diff options
Diffstat (limited to 'tools/testing/selftests')
246 files changed, 11878 insertions, 2647 deletions
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 90a62cf75008..6b456c5ecec1 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -4,6 +4,7 @@ TARGETS += amd-pstate TARGETS += arm64 TARGETS += bpf TARGETS += breakpoints +TARGETS += cachestat TARGETS += capabilities TARGETS += cgroup TARGETS += clone3 @@ -144,10 +145,12 @@ ifneq ($(KBUILD_OUTPUT),) abs_objtree := $(realpath $(abs_objtree)) BUILD := $(abs_objtree)/kselftest KHDR_INCLUDES := -isystem ${abs_objtree}/usr/include + KHDR_DIR := ${abs_objtree}/usr/include else BUILD := $(CURDIR) abs_srctree := $(shell cd $(top_srcdir) && pwd) KHDR_INCLUDES := -isystem ${abs_srctree}/usr/include + KHDR_DIR := ${abs_srctree}/usr/include DEFAULT_INSTALL_HDR_PATH := 1 endif @@ -161,7 +164,7 @@ export KHDR_INCLUDES # all isn't the first target in the file. .DEFAULT_GOAL := all -all: +all: kernel_header_files @ret=1; \ for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ @@ -172,6 +175,23 @@ all: ret=$$((ret * $$?)); \ done; exit $$ret; +kernel_header_files: + @ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null; \ + if [ $$? -ne 0 ]; then \ + RED='\033[1;31m'; \ + NOCOLOR='\033[0m'; \ + echo; \ + echo -e "$${RED}error$${NOCOLOR}: missing kernel header files."; \ + echo "Please run this and try again:"; \ + echo; \ + echo " cd $(top_srcdir)"; \ + echo " make headers"; \ + echo; \ + exit 1; \ + fi + +.PHONY: kernel_header_files + run_tests: all @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile index 901949db80ad..5af9ba8a4645 100644 --- a/tools/testing/selftests/alsa/Makefile +++ b/tools/testing/selftests/alsa/Makefile @@ -12,7 +12,7 @@ LDLIBS+=-lpthread OVERRIDE_TARGETS = 1 -TEST_GEN_PROGS := mixer-test pcm-test +TEST_GEN_PROGS := mixer-test pcm-test test-pcmtest-driver TEST_GEN_PROGS_EXTENDED := libatest.so diff --git a/tools/testing/selftests/alsa/pcm-test.c b/tools/testing/selftests/alsa/pcm-test.c index 3e390fe67eb9..b7eef32addb4 100644 --- a/tools/testing/selftests/alsa/pcm-test.c +++ b/tools/testing/selftests/alsa/pcm-test.c @@ -381,7 +381,7 @@ __format: goto __close; } if (rrate != rate) { - snprintf(msg, sizeof(msg), "rate mismatch %ld != %ld", rate, rrate); + snprintf(msg, sizeof(msg), "rate mismatch %ld != %d", rate, rrate); goto __close; } rperiod_size = period_size; @@ -447,24 +447,24 @@ __format: frames = snd_pcm_writei(handle, samples, rate); if (frames < 0) { snprintf(msg, sizeof(msg), - "Write failed: expected %d, wrote %li", rate, frames); + "Write failed: expected %ld, wrote %li", rate, frames); goto __close; } if (frames < rate) { snprintf(msg, sizeof(msg), - "expected %d, wrote %li", rate, frames); + "expected %ld, wrote %li", rate, frames); goto __close; } } else { frames = snd_pcm_readi(handle, samples, rate); if (frames < 0) { snprintf(msg, sizeof(msg), - "expected %d, wrote %li", rate, frames); + "expected %ld, wrote %li", rate, frames); goto __close; } if (frames < rate) { snprintf(msg, sizeof(msg), - "expected %d, wrote %li", rate, frames); + "expected %ld, wrote %li", rate, frames); goto __close; } } diff --git a/tools/testing/selftests/alsa/test-pcmtest-driver.c b/tools/testing/selftests/alsa/test-pcmtest-driver.c new file mode 100644 index 000000000000..71931b240a83 --- /dev/null +++ b/tools/testing/selftests/alsa/test-pcmtest-driver.c @@ -0,0 +1,333 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This is the test which covers PCM middle layer data transferring using + * the virtual pcm test driver (snd-pcmtest). + * + * Copyright 2023 Ivan Orlov <ivan.orlov0322@gmail.com> + */ +#include <string.h> +#include <alsa/asoundlib.h> +#include "../kselftest_harness.h" + +#define CH_NUM 4 + +struct pattern_buf { + char buf[1024]; + int len; +}; + +struct pattern_buf patterns[CH_NUM]; + +struct pcmtest_test_params { + unsigned long buffer_size; + unsigned long period_size; + unsigned long channels; + unsigned int rate; + snd_pcm_access_t access; + size_t sec_buf_len; + size_t sample_size; + int time; + snd_pcm_format_t format; +}; + +static int read_patterns(void) +{ + FILE *fp, *fpl; + int i; + char pf[64]; + char plf[64]; + + for (i = 0; i < CH_NUM; i++) { + sprintf(plf, "/sys/kernel/debug/pcmtest/fill_pattern%d_len", i); + fpl = fopen(plf, "r"); + if (!fpl) + return -1; + fscanf(fpl, "%u", &patterns[i].len); + fclose(fpl); + + sprintf(pf, "/sys/kernel/debug/pcmtest/fill_pattern%d", i); + fp = fopen(pf, "r"); + if (!fp) { + fclose(fpl); + return -1; + } + fread(patterns[i].buf, 1, patterns[i].len, fp); + fclose(fp); + } + + return 0; +} + +static int get_test_results(char *debug_name) +{ + int result; + FILE *f; + char fname[128]; + + sprintf(fname, "/sys/kernel/debug/pcmtest/%s", debug_name); + + f = fopen(fname, "r"); + if (!f) { + printf("Failed to open file\n"); + return -1; + } + fscanf(f, "%d", &result); + fclose(f); + + return result; +} + +static size_t get_sec_buf_len(unsigned int rate, unsigned long channels, snd_pcm_format_t format) +{ + return rate * channels * snd_pcm_format_physical_width(format) / 8; +} + +static int setup_handle(snd_pcm_t **handle, snd_pcm_sw_params_t *swparams, + snd_pcm_hw_params_t *hwparams, struct pcmtest_test_params *params, + int card, snd_pcm_stream_t stream) +{ + char pcm_name[32]; + int err; + + sprintf(pcm_name, "hw:%d,0,0", card); + err = snd_pcm_open(handle, pcm_name, stream, 0); + if (err < 0) + return err; + snd_pcm_hw_params_any(*handle, hwparams); + snd_pcm_hw_params_set_rate_resample(*handle, hwparams, 0); + snd_pcm_hw_params_set_access(*handle, hwparams, params->access); + snd_pcm_hw_params_set_format(*handle, hwparams, params->format); + snd_pcm_hw_params_set_channels(*handle, hwparams, params->channels); + snd_pcm_hw_params_set_rate_near(*handle, hwparams, ¶ms->rate, 0); + snd_pcm_hw_params_set_period_size_near(*handle, hwparams, ¶ms->period_size, 0); + snd_pcm_hw_params_set_buffer_size_near(*handle, hwparams, ¶ms->buffer_size); + snd_pcm_hw_params(*handle, hwparams); + snd_pcm_sw_params_current(*handle, swparams); + + snd_pcm_hw_params_set_rate_resample(*handle, hwparams, 0); + snd_pcm_sw_params_set_avail_min(*handle, swparams, params->period_size); + snd_pcm_hw_params_set_buffer_size_near(*handle, hwparams, ¶ms->buffer_size); + snd_pcm_hw_params_set_period_size_near(*handle, hwparams, ¶ms->period_size, 0); + snd_pcm_sw_params(*handle, swparams); + snd_pcm_hw_params(*handle, hwparams); + + return 0; +} + +FIXTURE(pcmtest) { + int card; + snd_pcm_sw_params_t *swparams; + snd_pcm_hw_params_t *hwparams; + struct pcmtest_test_params params; +}; + +FIXTURE_TEARDOWN(pcmtest) { +} + +FIXTURE_SETUP(pcmtest) { + char *card_name; + int err; + + if (geteuid()) + SKIP(exit(-1), "This test needs root to run!"); + + err = read_patterns(); + if (err) + SKIP(exit(-1), "Can't read patterns. Probably, module isn't loaded"); + + card_name = malloc(127); + ASSERT_NE(card_name, NULL); + self->params.buffer_size = 16384; + self->params.period_size = 4096; + self->params.channels = CH_NUM; + self->params.rate = 8000; + self->params.access = SND_PCM_ACCESS_RW_INTERLEAVED; + self->params.format = SND_PCM_FORMAT_S16_LE; + self->card = -1; + self->params.sample_size = snd_pcm_format_physical_width(self->params.format) / 8; + + self->params.sec_buf_len = get_sec_buf_len(self->params.rate, self->params.channels, + self->params.format); + self->params.time = 4; + + while (snd_card_next(&self->card) >= 0) { + if (self->card == -1) + break; + snd_card_get_name(self->card, &card_name); + if (!strcmp(card_name, "PCM-Test")) + break; + } + free(card_name); + ASSERT_NE(self->card, -1); +} + +/* + * Here we are trying to send the looped monotonically increasing sequence of bytes to the driver. + * If our data isn't corrupted, the driver will set the content of 'pc_test' debugfs file to '1' + */ +TEST_F(pcmtest, playback) { + snd_pcm_t *handle; + unsigned char *it; + size_t write_res; + int test_results; + int i, cur_ch, pos_in_ch; + void *samples; + struct pcmtest_test_params *params = &self->params; + + samples = calloc(self->params.sec_buf_len * self->params.time, 1); + ASSERT_NE(samples, NULL); + + snd_pcm_sw_params_alloca(&self->swparams); + snd_pcm_hw_params_alloca(&self->hwparams); + + ASSERT_EQ(setup_handle(&handle, self->swparams, self->hwparams, params, + self->card, SND_PCM_STREAM_PLAYBACK), 0); + snd_pcm_format_set_silence(params->format, samples, + params->rate * params->channels * params->time); + it = samples; + for (i = 0; i < self->params.sec_buf_len * params->time; i++) { + cur_ch = (i / params->sample_size) % CH_NUM; + pos_in_ch = i / params->sample_size / CH_NUM * params->sample_size + + (i % params->sample_size); + it[i] = patterns[cur_ch].buf[pos_in_ch % patterns[cur_ch].len]; + } + write_res = snd_pcm_writei(handle, samples, params->rate * params->time); + ASSERT_GE(write_res, 0); + + snd_pcm_close(handle); + free(samples); + test_results = get_test_results("pc_test"); + ASSERT_EQ(test_results, 1); +} + +/* + * Here we test that the virtual alsa driver returns looped and monotonically increasing sequence + * of bytes. In the interleaved mode the buffer will contain samples in the following order: + * C0, C1, C2, C3, C0, C1, ... + */ +TEST_F(pcmtest, capture) { + snd_pcm_t *handle; + unsigned char *it; + size_t read_res; + int i, cur_ch, pos_in_ch; + void *samples; + struct pcmtest_test_params *params = &self->params; + + samples = calloc(self->params.sec_buf_len * self->params.time, 1); + ASSERT_NE(samples, NULL); + + snd_pcm_sw_params_alloca(&self->swparams); + snd_pcm_hw_params_alloca(&self->hwparams); + + ASSERT_EQ(setup_handle(&handle, self->swparams, self->hwparams, + params, self->card, SND_PCM_STREAM_CAPTURE), 0); + snd_pcm_format_set_silence(params->format, samples, + params->rate * params->channels * params->time); + read_res = snd_pcm_readi(handle, samples, params->rate * params->time); + ASSERT_GE(read_res, 0); + snd_pcm_close(handle); + it = (unsigned char *)samples; + for (i = 0; i < self->params.sec_buf_len * self->params.time; i++) { + cur_ch = (i / params->sample_size) % CH_NUM; + pos_in_ch = i / params->sample_size / CH_NUM * params->sample_size + + (i % params->sample_size); + ASSERT_EQ(it[i], patterns[cur_ch].buf[pos_in_ch % patterns[cur_ch].len]); + } + free(samples); +} + +// Test capture in the non-interleaved access mode. The are buffers for each recorded channel +TEST_F(pcmtest, ni_capture) { + snd_pcm_t *handle; + struct pcmtest_test_params params = self->params; + char **chan_samples; + size_t i, j, read_res; + + chan_samples = calloc(CH_NUM, sizeof(*chan_samples)); + ASSERT_NE(chan_samples, NULL); + + snd_pcm_sw_params_alloca(&self->swparams); + snd_pcm_hw_params_alloca(&self->hwparams); + + params.access = SND_PCM_ACCESS_RW_NONINTERLEAVED; + + ASSERT_EQ(setup_handle(&handle, self->swparams, self->hwparams, + ¶ms, self->card, SND_PCM_STREAM_CAPTURE), 0); + + for (i = 0; i < CH_NUM; i++) + chan_samples[i] = calloc(params.sec_buf_len * params.time, 1); + + for (i = 0; i < 1; i++) { + read_res = snd_pcm_readn(handle, (void **)chan_samples, params.rate * params.time); + ASSERT_GE(read_res, 0); + } + snd_pcm_close(handle); + + for (i = 0; i < CH_NUM; i++) { + for (j = 0; j < params.rate * params.time; j++) + ASSERT_EQ(chan_samples[i][j], patterns[i].buf[j % patterns[i].len]); + free(chan_samples[i]); + } + free(chan_samples); +} + +TEST_F(pcmtest, ni_playback) { + snd_pcm_t *handle; + struct pcmtest_test_params params = self->params; + char **chan_samples; + size_t i, j, read_res; + int test_res; + + chan_samples = calloc(CH_NUM, sizeof(*chan_samples)); + ASSERT_NE(chan_samples, NULL); + + snd_pcm_sw_params_alloca(&self->swparams); + snd_pcm_hw_params_alloca(&self->hwparams); + + params.access = SND_PCM_ACCESS_RW_NONINTERLEAVED; + + ASSERT_EQ(setup_handle(&handle, self->swparams, self->hwparams, + ¶ms, self->card, SND_PCM_STREAM_PLAYBACK), 0); + + for (i = 0; i < CH_NUM; i++) { + chan_samples[i] = calloc(params.sec_buf_len * params.time, 1); + for (j = 0; j < params.sec_buf_len * params.time; j++) + chan_samples[i][j] = patterns[i].buf[j % patterns[i].len]; + } + + for (i = 0; i < 1; i++) { + read_res = snd_pcm_writen(handle, (void **)chan_samples, params.rate * params.time); + ASSERT_GE(read_res, 0); + } + + snd_pcm_close(handle); + test_res = get_test_results("pc_test"); + ASSERT_EQ(test_res, 1); + + for (i = 0; i < CH_NUM; i++) + free(chan_samples[i]); + free(chan_samples); +} + +/* + * Here we are testing the custom ioctl definition inside the virtual driver. If it triggers + * successfully, the driver sets the content of 'ioctl_test' debugfs file to '1'. + */ +TEST_F(pcmtest, reset_ioctl) { + snd_pcm_t *handle; + unsigned char *it; + int test_res; + struct pcmtest_test_params *params = &self->params; + + snd_pcm_sw_params_alloca(&self->swparams); + snd_pcm_hw_params_alloca(&self->hwparams); + + ASSERT_EQ(setup_handle(&handle, self->swparams, self->hwparams, params, + self->card, SND_PCM_STREAM_CAPTURE), 0); + snd_pcm_reset(handle); + test_res = get_test_results("ioctl_test"); + ASSERT_EQ(test_res, 1); + snd_pcm_close(handle); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index 93333a90bf3a..d4ad813fed10 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -39,6 +39,20 @@ static void cssc_sigill(void) asm volatile(".inst 0xdac01c00" : : : "x0"); } +static void mops_sigill(void) +{ + char dst[1], src[1]; + register char *dstp asm ("x0") = dst; + register char *srcp asm ("x1") = src; + register long size asm ("x2") = 1; + + /* CPYP [x0]!, [x1]!, x2! */ + asm volatile(".inst 0x1d010440" + : "+r" (dstp), "+r" (srcp), "+r" (size) + : + : "cc", "memory"); +} + static void rng_sigill(void) { asm volatile("mrs x0, S3_3_C2_C4_0" : : : "x0"); @@ -210,6 +224,14 @@ static const struct hwcap_data { .sigill_fn = cssc_sigill, }, { + .name = "MOPS", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_MOPS, + .cpuinfo = "mops", + .sigill_fn = mops_sigill, + .sigill_reliable = true, + }, + { .name = "RNG", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_RNG, diff --git a/tools/testing/selftests/arm64/abi/ptrace.c b/tools/testing/selftests/arm64/abi/ptrace.c index be952511af22..abe4d58d731d 100644 --- a/tools/testing/selftests/arm64/abi/ptrace.c +++ b/tools/testing/selftests/arm64/abi/ptrace.c @@ -20,7 +20,7 @@ #include "../../kselftest.h" -#define EXPECTED_TESTS 7 +#define EXPECTED_TESTS 11 #define MAX_TPIDRS 2 @@ -132,6 +132,34 @@ static void test_tpidr(pid_t child) } } +static void test_hw_debug(pid_t child, int type, const char *type_name) +{ + struct user_hwdebug_state state; + struct iovec iov; + int slots, arch, ret; + + iov.iov_len = sizeof(state); + iov.iov_base = &state; + + /* Should be able to read the values */ + ret = ptrace(PTRACE_GETREGSET, child, type, &iov); + ksft_test_result(ret == 0, "read_%s\n", type_name); + + if (ret == 0) { + /* Low 8 bits is the number of slots, next 4 bits the arch */ + slots = state.dbg_info & 0xff; + arch = (state.dbg_info >> 8) & 0xf; + + ksft_print_msg("%s version %d with %d slots\n", type_name, + arch, slots); + + /* Zero is not currently architecturally valid */ + ksft_test_result(arch, "%s_arch_set\n", type_name); + } else { + ksft_test_result_skip("%s_arch_set\n"); + } +} + static int do_child(void) { if (ptrace(PTRACE_TRACEME, -1, NULL, NULL)) @@ -207,6 +235,8 @@ static int do_parent(pid_t child) ksft_print_msg("Parent is %d, child is %d\n", getpid(), child); test_tpidr(child); + test_hw_debug(child, NT_ARM_HW_WATCH, "NT_ARM_HW_WATCH"); + test_hw_debug(child, NT_ARM_HW_BREAK, "NT_ARM_HW_BREAK"); ret = EXIT_SUCCESS; diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore index 8ab4c86837fd..839e3a252629 100644 --- a/tools/testing/selftests/arm64/signal/.gitignore +++ b/tools/testing/selftests/arm64/signal/.gitignore @@ -4,7 +4,7 @@ fake_sigreturn_* sme_* ssve_* sve_* -tpidr2_siginfo +tpidr2_* za_* zt_* !*.[ch] diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 40be8443949d..0dc948db3a4a 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -249,7 +249,8 @@ static void default_handler(int signum, siginfo_t *si, void *uc) fprintf(stderr, "-- Timeout !\n"); } else { fprintf(stderr, - "-- RX UNEXPECTED SIGNAL: %d\n", signum); + "-- RX UNEXPECTED SIGNAL: %d code %d address %p\n", + signum, si->si_code, si->si_addr); } default_result(current, 1); } diff --git a/tools/testing/selftests/arm64/signal/testcases/tpidr2_restore.c b/tools/testing/selftests/arm64/signal/testcases/tpidr2_restore.c new file mode 100644 index 000000000000..f9a86c00c28c --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/tpidr2_restore.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 ARM Limited + * + * Verify that the TPIDR2 register context in signal frames is restored. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/auxv.h> +#include <sys/prctl.h> +#include <unistd.h> +#include <asm/sigcontext.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +#define SYS_TPIDR2 "S3_3_C13_C0_5" + +static uint64_t get_tpidr2(void) +{ + uint64_t val; + + asm volatile ( + "mrs %0, " SYS_TPIDR2 "\n" + : "=r"(val) + : + : "cc"); + + return val; +} + +static void set_tpidr2(uint64_t val) +{ + asm volatile ( + "msr " SYS_TPIDR2 ", %0\n" + : + : "r"(val) + : "cc"); +} + + +static uint64_t initial_tpidr2; + +static bool save_tpidr2(struct tdescr *td) +{ + initial_tpidr2 = get_tpidr2(); + fprintf(stderr, "Initial TPIDR2: %lx\n", initial_tpidr2); + + return true; +} + +static int modify_tpidr2(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + uint64_t my_tpidr2 = get_tpidr2(); + + my_tpidr2++; + fprintf(stderr, "Setting TPIDR2 to %lx\n", my_tpidr2); + set_tpidr2(my_tpidr2); + + return 0; +} + +static void check_tpidr2(struct tdescr *td) +{ + uint64_t tpidr2 = get_tpidr2(); + + td->pass = tpidr2 == initial_tpidr2; + + if (td->pass) + fprintf(stderr, "TPIDR2 restored\n"); + else + fprintf(stderr, "TPIDR2 was %lx but is now %lx\n", + initial_tpidr2, tpidr2); +} + +struct tdescr tde = { + .name = "TPIDR2 restore", + .descr = "Validate that TPIDR2 is restored from the sigframe", + .feats_required = FEAT_SME, + .timeout = 3, + .sig_trig = SIGUSR1, + .init = save_tpidr2, + .run = modify_tpidr2, + .check_result = check_tpidr2, +}; diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64 index 0a6837f97c32..08adc805878b 100644 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ b/tools/testing/selftests/bpf/DENYLIST.aarch64 @@ -1,33 +1,6 @@ -bloom_filter_map # libbpf: prog 'check_bloom': failed to attach: ERROR: strerror_r(-524)=22 -bpf_cookie/lsm -bpf_cookie/multi_kprobe_attach_api -bpf_cookie/multi_kprobe_link_api -bpf_cookie/trampoline -bpf_loop/check_callback_fn_stop # link unexpected error: -524 -bpf_loop/check_invalid_flags -bpf_loop/check_nested_calls -bpf_loop/check_non_constant_callback -bpf_loop/check_nr_loops -bpf_loop/check_null_callback_ctx -bpf_loop/check_stack -bpf_mod_race # bpf_mod_kfunc_race__attach unexpected error: -524 (errno 524) -bpf_tcp_ca/dctcp_fallback -btf_dump/btf_dump: var_data # find type id unexpected find type id: actual -2 < expected 0 -cgroup_hierarchical_stats # attach unexpected error: -524 (errno 524) -d_path/basic # setup attach failed: -524 -deny_namespace # attach unexpected error: -524 (errno 524) -fentry_fexit # fentry_attach unexpected error: -1 (errno 524) -fentry_test # fentry_attach unexpected error: -1 (errno 524) -fexit_sleep # fexit_attach fexit attach failed: -1 -fexit_stress # fexit attach unexpected fexit attach: actual -524 < expected 0 -fexit_test # fexit_attach unexpected error: -1 (errno 524) -get_func_args_test # get_func_args_test__attach unexpected error: -524 (errno 524) (trampoline) -get_func_ip_test # get_func_ip_test__attach unexpected error: -524 (errno 524) (trampoline) -htab_update/reenter_update -kfree_skb # attach fentry unexpected error: -524 (trampoline) -kfunc_call/subprog # extern (var ksym) 'bpf_prog_active': not found in kernel BTF -kfunc_call/subprog_lskel # skel unexpected error: -2 -kfunc_dynptr_param/dynptr_data_null # libbpf: prog 'dynptr_data_null': failed to attach: ERROR: strerror_r(-524)=22 +bpf_cookie/multi_kprobe_attach_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3 +bpf_cookie/multi_kprobe_link_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3 +fexit_sleep # The test never returns. The remaining tests cannot start. kprobe_multi_bench_attach # bpf_program__attach_kprobe_multi_opts unexpected error: -95 kprobe_multi_test/attach_api_addrs # bpf_program__attach_kprobe_multi_opts unexpected error: -95 kprobe_multi_test/attach_api_pattern # bpf_program__attach_kprobe_multi_opts unexpected error: -95 @@ -35,51 +8,5 @@ kprobe_multi_test/attach_api_syms # bpf_program__attach_kprobe_mu kprobe_multi_test/bench_attach # bpf_program__attach_kprobe_multi_opts unexpected error: -95 kprobe_multi_test/link_api_addrs # link_fd unexpected link_fd: actual -95 < expected 0 kprobe_multi_test/link_api_syms # link_fd unexpected link_fd: actual -95 < expected 0 -kprobe_multi_test/skel_api # kprobe_multi__attach unexpected error: -524 (errno 524) -ksyms_module/libbpf # 'bpf_testmod_ksym_percpu': not found in kernel BTF -ksyms_module/lskel # test_ksyms_module_lskel__open_and_load unexpected error: -2 -libbpf_get_fd_by_id_opts # test_libbpf_get_fd_by_id_opts__attach unexpected error: -524 (errno 524) -linked_list -lookup_key # test_lookup_key__attach unexpected error: -524 (errno 524) -lru_bug # lru_bug__attach unexpected error: -524 (errno 524) -modify_return # modify_return__attach failed unexpected error: -524 (errno 524) -module_attach # skel_attach skeleton attach failed: -524 -module_fentry_shadow # bpf_link_create unexpected bpf_link_create: actual -524 < expected 0 -mptcp/base # run_test mptcp unexpected error: -524 (errno 524) -netcnt # packets unexpected packets: actual 10001 != expected 10000 -rcu_read_lock # failed to attach: ERROR: strerror_r(-524)=22 -recursion # skel_attach unexpected error: -524 (errno 524) -ringbuf # skel_attach skeleton attachment failed: -1 -setget_sockopt # attach_cgroup unexpected error: -524 -sk_storage_tracing # test_sk_storage_tracing__attach unexpected error: -524 (errno 524) -skc_to_unix_sock # could not attach BPF object unexpected error: -524 (errno 524) -socket_cookie # prog_attach unexpected error: -524 -stacktrace_build_id # compare_stack_ips stackmap vs. stack_amap err -1 errno 2 -task_local_storage/exit_creds # skel_attach unexpected error: -524 (errno 524) -task_local_storage/recursion # skel_attach unexpected error: -524 (errno 524) -test_bprm_opts # attach attach failed: -524 -test_ima # attach attach failed: -524 -test_local_storage # attach lsm attach failed: -524 -test_lsm # test_lsm_first_attach unexpected error: -524 (errno 524) -test_overhead # attach_fentry unexpected error: -524 -timer # timer unexpected error: -524 (errno 524) -timer_crash # timer_crash__attach unexpected error: -524 (errno 524) -timer_mim # timer_mim unexpected error: -524 (errno 524) -trace_printk # trace_printk__attach unexpected error: -1 (errno 524) -trace_vprintk # trace_vprintk__attach unexpected error: -1 (errno 524) -tracing_struct # tracing_struct__attach unexpected error: -524 (errno 524) -trampoline_count # attach_prog unexpected error: -524 -unpriv_bpf_disabled # skel_attach unexpected error: -524 (errno 524) -user_ringbuf/test_user_ringbuf_post_misaligned # misaligned_skel unexpected error: -524 (errno 524) -user_ringbuf/test_user_ringbuf_post_producer_wrong_offset -user_ringbuf/test_user_ringbuf_post_larger_than_ringbuf_sz -user_ringbuf/test_user_ringbuf_basic # ringbuf_basic_skel unexpected error: -524 (errno 524) -user_ringbuf/test_user_ringbuf_sample_full_ring_buffer -user_ringbuf/test_user_ringbuf_post_alignment_autoadjust -user_ringbuf/test_user_ringbuf_overfill -user_ringbuf/test_user_ringbuf_discards_properly_ignored -user_ringbuf/test_user_ringbuf_loop -user_ringbuf/test_user_ringbuf_msg_protocol -user_ringbuf/test_user_ringbuf_blocking_reserve -verify_pkcs7_sig # test_verify_pkcs7_sig__attach unexpected error: -524 (errno 524) -vmlinux # skel_attach skeleton attach failed: -524 +kprobe_multi_test/skel_api # libbpf: failed to load BPF skeleton 'kprobe_multi': -3 +module_attach # prog 'kprobe_multi': failed to auto-attach: -95 diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x index c7463f3ec3c0..5061d9e24c16 100644 --- a/tools/testing/selftests/bpf/DENYLIST.s390x +++ b/tools/testing/selftests/bpf/DENYLIST.s390x @@ -26,3 +26,4 @@ user_ringbuf # failed to find kernel BTF type ID of verif_stats # trace_vprintk__open_and_load unexpected error: -9 (?) xdp_bonding # failed to auto-attach program 'trace_on_entry': -524 (trampoline) xdp_metadata # JIT does not support calling kernel function (kfunc) +test_task_under_cgroup # JIT does not support calling kernel function (kfunc) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index c49e5403ad0e..538df8fb8c42 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -88,8 +88,7 @@ TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \ xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \ xdp_features -TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read $(OUTPUT)/sign-file -TEST_GEN_FILES += liburandom_read.so +TEST_GEN_FILES += liburandom_read.so urandom_read sign-file # Emit succinct information message describing current building step # $1 - generic step name (e.g., CC, LINK, etc); @@ -197,7 +196,7 @@ $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_r $(OUTPUT)/sign-file: ../../../../scripts/sign-file.c $(call msg,SIGN-FILE,,$@) - $(Q)$(CC) $(shell $(HOSTPKG_CONFIG)--cflags libcrypto 2> /dev/null) \ + $(Q)$(CC) $(shell $(HOSTPKG_CONFIG) --cflags libcrypto 2> /dev/null) \ $< -o $@ \ $(shell $(HOSTPKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto) diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index d9c080ac1796..41fe5a82b88b 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -17,7 +17,7 @@ struct env env = { .duration_sec = 5, .affinity = false, .quiet = false, - .consumer_cnt = 1, + .consumer_cnt = 0, .producer_cnt = 1, }; @@ -441,12 +441,14 @@ static void setup_timer() static void set_thread_affinity(pthread_t thread, int cpu) { cpu_set_t cpuset; + int err; CPU_ZERO(&cpuset); CPU_SET(cpu, &cpuset); - if (pthread_setaffinity_np(thread, sizeof(cpuset), &cpuset)) { + err = pthread_setaffinity_np(thread, sizeof(cpuset), &cpuset); + if (err) { fprintf(stderr, "setting affinity to CPU #%d failed: %d\n", - cpu, errno); + cpu, -err); exit(1); } } @@ -467,7 +469,7 @@ static int next_cpu(struct cpu_set *cpu_set) exit(1); } - return cpu_set->next_cpu++; + return cpu_set->next_cpu++ % env.nr_cpus; } static struct bench_state { @@ -605,7 +607,7 @@ static void setup_benchmark(void) bench->consumer_thread, (void *)(long)i); if (err) { fprintf(stderr, "failed to create consumer thread #%d: %d\n", - i, -errno); + i, -err); exit(1); } if (env.affinity) @@ -624,7 +626,7 @@ static void setup_benchmark(void) bench->producer_thread, (void *)(long)i); if (err) { fprintf(stderr, "failed to create producer thread #%d: %d\n", - i, -errno); + i, -err); exit(1); } if (env.affinity) @@ -657,6 +659,7 @@ static void collect_measurements(long delta_ns) { int main(int argc, char **argv) { + env.nr_cpus = get_nprocs(); parse_cmdline_args_init(argc, argv); if (env.list) { diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h index 402729c6a3ac..7ff32be3d730 100644 --- a/tools/testing/selftests/bpf/bench.h +++ b/tools/testing/selftests/bpf/bench.h @@ -27,6 +27,7 @@ struct env { bool quiet; int consumer_cnt; int producer_cnt; + int nr_cpus; struct cpu_set prod_cpus; struct cpu_set cons_cpus; }; diff --git a/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c b/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c index 7c8ccc108313..e289dd1a14ee 100644 --- a/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c +++ b/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c @@ -107,9 +107,9 @@ const struct argp bench_bloom_map_argp = { static void validate(void) { - if (env.consumer_cnt != 1) { + if (env.consumer_cnt != 0) { fprintf(stderr, - "The bloom filter benchmarks do not support multi-consumer use\n"); + "The bloom filter benchmarks do not support consumer\n"); exit(1); } } @@ -421,18 +421,12 @@ static void measure(struct bench_res *res) last_false_hits = total_false_hits; } -static void *consumer(void *input) -{ - return NULL; -} - const struct bench bench_bloom_lookup = { .name = "bloom-lookup", .argp = &bench_bloom_map_argp, .validate = validate, .setup = bloom_lookup_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -444,7 +438,6 @@ const struct bench bench_bloom_update = { .validate = validate, .setup = bloom_update_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -456,7 +449,6 @@ const struct bench bench_bloom_false_positive = { .validate = validate, .setup = false_positive_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = false_hits_report_progress, .report_final = false_hits_report_final, @@ -468,7 +460,6 @@ const struct bench bench_hashmap_without_bloom = { .validate = validate, .setup = hashmap_no_bloom_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -480,7 +471,6 @@ const struct bench bench_hashmap_with_bloom = { .validate = validate, .setup = hashmap_with_bloom_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c index 75abe8137b6c..ee1dc12c5e5e 100644 --- a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c +++ b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c @@ -14,8 +14,8 @@ static struct ctx { static void validate(void) { - if (env.consumer_cnt != 1) { - fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer!\n"); exit(1); } } @@ -30,11 +30,6 @@ static void *producer(void *input) return NULL; } -static void *consumer(void *input) -{ - return NULL; -} - static void measure(struct bench_res *res) { } @@ -88,7 +83,6 @@ const struct bench bench_bpf_hashmap_full_update = { .validate = validate, .setup = setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = NULL, .report_final = hashmap_report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c index 8dbb02f75cff..279ff1b8b5b2 100644 --- a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c +++ b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c @@ -113,8 +113,8 @@ const struct argp bench_hashmap_lookup_argp = { static void validate(void) { - if (env.consumer_cnt != 1) { - fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer!\n"); exit(1); } @@ -134,11 +134,6 @@ static void *producer(void *input) return NULL; } -static void *consumer(void *input) -{ - return NULL; -} - static void measure(struct bench_res *res) { } @@ -276,7 +271,6 @@ const struct bench bench_bpf_hashmap_lookup = { .validate = validate, .setup = setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = NULL, .report_final = hashmap_report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c b/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c index d8a0394e10b1..a705cfb2bccc 100644 --- a/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c +++ b/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c @@ -47,8 +47,8 @@ const struct argp bench_bpf_loop_argp = { static void validate(void) { - if (env.consumer_cnt != 1) { - fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer!\n"); exit(1); } } @@ -62,11 +62,6 @@ static void *producer(void *input) return NULL; } -static void *consumer(void *input) -{ - return NULL; -} - static void measure(struct bench_res *res) { res->hits = atomic_swap(&ctx.skel->bss->hits, 0); @@ -99,7 +94,6 @@ const struct bench bench_bpf_loop = { .validate = validate, .setup = setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = ops_report_progress, .report_final = ops_report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_count.c b/tools/testing/selftests/bpf/benchs/bench_count.c index 078972ce208e..ba89ed3936b7 100644 --- a/tools/testing/selftests/bpf/benchs/bench_count.c +++ b/tools/testing/selftests/bpf/benchs/bench_count.c @@ -18,11 +18,6 @@ static void *count_global_producer(void *input) return NULL; } -static void *count_global_consumer(void *input) -{ - return NULL; -} - static void count_global_measure(struct bench_res *res) { struct count_global_ctx *ctx = &count_global_ctx; @@ -40,7 +35,7 @@ static void count_local_setup(void) { struct count_local_ctx *ctx = &count_local_ctx; - ctx->hits = calloc(env.consumer_cnt, sizeof(*ctx->hits)); + ctx->hits = calloc(env.producer_cnt, sizeof(*ctx->hits)); if (!ctx->hits) exit(1); } @@ -56,11 +51,6 @@ static void *count_local_producer(void *input) return NULL; } -static void *count_local_consumer(void *input) -{ - return NULL; -} - static void count_local_measure(struct bench_res *res) { struct count_local_ctx *ctx = &count_local_ctx; @@ -74,7 +64,6 @@ static void count_local_measure(struct bench_res *res) const struct bench bench_count_global = { .name = "count-global", .producer_thread = count_global_producer, - .consumer_thread = count_global_consumer, .measure = count_global_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -84,7 +73,6 @@ const struct bench bench_count_local = { .name = "count-local", .setup = count_local_setup, .producer_thread = count_local_producer, - .consumer_thread = count_local_consumer, .measure = count_local_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_local_storage.c b/tools/testing/selftests/bpf/benchs/bench_local_storage.c index d4b2817306d4..452499428ceb 100644 --- a/tools/testing/selftests/bpf/benchs/bench_local_storage.c +++ b/tools/testing/selftests/bpf/benchs/bench_local_storage.c @@ -74,8 +74,8 @@ static void validate(void) fprintf(stderr, "benchmark doesn't support multi-producer!\n"); exit(1); } - if (env.consumer_cnt != 1) { - fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer!\n"); exit(1); } @@ -230,11 +230,6 @@ static inline void trigger_bpf_program(void) syscall(__NR_getpgid); } -static void *consumer(void *input) -{ - return NULL; -} - static void *producer(void *input) { while (true) @@ -259,7 +254,6 @@ const struct bench bench_local_storage_cache_seq_get = { .validate = validate, .setup = local_storage_cache_get_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = local_storage_report_progress, .report_final = local_storage_report_final, @@ -271,7 +265,6 @@ const struct bench bench_local_storage_cache_interleaved_get = { .validate = validate, .setup = local_storage_cache_get_interleaved_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = local_storage_report_progress, .report_final = local_storage_report_final, @@ -283,7 +276,6 @@ const struct bench bench_local_storage_cache_hashmap_control = { .validate = validate, .setup = hashmap_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = local_storage_report_progress, .report_final = local_storage_report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c b/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c index cff703f90e95..b36de42ee4d9 100644 --- a/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c +++ b/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c @@ -71,7 +71,7 @@ const struct argp bench_local_storage_create_argp = { static void validate(void) { - if (env.consumer_cnt > 1) { + if (env.consumer_cnt != 0) { fprintf(stderr, "local-storage-create benchmark does not need consumer\n"); exit(1); @@ -143,11 +143,6 @@ static void measure(struct bench_res *res) res->drops = atomic_swap(&skel->bss->kmalloc_cnts, 0); } -static void *consumer(void *input) -{ - return NULL; -} - static void *sk_producer(void *input) { struct thread *t = &threads[(long)(input)]; @@ -257,7 +252,6 @@ const struct bench bench_local_storage_create = { .validate = validate, .setup = setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = report_progress, .report_final = report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c b/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c index d5eb5587f2aa..edf0b00418c1 100644 --- a/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c +++ b/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c @@ -72,8 +72,8 @@ static void validate(void) fprintf(stderr, "benchmark doesn't support multi-producer!\n"); exit(1); } - if (env.consumer_cnt != 1) { - fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer!\n"); exit(1); } @@ -197,11 +197,6 @@ static void measure(struct bench_res *res) ctx.prev_kthread_stime = ticks; } -static void *consumer(void *input) -{ - return NULL; -} - static void *producer(void *input) { while (true) @@ -262,7 +257,6 @@ const struct bench bench_local_storage_tasks_trace = { .validate = validate, .setup = local_storage_tasks_trace_setup, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = report_progress, .report_final = report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_rename.c b/tools/testing/selftests/bpf/benchs/bench_rename.c index 3c203b6d6a6e..bf66893c7a33 100644 --- a/tools/testing/selftests/bpf/benchs/bench_rename.c +++ b/tools/testing/selftests/bpf/benchs/bench_rename.c @@ -17,8 +17,8 @@ static void validate(void) fprintf(stderr, "benchmark doesn't support multi-producer!\n"); exit(1); } - if (env.consumer_cnt != 1) { - fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer!\n"); exit(1); } } @@ -106,17 +106,11 @@ static void setup_fexit(void) attach_bpf(ctx.skel->progs.prog5); } -static void *consumer(void *input) -{ - return NULL; -} - const struct bench bench_rename_base = { .name = "rename-base", .validate = validate, .setup = setup_base, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -127,7 +121,6 @@ const struct bench bench_rename_kprobe = { .validate = validate, .setup = setup_kprobe, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -138,7 +131,6 @@ const struct bench bench_rename_kretprobe = { .validate = validate, .setup = setup_kretprobe, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -149,7 +141,6 @@ const struct bench bench_rename_rawtp = { .validate = validate, .setup = setup_rawtp, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -160,7 +151,6 @@ const struct bench bench_rename_fentry = { .validate = validate, .setup = setup_fentry, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -171,7 +161,6 @@ const struct bench bench_rename_fexit = { .validate = validate, .setup = setup_fexit, .producer_thread = producer, - .consumer_thread = consumer, .measure = measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c index fc91fdac4faa..3ca14ad36607 100644 --- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c +++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c @@ -96,7 +96,7 @@ static inline void bufs_trigger_batch(void) static void bufs_validate(void) { if (env.consumer_cnt != 1) { - fprintf(stderr, "rb-libbpf benchmark doesn't support multi-consumer!\n"); + fprintf(stderr, "rb-libbpf benchmark needs one consumer!\n"); exit(1); } diff --git a/tools/testing/selftests/bpf/benchs/bench_strncmp.c b/tools/testing/selftests/bpf/benchs/bench_strncmp.c index d3fad2ba6916..a5e1428fd7a0 100644 --- a/tools/testing/selftests/bpf/benchs/bench_strncmp.c +++ b/tools/testing/selftests/bpf/benchs/bench_strncmp.c @@ -50,8 +50,8 @@ const struct argp bench_strncmp_argp = { static void strncmp_validate(void) { - if (env.consumer_cnt != 1) { - fprintf(stderr, "strncmp benchmark doesn't support multi-consumer!\n"); + if (env.consumer_cnt != 0) { + fprintf(stderr, "strncmp benchmark doesn't support consumer!\n"); exit(1); } } @@ -128,11 +128,6 @@ static void *strncmp_producer(void *ctx) return NULL; } -static void *strncmp_consumer(void *ctx) -{ - return NULL; -} - static void strncmp_measure(struct bench_res *res) { res->hits = atomic_swap(&ctx.skel->bss->hits, 0); @@ -144,7 +139,6 @@ const struct bench bench_strncmp_no_helper = { .validate = strncmp_validate, .setup = strncmp_no_helper_setup, .producer_thread = strncmp_producer, - .consumer_thread = strncmp_consumer, .measure = strncmp_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -156,7 +150,6 @@ const struct bench bench_strncmp_helper = { .validate = strncmp_validate, .setup = strncmp_helper_setup, .producer_thread = strncmp_producer, - .consumer_thread = strncmp_consumer, .measure = strncmp_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c index 0c481de2833d..dbd362771d6a 100644 --- a/tools/testing/selftests/bpf/benchs/bench_trigger.c +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -13,8 +13,8 @@ static struct counter base_hits; static void trigger_validate(void) { - if (env.consumer_cnt != 1) { - fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer!\n"); exit(1); } } @@ -103,11 +103,6 @@ static void trigger_fmodret_setup(void) attach_bpf(ctx.skel->progs.bench_trigger_fmodret); } -static void *trigger_consumer(void *input) -{ - return NULL; -} - /* make sure call is not inlined and not avoided by compiler, so __weak and * inline asm volatile in the body of the function * @@ -205,7 +200,6 @@ const struct bench bench_trig_base = { .name = "trig-base", .validate = trigger_validate, .producer_thread = trigger_base_producer, - .consumer_thread = trigger_consumer, .measure = trigger_base_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -216,7 +210,6 @@ const struct bench bench_trig_tp = { .validate = trigger_validate, .setup = trigger_tp_setup, .producer_thread = trigger_producer, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -227,7 +220,6 @@ const struct bench bench_trig_rawtp = { .validate = trigger_validate, .setup = trigger_rawtp_setup, .producer_thread = trigger_producer, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -238,7 +230,6 @@ const struct bench bench_trig_kprobe = { .validate = trigger_validate, .setup = trigger_kprobe_setup, .producer_thread = trigger_producer, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -249,7 +240,6 @@ const struct bench bench_trig_fentry = { .validate = trigger_validate, .setup = trigger_fentry_setup, .producer_thread = trigger_producer, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -260,7 +250,6 @@ const struct bench bench_trig_fentry_sleep = { .validate = trigger_validate, .setup = trigger_fentry_sleep_setup, .producer_thread = trigger_producer, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -271,7 +260,6 @@ const struct bench bench_trig_fmodret = { .validate = trigger_validate, .setup = trigger_fmodret_setup, .producer_thread = trigger_producer, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -281,7 +269,6 @@ const struct bench bench_trig_uprobe_base = { .name = "trig-uprobe-base", .setup = NULL, /* no uprobe/uretprobe is attached */ .producer_thread = uprobe_base_producer, - .consumer_thread = trigger_consumer, .measure = trigger_base_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -291,7 +278,6 @@ const struct bench bench_trig_uprobe_with_nop = { .name = "trig-uprobe-with-nop", .setup = uprobe_setup_with_nop, .producer_thread = uprobe_producer_with_nop, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -301,7 +287,6 @@ const struct bench bench_trig_uretprobe_with_nop = { .name = "trig-uretprobe-with-nop", .setup = uretprobe_setup_with_nop, .producer_thread = uprobe_producer_with_nop, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -311,7 +296,6 @@ const struct bench bench_trig_uprobe_without_nop = { .name = "trig-uprobe-without-nop", .setup = uprobe_setup_without_nop, .producer_thread = uprobe_producer_without_nop, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, @@ -321,7 +305,6 @@ const struct bench bench_trig_uretprobe_without_nop = { .name = "trig-uretprobe-without-nop", .setup = uretprobe_setup_without_nop, .producer_thread = uprobe_producer_without_nop, - .consumer_thread = trigger_consumer, .measure = trigger_measure, .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, diff --git a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh index ada028aa9007..91e3567962ff 100755 --- a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh +++ b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh @@ -4,46 +4,48 @@ source ./benchs/run_common.sh set -eufo pipefail +RUN_RB_BENCH="$RUN_BENCH -c1" + header "Single-producer, parallel producer" for b in rb-libbpf rb-custom pb-libbpf pb-custom; do - summarize $b "$($RUN_BENCH $b)" + summarize $b "$($RUN_RB_BENCH $b)" done header "Single-producer, parallel producer, sampled notification" for b in rb-libbpf rb-custom pb-libbpf pb-custom; do - summarize $b "$($RUN_BENCH --rb-sampled $b)" + summarize $b "$($RUN_RB_BENCH --rb-sampled $b)" done header "Single-producer, back-to-back mode" for b in rb-libbpf rb-custom pb-libbpf pb-custom; do - summarize $b "$($RUN_BENCH --rb-b2b $b)" - summarize $b-sampled "$($RUN_BENCH --rb-sampled --rb-b2b $b)" + summarize $b "$($RUN_RB_BENCH --rb-b2b $b)" + summarize $b-sampled "$($RUN_RB_BENCH --rb-sampled --rb-b2b $b)" done header "Ringbuf back-to-back, effect of sample rate" for b in 1 5 10 25 50 100 250 500 1000 2000 3000; do - summarize "rb-sampled-$b" "$($RUN_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b rb-custom)" + summarize "rb-sampled-$b" "$($RUN_RB_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b rb-custom)" done header "Perfbuf back-to-back, effect of sample rate" for b in 1 5 10 25 50 100 250 500 1000 2000 3000; do - summarize "pb-sampled-$b" "$($RUN_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b pb-custom)" + summarize "pb-sampled-$b" "$($RUN_RB_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b pb-custom)" done header "Ringbuf back-to-back, reserve+commit vs output" -summarize "reserve" "$($RUN_BENCH --rb-b2b rb-custom)" -summarize "output" "$($RUN_BENCH --rb-b2b --rb-use-output rb-custom)" +summarize "reserve" "$($RUN_RB_BENCH --rb-b2b rb-custom)" +summarize "output" "$($RUN_RB_BENCH --rb-b2b --rb-use-output rb-custom)" header "Ringbuf sampled, reserve+commit vs output" -summarize "reserve-sampled" "$($RUN_BENCH --rb-sampled rb-custom)" -summarize "output-sampled" "$($RUN_BENCH --rb-sampled --rb-use-output rb-custom)" +summarize "reserve-sampled" "$($RUN_RB_BENCH --rb-sampled rb-custom)" +summarize "output-sampled" "$($RUN_RB_BENCH --rb-sampled --rb-use-output rb-custom)" header "Single-producer, consumer/producer competing on the same CPU, low batch count" for b in rb-libbpf rb-custom pb-libbpf pb-custom; do - summarize $b "$($RUN_BENCH --rb-batch-cnt 1 --rb-sample-rate 1 --prod-affinity 0 --cons-affinity 0 $b)" + summarize $b "$($RUN_RB_BENCH --rb-batch-cnt 1 --rb-sample-rate 1 --prod-affinity 0 --cons-affinity 0 $b)" done header "Ringbuf, multi-producer contention" for b in 1 2 3 4 8 12 16 20 24 28 32 36 40 44 48 52; do - summarize "rb-libbpf nr_prod $b" "$($RUN_BENCH -p$b --rb-batch-cnt 50 rb-libbpf)" + summarize "rb-libbpf nr_prod $b" "$($RUN_RB_BENCH -p$b --rb-batch-cnt 50 rb-libbpf)" done diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h index 8c993ec8ceea..642dda0e758a 100644 --- a/tools/testing/selftests/bpf/bpf_kfuncs.h +++ b/tools/testing/selftests/bpf/bpf_kfuncs.h @@ -35,4 +35,10 @@ extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, __u32 offset, extern void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *ptr, __u32 offset, void *buffer, __u32 buffer__szk) __ksym; +extern int bpf_dynptr_adjust(const struct bpf_dynptr *ptr, __u32 start, __u32 end) __ksym; +extern bool bpf_dynptr_is_null(const struct bpf_dynptr *ptr) __ksym; +extern bool bpf_dynptr_is_rdonly(const struct bpf_dynptr *ptr) __ksym; +extern __u32 bpf_dynptr_size(const struct bpf_dynptr *ptr) __ksym; +extern int bpf_dynptr_clone(const struct bpf_dynptr *ptr, struct bpf_dynptr *clone__init) __ksym; + #endif diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 52785ba671e6..aaf6ef1201c7 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -9,6 +9,7 @@ #include <linux/sysfs.h> #include <linux/tracepoint.h> #include "bpf_testmod.h" +#include "bpf_testmod_kfunc.h" #define CREATE_TRACE_POINTS #include "bpf_testmod-events.h" @@ -190,8 +191,6 @@ noinline int bpf_testmod_fentry_test3(char a, int b, u64 c) return a + b + c; } -__diag_pop(); - int bpf_testmod_fentry_ok; noinline ssize_t @@ -272,6 +271,14 @@ bpf_testmod_test_write(struct file *file, struct kobject *kobj, EXPORT_SYMBOL(bpf_testmod_test_write); ALLOW_ERROR_INJECTION(bpf_testmod_test_write, ERRNO); +noinline int bpf_fentry_shadow_test(int a) +{ + return a + 2; +} +EXPORT_SYMBOL_GPL(bpf_fentry_shadow_test); + +__diag_pop(); + static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = { .attr = { .name = "bpf_testmod", .mode = 0666, }, .read = bpf_testmod_test_read, @@ -289,8 +296,171 @@ static const struct btf_kfunc_id_set bpf_testmod_common_kfunc_set = { .set = &bpf_testmod_common_kfunc_ids, }; +__bpf_kfunc u64 bpf_kfunc_call_test1(struct sock *sk, u32 a, u64 b, u32 c, u64 d) +{ + return a + b + c + d; +} + +__bpf_kfunc int bpf_kfunc_call_test2(struct sock *sk, u32 a, u32 b) +{ + return a + b; +} + +__bpf_kfunc struct sock *bpf_kfunc_call_test3(struct sock *sk) +{ + return sk; +} + +__bpf_kfunc long noinline bpf_kfunc_call_test4(signed char a, short b, int c, long d) +{ + /* Provoke the compiler to assume that the caller has sign-extended a, + * b and c on platforms where this is required (e.g. s390x). + */ + return (long)a + (long)b + (long)c + d; +} + +static struct prog_test_ref_kfunc prog_test_struct = { + .a = 42, + .b = 108, + .next = &prog_test_struct, + .cnt = REFCOUNT_INIT(1), +}; + +__bpf_kfunc struct prog_test_ref_kfunc * +bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) +{ + refcount_inc(&prog_test_struct.cnt); + return &prog_test_struct; +} + +__bpf_kfunc void bpf_kfunc_call_test_offset(struct prog_test_ref_kfunc *p) +{ + WARN_ON_ONCE(1); +} + +__bpf_kfunc struct prog_test_member * +bpf_kfunc_call_memb_acquire(void) +{ + WARN_ON_ONCE(1); + return NULL; +} + +__bpf_kfunc void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p) +{ + WARN_ON_ONCE(1); +} + +static int *__bpf_kfunc_call_test_get_mem(struct prog_test_ref_kfunc *p, const int size) +{ + if (size > 2 * sizeof(int)) + return NULL; + + return (int *)p; +} + +__bpf_kfunc int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, + const int rdwr_buf_size) +{ + return __bpf_kfunc_call_test_get_mem(p, rdwr_buf_size); +} + +__bpf_kfunc int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, + const int rdonly_buf_size) +{ + return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size); +} + +/* the next 2 ones can't be really used for testing expect to ensure + * that the verifier rejects the call. + * Acquire functions must return struct pointers, so these ones are + * failing. + */ +__bpf_kfunc int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, + const int rdonly_buf_size) +{ + return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size); +} + +__bpf_kfunc void bpf_kfunc_call_int_mem_release(int *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_mem_len_pass1(void *mem, int mem__sz) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) +{ + /* p != NULL, but p->cnt could be 0 */ +} + +__bpf_kfunc void bpf_kfunc_call_test_destructive(void) +{ +} + +__bpf_kfunc static u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) +{ + return arg; +} + BTF_SET8_START(bpf_testmod_check_kfunc_ids) BTF_ID_FLAGS(func, bpf_testmod_test_mod_kfunc) +BTF_ID_FLAGS(func, bpf_kfunc_call_test1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test2) +BTF_ID_FLAGS(func, bpf_kfunc_call_test3) +BTF_ID_FLAGS(func, bpf_kfunc_call_test4) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_pass1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail2) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_acquire, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_memb_acquire, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_memb1_release, KF_RELEASE) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_get_rdwr_mem, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_get_rdonly_mem, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_acq_rdonly_mem, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_int_mem_release, KF_RELEASE) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass_ctx) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass2) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail2) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail3) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_ref, KF_TRUSTED_ARGS | KF_RCU) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset) BTF_SET8_END(bpf_testmod_check_kfunc_ids) static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = { @@ -298,12 +468,6 @@ static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = { .set = &bpf_testmod_check_kfunc_ids, }; -noinline int bpf_fentry_shadow_test(int a) -{ - return a + 2; -} -EXPORT_SYMBOL_GPL(bpf_fentry_shadow_test); - extern int bpf_fentry_test1(int a); static int bpf_testmod_init(void) @@ -312,6 +476,8 @@ static int bpf_testmod_init(void) ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &bpf_testmod_common_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_testmod_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_testmod_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &bpf_testmod_kfunc_set); if (ret < 0) return ret; if (bpf_fentry_test1(0) < 0) diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h new file mode 100644 index 000000000000..f5c5b1375c24 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _BPF_TESTMOD_KFUNC_H +#define _BPF_TESTMOD_KFUNC_H + +#ifndef __KERNEL__ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#else +#define __ksym +struct prog_test_member1 { + int a; +}; + +struct prog_test_member { + struct prog_test_member1 m; + int c; +}; + +struct prog_test_ref_kfunc { + int a; + int b; + struct prog_test_member memb; + struct prog_test_ref_kfunc *next; + refcount_t cnt; +}; +#endif + +struct prog_test_pass1 { + int x0; + struct { + int x1; + struct { + int x2; + struct { + int x3; + }; + }; + }; +}; + +struct prog_test_pass2 { + int len; + short arr1[4]; + struct { + char arr2[4]; + unsigned long arr3[8]; + } x; +}; + +struct prog_test_fail1 { + void *p; + int x; +}; + +struct prog_test_fail2 { + int x8; + struct prog_test_pass1 x; +}; + +struct prog_test_fail3 { + int len; + char arr1[2]; + char arr2[]; +}; + +struct prog_test_ref_kfunc * +bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) __ksym; +void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; +void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) __ksym; + +void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; +int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym; +int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; +int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; +void bpf_kfunc_call_int_mem_release(int *p) __ksym; + +/* The bpf_kfunc_call_test_static_unused_arg is defined as static, + * but bpf program compilation needs to see it as global symbol. + */ +#ifndef __KERNEL__ +u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) __ksym; +#endif + +void bpf_testmod_test_mod_kfunc(int i) __ksym; + +__u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, + __u32 c, __u64 d) __ksym; +int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; +struct sock *bpf_kfunc_call_test3(struct sock *sk) __ksym; +long bpf_kfunc_call_test4(signed char a, short b, int c, long d) __ksym; + +void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) __ksym; +void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) __ksym; +void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) __ksym; +void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym; + +void bpf_kfunc_call_test_destructive(void) __ksym; + +void bpf_kfunc_call_test_offset(struct prog_test_ref_kfunc *p); +struct prog_test_member *bpf_kfunc_call_memb_acquire(void); +void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p); +void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p); +void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p); +void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p); +void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len); +#endif /* _BPF_TESTMOD_KFUNC_H */ diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 63cd4ab70171..3b350bc31343 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -13,6 +13,9 @@ CONFIG_CGROUP_BPF=y CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_USER_API_HASH=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_BTF=y +CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DYNAMIC_FTRACE=y CONFIG_FPROBE=y CONFIG_FTRACE_SYSCALLS=y @@ -60,6 +63,7 @@ CONFIG_NET_SCH_INGRESS=y CONFIG_NET_SCHED=y CONFIG_NETDEVSIM=y CONFIG_NETFILTER=y +CONFIG_NETFILTER_ADVANCED=y CONFIG_NETFILTER_SYNPROXY=y CONFIG_NETFILTER_XT_CONNMARK=y CONFIG_NETFILTER_XT_MATCH_STATE=y diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 596caa176582..a105c0cd008a 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -427,3 +427,26 @@ void close_netns(struct nstoken *token) close(token->orig_netns_fd); free(token); } + +int get_socket_local_port(int sock_fd) +{ + struct sockaddr_storage addr; + socklen_t addrlen = sizeof(addr); + int err; + + err = getsockname(sock_fd, (struct sockaddr *)&addr, &addrlen); + if (err < 0) + return err; + + if (addr.ss_family == AF_INET) { + struct sockaddr_in *sin = (struct sockaddr_in *)&addr; + + return sin->sin_port; + } else if (addr.ss_family == AF_INET6) { + struct sockaddr_in6 *sin = (struct sockaddr_in6 *)&addr; + + return sin->sin6_port; + } + + return -1; +} diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index f882c691b790..694185644da6 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -56,6 +56,7 @@ int fastopen_connect(int server_fd, const char *data, unsigned int data_len, int make_sockaddr(int family, const char *addr_str, __u16 port, struct sockaddr_storage *addr, socklen_t *len); char *ping_command(int family); +int get_socket_local_port(int sock_fd); struct nstoken; /** diff --git a/tools/testing/selftests/bpf/prog_tests/arg_parsing.c b/tools/testing/selftests/bpf/prog_tests/arg_parsing.c index b17bfa0e0aac..bb143de68875 100644 --- a/tools/testing/selftests/bpf/prog_tests/arg_parsing.c +++ b/tools/testing/selftests/bpf/prog_tests/arg_parsing.c @@ -96,12 +96,80 @@ static void test_parse_test_list(void) goto error; ASSERT_OK(strcmp("*bpf_cookie*", set.tests[0].name), "test name"); ASSERT_OK(strcmp("*trace*", set.tests[0].subtests[0]), "subtest name"); + free_test_filter_set(&set); + + ASSERT_OK(parse_test_list("t/subtest1,t/subtest2", &set, true), + "parsing"); + if (!ASSERT_EQ(set.cnt, 1, "count of test filters")) + goto error; + if (!ASSERT_OK_PTR(set.tests, "test filters initialized")) + goto error; + if (!ASSERT_EQ(set.tests[0].subtest_cnt, 2, "subtest filters count")) + goto error; + ASSERT_OK(strcmp("t", set.tests[0].name), "test name"); + ASSERT_OK(strcmp("subtest1", set.tests[0].subtests[0]), "subtest name"); + ASSERT_OK(strcmp("subtest2", set.tests[0].subtests[1]), "subtest name"); error: free_test_filter_set(&set); } +static void test_parse_test_list_file(void) +{ + struct test_filter_set set; + char tmpfile[80]; + FILE *fp; + int fd; + + snprintf(tmpfile, sizeof(tmpfile), "/tmp/bpf_arg_parsing_test.XXXXXX"); + fd = mkstemp(tmpfile); + if (!ASSERT_GE(fd, 0, "create tmp")) + return; + + fp = fdopen(fd, "w"); + if (!ASSERT_NEQ(fp, NULL, "fdopen tmp")) { + close(fd); + goto out_remove; + } + + fprintf(fp, "# comment\n"); + fprintf(fp, " test_with_spaces \n"); + fprintf(fp, "testA/subtest # comment\n"); + fprintf(fp, "testB#comment with no space\n"); + fprintf(fp, "testB # duplicate\n"); + fprintf(fp, "testA/subtest # subtest duplicate\n"); + fprintf(fp, "testA/subtest2\n"); + fprintf(fp, "testC_no_eof_newline"); + fflush(fp); + + if (!ASSERT_OK(ferror(fp), "prepare tmp")) + goto out_fclose; + + init_test_filter_set(&set); + + ASSERT_OK(parse_test_list_file(tmpfile, &set, true), "parse file"); + + ASSERT_EQ(set.cnt, 4, "test count"); + ASSERT_OK(strcmp("test_with_spaces", set.tests[0].name), "test 0 name"); + ASSERT_EQ(set.tests[0].subtest_cnt, 0, "test 0 subtest count"); + ASSERT_OK(strcmp("testA", set.tests[1].name), "test 1 name"); + ASSERT_EQ(set.tests[1].subtest_cnt, 2, "test 1 subtest count"); + ASSERT_OK(strcmp("subtest", set.tests[1].subtests[0]), "test 1 subtest 0"); + ASSERT_OK(strcmp("subtest2", set.tests[1].subtests[1]), "test 1 subtest 1"); + ASSERT_OK(strcmp("testB", set.tests[2].name), "test 2 name"); + ASSERT_OK(strcmp("testC_no_eof_newline", set.tests[3].name), "test 3 name"); + + free_test_filter_set(&set); + +out_fclose: + fclose(fp); +out_remove: + remove(tmpfile); +} + void test_arg_parsing(void) { if (test__start_subtest("test_parse_test_list")) test_parse_test_list(); + if (test__start_subtest("test_parse_test_list_file")) + test_parse_test_list_file(); } diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c index a4d0cc9d3367..fe2c502e5089 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c @@ -11,6 +11,7 @@ #include "ksym_race.skel.h" #include "bpf_mod_race.skel.h" #include "kfunc_call_race.skel.h" +#include "testing_helpers.h" /* This test crafts a race between btf_try_get_module and do_init_module, and * checks whether btf_try_get_module handles the invocation for a well-formed @@ -44,35 +45,10 @@ enum bpf_test_state { static _Atomic enum bpf_test_state state = _TS_INVALID; -static int sys_finit_module(int fd, const char *param_values, int flags) -{ - return syscall(__NR_finit_module, fd, param_values, flags); -} - -static int sys_delete_module(const char *name, unsigned int flags) -{ - return syscall(__NR_delete_module, name, flags); -} - -static int load_module(const char *mod) -{ - int ret, fd; - - fd = open("bpf_testmod.ko", O_RDONLY); - if (fd < 0) - return fd; - - ret = sys_finit_module(fd, "", 0); - close(fd); - if (ret < 0) - return ret; - return 0; -} - static void *load_module_thread(void *p) { - if (!ASSERT_NEQ(load_module("bpf_testmod.ko"), 0, "load_module_thread must fail")) + if (!ASSERT_NEQ(load_bpf_testmod(false), 0, "load_module_thread must fail")) atomic_store(&state, TS_MODULE_LOAD); else atomic_store(&state, TS_MODULE_LOAD_FAIL); @@ -124,7 +100,7 @@ static void test_bpf_mod_race_config(const struct test_config *config) if (!ASSERT_NEQ(fault_addr, MAP_FAILED, "mmap for uffd registration")) return; - if (!ASSERT_OK(sys_delete_module("bpf_testmod", 0), "unload bpf_testmod")) + if (!ASSERT_OK(unload_bpf_testmod(false), "unload bpf_testmod")) goto end_mmap; skel = bpf_mod_race__open(); @@ -202,8 +178,8 @@ end_destroy: bpf_mod_race__destroy(skel); ASSERT_OK(kern_sync_rcu(), "kern_sync_rcu"); end_module: - sys_delete_module("bpf_testmod", 0); - ASSERT_OK(load_module("bpf_testmod.ko"), "restore bpf_testmod"); + unload_bpf_testmod(false); + ASSERT_OK(load_bpf_testmod(false), "restore bpf_testmod"); end_mmap: munmap(fault_addr, 4096); atomic_store(&state, _TS_INVALID); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c new file mode 100644 index 000000000000..31f1e815f671 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c @@ -0,0 +1,268 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#define _GNU_SOURCE +#include <test_progs.h> +#include <bpf/btf.h> +#include <fcntl.h> +#include <unistd.h> +#include <linux/unistd.h> +#include <linux/mount.h> +#include <sys/syscall.h> + +static inline int sys_fsopen(const char *fsname, unsigned flags) +{ + return syscall(__NR_fsopen, fsname, flags); +} + +static inline int sys_fsconfig(int fs_fd, unsigned cmd, const char *key, const void *val, int aux) +{ + return syscall(__NR_fsconfig, fs_fd, cmd, key, val, aux); +} + +static inline int sys_fsmount(int fs_fd, unsigned flags, unsigned ms_flags) +{ + return syscall(__NR_fsmount, fs_fd, flags, ms_flags); +} + +__attribute__((unused)) +static inline int sys_move_mount(int from_dfd, const char *from_path, + int to_dfd, const char *to_path, + unsigned int ms_flags) +{ + return syscall(__NR_move_mount, from_dfd, from_path, to_dfd, to_path, ms_flags); +} + +static void bpf_obj_pinning_detached(void) +{ + LIBBPF_OPTS(bpf_obj_pin_opts, pin_opts); + LIBBPF_OPTS(bpf_obj_get_opts, get_opts); + int fs_fd = -1, mnt_fd = -1; + int map_fd = -1, map_fd2 = -1; + int zero = 0, src_value, dst_value, err; + const char *map_name = "fsmount_map"; + + /* A bunch of below UAPI calls are constructed based on reading: + * https://brauner.io/2023/02/28/mounting-into-mount-namespaces.html + */ + + /* create VFS context */ + fs_fd = sys_fsopen("bpf", 0); + if (!ASSERT_GE(fs_fd, 0, "fs_fd")) + goto cleanup; + + /* instantiate FS object */ + err = sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); + if (!ASSERT_OK(err, "fs_create")) + goto cleanup; + + /* create O_PATH fd for detached mount */ + mnt_fd = sys_fsmount(fs_fd, 0, 0); + if (!ASSERT_GE(mnt_fd, 0, "mnt_fd")) + goto cleanup; + + /* If we wanted to expose detached mount in the file system, we'd do + * something like below. But the whole point is that we actually don't + * even have to expose BPF FS in the file system to be able to work + * (pin/get objects) with it. + * + * err = sys_move_mount(mnt_fd, "", -EBADF, mnt_path, MOVE_MOUNT_F_EMPTY_PATH); + * if (!ASSERT_OK(err, "move_mount")) + * goto cleanup; + */ + + /* create BPF map to pin */ + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, map_name, 4, 4, 1, NULL); + if (!ASSERT_GE(map_fd, 0, "map_fd")) + goto cleanup; + + /* pin BPF map into detached BPF FS through mnt_fd */ + pin_opts.file_flags = BPF_F_PATH_FD; + pin_opts.path_fd = mnt_fd; + err = bpf_obj_pin_opts(map_fd, map_name, &pin_opts); + if (!ASSERT_OK(err, "map_pin")) + goto cleanup; + + /* get BPF map from detached BPF FS through mnt_fd */ + get_opts.file_flags = BPF_F_PATH_FD; + get_opts.path_fd = mnt_fd; + map_fd2 = bpf_obj_get_opts(map_name, &get_opts); + if (!ASSERT_GE(map_fd2, 0, "map_get")) + goto cleanup; + + /* update map through one FD */ + src_value = 0xcafebeef; + err = bpf_map_update_elem(map_fd, &zero, &src_value, 0); + ASSERT_OK(err, "map_update"); + + /* check values written/read through different FDs do match */ + dst_value = 0; + err = bpf_map_lookup_elem(map_fd2, &zero, &dst_value); + ASSERT_OK(err, "map_lookup"); + ASSERT_EQ(dst_value, src_value, "map_value_eq1"); + ASSERT_EQ(dst_value, 0xcafebeef, "map_value_eq2"); + +cleanup: + if (map_fd >= 0) + ASSERT_OK(close(map_fd), "close_map_fd"); + if (map_fd2 >= 0) + ASSERT_OK(close(map_fd2), "close_map_fd2"); + if (fs_fd >= 0) + ASSERT_OK(close(fs_fd), "close_fs_fd"); + if (mnt_fd >= 0) + ASSERT_OK(close(mnt_fd), "close_mnt_fd"); +} + +enum path_kind +{ + PATH_STR_ABS, + PATH_STR_REL, + PATH_FD_REL, +}; + +static void validate_pin(int map_fd, const char *map_name, int src_value, + enum path_kind path_kind) +{ + LIBBPF_OPTS(bpf_obj_pin_opts, pin_opts); + char abs_path[PATH_MAX], old_cwd[PATH_MAX]; + const char *pin_path = NULL; + int zero = 0, dst_value, map_fd2, err; + + snprintf(abs_path, sizeof(abs_path), "/sys/fs/bpf/%s", map_name); + old_cwd[0] = '\0'; + + switch (path_kind) { + case PATH_STR_ABS: + /* absolute path */ + pin_path = abs_path; + break; + case PATH_STR_REL: + /* cwd + relative path */ + ASSERT_OK_PTR(getcwd(old_cwd, sizeof(old_cwd)), "getcwd"); + ASSERT_OK(chdir("/sys/fs/bpf"), "chdir"); + pin_path = map_name; + break; + case PATH_FD_REL: + /* dir fd + relative path */ + pin_opts.file_flags = BPF_F_PATH_FD; + pin_opts.path_fd = open("/sys/fs/bpf", O_PATH); + ASSERT_GE(pin_opts.path_fd, 0, "path_fd"); + pin_path = map_name; + break; + } + + /* pin BPF map using specified path definition */ + err = bpf_obj_pin_opts(map_fd, pin_path, &pin_opts); + ASSERT_OK(err, "obj_pin"); + + /* cleanup */ + if (pin_opts.path_fd >= 0) + close(pin_opts.path_fd); + if (old_cwd[0]) + ASSERT_OK(chdir(old_cwd), "restore_cwd"); + + map_fd2 = bpf_obj_get(abs_path); + if (!ASSERT_GE(map_fd2, 0, "map_get")) + goto cleanup; + + /* update map through one FD */ + err = bpf_map_update_elem(map_fd, &zero, &src_value, 0); + ASSERT_OK(err, "map_update"); + + /* check values written/read through different FDs do match */ + dst_value = 0; + err = bpf_map_lookup_elem(map_fd2, &zero, &dst_value); + ASSERT_OK(err, "map_lookup"); + ASSERT_EQ(dst_value, src_value, "map_value_eq"); +cleanup: + if (map_fd2 >= 0) + ASSERT_OK(close(map_fd2), "close_map_fd2"); + unlink(abs_path); +} + +static void validate_get(int map_fd, const char *map_name, int src_value, + enum path_kind path_kind) +{ + LIBBPF_OPTS(bpf_obj_get_opts, get_opts); + char abs_path[PATH_MAX], old_cwd[PATH_MAX]; + const char *pin_path = NULL; + int zero = 0, dst_value, map_fd2, err; + + snprintf(abs_path, sizeof(abs_path), "/sys/fs/bpf/%s", map_name); + /* pin BPF map using specified path definition */ + err = bpf_obj_pin(map_fd, abs_path); + if (!ASSERT_OK(err, "pin_map")) + return; + + old_cwd[0] = '\0'; + + switch (path_kind) { + case PATH_STR_ABS: + /* absolute path */ + pin_path = abs_path; + break; + case PATH_STR_REL: + /* cwd + relative path */ + ASSERT_OK_PTR(getcwd(old_cwd, sizeof(old_cwd)), "getcwd"); + ASSERT_OK(chdir("/sys/fs/bpf"), "chdir"); + pin_path = map_name; + break; + case PATH_FD_REL: + /* dir fd + relative path */ + get_opts.file_flags = BPF_F_PATH_FD; + get_opts.path_fd = open("/sys/fs/bpf", O_PATH); + ASSERT_GE(get_opts.path_fd, 0, "path_fd"); + pin_path = map_name; + break; + } + + map_fd2 = bpf_obj_get_opts(pin_path, &get_opts); + if (!ASSERT_GE(map_fd2, 0, "map_get")) + goto cleanup; + + /* cleanup */ + if (get_opts.path_fd >= 0) + close(get_opts.path_fd); + if (old_cwd[0]) + ASSERT_OK(chdir(old_cwd), "restore_cwd"); + + /* update map through one FD */ + err = bpf_map_update_elem(map_fd, &zero, &src_value, 0); + ASSERT_OK(err, "map_update"); + + /* check values written/read through different FDs do match */ + dst_value = 0; + err = bpf_map_lookup_elem(map_fd2, &zero, &dst_value); + ASSERT_OK(err, "map_lookup"); + ASSERT_EQ(dst_value, src_value, "map_value_eq"); +cleanup: + if (map_fd2 >= 0) + ASSERT_OK(close(map_fd2), "close_map_fd2"); + unlink(abs_path); +} + +static void bpf_obj_pinning_mounted(enum path_kind path_kind) +{ + const char *map_name = "mounted_map"; + int map_fd; + + /* create BPF map to pin */ + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, map_name, 4, 4, 1, NULL); + if (!ASSERT_GE(map_fd, 0, "map_fd")) + return; + + validate_pin(map_fd, map_name, 100 + (int)path_kind, path_kind); + validate_get(map_fd, map_name, 200 + (int)path_kind, path_kind); + ASSERT_OK(close(map_fd), "close_map_fd"); +} + +void test_bpf_obj_pinning() +{ + if (test__start_subtest("detached")) + bpf_obj_pinning_detached(); + if (test__start_subtest("mounted-str-abs")) + bpf_obj_pinning_mounted(PATH_STR_ABS); + if (test__start_subtest("mounted-str-rel")) + bpf_obj_pinning_mounted(PATH_STR_REL); + if (test__start_subtest("mounted-fd-rel")) + bpf_obj_pinning_mounted(PATH_FD_REL); +} diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 210d643fda6c..4e0cdb593318 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -3991,6 +3991,46 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid arg#1", }, { + .descr = "decl_tag test #18, decl_tag as the map key type", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_STRUCT_ENC(0, 2, 8), /* [2] */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_MEMBER_ENC(NAME_TBD, 1, 32), + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), /* [3] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0m1\0m2\0tag"), + .map_type = BPF_MAP_TYPE_HASH, + .map_name = "tag_type_check_btf", + .key_size = 8, + .value_size = 4, + .key_type_id = 3, + .value_type_id = 1, + .max_entries = 1, + .map_create_err = true, +}, +{ + .descr = "decl_tag test #19, decl_tag as the map value type", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_STRUCT_ENC(0, 2, 8), /* [2] */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_MEMBER_ENC(NAME_TBD, 1, 32), + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), /* [3] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0m1\0m2\0tag"), + .map_type = BPF_MAP_TYPE_HASH, + .map_name = "tag_type_check_btf", + .key_size = 4, + .value_size = 8, + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 1, + .map_create_err = true, +}, +{ .descr = "type_tag test #1", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c index 4d2fa99273d8..2bb5773d6f99 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c @@ -25,6 +25,8 @@ static void test_setsockopt_set(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that sets EUNATCH, assert that * we actually get that error when we run setsockopt() */ @@ -59,6 +61,8 @@ static void test_setsockopt_set_and_get(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that sets EUNATCH, and one that gets the * previously set errno. Assert that we get the same errno back. */ @@ -100,6 +104,8 @@ static void test_setsockopt_default_zero(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that gets the previously set errno. * Assert that, without anything setting one, we get 0. */ @@ -134,6 +140,8 @@ static void test_setsockopt_default_zero_and_set(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that gets the previously set errno, and then * one that sets the errno to EUNATCH. Assert that the get does not * see EUNATCH set later, and does not prevent EUNATCH from being set. @@ -177,6 +185,8 @@ static void test_setsockopt_override(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that sets EUNATCH, then one that sets EISCONN, * and then one that gets the exported errno. Assert both the syscall * and the helper sees the last set errno. @@ -224,6 +234,8 @@ static void test_setsockopt_legacy_eperm(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that return a reject without setting errno * (legacy reject), and one that gets the errno. Assert that for * backward compatibility the syscall result in EPERM, and this @@ -268,6 +280,8 @@ static void test_setsockopt_legacy_no_override(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that sets EUNATCH, then one that return a reject * without setting errno, and then one that gets the exported errno. * Assert both the syscall and the helper's errno are unaffected by @@ -319,6 +333,8 @@ static void test_getsockopt_get(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach getsockopt that gets previously set errno. Assert that the * error from kernel is in both ctx_retval_value and retval_value. */ @@ -359,6 +375,8 @@ static void test_getsockopt_override(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach getsockopt that sets retval to -EISCONN. Assert that this * overrides the value from kernel. */ @@ -396,6 +414,8 @@ static void test_getsockopt_retval_sync(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach getsockopt that sets retval to -EISCONN, and one that clears * ctx retval. Assert that the clearing ctx retval is synced to helper * and clears any errors both from kernel and BPF.. diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c index 5338d2ea0460..2a9a30650350 100644 --- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c +++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c @@ -183,7 +183,7 @@ cleanup: void serial_test_check_mtu(void) { - __u32 mtu_lo; + int mtu_lo; if (test__start_subtest("bpf_check_mtu XDP-attach")) test_check_mtu_xdp_attach(); diff --git a/tools/testing/selftests/bpf/prog_tests/cpumask.c b/tools/testing/selftests/bpf/prog_tests/cpumask.c index cdf4acc18e4c..756ea8b590b6 100644 --- a/tools/testing/selftests/bpf/prog_tests/cpumask.c +++ b/tools/testing/selftests/bpf/prog_tests/cpumask.c @@ -10,6 +10,7 @@ static const char * const cpumask_success_testcases[] = { "test_set_clear_cpu", "test_setall_clear_cpu", "test_first_firstzero_cpu", + "test_firstand_nocpu", "test_test_and_set_clear", "test_and_or_xor", "test_intersects_subset", @@ -70,5 +71,6 @@ void test_cpumask(void) verify_success(cpumask_success_testcases[i]); } + RUN_TESTS(cpumask_success); RUN_TESTS(cpumask_failure); } diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c index d176c34a7d2e..7cfac53c0d58 100644 --- a/tools/testing/selftests/bpf/prog_tests/dynptr.c +++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c @@ -20,6 +20,14 @@ static struct { {"test_ringbuf", SETUP_SYSCALL_SLEEP}, {"test_skb_readonly", SETUP_SKB_PROG}, {"test_dynptr_skb_data", SETUP_SKB_PROG}, + {"test_adjust", SETUP_SYSCALL_SLEEP}, + {"test_adjust_err", SETUP_SYSCALL_SLEEP}, + {"test_zero_size_dynptr", SETUP_SYSCALL_SLEEP}, + {"test_dynptr_is_null", SETUP_SYSCALL_SLEEP}, + {"test_dynptr_is_rdonly", SETUP_SKB_PROG}, + {"test_dynptr_clone", SETUP_SKB_PROG}, + {"test_dynptr_skb_no_buff", SETUP_SKB_PROG}, + {"test_dynptr_skb_strcmp", SETUP_SKB_PROG}, }; static void verify_success(const char *prog_name, enum test_setup_type setup_type) diff --git a/tools/testing/selftests/bpf/prog_tests/fib_lookup.c b/tools/testing/selftests/bpf/prog_tests/fib_lookup.c index a1e712105811..2fd05649bad1 100644 --- a/tools/testing/selftests/bpf/prog_tests/fib_lookup.c +++ b/tools/testing/selftests/bpf/prog_tests/fib_lookup.