diff options
Diffstat (limited to 'tools/testing')
180 files changed, 12810 insertions, 1699 deletions
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 0f1d91f57ba3..d533481672b7 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -1828,27 +1828,10 @@ static ssize_t fw_buf_checksum_show(struct device *dev, { struct cxl_mockmem_data *mdata = dev_get_drvdata(dev); u8 hash[SHA256_DIGEST_SIZE]; - unsigned char *hstr, *hptr; - struct sha256_state sctx; - ssize_t written = 0; - int i; - - sha256_init(&sctx); - sha256_update(&sctx, mdata->fw, mdata->fw_size); - sha256_final(&sctx, hash); - - hstr = kzalloc((SHA256_DIGEST_SIZE * 2) + 1, GFP_KERNEL); - if (!hstr) - return -ENOMEM; - - hptr = hstr; - for (i = 0; i < SHA256_DIGEST_SIZE; i++) - hptr += sprintf(hptr, "%02x", hash[i]); - written = sysfs_emit(buf, "%s\n", hstr); + sha256(mdata->fw, mdata->fw_size, hash); - kfree(hstr); - return written; + return sysfs_emit(buf, "%*phN\n", SHA256_DIGEST_SIZE, hash); } static DEVICE_ATTR_RO(fw_buf_checksum); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 339b31e6a6b5..030da61dbff3 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -77,6 +77,7 @@ TARGETS += net/ovpn TARGETS += net/packetdrill TARGETS += net/rds TARGETS += net/tcp_ao +TARGETS += nolibc TARGETS += nsfs TARGETS += pci_endpoint TARGETS += pcie_bwctrl @@ -293,6 +294,14 @@ ifdef INSTALL_PATH $(MAKE) -s --no-print-directory OUTPUT=$$BUILD_TARGET COLLECTION=$$TARGET \ -C $$TARGET emit_tests >> $(TEST_LIST); \ done; + @VERSION=$$(git describe HEAD 2>/dev/null); \ + if [ -n "$$VERSION" ]; then \ + echo "$$VERSION" > $(INSTALL_PATH)/VERSION; \ + printf "Version saved to $(INSTALL_PATH)/VERSION\n"; \ + else \ + printf "Unable to get version from git describe\n"; \ + fi + @echo "**Kselftest Installation is complete: $(INSTALL_PATH)**" else $(error Error: set INSTALL_PATH to use install) endif diff --git a/tools/testing/selftests/arm64/abi/Makefile b/tools/testing/selftests/arm64/abi/Makefile index a6d30c620908..483488f8c2ad 100644 --- a/tools/testing/selftests/arm64/abi/Makefile +++ b/tools/testing/selftests/arm64/abi/Makefile @@ -12,4 +12,4 @@ $(OUTPUT)/syscall-abi: syscall-abi.c syscall-abi-asm.S $(OUTPUT)/tpidr2: tpidr2.c $(CC) -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \ -static -include ../../../../include/nolibc/nolibc.h \ - -ffreestanding -Wall $^ -o $@ -lgcc + -I../.. -ffreestanding -Wall $^ -o $@ -lgcc diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index 35f521e5f41c..002ec38a8bbb 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -21,6 +21,10 @@ #define TESTS_PER_HWCAP 3 +#ifndef AT_HWCAP3 +#define AT_HWCAP3 29 +#endif + /* * Function expected to generate exception when the feature is not * supported and return when it is supported. If the specific exception @@ -1098,6 +1102,18 @@ static const struct hwcap_data { .sigill_fn = hbc_sigill, .sigill_reliable = true, }, + { + .name = "MTE_FAR", + .at_hwcap = AT_HWCAP3, + .hwcap_bit = HWCAP3_MTE_FAR, + .cpuinfo = "mtefar", + }, + { + .name = "MTE_STOREONLY", + .at_hwcap = AT_HWCAP3, + .hwcap_bit = HWCAP3_MTE_STORE_ONLY, + .cpuinfo = "mtestoreonly", + }, }; typedef void (*sighandler_fn)(int, siginfo_t *, void *); diff --git a/tools/testing/selftests/arm64/abi/tpidr2.c b/tools/testing/selftests/arm64/abi/tpidr2.c index eb19dcc37a75..f58a9f89b952 100644 --- a/tools/testing/selftests/arm64/abi/tpidr2.c +++ b/tools/testing/selftests/arm64/abi/tpidr2.c @@ -3,31 +3,12 @@ #include <linux/sched.h> #include <linux/wait.h> +#include "kselftest.h" + #define SYS_TPIDR2 "S3_3_C13_C0_5" #define EXPECTED_TESTS 5 -static void putstr(const char *str) -{ - write(1, str, strlen(str)); -} - -static void putnum(unsigned int num) -{ - char c; - - if (num / 10) - putnum(num / 10); - - c = '0' + (num % 10); - write(1, &c, 1); -} - -static int tests_run; -static int tests_passed; -static int tests_failed; -static int tests_skipped; - static void set_tpidr2(uint64_t val) { asm volatile ( @@ -50,20 +31,6 @@ static uint64_t get_tpidr2(void) return val; } -static void print_summary(void) -{ - if (tests_passed + tests_failed + tests_skipped != EXPECTED_TESTS) - putstr("# UNEXPECTED TEST COUNT: "); - - putstr("# Totals: pass:"); - putnum(tests_passed); - putstr(" fail:"); - putnum(tests_failed); - putstr(" xfail:0 xpass:0 skip:"); - putnum(tests_skipped); - putstr(" error:0\n"); -} - /* Processes should start with TPIDR2 == 0 */ static int default_value(void) { @@ -105,9 +72,8 @@ static int write_fork_read(void) if (newpid == 0) { /* In child */ if (get_tpidr2() != oldpid) { - putstr("# TPIDR2 changed in child: "); - putnum(get_tpidr2()); - putstr("\n"); + ksft_print_msg("TPIDR2 changed in child: %llx\n", + get_tpidr2()); exit(0); } @@ -115,14 +81,12 @@ static int write_fork_read(void) if (get_tpidr2() == getpid()) { exit(1); } else { - putstr("# Failed to set TPIDR2 in child\n"); + ksft_print_msg("Failed to set TPIDR2 in child\n"); exit(0); } } if (newpid < 0) { - putstr("# fork() failed: -"); - putnum(-newpid); - putstr("\n"); + ksft_print_msg("fork() failed: %d\n", newpid); return 0; } @@ -132,23 +96,22 @@ static int write_fork_read(void) if (waiting < 0) { if (errno == EINTR) continue; - putstr("# waitpid() failed: "); - putnum(errno); - putstr("\n"); + ksft_print_msg("waitpid() failed: %d\n", errno); return 0; } if (waiting != newpid) { - putstr("# waitpid() returned wrong PID\n"); + ksft_print_msg("waitpid() returned wrong PID: %d != %d\n", + waiting, newpid); return 0; } if (!WIFEXITED(status)) { - putstr("# child did not exit\n"); + ksft_print_msg("child did not exit\n"); return 0; } if (getpid() != get_tpidr2()) { - putstr("# TPIDR2 corrupted in parent\n"); + ksft_print_msg("TPIDR2 corrupted in parent\n"); return 0; } @@ -188,35 +151,32 @@ static int write_clone_read(void) stack = malloc(__STACK_SIZE); if (!stack) { - putstr("# malloc() failed\n"); + ksft_print_msg("malloc() failed\n"); return 0; } ret = sys_clone(CLONE_VM, (unsigned long)stack + __STACK_SIZE, &parent_tid, 0, &child_tid); if (ret == -1) { - putstr("# clone() failed\n"); - putnum(errno); - putstr("\n"); + ksft_print_msg("clone() failed: %d\n", errno); return 0; } if (ret == 0) { /* In child */ if (get_tpidr2() != 0) { - putstr("# TPIDR2 non-zero in child: "); - putnum(get_tpidr2()); - putstr("\n"); + ksft_print_msg("TPIDR2 non-zero in child: %llx\n", + get_tpidr2()); exit(0); } if (gettid() == 0) - putstr("# Child TID==0\n"); + ksft_print_msg("Child TID==0\n"); set_tpidr2(gettid()); if (get_tpidr2() == gettid()) { exit(1); } else { - putstr("# Failed to set TPIDR2 in child\n"); + ksft_print_msg("Failed to set TPIDR2 in child\n"); exit(0); } } @@ -227,25 +187,22 @@ static int write_clone_read(void) if (waiting < 0) { if (errno == EINTR) continue; - putstr("# wait4() failed: "); - putnum(errno); - putstr("\n"); + ksft_print_msg("wait4() failed: %d\n", errno); return 0; } if (waiting != ret) { - putstr("# wait4() returned wrong PID "); - putnum(waiting); - putstr("\n"); + ksft_print_msg("wait4() returned wrong PID %d\n", + waiting); return 0; } if (!WIFEXITED(status)) { - putstr("# child did not exit\n"); + ksft_print_msg("child did not exit\n"); return 0; } if (parent != get_tpidr2()) { - putstr("# TPIDR2 corrupted in parent\n"); + ksft_print_msg("TPIDR2 corrupted in parent\n"); return 0; } @@ -253,35 +210,14 @@ static int write_clone_read(void) } } -#define run_test(name) \ - if (name()) { \ - tests_passed++; \ - } else { \ - tests_failed++; \ - putstr("not "); \ - } \ - putstr("ok "); \ - putnum(++tests_run); \ - putstr(" " #name "\n"); - -#define skip_test(name) \ - tests_skipped++; \ - putstr("ok "); \ - putnum(++tests_run); \ - putstr(" # SKIP " #name "\n"); - int main(int argc, char **argv) { int ret; - putstr("TAP version 13\n"); - putstr("1.."); - putnum(EXPECTED_TESTS); - putstr("\n"); + ksft_print_header(); + ksft_set_plan(5); - putstr("# PID: "); - putnum(getpid()); - putstr("\n"); + ksft_print_msg("PID: %d\n", getpid()); /* * This test is run with nolibc which doesn't support hwcap and @@ -290,23 +226,21 @@ int main(int argc, char **argv) */ ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0); if (ret >= 0) { - run_test(default_value); - run_test(write_read); - run_test(write_sleep_read); - run_test(write_fork_read); - run_test(write_clone_read); + ksft_test_result(default_value(), "default_value\n"); + ksft_test_result(write_read, "write_read\n"); + ksft_test_result(write_sleep_read, "write_sleep_read\n"); + ksft_test_result(write_fork_read, "write_fork_read\n"); + ksft_test_result(write_clone_read, "write_clone_read\n"); } else { - putstr("# SME support not present\n"); + ksft_print_msg("SME support not present\n"); - skip_test(default_value); - skip_test(write_read); - skip_test(write_sleep_read); - skip_test(write_fork_read); - skip_test(write_clone_read); + ksft_test_result_skip("default_value\n"); + ksft_test_result_skip("write_read\n"); + ksft_test_result_skip("write_sleep_read\n"); + ksft_test_result_skip("write_fork_read\n"); + ksft_test_result_skip("write_clone_read\n"); } - print_summary(); - - return 0; + ksft_finished(); } diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.c b/tools/testing/selftests/arm64/fp/fp-ptrace.c index 191c47ca0ed8..124bc883365e 100644 --- a/tools/testing/selftests/arm64/fp/fp-ptrace.c +++ b/tools/testing/selftests/arm64/fp/fp-ptrace.c @@ -1061,11 +1061,31 @@ static bool sve_write_supported(struct test_config *config) if (config->sme_vl_in != config->sme_vl_expected) { return false; } + + if (!sve_supported()) + return false; } return true; } +static bool sve_write_fpsimd_supported(struct test_config *config) +{ + if (!sve_supported()) + return false; + + if ((config->svcr_in & SVCR_ZA) != (config->svcr_expected & SVCR_ZA)) + return false; + + if (config->svcr_expected & SVCR_SM) + return false; + + if (config->sme_vl_in != config->sme_vl_expected) + return false; + + return true; +} + static void fpsimd_write_expected(struct test_config *config) { int vl; @@ -1134,6 +1154,9 @@ static void sve_write_expected(struct test_config *config) int vl = vl_expected(config); int sme_vq = __sve_vq_from_vl(config->sme_vl_expected); + if (!vl) + return; + fill_random(z_expected, __SVE_ZREGS_SIZE(__sve_vq_from_vl(vl))); fill_random(p_expected, __SVE_PREGS_SIZE(__sve_vq_from_vl(vl))); @@ -1152,7 +1175,7 @@ static void sve_write_expected(struct test_config *config) } } -static void sve_write(pid_t child, struct test_config *config) +static void sve_write_sve(pid_t child, struct test_config *config) { struct user_sve_header *sve; struct iovec iov; @@ -1161,6 +1184,9 @@ static void sve_write(pid_t child, struct test_config *config) vl = vl_expected(config); vq = __sve_vq_from_vl(vl); + if (!vl) + return; + iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); iov.iov_base = malloc(iov.iov_len); if (!iov.iov_base) { @@ -1195,6 +1221,45 @@ static void sve_write(pid_t child, struct test_config *config) free(iov.iov_base); } +static void sve_write_fpsimd(pid_t child, struct test_config *config) +{ + struct user_sve_header *sve; + struct user_fpsimd_state *fpsimd; + struct iovec iov; + int ret, vl, vq; + + vl = vl_expected(config); + vq = __sve_vq_from_vl(vl); + + if (!vl) + return; + + iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, + SVE_PT_REGS_FPSIMD); + iov.iov_base = malloc(iov.iov_len); + if (!iov.iov_base) { + ksft_print_msg("Failed allocating %lu byte SVE write buffer\n", + iov.iov_len); + return; + } + memset(iov.iov_base, 0, iov.iov_len); + + sve = iov.iov_base; + sve->size = iov.iov_len; + sve->flags = SVE_PT_REGS_FPSIMD; + sve->vl = vl; + + fpsimd = iov.iov_base + SVE_PT_REGS_OFFSET; + memcpy(&fpsimd->vregs, v_expected, sizeof(v_expected)); + + ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_SVE, &iov); + if (ret != 0) + ksft_print_msg("Failed to write SVE: %s (%d)\n", + strerror(errno), errno); + + free(iov.iov_base); +} + static bool za_write_supported(struct test_config *config) { if ((config->svcr_in & SVCR_SM) != (config->svcr_expected & SVCR_SM)) @@ -1386,7 +1451,13 @@ static struct test_definition sve_test_defs[] = { .name = "SVE write", .supported = sve_write_supported, .set_expected_values = sve_write_expected, - .modify_values = sve_write, + .modify_values = sve_write_sve, + }, + { + .name = "SVE write FPSIMD format", + .supported = sve_write_fpsimd_supported, + .set_expected_values = fpsimd_write_expected, + .modify_values = sve_write_fpsimd, }, }; @@ -1607,7 +1678,7 @@ int main(void) * Run the test set if there is no SVE or SME, with those we * have to pick a VL for each run. */ - if (!sve_supported()) { + if (!sve_supported() && !sme_supported()) { test_config.sve_vl_in = 0; test_config.sve_vl_expected = 0; test_config.sme_vl_in = 0; diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c index 577b6e05e860..b22303778fb0 100644 --- a/tools/testing/selftests/arm64/fp/sve-ptrace.c +++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c @@ -170,7 +170,7 @@ static void ptrace_set_get_inherit(pid_t child, const struct vec_type *type) memset(&sve, 0, sizeof(sve)); sve.size = sizeof(sve); sve.vl = sve_vl_from_vq(SVE_VQ_MIN); - sve.flags = SVE_PT_VL_INHERIT; + sve.flags = SVE_PT_VL_INHERIT | SVE_PT_REGS_SVE; ret = set_sve(child, type, &sve); if (ret != 0) { ksft_test_result_fail("Failed to set %s SVE_PT_VL_INHERIT\n", @@ -235,6 +235,7 @@ static void ptrace_set_get_vl(pid_t child, const struct vec_type *type, /* Set the VL by doing a set with no register payload */ memset(&sve, 0, sizeof(sve)); sve.size = sizeof(sve); + sve.flags = SVE_PT_REGS_SVE; sve.vl = vl; ret = set_sve(child, type, &sve); if (ret != 0) { @@ -253,7 +254,7 @@ static void ptrace_set_get_vl(pid_t child, const struct vec_type *type, return; } - ksft_test_result(new_sve->vl = prctl_vl, "Set %s VL %u\n", + ksft_test_result(new_sve->vl == prctl_vl, "Set %s VL %u\n", type->name, vl); free(new_sve); @@ -301,8 +302,10 @@ static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type) p[j] = j; } + /* This should only succeed for SVE */ ret = set_sve(child, type, sve); - ksft_test_result(ret == 0, "%s FPSIMD set via SVE: %d\n", + ksft_test_result((type->regset == NT_ARM_SVE) == (ret == 0), + "%s FPSIMD set via SVE: %d\n", type->name, ret); if (ret) goto out; @@ -750,9 +753,6 @@ int main(void) ksft_print_header(); ksft_set_plan(EXPECTED_TESTS); - if (!(getauxval(AT_HWCAP) & HWCAP_SVE)) - ksft_exit_skip("SVE not available\n"); - child = fork(); if (!child) return do_child(); diff --git a/tools/testing/selftests/arm64/gcs/basic-gcs.c b/tools/testing/selftests/arm64/gcs/basic-gcs.c index 3fb9742342a3..54f9c888249d 100644 --- a/tools/testing/selftests/arm64/gcs/basic-gcs.c +++ b/tools/testing/selftests/arm64/gcs/basic-gcs.c @@ -298,6 +298,68 @@ out: return pass; } +/* A vfork()ed process can run and exit */ +static bool test_vfork(void) +{ + unsigned long child_mode; + int ret, status; + pid_t pid; + bool pass = true; + + pid = vfork(); + if (pid == -1) { + ksft_print_msg("vfork() failed: %d\n", errno); + pass = false; + goto out; + } + if (pid == 0) { + /* + * In child, make sure we can call a function, read + * the GCS pointer and status and then exit. + */ + valid_gcs_function(); + get_gcspr(); + + ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, + &child_mode, 0, 0, 0); + if (ret == 0 && !(child_mode & PR_SHADOW_STACK_ENABLE)) { + ksft_print_msg("GCS not enabled in child\n"); + ret = EXIT_FAILURE; + } + + _exit(ret); + } + + /* + * In parent, check we can still do function calls then check + * on the child. + */ + valid_gcs_function(); + + ksft_print_msg("Waiting for child %d\n", pid); + + ret = waitpid(pid, &status, 0); + if (ret == -1) { + ksft_print_msg("Failed to wait for child: %d\n", + errno); + return false; + } + + if (!WIFEXITED(status)) { + ksft_print_msg("Child exited due to signal %d\n", + WTERMSIG(status)); + pass = false; + } else if (WEXITSTATUS(status)) { + ksft_print_msg("Child exited with status %d\n", + WEXITSTATUS(status)); + pass = false; + } + +out: + + return pass; +} + typedef bool (*gcs_test)(void); static struct { @@ -314,6 +376,7 @@ static struct { { "enable_invalid", enable_invalid, true }, { "map_guarded_stack", map_guarded_stack }, { "fork", test_fork }, + { "vfork", test_vfork }, }; int main(void) diff --git a/tools/testing/selftests/arm64/mte/check_buffer_fill.c b/tools/testing/selftests/arm64/mte/check_buffer_fill.c index 2ee7f114d7fa..ff4e07503349 100644 --- a/tools/testing/selftests/arm64/mte/check_buffer_fill.c +++ b/tools/testing/selftests/arm64/mte/check_buffer_fill.c @@ -31,7 +31,7 @@ static int check_buffer_by_byte(int mem_type, int mode) int i, j, item; bool err; - mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); + mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false); item = ARRAY_SIZE(sizes); for (i = 0; i < item; i++) { @@ -68,7 +68,7 @@ static int check_buffer_underflow_by_byte(int mem_type, int mode, bool err; char *und_ptr = NULL; - mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); + mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false); item = ARRAY_SIZE(sizes); for (i = 0; i < item; i++) { ptr = (char *)mte_allocate_memory_tag_range(sizes[i], mem_type, 0, @@ -164,7 +164,7 @@ static int check_buffer_overflow_by_byte(int mem_type, int mode, size_t tagged_size, overflow_size; char *over_ptr = NULL; - mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); + mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false); item = ARRAY_SIZE(sizes); for (i = 0; i < item; i++) { ptr = (char *)mte_allocate_memory_tag_range(sizes[i], mem_type, 0, @@ -337,7 +337,7 @@ static int check_buffer_by_block(int mem_type, int mode) { int i, item, result = KSFT_PASS; - mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); + mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false); item = ARRAY_SIZE(sizes); cur_mte_cxt.fault_valid = false; for (i = 0; i < item; i++) { @@ -368,7 +368,7 @@ static int check_memory_initial_tags(int mem_type, int mode, int mapping) int run, fd; int total = ARRAY_SIZE(sizes); - mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); + mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false); for (run = 0; run < total; run++) { /* check initial tags for anonymous mmap */ ptr = (char *)mte_allocate_memory(sizes[run], mem_type, mapping, false); @@ -415,7 +415,7 @@ int main(int argc, char *argv[]) return err; /* Register SIGSEGV handler */ - mte_register_signal(SIGSEGV, mte_default_handler); + mte_register_signal(SIGSEGV, mte_default_handler, false); /* Set test plan */ ksft_set_plan(20); diff --git a/tools/testing/selftests/arm64/mte/check_child_memory.c b/tools/testing/selftests/arm64/mte/check_child_memory.c index 7597fc632cad..5e97ee792e4d 100644 --- a/tools/testing/selftests/arm64/mte/check_child_memory.c +++ b/tools/testing/selftests/arm64/mte/check_child_memory.c @@ -88,7 +88,7 @@ static int check_child_memory_mapping(int mem_type, int mode, int mapping) int item = ARRAY_SIZE(sizes); item = ARRAY_SIZE(sizes); - mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); + mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false); for (run = 0; run < item; run++) { ptr = (char *)mte_allocate_memory_tag_range(sizes[run], mem_type, mapping, UNDERFLOW, OVERFLOW); @@ -109,7 +109,7 @@ static int check_child_file_mapping(int mem_type, int mode, int mapping) int run, fd, map_size, result = KSFT_PASS; int total = ARRAY_SIZE(sizes); - mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); + mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false); for (run = 0; run < total; run++) { fd = create_temp_file(); if (fd == -1) @@ -160,8 +160,8 @@ int main(int argc, char *argv[]) return err; /* Register SIGSEGV handler */ - mte_register_signal(SIGSEGV, mte_default_handler); - mte_register_signal(SIGBUS, mte_default_handler); + mte_register_signal(SIGSEGV, mte_default_handler, false); + mte_register_signal(SIGBUS, mte_default_handler, false); /* Set test plan */ ksft_set_plan(12); diff --git a/tools/testing/selftests/arm64/mte/check_hugetlb_options.c b/tools/testing/selftests/arm64/mte/check_hugetlb_options.c index 3bfcd3848432..aad1234c7e0f 100644 --- a/tools/testing/selftests/arm64/mte/check_hugetlb_options.c +++ b/tools/testing/selftests/arm64/mte/check_hugetlb_options.c @@ -151,7 +151,7 @@ static int check_hugetlb_memory_mapping(int mem_type, int mode, int mapping, int map_size = default_huge_page_size(); - mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); + mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false); map_ptr = (char *)mte_allocate_memory(map_size, mem_type, mapping, false); if (check_allocated_memory(map_ptr, map_size, mem_type, false) != KSFT_PASS) return KSFT_FAIL; @@ -180,7 +180,7 @@ static int check_clear_prot_mte_flag(int mem_type, int mode, int mapping) unsigned long map_size; prot_flag = PROT_READ | PROT_WRITE; - mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); + mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false); map_size = default_huge_page_size(); map_ptr = (char *)mte_allocate_memory_tag_range(map_size, mem_type, mapping, 0, 0); @@ -210,7 +210,7 @@ static int check_child_hugetlb_memory_mapping(int mem_type, int mode, int mappin map_size = default_huge_page_size(); - mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); + mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false); ptr = (char *)mte_allocate_memory_tag_range(map_size, mem_type, mapping, 0, 0); if (check_allocated_memory_range(ptr, map_size, mem_type, @@ -235,8 +235,8 @@ int main(int argc, char *argv[]) return err; /* Register signal handlers */ - mte_register_signal(SIGBUS, mte_default_handler); - mte_register_signal(SIGSEGV, mte_default_handler); + mte_register_signal(SIGBUS, mte_default_handler, false); + mte_register_signal(SIGSEGV, mte_default_handler, false); allocate_hugetlb(); diff --git a/tools/testing/selftests/arm64/mte/check_ksm_options.c b/tools/testing/selftests/arm64/mte/check_ksm_options.c index 88c74bc46d4f..0cf5faef1724 100644 --- a/tools/testing/selftests/arm64/mte/check_ksm_options.c +++ b/tools/testing/selftests/arm64/mte/check_ksm_options.c @@ -106,7 +106,7 @@ static int check_madvise_options(int mem_type, int mode, int mapping) return err; } - mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); + mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false); ptr = mte_allocate_memory(TEST_UNIT * page_sz, mem_type, mapping, true); if (check_allocated_memory(ptr, TEST_UNIT * page_sz, mem_type, false) != KSFT_PASS) return KSFT_FAIL; @@ -141,8 +141,8 @@ int main(int argc, char *argv[]) return KSFT_FAIL; } /* Register signal handlers */ - mte_register_signal(SIGBUS, mte_default_handler); - mte_register_signal(SIGSEGV, mte_default_handler); + mte_register_signal(SIGBUS, mte_default_handler, false); + mte_register_signal(SIGSEGV, mte_default_handler, false); /* Set test plan */ ksft_set_plan(4); diff --git a/tools/testing/selftests/arm64/mte/check_mmap_options.c b/tools/testing/selftests/arm64/mte/check_mmap_options.c index 17694caaff53..c100af3012cb 100644 --- a/tools/testing/selftests/arm64/mte/check_mmap_options.c +++ b/tools/testing/selftests/arm64/mte/check_mmap_options.c @@ -3,6 +3,7 @@ #define _GNU_SOURCE +#include <assert.h> #include <errno.h> #include <fcntl.h> #include <signal.h> @@ -23,6 +24,35 @@ #define OVERFLOW MT_GRANULE_SIZE #define TAG_CHECK_ON 0 #define TAG_CHECK_OFF 1 +#define ATAG_CHECK_ON 1 +#define ATAG_CHECK_OFF 0 + +#define TEST_NAME_MAX 256 + +enum mte_mem_check_type { + CHECK_ANON_MEM = 0, + CHECK_FILE_MEM = 1, + CHECK_CLEAR_PROT_MTE = 2, +}; + +enum mte_tag_op_type { + TAG_OP_ALL = 0, + TAG_OP_STONLY = 1, +}; + +struct check_mmap_testcase { + int check_type; + int mem_type; + int mte_sync; + int mapping; + int tag_check; + int atag_check; + int tag_op; + bool enable_tco; +}; + +#define TAG_OP_ALL 0 +#define TAG_OP_STONLY 1 static size_t page_size; static int sizes[] = { @@ -30,8 +60,17 @@ static int sizes[] = { /* page size - 1*/ 0, /* page_size */ 0, /* page size + 1 */ 0 }; -static int check_mte_memory(char *ptr, int size, int mode, int tag_check) +static int check_mte_memory(char *ptr, int size, int mode, + int tag_check,int atag_check, int tag_op) { + char buf[MT_GRANULE_SIZE]; + + if (!mtefar_support && atag_check == ATAG_CHECK_ON) + return KSFT_SKIP; + + if (atag_check == ATAG_CHECK_ON) + ptr = mte_insert_atag(ptr); + mte_initialize_current_context(mode, (uintptr_t)ptr, size); memset(ptr, '1', size); mte_wait_after_trig(); @@ -54,16 +93,34 @@ static int check_mte_memory(char *ptr, int size, int mode, int tag_check) if (cur_mte_cxt.fault_valid == true && tag_check == TAG_CHECK_OFF) return KSFT_FAIL; + if (tag_op == TAG_OP_STONLY) { + mte_initialize_current_context(mode, (uintptr_t)ptr, -UNDERFLOW); + memcpy(buf, ptr - UNDERFLOW, MT_GRANULE_SIZE); + mte_wait_after_trig(); + if (cur_mte_cxt.fault_valid == true) + return KSFT_FAIL; + + mte_initialize_current_context(mode, (uintptr_t)ptr, size + OVERFLOW); + memcpy(buf, ptr + size, MT_GRANULE_SIZE); + mte_wait_after_trig(); + if (cur_mte_cxt.fault_valid == true) + return KSFT_FAIL; + } + return KSFT_PASS; } -static int check_anonymous_memory_mapping(int mem_type, int mode, int mapping, int tag_check) +static int check_anonymous_memory_mapping(int mem_type, int mode, int mapping, + int tag_check, int atag_check, int tag_op) { char *ptr, *map_ptr; int run, result, map_size; int item = ARRAY_SIZE(sizes); - mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); + if (tag_op == TAG_OP_STONLY && !mtestonly_support) + return KSFT_SKIP; + + mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, tag_op); for (run = 0; run < item; run++) { map_size = sizes[run] + OVERFLOW + UNDERFLOW; map_ptr = (char *)mte_allocate_memory(map_size, mem_type, mapping, false); @@ -79,23 +136,27 @@ static int check_anonymous_memory_mapping(int mem_type, int mode, int mapping, i munmap((void *)map_ptr, map_size); return KSFT_FAIL; } - result = check_mte_memory(ptr, sizes[run], mode, tag_check); + result = check_mte_memory(ptr, sizes[run], mode, tag_check, atag_check, tag_op); mte_clear_tags((void *)ptr, sizes[run]); mte_free_memory((void *)map_ptr, map_size, mem_type, false); - if (result == KSFT_FAIL) - return KSFT_FAIL; + if (result != KSFT_PASS) + return result; } return KSFT_PASS; } -static int check_file_memory_mapping(int mem_type, int mode, int mapping, int tag_check) +static int check_file_memory_mapping(int mem_type, int mode, int mapping, + int tag_check, int atag_check, int tag_op) { char *ptr, *map_ptr; int run, fd, map_size; int total = ARRAY_SIZE(sizes); int result = KSFT_PASS; - mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); + if (tag_op == TAG_OP_STONLY && !mtestonly_support) + return KSFT_SKIP; + + mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, tag_op); for (run = 0; run < total; run++) { fd = create_temp_file(); if (fd == -1) @@ -117,24 +178,24 @@ static int check_file_memory_mapping(int mem_type, int mode, int mapping, int ta close(fd); return KSFT_FAIL; } - result = check_mte_memory(ptr, sizes[run], mode, tag_check); + result = check_mte_memory(ptr, sizes[run], mode, tag_check, atag_check, tag_op); mte_clear_tags((void *)ptr, sizes[run]); munmap((void *)map_ptr, map_size); close(fd); - if (result == KSFT_FAIL) - break; + if (result != KSFT_PASS) + return result; } - return result; + return KSFT_PASS; } -static int check_clear_prot_mte_flag(int mem_type, int mode, int mapping) +static int check_clear_prot_mte_flag(int mem_type, int mode, int mapping, int atag_check) { char *ptr, *map_ptr; int run, prot_flag, result, fd, map_size; int total = ARRAY_SIZE(sizes); prot_flag = PROT_READ | PROT_WRITE; - mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); + mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false); for (run = 0; run < total; run++) { map_size = sizes[run] + OVERFLOW + UNDERFLOW; ptr = (char *)mte_allocate_memory_tag_range(sizes[run], mem_type, mapping, @@ -150,10 +211,10 @@ static int check_clear_prot_mte_flag(int mem_type, int mode, int mapping) ksft_print_msg("FAIL: mprotect not ignoring clear PROT_MTE property\n"); return KSFT_FAIL; } - result = check_mte_memory(ptr, sizes[run], mode, TAG_CHECK_ON); + result = check_mte_memory(ptr, sizes[run], mode, TAG_CHECK_ON, atag_check, TAG_OP_ALL); mte_free_memory_tag_range((void *)ptr, sizes[run], mem_type, UNDERFLOW, OVERFLOW); if (result != KSFT_PASS) - return KSFT_FAIL; + return result; fd = create_temp_file(); if (fd == -1) @@ -174,19 +235,715 @@ static int check_clear_prot_mte_flag(int mem_type, int mode, int mapping) close(fd); return KSFT_FAIL; } - result = check_mte_memory(ptr, sizes[run], mode, TAG_CHECK_ON); + result = check_mte_memory(ptr, sizes[run], mode, TAG_CHECK_ON, atag_check, TAG_OP_ALL); mte_free_memory_tag_range((void *)ptr, sizes[run], mem_type, UNDERFLOW, OVERFLOW); close(fd); if (result != KSFT_PASS) - return KSFT_FAIL; + return result; } return KSFT_PASS; } +const char *format_test_name(struct check_mmap_testcase *tc) +{ + static char test_name[TEST_NAME_MAX]; + const char *check_type_str; + const char *mem_type_str; + const char *sync_str; + const char *mapping_str; + const char *tag_check_str; + const char *atag_check_str; + const char *tag_op_str; + + switch (tc->check_type) { + case CHECK_ANON_MEM: + check_type_str = "anonymous memory"; + break; + case CHECK_FILE_MEM: + check_type_str = "file memory"; + break; + case CHECK_CLEAR_PROT_MTE: + check_type_str = "clear PROT_MTE flags"; + break; + default: + assert(0); + break; + } + + switch (tc->mem_type) { + case USE_MMAP: + mem_type_str = "mmap"; + break; + case USE_MPROTECT: + mem_type_str = "mmap/mprotect"; + break; + default: + assert(0); + break; + } + + switch (tc->mte_sync) { + case MTE_NONE_ERR: + sync_str = "no error"; + break; + case MTE_SYNC_ERR: + sync_str = "sync error"; + break; + case MTE_ASYNC_ERR: + sync_str = "async error"; + break; + default: + assert(0); + break; + } + + switch (tc->mapping) { + case MAP_SHARED: + mapping_str = "shared"; + break; + case MAP_PRIVATE: + mapping_str = "private"; + break; + default: + assert(0); + break; + } + + switch (tc->tag_check) { + case TAG_CHECK_ON: + tag_check_str = "tag check on"; + break; + case TAG_CHECK_OFF: + tag_check_str = "tag check off"; + break; + default: + assert(0); + break; + } + + switch (tc->atag_check) { + case ATAG_CHECK_ON: + atag_check_str = "with address tag [63:60]"; + break; + case ATAG_CHECK_OFF: + atag_check_str = "without address tag [63:60]"; + break; + default: + assert(0); + break; + } + + snprintf(test_name, sizeof(test_name), + "Check %s with %s mapping, %s mode, %s memory and %s (%s)\n", + check_type_str, mapping_str, sync_str, mem_type_str, + tag_check_str, atag_check_str); + + switch (tc->tag_op) { + case TAG_OP_ALL: + tag_op_str = ""; + break; + case TAG_OP_STONLY: + tag_op_str = " / store-only"; + break; + default: + assert(0); + break; + } + + snprintf(test_name, TEST_NAME_MAX, + "Check %s with %s mapping, %s mode, %s memory and %s (%s%s)\n", + check_type_str, mapping_str, sync_str, mem_type_str, + tag_check_str, atag_check_str, tag_op_str); + + return test_name; +} + int main(int argc, char *argv[]) { - int err; + int err, i; int item = ARRAY_SIZE(sizes); + struct check_mmap_testcase test_cases[]= { + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_OFF, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = true, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_OFF, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = true, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_NONE_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_OFF, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_NONE_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_OFF, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_CLEAR_PROT_MTE, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_CLEAR_PROT_MTE, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_OFF, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_ANON_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_SHARED, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_FILE_MEM, + .mem_type = USE_MMAP, + .mte_sync = MTE_ASYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_STONLY, + .enable_tco = false, + }, + { + .check_type = CHECK_CLEAR_PROT_MTE, + .mem_type = USE_MMAP, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + { + .check_type = CHECK_CLEAR_PROT_MTE, + .mem_type = USE_MPROTECT, + .mte_sync = MTE_SYNC_ERR, + .mapping = MAP_PRIVATE, + .tag_check = TAG_CHECK_ON, + .atag_check = ATAG_CHECK_ON, + .tag_op = TAG_OP_ALL, + .enable_tco = false, + }, + }; err = mte_default_setup(); if (err) @@ -200,64 +957,51 @@ int main(int argc, char *argv[]) sizes[item - 2] = page_size; sizes[item - 1] = page_size + 1; - /* Register signal handlers */ - mte_register_signal(SIGBUS, mte_default_handler); - mte_register_signal(SIGSEGV, mte_default_handler); - /* Set test plan */ - ksft_set_plan(22); - - mte_enable_pstate_tco(); - - evaluate_test(check_anonymous_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE, TAG_CHECK_OFF), - "Check anonymous memory with private mapping, sync error mode, mmap memory and tag check off\n"); - evaluate_test(check_file_memory_mapping(USE_MPROTECT, MTE_SYNC_ERR, MAP_PRIVATE, TAG_CHECK_OFF), - "Check file memory with private mapping, sync error mode, mmap/mprotect memory and tag check off\n"); + ksft_set_plan(ARRAY_SIZE(test_cases)); - mte_disable_pstate_tco(); - evaluate_test(check_anonymous_memory_mapping(USE_MMAP, MTE_NONE_ERR, MAP_PRIVATE, TAG_CHECK_OFF), - "Check anonymous memory with private mapping, no error mode, mmap memory and tag check off\n"); - evaluate_test(check_file_memory_mapping(USE_MPROTECT, MTE_NONE_ERR, MAP_PRIVATE, TAG_CHECK_OFF), - "Check file memory with private mapping, no error mode, mmap/mprotect memory and tag check off\n"); + for (i = 0 ; i < ARRAY_SIZE(test_cases); i++) { + /* Register signal handlers */ + mte_register_signal(SIGBUS, mte_default_handler, + test_cases[i].atag_check == ATAG_CHECK_ON); + mte_register_signal(SIGSEGV, mte_default_handler, + test_cases[i].atag_check == ATAG_CHECK_ON); - evaluate_test(check_anonymous_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE, TAG_CHECK_ON), - "Check anonymous memory with private mapping, sync error mode, mmap memory and tag check on\n"); - evaluate_test(check_anonymous_memory_mapping(USE_MPROTECT, MTE_SYNC_ERR, MAP_PRIVATE, TAG_CHECK_ON), - "Check anonymous memory with private mapping, sync error mode, mmap/mprotect memory and tag check on\n"); - evaluate_test(check_anonymous_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_SHARED, TAG_CHECK_ON), - "Check anonymous memory with shared mapping, sync error mode, mmap memory and tag check on\n"); - evaluate_test(check_anonymous_memory_mapping(USE_MPROTECT, MTE_SYNC_ERR, MAP_SHARED, TAG_CHECK_ON), - "Check anonymous memory with shared mapping, sync error mode, mmap/mprotect memory and tag check on\n"); - evaluate_test(check_anonymous_memory_mapping(USE_MMAP, MTE_ASYNC_ERR, MAP_PRIVATE, TAG_CHECK_ON), - "Check anonymous memory with private mapping, async error mode, mmap memory and tag check on\n"); - evaluate_test(check_anonymous_memory_mapping(USE_MPROTECT, MTE_ASYNC_ERR, MAP_PRIVATE, TAG_CHECK_ON), - "Check anonymous memory with private mapping, async error mode, mmap/mprotect memory and tag check on\n"); - evaluate_test(check_anonymous_memory_mapping(USE_MMAP, MTE_ASYNC_ERR, MAP_SHARED, TAG_CHECK_ON), - "Check anonymous memory with shared mapping, async error mode, mmap memory and tag check on\n"); - evaluate_test(check_anonymous_memory_mapping(USE_MPROTECT, MTE_ASYNC_ERR, MAP_SHARED, TAG_CHECK_ON), - "Check anonymous memory with shared mapping, async error mode, mmap/mprotect memory and tag check on\n"); + if (test_cases[i].enable_tco) + mte_enable_pstate_tco(); + else + mte_disable_pstate_tco(); - evaluate_test(check_file_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE, TAG_CHECK_ON), - "Check file memory with private mapping, sync error mode, mmap memory and tag check on\n"); - evaluate_test(check_file_memory_mapping(USE_MPROTECT, MTE_SYNC_ERR, MAP_PRIVATE, TAG_CHECK_ON), - "Check file memory with private mapping, sync error mode, mmap/mprotect memory and tag check on\n"); - evaluate_test(check_file_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_SHARED, TAG_CHECK_ON), - "Check file memory with shared mapping, sync error mode, mmap memory and tag check on\n"); - evaluate_test(check_file_memory_mapping(USE_MPROTECT, MTE_SYNC_ERR, MAP_SHARED, TAG_CHECK_ON), - "Check file memory with shared mapping, sync error mode, mmap/mprotect memory and tag check on\n"); - evaluate_test(check_file_memory_mapping(USE_MMAP, MTE_ASYNC_ERR, MAP_PRIVATE, TAG_CHECK_ON), - "Check file memory with private mapping, async error mode, mmap memory and tag check on\n"); - evaluate_test(check_file_memory_mapping(USE_MPROTECT, MTE_ASYNC_ERR, MAP_PRIVATE, TAG_CHECK_ON), - "Check file memory with private mapping, async error mode, mmap/mprotect memory and tag check on\n"); - evaluate_test(check_file_memory_mapping(USE_MMAP, MTE_ASYNC_ERR, MAP_SHARED, TAG_CHECK_ON), - "Check file memory with shared mapping, async error mode, mmap memory and tag check on\n"); - evaluate_test(check_file_memory_mapping(USE_MPROTECT, MTE_ASYNC_ERR, MAP_SHARED, TAG_CHECK_ON), - "Check file memory with shared mapping, async error mode, mmap/mprotect memory and tag check on\n"); - - evaluate_test(check_clear_prot_mte_flag(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE), - "Check clear PROT_MTE flags with private mapping, sync error mode and mmap memory\n"); - evaluate_test(check_clear_prot_mte_flag(USE_MPROTECT, MTE_SYNC_ERR, MAP_PRIVATE), - "Check clear PROT_MTE flags with private mapping and sync error mode and mmap/mprotect memory\n"); + switch (test_cases[i].check_type) { + case CHECK_ANON_MEM: + evaluate_test(check_anonymous_memory_mapping(test_cases[i].mem_type, + test_cases[i].mte_sync, + test_cases[i].mapping, + test_cases[i].tag_check, + test_cases[i].atag_check, + test_cases[i].tag_op), + format_test_name(&test_cases[i])); + break; + case CHECK_FILE_MEM: + evaluate_test(check_file_memory_mapping(test_cases[i].mem_type, + test_cases[i].mte_sync, + test_cases[i].mapping, + test_cases[i].tag_check, + test_cases[i].atag_check, + test_cases[i].tag_op), + format_test_name(&test_cases[i])); + break; + case CHECK_CLEAR_PROT_MTE: + evaluate_test(check_clear_prot_mte_flag(test_cases[i].mem_type, + test_cases[i].mte_sync, + test_cases[i].mapping, + test_cases[i].atag_check), + format_test_name(&test_cases[i])); + break; + default: + exit(KSFT_FAIL); + } + } mte_restore_setup(); ksft_print_cnts(); diff --git a/tools/testing/selftests/arm64/mte/check_prctl.c b/tools/testing/selftests/arm64/mte/check_prctl.c index 4c89e9538ca0..f7f320defa7b 100644 --- a/tools/testing/selftests/arm64/mte/check_prctl.c +++ b/tools/testing/selftests/arm64/mte/check_prctl.c @@ -12,6 +12,10 @@ #include "kselftest.h" +#ifndef AT_HWCAP3 +#define AT_HWCAP3 29 +#endif + static int set_tagged_addr_ctrl(int val) { int ret; @@ -60,7 +64,7 @@ void check_basic_read(void) /* * Attempt to set a specified combination of modes. */ -void set_mode_test(const char *name, int hwcap2, int mask) +void set_mode_test(const char *name, int hwcap2, int hwcap3, int mask) { int ret; @@ -69,6 +73,11 @@ void set_mode_test(const char *name, int hwcap2, int mask) return; } + if ((getauxval(AT_HWCAP3) & hwcap3) != hwcap3) { + ksft_test_result_skip("%s\n", name); + return; + } + ret = set_tagged_addr_ctrl(mask); if (ret < 0) { ksft_test_result_fail("%s\n", name); @@ -81,7 +90,7 @@ void set_mode_test(const char *name, int hwcap2, int mask) return; } - if ((ret & PR_MTE_TCF_MASK) == mask) { + if ((ret & (PR_MTE_TCF_MASK | PR_MTE_STORE_ONLY)) == mask) { ksft_test_result_pass("%s\n", name); } else { ksft_print_msg("Got %x, expected %x\n", @@ -93,12 +102,16 @@ void set_mode_test(const char *name, int hwcap2, int mask) struct mte_mode { int mask; int hwcap2; + int hwcap3; const char *name; } mte_modes[] = { - { PR_MTE_TCF_NONE, 0, "NONE" }, - { PR_MTE_TCF_SYNC, HWCAP2_MTE, "SYNC" }, - { PR_MTE_TCF_ASYNC, HWCAP2_MTE, "ASYNC" }, - { PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC, HWCAP2_MTE, "SYNC+ASYNC" }, + { PR_MTE_TCF_NONE, 0, 0, "NONE" }, + { PR_MTE_TCF_SYNC, HWCAP2_MTE, 0, "SYNC" }, + { PR_MTE_TCF_ASYNC, HWCAP2_MTE, 0, "ASYNC" }, + { PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC, HWCAP2_MTE, 0, "SYNC+ASYNC" }, + { PR_MTE_TCF_SYNC | PR_MTE_STORE_ONLY, HWCAP2_MTE, HWCAP3_MTE_STORE_ONLY, "SYNC+STONLY" }, + { PR_MTE_TCF_ASYNC | PR_MTE_STORE_ONLY, HWCAP2_MTE, HWCAP3_MTE_STORE_ONLY, "ASYNC+STONLY" }, + { PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC | PR_MTE_STORE_ONLY, HWCAP2_MTE, HWCAP3_MTE_STORE_ONLY, "SYNC+ASYNC+STONLY" }, }; int main(void) @@ -106,11 +119,11 @@ int main(void) int i; ksft_print_header(); - ksft_set_plan(5); + ksft_set_plan(ARRAY_SIZE(mte_modes)); check_basic_read(); for (i = 0; i < ARRAY_SIZE(mte_modes); i++) - set_mode_test(mte_modes[i].name, mte_modes[i].hwcap2, + set_mode_test(mte_modes[i].name, mte_modes[i].hwcap2, mte_modes[i].hwcap3, mte_modes[i].mask); ksft_print_cnts(); diff --git a/tools/testing/selftests/arm64/mte/check_tags_inclusion.c b/tools/testing/selftests/arm64/mte/check_tags_inclusion.c index a3d1e23fe02a..4b764f2a8185 100644 --- a/tools/testing/selftests/arm64/mte/check_tags_inclusion.c +++ b/tools/testing/selftests/arm64/mte/check_tags_inclusion.c @@ -57,7 +57,7 @@ static int check_single_included_tags(int mem_type, int mode) return KSFT_FAIL; for (tag = 0; (tag < MT_TAG_COUNT) && (result == KSFT_PASS); tag++) { - ret = mte_switch_mode(mode, MT_INCLUDE_VALID_TAG(tag)); + ret = mte_switch_mode(mode, MT_INCLUDE_VALID_TAG(tag), false); if (ret != 0) result = KSFT_FAIL; /* Try to catch a excluded tag by a number of tries. */ @@ -91,7 +91,7 @@ static int check_multiple_included_tags(int mem_type, int mode) for (tag = 0; (tag < MT_TAG_COUNT - 1) && (result == KSFT_PASS); tag++) { excl_mask |= 1 << tag; - mte_switch_mode(mode, MT_INCLUDE_VALID_TAGS(excl_mask)); + mte_switch_mode(mode, MT_INCLUDE_VALID_TAGS(excl_mask), false); /* Try to catch a excluded tag by a number of tries. */ for (run = 0; (run < RUNS) && (result == KSFT_PASS); run++) { ptr = mte_insert_tags(ptr, BUFFER_SIZE); @@ -120,7 +120,7 @@ static int check_all_included_tags(int mem_type, int mode) mem_type, false) != KSFT_PASS) return KSFT_FAIL; - ret = mte_switch_mode(mode, MT_INCLUDE_TAG_MASK); + ret = mte_switch_mode(mode, MT_INCLUDE_TAG_MASK, false); if (ret != 0) return KSFT_FAIL; /* Try to catch a excluded tag by a number of tries. */ @@ -145,7 +145,7 @@ static int check_none_included_tags(int mem_type, int mode) if (check_allocated_memory(ptr, BUFFER_SIZE, mem_type, false) != KSFT_PASS) return KSFT_FAIL; - ret = mte_switch_mode(mode, MT_EXCLUDE_TAG_MASK); + ret = mte_switch_mode(mode, MT_EXCLUDE_TAG_MASK, false); if (ret != 0) return KSFT_FAIL; /* Try to catch a excluded tag by a number of tries. */ @@ -180,7 +180,7 @@ int main(int argc, char *argv[]) return err; /* Register SIGSEGV handler */ - mte_register_signal(SIGSEGV, mte_default_handler); + mte_register_signal(SIGSEGV, mte_default_handler, false); /* Set test plan */ ksft_set_plan(4); diff --git a/tools/testing/selftests/arm64/mte/check_user_mem.c b/tools/testing/selftests/arm64/mte/check_user_mem.c index f4ae5f87a3b7..fb7936c4e097 100644 --- a/tools/testing/selftests/arm64/mte/check_user_mem.c +++ b/tools/testing/selftests/arm64/mte/check_user_mem.c @@ -44,7 +44,7 @@ static int check_usermem_access_fault(int mem_type, int mode, int mapping, err = KSFT_PASS; len = 2 * page_sz; - mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG); + mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false); fd = create_temp_file(); if (fd == -1) return KSFT_FAIL; @@ -211,7 +211,7 @@ int main(int argc, char *argv[]) return err; /* Register signal handlers */ - mte_register_signal(SIGSEGV, mte_default_handler); + mte_register_signal(SIGSEGV, mte_default_handler, false); /* Set test plan */ ksft_set_plan(64); diff --git a/tools/testing/selftests/arm64/mte/mte_common_util.c b/tools/testing/selftests/arm64/mte/mte_common_util.c index a1dc2fe5285b..397e57dd946a 100644 --- a/tools/testing/selftests/arm64/mte/mte_common_util.c +++ b/tools/testing/selftests/arm64/mte/mte_common_util.c @@ -6,6 +6,7 @@ #include <signal.h> #include <stdio.h> #include <stdlib.h> +#include <time.h> #include <unistd.h> #include <linux/auxvec.h> @@ -19,20 +20,40 @@ #include "mte_common_util.h" #include "mte_def.h" +#ifndef SA_EXPOSE_TAGBITS +#define SA_EXPOSE_TAGBITS 0x00000800 +#endif + #define INIT_BUFFER_SIZE 256 struct mte_fault_cxt cur_mte_cxt; +bool mtefar_support; +bool mtestonly_support; static unsigned int mte_cur_mode; static unsigned int mte_cur_pstate_tco; +static bool mte_cur_stonly; void mte_default_handler(int signum, siginfo_t *si, void *uc) { + struct sigaction sa; unsigned long addr = (unsigned long)si->si_addr; + unsigned char si_tag, si_atag; + + sigaction(signum, NULL, &sa); + + if (sa.sa_flags & SA_EXPOSE_TAGBITS) { + si_tag = MT_FETCH_TAG(addr); + si_atag = MT_FETCH_ATAG(addr); + addr = MT_CLEAR_TAGS(addr); + } else { + si_tag = 0; + si_atag = 0; + } if (signum == SIGSEGV) { #ifdef DEBUG - ksft_print_msg("INFO: SIGSEGV signal at pc=%lx, fault addr=%lx, si_code=%lx\n", - ((ucontext_t *)uc)->uc_mcontext.pc, addr, si->si_code); + ksft_print_msg("INFO: SIGSEGV signal at pc=%lx, fault addr=%lx, si_code=%lx, si_tag=%x, si_atag=%x\n", + ((ucontext_t *)uc)->uc_mcontext.pc, addr, si->si_code, si_tag, si_atag); #endif if (si->si_code == SEGV_MTEAERR) { if (cur_mte_cxt.trig_si_code == si->si_code) @@ -45,13 +66,18 @@ void mte_default_handler(int signum, siginfo_t *si, void *uc) } /* Compare the context for precise error */ else if (si->si_code == SEGV_MTESERR) { + if ((!mtefar_support && si_atag) || (si_atag != MT_FETCH_ATAG(cur_mte_cxt.trig_addr))) { + ksft_print_msg("Invalid MTE synchronous exception caught for address tag! si_tag=%x, si_atag: %x\n", si_tag, si_atag); + exit(KSFT_FAIL); + } + if (cur_mte_cxt.trig_si_code == si->si_code && ((cur_mte_cxt.trig_range >= 0 && - addr >= MT_CLEAR_TAG(cur_mte_cxt.trig_addr) && - addr <= (MT_CLEAR_TAG(cur_mte_cxt.trig_addr) + cur_mte_cxt.trig_range)) || + addr >= MT_CLEAR_TAGS(cur_mte_cxt.trig_addr) && + addr <= (MT_CLEAR_TAGS(cur_mte_cxt.trig_addr) + cur_mte_cxt.trig_range)) || (cur_mte_cxt.trig_range < 0 && - addr <= MT_CLEAR_TAG(cur_mte_cxt.trig_addr) && - addr >= (MT_CLEAR_TAG(cur_mte_cxt.trig_addr) + cur_mte_cxt.trig_range)))) { + addr <= MT_CLEAR_TAGS(cur_mte_cxt.trig_addr) && + addr >= (MT_CLEAR_TAGS(cur_mte_cxt.trig_addr) + cur_mte_cxt.trig_range)))) { cur_mte_cxt.fault_valid = true; /* Adjust the pc by 4 */ ((ucontext_t *)uc)->uc_mcontext.pc += 4; @@ -67,11 +93,11 @@ void mte_default_handler(int signum, siginfo_t *si, void *uc) ksft_print_msg("INFO: SIGBUS signal at pc=%llx, fault addr=%lx, si_code=%x\n", ((ucontext_t *)uc)->uc_mcontext.pc, addr, si->si_code); if ((cur_mte_cxt.trig_range >= 0 && - addr >= MT_CLEAR_TAG(cur_mte_cxt.trig_addr) && - addr <= (MT_CLEAR_TAG(cur_mte_cxt.trig_addr) + cur_mte_cxt.trig_range)) || + addr >= MT_CLEAR_TAGS(cur_mte_cxt.trig_addr) && + addr <= (MT_CLEAR_TAGS(cur_mte_cxt.trig_addr) + cur_mte_cxt.trig_range)) || (cur_mte_cxt.trig_range < 0 && - addr <= MT_CLEAR_TAG(cur_mte_cxt.trig_addr) && - addr >= (MT_CLEAR_TAG(cur_mte_cxt.trig_addr) + cur_mte_cxt.trig_range))) { + addr <= MT_CLEAR_TAGS(cur_mte_cxt.trig_addr) && + addr >= (MT_CLEAR_TAGS(cur_mte_cxt.trig_addr) + cur_mte_cxt.trig_range))) { cur_mte_cxt.fault_valid = true; /* Adjust the pc by 4 */ ((ucontext_t *)uc)->uc_mcontext.pc += 4; @@ -79,12 +105,17 @@ void mte_default_handler(int signum, siginfo_t *si, void *uc) } } -void mte_register_signal(int signal, void (*handler)(int, siginfo_t *, void *)) +void mte_register_signal(int signal, void (*handler)(int, siginfo_t *, void *), + bool export_tags) { struct sigaction sa; sa.sa_sigaction = handler; sa.sa_flags = SA_SIGINFO; + + if (export_tags && signal == SIGSEGV) + sa.sa_flags |= SA_EXPOSE_TAGBITS; + sigemptyset(&sa.sa_mask); sigaction(signal, &sa, NULL); } @@ -120,6 +151,19 @@ void mte_clear_tags(void *ptr, size_t size) mte_clear_tag_address_range(ptr, size); } +void *mte_insert_atag(void *ptr) +{ + unsigned char atag; + + atag = mtefar_support ? (random() % MT_ATAG_MASK) + 1 : 0; + return (void *)MT_SET_ATAG((unsigned long)ptr, atag); +} + +void *mte_clear_atag(void *ptr) +{ + return (void *)MT_CLEAR_ATAG((unsigned long)ptr); +} + static void *__mte_allocate_memory_range(size_t size, int mem_type, int mapping, size_t range_before, size_t range_after, bool tags, int fd) @@ -272,7 +316,7 @@ void mte_initialize_current_context(int mode, uintptr_t ptr, ssize_t range) cur_mte_cxt.trig_si_code = 0; } -int mte_switch_mode(int mte_option, unsigned long incl_mask) +int mte_switch_mode(int mte_option, unsigned long incl_mask, bool stonly) { unsigned long en = 0; @@ -304,6 +348,9 @@ int mte_switch_mode(int mte_option, unsigned long incl_mask) break; } + if (mtestonly_support && stonly) + en |= PR_MTE_STORE_ONLY; + en |= (incl_mask << PR_MTE_TAG_SHIFT); /* Enable address tagging ABI, mte error reporting mode and tag inclusion mask. */ if (prctl(PR_SET_TAGGED_ADDR_CTRL, en, 0, 0, 0) != 0) { @@ -316,12 +363,21 @@ int mte_switch_mode(int mte_option, unsigned long incl_mask) int mte_default_setup(void) { unsigned long hwcaps2 = getauxval(AT_HWCAP2); + unsigned long hwcaps3 = getauxval(AT_HWCAP3); unsigned long en = 0; int ret; + /* To generate random address tag */ + srandom(time(NULL)); + if (!(hwcaps2 & HWCAP2_MTE)) ksft_exit_skip("MTE features unavailable\n"); + mtefar_support = !!(hwcaps3 & HWCAP3_MTE_FAR); + + if (hwcaps3 & HWCAP3_MTE_STORE_ONLY) + mtestonly_support = true; + /* Get current mte mode */ ret = prctl(PR_GET_TAGGED_ADDR_CTRL, en, 0, 0, 0); if (ret < 0) { @@ -335,6 +391,8 @@ int mte_default_setup(void) else if (ret & PR_MTE_TCF_NONE) mte_cur_mode = MTE_NONE_ERR; + mte_cur_stonly = (ret & PR_MTE_STORE_ONLY) ? true : false; + mte_cur_pstate_tco = mte_get_pstate_tco(); /* Disable PSTATE.TCO */ mte_disable_pstate_tco(); @@ -343,7 +401,7 @@ int mte_default_setup(void) void mte_restore_setup(void) { - mte_switch_mode(mte_cur_mode, MTE_ALLOW_NON_ZERO_TAG); + mte_switch_mode(mte_cur_mode, MTE_ALLOW_NON_ZERO_TAG, mte_cur_stonly); if (mte_cur_pstate_tco == MT_PSTATE_TCO_EN) mte_enable_pstate_tco(); else if (mte_cur_pstate_tco == MT_PSTATE_TCO_DIS) diff --git a/tools/testing/selftests/arm64/mte/mte_common_util.h b/tools/testing/selftests/arm64/mte/mte_common_util.h index a0017a303beb..250d671329a5 100644 --- a/tools/testing/selftests/arm64/mte/mte_common_util.h +++ b/tools/testing/selftests/arm64/mte/mte_common_util.h @@ -37,10 +37,13 @@ struct mte_fault_cxt { }; extern struct mte_fault_cxt cur_mte_cxt; +extern bool mtefar_support; +extern bool mtestonly_support; /* MTE utility functions */ void mte_default_handler(int signum, siginfo_t *si, void *uc); -void mte_register_signal(int signal, void (*handler)(int, siginfo_t *, void *)); +void mte_register_signal(int signal, void (*handler)(int, siginfo_t *, void *), + bool export_tags); void mte_wait_after_trig(void); void *mte_allocate_memory(size_t size, int mem_type, int mapping, bool tags); void *mte_allocate_memory_tag_range(size_t size, int mem_type, int mapping, @@ -54,9 +57,11 @@ void mte_free_memory_tag_range(void *ptr, size_t size, int mem_type, size_t range_before, size_t range_after); void *mte_insert_tags(void *ptr, size_t size); void mte_clear_tags(void *ptr, size_t size); +void *mte_insert_atag(void *ptr); +void *mte_clear_atag(void *ptr); int mte_default_setup(void); void mte_restore_setup(void); -int mte_switch_mode(int mte_option, unsigned long incl_mask); +int mte_switch_mode(int mte_option, unsigned long incl_mask, bool stonly); void mte_initialize_current_context(int mode, uintptr_t ptr, ssize_t range); /* Common utility functions */ diff --git a/tools/testing/selftests/arm64/mte/mte_def.h b/tools/testing/selftests/arm64/mte/mte_def.h index 9b188254b61a..6ad22f07c9b8 100644 --- a/tools/testing/selftests/arm64/mte/mte_def.h +++ b/tools/testing/selftests/arm64/mte/mte_def.h @@ -42,6 +42,8 @@ #define MT_TAG_COUNT 16 #define MT_INCLUDE_TAG_MASK 0xFFFF #define MT_EXCLUDE_TAG_MASK 0x0 +#define MT_ATAG_SHIFT 60 +#define MT_ATAG_MASK 0xFUL #define MT_ALIGN_GRANULE (MT_GRANULE_SIZE - 1) #define MT_CLEAR_TAG(x) ((x) & ~(MT_TAG_MASK << MT_TAG_SHIFT)) @@ -49,6 +51,12 @@ #define MT_FETCH_TAG(x) ((x >> MT_TAG_SHIFT) & (MT_TAG_MASK)) #define MT_ALIGN_UP(x) ((x + MT_ALIGN_GRANULE) & ~(MT_ALIGN_GRANULE)) +#define MT_CLEAR_ATAG(x) ((x) & ~(MT_TAG_MASK << MT_ATAG_SHIFT)) +#define MT_SET_ATAG(x, y) ((x) | (((y) & MT_ATAG_MASK) << MT_ATAG_SHIFT)) +#define MT_FETCH_ATAG(x) ((x >> MT_ATAG_SHIFT) & (MT_ATAG_MASK)) + +#define MT_CLEAR_TAGS(x) (MT_CLEAR_ATAG(MT_CLEAR_TAG(x))) + #define MT_PSTATE_TCO_SHIFT 25 #define MT_PSTATE_TCO_MASK ~(0x1 << MT_PSTATE_TCO_SHIFT) #define MT_PSTATE_TCO_EN 1 diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 7247833fe623..8916ab814a3e 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -97,6 +97,9 @@ CONFIG_NF_TABLES_NETDEV=y CONFIG_NF_TABLES_IPV4=y CONFIG_NF_TABLES_IPV6=y CONFIG_NETFILTER_INGRESS=y +CONFIG_IP_NF_IPTABLES_LEGACY=y +CONFIG_IP6_NF_IPTABLES_LEGACY=y +CONFIG_NETFILTER_XTABLES_LEGACY=y CONFIG_NF_FLOW_TABLE=y CONFIG_NF_FLOW_TABLE_INET=y CONFIG_NETFILTER_NETLINK=y diff --git a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c index a4517bee34d5..27781df8f2fb 100644 --- a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c +++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c @@ -1,11 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2024 Meta +#include <poll.h> #include <test_progs.h> #include "network_helpers.h" #include "sock_iter_batch.skel.h" #define TEST_NS "sock_iter_batch_netns" +#define TEST_CHILD_NS "sock_iter_batch_child_netns" static const int init_batch_size = 16; static const int nr_soreuse = 4; @@ -118,6 +120,45 @@ done: return nth_sock_idx; } +static void destroy(int fd) +{ + struct sock_iter_batch *skel = NULL; + __u64 cookie = socket_cookie(fd); + struct bpf_link *link = NULL; + int iter_fd = -1; + int nread; + __u64 out; + + skel = sock_iter_batch__open(); + if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open")) + goto done; + + skel->rodata->destroy_cookie = cookie; + + if (!ASSERT_OK(sock_iter_batch__load(skel), "sock_iter_batch__load")) + goto done; + + link = bpf_program__attach_iter(skel->progs.iter_tcp_destroy, NULL); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter")) + goto done; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (!ASSERT_OK_FD(iter_fd, "bpf_iter_create")) + goto done; + + /* Delete matching socket. */ + nread = read(iter_fd, &out, sizeof(out)); + ASSERT_GE(nread, 0, "nread"); + if (nread) + ASSERT_EQ(out, cookie, "cookie matches"); +done: + if (iter_fd >= 0) + close(iter_fd); + bpf_link__destroy(link); + sock_iter_batch__destroy(skel); + close(fd); +} + static int get_seen_count(int fd, struct sock_count counts[], int n) { __u64 cookie = socket_cookie(fd); @@ -152,8 +193,71 @@ static void check_n_were_seen_once(int *fds, int fds_len, int n, ASSERT_EQ(seen_once, n, "seen_once"); } +static int accept_from_one(struct pollfd *server_poll_fds, + int server_poll_fds_len) +{ + static const int poll_timeout_ms = 5000; /* 5s */ + int ret; + int i; + + ret = poll(server_poll_fds, server_poll_fds_len, poll_timeout_ms); + if (!ASSERT_EQ(ret, 1, "poll")) + return -1; + + for (i = 0; i < server_poll_fds_len; i++) + if (server_poll_fds[i].revents & POLLIN) + return accept(server_poll_fds[i].fd, NULL, NULL); + + return -1; +} + +static int *connect_to_server(int family, int sock_type, const char *addr, + __u16 port, int nr_connects, int *server_fds, + int server_fds_len) +{ + struct pollfd *server_poll_fds = NULL; + int *established_socks = NULL; + int i; + + server_poll_fds = calloc(server_fds_len, sizeof(*server_poll_fds)); + if (!ASSERT_OK_PTR(server_poll_fds, "server_poll_fds")) + return NULL; + + for (i = 0; i < server_fds_len; i++) { + server_poll_fds[i].fd = server_fds[i]; + server_poll_fds[i].events = POLLIN; + } + + i = 0; + + established_socks = malloc(sizeof(*established_socks) * nr_connects*2); + if (!ASSERT_OK_PTR(established_socks, "established_socks")) + goto error; + + while (nr_connects--) { + established_socks[i] = connect_to_addr_str(family, sock_type, + addr, port, NULL); + if (!ASSERT_OK_FD(established_socks[i], "connect_to_addr_str")) + goto error; + i++; + established_socks[i] = accept_from_one(server_poll_fds, + server_fds_len); + if (!ASSERT_OK_FD(established_socks[i], "accept_from_one")) + goto error; + i++; + } + + free(server_poll_fds); + return established_socks; +error: + free_fds(established_socks, i); + free(server_poll_fds); + return NULL; +} + static void remove_seen(int family, int sock_type, const char *addr, __u16 port, - int *socks, int socks_len, struct sock_count *counts, + int *socks, int socks_len, int *established_socks, + int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { int close_idx; @@ -182,8 +286,46 @@ static void remove_seen(int family, int sock_type, const char *addr, __u16 port, counts_len); } +static void remove_seen_established(int family, int sock_type, const char *addr, + __u16 port, int *listen_socks, + int listen_socks_len, int *established_socks, + int established_socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + int close_idx; + + /* Iterate through all listening sockets. */ + read_n(iter_fd, listen_socks_len, counts, counts_len); + + /* Make sure we saw all listening sockets exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + + /* Leave one established socket. */ + read_n(iter_fd, established_socks_len - 1, counts, counts_len); + + /* Close a socket we've already seen to remove it from the bucket. */ + close_idx = get_nth_socket(established_socks, established_socks_len, + link, listen_socks_len + 1); + if (!ASSERT_GE(close_idx, 0, "close_idx")) + return; + destroy(established_socks[close_idx]); + established_socks[close_idx] = -1; + + /* Iterate through the rest of the sockets. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure the last socket wasn't skipped and that there were no + * repeats. + */ + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len - 1, counts, counts_len); +} + static void remove_unseen(int family, int sock_type, const char *addr, __u16 port, int *socks, int socks_len, + int *established_socks, int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { @@ -214,8 +356,54 @@ static void remove_unseen(int family, int sock_type, const char *addr, counts_len); } +static void remove_unseen_established(int family, int sock_type, + const char *addr, __u16 port, + int *listen_socks, int listen_socks_len, + int *established_socks, + int established_socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + int close_idx; + + /* Iterate through all listening sockets. */ + read_n(iter_fd, listen_socks_len, counts, counts_len); + + /* Make sure we saw all listening sockets exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + + /* Iterate through the first established socket. */ + read_n(iter_fd, 1, counts, counts_len); + + /* Make sure we saw one established socks. */ + check_n_were_seen_once(established_socks, established_socks_len, 1, + counts, counts_len); + + /* Close what would be the next socket in the bucket to exercise the + * condition where we need to skip past the first cookie we remembered. + */ + close_idx = get_nth_socket(established_socks, established_socks_len, + link, listen_socks_len + 1); + if (!ASSERT_GE(close_idx, 0, "close_idx")) + return; + + destroy(established_socks[close_idx]); + established_socks[close_idx] = -1; + + /* Iterate through the rest of the sockets. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure the remaining sockets were seen exactly once and that we + * didn't repeat the socket that was already seen. + */ + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len - 1, counts, counts_len); +} + static void remove_all(int family, int sock_type, const char *addr, __u16 port, int *socks, int socks_len, + int *established_socks, int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { @@ -242,8 +430,57 @@ static void remove_all(int family, int sock_type, const char *addr, ASSERT_EQ(read_n(iter_fd, -1, counts, counts_len), 0, "read_n"); } +static void remove_all_established(int family, int sock_type, const char *addr, + __u16 port, int *listen_socks, + int listen_socks_len, int *established_socks, + int established_socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + int *close_idx = NULL; + int i; + + /* Iterate through all listening sockets. */ + read_n(iter_fd, listen_socks_len, counts, counts_len); + + /* Make sure we saw all listening sockets exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + + /* Iterate through the first established socket. */ + read_n(iter_fd, 1, counts, counts_len); + + /* Make sure we saw one established socks. */ + check_n_were_seen_once(established_socks, established_socks_len, 1, + counts, counts_len); + + /* Close all remaining sockets to exhaust the list of saved cookies and + * exit without putting any sockets into the batch on the next read. + */ + close_idx = malloc(sizeof(int) * (established_socks_len - 1)); + if (!ASSERT_OK_PTR(close_idx, "close_idx malloc")) + return; + for (i = 0; i < established_socks_len - 1; i++) { + close_idx[i] = get_nth_socket(established_socks, + established_socks_len, link, + listen_socks_len + i); + if (!ASSERT_GE(close_idx[i], 0, "close_idx")) + return; + } + + for (i = 0; i < established_socks_len - 1; i++) { + destroy(established_socks[close_idx[i]]); + established_socks[close_idx[i]] = -1; + } + + /* Make sure there are no more sockets returned */ + ASSERT_EQ(read_n(iter_fd, -1, counts, counts_len), 0, "read_n"); + free(close_idx); +} + static void add_some(int family, int sock_type, const char *addr, __u16 port, - int *socks, int socks_len, struct sock_count *counts, + int *socks, int socks_len, int *established_socks, + int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { int *new_socks = NULL; @@ -271,8 +508,52 @@ done: free_fds(new_socks, socks_len); } +static void add_some_established(int family, int sock_type, const char *addr, + __u16 port, int *listen_socks, + int listen_socks_len, int *established_socks, + int established_socks_len, + struct sock_count *counts, + int counts_len, struct bpf_link *link, + int iter_fd) +{ + int *new_socks = NULL; + + /* Iterate through all listening sockets. */ + read_n(iter_fd, listen_socks_len, counts, counts_len); + + /* Make sure we saw all listening sockets exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + + /* Iterate through the first established_socks_len - 1 sockets. */ + read_n(iter_fd, established_socks_len - 1, counts, counts_len); + + /* Make sure we saw established_socks_len - 1 sockets exactly once. */ + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len - 1, counts, counts_len); + + /* Double the number of established sockets in the bucket. */ + new_socks = connect_to_server(family, sock_type, addr, port, + established_socks_len / 2, listen_socks, + listen_socks_len); + if (!ASSERT_OK_PTR(new_socks, "connect_to_server")) + goto done; + + /* Iterate through the rest of the sockets. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure each of the original sockets was seen exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len, counts, counts_len); +done: + free_fds(new_socks, established_socks_len); +} + static void force_realloc(int family, int sock_type, const char *addr, __u16 port, int *socks, int socks_len, + int *established_socks, int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { @@ -299,11 +580,32 @@ done: free_fds(new_socks, socks_len); } +static void force_realloc_established(int family, int sock_type, + const char *addr, __u16 port, + int *listen_socks, int listen_socks_len, + int *established_socks, + int established_socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + /* Iterate through all sockets to trigger a realloc. