diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-08-07 13:14:23 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-08-07 13:14:23 +0000 |
commit | dcfb98cf8931dc6bce38eff8e1c82972e1adf484 (patch) | |
tree | 5395e7ca0effa58c164a86740b6470cbb47fe05e /tools | |
parent | Adding upstream version 6.9.8. (diff) | |
download | linux-dcfb98cf8931dc6bce38eff8e1c82972e1adf484.tar.xz linux-dcfb98cf8931dc6bce38eff8e1c82972e1adf484.zip |
Adding upstream version 6.9.9.upstream/6.9.9
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'tools')
-rw-r--r-- | tools/lib/bpf/bpf_core_read.h | 1 | ||||
-rw-r--r-- | tools/lib/bpf/features.c | 32 | ||||
-rw-r--r-- | tools/power/x86/turbostat/turbostat.c | 35 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c | 34 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/progs/dummy_st_ops_success.c | 15 | ||||
-rw-r--r-- | tools/testing/selftests/kselftest_harness.h | 43 | ||||
-rw-r--r-- | tools/testing/selftests/net/gro.c | 3 | ||||
-rw-r--r-- | tools/testing/selftests/net/ip_local_port_range.c | 2 | ||||
-rw-r--r-- | tools/testing/selftests/net/mptcp/pm_nl_ctl.c | 2 | ||||
-rw-r--r-- | tools/testing/selftests/net/msg_zerocopy.c | 14 | ||||
-rw-r--r-- | tools/testing/selftests/resctrl/cat_test.c | 32 |
11 files changed, 163 insertions, 50 deletions
diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h index 1ce738d916..670726353a 100644 --- a/tools/lib/bpf/bpf_core_read.h +++ b/tools/lib/bpf/bpf_core_read.h @@ -104,6 +104,7 @@ enum bpf_enum_value_kind { case 2: val = *(const unsigned short *)p; break; \ case 4: val = *(const unsigned int *)p; break; \ case 8: val = *(const unsigned long long *)p; break; \ + default: val = 0; break; \ } \ val <<= __CORE_RELO(s, field, LSHIFT_U64); \ if (__CORE_RELO(s, field, SIGNED)) \ diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c index a336786a22..50befe125d 100644 --- a/tools/lib/bpf/features.c +++ b/tools/lib/bpf/features.c @@ -392,11 +392,41 @@ static int probe_uprobe_multi_link(int token_fd) link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); err = -errno; /* close() can clobber errno */ + if (link_fd >= 0 || err != -EBADF) { + if (link_fd >= 0) + close(link_fd); + close(prog_fd); + return 0; + } + + /* Initial multi-uprobe support in kernel didn't handle PID filtering + * correctly (it was doing thread filtering, not process filtering). + * So now we'll detect if PID filtering logic was fixed, and, if not, + * we'll pretend multi-uprobes are not supported, if not. + * Multi-uprobes are used in USDT attachment logic, and we need to be + * conservative here, because multi-uprobe selection happens early at + * load time, while the use of PID filtering is known late at + * attachment time, at which point it's too late to undo multi-uprobe + * selection. + * + * Creating uprobe with pid == -1 for (invalid) '/' binary will fail + * early with -EINVAL on kernels with fixed PID filtering logic; + * otherwise -ESRCH would be returned if passed correct binary path + * (but we'll just get -BADF, of course). + */ + link_opts.uprobe_multi.pid = -1; /* invalid PID */ + link_opts.uprobe_multi.path = "/"; /* invalid path */ + link_opts.uprobe_multi.offsets = &offset; + link_opts.uprobe_multi.cnt = 1; + + link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); + err = -errno; /* close() can clobber errno */ + if (link_fd >= 0) close(link_fd); close(prog_fd); - return link_fd < 0 && err == -EBADF; + return link_fd < 0 && err == -EINVAL; } static int probe_kern_bpf_cookie(int token_fd) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 8071a3ef2a..5d80d193e5 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -1022,6 +1022,7 @@ struct rapl_counter_info_t { /* struct rapl_counter_info_t for each RAPL domain */ struct rapl_counter_info_t *rapl_counter_info_perdomain; +unsigned int rapl_counter_info_perdomain_size; #define