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include <linux/rtnetlink.h> #include <sys/types.h> #include <net/if.h> @@ -15,14 +16,23 @@ #define IPV4_IFACE_ADDR "10.0.0.254" #define IPV4_NUD_FAILED_ADDR "10.0.0.1" #define IPV4_NUD_STALE_ADDR "10.0.0.2" +#define IPV4_TBID_ADDR "172.0.0.254" +#define IPV4_TBID_NET "172.0.0.0" +#define IPV4_TBID_DST "172.0.0.2" +#define IPV6_TBID_ADDR "fd00::FFFF" +#define IPV6_TBID_NET "fd00::" +#define IPV6_TBID_DST "fd00::2" #define DMAC "11:11:11:11:11:11" #define DMAC_INIT { 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, } +#define DMAC2 "01:01:01:01:01:01" +#define DMAC_INIT2 { 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, } struct fib_lookup_test { const char *desc; const char *daddr; int expected_ret; int lookup_flags; + __u32 tbid; __u8 dmac[6]; }; @@ -43,6 +53,22 @@ static const struct fib_lookup_test tests[] = { { .desc = "IPv4 skip neigh", .daddr = IPV4_NUD_FAILED_ADDR, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS, .lookup_flags = BPF_FIB_LOOKUP_SKIP_NEIGH, }, + { .desc = "IPv4 TBID lookup failure", + .daddr = IPV4_TBID_DST, .expected_ret = BPF_FIB_LKUP_RET_NOT_FWDED, + .lookup_flags = BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID, + .tbid = RT_TABLE_MAIN, }, + { .desc = "IPv4 TBID lookup success", + .daddr = IPV4_TBID_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS, + .lookup_flags = BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID, .tbid = 100, + .dmac = DMAC_INIT2, }, + { .desc = "IPv6 TBID lookup failure", + .daddr = IPV6_TBID_DST, .expected_ret = BPF_FIB_LKUP_RET_NOT_FWDED, + .lookup_flags = BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID, + .tbid = RT_TABLE_MAIN, }, + { .desc = "IPv6 TBID lookup success", + .daddr = IPV6_TBID_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS, + .lookup_flags = BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID, .tbid = 100, + .dmac = DMAC_INIT2, }, }; static int ifindex; @@ -53,6 +79,7 @@ static int setup_netns(void) SYS(fail, "ip link add veth1 type veth peer name veth2"); SYS(fail, "ip link set dev veth1 up"); + SYS(fail, "ip link set dev veth2 up"); err = write_sysctl("/proc/sys/net/ipv4/neigh/veth1/gc_stale_time", "900"); if (!ASSERT_OK(err, "write_sysctl(net.ipv4.neigh.veth1.gc_stale_time)")) @@ -70,6 +97,17 @@ static int setup_netns(void) SYS(fail, "ip neigh add %s dev veth1 nud failed", IPV4_NUD_FAILED_ADDR); SYS(fail, "ip neigh add %s dev veth1 lladdr %s nud stale", IPV4_NUD_STALE_ADDR, DMAC); + /* Setup for tbid lookup tests */ + SYS(fail, "ip addr add %s/24 dev veth2", IPV4_TBID_ADDR); + SYS(fail, "ip route del %s/24 dev veth2", IPV4_TBID_NET); + SYS(fail, "ip route add table 100 %s/24 dev veth2", IPV4_TBID_NET); + SYS(fail, "ip neigh add %s dev veth2 lladdr %s nud stale", IPV4_TBID_DST, DMAC2); + + SYS(fail, "ip addr add %s/64 dev veth2", IPV6_TBID_ADDR); + SYS(fail, "ip -6 route del %s/64 dev veth2", IPV6_TBID_NET); + SYS(fail, "ip -6 route add table 100 %s/64 dev veth2", IPV6_TBID_NET); + SYS(fail, "ip neigh add %s dev veth2 lladdr %s nud stale", IPV6_TBID_DST, DMAC2); + err = write_sysctl("/proc/sys/net/ipv4/conf/veth1/forwarding", "1"); if (!ASSERT_OK(err, "write_sysctl(net.ipv4.conf.veth1.forwarding)")) goto fail; @@ -83,7 +121,7 @@ fail: return -1; } -static int set_lookup_params(struct bpf_fib_lookup *params, const char *daddr) +static int set_lookup_params(struct bpf_fib_lookup *params, const struct fib_lookup_test *test) { int ret; @@ -91,8 +129,9 @@ static int set_lookup_params(struct bpf_fib_lookup *params, const char *daddr) params->l4_protocol = IPPROTO_TCP; params->ifindex = ifindex; + params->tbid = test->tbid; - if (inet_pton(AF_INET6, daddr, params->ipv6_dst) == 1) { + if (inet_pton(AF_INET6, test->daddr, params->ipv6_dst) == 1) { params->family = AF_INET6; ret = inet_pton(AF_INET6, IPV6_IFACE_ADDR, params->ipv6_src); if (!ASSERT_EQ(ret, 1, "inet_pton(IPV6_IFACE_ADDR)")) @@ -100,7 +139,7 @@ static int set_lookup_params(struct bpf_fib_lookup *params, const char *daddr) return 0; } - ret = inet_pton(AF_INET, daddr, ¶ms->ipv4_dst); + ret = inet_pton(AF_INET, test->daddr, ¶ms->ipv4_dst); if (!ASSERT_EQ(ret, 1, "convert IP[46] address")) return -1; params->family = AF_INET; @@ -154,13 +193,12 @@ void test_fib_lookup(void) fib_params = &skel->bss->fib_params; for (i = 0; i < ARRAY_SIZE(tests); i++) { - printf("Testing %s\n", tests[i].desc); + printf("Testing %s ", tests[i].desc); - if (set_lookup_params(fib_params, tests[i].daddr)) + if (set_lookup_params(fib_params, &tests[i])) continue; skel->bss->fib_lookup_ret = -1; - skel->bss->lookup_flags = BPF_FIB_LOOKUP_OUTPUT | - tests[i].lookup_flags; + skel->bss->lookup_flags = tests[i].lookup_flags; err = bpf_prog_test_run_opts(prog_fd, &run_opts); if (!ASSERT_OK(err, "bpf_prog_test_run_opts")) @@ -175,7 +213,14 @@ void test_fib_lookup(void) mac_str(expected, tests[i].dmac); mac_str(actual, fib_params->dmac); - printf("dmac expected %s actual %s\n", expected, actual); + printf("dmac expected %s actual %s ", expected, actual); + } + + // ensure tbid is zero'd out after fib lookup. + if (tests[i].lookup_flags & BPF_FIB_LOOKUP_DIRECT) { + if (!ASSERT_EQ(skel->bss->fib_params.tbid, 0, + "expected fib_params.tbid to be zero")) + goto fail; } } diff --git a/tools/testing/selftests/bpf/prog_tests/global_map_resize.c b/tools/testing/selftests/bpf/prog_tests/global_map_resize.c new file mode 100644 index 000000000000..fd41425d2e5c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/global_map_resize.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include <errno.h> +#include <sys/syscall.h> +#include <unistd.h> +#include "test_global_map_resize.skel.h" +#include "test_progs.h" + +static void run_prog_bss_array_sum(void) +{ + (void)syscall(__NR_getpid); +} + +static void run_prog_data_array_sum(void) +{ + (void)syscall(__NR_getuid); +} + +static void global_map_resize_bss_subtest(void) +{ + int err; + struct test_global_map_resize *skel; + struct bpf_map *map; + const __u32 desired_sz = sizeof(skel->bss->sum) + sysconf(_SC_PAGE_SIZE) * 2; + size_t array_len, actual_sz; + + skel = test_global_map_resize__open(); + if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open")) + goto teardown; + + /* set some initial value before resizing. + * it is expected this non-zero value will be preserved + * while resizing. + */ + skel->bss->array[0] = 1; + + /* resize map value and verify the new size */ + map = skel->maps.bss; + err = bpf_map__set_value_size(map, desired_sz); + if (!ASSERT_OK(err, "bpf_map__set_value_size")) + goto teardown; + if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "resize")) + goto teardown; + + /* set the expected number of elements based on the resized array */ + array_len = (desired_sz - sizeof(skel->bss->sum)) / sizeof(skel->bss->array[0]); + if (!ASSERT_GT(array_len, 1, "array_len")) + goto teardown; + + skel->bss = bpf_map__initial_value(skel->maps.bss, &actual_sz); + if (!ASSERT_OK_PTR(skel->bss, "bpf_map__initial_value (ptr)")) + goto teardown; + if (!ASSERT_EQ(actual_sz, desired_sz, "bpf_map__initial_value (size)")) + goto teardown; + + /* fill the newly resized array with ones, + * skipping the first element which was previously set + */ + for (int i = 1; i < array_len; i++) + skel->bss->array[i] = 1; + + /* set global const values before loading */ + skel->rodata->pid = getpid(); + skel->rodata->bss_array_len = array_len; + skel->rodata->data_array_len = 1; + + err = test_global_map_resize__load(skel); + if (!ASSERT_OK(err, "test_global_map_resize__load")) + goto teardown; + err = test_global_map_resize__attach(skel); + if (!ASSERT_OK(err, "test_global_map_resize__attach")) + goto teardown; + + /* run the bpf program which will sum the contents of the array. + * since the array was filled with ones,verify the sum equals array_len + */ + run_prog_bss_array_sum(); + if (!ASSERT_EQ(skel->bss->sum, array_len, "sum")) + goto teardown; + +teardown: + test_global_map_resize__destroy(skel); +} + +static void global_map_resize_data_subtest(void) +{ + int err; + struct test_global_map_resize *skel; + struct bpf_map *map; + const __u32 desired_sz = sysconf(_SC_PAGE_SIZE) * 2; + size_t array_len, actual_sz; + + skel = test_global_map_resize__open(); + if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open")) + goto teardown; + + /* set some initial value before resizing. + * it is expected this non-zero value will be preserved + * while resizing. + */ + skel->data_custom->my_array[0] = 1; + + /* resize map value and verify the new size */ + map = skel->maps.data_custom; + err = bpf_map__set_value_size(map, desired_sz); + if (!ASSERT_OK(err, "bpf_map__set_value_size")) + goto teardown; + if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "resize")) + goto teardown; + + /* set the expected number of elements based on the resized array */ + array_len = (desired_sz - sizeof(skel->bss->sum)) / sizeof(skel->data_custom->my_array[0]); + if (!ASSERT_GT(array_len, 1, "array_len")) + goto teardown; + + skel->data_custom = bpf_map__initial_value(skel->maps.data_custom, &actual_sz); + if (!ASSERT_OK_PTR(skel->data_custom, "bpf_map__initial_value (ptr)")) + goto teardown; + if (!ASSERT_EQ(actual_sz, desired_sz, "bpf_map__initial_value (size)")) + goto teardown; + + /* fill the newly resized array with ones, + * skipping the first element which was previously set + */ + for (int i = 1; i < array_len; i++) + skel->data_custom->my_array[i] = 1; + + /* set global const values before loading */ + skel->rodata->pid = getpid(); + skel->rodata->bss_array_len = 1; + skel->rodata->data_array_len = array_len; + + err = test_global_map_resize__load(skel); + if (!ASSERT_OK(err, "test_global_map_resize__load")) + goto teardown; + err = test_global_map_resize__attach(skel); + if (!ASSERT_OK(err, "test_global_map_resize__attach")) + goto teardown; + + /* run the bpf program which will sum the contents of the array. + * since the array was filled with ones,verify the sum equals array_len + */ + run_prog_data_array_sum(); + if (!ASSERT_EQ(skel->bss->sum, array_len, "sum")) + goto teardown; + +teardown: + test_global_map_resize__destroy(skel); +} + +static void global_map_resize_invalid_subtest(void) +{ + int err; + struct test_global_map_resize *skel; + struct bpf_map *map; + __u32 element_sz, desired_sz; + + skel = test_global_map_resize__open(); + if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open")) + return; + + /* attempt to resize a global datasec map to size + * which does NOT align with array + */ + map = skel->maps.data_custom; + if (!ASSERT_NEQ(bpf_map__btf_value_type_id(map), 0, ".data.custom initial btf")) + goto teardown; + /* set desired size a fraction of element size beyond an aligned size */ + element_sz = sizeof(skel->data_custom->my_array[0]); + desired_sz = element_sz + element_sz / 2; + /* confirm desired size does NOT align with array */ + if (!ASSERT_NEQ(desired_sz % element_sz, 0, "my_array alignment")) + goto teardown; + err = bpf_map__set_value_size(map, desired_sz); + /* confirm resize is OK but BTF info is cleared */ + if (!ASSERT_OK(err, ".data.custom bpf_map__set_value_size") || + !ASSERT_EQ(bpf_map__btf_key_type_id(map), 0, ".data.custom clear btf key") || + !ASSERT_EQ(bpf_map__btf_value_type_id(map), 0, ".data.custom clear btf val")) + goto teardown; + + /* attempt to resize a global datasec map whose only var is NOT an array */ + map = skel->maps.data_non_array; + if (!ASSERT_NEQ(bpf_map__btf_value_type_id(map), 0, ".data.non_array initial btf")) + goto teardown; + /* set desired size to arbitrary value */ + desired_sz = 1024; + err = bpf_map__set_value_size(map, desired_sz); + /* confirm resize is OK but BTF info is cleared */ + if (!ASSERT_OK(err, ".data.non_array bpf_map__set_value_size") || + !ASSERT_EQ(bpf_map__btf_key_type_id(map), 0, ".data.non_array clear btf key") || + !ASSERT_EQ(bpf_map__btf_value_type_id(map), 0, ".data.non_array clear btf val")) + goto teardown; + + /* attempt to resize a global datasec map + * whose last var is NOT an array + */ + map = skel->maps.data_array_not_last; + if (!ASSERT_NEQ(bpf_map__btf_value_type_id(map), 0, ".data.array_not_last initial btf")) + goto teardown; + /* set desired size to a multiple of element size */ + element_sz = sizeof(skel->data_array_not_last->my_array_first[0]); + desired_sz = element_sz * 8; + /* confirm desired size aligns with array */ + if (!ASSERT_EQ(desired_sz % element_sz, 0, "my_array_first alignment")) + goto teardown; + err = bpf_map__set_value_size(map, desired_sz); + /* confirm resize is OK but BTF info is cleared */ + if (!ASSERT_OK(err, ".data.array_not_last bpf_map__set_value_size") || + !ASSERT_EQ(bpf_map__btf_key_type_id(map), 0, ".data.array_not_last clear btf key") || + !ASSERT_EQ(bpf_map__btf_value_type_id(map), 0, ".data.array_not_last clear btf val")) + goto teardown; + +teardown: + test_global_map_resize__destroy(skel); +} + +void test_global_map_resize(void) +{ + if (test__start_subtest("global_map_resize_bss")) + global_map_resize_bss_subtest(); + + if (test__start_subtest("global_map_resize_data")) + global_map_resize_data_subtest(); + + if (test__start_subtest("global_map_resize_invalid")) + global_map_resize_invalid_subtest(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c b/tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c new file mode 100644 index 000000000000..9ab4cd195108 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <test_progs.h> + +#include "inner_array_lookup.skel.h" + +void test_inner_array_lookup(void) +{ + int map1_fd, err; + int key = 3; + int val = 1; + struct inner_array_lookup *skel; + + skel = inner_array_lookup__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_load_skeleton")) + return; + + err = inner_array_lookup__attach(skel); + if (!ASSERT_OK(err, "skeleton_attach")) + goto cleanup; + + map1_fd = bpf_map__fd(skel->maps.inner_map1); + bpf_map_update_elem(map1_fd, &key, &val, 0); + + /* Probe should have set the element at index 3 to 2 */ + bpf_map_lookup_elem(map1_fd, &key, &val); + ASSERT_EQ(val, 2, "value_is_2"); + +cleanup: + inner_array_lookup__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c index 7fc01ff490db..f53d658ed080 100644 --- a/tools/testing/selftests/bpf/prog_tests/module_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c @@ -4,6 +4,7 @@ #include <test_progs.h> #include <stdbool.h> #include "test_module_attach.skel.h" +#include "testing_helpers.h" static int duration; @@ -32,11 +33,6 @@ static int trigger_module_test_writable(int *val) return 0; } -static int delete_module(const char *name, int flags) -{ - return syscall(__NR_delete_module, name, flags); -} - void test_module_attach(void) { const int READ_SZ = 456; @@ -93,21 +89,21 @@ void test_module_attach(void) if (!ASSERT_OK_PTR(link, "attach_fentry")) goto cleanup; - ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module"); + ASSERT_ERR(unload_bpf_testmod(false), "unload_bpf_testmod"); bpf_link__destroy(link); link = bpf_program__attach(skel->progs.handle_fexit); if (!ASSERT_OK_PTR(link, "attach_fexit")) goto cleanup; - ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module"); + ASSERT_ERR(unload_bpf_testmod(false), "unload_bpf_testmod"); bpf_link__destroy(link); link = bpf_program__attach(skel->progs.kprobe_multi); if (!ASSERT_OK_PTR(link, "attach_kprobe_multi")) goto cleanup; - ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module"); + ASSERT_ERR(unload_bpf_testmod(false), "unload_bpf_testmod"); bpf_link__destroy(link); cleanup: diff --git a/tools/testing/selftests/bpf/prog_tests/netcnt.c b/tools/testing/selftests/bpf/prog_tests/netcnt.c index d3915c58d0e1..c3333edd029f 100644 --- a/tools/testing/selftests/bpf/prog_tests/netcnt.c +++ b/tools/testing/selftests/bpf/prog_tests/netcnt.c @@ -67,12 +67,12 @@ void serial_test_netcnt(void) } /* No packets should be lost */ - ASSERT_EQ(packets, 10000, "packets"); + ASSERT_GE(packets, 10000, "packets"); /* Let's check that bytes counter matches the number of packets * multiplied by the size of ipv6 ICMP packet. */ - ASSERT_EQ(bytes, packets * 104, "bytes"); + ASSERT_GE(bytes, packets * 104, "bytes"); err: if (cg_fd != -1) diff --git a/tools/testing/selftests/bpf/prog_tests/sock_destroy.c b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c new file mode 100644 index 000000000000..b0583309a94e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c @@ -0,0 +1,221 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <bpf/bpf_endian.h> + +#include "sock_destroy_prog.skel.h" +#include "sock_destroy_prog_fail.skel.h" +#include "network_helpers.h" + +#define TEST_NS "sock_destroy_netns" + +static void start_iter_sockets(struct bpf_program *prog) +{ + struct bpf_link *link; + char buf[50] = {}; + int iter_fd, len; + + link = bpf_program__attach_iter(prog, NULL); + if (!ASSERT_OK_PTR(link, "attach_iter")) + return; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (!ASSERT_GE(iter_fd, 0, "create_iter")) + goto free_link; + + while ((len = read(iter_fd, buf, sizeof(buf))) > 0) + ; + ASSERT_GE(len, 0, "read"); + + close(iter_fd); + +free_link: + bpf_link__destroy(link); +} + +static void test_tcp_client(struct sock_destroy_prog *skel) +{ + int serv = -1, clien = -1, accept_serv = -1, n; + + serv = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); + if (!ASSERT_GE(serv, 0, "start_server")) + goto cleanup; + + clien = connect_to_fd(serv, 0); + if (!ASSERT_GE(clien, 0, "connect_to_fd")) + goto cleanup; + + accept_serv = accept(serv, NULL, NULL); + if (!ASSERT_GE(accept_serv, 0, "serv accept")) + goto cleanup; + + n = send(clien, "t", 1, 0); + if (!ASSERT_EQ(n, 1, "client send")) + goto cleanup; + + /* Run iterator program that destroys connected client sockets. */ + start_iter_sockets(skel->progs.iter_tcp6_client); + + n = send(clien, "t", 1, 0); + if (!ASSERT_LT(n, 0, "client_send on destroyed socket")) + goto cleanup; + ASSERT_EQ(errno, ECONNABORTED, "error code on destroyed socket"); + +cleanup: + if (clien != -1) + close(clien); + if (accept_serv != -1) + close(accept_serv); + if (serv != -1) + close(serv); +} + +static void test_tcp_server(struct sock_destroy_prog *skel) +{ + int serv = -1, clien = -1, accept_serv = -1, n, serv_port; + + serv = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); + if (!ASSERT_GE(serv, 0, "start_server")) + goto cleanup; + serv_port = get_socket_local_port(serv); + if (!ASSERT_GE(serv_port, 0, "get_sock_local_port")) + goto cleanup; + skel->bss->serv_port = (__be16) serv_port; + + clien = connect_to_fd(serv, 0); + if (!ASSERT_GE(clien, 0, "connect_to_fd")) + goto cleanup; + + accept_serv = accept(serv, NULL, NULL); + if (!ASSERT_GE(accept_serv, 0, "serv accept")) + goto cleanup; + + n = send(clien, "t", 1, 0); + if (!ASSERT_EQ(n, 1, "client send")) + goto cleanup; + + /* Run iterator program that destroys server sockets. */ + start_iter_sockets(skel->progs.iter_tcp6_server); + + n = send(clien, "t", 1, 0); + if (!ASSERT_LT(n, 0, "client_send on destroyed socket")) + goto cleanup; + ASSERT_EQ(errno, ECONNRESET, "error code on destroyed socket"); + +cleanup: + if (clien != -1) + close(clien); + if (accept_serv != -1) + close(accept_serv); + if (serv != -1) + close(serv); +} + +static void test_udp_client(struct sock_destroy_prog *skel) +{ + int serv = -1, clien = -1, n = 0; + + serv = start_server(AF_INET6, SOCK_DGRAM, NULL, 0, 0); + if (!ASSERT_GE(serv, 0, "start_server")) + goto cleanup; + + clien = connect_to_fd(serv, 0); + if (!ASSERT_GE(clien, 0, "connect_to_fd")) + goto cleanup; + + n = send(clien, "t", 1, 0); + if (!ASSERT_EQ(n, 1, "client send")) + goto cleanup; + + /* Run iterator program that destroys sockets. */ + start_iter_sockets(skel->progs.iter_udp6_client); + + n = send(clien, "t", 1, 0); + if (!ASSERT_LT(n, 0, "client_send on destroyed socket")) + goto cleanup; + /* UDP sockets have an overriding error code after they are disconnected, + * so we don't check for ECONNABORTED error code. + */ + +cleanup: + if (clien != -1) + close(clien); + if (serv != -1) + close(serv); +} + +static void test_udp_server(struct sock_destroy_prog *skel) +{ + int *listen_fds = NULL, n, i, serv_port; + unsigned int num_listens = 5; + char buf[1]; + + /* Start reuseport servers. */ + listen_fds = start_reuseport_server(AF_INET6, SOCK_DGRAM, + "::1", 0, 0, num_listens); + if (!ASSERT_OK_PTR(listen_fds, "start_reuseport_server")) + goto cleanup; + serv_port = get_socket_local_port(listen_fds[0]); + if (!ASSERT_GE(serv_port, 0, "get_sock_local_port")) + goto cleanup; + skel->bss->serv_port = (__be16) serv_port; + + /* Run iterator program that destroys server sockets. */ + start_iter_sockets(skel->progs.iter_udp6_server); + + for (i = 0; i < num_listens; ++i) { + n = read(listen_fds[i], buf, sizeof(buf)); + if (!ASSERT_EQ(n, -1, "read") || + !ASSERT_EQ(errno, ECONNABORTED, "error code on destroyed socket")) + break; + } + ASSERT_EQ(i, num_listens, "server socket"); + +cleanup: + free_fds(listen_fds, num_listens); +} + +void test_sock_destroy(void) +{ + struct sock_destroy_prog *skel; + struct nstoken *nstoken = NULL; + int cgroup_fd; + + skel = sock_destroy_prog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + cgroup_fd = test__join_cgroup("/sock_destroy"); + if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup")) + goto cleanup; + + skel->links.sock_connect = bpf_program__attach_cgroup( + skel->progs.sock_connect, cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.sock_connect, "prog_attach")) + goto cleanup; + + SYS(cleanup, "ip netns add %s", TEST_NS); + SYS(cleanup, "ip -net %s link set dev lo up", TEST_NS); + + nstoken = open_netns(TEST_NS); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto cleanup; + + if (test__start_subtest("tcp_client")) + test_tcp_client(skel); + if (test__start_subtest("tcp_server")) + test_tcp_server(skel); + if (test__start_subtest("udp_client")) + test_udp_client(skel); + if (test__start_subtest("udp_server")) + test_udp_server(skel); + + RUN_TESTS(sock_destroy_prog_fail); + +cleanup: + if (nstoken) + close_netns(nstoken); + SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null"); + if (cgroup_fd >= 0) + close(cgroup_fd); + sock_destroy_prog__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 0ce25a967481..064cc5e8d9ad 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -2,6 +2,7 @@ // Copyright (c) 2020 Cloudflare #include <error.h> #include <netinet/tcp.h> +#include <sys/epoll.h> #include "test_progs.h" #include "test_skmsg_load_helpers.skel.h" @@ -9,8 +10,12 @@ #include "test_sockmap_invalid_update.skel.h" #include "test_sockmap_skb_verdict_attach.skel.h" #include "test_sockmap_progs_query.skel.h" +#include "test_sockmap_pass_prog.skel.h" +#include "test_sockmap_drop_prog.skel.h" #include "bpf_iter_sockmap.skel.h" +#include "sockmap_helpers.h" + #define TCP_REPAIR 19 /* TCP sock is under repair right now */ #define TCP_REPAIR_ON 1 @@ -350,6 +355,126 @@ out: test_sockmap_progs_query__destroy(skel); } +#define MAX_EVENTS 10 +static void test_sockmap_skb_verdict_shutdown(void) +{ + struct epoll_event ev, events[MAX_EVENTS]; + int n, err, map, verdict, s, c1, p1; + struct test_sockmap_pass_prog *skel; + int epollfd; + int zero = 0; + char b; + + skel = test_sockmap_pass_prog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + verdict = bpf_program__fd(skel->progs.prog_skb_verdict); + map = bpf_map__fd(skel->maps.sock_map_rx); + + err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out; + + s = socket_loopback(AF_INET, SOCK_STREAM); + if (s < 0) + goto out; + err = create_pair(s, AF_INET, SOCK_STREAM, &c1, &p1); + if (err < 0) + goto out; + + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (err < 0) + goto out_close; + + shutdown(p1, SHUT_WR); + + ev.events = EPOLLIN; + ev.data.fd = c1; + + epollfd = epoll_create1(0); + if (!ASSERT_GT(epollfd, -1, "epoll_create(0)")) + goto out_close; + err = epoll_ctl(epollfd, EPOLL_CTL_ADD, c1, &ev); + if (!ASSERT_OK(err, "epoll_ctl(EPOLL_CTL_ADD)")) + goto out_close; + err = epoll_wait(epollfd, events, MAX_EVENTS, -1); + if (!ASSERT_EQ(err, 1, "epoll_wait(fd)")) + goto out_close; + + n = recv(c1, &b, 1, SOCK_NONBLOCK); + ASSERT_EQ(n, 0, "recv_timeout(fin)"); +out_close: + close(c1); + close(p1); +out: + test_sockmap_pass_prog__destroy(skel); +} + +static void test_sockmap_skb_verdict_fionread(bool pass_prog) +{ + int expected, zero = 0, sent, recvd, avail; + int err, map, verdict, s, c0, c1, p0, p1; + struct test_sockmap_pass_prog *pass; + struct test_sockmap_drop_prog *drop; + char buf[256] = "0123456789"; + + if (pass_prog) { + pass = test_sockmap_pass_prog__open_and_load(); + if (!ASSERT_OK_PTR(pass, "open_and_load")) + return; + verdict = bpf_program__fd(pass->progs.prog_skb_verdict); + map = bpf_map__fd(pass->maps.sock_map_rx); + expected = sizeof(buf); + } else { + drop = test_sockmap_drop_prog__open_and_load(); + if (!ASSERT_OK_PTR(drop, "open_and_load")) + return; + verdict = bpf_program__fd(drop->progs.prog_skb_verdict); + map = bpf_map__fd(drop->maps.sock_map_rx); + /* On drop data is consumed immediately and copied_seq inc'd */ + expected = 0; + } + + + err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out; + + s = socket_loopback(AF_INET, SOCK_STREAM); + if (!ASSERT_GT(s, -1, "socket_loopback(s)")) + goto out; + err = create_socket_pairs(s, AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1); + if (!ASSERT_OK(err, "create_socket_pairs(s)")) + goto out; + + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(c1)")) + goto out_close; + + sent = xsend(p1, &buf, sizeof(buf), 0); + ASSERT_EQ(sent, sizeof(buf), "xsend(p0)"); + err = ioctl(c1, FIONREAD, &avail); + ASSERT_OK(err, "ioctl(FIONREAD) error"); + ASSERT_EQ(avail, expected, "ioctl(FIONREAD)"); + /* On DROP test there will be no data to read */ + if (pass_prog) { + recvd = recv_timeout(c1, &buf, sizeof(buf), SOCK_NONBLOCK, IO_TIMEOUT_SEC); + ASSERT_EQ(recvd, sizeof(buf), "recv_timeout(c0)"); + } + +out_close: + close(c0); + close(p0); + close(c1); + close(p1); +out: + if (pass_prog) + test_sockmap_pass_prog__destroy(pass); + else + test_sockmap_drop_prog__destroy(drop); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -384,4 +509,10 @@ void test_sockmap_basic(void) test_sockmap_progs_query(BPF_SK_SKB_STREAM_VERDICT); if (test__start_subtest("sockmap skb_verdict progs query")) test_sockmap_progs_query(BPF_SK_SKB_VERDICT); + if (test__start_subtest("sockmap skb_verdict shutdown")) + test_sockmap_skb_verdict_shutdown(); + if (test__start_subtest("sockmap skb_verdict fionread")) + test_sockmap_skb_verdict_fionread(true); + if (test__start_subtest("sockmap skb_verdict fionread on drop")) + test_sockmap_skb_verdict_fionread(false); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h new file mode 100644 index 000000000000..d12665490a90 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h @@ -0,0 +1,390 @@ +#ifndef __SOCKMAP_HELPERS__ +#define __SOCKMAP_HELPERS__ + +#include <linux/vm_sockets.h> + +#define IO_TIMEOUT_SEC 30 +#define MAX_STRERR_LEN 256 +#define MAX_TEST_NAME 80 + +/* workaround for older vm_sockets.h */ +#ifndef VMADDR_CID_LOCAL +#define VMADDR_CID_LOCAL 1 +#endif + +#define __always_unused __attribute__((__unused__)) + +#define _FAIL(errnum, fmt...) \ + ({ \ + error_at_line(0, (errnum), __func__, __LINE__, fmt); \ + CHECK_FAIL(true); \ + }) +#define FAIL(fmt...) _FAIL(0, fmt) +#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) +#define FAIL_LIBBPF(err, msg) \ + ({ \ + char __buf[MAX_STRERR_LEN]; \ + libbpf_strerror((err), __buf, sizeof(__buf)); \ + FAIL("%s: %s", (msg), __buf); \ + }) + +/* Wrappers that fail the test on error and report it. */ + +#define xaccept_nonblock(fd, addr, len) \ + ({ \ + int __ret = \ + accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("accept"); \ + __ret; \ + }) + +#define xbind(fd, addr, len) \ + ({ \ + int __ret = bind((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("bind"); \ + __ret; \ + }) + +#define xclose(fd) \ + ({ \ + int __ret = close((fd)); \ + if (__ret == -1) \ + FAIL_ERRNO("close"); \ + __ret; \ + }) + +#define xconnect(fd, addr, len) \ + ({ \ + int __ret = connect((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("connect"); \ + __ret; \ + }) + +#define xgetsockname(fd, addr, len) \ + ({ \ + int __ret = getsockname((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockname"); \ + __ret; \ + }) + +#define xgetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = getsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockopt(" #name ")"); \ + __ret; \ + }) + +#define xlisten(fd, backlog) \ + ({ \ + int __ret = listen((fd), (backlog)); \ + if (__ret == -1) \ + FAIL_ERRNO("listen"); \ + __ret; \ + }) + +#define xsetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = setsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("setsockopt(" #name ")"); \ + __ret; \ + }) + +#define xsend(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = send((fd), (buf), (len), (flags)); \ + if (__ret == -1) \ + FAIL_ERRNO("send"); \ + __ret; \ + }) + +#define xrecv_nonblock(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ + IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("recv"); \ + __ret; \ + }) + +#define xsocket(family, sotype, flags) \ + ({ \ + int __ret = socket(family, sotype, flags); \ + if (__ret == -1) \ + FAIL_ERRNO("socket"); \ + __ret; \ + }) + +#define xbpf_map_delete_elem(fd, key) \ + ({ \ + int __ret = bpf_map_delete_elem((fd), (key)); \ + if (__ret < 0) \ + FAIL_ERRNO("map_delete"); \ + __ret; \ + }) + +#define xbpf_map_lookup_elem(fd, key, val) \ + ({ \ + int __ret = bpf_map_lookup_elem((fd), (key), (val)); \ + if (__ret < 0) \ + FAIL_ERRNO("map_lookup"); \ + __ret; \ + }) + +#define xbpf_map_update_elem(fd, key, val, flags) \ + ({ \ + int __ret = bpf_map_update_elem((fd), (key), (val), (flags)); \ + if (__ret < 0) \ + FAIL_ERRNO("map_update"); \ + __ret; \ + }) + +#define xbpf_prog_attach(prog, target, type, flags) \ + ({ \ + int __ret = \ + bpf_prog_attach((prog), (target), (type), (flags)); \ + if (__ret < 0) \ + FAIL_ERRNO("prog_attach(" #type ")"); \ + __ret; \ + }) + +#define xbpf_prog_detach2(prog, target, type) \ + ({ \ + int __ret = bpf_prog_detach2((prog), (target), (type)); \ + if (__ret < 0) \ + FAIL_ERRNO("prog_detach2(" #type ")"); \ + __ret; \ + }) + +#define xpthread_create(thread, attr, func, arg) \ + ({ \ + int __ret = pthread_create((thread), (attr), (func), (arg)); \ + errno = __ret; \ + if (__ret) \ + FAIL_ERRNO("pthread_create"); \ + __ret; \ + }) + +#define xpthread_join(thread, retval) \ + ({ \ + int __ret = pthread_join((thread), (retval)); \ + errno = __ret; \ + if (__ret) \ + FAIL_ERRNO("pthread_join"); \ + __ret; \ + }) + +static inline int poll_read(int fd, unsigned int timeout_sec) +{ + struct timeval timeout = { .tv_sec = timeout_sec }; + fd_set rfds; + int r; + + FD_ZERO(&rfds); + FD_SET(fd, &rfds); + + r = select(fd + 1, &rfds, NULL, NULL, &timeout); + if (r == 0) + errno = ETIME; + + return r == 1 ? 0 : -1; +} + +static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return accept(fd, addr, len); +} + +static inline int recv_timeout(int fd, void *buf, size_t len, int flags, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return recv(fd, buf, len, flags); +} + +static inline void init_addr_loopback4(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); + + addr4->sin_family = AF_INET; + addr4->sin_port = 0; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + *len = sizeof(*addr4); +} + +static inline void init_addr_loopback6(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); + + addr6->sin6_family = AF_INET6; + addr6->sin6_port = 0; + addr6->sin6_addr = in6addr_loopback; + *len = sizeof(*addr6); +} + +static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); + + addr->svm_family = AF_VSOCK; + addr->svm_port = VMADDR_PORT_ANY; + addr->svm_cid = VMADDR_CID_LOCAL; + *len = sizeof(*addr); +} + +static inline void init_addr_loopback(int family, struct sockaddr_storage *ss, + socklen_t *len) +{ + switch (family) { + case AF_INET: + init_addr_loopback4(ss, len); + return; + case AF_INET6: + init_addr_loopback6(ss, len); + return; + case AF_VSOCK: + init_addr_loopback_vsock(ss, len); + return; + default: + FAIL("unsupported address family %d", family); + } +} + +static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) +{ + return (struct sockaddr *)ss; +} + +static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2) +{ + u64 value; + u32 key; + int err; + + key = 0; + value = fd1; + err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); + if (err) + return err; + + key = 1; + value = fd2; + return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); +} + +static inline int create_pair(int s, int family, int sotype, int *c, int *p) +{ + struct sockaddr_storage addr; + socklen_t len; + int err = 0; + + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + return err; + + *c = xsocket(family, sotype, 0); + if (*c < 0) + return errno; + err = xconnect(*c, sockaddr(&addr), len); + if (err) { + err = errno; + goto close_cli0; + } + + *p = xaccept_nonblock(s, NULL, NULL); + if (*p < 0) { + err = errno; + goto close_cli0; + } + return err; +close_cli0: + close(*c); + return err; +} + +static inline int create_socket_pairs(int s, int family, int sotype, + int *c0, int *c1, int *p0, int *p1) +{ + int err; + + err = create_pair(s, family, sotype, c0, p0); + if (err) + return err; + + err = create_pair(s, family, sotype, c1, p1); + if (err) { + close(*c0); + close(*p0); + } + return err; +} + +static inline int enable_reuseport(int s, int progfd) +{ + int err, one = 1; + + err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); + if (err) + return -1; + err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, + sizeof(progfd)); + if (err) + return -1; + + return 0; +} + +static inline int socket_loopback_reuseport(int family, int sotype, int progfd) +{ + struct sockaddr_storage addr; + socklen_t len; + int err, s; + + init_addr_loopback(family, &addr, &len); + + s = xsocket(family, sotype, 0); + if (s == -1) + return -1; + + if (progfd >= 0) + enable_reuseport(s, progfd); + + err = xbind(s, sockaddr(&addr), len); + if (err) + goto close; + + if (sotype & SOCK_DGRAM) + return s; + + err = xlisten(s, SOMAXCONN); + if (err) + goto close; + + return s; +close: + xclose(s); + return -1; +} + +static inline int socket_loopback(int family, int sotype) +{ + return socket_loopback_reuseport(family, sotype, -1); +} + + +#endif // __SOCKMAP_HELPERS__ diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 141c1e5944ee..b4f6f3a50ae5 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -20,11 +20,6 @@ #include <unistd.h> #include <linux/vm_sockets.h> -/* workaround for older vm_sockets.h */ -#ifndef VMADDR_CID_LOCAL -#define VMADDR_CID_LOCAL 1 -#endif - #include <bpf/bpf.h> #include <bpf/libbpf.h> @@ -32,315 +27,7 @@ #include "test_progs.h" #include "test_sockmap_listen.skel.h" -#define IO_TIMEOUT_SEC 30 -#define MAX_STRERR_LEN 256 -#define MAX_TEST_NAME 80 - -#define __always_unused __attribute__((__unused__)) - -#define _FAIL(errnum, fmt...) \ - ({ \ - error_at_line(0, (errnum), __func__, __LINE__, fmt); \ - CHECK_FAIL(true); \ - }) -#define FAIL(fmt...) _FAIL(0, fmt) -#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) -#define FAIL_LIBBPF(err, msg) \ - ({ \ - char __buf[MAX_STRERR_LEN]; \ - libbpf_strerror((err), __buf, sizeof(__buf)); \ - FAIL("%s: %s", (msg), __buf); \ - }) - -/* Wrappers that fail the test on error and report it. */ - -#define xaccept_nonblock(fd, addr, len) \ - ({ \ - int __ret = \ - accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("accept"); \ - __ret; \ - }) - -#define xbind(fd, addr, len) \ - ({ \ - int __ret = bind((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("bind"); \ - __ret; \ - }) - -#define xclose(fd) \ - ({ \ - int __ret = close((fd)); \ - if (__ret == -1) \ - FAIL_ERRNO("close"); \ - __ret; \ - }) - -#define xconnect(fd, addr, len) \ - ({ \ - int __ret = connect((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("connect"); \ - __ret; \ - }) - -#define xgetsockname(fd, addr, len) \ - ({ \ - int __ret = getsockname((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockname"); \ - __ret; \ - }) - -#define xgetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = getsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockopt(" #name ")"); \ - __ret; \ - }) - -#define xlisten(fd, backlog) \ - ({ \ - int __ret = listen((fd), (backlog)); \ - if (__ret == -1) \ - FAIL_ERRNO("listen"); \ - __ret; \ - }) - -#define xsetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = setsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("setsockopt(" #name ")"); \ - __ret; \ - }) - -#define xsend(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = send((fd), (buf), (len), (flags)); \ - if (__ret == -1) \ - FAIL_ERRNO("send"); \ - __ret; \ - }) - -#define xrecv_nonblock(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ - IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("recv"); \ - __ret; \ - }) - -#define xsocket(family, sotype, flags) \ - ({ \ - int __ret = socket(family, sotype, flags); \ - if (__ret == -1) \ - FAIL_ERRNO("socket"); \ - __ret; \ - }) - -#define xbpf_map_delete_elem(fd, key) \ - ({ \ - int __ret = bpf_map_delete_elem((fd), (key)); \ - if (__ret < 0) \ - FAIL_ERRNO("map_delete"); \ - __ret; \ - }) - -#define xbpf_map_lookup_elem(fd, key, val) \ - ({ \ - int __ret = bpf_map_lookup_elem((fd), (key), (val)); \ - if (__ret < 0) \ - FAIL_ERRNO("map_lookup"); \ - __ret; \ - }) - -#define xbpf_map_update_elem(fd, key, val, flags) \ - ({ \ - int __ret = bpf_map_update_elem((fd), (key), (val), (flags)); \ - if (__ret < 0) \ - FAIL_ERRNO("map_update"); \ - __ret; \ - }) - -#define xbpf_prog_attach(prog, target, type, flags) \ - ({ \ - int __ret = \ - bpf_prog_attach((prog), (target), (type), (flags)); \ - if (__ret < 0) \ - FAIL_ERRNO("prog_attach(" #type ")"); \ - __ret; \ - }) - -#define xbpf_prog_detach2(prog, target, type) \ - ({ \ - int __ret = bpf_prog_detach2((prog), (target), (type)); \ - if (__ret < 0) \ - FAIL_ERRNO("prog_detach2(" #type ")"); \ - __ret; \ - }) - -#define xpthread_create(thread, attr, func, arg) \ - ({ \ - int __ret = pthread_create((thread), (attr), (func), (arg)); \ - errno = __ret; \ - if (__ret) \ - FAIL_ERRNO("pthread_create"); \ - __ret; \ - }) - -#define xpthread_join(thread, retval) \ - ({ \ - int __ret = pthread_join((thread), (retval)); \ - errno = __ret; \ - if (__ret) \ - FAIL_ERRNO("pthread_join"); \ - __ret; \ - }) - -static int poll_read(int fd, unsigned int timeout_sec) -{ - struct timeval timeout = { .tv_sec = timeout_sec }; - fd_set rfds; - int r; - - FD_ZERO(&rfds); - FD_SET(fd, &rfds); - - r = select(fd + 1, &rfds, NULL, NULL, &timeout); - if (r == 0) - errno = ETIME; - - return r == 1 ? 0 : -1; -} - -static int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return accept(fd, addr, len); -} - -static int recv_timeout(int fd, void *buf, size_t len, int flags, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return recv(fd, buf, len, flags); -} - -static void init_addr_loopback4(struct sockaddr_storage *ss, socklen_t *len) -{ - struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); - - addr4->sin_family = AF_INET; - addr4->sin_port = 0; - addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); - *len = sizeof(*addr4); -} - -static void init_addr_loopback6(struct sockaddr_storage *ss, socklen_t *len) -{ - struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); - - addr6->sin6_family = AF_INET6; - addr6->sin6_port = 0; - addr6->sin6_addr = in6addr_loopback; - *len = sizeof(*addr6); -} - -static void init_addr_loopback_vsock(struct sockaddr_storage *ss, socklen_t *len) -{ - struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); - - addr->svm_family = AF_VSOCK; - addr->svm_port = VMADDR_PORT_ANY; - addr->svm_cid = VMADDR_CID_LOCAL; - *len = sizeof(*addr); -} - -static void init_addr_loopback(int family, struct sockaddr_storage *ss, - socklen_t *len) -{ - switch (family) { - case AF_INET: - init_addr_loopback4(ss, len); - return; - case AF_INET6: - init_addr_loopback6(ss, len); - return; - case AF_VSOCK: - init_addr_loopback_vsock(ss, len); - return; - default: - FAIL("unsupported address family %d", family); - } -} - -static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) -{ - return (struct sockaddr *)ss; -} - -static int enable_reuseport(int s, int progfd) -{ - int err, one = 1; - - err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); - if (err) - return -1; - err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, - sizeof(progfd)); - if (err) - return -1; - - return 0; -} - -static int socket_loopback_reuseport(int family, int sotype, int progfd) -{ - struct sockaddr_storage addr; - socklen_t len; - int err, s; - - init_addr_loopback(family, &addr, &len); - - s = xsocket(family, sotype, 0); - if (s == -1) - return -1; - - if (progfd >= 0) - enable_reuseport(s, progfd); - - err = xbind(s, sockaddr(&addr), len); - if (err) - goto close; - - if (sotype & SOCK_DGRAM) - return s; - - err = xlisten(s, SOMAXCONN); - if (err) - goto close; - - return s; -close: - xclose(s); - return -1; -} - -static int socket_loopback(int family, int sotype) -{ - return socket_loopback_reuseport(family, sotype, -1); -} +#include "sockmap_helpers.h" static void test_insert_invalid(struct test_sockmap_listen *skel __always_unused, int family, int sotype, int mapfd) @@ -984,31 +671,12 @@ static const char *redir_mode_str(enum redir_mode mode) } } -static int add_to_sockmap(int sock_mapfd, int fd1, int fd2) -{ - u64 value; - u32 key; - int err; - - key = 0; - value = fd1; - err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); - if (err) - return err; - - key = 1; - value = fd2; - return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); -} - static void redir_to_connected(int family, int sotype, int sock_mapfd, int verd_mapfd, enum redir_mode mode) { const char *log_prefix = redir_mode_str(mode); - struct sockaddr_storage addr; int s, c0, c1, p0, p1; unsigned int pass; - socklen_t len; int err, n; u32 key; char b; @@ -1019,36 +687,13 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (s < 0) return; - len = sizeof(addr); - err = xgetsockname(s, sockaddr(&addr), &len); + err = create_socket_pairs(s, family, sotype, &c0, &c1, &p0, &p1); if (err) goto close_srv; - c0 = xsocket(family, sotype, 0); - if (c0 < 0) - goto close_srv; - err = xconnect(c0, sockaddr(&addr), len); - if (err) - goto close_cli0; - - p0 = xaccept_nonblock(s, NULL, NULL); - if (p0 < 0) - goto close_cli0; - - c1 = xsocket(family, sotype, 0); - if (c1 < 0) - goto close_peer0; - err = xconnect(c1, sockaddr(&addr), len); - if (err) - goto close_cli1; - - p1 = xaccept_nonblock(s, NULL, NULL); - if (p1 < 0) - goto close_cli1; - err = add_to_sockmap(sock_mapfd, p0, p1); if (err) - goto close_peer1; + goto close; n = write(mode == REDIR_INGRESS ? c1 : p1, "a", 1); if (n < 0) @@ -1056,12 +701,12 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (n == 0) FAIL("%s: incomplete write", log_prefix); if (n < 1) - goto close_peer1; + goto close; key = SK_PASS; err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass); if (err) - goto close_peer1; + goto close; if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); n = recv_timeout(c0, &b, 1, 0, IO_TIMEOUT_SEC); @@ -1070,13 +715,10 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (n == 0) FAIL("%s: incomplete recv", log_prefix); -close_peer1: +close: xclose(p1); -close_cli1: xclose(c1); -close_peer0: xclose(p0); -close_cli0: xclose(c0); close_srv: xclose(s); diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt.c b/tools/testing/selftests/bpf/prog_tests/sockopt.c index aa4debf62fc6..9e6a5e3ed4de 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt.c @@ -5,10 +5,15 @@ static char bpf_log_buf[4096]; static bool verbose; +#ifndef PAGE_SIZE +#define PAGE_SIZE 4096 +#endif + enum sockopt_test_error { OK = 0, DENY_LOAD, DENY_ATTACH, + EOPNOTSUPP_GETSOCKOPT, EPERM_GETSOCKOPT, EFAULT_GETSOCKOPT, EPERM_SETSOCKOPT, @@ -273,10 +278,31 @@ static struct sockopt_test { .error = EFAULT_GETSOCKOPT, }, { - .descr = "getsockopt: deny arbitrary ctx->retval", + .descr = "getsockopt: ignore >PAGE_SIZE optlen", .insns = { - /* ctx->retval = 123 */ - BPF_MOV64_IMM(BPF_REG_0, 123), + /* write 0xFF to the first optval byte */ + + /* r6 = ctx->optval */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optval)), + /* r2 = ctx->optval */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + /* r6 = ctx->optval + 1 */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + + /* r7 = ctx->optval_end */ + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1, + offsetof(struct bpf_sockopt, optval_end)), + + /* if (ctx->optval + 1 <= ctx->optval_end) { */ + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1), + /* ctx->optval[0] = 0xF0 */ + BPF_ST_MEM(BPF_B, BPF_REG_2, 0, 0xFF), + /* } */ + + /* retval changes are ignored */ + /* ctx->retval = 5 */ + BPF_MOV64_IMM(BPF_REG_0, 5), BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, offsetof(struct bpf_sockopt, retval)), @@ -287,9 +313,11 @@ static struct sockopt_test { .attach_type = BPF_CGROUP_GETSOCKOPT, .expected_attach_type = BPF_CGROUP_GETSOCKOPT, - .get_optlen = 64, - - .error = EFAULT_GETSOCKOPT, + .get_level = 1234, + .get_optname = 5678, + .get_optval = {}, /* the changes are ignored */ + .get_optlen = PAGE_SIZE + 1, + .error = EOPNOTSUPP_GETSOCKOPT, }, { .descr = "getsockopt: support smaller ctx->optlen", @@ -649,6 +677,45 @@ static struct sockopt_test { .error = EFAULT_SETSOCKOPT, }, { + .descr = "setsockopt: ignore >PAGE_SIZE optlen", + .insns = { + /* write 0xFF to the first optval byte */ + + /* r6 = ctx->optval */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optval)), + /* r2 = ctx->optval */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + /* r6 = ctx->optval + 1 */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + + /* r7 = ctx->optval_end */ + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1, + offsetof(struct bpf_sockopt, optval_end)), + + /* if (ctx->optval + 1 <= ctx->optval_end) { */ + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1), + /* ctx->optval[0] = 0xF0 */ + BPF_ST_MEM(BPF_B, BPF_REG_2, 0, 0xF0), + /* } */ + + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .set_level = SOL_IP, + .set_optname = IP_TOS, + .set_optval = {}, + .set_optlen = PAGE_SIZE + 1, + + .get_level = SOL_IP, + .get_optname = IP_TOS, + .get_optval = {}, /* the changes are ignored */ + .get_optlen = 4, + }, + { .descr = "setsockopt: allow changing ctx->optlen within bounds", .insns = { /* r6 = ctx->optval */ @@ -906,6 +973,13 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) } if (test->set_optlen) { + if (test->set_optlen >= PAGE_SIZE) { + int num_pages = test->set_optlen / PAGE_SIZE; + int remainder = test->set_optlen % PAGE_SIZE; + + test->set_optlen = num_pages * sysconf(_SC_PAGESIZE) + remainder; + } + err = setsockopt(sock_fd, test->set_level, test->set_optname, test->set_optval, test->set_optlen); if (err) { @@ -921,7 +995,15 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) } if (test->get_optlen) { + if (test->get_optlen >= PAGE_SIZE) { + int num_pages = test->get_optlen / PAGE_SIZE; + int remainder = test->get_optlen % PAGE_SIZE; + + test->get_optlen = num_pages * sysconf(_SC_PAGESIZE) + remainder; + } + optval = malloc(test->get_optlen); + memset(optval, 0, test->get_optlen); socklen_t optlen = test->get_optlen; socklen_t expected_get_optlen = test->get_optlen_ret ?: test->get_optlen; @@ -929,6 +1011,8 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) err = getsockopt(sock_fd, test->get_level, test->get_optname, optval, &optlen); if (err) { + if (errno == EOPNOTSUPP && test->error == EOPNOTSUPP_GETSOCKOPT) + goto free_optval; if (errno == EPERM && test->error == EPERM_GETSOCKOPT) goto free_optval; if (errno == EFAULT && test->error == EFAULT_GETSOCKOPT) @@ -976,7 +1060,9 @@ void test_sockopt(void) return; for (i = 0; i < ARRAY_SIZE(tests); i++) { - test__start_subtest(tests[i].descr); + if (!test__start_subtest(tests[i].descr)) + continue; + ASSERT_OK(run_test(cgroup_fd, &tests[i]), tests[i].descr); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c index 60c17a8e2789..917f486db826 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c @@ -2,6 +2,8 @@ #include <test_progs.h> #include "cgroup_helpers.h" +#include "sockopt_inherit.skel.h" + #define SOL_CUSTOM 0xdeadbeef #define CUSTOM_INHERIT1 0 #define CUSTOM_INHERIT2 1 @@ -132,58 +134,30 @@ static int start_server(void) return fd; } -static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title, - const char *prog_name) -{ - enum bpf_attach_type attach_type; - enum bpf_prog_type prog_type; - struct bpf_program *prog; - int err; - - err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); - if (err) { - log_err("Failed to deduct types for %s BPF program", prog_name); - return -1; - } - - prog = bpf_object__find_program_by_name(obj, prog_name); - if (!prog) { - log_err("Failed to find %s BPF program", prog_name); - return -1; - } - - err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, - attach_type, 0); - if (err) { - log_err("Failed to attach %s BPF program", prog_name); - return -1; - } - - return 0; -} - static void run_test(int cgroup_fd) { + struct bpf_link *link_getsockopt = NULL; + struct bpf_link *link_setsockopt = NULL; int server_fd = -1, client_fd; - struct bpf_object *obj; + struct sockopt_inherit *obj; void *server_err; pthread_t tid; int err; - obj = bpf_object__open_file("sockopt_inherit.bpf.o", NULL); - if (!ASSERT_OK_PTR(obj, "obj_open")) + obj = sockopt_inherit__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) return; - err = bpf_object__load(obj); - if (!ASSERT_OK(err, "obj_load")) - goto close_bpf_object; + obj->bss->page_size = sysconf(_SC_PAGESIZE); - err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt", "_getsockopt"); - if (!ASSERT_OK(err, "prog_attach _getsockopt")) + link_getsockopt = bpf_program__attach_cgroup(obj->progs._getsockopt, + cgroup_fd); + if (!ASSERT_OK_PTR(link_getsockopt, "cg-attach-getsockopt")) goto close_bpf_object; - err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt", "_setsockopt"); - if (!ASSERT_OK(err, "prog_attach _setsockopt")) + link_setsockopt = bpf_program__attach_cgroup(obj->progs._setsockopt, + cgroup_fd); + if (!ASSERT_OK_PTR(link_setsockopt, "cg-attach-setsockopt")) goto close_bpf_object; server_fd = start_server(); @@ -217,7 +191,10 @@ static void run_test(int cgroup_fd) close_server_fd: close(server_fd); close_bpf_object: - bpf_object__close(obj); + bpf_link__destroy(link_getsockopt); + bpf_link__destroy(link_setsockopt); + + sockopt_inherit__destroy(obj); } void test_sockopt_inherit(void) diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c index 7f5659349011..759bbb6f8c5f 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c @@ -2,61 +2,13 @@ #include <test_progs.h> #include "cgroup_helpers.h" -static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name) -{ - enum bpf_attach_type attach_type; - enum bpf_prog_type prog_type; - struct bpf_program *prog; - int err; - - err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); - if (err) { - log_err("Failed to deduct types for %s BPF program", title); - return -1; - } - - prog = bpf_object__find_program_by_name(obj, name); - if (!prog) { - log_err("Failed to find %s BPF program", name); - return -1; - } - - err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, - attach_type, BPF_F_ALLOW_MULTI); - if (err) { - log_err("Failed to attach %s BPF program", name); - return -1; - } - - return 0; -} +#include "sockopt_multi.skel.h" -static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name) -{ - enum bpf_attach_type attach_type; - enum bpf_prog_type prog_type; - struct bpf_program *prog; - int err; - - err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); - if (err) - return -1; - - prog = bpf_object__find_program_by_name(obj, name); - if (!prog) - return -1; - - err = bpf_prog_detach2(bpf_program__fd(prog), cgroup_fd, - attach_type); - if (err) - return -1; - - return 0; -} - -static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, +static int run_getsockopt_test(struct sockopt_multi *obj, int cg_parent, int cg_child, int sock_fd) { + struct bpf_link *link_parent = NULL; + struct bpf_link *link_child = NULL; socklen_t optlen; __u8 buf; int err; @@ -89,8 +41,9 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - child: 0x80 -> 0x90 */ - err = prog_attach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); - if (err) + link_child = bpf_program__attach_cgroup(obj->progs._getsockopt_child, + cg_child); + if (!ASSERT_OK_PTR(link_child, "cg-attach-getsockopt_child")) goto detach; buf = 0x00; @@ -113,8 +66,9 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - parent: 0x90 -> 0xA0 */ - err = prog_attach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent"); - if (err) + link_parent = bpf_program__attach_cgroup(obj->progs._getsockopt_parent, + cg_parent); + if (!ASSERT_OK_PTR(link_parent, "cg-attach-getsockopt_parent")) goto detach; buf = 0x00; @@ -157,11 +111,8 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - parent: unexpected 0x40, EPERM */ - err = prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); - if (err) { - log_err("Failed to detach child program"); - goto detach; - } + bpf_link__destroy(link_child); + link_child = NULL; buf = 0x00; optlen = 1; @@ -198,15 +149,17 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, } detach: - prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); - prog_detach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent"); + bpf_link__destroy(link_child); + bpf_link__destroy(link_parent); return err; } -static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, +static int run_setsockopt_test(struct sockopt_multi *obj, int cg_parent, int cg_child, int sock_fd) { + struct bpf_link *link_parent = NULL; + struct bpf_link *link_child = NULL; socklen_t optlen; __u8 buf; int err; @@ -236,8 +189,9 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, /* Attach child program and make sure it adds 0x10. */ - err = prog_attach(obj, cg_child, "cgroup/setsockopt", "_setsockopt"); - if (err) + link_child = bpf_program__attach_cgroup(obj->progs._setsockopt, + cg_child); + if (!ASSERT_OK_PTR(link_child, "cg-attach-setsockopt_child")) goto detach; buf = 0x80; @@ -263,8 +217,9 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, /* Attach parent program and make sure it adds another 0x10. */ - err = prog_attach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt"); - if (err) + link_parent = bpf_program__attach_cgroup(obj->progs._setsockopt, + cg_parent); + if (!ASSERT_OK_PTR(link_parent, "cg-attach-setsockopt_parent")) goto detach; buf = 0x80; @@ -289,8 +244,8 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, } detach: - prog_detach(obj, cg_child, "cgroup/setsockopt", "_setsockopt"); - prog_detach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt"); + bpf_link__destroy(link_child); + bpf_link__destroy(link_parent); return err; } @@ -298,9 +253,8 @@ detach: void test_sockopt_multi(void) { int cg_parent = -1, cg_child = -1; - struct bpf_object *obj = NULL; + struct sockopt_multi *obj = NULL; int sock_fd = -1; - int err = -1; cg_parent = test__join_cgroup("/parent"); if (!ASSERT_GE(cg_parent, 0, "join_cgroup /parent")) @@ -310,13 +264,11 @@ void test_sockopt_multi(void) if (!ASSERT_GE(cg_child, 0, "join_cgroup /parent/child")) goto out; - obj = bpf_object__open_file("sockopt_multi.bpf.o", NULL); - if (!ASSERT_OK_PTR(obj, "obj_load")) + obj = sockopt_multi__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) goto out; - err = bpf_object__load(obj); - if (!ASSERT_OK(err, "obj_load")) - goto out; + obj->bss->page_size = sysconf(_SC_PAGESIZE); sock_fd = socket(AF_INET, SOCK_STREAM, 0); if (!ASSERT_GE(sock_fd, 0, "socket")) @@ -327,7 +279,7 @@ void test_sockopt_multi(void) out: close(sock_fd); - bpf_object__close(obj); + sockopt_multi__destroy(obj); close(cg_child); close(cg_parent); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c index 6b53b3cb8dad..6b2d300e9fd4 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c @@ -42,6 +42,8 @@ void test_sockopt_qos_to_cc(void) if (!ASSERT_OK_PTR(skel, "skel")) goto done; + skel->bss->page_size = sysconf(_SC_PAGESIZE); + sock_fd = socket(AF_INET6, SOCK_STREAM, 0); if (!ASSERT_GE(sock_fd, 0, "v6 socket open")) goto done; diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index 4512dd808c33..05d0e07da394 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -209,7 +209,7 @@ static int getsetsockopt(void) err, errno); goto err; } - ASSERT_EQ(optlen, 4, "Unexpected NETLINK_LIST_MEMBERSHIPS value"); + ASSERT_EQ(optlen, 8, "Unexpected NETLINK_LIST_MEMBERSHIPS value"); free(big_buf); close(fd); diff --git a/tools/testing/selftests/bpf/prog_tests/subprogs_extable.c b/tools/testing/selftests/bpf/prog_tests/subprogs_extable.c new file mode 100644 index 000000000000..3afd9f775f68 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/subprogs_extable.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include "test_subprogs_extable.skel.h" + +void test_subprogs_extable(void) +{ + const int read_sz = 456; + struct test_subprogs_extable *skel; + int err; + + skel = test_subprogs_extable__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + return; + + err = test_subprogs_extable__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto cleanup; + + /* trigger tracepoint */ + ASSERT_OK(trigger_module_test_read(read_sz), "trigger_read"); + + ASSERT_NEQ(skel->bss->triggered, 0, "verify at least one program ran"); + + test_subprogs_extable__detach(skel); + +cleanup: + test_subprogs_extable__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c b/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c new file mode 100644 index 000000000000..4224727fb364 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Bytedance */ + +#include <sys/syscall.h> +#include <test_progs.h> +#include <cgroup_helpers.h> +#include "test_task_under_cgroup.skel.h" + +#define FOO "/foo" + +void test_task_under_cgroup(void) +{ + struct test_task_under_cgroup *skel; + int ret, foo; + pid_t pid; + + foo = test__join_cgroup(FOO); + if (!ASSERT_OK(foo < 0, "cgroup_join_foo")) + return; + + skel = test_task_under_cgroup__open(); + if (!ASSERT_OK_PTR(skel, "test_task_under_cgroup__open")) + goto cleanup; + + skel->rodata->local_pid = getpid(); + skel->bss->remote_pid = getpid(); + skel->rodata->cgid = get_cgroup_id(FOO); + + ret = test_task_under_cgroup__load(skel); + if (!ASSERT_OK(ret, "test_task_under_cgroup__load")) + goto cleanup; + + ret = test_task_under_cgroup__attach(skel); + if (!ASSERT_OK(ret, "test_task_under_cgroup__attach")) + goto cleanup; + + pid = fork(); + if (pid == 0) + exit(0); + + ret = (pid == -1); + if (ASSERT_OK(ret, "fork process")) + wait(NULL); + + test_task_under_cgroup__detach(skel); + + ASSERT_NEQ(skel->bss->remote_pid, skel->rodata->local_pid, + "test task_under_cgroup"); + +cleanup: + test_task_under_cgroup__destroy(skel); + close(foo); +} diff --git a/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c b/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c index 8383a99f610f..0adf8d9475cb 100644 --- a/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c +++ b/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c @@ -171,7 +171,11 @@ static void test_unpriv_bpf_disabled_negative(struct test_unpriv_bpf_disabled *s prog_insns, prog_insn_cnt, &load_opts), -EPERM, "prog_load_fails"); - for (i = BPF_MAP_TYPE_HASH; i <= BPF_MAP_TYPE_BLOOM_FILTER; i++) + /* some map types require particular correct parameters which could be + * sanity-checked before enforcing -EPERM, so only validate that + * the simple ARRAY and HASH maps are failing with -EPERM + */ + for (i = BPF_MAP_TYPE_HASH; i <= BPF_MAP_TYPE_ARRAY; i++) ASSERT_EQ(bpf_map_create(i, NULL, sizeof(int), sizeof(int), 1, NULL), -EPERM, "map_create_fails"); diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 2497716ee379..070a13833c3f 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -50,11 +50,13 @@ #include "verifier_regalloc.skel.h" #include "verifier_ringbuf.skel.h" #include "verifier_runtime_jit.skel.h" +#include "verifier_scalar_ids.skel.h" #include "verifier_search_pruning.skel.h" #include "verifier_sock.skel.h" #include "verifier_spill_fill.skel.h" #include "verifier_spin_lock.skel.h" #include "verifier_stack_ptr.skel.h" +#include "verifier_subprog_precision.skel.h" #include "verifier_subreg.skel.h" #include "verifier_uninit.skel.h" #include "verifier_unpriv.skel.h" @@ -149,11 +151,13 @@ void test_verifier_ref_tracking(void) { RUN(verifier_ref_tracking); } void test_verifier_regalloc(void) { RUN(verifier_regalloc); } void test_verifier_ringbuf(void) { RUN(verifier_ringbuf); } void test_verifier_runtime_jit(void) { RUN(verifier_runtime_jit); } +void test_verifier_scalar_ids(void) { RUN(verifier_scalar_ids); } void test_verifier_search_pruning(void) { RUN(verifier_search_pruning); } void test_verifier_sock(void) { RUN(verifier_sock); } void test_verifier_spill_fill(void) { RUN(verifier_spill_fill); } void test_verifier_spin_lock(void) { RUN(verifier_spin_lock); } void test_verifier_stack_ptr(void) { RUN(verifier_stack_ptr); } +void test_verifier_subprog_precision(void) { RUN(verifier_subprog_precision); } void test_verifier_subreg(void) { RUN(verifier_subreg); } void test_verifier_uninit(void) { RUN(verifier_uninit); } void test_verifier_unpriv(void) { RUN(verifier_unpriv); } diff --git a/tools/testing/selftests/bpf/prog_tests/vrf_socket_lookup.c b/tools/testing/selftests/bpf/prog_tests/vrf_socket_lookup.c new file mode 100644 index 000000000000..2a5e207edad6 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/vrf_socket_lookup.c @@ -0,0 +1,312 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + +/* + * Topology: + * --------- + * NS0 namespace | NS1 namespace + * | + * +--------------+ | +--------------+ + * | veth01 |----------| veth10 | + * | 172.16.1.100 | | | 172.16.1.200 | + * | bpf | | +--------------+ + * +--------------+ | + * server(UDP/TCP) | + * +-------------------+ | + * | vrf1 | | + * | +--------------+ | | +--------------+ + * | | veth02 |----------| veth20 | + * | | 172.16.2.100 | | | | 172.16.2.200 | + * | | bpf | | | +--------------+ + * | +--------------+ | | + * | server(UDP/TCP) | | + * +-------------------+ | + * + * Test flow + * ----------- + * The tests verifies that socket lookup via TC is VRF aware: + * 1) Creates two veth pairs between NS0 and NS1: + * a) veth01 <-> veth10 outside the VRF + * b) veth02 <-> veth20 in the VRF + * 2) Attaches to veth01 and veth02 a program that calls: + * a) bpf_skc_lookup_tcp() with TCP and tcp_skc is true + * b) bpf_sk_lookup_tcp() with TCP and tcp_skc is false + * c) bpf_sk_lookup_udp() with UDP + * The program stores the lookup result in bss->lookup_status. + * 3) Creates a socket TCP/UDP server in/outside the VRF. + * 4) The test expects lookup_status to be: + * a) 0 from device in VRF to server outside VRF + * b) 0 from device outside VRF to server in VRF + * c) 1 from device in VRF to server in VRF + * d) 1 from device outside VRF to server outside VRF + */ + +#include <net/if.h> + +#include "test_progs.h" +#include "network_helpers.h" +#include "vrf_socket_lookup.skel.h" + +#define NS0 "vrf_socket_lookup_0" +#define NS1 "vrf_socket_lookup_1" + +#define IP4_ADDR_VETH01 "172.16.1.100" +#define IP4_ADDR_VETH10 "172.16.1.200" +#define IP4_ADDR_VETH02 "172.16.2.100" +#define IP4_ADDR_VETH20 "172.16.2.200" + +#define NON_VRF_PORT 5000 +#define IN_VRF_PORT 5001 + +#define TIMEOUT_MS 3000 + +static int make_socket(int sotype, const char *ip, int port, + struct sockaddr_storage *addr) +{ + int err, fd; + + err = make_sockaddr(AF_INET, ip, port, addr, NULL); + if (!ASSERT_OK(err, "make_address")) + return -1; + + fd = socket(AF_INET, sotype, 0); + if (!ASSERT_GE(fd, 0, "socket")) + return -1; + + if (!ASSERT_OK(settimeo(fd, TIMEOUT_MS), "settimeo")) + goto fail; + + return fd; +fail: + close(fd); + return -1; +} + +static int make_server(int sotype, const char *ip, int port, const char *ifname) +{ + int err, fd = -1; + + fd = start_server(AF_INET, sotype, ip, port, TIMEOUT_MS); + if (!ASSERT_GE(fd, 0, "start_server")) + return -1; + + if (ifname) { + err = setsockopt(fd, SOL_SOCKET, SO_BINDTODEVICE, + ifname, strlen(ifname) + 1); + if (!ASSERT_OK(err, "setsockopt(SO_BINDTODEVICE)")) + goto fail; + } + + return fd; +fail: + close(fd); + return -1; +} + +static int attach_progs(char *ifname, int tc_prog_fd, int xdp_prog_fd) +{ + LIBBPF_OPTS(bpf_tc_hook, hook, .attach_point = BPF_TC_INGRESS); + LIBBPF_OPTS(bpf_tc_opts, opts, .handle = 1, .priority = 1, + .prog_fd = tc_prog_fd); + int ret, ifindex; + + ifindex = if_nametoindex(ifname); + if (!ASSERT_NEQ(ifindex, 0, "if_nametoindex")) + return -1; + hook.ifindex = ifindex; + + ret = bpf_tc_hook_create(&hook); + if (!ASSERT_OK(ret, "bpf_tc_hook_create")) + return ret; + + ret = bpf_tc_attach(&hook, &opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) { + bpf_tc_hook_destroy(&hook); + return ret; + } + ret = bpf_xdp_attach(ifindex, xdp_prog_fd, 0, NULL); + if (!ASSERT_OK(ret, "bpf_xdp_attach")) { + bpf_tc_hook_destroy(&hook); + return ret; + } + + return 0; +} + +static void cleanup(void) +{ + SYS_NOFAIL("test -f /var/run/netns/" NS0 " && ip netns delete " + NS0); + SYS_NOFAIL("test -f /var/run/netns/" NS1 " && ip netns delete " + NS1); +} + +static int setup(struct vrf_socket_lookup *skel) +{ + int tc_prog_fd, xdp_prog_fd, ret = 0; + struct nstoken *nstoken = NULL; + + SYS(fail, "ip netns add " NS0); + SYS(fail, "ip netns add " NS1); + + /* NS0 <-> NS1 [veth01 <-> veth10] */ + SYS(fail, "ip link add veth01 netns " NS0 " type veth peer name veth10" + " netns " NS1); + SYS(fail, "ip -net " NS0 " addr add " IP4_ADDR_VETH01 "/24 dev veth01"); + SYS(fail, "ip -net " NS0 " link set dev veth01 up"); + SYS(fail, "ip -net " NS1 " addr add " IP4_ADDR_VETH10 "/24 dev veth10"); + SYS(fail, "ip -net " NS1 " link set dev veth10 up"); + + /* NS0 <-> NS1 [veth02 <-> veth20] */ + SYS(fail, "ip link add veth02 netns " NS0 " type veth peer name veth20" + " netns " NS1); + SYS(fail, "ip -net " NS0 " addr add " IP4_ADDR_VETH02 "/24 dev veth02"); + SYS(fail, "ip -net " NS0 " link set dev veth02 up"); + SYS(fail, "ip -net " NS1 " addr add " IP4_ADDR_VETH20 "/24 dev veth20"); + SYS(fail, "ip -net " NS1 " link set dev veth20 up"); + + /* veth02 -> vrf1 */ + SYS(fail, "ip -net " NS0 " link add vrf1 type vrf table 11"); + SYS(fail, "ip -net " NS0 " route add vrf vrf1 unreachable default" + " metric 4278198272"); + SYS(fail, "ip -net " NS0 " link set vrf1 alias vrf"); + SYS(fail, "ip -net " NS0 " link set vrf1 up"); + SYS(fail, "ip -net " NS0 " link set veth02 master vrf1"); + + /* Attach TC and XDP progs to veth devices in NS0 */ + nstoken = open_netns(NS0); + if (!ASSERT_OK_PTR(nstoken, "setns " NS0)) + goto fail; + tc_prog_fd = bpf_program__fd(skel->progs.tc_socket_lookup); + if (!ASSERT_GE(tc_prog_fd, 0, "bpf_program__tc_fd")) + goto fail; + xdp_prog_fd = bpf_program__fd(skel->progs.xdp_socket_lookup); + if (!ASSERT_GE(xdp_prog_fd, 0, "bpf_program__xdp_fd")) + goto fail; + + if (attach_progs("veth01", tc_prog_fd, xdp_prog_fd)) + goto fail; + + if (attach_progs("veth02", tc_prog_fd, xdp_prog_fd)) + goto fail; + + goto close; +fail: + ret = -1; +close: + if (nstoken) + close_netns(nstoken); + return ret; +} + +static int test_lookup(struct vrf_socket_lookup *skel, int sotype, + const char *ip, int port, bool test_xdp, bool tcp_skc, + int lookup_status_exp) +{ + static const char msg[] = "Hello Server"; + struct sockaddr_storage addr = {}; + int fd, ret = 0; + + fd = make_socket(sotype, ip, port, &addr); + if (fd < 0) + return -1; + + skel->bss->test_xdp = test_xdp; + skel->bss->tcp_skc = tcp_skc; + skel->bss->lookup_status = -1; + + if (sotype == SOCK_STREAM) + connect(fd, (void *)&addr, sizeof(struct sockaddr_in)); + else + sendto(fd, msg, sizeof(msg), 0, (void *)&addr, + sizeof(struct sockaddr_in)); + + if (!ASSERT_EQ(skel->bss->lookup_status, lookup_status_exp, + "lookup_status")) + goto fail; + + goto close; + +fail: + ret = -1; +close: + close(fd); + return ret; +} + +static void _test_vrf_socket_lookup(struct vrf_socket_lookup *skel, int sotype, + bool test_xdp, bool tcp_skc) +{ + int in_vrf_server = -1, non_vrf_server = -1; + struct nstoken *nstoken = NULL; + + nstoken = open_netns(NS0); + if (!ASSERT_OK_PTR(nstoken, "setns " NS0)) + goto done; + + /* Open sockets in and outside VRF */ + non_vrf_server = make_server(sotype, "0.0.0.0", NON_VRF_PORT, NULL); + if (!ASSERT_GE(non_vrf_server, 0, "make_server__outside_vrf_fd")) + goto done; + + in_vrf_server = make_server(sotype, "0.0.0.0", IN_VRF_PORT, "veth02"); + if (!ASSERT_GE(in_vrf_server, 0, "make_server__in_vrf_fd")) + goto done; + + /* Perform test from NS1 */ + close_netns(nstoken); + nstoken = open_netns(NS1); + if (!ASSERT_OK_PTR(nstoken, "setns " NS1)) + goto done; + + if (!ASSERT_OK(test_lookup(skel, sotype, IP4_ADDR_VETH02, NON_VRF_PORT, + test_xdp, tcp_skc, 0), "in_to_out")) + goto done; + if (!ASSERT_OK(test_lookup(skel, sotype, IP4_ADDR_VETH02, IN_VRF_PORT, + test_xdp, tcp_skc, 1), "in_to_in")) + goto done; + if (!ASSERT_OK(test_lookup(skel, sotype, IP4_ADDR_VETH01, NON_VRF_PORT, + test_xdp, tcp_skc, 1), "out_to_out")) + goto done; + if (!ASSERT_OK(test_lookup(skel, sotype, IP4_ADDR_VETH01, IN_VRF_PORT, + test_xdp, tcp_skc, 0), "out_to_in")) + goto done; + +done: + if (non_vrf_server >= 0) + close(non_vrf_server); + if (in_vrf_server >= 0) + close(in_vrf_server); + if (nstoken) + close_netns(nstoken); +} + +void test_vrf_socket_lookup(void) +{ + struct vrf_socket_lookup *skel; + + cleanup(); + + skel = vrf_socket_lookup__open_and_load(); + if (!ASSERT_OK_PTR(skel, "vrf_socket_lookup__open_and_load")) + return; + + if (!ASSERT_OK(setup(skel), "setup")) + goto done; + + if (test__start_subtest("tc_socket_lookup_tcp")) + _test_vrf_socket_lookup(skel, SOCK_STREAM, false, false); + if (test__start_subtest("tc_socket_lookup_tcp_skc")) + _test_vrf_socket_lookup(skel, SOCK_STREAM, false, false); + if (test__start_subtest("tc_socket_lookup_udp")) + _test_vrf_socket_lookup(skel, SOCK_STREAM, false, false); + if (test__start_subtest("xdp_socket_lookup_tcp")) + _test_vrf_socket_lookup(skel, SOCK_STREAM, true, false); + if (test__start_subtest("xdp_socket_lookup_tcp_skc")) + _test_vrf_socket_lookup(skel, SOCK_STREAM, true, false); + if (test__start_subtest("xdp_socket_lookup_udp")) + _test_vrf_socket_lookup(skel, SOCK_STREAM, true, false); + +done: + vrf_socket_lookup__destroy(skel); + cleanup(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c index d19f79048ff6..c3b45745cbcc 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c @@ -18,6 +18,7 @@ #include <linux/if_bonding.h> #include <linux/limits.h> #include <linux/udp.h> +#include <uapi/linux/netdev.h> #include "xdp_dummy.skel.h" #include "xdp_redirect_multi_kern.skel.h" @@ -492,6 +493,123 @@ out: system("ip link del bond_nest2"); } +static void test_xdp_bonding_features(struct skeletons *skeletons) +{ + LIBBPF_OPTS(bpf_xdp_query_opts, query_opts); + int bond_idx, veth1_idx, err; + struct bpf_link *link = NULL; + + if (!ASSERT_OK(system("ip link add bond type bond"), "add bond")) + goto out; + + bond_idx = if_nametoindex("bond"); + if (!ASSERT_GE(bond_idx, 0, "if_nametoindex bond")) + goto out; + + /* query default xdp-feature for bond device */ + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK, + "bond query_opts.feature_flags")) + goto out; + + if (!ASSERT_OK(system("ip link add veth0 type veth peer name veth1"), + "add veth{0,1} pair")) + goto out; + + if (!ASSERT_OK(system("ip link add veth2 type veth peer name veth3"), + "add veth{2,3} pair")) + goto out; + + if (!ASSERT_OK(system("ip link set veth0 master bond"), + "add veth0 to master bond")) + goto out; + + /* xdp-feature for bond device should be obtained from the single slave + * device (veth0) + */ + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG, + "bond query_opts.feature_flags")) + goto out; + + veth1_idx = if_nametoindex("veth1"); + if (!ASSERT_GE(veth1_idx, 0, "if_nametoindex veth1")) + goto out; + + link = bpf_program__attach_xdp(skeletons->xdp_dummy->progs.xdp_dummy_prog, + veth1_idx); + if (!ASSERT_OK_PTR(link, "attach program to veth1")) + goto out; + + /* xdp-feature for veth0 are changed */ + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG | NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "bond query_opts.feature_flags")) + goto out; + + if (!ASSERT_OK(system("ip link set veth2 master bond"), + "add veth2 to master bond")) + goto out; + + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + /* xdp-feature for bond device should be set to the most restrict + * value obtained from attached slave devices (veth0 and veth2) + */ + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG, + "bond query_opts.feature_flags")) + goto out; + + if (!ASSERT_OK(system("ip link set veth2 nomaster"), + "del veth2 to master bond")) + goto out; + + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG | NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "bond query_opts.feature_flags")) + goto out; + + if (!ASSERT_OK(system("ip link set veth0 nomaster"), + "del veth0 to master bond")) + goto out; + + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK, + "bond query_opts.feature_flags"); +out: + bpf_link__destroy(link); + system("ip link del veth0"); + system("ip link del veth2"); + system("ip link del bond"); +} + static int libbpf_debug_print(enum libbpf_print_level level, const char *format, va_list args) { @@ -546,6 +664,9 @@ void serial_test_xdp_bonding(void) if (test__start_subtest("xdp_bonding_nested")) test_xdp_bonding_nested(&skeletons); + if (test__start_subtest("xdp_bonding_features")) + test_xdp_bonding_features(&skeletons); + for (i = 0; i < ARRAY_SIZE(bond_test_cases); i++) { struct bond_test_case *test_case = &bond_test_cases[i]; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c b/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c index 5ddcc46fd886..521267818f4d 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c @@ -59,9 +59,7 @@ int dump_ksym(struct bpf_iter__ksym *ctx) } else { BPF_SEQ_PRINTF(seq, "0x%llx %c %s ", value, type, iter->name); } - if (!iter->pos_arch_end || iter->pos_arch_end > iter->pos) - BPF_SEQ_PRINTF(seq, "CORE "); - else if (!iter->pos_mod_end || iter->pos_mod_end > iter->pos) + if (!iter->pos_mod_end || iter->pos_mod_end > iter->pos) BPF_SEQ_PRINTF(seq, "MOD "); else if (!iter->pos_ftrace_mod_end || iter->pos_ftrace_mod_end > iter->pos) BPF_SEQ_PRINTF(seq, "FTRACE_MOD "); diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h index d3c1217ba79a..38a57a2e70db 100644 --- a/tools/testing/selftests/bpf/progs/bpf_misc.h +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -86,6 +86,10 @@ #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 +#ifndef __used +#define __used __attribute__((used)) +#endif + #if defined(__TARGET_ARCH_x86) #define SYSCALL_WRAPPER 1 #define SYS_PREFIX "__x64_" diff --git a/tools/testing/selftests/bpf/progs/cb_refs.c b/tools/testing/selftests/bpf/progs/cb_refs.c index 50f95ec61165..76d661b20e87 100644 --- a/tools/testing/selftests/bpf/progs/cb_refs.c +++ b/tools/testing/selftests/bpf/progs/cb_refs.c @@ -2,6 +2,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct map_value { struct prog_test_ref_kfunc __kptr *ptr; @@ -14,9 +15,6 @@ struct { __uint(max_entries, 16); } array_map SEC(".maps"); -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; - static __noinline int cb1(void *map, void *key, void *value, void *ctx) { void *p = *(void **)ctx; diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c index b2a409e6382a..932b8ecd4ae3 100644 --- a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c @@ -12,6 +12,7 @@ __u32 invocations = 0; __u32 assertion_error = 0; __u32 retval_value = 0; __u32 ctx_retval_value = 0; +__u32 page_size = 0; SEC("cgroup/getsockopt") int get_retval(struct bpf_sockopt *ctx) @@ -20,6 +21,10 @@ int get_retval(struct bpf_sockopt *ctx) ctx_retval_value = ctx->retval; __sync_fetch_and_add(&invocations, 1); + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } @@ -31,6 +36,10 @@ int set_eisconn(struct bpf_sockopt *ctx) if (bpf_set_retval(-EISCONN)) assertion_error = 1; + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } @@ -41,5 +50,9 @@ int clear_retval(struct bpf_sockopt *ctx) ctx->retval = 0; + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c index d6e5903e06ba..b7fa8804e19d 100644 --- a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c @@ -11,6 +11,7 @@ __u32 invocations = 0; __u32 assertion_error = 0; __u32 retval_value = 0; +__u32 page_size = 0; SEC("cgroup/setsockopt") int get_retval(struct bpf_sockopt *ctx) @@ -18,6 +19,10 @@ int get_retval(struct bpf_sockopt *ctx) retval_value = bpf_get_retval(); __sync_fetch_and_add(&invocations, 1); + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } @@ -29,6 +34,10 @@ int set_eunatch(struct bpf_sockopt *ctx) if (bpf_set_retval(-EUNATCH)) assertion_error = 1; + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 0; } @@ -40,6 +49,10 @@ int set_eisconn(struct bpf_sockopt *ctx) if (bpf_set_retval(-EISCONN)) assertion_error = 1; + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 0; } @@ -48,5 +61,9 @@ int legacy_eperm(struct bpf_sockopt *ctx) { __sync_fetch_and_add(&invocations, 1); + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 0; } diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h index 0c5b785a93e4..b15c588ace15 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_common.h +++ b/tools/testing/selftests/bpf/progs/cpumask_common.h @@ -28,6 +28,8 @@ void bpf_cpumask_release(struct bpf_cpumask *cpumask) __ksym; struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) __ksym; u32 bpf_cpumask_first(const struct cpumask *cpumask) __ksym; u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym; +u32 bpf_cpumask_first_and(const struct cpumask *src1, + const struct cpumask *src2) __ksym; void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym; void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym; bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask) __ksym; @@ -50,8 +52,8 @@ bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2) bool bpf_cpumask_empty(const struct cpumask *cpumask) __ksym; bool bpf_cpumask_full(const struct cpumask *cpumask) __ksym; void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym; -u32 bpf_cpumask_any(const struct cpumask *src) __ksym; -u32 bpf_cpumask_any_and(const struct cpumask *src1, const struct cpumask *src2) __ksym; +u32 bpf_cpumask_any_distribute(const struct cpumask *src) __ksym; +u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, const struct cpumask *src2) __ksym; void bpf_rcu_read_lock(void) __ksym; void bpf_rcu_read_unlock(void) __ksym; diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c index 2fcdd7f68ac7..674a63424dee 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_success.c +++ b/tools/testing/selftests/bpf/progs/cpumask_success.c @@ -5,6 +5,7 @@ #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" #include "cpumask_common.h" char _license[] SEC("license") = "GPL"; @@ -175,6 +176,38 @@ release_exit: } SEC("tp_btf/task_newtask") +int BPF_PROG(test_firstand_nocpu, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *mask1, *mask2; + u32 first; + + if (!is_test_task()) + return 0; + + mask1 = create_cpumask(); + if (!mask1) + return 0; + + mask2 = create_cpumask(); + if (!mask2) + goto release_exit; + + bpf_cpumask_set_cpu(0, mask1); + bpf_cpumask_set_cpu(1, mask2); + + first = bpf_cpumask_first_and(cast(mask1), cast(mask2)); + if (first <= 1) + err = 3; + +release_exit: + if (mask1) + bpf_cpumask_release(mask1); + if (mask2) + bpf_cpumask_release(mask2); + return 0; +} + +SEC("tp_btf/task_newtask") int BPF_PROG(test_test_and_set_clear, struct task_struct *task, u64 clone_flags) { struct bpf_cpumask *cpumask; @@ -311,13 +344,13 @@ int BPF_PROG(test_copy_any_anyand, struct task_struct *task, u64 clone_flags) bpf_cpumask_set_cpu(1, mask2); bpf_cpumask_or(dst1, cast(mask1), cast(mask2)); - cpu = bpf_cpumask_any(cast(mask1)); + cpu = bpf_cpumask_any_distribute(cast(mask1)); if (cpu != 0) { err = 6; goto release_exit; } - cpu = bpf_cpumask_any(cast(dst2)); + cpu = bpf_cpumask_any_distribute(cast(dst2)); if (cpu < nr_cpus) { err = 7; goto release_exit; @@ -329,13 +362,13 @@ int BPF_PROG(test_copy_any_anyand, struct task_struct *task, u64 clone_flags) goto release_exit; } - cpu = bpf_cpumask_any(cast(dst2)); + cpu = bpf_cpumask_any_distribute(cast(dst2)); if (cpu > 1) { err = 9; goto release_exit; } - cpu = bpf_cpumask_any_and(cast(mask1), cast(mask2)); + cpu = bpf_cpumask_any_and_distribute(cast(mask1), cast(mask2)); if (cpu < nr_cpus) { err = 10; goto release_exit; @@ -426,3 +459,26 @@ int BPF_PROG(test_global_mask_rcu, struct task_struct *task, u64 clone_flags) return 0; } + +SEC("tp_btf/task_newtask") +__success +int BPF_PROG(test_refcount_null_tracking, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *mask1, *mask2; + + mask1 = bpf_cpumask_create(); + mask2 = bpf_cpumask_create(); + + if (!mask1 || !mask2) + goto free_masks_return; + + bpf_cpumask_test_cpu(0, (const struct cpumask *)mask1); + bpf_cpumask_test_cpu(0, (const struct cpumask *)mask2); + +free_masks_return: + if (mask1) + bpf_cpumask_release(mask1); + if (mask2) + bpf_cpumask_release(mask2); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index 759eb5c245cd..7ce7e827d5f0 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -3,6 +3,7 @@ #include <errno.h> #include <string.h> +#include <stdbool.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include <linux/if_ether.h> @@ -1378,3 +1379,310 @@ int invalid_slice_rdwr_rdonly(struct __sk_buff *skb) return 0; } + +/* bpf_dynptr_adjust can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_adjust_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_adjust(&ptr, 1, 2); + + return 0; +} + +/* bpf_dynptr_is_null can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_is_null_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_is_null(&ptr); + + return 0; +} + +/* bpf_dynptr_is_rdonly can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_is_rdonly_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_is_rdonly(&ptr); + + return 0; +} + +/* bpf_dynptr_size can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_size_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_size(&ptr); + + return 0; +} + +/* Only initialized dynptrs can be cloned */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int clone_invalid1(void *ctx) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + + /* this should fail */ + bpf_dynptr_clone(&ptr1, &ptr2); + + return 0; +} + +/* Can't overwrite an existing dynptr when cloning */ +SEC("?xdp") +__failure __msg("cannot overwrite referenced dynptr") +int clone_invalid2(struct xdp_md *xdp) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr clone; + + bpf_dynptr_from_xdp(xdp, 0, &ptr1); + + bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &clone); + + /* this should fail */ + bpf_dynptr_clone(&ptr1, &clone); + + bpf_ringbuf_submit_dynptr(&clone, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate its clones */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #3") +int clone_invalidate1(void *ctx) +{ + struct bpf_dynptr clone; + struct bpf_dynptr ptr; + char read_data[64]; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + + bpf_ringbuf_submit_dynptr(&ptr, 0); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &clone, 0, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate its parent */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #3") +int clone_invalidate2(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone; + char read_data[64]; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + + bpf_ringbuf_submit_dynptr(&clone, 0); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate its siblings */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #3") +int clone_invalidate3(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone1; + struct bpf_dynptr clone2; + char read_data[64]; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone1); + + bpf_dynptr_clone(&ptr, &clone2); + + bpf_ringbuf_submit_dynptr(&clone2, 0); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &clone1, 0, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate any data slices + * of its clones + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int clone_invalidate4(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone; + int *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + data = bpf_dynptr_data(&clone, 0, sizeof(val)); + if (!data) + return 0; + + bpf_ringbuf_submit_dynptr(&ptr, 0); + + /* this should fail */ + *data = 123; + + return 0; +} + +/* Invalidating a dynptr should invalidate any data slices + * of its parent + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int clone_invalidate5(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone; + int *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + data = bpf_dynptr_data(&ptr, 0, sizeof(val)); + if (!data) + return 0; + + bpf_dynptr_clone(&ptr, &clone); + + bpf_ringbuf_submit_dynptr(&clone, 0); + + /* this should fail */ + *data = 123; + + return 0; +} + +/* Invalidating a dynptr should invalidate any data slices + * of its sibling + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int clone_invalidate6(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone1; + struct bpf_dynptr clone2; + int *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone1); + + bpf_dynptr_clone(&ptr, &clone2); + + data = bpf_dynptr_data(&clone1, 0, sizeof(val)); + if (!data) + return 0; + + bpf_ringbuf_submit_dynptr(&clone2, 0); + + /* this should fail */ + *data = 123; + + return 0; +} + +/* A skb clone's data slices should be invalid anytime packet data changes */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int clone_skb_packet_data(struct __sk_buff *skb) +{ + char buffer[sizeof(__u32)] = {}; + struct bpf_dynptr clone; + struct bpf_dynptr ptr; + __u32 *data; + + bpf_dynptr_from_skb(skb, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + data = bpf_dynptr_slice_rdwr(&clone, 0, buffer, sizeof(buffer)); + if (!data) + return XDP_DROP; + + if (bpf_skb_pull_data(skb, skb->len)) + return SK_DROP; + + /* this should fail */ + *data = 123; + + return 0; +} + +/* A xdp clone's data slices should be invalid anytime packet data changes */ +SEC("?xdp") +__failure __msg("invalid mem access 'scalar'") +int clone_xdp_packet_data(struct xdp_md *xdp) +{ + char buffer[sizeof(__u32)] = {}; + struct bpf_dynptr clone; + struct bpf_dynptr ptr; + struct ethhdr *hdr; + __u32 *data; + + bpf_dynptr_from_xdp(xdp, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + data = bpf_dynptr_slice_rdwr(&clone, 0, buffer, sizeof(buffer)); + if (!data) + return XDP_DROP; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(*hdr))) + return XDP_DROP; + + /* this should fail */ + *data = 123; + + return 0; +} + +/* Buffers that are provided must be sufficiently long */ +SEC("?cgroup_skb/egress") +__failure __msg("memory, len pair leads to invalid memory access") +int test_dynptr_skb_small_buff(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + char buffer[8] = {}; + __u64 *data; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* This may return NULL. SKB may require a buffer */ + data = bpf_dynptr_slice(&ptr, 0, buffer, 9); + + return !!data; +} diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c index b2fa6c47ecc0..5985920d162e 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_success.c +++ b/tools/testing/selftests/bpf/progs/dynptr_success.c @@ -2,6 +2,7 @@ /* Copyright (c) 2022 Facebook */ #include <string.h> +#include <stdbool.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include "bpf_misc.h" @@ -207,3 +208,339 @@ int test_dynptr_skb_data(struct __sk_buff *skb) return 1; } + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_adjust(void *ctx) +{ + struct bpf_dynptr ptr; + __u32 bytes = 64; + __u32 off = 10; + __u32 trim = 15; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + err = bpf_ringbuf_reserve_dynptr(&ringbuf, bytes, 0, &ptr); + if (err) { + err = 1; + goto done; + } + + if (bpf_dynptr_size(&ptr) != bytes) { + err = 2; + goto done; + } + + /* Advance the dynptr by off */ + err = bpf_dynptr_adjust(&ptr, off, bpf_dynptr_size(&ptr)); + if (err) { + err = 3; + goto done; + } + + if (bpf_dynptr_size(&ptr) != bytes - off) { + err = 4; + goto done; + } + + /* Trim the dynptr */ + err = bpf_dynptr_adjust(&ptr, off, 15); + if (err) { + err = 5; + goto done; + } + + /* Check that the size was adjusted correctly */ + if (bpf_dynptr_size(&ptr) != trim - off) { + err = 6; + goto done; + } + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_adjust_err(void *ctx) +{ + char write_data[45] = "hello there, world!!"; + struct bpf_dynptr ptr; + __u32 size = 64; + __u32 off = 20; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr)) { + err = 1; + goto done; + } + + /* Check that start can't be greater than end */ + if (bpf_dynptr_adjust(&ptr, 5, 1) != -EINVAL) { + err = 2; + goto done; + } + + /* Check that start can't be greater than size */ + if (bpf_dynptr_adjust(&ptr, size + 1, size + 1) != -ERANGE) { + err = 3; + goto done; + } + + /* Check that end can't be greater than size */ + if (bpf_dynptr_adjust(&ptr, 0, size + 1) != -ERANGE) { + err = 4; + goto done; + } + + if (bpf_dynptr_adjust(&ptr, off, size)) { + err = 5; + goto done; + } + + /* Check that you can't write more bytes than available into the dynptr + * after you've adjusted it + */ + if (bpf_dynptr_write(&ptr, 0, &write_data, sizeof(write_data), 0) != -E2BIG) { + err = 6; + goto done; + } + + /* Check that even after adjusting, submitting/discarding + * a ringbuf dynptr works + */ + bpf_ringbuf_submit_dynptr(&ptr, 0); + return 0; + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_zero_size_dynptr(void *ctx) +{ + char write_data = 'x', read_data; + struct bpf_dynptr ptr; + __u32 size = 64; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr)) { + err = 1; + goto done; + } + + /* After this, the dynptr has a size of 0 */ + if (bpf_dynptr_adjust(&ptr, size, size)) { + err = 2; + goto done; + } + + /* Test that reading + writing non-zero bytes is not ok */ + if (bpf_dynptr_read(&read_data, sizeof(read_data), &ptr, 0, 0) != -E2BIG) { + err = 3; + goto done; + } + + if (bpf_dynptr_write(&ptr, 0, &write_data, sizeof(write_data), 0) != -E2BIG) { + err = 4; + goto done; + } + + /* Test that reading + writing 0 bytes from a 0-size dynptr is ok */ + if (bpf_dynptr_read(&read_data, 0, &ptr, 0, 0)) { + err = 5; + goto done; + } + + if (bpf_dynptr_write(&ptr, 0, &write_data, 0, 0)) { + err = 6; + goto done; + } + + err = 0; + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_dynptr_is_null(void *ctx) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + __u64 size = 4; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + /* Pass in invalid flags, get back an invalid dynptr */ + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 123, &ptr1) != -EINVAL) { + err = 1; + goto exit_early; + } + + /* Test that the invalid dynptr is null */ + if (!bpf_dynptr_is_null(&ptr1)) { + err = 2; + goto exit_early; + } + + /* Get a valid dynptr */ + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr2)) { + err = 3; + goto exit; + } + + /* Test that the valid dynptr is not null */ + if (bpf_dynptr_is_null(&ptr2)) { + err = 4; + goto exit; + } + +exit: + bpf_ringbuf_discard_dynptr(&ptr2, 0); +exit_early: + bpf_ringbuf_discard_dynptr(&ptr1, 0); + return 0; +} + +SEC("cgroup_skb/egress") +int test_dynptr_is_rdonly(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + struct bpf_dynptr ptr3; + + /* Pass in invalid flags, get back an invalid dynptr */ + if (bpf_dynptr_from_skb(skb, 123, &ptr1) != -EINVAL) { + err = 1; + return 0; + } + + /* Test that an invalid dynptr is_rdonly returns false */ + if (bpf_dynptr_is_rdonly(&ptr1)) { + err = 2; + return 0; + } + + /* Get a read-only dynptr */ + if (bpf_dynptr_from_skb(skb, 0, &ptr2)) { + err = 3; + return 0; + } + + /* Test that the dynptr is read-only */ + if (!bpf_dynptr_is_rdonly(&ptr2)) { + err = 4; + return 0; + } + + /* Get a read-writeable dynptr */ + if (bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr3)) { + err = 5; + goto done; + } + + /* Test that the dynptr is read-only */ + if (bpf_dynptr_is_rdonly(&ptr3)) { + err = 6; + goto done; + } + +done: + bpf_ringbuf_discard_dynptr(&ptr3, 0); + return 0; +} + +SEC("cgroup_skb/egress") +int test_dynptr_clone(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + __u32 off = 2, size; + + /* Get a dynptr */ + if (bpf_dynptr_from_skb(skb, 0, &ptr1)) { + err = 1; + return 0; + } + + if (bpf_dynptr_adjust(&ptr1, off, bpf_dynptr_size(&ptr1))) { + err = 2; + return 0; + } + + /* Clone the dynptr */ + if (bpf_dynptr_clone(&ptr1, &ptr2)) { + err = 3; + return 0; + } + + size = bpf_dynptr_size(&ptr1); + + /* Check that the clone has the same size and rd-only */ + if (bpf_dynptr_size(&ptr2) != size) { + err = 4; + return 0; + } + + if (bpf_dynptr_is_rdonly(&ptr2) != bpf_dynptr_is_rdonly(&ptr1)) { + err = 5; + return 0; + } + + /* Advance and trim the original dynptr */ + bpf_dynptr_adjust(&ptr1, 5, 5); + + /* Check that only original dynptr was affected, and the clone wasn't */ + if (bpf_dynptr_size(&ptr2) != size) { + err = 6; + return 0; + } + + return 0; +} + +SEC("?cgroup_skb/egress") +int test_dynptr_skb_no_buff(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + __u64 *data; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* This may return NULL. SKB may require a buffer */ + data = bpf_dynptr_slice(&ptr, 0, NULL, 1); + + return !!data; +} + +SEC("?cgroup_skb/egress") +int test_dynptr_skb_strcmp(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + char *data; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* This may return NULL. SKB may require a buffer */ + data = bpf_dynptr_slice(&ptr, 0, NULL, 10); + if (data) { + bpf_strncmp(data, 10, "foo"); + return 1; + } + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/inner_array_lookup.c b/tools/testing/selftests/bpf/progs/inner_array_lookup.c new file mode 100644 index 000000000000..c2c8f2fa451d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/inner_array_lookup.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct inner_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 5); + __type(key, int); + __type(value, int); +} inner_map1 SEC(".maps"); + +struct outer_map { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 3); + __type(key, int); + __array(values, struct inner_map); +} outer_map1 SEC(".maps") = { + .values = { + [2] = &inner_map1, + }, +}; + +SEC("raw_tp/sys_enter") +int handle__sys_enter(void *ctx) +{ + int outer_key = 2, inner_key = 3; + int *val; + void *map; + + map = bpf_map_lookup_elem(&outer_map1, &outer_key); + if (!map) + return 1; + + val = bpf_map_lookup_elem(map, &inner_key); + if (!val) + return 1; + + if (*val == 1) + *val = 2; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index be16143ae292..6b9b3c56f009 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -651,29 +651,25 @@ int iter_stack_array_loop(const void *ctx) return sum; } -#define ARR_SZ 16 - -static __noinline void fill(struct bpf_iter_num *it, int *arr, int mul) +static __noinline void fill(struct bpf_iter_num *it, int *arr, __u32 n, int mul) { - int *t; - __u64 i; + int *t, i; while ((t = bpf_iter_num_next(it))) { i = *t; - if (i >= ARR_SZ) + if (i >= n) break; arr[i] = i * mul; } } -static __noinline int sum(struct bpf_iter_num *it, int *arr) +static __noinline int sum(struct bpf_iter_num *it, int *arr, __u32 n) { - int *t, sum = 0;; - __u64 i; + int *t, i, sum = 0;; while ((t = bpf_iter_num_next(it))) { i = *t; - if (i >= ARR_SZ) + if (i >= n) break; sum += arr[i]; } @@ -685,7 +681,7 @@ SEC("raw_tp") __success int iter_pass_iter_ptr_to_subprog(const void *ctx) { - int arr1[ARR_SZ], arr2[ARR_SZ]; + int arr1[16], arr2[32]; struct bpf_iter_num it; int n, sum1, sum2; @@ -694,25 +690,25 @@ int iter_pass_iter_ptr_to_subprog(const void *ctx) /* fill arr1 */ n = ARRAY_SIZE(arr1); bpf_iter_num_new(&it, 0, n); - fill(&it, arr1, 2); + fill(&it, arr1, n, 2); bpf_iter_num_destroy(&it); /* fill arr2 */ n = ARRAY_SIZE(arr2); bpf_iter_num_new(&it, 0, n); - fill(&it, arr2, 10); + fill(&it, arr2, n, 10); bpf_iter_num_destroy(&it); /* sum arr1 */ n = ARRAY_SIZE(arr1); bpf_iter_num_new(&it, 0, n); - sum1 = sum(&it, arr1); + sum1 = sum(&it, arr1, n); bpf_iter_num_destroy(&it); /* sum arr2 */ n = ARRAY_SIZE(arr2); bpf_iter_num_new(&it, 0, n); - sum2 = sum(&it, arr2); + sum2 = sum(&it, arr2, n); bpf_iter_num_destroy(&it); bpf_printk("sum1=%d, sum2=%d", sum1, sum2); diff --git a/tools/testing/selftests/bpf/progs/jit_probe_mem.c b/tools/testing/selftests/bpf/progs/jit_probe_mem.c index 13f00ca2ed0a..f9789e668297 100644 --- a/tools/testing/selftests/bpf/progs/jit_probe_mem.c +++ b/tools/testing/selftests/bpf/progs/jit_probe_mem.c @@ -3,13 +3,11 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" static struct prog_test_ref_kfunc __kptr *v; long total_sum = -1; -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; - SEC("tc") int test_jit_probe_mem(struct __sk_buff *ctx) { diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c b/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c index 767472bc5a97..7632d9ecb253 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c @@ -1,8 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <vmlinux.h> #include <bpf/bpf_helpers.h> - -extern void bpf_kfunc_call_test_destructive(void) __ksym; +#include "../bpf_testmod/bpf_testmod_kfunc.h" SEC("tc") int kfunc_destructive_test(void) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c index b98313d391c6..4b0b7b79cdfb 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c @@ -2,14 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> - -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; -extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; -extern int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym; -extern int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; -extern int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; -extern void bpf_kfunc_call_int_mem_release(int *p) __ksym; +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct syscall_test_args { __u8 data[16]; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_race.c b/tools/testing/selftests/bpf/progs/kfunc_call_race.c index 4e8fed75a4e0..d532af07decf 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_race.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_race.c @@ -1,8 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <vmlinux.h> #include <bpf/bpf_helpers.h> - -extern void bpf_testmod_test_mod_kfunc(int i) __ksym; +#include "../bpf_testmod/bpf_testmod_kfunc.h" SEC("tc") int kfunc_call_fail(struct __sk_buff *ctx) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index 7daa8f5720b9..cf68d1e48a0f 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -2,22 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> - -extern long bpf_kfunc_call_test4(signed char a, short b, int c, long d) __ksym; -extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; -extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, - __u32 c, __u64 d) __ksym; - -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; -extern void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) __ksym; -extern void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) __ksym; -extern void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) __ksym; -extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; -extern void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym; -extern int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym; -extern int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; -extern u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) __ksym; +#include "../bpf_testmod/bpf_testmod_kfunc.h" SEC("tc") int kfunc_call_test4(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c index c1fdecabeabf..2380c75e74ce 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c @@ -1,13 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ -#include <linux/bpf.h> -#include <bpf/bpf_helpers.h> -#include "bpf_tcp_helpers.h" +#include "../bpf_testmod/bpf_testmod_kfunc.h" extern const int bpf_prog_active __ksym; -extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, - __u32 c, __u64 d) __ksym; -extern struct sock *bpf_kfunc_call_test3(struct sock *sk) __ksym; int active_res = -1; int sk_state_res = -1; @@ -28,7 +23,7 @@ int __noinline f1(struct __sk_buff *skb) if (active) active_res = *active; - sk_state_res = bpf_kfunc_call_test3((struct sock *)sk)->sk_state; + sk_state_res = bpf_kfunc_call_test3((struct sock *)sk)->__sk_common.skc_state; return (__u32)bpf_kfunc_call_test1((struct sock *)sk, 1, 2, 3, 4); } diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash.c b/tools/testing/selftests/bpf/progs/local_kptr_stash.c index 0ef286da092b..06838083079c 100644 --- a/tools/testing/selftests/bpf/progs/local_kptr_stash.c +++ b/tools/testing/selftests/bpf/progs/local_kptr_stash.c @@ -5,7 +5,8 @@ #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_core_read.h> -#include "bpf_experimental.h" +#include "../bpf_experimental.h" +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct node_data { long key; @@ -32,8 +33,6 @@ struct map_value { */ struct node_data *just_here_because_btf_bug; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; - struct { __uint(type, BPF_MAP_TYPE_ARRAY); __type(key, int); diff --git a/tools/testing/selftests/bpf/progs/map_kptr.c b/tools/testing/selftests/bpf/progs/map_kptr.c index d7150041e5d1..da30f0d59364 100644 --- a/tools/testing/selftests/bpf/progs/map_kptr.c +++ b/tools/testing/selftests/bpf/progs/map_kptr.c @@ -2,6 +2,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct map_value { struct prog_test_ref_kfunc __kptr_untrusted *unref_ptr; @@ -114,10 +115,6 @@ DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, hash_map, hash_of_hash_maps); DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, hash_malloc_map, hash_of_hash_malloc_maps); DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, lru_hash_map, hash_of_lru_hash_maps); -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; -void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) __ksym; - #define WRITE_ONCE(x, val) ((*(volatile typeof(x) *) &(x)) = (val)) static void test_kptr_unref(struct map_value *v) diff --git a/tools/testing/selftests/bpf/progs/map_kptr_fail.c b/tools/testing/selftests/bpf/progs/map_kptr_fail.c index da8c724f839b..450bb373b179 100644 --- a/tools/testing/selftests/bpf/progs/map_kptr_fail.c +++ b/tools/testing/selftests/bpf/progs/map_kptr_fail.c @@ -4,6 +4,7 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_core_read.h> #include "bpf_misc.h" +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct map_value { char buf[8]; @@ -19,9 +20,6 @@ struct array_map { __uint(max_entries, 1); } array_map SEC(".maps"); -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; - SEC("?tc") __failure __msg("kptr access size must be BPF_DW") int size_not_bpf_dw(struct __sk_buff *ctx) diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr.c b/tools/testing/selftests/bpf/progs/refcounted_kptr.c index 1d348a225140..a3da610b1e6b 100644 --- a/tools/testing/selftests/bpf/progs/refcounted_kptr.c +++ b/tools/testing/selftests/bpf/progs/refcounted_kptr.c @@ -375,6 +375,8 @@ long rbtree_refcounted_node_ref_escapes(void *ctx) bpf_rbtree_add(&aroot, &n->node, less_a); m = bpf_refcount_acquire(n); bpf_spin_unlock(&alock); + if (!m) + return 2; m->key = 2; bpf_obj_drop(m); diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c index efcb308f80ad..0b09e5c915b1 100644 --- a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c +++ b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c @@ -29,7 +29,7 @@ static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b) } SEC("?tc") -__failure __msg("Unreleased reference id=3 alloc_insn=21") +__failure __msg("Unreleased reference id=4 alloc_insn=21") long rbtree_refcounted_node_ref_escapes(void *ctx) { struct node_acquire *n, *m; @@ -43,6 +43,8 @@ long rbtree_refcounted_node_ref_escapes(void *ctx) /* m becomes an owning ref but is never drop'd or added to a tree */ m = bpf_refcount_acquire(n); bpf_spin_unlock(&glock); + if (!m) + return 2; m->key = 2; return 0; diff --git a/tools/testing/selftests/bpf/progs/sock_destroy_prog.c b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c new file mode 100644 index 000000000000..9e0bf7a54cec --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include "bpf_tracing_net.h" + +__be16 serv_port = 0; + +int bpf_sock_destroy(struct sock_common *sk) __ksym; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} tcp_conn_sockets SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} udp_conn_sockets SEC(".maps"); + +SEC("cgroup/connect6") +int sock_connect(struct bpf_sock_addr *ctx) +{ + __u64 sock_cookie = 0; + int key = 0; + __u32 keyc = 0; + + if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6) + return 1; + + sock_cookie = bpf_get_socket_cookie(ctx); + if (ctx->protocol == IPPROTO_TCP) + bpf_map_update_elem(&tcp_conn_sockets, &key, &sock_cookie, 0); + else if (ctx->protocol == IPPROTO_UDP) + bpf_map_update_elem(&udp_conn_sockets, &keyc, &sock_cookie, 0); + else + return 1; + + return 1; +} + +SEC("iter/tcp") +int iter_tcp6_client(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + __u64 sock_cookie = 0; + __u64 *val; + int key = 0; + + if (!sk_common) + return 0; + + if (sk_common->skc_family != AF_INET6) + return 0; + + sock_cookie = bpf_get_socket_cookie(sk_common); + val = bpf_map_lookup_elem(&tcp_conn_sockets, &key); + if (!val) + return 0; + /* Destroy connected client sockets. */ + if (sock_cookie == *val) + bpf_sock_destroy(sk_common); + + return 0; +} + +SEC("iter/tcp") +int iter_tcp6_server(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + const struct inet_connection_sock *icsk; + const struct inet_sock *inet; + struct tcp6_sock *tcp_sk; + __be16 srcp; + + if (!sk_common) + return 0; + + if (sk_common->skc_family != AF_INET6) + return 0; + + tcp_sk = bpf_skc_to_tcp6_sock(sk_common); + if (!tcp_sk) + return 0; + + icsk = &tcp_sk->tcp.inet_conn; + inet = &icsk->icsk_inet; + srcp = inet->inet_sport; + + /* Destroy server sockets. */ + if (srcp == serv_port) + bpf_sock_destroy(sk_common); + + return 0; +} + + +SEC("iter/udp") +int iter_udp6_client(struct bpf_iter__udp *ctx) +{ + struct udp_sock *udp_sk = ctx->udp_sk; + struct sock *sk = (struct sock *) udp_sk; + __u64 sock_cookie = 0, *val; + int key = 0; + + if (!sk) + return 0; + + sock_cookie = bpf_get_socket_cookie(sk); + val = bpf_map_lookup_elem(&udp_conn_sockets, &key); + if (!val) + return 0; + /* Destroy connected client sockets. */ + if (sock_cookie == *val) + bpf_sock_destroy((struct sock_common *)sk); + + return 0; +} + +SEC("iter/udp") +int iter_udp6_server(struct bpf_iter__udp *ctx) +{ + struct udp_sock *udp_sk = ctx->udp_sk; + struct sock *sk = (struct sock *) udp_sk; + struct inet_sock *inet; + __be16 srcp; + + if (!sk) + return 0; + + inet = &udp_sk->inet; + srcp = inet->inet_sport; + if (srcp == serv_port) + bpf_sock_destroy((struct sock_common *)sk); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c b/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c new file mode 100644 index 000000000000..dd6850b58e25 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +int bpf_sock_destroy(struct sock_common *sk) __ksym; + +SEC("tp_btf/tcp_destroy_sock") +__failure __msg("calling kernel function bpf_sock_destroy is not allowed") +int BPF_PROG(trace_tcp_destroy_sock, struct sock *sk) +{ + /* should not load */ + bpf_sock_destroy((struct sock_common *)sk); + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c index 9fb241b97291..c8f59caa4639 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c @@ -9,6 +9,8 @@ char _license[] SEC("license") = "GPL"; #define CUSTOM_INHERIT2 1 #define CUSTOM_LISTENER 2 +__u32 page_size = 0; + struct sockopt_inherit { __u8 val; }; @@ -55,7 +57,7 @@ int _getsockopt(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_CUSTOM) - return 1; /* only interested in SOL_CUSTOM */ + goto out; /* only interested in SOL_CUSTOM */ if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -70,6 +72,12 @@ int _getsockopt(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } SEC("cgroup/setsockopt") @@ -80,7 +88,7 @@ int _setsockopt(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_CUSTOM) - return 1; /* only interested in SOL_CUSTOM */ + goto out; /* only interested in SOL_CUSTOM */ if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -93,4 +101,10 @@ int _setsockopt(struct bpf_sockopt *ctx) ctx->optlen = -1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c index 177a59069dae..96f29fce050b 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_multi.c +++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c @@ -5,6 +5,8 @@ char _license[] SEC("license") = "GPL"; +__u32 page_size = 0; + SEC("cgroup/getsockopt") int _getsockopt_child(struct bpf_sockopt *ctx) { @@ -12,7 +14,7 @@ int _getsockopt_child(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_IP || ctx->optname != IP_TOS) - return 1; + goto out; if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -26,6 +28,12 @@ int _getsockopt_child(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } SEC("cgroup/getsockopt") @@ -35,7 +43,7 @@ int _getsockopt_parent(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_IP || ctx->optname != IP_TOS) - return 1; + goto out; if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -49,6 +57,12 @@ int _getsockopt_parent(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } SEC("cgroup/setsockopt") @@ -58,7 +72,7 @@ int _setsockopt(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_IP || ctx->optname != IP_TOS) - return 1; + goto out; if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -67,4 +81,10 @@ int _setsockopt(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c index 1bce83b6e3a7..dbe235ede7f3 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c +++ b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c @@ -9,6 +9,8 @@ char _license[] SEC("license") = "GPL"; +__u32 page_size = 0; + SEC("cgroup/setsockopt") int sockopt_qos_to_cc(struct bpf_sockopt *ctx) { @@ -19,7 +21,7 @@ int sockopt_qos_to_cc(struct bpf_sockopt *ctx) char cc_cubic[TCP_CA_NAME_MAX] = "cubic"; if (ctx->level != SOL_IPV6 || ctx->optname != IPV6_TCLASS) - return 1; + goto out; if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -36,4 +38,10 @@ int sockopt_qos_to_cc(struct bpf_sockopt *ctx) return 0; } return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index fe1df4cd206e..cb990a7d3d45 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -37,7 +37,7 @@ int _getsockopt(struct bpf_sockopt *ctx) /* Bypass AF_NETLINK. */ sk = ctx->sk; if (sk && sk->family == AF_NETLINK) - return 1; + goto out; /* Make sure bpf_get_netns_cookie is callable. */ @@ -52,8 +52,7 @@ int _getsockopt(struct bpf_sockopt *ctx) * let next BPF program in the cgroup chain or kernel * handle it. */ - ctx->optlen = 0; /* bypass optval>PAGE_SIZE */ - return 1; + goto out; } if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) { @@ -61,7 +60,7 @@ int _getsockopt(struct bpf_sockopt *ctx) * let next BPF program in the cgroup chain or kernel * handle it. */ - return 1; + goto out; } if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) { @@ -69,7 +68,7 @@ int _getsockopt(struct bpf_sockopt *ctx) * let next BPF program in the cgroup chain or kernel * handle it. */ - return 1; + goto out; } if (ctx->level == SOL_TCP && ctx->optname == TCP_ZEROCOPY_RECEIVE) { @@ -85,7 +84,7 @@ int _getsockopt(struct bpf_sockopt *ctx) if (((struct tcp_zerocopy_receive *)optval)->address != 0) return 0; /* unexpected data */ - return 1; + goto out; } if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { @@ -129,6 +128,12 @@ int _getsockopt(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } SEC("cgroup/setsockopt") @@ -142,7 +147,7 @@ int _setsockopt(struct bpf_sockopt *ctx) /* Bypass AF_NETLINK. */ sk = ctx->sk; if (sk && sk->family == AF_NETLINK) - return 1; + goto out; /* Make sure bpf_get_netns_cookie is callable. */ @@ -224,4 +229,10 @@ int _setsockopt(struct bpf_sockopt *ctx) */ return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c index b85fc8c423ba..17a9f59bf5f3 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func1.c +++ b/tools/testing/selftests/bpf/progs/test_global_func1.c @@ -10,6 +10,8 @@ static __attribute__ ((noinline)) int f0(int var, struct __sk_buff *skb) { + asm volatile (""); + return skb->len; } diff --git a/tools/testing/selftests/bpf/progs/test_global_map_resize.c b/tools/testing/selftests/bpf/progs/test_global_map_resize.c new file mode 100644 index 000000000000..2588f2384246 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_map_resize.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +/* rodata section */ +const volatile pid_t pid; +const volatile size_t bss_array_len; +const volatile size_t data_array_len; + +/* bss section */ +int sum = 0; +int array[1]; + +/* custom data secton */ +int my_array[1] SEC(".data.custom"); + +/* custom data section which should NOT be resizable, + * since it contains a single var which is not an array + */ +int my_int SEC(".data.non_array"); + +/* custom data section which should NOT be resizable, + * since its last var is not an array + */ +int my_array_first[1] SEC(".data.array_not_last"); +int my_int_last SEC(".data.array_not_last"); + +SEC("tp/syscalls/sys_enter_getpid") +int bss_array_sum(void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + sum = 0; + + for (size_t i = 0; i < bss_array_len; ++i) + sum += array[i]; + + return 0; +} + +SEC("tp/syscalls/sys_enter_getuid") +int data_array_sum(void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + sum = 0; + + for (size_t i = 0; i < data_array_len; ++i) + sum += my_array[i]; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c index bbad3c2d9aa5..f75e531bf36f 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c @@ -265,7 +265,10 @@ static __noinline bool sk_dst_port__load_word(struct bpf_sock *sk) static __noinline bool sk_dst_port__load_half(struct bpf_sock *sk) { - __u16 *half = (__u16 *)&sk->dst_port; + __u16 *half; + + asm volatile (""); + half = (__u16 *)&sk->dst_port; return half[0] == bpf_htons(0xcafe); } diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c b/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c new file mode 100644 index 000000000000..29314805ce42 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c @@ -0,0 +1,32 @@ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_tx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_msg SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h index baf9ebc6d903..99d2ea9fb658 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h @@ -191,7 +191,7 @@ SEC("sockops") int bpf_sockmap(struct bpf_sock_ops *skops) { __u32 lport, rport; - int op, err, ret; + int op, ret; op = (int) skops->op; @@ -203,10 +203,10 @@ int bpf_sockmap(struct bpf_sock_ops *skops) if (lport == 10000) { ret = 1; #ifdef SOCKMAP - err = bpf_sock_map_update(skops, &sock_map, &ret, + bpf_sock_map_update(skops, &sock_map, &ret, BPF_NOEXIST); #else - err = bpf_sock_hash_update(skops, &sock_map, &ret, + bpf_sock_hash_update(skops, &sock_map, &ret, BPF_NOEXIST); #endif } @@ -218,10 +218,10 @@ int bpf_sockmap(struct bpf_sock_ops *skops) if (bpf_ntohl(rport) == 10001) { ret = 10; #ifdef SOCKMAP - err = bpf_sock_map_update(skops, &sock_map, &ret, + bpf_sock_map_update(skops, &sock_map, &ret, BPF_NOEXIST); #else - err = bpf_sock_hash_update(skops, &sock_map, &ret, + bpf_sock_hash_update(skops, &sock_map, &ret, BPF_NOEXIST); #endif } @@ -230,8 +230,6 @@ int bpf_sockmap(struct bpf_sock_ops *skops) break; } - __sink(err); - return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c b/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c new file mode 100644 index 000000000000..1d86a717a290 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c @@ -0,0 +1,32 @@ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_tx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_msg SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_subprogs_extable.c b/tools/testing/selftests/bpf/progs/test_subprogs_extable.c new file mode 100644 index 000000000000..e2a21fbd4e44 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subprogs_extable.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 8); + __type(key, __u32); + __type(value, __u64); +} test_array SEC(".maps"); + +unsigned int triggered; + +static __u64 test_cb(struct bpf_map *map, __u32 *key, __u64 *val, void *data) +{ + return 1; +} + +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret_subprogs, int arg, struct file *ret) +{ + *(volatile long *)ret; + *(volatile int *)&ret->f_mode; + bpf_for_each_map_elem(&test_array, test_cb, NULL, 0); + triggered++; + return 0; +} + +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret_subprogs2, int arg, struct file *ret) +{ + *(volatile long *)ret; + *(volatile int *)&ret->f_mode; + bpf_for_each_map_elem(&test_array, test_cb, NULL, 0); + triggered++; + return 0; +} + +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret_subprogs3, int arg, struct file *ret) +{ + *(volatile long *)ret; + *(volatile int *)&ret->f_mode; + bpf_for_each_map_elem(&test_array, test_cb, NULL, 0); + triggered++; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c new file mode 100644 index 000000000000..56cdc0a553f0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Bytedance */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +long bpf_task_under_cgroup(struct task_struct *task, struct cgroup *ancestor) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; +struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym; +void bpf_task_release(struct task_struct *p) __ksym; + +const volatile int local_pid; +const volatile __u64 cgid; +int remote_pid; + +SEC("tp_btf/task_newtask") +int BPF_PROG(handle__task_newtask, struct task_struct *task, u64 clone_flags) +{ + struct cgroup *cgrp = NULL; + struct task_struct *acquired; + + if (local_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + acquired = bpf_task_acquire(task); + if (!acquired) + return 0; + + if (local_pid == acquired->tgid) + goto out; + + cgrp = bpf_cgroup_from_id(cgid); + if (!cgrp) + goto out; + + if (bpf_task_under_cgroup(acquired, cgrp)) + remote_pid = acquired->tgid; + +out: + if (cgrp) + bpf_cgroup_release(cgrp); + bpf_task_release(acquired); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c index 25ee4a22e48d..78c368e71797 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c @@ -2,6 +2,7 @@ /* Copyright (c) 2022 Meta */ #include <stddef.h> #include <string.h> +#include <stdbool.h> #include <linux/bpf.h> #include <linux/if_ether.h> #include <linux/if_packet.h> diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c new file mode 100644 index 000000000000..13b29a7faa71 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c @@ -0,0 +1,659 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +/* Check that precision marks propagate through scalar IDs. + * Registers r{0,1,2} have the same scalar ID at the moment when r0 is + * marked to be precise, this mark is immediately propagated to r{1,2}. + */ +SEC("socket") +__success __log_level(2) +__msg("frame0: regs=r0,r1,r2 stack= before 4: (bf) r3 = r10") +__msg("frame0: regs=r0,r1,r2 stack= before 3: (bf) r2 = r0") +__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_same_state(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == r2.id */ + "r1 = r0;" + "r2 = r0;" + /* force r0 to be precise, this immediately marks r1 and r2 as + * precise as well because of shared IDs + */ + "r3 = r10;" + "r3 += r0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Same as precision_same_state, but mark propagates through state / + * parent state boundary. + */ +SEC("socket") +__success __log_level(2) +__msg("frame0: last_idx 6 first_idx 5 subseq_idx -1") +__msg("frame0: regs=r0,r1,r2 stack= before 5: (bf) r3 = r10") +__msg("frame0: parent state regs=r0,r1,r2 stack=:") +__msg("frame0: regs=r0,r1,r2 stack= before 4: (05) goto pc+0") +__msg("frame0: regs=r0,r1,r2 stack= before 3: (bf) r2 = r0") +__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__msg("frame0: parent state regs=r0 stack=:") +__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_cross_state(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == r2.id */ + "r1 = r0;" + "r2 = r0;" + /* force checkpoint */ + "goto +0;" + /* force r0 to be precise, this immediately marks r1 and r2 as + * precise as well because of shared IDs + */ + "r3 = r10;" + "r3 += r0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Same as precision_same_state, but break one of the + * links, note that r1 is absent from regs=... in __msg below. + */ +SEC("socket") +__success __log_level(2) +__msg("frame0: regs=r0,r2 stack= before 5: (bf) r3 = r10") +__msg("frame0: regs=r0,r2 stack= before 4: (b7) r1 = 0") +__msg("frame0: regs=r0,r2 stack= before 3: (bf) r2 = r0") +__msg("frame0: regs=r0 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_same_state_broken_link(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == r2.id */ + "r1 = r0;" + "r2 = r0;" + /* break link for r1, this is the only line that differs + * compared to the previous test + */ + "r1 = 0;" + /* force r0 to be precise, this immediately marks r1 and r2 as + * precise as well because of shared IDs + */ + "r3 = r10;" + "r3 += r0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Same as precision_same_state_broken_link, but with state / + * parent state boundary. + */ +SEC("socket") +__success __log_level(2) +__msg("frame0: regs=r0,r2 stack= before 6: (bf) r3 = r10") +__msg("frame0: regs=r0,r2 stack= before 5: (b7) r1 = 0") +__msg("frame0: parent state regs=r0,r2 stack=:") +__msg("frame0: regs=r0,r1,r2 stack= before 4: (05) goto pc+0") +__msg("frame0: regs=r0,r1,r2 stack= before 3: (bf) r2 = r0") +__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__msg("frame0: parent state regs=r0 stack=:") +__msg("frame0: regs=r0 stack= before 0: (85) call bpf_ktime_get_ns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_cross_state_broken_link(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == r2.id */ + "r1 = r0;" + "r2 = r0;" + /* force checkpoint, although link between r1 and r{0,2} is + * broken by the next statement current precision tracking + * algorithm can't react to it and propagates mark for r1 to + * the parent state. + */ + "goto +0;" + /* break link for r1, this is the only line that differs + * compared to precision_cross_state() + */ + "r1 = 0;" + /* force r0 to be precise, this immediately marks r1 and r2 as + * precise as well because of shared IDs + */ + "r3 = r10;" + "r3 += r0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Check that precision marks propagate through scalar IDs. + * Use the same scalar ID in multiple stack frames, check that + * precision information is propagated up the call stack. + */ +SEC("socket") +__success __log_level(2) +__msg("11: (0f) r2 += r1") +/* Current state */ +__msg("frame2: last_idx 11 first_idx 10 subseq_idx -1") +__msg("frame2: regs=r1 stack= before 10: (bf) r2 = r10") +__msg("frame2: parent state regs=r1 stack=") +/* frame1.r{6,7} are marked because mark_precise_scalar_ids() + * looks for all registers with frame2.r1.id in the current state + */ +__msg("frame1: parent state regs=r6,r7 stack=") +__msg("frame0: parent state regs=r6 stack=") +/* Parent state */ +__msg("frame2: last_idx 8 first_idx 8 subseq_idx 10") +__msg("frame2: regs=r1 stack= before 8: (85) call pc+1") +/* frame1.r1 is marked because of backtracking of call instruction */ +__msg("frame1: parent state regs=r1,r6,r7 stack=") +__msg("frame0: parent state regs=r6 stack=") +/* Parent state */ +__msg("frame1: last_idx 7 first_idx 6 subseq_idx 8") +__msg("frame1: regs=r1,r6,r7 stack= before 7: (bf) r7 = r1") +__msg("frame1: regs=r1,r6 stack= before 6: (bf) r6 = r1") +__msg("frame1: parent state regs=r1 stack=") +__msg("frame0: parent state regs=r6 stack=") +/* Parent state */ +__msg("frame1: last_idx 4 first_idx 4 subseq_idx 6") +__msg("frame1: regs=r1 stack= before 4: (85) call pc+1") +__msg("frame0: parent state regs=r1,r6 stack=") +/* Parent state */ +__msg("frame0: last_idx 3 first_idx 1 subseq_idx 4") +__msg("frame0: regs=r0,r1,r6 stack= before 3: (bf) r6 = r0") +__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_many_frames(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == r6.id */ + "r1 = r0;" + "r6 = r0;" + "call precision_many_frames__foo;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +static __naked __noinline __used +void precision_many_frames__foo(void) +{ + asm volatile ( + /* conflate one of the register numbers (r6) with outer frame, + * to verify that those are tracked independently + */ + "r6 = r1;" + "r7 = r1;" + "call precision_many_frames__bar;" + "exit" + ::: __clobber_all); +} + +static __naked __noinline __used +void precision_many_frames__bar(void) +{ + asm volatile ( + /* force r1 to be precise, this immediately marks: + * - bar frame r1 + * - foo frame r{1,6,7} + * - main frame r{1,6} + */ + "r2 = r10;" + "r2 += r1;" + "r0 = 0;" + "exit;" + ::: __clobber_all); +} + +/* Check that scalars with the same IDs are marked precise on stack as + * well as in registers. + */ +SEC("socket") +__success __log_level(2) +/* foo frame */ +__msg("frame1: regs=r1 stack=-8,-16 before 9: (bf) r2 = r10") +__msg("frame1: regs=r1 stack=-8,-16 before 8: (7b) *(u64 *)(r10 -16) = r1") +__msg("frame1: regs=r1 stack=-8 before 7: (7b) *(u64 *)(r10 -8) = r1") +__msg("frame1: regs=r1 stack= before 4: (85) call pc+2") +/* main frame */ +__msg("frame0: regs=r0,r1 stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r1") +__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0") +__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_stack(void) +{ + asm volatile ( + /* r0 = random number up to 0xff */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* tie r0.id == r1.id == fp[-8].id */ + "r1 = r0;" + "*(u64*)(r10 - 8) = r1;" + "call precision_stack__foo;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +static __naked __noinline __used +void precision_stack__foo(void) +{ + asm volatile ( + /* conflate one of the register numbers (r6) with outer frame, + * to verify that those are tracked independently + */ + "*(u64*)(r10 - 8) = r1;" + "*(u64*)(r10 - 16) = r1;" + /* force r1 to be precise, this immediately marks: + * - foo frame r1,fp{-8,-16} + * - main frame r1,fp{-8} + */ + "r2 = r10;" + "r2 += r1;" + "exit" + ::: __clobber_all); +} + +/* Use two separate scalar IDs to check that these are propagated + * independently. + */ +SEC("socket") +__success __log_level(2) +/* r{6,7} */ +__msg("11: (0f) r3 += r7") +__msg("frame0: regs=r6,r7 stack= before 10: (bf) r3 = r10") +/* ... skip some insns ... */ +__msg("frame0: regs=r6,r7 stack= before 3: (bf) r7 = r0") +__msg("frame0: regs=r0,r6 stack= before 2: (bf) r6 = r0") +/* r{8,9} */ +__msg("12: (0f) r3 += r9") +__msg("frame0: regs=r8,r9 stack= before 11: (0f) r3 += r7") +/* ... skip some insns ... */ +__msg("frame0: regs=r8,r9 stack= before 7: (bf) r9 = r0") +__msg("frame0: regs=r0,r8 stack= before 6: (bf) r8 = r0") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void precision_two_ids(void) +{ + asm volatile ( + /* r6 = random number up to 0xff + * r6.id == r7.id + */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + "r6 = r0;" + "r7 = r0;" + /* same, but for r{8,9} */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + "r8 = r0;" + "r9 = r0;" + /* clear r0 id */ + "r0 = 0;" + /* force checkpoint */ + "goto +0;" + "r3 = r10;" + /* force r7 to be precise, this also marks r6 */ + "r3 += r7;" + /* force r9 to be precise, this also marks r8 */ + "r3 += r9;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Verify that check_ids() is used by regsafe() for scalars. + * + * r9 = ... some pointer with range X ... + * r6 = ... unbound scalar ID=a ... + * r7 = ... unbound scalar ID=b ... + * if (r6 > r7) goto +1 + * r7 = r6 + * if (r7 > X) goto exit + * r9 += r6 + * ... access memory using r9 ... + * + * The memory access is safe only if r7 is bounded, + * which is true for one branch and not true for another. + */ +SEC("socket") +__failure __msg("register with unbounded min value") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void check_ids_in_regsafe(void) +{ + asm volatile ( + /* Bump allocated stack */ + "r1 = 0;" + "*(u64*)(r10 - 8) = r1;" + /* r9 = pointer to stack */ + "r9 = r10;" + "r9 += -8;" + /* r7 = ktime_get_ns() */ + "call %[bpf_ktime_get_ns];" + "r7 = r0;" + /* r6 = ktime_get_ns() */ + "call %[bpf_ktime_get_ns];" + "r6 = r0;" + /* if r6 > r7 is an unpredictable jump */ + "if r6 > r7 goto l1_%=;" + "r7 = r6;" +"l1_%=:" + /* if r7 > 4 ...; transfers range to r6 on one execution path + * but does not transfer on another + */ + "if r7 > 4 goto l2_%=;" + /* Access memory at r9[r6], r6 is not always bounded */ + "r9 += r6;" + "r0 = *(u8*)(r9 + 0);" +"l2_%=:" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Similar to check_ids_in_regsafe. + * The l0 could be reached in two states: + * + * (1) r6{.id=A}, r7{.id=A}, r8{.id=B} + * (2) r6{.id=B}, r7{.id=A}, r8{.id=B} + * + * Where (2) is not safe, as "r7 > 4" check won't propagate range for it. + * This example would be considered safe without changes to + * mark_chain_precision() to track scalar values with equal IDs. + */ +SEC("socket") +__failure __msg("register with unbounded min value") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void check_ids_in_regsafe_2(void) +{ + asm volatile ( + /* Bump allocated stack */ + "r1 = 0;" + "*(u64*)(r10 - 8) = r1;" + /* r9 = pointer to stack */ + "r9 = r10;" + "r9 += -8;" + /* r8 = ktime_get_ns() */ + "call %[bpf_ktime_get_ns];" + "r8 = r0;" + /* r7 = ktime_get_ns() */ + "call %[bpf_ktime_get_ns];" + "r7 = r0;" + /* r6 = ktime_get_ns() */ + "call %[bpf_ktime_get_ns];" + "r6 = r0;" + /* scratch .id from r0 */ + "r0 = 0;" + /* if r6 > r7 is an unpredictable jump */ + "if r6 > r7 goto l1_%=;" + /* tie r6 and r7 .id */ + "r6 = r7;" +"l0_%=:" + /* if r7 > 4 exit(0) */ + "if r7 > 4 goto l2_%=;" + /* Access memory at r9[r6] */ + "r9 += r6;" + "r0 = *(u8*)(r9 + 0);" +"l2_%=:" + "r0 = 0;" + "exit;" +"l1_%=:" + /* tie r6 and r8 .id */ + "r6 = r8;" + "goto l0_%=;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Check that scalar IDs *are not* generated on register to register + * assignments if source register is a constant. + * + * If such IDs *are* generated the 'l1' below would be reached in + * two states: + * + * (1) r1{.id=A}, r2{.id=A} + * (2) r1{.id=C}, r2{.id=C} + * + * Thus forcing 'if r1 == r2' verification twice. + */ +SEC("socket") +__success __log_level(2) +__msg("11: (1d) if r3 == r4 goto pc+0") +__msg("frame 0: propagating r3,r4") +__msg("11: safe") +__msg("processed 15 insns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void no_scalar_id_for_const(void) +{ + asm volatile ( + "call %[bpf_ktime_get_ns];" + /* unpredictable jump */ + "if r0 > 7 goto l0_%=;" + /* possibly generate same scalar ids for r3 and r4 */ + "r1 = 0;" + "r1 = r1;" + "r3 = r1;" + "r4 = r1;" + "goto l1_%=;" +"l0_%=:" + /* possibly generate different scalar ids for r3 and r4 */ + "r1 = 0;" + "r2 = 0;" + "r3 = r1;" + "r4 = r2;" +"l1_%=:" + /* predictable jump, marks r3 and r4 precise */ + "if r3 == r4 goto +0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Same as no_scalar_id_for_const() but for 32-bit values */ +SEC("socket") +__success __log_level(2) +__msg("11: (1e) if w3 == w4 goto pc+0") +__msg("frame 0: propagating r3,r4") +__msg("11: safe") +__msg("processed 15 insns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void no_scalar_id_for_const32(void) +{ + asm volatile ( + "call %[bpf_ktime_get_ns];" + /* unpredictable jump */ + "if r0 > 7 goto l0_%=;" + /* possibly generate same scalar ids for r3 and r4 */ + "w1 = 0;" + "w1 = w1;" + "w3 = w1;" + "w4 = w1;" + "goto l1_%=;" +"l0_%=:" + /* possibly generate different scalar ids for r3 and r4 */ + "w1 = 0;" + "w2 = 0;" + "w3 = w1;" + "w4 = w2;" +"l1_%=:" + /* predictable jump, marks r1 and r2 precise */ + "if w3 == w4 goto +0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Check that unique scalar IDs are ignored when new verifier state is + * compared to cached verifier state. For this test: + * - cached state has no id on r1 + * - new state has a unique id on r1 + */ +SEC("socket") +__success __log_level(2) +__msg("6: (25) if r6 > 0x7 goto pc+1") +__msg("7: (57) r1 &= 255") +__msg("8: (bf) r2 = r10") +__msg("from 6 to 8: safe") +__msg("processed 12 insns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void ignore_unique_scalar_ids_cur(void) +{ + asm volatile ( + "call %[bpf_ktime_get_ns];" + "r6 = r0;" + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* r1.id == r0.id */ + "r1 = r0;" + /* make r1.id unique */ + "r0 = 0;" + "if r6 > 7 goto l0_%=;" + /* clear r1 id, but keep the range compatible */ + "r1 &= 0xff;" +"l0_%=:" + /* get here in two states: + * - first: r1 has no id (cached state) + * - second: r1 has a unique id (should be considered equivalent) + */ + "r2 = r10;" + "r2 += r1;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Check that unique scalar IDs are ignored when new verifier state is + * compared to cached verifier state. For this test: + * - cached state has a unique id on r1 + * - new state has no id on r1 + */ +SEC("socket") +__success __log_level(2) +__msg("6: (25) if r6 > 0x7 goto pc+1") +__msg("7: (05) goto pc+1") +__msg("9: (bf) r2 = r10") +__msg("9: safe") +__msg("processed 13 insns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void ignore_unique_scalar_ids_old(void) +{ + asm volatile ( + "call %[bpf_ktime_get_ns];" + "r6 = r0;" + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + /* r1.id == r0.id */ + "r1 = r0;" + /* make r1.id unique */ + "r0 = 0;" + "if r6 > 7 goto l1_%=;" + "goto l0_%=;" +"l1_%=:" + /* clear r1 id, but keep the range compatible */ + "r1 &= 0xff;" +"l0_%=:" + /* get here in two states: + * - first: r1 has a unique id (cached state) + * - second: r1 has no id (should be considered equivalent) + */ + "r2 = r10;" + "r2 += r1;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +/* Check that two different scalar IDs in a verified state can't be + * mapped to the same scalar ID in current state. + */ +SEC("socket") +__success __log_level(2) +/* The exit instruction should be reachable from two states, + * use two matches and "processed .. insns" to ensure this. + */ +__msg("13: (95) exit") +__msg("13: (95) exit") +__msg("processed 18 insns") +__flag(BPF_F_TEST_STATE_FREQ) +__naked void two_old_ids_one_cur_id(void) +{ + asm volatile ( + /* Give unique scalar IDs to r{6,7} */ + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + "r6 = r0;" + "call %[bpf_ktime_get_ns];" + "r0 &= 0xff;" + "r7 = r0;" + "r0 = 0;" + /* Maybe make r{6,7} IDs identical */ + "if r6 > r7 goto l0_%=;" + "goto l1_%=;" +"l0_%=:" + "r6 = r7;" +"l1_%=:" + /* Mark r{6,7} precise. + * Get here in two states: + * - first: r6{.id=A}, r7{.id=B} (cached state) + * - second: r6{.id=A}, r7{.id=A} + * Currently we don't want to consider such states equivalent. + * Thus "exit;" would be verified twice. + */ + "r2 = r10;" + "r2 += r6;" + "r2 += r7;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c index 136e5530b72c..6115520154e3 100644 --- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c +++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c @@ -371,4 +371,83 @@ __naked void and_then_at_fp_8(void) " ::: __clobber_all); } +SEC("xdp") +__description("32-bit spill of 64-bit reg should clear ID") +__failure __msg("math between ctx pointer and 4294967295 is not allowed") +__naked void spill_32bit_of_64bit_fail(void) +{ + asm volatile (" \ + r6 = r1; \ + /* Roll one bit to force the verifier to track both branches. */\ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x8; \ + /* Put a large number into r1. */ \ + r1 = 0xffffffff; \ + r1 <<= 32; \ + r1 += r0; \ + /* Assign an ID to r1. */ \ + r2 = r1; \ + /* 32-bit spill r1 to stack - should clear the ID! */\ + *(u32*)(r10 - 8) = r1; \ + /* 32-bit fill r2 from stack. */ \ + r2 = *(u32*)(r10 - 8); \ + /* Compare r2 with another register to trigger find_equal_scalars.\ + * Having one random bit is important here, otherwise the verifier cuts\ + * the corners. If the ID was mistakenly preserved on spill, this would\ + * cause the verifier to think that r1 is also equal to zero in one of\ + * the branches, and equal to eight on the other branch.\ + */ \ + r3 = 0; \ + if r2 != r3 goto l0_%=; \ +l0_%=: r1 >>= 32; \ + /* At this point, if the verifier thinks that r1 is 0, an out-of-bounds\ + * read will happen, because it actually contains 0xffffffff.\ + */ \ + r6 += r1; \ + r0 = *(u32*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("xdp") +__description("16-bit spill of 32-bit reg should clear ID") +__failure __msg("dereference of modified ctx ptr R6 off=65535 disallowed") +__naked void spill_16bit_of_32bit_fail(void) +{ + asm volatile (" \ + r6 = r1; \ + /* Roll one bit to force the verifier to track both branches. */\ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x8; \ + /* Put a large number into r1. */ \ + w1 = 0xffff0000; \ + r1 += r0; \ + /* Assign an ID to r1. */ \ + r2 = r1; \ + /* 16-bit spill r1 to stack - should clear the ID! */\ + *(u16*)(r10 - 8) = r1; \ + /* 16-bit fill r2 from stack. */ \ + r2 = *(u16*)(r10 - 8); \ + /* Compare r2 with another register to trigger find_equal_scalars.\ + * Having one random bit is important here, otherwise the verifier cuts\ + * the corners. If the ID was mistakenly preserved on spill, this would\ + * cause the verifier to think that r1 is also equal to zero in one of\ + * the branches, and equal to eight on the other branch.\ + */ \ + r3 = 0; \ + if r2 != r3 goto l0_%=; \ +l0_%=: r1 >>= 16; \ + /* At this point, if the verifier thinks that r1 is 0, an out-of-bounds\ + * read will happen, because it actually contains 0xffff.\ + */ \ + r6 += r1; \ + r0 = *(u32*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c new file mode 100644 index 000000000000..db6b3143338b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -0,0 +1,536 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <errno.h> +#include <string.