July 2025 - Linux-kselftest-mirror

[PATCH bpf-next v2 17/18] selftests/bpf: add basic testcases for tracing_multi

by Menglong Dong

In this commit, we add some testcases for the following attach types: BPF_TRACE_FENTRY_MULTI BPF_TRACE_FEXIT_MULTI BPF_MODIFY_RETURN_MULTI We reuse the testings in fentry_test.c, fexit_test.c and modify_return.c by attach the tracing bpf prog as tracing_multi. We add some functions to skip for tracing progs to bpf_get_ksyms(). The functions that in the "btf_id_deny" should be skipped. What's more, the kernel can't find the right function address according to the btf type id when duplicated function name exist. So we skip such functions that we meet. The list is not whole, so we still can fail during attaching the FENTRY_MULTI to all the kernel functions. This is something that we need to fix in the feature. Signed-off-by: Menglong Dong <dongml2(a)chinatelecom.cn> --- tools/testing/selftests/bpf/Makefile | 2 +- .../selftests/bpf/prog_tests/fentry_fexit.c | 22 +- .../selftests/bpf/prog_tests/fentry_test.c | 79 +++++-- .../selftests/bpf/prog_tests/fexit_test.c | 79 +++++-- .../selftests/bpf/prog_tests/modify_return.c | 60 +++++ .../bpf/prog_tests/tracing_multi_link.c | 210 ++++++++++++++++++ .../selftests/bpf/progs/fentry_multi_empty.c | 13 ++ .../selftests/bpf/progs/tracing_multi_test.c | 181 +++++++++++++++ .../selftests/bpf/test_kmods/bpf_testmod.c | 24 ++ tools/testing/selftests/bpf/test_progs.c | 50 +++++ tools/testing/selftests/bpf/test_progs.h | 3 + tools/testing/selftests/bpf/trace_helpers.c | 69 ++++++ 12 files changed, 744 insertions(+), 48 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/tracing_multi_link.c create mode 100644 tools/testing/selftests/bpf/progs/fentry_multi_empty.c create mode 100644 tools/testing/selftests/bpf/progs/tracing_multi_test.c diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 4863106034df..1fa0da096262 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -496,7 +496,7 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ test_subskeleton.skel.h test_subskeleton_lib.skel.h \ test_usdt.skel.h -LSKELS := fentry_test.c fexit_test.c fexit_sleep.c atomics.c \ +LSKELS := fexit_sleep.c atomics.c \ trace_printk.c trace_vprintk.c map_ptr_kern.c \ core_kern.c core_kern_overflow.c test_ringbuf.c \ test_ringbuf_n.c test_ringbuf_map_key.c test_ringbuf_write.c diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 130f5b82d2e6..84cc8b669684 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -1,32 +1,32 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> -#include "fentry_test.lskel.h" -#include "fexit_test.lskel.h" +#include "fentry_test.skel.h" +#include "fexit_test.skel.h" void test_fentry_fexit(void) { - struct fentry_test_lskel *fentry_skel = NULL; - struct fexit_test_lskel *fexit_skel = NULL; + struct fentry_test *fentry_skel = NULL; + struct fexit_test *fexit_skel = NULL; __u64 *fentry_res, *fexit_res; int err, prog_fd, i; LIBBPF_OPTS(bpf_test_run_opts, topts); - fentry_skel = fentry_test_lskel__open_and_load(); + fentry_skel = fentry_test__open_and_load(); if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load")) goto close_prog; - fexit_skel = fexit_test_lskel__open_and_load(); + fexit_skel = fexit_test__open_and_load(); if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load")) goto close_prog; - err = fentry_test_lskel__attach(fentry_skel); + err = fentry_test__attach(fentry_skel); if (!ASSERT_OK(err, "fentry_attach")) goto close_prog; - err = fexit_test_lskel__attach(fexit_skel); + err = fexit_test__attach(fexit_skel); if (!ASSERT_OK(err, "fexit_attach")) goto close_prog; - prog_fd = fexit_skel->progs.test1.prog_fd; + prog_fd = bpf_program__fd(fexit_skel->progs.test1); err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "ipv6 test_run"); ASSERT_OK(topts.retval, "ipv6 test retval"); @@ -40,6 +40,6 @@ void test_fentry_fexit(void) } close_prog: - fentry_test_lskel__destroy(fentry_skel); - fexit_test_lskel__destroy(fexit_skel); + fentry_test__destroy(fentry_skel); + fexit_test__destroy(fexit_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c index aee1bc77a17f..9edd383feabd 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c @@ -1,26 +1,16 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> -#include "fentry_test.lskel.h" +#include "fentry_test.skel.h" #include "fentry_many_args.skel.h" -static int fentry_test_common(struct fentry_test_lskel *fentry_skel) +static int fentry_test_check(struct fentry_test *fentry_skel) { + LIBBPF_OPTS(bpf_test_run_opts, topts); int err, prog_fd, i; - int link_fd; __u64 *result; - LIBBPF_OPTS(bpf_test_run_opts, topts); - - err = fentry_test_lskel__attach(fentry_skel); - if (!ASSERT_OK(err, "fentry_attach")) - return err; - /* Check that already linked program can't be attached again. */ - link_fd = fentry_test_lskel__test1__attach(fentry_skel); - if (!ASSERT_LT(link_fd, 0, "fentry_attach_link")) - return -1; - - prog_fd = fentry_skel->progs.test1.prog_fd; + prog_fd = bpf_program__fd(fentry_skel->progs.test1); err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); ASSERT_EQ(topts.retval, 0, "test_run"); @@ -31,7 +21,28 @@ static int fentry_test_common(struct fentry_test_lskel *fentry_skel) return -1; } - fentry_test_lskel__detach(fentry_skel); + return 0; +} + +static int fentry_test_common(struct fentry_test *fentry_skel) +{ + struct bpf_link *link; + int err; + + err = fentry_test__attach(fentry_skel); + if (!ASSERT_OK(err, "fentry_attach")) + return err; + + /* Check that already linked program can't be attached again. */ + link = bpf_program__attach(fentry_skel->progs.test1); + if (!ASSERT_ERR_PTR(link, "fentry_attach_link")) + return -1; + + err = fentry_test_check(fentry_skel); + if (!ASSERT_OK(err, "fentry_test_check")) + return err; + + fentry_test__detach(fentry_skel); /* zero results for re-attach test */ memset(fentry_skel->bss, 0, sizeof(*fentry_skel->bss)); @@ -40,10 +51,10 @@ static int fentry_test_common(struct fentry_test_lskel *fentry_skel) static void fentry_test(void) { - struct fentry_test_lskel *fentry_skel = NULL; + struct fentry_test *fentry_skel = NULL; int err; - fentry_skel = fentry_test_lskel__open_and_load(); + fentry_skel = fentry_test__open_and_load(); if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load")) goto cleanup; @@ -55,7 +66,7 @@ static void fentry_test(void) ASSERT_OK(err, "fentry_second_attach"); cleanup: - fentry_test_lskel__destroy(fentry_skel); + fentry_test__destroy(fentry_skel); } static void fentry_many_args(void) @@ -84,10 +95,42 @@ static void fentry_many_args(void) fentry_many_args__destroy(fentry_skel); } +static void fentry_multi_test(void) +{ + struct fentry_test *fentry_skel = NULL; + int err, prog_cnt; + + fentry_skel = fentry_test__open(); + if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_open")) + goto cleanup; + + prog_cnt = sizeof(fentry_skel->progs) / sizeof(long); + err = bpf_to_tracing_multi((void *)&fentry_skel->progs, prog_cnt); + if (!ASSERT_OK(err, "fentry_to_multi")) + goto cleanup; + + err = fentry_test__load(fentry_skel); + if (!ASSERT_OK(err, "fentry_skel_load")) + goto cleanup; + + err = bpf_attach_as_tracing_multi((void *)&fentry_skel->progs, + prog_cnt, + (void *)&fentry_skel->links); + if (!ASSERT_OK(err, "fentry_attach_multi")) + goto cleanup; + + err = fentry_test_check(fentry_skel); + ASSERT_OK(err, "fentry_first_attach"); +cleanup: + fentry_test__destroy(fentry_skel); +} + void test_fentry_test(void) { if (test__start_subtest("fentry")) fentry_test(); + if (test__start_subtest("fentry_multi")) + fentry_multi_test(); if (test__start_subtest("fentry_many_args")) fentry_many_args(); } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c index 1c13007e37dd..5652d02b3ad9 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c @@ -1,26 +1,16 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> -#include "fexit_test.lskel.h" +#include "fexit_test.skel.h" #include "fexit_many_args.skel.h" -static int fexit_test_common(struct fexit_test_lskel *fexit_skel) +static int fexit_test_check(struct fexit_test *fexit_skel) { + LIBBPF_OPTS(bpf_test_run_opts, topts); int err, prog_fd, i; - int link_fd; __u64 *result; - LIBBPF_OPTS(bpf_test_run_opts, topts); - - err = fexit_test_lskel__attach(fexit_skel); - if (!ASSERT_OK(err, "fexit_attach")) - return err; - /* Check that already linked program can't be attached again. */ - link_fd = fexit_test_lskel__test1__attach(fexit_skel); - if (!ASSERT_LT(link_fd, 0, "fexit_attach_link")) - return -1; - - prog_fd = fexit_skel->progs.test1.prog_fd; + prog_fd = bpf_program__fd(fexit_skel->progs.test1); err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); ASSERT_EQ(topts.retval, 0, "test_run"); @@ -31,7 +21,28 @@ static int fexit_test_common(struct fexit_test_lskel *fexit_skel) return -1; } - fexit_test_lskel__detach(fexit_skel); + return 0; +} + +static int fexit_test_common(struct fexit_test *fexit_skel) +{ + struct bpf_link *link; + int err; + + err = fexit_test__attach(fexit_skel); + if (!ASSERT_OK(err, "fexit_attach")) + return err; + + /* Check that already linked program can't be attached again. */ + link = bpf_program__attach(fexit_skel->progs.test1); + if (!ASSERT_ERR_PTR(link, "fexit_attach_link")) + return -1; + + err = fexit_test_check(fexit_skel); + if (!ASSERT_OK(err, "fexit_test_check")) + return err; + + fexit_test__detach(fexit_skel); /* zero results for re-attach test */ memset(fexit_skel->bss, 0, sizeof(*fexit_skel->bss)); @@ -40,10 +51,10 @@ static int fexit_test_common(struct fexit_test_lskel *fexit_skel) static void fexit_test(void) { - struct fexit_test_lskel *fexit_skel = NULL; + struct fexit_test *fexit_skel = NULL; int err; - fexit_skel = fexit_test_lskel__open_and_load(); + fexit_skel = fexit_test__open_and_load(); if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load")) goto cleanup; @@ -55,7 +66,7 @@ static void fexit_test(void) ASSERT_OK(err, "fexit_second_attach"); cleanup: - fexit_test_lskel__destroy(fexit_skel); + fexit_test__destroy(fexit_skel); } static void fexit_many_args(void) @@ -84,10 +95,42 @@ static void fexit_many_args(void) fexit_many_args__destroy(fexit_skel); } +static void fexit_test_multi(void) +{ + struct fexit_test *fexit_skel = NULL; + int err, prog_cnt; + + fexit_skel = fexit_test__open(); + if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_open")) + goto cleanup; + + prog_cnt = sizeof(fexit_skel->progs) / sizeof(long); + err = bpf_to_tracing_multi((void *)&fexit_skel->progs, prog_cnt); + if (!ASSERT_OK(err, "fexit_to_multi")) + goto cleanup; + + err = fexit_test__load(fexit_skel); + if (!ASSERT_OK(err, "fexit_skel_load")) + goto cleanup; + + err = bpf_attach_as_tracing_multi((void *)&fexit_skel->progs, + prog_cnt, + (void *)&fexit_skel->links); + if (!ASSERT_OK(err, "fexit_attach_multi")) + goto cleanup; + + err = fexit_test_check(fexit_skel); + ASSERT_OK(err, "fexit_first_attach"); +cleanup: + fexit_test__destroy(fexit_skel); +} + void test_fexit_test(void) { if (test__start_subtest("fexit")) fexit_test(); + if (test__start_subtest("fexit_multi")) + fexit_test_multi(); if (test__start_subtest("fexit_many_args")) fexit_many_args(); } diff --git a/tools/testing/selftests/bpf/prog_tests/modify_return.c b/tools/testing/selftests/bpf/prog_tests/modify_return.c index a70c99c2f8c8..3ca454379e90 100644 --- a/tools/testing/selftests/bpf/prog_tests/modify_return.c +++ b/tools/testing/selftests/bpf/prog_tests/modify_return.c @@ -49,6 +49,56 @@ static void run_test(__u32 input_retval, __u16 want_side_effect, __s16 want_ret) modify_return__destroy(skel); } +static void run_multi_test(__u32 input_retval, __u16 want_side_effect, __s16 want_ret) +{ + struct modify_return *skel = NULL; + int err, prog_fd, prog_cnt; + __u16 side_effect; + __s16 ret; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + skel = modify_return__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + /* stack function args is not supported by tracing multi-link yet, + * so we only enable the bpf progs without stack function args. + */ + bpf_program__set_expected_attach_type(skel->progs.fentry_test, + BPF_TRACE_FENTRY_MULTI); + bpf_program__set_expected_attach_type(skel->progs.fexit_test, + BPF_TRACE_FEXIT_MULTI); + bpf_program__set_expected_attach_type(skel->progs.fmod_ret_test, + BPF_MODIFY_RETURN_MULTI); + + err = modify_return__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + prog_cnt = sizeof(skel->progs) / sizeof(long); + err = bpf_attach_as_tracing_multi((void *)&skel->progs, + prog_cnt, + (void *)&skel->links); + if (!ASSERT_OK(err, "modify_return__attach failed")) + goto cleanup; + + skel->bss->input_retval = input_retval; + prog_fd = bpf_program__fd(skel->progs.fmod_ret_test); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + + side_effect = UPPER(topts.retval); + ret = LOWER(topts.retval); + + ASSERT_EQ(ret, want_ret, "test_run ret"); + ASSERT_EQ(side_effect, want_side_effect, "modify_return side_effect"); + ASSERT_EQ(skel->bss->fentry_result, 1, "modify_return fentry_result"); + ASSERT_EQ(skel->bss->fexit_result, 1, "modify_return fexit_result"); + ASSERT_EQ(skel->bss->fmod_ret_result, 1, "modify_return fmod_ret_result"); +cleanup: + modify_return__destroy(skel); +} + /* TODO: conflict with get_func_ip_test */ void serial_test_modify_return(void) { @@ -59,3 +109,13 @@ void serial_test_modify_return(void) 0 /* want_side_effect */, -EINVAL * 2 /* want_ret */); } + +void serial_test_modify_return_multi(void) +{ + run_multi_test(0 /* input_retval */, + 2 /* want_side_effect */, + 33 /* want_ret */); + run_multi_test(-EINVAL /* input_retval */, + 1 /* want_side_effect */, + -EINVAL + 29 /* want_ret */); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_multi_link.c b/tools/testing/selftests/bpf/prog_tests/tracing_multi_link.c new file mode 100644 index 000000000000..1cbe6089472f --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tracing_multi_link.c @@ -0,0 +1,210 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 ChinaTelecom */ + +#include <test_progs.h> + +#include "tracing_multi_test.skel.h" +#include "fentry_multi_empty.skel.h" + +static void test_run(struct tracing_multi_test *skel) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts); + int err, prog_fd; + + skel->bss->pid = getpid(); + prog_fd = bpf_program__fd(skel->progs.fentry_cookie_test1); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); + + ASSERT_EQ(skel->bss->fentry_test1_result, 1, "fentry_test1_result"); + ASSERT_EQ(skel->bss->fentry_test2_result, 1, "fentry_test2_result"); + ASSERT_EQ(skel->bss->fentry_test3_result, 1, "fentry_test3_result"); + ASSERT_EQ(skel->bss->fentry_test4_result, 1, "fentry_test4_result"); + ASSERT_EQ(skel->bss->fentry_test5_result, 1, "fentry_test5_result"); + ASSERT_EQ(skel->bss->fentry_test6_result, 1, "fentry_test6_result"); + ASSERT_EQ(skel->bss->fentry_test7_result, 1, "fentry_test7_result"); + ASSERT_EQ(skel->bss->fentry_test8_result, 1, "fentry_test8_result"); +} + +static void test_skel_auto_api(void) +{ + struct tracing_multi_test *skel; + int err; + + skel = tracing_multi_test__open_and_load(); + if (!ASSERT_OK_PTR(skel, "tracing_multi_test__open_and_load")) + return; + + /* disable all programs that should fail */ + bpf_program__set_autoattach(skel->progs.fentry_fail_test1, false); + bpf_program__set_autoattach(skel->progs.fentry_fail_test2, false); + bpf_program__set_autoattach(skel->progs.fentry_fail_test3, false); + bpf_program__set_autoattach(skel->progs.fentry_fail_test4, false); + bpf_program__set_autoattach(skel->progs.fentry_fail_test5, false); + bpf_program__set_autoattach(skel->progs.fentry_fail_test6, false); + + bpf_program__set_autoattach(skel->progs.fexit_fail_test1, false); + bpf_program__set_autoattach(skel->progs.fexit_fail_test2, false); + bpf_program__set_autoattach(skel->progs.fexit_fail_test3, false); + + err = tracing_multi_test__attach(skel); + if (!ASSERT_OK(err, "tracing_multi_test__attach")) + goto cleanup; + + test_run(skel); + +cleanup: + tracing_multi_test__destroy(skel); +} + +static int attach_bpf(struct bpf_program *prog, struct bpf_link **link_ptr, + bool success) +{ + struct bpf_link *link; + int err; + + link = bpf_program__attach(prog); + err = libbpf_get_error(link); + if (!ASSERT_OK(success ? err : !err, "attach_bpf")) + return err; + *link_ptr = link; + + return 0; +} + +#define attach_skel_bpf(name, success) \ + attach_bpf(skel->progs.name, &skel->links.name, success) + +static void test_skel_manual_api(void) +{ + struct tracing_multi_test *skel; + + skel = tracing_multi_test__open_and_load(); + if (!ASSERT_OK_PTR(skel, "tracing_multi_test__open_and_load")) + return; + + if (attach_skel_bpf(fentry_success_test1, true) || + attach_skel_bpf(fentry_success_test2, true) || + attach_skel_bpf(fentry_success_test3, true) || + attach_skel_bpf(fentry_success_test4, true) || + attach_skel_bpf(fexit_success_test1, true) || + attach_skel_bpf(fexit_success_test2, true) || + attach_skel_bpf(fentry_fail_test1, false) || + attach_skel_bpf(fentry_fail_test2, false) || + attach_skel_bpf(fentry_fail_test3, false) || + attach_skel_bpf(fentry_fail_test4, false) || + attach_skel_bpf(fentry_fail_test5, false) || + attach_skel_bpf(fentry_fail_test6, false) || + attach_skel_bpf(fexit_fail_test1, false) || + attach_skel_bpf(fexit_fail_test2, false) || + attach_skel_bpf(fexit_fail_test3, false) || + attach_skel_bpf(fentry_cookie_test1, true)) + goto cleanup; + + test_run(skel); + +cleanup: + tracing_multi_test__destroy(skel); +} + +static void test_attach_api(void) +{ + LIBBPF_OPTS(bpf_trace_multi_opts, opts); + struct tracing_multi_test *skel; + struct bpf_link *link; + const char *syms[8] = { + "bpf_fentry_test1", + "bpf_fentry_test2", + "bpf_fentry_test3", + "bpf_fentry_test4", + "bpf_fentry_test5", + "bpf_fentry_test6", + "bpf_fentry_test7", + "bpf_fentry_test8", + }; + __u64 cookies[] = {1, 7, 2, 3, 4, 5, 6, 8}; + + skel = tracing_multi_test__open_and_load(); + if (!ASSERT_OK_PTR(skel, "tracing_multi_test__open_and_load")) + return; + + opts.syms = syms; + opts.cookies = cookies; + opts.cnt = ARRAY_SIZE(syms); + link = bpf_program__attach_trace_multi_opts(skel->progs.fentry_cookie_test1, + &opts); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_trace_multi_opts")) + goto cleanup; + skel->links.fentry_cookie_test1 = link; + + skel->bss->test_cookie = true; + test_run(skel); +cleanup: + tracing_multi_test__destroy(skel); +} + +static void test_attach_bench(bool kernel) +{ + LIBBPF_OPTS(bpf_trace_multi_opts, opts); + struct fentry_multi_empty *skel; + long attach_start_ns, attach_end_ns; + long detach_start_ns, detach_end_ns; + double attach_delta, detach_delta; + struct bpf_link *link = NULL; + char **syms = NULL; + size_t cnt = 0; + + if (!ASSERT_OK(bpf_get_ksyms(&syms, &cnt, kernel), "get_syms")) + return; + + skel = fentry_multi_empty__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_multi_empty__open_and_load")) + goto cleanup; + + opts.syms = (const char **) syms; + opts.cnt = cnt; + opts.skip_invalid = true; + + attach_start_ns = get_time_ns(); + link = bpf_program__attach_trace_multi_opts(skel->progs.fentry_multi_empty, + &opts); + attach_end_ns = get_time_ns(); + + if (!ASSERT_OK_PTR(link, "bpf_program__attach_trace_multi_opts")) + return; + + detach_start_ns = get_time_ns(); + bpf_link__destroy(link); + detach_end_ns = get_time_ns(); + + attach_delta = (attach_end_ns - attach_start_ns) / 1000000000.0; + detach_delta = (detach_end_ns - detach_start_ns) / 1000000000.0; + + printf("%s: found %lu functions\n", __func__, opts.cnt); + printf("%s: attached in %7.3lfs\n", __func__, attach_delta); + printf("%s: detached in %7.3lfs\n", __func__, detach_delta); + +cleanup: + fentry_multi_empty__destroy(skel); + if (syms) + free(syms); +} + +void serial_test_tracing_multi_attach_bench(void) +{ + if (test__start_subtest("kernel")) + test_attach_bench(true); + if (test__start_subtest("modules")) + test_attach_bench(false); +} + +void test_tracing_multi_attach_test(void) +{ + if (test__start_subtest("skel_auto_api")) + test_skel_auto_api(); + if (test__start_subtest("skel_manual_api")) + test_skel_manual_api(); + if (test__start_subtest("attach_api")) + test_attach_api(); +} diff --git a/tools/testing/selftests/bpf/progs/fentry_multi_empty.c b/tools/testing/selftests/bpf/progs/fentry_multi_empty.c new file mode 100644 index 000000000000..a09ba216dff8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fentry_multi_empty.