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure each socket was seen exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len, counts, counts_len); +} + struct test_case { void (*test)(int family, int sock_type, const char *addr, __u16 port, - int *socks, int socks_len, struct sock_count *counts, + int *socks, int socks_len, int *established_socks, + int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd); const char *description; + int ehash_buckets; + int connections; int init_socks; int max_socks; int sock_type; @@ -358,18 +660,140 @@ static struct test_case resume_tests[] = { .family = AF_INET6, .test = force_realloc, }, + { + .description = "tcp: resume after removing a seen socket (listening)", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_seen, + }, + { + .description = "tcp: resume after removing one unseen socket (listening)", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_unseen, + }, + { + .description = "tcp: resume after removing all unseen sockets (listening)", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_all, + }, + { + .description = "tcp: resume after adding a few sockets (listening)", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_STREAM, + /* Use AF_INET so that new sockets are added to the head of the + * bucket's list. + */ + .family = AF_INET, + .test = add_some, + }, + { + .description = "tcp: force a realloc to occur (listening)", + .init_socks = init_batch_size, + .max_socks = init_batch_size * 2, + .sock_type = SOCK_STREAM, + /* Use AF_INET6 so that new sockets are added to the tail of the + * bucket's list, needing to be added to the next batch to force + * a realloc. + */ + .family = AF_INET6, + .test = force_realloc, + }, + { + .description = "tcp: resume after removing a seen socket (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + .connections = nr_soreuse, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse * 3, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_seen_established, + }, + { + .description = "tcp: resume after removing one unseen socket (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + .connections = nr_soreuse, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse * 3, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_unseen_established, + }, + { + .description = "tcp: resume after removing all unseen sockets (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + .connections = nr_soreuse, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse * 3, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_all_established, + }, + { + .description = "tcp: resume after adding a few sockets (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + .connections = nr_soreuse, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse * 3, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = add_some_established, + }, + { + .description = "tcp: force a realloc to occur (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + /* Bucket size will need to double when going from listening to + * established sockets. + */ + .connections = init_batch_size, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse + (init_batch_size * 2), + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = force_realloc_established, + }, }; static void do_resume_test(struct test_case *tc) { struct sock_iter_batch *skel = NULL; + struct sock_count *counts = NULL; static const __u16 port = 10001; + struct nstoken *nstoken = NULL; struct bpf_link *link = NULL; - struct sock_count *counts; + int *established_fds = NULL; int err, iter_fd = -1; const char *addr; int *fds = NULL; - int local_port; + + if (tc->ehash_buckets) { + SYS_NOFAIL("ip netns del " TEST_CHILD_NS); + SYS(done, "sysctl -wq net.ipv4.tcp_child_ehash_entries=%d", + tc->ehash_buckets); + SYS(done, "ip netns add %s", TEST_CHILD_NS); + SYS(done, "ip -net %s link set dev lo up", TEST_CHILD_NS); + nstoken = open_netns(TEST_CHILD_NS); + if (!ASSERT_OK_PTR(nstoken, "open_child_netns")) + goto done; + } counts = calloc(tc->max_socks, sizeof(*counts)); if (!ASSERT_OK_PTR(counts, "counts")) @@ -384,11 +808,18 @@ static void do_resume_test(struct test_case *tc) tc->init_socks); if (!ASSERT_OK_PTR(fds, "start_reuseport_server")) goto done; - local_port = get_socket_local_port(*fds); - if (!ASSERT_GE(local_port, 0, "get_socket_local_port")) - goto done; - skel->rodata->ports[0] = ntohs(local_port); + if (tc->connections) { + established_fds = connect_to_server(tc->family, tc->sock_type, + addr, port, + tc->connections, fds, + tc->init_socks); + if (!ASSERT_OK_PTR(established_fds, "connect_to_server")) + goto done; + } + skel->rodata->ports[0] = 0; + skel->rodata->ports[1] = 0; skel->rodata->sf = tc->family; + skel->rodata->ss = 0; err = sock_iter_batch__load(skel); if (!ASSERT_OK(err, "sock_iter_batch__load")) @@ -406,10 +837,15 @@ static void do_resume_test(struct test_case *tc) goto done; tc->test(tc->family, tc->sock_type, addr, port, fds, tc->init_socks, - counts, tc->max_socks, link, iter_fd); + established_fds, tc->connections*2, counts, tc->max_socks, + link, iter_fd); done: + close_netns(nstoken); + SYS_NOFAIL("ip netns del " TEST_CHILD_NS); + SYS_NOFAIL("sysctl -w net.ipv4.tcp_child_ehash_entries=0"); free(counts); free_fds(fds, tc->init_socks); + free_fds(established_fds, tc->connections*2); if (iter_fd >= 0) close(iter_fd); bpf_link__destroy(link); @@ -454,6 +890,8 @@ static void do_test(int sock_type, bool onebyone) skel->rodata->ports[i] = ntohs(local_port); } skel->rodata->sf = AF_INET6; + if (sock_type == SOCK_STREAM) + skel->rodata->ss = TCP_LISTEN; err = sock_iter_batch__load(skel); if (!ASSERT_OK(err, "sock_iter_batch__load")) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c index b6c471da5c28..b87e7f39e15a 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c @@ -314,6 +314,95 @@ out: test_sockmap_ktls__destroy(skel); } +static void test_sockmap_ktls_tx_pop(int family, int sotype) +{ + char msg[37] = "0123456789abcdefghijklmnopqrstuvwxyz\0"; + int c = 0, p = 0, one = 1, sent, recvd; + struct test_sockmap_ktls *skel; + int prog_fd, map_fd; + char rcv[50] = {0}; + int err; + int i, m, r; + + skel = test_sockmap_ktls__open_and_load(); + if (!ASSERT_TRUE(skel, "open ktls skel")) + return; + + err = create_pair(family, sotype, &c, &p); + if (!ASSERT_OK(err, "create_pair()")) + goto out; + + prog_fd = bpf_program__fd(skel->progs.prog_sk_policy); + map_fd = bpf_map__fd(skel->maps.sock_map); + + err = bpf_prog_attach(prog_fd, map_fd, BPF_SK_MSG_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach sk msg")) + goto out; + + err = bpf_map_update_elem(map_fd, &one, &c, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(c)")) + goto out; + + err = init_ktls_pairs(c, p); + if (!ASSERT_OK(err, "init_ktls_pairs(c, p)")) + goto out; + + struct { + int pop_start; + int pop_len; + } pop_policy[] = { + /* trim the start */ + {0, 2}, + {0, 10}, + {1, 2}, + {1, 10}, + /* trim the end */ + {35, 2}, + /* New entries should be added before this line */ + {-1, -1}, + }; + + i = 0; + while (pop_policy[i].pop_start >= 0) { + skel->bss->pop_start = pop_policy[i].pop_start; + skel->bss->pop_end = pop_policy[i].pop_len; + + sent = send(c, msg, sizeof(msg), 0); + if (!ASSERT_EQ(sent, sizeof(msg), "send(msg)")) + goto out; + + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1); + if (!ASSERT_EQ(recvd, sizeof(msg) - pop_policy[i].pop_len, "pop len mismatch")) + goto out; + + /* verify the data + * msg: 0123456789a bcdefghij klmnopqrstuvwxyz + * | | + * popped data + */ + for (m = 0, r = 0; m < sizeof(msg);) { + /* skip checking the data that has been popped */ + if (m >= pop_policy[i].pop_start && + m <= pop_policy[i].pop_start + pop_policy[i].pop_len - 1) { + m++; + continue; + } + + if (!ASSERT_EQ(msg[m], rcv[r], "data mismatch")) + goto out; + m++; + r++; + } + i++; + } +out: + if (c) + close(c); + if (p) + close(p); + test_sockmap_ktls__destroy(skel); +} + static void run_tests(int family, enum bpf_map_type map_type) { int map; @@ -338,6 +427,8 @@ static void run_ktls_test(int family, int sotype) test_sockmap_ktls_tx_cork(family, sotype, true); if (test__start_subtest("tls tx egress with no buf")) test_sockmap_ktls_tx_no_buf(family, sotype, true); + if (test__start_subtest("tls tx with pop")) + test_sockmap_ktls_tx_pop(family, sotype); } void test_sockmap_ktls(void) diff --git a/tools/testing/selftests/bpf/progs/sock_iter_batch.c b/tools/testing/selftests/bpf/progs/sock_iter_batch.c index 8f483337e103..77966ded5467 100644 --- a/tools/testing/selftests/bpf/progs/sock_iter_batch.c +++ b/tools/testing/selftests/bpf/progs/sock_iter_batch.c @@ -23,6 +23,7 @@ static bool ipv4_addr_loopback(__be32 a) } volatile const unsigned int sf; +volatile const unsigned int ss; volatile const __u16 ports[2]; unsigned int bucket[2]; @@ -42,16 +43,18 @@ int iter_tcp_soreuse(struct bpf_iter__tcp *ctx) sock_cookie = bpf_get_socket_cookie(sk); sk = bpf_core_cast(sk, struct sock); if (sk->sk_family != sf || - sk->sk_state != TCP_LISTEN || - sk->sk_family == AF_INET6 ? + (ss && sk->sk_state != ss) || + (sk->sk_family == AF_INET6 ? !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr) : - !ipv4_addr_loopback(sk->sk_rcv_saddr)) + !ipv4_addr_loopback(sk->sk_rcv_saddr))) return 0; if (sk->sk_num == ports[0]) idx = 0; else if (sk->sk_num == ports[1]) idx = 1; + else if (!ports[0] && !ports[1]) + idx = 0; else return 0; @@ -67,6 +70,27 @@ int iter_tcp_soreuse(struct bpf_iter__tcp *ctx) return 0; } +volatile const __u64 destroy_cookie; + +SEC("iter/tcp") +int iter_tcp_destroy(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = (struct sock_common *)ctx->sk_common; + __u64 sock_cookie; + + if (!sk_common) + return 0; + + sock_cookie = bpf_get_socket_cookie(sk_common); + if (sock_cookie != destroy_cookie) + return 0; + + bpf_sock_destroy(sk_common); + bpf_seq_write(ctx->meta->seq, &sock_cookie, sizeof(sock_cookie)); + + return 0; +} + #define udp_sk(ptr) container_of(ptr, struct udp_sock, inet.sk) SEC("iter/udp") @@ -83,15 +107,17 @@ int iter_udp_soreuse(struct bpf_iter__udp *ctx) sock_cookie = bpf_get_socket_cookie(sk); sk = bpf_core_cast(sk, struct sock); if (sk->sk_family != sf || - sk->sk_family == AF_INET6 ? + (sk->sk_family == AF_INET6 ? !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr) : - !ipv4_addr_loopback(sk->sk_rcv_saddr)) + !ipv4_addr_loopback(sk->sk_rcv_saddr))) return 0; if (sk->sk_num == ports[0]) idx = 0; else if (sk->sk_num == ports[1]) idx = 1; + else if (!ports[0] && !ports[1]) + idx = 0; else return 0; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c b/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c index 8bdb9987c0c7..83df4919c224 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c @@ -7,6 +7,8 @@ int cork_byte; int push_start; int push_end; int apply_bytes; +int pop_start; +int pop_end; struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); @@ -22,6 +24,8 @@ int prog_sk_policy(struct sk_msg_md *msg) bpf_msg_cork_bytes(msg, cork_byte); if (push_start > 0 && push_end > 0) bpf_msg_push_data(msg, push_start, push_end, 0); + if (pop_start >= 0 && pop_end > 0) + bpf_msg_pop_data(msg, pop_start, pop_end, 0); return SK_PASS; } diff --git a/tools/testing/selftests/bpf/progs/verifier_ctx.c b/tools/testing/selftests/bpf/progs/verifier_ctx.c index a83809a1dbbf..0450840c92d9 100644 --- a/tools/testing/selftests/bpf/progs/verifier_ctx.c +++ b/tools/testing/selftests/bpf/progs/verifier_ctx.c @@ -218,4 +218,29 @@ __naked void null_check_8_null_bind(void) : __clobber_all); } +#define narrow_load(type, ctx, field) \ + SEC(type) \ + __description("narrow load on field " #field " of " #ctx) \ + __failure __msg("invalid bpf_context access") \ + __naked void invalid_narrow_load##ctx##field(void) \ + { \ + asm volatile (" \ + r1 = *(u32 *)(r1 + %[off]); \ + r0 = 0; \ + exit;" \ + : \ + : __imm_const(off, offsetof(struct ctx, field) + 4) \ + : __clobber_all); \ + } + +narrow_load("cgroup/getsockopt", bpf_sockopt, sk); +narrow_load("cgroup/getsockopt", bpf_sockopt, optval); +narrow_load("cgroup/getsockopt", bpf_sockopt, optval_end); +narrow_load("tc", __sk_buff, sk); +narrow_load("cgroup/bind4", bpf_sock_addr, sk); +narrow_load("sockops", bpf_sock_ops, sk); +narrow_load("sockops", bpf_sock_ops, skb_data); +narrow_load("sockops", bpf_sock_ops, skb_data_end); +narrow_load("sockops", bpf_sock_ops, skb_hwtstamp); + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c index 0ced4026ee44..a29de0713f19 100644 --- a/tools/testing/selftests/bpf/xskxceiver.c +++ b/tools/testing/selftests/bpf/xskxceiver.c @@ -109,6 +109,8 @@ #include <network_helpers.h> +#define MAX_TX_BUDGET_DEFAULT 32 + static bool opt_verbose; static bool opt_print_tests; static enum test_mode opt_mode = TEST_MODE_ALL; @@ -1091,11 +1093,45 @@ static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) return true; } +static u32 load_value(u32 *counter) +{ + return __atomic_load_n(counter, __ATOMIC_ACQUIRE); +} + +static bool kick_tx_with_check(struct xsk_socket_info *xsk, int *ret) +{ + u32 max_budget = MAX_TX_BUDGET_DEFAULT; + u32 cons, ready_to_send; + int delta; + + cons = load_value(xsk->tx.consumer); + ready_to_send = load_value(xsk->tx.producer) - cons; + *ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + + delta = load_value(xsk->tx.consumer) - cons; + /* By default, xsk should consume exact @max_budget descs at one + * send in this case where hitting the max budget limit in while + * loop is triggered in __xsk_generic_xmit(). Please make sure that + * the number of descs to be sent is larger than @max_budget, or + * else the tx.consumer will be updated in xskq_cons_peek_desc() + * in time which hides the issue we try to verify. + */ + if (ready_to_send > max_budget && delta != max_budget) + return false; + + return true; +} + static int kick_tx(struct xsk_socket_info *xsk) { int ret; - ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + if (xsk->check_consumer) { + if (!kick_tx_with_check(xsk, &ret)) + return TEST_FAILURE; + } else { + ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + } if (ret >= 0) return TEST_PASS; if (errno == ENOBUFS || errno == EAGAIN || errno == EBUSY || errno == ENETDOWN) { @@ -2613,6 +2649,23 @@ static int testapp_adjust_tail_grow_mb(struct test_spec *test) XSK_UMEM__LARGE_FRAME_SIZE * 2); } +static int testapp_tx_queue_consumer(struct test_spec *test) +{ + int nr_packets; + + if (test->mode == TEST_MODE_ZC) { + ksft_test_result_skip("Can not run TX_QUEUE_CONSUMER test for ZC mode\n"); + return TEST_SKIP; + } + + nr_packets = MAX_TX_BUDGET_DEFAULT + 1; + pkt_stream_replace(test, nr_packets, MIN_PKT_SIZE); + test->ifobj_tx->xsk->batch_size = nr_packets; + test->ifobj_tx->xsk->check_consumer = true; + + return testapp_validate_traffic(test); +} + static void run_pkt_test(struct test_spec *test) { int ret; @@ -2723,6 +2776,7 @@ static const struct test_spec tests[] = { {.name = "XDP_ADJUST_TAIL_SHRINK_MULTI_BUFF", .test_func = testapp_adjust_tail_shrink_mb}, {.name = "XDP_ADJUST_TAIL_GROW", .test_func = testapp_adjust_tail_grow}, {.name = "XDP_ADJUST_TAIL_GROW_MULTI_BUFF", .test_func = testapp_adjust_tail_grow_mb}, + {.name = "TX_QUEUE_CONSUMER", .test_func = testapp_tx_queue_consumer}, }; static void print_tests(void) diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h index 67fc44b2813b..4df3a5d329ac 100644 --- a/tools/testing/selftests/bpf/xskxceiver.h +++ b/tools/testing/selftests/bpf/xskxceiver.h @@ -95,6 +95,7 @@ struct xsk_socket_info { u32 batch_size; u8 dst_mac[ETH_ALEN]; u8 src_mac[ETH_ALEN]; + bool check_consumer; }; struct pkt { diff --git a/tools/testing/selftests/breakpoints/step_after_suspend_test.c b/tools/testing/selftests/breakpoints/step_after_suspend_test.c index 8d275f03e977..8d233ac95696 100644 --- a/tools/testing/selftests/breakpoints/step_after_suspend_test.c +++ b/tools/testing/selftests/breakpoints/step_after_suspend_test.c @@ -127,22 +127,42 @@ int run_test(int cpu) return KSFT_PASS; } +/* + * Reads the suspend success count from sysfs. + * Returns the count on success or exits on failure. + */ +static int get_suspend_success_count_or_fail(void) +{ + FILE *fp; + int val; + + fp = fopen("/sys/power/suspend_stats/success", "r"); + if (!fp) + ksft_exit_fail_msg( + "Failed to open suspend_stats/success: %s\n", + strerror(errno)); + + if (fscanf(fp, "%d", &val) != 1) { + fclose(fp); + ksft_exit_fail_msg( + "Failed to read suspend success count\n"); + } + + fclose(fp); + return val; +} + void suspend(void) { - int power_state_fd; int timerfd; int err; + int count_before; + int count_after; struct itimerspec spec = {}; if (getuid() != 0) ksft_exit_skip("Please run the test as root - Exiting.\n"); - power_state_fd = open("/sys/power/state", O_RDWR); - if (power_state_fd < 0) - ksft_exit_fail_msg( - "open(\"/sys/power/state\") failed %s)\n", - strerror(errno)); - timerfd = timerfd_create(CLOCK_BOOTTIME_ALARM, 0); if (timerfd < 0) ksft_exit_fail_msg("timerfd_create() failed\n"); @@ -152,14 +172,15 @@ void suspend(void) if (err < 0) ksft_exit_fail_msg("timerfd_settime() failed\n"); + count_before = get_suspend_success_count_or_fail(); + system("(echo mem > /sys/power/state) 2> /dev/null"); - timerfd_gettime(timerfd, &spec); - if (spec.it_value.tv_sec != 0 || spec.it_value.tv_nsec != 0) + count_after = get_suspend_success_count_or_fail(); + if (count_after <= count_before) ksft_exit_fail_msg("Failed to enter Suspend state\n"); close(timerfd); - close(power_state_fd); } int main(int argc, char **argv) diff --git a/tools/testing/selftests/coredump/Makefile b/tools/testing/selftests/coredump/Makefile index ed210037b29d..77b3665c73c7 100644 --- a/tools/testing/selftests/coredump/Makefile +++ b/tools/testing/selftests/coredump/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -CFLAGS = $(KHDR_INCLUDES) +CFLAGS += -Wall -O0 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES) TEST_GEN_PROGS := stackdump_test TEST_FILES := stackdump diff --git a/tools/testing/selftests/coredump/config b/tools/testing/selftests/coredump/config new file mode 100644 index 000000000000..a05ef112b4f9 --- /dev/null +++ b/tools/testing/selftests/coredump/config @@ -0,0 +1,3 @@ +CONFIG_COREDUMP=y +CONFIG_NET=y +CONFIG_UNIX=y diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c index 68f8e479ac36..5a5a7a5f7e1d 100644 --- a/tools/testing/selftests/coredump/stackdump_test.c +++ b/tools/testing/selftests/coredump/stackdump_test.c @@ -1,12 +1,18 @@ // SPDX-License-Identifier: GPL-2.0 +#include <assert.h> #include <fcntl.h> #include <inttypes.h> #include <libgen.h> +#include <limits.h> +#include <linux/coredump.h> +#include <linux/fs.h> #include <linux/limits.h> #include <pthread.h> #include <string.h> #include <sys/mount.h> +#include <poll.h> +#include <sys/epoll.h> #include <sys/resource.h> #include <sys/stat.h> #include <sys/socket.h> @@ -14,16 +20,23 @@ #include <unistd.h> #include "../kselftest_harness.h" +#include "../filesystems/wrappers.h" #include "../pidfd/pidfd.h" #define STACKDUMP_FILE "stack_values" #define STACKDUMP_SCRIPT "stackdump" #define NUM_THREAD_SPAWN 128 +#ifndef PAGE_SIZE +#define PAGE_SIZE 4096 +#endif + static void *do_nothing(void *) { while (1) pause(); + + return NULL; } static void crashing_child(void) @@ -42,16 +55,32 @@ FIXTURE(coredump) { char original_core_pattern[256]; pid_t pid_coredump_server; + int fd_tmpfs_detached; }; +static int create_detached_tmpfs(void) +{ + int fd_context, fd_tmpfs; + + fd_context = sys_fsopen("tmpfs", 0); + if (fd_context < 0) + return -1; + + if (sys_fsconfig(fd_context, FSCONFIG_CMD_CREATE, NULL, NULL, 0) < 0) + return -1; + + fd_tmpfs = sys_fsmount(fd_context, 0, 0); + close(fd_context); + return fd_tmpfs; +} + FIXTURE_SETUP(coredump) { - char buf[PATH_MAX]; FILE *file; - char *dir; int ret; self->pid_coredump_server = -ESRCH; + self->fd_tmpfs_detached = -1; file = fopen("/proc/sys/kernel/core_pattern", "r"); ASSERT_NE(NULL, file); @@ -60,6 +89,8 @@ FIXTURE_SETUP(coredump) ASSERT_LT(ret, sizeof(self->original_core_pattern)); self->original_core_pattern[ret] = '\0'; + self->fd_tmpfs_detached = create_detached_tmpfs(); + ASSERT_GE(self->fd_tmpfs_detached, 0); ret = fclose(file); ASSERT_EQ(0, ret); @@ -98,6 +129,15 @@ FIXTURE_TEARDOWN(coredump) goto fail; } + if (self->fd_tmpfs_detached >= 0) { + ret = close(self->fd_tmpfs_detached); + if (ret < 0) { + reason = "Unable to close detached tmpfs"; + goto fail; + } + self->fd_tmpfs_detached = -1; + } + return; fail: /* This should never happen */ @@ -106,11 +146,10 @@ fail: TEST_F_TIMEOUT(coredump, stackdump, 120) { - struct sigaction action = {}; unsigned long long stack; char *test_dir, *line; size_t line_length; - char buf[PATH_MAX]; + char buf[PAGE_SIZE]; int ret, i, status; FILE *file; pid_t pid; @@ -169,153 +208,166 @@ TEST_F_TIMEOUT(coredump, stackdump, 120) fclose(file); } +static int create_and_listen_unix_socket(const char *path) +{ + struct sockaddr_un addr = { + .sun_family = AF_UNIX, + }; + assert(strlen(path) < sizeof(addr.sun_path) - 1); + strncpy(addr.sun_path, path, sizeof(addr.sun_path) - 1); + size_t addr_len = + offsetof(struct sockaddr_un, sun_path) + strlen(path) + 1; + int fd, ret; + + fd = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0); + if (fd < 0) + goto out; + + ret = bind(fd, (const struct sockaddr *)&addr, addr_len); + if (ret < 0) + goto out; + + ret = listen(fd, 128); + if (ret < 0) + goto out; + + return fd; + +out: + if (fd >= 0) + close(fd); + return -1; +} + +static bool set_core_pattern(const char *pattern) +{ + int fd; + ssize_t ret; + + fd = open("/proc/sys/kernel/core_pattern", O_WRONLY | O_CLOEXEC); + if (fd < 0) + return false; + + ret = write(fd, pattern, strlen(pattern)); + close(fd); + if (ret < 0) + return false; + + fprintf(stderr, "Set core_pattern to '%s' | %zu == %zu\n", pattern, ret, strlen(pattern)); + return ret == strlen(pattern); +} + +static int get_peer_pidfd(int fd) +{ + int fd_peer_pidfd; + socklen_t fd_peer_pidfd_len = sizeof(fd_peer_pidfd); + int ret = getsockopt(fd, SOL_SOCKET, SO_PEERPIDFD, &fd_peer_pidfd, + &fd_peer_pidfd_len); + if (ret < 0) { + fprintf(stderr, "%m - Failed to retrieve peer pidfd for coredump socket connection\n"); + return -1; + } + return fd_peer_pidfd; +} + +static bool get_pidfd_info(int fd_peer_pidfd, struct pidfd_info *info) +{ + memset(info, 0, sizeof(*info)); + info->mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP; + return ioctl(fd_peer_pidfd, PIDFD_GET_INFO, info) == 0; +} + +static void +wait_and_check_coredump_server(pid_t pid_coredump_server, + struct __test_metadata *const _metadata, + FIXTURE_DATA(coredump)* self) +{ + int status; + waitpid(pid_coredump_server, &status, 0); + self->pid_coredump_server = -ESRCH; + ASSERT_TRUE(WIFEXITED(status)); + ASSERT_EQ(WEXITSTATUS(status), 0); +} + TEST_F(coredump, socket) { - int fd, pidfd, ret, status; - FILE *file; + int pidfd, ret, status; pid_t pid, pid_coredump_server; struct stat st; - char core_file[PATH_MAX]; struct pidfd_info info = {}; int ipc_sockets[2]; char c; - const struct sockaddr_un coredump_sk = { - .sun_family = AF_UNIX, - .sun_path = "/tmp/coredump.socket", - }; - size_t coredump_sk_len = offsetof(struct sockaddr_un, sun_path) + - sizeof("/tmp/coredump.socket"); + + ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket")); ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); ASSERT_EQ(ret, 0); - file = fopen("/proc/sys/kernel/core_pattern", "w"); - ASSERT_NE(file, NULL); - - ret = fprintf(file, "@/tmp/coredump.socket"); - ASSERT_EQ(ret, strlen("@/tmp/coredump.socket")); - ASSERT_EQ(fclose(file), 0); - pid_coredump_server = fork(); ASSERT_GE(pid_coredump_server, 0); if (pid_coredump_server == 0) { - int fd_server, fd_coredump, fd_peer_pidfd, fd_core_file; - socklen_t fd_peer_pidfd_len; + int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1; + int exit_code = EXIT_FAILURE; close(ipc_sockets[0]); - fd_server = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0); + fd_server = create_and_listen_unix_socket("/tmp/coredump.socket"); if (fd_server < 0) - _exit(EXIT_FAILURE); - - ret = bind(fd_server, (const struct sockaddr *)&coredump_sk, coredump_sk_len); - if (ret < 0) { - fprintf(stderr, "Failed to bind coredump socket\n"); - close(fd_server); - close(ipc_sockets[1]); - _exit(EXIT_FAILURE); - } - - ret = listen(fd_server, 1); - if (ret < 0) { - fprintf(stderr, "Failed to listen on coredump socket\n"); - close(fd_server); - close(ipc_sockets[1]); - _exit(EXIT_FAILURE); - } + goto out; - if (write_nointr(ipc_sockets[1], "1", 1) < 0) { - close(fd_server); - close(ipc_sockets[1]); - _exit(EXIT_FAILURE); - } + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + goto out; close(ipc_sockets[1]); fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC); - if (fd_coredump < 0) { - fprintf(stderr, "Failed to accept coredump socket connection\n"); - close(fd_server); - _exit(EXIT_FAILURE); - } + if (fd_coredump < 0) + goto out; - fd_peer_pidfd_len = sizeof(fd_peer_pidfd); - ret = getsockopt(fd_coredump, SOL_SOCKET, SO_PEERPIDFD, - &fd_peer_pidfd, &fd_peer_pidfd_len); - if (ret < 0) { - fprintf(stderr, "%m - Failed to retrieve peer pidfd for coredump socket connection\n"); - close(fd_coredump); - close(fd_server); - _exit(EXIT_FAILURE); - } + fd_peer_pidfd = get_peer_pidfd(fd_coredump); + if (fd_peer_pidfd < 0) + goto out; - memset(&info, 0, sizeof(info)); - info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP; - ret = ioctl(fd_peer_pidfd, PIDFD_GET_INFO, &info); - if (ret < 0) { - fprintf(stderr, "Failed to retrieve pidfd info from peer pidfd for coredump socket connection\n"); - close(fd_coredump); - close(fd_server); - close(fd_peer_pidfd); - _exit(EXIT_FAILURE); - } + if (!get_pidfd_info(fd_peer_pidfd, &info)) + goto out; - if (!(info.mask & PIDFD_INFO_COREDUMP)) { - fprintf(stderr, "Missing coredump information from coredumping task\n"); - close(fd_coredump); - close(fd_server); - close(fd_peer_pidfd); - _exit(EXIT_FAILURE); - } + if (!(info.mask & PIDFD_INFO_COREDUMP)) + goto out; - if (!(info.coredump_mask & PIDFD_COREDUMPED)) { - fprintf(stderr, "Received connection from non-coredumping task\n"); - close(fd_coredump); - close(fd_server); - close(fd_peer_pidfd); - _exit(EXIT_FAILURE); - } + if (!(info.coredump_mask & PIDFD_COREDUMPED)) + goto out; fd_core_file = creat("/tmp/coredump.file", 0644); - if (fd_core_file < 0) { - fprintf(stderr, "Failed to create coredump file\n"); - close(fd_coredump); - close(fd_server); - close(fd_peer_pidfd); - _exit(EXIT_FAILURE); - } + if (fd_core_file < 0) + goto out; for (;;) { char buffer[4096]; ssize_t bytes_read, bytes_write; bytes_read = read(fd_coredump, buffer, sizeof(buffer)); - if (bytes_read < 0) { - close(fd_coredump); - close(fd_server); - close(fd_peer_pidfd); - close(fd_core_file); - _exit(EXIT_FAILURE); - } + if (bytes_read < 0) + goto out; if (bytes_read == 0) break; bytes_write = write(fd_core_file, buffer, bytes_read); - if (bytes_read != bytes_write) { - close(fd_coredump); - close(fd_server); - close(fd_peer_pidfd); - close(fd_core_file); - _exit(EXIT_FAILURE); - } + if (bytes_read != bytes_write) + goto out; } - close(fd_coredump); - close(fd_server); - close(fd_peer_pidfd); - close(fd_core_file); - _exit(EXIT_SUCCESS); + exit_code = EXIT_SUCCESS; +out: + if (fd_core_file >= 0) + close(fd_core_file); + if (fd_peer_pidfd >= 0) + close(fd_peer_pidfd); + if (fd_coredump >= 0) + close(fd_coredump); + if (fd_server >= 0) + close(fd_server); + _exit(exit_code); } self->pid_coredump_server = pid_coredump_server; @@ -335,48 +387,27 @@ TEST_F(coredump, socket) ASSERT_TRUE(WIFSIGNALED(status)); ASSERT_TRUE(WCOREDUMP(status)); - info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP; - ASSERT_EQ(ioctl(pidfd, PIDFD_GET_INFO, &info), 0); + ASSERT_TRUE(get_pidfd_info(pidfd, &info)); ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0); ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0); - waitpid(pid_coredump_server, &status, 0); - self->pid_coredump_server = -ESRCH; - ASSERT_TRUE(WIFEXITED(status)); - ASSERT_EQ(WEXITSTATUS(status), 0); + wait_and_check_coredump_server(pid_coredump_server, _metadata, self); ASSERT_EQ(stat("/tmp/coredump.file", &st), 0); ASSERT_GT(st.st_size, 0); - /* - * We should somehow validate the produced core file. - * For now just allow for visual inspection - */ system("file /tmp/coredump.file"); } TEST_F(coredump, socket_detect_userspace_client) { - int fd, pidfd, ret, status; - FILE *file; + int pidfd, ret, status; pid_t pid, pid_coredump_server; struct stat st; - char core_file[PATH_MAX]; struct pidfd_info info = {}; int ipc_sockets[2]; char c; - const struct sockaddr_un coredump_sk = { - .sun_family = AF_UNIX, - .sun_path = "/tmp/coredump.socket", - }; - size_t coredump_sk_len = offsetof(struct sockaddr_un, sun_path) + - sizeof("/tmp/coredump.socket"); - - file = fopen("/proc/sys/kernel/core_pattern", "w"); - ASSERT_NE(file, NULL); - ret = fprintf(file, "@/tmp/coredump.socket"); - ASSERT_EQ(ret, strlen("@/tmp/coredump.socket")); - ASSERT_EQ(fclose(file), 0); + ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket")); ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); ASSERT_EQ(ret, 0); @@ -384,93 +415,49 @@ TEST_F(coredump, socket_detect_userspace_client) pid_coredump_server = fork(); ASSERT_GE(pid_coredump_server, 0); if (pid_coredump_server == 0) { - int fd_server, fd_coredump, fd_peer_pidfd, fd_core_file; - socklen_t fd_peer_pidfd_len; + int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1; + int exit_code = EXIT_FAILURE; close(ipc_sockets[0]); - fd_server = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0); + fd_server = create_and_listen_unix_socket("/tmp/coredump.socket"); if (fd_server < 0) - _exit(EXIT_FAILURE); - - ret = bind(fd_server, (const struct sockaddr *)&coredump_sk, coredump_sk_len); - if (ret < 0) { - fprintf(stderr, "Failed to bind coredump socket\n"); - close(fd_server); - close(ipc_sockets[1]); - _exit(EXIT_FAILURE); - } + goto out; - ret = listen(fd_server, 1); - if (ret < 0) { - fprintf(stderr, "Failed to listen on coredump socket\n"); - close(fd_server); - close(ipc_sockets[1]); - _exit(EXIT_FAILURE); - } - - if (write_nointr(ipc_sockets[1], "1", 1) < 0) { - close(fd_server); - close(ipc_sockets[1]); - _exit(EXIT_FAILURE); - } + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + goto out; close(ipc_sockets[1]); fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC); - if (fd_coredump < 0) { - fprintf(stderr, "Failed to accept coredump socket connection\n"); - close(fd_server); - _exit(EXIT_FAILURE); - } - - fd_peer_pidfd_len = sizeof(fd_peer_pidfd); - ret = getsockopt(fd_coredump, SOL_SOCKET, SO_PEERPIDFD, - &fd_peer_pidfd, &fd_peer_pidfd_len); - if (ret < 0) { - fprintf(stderr, "%m - Failed to retrieve peer pidfd for coredump socket connection\n"); - close(fd_coredump); - close(fd_server); - _exit(EXIT_FAILURE); - } + if (fd_coredump < 0) + goto out; - memset(&info, 0, sizeof(info)); - info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP; - ret = ioctl(fd_peer_pidfd, PIDFD_GET_INFO, &info); - if (ret < 0) { - fprintf(stderr, "Failed to retrieve pidfd info from peer pidfd for coredump socket connection\n"); - close(fd_coredump); - close(fd_server); - close(fd_peer_pidfd); - _exit(EXIT_FAILURE); - } + fd_peer_pidfd = get_peer_pidfd(fd_coredump); + if (fd_peer_pidfd < 0) + goto out; - if (!(info.mask & PIDFD_INFO_COREDUMP)) { - fprintf(stderr, "Missing coredump information from coredumping task\n"); - close(fd_coredump); - close(fd_server); - close(fd_peer_pidfd); - _exit(EXIT_FAILURE); - } + if (!get_pidfd_info(fd_peer_pidfd, &info)) + goto out; - if (info.coredump_mask & PIDFD_COREDUMPED) { - fprintf(stderr, "Received unexpected connection from coredumping task\n"); - close(fd_coredump); - close(fd_server); - close(fd_peer_pidfd); - _exit(EXIT_FAILURE); - } + if (!(info.mask & PIDFD_INFO_COREDUMP)) + goto out; - ret = read(fd_coredump, &c, 1); + if (info.coredump_mask & PIDFD_COREDUMPED) + goto out; - close(fd_coredump); - close(fd_server); - close(fd_peer_pidfd); - close(fd_core_file); + if (read(fd_coredump, &c, 1) < 1) + goto out; - if (ret < 1) - _exit(EXIT_FAILURE); - _exit(EXIT_SUCCESS); + exit_code = EXIT_SUCCESS; +out: + if (fd_peer_pidfd >= 0) + close(fd_peer_pidfd); + if (fd_coredump >= 0) + close(fd_coredump); + if (fd_server >= 0) + close(fd_server); + _exit(exit_code); } self->pid_coredump_server = pid_coredump_server; @@ -483,17 +470,22 @@ TEST_F(coredump, socket_detect_userspace_client) if (pid == 0) { int fd_socket; ssize_t ret; + const struct sockaddr_un coredump_sk = { + .sun_family = AF_UNIX, + .sun_path = "/tmp/coredump.socket", + }; + size_t coredump_sk_len = + offsetof(struct sockaddr_un, sun_path) + + sizeof("/tmp/coredump.socket"); fd_socket = socket(AF_UNIX, SOCK_STREAM, 0); if (fd_socket < 0) _exit(EXIT_FAILURE); - ret = connect(fd_socket, (const struct sockaddr *)&coredump_sk, coredump_sk_len); if (ret < 0) _exit(EXIT_FAILURE); - (void *)write(fd_socket, &(char){ 0 }, 1); close(fd_socket); _exit(EXIT_SUCCESS); } @@ -505,15 +497,11 @@ TEST_F(coredump, socket_detect_userspace_client) ASSERT_TRUE(WIFEXITED(status)); ASSERT_EQ(WEXITSTATUS(status), 0); - info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP; - ASSERT_EQ(ioctl(pidfd, PIDFD_GET_INFO, &info), 0); + ASSERT_TRUE(get_pidfd_info(pidfd, &info)); ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0); ASSERT_EQ((info.coredump_mask & PIDFD_COREDUMPED), 0); - waitpid(pid_coredump_server, &status, 0); - self->pid_coredump_server = -ESRCH; - ASSERT_TRUE(WIFEXITED(status)); - ASSERT_EQ(WEXITSTATUS(status), 0); + wait_and_check_coredump_server(pid_coredump_server, _metadata, self); ASSERT_NE(stat("/tmp/coredump.file", &st), 0); ASSERT_EQ(errno, ENOENT); @@ -521,17 +509,10 @@ TEST_F(coredump, socket_detect_userspace_client) TEST_F(coredump, socket_enoent) { - int pidfd, ret, status; - FILE *file; + int pidfd, status; pid_t pid; - char core_file[PATH_MAX]; - file = fopen("/proc/sys/kernel/core_pattern", "w"); - ASSERT_NE(file, NULL); - - ret = fprintf(file, "@/tmp/coredump.socket"); - ASSERT_EQ(ret, strlen("@/tmp/coredump.socket")); - ASSERT_EQ(fclose(file), 0); + ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket")); pid = fork(); ASSERT_GE(pid, 0); @@ -549,7 +530,6 @@ TEST_F(coredump, socket_enoent) TEST_F(coredump, socket_no_listener) { int pidfd, ret, status; - FILE *file; pid_t pid, pid_coredump_server; int ipc_sockets[2]; char c; @@ -560,45 +540,616 @@ TEST_F(coredump, socket_no_listener) size_t coredump_sk_len = offsetof(struct sockaddr_un, sun_path) + sizeof("/tmp/coredump.socket"); + ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket")); + ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); ASSERT_EQ(ret, 0); - file = fopen("/proc/sys/kernel/core_pattern", "w"); - ASSERT_NE(file, NULL); - - ret = fprintf(file, "@/tmp/coredump.socket"); - ASSERT_EQ(ret, strlen("@/tmp/coredump.socket")); - ASSERT_EQ(fclose(file), 0); - pid_coredump_server = fork(); ASSERT_GE(pid_coredump_server, 0); if (pid_coredump_server == 0) { - int fd_server; - socklen_t fd_peer_pidfd_len; + int fd_server = -1; + int exit_code = EXIT_FAILURE; close(ipc_sockets[0]); fd_server = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0); if (fd_server < 0) - _exit(EXIT_FAILURE); + goto out; ret = bind(fd_server, (const struct sockaddr *)&coredump_sk, coredump_sk_len); - if (ret < 0) { - fprintf(stderr, "Failed to bind coredump socket\n"); + if (ret < 0) + goto out; + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + goto out; + + exit_code = EXIT_SUCCESS; +out: + if (fd_server >= 0) close(fd_server); - close(ipc_sockets[1]); - _exit(EXIT_FAILURE); + close(ipc_sockets[1]); + _exit(exit_code); + } + self->pid_coredump_server = pid_coredump_server; + + EXPECT_EQ(close(ipc_sockets[1]), 0); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + EXPECT_EQ(close(ipc_sockets[0]), 0); + + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) + crashing_child(); + + pidfd = sys_pidfd_open(pid, 0); + ASSERT_GE(pidfd, 0); + + waitpid(pid, &status, 0); + ASSERT_TRUE(WIFSIGNALED(status)); + ASSERT_FALSE(WCOREDUMP(status)); + + wait_and_check_coredump_server(pid_coredump_server, _metadata, self); +} + +static ssize_t recv_marker(int fd) +{ + enum coredump_mark mark = COREDUMP_MARK_REQACK; + ssize_t ret; + + ret = recv(fd, &mark, sizeof(mark), MSG_WAITALL); + if (ret != sizeof(mark)) + return -1; + + switch (mark) { + case COREDUMP_MARK_REQACK: + fprintf(stderr, "Received marker: ReqAck\n"); + return COREDUMP_MARK_REQACK; + case COREDUMP_MARK_MINSIZE: + fprintf(stderr, "Received marker: MinSize\n"); + return COREDUMP_MARK_MINSIZE; + case COREDUMP_MARK_MAXSIZE: + fprintf(stderr, "Received marker: MaxSize\n"); + return COREDUMP_MARK_MAXSIZE; + case COREDUMP_MARK_UNSUPPORTED: + fprintf(stderr, "Received marker: Unsupported\n"); + return COREDUMP_MARK_UNSUPPORTED; + case COREDUMP_MARK_CONFLICTING: + fprintf(stderr, "Received marker: Conflicting\n"); + return COREDUMP_MARK_CONFLICTING; + default: + fprintf(stderr, "Received unknown marker: %u\n", mark); + break; + } + return -1; +} + +static bool read_marker(int fd, enum coredump_mark mark) +{ + ssize_t ret; + + ret = recv_marker(fd); + if (ret < 0) + return false; + return ret == mark; +} + +static bool read_coredump_req(int fd, struct coredump_req *req) +{ + ssize_t ret; + size_t field_size, user_size, ack_size, kernel_size, remaining_size; + + memset(req, 0, sizeof(*req)); + field_size = sizeof(req->size); + + /* Peek the size of the coredump request. */ + ret = recv(fd, req, field_size, MSG_PEEK | MSG_WAITALL); + if (ret != field_size) + return false; + kernel_size = req->size; + + if (kernel_size < COREDUMP_ACK_SIZE_VER0) + return false; + if (kernel_size >= PAGE_SIZE) + return false; + + /* Use the minimum of user and kernel size to read the full request. */ + user_size = sizeof(struct coredump_req); + ack_size = user_size < kernel_size ? user_size : kernel_size; + ret = recv(fd, req, ack_size, MSG_WAITALL); + if (ret != ack_size) + return false; + + fprintf(stderr, "Read coredump request with size %u and mask 0x%llx\n", + req->size, (unsigned long long)req->mask); + + if (user_size > kernel_size) + remaining_size = user_size - kernel_size; + else + remaining_size = kernel_size - user_size; + + if (PAGE_SIZE <= remaining_size) + return false; + + /* + * Discard any additional data if the kernel's request was larger than + * what we knew about or cared about. + */ + if (remaining_size) { + char buffer[PAGE_SIZE]; + + ret = recv(fd, buffer, sizeof(buffer), MSG_WAITALL); + if (ret != remaining_size) + return false; + fprintf(stderr, "Discarded %zu bytes of data after coredump request\n", remaining_size); + } + + return true; +} + +static bool send_coredump_ack(int fd, const struct coredump_req *req, + __u64 mask, size_t size_ack) +{ + ssize_t ret; + /* + * Wrap struct coredump_ack in a larger struct so we can + * simulate sending to much data to the kernel. + */ + struct large_ack_for_size_testing { + struct coredump_ack ack; + char buffer[PAGE_SIZE]; + } large_ack = {}; + + if (!size_ack) + size_ack = sizeof(struct coredump_ack) < req->size_ack ? + sizeof(struct coredump_ack) : + req->size_ack; + large_ack.ack.mask = mask; + large_ack.ack.size = size_ack; + ret = send(fd, &large_ack, size_ack, MSG_NOSIGNAL); + if (ret != size_ack) + return false; + + fprintf(stderr, "Sent coredump ack with size %zu and mask 0x%llx\n", + size_ack, (unsigned long long)mask); + return true; +} + +static bool check_coredump_req(const struct coredump_req *req, size_t min_size, + __u64 required_mask) +{ + if (req->size < min_size) + return false; + if ((req->mask & required_mask) != required_mask) + return false; + if (req->mask & ~required_mask) + return false; + return true; +} + +TEST_F(coredump, socket_request_kernel) +{ + int pidfd, ret, status; + pid_t pid, pid_coredump_server; + struct stat st; + struct pidfd_info info = {}; + int ipc_sockets[2]; + char c; + + ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket")); + + ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + ASSERT_EQ(ret, 0); + + pid_coredump_server = fork(); + ASSERT_GE(pid_coredump_server, 0); + if (pid_coredump_server == 0) { + struct coredump_req req = {}; + int fd_server = -1, fd_coredump = -1, fd_core_file = -1, fd_peer_pidfd = -1; + int exit_code = EXIT_FAILURE; + + close(ipc_sockets[0]); + + fd_server = create_and_listen_unix_socket("/tmp/coredump.socket"); + if (fd_server < 0) + goto out; + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + goto out; + + close(ipc_sockets[1]); + + fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC); + if (fd_coredump < 0) + goto out; + + fd_peer_pidfd = get_peer_pidfd(fd_coredump); + if (fd_peer_pidfd < 0) + goto out; + + if (!get_pidfd_info(fd_peer_pidfd, &info)) + goto out; + + if (!(info.mask & PIDFD_INFO_COREDUMP)) + goto out; + + if (!(info.coredump_mask & PIDFD_COREDUMPED)) + goto out; + + fd_core_file = creat("/tmp/coredump.file", 0644); + if (fd_core_file < 0) + goto out; + + if (!read_coredump_req(fd_coredump, &req)) + goto out; + + if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0, + COREDUMP_KERNEL | COREDUMP_USERSPACE | + COREDUMP_REJECT | COREDUMP_WAIT)) + goto out; + + if (!send_coredump_ack(fd_coredump, &req, + COREDUMP_KERNEL | COREDUMP_WAIT, 0)) + goto out; + + if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) + goto out; + + for (;;) { + char buffer[4096]; + ssize_t bytes_read, bytes_write; + + bytes_read = read(fd_coredump, buffer, sizeof(buffer)); + if (bytes_read < 0) + goto out; + + if (bytes_read == 0) + break; + + bytes_write = write(fd_core_file, buffer, bytes_read); + if (bytes_read != bytes_write) + goto out; } - if (write_nointr(ipc_sockets[1], "1", 1) < 0) { + exit_code = EXIT_SUCCESS; +out: + if (fd_core_file >= 0) + close(fd_core_file); + if (fd_peer_pidfd >= 0) + close(fd_peer_pidfd); + if (fd_coredump >= 0) + close(fd_coredump); + if (fd_server >= 0) close(fd_server); - close(ipc_sockets[1]); - _exit(EXIT_FAILURE); + _exit(exit_code); + } + self->pid_coredump_server = pid_coredump_server; + + EXPECT_EQ(close(ipc_sockets[1]), 0); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + EXPECT_EQ(close(ipc_sockets[0]), 0); + + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) + crashing_child(); + + pidfd = sys_pidfd_open(pid, 0); + ASSERT_GE(pidfd, 0); + + waitpid(pid, &status, 0); + ASSERT_TRUE(WIFSIGNALED(status)); + ASSERT_TRUE(WCOREDUMP(status)); + + ASSERT_TRUE(get_pidfd_info(pidfd, &info)); + ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0); + ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0); + + wait_and_check_coredump_server(pid_coredump_server, _metadata, self); + + ASSERT_EQ(stat("/tmp/coredump.file", &st), 0); + ASSERT_GT(st.st_size, 0); + system("file /tmp/coredump.file"); +} + +TEST_F(coredump, socket_request_userspace) +{ + int pidfd, ret, status; + pid_t pid, pid_coredump_server; + struct pidfd_info info = {}; + int ipc_sockets[2]; + char c; + + ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket")); + + ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + ASSERT_EQ(ret, 0); + + pid_coredump_server = fork(); + ASSERT_GE(pid_coredump_server, 0); + if (pid_coredump_server == 0) { + struct coredump_req req = {}; + int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1; + int exit_code = EXIT_FAILURE; + + close(ipc_sockets[0]); + + fd_server = create_and_listen_unix_socket("/tmp/coredump.socket"); + if (fd_server < 0) + goto out; + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + goto out; + + close(ipc_sockets[1]); + + fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC); + if (fd_coredump < 0) + goto out; + + fd_peer_pidfd = get_peer_pidfd(fd_coredump); + if (fd_peer_pidfd < 0) + goto out; + + if (!get_pidfd_info(fd_peer_pidfd, &info)) + goto out; + + if (!(info.mask & PIDFD_INFO_COREDUMP)) + goto out; + + if (!(info.coredump_mask & PIDFD_COREDUMPED)) + goto out; + + if (!read_coredump_req(fd_coredump, &req)) + goto out; + + if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0, + COREDUMP_KERNEL | COREDUMP_USERSPACE | + COREDUMP_REJECT | COREDUMP_WAIT)) + goto out; + + if (!send_coredump_ack(fd_coredump, &req, + COREDUMP_USERSPACE | COREDUMP_WAIT, 0)) + goto out; + + if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) + goto out; + + for (;;) { + char buffer[4096]; + ssize_t bytes_read; + + bytes_read = read(fd_coredump, buffer, sizeof(buffer)); + if (bytes_read > 0) + goto out; + + if (bytes_read < 0) + goto out; + + if (bytes_read == 0) + break; + } + + exit_code = EXIT_SUCCESS; +out: + if (fd_peer_pidfd >= 0) + close(fd_peer_pidfd); + if (fd_coredump >= 0) + close(fd_coredump); + if (fd_server >= 0) + close(fd_server); + _exit(exit_code); + } + self->pid_coredump_server = pid_coredump_server; + + EXPECT_EQ(close(ipc_sockets[1]), 0); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + EXPECT_EQ(close(ipc_sockets[0]), 0); + + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) + crashing_child(); + + pidfd = sys_pidfd_open(pid, 0); + ASSERT_GE(pidfd, 0); + + waitpid(pid, &status, 0); + ASSERT_TRUE(WIFSIGNALED(status)); + ASSERT_TRUE(WCOREDUMP(status)); + + ASSERT_TRUE(get_pidfd_info(pidfd, &info)); + ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0); + ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0); + + wait_and_check_coredump_server(pid_coredump_server, _metadata, self); +} + +TEST_F(coredump, socket_request_reject) +{ + int pidfd, ret, status; + pid_t pid, pid_coredump_server; + struct pidfd_info info = {}; + int ipc_sockets[2]; + char c; + + ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket")); + + ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + ASSERT_EQ(ret, 0); + + pid_coredump_server = fork(); + ASSERT_GE(pid_coredump_server, 0); + if (pid_coredump_server == 0) { + struct coredump_req req = {}; + int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1; + int exit_code = EXIT_FAILURE; + + close(ipc_sockets[0]); + + fd_server = create_and_listen_unix_socket("/tmp/coredump.socket"); + if (fd_server < 0) + goto out; + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + goto out; + + close(ipc_sockets[1]); + + fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC); + if (fd_coredump < 0) + goto out; + + fd_peer_pidfd = get_peer_pidfd(fd_coredump); + if (fd_peer_pidfd < 0) + goto out; + + if (!get_pidfd_info(fd_peer_pidfd, &info)) + goto out; + + if (!(info.mask & PIDFD_INFO_COREDUMP)) + goto out; + + if (!(info.coredump_mask & PIDFD_COREDUMPED)) + goto out; + + if (!read_coredump_req(fd_coredump, &req)) + goto out; + + if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0, + COREDUMP_KERNEL | COREDUMP_USERSPACE | + COREDUMP_REJECT | COREDUMP_WAIT)) + goto out; + + if (!send_coredump_ack(fd_coredump, &req, + COREDUMP_REJECT | COREDUMP_WAIT, 0)) + goto out; + + if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) + goto out; + + for (;;) { + char buffer[4096]; + ssize_t bytes_read; + + bytes_read = read(fd_coredump, buffer, sizeof(buffer)); + if (bytes_read > 0) + goto out; + + if (bytes_read < 0) + goto out; + + if (bytes_read == 0) + break; } - close(fd_server); + exit_code = EXIT_SUCCESS; +out: + if (fd_peer_pidfd >= 0) + close(fd_peer_pidfd); + if (fd_coredump >= 0) + close(fd_coredump); + if (fd_server >= 0) + close(fd_server); + _exit(exit_code); + } + self->pid_coredump_server = pid_coredump_server; + + EXPECT_EQ(close(ipc_sockets[1]), 0); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + EXPECT_EQ(close(ipc_sockets[0]), 0); + + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) + crashing_child(); + + pidfd = sys_pidfd_open(pid, 0); + ASSERT_GE(pidfd, 0); + + waitpid(pid, &status, 0); + ASSERT_TRUE(WIFSIGNALED(status)); + ASSERT_FALSE(WCOREDUMP(status)); + + ASSERT_TRUE(get_pidfd_info(pidfd, &info)); + ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0); + ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0); + + wait_and_check_coredump_server(pid_coredump_server, _metadata, self); +} + +TEST_F(coredump, socket_request_invalid_flag_combination) +{ + int pidfd, ret, status; + pid_t pid, pid_coredump_server; + struct pidfd_info info = {}; + int ipc_sockets[2]; + char c; + + ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket")); + + ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + ASSERT_EQ(ret, 0); + + pid_coredump_server = fork(); + ASSERT_GE(pid_coredump_server, 0); + if (pid_coredump_server == 0) { + struct coredump_req req = {}; + int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1; + int exit_code = EXIT_FAILURE; + + close(ipc_sockets[0]); + + fd_server = create_and_listen_unix_socket("/tmp/coredump.socket"); + if (fd_server < 0) + goto out; + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + goto out; + close(ipc_sockets[1]); - _exit(EXIT_SUCCESS); + + fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC); + if (fd_coredump < 0) + goto out; + + fd_peer_pidfd = get_peer_pidfd(fd_coredump); + if (fd_peer_pidfd < 0) + goto out; + + if (!get_pidfd_info(fd_peer_pidfd, &info)) + goto out; + + if (!(info.mask & PIDFD_INFO_COREDUMP)) + goto out; + + if (!(info.coredump_mask & PIDFD_COREDUMPED)) + goto out; + + if (!read_coredump_req(fd_coredump, &req)) + goto out; + + if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0, + COREDUMP_KERNEL | COREDUMP_USERSPACE | + COREDUMP_REJECT | COREDUMP_WAIT)) + goto out; + + if (!send_coredump_ack(fd_coredump, &req, + COREDUMP_KERNEL | COREDUMP_REJECT | COREDUMP_WAIT, 0)) + goto out; + + if (!read_marker(fd_coredump, COREDUMP_MARK_CONFLICTING)) + goto out; + + exit_code = EXIT_SUCCESS; +out: + if (fd_peer_pidfd >= 0) + close(fd_peer_pidfd); + if (fd_coredump >= 0) + close(fd_coredump); + if (fd_server >= 0) + close(fd_server); + _exit(exit_code); } self->pid_coredump_server = pid_coredump_server; @@ -618,10 +1169,662 @@ TEST_F(coredump, socket_no_listener) ASSERT_TRUE(WIFSIGNALED(status)); ASSERT_FALSE(WCOREDUMP(status)); - waitpid(pid_coredump_server, &status, 0); - self->pid_coredump_server = -ESRCH; - ASSERT_TRUE(WIFEXITED(status)); - ASSERT_EQ(WEXITSTATUS(status), 0); + ASSERT_TRUE(get_pidfd_info(pidfd, &info)); + ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0); + ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0); + + wait_and_check_coredump_server(pid_coredump_server, _metadata, self); +} + +TEST_F(coredump, socket_request_unknown_flag) +{ + int pidfd, ret, status; + pid_t pid, pid_coredump_server; + struct pidfd_info info = {}; + int ipc_sockets[2]; + char c; + + ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket")); + + ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + ASSERT_EQ(ret, 0); + + pid_coredump_server = fork(); + ASSERT_GE(pid_coredump_server, 0); + if (pid_coredump_server == 0) { + struct coredump_req req = {}; + int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1; + int exit_code = EXIT_FAILURE; + + close(ipc_sockets[0]); + + fd_server = create_and_listen_unix_socket("/tmp/coredump.socket"); + if (fd_server < 0) + goto out; + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + goto out; + + close(ipc_sockets[1]); + + fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC); + if (fd_coredump < 0) + goto out; + + fd_peer_pidfd = get_peer_pidfd(fd_coredump); + if (fd_peer_pidfd < 0) + goto out; + + if (!get_pidfd_info(fd_peer_pidfd, &info)) + goto out; + + if (!(info.mask & PIDFD_INFO_COREDUMP)) + goto out; + + if (!(info.coredump_mask & PIDFD_COREDUMPED)) + goto out; + + if (!read_coredump_req(fd_coredump, &req)) + goto out; + + if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0, + COREDUMP_KERNEL | COREDUMP_USERSPACE | + COREDUMP_REJECT | COREDUMP_WAIT)) + goto out; + + if (!send_coredump_ack(fd_coredump, &req, (1ULL << 63), 0)) + goto out; + + if (!read_marker(fd_coredump, COREDUMP_MARK_UNSUPPORTED)) + goto out; + + exit_code = EXIT_SUCCESS; +out: + if (fd_peer_pidfd >= 0) + close(fd_peer_pidfd); + if (fd_coredump >= 0) + close(fd_coredump); + if (fd_server >= 0) + close(fd_server); + _exit(exit_code); + } + self->pid_coredump_server = pid_coredump_server; + + EXPECT_EQ(close(ipc_sockets[1]), 0); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + EXPECT_EQ(close(ipc_sockets[0]), 0); + + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) + crashing_child(); + + pidfd = sys_pidfd_open(pid, 0); + ASSERT_GE(pidfd, 0); + + waitpid(pid, &status, 0); + ASSERT_TRUE(WIFSIGNALED(status)); + ASSERT_FALSE(WCOREDUMP(status)); + + ASSERT_TRUE(get_pidfd_info(pidfd, &info)); + ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0); + ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0); + + wait_and_check_coredump_server(pid_coredump_server, _metadata, self); +} + +TEST_F(coredump, socket_request_invalid_size_small) +{ + int pidfd, ret, status; + pid_t pid, pid_coredump_server; + struct pidfd_info info = {}; + int ipc_sockets[2]; + char c; + + ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket")); + + ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + ASSERT_EQ(ret, 0); + + pid_coredump_server = fork(); + ASSERT_GE(pid_coredump_server, 0); + if (pid_coredump_server == 0) { + struct coredump_req req = {}; + int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1; + int exit_code = EXIT_FAILURE; + + close(ipc_sockets[0]); + + fd_server = create_and_listen_unix_socket("/tmp/coredump.socket"); + if (fd_server < 0) + goto out; + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + goto out; + + close(ipc_sockets[1]); + + fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC); + if (fd_coredump < 0) + goto out; + + fd_peer_pidfd = get_peer_pidfd(fd_coredump); + if (fd_peer_pidfd < 0) + goto out; + + if (!get_pidfd_info(fd_peer_pidfd, &info)) + goto out; + + if (!(info.mask & PIDFD_INFO_COREDUMP)) + goto out; + + if (!(info.coredump_mask & PIDFD_COREDUMPED)) + goto out; + + if (!read_coredump_req(fd_coredump, &req)) + goto out; + + if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0, + COREDUMP_KERNEL | COREDUMP_USERSPACE | + COREDUMP_REJECT | COREDUMP_WAIT)) + goto out; + + if (!send_coredump_ack(fd_coredump, &req, + COREDUMP_REJECT | COREDUMP_WAIT, + COREDUMP_ACK_SIZE_VER0 / 2)) + goto out; + + if (!read_marker(fd_coredump, COREDUMP_MARK_MINSIZE)) + goto out; + + exit_code = EXIT_SUCCESS; +out: + if (fd_peer_pidfd >= 0) + close(fd_peer_pidfd); + if (fd_coredump >= 0) + close(fd_coredump); + if (fd_server >= 0) + close(fd_server); + _exit(exit_code); + } + self->pid_coredump_server = pid_coredump_server; + + EXPECT_EQ(close(ipc_sockets[1]), 0); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + EXPECT_EQ(close(ipc_sockets[0]), 0); + + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) + crashing_child(); + + pidfd = sys_pidfd_open(pid, 0); + ASSERT_GE(pidfd, 0); + + waitpid(pid, &status, 0); + ASSERT_TRUE(WIFSIGNALED(status)); + ASSERT_FALSE(WCOREDUMP(status)); + + ASSERT_TRUE(get_pidfd_info(pidfd, &info)); + ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0); + ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0); + + wait_and_check_coredump_server(pid_coredump_server, _metadata, self); +} + +TEST_F(coredump, socket_request_invalid_size_large) +{ + int pidfd, ret, status; + pid_t pid, pid_coredump_server; + struct pidfd_info info = {}; + int ipc_sockets[2]; + char c; + + ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket")); + + ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + ASSERT_EQ(ret, 0); + + pid_coredump_server = fork(); + ASSERT_GE(pid_coredump_server, 0); + if (pid_coredump_server == 0) { + struct coredump_req req = {}; + int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1; + int exit_code = EXIT_FAILURE; + + close(ipc_sockets[0]); + + fd_server = create_and_listen_unix_socket("/tmp/coredump.socket"); + if (fd_server < 0) + goto out; + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + goto out; + + close(ipc_sockets[1]); + + fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC); + if (fd_coredump < 0) + goto out; + + fd_peer_pidfd = get_peer_pidfd(fd_coredump); + if (fd_peer_pidfd < 0) + goto out; + + if (!get_pidfd_info(fd_peer_pidfd, &info)) + goto out; + + if (!(info.mask & PIDFD_INFO_COREDUMP)) + goto out; + + if (!(info.coredump_mask & PIDFD_COREDUMPED)) + goto out; + + if (!read_coredump_req(fd_coredump, &req)) + goto out; + + if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0, + COREDUMP_KERNEL | COREDUMP_USERSPACE | + COREDUMP_REJECT | COREDUMP_WAIT)) + goto out; + + if (!send_coredump_ack(fd_coredump, &req, + COREDUMP_REJECT | COREDUMP_WAIT, + COREDUMP_ACK_SIZE_VER0 + PAGE_SIZE)) + goto out; + + if (!read_marker(fd_coredump, COREDUMP_MARK_MAXSIZE)) + goto out; + + exit_code = EXIT_SUCCESS; +out: + if (fd_peer_pidfd >= 0) + close(fd_peer_pidfd); + if (fd_coredump >= 0) + close(fd_coredump); + if (fd_server >= 0) + close(fd_server); + _exit(exit_code); + } + self->pid_coredump_server = pid_coredump_server; + + EXPECT_EQ(close(ipc_sockets[1]), 0); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + EXPECT_EQ(close(ipc_sockets[0]), 0); + + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) + crashing_child(); + + pidfd = sys_pidfd_open(pid, 0); + ASSERT_GE(pidfd, 0); + + waitpid(pid, &status, 0); + ASSERT_TRUE(WIFSIGNALED(status)); + ASSERT_FALSE(WCOREDUMP(status)); + + ASSERT_TRUE(get_pidfd_info(pidfd, &info)); + ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0); + ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0); + + wait_and_check_coredump_server(pid_coredump_server, _metadata, self); +} + +static int open_coredump_tmpfile(int fd_tmpfs_detached) +{ + return openat(fd_tmpfs_detached, ".", O_TMPFILE | O_RDWR | O_EXCL, 0600); +} + +#define NUM_CRASHING_COREDUMPS 5 + +TEST_F_TIMEOUT(coredump, socket_multiple_crashing_coredumps, 500) +{ + int pidfd[NUM_CRASHING_COREDUMPS], status[NUM_CRASHING_COREDUMPS]; + pid_t pid[NUM_CRASHING_COREDUMPS], pid_coredump_server; + struct pidfd_info info = {}; + int ipc_sockets[2]; + char c; + + ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket")); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets), 0); + + pid_coredump_server = fork(); + ASSERT_GE(pid_coredump_server, 0); + if (pid_coredump_server == 0) { + int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1; + int exit_code = EXIT_FAILURE; + struct coredump_req req = {}; + + close(ipc_sockets[0]); + fd_server = create_and_listen_unix_socket("/tmp/coredump.socket"); + if (fd_server < 0) { + fprintf(stderr, "Failed to create and listen on unix socket\n"); + goto out; + } + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) { + fprintf(stderr, "Failed to notify parent via ipc socket\n"); + goto out; + } + close(ipc_sockets[1]); + + for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) { + fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC); + if (fd_coredump < 0) { + fprintf(stderr, "accept4 failed: %m\n"); + goto out; + } + + fd_peer_pidfd = get_peer_pidfd(fd_coredump); + if (fd_peer_pidfd < 0) { + fprintf(stderr, "get_peer_pidfd failed for fd %d: %m\n", fd_coredump); + goto out; + } + + if (!get_pidfd_info(fd_peer_pidfd, &info)) { + fprintf(stderr, "get_pidfd_info failed for fd %d\n", fd_peer_pidfd); + goto out; + } + + if (!(info.mask & PIDFD_INFO_COREDUMP)) { + fprintf(stderr, "pidfd info missing PIDFD_INFO_COREDUMP for fd %d\n", fd_peer_pidfd); + goto out; + } + if (!(info.coredump_mask & PIDFD_COREDUMPED)) { + fprintf(stderr, "pidfd info missing PIDFD_COREDUMPED for fd %d\n", fd_peer_pidfd); + goto out; + } + + if (!read_coredump_req(fd_coredump, &req)) { + fprintf(stderr, "read_coredump_req failed for fd %d\n", fd_coredump); + goto out; + } + + if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0, + COREDUMP_KERNEL | COREDUMP_USERSPACE | + COREDUMP_REJECT | COREDUMP_WAIT)) { + fprintf(stderr, "check_coredump_req failed for fd %d\n", fd_coredump); + goto out; + } + + if (!send_coredump_ack(fd_coredump, &req, + COREDUMP_KERNEL | COREDUMP_WAIT, 0)) { + fprintf(stderr, "send_coredump_ack failed for fd %d\n", fd_coredump); + goto out; + } + + if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) { + fprintf(stderr, "read_marker failed for fd %d\n", fd_coredump); + goto out; + } + + fd_core_file = open_coredump_tmpfile(self->fd_tmpfs_detached); + if (fd_core_file < 0) { + fprintf(stderr, "%m - open_coredump_tmpfile failed for fd %d\n", fd_coredump); + goto out; + } + + for (;;) { + char buffer[4096]; + ssize_t bytes_read, bytes_write; + + bytes_read = read(fd_coredump, buffer, sizeof(buffer)); + if (bytes_read < 0) { + fprintf(stderr, "read failed for fd %d: %m\n", fd_coredump); + goto out; + } + + if (bytes_read == 0) + break; + + bytes_write = write(fd_core_file, buffer, bytes_read); + if (bytes_read != bytes_write) { + fprintf(stderr, "write failed for fd %d: %m\n", fd_core_file); + goto out; + } + } + + close(fd_core_file); + close(fd_peer_pidfd); + close(fd_coredump); + fd_peer_pidfd = -1; + fd_coredump = -1; + } + + exit_code = EXIT_SUCCESS; +out: + if (fd_core_file >= 0) + close(fd_core_file); + if (fd_peer_pidfd >= 0) + close(fd_peer_pidfd); + if (fd_coredump >= 0) + close(fd_coredump); + if (fd_server >= 0) + close(fd_server); + _exit(exit_code); + } + self->pid_coredump_server = pid_coredump_server; + + EXPECT_EQ(close(ipc_sockets[1]), 0); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + EXPECT_EQ(close(ipc_sockets[0]), 0); + + for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) { + pid[i] = fork(); + ASSERT_GE(pid[i], 0); + if (pid[i] == 0) + crashing_child(); + pidfd[i] = sys_pidfd_open(pid[i], 0); + ASSERT_GE(pidfd[i], 0); + } + + for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) { + waitpid(pid[i], &status[i], 0); + ASSERT_TRUE(WIFSIGNALED(status[i])); + ASSERT_TRUE(WCOREDUMP(status[i])); + } + + for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) { + info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP; + ASSERT_EQ(ioctl(pidfd[i], PIDFD_GET_INFO, &info), 0); + ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0); + ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0); + } + + wait_and_check_coredump_server(pid_coredump_server, _metadata, self); +} + +#define MAX_EVENTS 128 + +static void process_coredump_worker(int fd_coredump, int fd_peer_pidfd, int fd_core_file) +{ + int epfd = -1; + int exit_code = EXIT_FAILURE; + + epfd = epoll_create1(0); + if (epfd < 0) + goto out; + + struct epoll_event ev; + ev.events = EPOLLIN | EPOLLRDHUP | EPOLLET; + ev.data.fd = fd_coredump; + if (epoll_ctl(epfd, EPOLL_CTL_ADD, fd_coredump, &ev) < 0) + goto out; + + for (;;) { + struct epoll_event events[1]; + int n = epoll_wait(epfd, events, 1, -1); + if (n < 0) + break; + + if (events[0].events & (EPOLLIN | EPOLLRDHUP)) { + for (;;) { + char buffer[4096]; + ssize_t bytes_read = read(fd_coredump, buffer, sizeof(buffer)); + if (bytes_read < 0) { + if (errno == EAGAIN || errno == EWOULDBLOCK) + break; + goto out; + } + if (bytes_read == 0) + goto done; + ssize_t bytes_write = write(fd_core_file, buffer, bytes_read); + if (bytes_write != bytes_read) + goto out; + } + } + } + +done: + exit_code = EXIT_SUCCESS; +out: + if (epfd >= 0) + close(epfd); + if (fd_core_file >= 0) + close(fd_core_file); + if (fd_peer_pidfd >= 0) + close(fd_peer_pidfd); + if (fd_coredump >= 0) + close(fd_coredump); + _exit(exit_code); +} + +TEST_F_TIMEOUT(coredump, socket_multiple_crashing_coredumps_epoll_workers, 500) +{ + int pidfd[NUM_CRASHING_COREDUMPS], status[NUM_CRASHING_COREDUMPS]; + pid_t pid[NUM_CRASHING_COREDUMPS], pid_coredump_server, worker_pids[NUM_CRASHING_COREDUMPS]; + struct pidfd_info info = {}; + int ipc_sockets[2]; + char c; + + ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket")); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets), 0); + + pid_coredump_server = fork(); + ASSERT_GE(pid_coredump_server, 0); + if (pid_coredump_server == 0) { + int fd_server = -1, exit_code = EXIT_FAILURE, n_conns = 0; + fd_server = -1; + exit_code = EXIT_FAILURE; + n_conns = 0; + close(ipc_sockets[0]); + fd_server = create_and_listen_unix_socket("/tmp/coredump.socket"); + if (fd_server < 0) + goto out; + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + goto out; + close(ipc_sockets[1]); + + while (n_conns < NUM_CRASHING_COREDUMPS) { + int fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1; + struct coredump_req req = {}; + fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC); + if (fd_coredump < 0) { + if (errno == EAGAIN || errno == EWOULDBLOCK) + continue; + goto out; + } + fd_peer_pidfd = get_peer_pidfd(fd_coredump); + if (fd_peer_pidfd < 0) + goto out; + if (!get_pidfd_info(fd_peer_pidfd, &info)) + goto out; + if (!(info.mask & PIDFD_INFO_COREDUMP) || !(info.coredump_mask & PIDFD_COREDUMPED)) + goto out; + if (!read_coredump_req(fd_coredump, &req)) + goto out; + if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0, + COREDUMP_KERNEL | COREDUMP_USERSPACE | + COREDUMP_REJECT | COREDUMP_WAIT)) + goto out; + if (!send_coredump_ack(fd_coredump, &req, COREDUMP_KERNEL | COREDUMP_WAIT, 0)) + goto out; + if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) + goto out; + fd_core_file = open_coredump_tmpfile(self->fd_tmpfs_detached); + if (fd_core_file < 0) + goto out; + pid_t worker = fork(); + if (worker == 0) { + close(fd_server); + process_coredump_worker(fd_coredump, fd_peer_pidfd, fd_core_file); + } + worker_pids[n_conns] = worker; + if (fd_coredump >= 0) + close(fd_coredump); + if (fd_peer_pidfd >= 0) + close(fd_peer_pidfd); + if (fd_core_file >= 0) + close(fd_core_file); + n_conns++; + } + exit_code = EXIT_SUCCESS; +out: + if (fd_server >= 0) + close(fd_server); + + // Reap all worker processes + for (int i = 0; i < n_conns; i++) { + int wstatus; + if (waitpid(worker_pids[i], &wstatus, 0) < 0) { + fprintf(stderr, "Failed to wait for worker %d: %m\n", worker_pids[i]); + } else if (WIFEXITED(wstatus) && WEXITSTATUS(wstatus) != EXIT_SUCCESS) { + fprintf(stderr, "Worker %d exited with error code %d\n", worker_pids[i], WEXITSTATUS(wstatus)); + exit_code = EXIT_FAILURE; + } + } + + _exit(exit_code); + } + self->pid_coredump_server = pid_coredump_server; + + EXPECT_EQ(close(ipc_sockets[1]), 0); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + EXPECT_EQ(close(ipc_sockets[0]), 0); + + for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) { + pid[i] = fork(); + ASSERT_GE(pid[i], 0); + if (pid[i] == 0) + crashing_child(); + pidfd[i] = sys_pidfd_open(pid[i], 0); + ASSERT_GE(pidfd[i], 0); + } + + for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) { + ASSERT_GE(waitpid(pid[i], &status[i], 0), 0); + ASSERT_TRUE(WIFSIGNALED(status[i])); + ASSERT_TRUE(WCOREDUMP(status[i])); + } + + for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) { + info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP; + ASSERT_EQ(ioctl(pidfd[i], PIDFD_GET_INFO, &info), 0); + ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0); + ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0); + } + + wait_and_check_coredump_server(pid_coredump_server, _metadata, self); +} + +TEST_F(coredump, socket_invalid_paths) +{ + ASSERT_FALSE(set_core_pattern("@ /tmp/coredump.socket")); + ASSERT_FALSE(set_core_pattern("@/tmp/../coredump.socket")); + ASSERT_FALSE(set_core_pattern("@../coredump.socket")); + ASSERT_FALSE(set_core_pattern("@/tmp/coredump.socket/..")); + ASSERT_FALSE(set_core_pattern("@..")); + + ASSERT_FALSE(set_core_pattern("@@ /tmp/coredump.socket")); + ASSERT_FALSE(set_core_pattern("@@/tmp/../coredump.socket")); + ASSERT_FALSE(set_core_pattern("@@../coredump.socket")); + ASSERT_FALSE(set_core_pattern("@@/tmp/coredump.socket/..")); + ASSERT_FALSE(set_core_pattern("@@..")); + + ASSERT_FALSE(set_core_pattern("@@@/tmp/coredump.socket")); } TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh index d5dc7e0dc726..6232a46ca6e1 100755 --- a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh +++ b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh @@ -67,7 +67,7 @@ hotpluggable_cpus() done } -hotplaggable_offline_cpus() +hotpluggable_offline_cpus() { hotpluggable_cpus 0 } @@ -151,7 +151,7 @@ offline_cpu_expect_fail() online_all_hot_pluggable_cpus() { - for cpu in `hotplaggable_offline_cpus`; do + for cpu in `hotpluggable_offline_cpus`; do online_cpu_expect_success $cpu done } diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index be780bcb73a3..3556f3563e08 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -12,14 +12,17 @@ TEST_GEN_FILES := \ TEST_PROGS := \ napi_id.py \ netcons_basic.sh \ + netcons_cmdline.sh \ netcons_fragmented_msg.sh \ netcons_overflow.sh \ netcons_sysdata.sh \ + netpoll_basic.py \ ping.py \ queues.py \ stats.py \ shaper.py \ hds.py \ + xdp.py \ # end of TEST_PROGS include ../../lib.mk diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index df2c047ffa90..fdc97355588c 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -16,6 +16,7 @@ TEST_PROGS = \ irq.py \ loopback.sh \ pp_alloc_fail.py \ + rss_api.py \ rss_ctx.py \ rss_input_xfrm.py \ tso.py \ diff --git a/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py b/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py new file mode 100755 index 000000000000..ead6784d1910 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py @@ -0,0 +1,465 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +Devlink Rate TC Bandwidth Test Suite +=================================== + +This test suite verifies the functionality of devlink-rate traffic class (TC) +bandwidth distribution in a virtualized environment. The tests validate that +bandwidth can be properly allocated between different traffic classes and +that TC mapping works as expected. + +Test Environment: +---------------- +- Creates 1 VF +- Establishes a bridge connecting the VF representor and the uplink representor +- Sets up 2 VLAN interfaces on the VF with different VLAN IDs (101, 102) +- Configures different traffic classes (TC3 and TC4) for each VLAN + +Test Cases: +---------- +1. test_no_tc_mapping_bandwidth: + - Verifies that without TC mapping, bandwidth is NOT distributed according to + the configured 80/20 split between TC4 and TC3 + - This test should fail if bandwidth matches the 80/20 split without TC + mapping + - Expected: Bandwidth should NOT be distributed as 80/20 + +2. test_tc_mapping_bandwidth: + - Configures TC mapping using mqprio qdisc + - Verifies that with TC mapping, bandwidth IS distributed according to the + configured 80/20 split between TC3 and TC4 + - Expected: Bandwidth should be distributed as 80/20 + +Bandwidth Distribution: +---------------------- +- TC3 (VLAN 101): Configured for 80% of total bandwidth +- TC4 (VLAN 102): Configured for 20% of total bandwidth +- Total bandwidth: 1Gbps +- Tolerance: +-12% + +Hardware-Specific Behavior (mlx5): +-------------------------- +mlx5 hardware enforces traffic class separation by ensuring that each transmit +queue (SQ) is associated with a single TC. If a packet is sent on a queue that +doesn't match the expected TC (based on DSCP or VLAN priority and hypervisor-set +mapping), the hardware moves the queue to the correct TC scheduler to preserve +traffic isolation. + +This behavior means that even without explicit TC-to-queue mapping, bandwidth +enforcement may still appear to work—because the hardware dynamically adjusts +the scheduling context. However, this can lead to performance issues in high +rates and HOL blocking if traffic from different TCs is mixed on the same queue. +""" + +import json +import os +import subprocess +import threading +import time + +from lib.py import ksft_pr, ksft_run, ksft_exit +from lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx +from lib.py import NetDrvEpEnv, DevlinkFamily +from lib.py import NlError +from lib.py import cmd, defer, ethtool, ip + + +class BandwidthValidator: + """ + Validates bandwidth totals and per-TC shares against expected values + with a tolerance. + """ + + def __init__(self): + self.tolerance_percent = 12 + self.expected_total_gbps = 1.0 + self.total_min_expected = self.min_expected(self.expected_total_gbps) + self.total_max_expected = self.max_expected(self.expected_total_gbps) + self.tc_expected_percent = { + 3: 20.0, + 4: 80.0, + } + + def min_expected(self, value): + """Calculates the minimum acceptable value based on tolerance.""" + return value - (value * self.tolerance_percent / 100) + + def max_expected(self, value): + """Calculates the maximum acceptable value based on tolerance.""" + return value + (value * self.tolerance_percent / 100) + + def bound(self, expected, value): + """Returns True if value is within expected tolerance.""" + return self.min_expected(expected) <= value <= self.max_expected(expected) + + def tc_bandwidth_bound(self, value, tc_ix): + """ + Returns True if the given bandwidth value is within tolerance + for the TC's expected bandwidth. + """ + expected = self.tc_expected_percent[tc_ix] + return self.bound(expected, value) + + +def setup_vf(cfg, set_tc_mapping=True): + """ + Sets up a VF on the given network interface. + + Enables SR-IOV and switchdev mode, brings the VF interface up, + and optionally configures TC mapping using mqprio. + """ + try: + cmd(f"devlink dev eswitch set pci/{cfg.pci} mode switchdev") + defer(cmd, f"devlink dev eswitch set pci/{cfg.pci} mode legacy") + except Exception as exc: + raise KsftSkipEx(f"Failed to enable switchdev mode on {cfg.pci}") from exc + try: + cmd(f"echo 1 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs") + defer(cmd, f"echo 0 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs") + except Exception as exc: + raise KsftSkipEx(f"Failed to enable SR-IOV on {cfg.ifname}") from exc + + time.sleep(2) + vf_ifc = (os.listdir( + f"/sys/class/net/{cfg.ifname}/device/virtfn0/net") or [None])[0] + if vf_ifc: + ip(f"link set dev {vf_ifc} up") + else: + raise KsftSkipEx("VF interface not found") + if set_tc_mapping: + cmd(f"tc qdisc add dev {vf_ifc} root handle 5 mqprio mode dcb hw 1 num_tc 8") + + return vf_ifc + + +def setup_vlans_on_vf(vf_ifc): + """ + Sets up two VLAN interfaces on the given VF, each mapped to a different TC. + """ + vlan_configs = [ + {"vlan_id": 101, "tc": 3, "ip": "198.51.100.2"}, + {"vlan_id": 102, "tc": 4, "ip": "198.51.100.10"}, + ] + + for config in vlan_configs: + vlan_dev = f"{vf_ifc}.