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof(x[0])) + +int vals[] SEC(".data.vals") = {1, 2, 3, 4}; + +__naked __noinline __used +static unsigned long identity_subprog() +{ + /* the simplest *static* 64-bit identity function */ + asm volatile ( + "r0 = r1;" + "exit;" + ); +} + +__noinline __used +unsigned long global_identity_subprog(__u64 x) +{ + /* the simplest *global* 64-bit identity function */ + return x; +} + +__naked __noinline __used +static unsigned long callback_subprog() +{ + /* the simplest callback function */ + asm volatile ( + "r0 = 0;" + "exit;" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("7: (0f) r1 += r0") +__msg("mark_precise: frame0: regs=r0 stack= before 6: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r0 stack= before 5: (27) r0 *= 4") +__msg("mark_precise: frame0: regs=r0 stack= before 11: (95) exit") +__msg("mark_precise: frame1: regs=r0 stack= before 10: (bf) r0 = r1") +__msg("mark_precise: frame1: regs=r1 stack= before 4: (85) call pc+5") +__msg("mark_precise: frame0: regs=r1 stack= before 3: (bf) r1 = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int subprog_result_precise(void) +{ + asm volatile ( + "r6 = 3;" + /* pass r6 through r1 into subprog to get it back as r0; + * this whole chain will have to be marked as precise later + */ + "r1 = r6;" + "call identity_subprog;" + /* now use subprog's returned value (which is a + * r6 -> r1 -> r0 chain), as index into vals array, forcing + * all of that to be known precisely + */ + "r0 *= 4;" + "r1 = %[vals];" + /* here r0->r1->r6 chain is forced to be precise and has to be + * propagated back to the beginning, including through the + * subprog call + */ + "r1 += r0;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("9: (0f) r1 += r0") +__msg("mark_precise: frame0: last_idx 9 first_idx 0") +__msg("mark_precise: frame0: regs=r0 stack= before 8: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r0 stack= before 7: (27) r0 *= 4") +__msg("mark_precise: frame0: regs=r0 stack= before 5: (a5) if r0 < 0x4 goto pc+1") +__msg("mark_precise: frame0: regs=r0 stack= before 4: (85) call pc+7") +__naked int global_subprog_result_precise(void) +{ + asm volatile ( + "r6 = 3;" + /* pass r6 through r1 into subprog to get it back as r0; + * given global_identity_subprog is global, precision won't + * propagate all the way back to r6 + */ + "r1 = r6;" + "call global_identity_subprog;" + /* now use subprog's returned value (which is unknown now, so + * we need to clamp it), as index into vals array, forcing r0 + * to be marked precise (with no effect on r6, though) + */ + "if r0 < %[vals_arr_sz] goto 1f;" + "r0 = %[vals_arr_sz] - 1;" + "1:" + "r0 *= 4;" + "r1 = %[vals];" + /* here r0 is forced to be precise and has to be + * propagated back to the global subprog call, but it + * shouldn't go all the way to mark r6 as precise + */ + "r1 += r0;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals), + __imm_const(vals_arr_sz, ARRAY_SIZE(vals)) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("14: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 14 first_idx 10") +__msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (25) if r6 > 0x3 goto pc+4") +__msg("mark_precise: frame0: regs=r6 stack= before 10: (bf) r6 = r0") +__msg("mark_precise: frame0: parent state regs=r0 stack=:") +__msg("mark_precise: frame0: last_idx 18 first_idx 0") +__msg("mark_precise: frame0: regs=r0 stack= before 18: (95) exit") +__naked int callback_result_precise(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and use result; r0 shouldn't propagate back to + * callback_subprog + */ + "r1 = r6;" /* nr_loops */ + "r2 = %[callback_subprog];" /* callback_fn */ + "r3 = 0;" /* callback_ctx */ + "r4 = 0;" /* flags */ + "call %[bpf_loop];" + + "r6 = r0;" + "if r6 > 3 goto 1f;" + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the bpf_loop() call, but not beyond + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "1:" + "exit;" + : + : __imm_ptr(vals), + __imm_ptr(callback_subprog), + __imm(bpf_loop) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("7: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 7 first_idx 0") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 5: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 10: (bf) r0 = r1") +__msg("mark_precise: frame1: regs= stack= before 4: (85) call pc+5") +__msg("mark_precise: frame0: regs=r6 stack= before 3: (b7) r1 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_callee_saved_reg_precise(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call identity_subprog;" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("7: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 7 first_idx 0") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 5: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (85) call pc+5") +__msg("mark_precise: frame0: regs=r6 stack= before 3: (b7) r1 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_callee_saved_reg_precise_global(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call global_identity_subprog;" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("12: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 12 first_idx 10") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 10: (27) r6 *= 4") +__msg("mark_precise: frame0: parent state regs=r6 stack=:") +__msg("mark_precise: frame0: last_idx 16 first_idx 0") +__msg("mark_precise: frame0: regs=r6 stack= before 16: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0") +__msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop#181") +__msg("mark_precise: frame0: regs=r6 stack= before 8: (b7) r4 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 7: (b7) r3 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r2 = r8") +__msg("mark_precise: frame0: regs=r6 stack= before 5: (b7) r1 = 1") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +__naked int parent_callee_saved_reg_precise_with_callback(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 1;" /* nr_loops */ + "r2 = %[callback_subprog];" /* callback_fn */ + "r3 = 0;" /* callback_ctx */ + "r4 = 0;" /* flags */ + "call %[bpf_loop];" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) callback call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals), + __imm_ptr(callback_subprog), + __imm(bpf_loop) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("9: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 9 first_idx 6") +__msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: parent state regs= stack=-8:") +__msg("mark_precise: frame0: last_idx 13 first_idx 0") +__msg("mark_precise: frame0: regs= stack=-8 before 13: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 12: (bf) r0 = r1") +__msg("mark_precise: frame1: regs= stack= before 5: (85) call pc+6") +__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_stack_slot_precise(void) +{ + asm volatile ( + /* spill reg */ + "r6 = 3;" + "*(u64 *)(r10 - 8) = r6;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call identity_subprog;" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r6 = *(u64 *)(r10 - 8);" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("9: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 9 first_idx 6") +__msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: parent state regs= stack=-8:") +__msg("mark_precise: frame0: last_idx 5 first_idx 0") +__msg("mark_precise: frame0: regs= stack=-8 before 5: (85) call pc+6") +__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_stack_slot_precise_global(void) +{ + asm volatile ( + /* spill reg */ + "r6 = 3;" + "*(u64 *)(r10 - 8) = r6;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call global_identity_subprog;" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r6 = *(u64 *)(r10 - 8);" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("14: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 14 first_idx 11") +__msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: parent state regs= stack=-8:") +__msg("mark_precise: frame0: last_idx 18 first_idx 0") +__msg("mark_precise: frame0: regs= stack=-8 before 18: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0") +__msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181") +__msg("mark_precise: frame0: regs= stack=-8 before 9: (b7) r4 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 8: (b7) r3 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r2 = r8") +__msg("mark_precise: frame0: regs= stack=-8 before 6: (bf) r1 = r6") +__msg("mark_precise: frame0: regs= stack=-8 before 5: (7b) *(u64 *)(r10 -8) = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +__naked int parent_stack_slot_precise_with_callback(void) +{ + asm volatile ( + /* spill reg */ + "r6 = 3;" + "*(u64 *)(r10 - 8) = r6;" + + /* ensure we have callback frame in jump history */ + "r1 = r6;" /* nr_loops */ + "r2 = %[callback_subprog];" /* callback_fn */ + "r3 = 0;" /* callback_ctx */ + "r4 = 0;" /* flags */ + "call %[bpf_loop];" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r6 = *(u64 *)(r10 - 8);" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals), + __imm_ptr(callback_subprog), + __imm(bpf_loop) + : __clobber_common, "r6" + ); +} + +__noinline __used +static __u64 subprog_with_precise_arg(__u64 x) +{ + return vals[x]; /* x is forced to be precise */ +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("8: (0f) r2 += r1") +__msg("mark_precise: frame1: last_idx 8 first_idx 0") +__msg("mark_precise: frame1: regs=r1 stack= before 6: (18) r2 = ") +__msg("mark_precise: frame1: regs=r1 stack= before 5: (67) r1 <<= 2") +__msg("mark_precise: frame1: regs=r1 stack= before 2: (85) call pc+2") +__msg("mark_precise: frame0: regs=r1 stack= before 1: (bf) r1 = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 0: (b7) r6 = 3") +__naked int subprog_arg_precise(void) +{ + asm volatile ( + "r6 = 3;" + "r1 = r6;" + /* subprog_with_precise_arg expects its argument to be + * precise, so r1->r6 will be marked precise from inside the + * subprog + */ + "call subprog_with_precise_arg;" + "r0 += r6;" + "exit;" + : + : + : __clobber_common, "r6" + ); +} + +/* r1 is pointer to stack slot; + * r2 is a register to spill into that slot + * subprog also spills r2 into its own stack slot + */ +__naked __noinline __used +static __u64 subprog_spill_reg_precise(void) +{ + asm volatile ( + /* spill to parent stack */ + "*(u64 *)(r1 + 0) = r2;" + /* spill to subprog stack (we use -16 offset to avoid + * accidental confusion with parent's -8 stack slot in + * verifier log output) + */ + "*(u64 *)(r10 - 16) = r2;" + /* use both spills as return result to propagete precision everywhere */ + "r0 = *(u64 *)(r10 - 16);" + "r2 = *(u64 *)(r1 + 0);" + "r0 += r2;" + "exit;" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +/* precision backtracking can't currently handle stack access not through r10, + * so we won't be able to mark stack slot fp-8 as precise, and so will + * fallback to forcing all as precise + */ +__msg("mark_precise: frame0: falling back to forcing all scalars precise") +__naked int subprog_spill_into_parent_stack_slot_precise(void) +{ + asm volatile ( + "r6 = 1;" + + /* pass pointer to stack slot and r6 to subprog; + * r6 will be marked precise and spilled into fp-8 slot, which + * also should be marked precise + */ + "r1 = r10;" + "r1 += -8;" + "r2 = r6;" + "call subprog_spill_reg_precise;" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r7 = *(u64 *)(r10 - 8);" + + "r7 *= 4;" + "r1 = %[vals];" + /* here r7 is forced to be precise and has to be propagated + * back to the beginning, handling subprog call and logic + */ + "r1 += r7;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6", "r7" + ); +} + +__naked __noinline __used +static __u64 subprog_with_checkpoint(void) +{ + asm volatile ( + "r0 = 0;" + /* guaranteed checkpoint if BPF_F_TEST_STATE_FREQ is used */ + "goto +0;" + "exit;" + ); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/vrf_socket_lookup.c b/tools/testing/selftests/bpf/progs/vrf_socket_lookup.c new file mode 100644 index 000000000000..bcfb6feb38c0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/vrf_socket_lookup.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include <linux/ip.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/pkt_cls.h> +#include <stdbool.h> + +int lookup_status; +bool test_xdp; +bool tcp_skc; + +#define CUR_NS BPF_F_CURRENT_NETNS + +static void socket_lookup(void *ctx, void *data_end, void *data) +{ + struct ethhdr *eth = data; + struct bpf_sock_tuple *tp; + struct bpf_sock *sk; + struct iphdr *iph; + int tplen; + + if (eth + 1 > data_end) + return; + + if (eth->h_proto != bpf_htons(ETH_P_IP)) + return; + + iph = (struct iphdr *)(eth + 1); + if (iph + 1 > data_end) + return; + + tp = (struct bpf_sock_tuple *)&iph->saddr; + tplen = sizeof(tp->ipv4); + if ((void *)tp + tplen > data_end) + return; + + switch (iph->protocol) { + case IPPROTO_TCP: + if (tcp_skc) + sk = bpf_skc_lookup_tcp(ctx, tp, tplen, CUR_NS, 0); + else + sk = bpf_sk_lookup_tcp(ctx, tp, tplen, CUR_NS, 0); + break; + case IPPROTO_UDP: + sk = bpf_sk_lookup_udp(ctx, tp, tplen, CUR_NS, 0); + break; + default: + return; + } + + lookup_status = 0; + + if (sk) { + bpf_sk_release(sk); + lookup_status = 1; + } +} + +SEC("tc") +int tc_socket_lookup(struct __sk_buff *skb) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + + if (test_xdp) + return TC_ACT_UNSPEC; + + socket_lookup(skb, data_end, data); + return TC_ACT_UNSPEC; +} + +SEC("xdp") +int xdp_socket_lookup(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + + if (!test_xdp) + return XDP_PASS; + + socket_lookup(xdp, data_end, data); + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c index e1c787815e44..b2dfd7066c6e 100644 --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -77,7 +77,9 @@ int rx(struct xdp_md *ctx) } err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp); - if (err) + if (!err) + meta->xdp_timestamp = bpf_ktime_get_tai_ns(); + else meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */ err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index ea82921110da..4d582cac2c09 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -11,7 +11,6 @@ #include <signal.h> #include <string.h> #include <execinfo.h> /* backtrace */ -#include <linux/membarrier.h> #include <sys/sysinfo.h> /* get_nprocs */ #include <netinet/in.h> #include <sys/select.h> @@ -629,68 +628,6 @@ out: return err; } -static int finit_module(int fd, const char *param_values, int flags) -{ - return syscall(__NR_finit_module, fd, param_values, flags); -} - -static int delete_module(const char *name, int flags) -{ - return syscall(__NR_delete_module, name, flags); -} - -/* - * Trigger synchronize_rcu() in kernel. - */ -int kern_sync_rcu(void) -{ - return syscall(__NR_membarrier, MEMBARRIER_CMD_SHARED, 0, 0); -} - -static void unload_bpf_testmod(void) -{ - if (kern_sync_rcu()) - fprintf(env.stderr, "Failed to trigger kernel-side RCU sync!\n"); - if (delete_module("bpf_testmod", 0)) { - if (errno == ENOENT) { - if (verbose()) - fprintf(stdout, "bpf_testmod.ko is already unloaded.\n"); - return; - } - fprintf(env.stderr, "Failed to unload bpf_testmod.ko from kernel: %d\n", -errno); - return; - } - if (verbose()) - fprintf(stdout, "Successfully unloaded bpf_testmod.ko.\n"); -} - -static int load_bpf_testmod(void) -{ - int fd; - - /* ensure previous instance of the module is unloaded */ - unload_bpf_testmod(); - - if (verbose()) - fprintf(stdout, "Loading bpf_testmod.ko...\n"); - - fd = open("bpf_testmod.ko", O_RDONLY); - if (fd < 0) { - fprintf(env.stderr, "Can't find bpf_testmod.ko kernel module: %d\n", -errno); - return -ENOENT; - } - if (finit_module(fd, "", 0)) { - fprintf(env.stderr, "Failed to load bpf_testmod.ko into the kernel: %d\n", -errno); - close(fd); - return -EINVAL; - } - close(fd); - - if (verbose()) - fprintf(stdout, "Successfully loaded bpf_testmod.ko.\n"); - return 0; -} - /* extern declarations for test funcs */ #define DEFINE_TEST(name) \ extern void test_##name(void) __weak; \ @@ -714,7 +651,13 @@ static struct test_state test_states[ARRAY_SIZE(prog_test_defs)]; const char *argp_program_version = "test_progs 0.1"; const char *argp_program_bug_address = "<bpf@vger.kernel.org>"; -static const char argp_program_doc[] = "BPF selftests test runner"; +static const char argp_program_doc[] = +"BPF selftests test runner\v" +"Options accepting the NAMES parameter take either a comma-separated list\n" +"of test names, or a filename prefixed with @. The file contains one name\n" +"(or wildcard pattern) per line, and comments beginning with # are ignored.\n" +"\n" +"These options can be passed repeatedly to read multiple files.\n"; enum ARG_KEYS { ARG_TEST_NUM = 'n', @@ -797,6 +740,7 @@ extern int extra_prog_load_log_flags; static error_t parse_arg(int key, char *arg, struct argp_state *state) { struct test_env *env = state->input; + int err = 0; switch (key) { case ARG_TEST_NUM: { @@ -821,18 +765,28 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) } case ARG_TEST_NAME_GLOB_ALLOWLIST: case ARG_TEST_NAME: { - if (parse_test_list(arg, - &env->test_selector.whitelist, - key == ARG_TEST_NAME_GLOB_ALLOWLIST)) - return -ENOMEM; + if (arg[0] == '@') + err = parse_test_list_file(arg + 1, + &env->test_selector.whitelist, + key == ARG_TEST_NAME_GLOB_ALLOWLIST); + else + err = parse_test_list(arg, + &env->test_selector.whitelist, + key == ARG_TEST_NAME_GLOB_ALLOWLIST); + break; } case ARG_TEST_NAME_GLOB_DENYLIST: case ARG_TEST_NAME_BLACKLIST: { - if (parse_test_list(arg, - &env->test_selector.blacklist, - key == ARG_TEST_NAME_GLOB_DENYLIST)) - return -ENOMEM; + if (arg[0] == '@') + err = parse_test_list_file(arg + 1, + &env->test_selector.blacklist, + key == ARG_TEST_NAME_GLOB_DENYLIST); + else + err = parse_test_list(arg, + &env->test_selector.blacklist, + key == ARG_TEST_NAME_GLOB_DENYLIST); + break; } case ARG_VERIFIER_STATS: @@ -900,7 +854,7 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) default: return ARGP_ERR_UNKNOWN; } - return 0; + return err; } /* @@ -1703,9 +1657,14 @@ int main(int argc, char **argv) env.stderr = stderr; env.has_testmod = true; - if (!env.list_test_names && load_bpf_testmod()) { - fprintf(env.stderr, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n"); - env.has_testmod = false; + if (!env.list_test_names) { + /* ensure previous instance of the module is unloaded */ + unload_bpf_testmod(verbose()); + + if (load_bpf_testmod(verbose())) { + fprintf(env.stderr, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n"); + env.has_testmod = false; + } } /* initializing tests */ @@ -1802,7 +1761,7 @@ int main(int argc, char **argv) close(env.saved_netns_fd); out: if (!env.list_test_names && env.has_testmod) - unload_bpf_testmod(); + unload_bpf_testmod(verbose()); free_test_selector(&env.test_selector); free_test_selector(&env.subtest_selector); diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 0ed3134333d4..77bd492c6024 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -405,7 +405,6 @@ static inline void *u64_to_ptr(__u64 ptr) int bpf_find_map(const char *test, struct bpf_object *obj, const char *name); int compare_map_keys(int map1_fd, int map2_fd); int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len); -int kern_sync_rcu(void); int trigger_module_test_read(int read_sz); int trigger_module_test_write(int write_sz); int write_sysctl(const char *sysctl, const char *value); diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index e4657c5bc3f1..31f1c935cd07 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -40,6 +40,7 @@ #include "bpf_util.h" #include "test_btf.h" #include "../../../include/linux/filter.h" +#include "testing_helpers.h" #ifndef ENOTSUPP #define ENOTSUPP 524 @@ -873,8 +874,140 @@ static int create_map_kptr(void) return fd; } +static void set_root(bool set) +{ + __u64 caps; + + if (set) { + if (cap_enable_effective(1ULL << CAP_SYS_ADMIN, &caps)) + perror("cap_disable_effective(CAP_SYS_ADMIN)"); + } else { + if (cap_disable_effective(1ULL << CAP_SYS_ADMIN, &caps)) + perror("cap_disable_effective(CAP_SYS_ADMIN)"); + } +} + +static __u64 ptr_to_u64(const void *ptr) +{ + return (uintptr_t) ptr; +} + +static struct btf *btf__load_testmod_btf(struct btf *vmlinux) +{ + struct bpf_btf_info info; + __u32 len = sizeof(info); + struct btf *btf = NULL; + char name[64]; + __u32 id = 0; + int err, fd; + + /* Iterate all loaded BTF objects and find bpf_testmod, + * we need SYS_ADMIN cap for that. + */ + set_root(true); + + while (true) { + err = bpf_btf_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + break; + perror("bpf_btf_get_next_id failed"); + break; + } + + fd = bpf_btf_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + perror("bpf_btf_get_fd_by_id failed"); + break; + } + + memset(&info, 0, sizeof(info)); + info.name_len = sizeof(name); + info.name = ptr_to_u64(name); + len = sizeof(info); + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + close(fd); + perror("bpf_obj_get_info_by_fd failed"); + break; + } + + if (strcmp("bpf_testmod", name)) { + close(fd); + continue; + } + + btf = btf__load_from_kernel_by_id_split(id, vmlinux); + if (!btf) { + close(fd); + break; + } + + /* We need the fd to stay open so it can be used in fd_array. + * The final cleanup call to btf__free will free btf object + * and close the file descriptor. + */ + btf__set_fd(btf, fd); + break; + } + + set_root(false); + return btf; +} + +static struct btf *testmod_btf; +static struct btf *vmlinux_btf; + +static void kfuncs_cleanup(void) +{ + btf__free(testmod_btf); + btf__free(vmlinux_btf); +} + +static void fixup_prog_kfuncs(struct bpf_insn *prog, int *fd_array, + struct kfunc_btf_id_pair *fixup_kfunc_btf_id) +{ + /* Patch in kfunc BTF IDs */ + while (fixup_kfunc_btf_id->kfunc) { + int btf_id = 0; + + /* try to find kfunc in kernel BTF */ + vmlinux_btf = vmlinux_btf ?: btf__load_vmlinux_btf(); + if (vmlinux_btf) { + btf_id = btf__find_by_name_kind(vmlinux_btf, + fixup_kfunc_btf_id->kfunc, + BTF_KIND_FUNC); + btf_id = btf_id < 0 ? 0 : btf_id; + } + + /* kfunc not found in kernel BTF, try bpf_testmod BTF */ + if (!btf_id) { + testmod_btf = testmod_btf ?: btf__load_testmod_btf(vmlinux_btf); + if (testmod_btf) { + btf_id = btf__find_by_name_kind(testmod_btf, + fixup_kfunc_btf_id->kfunc, + BTF_KIND_FUNC); + btf_id = btf_id < 0 ? 0 : btf_id; + if (btf_id) { + /* We put bpf_testmod module fd into fd_array + * and its index 1 into instruction 'off'. + */ + *fd_array = btf__fd(testmod_btf); + prog[fixup_kfunc_btf_id->insn_idx].off = 1; + } + } + } + + prog[fixup_kfunc_btf_id->insn_idx].imm = btf_id; + fixup_kfunc_btf_id++; + } +} + static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, - struct bpf_insn *prog, int *map_fds) + struct bpf_insn *prog, int *map_fds, int *fd_array) { int *fixup_map_hash_8b = test->fixup_map_hash_8b; int *fixup_map_hash_48b = test->fixup_map_hash_48b; @@ -899,7 +1032,6 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_ringbuf = test->fixup_map_ringbuf; int *fixup_map_timer = test->fixup_map_timer; int *fixup_map_kptr = test->fixup_map_kptr; - struct kfunc_btf_id_pair *fixup_kfunc_btf_id = test->fixup_kfunc_btf_id; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -1100,25 +1232,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, } while (*fixup_map_kptr); } - /* Patch in kfunc BTF IDs */ - if (fixup_kfunc_btf_id->kfunc) { - struct btf *btf; - int btf_id; - - do { - btf_id = 0; - btf = btf__load_vmlinux_btf(); - if (btf) { - btf_id = btf__find_by_name_kind(btf, - fixup_kfunc_btf_id->kfunc, - BTF_KIND_FUNC); - btf_id = btf_id < 0 ? 0 : btf_id; - } - btf__free(btf); - prog[fixup_kfunc_btf_id->insn_idx].imm = btf_id; - fixup_kfunc_btf_id++; - } while (fixup_kfunc_btf_id->kfunc); - } + fixup_prog_kfuncs(prog, fd_array, test->fixup_kfunc_btf_id); } struct libcap { @@ -1227,45 +1341,46 @@ static bool cmp_str_seq(const char *log, const char *exp) return true; } -static int get_xlated_program(int fd_prog, struct bpf_insn **buf, int *cnt) +static struct bpf_insn *get_xlated_program(int fd_prog, int *cnt) { + __u32 buf_element_size = sizeof(struct bpf_insn); struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); __u32 xlated_prog_len; - __u32 buf_element_size = sizeof(struct bpf_insn); + struct bpf_insn *buf; if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) { perror("bpf_prog_get_info_by_fd failed"); - return -1; + return NULL; } xlated_prog_len = info.xlated_prog_len; if (xlated_prog_len % buf_element_size) { printf("Program length %d is not multiple of %d\n", xlated_prog_len, buf_element_size); - return -1; + return NULL; } *cnt = xlated_prog_len / buf_element_size; - *buf = calloc(*cnt, buf_element_size); + buf = calloc(*cnt, buf_element_size); if (!buf) { perror("can't allocate xlated program buffer"); - return -ENOMEM; + return NULL; } bzero(&info, sizeof(info)); info.xlated_prog_len = xlated_prog_len; - info.xlated_prog_insns = (__u64)(unsigned long)*buf; + info.xlated_prog_insns = (__u64)(unsigned long)buf; if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) { perror("second bpf_prog_get_info_by_fd failed"); goto out_free_buf; } - return 0; + return buf; out_free_buf: - free(*buf); - return -1; + free(buf); + return NULL; } static bool is_null_insn(struct bpf_insn *insn) @@ -1398,7 +1513,8 @@ static bool check_xlated_program(struct bpf_test *test, int fd_prog) if (!check_expected && !check_unexpected) goto out; - if (get_xlated_program(fd_prog, &buf, &cnt)) { + buf = get_xlated_program(fd_prog, &cnt); + if (!buf) { printf("FAIL: can't get xlated program\n"); result = false; goto out; @@ -1445,6 +1561,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, int run_errs, run_successes; int map_fds[MAX_NR_MAPS]; const char *expected_err; + int fd_array[2] = { -1, -1 }; int saved_errno; int fixup_skips; __u32 pflags; @@ -1458,7 +1575,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, if (!prog_type) prog_type = BPF_PROG_TYPE_SOCKET_FILTER; fixup_skips = skips; - do_test_fixup(test, prog_type, prog, map_fds); + do_test_fixup(test, prog_type, prog, map_fds, &fd_array[1]); if (test->fill_insns) { prog = test->fill_insns; prog_len = test->prog_len; @@ -1492,6 +1609,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv, else opts.log_level = DEFAULT_LIBBPF_LOG_LEVEL; opts.prog_flags = pflags; + if (fd_array[1] != -1) + opts.fd_array = &fd_array[0]; if ((prog_type == BPF_PROG_TYPE_TRACING || prog_type == BPF_PROG_TYPE_LSM) && test->kfunc) { @@ -1684,6 +1803,12 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to) { int i, passes = 0, errors = 0; + /* ensure previous instance of the module is unloaded */ + unload_bpf_testmod(verbose); + + if (load_bpf_testmod(verbose)) + return EXIT_FAILURE; + for (i = from; i < to; i++) { struct bpf_test *test = &tests[i]; @@ -1711,6 +1836,9 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to) } } + unload_bpf_testmod(verbose); + kfuncs_cleanup(); + printf("Summary: %d PASSED, %d SKIPPED, %d FAILED\n", passes, skips, errors); return errors ? EXIT_FAILURE : EXIT_SUCCESS; diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh index 377fb157a57c..c2ad50f26b63 100755 --- a/tools/testing/selftests/bpf/test_xsk.sh +++ b/tools/testing/selftests/bpf/test_xsk.sh @@ -68,9 +68,6 @@ # Run with verbose output: # sudo ./test_xsk.sh -v # -# Run and dump packet contents: -# sudo ./test_xsk.sh -D -# # Set up veth interfaces and leave them up so xskxceiver can be launched in a debugger: # sudo ./test_xsk.sh -d # @@ -81,11 +78,10 @@ ETH="" -while getopts "vDi:d" flag +while getopts "vi:d" flag do case "${flag}" in v) verbose=1;; - D) dump_pkts=1;; d) debug=1;; i) ETH=${OPTARG};; esac @@ -157,10 +153,6 @@ if [[ $verbose -eq 1 ]]; then ARGS+="-v " fi -if [[ $dump_pkts -eq 1 ]]; then - ARGS="-D " -fi - retval=$? test_status $retval "${TEST_NAME}" diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index 0b5e0829e5be..8d994884c7b4 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) /* Copyright (C) 2019 Netronome Systems, Inc. */ /* Copyright (C) 2020 Facebook, Inc. */ +#include <ctype.h> #include <stdlib.h> #include <string.h> #include <errno.h> @@ -8,6 +9,7 @@ #include <bpf/libbpf.h> #include "test_progs.h" #include "testing_helpers.h" +#include <linux/membarrier.h> int parse_num_list(const char *s, bool **num_set, int *num_set_len) { @@ -70,92 +72,168 @@ int parse_num_list(const char *s, bool **num_set, int *num_set_len) return 0; } -int parse_test_list(const char *s, - struct test_filter_set *set, - bool is_glob_pattern) +static int do_insert_test(struct test_filter_set *set, + char *test_str, + char *subtest_str) { - char *input, *state = NULL, *next; - struct test_filter *tmp, *tests = NULL; - int i, j, cnt = 0; + struct test_filter *tmp, *test; + char **ctmp; + int i; - input = strdup(s); - if (!input) + for (i = 0; i < set->cnt; i++) { + test = &set->tests[i]; + + if (strcmp(test_str, test->name) == 0) { + free(test_str); + goto subtest; + } + } + + tmp = realloc(set->tests, sizeof(*test) * (set->cnt + 1)); + if (!tmp) return -ENOMEM; - while ((next = strtok_r(state ? NULL : input, ",", &state))) { - char *subtest_str = strchr(next, '/'); - char *pattern = NULL; - int glob_chars = 0; + set->tests = tmp; + test = &set->tests[set->cnt]; - tmp = realloc(tests, sizeof(*tests) * (cnt + 1)); - if (!tmp) - goto err; - tests = tmp; + test->name = test_str; + test->subtests = NULL; + test->subtest_cnt = 0; - tests[cnt].subtest_cnt = 0; - tests[cnt].subtests = NULL; + set->cnt++; - if (is_glob_pattern) { - pattern = "%s"; - } else { - pattern = "*%s*"; - glob_chars = 2; - } +subtest: + if (!subtest_str) + return 0; - if (subtest_str) { - char **tmp_subtests = NULL; - int subtest_cnt = tests[cnt].subtest_cnt; - - *subtest_str = '\0'; - subtest_str += 1; - tmp_subtests = realloc(tests[cnt].subtests, - sizeof(*tmp_subtests) * - (subtest_cnt + 1)); - if (!tmp_subtests) - goto err; - tests[cnt].subtests = tmp_subtests; - - tests[cnt].subtests[subtest_cnt] = - malloc(strlen(subtest_str) + glob_chars + 1); - if (!tests[cnt].subtests[subtest_cnt]) - goto err; - sprintf(tests[cnt].subtests[subtest_cnt], - pattern, - subtest_str); - - tests[cnt].subtest_cnt++; + for (i = 0; i < test->subtest_cnt; i++) { + if (strcmp(subtest_str, test->subtests[i]) == 0) { + free(subtest_str); + return 0; } + } - tests[cnt].name = malloc(strlen(next) + glob_chars + 1); - if (!tests[cnt].name) - goto err; - sprintf(tests[cnt].name, pattern, next); + ctmp = realloc(test->subtests, + sizeof(*test->subtests) * (test->subtest_cnt + 1)); + if (!ctmp) + return -ENOMEM; - cnt++; + test->subtests = ctmp; + test->subtests[test->subtest_cnt] = subtest_str; + + test->subtest_cnt++; + + return 0; +} + +static int insert_test(struct test_filter_set *set, + char *test_spec, + bool is_glob_pattern) +{ + char *pattern, *subtest_str, *ext_test_str, *ext_subtest_str = NULL; + int glob_chars = 0; + + if (is_glob_pattern) { + pattern = "%s"; + } else { + pattern = "*%s*"; + glob_chars = 2; } - tmp = realloc(set->tests, sizeof(*tests) * (cnt + set->cnt)); - if (!tmp) + subtest_str = strchr(test_spec, '/'); + if (subtest_str) { + *subtest_str = '\0'; + subtest_str += 1; + } + + ext_test_str = malloc(strlen(test_spec) + glob_chars + 1); + if (!ext_test_str) goto err; - memcpy(tmp + set->cnt, tests, sizeof(*tests) * cnt); - set->tests = tmp; - set->cnt += cnt; + sprintf(ext_test_str, pattern, test_spec); - free(tests); - free(input); - return 0; + if (subtest_str) { + ext_subtest_str = malloc(strlen(subtest_str) + glob_chars + 1); + if (!ext_subtest_str) + goto err; + + sprintf(ext_subtest_str, pattern, subtest_str); + } + + return do_insert_test(set, ext_test_str, ext_subtest_str); err: - for (i = 0; i < cnt; i++) { - for (j = 0; j < tests[i].subtest_cnt; j++) - free(tests[i].subtests[j]); + free(ext_test_str); + free(ext_subtest_str); + + return -ENOMEM; +} + +int parse_test_list_file(const char *path, + struct test_filter_set *set, + bool is_glob_pattern) +{ + char *buf = NULL, *capture_start, *capture_end, *scan_end; + size_t buflen = 0; + int err = 0; + FILE *f; + + f = fopen(path, "r"); + if (!f) { + err = -errno; + fprintf(stderr, "Failed to open '%s': %d\n", path, err); + return err; + } + + while (getline(&buf, &buflen, f) != -1) { + capture_start = buf; + + while (isspace(*capture_start)) + ++capture_start; + + capture_end = capture_start; + scan_end = capture_start; + + while (*scan_end && *scan_end != '#') { + if (!isspace(*scan_end)) + capture_end = scan_end; + + ++scan_end; + } + + if (capture_end == capture_start) + continue; + + *(++capture_end) = '\0'; + + err = insert_test(set, capture_start, is_glob_pattern); + if (err) + break; + } + + fclose(f); + return err; +} + +int parse_test_list(const char *s, + struct test_filter_set *set, + bool is_glob_pattern) +{ + char *input, *state = NULL, *test_spec; + int err = 0; + + input = strdup(s); + if (!input) + return -ENOMEM; - free(tests[i].name); + while ((test_spec = strtok_r(state ? NULL : input, ",", &state))) { + err = insert_test(set, test_spec, is_glob_pattern); + if (err) + break; } - free(tests); + free(input); - return -ENOMEM; + return err; } __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info) @@ -249,3 +327,63 @@ __u64 read_perf_max_sample_freq(void) fclose(f); return sample_freq; } + +static int finit_module(int fd, const char *param_values, int flags) +{ + return syscall(__NR_finit_module, fd, param_values, flags); +} + +static int delete_module(const char *name, int flags) +{ + return syscall(__NR_delete_module, name, flags); +} + +int unload_bpf_testmod(bool verbose) +{ + if (kern_sync_rcu()) + fprintf(stdout, "Failed to trigger kernel-side RCU sync!\n"); + if (delete_module("bpf_testmod", 0)) { + if (errno == ENOENT) { + if (verbose) + fprintf(stdout, "bpf_testmod.ko is already unloaded.\n"); + return -1; + } + fprintf(stdout, "Failed to unload bpf_testmod.ko from kernel: %d\n", -errno); + return -1; + } + if (verbose) + fprintf(stdout, "Successfully unloaded bpf_testmod.ko.\n"); + return 0; +} + +int load_bpf_testmod(bool verbose) +{ + int fd; + + if (verbose) + fprintf(stdout, "Loading bpf_testmod.ko...\n"); + + fd = open("bpf_testmod.ko", O_RDONLY); + if (fd < 0) { + fprintf(stdout, "Can't find bpf_testmod.ko kernel module: %d\n", -errno); + return -ENOENT; + } + if (finit_module(fd, "", 0)) { + fprintf(stdout, "Failed to load bpf_testmod.ko into the kernel: %d\n", -errno); + close(fd); + return -EINVAL; + } + close(fd); + + if (verbose) + fprintf(stdout, "Successfully loaded bpf_testmod.ko.\n"); + return 0; +} + +/* + * Trigger synchronize_rcu() in kernel. + */ +int kern_sync_rcu(void) +{ + return syscall(__NR_membarrier, MEMBARRIER_CMD_SHARED, 0, 0); +} diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h index eb8790f928e4..5312323881b6 100644 --- a/tools/testing/selftests/bpf/testing_helpers.h +++ b/tools/testing/selftests/bpf/testing_helpers.h @@ -1,5 +1,9 @@ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ /* Copyright (C) 2020 Facebook, Inc. */ + +#ifndef __TESTING_HELPERS_H +#define __TESTING_HELPERS_H + #include <stdbool.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> @@ -20,5 +24,13 @@ struct test_filter_set; int parse_test_list(const char *s, struct test_filter_set *test_set, bool is_glob_pattern); +int parse_test_list_file(const char *path, + struct test_filter_set *test_set, + bool is_glob_pattern); __u64 read_perf_max_sample_freq(void); +int load_bpf_testmod(bool verbose); +int unload_bpf_testmod(bool verbose); +int kern_sync_rcu(void); + +#endif /* __TESTING_HELPERS_H */ diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c index 6c03a7d805f9..99272bb890da 100644 --- a/tools/testing/selftests/bpf/verifier/precise.c +++ b/tools/testing/selftests/bpf/verifier/precise.c @@ -38,25 +38,24 @@ .fixup_map_array_48b = { 1 }, .result = VERBOSE_ACCEPT, .errstr = - "26: (85) call bpf_probe_read_kernel#113\ - last_idx 26 first_idx 20\ - regs=4 stack=0 before 25\ - regs=4 stack=0 before 24\ - regs=4 stack=0 before 23\ - regs=4 stack=0 before 22\ - regs=4 stack=0 before 20\ - parent didn't have regs=4 stack=0 marks\ - last_idx 19 first_idx 10\ - regs=4 stack=0 before 19\ - regs=200 stack=0 before 18\ - regs=300 stack=0 before 17\ - regs=201 stack=0 before 15\ - regs=201 stack=0 before 14\ - regs=200 stack=0 before 13\ - regs=200 stack=0 before 12\ - regs=200 stack=0 before 11\ - regs=200 stack=0 before 10\ - parent already had regs=0 stack=0 marks", + "mark_precise: frame0: last_idx 26 first_idx 20\ + mark_precise: frame0: regs=r2 stack= before 25\ + mark_precise: frame0: regs=r2 stack= before 24\ + mark_precise: frame0: regs=r2 stack= before 23\ + mark_precise: frame0: regs=r2 stack= before 22\ + mark_precise: frame0: regs=r2 stack= before 20\ + mark_precise: frame0: parent state regs=r2 stack=:\ + mark_precise: frame0: last_idx 19 first_idx 10\ + mark_precise: frame0: regs=r2,r9 stack= before 19\ + mark_precise: frame0: regs=r9 stack= before 18\ + mark_precise: frame0: regs=r8,r9 stack= before 17\ + mark_precise: frame0: regs=r0,r9 stack= before 15\ + mark_precise: frame0: regs=r0,r9 stack= before 14\ + mark_precise: frame0: regs=r9 stack= before 13\ + mark_precise: frame0: regs=r9 stack= before 12\ + mark_precise: frame0: regs=r9 stack= before 11\ + mark_precise: frame0: regs=r9 stack= before 10\ + mark_precise: frame0: parent state regs= stack=:", }, { "precise: test 2", @@ -100,20 +99,20 @@ .flags = BPF_F_TEST_STATE_FREQ, .errstr = "26: (85) call bpf_probe_read_kernel#113\ - last_idx 26 first_idx 22\ - regs=4 stack=0 before 25\ - regs=4 stack=0 before 24\ - regs=4 stack=0 before 23\ - regs=4 stack=0 before 22\ - parent didn't have regs=4 stack=0 marks\ - last_idx 20 first_idx 20\ - regs=4 stack=0 before 20\ - parent didn't have regs=4 stack=0 marks\ - last_idx 19 first_idx 17\ - regs=4 stack=0 before 19\ - regs=200 stack=0 before 18\ - regs=300 stack=0 before 17\ - parent already had regs=0 stack=0 marks", + mark_precise: frame0: last_idx 26 first_idx 22\ + mark_precise: frame0: regs=r2 stack= before 25\ + mark_precise: frame0: regs=r2 stack= before 24\ + mark_precise: frame0: regs=r2 stack= before 23\ + mark_precise: frame0: regs=r2 stack= before 22\ + mark_precise: frame0: parent state regs=r2 stack=:\ + mark_precise: frame0: last_idx 20 first_idx 20\ + mark_precise: frame0: regs=r2,r9 stack= before 20\ + mark_precise: frame0: parent state regs=r2,r9 stack=:\ + mark_precise: frame0: last_idx 19 first_idx 17\ + mark_precise: frame0: regs=r2,r9 stack= before 19\ + mark_precise: frame0: regs=r9 stack= before 18\ + mark_precise: frame0: regs=r8,r9 stack= before 17\ + mark_precise: frame0: parent state regs= stack=:", }, { "precise: cross frame pruning", @@ -153,15 +152,16 @@ }, .prog_type = BPF_PROG_TYPE_XDP, .flags = BPF_F_TEST_STATE_FREQ, - .errstr = "5: (2d) if r4 > r0 goto pc+0\ - last_idx 5 first_idx 5\ - parent didn't have regs=10 stack=0 marks\ - last_idx 4 first_idx 2\ - regs=10 stack=0 before 4\ - regs=10 stack=0 before 3\ - regs=0 stack=1 before 2\ - last_idx 5 first_idx 5\ - parent didn't have regs=1 stack=0 marks", + .errstr = "mark_precise: frame0: last_idx 5 first_idx 5\ + mark_precise: frame0: parent state regs=r4 stack=:\ + mark_precise: frame0: last_idx 4 first_idx 2\ + mark_precise: frame0: regs=r4 stack= before 4\ + mark_precise: frame0: regs=r4 stack= before 3\ + mark_precise: frame0: regs= stack=-8 before 2\ + mark_precise: frame0: falling back to forcing all scalars precise\ + force_precise: frame0: forcing r0 to be precise\ + mark_precise: frame0: last_idx 5 first_idx 5\ + mark_precise: frame0: parent state regs= stack=:", .result = VERBOSE_ACCEPT, .retval = -1, }, @@ -179,16 +179,19 @@ }, .prog_type = BPF_PROG_TYPE_XDP, .flags = BPF_F_TEST_STATE_FREQ, - .errstr = "last_idx 6 first_idx 6\ - parent didn't have regs=10 stack=0 marks\ - last_idx 5 first_idx 3\ - regs=10 stack=0 before 5\ - regs=10 stack=0 before 4\ - regs=0 stack=1 before 3\ - last_idx 6 first_idx 6\ - parent didn't have regs=1 stack=0 marks\ - last_idx 5 first_idx 3\ - regs=1 stack=0 before 5", + .errstr = "mark_precise: frame0: last_idx 6 first_idx 6\ + mark_precise: frame0: parent state regs=r4 stack=:\ + mark_precise: frame0: last_idx 5 first_idx 3\ + mark_precise: frame0: regs=r4 stack= before 5\ + mark_precise: frame0: regs=r4 stack= before 4\ + mark_precise: frame0: regs= stack=-8 before 3\ + mark_precise: frame0: falling back to forcing all scalars precise\ + force_precise: frame0: forcing r0 to be precise\ + force_precise: frame0: forcing r0 to be precise\ + force_precise: frame0: forcing r0 to be precise\ + force_precise: frame0: forcing r0 to be precise\ + mark_precise: frame0: last_idx 6 first_idx 6\ + mark_precise: frame0: parent state regs= stack=:", .result = VERBOSE_ACCEPT, .retval = -1, }, @@ -217,3 +220,39 @@ .errstr = "invalid access to memory, mem_size=1 off=42 size=8", .result = REJECT, }, +{ + "precise: program doesn't prematurely prune branches", + .insns = { + BPF_ALU64_IMM(BPF_MOV, BPF_REG_6, 0x400), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_8, 0), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_9, 0x80000000), + BPF_ALU64_IMM(BPF_MOD, BPF_REG_6, 0x401), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), + BPF_JMP_REG(BPF_JLE, BPF_REG_6, BPF_REG_9, 2), + BPF_ALU64_IMM(BPF_MOD, BPF_REG_6, 1), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_9, 0), + BPF_JMP_REG(BPF_JLE, BPF_REG_6, BPF_REG_9, 1), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_6, 0), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), + BPF_LD_MAP_FD(BPF_REG_4, 0), + BPF_ALU64_REG(BPF_MOV, BPF_REG_1, BPF_REG_4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_6, 10), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_6, 8192), + BPF_ALU64_REG(BPF_MOV, BPF_REG_1, BPF_REG_0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_6), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_3, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 13 }, + .prog_type = BPF_PROG_TYPE_XDP, + .result = REJECT, + .errstr = "register with unbounded min value is not allowed", +}, diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index 1db7185181da..655095810d4a 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -141,6 +141,7 @@ static struct env { bool verbose; bool debug; bool quiet; + bool force_checkpoints; enum resfmt out_fmt; bool show_version; bool comparison_mode; @@ -209,6 +210,8 @@ static const struct argp_option opts[] = { { "log-level", 'l', "LEVEL", 0, "Verifier log level (default 0 for normal mode, 1 for verbose mode)" }, { "log-fixed", OPT_LOG_FIXED, NULL, 0, "Disable verifier log rotation" }, { "log-size", OPT_LOG_SIZE, "BYTES", 0, "Customize verifier log size (default to 16MB)" }, + { "test-states", 't', NULL, 0, + "Force frequent BPF verifier state checkpointing (set BPF_F_TEST_STATE_FREQ program flag)" }, { "quiet", 'q', NULL, 0, "Quiet mode" }, { "emit", 'e', "SPEC", 0, "Specify stats to be emitted" }, { "sort", 's', "SPEC", 0, "Specify sort order" }, @@ -284,6 +287,9 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) argp_usage(state); } break; + case 't': + env.force_checkpoints = true; + break; case 'C': env.comparison_mode = true; break; @@ -989,6 +995,9 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf /* increase chances of successful BPF object loading */ fixup_obj(obj, prog, base_filename); + if (env.force_checkpoints) + bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_STATE_FREQ); + err = bpf_object__load(obj); env.progs_processed++; diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 987cf0db5ebc..613321eb84c1 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -27,6 +27,7 @@ #include <sys/mman.h> #include <net/if.h> #include <poll.h> +#include <time.h> #include "xdp_metadata.h" @@ -134,18 +135,52 @@ static void refill_rx(struct xsk *xsk, __u64 addr) } } -static void verify_xdp_metadata(void *data) +#define NANOSEC_PER_SEC 1000000000 /* 10^9 */ +static __u64 gettime(clockid_t clock_id) +{ + struct timespec t; + int res; + + /* See man clock_gettime(2) for type of clock_id's */ + res = clock_gettime(clock_id, &t); + + if (res < 0) + error(res, errno, "Error with clock_gettime()"); + + return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec; +} + +static void verify_xdp_metadata(void *data, clockid_t clock_id) { struct xdp_meta *meta; meta = data - sizeof(*meta); - printf("rx_timestamp: %llu\n", meta->rx_timestamp); if (meta->rx_hash_err < 0) printf("No rx_hash err=%d\n", meta->rx_hash_err); else printf("rx_hash: 0x%X with RSS type:0x%X\n", meta->rx_hash, meta->rx_hash_type); + + printf("rx_timestamp: %llu (sec:%0.4f)\n", meta->rx_timestamp, + (double)meta->rx_timestamp / NANOSEC_PER_SEC); + if (meta->rx_timestamp) { + __u64 usr_clock = gettime(clock_id); + __u64 xdp_clock = meta->xdp_timestamp; + __s64 delta_X = xdp_clock - meta->rx_timestamp; + __s64 delta_X2U = usr_clock - xdp_clock; + + printf("XDP RX-time: %llu (sec:%0.4f) delta sec:%0.4f (%0.3f usec)\n", + xdp_clock, (double)xdp_clock / NANOSEC_PER_SEC, + (double)delta_X / NANOSEC_PER_SEC, + (double)delta_X / 1000); + + printf("AF_XDP time: %llu (sec:%0.4f) delta sec:%0.4f (%0.3f usec)\n", + usr_clock, (double)usr_clock / NANOSEC_PER_SEC, + (double)delta_X2U / NANOSEC_PER_SEC, + (double)delta_X2U / 1000); + } + } static void verify_skb_metadata(int fd) @@ -193,7 +228,7 @@ static void verify_skb_metadata(int fd) printf("skb hwtstamp is not found!\n"); } -static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd) +static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t clock_id) { const struct xdp_desc *rx_desc; struct pollfd fds[rxq + 1]; @@ -243,7 +278,8 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd) addr = xsk_umem__add_offset_to_addr(rx_desc->addr); printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx\n", xsk, idx, rx_desc->addr, addr, comp_addr); - verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr)); + verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr), + clock_id); xsk_ring_cons__release(&xsk->rx, 1); refill_rx(xsk, comp_addr); } @@ -370,6 +406,7 @@ static void timestamping_enable(int fd, int val) int main(int argc, char *argv[]) { + clockid_t clock_id = CLOCK_TAI; int server_fd = -1; int ret; int i; @@ -443,7 +480,7 @@ int main(int argc, char *argv[]) error(1, -ret, "bpf_xdp_attach"); signal(SIGINT, handle_signal); - ret = verify_metadata(rx_xsk, rxq, server_fd); + ret = verify_metadata(rx_xsk, rxq, server_fd, clock_id); close(server_fd); cleanup(); if (ret) diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h index 0c4624dc6f2f..938a729bd307 100644 --- a/tools/testing/selftests/bpf/xdp_metadata.h +++ b/tools/testing/selftests/bpf/xdp_metadata.h @@ -11,6 +11,7 @@ struct xdp_meta { __u64 rx_timestamp; + __u64 xdp_timestamp; __u32 rx_hash; union { __u32 rx_hash_type; diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h index 04ed8b544712..8da8d557768b 100644 --- a/tools/testing/selftests/bpf/xsk.h +++ b/tools/testing/selftests/bpf/xsk.h @@ -134,6 +134,11 @@ static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, __u32 nb) __atomic_store_n(prod->producer, *prod->producer + nb, __ATOMIC_RELEASE); } +static inline void xsk_ring_prod__cancel(struct xsk_ring_prod *prod, __u32 nb) +{ + prod->cached_prod -= nb; +} + static inline __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __u32 *idx) { __u32 entries = xsk_cons_nb_avail(cons, nb); diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c index f144d0604ddf..218d7f694e5c 100644 --- a/tools/testing/selftests/bpf/xskxceiver.c +++ b/tools/testing/selftests/bpf/xskxceiver.c @@ -76,16 +76,13 @@ #include <asm/barrier.h> #include <linux/if_link.h> #include <linux/if_ether.h> -#include <linux/ip.h> #include <linux/mman.h> -#include <linux/udp.h> #include <arpa/inet.h> #include <net/if.h> #include <locale.h> #include <poll.h> #include <pthread.h> #include <signal.h> -#include <stdbool.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -94,10 +91,8 @@ #include <sys/socket.h> #include <sys/time.h> #include <sys/types.h> -#include <sys/queue.h> #include <time.h> #include <unistd.h> -#include <stdatomic.h> #include "xsk_xdp_progs.skel.h" #include "xsk.h" @@ -109,10 +104,6 @@ static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62"; static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61"; -static const char *IP1 = "192.168.100.162"; -static const char *IP2 = "192.168.100.161"; -static const u16 UDP_PORT1 = 2020; -static const u16 UDP_PORT2 = 2121; static void __exit_with_error(int error, const char *file, const char *func, int line) { @@ -147,112 +138,25 @@ static void report_failure(struct test_spec *test) test->fail = true; } -static void memset32_htonl(void *dest, u32 val, u32 size) -{ - u32 *ptr = (u32 *)dest; - int i; - - val = htonl(val); - - for (i = 0; i < (size & (~0x3)); i += 4) - ptr[i >> 2] = val; -} - -/* - * Fold a partial checksum - * This function code has been taken from - * Linux kernel include/asm-generic/checksum.h - */ -static __u16 csum_fold(__u32 csum) -{ - u32 sum = (__force u32)csum; - - sum = (sum & 0xffff) + (sum >> 16); - sum = (sum & 0xffff) + (sum >> 16); - return (__force __u16)~sum; -} - -/* - * This function code has been taken from - * Linux kernel lib/checksum.c - */ -static u32 from64to32(u64 x) -{ - /* add up 32-bit and 32-bit for 32+c bit */ - x = (x & 0xffffffff) + (x >> 32); - /* add up carry.. */ - x = (x & 0xffffffff) + (x >> 32); - return (u32)x; -} - -/* - * This function code has been taken from - * Linux kernel lib/checksum.c - */ -static __u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum) -{ - unsigned long long s = (__force u32)sum; - - s += (__force u32)saddr; - s += (__force u32)daddr; -#ifdef __BIG_ENDIAN__ - s += proto + len; -#else - s += (proto + len) << 8; -#endif - return (__force __u32)from64to32(s); -} - -/* - * This function has been taken from - * Linux kernel include/asm-generic/checksum.h +/* The payload is a word consisting of a packet sequence number in the upper + * 16-bits and a intra packet data sequence number in the lower 16 bits. So the 3rd packet's + * 5th word of data will contain the number (2<<16) | 4 as they are numbered from 0. */ -static __u16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum) -{ - return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum)); -} - -static u16 udp_csum(u32 saddr, u32 daddr, u32 len, u8 proto, u16 *udp_pkt) +static void write_payload(void *dest, u32 pkt_nb, u32 start, u32 size) { - u32 csum = 0; - u32 cnt = 0; - - /* udp hdr and data */ - for (; cnt < len; cnt += 2) - csum += udp_pkt[cnt >> 1]; + u32 *ptr = (u32 *)dest, i; - return csum_tcpudp_magic(saddr, daddr, len, proto, csum); + start /= sizeof(*ptr); + size /= sizeof(*ptr); + for (i = 0; i < size; i++) + ptr[i] = htonl(pkt_nb << 16 | (i + start)); } static void gen_eth_hdr(struct ifobject *ifobject, struct ethhdr *eth_hdr) { memcpy(eth_hdr->h_dest, ifobject->dst_mac, ETH_ALEN); memcpy(eth_hdr->h_source, ifobject->src_mac, ETH_ALEN); - eth_hdr->h_proto = htons(ETH_P_IP); -} - -static void gen_ip_hdr(struct ifobject *ifobject, struct iphdr *ip_hdr) -{ - ip_hdr->version = IP_PKT_VER; - ip_hdr->ihl = 0x5; - ip_hdr->tos = IP_PKT_TOS; - ip_hdr->tot_len = htons(IP_PKT_SIZE); - ip_hdr->id = 0; - ip_hdr->frag_off = 0; - ip_hdr->ttl = IPDEFTTL; - ip_hdr->protocol = IPPROTO_UDP; - ip_hdr->saddr = ifobject->src_ip; - ip_hdr->daddr = ifobject->dst_ip; - ip_hdr->check = 0; -} - -static void gen_udp_hdr(u32 payload, void *pkt, struct ifobject *ifobject, - struct udphdr *udp_hdr) -{ - udp_hdr->source = htons(ifobject->src_port); - udp_hdr->dest = htons(ifobject->dst_port); - udp_hdr->len = htons(UDP_PKT_SIZE); - memset32_htonl(pkt + PKT_HDR_SIZE, payload, UDP_PKT_DATA_SIZE); + eth_hdr->h_proto = htons(ETH_P_LOOPBACK); } static bool is_umem_valid(struct ifobject *ifobj) @@ -260,19 +164,18 @@ static bool is_umem_valid(struct ifobject *ifobj) return !!ifobj->umem->umem; } -static void gen_udp_csum(struct udphdr *udp_hdr, struct iphdr *ip_hdr) +static u32 mode_to_xdp_flags(enum test_mode mode) { - udp_hdr->check = 0; - udp_hdr->check = - udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE, IPPROTO_UDP, (u16 *)udp_hdr); + return (mode == TEST_MODE_SKB) ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE; } -static u32 mode_to_xdp_flags(enum test_mode mode) +static u64 umem_size(struct xsk_umem_info *umem) { - return (mode == TEST_MODE_SKB) ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE; + return umem->num_frames * umem->frame_size; } -static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size) +static int xsk_configure_umem(struct ifobject *ifobj, struct xsk_umem_info *umem, void *buffer, + u64 size) { struct xsk_umem_config cfg = { .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, @@ -292,9 +195,31 @@ static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size return ret; umem->buffer = buffer; + if (ifobj->shared_umem && ifobj->rx_on) { + umem->base_addr = umem_size(umem); + umem->next_buffer = umem_size(umem); + } + return 0; } +static u64 umem_alloc_buffer(struct xsk_umem_info *umem) +{ + u64 addr; + + addr = umem->next_buffer; + umem->next_buffer += umem->frame_size; + if (umem->next_buffer >= umem->base_addr + umem_size(umem)) + umem->next_buffer = umem->base_addr; + + return addr; +} + +static void umem_reset_alloc(struct xsk_umem_info *umem) +{ + umem->next_buffer = 0; +} + static void enable_busy_poll(struct xsk_socket_info *xsk) { int sock_opt; @@ -354,7 +279,7 @@ static bool ifobj_zc_avail(struct ifobject *ifobject) exit_with_error(ENOMEM); } umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; - ret = xsk_configure_umem(umem, bufs, umem_sz); + ret = xsk_configure_umem(ifobject, umem, bufs, umem_sz); if (ret) exit_with_error(-ret); @@ -380,7 +305,6 @@ out: static struct option long_options[] = { {"interface", required_argument, 0, 'i'}, {"busy-poll", no_argument, 0, 'b'}, - {"dump-pkts", no_argument, 0, 'D'}, {"verbose", no_argument, 0, 'v'}, {0, 0, 0, 0} }; @@ -391,7 +315,6 @@ static void usage(const char *prog) " Usage: %s [OPTIONS]\n" " Options:\n" " -i, --interface Use interface\n" - " -D, --dump-pkts Dump packets L2 - L5\n" " -v, --verbose Verbose output\n" " -b, --busy-poll Enable busy poll\n"; @@ -415,7 +338,7 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj opterr = 0; for (;;) { - c = getopt_long(argc, argv, "i:Dvb", long_options, &option_index); + c = getopt_long(argc, argv, "i:vb", long_options, &option_index); if (c == -1) break; @@ -437,9 +360,6 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj interface_nb++; break; - case 'D': - opt_pkt_dump = true; - break; case 'v': opt_verbose = true; break; @@ -482,9 +402,6 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, memset(ifobj->umem, 0, sizeof(*ifobj->umem)); ifobj->umem->num_frames = DEFAULT_UMEM_BUFFERS; ifobj->umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; - if (ifobj->shared_umem && ifobj->rx_on) - ifobj->umem->base_addr = DEFAULT_UMEM_BUFFERS * - XSK_UMEM__DEFAULT_FRAME_SIZE; for (j = 0; j < MAX_SOCKETS; j++) { memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j])); @@ -554,24 +471,24 @@ static void test_spec_set_xdp_prog(struct test_spec *test, struct bpf_program *x static void pkt_stream_reset(struct pkt_stream *pkt_stream) { if (pkt_stream) - pkt_stream->rx_pkt_nb = 0; + pkt_stream->current_pkt_nb = 0; } -static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb) +static struct pkt *pkt_stream_get_next_tx_pkt(struct pkt_stream *pkt_stream) { - if (pkt_nb >= pkt_stream->nb_pkts) + if (pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts) return NULL; - return &pkt_stream->pkts[pkt_nb]; + return &pkt_stream->pkts[pkt_stream->current_pkt_nb++]; } static struct pkt *pkt_stream_get_next_rx_pkt(struct pkt_stream *pkt_stream, u32 *pkts_sent) { - while (pkt_stream->rx_pkt_nb < pkt_stream->nb_pkts) { + while (pkt_stream->current_pkt_nb < pkt_stream->nb_pkts) { (*pkts_sent)++; - if (pkt_stream->pkts[pkt_stream->rx_pkt_nb].valid) - return &pkt_stream->pkts[pkt_stream->rx_pkt_nb++]; - pkt_stream->rx_pkt_nb++; + if (pkt_stream->pkts[pkt_stream->current_pkt_nb].valid) + return &pkt_stream->pkts[pkt_stream->current_pkt_nb++]; + pkt_stream->current_pkt_nb++; } return NULL; } @@ -616,9 +533,21 @@ static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts) return pkt_stream; } -static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr, u32 len) +static u32 ceil_u32(u32 a, u32 b) +{ + return (a + b - 1) / b; +} + +static u32 pkt_nb_frags(u32 frame_size, struct pkt *pkt) +{ + if (!pkt || !pkt->valid) + return 1; + return ceil_u32(pkt->len, frame_size); +} + +static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, int offset, u32 len) { - pkt->addr = addr + umem->base_addr; + pkt->offset = offset; pkt->len = len; if (len > umem->frame_size - XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 2 - umem->frame_headroom) pkt->valid = false; @@ -626,6 +555,11 @@ static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr, u32 l pkt->valid = true; } +static u32 pkt_get_buffer_len(struct xsk_umem_info *umem, u32 len) +{ + return ceil_u32(len, umem->frame_size) * umem->frame_size; +} + static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb_pkts, u32 pkt_len) { struct pkt_stream *pkt_stream; @@ -635,10 +569,13 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb if (!pkt_stream) exit_with_error(ENOMEM); + pkt_stream->nb_pkts = nb_pkts; + pkt_stream->max_pkt_len = pkt_len; for (i = 0; i < nb_pkts; i++) { - pkt_set(umem, &pkt_stream->pkts[i], (i % umem->num_frames) * umem->frame_size, - pkt_len); - pkt_stream->pkts[i].payload = i; + struct pkt *pkt = &pkt_stream->pkts[i]; + + pkt_set(umem, pkt, 0, pkt_len); + pkt->pkt_nb = i; } return pkt_stream; @@ -669,8 +606,7 @@ static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len, pkt_stream = pkt_stream_clone(umem, ifobj->pkt_stream); for (i = 1; i < ifobj->pkt_stream->nb_pkts; i += 2) - pkt_set(umem, &pkt_stream->pkts[i], - (i % umem->num_frames) * umem->frame_size + offset, pkt_len); + pkt_set(umem, &pkt_stream->pkts[i], offset, pkt_len); ifobj->pkt_stream = pkt_stream; } @@ -694,30 +630,31 @@ static void pkt_stream_receive_half(struct test_spec *test) pkt_stream->pkts[i].valid = false; } -static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb) +static u64 pkt_get_addr(struct pkt *pkt, struct xsk_umem_info *umem) { - struct pkt *pkt = pkt_stream_get_pkt(ifobject->pkt_stream, pkt_nb); - struct udphdr *udp_hdr; - struct ethhdr *eth_hdr; - struct iphdr *ip_hdr; - void *data; + if (!pkt->valid) + return pkt->offset; + return pkt->offset + umem_alloc_buffer(umem); +} - if (!pkt) - return NULL; - if (!pkt->valid || pkt->len < MIN_PKT_SIZE) - return pkt; +static void pkt_generate(struct ifobject *ifobject, u64 addr, u32 len, u32 pkt_nb, + u32 bytes_written) +{ + void *data = xsk_umem__get_data(ifobject->umem->buffer, addr); - data = xsk_umem__get_data(ifobject->umem->buffer, pkt->addr); - udp_hdr = (struct udphdr *)(data + sizeof(struct ethhdr) + sizeof(struct iphdr)); - ip_hdr = (struct iphdr *)(data + sizeof(struct ethhdr)); - eth_hdr = (struct ethhdr *)data; + if (len < MIN_PKT_SIZE) + return; - gen_udp_hdr(pkt_nb, data, ifobject, udp_hdr); - gen_ip_hdr(ifobject, ip_hdr); - gen_udp_csum(udp_hdr, ip_hdr); - gen_eth_hdr(ifobject, eth_hdr); + if (!bytes_written) { + gen_eth_hdr(ifobject, data); - return pkt; + len -= PKT_HDR_SIZE; + data += PKT_HDR_SIZE; + } else { + bytes_written -= PKT_HDR_SIZE; + } + + write_payload(data, pkt_nb, bytes_written, len); } static void __pkt_stream_generate_custom(struct ifobject *ifobj, @@ -731,10 +668,14 @@ static void __pkt_stream_generate_custom(struct ifobject *ifobj, exit_with_error(ENOMEM); for (i = 0; i < nb_pkts; i++) { - pkt_stream->pkts[i].addr = pkts[i].addr + ifobj->umem->base_addr; - pkt_stream->pkts[i].len = pkts[i].len; - pkt_stream->pkts[i].payload = i; - pkt_stream->pkts[i].valid = pkts[i].valid; + struct pkt *pkt = &pkt_stream->pkts[i]; + + pkt->offset = pkts[i].offset; + pkt->len = pkts[i].len; + pkt->pkt_nb = i; + pkt->valid = pkts[i].valid; + if (pkt->len > pkt_stream->max_pkt_len) + pkt_stream->max_pkt_len = pkt->len; } ifobj->pkt_stream = pkt_stream; @@ -746,53 +687,62 @@ static void pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, __pkt_stream_generate_custom(test->ifobj_rx, pkts, nb_pkts); } -static void pkt_dump(void *pkt, u32 len) -{ - char s[INET_ADDRSTRLEN]; - struct ethhdr *ethhdr; - struct udphdr *udphdr; - struct iphdr *iphdr; - u32 payload, i; - - ethhdr = pkt; - iphdr = pkt + sizeof(*ethhdr); - udphdr = pkt + sizeof(*ethhdr) + sizeof(*iphdr); - - /*extract L2 frame */ - fprintf(stdout, "DEBUG>> L2: dst mac: "); - for (i = 0; i < ETH_ALEN; i++) - fprintf(stdout, "%02X", ethhdr->h_dest[i]); - - fprintf(stdout, "\nDEBUG>> L2: src mac: "); - for (i = 0; i < ETH_ALEN; i++) - fprintf(stdout, "%02X", ethhdr->h_source[i]); - - /*extract L3 frame */ - fprintf(stdout, "\nDEBUG>> L3: ip_hdr->ihl: %02X\n", iphdr->ihl); - fprintf(stdout, "DEBUG>> L3: ip_hdr->saddr: %s\n", - inet_ntop(AF_INET, &iphdr->saddr, s, sizeof(s))); - fprintf(stdout, "DEBUG>> L3: ip_hdr->daddr: %s\n", - inet_ntop(AF_INET, &iphdr->daddr, s, sizeof(s))); - /*extract L4 frame */ - fprintf(stdout, "DEBUG>> L4: udp_hdr->src: %d\n", ntohs(udphdr->source)); - fprintf(stdout, "DEBUG>> L4: udp_hdr->dst: %d\n", ntohs(udphdr->dest)); - /*extract L5 frame */ - payload = ntohl(*((u32 *)(pkt + PKT_HDR_SIZE))); +static void pkt_print_data(u32 *data, u32 cnt) +{ + u32 i; + + for (i = 0; i < cnt; i++) { + u32 seqnum, pkt_nb; - fprintf(stdout, "DEBUG>> L5: payload: %d\n", payload); - fprintf(stdout, "---------------------------------------\n"); + seqnum = ntohl(*data) & 0xffff; + pkt_nb = ntohl(*data) >> 16; + fprintf(stdout, "%u:%u ", pkt_nb, seqnum); + data++; + } } -static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, u64 addr, - u64 pkt_stream_addr) +static void pkt_dump(void *pkt, u32 len, bool eth_header) +{ + struct ethhdr *ethhdr = pkt; + u32 i, *data; + + if (eth_header) { + /*extract L2 frame */ + fprintf(stdout, "DEBUG>> L2: dst mac: "); + for (i = 0; i < ETH_ALEN; i++) + fprintf(stdout, "%02X", ethhdr->h_dest[i]); + + fprintf(stdout, "\nDEBUG>> L2: src mac: "); + for (i = 0; i < ETH_ALEN; i++) + fprintf(stdout, "%02X", ethhdr->h_source[i]); + + data = pkt + PKT_HDR_SIZE; + } else { + data = pkt; + } + + /*extract L5 frame */ + fprintf(stdout, "\nDEBUG>> L5: seqnum: "); + pkt_print_data(data, PKT_DUMP_NB_TO_PRINT); + fprintf(stdout, "...."); + if (len > PKT_DUMP_NB_TO_PRINT * sizeof(u32)) { + fprintf(stdout, "\n.... "); + pkt_print_data(data + len / sizeof(u32) - PKT_DUMP_NB_TO_PRINT, + PKT_DUMP_NB_TO_PRINT); + } + fprintf(stdout, "\n---------------------------------------\n"); +} + +static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr) { u32 headroom = umem->unaligned_mode ? 0 : umem->frame_headroom; - u32 offset = addr % umem->frame_size, expected_offset = 0; + u32 offset = addr % umem->frame_size, expected_offset; + int pkt_offset = pkt->valid ? pkt->offset : 0; - if (!pkt_stream->use_addr_for_fill) - pkt_stream_addr = 0; + if (!umem->unaligned_mode) + pkt_offset = 0; - expected_offset += (pkt_stream_addr + headroom + XDP_PACKET_HEADROOM) % umem->frame_size; + expected_offset = (pkt_offset + headroom + XDP_PACKET_HEADROOM) % umem->frame_size; if (offset == expected_offset) return true; @@ -806,9 +756,9 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr) void *data = xsk_umem__get_data(buffer, addr); struct xdp_info *meta = data - sizeof(struct xdp_info); - if (meta->count != pkt->payload) { + if (meta->count != pkt->pkt_nb) { ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%d]\n", - __func__, pkt->payload, meta->count); + __func__, pkt->pkt_nb, meta->count); return false; } @@ -818,11 +768,11 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr) static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) { void *data = xsk_umem__get_data(buffer, addr); - struct iphdr *iphdr = (struct iphdr *)(data + sizeof(struct ethhdr)); + u32 seqnum, pkt_data; if (!pkt) { ksft_print_msg("[%s] too many packets received\n", __func__); - return false; + goto error; } if (len < MIN_PKT_SIZE || pkt->len < MIN_PKT_SIZE) { @@ -833,28 +783,23 @@ static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) if (pkt->len != len) { ksft_print_msg("[%s] expected length [%d], got length [%d]\n", __func__, pkt->len, len); - return false; + goto error; } - if (iphdr->version == IP_PKT_VER && iphdr->tos == IP_PKT_TOS) { - u32 seqnum = ntohl(*((u32 *)(data + PKT_HDR_SIZE))); - - if (opt_pkt_dump) - pkt_dump(data, PKT_SIZE); + pkt_data = ntohl(*((u32 *)(data + PKT_HDR_SIZE))); + seqnum = pkt_data >> 16; - if (pkt->payload != seqnum) { - ksft_print_msg("[%s] expected seqnum [%d], got seqnum [%d]\n", - __func__, pkt->payload, seqnum); - return false; - } - } else { - ksft_print_msg("Invalid frame received: "); - ksft_print_msg("[IP_PKT_VER: %02X], [IP_PKT_TOS: %02X]\n", iphdr->version, - iphdr->tos); - return false; + if (pkt->pkt_nb != seqnum) { + ksft_print_msg("[%s] expected seqnum [%d], got seqnum [%d]\n", + __func__, pkt->pkt_nb, seqnum); + goto error; } return true; + +error: + pkt_dump(data, len, true); + return false; } static void kick_tx(struct xsk_socket_info *xsk) @@ -976,7 +921,7 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) addr = xsk_umem__add_offset_to_addr(addr); if (!is_pkt_valid(pkt, umem->buffer, addr, desc->len) || - !is_offset_correct(umem, pkt_stream, addr, pkt->addr) || + !is_offset_correct(umem, pkt, addr) || (ifobj->use_metadata && !is_metadata_correct(pkt, umem->buffer, addr))) return TEST_FAILURE; @@ -992,8 +937,6 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) pthread_mutex_lock(&pacing_mutex); pkts_in_flight -= pkts_sent; - if (pkts_in_flight < umem->num_frames) - pthread_cond_signal(&pacing_cond); pthread_mutex_unlock(&pacing_mutex); pkts_sent = 0; } @@ -1001,14 +944,21 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) return TEST_PASS; } -static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb, struct pollfd *fds, - bool timeout) +static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeout) { struct xsk_socket_info *xsk = ifobject->xsk; + struct xsk_umem_info *umem = ifobject->umem; + u32 i, idx = 0, valid_pkts = 0, buffer_len; bool use_poll = ifobject->use_poll; - u32 i, idx = 0, valid_pkts = 0; int ret; + buffer_len = pkt_get_buffer_len(umem, ifobject->pkt_stream->max_pkt_len); + /* pkts_in_flight might be negative if many invalid packets are sent */ + if (pkts_in_flight >= (int)((umem_size(umem) - BATCH_SIZE * buffer_len) / buffer_len)) { + kick_tx(xsk); + return TEST_CONTINUE; + } + while (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) < BATCH_SIZE) { if (use_poll) { ret = poll(fds, 1, POLL_TMOUT); @@ -1034,25 +984,21 @@ static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb, struct pollfd *fd for (i = 0; i < BATCH_SIZE; i++) { struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i); - struct pkt *pkt = pkt_generate(ifobject, *pkt_nb); + struct pkt *pkt = pkt_stream_get_next_tx_pkt(ifobject->pkt_stream); if (!pkt) break; - tx_desc->addr = pkt->addr; + tx_desc->addr = pkt_get_addr(pkt, umem); tx_desc->len = pkt->len; - (*pkt_nb)++; - if (pkt->valid) + if (pkt->valid) { valid_pkts++; + pkt_generate(ifobject, tx_desc->addr, tx_desc->len, pkt->pkt_nb, 0); + } } pthread_mutex_lock(&pacing_mutex); pkts_in_flight += valid_pkts; - /* pkts_in_flight might be negative if many invalid packets are sent */ - if (pkts_in_flight >= (int)(ifobject->umem->num_frames - BATCH_SIZE)) { - kick_tx(xsk); - pthread_cond_wait(&pacing_cond, &pacing_mutex); - } pthread_mutex_unlock(&pacing_mutex); xsk_ring_prod__submit(&xsk->tx, i); @@ -1088,18 +1034,21 @@ static void wait_for_tx_completion(struct xsk_socket_info *xsk) static int send_pkts(struct test_spec *test, struct ifobject *ifobject) { + struct pkt_stream *pkt_stream = ifobject->pkt_stream; bool timeout = !is_umem_valid(test->ifobj_rx); struct pollfd fds = { }; - u32 pkt_cnt = 0, ret; + u32 ret; fds.fd = xsk_socket__fd(ifobject->xsk->xsk); fds.events = POLLOUT; - while (pkt_cnt < ifobject->pkt_stream->nb_pkts) { - ret = __send_pkts(ifobject, &pkt_cnt, &fds, timeout); + while (pkt_stream->current_pkt_nb < pkt_stream->nb_pkts) { + ret = __send_pkts(ifobject, &fds, timeout); + if (ret == TEST_CONTINUE && !test->fail) + continue; if ((ret || test->fail) && !timeout) return TEST_FAILURE; - else if (ret == TEST_PASS && timeout) + if (ret == TEST_PASS && timeout) return ret; } @@ -1249,11 +1198,14 @@ static void thread_common_ops_tx(struct test_spec *test, struct ifobject *ifobje ifobject->xsk = &ifobject->xsk_arr[0]; ifobject->xskmap = test->ifobj_rx->xskmap; memcpy(ifobject->umem, test->ifobj_rx->umem, sizeof(struct xsk_umem_info)); + ifobject->umem->base_addr = 0; } -static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream) +static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, + bool fill_up) { - u32 idx = 0, i, buffers_to_fill; + u32 rx_frame_size = umem->frame_size - XDP_PACKET_HEADROOM; + u32 idx = 0, filled = 0, buffers_to_fill, nb_pkts; int ret; if (umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS) @@ -1264,22 +1216,33 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream ret = xsk_ring_prod__reserve(&umem->fq, buffers_to_fill, &idx); if (ret != buffers_to_fill) exit_with_error(ENOSPC); - for (i = 0; i < buffers_to_fill; i++) { - u64 addr; - if (pkt_stream->use_addr_for_fill) { - struct pkt *pkt = pkt_stream_get_pkt(pkt_stream, i); + while (filled < buffers_to_fill) { + struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &nb_pkts); + u64 addr; + u32 i; + + for (i = 0; i < pkt_nb_frags(rx_frame_size, pkt); i++) { + if (!pkt) { + if (!fill_up) + break; + addr = filled * umem->frame_size + umem->base_addr; + } else if (pkt->offset >= 0) { + addr = pkt->offset % umem->frame_size + umem_alloc_buffer(umem); + } else { + addr = pkt->offset + umem_alloc_buffer(umem); + } - if (!pkt) + *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; + if (++filled >= buffers_to_fill) break; - addr = pkt->addr; - } else { - addr = i * umem->frame_size; } - - *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; } - xsk_ring_prod__submit(&umem->fq, i); + xsk_ring_prod__submit(&umem->fq, filled); + xsk_ring_prod__cancel(&umem->fq, buffers_to_fill - filled); + + pkt_stream_reset(pkt_stream); + umem_reset_alloc(umem); } static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) @@ -1300,12 +1263,10 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) if (bufs == MAP_FAILED) exit_with_error(errno); - ret = xsk_configure_umem(ifobject->umem, bufs, umem_sz); + ret = xsk_configure_umem(ifobject, ifobject->umem, bufs, umem_sz); if (ret) exit_with_error(-ret); - xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream); - xsk_configure_socket(test, ifobject, ifobject->umem, false); ifobject->xsk = &ifobject->xsk_arr[0]; @@ -1313,6 +1274,8 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) if (!ifobject->rx_on) return; + xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream, ifobject->use_fill_ring); + ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk); if (ret) exit_with_error(errno); @@ -1370,12 +1333,8 @@ static void *worker_testapp_validate_rx(void *arg) if (!err && ifobject->validation_func) err = ifobject->validation_func(ifobject); - if (err) { + if (err) report_failure(test); - pthread_mutex_lock(&pacing_mutex); - pthread_cond_signal(&pacing_cond); - pthread_mutex_unlock(&pacing_mutex); - } pthread_exit(NULL); } @@ -1402,11 +1361,20 @@ static void handler(int signum) pthread_exit(NULL); } -static bool xdp_prog_changed(struct test_spec *test, struct ifobject *ifobj) +static bool xdp_prog_changed_rx(struct test_spec *test) { + struct ifobject *ifobj = test->ifobj_rx; + return ifobj->xdp_prog != test->xdp_prog_rx || ifobj->mode != test->mode; } +static bool xdp_prog_changed_tx(struct test_spec *test) +{ + struct ifobject *ifobj = test->ifobj_tx; + + return ifobj->xdp_prog != test->xdp_prog_tx || ifobj->mode != test->mode; +} + static void xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_prog, struct bpf_map *xskmap, enum test_mode mode) { @@ -1433,13 +1401,13 @@ static void xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_pro static void xsk_attach_xdp_progs(struct test_spec *test, struct ifobject *ifobj_rx, struct ifobject *ifobj_tx) { - if (xdp_prog_changed(test, ifobj_rx)) + if (xdp_prog_changed_rx(test)) xsk_reattach_xdp(ifobj_rx, test->xdp_prog_rx, test->xskmap_rx, test->mode); if (!ifobj_tx || ifobj_tx->shared_umem) return; - if (xdp_prog_changed(test, ifobj_tx)) + if (xdp_prog_changed_tx(test)) xsk_reattach_xdp(ifobj_tx, test->xdp_prog_tx, test->xskmap_tx, test->mode); } @@ -1448,9 +1416,11 @@ static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *i { pthread_t t0, t1; - if (ifobj2) + if (ifobj2) { if (pthread_barrier_init(&barr, NULL, 2)) exit_with_error(errno); + pkt_stream_reset(ifobj2->pkt_stream); + } test->current_step++; pkt_stream_reset(ifobj1->pkt_stream); @@ -1493,6 +1463,12 @@ static int testapp_validate_traffic(struct test_spec *test) struct ifobject *ifobj_rx = test->ifobj_rx; struct ifobject *ifobj_tx = test->ifobj_tx; + if ((ifobj_rx->umem->unaligned_mode && !ifobj_rx->unaligned_supp) || + (ifobj_tx->umem->unaligned_mode && !ifobj_tx->unaligned_supp)) { + ksft_test_result_skip("No huge pages present.\n"); + return TEST_SKIP; + } + xsk_attach_xdp_progs(test, ifobj_rx, ifobj_tx); return __testapp_validate_traffic(test, ifobj_rx, ifobj_tx); } @@ -1502,16 +1478,18 @@ static int testapp_validate_traffic_single_thread(struct test_spec *test, struct return __testapp_validate_traffic(test, ifobj, NULL); } -static void testapp_teardown(struct test_spec *test) +static int testapp_teardown(struct test_spec *test) { int i; test_spec_set_name(test, "TEARDOWN"); for (i = 0; i < MAX_TEARDOWN_ITER; i++) { if (testapp_validate_traffic(test)) - return; + return TEST_FAILURE; test_spec_reset(test); } + + return TEST_PASS; } static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2) @@ -1526,20 +1504,23 @@ static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2) *ifobj2 = tmp_ifobj; } -static void testapp_bidi(struct test_spec *test) +static int testapp_bidi(struct test_spec *test) { + int res; + test_spec_set_name(test, "BIDIRECTIONAL"); test->ifobj_tx->rx_on = true; test->ifobj_rx->tx_on = true; test->total_steps = 2; if (testapp_validate_traffic(test)) - return; + return TEST_FAILURE; print_verbose("Switching Tx/Rx vectors\n"); swap_directions(&test->ifobj_rx, &test->ifobj_tx); - __testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx); + res = __testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx); swap_directions(&test->ifobj_rx, &test->ifobj_tx); + return res; } static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx) @@ -1556,160 +1537,139 @@ static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj exit_with_error(errno); } -static void testapp_bpf_res(struct test_spec *test) +static int testapp_bpf_res(struct test_spec *test) { test_spec_set_name(test, "BPF_RES"); test->total_steps = 2; test->nb_sockets = 2; if (testapp_validate_traffic(test)) - return; + return TEST_FAILURE; swap_xsk_resources(test->ifobj_tx, test->ifobj_rx); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_headroom(struct test_spec *test) +static int testapp_headroom(struct test_spec *test) { test_spec_set_name(test, "UMEM_HEADROOM"); test->ifobj_rx->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE; - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_stats_rx_dropped(struct test_spec *test) +static int testapp_stats_rx_dropped(struct test_spec *test) { test_spec_set_name(test, "STAT_RX_DROPPED"); + if (test->mode == TEST_MODE_ZC) { + ksft_test_result_skip("Can not run RX_DROPPED test for ZC mode\n"); + return TEST_SKIP; + } + pkt_stream_replace_half(test, MIN_PKT_SIZE * 4, 0); test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size - XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 3; pkt_stream_receive_half(test); test->ifobj_rx->validation_func = validate_rx_dropped; - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_stats_tx_invalid_descs(struct test_spec *test) +static int testapp_stats_tx_invalid_descs(struct test_spec *test) { test_spec_set_name(test, "STAT_TX_INVALID"); pkt_stream_replace_half(test, XSK_UMEM__INVALID_FRAME_SIZE, 0); test->ifobj_tx->validation_func = validate_tx_invalid_descs; - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_stats_rx_full(struct test_spec *test) +static int testapp_stats_rx_full(struct test_spec *test) { test_spec_set_name(test, "STAT_RX_FULL"); - pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, PKT_SIZE); + pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem, - DEFAULT_UMEM_BUFFERS, PKT_SIZE); - if (!test->ifobj_rx->pkt_stream) - exit_with_error(ENOMEM); + DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS; test->ifobj_rx->release_rx = false; test->ifobj_rx->validation_func = validate_rx_full; - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_stats_fill_empty(struct test_spec *test) +static int testapp_stats_fill_empty(struct test_spec *test) { test_spec_set_name(test, "STAT_RX_FILL_EMPTY"); - pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, PKT_SIZE); + pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem, - DEFAULT_UMEM_BUFFERS, PKT_SIZE); - if (!test->ifobj_rx->pkt_stream) - exit_with_error(ENOMEM); + DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); test->ifobj_rx->use_fill_ring = false; test->ifobj_rx->validation_func = validate_fill_empty; - testapp_validate_traffic(test); -} - -/* Simple test */ -static bool hugepages_present(struct ifobject *ifobject) -{ - size_t mmap_sz = 2 * ifobject->umem->num_frames * ifobject->umem->frame_size; - void *bufs; - - bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | MAP_HUGE_2MB, -1, 0); - if (bufs == MAP_FAILED) - return false; - - mmap_sz = ceil_u64(mmap_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE; - munmap(bufs, mmap_sz); - return true; + return testapp_validate_traffic(test); } -static bool testapp_unaligned(struct test_spec *test) +static int testapp_unaligned(struct test_spec *test) { - if (!hugepages_present(test->ifobj_tx)) { - ksft_test_result_skip("No 2M huge pages present.