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 ChinaTelecom */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +SEC("fentry.multi/bpf_fentry_test1") +int BPF_PROG(fentry_multi_empty) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/tracing_multi_test.c b/tools/testing/selftests/bpf/progs/tracing_multi_test.c new file mode 100644 index 000000000000..fa27851896b9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tracing_multi_test.c @@ -0,0 +1,181 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 ChinaTelecom */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct bpf_testmod_struct_arg_1 { + int a; +}; +struct bpf_testmod_struct_arg_2 { + long a; + long b; +}; + +__u64 test_result = 0; + +int pid = 0; +int test_cookie = 0; + +__u64 fentry_test1_result = 0; +__u64 fentry_test2_result = 0; +__u64 fentry_test3_result = 0; +__u64 fentry_test4_result = 0; +__u64 fentry_test5_result = 0; +__u64 fentry_test6_result = 0; +__u64 fentry_test7_result = 0; +__u64 fentry_test8_result = 0; + +extern const void bpf_fentry_test1 __ksym; +extern const void bpf_fentry_test2 __ksym; +extern const void bpf_fentry_test3 __ksym; +extern const void bpf_fentry_test4 __ksym; +extern const void bpf_fentry_test5 __ksym; +extern const void bpf_fentry_test6 __ksym; +extern const void bpf_fentry_test7 __ksym; +extern const void bpf_fentry_test8 __ksym; + +SEC("fentry.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_13") +int BPF_PROG2(fentry_success_test1, struct bpf_testmod_struct_arg_2, a) +{ + test_result = a.a + a.b; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_2,bpf_testmod_test_struct_arg_10") +int BPF_PROG2(fentry_success_test2, int, a, struct bpf_testmod_struct_arg_2, b) +{ + test_result = a + b.a + b.b; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_4") +int BPF_PROG2(fentry_success_test3, struct bpf_testmod_struct_arg_2, a, int, b, + int, c) +{ + test_result = c; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_2") +int BPF_PROG2(fentry_success_test4, struct bpf_testmod_struct_arg_2, a, int, b, + int, c) +{ + test_result = c; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_1") +int BPF_PROG2(fentry_fail_test1, struct bpf_testmod_struct_arg_2, a) +{ + test_result = a.a + a.b; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_2") +int BPF_PROG2(fentry_fail_test2, struct bpf_testmod_struct_arg_2, a) +{ + test_result = a.a + a.b; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_4") +int BPF_PROG2(fentry_fail_test3, struct bpf_testmod_struct_arg_2, a) +{ + test_result = a.a + a.b; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_2,bpf_testmod_test_struct_arg_2") +int BPF_PROG2(fentry_fail_test4, int, a, struct bpf_testmod_struct_arg_2, b) +{ + test_result = a + b.a + b.b; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_2,bpf_testmod_test_struct_arg_13") +int BPF_PROG2(fentry_fail_test5, int, a, struct bpf_testmod_struct_arg_2, b) +{ + test_result = a + b.a + b.b; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_12") +int BPF_PROG2(fentry_fail_test6, struct bpf_testmod_struct_arg_2, a, int, b, + int, c) +{ + test_result = c; + return 0; +} + +SEC("fexit.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_2,bpf_testmod_test_struct_arg_3") +int BPF_PROG2(fexit_success_test1, struct bpf_testmod_struct_arg_2, a, int, b, + int, c, int, retval) +{ + test_result = retval; + return 0; +} + +SEC("fexit.multi/bpf_testmod_test_struct_arg_2,bpf_testmod_test_struct_arg_12") +int BPF_PROG2(fexit_success_test2, int, a, struct bpf_testmod_struct_arg_2, b, + int, c, int, retval) +{ + test_result = a + b.a + b.b + retval; + return 0; +} + +SEC("fexit.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_4") +int BPF_PROG2(fexit_fail_test1, struct bpf_testmod_struct_arg_2, a, int, b, + int, c, int, retval) +{ + test_result = retval; + return 0; +} + +SEC("fexit.multi/bpf_testmod_test_struct_arg_2,bpf_testmod_test_struct_arg_10") +int BPF_PROG2(fexit_fail_test2, int, a, struct bpf_testmod_struct_arg_2, b, + int, c, int, retval) +{ + test_result = a + b.a + b.b + retval; + return 0; +} + +SEC("fexit.multi/bpf_testmod_test_struct_arg_2,bpf_testmod_test_struct_arg_11") +int BPF_PROG2(fexit_fail_test3, int, a, struct bpf_testmod_struct_arg_2, b, + int, c, int, retval) +{ + test_result = a + b.a + b.b + retval; + return 0; +} + +static void tracing_multi_check_cookie(unsigned long long *ctx) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return; + + __u64 cookie = test_cookie ? bpf_get_attach_cookie(ctx) : 0; + __u64 addr = bpf_get_func_ip(ctx); + +#define SET(__var, __addr, __cookie) ({ \ + if (((const void *) addr == __addr) && \ + (!test_cookie || (cookie == __cookie))) \ + __var = 1; \ +}) + SET(fentry_test1_result, &bpf_fentry_test1, 1); + SET(fentry_test2_result, &bpf_fentry_test2, 7); + SET(fentry_test3_result, &bpf_fentry_test3, 2); + SET(fentry_test4_result, &bpf_fentry_test4, 3); + SET(fentry_test5_result, &bpf_fentry_test5, 4); + SET(fentry_test6_result, &bpf_fentry_test6, 5); + SET(fentry_test7_result, &bpf_fentry_test7, 6); + SET(fentry_test8_result, &bpf_fentry_test8, 8); +} + +SEC("fentry.multi/bpf_fentry_test1,bpf_fentry_test2,bpf_fentry_test3,bpf_fentry_test4,bpf_fentry_test5,bpf_fentry_test6,bpf_fentry_test7,bpf_fentry_test8") +int BPF_PROG(fentry_cookie_test1) +{ + tracing_multi_check_cookie(ctx); + return 0; +} diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c index e9e918cdf31f..07ea1d5d3795 100644 --- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c @@ -128,6 +128,30 @@ bpf_testmod_test_struct_arg_9(u64 a, void *b, short c, int d, void *e, char f, return bpf_testmod_test_struct_arg_result; } +noinline int +bpf_testmod_test_struct_arg_10(int a, struct bpf_testmod_struct_arg_2 b) { + bpf_testmod_test_struct_arg_result = a + b.a + b.b; + return bpf_testmod_test_struct_arg_result; +} + +noinline struct bpf_testmod_struct_arg_2 * +bpf_testmod_test_struct_arg_11(int a, struct bpf_testmod_struct_arg_2 b, int c) { + bpf_testmod_test_struct_arg_result = a + b.a + b.b + c; + return (void *)bpf_testmod_test_struct_arg_result; +} + +noinline int +bpf_testmod_test_struct_arg_12(int a, struct bpf_testmod_struct_arg_2 b, int *c) { + bpf_testmod_test_struct_arg_result = a + b.a + b.b + *c; + return bpf_testmod_test_struct_arg_result; +} + +noinline int +bpf_testmod_test_struct_arg_13(struct bpf_testmod_struct_arg_2 b) { + bpf_testmod_test_struct_arg_result = b.a + b.b; + return bpf_testmod_test_struct_arg_result; +} + noinline int bpf_testmod_test_arg_ptr_to_struct(struct bpf_testmod_struct_arg_1 *a) { bpf_testmod_test_struct_arg_result = a->a; diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 309d9d4a8ace..533b714f1ca6 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -667,6 +667,56 @@ int bpf_find_map(const char *test, struct bpf_object *obj, const char *name) return bpf_map__fd(map); } +int bpf_to_tracing_multi(struct bpf_program **progs, int prog_cnt) +{ + enum bpf_attach_type type; + int i, err; + + for (i = 0; i < prog_cnt; i++) { + type = bpf_program__get_expected_attach_type(progs[i]); + if (type == BPF_TRACE_FENTRY) + type = BPF_TRACE_FENTRY_MULTI; + else if (type == BPF_TRACE_FEXIT) + type = BPF_TRACE_FEXIT_MULTI; + else if (type == BPF_MODIFY_RETURN) + type = BPF_MODIFY_RETURN_MULTI; + else + continue; + err = bpf_program__set_expected_attach_type(progs[i], type); + if (err) + return err; + } + + return 0; +} + +int bpf_attach_as_tracing_multi(struct bpf_program **progs, int prog_cnt, + struct bpf_link **link) +{ + struct bpf_link *__link; + int err, type; + + for (int i = 0; i < prog_cnt; i++) { + LIBBPF_OPTS(bpf_trace_multi_opts, opts); + + type = bpf_program__get_expected_attach_type(progs[i]); + if (type != BPF_TRACE_FENTRY_MULTI && + type != BPF_TRACE_FEXIT_MULTI && + type != BPF_MODIFY_RETURN_MULTI) + continue; + + opts.attach_tracing = true; + __link = bpf_program__attach_trace_multi_opts(progs[i], &opts); + err = libbpf_get_error(link); + if (err) + return err; + + link[i] = __link; + } + + return 0; +} + int compare_map_keys(int map1_fd, int map2_fd) { __u32 key, next_key; diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index df2222a1806f..7e30c6dbf35c 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -496,6 +496,9 @@ int trigger_module_test_write(int write_sz); int write_sysctl(const char *sysctl, const char *value); int get_bpf_max_tramp_links_from(struct btf *btf); int get_bpf_max_tramp_links(void); +int bpf_to_tracing_multi(struct bpf_program **progs, int prog_cnt); +int bpf_attach_as_tracing_multi(struct bpf_program **progs, int prog_cnt, + struct bpf_link **link); struct netns_obj; struct netns_obj *netns_new(const char *name, bool open); diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index d24baf244d1f..a9e9dd3be226 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -559,6 +559,75 @@ static bool skip_entry(char *name) if (!strncmp(name, "__ftrace_invalid_address__", sizeof("__ftrace_invalid_address__") - 1)) return true; + + /* skip functions in "btf_id_deny" */ + if (!strcmp(name, "migrate_disable")) + return true; + if (!strcmp(name, "migrate_enable")) + return true; + if (!strcmp(name, "rcu_read_unlock_strict")) + return true; + if (!strcmp(name, "preempt_count_add")) + return true; + if (!strcmp(name, "preempt_count_sub")) + return true; + if (!strcmp(name, "__rcu_read_lock")) + return true; + if (!strcmp(name, "__rcu_read_unlock")) + return true; + + /* Following symbols have multi definition in kallsyms, take + * "t_next" for example: + * + * ffffffff813c10d0 t t_next + * ffffffff813d31b0 t t_next + * ffffffff813e06b0 t t_next + * ffffffff813eb360 t t_next + * ffffffff81613360 t t_next + * + * but only one of them have corresponding mrecord: + * ffffffff81613364 t_next + * + * The kernel search the target function address by the symbol + * name "t_next" with kallsyms_lookup_name() during attaching + * and the function "0xffffffff813c10d0" can be matched, which + * doesn't have a corresponding mrecord. And this will make + * the attach failing. Skip the functions like this. + * + * The list maybe not whole, so we still can fail......We need a + * way to make the whole things right. Yes, we need fix it :/ + */ + if (!strcmp(name, "kill_pid_usb_asyncio")) + return true; + if (!strcmp(name, "t_next")) + return true; + if (!strcmp(name, "t_stop")) + return true; + if (!strcmp(name, "t_start")) + return true; + if (!strcmp(name, "p_next")) + return true; + if (!strcmp(name, "p_stop")) + return true; + if (!strcmp(name, "p_start")) + return true; + if (!strcmp(name, "mem32_serial_out")) + return true; + if (!strcmp(name, "mem32_serial_in")) + return true; + if (!strcmp(name, "io_serial_in")) + return true; + if (!strcmp(name, "io_serial_out")) + return true; + if (!strcmp(name, "event_callback")) + return true; + if (!strcmp(name, "amd_pmu_init")) + return true; + if (!strcmp(name, "sync_regs")) + return true; + if (!strcmp(name, "empty")) + return true; + return false; } -- 2.39.5