{config['vlan_id']}" + ip(f"link add link {vf_ifc} name {vlan_dev} type vlan id {config['vlan_id']}") + ip(f"addr add {config['ip']}/29 dev {vlan_dev}") + ip(f"link set dev {vlan_dev} up") + ip(f"link set dev {vlan_dev} type vlan egress-qos-map 0:{config['tc']}") + ksft_pr(f"Created VLAN {vlan_dev} on {vf_ifc} with tc {config['tc']} and IP {config['ip']}") + + +def get_vf_info(cfg): + """ + Finds the VF representor interface and devlink port index + for the given PCI device used in the test environment. + """ + cfg.vf_representor = None + cfg.vf_port_index = None + out = subprocess.check_output(["devlink", "-j", "port", "show"], encoding="utf-8") + ports = json.loads(out)["port"] + + for port_name, props in ports.items(): + netdev = props.get("netdev") + + if (port_name.startswith(f"pci/{cfg.pci}/") and + props.get("vfnum") == 0): + cfg.vf_representor = netdev + cfg.vf_port_index = int(port_name.split("/")[-1]) + break + + +def setup_bridge(cfg): + """ + Creates and configures a Linux bridge, with both the uplink + and VF representor interfaces attached to it. + """ + bridge_name = f"br_{os.getpid()}" + ip(f"link add name {bridge_name} type bridge") + defer(cmd, f"ip link del name {bridge_name} type bridge") + + ip(f"link set dev {cfg.ifname} master {bridge_name}") + + rep_name = cfg.vf_representor + if rep_name: + ip(f"link set dev {rep_name} master {bridge_name}") + ip(f"link set dev {rep_name} up") + ksft_pr(f"Set representor {rep_name} up and added to bridge") + else: + raise KsftSkipEx("Could not find representor for the VF") + + ip(f"link set dev {bridge_name} up") + + +def setup_devlink_rate(cfg): + """ + Configures devlink rate tx_max and traffic class bandwidth for the VF. + """ + port_index = cfg.vf_port_index + if port_index is None: + raise KsftSkipEx("Could not find VF port index") + try: + cfg.devnl.rate_set({ + "bus-name": "pci", + "dev-name": cfg.pci, + "port-index": port_index, + "rate-tx-max": 125000000, + "rate-tc-bws": [ + {"index": 0, "bw": 0}, + {"index": 1, "bw": 0}, + {"index": 2, "bw": 0}, + {"index": 3, "bw": 20}, + {"index": 4, "bw": 80}, + {"index": 5, "bw": 0}, + {"index": 6, "bw": 0}, + {"index": 7, "bw": 0}, + ] + }) + except NlError as exc: + if exc.error == 95: # EOPNOTSUPP + raise KsftSkipEx("devlink rate configuration is not supported on the VF") from exc + raise KsftFailEx(f"rate_set failed on VF port {port_index}") from exc + + +def setup_remote_server(cfg): + """ + Sets up VLAN interfaces and starts iperf3 servers on the remote side. + """ + remote_dev = cfg.remote_ifname + vlan_ids = [101, 102] + remote_ips = ["198.51.100.1", "198.51.100.9"] + + for vlan_id, ip_addr in zip(vlan_ids, remote_ips): + vlan_dev = f"{remote_dev}.{vlan_id}" + cmd(f"ip link add link {remote_dev} name {vlan_dev} " + f"type vlan id {vlan_id}", host=cfg.remote) + cmd(f"ip addr add {ip_addr}/29 dev {vlan_dev}", host=cfg.remote) + cmd(f"ip link set dev {vlan_dev} up", host=cfg.remote) + cmd(f"iperf3 -s -1 -B {ip_addr}",background=True, host=cfg.remote) + defer(cmd, f"ip link del {vlan_dev}", host=cfg.remote) + + +def setup_test_environment(cfg, set_tc_mapping=True): + """ + Sets up the complete test environment including VF creation, VLANs, + bridge configuration, devlink rate setup, and the remote server. + """ + vf_ifc = setup_vf(cfg, set_tc_mapping) + ksft_pr(f"Created VF interface: {vf_ifc}") + + setup_vlans_on_vf(vf_ifc) + + get_vf_info(cfg) + setup_bridge(cfg) + + setup_devlink_rate(cfg) + setup_remote_server(cfg) + time.sleep(2) + + +def run_iperf_client(server_ip, local_ip, barrier, min_expected_gbps=0.1): + """ + Runs a single iperf3 client instance, binding to the given local IP. + Waits on a barrier to synchronize with other threads. + """ + try: + barrier.wait(timeout=10) + except Exception as exc: + raise KsftFailEx("iperf3 barrier wait timed") from exc + + iperf_cmd = ["iperf3", "-c", server_ip, "-B", local_ip, "-J"] + result = subprocess.run(iperf_cmd, capture_output=True, text=True, + check=True) + + try: + output = json.loads(result.stdout) + bits_per_second = output["end"]["sum_received"]["bits_per_second"] + gbps = bits_per_second / 1e9 + if gbps < min_expected_gbps: + ksft_pr( + f"iperf3 bandwidth too low: {gbps:.2f} Gbps " + f"(expected ≥ {min_expected_gbps} Gbps)" + ) + return None + return gbps + except json.JSONDecodeError as exc: + ksft_pr(f"Failed to parse iperf3 JSON output: {exc}") + return None + + +def run_bandwidth_test(): + """ + Launches iperf3 client threads for each VLAN/TC pair and collects results. + """ + def _run_iperf_client_thread(server_ip, local_ip, results, barrier, tc_ix): + results[tc_ix] = run_iperf_client(server_ip, local_ip, barrier) + + vf_vlan_data = [ + # (local_ip, remote_ip, TC) + ("198.51.100.2", "198.51.100.1", 3), + ("198.51.100.10", "198.51.100.9", 4), + ] + + results = {} + threads = [] + start_barrier = threading.Barrier(len(vf_vlan_data)) + + for local_ip, remote_ip, tc_ix in vf_vlan_data: + thread = threading.Thread( + target=_run_iperf_client_thread, + args=(remote_ip, local_ip, results, start_barrier, tc_ix) + ) + thread.start() + threads.append(thread) + + for thread in threads: + thread.join() + + for tc_ix, tc_bw in results.items(): + if tc_bw is None: + raise KsftFailEx("iperf3 client failed; cannot evaluate bandwidth") + + return results + +def calculate_bandwidth_percentages(results): + """ + Calculates the percentage of total bandwidth received by TC3 and TC4. + """ + if 3 not in results or 4 not in results: + raise KsftFailEx(f"Missing expected TC results in {results}") + + tc3_bw = results[3] + tc4_bw = results[4] + total_bw = tc3_bw + tc4_bw + tc3_percentage = (tc3_bw / total_bw) * 100 + tc4_percentage = (tc4_bw / total_bw) * 100 + + return { + 'tc3_bw': tc3_bw, + 'tc4_bw': tc4_bw, + 'tc3_percentage': tc3_percentage, + 'tc4_percentage': tc4_percentage, + 'total_bw': total_bw + } + + +def print_bandwidth_results(bw_data, test_name): + """ + Prints bandwidth measurements and TC usage summary for a given test. + """ + ksft_pr(f"Bandwidth check results {test_name}:") + ksft_pr(f"TC 3: {bw_data['tc3_bw']:.2f} Gbits/sec") + ksft_pr(f"TC 4: {bw_data['tc4_bw']:.2f} Gbits/sec") + ksft_pr(f"Total bandwidth: {bw_data['total_bw']:.2f} Gbits/sec") + ksft_pr(f"TC 3 percentage: {bw_data['tc3_percentage']:.1f}%") + ksft_pr(f"TC 4 percentage: {bw_data['tc4_percentage']:.1f}%") + + +def verify_total_bandwidth(bw_data, validator): + """ + Ensures the total measured bandwidth falls within the acceptable tolerance. + """ + total = bw_data['total_bw'] + + if validator.bound(validator.expected_total_gbps, total): + return + + if total < validator.total_min_expected: + raise KsftSkipEx( + f"Total bandwidth {total:.2f} Gbps < minimum " + f"{validator.total_min_expected:.2f} Gbps; " + f"parent tx_max ({validator.expected_total_gbps:.1f} G) " + f"not reached, cannot validate share" + ) + + raise KsftFailEx( + f"Total bandwidth {total:.2f} Gbps exceeds allowed ceiling " + f"{validator.total_max_expected:.2f} Gbps " + f"(VF tx_max set to {validator.expected_total_gbps:.1f} G)" + ) + + +def check_bandwidth_distribution(bw_data, validator): + """ + Checks whether the measured TC3 and TC4 bandwidth percentages + fall within their expected tolerance ranges. + + Returns: + bool: True if both TC3 and TC4 percentages are within bounds. + """ + tc3_valid = validator.tc_bandwidth_bound(bw_data['tc3_percentage'], 3) + tc4_valid = validator.tc_bandwidth_bound(bw_data['tc4_percentage'], 4) + + return tc3_valid and tc4_valid + + +def run_bandwidth_distribution_test(cfg, set_tc_mapping): + """ + Runs parallel iperf3 tests for both TCs and collects results. + """ + setup_test_environment(cfg, set_tc_mapping) + bandwidths = run_bandwidth_test() + bw_data = calculate_bandwidth_percentages(bandwidths) + test_name = "with TC mapping" if set_tc_mapping else "without TC mapping" + print_bandwidth_results(bw_data, test_name) + + verify_total_bandwidth(bw_data, cfg.bw_validator) + + return check_bandwidth_distribution(bw_data, cfg.bw_validator) + + +def test_no_tc_mapping_bandwidth(cfg): + """ + Verifies that bandwidth is not split 80/20 without traffic class mapping. + """ + pass_bw_msg = "Bandwidth is NOT distributed as 80/20 without TC mapping" + fail_bw_msg = "Bandwidth matched 80/20 split without TC mapping" + is_mlx5 = "driver: mlx5" in ethtool(f"-i {cfg.ifname}").stdout + + if run_bandwidth_distribution_test(cfg, set_tc_mapping=False): + if is_mlx5: + raise KsftXfailEx(fail_bw_msg) + raise KsftFailEx(fail_bw_msg) + if is_mlx5: + raise KsftFailEx("mlx5 behavior changed:" + pass_bw_msg) + ksft_pr(pass_bw_msg) + + +def test_tc_mapping_bandwidth(cfg): + """ + Verifies that bandwidth is correctly split 80/20 between TC3 and TC4 + when traffic class mapping is set. + """ + if run_bandwidth_distribution_test(cfg, set_tc_mapping=True): + ksft_pr("Bandwidth is distributed as 80/20 with TC mapping") + else: + raise KsftFailEx("Bandwidth did not match 80/20 split with TC mapping") + + +def main() -> None: + """ + Main entry point for running the test cases. + """ + with NetDrvEpEnv(__file__, nsim_test=False) as cfg: + cfg.devnl = DevlinkFamily() + + cfg.pci = os.path.basename( + os.path.realpath(f"/sys/class/net/{cfg.ifname}/device") + ) + if not cfg.pci: + raise KsftSkipEx("Could not get PCI address of the interface") + cfg.require_cmd("iperf3", local=True, remote=True) + + cfg.bw_validator = BandwidthValidator() + + cases = [test_no_tc_mapping_bandwidth, test_tc_mapping_bandwidth] + + ksft_run(cases=cases, args=(cfg,)) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py index 7947650210a0..baa2f24240ba 100755 --- a/tools/testing/selftests/drivers/net/hw/devmem.py +++ b/tools/testing/selftests/drivers/net/hw/devmem.py @@ -51,15 +51,14 @@ def check_tx(cfg) -> None: @ksft_disruptive def check_tx_chunks(cfg) -> None: - cfg.require_ipver("6") require_devmem(cfg) port = rand_port() - listen_cmd = f"socat -U - TCP6-LISTEN:{port}" + listen_cmd = f"socat -U - TCP{cfg.addr_ipver}-LISTEN:{port}" with bkg(listen_cmd, exit_wait=True) as socat: wait_port_listen(port) - cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_remote} -f {cfg.ifname} -s {cfg.addr_v['6']} -p {port} -z 3", host=cfg.remote, shell=True) + cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_remote} -f {cfg.ifname} -s {cfg.addr} -p {port} -z 3", host=cfg.remote, shell=True) ksft_eq(socat.stdout.strip(), "hello\nworld") diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py index 9c03fd777f3d..712c806508b5 100755 --- a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py +++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py @@ -3,37 +3,37 @@ import re from os import path -from lib.py import ksft_run, ksft_exit +from lib.py import ksft_run, ksft_exit, KsftSkipEx from lib.py import NetDrvEpEnv from lib.py import bkg, cmd, defer, ethtool, rand_port, wait_port_listen def _get_current_settings(cfg): - output = ethtool(f"-g {cfg.ifname}", json=True, host=cfg.remote)[0] + output = ethtool(f"-g {cfg.ifname}", json=True)[0] return (output['rx'], output['hds-thresh']) def _get_combined_channels(cfg): - output = ethtool(f"-l {cfg.ifname}", host=cfg.remote).stdout + output = ethtool(f"-l {cfg.ifname}").stdout values = re.findall(r'Combined:\s+(\d+)', output) return int(values[1]) def _create_rss_ctx(cfg, chan): - output = ethtool(f"-X {cfg.ifname} context new start {chan} equal 1", host=cfg.remote).stdout + output = ethtool(f"-X {cfg.ifname} context new start {chan} equal 1").stdout values = re.search(r'New RSS context is (\d+)', output).group(1) ctx_id = int(values) - return (ctx_id, defer(ethtool, f"-X {cfg.ifname} delete context {ctx_id}", host=cfg.remote)) + return (ctx_id, defer(ethtool, f"-X {cfg.ifname} delete context {ctx_id}")) def _set_flow_rule(cfg, port, chan): - output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {port} action {chan}", host=cfg.remote).stdout + output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {port} action {chan}").stdout values = re.search(r'ID (\d+)', output).group(1) return int(values) def _set_flow_rule_rss(cfg, port, ctx_id): - output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {port} context {ctx_id}", host=cfg.remote).stdout + output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {port} context {ctx_id}").stdout values = re.search(r'ID (\d+)', output).group(1) return int(values) @@ -47,26 +47,26 @@ def test_zcrx(cfg) -> None: (rx_ring, hds_thresh) = _get_current_settings(cfg) port = rand_port() - ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote) + ethtool(f"-G {cfg.ifname} tcp-data-split on") + defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto") - ethtool(f"-G {cfg.ifname} hds-thresh 0", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}", host=cfg.remote) + ethtool(f"-G {cfg.ifname} hds-thresh 0") + defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}") - ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote) + ethtool(f"-G {cfg.ifname} rx 64") + defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}") - ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote) - defer(ethtool, f"-X {cfg.ifname} default", host=cfg.remote) + ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}") + defer(ethtool, f"-X {cfg.ifname} default") flow_rule_id = _set_flow_rule(cfg, port, combined_chans - 1) - defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote) + defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}") - rx_cmd = f"{cfg.bin_remote} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1}" - tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p {port} -l 12840" - with bkg(rx_cmd, host=cfg.remote, exit_wait=True): - wait_port_listen(port, proto="tcp", host=cfg.remote) - cmd(tx_cmd) + rx_cmd = f"{cfg.bin_local} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1}" + tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {port} -l 12840" + with bkg(rx_cmd, exit_wait=True): + wait_port_listen(port, proto="tcp") + cmd(tx_cmd, host=cfg.remote) def test_zcrx_oneshot(cfg) -> None: @@ -78,26 +78,26 @@ def test_zcrx_oneshot(cfg) -> None: (rx_ring, hds_thresh) = _get_current_settings(cfg) port = rand_port() - ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote) + ethtool(f"-G {cfg.ifname} tcp-data-split on") + defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto") - ethtool(f"-G {cfg.ifname} hds-thresh 0", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}", host=cfg.remote) + ethtool(f"-G {cfg.ifname} hds-thresh 0") + defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}") - ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote) + ethtool(f"-G {cfg.ifname} rx 64") + defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}") - ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote) - defer(ethtool, f"-X {cfg.ifname} default", host=cfg.remote) + ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}") + defer(ethtool, f"-X {cfg.ifname} default") flow_rule_id = _set_flow_rule(cfg, port, combined_chans - 1) - defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote) + defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}") - rx_cmd = f"{cfg.bin_remote} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1} -o 4" - tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p {port} -l 4096 -z 16384" - with bkg(rx_cmd, host=cfg.remote, exit_wait=True): - wait_port_listen(port, proto="tcp", host=cfg.remote) - cmd(tx_cmd) + rx_cmd = f"{cfg.bin_local} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1} -o 4" + tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {port} -l 4096 -z 16384" + with bkg(rx_cmd, exit_wait=True): + wait_port_listen(port, proto="tcp") + cmd(tx_cmd, host=cfg.remote) def test_zcrx_rss(cfg) -> None: @@ -109,27 +109,27 @@ def test_zcrx_rss(cfg) -> None: (rx_ring, hds_thresh) = _get_current_settings(cfg) port = rand_port() - ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote) + ethtool(f"-G {cfg.ifname} tcp-data-split on") + defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto") - ethtool(f"-G {cfg.ifname} hds-thresh 0", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}", host=cfg.remote) + ethtool(f"-G {cfg.ifname} hds-thresh 0") + defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}") - ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote) - defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote) + ethtool(f"-G {cfg.ifname} rx 64") + defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}") - ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote) - defer(ethtool, f"-X {cfg.ifname} default", host=cfg.remote) + ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}") + defer(ethtool, f"-X {cfg.ifname} default") (ctx_id, delete_ctx) = _create_rss_ctx(cfg, combined_chans - 1) flow_rule_id = _set_flow_rule_rss(cfg, port, ctx_id) - defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote) + defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}") - rx_cmd = f"{cfg.bin_remote} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1}" - tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p {port} -l 12840" - with bkg(rx_cmd, host=cfg.remote, exit_wait=True): - wait_port_listen(port, proto="tcp", host=cfg.remote) - cmd(tx_cmd) + rx_cmd = f"{cfg.bin_local} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1}" + tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {port} -l 12840" + with bkg(rx_cmd, exit_wait=True): + wait_port_listen(port, proto="tcp") + cmd(tx_cmd, host=cfg.remote) def main() -> None: diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py index b582885786f5..1462a339a74b 100644 --- a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py @@ -7,8 +7,25 @@ KSFT_DIR = (Path(__file__).parent / "../../../../..").resolve() try: sys.path.append(KSFT_DIR.as_posix()) + from net.lib.py import * from drivers.net.lib.py import * + + # Import one by one to avoid pylint false positives + from net.lib.py import EthtoolFamily, NetdevFamily, NetshaperFamily, \ + NlError, RtnlFamily, DevlinkFamily + from net.lib.py import CmdExitFailure + from net.lib.py import bkg, cmd, defer, ethtool, fd_read_timeout, ip, \ + rand_port, tool, wait_port_listen + from net.lib.py import fd_read_timeout + from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx + from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \ + ksft_setup + from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \ + ksft_ne, ksft_not_in, ksft_raises, ksft_true + from net.lib.py import NetNSEnter + from drivers.net.lib.py import GenerateTraffic + from drivers.net.lib.py import NetDrvEnv, NetDrvEpEnv except ModuleNotFoundError as e: ksft_pr("Failed importing `net` library from kernel sources") ksft_pr(str(e)) diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c index 02e4d3d7ded2..72f828021f83 100644 --- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c +++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c @@ -526,12 +526,10 @@ static struct netdev_queue_id *create_queues(void) struct netdev_queue_id *queues; size_t i = 0; - queues = calloc(num_queues, sizeof(*queues)); + queues = netdev_queue_id_alloc(num_queues); for (i = 0; i < num_queues; i++) { - queues[i]._present.type = 1; - queues[i]._present.id = 1; - queues[i].type = NETDEV_QUEUE_TYPE_RX; - queues[i].id = start_queue + i; + netdev_queue_id_set_type(&queues[i], NETDEV_QUEUE_TYPE_RX); + netdev_queue_id_set_id(&queues[i], start_queue + i); } return queues; @@ -852,7 +850,6 @@ static int do_client(struct memory_buffer *mem) ssize_t line_size = 0; struct cmsghdr *cmsg; char *line = NULL; - unsigned long mid; size_t len = 0; int socket_fd; __u32 ddmabuf; diff --git a/tools/testing/selftests/drivers/net/hw/rss_api.py b/tools/testing/selftests/drivers/net/hw/rss_api.py new file mode 100755 index 000000000000..19847f3d4a00 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/rss_api.py @@ -0,0 +1,476 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +API level tests for RSS (mostly Netlink vs IOCTL). +""" + +import errno +import glob +import random +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_is, ksft_ne, ksft_raises +from lib.py import KsftSkipEx, KsftFailEx +from lib.py import defer, ethtool, CmdExitFailure +from lib.py import EthtoolFamily, NlError +from lib.py import NetDrvEnv + + +def _require_2qs(cfg): + qcnt = len(glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*")) + if qcnt < 2: + raise KsftSkipEx(f"Local has only {qcnt} queues") + return qcnt + + +def _ethtool_create(cfg, act, opts): + output = ethtool(f"{act} {cfg.ifname} {opts}").stdout + # Output will be something like: "New RSS context is 1" or + # "Added rule with ID 7", we want the integer from the end + return int(output.split()[-1]) + + +def _ethtool_get_cfg(cfg, fl_type, to_nl=False): + descr = ethtool(f"-n {cfg.ifname} rx-flow-hash {fl_type}").stdout + + if to_nl: + converter = { + "IP SA": "ip-src", + "IP DA": "ip-dst", + "L4 bytes 0 & 1 [TCP/UDP src port]": "l4-b-0-1", + "L4 bytes 2 & 3 [TCP/UDP dst port]": "l4-b-2-3", + } + + ret = set() + else: + converter = { + "IP SA": "s", + "IP DA": "d", + "L3 proto": "t", + "L4 bytes 0 & 1 [TCP/UDP src port]": "f", + "L4 bytes 2 & 3 [TCP/UDP dst port]": "n", + } + + ret = "" + + for line in descr.split("\n")[1:-2]: + # if this raises we probably need to add more keys to converter above + if to_nl: + ret.add(converter[line]) + else: + ret += converter[line] + return ret + + +def test_rxfh_nl_set_fail(cfg): + """ + Test error path of Netlink SET. + """ + _require_2qs(cfg) + + ethnl = EthtoolFamily() + ethnl.ntf_subscribe("monitor") + + with ksft_raises(NlError): + ethnl.rss_set({"header": {"dev-name": "lo"}, + "indir": None}) + + with ksft_raises(NlError): + ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "indir": [100000]}) + ntf = next(ethnl.poll_ntf(duration=0.2), None) + ksft_is(ntf, None) + + +def test_rxfh_nl_set_indir(cfg): + """ + Test setting indirection table via Netlink. + """ + qcnt = _require_2qs(cfg) + + # Test some SETs with a value + reset = defer(cfg.ethnl.rss_set, + {"header": {"dev-index": cfg.ifindex}, "indir": None}) + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "indir": [1]}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(set(rss.get("indir", [-1])), {1}) + + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "indir": [0, 1]}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(set(rss.get("indir", [-1])), {0, 1}) + + # Make sure we can't set the queue count below max queue used + with ksft_raises(CmdExitFailure): + ethtool(f"-L {cfg.ifname} combined 0 rx 1") + with ksft_raises(CmdExitFailure): + ethtool(f"-L {cfg.ifname} combined 1 rx 0") + + # Test reset back to default + reset.exec() + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(set(rss.get("indir", [-1])), set(range(qcnt))) + + +def test_rxfh_nl_set_indir_ctx(cfg): + """ + Test setting indirection table for a custom context via Netlink. + """ + _require_2qs(cfg) + + # Get setting for ctx 0, we'll make sure they don't get clobbered + dflt = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + + # Create context + ctx_id = _ethtool_create(cfg, "-X", "context new") + defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete") + + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "context": ctx_id, "indir": [1]}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}, + "context": ctx_id}) + ksft_eq(set(rss.get("indir", [-1])), {1}) + + ctx0 = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(ctx0, dflt) + + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "context": ctx_id, "indir": [0, 1]}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}, + "context": ctx_id}) + ksft_eq(set(rss.get("indir", [-1])), {0, 1}) + + ctx0 = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(ctx0, dflt) + + # Make sure we can't set the queue count below max queue used + with ksft_raises(CmdExitFailure): + ethtool(f"-L {cfg.ifname} combined 0 rx 1") + with ksft_raises(CmdExitFailure): + ethtool(f"-L {cfg.ifname} combined 1 rx 0") + + +def test_rxfh_indir_ntf(cfg): + """ + Check that Netlink notifications are generated when RSS indirection + table was modified. + """ + _require_2qs(cfg) + + ethnl = EthtoolFamily() + ethnl.ntf_subscribe("monitor") + + ethtool(f"--disable-netlink -X {cfg.ifname} weight 0 1") + reset = defer(ethtool, f"-X {cfg.ifname} default") + + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("No notification received") + ksft_eq(ntf["name"], "rss-ntf") + ksft_eq(set(ntf["msg"]["indir"]), {1}) + + reset.exec() + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("No notification received after reset") + ksft_eq(ntf["name"], "rss-ntf") + ksft_is(ntf["msg"].get("context"), None) + ksft_ne(set(ntf["msg"]["indir"]), {1}) + + +def test_rxfh_indir_ctx_ntf(cfg): + """ + Check that Netlink notifications are generated when RSS indirection + table was modified on an additional RSS context. + """ + _require_2qs(cfg) + + ctx_id = _ethtool_create(cfg, "-X", "context new") + defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete") + + ethnl = EthtoolFamily() + ethnl.ntf_subscribe("monitor") + + ethtool(f"--disable-netlink -X {cfg.ifname} context {ctx_id} weight 0 1") + + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("No notification received") + ksft_eq(ntf["name"], "rss-ntf") + ksft_eq(ntf["msg"].get("context"), ctx_id) + ksft_eq(set(ntf["msg"]["indir"]), {1}) + + +def test_rxfh_nl_set_key(cfg): + """ + Test setting hashing key via Netlink. + """ + + dflt = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + defer(cfg.ethnl.rss_set, + {"header": {"dev-index": cfg.ifindex}, + "hkey": dflt["hkey"], "indir": None}) + + # Empty key should error out + with ksft_raises(NlError) as cm: + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "hkey": None}) + ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.hkey') + + # Set key to random + mod = random.randbytes(len(dflt["hkey"])) + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "hkey": mod}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(rss.get("hkey", [-1]), mod) + + # Set key to random and indir tbl to something at once + mod = random.randbytes(len(dflt["hkey"])) + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "indir": [0, 1], "hkey": mod}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(rss.get("hkey", [-1]), mod) + ksft_eq(set(rss.get("indir", [-1])), {0, 1}) + + +def test_rxfh_fields(cfg): + """ + Test reading Rx Flow Hash over Netlink. + """ + + flow_types = ["tcp4", "tcp6", "udp4", "udp6"] + ethnl = EthtoolFamily() + + cfg_nl = ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + for fl_type in flow_types: + one = _ethtool_get_cfg(cfg, fl_type, to_nl=True) + ksft_eq(one, cfg_nl["flow-hash"][fl_type], + comment="Config for " + fl_type) + + +def test_rxfh_fields_set(cfg): + """ Test configuring Rx Flow Hash over Netlink. """ + + flow_types = ["tcp4", "tcp6", "udp4", "udp6"] + + # Collect current settings + cfg_old = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + # symmetric hashing is config-order-sensitive make sure we leave + # symmetric mode, or make the flow-hash sym-compatible first + changes = [{"flow-hash": cfg_old["flow-hash"],}, + {"input-xfrm": cfg_old.get("input-xfrm", {}),}] + if cfg_old.get("input-xfrm"): + changes = list(reversed(changes)) + for old in changes: + defer(cfg.ethnl.rss_set, {"header": {"dev-index": cfg.ifindex},} | old) + + # symmetric hashing prevents some of the configs below + if cfg_old.get("input-xfrm"): + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "input-xfrm": {}}) + + for fl_type in flow_types: + cur = _ethtool_get_cfg(cfg, fl_type) + if cur == "sdfn": + change_nl = {"ip-src", "ip-dst"} + change_ic = "sd" + else: + change_nl = {"l4-b-0-1", "l4-b-2-3", "ip-src", "ip-dst"} + change_ic = "sdfn" + + cfg.ethnl.rss_set({ + "header": {"dev-index": cfg.ifindex}, + "flow-hash": {fl_type: change_nl} + }) + reset = defer(ethtool, f"--disable-netlink -N {cfg.ifname} " + f"rx-flow-hash {fl_type} {cur}") + + cfg_nl = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(change_nl, cfg_nl["flow-hash"][fl_type], + comment=f"Config for {fl_type} over Netlink") + cfg_ic = _ethtool_get_cfg(cfg, fl_type) + ksft_eq(change_ic, cfg_ic, + comment=f"Config for {fl_type} over IOCTL") + + reset.exec() + cfg_nl = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(cfg_old["flow-hash"][fl_type], cfg_nl["flow-hash"][fl_type], + comment=f"Un-config for {fl_type} over Netlink") + cfg_ic = _ethtool_get_cfg(cfg, fl_type) + ksft_eq(cur, cfg_ic, comment=f"Un-config for {fl_type} over IOCTL") + + # Try to set multiple at once, the defer was already installed at the start + change = {"ip-src"} + if change == cfg_old["flow-hash"]["tcp4"]: + change = {"ip-dst"} + cfg.ethnl.rss_set({ + "header": {"dev-index": cfg.ifindex}, + "flow-hash": {x: change for x in flow_types} + }) + + cfg_nl = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + for fl_type in flow_types: + ksft_eq(change, cfg_nl["flow-hash"][fl_type], + comment=f"multi-config for {fl_type} over Netlink") + + +def test_rxfh_fields_set_xfrm(cfg): + """ Test changing Rx Flow Hash vs xfrm_input at once. """ + + def set_rss(cfg, xfrm, fh): + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "input-xfrm": xfrm, "flow-hash": fh}) + + # Install the reset handler + cfg_old = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + # symmetric hashing is config-order-sensitive make sure we leave + # symmetric mode, or make the flow-hash sym-compatible first + changes = [{"flow-hash": cfg_old["flow-hash"],}, + {"input-xfrm": cfg_old.get("input-xfrm", {}),}] + if cfg_old.get("input-xfrm"): + changes = list(reversed(changes)) + for old in changes: + defer(cfg.ethnl.rss_set, {"header": {"dev-index": cfg.ifindex},} | old) + + # Make sure we start with input-xfrm off, and tcp4 config non-sym + set_rss(cfg, {}, {}) + set_rss(cfg, {}, {"tcp4": {"ip-src"}}) + + # Setting sym and fixing tcp4 config not expected to pass right now + with ksft_raises(NlError): + set_rss(cfg, {"sym-xor"}, {"tcp4": {"ip-src", "ip-dst"}}) + # One at a time should work, hopefully + set_rss(cfg, 0, {"tcp4": {"ip-src", "ip-dst"}}) + no_support = False + try: + set_rss(cfg, {"sym-xor"}, {}) + except NlError: + try: + set_rss(cfg, {"sym-or-xor"}, {}) + except NlError: + no_support = True + if no_support: + raise KsftSkipEx("no input-xfrm supported") + # Disabling two at once should not work either without kernel changes + with ksft_raises(NlError): + set_rss(cfg, {}, {"tcp4": {"ip-src"}}) + + +def test_rxfh_fields_ntf(cfg): + """ Test Rx Flow Hash notifications. """ + + cur = _ethtool_get_cfg(cfg, "tcp4") + if cur == "sdfn": + change = {"ip-src", "ip-dst"} + else: + change = {"l4-b-0-1", "l4-b-2-3", "ip-src", "ip-dst"} + + ethnl = EthtoolFamily() + ethnl.ntf_subscribe("monitor") + + ethnl.rss_set({ + "header": {"dev-index": cfg.ifindex}, + "flow-hash": {"tcp4": change} + }) + reset = defer(ethtool, + f"--disable-netlink -N {cfg.ifname} rx-flow-hash tcp4 {cur}") + + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("No notification received after IOCTL change") + ksft_eq(ntf["name"], "rss-ntf") + ksft_eq(ntf["msg"]["flow-hash"]["tcp4"], change) + ksft_eq(next(ethnl.poll_ntf(duration=0.01), None), None) + + reset.exec() + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("No notification received after Netlink change") + ksft_eq(ntf["name"], "rss-ntf") + ksft_ne(ntf["msg"]["flow-hash"]["tcp4"], change) + ksft_eq(next(ethnl.poll_ntf(duration=0.01), None), None) + + +def test_rss_ctx_add(cfg): + """ Test creating an additional RSS context via Netlink """ + + _require_2qs(cfg) + + # Test basic creation + ctx = cfg.ethnl.rss_create_act({"header": {"dev-index": cfg.ifindex}}) + d = defer(ethtool, f"-X {cfg.ifname} context {ctx.get('context')} delete") + ksft_ne(ctx.get("context", 0), 0) + ksft_ne(set(ctx.get("indir", [0])), {0}, + comment="Driver should init the indirection table") + + # Try requesting the ID we just got allocated + with ksft_raises(NlError) as cm: + ctx = cfg.ethnl.rss_create_act({ + "header": {"dev-index": cfg.ifindex}, + "context": ctx.get("context"), + }) + ethtool(f"-X {cfg.ifname} context {ctx.get('context')} delete") + d.exec() + ksft_eq(cm.exception.nl_msg.error, -errno.EBUSY) + + # Test creating with a specified RSS table, and context ID + ctx_id = ctx.get("context") + ctx = cfg.ethnl.rss_create_act({ + "header": {"dev-index": cfg.ifindex}, + "context": ctx_id, + "indir": [1], + }) + ethtool(f"-X {cfg.ifname} context {ctx.get('context')} delete") + ksft_eq(ctx.get("context"), ctx_id) + ksft_eq(set(ctx.get("indir", [0])), {1}) + + +def test_rss_ctx_ntf(cfg): + """ Test notifications for creating additional RSS contexts """ + + ethnl = EthtoolFamily() + ethnl.ntf_subscribe("monitor") + + # Create / delete via Netlink + ctx = cfg.ethnl.rss_create_act({"header": {"dev-index": cfg.ifindex}}) + cfg.ethnl.rss_delete_act({ + "header": {"dev-index": cfg.ifindex}, + "context": ctx["context"], + }) + + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("[NL] No notification after context creation") + ksft_eq(ntf["name"], "rss-create-ntf") + ksft_eq(ctx, ntf["msg"]) + + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("[NL] No notification after context deletion") + ksft_eq(ntf["name"], "rss-delete-ntf") + + # Create / deleve via IOCTL + ctx_id = _ethtool_create(cfg, "--disable-netlink -X", "context new") + ethtool(f"--disable-netlink -X {cfg.ifname} context {ctx_id} delete") + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("[IOCTL] No notification after context creation") + ksft_eq(ntf["name"], "rss-create-ntf") + + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("[IOCTL] No notification after context deletion") + ksft_eq(ntf["name"], "rss-delete-ntf") + + +def main() -> None: + """ Ksft boiler plate main """ + + with NetDrvEnv(__file__, nsim_test=False) as cfg: + cfg.ethnl = EthtoolFamily() + ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, )) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py index 648ff50bc1c3..72880e388478 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py +++ b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py @@ -32,16 +32,16 @@ def test_rss_input_xfrm(cfg, ipver): if multiprocessing.cpu_count() < 2: raise KsftSkipEx("Need at least two CPUs to test symmetric RSS hash") - cfg.require_cmd("socat", remote=True) + cfg.require_cmd("socat", local=False, remote=True) if not hasattr(socket, "SO_INCOMING_CPU"): raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11") - input_xfrm = cfg.ethnl.rss_get( - {'header': {'dev-name': cfg.ifname}}).get('input-xfrm') + rss = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}}) + input_xfrm = set(filter(lambda x: 'sym' in x, rss.get('input-xfrm', {}))) # Check for symmetric xor/or-xor - if not input_xfrm or (input_xfrm != 1 and input_xfrm != 2): + if not input_xfrm: raise KsftSkipEx("Symmetric RSS hash not requested") cpus = set() diff --git a/tools/testing/selftests/drivers/net/hw/tso.py b/tools/testing/selftests/drivers/net/hw/tso.py index 3370827409aa..c13dd5efa27a 100755 --- a/tools/testing/selftests/drivers/net/hw/tso.py +++ b/tools/testing/selftests/drivers/net/hw/tso.py @@ -34,7 +34,7 @@ def tcp_sock_get_retrans(sock): def run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso): - cfg.require_cmd("socat", remote=True) + cfg.require_cmd("socat", local=False, remote=True) port = rand_port() listen_cmd = f"socat -{ipver} -t 2 -u TCP-LISTEN:{port},reuseport /dev/null,ignoreeof" @@ -102,7 +102,7 @@ def build_tunnel(cfg, outer_ipver, tun_info): remote_addr = cfg.remote_addr_v[outer_ipver] tun_type = tun_info[0] - tun_arg = tun_info[2] + tun_arg = tun_info[1] ip(f"link add {tun_type}-ksft type {tun_type} {tun_arg} local {local_addr} remote {remote_addr} dev {cfg.ifname}") defer(ip, f"link del {tun_type}-ksft") ip(f"link set dev {tun_type}-ksft up") @@ -119,15 +119,30 @@ def build_tunnel(cfg, outer_ipver, tun_info): return remote_v4, remote_v6 +def restore_wanted_features(cfg): + features_cmd = "" + for feature in cfg.hw_features: + setting = "on" if feature in cfg.wanted_features else "off" + features_cmd += f" {feature} {setting}" + try: + ethtool(f"-K {cfg.ifname} {features_cmd}") + except Exception as e: + ksft_pr(f"WARNING: failure restoring wanted features: {e}") + + def test_builder(name, cfg, outer_ipver, feature, tun=None, inner_ipver=None): """Construct specific tests from the common template.""" def f(cfg): cfg.require_ipver(outer_ipver) + defer(restore_wanted_features, cfg) if not cfg.have_stat_super_count and \ not cfg.have_stat_wire_count: raise KsftSkipEx(f"Device does not support LSO queue stats") + if feature not in cfg.hw_features: + raise KsftSkipEx(f"Device does not support {feature}") + ipver = outer_ipver if tun: remote_v4, remote_v6 = build_tunnel(cfg, ipver, tun) @@ -136,36 +151,21 @@ def test_builder(name, cfg, outer_ipver, feature, tun=None, inner_ipver=None): remote_v4 = cfg.remote_addr_v["4"] remote_v6 = cfg.remote_addr_v["6"] - tun_partial = tun and tun[1] - # Tunnel which can silently fall back to gso-partial - has_gso_partial = tun and 'tx-gso-partial' in cfg.features - - # For TSO4 via partial we need mangleid - if ipver == "4" and feature in cfg.partial_features: - ksft_pr("Testing with mangleid enabled") - if 'tx-tcp-mangleid-segmentation' not in cfg.features: - ethtool(f"-K {cfg.ifname} tx-tcp-mangleid-segmentation on") - defer(ethtool, f"-K {cfg.ifname} tx-tcp-mangleid-segmentation off") - # First test without the feature enabled. ethtool(f"-K {cfg.ifname} {feature} off") - if has_gso_partial: - ethtool(f"-K {cfg.ifname} tx-gso-partial off") run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=False) - # Now test with the feature enabled. - # For compatible tunnels only - just GSO partial, not specific feature. - if has_gso_partial: + ethtool(f"-K {cfg.ifname} tx-gso-partial off") + ethtool(f"-K {cfg.ifname} tx-tcp-mangleid-segmentation off") + if feature in cfg.partial_features: ethtool(f"-K {cfg.ifname} tx-gso-partial on") - run_one_stream(cfg, ipver, remote_v4, remote_v6, - should_lso=tun_partial) + if ipver == "4": + ksft_pr("Testing with mangleid enabled") + ethtool(f"-K {cfg.ifname} tx-tcp-mangleid-segmentation on") # Full feature enabled. - if feature in cfg.features: - ethtool(f"-K {cfg.ifname} {feature} on") - run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=True) - else: - raise KsftXfailEx(f"Device does not support {feature}") + ethtool(f"-K {cfg.ifname} {feature} on") + run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=True) f.__name__ = name + ((outer_ipver + "_") if tun else "") + "ipv" + inner_ipver return f @@ -176,23 +176,39 @@ def query_nic_features(cfg) -> None: cfg.have_stat_super_count = False cfg.have_stat_wire_count = False - cfg.features = set() features = cfg.ethnl.features_get({"header": {"dev-index": cfg.ifindex}}) - for f in features["active"]["bits"]["bit"]: - cfg.features.add(f["name"]) + + cfg.wanted_features = set() + for f in features["wanted"]["bits"]["bit"]: + cfg.wanted_features.add(f["name"]) + + cfg.hw_features = set() + hw_all_features_cmd = "" + for f in features["hw"]["bits"]["bit"]: + if f.get("value", False): + feature = f["name"] + cfg.hw_features.add(feature) + hw_all_features_cmd += f" {feature} on" + try: + ethtool(f"-K {cfg.ifname} {hw_all_features_cmd}") + except Exception as e: + ksft_pr(f"WARNING: failure enabling all hw features: {e}") + ksft_pr("partial gso feature detection may be impacted") # Check which features are supported via GSO partial cfg.partial_features = set() - if 'tx-gso-partial' in cfg.features: + if 'tx-gso-partial' in cfg.hw_features: ethtool(f"-K {cfg.ifname} tx-gso-partial off") no_partial = set() features = cfg.ethnl.features_get({"header": {"dev-index": cfg.ifindex}}) for f in features["active"]["bits"]["bit"]: no_partial.add(f["name"]) - cfg.partial_features = cfg.features - no_partial + cfg.partial_features = cfg.hw_features - no_partial ethtool(f"-K {cfg.ifname} tx-gso-partial on") + restore_wanted_features(cfg) + stats = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True) if stats: if 'tx-hw-gso-packets' in stats[0]: @@ -211,13 +227,14 @@ def main() -> None: query_nic_features(cfg) test_info = ( - # name, v4/v6 ethtool_feature tun:(type, partial, args) - ("", "4", "tx-tcp-segmentation", None), - ("", "6", "tx-tcp6-segmentation", None), - ("vxlan", "", "tx-udp_tnl-segmentation", ("vxlan", True, "id 100 dstport 4789 noudpcsum")), - ("vxlan_csum", "", "tx-udp_tnl-csum-segmentation", ("vxlan", False, "id 100 dstport 4789 udpcsum")), - ("gre", "4", "tx-gre-segmentation", ("gre", False, "")), - ("gre", "6", "tx-gre-segmentation", ("ip6gre", False, "")), + # name, v4/v6 ethtool_feature tun:(type, args, inner ip versions) + ("", "4", "tx-tcp-segmentation", None), + ("", "6", "tx-tcp6-segmentation", None), + ("vxlan", "4", "tx-udp_tnl-segmentation", ("vxlan", "id 100 dstport 4789 noudpcsum", ("4", "6"))), + ("vxlan", "6", "tx-udp_tnl-segmentation", ("vxlan", "id 100 dstport 4789 udp6zerocsumtx udp6zerocsumrx", ("4", "6"))), + ("vxlan_csum", "", "tx-udp_tnl-csum-segmentation", ("vxlan", "id 100 dstport 4789 udpcsum", ("4", "6"))), + ("gre", "4", "tx-gre-segmentation", ("gre", "", ("4", "6"))), + ("gre", "6", "tx-gre-segmentation", ("ip6gre","", ("4", "6"))), ) cases = [] @@ -227,11 +244,13 @@ def main() -> None: if info[1] and outer_ipver != info[1]: continue - cases.append(test_builder(info[0], cfg, outer_ipver, info[2], - tun=info[3], inner_ipver="4")) if info[3]: - cases.append(test_builder(info[0], cfg, outer_ipver, info[2], - tun=info[3], inner_ipver="6")) + cases += [ + test_builder(info[0], cfg, outer_ipver, info[2], info[3], inner_ipver) + for inner_ipver in info[3][2] + ] + else: + cases.append(test_builder(info[0], cfg, outer_ipver, info[2], None, outer_ipver)) ksft_run(cases=cases, args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/lib/py/__init__.py b/tools/testing/selftests/drivers/net/lib/py/__init__.py index 401e70f7f136..8711c67ad658 100644 --- a/tools/testing/selftests/drivers/net/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/lib/py/__init__.py @@ -7,7 +7,21 @@ KSFT_DIR = (Path(__file__).parent / "../../../..").resolve() try: sys.path.append(KSFT_DIR.as_posix()) + from net.lib.py import * + + # Import one by one to avoid pylint false positives + from net.lib.py import EthtoolFamily, NetdevFamily, NetshaperFamily, \ + NlError, RtnlFamily, DevlinkFamily + from net.lib.py import CmdExitFailure + from net.lib.py import bkg, cmd, bpftool, bpftrace, defer, ethtool, \ + fd_read_timeout, ip, rand_port, tool, wait_port_listen + from net.lib.py import fd_read_timeout + from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx + from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \ + ksft_setup + from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \ + ksft_ne, ksft_not_in, ksft_raises, ksft_true except ModuleNotFoundError as e: ksft_pr("Failed importing `net` library from kernel sources") ksft_pr(str(e)) diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py index 3bccddf8cbc5..1b8bd648048f 100644 --- a/tools/testing/selftests/drivers/net/lib/py/env.py +++ b/tools/testing/selftests/drivers/net/lib/py/env.py @@ -259,7 +259,7 @@ class NetDrvEpEnv(NetDrvEnvBase): if not self._require_cmd(comm, "local"): raise KsftSkipEx("Test requires command: " + comm) if remote: - if not self._require_cmd(comm, "remote"): + if not self._require_cmd(comm, "remote", host=self.remote): raise KsftSkipEx("Test requires (remote) command: " + comm) def wait_hw_stats_settle(self): diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py index d9c10613ae67..c4e808407cc4 100644 --- a/tools/testing/selftests/drivers/net/lib/py/load.py +++ b/tools/testing/selftests/drivers/net/lib/py/load.py @@ -1,21 +1,21 @@ # SPDX-License-Identifier: GPL-2.0 +import re import time from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen class GenerateTraffic: def __init__(self, env, port=None): - env.require_cmd("iperf3", remote=True) + env.require_cmd("iperf3", local=True, remote=True) self.env = env - if port is None: - port = rand_port() - self._iperf_server = cmd(f"iperf3 -s -1 -p {port}", background=True) - wait_port_listen(port) + self.port = rand_port() if port is None else port + self._iperf_server = cmd(f"iperf3 -s -1 -p {self.port}", background=True) + wait_port_listen(self.port) time.sleep(0.1) - self._iperf_client = cmd(f"iperf3 -c {env.addr} -P 16 -p {port} -t 86400", + self._iperf_client = cmd(f"iperf3 -c {env.addr} -P 16 -p {self.port} -t 86400", background=True, host=env.remote) # Wait for traffic to ramp up @@ -56,3 +56,16 @@ class GenerateTraffic: ksft_pr(">> Server:") ksft_pr(self._iperf_server.stdout) ksft_pr(self._iperf_server.stderr) + self._wait_client_stopped() + + def _wait_client_stopped(self, sleep=0.005, timeout=5): + end = time.monotonic() + timeout + + live_port_pattern = re.compile(fr":{self.port:04X} 0[^6] ") + + while time.monotonic() < end: + data = cmd("cat /proc/net/tcp*", host=self.env.remote).stdout + if not live_port_pattern.search(data): + return + time.sleep(sleep) + raise Exception(f"Waiting for client to stop timed out after {timeout}s") diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh index 29b01b8e2215..b6071e80ebbb 100644 --- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh +++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh @@ -11,9 +11,11 @@ set -euo pipefail LIBDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") SRCIF="" # to be populated later -SRCIP=192.0.2.1 +SRCIP4="192.0.2.1" +SRCIP6="fc00::1" DSTIF="" # to be populated later -DSTIP=192.0.2.2 +DSTIP4="192.0.2.2" +DSTIP6="fc00::2" PORT="6666" MSG="netconsole selftest" @@ -80,7 +82,23 @@ function configure_ip() { ip link set "${SRCIF}" up } +function select_ipv4_or_ipv6() +{ + local VERSION=${1} + + if [[ "$VERSION" == "ipv6" ]] + then + DSTIP="${DSTIP6}" + SRCIP="${SRCIP6}" + else + DSTIP="${DSTIP4}" + SRCIP="${SRCIP4}" + fi +} + function set_network() { + local IP_VERSION=${1:-"ipv4"} + # setup_ns function is coming from lib.sh setup_ns NAMESPACE @@ -91,10 +109,13 @@ function set_network() { # Link both interfaces back to back link_ifaces + select_ipv4_or_ipv6 "${IP_VERSION}" configure_ip } function create_dynamic_target() { + local FORMAT=${1:-"extended"} + DSTMAC=$(ip netns exec "${NAMESPACE}" \ ip link show "${DSTIF}" | awk '/ether/ {print $2}') @@ -106,7 +127,33 @@ function create_dynamic_target() { echo "${DSTMAC}" > "${NETCONS_PATH}"/remote_mac echo "${SRCIF}" > "${NETCONS_PATH}"/dev_name + if [ "${FORMAT}" == "basic" ] + then + # Basic target does not support release + echo 0 > "${NETCONS_PATH}"/release + echo 0 > "${NETCONS_PATH}"/extended + elif [ "${FORMAT}" == "extended" ] + then + echo 1 > "${NETCONS_PATH}"/extended + fi + echo 1 > "${NETCONS_PATH}"/enabled + + # This will make sure that the kernel was able to + # load the netconsole driver configuration. The console message + # gets more organized/sequential as well. + sleep 1 +} + +# Generate the command line argument for netconsole following: +# netconsole=[+][src-port]@[src-ip]/[<dev>],[tgt-port]@<tgt-ip>/[tgt-macaddr] +function create_cmdline_str() { + DSTMAC=$(ip netns exec "${NAMESPACE}" \ + ip link show "${DSTIF}" | awk '/ether/ {print $2}') + SRCPORT="1514" + TGTPORT="6666" + + echo "netconsole=\"+${SRCPORT}@${SRCIP}/${SRCIF},${TGTPORT}@${DSTIP}/${DSTMAC}\"" } # Do not append the release to the header of the message @@ -116,16 +163,9 @@ function disable_release_append() { echo 1 > "${NETCONS_PATH}"/enabled } -function cleanup() { +function do_cleanup() { local NSIM_DEV_SYS_DEL="/sys/bus/netdevsim/del_device" - # delete netconsole dynamic reconfiguration - echo 0 > "${NETCONS_PATH}"/enabled - # Remove all the keys that got created during the selftest - find "${NETCONS_PATH}/userdata/" -mindepth 1 -type d -delete - # Remove the configfs entry - rmdir "${NETCONS_PATH}" - # Delete netdevsim devices echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_DEL" echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_DEL" @@ -137,6 +177,17 @@ function cleanup() { echo "${DEFAULT_PRINTK_VALUES}" > /proc/sys/kernel/printk } +function cleanup() { + # delete netconsole dynamic reconfiguration + echo 0 > "${NETCONS_PATH}"/enabled + # Remove all the keys that got created during the selftest + find "${NETCONS_PATH}/userdata/" -mindepth 1 -type d -delete + # Remove the configfs entry + rmdir "${NETCONS_PATH}" + + do_cleanup +} + function set_user_data() { if [[ ! -d "${NETCONS_PATH}""/userdata" ]] then @@ -152,18 +203,24 @@ function set_user_data() { function listen_port_and_save_to() { local OUTPUT=${1} + local IPVERSION=${2:-"ipv4"} + + if [ "${IPVERSION}" == "ipv4" ] + then + SOCAT_MODE="UDP-LISTEN" + else + SOCAT_MODE="UDP6-LISTEN" + fi + # Just wait for 2 seconds timeout 2 ip netns exec "${NAMESPACE}" \ - socat UDP-LISTEN:"${PORT}",fork "${OUTPUT}" + socat "${SOCAT_MODE}":"${PORT}",fork "${OUTPUT}" } -function validate_result() { +# Only validate that the message arrived properly +function validate_msg() { local TMPFILENAME="$1" - # TMPFILENAME will contain something like: - # 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM - # key=value - # Check if the file exists if [ ! -f "$TMPFILENAME" ]; then echo "FAIL: File was not generated." >&2 @@ -175,17 +232,32 @@ function validate_result() { cat "${TMPFILENAME}" >&2 exit "${ksft_fail}" fi +} - if ! grep -q "${USERDATA_KEY}=${USERDATA_VALUE}" "${TMPFILENAME}"; then - echo "FAIL: ${USERDATA_KEY}=${USERDATA_VALUE} not found in ${TMPFILENAME}" >&2 - cat "${TMPFILENAME}" >&2 - exit "${ksft_fail}" +# Validate the message and userdata +function validate_result() { + local TMPFILENAME="$1" + + # TMPFILENAME will contain something like: + # 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM + # key=value + + validate_msg "${TMPFILENAME}" + + # userdata is not supported on basic format target, + # thus, do not validate it. + if [ "${FORMAT}" != "basic" ]; + then + if ! grep -q "${USERDATA_KEY}=${USERDATA_VALUE}" "${TMPFILENAME}"; then + echo "FAIL: ${USERDATA_KEY}=${USERDATA_VALUE} not found in ${TMPFILENAME}" >&2 + cat "${TMPFILENAME}" >&2 + exit "${ksft_fail}" + fi fi # Delete the file once it is validated, otherwise keep it # for debugging purposes rm "${TMPFILENAME}" - exit "${ksft_pass}" } function check_for_dependencies() { @@ -209,6 +281,11 @@ function check_for_dependencies() { exit "${ksft_skip}" fi + if [ ! -f /proc/net/if_inet6 ]; then + echo "SKIP: IPv6 not configured. Check if CONFIG_IPV6 is enabled" >&2 + exit "${ksft_skip}" + fi + if [ ! -f "${NSIM_DEV_SYS_NEW}" ]; then echo "SKIP: file ${NSIM_DEV_SYS_NEW} does not exist. Check if CONFIG_NETDEVSIM is enabled" >&2 exit "${ksft_skip}" @@ -224,8 +301,15 @@ function check_for_dependencies() { exit "${ksft_skip}" fi - if ip addr list | grep -E "inet.*(${SRCIP}|${DSTIP})" 2> /dev/null; then - echo "SKIP: IPs already in use. Skipping it" >&2 + REGEXP4="inet.*(${SRCIP4}|${DSTIP4})" + REGEXP6="inet.*(${SRCIP6}|${DSTIP6})" + if ip addr list | grep -E "${REGEXP4}" 2> /dev/null; then + echo "SKIP: IPv4s already in use. Skipping it" >&2 + exit "${ksft_skip}" + fi + + if ip addr list | grep -E "${REGEXP6}" 2> /dev/null; then + echo "SKIP: IPv6s already in use. Skipping it" >&2 exit "${ksft_skip}" fi } @@ -239,10 +323,41 @@ function check_for_taskset() { # This is necessary if running multiple tests in a row function pkill_socat() { - PROCESS_NAME="socat UDP-LISTEN:6666,fork ${OUTPUT_FILE}" + PROCESS_NAME4="socat UDP-LISTEN:6666,fork ${OUTPUT_FILE}" + PROCESS_NAME6="socat UDP6-LISTEN:6666,fork ${OUTPUT_FILE}" # socat runs under timeout(1), kill it if it is still alive # do not fail if socat doesn't exist anymore set +e - pkill -f "${PROCESS_NAME}" + pkill -f "${PROCESS_NAME4}" + pkill -f "${PROCESS_NAME6}" set -e } + +# Check if netconsole was compiled as a module, otherwise exit +function check_netconsole_module() { + if modinfo netconsole | grep filename: | grep -q builtin + then + echo "SKIP: netconsole should be compiled as a module" >&2 + exit "${ksft_skip}" + fi +} + +# A wrapper to translate protocol version to udp version +function wait_for_port() { + local NAMESPACE=${1} + local PORT=${2} + IP_VERSION=${3} + + if [ "${IP_VERSION}" == "ipv6" ] + then + PROTOCOL="udp6" + else + PROTOCOL="udp" + fi + + wait_local_port_listen "${NAMESPACE}" "${PORT}" "${PROTOCOL}" + # even after the port is open, let's wait 1 second before writing + # otherwise the packet could be missed, and the test will fail. Happens + # more frequently on IPv6 + sleep 1 +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh index 899b6892603f..d7505b933aef 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh @@ -51,7 +51,7 @@ for current_test in ${TESTS:-$ALL_TESTS}; do fi ${current_test}_setup_prepare - setup_wait $num_netifs + setup_wait_n $num_netifs # Update target in case occupancy of a certain resource changed # following the test setup. target=$(${current_test}_get_target "$should_fail") diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh index 482ebb744eba..7b98cdd0580d 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh @@ -55,7 +55,7 @@ for current_test in ${TESTS:-$ALL_TESTS}; do continue fi ${current_test}_setup_prepare - setup_wait $num_netifs + setup_wait_n $num_netifs # Update target in case occupancy of a certain resource # changed following the test setup. target=$(${current_test}_get_target "$should_fail") diff --git a/tools/testing/selftests/drivers/net/napi_id.py b/tools/testing/selftests/drivers/net/napi_id.py index 356bac46ba04..d05eddcad539 100755 --- a/tools/testing/selftests/drivers/net/napi_id.py +++ b/tools/testing/selftests/drivers/net/napi_id.py @@ -7,10 +7,10 @@ from lib.py import bkg, cmd, rand_port, NetNSEnter def test_napi_id(cfg) -> None: port = rand_port() - listen_cmd = f"{cfg.test_dir}/napi_id_helper {cfg.addr_v['4']} {port}" + listen_cmd = f"{cfg.test_dir}/napi_id_helper {cfg.addr} {port}" with bkg(listen_cmd, ksft_wait=3) as server: - cmd(f"echo a | socat - TCP:{cfg.addr_v['4']}:{port}", host=cfg.remote, shell=True) + cmd(f"echo a | socat - TCP:{cfg.baddr}:{port}", host=cfg.remote, shell=True) ksft_eq(0, server.ret) diff --git a/tools/testing/selftests/drivers/net/napi_id_helper.c b/tools/testing/selftests/drivers/net/napi_id_helper.c index eecd610c2109..7f49ca6c8637 100644 --- a/tools/testing/selftests/drivers/net/napi_id_helper.c +++ b/tools/testing/selftests/drivers/net/napi_id_helper.c @@ -7,41 +7,58 @@ #include <unistd.h> #include <arpa/inet.h> #include <sys/socket.h> +#include <netdb.h> #include "../../net/lib/ksft.h" int main(int argc, char *argv[]) { - struct sockaddr_in address; + struct sockaddr_storage address; + struct addrinfo *result; + struct addrinfo hints; unsigned int napi_id; - unsigned int port; + socklen_t addr_len; socklen_t optlen; char buf[1024]; int opt = 1; + int family; int server; int client; int ret; - server = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); + memset(&hints, 0, sizeof(hints)); + hints.ai_family = AF_UNSPEC; + hints.ai_socktype = SOCK_STREAM; + hints.ai_flags = AI_PASSIVE; + + ret = getaddrinfo(argv[1], argv[2], &hints, &result); + if (ret != 0) { + fprintf(stderr, "getaddrinfo: %s\n", gai_strerror(ret)); + return 1; + } + + family = result->ai_family; + addr_len = result->ai_addrlen; + + server = socket(family, SOCK_STREAM, IPPROTO_TCP); if (server < 0) { perror("socket creation failed"); + freeaddrinfo(result); if (errno == EAFNOSUPPORT) return -1; return 1; } - port = atoi(argv[2]); - if (setsockopt(server, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt))) { perror("setsockopt"); + freeaddrinfo(result); return 1; } - address.sin_family = AF_INET; - inet_pton(AF_INET, argv[1], &address.sin_addr); - address.sin_port = htons(port); + memcpy(&address, result->ai_addr, result->ai_addrlen); + freeaddrinfo(result); - if (bind(server, (struct sockaddr *)&address, sizeof(address)) < 0) { + if (bind(server, (struct sockaddr *)&address, addr_len) < 0) { perror("bind failed"); return 1; } diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh index fe765da498e8..a3446b569976 100755 --- a/tools/testing/selftests/drivers/net/netcons_basic.sh +++ b/tools/testing/selftests/drivers/net/netcons_basic.sh @@ -32,21 +32,42 @@ check_for_dependencies echo "6 5" > /proc/sys/kernel/printk # Remove the namespace, interfaces and netconsole target on exit trap cleanup EXIT -# Create one namespace and two interfaces -set_network -# Create a dynamic target for netconsole -create_dynamic_target -# Set userdata "key" with the "value" value -set_user_data -# Listed for netconsole port inside the namespace and destination interface -listen_port_and_save_to "${OUTPUT_FILE}" & -# Wait for socat to start and listen to the port. -wait_local_port_listen "${NAMESPACE}" "${PORT}" udp -# Send the message -echo "${MSG}: ${TARGET}" > /dev/kmsg -# Wait until socat saves the file to disk -busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" -# Make sure the message was received in the dst part -# and exit -validate_result "${OUTPUT_FILE}" +# Run the test twice, with different format modes +for FORMAT in "basic" "extended" +do + for IP_VERSION in "ipv6" "ipv4" + do + echo "Running with target mode: ${FORMAT} (${IP_VERSION})" + # Create one namespace and two interfaces + set_network "${IP_VERSION}" + # Create a dynamic target for netconsole + create_dynamic_target "${FORMAT}" + # Only set userdata for extended format + if [ "$FORMAT" == "extended" ] + then + # Set userdata "key" with the "value" value + set_user_data + fi + # Listed for netconsole port inside the namespace and + # destination interface + listen_port_and_save_to "${OUTPUT_FILE}" "${IP_VERSION}" & + # Wait for socat to start and listen to the port. + wait_for_port "${NAMESPACE}" "${PORT}" "${IP_VERSION}" + # Send the message + echo "${MSG}: ${TARGET}" > /dev/kmsg + # Wait until socat saves the file to disk + busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" + + # Make sure the message was received in the dst part + # and exit + validate_result "${OUTPUT_FILE}" "${FORMAT}" + # kill socat in case it is still running + pkill_socat + cleanup + echo "${FORMAT} : ${IP_VERSION} : Test passed" >&2 + done +done + +trap - EXIT +exit "${ksft_pass}" diff --git a/tools/testing/selftests/drivers/net/netcons_cmdline.sh b/tools/testing/selftests/drivers/net/netcons_cmdline.sh new file mode 100755 index 000000000000..ad2fb8b1c463 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netcons_cmdline.sh @@ -0,0 +1,52 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 + +# This is a selftest to test cmdline arguments on netconsole. +# It exercises loading of netconsole from cmdline instead of the dynamic +# reconfiguration. This includes parsing the long netconsole= line and all the +# flow through init_netconsole(). +# +# Author: Breno Leitao <[email protected]> + +set -euo pipefail + +SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh + +check_netconsole_module + +modprobe netdevsim 2> /dev/null || true +rmmod netconsole 2> /dev/null || true + +# The content of kmsg will be save to the following file +OUTPUT_FILE="/tmp/${TARGET}" + +# Check for basic system dependency and exit if not found +# check_for_dependencies +# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5) +echo "6 5" > /proc/sys/kernel/printk +# Remove the namespace and network interfaces +trap do_cleanup EXIT +# Create one namespace and two interfaces +set_network +# Create the command line for netconsole, with the configuration from the +# function above +CMDLINE="$(create_cmdline_str)" + +# Load the module, with the cmdline set +modprobe netconsole "${CMDLINE}" + +# Listed for netconsole port inside the namespace and destination interface +listen_port_and_save_to "${OUTPUT_FILE}" & +# Wait for socat to start and listen to the port. +wait_local_port_listen "${NAMESPACE}" "${PORT}" udp +# Send the message +echo "${MSG}: ${TARGET}" > /dev/kmsg +# Wait until socat saves the file to disk +busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" +# Make sure the message was received in the dst part +# and exit +validate_msg "${OUTPUT_FILE}" + +exit "${ksft_pass}" diff --git a/tools/testing/selftests/drivers/net/netcons_sysdata.sh b/tools/testing/selftests/drivers/net/netcons_sysdata.sh index a737e377bf08..baf69031089e 100755 --- a/tools/testing/selftests/drivers/net/netcons_sysdata.sh +++ b/tools/testing/selftests/drivers/net/netcons_sysdata.sh @@ -53,6 +53,17 @@ function set_release() { echo 1 > "${NETCONS_PATH}/userdata/release_enabled" } +# Enable the msgid to be appended to sysdata +function set_msgid() { + if [[ ! -f "${NETCONS_PATH}/userdata/msgid_enabled" ]] + then + echo "Not able to enable msgid sysdata append. Configfs not available in ${NETCONS_PATH}/userdata/msgid_enabled" >&2 + exit "${ksft_skip}" + fi + + echo 1 > "${NETCONS_PATH}/userdata/msgid_enabled" +} + # Disable the sysdata cpu_nr feature function unset_cpu_nr() { echo 0 > "${NETCONS_PATH}/userdata/cpu_nr_enabled" @@ -67,6 +78,10 @@ function unset_release() { echo 0 > "${NETCONS_PATH}/userdata/release_enabled" } +function unset_msgid() { + echo 0 > "${NETCONS_PATH}/userdata/msgid_enabled" +} + # Test if MSG contains sysdata function validate_sysdata() { # OUTPUT_FILE will contain something like: @@ -74,6 +89,7 @@ function validate_sysdata() { # userdatakey=userdatavalue # cpu=X # taskname=<taskname> + # msgid=<id> # Echo is what this test uses to create the message. See runtest() # function @@ -104,6 +120,12 @@ function validate_sysdata() { exit "${ksft_fail}" fi + if ! grep -q "msgid=[0-9]\+$" "${OUTPUT_FILE}"; then + echo "FAIL: 'msgid=<id>' not found in ${OUTPUT_FILE}" >&2 + cat "${OUTPUT_FILE}" >&2 + exit "${ksft_fail}" + fi + rm "${OUTPUT_FILE}" pkill_socat } @@ -155,6 +177,12 @@ function validate_no_sysdata() { exit "${ksft_fail}" fi + if grep -q "msgid=" "${OUTPUT_FILE}"; then + echo "FAIL: 'msgid= found in ${OUTPUT_FILE}" >&2 + cat "${OUTPUT_FILE}" >&2 + exit "${ksft_fail}" + fi + rm "${OUTPUT_FILE}" } @@ -206,6 +234,7 @@ set_cpu_nr # Enable taskname to be appended to sysdata set_taskname set_release +set_msgid runtest # Make sure the message was received in the dst part # and exit @@ -235,6 +264,7 @@ MSG="Test #3 from CPU${CPU}" unset_cpu_nr unset_taskname unset_release +unset_msgid runtest # At this time, cpu= shouldn't be present in the msg validate_no_sysdata diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh index b5ea2526f23c..030762b203d7 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh @@ -40,6 +40,8 @@ fw_flash_test() return fi + echo "10"> $DEBUGFS_DIR/fw_update_flash_chunk_time_ms + devlink dev flash $DL_HANDLE file $DUMMYFILE check_err $? "Failed to flash with status updates on" @@ -608,6 +610,46 @@ rate_attr_parent_check() check_err $? "Unexpected parent attr value $api_value != $parent" } +rate_attr_tc_bw_check() +{ + local handle=$1 + local tc_bw=$2 + local debug_file=$3 + + local tc_bw_str="" + for bw in $tc_bw; do + local tc=${bw%%:*} + local value=${bw##*:} + tc_bw_str="$tc_bw_str $tc:$value" + done + tc_bw_str=${tc_bw_str# } + + rate_attr_set "$handle" tc-bw "$tc_bw_str" + check_err $? "Failed to set tc-bw values" + + for bw in $tc_bw; do + local tc=${bw%%:*} + local value=${bw##*:} + local debug_value + debug_value=$(cat "$debug_file"/tc"${tc}"_bw) + check_err $? "Failed to read tc-bw value from debugfs for tc$tc" + [ "$debug_value" == "$value" ] + check_err $? "Unexpected tc-bw debug value for tc$tc: $debug_value != $value" + done + + for bw in $tc_bw; do + local tc=${bw%%:*} + local expected_value=${bw##*:} + local api_value + api_value=$(rate_attr_get "$handle" tc_"$tc") + if [ "$api_value" = "null" ]; then + api_value=0 + fi + [ "$api_value" == "$expected_value" ] + check_err $? "Unexpected tc-bw value for tc$tc: $api_value != $expected_value" + done +} + rate_node_add() { local handle=$1 @@ -649,6 +691,13 @@ rate_test() rate=$(($rate+100)) done + local tc_bw="0:0 1:40 2:0 3:0 4:0 5:0 6:60 7:0" + for r_obj in $leafs + do + rate_attr_tc_bw_check "$r_obj" "$tc_bw" \ + "$DEBUGFS_DIR"/ports/"${r_obj##*/}" + done + local node1_name='group1' local node1="$DL_HANDLE/$node1_name" rate_node_add "$node1" @@ -666,6 +715,12 @@ rate_test() rate_attr_tx_rate_check $node1 tx_max $node_tx_max \ $DEBUGFS_DIR/rate_nodes/${node1##*/}/tx_max + + local tc_bw="0:20 1:0 2:0 3:0 4:0 5:20 6:60 7:0" + rate_attr_tc_bw_check $node1 "$tc_bw" \ + "$DEBUGFS_DIR"/rate_nodes/"${node1##*/}" + + rate_node_del "$node1" check_err $? "Failed to delete node $node1" local num_nodes=`rate_nodes_get $DL_HANDLE | wc -w` diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh index 92c2f0376c08..4c859ecdad94 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh @@ -266,7 +266,6 @@ for port in 0 1; do echo $NSIM_ID > /sys/bus/netdevsim/new_device else echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep echo 1 > $NSIM_DEV_SYS/new_port fi NSIM_NETDEV=`get_netdev_name old_netdevs` @@ -350,23 +349,11 @@ old_netdevs=$(ls /sys/class/net) port=0 echo $NSIM_ID > /sys/bus/netdevsim/new_device echo 0 > $NSIM_DEV_SYS/del_port -echo 1000 > $NSIM_DEV_DFS/udp_ports_sleep echo 0 > $NSIM_DEV_SYS/new_port NSIM_NETDEV=`get_netdev_name old_netdevs` msg="create VxLANs" -exp0=( 0 0 0 0 ) # sleep is longer than out wait -new_vxlan