\n"); - return false; - } - test_spec_set_name(test, "UNALIGNED_MODE"); test->ifobj_tx->umem->unaligned_mode = true; test->ifobj_rx->umem->unaligned_mode = true; - /* Let half of the packets straddle a buffer boundrary */ - pkt_stream_replace_half(test, PKT_SIZE, -PKT_SIZE / 2); - test->ifobj_rx->pkt_stream->use_addr_for_fill = true; - testapp_validate_traffic(test); + /* Let half of the packets straddle a 4K buffer boundary */ + pkt_stream_replace_half(test, MIN_PKT_SIZE, -MIN_PKT_SIZE / 2); - return true; + return testapp_validate_traffic(test); } -static void testapp_single_pkt(struct test_spec *test) +static int testapp_single_pkt(struct test_spec *test) { - struct pkt pkts[] = {{0x1000, PKT_SIZE, 0, true}}; + struct pkt pkts[] = {{0, MIN_PKT_SIZE, 0, true}}; pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_invalid_desc(struct test_spec *test) +static int testapp_invalid_desc(struct test_spec *test) { - u64 umem_size = test->ifobj_tx->umem->num_frames * test->ifobj_tx->umem->frame_size; + struct xsk_umem_info *umem = test->ifobj_tx->umem; + u64 umem_size = umem->num_frames * umem->frame_size; struct pkt pkts[] = { /* Zero packet address allowed */ - {0, PKT_SIZE, 0, true}, + {0, MIN_PKT_SIZE, 0, true}, /* Allowed packet */ - {0x1000, PKT_SIZE, 0, true}, + {0, MIN_PKT_SIZE, 0, true}, /* Straddling the start of umem */ - {-2, PKT_SIZE, 0, false}, + {-2, MIN_PKT_SIZE, 0, false}, /* Packet too large */ - {0x2000, XSK_UMEM__INVALID_FRAME_SIZE, 0, false}, + {0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false}, /* Up to end of umem allowed */ - {umem_size - PKT_SIZE, PKT_SIZE, 0, true}, + {umem_size - MIN_PKT_SIZE - 2 * umem->frame_size, MIN_PKT_SIZE, 0, true}, /* After umem ends */ - {umem_size, PKT_SIZE, 0, false}, + {umem_size, MIN_PKT_SIZE, 0, false}, /* Straddle the end of umem */ - {umem_size - PKT_SIZE / 2, PKT_SIZE, 0, false}, - /* Straddle a page boundrary */ - {0x3000 - PKT_SIZE / 2, PKT_SIZE, 0, false}, - /* Straddle a 2K boundrary */ - {0x3800 - PKT_SIZE / 2, PKT_SIZE, 0, true}, + {umem_size - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false}, + /* Straddle a 4K boundary */ + {0x1000 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false}, + /* Straddle a 2K boundary */ + {0x800 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, true}, /* Valid packet for synch so that something is received */ - {0x4000, PKT_SIZE, 0, true}}; + {0, MIN_PKT_SIZE, 0, true}}; - if (test->ifobj_tx->umem->unaligned_mode) { - /* Crossing a page boundrary allowed */ + if (umem->unaligned_mode) { + /* Crossing a page boundary allowed */ pkts[7].valid = true; } - if (test->ifobj_tx->umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) { - /* Crossing a 2K frame size boundrary not allowed */ + if (umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) { + /* Crossing a 2K frame size boundary not allowed */ pkts[8].valid = false; } if (test->ifobj_tx->shared_umem) { - pkts[4].addr += umem_size; - pkts[5].addr += umem_size; - pkts[6].addr += umem_size; + pkts[4].offset += umem_size; + pkts[5].offset += umem_size; + pkts[6].offset += umem_size; } pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_xdp_drop(struct test_spec *test) +static int testapp_xdp_drop(struct test_spec *test) { struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; @@ -1719,10 +1679,10 @@ static void testapp_xdp_drop(struct test_spec *test) skel_rx->maps.xsk, skel_tx->maps.xsk); pkt_stream_receive_half(test); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_xdp_metadata_count(struct test_spec *test) +static int testapp_xdp_metadata_count(struct test_spec *test) { struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; @@ -1743,10 +1703,10 @@ static void testapp_xdp_metadata_count(struct test_spec *test) if (bpf_map_update_elem(bpf_map__fd(data_map), &key, &count, BPF_ANY)) exit_with_error(errno); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_poll_txq_tmout(struct test_spec *test) +static int testapp_poll_txq_tmout(struct test_spec *test) { test_spec_set_name(test, "POLL_TXQ_FULL"); @@ -1754,14 +1714,14 @@ static void testapp_poll_txq_tmout(struct test_spec *test) /* create invalid frame by set umem frame_size and pkt length equal to 2048 */ test->ifobj_tx->umem->frame_size = 2048; pkt_stream_replace(test, 2 * DEFAULT_PKT_CNT, 2048); - testapp_validate_traffic_single_thread(test, test->ifobj_tx); + return testapp_validate_traffic_single_thread(test, test->ifobj_tx); } -static void testapp_poll_rxq_tmout(struct test_spec *test) +static int testapp_poll_rxq_tmout(struct test_spec *test) { test_spec_set_name(test, "POLL_RXQ_EMPTY"); test->ifobj_rx->use_poll = true; - testapp_validate_traffic_single_thread(test, test->ifobj_rx); + return testapp_validate_traffic_single_thread(test, test->ifobj_rx); } static int xsk_load_xdp_programs(struct ifobject *ifobj) @@ -1778,25 +1738,30 @@ static void xsk_unload_xdp_programs(struct ifobject *ifobj) xsk_xdp_progs__destroy(ifobj->xdp_progs); } +/* Simple test */ +static bool hugepages_present(void) +{ + size_t mmap_sz = 2 * DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE; + void *bufs; + + bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, MAP_HUGE_2MB); + if (bufs == MAP_FAILED) + return false; + + mmap_sz = ceil_u64(mmap_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE; + munmap(bufs, mmap_sz); + return true; +} + static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac, - const char *dst_ip, const char *src_ip, const u16 dst_port, - const u16 src_port, thread_func_t func_ptr) + thread_func_t func_ptr) { - struct in_addr ip; int err; memcpy(ifobj->dst_mac, dst_mac, ETH_ALEN); memcpy(ifobj->src_mac, src_mac, ETH_ALEN); - inet_aton(dst_ip, &ip); - ifobj->dst_ip = ip.s_addr; - - inet_aton(src_ip, &ip); - ifobj->src_ip = ip.s_addr; - - ifobj->dst_port = dst_port; - ifobj->src_port = src_port; - ifobj->func_ptr = func_ptr; err = xsk_load_xdp_programs(ifobj); @@ -1804,94 +1769,87 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char * printf("Error loading XDP program\n"); exit_with_error(err); } + + if (hugepages_present()) + ifobj->unaligned_supp = true; } static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_type type) { + int ret = TEST_SKIP; + switch (type) { case TEST_TYPE_STATS_RX_DROPPED: - if (mode == TEST_MODE_ZC) { - ksft_test_result_skip("Can not run RX_DROPPED test for ZC mode\n"); - return; - } - testapp_stats_rx_dropped(test); + ret = testapp_stats_rx_dropped(test); break; case TEST_TYPE_STATS_TX_INVALID_DESCS: - testapp_stats_tx_invalid_descs(test); + ret = testapp_stats_tx_invalid_descs(test); break; case TEST_TYPE_STATS_RX_FULL: - testapp_stats_rx_full(test); + ret = testapp_stats_rx_full(test); break; case TEST_TYPE_STATS_FILL_EMPTY: - testapp_stats_fill_empty(test); + ret = testapp_stats_fill_empty(test); break; case TEST_TYPE_TEARDOWN: - testapp_teardown(test); + ret = testapp_teardown(test); break; case TEST_TYPE_BIDI: - testapp_bidi(test); + ret = testapp_bidi(test); break; case TEST_TYPE_BPF_RES: - testapp_bpf_res(test); + ret = testapp_bpf_res(test); break; case TEST_TYPE_RUN_TO_COMPLETION: test_spec_set_name(test, "RUN_TO_COMPLETION"); - testapp_validate_traffic(test); + ret = testapp_validate_traffic(test); break; case TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT: test_spec_set_name(test, "RUN_TO_COMPLETION_SINGLE_PKT"); - testapp_single_pkt(test); + ret = testapp_single_pkt(test); break; case TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME: test_spec_set_name(test, "RUN_TO_COMPLETION_2K_FRAME_SIZE"); test->ifobj_tx->umem->frame_size = 2048; test->ifobj_rx->umem->frame_size = 2048; - pkt_stream_replace(test, DEFAULT_PKT_CNT, PKT_SIZE); - testapp_validate_traffic(test); + pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE); + ret = testapp_validate_traffic(test); break; case TEST_TYPE_RX_POLL: test->ifobj_rx->use_poll = true; test_spec_set_name(test, "POLL_RX"); - testapp_validate_traffic(test); + ret = testapp_validate_traffic(test); break; case TEST_TYPE_TX_POLL: test->ifobj_tx->use_poll = true; test_spec_set_name(test, "POLL_TX"); - testapp_validate_traffic(test); + ret = testapp_validate_traffic(test); break; case TEST_TYPE_POLL_TXQ_TMOUT: - testapp_poll_txq_tmout(test); + ret = testapp_poll_txq_tmout(test); break; case TEST_TYPE_POLL_RXQ_TMOUT: - testapp_poll_rxq_tmout(test); + ret = testapp_poll_rxq_tmout(test); break; case TEST_TYPE_ALIGNED_INV_DESC: test_spec_set_name(test, "ALIGNED_INV_DESC"); - testapp_invalid_desc(test); + ret = testapp_invalid_desc(test); break; case TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME: test_spec_set_name(test, "ALIGNED_INV_DESC_2K_FRAME_SIZE"); test->ifobj_tx->umem->frame_size = 2048; test->ifobj_rx->umem->frame_size = 2048; - testapp_invalid_desc(test); + ret = testapp_invalid_desc(test); break; case TEST_TYPE_UNALIGNED_INV_DESC: - if (!hugepages_present(test->ifobj_tx)) { - ksft_test_result_skip("No 2M huge pages present.\n"); - return; - } test_spec_set_name(test, "UNALIGNED_INV_DESC"); test->ifobj_tx->umem->unaligned_mode = true; test->ifobj_rx->umem->unaligned_mode = true; - testapp_invalid_desc(test); + ret = testapp_invalid_desc(test); break; case TEST_TYPE_UNALIGNED_INV_DESC_4K1_FRAME: { u64 page_size, umem_size; - if (!hugepages_present(test->ifobj_tx)) { - ksft_test_result_skip("No 2M huge pages present.\n"); - return; - } test_spec_set_name(test, "UNALIGNED_INV_DESC_4K1_FRAME_SIZE"); /* Odd frame size so the UMEM doesn't end near a page boundary. */ test->ifobj_tx->umem->frame_size = 4001; @@ -1903,29 +1861,28 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_ */ page_size = sysconf(_SC_PAGESIZE); umem_size = test->ifobj_tx->umem->num_frames * test->ifobj_tx->umem->frame_size; - assert(umem_size % page_size > PKT_SIZE); - assert(umem_size % page_size < page_size - PKT_SIZE); - testapp_invalid_desc(test); + assert(umem_size % page_size > MIN_PKT_SIZE); + assert(umem_size % page_size < page_size - MIN_PKT_SIZE); + ret = testapp_invalid_desc(test); break; } case TEST_TYPE_UNALIGNED: - if (!testapp_unaligned(test)) - return; + ret = testapp_unaligned(test); break; case TEST_TYPE_HEADROOM: - testapp_headroom(test); + ret = testapp_headroom(test); break; case TEST_TYPE_XDP_DROP_HALF: - testapp_xdp_drop(test); + ret = testapp_xdp_drop(test); break; case TEST_TYPE_XDP_METADATA_COUNT: - testapp_xdp_metadata_count(test); + ret = testapp_xdp_metadata_count(test); break; default: break; } - if (!test->fail) + if (ret == TEST_PASS) ksft_test_result_pass("PASS: %s %s%s\n", mode_string(test), busy_poll_string(test), test->name); pkt_stream_restore_default(test); @@ -2030,14 +1987,12 @@ int main(int argc, char **argv) modes++; } - init_iface(ifobj_rx, MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, - worker_testapp_validate_rx); - init_iface(ifobj_tx, MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, - worker_testapp_validate_tx); + init_iface(ifobj_rx, MAC1, MAC2, worker_testapp_validate_rx); + init_iface(ifobj_tx, MAC2, MAC1, worker_testapp_validate_tx); test_spec_init(&test, ifobj_tx, ifobj_rx, 0); - tx_pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, PKT_SIZE); - rx_pkt_stream_default = pkt_stream_generate(ifobj_rx->umem, DEFAULT_PKT_CNT, PKT_SIZE); + tx_pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, MIN_PKT_SIZE); + rx_pkt_stream_default = pkt_stream_generate(ifobj_rx->umem, DEFAULT_PKT_CNT, MIN_PKT_SIZE); if (!tx_pkt_stream_default || !rx_pkt_stream_default) exit_with_error(ENOMEM); test.tx_pkt_stream_default = tx_pkt_stream_default; diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h index c535aeab2ca3..aaf27e067640 100644 --- a/tools/testing/selftests/bpf/xskxceiver.h +++ b/tools/testing/selftests/bpf/xskxceiver.h @@ -30,22 +30,14 @@ #define TEST_PASS 0 #define TEST_FAILURE -1 #define TEST_CONTINUE 1 +#define TEST_SKIP 2 #define MAX_INTERFACES 2 #define MAX_INTERFACE_NAME_CHARS 16 #define MAX_SOCKETS 2 #define MAX_TEST_NAME_SIZE 32 #define MAX_TEARDOWN_ITER 10 -#define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \ - sizeof(struct udphdr)) -#define MIN_ETH_PKT_SIZE 64 -#define ETH_FCS_SIZE 4 -#define MIN_PKT_SIZE (MIN_ETH_PKT_SIZE - ETH_FCS_SIZE) -#define PKT_SIZE (MIN_PKT_SIZE) -#define IP_PKT_SIZE (PKT_SIZE - sizeof(struct ethhdr)) -#define IP_PKT_VER 0x4 -#define IP_PKT_TOS 0x9 -#define UDP_PKT_SIZE (IP_PKT_SIZE - sizeof(struct iphdr)) -#define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr)) +#define PKT_HDR_SIZE (sizeof(struct ethhdr) + 2) /* Just to align the data in the packet */ +#define MIN_PKT_SIZE 64 #define USLEEP_MAX 10000 #define SOCK_RECONF_CTR 10 #define BATCH_SIZE 64 @@ -57,6 +49,7 @@ #define UMEM_HEADROOM_TEST_SIZE 128 #define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1) #define HUGEPAGE_SIZE (2 * 1024 * 1024) +#define PKT_DUMP_NB_TO_PRINT 16 #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0) @@ -93,13 +86,13 @@ enum test_type { TEST_TYPE_MAX }; -static bool opt_pkt_dump; static bool opt_verbose; struct xsk_umem_info { struct xsk_ring_prod fq; struct xsk_ring_cons cq; struct xsk_umem *umem; + u64 next_buffer; u32 num_frames; u32 frame_headroom; void *buffer; @@ -118,17 +111,17 @@ struct xsk_socket_info { }; struct pkt { - u64 addr; + int offset; u32 len; - u32 payload; + u32 pkt_nb; bool valid; }; struct pkt_stream { u32 nb_pkts; - u32 rx_pkt_nb; + u32 current_pkt_nb; struct pkt *pkts; - bool use_addr_for_fill; + u32 max_pkt_len; }; struct ifobject; @@ -148,11 +141,7 @@ struct ifobject { struct bpf_program *xdp_prog; enum test_mode mode; int ifindex; - u32 dst_ip; - u32 src_ip; u32 bind_flags; - u16 src_port; - u16 dst_port; bool tx_on; bool rx_on; bool use_poll; @@ -161,6 +150,7 @@ struct ifobject { bool release_rx; bool shared_umem; bool use_metadata; + bool unaligned_supp; u8 dst_mac[ETH_ALEN]; u8 src_mac[ETH_ALEN]; }; @@ -184,7 +174,6 @@ struct test_spec { pthread_barrier_t barr; pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER; -pthread_cond_t pacing_cond = PTHREAD_COND_INITIALIZER; int pkts_in_flight; diff --git a/tools/testing/selftests/cachestat/.gitignore b/tools/testing/selftests/cachestat/.gitignore new file mode 100644 index 000000000000..d6c30b43a4bb --- /dev/null +++ b/tools/testing/selftests/cachestat/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +test_cachestat diff --git a/tools/testing/selftests/cachestat/Makefile b/tools/testing/selftests/cachestat/Makefile new file mode 100644 index 000000000000..fca73aaa7d14 --- /dev/null +++ b/tools/testing/selftests/cachestat/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0 +TEST_GEN_PROGS := test_cachestat + +CFLAGS += $(KHDR_INCLUDES) +CFLAGS += -Wall +CFLAGS += -lrt + +include ../lib.mk diff --git a/tools/testing/selftests/cachestat/test_cachestat.c b/tools/testing/selftests/cachestat/test_cachestat.c new file mode 100644 index 000000000000..54d09b820ed4 --- /dev/null +++ b/tools/testing/selftests/cachestat/test_cachestat.c @@ -0,0 +1,269 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdbool.h> +#include <linux/kernel.h> +#include <linux/mman.h> +#include <sys/mman.h> +#include <sys/shm.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <string.h> +#include <fcntl.h> +#include <errno.h> + +#include "../kselftest.h" + +static const char * const dev_files[] = { + "/dev/zero", "/dev/null", "/dev/urandom", + "/proc/version", "/proc" +}; +static const int cachestat_nr = 451; + +void print_cachestat(struct cachestat *cs) +{ + ksft_print_msg( + "Using cachestat: Cached: %lu, Dirty: %lu, Writeback: %lu, Evicted: %lu, Recently Evicted: %lu\n", + cs->nr_cache, cs->nr_dirty, cs->nr_writeback, + cs->nr_evicted, cs->nr_recently_evicted); +} + +bool write_exactly(int fd, size_t filesize) +{ + int random_fd = open("/dev/urandom", O_RDONLY); + char *cursor, *data; + int remained; + bool ret; + + if (random_fd < 0) { + ksft_print_msg("Unable to access urandom.\n"); + ret = false; + goto out; + } + + data = malloc(filesize); + if (!data) { + ksft_print_msg("Unable to allocate data.\n"); + ret = false; + goto close_random_fd; + } + + remained = filesize; + cursor = data; + + while (remained) { + ssize_t read_len = read(random_fd, cursor, remained); + + if (read_len <= 0) { + ksft_print_msg("Unable to read from urandom.\n"); + ret = false; + goto out_free_data; + } + + remained -= read_len; + cursor += read_len; + } + + /* write random data to fd */ + remained = filesize; + cursor = data; + while (remained) { + ssize_t write_len = write(fd, cursor, remained); + + if (write_len <= 0) { + ksft_print_msg("Unable write random data to file.\n"); + ret = false; + goto out_free_data; + } + + remained -= write_len; + cursor += write_len; + } + + ret = true; +out_free_data: + free(data); +close_random_fd: + close(random_fd); +out: + return ret; +} + +/* + * Open/create the file at filename, (optionally) write random data to it + * (exactly num_pages), then test the cachestat syscall on this file. + * + * If test_fsync == true, fsync the file, then check the number of dirty + * pages. + */ +bool test_cachestat(const char *filename, bool write_random, bool create, + bool test_fsync, unsigned long num_pages, int open_flags, + mode_t open_mode) +{ + size_t PS = sysconf(_SC_PAGESIZE); + int filesize = num_pages * PS; + bool ret = true; + long syscall_ret; + struct cachestat cs; + struct cachestat_range cs_range = { 0, filesize }; + + int fd = open(filename, open_flags, open_mode); + + if (fd == -1) { + ksft_print_msg("Unable to create/open file.\n"); + ret = false; + goto out; + } else { + ksft_print_msg("Create/open %s\n", filename); + } + + if (write_random) { + if (!write_exactly(fd, filesize)) { + ksft_print_msg("Unable to access urandom.\n"); + ret = false; + goto out1; + } + } + + syscall_ret = syscall(cachestat_nr, fd, &cs_range, &cs, 0); + + ksft_print_msg("Cachestat call returned %ld\n", syscall_ret); + + if (syscall_ret) { + ksft_print_msg("Cachestat returned non-zero.\n"); + ret = false; + goto out1; + + } else { + print_cachestat(&cs); + + if (write_random) { + if (cs.nr_cache + cs.nr_evicted != num_pages) { + ksft_print_msg( + "Total number of cached and evicted pages is off.\n"); + ret = false; + } + } + } + + if (test_fsync) { + if (fsync(fd)) { + ksft_print_msg("fsync fails.\n"); + ret = false; + } else { + syscall_ret = syscall(cachestat_nr, fd, &cs_range, &cs, 0); + + ksft_print_msg("Cachestat call (after fsync) returned %ld\n", + syscall_ret); + + if (!syscall_ret) { + print_cachestat(&cs); + + if (cs.nr_dirty) { + ret = false; + ksft_print_msg( + "Number of dirty should be zero after fsync.\n"); + } + } else { + ksft_print_msg("Cachestat (after fsync) returned non-zero.\n"); + ret = false; + goto out1; + } + } + } + +out1: + close(fd); + + if (create) + remove(filename); +out: + return ret; +} + +bool test_cachestat_shmem(void) +{ + size_t PS = sysconf(_SC_PAGESIZE); + size_t filesize = PS * 512 * 2; /* 2 2MB huge pages */ + int syscall_ret; + size_t compute_len = PS * 512; + struct cachestat_range cs_range = { PS, compute_len }; + char *filename = "tmpshmcstat"; + struct cachestat cs; + bool ret = true; + unsigned long num_pages = compute_len / PS; + int fd = shm_open(filename, O_CREAT | O_RDWR, 0600); + + if (fd < 0) { + ksft_print_msg("Unable to create shmem file.\n"); + ret = false; + goto out; + } + + if (ftruncate(fd, filesize)) { + ksft_print_msg("Unable to truncate shmem file.\n"); + ret = false; + goto close_fd; + } + + if (!write_exactly(fd, filesize)) { + ksft_print_msg("Unable to write to shmem file.\n"); + ret = false; + goto close_fd; + } + + syscall_ret = syscall(cachestat_nr, fd, &cs_range, &cs, 0); + + if (syscall_ret) { + ksft_print_msg("Cachestat returned non-zero.\n"); + ret = false; + goto close_fd; + } else { + print_cachestat(&cs); + if (cs.nr_cache + cs.nr_evicted != num_pages) { + ksft_print_msg( + "Total number of cached and evicted pages is off.\n"); + ret = false; + } + } + +close_fd: + shm_unlink(filename); +out: + return ret; +} + +int main(void) +{ + int ret = 0; + + for (int i = 0; i < 5; i++) { + const char *dev_filename = dev_files[i]; + + if (test_cachestat(dev_filename, false, false, false, + 4, O_RDONLY, 0400)) + ksft_test_result_pass("cachestat works with %s\n", dev_filename); + else { + ksft_test_result_fail("cachestat fails with %s\n", dev_filename); + ret = 1; + } + } + + if (test_cachestat("tmpfilecachestat", true, true, + true, 4, O_CREAT | O_RDWR, 0400 | 0600)) + ksft_test_result_pass("cachestat works with a normal file\n"); + else { + ksft_test_result_fail("cachestat fails with normal file\n"); + ret = 1; + } + + if (test_cachestat_shmem()) + ksft_test_result_pass("cachestat works with a shmem file\n"); + else { + ksft_test_result_fail("cachestat fails with a shmem file\n"); + ret = 1; + } + + return ret; +} diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index f4f7c0aef702..c7c9572003a8 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -292,6 +292,7 @@ static int test_memcg_protection(const char *root, bool min) char *children[4] = {NULL}; const char *attribute = min ? "memory.min" : "memory.low"; long c[4]; + long current; int i, attempts; int fd; @@ -400,7 +401,8 @@ static int test_memcg_protection(const char *root, bool min) goto cleanup; } - if (!values_close(cg_read_long(parent[1], "memory.current"), MB(50), 3)) + current = min ? MB(50) : MB(30); + if (!values_close(cg_read_long(parent[1], "memory.current"), current, 3)) goto cleanup; if (!reclaim_until(children[0], MB(10))) @@ -987,7 +989,9 @@ static int tcp_client(const char *cgroup, unsigned short port) char servport[6]; int retries = 0x10; /* nice round number */ int sk, ret; + long allocated; + allocated = cg_read_long(cgroup, "memory.current"); snprintf(servport, sizeof(servport), "%hd", port); ret = getaddrinfo(server, servport, NULL, &ai); if (ret) @@ -1015,7 +1019,8 @@ static int tcp_client(const char *cgroup, unsigned short port) if (current < 0 || sock < 0) goto close_sk; - if (values_close(current, sock, 10)) { + /* exclude the memory not related to socket connection */ + if (values_close(current - allocated, sock, 10)) { ret = KSFT_PASS; break; } diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index e495f895a2cd..e60cf4da8fb0 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -129,7 +129,7 @@ int main(int argc, char *argv[]) uid_t uid = getuid(); ksft_print_header(); - ksft_set_plan(18); + ksft_set_plan(19); test_clone3_supported(); /* Just a simple clone3() should return 0.*/ @@ -198,5 +198,8 @@ int main(int argc, char *argv[]) /* Do a clone3() in a new time namespace */ test_clone3(CLONE_NEWTIME, 0, 0, CLONE3_ARGS_NO_TEST); + /* Do a clone3() with exit signal (SIGCHLD) in flags */ + test_clone3(SIGCHLD, 0, -EINVAL, CLONE3_ARGS_NO_TEST); + ksft_finished(); } diff --git a/tools/testing/selftests/cpufreq/config b/tools/testing/selftests/cpufreq/config index 75e900793e8a..ce5068f5a6a2 100644 --- a/tools/testing/selftests/cpufreq/config +++ b/tools/testing/selftests/cpufreq/config @@ -5,11 +5,3 @@ CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y -CONFIG_DEBUG_RT_MUTEXES=y -CONFIG_DEBUG_PLIST=y -CONFIG_DEBUG_SPINLOCK=y -CONFIG_DEBUG_MUTEXES=y -CONFIG_DEBUG_LOCK_ALLOC=y -CONFIG_PROVE_LOCKING=y -CONFIG_LOCKDEP=y -CONFIG_DEBUG_ATOMIC_SLEEP=y diff --git a/tools/testing/selftests/damon/config b/tools/testing/selftests/damon/config new file mode 100644 index 000000000000..0daf38974eb0 --- /dev/null +++ b/tools/testing/selftests/damon/config @@ -0,0 +1,7 @@ +CONFIG_DAMON=y +CONFIG_DAMON_SYSFS=y +CONFIG_DAMON_DBGFS=y +CONFIG_DAMON_PADDR=y +CONFIG_DAMON_VADDR=y +CONFIG_DAMON_RECLAIM=y +CONFIG_DAMON_LRU_SORT=y diff --git a/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh b/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh index 5cdd22048ba7..862e947e17c7 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh @@ -53,7 +53,6 @@ bond_test_enslave_type_change() # restore ARPHRD_ETHER type by enslaving such device ip link set dev "$devbond2" master "$devbond0" check_err $? "could not enslave $devbond2 to $devbond0" - ip link set dev "$devbond1" nomaster bond_check_flags "$devbond0" diff --git a/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh b/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh index 0cf9e47e3209..a5c2aec52898 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh @@ -16,10 +16,9 @@ # +----------------|--+ +--|-----------------+ # | | # +----------------|-------------------------|-----------------+ -# | SW | | | +# | SW $swp1 + + $swp2 | +# | | | | # | +--------------|-------------------------|---------------+ | -# | | $swp1 + + $swp2 | | -# | | | | | | # | | $swp1.10 + + $swp2.10 | | # | | | | # | | br0 | | diff --git a/tools/testing/selftests/drivers/net/mlxsw/extack.sh b/tools/testing/selftests/drivers/net/mlxsw/extack.sh index 7a0a99c1d22f..6fd422d38fe8 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/extack.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/extack.sh @@ -35,7 +35,9 @@ netdev_pre_up_test() { RET=0 - ip link add name br1 up type bridge vlan_filtering 0 mcast_snooping 0 + ip link add name br1 type bridge vlan_filtering 0 mcast_snooping 0 + ip link set dev br1 addrgenmode none + ip link set dev br1 up ip link add name vx1 up type vxlan id 1000 \ local 192.0.2.17 remote 192.0.2.18 \ dstport 4789 nolearning noudpcsum tos inherit ttl 100 @@ -46,7 +48,9 @@ netdev_pre_up_test() ip link set dev $swp1 master br1 check_err $? - ip link add name br2 up type bridge vlan_filtering 0 mcast_snooping 0 + ip link add name br2 type bridge vlan_filtering 0 mcast_snooping 0 + ip link set dev br2 addrgenmode none + ip link set dev br2 up ip link add name vx2 up type vxlan id 2000 \ local 192.0.2.17 remote 192.0.2.18 \ dstport 4789 nolearning noudpcsum tos inherit ttl 100 @@ -81,7 +85,9 @@ vxlan_vlan_add_test() { RET=0 - ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 0 + ip link add name br1 type bridge vlan_filtering 1 mcast_snooping 0 + ip link set dev br1 addrgenmode none + ip link set dev br1 up # Unsupported configuration: mlxsw demands VXLAN with "noudpcsum". ip link add name vx1 up type vxlan id 1000 \ @@ -117,7 +123,9 @@ vxlan_bridge_create_test() dstport 4789 tos inherit ttl 100 # Test with VLAN-aware bridge. - ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 0 + ip link add name br1 type bridge vlan_filtering 1 mcast_snooping 0 + ip link set dev br1 addrgenmode none + ip link set dev br1 up ip link set dev vx1 master br1 @@ -142,8 +150,12 @@ bridge_create_test() { RET=0 - ip link add name br1 up type bridge vlan_filtering 1 - ip link add name br2 up type bridge vlan_filtering 1 + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 addrgenmode none + ip link set dev br1 up + ip link add name br2 type bridge vlan_filtering 1 + ip link set dev br2 addrgenmode none + ip link set dev br2 up ip link set dev $swp1 master br1 check_err $? diff --git a/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh b/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh index df2b09966886..7d7f862c809c 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh @@ -15,10 +15,9 @@ # +----------------|--+ +--|-----------------+ # | | # +----------------|-------------------------|-----------------+ -# | SW | | | +# | SW $swp1 + + $swp2 | +# | | | | # | +--------------|-------------------------|---------------+ | -# | | $swp1 + + $swp2 | | -# | | | | | | # | | $swp1.10 + + $swp2.10 | | # | | | | # | | br0 | | diff --git a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh index e00435753008..e5589e2fca85 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh @@ -165,6 +165,7 @@ mirror_gre_setup_prepare() simple_if_init $h3 ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 addrgenmode none ip link set dev br1 up ip link set dev $swp1 master br1 diff --git a/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh b/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh index f02d83e94576..fca0e1e642c6 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh @@ -83,7 +83,8 @@ h2_destroy() switch_create() { - ip link add name br0 type bridge mcast_snooping 0 + ip link add name br0 address $(mac_get $swp1) \ + type bridge mcast_snooping 0 ip link set dev br0 up ip link set dev $swp1 master br0 diff --git a/tools/testing/selftests/drivers/net/mlxsw/q_in_q_veto.sh b/tools/testing/selftests/drivers/net/mlxsw/q_in_q_veto.sh index 7edaed8eb86a..00d55b0e98c1 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/q_in_q_veto.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/q_in_q_veto.sh @@ -48,6 +48,7 @@ create_vlan_upper_on_top_of_bridge() ip link add dev br0 type bridge vlan_filtering 1 \ vlan_protocol $bridge_proto vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev br0 up ip link set dev $swp1 master br0 @@ -88,6 +89,7 @@ create_8021ad_vlan_upper_on_top_bridge_port() ip link add dev br0 type bridge vlan_filtering 1 \ vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev $swp1 master br0 ip link set dev br0 up @@ -155,6 +157,7 @@ create_vlan_upper_on_top_front_panel_enslaved_to_8021ad_bridge() ip link add dev br0 type bridge vlan_filtering 1 \ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev br0 up ip link set dev $swp1 master br0 @@ -177,6 +180,7 @@ create_vlan_upper_on_top_lag_enslaved_to_8021ad_bridge() ip link add dev br0 type bridge vlan_filtering 1 \ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev br0 up ip link add name bond1 type bond mode 802.3ad @@ -203,6 +207,7 @@ enslave_front_panel_with_vlan_upper_to_8021ad_bridge() ip link add dev br0 type bridge vlan_filtering 1 \ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev br0 up ip link add name $swp1.100 link $swp1 type vlan id 100 @@ -225,6 +230,7 @@ enslave_lag_with_vlan_upper_to_8021ad_bridge() ip link add dev br0 type bridge vlan_filtering 1 \ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev br0 up ip link add name bond1 type bond mode 802.3ad @@ -252,6 +258,7 @@ add_ip_address_to_8021ad_bridge() ip link add dev br0 type bridge vlan_filtering 1 \ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev br0 up ip link set dev $swp1 master br0 @@ -273,6 +280,7 @@ switch_bridge_protocol_from_8021q_to_8021ad() ip link add dev br0 type bridge vlan_filtering 1 \ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev br0 up ip link set dev $swp1 master br0 diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh index 87c41f5727c9..914c63d6318a 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh @@ -65,6 +65,7 @@ h2_destroy() switch_create() { ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 addrgenmode none ip link set dev br1 up ip link set dev $swp1 master br1 ip link set dev $swp1 up diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh index 690d8daa71b4..fee74f215cec 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh @@ -138,11 +138,15 @@ switch_create() vlan_create $swp3 111 vlan_create $swp3 222 - ip link add name br111 up type bridge vlan_filtering 0 + ip link add name br111 type bridge vlan_filtering 0 + ip link set dev br111 addrgenmode none + ip link set dev br111 up ip link set dev $swp1.111 master br111 ip link set dev $swp3.111 master br111 - ip link add name br222 up type bridge vlan_filtering 0 + ip link add name br222 type bridge vlan_filtering 0 + ip link set dev br222 addrgenmode none + ip link set dev br222 up ip link set dev $swp2.222 master br222 ip link set dev $swp3.222 master br222 diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh index c8e55fa91660..6d892de43fa8 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh @@ -135,11 +135,13 @@ switch_create() prio bands 8 priomap 7 7 7 7 7 7 7 7 ip link add name br1 type bridge vlan_filtering 0 + ip link set dev br1 addrgenmode none ip link set dev br1 up ip link set dev $swp1 master br1 ip link set dev $swp3 master br1 ip link add name br111 type bridge vlan_filtering 0 + ip link set dev br111 addrgenmode none ip link set dev br111 up ip link set dev $swp2.111 master br111 ip link set dev $swp3.111 master br111 diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/q_in_vni_veto.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/q_in_vni_veto.sh index f0443b1b05b9..60753d46a2d4 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/q_in_vni_veto.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/q_in_vni_veto.sh @@ -34,6 +34,7 @@ create_vxlan_on_top_of_8021ad_bridge() ip link add dev br0 type bridge vlan_filtering 1 vlan_protocol 802.1ad \ vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br0 addrgenmode none ip link set dev br0 up ip link add name vx100 type vxlan id 1000 local 192.0.2.17 dstport \ diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh index 99a332b712f0..4687b0a7dffb 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh @@ -444,8 +444,12 @@ offload_indication_setup_create() { # Create a simple setup with two bridges, each with a VxLAN device # and one local port - ip link add name br0 up type bridge mcast_snooping 0 - ip link add name br1 up type bridge mcast_snooping 0 + ip link add name br0 type bridge mcast_snooping 0 + ip link set dev br0 addrgenmode none + ip link set dev br0 up + ip link add name br1 type bridge mcast_snooping 0 + ip link set dev br1 addrgenmode none + ip link set dev br1 up ip link set dev $swp1 master br0 ip link set dev $swp2 master br1 @@ -646,8 +650,12 @@ offload_indication_decap_route_test() RET=0 - ip link add name br0 up type bridge mcast_snooping 0 - ip link add name br1 up type bridge mcast_snooping 0 + ip link add name br0 type bridge mcast_snooping 0 + ip link set dev br0 addrgenmode none + ip link set dev br0 up + ip link add name br1 type bridge mcast_snooping 0 + ip link set dev br1 addrgenmode none + ip link set dev br1 up ip link set dev $swp1 master br0 ip link set dev $swp2 master br1 ip link set dev vxlan0 master br0 @@ -780,7 +788,9 @@ __offload_indication_join_vxlan_first() offload_indication_join_vxlan_first() { - ip link add dev br0 up type bridge mcast_snooping 0 + ip link add dev br0 type bridge mcast_snooping 0 + ip link set dev br0 addrgenmode none + ip link set dev br0 up ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 @@ -815,7 +825,9 @@ __offload_indication_join_vxlan_last() offload_indication_join_vxlan_last() { - ip link add dev br0 up type bridge mcast_snooping 0 + ip link add dev br0 type bridge mcast_snooping 0 + ip link set dev br0 addrgenmode none + ip link set dev br0 up ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 @@ -842,6 +854,7 @@ sanitization_vlan_aware_test() RET=0 ip link add dev br0 type bridge mcast_snooping 0 vlan_filtering 1 + ip link set dev br0 addrgenmode none ip link add name vxlan10 up master br0 type vxlan id 10 nolearning \ $UDPCSUM_FLAFS ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 @@ -915,8 +928,10 @@ offload_indication_vlan_aware_setup_create() { # Create a simple setup with two VxLAN devices and a single VLAN-aware # bridge - ip link add name br0 up type bridge mcast_snooping 0 vlan_filtering 1 \ + ip link add name br0 type bridge mcast_snooping 0 vlan_filtering 1 \ vlan_default_pvid 0 + ip link set dev br0 addrgenmode none + ip link set dev br0 up ip link set dev $swp1 master br0 @@ -1060,8 +1075,10 @@ offload_indication_vlan_aware_decap_route_test() offload_indication_vlan_aware_join_vxlan_first() { - ip link add dev br0 up type bridge mcast_snooping 0 \ + ip link add dev br0 type bridge mcast_snooping 0 \ vlan_filtering 1 vlan_default_pvid 1 + ip link set dev br0 addrgenmode none + ip link set dev br0 up ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 @@ -1073,8 +1090,10 @@ offload_indication_vlan_aware_join_vxlan_first() offload_indication_vlan_aware_join_vxlan_last() { - ip link add dev br0 up type bridge mcast_snooping 0 \ + ip link add dev br0 type bridge mcast_snooping 0 \ vlan_filtering 1 vlan_default_pvid 1 + ip link set dev br0 addrgenmode none + ip link set dev br0 up ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 @@ -1091,8 +1110,10 @@ offload_indication_vlan_aware_l3vni_test() RET=0 sysctl_set net.ipv6.conf.default.disable_ipv6 1 - ip link add dev br0 up type bridge mcast_snooping 0 \ + ip link add dev br0 type bridge mcast_snooping 0 \ vlan_filtering 1 vlan_default_pvid 0 + ip link set dev br0 addrgenmode none + ip link set dev br0 up ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \ ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789 diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index d6e106fbce11..a1e955d2de4c 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 all: -TEST_PROGS := ftracetest +TEST_PROGS_EXTENDED := ftracetest +TEST_PROGS := ftracetest-ktap TEST_FILES := test.d settings EXTRA_CLEAN := $(OUTPUT)/logs/* diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index c3311c8c4089..cb5f18c06593 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -13,6 +13,7 @@ echo "Usage: ftracetest [options] [testcase(s)] [testcase-directory(s)]" echo " Options:" echo " -h|--help Show help message" echo " -k|--keep Keep passed test logs" +echo " -K|--ktap Output in KTAP format" echo " -v|--verbose Increase verbosity of test messages" echo " -vv Alias of -v -v (Show all results in stdout)" echo " -vvv Alias of -v -v -v (Show all commands immediately)" @@ -85,6 +86,10 @@ parse_opts() { # opts KEEP_LOG=1 shift 1 ;; + --ktap|-K) + KTAP=1 + shift 1 + ;; --verbose|-v|-vv|-vvv) if [ $VERBOSE -eq -1 ]; then usage "--console can not use with --verbose" @@ -178,6 +183,7 @@ TEST_DIR=$TOP_DIR/test.d TEST_CASES=`find_testcases $TEST_DIR` LOG_DIR=$TOP_DIR/logs/`date +%Y%m%d-%H%M%S`/ KEEP_LOG=0 +KTAP=0 DEBUG=0 VERBOSE=0 UNSUPPORTED_RESULT=0 @@ -229,7 +235,7 @@ prlog() { # messages newline= shift fi - printf "$*$newline" + [ "$KTAP" != "1" ] && printf "$*$newline" [ "$LOG_FILE" ] && printf "$*$newline" | strip_esc >> $LOG_FILE } catlog() { #file @@ -260,11 +266,11 @@ TOTAL_RESULT=0 INSTANCE= CASENO=0 +CASENAME= testcase() { # testfile CASENO=$((CASENO+1)) - desc=`grep "^#[ \t]*description:" $1 | cut -f2- -d:` - prlog -n "[$CASENO]$INSTANCE$desc" + CASENAME=`grep "^#[ \t]*description:" $1 | cut -f2- -d:` } checkreq() { # testfile @@ -277,40 +283,68 @@ test_on_instance() { # testfile grep -q "^#[ \t]*flags:.*instance" $1 } +ktaptest() { # result comment + if [ "$KTAP" != "1" ]; then + return + fi + + local result= + if [ "$1" = "1" ]; then + result="ok" + else + result="not ok" + fi + shift + + local comment=$* + if [ "$comment" != "" ]; then + comment="# $comment" + fi + + echo $result $CASENO $INSTANCE$CASENAME $comment +} + eval_result() { # sigval case $1 in $PASS) prlog " [${color_green}PASS${color_reset}]" + ktaptest 1 PASSED_CASES="$PASSED_CASES $CASENO" return 0 ;; $FAIL) prlog " [${color_red}FAIL${color_reset}]" + ktaptest 0 FAILED_CASES="$FAILED_CASES $CASENO" return 1 # this is a bug. ;; $UNRESOLVED) prlog " [${color_blue}UNRESOLVED${color_reset}]" + ktaptest 0 UNRESOLVED UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO" return $UNRESOLVED_RESULT # depends on use case ;; $UNTESTED) prlog " [${color_blue}UNTESTED${color_reset}]" + ktaptest 1 SKIP UNTESTED_CASES="$UNTESTED_CASES $CASENO" return 0 ;; $UNSUPPORTED) prlog " [${color_blue}UNSUPPORTED${color_reset}]" + ktaptest 1 SKIP UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO" return $UNSUPPORTED_RESULT # depends on use case ;; $XFAIL) prlog " [${color_green}XFAIL${color_reset}]" + ktaptest 1 XFAIL XFAILED_CASES="$XFAILED_CASES $CASENO" return 0 ;; *) prlog " [${color_blue}UNDEFINED${color_reset}]" + ktaptest 0 error UNDEFINED_CASES="$UNDEFINED_CASES $CASENO" return 1 # this must be a test bug ;; @@ -371,6 +405,7 @@ __run_test() { # testfile run_test() { # testfile local testname=`basename $1` testcase $1 + prlog -n "[$CASENO]$INSTANCE$CASENAME" if [ ! -z "$LOG_FILE" ] ; then local testlog=`mktemp $LOG_DIR/${CASENO}-${testname}-log.XXXXXX` else @@ -405,6 +440,17 @@ run_test() { # testfile # load in the helper functions . $TEST_DIR/functions +if [ "$KTAP" = "1" ]; then + echo "TAP version 13" + + casecount=`echo $TEST_CASES | wc -w` + for t in $TEST_CASES; do + test_on_instance $t || continue + casecount=$((casecount+1)) + done + echo "1..${casecount}" +fi + # Main loop for t in $TEST_CASES; do run_test $t @@ -439,6 +485,17 @@ prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w` prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w` prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w` +if [ "$KTAP" = "1" ]; then + echo -n "# Totals:" + echo -n " pass:"`echo $PASSED_CASES | wc -w` + echo -n " faii:"`echo $FAILED_CASES | wc -w` + echo -n " xfail:"`echo $XFAILED_CASES | wc -w` + echo -n " xpass:0" + echo -n " skip:"`echo $UNTESTED_CASES $UNSUPPORTED_CASES | wc -w` + echo -n " error:"`echo $UNRESOLVED_CASES $UNDEFINED_CASES | wc -w` + echo +fi + cleanup # if no error, return 0 diff --git a/tools/testing/selftests/ftrace/ftracetest-ktap b/tools/testing/selftests/ftrace/ftracetest-ktap new file mode 100755 index 000000000000..b3284679ef3a --- /dev/null +++ b/tools/testing/selftests/ftrace/ftracetest-ktap @@ -0,0 +1,8 @@ +#!/bin/sh -e +# SPDX-License-Identifier: GPL-2.0-only +# +# ftracetest-ktap: Wrapper to integrate ftracetest with the kselftest runner +# +# Copyright (C) Arm Ltd., 2023 + +./ftracetest -K diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc index e2ff3bf4df80..2de7c61d1ae3 100644 --- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc +++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc @@ -9,18 +9,33 @@ fail() { #msg exit_fail } -echo "Test event filter function name" +sample_events() { + echo > trace + echo 1 > events/kmem/kmem_cache_free/enable + echo 1 > tracing_on + ls > /dev/null + echo 0 > tracing_on + echo 0 > events/kmem/kmem_cache_free/enable +} + echo 0 > tracing_on echo 0 > events/enable + +echo "Get the most frequently calling function" +sample_events + +target_func=`cut -d: -f3 trace | sed 's/call_site=\([^+]*\)+0x.*/\1/' | sort | uniq -c | sort | tail -n 1 | sed 's/^[ 0-9]*//'` +if [ -z "$target_func" ]; then + exit_fail +fi echo > trace -echo 'call_site.function == exit_mmap' > events/kmem/kmem_cache_free/filter -echo 1 > events/kmem/kmem_cache_free/enable -echo 1 > tracing_on -ls > /dev/null -echo 0 > events/kmem/kmem_cache_free/enable -hitcnt=`grep kmem_cache_free trace| grep exit_mmap | wc -l` -misscnt=`grep kmem_cache_free trace| grep -v exit_mmap | wc -l` +echo "Test event filter function name" +echo "call_site.function == $target_func" > events/kmem/kmem_cache_free/filter +sample_events + +hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l` +misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l` if [ $hitcnt -eq 0 ]; then exit_fail @@ -30,20 +45,14 @@ if [ $misscnt -gt 0 ]; then exit_fail fi -address=`grep ' exit_mmap$' /proc/kallsyms | cut -d' ' -f1` +address=`grep " ${target_func}\$" /proc/kallsyms | cut -d' ' -f1` echo "Test event filter function address" -echo 0 > tracing_on -echo 0 > events/enable -echo > trace echo "call_site.function == 0x$address" > events/kmem/kmem_cache_free/filter -echo 1 > events/kmem/kmem_cache_free/enable -echo 1 > tracing_on -sleep 1 -echo 0 > events/kmem/kmem_cache_free/enable +sample_events -hitcnt=`grep kmem_cache_free trace| grep exit_mmap | wc -l` -misscnt=`grep kmem_cache_free trace| grep -v exit_mmap | wc -l` +hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l` +misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l` if [ $hitcnt -eq 0 ]; then exit_fail diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_opt_types.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_opt_types.tc new file mode 100644 index 000000000000..9f5d99328086 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_opt_types.tc @@ -0,0 +1,34 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-or-later +# Copyright (C) 2023 Akanksha J N, IBM corporation +# description: Register/unregister optimized probe +# requires: kprobe_events + +case `uname -m` in +x86_64) +;; +arm*) +;; +ppc*) +;; +*) + echo "Please implement other architecture here" + exit_unsupported +esac + +DEFAULT=$(cat /proc/sys/debug/kprobes-optimization) +echo 1 > /proc/sys/debug/kprobes-optimization +for i in `seq 0 255`; do + echo "p:testprobe $FUNCTION_FORK+${i}" > kprobe_events || continue + echo 1 > events/kprobes/enable || continue + (echo "forked") + PROBE=$(grep $FUNCTION_FORK /sys/kernel/debug/kprobes/list) + echo 0 > events/kprobes/enable + echo > kprobe_events + if echo $PROBE | grep -q OPTIMIZED; then + echo "$DEFAULT" > /proc/sys/debug/kprobes-optimization + exit_pass + fi +done +echo "$DEFAULT" > /proc/sys/debug/kprobes-optimization +exit_unresolved diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc new file mode 100644 index 000000000000..d0cd91a93069 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc @@ -0,0 +1,24 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event trigger - test inter-event histogram trigger trace action with dynamic string param (legacy stack) +# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[] stack' >> synthetic_events":README + +fail() { #msg + echo $1 + exit_fail +} + +echo "Test create synthetic event with stack" + +# Test the old stacktrace keyword (for backward compatibility) +echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events +echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger +echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger +echo 1 > events/synthetic/wake_lat/enable +sleep 1 + +if ! grep -q "=>.*sched" trace; then + fail "Failed to create synthetic event with stack" +fi + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc index 755dbe94ccf4..8f1cc9a86a06 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: event trigger - test inter-event histogram trigger trace action with dynamic string param -# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[]' >> synthetic_events":README +# requires: set_event synthetic_events events/sched/sched_process_exec/hist "can be any field, or the special string 'common_stacktrace'":README fail() { #msg echo $1 @@ -10,9 +10,8 @@ fail() { #msg echo "Test create synthetic event with stack" - echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events -echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger +echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=common_stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger echo 1 > events/synthetic/wake_lat/enable sleep 1 diff --git a/tools/testing/selftests/gpio/gpio-sim.sh b/tools/testing/selftests/gpio/gpio-sim.sh index 9f539d454ee4..6fb66a687f17 100755 --- a/tools/testing/selftests/gpio/gpio-sim.sh +++ b/tools/testing/selftests/gpio/gpio-sim.sh @@ -152,9 +152,9 @@ sysfs_set_pull() { local PULL=$4 local DEVNAME=`configfs_dev_name $DEV` local CHIPNAME=`configfs_chip_name $DEV $BANK` - local SYSFSPATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio$OFFSET/pull" + local SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio$OFFSET/pull" - echo $PULL > $SYSFSPATH || fail "Unable to set line pull in sysfs" + echo $PULL > $SYSFS_PATH || fail "Unable to set line pull in sysfs" } # Load the gpio-sim module. This will pull in configfs if needed too. @@ -389,6 +389,9 @@ create_chip chip create_bank chip bank set_num_lines chip bank 8 enable_chip chip +DEVNAME=`configfs_dev_name chip` +CHIPNAME=`configfs_chip_name chip bank` +SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value" $BASE_DIR/gpio-mockup-cdev -b pull-up /dev/`configfs_chip_name chip bank` 0 test `cat $SYSFS_PATH` = "1" || fail "bias setting does not work" remove_chip chip diff --git a/tools/testing/selftests/hid/tests/test_wacom_generic.py b/tools/testing/selftests/hid/tests/test_wacom_generic.py index b1eb2bc787fc..f92fe8e02c1b 100644 --- a/tools/testing/selftests/hid/tests/test_wacom_generic.py +++ b/tools/testing/selftests/hid/tests/test_wacom_generic.py @@ -31,6 +31,7 @@ from enum import Enum from hidtools.hut import HUT from hidtools.hid import HidUnit from . import base +from . import test_multitouch import libevdev import pytest @@ -517,7 +518,7 @@ class BaseTest: for usage in get_report_usages(report): yield usage - def assertName(self, uhdev): + def assertName(self, uhdev, type): """ Assert that the name is as we expect. @@ -526,7 +527,7 @@ class BaseTest: this assertion from the base class to work properly. """ evdev = uhdev.get_evdev() - expected_name = uhdev.name + " Pen" + expected_name = uhdev.name + type if "wacom" not in expected_name.lower(): expected_name = "Wacom " + expected_name assert evdev.name == expected_name @@ -549,6 +550,12 @@ class BaseTest: usage_id("Generic Desktop", "Y"): PhysRange( PhysRange.CENTIMETER, 5, 150 ), + usage_id("Digitizers", "Width"): PhysRange( + PhysRange.CENTIMETER, 5, 150 + ), + usage_id("Digitizers", "Height"): PhysRange( + PhysRange.CENTIMETER, 5, 150 + ), usage_id("Digitizers", "X Tilt"): PhysRange(PhysRange.DEGREE, 90, 180), usage_id("Digitizers", "Y Tilt"): PhysRange(PhysRange.DEGREE, 90, 180), usage_id("Digitizers", "Twist"): PhysRange(PhysRange.DEGREE, 358, 360), @@ -603,7 +610,17 @@ class BaseTest: pass -class TestOpaqueTablet(BaseTest.TestTablet): +class PenTabletTest(BaseTest.TestTablet): + def assertName(self, uhdev): + super().assertName(uhdev, " Pen") + + +class TouchTabletTest(BaseTest.TestTablet): + def assertName(self, uhdev): + super().assertName(uhdev, " Finger") + + +class TestOpaqueTablet(PenTabletTest): def create_device(self): return OpaqueTablet() @@ -842,3 +859,64 @@ class TestPTHX60_Pen(TestOpaqueCTLTablet): libevdev.InputEvent(libevdev.EV_KEY.BTN_0, 0), ], ) + + +class TestDTH2452Tablet(test_multitouch.BaseTest.TestMultitouch, TouchTabletTest): + def create_device(self): + return test_multitouch.Digitizer( + "DTH 2452", + rdesc="05 0d 09 04 a1 01 85 0c 95 01 75 08 15 00 26 ff 00 81 03 09 54 81 02 09 22 a1 02 05 0d 95 01 75 01 25 01 09 42 81 02 81 03 09 47 81 02 95 05 81 03 09 51 26 ff 00 75 10 95 01 81 02 35 00 65 11 55 0e 05 01 09 30 26 a0 44 46 96 14 81 42 09 31 26 9a 26 46 95 0b 81 42 05 0d 75 08 95 01 15 00 09 48 26 5f 00 46 7c 14 81 02 09 49 25 35 46 7d 0b 81 02 45 00 65 00 55 00 c0 05 0d 09 22 a1 02 05 0d 95 01 75 01 25 01 09 42 81 02 81 03 09 47 81 02 95 05 81 03 09 51 26 ff 00 75 10 95 01 81 02 35 00 65 11 55 0e 05 01 09 30 26 a0 44 46 96 14 81 42 09 31 26 9a 26 46 95 0b 81 42 05 0d 75 08 95 01 15 00 09 48 26 5f 00 46 7c 14 81 02 09 49 25 35 46 7d 0b 81 02 45 00 65 00 55 00 c0 05 0d 09 22 a1 02 05 0d 95 01 75 01 25 01 09 42 81 02 81 03 09 47 81 02 95 05 81 03 09 51 26 ff 00 75 10 95 01 81 02 35 00 65 11 55 0e 05 01 09 30 26 a0 44 46 96 14 81 42 09 31 26 9a 26 46 95 0b 81 42 05 0d 75 08 95 01 15 00 09 48 26 5f 00 46 7c 14 81 02 09 49 25 35 46 7d 0b 81 02 45 00 65 00 55 00 c0 05 0d 09 22 a1 02 05 0d 95 01 75 01 25 01 09 42 81 02 81 03 09 47 81 02 95 05 81 03 09 51 26 ff 00 75 10 95 01 81 02 35 00 65 11 55 0e 05 01 09 30 26 a0 44 46 96 14 81 42 09 31 26 9a 26 46 95 0b 81 42 05 0d 75 08 95 01 15 00 09 48 26 5f 00 46 7c 14 81 02 09 49 25 35 46 7d 0b 81 02 45 00 65 00 55 00 c0 05 0d 09 22 a1 02 05 0d 95 01 75 01 25 01 09 42 81 02 81 03 09 47 81 02 95 05 81 03 09 51 26 ff 00 75 10 95 01 81 02 35 00 65 11 55 0e 05 01 09 30 26 a0 44 46 96 14 81 42 09 31 26 9a 26 46 95 0b 81 42 05 0d 75 08 95 01 15 00 09 48 26 5f 00 46 7c 14 81 02 09 49 25 35 46 7d 0b 81 02 45 00 65 00 55 00 c0 05 0d 27 ff ff 00 00 75 10 95 01 09 56 81 02 75 08 95 0e 81 03 09 55 26 ff 00 75 08 b1 02 85 0a 06 00 ff 09 c5 96 00 01 b1 02 c0 06 00 ff 09 01 a1 01 09 01 85 13 15 00 26 ff 00 75 08 95 3f 81 02 06 00 ff 09 01 15 00 26 ff 00 75 08 95 3f 91 02 c0", + input_info=(0x3, 0x056A, 0x0383), + ) + + def test_contact_id_0(self): + """ + Bring a finger in contact with the tablet, then hold it down and remove it. + + Ensure that even with contact ID = 0 which is usually given as an invalid + touch event by most tablets with the exception of a few, that given the + confidence bit is set to 1 it should process it as a valid touch to cover + the few tablets using contact ID = 0 as a valid touch value. + """ + uhdev = self.uhdev + evdev = uhdev.get_evdev() + + t0 = test_multitouch.Touch(0, 50, 100) + r = uhdev.event([t0]) + events = uhdev.next_sync_events() + self.debug_reports(r, uhdev, events) + + slot = self.get_slot(uhdev, t0, 0) + + assert libevdev.InputEvent(libevdev.EV_KEY.BTN_TOUCH, 1) in events + assert evdev.slots[slot][libevdev.EV_ABS.ABS_MT_TRACKING_ID] == 0 + assert evdev.slots[slot][libevdev.EV_ABS.ABS_MT_POSITION_X] == 50 + assert evdev.slots[slot][libevdev.EV_ABS.ABS_MT_POSITION_Y] == 100 + + t0.tipswitch = False + if uhdev.quirks is None or "VALID_IS_INRANGE" not in uhdev.quirks: + t0.inrange = False + r = uhdev.event([t0]) + events = uhdev.next_sync_events() + self.debug_reports(r, uhdev, events) + assert libevdev.InputEvent(libevdev.EV_KEY.BTN_TOUCH, 0) in events + assert evdev.slots[slot][libevdev.EV_ABS.ABS_MT_TRACKING_ID] == -1 + + def test_confidence_false(self): + """ + Bring a finger in contact with the tablet with confidence set to false. + + Ensure that the confidence bit being set to false should not result in a touch event. + """ + uhdev = self.uhdev + evdev = uhdev.get_evdev() + + t0 = test_multitouch.Touch(1, 50, 100) + t0.confidence = False + r = uhdev.event([t0]) + events = uhdev.next_sync_events() + self.debug_reports(r, uhdev, events) + + slot = self.get_slot(uhdev, t0, 0) + + assert not events
\ No newline at end of file diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index 294619ade49f..1c952d1401d4 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -8,7 +8,8 @@ export logfile=/dev/stdout export per_test_logging= # Defaults for "settings" file fields: -# "timeout" how many seconds to let each test run before failing. +# "timeout" how many seconds to let each test run before running +# over our soft timeout limit. export kselftest_default_timeout=45 # There isn't a shell-agnostic way to find the path of a sourced file, @@ -90,6 +91,14 @@ run_one() done < "$settings" fi + # Command line timeout overrides the settings file + if [ -n "$kselftest_override_timeout" ]; then + kselftest_timeout="$kselftest_override_timeout" + echo "# overriding timeout to $kselftest_timeout" >> "$logfile" + else + echo "# timeout set to $kselftest_timeout" >> "$logfile" + fi + TEST_HDR_MSG="selftests: $DIR: $BASENAME_TEST" echo "# $TEST_HDR_MSG" if [ ! -e "$TEST" ]; then diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index d8bff2005dfc..5fd49ad0c696 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -249,7 +249,7 @@ /** * FIXTURE_SETUP() - Prepares the setup function for the fixture. - * *_metadata* is included so that EXPECT_* and ASSERT_* work correctly. + * *_metadata* is included so that EXPECT_*, ASSERT_* etc. work correctly. * * @fixture_name: fixture name * @@ -275,7 +275,7 @@ /** * FIXTURE_TEARDOWN() - * *_metadata* is included so that EXPECT_* and ASSERT_* work correctly. + * *_metadata* is included so that EXPECT_*, ASSERT_* etc. work correctly. * * @fixture_name: fixture name * @@ -388,7 +388,7 @@ if (setjmp(_metadata->env) == 0) { \ fixture_name##_setup(_metadata, &self, variant->data); \ /* Let setup failure terminate early. */ \ - if (!_metadata->passed) \ + if (!_metadata->passed || _metadata->skip) \ return; \ _metadata->setup_completed = true; \ fixture_name##_##test_name(_metadata, &self, variant->data); \ diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 7a5ff646e7e7..4761b768b773 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -116,6 +116,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests TEST_GEN_PROGS_x86_64 += x86_64/amx_test TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test +TEST_GEN_PROGS_x86_64 += x86_64/recalc_apic_map_test TEST_GEN_PROGS_x86_64 += access_tracking_perf_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index d4e1f4af29d6..4f10055af2aa 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -48,6 +48,34 @@ struct reg_sublist { __u64 rejects_set_n; }; +struct feature_id_reg { + __u64 reg; + __u64 id_reg; + __u64 feat_shift; + __u64 feat_min; +}; + +static struct feature_id_reg feat_id_regs[] = { + { + ARM64_SYS_REG(3, 0, 2, 0, 3), /* TCR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ + 0, + 1 + }, + { + ARM64_SYS_REG(3, 0, 10, 2, 2), /* PIRE0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ + 4, + 1 + }, + { + ARM64_SYS_REG(3, 0, 10, 2, 3), /* PIR_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ + 4, + 1 + } +}; + struct vcpu_config { char *name; struct reg_sublist sublists[]; @@ -68,7 +96,8 @@ static int vcpu_configs_n; #define for_each_missing_reg(i) \ for ((i) = 0; (i) < blessed_n; ++(i)) \ - if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i])) + if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i])) \ + if (check_supported_feat_reg(vcpu, blessed_reg[i])) #define for_each_new_reg(i) \ for_each_reg_filtered(i) \ @@ -132,6 +161,25 @@ static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg) return false; } +static bool check_supported_feat_reg(struct kvm_vcpu *vcpu, __u64 reg) +{ + int i, ret; + __u64 data, feat_val; + + for (i = 0; i < ARRAY_SIZE(feat_id_regs); i++) { + if (feat_id_regs[i].reg == reg) { + ret = __vcpu_get_reg(vcpu, feat_id_regs[i].id_reg, &data); + if (ret < 0) + return false; + + feat_val = ((data >> feat_id_regs[i].feat_shift) & 0xf); + return feat_val >= feat_id_regs[i].feat_min; + } + } + + return true; +} + static const char *str_with_index(const char *template, __u64 index) { char *str, *p; @@ -843,12 +891,15 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 0, 2, 0, 0), /* TTBR0_EL1 */ ARM64_SYS_REG(3, 0, 2, 0, 1), /* TTBR1_EL1 */ ARM64_SYS_REG(3, 0, 2, 0, 2), /* TCR_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 3), /* TCR2_EL1 */ ARM64_SYS_REG(3, 0, 5, 1, 0), /* AFSR0_EL1 */ ARM64_SYS_REG(3, 0, 5, 1, 1), /* AFSR1_EL1 */ ARM64_SYS_REG(3, 0, 5, 2, 0), /* ESR_EL1 */ ARM64_SYS_REG(3, 0, 6, 0, 0), /* FAR_EL1 */ ARM64_SYS_REG(3, 0, 7, 4, 0), /* PAR_EL1 */ ARM64_SYS_REG(3, 0, 10, 2, 0), /* MAIR_EL1 */ + ARM64_SYS_REG(3, 0, 10, 2, 2), /* PIRE0_EL1 */ + ARM64_SYS_REG(3, 0, 10, 2, 3), /* PIR_EL1 */ ARM64_SYS_REG(3, 0, 10, 3, 0), /* AMAIR_EL1 */ ARM64_SYS_REG(3, 0, 12, 0, 0), /* VBAR_EL1 */ ARM64_SYS_REG(3, 0, 12, 1, 1), /* DISR_EL1 */ diff --git a/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c b/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c new file mode 100644 index 000000000000..4c416ebe7d66 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test edge cases and race conditions in kvm_recalculate_apic_map(). + */ + +#include <sys/ioctl.h> +#include <pthread.h> +#include <time.h> + +#include "processor.h" +#include "test_util.h" +#include "kvm_util.h" +#include "apic.h" + +#define TIMEOUT 5 /* seconds */ + +#define LAPIC_DISABLED 0 +#define LAPIC_X2APIC (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE) +#define MAX_XAPIC_ID 0xff + +static void *race(void *arg) +{ + struct kvm_lapic_state lapic = {}; + struct kvm_vcpu *vcpu = arg; + + while (1) { + /* Trigger kvm_recalculate_apic_map(). */ + vcpu_ioctl(vcpu, KVM_SET_LAPIC, &lapic); + pthread_testcancel(); + } + + return NULL; +} + +int main(void) +{ + struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + struct kvm_vcpu *vcpuN; + struct kvm_vm *vm; + pthread_t thread; + time_t t; + int i; + + kvm_static_assert(KVM_MAX_VCPUS > MAX_XAPIC_ID); + + /* + * Create the max number of vCPUs supported by selftests so that KVM + * has decent amount of work to do when recalculating the map, i.e. to + * make the problematic window large enough to hit. + */ + vm = vm_create_with_vcpus(KVM_MAX_VCPUS, NULL, vcpus); + + /* + * Enable x2APIC on all vCPUs so that KVM doesn't bail from the recalc + * due to vCPUs having aliased xAPIC IDs (truncated to 8 bits). + */ + for (i = 0; i < KVM_MAX_VCPUS; i++) + vcpu_set_msr(vcpus[i], MSR_IA32_APICBASE, LAPIC_X2APIC); + + ASSERT_EQ(pthread_create(&thread, NULL, race, vcpus[0]), 0); + + vcpuN = vcpus[KVM_MAX_VCPUS - 1]; + for (t = time(NULL) + TIMEOUT; time(NULL) < t;) { + vcpu_set_msr(vcpuN, MSR_IA32_APICBASE, LAPIC_X2APIC); + vcpu_set_msr(vcpuN, MSR_IA32_APICBASE, LAPIC_DISABLED); + } + + ASSERT_EQ(pthread_cancel(thread), 0); + ASSERT_EQ(pthread_join(thread, NULL), 0); + + kvm_vm_free(vm); + + return 0; +} diff --git a/tools/testing/selftests/landlock/config b/tools/testing/selftests/landlock/config index 0f0a65287bac..3dc9e438eab1 100644 --- a/tools/testing/selftests/landlock/config +++ b/tools/testing/selftests/landlock/config @@ -1,7 +1,10 @@ +CONFIG_CGROUPS=y +CONFIG_CGROUP_SCHED=y CONFIG_OVERLAY_FS=y -CONFIG_SECURITY_LANDLOCK=y -CONFIG_SECURITY_PATH=y +CONFIG_PROC_FS=y CONFIG_SECURITY=y +CONFIG_SECURITY_LANDLOCK=y CONFIG_SHMEM=y -CONFIG_TMPFS_XATTR=y +CONFIG_SYSFS=y CONFIG_TMPFS=y +CONFIG_TMPFS_XATTR=y diff --git a/tools/testing/selftests/landlock/config.um b/tools/testing/selftests/landlock/config.um new file mode 100644 index 000000000000..40937c0395d6 --- /dev/null +++ b/tools/testing/selftests/landlock/config.um @@ -0,0 +1 @@ +CONFIG_HOSTFS=y diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index b6c4be3faf7a..83d565569512 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -10,6 +10,7 @@ #define _GNU_SOURCE #include <fcntl.h> #include <linux/landlock.h> +#include <linux/magic.h> #include <sched.h> #include <stdio.h> #include <string.h> @@ -19,6 +20,7 @@ #include <sys/sendfile.h> #include <sys/stat.h> #include <sys/sysmacros.h> +#include <sys/vfs.h> #include <unistd.h> #include "common.h" @@ -107,8 +109,10 @@ static bool fgrep(FILE *const inf, const char *const str) return false; } -static bool supports_overlayfs(void) +static bool supports_filesystem(const char *const filesystem) { + char str[32]; + int len; bool res; FILE *const inf = fopen("/proc/filesystems", "r"); @@ -119,11 +123,33 @@ static bool supports_overlayfs(void) if (!inf) return true; - res = fgrep(inf, "nodev\toverlay\n"); + /* filesystem can be null for bind mounts. */ + if (!filesystem) + return true; + + len = snprintf(str, sizeof(str), "nodev\t%s\n", filesystem); + if (len >= sizeof(str)) + /* Ignores too-long filesystem names. */ + return true; + + res = fgrep(inf, str); fclose(inf); return res; } +static bool cwd_matches_fs(unsigned int fs_magic) +{ + struct statfs statfs_buf; + + if (!fs_magic) + return true; + + if (statfs(".", &statfs_buf)) + return true; + + return statfs_buf.f_type == fs_magic; +} + static void mkdir_parents(struct __test_metadata *const _metadata, const char *const path) { @@ -206,7 +232,26 @@ out: return err; } -static void prepare_layout(struct __test_metadata *const _metadata) +struct mnt_opt { + const char *const source; + const char *const type; + const unsigned long flags; + const char *const data; +}; + +const struct mnt_opt mnt_tmp = { + .type = "tmpfs", + .data = "size=4m,mode=700", +}; + +static int mount_opt(const struct mnt_opt *const mnt, const char *const target) +{ + return mount(mnt->source ?: mnt->type, target, mnt->type, mnt->flags, + mnt->data); +} + +static void prepare_layout_opt(struct __test_metadata *const _metadata, + const struct mnt_opt *const mnt) { disable_caps(_metadata); umask(0077); @@ -217,12 +262,28 @@ static void prepare_layout(struct __test_metadata *const _metadata) * for tests relying on pivot_root(2) and move_mount(2). */ set_cap(_metadata, CAP_SYS_ADMIN); - ASSERT_EQ(0, unshare(CLONE_NEWNS)); - ASSERT_EQ(0, mount("tmp", TMP_DIR, "tmpfs", 0, "size=4m,mode=700")); + ASSERT_EQ(0, unshare(CLONE_NEWNS | CLONE_NEWCGROUP)); + ASSERT_EQ(0, mount_opt(mnt, TMP_DIR)) + { + TH_LOG("Failed to mount the %s filesystem: %s", mnt->type, + strerror(errno)); + /* + * FIXTURE_TEARDOWN() is not called when FIXTURE_SETUP() + * failed, so we need to explicitly do a minimal cleanup to + * avoid cascading errors with other tests that don't depend on + * the same filesystem. + */ + remove_path(TMP_DIR); + } ASSERT_EQ(0, mount(NULL, TMP_DIR, NULL, MS_PRIVATE | MS_REC, NULL)); clear_cap(_metadata, CAP_SYS_ADMIN); } +static void prepare_layout(struct __test_metadata *const _metadata) +{ + prepare_layout_opt(_metadata, &mnt_tmp); +} + static void cleanup_layout(struct __test_metadata *const _metadata) { set_cap(_metadata, CAP_SYS_ADMIN); @@ -231,6 +292,20 @@ static void cleanup_layout(struct __test_metadata *const _metadata) EXPECT_EQ(0, remove_path(TMP_DIR)); } +/* clang-format off */ +FIXTURE(layout0) {}; +/* clang-format on */ + +FIXTURE_SETUP(layout0) +{ + prepare_layout(_metadata); +} + +FIXTURE_TEARDOWN(layout0) +{ + cleanup_layout(_metadata); +} + static void create_layout1(struct __test_metadata *const _metadata) { create_file(_metadata, file1_s1d1); @@ -248,7 +323,7 @@ static void create_layout1(struct __test_metadata *const _metadata) create_file(_metadata, file1_s3d1); create_directory(_metadata, dir_s3d2); set_cap(_metadata, CAP_SYS_ADMIN); - ASSERT_EQ(0, mount("tmp", dir_s3d2, "tmpfs", 0, "size=4m,mode=700")); + ASSERT_EQ(0, mount_opt(&mnt_tmp, dir_s3d2)); clear_cap(_metadata, CAP_SYS_ADMIN); ASSERT_EQ(0, mkdir(dir_s3d3, 0700)); @@ -262,11 +337,13 @@ static void remove_layout1(struct __test_metadata *const _metadata) EXPECT_EQ(0, remove_path(file1_s1d3)); EXPECT_EQ(0, remove_path(file1_s1d2)); EXPECT_EQ(0, remove_path(file1_s1d1)); + EXPECT_EQ(0, remove_path(dir_s1d3)); EXPECT_EQ(0, remove_path(file2_s2d3)); EXPECT_EQ(0, remove_path(file1_s2d3)); EXPECT_EQ(0, remove_path(file1_s2d2)); EXPECT_EQ(0, remove_path(file1_s2d1)); + EXPECT_EQ(0, remove_path(dir_s2d2)); EXPECT_EQ(0, remove_path(file1_s3d1)); EXPECT_EQ(0, remove_path(dir_s3d3)); @@ -510,7 +587,7 @@ TEST_F_FORK(layout1, file_and_dir_access_rights) ASSERT_EQ(0, close(ruleset_fd)); } -TEST_F_FORK(layout1, unknown_access_rights) +TEST_F_FORK(layout0, unknown_access_rights) { __u64 access_mask; @@ -608,7 +685,7 @@ static void enforce_ruleset(struct __test_metadata *const _metadata, } } -TEST_F_FORK(layout1, proc_nsfs) +TEST_F_FORK(layout0, proc_nsfs) { const struct rule rules[] = { { @@ -657,11 +734,11 @@ TEST_F_FORK(layout1, proc_nsfs) ASSERT_EQ(0, close(path_beneath.parent_fd)); } -TEST_F_FORK(layout1, unpriv) +TEST_F_FORK(layout0, unpriv) { const struct rule rules[] = { { - .path = dir_s1d2, + .path = TMP_DIR, .access = ACCESS_RO, }, {}, @@ -1301,12 +1378,12 @@ TEST_F_FORK(layout1, inherit_superset) ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY)); } -TEST_F_FORK(layout1, max_layers) +TEST_F_FORK(layout0, max_layers) { int i, err; const struct rule rules[] = { { - .path = dir_s1d2, + .path = TMP_DIR, .access = ACCESS_RO, }, {}, @@ -4030,21 +4107,24 @@ static const char (*merge_sub_files[])[] = { * └── work */ -/* clang-format off */ -FIXTURE(layout2_overlay) {}; -/* clang-format on */ +FIXTURE(layout2_overlay) +{ + bool skip_test; +}; FIXTURE_SETUP(layout2_overlay) { - if (!supports_overlayfs()) - SKIP(return, "overlayfs is not supported"); + if (!supports_filesystem("overlay")) { + self->skip_test = true; + SKIP(return, "overlayfs is not supported (setup)"); + } prepare_layout(_metadata); create_directory(_metadata, LOWER_BASE); set_cap(_metadata, CAP_SYS_ADMIN); /* Creates tmpfs mount points to get deterministic overlayfs. */ - ASSERT_EQ(0, mount("tmp", LOWER_BASE, "tmpfs", 0, "size=4m,mode=700")); + ASSERT_EQ(0, mount_opt(&mnt_tmp, LOWER_BASE)); clear_cap(_metadata, CAP_SYS_ADMIN); create_file(_metadata, lower_fl1); create_file(_metadata, lower_dl1_fl2); @@ -4054,7 +4134,7 @@ FIXTURE_SETUP(layout2_overlay) create_directory(_metadata, UPPER_BASE); set_cap(_metadata, CAP_SYS_ADMIN); - ASSERT_EQ(0, mount("tmp", UPPER_BASE, "tmpfs", 0, "size=4m,mode=700")); + ASSERT_EQ(0, mount_opt(&mnt_tmp, UPPER_BASE)); clear_cap(_metadata, CAP_SYS_ADMIN); create_file(_metadata, upper_fu1); create_file(_metadata, upper_du1_fu2); @@ -4075,8 +4155,8 @@ FIXTURE_SETUP(layout2_overlay) FIXTURE_TEARDOWN(layout2_overlay) { - if (!supports_overlayfs()) - SKIP(return, "overlayfs is not supported"); + if (self->skip_test) + SKIP(return, "overlayfs is not supported (teardown)"); EXPECT_EQ(0, remove_path(lower_do1_fl3)); EXPECT_EQ(0, remove_path(lower_dl1_fl2)); @@ -4109,8 +4189,8 @@ FIXTURE_TEARDOWN(layout2_overlay) TEST_F_FORK(layout2_overlay, no_restriction) { - if (!supports_overlayfs()) - SKIP(return, "overlayfs is not supported"); + if (self->skip_test) + SKIP(return, "overlayfs is not supported (test)"); ASSERT_EQ(0, test_open(lower_fl1, O_RDONLY)); ASSERT_EQ(0, test_open(lower_dl1, O_RDONLY)); @@ -4275,8 +4355,8 @@ TEST_F_FORK(layout2_overlay, same_content_different_file) size_t i; const char *path_entry; - if (!supports_overlayfs()) - SKIP(return, "overlayfs is not supported"); + if (self->skip_test) + SKIP(return, "overlayfs is not supported (test)"); /* Sets rules on base directories (i.e. outside overlay scope). */ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer1_base); @@ -4423,4 +4503,261 @@ TEST_F_FORK(layout2_overlay, same_content_different_file) } } +FIXTURE(layout3_fs) +{ + bool has_created_dir; + bool has_created_file; + char *dir_path; + bool skip_test; +}; + +FIXTURE_VARIANT(layout3_fs) +{ + const struct mnt_opt mnt; + const char *const file_path; + unsigned int cwd_fs_magic; +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(layout3_fs, tmpfs) { + /* clang-format on */ + .mnt = mnt_tmp, + .file_path = file1_s1d1, +}; + +FIXTURE_VARIANT_ADD(layout3_fs, ramfs) { + .mnt = { + .type = "ramfs", + .data = "mode=700", + }, + .file_path = TMP_DIR "/dir/file", +}; + +FIXTURE_VARIANT_ADD(layout3_fs, cgroup2) { + .mnt = { + .type = "cgroup2", + }, + .file_path = TMP_DIR "/test/cgroup.procs", +}; + +FIXTURE_VARIANT_ADD(layout3_fs, proc) { + .mnt = { + .type = "proc", + }, + .file_path = TMP_DIR "/self/status", +}; + +FIXTURE_VARIANT_ADD(layout3_fs, sysfs) { + .mnt = { + .type = "sysfs", + }, + .file_path = TMP_DIR "/kernel/notes", +}; + +FIXTURE_VARIANT_ADD(layout3_fs, hostfs) { + .mnt = { + .source = TMP_DIR, + .flags = MS_BIND, + }, + .file_path = TMP_DIR "/dir/file", + .cwd_fs_magic = HOSTFS_SUPER_MAGIC, +}; + +FIXTURE_SETUP(layout3_fs) +{ + struct stat statbuf; + const char *slash; + size_t dir_len; + + if (!supports_filesystem(variant->mnt.type) || + !cwd_matches_fs(variant->cwd_fs_magic)) { + self->skip_test = true; + SKIP(return, "this filesystem is not supported (setup)"); + } + + slash = strrchr(variant->file_path, '/'); + ASSERT_NE(slash, NULL); + dir_len = (size_t)slash - (size_t)variant->file_path; + ASSERT_LT(0, dir_len); + self->dir_path = malloc(dir_len + 1); + self->dir_path[dir_len] = '\0'; + strncpy(self->dir_path, variant->file_path, dir_len); + + prepare_layout_opt(_metadata, &variant->mnt); + + /* Creates directory when required. */ + if (stat(self->dir_path, &statbuf)) { + set_cap(_metadata, CAP_DAC_OVERRIDE); + EXPECT_EQ(0, mkdir(self->dir_path, 0700)) + { + TH_LOG("Failed to create directory \"%s\": %s", + self->dir_path, strerror(errno)); + free(self->dir_path); + self->dir_path = NULL; + } + self->has_created_dir = true; + clear_cap(_metadata, CAP_DAC_OVERRIDE); + } + + /* Creates file when required. */ + if (stat(variant->file_path, &statbuf)) { + int fd; + + set_cap(_metadata, CAP_DAC_OVERRIDE); + fd = creat(variant->file_path, 0600); + EXPECT_LE(0, fd) + { + TH_LOG("Failed to create file \"%s\": %s", + variant->file_path, strerror(errno)); + } + EXPECT_EQ(0, close(fd)); + self->has_created_file = true; + clear_cap(_metadata, CAP_DAC_OVERRIDE); + } +} + +FIXTURE_TEARDOWN(layout3_fs) +{ + if (self->skip_test) + SKIP(return, "this filesystem is not supported (teardown)"); + + if (self->has_created_file) { + set_cap(_metadata, CAP_DAC_OVERRIDE); + /* + * Don't check for error because the file might already + * have been removed (cf. release_inode test). + */ + unlink(variant->file_path); + clear_cap(_metadata, CAP_DAC_OVERRIDE); + } + + if (self->has_created_dir) { + set_cap(_metadata, CAP_DAC_OVERRIDE); + /* + * Don't check for error because the directory might already + * have been removed (cf. release_inode test). + */ + rmdir(self->dir_path); + clear_cap(_metadata, CAP_DAC_OVERRIDE); + } + free(self->dir_path); + self->dir_path = NULL; + + cleanup_layout(_metadata); +} + +static void layer3_fs_tag_inode(struct __test_metadata *const _metadata, + FIXTURE_DATA(layout3_fs) * self, + const FIXTURE_VARIANT(layout3_fs) * variant, + const char *const rule_path) +{ + const struct rule layer1_allow_read_file[] = { + { + .path = rule_path, + .access = LANDLOCK_ACCESS_FS_READ_FILE, + }, + {}, + }; + const struct landlock_ruleset_attr