1 day, 22 hours

1
0
0 0

[PATCH bpf-next v2 16/18] selftests/bpf: move get_ksyms and get_addrs to trace_helpers.c

by Menglong Dong

We need to get all the kernel function that can be traced sometimes, so we move the get_syms() and get_addrs() in kprobe_multi_test.c to trace_helpers.c and rename it to bpf_get_ksyms() and bpf_get_addrs(). Signed-off-by: Menglong Dong <dongml2(a)chinatelecom.cn> --- .../bpf/prog_tests/kprobe_multi_test.c | 220 +----------------- tools/testing/selftests/bpf/trace_helpers.c | 214 +++++++++++++++++ tools/testing/selftests/bpf/trace_helpers.h | 3 + 3 files changed, 220 insertions(+), 217 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c index e19ef509ebf8..171706e78da8 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -422,220 +422,6 @@ static void test_unique_match(void) kprobe_multi__destroy(skel); } -static size_t symbol_hash(long key, void *ctx __maybe_unused) -{ - return str_hash((const char *) key); -} - -static bool symbol_equal(long key1, long key2, void *ctx __maybe_unused) -{ - return strcmp((const char *) key1, (const char *) key2) == 0; -} - -static bool is_invalid_entry(char *buf, bool kernel) -{ - if (kernel && strchr(buf, '[')) - return true; - if (!kernel && !strchr(buf, '[')) - return true; - return false; -} - -static bool skip_entry(char *name) -{ - /* - * We attach to almost all kernel functions and some of them - * will cause 'suspicious RCU usage' when fprobe is attached - * to them. Filter out the current culprits - arch_cpu_idle - * default_idle and rcu_* functions. - */ - if (!strcmp(name, "arch_cpu_idle")) - return true; - if (!strcmp(name, "default_idle")) - return true; - if (!strncmp(name, "rcu_", 4)) - return true; - if (!strcmp(name, "bpf_dispatcher_xdp_func")) - return true; - if (!strncmp(name, "__ftrace_invalid_address__", - sizeof("__ftrace_invalid_address__") - 1)) - return true; - return false; -} - -/* Do comparision by ignoring '.llvm.<hash>' suffixes. */ -static int compare_name(const char *name1, const char *name2) -{ - const char *res1, *res2; - int len1, len2; - - res1 = strstr(name1, ".llvm."); - res2 = strstr(name2, ".llvm."); - len1 = res1 ? res1 - name1 : strlen(name1); - len2 = res2 ? res2 - name2 : strlen(name2); - - if (len1 == len2) - return strncmp(name1, name2, len1); - if (len1 < len2) - return strncmp(name1, name2, len1) <= 0 ? -1 : 1; - return strncmp(name1, name2, len2) >= 0 ? 1 : -1; -} - -static int load_kallsyms_compare(const void *p1, const void *p2) -{ - return compare_name(((const struct ksym *)p1)->name, ((const struct ksym *)p2)->name); -} - -static int search_kallsyms_compare(const void *p1, const struct ksym *p2) -{ - return compare_name(p1, p2->name); -} - -static int get_syms(char ***symsp, size_t *cntp, bool kernel) -{ - size_t cap = 0, cnt = 0; - char *name = NULL, *ksym_name, **syms = NULL; - struct hashmap *map; - struct ksyms *ksyms; - struct ksym *ks; - char buf[256]; - FILE *f; - int err = 0; - - ksyms = load_kallsyms_custom_local(load_kallsyms_compare); - if (!ASSERT_OK_PTR(ksyms, "load_kallsyms_custom_local")) - return -EINVAL; - - /* - * The available_filter_functions contains many duplicates, - * but other than that all symbols are usable in kprobe multi - * interface. - * Filtering out duplicates by using hashmap__add, which won't - * add existing entry. - */ - - if (access("/sys/kernel/tracing/trace", F_OK) == 0) - f = fopen("/sys/kernel/tracing/available_filter_functions", "r"); - else - f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r"); - - if (!f) - return -EINVAL; - - map = hashmap__new(symbol_hash, symbol_equal, NULL); - if (IS_ERR(map)) { - err = libbpf_get_error(map); - goto error; - } - - while (fgets(buf, sizeof(buf), f)) { - if (is_invalid_entry(buf, kernel)) - continue; - - free(name); - if (sscanf(buf, "%ms$*[^\n]\n", &name) != 1) - continue; - if (skip_entry(name)) - continue; - - ks = search_kallsyms_custom_local(ksyms, name, search_kallsyms_compare); - if (!ks) { - err = -EINVAL; - goto error; - } - - ksym_name = ks->name; - err = hashmap__add(map, ksym_name, 0); - if (err == -EEXIST) { - err = 0; - continue; - } - if (err) - goto error; - - err = libbpf_ensure_mem((void **) &syms, &cap, - sizeof(*syms), cnt + 1); - if (err) - goto error; - - syms[cnt++] = ksym_name; - } - - *symsp = syms; - *cntp = cnt; - -error: - free(name); - fclose(f); - hashmap__free(map); - if (err) - free(syms); - return err; -} - -static int get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel) -{ - unsigned long *addr, *addrs, *tmp_addrs; - int err = 0, max_cnt, inc_cnt; - char *name = NULL; - size_t cnt = 0; - char buf[256]; - FILE *f; - - if (access("/sys/kernel/tracing/trace", F_OK) == 0) - f = fopen("/sys/kernel/tracing/available_filter_functions_addrs", "r"); - else - f = fopen("/sys/kernel/debug/tracing/available_filter_functions_addrs", "r"); - - if (!f) - return -ENOENT; - - /* In my local setup, the number of entries is 50k+ so Let us initially - * allocate space to hold 64k entries. If 64k is not enough, incrementally - * increase 1k each time. - */ - max_cnt = 65536; - inc_cnt = 1024; - addrs = malloc(max_cnt * sizeof(long)); - if (addrs == NULL) { - err = -ENOMEM; - goto error; - } - - while (fgets(buf, sizeof(buf), f)) { - if (is_invalid_entry(buf, kernel)) - continue; - - free(name); - if (sscanf(buf, "%p %ms$*[^\n]\n", &addr, &name) != 2) - continue; - if (skip_entry(name)) - continue; - - if (cnt == max_cnt) { - max_cnt += inc_cnt; - tmp_addrs = realloc(addrs, max_cnt); - if (!tmp_addrs) { - err = -ENOMEM; - goto error; - } - addrs = tmp_addrs; - } - - addrs[cnt++] = (unsigned long)addr; - } - - *addrsp = addrs; - *cntp = cnt; - -error: - free(name); - fclose(f); - if (err) - free(addrs); - return err; -} - static void do_bench_test(struct kprobe_multi_empty *skel, struct bpf_kprobe_multi_opts *opts) { long attach_start_ns, attach_end_ns; @@ -670,7 +456,7 @@ static void test_kprobe_multi_bench_attach(bool kernel) char **syms = NULL; size_t cnt = 0; - if (!ASSERT_OK(get_syms(&syms, &cnt, kernel), "get_syms")) + if (!ASSERT_OK(bpf_get_ksyms(&syms, &cnt, kernel), "bpf_get_ksyms")) return; skel = kprobe_multi_empty__open_and_load(); @@ -696,13 +482,13 @@ static void test_kprobe_multi_bench_attach_addr(bool kernel) size_t cnt = 0; int err; - err = get_addrs(&addrs, &cnt, kernel); + err = bpf_get_addrs(&addrs, &cnt, kernel); if (err == -ENOENT) { test__skip(); return; } - if (!ASSERT_OK(err, "get_addrs")) + if (!ASSERT_OK(err, "bpf_get_addrs")) return; skel = kprobe_multi_empty__open_and_load(); diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 81943c6254e6..d24baf244d1f 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -17,6 +17,7 @@ #include <linux/limits.h> #include <libelf.h> #include <gelf.h> +#include "bpf/hashmap.h" #include "bpf/libbpf_internal.h" #define TRACEFS_PIPE "/sys/kernel/tracing/trace_pipe" @@ -519,3 +520,216 @@ void read_trace_pipe(void) { read_trace_pipe_iter(trace_pipe_cb, NULL, 0); } + +static size_t symbol_hash(long key, void *ctx __maybe_unused) +{ + return str_hash((const char *) key); +} + +static bool symbol_equal(long key1, long key2, void *ctx __maybe_unused) +{ + return strcmp((const char *) key1, (const char *) key2) == 0; +} + +static bool is_invalid_entry(char *buf, bool kernel) +{ + if (kernel && strchr(buf, '[')) + return true; + if (!kernel && !strchr(buf, '[')) + return true; + return false; +} + +static bool skip_entry(char *name) +{ + /* + * We attach to almost all kernel functions and some of them + * will cause 'suspicious RCU usage' when fprobe is attached + * to them. Filter out the current culprits - arch_cpu_idle + * default_idle and rcu_* functions. + */ + if (!strcmp(name, "arch_cpu_idle")) + return true; + if (!strcmp(name, "default_idle")) + return true; + if (!strncmp(name, "rcu_", 4)) + return true; + if (!strcmp(name, "bpf_dispatcher_xdp_func")) + return true; + if (!strncmp(name, "__ftrace_invalid_address__", + sizeof("__ftrace_invalid_address__") - 1)) + return true; + return false; +} + +/* Do comparison by ignoring '.llvm.<hash>' suffixes. */ +static int compare_name(const char *name1, const char *name2) +{ + const char *res1, *res2; + int len1, len2; + + res1 = strstr(name1, ".llvm."); + res2 = strstr(name2, ".llvm."); + len1 = res1 ? res1 - name1 : strlen(name1); + len2 = res2 ? res2 - name2 : strlen(name2); + + if (len1 == len2) + return strncmp(name1, name2, len1); + if (len1 < len2) + return strncmp(name1, name2, len1) <= 0 ? -1 : 1; + return strncmp(name1, name2, len2) >= 0 ? 1 : -1; +} + +static int load_kallsyms_compare(const void *p1, const void *p2) +{ + return compare_name(((const struct ksym *)p1)->name, ((const struct ksym *)p2)->name); +} + +static int search_kallsyms_compare(const void *p1, const struct ksym *p2) +{ + return compare_name(p1, p2->name); +} + +int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel) +{ + size_t cap = 0, cnt = 0; + char *name = NULL, *ksym_name, **syms = NULL; + struct hashmap *map; + struct ksyms *ksyms; + struct ksym *ks; + char buf[256]; + FILE *f; + int err = 0; + + ksyms = load_kallsyms_custom_local(load_kallsyms_compare); + if (!ksyms) + return -EINVAL; + + /* + * The available_filter_functions contains many duplicates, + * but other than that all symbols are usable to trace. + * Filtering out duplicates by using hashmap__add, which won't + * add existing entry. + */ + + if (access("/sys/kernel/tracing/trace", F_OK) == 0) + f = fopen("/sys/kernel/tracing/available_filter_functions", "r"); + else + f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r"); + + if (!f) + return -EINVAL; + + map = hashmap__new(symbol_hash, symbol_equal, NULL); + if (IS_ERR(map)) { + err = libbpf_get_error(map); + goto error; + } + + while (fgets(buf, sizeof(buf), f)) { + if (is_invalid_entry(buf, kernel)) + continue; + + free(name); + if (sscanf(buf, "%ms$*[^\n]\n", &name) != 1) + continue; + if (skip_entry(name)) + continue; + + ks = search_kallsyms_custom_local(ksyms, name, search_kallsyms_compare); + if (!ks) { + err = -EINVAL; + goto error; + } + + ksym_name = ks->name; + err = hashmap__add(map, ksym_name, 0); + if (err == -EEXIST) { + err = 0; + continue; + } + if (err) + goto error; + + err = libbpf_ensure_mem((void **) &syms, &cap, + sizeof(*syms), cnt + 1); + if (err) + goto error; + + syms[cnt++] = ksym_name; + } + + *symsp = syms; + *cntp = cnt; + +error: + free(name); + fclose(f); + hashmap__free(map); + if (err) + free(syms); + return err; +} + +int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel) +{ + unsigned long *addr, *addrs, *tmp_addrs; + int err = 0, max_cnt, inc_cnt; + char *name = NULL; + size_t cnt = 0; + char buf[256]; + FILE *f; + + if (access("/sys/kernel/tracing/trace", F_OK) == 0) + f = fopen("/sys/kernel/tracing/available_filter_functions_addrs", "r"); + else + f = fopen("/sys/kernel/debug/tracing/available_filter_functions_addrs", "r"); + + if (!f) + return -ENOENT; + + /* In my local setup, the number of entries is 50k+ so Let us initially + * allocate space to hold 64k entries. If 64k is not enough, incrementally + * increase 1k each time. + */ + max_cnt = 65536; + inc_cnt = 1024; + addrs = malloc(max_cnt * sizeof(long)); + if (addrs == NULL) { + err = -ENOMEM; + goto error; + } + + while (fgets(buf, sizeof(buf), f)) { + if (is_invalid_entry(buf, kernel)) + continue; + + free(name); + if (sscanf(buf, "%p %ms$*[^\n]\n", &addr, &name) != 2) + continue; + if (skip_entry(name)) + continue; + + if (cnt == max_cnt) { + max_cnt += inc_cnt; + tmp_addrs = realloc(addrs, max_cnt); + if (!tmp_addrs) { + err = -ENOMEM; + goto error; + } + addrs = tmp_addrs; + } + + addrs[cnt++] = (unsigned long)addr; + } + + *addrsp = addrs; + *cntp = cnt; + +error: + free(name); + fclose(f); + if (err) + free(addrs); + return err; +} diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index 2ce873c9f9aa..9437bdd4afa5 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -41,4 +41,7 @@ ssize_t get_rel_offset(uintptr_t addr); int read_build_id(const char *path, char *build_id, size_t size); +int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel); +int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel); + #endif -- 2.39.5

1 day, 22 hours

1
0
0 0

[PATCH v2 0/4] kselftest/arm64: Add coverage for the interaction of vfork() and GCS

by Mark Brown

I had cause to look at the vfork() support for GCS and realised that we don't have any direct test coverage, this series does so by adding vfork() to nolibc and then using that in basic-gcs to provide some simple vfork() coverage. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v2: - Add replacement of ifdef with if defined() in nolibc since the code doesn't reflect the coding style. - Remove check for arch specific vfork(). - Link to v1: https://lore.kernel.org/r/20250609-arm64-gcs-vfork-exit-v1-0-baad0f085747@k… --- Mark Brown (4): tools/nolibc: Replace ifdef with if defined() in sys.h tools/nolibc: Provide vfork() kselftest/arm64: Add a test for vfork() with GCS selftests/nolibc: Add coverage of vfork() tools/include/nolibc/sys.h | 57 +++++++++++++++++------- tools/testing/selftests/arm64/gcs/basic-gcs.c | 63 +++++++++++++++++++++++++++ tools/testing/selftests/nolibc/nolibc-test.c | 23 ++++++++-- 3 files changed, 124 insertions(+), 19 deletions(-) --- base-commit: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494 change-id: 20250528-arm64-gcs-vfork-exit-4a7daf7652ee Best regards, -- Mark Brown <broonie(a)kernel.org>

1 day, 23 hours

3
7
0 0

[PATCH] selftests: net: fix resource leak in napi_id_helper.c

by Malaya Kumar Rout

Resolve minor resource leaks reported by cppcheck in napi_id_helper.c cppcheck output before this patch: tools/testing/selftests/drivers/net/napi_id_helper.c:37:3: error: Resource leak: server [resourceLeak] tools/testing/selftests/drivers/net/napi_id_helper.c:46:3: error: Resource leak: server [resourceLeak] tools/testing/selftests/drivers/net/napi_id_helper.c:51:3: error: Resource leak: server [resourceLeak] tools/testing/selftests/drivers/net/napi_id_helper.c:59:3: error: Resource leak: server [resourceLeak] tools/testing/selftests/drivers/net/napi_id_helper.c:67:3: error: Resource leak: server [resourceLeak] tools/testing/selftests/drivers/net/napi_id_helper.c:76:3: error: Resource leak: server [resourceLeak] cppcheck output after this patch: No resource leaks found Signed-off-by: Malaya Kumar Rout <malayarout91(a)gmail.com> --- tools/testing/selftests/drivers/net/napi_id_helper.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/drivers/net/napi_id_helper.c b/tools/testing/selftests/drivers/net/napi_id_helper.c index eecd610c2109..1441b8d49b91 100644 --- a/tools/testing/selftests/drivers/net/napi_id_helper.c +++ b/tools/testing/selftests/drivers/net/napi_id_helper.c @@ -34,6 +34,7 @@ int main(int argc, char *argv[]) if (setsockopt(server, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt))) { perror("setsockopt"); + close(server); return 1; } @@ -43,11 +44,13 @@ int main(int argc, char *argv[]) if (bind(server, (struct sockaddr *)&address, sizeof(address)) < 0) { perror("bind failed"); + close(server); return 1; } if (listen(server, 1) < 0) { perror("listen"); + close(server); return 1; } @@ -56,6 +59,7 @@ int main(int argc, char *argv[]) client = accept(server, NULL, 0); if (client < 0) { perror("accept"); + close(server); return 1; } @@ -64,6 +68,7 @@ int main(int argc, char *argv[]) &optlen); if (ret != 0) { perror("getsockopt"); + close(server); return 1; } @@ -73,6 +78,7 @@ int main(int argc, char *argv[]) if (napi_id == 0) { fprintf(stderr, "napi ID is 0\n"); + close(server); return 1; } -- 2.43.0