RAPL_COUNTER_FLAG_USE_MSR_SUM (1u << 1) @@ -1415,6 +1416,9 @@ struct topo_params { int allowed_cpus; int allowed_cores; int max_cpu_num; + int max_core_id; + int max_package_id; + int max_die_id; int max_node_num; int nodes_per_pkg; int cores_per_node; @@ -3368,15 +3372,18 @@ void write_rapl_counter(struct rapl_counter *rc, struct rapl_counter_info_t *rci rc->scale = rci->scale[idx]; } -int get_rapl_counters(int cpu, int domain, struct core_data *c, struct pkg_data *p) +int get_rapl_counters(int cpu, unsigned int domain, struct core_data *c, struct pkg_data *p) { unsigned long long perf_data[NUM_RAPL_COUNTERS + 1]; - struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[domain]; + struct rapl_counter_info_t *rci; if (debug) fprintf(stderr, "%s: cpu%d domain%d\n", __func__, cpu, domain); assert(rapl_counter_info_perdomain); + assert(domain < rapl_counter_info_perdomain_size); + + rci = &rapl_counter_info_perdomain[domain]; /* * If we have any perf counters to read, read them all now, in bulk @@ -4180,7 +4187,7 @@ void free_fd_rapl_percpu(void) if (!rapl_counter_info_perdomain) return; - const int num_domains = platform->has_per_core_rapl ? topo.num_cores : topo.num_packages; + const int num_domains = rapl_counter_info_perdomain_size; for (int domain_id = 0; domain_id < num_domains; ++domain_id) { if (rapl_counter_info_perdomain[domain_id].fd_perf != -1) @@ -4188,6 +4195,8 @@ void free_fd_rapl_percpu(void) } free(rapl_counter_info_perdomain); + rapl_counter_info_perdomain = NULL; + rapl_counter_info_perdomain_size = 0; } void free_all_buffers(void) @@ -6478,17 +6487,18 @@ void linux_perf_init(void) void rapl_perf_init(void) { - const int num_domains = platform->has_per_core_rapl ? topo.num_cores : topo.num_packages; + const unsigned int num_domains = (platform->has_per_core_rapl ? topo.max_core_id : topo.max_package_id) + 1; bool *domain_visited = calloc(num_domains, sizeof(bool)); rapl_counter_info_perdomain = calloc(num_domains, sizeof(*rapl_counter_info_perdomain)); if (rapl_counter_info_perdomain == NULL) err(-1, "calloc rapl_counter_info_percpu"); + rapl_counter_info_perdomain_size = num_domains; /* * Initialize rapl_counter_info_percpu */ - for (int domain_id = 0; domain_id < num_domains; ++domain_id) { + for (unsigned int domain_id = 0; domain_id < num_domains; ++domain_id) { struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[domain_id]; rci->fd_perf = -1; @@ -6508,7 +6518,7 @@ void rapl_perf_init(void) bool has_counter = 0; double scale; enum rapl_unit unit; - int next_domain; + unsigned int next_domain; memset(domain_visited, 0, num_domains * sizeof(*domain_visited)); @@ -6521,6 +6531,8 @@ void rapl_perf_init(void) next_domain = platform->has_per_core_rapl ? cpus[cpu].physical_core_id : cpus[cpu].physical_package_id; + assert(next_domain < num_domains); + if (domain_visited[next_domain]) continue; @@ -6967,7 +6979,6 @@ void topology_probe(bool startup) int i; int max_core_id = 0; int max_package_id = 0; - int max_die_id = 0; int max_siblings = 0; /* Initialize num_cpus, max_cpu_num */ @@ -7084,8 +7095,8 @@ void topology_probe(bool startup) /* get die information */ cpus[i].die_id = get_die_id(i); - if (cpus[i].die_id > max_die_id) - max_die_id = cpus[i].die_id; + if (cpus[i].die_id > topo.max_die_id) + topo.max_die_id = cpus[i].die_id; /* get numa node information */ cpus[i].physical_node_id = get_physical_node_id(&cpus[i]); @@ -7104,6 +7115,8 @@ void topology_probe(bool startup) if (cpus[i].thread_id == 0) topo.num_cores++; } + topo.max_core_id = max_core_id; + topo.max_package_id = max_package_id; topo.cores_per_node = max_core_id + 1; if (debug > 1) @@ -7111,9 +7124,9 @@ void topology_probe(bool startup) if (!summary_only && topo.cores_per_node > 1) BIC_PRESENT(BIC_Core); - topo.num_die = max_die_id + 1; + topo.num_die = topo.max_die_id + 1; if (debug > 1) - fprintf(outf, "max_die_id %d, sizing