layer2_deny_everything_attr = { + .handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE, + }; + const char *const dev_null_path = "/dev/null"; + int ruleset_fd; + + if (self->skip_test) + SKIP(return, "this filesystem is not supported (test)"); + + /* Checks without Landlock. */ + EXPECT_EQ(0, test_open(dev_null_path, O_RDONLY | O_CLOEXEC)); + EXPECT_EQ(0, test_open(variant->file_path, O_RDONLY | O_CLOEXEC)); + + ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE, + layer1_allow_read_file); + EXPECT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + EXPECT_EQ(0, close(ruleset_fd)); + + EXPECT_EQ(EACCES, test_open(dev_null_path, O_RDONLY | O_CLOEXEC)); + EXPECT_EQ(0, test_open(variant->file_path, O_RDONLY | O_CLOEXEC)); + + /* Forbids directory reading. */ + ruleset_fd = + landlock_create_ruleset(&layer2_deny_everything_attr, + sizeof(layer2_deny_everything_attr), 0); + EXPECT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + EXPECT_EQ(0, close(ruleset_fd)); + + /* Checks with Landlock and forbidden access. */ + EXPECT_EQ(EACCES, test_open(dev_null_path, O_RDONLY | O_CLOEXEC)); + EXPECT_EQ(EACCES, test_open(variant->file_path, O_RDONLY | O_CLOEXEC)); +} + +/* Matrix of tests to check file hierarchy evaluation. */ + +TEST_F_FORK(layout3_fs, tag_inode_dir_parent) +{ + /* The current directory must not be the root for this test. */ + layer3_fs_tag_inode(_metadata, self, variant, "."); +} + +TEST_F_FORK(layout3_fs, tag_inode_dir_mnt) +{ + layer3_fs_tag_inode(_metadata, self, variant, TMP_DIR); +} + +TEST_F_FORK(layout3_fs, tag_inode_dir_child) +{ + layer3_fs_tag_inode(_metadata, self, variant, self->dir_path); +} + +TEST_F_FORK(layout3_fs, tag_inode_file) +{ + layer3_fs_tag_inode(_metadata, self, variant, variant->file_path); +} + +/* Light version of layout1.release_inodes */ +TEST_F_FORK(layout3_fs, release_inodes) +{ + const struct rule layer1[] = { + { + .path = TMP_DIR, + .access = LANDLOCK_ACCESS_FS_READ_DIR, + }, + {}, + }; + int ruleset_fd; + + if (self->skip_test) + SKIP(return, "this filesystem is not supported (test)"); + + /* Clean up for the teardown to not fail. */ + if (self->has_created_file) + EXPECT_EQ(0, remove_path(variant->file_path)); + + if (self->has_created_dir) + /* Don't check for error because of cgroup specificities. */ + remove_path(self->dir_path); + + ruleset_fd = + create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_DIR, layer1); + ASSERT_LE(0, ruleset_fd); + + /* Unmount the filesystem while it is being used by a ruleset. */ + set_cap(_metadata, CAP_SYS_ADMIN); + ASSERT_EQ(0, umount(TMP_DIR)); + clear_cap(_metadata, CAP_SYS_ADMIN); + + /* Replaces with a new mount point to simplify FIXTURE_TEARDOWN. */ + set_cap(_metadata, CAP_SYS_ADMIN); + ASSERT_EQ(0, mount_opt(&mnt_tmp, TMP_DIR)); + clear_cap(_metadata, CAP_SYS_ADMIN); + + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); + + /* Checks that access to the new mount point is denied. */ + ASSERT_EQ(EACCES, test_open(TMP_DIR, O_RDONLY)); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 05400462c779..d17854285f2b 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -44,10 +44,26 @@ endif selfdir = $(realpath $(dir $(filter %/lib.mk,$(MAKEFILE_LIST)))) top_srcdir = $(selfdir)/../../.. -ifeq ($(KHDR_INCLUDES),) -KHDR_INCLUDES := -isystem $(top_srcdir)/usr/include +ifeq ("$(origin O)", "command line") + KBUILD_OUTPUT := $(O) endif +ifneq ($(KBUILD_OUTPUT),) + # Make's built-in functions such as $(abspath ...), $(realpath ...) cannot + # expand a shell special character '~'. We use a somewhat tedious way here. + abs_objtree := $(shell cd $(top_srcdir) && mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd) + $(if $(abs_objtree),, \ + $(error failed to create output directory "$(KBUILD_OUTPUT)")) + # $(realpath ...) resolves symlinks + abs_objtree := $(realpath $(abs_objtree)) + KHDR_DIR := ${abs_objtree}/usr/include +else + abs_srctree := $(shell cd $(top_srcdir) && pwd) + KHDR_DIR := ${abs_srctree}/usr/include +endif + +KHDR_INCLUDES := -isystem $(KHDR_DIR) + # The following are built by lib.mk common compile rules. # TEST_CUSTOM_PROGS should be used by tests that require # custom build rule and prevent common build rule use. @@ -58,7 +74,25 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) -all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) +all: kernel_header_files $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) \ + $(TEST_GEN_FILES) + +kernel_header_files: + @ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null; \ + if [ $$? -ne 0 ]; then \ + RED='\033[1;31m'; \ + NOCOLOR='\033[0m'; \ + echo; \ + echo -e "$${RED}error$${NOCOLOR}: missing kernel header files."; \ + echo "Please run this and try again:"; \ + echo; \ + echo " cd $(top_srcdir)"; \ + echo " make headers"; \ + echo; \ + exit 1; \ + fi + +.PHONY: kernel_header_files define RUN_TESTS BASE_DIR="$(selfdir)"; \ diff --git a/tools/testing/selftests/media_tests/video_device_test.c b/tools/testing/selftests/media_tests/video_device_test.c index 0f6aef2e2593..2c44e115f2f0 100644 --- a/tools/testing/selftests/media_tests/video_device_test.c +++ b/tools/testing/selftests/media_tests/video_device_test.c @@ -37,45 +37,58 @@ #include <time.h> #include <linux/videodev2.h> -int main(int argc, char **argv) +#define PRIORITY_MAX 4 + +int priority_test(int fd) { - int opt; - char video_dev[256]; - int count; - struct v4l2_tuner vtuner; - struct v4l2_capability vcap; + /* This test will try to update the priority associated with a file descriptor */ + + enum v4l2_priority old_priority, new_priority, priority_to_compare; int ret; - int fd; + int result = 0; - if (argc < 2) { - printf("Usage: %s [-d </dev/videoX>]\n", argv[0]); - exit(-1); + ret = ioctl(fd, VIDIOC_G_PRIORITY, &old_priority); + if (ret < 0) { + printf("Failed to get priority: %s\n", strerror(errno)); + return -1; + } + new_priority = (old_priority + 1) % PRIORITY_MAX; + ret = ioctl(fd, VIDIOC_S_PRIORITY, &new_priority); + if (ret < 0) { + printf("Failed to set priority: %s\n", strerror(errno)); + return -1; + } + ret = ioctl(fd, VIDIOC_G_PRIORITY, &priority_to_compare); + if (ret < 0) { + printf("Failed to get new priority: %s\n", strerror(errno)); + result = -1; + goto cleanup; + } + if (priority_to_compare != new_priority) { + printf("Priority wasn't set - test failed\n"); + result = -1; } - /* Process arguments */ - while ((opt = getopt(argc, argv, "d:")) != -1) { - switch (opt) { - case 'd': - strncpy(video_dev, optarg, sizeof(video_dev) - 1); - video_dev[sizeof(video_dev)-1] = '\0'; - break; - default: - printf("Usage: %s [-d </dev/videoX>]\n", argv[0]); - exit(-1); - } +cleanup: + ret = ioctl(fd, VIDIOC_S_PRIORITY, &old_priority); + if (ret < 0) { + printf("Failed to restore priority: %s\n", strerror(errno)); + return -1; } + return result; +} + +int loop_test(int fd) +{ + int count; + struct v4l2_tuner vtuner; + struct v4l2_capability vcap; + int ret; /* Generate random number of interations */ srand((unsigned int) time(NULL)); count = rand(); - /* Open Video device and keep it open */ - fd = open(video_dev, O_RDWR); - if (fd == -1) { - printf("Video Device open errno %s\n", strerror(errno)); - exit(-1); - } - printf("\nNote:\n" "While test is running, remove the device or unbind\n" "driver and ensure there are no use after free errors\n" @@ -98,4 +111,46 @@ int main(int argc, char **argv) sleep(10); count--; } + return 0; +} + +int main(int argc, char **argv) +{ + int opt; + char video_dev[256]; + int fd; + int test_result; + + if (argc < 2) { + printf("Usage: %s [-d </dev/videoX>]\n", argv[0]); + exit(-1); + } + + /* Process arguments */ + while ((opt = getopt(argc, argv, "d:")) != -1) { + switch (opt) { + case 'd': + strncpy(video_dev, optarg, sizeof(video_dev) - 1); + video_dev[sizeof(video_dev)-1] = '\0'; + break; + default: + printf("Usage: %s [-d </dev/videoX>]\n", argv[0]); + exit(-1); + } + } + + /* Open Video device and keep it open */ + fd = open(video_dev, O_RDWR); + if (fd == -1) { + printf("Video Device open errno %s\n", strerror(errno)); + exit(-1); + } + + test_result = priority_test(fd); + if (!test_result) + printf("Priority test - PASSED\n"); + else + printf("Priority test - FAILED\n"); + + loop_test(fd); } diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 8917455f4f51..7e2a982383c0 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -39,3 +39,6 @@ local_config.h local_config.mk ksm_functional_tests mdwe_test +gup_longterm +mkdirty +va_high_addr_switch diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 23af4633f0f4..66d7c07dc177 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -5,12 +5,15 @@ LOCAL_HDRS += $(selfdir)/mm/local_config.h $(top_srcdir)/mm/gup_test.h include local_config.mk +ifeq ($(ARCH),) + ifeq ($(CROSS_COMPILE),) uname_M := $(shell uname -m 2>/dev/null || echo not) else uname_M := $(shell echo $(CROSS_COMPILE) | grep -o '^[a-z0-9]\+') endif -MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') +ARCH ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') +endif # Without this, failed build products remain, with up-to-date timestamps, # thus tricking Make (and you!) into believing that All Is Well, in subsequent @@ -29,11 +32,12 @@ MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/p # LDLIBS. MAKEFLAGS += --no-builtin-rules -CFLAGS = -Wall -I $(top_srcdir) -I $(top_srcdir)/tools/include/uapi $(EXTRA_CFLAGS) $(KHDR_INCLUDES) +CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) LDLIBS = -lrt -lpthread TEST_GEN_PROGS = cow TEST_GEN_PROGS += compaction_test +TEST_GEN_PROGS += gup_longterm TEST_GEN_PROGS += gup_test TEST_GEN_PROGS += hmm-tests TEST_GEN_PROGS += hugetlb-madvise @@ -65,7 +69,7 @@ TEST_GEN_PROGS += ksm_tests TEST_GEN_PROGS += ksm_functional_tests TEST_GEN_PROGS += mdwe_test -ifeq ($(MACHINE),x86_64) +ifeq ($(ARCH),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_program.c -m32) CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_64bit_program.c) CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_program.c -no-pie) @@ -87,13 +91,13 @@ TEST_GEN_PROGS += $(BINARIES_64) endif else -ifneq (,$(findstring $(MACHINE),ppc64)) +ifneq (,$(findstring $(ARCH),ppc64)) TEST_GEN_PROGS += protection_keys endif endif -ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sparc64 x86_64)) +ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sparc64 x86_64)) TEST_GEN_PROGS += va_high_addr_switch TEST_GEN_PROGS += virtual_address_range TEST_GEN_PROGS += write_to_hugetlbfs @@ -112,7 +116,7 @@ $(TEST_GEN_PROGS): vm_util.c $(OUTPUT)/uffd-stress: uffd-common.c $(OUTPUT)/uffd-unit-tests: uffd-common.c -ifeq ($(MACHINE),x86_64) +ifeq ($(ARCH),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) @@ -164,6 +168,8 @@ endif # IOURING_EXTRA_LIBS may get set in local_config.mk, or it may be left empty. $(OUTPUT)/cow: LDLIBS += $(IOURING_EXTRA_LIBS) +$(OUTPUT)/gup_longterm: LDLIBS += $(IOURING_EXTRA_LIBS) + $(OUTPUT)/mlock-random-test $(OUTPUT)/memfd_secret: LDLIBS += -lcap $(OUTPUT)/ksm_tests: LDLIBS += -lnuma diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index dc9d6fe86028..7324ce5363c0 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -14,8 +14,8 @@ #include <unistd.h> #include <errno.h> #include <fcntl.h> -#include <dirent.h> #include <assert.h> +#include <linux/mman.h> #include <sys/mman.h> #include <sys/ioctl.h> #include <sys/wait.h> @@ -30,13 +30,6 @@ #include "../kselftest.h" #include "vm_util.h" -#ifndef MADV_PAGEOUT -#define MADV_PAGEOUT 21 -#endif -#ifndef MADV_COLLAPSE -#define MADV_COLLAPSE 25 -#endif - static size_t pagesize; static int pagemap_fd; static size_t thpsize; @@ -70,31 +63,6 @@ static void detect_huge_zeropage(void) close(fd); } -static void detect_hugetlbsizes(void) -{ - DIR *dir = opendir("/sys/kernel/mm/hugepages/"); - - if (!dir) - return; - - while (nr_hugetlbsizes < ARRAY_SIZE(hugetlbsizes)) { - struct dirent *entry = readdir(dir); - size_t kb; - - if (!entry) - break; - if (entry->d_type != DT_DIR) - continue; - if (sscanf(entry->d_name, "hugepages-%zukB", &kb) != 1) - continue; - hugetlbsizes[nr_hugetlbsizes] = kb * 1024; - nr_hugetlbsizes++; - ksft_print_msg("[INFO] detected hugetlb size: %zu KiB\n", - kb); - } - closedir(dir); -} - static bool range_is_swapped(void *addr, size_t size) { for (; size; addr += pagesize, size -= pagesize) @@ -1717,7 +1685,8 @@ int main(int argc, char **argv) if (thpsize) ksft_print_msg("[INFO] detected THP size: %zu KiB\n", thpsize / 1024); - detect_hugetlbsizes(); + nr_hugetlbsizes = detect_hugetlb_page_sizes(hugetlbsizes, + ARRAY_SIZE(hugetlbsizes)); detect_huge_zeropage(); ksft_print_header(); diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c new file mode 100644 index 000000000000..d33d3e68ffab --- /dev/null +++ b/tools/testing/selftests/mm/gup_longterm.c @@ -0,0 +1,459 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * GUP long-term page pinning tests. + * + * Copyright 2023, Red Hat, Inc. + * + * Author(s): David Hildenbrand <david@redhat.com> + */ +#define _GNU_SOURCE +#include <stdlib.h> +#include <string.h> +#include <stdbool.h> +#include <stdint.h> +#include <unistd.h> +#include <errno.h> +#include <fcntl.h> +#include <assert.h> +#include <sys/mman.h> +#include <sys/ioctl.h> +#include <sys/vfs.h> +#include <linux/magic.h> +#include <linux/memfd.h> + +#include "local_config.h" +#ifdef LOCAL_CONFIG_HAVE_LIBURING +#include <liburing.h> +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ + +#include "../../../../mm/gup_test.h" +#include "../kselftest.h" +#include "vm_util.h" + +static size_t pagesize; +static int nr_hugetlbsizes; +static size_t hugetlbsizes[10]; +static int gup_fd; + +static __fsword_t get_fs_type(int fd) +{ + struct statfs fs; + int ret; + + do { + ret = fstatfs(fd, &fs); + } while (ret && errno == EINTR); + + return ret ? 0 : fs.f_type; +} + +static bool fs_is_unknown(__fsword_t fs_type) +{ + /* + * We only support some filesystems in our tests when dealing with + * R/W long-term pinning. For these filesystems, we can be fairly sure + * whether they support it or not. + */ + switch (fs_type) { + case TMPFS_MAGIC: + case HUGETLBFS_MAGIC: + case BTRFS_SUPER_MAGIC: + case EXT4_SUPER_MAGIC: + case XFS_SUPER_MAGIC: + return false; + default: + return true; + } +} + +static bool fs_supports_writable_longterm_pinning(__fsword_t fs_type) +{ + assert(!fs_is_unknown(fs_type)); + switch (fs_type) { + case TMPFS_MAGIC: + case HUGETLBFS_MAGIC: + return true; + default: + return false; + } +} + +enum test_type { + TEST_TYPE_RO, + TEST_TYPE_RO_FAST, + TEST_TYPE_RW, + TEST_TYPE_RW_FAST, +#ifdef LOCAL_CONFIG_HAVE_LIBURING + TEST_TYPE_IOURING, +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ +}; + +static void do_test(int fd, size_t size, enum test_type type, bool shared) +{ + __fsword_t fs_type = get_fs_type(fd); + bool should_work; + char *mem; + int ret; + + if (ftruncate(fd, size)) { + ksft_test_result_fail("ftruncate() failed\n"); + return; + } + + if (fallocate(fd, 0, 0, size)) { + if (size == pagesize) + ksft_test_result_fail("fallocate() failed\n"); + else + ksft_test_result_skip("need more free huge pages\n"); + return; + } + + mem = mmap(NULL, size, PROT_READ | PROT_WRITE, + shared ? MAP_SHARED : MAP_PRIVATE, fd, 0); + if (mem == MAP_FAILED) { + if (size == pagesize || shared) + ksft_test_result_fail("mmap() failed\n"); + else + ksft_test_result_skip("need more free huge pages\n"); + return; + } + + /* + * Fault in the page writable such that GUP-fast can eventually pin + * it immediately. + */ + memset(mem, 0, size); + + switch (type) { + case TEST_TYPE_RO: + case TEST_TYPE_RO_FAST: + case TEST_TYPE_RW: + case TEST_TYPE_RW_FAST: { + struct pin_longterm_test args; + const bool fast = type == TEST_TYPE_RO_FAST || + type == TEST_TYPE_RW_FAST; + const bool rw = type == TEST_TYPE_RW || + type == TEST_TYPE_RW_FAST; + + if (gup_fd < 0) { + ksft_test_result_skip("gup_test not available\n"); + break; + } + + if (rw && shared && fs_is_unknown(fs_type)) { + ksft_test_result_skip("Unknown filesystem\n"); + return; + } + /* + * R/O pinning or pinning in a private mapping is always + * expected to work. Otherwise, we expect long-term R/W pinning + * to only succeed for special fielesystems. + */ + should_work = !shared || !rw || + fs_supports_writable_longterm_pinning(fs_type); + + args.addr = (__u64)(uintptr_t)mem; + args.size = size; + args.flags = fast ? PIN_LONGTERM_TEST_FLAG_USE_FAST : 0; + args.flags |= rw ? PIN_LONGTERM_TEST_FLAG_USE_WRITE : 0; + ret = ioctl(gup_fd, PIN_LONGTERM_TEST_START, &args); + if (ret && errno == EINVAL) { + ksft_test_result_skip("PIN_LONGTERM_TEST_START failed\n"); + break; + } else if (ret && errno == EFAULT) { + ksft_test_result(!should_work, "Should have failed\n"); + break; + } else if (ret) { + ksft_test_result_fail("PIN_LONGTERM_TEST_START failed\n"); + break; + } + + if (ioctl(gup_fd, PIN_LONGTERM_TEST_STOP)) + ksft_print_msg("[INFO] PIN_LONGTERM_TEST_STOP failed\n"); + + /* + * TODO: if the kernel ever supports long-term R/W pinning on + * some previously unsupported filesystems, we might want to + * perform some additional tests for possible data corruptions. + */ + ksft_test_result(should_work, "Should have worked\n"); + break; + } +#ifdef LOCAL_CONFIG_HAVE_LIBURING + case TEST_TYPE_IOURING: { + struct io_uring ring; + struct iovec iov; + + /* io_uring always pins pages writable. */ + if (shared && fs_is_unknown(fs_type)) { + ksft_test_result_skip("Unknown filesystem\n"); + return; + } + should_work = !shared || + fs_supports_writable_longterm_pinning(fs_type); + + /* Skip on errors, as we might just lack kernel support. */ + ret = io_uring_queue_init(1, &ring, 0); + if (ret < 0) { + ksft_test_result_skip("io_uring_queue_init() failed\n"); + break; + } + /* + * Register the range as a fixed buffer. This will FOLL_WRITE | + * FOLL_PIN | FOLL_LONGTERM the range. + */ + iov.iov_base = mem; + iov.iov_len = size; + ret = io_uring_register_buffers(&ring, &iov, 1); + /* Only new kernels return EFAULT. */ + if (ret && (errno == ENOSPC || errno == EOPNOTSUPP || + errno == EFAULT)) { + ksft_test_result(!should_work, "Should have failed\n"); + } else if (ret) { + /* + * We might just lack support or have insufficient + * MEMLOCK limits. + */ + ksft_test_result_skip("io_uring_register_buffers() failed\n"); + } else { + ksft_test_result(should_work, "Should have worked\n"); + io_uring_unregister_buffers(&ring); + } + + io_uring_queue_exit(&ring); + break; + } +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ + default: + assert(false); + } + + munmap(mem, size); +} + +typedef void (*test_fn)(int fd, size_t size); + +static void run_with_memfd(test_fn fn, const char *desc) +{ + int fd; + + ksft_print_msg("[RUN] %s ... with memfd\n", desc); + + fd = memfd_create("test", 0); + if (fd < 0) { + ksft_test_result_fail("memfd_create() failed\n"); + return; + } + + fn(fd, pagesize); + close(fd); +} + +static void run_with_tmpfile(test_fn fn, const char *desc) +{ + FILE *file; + int fd; + + ksft_print_msg("[RUN] %s ... with tmpfile\n", desc); + + file = tmpfile(); + if (!file) { + ksft_test_result_fail("tmpfile() failed\n"); + return; + } + + fd = fileno(file); + if (fd < 0) { + ksft_test_result_fail("fileno() failed\n"); + return; + } + + fn(fd, pagesize); + fclose(file); +} + +static void run_with_local_tmpfile(test_fn fn, const char *desc) +{ + char filename[] = __FILE__"_tmpfile_XXXXXX"; + int fd; + + ksft_print_msg("[RUN] %s ... with local tmpfile\n", desc); + + fd = mkstemp(filename); + if (fd < 0) { + ksft_test_result_fail("mkstemp() failed\n"); + return; + } + + if (unlink(filename)) { + ksft_test_result_fail("unlink() failed\n"); + goto close; + } + + fn(fd, pagesize); +close: + close(fd); +} + +static void run_with_memfd_hugetlb(test_fn fn, const char *desc, + size_t hugetlbsize) +{ + int flags = MFD_HUGETLB; + int fd; + + ksft_print_msg("[RUN] %s ... with memfd hugetlb (%zu kB)\n", desc, + hugetlbsize / 1024); + + flags |= __builtin_ctzll(hugetlbsize) << MFD_HUGE_SHIFT; + + fd = memfd_create("test", flags); + if (fd < 0) { + ksft_test_result_skip("memfd_create() failed\n"); + return; + } + + fn(fd, hugetlbsize); + close(fd); +} + +struct test_case { + const char *desc; + test_fn fn; +}; + +static void test_shared_rw_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RW, true); +} + +static void test_shared_rw_fast_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RW_FAST, true); +} + +static void test_shared_ro_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RO, true); +} + +static void test_shared_ro_fast_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RO_FAST, true); +} + +static void test_private_rw_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RW, false); +} + +static void test_private_rw_fast_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RW_FAST, false); +} + +static void test_private_ro_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RO, false); +} + +static void test_private_ro_fast_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RO_FAST, false); +} + +#ifdef LOCAL_CONFIG_HAVE_LIBURING +static void test_shared_iouring(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_IOURING, true); +} + +static void test_private_iouring(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_IOURING, false); +} +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ + +static const struct test_case test_cases[] = { + { + "R/W longterm GUP pin in MAP_SHARED file mapping", + test_shared_rw_pin, + }, + { + "R/W longterm GUP-fast pin in MAP_SHARED file mapping", + test_shared_rw_fast_pin, + }, + { + "R/O longterm GUP pin in MAP_SHARED file mapping", + test_shared_ro_pin, + }, + { + "R/O longterm GUP-fast pin in MAP_SHARED file mapping", + test_shared_ro_fast_pin, + }, + { + "R/W longterm GUP pin in MAP_PRIVATE file mapping", + test_private_rw_pin, + }, + { + "R/W longterm GUP-fast pin in MAP_PRIVATE file mapping", + test_private_rw_fast_pin, + }, + { + "R/O longterm GUP pin in MAP_PRIVATE file mapping", + test_private_ro_pin, + }, + { + "R/O longterm GUP-fast pin in MAP_PRIVATE file mapping", + test_private_ro_fast_pin, + }, +#ifdef LOCAL_CONFIG_HAVE_LIBURING + { + "io_uring fixed buffer with MAP_SHARED file mapping", + test_shared_iouring, + }, + { + "io_uring fixed buffer with MAP_PRIVATE file mapping", + test_private_iouring, + }, +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ +}; + +static void run_test_case(struct test_case const *test_case) +{ + int i; + + run_with_memfd(test_case->fn, test_case->desc); + run_with_tmpfile(test_case->fn, test_case->desc); + run_with_local_tmpfile(test_case->fn, test_case->desc); + for (i = 0; i < nr_hugetlbsizes; i++) + run_with_memfd_hugetlb(test_case->fn, test_case->desc, + hugetlbsizes[i]); +} + +static int tests_per_test_case(void) +{ + return 3 + nr_hugetlbsizes; +} + +int main(int argc, char **argv) +{ + int i, err; + + pagesize = getpagesize(); + nr_hugetlbsizes = detect_hugetlb_page_sizes(hugetlbsizes, + ARRAY_SIZE(hugetlbsizes)); + + ksft_print_header(); + ksft_set_plan(ARRAY_SIZE(test_cases) * tests_per_test_case()); + + gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) + run_test_case(&test_cases[i]); + + err = ksft_get_fail_cnt(); + if (err) + ksft_exit_fail_msg("%d out of %d tests failed\n", + err, ksft_test_num()); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/mm/hugepage-shm.c b/tools/testing/selftests/mm/hugepage-shm.c index e2527f32005b..478bb1e989e9 100644 --- a/tools/testing/selftests/mm/hugepage-shm.c +++ b/tools/testing/selftests/mm/hugepage-shm.c @@ -35,10 +35,6 @@ #include <sys/shm.h> #include <sys/mman.h> -#ifndef SHM_HUGETLB -#define SHM_HUGETLB 04000 -#endif - #define LENGTH (256UL*1024*1024) #define dprintf(x) printf(x) diff --git a/tools/testing/selftests/mm/hugepage-vmemmap.c b/tools/testing/selftests/mm/hugepage-vmemmap.c index 557bdbd4f87e..5b354c209e93 100644 --- a/tools/testing/selftests/mm/hugepage-vmemmap.c +++ b/tools/testing/selftests/mm/hugepage-vmemmap.c @@ -13,10 +13,6 @@ #define MAP_LENGTH (2UL * 1024 * 1024) -#ifndef MAP_HUGETLB -#define MAP_HUGETLB 0x40000 /* arch specific */ -#endif - #define PAGE_SIZE 4096 #define PAGE_COMPOUND_HEAD (1UL << 15) diff --git a/tools/testing/selftests/mm/hugetlb-madvise.c b/tools/testing/selftests/mm/hugetlb-madvise.c index 28426e30d9bc..d55322df4b73 100644 --- a/tools/testing/selftests/mm/hugetlb-madvise.c +++ b/tools/testing/selftests/mm/hugetlb-madvise.c @@ -65,11 +65,15 @@ void write_fault_pages(void *addr, unsigned long nr_pages) void read_fault_pages(void *addr, unsigned long nr_pages) { - unsigned long dummy = 0; + volatile unsigned long dummy = 0; unsigned long i; - for (i = 0; i < nr_pages; i++) + for (i = 0; i < nr_pages; i++) { dummy += *((unsigned long *)(addr + (i * huge_page_size))); + + /* Prevent the compiler from optimizing out the entire loop: */ + asm volatile("" : "+r" (dummy)); + } } int main(int argc, char **argv) diff --git a/tools/testing/selftests/mm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c index 97adc0f34f9c..030667cb5533 100644 --- a/tools/testing/selftests/mm/khugepaged.c +++ b/tools/testing/selftests/mm/khugepaged.c @@ -11,6 +11,7 @@ #include <string.h> #include <unistd.h> +#include <linux/mman.h> #include <sys/mman.h> #include <sys/wait.h> #include <sys/types.h> @@ -22,16 +23,6 @@ #include "vm_util.h" -#ifndef MADV_PAGEOUT -#define MADV_PAGEOUT 21 -#endif -#ifndef MADV_POPULATE_READ -#define MADV_POPULATE_READ 22 -#endif -#ifndef MADV_COLLAPSE -#define MADV_COLLAPSE 25 -#endif - #define BASE_ADDR ((void *)(1UL << 30)) static unsigned long hpage_pmd_size; static unsigned long page_size; diff --git a/tools/testing/selftests/mm/madv_populate.c b/tools/testing/selftests/mm/madv_populate.c index 262eae6b58f2..60547245e479 100644 --- a/tools/testing/selftests/mm/madv_populate.c +++ b/tools/testing/selftests/mm/madv_populate.c @@ -20,13 +20,6 @@ #include "../kselftest.h" #include "vm_util.h" -#ifndef MADV_POPULATE_READ -#define MADV_POPULATE_READ 22 -#endif /* MADV_POPULATE_READ */ -#ifndef MADV_POPULATE_WRITE -#define MADV_POPULATE_WRITE 23 -#endif /* MADV_POPULATE_WRITE */ - /* * For now, we're using 2 MiB of private anonymous memory for all tests. */ diff --git a/tools/testing/selftests/mm/map_fixed_noreplace.c b/tools/testing/selftests/mm/map_fixed_noreplace.c index eed44322d1a6..598159f3df1f 100644 --- a/tools/testing/selftests/mm/map_fixed_noreplace.c +++ b/tools/testing/selftests/mm/map_fixed_noreplace.c @@ -13,10 +13,6 @@ #include <stdlib.h> #include <unistd.h> -#ifndef MAP_FIXED_NOREPLACE -#define MAP_FIXED_NOREPLACE 0x100000 -#endif - static void dump_maps(void) { char cmd[32]; diff --git a/tools/testing/selftests/mm/map_hugetlb.c b/tools/testing/selftests/mm/map_hugetlb.c index 312889edb84a..193281560b61 100644 --- a/tools/testing/selftests/mm/map_hugetlb.c +++ b/tools/testing/selftests/mm/map_hugetlb.c @@ -19,18 +19,6 @@ #define LENGTH (256UL*1024*1024) #define PROTECTION (PROT_READ | PROT_WRITE) -#ifndef MAP_HUGETLB -#define MAP_HUGETLB 0x40000 /* arch specific */ -#endif - -#ifndef MAP_HUGE_SHIFT -#define MAP_HUGE_SHIFT 26 -#endif - -#ifndef MAP_HUGE_MASK -#define MAP_HUGE_MASK 0x3f -#endif - /* Only ia64 requires this */ #ifdef __ia64__ #define ADDR (void *)(0x8000000000000000UL) diff --git a/tools/testing/selftests/mm/map_populate.c b/tools/testing/selftests/mm/map_populate.c index 6b8aeaa0bf7a..240f2d9dae7a 100644 --- a/tools/testing/selftests/mm/map_populate.c +++ b/tools/testing/selftests/mm/map_populate.c @@ -17,9 +17,7 @@ #include <string.h> #include <unistd.h> -#ifndef MMAP_SZ #define MMAP_SZ 4096 -#endif #define BUG_ON(condition, description) \ do { \ diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c index 1cec8425e3ca..379581567f27 100644 --- a/tools/testing/selftests/mm/migration.c +++ b/tools/testing/selftests/mm/migration.c @@ -95,12 +95,15 @@ int migrate(uint64_t *ptr, int n1, int n2) void *access_mem(void *ptr) { - uint64_t y = 0; + volatile uint64_t y = 0; volatile uint64_t *x = ptr; while (1) { pthread_testcancel(); y += *x; + + /* Prevent the compiler from optimizing out the writes to y: */ + asm volatile("" : "+r" (y)); } return NULL; diff --git a/tools/testing/selftests/mm/mlock-random-test.c b/tools/testing/selftests/mm/mlock-random-test.c index 782ea94dee2f..1fba77df7f62 100644 --- a/tools/testing/selftests/mm/mlock-random-test.c +++ b/tools/testing/selftests/mm/mlock-random-test.c @@ -7,6 +7,7 @@ #include <sys/resource.h> #include <sys/capability.h> #include <sys/mman.h> +#include <linux/mman.h> #include <fcntl.h> #include <string.h> #include <sys/ipc.h> diff --git a/tools/testing/selftests/mm/mlock2-tests.c b/tools/testing/selftests/mm/mlock2-tests.c index 11b2301f3aa3..80cddc0de206 100644 --- a/tools/testing/selftests/mm/mlock2-tests.c +++ b/tools/testing/selftests/mm/mlock2-tests.c @@ -50,7 +50,6 @@ static int get_vm_area(unsigned long addr, struct vm_boundaries *area) printf("cannot parse /proc/self/maps\n"); goto out; } - stop = '\0'; sscanf(line, "%lx", &start); sscanf(end_addr, "%lx", &end); diff --git a/tools/testing/selftests/mm/mlock2.h b/tools/testing/selftests/mm/mlock2.h index 2a6e76c226bc..8e02991b313c 100644 --- a/tools/testing/selftests/mm/mlock2.h +++ b/tools/testing/selftests/mm/mlock2.h @@ -4,14 +4,6 @@ #include <stdio.h> #include <stdlib.h> -#ifndef MLOCK_ONFAULT -#define MLOCK_ONFAULT 1 -#endif - -#ifndef MCL_ONFAULT -#define MCL_ONFAULT (MCL_FUTURE << 1) -#endif - static int mlock2_(void *start, size_t len, int flags) { #ifdef __NR_mlock2 diff --git a/tools/testing/selftests/mm/mrelease_test.c b/tools/testing/selftests/mm/mrelease_test.c index 37b6d33b9e84..dca21042b679 100644 --- a/tools/testing/selftests/mm/mrelease_test.c +++ b/tools/testing/selftests/mm/mrelease_test.c @@ -9,18 +9,10 @@ #include <stdlib.h> #include <sys/wait.h> #include <unistd.h> +#include <asm-generic/unistd.h> #include "vm_util.h" - #include "../kselftest.h" -#ifndef __NR_pidfd_open -#define __NR_pidfd_open -1 -#endif - -#ifndef __NR_process_mrelease -#define __NR_process_mrelease -1 -#endif - #define MB(x) (x << 20) #define MAX_SIZE_MB 1024 diff --git a/tools/testing/selftests/mm/mremap_dontunmap.c b/tools/testing/selftests/mm/mremap_dontunmap.c index f01dc4a85b0b..ca2359835e75 100644 --- a/tools/testing/selftests/mm/mremap_dontunmap.c +++ b/tools/testing/selftests/mm/mremap_dontunmap.c @@ -15,10 +15,6 @@ #include "../kselftest.h" -#ifndef MREMAP_DONTUNMAP -#define MREMAP_DONTUNMAP 4 -#endif - unsigned long page_size; char *page_buffer; diff --git a/tools/testing/selftests/mm/on-fault-limit.c b/tools/testing/selftests/mm/on-fault-limit.c index 634d87dfb2a4..b5888d613f34 100644 --- a/tools/testing/selftests/mm/on-fault-limit.c +++ b/tools/testing/selftests/mm/on-fault-limit.c @@ -6,10 +6,6 @@ #include <sys/time.h> #include <sys/resource.h> -#ifndef MCL_ONFAULT -#define MCL_ONFAULT (MCL_FUTURE << 1) -#endif - static int test_limit(void) { int ret = 1; diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h index 1ebb586b2fbc..ae5df26104e5 100644 --- a/tools/testing/selftests/mm/pkey-powerpc.h +++ b/tools/testing/selftests/mm/pkey-powerpc.h @@ -3,9 +3,6 @@ #ifndef _PKEYS_POWERPC_H #define _PKEYS_POWERPC_H -#ifndef SYS_mprotect_key -# define SYS_mprotect_key 386 -#endif #ifndef SYS_pkey_alloc # define SYS_pkey_alloc 384 # define SYS_pkey_free 385 diff --git a/tools/testing/selftests/mm/pkey-x86.h b/tools/testing/selftests/mm/pkey-x86.h index 72c14cd3ddc7..814758e109c0 100644 --- a/tools/testing/selftests/mm/pkey-x86.h +++ b/tools/testing/selftests/mm/pkey-x86.h @@ -5,29 +5,11 @@ #ifdef __i386__ -#ifndef SYS_mprotect_key -# define SYS_mprotect_key 380 -#endif - -#ifndef SYS_pkey_alloc -# define SYS_pkey_alloc 381 -# define SYS_pkey_free 382 -#endif - #define REG_IP_IDX REG_EIP #define si_pkey_offset 0x14 #else -#ifndef SYS_mprotect_key -# define SYS_mprotect_key 329 -#endif - -#ifndef SYS_pkey_alloc -# define SYS_pkey_alloc 330 -# define SYS_pkey_free 331 -#endif - #define REG_IP_IDX REG_RIP #define si_pkey_offset 0x20 @@ -132,7 +114,7 @@ int pkey_reg_xstate_offset(void) unsigned int ecx; unsigned int edx; int xstate_offset; - int xstate_size; + int xstate_size = 0; unsigned long XSTATE_CPUID = 0xd; int leaf; diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index 0381c34fdd56..48dc151f8fca 100644 --- a/tools/testing/selftests/mm/protection_keys.c +++ b/tools/testing/selftests/mm/protection_keys.c @@ -294,15 +294,6 @@ void pkey_access_deny(int pkey) pkey_disable_set(pkey, PKEY_DISABLE_ACCESS); } -/* Failed address bound checks: */ -#ifndef SEGV_BNDERR -# define SEGV_BNDERR 3 -#endif - -#ifndef SEGV_PKUERR -# define SEGV_PKUERR 4 -#endif - static char *si_code_str(int si_code) { if (si_code == SEGV_MAPERR) @@ -476,7 +467,7 @@ int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, ptr, size, orig_prot, pkey); errno = 0; - sret = syscall(SYS_mprotect_key, ptr, size, orig_prot, pkey); + sret = syscall(__NR_pkey_mprotect, ptr, size, orig_prot, pkey); if (errno) { dprintf2("SYS_mprotect_key sret: %d\n", sret); dprintf2("SYS_mprotect_key prot: 0x%lx\n", orig_prot); @@ -1684,7 +1675,7 @@ void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) return; } - sret = syscall(SYS_mprotect_key, ptr, size, PROT_READ, pkey); + sret = syscall(__NR_pkey_mprotect, ptr, size, PROT_READ, pkey); pkey_assert(sret < 0); } diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 4893eb60d96d..3f26f6e15b2a 100644 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -24,7 +24,7 @@ separated by spaces: - mmap tests for mmap(2) - gup_test - tests for gup using gup_test interface + tests for gup - userfaultfd tests for userfaultfd(2) - compaction @@ -196,6 +196,8 @@ CATEGORY="gup_test" run_test ./gup_test -a # Dump pages 0, 19, and 4096, using pin_user_pages: CATEGORY="gup_test" run_test ./gup_test -ct -F 0x1 0 19 0x1000 +CATEGORY="gup_test" run_test ./gup_longterm + CATEGORY="userfaultfd" run_test ./uffd-unit-tests uffd_stress_bin=./uffd-stress CATEGORY="userfaultfd" run_test ${uffd_stress_bin} anon 20 16 @@ -242,18 +244,18 @@ if [ $VADDR64 -ne 0 ]; then if [ "$ARCH" == "$ARCH_ARM64" ]; then echo 6 > /proc/sys/vm/nr_hugepages fi - CATEGORY="hugevm" run_test ./va_high_addr_switch.sh + CATEGORY="hugevm" run_test bash ./va_high_addr_switch.sh if [ "$ARCH" == "$ARCH_ARM64" ]; then echo $prev_nr_hugepages > /proc/sys/vm/nr_hugepages fi fi # VADDR64 # vmalloc stability smoke test -CATEGORY="vmalloc" run_test ./test_vmalloc.sh smoke +CATEGORY="vmalloc" run_test bash ./test_vmalloc.sh smoke CATEGORY="mremap" run_test ./mremap_dontunmap -CATEGORY="hmm" run_test ./test_hmm.sh smoke +CATEGORY="hmm" run_test bash ./test_hmm.sh smoke # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index 61c6250adf93..ba20d7504022 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -616,3 +616,62 @@ int copy_page(int ufd, unsigned long offset, bool wp) { return __copy_page(ufd, offset, false, wp); } + +int uffd_open_dev(unsigned int flags) +{ + int fd, uffd; + + fd = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC); + if (fd < 0) + return fd; + uffd = ioctl(fd, USERFAULTFD_IOC_NEW, flags); + close(fd); + + return uffd; +} + +int uffd_open_sys(unsigned int flags) +{ +#ifdef __NR_userfaultfd + return syscall(__NR_userfaultfd, flags); +#else + return -1; +#endif +} + +int uffd_open(unsigned int flags) +{ + int uffd = uffd_open_sys(flags); + + if (uffd < 0) + uffd = uffd_open_dev(flags); + + return uffd; +} + +int uffd_get_features(uint64_t *features) +{ + struct uffdio_api uffdio_api = { .api = UFFD_API, .features = 0 }; + /* + * This should by default work in most kernels; the feature list + * will be the same no matter what we pass in here. + */ + int fd = uffd_open(UFFD_USER_MODE_ONLY); + + if (fd < 0) + /* Maybe the kernel is older than user-only mode? */ + fd = uffd_open(0); + + if (fd < 0) + return fd; + + if (ioctl(fd, UFFDIO_API, &uffdio_api)) { + close(fd); + return -errno; + } + + *features = uffdio_api.features; + close(fd); + + return 0; +} diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index 6068f2346b86..197f5262fe0d 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -110,6 +110,11 @@ int __copy_page(int ufd, unsigned long offset, bool retry, bool wp); int copy_page(int ufd, unsigned long offset, bool wp); void *uffd_poll_thread(void *arg); +int uffd_open_dev(unsigned int flags); +int uffd_open_sys(unsigned int flags); +int uffd_open(unsigned int flags); +int uffd_get_features(uint64_t *features); + #define TEST_ANON 1 #define TEST_HUGETLB 2 #define TEST_SHMEM 3 diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index f1ad9eef1c3a..995ff13e74c7 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -88,16 +88,6 @@ static void uffd_stats_reset(struct uffd_args *args, unsigned long n_cpus) } } -static inline uint64_t uffd_minor_feature(void) -{ - if (test_type == TEST_HUGETLB && map_shared) - return UFFD_FEATURE_MINOR_HUGETLBFS; - else if (test_type == TEST_SHMEM) - return UFFD_FEATURE_MINOR_SHMEM; - else - return 0; -} - static void *locking_thread(void *arg) { unsigned long cpu = (unsigned long) arg; diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 269c86768a02..04d91f144d1c 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -109,12 +109,11 @@ static void uffd_test_pass(void) ksft_inc_fail_cnt(); \ } while (0) -#define uffd_test_skip(...) do { \ - printf("skipped [reason: "); \ - printf(__VA_ARGS__); \ - printf("]\n"); \ - ksft_inc_xskip_cnt(); \ - } while (0) +static void uffd_test_skip(const char *message) +{ + printf("skipped [reason: %s]\n", message); + ksft_inc_xskip_cnt(); +} /* * Returns 1 if specific userfaultfd supported, 0 otherwise. Note, we'll @@ -1149,7 +1148,6 @@ int main(int argc, char *argv[]) uffd_test_case_t *test; mem_type_t *mem_type; uffd_test_args_t args; - char test_name[128]; const char *errmsg; int has_uffd, opt; int i, j; @@ -1192,10 +1190,8 @@ int main(int argc, char *argv[]) mem_type = &mem_types[j]; if (!(test->mem_targets & mem_type->mem_flag)) continue; - snprintf(test_name, sizeof(test_name), - "%s on %s", test->name, mem_type->name); - uffd_test_start(test_name); + uffd_test_start("%s on %s", test->name, mem_type->name); if (!uffd_feature_supported(test)) { uffd_test_skip("feature missing"); continue; diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 9b06a5034808..558c9cd8901c 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <string.h> #include <fcntl.h> +#include <dirent.h> #include <sys/ioctl.h> #include <linux/userfaultfd.h> #include <sys/syscall.h> @@ -198,6 +199,32 @@ unsigned long default_huge_page_size(void) return hps; } +int detect_hugetlb_page_sizes(size_t sizes[], int max) +{ + DIR *dir = opendir("/sys/kernel/mm/hugepages/"); + int count = 0; + + if (!dir) + return 0; + + while (count < max) { + struct dirent *entry = readdir(dir); + size_t kb; + + if (!entry) + break; + if (entry->d_type != DT_DIR) + continue; + if (sscanf(entry->d_name, "hugepages-%zukB", &kb) != 1) + continue; + sizes[count++] = kb * 1024; + ksft_print_msg("[INFO] detected hugetlb page size: %zu KiB\n", + kb); + } + closedir(dir); + return count; +} + /* If `ioctls' non-NULL, the allowed ioctls will be returned into the var */ int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor, uint64_t *ioctls) @@ -242,62 +269,3 @@ int uffd_unregister(int uffd, void *addr, uint64_t len) return ret; } - -int uffd_open_dev(unsigned int flags) -{ - int fd, uffd; - - fd = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC); - if (fd < 0) - return fd; - uffd = ioctl(fd, USERFAULTFD_IOC_NEW, flags); - close(fd); - - return uffd; -} - -int uffd_open_sys(unsigned int flags) -{ -#ifdef __NR_userfaultfd - return syscall(__NR_userfaultfd, flags); -#else - return -1; -#endif -} - -int uffd_open(unsigned int flags) -{ - int uffd = uffd_open_sys(flags); - - if (uffd < 0) - uffd = uffd_open_dev(flags); - - return uffd; -} - -int uffd_get_features(uint64_t *features) -{ - struct uffdio_api uffdio_api = { .api = UFFD_API, .features = 0 }; - /* - * This should by default work in most kernels; the feature list - * will be the same no matter what we pass in here. - */ - int fd = uffd_open(UFFD_USER_MODE_ONLY); - - if (fd < 0) - /* Maybe the kernel is older than user-only mode? */ - fd = uffd_open(0); - - if (fd < 0) - return fd; - - if (ioctl(fd, UFFDIO_API, &uffdio_api)) { - close(fd); - return -errno; - } - - *features = uffdio_api.features; - close(fd); - - return 0; -} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index b950bd16083a..c7fa61f0dff8 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -44,14 +44,11 @@ bool check_huge_file(void *addr, int nr_hpages, uint64_t hpage_size); bool check_huge_shmem(void *addr, int nr_hpages, uint64_t hpage_size); int64_t allocate_transhuge(void *ptr, int pagemap_fd); unsigned long default_huge_page_size(void); +int detect_hugetlb_page_sizes(size_t sizes[], int max); int uffd_register(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor); int uffd_unregister(int uffd, void *addr, uint64_t len); -int uffd_open_dev(unsigned int flags); -int uffd_open_sys(unsigned int flags); -int uffd_open(unsigned int flags); -int uffd_get_features(uint64_t *features); int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor, uint64_t *ioctls); diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 80f06aa62034..501854a89cc0 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -8,8 +8,10 @@ diag_uid fin_ack_lat gro hwtstamp_config +io_uring_zerocopy_tx ioam6_parser ip_defrag +ip_local_port_range ipsec ipv6_flowlabel ipv6_flowlabel_mgr @@ -26,6 +28,8 @@ reuseport_bpf_cpu reuseport_bpf_numa reuseport_dualstack rxtimestamp +sctp_hello +scm_pidfd sk_bind_sendto_listen sk_connect_zero_addr socket diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index c12df57d5539..7f3ab2a93ed6 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -84,6 +84,7 @@ TEST_GEN_FILES += ip_local_port_range TEST_GEN_FILES += bind_wildcard TEST_PROGS += test_vxlan_mdb.sh TEST_PROGS += test_bridge_neigh_suppress.sh +TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_FILES := settings diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 1e4b397cece6..221c387a7d7f 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,3 +1,4 @@ -TEST_GEN_PROGS := diag_uid test_unix_oob unix_connect +CFLAGS += $(KHDR_INCLUDES) +TEST_GEN_PROGS := diag_uid test_unix_oob unix_connect scm_pidfd include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c new file mode 100644 index 000000000000..a86222143d79 --- /dev/null +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -0,0 +1,430 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +#define _GNU_SOURCE +#include <error.h> +#include <limits.h> +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/socket.h> +#include <linux/socket.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> +#include <sys/un.h> +#include <sys/signal.h> +#include <sys/types.h> +#include <sys/wait.h> + +#include "../../kselftest_harness.h" + +#define clean_errno() (errno == 0 ? "None" : strerror(errno)) +#define log_err(MSG, ...) \ + fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", __FILE__, __LINE__, \ + clean_errno(), ##__VA_ARGS__) + +#ifndef SCM_PIDFD +#define SCM_PIDFD 0x04 +#endif + +static void child_die() +{ + exit(1); +} + +static int safe_int(const char *numstr, int *converted) +{ + char *err = NULL; + long sli; + + errno = 0; + sli = strtol(numstr, &err, 0); + if (errno == ERANGE && (sli == LONG_MAX || sli == LONG_MIN)) + return -ERANGE; + + if (errno != 0 && sli == 0) + return -EINVAL; + + if (err == numstr || *err != '\0') + return -EINVAL; + + if (sli > INT_MAX || sli < INT_MIN) + return -ERANGE; + + *converted = (int)sli; + return 0; +} + +static int char_left_gc(const char *buffer, size_t len) +{ + size_t i; + + for (i = 0; i < len; i++) { + if (buffer[i] == ' ' || buffer[i] == '\t') + continue; + + return i; + } + + return 0; +} + +static int char_right_gc(const char *buffer, size_t len) +{ + int i; + + for (i = len - 1; i >= 0; i--) { + if (buffer[i] == ' ' || buffer[i] == '\t' || + buffer[i] == '\n' || buffer[i] == '\0') + continue; + + return i + 1; + } + + return 0; +} + +static char *trim_whitespace_in_place(char *buffer) +{ + buffer += char_left_gc(buffer, strlen(buffer)); + buffer[char_right_gc(buffer, strlen(buffer))] = '\0'; + return buffer; +} + +/* borrowed (with all helpers) from pidfd/pidfd_open_test.c */ +static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen) +{ + int ret; + char path[512]; + FILE *f; + size_t n = 0; + pid_t result = -1; + char *line = NULL; + + snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", pidfd); + + f = fopen(path, "re"); + if (!f) + return -1; + + while (getline(&line, &n, f) != -1) { + char *numstr; + + if (strncmp(line, key, keylen)) + continue; + + numstr = trim_whitespace_in_place(line + 4); + ret = safe_int(numstr, &result); + if (ret < 0) + goto out; + + break; + } + +out: + free(line); + fclose(f); + return result; +} + +static int cmsg_check(int fd) +{ + struct msghdr msg = { 0 }; + struct cmsghdr *cmsg; + struct iovec iov; + struct ucred *ucred = NULL; + int data = 0; + char control[CMSG_SPACE(sizeof(struct ucred)) + + CMSG_SPACE(sizeof(int))] = { 0 }; + int *pidfd = NULL; + pid_t parent_pid; + int err; + + iov.iov_base = &data; + iov.iov_len = sizeof(data); + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + err = recvmsg(fd, &msg, 0); + if (err < 0) { + log_err("recvmsg"); + return 1; + } + + if (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) { + log_err("recvmsg: truncated"); + return 1; + } + + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL; + cmsg = CMSG_NXTHDR(&msg, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_PIDFD) { + if (cmsg->cmsg_len < sizeof(*pidfd)) { + log_err("CMSG parse: SCM_PIDFD wrong len"); + return 1; + } + + pidfd = (void *)CMSG_DATA(cmsg); + } + + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_CREDENTIALS) { + if (cmsg->cmsg_len < sizeof(*ucred)) { + log_err("CMSG parse: SCM_CREDENTIALS wrong len"); + return 1; + } + + ucred = (void *)CMSG_DATA(cmsg); + } + } + + /* send(pfd, "x", sizeof(char), 0) */ + if (data != 'x') { + log_err("recvmsg: data corruption"); + return 1; + } + + if (!pidfd) { + log_err("CMSG parse: SCM_PIDFD not found"); + return 1; + } + + if (!ucred) { + log_err("CMSG parse: SCM_CREDENTIALS not found"); + return 1; + } + + /* pidfd from SCM_PIDFD should point to the parent process PID */ + parent_pid = + get_pid_from_fdinfo_file(*pidfd, "Pid:", sizeof("Pid:") - 1); + if (parent_pid != getppid()) { + log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid()); + return 1; + } + + return 0; +} + +struct sock_addr { + char sock_name[32]; + struct sockaddr_un listen_addr; + socklen_t addrlen; +}; + +FIXTURE(scm_pidfd) +{ + int server; + pid_t client_pid; + int startup_pipe[2]; + struct sock_addr server_addr; + struct sock_addr *client_addr; +}; + +FIXTURE_VARIANT(scm_pidfd) +{ + int type; + bool abstract; +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, stream_pathname) +{ + .type = SOCK_STREAM, + .abstract = 0, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, stream_abstract) +{ + .type = SOCK_STREAM, + .abstract = 1, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, dgram_pathname) +{ + .type = SOCK_DGRAM, + .abstract = 0, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, dgram_abstract) +{ + .type = SOCK_DGRAM, + .abstract = 1, +}; + +FIXTURE_SETUP(scm_pidfd) +{ + self->client_addr = mmap(NULL, sizeof(*self->client_addr), PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(MAP_FAILED, self->client_addr); +} + +FIXTURE_TEARDOWN(scm_pidfd) +{ + close(self->server); + + kill(self->client_pid, SIGKILL); + waitpid(self->client_pid, NULL, 0); + + if (!variant->abstract) { + unlink(self->server_addr.sock_name); + unlink(self->client_addr->sock_name); + } +} + +static void fill_sockaddr(struct sock_addr *addr, bool abstract) +{ + char *sun_path_buf = (char *)&addr->listen_addr.sun_path; + + addr->listen_addr.sun_family = AF_UNIX; + addr->addrlen = offsetof(struct sockaddr_un, sun_path); + snprintf(addr->sock_name, sizeof(addr->sock_name), "scm_pidfd_%d", getpid()); + addr->addrlen += strlen(addr->sock_name); + if (abstract) { + *sun_path_buf = '\0'; + addr->addrlen++; + sun_path_buf++; + } else { + unlink(addr->sock_name); + } + memcpy(sun_path_buf, addr->sock_name, strlen(addr->sock_name)); +} + +static void client(FIXTURE_DATA(scm_pidfd) *self, + const FIXTURE_VARIANT(scm_pidfd) *variant) +{ + int err; + int cfd; + socklen_t len; + struct ucred peer_cred; + int peer_pidfd; + pid_t peer_pid; + int on = 0; + + cfd = socket(AF_UNIX, variant->type, 0); + if (cfd < 0) { + log_err("socket"); + child_die(); + } + + if (variant->type == SOCK_DGRAM) { + fill_sockaddr(self->client_addr, variant->abstract); + + if (bind(cfd, (struct sockaddr *)&self->client_addr->listen_addr, self->client_addr->addrlen)) { + log_err("bind"); + child_die(); + } + } + + if (connect(cfd, (struct sockaddr *)&self->server_addr.listen_addr, + self->server_addr.addrlen) != 0) { + log_err("connect"); + child_die(); + } + + on = 1; + if (setsockopt(cfd, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) { + log_err("Failed to set SO_PASSCRED"); + child_die(); + } + + if (setsockopt(cfd, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) { + log_err("Failed to set SO_PASSPIDFD"); + child_die(); + } + + close(self->startup_pipe[1]); + + if (cmsg_check(cfd)) { + log_err("cmsg_check failed"); + child_die(); + } + + /* skip further for SOCK_DGRAM as it's not applicable */ + if (variant->type == SOCK_DGRAM) + return; + + len = sizeof(peer_cred); + if (getsockopt(cfd, SOL_SOCKET, SO_PEERCRED, &peer_cred, &len)) { + log_err("Failed to get SO_PEERCRED"); + child_die(); + } + + len = sizeof(peer_pidfd); + if (getsockopt(cfd, SOL_SOCKET, SO_PEERPIDFD, &peer_pidfd, &len)) { + log_err("Failed to get SO_PEERPIDFD"); + child_die(); + } + + /* pid from SO_PEERCRED should point to the parent process PID */ + if (peer_cred.pid != getppid()) { + log_err("peer_cred.pid != getppid(): %d != %d", peer_cred.pid, getppid()); + child_die(); + } + + peer_pid = get_pid_from_fdinfo_file(peer_pidfd, + "Pid:", sizeof("Pid:") - 1); + if (peer_pid != peer_cred.pid) { + log_err("peer_pid != peer_cred.pid: %d != %d", peer_pid, peer_cred.pid); + child_die(); + } +} + +TEST_F(scm_pidfd, test) +{ + int err; + int pfd; + int child_status = 0; + + self->server = socket(AF_UNIX, variant->type, 0); + ASSERT_NE(-1, self->server); + + fill_sockaddr(&self->server_addr, variant->abstract); + + err = bind(self->server, (struct sockaddr *)&self->server_addr.listen_addr, self->server_addr.addrlen); + ASSERT_EQ(0, err); + + if (variant->type == SOCK_STREAM) { + err = listen(self->server, 1); + ASSERT_EQ(0, err); + } + + err = pipe(self->startup_pipe); + ASSERT_NE(-1, err); + + self->client_pid = fork(); + ASSERT_NE(-1, self->client_pid); + if (self->client_pid == 0) { + close(self->server); + close(self->startup_pipe[0]); + client(self, variant); + exit(0); + } + close(self->startup_pipe[1]); + + if (variant->type == SOCK_STREAM) { + pfd = accept(self->server, NULL, NULL); + ASSERT_NE(-1, pfd); + } else { + pfd = self->server; + } + + /* wait until the child arrives at checkpoint */ + read(self->startup_pipe[0], &err, sizeof(int)); + close(self->startup_pipe[0]); + + if (variant->type == SOCK_DGRAM) { + err = sendto(pfd, "x", sizeof(char), 0, (struct sockaddr *)&self->client_addr->listen_addr, self->client_addr->addrlen); + ASSERT_NE(-1, err); + } else { + err = send(pfd, "x", sizeof(char), 0); + ASSERT_NE(-1, err); + } + + close(pfd); + waitpid(self->client_pid, &child_status, 0); + ASSERT_EQ(0, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 21ca91473c09..d32a14ba069a 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -92,6 +92,13 @@ NSC_CMD="ip netns exec ${NSC}" which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) +# Check if FIPS mode is enabled +if [ -f /proc/sys/crypto/fips_enabled ]; then + fips_enabled=`cat /proc/sys/crypto/fips_enabled` +else + fips_enabled=0 +fi + ################################################################################ # utilities @@ -585,6 +592,20 @@ ipv4_ping_novrf() done # + # out, but don't use gateway if peer is not on link + # + a=${NSB_IP} + log_start + run_cmd ping -c 1 -w 1 -r ${a} + log_test_addr ${a} $? 0 "ping out (don't route), peer on link" + + a=${NSB_LO_IP} + log_start + show_hint "Fails since peer is not on link" + run_cmd ping -c 1 -w 1 -r ${a} + log_test_addr ${a} $? 1 "ping out (don't route), peer not on link" + + # # in # for a in ${NSA_IP} ${NSA_LO_IP} @@ -1098,6 +1119,59 @@ test_ipv4_md5_vrf__global_server__bind_ifindex0() set_sysctl net.ipv4.tcp_l3mdev_accept="$old_tcp_l3mdev_accept" } +ipv4_tcp_dontroute() +{ + local syncookies=$1 + local nsa_syncookies + local nsb_syncookies + local a + + # + # Link local connection tests (SO_DONTROUTE). + # Connections should succeed only when the remote IP address is + # on link (doesn't need to be routed through a gateway). + # + + nsa_syncookies=$(ip netns exec "${NSA}" sysctl -n net.ipv4.tcp_syncookies) + nsb_syncookies=$(ip netns exec "${NSB}" sysctl -n net.ipv4.tcp_syncookies) + ip netns exec "${NSA}" sysctl -wq net.ipv4.tcp_syncookies=${syncookies} + ip netns exec "${NSB}" sysctl -wq net.ipv4.tcp_syncookies=${syncookies} + + # Test with eth1 address (on link). + + a=${NSB_IP} + log_start + do_run_cmd nettest -B -N "${NSA}" -O "${NSB}" -r ${a} --client-dontroute + log_test_addr ${a} $? 0 "SO_DONTROUTE client, syncookies=${syncookies}" + + a=${NSB_IP} + log_start + do_run_cmd nettest -B -N "${NSA}" -O "${NSB}" -r ${a} --server-dontroute + log_test_addr ${a} $? 0 "SO_DONTROUTE server, syncookies=${syncookies}" + + # Test with loopback address (routed). + # + # The client would use the eth1 address as source IP by default. + # Therefore, we need to use the -c option here, to force the use of the + # routed (loopback) address as source IP (so that the server will try + # to respond to a routed address and not a link local one). + + a=${NSB_LO_IP} + log_start + show_hint "Should fail 'Network is unreachable' since server is not on link" + do_run_cmd nettest -B -N "${NSA}" -O "${NSB}" -c "${NSA_LO_IP}" -r ${a} --client-dontroute + log_test_addr ${a} $? 1 "SO_DONTROUTE client, syncookies=${syncookies}" + + a=${NSB_LO_IP} + log_start + show_hint "Should timeout since server cannot respond (client is not on link)" + do_run_cmd nettest -B -N "${NSA}" -O "${NSB}" -c "${NSA_LO_IP}" -r ${a} --server-dontroute + log_test_addr ${a} $? 2 "SO_DONTROUTE server, syncookies=${syncookies}" + + ip netns exec "${NSB}" sysctl -wq net.ipv4.tcp_syncookies=${nsb_syncookies} + ip netns exec "${NSA}" sysctl -wq net.ipv4.tcp_syncookies=${nsa_syncookies} +} + ipv4_tcp_novrf() { local a @@ -1216,7 +1290,10 @@ ipv4_tcp_novrf() run_cmd nettest -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 1 "No server, device client, local conn" - ipv4_tcp_md5_novrf + [ "$fips_enabled" = "1" ] || ipv4_tcp_md5_novrf + + ipv4_tcp_dontroute 0 + ipv4_tcp_dontroute 2 } ipv4_tcp_vrf() @@ -1270,9 +1347,11 @@ ipv4_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection" # run MD5 tests - setup_vrf_dup - ipv4_tcp_md5 - cleanup_vrf_dup + if [ "$fips_enabled" = "0" ]; then + setup_vrf_dup + ipv4_tcp_md5 + cleanup_vrf_dup + fi # # enable VRF global server @@ -1585,6 +1664,23 @@ ipv4_udp_novrf() log_start run_cmd nettest -D -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 2 "No server, device client, local conn" + + # + # Link local connection tests (SO_DONTROUTE). + # Connections should succeed only when the remote IP address is + # on link (doesn't need to be routed through a gateway). + # + + a=${NSB_IP} + log_start + do_run_cmd nettest -B -D -N "${NSA}" -O "${NSB}" -r ${a} --client-dontroute + log_test_addr ${a} $? 0 "SO_DONTROUTE client" + + a=${NSB_LO_IP} + log_start + show_hint "Should fail 'Network is unreachable' since server is not on link" + do_run_cmd nettest -B -D -N "${NSA}" -O "${NSB}" -r ${a} --client-dontroute + log_test_addr ${a} $? 1 "SO_DONTROUTE client" } ipv4_udp_vrf() @@ -2772,7 +2868,7 @@ ipv6_tcp_novrf() log_test_addr ${a} $? 1 "No server, device client, local conn" done - ipv6_tcp_md5_novrf + [ "$fips_enabled" = "1" ] || ipv6_tcp_md5_novrf } ipv6_tcp_vrf() @@ -2842,9 +2938,11 @@ ipv6_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection" # run MD5 tests - setup_vrf_dup - ipv6_tcp_md5 - cleanup_vrf_dup + if [ "$fips_enabled" = "0" ]; then + setup_vrf_dup + ipv6_tcp_md5 + cleanup_vrf_dup + fi # # enable VRF global server diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index a47b26ab48f2..0f5e88c8f4ff 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -2283,7 +2283,7 @@ EOF ################################################################################ # main -while getopts :t:pP46hv:w: o +while getopts :t:pP46hvw: o do case $o in t) TESTS=$OPTARG;; diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 7da8ec838c63..35d89dfa6f11 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -68,7 +68,7 @@ setup() cleanup() { $IP link del dev dummy0 &> /dev/null - ip netns del ns1 + ip netns del ns1 &> /dev/null ip netns del ns2 &> /dev/null } diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index a474c60fe348..770efbe24f0d 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -83,6 +83,8 @@ TEST_PROGS = bridge_igmp.sh \ tc_chains.sh \ tc_flower_router.sh \ tc_flower.sh \ + tc_flower_l2_miss.sh \ + tc_flower_cfm.sh \ tc_mpls_l2vpn.sh \ tc_police.sh \ tc_shblocks.sh \ diff --git a/tools/testing/selftests/net/forwarding/dual_vxlan_bridge.sh b/tools/testing/selftests/net/forwarding/dual_vxlan_bridge.sh index 5148d97a5df8..68ee92df3e07 100755 --- a/tools/testing/selftests/net/forwarding/dual_vxlan_bridge.sh +++ b/tools/testing/selftests/net/forwarding/dual_vxlan_bridge.sh @@ -132,6 +132,7 @@ switch_create() #### BR1 #### ip link add name br1 type bridge vlan_filtering 1 \ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br1 addrgenmode none # Make sure the bridge uses the MAC address of the local port and not # that of the VxLAN's device. ip link set dev br1 address $(mac_get $swp1) diff --git a/tools/testing/selftests/net/forwarding/hw_stats_l3.sh b/tools/testing/selftests/net/forwarding/hw_stats_l3.sh index 432fe8469851..48584a51388f 100755 --- a/tools/testing/selftests/net/forwarding/hw_stats_l3.sh +++ b/tools/testing/selftests/net/forwarding/hw_stats_l3.sh @@ -84,8 +84,9 @@ h2_destroy() router_rp1_200_create() { - ip link add name $rp1.200 up \ - link $rp1 addrgenmode eui64 type vlan id 200 + ip link add name $rp1.200 link $rp1 type vlan id 200 + ip link set dev $rp1.200 addrgenmode eui64 + ip link set dev $rp1.200 up ip address add dev $rp1.200 192.0.2.2/28 ip address add dev $rp1.200 2001:db8:1::2/64 ip stats set dev $rp1.200 l3_stats on @@ -256,9 +257,11 @@ reapply_config() router_rp1_200_destroy - ip link add name $rp1.200 link $rp1 addrgenmode none type vlan id 200 + ip link add name $rp1.200 link $rp1 type vlan id 200 + ip link set dev $rp1.200 addrgenmode none ip stats set dev $rp1.200 l3_stats on - ip link set dev $rp1.200 up addrgenmode eui64 + ip link set dev $rp1.200 addrgenmode eui64 + ip link set dev $rp1.200 up ip address add dev $rp1.200 192.0.2.2/28 ip address add dev $rp1.200 2001:db8:1::2/64 } diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh index 360ca133bead..6c257ec03756 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh @@ -98,6 +98,7 @@ switch_create() # Bridge between H1 and H2. ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 addrgenmode none ip link set dev br1 up ip link set dev $swp1 master br1 diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh index c5095da7f6bf..04fd14b0a9b7 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh @@ -65,7 +65,8 @@ setup_prepare() vrf_prepare mirror_gre_topo_create - ip link add name br2 type bridge vlan_filtering 0 + ip link add name br2 address $(mac_get $swp3) \ + type bridge vlan_filtering 0 ip link set dev br2 up ip link set dev $swp3 master br2 @@ -93,12 +94,16 @@ cleanup() test_gretap() { + ip neigh replace 192.0.2.130 lladdr $(mac_get $h3) \ + nud permanent dev br2 full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap" full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap" } test_ip6gretap() { + ip neigh replace 2001:db8:2::2 lladdr $(mac_get $h3) \ + nud permanent dev br2 full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap" full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap" } diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh index 1b27f2b0f196..f35313c76fac 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh @@ -35,7 +35,8 @@ setup_prepare() vrf_prepare mirror_gre_topo_create - ip link add name br2 type bridge vlan_filtering 0 + ip link add name br2 address $(mac_get $swp3) \ + type bridge vlan_filtering 0 ip link set dev br2 up vlan_create $swp3 555 diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh index 9ff22f28032d..0cf4c47a46f9 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh @@ -90,12 +90,16 @@ cleanup() test_gretap() { + ip neigh replace 192.0.2.130 lladdr $(mac_get $h3) \ + nud permanent dev br1 full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap" full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap" } test_ip6gretap() { + ip neigh replace 2001:db8:2::2 lladdr $(mac_get $h3) \ + nud permanent dev br1 full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap" full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap" } diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh index 91e431cd919e..c53148b1dc63 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh @@ -140,7 +140,8 @@ switch_create() ip link set dev $swp3 up ip link set dev $swp4 up - ip link add name br1 type bridge vlan_filtering 1 + ip link add name br1 address $(mac_get $swp3) \ + type bridge vlan_filtering 1 team_create lag loadbalance $swp3 $swp4 ip link set dev lag master br1 diff --git a/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh b/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh index 04979e5962e7..bb1adbb7b98a 100644 --- a/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh +++ b/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh @@ -60,6 +60,7 @@ mirror_topo_switch_create() ip link set dev $swp3 up ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 addrgenmode none ip link set dev br1 up ip link set dev $swp1 master br1 diff --git a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh index 64fbd211d907..af008fbf2725 100755 --- a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh +++ b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh @@ -60,7 +60,9 @@ h2_destroy() switch_create() { - ip link add name br1 up type bridge vlan_filtering 1 + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 addrgenmode none + ip link set dev br1 up ip link set dev $swp1 master br1 ip link set dev $swp1 up ip link set dev $swp2 master br1 diff --git a/tools/testing/selftests/net/forwarding/q_in_vni.sh b/tools/testing/selftests/net/forwarding/q_in_vni.sh index 4c50c0234bce..798b13525c02 100755 --- a/tools/testing/selftests/net/forwarding/q_in_vni.sh +++ b/tools/testing/selftests/net/forwarding/q_in_vni.sh @@ -137,6 +137,7 @@ switch_create() { ip link add name br1 type bridge vlan_filtering 1 vlan_protocol 802.1ad \ vlan_default_pvid 0 mcast_snooping 0 + ip link set dev br1 addrgenmode none # Make sure the bridge uses the MAC address of the local port and not # that of the VxLAN's device. ip link set dev br1 address $(mac_get $swp1) diff --git a/tools/testing/selftests/net/forwarding/router_bridge.sh b/tools/testing/selftests/net/forwarding/router_bridge.sh index ebc596a272f7..8ce0aed54ece 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge.sh @@ -38,7 +38,8 @@ h2_destroy() router_create() { - ip link add name br1 type bridge vlan_filtering 1 + ip link add name br1 address $(mac_get $swp1) \ + type bridge vlan_filtering 1 ip link set dev br1 up ip link set dev $swp1 master br1 diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh index fa6a88c50750..de2b2d5480dd 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh @@ -1,6 +1,28 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# +------------------------+ +----------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1.555 | | + $h2 | +# | | 192.0.2.1/28 | | | 192.0.2.130/28 | +# | | 2001:db8:1::1/64 | | | 2001:db8:2::2/64 | +# | | | | | | +# | + $h1 | | | | +# +----|-------------------+ +--|-------------------+ +# | | +# +----|--------------------------------------------------|-------------------+ +# | SW | | | +# | +--|-------------------------------+ + $swp2 | +# | | + $swp1 | 192.0.2.129/28 | +# | | vid 555 | 2001:db8:2::1/64 | +# | | | | +# | | + BR1 (802.1q) | | +# | | vid 555 pvid untagged | | +# | | 192.0.2.2/28 | | +# | | 2001:db8:1::2/64 | | +# | +----------------------------------+ | +# +---------------------------------------------------------------------------+ + ALL_TESTS=" ping_ipv4 ping_ipv6 @@ -41,7 +63,7 @@ h2_destroy() router_create() { - ip link add name br1 type bridge vlan_filtering 1 + ip link add name br1 type bridge vlan_filtering 1 vlan_default_pvid 0 ip link set dev br1 up ip link set dev $swp1 master br1 diff --git a/tools/testing/selftests/net/forwarding/skbedit_priority.sh b/tools/testing/selftests/net/forwarding/skbedit_priority.sh index bde11dc27873..3dd5fcbd3eaa 100755 --- a/tools/testing/selftests/net/forwarding/skbedit_priority.sh +++ b/tools/testing/selftests/net/forwarding/skbedit_priority.sh @@ -54,7 +54,9 @@ h2_destroy() switch_create() { - ip link add name br1 up type bridge vlan_filtering 1 + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 addrgenmode none + ip link set dev br1 up ip link set dev $swp1 master br1 ip link set dev $swp1 up ip link set dev $swp2 master br1 diff --git a/tools/testing/selftests/net/forwarding/tc_flower_cfm.sh b/tools/testing/selftests/net/forwarding/tc_flower_cfm.sh new file mode 100755 index 000000000000..3ca20df952eb --- /dev/null +++ b/tools/testing/selftests/net/forwarding/tc_flower_cfm.sh @@ -0,0 +1,206 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS="match_cfm_opcode match_cfm_level match_cfm_level_and_opcode" +NUM_NETIFS=2 +source tc_common.sh +source lib.sh + +h1_create() +{ + simple_if_init $h1 +} + +h1_destroy() +{ + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 + tc qdisc add dev $h2 clsact +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + simple_if_fini $h2 +} + +u8_to_hex() +{ + local u8=$1; shift + + printf "%02x" $u8 +} + +generate_cfm_hdr() +{ + local mdl=$1; shift + local op=$1; shift + local flags=$1; shift + local tlv_offset=$1; shift + + local cfm_hdr=$(: + )"$(u8_to_hex $((mdl << 5))):"$( : MD level and Version + )"$(u8_to_hex $op):"$( : OpCode + )"$(u8_to_hex $flags):"$( : Flags + )"$(u8_to_hex $tlv_offset)"$( : TLV offset + ) + + echo $cfm_hdr +} + +match_cfm_opcode() +{ + local ethtype="89 02"; readonly ethtype + RET=0 + + tc filter add dev $h2 ingress protocol cfm pref 1 handle 101 \ + flower cfm op 47 action drop + tc filter add dev $h2 ingress protocol cfm pref 1 handle 102 \ + flower cfm op 43 action drop + + pkt="$ethtype $(generate_cfm_hdr 7 47 0 32)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + pkt="$ethtype $(generate_cfm_hdr 6 5 0 4)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Did not match on correct opcode" + + tc_check_packets "dev $h2 ingress" 102 0 + check_err $? "Matched on the wrong opcode" + + pkt="$ethtype $(generate_cfm_hdr 0 43 0 12)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Matched on the wrong opcode" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Did not match on correct opcode" + + tc filter del dev $h2 ingress protocol cfm pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol cfm pref 1 handle 102 flower + + log_test "CFM opcode match test" +} + +match_cfm_level() +{ + local ethtype="89 02"; readonly ethtype + RET=0 + + tc filter add dev $h2 ingress protocol cfm pref 1 handle 101 \ + flower cfm mdl 5 action drop + tc filter add dev $h2 ingress protocol cfm pref 1 handle 102 \ + flower cfm mdl 3 action drop + tc filter add dev $h2 ingress protocol cfm pref 1 handle 103 \ + flower cfm mdl 0 action drop + + pkt="$ethtype $(generate_cfm_hdr 5 42 0 12)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + pkt="$ethtype $(generate_cfm_hdr 6 1 0 70)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + pkt="$ethtype $(generate_cfm_hdr 0 1 0 70)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Did not match on correct level" + + tc_check_packets "dev $h2 ingress" 102 0 + check_err $? "Matched on the wrong level" + + tc_check_packets "dev $h2 ingress" 103 1 + check_err $? "Did not match on correct level" + + pkt="$ethtype $(generate_cfm_hdr 3 0 0 4)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Matched on the wrong level" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Did not match on correct level" + + tc_check_packets "dev $h2 ingress" 103 1 + check_err $? "Matched on the wrong level" + + tc filter del dev $h2 ingress protocol cfm pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol cfm pref 1 handle 102 flower + tc filter del dev $h2 ingress protocol cfm pref 1 handle 103 flower + + log_test "CFM level match test" +} + +match_cfm_level_and_opcode() +{ + local ethtype="89 02"; readonly ethtype + RET=0 + + tc filter add dev $h2 ingress protocol cfm pref 1 handle 101 \ + flower cfm mdl 5 op 41 action drop + tc filter add dev $h2 ingress protocol cfm pref 1 handle 102 \ + flower cfm mdl 7 op 42 action drop + + pkt="$ethtype $(generate_cfm_hdr 5 41 0 4)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + pkt="$ethtype $(generate_cfm_hdr 7 3 0 4)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + pkt="$ethtype $(generate_cfm_hdr 3 42 0 12)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Did not match on correct level and opcode" + + tc_check_packets "dev $h2 ingress" 102 0 + check_err $? "Matched on the wrong level and opcode" + + pkt="$ethtype $(generate_cfm_hdr 7 42 0 12)" + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac "$pkt" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Matched on the wrong level and opcode" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Did not match on correct level and opcode" + + tc filter del dev $h2 ingress protocol cfm pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol cfm pref 1 handle 102 flower + + log_test "CFM opcode and level match test" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + h2=${NETIFS[p2]} + h1mac=$(mac_get $h1) + h2mac=$(mac_get $h2) + + vrf_prepare + + h1_create + h2_create +} + +cleanup() +{ + pre_cleanup + + h2_destroy + h1_destroy + + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh new file mode 100755 index 000000000000..e22c2d28b6eb --- /dev/null +++ b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh @@ -0,0 +1,350 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +-----------------------+ +----------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# | | 2001:db8:1::1/64 | | 2001:db8:1::2/64 | | +# +----|------------------+ +------------------|---+ +# | | +# +----|-------------------------------------------------------------------|---+ +# | SW | | | +# | +-|-------------------------------------------------------------------|-+ | +# | | + $swp1 BR $swp2 + | | +# | +-----------------------------------------------------------------------+ | +# +----------------------------------------------------------------------------+ + +ALL_TESTS=" + test_l2_miss_unicast + test_l2_miss_multicast + test_l2_miss_ll_multicast + test_l2_miss_broadcast +" + +NUM_NETIFS=4 +source lib.sh +source tc_common.