2 days

5
6
0 0

[PATCH v2] selftests/kexec: fix test_kexec_jump build

by Moon Hee Lee

The test_kexec_jump program builds correctly when invoked from the top-level selftests/Makefile, which explicitly sets the OUTPUT variable. However, building directly in tools/testing/selftests/kexec fails with: make: *** No rule to make target '/test_kexec_jump', needed by 'test_kexec_jump.sh'. Stop. This failure occurs because the Makefile rule relies on $(OUTPUT), which is undefined in direct builds. Fix this by listing test_kexec_jump in TEST_GEN_PROGS, the standard way to declare generated test binaries in the kselftest framework. This ensures the binary is built regardless of invocation context and properly removed by make clean. Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Moon Hee Lee <moonhee.lee.ca(a)gmail.com> --- Changes in v2: - Dropped the .gitignore addition, as it is already handled in [1] [1] https://lore.kernel.org/r/20250623232549.3263273-1-dyudaken@gmail.com tools/testing/selftests/kexec/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kexec/Makefile b/tools/testing/selftests/kexec/Makefile index e3000ccb9a5d..874cfdd3b75b 100644 --- a/tools/testing/selftests/kexec/Makefile +++ b/tools/testing/selftests/kexec/Makefile @@ -12,7 +12,7 @@ include ../../../scripts/Makefile.arch ifeq ($(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 -- 2.43.0

2 days, 3 hours

3
2
0 0

[PATCH] global: fix misapplications of "awhile"

by Ahelenia Ziemiańska

Of these: 7 "for a while" typos 5 "take a while" typos 1 misreading of "once in a while"? 3 awhiles used correctly remain in the tree Signed-off-by: Ahelenia Ziemiańska <nabijaczleweli(a)nabijaczleweli.xyz> --- Documentation/trace/histogram.rst | 2 +- arch/sh/drivers/pci/common.c | 2 +- arch/sh/drivers/pci/pci-sh7780.c | 2 +- drivers/atm/lanai.c | 2 +- drivers/md/bcache/bcache.h | 2 +- drivers/md/bcache/request.c | 2 +- drivers/net/ethernet/google/gve/gve_rx_dqo.c | 2 +- drivers/scsi/hpsa.c | 2 +- drivers/tty/serial/jsm/jsm_neo.c | 2 +- fs/ocfs2/dlm/dlmrecovery.c | 2 +- sound/pci/emu10k1/emu10k1_main.c | 2 +- sound/pci/emu10k1/emupcm.c | 2 +- tools/testing/selftests/powerpc/tm/tm-tmspr.c | 2 +- 13 files changed, 13 insertions(+), 13 deletions(-) diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst index 0aada18c38c6..2b98c1720a54 100644 --- a/Documentation/trace/histogram.rst +++ b/Documentation/trace/histogram.rst @@ -249,7 +249,7 @@ Extended error information table, it should keep a running total of the number of bytes requested by that call_site. - We'll let it run for awhile and then dump the contents of the 'hist' + We'll let it run for a while and then dump the contents of the 'hist' file in the kmalloc event's subdirectory (for readability, a number of entries have been omitted):: diff --git a/arch/sh/drivers/pci/common.c b/arch/sh/drivers/pci/common.c index 9633b6147a05..f95004c67e6c 100644 --- a/arch/sh/drivers/pci/common.c +++ b/arch/sh/drivers/pci/common.c @@ -148,7 +148,7 @@ unsigned int pcibios_handle_status_errors(unsigned long addr, cmd |= PCI_STATUS_PARITY | PCI_STATUS_DETECTED_PARITY; - /* Now back off of the IRQ for awhile */ + /* Now back off of the IRQ for a while */ if (hose->err_irq) { disable_irq_nosync(hose->err_irq); hose->err_timer.expires = jiffies + HZ; diff --git a/arch/sh/drivers/pci/pci-sh7780.c b/arch/sh/drivers/pci/pci-sh7780.c index 9a624a6ee354..f41d6939a3d9 100644 --- a/arch/sh/drivers/pci/pci-sh7780.c +++ b/arch/sh/drivers/pci/pci-sh7780.c @@ -153,7 +153,7 @@ static irqreturn_t sh7780_pci_serr_irq(int irq, void *dev_id) /* Deassert SERR */ __raw_writel(SH4_PCIINTM_SDIM, hose->reg_base + SH4_PCIINTM); - /* Back off the IRQ for awhile */ + /* Back off the IRQ for a while */ disable_irq_nosync(irq); hose->serr_timer.expires = jiffies + HZ; add_timer(&hose->serr_timer); diff --git a/drivers/atm/lanai.c b/drivers/atm/lanai.c index 2a1fe3080712..0dfa2cdc897c 100644 --- a/drivers/atm/lanai.c +++ b/drivers/atm/lanai.c @@ -755,7 +755,7 @@ static void lanai_shutdown_rx_vci(const struct lanai_vcc *lvcc) /* Shutdown transmitting on card. * Unfortunately the lanai needs us to wait until all the data * drains out of the buffer before we can dealloc it, so this - * can take awhile -- up to 370ms for a full 128KB buffer + * can take a while -- up to 370ms for a full 128KB buffer * assuming everone else is quiet. In theory the time is * boundless if there's a CBR VCC holding things up. */ diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 1d33e40d26ea..7318d9800370 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -499,7 +499,7 @@ struct gc_stat { * won't automatically reattach). * * CACHE_SET_STOPPING always gets set first when we're closing down a cache set; - * we'll continue to run normally for awhile with CACHE_SET_STOPPING set (i.e. + * we'll continue to run normally for a while with CACHE_SET_STOPPING set (i.e. * flushing dirty data). * * CACHE_SET_RUNNING means all cache devices have been registered and journal diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index af345dc6fde1..87b4341cb42c 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -257,7 +257,7 @@ static CLOSURE_CALLBACK(bch_data_insert_start) /* * But if it's not a writeback write we'd rather just bail out if - * there aren't any buckets ready to write to - it might take awhile and + * there aren't any buckets ready to write to - it might take a while and * we might be starving btree writes for gc or something. */ diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index dcb0545baa50..6a0be54f1c81 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -608,7 +608,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, buf_len = compl_desc->packet_len; hdr_len = compl_desc->header_len; - /* Page might have not been used for awhile and was likely last written + /* Page might have not been used for a while and was likely last written * by a different thread. */ if (rx->dqo.page_pool) { diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index c73a71ac3c29..0066f15153a7 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -7795,7 +7795,7 @@ static int hpsa_wait_for_mode_change_ack(struct ctlr_info *h) u32 doorbell_value; unsigned long flags; - /* under certain very rare conditions, this can take awhile. + /* under certain very rare conditions, this can take a while. * (e.g.: hot replace a failed 144GB drive in a RAID 5 set right * as we enter this code.) */ diff --git a/drivers/tty/serial/jsm/jsm_neo.c b/drivers/tty/serial/jsm/jsm_neo.c index e8e13bf056e2..2eb9ff26d6e8 100644 --- a/drivers/tty/serial/jsm/jsm_neo.c +++ b/drivers/tty/serial/jsm/jsm_neo.c @@ -1189,7 +1189,7 @@ static irqreturn_t neo_intr(int irq, void *voidbrd) /* * The UART triggered us with a bogus interrupt type. * It appears the Exar chip, when REALLY bogged down, will throw - * these once and awhile. + * these periodically. * Its harmless, just ignore it and move on. */ jsm_dbg(INTR, &brd->pci_dev, diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 67fc62a49a76..00f52812dbb0 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -2632,7 +2632,7 @@ static int dlm_pick_recovery_master(struct dlm_ctxt *dlm) dlm_reco_master_ready(dlm), msecs_to_jiffies(1000)); if (!dlm_reco_master_ready(dlm)) { - mlog(0, "%s: reco master taking awhile\n", + mlog(0, "%s: reco master taking a while\n", dlm->name); goto again; } diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c index bbe252b8916c..6050201851b1 100644 --- a/sound/pci/emu10k1/emu10k1_main.c +++ b/sound/pci/emu10k1/emu10k1_main.c @@ -606,7 +606,7 @@ static int snd_emu10k1_ecard_init(struct snd_emu10k1 *emu) /* Step 2: Calibrate the ADC and DAC */ snd_emu10k1_ecard_write(emu, EC_DACCAL | EC_LEDN | EC_TRIM_CSN); - /* Step 3: Wait for awhile; XXX We can't get away with this + /* Step 3: Wait for a while; XXX We can't get away with this * under a real operating system; we'll need to block and wait that * way. */ snd_emu10k1_wait(emu, 48000); diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c index 1bf6e3d652f8..ca4b03317539 100644 --- a/sound/pci/emu10k1/emupcm.c +++ b/sound/pci/emu10k1/emupcm.c @@ -991,7 +991,7 @@ static snd_pcm_uframes_t snd_emu10k1_capture_pointer(struct snd_pcm_substream *s if (!epcm->running) return 0; if (epcm->first_ptr) { - udelay(50); /* hack, it takes awhile until capture is started */ + udelay(50); /* hack, it takes a while until capture is started */ epcm->first_ptr = 0; } ptr = snd_emu10k1_ptr_read(emu, epcm->capture_idx_reg, 0) & 0x0000ffff; diff --git a/tools/testing/selftests/powerpc/tm/tm-tmspr.c b/tools/testing/selftests/powerpc/tm/tm-tmspr.c index dd5ddffa28b7..0d64988ffb40 100644 --- a/tools/testing/selftests/powerpc/tm/tm-tmspr.c +++ b/tools/testing/selftests/powerpc/tm/tm-tmspr.c @@ -14,7 +14,7 @@ * (1) create more threads than cpus * (2) in each thread: * (a) set TFIAR and TFHAR a unique value - * (b) loop for awhile, continually checking to see if + * (b) loop for a while, continually checking to see if * either register has been corrupted. * * (3) Loop: -- 2.39.5