for %d die\n", max_die_id, topo.num_die); + fprintf(outf, "max_die_id %d, sizing for %d die\n", topo.max_die_id, topo.num_die); if (!summary_only && topo.num_die > 1) BIC_PRESENT(BIC_Die); diff --git a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c index f43fcb13d2..d3d94596ab 100644 --- a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c +++ b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c @@ -98,7 +98,8 @@ done: static void test_dummy_multiple_args(void) { - __u64 args[5] = {0, -100, 0x8a5f, 'c', 0x1234567887654321ULL}; + struct bpf_dummy_ops_state st = { 7 }; + __u64 args[5] = {(__u64)&st, -100, 0x8a5f, 'c', 0x1234567887654321ULL}; LIBBPF_OPTS(bpf_test_run_opts, attr, .ctx_in = args, .ctx_size_in = sizeof(args), @@ -115,6 +116,7 @@ static void test_dummy_multiple_args(void) fd = bpf_program__fd(skel->progs.test_2); err = bpf_prog_test_run_opts(fd, &attr); ASSERT_OK(err, "test_run"); + args[0] = 7; for (i = 0; i < ARRAY_SIZE(args); i++) { snprintf(name, sizeof(name), "arg %zu", i); ASSERT_EQ(skel->bss->test_2_args[i], args[i], name); @@ -125,7 +127,8 @@ static void test_dummy_multiple_args(void) static void test_dummy_sleepable(void) { - __u64 args[1] = {0}; + struct bpf_dummy_ops_state st; + __u64 args[1] = {(__u64)&st}; LIBBPF_OPTS(bpf_test_run_opts, attr, .ctx_in = args, .ctx_size_in = sizeof(args), @@ -144,6 +147,31 @@ static void test_dummy_sleepable(void) dummy_st_ops_success__destroy(skel); } +/* dummy_st_ops.test_sleepable() parameter is not marked as nullable, + * thus bpf_prog_test_run_opts() below should be rejected as it tries + * to pass NULL for this parameter. + */ +static void test_dummy_sleepable_reject_null(void) +{ + __u64 args[1] = {0}; + LIBBPF_OPTS(bpf_test_run_opts, attr, + .ctx_in = args, + .ctx_size_in = sizeof(args), + ); + struct dummy_st_ops_success *skel; + int fd, err; + + skel = dummy_st_ops_success__open_and_load(); + if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load")) + return; + + fd = bpf_program__fd(skel->progs.test_sleepable); + err = bpf_prog_test_run_opts(fd, &attr); + ASSERT_EQ(err, -EINVAL, "test_run"); + + dummy_st_ops_success__destroy(skel); +} + void test_dummy_st_ops(void) { if (test__start_subtest("dummy_st_ops_attach")) @@ -156,6 +184,8 @@ void test_dummy_st_ops(void) test_dummy_multiple_args(); if (test__start_subtest("dummy_sleepable")) test_dummy_sleepable(); + if (test__start_subtest("dummy_sleepable_reject_null")) + test_dummy_sleepable_reject_null(); RUN_TESTS(dummy_st_ops_fail); } diff --git a/tools/testing/selftests/bpf/progs/dummy_st_ops_success.c b/tools/testing/selftests/bpf/progs/dummy_st_ops_success.c index 1efa746c25..ec0c595d47 100644 --- a/tools/testing/selftests/bpf/progs/dummy_st_ops_success.c +++ b/tools/testing/selftests/bpf/progs/dummy_st_ops_success.c @@ -11,8 +11,17 @@ int BPF_PROG(test_1, struct bpf_dummy_ops_state *state) { int ret; - if (!state) - return 0xf2f3f4f5; + /* Check that 'state' nullable status is detected correctly. + * If 'state' argument would be assumed non-null by verifier + * the code below would be deleted as dead (which it shouldn't). + * Hide it from the compiler behind 'asm' block to avoid + * unnecessary optimizations. + */ + asm volatile ( + "if %[state] != 0 goto +2;" + "r0 = 0xf2f3f4f5;" + "exit;" + ::[state]"p"(state)); ret = state->val; state->val = 0x5a; @@ -25,7 +34,7 @@ SEC("struct_ops/test_2") int BPF_PROG(test_2, struct bpf_dummy_ops_state *state, int a1, unsigned short a2, char a3, unsigned long a4) { - test_2_args[0] = (unsigned long)state; + test_2_args[0] = state->val; test_2_args[1] = a1; test_2_args[2] = a2; test_2_args[3] = a3; diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index b634969cbb..40723a6a08 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -66,8 +66,6 @@ #include <sys/wait.h> #include <unistd.h> #include <setjmp.h> -#include <syscall.h> -#include <linux/sched.h> #include "kselftest.h" @@ -82,17 +80,6 @@ # define TH_LOG_ENABLED 1 #endif -/* Wait for the child process to end but without sharing memory mapping. */ -static inline pid_t clone3_vfork(void) -{ - struct clone_args args = { - .flags = CLONE_VFORK, - .exit_signal = SIGCHLD, - }; - - return syscall(__NR_clone3, &args, sizeof(args)); -} - /** * TH_LOG() * @@ -437,7 +424,7 @@ static inline pid_t clone3_vfork(void) } \ if (setjmp(_metadata->env) == 0) { \ /* _metadata and potentially self are shared with all forks. */ \ - child = clone3_vfork(); \ + child = fork(); \ if (child == 0) { \ fixture_name##_setup(_metadata, self, variant->data); \ /* Let setup failure terminate early. */ \ @@ -1016,7 +1003,14 @@ void __wait_for_test(struct __test_metadata *t) .sa_flags = SA_SIGINFO, }; struct sigaction saved_action; - int status; + /* + * Sets status so that WIFEXITED(status) returns true and + * WEXITSTATUS(status) returns KSFT_FAIL. This safe default value + * should never be evaluated because of the waitpid(2) check and + * SIGALRM handling. + */ + int status = KSFT_FAIL << 8; + int child; if (sigaction(SIGALRM, &action, &saved_action)) { t->exit_code = KSFT_FAIL; @@ -1028,7 +1022,15 @@ void __wait_for_test(struct __test_metadata *t) __active_test = t; t->timed_out = false; alarm(t->timeout); - waitpid(t->pid, &status, 0); + child = waitpid(t->pid, &status, 0); + if (child == -1 && errno != EINTR) { + t->exit_code = KSFT_FAIL; + fprintf(TH_LOG_STREAM, + "# %s: Failed to wait for PID %d (errno: %d)\n", + t->name, t->pid, errno); + return; + } + alarm(0); if (sigaction(SIGALRM, &saved_action, NULL)) { t->exit_code = KSFT_FAIL; @@ -1083,6 +1085,7 @@ void __wait_for_test(struct __test_metadata *t) WTERMSIG(status)); } } else { + t->exit_code = KSFT_FAIL; fprintf(TH_LOG_STREAM, "# %s: Test ended in some other way [%u]\n", t->name, @@ -1218,6 +1221,7 @@ void __run_test(struct __fixture_metadata *f, struct __test_xfail *xfail; char test_name[1024]; const char *diagnostic; + int child; /* reset test struct */ t->exit_code = KSFT_PASS; @@ -1236,15 +1240,16 @@ void __run_test(struct __fixture_metadata *f, fflush(stdout); fflush(stderr); - t->pid = clone3_vfork(); - if (t->pid < 0) { + child = fork(); + if (child < 0) { ksft_print_msg("ERROR SPAWNING TEST CHILD\n"); t->exit_code = KSFT_FAIL; - } else if (t->pid == 0) { + } else if (child == 0) { setpgrp(); t->fn(t, variant); _exit(t->exit_code); } else { + t->pid = child; __wait_for_test(t); } ksft_print_msg(" %4s %s\n", diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/net/gro.c index 353e1e867f..6038b96ece 100644 --- a/tools/testing/selftests/net/gro.c +++ b/tools/testing/selftests/net/gro.c @@ -119,6 +119,9 @@ static void setup_sock_filter(int fd) next_off = offsetof(struct ipv6hdr, nexthdr); ipproto_off = ETH_HLEN + next_off; + /* Overridden later if exthdrs are used: */ + opt_ipproto_off = ipproto_off; + if (strcmp(testname, "ip") == 0) { if (proto == PF_INET) optlen = sizeof(struct ip_timestamp); diff --git a/tools/testing/selftests/net/ip_local_port_range.c b/tools/testing/selftests/net/ip_local_port_range.c index 193b82745f..29451d2244 100644 --- a/tools/testing/selftests/net/ip_local_port_range.c +++ b/tools/testing/selftests/net/ip_local_port_range.c @@ -359,7 +359,7 @@ TEST_F(ip_local_port_range, late_bind) struct sockaddr_in v4; struct sockaddr_in6 v6; } addr; - socklen_t addr_len; + socklen_t addr_len = 0; const int one = 1; int fd, err; __u32 range; diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c index 7426a2cbd4..7ad5a59adf 100644 --- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -1276,7 +1276,7 @@ int add_listener(int argc, char *argv[]) struct sockaddr_storage addr; struct sockaddr_in6 *a6; struct sockaddr_in *a4; - u_int16_t family; + u_int16_t family = AF_UNSPEC; int enable = 1; int sock; int err; diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index bdc03a2097..7ea5fb28c9 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -85,6 +85,7 @@ static bool cfg_rx; static int cfg_runtime_ms = 4200; static int cfg_verbose; static int cfg_waittime_ms = 500; +static int cfg_notification_limit = 32; static bool cfg_zerocopy; static socklen_t cfg_alen; @@ -95,6 +96,7 @@ static char payload[IP_MAXPACKET]; static long packets, bytes, completions, expected_completions; static int zerocopied = -1; static uint32_t next_completion; +static uint32_t sends_since_notify; static unsigned long gettimeofday_ms(void) { @@ -208,6 +210,7 @@ static bool do_sendmsg(int fd, struct msghdr *msg, bool do_zerocopy, int domain) error(1, errno, "send"); if (cfg_verbose && ret != len) fprintf(stderr, "send: ret=%u != %u\n", ret, len); + sends_since_notify++; if (len) { packets++; @@ -435,7 +438,7 @@ static bool do_recv_completion(int fd, int domain) /* Detect notification gaps. These should not happen often, if at all. * Gaps can occur due to drops, reordering and retransmissions. */ - if (lo != next_completion) + if (cfg_verbose && lo != next_completion) fprintf(stderr, "gap: %u..%u does not append to %u\n", lo, hi, next_completion); next_completion = hi + 1; @@ -460,6 +463,7 @@ static bool do_recv_completion(int fd, int domain) static void do_recv_completions(int fd, int domain) { while (do_recv_completion(fd, domain)) {} + sends_since_notify = 0; } /* Wait for all remaining completions on the errqueue */ @@ -549,6 +553,9 @@ static void do_tx(int domain, int type, int protocol) else do_sendmsg(fd, &msg, cfg_zerocopy, domain); + if (cfg_zerocopy && sends_since_notify >= cfg_notification_limit) + do_recv_completions(fd, domain); + while (!do_poll(fd, POLLOUT)) { if (cfg_zerocopy) do_recv_completions(fd, domain); @@ -708,7 +715,7 @@ static void parse_opts(int argc, char **argv) cfg_payload_len = max_payload_len; - while ((c = getopt(argc, argv, "46c:C:D:i:mp:rs:S:t:vz")) != -1) { + while ((c = getopt(argc, argv, "46c:C:D:i:l:mp:rs:S:t:vz")) != -1) { switch (c) { case '4': if (cfg_family != PF_UNSPEC) @@ -736,6 +743,9 @@ static void parse_opts(int argc, char **argv) if (cfg_ifindex == 0) error(1, errno, "invalid iface: %s", optarg); break; + case 'l': + cfg_notification_limit = strtoul(optarg, NULL, 0); + break; case 'm': cfg_cork_mixed = true; break; diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index 4cb991be8e..178a41d4bb 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -294,11 +294,30 @@ out: return ret; } +static bool arch_supports_noncont_cat(const struct resctrl_test *test) +{ + unsigned int eax, ebx, ecx, edx; + + /* AMD always supports non-contiguous CBM. */ + if (get_vendor() == ARCH_AMD) + return true; + + /* Intel support for non-contiguous CBM needs to be discovered. */ + if (!strcmp(test->resource, "L3")) + __cpuid_count(0x10, 1, eax, ebx, ecx, edx); + else if (!strcmp(test->resource, "L2")) + __cpuid_count(0x10, 2, eax, ebx, ecx, edx); + else + return false; + + return ((ecx >> 3) & 1); +} + static int noncont_cat_run_test(const struct resctrl_test *test, const struct user_params *uparams) { unsigned long full_cache_mask, cont_mask, noncont_mask; - unsigned int eax, ebx, ecx, edx, sparse_masks; + unsigned int sparse_masks; int bit_center, ret; char schemata[64]; @@ -307,15 +326,8 @@ static int noncont_cat_run_test(const struct resctrl_test *test, if (ret) return ret; - if (!strcmp(test->resource, "L3")) - __cpuid_count(0x10, 1, eax, ebx, ecx, edx); - else if (!strcmp(test->resource, "L2")) - __cpuid_count(0x10, 2, eax, ebx, ecx, edx); - else - return -EINVAL; - - if (sparse_masks != ((ecx >> 3) & 1)) { - ksft_print_msg("CPUID output doesn't match 'sparse_masks' file content!\n"); + if (arch_supports_noncont_cat(test) != sparse_masks) { + ksft_print_msg("Hardware and kernel differ on non-contiguous CBM support!\n"); return 1; } |