vxlan0 10000 $NSIM_NETDEV - -modprobe -r vxlan -modprobe -r udp_tunnel - -msg="remove tunnels" -exp0=( 0 0 0 0 ) -check_tables - -msg="create VxLANs" -exp0=( 0 0 0 0 ) # sleep is longer than out wait +exp0=( `mke 10000 1` 0 0 0 ) new_vxlan vxlan0 10000 $NSIM_NETDEV exp0=( 0 0 0 0 ) @@ -428,7 +415,6 @@ echo 0 > $NSIM_DEV_SYS/del_port for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port @@ -486,7 +472,6 @@ echo 1 > $NSIM_DEV_DFS/udp_ports_sync_all for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port @@ -543,7 +528,6 @@ echo 0 > $NSIM_DEV_SYS/del_port for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port @@ -573,7 +557,6 @@ echo 1 > $NSIM_DEV_DFS/udp_ports_ipv4_only for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port @@ -634,7 +617,6 @@ echo 0 > $NSIM_DEV_SYS/del_port for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port @@ -690,7 +672,6 @@ echo 0 > $NSIM_DEV_SYS/del_port for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port @@ -750,7 +731,6 @@ echo 0 > $NSIM_DEV_SYS/del_port for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port @@ -809,7 +789,6 @@ echo $NSIM_ID > /sys/bus/netdevsim/new_device echo 0 > $NSIM_DEV_SYS/del_port echo 0 > $NSIM_DEV_DFS/udp_ports_open_only -echo 1 > $NSIM_DEV_DFS/udp_ports_sleep echo 1 > $NSIM_DEV_DFS/udp_ports_shared old_netdevs=$(ls /sys/class/net) diff --git a/tools/testing/selftests/drivers/net/netpoll_basic.py b/tools/testing/selftests/drivers/net/netpoll_basic.py new file mode 100755 index 000000000000..408bd54d6779 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netpoll_basic.py @@ -0,0 +1,396 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# Author: Breno Leitao <[email protected]> +""" + This test aims to evaluate the netpoll polling mechanism (as in + netpoll_poll_dev()). It presents a complex scenario where the network + attempts to send a packet but fails, prompting it to poll the NIC from within + the netpoll TX side. + + This has been a crucial path in netpoll that was previously untested. Jakub + suggested using a single RX/TX queue, pushing traffic to the NIC, and then + sending netpoll messages (via netconsole) to trigger the poll. + + In parallel, bpftrace is used to detect if netpoll_poll_dev() was called. If + so, the test passes, otherwise it will be skipped. This test is very dependent on + the driver and environment, given we are trying to trigger a tricky scenario. +""" + +import errno +import logging +import os +import random +import string +import threading +import time +from typing import Optional + +from lib.py import ( + bpftrace, + CmdExitFailure, + defer, + ethtool, + GenerateTraffic, + ksft_exit, + ksft_pr, + ksft_run, + KsftFailEx, + KsftSkipEx, + NetDrvEpEnv, + KsftXfailEx, +) + +# Configure logging +logging.basicConfig( + level=logging.INFO, + format="%(asctime)s - %(levelname)s - %(message)s", +) + +NETCONSOLE_CONFIGFS_PATH: str = "/sys/kernel/config/netconsole" +NETCONS_REMOTE_PORT: int = 6666 +NETCONS_LOCAL_PORT: int = 1514 + +# Max number of netcons messages to send. Each iteration will setup +# netconsole and send MAX_WRITES messages +ITERATIONS: int = 20 +# Number of writes to /dev/kmsg per iteration +MAX_WRITES: int = 40 +# MAPS contains the information coming from bpftrace it will have only one +# key: "hits", which tells the number of times netpoll_poll_dev() was called +MAPS: dict[str, int] = {} +# Thread to run bpftrace in parallel +BPF_THREAD: Optional[threading.Thread] = None +# Time bpftrace will be running in parallel. +BPFTRACE_TIMEOUT: int = 10 + + +def ethtool_get_ringsize(interface_name: str) -> tuple[int, int]: + """ + Read the ringsize using ethtool. This will be used to restore it after the test + """ + try: + ethtool_result = ethtool(f"-g {interface_name}", json=True)[0] + rxs = ethtool_result["rx"] + txs = ethtool_result["tx"] + except (KeyError, IndexError) as exception: + raise KsftSkipEx( + f"Failed to read RX/TX ringsize: {exception}. Not going to mess with them." + ) from exception + + return rxs, txs + + +def ethtool_set_ringsize(interface_name: str, ring_size: tuple[int, int]) -> bool: + """Try to the number of RX and TX ringsize.""" + rxs = ring_size[0] + txs = ring_size[1] + + logging.debug("Setting ring size to %d/%d", rxs, txs) + try: + ethtool(f"-G {interface_name} rx {rxs} tx {txs}") + except CmdExitFailure: + # This might fail on real device, retry with a higher value, + # worst case, keep it as it is. + return False + + return True + + +def ethtool_get_queues_cnt(interface_name: str) -> tuple[int, int, int]: + """Read the number of RX, TX and combined queues using ethtool""" + + try: + ethtool_result = ethtool(f"-l {interface_name}", json=True)[0] + rxq = ethtool_result.get("rx", -1) + txq = ethtool_result.get("tx", -1) + combined = ethtool_result.get("combined", -1) + + except IndexError as exception: + raise KsftSkipEx( + f"Failed to read queues numbers: {exception}. Not going to mess with them." + ) from exception + + return rxq, txq, combined + + +def ethtool_set_queues_cnt(interface_name: str, queues: tuple[int, int, int]) -> None: + """Set the number of RX, TX and combined queues using ethtool""" + rxq, txq, combined = queues + + cmdline = f"-L {interface_name}" + + if rxq != -1: + cmdline += f" rx {rxq}" + if txq != -1: + cmdline += f" tx {txq}" + if combined != -1: + cmdline += f" combined {combined}" + + logging.debug("calling: ethtool %s", cmdline) + + try: + ethtool(cmdline) + except CmdExitFailure as exception: + raise KsftSkipEx( + f"Failed to configure RX/TX queues: {exception}. Ethtool not available?" + ) from exception + + +def netcons_generate_random_target_name() -> str: + """Generate a random target name starting with 'netcons'""" + random_suffix = "".join(random.choices(string.ascii_lowercase + string.digits, k=8)) + return f"netcons_{random_suffix}" + + +def netcons_create_target( + config_data: dict[str, str], + target_name: str, +) -> None: + """Create a netconsole dynamic target against the interfaces""" + logging.debug("Using netconsole name: %s", target_name) + try: + os.makedirs(f"{NETCONSOLE_CONFIGFS_PATH}/{target_name}", exist_ok=True) + logging.debug( + "Created target directory: %s/%s", NETCONSOLE_CONFIGFS_PATH, target_name + ) + except OSError as exception: + if exception.errno != errno.EEXIST: + raise KsftFailEx( + f"Failed to create netconsole target directory: {exception}" + ) from exception + + try: + for key, value in config_data.items(): + path = f"{NETCONSOLE_CONFIGFS_PATH}/{target_name}/{key}" + logging.debug("Writing %s to %s", key, path) + with open(path, "w", encoding="utf-8") as file: + # Always convert to string to write to file + file.write(str(value)) + + # Read all configuration values for debugging purposes + for debug_key in config_data.keys(): + with open( + f"{NETCONSOLE_CONFIGFS_PATH}/{target_name}/{debug_key}", + "r", + encoding="utf-8", + ) as file: + content = file.read() + logging.debug( + "%s/%s/%s : %s", + NETCONSOLE_CONFIGFS_PATH, + target_name, + debug_key, + content.strip(), + ) + + except Exception as exception: + raise KsftFailEx( + f"Failed to configure netconsole target: {exception}" + ) from exception + + +def netcons_configure_target( + cfg: NetDrvEpEnv, interface_name: str, target_name: str +) -> None: + """Configure netconsole on the interface with the given target name""" + config_data = { + "extended": "1", + "dev_name": interface_name, + "local_port": NETCONS_LOCAL_PORT, + "remote_port": NETCONS_REMOTE_PORT, + "local_ip": cfg.addr, + "remote_ip": cfg.remote_addr, + "remote_mac": "00:00:00:00:00:00", # Not important for this test + "enabled": "1", + } + + netcons_create_target(config_data, target_name) + logging.debug( + "Created netconsole target: %s on interface %s", target_name, interface_name + ) + + +def netcons_delete_target(name: str) -> None: + """Delete a netconsole dynamic target""" + target_path = f"{NETCONSOLE_CONFIGFS_PATH}/{name}" + try: + if os.path.exists(target_path): + os.rmdir(target_path) + except OSError as exception: + raise KsftFailEx( + f"Failed to delete netconsole target: {exception}" + ) from exception + + +def netcons_load_module() -> None: + """Try to load the netconsole module""" + os.system("modprobe netconsole") + + +def bpftrace_call() -> None: + """Call bpftrace to find how many times netpoll_poll_dev() is called. + Output is saved in the global variable `maps`""" + + # This is going to update the global variable, that will be seen by the + # main function + global MAPS # pylint: disable=W0603 + + # This will be passed to bpftrace as in bpftrace -e "expr" + expr = "kprobe:netpoll_poll_dev { @hits = count(); }" + + MAPS = bpftrace(expr, timeout=BPFTRACE_TIMEOUT, json=True) + logging.debug("BPFtrace output: %s", MAPS) + + +def bpftrace_start(): + """Start a thread to call `call_bpf` in a parallel thread""" + global BPF_THREAD # pylint: disable=W0603 + + BPF_THREAD = threading.Thread(target=bpftrace_call) + BPF_THREAD.start() + if not BPF_THREAD.is_alive(): + raise KsftSkipEx("BPFtrace thread is not alive. Skipping test") + + +def bpftrace_stop() -> None: + """Stop the bpftrace thread""" + if BPF_THREAD: + BPF_THREAD.join() + + +def bpftrace_any_hit(join: bool) -> bool: + """Check if netpoll_poll_dev() was called by checking the global variable `maps`""" + if not BPF_THREAD: + raise KsftFailEx("BPFtrace didn't start") + + if BPF_THREAD.is_alive(): + if join: + # Wait for bpftrace to finish + BPF_THREAD.join() + else: + # bpftrace is still running, so, we will not check the result yet + return False + + logging.debug("MAPS coming from bpftrace = %s", MAPS) + if "hits" not in MAPS.keys(): + raise KsftFailEx(f"bpftrace failed to run!?: {MAPS}") + + logging.debug("Got a total of %d hits", MAPS["hits"]) + return MAPS["hits"] > 0 + + +def do_netpoll_flush_monitored(cfg: NetDrvEpEnv, ifname: str, target_name: str) -> None: + """Print messages to the console, trying to trigger a netpoll poll""" + # Start bpftrace in parallel, so, it is watching + # netpoll_poll_dev() while we are sending netconsole messages + bpftrace_start() + defer(bpftrace_stop) + + do_netpoll_flush(cfg, ifname, target_name) + + if bpftrace_any_hit(join=True): + ksft_pr("netpoll_poll_dev() was called. Success") + return + + raise KsftXfailEx("netpoll_poll_dev() was not called during the test...") + + +def do_netpoll_flush(cfg: NetDrvEpEnv, ifname: str, target_name: str) -> None: + """Print messages to the console, trying to trigger a netpoll poll""" + netcons_configure_target(cfg, ifname, target_name) + retry = 0 + + for i in range(int(ITERATIONS)): + if not BPF_THREAD.is_alive() or bpftrace_any_hit(join=False): + # bpftrace is done, stop sending messages + break + + msg = f"netcons test #{i}" + with open("/dev/kmsg", "w", encoding="utf-8") as kmsg: + for j in range(MAX_WRITES): + try: + kmsg.write(f"{msg}-{j}\n") + except OSError as exception: + # in some cases, kmsg can be busy, so, we will retry + time.sleep(1) + retry += 1 + if retry < 5: + logging.info("Failed to write to kmsg. Retrying") + # Just retry a few times + continue + raise KsftFailEx( + f"Failed to write to kmsg: {exception}" + ) from exception + + netcons_delete_target(target_name) + netcons_configure_target(cfg, ifname, target_name) + # If we sleep here, we will have a better chance of triggering + # This number is based on a few tests I ran while developing this test + time.sleep(0.4) + + +def configure_network(ifname: str) -> None: + """Configure ring size and queue numbers""" + + # Set defined queues to 1 to force congestion + prev_queues = ethtool_get_queues_cnt(ifname) + logging.debug("RX/TX/combined queues: %s", prev_queues) + # Only set the queues to 1 if they exists in the device. I.e, they are > 0 + ethtool_set_queues_cnt(ifname, tuple(1 if x > 0 else x for x in prev_queues)) + defer(ethtool_set_queues_cnt, ifname, prev_queues) + + # Try to set the ring size to some low value. + # Do not fail if the hardware do not accepted desired values + prev_ring_size = ethtool_get_ringsize(ifname) + for size in [(1, 1), (128, 128), (256, 256)]: + if ethtool_set_ringsize(ifname, size): + # hardware accepted the desired ringsize + logging.debug("Set RX/TX ringsize to: %s from %s", size, prev_ring_size) + break + defer(ethtool_set_ringsize, ifname, prev_ring_size) + + +def test_netpoll(cfg: NetDrvEpEnv) -> None: + """ + Test netpoll by sending traffic to the interface and then sending + netconsole messages to trigger a poll + """ + + ifname = cfg.ifname + configure_network(ifname) + target_name = netcons_generate_random_target_name() + traffic = None + + try: + traffic = GenerateTraffic(cfg) + do_netpoll_flush_monitored(cfg, ifname, target_name) + finally: + if traffic: + traffic.stop() + + # Revert RX/TX queues + netcons_delete_target(target_name) + + +def test_check_dependencies() -> None: + """Check if the dependencies are met""" + if not os.path.exists(NETCONSOLE_CONFIGFS_PATH): + raise KsftSkipEx( + f"Directory {NETCONSOLE_CONFIGFS_PATH} does not exist. CONFIG_NETCONSOLE_DYNAMIC might not be set." # pylint: disable=C0301 + ) + + +def main() -> None: + """Main function to run the test""" + netcons_load_module() + test_check_dependencies() + with NetDrvEpEnv(__file__) as cfg: + ksft_run( + [test_netpoll], + args=(cfg,), + ) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py index e0f114612c1a..da3623c5e8a9 100755 --- a/tools/testing/selftests/drivers/net/ping.py +++ b/tools/testing/selftests/drivers/net/ping.py @@ -30,7 +30,7 @@ def _test_v6(cfg) -> None: cmd("ping -s 65000 -c 1 -W0.5 " + cfg.addr_v["6"], host=cfg.remote) def _test_tcp(cfg) -> None: - cfg.require_cmd("socat", remote=True) + cfg.require_cmd("socat", local=False, remote=True) port = rand_port() listen_cmd = f"socat -{cfg.addr_ipver} -t 2 -u TCP-LISTEN:{port},reuseport STDOUT" diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py index efcc1e10575b..c2bb5d3f1ca1 100755 --- a/tools/testing/selftests/drivers/net/stats.py +++ b/tools/testing/selftests/drivers/net/stats.py @@ -1,12 +1,16 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 +""" +Tests related to standard netdevice statistics. +""" + import errno import subprocess import time from lib.py import ksft_run, ksft_exit, ksft_pr from lib.py import ksft_ge, ksft_eq, ksft_is, ksft_in, ksft_lt, ksft_true, ksft_raises -from lib.py import KsftSkipEx, KsftXfailEx +from lib.py import KsftSkipEx, KsftFailEx from lib.py import ksft_disruptive from lib.py import EthtoolFamily, NetdevFamily, RtnlFamily, NlError from lib.py import NetDrvEnv @@ -18,13 +22,16 @@ rtnl = RtnlFamily() def check_pause(cfg) -> None: - global ethnl + """ + Check that drivers which support Pause config also report standard + pause stats. + """ try: ethnl.pause_get({"header": {"dev-index": cfg.ifindex}}) except NlError as e: if e.error == errno.EOPNOTSUPP: - raise KsftXfailEx("pause not supported by the device") + raise KsftSkipEx("pause not supported by the device") from e raise data = ethnl.pause_get({"header": {"dev-index": cfg.ifindex, @@ -33,13 +40,16 @@ def check_pause(cfg) -> None: def check_fec(cfg) -> None: - global ethnl + """ + Check that drivers which support FEC config also report standard + FEC stats. + """ try: ethnl.fec_get({"header": {"dev-index": cfg.ifindex}}) except NlError as e: if e.error == errno.EOPNOTSUPP: - raise KsftXfailEx("FEC not supported by the device") + raise KsftSkipEx("FEC not supported by the device") from e raise data = ethnl.fec_get({"header": {"dev-index": cfg.ifindex, @@ -48,15 +58,17 @@ def check_fec(cfg) -> None: def pkt_byte_sum(cfg) -> None: - global netfam, rtnl + """ + Check that qstat and interface stats match in value. + """ def get_qstat(test): - global netfam stats = netfam.qstats_get({}, dump=True) if stats: for qs in stats: if qs["ifindex"]== test.ifindex: return qs + return None qstat = get_qstat(cfg) if qstat is None: @@ -77,15 +89,14 @@ def pkt_byte_sum(cfg) -> None: for _ in range(10): rtstat = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] if stat_cmp(rtstat, qstat) < 0: - raise Exception("RTNL stats are lower, fetched later") + raise KsftFailEx("RTNL stats are lower, fetched later") qstat = get_qstat(cfg) if stat_cmp(rtstat, qstat) > 0: - raise Exception("Qstats are lower, fetched later") + raise KsftFailEx("Qstats are lower, fetched later") def qstat_by_ifindex(cfg) -> None: - global netfam - global rtnl + """ Qstats Netlink API tests - querying by ifindex. """ # Construct a map ifindex -> [dump, by-index, dump] ifindexes = {} @@ -93,7 +104,7 @@ def qstat_by_ifindex(cfg) -> None: for entry in stats: ifindexes[entry['ifindex']] = [entry, None, None] - for ifindex in ifindexes.keys(): + for ifindex in ifindexes: entry = netfam.qstats_get({"ifindex": ifindex}, dump=True) ksft_eq(len(entry), 1) ifindexes[entry[0]['ifindex']][1] = entry[0] @@ -145,7 +156,7 @@ def qstat_by_ifindex(cfg) -> None: # Try to get stats for lowest unused ifindex but not 0 devs = rtnl.getlink({}, dump=True) - all_ifindexes = set([dev["ifi-index"] for dev in devs]) + all_ifindexes = set(dev["ifi-index"] for dev in devs) lowest = 2 while lowest in all_ifindexes: lowest += 1 @@ -158,18 +169,20 @@ def qstat_by_ifindex(cfg) -> None: @ksft_disruptive def check_down(cfg) -> None: + """ Test statistics (interface and qstat) are not impacted by ifdown """ + try: qstat = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] except NlError as e: if e.error == errno.EOPNOTSUPP: - raise KsftSkipEx("qstats not supported by the device") + raise KsftSkipEx("qstats not supported by the device") from e raise ip(f"link set dev {cfg.dev['ifname']} down") defer(ip, f"link set dev {cfg.dev['ifname']} up") qstat2 = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] - for k, v in qstat.items(): + for k in qstat: ksft_ge(qstat2[k], qstat[k], comment=f"{k} went backwards on device down") # exercise per-queue API to make sure that "device down" state @@ -263,6 +276,8 @@ def procfs_downup_hammer(cfg) -> None: def main() -> None: + """ Ksft boiler plate main """ + with NetDrvEnv(__file__, queue_count=100) as cfg: ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex, check_down, procfs_hammer, procfs_downup_hammer], diff --git a/tools/testing/selftests/drivers/net/xdp.py b/tools/testing/selftests/drivers/net/xdp.py new file mode 100755 index 000000000000..1dd8bf3bf6c9 --- /dev/null +++ b/tools/testing/selftests/drivers/net/xdp.py @@ -0,0 +1,658 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +This file contains tests to verify native XDP support in network drivers. +The tests utilize the BPF program `xdp_native.bpf.o` from the `selftests.net.lib` +directory, with each test focusing on a specific aspect of XDP functionality. +""" +import random +import string +from dataclasses import dataclass +from enum import Enum + +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ne, ksft_pr +from lib.py import KsftFailEx, NetDrvEpEnv, EthtoolFamily, NlError +from lib.py import bkg, cmd, rand_port, wait_port_listen +from lib.py import ip, bpftool, defer + + +class TestConfig(Enum): + """Enum for XDP configuration options.""" + MODE = 0 # Configures the BPF program for a specific test + PORT = 1 # Port configuration to communicate with the remote host + ADJST_OFFSET = 2 # Tail/Head adjustment offset for extension/shrinking + ADJST_TAG = 3 # Adjustment tag to annotate the start and end of extension + + +class XDPAction(Enum): + """Enum for XDP actions.""" + PASS = 0 # Pass the packet up to the stack + DROP = 1 # Drop the packet + TX = 2 # Route the packet to the remote host + TAIL_ADJST = 3 # Adjust the tail of the packet + HEAD_ADJST = 4 # Adjust the head of the packet + + +class XDPStats(Enum): + """Enum for XDP statistics.""" + RX = 0 # Count of valid packets received for testing + PASS = 1 # Count of packets passed up to the stack + DROP = 2 # Count of packets dropped + TX = 3 # Count of incoming packets routed to the remote host + ABORT = 4 # Count of packets that were aborted + + +@dataclass +class BPFProgInfo: + """Data class to store information about a BPF program.""" + name: str # Name of the BPF program + file: str # BPF program object file + xdp_sec: str = "xdp" # XDP section name (e.g., "xdp" or "xdp.frags") + mtu: int = 1500 # Maximum Transmission Unit, default is 1500 + + +def _exchg_udp(cfg, port, test_string): + """ + Exchanges UDP packets between a local and remote host using the socat tool. + + Args: + cfg: Configuration object containing network settings. + port: Port number to use for the UDP communication. + test_string: String that the remote host will send. + + Returns: + The string received by the test host. + """ + cfg.require_cmd("socat", remote=True) + + rx_udp_cmd = f"socat -{cfg.addr_ipver} -T 2 -u UDP-RECV:{port},reuseport STDOUT" + tx_udp_cmd = f"echo -n {test_string} | socat -t 2 -u STDIN UDP:{cfg.baddr}:{port}" + + with bkg(rx_udp_cmd, exit_wait=True) as nc: + wait_port_listen(port, proto="udp") + cmd(tx_udp_cmd, host=cfg.remote, shell=True) + + return nc.stdout.strip() + + +def _test_udp(cfg, port, size=256): + """ + Tests UDP packet exchange between a local and remote host. + + Args: + cfg: Configuration object containing network settings. + port: Port number to use for the UDP communication. + size: The length of the test string to be exchanged, default is 256 characters. + + Returns: + bool: True if the received string matches the sent string, False otherwise. + """ + test_str = "".join(random.choice(string.ascii_lowercase) for _ in range(size)) + recvd_str = _exchg_udp(cfg, port, test_str) + + return recvd_str == test_str + + +def _load_xdp_prog(cfg, bpf_info): + """ + Loads an XDP program onto a network interface. + + Args: + cfg: Configuration object containing network settings. + bpf_info: BPFProgInfo object containing information about the BPF program. + + Returns: + dict: A dictionary containing the XDP program ID, name, and associated map IDs. + """ + abs_path = cfg.net_lib_dir / bpf_info.file + prog_info = {} + + cmd(f"ip link set dev {cfg.remote_ifname} mtu {bpf_info.mtu}", shell=True, host=cfg.remote) + defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote) + + cmd( + f"ip link set dev {cfg.ifname} mtu {bpf_info.mtu} xdp obj {abs_path} sec {bpf_info.xdp_sec}", + shell=True + ) + defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off") + + xdp_info = ip(f"-d link show dev {cfg.ifname}", json=True)[0] + prog_info["id"] = xdp_info["xdp"]["prog"]["id"] + prog_info["name"] = xdp_info["xdp"]["prog"]["name"] + prog_id = prog_info["id"] + + map_ids = bpftool(f"prog show id {prog_id}", json=True)["map_ids"] + prog_info["maps"] = {} + for map_id in map_ids: + name = bpftool(f"map show id {map_id}", json=True)["name"] + prog_info["maps"][name] = map_id + + return prog_info + + +def format_hex_bytes(value): + """ + Helper function that converts an integer into a formatted hexadecimal byte string. + + Args: + value: An integer representing the number to be converted. + + Returns: + A string representing hexadecimal equivalent of value, with bytes separated by spaces. + """ + hex_str = value.to_bytes(4, byteorder='little', signed=True) + return ' '.join(f'{byte:02x}' for byte in hex_str) + + +def _set_xdp_map(map_name, key, value): + """ + Updates an XDP map with a given key-value pair using bpftool. + + Args: + map_name: The name of the XDP map to update. + key: The key to update in the map, formatted as a hexadecimal string. + value: The value to associate with the key, formatted as a hexadecimal string. + """ + key_formatted = format_hex_bytes(key) + value_formatted = format_hex_bytes(value) + bpftool( + f"map update name {map_name} key hex {key_formatted} value hex {value_formatted}" + ) + + +def _get_stats(xdp_map_id): + """ + Retrieves and formats statistics from an XDP map. + + Args: + xdp_map_id: The ID of the XDP map from which to retrieve statistics. + + Returns: + A dictionary containing formatted packet statistics for various XDP actions. + The keys are based on the XDPStats Enum values. + + Raises: + KsftFailEx: If the stats retrieval fails. + """ + stats_dump = bpftool(f"map dump id {xdp_map_id}", json=True) + if not stats_dump: + raise KsftFailEx(f"Failed to get stats for map {xdp_map_id}") + + stats_formatted = {} + for key in range(0, 5): + val = stats_dump[key]["formatted"]["value"] + if stats_dump[key]["formatted"]["key"] == XDPStats.RX.value: + stats_formatted[XDPStats.RX.value] = val + elif stats_dump[key]["formatted"]["key"] == XDPStats.PASS.value: + stats_formatted[XDPStats.PASS.value] = val + elif stats_dump[key]["formatted"]["key"] == XDPStats.DROP.value: + stats_formatted[XDPStats.DROP.value] = val + elif stats_dump[key]["formatted"]["key"] == XDPStats.TX.value: + stats_formatted[XDPStats.TX.value] = val + elif stats_dump[key]["formatted"]["key"] == XDPStats.ABORT.value: + stats_formatted[XDPStats.ABORT.value] = val + + return stats_formatted + + +def _test_pass(cfg, bpf_info, msg_sz): + """ + Tests the XDP_PASS action by exchanging UDP packets. + + Args: + cfg: Configuration object containing network settings. + bpf_info: BPFProgInfo object containing information about the BPF program. + msg_sz: Size of the test message to send. + """ + + prog_info = _load_xdp_prog(cfg, bpf_info) + port = rand_port() + + _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.PASS.value) + _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port) + + ksft_eq(_test_udp(cfg, port, msg_sz), True, "UDP packet exchange failed") + stats = _get_stats(prog_info["maps"]["map_xdp_stats"]) + + ksft_ne(stats[XDPStats.RX.value], 0, "RX stats should not be zero") + ksft_eq(stats[XDPStats.RX.value], stats[XDPStats.PASS.value], "RX and PASS stats mismatch") + + +def test_xdp_native_pass_sb(cfg): + """ + Tests the XDP_PASS action for single buffer case. + + Args: + cfg: Configuration object containing network settings. + """ + bpf_info = BPFProgInfo("xdp_prog", "xdp_native.bpf.o", "xdp", 1500) + + _test_pass(cfg, bpf_info, 256) + + +def test_xdp_native_pass_mb(cfg): + """ + Tests the XDP_PASS action for a multi-buff size. + + Args: + cfg: Configuration object containing network settings. + """ + bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o", "xdp.frags", 9000) + + _test_pass(cfg, bpf_info, 8000) + + +def _test_drop(cfg, bpf_info, msg_sz): + """ + Tests the XDP_DROP action by exchanging UDP packets. + + Args: + cfg: Configuration object containing network settings. + bpf_info: BPFProgInfo object containing information about the BPF program. + msg_sz: Size of the test message to send. + """ + + prog_info = _load_xdp_prog(cfg, bpf_info) + port = rand_port() + + _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.DROP.value) + _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port) + + ksft_eq(_test_udp(cfg, port, msg_sz), False, "UDP packet exchange should fail") + stats = _get_stats(prog_info["maps"]["map_xdp_stats"]) + + ksft_ne(stats[XDPStats.RX.value], 0, "RX stats should be zero") + ksft_eq(stats[XDPStats.RX.value], stats[XDPStats.DROP.value], "RX and DROP stats mismatch") + + +def test_xdp_native_drop_sb(cfg): + """ + Tests the XDP_DROP action for a signle-buff case. + + Args: + cfg: Configuration object containing network settings. + """ + bpf_info = BPFProgInfo("xdp_prog", "xdp_native.bpf.o", "xdp", 1500) + + _test_drop(cfg, bpf_info, 256) + + +def test_xdp_native_drop_mb(cfg): + """ + Tests the XDP_DROP action for a multi-buff case. + + Args: + cfg: Configuration object containing network settings. + """ + bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o", "xdp.frags", 9000) + + _test_drop(cfg, bpf_info, 8000) + + +def test_xdp_native_tx_mb(cfg): + """ + Tests the XDP_TX action for a multi-buff case. + + Args: + cfg: Configuration object containing network settings. + """ + cfg.require_cmd("socat", remote=True) + + bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o", "xdp.frags", 9000) + prog_info = _load_xdp_prog(cfg, bpf_info) + port = rand_port() + + _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.TX.value) + _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port) + + test_string = ''.join(random.choice(string.ascii_lowercase) for _ in range(8000)) + rx_udp = f"socat -{cfg.addr_ipver} -T 2 -u UDP-RECV:{port},reuseport STDOUT" + tx_udp = f"echo {test_string} | socat -t 2 -u STDIN UDP:{cfg.baddr}:{port}" + + with bkg(rx_udp, host=cfg.remote, exit_wait=True) as rnc: + wait_port_listen(port, proto="udp", host=cfg.remote) + cmd(tx_udp, host=cfg.remote, shell=True) + + stats = _get_stats(prog_info['maps']['map_xdp_stats']) + + ksft_eq(rnc.stdout.strip(), test_string, "UDP packet exchange failed") + ksft_eq(stats[XDPStats.TX.value], 1, "TX stats mismatch") + + +def _validate_res(res, offset_lst, pkt_sz_lst): + """ + Validates the result of a test. + + Args: + res: The result of the test, which should be a dictionary with a "status" key. + + Raises: + KsftFailEx: If the test fails to pass any combination of offset and packet size. + """ + if "status" not in res: + raise KsftFailEx("Missing 'status' key in result dictionary") + + # Validate that not a single case was successful + if res["status"] == "fail": + if res["offset"] == offset_lst[0] and res["pkt_sz"] == pkt_sz_lst[0]: + raise KsftFailEx(f"{res['reason']}") + + # Get the previous offset and packet size to report the successful run + tmp_idx = offset_lst.index(res["offset"]) + prev_offset = offset_lst[tmp_idx - 1] + if tmp_idx == 0: + tmp_idx = pkt_sz_lst.index(res["pkt_sz"]) + prev_pkt_sz = pkt_sz_lst[tmp_idx - 1] + else: + prev_pkt_sz = res["pkt_sz"] + + # Use these values for error reporting + ksft_pr( + f"Failed run: pkt_sz {res['pkt_sz']}, offset {res['offset']}. " + f"Last successful run: pkt_sz {prev_pkt_sz}, offset {prev_offset}. " + f"Reason: {res['reason']}" + ) + + +def _check_for_failures(recvd_str, stats): + """ + Checks for common failures while adjusting headroom or tailroom. + + Args: + recvd_str: The string received from the remote host after sending a test string. + stats: A dictionary containing formatted packet statistics for various XDP actions. + + Returns: + str: A string describing the failure reason if a failure is detected, otherwise None. + """ + + # Any adjustment failure result in an abort hence, we track this counter + if stats[XDPStats.ABORT.value] != 0: + return "Adjustment failed" + + # Since we are using aggregate stats for a single test across all offsets and packet sizes + # we can't use RX stats only to track data exchange failure without taking a previous + # snapshot. An easier way is to simply check for non-zero length of received string. + if len(recvd_str) == 0: + return "Data exchange failed" + + # Check for RX and PASS stats mismatch. Ideally, they should be equal for a successful run + if stats[XDPStats.RX.value] != stats[XDPStats.PASS.value]: + return "RX stats mismatch" + + return None + + +def _test_xdp_native_tail_adjst(cfg, pkt_sz_lst, offset_lst): + """ + Tests the XDP tail adjustment functionality. + + This function loads the appropriate XDP program based on the provided + program name and configures the XDP map for tail adjustment. It then + validates the tail adjustment by sending and receiving UDP packets + with specified packet sizes and offsets. + + Args: + cfg: Configuration object containing network settings. + prog: Name of the XDP program to load. + pkt_sz_lst: List of packet sizes to test. + offset_lst: List of offsets to validate support for tail adjustment. + + Returns: + dict: A dictionary with test status and failure details if applicable. + """ + port = rand_port() + bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o", "xdp.frags", 9000) + + prog_info = _load_xdp_prog(cfg, bpf_info) + + # Configure the XDP map for tail adjustment + _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.TAIL_ADJST.value) + _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port) + + for offset in offset_lst: + tag = format(random.randint(65, 90), "02x") + + _set_xdp_map("map_xdp_setup", TestConfig.ADJST_OFFSET.value, offset) + if offset > 0: + _set_xdp_map("map_xdp_setup", TestConfig.ADJST_TAG.value, int(tag, 16)) + + for pkt_sz in pkt_sz_lst: + test_str = "".join(random.choice(string.ascii_lowercase) for _ in range(pkt_sz)) + recvd_str = _exchg_udp(cfg, port, test_str) + stats = _get_stats(prog_info["maps"]["map_xdp_stats"]) + + failure = _check_for_failures(recvd_str, stats) + if failure is not None: + return { + "status": "fail", + "reason": failure, + "offset": offset, + "pkt_sz": pkt_sz, + } + + # Validate data content based on offset direction + expected_data = None + if offset > 0: + expected_data = test_str + (offset * chr(int(tag, 16))) + else: + expected_data = test_str[0:pkt_sz + offset] + + if recvd_str != expected_data: + return { + "status": "fail", + "reason": "Data mismatch", + "offset": offset, + "pkt_sz": pkt_sz, + } + + return {"status": "pass"} + + +def test_xdp_native_adjst_tail_grow_data(cfg): + """ + Tests the XDP tail adjustment by growing packet data. + + Args: + cfg: Configuration object containing network settings. + """ + pkt_sz_lst = [512, 1024, 2048] + offset_lst = [1, 16, 32, 64, 128, 256] + res = _test_xdp_native_tail_adjst( + cfg, + pkt_sz_lst, + offset_lst, + ) + + _validate_res(res, offset_lst, pkt_sz_lst) + + +def test_xdp_native_adjst_tail_shrnk_data(cfg): + """ + Tests the XDP tail adjustment by shrinking packet data. + + Args: + cfg: Configuration object containing network settings. + """ + pkt_sz_lst = [512, 1024, 2048] + offset_lst = [-16, -32, -64, -128, -256] + res = _test_xdp_native_tail_adjst( + cfg, + pkt_sz_lst, + offset_lst, + ) + + _validate_res(res, offset_lst, pkt_sz_lst) + + +def get_hds_thresh(cfg): + """ + Retrieves the header data split (HDS) threshold for a network interface. + + Args: + cfg: Configuration object containing network settings. + + Returns: + The HDS threshold value. If the threshold is not supported or an error occurs, + a default value of 1500 is returned. + """ + netnl = cfg.netnl + hds_thresh = 1500 + + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + if 'hds-thresh' not in rings: + ksft_pr(f'hds-thresh not supported. Using default: {hds_thresh}') + return hds_thresh + hds_thresh = rings['hds-thresh'] + except NlError as e: + ksft_pr(f"Failed to get rings: {e}. Using default: {hds_thresh}") + + return hds_thresh + + +def _test_xdp_native_head_adjst(cfg, prog, pkt_sz_lst, offset_lst): + """ + Tests the XDP head adjustment action for a multi-buffer case. + + Args: + cfg: Configuration object containing network settings. + netnl: Network namespace or link object (not used in this function). + + This function sets up the packet size and offset lists, then performs + the head adjustment test by sending and receiving UDP packets. + """ + cfg.require_cmd("socat", remote=True) + + prog_info = _load_xdp_prog(cfg, BPFProgInfo(prog, "xdp_native.bpf.o", "xdp.frags", 9000)) + port = rand_port() + + _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.HEAD_ADJST.value) + _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port) + + hds_thresh = get_hds_thresh(cfg) + for offset in offset_lst: + for pkt_sz in pkt_sz_lst: + # The "head" buffer must contain at least the Ethernet header + # after we eat into it. We send large-enough packets, but if HDS + # is enabled head will only contain headers. Don't try to eat + # more than 28 bytes (UDPv4 + eth hdr left: (14 + 20 + 8) - 14) + l2_cut_off = 28 if cfg.addr_ipver == 4 else 48 + if pkt_sz > hds_thresh and offset > l2_cut_off: + ksft_pr( + f"Failed run: pkt_sz ({pkt_sz}) > HDS threshold ({hds_thresh}) and " + f"offset {offset} > {l2_cut_off}" + ) + return {"status": "pass"} + + test_str = ''.join(random.choice(string.ascii_lowercase) for _ in range(pkt_sz)) + tag = format(random.randint(65, 90), '02x') + + _set_xdp_map("map_xdp_setup", + TestConfig.ADJST_OFFSET.value, + offset) + _set_xdp_map("map_xdp_setup", TestConfig.ADJST_TAG.value, int(tag, 16)) + _set_xdp_map("map_xdp_setup", TestConfig.ADJST_OFFSET.value, offset) + + recvd_str = _exchg_udp(cfg, port, test_str) + + # Check for failures around adjustment and data exchange + failure = _check_for_failures(recvd_str, _get_stats(prog_info['maps']['map_xdp_stats'])) + if failure is not None: + return { + "status": "fail", + "reason": failure, + "offset": offset, + "pkt_sz": pkt_sz + } + + # Validate data content based on offset direction + expected_data = None + if offset < 0: + expected_data = chr(int(tag, 16)) * (0 - offset) + test_str + else: + expected_data = test_str[offset:] + + if recvd_str != expected_data: + return { + "status": "fail", + "reason": "Data mismatch", + "offset": offset, + "pkt_sz": pkt_sz + } + + return {"status": "pass"} + + +def test_xdp_native_adjst_head_grow_data(cfg): + """ + Tests the XDP headroom growth support. + + Args: + cfg: Configuration object containing network settings. + + This function sets up the packet size and offset lists, then calls the + _test_xdp_native_head_adjst_mb function to perform the actual test. The + test is passed if the headroom is successfully extended for given packet + sizes and offsets. + """ + pkt_sz_lst = [512, 1024, 2048] + + # Negative values result in headroom shrinking, resulting in growing of payload + offset_lst = [-16, -32, -64, -128, -256] + res = _test_xdp_native_head_adjst(cfg, "xdp_prog_frags", pkt_sz_lst, offset_lst) + + _validate_res(res, offset_lst, pkt_sz_lst) + + +def test_xdp_native_adjst_head_shrnk_data(cfg): + """ + Tests the XDP headroom shrinking support. + + Args: + cfg: Configuration object containing network settings. + + This function sets up the packet size and offset lists, then calls the + _test_xdp_native_head_adjst_mb function to perform the actual test. The + test is passed if the headroom is successfully shrunk for given packet + sizes and offsets. + """ + pkt_sz_lst = [512, 1024, 2048] + + # Positive values result in headroom growing, resulting in shrinking of payload + offset_lst = [16, 32, 64, 128, 256] + res = _test_xdp_native_head_adjst(cfg, "xdp_prog_frags", pkt_sz_lst, offset_lst) + + _validate_res(res, offset_lst, pkt_sz_lst) + + +def main(): + """ + Main function to execute the XDP tests. + + This function runs a series of tests to validate the XDP support for + both the single and multi-buffer. It uses the NetDrvEpEnv context + manager to manage the network driver environment and the ksft_run + function to execute the tests. + """ + with NetDrvEpEnv(__file__) as cfg: + cfg.netnl = EthtoolFamily() + ksft_run( + [ + test_xdp_native_pass_sb, + test_xdp_native_pass_mb, + test_xdp_native_drop_sb, + test_xdp_native_drop_mb, + test_xdp_native_tx_mb, + test_xdp_native_adjst_tail_grow_data, + test_xdp_native_adjst_tail_shrnk_data, + test_xdp_native_adjst_head_grow_data, + test_xdp_native_adjst_head_shrnk_data, + ], + args=(cfg,)) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/filesystems/.gitignore b/tools/testing/selftests/filesystems/.gitignore index 7afa58e2bb20..fcbdb1297e24 100644 --- a/tools/testing/selftests/filesystems/.gitignore +++ b/tools/testing/selftests/filesystems/.gitignore @@ -3,3 +3,4 @@ dnotify_test devpts_pts file_stressor anon_inode_test +kernfs_test diff --git a/tools/testing/selftests/filesystems/Makefile b/tools/testing/selftests/filesystems/Makefile index b02326193fee..73d4650af1a5 100644 --- a/tools/testing/selftests/filesystems/Makefile +++ b/tools/testing/selftests/filesystems/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += $(KHDR_INCLUDES) -TEST_GEN_PROGS := devpts_pts file_stressor anon_inode_test +TEST_GEN_PROGS := devpts_pts file_stressor anon_inode_test kernfs_test TEST_GEN_PROGS_EXTENDED := dnotify_test include ../lib.mk diff --git a/tools/testing/selftests/filesystems/kernfs_test.c b/tools/testing/selftests/filesystems/kernfs_test.c new file mode 100644 index 000000000000..16538b3b318e --- /dev/null +++ b/tools/testing/selftests/filesystems/kernfs_test.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#define __SANE_USERSPACE_TYPES__ + +#include <fcntl.h> +#include <stdio.h> +#include <sys/stat.h> +#include <sys/xattr.h> + +#include "../kselftest_harness.h" +#include "wrappers.h" + +TEST(kernfs_listxattr) +{ + int fd; + + /* Read-only file that can never have any extended attributes set. */ + fd = open("/sys/kernel/warn_count", O_RDONLY | O_CLOEXEC); + ASSERT_GE(fd, 0); + ASSERT_EQ(flistxattr(fd, NULL, 0), 0); + EXPECT_EQ(close(fd), 0); +} + +TEST(kernfs_getxattr) +{ + int fd; + char buf[1]; + + /* Read-only file that can never have any extended attributes set. */ + fd = open("/sys/kernel/warn_count", O_RDONLY | O_CLOEXEC); + ASSERT_GE(fd, 0); + ASSERT_LT(fgetxattr(fd, "user.foo", buf, sizeof(buf)), 0); + ASSERT_EQ(errno, ENODATA); + EXPECT_EQ(close(fd), 0); +} + +TEST_HARNESS_MAIN + diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc index b7c8f29c09a9..65916bb55dfb 100644 --- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc +++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc @@ -14,11 +14,35 @@ fail() { #msg exit_fail } +# As reading trace can last forever, simply look for 3 different +# events then exit out of reading the file. If there's not 3 different +# events, then the test has failed. +check_unique() { + cat trace | grep -v '^#' | awk ' + BEGIN { cnt = 0; } + { + for (i = 0; i < cnt; i++) { + if (event[i] == $5) { + break; + } + } + if (i == cnt) { + event[cnt++] = $5; + if (cnt > 2) { + exit; + } + } + } + END { + printf "%d", cnt; + }' +} + echo 'sched:*' > set_event yield -count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`check_unique` if [ $count -lt 3 ]; then fail "at least fork, exec and exit events should be recorded" fi @@ -29,7 +53,7 @@ echo 1 > events/sched/enable yield -count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`check_unique` if [ $count -lt 3 ]; then fail "at least fork, exec and exit events should be recorded" fi diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc index 4b994b6df5ac..ed81eaf2afd6 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc @@ -29,7 +29,7 @@ ftrace_filter_check 'schedule*' '^schedule.*$' ftrace_filter_check '*pin*lock' '.*pin.*lock$' # filter by start*mid* -ftrace_filter_check 'mutex*try*' '^mutex.*try.*' +ftrace_filter_check 'mutex*unl*' '^mutex.*unl.*' # Advanced full-glob matching feature is recently supported. # Skip the tests if we are sure the kernel does not support it. diff --git a/tools/testing/selftests/futex/functional/futex_priv_hash.c b/tools/testing/selftests/futex/functional/futex_priv_hash.c index 24a92dc94eb8..aea001ac4946 100644 --- a/tools/testing/selftests/futex/functional/futex_priv_hash.c +++ b/tools/testing/selftests/futex/functional/futex_priv_hash.c @@ -26,14 +26,12 @@ static int counter; #ifndef PR_FUTEX_HASH #define PR_FUTEX_HASH 78 # define PR_FUTEX_HASH_SET_SLOTS 1 -# define FH_FLAG_IMMUTABLE (1ULL << 0) # define PR_FUTEX_HASH_GET_SLOTS 2 -# define PR_FUTEX_HASH_GET_IMMUTABLE 3 #endif -static int futex_hash_slots_set(unsigned int slots, int flags) +static int futex_hash_slots_set(unsigned int slots) { - return prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_SET_SLOTS, slots, flags); + return prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_SET_SLOTS, slots, 0); } static int futex_hash_slots_get(void) @@ -41,16 +39,11 @@ static int futex_hash_slots_get(void) return prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_GET_SLOTS); } -static int futex_hash_immutable_get(void) -{ - return prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_GET_IMMUTABLE); -} - static void futex_hash_slots_set_verify(int slots) { int ret; - ret = futex_hash_slots_set(slots, 0); + ret = futex_hash_slots_set(slots); if (ret != 0) { ksft_test_result_fail("Failed to set slots to %d: %m\n", slots); ksft_finished(); @@ -64,13 +57,13 @@ static void futex_hash_slots_set_verify(int slots) ksft_test_result_pass("SET and GET slots %d passed\n", slots); } -static void futex_hash_slots_set_must_fail(int slots, int flags) +static void futex_hash_slots_set_must_fail(int slots) { int ret; - ret = futex_hash_slots_set(slots, flags); - ksft_test_result(ret < 0, "futex_hash_slots_set(%d, %d)\n", - slots, flags); + ret = futex_hash_slots_set(slots); + ksft_test_result(ret < 0, "futex_hash_slots_set(%d)\n", + slots); } static void *thread_return_fn(void *arg) @@ -111,6 +104,30 @@ static void join_max_threads(void) } } +#define SEC_IN_NSEC 1000000000 +#define MSEC_IN_NSEC 1000000 + +static void futex_dummy_op(void) +{ + pthread_mutex_t lock = PTHREAD_MUTEX_INITIALIZER; + struct timespec timeout; + int ret; + + pthread_mutex_lock(&lock); + clock_gettime(CLOCK_REALTIME, &timeout); + timeout.tv_nsec += 100 * MSEC_IN_NSEC; + if (timeout.tv_nsec >= SEC_IN_NSEC) { + timeout.tv_nsec -= SEC_IN_NSEC; + timeout.tv_sec++; + } + ret = pthread_mutex_timedlock(&lock, &timeout); + if (ret == 0) + ksft_exit_fail_msg("Successfully locked an already locked mutex.\n"); + + if (ret != ETIMEDOUT) + ksft_exit_fail_msg("pthread_mutex_timedlock() did not timeout: %d.\n", ret); +} + static void usage(char *prog) { printf("Usage: %s\n", prog); @@ -128,18 +145,14 @@ int main(int argc, char *argv[]) { int futex_slots1, futex_slotsn, online_cpus; pthread_mutexattr_t mutex_attr_pi; - int use_global_hash = 0; - int ret; + int ret, retry = 20; int c; - while ((c = getopt(argc, argv, "cghv:")) != -1) { + while ((c = getopt(argc, argv, "chv:")) != -1) { switch (c) { case 'c': log_color(1); break; - case 'g': - use_global_hash = 1; - break; case 'h': usage(basename(argv[0])); exit(0); @@ -154,7 +167,7 @@ int main(int argc, char *argv[]) } ksft_print_header(); - ksft_set_plan(22); + ksft_set_plan(21); ret = pthread_mutexattr_init(&mutex_attr_pi); ret |= pthread_mutexattr_setprotocol(&mutex_attr_pi, PTHREAD_PRIO_INHERIT); @@ -167,10 +180,6 @@ int main(int argc, char *argv[]) if (ret != 0) ksft_exit_fail_msg("futex_hash_slots_get() failed: %d, %m\n", ret); - ret = futex_hash_immutable_get(); - if (ret != 0) - ksft_exit_fail_msg("futex_hash_immutable_get() failed: %d, %m\n", ret); - ksft_test_result_pass("Basic get slots and immutable status.\n"); ret = pthread_create(&threads[0], NULL, thread_return_fn, NULL); if (ret != 0) @@ -208,8 +217,24 @@ int main(int argc, char *argv[]) */ ksft_print_msg("Online CPUs: %d\n", online_cpus); if (online_cpus > 16) { +retry_getslots: futex_slotsn = futex_hash_slots_get(); if (futex_slotsn < 0 || futex_slots1 == futex_slotsn) { + retry--; + /* + * Auto scaling on thread creation can be slightly delayed + * because it waits for a RCU grace period twice. The new + * private hash is assigned upon the first futex operation + * after grace period. + * To cover all this for testing purposes the function + * below will acquire a lock and acquire it again with a + * 100ms timeout which must timeout. This ensures we + * sleep for 100ms and issue a futex operation. + */ + if (retry > 0) { + futex_dummy_op(); + goto retry_getslots; + } ksft_print_msg("Expected increase of hash buckets but got: %d -> %d\n", futex_slots1, futex_slotsn); ksft_exit_fail_msg(test_msg_auto_inc); @@ -227,7 +252,7 @@ int main(int argc, char *argv[]) futex_hash_slots_set_verify(32); futex_hash_slots_set_verify(16); - ret = futex_hash_slots_set(15, 0); + ret = futex_hash_slots_set(15); ksft_test_result(ret < 0, "Use 15 slots\n"); futex_hash_slots_set_verify(2); @@ -245,28 +270,23 @@ int main(int argc, char *argv[]) ksft_test_result(ret == 2, "No more auto-resize after manaul setting, got %d\n", ret); - futex_hash_slots_set_must_fail(1 << 29, 0); + futex_hash_slots_set_must_fail(1 << 29); + futex_hash_slots_set_verify(4); /* - * Once the private hash has been made immutable or global hash has been requested, - * then this requested can not be undone. + * Once the global hash has been requested, then this requested can not + * be undone. */ - if (use_global_hash) { - ret = futex_hash_slots_set(0, 0); - ksft_test_result(ret == 0, "Global hash request\n"); - } else { - ret = futex_hash_slots_set(4, FH_FLAG_IMMUTABLE); - ksft_test_result(ret == 0, "Immutable resize to 4\n"); - } + ret = futex_hash_slots_set(0); + ksft_test_result(ret == 0, "Global hash request\n"); if (ret != 0) goto out; - futex_hash_slots_set_must_fail(4, 0); - futex_hash_slots_set_must_fail(4, FH_FLAG_IMMUTABLE); - futex_hash_slots_set_must_fail(8, 0); - futex_hash_slots_set_must_fail(8, FH_FLAG_IMMUTABLE); - futex_hash_slots_set_must_fail(0, FH_FLAG_IMMUTABLE); - futex_hash_slots_set_must_fail(6, FH_FLAG_IMMUTABLE); + futex_hash_slots_set_must_fail(4); + futex_hash_slots_set_must_fail(8); + futex_hash_slots_set_must_fail(8); + futex_hash_slots_set_must_fail(0); + futex_hash_slots_set_must_fail(6); ret = pthread_barrier_init(&barrier_main, NULL, MAX_THREADS); if (ret != 0) { @@ -277,14 +297,7 @@ int main(int argc, char *argv[]) join_max_threads(); ret = futex_hash_slots_get(); - if (use_global_hash) { - ksft_test_result(ret == 0, "Continue to use global hash\n"); - } else { - ksft_test_result(ret == 4, "Continue to use the 4 hash buckets\n"); - } - - ret = futex_hash_immutable_get(); - ksft_test_result(ret == 1, "Hash reports to be immutable\n"); + ksft_test_result(ret == 0, "Continue to use global hash\n"); out: ksft_finished(); diff --git a/tools/testing/selftests/futex/include/futex2test.h b/tools/testing/selftests/futex/include/futex2test.h index ea79662405bc..1f625b39948a 100644 --- a/tools/testing/selftests/futex/include/futex2test.h +++ b/tools/testing/selftests/futex/include/futex2test.h @@ -4,6 +4,7 @@ * * Copyright 2021 Collabora Ltd. */ +#include <linux/time_types.h> #include <stdint.h> #define u64_to_ptr(x) ((void *)(uintptr_t)(x)) @@ -65,7 +66,12 @@ struct futex32_numa { static inline int futex_waitv(volatile struct futex_waitv *waiters, unsigned long nr_waiters, unsigned long flags, struct timespec *timo, clockid_t clockid) { - return syscall(__NR_futex_waitv, waiters, nr_waiters, flags, timo, clockid); + struct __kernel_timespec ts = { + .tv_sec = timo->tv_sec, + .tv_nsec = timo->tv_nsec, + }; + + return syscall(__NR_futex_waitv, waiters, nr_waiters, flags, &ts, clockid); } /* diff --git a/tools/testing/selftests/futex/include/futextest.h b/tools/testing/selftests/futex/include/futextest.h index ddbcfc9b7bac..7a5fd1d5355e 100644 --- a/tools/testing/selftests/futex/include/futextest.h +++ b/tools/testing/selftests/futex/include/futextest.h @@ -47,6 +47,17 @@ typedef volatile u_int32_t futex_t; FUTEX_PRIVATE_FLAG) #endif +/* + * SYS_futex is expected from system C library, in glibc some 32-bit + * architectures (e.g. RV32) are using 64-bit time_t, therefore it doesn't have + * SYS_futex defined but just SYS_futex_time64. Define SYS_futex as + * SYS_futex_time64 in this situation to ensure the compilation and the + * compatibility. + */ +#if !defined(SYS_futex) && defined(SYS_futex_time64) +#define SYS_futex SYS_futex_time64 +#endif + /** * futex() - SYS_futex syscall wrapper * @uaddr: address of first futex diff --git a/tools/testing/selftests/hid/config.common b/tools/testing/selftests/hid/config.common index b1f40857307d..38c51158adf8 100644 --- a/tools/testing/selftests/hid/config.common +++ b/tools/testing/selftests/hid/config.common @@ -135,6 +135,7 @@ CONFIG_NET_EMATCH=y CONFIG_NETFILTER_NETLINK_LOG=y CONFIG_NETFILTER_NETLINK_QUEUE=y CONFIG_NETFILTER_XTABLES=y +CONFIG_NETFILTER_XTABLES_LEGACY=y CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=y CONFIG_NETFILTER_XT_MATCH_BPF=y CONFIG_NETFILTER_XT_MATCH_COMMENT=y diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c index e9dbb84c100a..5e36aeeb9901 100644 --- a/tools/testing/selftests/ipc/msgque.c +++ b/tools/testing/selftests/ipc/msgque.c @@ -39,26 +39,26 @@ int restore_queue(struct msgque_data *msgque) fd = open("/proc/sys/kernel/msg_next_id", O_WRONLY); if (fd == -1) { - printf("Failed to open /proc/sys/kernel/msg_next_id\n"); + ksft_test_result_fail("Failed to open /proc/sys/kernel/msg_next_id\n"); return -errno; } sprintf(buf, "%d", msgque->msq_id); ret = write(fd, buf, strlen(buf)); if (ret != strlen(buf)) { - printf("Failed to write to /proc/sys/kernel/msg_next_id\n"); + ksft_test_result_fail("Failed to write to /proc/sys/kernel/msg_next_id\n"); return -errno; } id = msgget(msgque->key, msgque->mode | IPC_CREAT | IPC_EXCL); if (id == -1) { - printf("Failed to create queue\n"); + ksft_test_result_fail("Failed to create queue\n"); return -errno; } if (id != msgque->msq_id) { - printf("Restored queue has wrong id (%d instead of %d)\n", - id, msgque->msq_id); + ksft_test_result_fail("Restored queue has wrong id (%d instead of %d)\n" + , id, msgque->msq_id); ret = -EFAULT; goto destroy; } @@ -66,7 +66,7 @@ int restore_queue(struct msgque_data *msgque) for (i = 0; i < msgque->qnum; i++) { if (msgsnd(msgque->msq_id, &msgque->messages[i].mtype, msgque->messages[i].msize, IPC_NOWAIT) != 0) { - printf("msgsnd failed (%m)\n"); + ksft_test_result_fail("msgsnd failed (%m)\n"); ret = -errno; goto destroy; } @@ -90,23 +90,22 @@ int check_and_destroy_queue(struct msgque_data *msgque) if (ret < 0) { if (errno == ENOMSG) break; - printf("Failed to read IPC message: %m\n"); + ksft_test_result_fail("Failed to read IPC message: %m\n"); ret = -errno; goto err; } if (ret != msgque->messages[cnt].msize) { - printf("Wrong message size: %d (expected %d)\n", ret, - msgque->messages[cnt].msize); + ksft_test_result_fail("Wrong message size: %d (expected %d)\n", ret, msgque->messages[cnt].msize); ret = -EINVAL; goto err; } if (message.mtype != msgque->messages[cnt].mtype) { - printf("Wrong message type\n"); + ksft_test_result_fail("Wrong message type\n"); ret = -EINVAL; goto err; } if (memcmp(message.mtext, msgque->messages[cnt].mtext, ret)) { - printf("Wrong message content\n"); + ksft_test_result_fail("Wrong message content\n"); ret = -EINVAL; goto err; } @@ -114,7 +113,7 @@ int check_and_destroy_queue(struct msgque_data *msgque) } if (cnt != msgque->qnum) { - printf("Wrong message number\n"); + ksft_test_result_fail("Wrong message number\n"); ret = -EINVAL; goto err; } @@ -139,7 +138,7 @@ int dump_queue(struct msgque_data *msgque) if (ret < 0) { if (errno == EINVAL) continue; - printf("Failed to get stats for IPC queue with id %d\n", + ksft_test_result_fail("Failed to get stats for IPC queue with id %d\n", kern_id); return -errno; } @@ -150,7 +149,7 @@ int dump_queue(struct msgque_data *msgque) msgque->messages = malloc(sizeof(struct msg1) * ds.msg_qnum); if (msgque->messages == NULL) { - printf("Failed to get stats for IPC queue\n"); + ksft_test_result_fail("Failed to get stats for IPC queue\n"); return -ENOMEM; } @@ -162,7 +161,7 @@ int dump_queue(struct msgque_data *msgque) ret = msgrcv(msgque->msq_id, &msgque->messages[i].mtype, MAX_MSG_SIZE, i, IPC_NOWAIT | MSG_COPY); if (ret < 0) { - printf("Failed to copy IPC message: %m (%d)\n", errno); + ksft_test_result_fail("Failed to copy IPC message: %m (%d)\n", errno); return -errno; } msgque->messages[i].msize = ret; @@ -178,7 +177,7 @@ int fill_msgque(struct msgque_data *msgque) memcpy(msgbuf.mtext, TEST_STRING, sizeof(TEST_STRING)); if (msgsnd(msgque->msq_id, &msgbuf.mtype, sizeof(TEST_STRING), IPC_NOWAIT) != 0) { - printf("First message send failed (%m)\n"); + ksft_test_result_fail("First message send failed (%m)\n"); return -errno; } @@ -186,7 +185,7 @@ int fill_msgque(struct msgque_data *msgque) memcpy(msgbuf.mtext, ANOTHER_TEST_STRING, sizeof(ANOTHER_TEST_STRING)); if (msgsnd(msgque->msq_id, &msgbuf.mtype, sizeof(ANOTHER_TEST_STRING), IPC_NOWAIT) != 0) { - printf("Second message send failed (%m)\n"); + ksft_test_result_fail("Second message send failed (%m)\n"); return -errno; } return 0; @@ -202,44 +201,44 @@ int main(int argc, char **argv) msgque.key = ftok(argv[0], 822155650); if (msgque.key == -1) { - printf("Can't make key: %d\n", -errno); + ksft_test_result_fail("Can't make key: %d\n", -errno); ksft_exit_fail(); } msgque.msq_id = msgget(msgque.key, IPC_CREAT | IPC_EXCL | 0666); if (msgque.msq_id == -1) { err = -errno; - printf("Can't create queue: %d\n", err); + ksft_test_result_fail("Can't create queue: %d\n", err); goto err_out; } err = fill_msgque(&msgque); if (err) { - printf("Failed to fill queue: %d\n", err); + ksft_test_result_fail("Failed to fill queue: %d\n", err); goto err_destroy; } err = dump_queue(&msgque); if (err) { - printf("Failed to dump queue: %d\n", err); + ksft_test_result_fail("Failed to dump queue: %d\n", err); goto err_destroy; } err = check_and_destroy_queue(&msgque); if (err) { - printf("Failed to check and destroy queue: %d\n", err); + ksft_test_result_fail("Failed to check and destroy queue: %d\n", err); goto err_out; } err = restore_queue(&msgque); if (err) { - printf("Failed to restore queue: %d\n", err); + ksft_test_result_fail("Failed to restore queue: %d\n", err); goto err_destroy; } err = check_and_destroy_queue(&msgque); if (err) { - printf("Failed to test queue: %d\n", err); + ksft_test_result_fail("Failed to test queue: %d\n", err); goto err_out; } ksft_exit_pass(); diff --git a/tools/testing/selftests/kexec/Makefile b/tools/testing/selftests/kexec/Makefile index e3000ccb9a5d..874cfdd3b75b 100644 --- a/tools/testing/selftests/kexec/Makefile +++ b/tools/testing/selftests/kexec/Makefile @@ -12,7 +12,7 @@ include ../../../scripts/Makefile.arch ifeq ($(IS_64_BIT)$(ARCH_PROCESSED),1x86) TEST_PROGS += test_kexec_jump.sh -test_kexec_jump.sh: $(OUTPUT)/test_kexec_jump +TEST_GEN_PROGS := test_kexec_jump endif include ../lib.mk diff --git a/tools/testing/selftests/kvm/arm64/debug-exceptions.c b/tools/testing/selftests/kvm/arm64/debug-exceptions.c index c7fb55c9135b..e34963956fbc 100644 --- a/tools/testing/selftests/kvm/arm64/debug-exceptions.c +++ b/tools/testing/selftests/kvm/arm64/debug-exceptions.c @@ -140,7 +140,7 @@ static void enable_os_lock(void) static void enable_monitor_debug_exceptions(void) { - uint32_t mdscr; + uint64_t mdscr; asm volatile("msr daifclr, #8"); @@ -223,7 +223,7 @@ void install_hw_bp_ctx(uint8_t addr_bp, uint8_t ctx_bp, uint64_t addr, static void install_ss(void) { - uint32_t mdscr; + uint64_t mdscr; asm volatile("msr daifclr, #8"); diff --git a/tools/testing/selftests/landlock/audit.h b/tools/testing/selftests/landlock/audit.h index 18a6014920b5..b16986aa6442 100644 --- a/tools/testing/selftests/landlock/audit.h +++ b/tools/testing/selftests/landlock/audit.h @@ -403,11 +403,12 @@ static int audit_init_filter_exe(struct audit_filter *filter, const char *path) /* It is assume that there is not already filtering rules. */ filter->record_type = AUDIT_EXE; if (!path) { - filter->exe_len = readlink("/proc/self/exe", filter->exe, - sizeof(filter->exe) - 1); - if (filter->exe_len < 0) + int ret = readlink("/proc/self/exe", filter->exe, + sizeof(filter->exe) - 1); + if (ret < 0) return -errno; + filter->exe_len = ret; return 0; } diff --git a/tools/testing/selftests/landlock/audit_test.c b/tools/testing/selftests/landlock/audit_test.c index cfc571afd0eb..46d02d49835a 100644 --- a/tools/testing/selftests/landlock/audit_test.c +++ b/tools/testing/selftests/landlock/audit_test.c @@ -7,6 +7,7 @@ #define _GNU_SOURCE #include <errno.h> +#include <fcntl.h> #include <limits.h> #include <linux/landlock.h> #include <pthread.h> diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 73729382d40f..fa0f18ec62c4 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -1832,6 +1832,46 @@ TEST_F_FORK(layout1, release_inodes) ASSERT_EQ(ENOENT, test_open(dir_s3d3, O_RDONLY)); } +/* + * This test checks that a rule on a directory used as a mount point does not + * grant access to the mount covering it. It is a generalization of the bind + * mount case in layout3_fs.hostfs.release_inodes that tests hidden mount points. + */ +TEST_F_FORK(layout1, covered_rule) +{ + const struct rule layer1[] = { + { + .path = dir_s3d2, + .access = LANDLOCK_ACCESS_FS_READ_DIR, + }, + {}, + }; + int ruleset_fd; + + /* Unmount to simplify FIXTURE_TEARDOWN. */ + set_cap(_metadata, CAP_SYS_ADMIN); + ASSERT_EQ(0, umount(dir_s3d2)); + clear_cap(_metadata, CAP_SYS_ADMIN); + + /* Creates a ruleset with the future hidden directory. */ + ruleset_fd = + create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_DIR, layer1); + ASSERT_LE(0, ruleset_fd); + + /* Covers with a new mount point. */ + set_cap(_metadata, CAP_SYS_ADMIN); + ASSERT_EQ(0, mount_opt(&mnt_tmp, dir_s3d2)); + clear_cap(_metadata, CAP_SYS_ADMIN); + + ASSERT_EQ(0, test_open(dir_s3d2, O_RDONLY)); + + 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(dir_s3d2, O_RDONLY)); +} + enum relative_access { REL_OPEN, REL_CHDIR, diff --git a/tools/testing/selftests/lkdtm/config b/tools/testing/selftests/lkdtm/config index 7afe05e8c4d7..bd09fdaf53e0 100644 --- a/tools/testing/selftests/lkdtm/config +++ b/tools/testing/selftests/lkdtm/config @@ -2,7 +2,7 @@ CONFIG_LKDTM=y CONFIG_DEBUG_LIST=y CONFIG_SLAB_FREELIST_HARDENED=y CONFIG_FORTIFY_SOURCE=y -CONFIG_GCC_PLUGIN_STACKLEAK=y +CONFIG_KSTACK_ERASE=y CONFIG_HARDENED_USERCOPY=y CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT=y CONFIG_INIT_ON_FREE_DEFAULT_ON=y diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index aa7400ed0e99..f0d9c035641d 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -31,6 +31,7 @@ uint64_t pmd_pagesize; #define INPUT_MAX 80 #define PID_FMT "%d,0x%lx,0x%lx,%d" +#define PID_FMT_OFFSET "%d,0x%lx,0x%lx,%d,%d" #define PATH_FMT "%s,0x%lx,0x%lx,%d" #define PFN_MASK ((1UL<<55)-1) @@ -483,7 +484,7 @@ void split_thp_in_pagecache_to_order_at(size_t fd_size, const char *fs_loc, write_debugfs(PID_FMT, getpid(), (uint64_t)addr, (uint64_t)addr + fd_size, order); else - write_debugfs(PID_FMT, getpid(), (uint64_t)addr, + write_debugfs(PID_FMT_OFFSET, getpid(), (uint64_t)addr, (uint64_t)addr + fd_size, order, offset); for (i = 0; i < fd_size; i++) diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index c6dd2a335cf4..47c293c2962f 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -34,6 +34,7 @@ reuseport_bpf_numa reuseport_dualstack rxtimestamp sctp_hello +scm_inq scm_pidfd scm_rights sk_bind_sendto_listen diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 332f387615d7..b31a71f2b372 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -41,6 +41,7 @@ TEST_PROGS += netns-name.sh TEST_PROGS += link_netns.py TEST_PROGS += nl_netdev.py TEST_PROGS += rtnetlink.py +TEST_PROGS += rtnetlink_notification.sh TEST_PROGS += srv6_end_dt46_l3vpn_test.sh TEST_PROGS += srv6_end_dt4_l3vpn_test.sh TEST_PROGS += srv6_end_dt6_l3vpn_test.sh @@ -62,6 +63,7 @@ TEST_PROGS += ip_local_port_range.sh TEST_PROGS += rps_default_mask.sh TEST_PROGS += big_tcp.sh TEST_PROGS += netns-sysctl.sh +TEST_PROGS += netdev-l2addr.sh TEST_PROGS_EXTENDED := toeplitz_client.sh toeplitz.sh xfrm_policy_add_speed.sh TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any @@ -99,6 +101,7 @@ TEST_PROGS += test_vxlan_mdb.sh TEST_PROGS += test_bridge_neigh_suppress.sh TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_PROGS += test_bridge_backup_port.sh +TEST_PROGS += test_neigh.sh TEST_PROGS += fdb_flush.sh fdb_notify.sh TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh @@ -112,6 +115,8 @@ TEST_PROGS += skf_net_off.sh TEST_GEN_FILES += skf_net_off TEST_GEN_FILES += tfo TEST_PROGS += tfo_passive.sh +TEST_PROGS += broadcast_pmtu.sh +TEST_PROGS += ipv6_force_forwarding.sh # YNL files, must be before "include ..lib.mk" YNL_GEN_FILES := busy_poller netlink-dumps diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 50584479540b..a4b61c6d0290 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,4 +1,4 @@ CFLAGS += $(KHDR_INCLUDES) -TEST_GEN_PROGS := diag_uid msg_oob scm_pidfd scm_rights unix_connect +TEST_GEN_PROGS := diag_uid msg_oob scm_inq scm_pidfd scm_rights unix_connect include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/scm_inq.c b/tools/testing/selftests/net/af_unix/scm_inq.c new file mode 100644 index 000000000000..9d22561e7b8f --- /dev/null +++ b/tools/testing/selftests/net/af_unix/scm_inq.c @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2025 Google LLC */ + +#include <linux/sockios.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <sys/types.h> + +#include "../../kselftest_harness.h" + +#define NR_CHUNKS 100 +#define MSG_LEN 256 + +struct scm_inq { + struct cmsghdr cmsghdr; + int inq; +}; + +FIXTURE(scm_inq) +{ + int fd[2]; +}; + +FIXTURE_VARIANT(scm_inq) +{ + int type; +}; + +FIXTURE_VARIANT_ADD(scm_inq, stream) +{ + .type = SOCK_STREAM, +}; + +FIXTURE_VARIANT_ADD(scm_inq, dgram) +{ + .type = SOCK_DGRAM, +}; + +FIXTURE_VARIANT_ADD(scm_inq, seqpacket) +{ + .type = SOCK_SEQPACKET, +}; + +FIXTURE_SETUP(scm_inq) +{ + int err; + + err = socketpair(AF_UNIX, variant->type | SOCK_NONBLOCK, 0, self->fd); + ASSERT_EQ(0, err); +} + +FIXTURE_TEARDOWN(scm_inq) +{ + close(self->fd[0]); + close(self->fd[1]); +} + +static void send_chunks(struct __test_metadata *_metadata, + FIXTURE_DATA(scm_inq) *self) +{ + char buf[MSG_LEN] = {}; + int i, ret; + + for (i = 0; i < NR_CHUNKS; i++) { + ret = send(self->fd[0], buf, sizeof(buf), 0); + ASSERT_EQ(sizeof(buf), ret); + } +} + +static void recv_chunks(struct __test_metadata *_metadata, + FIXTURE_DATA(scm_inq) *self) +{ + struct msghdr msg = {}; + struct iovec iov = {}; + struct scm_inq cmsg; + char buf[MSG_LEN]; + int i, ret; + int inq; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = &cmsg; + msg.msg_controllen = CMSG_SPACE(sizeof(cmsg.inq)); + + iov.iov_base = buf; + iov.iov_len = sizeof(buf); + + for (i = 0; i < NR_CHUNKS; i++) { + memset(buf, 0, sizeof(buf)); + memset(&cmsg, 0, sizeof(cmsg)); + + ret = recvmsg(self->fd[1], &msg, 0); + ASSERT_EQ(MSG_LEN, ret); + ASSERT_NE(NULL, CMSG_FIRSTHDR(&msg)); + ASSERT_EQ(CMSG_LEN(sizeof(cmsg.inq)), cmsg.cmsghdr.cmsg_len); + ASSERT_EQ(SOL_SOCKET, cmsg.cmsghdr.cmsg_level); + ASSERT_EQ(SCM_INQ, cmsg.cmsghdr.cmsg_type); + + ret = ioctl(self->fd[1], SIOCINQ, &inq); + ASSERT_EQ(0, ret); + ASSERT_EQ(cmsg.inq, inq); + } +} + +TEST_F(scm_inq, basic) +{ + int err, inq; + + err = setsockopt(self->fd[1], SOL_SOCKET, SO_INQ, &(int){1}, sizeof(int)); + if (variant->type != SOCK_STREAM) { + ASSERT_EQ(-ENOPROTOOPT, -errno); + return; + } + + ASSERT_EQ(0, err); + + err = ioctl(self->fd[1], SIOCINQ, &inq); + ASSERT_EQ(0, err); + ASSERT_EQ(0, inq); + + send_chunks(_metadata, self); + recv_chunks(_metadata, self); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c index 7e534594167e..37e034874034 100644 --- a/tools/testing/selftests/net/af_unix/scm_pidfd.c +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -15,6 +15,7 @@ #include <sys/types.h> #include <sys/wait.h> +#include "../../pidfd/pidfd.h" #include "../../kselftest_harness.h" #define clean_errno() (errno == 0 ? "None" : strerror(errno)) @@ -26,6 +27,8 @@ #define SCM_PIDFD 0x04 #endif +#define CHILD_EXIT_CODE_OK 123 + static void child_die() { exit(1); @@ -126,16 +129,65 @@ out: return result; } +struct cmsg_data { + struct ucred *ucred; + int *pidfd; +}; + +static int parse_cmsg(struct msghdr *msg, struct cmsg_data *res) +{ + struct cmsghdr *cmsg; + int data = 0; + + 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(*res->pidfd)) { + log_err("CMSG parse: SCM_PIDFD wrong len"); + return 1; + } + + res->pidfd = (void *)CMSG_DATA(cmsg); + } + + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_CREDENTIALS) { + if (cmsg->cmsg_len < sizeof(*res->ucred)) { + log_err("CMSG parse: SCM_CREDENTIALS wrong len"); + return 1; + } + + res->ucred = (void *)CMSG_DATA(cmsg); + } + } + + if (!res->pidfd) { + log_err("CMSG parse: SCM_PIDFD not found"); + return 1; + } + + if (!res->ucred) { + log_err("CMSG parse: SCM_CREDENTIALS not found"); + return 1; + } + + return 0; +} + static int cmsg_check(int fd) { struct msghdr msg = { 0 }; - struct cmsghdr *cmsg; + struct cmsg_data res; 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; @@ -158,53 +210,99 @@ static int cmsg_check(int fd) 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; - } + /* send(pfd, "x", sizeof(char), 0) */ + if (data != 'x') { + log_err("recvmsg: data corruption"); + return 1; + } - pidfd = (void *)CMSG_DATA(cmsg); - } + if (parse_cmsg(&msg, &res)) { + log_err("CMSG parse: parse_cmsg() failed"); + return 1; + } - 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; - } + /* pidfd from SCM_PIDFD should point to the parent process PID */ + parent_pid = + get_pid_from_fdinfo_file(*res.pidfd, "Pid:", sizeof("Pid:") - 1); + if (parent_pid != getppid()) { + log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid()); + close(*res.pidfd); + return 1; + } - ucred = (void *)CMSG_DATA(cmsg); - } + close(*res.pidfd); + return 0; +} + +static int cmsg_check_dead(int fd, int expected_pid) +{ + int err; + struct msghdr msg = { 0 }; + struct cmsg_data res; + struct iovec iov; + int data = 0; + char control[CMSG_SPACE(sizeof(struct ucred)) + + CMSG_SPACE(sizeof(int))] = { 0 }; + pid_t client_pid; + struct pidfd_info info = { + .mask = PIDFD_INFO_EXIT, + }; + + 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; } - /* send(pfd, "x", sizeof(char), 0) */ - if (data != 'x') { + if (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) { + log_err("recvmsg: truncated"); + return 1; + } + + /* send(cfd, "y", sizeof(char), 0) */ + if (data != 'y') { log_err("recvmsg: data corruption"); return 1; } - if (!pidfd) { - log_err("CMSG parse: SCM_PIDFD not found"); + if (parse_cmsg(&msg, &res)) { + log_err("CMSG parse: parse_cmsg() failed"); return 1; } - if (!ucred) { - log_err("CMSG parse: SCM_CREDENTIALS not found"); + /* + * pidfd from SCM_PIDFD should point to the client_pid. + * Let's read exit information and check if it's what + * we expect to see. + */ + if (ioctl(*res.pidfd, PIDFD_GET_INFO, &info)) { + log_err("%s: ioctl(PIDFD_GET_INFO) failed", __func__); + close(*res.pidfd); 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()); + if (!