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 2001:db8:1::2/64 +} + +h2_destroy() +{ + simple_if_fini $h2 192.0.2.2/28 2001:db8:1::2/64 +} + +switch_create() +{ + ip link add name br1 up type bridge + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + tc qdisc add dev $swp2 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp2 clsact + + ip link set dev $swp2 down + ip link set dev $swp2 nomaster + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + ip link del dev br1 +} + +test_l2_miss_unicast() +{ + local dmac=00:01:02:03:04:05 + local dip=192.0.2.2 + local sip=192.0.2.1 + + RET=0 + + # Unknown unicast. + tc filter add dev $swp2 egress protocol ipv4 handle 101 pref 1 \ + flower indev $swp1 l2_miss 1 dst_mac $dmac src_ip $sip \ + dst_ip $dip action pass + # Known unicast. + tc filter add dev $swp2 egress protocol ipv4 handle 102 pref 1 \ + flower indev $swp1 l2_miss 0 dst_mac $dmac src_ip $sip \ + dst_ip $dip action pass + + # Before adding FDB entry. + $MZ $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Unknown unicast filter was not hit before adding FDB entry" + + tc_check_packets "dev $swp2 egress" 102 0 + check_err $? "Known unicast filter was hit before adding FDB entry" + + # Adding FDB entry. + bridge fdb replace $dmac dev $swp2 master static + + $MZ $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Unknown unicast filter was hit after adding FDB entry" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "Known unicast filter was not hit after adding FDB entry" + + # Deleting FDB entry. + bridge fdb del $dmac dev $swp2 master static + + $MZ $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 2 + check_err $? "Unknown unicast filter was not hit after deleting FDB entry" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "Known unicast filter was hit after deleting FDB entry" + + tc filter del dev $swp2 egress protocol ipv4 pref 1 handle 102 flower + tc filter del dev $swp2 egress protocol ipv4 pref 1 handle 101 flower + + log_test "L2 miss - Unicast" +} + +test_l2_miss_multicast_common() +{ + local proto=$1; shift + local sip=$1; shift + local dip=$1; shift + local mode=$1; shift + local name=$1; shift + + RET=0 + + # Unregistered multicast. + tc filter add dev $swp2 egress protocol $proto handle 101 pref 1 \ + flower indev $swp1 l2_miss 1 src_ip $sip dst_ip $dip \ + action pass + # Registered multicast. + tc filter add dev $swp2 egress protocol $proto handle 102 pref 1 \ + flower indev $swp1 l2_miss 0 src_ip $sip dst_ip $dip \ + action pass + + # Before adding MDB entry. + $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Unregistered multicast filter was not hit before adding MDB entry" + + tc_check_packets "dev $swp2 egress" 102 0 + check_err $? "Registered multicast filter was hit before adding MDB entry" + + # Adding MDB entry. + bridge mdb replace dev br1 port $swp2 grp $dip permanent + + $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Unregistered multicast filter was hit after adding MDB entry" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "Registered multicast filter was not hit after adding MDB entry" + + # Deleting MDB entry. + bridge mdb del dev br1 port $swp2 grp $dip + + $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 2 + check_err $? "Unregistered multicast filter was not hit after deleting MDB entry" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "Registered multicast filter was hit after deleting MDB entry" + + tc filter del dev $swp2 egress protocol $proto pref 1 handle 102 flower + tc filter del dev $swp2 egress protocol $proto pref 1 handle 101 flower + + log_test "L2 miss - Multicast ($name)" +} + +test_l2_miss_multicast_ipv4() +{ + local proto="ipv4" + local sip=192.0.2.1 + local dip=239.1.1.1 + local mode="-4" + local name="IPv4" + + test_l2_miss_multicast_common $proto $sip $dip $mode $name +} + +test_l2_miss_multicast_ipv6() +{ + local proto="ipv6" + local sip=2001:db8:1::1 + local dip=ff0e::1 + local mode="-6" + local name="IPv6" + + test_l2_miss_multicast_common $proto $sip $dip $mode $name +} + +test_l2_miss_multicast() +{ + # Configure $swp2 as a multicast router port so that it will forward + # both registered and unregistered multicast traffic. + bridge link set dev $swp2 mcast_router 2 + + # Forwarding according to MDB entries only takes place when the bridge + # detects that there is a valid querier in the network. Set the bridge + # as the querier and assign it a valid IPv6 link-local address to be + # used as the source address for MLD queries. + ip link set dev br1 type bridge mcast_querier 1 + ip -6 address add fe80::1/64 nodad dev br1 + # Wait the default Query Response Interval (10 seconds) for the bridge + # to determine that there are no other queriers in the network. + sleep 10 + + test_l2_miss_multicast_ipv4 + test_l2_miss_multicast_ipv6 + + ip -6 address del fe80::1/64 dev br1 + ip link set dev br1 type bridge mcast_querier 0 + bridge link set dev $swp2 mcast_router 1 +} + +test_l2_miss_multicast_common2() +{ + local name=$1; shift + local dmac=$1; shift + local dip=224.0.0.1 + local sip=192.0.2.1 + +} + +test_l2_miss_ll_multicast_common() +{ + local proto=$1; shift + local dmac=$1; shift + local sip=$1; shift + local dip=$1; shift + local mode=$1; shift + local name=$1; shift + + RET=0 + + tc filter add dev $swp2 egress protocol $proto handle 101 pref 1 \ + flower indev $swp1 l2_miss 1 dst_mac $dmac src_ip $sip \ + dst_ip $dip action pass + + $MZ $mode $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Filter was not hit" + + tc filter del dev $swp2 egress protocol $proto pref 1 handle 101 flower + + log_test "L2 miss - Link-local multicast ($name)" +} + +test_l2_miss_ll_multicast_ipv4() +{ + local proto=ipv4 + local dmac=01:00:5e:00:00:01 + local sip=192.0.2.1 + local dip=224.0.0.1 + local mode="-4" + local name="IPv4" + + test_l2_miss_ll_multicast_common $proto $dmac $sip $dip $mode $name +} + +test_l2_miss_ll_multicast_ipv6() +{ + local proto=ipv6 + local dmac=33:33:00:00:00:01 + local sip=2001:db8:1::1 + local dip=ff02::1 + local mode="-6" + local name="IPv6" + + test_l2_miss_ll_multicast_common $proto $dmac $sip $dip $mode $name +} + +test_l2_miss_ll_multicast() +{ + test_l2_miss_ll_multicast_ipv4 + test_l2_miss_ll_multicast_ipv6 +} + +test_l2_miss_broadcast() +{ + local dmac=ff:ff:ff:ff:ff:ff + local smac=00:01:02:03:04:05 + + RET=0 + + tc filter add dev $swp2 egress protocol all handle 101 pref 1 \ + flower l2_miss 1 dst_mac $dmac src_mac $smac \ + action pass + tc filter add dev $swp2 egress protocol all handle 102 pref 1 \ + flower l2_miss 0 dst_mac $dmac src_mac $smac \ + action pass + + $MZ $h1 -a $smac -b $dmac -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 0 + check_err $? "L2 miss filter was hit when should not" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "L2 no miss filter was not hit when should" + + tc filter del dev $swp2 egress protocol all pref 1 handle 102 flower + tc filter del dev $swp2 egress protocol all pref 1 handle 101 flower + + log_test "L2 miss - Broadcast" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 43a723626126..7b936a926859 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -9,7 +9,7 @@ TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq -TEST_FILES := settings +TEST_FILES := mptcp_lib.sh settings EXTRA_CLEAN := *.pcap diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index 38021a0dd527..6032f9b23c4c 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -1,3 +1,4 @@ +CONFIG_KALLSYMS=y CONFIG_MPTCP=y CONFIG_IPV6=y CONFIG_MPTCP_IPV6=y diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index ef628b16fe9b..fa9e09ad97d9 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + sec=$(date +%s) rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) ns="ns1-$rndh" @@ -31,6 +33,8 @@ cleanup() ip netns del $ns } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" @@ -51,16 +55,20 @@ __chk_nr() { local command="$1" local expected=$2 - local msg nr + local msg="$3" + local skip="${4:-SKIP}" + local nr - shift 2 - msg=$* nr=$(eval $command) printf "%-50s" "$msg" if [ $nr != $expected ]; then - echo "[ fail ] expected $expected found $nr" - ret=$test_cnt + if [ $nr = "$skip" ] && ! mptcp_lib_expect_all_features; then + echo "[ skip ] Feature probably not supported" + else + echo "[ fail ] expected $expected found $nr" + ret=$test_cnt + fi else echo "[ ok ]" fi @@ -72,12 +80,12 @@ __chk_msk_nr() local condition=$1 shift 1 - __chk_nr "ss -inmHMN $ns | $condition" $* + __chk_nr "ss -inmHMN $ns | $condition" "$@" } chk_msk_nr() { - __chk_msk_nr "grep -c token:" $* + __chk_msk_nr "grep -c token:" "$@" } wait_msk_nr() @@ -115,37 +123,26 @@ wait_msk_nr() chk_msk_fallback_nr() { - __chk_msk_nr "grep -c fallback" $* + __chk_msk_nr "grep -c fallback" "$@" } chk_msk_remote_key_nr() { - __chk_msk_nr "grep -c remote_key" $* + __chk_msk_nr "grep -c remote_key" "$@" } __chk_listen() { local filter="$1" local expected=$2 + local msg="$3" - shift 2 - msg=$* - - nr=$(ss -N $ns -Ml "$filter" | grep -c LISTEN) - printf "%-50s" "$msg" - - if [ $nr != $expected ]; then - echo "[ fail ] expected $expected found $nr" - ret=$test_cnt - else - echo "[ ok ]" - fi + __chk_nr "ss -N $ns -Ml '$filter' | grep -c LISTEN" "$expected" "$msg" 0 } chk_msk_listen() { lport=$1 - local msg="check for listen socket" # destination port search should always return empty list __chk_listen "dport $lport" 0 "listen match for dport $lport" @@ -163,10 +160,9 @@ chk_msk_listen() chk_msk_inuse() { local expected=$1 + local msg="$2" local listen_nr - shift 1 - listen_nr=$(ss -N "${ns}" -Ml | grep -c LISTEN) expected=$((expected + listen_nr)) @@ -177,7 +173,7 @@ chk_msk_inuse() sleep 0.1 done - __chk_nr get_msk_inuse $expected $* + __chk_nr get_msk_inuse $expected "$msg" 0 } # $1: ns, $2: port diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index a43d3e2f59bb..13561e5bc0cd 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + time_start=$(date +%s) optstring="S:R:d:e:l:r:h4cm:f:tC" @@ -141,6 +143,9 @@ cleanup() done } +mptcp_lib_check_mptcp +mptcp_lib_check_kallsyms + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" @@ -691,6 +696,15 @@ run_test_transparent() return 0 fi + # IP(V6)_TRANSPARENT has been added after TOS support which came with + # the required infrastructure in MPTCP sockopt code. To support TOS, the + # following function has been exported (T). Not great but better than + # checking for a specific kernel version. + if ! mptcp_lib_kallsyms_has "T __ip_sock_set_tos$"; then + echo "INFO: ${msg} not supported by the kernel: SKIP" + return + fi + ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF" flush ruleset table inet mangle { @@ -763,6 +777,11 @@ run_tests_peekmode() run_tests_mptfo() { + if ! mptcp_lib_kallsyms_has "mptcp_fastopen_"; then + echo "INFO: TFO not supported by the kernel: SKIP" + return + fi + echo "INFO: with MPTFO start" ip netns exec "$ns1" sysctl -q net.ipv4.tcp_fastopen=2 ip netns exec "$ns2" sysctl -q net.ipv4.tcp_fastopen=1 @@ -783,9 +802,14 @@ run_tests_disconnect() local old_cin=$cin local old_sin=$sin + if ! mptcp_lib_kallsyms_has "mptcp_pm_data_reset$"; then + echo "INFO: Full disconnect not supported: SKIP" + return + fi + cat $cin $cin $cin > "$cin".disconnect - # force do_transfer to cope with the multiple tranmissions + # force do_transfer to cope with the multiple transmissions sin="$cin.disconnect" cin="$cin.disconnect" cin_disconnect="$old_cin" diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 26310c17b4c6..e6c9d5451c5b 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -10,6 +10,8 @@ # because it's invoked by variable name, see how the "tests" array is used #shellcheck disable=SC2317 +. "$(dirname "${0}")/mptcp_lib.sh" + ret=0 sin="" sinfail="" @@ -17,11 +19,14 @@ sout="" cin="" cinfail="" cinsent="" +tmpfile="" cout="" capout="" ns1="" ns2="" ksft_skip=4 +iptables="iptables" +ip6tables="ip6tables" timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) capture=0 @@ -34,6 +39,7 @@ evts_ns1="" evts_ns2="" evts_ns1_pid=0 evts_ns2_pid=0 +stats_dumped=0 declare -A all_tests declare -a only_tests_ids @@ -44,6 +50,10 @@ TEST_NAME="" nr_blank=40 export FAILING_LINKS="" +export test_linkfail=0 +export addr_nr_ns1=0 +export addr_nr_ns2=0 +export sflags="" # generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) || # (ip6 && (ip6[74] & 0xf0) == 0x30)'" @@ -79,7 +89,7 @@ init_partial() ip netns add $netns || exit $ksft_skip ip -net $netns link set lo up ip netns exec $netns sysctl -q net.mptcp.enabled=1 - ip netns exec $netns sysctl -q net.mptcp.pm_type=0 + ip netns exec $netns sysctl -q net.mptcp.pm_type=0 2>/dev/null || true ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0 ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0 if [ $checksum -eq 1 ]; then @@ -87,6 +97,7 @@ init_partial() fi done + stats_dumped=0 check_invert=0 validate_checksum=$checksum FAILING_LINKS="" @@ -136,12 +147,19 @@ cleanup_partial() check_tools() { + mptcp_lib_check_mptcp + mptcp_lib_check_kallsyms + if ! ip -Version &> /dev/null; then echo "SKIP: Could not run test without ip tool" exit $ksft_skip fi - if ! iptables -V &> /dev/null; then + # Use the legacy version if available to support old kernel versions + if iptables-legacy -V &> /dev/null; then + iptables="iptables-legacy" + ip6tables="ip6tables-legacy" + elif ! iptables -V &> /dev/null; then echo "SKIP: Could not run all tests without iptables tool" exit $ksft_skip fi @@ -175,10 +193,37 @@ cleanup() { rm -f "$cin" "$cout" "$sinfail" rm -f "$sin" "$sout" "$cinsent" "$cinfail" + rm -f "$tmpfile" rm -rf $evts_ns1 $evts_ns2 cleanup_partial } +# $1: msg +print_title() +{ + printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${1}" +} + +# [ $1: fail msg ] +mark_as_skipped() +{ + local msg="${1:-"Feature not supported"}" + + mptcp_lib_fail_if_expected_feature "${msg}" + + print_title "[ skip ] ${msg}" + printf "\n" +} + +# $@: condition +continue_if() +{ + if ! "${@}"; then + mark_as_skipped + return 1 + fi +} + skip_test() { if [ "${#only_tests_ids[@]}" -eq 0 ] && [ "${#only_tests_names[@]}" -eq 0 ]; then @@ -222,6 +267,19 @@ reset() return 0 } +# $1: test name ; $2: counter to check +reset_check_counter() +{ + reset "${1}" || return 1 + + local counter="${2}" + + if ! nstat -asz "${counter}" | grep -wq "${counter}"; then + mark_as_skipped "counter '${counter}' is not available" + return 1 + fi +} + # $1: test name reset_with_cookies() { @@ -241,17 +299,21 @@ reset_with_add_addr_timeout() reset "${1}" || return 1 - tables="iptables" + tables="${iptables}" if [ $ip -eq 6 ]; then - tables="ip6tables" + tables="${ip6tables}" fi ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 - ip netns exec $ns2 $tables -A OUTPUT -p tcp \ - -m tcp --tcp-option 30 \ - -m bpf --bytecode \ - "$CBPF_MPTCP_SUBOPTION_ADD_ADDR" \ - -j DROP + + if ! ip netns exec $ns2 $tables -A OUTPUT -p tcp \ + -m tcp --tcp-option 30 \ + -m bpf --bytecode \ + "$CBPF_MPTCP_SUBOPTION_ADD_ADDR" \ + -j DROP; then + mark_as_skipped "unable to set the 'add addr' rule" + return 1 + fi } # $1: test name @@ -295,22 +357,17 @@ reset_with_allow_join_id0() # tc action pedit offset 162 out of bounds # # Netfilter is used to mark packets with enough data. -reset_with_fail() +setup_fail_rules() { - reset "${1}" || return 1 - - ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=1 - ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=1 - check_invert=1 validate_checksum=1 - local i="$2" - local ip="${3:-4}" + local i="$1" + local ip="${2:-4}" local tables - tables="iptables" + tables="${iptables}" if [ $ip -eq 6 ]; then - tables="ip6tables" + tables="${ip6tables}" fi ip netns exec $ns2 $tables \ @@ -320,15 +377,32 @@ reset_with_fail() -p tcp \ -m length --length 150:9999 \ -m statistic --mode nth --packet 1 --every 99999 \ - -j MARK --set-mark 42 || exit 1 + -j MARK --set-mark 42 || return ${ksft_skip} - tc -n $ns2 qdisc add dev ns2eth$i clsact || exit 1 + tc -n $ns2 qdisc add dev ns2eth$i clsact || return ${ksft_skip} tc -n $ns2 filter add dev ns2eth$i egress \ protocol ip prio 1000 \ handle 42 fw \ action pedit munge offset 148 u8 invert \ pipe csum tcp \ - index 100 || exit 1 + index 100 || return ${ksft_skip} +} + +reset_with_fail() +{ + reset_check_counter "${1}" "MPTcpExtInfiniteMapTx" || return 1 + shift + + ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=1 + ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=1 + + local rc=0 + setup_fail_rules "${@}" || rc=$? + + if [ ${rc} -eq ${ksft_skip} ]; then + mark_as_skipped "unable to set the 'fail' rules" + return 1 + fi } reset_with_events() @@ -343,10 +417,32 @@ reset_with_events() evts_ns2_pid=$! } +reset_with_tcp_filter() +{ + reset "${1}" || return 1 + shift + + local ns="${!1}" + local src="${2}" + local target="${3}" + + if ! ip netns exec "${ns}" ${iptables} \ + -A INPUT \ + -s "${src}" \ + -p tcp \ + -j "${target}"; then + mark_as_skipped "unable to set the filter rules" + return 1 + fi +} + fail_test() { ret=1 failed_tests[${TEST_COUNT}]="${TEST_NAME}" + + [ "${stats_dumped}" = 0 ] && dump_stats + stats_dumped=1 } get_failed_tests_ids() @@ -383,9 +479,16 @@ check_transfer() fail_test return 1 fi - bytes="--bytes=${bytes}" + + # note: BusyBox's "cmp" command doesn't support --bytes + tmpfile=$(mktemp) + head --bytes="$bytes" "$in" > "$tmpfile" + mv "$tmpfile" "$in" + head --bytes="$bytes" "$out" > "$tmpfile" + mv "$tmpfile" "$out" + tmpfile="" fi - cmp -l "$in" "$out" ${bytes} | while read -r i a b; do + cmp -l "$in" "$out" | while read -r i a b; do local sum=$((0${a} + 0${b})) if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then echo "[ FAIL ] $what does not match (in, out):" @@ -454,11 +557,25 @@ wait_local_port_listen() done } -rm_addr_count() +# $1: ns ; $2: counter +get_counter() { - local ns=${1} + local ns="${1}" + local counter="${2}" + local count - ip netns exec ${ns} nstat -as | grep MPTcpExtRmAddr | awk '{print $2}' + count=$(ip netns exec ${ns} nstat -asz "${counter}" | awk 'NR==1 {next} {print $2}') + if [ -z "${count}" ]; then + mptcp_lib_fail_if_expected_feature "${counter} counter" + return 1 + fi + + echo "${count}" +} + +rm_addr_count() +{ + get_counter "${1}" "MPTcpExtRmAddr" } # $1: ns, $2: old rm_addr counter in $ns @@ -476,16 +593,36 @@ wait_rm_addr() done } +rm_sf_count() +{ + get_counter "${1}" "MPTcpExtRmSubflow" +} + +# $1: ns, $2: old rm_sf counter in $ns +wait_rm_sf() +{ + local ns="${1}" + local old_cnt="${2}" + local cnt + + local i + for i in $(seq 10); do + cnt=$(rm_sf_count ${ns}) + [ "$cnt" = "${old_cnt}" ] || break + sleep 0.1 + done +} + wait_mpj() { local ns="${1}" local cnt old_cnt - old_cnt=$(ip netns exec ${ns} nstat -as | grep MPJoinAckRx | awk '{print $2}') + old_cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") local i for i in $(seq 10); do - cnt=$(ip netns exec ${ns} nstat -as | grep MPJoinAckRx | awk '{print $2}') + cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") [ "$cnt" = "${old_cnt}" ] || break sleep 0.1 done @@ -685,144 +822,11 @@ pm_nl_check_endpoint() fi } -filter_tcp_from() -{ - local ns="${1}" - local src="${2}" - local target="${3}" - - ip netns exec "${ns}" iptables -A INPUT -s "${src}" -p tcp -j "${target}" -} - -do_transfer() +pm_nl_set_endpoint() { local listener_ns="$1" local connector_ns="$2" - local cl_proto="$3" - local srv_proto="$4" - local connect_addr="$5" - local test_link_fail="$6" - local addr_nr_ns1="$7" - local addr_nr_ns2="$8" - local speed="$9" - local sflags="${10}" - - local port=$((10000 + TEST_COUNT - 1)) - local cappid - local userspace_pm=0 - - :> "$cout" - :> "$sout" - :> "$capout" - - if [ $capture -eq 1 ]; then - local capuser - if [ -z $SUDO_USER ] ; then - capuser="" - else - capuser="-Z $SUDO_USER" - fi - - capfile=$(printf "mp_join-%02u-%s.pcap" "$TEST_COUNT" "${listener_ns}") - - echo "Capturing traffic for test $TEST_COUNT into $capfile" - ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 & - cappid=$! - - sleep 1 - fi - - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat -n - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat -n - - local extra_args - if [ $speed = "fast" ]; then - extra_args="-j" - elif [ $speed = "slow" ]; then - extra_args="-r 50" - elif [[ $speed = "speed_"* ]]; then - extra_args="-r ${speed:6}" - fi - - if [[ "${addr_nr_ns1}" = "userspace_"* ]]; then - userspace_pm=1 - addr_nr_ns1=${addr_nr_ns1:10} - fi - - local flags="subflow" - local extra_cl_args="" - local extra_srv_args="" - local trunc_size="" - if [[ "${addr_nr_ns2}" = "fastclose_"* ]]; then - if [ ${test_link_fail} -le 1 ]; then - echo "fastclose tests need test_link_fail argument" - fail_test - return 1 - fi - - # disconnect - trunc_size=${test_link_fail} - local side=${addr_nr_ns2:10} - - if [ ${side} = "client" ]; then - extra_cl_args="-f ${test_link_fail}" - extra_srv_args="-f -1" - elif [ ${side} = "server" ]; then - extra_srv_args="-f ${test_link_fail}" - extra_cl_args="-f -1" - else - echo "wrong/unknown fastclose spec ${side}" - fail_test - return 1 - fi - addr_nr_ns2=0 - elif [[ "${addr_nr_ns2}" = "userspace_"* ]]; then - userspace_pm=1 - addr_nr_ns2=${addr_nr_ns2:10} - elif [[ "${addr_nr_ns2}" = "fullmesh_"* ]]; then - flags="${flags},fullmesh" - addr_nr_ns2=${addr_nr_ns2:9} - fi - - extra_srv_args="$extra_args $extra_srv_args" - if [ "$test_link_fail" -gt 1 ];then - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - $extra_srv_args "::" < "$sinfail" > "$sout" & - else - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - $extra_srv_args "::" < "$sin" > "$sout" & - fi - local spid=$! - - wait_local_port_listen "${listener_ns}" "${port}" - - extra_cl_args="$extra_args $extra_cl_args" - if [ "$test_link_fail" -eq 0 ];then - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_cl_args $connect_addr < "$cin" > "$cout" & - elif [ "$test_link_fail" -eq 1 ] || [ "$test_link_fail" -eq 2 ];then - ( cat "$cinfail" ; sleep 2; link_failure $listener_ns ; cat "$cinfail" ) | \ - tee "$cinsent" | \ - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_cl_args $connect_addr > "$cout" & - else - tee "$cinsent" < "$cinfail" | \ - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_cl_args $connect_addr > "$cout" & - fi - local cpid=$! + local connect_addr="$3" # let the mptcp subflow be established in background before # do endpoint manipulation @@ -834,7 +838,6 @@ do_transfer() local counter=2 local add_nr_ns1=${addr_nr_ns1} local id=10 - local tk while [ $add_nr_ns1 -gt 0 ]; do local addr if is_v6 "${connect_addr}"; then @@ -842,16 +845,7 @@ do_transfer() else addr="10.0.$counter.1" fi - if [ $userspace_pm -eq 0 ]; then - pm_nl_add_endpoint $ns1 $addr flags signal - else - tk=$(grep "type:1," "$evts_ns1" | - sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q') - ip netns exec ${listener_ns} ./pm_nl_ctl ann $addr token $tk id $id - sleep 1 - ip netns exec ${listener_ns} ./pm_nl_ctl rem token $tk id $id - fi - + pm_nl_add_endpoint $ns1 $addr flags signal counter=$((counter + 1)) add_nr_ns1=$((add_nr_ns1 - 1)) id=$((id + 1)) @@ -896,7 +890,6 @@ do_transfer() local add_nr_ns2=${addr_nr_ns2} local counter=3 local id=20 - local tk da dp sp while [ $add_nr_ns2 -gt 0 ]; do local addr if is_v6 "${connect_addr}"; then @@ -904,20 +897,7 @@ do_transfer() else addr="10.0.$counter.2" fi - if [ $userspace_pm -eq 0 ]; then - pm_nl_add_endpoint $ns2 $addr flags $flags - else - tk=$(sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") - da=$(sed -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evts_ns2") - dp=$(sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") - ip netns exec ${connector_ns} ./pm_nl_ctl csf lip $addr lid $id \ - rip $da rport $dp token $tk - sleep 1 - sp=$(grep "type:10" "$evts_ns2" | - sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') - ip netns exec ${connector_ns} ./pm_nl_ctl dsf lip $addr lport $sp \ - rip $da rport $dp token $tk - fi + pm_nl_add_endpoint $ns2 $addr flags $flags counter=$((counter + 1)) add_nr_ns2=$((add_nr_ns2 - 1)) id=$((id + 1)) @@ -986,6 +966,126 @@ do_transfer() done done fi +} + +do_transfer() +{ + local listener_ns="$1" + local connector_ns="$2" + local cl_proto="$3" + local srv_proto="$4" + local connect_addr="$5" + local speed="$6" + + local port=$((10000 + TEST_COUNT - 1)) + local cappid + + :> "$cout" + :> "$sout" + :> "$capout" + + if [ $capture -eq 1 ]; then + local capuser + if [ -z $SUDO_USER ] ; then + capuser="" + else + capuser="-Z $SUDO_USER" + fi + + capfile=$(printf "mp_join-%02u-%s.pcap" "$TEST_COUNT" "${listener_ns}") + + echo "Capturing traffic for test $TEST_COUNT into $capfile" + ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 & + cappid=$! + + sleep 1 + fi + + NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ + nstat -n + NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ + nstat -n + + local extra_args + if [ $speed = "fast" ]; then + extra_args="-j" + elif [ $speed = "slow" ]; then + extra_args="-r 50" + elif [[ $speed = "speed_"* ]]; then + extra_args="-r ${speed:6}" + fi + + local flags="subflow" + local extra_cl_args="" + local extra_srv_args="" + local trunc_size="" + if [[ "${addr_nr_ns2}" = "fastclose_"* ]]; then + if [ ${test_linkfail} -le 1 ]; then + echo "fastclose tests need test_linkfail argument" + fail_test + return 1 + fi + + # disconnect + trunc_size=${test_linkfail} + local side=${addr_nr_ns2:10} + + if [ ${side} = "client" ]; then + extra_cl_args="-f ${test_linkfail}" + extra_srv_args="-f -1" + elif [ ${side} = "server" ]; then + extra_srv_args="-f ${test_linkfail}" + extra_cl_args="-f -1" + else + echo "wrong/unknown fastclose spec ${side}" + fail_test + return 1 + fi + addr_nr_ns2=0 + elif [[ "${addr_nr_ns2}" = "fullmesh_"* ]]; then + flags="${flags},fullmesh" + addr_nr_ns2=${addr_nr_ns2:9} + fi + + extra_srv_args="$extra_args $extra_srv_args" + if [ "$test_linkfail" -gt 1 ];then + timeout ${timeout_test} \ + ip netns exec ${listener_ns} \ + ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ + $extra_srv_args "::" < "$sinfail" > "$sout" & + else + timeout ${timeout_test} \ + ip netns exec ${listener_ns} \ + ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ + $extra_srv_args "::" < "$sin" > "$sout" & + fi + local spid=$! + + wait_local_port_listen "${listener_ns}" "${port}" + + extra_cl_args="$extra_args $extra_cl_args" + if [ "$test_linkfail" -eq 0 ];then + timeout ${timeout_test} \ + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr < "$cin" > "$cout" & + elif [ "$test_linkfail" -eq 1 ] || [ "$test_linkfail" -eq 2 ];then + ( cat "$cinfail" ; sleep 2; link_failure $listener_ns ; cat "$cinfail" ) | \ + tee "$cinsent" | \ + timeout ${timeout_test} \ + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr > "$cout" & + else + tee "$cinsent" < "$cinfail" | \ + timeout ${timeout_test} \ + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr > "$cout" & + fi + local cpid=$! + + pm_nl_set_endpoint $listener_ns $connector_ns $connect_addr wait $cpid local retc=$? @@ -1016,13 +1116,13 @@ do_transfer() return 1 fi - if [ "$test_link_fail" -gt 1 ];then + if [ "$test_linkfail" -gt 1 ];then check_transfer $sinfail $cout "file received by client" $trunc_size else check_transfer $sin $cout "file received by client" $trunc_size fi retc=$? - if [ "$test_link_fail" -eq 0 ];then + if [ "$test_linkfail" -eq 0 ];then check_transfer $cin $sout "file received by server" $trunc_size else check_transfer $cinsent $sout "file received by server" $trunc_size @@ -1055,11 +1155,7 @@ run_tests() local listener_ns="$1" local connector_ns="$2" local connect_addr="$3" - local test_linkfail="${4:-0}" - local addr_nr_ns1="${5:-0}" - local addr_nr_ns2="${6:-0}" - local speed="${7:-fast}" - local sflags="${8:-""}" + local speed="${4:-fast}" local size @@ -1103,8 +1199,7 @@ run_tests() make_file "$sinfail" "server" $size fi - do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} \ - ${test_linkfail} ${addr_nr_ns1} ${addr_nr_ns2} ${speed} ${sflags} + do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} ${speed} } dump_stats() @@ -1120,7 +1215,6 @@ chk_csum_nr() local csum_ns1=${1:-0} local csum_ns2=${2:-0} local count - local dump_stats local extra_msg="" local allow_multi_errors_ns1=0 local allow_multi_errors_ns2=0 @@ -1135,34 +1229,33 @@ chk_csum_nr() fi printf "%-${nr_blank}s %s" " " "sum" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns1} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns1" ]; then extra_msg="$extra_msg ns1=$count" fi - if { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } || { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then echo "[fail] got $count data checksum error[s] expected $csum_ns1" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - csum " - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns2} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns2" ]; then extra_msg="$extra_msg ns2=$count" fi - if { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } || { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then echo "[fail] got $count data checksum error[s] expected $csum_ns2" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats echo "$extra_msg" } @@ -1173,7 +1266,6 @@ chk_fail_nr() local fail_rx=$2 local ns_invert=${3:-""} local count - local dump_stats local ns_tx=$ns1 local ns_rx=$ns2 local extra_msg="" @@ -1196,37 +1288,35 @@ chk_fail_nr() fi printf "%-${nr_blank}s %s" " " "ftx" - count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPFailTx | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns_tx} "MPTcpExtMPFailTx") if [ "$count" != "$fail_tx" ]; then extra_msg="$extra_msg,tx=$count" fi - if { [ "$count" != "$fail_tx" ] && [ $allow_tx_lost -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != "$fail_tx" ] && [ $allow_tx_lost -eq 0 ]; } || { [ "$count" -gt "$fail_tx" ] && [ $allow_tx_lost -eq 1 ]; }; then echo "[fail] got $count MP_FAIL[s] TX expected $fail_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - failrx" - count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPFailRx | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns_rx} "MPTcpExtMPFailRx") if [ "$count" != "$fail_rx" ]; then extra_msg="$extra_msg,rx=$count" fi - if { [ "$count" != "$fail_rx" ] && [ $allow_rx_lost -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != "$fail_rx" ] && [ $allow_rx_lost -eq 0 ]; } || { [ "$count" -gt "$fail_rx" ] && [ $allow_rx_lost -eq 1 ]; }; then echo "[fail] got $count MP_FAIL[s] RX expected $fail_rx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats - echo "$extra_msg" } @@ -1236,7 +1326,6 @@ chk_fclose_nr() local fclose_rx=$2 local ns_invert=$3 local count - local dump_stats local ns_tx=$ns2 local ns_rx=$ns1 local extra_msg=" " @@ -1248,31 +1337,29 @@ chk_fclose_nr() fi printf "%-${nr_blank}s %s" " " "ctx" - count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPFastcloseTx | awk '{print $2}') - [ -z "$count" ] && count=0 - [ "$count" != "$fclose_tx" ] && extra_msg="$extra_msg,tx=$count" - if [ "$count" != "$fclose_tx" ]; then + count=$(get_counter ${ns_tx} "MPTcpExtMPFastcloseTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$fclose_tx" ]; then + extra_msg="$extra_msg,tx=$count" echo "[fail] got $count MP_FASTCLOSE[s] TX expected $fclose_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - fclzrx" - count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPFastcloseRx | awk '{print $2}') - [ -z "$count" ] && count=0 - [ "$count" != "$fclose_rx" ] && extra_msg="$extra_msg,rx=$count" - if [ "$count" != "$fclose_rx" ]; then + count=$(get_counter ${ns_rx} "MPTcpExtMPFastcloseRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$fclose_rx" ]; then + extra_msg="$extra_msg,rx=$count" echo "[fail] got $count MP_FASTCLOSE[s] RX expected $fclose_rx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats - echo "$extra_msg" } @@ -1282,7 +1369,6 @@ chk_rst_nr() local rst_rx=$2 local ns_invert=${3:-""} local count - local dump_stats local ns_tx=$ns1 local ns_rx=$ns2 local extra_msg="" @@ -1294,29 +1380,27 @@ chk_rst_nr() fi printf "%-${nr_blank}s %s" " " "rtx" - count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPRstTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ $count -lt $rst_tx ]; then + count=$(get_counter ${ns_tx} "MPTcpExtMPRstTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ $count -lt $rst_tx ]; then echo "[fail] got $count MP_RST[s] TX expected $rst_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - rstrx " - count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPRstRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" -lt "$rst_rx" ]; then + count=$(get_counter ${ns_rx} "MPTcpExtMPRstRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" -lt "$rst_rx" ]; then echo "[fail] got $count MP_RST[s] RX expected $rst_rx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats - echo "$extra_msg" } @@ -1325,31 +1409,28 @@ chk_infi_nr() local infi_tx=$1 local infi_rx=$2 local count - local dump_stats printf "%-${nr_blank}s %s" " " "itx" - count=$(ip netns exec $ns2 nstat -as | grep InfiniteMapTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$infi_tx" ]; then + count=$(get_counter ${ns2} "MPTcpExtInfiniteMapTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$infi_tx" ]; then echo "[fail] got $count infinite map[s] TX expected $infi_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - infirx" - count=$(ip netns exec $ns1 nstat -as | grep InfiniteMapRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$infi_rx" ]; then + count=$(get_counter ${ns1} "MPTcpExtInfiniteMapRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$infi_rx" ]; then echo "[fail] got $count infinite map[s] RX expected $infi_rx" fail_test - dump_stats=1 else echo "[ ok ]" fi - - [ "${dump_stats}" = 1 ] && dump_stats } chk_join_nr() @@ -1364,7 +1445,6 @@ chk_join_nr() local infi_nr=${8:-0} local corrupted_pkts=${9:-0} local count - local dump_stats local with_cookie local title="${TEST_NAME}" @@ -1373,21 +1453,22 @@ chk_join_nr() fi printf "%03u %-36s %s" "${TEST_COUNT}" "${title}" "syn" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn expected $syn_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - synack" with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies) - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinSynAckRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_ack_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtMPJoinSynAckRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_ack_nr" ]; then # simult connections exceeding the limit with cookie enabled could go up to # synack validation as the conn limit can be enforced reliably only after # the subflow creation @@ -1396,23 +1477,21 @@ chk_join_nr() else echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr" fail_test - dump_stats=1 fi else echo -n "[ ok ]" fi echo -n " - ack" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinAckRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$ack_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack expected $ack_nr" fail_test - dump_stats=1 else echo "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats if [ $validate_checksum -eq 1 ]; then chk_csum_nr $csum_ns1 $csum_ns2 chk_fail_nr $fail_nr $fail_nr @@ -1437,12 +1516,12 @@ chk_stale_nr() local recover_nr printf "%-${nr_blank}s %-18s" " " "stale" - stale_nr=$(ip netns exec $ns nstat -as | grep MPTcpExtSubflowStale | awk '{print $2}') - [ -z "$stale_nr" ] && stale_nr=0 - recover_nr=$(ip netns exec $ns nstat -as | grep MPTcpExtSubflowRecover | awk '{print $2}') - [ -z "$recover_nr" ] && recover_nr=0 - if [ $stale_nr -lt $stale_min ] || + stale_nr=$(get_counter ${ns} "MPTcpExtSubflowStale") + recover_nr=$(get_counter ${ns} "MPTcpExtSubflowRecover") + if [ -z "$stale_nr" ] || [ -z "$recover_nr" ]; then + echo "[skip]" + elif [ $stale_nr -lt $stale_min ] || { [ $stale_max -gt 0 ] && [ $stale_nr -gt $stale_max ]; } || [ $((stale_nr - recover_nr)) -ne $stale_delta ]; then echo "[fail] got $stale_nr stale[s] $recover_nr recover[s], " \ @@ -1472,117 +1551,142 @@ chk_add_nr() local mis_syn_nr=${7:-0} local mis_ack_nr=${8:-0} local count - local dump_stats local timeout timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) printf "%-${nr_blank}s %s" " " "add" - count=$(ip netns exec $ns2 nstat -as MPTcpExtAddAddr | grep MPTcpExtAddAddr | awk '{print $2}') - [ -z "$count" ] && count=0 - + count=$(get_counter ${ns2} "MPTcpExtAddAddr") + if [ -z "$count" ]; then + echo -n "[skip]" # if the test configured a short timeout tolerate greater then expected # add addrs options, due to retransmissions - if [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then + elif [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then echo "[fail] got $count ADD_ADDR[s] expected $add_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - echo " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtEchoAdd | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$echo_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtEchoAdd") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$echo_nr" ]; then echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi if [ $port_nr -gt 0 ]; then echo -n " - pt " - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtPortAdd | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$port_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtPortAdd") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$port_nr" ]; then echo "[fail] got $count ADD_ADDR[s] with a port-number expected $port_nr" fail_test - dump_stats=1 else echo "[ ok ]" fi printf "%-${nr_blank}s %s" " " "syn" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortSynRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinPortSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn with a different \ port-number expected $syn_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - synack" - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinPortSynAckRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_ack_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_ack_nr" ]; then echo "[fail] got $count JOIN[s] synack with a different \ port-number expected $syn_ack_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - ack" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortAckRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$ack_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinPortAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack with a different \ port-number expected $ack_nr" fail_test - dump_stats=1 else echo "[ ok ]" fi printf "%-${nr_blank}s %s" " " "syn" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortSynRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mis_syn_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMismatchPortSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$mis_syn_nr" ]; then echo "[fail] got $count JOIN[s] syn with a mismatched \ port-number expected $mis_syn_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - ack " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortAckRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mis_ack_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMismatchPortAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$mis_ack_nr" ]; then echo "[fail] got $count JOIN[s] ack with a mismatched \ port-number expected $mis_ack_nr" fail_test - dump_stats=1 else echo "[ ok ]" fi else echo "" fi +} + +chk_add_tx_nr() +{ + local add_tx_nr=$1 + local echo_tx_nr=$2 + local timeout + local count + + timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) + + printf "%-${nr_blank}s %s" " " "add TX" + count=$(get_counter ${ns1} "MPTcpExtAddAddrTx") + if [ -z "$count" ]; then + echo -n "[skip]" + # if the test configured a short timeout tolerate greater then expected + # add addrs options, due to retransmissions + elif [ "$count" != "$add_tx_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_tx_nr" ]; }; then + echo "[fail] got $count ADD_ADDR[s] TX, expected $add_tx_nr" + fail_test + else + echo -n "[ ok ]" + fi - [ "${dump_stats}" = 1 ] && dump_stats + echo -n " - echo TX " + count=$(get_counter ${ns2} "MPTcpExtEchoAddTx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$echo_tx_nr" ]; then + echo "[fail] got $count ADD_ADDR echo[s] TX, expected $echo_tx_nr" + fail_test + else + echo "[ ok ]" + fi } chk_rm_nr() @@ -1592,7 +1696,6 @@ chk_rm_nr() local invert local simult local count - local dump_stats local addr_ns=$ns1 local subflow_ns=$ns2 local extra_msg="" @@ -1614,82 +1717,89 @@ chk_rm_nr() fi printf "%-${nr_blank}s %s" " " "rm " - count=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmAddr | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$rm_addr_nr" ]; then + count=$(get_counter ${addr_ns} "MPTcpExtRmAddr") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$rm_addr_nr" ]; then echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - rmsf " - count=$(ip netns exec $subflow_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ -n "$simult" ]; then + count=$(get_counter ${subflow_ns} "MPTcpExtRmSubflow") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ -n "$simult" ]; then local cnt suffix - cnt=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') + cnt=$(get_counter ${addr_ns} "MPTcpExtRmSubflow") # in case of simult flush, the subflow removal count on each side is # unreliable - [ -z "$cnt" ] && cnt=0 count=$((count + cnt)) [ "$count" != "$rm_subflow_nr" ] && suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]" if [ $count -ge "$rm_subflow_nr" ] && \ [ "$count" -le "$((rm_subflow_nr *2 ))" ]; then - echo "[ ok ] $suffix" + echo -n "[ ok ] $suffix" else echo "[fail] got $count RM_SUBFLOW[s] expected in range [$rm_subflow_nr:$((rm_subflow_nr*2))]" fail_test - dump_stats=1 fi - return - fi - if [ "$count" != "$rm_subflow_nr" ]; then + elif [ "$count" != "$rm_subflow_nr" ]; then echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats - echo "$extra_msg" } +chk_rm_tx_nr() +{ + local rm_addr_tx_nr=$1 + + printf "%-${nr_blank}s %s" " " "rm TX " + count=$(get_counter ${ns2} "MPTcpExtRmAddrTx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$rm_addr_tx_nr" ]; then + echo "[fail] got $count RM_ADDR[s] expected $rm_addr_tx_nr" + fail_test + else + echo "[ ok ]" + fi +} + chk_prio_nr() { local mp_prio_nr_tx=$1 local mp_prio_nr_rx=$2 local count - local dump_stats printf "%-${nr_blank}s %s" " " "ptx" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mp_prio_nr_tx" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPPrioTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$mp_prio_nr_tx" ]; then echo "[fail] got $count MP_PRIO[s] TX expected $mp_prio_nr_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - prx " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mp_prio_nr_rx" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPPrioRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$mp_prio_nr_rx" ]; then echo "[fail] got $count MP_PRIO[s] RX expected $mp_prio_nr_rx" fail_test - dump_stats=1 else echo "[ ok ]" fi - - [ "${dump_stats}" = 1 ] && dump_stats } chk_subflow_nr() @@ -1721,37 +1831,31 @@ chk_subflow_nr() ss -N $ns1 -tOni ss -N $ns1 -tOni | grep token ip -n $ns1 mptcp endpoint - dump_stats fi } chk_mptcp_info() { - local nr_info=$1 - local info + local info1=$1 + local exp1=$2 + local info2=$3 + local exp2=$4 local cnt1 local cnt2 local dump_stats - if [[ $nr_info = "subflows_"* ]]; then - info="subflows" - nr_info=${nr_info:9} - else - echo "[fail] unsupported argument: $nr_info" - fail_test - return 1 - fi - - printf "%-${nr_blank}s %-30s" " " "mptcp_info $info=$nr_info" + printf "%-${nr_blank}s %-30s" " " "mptcp_info $info1:$info2=$exp1:$exp2" - cnt1=$(ss -N $ns1 -inmHM | grep "$info:" | - sed -n 's/.*\('"$info"':\)\([[:digit:]]*\).*$/\2/p;q') + cnt1=$(ss -N $ns1 -inmHM | grep "$info1:" | + sed -n 's/.*\('"$info1"':\)\([[:digit:]]*\).*$/\2/p;q') + cnt2=$(ss -N $ns2 -inmHM | grep "$info2:" | + sed -n 's/.*\('"$info2"':\)\([[:digit:]]*\).*$/\2/p;q') + # 'ss' only display active connections and counters that are not 0. [ -z "$cnt1" ] && cnt1=0 - cnt2=$(ss -N $ns2 -inmHM | grep "$info:" | - sed -n 's/.*\('"$info"':\)\([[:digit:]]*\).*$/\2/p;q') [ -z "$cnt2" ] && cnt2=0 - if [ "$cnt1" != "$nr_info" ] || [ "$cnt2" != "$nr_info" ]; then - echo "[fail] got $cnt1:$cnt2 $info expected $nr_info" + + if [ "$cnt1" != "$exp1" ] || [ "$cnt2" != "$exp2" ]; then + echo "[fail] got $cnt1:$cnt2 $info1:$info2 expected $exp1:$exp2" fail_test dump_stats=1 else @@ -1761,7 +1865,6 @@ chk_mptcp_info() if [ "$dump_stats" = 1 ]; then ss -N $ns1 -inmHM ss -N $ns2 -inmHM - dump_stats fi } @@ -1797,7 +1900,7 @@ wait_attempt_fail() while [ $time -lt $timeout_ms ]; do local cnt - cnt=$(ip netns exec $ns nstat -as TcpAttemptFails | grep TcpAttemptFails | awk '{print $2}') + cnt=$(get_counter ${ns} "TcpAttemptFails") [ "$cnt" = 1 ] && return 1 time=$((time + 100)) @@ -1885,41 +1988,41 @@ subflows_error_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 0 0 0 fi # multiple subflows, with subflow creation error - if reset "multi subflows, with failing subflow"; then + if reset_with_tcp_filter "multi subflows, with failing subflow" ns1 10.0.3.2 REJECT && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - filter_tcp_from $ns1 10.0.3.2 REJECT - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 fi # multiple subflows, with subflow timeout on MPJ - if reset "multi subflows, with subflow timeout"; then + if reset_with_tcp_filter "multi subflows, with subflow timeout" ns1 10.0.3.2 DROP && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - filter_tcp_from $ns1 10.0.3.2 DROP - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 fi # multiple subflows, check that the endpoint corresponding to # closed subflow (due to reset) is not reused if additional # subflows are added later - if reset "multi subflows, fair usage on close"; then + if reset_with_tcp_filter "multi subflows, fair usage on close" ns1 10.0.3.2 REJECT && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - filter_tcp_from $ns1 10.0.3.2 REJECT - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & + run_tests $ns1 $ns2 10.0.1.1 slow & # mpj subflow will be in TW after the reset wait_attempt_fail $ns2 @@ -1939,6 +2042,7 @@ signal_address_tests() pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 + chk_add_tx_nr 1 1 chk_add_nr 1 1 fi @@ -2017,12 +2121,19 @@ signal_address_tests() # the peer could possibly miss some addr notification, allow retransmission ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr 3 3 3 + run_tests $ns1 $ns2 10.0.1.1 slow - # the server will not signal the address terminating - # the MPC subflow - chk_add_nr 3 3 + # It is not directly linked to the commit introducing this + # symbol but for the parent one which is linked anyway. + if ! mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then + chk_join_nr 3 3 2 + chk_add_nr 4 4 + else + chk_join_nr 3 3 3 + # the server will not signal the address terminating + # the MPC subflow + chk_add_nr 3 3 + fi fi } @@ -2042,7 +2153,8 @@ link_failure_tests() pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow - run_tests $ns1 $ns2 10.0.1.1 1 + test_linkfail=1 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 chk_add_nr 1 1 chk_stale_nr $ns2 1 5 1 @@ -2057,7 +2169,8 @@ link_failure_tests() pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow - run_tests $ns1 $ns2 10.0.1.1 2 + test_linkfail=2 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 chk_add_nr 1 1 chk_stale_nr $ns2 1 -1 1 @@ -2070,9 +2183,9 @@ link_failure_tests() pm_nl_set_limits $ns1 0 2 pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal pm_nl_set_limits $ns2 1 2 - FAILING_LINKS="1" pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 1 + FAILING_LINKS="1" test_linkfail=1 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 chk_add_nr 1 1 chk_link_usage $ns2 ns2eth3 $cinsent 0 @@ -2086,8 +2199,8 @@ link_failure_tests() pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal pm_nl_set_limits $ns2 1 2 pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup - FAILING_LINKS="1 2" - run_tests $ns1 $ns2 10.0.1.1 1 + FAILING_LINKS="1 2" test_linkfail=1 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 chk_add_nr 1 1 chk_stale_nr $ns2 2 4 2 @@ -2102,8 +2215,8 @@ link_failure_tests() pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup - FAILING_LINKS="1 2" - run_tests $ns1 $ns2 10.0.1.1 2 + FAILING_LINKS="1 2" test_linkfail=2 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 chk_add_nr 1 1 chk_stale_nr $ns2 1 -1 2 @@ -2118,8 +2231,9 @@ add_addr_timeout_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 + chk_add_tx_nr 4 4 chk_add_nr 4 0 fi @@ -2128,7 +2242,7 @@ add_addr_timeout_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 1 1 1 chk_add_nr 4 0 fi @@ -2139,7 +2253,7 @@ add_addr_timeout_tests() pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_set_limits $ns2 2 2 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 speed_10 + run_tests $ns1 $ns2 10.0.1.1 speed_10 chk_join_nr 2 2 2 chk_add_nr 8 0 fi @@ -2150,7 +2264,7 @@ add_addr_timeout_tests() pm_nl_add_endpoint $ns1 10.0.12.1 flags signal pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_set_limits $ns2 2 2 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 speed_10 + run_tests $ns1 $ns2 10.0.1.1 speed_10 chk_join_nr 1 1 1 chk_add_nr 8 0 fi @@ -2163,8 +2277,10 @@ remove_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow + addr_nr_ns2=-1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 + chk_rm_tx_nr 1 chk_rm_nr 1 1 fi @@ -2174,7 +2290,8 @@ remove_tests() pm_nl_set_limits $ns2 0 2 pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -2 slow + addr_nr_ns2=-2 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 2 2 2 chk_rm_nr 2 2 fi @@ -2184,7 +2301,8 @@ remove_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow + addr_nr_ns1=-1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_add_nr 1 1 chk_rm_nr 1 1 invert @@ -2196,7 +2314,8 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_set_limits $ns2 1 2 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow + addr_nr_ns1=-1 addr_nr_ns2=-1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 2 2 2 chk_add_nr 1 1 chk_rm_nr 1 1 @@ -2209,7 +2328,8 @@ remove_tests() pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 speed_10 + addr_nr_ns1=-1 addr_nr_ns2=-2 \ + run_tests $ns1 $ns2 10.0.1.1 speed_10 chk_join_nr 3 3 3 chk_add_nr 1 1 chk_rm_nr 2 2 @@ -2222,7 +2342,8 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.4.1 flags signal pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -3 0 speed_10 + addr_nr_ns1=-3 \ + run_tests $ns1 $ns2 10.0.1.1 speed_10 chk_join_nr 3 3 3 chk_add_nr 3 3 chk_rm_nr 3 3 invert @@ -2235,7 +2356,8 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.14.1 flags signal pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -3 0 speed_10 + addr_nr_ns1=-3 \ + run_tests $ns1 $ns2 10.0.1.1 speed_10 chk_join_nr 1 1 1 chk_add_nr 3 3 chk_rm_nr 3 1 invert @@ -2248,7 +2370,8 @@ remove_tests() pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + addr_nr_ns1=-8 addr_nr_ns2=-8 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 3 3 3 chk_add_nr 1 1 chk_rm_nr 1 3 invert simult @@ -2261,9 +2384,16 @@ remove_tests() pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow id 150 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + addr_nr_ns1=-8 addr_nr_ns2=-8 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 3 3 3 - chk_rm_nr 0 3 simult + + if mptcp_lib_kversion_ge 5.18; then + chk_rm_tx_nr 0 + chk_rm_nr 0 3 simult + else + chk_rm_nr 3 3 + fi fi # addresses flush @@ -2273,7 +2403,8 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.4.1 flags signal pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + addr_nr_ns1=-8 addr_nr_ns2=-8 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 3 3 3 chk_add_nr 3 3 chk_rm_nr 3 3 invert simult @@ -2286,7 +2417,8 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.14.1 flags signal pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -8 0 slow + addr_nr_ns1=-8 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_add_nr 3 3 chk_rm_nr 3 1 invert @@ -2297,7 +2429,8 @@ remove_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -9 slow + addr_nr_ns2=-9 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_rm_nr 1 1 fi @@ -2307,7 +2440,8 @@ remove_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 -9 0 slow + addr_nr_ns1=-9 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_add_nr 1 1 chk_rm_nr 1 1 invert @@ -2320,7 +2454,8 @@ add_tests() if reset "add single subflow"; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 - run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow + addr_nr_ns2=1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 fi @@ -2328,7 +2463,8 @@ add_tests() if reset "add signal address"; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow + addr_nr_ns1=1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_add_nr 1 1 fi @@ -2337,7 +2473,8 @@ add_tests() if reset "add multiple subflows"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 - run_tests $ns1 $ns2 10.0.1.1 0 0 2 slow + addr_nr_ns2=2 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 2 2 2 fi @@ -2345,7 +2482,8 @@ add_tests() if reset "add multiple subflows IPv6"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 - run_tests $ns1 $ns2 dead:beef:1::1 0 0 2 slow + addr_nr_ns2=2 \ + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 2 2 2 fi @@ -2353,7 +2491,8 @@ add_tests() if reset "add multiple addresses IPv6"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 2 2 - run_tests $ns1 $ns2 dead:beef:1::1 0 2 0 slow + addr_nr_ns1=2 \ + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 2 2 2 chk_add_nr 2 2 fi @@ -2366,14 +2505,14 @@ ipv6_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 1 1 1 fi # add_address, unused IPv6 if reset "unused signal address IPv6"; then pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 0 0 0 chk_add_nr 1 1 fi @@ -2383,7 +2522,7 @@ ipv6_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 1 1 1 chk_add_nr 1 1 fi @@ -2393,7 +2532,8 @@ ipv6_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 dead:beef:1::1 0 -1 0 slow + addr_nr_ns1=-1 \ + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 1 1 1 chk_add_nr 1 1 chk_rm_nr 1 1 invert @@ -2405,7 +2545,8 @@ ipv6_tests() pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal pm_nl_set_limits $ns2 1 2 pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow - run_tests $ns1 $ns2 dead:beef:1::1 0 -1 -1 slow + addr_nr_ns1=-1 addr_nr_ns2=-1 \ + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 2 2 2 chk_add_nr 1 1 chk_rm_nr 1 1 @@ -2501,41 +2642,46 @@ v4mapped_tests() mixed_tests() { - if reset "IPv4 sockets do not use IPv6 addresses"; then + if reset "IPv4 sockets do not use IPv6 addresses" && + continue_if mptcp_lib_kversion_ge 6.3; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 0 0 0 fi # Need an IPv6 mptcp socket to allow subflows of both families - if reset "simult IPv4 and IPv6 subflows"; then + if reset "simult IPv4 and IPv6 subflows" && + continue_if mptcp_lib_kversion_ge 6.3; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns1 10.0.1.1 flags signal - run_tests $ns1 $ns2 dead:beef:2::1 0 0 0 slow + run_tests $ns1 $ns2 dead:beef:2::1 slow chk_join_nr 1 1 1 fi # cross families subflows will not be created even in fullmesh mode - if reset "simult IPv4 and IPv6 subflows, fullmesh 1x1"; then + if reset "simult IPv4 and IPv6 subflows, fullmesh 1x1" && + continue_if mptcp_lib_kversion_ge 6.3; then pm_nl_set_limits $ns1 0 4 pm_nl_set_limits $ns2 1 4 pm_nl_add_endpoint $ns2 dead:beef:2::2 flags subflow,fullmesh pm_nl_add_endpoint $ns1 10.0.1.1 flags signal - run_tests $ns1 $ns2 dead:beef:2::1 0 0 0 slow + run_tests $ns1 $ns2 dead:beef:2::1 slow chk_join_nr 1 1 1 fi # fullmesh still tries to create all the possibly subflows with # matching family - if reset "simult IPv4 and IPv6 subflows, fullmesh 2x2"; then + if reset "simult IPv4 and IPv6 subflows, fullmesh 2x2" && + continue_if mptcp_lib_kversion_ge 6.3; then pm_nl_set_limits $ns1 0 4 pm_nl_set_limits $ns2 2 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - run_tests $ns1 $ns2 dead:beef:1::1 0 0 fullmesh_1 slow + addr_nr_ns2=fullmesh_1 \ + run_tests $ns1 $ns2 dead:beef:1::1 slow chk_join_nr 4 4 4 fi } @@ -2543,63 +2689,75 @@ mixed_tests() backup_tests() { # single subflow, backup - if reset "single subflow, backup"; then + if reset "single subflow, backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup + sflags=nobackup \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_prio_nr 0 1 fi # single address, backup - if reset "single address, backup"; then + if reset "single address, backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + sflags=backup \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_add_nr 1 1 chk_prio_nr 1 1 fi # single address with port, backup - if reset "single address with port, backup"; then + if reset "single address with port, backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + sflags=backup \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_add_nr 1 1 chk_prio_nr 1 1 fi - if reset "mpc backup"; then + if reset "mpc backup" && + continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 0 0 0 chk_prio_nr 0 1 fi - if reset "mpc backup both sides"; then + if reset "mpc backup both sides" && + continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 0 0 0 chk_prio_nr 1 1 fi - if reset "mpc switch to backup"; then + if reset "mpc switch to backup" && + continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + sflags=backup \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 0 0 0 chk_prio_nr 0 1 fi - if reset "mpc switch to backup both sides"; then + if reset "mpc switch to backup both sides" && + continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + sflags=backup \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 0 0 0 chk_prio_nr 1 1 fi @@ -2622,38 +2780,41 @@ verify_listener_events() local family local saddr local sport + local name if [ $e_type = $LISTENER_CREATED ]; then - stdbuf -o0 -e0 printf "\t\t\t\t\t CREATE_LISTENER %s:%s"\ - $e_saddr $e_sport + name="LISTENER_CREATED" elif [ $e_type = $LISTENER_CLOSED ]; then - stdbuf -o0 -e0 printf "\t\t\t\t\t CLOSE_LISTENER %s:%s "\ - $e_saddr $e_sport + name="LISTENER_CLOSED" + else + name="$e_type" fi - type=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q') - family=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(family:\)\([[:digit:]]*\).*$/\2/p;q') - sport=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + printf "%-${nr_blank}s %s %s:%s " " " "$name" "$e_saddr" "$e_sport" + + if ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then + printf "[skip]: event not supported\n" + return + fi + + type=$(grep "type:$e_type," $evt | sed -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q') + family=$(grep "type:$e_type," $evt | sed -n 's/.*\(family:\)\([[:digit:]]*\).*$/\2/p;q') + sport=$(grep "type:$e_type," $evt | sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') if [ $family ] && [ $family = $AF_INET6 ]; then - saddr=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(saddr6:\)\([0-9a-f:.]*\).*$/\2/p;q') + saddr=$(grep "type:$e_type," $evt | sed -n 's/.*\(saddr6:\)\([0-9a-f:.]*\).*$/\2/p;q') else - saddr=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(saddr4:\)\([0-9.]*\).*$/\2/p;q') + saddr=$(grep "type:$e_type," $evt | sed -n 's/.*\(saddr4:\)\([0-9.]*\).*$/\2/p;q') fi if [ $type ] && [ $type = $e_type ] && [ $family ] && [ $family = $e_family ] && [ $saddr ] && [ $saddr = $e_saddr ] && [ $sport ] && [ $sport = $e_sport ]; then - stdbuf -o0 -e0 printf "[ ok ]\n" + echo "[ ok ]" return 0 fi fail_test - stdbuf -o0 -e0 printf "[fail]\n" + echo "[fail]" } add_addr_ports_tests() @@ -2685,7 +2846,8 @@ add_addr_ports_tests() pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow + addr_nr_ns1=-1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 1 chk_add_nr 1 1 1 chk_rm_nr 1 1 invert @@ -2701,7 +2863,8 @@ add_addr_ports_tests() pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 pm_nl_set_limits $ns2 1 2 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow + addr_nr_ns1=-1 addr_nr_ns2=-1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 2 2 2 chk_add_nr 1 1 1 chk_rm_nr 1 1 @@ -2714,7 +2877,8 @@ add_addr_ports_tests() pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -8 -2 slow + addr_nr_ns1=-8 addr_nr_ns2=-2 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 3 3 3 chk_add_nr 1 1 chk_rm_nr 1 3 invert simult @@ -2916,7 +3080,8 @@ fullmesh_tests() pm_nl_set_limits $ns2 1 4 pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,fullmesh pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,fullmesh - run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow + addr_nr_ns1=1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 4 4 4 chk_add_nr 1 1 fi @@ -2928,7 +3093,8 @@ fullmesh_tests() pm_nl_set_limits $ns1 1 3 pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow + addr_nr_ns2=fullmesh_1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 3 3 3 chk_add_nr 1 1 fi @@ -2940,7 +3106,8 @@ fullmesh_tests() pm_nl_set_limits $ns1 2 5 pm_nl_set_limits $ns2 1 5 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow + addr_nr_ns2=fullmesh_2 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 5 5 5 chk_add_nr 1 1 fi @@ -2953,48 +3120,57 @@ fullmesh_tests() pm_nl_set_limits $ns1 2 4 pm_nl_set_limits $ns2 1 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow + addr_nr_ns2=fullmesh_2 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 4 4 4 chk_add_nr 1 1 fi # set fullmesh flag - if reset "set fullmesh flag test"; then + if reset "set fullmesh flag test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow pm_nl_set_limits $ns2 4 4 - run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow fullmesh + addr_nr_ns2=1 sflags=fullmesh \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 2 2 2 chk_rm_nr 0 1 fi # set nofullmesh flag - if reset "set nofullmesh flag test"; then + if reset "set nofullmesh flag test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow,fullmesh pm_nl_set_limits $ns2 4 4 - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow nofullmesh + addr_nr_ns2=fullmesh_1 sflags=nofullmesh \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 2 2 2 chk_rm_nr 0 1 fi # set backup,fullmesh flags - if reset "set backup,fullmesh flags test"; then + if reset "set backup,fullmesh flags test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow pm_nl_set_limits $ns2 4 4 - run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow backup,fullmesh + addr_nr_ns2=1 sflags=backup,fullmesh \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 2 2 2 chk_prio_nr 0 1 chk_rm_nr 0 1 fi # set nobackup,nofullmesh flags - if reset "set nobackup,nofullmesh flags test"; then + if reset "set nobackup,nofullmesh flags test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_set_limits $ns2 4 4 pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,backup,fullmesh - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup,nofullmesh + sflags=nobackup,nofullmesh \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 2 2 2 chk_prio_nr 0 1 chk_rm_nr 0 1 @@ -3003,15 +3179,17 @@ fullmesh_tests() fastclose_tests() { - if reset "fastclose test"; then - run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_client + if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then + test_linkfail=1024 addr_nr_ns2=fastclose_client \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 chk_fclose_nr 1 1 chk_rst_nr 1 1 invert fi - if reset "fastclose server test"; then - run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_server + if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then + test_linkfail=1024 addr_nr_ns2=fastclose_server \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 chk_fclose_nr 1 1 invert chk_rst_nr 1 1 @@ -3029,7 +3207,8 @@ fail_tests() { # single subflow if reset_with_fail "Infinite map" 1; then - run_tests $ns1 $ns2 10.0.1.1 128 + test_linkfail=128 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 +1 +0 1 0 1 "$(pedit_action_pkts)" chk_fail_nr 1 -1 invert fi @@ -3040,15 +3219,82 @@ fail_tests() pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 1024 + test_linkfail=1024 \ + run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 1 0 1 1 0 "$(pedit_action_pkts)" fi } +userspace_pm_add_addr() +{ + local addr=$1 + local id=$2 + local tk + + tk=$(grep "type:1," "$evts_ns1" | + sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q') + ip netns exec $ns1 ./pm_nl_ctl ann $addr token $tk id $id + sleep 1 +} + +userspace_pm_rm_sf_addr_ns1() +{ + local addr=$1 + local id=$2 + local tk sp da dp + + tk=$(grep "type:1," "$evts_ns1" | + sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q') + sp=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + da=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(daddr6:\)\([0-9a-f:.]*\).*$/\2/p;q') + dp=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q') + ip netns exec $ns1 ./pm_nl_ctl rem token $tk id $id + ip netns exec $ns1 ./pm_nl_ctl dsf lip "::ffff:$addr" \ + lport $sp rip $da rport $dp token $tk + wait_rm_addr $ns1 1 + wait_rm_sf $ns1 1 +} + +userspace_pm_add_sf() +{ + local addr=$1 + local id=$2 + local tk da dp + + tk=$(sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") + da=$(sed -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evts_ns2") + dp=$(sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") + ip netns exec $ns2 ./pm_nl_ctl csf lip $addr lid $id \ + rip $da rport $dp token $tk + sleep 1 +} + +userspace_pm_rm_sf_addr_ns2() +{ + local addr=$1 + local id=$2 + local tk da dp sp + + tk=$(sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") + da=$(sed -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evts_ns2") + dp=$(sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") + sp=$(grep "type:10" "$evts_ns2" | + sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + ip netns exec $ns2 ./pm_nl_ctl rem token $tk id $id + ip netns exec $ns2 ./pm_nl_ctl dsf lip $addr lport $sp \ + rip $da rport $dp token $tk + wait_rm_addr $ns2 1 + wait_rm_sf $ns2 1 +} + userspace_tests() { # userspace pm type prevents add_addr - if reset "userspace pm type prevents add_addr"; then + if reset "userspace pm type prevents add_addr" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 @@ -3059,7 +3305,8 @@ userspace_tests() fi # userspace pm type does not echo add_addr without daemon - if reset "userspace pm no echo w/o daemon"; then + if reset "userspace pm no echo w/o daemon" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 @@ -3070,7 +3317,8 @@ userspace_tests() fi # userspace pm type rejects join - if reset "userspace pm type rejects join"; then + if reset "userspace pm type rejects join" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 @@ -3080,7 +3328,8 @@ userspace_tests() fi # userspace pm type does not send join - if reset "userspace pm type does not send join"; then + if reset "userspace pm type does not send join" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 @@ -3090,62 +3339,87 @@ userspace_tests() fi # userspace pm type prevents mp_prio - if reset "userspace pm type prevents mp_prio"; then + if reset "userspace pm type prevents mp_prio" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + sflags=backup \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 1 1 0 chk_prio_nr 0 0 fi # userspace pm type prevents rm_addr - if reset "userspace pm type prevents rm_addr"; then + if reset "userspace pm type prevents rm_addr" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow + addr_nr_ns2=-1 \ + run_tests $ns1 $ns2 10.0.1.1 slow chk_join_nr 0 0 0 chk_rm_nr 0 0 fi # userspace pm add & remove address - if reset_with_events "userspace pm add & remove address"; then + if reset_with_events "userspace pm add & remove address" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 userspace_1 0 slow + run_tests $ns1 $ns2 10.0.1.1 speed_10 & + local tests_pid=$! + wait_mpj $ns1 + userspace_pm_add_addr 10.0.2.1 10 chk_join_nr 1 1 1 chk_add_nr 1 1 + chk_mptcp_info subflows 1 subflows 1 + chk_mptcp_info add_addr_signal 1 add_addr_accepted 1 + userspace_pm_rm_sf_addr_ns1 10.0.2.1 10 chk_rm_nr 1 1 invert + chk_mptcp_info subflows 0 subflows 0 kill_events_pids + wait $tests_pid fi # userspace pm create destroy subflow - if reset_with_events "userspace pm create destroy subflow"; then + if reset_with_events "userspace pm create destroy subflow" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 - run_tests $ns1 $ns2 10.0.1.1 0 0 userspace_1 slow + run_tests $ns1 $ns2 10.0.1.1 speed_10 & + local tests_pid=$! + wait_mpj $ns2 + userspace_pm_add_sf 10.0.3.2 20 chk_join_nr 1 1 1 - chk_rm_nr 0 1 + chk_mptcp_info subflows 1 subflows 1 + userspace_pm_rm_sf_addr_ns2 10.0.3.2 20 + chk_rm_nr 1 1 + chk_mptcp_info subflows 0 subflows 0 kill_events_pids + wait $tests_pid fi } endpoint_tests() { + # subflow_rebuild_header is needed to support the implicit flag # userspace pm type prevents add_addr - if reset "implicit EP"; then + if reset "implicit EP" && + mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 2 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow 2>/dev/null & + run_tests $ns1 $ns2 10.0.1.1 slow 2>/dev/null & wait_mpj $ns1 pm_nl_check_endpoint 1 "creation" \ $ns2 10.0.2.2 id 1 flags implicit + chk_mptcp_info subflows 1 subflows 1 + chk_mptcp_info add_addr_signal 1 add_addr_accepted 1 pm_nl_add_endpoint $ns2 10.0.2.2 id 33 pm_nl_check_endpoint 0 "ID change is prevented" \ @@ -3157,25 +3431,27 @@ endpoint_tests() kill_tests_wait fi - if reset "delete and re-add"; then + if reset "delete and re-add" && + mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 4 0 0 speed_20 2>/dev/null & + test_linkfail=4 \ + run_tests $ns1 $ns2 10.0.1.1 speed_20 2>/dev/null & wait_mpj $ns2 chk_subflow_nr needtitle "before delete" 2 - chk_mptcp_info subflows_1 + chk_mptcp_info subflows 1 subflows 1 pm_nl_del_endpoint $ns2 2 10.0.2.2 sleep 0.5 chk_subflow_nr "" "after delete" 1 - chk_mptcp_info subflows_0 + chk_mptcp_info subflows 0 subflows 0 pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow wait_mpj $ns2 chk_subflow_nr "" "after re-add" 2 - chk_mptcp_info subflows_1 + chk_mptcp_info subflows 1 subflows 1 kill_tests_wait fi } diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh new file mode 100644 index 000000000000..f32045b23b89 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -0,0 +1,104 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 + +readonly KSFT_FAIL=1 +readonly KSFT_SKIP=4 + +# SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var can be set when validating all +# features using the last version of the kernel and the selftests to make sure +# a test is not being skipped by mistake. +mptcp_lib_expect_all_features() { + [ "${SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES:-}" = "1" ] +} + +# $1: msg +mptcp_lib_fail_if_expected_feature() { + if mptcp_lib_expect_all_features; then + echo "ERROR: missing feature: ${*}" + exit ${KSFT_FAIL} + fi + + return 1 +} + +# $1: file +mptcp_lib_has_file() { + local f="${1}" + + if [ -f "${f}" ]; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${f} file not found" +} + +mptcp_lib_check_mptcp() { + if ! mptcp_lib_has_file "/proc/sys/net/mptcp/enabled"; then + echo "SKIP: MPTCP support is not available" + exit ${KSFT_SKIP} + fi +} + +mptcp_lib_check_kallsyms() { + if ! mptcp_lib_has_file "/proc/kallsyms"; then + echo "SKIP: CONFIG_KALLSYMS is missing" + exit ${KSFT_SKIP} + fi +} + +# Internal: use mptcp_lib_kallsyms_has() instead +__mptcp_lib_kallsyms_has() { + local sym="${1}" + + mptcp_lib_check_kallsyms + + grep -q " ${sym}" /proc/kallsyms +} + +# $1: part of a symbol to look at, add '$' at the end for full name +mptcp_lib_kallsyms_has() { + local sym="${1}" + + if __mptcp_lib_kallsyms_has "${sym}"; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${sym} symbol not found" +} + +# $1: part of a symbol to look at, add '$' at the end for full name +mptcp_lib_kallsyms_doesnt_have() { + local sym="${1}" + + if ! __mptcp_lib_kallsyms_has "${sym}"; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${sym} symbol has been found" +} + +# !!!AVOID USING THIS!!! +# Features might not land in the expected version and features can be backported +# +# $1: kernel version, e.g. 6.3 +mptcp_lib_kversion_ge() { + local exp_maj="${1%.*}" + local exp_min="${1#*.}" + local v maj min + + # If the kernel has backported features, set this env var to 1: + if [ "${SELFTESTS_MPTCP_LIB_NO_KVERSION_CHECK:-}" = "1" ]; then + return 0 + fi + + v=$(uname -r | cut -d'.' -f1,2) + maj=${v%.*} + min=${v#*.