2 days, 4 hours

2
1
0 0

[PATCH v11 net-next 00/15] AccECN protocol patch series

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find the v10 AccECN protocol patch series, which covers the core functionality of Accurate ECN, AccECN negotiation, AccECN TCP options, and AccECN failure handling. The Accurate ECN draft can be found in https://datatracker.ietf.org/doc/html/draft-ietf-tcpm-accurate-ecn-28 This patch series is part of the full AccECN patch series, which is available at https://github.com/L4STeam/linux-net-next/commits/upstream_l4steam/ Best Regards, Chia-Yu --- v11 (04-Jul-2025) - Fix compilation issue of some intermediate patches in v10 v10 (03-Jul-2025) - Add new patch of separated header file include/net/tcp_ecn.h to include ECN and AccECN functions (Eric Dumazet <edumazet(a)google.com>) - Add comments on the AccECN helper functions in tcp_ecn.h (Eric Dumazet <edumazet(a)google.com>) - Add documentation of tcp_ecn, tcp_ecn_option, tcp_ecn_beacon in ip-sysctl.rst to the corresponding patch (Eric Dumazet <edumazet(a)google.com>) - Split wait third ACK functionality into a separated patch from AccECN negotiation patch (Eric Dumazet <edumazet(a)google.com>) - Add READ_ONCE() over every reads of sysctl for all patches in the series (Eric Dumazet <edumazet(a)google.com>) - Merge heuristics of AccECN option ceb/cep and ACE field multi-wrap into a single patch - Add a table of SACK block reduction and required AccECN field in patch #15 commit message (Eric Dumazet <edumazet(a)google.com>) v9 (21-Jun-2025) - Use tcp_data_ecn_check() to set TCP_ECN_SEE flag only for RFC3168 ECN (Paolo Abeni <pabeni(a)redhat.com>) - Add comments about setting TCP_ECN_SEEN flag for RFC3168 and Accruate ECN (Paolo Abeni <pabeni(a)redhat.com>) - Restruct the code in the for loop of tcp_accecn_process_option() (Paolo Abeni <pabeni(a)redhat.com>) - Remove ecn_bytes and add use_synack_ecn_bytes flag to identify whether syn_ack_bytes or received_ecn_bytes is used (Paolo Abeni <pabeni(a)redhat.com>) - Replace leftover_bytes and leftover_size with leftover_highbyte and leftover_lowbyte and add comments in tcp_options_write() (Paolo Abeni <pabeni(a)redhat.com>) - Add comments and commit message about the 1st retx SYN still attempt AccECN negotiation (Paolo Abeni <pabeni(a)redhat.com>) v8 (10-Jun-2025) - Add new helper function tcp_ecn_received_counters_payload() in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Set opts->num_sack_blocks=0 to avoid potential undefined value in #8 (Paolo Abeni <pabeni(a)redhat.com>) - Reset leftover_size to 2 once leftover_bytes is used in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_opt_demand_min() in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_saw_opt_fail_recv() in #11 (Paolo Abeni <pabeni(a)redhat.com>) - Update tcp_options_fit_accecn() to avoid using recursion in #14 (Paolo Abeni <pabeni(a)redhat.com>) v7 (14-May-2025) - Modify group sizes of tcp_sock_write_txrx and tcp_sock_write_rx in #3 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Fix the issue in #4 and #5 where the RFC3168 ECN behavior in tcp_ecn_send() is changed (Paolo Abeni <pabeni(a)redhat.com>) - Modify group size of tcp_sock_write_txrx in #4 and #6 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Update commit message for #9 to explain the increase in tcp_sock_write_rx group size - Modify group size of tcp_sock_write_tx in #10 based on pahole results v6 (09-May-2025) - Add #3 to utilize exisintg holes of tcp_sock_write_txrx group for later patches (#4, #9, #10) with new u8 members (Paolo Abeni <pabeni(a)redhat.com>) - Add pahole outcomes before and after commit in #4, #5, #6, #9, #10, #15 (Paolo Abeni <pabeni(a)redhat.com>) - Define new helper function tcp_send_ack_reflect_ect() for sending ACK with reflected ECT in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add comments for function tcp_ecn_rcv_synack() in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add enum/define to be used by sysctl_tcp_ecn in #5, sysctl_tcp_ecn_option in #9, and sysctl_tcp_ecn_option_beacon in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move accecn_fail_mode and saw_accecn_opt in #5 and #11 to use exisintg holes of tcp_sock (Paolo Abeni <pabeni(a)redhat.com>) - Change data type of new members of tcp_request_sock and move them to the end of struct in #5 and #11 (Paolo Abeni <pabeni(a)redhat.com>) - Move new members of tcp_info to the end of struct in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Merge previous #7 into #9 (Paolo Abeni <pabeni(a)redhat.com>) - Mask ecnfield with INET_ECN_MASK to remove WARN_ONCE in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Reduce the indentation levels for reabability in #9 and #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move delivered_ecn_bytes to the RX group in #9, accecn_opt_tstamp to the TX group in #10, pkts_acked_ewma to the RX group in #15 (Paolo Abeni <pabeni(a)redhat.com>) - Add changes in Documentation/networking/net_cachelines/tcp_sock.rst for new tcp_sock members in #3, #5, #6, #9, #10, #15 v5 (22-Apr-2025) - Further fix for 32-bit ARM alignment in tcp.c (Simon Horman <horms(a)kernel.org>) v4 (18-Apr-2025) - Fix 32-bit ARM assertion for alignment requirement (Simon Horman <horms(a)kernel.org>) v3 (14-Apr-2025) - Fix patch apply issue in v2 (Jakub Kicinski <kuba(a)kernel.org>) v2 (18-Mar-2025) - Add one missing patch from the previous AccECN protocol preparation patch series to this patch series. --- Chia-Yu Chang (6): tcp: reorganize tcp_sock_write_txrx group for variables later tcp: ecn functions in separated include file tcp: Add wait_third_ack flag for ECN negotiation in simultaneous connect tcp: accecn: AccECN option send control tcp: accecn: AccECN option failure handling tcp: accecn: try to fit AccECN option with SACK Ilpo Järvinen (9): tcp: reorganize SYN ECN code tcp: fast path functions later tcp: AccECN core tcp: accecn: AccECN negotiation tcp: accecn: add AccECN rx byte counters tcp: accecn: AccECN needs to know delivered bytes tcp: sack option handling improvements tcp: accecn: AccECN option tcp: accecn: AccECN option ceb/cep and ACE field multi-wrap heuristics Documentation/networking/ip-sysctl.rst | 55 +- .../networking/net_cachelines/tcp_sock.rst | 13 + include/linux/tcp.h | 33 +- include/net/netns/ipv4.h | 2 + include/net/tcp.h | 87 ++- include/net/tcp_ecn.h | 648 ++++++++++++++++++ include/uapi/linux/tcp.h | 7 + net/ipv4/syncookies.c | 4 + net/ipv4/sysctl_net_ipv4.c | 19 + net/ipv4/tcp.c | 29 +- net/ipv4/tcp_input.c | 371 ++++++++-- net/ipv4/tcp_ipv4.c | 8 +- net/ipv4/tcp_minisocks.c | 40 +- net/ipv4/tcp_output.c | 297 ++++++-- net/ipv6/syncookies.c | 2 + net/ipv6/tcp_ipv6.c | 1 + 16 files changed, 1429 insertions(+), 187 deletions(-) create mode 100644 include/net/tcp_ecn.h -- 2.34.1