(info.mask & PIDFD_INFO_EXIT)) { + log_err("%s: No exit information from ioctl(PIDFD_GET_INFO)", __func__); + close(*res.pidfd); return 1; } + err = WIFEXITED(info.exit_code) ? WEXITSTATUS(info.exit_code) : 1; + if (err != CHILD_EXIT_CODE_OK) { + log_err("%s: wrong exit_code %d != %d", __func__, err, CHILD_EXIT_CODE_OK); + close(*res.pidfd); + return 1; + } + + close(*res.pidfd); return 0; } @@ -291,6 +389,24 @@ static void fill_sockaddr(struct sock_addr *addr, bool abstract) memcpy(sun_path_buf, addr->sock_name, strlen(addr->sock_name)); } +static int sk_enable_cred_pass(int sk) +{ + int on = 0; + + on = 1; + if (setsockopt(sk, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) { + log_err("Failed to set SO_PASSCRED"); + return 1; + } + + if (setsockopt(sk, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) { + log_err("Failed to set SO_PASSPIDFD"); + return 1; + } + + return 0; +} + static void client(FIXTURE_DATA(scm_pidfd) *self, const FIXTURE_VARIANT(scm_pidfd) *variant) { @@ -299,7 +415,6 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, struct ucred peer_cred; int peer_pidfd; pid_t peer_pid; - int on = 0; cfd = socket(AF_UNIX, variant->type, 0); if (cfd < 0) { @@ -322,14 +437,8 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, 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"); + if (sk_enable_cred_pass(cfd)) { + log_err("sk_enable_cred_pass() failed"); child_die(); } @@ -340,6 +449,12 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, child_die(); } + /* send something to the parent so it can receive SCM_PIDFD too and validate it */ + if (send(cfd, "y", sizeof(char), 0) == -1) { + log_err("Failed to send(cfd, \"y\", sizeof(char), 0)"); + child_die(); + } + /* skip further for SOCK_DGRAM as it's not applicable */ if (variant->type == SOCK_DGRAM) return; @@ -398,7 +513,13 @@ TEST_F(scm_pidfd, test) close(self->server); close(self->startup_pipe[0]); client(self, variant); - exit(0); + + /* + * It's a bit unusual, but in case of success we return non-zero + * exit code (CHILD_EXIT_CODE_OK) and then we expect to read it + * from ioctl(PIDFD_GET_INFO) in cmsg_check_dead(). + */ + exit(CHILD_EXIT_CODE_OK); } close(self->startup_pipe[1]); @@ -421,9 +542,17 @@ TEST_F(scm_pidfd, test) ASSERT_NE(-1, err); } - close(pfd); waitpid(self->client_pid, &child_status, 0); - ASSERT_EQ(0, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1); + /* see comment before exit(CHILD_EXIT_CODE_OK) */ + ASSERT_EQ(CHILD_EXIT_CODE_OK, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1); + + err = sk_enable_cred_pass(pfd); + ASSERT_EQ(0, err); + + err = cmsg_check_dead(pfd, self->client_pid); + ASSERT_EQ(0, err); + + close(pfd); } TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/bench/Makefile b/tools/testing/selftests/net/bench/Makefile new file mode 100644 index 000000000000..2546c45e42f7 --- /dev/null +++ b/tools/testing/selftests/net/bench/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 + +TEST_GEN_MODS_DIR := page_pool + +TEST_PROGS += test_bench_page_pool.sh + +include ../../lib.mk diff --git a/tools/testing/selftests/net/bench/page_pool/Makefile b/tools/testing/selftests/net/bench/page_pool/Makefile new file mode 100644 index 000000000000..0549a16ba275 --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/Makefile @@ -0,0 +1,17 @@ +BENCH_PAGE_POOL_SIMPLE_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= /lib/modules/$(shell uname -r)/build + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +obj-m += bench_page_pool.o +bench_page_pool-y += bench_page_pool_simple.o time_bench.o + +all: + +$(Q)make -C $(KDIR) M=$(BENCH_PAGE_POOL_SIMPLE_TEST_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(BENCH_PAGE_POOL_SIMPLE_TEST_DIR) clean diff --git a/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c b/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c new file mode 100644 index 000000000000..cb6468adbda4 --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c @@ -0,0 +1,267 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Benchmark module for page_pool. + * + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/interrupt.h> +#include <linux/limits.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <net/page_pool/helpers.h> + +#include "time_bench.h" + +static int verbose = 1; +#define MY_POOL_SIZE 1024 + +/* Makes tests selectable. Useful for perf-record to analyze a single test. + * Hint: Bash shells support writing binary number like: $((2#101010) + * + * # modprobe bench_page_pool_simple run_flags=$((2#100)) + */ +static unsigned long run_flags = 0xFFFFFFFF; +module_param(run_flags, ulong, 0); +MODULE_PARM_DESC(run_flags, "Limit which bench test that runs"); + +/* Count the bit number from the enum */ +enum benchmark_bit { + bit_run_bench_baseline, + bit_run_bench_no_softirq01, + bit_run_bench_no_softirq02, + bit_run_bench_no_softirq03, +}; + +#define bit(b) (1 << (b)) +#define enabled(b) ((run_flags & (bit(b)))) + +/* notice time_bench is limited to U32_MAX nr loops */ +static unsigned long loops = 10000000; +module_param(loops, ulong, 0); +MODULE_PARM_DESC(loops, "Specify loops bench will run"); + +/* Timing at the nanosec level, we need to know the overhead + * introduced by the for loop itself + */ +static int time_bench_for_loop(struct time_bench_record *rec, void *data) +{ + uint64_t loops_cnt = 0; + int i; + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + loops_cnt++; + barrier(); /* avoid compiler to optimize this loop */ + } + time_bench_stop(rec, loops_cnt); + return loops_cnt; +} + +static int time_bench_atomic_inc(struct time_bench_record *rec, void *data) +{ + uint64_t loops_cnt = 0; + atomic_t cnt; + int i; + + atomic_set(&cnt, 0); + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + atomic_inc(&cnt); + barrier(); /* avoid compiler to optimize this loop */ + } + loops_cnt = atomic_read(&cnt); + time_bench_stop(rec, loops_cnt); + return loops_cnt; +} + +/* The ptr_ping in page_pool uses a spinlock. We need to know the minimum + * overhead of taking+releasing a spinlock, to know the cycles that can be saved + * by e.g. amortizing this via bulking. + */ +static int time_bench_lock(struct time_bench_record *rec, void *data) +{ + uint64_t loops_cnt = 0; + spinlock_t lock; + int i; + + spin_lock_init(&lock); + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + spin_lock(&lock); + loops_cnt++; + barrier(); /* avoid compiler to optimize this loop */ + spin_unlock(&lock); + } + time_bench_stop(rec, loops_cnt); + return loops_cnt; +} + +/* Helper for filling some page's into ptr_ring */ +static void pp_fill_ptr_ring(struct page_pool *pp, int elems) +{ + /* GFP_ATOMIC needed when under run softirq */ + gfp_t gfp_mask = GFP_ATOMIC; + struct page **array; + int i; + + array = kcalloc(elems, sizeof(struct page *), gfp_mask); + + for (i = 0; i < elems; i++) + array[i] = page_pool_alloc_pages(pp, gfp_mask); + for (i = 0; i < elems; i++) + page_pool_put_page(pp, array[i], -1, false); + + kfree(array); +} + +enum test_type { type_fast_path, type_ptr_ring, type_page_allocator }; + +/* Depends on compile optimizing this function */ +static int time_bench_page_pool(struct time_bench_record *rec, void *data, + enum test_type type, const char *func) +{ + uint64_t loops_cnt = 0; + gfp_t gfp_mask = GFP_ATOMIC; /* GFP_ATOMIC is not really needed */ + int i, err; + + struct page_pool *pp; + struct page *page; + + struct page_pool_params pp_params = { + .order = 0, + .flags = 0, + .pool_size = MY_POOL_SIZE, + .nid = NUMA_NO_NODE, + .dev = NULL, /* Only use for DMA mapping */ + .dma_dir = DMA_BIDIRECTIONAL, + }; + + pp = page_pool_create(&pp_params); + if (IS_ERR(pp)) { + err = PTR_ERR(pp); + pr_warn("%s: Error(%d) creating page_pool\n", func, err); + goto out; + } + pp_fill_ptr_ring(pp, 64); + + if (in_serving_softirq()) + pr_warn("%s(): in_serving_softirq fast-path\n", func); + else + pr_warn("%s(): Cannot use page_pool fast-path\n", func); + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + /* Common fast-path alloc that depend on in_serving_softirq() */ + page = page_pool_alloc_pages(pp, gfp_mask); + if (!page) + break; + loops_cnt++; + barrier(); /* avoid compiler to optimize this loop */ + + /* The benchmarks purpose it to test different return paths. + * Compiler should inline optimize other function calls out + */ + if (type == type_fast_path) { + /* Fast-path recycling e.g. XDP_DROP use-case */ + page_pool_recycle_direct(pp, page); + + } else if (type == type_ptr_ring) { + /* Normal return path */ + page_pool_put_page(pp, page, -1, false); + + } else if (type == type_page_allocator) { + /* Test if not pages are recycled, but instead + * returned back into systems page allocator + */ + get_page(page); /* cause no-recycling */ + page_pool_put_page(pp, page, -1, false); + put_page(page); + } else { + BUILD_BUG(); + } + } + time_bench_stop(rec, loops_cnt); +out: + page_pool_destroy(pp); + return loops_cnt; +} + +static int time_bench_page_pool01_fast_path(struct time_bench_record *rec, + void *data) +{ + return time_bench_page_pool(rec, data, type_fast_path, __func__); +} + +static int time_bench_page_pool02_ptr_ring(struct time_bench_record *rec, + void *data) +{ + return time_bench_page_pool(rec, data, type_ptr_ring, __func__); +} + +static int time_bench_page_pool03_slow(struct time_bench_record *rec, + void *data) +{ + return time_bench_page_pool(rec, data, type_page_allocator, __func__); +} + +static int run_benchmark_tests(void) +{ + uint32_t nr_loops = loops; + + /* Baseline tests */ + if (enabled(bit_run_bench_baseline)) { + time_bench_loop(nr_loops * 10, 0, "for_loop", NULL, + time_bench_for_loop); + time_bench_loop(nr_loops * 10, 0, "atomic_inc", NULL, + time_bench_atomic_inc); + time_bench_loop(nr_loops, 0, "lock", NULL, time_bench_lock); + } + + /* This test cannot activate correct code path, due to no-softirq ctx */ + if (enabled(bit_run_bench_no_softirq01)) + time_bench_loop(nr_loops, 0, "no-softirq-page_pool01", NULL, + time_bench_page_pool01_fast_path); + if (enabled(bit_run_bench_no_softirq02)) + time_bench_loop(nr_loops, 0, "no-softirq-page_pool02", NULL, + time_bench_page_pool02_ptr_ring); + if (enabled(bit_run_bench_no_softirq03)) + time_bench_loop(nr_loops, 0, "no-softirq-page_pool03", NULL, + time_bench_page_pool03_slow); + + return 0; +} + +static int __init bench_page_pool_simple_module_init(void) +{ + if (verbose) + pr_info("Loaded\n"); + + if (loops > U32_MAX) { + pr_err("Module param loops(%lu) exceeded U32_MAX(%u)\n", loops, + U32_MAX); + return -ECHRNG; + } + + run_benchmark_tests(); + + return 0; +} +module_init(bench_page_pool_simple_module_init); + +static void __exit bench_page_pool_simple_module_exit(void) +{ + if (verbose) + pr_info("Unloaded\n"); +} +module_exit(bench_page_pool_simple_module_exit); + +MODULE_DESCRIPTION("Benchmark of page_pool simple cases"); +MODULE_AUTHOR("Jesper Dangaard Brouer <[email protected]>"); +MODULE_LICENSE("GPL"); diff --git a/tools/testing/selftests/net/bench/page_pool/time_bench.c b/tools/testing/selftests/net/bench/page_pool/time_bench.c new file mode 100644 index 000000000000..073bb36ec5f2 --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/time_bench.c @@ -0,0 +1,394 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Benchmarking code execution time inside the kernel + * + * Copyright (C) 2014, Red Hat, Inc., Jesper Dangaard Brouer + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/time.h> + +#include <linux/perf_event.h> /* perf_event_create_kernel_counter() */ + +/* For concurrency testing */ +#include <linux/completion.h> +#include <linux/sched.h> +#include <linux/workqueue.h> +#include <linux/kthread.h> + +#include "time_bench.h" + +static int verbose = 1; + +/** TSC (Time-Stamp Counter) based ** + * See: linux/time_bench.h + * tsc_start_clock() and tsc_stop_clock() + */ + +/** Wall-clock based ** + */ + +/** PMU (Performance Monitor Unit) based ** + */ +#define PERF_FORMAT \ + (PERF_FORMAT_GROUP | PERF_FORMAT_ID | PERF_FORMAT_TOTAL_TIME_ENABLED | \ + PERF_FORMAT_TOTAL_TIME_RUNNING) + +struct raw_perf_event { + uint64_t config; /* event */ + uint64_t config1; /* umask */ + struct perf_event *save; + char *desc; +}; + +/* if HT is enable a maximum of 4 events (5 if one is instructions + * retired can be specified, if HT is disabled a maximum of 8 (9 if + * one is instructions retired) can be specified. + * + * From Table 19-1. Architectural Performance Events + * Architectures Software Developer’s Manual Volume 3: System Programming + * Guide + */ +struct raw_perf_event perf_events[] = { + { 0x3c, 0x00, NULL, "Unhalted CPU Cycles" }, + { 0xc0, 0x00, NULL, "Instruction Retired" } +}; + +#define NUM_EVTS (ARRAY_SIZE(perf_events)) + +/* WARNING: PMU config is currently broken! + */ +bool time_bench_PMU_config(bool enable) +{ + int i; + struct perf_event_attr perf_conf; + struct perf_event *perf_event; + int cpu; + + preempt_disable(); + cpu = smp_processor_id(); + pr_info("DEBUG: cpu:%d\n", cpu); + preempt_enable(); + + memset(&perf_conf, 0, sizeof(struct perf_event_attr)); + perf_conf.type = PERF_TYPE_RAW; + perf_conf.size = sizeof(struct perf_event_attr); + perf_conf.read_format = PERF_FORMAT; + perf_conf.pinned = 1; + perf_conf.exclude_user = 1; /* No userspace events */ + perf_conf.exclude_kernel = 0; /* Only kernel events */ + + for (i = 0; i < NUM_EVTS; i++) { + perf_conf.disabled = enable; + //perf_conf.disabled = (i == 0) ? 1 : 0; + perf_conf.config = perf_events[i].config; + perf_conf.config1 = perf_events[i].config1; + if (verbose) + pr_info("%s() enable PMU counter: %s\n", + __func__, perf_events[i].desc); + perf_event = perf_event_create_kernel_counter(&perf_conf, cpu, + NULL /* task */, + NULL /* overflow_handler*/, + NULL /* context */); + if (perf_event) { + perf_events[i].save = perf_event; + pr_info("%s():DEBUG perf_event success\n", __func__); + + perf_event_enable(perf_event); + } else { + pr_info("%s():DEBUG perf_event is NULL\n", __func__); + } + } + + return true; +} + +/** Generic functions ** + */ + +/* Calculate stats, store results in record */ +bool time_bench_calc_stats(struct time_bench_record *rec) +{ +#define NANOSEC_PER_SEC 1000000000 /* 10^9 */ + uint64_t ns_per_call_tmp_rem = 0; + uint32_t ns_per_call_remainder = 0; + uint64_t pmc_ipc_tmp_rem = 0; + uint32_t pmc_ipc_remainder = 0; + uint32_t pmc_ipc_div = 0; + uint32_t invoked_cnt_precision = 0; + uint32_t invoked_cnt = 0; /* 32-bit due to div_u64_rem() */ + + if (rec->flags & TIME_BENCH_LOOP) { + if (rec->invoked_cnt < 1000) { + pr_err("ERR: need more(>1000) loops(%llu) for timing\n", + rec->invoked_cnt); + return false; + } + if (rec->invoked_cnt > ((1ULL << 32) - 1)) { + /* div_u64_rem() can only support div with 32bit*/ + pr_err("ERR: Invoke cnt(%llu) too big overflow 32bit\n", + rec->invoked_cnt); + return false; + } + invoked_cnt = (uint32_t)rec->invoked_cnt; + } + + /* TSC (Time-Stamp Counter) records */ + if (rec->flags & TIME_BENCH_TSC) { + rec->tsc_interval = rec->tsc_stop - rec->tsc_start; + if (rec->tsc_interval == 0) { + pr_err("ABORT: timing took ZERO TSC time\n"); + return false; + } + /* Calculate stats */ + if (rec->flags & TIME_BENCH_LOOP) + rec->tsc_cycles = rec->tsc_interval / invoked_cnt; + else + rec->tsc_cycles = rec->tsc_interval; + } + + /* Wall-clock time calc */ + if (rec->flags & TIME_BENCH_WALLCLOCK) { + rec->time_start = rec->ts_start.tv_nsec + + (NANOSEC_PER_SEC * rec->ts_start.tv_sec); + rec->time_stop = rec->ts_stop.tv_nsec + + (NANOSEC_PER_SEC * rec->ts_stop.tv_sec); + rec->time_interval = rec->time_stop - rec->time_start; + if (rec->time_interval == 0) { + pr_err("ABORT: timing took ZERO wallclock time\n"); + return false; + } + /* Calculate stats */ + /*** Division in kernel it tricky ***/ + /* Orig: time_sec = (time_interval / NANOSEC_PER_SEC); */ + /* remainder only correct because NANOSEC_PER_SEC is 10^9 */ + rec->time_sec = div_u64_rem(rec->time_interval, NANOSEC_PER_SEC, + &rec->time_sec_remainder); + //TODO: use existing struct timespec records instead of div? + + if (rec->flags & TIME_BENCH_LOOP) { + /*** Division in kernel it tricky ***/ + /* Orig: ns = ((double)time_interval / invoked_cnt); */ + /* First get quotient */ + rec->ns_per_call_quotient = + div_u64_rem(rec->time_interval, invoked_cnt, + &ns_per_call_remainder); + /* Now get decimals .xxx precision (incorrect roundup)*/ + ns_per_call_tmp_rem = ns_per_call_remainder; + invoked_cnt_precision = invoked_cnt / 1000; + if (invoked_cnt_precision > 0) { + rec->ns_per_call_decimal = + div_u64_rem(ns_per_call_tmp_rem, + invoked_cnt_precision, + &ns_per_call_remainder); + } + } + } + + /* Performance Monitor Unit (PMU) counters */ + if (rec->flags & TIME_BENCH_PMU) { + //FIXME: Overflow handling??? + rec->pmc_inst = rec->pmc_inst_stop - rec->pmc_inst_start; + rec->pmc_clk = rec->pmc_clk_stop - rec->pmc_clk_start; + + /* Calc Instruction Per Cycle (IPC) */ + /* First get quotient */ + rec->pmc_ipc_quotient = div_u64_rem(rec->pmc_inst, rec->pmc_clk, + &pmc_ipc_remainder); + /* Now get decimals .xxx precision (incorrect roundup)*/ + pmc_ipc_tmp_rem = pmc_ipc_remainder; + pmc_ipc_div = rec->pmc_clk / 1000; + if (pmc_ipc_div > 0) { + rec->pmc_ipc_decimal = div_u64_rem(pmc_ipc_tmp_rem, + pmc_ipc_div, + &pmc_ipc_remainder); + } + } + + return true; +} + +/* Generic function for invoking a loop function and calculating + * execution time stats. The function being called/timed is assumed + * to perform a tight loop, and update the timing record struct. + */ +bool time_bench_loop(uint32_t loops, int step, char *txt, void *data, + int (*func)(struct time_bench_record *record, void *data)) +{ + struct time_bench_record rec; + + /* Setup record */ + memset(&rec, 0, sizeof(rec)); /* zero func might not update all */ + rec.version_abi = 1; + rec.loops = loops; + rec.step = step; + rec.flags = (TIME_BENCH_LOOP | TIME_BENCH_TSC | TIME_BENCH_WALLCLOCK); + + /*** Loop function being timed ***/ + if (!func(&rec, data)) { + pr_err("ABORT: function being timed failed\n"); + return false; + } + + if (rec.invoked_cnt < loops) + pr_warn("WARNING: Invoke count(%llu) smaller than loops(%d)\n", + rec.invoked_cnt, loops); + + /* Calculate stats */ + time_bench_calc_stats(&rec); + + pr_info("Type:%s Per elem: %llu cycles(tsc) %llu.%03llu ns (step:%d) - (measurement period time:%llu.%09u sec time_interval:%llu) - (invoke count:%llu tsc_interval:%llu)\n", + txt, rec.tsc_cycles, rec.ns_per_call_quotient, + rec.ns_per_call_decimal, rec.step, rec.time_sec, + rec.time_sec_remainder, rec.time_interval, rec.invoked_cnt, + rec.tsc_interval); + if (rec.flags & TIME_BENCH_PMU) + pr_info("Type:%s PMU inst/clock%llu/%llu = %llu.%03llu IPC (inst per cycle)\n", + txt, rec.pmc_inst, rec.pmc_clk, rec.pmc_ipc_quotient, + rec.pmc_ipc_decimal); + return true; +} + +/* Function getting invoked by kthread */ +static int invoke_test_on_cpu_func(void *private) +{ + struct time_bench_cpu *cpu = private; + struct time_bench_sync *sync = cpu->sync; + cpumask_t newmask = CPU_MASK_NONE; + void *data = cpu->data; + + /* Restrict CPU */ + cpumask_set_cpu(cpu->rec.cpu, &newmask); + set_cpus_allowed_ptr(current, &newmask); + + /* Synchronize start of concurrency test */ + atomic_inc(&sync->nr_tests_running); + wait_for_completion(&sync->start_event); + + /* Start benchmark function */ + if (!cpu->bench_func(&cpu->rec, data)) { + pr_err("ERROR: function being timed failed on CPU:%d(%d)\n", + cpu->rec.cpu, smp_processor_id()); + } else { + if (verbose) + pr_info("SUCCESS: ran on CPU:%d(%d)\n", cpu->rec.cpu, + smp_processor_id()); + } + cpu->did_bench_run = true; + + /* End test */ + atomic_dec(&sync->nr_tests_running); + /* Wait for kthread_stop() telling us to stop */ + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +void time_bench_print_stats_cpumask(const char *desc, + struct time_bench_cpu *cpu_tasks, + const struct cpumask *mask) +{ + uint64_t average = 0; + int cpu; + int step = 0; + struct sum { + uint64_t tsc_cycles; + int records; + } sum = { 0 }; + + /* Get stats */ + for_each_cpu(cpu, mask) { + struct time_bench_cpu *c = &cpu_tasks[cpu]; + struct time_bench_record *rec = &c->rec; + + /* Calculate stats */ + time_bench_calc_stats(rec); + + pr_info("Type:%s CPU(%d) %llu cycles(tsc) %llu.%03llu ns (step:%d) - (measurement period time:%llu.%09u sec time_interval:%llu) - (invoke count:%llu tsc_interval:%llu)\n", + desc, cpu, rec->tsc_cycles, rec->ns_per_call_quotient, + rec->ns_per_call_decimal, rec->step, rec->time_sec, + rec->time_sec_remainder, rec->time_interval, + rec->invoked_cnt, rec->tsc_interval); + + /* Collect average */ + sum.records++; + sum.tsc_cycles += rec->tsc_cycles; + step = rec->step; + } + + if (sum.records) /* avoid div-by-zero */ + average = sum.tsc_cycles / sum.records; + pr_info("Sum Type:%s Average: %llu cycles(tsc) CPUs:%d step:%d\n", desc, + average, sum.records, step); +} + +void time_bench_run_concurrent(uint32_t loops, int step, void *data, + const struct cpumask *mask, /* Support masking outsome CPUs*/ + struct time_bench_sync *sync, + struct time_bench_cpu *cpu_tasks, + int (*func)(struct time_bench_record *record, void *data)) +{ + int cpu, running = 0; + + if (verbose) // DEBUG + pr_warn("%s() Started on CPU:%d\n", __func__, + smp_processor_id()); + + /* Reset sync conditions */ + atomic_set(&sync->nr_tests_running, 0); + init_completion(&sync->start_event); + + /* Spawn off jobs on all CPUs */ + for_each_cpu(cpu, mask) { + struct time_bench_cpu *c = &cpu_tasks[cpu]; + + running++; + c->sync = sync; /* Send sync variable along */ + c->data = data; /* Send opaque along */ + + /* Init benchmark record */ + memset(&c->rec, 0, sizeof(struct time_bench_record)); + c->rec.version_abi = 1; + c->rec.loops = loops; + c->rec.step = step; + c->rec.flags = (TIME_BENCH_LOOP | TIME_BENCH_TSC | + TIME_BENCH_WALLCLOCK); + c->rec.cpu = cpu; + c->bench_func = func; + c->task = kthread_run(invoke_test_on_cpu_func, c, + "time_bench%d", cpu); + if (IS_ERR(c->task)) { + pr_err("%s(): Failed to start test func\n", __func__); + return; /* Argh, what about cleanup?! */ + } + } + + /* Wait until all processes are running */ + while (atomic_read(&sync->nr_tests_running) < running) { + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(10); + } + /* Kick off all CPU concurrently on completion event */ + complete_all(&sync->start_event); + + /* Wait for CPUs to finish */ + while (atomic_read(&sync->nr_tests_running)) { + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(10); + } + + /* Stop the kthreads */ + for_each_cpu(cpu, mask) { + struct time_bench_cpu *c = &cpu_tasks[cpu]; + + kthread_stop(c->task); + } + + if (verbose) // DEBUG - happens often, finish on another CPU + pr_warn("%s() Finished on CPU:%d\n", __func__, + smp_processor_id()); +} diff --git a/tools/testing/selftests/net/bench/page_pool/time_bench.h b/tools/testing/selftests/net/bench/page_pool/time_bench.h new file mode 100644 index 000000000000..e113fcf341dc --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/time_bench.h @@ -0,0 +1,238 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Benchmarking code execution time inside the kernel + * + * Copyright (C) 2014, Red Hat, Inc., Jesper Dangaard Brouer + * for licensing details see kernel-base/COPYING + */ +#ifndef _LINUX_TIME_BENCH_H +#define _LINUX_TIME_BENCH_H + +/* Main structure used for recording a benchmark run */ +struct time_bench_record { + uint32_t version_abi; + uint32_t loops; /* Requested loop invocations */ + uint32_t step; /* option for e.g. bulk invocations */ + + uint32_t flags; /* Measurements types enabled */ +#define TIME_BENCH_LOOP BIT(0) +#define TIME_BENCH_TSC BIT(1) +#define TIME_BENCH_WALLCLOCK BIT(2) +#define TIME_BENCH_PMU BIT(3) + + uint32_t cpu; /* Used when embedded in time_bench_cpu */ + + /* Records */ + uint64_t invoked_cnt; /* Returned actual invocations */ + uint64_t tsc_start; + uint64_t tsc_stop; + struct timespec64 ts_start; + struct timespec64 ts_stop; + /* PMU counters for instruction and cycles + * instructions counter including pipelined instructions + */ + uint64_t pmc_inst_start; + uint64_t pmc_inst_stop; + /* CPU unhalted clock counter */ + uint64_t pmc_clk_start; + uint64_t pmc_clk_stop; + + /* Result records */ + uint64_t tsc_interval; + uint64_t time_start, time_stop, time_interval; /* in nanosec */ + uint64_t pmc_inst, pmc_clk; + + /* Derived result records */ + uint64_t tsc_cycles; // +decimal? + uint64_t ns_per_call_quotient, ns_per_call_decimal; + uint64_t time_sec; + uint32_t time_sec_remainder; + uint64_t pmc_ipc_quotient, pmc_ipc_decimal; /* inst per cycle */ +}; + +/* For synchronizing parallel CPUs to run concurrently */ +struct time_bench_sync { + atomic_t nr_tests_running; + struct completion start_event; +}; + +/* Keep track of CPUs executing our bench function. + * + * Embed a time_bench_record for storing info per cpu + */ +struct time_bench_cpu { + struct time_bench_record rec; + struct time_bench_sync *sync; /* back ptr */ + struct task_struct *task; + /* "data" opaque could have been placed in time_bench_sync, + * but to avoid any false sharing, place it per CPU + */ + void *data; + /* Support masking outsome CPUs, mark if it ran */ + bool did_bench_run; + /* int cpu; // note CPU stored in time_bench_record */ + int (*bench_func)(struct time_bench_record *record, void *data); +}; + +/* + * Below TSC assembler code is not compatible with other archs, and + * can also fail on guests if cpu-flags are not correct. + * + * The way TSC reading is used, many iterations, does not require as + * high accuracy as described below (in Intel Doc #324264). + * + * Considering changing to use get_cycles() (#include <asm/timex.h>). + */ + +/** TSC (Time-Stamp Counter) based ** + * Recommend reading, to understand details of reading TSC accurately: + * Intel Doc #324264, "How to Benchmark Code Execution Times on Intel" + * + * Consider getting exclusive ownership of CPU by using: + * unsigned long flags; + * preempt_disable(); + * raw_local_irq_save(flags); + * _your_code_ + * raw_local_irq_restore(flags); + * preempt_enable(); + * + * Clobbered registers: "%rax", "%rbx", "%rcx", "%rdx" + * RDTSC only change "%rax" and "%rdx" but + * CPUID clears the high 32-bits of all (rax/rbx/rcx/rdx) + */ +static __always_inline uint64_t tsc_start_clock(void) +{ + /* See: Intel Doc #324264 */ + unsigned int hi, lo; + + asm volatile("CPUID\n\t" + "RDTSC\n\t" + "mov %%edx, %0\n\t" + "mov %%eax, %1\n\t" + : "=r"(hi), "=r"(lo)::"%rax", "%rbx", "%rcx", "%rdx"); + //FIXME: on 32bit use clobbered %eax + %edx + return ((uint64_t)lo) | (((uint64_t)hi) << 32); +} + +static __always_inline uint64_t tsc_stop_clock(void) +{ + /* See: Intel Doc #324264 */ + unsigned int hi, lo; + + asm volatile("RDTSCP\n\t" + "mov %%edx, %0\n\t" + "mov %%eax, %1\n\t" + "CPUID\n\t" + : "=r"(hi), "=r"(lo)::"%rax", "%rbx", "%rcx", "%rdx"); + return ((uint64_t)lo) | (((uint64_t)hi) << 32); +} + +/** Wall-clock based ** + * + * use: getnstimeofday() + * getnstimeofday(&rec->ts_start); + * getnstimeofday(&rec->ts_stop); + * + * API changed see: Documentation/core-api/timekeeping.rst + * https://www.kernel.org/doc/html/latest/core-api/timekeeping.html#c.getnstimeofday + * + * We should instead use: ktime_get_real_ts64() is a direct + * replacement, but consider using monotonic time (ktime_get_ts64()) + * and/or a ktime_t based interface (ktime_get()/ktime_get_real()). + */ + +/** PMU (Performance Monitor Unit) based ** + * + * Needed for calculating: Instructions Per Cycle (IPC) + * - The IPC number tell how efficient the CPU pipelining were + */ +//lookup: perf_event_create_kernel_counter() + +bool time_bench_PMU_config(bool enable); + +/* Raw reading via rdpmc() using fixed counters + * + * From: https://github.com/andikleen/simple-pmu + */ +enum { + FIXED_SELECT = (1U << 30), /* == 0x40000000 */ + FIXED_INST_RETIRED_ANY = 0, + FIXED_CPU_CLK_UNHALTED_CORE = 1, + FIXED_CPU_CLK_UNHALTED_REF = 2, +}; + +static __always_inline unsigned int long long p_rdpmc(unsigned int in) +{ + unsigned int d, a; + + asm volatile("rdpmc" : "=d"(d), "=a"(a) : "c"(in) : "memory"); + return ((unsigned long long)d << 32) | a; +} + +/* These PMU counter needs to be enabled, but I don't have the + * configure code implemented. My current hack is running: + * sudo perf stat -e cycles:k -e instructions:k insmod lib/ring_queue_test.ko + */ +/* Reading all pipelined instruction */ +static __always_inline unsigned long long pmc_inst(void) +{ + return p_rdpmc(FIXED_SELECT | FIXED_INST_RETIRED_ANY); +} + +/* Reading CPU clock cycles */ +static __always_inline unsigned long long pmc_clk(void) +{ + return p_rdpmc(FIXED_SELECT | FIXED_CPU_CLK_UNHALTED_CORE); +} + +/* Raw reading via MSR rdmsr() is likely wrong + * FIXME: How can I know which raw MSR registers are conf for what? + */ +#define MSR_IA32_PCM0 0x400000C1 /* PERFCTR0 */ +#define MSR_IA32_PCM1 0x400000C2 /* PERFCTR1 */ +#define MSR_IA32_PCM2 0x400000C3 +static inline uint64_t msr_inst(unsigned long long *msr_result) +{ + return rdmsrq_safe(MSR_IA32_PCM0, msr_result); +} + +/** Generic functions ** + */ +bool time_bench_loop(uint32_t loops, int step, char *txt, void *data, + int (*func)(struct time_bench_record *rec, void *data)); +bool time_bench_calc_stats(struct time_bench_record *rec); + +void time_bench_run_concurrent(uint32_t loops, int step, void *data, + const struct cpumask *mask, /* Support masking outsome CPUs*/ + struct time_bench_sync *sync, struct time_bench_cpu *cpu_tasks, + int (*func)(struct time_bench_record *record, void *data)); +void time_bench_print_stats_cpumask(const char *desc, + struct time_bench_cpu *cpu_tasks, + const struct cpumask *mask); + +//FIXME: use rec->flags to select measurement, should be MACRO +static __always_inline void time_bench_start(struct time_bench_record *rec) +{ + //getnstimeofday(&rec->ts_start); + ktime_get_real_ts64(&rec->ts_start); + if (rec->flags & TIME_BENCH_PMU) { + rec->pmc_inst_start = pmc_inst(); + rec->pmc_clk_start = pmc_clk(); + } + rec->tsc_start = tsc_start_clock(); +} + +static __always_inline void time_bench_stop(struct time_bench_record *rec, + uint64_t invoked_cnt) +{ + rec->tsc_stop = tsc_stop_clock(); + if (rec->flags & TIME_BENCH_PMU) { + rec->pmc_inst_stop = pmc_inst(); + rec->pmc_clk_stop = pmc_clk(); + } + //getnstimeofday(&rec->ts_stop); + ktime_get_real_ts64(&rec->ts_stop); + rec->invoked_cnt = invoked_cnt; +} + +#endif /* _LINUX_TIME_BENCH_H */ diff --git a/tools/testing/selftests/net/bench/test_bench_page_pool.sh b/tools/testing/selftests/net/bench/test_bench_page_pool.sh new file mode 100755 index 000000000000..7b8b18cfedce --- /dev/null +++ b/tools/testing/selftests/net/bench/test_bench_page_pool.sh @@ -0,0 +1,32 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# + +set -e + +DRIVER="./page_pool/bench_page_pool.ko" +result="" + +function run_test() +{ + rmmod "bench_page_pool.ko" || true + insmod $DRIVER > /dev/null 2>&1 + result=$(dmesg | tail -10) + echo "$result" + + echo + echo "Fast path results:" + echo "${result}" | grep -o -E "no-softirq-page_pool01 Per elem: ([0-9]+) cycles\(tsc\) ([0-9]+\.[0-9]+) ns" + + echo + echo "ptr_ring results:" + echo "${result}" | grep -o -E "no-softirq-page_pool02 Per elem: ([0-9]+) cycles\(tsc\) ([0-9]+\.[0-9]+) ns" + + echo + echo "slow path results:" + echo "${result}" | grep -o -E "no-softirq-page_pool03 Per elem: ([0-9]+) cycles\(tsc\) ([0-9]+\.[0-9]+) ns" +} + +run_test + +exit 0 diff --git a/tools/testing/selftests/net/broadcast_pmtu.sh b/tools/testing/selftests/net/broadcast_pmtu.sh new file mode 100755 index 000000000000..726eb5d25839 --- /dev/null +++ b/tools/testing/selftests/net/broadcast_pmtu.sh @@ -0,0 +1,47 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Ensures broadcast route MTU is respected + +CLIENT_NS=$(mktemp -u client-XXXXXXXX) +CLIENT_IP4="192.168.0.1/24" +CLIENT_BROADCAST_ADDRESS="192.168.0.255" + +SERVER_NS=$(mktemp -u server-XXXXXXXX) +SERVER_IP4="192.168.0.2/24" + +setup() { + ip netns add "${CLIENT_NS}" + ip netns add "${SERVER_NS}" + + ip -net "${SERVER_NS}" link add link1 type veth peer name link0 netns "${CLIENT_NS}" + + ip -net "${CLIENT_NS}" link set link0 up + ip -net "${CLIENT_NS}" link set link0 mtu 9000 + ip -net "${CLIENT_NS}" addr add "${CLIENT_IP4}" dev link0 + + ip -net "${SERVER_NS}" link set link1 up + ip -net "${SERVER_NS}" link set link1 mtu 1500 + ip -net "${SERVER_NS}" addr add "${SERVER_IP4}" dev link1 + + read -r -a CLIENT_BROADCAST_ENTRY <<< "$(ip -net "${CLIENT_NS}" route show table local type broadcast)" + ip -net "${CLIENT_NS}" route del "${CLIENT_BROADCAST_ENTRY[@]}" + ip -net "${CLIENT_NS}" route add "${CLIENT_BROADCAST_ENTRY[@]}" mtu 1500 + + ip net exec "${SERVER_NS}" sysctl -wq net.ipv4.icmp_echo_ignore_broadcasts=0 +} + +cleanup() { + ip -net "${SERVER_NS}" link del link1 + ip netns del "${CLIENT_NS}" + ip netns del "${SERVER_NS}" +} + +trap cleanup EXIT + +setup && + echo "Testing for broadcast route MTU" && + ip net exec "${CLIENT_NS}" ping -f -M want -q -c 1 -s 8000 -w 1 -b "${CLIENT_BROADCAST_ADDRESS}" > /dev/null 2>&1 + +exit $? + diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 3cfef5153823..c24417d0047b 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -30,16 +30,25 @@ CONFIG_NET_FOU=y CONFIG_NET_FOU_IP_TUNNELS=y CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y +CONFIG_NETFILTER_XTABLES_LEGACY=y CONFIG_NF_CONNTRACK=m CONFIG_IPV6_MROUTE=y CONFIG_IPV6_SIT=y CONFIG_NF_NAT=m CONFIG_IP6_NF_IPTABLES=m +CONFIG_IP6_NF_IPTABLES_LEGACY=m CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_IPTABLES_LEGACY=m +CONFIG_IP6_NF_MANGLE=m +CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_RAW=m +CONFIG_IP_NF_MANGLE=m +CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_NAT=m CONFIG_IP_NF_RAW=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_TTL=m CONFIG_IPV6_GRE=m CONFIG_IPV6_SEG6_LWTUNNEL=y @@ -57,6 +66,8 @@ CONFIG_NF_TABLES_IPV6=y CONFIG_NF_TABLES_IPV4=y CONFIG_NFT_NAT=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m +CONFIG_NETFILTER_XT_TARGET_HL=m +CONFIG_NETFILTER_XT_NAT=m CONFIG_NET_ACT_CSUM=m CONFIG_NET_ACT_CT=m CONFIG_NET_ACT_GACT=m diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 00bde7b6f39e..d7bb2e80e88c 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -102,6 +102,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \ vxlan_bridge_1d_port_8472.sh \ vxlan_bridge_1d.sh \ vxlan_bridge_1q_ipv6.sh \ + vxlan_bridge_1q_mc_ul.sh \ vxlan_bridge_1q_port_8472_ipv6.sh \ vxlan_bridge_1q_port_8472.sh \ vxlan_bridge_1q.sh \ diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 508f3c700d71..890b3374dacd 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -37,6 +37,7 @@ declare -A NETIFS=( : "${TEAMD:=teamd}" : "${MCD:=smcrouted}" : "${MC_CLI:=smcroutectl}" +: "${MCD_TABLE_NAME:=selftests}" # Constants for netdevice bring-up: # Default time in seconds to wait for an interface to come up before giving up @@ -141,6 +142,20 @@ check_tc_version() fi } +check_tc_erspan_support() +{ + local dev=$1; shift + + tc filter add dev $dev ingress pref 1 handle 1 flower \ + erspan_opts 1:0:0:0 &> /dev/null + if [[ $? -ne 0 ]]; then + echo "SKIP: iproute2 too old; tc is missing erspan support" + return $ksft_skip + fi + tc filter del dev $dev ingress pref 1 handle 1 flower \ + erspan_opts 1:0:0:0 &> /dev/null +} + # Old versions of tc don't understand "mpls_uc" check_tc_mpls_support() { @@ -525,9 +540,9 @@ setup_wait_dev_with_timeout() return 1 } -setup_wait() +setup_wait_n() { - local num_netifs=${1:-$NUM_NETIFS} + local num_netifs=$1; shift local i for ((i = 1; i <= num_netifs; ++i)); do @@ -538,6 +553,11 @@ setup_wait() sleep $WAIT_TIME } +setup_wait() +{ + setup_wait_n "$NUM_NETIFS" +} + wait_for_dev() { local dev=$1; shift @@ -1757,6 +1777,51 @@ mc_send() msend -g $groups -I $if_name -c 1 > /dev/null 2>&1 } +adf_mcd_start() +{ + local ifs=("$@") + + local table_name="$MCD_TABLE_NAME" + local smcroutedir + local pid + local if + local i + + check_command "$MCD" || return 1 + check_command "$MC_CLI" || return 1 + + smcroutedir=$(mktemp -d) + defer rm -rf "$smcroutedir" + + for ((i = 1; i <= NUM_NETIFS; ++i)); do + echo "phyint ${NETIFS[p$i]} enable" >> \ + "$smcroutedir/$table_name.conf" + done + + for if in "${ifs[@]}"; do + if ! ip_link_has_flag "$if" MULTICAST; then + ip link set dev "$if" multicast on + defer ip link set dev "$if" multicast off + fi + + echo "phyint $if enable" >> \ + "$smcroutedir/$table_name.conf" + done + + "$MCD" -N -I "$table_name" -f "$smcroutedir/$table_name.conf" \ + -P "$smcroutedir/$table_name.pid" + busywait "$BUSYWAIT_TIMEOUT" test -e "$smcroutedir/$table_name.pid" + pid=$(cat "$smcroutedir/$table_name.pid") + defer kill_process "$pid" +} + +mc_cli() +{ + local table_name="$MCD_TABLE_NAME" + + "$MC_CLI" -I "$table_name" "$@" +} + start_ip_monitor() { local mtype=$1; shift diff --git a/tools/testing/selftests/net/forwarding/router_multicast.sh b/tools/testing/selftests/net/forwarding/router_multicast.sh index 5a58b1ec8aef..83e52abdbc2e 100755 --- a/tools/testing/selftests/net/forwarding/router_multicast.sh +++ b/tools/testing/selftests/net/forwarding/router_multicast.sh @@ -33,10 +33,6 @@ NUM_NETIFS=6 source lib.sh source tc_common.sh -require_command $MCD -require_command $MC_CLI -table_name=selftests - h1_create() { simple_if_init $h1 198.51.100.2/28 2001:db8:1::2/64 @@ -149,25 +145,6 @@ router_destroy() ip link set dev $rp1 down } -start_mcd() -{ - SMCROUTEDIR="$(mktemp -d)" - - for ((i = 1; i <= $NUM_NETIFS; ++i)); do - echo "phyint ${NETIFS[p$i]} enable" >> \ - $SMCROUTEDIR/$table_name.conf - done - - $MCD -N -I $table_name -f $SMCROUTEDIR/$table_name.conf \ - -P $SMCROUTEDIR/$table_name.pid -} - -kill_mcd() -{ - pkill $MCD - rm -rf $SMCROUTEDIR -} - setup_prepare() { h1=${NETIFS[p1]} @@ -179,7 +156,7 @@ setup_prepare() rp3=${NETIFS[p5]} h3=${NETIFS[p6]} - start_mcd + adf_mcd_start || exit "$EXIT_STATUS" vrf_prepare @@ -206,7 +183,7 @@ cleanup() vrf_cleanup - kill_mcd + defer_scopes_cleanup } create_mcast_sg() @@ -214,9 +191,9 @@ create_mcast_sg() local if_name=$1; shift local s_addr=$1; shift local mcast=$1; shift - local dest_ifs=${@} + local dest_ifs=("${@}") - $MC_CLI -I $table_name add $if_name $s_addr $mcast $dest_ifs + mc_cli add "$if_name" "$s_addr" "$mcast" "${dest_ifs[@]}" } delete_mcast_sg() @@ -224,9 +201,9 @@ delete_mcast_sg() local if_name=$1; shift local s_addr=$1; shift local mcast=$1; shift - local dest_ifs=${@} + local dest_ifs=("${@}") - $MC_CLI -I $table_name remove $if_name $s_addr $mcast $dest_ifs + mc_cli remove "$if_name" "$s_addr" "$mcast" "${dest_ifs[@]}" } mcast_v4() diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh index b1daad19b01e..b58909a93112 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower.sh @@ -6,7 +6,7 @@ ALL_TESTS="match_dst_mac_test match_src_mac_test match_dst_ip_test \ match_ip_tos_test match_indev_test match_ip_ttl_test match_mpls_label_test \ match_mpls_tc_test match_mpls_bos_test match_mpls_ttl_test \ - match_mpls_lse_test" + match_mpls_lse_test match_erspan_opts_test" NUM_NETIFS=2 source tc_common.sh source lib.sh @@ -676,6 +676,56 @@ match_mpls_lse_test() log_test "mpls lse match ($tcflags)" } +match_erspan_opts_test() +{ + RET=0 + + check_tc_erspan_support $h2 || return 0 + + # h1 erspan setup + tunnel_create erspan1 erspan 192.0.2.1 192.0.2.2 dev $h1 seq key 1001 \ + tos C ttl 64 erspan_ver 1 erspan 6789 # ERSPAN Type II + tunnel_create erspan2 erspan 192.0.2.1 192.0.2.2 dev $h1 seq key 1002 \ + tos C ttl 64 erspan_ver 2 erspan_dir egress erspan_hwid 63 \ + # ERSPAN Type III + ip link set dev erspan1 master v$h1 + ip link set dev erspan2 master v$h1 + # h2 erspan setup + ip link add ep-ex type erspan ttl 64 external # To collect tunnel info + ip link set ep-ex up + ip link set dev ep-ex master v$h2 + tc qdisc add dev ep-ex clsact + + # ERSPAN Type II [decap direction] + tc filter add dev ep-ex ingress protocol ip handle 101 flower \ + $tcflags enc_src_ip 192.0.2.1 enc_dst_ip 192.0.2.2 \ + enc_key_id 1001 erspan_opts 1:6789:0:0 \ + action drop + # ERSPAN Type III [decap direction] + tc filter add dev ep-ex ingress protocol ip handle 102 flower \ + $tcflags enc_src_ip 192.0.2.1 enc_dst_ip 192.0.2.2 \ + enc_key_id 1002 erspan_opts 2:0:1:63 action drop + + ep1mac=$(mac_get erspan1) + $MZ erspan1 -c 1 -p 64 -a $ep1mac -b $h2mac -t ip -q + tc_check_packets "dev ep-ex ingress" 101 1 + check_err $? "ERSPAN Type II" + + ep2mac=$(mac_get erspan2) + $MZ erspan2 -c 1 -p 64 -a $ep1mac -b $h2mac -t ip -q + tc_check_packets "dev ep-ex ingress" 102 1 + check_err $? "ERSPAN Type III" + + # h2 erspan cleanup + tc qdisc del dev ep-ex clsact + tunnel_destroy ep-ex + # h1 erspan cleanup + tunnel_destroy erspan2 # ERSPAN Type III + tunnel_destroy erspan1 # ERSPAN Type II + + log_test "erspan_opts match ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh new file mode 100755 index 000000000000..462db0b603e7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh @@ -0,0 +1,771 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +-----------------------------------------+ +# | + $h1.10 + $h1.20 | +# | | 192.0.2.1/28 | 2001:db8:1::1/64 | +# | \________ ________/ | +# | \ / | +# | + $h1 H1 (vrf) | +# +-----------|-----------------------------+ +# | +# +-----------|----------------------------------------------------------------+ +# | +---------|--------------------------------------+ SWITCH (main vrf) | +# | | + $swp1 BR1 (802.1q) | | +# | | vid 10 20 | | +# | | | | +# | | + vx10 (vxlan) + vx20 (vxlan) | + lo10 (dummy) | +# | | local 192.0.2.100 local 2001:db8:4::1 | 192.0.2.100/28 | +# | | group 233.252.0.1 group ff0e::1:2:3 | 2001:db8:4::1/64 | +# | | id 1000 id 2000 | | +# | | vid 10 pvid untagged vid 20 pvid untagged | | +# | +------------------------------------------------+ | +# | | +# | + $swp2 $swp3 + | +# | | 192.0.2.33/28 192.0.2.65/28 | | +# | | 2001:db8:2::1/64 2001:db8:3::1/64 | | +# | | | | +# +---|--------------------------------------------------------------------|---+ +# | | +# +---|--------------------------------+ +--------------------------------|---+ +# | | H2 (vrf) | | H3 (vrf) | | +# | +-|----------------------------+ | | +-----------------------------|-+ | +# | | + $h2 BR2 (802.1d) | | | | BR3 (802.1d) $h3 + | | +# | | | | | | | | +# | | + v1$h2 (veth) | | | | v1$h3 (veth) + | | +# | +-|----------------------------+ | | +-----------------------------|-+ | +# | | | | | | +# +---|--------------------------------+ +--------------------------------|---+ +# | | +# +---|--------------------------------+ +--------------------------------|---+ +# | + v2$h2 (veth) NS2 (netns) | | NS3 (netns) v2$h3 (veth) + | +# | 192.0.2.34/28 | | 192.0.2.66/28 | +# | 2001:db8:2::2/64 | | 2001:db8:3::2/64 | +# | | | | +# | +--------------------------------+ | | +--------------------------------+ | +# | | BR1 (802.1q) | | | | BR1 (802.1q) | | +# | | + vx10 (vxlan) | | | | + vx10 (vxlan) | | +# | | local 192.0.2.34 | | | | local 192.0.2.50 | | +# | | group 233.252.0.1 dev v2$h2 | | | | group 233.252.0.1 dev v2$h3 | | +# | | id 1000 dstport $VXPORT | | | | id 1000 dstport $VXPORT | | +# | | vid 10 pvid untagged | | | | vid 10 pvid untagged | | +# | | | | | | | | +# | | + vx20 (vxlan) | | | | + vx20 (vxlan) | | +# | | local 2001:db8:2::2 | | | | local 2001:db8:3::2 | | +# | | group ff0e::1:2:3 dev v2$h2 | | | | group ff0e::1:2:3 dev v2$h3 | | +# | | id 2000 dstport $VXPORT | | | | id 2000 dstport $VXPORT | | +# | | vid 20 pvid untagged | | | | vid 20 pvid untagged | | +# | | | | | | | | +# | | + w1 (veth) | | | | + w1 (veth) | | +# | | | vid 10 20 | | | | | vid 10 20 | | +# | +--|-----------------------------+ | | +--|-----------------------------+ | +# | | | | | | +# | +--|-----------------------------+ | | +--|-----------------------------+ | +# | | + w2 (veth) VW2 (vrf) | | | | + w2 (veth) VW2 (vrf) | | +# | | |\ | | | | |\ | | +# | | | + w2.10 | | | | | + w2.10 | | +# | | | 192.0.2.3/28 | | | | | 192.0.2.4/28 | | +# | | | | | | | | | | +# | | + w2.20 | | | | + w2.20 | | +# | | 2001:db8:1::3/64 | | | | 2001:db8:1::4/64 | | +# | +--------------------------------+ | | +--------------------------------+ | +# +------------------------------------+ +------------------------------------+ +# +#shellcheck disable=SC2317 # SC doesn't see our uses of functions. + +: "${VXPORT:=4789}" +export VXPORT + +: "${GROUP4:=233.252.0.1}" +export GROUP4 + +: "${GROUP6:=ff0e::1:2:3}" +export GROUP6 + +: "${IPMR:=lo10}" + +ALL_TESTS=" + ipv4_nomcroute + ipv4_mcroute + ipv4_mcroute_changelink + ipv4_mcroute_starg + ipv4_mcroute_noroute + ipv4_mcroute_fdb + ipv4_mcroute_fdb_oif0 + ipv4_mcroute_fdb_oif0_sep + + ipv6_nomcroute + ipv6_mcroute + ipv6_mcroute_changelink + ipv6_mcroute_starg + ipv6_mcroute_noroute + ipv6_mcroute_fdb + ipv6_mcroute_fdb_oif0 + + ipv4_nomcroute_rx + ipv4_mcroute_rx + ipv4_mcroute_starg_rx + ipv4_mcroute_fdb_oif0_sep_rx + ipv4_mcroute_fdb_sep_rx + + ipv6_nomcroute_rx + ipv6_mcroute_rx + ipv6_mcroute_starg_rx + ipv6_mcroute_fdb_sep_rx +" + +NUM_NETIFS=6 +source lib.sh + +h1_create() +{ + simple_if_init "$h1" + defer simple_if_fini "$h1" + + ip_link_add "$h1.10" master "v$h1" link "$h1" type vlan id 10 + ip_link_set_up "$h1.10" + ip_addr_add "$h1.10" 192.0.2.1/28 + + ip_link_add "$h1.20" master "v$h1" link "$h1" type vlan id 20 + ip_link_set_up "$h1.20" + ip_addr_add "$h1.20" 2001:db8:1::1/64 +} + +install_capture() +{ + local dev=$1; shift + + tc qdisc add dev "$dev" clsact + defer tc qdisc del dev "$dev" clsact + + tc filter add dev "$dev" ingress proto ip pref 104 \ + flower skip_hw ip_proto udp dst_port "$VXPORT" \ + action pass + defer tc filter del dev "$dev" ingress proto ip pref 104 + + tc filter add dev "$dev" ingress proto ipv6 pref 106 \ + flower skip_hw ip_proto udp dst_port "$VXPORT" \ + action pass + defer tc filter del dev "$dev" ingress proto ipv6 pref 106 +} + +h2_create() +{ + # $h2 + ip_link_set_up "$h2" + + # H2 + vrf_create "v$h2" + defer vrf_destroy "v$h2" + + ip_link_set_up "v$h2" + + # br2 + ip_link_add br2 type bridge vlan_filtering 0 mcast_snooping 0 + ip_link_set_master br2 "v$h2" + ip_link_set_up br2 + + # $h2 + ip_link_set_master "$h2" br2 + install_capture "$h2" + + # v1$h2 + ip_link_set_up "v1$h2" + ip_link_set_master "v1$h2" br2 +} + +h3_create() +{ + # $h3 + ip_link_set_up "$h3" + + # H3 + vrf_create "v$h3" + defer vrf_destroy "v$h3" + + ip_link_set_up "v$h3" + + # br3 + ip_link_add br3 type bridge vlan_filtering 0 mcast_snooping 0 + ip_link_set_master br3 "v$h3" + ip_link_set_up br3 + + # $h3 + ip_link_set_master "$h3" br3 + install_capture "$h3" + + # v1$h3 + ip_link_set_up "v1$h3" + ip_link_set_master "v1$h3" br3 +} + +switch_create() +{ + local swp1_mac + + # br1 + swp1_mac=$(mac_get "$swp1") + ip_link_add br1 type bridge vlan_filtering 1 \ + vlan_default_pvid 0 mcast_snooping 0 + ip_link_set_addr br1 "$swp1_mac" + ip_link_set_up br1 + + # A dummy to force the IPv6 OIF=0 test to install a suitable MC route on + # $IPMR to be deterministic. Also used for the IPv6 RX!=TX ping test. + ip_link_add "X$IPMR" up type dummy + + # IPMR + ip_link_add "$IPMR" up type dummy + ip_addr_add "$IPMR" 192.0.2.100/28 + ip_addr_add "$IPMR" 2001:db8:4::1/64 + + # $swp1 + ip_link_set_up "$swp1" + ip_link_set_master "$swp1" br1 + bridge_vlan_add vid 10 dev "$swp1" + bridge_vlan_add vid 20 dev "$swp1" + + # $swp2 + ip_link_set_up "$swp2" + ip_addr_add "$swp2" 192.0.2.33/28 + ip_addr_add "$swp2" 2001:db8:2::1/64 + + # $swp3 + ip_link_set_up "$swp3" + ip_addr_add "$swp3" 192.0.2.65/28 + ip_addr_add "$swp3" 2001:db8:3::1/64 +} + +vx_create() +{ + local name=$1; shift + local vid=$1; shift + + ip_link_add "$name" up type vxlan dstport "$VXPORT" \ + nolearning noudpcsum tos inherit ttl 16 \ + "$@" + ip_link_set_master "$name" br1 + bridge_vlan_add vid "$vid" dev "$name" pvid untagged +} +export -f vx_create + +vx_wait() +{ + # Wait for all the ARP, IGMP etc. noise to settle down so that the + # tunnel is clear for measurements. + sleep 10 +} + +vx10_create() +{ + vx_create vx10 10 id 1000 "$@" +} +export -f vx10_create + +vx20_create() +{ + vx_create vx20 20 id 2000 "$@" +} +export -f vx20_create + +vx10_create_wait() +{ + vx10_create "$@" + vx_wait +} + +vx20_create_wait() +{ + vx20_create "$@" + vx_wait +} + +ns_init_common() +{ + local ns=$1; shift + local if_in=$1; shift + local ipv4_in=$1; shift + local ipv6_in=$1; shift + local ipv4_host=$1; shift + local ipv6_host=$1; shift + + # v2$h2 / v2$h3 + ip_link_set_up "$if_in" + ip_addr_add "$if_in" "$ipv4_in" + ip_addr_add "$if_in" "$ipv6_in" + + # br1 + ip_link_add br1 type bridge vlan_filtering 1 \ + vlan_default_pvid 0 mcast_snooping 0 + ip_link_set_up br1 + + # vx10, vx20 + vx10_create local "${ipv4_in%/*}" group "$GROUP4" dev "$if_in" + vx20_create local "${ipv6_in%/*}" group "$GROUP6" dev "$if_in" + + # w1 + ip_link_add w1 type veth peer name w2 + ip_link_set_master w1 br1 + ip_link_set_up w1 + bridge_vlan_add vid 10 dev w1 + bridge_vlan_add vid 20 dev w1 + + # w2 + simple_if_init w2 + defer simple_if_fini w2 + + # w2.10 + ip_link_add w2.10 master vw2 link w2 type vlan id 10 + ip_link_set_up w2.10 + ip_addr_add w2.10 "$ipv4_host" + + # w2.20 + ip_link_add w2.20 master vw2 link w2 type vlan id 20 + ip_link_set_up w2.20 + ip_addr_add w2.20 "$ipv6_host" +} +export -f ns_init_common + +ns2_create() +{ + # NS2 + ip netns add ns2 + defer ip netns del ns2 + + # v2$h2 + ip link set dev "v2$h2" netns ns2 + defer ip -n ns2 link set dev "v2$h2" netns 1 + + in_ns ns2 \ + ns_init_common ns2 "v2$h2" \ + 192.0.2.34/28 2001:db8:2::2/64 \ + 192.0.2.3/28 2001:db8:1::3/64 +} + +ns3_create() +{ + # NS3 + ip netns add ns3 + defer ip netns del ns3 + + # v2$h3 + ip link set dev "v2$h3" netns ns3 + defer ip -n ns3 link set dev "v2$h3" netns 1 + + ip -n ns3 link set dev "v2$h3" up + + in_ns ns3 \ + ns_init_common ns3 "v2$h3" \ + 192.0.2.66/28 2001:db8:3::2/64 \ + 192.0.2.4/28 2001:db8:1::4/64 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + defer vrf_cleanup + + forwarding_enable + defer forwarding_restore + + ip_link_add "v1$h2" type veth peer name "v2$h2" + ip_link_add "v1$h3" type veth peer name "v2$h3" + + h1_create + h2_create + h3_create + switch_create + ns2_create + ns3_create +} + +adf_install_broken_sg() +{ + adf_mcd_start "$IPMR" || exit "$EXIT_STATUS" + + mc_cli add "$swp2" 192.0.2.100 "$GROUP4" "$swp1" "$swp3" + defer mc_cli remove "$swp2" 192.0.2.100 "$GROUP4" "$swp1" "$swp3" + + mc_cli add "$swp2" 2001:db8:4::1 "$GROUP6" "$swp1" "$swp3" + defer mc_cli remove "$swp2" 2001:db8:4::1 "$GROUP6" "$swp1" "$swp3" +} + +adf_install_rx() +{ + mc_cli add "$swp2" 0.0.0.0 "$GROUP4" "$IPMR" + defer mc_cli remove "$swp2" 0.0.0.0 "$GROUP4" lo10 + + mc_cli add "$swp3" 0.0.0.0 "$GROUP4" "$IPMR" + defer mc_cli remove "$swp3" 0.0.0.0 "$GROUP4" lo10 + + mc_cli add "$swp2" :: "$GROUP6" "$IPMR" + defer mc_cli remove "$swp2" :: "$GROUP6" lo10 + + mc_cli add "$swp3" :: "$GROUP6" "$IPMR" + defer mc_cli remove "$swp3" :: "$GROUP6" lo10 +} + +adf_install_sg() +{ + adf_mcd_start "$IPMR" || exit "$EXIT_STATUS" + + mc_cli add "$IPMR" 192.0.2.100 "$GROUP4" "$swp2" "$swp3" + defer mc_cli remove "$IPMR" 192.0.2.33 "$GROUP4" "$swp2" "$swp3" + + mc_cli add "$IPMR" 2001:db8:4::1 "$GROUP6" "$swp2" "$swp3" + defer mc_cli remove "$IPMR" 2001:db8:4::1 "$GROUP6" "$swp2" "$swp3" + + adf_install_rx +} + +adf_install_sg_sep() +{ + adf_mcd_start lo || exit "$EXIT_STATUS" + + mc_cli add lo 192.0.2.120 "$GROUP4" "$swp2" "$swp3" + defer mc_cli remove lo 192.0.2.120 "$GROUP4" "$swp2" "$swp3" + + mc_cli add lo 2001:db8:5::1 "$GROUP6" "$swp2" "$swp3" + defer mc_cli remove lo 2001:db8:5::1 "$GROUP6" "$swp2" "$swp3" +} + +adf_install_sg_sep_rx() +{ + local lo=$1; shift + + adf_mcd_start "$IPMR" "$lo" || exit "$EXIT_STATUS" + + mc_cli add "$lo" 192.0.2.120 "$GROUP4" "$swp2" "$swp3" + defer mc_cli remove "$lo" 192.0.2.120 "$GROUP4" "$swp2" "$swp3" + + mc_cli add "$lo" 2001:db8:5::1 "$GROUP6" "$swp2" "$swp3" + defer mc_cli remove "$lo" 2001:db8:5::1 "$GROUP6" "$swp2" "$swp3" + + adf_install_rx +} + +adf_install_starg() +{ + adf_mcd_start "$IPMR" || exit "$EXIT_STATUS" + + mc_cli add "$IPMR" 0.0.0.0 "$GROUP4" "$swp2" "$swp3" + defer mc_cli remove "$IPMR" 0.0.0.0 "$GROUP4" "$swp2" "$swp3" + + mc_cli add "$IPMR" :: "$GROUP6" "$swp2" "$swp3" + defer mc_cli remove "$IPMR" :: "$GROUP6" "$swp2" "$swp3" + + adf_install_rx +} + +do_packets_v4() +{ + local mac + + mac=$(mac_get "$h2") + "$MZ" "$h1" -Q 10 -c 10 -d 100msec -p 64 -a own -b "$mac" \ + -A 192.0.2.1 -B 192.0.2.2 -t udp sp=1234,dp=2345 -q +} + +do_packets_v6() +{ + local mac + + mac=$(mac_get "$h2") + "$MZ" -6 "$h1" -Q 20 -c 10 -d 100msec -p 64 -a own -b "$mac" \ + -A 2001:db8:1::1 -B 2001:db8:1::2 -t udp sp=1234,dp=2345 -q +} + +do_test() +{ + local ipv=$1; shift + local expect_h2=$1; shift + local expect_h3=$1; shift + local what=$1; shift + + local pref=$((100 + ipv)) + local t0_h2 + local t0_h3 + local t1_h2 + local t1_h3 + local d_h2 + local d_h3 + + RET=0 + + t0_h2=$(tc_rule_stats_get "$h2" "$pref" ingress) + t0_h3=$(tc_rule_stats_get "$h3" "$pref" ingress) + + "do_packets_v$ipv" + sleep 1 + + t1_h2=$(tc_rule_stats_get "$h2" "$pref" ingress) + t1_h3=$(tc_rule_stats_get "$h3" "$pref" ingress) + + d_h2=$((t1_h2 - t0_h2)) + d_h3=$((t1_h3 - t0_h3)) + + ((d_h2 == expect_h2)) + check_err $? "Expected $expect_h2 packets on H2, got $d_h2" + + ((d_h3 == expect_h3)) + check_err $? "Expected $expect_h3 packets on H3, got $d_h3" + + log_test "VXLAN MC flood $what" +} + +ipv4_do_test_rx() +{ + local h3_should_fail=$1; shift + local what=$1; shift + + RET=0 + + ping_do "$h1.10" 192.0.2.3 + check_err $? "H2 should respond" + + ping_do "$h1.10" 192.0.2.4 + check_err_fail "$h3_should_fail" $? "H3 responds" + + log_test "VXLAN MC flood $what" +} + +ipv6_do_test_rx() +{ + local h3_should_fail=$1; shift + local what=$1; shift + + RET=0 + + ping6_do "$h1.20" 2001:db8:1::3 + check_err $? "H2 should respond" + + ping6_do "$h1.20" 2001:db8:1::4 + check_err_fail "$h3_should_fail" $? "H3 responds" + + log_test "VXLAN MC flood $what" +} + +ipv4_nomcroute() +{ + # Install a misleading (S,G) rule to attempt to trick the system into + # pushing the packets elsewhere. + adf_install_broken_sg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$swp2" + do_test 4 10 0 "IPv4 nomcroute" +} + +ipv6_nomcroute() +{ + # Like for IPv4, install a misleading (S,G). + adf_install_broken_sg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$swp2" + do_test 6 10 0 "IPv6 nomcroute" +} + +ipv4_nomcroute_rx() +{ + vx10_create local 192.0.2.100 group "$GROUP4" dev "$swp2" + ipv4_do_test_rx 1 "IPv4 nomcroute ping" +} + +ipv6_nomcroute_rx() +{ + vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$swp2" + ipv6_do_test_rx 1 "IPv6 nomcroute ping" +} + +ipv4_mcroute() +{ + adf_install_sg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + do_test 4 10 10 "IPv4 mcroute" +} + +ipv6_mcroute() +{ + adf_install_sg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + do_test 6 10 10 "IPv6 mcroute" +} + +ipv4_mcroute_rx() +{ + adf_install_sg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + ipv4_do_test_rx 0 "IPv4 mcroute ping" +} + +ipv6_mcroute_rx() +{ + adf_install_sg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + ipv6_do_test_rx 0 "IPv6 mcroute ping" +} + +ipv4_mcroute_changelink() +{ + adf_install_sg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" + ip link set dev vx10 type vxlan mcroute + sleep 1 + do_test 4 10 10 "IPv4 mcroute changelink" +} + +ipv6_mcroute_changelink() +{ + adf_install_sg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + ip link set dev vx20 type vxlan mcroute + sleep 1 + do_test 6 10 10 "IPv6 mcroute changelink" +} + +ipv4_mcroute_starg() +{ + adf_install_starg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + do_test 4 10 10 "IPv4 mcroute (*,G)" +} + +ipv6_mcroute_starg() +{ + adf_install_starg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + do_test 6 10 10 "IPv6 mcroute (*,G)" +} + +ipv4_mcroute_starg_rx() +{ + adf_install_starg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + ipv4_do_test_rx 0 "IPv4 mcroute (*,G) ping" +} + +ipv6_mcroute_starg_rx() +{ + adf_install_starg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + ipv6_do_test_rx 0 "IPv6 mcroute (*,G) ping" +} + +ipv4_mcroute_noroute() +{ + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + do_test 4 0 0 "IPv4 mcroute, no route" +} + +ipv6_mcroute_noroute() +{ + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + do_test 6 0 0 "IPv6 mcroute, no route" +} + +ipv4_mcroute_fdb() +{ + adf_install_sg + vx10_create_wait local 192.0.2.100 dev "$IPMR" mcroute + bridge fdb add dev vx10 \ + 00:00:00:00:00:00 self static dst "$GROUP4" via "$IPMR" + do_test 4 10 10 "IPv4 mcroute FDB" +} + +ipv6_mcroute_fdb() +{ + adf_install_sg + vx20_create_wait local 2001:db8:4::1 dev "$IPMR" mcroute + bridge -6 fdb add dev vx20 \ + 00:00:00:00:00:00 self static dst "$GROUP6" via "$IPMR" + do_test 6 10 10 "IPv6 mcroute FDB" +} + +# Use FDB to configure VXLAN in a way where oif=0 for purposes of FIB lookup. +ipv4_mcroute_fdb_oif0() +{ + adf_install_sg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + bridge fdb del dev vx10 00:00:00:00:00:00 + bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" + do_test 4 10 10 "IPv4 mcroute oif=0" +} + +ipv6_mcroute_fdb_oif0() +{ + # The IPv6 tunnel lookup does not fall back to selection by source + # address. Instead it just does a FIB match, and that would find one of + # the several ff00::/8 multicast routes -- each device has one. In order + # to reliably force the $IPMR device, add a /128 route for the + # destination group address. + ip -6 route add table local multicast "$GROUP6/128" dev "$IPMR" + defer ip -6 route del table local multicast "$GROUP6/128" dev "$IPMR" + + adf_install_sg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + bridge -6 fdb del dev vx20 00:00:00:00:00:00 + bridge -6 fdb add dev vx20 00:00:00:00:00:00 self static dst "$GROUP6" + do_test 6 10 10 "IPv6 mcroute oif=0" +} + +# In oif=0 test as above, have FIB lookup resolve to loopback instead of IPMR. +# This doesn't work with IPv6 -- a MC route on lo would be marked as RTF_REJECT. +ipv4_mcroute_fdb_oif0_sep() +{ + adf_install_sg_sep + + ip_addr_add lo 192.0.2.120/28 + vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute + bridge fdb del dev vx10 00:00:00:00:00:00 + bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" + do_test 4 10 10 "IPv4 mcroute TX!=RX oif=0" +} + +ipv4_mcroute_fdb_oif0_sep_rx() +{ + adf_install_sg_sep_rx lo + + ip_addr_add lo 192.0.2.120/28 + vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute + bridge fdb del dev vx10 00:00:00:00:00:00 + bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" + ipv4_do_test_rx 0 "IPv4 mcroute TX!=RX oif=0 ping" +} + +ipv4_mcroute_fdb_sep_rx() +{ + adf_install_sg_sep_rx lo + + ip_addr_add lo 192.0.2.120/28 + vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute + bridge fdb del dev vx10 00:00:00:00:00:00 + bridge fdb add \ + dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" via lo + ipv4_do_test_rx 0 "IPv4 mcroute TX!=RX ping" +} + +ipv6_mcroute_fdb_sep_rx() +{ + adf_install_sg_sep_rx "X$IPMR" + + ip_addr_add "X$IPMR" 2001:db8:5::1/64 + vx20_create_wait local 2001:db8:5::1 group "$GROUP6" dev "$IPMR" mcroute + bridge -6 fdb del dev vx20 00:00:00:00:00:00 + bridge -6 fdb add dev vx20 00:00:00:00:00:00 \ + self static dst "$GROUP6" via "X$IPMR" + ipv6_do_test_rx 0 "IPv6 mcroute TX!=RX ping" +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/ipv6_force_forwarding.sh b/tools/testing/selftests/net/ipv6_force_forwarding.sh new file mode 100755 index 000000000000..bf0243366caa --- /dev/null +++ b/tools/testing/selftests/net/ipv6_force_forwarding.sh @@ -0,0 +1,105 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test IPv6 force_forwarding interface property +# +# This test verifies that the force_forwarding property works correctly: +# - When global forwarding is disabled, packets are not forwarded normally +# - When force_forwarding is enabled on an interface, packets are forwarded +# regardless of the global forwarding setting + +source lib.sh + +cleanup() { + cleanup_ns $ns1 $ns2 $ns3 +} + +trap cleanup EXIT + +setup_test() { + # Create three namespaces: sender, router, receiver + setup_ns ns1 ns2 ns3 + + # Create veth pairs: ns1 <-> ns2 <-> ns3 + ip link add name veth12 type veth peer name veth21 + ip link add name veth23 type veth peer name veth32 + + # Move interfaces to namespaces + ip link set veth12 netns $ns1 + ip link set veth21 netns $ns2 + ip link set veth23 netns $ns2 + ip link set veth32 netns $ns3 + + # Configure interfaces + ip -n $ns1 addr add 2001:db8:1::1/64 dev veth12 nodad + ip -n $ns2 addr add 2001:db8:1::2/64 dev veth21 nodad + ip -n $ns2 addr add 2001:db8:2::1/64 dev veth23 nodad + ip -n $ns3 addr add 2001:db8:2::2/64 dev veth32 nodad + + # Bring up interfaces + ip -n $ns1 link set veth12 up + ip -n $ns2 link set veth21 up + ip -n $ns2 link set veth23 up + ip -n $ns3 link set veth32 up + + # Add routes + ip -n $ns1 route add 2001:db8:2::/64 via 2001:db8:1::2 + ip -n $ns3 route add 2001:db8:1::/64 via 2001:db8:2::1 + + # Disable global forwarding + ip netns exec $ns2 sysctl -qw net.ipv6.conf.all.forwarding=0 +} + +test_force_forwarding() { + local ret=0 + + echo "TEST: force_forwarding functionality" + + # Check if force_forwarding sysctl exists + if ! ip netns exec $ns2 test -f /proc/sys/net/ipv6/conf/veth21/force_forwarding; then + echo "SKIP: force_forwarding not available" + return $ksft_skip + fi + + # Test 1: Without force_forwarding, ping should fail + ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth21.force_forwarding=0 + ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth23.force_forwarding=0 + + if ip netns exec $ns1 ping -6 -c 1 -W 2 2001:db8:2::2 &>/dev/null; then + echo "FAIL: ping succeeded when forwarding disabled" + ret=1 + else + echo "PASS: forwarding disabled correctly" + fi + + # Test 2: With force_forwarding enabled, ping should succeed + ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth21.force_forwarding=1 + ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth23.force_forwarding=1 + + if ip netns exec $ns1 ping -6 -c 1 -W 2 2001:db8:2::2 &>/dev/null; then + echo "PASS: force_forwarding enabled forwarding" + else + echo "FAIL: ping failed with force_forwarding enabled" + ret=1 + fi + + return $ret +} + +echo "IPv6 force_forwarding test" +echo "==========================" + +setup_test +test_force_forwarding +ret=$? + +if [ $ret -eq 0 ]; then + echo "OK" + exit 0 +elif [ $ret -eq $ksft_skip ]; then + echo "SKIP" + exit $ksft_skip +else + echo "FAIL" + exit 1 +fi diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 86a216e9aca8..c7add0dc4c60 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -240,6 +240,29 @@ create_netdevsim() { echo nsim$id } +create_netdevsim_port() { + local nsim_id="$1" + local ns="$2" + local port_id="$3" + local perm_addr="$4" + local orig_dev + local new_dev + local nsim_path + + nsim_path="/sys/bus/netdevsim/devices/netdevsim$nsim_id" + + echo "$port_id $perm_addr" | ip netns exec "$ns" tee "$nsim_path"/new_port > /dev/null || return 1 + + orig_dev=$(ip netns exec "$ns" find "$nsim_path"/net/ -maxdepth 1 -name 'e*' | tail -n 1) + orig_dev=$(basename "$orig_dev") + new_dev="nsim${nsim_id}p$port_id" + + ip -netns "$ns" link set dev "$orig_dev" name "$new_dev" + ip -netns "$ns" link set dev "$new_dev" up + + echo "$new_dev" +} + # Remove netdevsim with given id. cleanup_netdevsim() { local id="$1" @@ -547,13 +570,19 @@ ip_link_set_addr() defer ip link set dev "$name" address "$old_addr" } -ip_link_is_up() +ip_link_has_flag() { local name=$1; shift + local flag=$1; shift local state=$(ip -j link show "$name" | - jq -r '(.[].flags[] | select(. == "UP")) // "DOWN"') - [[ $state == "UP" ]] + jq --arg flag "$flag" 'any(.[].flags.[]; . == $flag)') + [[ $state == true ]] +} + +ip_link_is_up() +{ + ip_link_has_flag "$1" UP } ip_link_set_up() diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py index 8697bd27dc30..02be28dcc089 100644 --- a/tools/testing/selftests/net/lib/py/__init__.py +++ b/tools/testing/selftests/net/lib/py/__init__.py @@ -6,4 +6,4 @@ from .netns import NetNS, NetNSEnter from .nsim import * from .utils import * from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily -from .ynl import NetshaperFamily +from .ynl import NetshaperFamily, DevlinkFamily diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 61287c203b6e..8e35ed12ed9e 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -32,6 +32,7 @@ class KsftTerminate(KeyboardInterrupt): def ksft_pr(*objs, **kwargs): + kwargs["flush"] = True print("#", *objs, **kwargs) @@ -139,7 +140,7 @@ def ktap_result(ok, cnt=1, case="", comment=""): res += "." + str(case.__name__) if comment: res += " # " + comment - print(res) + print(res, flush=True) def ksft_flush_defer(): @@ -227,8 +228,8 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()): totals = {"pass": 0, "fail": 0, "skip": 0, "xfail": 0} - print("TAP version 13") - print("1.." + str(len(cases))) + print("TAP version 13", flush=True) + print("1.." + str(len(cases)), flush=True) global KSFT_RESULT cnt = 0 diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py index 34470d65d871..f395c90fb0f1 100644 --- a/tools/testing/selftests/net/lib/py/utils.py +++ b/tools/testing/selftests/net/lib/py/utils.py @@ -175,6 +175,10 @@ def tool(name, args, json=None, ns=None, host=None): return cmd_obj +def bpftool(args, json=None, ns=None, host=None): + return tool('bpftool', args, json=json, ns=ns, host=host) + + def ip(args, json=None, ns=None, host=None): if ns: args = f'-netns {ns} ' + args @@ -185,6 +189,41 @@ def ethtool(args, json=None, ns=None, host=None): return tool('ethtool', args, json=json, ns=ns, host=host) +def bpftrace(expr, json=None, ns=None, host=None, timeout=None): + """ + Run bpftrace and return map data (if json=True). + The output of bpftrace is inconvenient, so the helper converts + to a dict indexed by map name, e.g.: + { + "@": { ... }, + "@map2": { ... }, + } + """ + cmd_arr = ['bpftrace'] + # Throw in --quiet if json, otherwise the output has two objects + if json: + cmd_arr += ['-f', 'json', '-q'] + if timeout: + expr += ' interval:s:' + str(timeout) + ' { exit(); }' + cmd_arr += ['-e', expr] + cmd_obj = cmd(cmd_arr, ns=ns, host=host, shell=False) + if json: + # bpftrace prints objects as lines + ret = {} + for l in cmd_obj.stdout.split('\n'): + if not l.strip(): + continue + one = _json.loads(l) + if one.get('type') != 'map': + continue + for k, v in one["data"].items(): + if k.startswith('@'): + k = k.lstrip('@') + ret[k] = v + return ret + return cmd_obj + + def rand_port(type=socket.SOCK_STREAM): """ Get a random unprivileged port. diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py index 6329ae805abf..2b3a61ea3bfa 100644 --- a/tools/testing/selftests/net/lib/py/ynl.py +++ b/tools/testing/selftests/net/lib/py/ynl.py @@ -56,3 +56,8 @@ class NetshaperFamily(YnlFamily): def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('net_shaper.yaml')).as_posix(), schema='', recv_size=recv_size) + +class DevlinkFamily(YnlFamily): + def __init__(self, recv_size=0): + super().