; +}; + +static int get_stack_print_output(void *data, int size) +{ + bool good_kern_stack = false, good_user_stack = false; + const char *nonjit_func = "___bpf_prog_run"; + struct get_stack_trace_t *e = data; + int i, num_stack; + static __u64 cnt; + struct ksym *ks; + + cnt++; + + if (size < sizeof(struct get_stack_trace_t)) { + __u64 *raw_data = data; + bool found = false; + + num_stack = size / sizeof(__u64); + /* If jit is enabled, we do not have a good way to + * verify the sanity of the kernel stack. So we + * just assume it is good if the stack is not empty. + * This could be improved in the future. + */ + if (jit_enabled) { + found = num_stack > 0; + } else { + for (i = 0; i < num_stack; i++) { + ks = ksym_search(raw_data[i]); + if (strcmp(ks->name, nonjit_func) == 0) { + found = true; + break; + } + } + } + if (found) { + good_kern_stack = true; + good_user_stack = true; + } + } else { + num_stack = e->kern_stack_size / sizeof(__u64); + if (jit_enabled) { + good_kern_stack = num_stack > 0; + } else { + for (i = 0; i < num_stack; i++) { + ks = ksym_search(e->kern_stack[i]); + if (strcmp(ks->name, nonjit_func) == 0) { + good_kern_stack = true; + break; + } + } + } + if (e->user_stack_size > 0 && e->user_stack_buildid_size > 0) + good_user_stack = true; + } + if (!good_kern_stack || !good_user_stack) + return PERF_EVENT_ERROR; + + if (cnt == MAX_CNT_RAWTP) + return PERF_EVENT_DONE; + + return PERF_EVENT_CONT; +} + +static void test_get_stack_raw_tp(void) +{ + const char *file = "./test_get_stack_rawtp.o"; + int i, efd, err, prog_fd, pmu_fd, perfmap_fd; + struct perf_event_attr attr = {}; + struct timespec tv = {0, 10}; + __u32 key = 0, duration = 0; + struct bpf_object *obj; + + err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); + if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno)) + return; + + efd = bpf_raw_tracepoint_open("sys_enter", prog_fd); + if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno)) + goto close_prog; + + perfmap_fd = bpf_find_map(__func__, obj, "perfmap"); + if (CHECK(perfmap_fd < 0, "bpf_find_map", "err %d errno %d\n", + perfmap_fd, errno)) + goto close_prog; + + err = load_kallsyms(); + if (CHECK(err < 0, "load_kallsyms", "err %d errno %d\n", err, errno)) + goto close_prog; + + attr.sample_type = PERF_SAMPLE_RAW; + attr.type = PERF_TYPE_SOFTWARE; + attr.config = PERF_COUNT_SW_BPF_OUTPUT; + pmu_fd = syscall(__NR_perf_event_open, &attr, getpid()/*pid*/, -1/*cpu*/, + -1/*group_fd*/, 0); + if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd, + errno)) + goto close_prog; + + err = bpf_map_update_elem(perfmap_fd, &key, &pmu_fd, BPF_ANY); + if (CHECK(err < 0, "bpf_map_update_elem", "err %d errno %d\n", err, + errno)) + goto close_prog; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); + if (CHECK(err < 0, "ioctl PERF_EVENT_IOC_ENABLE", "err %d errno %d\n", + err, errno)) + goto close_prog; + + err = perf_event_mmap(pmu_fd); + if (CHECK(err < 0, "perf_event_mmap", "err %d errno %d\n", err, errno)) + goto close_prog; + + /* trigger some syscall action */ + for (i = 0; i < MAX_CNT_RAWTP; i++) + nanosleep(&tv, NULL); + + err = perf_event_poller(pmu_fd, get_stack_print_output); + if (CHECK(err < 0, "perf_event_poller", "err %d errno %d\n", err, errno)) + goto close_prog; + + goto close_prog_noerr; +close_prog: + error_cnt++; +close_prog_noerr: + bpf_object__close(obj); +} + int main(void) { + jit_enabled = is_jit_enabled(); + test_pkt_access(); test_xdp(); test_xdp_adjust_tail(); @@ -1219,6 +1368,7 @@ int main(void) test_stacktrace_map(); test_stacktrace_build_id(); test_stacktrace_map_raw_tp(); + test_get_stack_raw_tp(); printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt); return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;