2 days, 5 hours

1
15
0 0

[PATCH v3] selftests/mm: add process_madvise() tests

by wang lian

Add tests for process_madvise(), focusing on verifying behavior under various conditions including valid usage and error cases. Signed-off-by: wang lian <lianux.mm(a)gmail.com> Suggested-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Suggested-by: David Hildenbrand <david(a)redhat.com> Acked-by: SeongJae Park <sj(a)kernel.org> --- Changelog v3: - Rebased onto the latest mm-stable branch to ensure clean application. - Refactor common signal handling logic into vm_util to reduce code duplication. - Improve test robustness and diagnostics based on community feedback. - Address minor code style and script corrections. Changelog v2: - Drop MADV_DONTNEED tests based on feedback. - Focus solely on process_madvise() syscall. - Improve error handling and structure. - Add future-proof flag test. - Style and comment cleanups. tools/testing/selftests/mm/.gitignore | 1 + tools/testing/selftests/mm/Makefile | 1 + tools/testing/selftests/mm/guard-regions.c | 51 --- tools/testing/selftests/mm/process_madv.c | 358 +++++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 5 + tools/testing/selftests/mm/vm_util.c | 35 ++ tools/testing/selftests/mm/vm_util.h | 22 ++ 7 files changed, 422 insertions(+), 51 deletions(-) create mode 100644 tools/testing/selftests/mm/process_madv.c diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 824266982aa3..95bd9c6ead9e 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -25,6 +25,7 @@ pfnmap protection_keys protection_keys_32 protection_keys_64 +process_madv madv_populate uffd-stress uffd-unit-tests diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index ae6f994d3add..d13b3cef2a2b 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -85,6 +85,7 @@ TEST_GEN_FILES += mseal_test TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += pagemap_ioctl TEST_GEN_FILES += pfnmap +TEST_GEN_FILES += process_madv TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += uffd-stress diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c index 93af3d3760f9..4cf101b0fe5e 100644 --- a/tools/testing/selftests/mm/guard-regions.c +++ b/tools/testing/selftests/mm/guard-regions.c @@ -9,8 +9,6 @@ #include <linux/limits.h> #include <linux/userfaultfd.h> #include <linux/fs.h> -#include <setjmp.h> -#include <signal.h> #include <stdbool.h> #include <stdio.h> #include <stdlib.h> @@ -24,24 +22,6 @@ #include "../pidfd/pidfd.h" -/* - * Ignore the checkpatch warning, as per the C99 standard, section 7.14.1.1: - * - * "If the signal occurs other than as the result of calling the abort or raise - * function, the behavior is undefined if the signal handler refers to any - * object with static storage duration other than by assigning a value to an - * object declared as volatile sig_atomic_t" - */ -static volatile sig_atomic_t signal_jump_set; -static sigjmp_buf signal_jmp_buf; - -/* - * Ignore the checkpatch warning, we must read from x but don't want to do - * anything with it in order to trigger a read page fault. We therefore must use - * volatile to stop the compiler from optimising this away. - */ -#define FORCE_READ(x) (*(volatile typeof(x) *)x) - /* * How is the test backing the mapping being tested? */ @@ -120,14 +100,6 @@ static int userfaultfd(int flags) return syscall(SYS_userfaultfd, flags); } -static void handle_fatal(int c) -{ - if (!signal_jump_set) - return; - - siglongjmp(signal_jmp_buf, c); -} - static ssize_t sys_process_madvise(int pidfd, const struct iovec *iovec, size_t n, int advice, unsigned int flags) { @@ -180,29 +152,6 @@ static bool try_read_write_buf(char *ptr) return try_read_buf(ptr) && try_write_buf(ptr); } -static void setup_sighandler(void) -{ - struct sigaction act = { - .sa_handler = &handle_fatal, - .sa_flags = SA_NODEFER, - }; - - sigemptyset(&act.sa_mask); - if (sigaction(SIGSEGV, &act, NULL)) - ksft_exit_fail_perror("sigaction"); -} - -static void teardown_sighandler(void) -{ - struct sigaction act = { - .sa_handler = SIG_DFL, - .sa_flags = SA_NODEFER, - }; - - sigemptyset(&act.sa_mask); - sigaction(SIGSEGV, &act, NULL); -} - static int open_file(const char *prefix, char *path) { int fd; diff --git a/tools/testing/selftests/mm/process_madv.c b/tools/testing/selftests/mm/process_madv.c new file mode 100644 index 000000000000..3d26105b4781 --- /dev/null +++ b/tools/testing/selftests/mm/process_madv.c @@ -0,0 +1,358 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#define _GNU_SOURCE +#include "../kselftest_harness.h" +#include <errno.h> +#include <setjmp.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <sched.h> +#include <sys/pidfd.h> +#include "vm_util.h" + +#include "../pidfd/pidfd.h" + +FIXTURE(process_madvise) +{ + int pidfd; + int flag; +}; + +FIXTURE_SETUP(process_madvise) +{ + self->pidfd = PIDFD_SELF; + self->flag = 0; + setup_sighandler(); +}; + +FIXTURE_TEARDOWN(process_madvise) +{ + teardown_sighandler(); +} + +static ssize_t sys_process_madvise(int pidfd, const struct iovec *iovec, + size_t vlen, int advice, unsigned int flags) +{ + return syscall(__NR_process_madvise, pidfd, iovec, vlen, advice, flags); +} + +/* + * Enable our signal catcher and try to read the specified buffer. The + * return value indicates whether the read succeeds without a fatal + * signal. + */ +static bool try_read_buf(char *ptr) +{ + bool failed; + + /* Tell signal handler to jump back here on fatal signal. */ + signal_jump_set = true; + /* If a fatal signal arose, we will jump back here and failed is set. */ + failed = sigsetjmp(signal_jmp_buf, 0) != 0; + + if (!failed) + FORCE_READ(ptr); + + signal_jump_set = false; + return !failed; +} + +TEST_F(process_madvise, basic) +{ + const unsigned long pagesize = (unsigned long)sysconf(_SC_PAGESIZE); + const int madvise_pages = 4; + char *map; + ssize_t ret; + struct iovec vec[madvise_pages]; + + /* + * Create a single large mapping. We will pick pages from this + * mapping to advise on. This ensures we test non-contiguous iovecs. + */ + map = mmap(NULL, pagesize * 10, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (map == MAP_FAILED) + ksft_exit_skip("mmap failed, not enough memory.\n"); + + /* Fill the entire region with a known pattern. */ + memset(map, 'A', pagesize * 10); + + /* + * Setup the iovec to point to 4 non-contiguous pages + * within the mapping. + */ + vec[0].iov_base = &map[0 * pagesize]; + vec[0].iov_len = pagesize; + vec[1].iov_base = &map[3 * pagesize]; + vec[1].iov_len = pagesize; + vec[2].iov_base = &map[5 * pagesize]; + vec[2].iov_len = pagesize; + vec[3].iov_base = &map[8 * pagesize]; + vec[3].iov_len = pagesize; + + ret = sys_process_madvise(PIDFD_SELF, vec, madvise_pages, MADV_DONTNEED, + 0); + if (ret == -1 && errno == EPERM) + ksft_exit_skip( + "process_madvise() unsupported or permission denied, try running as root.\n"); + else if (errno == EINVAL) + ksft_exit_skip( + "process_madvise() unsupported or parameter invalid, please check arguments.\n"); + + /* The call should succeed and report the total bytes processed. */ + ASSERT_EQ(ret, madvise_pages * pagesize); + + /* Check that advised pages are now zero. */ + for (int i = 0; i < madvise_pages; i++) { + char *advised_page = (char *)vec[i].iov_base; + + /* Access should be successful (kernel provides a new page). */ + ASSERT_TRUE(try_read_buf(advised_page)); + /* Content must be 0, not 'A'. */ + ASSERT_EQ(*advised_page, 0); + } + + /* Check that an un-advised page in between is still 'A'. */ + char *unadvised_page = &map[1 * pagesize]; + + ASSERT_TRUE(try_read_buf(unadvised_page)); + for (int i = 0; i < pagesize; i++) + ASSERT_EQ(unadvised_page[i], 'A'); + + /* Cleanup. */ + ASSERT_EQ(munmap(map, pagesize * 10), 0); +} + +static long get_smaps_anon_huge_pages(pid_t pid, void *addr) +{ + char smaps_path[64]; + char *line = NULL; + unsigned long start, end; + long anon_huge_kb; + size_t len; + FILE *f; + bool in_vma; + + in_vma = false; + snprintf(smaps_path, sizeof(smaps_path), "/proc/%d/smaps", pid); + f = fopen(smaps_path, "r"); + if (!f) + return -1; + + while (getline(&line, &len, f) != -1) { + /* Check if the line describes a VMA range */ + if (sscanf(line, "%lx-%lx", &start, &end) == 2) { + if ((unsigned long)addr >= start && + (unsigned long)addr < end) + in_vma = true; + else + in_vma = false; + continue; + } + + /* If we are in the correct VMA, look for the AnonHugePages field */ + if (in_vma && + sscanf(line, "AnonHugePages: %ld kB", &anon_huge_kb) == 1) + break; + } + + free(line); + fclose(f); + + return (anon_huge_kb > 0) ? (anon_huge_kb * 1024) : 0; +} + +/** + * TEST_F(process_madvise, remote_collapse) + * + * This test deterministically validates process_madvise() with MADV_COLLAPSE + * on a remote process, other advices are difficult to verify reliably. + * + * The test verifies that a memory region in a child process, initially + * backed by small pages, can be collapsed into a Transparent Huge Page by a + * request from the parent. The result is verified by parsing the child's + * /proc/<pid>/smaps file. + */ +TEST_F(process_madvise, remote_collapse) +{ + const unsigned long pagesize = (unsigned long)sysconf(_SC_PAGESIZE); + pid_t child_pid; + int pidfd; + long huge_page_size; + int pipe_info[2]; + ssize_t ret; + struct iovec vec; + + struct child_info { + pid_t pid; + void *map_addr; + } info; + + huge_page_size = default_huge_page_size(); + if (huge_page_size <= 0) + ksft_exit_skip("Could not determine a valid huge page size.\n"); + + ASSERT_EQ(pipe(pipe_info), 0); + + child_pid = fork(); + ASSERT_NE(child_pid, -1); + + if (child_pid == 0) { + char *map; + size_t map_size = 2 * huge_page_size; + + close(pipe_info[0]); + + map = mmap(NULL, map_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(map, MAP_FAILED); + + /* Fault in as small pages */ + for (size_t i = 0; i < map_size; i += pagesize) + map[i] = 'A'; + + /* Send info and pause */ + info.pid = getpid(); + info.map_addr = map; + ret = write(pipe_info[1], &info, sizeof(info)); + ASSERT_EQ(ret, sizeof(info)); + close(pipe_info[1]); + + pause(); + exit(0); + } + + close(pipe_info[1]); + + /* Receive child info */ + ret = read(pipe_info[0], &info, sizeof(info)); + if (ret <= 0) { + waitpid(child_pid, NULL, 0); + ksft_exit_skip("Failed to read child info from pipe.\n"); + } + ASSERT_EQ(ret, sizeof(info)); + close(pipe_info[0]); + child_pid = info.pid; + + pidfd = pidfd_open(child_pid, 0); + ASSERT_GE(pidfd, 0); + + /* Baseline Check from Parent's perspective */ + ASSERT_EQ(get_smaps_anon_huge_pages(child_pid, info.map_addr), 0); + + vec.iov_base = info.map_addr; + vec.iov_len = huge_page_size; + ret = sys_process_madvise(pidfd, &vec, 1, MADV_COLLAPSE, 0); + if (ret == -1) { + if (errno == EINVAL) + ksft_exit_skip( + "PROCESS_MADV_ADVISE is not supported.\n"); + else if (errno == EPERM) + ksft_exit_skip( + "No process_madvise() permissions, try running as root.\n"); + goto cleanup; + } + ASSERT_EQ(ret, huge_page_size); + + ASSERT_EQ(get_smaps_anon_huge_pages(child_pid, info.map_addr), + huge_page_size); + + ksft_test_result_pass( + "MADV_COLLAPSE successfully verified via smaps.\n"); + +cleanup: + /* Cleanup */ + kill(child_pid, SIGKILL); + waitpid(child_pid, NULL, 0); + if (pidfd >= 0) + close(pidfd); +} + +/* + * Test process_madvise() with various invalid pidfds to ensure correct error + * handling. This includes negative fds, non-pidfd fds, and pidfds for + * processes that no longer exist. + */ +TEST_F(process_madvise, invalid_pidfd) +{ + struct iovec vec; + pid_t child_pid; + ssize_t ret; + int pidfd; + + vec.iov_base = (void *)0x1234; + vec.iov_len = 4096; + + /* Using an invalid fd number (-1) should fail with EBADF. */ + ret = sys_process_madvise(-1, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EBADF); + + /* + * Using a valid fd that is not a pidfd (e.g. stdin) should fail + * with EBADF. + */ + ret = sys_process_madvise(STDIN_FILENO, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EBADF); + + /* + * Using a pidfd for a process that has already exited should fail + * with ESRCH. + */ + child_pid = fork(); + ASSERT_NE(child_pid, -1); + + if (child_pid == 0) + exit(0); + + pidfd = pidfd_open(child_pid, 0); + ASSERT_GE(pidfd, 0); + + /* Wait for the child to ensure it has terminated. */ + waitpid(child_pid, NULL, 0); + + ret = sys_process_madvise(pidfd, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ESRCH); + close(pidfd); +} + +/* + * Test process_madvise() with an invalid flag value. Now we only support flag=0 + * future we will use it support sync so reserve this test. + */ +TEST_F(process_madvise, flag) +{ + const unsigned long pagesize = (unsigned long)sysconf(_SC_PAGESIZE); + unsigned int invalid_flag; + struct iovec vec; + char *map; + ssize_t ret; + + map = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, + 0); + if (map == MAP_FAILED) + ksft_exit_skip("mmap failed, not enough memory.\n"); + + vec.iov_base = map; + vec.iov_len = pagesize; + + invalid_flag = 0x80000000; + + ret = sys_process_madvise(PIDFD_SELF, &vec, 1, MADV_DONTNEED, + invalid_flag); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); + + /* Cleanup. */ + ASSERT_EQ(munmap(map, pagesize), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index dddd1dd8af14..84fb51902c3e 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -65,6 +65,8 @@ separated by spaces: test pagemap_scan IOCTL - pfnmap tests for VM_PFNMAP handling +- process_madv + test process_madvise - cow test copy-on-write semantics - thp @@ -422,6 +424,9 @@ CATEGORY="hmm" run_test bash ./test_hmm.sh smoke # MADV_GUARD_INSTALL and MADV_GUARD_REMOVE tests CATEGORY="madv_guard" run_test ./guard-regions +# PROCESS_MADVISE TEST +CATEGORY="process_madv" run_test ./process_madv + # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 5492e3f784df..85b209260e5a 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -20,6 +20,9 @@ unsigned int __page_size; unsigned int __page_shift; +volatile sig_atomic_t signal_jump_set; +sigjmp_buf signal_jmp_buf; + uint64_t pagemap_get_entry(int fd, char *start) { const unsigned long pfn = (unsigned long)start / getpagesize(); @@ -524,3 +527,35 @@ int read_sysfs(const char *file_path, unsigned long *val) return 0; } + +static void handle_fatal(int c) +{ + if (!signal_jump_set) + return; + + siglongjmp(signal_jmp_buf, c); +} + +void setup_sighandler(void) +{ + struct sigaction act = { + .sa_handler = &handle_fatal, + .sa_flags = SA_NODEFER, + }; + + sigemptyset(&act.sa_mask); + if (sigaction(SIGSEGV, &act, NULL)) + ksft_exit_fail_perror("sigaction in setup"); +} + +void teardown_sighandler(void) +{ + struct sigaction act = { + .sa_handler = SIG_DFL, + .sa_flags = SA_NODEFER, + }; + + sigemptyset(&act.sa_mask); + if (sigaction(SIGSEGV, &act, NULL)) + ksft_exit_fail_perror("sigaction in teardown"); +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index b8136d12a0f8..6bc4177a2807 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -8,6 +8,8 @@ #include <unistd.h> /* _SC_PAGESIZE */ #include "../kselftest.h" #include <linux/fs.h> +#include <setjmp.h> +#include <signal.h> #define BIT_ULL(nr) (1ULL << (nr)) #define PM_SOFT_DIRTY BIT_ULL(55) @@ -61,6 +63,24 @@ static inline void skip_test_dodgy_fs(const char *op_name) ksft_test_result_skip("%s failed with ENOENT. Filesystem might be buggy (9pfs?)\n", op_name); } +/* + * Ignore the checkpatch warning, as per the C99 standard, section 7.14.1.1: + * + * "If the signal occurs other than as the result of calling the abort or raise + * function, the behavior is undefined if the signal handler refers to any + * object with static storage duration other than by assigning a value to an + * object declared as volatile sig_atomic_t" + */ +extern volatile sig_atomic_t signal_jump_set; +extern sigjmp_buf signal_jmp_buf; + +/* + * Ignore the checkpatch warning, we must read from x but don't want to do + * anything with it in order to trigger a read page fault. We therefore must use + * volatile to stop the compiler from optimising this away. + */ +#define FORCE_READ(x) (*(volatile typeof(x) *)x) + uint64_t pagemap_get_entry(int fd, char *start); bool pagemap_is_softdirty(int fd, char *start); bool pagemap_is_swapped(int fd, char *start); @@ -90,6 +110,8 @@ bool find_vma_procmap(struct procmap_fd *procmap, void *address); int close_procmap(struct procmap_fd *procmap); int write_sysfs(const char *file_path, unsigned long val); int read_sysfs(const char *file_path, unsigned long *val); +void setup_sighandler(void); +void teardown_sighandler(void); static inline int open_self_procmap(struct procmap_fd *procmap_out) { -- 2.43.0

2 days, 5 hours

1
0
0 0

[PATCH v6 14/14] selftests/sched_ext: Add test for DL server total_bw consistency