__init__((SPEC_PATH / Path('devlink.yaml')).as_posix(), + schema='', recv_size=recv_size) diff --git a/tools/testing/selftests/net/lib/xdp_native.bpf.c b/tools/testing/selftests/net/lib/xdp_native.bpf.c new file mode 100644 index 000000000000..521ba38f2ddd --- /dev/null +++ b/tools/testing/selftests/net/lib/xdp_native.bpf.c @@ -0,0 +1,621 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stddef.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/udp.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +#define MAX_ADJST_OFFSET 256 +#define MAX_PAYLOAD_LEN 5000 +#define MAX_HDR_LEN 64 + +enum { + XDP_MODE = 0, + XDP_PORT = 1, + XDP_ADJST_OFFSET = 2, + XDP_ADJST_TAG = 3, +} xdp_map_setup_keys; + +enum { + XDP_MODE_PASS = 0, + XDP_MODE_DROP = 1, + XDP_MODE_TX = 2, + XDP_MODE_TAIL_ADJST = 3, + XDP_MODE_HEAD_ADJST = 4, +} xdp_map_modes; + +enum { + STATS_RX = 0, + STATS_PASS = 1, + STATS_DROP = 2, + STATS_TX = 3, + STATS_ABORT = 4, +} xdp_stats; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 5); + __type(key, __u32); + __type(value, __s32); +} map_xdp_setup SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 5); + __type(key, __u32); + __type(value, __u64); +} map_xdp_stats SEC(".maps"); + +static __u32 min(__u32 a, __u32 b) +{ + return a < b ? a : b; +} + +static void record_stats(struct xdp_md *ctx, __u32 stat_type) +{ + __u64 *count; + + count = bpf_map_lookup_elem(&map_xdp_stats, &stat_type); + + if (count) + __sync_fetch_and_add(count, 1); +} + +static struct udphdr *filter_udphdr(struct xdp_md *ctx, __u16 port) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct udphdr *udph = NULL; + struct ethhdr *eth = data; + + if (data + sizeof(*eth) > data_end) + return NULL; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = data + sizeof(*eth); + + if (iph + 1 > (struct iphdr *)data_end || + iph->protocol != IPPROTO_UDP) + return NULL; + + udph = (void *)eth + sizeof(*iph) + sizeof(*eth); + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ipv6h = data + sizeof(*eth); + + if (ipv6h + 1 > (struct ipv6hdr *)data_end || + ipv6h->nexthdr != IPPROTO_UDP) + return NULL; + + udph = (void *)eth + sizeof(*ipv6h) + sizeof(*eth); + } else { + return NULL; + } + + if (udph + 1 > (struct udphdr *)data_end) + return NULL; + + if (udph->dest != bpf_htons(port)) + return NULL; + + record_stats(ctx, STATS_RX); + + return udph; +} + +static int xdp_mode_pass(struct xdp_md *ctx, __u16 port) +{ + struct udphdr *udph = NULL; + + udph = filter_udphdr(ctx, port); + if (!udph) + return XDP_PASS; + + record_stats(ctx, STATS_PASS); + + return XDP_PASS; +} + +static int xdp_mode_drop_handler(struct xdp_md *ctx, __u16 port) +{ + struct udphdr *udph = NULL; + + udph = filter_udphdr(ctx, port); + if (!udph) + return XDP_PASS; + + record_stats(ctx, STATS_DROP); + + return XDP_DROP; +} + +static void swap_machdr(void *data) +{ + struct ethhdr *eth = data; + __u8 tmp_mac[ETH_ALEN]; + + __builtin_memcpy(tmp_mac, eth->h_source, ETH_ALEN); + __builtin_memcpy(eth->h_source, eth->h_dest, ETH_ALEN); + __builtin_memcpy(eth->h_dest, tmp_mac, ETH_ALEN); +} + +static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct udphdr *udph = NULL; + struct ethhdr *eth = data; + + if (data + sizeof(*eth) > data_end) + return XDP_PASS; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = data + sizeof(*eth); + __be32 tmp_ip = iph->saddr; + + if (iph + 1 > (struct iphdr *)data_end || + iph->protocol != IPPROTO_UDP) + return XDP_PASS; + + udph = data + sizeof(*iph) + sizeof(*eth); + + if (udph + 1 > (struct udphdr *)data_end) + return XDP_PASS; + if (udph->dest != bpf_htons(port)) + return XDP_PASS; + + record_stats(ctx, STATS_RX); + swap_machdr((void *)eth); + + iph->saddr = iph->daddr; + iph->daddr = tmp_ip; + + record_stats(ctx, STATS_TX); + + return XDP_TX; + + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ipv6h = data + sizeof(*eth); + struct in6_addr tmp_ipv6; + + if (ipv6h + 1 > (struct ipv6hdr *)data_end || + ipv6h->nexthdr != IPPROTO_UDP) + return XDP_PASS; + + udph = data + sizeof(*ipv6h) + sizeof(*eth); + + if (udph + 1 > (struct udphdr *)data_end) + return XDP_PASS; + if (udph->dest != bpf_htons(port)) + return XDP_PASS; + + record_stats(ctx, STATS_RX); + swap_machdr((void *)eth); + + __builtin_memcpy(&tmp_ipv6, &ipv6h->saddr, sizeof(tmp_ipv6)); + __builtin_memcpy(&ipv6h->saddr, &ipv6h->daddr, + sizeof(tmp_ipv6)); + __builtin_memcpy(&ipv6h->daddr, &tmp_ipv6, sizeof(tmp_ipv6)); + + record_stats(ctx, STATS_TX); + + return XDP_TX; + } + + return XDP_PASS; +} + +static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct udphdr *udph = NULL; + struct ethhdr *eth = data; + __u32 len, len_new; + + if (data + sizeof(*eth) > data_end) + return NULL; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = data + sizeof(*eth); + __u16 total_len; + + if (iph + 1 > (struct iphdr *)data_end) + return NULL; + + iph->tot_len = bpf_htons(bpf_ntohs(iph->tot_len) + offset); + + udph = (void *)eth + sizeof(*iph) + sizeof(*eth); + if (!udph || udph + 1 > (struct udphdr *)data_end) + return NULL; + + len_new = bpf_htons(bpf_ntohs(udph->len) + offset); + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ipv6h = data + sizeof(*eth); + __u16 payload_len; + + if (ipv6h + 1 > (struct ipv6hdr *)data_end) + return NULL; + + udph = (void *)eth + sizeof(*ipv6h) + sizeof(*eth); + if (!udph || udph + 1 > (struct udphdr *)data_end) + return NULL; + + *udp_csum = ~((__u32)udph->check); + + len = ipv6h->payload_len; + len_new = bpf_htons(bpf_ntohs(len) + offset); + ipv6h->payload_len = len_new; + + *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), *udp_csum); + + len = udph->len; + len_new = bpf_htons(bpf_ntohs(udph->len) + offset); + *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), *udp_csum); + } else { + return NULL; + } + + udph->len = len_new; + + return udph; +} + +static __u16 csum_fold_helper(__u32 csum) +{ + return ~((csum & 0xffff) + (csum >> 16)) ? : 0xffff; +} + +static int xdp_adjst_tail_shrnk_data(struct xdp_md *ctx, __u16 offset, + __u32 hdr_len) +{ + char tmp_buff[MAX_ADJST_OFFSET]; + __u32 buff_pos, udp_csum = 0; + struct udphdr *udph = NULL; + __u32 buff_len; + + udph = update_pkt(ctx, 0 - offset, &udp_csum); + if (!udph) + return -1; + + buff_len = bpf_xdp_get_buff_len(ctx); + + offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET : + offset & 0xff; + if (offset == 0) + return -1; + + /* Make sure we have enough data to avoid eating the header */ + if (buff_len - offset < hdr_len) + return -1; + + buff_pos = buff_len - offset; + if (bpf_xdp_load_bytes(ctx, buff_pos, tmp_buff, offset) < 0) + return -1; + + udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum); + udph->check = (__u16)csum_fold_helper(udp_csum); + + if (bpf_xdp_adjust_tail(ctx, 0 - offset) < 0) + return -1; + + return 0; +} + +static int xdp_adjst_tail_grow_data(struct xdp_md *ctx, __u16 offset) +{ + char tmp_buff[MAX_ADJST_OFFSET]; + __u32 buff_pos, udp_csum = 0; + __u32 buff_len, hdr_len, key; + struct udphdr *udph; + __s32 *val; + __u8 tag; + + /* Proceed to update the packet headers before attempting to adjuste + * the tail. Once the tail is adjusted we lose access to the offset + * amount of data at the end of the packet which is crucial to update + * the checksum. + * Since any failure beyond this would abort the packet, we should + * not worry about passing a packet up the stack with wrong headers + */ + udph = update_pkt(ctx, offset, &udp_csum); + if (!udph) + return -1; + + key = XDP_ADJST_TAG; + val = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!val) + return -1; + + tag = (__u8)(*val); + + for (int i = 0; i < MAX_ADJST_OFFSET; i++) + __builtin_memcpy(&tmp_buff[i], &tag, 1); + + offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET : + offset & 0xff; + if (offset == 0) + return -1; + + udp_csum = bpf_csum_diff(0, 0, (__be32 *)tmp_buff, offset, udp_csum); + udph->check = (__u16)csum_fold_helper(udp_csum); + + buff_len = bpf_xdp_get_buff_len(ctx); + + if (bpf_xdp_adjust_tail(ctx, offset) < 0) { + bpf_printk("Failed to adjust tail\n"); + return -1; + } + + if (bpf_xdp_store_bytes(ctx, buff_len, tmp_buff, offset) < 0) + return -1; + + return 0; +} + +static int xdp_adjst_tail(struct xdp_md *ctx, __u16 port) +{ + void *data = (void *)(long)ctx->data; + struct udphdr *udph = NULL; + __s32 *adjust_offset, *val; + __u32 key, hdr_len; + void *offset_ptr; + __u8 tag; + int ret; + + udph = filter_udphdr(ctx, port); + if (!udph) + return XDP_PASS; + + hdr_len = (void *)udph - data + sizeof(struct udphdr); + key = XDP_ADJST_OFFSET; + adjust_offset = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!adjust_offset) + return XDP_PASS; + + if (*adjust_offset < 0) + ret = xdp_adjst_tail_shrnk_data(ctx, + (__u16)(0 - *adjust_offset), + hdr_len); + else + ret = xdp_adjst_tail_grow_data(ctx, (__u16)(*adjust_offset)); + if (ret) + goto abort_pkt; + + record_stats(ctx, STATS_PASS); + return XDP_PASS; + +abort_pkt: + record_stats(ctx, STATS_ABORT); + return XDP_ABORTED; +} + +static int xdp_adjst_head_shrnk_data(struct xdp_md *ctx, __u64 hdr_len, + __u32 offset) +{ + char tmp_buff[MAX_ADJST_OFFSET]; + struct udphdr *udph; + void *offset_ptr; + __u32 udp_csum = 0; + + /* Update the length information in the IP and UDP headers before + * adjusting the headroom. This simplifies accessing the relevant + * fields in the IP and UDP headers for fragmented packets. Any + * failure beyond this point will result in the packet being aborted, + * so we don't need to worry about incorrect length information for + * passed packets. + */ + udph = update_pkt(ctx, (__s16)(0 - offset), &udp_csum); + if (!udph) + return -1; + + offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET : + offset & 0xff; + if (offset == 0) + return -1; + + if (bpf_xdp_load_bytes(ctx, hdr_len, tmp_buff, offset) < 0) + return -1; + + udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum); + + udph->check = (__u16)csum_fold_helper(udp_csum); + + if (bpf_xdp_load_bytes(ctx, 0, tmp_buff, MAX_ADJST_OFFSET) < 0) + return -1; + + if (bpf_xdp_adjust_head(ctx, offset) < 0) + return -1; + + if (offset > MAX_ADJST_OFFSET) + return -1; + + if (hdr_len > MAX_ADJST_OFFSET || hdr_len == 0) + return -1; + + /* Added here to handle clang complain about negative value */ + hdr_len = hdr_len & 0xff; + + if (hdr_len == 0) + return -1; + + if (bpf_xdp_store_bytes(ctx, 0, tmp_buff, hdr_len) < 0) + return -1; + + return 0; +} + +static int xdp_adjst_head_grow_data(struct xdp_md *ctx, __u64 hdr_len, + __u32 offset) +{ + char hdr_buff[MAX_HDR_LEN]; + char data_buff[MAX_ADJST_OFFSET]; + void *offset_ptr; + __s32 *val; + __u32 key; + __u8 tag; + __u32 udp_csum = 0; + struct udphdr *udph; + + udph = update_pkt(ctx, (__s16)(offset), &udp_csum); + if (!udph) + return -1; + + key = XDP_ADJST_TAG; + val = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!val) + return -1; + + tag = (__u8)(*val); + for (int i = 0; i < MAX_ADJST_OFFSET; i++) + __builtin_memcpy(&data_buff[i], &tag, 1); + + offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET : + offset & 0xff; + if (offset == 0) + return -1; + + udp_csum = bpf_csum_diff(0, 0, (__be32 *)data_buff, offset, udp_csum); + udph->check = (__u16)csum_fold_helper(udp_csum); + + if (hdr_len > MAX_ADJST_OFFSET || hdr_len == 0) + return -1; + + /* Added here to handle clang complain about negative value */ + hdr_len = hdr_len & 0xff; + + if (hdr_len == 0) + return -1; + + if (bpf_xdp_load_bytes(ctx, 0, hdr_buff, hdr_len) < 0) + return -1; + + if (offset > MAX_ADJST_OFFSET) + return -1; + + if (bpf_xdp_adjust_head(ctx, 0 - offset) < 0) + return -1; + + if (bpf_xdp_store_bytes(ctx, 0, hdr_buff, hdr_len) < 0) + return -1; + + if (bpf_xdp_store_bytes(ctx, hdr_len, data_buff, offset) < 0) + return -1; + + return 0; +} + +static int xdp_head_adjst(struct xdp_md *ctx, __u16 port) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct udphdr *udph_ptr = NULL; + __u32 key, size, hdr_len; + __s32 *val; + int res; + + /* Filter packets based on UDP port */ + udph_ptr = filter_udphdr(ctx, port); + if (!udph_ptr) + return XDP_PASS; + + hdr_len = (void *)udph_ptr - data + sizeof(struct udphdr); + + key = XDP_ADJST_OFFSET; + val = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!val) + return XDP_PASS; + + switch (*val) { + case -16: + case 16: + size = 16; + break; + case -32: + case 32: + size = 32; + break; + case -64: + case 64: + size = 64; + break; + case -128: + case 128: + size = 128; + break; + case -256: + case 256: + size = 256; + break; + default: + bpf_printk("Invalid adjustment offset: %d\n", *val); + goto abort; + } + + if (*val < 0) + res = xdp_adjst_head_grow_data(ctx, hdr_len, size); + else + res = xdp_adjst_head_shrnk_data(ctx, hdr_len, size); + + if (res) + goto abort; + + record_stats(ctx, STATS_PASS); + return XDP_PASS; + +abort: + record_stats(ctx, STATS_ABORT); + return XDP_ABORTED; +} + +static int xdp_prog_common(struct xdp_md *ctx) +{ + __u32 key, *port; + __s32 *mode; + + key = XDP_MODE; + mode = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!mode) + return XDP_PASS; + + key = XDP_PORT; + port = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!port) + return XDP_PASS; + + switch (*mode) { + case XDP_MODE_PASS: + return xdp_mode_pass(ctx, (__u16)(*port)); + case XDP_MODE_DROP: + return xdp_mode_drop_handler(ctx, (__u16)(*port)); + case XDP_MODE_TX: + return xdp_mode_tx_handler(ctx, (__u16)(*port)); + case XDP_MODE_TAIL_ADJST: + return xdp_adjst_tail(ctx, (__u16)(*port)); + case XDP_MODE_HEAD_ADJST: + return xdp_head_adjst(ctx, (__u16)(*port)); + } + + /* Default action is to simple pass */ + return XDP_PASS; +} + +SEC("xdp") +int xdp_prog(struct xdp_md *ctx) +{ + return xdp_prog_common(ctx); +} + +SEC("xdp.frags") +int xdp_prog_frags(struct xdp_md *ctx) +{ + return xdp_prog_common(ctx); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index e47788bfa671..4c7e51336ab2 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -4,7 +4,8 @@ top_srcdir = ../../../../.. CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) -TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ +TEST_PROGS := mptcp_connect.sh mptcp_connect_mmap.sh mptcp_connect_sendfile.sh \ + mptcp_connect_checksum.sh pm_netlink.sh mptcp_join.sh diag.sh \ simult_flows.sh mptcp_sockopt.sh userspace_pm.sh TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq mptcp_diag diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index 4f80014cae49..968d440c03fe 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -13,6 +13,7 @@ CONFIG_NETFILTER_NETLINK=m CONFIG_NF_TABLES=m CONFIG_NFT_COMPAT=m CONFIG_NETFILTER_XTABLES=m +CONFIG_NETFILTER_XTABLES_LEGACY=y CONFIG_NETFILTER_XT_MATCH_BPF=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m @@ -25,6 +26,7 @@ CONFIG_IP_MULTIPLE_TABLES=y CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_IP6_NF_FILTER=m CONFIG_NET_ACT_CSUM=m diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh b/tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh new file mode 100755 index 000000000000..ce93ec2f107f --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh @@ -0,0 +1,5 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \ + "$(dirname "${0}")/mptcp_connect.sh" -C "${@}" diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh b/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh new file mode 100755 index 000000000000..5dd30f9394af --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh @@ -0,0 +1,5 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \ + "$(dirname "${0}")/mptcp_connect.sh" -m mmap "${@}" diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh b/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh new file mode 100755 index 000000000000..1d16fb1cc9bb --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh @@ -0,0 +1,5 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \ + "$(dirname "${0}")/mptcp_connect.sh" -m sendfile "${@}" diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index 7ea5fb28c93d..1d5d3c4e7e87 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -77,6 +77,7 @@ static int cfg_cork; static bool cfg_cork_mixed; static int cfg_cpu = -1; /* default: pin to last cpu */ +static int cfg_expect_zerocopy = -1; static int cfg_family = PF_UNSPEC; static int cfg_ifindex = 1; static int cfg_payload_len; @@ -92,9 +93,9 @@ static socklen_t cfg_alen; static struct sockaddr_storage cfg_dst_addr; static struct sockaddr_storage cfg_src_addr; +static int exitcode; static char payload[IP_MAXPACKET]; static long packets, bytes, completions, expected_completions; -static int zerocopied = -1; static uint32_t next_completion; static uint32_t sends_since_notify; @@ -444,11 +445,13 @@ static bool do_recv_completion(int fd, int domain) next_completion = hi + 1; zerocopy = !(serr->ee_code & SO_EE_CODE_ZEROCOPY_COPIED); - if (zerocopied == -1) - zerocopied = zerocopy; - else if (zerocopied != zerocopy) { - fprintf(stderr, "serr: inconsistent\n"); - zerocopied = zerocopy; + if (cfg_expect_zerocopy != -1 && + cfg_expect_zerocopy != zerocopy) { + fprintf(stderr, "serr: ee_code: %u != expected %u\n", + zerocopy, cfg_expect_zerocopy); + exitcode = 1; + /* suppress repeated messages */ + cfg_expect_zerocopy = zerocopy; } if (cfg_verbose >= 2) @@ -571,7 +574,7 @@ static void do_tx(int domain, int type, int protocol) fprintf(stderr, "tx=%lu (%lu MB) txc=%lu zc=%c\n", packets, bytes >> 20, completions, - zerocopied == 1 ? 'y' : 'n'); + cfg_zerocopy && cfg_expect_zerocopy == 1 ? 'y' : 'n'); } static int do_setup_rx(int domain, int type, int protocol) @@ -715,7 +718,7 @@ static void parse_opts(int argc, char **argv) cfg_payload_len = max_payload_len; - while ((c = getopt(argc, argv, "46c:C:D:i:l:mp:rs:S:t:vz")) != -1) { + while ((c = getopt(argc, argv, "46c:C:D:i:l:mp:rs:S:t:vzZ:")) != -1) { switch (c) { case '4': if (cfg_family != PF_UNSPEC) @@ -770,6 +773,9 @@ static void parse_opts(int argc, char **argv) case 'z': cfg_zerocopy = true; break; + case 'Z': + cfg_expect_zerocopy = !!atoi(optarg); + break; } } @@ -817,5 +823,5 @@ int main(int argc, char **argv) else error(1, 0, "unknown cfg_test %s", cfg_test); - return 0; + return exitcode; } diff --git a/tools/testing/selftests/net/msg_zerocopy.sh b/tools/testing/selftests/net/msg_zerocopy.sh index 89c22f5320e0..28178a38a4e7 100755 --- a/tools/testing/selftests/net/msg_zerocopy.sh +++ b/tools/testing/selftests/net/msg_zerocopy.sh @@ -6,6 +6,7 @@ set -e readonly DEV="veth0" +readonly DUMMY_DEV="dummy0" readonly DEV_MTU=65535 readonly BIN="./msg_zerocopy" @@ -14,21 +15,25 @@ readonly NSPREFIX="ns-${RAND}" readonly NS1="${NSPREFIX}1" readonly NS2="${NSPREFIX}2" -readonly SADDR4='192.168.1.1' -readonly DADDR4='192.168.1.2' -readonly SADDR6='fd::1' -readonly DADDR6='fd::2' +readonly LPREFIX4='192.168.1' +readonly RPREFIX4='192.168.2' +readonly LPREFIX6='fd' +readonly RPREFIX6='fc' + readonly path_sysctl_mem="net.core.optmem_max" # No arguments: automated test if [[ "$#" -eq "0" ]]; then - $0 4 tcp -t 1 - $0 6 tcp -t 1 - $0 4 udp -t 1 - $0 6 udp -t 1 - echo "OK. All tests passed" - exit 0 + ret=0 + + $0 4 tcp -t 1 || ret=1 + $0 6 tcp -t 1 || ret=1 + $0 4 udp -t 1 || ret=1 + $0 6 udp -t 1 || ret=1 + + [[ "$ret" == "0" ]] && echo "OK. All tests passed" + exit $ret fi # Argument parsing @@ -45,11 +50,18 @@ readonly EXTRA_ARGS="$@" # Argument parsing: configure addresses if [[ "${IP}" == "4" ]]; then - readonly SADDR="${SADDR4}" - readonly DADDR="${DADDR4}" + readonly SADDR="${LPREFIX4}.1" + readonly DADDR="${LPREFIX4}.2" + readonly DUMMY_ADDR="${RPREFIX4}.1" + readonly DADDR_TXONLY="${RPREFIX4}.2" + readonly MASK="24" elif [[ "${IP}" == "6" ]]; then - readonly SADDR="${SADDR6}" - readonly DADDR="${DADDR6}" + readonly SADDR="${LPREFIX6}::1" + readonly DADDR="${LPREFIX6}::2" + readonly DUMMY_ADDR="${RPREFIX6}::1" + readonly DADDR_TXONLY="${RPREFIX6}::2" + readonly MASK="64" + readonly NODAD="nodad" else echo "Invalid IP version ${IP}" exit 1 @@ -89,33 +101,61 @@ ip netns exec "${NS2}" sysctl -w -q "${path_sysctl_mem}=1000000" ip link add "${DEV}" mtu "${DEV_MTU}" netns "${NS1}" type veth \ peer name "${DEV}" mtu "${DEV_MTU}" netns "${NS2}" +ip link add "${DUMMY_DEV}" mtu "${DEV_MTU}" netns "${NS2}" type dummy + # Bring the devices up ip -netns "${NS1}" link set "${DEV}" up ip -netns "${NS2}" link set "${DEV}" up +ip -netns "${NS2}" link set "${DUMMY_DEV}" up # Set fixed MAC addresses on the devices ip -netns "${NS1}" link set dev "${DEV}" address 02:02:02:02:02:02 ip -netns "${NS2}" link set dev "${DEV}" address 06:06:06:06:06:06 # Add fixed IP addresses to the devices -ip -netns "${NS1}" addr add 192.168.1.1/24 dev "${DEV}" -ip -netns "${NS2}" addr add 192.168.1.2/24 dev "${DEV}" -ip -netns "${NS1}" addr add fd::1/64 dev "${DEV}" nodad -ip -netns "${NS2}" addr add fd::2/64 dev "${DEV}" nodad +ip -netns "${NS1}" addr add "${SADDR}/${MASK}" dev "${DEV}" ${NODAD} +ip -netns "${NS2}" addr add "${DADDR}/${MASK}" dev "${DEV}" ${NODAD} +ip -netns "${NS2}" addr add "${DUMMY_ADDR}/${MASK}" dev "${DUMMY_DEV}" ${NODAD} + +ip -netns "${NS1}" route add default via "${DADDR}" dev "${DEV}" +ip -netns "${NS2}" route add default via "${DADDR_TXONLY}" dev "${DUMMY_DEV}" + +ip netns exec "${NS2}" sysctl -wq net.ipv4.ip_forward=1 +ip netns exec "${NS2}" sysctl -wq net.ipv6.conf.all.forwarding=1 # Optionally disable sg or csum offload to test edge cases # ip netns exec "${NS1}" ethtool -K "${DEV}" sg off +ret=0 + do_test() { local readonly ARGS="$1" - echo "ipv${IP} ${TXMODE} ${ARGS}" - ip netns exec "${NS2}" "${BIN}" "-${IP}" -i "${DEV}" -t 2 -C 2 -S "${SADDR}" -D "${DADDR}" ${ARGS} -r "${RXMODE}" & + # tx-rx test + # packets queued to a local socket are copied, + # sender notification has SO_EE_CODE_ZEROCOPY_COPIED. + + echo -e "\nipv${IP} ${TXMODE} ${ARGS} tx-rx\n" + ip netns exec "${NS2}" "${BIN}" "-${IP}" -i "${DEV}" -t 2 -C 2 \ + -S "${SADDR}" -D "${DADDR}" ${ARGS} -r "${RXMODE}" & sleep 0.2 - ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 -S "${SADDR}" -D "${DADDR}" ${ARGS} "${TXMODE}" + ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 \ + -S "${SADDR}" -D "${DADDR}" ${ARGS} "${TXMODE}" -Z 0 || ret=1 wait + + # next test is unconnected tx to dummy0, cannot exercise with tcp + [[ "${TXMODE}" == "tcp" ]] && return + + # tx-only test: send out dummy0 + # packets leaving the host are not copied, + # sender notification does not have SO_EE_CODE_ZEROCOPY_COPIED. + + echo -e "\nipv${IP} ${TXMODE} ${ARGS} tx-only\n" + ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 \ + -S "${SADDR}" -D "${DADDR_TXONLY}" ${ARGS} "${TXMODE}" -Z 1 || ret=1 } do_test "${EXTRA_ARGS}" do_test "-z ${EXTRA_ARGS}" -echo ok + +[[ "$ret" == "0" ]] && echo "OK" diff --git a/tools/testing/selftests/net/netdev-l2addr.sh b/tools/testing/selftests/net/netdev-l2addr.sh new file mode 100755 index 000000000000..18509da293e5 --- /dev/null +++ b/tools/testing/selftests/net/netdev-l2addr.sh @@ -0,0 +1,59 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh +set -o pipefail + +NSIM_ADDR=2025 +TEST_ADDR="d0:be:d0:be:d0:00" + +RET_CODE=0 + +cleanup() { + cleanup_netdevsim "$NSIM_ADDR" + cleanup_ns "$NS" +} + +trap cleanup EXIT + +fail() { + echo "ERROR: ${1:-unexpected return code} (ret: $_)" >&2 + RET_CODE=1 +} + +get_addr() +{ + local type="$1" + local dev="$2" + local ns="$3" + + ip -j -n "$ns" link show dev "$dev" | jq -er ".[0].$type" +} + +setup_ns NS + +nsim=$(create_netdevsim $NSIM_ADDR "$NS") + +get_addr address "$nsim" "$NS" >/dev/null || fail "Couldn't get ether addr" +get_addr broadcast "$nsim" "$NS" >/dev/null || fail "Couldn't get brd addr" +get_addr permaddr "$nsim" "$NS" >/dev/null && fail "Found perm_addr without setting it" + +ip -n "$NS" link set dev "$nsim" address "$TEST_ADDR" +ip -n "$NS" link set dev "$nsim" brd "$TEST_ADDR" + +[[ "$(get_addr address "$nsim" "$NS")" == "$TEST_ADDR" ]] || fail "Couldn't set ether addr" +[[ "$(get_addr broadcast "$nsim" "$NS")" == "$TEST_ADDR" ]] || fail "Couldn't set brd addr" + +if create_netdevsim_port "$NSIM_ADDR" "$NS" 2 "FF:FF:FF:FF:FF:FF" 2>/dev/null; then + fail "Created netdevsim with broadcast permaddr" +fi + +nsim_port=$(create_netdevsim_port "$NSIM_ADDR" "$NS" 2 "$TEST_ADDR") + +get_addr address "$nsim_port" "$NS" >/dev/null || fail "Couldn't get ether addr" +get_addr broadcast "$nsim_port" "$NS" >/dev/null || fail "Couldn't get brd addr" +[[ "$(get_addr permaddr "$nsim_port" "$NS")" == "$TEST_ADDR" ]] || fail "Couldn't get permaddr" + +cleanup_netdevsim "$NSIM_ADDR" "$NS" + +exit $RET_CODE diff --git a/tools/testing/selftests/net/netfilter/config b/tools/testing/selftests/net/netfilter/config index 363646f4fefe..79d5b33966ba 100644 --- a/tools/testing/selftests/net/netfilter/config +++ b/tools/testing/selftests/net/netfilter/config @@ -1,6 +1,8 @@ CONFIG_AUDIT=y CONFIG_BPF_SYSCALL=y CONFIG_BRIDGE=m +CONFIG_NETFILTER_XTABLES_LEGACY=y +CONFIG_BRIDGE_NF_EBTABLES_LEGACY=m CONFIG_BRIDGE_EBT_BROUTE=m CONFIG_BRIDGE_EBT_IP=m CONFIG_BRIDGE_EBT_REDIRECT=m @@ -14,7 +16,10 @@ CONFIG_INET_ESP=m CONFIG_IP_NF_MATCH_RPFILTER=m CONFIG_IP6_NF_MATCH_RPFILTER=m CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_IPTABLES_LEGACY=m CONFIG_IP6_NF_IPTABLES=m +CONFIG_IP6_NF_IPTABLES_LEGACY=m +CONFIG_IP_NF_NAT=m CONFIG_IP_NF_FILTER=m CONFIG_IP6_NF_FILTER=m CONFIG_IP_NF_RAW=m @@ -92,4 +97,4 @@ CONFIG_XFRM_STATISTICS=y CONFIG_NET_PKTGEN=m CONFIG_TUN=m CONFIG_INET_DIAG=m -CONFIG_SCTP_DIAG=m +CONFIG_INET_SCTP_DIAG=m diff --git a/tools/testing/selftests/net/netfilter/conntrack_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_clash.sh index 3712c1b9b38b..606a43a60f73 100755 --- a/tools/testing/selftests/net/netfilter/conntrack_clash.sh +++ b/tools/testing/selftests/net/netfilter/conntrack_clash.sh @@ -93,32 +93,28 @@ ping_test() run_one_clash_test() { local ns="$1" - local daddr="$2" - local dport="$3" + local ctns="$2" + local daddr="$3" + local dport="$4" local entries local cre if ! ip netns exec "$ns" ./udpclash $daddr $dport;then - echo "FAIL: did not receive expected number of replies for $daddr:$dport" - ret=1 - return 1 + echo "INFO: did not receive expected number of replies for $daddr:$dport" + ip netns exec "$ctns" conntrack -S + # don't fail: check if clash resolution triggered after all. fi - entries=$(conntrack -S | wc -l) - cre=$(conntrack -S | grep -v "clash_resolve=0" | wc -l) + entries=$(ip netns exec "$ctns" conntrack -S | wc -l) + cre=$(ip netns exec "$ctns" conntrack -S | grep "clash_resolve=0" | wc -l) - if [ "$cre" -ne "$entries" ] ;then + if [ "$cre" -ne "$entries" ];then clash_resolution_active=1 return 0 fi - # 1 cpu -> parallel insertion impossible - if [ "$entries" -eq 1 ]; then - return 0 - fi - - # not a failure: clash resolution logic did not trigger, but all replies - # were received. With right timing, xmit completed sequentially and + # not a failure: clash resolution logic did not trigger. + # With right timing, xmit completed sequentially and # no parallel insertion occurs. return $ksft_skip } @@ -126,20 +122,23 @@ run_one_clash_test() run_clash_test() { local ns="$1" - local daddr="$2" - local dport="$3" + local ctns="$2" + local daddr="$3" + local dport="$4" + local softerr=0 for i in $(seq 1 10);do - run_one_clash_test "$ns" "$daddr" "$dport" + run_one_clash_test "$ns" "$ctns" "$daddr" "$dport" local rv=$? if [ $rv -eq 0 ];then echo "PASS: clash resolution test for $daddr:$dport on attempt $i" return 0 - elif [ $rv -eq 1 ];then - echo "FAIL: clash resolution test for $daddr:$dport on attempt $i" - return 1 + elif [ $rv -eq $ksft_skip ]; then + softerr=1 fi done + + [ $softerr -eq 1 ] && echo "SKIP: clash resolution for $daddr:$dport did not trigger" } ip link add veth0 netns "$nsclient1" type veth peer name veth0 netns "$nsrouter" @@ -161,11 +160,11 @@ spawn_servers "$nsclient2" # exercise clash resolution with nat: # nsrouter is supposed to dnat to 10.0.2.1:900{0,1,2,3}. -run_clash_test "$nsclient1" 10.0.1.99 "$dport" +run_clash_test "$nsclient1" "$nsrouter" 10.0.1.99 "$dport" # exercise clash resolution without nat. load_simple_ruleset "$nsclient2" -run_clash_test "$nsclient2" 127.0.0.1 9001 +run_clash_test "$nsclient2" "$nsclient2" 127.0.0.1 9001 if [ $clash_resolution_active -eq 0 ];then [ "$ret" -eq 0 ] && ret=$ksft_skip diff --git a/tools/testing/selftests/net/netfilter/ipvs.sh b/tools/testing/selftests/net/netfilter/ipvs.sh index 6af2ea3ad6b8..9c9d5b38ab71 100755 --- a/tools/testing/selftests/net/netfilter/ipvs.sh +++ b/tools/testing/selftests/net/netfilter/ipvs.sh @@ -151,7 +151,7 @@ test_nat() { test_tun() { ip netns exec "${ns0}" ip route add "${vip_v4}" via "${gip_v4}" dev br0 - ip netns exec "${ns1}" modprobe -q ipip + modprobe -q ipip ip netns exec "${ns1}" ip link set tunl0 up ip netns exec "${ns1}" sysctl -qw net.ipv4.ip_forward=0 ip netns exec "${ns1}" sysctl -qw net.ipv4.conf.all.send_redirects=0 @@ -160,10 +160,10 @@ test_tun() { ip netns exec "${ns1}" ipvsadm -a -i -t "${vip_v4}:${port}" -r ${rip_v4}:${port} ip netns exec "${ns1}" ip addr add ${vip_v4}/32 dev lo:1 - ip netns exec "${ns2}" modprobe -q ipip ip netns exec "${ns2}" ip link set tunl0 up ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_ignore=1 ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_announce=2 + ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.tunl0.rp_filter=0 ip netns exec "${ns2}" ip addr add "${vip_v4}/32" dev lo:1 test_service diff --git a/tools/testing/selftests/net/netfilter/nft_interface_stress.sh b/tools/testing/selftests/net/netfilter/nft_interface_stress.sh index 5ff7be9daeee..c0fffaa6dbd9 100755 --- a/tools/testing/selftests/net/netfilter/nft_interface_stress.sh +++ b/tools/testing/selftests/net/netfilter/nft_interface_stress.sh @@ -10,6 +10,8 @@ source lib.sh checktool "nft --version" "run test without nft tool" checktool "iperf3 --version" "run test without iperf3 tool" +read kernel_tainted < /proc/sys/kernel/tainted + # how many seconds to torture the kernel? # default to 80% of max run time but don't exceed 48s TEST_RUNTIME=$((${kselftest_timeout:-60} * 8 / 10)) @@ -135,7 +137,8 @@ else wait fi -[[ $(</proc/sys/kernel/tainted) -eq 0 ]] || { + +[[ $kernel_tainted -eq 0 && $(</proc/sys/kernel/tainted) -ne 0 ]] && { echo "FAIL: Kernel is tainted!" exit $ksft_fail } diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index cd8a58097448..1f5227f3d64d 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -385,7 +385,7 @@ static int get_bind_to_device(int sd, char *name, size_t len) name[0] = '\0'; rc = getsockopt(sd, SOL_SOCKET, SO_BINDTODEVICE, name, &optlen); if (rc < 0) - log_err_errno("setsockopt(SO_BINDTODEVICE)"); + log_err_errno("getsockopt(SO_BINDTODEVICE)"); return rc; } @@ -535,7 +535,7 @@ static int set_freebind(int sd, int version) break; case AF_INET6: if (setsockopt(sd, SOL_IPV6, IPV6_FREEBIND, &one, sizeof(one))) { - log_err_errno("setsockopt(IPV6_FREEBIND"); + log_err_errno("setsockopt(IPV6_FREEBIND)"); rc = -1; } break; @@ -812,7 +812,7 @@ static int convert_addr(struct sock_args *args, const char *_str, sep++; if (str_to_uint(sep, 1, pfx_len_max, &args->prefix_len) != 0) { - fprintf(stderr, "Invalid port\n"); + fprintf(stderr, "Invalid prefix length\n"); return 1; } } else { @@ -1272,7 +1272,7 @@ static int msg_loop(int client, int sd, void *addr, socklen_t alen, } } - nfds = interactive ? MAX(fileno(stdin), sd) + 1 : sd + 1; + nfds = interactive ? MAX(fileno(stdin), sd) + 1 : sd + 1; while (1) { FD_ZERO(&rfds); FD_SET(sd, &rfds); @@ -1492,7 +1492,7 @@ static int lsock_init(struct sock_args *args) sd = socket(args->version, args->type, args->protocol); if (sd < 0) { log_err_errno("Error opening socket"); - return -1; + return -1; } if (set_reuseaddr(sd) != 0) @@ -1912,7 +1912,7 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args) * waiting to be told when to continue */ if (read(fd, &buf, sizeof(buf)) <= 0) { - log_err_errno("Failed to read IPC status from status"); + log_err_errno("Failed to read IPC status from pipe"); return 1; } if (!buf) { diff --git a/tools/testing/selftests/net/nl_netdev.py b/tools/testing/selftests/net/nl_netdev.py index beaee5e4e2aa..5c66421ab8aa 100755 --- a/tools/testing/selftests/net/nl_netdev.py +++ b/tools/testing/selftests/net/nl_netdev.py @@ -2,8 +2,9 @@ # SPDX-License-Identifier: GPL-2.0 import time +from os import system from lib.py import ksft_run, ksft_exit, ksft_pr -from lib.py import ksft_eq, ksft_ge, ksft_busy_wait +from lib.py import ksft_eq, ksft_ge, ksft_ne, ksft_busy_wait from lib.py import NetdevFamily, NetdevSimDev, ip @@ -34,6 +35,128 @@ def napi_list_check(nf) -> None: ksft_eq(len(napis), 100, comment=f"queue count after reset queue {q} mode {i}") +def napi_set_threaded(nf) -> None: + """ + Test that verifies various cases of napi threaded + set and unset at napi and device level. + """ + with NetdevSimDev(queue_count=2) as nsimdev: + nsim = nsimdev.nsims[0] + + ip(f"link set dev {nsim.ifname} up") + + napis = nf.napi_get({'ifindex': nsim.ifindex}, dump=True) + ksft_eq(len(napis), 2) + + napi0_id = napis[0]['id'] + napi1_id = napis[1]['id'] + + # set napi threaded and verify + nf.napi_set({'id': napi0_id, 'threaded': "enabled"}) + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "enabled") + ksft_ne(napi0.get('pid'), None) + + # check it is not set for napi1 + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], "disabled") + ksft_eq(napi1.get('pid'), None) + + ip(f"link set dev {nsim.ifname} down") + ip(f"link set dev {nsim.ifname} up") + + # verify if napi threaded is still set + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "enabled") + ksft_ne(napi0.get('pid'), None) + + # check it is still not set for napi1 + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], "disabled") + ksft_eq(napi1.get('pid'), None) + + # unset napi threaded and verify + nf.napi_set({'id': napi0_id, 'threaded': "disabled"}) + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "disabled") + ksft_eq(napi0.get('pid'), None) + + # set threaded at device level + system(f"echo 1 > /sys/class/net/{nsim.ifname}/threaded") + + # check napi threaded is set for both napis + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "enabled") + ksft_ne(napi0.get('pid'), None) + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], "enabled") + ksft_ne(napi1.get('pid'), None) + + # unset threaded at device level + system(f"echo 0 > /sys/class/net/{nsim.ifname}/threaded") + + # check napi threaded is unset for both napis + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "disabled") + ksft_eq(napi0.get('pid'), None) + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], "disabled") + ksft_eq(napi1.get('pid'), None) + + # set napi threaded for napi0 + nf.napi_set({'id': napi0_id, 'threaded': 1}) + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "enabled") + ksft_ne(napi0.get('pid'), None) + + # unset threaded at device level + system(f"echo 0 > /sys/class/net/{nsim.ifname}/threaded") + + # check napi threaded is unset for both napis + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "disabled") + ksft_eq(napi0.get('pid'), None) + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], "disabled") + ksft_eq(napi1.get('pid'), None) + +def dev_set_threaded(nf) -> None: + """ + Test that verifies various cases of napi threaded + set and unset at device level using sysfs. + """ + with NetdevSimDev(queue_count=2) as nsimdev: + nsim = nsimdev.nsims[0] + + ip(f"link set dev {nsim.ifname} up") + + napis = nf.napi_get({'ifindex': nsim.ifindex}, dump=True) + ksft_eq(len(napis), 2) + + napi0_id = napis[0]['id'] + napi1_id = napis[1]['id'] + + # set threaded + system(f"echo 1 > /sys/class/net/{nsim.ifname}/threaded") + + # check napi threaded is set for both napis + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "enabled") + ksft_ne(napi0.get('pid'), None) + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], "enabled") + ksft_ne(napi1.get('pid'), None) + + # unset threaded + system(f"echo 0 > /sys/class/net/{nsim.ifname}/threaded") + + # check napi threaded is unset for both napis + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "disabled") + ksft_eq(napi0.get('pid'), None) + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], "disabled") + ksft_eq(napi1.get('pid'), None) def nsim_rxq_reset_down(nf) -> None: """ @@ -122,7 +245,7 @@ def page_pool_check(nf) -> None: def main() -> None: nf = NetdevFamily() ksft_run([empty_check, lo_check, page_pool_check, napi_list_check, - nsim_rxq_reset_down], + dev_set_threaded, napi_set_threaded, nsim_rxq_reset_down], args=(nf, )) ksft_exit() diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh index ef8b25a606d8..c5b01e1bd4c7 100755 --- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh +++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh @@ -39,11 +39,15 @@ if [[ -n "${KSFT_MACHINE_SLOW}" ]]; then # xfail tests that are known flaky with dbg config, not fixable. # still run them for coverage (and expect 100% pass without dbg). declare -ar xfail_list=( + "tcp_blocking_blocking-connect.pkt" + "tcp_blocking_blocking-read.pkt" "tcp_eor_no-coalesce-retrans.pkt" "tcp_fast_recovery_prr-ss.*.pkt" + "tcp_sack_sack-route-refresh-ip-tos.pkt" "tcp_slow_start_slow-start-after-win-update.pkt" "tcp_timestamping.*.pkt" "tcp_user_timeout_user-timeout-probe.pkt" + "tcp_zerocopy_cl.*.pkt" "tcp_zerocopy_epoll_.*.pkt" "tcp_tcp_info_tcp-info-.*-limited.pkt" ) diff --git a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt index 914eabab367a..657e42ca65b5 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Test for blocking read. + --tolerance_usecs=10000 +--mss=1000 `./defaults.sh` diff --git a/tools/testing/selftests/net/packetdrill/tcp_dsack_mult.pkt b/tools/testing/selftests/net/packetdrill/tcp_dsack_mult.pkt new file mode 100644 index 000000000000..c790d0af635e --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_dsack_mult.pkt @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test various DSACK (RFC 2883) behaviors. + +--mss=1000 + +`./defaults.sh` + + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 1024 + +0 accept(3, ..., ...) = 4 + +// First SACK range. + +0 < P. 1001:2001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 1 <nop, nop, sack 1001:2001> + +// Check SACK coalescing (contiguous sequence). + +0 < P. 2001:3001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 1 <nop,nop,sack 1001:3001> + +// Check we have two SACK ranges for non contiguous sequences. + +0 < P. 4001:5001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 1 <nop,nop,sack 4001:5001 1001:3001> + +// Three ranges. + +0 < P. 7001:8001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 1 <nop,nop,sack 7001:8001 4001:5001 1001:3001> + +// DSACK (1001:3001) + SACK (6001:7001) + +0 < P. 1:6001(6000) ack 1 win 1024 + +0 > . 1:1(0) ack 6001 <nop,nop,sack 1001:3001 7001:8001> + +// DSACK (7001:8001) + +0 < P. 6001:8001(2000) ack 1 win 1024 + +0 > . 1:1(0) ack 8001 <nop,nop,sack 7001:8001> + +// DSACK for an older segment. + +0 < P. 1:1001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 8001 <nop,nop,sack 1:1001> diff --git a/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt b/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt index df49c67645ac..e13f0eee9795 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt @@ -1,5 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Test TCP_INQ and TCP_CM_INQ on the client side. + +--mss=1000 + `./defaults.sh ` diff --git a/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt b/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt index 04a5e2590c62..14dd5f813d50 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt @@ -1,5 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Test TCP_INQ and TCP_CM_INQ on the server side. + +--mss=1000 + `./defaults.sh ` diff --git a/tools/testing/selftests/net/packetdrill/tcp_ooo_rcv_mss.pkt b/tools/testing/selftests/net/packetdrill/tcp_ooo_rcv_mss.pkt new file mode 100644 index 000000000000..7e6bc5fb0c8d --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_ooo_rcv_mss.pkt @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 + +--mss=1000 + +`./defaults.sh +sysctl -q net.ipv4.tcp_rmem="4096 131072 $((32*1024*1024))"` + + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 65535 <mss 1000,nop,nop,sackOK,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 10> + +.1 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + + +0 < . 2001:11001(9000) ack 1 win 257 + +0 > . 1:1(0) ack 1 win 81 <nop,nop,sack 2001:11001> + +// check that ooo packet properly updates tcpi_rcv_mss + +0 %{ assert tcpi_rcv_mss == 1000, tcpi_rcv_mss }% + + +0 < . 11001:21001(10000) ack 1 win 257 + +0 > . 1:1(0) ack 1 win 81 <nop,nop,sack 2001:21001> + diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt new file mode 100644 index 000000000000..3848b419e68c --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 + +--mss=1000 + +`./defaults.sh` + + 0 `nstat -n` + +// Establish a connection. + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [10000], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 0> + +.1 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + + +0 < P. 1:4001(4000) ack 1 win 257 + +0 > . 1:1(0) ack 4001 win 5000 + +// packet in sequence : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW + +0 < P. 4001:54001(50000) ack 1 win 257 + +0 > . 1:1(0) ack 4001 win 5000 + +// ooo packet. : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW + +1 < P. 5001:55001(50000) ack 1 win 257 + +0 > . 1:1(0) ack 4001 win 5000 + +// SKB_DROP_REASON_TCP_INVALID_SEQUENCE / LINUX_MIB_BEYOND_WINDOW + +0 < P. 70001:80001(10000) ack 1 win 257 + +0 > . 1:1(0) ack 4001 win 5000 + + +0 read(4, ..., 100000) = 4000 + +// If queue is empty, accept a packet even if its end_seq is above wup + rcv_wnd + +0 < P. 4001:54001(50000) ack 1 win 257 + +0 > . 1:1(0) ack 54001 win 0 + +// Check LINUX_MIB_BEYOND_WINDOW has been incremented 3 times. ++0 `nstat | grep TcpExtBeyondWindow | grep -q " 3 "` diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt new file mode 100644 index 000000000000..f575c0ff89da --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 + +--mss=1000 + +`./defaults.sh` + + 0 `nstat -n` + +// Establish a connection. + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 win 18980 <mss 1460,nop,wscale 0> + +.1 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + + +0 < P. 1:20001(20000) ack 1 win 257 + +.04 > . 1:1(0) ack 20001 win 18000 + + +0 setsockopt(4, SOL_SOCKET, SO_RCVBUF, [12000], 4) = 0 + +0 < P. 20001:80001(60000) ack 1 win 257 + +0 > . 1:1(0) ack 20001 win 18000 + + +0 read(4, ..., 20000) = 20000 +// A too big packet is accepted if the receive queue is empty + +0 < P. 20001:80001(60000) ack 1 win 257 + +0 > . 1:1(0) ack 80001 win 0 + diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 2e8243a65b50..d6c00efeb664 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -21,6 +21,7 @@ ALL_TESTS=" kci_test_vrf kci_test_encap kci_test_macsec + kci_test_macsec_vlan kci_test_ipsec kci_test_ipsec_offload kci_test_fdb_get @@ -30,6 +31,7 @@ ALL_TESTS=" kci_test_address_proto kci_test_enslave_bonding kci_test_mngtmpaddr + kci_test_operstate " devdummy="test-dummy0" @@ -291,6 +293,17 @@ kci_test_route_get() end_test "PASS: route get" } +check_addr_not_exist() +{ + dev=$1 + addr=$2 + if ip addr show dev $dev | grep -q $addr; then + return 1 + else + return 0 + fi +} + kci_test_addrlft() { for i in $(seq 10 100) ;do @@ -298,9 +311,8 @@ kci_test_addrlft() run_cmd ip addr add 10.23.11.$i/32 dev "$devdummy" preferred_lft $lft valid_lft $((lft+1)) done - sleep 5 - run_cmd_grep_fail "10.23.11." ip addr show dev "$devdummy" - if [ $? -eq 0 ]; then + slowwait 5 check_addr_not_exist "$devdummy" "10.23.11." + if [ $? -eq 1 ]; then check_err 1 end_test "FAIL: preferred_lft addresses remaining" return @@ -561,6 +573,41 @@ kci_test_macsec() end_test "PASS: macsec" } +# Test __dev_set_rx_mode call from dev_uc_add under addr_list_lock spinlock. +# Make sure __dev_set_promiscuity is not grabbing (sleeping) netdev instance +# lock. +# https://lore.kernel.org/netdev/[email protected]/ +kci_test_macsec_vlan() +{ + msname="test_macsec1" + vlanname="test_vlan1" + local ret=0 + run_cmd_grep "^Usage: ip macsec" ip macsec help + if [ $? -ne 0 ]; then + end_test "SKIP: macsec: iproute2 too old" + return $ksft_skip + fi + run_cmd ip link add link "$devdummy" "$msname" type macsec port 42 encrypt on + if [ $ret -ne 0 ];then + end_test "FAIL: can't add macsec interface, skipping test" + return 1 + fi + + run_cmd ip link set dev "$msname" up + ip link add link "$msname" name "$vlanname" type vlan id 1 + ip link set dev "$vlanname" address 00:11:22:33:44:88 + ip link set dev "$vlanname" up + run_cmd ip link del dev "$vlanname" + run_cmd ip link del dev "$msname" + + if [ $ret -ne 0 ];then + end_test "FAIL: macsec_vlan" + return 1 + fi + + end_test "PASS: macsec_vlan" +} + #------------------------------------------------------------------- # Example commands # ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \ @@ -673,6 +720,11 @@ kci_test_ipsec_offload() sysfsf=$sysfsd/ipsec sysfsnet=/sys/bus/netdevsim/devices/netdevsim0/net/ probed=false + esp4_offload_probed_default=false + + if lsmod | grep -q esp4_offload; then + esp4_offload_probed_default=true + fi if ! mount | grep -q debugfs; then mount -t debugfs none /sys/kernel/debug/ &> /dev/null @@ -766,6 +818,7 @@ EOF fi # clean up any leftovers + ! "$esp4_offload_probed_default" && lsmod | grep -q esp4_offload && rmmod esp4_offload echo 0 > /sys/bus/netdevsim/del_device $probed && rmmod netdevsim @@ -1334,6 +1387,39 @@ kci_test_mngtmpaddr() return $ret } +kci_test_operstate() +{ + local ret=0 + + # Check that it is possible to set operational state during device + # creation and that it is preserved when the administrative state of + # the device is toggled. + run_cmd ip link add name vx0 up state up type vxlan id 10010 dstport 4789 + run_cmd_grep "state UP" ip link show dev vx0 + run_cmd ip link set dev vx0 down + run_cmd_grep "state DOWN" ip link show dev vx0 + run_cmd ip link set dev vx0 up + run_cmd_grep "state UP" ip link show dev vx0 + + run_cmd ip link del dev vx0 + + # Check that it is possible to set the operational state of the device + # after creation. + run_cmd ip link add name vx0 up type vxlan id 10010 dstport 4789 + run_cmd_grep "state UNKNOWN" ip link show dev vx0 + run_cmd ip link set dev vx0 state up + run_cmd_grep "state UP" ip link show dev vx0 + + run_cmd ip link del dev vx0 + + if [ "$ret" -ne 0 ]; then + end_test "FAIL: operstate" + return 1 + fi + + end_test "PASS: operstate" +} + kci_test_rtnl() { local current_test diff --git a/tools/testing/selftests/net/rtnetlink_notification.sh b/tools/testing/selftests/net/rtnetlink_notification.sh new file mode 100755 index 000000000000..3f9780232bd6 --- /dev/null +++ b/tools/testing/selftests/net/rtnetlink_notification.sh @@ -0,0 +1,112 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# This test is for checking rtnetlink notification callpaths, and get as much +# coverage as possible. +# +# set -e + +ALL_TESTS=" + kci_test_mcast_addr_notification + kci_test_anycast_addr_notification +" + +source lib.sh +test_dev="test-dummy1" + +kci_test_mcast_addr_notification() +{ + RET=0 + local tmpfile + local monitor_pid + local match_result + + tmpfile=$(mktemp) + defer rm "$tmpfile" + + ip monitor maddr > $tmpfile & + monitor_pid=$! + defer kill_process "$monitor_pid" + + sleep 1 + + if [ ! -e "/proc/$monitor_pid" ]; then + RET=$ksft_skip + log_test "mcast addr notification: iproute2 too old" + return $RET + fi + + ip link add name "$test_dev" type dummy + check_err $? "failed to add dummy interface" + ip link set "$test_dev" up + check_err $? "failed to set dummy interface up" + ip link del dev "$test_dev" + check_err $? "Failed to delete dummy interface" + sleep 1 + + # There should be 4 line matches as follows. + # 13: test-dummy1  inet6 mcast ff02::1 scope global + # 13: test-dummy1  inet mcast 224.0.0.1 scope global + # Deleted 13: test-dummy1  inet mcast 224.0.0.1 scope global + # Deleted 13: test-dummy1  inet6 mcast ff02::1 scope global + match_result=$(grep -cE "$test_dev.*(224.0.0.1|ff02::1)" "$tmpfile") + if [ "$match_result" -ne 4 ]; then + RET=$ksft_fail + fi + log_test "mcast addr notification: Expected 4 matches, got $match_result" + return $RET +} + +kci_test_anycast_addr_notification() +{ + RET=0 + local tmpfile + local monitor_pid + local match_result + + tmpfile=$(mktemp) + defer rm "$tmpfile" + + ip monitor acaddress > "$tmpfile" & + monitor_pid=$! + defer kill_process "$monitor_pid" + sleep 1 + + if [ ! -e "/proc/$monitor_pid" ]; then + RET=$ksft_skip + log_test "anycast addr notification: iproute2 too old" + return "$RET" + fi + + ip link add name "$test_dev" type dummy + check_err $? "failed to add dummy interface" + ip link set "$test_dev" up + check_err $? "failed to set dummy interface up" + sysctl -qw net.ipv6.conf."$test_dev".forwarding=1 + ip link del dev "$test_dev" + check_err $? "Failed to delete dummy interface" + sleep 1 + + # There should be 2 line matches as follows. + # 9: dummy2 inet6 any fe80:: scope global + # Deleted 9: dummy2 inet6 any fe80:: scope global + match_result=$(grep -cE "$test_dev.*(fe80::)" "$tmpfile") + if [ "$match_result" -ne 2 ]; then + RET=$ksft_fail + fi + log_test "anycast addr notification: Expected 2 matches, got $match_result" + return "$RET" +} + +#check for needed privileges +if [ "$(id -u)" -ne 0 ];then + RET=$ksft_skip + log_test "need root privileges" + exit $RET +fi + +require_command ip + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh index ba730655a7bf..4bc135e5c22c 100755 --- a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh @@ -594,7 +594,7 @@ setup_rt_local_sids() dev "${DUMMY_DEVNAME}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behavior instaces are grouped together in the 'localsid' + # Endpoint behavior instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule \ add to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh index 4b86040c58c6..34b781a2ae74 100755 --- a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh @@ -72,6 +72,9 @@ # Every fcf0:0:x:y::/64 network interconnects the SRv6 routers rt-x with rt-y in # the selftest network. # +# In addition, every router interface connecting rt-x to rt-y is assigned an +# IPv6 link-local address fe80::x:y/64. +# # Local SID/C-SID table # ===================== # @@ -521,6 +524,9 @@ setup_rt_networking() ip -netns "${nsname}" addr \ add "${net_prefix}::${rt}/64" dev "${devname}" nodad + ip -netns "${nsname}" addr \ + add "fe80::${rt}:${neigh}/64" dev "${devname}" nodad + ip -netns "${nsname}" link set "${devname}" up done @@ -609,6 +615,27 @@ set_end_x_nextcsid() nflen "${LCNODEFUNC_BLEN}" dev "${DUMMY_DEVNAME}" } +set_end_x_ll_nextcsid() +{ + local rt="$1" + local adj="$2" + + eval nsname=\${$(get_rtname "${rt}")} + lcnode_func_prefix="$(build_lcnode_func_prefix "${rt}")" + nh6_ll_addr="fe80::${adj}:${rt}" + oifname="veth-rt-${rt}-${adj}" + + # enabled NEXT-C-SID SRv6 End.X behavior via an IPv6 link-local nexthop + # address (note that "dev" is the dummy dum0 device chosen for the sake + # of simplicity). + ip -netns "${nsname}" -6 route \ + replace "${lcnode_func_prefix}" \ + table "${LOCALSID_TABLE_ID}" \ + encap seg6local action End.X nh6 "${nh6_ll_addr}" \ + oif "${oifname}" flavors next-csid lblen "${LCBLOCK_BLEN}" \ + nflen "${LCNODEFUNC_BLEN}" dev "${DUMMY_DEVNAME}" +} + set_underlay_sids_reachability() { local rt="$1" @@ -654,7 +681,7 @@ setup_rt_local_sids() set_underlay_sids_reachability "${rt}" "${rt_neighs}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behavior instaces are grouped together in the 'localsid' + # Endpoint behavior instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule \ add to "${VPN_LOCATOR_SERVICE}::/16" \ @@ -1016,6 +1043,27 @@ host_vpn_tests() check_and_log_hs_ipv4_connectivity 1 2 check_and_log_hs_ipv4_connectivity 2 1 + + # Setup the adjacencies in the SRv6 aware routers using IPv6 link-local + # addresses. + # - rt-3 SRv6 End.X adjacency with rt-4 + # - rt-4 SRv6 End.X adjacency with rt-1 + set_end_x_ll_nextcsid 3 4 + set_end_x_ll_nextcsid 4 1 + + log_section "SRv6 VPN connectivity test hosts (h1 <-> h2, IPv6), link-local" + + check_and_log_hs_ipv6_connectivity 1 2 + check_and_log_hs_ipv6_connectivity 2 1 + + log_section "SRv6 VPN connectivity test hosts (h1 <-> h2, IPv4), link-local" + + check_and_log_hs_ipv4_connectivity 1 2 + check_and_log_hs_ipv4_connectivity 2 1 + + # Restore the previous adjacencies. + set_end_x_nextcsid 3 4 + set_end_x_nextcsid 4 1 } __nextcsid_end_x_behavior_test() diff --git a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh index 3efce1718c5f..6a68c7eff1dc 100755 --- a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh @@ -395,7 +395,7 @@ setup_rt_local_sids() dev "${VRF_DEVNAME}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behavior instaces are grouped together in the 'localsid' + # Endpoint behavior instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule \ add to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh index cabc70538ffe..0979b5316fdf 100755 --- a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh +++ b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh @@ -343,7 +343,7 @@ setup_rt_local_sids() encap seg6local action End dev "${DUMMY_DEVNAME}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behaviors instaces are grouped together in the 'localsid' + # Endpoint behaviors instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule add \ to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/tcp_ao/seq-ext.c b/tools/testing/selftests/net/tcp_ao/seq-ext.c index f00245263b20..6478da6a71c3 100644 --- a/tools/testing/selftests/net/tcp_ao/seq-ext.c +++ b/tools/testing/selftests/net/tcp_ao/seq-ext.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Check that after SEQ number wrap-around: * 1. SEQ-extension has upper bytes set - * 2. TCP conneciton is alive and no TCPAOBad segments + * 2. TCP connection is alive and no TCPAOBad segments * In order to test (2), the test doesn't just adjust seq number for a queue * on a connected socket, but migrates it to another sk+port number, so * that there won't be any delayed packets that will fail to verify diff --git a/tools/testing/selftests/net/test_neigh.sh b/tools/testing/selftests/net/test_neigh.sh new file mode 100755 index 000000000000..388056472b5b --- /dev/null +++ b/tools/testing/selftests/net/test_neigh.sh @@ -0,0 +1,366 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh +TESTS=" + extern_valid_ipv4 + extern_valid_ipv6 +" +VERBOSE=0 + +################################################################################ +# Utilities + +run_cmd() +{ + local cmd="$1" + local out + local stderr="2>/dev/null" + + if [ "$VERBOSE" = "1" ]; then + echo "COMMAND: $cmd" + stderr= + fi + + out=$(eval "$cmd" "$stderr") + rc=$? + if [ "$VERBOSE" -eq 1 ] && [ -n "$out" ]; then + echo " $out" + fi + + return $rc +} + +################################################################################ +# Setup + +setup() +{ + set -e + + setup_ns ns1 ns2 + + ip -n "$ns1" link add veth0 type veth peer name veth1 netns "$ns2" + ip -n "$ns1" link set dev veth0 up + ip -n "$ns2" link set dev veth1 up + + ip -n "$ns1" address add 192.0.2.1/24 dev veth0 + ip -n "$ns1" address add 2001:db8:1::1/64 dev veth0 nodad + ip -n "$ns2" address add 192.0.2.2/24 dev veth1 + ip -n "$ns2" address add 2001:db8:1::2/64 dev veth1 nodad + + ip netns exec "$ns1" sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + ip netns exec "$ns2" sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + + sleep 5 + + set +e +} + +exit_cleanup_all() +{ + cleanup_all_ns + exit "${EXIT_STATUS}" +} + +################################################################################ +# Tests + +extern_valid_common() +{ + local af_str=$1; shift + local ip_addr=$1; shift + local tbl_name=$1; shift + local subnet=$1; shift + local mac + + mac=$(ip -n "$ns2" -j link show dev veth1 | jq -r '.[]["address"]') + + RET=0 + + # Check that simple addition works. + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "No \"extern_valid\" flag after addition" + + log_test "$af_str \"extern_valid\" flag: Add entry" + + RET=0 + + # Check that an entry cannot be added with "extern_valid" flag and an + # invalid state. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr nud none dev veth0 extern_valid" + check_fail $? "Managed to add an entry with \"extern_valid\" flag and an invalid state" + + log_test "$af_str \"extern_valid\" flag: Add with an invalid state" + + RET=0 + + # Check that entry cannot be added with both "extern_valid" flag and + # "use" / "managed" flag. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid use" + check_fail $? "Managed to add an entry with \"extern_valid\" flag and \"use\" flag" + + log_test "$af_str \"extern_valid\" flag: Add with \"use\" flag" + + RET=0 + + # Check that "extern_valid" flag can be toggled using replace. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Did not manage to set \"extern_valid\" flag with replace" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_fail $? "Did not manage to clear \"extern_valid\" flag with replace" + + log_test "$af_str \"extern_valid\" flag: Replace entry" + + RET=0 + + # Check that an existing "extern_valid" entry can be marked as + # "managed". + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid managed" + check_err $? "Did not manage to add \"managed\" flag to an existing \"extern_valid\" entry" + + log_test "$af_str \"extern_valid\" flag: Replace entry with \"managed\" flag" + + RET=0 + + # Check that entry cannot be replaced with "extern_valid" flag and an + # invalid state. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh replace $ip_addr nud none dev veth0 extern_valid" + check_fail $? "Managed to replace an entry with \"extern_valid\" flag and an invalid state" + + log_test "$af_str \"extern_valid\" flag: Replace with an invalid state" + + RET=0 + + # Check that an "extern_valid" entry is flushed when the interface is + # put administratively down. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 link set dev veth0 down" + run_cmd "ip -n $ns1 link set dev veth0 up" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0" + check_fail $? "\"extern_valid\" entry not flushed upon interface down" + + log_test "$af_str \"extern_valid\" flag: Interface down" + + RET=0 + + # Check that an "extern_valid" entry is not flushed when the interface + # loses its carrier. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns2 link set dev veth1 down" + run_cmd "ip -n $ns2 link set dev veth1 up" + run_cmd "sleep 2" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0" + check_err $? "\"extern_valid\" entry flushed upon carrier down" + + log_test "$af_str \"extern_valid\" flag: Carrier down" + + RET=0 + + # Check that when entry transitions to "reachable" state it maintains + # the "extern_valid" flag. Wait "delay_probe" seconds for ARP request / + # NS to be sent. + local delay_probe + + delay_probe=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["delay_probe"]') + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid use" + run_cmd "sleep $((delay_probe / 1000 + 2))" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"REACHABLE\"" + check_err $? "Entry did not transition to \"reachable\" state" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Entry did not maintain \"extern_valid\" flag after transition to \"reachable\" state" + + log_test "$af_str \"extern_valid\" flag: Transition to \"reachable\" state" + + RET=0 + + # Drop all packets, trigger resolution and check that entry goes back + # to "stale" state instead of "failed". + local mcast_reprobes + local retrans_time + local ucast_probes + local app_probes + local probes + local delay + + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "tc -n $ns2 qdisc add dev veth1 clsact" + run_cmd "tc -n $ns2 filter add dev veth1 ingress proto all matchall action drop" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid use" + retrans_time=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["retrans"]') + ucast_probes=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["ucast_probes"]') + app_probes=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["app_probes"]') + mcast_reprobes=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["mcast_reprobes"]') + delay=$((delay_probe + (ucast_probes + app_probes + mcast_reprobes) * retrans_time)) + run_cmd "sleep $((delay / 1000 + 2))" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"STALE\"" + check_err $? "Entry did not return to \"stale\" state" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Entry did not maintain \"extern_valid\" flag after returning to \"stale\" state" + probes=$(ip -n "$ns1" -j -s neigh get "$ip_addr" dev veth0 | jq '.[]["probes"]') + if [[ $probes -eq 0 ]]; then + check_err 1 "No probes were sent" + fi + + log_test "$af_str \"extern_valid\" flag: Transition back to \"stale\" state" + + run_cmd "tc -n $ns2 qdisc del dev veth1 clsact" + + RET=0 + + # Forced garbage collection runs whenever the number of entries is + # larger than "thresh3" and deletes stale entries that have not been + # updated in the last 5 seconds. + # + # Check that an "extern_valid" entry survives a forced garbage + # collection. Add an entry, wait 5 seconds and add more entries than + # "thresh3" so that forced garbage collection will run. + # + # Note that the garbage collection thresholds are global resources and + # that changes in the initial namespace affect all the namespaces. + local forced_gc_runs_t0 + local forced_gc_runs_t1 + local orig_thresh1 + local orig_thresh2 + local orig_thresh3 + + run_cmd "ip -n $ns1 neigh flush dev veth0" + orig_thresh1=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh1")) | .["thresh1"]') + orig_thresh2=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh2")) | .["thresh2"]') + orig_thresh3=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh3")) | .["thresh3"]') + run_cmd "ip ntable change name $tbl_name thresh3 10 thresh2 9 thresh1 8" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh add ${subnet}3 lladdr $mac nud stale dev veth0" + run_cmd "sleep 5" + forced_gc_runs_t0=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("forced_gc_runs")) | .["forced_gc_runs"]') + for i in {1..20}; do + run_cmd "ip -n $ns1 neigh add ${subnet}$((i + 4)) nud none dev veth0" + done + forced_gc_runs_t1=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("forced_gc_runs")) | .["forced_gc_runs"]') + if [[ $forced_gc_runs_t1 -eq $forced_gc_runs_t0 ]]; then + check_err 1 "Forced garbage collection did not run" + fi + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Entry with \"extern_valid\" flag did not survive forced garbage collection" + run_cmd "ip -n $ns1 neigh get ${subnet}3 dev veth0" + check_fail $? "Entry without \"extern_valid\" flag survived forced garbage collection" + + log_test "$af_str \"extern_valid\" flag: Forced garbage collection" + + run_cmd "ip ntable change name $tbl_name thresh3 $orig_thresh3 thresh2 $orig_thresh2 thresh1 $orig_thresh1" + + RET=0 + + # Periodic garbage collection runs every "base_reachable"/2 seconds and + # if the number of entries is larger than "thresh1", then it deletes + # stale entries that have not been used in the last "gc_stale" seconds. + # + # Check that an "extern_valid" entry survives a periodic garbage + # collection. Add an "extern_valid" entry, add more than "thresh1" + # regular entries, wait "base_reachable" (longer than "gc_stale") + # seconds and check that the "extern_valid" entry was not deleted. + # + # Note that the garbage collection thresholds and "base_reachable" are + # global resources and that changes in the initial namespace affect all + # the namespaces. + local periodic_gc_runs_t0 + local periodic_gc_runs_t1 + local orig_base_reachable + local orig_gc_stale + + run_cmd "ip -n $ns1 neigh flush dev veth0" + orig_thresh1=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh1")) | .["thresh1"]') + orig_base_reachable=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh1")) | .["base_reachable"]') + run_cmd "ip ntable change name $tbl_name thresh1 10 base_reachable 10000" + orig_gc_stale=$(ip -n "$ns1" -j ntable show name "$tbl_name" dev veth0 | jq '.[]["gc_stale"]') + run_cmd "ip -n $ns1 ntable change name $tbl_name dev veth0 gc_stale 5000" + # Wait orig_base_reachable/2 for the new interval to take effect. + run_cmd "sleep $(((orig_base_reachable / 1000) / 2 + 2))" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh add ${subnet}3 lladdr $mac nud stale dev veth0" + for i in {1..20}; do + run_cmd "ip -n $ns1 neigh add ${subnet}$((i + 4)) nud none dev veth0" + done + periodic_gc_runs_t0=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("periodic_gc_runs")) | .["periodic_gc_runs"]') + run_cmd "sleep 10" + periodic_gc_runs_t1=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("periodic_gc_runs")) | .["periodic_gc_runs"]') + [[ $periodic_gc_runs_t1 -ne $periodic_gc_runs_t0 ]] + check_err $? "Periodic garbage collection did not run" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Entry with \"extern_valid\" flag did not survive periodic garbage collection" + run_cmd "ip -n $ns1 neigh get ${subnet}3 dev veth0" + check_fail $? "Entry without \"extern_valid\" flag survived periodic garbage collection" + + log_test "$af_str \"extern_valid\" flag: Periodic garbage collection" + + run_cmd "ip -n $ns1 ntable change name $tbl_name dev veth0 gc_stale $orig_gc_stale" + run_cmd "ip ntable change name $tbl_name thresh1 $orig_thresh1 base_reachable $orig_base_reachable" +} + +extern_valid_ipv4() +{ + extern_valid_common "IPv4" 192.0.2.2 "arp_cache" 192.0.2. +} + +extern_valid_ipv6() +{ + extern_valid_common "IPv6" 2001:db8:1::2 "ndisc_cache" 2001:db8:1:: +} + +################################################################################ +# Usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -t <test> Test(s) to run (default: all) + (options: $TESTS) + -p Pause on fail + -v Verbose mode (show commands and output) +EOF +} + +################################################################################ +# Main + +while getopts ":t:pvh" opt; do + case $opt in + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=$((VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +require_command jq + +if ! ip neigh help 2>&1 | grep -q "extern_valid"; then + echo "SKIP: iproute2 ip too old, missing \"extern_valid\" support" + exit "$ksft_skip" +fi + +trap exit_cleanup_all EXIT + +for t in $TESTS +do + setup; $t; cleanup_all_ns; +done diff --git a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh index 6127a78ee988..8deacc565afa 100755 --- a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh +++ b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh @@ -146,18 +146,17 @@ run_cmd() } check_hv_connectivity() { - ip netns exec $hv_1 ping -c 1 -W 1 $1 &>/dev/null - sleep 1 - ip netns exec $hv_1 ping -c 1 -W 1 $2 &>/dev/null + slowwait 5 ip netns exec $hv_1 ping -c 1 -W 1 $1 &>/dev/null + slowwait 5 ip netns exec $hv_1 ping -c 1 -W 1 $2 &>/dev/null return $? } check_vm_connectivity() { - run_cmd "ip netns exec $vm_11 ping -c 1 -W 1 10.0.10.12" + slowwait 5 run_cmd "ip netns exec $vm_11 ping -c 1 -W 1 10.0.10.12" log_test $? 