} + + if [ "${maj}" -gt "${exp_maj}" ] || + { [ "${maj}" -eq "${exp_maj}" ] && [ "${min}" -ge "${exp_min}" ]; }; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "kernel version ${1} lower than ${v}" +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c index ae61f39556ca..926b0be87c99 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -51,6 +51,11 @@ struct mptcp_info { __u8 mptcpi_local_addr_used; __u8 mptcpi_local_addr_max; __u8 mptcpi_csum_enabled; + __u32 mptcpi_retransmits; + __u64 mptcpi_bytes_retrans; + __u64 mptcpi_bytes_sent; + __u64 mptcpi_bytes_received; + __u64 mptcpi_bytes_acked; }; struct mptcp_subflow_data { @@ -81,12 +86,47 @@ struct mptcp_subflow_addrs { #define MPTCP_SUBFLOW_ADDRS 3 #endif +#ifndef MPTCP_FULL_INFO +struct mptcp_subflow_info { + __u32 id; + struct mptcp_subflow_addrs addrs; +}; + +struct mptcp_full_info { + __u32 size_tcpinfo_kernel; /* must be 0, set by kernel */ + __u32 size_tcpinfo_user; + __u32 size_sfinfo_kernel; /* must be 0, set by kernel */ + __u32 size_sfinfo_user; + __u32 num_subflows; /* must be 0, set by kernel (real subflow count) */ + __u32 size_arrays_user; /* max subflows that userspace is interested in; + * the buffers at subflow_info/tcp_info + * are respectively at least: + * size_arrays * size_sfinfo_user + * size_arrays * size_tcpinfo_user + * bytes wide + */ + __aligned_u64 subflow_info; + __aligned_u64 tcp_info; + struct mptcp_info mptcp_info; +}; + +#define MPTCP_FULL_INFO 4 +#endif + struct so_state { struct mptcp_info mi; + struct mptcp_info last_sample; + struct tcp_info tcp_info; + struct mptcp_subflow_addrs addrs; uint64_t mptcpi_rcv_delta; uint64_t tcpi_rcv_delta; + bool pkt_stats_avail; }; +#ifndef MIN +#define MIN(a, b) ((a) < (b) ? (a) : (b)) +#endif + static void die_perror(const char *msg) { perror(msg); @@ -318,8 +358,9 @@ static void do_getsockopt_mptcp_info(struct so_state *s, int fd, size_t w) if (ret < 0) die_perror("getsockopt MPTCP_INFO"); - assert(olen == sizeof(i)); + s->pkt_stats_avail = olen >= sizeof(i); + s->last_sample = i; if (s->mi.mptcpi_write_seq == 0) s->mi = i; @@ -349,13 +390,16 @@ static void do_getsockopt_tcp_info(struct so_state *s, int fd, size_t r, size_t xerror("getsockopt MPTCP_TCPINFO (tries %d, %m)"); assert(olen <= sizeof(ti)); - assert(ti.d.size_user == ti.d.size_kernel); - assert(ti.d.size_user == sizeof(struct tcp_info)); + assert(ti.d.size_kernel > 0); + assert(ti.d.size_user == + MIN(ti.d.size_kernel, sizeof(struct tcp_info))); assert(ti.d.num_subflows == 1); assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data)); olen -= sizeof(struct mptcp_subflow_data); - assert(olen == sizeof(struct tcp_info)); + assert(olen == ti.d.size_user); + + s->tcp_info = ti.ti[0]; if (ti.ti[0].tcpi_bytes_sent == w && ti.ti[0].tcpi_bytes_received == r) @@ -378,7 +422,7 @@ done: do_getsockopt_bogus_sf_data(fd, MPTCP_TCPINFO); } -static void do_getsockopt_subflow_addrs(int fd) +static void do_getsockopt_subflow_addrs(struct so_state *s, int fd) { struct sockaddr_storage remote, local; socklen_t olen, rlen, llen; @@ -401,13 +445,14 @@ static void do_getsockopt_subflow_addrs(int fd) die_perror("getsockopt MPTCP_SUBFLOW_ADDRS"); assert(olen <= sizeof(addrs)); - assert(addrs.d.size_user == addrs.d.size_kernel); - assert(addrs.d.size_user == sizeof(struct mptcp_subflow_addrs)); + assert(addrs.d.size_kernel > 0); + assert(addrs.d.size_user == + MIN(addrs.d.size_kernel, sizeof(struct mptcp_subflow_addrs))); assert(addrs.d.num_subflows == 1); assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data)); olen -= sizeof(struct mptcp_subflow_data); - assert(olen == sizeof(struct mptcp_subflow_addrs)); + assert(olen == addrs.d.size_user); llen = sizeof(local); ret = getsockname(fd, (struct sockaddr *)&local, &llen); @@ -425,6 +470,7 @@ static void do_getsockopt_subflow_addrs(int fd) assert(memcmp(&local, &addrs.addr[0].ss_local, sizeof(local)) == 0); assert(memcmp(&remote, &addrs.addr[0].ss_remote, sizeof(remote)) == 0); + s->addrs = addrs.addr[0]; memset(&addrs, 0, sizeof(addrs)); @@ -445,13 +491,70 @@ static void do_getsockopt_subflow_addrs(int fd) do_getsockopt_bogus_sf_data(fd, MPTCP_SUBFLOW_ADDRS); } +static void do_getsockopt_mptcp_full_info(struct so_state *s, int fd) +{ + size_t data_size = sizeof(struct mptcp_full_info); + struct mptcp_subflow_info sfinfo[2]; + struct tcp_info tcp_info[2]; + struct mptcp_full_info mfi; + socklen_t olen; + int ret; + + memset(&mfi, 0, data_size); + memset(tcp_info, 0, sizeof(tcp_info)); + memset(sfinfo, 0, sizeof(sfinfo)); + + mfi.size_tcpinfo_user = sizeof(struct tcp_info); + mfi.size_sfinfo_user = sizeof(struct mptcp_subflow_info); + mfi.size_arrays_user = 2; + mfi.subflow_info = (unsigned long)&sfinfo[0]; + mfi.tcp_info = (unsigned long)&tcp_info[0]; + olen = data_size; + + ret = getsockopt(fd, SOL_MPTCP, MPTCP_FULL_INFO, &mfi, &olen); + if (ret < 0) { + if (errno == EOPNOTSUPP) { + perror("MPTCP_FULL_INFO test skipped"); + return; + } + xerror("getsockopt MPTCP_FULL_INFO"); + } + + assert(olen <= data_size); + assert(mfi.size_tcpinfo_kernel > 0); + assert(mfi.size_tcpinfo_user == + MIN(mfi.size_tcpinfo_kernel, sizeof(struct tcp_info))); + assert(mfi.size_sfinfo_kernel > 0); + assert(mfi.size_sfinfo_user == + MIN(mfi.size_sfinfo_kernel, sizeof(struct mptcp_subflow_info))); + assert(mfi.num_subflows == 1); + + /* Tolerate future extension to mptcp_info struct and running newer + * test on top of older kernel. + * Anyway any kernel supporting MPTCP_FULL_INFO must at least include + * the following in mptcp_info. + */ + assert(olen > (socklen_t)__builtin_offsetof(struct mptcp_full_info, tcp_info)); + assert(mfi.mptcp_info.mptcpi_subflows == 0); + assert(mfi.mptcp_info.mptcpi_bytes_sent == s->last_sample.mptcpi_bytes_sent); + assert(mfi.mptcp_info.mptcpi_bytes_received == s->last_sample.mptcpi_bytes_received); + + assert(sfinfo[0].id == 1); + assert(tcp_info[0].tcpi_bytes_sent == s->tcp_info.tcpi_bytes_sent); + assert(tcp_info[0].tcpi_bytes_received == s->tcp_info.tcpi_bytes_received); + assert(!memcmp(&sfinfo->addrs, &s->addrs, sizeof(struct mptcp_subflow_addrs))); +} + static void do_getsockopts(struct so_state *s, int fd, size_t r, size_t w) { do_getsockopt_mptcp_info(s, fd, w); do_getsockopt_tcp_info(s, fd, r, w); - do_getsockopt_subflow_addrs(fd); + do_getsockopt_subflow_addrs(s, fd); + + if (r) + do_getsockopt_mptcp_full_info(s, fd); } static void connect_one_server(int fd, int pipefd) @@ -556,6 +659,23 @@ static void process_one_client(int fd, int pipefd) do_getsockopts(&s, fd, ret, ret2); if (s.mptcpi_rcv_delta != (uint64_t)ret + 1) xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64, s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - ret); + + /* be nice when running on top of older kernel */ + if (s.pkt_stats_avail) { + if (s.last_sample.mptcpi_bytes_sent != ret2) + xerror("mptcpi_bytes_sent %" PRIu64 ", expect %" PRIu64, + s.last_sample.mptcpi_bytes_sent, ret2, + s.last_sample.mptcpi_bytes_sent - ret2); + if (s.last_sample.mptcpi_bytes_received != ret) + xerror("mptcpi_bytes_received %" PRIu64 ", expect %" PRIu64, + s.last_sample.mptcpi_bytes_received, ret, + s.last_sample.mptcpi_bytes_received - ret); + if (s.last_sample.mptcpi_bytes_acked != ret) + xerror("mptcpi_bytes_acked %" PRIu64 ", expect %" PRIu64, + s.last_sample.mptcpi_bytes_acked, ret2, + s.last_sample.mptcpi_bytes_acked - ret2); + } + close(fd); } diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 1b70c0a304ce..f295a371ff14 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + ret=0 sin="" sout="" @@ -84,6 +86,9 @@ cleanup() rm -f "$sin" "$sout" } +mptcp_lib_check_mptcp +mptcp_lib_check_kallsyms + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" @@ -182,9 +187,14 @@ do_transfer() local_addr="0.0.0.0" fi + cmsg="TIMESTAMPNS" + if mptcp_lib_kallsyms_has "mptcp_ioctl$"; then + cmsg+=",TCPINQ" + fi + timeout ${timeout_test} \ ip netns exec ${listener_ns} \ - $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c TIMESTAMPNS,TCPINQ \ + $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \ ${local_addr} < "$sin" > "$sout" & local spid=$! @@ -192,7 +202,7 @@ do_transfer() timeout ${timeout_test} \ ip netns exec ${connector_ns} \ - $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c TIMESTAMPNS,TCPINQ \ + $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c "${cmsg}" \ $connect_addr < "$cin" > "$cout" & local cpid=$! @@ -249,6 +259,11 @@ do_mptcp_sockopt_tests() { local lret=0 + if ! mptcp_lib_kallsyms_has "mptcp_diag_fill_info$"; then + echo "INFO: MPTCP sockopt not supported: SKIP" + return + fi + ip netns exec "$ns_sbox" ./mptcp_sockopt lret=$? @@ -303,6 +318,11 @@ do_tcpinq_tests() { local lret=0 + if ! mptcp_lib_kallsyms_has "mptcp_ioctl$"; then + echo "INFO: TCP_INQ not supported: SKIP" + return + fi + local args for args in "-t tcp" "-r tcp"; do do_tcpinq_test $args diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 89839d1ff9d8..d02e0d63a8f9 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + ksft_skip=4 ret=0 @@ -34,6 +36,8 @@ cleanup() ip netns del $ns1 } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" @@ -69,8 +73,12 @@ check() } check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "defaults addr list" -check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 + +default_limits="$(ip netns exec $ns1 ./pm_nl_ctl limits)" +if mptcp_lib_expect_all_features; then + check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 subflows 2" "defaults limits" +fi ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.2 flags subflow dev lo @@ -117,12 +125,10 @@ ip netns exec $ns1 ./pm_nl_ctl flush check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "flush addrs" ip netns exec $ns1 ./pm_nl_ctl limits 9 1 -check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 2" "rcv addrs above hard limit" +check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "rcv addrs above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 1 9 -check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 2" "subflows above hard limit" +check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "subflows above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 8 8 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 8 @@ -172,14 +178,19 @@ subflow,backup 10.0.1.1" "set flags (backup)" ip netns exec $ns1 ./pm_nl_ctl set 10.0.1.1 flags nobackup check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow 10.0.1.1" " (nobackup)" + +# fullmesh support has been added later ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh -check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +if ip netns exec $ns1 ./pm_nl_ctl dump | grep -q "fullmesh" || + mptcp_lib_expect_all_features; then + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow,fullmesh 10.0.1.1" " (fullmesh)" -ip netns exec $ns1 ./pm_nl_ctl set id 1 flags nofullmesh -check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ + ip netns exec $ns1 ./pm_nl_ctl set id 1 flags nofullmesh + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow 10.0.1.1" " (nofullmesh)" -ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh -check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ + ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow,backup,fullmesh 10.0.1.1" " (backup,fullmesh)" +fi exit $ret diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 9f22f7e5027d..36a3c9d92e20 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + sec=$(date +%s) rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) ns1="ns1-$rndh" @@ -34,6 +36,8 @@ cleanup() done } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index b1eb7bce599d..98d9e4d2d3fc 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -1,10 +1,20 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + +mptcp_lib_check_mptcp +mptcp_lib_check_kallsyms + +if ! mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + echo "userspace pm tests are not supported by the kernel: SKIP" + exit ${KSFT_SKIP} +fi + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Cannot not run test without ip tool" - exit 1 + exit ${KSFT_SKIP} fi ANNOUNCED=6 # MPTCP_EVENT_ANNOUNCED @@ -905,6 +915,11 @@ test_listener() { print_title "Listener tests" + if ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then + stdbuf -o0 -e0 printf "LISTENER events \t[SKIP] Not supported\n" + return + fi + # Capture events on the network namespace running the client :>$client_evts diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index ee9a72982705..39a0e01f8554 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -76,7 +76,9 @@ struct sock_args { has_grp:1, has_expected_laddr:1, has_expected_raddr:1, - bind_test_only:1; + bind_test_only:1, + client_dontroute:1, + server_dontroute:1; unsigned short port; @@ -611,6 +613,18 @@ static int set_dsfield(int sd, int version, int dsfield) return 0; } +static int set_dontroute(int sd) +{ + unsigned int one = 1; + + if (setsockopt(sd, SOL_SOCKET, SO_DONTROUTE, &one, sizeof(one)) < 0) { + log_err_errno("setsockopt(SO_DONTROUTE)"); + return -1; + } + + return 0; +} + static int str_to_uint(const char *str, int min, int max, unsigned int *value) { int number; @@ -1351,6 +1365,14 @@ static int msock_init(struct sock_args *args, int server) if (set_dsfield(sd, AF_INET, args->dsfield) != 0) goto out_err; + if (server) { + if (args->server_dontroute && set_dontroute(sd) != 0) + goto out_err; + } else { + if (args->client_dontroute && set_dontroute(sd) != 0) + goto out_err; + } + if (args->dev && bind_to_device(sd, args->dev) != 0) goto out_err; else if (args->use_setsockopt && @@ -1482,6 +1504,9 @@ static int lsock_init(struct sock_args *args) if (set_dsfield(sd, args->version, args->dsfield) != 0) goto err; + if (args->server_dontroute && set_dontroute(sd) != 0) + goto err; + if (args->dev && bind_to_device(sd, args->dev) != 0) goto err; else if (args->use_setsockopt && @@ -1698,6 +1723,9 @@ static int connectsock(void *addr, socklen_t alen, struct sock_args *args) if (set_dsfield(sd, args->version, args->dsfield) != 0) goto err; + if (args->client_dontroute && set_dontroute(sd) != 0) + goto err; + if (args->dev && bind_to_device(sd, args->dev) != 0) goto err; else if (args->use_setsockopt && @@ -1905,10 +1933,14 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args) #define GETOPT_STR "sr:l:c:Q:p:t:g:P:DRn:M:X:m:d:I:BN:O:SUCi6xL:0:1:2:3:Fbqf" #define OPT_FORCE_BIND_KEY_IFINDEX 1001 #define OPT_NO_BIND_KEY_IFINDEX 1002 +#define OPT_CLIENT_DONTROUTE 1003 +#define OPT_SERVER_DONTROUTE 1004 static struct option long_opts[] = { {"force-bind-key-ifindex", 0, 0, OPT_FORCE_BIND_KEY_IFINDEX}, {"no-bind-key-ifindex", 0, 0, OPT_NO_BIND_KEY_IFINDEX}, + {"client-dontroute", 0, 0, OPT_CLIENT_DONTROUTE}, + {"server-dontroute", 0, 0, OPT_SERVER_DONTROUTE}, {0, 0, 0, 0} }; @@ -1954,6 +1986,12 @@ static void print_usage(char *prog) " --no-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX off\n" " --force-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX on\n" " (default: only if -I is passed)\n" + " --client-dontroute: don't use gateways for client socket: send\n" + " packets only if destination is on link (see\n" + " SO_DONTROUTE in socket(7))\n" + " --server-dontroute: don't use gateways for server socket: send\n" + " packets only if destination is on link (see\n" + " SO_DONTROUTE in socket(7))\n" "\n" " -g grp multicast group (e.g., 239.1.1.1)\n" " -i interactive mode (default is echo and terminate)\n" @@ -2076,6 +2114,12 @@ int main(int argc, char *argv[]) case OPT_NO_BIND_KEY_IFINDEX: args.bind_key_ifindex = -1; break; + case OPT_CLIENT_DONTROUTE: + args.client_dontroute = 1; + break; + case OPT_SERVER_DONTROUTE: + args.server_dontroute = 1; + break; case 'X': args.client_pw = optarg; break; diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 383ac6fc037d..ba286d680fd9 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -860,6 +860,7 @@ EOF fi # clean up any leftovers + echo 0 > /sys/bus/netdevsim/del_device $probed && rmmod netdevsim if [ $ret -ne 0 ]; then diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh index 1003119773e5..f96282362811 100755 --- a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh @@ -232,10 +232,14 @@ setup_rt_networking() local nsname=rt-${rt} ip netns add ${nsname} + + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip link set veth-rt-${rt} netns ${nsname} ip -netns ${nsname} link set veth-rt-${rt} name veth0 - ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 + ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad ip -netns ${nsname} link set veth0 up ip -netns ${nsname} link set lo up @@ -254,6 +258,12 @@ setup_hs() # set the networking for the host ip netns add ${hsname} + + # disable the rp_filter otherwise the kernel gets confused about how + # to route decap ipv4 packets. + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip -netns ${hsname} link add veth0 type veth peer name ${rtveth} ip -netns ${hsname} link set ${rtveth} netns ${rtname} ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hs}/24 dev veth0 @@ -272,11 +282,6 @@ setup_hs() ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.proxy_arp=1 - # disable the rp_filter otherwise the kernel gets confused about how - # to route decap ipv4 packets. - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.rp_filter=0 - ip netns exec ${rtname} sh -c "echo 1 > /proc/sys/net/vrf/strict_mode" } diff --git a/tools/testing/selftests/net/test_vxlan_nolocalbypass.sh b/tools/testing/selftests/net/test_vxlan_nolocalbypass.sh new file mode 100755 index 000000000000..f75212bf142c --- /dev/null +++ b/tools/testing/selftests/net/test_vxlan_nolocalbypass.sh @@ -0,0 +1,240 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test is for checking the [no]localbypass VXLAN device option. The test +# configures two VXLAN devices in the same network namespace and a tc filter on +# the loopback device that drops encapsulated packets. The test sends packets +# from the first VXLAN device and verifies that by default these packets are +# received by the second VXLAN device. The test then enables the nolocalbypass +# option and verifies that packets are no longer received by the second VXLAN +# device. + +ret=0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +TESTS=" + nolocalbypass +" +VERBOSE=0 +PAUSE_ON_FAIL=no +PAUSE=no + +################################################################################ +# Utilities + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf "TEST: %-60s [ OK ]\n" "${msg}" + nsuccess=$((nsuccess+1)) + else + ret=1 + nfail=$((nfail+1)) + printf "TEST: %-60s [FAIL]\n" "${msg}" + if [ "$VERBOSE" = "1" ]; then + echo " rc=$rc, expected $expected" + fi + + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi + + if [ "${PAUSE}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + + [ "$VERBOSE" = "1" ] && echo +} + +run_cmd() +{ + local cmd="$1" + local out + local stderr="2>/dev/null" + + if [ "$VERBOSE" = "1" ]; then + printf "COMMAND: $cmd\n" + stderr= + fi + + out=$(eval $cmd $stderr) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo " $out" + fi + + return $rc +} + +tc_check_packets() +{ + local ns=$1; shift + local id=$1; shift + local handle=$1; shift + local count=$1; shift + local pkts + + sleep 0.1 + pkts=$(tc -n $ns -j -s filter show $id \ + | jq ".[] | select(.options.handle == $handle) | \ + .options.actions[0].stats.packets") + [[ $pkts == $count ]] +} + +################################################################################ +# Setup + +setup() +{ + ip netns add ns1 + + ip -n ns1 link set dev lo up + ip -n ns1 address add 192.0.2.1/32 dev lo + ip -n ns1 address add 198.51.100.1/32 dev lo + + ip -n ns1 link add name vx0 up type vxlan id 100 local 198.51.100.1 \ + dstport 4789 nolearning + ip -n ns1 link add name vx1 up type vxlan id 100 dstport 4790 +} + +cleanup() +{ + ip netns del ns1 &> /dev/null +} + +################################################################################ +# Tests + +nolocalbypass() +{ + local smac=00:01:02:03:04:05 + local dmac=00:0a:0b:0c:0d:0e + + run_cmd "bridge -n ns1 fdb add $dmac dev vx0 self static dst 192.0.2.1 port 4790" + + run_cmd "tc -n ns1 qdisc add dev vx1 clsact" + run_cmd "tc -n ns1 filter add dev vx1 ingress pref 1 handle 101 proto all flower src_mac $smac dst_mac $dmac action pass" + + run_cmd "tc -n ns1 qdisc add dev lo clsact" + run_cmd "tc -n ns1 filter add dev lo ingress pref 1 handle 101 proto ip flower ip_proto udp dst_port 4790 action drop" + + run_cmd "ip -n ns1 -d -j link show dev vx0 | jq -e '.[][\"linkinfo\"][\"info_data\"][\"localbypass\"] == true'" + log_test $? 0 "localbypass enabled" + + run_cmd "ip netns exec ns1 mausezahn vx0 -a $smac -b $dmac -c 1 -p 100 -q" + + tc_check_packets "ns1" "dev vx1 ingress" 101 1 + log_test $? 0 "Packet received by local VXLAN device - localbypass" + + run_cmd "ip -n ns1 link set dev vx0 type vxlan nolocalbypass" + + run_cmd "ip -n ns1 -d -j link show dev vx0 | jq -e '.[][\"linkinfo\"][\"info_data\"][\"localbypass\"] == false'" + log_test $? 0 "localbypass disabled" + + run_cmd "ip netns exec ns1 mausezahn vx0 -a $smac -b $dmac -c 1 -p 100 -q" + + tc_check_packets "ns1" "dev vx1 ingress" 101 1 + log_test $? 0 "Packet not received by local VXLAN device - nolocalbypass" + + run_cmd "ip -n ns1 link set dev vx0 type vxlan localbypass" + + run_cmd "ip -n ns1 -d -j link show dev vx0 | jq -e '.[][\"linkinfo\"][\"info_data\"][\"localbypass\"] == true'" + log_test $? 0 "localbypass enabled" + + run_cmd "ip netns exec ns1 mausezahn vx0 -a $smac -b $dmac -c 1 -p 100 -q" + + tc_check_packets "ns1" "dev vx1 ingress" 101 2 + log_test $? 0 "Packet received by local VXLAN device - localbypass" +} + +################################################################################ +# Usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -t <test> Test(s) to run (default: all) + (options: $TESTS) + -p Pause on fail + -P Pause after each test before cleanup + -v Verbose mode (show commands and output) +EOF +} + +################################################################################ +# Main + +trap cleanup EXIT + +while getopts ":t:pPvh" opt; do + case $opt in + t) TESTS=$OPTARG ;; + p) PAUSE_ON_FAIL=yes;; + P) PAUSE=yes;; + v) VERBOSE=$(($VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +# Make sure we don't pause twice. +[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit $ksft_skip; +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +if [ ! -x "$(command -v bridge)" ]; then + echo "SKIP: Could not run test without bridge tool" + exit $ksft_skip +fi + +if [ ! -x "$(command -v mausezahn)" ]; then + echo "SKIP: Could not run test without mausezahn tool" + exit $ksft_skip +fi + +if [ ! -x "$(command -v jq)" ]; then + echo "SKIP: Could not run test without jq tool" + exit $ksft_skip +fi + +ip link help vxlan 2>&1 | grep -q "localbypass" +if [ $? -ne 0 ]; then + echo "SKIP: iproute2 ip too old, missing VXLAN nolocalbypass support" + exit $ksft_skip +fi + +cleanup + +for t in $TESTS +do + setup; $t; cleanup; +done + +if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} +fi + +exit $ret diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index e699548d4247..a3c57004344c 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -15,6 +15,7 @@ #include <linux/tcp.h> #include <linux/socket.h> +#include <sys/epoll.h> #include <sys/types.h> #include <sys/sendfile.h> #include <sys/socket.h> @@ -25,6 +26,8 @@ #define TLS_PAYLOAD_MAX_LEN 16384 #define SOL_TLS 282 +static int fips_enabled; + struct tls_crypto_info_keys { union { struct tls12_crypto_info_aes_gcm_128 aes128; @@ -235,7 +238,7 @@ FIXTURE_VARIANT(tls) { uint16_t tls_version; uint16_t cipher_type; - bool nopad; + bool nopad, fips_non_compliant; }; FIXTURE_VARIANT_ADD(tls, 12_aes_gcm) @@ -254,24 +257,28 @@ FIXTURE_VARIANT_ADD(tls, 12_chacha) { .tls_version = TLS_1_2_VERSION, .cipher_type = TLS_CIPHER_CHACHA20_POLY1305, + .fips_non_compliant = true, }; FIXTURE_VARIANT_ADD(tls, 13_chacha) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_CHACHA20_POLY1305, + .fips_non_compliant = true, }; FIXTURE_VARIANT_ADD(tls, 13_sm4_gcm) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_SM4_GCM, + .fips_non_compliant = true, }; FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_SM4_CCM, + .fips_non_compliant = true, }; FIXTURE_VARIANT_ADD(tls, 12_aes_ccm) @@ -311,6 +318,9 @@ FIXTURE_SETUP(tls) int one = 1; int ret; + if (fips_enabled && variant->fips_non_compliant) + SKIP(return, "Unsupported cipher in FIPS mode"); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12); @@ -1637,6 +1647,136 @@ TEST_F(tls_err, timeo) } } +TEST_F(tls_err, poll_partial_rec) +{ + struct pollfd pfd = { }; + ssize_t rec_len; + char rec[256]; + char buf[128]; + + if (self->notls) + SKIP(return, "no TLS support"); + + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 1), 0); + + memrnd(buf, sizeof(buf)); + EXPECT_EQ(send(self->fd, buf, sizeof(buf), 0), sizeof(buf)); + rec_len = recv(self->cfd, rec, sizeof(rec), 0); + EXPECT_GT(rec_len, sizeof(buf)); + + /* Write 100B, not the full record ... */ + EXPECT_EQ(send(self->fd2, rec, 100, 0), 100); + /* ... no full record should mean no POLLIN */ + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 1), 0); + /* Now write the rest, and it should all pop out of the other end. */ + EXPECT_EQ(send(self->fd2, rec + 100, rec_len - 100, 0), rec_len - 100); + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 1), 1); + EXPECT_EQ(recv(self->cfd2, rec, sizeof(rec), 0), sizeof(buf)); + EXPECT_EQ(memcmp(buf, rec, sizeof(buf)), 0); +} + +TEST_F(tls_err, epoll_partial_rec) +{ + struct epoll_event ev, events[10]; + ssize_t rec_len; + char rec[256]; + char buf[128]; + int epollfd; + + if (self->notls) + SKIP(return, "no TLS support"); + + epollfd = epoll_create1(0); + ASSERT_GE(epollfd, 0); + + memset(&ev, 0, sizeof(ev)); + ev.events = EPOLLIN; + ev.data.fd = self->cfd2; + ASSERT_GE(epoll_ctl(epollfd, EPOLL_CTL_ADD, self->cfd2, &ev), 0); + + EXPECT_EQ(epoll_wait(epollfd, events, 10, 0), 0); + + memrnd(buf, sizeof(buf)); + EXPECT_EQ(send(self->fd, buf, sizeof(buf), 0), sizeof(buf)); + rec_len = recv(self->cfd, rec, sizeof(rec), 0); + EXPECT_GT(rec_len, sizeof(buf)); + + /* Write 100B, not the full record ... */ + EXPECT_EQ(send(self->fd2, rec, 100, 0), 100); + /* ... no full record should mean no POLLIN */ + EXPECT_EQ(epoll_wait(epollfd, events, 10, 0), 0); + /* Now write the rest, and it should all pop out of the other end. */ + EXPECT_EQ(send(self->fd2, rec + 100, rec_len - 100, 0), rec_len - 100); + EXPECT_EQ(epoll_wait(epollfd, events, 10, 0), 1); + EXPECT_EQ(recv(self->cfd2, rec, sizeof(rec), 0), sizeof(buf)); + EXPECT_EQ(memcmp(buf, rec, sizeof(buf)), 0); + + close(epollfd); +} + +TEST_F(tls_err, poll_partial_rec_async) +{ + struct pollfd pfd = { }; + ssize_t rec_len; + char rec[256]; + char buf[128]; + char token; + int p[2]; + int ret; + + if (self->notls) + SKIP(return, "no TLS support"); + + ASSERT_GE(pipe(p), 0); + + memrnd(buf, sizeof(buf)); + EXPECT_EQ(send(self->fd, buf, sizeof(buf), 0), sizeof(buf)); + rec_len = recv(self->cfd, rec, sizeof(rec), 0); + EXPECT_GT(rec_len, sizeof(buf)); + + ret = fork(); + ASSERT_GE(ret, 0); + + if (ret) { + int status, pid2; + + close(p[1]); + usleep(1000); /* Give child a head start */ + + EXPECT_EQ(send(self->fd2, rec, 100, 0), 100); + + EXPECT_EQ(read(p[0], &token, 1), 1); /* Barrier #1 */ + + EXPECT_EQ(send(self->fd2, rec + 100, rec_len - 100, 0), + rec_len - 100); + + pid2 = wait(&status); + EXPECT_EQ(pid2, ret); + EXPECT_EQ(status, 0); + } else { + close(p[0]); + + /* Child should sleep in poll(), never get a wake */ + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 5), 0); + + EXPECT_EQ(write(p[1], &token, 1), 1); /* Barrier #1 */ + + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 5), 1); + + exit(!_metadata->passed); + } +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; @@ -1865,4 +2005,17 @@ TEST(prequeue) { close(cfd); } +static void __attribute__((constructor)) fips_check(void) { + int res; + FILE *f; + + f = fopen("/proc/sys/crypto/fips_enabled", "r"); + if (f) { + res = fscanf(f, "%d", &fips_enabled); + if (res != 1) + ksft_print_msg("ERROR: Couldn't read /proc/sys/crypto/fips_enabled\n"); + fclose(f); + } +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/vrf-xfrm-tests.sh b/tools/testing/selftests/net/vrf-xfrm-tests.sh index 184da81f554f..452638ae8aed 100755 --- a/tools/testing/selftests/net/vrf-xfrm-tests.sh +++ b/tools/testing/selftests/net/vrf-xfrm-tests.sh @@ -264,60 +264,60 @@ setup_xfrm() ip -netns host1 xfrm state add src ${HOST1_4} dst ${HOST2_4} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_4} dst ${h2_4} ${devarg} ip -netns host2 xfrm state add src ${HOST1_4} dst ${HOST2_4} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_4} dst ${h2_4} ip -netns host1 xfrm state add src ${HOST2_4} dst ${HOST1_4} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_4} dst ${h1_4} ${devarg} ip -netns host2 xfrm state add src ${HOST2_4} dst ${HOST1_4} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_4} dst ${h1_4} ip -6 -netns host1 xfrm state add src ${HOST1_6} dst ${HOST2_6} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_6} dst ${h2_6} ${devarg} ip -6 -netns host2 xfrm state add src ${HOST1_6} dst ${HOST2_6} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_6} dst ${h2_6} ip -6 -netns host1 xfrm state add src ${HOST2_6} dst ${HOST1_6} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_6} dst ${h1_6} ${devarg} ip -6 -netns host2 xfrm state add src ${HOST2_6} dst ${HOST1_6} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_6} dst ${h1_6} } diff --git a/tools/testing/selftests/nolibc/.gitignore b/tools/testing/selftests/nolibc/.gitignore index 4696df589d68..52f613cdad54 100644 --- a/tools/testing/selftests/nolibc/.gitignore +++ b/tools/testing/selftests/nolibc/.gitignore @@ -1,4 +1,5 @@ /initramfs/ +/libc-test /nolibc-test /run.out /sysroot/ diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index bbce57420465..1b7b3c82f8ad 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -64,7 +64,7 @@ QEMU_ARGS_mips = -M malta -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_riscv = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_s390 = -M s390-ccw-virtio -m 1G -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_loongarch = -M virt -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS = $(QEMU_ARGS_$(ARCH)) +QEMU_ARGS = $(QEMU_ARGS_$(ARCH)) $(QEMU_ARGS_EXTRA) # OUTPUT is only set when run from the main makefile, otherwise # it defaults to this nolibc directory. @@ -76,16 +76,12 @@ else Q=@ endif -CFLAGS_STACKPROTECTOR = -DNOLIBC_STACKPROTECTOR \ - $(call cc-option,-mstack-protector-guard=global) \ - $(call cc-option,-fstack-protector-all) -CFLAGS_STKP_i386 = $(CFLAGS_STACKPROTECTOR) -CFLAGS_STKP_x86_64 = $(CFLAGS_STACKPROTECTOR) -CFLAGS_STKP_x86 = $(CFLAGS_STACKPROTECTOR) CFLAGS_s390 = -m64 -CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables \ +CFLAGS_mips = -EL +CFLAGS_STACKPROTECTOR ?= $(call cc-option,-mstack-protector-guard=global $(call cc-option,-fstack-protector-all)) +CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables -std=c89 \ $(call cc-option,-fno-stack-protector) \ - $(CFLAGS_STKP_$(ARCH)) $(CFLAGS_$(ARCH)) + $(CFLAGS_$(ARCH)) $(CFLAGS_STACKPROTECTOR) LDFLAGS := -s help: @@ -94,6 +90,7 @@ help: @echo " help this help" @echo " sysroot create the nolibc sysroot here (uses \$$ARCH)" @echo " nolibc-test build the executable (uses \$$CC and \$$CROSS_COMPILE)" + @echo " libc-test build an executable using the compiler's default libc instead" @echo " run-user runs the executable under QEMU (uses \$$ARCH, \$$TEST)" @echo " initramfs prepare the initramfs with nolibc-test" @echo " defconfig create a fresh new default config (uses \$$ARCH)" @@ -128,10 +125,16 @@ nolibc-test: nolibc-test.c sysroot/$(ARCH)/include $(QUIET_CC)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ \ -nostdlib -static -Isysroot/$(ARCH)/include $< -lgcc +libc-test: nolibc-test.c + $(QUIET_CC)$(CC) -o $@ $< + # qemu user-land test run-user: nolibc-test $(Q)qemu-$(QEMU_ARCH) ./nolibc-test > "$(CURDIR)/run.out" || : - $(Q)grep -w FAIL "$(CURDIR)/run.out" && echo "See all results in $(CURDIR)/run.out" || echo "$$(grep -c ^[0-9].*OK $(CURDIR)/run.out) test(s) passed." + $(Q)awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{f++} /\[SKIPPED\][\r]*$$/{s++} \ + END{ printf("%d test(s) passed, %d skipped, %d failed.", p, s, f); \ + if (s+f > 0) printf(" See all results in %s\n", ARGV[1]); else print; }' \ + $(CURDIR)/run.out initramfs: nolibc-test $(QUIET_MKDIR)mkdir -p initramfs @@ -147,18 +150,26 @@ kernel: initramfs # run the tests after building the kernel run: kernel $(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(srctree)/$(IMAGE)" -serial stdio $(QEMU_ARGS) > "$(CURDIR)/run.out" - $(Q)grep -w FAIL "$(CURDIR)/run.out" && echo "See all results in $(CURDIR)/run.out" || echo "$$(grep -c ^[0-9].*OK $(CURDIR)/run.out) test(s) passed." + $(Q)awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{f++} /\[SKIPPED\][\r]*$$/{s++} \ + END{ printf("%d test(s) passed, %d skipped, %d failed.", p, s, f); \ + if (s+f > 0) printf(" See all results in %s\n", ARGV[1]); else print; }' \ + $(CURDIR)/run.out # re-run the tests from an existing kernel rerun: $(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(srctree)/$(IMAGE)" -serial stdio $(QEMU_ARGS) > "$(CURDIR)/run.out" - $(Q)grep -w FAIL "$(CURDIR)/run.out" && echo "See all results in $(CURDIR)/run.out" || echo "$$(grep -c ^[0-9].*OK $(CURDIR)/run.out) test(s) passed." + $(Q)awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{f++} /\[SKIPPED\][\r]*$$/{s++} \ + END{ printf("%d test(s) passed, %d skipped, %d failed.", p, s, f); \ + if (s+f > 0) printf(" See all results in %s\n", ARGV[1]); else print; }' \ + $(CURDIR)/run.out clean: $(call QUIET_CLEAN, sysroot) $(Q)rm -rf sysroot $(call QUIET_CLEAN, nolibc-test) $(Q)rm -f nolibc-test + $(call QUIET_CLEAN, libc-test) + $(Q)rm -f libc-test $(call QUIET_CLEAN, initramfs) $(Q)rm -rf initramfs $(call QUIET_CLEAN, run.out) diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index 21bacc928bf7..486334981e60 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -1,10 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ #define _GNU_SOURCE -/* platform-specific include files coming from the compiler */ -#include <limits.h> - /* libc-specific include files * The program may be built in 3 ways: * $(CC) -nostdlib -include /path/to/nolibc.h => NOLIBC already defined @@ -20,7 +17,9 @@ #include <linux/reboot.h> #include <sys/io.h> #include <sys/ioctl.h> +#include <sys/mman.h> #include <sys/mount.h> +#include <sys/prctl.h> #include <sys/reboot.h> #include <sys/stat.h> #include <sys/syscall.h> @@ -34,7 +33,10 @@ #include <sched.h> #include <signal.h> #include <stdarg.h> +#include <stddef.h> +#include <stdint.h> #include <unistd.h> +#include <limits.h> #endif #endif @@ -43,8 +45,8 @@ char **environ; /* definition of a series of tests */ struct test { - const char *name; // test name - int (*func)(int min, int max); // handler + const char *name; /* test name */ + int (*func)(int min, int max); /* handler */ }; #ifndef _NOLIBC_STDLIB_H @@ -103,24 +105,32 @@ const char *errorname(int err) CASE_ERR(EDOM); CASE_ERR(ERANGE); CASE_ERR(ENOSYS); + CASE_ERR(EOVERFLOW); default: return itoa(err); } } +static void putcharn(char c, size_t n) +{ + char buf[64]; + + memset(buf, c, n); + buf[n] = '\0'; + fputs(buf, stdout); +} + static int pad_spc(int llen, int cnt, const char *fmt, ...) { va_list args; - int len; int ret; - for (len = 0; len < cnt - llen; len++) - putchar(' '); + putcharn(' ', cnt - llen); va_start(args, fmt); ret = vfprintf(stdout, fmt, args); va_end(args); - return ret < 0 ? ret : ret + len; + return ret < 0 ? ret : ret + cnt - llen; } /* The tests below are intended to be used by the macroes, which evaluate @@ -162,7 +172,7 @@ static int expect_eq(uint64_t expr, int llen, uint64_t val) { int ret = !(expr == val); - llen += printf(" = %lld ", expr); + llen += printf(" = %lld ", (long long)expr); pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); return ret; } @@ -290,18 +300,24 @@ static int expect_sysne(int expr, int llen, int val) } +#define EXPECT_SYSER2(cond, expr, expret, experr1, experr2) \ + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_syserr2(expr, expret, experr1, experr2, llen); } while (0) + #define EXPECT_SYSER(cond, expr, expret, experr) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_syserr(expr, expret, experr, llen); } while (0) + EXPECT_SYSER2(cond, expr, expret, experr, 0) -static int expect_syserr(int expr, int expret, int experr, int llen) +static int expect_syserr2(int expr, int expret, int experr1, int experr2, int llen) { int ret = 0; int _errno = errno; llen += printf(" = %d %s ", expr, errorname(_errno)); - if (expr != expret || _errno != experr) { + if (expr != expret || (_errno != experr1 && _errno != experr2)) { ret = 1; - llen += printf(" != (%d %s) ", expret, errorname(experr)); + if (experr2 == 0) + llen += printf(" != (%d %s) ", expret, errorname(experr1)); + else + llen += printf(" != (%d %s %s) ", expret, errorname(experr1), errorname(experr2)); llen += pad_spc(llen, 64, "[FAIL]\n"); } else { llen += pad_spc(llen, 64, " [OK]\n"); @@ -471,11 +487,60 @@ static int test_getpagesize(void) return !c; } +static int test_fork(void) +{ + int status; + pid_t pid; + + /* flush the printf buffer to avoid child flush it */ + fflush(stdout); + fflush(stderr); + + pid = fork(); + + switch (pid) { + case -1: + return 1; + + case 0: + exit(123); + + default: + pid = waitpid(pid, &status, 0); + + return pid == -1 || !WIFEXITED(status) || WEXITSTATUS(status) != 123; + } +} + +static int test_stat_timestamps(void) +{ + struct stat st; + + if (sizeof(st.st_atim.tv_sec) != sizeof(st.st_atime)) + return 1; + + if (stat("/proc/self/", &st)) + return 1; + + if (st.st_atim.tv_sec != st.st_atime || st.st_atim.tv_nsec > 1000000000) + return 1; + + if (st.st_mtim.tv_sec != st.st_mtime || st.st_mtim.tv_nsec > 1000000000) + return 1; + + if (st.st_ctim.tv_sec != st.st_ctime || st.st_ctim.tv_nsec > 1000000000) + return 1; + + return 0; +} + /* Run syscall tests between IDs <min> and <max>. * Return 0 on success, non-zero on failure. */ int run_syscall(int min, int max) { + struct timeval tv; + struct timezone tz; struct stat stat_buf; int euid0; int proc; @@ -491,7 +556,7 @@ int run_syscall(int min, int max) euid0 = geteuid() == 0; for (test = min; test >= 0 && test <= max; test++) { - int llen = 0; // line length + int llen = 0; /* line length */ /* avoid leaving empty lines below, this will insert holes into * test numbers. @@ -527,14 +592,11 @@ int run_syscall(int min, int max) CASE_TEST(dup3_0); tmp = dup3(0, 100, 0); EXPECT_SYSNE(1, tmp, -1); close(tmp); break; CASE_TEST(dup3_m1); tmp = dup3(-1, 100, 0); EXPECT_SYSER(1, tmp, -1, EBADF); if (tmp != -1) close(tmp); break; CASE_TEST(execve_root); EXPECT_SYSER(1, execve("/", (char*[]){ [0] = "/", [1] = NULL }, NULL), -1, EACCES); break; + CASE_TEST(fork); EXPECT_SYSZR(1, test_fork()); break; CASE_TEST(getdents64_root); EXPECT_SYSNE(1, test_getdents64("/"), -1); break; CASE_TEST(getdents64_null); EXPECT_SYSER(1, test_getdents64("/dev/null"), -1, ENOTDIR); break; - CASE_TEST(gettimeofday_null); EXPECT_SYSZR(1, gettimeofday(NULL, NULL)); break; -#ifdef NOLIBC - CASE_TEST(gettimeofday_bad1); EXPECT_SYSER(1, gettimeofday((void *)1, NULL), -1, EFAULT); break; - CASE_TEST(gettimeofday_bad2); EXPECT_SYSER(1, gettimeofday(NULL, (void *)1), -1, EFAULT); break; - CASE_TEST(gettimeofday_bad2); EXPECT_SYSER(1, gettimeofday(NULL, (void *)1), -1, EFAULT); break; -#endif + CASE_TEST(gettimeofday_tv); EXPECT_SYSZR(1, gettimeofday(&tv, NULL)); break; + CASE_TEST(gettimeofday_tv_tz);EXPECT_SYSZR(1, gettimeofday(&tv, &tz)); break; CASE_TEST(getpagesize); EXPECT_SYSZR(1, test_getpagesize()); break; CASE_TEST(ioctl_tiocinq); EXPECT_SYSZR(1, ioctl(0, TIOCINQ, &tmp)); break; CASE_TEST(ioctl_tiocinq); EXPECT_SYSZR(1, ioctl(0, TIOCINQ, &tmp)); break; @@ -550,6 +612,7 @@ int run_syscall(int min, int max) CASE_TEST(poll_null); EXPECT_SYSZR(1, poll(NULL, 0, 0)); break; CASE_TEST(poll_stdout); EXPECT_SYSNE(1, ({ struct pollfd fds = { 1, POLLOUT, 0}; poll(&fds, 1, 0); }), -1); break; CASE_TEST(poll_fault); EXPECT_SYSER(1, poll((void *)1, 1, 0), -1, EFAULT); break; + CASE_TEST(prctl); EXPECT_SYSER(1, prctl(PR_SET_NAME, (unsigned long)NULL, 0, 0, 0), -1, EFAULT); break; CASE_TEST(read_badf); EXPECT_SYSER(1, read(-1, &tmp, 1), -1, EBADF); break; CASE_TEST(sched_yield); EXPECT_SYSZR(1, sched_yield()); break; CASE_TEST(select_null); EXPECT_SYSZR(1, ({ struct timeval tv = { 0 }; select(0, NULL, NULL, NULL, &tv); })); break; @@ -557,6 +620,7 @@ int run_syscall(int min, int max) CASE_TEST(select_fault); EXPECT_SYSER(1, select(1, (void *)1, NULL, NULL, 0), -1, EFAULT); break; CASE_TEST(stat_blah); EXPECT_SYSER(1, stat("/proc/self/blah", &stat_buf), -1, ENOENT); break; CASE_TEST(stat_fault); EXPECT_SYSER(1, stat(NULL, &stat_buf), -1, EFAULT); break; + CASE_TEST(stat_timestamps); EXPECT_SYSZR(1, test_stat_timestamps()); break; CASE_TEST(symlink_root); EXPECT_SYSER(1, symlink("/", "/"), -1, EEXIST); break; CASE_TEST(unlink_root); EXPECT_SYSER(1, unlink("/"), -1, EISDIR); break; CASE_TEST(unlink_blah); EXPECT_SYSER(1, unlink("/proc/self/blah"), -1, ENOENT); break; @@ -565,6 +629,8 @@ int run_syscall(int min, int max) CASE_TEST(waitpid_child); EXPECT_SYSER(1, waitpid(getpid(), &tmp, WNOHANG), -1, ECHILD); break; CASE_TEST(write_badf); EXPECT_SYSER(1, write(-1, &tmp, 1), -1, EBADF); break; CASE_TEST(write_zero); EXPECT_SYSZR(1, write(1, &tmp, 0)); break; + CASE_TEST(syscall_noargs); EXPECT_SYSEQ(1, syscall(__NR_getpid), getpid()); break; + CASE_TEST(syscall_args); EXPECT_SYSER(1, syscall(__NR_statx, 0, NULL, 0, 0, NULL), -1, EFAULT); break; case __LINE__: return ret; /* must be last */ /* note: do not set any defaults so as to permit holes above */ @@ -581,7 +647,7 @@ int run_stdlib(int min, int max) void *p1, *p2; for (test = min; test >= 0 && test <= max; test++) { - int llen = 0; // line length + int llen = 0; /* line length */ /* avoid leaving empty lines below, this will insert holes into * test numbers. @@ -639,9 +705,9 @@ int run_stdlib(int min, int max) CASE_TEST(limit_int_fast32_min); EXPECT_EQ(1, INT_FAST32_MIN, (int_fast32_t) INTPTR_MIN); break; CASE_TEST(limit_int_fast32_max); EXPECT_EQ(1, INT_FAST32_MAX, (int_fast32_t) INTPTR_MAX); break; CASE_TEST(limit_uint_fast32_max); EXPECT_EQ(1, UINT_FAST32_MAX, (uint_fast32_t) UINTPTR_MAX); break; - CASE_TEST(limit_int_fast64_min); EXPECT_EQ(1, INT_FAST64_MIN, (int_fast64_t) INTPTR_MIN); break; - CASE_TEST(limit_int_fast64_max); EXPECT_EQ(1, INT_FAST64_MAX, (int_fast64_t) INTPTR_MAX); break; - CASE_TEST(limit_uint_fast64_max); EXPECT_EQ(1, UINT_FAST64_MAX, (uint_fast64_t) UINTPTR_MAX); break; + CASE_TEST(limit_int_fast64_min); EXPECT_EQ(1, INT_FAST64_MIN, (int_fast64_t) INT64_MIN); break; + CASE_TEST(limit_int_fast64_max); EXPECT_EQ(1, INT_FAST64_MAX, (int_fast64_t) INT64_MAX); break; + CASE_TEST(limit_uint_fast64_max); EXPECT_EQ(1, UINT_FAST64_MAX, (uint_fast64_t) UINT64_MAX); break; #if __SIZEOF_LONG__ == 8 CASE_TEST(limit_intptr_min); EXPECT_EQ(1, INTPTR_MIN, (intptr_t) 0x8000000000000000LL); break; CASE_TEST(limit_intptr_max); EXPECT_EQ(1, INTPTR_MAX, (intptr_t) 0x7fffffffffffffffLL); break; @@ -667,17 +733,98 @@ int run_stdlib(int min, int max) return ret; } -#if defined(__clang__) -__attribute__((optnone)) -#elif defined(__GNUC__) -__attribute__((optimize("O0"))) -#endif +#define EXPECT_VFPRINTF(c, expected, fmt, ...) \ + ret += expect_vfprintf(llen, c, expected, fmt, ##__VA_ARGS__) + +static int expect_vfprintf(int llen, size_t c, const char *expected, const char *fmt, ...) +{ + int ret, fd, w, r; + char buf[100]; + FILE *memfile; + va_list args; + + fd = memfd_create("vfprintf", 0); + if (fd == -1) { + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + } + + memfile = fdopen(fd, "w+"); + if (!memfile) { + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + } + + va_start(args, fmt); + w = vfprintf(memfile, fmt, args); + va_end(args); + + if (w != c) { + llen += printf(" written(%d) != %d", w, (int) c); + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + } + + fflush(memfile); + lseek(fd, 0, SEEK_SET); + + r = read(fd, buf, sizeof(buf) - 1); + buf[r] = '\0'; + + fclose(memfile); + + if (r != w) { + llen += printf(" written(%d) != read(%d)", w, r); + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + } + + llen += printf(" \"%s\" = \"%s\"", expected, buf); + ret = strncmp(expected, buf, c); + + pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); + return ret; +} + +static int run_vfprintf(int min, int max) +{ + int test; + int tmp; + int ret = 0; + void *p1, *p2; + + for (test = min; test >= 0 && test <= max; test++) { + int llen = 0; /* line length */ + + /* avoid leaving empty lines below, this will insert holes into + * test numbers. + */ + switch (test + __LINE__ + 1) { + CASE_TEST(empty); EXPECT_VFPRINTF(0, "", ""); break; + CASE_TEST(simple); EXPECT_VFPRINTF(3, "foo", "foo"); break; + CASE_TEST(string); EXPECT_VFPRINTF(3, "foo", "%s", "foo"); break; + CASE_TEST(number); EXPECT_VFPRINTF(4, "1234", "%d", 1234); break; + CASE_TEST(negnumber); EXPECT_VFPRINTF(5, "-1234", "%d", -1234); break; + CASE_TEST(unsigned); EXPECT_VFPRINTF(5, "12345", "%u", 12345); break; + CASE_TEST(char); EXPECT_VFPRINTF(1, "c", "%c", 'c'); break; + CASE_TEST(hex); EXPECT_VFPRINTF(1, "f", "%x", 0xf); break; + CASE_TEST(pointer); EXPECT_VFPRINTF(3, "0x1", "%p", (void *) 0x1); break; + case __LINE__: + return ret; /* must be last */ + /* note: do not set any defaults so as to permit holes above */ + } + } + return ret; +} + static int smash_stack(void) { char buf[100]; + volatile char *ptr = buf; + size_t i; - for (size_t i = 0; i < 200; i++) - buf[i] = 'P'; + for (i = 0; i < 200; i++) + ptr[i] = 'P'; return 1; } @@ -689,12 +836,20 @@ static int run_protection(int min, int max) llen += printf("0 -fstackprotector "); -#if !defined(NOLIBC_STACKPROTECTOR) +#if !defined(_NOLIBC_STACKPROTECTOR) llen += printf("not supported"); pad_spc(llen, 64, "[SKIPPED]\n"); return 0; #endif +#if defined(_NOLIBC_STACKPROTECTOR) + if (!__stack_chk_guard) { + llen += printf("__stack_chk_guard not initialized"); + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + } +#endif + pid = -1; pid = fork(); @@ -708,6 +863,7 @@ static int run_protection(int min, int max) close(STDOUT_FILENO); close(STDERR_FILENO); + prctl(PR_SET_DUMPABLE, 0, 0, 0, 0); smash_stack(); return 1; @@ -778,6 +934,7 @@ static const struct test test_names[] = { /* add new tests here */ { .name = "syscall", .func = run_syscall }, { .name = "stdlib", .func = run_stdlib }, + { .name = "vfprintf", .func = run_vfprintf }, { .name = "protection", .func = run_protection }, { 0 } }; @@ -785,7 +942,7 @@ static const struct test test_names[] = { int main(int argc, char **argv, char **envp) { int min = 0; - int max = __INT_MAX__; + int max = INT_MAX; int ret = 0; int err; int idx; @@ -833,7 +990,7 @@ int main(int argc, char **argv, char **envp) * here, which defaults to the full range. */ do { - min = 0; max = __INT_MAX__; + min = 0; max = INT_MAX; value = colon; if (value && *value) { colon = strchr(value, ':'); @@ -899,7 +1056,7 @@ int main(int argc, char **argv, char **envp) #else else if (ioperm(0x501, 1, 1) == 0) #endif - asm volatile ("outb %%al, %%dx" :: "d"(0x501), "a"(0)); + __asm__ volatile ("outb %%al, %%dx" :: "d"(0x501), "a"(0)); /* if it does nothing, fall back to the regular panic */ #endif } diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index 6922d6417e1c..88d6830ee004 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -90,7 +90,6 @@ again: } ret = WEXITSTATUS(status); - ksft_print_msg("waitpid WEXITSTATUS=%d\n", ret); return ret; } diff --git a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c index 3fd8e903118f..4e86f927880c 100644 --- a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c +++ b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c @@ -143,6 +143,7 @@ static inline int child_join(struct child *child, struct error *err) r = -1; } + ksft_print_msg("waitpid WEXITSTATUS=%d\n", r); return r; } diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index e2dd4ed84984..00a07e7c571c 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -115,7 +115,8 @@ static int test_pidfd_send_signal_exited_fail(void) pidfd = open(buf, O_DIRECTORY | O_CLOEXEC); - (void)wait_for_pid(pid); + ret = wait_for_pid(pid); + ksft_print_msg("waitpid WEXITSTATUS=%d\n", ret); if (pidfd < 0) ksft_exit_fail_msg( diff --git a/tools/testing/selftests/prctl/set-anon-vma-name-test.c b/tools/testing/selftests/prctl/set-anon-vma-name-test.c index 26d853c5a0c1..4275cb256dce 100644 --- a/tools/testing/selftests/prctl/set-anon-vma-name-test.c +++ b/tools/testing/selftests/prctl/set-anon-vma-name-test.c @@ -97,7 +97,7 @@ TEST_F(vma, renaming) { TH_LOG("Try to pass invalid name (with non-printable character \\1) to rename the VMA"); EXPECT_EQ(rename_vma((unsigned long)self->ptr_anon, AREA_SIZE, BAD_NAME), -EINVAL); - TH_LOG("Try to rename non-anonynous VMA"); + TH_LOG("Try to rename non-anonymous VMA"); EXPECT_EQ(rename_vma((unsigned long) self->ptr_not_anon, AREA_SIZE, GOOD_NAME), -EINVAL); } diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index 198ad5f32187..e9438a1862ad 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -110,7 +110,7 @@ static long ppb_to_scaled_ppm(int ppb) static int64_t pctns(struct ptp_clock_time *t) { - return t->sec * 1000000000LL + t->nsec; + return t->sec * NSEC_PER_SEC + t->nsec; } static void usage(char *progname) @@ -134,6 +134,7 @@ static void usage(char *progname) " 1 - external time stamp\n" " 2 - periodic output\n" " -n val shift the ptp clock time by 'val' nanoseconds\n" + " -o val phase offset (in nanoseconds) to be provided to the PHC servo\n" " -p val enable output with a period of 'val' nanoseconds\n" " -H val set output phase to 'val' nanoseconds (requires -p)\n" " -w val set output pulse width to 'val' nanoseconds (requires -p)\n" @@ -167,6 +168,7 @@ int main(int argc, char *argv[]) int adjfreq = 0x7fffffff; int adjtime = 0; int adjns = 0; + int adjphase = 0; int capabilities = 0; int extts = 0; int flagtest = 0; @@ -188,7 +190,7 @@ int main(int argc, char *argv[]) progname = strrchr(argv[0], '/'); progname = progname ? 1+progname : argv[0]; - while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:n:p:P:sSt:T:w:z"))) { + while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:n:o:p:P:sSt:T:w:z"))) { switch (c) { case 'c': capabilities = 1; @@ -228,6 +230,9 @@ int main(int argc, char *argv[]) case 'n': adjns = atoi(optarg); break; + case 'o': + adjphase = atoi(optarg); + break; case 'p': perout = atoll(optarg); break; @@ -287,7 +292,8 @@ int main(int argc, char *argv[]) " %d pulse per second\n" " %d programmable pins\n" " %d cross timestamping\n" - " %d adjust_phase\n", + " %d adjust_phase\n" + " %d maximum phase adjustment (ns)\n", caps.max_adj, caps.n_alarm, caps.n_ext_ts, @@ -295,7 +301,8 @@ int main(int argc, char *argv[]) caps.pps, caps.n_pins, caps.cross_timestamping, - caps.adjust_phase); + caps.adjust_phase, + caps.max_phase_adj); } } @@ -317,7 +324,7 @@ int main(int argc, char *argv[]) tx.time.tv_usec = adjns; while (tx.time.tv_usec < 0) { tx.time.tv_sec -= 1; - tx.time.tv_usec += 1000000000; + tx.time.tv_usec += NSEC_PER_SEC; } if (clock_adjtime(clkid, &tx) < 0) { @@ -327,6 +334,18 @@ int main(int argc, char *argv[]) } } + if (adjphase) { + memset(&tx, 0, sizeof(tx)); + tx.modes = ADJ_OFFSET | ADJ_NANO; + tx.offset = adjphase; + + if (clock_adjtime(clkid, &tx) < 0) { + perror("clock_adjtime"); + } else { + puts("phase adjustment okay"); + } + } + if (gettime) { if (clock_gettime(clkid, &ts)) { perror("clock_gettime"); @@ -502,11 +521,11 @@ int main(int argc, char *argv[]) interval = t2 - t1; offset = (t2 + t1) / 2 - tp; - printf("system time: %lld.%u\n", + printf("system time: %lld.%09u\n", (pct+2*i)->sec, (pct+2*i)->nsec); - printf("phc time: %lld.%u\n", + printf("phc time: %lld.%09u\n", (pct+2*i+1)->sec, (pct+2*i+1)->nsec); - printf("system time: %lld.%u\n", + printf("system time: %lld.%09u\n", (pct+2*i+2)->sec, (pct+2*i+2)->nsec); printf("system/phc clock time offset is %" PRId64 " ns\n" "system clock time delay is %" PRId64 " ns\n", diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index b52d5069563c..48b9147e8c91 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -250,7 +250,7 @@ identify_qemu_args () { echo -machine virt,gic-version=host -cpu host ;; qemu-system-ppc64) - echo -enable-kvm -M pseries -nodefaults + echo -M pseries -nodefaults echo -device spapr-vscsi if test -n "$TORTURE_QEMU_INTERACTIVE" -a -n "$TORTURE_QEMU_MAC" then diff --git a/tools/testing/selftests/rcutorture/configs/rcu/BUSTED-BOOST.boot b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED-BOOST.boot index f57720c52c0f..84f6bb98ce99 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/BUSTED-BOOST.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED-BOOST.boot @@ -5,4 +5,4 @@ rcutree.gp_init_delay=3 rcutree.gp_cleanup_delay=3 rcutree.kthread_prio=2 threadirqs -tree.use_softirq=0 +rcutree.use_softirq=0 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot index 64f864f1f361..8e50bfd4b710 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot @@ -4,4 +4,4 @@ rcutree.gp_init_delay=3 rcutree.gp_cleanup_delay=3 rcutree.kthread_prio=2 threadirqs -tree.use_softirq=0 +rcutree.use_softirq=0 diff --git a/tools/testing/selftests/run_kselftest.sh b/tools/testing/selftests/run_kselftest.sh index 97165a83df63..92743980e553 100755 --- a/tools/testing/selftests/run_kselftest.sh +++ b/tools/testing/selftests/run_kselftest.sh @@ -26,6 +26,7 @@ Usage: $0 [OPTIONS] -l | --list List the available collection:test entries -d | --dry-run Don't actually run any tests -h | --help Show this usage info + -o | --override-timeout Number of seconds after which we timeout EOF exit $1 } @@ -33,6 +34,7 @@ EOF COLLECTIONS="" TESTS="" dryrun="" +kselftest_override_timeout="" while true; do case "$1" in -s | --summary) @@ -51,6 +53,9 @@ while true; do -d | --dry-run) dryrun="echo" shift ;; + -o | --override-timeout) + kselftest_override_timeout="$2" + shift 2 ;; -h | --help) usage 0 ;; "") @@ -85,7 +90,7 @@ if [ -n "$TESTS" ]; then available="$(echo "$valid" | sed -e 's/ /\n/g')" fi -collections=$(echo "$available" | cut -d: -f1 | uniq) +collections=$(echo "$available" | cut -d: -f1 | sort | uniq) for collection in $collections ; do [ -w /dev/kmsg ] && echo "kselftest: Running tests in $collection" >> /dev/kmsg tests=$(echo "$available" | grep "^$collection:" | cut -d: -f2) diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile index 75af864e07b6..50aab6b57da3 100644 --- a/tools/testing/selftests/sgx/Makefile +++ b/tools/testing/selftests/sgx/Makefile @@ -17,6 +17,7 @@ ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \ -fno-stack-protector -mrdrnd $(INCLUDES) TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx +TEST_FILES := $(OUTPUT)/test_encl.elf ifeq ($(CAN_BUILD_X86_64), 1) all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/test_encl.elf diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh index bfc54b422f25..444b2befda82 100755 --- a/tools/testing/selftests/sysctl/sysctl.sh +++ b/tools/testing/selftests/sysctl/sysctl.sh @@ -14,23 +14,27 @@ TEST_FILE=$(mktemp) # This represents # -# TEST_ID:TEST_COUNT:ENABLED:TARGET +# TEST_ID:TEST_COUNT:ENABLED:TARGET:SKIP_NO_TARGET # # TEST_ID: is the test id number # TEST_COUNT: number of times we should run the test # ENABLED: 1 if enabled, 0 otherwise # TARGET: test target file required on the test_sysctl module +# SKIP_NO_TARGET: 1 skip if TARGET not there +# 0 run eventhough TARGET not there # # Once these are enabled please leave them as-is. Write your own test, # we have tons of space. -ALL_TESTS="0001:1:1:int_0001" -ALL_TESTS="$ALL_TESTS 0002:1:1:string_0001" -ALL_TESTS="$ALL_TESTS 0003:1:1:int_0002" -ALL_TESTS="$ALL_TESTS 0004:1:1:uint_0001" -ALL_TESTS="$ALL_TESTS 0005:3:1:int_0003" -ALL_TESTS="$ALL_TESTS 0006:50:1:bitmap_0001" -ALL_TESTS="$ALL_TESTS 0007:1:1:boot_int" -ALL_TESTS="$ALL_TESTS 0008:1:1:match_int" +ALL_TESTS="0001:1:1:int_0001:1" +ALL_TESTS="$ALL_TESTS 0002:1:1:string_0001:1" +ALL_TESTS="$ALL_TESTS 0003:1:1:int_0002:1" +ALL_TESTS="$ALL_TESTS 0004:1:1:uint_0001:1" +ALL_TESTS="$ALL_TESTS 0005:3:1:int_0003:1" +ALL_TESTS="$ALL_TESTS 0006:50:1:bitmap_0001:1" +ALL_TESTS="$ALL_TESTS 0007:1:1:boot_int:1" +ALL_TESTS="$ALL_TESTS 0008:1:1:match_int:1" +ALL_TESTS="$ALL_TESTS 0009:1:1:unregister_error:0" +ALL_TESTS="$ALL_TESTS 0010:1:1:mnt/mnt_error:0" function allow_user_defaults() { @@ -613,7 +617,6 @@ target_exists() TEST_ID="$2" if [ ! -f ${TARGET} ] ; then - echo "Target for test $TEST_ID: $TARGET not exist, skipping test ..." return 0 fi return 1 @@ -730,7 +733,7 @@ sysctl_test_0005() sysctl_test_0006() { - TARGET="${SYSCTL}/bitmap_0001" + TARGET="${SYSCTL}/$(get_test_target 0006)" reset_vals ORIG="" run_bitmaptest @@ -738,7 +741,7 @@ sysctl_test_0006() sysctl_test_0007() { - TARGET="${SYSCTL}/boot_int" + TARGET="${SYSCTL}/$(get_test_target 0007)" if [ ! -f $TARGET ]; then echo "Skipping test for $TARGET as it is not present ..." return $ksft_skip @@ -778,7 +781,7 @@ sysctl_test_0007() sysctl_test_0008() { - TARGET="${SYSCTL}/match_int" + TARGET="${SYSCTL}/$(get_test_target 0008)" if [ ! -f $TARGET ]; then echo "Skipping test for $TARGET as it is not present ..." return $ksft_skip @@ -797,6 +800,34 @@ sysctl_test_0008() return 0 } +sysctl_test_0009() +{ + TARGET="${SYSCTL}/$(get_test_target 0009)" + echo -n "Testing if $TARGET unregistered correctly ..." + if [ -d $TARGET ]; then + echo "TEST FAILED" + rc=1 + test_rc + fi + + echo "ok" + return 0 +} + +sysctl_test_0010() +{ + TARGET="${SYSCTL}/$(get_test_target 0010)" + echo -n "Testing that $TARGET was not created ..." + if [ -d $TARGET ]; then + echo "TEST FAILED" + rc=1 + test_rc + fi + + echo "ok" + return 0 +} + list_tests() { echo "Test ID list:" @@ -813,6 +844,8 @@ list_tests() echo "0006 x $(get_test_count 0006) - tests proc_do_large_bitmap()" echo "0007 x $(get_test_count 0007) - tests setting sysctl from kernel boot param" echo "0008 x $(get_test_count 0008) - tests sysctl macro values match" + echo "0009 x $(get_test_count 0009) - tests sysct unregister" + echo "0010 x $(get_test_count 0010) - tests sysct mount point" } usage() @@ -857,38 +890,65 @@ function test_num() usage fi } +function remove_leading_zeros() +{ + echo $1 | sed 's/^0*//' +} function get_test_count() { test_num $1 - TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + awk_field=$(remove_leading_zeros $1) + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$awk_field'}') echo ${TEST_DATA} | awk -F":" '{print $2}' } function get_test_enabled() { test_num $1 - TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + awk_field=$(remove_leading_zeros $1) + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$awk_field'}') echo ${TEST_DATA} | awk -F":" '{print $3}' } function get_test_target() { test_num $1 - TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + awk_field=$(remove_leading_zeros $1) + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$awk_field'}') echo ${TEST_DATA} | awk -F":" '{print $4}' } +function get_test_skip_no_target() +{ + test_num $1 + awk_field=$(remove_leading_zeros $1) + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$awk_field'}') + echo ${TEST_DATA} | awk -F":" '{print $5}' +} + +function skip_test() +{ + TEST_ID=$1 + TEST_TARGET=$2 + if target_exists $TEST_TARGET $TEST_ID; then + TEST_SKIP=$(get_test_skip_no_target $TEST_ID) + if [[ $TEST_SKIP -eq "1" ]]; then + echo "Target for test $TEST_ID: $TEST_TARGET not exist, skipping test ..." + return 0 + fi + fi + return 1 +} + function run_all_tests() { for i in $ALL_TESTS ; do - TEST_ID=${i%:*:*:*} + TEST_ID=${i%:*:*:*:*} ENABLED=$(get_test_enabled $TEST_ID) TEST_COUNT=$(get_test_count $TEST_ID) TEST_TARGET=$(get_test_target $TEST_ID) - if target_exists $TEST_TARGET $TEST_ID; then - continue - fi + if [[ $ENABLED -eq "1" ]]; then test_case $TEST_ID $TEST_COUNT $TEST_TARGET fi @@ -923,18 +983,19 @@ function watch_case() function test_case() { + TEST_ID=$1 NUM_TESTS=$2 + TARGET=$3 - i=0 - - if target_exists $3 $1; then - continue + if skip_test $TEST_ID $TARGET; then + return fi + i=0 while [ $i -lt $NUM_TESTS ]; do - test_num $1 - watch_log $i ${TEST_NAME}_test_$1 noclear - RUN_TEST=${TEST_NAME}_test_$1 + test_num $TEST_ID + watch_log $i ${TEST_NAME}_test_${TEST_ID} noclear + RUN_TEST=${TEST_NAME}_test_${TEST_ID} $RUN_TEST let i=$i+1 done diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index 4638c63a339f..6e73b09c20c8 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -6,20 +6,18 @@ CONFIG_NF_CONNTRACK_MARK=y CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_CONNTRACK_LABELS=y CONFIG_NF_NAT=m +CONFIG_NETFILTER_XT_TARGET_LOG=m CONFIG_NET_SCHED=y # # Queueing/Scheduling # -CONFIG_NET_SCH_ATM=m CONFIG_NET_SCH_CAKE=m -CONFIG_NET_SCH_CBQ=m CONFIG_NET_SCH_CBS=m CONFIG_NET_SCH_CHOKE=m CONFIG_NET_SCH_CODEL=m CONFIG_NET_SCH_DRR=m -CONFIG_NET_SCH_DSMARK=m CONFIG_NET_SCH_ETF=m CONFIG_NET_SCH_FQ=m CONFIG_NET_SCH_FQ_CODEL=m @@ -57,8 +55,6 @@ CONFIG_NET_CLS_FLOW=m CONFIG_NET_CLS_FLOWER=m CONFIG_NET_CLS_MATCHALL=m CONFIG_NET_CLS_ROUTE4=m -CONFIG_NET_CLS_RSVP=m -CONFIG_NET_CLS_TCINDEX=m CONFIG_NET_EMATCH=y CONFIG_NET_EMATCH_STACK=32 CONFIG_NET_EMATCH_CMP=m diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json b/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json new file mode 100644 index 000000000000..c4c778e83da2 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json @@ -0,0 +1,25 @@ +[ + { + "id": "c2b4", + "name": "soft lockup alarm will be not generated after delete the prio 0 filter of the chain", + "category": [ + "filter", + "chain" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY root handle 1: htb default 1", + "$TC chain add dev $DUMMY", + "$TC filter del dev $DUMMY chain 0 parent 1: prio 0" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY chain 0 parent 1:", + "expExitCode": "2", + "verifyCmd": "$TC chain ls dev $DUMMY", + "matchPattern": "chain parent 1: chain 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: htb default 1", + "$IP link del dev $DUMMY type dummy" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json index 44fbfc6caec7..e3d2de5c184f 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json @@ -155,5 +155,28 @@ "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" ] - } + }, + { + "id": "0531", + "name": "Replace mq with invalid parent ID", + "category": [ + "qdisc", + "mq" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 16\" > /sys/bus/netdevsim/new_device", + "$TC qdisc add dev $ETH root handle ffff: mq" + ], + "cmdUnderTest": "$TC qdisc replace dev $ETH parent ffff:fff1 handle ffff: mq", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $ETH", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent ffff", + "matchCount": "16", + "teardown": [ + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] + } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json index ba2f5e79cdbf..e21c7f22c6d4 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json @@ -58,10 +58,10 @@ "setup": [ "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb db 10", + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb db 100", "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc sfb 1: root refcnt [0-9]+ rehash 600s db 10ms", + "matchPattern": "qdisc sfb 1: root refcnt [0-9]+ rehash 600s db 100ms", "matchCount": "1", "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root", diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh index afb0cd86fa3d..eb357bd7923c 100755 --- a/tools/testing/selftests/tc-testing/tdc.sh +++ b/tools/testing/selftests/tc-testing/tdc.sh @@ -2,5 +2,6 @@ # SPDX-License-Identifier: GPL-2.0 modprobe netdevsim +modprobe sch_teql ./tdc.py -c actions --nobuildebpf ./tdc.py -c qdisc diff --git a/tools/testing/selftests/user_events/dyn_test.c b/tools/testing/selftests/user_events/dyn_test.c index 8879a7b04c6a..d6979a48478f 100644 --- a/tools/testing/selftests/user_events/dyn_test.c +++ b/tools/testing/selftests/user_events/dyn_test.c @@ -16,42 +16,140 @@ #include "../kselftest_harness.h" -const char *dyn_file = "/sys/kernel/tracing/dynamic_events"; -const char *clear = "!u:__test_event"; +const char *abi_file = "/sys/kernel/tracing/user_events_data"; +const char *enable_file = "/sys/kernel/tracing/events/user_events/__test_event/enable"; -static int Append(const char *value) +static bool wait_for_delete(void) { - int fd = open(dyn_file, O_RDWR | O_APPEND); - int ret = write(fd, value, strlen(value)); + int i; + + for (i = 0; i < 1000; ++i) { + int fd = open(enable_file, O_RDONLY); + + if (fd == -1) + return true; + + close(fd); + usleep(1000); + } + + return false; +} + +static int reg_event(int fd, int *check, int bit, const char *value) +{ + struct user_reg reg = {0}; + + reg.size = sizeof(reg); + reg.name_args = (__u64)value; + reg.enable_bit = bit; + reg.enable_addr = (__u64)check; + reg.enable_size = sizeof(*check); + + if (ioctl(fd, DIAG_IOCSREG, ®) == -1) + return -1; + + return 0; +} + +static int unreg_event(int fd, int *check, int bit) +{ + struct user_unreg unreg = {0}; + + unreg.size = sizeof(unreg); + unreg.disable_bit = bit; + unreg.disable_addr = (__u64)check; + + return ioctl(fd, DIAG_IOCSUNREG, &unreg); +} + +static int parse(int *check, const char *value) +{ + int fd = open(abi_file, O_RDWR); + int ret; + + if (fd == -1) + return -1; + + /* Until we have persist flags via dynamic events, use the base name */ + if (value[0] != 'u' || value[1] != ':') { + close(fd); + return -1; + } + + ret = reg_event(fd, check, 31, value + 2); + + if (ret != -1) { + if (unreg_event(fd, check, 31) == -1) + printf("WARN: Couldn't unreg event\n"); + } close(fd); + return ret; } -#define CLEAR() \ +static int check_match(int *check, const char *first, const char *second, bool *match) +{ + int fd = open(abi_file, O_RDWR); + int ret = -1; + + if (fd == -1) + return -1; + + if (reg_event(fd, check, 31, first) == -1) + goto cleanup; + + if (reg_event(fd, check, 30, second) == -1) { + if (errno == EADDRINUSE) { + /* Name is in use, with different fields */ + *match = false; + ret = 0; + } + + goto cleanup; + } + + *match = true; + ret = 0; +cleanup: + unreg_event(fd, check, 31); + unreg_event(fd, check, 30); + + close(fd); + + wait_for_delete(); + + return ret; +} + +#define TEST_MATCH(x, y) \ do { \ - int ret = Append(clear); \ - if (ret == -1) \ - ASSERT_EQ(ENOENT, errno); \ + bool match; \ + ASSERT_NE(-1, check_match(&self->check, x, y, &match)); \ + ASSERT_EQ(true, match); \ } while (0) -#define TEST_PARSE(x) \ +#define TEST_NMATCH(x, y) \ do { \ - ASSERT_NE(-1, Append(x)); \ - CLEAR(); \ + bool match; \ + ASSERT_NE(-1, check_match(&self->check, x, y, &match)); \ + ASSERT_EQ(false, match); \ } while (0) -#define TEST_NPARSE(x) ASSERT_EQ(-1, Append(x)) +#define TEST_PARSE(x) ASSERT_NE(-1, parse(&self->check, x)) + +#define TEST_NPARSE(x) ASSERT_EQ(-1, parse(&self->check, x)) FIXTURE(user) { + int check; }; FIXTURE_SETUP(user) { - CLEAR(); } FIXTURE_TEARDOWN(user) { - CLEAR(); + wait_for_delete(); } TEST_F(user, basic_types) { @@ -95,33 +193,30 @@ TEST_F(user, size_types) { TEST_NPARSE("u:__test_event char a 20"); } -TEST_F(user, flags) { - /* Should work */ - TEST_PARSE("u:__test_event:BPF_ITER u32 a"); - /* Forward compat */ - TEST_PARSE("u:__test_event:BPF_ITER,FLAG_FUTURE u32 a"); -} - TEST_F(user, matching) { - /* Register */ - ASSERT_NE(-1, Append("u:__test_event struct custom a 20")); - /* Should not match */ - TEST_NPARSE("!u:__test_event struct custom b"); - /* Should match */ - TEST_PARSE("!u:__test_event struct custom a"); - /* Multi field reg */ - ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b")); - /* Non matching cases */ - TEST_NPARSE("!u:__test_event u32 a"); - TEST_NPARSE("!u:__test_event u32 b"); - TEST_NPARSE("!u:__test_event u32 a; u32 "); - TEST_NPARSE("!u:__test_event u32 a; u32 a"); - /* Matching case */ - TEST_PARSE("!u:__test_event u32 a; u32 b"); - /* Register */ - ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b")); - /* Ensure trailing semi-colon case */ - TEST_PARSE("!u:__test_event u32 a; u32 b;"); + /* Single name matches */ + TEST_MATCH("__test_event u32 a", + "__test_event u32 a"); + + /* Multiple names match */ + TEST_MATCH("__test_event u32 a; u32 b", + "__test_event u32 a; u32 b"); + + /* Multiple names match with dangling ; */ + TEST_MATCH("__test_event u32 a; u32 b", + "__test_event u32 a; u32 b;"); + + /* Single name doesn't match */ + TEST_NMATCH("__test_event u32 a", + "__test_event u32 b"); + + /* Multiple names don't match */ + TEST_NMATCH("__test_event u32 a; u32 b", + "__test_event u32 b; u32 a"); + + /* Types don't match */ + TEST_NMATCH("__test_event u64 a; u64 b", + "__test_event u32 a; u32 b"); } int main(int argc, char **argv) diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c index 7c99cef94a65..eb6904d89f14 100644 --- a/tools/testing/selftests/user_events/ftrace_test.c +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -102,30 +102,56 @@ err: return -1; } +static bool wait_for_delete(void) +{ + int i; + + for (i = 0; i < 1000; ++i) { + int fd = open(enable_file, O_RDONLY); + + if (fd == -1) + return true; + + close(fd); + usleep(1000); + } + + return false; +} + static int clear(int *check) { struct user_unreg unreg = {0}; + int fd; unreg.size = sizeof(unreg); unreg.disable_bit = 31; unreg.disable_addr = (__u64)check; - int fd = open(data_file, O_RDWR); + fd = open(data_file, O_RDWR); if (fd == -1) return -1; if (ioctl(fd, DIAG_IOCSUNREG, &unreg) == -1) if (errno != ENOENT) - return -1; - - if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) - if (errno != ENOENT) - return -1; + goto fail; + + if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) { + if (errno == EBUSY) { + if (!wait_for_delete()) + goto fail; + } else if (errno != ENOENT) + goto fail; + } close(fd); return 0; +fail: + close(fd); + + return -1; } static int check_print_fmt(const char *event, const char *expected, int *check) @@ -155,9 +181,8 @@ static int check_print_fmt(const char *event, const char *expected, int *check) /* Register should work */ ret = ioctl(fd, DIAG_IOCSREG, ®); - close(fd); - if (ret != 0) { + close(fd); printf("Reg failed in fmt\n"); return ret; } @@ -165,6 +190,8 @@ static int check_print_fmt(const char *event, const char *expected, int *check) /* Ensure correct print_fmt */ ret = get_print_fmt(print_fmt, sizeof(print_fmt)); + close(fd); + if (ret != 0) return ret; @@ -228,6 +255,12 @@ TEST_F(user, register_events) { ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); + /* Multiple registers to same name but different args should fail */ + reg.enable_bit = 29; + reg.name_args = (__u64)"__test_event u32 field1;"; + ASSERT_EQ(-1, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(EADDRINUSE, errno); + /* Ensure disabled */ self->enable_fd = open(enable_file, O_RDWR); ASSERT_NE(-1, self->enable_fd); @@ -250,10 +283,10 @@ TEST_F(user, register_events) { unreg.disable_bit = 30; ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSUNREG, &unreg)); - /* Delete should work only after close and unregister */ + /* Delete should have been auto-done after close and unregister */ close(self->data_fd); - self->data_fd = open(data_file, O_RDWR); - ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event")); + + ASSERT_EQ(true, wait_for_delete()); } TEST_F(user, write_events) { @@ -310,6 +343,39 @@ TEST_F(user, write_events) { ASSERT_EQ(EINVAL, errno); } +TEST_F(user, write_empty_events) { + struct user_reg reg = {0}; + struct iovec io[1]; + int before = 0, after = 0; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); + + io[0].iov_base = ®.write_index; + io[0].iov_len = sizeof(reg.write_index); + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_EQ(0, self->check); + + /* Enable event */ + self->enable_fd = open(enable_file, O_RDWR); + ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) + + /* Event should now be enabled */ + ASSERT_EQ(1 << reg.enable_bit, self->check); + + /* Write should make it out to ftrace buffers */ + before = trace_bytes(); + ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 1)); + after = trace_bytes(); + ASSERT_GT(after, before); +} + TEST_F(user, write_fault) { struct user_reg reg = {0}; struct iovec io[2]; diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c index a070258d4449..8b09be566fa2 100644 --- a/tools/testing/selftests/user_events/perf_test.c +++ b/tools/testing/selftests/user_events/perf_test.c @@ -81,6 +81,32 @@ static int get_offset(void) return offset; } +static int clear(int *check) +{ + struct user_unreg unreg = {0}; + + unreg.size = sizeof(unreg); + unreg.disable_bit = 31; + unreg.disable_addr = (__u64)check; + + int fd = open(data_file, O_RDWR); + + if (fd == -1) + return -1; + + if (ioctl(fd, DIAG_IOCSUNREG, &unreg) == -1) + if (errno != ENOENT) + return -1; + + if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) + if (errno != ENOENT) + return -1; + + close(fd); + + return 0; +} + FIXTURE(user) { int data_fd; int check; @@ -93,6 +119,9 @@ FIXTURE_SETUP(user) { FIXTURE_TEARDOWN(user) { close(self->data_fd); + + if (clear(&self->check) != 0) + printf("WARNING: Clear didn't work!\n"); } TEST_F(user, perf_write) { @@ -160,6 +189,59 @@ TEST_F(user, perf_write) { ASSERT_EQ(0, self->check); } +TEST_F(user, perf_empty_events) { + struct perf_event_attr pe = {0}; + struct user_reg reg = {0}; + struct perf_event_mmap_page *perf_page; + int page_size = sysconf(_SC_PAGESIZE); + int id, fd; + __u32 *val; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_EQ(0, self->check); + + /* Id should be there */ + id = get_id(); + ASSERT_NE(-1, id); + + pe.type = PERF_TYPE_TRACEPOINT; + pe.size = sizeof(pe); + pe.config = id; + pe.sample_type = PERF_SAMPLE_RAW; + pe.sample_period = 1; + pe.wakeup_events = 1; + + /* Tracepoint attach should work */ + fd = perf_event_open(&pe, 0, -1, -1, 0); + ASSERT_NE(-1, fd); + + perf_page = mmap(NULL, page_size * 2, PROT_READ, MAP_SHARED, fd, 0); + ASSERT_NE(MAP_FAILED, perf_page); + + /* Status should be updated */ + ASSERT_EQ(1 << reg.enable_bit, self->check); + + /* Ensure write shows up at correct offset */ + ASSERT_NE(-1, write(self->data_fd, ®.write_index, + sizeof(reg.write_index))); + val = (void *)(((char *)perf_page) + perf_page->data_offset); + ASSERT_EQ(PERF_RECORD_SAMPLE, *val); + + munmap(perf_page, page_size * 2); + close(fd); + + /* Status should be updated */ + ASSERT_EQ(0, self->check); +} + int main(int argc, char **argv) { return test_harness_run(argc, argv); diff --git a/tools/testing/selftests/vDSO/vdso_test_clock_getres.c b/tools/testing/selftests/vDSO/vdso_test_clock_getres.c index 15dcee16ff72..38d46a8bf7cb 100644 --- a/tools/testing/selftests/vDSO/vdso_test_clock_getres.c +++ b/tools/testing/selftests/vDSO/vdso_test_clock_getres.c @@ -84,12 +84,12 @@ static inline int vdso_test_clock(unsigned int clock_id) int main(int argc, char **argv) { - int ret; + int ret = 0; #if _POSIX_TIMERS > 0 #ifdef CLOCK_REALTIME - ret = vdso_test_clock(CLOCK_REALTIME); + ret += vdso_test_clock(CLOCK_REALTIME); #endif #ifdef CLOCK_BOOTTIME |