by Joel Fernandes

Add a new kselftest to verify that the total_bw value in /sys/kernel/debug/sched/debug remains consistent across all CPUs under different sched_ext BPF program states: 1. Before a BPF scheduler is loaded 2. While a BPF scheduler is loaded and active 3. After a BPF scheduler is unloaded The test runs CPU stress threads to ensure DL server bandwidth values stabilize before checking consistency. This helps catch potential issues with DL server bandwidth accounting during sched_ext transitions. Signed-off-by: Joel Fernandes <joelagnelf(a)nvidia.com> --- tools/testing/selftests/sched_ext/Makefile | 1 + tools/testing/selftests/sched_ext/total_bw.c | 286 +++++++++++++++++++ 2 files changed, 287 insertions(+) create mode 100644 tools/testing/selftests/sched_ext/total_bw.c diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index f0a8cba3a99f..d48be158b0a1 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -184,6 +184,7 @@ auto-test-targets := \ select_cpu_vtime \ rt_stall \ test_example \ + total_bw \ testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets))) diff --git a/tools/testing/selftests/sched_ext/total_bw.c b/tools/testing/selftests/sched_ext/total_bw.c new file mode 100644 index 000000000000..6b81d6c51054 --- /dev/null +++ b/tools/testing/selftests/sched_ext/total_bw.c @@ -0,0 +1,286 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test to verify that total_bw value remains consistent across all CPUs + * in different BPF program states. + * + * Copyright (C) 2025 Nvidia Corporation. + */ +#include <bpf/bpf.h> +#include <errno.h> +#include <pthread.h> +#include <scx/common.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/wait.h> +#include <unistd.h> +#include "minimal.bpf.skel.h" +#include "scx_test.h" + +#define MAX_CPUS 512 +#define STABILIZATION_TIME_SEC 5 +#define STRESS_DURATION_SEC 5 + +struct total_bw_ctx { + struct minimal *skel; + long baseline_bw[MAX_CPUS]; + int nr_cpus; +}; + +static void *cpu_stress_thread(void *arg) +{ + volatile int i; + time_t end_time = time(NULL) + STRESS_DURATION_SEC; + + while (time(NULL) < end_time) { + for (i = 0; i < 1000000; i++); + } + + return NULL; +} + +/* + * The first enqueue on a CPU causes the DL server to start, for that + * reason run stressor threads in the hopes it schedules on all CPUs. + */ +static int run_cpu_stress(int nr_cpus) +{ + pthread_t *threads; + int i, ret = 0; + + threads = calloc(nr_cpus, sizeof(pthread_t)); + if (!threads) + return -ENOMEM; + + /* Create threads to run on each CPU */ + for (i = 0; i < nr_cpus; i++) { + if (pthread_create(&threads[i], NULL, cpu_stress_thread, NULL)) { + ret = -errno; + fprintf(stderr, "Failed to create thread %d: %s\n", i, strerror(-ret)); + break; + } + } + + /* Wait for all threads to complete */ + for (i = 0; i < nr_cpus; i++) { + if (threads[i]) + pthread_join(threads[i], NULL); + } + + free(threads); + return ret; +} + +static int read_total_bw_values(long *bw_values, int max_cpus) +{ + FILE *fp; + char line[256]; + int cpu_count = 0; + + fp = fopen("/sys/kernel/debug/sched/debug", "r"); + if (!fp) { + SCX_ERR("Failed to open debug file"); + return -1; + } + + while (fgets(line, sizeof(line), fp)) { + char *bw_str = strstr(line, "total_bw"); + if (bw_str) { + bw_str = strchr(bw_str, ':'); + if (bw_str) { + /* Only store up to max_cpus values */ + if (cpu_count < max_cpus) { + bw_values[cpu_count] = atol(bw_str + 1); + } + cpu_count++; + } + } + } + + fclose(fp); + return cpu_count; +} + +static bool verify_total_bw_consistency(long *bw_values, int count) +{ + int i; + long first_value; + + if (count <= 0) + return false; + + first_value = bw_values[0]; + + for (i = 1; i < count; i++) { + if (bw_values[i] != first_value) { + SCX_ERR("Inconsistent total_bw: CPU0=%ld, CPU%d=%ld", + first_value, i, bw_values[i]); + return false; + } + } + + return true; +} + +static int fetch_verify_total_bw(long *bw_values, int nr_cpus) +{ + int attempts = 0; + int max_attempts = 10; + int count; + + /* + * The first enqueue on a CPU causes the DL server to start, for that + * reason run stressor threads in the hopes it schedules on all CPUs. + */ + if (run_cpu_stress(nr_cpus) < 0) { + SCX_ERR("Failed to run CPU stress"); + return -1; + } + + /* Let things settle down */ + sleep(STABILIZATION_TIME_SEC); + + /* Try multiple times to get stable values */ + while (attempts < max_attempts) { + count = read_total_bw_values(bw_values, nr_cpus); + fprintf(stderr, "Read %d total_bw values (testing %d CPUs)\n", count, nr_cpus); + /* If system has more CPUs than we're testing, that's OK */ + if (count < nr_cpus) { + SCX_ERR("Expected at least %d CPUs, got %d", nr_cpus, count); + attempts++; + sleep(1); + continue; + } + + /* Only verify the CPUs we're testing */ + if (verify_total_bw_consistency(bw_values, nr_cpus)) { + fprintf(stderr, "Values are consistent: %ld\n", bw_values[0]); + return 0; + } + + attempts++; + sleep(1); + } + + return -1; +} + +static enum scx_test_status setup(void **ctx) +{ + struct total_bw_ctx *test_ctx; + + if (access("/sys/kernel/debug/sched/debug", R_OK) != 0) { + fprintf(stderr, "Skipping test: debugfs sched/debug not accessible\n"); + return SCX_TEST_SKIP; + } + + test_ctx = calloc(1, sizeof(*test_ctx)); + if (!test_ctx) + return SCX_TEST_FAIL; + + test_ctx->nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + if (test_ctx->nr_cpus <= 0) { + free(test_ctx); + return SCX_TEST_FAIL; + } + + /* If system has more CPUs than MAX_CPUS, just test the first MAX_CPUS */ + if (test_ctx->nr_cpus > MAX_CPUS) { + test_ctx->nr_cpus = MAX_CPUS; + } + + /* Test scenario 1: BPF program not loaded */ + /* Read and verify baseline total_bw before loading BPF program */ + fprintf(stderr, "BPF prog initially not loaded, reading total_bw values\n"); + if (fetch_verify_total_bw(test_ctx->baseline_bw, test_ctx->nr_cpus) < 0) { + SCX_ERR("Failed to get stable baseline values"); + free(test_ctx); + return SCX_TEST_FAIL; + } + + /* Load the BPF skeleton */ + test_ctx->skel = minimal__open(); + if (!test_ctx->skel) { + free(test_ctx); + return SCX_TEST_FAIL; + } + + SCX_ENUM_INIT(test_ctx->skel); + if (minimal__load(test_ctx->skel)) { + minimal__destroy(test_ctx->skel); + free(test_ctx); + return SCX_TEST_FAIL; + } + + *ctx = test_ctx; + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct total_bw_ctx *test_ctx = ctx; + struct bpf_link *link; + long loaded_bw[MAX_CPUS]; + long unloaded_bw[MAX_CPUS]; + int i; + + /* Test scenario 2: BPF program loaded */ + link = bpf_map__attach_struct_ops(test_ctx->skel->maps.minimal_ops); + if (!link) { + SCX_ERR("Failed to attach scheduler"); + return SCX_TEST_FAIL; + } + + fprintf(stderr, "BPF program loaded, reading total_bw values\n"); + if (fetch_verify_total_bw(loaded_bw, test_ctx->nr_cpus) < 0) { + SCX_ERR("Failed to get stable values with BPF loaded"); + bpf_link__destroy(link); + return SCX_TEST_FAIL; + } + bpf_link__destroy(link); + + /* Test scenario 3: BPF program unloaded */ + fprintf(stderr, "BPF program unloaded, reading total_bw values\n"); + if (fetch_verify_total_bw(unloaded_bw, test_ctx->nr_cpus) < 0) { + SCX_ERR("Failed to get stable values after BPF unload"); + return SCX_TEST_FAIL; + } + + /* Verify all three scenarios have the same total_bw values */ + for (i = 0; i < test_ctx->nr_cpus; i++) { + if (test_ctx->baseline_bw[i] != loaded_bw[i]) { + SCX_ERR("CPU%d: baseline_bw=%ld != loaded_bw=%ld", + i, test_ctx->baseline_bw[i], loaded_bw[i]); + return SCX_TEST_FAIL; + } + + if (test_ctx->baseline_bw[i] != unloaded_bw[i]) { + SCX_ERR("CPU%d: baseline_bw=%ld != unloaded_bw=%ld", + i, test_ctx->baseline_bw[i], unloaded_bw[i]); + return SCX_TEST_FAIL; + } + } + + fprintf(stderr, "All total_bw values are consistent across all scenarios\n"); + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct total_bw_ctx *test_ctx = ctx; + + if (test_ctx) { + if (test_ctx->skel) + minimal__destroy(test_ctx->skel); + free(test_ctx); + } +} + +struct scx_test total_bw = { + .name = "total_bw", + .description = "Verify total_bw consistency across BPF program states", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&total_bw) -- 2.34.1

2 days, 10 hours

1
0
0 0

[PATCH v6 12/14] selftests/sched_ext: Add test for sched_ext dl_server

by Joel Fernandes

From: Andrea Righi <arighi(a)nvidia.com> Add a selftest to validate the correct behavior of the deadline server for the ext_sched_class. [ Joel: Replaced occurences of CFS in the test with EXT. ] Signed-off-by: Joel Fernandes <joelagnelf(a)nvidia.com> Signed-off-by: Andrea Righi <arighi(a)nvidia.com> --- tools/testing/selftests/sched_ext/Makefile | 1 + .../selftests/sched_ext/rt_stall.bpf.c | 23 ++ tools/testing/selftests/sched_ext/rt_stall.c | 213 ++++++++++++++++++ 3 files changed, 237 insertions(+) create mode 100644 tools/testing/selftests/sched_ext/rt_stall.bpf.c create mode 100644 tools/testing/selftests/sched_ext/rt_stall.c diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index 9d9d6b4c38b0..f0a8cba3a99f 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -182,6 +182,7 @@ auto-test-targets := \ select_cpu_dispatch_bad_dsq \ select_cpu_dispatch_dbl_dsp \ select_cpu_vtime \ + rt_stall \ test_example \ testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets))) diff --git a/tools/testing/selftests/sched_ext/rt_stall.bpf.c b/tools/testing/selftests/sched_ext/rt_stall.bpf.c new file mode 100644 index 000000000000..80086779dd1e --- /dev/null +++ b/tools/testing/selftests/sched_ext/rt_stall.bpf.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A scheduler that verified if RT tasks can stall SCHED_EXT tasks. + * + * Copyright (c) 2025 NVIDIA Corporation. + */ + +#include <scx/common.bpf.h> + +char _license[] SEC("license") = "GPL"; + +UEI_DEFINE(uei); + +void BPF_STRUCT_OPS(rt_stall_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops rt_stall_ops = { + .exit = (void *)rt_stall_exit, + .name = "rt_stall", +}; diff --git a/tools/testing/selftests/sched_ext/rt_stall.c b/tools/testing/selftests/sched_ext/rt_stall.c new file mode 100644 index 000000000000..d4cb545ebfd8 --- /dev/null +++ b/tools/testing/selftests/sched_ext/rt_stall.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2025 NVIDIA Corporation. + */ +#define _GNU_SOURCE +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <sched.h> +#include <sys/prctl.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <time.h> +#include <linux/sched.h> +#include <signal.h> +#include <bpf/bpf.h> +#include <scx/common.h> +#include <sys/wait.h> +#include <unistd.h> +#include "rt_stall.bpf.skel.h" +#include "scx_test.h" +#include "../kselftest.h" + +#define CORE_ID 0 /* CPU to pin tasks to */ +#define RUN_TIME 5 /* How long to run the test in seconds */ + +/* Simple busy-wait function for test tasks */ +static void process_func(void) +{ + while (1) { + /* Busy wait */ + for (volatile unsigned long i = 0; i < 10000000UL; i++); + } +} + +/* Set CPU affinity to a specific core */ +static void set_affinity(int cpu) +{ + cpu_set_t mask; + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + if (sched_setaffinity(0, sizeof(mask), &mask) != 0) { + perror("sched_setaffinity"); + exit(EXIT_FAILURE); + } +} + +/* Set task scheduling policy and priority */ +static void set_sched(int policy, int priority) +{ + struct sched_param param; + + param.sched_priority = priority; + if (sched_setscheduler(0, policy, &param) != 0) { + perror("sched_setscheduler"); + exit(EXIT_FAILURE); + } +} + +/* Get process runtime from /proc/<pid>/stat */ +static float get_process_runtime(int pid) +{ + char path[256]; + FILE *file; + long utime, stime; + int fields; + + snprintf(path, sizeof(path), "/proc/%d/stat", pid); + file = fopen(path, "r"); + if (file == NULL) { + perror("Failed to open stat file"); + return -1; + } + + /* Skip the first 13 fields and read the 14th and 15th */ + fields = fscanf(file, + "%*d %*s %*c %*d %*d %*d %*d %*d %*u %*u %*u %*u %*u %lu %lu", + &utime, &stime); + fclose(file); + + if (fields != 2) { + fprintf(stderr, "Failed to read stat file\n"); + return -1; + } + + /* Calculate the total time spent in the process */ + long total_time = utime + stime; + long ticks_per_second = sysconf(_SC_CLK_TCK); + float runtime_seconds = total_time * 1.0 / ticks_per_second; + + return runtime_seconds; +} + +static enum scx_test_status setup(void **ctx) +{ + struct rt_stall *skel; + + skel = rt_stall__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(rt_stall__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static bool sched_stress_test(void) +{ + float cfs_runtime, rt_runtime; + int cfs_pid, rt_pid; + float expected_min_ratio = 0.04; /* 4% */ + + ksft_print_header(); + ksft_set_plan(1); + + /* Create and set up a EXT task */ + cfs_pid = fork(); + if (cfs_pid == 0) { + set_affinity(CORE_ID); + process_func(); + exit(0); + } else if (cfs_pid < 0) { + perror("fork for EXT task"); + ksft_exit_fail(); + } + + /* Create an RT task */ + rt_pid = fork(); + if (rt_pid == 0) { + set_affinity(CORE_ID); + set_sched(SCHED_FIFO, 50); + process_func(); + exit(0); + } else if (rt_pid < 0) { + perror("fork for RT task"); + ksft_exit_fail(); + } + + /* Let the processes run for the specified time */ + sleep(RUN_TIME); + + /* Get runtime for the EXT task */ + cfs_runtime = get_process_runtime(cfs_pid); + if (cfs_runtime != -1) + ksft_print_msg("Runtime of EXT task (PID %d) is %f seconds\n", cfs_pid, cfs_runtime); + else + ksft_exit_fail_msg("Error getting runtime for EXT task (PID %d)\n", cfs_pid); + + /* Get runtime for the RT task */ + rt_runtime = get_process_runtime(rt_pid); + if (rt_runtime != -1) + ksft_print_msg("Runtime of RT task (PID %d) is %f seconds\n", rt_pid, rt_runtime); + else + ksft_exit_fail_msg("Error getting runtime for RT task (PID %d)\n", rt_pid); + + /* Kill the processes */ + kill(cfs_pid, SIGKILL); + kill(rt_pid, SIGKILL); + waitpid(cfs_pid, NULL, 0); + waitpid(rt_pid, NULL, 0); + + /* Verify that the scx task got enough runtime */ + float actual_ratio = cfs_runtime / (cfs_runtime + rt_runtime); + ksft_print_msg("EXT task got %.2f%% of total runtime\n", actual_ratio * 100); + + if (actual_ratio >= expected_min_ratio) { + ksft_test_result_pass("PASS: EXT task got more than %.2f%% of runtime\n", + expected_min_ratio * 100); + return true; + } else { + ksft_test_result_fail("FAIL: EXT task got less than %.2f%% of runtime\n", + expected_min_ratio * 100); + return false; + } +} + +static enum scx_test_status run(void *ctx) +{ + struct rt_stall *skel = ctx; + struct bpf_link *link; + bool res; + + link = bpf_map__attach_struct_ops(skel->maps.rt_stall_ops); + SCX_FAIL_IF(!link, "Failed to attach scheduler"); + + res = sched_stress_test(); + + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_NONE)); + bpf_link__destroy(link); + + if (!res) + ksft_exit_fail(); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct rt_stall *skel = ctx; + + rt_stall__destroy(skel); +} + +struct scx_test rt_stall = { + .name = "rt_stall", + .description = "Verify that RT tasks cannot stall SCHED_EXT tasks", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&rt_stall) -- 2.34.1

2 days, 10 hours

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror July 2025