0 "VM connectivity over $1 (ipv4 default rdst)" - run_cmd "ip netns exec $vm_21 ping -c 1 -W 1 10.0.10.22" + slowwait 5 run_cmd "ip netns exec $vm_21 ping -c 1 -W 1 10.0.10.22" log_test $? 0 "VM connectivity over $1 (ipv6 default rdst)" } diff --git a/tools/testing/selftests/net/vrf_route_leaking.sh b/tools/testing/selftests/net/vrf_route_leaking.sh index e9c2f71da207..ce34cb2e6e0b 100755 --- a/tools/testing/selftests/net/vrf_route_leaking.sh +++ b/tools/testing/selftests/net/vrf_route_leaking.sh @@ -275,7 +275,7 @@ setup_sym() # Wait for ip config to settle - sleep 2 + slowwait 5 ip netns exec $h1 "${ping6}" -c1 -w1 ${H2_N2_IP6} >/dev/null 2>&1 } setup_asym() @@ -370,7 +370,7 @@ setup_asym() ip -netns $r2 -6 addr add dev eth1 ${R2_N2_IP6}/64 nodad # Wait for ip config to settle - sleep 2 + slowwait 5 ip netns exec $h1 "${ping6}" -c1 -w1 ${H2_N2_IP6} >/dev/null 2>&1 } check_connectivity() diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index 94176ffe4646..40f5c2908dda 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -1,341 +1,26 @@ # SPDX-License-Identifier: GPL-2.0 -# Makefile for nolibc tests -# we're in ".../tools/testing/selftests/nolibc" -ifeq ($(srctree),) -srctree := $(patsubst %/tools/testing/selftests/,%,$(dir $(CURDIR))) -endif - -include $(srctree)/tools/scripts/utilities.mak -# We need this for the "__cc-option" macro. -include $(srctree)/scripts/Makefile.compiler - -ifneq ($(O),) -ifneq ($(call is-absolute,$(O)),y) -$(error Only absolute O= parameters are supported) -endif -objtree := $(O) -else -objtree ?= $(srctree) -endif - -ifeq ($(ARCH),) -include $(srctree)/scripts/subarch.include -ARCH = $(SUBARCH) -endif - -cc-option = $(call __cc-option, $(CC),$(CLANG_CROSS_FLAGS),$(1),$(2)) - -# XARCH extends the kernel's ARCH with a few variants of the same -# architecture that only differ by the configuration, the toolchain -# and the Qemu program used. It is copied as-is into ARCH except for -# a few specific values which are mapped like this: -# -# XARCH | ARCH | config -# -------------|-----------|------------------------- -# ppc | powerpc | 32 bits -# ppc64 | powerpc | 64 bits big endian -# ppc64le | powerpc | 64 bits little endian -# -# It is recommended to only use XARCH, though it does not harm if -# ARCH is already set. For simplicity, ARCH is sufficient for all -# architectures where both are equal. - -# configure default variants for target kernel supported architectures -XARCH_powerpc = ppc -XARCH_mips = mips32le -XARCH_riscv = riscv64 -XARCH = $(or $(XARCH_$(ARCH)),$(ARCH)) - -# map from user input variants to their kernel supported architectures -ARCH_armthumb = arm -ARCH_ppc = powerpc -ARCH_ppc64 = powerpc -ARCH_ppc64le = powerpc -ARCH_mips32le = mips -ARCH_mips32be = mips -ARCH_riscv32 = riscv -ARCH_riscv64 = riscv -ARCH_s390x = s390 -ARCH_sparc32 = sparc -ARCH_sparc64 = sparc -ARCH := $(or $(ARCH_$(XARCH)),$(XARCH)) -# kernel image names by architecture -IMAGE_i386 = arch/x86/boot/bzImage -IMAGE_x86_64 = arch/x86/boot/bzImage -IMAGE_x86 = arch/x86/boot/bzImage -IMAGE_arm64 = arch/arm64/boot/Image -IMAGE_arm = arch/arm/boot/zImage -IMAGE_armthumb = arch/arm/boot/zImage -IMAGE_mips32le = vmlinuz -IMAGE_mips32be = vmlinuz -IMAGE_ppc = vmlinux -IMAGE_ppc64 = vmlinux -IMAGE_ppc64le = arch/powerpc/boot/zImage -IMAGE_riscv = arch/riscv/boot/Image -IMAGE_riscv32 = arch/riscv/boot/Image -IMAGE_riscv64 = arch/riscv/boot/Image -IMAGE_s390x = arch/s390/boot/bzImage -IMAGE_s390 = arch/s390/boot/bzImage -IMAGE_loongarch = arch/loongarch/boot/vmlinuz.efi -IMAGE_sparc32 = arch/sparc/boot/image -IMAGE_sparc64 = arch/sparc/boot/image -IMAGE_m68k = vmlinux -IMAGE = $(objtree)/$(IMAGE_$(XARCH)) -IMAGE_NAME = $(notdir $(IMAGE)) +TEST_GEN_PROGS := nolibc-test -# default kernel configurations that appear to be usable -DEFCONFIG_i386 = defconfig -DEFCONFIG_x86_64 = defconfig -DEFCONFIG_x86 = defconfig -DEFCONFIG_arm64 = defconfig -DEFCONFIG_arm = multi_v7_defconfig -DEFCONFIG_armthumb = multi_v7_defconfig -DEFCONFIG_mips32le = malta_defconfig -DEFCONFIG_mips32be = malta_defconfig generic/eb.config -DEFCONFIG_ppc = pmac32_defconfig -DEFCONFIG_ppc64 = powernv_be_defconfig -DEFCONFIG_ppc64le = powernv_defconfig -DEFCONFIG_riscv = defconfig -DEFCONFIG_riscv32 = rv32_defconfig -DEFCONFIG_riscv64 = defconfig -DEFCONFIG_s390x = defconfig -DEFCONFIG_s390 = defconfig compat.config -DEFCONFIG_loongarch = defconfig -DEFCONFIG_sparc32 = sparc32_defconfig -DEFCONFIG_sparc64 = sparc64_defconfig -DEFCONFIG_m68k = virt_defconfig -DEFCONFIG = $(DEFCONFIG_$(XARCH)) +include ../lib.mk +include $(top_srcdir)/scripts/Makefile.compiler -EXTRACONFIG_m68k = -e CONFIG_BLK_DEV_INITRD -EXTRACONFIG = $(EXTRACONFIG_$(XARCH)) -EXTRACONFIG_arm = -e CONFIG_NAMESPACES -EXTRACONFIG_armthumb = -e CONFIG_NAMESPACES - -# optional tests to run (default = all) -TEST = - -# QEMU_ARCH: arch names used by qemu -QEMU_ARCH_i386 = i386 -QEMU_ARCH_x86_64 = x86_64 -QEMU_ARCH_x86 = x86_64 -QEMU_ARCH_arm64 = aarch64 -QEMU_ARCH_arm = arm -QEMU_ARCH_armthumb = arm -QEMU_ARCH_mips32le = mipsel # works with malta_defconfig -QEMU_ARCH_mips32be = mips -QEMU_ARCH_ppc = ppc -QEMU_ARCH_ppc64 = ppc64 -QEMU_ARCH_ppc64le = ppc64 -QEMU_ARCH_riscv = riscv64 -QEMU_ARCH_riscv32 = riscv32 -QEMU_ARCH_riscv64 = riscv64 -QEMU_ARCH_s390x = s390x -QEMU_ARCH_s390 = s390x -QEMU_ARCH_loongarch = loongarch64 -QEMU_ARCH_sparc32 = sparc -QEMU_ARCH_sparc64 = sparc64 -QEMU_ARCH_m68k = m68k -QEMU_ARCH = $(QEMU_ARCH_$(XARCH)) - -QEMU_ARCH_USER_ppc64le = ppc64le -QEMU_ARCH_USER = $(or $(QEMU_ARCH_USER_$(XARCH)),$(QEMU_ARCH_$(XARCH))) - -QEMU_BIOS_DIR = /usr/share/edk2/ -QEMU_BIOS_loongarch = $(QEMU_BIOS_DIR)/loongarch64/OVMF_CODE.fd - -ifneq ($(QEMU_BIOS_$(XARCH)),) -QEMU_ARGS_BIOS = -bios $(QEMU_BIOS_$(XARCH)) -endif - -# QEMU_ARGS : some arch-specific args to pass to qemu -QEMU_ARGS_i386 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_x86_64 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_x86 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_arm64 = -M virt -cpu cortex-a53 -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_arm = -M virt -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_armthumb = -M virt -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_mips32le = -M malta -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_mips32be = -M malta -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_ppc = -M g3beige -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_ppc64 = -M powernv -append "console=hvc0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_ppc64le = -M powernv -append "console=hvc0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_riscv = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_riscv32 = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_riscv64 = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_s390x = -M s390-ccw-virtio -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_s390 = -M s390-ccw-virtio -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_loongarch = -M virt -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_sparc32 = -M SS-5 -m 256M -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_sparc64 = -M sun4u -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS_m68k = -M virt -append "console=ttyGF0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS = -m 1G $(QEMU_ARGS_$(XARCH)) $(QEMU_ARGS_BIOS) $(QEMU_ARGS_EXTRA) - -# OUTPUT is only set when run from the main makefile, otherwise -# it defaults to this nolibc directory. -OUTPUT ?= $(CURDIR)/ - -ifeq ($(V),1) -Q= -else -Q=@ -endif +cc-option = $(call __cc-option, $(CC),,$(1),$(2)) -CFLAGS_i386 = $(call cc-option,-m32) -CFLAGS_arm = -marm -CFLAGS_armthumb = -mthumb -march=armv6t2 -CFLAGS_ppc = -m32 -mbig-endian -mno-vsx $(call cc-option,-mmultiple) -CFLAGS_ppc64 = -m64 -mbig-endian -mno-vsx $(call cc-option,-mmultiple) -CFLAGS_ppc64le = -m64 -mlittle-endian -mno-vsx $(call cc-option,-mabi=elfv2) -CFLAGS_s390x = -m64 -CFLAGS_s390 = -m31 -CFLAGS_mips32le = -EL -mabi=32 -fPIC -CFLAGS_mips32be = -EB -mabi=32 -CFLAGS_sparc32 = $(call cc-option,-m32) -ifeq ($(origin XARCH),command line) -CFLAGS_XARCH = $(CFLAGS_$(XARCH)) -endif -CFLAGS_STACKPROTECTOR ?= $(call cc-option,-mstack-protector-guard=global $(call cc-option,-fstack-protector-all)) -CFLAGS_SANITIZER ?= $(call cc-option,-fsanitize=undefined -fsanitize-trap=all) -CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables -std=c89 -W -Wall -Wextra \ - $(call cc-option,-fno-stack-protector) $(call cc-option,-Wmissing-prototypes) \ - $(CFLAGS_XARCH) $(CFLAGS_STACKPROTECTOR) $(CFLAGS_SANITIZER) $(CFLAGS_EXTRA) -LDFLAGS := +include Makefile.include -LIBGCC := -lgcc +CFLAGS = -nostdlib -nostdinc -static \ + -isystem $(top_srcdir)/tools/include/nolibc -isystem $(top_srcdir)/usr/include \ + $(CFLAGS_NOLIBC_TEST) -ifneq ($(LLVM),) -# Not needed for clang -LIBGCC := +ifeq ($(LLVM),) +LDLIBS := -lgcc endif -# Modify CFLAGS based on LLVM= -include $(srctree)/tools/scripts/Makefile.include - -# GCC uses "s390", clang "systemz" -CLANG_CROSS_FLAGS := $(subst --target=s390-linux,--target=systemz-linux,$(CLANG_CROSS_FLAGS)) - -REPORT ?= awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{if (!f) printf("\n"); f++; print;} /\[SKIPPED\][\r]*$$/{s++} \ - END{ printf("\n%3d test(s): %3d passed, %3d skipped, %3d failed => status: ", p+s+f, p, s, f); \ - if (f || !p) printf("failure\n"); else if (s) printf("warning\n"); else printf("success\n");; \ - printf("\nSee all results in %s\n", ARGV[1]); }' +$(OUTPUT)/nolibc-test: nolibc-test.c nolibc-test-linkage.c | headers help: - @echo "Supported targets under selftests/nolibc:" - @echo " all call the \"run\" target below" - @echo " help this help" - @echo " sysroot create the nolibc sysroot here (uses \$$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 \$$XARCH, \$$TEST)" - @echo " initramfs.cpio prepare the initramfs archive with nolibc-test" - @echo " initramfs prepare the initramfs tree with nolibc-test" - @echo " defconfig create a fresh new default config (uses \$$XARCH)" - @echo " kernel (re)build the kernel (uses \$$XARCH)" - @echo " kernel-standalone (re)build the kernel with the initramfs (uses \$$XARCH)" - @echo " run runs the kernel in QEMU after building it (uses \$$XARCH, \$$TEST)" - @echo " rerun runs a previously prebuilt kernel in QEMU (uses \$$XARCH, \$$TEST)" - @echo " clean clean the sysroot, initramfs, build and output files" - @echo "" - @echo "The output file is \"run.out\". Test ranges may be passed using \$$TEST." - @echo "" - @echo "Currently using the following variables:" - @echo " ARCH = $(ARCH)" - @echo " XARCH = $(XARCH)" - @echo " CROSS_COMPILE = $(CROSS_COMPILE)" - @echo " CC = $(CC)" - @echo " OUTPUT = $(OUTPUT)" - @echo " TEST = $(TEST)" - @echo " QEMU_ARCH = $(if $(QEMU_ARCH),$(QEMU_ARCH),UNKNOWN_ARCH) [determined from \$$XARCH]" - @echo " IMAGE_NAME = $(if $(IMAGE_NAME),$(IMAGE_NAME),UNKNOWN_ARCH) [determined from \$$XARCH]" - @echo "" - -all: run - -sysroot: sysroot/$(ARCH)/include - -sysroot/$(ARCH)/include: - $(Q)rm -rf sysroot/$(ARCH) sysroot/sysroot - $(QUIET_MKDIR)mkdir -p sysroot - $(Q)$(MAKE) -C $(srctree) outputmakefile - $(Q)$(MAKE) -C $(srctree)/tools/include/nolibc ARCH=$(ARCH) OUTPUT=$(CURDIR)/sysroot/ headers_standalone headers_check - $(Q)mv sysroot/sysroot sysroot/$(ARCH) - -ifneq ($(NOLIBC_SYSROOT),0) -nolibc-test: nolibc-test.c nolibc-test-linkage.c sysroot/$(ARCH)/include - $(QUIET_CC)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ \ - -nostdlib -nostdinc -static -Isysroot/$(ARCH)/include nolibc-test.c nolibc-test-linkage.c $(LIBGCC) -else -nolibc-test: nolibc-test.c nolibc-test-linkage.c - $(QUIET_CC)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ \ - -nostdlib -static -include $(srctree)/tools/include/nolibc/nolibc.h nolibc-test.c nolibc-test-linkage.c $(LIBGCC) -endif - -libc-test: nolibc-test.c nolibc-test-linkage.c - $(QUIET_CC)$(HOSTCC) -o $@ nolibc-test.c nolibc-test-linkage.c - -# local libc-test -run-libc-test: libc-test - $(Q)./libc-test > "$(CURDIR)/run.out" || : - $(Q)$(REPORT) $(CURDIR)/run.out - -# local nolibc-test -run-nolibc-test: nolibc-test - $(Q)./nolibc-test > "$(CURDIR)/run.out" || : - $(Q)$(REPORT) $(CURDIR)/run.out - -# qemu user-land test -run-user: nolibc-test - $(Q)qemu-$(QEMU_ARCH_USER) ./nolibc-test > "$(CURDIR)/run.out" || : - $(Q)$(REPORT) $(CURDIR)/run.out - -initramfs.cpio: kernel nolibc-test - $(QUIET_GEN)echo 'file /init nolibc-test 755 0 0' | $(objtree)/usr/gen_init_cpio - > initramfs.cpio - -initramfs: nolibc-test - $(QUIET_MKDIR)mkdir -p initramfs - $(call QUIET_INSTALL, initramfs/init) - $(Q)cp nolibc-test initramfs/init - -defconfig: - $(Q)$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) $(DEFCONFIG) - $(Q)if [ -n "$(EXTRACONFIG)" ]; then \ - $(srctree)/scripts/config --file $(objtree)/.config $(EXTRACONFIG); \ - $(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) olddefconfig < /dev/null; \ - fi - -kernel: | defconfig - $(Q)$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) $(IMAGE_NAME) < /dev/null - -kernel-standalone: initramfs | defconfig - $(Q)$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) $(IMAGE_NAME) CONFIG_INITRAMFS_SOURCE=$(CURDIR)/initramfs < /dev/null - -# run the tests after building the kernel -run: kernel initramfs.cpio - $(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(IMAGE)" -initrd initramfs.cpio -serial stdio $(QEMU_ARGS) > "$(CURDIR)/run.out" - $(Q)$(REPORT) $(CURDIR)/run.out - -# re-run the tests from an existing kernel -rerun: - $(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(IMAGE)" -initrd initramfs.cpio -serial stdio $(QEMU_ARGS) > "$(CURDIR)/run.out" - $(Q)$(REPORT) $(CURDIR)/run.out - -# report with existing test log -report: - $(Q)$(REPORT) $(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.cpio) - $(Q)rm -rf initramfs.cpio - $(call QUIET_CLEAN, initramfs) - $(Q)rm -rf initramfs - $(call QUIET_CLEAN, run.out) - $(Q)rm -rf run.out + @echo "For the custom nolibc testsuite use '$(MAKE) -f Makefile.nolibc'; available targets:" + @$(MAKE) -f Makefile.nolibc help -.PHONY: sysroot/$(ARCH)/include +.PHONY: help diff --git a/tools/testing/selftests/nolibc/Makefile.include b/tools/testing/selftests/nolibc/Makefile.include new file mode 100644 index 000000000000..66287fafbbe0 --- /dev/null +++ b/tools/testing/selftests/nolibc/Makefile.include @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 + +__CFLAGS_STACKPROTECTOR = $(call cc-option,-fstack-protector-all) $(call cc-option,-mstack-protector-guard=global) +_CFLAGS_STACKPROTECTOR ?= $(call try-run, \ + echo 'void foo(void) {}' | $(CC) -x c - -o - -S $(CLANG_CROSS_FLAGS) $(__CFLAGS_STACKPROTECTOR) | grep -q __stack_chk_guard, \ + $(__CFLAGS_STACKPROTECTOR)) +_CFLAGS_SANITIZER ?= $(call cc-option,-fsanitize=undefined -fsanitize-trap=all) +CFLAGS_NOLIBC_TEST ?= -Os -fno-ident -fno-asynchronous-unwind-tables -std=c89 -W -Wall -Wextra \ + $(call cc-option,-fno-stack-protector) $(call cc-option,-Wmissing-prototypes) \ + $(_CFLAGS_STACKPROTECTOR) $(_CFLAGS_SANITIZER) diff --git a/tools/testing/selftests/nolibc/Makefile.nolibc b/tools/testing/selftests/nolibc/Makefile.nolibc new file mode 100644 index 000000000000..0fb759ba992e --- /dev/null +++ b/tools/testing/selftests/nolibc/Makefile.nolibc @@ -0,0 +1,383 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for nolibc tests +# we're in ".../tools/testing/selftests/nolibc" +ifeq ($(srctree),) +srctree := $(patsubst %/tools/testing/selftests/,%,$(dir $(CURDIR))) +endif + +include $(srctree)/tools/scripts/utilities.mak +# We need this for the "__cc-option" macro. +include $(srctree)/scripts/Makefile.compiler + +ifneq ($(O),) +ifneq ($(call is-absolute,$(O)),y) +$(error Only absolute O= parameters are supported) +endif +objtree := $(O) +else +objtree ?= $(srctree) +endif + +ifeq ($(ARCH),) +include $(srctree)/scripts/subarch.include +ARCH = $(SUBARCH) +endif + +cc-option = $(call __cc-option, $(CC),$(CLANG_CROSS_FLAGS),$(1),$(2)) + +# XARCH extends the kernel's ARCH with a few variants of the same +# architecture that only differ by the configuration, the toolchain +# and the Qemu program used. It is copied as-is into ARCH except for +# a few specific values which are mapped like this: +# +# XARCH | ARCH | config +# -------------|-----------|------------------------- +# ppc | powerpc | 32 bits +# ppc64 | powerpc | 64 bits big endian +# ppc64le | powerpc | 64 bits little endian +# +# It is recommended to only use XARCH, though it does not harm if +# ARCH is already set. For simplicity, ARCH is sufficient for all +# architectures where both are equal. + +# configure default variants for target kernel supported architectures +XARCH_powerpc = ppc +XARCH_mips = mips32le +XARCH_riscv = riscv64 +XARCH = $(or $(XARCH_$(ARCH)),$(ARCH)) + +# map from user input variants to their kernel supported architectures +ARCH_x32 = x86 +ARCH_armthumb = arm +ARCH_ppc = powerpc +ARCH_ppc64 = powerpc +ARCH_ppc64le = powerpc +ARCH_mips32le = mips +ARCH_mips32be = mips +ARCH_mipsn32le = mips +ARCH_mipsn32be = mips +ARCH_mips64le = mips +ARCH_mips64be = mips +ARCH_riscv32 = riscv +ARCH_riscv64 = riscv +ARCH_s390x = s390 +ARCH_sparc32 = sparc +ARCH_sparc64 = sparc +ARCH_sh4 = sh +ARCH := $(or $(ARCH_$(XARCH)),$(XARCH)) + +# kernel image names by architecture +IMAGE_i386 = arch/x86/boot/bzImage +IMAGE_x86_64 = arch/x86/boot/bzImage +IMAGE_x32 = arch/x86/boot/bzImage +IMAGE_x86 = arch/x86/boot/bzImage +IMAGE_arm64 = arch/arm64/boot/Image +IMAGE_arm = arch/arm/boot/zImage +IMAGE_armthumb = arch/arm/boot/zImage +IMAGE_mips32le = vmlinuz +IMAGE_mips32be = vmlinuz +IMAGE_mipsn32le = vmlinuz +IMAGE_mipsn32be = vmlinuz +IMAGE_mips64le = vmlinuz +IMAGE_mips64be = vmlinuz +IMAGE_ppc = vmlinux +IMAGE_ppc64 = vmlinux +IMAGE_ppc64le = arch/powerpc/boot/zImage +IMAGE_riscv = arch/riscv/boot/Image +IMAGE_riscv32 = arch/riscv/boot/Image +IMAGE_riscv64 = arch/riscv/boot/Image +IMAGE_s390x = arch/s390/boot/bzImage +IMAGE_s390 = arch/s390/boot/bzImage +IMAGE_loongarch = arch/loongarch/boot/vmlinuz.efi +IMAGE_sparc32 = arch/sparc/boot/image +IMAGE_sparc64 = arch/sparc/boot/image +IMAGE_m68k = vmlinux +IMAGE_sh4 = arch/sh/boot/zImage +IMAGE = $(objtree)/$(IMAGE_$(XARCH)) +IMAGE_NAME = $(notdir $(IMAGE)) + +# default kernel configurations that appear to be usable +DEFCONFIG_i386 = defconfig +DEFCONFIG_x86_64 = defconfig +DEFCONFIG_x32 = defconfig +DEFCONFIG_x86 = defconfig +DEFCONFIG_arm64 = defconfig +DEFCONFIG_arm = multi_v7_defconfig +DEFCONFIG_armthumb = multi_v7_defconfig +DEFCONFIG_mips32le = malta_defconfig +DEFCONFIG_mips32be = malta_defconfig generic/eb.config +DEFCONFIG_mipsn32le = malta_defconfig generic/64r2.config +DEFCONFIG_mipsn32be = malta_defconfig generic/64r6.config generic/eb.config +DEFCONFIG_mips64le = malta_defconfig generic/64r6.config +DEFCONFIG_mips64be = malta_defconfig generic/64r2.config generic/eb.config +DEFCONFIG_ppc = pmac32_defconfig +DEFCONFIG_ppc64 = powernv_be_defconfig +DEFCONFIG_ppc64le = powernv_defconfig +DEFCONFIG_riscv = defconfig +DEFCONFIG_riscv32 = rv32_defconfig +DEFCONFIG_riscv64 = defconfig +DEFCONFIG_s390x = defconfig +DEFCONFIG_s390 = defconfig compat.config +DEFCONFIG_loongarch = defconfig +DEFCONFIG_sparc32 = sparc32_defconfig +DEFCONFIG_sparc64 = sparc64_defconfig +DEFCONFIG_m68k = virt_defconfig +DEFCONFIG_sh4 = rts7751r2dplus_defconfig +DEFCONFIG = $(DEFCONFIG_$(XARCH)) + +EXTRACONFIG_x32 = -e CONFIG_X86_X32_ABI +EXTRACONFIG_arm = -e CONFIG_NAMESPACES +EXTRACONFIG_armthumb = -e CONFIG_NAMESPACES +EXTRACONFIG_m68k = -e CONFIG_BLK_DEV_INITRD +EXTRACONFIG_sh4 = -e CONFIG_BLK_DEV_INITRD -e CONFIG_CMDLINE_FROM_BOOTLOADER +EXTRACONFIG = $(EXTRACONFIG_$(XARCH)) + +# optional tests to run (default = all) +TEST = + +# QEMU_ARCH: arch names used by qemu +QEMU_ARCH_i386 = i386 +QEMU_ARCH_x86_64 = x86_64 +QEMU_ARCH_x32 = x86_64 +QEMU_ARCH_x86 = x86_64 +QEMU_ARCH_arm64 = aarch64 +QEMU_ARCH_arm = arm +QEMU_ARCH_armthumb = arm +QEMU_ARCH_mips32le = mipsel # works with malta_defconfig +QEMU_ARCH_mips32be = mips +QEMU_ARCH_mipsn32le = mips64el +QEMU_ARCH_mipsn32be = mips64 +QEMU_ARCH_mips64le = mips64el +QEMU_ARCH_mips64be = mips64 +QEMU_ARCH_ppc = ppc +QEMU_ARCH_ppc64 = ppc64 +QEMU_ARCH_ppc64le = ppc64 +QEMU_ARCH_riscv = riscv64 +QEMU_ARCH_riscv32 = riscv32 +QEMU_ARCH_riscv64 = riscv64 +QEMU_ARCH_s390x = s390x +QEMU_ARCH_s390 = s390x +QEMU_ARCH_loongarch = loongarch64 +QEMU_ARCH_sparc32 = sparc +QEMU_ARCH_sparc64 = sparc64 +QEMU_ARCH_m68k = m68k +QEMU_ARCH_sh4 = sh4 +QEMU_ARCH = $(QEMU_ARCH_$(XARCH)) + +QEMU_ARCH_USER_ppc64le = ppc64le +QEMU_ARCH_USER_mipsn32le = mipsn32el +QEMU_ARCH_USER_mipsn32be = mipsn32 +QEMU_ARCH_USER = $(or $(QEMU_ARCH_USER_$(XARCH)),$(QEMU_ARCH_$(XARCH))) + +QEMU_BIOS_DIR = /usr/share/edk2/ +QEMU_BIOS_loongarch = $(QEMU_BIOS_DIR)/loongarch64/OVMF_CODE.fd + +ifneq ($(QEMU_BIOS_$(XARCH)),) +QEMU_ARGS_BIOS = -bios $(QEMU_BIOS_$(XARCH)) +endif + +# QEMU_ARGS : some arch-specific args to pass to qemu +QEMU_ARGS_i386 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_x86_64 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_x32 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_x86 = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_arm64 = -M virt -cpu cortex-a53 -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_arm = -M virt -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_armthumb = -M virt -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_mips32le = -M malta -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_mips32be = -M malta -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_mipsn32le = -M malta -cpu 5KEc -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_mipsn32be = -M malta -cpu I6400 -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_mips64le = -M malta -cpu I6400 -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_mips64be = -M malta -cpu 5KEc -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_ppc = -M g3beige -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_ppc64 = -M powernv -append "console=hvc0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_ppc64le = -M powernv -append "console=hvc0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_riscv = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_riscv32 = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_riscv64 = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_s390x = -M s390-ccw-virtio -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_s390 = -M s390-ccw-virtio -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_loongarch = -M virt -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_sparc32 = -M SS-5 -m 256M -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_sparc64 = -M sun4u -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_m68k = -M virt -append "console=ttyGF0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_sh4 = -M r2d -serial file:/dev/stdout -append "console=ttySC1,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS = -m 1G $(QEMU_ARGS_$(XARCH)) $(QEMU_ARGS_BIOS) $(QEMU_ARGS_EXTRA) + +# OUTPUT is only set when run from the main makefile, otherwise +# it defaults to this nolibc directory. +OUTPUT ?= $(CURDIR)/ + +ifeq ($(V),1) +Q= +else +Q=@ +endif + +CFLAGS_i386 = $(call cc-option,-m32) +CFLAGS_x32 = -mx32 +CFLAGS_arm = -marm +CFLAGS_armthumb = -mthumb -march=armv6t2 +CFLAGS_ppc = -m32 -mbig-endian -mno-vsx $(call cc-option,-mmultiple) +CFLAGS_ppc64 = -m64 -mbig-endian -mno-vsx $(call cc-option,-mmultiple) +CFLAGS_ppc64le = -m64 -mlittle-endian -mno-vsx $(call cc-option,-mabi=elfv2) +CFLAGS_s390x = -m64 +CFLAGS_s390 = -m31 +CFLAGS_mips32le = -EL -mabi=32 -fPIC +CFLAGS_mips32be = -EB -mabi=32 +CFLAGS_mipsn32le = -EL -mabi=n32 -fPIC -march=mips64r2 +CFLAGS_mipsn32be = -EB -mabi=n32 -march=mips64r6 +CFLAGS_mips64le = -EL -mabi=64 -march=mips64r6 +CFLAGS_mips64be = -EB -mabi=64 -march=mips64r2 +CFLAGS_sparc32 = $(call cc-option,-m32) +CFLAGS_sh4 = -ml -m4 +ifeq ($(origin XARCH),command line) +CFLAGS_XARCH = $(CFLAGS_$(XARCH)) +endif + +include Makefile.include + +CFLAGS ?= $(CFLAGS_NOLIBC_TEST) $(CFLAGS_XARCH) $(CFLAGS_EXTRA) +LDFLAGS := + +LIBGCC := -lgcc + +ifeq ($(ARCH),x86) +# Not needed on x86, probably not present for x32 +LIBGCC := +endif + +ifneq ($(LLVM),) +# Not needed for clang +LIBGCC := +endif + +# Modify CFLAGS based on LLVM= +include $(srctree)/tools/scripts/Makefile.include + +REPORT ?= awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{if (!f) printf("\n"); f++; print;} /\[SKIPPED\][\r]*$$/{s++} \ + /^Total number of errors:/{done++} \ + END{ printf("\n%3d test(s): %3d passed, %3d skipped, %3d failed => status: ", p+s+f, p, s, f); \ + if (f || !p || !done) printf("failure\n"); else if (s) printf("warning\n"); else printf("success\n");; \ + printf("\nSee all results in %s\n", ARGV[1]); }' + +help: + @echo "Supported targets under selftests/nolibc:" + @echo " all call the \"run\" target below" + @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 \$$XARCH, \$$TEST)" + @echo " initramfs.cpio prepare the initramfs archive with nolibc-test" + @echo " initramfs prepare the initramfs tree with nolibc-test" + @echo " defconfig create a fresh new default config (uses \$$XARCH)" + @echo " kernel (re)build the kernel (uses \$$XARCH)" + @echo " kernel-standalone (re)build the kernel with the initramfs (uses \$$XARCH)" + @echo " run runs the kernel in QEMU after building it (uses \$$XARCH, \$$TEST)" + @echo " rerun runs a previously prebuilt kernel in QEMU (uses \$$XARCH, \$$TEST)" + @echo " clean clean the sysroot, initramfs, build and output files" + @echo "" + @echo "The output file is \"run.out\". Test ranges may be passed using \$$TEST." + @echo "" + @echo "Currently using the following variables:" + @echo " ARCH = $(ARCH)" + @echo " XARCH = $(XARCH)" + @echo " CROSS_COMPILE = $(CROSS_COMPILE)" + @echo " CC = $(CC)" + @echo " OUTPUT = $(OUTPUT)" + @echo " TEST = $(TEST)" + @echo " QEMU_ARCH = $(if $(QEMU_ARCH),$(QEMU_ARCH),UNKNOWN_ARCH) [determined from \$$XARCH]" + @echo " IMAGE_NAME = $(if $(IMAGE_NAME),$(IMAGE_NAME),UNKNOWN_ARCH) [determined from \$$XARCH]" + @echo "" + +all: run + +sysroot: sysroot/$(ARCH)/include + +sysroot/$(ARCH)/include: + $(Q)rm -rf sysroot/$(ARCH) sysroot/sysroot + $(QUIET_MKDIR)mkdir -p sysroot + $(Q)$(MAKE) -C $(srctree) outputmakefile + $(Q)$(MAKE) -C $(srctree)/tools/include/nolibc ARCH=$(ARCH) OUTPUT=$(CURDIR)/sysroot/ headers_standalone headers_check + $(Q)mv sysroot/sysroot sysroot/$(ARCH) + +ifneq ($(NOLIBC_SYSROOT),0) +nolibc-test: nolibc-test.c nolibc-test-linkage.c sysroot/$(ARCH)/include + $(QUIET_CC)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ \ + -nostdlib -nostdinc -static -Isysroot/$(ARCH)/include nolibc-test.c nolibc-test-linkage.c $(LIBGCC) +else +nolibc-test: nolibc-test.c nolibc-test-linkage.c + $(QUIET_CC)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ \ + -nostdlib -static -include $(srctree)/tools/include/nolibc/nolibc.h nolibc-test.c nolibc-test-linkage.c $(LIBGCC) +endif + +libc-test: nolibc-test.c nolibc-test-linkage.c + $(QUIET_CC)$(HOSTCC) -o $@ nolibc-test.c nolibc-test-linkage.c + +# local libc-test +run-libc-test: libc-test + $(Q)./libc-test > "$(CURDIR)/run.out" || : + $(Q)$(REPORT) $(CURDIR)/run.out + +# local nolibc-test +run-nolibc-test: nolibc-test + $(Q)./nolibc-test > "$(CURDIR)/run.out" || : + $(Q)$(REPORT) $(CURDIR)/run.out + +# qemu user-land test +run-user: nolibc-test + $(Q)qemu-$(QEMU_ARCH_USER) ./nolibc-test > "$(CURDIR)/run.out" || : + $(Q)$(REPORT) $(CURDIR)/run.out + +initramfs.cpio: kernel nolibc-test + $(QUIET_GEN)echo 'file /init nolibc-test 755 0 0' | $(objtree)/usr/gen_init_cpio - > initramfs.cpio + +initramfs: nolibc-test + $(QUIET_MKDIR)mkdir -p initramfs + $(call QUIET_INSTALL, initramfs/init) + $(Q)cp nolibc-test initramfs/init + +defconfig: + $(Q)$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) $(DEFCONFIG) + $(Q)if [ -n "$(EXTRACONFIG)" ]; then \ + $(srctree)/scripts/config --file $(objtree)/.config $(EXTRACONFIG); \ + $(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) olddefconfig < /dev/null; \ + fi + +kernel: + $(Q)$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) $(IMAGE_NAME) < /dev/null + +kernel-standalone: initramfs + $(Q)$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) $(IMAGE_NAME) CONFIG_INITRAMFS_SOURCE=$(CURDIR)/initramfs < /dev/null + +# run the tests after building the kernel +run: kernel initramfs.cpio + $(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(IMAGE)" -initrd initramfs.cpio -serial file:/dev/stdout $(QEMU_ARGS) > "$(CURDIR)/run.out" + $(Q)$(REPORT) $(CURDIR)/run.out + +# re-run the tests from an existing kernel +rerun: + $(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(IMAGE)" -initrd initramfs.cpio -serial file:/dev/stdout $(QEMU_ARGS) > "$(CURDIR)/run.out" + $(Q)$(REPORT) $(CURDIR)/run.out + +# report with existing test log +report: + $(Q)$(REPORT) $(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.cpio) + $(Q)rm -rf initramfs.cpio + $(call QUIET_CLEAN, initramfs) + $(Q)rm -rf initramfs + $(call QUIET_CLEAN, run.out) + $(Q)rm -rf run.out + +.PHONY: sysroot/$(ARCH)/include diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index dbe13000fb1a..a297ee0d6d07 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -877,7 +877,12 @@ int test_file_stream(void) return 0; } -int test_fork(void) +enum fork_type { + FORK_STANDARD, + FORK_VFORK, +}; + +int test_fork(enum fork_type type) { int status; pid_t pid; @@ -886,14 +891,23 @@ int test_fork(void) fflush(stdout); fflush(stderr); - pid = fork(); + switch (type) { + case FORK_STANDARD: + pid = fork(); + break; + case FORK_VFORK: + pid = vfork(); + break; + default: + return 1; + } switch (pid) { case -1: return 1; case 0: - exit(123); + _exit(123); default: pid = waitpid(pid, &status, 0); @@ -1330,7 +1344,7 @@ int run_syscall(int min, int max) 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(file_stream); EXPECT_SYSZR(1, test_file_stream()); break; - CASE_TEST(fork); EXPECT_SYSZR(1, test_fork()); break; + CASE_TEST(fork); EXPECT_SYSZR(1, test_fork(FORK_STANDARD)); 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(directories); EXPECT_SYSZR(proc, test_dirent()); break; @@ -1349,6 +1363,7 @@ int run_syscall(int min, int max) CASE_TEST(mmap_bad); EXPECT_PTRER(1, mmap(NULL, 0, PROT_READ, MAP_PRIVATE, 0, 0), MAP_FAILED, EINVAL); break; CASE_TEST(munmap_bad); EXPECT_SYSER(1, munmap(NULL, 0), -1, EINVAL); break; CASE_TEST(mmap_munmap_good); EXPECT_SYSZR(1, test_mmap_munmap()); break; + CASE_TEST(nanosleep); ts.tv_nsec = -1; EXPECT_SYSER(1, nanosleep(&ts, NULL), -1, EINVAL); break; CASE_TEST(open_tty); EXPECT_SYSNE(1, tmp = open("/dev/null", O_RDONLY), -1); if (tmp != -1) close(tmp); break; CASE_TEST(open_blah); EXPECT_SYSER(1, tmp = open("/proc/self/blah", O_RDONLY), -1, ENOENT); if (tmp != -1) close(tmp); break; CASE_TEST(openat_dir); EXPECT_SYSZR(1, test_openat()); break; @@ -1374,6 +1389,7 @@ int run_syscall(int min, int max) CASE_TEST(uname_fault); EXPECT_SYSER(1, uname(NULL), -1, EFAULT); 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; + CASE_TEST(vfork); EXPECT_SYSZR(1, test_fork(FORK_VFORK)); break; CASE_TEST(wait_child); EXPECT_SYSER(1, wait(&tmp), -1, ECHILD); break; CASE_TEST(waitpid_min); EXPECT_SYSER(1, waitpid(INT_MIN, &tmp, WNOHANG), -1, ESRCH); break; CASE_TEST(waitpid_child); EXPECT_SYSER(1, waitpid(getpid(), &tmp, WNOHANG), -1, ECHILD); break; @@ -1413,7 +1429,7 @@ int run_stdlib(int min, int max) * Add some more chars after the \0, to test functions that overwrite the buffer set * the \0 at the exact right position. */ - char buf[10] = "test123456"; + char buf[11] = "test123456"; buf[4] = '\0'; @@ -1646,6 +1662,28 @@ int test_strerror(void) return 0; } +static int test_printf_error(void) +{ + int fd, ret, saved_errno; + + fd = open("/dev/full", O_RDWR); + if (fd == -1) + return 1; + + errno = 0; + ret = dprintf(fd, "foo"); + saved_errno = errno; + close(fd); + + if (ret != -1) + return 2; + + if (saved_errno != ENOSPC) + return 3; + + return 0; +} + static int run_printf(int min, int max) { int test; @@ -1675,6 +1713,7 @@ static int run_printf(int min, int max) CASE_TEST(width_trunc); EXPECT_VFPRINTF(25, " ", "%25d", 1); break; CASE_TEST(scanf); EXPECT_ZR(1, test_scanf()); break; CASE_TEST(strerror); EXPECT_ZR(1, test_strerror()); break; + CASE_TEST(printf_error); EXPECT_ZR(1, test_printf_error()); break; case __LINE__: return ret; /* must be last */ /* note: do not set any defaults so as to permit holes above */ @@ -1762,12 +1801,14 @@ int prepare(void) if (stat("/dev/.", &stat_buf) == 0 || mkdir("/dev", 0755) == 0) { if (stat("/dev/console", &stat_buf) != 0 || stat("/dev/null", &stat_buf) != 0 || - stat("/dev/zero", &stat_buf) != 0) { + stat("/dev/zero", &stat_buf) != 0 || + stat("/dev/full", &stat_buf) != 0) { /* try devtmpfs first, otherwise fall back to manual creation */ if (mount("/dev", "/dev", "devtmpfs", 0, 0) != 0) { mknod("/dev/console", 0600 | S_IFCHR, makedev(5, 1)); mknod("/dev/null", 0666 | S_IFCHR, makedev(1, 3)); mknod("/dev/zero", 0666 | S_IFCHR, makedev(1, 5)); + mknod("/dev/full", 0666 | S_IFCHR, makedev(1, 7)); } } } diff --git a/tools/testing/selftests/nolibc/run-tests.sh b/tools/testing/selftests/nolibc/run-tests.sh index 8277599e6441..e8af1fb505cf 100755 --- a/tools/testing/selftests/nolibc/run-tests.sh +++ b/tools/testing/selftests/nolibc/run-tests.sh @@ -18,15 +18,16 @@ test_mode=system werror=1 llvm= all_archs=( - i386 x86_64 + i386 x86_64 x32 arm64 arm armthumb - mips32le mips32be + mips32le mips32be mipsn32le mipsn32be mips64le mips64be ppc ppc64 ppc64le riscv32 riscv64 s390x s390 loongarch sparc32 sparc64 m68k + sh4 ) archs="${all_archs[@]}" @@ -114,6 +115,7 @@ crosstool_arch() { mips*) echo mips;; s390*) echo s390;; sparc*) echo sparc64;; + x32*) echo x86_64;; *) echo "$1";; esac } @@ -169,7 +171,7 @@ test_arch() { if [ "$werror" -ne 0 ]; then CFLAGS_EXTRA="$CFLAGS_EXTRA -Werror" fi - MAKE=(make -j"${nproc}" XARCH="${arch}" CROSS_COMPILE="${cross_compile}" LLVM="${llvm}" O="${build_dir}") + MAKE=(make -f Makefile.nolibc -j"${nproc}" XARCH="${arch}" CROSS_COMPILE="${cross_compile}" LLVM="${llvm}" O="${build_dir}") case "$test_mode" in 'system') @@ -187,7 +189,11 @@ test_arch() { echo "Unsupported configuration" return fi - if [ "$arch" = "m68k" ] && [ "$llvm" = "1" ]; then + if [ "$arch" = "m68k" -o "$arch" = "sh4" ] && [ "$llvm" = "1" ]; then + echo "Unsupported configuration" + return + fi + if [ "$arch" = "x32" ] && [ "$test_mode" = "user" ]; then echo "Unsupported configuration" return fi diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore index 0406a065deb4..144e7ff65d6a 100644 --- a/tools/testing/selftests/pidfd/.gitignore +++ b/tools/testing/selftests/pidfd/.gitignore @@ -10,3 +10,5 @@ pidfd_file_handle_test pidfd_bind_mount pidfd_info_test pidfd_exec_helper +pidfd_xattr_test +pidfd_setattr_test diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile index fcbefc0d77f6..764a8f9ecefa 100644 --- a/tools/testing/selftests/pidfd/Makefile +++ b/tools/testing/selftests/pidfd/Makefile @@ -1,9 +1,10 @@ # SPDX-License-Identifier: GPL-2.0-only -CFLAGS += -g $(KHDR_INCLUDES) -pthread -Wall +CFLAGS += -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES) -pthread -Wall TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test \ pidfd_poll_test pidfd_wait pidfd_getfd_test pidfd_setns_test \ - pidfd_file_handle_test pidfd_bind_mount pidfd_info_test + pidfd_file_handle_test pidfd_bind_mount pidfd_info_test \ + pidfd_xattr_test pidfd_setattr_test TEST_GEN_PROGS_EXTENDED := pidfd_exec_helper diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index efd74063126e..f87993def738 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -16,9 +16,22 @@ #include <sys/types.h> #include <sys/wait.h> +/* + * Remove the userspace definitions of the following preprocessor symbols + * to avoid duplicate-definition warnings from the subsequent in-kernel + * definitions. + */ +#undef SCHED_NORMAL +#undef SCHED_FLAG_KEEP_ALL +#undef SCHED_FLAG_UTIL_CLAMP + #include "../kselftest.h" #include "../clone3/clone3_selftests.h" +#ifndef FD_PIDFS_ROOT +#define FD_PIDFS_ROOT -10002 +#endif + #ifndef P_PIDFD #define P_PIDFD 3 #endif @@ -56,7 +69,7 @@ #endif #ifndef PIDFD_SELF_THREAD_GROUP -#define PIDFD_SELF_THREAD_GROUP -20000 /* Current thread group leader. */ +#define PIDFD_SELF_THREAD_GROUP -10001 /* Current thread group leader. */ #endif #ifndef PIDFD_SELF diff --git a/tools/testing/selftests/pidfd/pidfd_file_handle_test.c b/tools/testing/selftests/pidfd/pidfd_file_handle_test.c index 439b9c6c0457..6bd2e9c9565b 100644 --- a/tools/testing/selftests/pidfd/pidfd_file_handle_test.c +++ b/tools/testing/selftests/pidfd/pidfd_file_handle_test.c @@ -500,4 +500,64 @@ TEST_F(file_handle, valid_name_to_handle_at_flags) ASSERT_EQ(close(pidfd), 0); } +/* + * That we decode a file handle without having to pass a pidfd. + */ +TEST_F(file_handle, decode_purely_based_on_file_handle) +{ + int mnt_id; + struct file_handle *fh; + int pidfd = -EBADF; + struct stat st1, st2; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->child_pidfd1, "", fh, &mnt_id, AT_EMPTY_PATH), 0); + + ASSERT_EQ(fstat(self->child_pidfd1, &st1), 0); + + pidfd = open_by_handle_at(FD_PIDFS_ROOT, fh, 0); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + pidfd = open_by_handle_at(FD_PIDFS_ROOT, fh, O_CLOEXEC); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + pidfd = open_by_handle_at(FD_PIDFS_ROOT, fh, O_NONBLOCK); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, 0); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + pidfd = open_by_handle_at(-EBADF, fh, 0); + ASSERT_LT(pidfd, 0); + + pidfd = open_by_handle_at(AT_FDCWD, fh, 0); + ASSERT_LT(pidfd, 0); + + free(fh); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/pidfd/pidfd_setattr_test.c b/tools/testing/selftests/pidfd/pidfd_setattr_test.c new file mode 100644 index 000000000000..d7de05edc4b3 --- /dev/null +++ b/tools/testing/selftests/pidfd/pidfd_setattr_test.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <limits.h> +#include <linux/types.h> +#include <poll.h> +#include <pthread.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <sys/prctl.h> +#include <sys/wait.h> +#include <unistd.h> +#include <sys/socket.h> +#include <linux/kcmp.h> +#include <sys/stat.h> +#include <sys/xattr.h> + +#include "pidfd.h" +#include "../kselftest_harness.h" + +FIXTURE(pidfs_setattr) +{ + pid_t child_pid; + int child_pidfd; +}; + +FIXTURE_SETUP(pidfs_setattr) +{ + self->child_pid = create_child(&self->child_pidfd, CLONE_NEWUSER | CLONE_NEWPID); + EXPECT_GE(self->child_pid, 0); + + if (self->child_pid == 0) + _exit(EXIT_SUCCESS); +} + +FIXTURE_TEARDOWN(pidfs_setattr) +{ + sys_waitid(P_PID, self->child_pid, NULL, WEXITED); + EXPECT_EQ(close(self->child_pidfd), 0); +} + +TEST_F(pidfs_setattr, no_chown) +{ + ASSERT_LT(fchown(self->child_pidfd, 1234, 5678), 0); + ASSERT_EQ(errno, EOPNOTSUPP); +} + +TEST_F(pidfs_setattr, no_chmod) +{ + ASSERT_LT(fchmod(self->child_pidfd, 0777), 0); + ASSERT_EQ(errno, EOPNOTSUPP); +} + +TEST_F(pidfs_setattr, no_exec) +{ + char *const argv[] = { NULL }; + char *const envp[] = { NULL }; + + ASSERT_LT(execveat(self->child_pidfd, "", argv, envp, AT_EMPTY_PATH), 0); + ASSERT_EQ(errno, EACCES); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/pidfd/pidfd_xattr_test.c b/tools/testing/selftests/pidfd/pidfd_xattr_test.c new file mode 100644 index 000000000000..5cf7bb0e4bf2 --- /dev/null +++ b/tools/testing/selftests/pidfd/pidfd_xattr_test.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <limits.h> +#include <linux/types.h> +#include <poll.h> +#include <pthread.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <sys/prctl.h> +#include <sys/wait.h> +#include <unistd.h> +#include <sys/socket.h> +#include <linux/kcmp.h> +#include <sys/stat.h> +#include <sys/xattr.h> + +#include "pidfd.h" +#include "../kselftest_harness.h" + +FIXTURE(pidfs_xattr) +{ + pid_t child_pid; + int child_pidfd; +}; + +FIXTURE_SETUP(pidfs_xattr) +{ + self->child_pid = create_child(&self->child_pidfd, CLONE_NEWUSER | CLONE_NEWPID); + EXPECT_GE(self->child_pid, 0); + + if (self->child_pid == 0) + _exit(EXIT_SUCCESS); +} + +FIXTURE_TEARDOWN(pidfs_xattr) +{ + sys_waitid(P_PID, self->child_pid, NULL, WEXITED); +} + +TEST_F(pidfs_xattr, set_get_list_xattr_multiple) +{ + int ret, i; + char xattr_name[32]; + char xattr_value[32]; + char buf[32]; + const int num_xattrs = 10; + char list[PATH_MAX] = {}; + + for (i = 0; i < num_xattrs; i++) { + snprintf(xattr_name, sizeof(xattr_name), "trusted.testattr%d", i); + snprintf(xattr_value, sizeof(xattr_value), "testvalue%d", i); + ret = fsetxattr(self->child_pidfd, xattr_name, xattr_value, strlen(xattr_value), 0); + ASSERT_EQ(ret, 0); + } + + for (i = 0; i < num_xattrs; i++) { + snprintf(xattr_name, sizeof(xattr_name), "trusted.testattr%d", i); + snprintf(xattr_value, sizeof(xattr_value), "testvalue%d", i); + memset(buf, 0, sizeof(buf)); + ret = fgetxattr(self->child_pidfd, xattr_name, buf, sizeof(buf)); + ASSERT_EQ(ret, strlen(xattr_value)); + ASSERT_EQ(strcmp(buf, xattr_value), 0); + } + + ret = flistxattr(self->child_pidfd, list, sizeof(list)); + ASSERT_GT(ret, 0); + for (i = 0; i < num_xattrs; i++) { + snprintf(xattr_name, sizeof(xattr_name), "trusted.testattr%d", i); + bool found = false; + for (char *it = list; it < list + ret; it += strlen(it) + 1) { + if (strcmp(it, xattr_name)) + continue; + found = true; + break; + } + ASSERT_TRUE(found); + } + + for (i = 0; i < num_xattrs; i++) { + snprintf(xattr_name, sizeof(xattr_name), "trusted.testattr%d", i); + ret = fremovexattr(self->child_pidfd, xattr_name); + ASSERT_EQ(ret, 0); + + ret = fgetxattr(self->child_pidfd, xattr_name, buf, sizeof(buf)); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ENODATA); + } +} + +TEST_F(pidfs_xattr, set_get_list_xattr_persistent) +{ + int ret; + char buf[32]; + char list[PATH_MAX] = {}; + + ret = fsetxattr(self->child_pidfd, "trusted.persistent", "persistent value", strlen("persistent value"), 0); + ASSERT_EQ(ret, 0); + + memset(buf, 0, sizeof(buf)); + ret = fgetxattr(self->child_pidfd, "trusted.persistent", buf, sizeof(buf)); + ASSERT_EQ(ret, strlen("persistent value")); + ASSERT_EQ(strcmp(buf, "persistent value"), 0); + + ret = flistxattr(self->child_pidfd, list, sizeof(list)); + ASSERT_GT(ret, 0); + ASSERT_EQ(strcmp(list, "trusted.persistent"), 0) + + ASSERT_EQ(close(self->child_pidfd), 0); + self->child_pidfd = -EBADF; + sleep(2); + + self->child_pidfd = sys_pidfd_open(self->child_pid, 0); + ASSERT_GE(self->child_pidfd, 0); + + memset(buf, 0, sizeof(buf)); + ret = fgetxattr(self->child_pidfd, "trusted.persistent", buf, sizeof(buf)); + ASSERT_EQ(ret, strlen("persistent value")); + ASSERT_EQ(strcmp(buf, "persistent value"), 0); + + ret = flistxattr(self->child_pidfd, list, sizeof(list)); + ASSERT_GT(ret, 0); + ASSERT_EQ(strcmp(list, "trusted.persistent"), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index edc08a4433fd..ed1e2886ba3c 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -120,6 +120,7 @@ static void usage(char *progname) " -c query the ptp clock's capabilities\n" " -d name device to open\n" " -e val read 'val' external time stamp events\n" + " -E val enable rising (1), falling (2), or both (3) edges\n" " -f val adjust the ptp clock frequency by 'val' ppb\n" " -F chan Enable single channel mask and keep device open for debugfs verification.\n" " -g get the ptp clock time\n" @@ -178,6 +179,7 @@ int main(int argc, char *argv[]) int adjphase = 0; int capabilities = 0; int extts = 0; + int edge = 0; int flagtest = 0; int gettime = 0; int index = 0; @@ -202,7 +204,7 @@ 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:F:ghH:i:k:lL:n:o:p:P:rsSt:T:w:x:Xy:z"))) { + while (EOF != (c = getopt(argc, argv, "cd:e:E:f:F:ghH:i:k:lL:n:o:p:P:rsSt:T:w:x:Xy:z"))) { switch (c) { case 'c': capabilities = 1; @@ -213,6 +215,11 @@ int main(int argc, char *argv[]) case 'e': extts = atoi(optarg); break; + case 'E': + edge = atoi(optarg); + edge = (edge & 1 ? PTP_RISING_EDGE : 0) | + (edge & 2 ? PTP_FALLING_EDGE : 0); + break; case 'f': adjfreq = atoi(optarg); break; @@ -444,7 +451,7 @@ int main(int argc, char *argv[]) if (!readonly) { memset(&extts_request, 0, sizeof(extts_request)); extts_request.index = index; - extts_request.flags = PTP_ENABLE_FEATURE; + extts_request.flags = PTP_ENABLE_FEATURE | edge; if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) { perror("PTP_EXTTS_REQUEST"); extts = 0; diff --git a/tools/testing/selftests/ptrace/peeksiginfo.c b/tools/testing/selftests/ptrace/peeksiginfo.c index a6884f66dc01..2f345d11e4b8 100644 --- a/tools/testing/selftests/ptrace/peeksiginfo.c +++ b/tools/testing/selftests/ptrace/peeksiginfo.c @@ -199,7 +199,7 @@ int main(int argc, char *argv[]) /* * Dump signal from the process-wide queue. - * The number of signals is not multible to the buffer size + * The number of signals is not multiple to the buffer size */ if (check_direct_path(child, 1, 3)) goto out; diff --git a/tools/testing/selftests/sched_ext/exit.c b/tools/testing/selftests/sched_ext/exit.c index 9451782689de..ee25824b1cbe 100644 --- a/tools/testing/selftests/sched_ext/exit.c +++ b/tools/testing/selftests/sched_ext/exit.c @@ -22,6 +22,14 @@ static enum scx_test_status run(void *ctx) struct bpf_link *link; char buf[16]; + /* + * On single-CPU systems, ops.select_cpu() is never + * invoked, so skip this test to avoid getting stuck + * indefinitely. + */ + if (tc == EXIT_SELECT_CPU && libbpf_num_possible_cpus() == 1) + continue; + skel = exit__open(); SCX_ENUM_INIT(skel); skel->rodata->exit_point = tc; diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_test.c b/tools/testing/selftests/syscall_user_dispatch/sud_test.c index d975a6767329..2eb2c06303f2 100644 --- a/tools/testing/selftests/syscall_user_dispatch/sud_test.c +++ b/tools/testing/selftests/syscall_user_dispatch/sud_test.c @@ -10,6 +10,8 @@ #include <sys/sysinfo.h> #include <sys/syscall.h> #include <signal.h> +#include <stdbool.h> +#include <stdlib.h> #include <asm/unistd.h> #include "../kselftest_harness.h" @@ -17,11 +19,15 @@ #ifndef PR_SET_SYSCALL_USER_DISPATCH # define PR_SET_SYSCALL_USER_DISPATCH 59 # define PR_SYS_DISPATCH_OFF 0 -# define PR_SYS_DISPATCH_ON 1 # define SYSCALL_DISPATCH_FILTER_ALLOW 0 # define SYSCALL_DISPATCH_FILTER_BLOCK 1 #endif +#ifndef PR_SYS_DISPATCH_EXCLUSIVE_ON +# define PR_SYS_DISPATCH_EXCLUSIVE_ON 1 +# define PR_SYS_DISPATCH_INCLUSIVE_ON 2 +#endif + #ifndef SYS_USER_DISPATCH # define SYS_USER_DISPATCH 2 #endif @@ -65,7 +71,7 @@ TEST_SIGNAL(dispatch_trigger_sigsys, SIGSYS) ret = sysinfo(&info); ASSERT_EQ(0, ret); - ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 0, 0, &sel); + ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_EXCLUSIVE_ON, 0, 0, &sel); ASSERT_EQ(0, ret) { TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH"); } @@ -79,6 +85,21 @@ TEST_SIGNAL(dispatch_trigger_sigsys, SIGSYS) } } +static void prctl_valid(struct __test_metadata *_metadata, + unsigned long op, unsigned long off, + unsigned long size, void *sel) +{ + EXPECT_EQ(0, prctl(PR_SET_SYSCALL_USER_DISPATCH, op, off, size, sel)); +} + +static void prctl_invalid(struct __test_metadata *_metadata, + unsigned long op, unsigned long off, + unsigned long size, void *sel, int err) +{ + EXPECT_EQ(-1, prctl(PR_SET_SYSCALL_USER_DISPATCH, op, off, size, sel)); + EXPECT_EQ(err, errno); +} + TEST(bad_prctl_param) { char sel = SYSCALL_DISPATCH_FILTER_ALLOW; @@ -86,57 +107,54 @@ TEST(bad_prctl_param) /* Invalid op */ op = -1; - prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0, 0, &sel); - ASSERT_EQ(EINVAL, errno); + prctl_invalid(_metadata, op, 0, 0, &sel, EINVAL); /* PR_SYS_DISPATCH_OFF */ op = PR_SYS_DISPATCH_OFF; /* offset != 0 */ - prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x1, 0x0, 0); - EXPECT_EQ(EINVAL, errno); + prctl_invalid(_metadata, op, 0x1, 0x0, 0, EINVAL); /* len != 0 */ - prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x0, 0xff, 0); - EXPECT_EQ(EINVAL, errno); + prctl_invalid(_metadata, op, 0x0, 0xff, 0, EINVAL); /* sel != NULL */ - prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x0, 0x0, &sel); - EXPECT_EQ(EINVAL, errno); + prctl_invalid(_metadata, op, 0x0, 0x0, &sel, EINVAL); /* Valid parameter */ - errno = 0; - prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x0, 0x0, 0x0); - EXPECT_EQ(0, errno); + prctl_valid(_metadata, op, 0x0, 0x0, 0x0); - /* PR_SYS_DISPATCH_ON */ - op = PR_SYS_DISPATCH_ON; + /* PR_SYS_DISPATCH_EXCLUSIVE_ON */ + op = PR_SYS_DISPATCH_EXCLUSIVE_ON; /* Dispatcher region is bad (offset > 0 && len == 0) */ - prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x1, 0x0, &sel); - EXPECT_EQ(EINVAL, errno); - prctl(PR_SET_SYSCALL_USER_DISPATCH, op, -1L, 0x0, &sel); - EXPECT_EQ(EINVAL, errno); + prctl_invalid(_metadata, op, 0x1, 0x0, &sel, EINVAL); + prctl_invalid(_metadata, op, -1L, 0x0, &sel, EINVAL); /* Invalid selector */ - prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x0, 0x1, (void *) -1); - ASSERT_EQ(EFAULT, errno); + prctl_invalid(_metadata, op, 0x0, 0x1, (void *) -1, EFAULT); /* * Dispatcher range overflows unsigned long */ - prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 1, -1L, &sel); - ASSERT_EQ(EINVAL, errno) { - TH_LOG("Should reject bad syscall range"); - } + prctl_invalid(_metadata, PR_SYS_DISPATCH_EXCLUSIVE_ON, 1, -1L, &sel, EINVAL); /* * Allowed range overflows usigned long */ - prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, -1L, 0x1, &sel); - ASSERT_EQ(EINVAL, errno) { - TH_LOG("Should reject bad syscall range"); - } + prctl_invalid(_metadata, PR_SYS_DISPATCH_EXCLUSIVE_ON, -1L, 0x1, &sel, EINVAL); + + /* 0 len should fail for PR_SYS_DISPATCH_INCLUSIVE_ON */ + prctl_invalid(_metadata, PR_SYS_DISPATCH_INCLUSIVE_ON, 1, 0, 0, EINVAL); + + /* Range wrap-around should fail */ + prctl_invalid(_metadata, PR_SYS_DISPATCH_INCLUSIVE_ON, -1L, 2, 0, EINVAL); + + /* Normal range shouldn't fail */ + prctl_valid(_metadata, PR_SYS_DISPATCH_INCLUSIVE_ON, 2, 3, 0); + + /* Invalid selector */ + prctl_invalid(_metadata, PR_SYS_DISPATCH_INCLUSIVE_ON, 2, 3, (void *) -1, EFAULT); } /* @@ -147,11 +165,13 @@ char glob_sel; int nr_syscalls_emulated; int si_code; int si_errno; +unsigned long syscall_addr; static void handle_sigsys(int sig, siginfo_t *info, void *ucontext) { si_code = info->si_code; si_errno = info->si_errno; + syscall_addr = (unsigned long)info->si_call_addr; if (info->si_syscall == MAGIC_SYSCALL_1) nr_syscalls_emulated++; @@ -174,31 +194,34 @@ static void handle_sigsys(int sig, siginfo_t *info, void *ucontext) #endif } -TEST(dispatch_and_return) +int setup_sigsys_handler(void) { - long ret; struct sigaction act; sigset_t mask; - glob_sel = 0; - nr_syscalls_emulated = 0; - si_code = 0; - si_errno = 0; - memset(&act, 0, sizeof(act)); sigemptyset(&mask); - act.sa_sigaction = handle_sigsys; act.sa_flags = SA_SIGINFO; act.sa_mask = mask; + return sigaction(SIGSYS, &act, NULL); +} - ret = sigaction(SIGSYS, &act, NULL); - ASSERT_EQ(0, ret); +TEST(dispatch_and_return) +{ + long ret; + + glob_sel = 0; + nr_syscalls_emulated = 0; + si_code = 0; + si_errno = 0; + + ASSERT_EQ(0, setup_sigsys_handler()); /* Make sure selector is good prior to prctl. */ SYSCALL_DISPATCH_OFF(glob_sel); - ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 0, 0, &glob_sel); + ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_EXCLUSIVE_ON, 0, 0, &glob_sel); ASSERT_EQ(0, ret) { TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH"); } @@ -254,7 +277,7 @@ TEST_SIGNAL(bad_selector, SIGSYS) /* Make sure selector is good prior to prctl. */ SYSCALL_DISPATCH_OFF(glob_sel); - ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 0, 0, &glob_sel); + ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_EXCLUSIVE_ON, 0, 0, &glob_sel); ASSERT_EQ(0, ret) { TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH"); } @@ -278,7 +301,7 @@ TEST(disable_dispatch) struct sysinfo info; char sel = 0; - ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 0, 0, &sel); + ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_EXCLUSIVE_ON, 0, 0, &sel); ASSERT_EQ(0, ret) { TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH"); } @@ -310,7 +333,7 @@ TEST(direct_dispatch_range) * Instead of calculating libc addresses; allow the entire * memory map and lock the selector. */ - ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 0, -1L, &sel); + ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_EXCLUSIVE_ON, 0, -1L, &sel); ASSERT_EQ(0, ret) { TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH"); } @@ -323,4 +346,35 @@ TEST(direct_dispatch_range) } } +static void test_range(struct __test_metadata *_metadata, + unsigned long op, unsigned long off, + unsigned long size, bool dispatch) +{ + nr_syscalls_emulated = 0; + SYSCALL_DISPATCH_OFF(glob_sel); + EXPECT_EQ(0, prctl(PR_SET_SYSCALL_USER_DISPATCH, op, off, size, &glob_sel)); + SYSCALL_DISPATCH_ON(glob_sel); + if (dispatch) { + EXPECT_EQ(syscall(MAGIC_SYSCALL_1), MAGIC_SYSCALL_1); + EXPECT_EQ(nr_syscalls_emulated, 1); + } else { + EXPECT_EQ(syscall(MAGIC_SYSCALL_1), -1); + EXPECT_EQ(nr_syscalls_emulated, 0); + } +} + +TEST(dispatch_range) +{ + ASSERT_EQ(0, setup_sigsys_handler()); + test_range(_metadata, PR_SYS_DISPATCH_EXCLUSIVE_ON, 0, 0, true); + test_range(_metadata, PR_SYS_DISPATCH_EXCLUSIVE_ON, syscall_addr, 1, false); + test_range(_metadata, PR_SYS_DISPATCH_EXCLUSIVE_ON, syscall_addr-100, 200, false); + test_range(_metadata, PR_SYS_DISPATCH_EXCLUSIVE_ON, syscall_addr+1, 100, true); + test_range(_metadata, PR_SYS_DISPATCH_EXCLUSIVE_ON, syscall_addr-100, 100, true); + test_range(_metadata, PR_SYS_DISPATCH_INCLUSIVE_ON, syscall_addr, 1, true); + test_range(_metadata, PR_SYS_DISPATCH_INCLUSIVE_ON, syscall_addr-1, 1, false); + test_range(_metadata, PR_SYS_DISPATCH_INCLUSIVE_ON, syscall_addr+1, 1, false); + SYSCALL_DISPATCH_OFF(glob_sel); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh index a10350c8a46e..b2d8bd9026a7 100755 --- a/tools/testing/selftests/sysctl/sysctl.sh +++ b/tools/testing/selftests/sysctl/sysctl.sh @@ -1,4 +1,4 @@ -#!/bin/bash +#!/usr/bin/env bash # SPDX-License-Identifier: GPL-2.0-or-later OR copyleft-next-0.3.1 # Copyright (C) 2017 Luis R. Rodriguez <[email protected]> diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index db176fe7d0c3..c20aa16b1d63 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -21,6 +21,7 @@ CONFIG_NF_NAT=m CONFIG_NETFILTER_XT_TARGET_LOG=m CONFIG_NET_SCHED=y +CONFIG_IP_SET=m # # Queueing/Scheduling @@ -30,6 +31,7 @@ CONFIG_NET_SCH_CBS=m CONFIG_NET_SCH_CHOKE=m CONFIG_NET_SCH_CODEL=m CONFIG_NET_SCH_DRR=m +CONFIG_NET_SCH_DUALPI2=m CONFIG_NET_SCH_ETF=m CONFIG_NET_SCH_FQ=m CONFIG_NET_SCH_FQ_CODEL=m diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index c6db7fa94f55..23a61e5b99d0 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -504,7 +504,6 @@ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%", "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip dst 10.10.10.1/32 flowid 1:1", "$TC class add dev $DUMMY parent 1:0 classid 1:2 hfsc ls m2 10Mbit", - "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 netem duplicate 100%", "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 2 u32 match ip dst 10.10.10.2/32 flowid 1:2", "ping -c 1 10.10.10.1 -I$DUMMY > /dev/null || true", "$TC filter del dev $DUMMY parent 1:0 protocol ip prio 1", @@ -517,8 +516,8 @@ { "kind": "hfsc", "handle": "1:", - "bytes": 392, - "packets": 4 + "bytes": 294, + "packets": 3 } ], "matchCount": "1", diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json new file mode 100644 index 000000000000..cd1f2ee8f354 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json @@ -0,0 +1,254 @@ +[ + { + "id": "a4c7", + "name": "Create DualPI2 with default setting", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* step_thresh 1ms min_qlen_step 0p coupling_factor 2 drop_on_overload drop_dequeue classic_protection 10% l4s_ect split_gso", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "1ea4", + "name": "Create DualPI2 with memlimit", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 memlimit 20000000", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* memlimit 20000000B", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "2130", + "name": "Create DualPI2 with typical_rtt and max_rtt", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 typical_rtt 20ms max_rtt 200ms", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* target 20ms tupdate 20ms alpha 0.042969 beta 1.496094", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "90c1", + "name": "Create DualPI2 with max_rtt", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 max_rtt 300ms", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* target 50ms tupdate 50ms alpha 0.050781 beta 0.996094", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "7b3c", + "name": "Create DualPI2 with any_ect option", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 any_ect", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* any_ect", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "49a3", + "name": "Create DualPI2 with overflow option", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 overflow", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* overflow", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "d0a1", + "name": "Create DualPI2 with drop_enqueue option", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 drop_enqueue", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* drop_enqueue", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "f051", + "name": "Create DualPI2 with no_split_gso option", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 no_split_gso", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* no_split_gso", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "456b", + "name": "Create DualPI2 with packet step_thresh", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 step_thresh 3p", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* step_thresh 3p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "610c", + "name": "Create DualPI2 with packet min_qlen_step", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 min_qlen_step 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* min_qlen_step 1p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "b4fa", + "name": "Create DualPI2 with packet coupling_factor", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 coupling_factor 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* coupling_factor 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "37f1", + "name": "Create DualPI2 with packet classic_protection", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 classic_protection 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* classic_protection 0%", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/netem.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/netem.json index 3c4444961488..718d2df2aafa 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/netem.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/netem.json @@ -336,5 +336,86 @@ "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root" ] + }, + { + "id": "d34d", + "name": "NETEM test qdisc duplication restriction in qdisc tree in netem_change root", + "category": ["qdisc", "netem"], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle 1: netem limit 1", + "$TC qdisc add dev $DUMMY parent 1: handle 2: netem limit 1" + ], + "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 1: netem duplicate 50%", + "expExitCode": "2", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "qdisc netem", + "matchCount": "2", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1:0 root" + ] + }, + { + "id": "b33f", + "name": "NETEM test qdisc duplication restriction in qdisc tree in netem_change non-root", + "category": ["qdisc", "netem"], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle 1: netem limit 1", + "$TC qdisc add dev $DUMMY parent 1: handle 2: netem limit 1" + ], + "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 2: netem duplicate 50%", + "expExitCode": "2", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "qdisc netem", + "matchCount": "2", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1:0 root" + ] + }, + { + "id": "cafe", + "name": "NETEM test qdisc duplication restriction in qdisc tree", + "category": ["qdisc", "netem"], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle 1: netem limit 1 duplicate 100%" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent 1: handle 2: netem duplicate 100%", + "expExitCode": "2", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "qdisc netem", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1:0 root" + ] + }, + { + "id": "1337", + "name": "NETEM test qdisc duplication restriction in qdisc tree across branches", + "category": ["qdisc", "netem"], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY parent root handle 1:0 hfsc", + "$TC class add dev $DUMMY parent 1:0 classid 1:1 hfsc rt m2 10Mbit", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem", + "$TC class add dev $DUMMY parent 1:0 classid 1:2 hfsc rt m2 10Mbit" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 netem duplicate 100%", + "expExitCode": "2", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "qdisc netem", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1:0 root" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json index 28c6ce6da7db..531a2f6e4900 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json @@ -264,5 +264,41 @@ "matchPattern": "sfq", "matchCount": "0", "teardown": [] + }, + { + "id": "cdc1", + "name": "Check that a negative perturb timer is rejected", + "category": [ + "qdisc", + "sfq" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq perturb -10", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "sfq", + "matchCount": "0", + "teardown": [] + }, + { + "id": "a9f0", + "name": "Check that a too big perturb timer is rejected", + "category": [ + "qdisc", + "sfq" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq perturb 1000000000", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "sfq", + "matchCount": "0", + "teardown": [] } ] diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh index 589b18ed758a..dae19687912d 100755 --- a/tools/testing/selftests/tc-testing/tdc.sh +++ b/tools/testing/selftests/tc-testing/tdc.sh @@ -4,8 +4,7 @@ # If a module is required and was not compiled # the test that requires it will fail anyways try_modprobe() { - modprobe -q -R "$1" - if [ $? -ne 0 ]; then + if ! modprobe -q -R "$1"; then echo "Module $1 not found... skipping." else modprobe "$1" @@ -67,4 +66,5 @@ try_modprobe sch_hfsc try_modprobe sch_hhf try_modprobe sch_htb try_modprobe sch_teql -./tdc.py -J`nproc` +try_modprobe sch_dualpi2 +./tdc.py -J"$(nproc)" diff --git a/tools/testing/selftests/ublk/fault_inject.c b/tools/testing/selftests/ublk/fault_inject.c index 6e60f7d97125..b227bd78b252 100644 --- a/tools/testing/selftests/ublk/fault_inject.c +++ b/tools/testing/selftests/ublk/fault_inject.c @@ -38,7 +38,8 @@ static int ublk_fault_inject_tgt_init(const struct dev_ctx *ctx, return 0; } -static int ublk_fault_inject_queue_io(struct ublk_queue *q, int tag) +static int ublk_fault_inject_queue_io(struct ublk_thread *t, + struct ublk_queue *q, int tag) { const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag); struct io_uring_sqe *sqe; @@ -46,25 +47,27 @@ static int ublk_fault_inject_queue_io(struct ublk_queue *q, int tag) .tv_nsec = (long long)q->dev->private_data, }; - ublk_io_alloc_sqes(ublk_get_io(q, tag), &sqe, 1); + ublk_io_alloc_sqes(t, &sqe, 1); io_uring_prep_timeout(sqe, &ts, 1, 0); sqe->user_data = build_user_data(tag, ublksrv_get_op(iod), 0, q->q_id, 1); - ublk_queued_tgt_io(q, tag, 1); + ublk_queued_tgt_io(t, q, tag, 1); return 0; } -static void ublk_fault_inject_tgt_io_done(struct ublk_queue *q, int tag, +static void ublk_fault_inject_tgt_io_done(struct ublk_thread *t, + struct ublk_queue *q, const struct io_uring_cqe *cqe) { + unsigned tag = user_data_to_tag(cqe->user_data); const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag); if (cqe->res != -ETIME) ublk_err("%s: unexpected cqe res %d\n", __func__, cqe->res); - if (ublk_completed_tgt_io(q, tag)) - ublk_complete_io(q, tag, iod->nr_sectors << 9); + if (ublk_completed_tgt_io(t, q, tag)) + ublk_complete_io(t, q, tag, iod->nr_sectors << 9); else ublk_err("%s: io not complete after 1 cqe\n", __func__); } diff --git a/tools/testing/selftests/ublk/file_backed.c b/tools/testing/selftests/ublk/file_backed.c index cfa59b631693..2d93ac860bd5 100644 --- a/tools/testing/selftests/ublk/file_backed.c +++ b/tools/testing/selftests/ublk/file_backed.c @@ -13,12 +13,13 @@ static enum io_uring_op ublk_to_uring_op(const struct ublksrv_io_desc *iod, int assert(0); } -static int loop_queue_flush_io(struct ublk_queue *q, const struct ublksrv_io_desc *iod, int tag) +static int loop_queue_flush_io(struct ublk_thread *t, struct ublk_queue *q, + const struct ublksrv_io_desc *iod, int tag) { unsigned ublk_op = ublksrv_get_op(iod); struct io_uring_sqe *sqe[1]; - ublk_io_alloc_sqes(ublk_get_io(q, tag), sqe, 1); + ublk_io_alloc_sqes(t, sqe, 1); io_uring_prep_fsync(sqe[0], 1 /*fds[1]*/, IORING_FSYNC_DATASYNC); io_uring_sqe_set_flags(sqe[0], IOSQE_FIXED_FILE); /* bit63 marks us as tgt io */ @@ -26,7 +27,8 @@ static int loop_queue_flush_io(struct ublk_queue *q, const struct ublksrv_io_des return 1; } -static int loop_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_desc *iod, int tag) +static int loop_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q, + const struct ublksrv_io_desc *iod, int tag) { unsigned ublk_op = ublksrv_get_op(iod); unsigned zc = ublk_queue_use_zc(q); @@ -36,7 +38,7 @@ static int loop_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_de void *addr = (zc | auto_zc) ? NULL : (void *)iod->addr; if (!zc || auto_zc) { - ublk_io_alloc_sqes(ublk_get_io(q, tag), sqe, 1); + ublk_io_alloc_sqes(t, sqe, 1); if (!sqe[0]) return -ENOMEM; @@ -52,7 +54,7 @@ static int loop_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_de return 1; } - ublk_io_alloc_sqes(ublk_get_io(q, tag), sqe, 3); + ublk_io_alloc_sqes(t, sqe, 3); io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index); sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK; @@ -72,7 +74,7 @@ static int loop_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_de return 2; } -static int loop_queue_tgt_io(struct ublk_queue *q, int tag) +static int loop_queue_tgt_io(struct ublk_thread *t, struct ublk_queue *q, int tag) { const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag); unsigned ublk_op = ublksrv_get_op(iod); @@ -80,7 +82,7 @@ static int loop_queue_tgt_io(struct ublk_queue *q, int tag) switch (ublk_op) { case UBLK_IO_OP_FLUSH: - ret = loop_queue_flush_io(q, iod, tag); + ret = loop_queue_flush_io(t, q, iod, tag); break; case UBLK_IO_OP_WRITE_ZEROES: case UBLK_IO_OP_DISCARD: @@ -88,7 +90,7 @@ static int loop_queue_tgt_io(struct ublk_queue *q, int tag) break; case UBLK_IO_OP_READ: case UBLK_IO_OP_WRITE: - ret = loop_queue_tgt_rw_io(q, iod, tag); + ret = loop_queue_tgt_rw_io(t, q, iod, tag); break; default: ret = -EINVAL; @@ -100,17 +102,19 @@ static int loop_queue_tgt_io(struct ublk_queue *q, int tag) return ret; } -static int ublk_loop_queue_io(struct ublk_queue *q, int tag) +static int ublk_loop_queue_io(struct ublk_thread *t, struct ublk_queue *q, + int tag) { - int queued = loop_queue_tgt_io(q, tag); + int queued = loop_queue_tgt_io(t, q, tag); - ublk_queued_tgt_io(q, tag, queued); + ublk_queued_tgt_io(t, q, tag, queued); return 0; } -static void ublk_loop_io_done(struct ublk_queue *q, int tag, +static void ublk_loop_io_done(struct ublk_thread *t, struct ublk_queue *q, const struct io_uring_cqe *cqe) { + unsigned tag = user_data_to_tag(cqe->user_data); unsigned op = user_data_to_op(cqe->user_data); struct ublk_io *io = ublk_get_io(q, tag); @@ -126,8 +130,8 @@ static void ublk_loop_io_done(struct ublk_queue *q, int tag, if (op == ublk_cmd_op_nr(UBLK_U_IO_REGISTER_IO_BUF)) io->tgt_ios += 1; - if (ublk_completed_tgt_io(q, tag)) - ublk_complete_io(q, tag, io->result); + if (ublk_completed_tgt_io(t, q, tag)) + ublk_complete_io(t, q, tag, io->result); } static int ublk_loop_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev) diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c index e2d2042810d4..95188065b2e9 100644 --- a/tools/testing/selftests/ublk/kublk.c +++ b/tools/testing/selftests/ublk/kublk.c @@ -441,17 +441,10 @@ static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags) unsigned long off; q->tgt_ops = dev->tgt.ops; - q->state = 0; + q->flags = 0; q->q_depth = depth; - - if (dev->dev_info.flags & (UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_AUTO_BUF_REG)) { - q->state |= UBLKSRV_NO_BUF; - if (dev->dev_info.flags & UBLK_F_SUPPORT_ZERO_COPY) - q->state |= UBLKSRV_ZC; - if (dev->dev_info.flags & UBLK_F_AUTO_BUF_REG) - q->state |= UBLKSRV_AUTO_BUF_REG; - } - q->state |= extra_flags; + q->flags = dev->dev_info.flags; + q->flags |= extra_flags; cmd_buf_size = ublk_queue_cmd_buf_sz(q); off = UBLKSRV_CMD_BUF_OFFSET + q->q_id * ublk_queue_max_cmd_buf_sz(); @@ -466,10 +459,10 @@ static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags) io_buf_size = dev->dev_info.max_io_buf_bytes; for (i = 0; i < q->q_depth; i++) { q->ios[i].buf_addr = NULL; - q->ios[i].flags = UBLKSRV_NEED_FETCH_RQ | UBLKSRV_IO_FREE; + q->ios[i].flags = UBLKS_IO_NEED_FETCH_RQ | UBLKS_IO_FREE; q->ios[i].tag = i; - if (q->state & UBLKSRV_NO_BUF) + if (ublk_queue_no_buf(q)) continue; if (posix_memalign((void **)&q->ios[i].buf_addr, @@ -583,15 +576,14 @@ static void ublk_set_auto_buf_reg(const struct ublk_queue *q, else buf.index = q->ios[tag].buf_index; - if (q->state & UBLKSRV_AUTO_BUF_REG_FALLBACK) + if (ublk_queue_auto_zc_fallback(q)) buf.flags = UBLK_AUTO_BUF_REG_FALLBACK; sqe->addr = ublk_auto_buf_reg_to_sqe_addr(&buf); } -int ublk_queue_io_cmd(struct ublk_io *io) +int ublk_queue_io_cmd(struct ublk_thread *t, struct ublk_io *io) { - struct ublk_thread *t = io->t; struct ublk_queue *q = ublk_io_to_queue(io); struct ublksrv_io_cmd *cmd; struct io_uring_sqe *sqe[1]; @@ -599,7 +591,7 @@ int ublk_queue_io_cmd(struct ublk_io *io) __u64 user_data; /* only freed io can be issued */ - if (!(io->flags & UBLKSRV_IO_FREE)) + if (!(io->flags & UBLKS_IO_FREE)) return 0; /* @@ -607,20 +599,20 @@ int ublk_queue_io_cmd(struct ublk_io *io) * getting data */ if (!(io->flags & - (UBLKSRV_NEED_FETCH_RQ | UBLKSRV_NEED_COMMIT_RQ_COMP | UBLKSRV_NEED_GET_DATA))) + (UBLKS_IO_NEED_FETCH_RQ | UBLKS_IO_NEED_COMMIT_RQ_COMP | UBLKS_IO_NEED_GET_DATA))) return 0; - if (io->flags & UBLKSRV_NEED_GET_DATA) + if (io->flags & UBLKS_IO_NEED_GET_DATA) cmd_op = UBLK_U_IO_NEED_GET_DATA; - else if (io->flags & UBLKSRV_NEED_COMMIT_RQ_COMP) + else if (io->flags & UBLKS_IO_NEED_COMMIT_RQ_COMP) cmd_op = UBLK_U_IO_COMMIT_AND_FETCH_REQ; - else if (io->flags & UBLKSRV_NEED_FETCH_RQ) + else if (io->flags & UBLKS_IO_NEED_FETCH_RQ) cmd_op = UBLK_U_IO_FETCH_REQ; if (io_uring_sq_space_left(&t->ring) < 1) io_uring_submit(&t->ring); - ublk_io_alloc_sqes(io, sqe, 1); + ublk_io_alloc_sqes(t, sqe, 1); if (!sqe[0]) { ublk_err("%s: run out of sqe. thread %u, tag %d\n", __func__, t->idx, io->tag); @@ -640,12 +632,12 @@ int ublk_queue_io_cmd(struct ublk_io *io) sqe[0]->rw_flags = 0; cmd->tag = io->tag; cmd->q_id = q->q_id; - if (!(q->state & UBLKSRV_NO_BUF)) + if (!ublk_queue_no_buf(q)) cmd->addr = (__u64) (uintptr_t) io->buf_addr; else cmd->addr = 0; - if (q->state & UBLKSRV_AUTO_BUF_REG) + if (ublk_queue_use_auto_zc(q)) ublk_set_auto_buf_reg(q, sqe[0], io->tag); user_data = build_user_data(io->tag, _IOC_NR(cmd_op), 0, q->q_id, 0); @@ -657,7 +649,7 @@ int ublk_queue_io_cmd(struct ublk_io *io) ublk_dbg(UBLK_DBG_IO_CMD, "%s: (thread %u qid %d tag %u cmd_op %u) iof %x stopping %d\n", __func__, t->idx, q->q_id, io->tag, cmd_op, - io->flags, !!(t->state & UBLKSRV_THREAD_STOPPING)); + io->flags, !!(t->state & UBLKS_T_STOPPING)); return 1; } @@ -685,9 +677,8 @@ static void ublk_submit_fetch_commands(struct ublk_thread *t) int tag = i % dinfo->queue_depth; q = &t->dev->q[q_id]; io = &q->ios[tag]; - io->t = t; io->buf_index = j++; - ublk_queue_io_cmd(io); + ublk_queue_io_cmd(t, io); } } else { /* @@ -697,9 +688,8 @@ static void ublk_submit_fetch_commands(struct ublk_thread *t) struct ublk_queue *q = &t->dev->q[t->idx]; for (i = 0; i < q->q_depth; i++) { io = &q->ios[i]; - io->t = t; io->buf_index = i; - ublk_queue_io_cmd(io); + ublk_queue_io_cmd(t, io); } } } @@ -711,14 +701,13 @@ static int ublk_thread_is_idle(struct ublk_thread *t) static int ublk_thread_is_done(struct ublk_thread *t) { - return (t->state & UBLKSRV_THREAD_STOPPING) && ublk_thread_is_idle(t); + return (t->state & UBLKS_T_STOPPING) && ublk_thread_is_idle(t); } -static inline void ublksrv_handle_tgt_cqe(struct ublk_queue *q, - struct io_uring_cqe *cqe) +static inline void ublksrv_handle_tgt_cqe(struct ublk_thread *t, + struct ublk_queue *q, + struct io_uring_cqe *cqe) { - unsigned tag = user_data_to_tag(cqe->user_data); - if (cqe->res < 0 && cqe->res != -EAGAIN) ublk_err("%s: failed tgt io: res %d qid %u tag %u, cmd_op %u\n", __func__, cqe->res, q->q_id, @@ -726,7 +715,41 @@ static inline void ublksrv_handle_tgt_cqe(struct ublk_queue *q, user_data_to_op(cqe->user_data)); if (q->tgt_ops->tgt_io_done) - q->tgt_ops->tgt_io_done(q, tag, cqe); + q->tgt_ops->tgt_io_done(t, q, cqe); +} + +static void ublk_handle_uring_cmd(struct ublk_thread *t, + struct ublk_queue *q, + const struct io_uring_cqe *cqe) +{ + int fetch = (cqe->res != UBLK_IO_RES_ABORT) && + !(t->state & UBLKS_T_STOPPING); + unsigned tag = user_data_to_tag(cqe->user_data); + struct ublk_io *io = &q->ios[tag]; + + if (!fetch) { + t->state |= UBLKS_T_STOPPING; + io->flags &= ~UBLKS_IO_NEED_FETCH_RQ; + } + + if (cqe->res == UBLK_IO_RES_OK) { + assert(tag < q->q_depth); + if (q->tgt_ops->queue_io) + q->tgt_ops->queue_io(t, q, tag); + } else if (cqe->res == UBLK_IO_RES_NEED_GET_DATA) { + io->flags |= UBLKS_IO_NEED_GET_DATA | UBLKS_IO_FREE; + ublk_queue_io_cmd(t, io); + } else { + /* + * COMMIT_REQ will be completed immediately since no fetching + * piggyback is required. + * + * Marking IO_FREE only, then this io won't be issued since + * we only issue io with (UBLKS_IO_FREE | UBLKSRV_NEED_*) + * + * */ + io->flags = UBLKS_IO_FREE; + } } static void ublk_handle_cqe(struct ublk_thread *t, @@ -735,54 +758,27 @@ static void ublk_handle_cqe(struct ublk_thread *t, struct ublk_dev *dev = t->dev; unsigned q_id = user_data_to_q_id(cqe->user_data); struct ublk_queue *q = &dev->q[q_id]; - unsigned tag = user_data_to_tag(cqe->user_data); unsigned cmd_op = user_data_to_op(cqe->user_data); - int fetch = (cqe->res != UBLK_IO_RES_ABORT) && - !(t->state & UBLKSRV_THREAD_STOPPING); - struct ublk_io *io; if (cqe->res < 0 && cqe->res != -ENODEV) ublk_err("%s: res %d userdata %llx queue state %x\n", __func__, - cqe->res, cqe->user_data, q->state); + cqe->res, cqe->user_data, q->flags); ublk_dbg(UBLK_DBG_IO_CMD, "%s: res %d (qid %d tag %u cmd_op %u target %d/%d) stopping %d\n", - __func__, cqe->res, q->q_id, tag, cmd_op, - is_target_io(cqe->user_data), + __func__, cqe->res, q->q_id, user_data_to_tag(cqe->user_data), + cmd_op, is_target_io(cqe->user_data), user_data_to_tgt_data(cqe->user_data), - (t->state & UBLKSRV_THREAD_STOPPING)); + (t->state & UBLKS_T_STOPPING)); /* Don't retrieve io in case of target io */ if (is_target_io(cqe->user_data)) { - ublksrv_handle_tgt_cqe(q, cqe); + ublksrv_handle_tgt_cqe(t, q, cqe); return; } - io = &q->ios[tag]; t->cmd_inflight--; - if (!fetch) { - t->state |= UBLKSRV_THREAD_STOPPING; - io->flags &= ~UBLKSRV_NEED_FETCH_RQ; - } - - if (cqe->res == UBLK_IO_RES_OK) { - assert(tag < q->q_depth); - if (q->tgt_ops->queue_io) - q->tgt_ops->queue_io(q, tag); - } else if (cqe->res == UBLK_IO_RES_NEED_GET_DATA) { - io->flags |= UBLKSRV_NEED_GET_DATA | UBLKSRV_IO_FREE; - ublk_queue_io_cmd(io); - } else { - /* - * COMMIT_REQ will be completed immediately since no fetching - * piggyback is required. - * - * Marking IO_FREE only, then this io won't be issued since - * we only issue io with (UBLKSRV_IO_FREE | UBLKSRV_NEED_*) - * - * */ - io->flags = UBLKSRV_IO_FREE; - } + ublk_handle_uring_cmd(t, q, cqe); } static int ublk_reap_events_uring(struct ublk_thread *t) @@ -808,7 +804,7 @@ static int ublk_process_io(struct ublk_thread *t) t->dev->dev_info.dev_id, t->idx, io_uring_sq_ready(&t->ring), t->cmd_inflight, - (t->state & UBLKSRV_THREAD_STOPPING)); + (t->state & UBLKS_T_STOPPING)); if (ublk_thread_is_done(t)) return -ENODEV; @@ -817,8 +813,8 @@ static int ublk_process_io(struct ublk_thread *t) reapped = ublk_reap_events_uring(t); ublk_dbg(UBLK_DBG_THREAD, "submit result %d, reapped %d stop %d idle %d\n", - ret, reapped, (t->state & UBLKSRV_THREAD_STOPPING), - (t->state & UBLKSRV_THREAD_IDLE)); + ret, reapped, (t->state & UBLKS_T_STOPPING), + (t->state & UBLKS_T_IDLE)); return reapped; } @@ -915,7 +911,7 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev) { const struct ublksrv_ctrl_dev_info *dinfo = &dev->dev_info; struct ublk_thread_info *tinfo; - unsigned extra_flags = 0; + unsigned long long extra_flags = 0; cpu_set_t *affinity_buf; void *thread_ret; sem_t ready; @@ -937,7 +933,7 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev) return ret; if (ctx->auto_zc_fallback) - extra_flags = UBLKSRV_AUTO_BUF_REG_FALLBACK; + extra_flags = UBLKS_Q_AUTO_BUF_REG_FALLBACK; for (i = 0; i < dinfo->nr_hw_queues; i++) { dev->q[i].dev = dev; diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h index 6be601536b3d..219233f8a053 100644 --- a/tools/testing/selftests/ublk/kublk.h +++ b/tools/testing/selftests/ublk/kublk.h @@ -29,13 +29,9 @@ #include "ublk_dep.h" #include <linux/ublk_cmd.h> -#define __maybe_unused __attribute__((unused)) -#define MAX_BACK_FILES 4 -#ifndef min -#define min(a, b) ((a) < (b) ? (a) : (b)) -#endif +#include "utils.h" -#define ARRAY_SIZE(x) (sizeof(x) / sizeof(x[0])) +#define MAX_BACK_FILES 4 /****************** part 1: libublk ********************/ @@ -45,9 +41,6 @@ #define UBLK_CTRL_RING_DEPTH 32 #define ERROR_EVTFD_DEVID -2 -/* queue idle timeout */ -#define UBLKSRV_IO_IDLE_SECS 20 - #define UBLK_IO_MAX_BYTES (1 << 20) #define UBLK_MAX_QUEUES_SHIFT 5 #define UBLK_MAX_QUEUES (1 << UBLK_MAX_QUEUES_SHIFT) @@ -55,13 +48,6 @@ #define UBLK_MAX_THREADS (1 << UBLK_MAX_THREADS_SHIFT) #define UBLK_QUEUE_DEPTH 1024 -#define UBLK_DBG_DEV (1U << 0) -#define UBLK_DBG_THREAD (1U << 1) -#define UBLK_DBG_IO_CMD (1U << 2) -#define UBLK_DBG_IO (1U << 3) -#define UBLK_DBG_CTRL_CMD (1U << 4) -#define UBLK_LOG (1U << 5) - struct ublk_dev; struct ublk_queue; struct ublk_thread; @@ -121,11 +107,11 @@ struct ublk_ctrl_cmd_data { struct ublk_io { char *buf_addr; -#define UBLKSRV_NEED_FETCH_RQ (1UL << 0) -#define UBLKSRV_NEED_COMMIT_RQ_COMP (1UL << 1) -#define UBLKSRV_IO_FREE (1UL << 2) -#define UBLKSRV_NEED_GET_DATA (1UL << 3) -#define UBLKSRV_NEED_REG_BUF (1UL << 4) +#define UBLKS_IO_NEED_FETCH_RQ (1UL << 0) +#define UBLKS_IO_NEED_COMMIT_RQ_COMP (1UL << 1) +#define UBLKS_IO_FREE (1UL << 2) +#define UBLKS_IO_NEED_GET_DATA (1UL << 3) +#define UBLKS_IO_NEED_REG_BUF (1UL << 4) unsigned short flags; unsigned short refs; /* used by target code only */ @@ -136,7 +122,6 @@ struct ublk_io { unsigned short buf_index; unsigned short tgt_ios; void *private_data; - struct ublk_thread *t; }; struct ublk_tgt_ops { @@ -144,9 +129,9 @@ struct ublk_tgt_ops { int (*init_tgt)(const struct dev_ctx *ctx, struct ublk_dev *); void (*deinit_tgt)(struct ublk_dev *); - int (*queue_io)(struct ublk_queue *, int tag); - void (*tgt_io_done)(struct ublk_queue *, - int tag, const struct io_uring_cqe *); + int (*queue_io)(struct ublk_thread *, struct ublk_queue *, int tag); + void (*tgt_io_done)(struct ublk_thread *, struct ublk_queue *, + const struct io_uring_cqe *); /* * Target specific command line handling @@ -179,12 +164,10 @@ struct ublk_queue { const struct ublk_tgt_ops *tgt_ops; struct ublksrv_io_desc *io_cmd_buf; +/* borrow one bit of ublk uapi flags, which may never be used */ +#define UBLKS_Q_AUTO_BUF_REG_FALLBACK (1ULL << 63) + __u64 flags; struct ublk_io ios[UBLK_QUEUE_DEPTH]; -#define UBLKSRV_NO_BUF (1U << 2) -#define UBLKSRV_ZC (1U << 3) -#define UBLKSRV_AUTO_BUF_REG (1U << 4) -#define UBLKSRV_AUTO_BUF_REG_FALLBACK (1U << 5) - unsigned state; }; struct ublk_thread { @@ -196,8 +179,8 @@ struct ublk_thread { pthread_t thread; unsigned idx; -#define UBLKSRV_THREAD_STOPPING (1U << 0) -#define UBLKSRV_THREAD_IDLE (1U << 1) +#define UBLKS_T_STOPPING (1U << 0) +#define UBLKS_T_IDLE (1U << 1) unsigned state; }; @@ -217,22 +200,7 @@ struct ublk_dev { void *private_data; }; -#ifndef offsetof -#define offsetof(TYPE, MEMBER) ((size_t)&((TYPE *)0)->MEMBER) -#endif - -#ifndef container_of -#define container_of(ptr, type, member) ({ \ - unsigned long __mptr = (unsigned long)(ptr); \ - ((type *)(__mptr - offsetof(type, member))); }) -#endif - -#define round_up(val, rnd) \ - (((val) + ((rnd) - 1)) & ~((rnd) - 1)) - - -extern unsigned int ublk_dbg_mask; -extern int ublk_queue_io_cmd(struct ublk_io *io); +extern int ublk_queue_io_cmd(struct ublk_thread *t, struct ublk_io *io); static inline int ublk_io_auto_zc_fallback(const struct ublksrv_io_desc *iod) @@ -281,43 +249,15 @@ static inline unsigned short ublk_cmd_op_nr(unsigned int op) return _IOC_NR(op); } -static inline void ublk_err(const char *fmt, ...) -{ - va_list ap; - - va_start(ap, fmt); - vfprintf(stderr, fmt, ap); -} - -static inline void ublk_log(const char *fmt, ...) -{ - if (ublk_dbg_mask & UBLK_LOG) { - va_list ap; - - va_start(ap, fmt); - vfprintf(stdout, fmt, ap); - } -} - -static inline void ublk_dbg(int level, const char *fmt, ...) -{ - if (level & ublk_dbg_mask) { - va_list ap; - - va_start(ap, fmt); - vfprintf(stdout, fmt, ap); - } -} - static inline struct ublk_queue *ublk_io_to_queue(const struct ublk_io *io) { return container_of(io, struct ublk_queue, ios[io->tag]); } -static inline int ublk_io_alloc_sqes(struct ublk_io *io, +static inline int ublk_io_alloc_sqes(struct ublk_thread *t, struct io_uring_sqe *sqes[], int nr_sqes) { - struct io_uring *ring = &io->t->ring; + struct io_uring *ring = &t->ring; unsigned left = io_uring_sq_space_left(ring); int i; @@ -380,7 +320,7 @@ static inline int ublk_get_io_res(const struct ublk_queue *q, unsigned tag) static inline void ublk_mark_io_done(struct ublk_io *io, int res) { - io->flags |= (UBLKSRV_NEED_COMMIT_RQ_COMP | UBLKSRV_IO_FREE); + io->flags |= (UBLKS_IO_NEED_COMMIT_RQ_COMP | UBLKS_IO_FREE); io->result = res; } @@ -402,45 +342,58 @@ static inline struct ublk_io *ublk_get_io(struct ublk_queue *q, unsigned tag) return &q->ios[tag]; } -static inline int ublk_complete_io(struct ublk_queue *q, unsigned tag, int res) +static inline int ublk_complete_io(struct ublk_thread *t, struct ublk_queue *q, + unsigned tag, int res) { struct ublk_io *io = &q->ios[tag]; ublk_mark_io_done(io, res); - return ublk_queue_io_cmd(io); + return ublk_queue_io_cmd(t, io); } -static inline void ublk_queued_tgt_io(struct ublk_queue *q, unsigned tag, int queued) +static inline void ublk_queued_tgt_io(struct ublk_thread *t, struct ublk_queue *q, + unsigned tag, int queued) { if (queued < 0) - ublk_complete_io(q, tag, queued); + ublk_complete_io(t, q, tag, queued); else { struct ublk_io *io = ublk_get_io(q, tag); - io->t->io_inflight += queued; + t->io_inflight += queued; io->tgt_ios = queued; io->result = 0; } } -static inline int ublk_completed_tgt_io(struct ublk_queue *q, unsigned tag) +static inline int ublk_completed_tgt_io(struct ublk_thread *t, + struct ublk_queue *q, unsigned tag) { struct ublk_io *io = ublk_get_io(q, tag); - io->t->io_inflight--; + t->io_inflight--; return --io->tgt_ios == 0; } static inline int ublk_queue_use_zc(const struct ublk_queue *q) { - return q->state & UBLKSRV_ZC; + return q->flags & UBLK_F_SUPPORT_ZERO_COPY; } static inline int ublk_queue_use_auto_zc(const struct ublk_queue *q) { - return q->state & UBLKSRV_AUTO_BUF_REG; + return q->flags & UBLK_F_AUTO_BUF_REG; +} + +static inline int ublk_queue_auto_zc_fallback(const struct ublk_queue *q) +{ + return q->flags & UBLKS_Q_AUTO_BUF_REG_FALLBACK; +} + +static inline int ublk_queue_no_buf(const struct ublk_queue *q) +{ + return ublk_queue_use_zc(q) || ublk_queue_use_auto_zc(q); } extern const struct ublk_tgt_ops null_tgt_ops; @@ -451,10 +404,4 @@ extern const struct ublk_tgt_ops fault_inject_tgt_ops; void backing_file_tgt_deinit(struct ublk_dev *dev); int backing_file_tgt_init(struct ublk_dev *dev); -static inline unsigned int ilog2(unsigned int x) -{ - if (x == 0) - return 0; - return (sizeof(x) * 8 - 1) - __builtin_clz(x); -} #endif diff --git a/tools/testing/selftests/ublk/null.c b/tools/testing/selftests/ublk/null.c index afe0b99d77ee..f0e0003a4860 100644 --- a/tools/testing/selftests/ublk/null.c +++ b/tools/testing/selftests/ublk/null.c @@ -55,12 +55,13 @@ static void __setup_nop_io(int tag, const struct ublksrv_io_desc *iod, sqe->user_data = build_user_data(tag, ublk_op, 0, q_id, 1); } -static int null_queue_zc_io(struct ublk_queue *q, int tag) +static int null_queue_zc_io(struct ublk_thread *t, struct ublk_queue *q, + int tag) { const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag); struct io_uring_sqe *sqe[3]; - ublk_io_alloc_sqes(ublk_get_io(q, tag), sqe, 3); + ublk_io_alloc_sqes(t, sqe, 3); io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index); sqe[0]->user_data = build_user_data(tag, @@ -77,19 +78,21 @@ static int null_queue_zc_io(struct ublk_queue *q, int tag) return 2; } -static int null_queue_auto_zc_io(struct ublk_queue *q, int tag) +static int null_queue_auto_zc_io(struct ublk_thread *t, struct ublk_queue *q, + int tag) { const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag); struct io_uring_sqe *sqe[1]; - ublk_io_alloc_sqes(ublk_get_io(q, tag), sqe, 1); + ublk_io_alloc_sqes(t, sqe, 1); __setup_nop_io(tag, iod, sqe[0], q->q_id); return 1; } -static void ublk_null_io_done(struct ublk_queue *q, int tag, - const struct io_uring_cqe *cqe) +static void ublk_null_io_done(struct ublk_thread *t, struct ublk_queue *q, + const struct io_uring_cqe *cqe) { + unsigned tag = user_data_to_tag(cqe->user_data); unsigned op = user_data_to_op(cqe->user_data); struct ublk_io *io = ublk_get_io(q, tag); @@ -105,11 +108,12 @@ static void ublk_null_io_done(struct ublk_queue *q, int tag, if (op == ublk_cmd_op_nr(UBLK_U_IO_REGISTER_IO_BUF)) io->tgt_ios += 1; - if (ublk_completed_tgt_io(q, tag)) - ublk_complete_io(q, tag, io->result); + if (ublk_completed_tgt_io(t, q, tag)) + ublk_complete_io(t, q, tag, io->result); } -static int ublk_null_queue_io(struct ublk_queue *q, int tag) +static int ublk_null_queue_io(struct ublk_thread *t, struct ublk_queue *q, + int tag) { const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag); unsigned auto_zc = ublk_queue_use_auto_zc(q); @@ -117,14 +121,14 @@ static int ublk_null_queue_io(struct ublk_queue *q, int tag) int queued; if (auto_zc && !ublk_io_auto_zc_fallback(iod)) - queued = null_queue_auto_zc_io(q, tag); + queued = null_queue_auto_zc_io(t, q, tag); else if (zc) - queued = null_queue_zc_io(q, tag); + queued = null_queue_zc_io(t, q, tag); else { - ublk_complete_io(q, tag, iod->nr_sectors << 9); + ublk_complete_io(t, q, tag, iod->nr_sectors << 9); return 0; } - ublk_queued_tgt_io(q, tag, queued); + ublk_queued_tgt_io(t, q, tag, queued); return 0; } @@ -134,7 +138,7 @@ static int ublk_null_queue_io(struct ublk_queue *q, int tag) */ static unsigned short ublk_null_buf_index(const struct ublk_queue *q, int tag) { - if (q->state & UBLKSRV_AUTO_BUF_REG_FALLBACK) + if (ublk_queue_auto_zc_fallback(q)) return (unsigned short)-1; return q->ios[tag].buf_index; } diff --git a/tools/testing/selftests/ublk/stripe.c b/tools/testing/selftests/ublk/stripe.c index 37d50bbf5f5e..1fb9b7cc281b 100644 --- a/tools/testing/selftests/ublk/stripe.c +++ b/tools/testing/selftests/ublk/stripe.c @@ -123,7 +123,8 @@ static inline enum io_uring_op stripe_to_uring_op( assert(0); } -static int stripe_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_desc *iod, int tag) +static int stripe_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q, + const struct ublksrv_io_desc *iod, int tag) { const struct stripe_conf *conf = get_chunk_shift(q); unsigned auto_zc = (ublk_queue_use_auto_zc(q) != 0); @@ -138,7 +139,7 @@ static int stripe_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_ io->private_data = s; calculate_stripe_array(conf, iod, s, base); - ublk_io_alloc_sqes(ublk_get_io(q, tag), sqe, s->nr + extra); + ublk_io_alloc_sqes(t, sqe, s->nr + extra); if (zc) { io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, io->buf_index); @@ -176,13 +177,14 @@ static int stripe_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_ return s->nr + zc; } -static int handle_flush(struct ublk_queue *q, const struct ublksrv_io_desc *iod, int tag) +static int handle_flush(struct ublk_thread *t, struct ublk_queue *q, + const struct ublksrv_io_desc *iod, int tag) { const struct stripe_conf *conf = get_chunk_shift(q); struct io_uring_sqe *sqe[NR_STRIPE]; int i; - ublk_io_alloc_sqes(ublk_get_io(q, tag), sqe, conf->nr_files); + ublk_io_alloc_sqes(t, sqe, conf->nr_files); for (i = 0; i < conf->nr_files; i++) { io_uring_prep_fsync(sqe[i], i + 1, IORING_FSYNC_DATASYNC); io_uring_sqe_set_flags(sqe[i], IOSQE_FIXED_FILE); @@ -191,7 +193,8 @@ static int handle_flush(struct ublk_queue *q, const struct ublksrv_io_desc *iod, return conf->nr_files; } -static int stripe_queue_tgt_io(struct ublk_queue *q, int tag) +static int stripe_queue_tgt_io(struct ublk_thread *t, struct ublk_queue *q, + int tag) { const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag); unsigned ublk_op = ublksrv_get_op(iod); @@ -199,7 +202,7 @@ static int stripe_queue_tgt_io(struct ublk_queue *q, int tag) switch (ublk_op) { case UBLK_IO_OP_FLUSH: - ret = handle_flush(q, iod, tag); + ret = handle_flush(t, q, iod, tag); break; case UBLK_IO_OP_WRITE_ZEROES: case UBLK_IO_OP_DISCARD: @@ -207,7 +210,7 @@ static int stripe_queue_tgt_io(struct ublk_queue *q, int tag) break; case UBLK_IO_OP_READ: case UBLK_IO_OP_WRITE: - ret = stripe_queue_tgt_rw_io(q, iod, tag); + ret = stripe_queue_tgt_rw_io(t, q, iod, tag); break; default: ret = -EINVAL; @@ -218,17 +221,19 @@ static int stripe_queue_tgt_io(struct ublk_queue *q, int tag) return ret; } -static int ublk_stripe_queue_io(struct ublk_queue *q, int tag) +static int ublk_stripe_queue_io(struct ublk_thread *t, struct ublk_queue *q, + int tag) { - int queued = stripe_queue_tgt_io(q, tag); + int queued = stripe_queue_tgt_io(t, q, tag); - ublk_queued_tgt_io(q, tag, queued); + ublk_queued_tgt_io(t, q, tag, queued); return 0; } -static void ublk_stripe_io_done(struct ublk_queue *q, int tag, - const struct io_uring_cqe *cqe) +static void ublk_stripe_io_done(struct ublk_thread *t, struct ublk_queue *q, + const struct io_uring_cqe *cqe) { + unsigned tag = user_data_to_tag(cqe->user_data); const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag); unsigned op = user_data_to_op(cqe->user_data); struct ublk_io *io = ublk_get_io(q, tag); @@ -257,13 +262,13 @@ static void ublk_stripe_io_done(struct ublk_queue *q, int tag, } } - if (ublk_completed_tgt_io(q, tag)) { + if (ublk_completed_tgt_io(t, q, tag)) { int res = io->result; if (!res) res = iod->nr_sectors << 9; - ublk_complete_io(q, tag, res); + ublk_complete_io(t, q, tag, res); free_stripe_array(io->private_data); io->private_data = NULL; diff --git a/tools/testing/selftests/ublk/utils.h b/tools/testing/selftests/ublk/utils.h new file mode 100644 index 000000000000..36545d1567f1 --- /dev/null +++ b/tools/testing/selftests/ublk/utils.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef KUBLK_UTILS_H +#define KUBLK_UTILS_H + +#define __maybe_unused __attribute__((unused)) + +#ifndef min +#define min(a, b) ((a) < (b) ? (a) : (b)) +#endif + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof(x[0])) + +#ifndef offsetof +#define offsetof(TYPE, MEMBER) ((size_t)&((TYPE *)0)->MEMBER) +#endif + +#ifndef container_of +#define container_of(ptr, type, member) ({ \ + unsigned long __mptr = (unsigned long)(ptr); \ + ((type *)(__mptr - offsetof(type, member))); }) +#endif + +#define round_up(val, rnd) \ + (((val) + ((rnd) - 1)) & ~((rnd) - 1)) + +static inline unsigned int ilog2(unsigned int x) +{ + if (x == 0) + return 0; + return (sizeof(x) * 8 - 1) - __builtin_clz(x); +} + +#define UBLK_DBG_DEV (1U << 0) +#define UBLK_DBG_THREAD (1U << 1) +#define UBLK_DBG_IO_CMD (1U << 2) +#define UBLK_DBG_IO (1U << 3) +#define UBLK_DBG_CTRL_CMD (1U << 4) +#define UBLK_LOG (1U << 5) + +extern unsigned int ublk_dbg_mask; + +static inline void ublk_err(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); +} + +static inline void ublk_log(const char *fmt, ...) +{ + if (ublk_dbg_mask & UBLK_LOG) { + va_list ap; + + va_start(ap, fmt); + vfprintf(stdout, fmt, ap); + } +} + +static inline void ublk_dbg(int level, const char *fmt, ...) +{ + if (level & ublk_dbg_mask) { + va_list ap; + + va_start(ap, fmt); + vfprintf(stdout, fmt, ap); + } +} + +#endif diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile index 12a0614b9fd4..918a2caa070e 100644 --- a/tools/testing/selftests/vDSO/Makefile +++ b/tools/testing/selftests/vDSO/Makefile @@ -12,7 +12,7 @@ TEST_GEN_PROGS += vdso_test_correctness TEST_GEN_PROGS += vdso_test_getrandom TEST_GEN_PROGS += vdso_test_chacha -CFLAGS := -std=gnu99 -O2 +CFLAGS := -std=gnu99 -O2 -Wall -Wstrict-prototypes ifeq ($(CONFIG_X86_32),y) LDLIBS += -lgcc_s diff --git a/tools/testing/selftests/vDSO/vdso_config.h b/tools/testing/selftests/vDSO/vdso_config.h index 722260f97561..5fdd0f362337 100644 --- a/tools/testing/selftests/vDSO/vdso_config.h +++ b/tools/testing/selftests/vDSO/vdso_config.h @@ -58,6 +58,7 @@ #define VDSO_NAMES 1 #endif +__attribute__((unused)) static const char *versions[7] = { "LINUX_2.6", "LINUX_2.6.15", @@ -68,6 +69,7 @@ static const char *versions[7] = { "LINUX_5.10" }; +__attribute__((unused)) static const char *names[2][7] = { { "__kernel_gettimeofday", diff --git a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c index 9ce795b806f0..4d3d96f1e440 100644..120000 --- a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c +++ b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c @@ -1,58 +1 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * vdso_test_gettimeofday.c: Sample code to test parse_vdso.c and - * vDSO gettimeofday() - * Copyright (c) 2014 Andy Lutomirski - * - * Compile with: - * gcc -std=gnu99 vdso_test_gettimeofday.c parse_vdso_gettimeofday.c - * - * Tested on x86, 32-bit and 64-bit. It may work on other architectures, too. - */ - -#include <stdio.h> -#ifndef NOLIBC -#include <sys/auxv.h> -#include <sys/time.h> -#endif - -#include "../kselftest.h" -#include "parse_vdso.h" -#include "vdso_config.h" -#include "vdso_call.h" - -int main(int argc, char **argv) -{ - const char *version = versions[VDSO_VERSION]; - const char **name = (const char **)&names[VDSO_NAMES]; - - unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR); - if (!sysinfo_ehdr) { - printf("AT_SYSINFO_EHDR is not present!\n"); - return KSFT_SKIP; - } - - vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR)); - - /* Find gettimeofday. */ - typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz); - gtod_t gtod = (gtod_t)vdso_sym(version, name[0]); - - if (!gtod) { - printf("Could not find %s\n", name[0]); - return KSFT_SKIP; - } - - struct timeval tv; - long ret = VDSO_CALL(gtod, 2, &tv, 0); - - if (ret == 0) { - printf("The time is %lld.%06lld\n", - (long long)tv.tv_sec, (long long)tv.tv_usec); - } else { - printf("%s failed\n", name[0]); - return KSFT_FAIL; - } - - return 0; -} +vdso_test_gettimeofday.c
\ No newline at end of file diff --git a/tools/testing/selftests/vDSO/vdso_test_chacha.c b/tools/testing/selftests/vDSO/vdso_test_chacha.c index 8757f738b0b1..0aad682b12c8 100644 --- a/tools/testing/selftests/vDSO/vdso_test_chacha.c +++ b/tools/testing/selftests/vDSO/vdso_test_chacha.c @@ -76,7 +76,8 @@ static void reference_chacha20_blocks(uint8_t *dst_bytes, const uint32_t *key, u void __weak __arch_chacha20_blocks_nostack(uint8_t *dst_bytes, const uint32_t *key, uint32_t *counter, size_t nblocks) { - ksft_exit_skip("Not implemented on architecture\n"); + ksft_test_result_skip("Not implemented on architecture\n"); + ksft_finished(); } int main(int argc, char *argv[]) diff --git a/tools/testing/selftests/vDSO/vdso_test_clock_getres.c b/tools/testing/selftests/vDSO/vdso_test_clock_getres.c index 38d46a8bf7cb..b5d5f59f725a 100644 --- a/tools/testing/selftests/vDSO/vdso_test_clock_getres.c +++ b/tools/testing/selftests/vDSO/vdso_test_clock_getres.c @@ -13,7 +13,6 @@ #define _GNU_SOURCE #include <elf.h> -#include <err.h> #include <fcntl.h> #include <stdint.h> #include <stdio.h> diff --git a/tools/testing/selftests/vDSO/vdso_test_correctness.c b/tools/testing/selftests/vDSO/vdso_test_correctness.c index 5fb97ad67eea..da651cf53c6c 100644 --- a/tools/testing/selftests/vDSO/vdso_test_correctness.c +++ b/tools/testing/selftests/vDSO/vdso_test_correctness.c @@ -108,7 +108,7 @@ static void *vsyscall_getcpu(void) } -static void fill_function_pointers() +static void fill_function_pointers(void) { void *vdso = dlopen("linux-vdso.so.1", RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); diff --git a/tools/testing/selftests/vDSO/vdso_test_getrandom.c b/tools/testing/selftests/vDSO/vdso_test_getrandom.c index 95057f7567db..dd1132508a0d 100644 --- a/tools/testing/selftests/vDSO/vdso_test_getrandom.c +++ b/tools/testing/selftests/vDSO/vdso_test_getrandom.c @@ -21,7 +21,6 @@ #include <sys/wait.h> #include <sys/types.h> #include <linux/random.h> -#include <linux/compiler.h> #include <linux/ptrace.h> #include "../kselftest.h" @@ -101,6 +100,7 @@ out: return state; } +__attribute__((unused)) /* Example for libc implementors */ static void vgetrandom_put_state(void *state) { if (!state) @@ -242,6 +242,7 @@ static void kselftest(void) pid_t child; ksft_print_header(); + vgetrandom_init(); ksft_set_plan(2); for (size_t i = 0; i < 1000; ++i) { @@ -265,7 +266,7 @@ static void kselftest(void) } for (;;) { struct ptrace_syscall_info info = { 0 }; - int status, ret; + int status; ksft_assert(waitpid(child, &status, 0) >= 0); if (WIFEXITED(status)) { ksft_assert(WEXITSTATUS(status) == 0); @@ -295,8 +296,6 @@ static void usage(const char *argv0) int main(int argc, char *argv[]) { - vgetrandom_init(); - if (argc == 1) { kselftest(); return 0; @@ -306,6 +305,9 @@ int main(int argc, char *argv[]) usage(argv[0]); return 1; } + + vgetrandom_init(); + if (!strcmp(argv[1], "bench-single")) bench_single(); else if (!strcmp(argv[1], "bench-multi")) diff --git a/tools/testing/selftests/vsock/.gitignore b/tools/testing/selftests/vsock/.gitignore new file mode 100644 index 000000000000..9c5bf379480f --- /dev/null +++ b/tools/testing/selftests/vsock/.gitignore @@ -0,0 +1,2 @@ +vmtest.log +vsock_test diff --git a/tools/testing/selftests/vsock/Makefile b/tools/testing/selftests/vsock/Makefile new file mode 100644 index 000000000000..c407c0afd938 --- /dev/null +++ b/tools/testing/selftests/vsock/Makefile @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0 + +CURDIR := $(abspath .) +TOOLSDIR := $(abspath ../../..) +VSOCK_TEST_DIR := $(TOOLSDIR)/testing/vsock +VSOCK_TEST_SRCS := $(wildcard $(VSOCK_TEST_DIR)/*.c $(VSOCK_TEST_DIR)/*.h) + +$(OUTPUT)/vsock_test: $(VSOCK_TEST_DIR)/vsock_test + install -m 755 $< $@ + +$(VSOCK_TEST_DIR)/vsock_test: $(VSOCK_TEST_SRCS) + $(MAKE) -C $(VSOCK_TEST_DIR) vsock_test +TEST_PROGS += vmtest.sh +TEST_GEN_FILES := vsock_test + +include ../lib.mk + diff --git a/tools/testing/selftests/vsock/config b/tools/testing/selftests/vsock/config new file mode 100644 index 000000000000..5f0a4f17dfc9 --- /dev/null +++ b/tools/testing/selftests/vsock/config @@ -0,0 +1,111 @@ +CONFIG_BLK_DEV_INITRD=y +CONFIG_BPF=y +CONFIG_BPF_SYSCALL=y +CONFIG_BPF_JIT=y +CONFIG_HAVE_EBPF_JIT=y +CONFIG_BPF_EVENTS=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_FUNCTION_TRACER=y +CONFIG_HAVE_DYNAMIC_FTRACE=y +CONFIG_DYNAMIC_FTRACE=y +CONFIG_HAVE_KPROBES=y +CONFIG_KPROBES=y +CONFIG_KPROBE_EVENTS=y +CONFIG_ARCH_SUPPORTS_UPROBES=y +CONFIG_UPROBES=y +CONFIG_UPROBE_EVENTS=y +CONFIG_DEBUG_FS=y +CONFIG_FW_CFG_SYSFS=y +CONFIG_FW_CFG_SYSFS_CMDLINE=y +CONFIG_DRM=y +CONFIG_DRM_VIRTIO_GPU=y +CONFIG_DRM_VIRTIO_GPU_KMS=y +CONFIG_DRM_BOCHS=y +CONFIG_VIRTIO_IOMMU=y +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_SND_SEQUENCER=y +CONFIG_SND_PCI=y +CONFIG_SND_INTEL8X0=y +CONFIG_SND_HDA_CODEC_REALTEK=y +CONFIG_SECURITYFS=y +CONFIG_CGROUP_BPF=y +CONFIG_SQUASHFS=y +CONFIG_SQUASHFS_XZ=y +CONFIG_SQUASHFS_ZSTD=y +CONFIG_FUSE_FS=y +CONFIG_VIRTIO_FS=y +CONFIG_SERIO=y +CONFIG_PCI=y +CONFIG_INPUT=y +CONFIG_INPUT_KEYBOARD=y +CONFIG_KEYBOARD_ATKBD=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_X86_VERBOSE_BOOTUP=y +CONFIG_VGA_CONSOLE=y +CONFIG_FB=y +CONFIG_FB_VESA=y +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_HCTOSYS=y +CONFIG_RTC_DRV_CMOS=y +CONFIG_HYPERVISOR_GUEST=y +CONFIG_PARAVIRT=y +CONFIG_KVM_GUEST=y +CONFIG_KVM=y +CONFIG_KVM_INTEL=y +CONFIG_KVM_AMD=y +CONFIG_VSOCKETS=y +CONFIG_VSOCKETS_DIAG=y +CONFIG_VSOCKETS_LOOPBACK=y +CONFIG_VMWARE_VMCI_VSOCKETS=y +CONFIG_VIRTIO_VSOCKETS=y +CONFIG_VIRTIO_VSOCKETS_COMMON=y +CONFIG_HYPERV_VSOCKETS=y +CONFIG_VMWARE_VMCI=y +CONFIG_VHOST_VSOCK=y +CONFIG_HYPERV=y +CONFIG_UEVENT_HELPER=n +CONFIG_VIRTIO=y +CONFIG_VIRTIO_PCI=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_BALLOON=y +CONFIG_NET=y +CONFIG_NET_CORE=y +CONFIG_NETDEVICES=y +CONFIG_NETWORK_FILESYSTEMS=y +CONFIG_INET=y +CONFIG_NET_9P=y +CONFIG_NET_9P_VIRTIO=y +CONFIG_9P_FS=y +CONFIG_VIRTIO_NET=y +CONFIG_CMDLINE_OVERRIDE=n +CONFIG_BINFMT_SCRIPT=y +CONFIG_SHMEM=y +CONFIG_TMPFS=y +CONFIG_UNIX=y +CONFIG_MODULE_SIG_FORCE=n +CONFIG_DEVTMPFS=y +CONFIG_TTY=y +CONFIG_VT=y +CONFIG_UNIX98_PTYS=y +CONFIG_EARLY_PRINTK=y +CONFIG_INOTIFY_USER=y +CONFIG_BLOCK=y +CONFIG_SCSI_LOWLEVEL=y +CONFIG_SCSI=y +CONFIG_SCSI_VIRTIO=y +CONFIG_BLK_DEV_SD=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_WATCHDOG=y +CONFIG_WATCHDOG_CORE=y +CONFIG_I6300ESB_WDT=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y +CONFIG_OVERLAY_FS=y +CONFIG_DAX=y +CONFIG_DAX_DRIVER=y +CONFIG_FS_DAX=y +CONFIG_MEMORY_HOTPLUG=y +CONFIG_MEMORY_HOTREMOVE=y +CONFIG_ZONE_DEVICE=y diff --git a/tools/testing/selftests/vsock/settings b/tools/testing/selftests/vsock/settings new file mode 100644 index 000000000000..694d70710ff0 --- /dev/null +++ b/tools/testing/selftests/vsock/settings @@ -0,0 +1 @@ +timeout=300 diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh new file mode 100755 index 000000000000..edacebfc1632 --- /dev/null +++ b/tools/testing/selftests/vsock/vmtest.sh @@ -0,0 +1,487 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2025 Meta Platforms, Inc. and affiliates +# +# Dependencies: +# * virtme-ng +# * busybox-static (used by virtme-ng) +# * qemu (used by virtme-ng) + +readonly SCRIPT_DIR="$(cd -P -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)" +readonly KERNEL_CHECKOUT=$(realpath "${SCRIPT_DIR}"/../../../../) + +source "${SCRIPT_DIR}"/../kselftest/ktap_helpers.sh + +readonly VSOCK_TEST="${SCRIPT_DIR}"/vsock_test +readonly TEST_GUEST_PORT=51000 +readonly TEST_HOST_PORT=50000 +readonly TEST_HOST_PORT_LISTENER=50001 +readonly SSH_GUEST_PORT=22 +readonly SSH_HOST_PORT=2222 +readonly VSOCK_CID=1234 +readonly WAIT_PERIOD=3 +readonly WAIT_PERIOD_MAX=60 +readonly WAIT_TOTAL=$(( WAIT_PERIOD * WAIT_PERIOD_MAX )) +readonly QEMU_PIDFILE=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) + +# virtme-ng offers a netdev for ssh when using "--ssh", but we also need a +# control port forwarded for vsock_test. Because virtme-ng doesn't support +# adding an additional port to forward to the device created from "--ssh" and +# virtme-init mistakenly sets identical IPs to the ssh device and additional +# devices, we instead opt out of using --ssh, add the device manually, and also +# add the kernel cmdline options that virtme-init uses to setup the interface. +readonly QEMU_TEST_PORT_FWD="hostfwd=tcp::${TEST_HOST_PORT}-:${TEST_GUEST_PORT}" +readonly QEMU_SSH_PORT_FWD="hostfwd=tcp::${SSH_HOST_PORT}-:${SSH_GUEST_PORT}" +readonly QEMU_OPTS="\ + -netdev user,id=n0,${QEMU_TEST_PORT_FWD},${QEMU_SSH_PORT_FWD} \ + -device virtio-net-pci,netdev=n0 \ + -device vhost-vsock-pci,guest-cid=${VSOCK_CID} \ + --pidfile ${QEMU_PIDFILE} \ +" +readonly KERNEL_CMDLINE="\ + virtme.dhcp net.ifnames=0 biosdevname=0 \ + virtme.ssh virtme_ssh_channel=tcp virtme_ssh_user=$USER \ +" +readonly LOG=$(mktemp /tmp/vsock_vmtest_XXXX.log) +readonly TEST_NAMES=(vm_server_host_client vm_client_host_server vm_loopback) +readonly TEST_DESCS=( + "Run vsock_test in server mode on the VM and in client mode on the host." + "Run vsock_test in client mode on the VM and in server mode on the host." + "Run vsock_test using the loopback transport in the VM." +) + +VERBOSE=0 + +usage() { + local name + local desc + local i + + echo + echo "$0 [OPTIONS] [TEST]..." + echo "If no TEST argument is given, all tests will be run." + echo + echo "Options" + echo " -b: build the kernel from the current source tree and use it for guest VMs" + echo " -q: set the path to or name of qemu binary" + echo " -v: verbose output" + echo + echo "Available tests" + + for ((i = 0; i < ${#TEST_NAMES[@]}; i++)); do + name=${TEST_NAMES[${i}]} + desc=${TEST_DESCS[${i}]} + printf "\t%-35s%-35s\n" "${name}" "${desc}" + done + echo + + exit 1 +} + +die() { + echo "$*" >&2 + exit "${KSFT_FAIL}" +} + +vm_ssh() { + ssh -q -o UserKnownHostsFile=/dev/null -p ${SSH_HOST_PORT} localhost "$@" + return $? +} + +cleanup() { + if [[ -s "${QEMU_PIDFILE}" ]]; then + pkill -SIGTERM -F "${QEMU_PIDFILE}" > /dev/null 2>&1 + fi + + # If failure occurred during or before qemu start up, then we need + # to clean this up ourselves. + if [[ -e "${QEMU_PIDFILE}" ]]; then + rm "${QEMU_PIDFILE}" + fi +} + +check_args() { + local found + + for arg in "$@"; do + found=0 + for name in "${TEST_NAMES[@]}"; do + if [[ "${name}" = "${arg}" ]]; then + found=1 + break + fi + done + + if [[ "${found}" -eq 0 ]]; then + echo "${arg} is not an available test" >&2 + usage + fi + done + + for arg in "$@"; do + if ! command -v > /dev/null "test_${arg}"; then + echo "Test ${arg} not found" >&2 + usage + fi + done +} + +check_deps() { + for dep in vng ${QEMU} busybox pkill ssh; do + if [[ ! -x $(command -v "${dep}") ]]; then + echo -e "skip: dependency ${dep} not found!\n" + exit "${KSFT_SKIP}" + fi + done + + if [[ ! -x $(command -v "${VSOCK_TEST}") ]]; then + printf "skip: %s not found!" "${VSOCK_TEST}" + printf " Please build the kselftest vsock target.\n" + exit "${KSFT_SKIP}" + fi +} + +check_vng() { + local tested_versions + local version + local ok + + tested_versions=("1.33" "1.36") + version="$(vng --version)" + + ok=0 + for tv in "${tested_versions[@]}"; do + if [[ "${version}" == *"${tv}"* ]]; then + ok=1 + break + fi + done + + if [[ ! "${ok}" -eq 1 ]]; then + printf "warning: vng version '%s' has not been tested and may " "${version}" >&2 + printf "not function properly.\n\tThe following versions have been tested: " >&2 + echo "${tested_versions[@]}" >&2 + fi +} + +handle_build() { + if [[ ! "${BUILD}" -eq 1 ]]; then + return + fi + + if [[ ! -d "${KERNEL_CHECKOUT}" ]]; then + echo "-b requires vmtest.sh called from the kernel source tree" >&2 + exit 1 + fi + + pushd "${KERNEL_CHECKOUT}" &>/dev/null + + if ! vng --kconfig --config "${SCRIPT_DIR}"/config; then + die "failed to generate .config for kernel source tree (${KERNEL_CHECKOUT})" + fi + + if ! make -j$(nproc); then + die "failed to build kernel from source tree (${KERNEL_CHECKOUT})" + fi + + popd &>/dev/null +} + +vm_start() { + local logfile=/dev/null + local verbose_opt="" + local kernel_opt="" + local qemu + + qemu=$(command -v "${QEMU}") + + if [[ "${VERBOSE}" -eq 1 ]]; then + verbose_opt="--verbose" + logfile=/dev/stdout + fi + + if [[ "${BUILD}" -eq 1 ]]; then + kernel_opt="${KERNEL_CHECKOUT}" + fi + + vng \ + --run \ + ${kernel_opt} \ + ${verbose_opt} \ + --qemu-opts="${QEMU_OPTS}" \ + --qemu="${qemu}" \ + --user root \ + --append "${KERNEL_CMDLINE}" \ + --rw &> ${logfile} & + + if ! timeout ${WAIT_TOTAL} \ + bash -c 'while [[ ! -s '"${QEMU_PIDFILE}"' ]]; do sleep 1; done; exit 0'; then + die "failed to boot VM" + fi +} + +vm_wait_for_ssh() { + local i + + i=0 + while true; do + if [[ ${i} -gt ${WAIT_PERIOD_MAX} ]]; then + die "Timed out waiting for guest ssh" + fi + if vm_ssh -- true; then + break + fi + i=$(( i + 1 )) + sleep ${WAIT_PERIOD} + done +} + +# derived from selftests/net/net_helper.sh +wait_for_listener() +{ + local port=$1 + local interval=$2 + local max_intervals=$3 + local protocol=tcp + local pattern + local i + + pattern=":$(printf "%04X" "${port}") " + + # for tcp protocol additionally check the socket state + [ "${protocol}" = "tcp" ] && pattern="${pattern}0A" + for i in $(seq "${max_intervals}"); do + if awk '{print $2" "$4}' /proc/net/"${protocol}"* | \ + grep -q "${pattern}"; then + break + fi + sleep "${interval}" + done +} + +vm_wait_for_listener() { + local port=$1 + + vm_ssh <<EOF +$(declare -f wait_for_listener) +wait_for_listener ${port} ${WAIT_PERIOD} ${WAIT_PERIOD_MAX} +EOF +} + +host_wait_for_listener() { + wait_for_listener "${TEST_HOST_PORT_LISTENER}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}" +} + +__log_stdin() { + cat | awk '{ printf "%s:\t%s\n","'"${prefix}"'", $0 }' +} + +__log_args() { + echo "$*" | awk '{ printf "%s:\t%s\n","'"${prefix}"'", $0 }' +} + +log() { + local prefix="$1" + + shift + local redirect= + if [[ ${VERBOSE} -eq 0 ]]; then + redirect=/dev/null + else + redirect=/dev/stdout + fi + + if [[ "$#" -eq 0 ]]; then + __log_stdin | tee -a "${LOG}" > ${redirect} + else + __log_args "$@" | tee -a "${LOG}" > ${redirect} + fi +} + +log_setup() { + log "setup" "$@" +} + +log_host() { + local testname=$1 + + shift + log "test:${testname}:host" "$@" +} + +log_guest() { + local testname=$1 + + shift + log "test:${testname}:guest" "$@" +} + +test_vm_server_host_client() { + local testname="${FUNCNAME[0]#test_}" + + vm_ssh -- "${VSOCK_TEST}" \ + --mode=server \ + --control-port="${TEST_GUEST_PORT}" \ + --peer-cid=2 \ + 2>&1 | log_guest "${testname}" & + + vm_wait_for_listener "${TEST_GUEST_PORT}" + + ${VSOCK_TEST} \ + --mode=client \ + --control-host=127.0.0.1 \ + --peer-cid="${VSOCK_CID}" \ + --control-port="${TEST_HOST_PORT}" 2>&1 | log_host "${testname}" + + return $? +} + +test_vm_client_host_server() { + local testname="${FUNCNAME[0]#test_}" + + ${VSOCK_TEST} \ + --mode "server" \ + --control-port "${TEST_HOST_PORT_LISTENER}" \ + --peer-cid "${VSOCK_CID}" 2>&1 | log_host "${testname}" & + + host_wait_for_listener + + vm_ssh -- "${VSOCK_TEST}" \ + --mode=client \ + --control-host=10.0.2.2 \ + --peer-cid=2 \ + --control-port="${TEST_HOST_PORT_LISTENER}" 2>&1 | log_guest "${testname}" + + return $? +} + +test_vm_loopback() { + local testname="${FUNCNAME[0]#test_}" + local port=60000 # non-forwarded local port + + vm_ssh -- "${VSOCK_TEST}" \ + --mode=server \ + --control-port="${port}" \ + --peer-cid=1 2>&1 | log_guest "${testname}" & + + vm_wait_for_listener "${port}" + + vm_ssh -- "${VSOCK_TEST}" \ + --mode=client \ + --control-host="127.0.0.1" \ + --control-port="${port}" \ + --peer-cid=1 2>&1 | log_guest "${testname}" + + return $? +} + +run_test() { + local host_oops_cnt_before + local host_warn_cnt_before + local vm_oops_cnt_before + local vm_warn_cnt_before + local host_oops_cnt_after + local host_warn_cnt_after + local vm_oops_cnt_after + local vm_warn_cnt_after + local name + local rc + + host_oops_cnt_before=$(dmesg | grep -c -i 'Oops') + host_warn_cnt_before=$(dmesg --level=warn | wc -l) + vm_oops_cnt_before=$(vm_ssh -- dmesg | grep -c -i 'Oops') + vm_warn_cnt_before=$(vm_ssh -- dmesg --level=warn | wc -l) + + name=$(echo "${1}" | awk '{ print $1 }') + eval test_"${name}" + rc=$? + + host_oops_cnt_after=$(dmesg | grep -i 'Oops' | wc -l) + if [[ ${host_oops_cnt_after} -gt ${host_oops_cnt_before} ]]; then + echo "FAIL: kernel oops detected on host" | log_host "${name}" + rc=$KSFT_FAIL + fi + + host_warn_cnt_after=$(dmesg --level=warn | wc -l) + if [[ ${host_warn_cnt_after} -gt ${host_warn_cnt_before} ]]; then + echo "FAIL: kernel warning detected on host" | log_host "${name}" + rc=$KSFT_FAIL + fi + + vm_oops_cnt_after=$(vm_ssh -- dmesg | grep -i 'Oops' | wc -l) + if [[ ${vm_oops_cnt_after} -gt ${vm_oops_cnt_before} ]]; then + echo "FAIL: kernel oops detected on vm" | log_host "${name}" + rc=$KSFT_FAIL + fi + + vm_warn_cnt_after=$(vm_ssh -- dmesg --level=warn | wc -l) + if [[ ${vm_warn_cnt_after} -gt ${vm_warn_cnt_before} ]]; then + echo "FAIL: kernel warning detected on vm" | log_host "${name}" + rc=$KSFT_FAIL + fi + + return "${rc}" +} + +QEMU="qemu-system-$(uname -m)" + +while getopts :hvsq:b o +do + case $o in + v) VERBOSE=1;; + b) BUILD=1;; + q) QEMU=$OPTARG;; + h|*) usage;; + esac +done +shift $((OPTIND-1)) + +trap cleanup EXIT + +if [[ ${#} -eq 0 ]]; then + ARGS=("${TEST_NAMES[@]}") +else + ARGS=("$@") +fi + +check_args "${ARGS[@]}" +check_deps +check_vng +handle_build + +echo "1..${#ARGS[@]}" + +log_setup "Booting up VM" +vm_start +vm_wait_for_ssh +log_setup "VM booted up" + +cnt_pass=0 +cnt_fail=0 +cnt_skip=0 +cnt_total=0 +for arg in "${ARGS[@]}"; do + run_test "${arg}" + rc=$? + if [[ ${rc} -eq $KSFT_PASS ]]; then + cnt_pass=$(( cnt_pass + 1 )) + echo "ok ${cnt_total} ${arg}" + elif [[ ${rc} -eq $KSFT_SKIP ]]; then + cnt_skip=$(( cnt_skip + 1 )) + echo "ok ${cnt_total} ${arg} # SKIP" + elif [[ ${rc} -eq $KSFT_FAIL ]]; then + cnt_fail=$(( cnt_fail + 1 )) + echo "not ok ${cnt_total} ${arg} # exit=$rc" + fi + cnt_total=$(( cnt_total + 1 )) +done + +echo "SUMMARY: PASS=${cnt_pass} SKIP=${cnt_skip} FAIL=${cnt_fail}" +echo "Log: ${LOG}" + +if [ $((cnt_pass + cnt_skip)) -eq ${cnt_total} ]; then + exit "$KSFT_PASS" +else + exit "$KSFT_FAIL" +fi diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config index f314d3789f17..0a5381717e9f 100644 --- a/tools/testing/selftests/wireguard/qemu/kernel.config +++ b/tools/testing/selftests/wireguard/qemu/kernel.config @@ -16,9 +16,13 @@ CONFIG_NETFILTER_ADVANCED=y CONFIG_NF_CONNTRACK=y CONFIG_NF_NAT=y CONFIG_NETFILTER_XTABLES=y +CONFIG_NETFILTER_XTABLES_LEGACY=y CONFIG_NETFILTER_XT_NAT=y CONFIG_NETFILTER_XT_MATCH_LENGTH=y CONFIG_NETFILTER_XT_MARK=y +CONFIG_NETFILTER_XT_TARGET_MASQUERADE=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP_NF_IPTABLES=y CONFIG_IP_NF_FILTER=y CONFIG_IP_NF_MANGLE=y diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h index 14718ca23a05..816e7e057585 100644 --- a/tools/testing/vma/vma_internal.h +++ b/tools/testing/vma/vma_internal.h @@ -1442,8 +1442,29 @@ static inline void free_anon_vma_name(struct vm_area_struct *vma) (void)vma; } +/* Declared in vma.h. */ +static inline void set_vma_from_desc(struct vm_area_struct *vma, + struct vm_area_desc *desc); + +static inline struct vm_area_desc *vma_to_desc(struct vm_area_struct *vma, + struct vm_area_desc *desc); + +static int compat_vma_mmap_prepare(struct file *file, + struct vm_area_struct *vma) +{ + struct vm_area_desc desc; + int err; + + err = file->f_op->mmap_prepare(vma_to_desc(vma, &desc)); + if (err) + return err; + set_vma_from_desc(vma, &desc); + + return 0; +} + /* Did the driver provide valid mmap hook configuration? */ -static inline bool file_has_valid_mmap_hooks(struct file *file) +static inline bool can_mmap_file(struct file *file) { bool has_mmap = file->f_op->mmap; bool has_mmap_prepare = file->f_op->mmap_prepare; @@ -1451,22 +1472,21 @@ static inline bool file_has_valid_mmap_hooks(struct file *file) /* Hooks are mutually exclusive. */ if (WARN_ON_ONCE(has_mmap && has_mmap_prepare)) return false; - if (WARN_ON_ONCE(!has_mmap && !has_mmap_prepare)) + if (!has_mmap && !has_mmap_prepare) return false; return true; } -static inline int call_mmap(struct file *file, struct vm_area_struct *vma) +static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma) { - if (WARN_ON_ONCE(file->f_op->mmap_prepare)) - return -EINVAL; + if (file->f_op->mmap_prepare) + return compat_vma_mmap_prepare(file, vma); return file->f_op->mmap(file, vma); } -static inline int __call_mmap_prepare(struct file *file, - struct vm_area_desc *desc) +static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc) { return file->f_op->mmap_prepare(desc); } diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile index 6e0b4e95e230..88211fd132d2 100644 --- a/tools/testing/vsock/Makefile +++ b/tools/testing/vsock/Makefile @@ -5,6 +5,7 @@ vsock_test: vsock_test.o vsock_test_zerocopy.o timeout.o control.o util.o msg_ze vsock_diag_test: vsock_diag_test.o timeout.o control.o util.o vsock_perf: vsock_perf.o msg_zerocopy_common.o +vsock_test: LDLIBS = -lpthread vsock_uring_test: LDLIBS = -luring vsock_uring_test: control.o util.o vsock_uring_test.o timeout.o msg_zerocopy_common.o diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index 0c7e9cbcbc85..7b861a8e997a 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -7,6 +7,7 @@ * Author: Stefan Hajnoczi <[email protected]> */ +#include <ctype.h> #include <errno.h> #include <stdio.h> #include <stdint.h> @@ -16,6 +17,7 @@ #include <unistd.h> #include <assert.h> #include <sys/epoll.h> +#include <sys/ioctl.h> #include <sys/mman.h> #include <linux/sockios.h> @@ -23,6 +25,9 @@ #include "control.h" #include "util.h" +#define KALLSYMS_PATH "/proc/kallsyms" +#define KALLSYMS_LINE_LEN 512 + /* Install signal handlers */ void init_signals(void) { @@ -97,39 +102,52 @@ void vsock_wait_remote_close(int fd) close(epollfd); } -/* Wait until transport reports no data left to be sent. - * Return false if transport does not implement the unsent_bytes() callback. +/* Wait until ioctl gives an expected int value. + * Return false if the op is not supported. */ -bool vsock_wait_sent(int fd) +bool vsock_ioctl_int(int fd, unsigned long op, int expected) { - int ret, sock_bytes_unsent; + int actual, ret; + char name[32]; + + snprintf(name, sizeof(name), "ioctl(%lu)", op); timeout_begin(TIMEOUT); do { - ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent); + ret = ioctl(fd, op, &actual); if (ret < 0) { - if (errno == EOPNOTSUPP) + if (errno == EOPNOTSUPP || errno == ENOTTY) break; - perror("ioctl(SIOCOUTQ)"); + perror(name); exit(EXIT_FAILURE); } - timeout_check("SIOCOUTQ"); - } while (sock_bytes_unsent != 0); + timeout_check(name); + } while (actual != expected); timeout_end(); - return !ret; + return ret >= 0; } -/* Create socket <type>, bind to <cid, port> and return the file descriptor. */ -int vsock_bind(unsigned int cid, unsigned int port, int type) +/* Wait until transport reports no data left to be sent. + * Return false if transport does not implement the unsent_bytes() callback. + */ +bool vsock_wait_sent(int fd) +{ + return vsock_ioctl_int(fd, SIOCOUTQ, 0); +} + +/* Create socket <type>, bind to <cid, port>. + * Return the file descriptor, or -1 on error. + */ +int vsock_bind_try(unsigned int cid, unsigned int port, int type) { struct sockaddr_vm sa = { .svm_family = AF_VSOCK, .svm_cid = cid, .svm_port = port, }; - int fd; + int fd, saved_errno; fd = socket(AF_VSOCK, type, 0); if (fd < 0) { @@ -138,6 +156,22 @@ int vsock_bind(unsigned int cid, unsigned int port, int type) } if (bind(fd, (struct sockaddr *)&sa, sizeof(sa))) { + saved_errno = errno; + close(fd); + errno = saved_errno; + fd = -1; + } + + return fd; +} + +/* Create socket <type>, bind to <cid, port> and return the file descriptor. */ +int vsock_bind(unsigned int cid, unsigned int port, int type) +{ + int fd; + + fd = vsock_bind_try(cid, port, type); + if (fd < 0) { perror("bind"); exit(EXIT_FAILURE); } @@ -836,3 +870,55 @@ void enable_so_linger(int fd, int timeout) exit(EXIT_FAILURE); } } + +static int __get_transports(void) +{ + char buf[KALLSYMS_LINE_LEN]; + const char *ksym; + int ret = 0; + FILE *f; + + f = fopen(KALLSYMS_PATH, "r"); + if (!f) { + perror("Can't open " KALLSYMS_PATH); + exit(EXIT_FAILURE); + } + + while (fgets(buf, sizeof(buf), f)) { + char *match; + int i; + + assert(buf[strlen(buf) - 1] == '\n'); + + for (i = 0; i < TRANSPORT_NUM; ++i) { + if (ret & BIT(i)) + continue; + + /* Match should be followed by '\t' or '\n'. + * See kallsyms.c:s_show(). + */ + ksym = transport_ksyms[i]; + match = strstr(buf, ksym); + if (match && isspace(match[strlen(ksym)])) { + ret |= BIT(i); + break; + } + } + } + + fclose(f); + return ret; +} + +/* Return integer with TRANSPORT_* bit set for every (known) registered vsock + * transport. + */ +int get_transports(void) +{ + static int tr = -1; + + if (tr == -1) + tr = __get_transports(); + + return tr; +} diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index 5e2db67072d5..142c02a6834a 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -3,8 +3,40 @@ #define UTIL_H #include <sys/socket.h> +#include <linux/bitops.h> +#include <linux/kernel.h> #include <linux/vm_sockets.h> +/* All known vsock transports, see callers of vsock_core_register() */ +#define KNOWN_TRANSPORTS(x) \ + x(LOOPBACK, "loopback") \ + x(VIRTIO, "virtio") \ + x(VHOST, "vhost") \ + x(VMCI, "vmci") \ + x(HYPERV, "hvs") + +enum transport { + TRANSPORT_COUNTER_BASE = __COUNTER__ + 1, + #define x(name, symbol) \ + TRANSPORT_##name = BIT(__COUNTER__ - TRANSPORT_COUNTER_BASE), + KNOWN_TRANSPORTS(x) + TRANSPORT_NUM = __COUNTER__ - TRANSPORT_COUNTER_BASE, + #undef x +}; + +static const char * const transport_ksyms[] = { + #define x(name, symbol) "d " symbol "_transport", + KNOWN_TRANSPORTS(x) + #undef x +}; + +static_assert(ARRAY_SIZE(transport_ksyms) == TRANSPORT_NUM); +static_assert(BITS_PER_TYPE(int) >= TRANSPORT_NUM); + +#define TRANSPORTS_G2H (TRANSPORT_VIRTIO | TRANSPORT_VMCI | TRANSPORT_HYPERV) +#define TRANSPORTS_H2G (TRANSPORT_VHOST | TRANSPORT_VMCI) +#define TRANSPORTS_LOCAL (TRANSPORT_LOOPBACK) + /* Tests can either run as the client or the server */ enum test_mode { TEST_MODE_UNSET, @@ -44,6 +76,7 @@ int vsock_connect(unsigned int cid, unsigned int port, int type); int vsock_accept(unsigned int cid, unsigned int port, struct sockaddr_vm *clientaddrp, int type); int vsock_stream_connect(unsigned int cid, unsigned int port); +int vsock_bind_try(unsigned int cid, unsigned int port, int type); int vsock_bind(unsigned int cid, unsigned int port, int type); int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type); @@ -54,6 +87,7 @@ int vsock_stream_listen(unsigned int cid, unsigned int port); int vsock_seqpacket_accept(unsigned int cid, unsigned int port, struct sockaddr_vm *clientaddrp); void vsock_wait_remote_close(int fd); +bool vsock_ioctl_int(int fd, unsigned long op, int expected); bool vsock_wait_sent(int fd); void send_buf(int fd, const void *buf, size_t len, int flags, ssize_t expected_ret); @@ -81,4 +115,5 @@ void setsockopt_timeval_check(int fd, int level, int optname, struct timeval val, char const *errmsg); void enable_so_zerocopy_check(int fd); void enable_so_linger(int fd, int timeout); +int get_transports(void); #endif /* UTIL_H */ diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index f669baaa0dca..d4517386e551 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -22,6 +22,9 @@ #include <signal.h> #include <sys/ioctl.h> #include <linux/time64.h> +#include <pthread.h> +#include <fcntl.h> +#include <linux/sockios.h> #include "vsock_test_zerocopy.h" #include "timeout.h" @@ -1305,6 +1308,54 @@ static void test_unsent_bytes_client(const struct test_opts *opts, int type) close(fd); } +static void test_unread_bytes_server(const struct test_opts *opts, int type) +{ + unsigned char buf[MSG_BUF_IOCTL_LEN]; + int client_fd; + + client_fd = vsock_accept(VMADDR_CID_ANY, opts->peer_port, NULL, type); + if (client_fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + for (int i = 0; i < sizeof(buf); i++) + buf[i] = rand() & 0xFF; + + send_buf(client_fd, buf, sizeof(buf), 0, sizeof(buf)); + control_writeln("SENT"); + + close(client_fd); +} + +static void test_unread_bytes_client(const struct test_opts *opts, int type) +{ + unsigned char buf[MSG_BUF_IOCTL_LEN]; + int fd; + + fd = vsock_connect(opts->peer_cid, opts->peer_port, type); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + control_expectln("SENT"); + /* The data has arrived but has not been read. The expected is + * MSG_BUF_IOCTL_LEN. + */ + if (!vsock_ioctl_int(fd, SIOCINQ, MSG_BUF_IOCTL_LEN)) { + fprintf(stderr, "Test skipped, SIOCINQ not supported.\n"); + goto out; + } + + recv_buf(fd, buf, sizeof(buf), 0, sizeof(buf)); + /* All data has been consumed, so the expected is 0. */ + vsock_ioctl_int(fd, SIOCINQ, 0); + +out: + close(fd); +} + static void test_stream_unsent_bytes_client(const struct test_opts *opts) { test_unsent_bytes_client(opts, SOCK_STREAM); @@ -1325,6 +1376,26 @@ static void test_seqpacket_unsent_bytes_server(const struct test_opts *opts) test_unsent_bytes_server(opts, SOCK_SEQPACKET); } +static void test_stream_unread_bytes_client(const struct test_opts *opts) +{ + test_unread_bytes_client(opts, SOCK_STREAM); +} + +static void test_stream_unread_bytes_server(const struct test_opts *opts) +{ + test_unread_bytes_server(opts, SOCK_STREAM); +} + +static void test_seqpacket_unread_bytes_client(const struct test_opts *opts) +{ + test_unread_bytes_client(opts, SOCK_SEQPACKET); +} + +static void test_seqpacket_unread_bytes_server(const struct test_opts *opts) +{ + test_unread_bytes_server(opts, SOCK_SEQPACKET); +} + #define RCVLOWAT_CREDIT_UPD_BUF_SIZE (1024 * 128) /* This define is the same as in 'include/linux/virtio_vsock.h': * it is used to decide when to send credit update message during @@ -1718,16 +1789,27 @@ static void test_stream_msgzcopy_leak_zcskb_server(const struct test_opts *opts) #define MAX_PORT_RETRIES 24 /* net/vmw_vsock/af_vsock.c */ -/* Test attempts to trigger a transport release for an unbound socket. This can - * lead to a reference count mishandling. - */ -static void test_stream_transport_uaf_client(const struct test_opts *opts) +static bool test_stream_transport_uaf(int cid) { int sockets[MAX_PORT_RETRIES]; struct sockaddr_vm addr; - int fd, i, alen; + socklen_t alen; + int fd, i, c; + bool ret; - fd = vsock_bind(VMADDR_CID_ANY, VMADDR_PORT_ANY, SOCK_STREAM); + /* Probe for a transport by attempting a local CID bind. Unavailable + * transport (or more specifically: an unsupported transport/CID + * combination) results in EADDRNOTAVAIL, other errnos are fatal. + */ + fd = vsock_bind_try(cid, VMADDR_PORT_ANY, SOCK_STREAM); + if (fd < 0) { + if (errno != EADDRNOTAVAIL) { + perror("Unexpected bind() errno"); + exit(EXIT_FAILURE); + } + + return false; + } alen = sizeof(addr); if (getsockname(fd, (struct sockaddr *)&addr, &alen)) { @@ -1735,38 +1817,83 @@ static void test_stream_transport_uaf_client(const struct test_opts *opts) exit(EXIT_FAILURE); } + /* Drain the autobind pool; see __vsock_bind_connectible(). */ for (i = 0; i < MAX_PORT_RETRIES; ++i) - sockets[i] = vsock_bind(VMADDR_CID_ANY, ++addr.svm_port, - SOCK_STREAM); + sockets[i] = vsock_bind(cid, ++addr.svm_port, SOCK_STREAM); close(fd); - fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + /* Setting SOCK_NONBLOCK makes connect() return soon after + * (re-)assigning the transport. We are not connecting to anything + * anyway, so there is no point entering the main loop in + * vsock_connect(); waiting for timeout, checking for signals, etc. + */ + fd = socket(AF_VSOCK, SOCK_STREAM | SOCK_NONBLOCK, 0); if (fd < 0) { perror("socket"); exit(EXIT_FAILURE); } - if (!vsock_connect_fd(fd, addr.svm_cid, addr.svm_port)) { - perror("Unexpected connect() #1 success"); + /* Assign transport, while failing to autobind. Autobind pool was + * drained, so EADDRNOTAVAIL coming from __vsock_bind_connectible() is + * expected. + * + * One exception is ENODEV which is thrown by vsock_assign_transport(), + * i.e. before vsock_auto_bind(), when the only transport loaded is + * vhost. + */ + if (!connect(fd, (struct sockaddr *)&addr, alen)) { + fprintf(stderr, "Unexpected connect() success\n"); exit(EXIT_FAILURE); } - - /* Vulnerable system may crash now. */ - if (!vsock_connect_fd(fd, VMADDR_CID_HOST, VMADDR_PORT_ANY)) { - perror("Unexpected connect() #2 success"); + if (errno == ENODEV && cid == VMADDR_CID_HOST) { + ret = false; + goto cleanup; + } + if (errno != EADDRNOTAVAIL) { + perror("Unexpected connect() errno"); exit(EXIT_FAILURE); } + /* Reassign transport, triggering old transport release and + * (potentially) unbinding of an unbound socket. + * + * Vulnerable system may crash now. + */ + for (c = VMADDR_CID_HYPERVISOR; c <= VMADDR_CID_HOST + 1; ++c) { + if (c != cid) { + addr.svm_cid = c; + (void)connect(fd, (struct sockaddr *)&addr, alen); + } + } + + ret = true; +cleanup: close(fd); while (i--) close(sockets[i]); - control_writeln("DONE"); + return ret; } -static void test_stream_transport_uaf_server(const struct test_opts *opts) +/* Test attempts to trigger a transport release for an unbound socket. This can + * lead to a reference count mishandling. + */ +static void test_stream_transport_uaf_client(const struct test_opts *opts) { - control_expectln("DONE"); + bool tested = false; + int cid, tr; + + for (cid = VMADDR_CID_HYPERVISOR; cid <= VMADDR_CID_HOST + 1; ++cid) + tested |= test_stream_transport_uaf(cid); + + tr = get_transports(); + if (!tr) + fprintf(stderr, "No transports detected\n"); + else if (tr == TRANSPORT_VIRTIO) + fprintf(stderr, "Setup unsupported: sole virtio transport\n"); + else if (!tested) + fprintf(stderr, "No transports tested\n"); } static void test_stream_connect_retry_client(const struct test_opts *opts) @@ -1811,6 +1938,180 @@ static void test_stream_connect_retry_server(const struct test_opts *opts) close(fd); } +#define TRANSPORT_CHANGE_TIMEOUT 2 /* seconds */ + +static void *test_stream_transport_change_thread(void *vargp) +{ + pid_t *pid = (pid_t *)vargp; + int ret; + + ret = pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, NULL); + if (ret) { + fprintf(stderr, "pthread_setcanceltype: %d\n", ret); + exit(EXIT_FAILURE); + } + + while (true) { + if (kill(*pid, SIGUSR1) < 0) { + perror("kill"); + exit(EXIT_FAILURE); + } + } + return NULL; +} + +static void test_transport_change_signal_handler(int signal) +{ + /* We need a custom handler for SIGUSR1 as the default one terminates the process. */ +} + +static void test_stream_transport_change_client(const struct test_opts *opts) +{ + __sighandler_t old_handler; + pid_t pid = getpid(); + pthread_t thread_id; + time_t tout; + int ret, tr; + + tr = get_transports(); + + /* Print a warning if there is a G2H transport loaded. + * This is on a best effort basis because VMCI can be either G2H and H2G, and there is + * no easy way to understand it. + * The bug we are testing only appears when G2H transports are not loaded. + * This is because `vsock_assign_transport`, when using CID 0, assigns a G2H transport + * to vsk->transport. If none is available it is set to NULL, causing the null-ptr-deref. + */ + if (tr & TRANSPORTS_G2H) + fprintf(stderr, "G2H Transport detected. This test will not fail.\n"); + + old_handler = signal(SIGUSR1, test_transport_change_signal_handler); + if (old_handler == SIG_ERR) { + perror("signal"); + exit(EXIT_FAILURE); + } + + ret = pthread_create(&thread_id, NULL, test_stream_transport_change_thread, &pid); + if (ret) { + fprintf(stderr, "pthread_create: %d\n", ret); + exit(EXIT_FAILURE); + } + + control_expectln("LISTENING"); + + tout = current_nsec() + TRANSPORT_CHANGE_TIMEOUT * NSEC_PER_SEC; + do { + struct sockaddr_vm sa = { + .svm_family = AF_VSOCK, + .svm_cid = opts->peer_cid, + .svm_port = opts->peer_port, + }; + bool send_control = false; + int s; + + s = socket(AF_VSOCK, SOCK_STREAM, 0); + if (s < 0) { + perror("socket"); + exit(EXIT_FAILURE); + } + + ret = connect(s, (struct sockaddr *)&sa, sizeof(sa)); + /* The connect can fail due to signals coming from the thread, + * or because the receiver connection queue is full. + * Ignoring also the latter case because there is no way + * of synchronizing client's connect and server's accept when + * connect(s) are constantly being interrupted by signals. + */ + if (ret == -1 && (errno != EINTR && errno != ECONNRESET)) { + perror("connect"); + exit(EXIT_FAILURE); + } + + /* Notify the server if the connect() is successful or the + * receiver connection queue is full, so it will do accept() + * to drain it. + */ + if (!ret || errno == ECONNRESET) + send_control = true; + + /* Set CID to 0 cause a transport change. */ + sa.svm_cid = 0; + + /* There is a case where this will not fail: + * if the previous connect() is interrupted while the + * connection request is already sent, this second + * connect() will wait for the response. + */ + ret = connect(s, (struct sockaddr *)&sa, sizeof(sa)); + if (!ret || errno == ECONNRESET) + send_control = true; + + close(s); + + if (send_control) + control_writeulong(CONTROL_CONTINUE); + + } while (current_nsec() < tout); + + control_writeulong(CONTROL_DONE); + + ret = pthread_cancel(thread_id); + if (ret) { + fprintf(stderr, "pthread_cancel: %d\n", ret); + exit(EXIT_FAILURE); + } + + ret = pthread_join(thread_id, NULL); + if (ret) { + fprintf(stderr, "pthread_join: %d\n", ret); + exit(EXIT_FAILURE); + } + + if (signal(SIGUSR1, old_handler) == SIG_ERR) { + perror("signal"); + exit(EXIT_FAILURE); + } +} + +static void test_stream_transport_change_server(const struct test_opts *opts) +{ + int s = vsock_stream_listen(VMADDR_CID_ANY, opts->peer_port); + + /* Set the socket to be nonblocking because connects that have been interrupted + * (EINTR) can fill the receiver's accept queue anyway, leading to connect failure. + * As of today (6.15) in such situation there is no way to understand, from the + * client side, if the connection has been queued in the server or not. + */ + if (fcntl(s, F_SETFL, fcntl(s, F_GETFL, 0) | O_NONBLOCK) < 0) { + perror("fcntl"); + exit(EXIT_FAILURE); + } + control_writeln("LISTENING"); + + while (control_readulong() == CONTROL_CONTINUE) { + /* Must accept the connection, otherwise the `listen` + * queue will fill up and new connections will fail. + * There can be more than one queued connection, + * clear them all. + */ + while (true) { + int client = accept(s, NULL, NULL); + + if (client < 0) { + if (errno == EAGAIN) + break; + + perror("accept"); + exit(EXIT_FAILURE); + } + + close(client); + } + } + + close(s); +} + static void test_stream_linger_client(const struct test_opts *opts) { int fd; @@ -2034,7 +2335,6 @@ static struct test_case test_cases[] = { { .name = "SOCK_STREAM transport release use-after-free", .run_client = test_stream_transport_uaf_client, - .run_server = test_stream_transport_uaf_server, }, { .name = "SOCK_STREAM retry failed connect()", @@ -2051,6 +2351,21 @@ static struct test_case test_cases[] = { .run_client = test_stream_nolinger_client, .run_server = test_stream_nolinger_server, }, + { + .name = "SOCK_STREAM transport change null-ptr-deref", + .run_client = test_stream_transport_change_client, + .run_server = test_stream_transport_change_server, + }, + { + .name = "SOCK_STREAM ioctl(SIOCINQ) functionality", + .run_client = test_stream_unread_bytes_client, + .run_server = test_stream_unread_bytes_server, + }, + { + .name = "SOCK_SEQPACKET ioctl(SIOCINQ) functionality", + .run_client = test_seqpacket_unread_bytes_client, + .run_server = test_seqpacket_unread_bytes_server, + }, {}, }; |